4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 787bea7748a76130566f881c2342a0be4127d182 upstream.

We will soon initialize one rhashtable per struct netns_frags in inet_frags_init_net().

This patch changes the return value to eventually propagate an error.

Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/inet_frag.h | 3 ++- net/ieee802154/6lowpan/reassembly.c | 11 ++++++++--- net/ipv4/ip_fragment.c | 12 +++++++++--- net/ipv6/netfilter/nf_conntrack_reasm.c | 12 +++++++++--- net/ipv6/reassembly.c | 11 +++++++++-- 5 files changed, 37 insertions(+), 12 deletions(-)

--- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -103,9 +103,10 @@ struct inet_frags { int inet_frags_init(struct inet_frags *); void inet_frags_fini(struct inet_frags *);

-static inline void inet_frags_init_net(struct netns_frags *nf) +static inline int inet_frags_init_net(struct netns_frags *nf) { atomic_set(&nf->mem, 0); + return 0; } void inet_frags_exit_net(struct netns_frags *nf, struct inet_frags *f);

--- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -580,14 +580,19 @@ static int __net_init lowpan_frags_init_ { struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); + int res;

ieee802154_lowpan->frags.high_thresh = IPV6_FRAG_HIGH_THRESH; ieee802154_lowpan->frags.low_thresh = IPV6_FRAG_LOW_THRESH; ieee802154_lowpan->frags.timeout = IPV6_FRAG_TIMEOUT;

- inet_frags_init_net(&ieee802154_lowpan->frags); - - return lowpan_frags_ns_sysctl_register(net); + res = inet_frags_init_net(&ieee802154_lowpan->frags); + if (res < 0) + return res; + res = lowpan_frags_ns_sysctl_register(net); + if (res < 0) + inet_frags_exit_net(&ieee802154_lowpan->frags, &lowpan_frags); + return res; }

static void __net_exit lowpan_frags_exit_net(struct net *net) --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -853,6 +853,8 @@ static void __init ip4_frags_ctl_registe

static int __net_init ipv4_frags_init_net(struct net *net) { + int res; + /* Fragment cache limits. * * The fragment memory accounting code, (tries to) account for @@ -876,9 +878,13 @@ static int __net_init ipv4_frags_init_ne */ net->ipv4.frags.timeout = IP_FRAG_TIME;

- inet_frags_init_net(&net->ipv4.frags); - - return ip4_frags_ns_ctl_register(net); + res = inet_frags_init_net(&net->ipv4.frags); + if (res < 0) + return res; + res = ip4_frags_ns_ctl_register(net); + if (res < 0) + inet_frags_exit_net(&net->ipv4.frags, &ip4_frags); + return res; }

static void __net_exit ipv4_frags_exit_net(struct net *net) --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -650,12 +650,18 @@ EXPORT_SYMBOL_GPL(nf_ct_frag6_consume_or

static int nf_ct_net_init(struct net *net) { + int res; + net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH; net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT; - inet_frags_init_net(&net->nf_frag.frags); - - return nf_ct_frag6_sysctl_register(net); + res = inet_frags_init_net(&net->nf_frag.frags); + if (res < 0) + return res; + res = nf_ct_frag6_sysctl_register(net); + if (res < 0) + inet_frags_exit_net(&net->nf_frag.frags, &nf_frags); + return res; }

static void nf_ct_net_exit(struct net *net) --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -708,13 +708,20 @@ static void ip6_frags_sysctl_unregister(

static int __net_init ipv6_frags_init_net(struct net *net) { + int res; + net->ipv6.frags.high_thresh = IPV6_FRAG_HIGH_THRESH; net->ipv6.frags.low_thresh = IPV6_FRAG_LOW_THRESH; net->ipv6.frags.timeout = IPV6_FRAG_TIMEOUT;

- inet_frags_init_net(&net->ipv6.frags); + res = inet_frags_init_net(&net->ipv6.frags); + if (res < 0) + return res;

- return ip6_frags_ns_sysctl_register(net); + res = ip6_frags_ns_sysctl_register(net); + if (res < 0) + inet_frags_exit_net(&net->ipv6.frags, &ip6_frags); + return res; }

static void __net_exit ipv6_frags_exit_net(struct net *net)

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 483a6e4fa055123142d8956866fe2aa9c98d546d upstream.

We need to call inet_frags_init() before register_pernet_subsys(), as a prereq for following patch ("inet: frags: use rhashtables for reassembly units")

Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/ip_fragment.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -902,8 +902,6 @@ static struct pernet_operations ip4_frag

void __init ipfrag_init(void) { - ip4_frags_ctl_register(); - register_pernet_subsys(&ip4_frags_ops); ip4_frags.hashfn = ip4_hashfn; ip4_frags.constructor = ip4_frag_init; ip4_frags.destructor = ip4_frag_free; @@ -914,4 +912,6 @@ void __init ipfrag_init(void) ip4_frags.frags_cache_name = ip_frag_cache_name; if (inet_frags_init(&ip4_frags)) panic("IP: failed to allocate ip4_frags cache\n"); + ip4_frags_ctl_register(); + register_pernet_subsys(&ip4_frags_ops); }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 807f1844df4ac23594268fa9f41902d0549e92aa upstream.

We want to call lowpan_net_frag_init() earlier. Similar to commit "inet: frags: refactor ipv6_frag_init()"

This is a prereq to "inet: frags: use rhashtables for reassembly units"

Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ieee802154/6lowpan/reassembly.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-)

--- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -614,14 +614,6 @@ int __init lowpan_net_frag_init(void) { int ret;

- ret = lowpan_frags_sysctl_register(); - if (ret) - return ret; - - ret = register_pernet_subsys(&lowpan_frags_ops); - if (ret) - goto err_pernet; - lowpan_frags.hashfn = lowpan_hashfn; lowpan_frags.constructor = lowpan_frag_init; lowpan_frags.destructor = NULL; @@ -632,11 +624,21 @@ int __init lowpan_net_frag_init(void) lowpan_frags.frags_cache_name = lowpan_frags_cache_name; ret = inet_frags_init(&lowpan_frags); if (ret) - goto err_pernet; + goto out; + + ret = lowpan_frags_sysctl_register(); + if (ret) + goto err_sysctl;

+ ret = register_pernet_subsys(&lowpan_frags_ops); + if (ret) + goto err_pernet; +out: return ret; err_pernet: lowpan_frags_sysctl_unregister(); +err_sysctl: + inet_frags_fini(&lowpan_frags); return ret; }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Ben Hutchings ben.hutchings@codethink.co.uk

Extracted from commit ca26893f05e8 "rhashtable: Add rhlist interface".

Cc: Herbert Xu herbert@gondor.apana.org.au Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/rhashtable.h | 69 +++++++++++++++++++++++++++++++++------------ 1 file changed, 52 insertions(+), 17 deletions(-)

--- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -515,18 +515,8 @@ static inline int rhashtable_compare(str return memcmp(ptr + ht->p.key_offset, arg->key, ht->p.key_len); }

-/** - * rhashtable_lookup_fast - search hash table, inlined version - * @ht: hash table - * @key: the pointer to the key - * @params: hash table parameters - * - * Computes the hash value for the key and traverses the bucket chain looking - * for a entry with an identical key. The first matching entry is returned. - * - * Returns the first entry on which the compare function returned true. - */ -static inline void *rhashtable_lookup_fast( +/* Internal function, do not use. */ +static inline struct rhash_head *__rhashtable_lookup( struct rhashtable *ht, const void *key, const struct rhashtable_params params) { @@ -538,8 +528,6 @@ static inline void *rhashtable_lookup_fa struct rhash_head *he; unsigned int hash;

- rcu_read_lock(); - tbl = rht_dereference_rcu(ht->tbl, ht); restart: hash = rht_key_hashfn(ht, tbl, key, params); @@ -548,8 +536,7 @@ restart: params.obj_cmpfn(&arg, rht_obj(ht, he)) : rhashtable_compare(&arg, rht_obj(ht, he))) continue; - rcu_read_unlock(); - return rht_obj(ht, he); + return he; }

/* Ensure we see any new tables. */ @@ -558,11 +545,59 @@ restart: tbl = rht_dereference_rcu(tbl->future_tbl, ht); if (unlikely(tbl)) goto restart; - rcu_read_unlock();

return NULL; }

+/** + * rhashtable_lookup - search hash table + * @ht: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. The first matching entry is returned. + * + * This must only be called under the RCU read lock. + * + * Returns the first entry on which the compare function returned true. + */ +static inline void *rhashtable_lookup( + struct rhashtable *ht, const void *key, + const struct rhashtable_params params) +{ + struct rhash_head *he = __rhashtable_lookup(ht, key, params); + + return he ? rht_obj(ht, he) : NULL; +} + +/** + * rhashtable_lookup_fast - search hash table, without RCU read lock + * @ht: hash table + * @key: the pointer to the key + * @params: hash table parameters + * + * Computes the hash value for the key and traverses the bucket chain looking + * for a entry with an identical key. The first matching entry is returned. + * + * Only use this function when you have other mechanisms guaranteeing + * that the object won't go away after the RCU read lock is released. + * + * Returns the first entry on which the compare function returned true. + */ +static inline void *rhashtable_lookup_fast( + struct rhashtable *ht, const void *key, + const struct rhashtable_params params) +{ + void *obj; + + rcu_read_lock(); + obj = rhashtable_lookup(ht, key, params); + rcu_read_unlock(); + + return obj; +} + /* Internal function, please use rhashtable_insert_fast() instead. This * function returns the existing element already in hashes in there is a clash, * otherwise it returns an error via ERR_PTR().

