2
0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-23 12:43:55 +08:00
linux-next/net/ipv4/inet_fragment.c
Jesper Dangaard Brouer fb452a1aa3 Revert "net: use lib/percpu_counter API for fragmentation mem accounting"
This reverts commit 6d7b857d54.

There is a bug in fragmentation codes use of the percpu_counter API,
that can cause issues on systems with many CPUs.

The frag_mem_limit() just reads the global counter (fbc->count),
without considering other CPUs can have upto batch size (130K) that
haven't been subtracted yet.  Due to the 3MBytes lower thresh limit,
this become dangerous at >=24 CPUs (3*1024*1024/130000=24).

The correct API usage would be to use __percpu_counter_compare() which
does the right thing, and takes into account the number of (online)
CPUs and batch size, to account for this and call __percpu_counter_sum()
when needed.

We choose to revert the use of the lib/percpu_counter API for frag
memory accounting for several reasons:

1) On systems with CPUs > 24, the heavier fully locked
   __percpu_counter_sum() is always invoked, which will be more
   expensive than the atomic_t that is reverted to.

Given systems with more than 24 CPUs are becoming common this doesn't
seem like a good option.  To mitigate this, the batch size could be
decreased and thresh be increased.

2) The add_frag_mem_limit+sub_frag_mem_limit pairs happen on the RX
   CPU, before SKBs are pushed into sockets on remote CPUs.  Given
   NICs can only hash on L2 part of the IP-header, the NIC-RXq's will
   likely be limited.  Thus, a fair chance that atomic add+dec happen
   on the same CPU.

Revert note that commit 1d6119baf0 ("net: fix percpu memory leaks")
removed init_frag_mem_limit() and instead use inet_frags_init_net().
After this revert, inet_frags_uninit_net() becomes empty.

Fixes: 6d7b857d54 ("net: use lib/percpu_counter API for fragmentation mem accounting")
Fixes: 1d6119baf0 ("net: fix percpu memory leaks")
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Acked-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>
2017-09-03 11:01:05 -07:00

