linux/net/ipv4/inet_fragment.c
Linus Torvalds 5bbcc0f595 Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
 "Highlights:

   1) Maintain the TCP retransmit queue using an rbtree, with 1GB
      windows at 100Gb this really has become necessary. From Eric
      Dumazet.

   2) Multi-program support for cgroup+bpf, from Alexei Starovoitov.

   3) Perform broadcast flooding in hardware in mv88e6xxx, from Andrew
      Lunn.

   4) Add meter action support to openvswitch, from Andy Zhou.

   5) Add a data meta pointer for BPF accessible packets, from Daniel
      Borkmann.

   6) Namespace-ify almost all TCP sysctl knobs, from Eric Dumazet.

   7) Turn on Broadcom Tags in b53 driver, from Florian Fainelli.

   8) More work to move the RTNL mutex down, from Florian Westphal.

   9) Add 'bpftool' utility, to help with bpf program introspection.
      From Jakub Kicinski.

  10) Add new 'cpumap' type for XDP_REDIRECT action, from Jesper
      Dangaard Brouer.

  11) Support 'blocks' of transformations in the packet scheduler which
      can span multiple network devices, from Jiri Pirko.

  12) TC flower offload support in cxgb4, from Kumar Sanghvi.

  13) Priority based stream scheduler for SCTP, from Marcelo Ricardo
      Leitner.

  14) Thunderbolt networking driver, from Amir Levy and Mika Westerberg.

  15) Add RED qdisc offloadability, and use it in mlxsw driver. From
      Nogah Frankel.

  16) eBPF based device controller for cgroup v2, from Roman Gushchin.

  17) Add some fundamental tracepoints for TCP, from Song Liu.

  18) Remove garbage collection from ipv6 route layer, this is a
      significant accomplishment. From Wei Wang.

  19) Add multicast route offload support to mlxsw, from Yotam Gigi"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (2177 commits)
  tcp: highest_sack fix
  geneve: fix fill_info when link down
  bpf: fix lockdep splat
  net: cdc_ncm: GetNtbFormat endian fix
  openvswitch: meter: fix NULL pointer dereference in ovs_meter_cmd_reply_start
  netem: remove unnecessary 64 bit modulus
  netem: use 64 bit divide by rate
  tcp: Namespace-ify sysctl_tcp_default_congestion_control
  net: Protect iterations over net::fib_notifier_ops in fib_seq_sum()
  ipv6: set all.accept_dad to 0 by default
  uapi: fix linux/tls.h userspace compilation error
  usbnet: ipheth: prevent TX queue timeouts when device not ready
  vhost_net: conditionally enable tx polling
  uapi: fix linux/rxrpc.h userspace compilation errors
  net: stmmac: fix LPI transitioning for dwmac4
  atm: horizon: Fix irq release error
  net-sysfs: trigger netlink notification on ifalias change via sysfs
  openvswitch: Using kfree_rcu() to simplify the code
  openvswitch: Make local function ovs_nsh_key_attr_size() static
  openvswitch: Fix return value check in ovs_meter_cmd_features()
  ...
2017-11-15 11:56:19 -08:00

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(&fq->timer);
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 = READ_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);
timer_setup(&q->timer, f->frag_expire, 0);
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);