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 648700f76b03b7e8149d13cc2bdb3355035258a9 upstream.

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 [bwh: Backported to 4.4: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/networking/ip-sysctl.txt | 7 include/net/inet_frag.h | 81 +++---- include/net/ipv6.h | 16 - net/ieee802154/6lowpan/6lowpan_i.h | 26 -- net/ieee802154/6lowpan/reassembly.c | 91 +++----- net/ipv4/inet_fragment.c | 349 ++++++-------------------------- net/ipv4/ip_fragment.c | 112 ++++------ net/ipv6/netfilter/nf_conntrack_reasm.c | 51 +--- net/ipv6/reassembly.c | 110 ++++------ 9 files changed, 267 insertions(+), 576 deletions(-)

--- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -113,13 +113,10 @@ min_adv_mss - INTEGER IP Fragmentation:

ipfrag_high_thresh - INTEGER - Maximum memory used to reassemble IP fragments. When - ipfrag_high_thresh bytes of memory is allocated for this purpose, - the fragment handler will toss packets until ipfrag_low_thresh - is reached. This also serves as a maximum limit to namespaces - different from the initial one. + Maximum memory used to reassemble IP fragments.

ipfrag_low_thresh - INTEGER + (Obsolete since linux-4.17) Maximum memory used to reassemble IP fragments before the kernel begins to remove incomplete fragment queues to free up resources. The kernel still accepts new fragments for defragmentation. --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -1,7 +1,11 @@ #ifndef __NET_FRAG_H__ #define __NET_FRAG_H__

+#include <linux/rhashtable.h> + struct netns_frags { + struct rhashtable rhashtable ____cacheline_aligned_in_smp; + /* Keep atomic mem on separate cachelines in structs that include it */ atomic_t mem ____cacheline_aligned_in_smp; /* sysctls */ @@ -24,12 +28,30 @@ enum { INET_FRAG_COMPLETE = BIT(2), };

+struct frag_v4_compare_key { + __be32 saddr; + __be32 daddr; + u32 user; + u32 vif; + __be16 id; + u16 protocol; +}; + +struct frag_v6_compare_key { + struct in6_addr saddr; + struct in6_addr daddr; + u32 user; + __be32 id; + u32 iif; +}; + /** * struct inet_frag_queue - fragment queue * - * @lock: spinlock protecting the queue + * @node: rhash node + * @key: keys identifying this frag. * @timer: queue expiration timer - * @list: hash bucket list + * @lock: spinlock protecting this frag * @refcnt: reference count of the queue * @fragments: received fragments head * @fragments_tail: received fragments tail @@ -39,12 +61,16 @@ enum { * @flags: fragment queue flags * @max_size: maximum received fragment size * @net: namespace that this frag belongs to - * @list_evictor: list of queues to forcefully evict (e.g. due to low memory) + * @rcu: rcu head for freeing deferall */ struct inet_frag_queue { - spinlock_t lock; + struct rhash_head node; + union { + struct frag_v4_compare_key v4; + struct frag_v6_compare_key v6; + } key; struct timer_list timer; - struct hlist_node list; + spinlock_t lock; atomic_t refcnt; struct sk_buff *fragments; struct sk_buff *fragments_tail; @@ -53,45 +79,13 @@ struct inet_frag_queue { int meat; __u8 flags; u16 max_size; - struct netns_frags *net; - struct hlist_node list_evictor; -}; - -#define INETFRAGS_HASHSZ 1024 - -/* averaged: - * max_depth = default ipfrag_high_thresh / INETFRAGS_HASHSZ / - * rounded up (SKB_TRUELEN(0) + sizeof(struct ipq or - * struct frag_queue)) - */ -#define INETFRAGS_MAXDEPTH 128 - -struct inet_frag_bucket { - struct hlist_head chain; - spinlock_t chain_lock; + struct netns_frags *net; + struct rcu_head rcu; };

struct inet_frags { - struct inet_frag_bucket hash[INETFRAGS_HASHSZ]; - - struct work_struct frags_work; - unsigned int next_bucket; - unsigned long last_rebuild_jiffies; - bool rebuild; - - /* The first call to hashfn is responsible to initialize - * rnd. This is best done with net_get_random_once. - * - * rnd_seqlock is used to let hash insertion detect - * when it needs to re-lookup the hash chain to use. - */ - u32 rnd; - seqlock_t rnd_seqlock; int qsize;

- unsigned int (*hashfn)(const struct inet_frag_queue *); - bool (*match)(const struct inet_frag_queue *q, - const void *arg); void (*constructor)(struct inet_frag_queue *q, const void *arg); void (*destructor)(struct inet_frag_queue *); @@ -99,6 +93,7 @@ struct inet_frags { void (*frag_expire)(unsigned long data); struct kmem_cache *frags_cachep; const char *frags_cache_name; + struct rhashtable_params rhash_params; };

int inet_frags_init(struct inet_frags *); @@ -107,15 +102,13 @@ void inet_frags_fini(struct inet_frags * static inline int inet_frags_init_net(struct netns_frags *nf) { atomic_set(&nf->mem, 0); - return 0; + return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params); } void inet_frags_exit_net(struct netns_frags *nf);

void inet_frag_kill(struct inet_frag_queue *q); void inet_frag_destroy(struct inet_frag_queue *q); -struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, - struct inet_frags *f, void *key, unsigned int hash); - +struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key); void inet_frag_maybe_warn_overflow(struct inet_frag_queue *q, const char *prefix);

@@ -127,7 +120,7 @@ static inline void inet_frag_put(struct

static inline bool inet_frag_evicting(struct inet_frag_queue *q) { - return !hlist_unhashed(&q->list_evictor); + return false; }

/* Memory Tracking Functions. */ --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -505,17 +505,8 @@ enum ip6_defrag_users { __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, };

-struct ip6_create_arg { - __be32 id; - u32 user; - const struct in6_addr *src; - const struct in6_addr *dst; - int iif; - u8 ecn; -}; - void ip6_frag_init(struct inet_frag_queue *q, const void *a); -bool ip6_frag_match(const struct inet_frag_queue *q, const void *a); +extern const struct rhashtable_params ip6_rhash_params;

/* * Equivalent of ipv4 struct ip @@ -523,11 +514,6 @@ bool ip6_frag_match(const struct inet_fr struct frag_queue { struct inet_frag_queue q;

- __be32 id; /* fragment id */ - u32 user; - struct in6_addr saddr; - struct in6_addr daddr; - int iif; unsigned int csum; __u16 nhoffset; --- a/net/ieee802154/6lowpan/6lowpan_i.h +++ b/net/ieee802154/6lowpan/6lowpan_i.h @@ -16,37 +16,19 @@ typedef unsigned __bitwise__ lowpan_rx_r #define LOWPAN_DISPATCH_FRAG1 0xc0 #define LOWPAN_DISPATCH_FRAGN 0xe0

-struct lowpan_create_arg { +struct frag_lowpan_compare_key { u16 tag; u16 d_size; - const struct ieee802154_addr *src; - const struct ieee802154_addr *dst; + const struct ieee802154_addr src; + const struct ieee802154_addr dst; };

-/* Equivalent of ipv4 struct ip +/* Equivalent of ipv4 struct ipq */ struct lowpan_frag_queue { struct inet_frag_queue q; - - u16 tag; - u16 d_size; - struct ieee802154_addr saddr; - struct ieee802154_addr daddr; };

-static inline u32 ieee802154_addr_hash(const struct ieee802154_addr *a) -{ - switch (a->mode) { - case IEEE802154_ADDR_LONG: - return (((__force u64)a->extended_addr) >> 32) ^ - (((__force u64)a->extended_addr) & 0xffffffff); - case IEEE802154_ADDR_SHORT: - return (__force u32)(a->short_addr); - default: - return 0; - } -} - /* private device info */ struct lowpan_dev_info { struct net_device *wdev; /* wpan device ptr */ --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -37,47 +37,15 @@ static struct inet_frags lowpan_frags; static int lowpan_frag_reasm(struct lowpan_frag_queue *fq, struct sk_buff *prev, struct net_device *ldev);

-static unsigned int lowpan_hash_frag(u16 tag, u16 d_size, - const struct ieee802154_addr *saddr, - const struct ieee802154_addr *daddr) -{ - net_get_random_once(&lowpan_frags.rnd, sizeof(lowpan_frags.rnd)); - return jhash_3words(ieee802154_addr_hash(saddr), - ieee802154_addr_hash(daddr), - (__force u32)(tag + (d_size << 16)), - lowpan_frags.rnd); -} - -static unsigned int lowpan_hashfn(const struct inet_frag_queue *q) -{ - const struct lowpan_frag_queue *fq; - - fq = container_of(q, struct lowpan_frag_queue, q); - return lowpan_hash_frag(fq->tag, fq->d_size, &fq->saddr, &fq->daddr); -} - -static bool lowpan_frag_match(const struct inet_frag_queue *q, const void *a) -{ - const struct lowpan_frag_queue *fq; - const struct lowpan_create_arg *arg = a; - - fq = container_of(q, struct lowpan_frag_queue, q); - return fq->tag == arg->tag && fq->d_size == arg->d_size && - ieee802154_addr_equal(&fq->saddr, arg->src) && - ieee802154_addr_equal(&fq->daddr, arg->dst); -} - static void lowpan_frag_init(struct inet_frag_queue *q, const void *a) { - const struct lowpan_create_arg *arg = a; + const struct frag_lowpan_compare_key *key = a; struct lowpan_frag_queue *fq;

fq = container_of(q, struct lowpan_frag_queue, q);