438 lines
10 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
*/
#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>
#define INETFRAGS_EVICT_BUCKETS 128
#define INETFRAGS_EVICT_MAX 512
/* don't rebuild inetfrag table with new secret more often than this */
#define INETFRAGS_MIN_REBUILD_INTERVAL (5 * HZ)
/* 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);
static unsigned int
inet_frag_hashfn(const struct inet_frags *f, const struct inet_frag_queue *q)
{
return f->hashfn(q) & (INETFRAGS_HASHSZ - 1);
}
static bool inet_frag_may_rebuild(struct inet_frags *f)
{
return time_after(jiffies,
f->last_rebuild_jiffies + INETFRAGS_MIN_REBUILD_INTERVAL);
}
static void inet_frag_secret_rebuild(struct inet_frags *f)
{
int i;
write_seqlock_bh(&f->rnd_seqlock);
if (!inet_frag_may_rebuild(f))
goto out;
get_random_bytes(&f->rnd, sizeof(u32));
for (i = 0; i < INETFRAGS_HASHSZ; i++) {
struct inet_frag_bucket *hb;
struct inet_frag_queue *q;
struct hlist_node *n;
hb = &f->hash[i];
spin_lock(&hb->chain_lock);
hlist_for_each_entry_safe(q, n, &hb->chain, list) {
unsigned int hval = inet_frag_hashfn(f, q);
if (hval != i) {
struct inet_frag_bucket *hb_dest;
hlist_del(&q->list);
/* Relink to new hash chain. */
hb_dest = &f->hash[hval];
/* This is the only place where we take
* another chain_lock while already holding
* one. As this will not run concurrently,
* we cannot deadlock on hb_dest lock below, if its
* already locked it will be released soon since
* other caller cannot be waiting for hb lock
* that we've taken above.
*/
spin_lock_nested(&hb_dest->chain_lock,
SINGLE_DEPTH_NESTING);
hlist_add_head(&q->list, &hb_dest->chain);
spin_unlock(&hb_dest->chain_lock);
}
}
spin_unlock(&hb->chain_lock);
}
f->rebuild = false;
f->last_rebuild_jiffies = jiffies;
out:
write_sequnlock_bh(&f->rnd_seqlock);
}
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;
hlist_add_head(&fq->list_evictor, &expired);
++evicted;
}
spin_unlock(&hb->chain_lock);
hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
f->frag_expire((unsigned long) fq);
return evicted;
}
static void inet_frag_worker(struct work_struct *work)
{
unsigned int budget = INETFRAGS_EVICT_BUCKETS;
unsigned int i, evicted = 0;
struct inet_frags *f;
f = container_of(work, struct inet_frags, frags_work);
BUILD_BUG_ON(INETFRAGS_EVICT_BUCKETS >= INETFRAGS_HASHSZ);
local_bh_disable();
for (i = ACCESS_ONCE(f->next_bucket); budget; --budget) {
evicted += inet_evict_bucket(f, &f->hash[i]);
i = (i + 1) & (INETFRAGS_HASHSZ - 1);
if (evicted > INETFRAGS_EVICT_MAX)
break;
}
f->next_bucket = i;
local_bh_enable();
if (f->rebuild && inet_frag_may_rebuild(f))
inet_frag_secret_rebuild(f);
}
static void inet_frag_schedule_worker(struct inet_frags *f)
{
if (unlikely(!work_pending(&f->frags_work)))
schedule_work(&f->frags_work);
}
int inet_frags_init(struct inet_frags *f)
{
int i;
INIT_WORK(&f->frags_work, inet_frag_worker);
for (i = 0; i < INETFRAGS_HASHSZ; i++) {
struct inet_frag_bucket *hb = &f->hash[i];
spin_lock_init(&hb->chain_lock);
INIT_HLIST_HEAD(&hb->chain);
}
seqlock_init(&f->rnd_seqlock);
f->last_rebuild_jiffies = 0;
f->frags_cachep = kmem_cache_create(f->frags_cache_name, f->qsize, 0, 0,
NULL);
if (!f->frags_cachep)
return -ENOMEM;
return 0;
}
EXPORT_SYMBOL(inet_frags_init);
void inet_frags_fini(struct inet_frags *f)
{
cancel_work_sync(&f->frags_work);
kmem_cache_destroy(f->frags_cachep);
}
EXPORT_SYMBOL(inet_frags_fini);
void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f)
{
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) ||
sum_frag_mem_limit(nf))
goto evict_again;
}
EXPORT_SYMBOL(inet_frags_exit_net);
static struct inet_frag_bucket *
get_frag_bucket_locked(struct inet_frag_queue *fq, struct inet_frags *f)
__acquires(hb->chain_lock)
{
struct inet_frag_bucket *hb;
unsigned int seq, hash;
restart:
seq = read_seqbegin(&f->rnd_seqlock);