- fq->tag = arg->tag; - fq->d_size = arg->d_size; - fq->saddr = *arg->src; - fq->daddr = *arg->dst; + BUILD_BUG_ON(sizeof(*key) > sizeof(q->key)); + memcpy(&q->key, key, sizeof(*key)); }

static void lowpan_frag_expire(unsigned long data) @@ -104,21 +72,17 @@ fq_find(struct net *net, const struct lo const struct ieee802154_addr *src, const struct ieee802154_addr *dst) { - struct inet_frag_queue *q; - struct lowpan_create_arg arg; - unsigned int hash; struct netns_ieee802154_lowpan *ieee802154_lowpan = net_ieee802154_lowpan(net); + struct frag_lowpan_compare_key key = { + .tag = cb->d_tag, + .d_size = cb->d_size, + .src = *src, + .dst = *dst, + }; + struct inet_frag_queue *q;

- arg.tag = cb->d_tag; - arg.d_size = cb->d_size; - arg.src = src; - arg.dst = dst; - - hash = lowpan_hash_frag(cb->d_tag, cb->d_size, src, dst); - - q = inet_frag_find(&ieee802154_lowpan->frags, - &lowpan_frags, &arg, hash); + q = inet_frag_find(&ieee802154_lowpan->frags, &key); if (IS_ERR_OR_NULL(q)) { inet_frag_maybe_warn_overflow(q, pr_fmt()); return NULL; @@ -610,18 +574,47 @@ static struct pernet_operations lowpan_f .exit = lowpan_frags_exit_net, };

+static u32 lowpan_key_hashfn(const void *data, u32 len, u32 seed) +{ + return jhash2(data, + sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed); +} + +static u32 lowpan_obj_hashfn(const void *data, u32 len, u32 seed) +{ + const struct inet_frag_queue *fq = data; + + return jhash2((const u32 *)&fq->key, + sizeof(struct frag_lowpan_compare_key) / sizeof(u32), seed); +} + +static int lowpan_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) +{ + const struct frag_lowpan_compare_key *key = arg->key; + const struct inet_frag_queue *fq = ptr; + + return !!memcmp(&fq->key, key, sizeof(*key)); +} + +static const struct rhashtable_params lowpan_rhash_params = { + .head_offset = offsetof(struct inet_frag_queue, node), + .hashfn = lowpan_key_hashfn, + .obj_hashfn = lowpan_obj_hashfn, + .obj_cmpfn = lowpan_obj_cmpfn, + .automatic_shrinking = true, +}; + int __init lowpan_net_frag_init(void) { int ret;

- lowpan_frags.hashfn = lowpan_hashfn; lowpan_frags.constructor = lowpan_frag_init; lowpan_frags.destructor = NULL; lowpan_frags.skb_free = NULL; lowpan_frags.qsize = sizeof(struct frag_queue); - lowpan_frags.match = lowpan_frag_match; lowpan_frags.frag_expire = lowpan_frag_expire; lowpan_frags.frags_cache_name = lowpan_frags_cache_name; + lowpan_frags.rhash_params = lowpan_rhash_params; ret = inet_frags_init(&lowpan_frags); if (ret) goto out; --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -25,12 +25,6 @@ #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 @@ -52,157 +46,8 @@ const u8 ip_frag_ecn_table[16] = { }; 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) -{ - if (!hlist_unhashed(&q->list_evictor)) - return false; - - 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) @@ -214,66 +59,42 @@ EXPORT_SYMBOL(inet_frags_init);

void inet_frags_fini(struct inet_frags *f) { - cancel_work_sync(&f->frags_work); + /* We must wait that all inet_frag_destroy_rcu() have completed. */ + rcu_barrier(); + kmem_cache_destroy(f->frags_cachep); + f->frags_cachep = NULL; } EXPORT_SYMBOL(inet_frags_fini);

-void inet_frags_exit_net(struct netns_frags *nf) +static void inet_frags_free_cb(void *ptr, void *arg) { - struct inet_frags *f =nf->f; - unsigned int seq; - int i; + struct inet_frag_queue *fq = ptr;

- 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); + /* If we can not cancel the timer, it means this frag_queue + * is already disappearing, we have nothing to do. + * Otherwise, we own a refcount until the end of this function. + */ + if (!del_timer(&fq->timer)) + return;

-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; + spin_lock_bh(&fq->lock); + if (!(fq->flags & INET_FRAG_COMPLETE)) { + fq->flags |= INET_FRAG_COMPLETE; + atomic_dec(&fq->refcnt); } + spin_unlock_bh(&fq->lock);

- return hb; + inet_frag_put(fq); }

-static inline void fq_unlink(struct inet_frag_queue *fq) +void inet_frags_exit_net(struct netns_frags *nf) { - struct inet_frag_bucket *hb; + nf->low_thresh = 0; /* prevent creation of new frags */

- hb = get_frag_bucket_locked(fq, fq->net->f); - hlist_del(&fq->list); - fq->flags |= INET_FRAG_COMPLETE; - spin_unlock(&hb->chain_lock); + rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL); } +EXPORT_SYMBOL(inet_frags_exit_net);

void inet_frag_kill(struct inet_frag_queue *fq) { @@ -281,7 +102,10 @@ void inet_frag_kill(struct inet_frag_que atomic_dec(&fq->refcnt);

if (!(fq->flags & INET_FRAG_COMPLETE)) { - fq_unlink(fq); + struct netns_frags *nf = fq->net; + + fq->flags |= INET_FRAG_COMPLETE; + rhashtable_remove_fast(&nf->rhashtable, &fq->node, nf->f->rhash_params); atomic_dec(&fq->refcnt); } } @@ -295,6 +119,17 @@ static inline void frag_kfree_skb(struct kfree_skb(skb); }

+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->net->f; + + if (f->destructor) + f->destructor(q); + kmem_cache_free(f->frags_cachep, q); +} + void inet_frag_destroy(struct inet_frag_queue *q) { struct sk_buff *fp; @@ -318,55 +153,21 @@ void inet_frag_destroy(struct inet_frag_ } sum = sum_truesize + f->qsize;

- if (f->destructor) - f->destructor(q); - kmem_cache_free(f->frags_cachep, q); + call_rcu(&q->rcu, inet_frag_destroy_rcu);

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)) { - atomic_inc(&qp->refcnt); - spin_unlock(&hb->chain_lock); - qp_in->flags |= INET_FRAG_COMPLETE; - inet_frag_put(qp_in); - return qp; - } - } -#endif - qp = qp_in; - if (!mod_timer(&qp->timer, jiffies + nf->timeout)) - atomic_inc(&qp->refcnt); - - atomic_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) + return NULL; + q = kmem_cache_zalloc(f->frags_cachep, GFP_ATOMIC); if (!q) return NULL; @@ -377,64 +178,51 @@ static struct inet_frag_queue *inet_frag

setup_timer(&q->timer, f->frag_expire, (unsigned long)q); spin_lock_init(&q->lock); - atomic_set(&q->refcnt, 1); + atomic_set(&q->refcnt, 3);

return q; }

static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, - struct inet_frags *f, void *arg) { + struct inet_frags *f = nf->f; struct inet_frag_queue *q; + int err;

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; + mod_timer(&q->timer, jiffies + nf->timeout);

- if (!nf->high_thresh || frag_mem_limit(nf) > nf->high_thresh) { - inet_frag_schedule_worker(f); + err = rhashtable_insert_fast(&nf->rhashtable, &q->node, + f->rhash_params); + if (err < 0) { + q->flags |= INET_FRAG_COMPLETE; + inet_frag_kill(q); + inet_frag_destroy(q); return NULL; } + return q; +} +EXPORT_SYMBOL(inet_frag_create);

- 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)) { - atomic_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); +/* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ +struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) +{ + struct inet_frag_queue *fq;

- if (inet_frag_may_rebuild(f)) { - if (!f->rebuild) - f->rebuild = true; - inet_frag_schedule_worker(f); + rcu_read_lock(); + fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); + if (fq) { + if (!atomic_inc_not_zero(&fq->refcnt)) + fq = NULL; + rcu_read_unlock(); + return fq; } - - return ERR_PTR(-ENOBUFS); + rcu_read_unlock(); + return inet_frag_create(nf, key); } EXPORT_SYMBOL(inet_frag_find);

@@ -442,8 +230,7 @@ void inet_frag_maybe_warn_overflow(struc const char *prefix) { static const char msg[] = "inet_frag_find: Fragment hash bucket" - " list length grew over limit " __stringify(INETFRAGS_MAXDEPTH) - ". Dropping fragment.\n"; + " list length grew over limit. Dropping fragment.\n";

if (PTR_ERR(q) == -ENOBUFS) net_dbg_ratelimited("%s%s", prefix, msg); --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -70,15 +70,9 @@ struct ipfrag_skb_cb struct ipq { struct inet_frag_queue q;

- u32 user; - __be32 saddr; - __be32 daddr; - __be16 id; - u8 protocol; u8 ecn; /* RFC3168 support */ u16 max_df_size; /* largest frag with DF set seen */ int iif; - int vif; /* L3 master device index */ unsigned int rid; struct inet_peer *peer; }; @@ -98,41 +92,6 @@ int ip_frag_mem(struct net *net) static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, struct net_device *dev);

-struct ip4_create_arg { - struct iphdr *iph; - u32 user; - int vif; -}; - -static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot) -{ - net_get_random_once(&ip4_frags.rnd, sizeof(ip4_frags.rnd)); - return jhash_3words((__force u32)id << 16 | prot, - (__force u32)saddr, (__force u32)daddr, - ip4_frags.rnd); -} - -static unsigned int ip4_hashfn(const struct inet_frag_queue *q) -{ - const struct ipq *ipq; - - ipq = container_of(q, struct ipq, q); - return ipqhashfn(ipq->id, ipq->saddr, ipq->daddr, ipq->protocol); -} - -static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a) -{ - const struct ipq *qp; - const struct ip4_create_arg *arg = a; - - qp = container_of(q, struct ipq, q); - return qp->id == arg->iph->id && - qp->saddr == arg->iph->saddr && - qp->daddr == arg->iph->daddr && - qp->protocol == arg->iph->protocol && - qp->user == arg->user && - qp->vif == arg->vif; -}

static void ip4_frag_init(struct inet_frag_queue *q, const void *a) { @@ -141,17 +100,12 @@ static void ip4_frag_init(struct inet_fr frags); struct net *net = container_of(ipv4, struct net, ipv4);

- const struct ip4_create_arg *arg = a; + const struct frag_v4_compare_key *key = a;

- qp->protocol = arg->iph->protocol; - qp->id = arg->iph->id; - qp->ecn = ip4_frag_ecn(arg->iph->tos); - qp->saddr = arg->iph->saddr; - qp->daddr = arg->iph->daddr; - qp->vif = arg->vif; - qp->user = arg->user; + q->key.v4 = *key; + qp->ecn = 0; qp->peer = sysctl_ipfrag_max_dist ? - inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) : + inet_getpeer_v4(net->ipv4.peers, key->saddr, key->vif, 1) : NULL; }

@@ -234,7 +188,7 @@ static void ip_expire(unsigned long arg) /* Only an end host needs to send an ICMP * "Fragment Reassembly Timeout" message, per RFC792. */ - if (frag_expire_skip_icmp(qp->user) && + if (frag_expire_skip_icmp(qp->q.key.v4.user) && (skb_rtable(head)->rt_type != RTN_LOCAL)) goto out;

@@ -262,17 +216,17 @@ out_rcu_unlock: static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user, int vif) { + struct frag_v4_compare_key key = { + .saddr = iph->saddr, + .daddr = iph->daddr, + .user = user, + .vif = vif, + .id = iph->id, + .protocol = iph->protocol, + }; struct inet_frag_queue *q; - struct ip4_create_arg arg; - unsigned int hash; - - arg.iph = iph; - arg.user = user; - arg.vif = vif;

- hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); - - q = inet_frag_find(&net->ipv4.frags, &ip4_frags, &arg, hash); + q = inet_frag_find(&net->ipv4.frags, &key); if (IS_ERR_OR_NULL(q)) { inet_frag_maybe_warn_overflow(q, pr_fmt()); return NULL; @@ -656,7 +610,7 @@ out_nomem: err = -ENOMEM; goto out_fail; out_oversize: - net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->saddr); + net_info_ratelimited("Oversized IP packet from %pI4\n", &qp->q.key.v4.saddr); out_fail: IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS); return err; @@ -900,16 +854,48 @@ static struct pernet_operations ip4_frag .exit = ipv4_frags_exit_net, };

+ +static u32 ip4_key_hashfn(const void *data, u32 len, u32 seed) +{ + return jhash2(data, + sizeof(struct frag_v4_compare_key) / sizeof(u32), seed); +} + +static u32 ip4_obj_hashfn(const void *data, u32 len, u32 seed) +{ + const struct inet_frag_queue *fq = data; + + return jhash2((const u32 *)&fq->key.v4, + sizeof(struct frag_v4_compare_key) / sizeof(u32), seed); +} + +static int ip4_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) +{ + const struct frag_v4_compare_key *key = arg->key; + const struct inet_frag_queue *fq = ptr; + + return !!memcmp(&fq->key, key, sizeof(*key)); +} + +static const struct rhashtable_params ip4_rhash_params = { + .head_offset = offsetof(struct inet_frag_queue, node), + .key_offset = offsetof(struct inet_frag_queue, key), + .key_len = sizeof(struct frag_v4_compare_key), + .hashfn = ip4_key_hashfn, + .obj_hashfn = ip4_obj_hashfn, + .obj_cmpfn = ip4_obj_cmpfn, + .automatic_shrinking = true, +}; + void __init ipfrag_init(void) { - ip4_frags.hashfn = ip4_hashfn; ip4_frags.constructor = ip4_frag_init; ip4_frags.destructor = ip4_frag_free; ip4_frags.skb_free = NULL; ip4_frags.qsize = sizeof(struct ipq); - ip4_frags.match = ip4_frag_match; ip4_frags.frag_expire = ip_expire; ip4_frags.frags_cache_name = ip_frag_cache_name; + ip4_frags.rhash_params = ip4_rhash_params; if (inet_frags_init(&ip4_frags)) panic("IP: failed to allocate ip4_frags cache\n"); ip4_frags_ctl_register(); --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -153,23 +153,6 @@ static inline u8 ip6_frag_ecn(const stru return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); }

-static unsigned int nf_hash_frag(__be32 id, const struct in6_addr *saddr, - const struct in6_addr *daddr) -{ - net_get_random_once(&nf_frags.rnd, sizeof(nf_frags.rnd)); - return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), - (__force u32)id, nf_frags.rnd); -} - - -static unsigned int nf_hashfn(const struct inet_frag_queue *q) -{ - const struct frag_queue *nq; - - nq = container_of(q, struct frag_queue, q); - return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr); -} - static void nf_skb_free(struct sk_buff *skb) { if (NFCT_FRAG6_CB(skb)->orig) @@ -188,26 +171,19 @@ static void nf_ct_frag6_expire(unsigned }

/* Creation primitives. */ -static inline struct frag_queue *fq_find(struct net *net, __be32 id, - u32 user, struct in6_addr *src, - struct in6_addr *dst, int iif, u8 ecn) +static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, + const struct ipv6hdr *hdr, int iif) { + struct frag_v6_compare_key key = { + .id = id, + .saddr = hdr->saddr, + .daddr = hdr->daddr, + .user = user, + .iif = iif, + }; struct inet_frag_queue *q; - struct ip6_create_arg arg; - unsigned int hash; - - arg.id = id; - arg.user = user; - arg.src = src; - arg.dst = dst; - arg.iif = iif; - arg.ecn = ecn; - - local_bh_disable(); - hash = nf_hash_frag(id, src, dst);

- q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash); - local_bh_enable(); + q = inet_frag_find(&net->nf_frag.frags, &key); if (IS_ERR_OR_NULL(q)) { inet_frag_maybe_warn_overflow(q, pr_fmt()); return NULL; @@ -602,8 +578,8 @@ struct sk_buff *nf_ct_frag6_gather(struc fhdr = (struct frag_hdr *)skb_transport_header(clone);

skb_orphan(skb); - fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr, - skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr)); + fq = fq_find(net, fhdr->identification, user, hdr, + skb->dev ? skb->dev->ifindex : 0); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); goto ret_orig; @@ -681,14 +657,13 @@ int nf_ct_frag6_init(void) { int ret = 0;

- nf_frags.hashfn = nf_hashfn; nf_frags.constructor = ip6_frag_init; nf_frags.destructor = NULL; nf_frags.skb_free = nf_skb_free; nf_frags.qsize = sizeof(struct frag_queue); - nf_frags.match = ip6_frag_match; nf_frags.frag_expire = nf_ct_frag6_expire; nf_frags.frags_cache_name = nf_frags_cache_name; + nf_frags.rhash_params = ip6_rhash_params; ret = inet_frags_init(&nf_frags); if (ret) goto out; --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -79,52 +79,13 @@ static struct inet_frags ip6_frags; static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev);

-/* - * callers should be careful not to use the hash value outside the ipfrag_lock - * as doing so could race with ipfrag_hash_rnd being recalculated. - */ -static unsigned int inet6_hash_frag(__be32 id, const struct in6_addr *saddr, - const struct in6_addr *daddr) -{ - net_get_random_once(&ip6_frags.rnd, sizeof(ip6_frags.rnd)); - return jhash_3words(ipv6_addr_hash(saddr), ipv6_addr_hash(daddr), - (__force u32)id, ip6_frags.rnd); -} - -static unsigned int ip6_hashfn(const struct inet_frag_queue *q) -{ - const struct frag_queue *fq; - - fq = container_of(q, struct frag_queue, q); - return inet6_hash_frag(fq->id, &fq->saddr, &fq->daddr); -} - -bool ip6_frag_match(const struct inet_frag_queue *q, const void *a) -{ - const struct frag_queue *fq; - const struct ip6_create_arg *arg = a; - - fq = container_of(q, struct frag_queue, q); - return fq->id == arg->id && - fq->user == arg->user && - ipv6_addr_equal(&fq->saddr, arg->src) && - ipv6_addr_equal(&fq->daddr, arg->dst) && - (arg->iif == fq->iif || - !(ipv6_addr_type(arg->dst) & (IPV6_ADDR_MULTICAST | - IPV6_ADDR_LINKLOCAL))); -} -EXPORT_SYMBOL(ip6_frag_match); - void ip6_frag_init(struct inet_frag_queue *q, const void *a) { struct frag_queue *fq = container_of(q, struct frag_queue, q); - const struct ip6_create_arg *arg = a; + const struct frag_v6_compare_key *key = a;