hash = inet_frag_hashfn(f, fq);
hb = &f->hash[hash];
spin_lock(&hb->chain_lock);
if (read_seqretry(&f->rnd_seqlock, seq)) {
spin_unlock(&hb->chain_lock);
goto restart;
}
return hb;
}
static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
{
struct inet_frag_bucket *hb;
hb = get_frag_bucket_locked(fq, f);
hlist_del(&fq->list);
fq->flags |= INET_FRAG_COMPLETE;
spin_unlock(&hb->chain_lock);
}
void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
{
if (del_timer(&fq->timer))
refcount_dec(&fq->refcnt);
if (!(fq->flags & INET_FRAG_COMPLETE)) {
fq_unlink(fq, f);
refcount_dec(&fq->refcnt);
}
}
EXPORT_SYMBOL(inet_frag_kill);
void inet_frag_destroy(struct inet_frag_queue *q, struct inet_frags *f)
{
struct sk_buff *fp;
struct netns_frags *nf;
unsigned int sum, sum_truesize = 0;
WARN_ON(!(q->flags & INET_FRAG_COMPLETE));
WARN_ON(del_timer(&q->timer) != 0);
/* Release all fragment data. */
fp = q->fragments;
nf = q->net;
while (fp) {
struct sk_buff *xp = fp->next;
sum_truesize += fp->truesize;
kfree_skb(fp);
fp = xp;
}
sum = sum_truesize + f->qsize;
if (f->destructor)
f->destructor(q);
kmem_cache_free(f->frags_cachep, q);
sub_frag_mem_limit(nf, sum);
}
EXPORT_SYMBOL(inet_frag_destroy);
static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
struct inet_frag_queue *qp_in,
struct inet_frags *f,
void *arg)
{
struct inet_frag_bucket *hb = get_frag_bucket_locked(qp_in, f);
struct inet_frag_queue *qp;
#ifdef CONFIG_SMP
/* With SMP race we have to recheck hash table, because
* such entry could have been created on other cpu before
* we acquired hash bucket lock.
*/
hlist_for_each_entry(qp, &hb->chain, list) {
if (qp->net == nf && f->match(qp, arg)) {
refcount_inc(&qp->refcnt);
spin_unlock(&hb->chain_lock);
qp_in->flags |= INET_FRAG_COMPLETE;
inet_frag_put(qp_in, f);
return qp;
}
}
#endif
qp = qp_in;
if (!mod_timer(&qp->timer, jiffies + nf->timeout))
refcount_inc(&qp->refcnt);
refcount_inc(&qp->refcnt);
hlist_add_head(&qp->list, &hb->chain);
spin_unlock(&hb->chain_lock);
return qp;
}
static struct inet_frag_queue *inet_frag_alloc(struct netns_frags *nf,
struct inet_frags *f,
void *arg)
{
struct inet_frag_queue *q;
if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) {
inet_frag_schedule_worker(f);
return NULL;
}
q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC);
if (!q)
return NULL;
q->net = nf;
f->constructor(q, arg);
add_frag_mem_limit(nf, f->qsize);
setup_timer(&q->timer, f->frag_expire, (unsigned long)q);
spin_lock_init(&q->lock);
refcount_set(&q->refcnt, 1);
return q;
}
static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf,
struct inet_frags *f,
void *arg)
{
struct inet_frag_queue *q;
q = inet_frag_alloc(nf, f, arg);
if (!q)
return NULL;
return inet_frag_intern(nf, q, f, arg);
}
struct inet_frag_queue *inet_frag_find(struct netns_frags *nf,
struct inet_frags *f, void *key,
unsigned int hash)
{
struct inet_frag_bucket *hb;
struct inet_frag_queue *q;
int depth = 0;
if (frag_mem_limit(nf) > nf->low_thresh)
inet_frag_schedule_worker(f);
hash &= (INETFRAGS_HASHSZ - 1);
hb = &f->hash[hash];
spin_lock(&hb->chain_lock);
hlist_for_each_entry(q, &hb->chain, list) {
if (q->net == nf && f->match(q, key)) {
refcount_inc(&q->refcnt);
spin_unlock(&hb->chain_lock);
return q;
}
depth++;
}
spin_unlock(&hb->chain_lock);
if (depth <= INETFRAGS_MAXDEPTH)
return inet_frag_create(nf, f, key);
if (inet_frag_may_rebuild(f)) {
if (!f->rebuild)
f->rebuild = true;
inet_frag_schedule_worker(f);
}
return ERR_PTR(-ENOBUFS);
}
EXPORT_SYMBOL(inet_frag_find);
void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q,
const char *prefix)
{
static const char msg[] = "inet_frag_find: Fragment hash bucket"
" list length grew over limit " __stringify(INETFRAGS_MAXDEPTH)
". Dropping fragment.\n";
if (PTR_ERR(q) == -ENOBUFS)
net_dbg_ratelimited("%s%s", prefix, msg);
}
EXPORT_SYMBOL(inet_frag_maybe_warn_overflow);