- fq->id = arg->id; - fq->user = arg->user; - fq->saddr = *arg->src; - fq->daddr = *arg->dst; - fq->ecn = arg->ecn; + q->key.v6 = *key; + fq->ecn = 0; } EXPORT_SYMBOL(ip6_frag_init);

@@ -181,23 +142,22 @@ static void ip6_frag_expire(unsigned lon }

static struct frag_queue * -fq_find(struct net *net, __be32 id, const struct in6_addr *src, - const struct in6_addr *dst, int iif, u8 ecn) +fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif) { + 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; - struct ip6_create_arg arg; - unsigned int hash; - - arg.id = id; - arg.user = IP6_DEFRAG_LOCAL_DELIVER; - arg.src = src; - arg.dst = dst; - arg.iif = iif; - arg.ecn = ecn;

- hash = inet6_hash_frag(id, src, dst); + if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST | + IPV6_ADDR_LINKLOCAL))) + key.iif = 0;

- q = inet_frag_find(&net->ipv6.frags, &ip6_frags, &arg, hash); + q = inet_frag_find(&net->ipv6.frags, &key); if (IS_ERR_OR_NULL(q)) { inet_frag_maybe_warn_overflow(q, pr_fmt()); return NULL; @@ -523,6 +483,7 @@ static int ipv6_frag_rcv(struct sk_buff struct frag_queue *fq; const struct ipv6hdr *hdr = ipv6_hdr(skb); struct net *net = dev_net(skb_dst(skb)->dev); + int iif;

if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED) goto fail_hdr; @@ -551,13 +512,14 @@ static int ipv6_frag_rcv(struct sk_buff return 1; }

- fq = fq_find(net, fhdr->identification, &hdr->saddr, &hdr->daddr, - skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr)); + iif = skb->dev ? skb->dev->ifindex : 0; + fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { int ret;

spin_lock(&fq->q.lock);

+ fq->iif = iif; ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff);

spin_unlock(&fq->q.lock); @@ -735,17 +697,47 @@ static struct pernet_operations ip6_frag .exit = ipv6_frags_exit_net, };

+static u32 ip6_key_hashfn(const void *data, u32 len, u32 seed) +{ + return jhash2(data, + sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); +} + +static u32 ip6_obj_hashfn(const void *data, u32 len, u32 seed) +{ + const struct inet_frag_queue *fq = data; + + return jhash2((const u32 *)&fq->key.v6, + sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); +} + +static int ip6_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) +{ + const struct frag_v6_compare_key *key = arg->key; + const struct inet_frag_queue *fq = ptr; + + return !!memcmp(&fq->key, key, sizeof(*key)); +} + +const struct rhashtable_params ip6_rhash_params = { + .head_offset = offsetof(struct inet_frag_queue, node), + .hashfn = ip6_key_hashfn, + .obj_hashfn = ip6_obj_hashfn, + .obj_cmpfn = ip6_obj_cmpfn, + .automatic_shrinking = true, +}; +EXPORT_SYMBOL(ip6_rhash_params); + int __init ipv6_frag_init(void) { int ret;

- ip6_frags.hashfn = ip6_hashfn; ip6_frags.constructor = ip6_frag_init; ip6_frags.destructor = NULL; ip6_frags.qsize = sizeof(struct frag_queue); - ip6_frags.match = ip6_frag_match; ip6_frags.frag_expire = ip6_frag_expire; ip6_frags.frags_cache_name = ip6_frag_cache_name; + ip6_frags.rhash_params = ip6_rhash_params; ret = inet_frags_init(&ip6_frags); if (ret) goto out;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Paolo Abeni pabeni@redhat.com

commit f6f2a4a2eb92bc73671204198bb2f8ab53ff59fb upstream.

Setting the low threshold to 0 has no effect on frags allocation, we need to clear high_thresh instead.

The code was pre-existent to commit 648700f76b03 ("inet: frags: use rhashtables for reassembly units"), but before the above, such assignment had a different role: prevent concurrent eviction from the worker and the netns cleanup helper.

Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units") Signed-off-by: Paolo Abeni pabeni@redhat.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/inet_fragment.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -90,7 +90,7 @@ static void inet_frags_free_cb(void *ptr

void inet_frags_exit_net(struct netns_frags *nf) { - nf->low_thresh = 0; /* prevent creation of new frags */ + nf->high_thresh = 0; /* prevent creation of new frags */

rhashtable_free_and_destroy(&nf->rhashtable, inet_frags_free_cb, NULL); }

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 399d1404be660d355192ff4df5ccc3f4159ec1e4 upstream.

This refactors ip_expire() since one indentation level is removed.

Note: in the future, we should try hard to avoid the skb_clone() since this is a serious performance cost. Under DDOS, the ICMP message wont be sent because of rate limits.

Fact that ip6_expire_frag_queue() does not use skb_clone() is disturbing too. Presumably IPv6 should have the same issue than the one we fixed in commit ec4fbd64751d ("inet: frag: release spinlock before calling icmp_send()")

Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Mao Wenan maowenan@huawei.com [bwh: Backported to 4.4: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/inet_frag.h | 5 --- net/ipv4/ip_fragment.c | 65 +++++++++++++++++++++++------------------------- net/ipv6/reassembly.c | 4 -- 3 files changed, 32 insertions(+), 42 deletions(-)

--- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -118,11 +118,6 @@ static inline void inet_frag_put(struct inet_frag_destroy(q); }

-static inline bool inet_frag_evicting(struct inet_frag_queue *q) -{ - return false; -} - /* Memory Tracking Functions. */

static inline int frag_mem_limit(struct netns_frags *nf) --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -143,8 +143,11 @@ static bool frag_expire_skip_icmp(u32 us */ static void ip_expire(unsigned long arg) { - struct ipq *qp; + struct sk_buff *clone, *head; + const struct iphdr *iph; struct net *net; + struct ipq *qp; + int err;

qp = container_of((struct inet_frag_queue *) arg, struct ipq, q); net = container_of(qp->q.net, struct net, ipv4.frags); @@ -158,45 +161,41 @@ static void ip_expire(unsigned long arg) ipq_kill(qp); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);

- if (!inet_frag_evicting(&qp->q)) { - struct sk_buff *clone, *head = qp->q.fragments; - const struct iphdr *iph; - int err; + head = qp->q.fragments;

- IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT); + IP_INC_STATS_BH(net, IPSTATS_MIB_REASMTIMEOUT);

- if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !qp->q.fragments) - goto out; + if (!(qp->q.flags & INET_FRAG_FIRST_IN) || !head) + goto out;

- head->dev = dev_get_by_index_rcu(net, qp->iif); - if (!head->dev) - goto out; + head->dev = dev_get_by_index_rcu(net, qp->iif); + if (!head->dev) + goto out;

- /* skb has no dst, perform route lookup again */ - iph = ip_hdr(head); - err = ip_route_input_noref(head, iph->daddr, iph->saddr, + /* skb has no dst, perform route lookup again */ + iph = ip_hdr(head); + err = ip_route_input_noref(head, iph->daddr, iph->saddr, iph->tos, head->dev); - if (err) - goto out; + if (err) + goto out; + + /* Only an end host needs to send an ICMP + * "Fragment Reassembly Timeout" message, per RFC792. + */ + if (frag_expire_skip_icmp(qp->q.key.v4.user) && + (skb_rtable(head)->rt_type != RTN_LOCAL)) + goto out; + + clone = skb_clone(head, GFP_ATOMIC);

- /* Only an end host needs to send an ICMP - * "Fragment Reassembly Timeout" message, per RFC792. - */ - if (frag_expire_skip_icmp(qp->q.key.v4.user) && - (skb_rtable(head)->rt_type != RTN_LOCAL)) - goto out; - - clone = skb_clone(head, GFP_ATOMIC); - - /* Send an ICMP "Fragment Reassembly Timeout" message. */ - if (clone) { - spin_unlock(&qp->q.lock); - icmp_send(clone, ICMP_TIME_EXCEEDED, - ICMP_EXC_FRAGTIME, 0); - consume_skb(clone); - goto out_rcu_unlock; - } + /* Send an ICMP "Fragment Reassembly Timeout" message. */ + if (clone) { + spin_unlock(&qp->q.lock); + icmp_send(clone, ICMP_TIME_EXCEEDED, + ICMP_EXC_FRAGTIME, 0); + consume_skb(clone); + goto out_rcu_unlock; } out: spin_unlock(&qp->q.lock); --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -106,10 +106,6 @@ void ip6_expire_frag_queue(struct net *n goto out_rcu_unlock;

IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); - - if (inet_frag_evicting(&fq->q)) - goto out_rcu_unlock; - IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);

/* Don't send error if the first segment did not arrive. */

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 3e67f106f619dcfaf6f4e2039599bdb69848c714 upstream.

Some users are willing to provision huge amounts of memory to be able to perform reassembly reasonnably well under pressure.

Current memory tracking is using one atomic_t and integers.

Switch to atomic_long_t so that 64bit arches can use more than 2GB, without any cost for 32bit arches.

Note that this patch avoids an overflow error, if high_thresh was set to ~2GB, since this test in inet_frag_alloc() was never true :

if (... || frag_mem_limit(nf) > nf->high_thresh)

Tested:

$ echo 16000000000 >/proc/sys/net/ipv4/ipfrag_high_thresh

<frag DDOS>

$ grep FRAG /proc/net/sockstat FRAG: inuse 14705885 memory 16000002880

$ nstat -n ; sleep 1 ; nstat | grep Reas IpReasmReqds 3317150 0.0 IpReasmFails 3317112 0.0

Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- Documentation/networking/ip-sysctl.txt | 4 ++-- include/net/inet_frag.h | 20 ++++++++++---------- net/ieee802154/6lowpan/reassembly.c | 10 +++++----- net/ipv4/ip_fragment.c | 10 +++++----- net/ipv4/proc.c | 2 +- net/ipv6/netfilter/nf_conntrack_reasm.c | 10 +++++----- net/ipv6/proc.c | 2 +- net/ipv6/reassembly.c | 6 +++--- 8 files changed, 32 insertions(+), 32 deletions(-)

--- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -112,10 +112,10 @@ min_adv_mss - INTEGER

IP Fragmentation:

-ipfrag_high_thresh - INTEGER +ipfrag_high_thresh - LONG INTEGER Maximum memory used to reassemble IP fragments.

-ipfrag_low_thresh - INTEGER +ipfrag_low_thresh - LONG INTEGER (Obsolete since linux-4.17) Maximum memory used to reassemble IP fragments before the kernel begins to remove incomplete fragment queues to free up resources. --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -7,11 +7,11 @@ struct netns_frags { struct rhashtable rhashtable ____cacheline_aligned_in_smp;

/* Keep atomic mem on separate cachelines in structs that include it */ - atomic_t mem ____cacheline_aligned_in_smp; + atomic_long_t mem ____cacheline_aligned_in_smp; /* sysctls */ + long high_thresh; + long low_thresh; int timeout; - int high_thresh; - int low_thresh; struct inet_frags *f; };

@@ -101,7 +101,7 @@ void inet_frags_fini(struct inet_frags *

static inline int inet_frags_init_net(struct netns_frags *nf) { - atomic_set(&nf->mem, 0); + atomic_long_set(&nf->mem, 0); return rhashtable_init(&nf->rhashtable, &nf->f->rhash_params); } void inet_frags_exit_net(struct netns_frags *nf); @@ -118,19 +118,19 @@ static inline void inet_frag_put(struct

/* Memory Tracking Functions. */

-static inline int frag_mem_limit(struct netns_frags *nf) +static inline long frag_mem_limit(const struct netns_frags *nf) { - return atomic_read(&nf->mem); + return atomic_long_read(&nf->mem); }

-static inline void sub_frag_mem_limit(struct netns_frags *nf, int i) +static inline void sub_frag_mem_limit(struct netns_frags *nf, long val) { - atomic_sub(i, &nf->mem); + atomic_long_sub(val, &nf->mem); }

-static inline void add_frag_mem_limit(struct netns_frags *nf, int i) +static inline void add_frag_mem_limit(struct netns_frags *nf, long val) { - atomic_add(i, &nf->mem); + atomic_long_add(val, &nf->mem); }

/* RFC 3168 support : --- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -410,23 +410,23 @@ err: }

#ifdef CONFIG_SYSCTL -static int zero; +static long zero;

static struct ctl_table lowpan_frags_ns_ctl_table[] = { { .procname = "6lowpanfrag_high_thresh", .data = &init_net.ieee802154_lowpan.frags.high_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &init_net.ieee802154_lowpan.frags.low_thresh }, { .procname = "6lowpanfrag_low_thresh", .data = &init_net.ieee802154_lowpan.frags.low_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &zero, .extra2 = &init_net.ieee802154_lowpan.frags.high_thresh }, --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -682,23 +682,23 @@ struct sk_buff *ip_check_defrag(struct n EXPORT_SYMBOL(ip_check_defrag);

#ifdef CONFIG_SYSCTL -static int zero; +static long zero;

static struct ctl_table ip4_frags_ns_ctl_table[] = { { .procname = "ipfrag_high_thresh", .data = &init_net.ipv4.frags.high_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &init_net.ipv4.frags.low_thresh }, { .procname = "ipfrag_low_thresh", .data = &init_net.ipv4.frags.low_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &zero, .extra2 = &init_net.ipv4.frags.high_thresh }, --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -71,7 +71,7 @@ static int sockstat_seq_show(struct seq_ sock_prot_inuse_get(net, &udplite_prot)); seq_printf(seq, "RAW: inuse %d\n", sock_prot_inuse_get(net, &raw_prot)); - seq_printf(seq, "FRAG: inuse %u memory %u\n", + seq_printf(seq, "FRAG: inuse %u memory %lu\n", atomic_read(&net->ipv4.frags.rhashtable.nelems), frag_mem_limit(&net->ipv4.frags)); return 0; --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -64,7 +64,7 @@ struct nf_ct_frag6_skb_cb static struct inet_frags nf_frags;

#ifdef CONFIG_SYSCTL -static int zero; +static long zero;

static struct ctl_table nf_ct_frag6_sysctl_table[] = { { @@ -77,18 +77,18 @@ static struct ctl_table nf_ct_frag6_sysc { .procname = "nf_conntrack_frag6_low_thresh", .data = &init_net.nf_frag.frags.low_thresh, - .maxlen = sizeof(unsigned int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &zero, .extra2 = &init_net.nf_frag.frags.high_thresh }, { .procname = "nf_conntrack_frag6_high_thresh", .data = &init_net.nf_frag.frags.high_thresh, - .maxlen = sizeof(unsigned int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &init_net.nf_frag.frags.low_thresh }, { } --- a/net/ipv6/proc.c +++ b/net/ipv6/proc.c @@ -42,7 +42,7 @@ static int sockstat6_seq_show(struct seq sock_prot_inuse_get(net, &udplitev6_prot)); seq_printf(seq, "RAW6: inuse %d\n", sock_prot_inuse_get(net, &rawv6_prot)); - seq_printf(seq, "FRAG6: inuse %u memory %u\n", + seq_printf(seq, "FRAG6: inuse %u memory %lu\n", atomic_read(&net->ipv6.frags.rhashtable.nelems), frag_mem_limit(&net->ipv6.frags)); return 0; --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -545,15 +545,15 @@ static struct ctl_table ip6_frags_ns_ctl { .procname = "ip6frag_high_thresh", .data = &init_net.ipv6.frags.high_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, + .proc_handler = proc_doulongvec_minmax, .extra1 = &init_net.ipv6.frags.low_thresh }, { .procname = "ip6frag_low_thresh", .data = &init_net.ipv6.frags.low_thresh, - .maxlen = sizeof(int), + .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &zero,

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 05c0b86b9696802fd0ce5676a92a63f1b455bdf3 upstream.

Make it similar to IPv4 ip_expire(), and release the lock before calling icmp functions.

Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net [bwh: Backported to 4.4: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv6/reassembly.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-)

--- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -92,7 +92,9 @@ EXPORT_SYMBOL(ip6_frag_init); void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq) { struct net_device *dev = NULL; + struct sk_buff *head;

+ rcu_read_lock(); spin_lock(&fq->q.lock);

if (fq->q.flags & INET_FRAG_COMPLETE) @@ -100,28 +102,34 @@ void ip6_expire_frag_queue(struct net *n

inet_frag_kill(&fq->q);

- rcu_read_lock(); dev = dev_get_by_index_rcu(net, fq->iif); if (!dev) - goto out_rcu_unlock; + goto out;

IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);

/* Don't send error if the first segment did not arrive. */ - if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !fq->q.fragments) - goto out_rcu_unlock; + head = fq->q.fragments; + if (!(fq->q.flags & INET_FRAG_FIRST_IN) || !head) + goto out;

/* But use as source device on which LAST ARRIVED * segment was received. And do not use fq->dev * pointer directly, device might already disappeared. */ - fq->q.fragments->dev = dev; - icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); -out_rcu_unlock: - rcu_read_unlock(); + head->dev = dev; + skb_get(head); + spin_unlock(&fq->q.lock); + + icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); + kfree_skb(head); + goto out_rcu_unlock; + out: spin_unlock(&fq->q.lock); +out_rcu_unlock: + rcu_read_unlock(); inet_frag_put(&fq->q); } EXPORT_SYMBOL(ip6_expire_frag_queue);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit c2615cf5a761b32bf74e85bddc223dfff3d9b9f0 upstream.

Put the read-mostly fields in a separate cache line at the beginning of struct netns_frags, to reduce false sharing noticed in inet_frag_kill()

Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net [bwh: Backported to 4.4: adjust context] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/inet_frag.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)

--- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -4,15 +4,16 @@ #include <linux/rhashtable.h>

struct netns_frags { - struct rhashtable rhashtable ____cacheline_aligned_in_smp; - - /* Keep atomic mem on separate cachelines in structs that include it */ - atomic_long_t mem ____cacheline_aligned_in_smp; /* sysctls */ long high_thresh; long low_thresh; int timeout; struct inet_frags *f; + + struct rhashtable rhashtable ____cacheline_aligned_in_smp; + + /* Keep atomic mem on separate cachelines in structs that include it */ + atomic_long_t mem ____cacheline_aligned_in_smp; };

/**

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 3d23401283e80ceb03f765842787e0e79ff598b7 upstream.

Giving an integer to proc_doulongvec_minmax() is dangerous on 64bit arches, since linker might place next to it a non zero value preventing a change to ip6frag_low_thresh.

ip6frag_low_thresh is not used anymore in the kernel, but we do not want to prematuraly break user scripts wanting to change it.

Since specifying a minimal value of 0 for proc_doulongvec_minmax() is moot, let's remove these zero values in all defrag units.

Fixes: 6e00f7dd5e4e ("ipv6: frags: fix /proc/sys/net/ipv6/ip6frag_low_thresh") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: Maciej Żenczykowski maze@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ieee802154/6lowpan/reassembly.c | 2 - net/ipv4/ip_fragment.c | 40 ++++++++++++-------------------- net/ipv6/netfilter/nf_conntrack_reasm.c | 2 - net/ipv6/reassembly.c | 4 --- 4 files changed, 17 insertions(+), 31 deletions(-)

--- a/net/ieee802154/6lowpan/reassembly.c +++ b/net/ieee802154/6lowpan/reassembly.c @@ -410,7 +410,6 @@ err: }

#ifdef CONFIG_SYSCTL -static long zero;

static struct ctl_table lowpan_frags_ns_ctl_table[] = { { @@ -427,7 +426,6 @@ static struct ctl_table lowpan_frags_ns_ .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, .extra2 = &init_net.ieee802154_lowpan.frags.high_thresh }, { --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -58,14 +58,6 @@ static int sysctl_ipfrag_max_dist __read_mostly = 64; static const char ip_frag_cache_name[] = "ip4-frags";

-struct ipfrag_skb_cb -{ - struct inet_skb_parm h; - int offset; -}; - -#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) - /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; @@ -353,13 +345,13 @@ static int ip_frag_queue(struct ipq *qp, * this fragment, right? */ prev = qp->q.fragments_tail; - if (!prev || FRAG_CB(prev)->offset < offset) { + if (!prev || prev->ip_defrag_offset < offset) { next = NULL; goto found; } prev = NULL; for (next = qp->q.fragments; next != NULL; next = next->next) { - if (FRAG_CB(next)->offset >= offset) + if (next->ip_defrag_offset >= offset) break; /* bingo! */ prev = next; } @@ -370,7 +362,7 @@ found: * any overlaps are eliminated. */ if (prev) { - int i = (FRAG_CB(prev)->offset + prev->len) - offset; + int i = (prev->ip_defrag_offset + prev->len) - offset;

if (i > 0) { offset += i; @@ -387,8 +379,8 @@ found:

err = -ENOMEM;

- while (next && FRAG_CB(next)->offset < end) { - int i = end - FRAG_CB(next)->offset; /* overlap is 'i' bytes */ + while (next && next->ip_defrag_offset < end) { + int i = end - next->ip_defrag_offset; /* overlap is 'i' bytes */

if (i < next->len) { /* Eat head of the next overlapped fragment @@ -396,7 +388,7 @@ found: */ if (!pskb_pull(next, i)) goto err; - FRAG_CB(next)->offset += i; + next->ip_defrag_offset += i; qp->q.meat -= i; if (next->ip_summed != CHECKSUM_UNNECESSARY) next->ip_summed = CHECKSUM_NONE; @@ -420,7 +412,13 @@ found: } }

- FRAG_CB(skb)->offset = offset; + /* Note : skb->ip_defrag_offset and skb->dev share the same location */ + dev = skb->dev; + if (dev) + qp->iif = dev->ifindex; + /* Makes sure compiler wont do silly aliasing games */ + barrier(); + skb->ip_defrag_offset = offset;

/* Insert this fragment in the chain of fragments. */ skb->next = next; @@ -431,11 +429,6 @@ found: else qp->q.fragments = skb;

- dev = skb->dev; - if (dev) { - qp->iif = dev->ifindex; - skb->dev = NULL; - } qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; qp->ecn |= ecn; @@ -511,7 +504,7 @@ static int ip_frag_reasm(struct ipq *qp, }

WARN_ON(!head); - WARN_ON(FRAG_CB(head)->offset != 0); + WARN_ON(head->ip_defrag_offset != 0);

/* Allocate a new buffer for the datagram. */ ihlen = ip_hdrlen(head); @@ -678,7 +671,7 @@ struct sk_buff *ip_check_defrag(struct n EXPORT_SYMBOL(ip_check_defrag);

#ifdef CONFIG_SYSCTL -static long zero; +static int dist_min;

static struct ctl_table ip4_frags_ns_ctl_table[] = { { @@ -695,7 +688,6 @@ static struct ctl_table ip4_frags_ns_ctl .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, .extra2 = &init_net.ipv4.frags.high_thresh }, { @@ -724,7 +716,7 @@ static struct ctl_table ip4_frags_ctl_ta .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .extra1 = &dist_min, }, { } }; --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -64,7 +64,6 @@ struct nf_ct_frag6_skb_cb static struct inet_frags nf_frags;

#ifdef CONFIG_SYSCTL -static long zero;

static struct ctl_table nf_ct_frag6_sysctl_table[] = { { @@ -80,7 +79,6 @@ static struct ctl_table nf_ct_frag6_sysc .maxlen = sizeof(unsigned long), .mode = 0644, .proc_handler = proc_doulongvec_minmax, - .extra1 = &zero, .extra2 = &init_net.nf_frag.frags.high_thresh }, { --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -547,7 +547,6 @@ static const struct inet6_protocol frag_ };

#ifdef CONFIG_SYSCTL -static int zero;

static struct ctl_table ip6_frags_ns_ctl_table[] = { { @@ -563,8 +562,7 @@ static struct ctl_table ip6_frags_ns_ctl .data = &init_net.ipv6.frags.low_thresh, .maxlen = sizeof(unsigned long), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero, + .proc_handler = proc_doulongvec_minmax, .extra2 = &init_net.ipv6.frags.high_thresh }, {

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Peter Oskolkov posk@google.com

commit 385114dec8a49b5e5945e77ba7de6356106713f4 upstream.

Tested: see the next patch is the series.

Suggested-by: Eric Dumazet edumazet@google.com Signed-off-by: Peter Oskolkov posk@google.com Signed-off-by: Eric Dumazet edumazet@google.com Cc: Florian Westphal fw@strlen.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Mao Wenan maowenan@huawei.com Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/skbuff.h | 2 +- net/core/skbuff.c | 6 +++++- 2 files changed, 6 insertions(+), 2 deletions(-)

--- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2278,7 +2278,7 @@ static inline void __skb_queue_purge(str kfree_skb(skb); }

-void skb_rbtree_purge(struct rb_root *root); +unsigned int skb_rbtree_purge(struct rb_root *root);

void *netdev_alloc_frag(unsigned int fragsz);

--- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2380,23 +2380,27 @@ EXPORT_SYMBOL(skb_queue_purge); /** * skb_rbtree_purge - empty a skb rbtree * @root: root of the rbtree to empty + * Return value: the sum of truesizes of all purged skbs. * * Delete all buffers on an &sk_buff rbtree. Each buffer is removed from * the list and one reference dropped. This function does not take * any lock. Synchronization should be handled by the caller (e.g., TCP * out-of-order queue is protected by the socket lock). */ -void skb_rbtree_purge(struct rb_root *root) +unsigned int skb_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); + sum += skb->truesize; kfree_skb(skb); } + return sum; }

/**

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 88078d98d1bb085d72af8437707279e203524fa5 upstream.

After working on IP defragmentation lately, I found that some large packets defeat CHECKSUM_COMPLETE optimization because of NIC adding zero paddings on the last (small) fragment.

While removing the padding with pskb_trim_rcsum(), we set skb->ip_summed to CHECKSUM_NONE, forcing a full csum validation, even if all prior fragments had CHECKSUM_COMPLETE set.

We can instead compute the checksum of the part we are trimming, usually smaller than the part we keep.

Signed-off-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/linux/skbuff.h | 5 ++--- net/core/skbuff.c | 14 ++++++++++++++ 2 files changed, 16 insertions(+), 3 deletions(-)

--- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2796,6 +2796,7 @@ static inline unsigned char *skb_push_rc return skb->data; }

+int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim @@ -2810,9 +2811,7 @@ static inline int pskb_trim_rcsum(struct { if (likely(len >= skb->len)) return 0; - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = CHECKSUM_NONE; - return __pskb_trim(skb, len); + return pskb_trim_rcsum_slow(skb, len); }

#define rb_to_skb(rb) rb_entry_safe(rb, struct sk_buff, rbnode) --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1502,6 +1502,20 @@ done: } EXPORT_SYMBOL(___pskb_trim);

+/* Note : use pskb_trim_rcsum() instead of calling this directly + */ +int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) { + int delta = skb->len - len; + + skb->csum = csum_sub(skb->csum, + skb_checksum(skb, len, delta, 0)); + } + return __pskb_trim(skb, len); +} +EXPORT_SYMBOL(pskb_trim_rcsum_slow); + /** * __pskb_pull_tail - advance tail of skb header * @skb: buffer to reallocate

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Peter Oskolkov posk@google.com

commit 353c9cb360874e737fb000545f783df756c06f9a upstream.

This patch introduces several helper functions/macros that will be used in the follow-up patch. No runtime changes yet.

The new logic (fully implemented in the second patch) is as follows:

* Nodes in the rb-tree will now contain not single fragments, but lists of consecutive fragments ("runs").

* At each point in time, the current "active" run at the tail is maintained/tracked. Fragments that arrive in-order, adjacent to the previous tail fragment, are added to this tail run without triggering the re-balancing of the rb-tree.

* If a fragment arrives out of order with the offset _before_ the tail run, it is inserted into the rb-tree as a single fragment.

* If a fragment arrives after the current tail fragment (with a gap), it starts a new "tail" run, as is inserted into the rb-tree at the end as the head of the new run.

skb->cb is used to store additional information needed here (suggested by Eric Dumazet).

Reported-by: Willem de Bruijn willemb@google.com Signed-off-by: Peter Oskolkov posk@google.com Cc: Eric Dumazet edumazet@google.com Cc: Florian Westphal fw@strlen.de Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Mao Wenan maowenan@huawei.com Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- include/net/inet_frag.h | 6 +++ net/ipv4/ip_fragment.c | 73 ++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 79 insertions(+)

--- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -55,7 +55,9 @@ struct frag_v6_compare_key { * @lock: spinlock protecting this frag * @refcnt: reference count of the queue * @fragments: received fragments head + * @rb_fragments: received fragments rb-tree root * @fragments_tail: received fragments tail + * @last_run_head: the head of the last "run". see ip_fragment.c * @stamp: timestamp of the last received fragment * @len: total length of the original datagram * @meat: length of received fragments so far @@ -76,6 +78,7 @@ struct inet_frag_queue { struct sk_buff *fragments; /* Used in IPv6. */ struct rb_root rb_fragments; /* Used in IPv4. */ struct sk_buff *fragments_tail; + struct sk_buff *last_run_head; ktime_t stamp; int len; int meat; @@ -112,6 +115,9 @@ void inet_frag_kill(struct inet_frag_que void inet_frag_destroy(struct inet_frag_queue *q); struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key);

+/* Free all skbs in the queue; return the sum of their truesizes. */ +unsigned int inet_frag_rbtree_purge(struct rb_root *root); + static inline void inet_frag_put(struct inet_frag_queue *q) { if (atomic_dec_and_test(&q->refcnt)) --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -58,6 +58,57 @@ static int sysctl_ipfrag_max_dist __read_mostly = 64; static const char ip_frag_cache_name[] = "ip4-frags";

+/* 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 { + struct inet_skb_parm h; + struct sk_buff *next_frag; + int frag_run_len; +}; + +#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) + +static void ip4_frag_init_run(struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); + + FRAG_CB(skb)->next_frag = NULL; + FRAG_CB(skb)->frag_run_len = skb->len; +} + +/* Append skb to the last "run". */ +static void ip4_frag_append_to_last_run(struct inet_frag_queue *q, + struct sk_buff *skb) +{ + RB_CLEAR_NODE(&skb->rbnode); + FRAG_CB(skb)->next_frag = NULL; + + 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 ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *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); + + ip4_frag_init_run(skb); + q->fragments_tail = skb; + q->last_run_head = skb; +} + /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; @@ -658,6 +709,28 @@ struct sk_buff *ip_check_defrag(struct n } EXPORT_SYMBOL(ip_check_defrag);

+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); + #ifdef CONFIG_SYSCTL static int dist_min;

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Taehee Yoo ap420073@gmail.com

commit 5d407b071dc369c26a38398326ee2be53651cfe4 upstream.

A kernel crash occurrs when defragmented packet is fragmented in ip_do_fragment(). In defragment routine, skb_orphan() is called and skb->ip_defrag_offset is set. but skb->sk and skb->ip_defrag_offset are same union member. so that frag->sk is not NULL. Hence crash occurrs in skb->sk check routine in ip_do_fragment() when defragmented packet is fragmented.

test commands: %iptables -t nat -I POSTROUTING -j MASQUERADE %hping3 192.168.4.2 -s 1000 -p 2000 -d 60000

splat looks like: [ 261.069429] kernel BUG at net/ipv4/ip_output.c:636! [ 261.075753] invalid opcode: 0000 [#1] SMP DEBUG_PAGEALLOC KASAN PTI [ 261.083854] CPU: 1 PID: 1349 Comm: hping3 Not tainted 4.19.0-rc2+ #3 [ 261.100977] RIP: 0010:ip_do_fragment+0x1613/0x2600 [ 261.106945] Code: e8 e2 38 e3 fe 4c 8b 44 24 18 48 8b 74 24 08 e9 92 f6 ff ff 80 3c 02 00 0f 85 da 07 00 00 48 8b b5 d0 00 00 00 e9 25 f6 ff ff <0f> 0b 0f 0b 44 8b 54 24 58 4c 8b 4c 24 18 4c 8b 5c 24 60 4c 8b 6c [ 261.127015] RSP: 0018:ffff8801031cf2c0 EFLAGS: 00010202 [ 261.134156] RAX: 1ffff1002297537b RBX: ffffed0020639e6e RCX: 0000000000000004 [ 261.142156] RDX: 0000000000000000 RSI: 0000000000000000 RDI: ffff880114ba9bd8 [ 261.150157] RBP: ffff880114ba8a40 R08: ffffed0022975395 R09: ffffed0022975395 [ 261.158157] R10: 0000000000000001 R11: ffffed0022975394 R12: ffff880114ba9ca4 [ 261.166159] R13: 0000000000000010 R14: ffff880114ba9bc0 R15: dffffc0000000000 [ 261.174169] FS: 00007fbae2199700(0000) GS:ffff88011b400000(0000) knlGS:0000000000000000 [ 261.183012] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 261.189013] CR2: 00005579244fe000 CR3: 0000000119bf4000 CR4: 00000000001006e0 [ 261.198158] Call Trace: [ 261.199018] ? dst_output+0x180/0x180 [ 261.205011] ? save_trace+0x300/0x300 [ 261.209018] ? ip_copy_metadata+0xb00/0xb00 [ 261.213034] ? sched_clock_local+0xd4/0x140 [ 261.218158] ? kill_l4proto+0x120/0x120 [nf_conntrack] [ 261.223014] ? rt_cpu_seq_stop+0x10/0x10 [ 261.227014] ? find_held_lock+0x39/0x1c0 [ 261.233008] ip_finish_output+0x51d/0xb50 [ 261.237006] ? ip_fragment.constprop.56+0x220/0x220 [ 261.243011] ? nf_ct_l4proto_register_one+0x5b0/0x5b0 [nf_conntrack] [ 261.250152] ? rcu_is_watching+0x77/0x120 [ 261.255010] ? nf_nat_ipv4_out+0x1e/0x2b0 [nf_nat_ipv4] [ 261.261033] ? nf_hook_slow+0xb1/0x160 [ 261.265007] ip_output+0x1c7/0x710 [ 261.269005] ? ip_mc_output+0x13f0/0x13f0 [ 261.273002] ? __local_bh_enable_ip+0xe9/0x1b0 [ 261.278152] ? ip_fragment.constprop.56+0x220/0x220 [ 261.282996] ? nf_hook_slow+0xb1/0x160 [ 261.287007] raw_sendmsg+0x21f9/0x4420 [ 261.291008] ? dst_output+0x180/0x180 [ 261.297003] ? sched_clock_cpu+0x126/0x170 [ 261.301003] ? find_held_lock+0x39/0x1c0 [ 261.306155] ? stop_critical_timings+0x420/0x420 [ 261.311004] ? check_flags.part.36+0x450/0x450 [ 261.315005] ? _raw_spin_unlock_irq+0x29/0x40 [ 261.320995] ? _raw_spin_unlock_irq+0x29/0x40 [ 261.326142] ? cyc2ns_read_end+0x10/0x10 [ 261.330139] ? raw_bind+0x280/0x280 [ 261.334138] ? sched_clock_cpu+0x126/0x170 [ 261.338995] ? check_flags.part.36+0x450/0x450 [ 261.342991] ? __lock_acquire+0x4500/0x4500 [ 261.348994] ? inet_sendmsg+0x11c/0x500 [ 261.352989] ? dst_output+0x180/0x180 [ 261.357012] inet_sendmsg+0x11c/0x500 [ ... ]

v2: - clear skb->sk at reassembly routine.(Eric Dumarzet)

Fixes: fa0f527358bd ("ip: use rb trees for IP frag queue.") Suggested-by: Eric Dumazet edumazet@google.com Signed-off-by: Taehee Yoo ap420073@gmail.com Reviewed-by: Eric Dumazet edumazet@google.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Mao Wenan maowenan@huawei.com Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/ip_fragment.c | 1 + net/ipv6/netfilter/nf_conntrack_reasm.c | 1 + 2 files changed, 2 insertions(+)

--- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -599,6 +599,7 @@ static int ip_frag_reasm(struct ipq *qp, 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) --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -427,6 +427,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, else if (head->ip_summed == CHECKSUM_COMPLETE) head->csum = csum_add(head->csum, fp->csum); head->truesize += fp->truesize; + fp->sk = NULL; } sub_frag_mem_limit(fq->q.net, head->truesize);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Eric Dumazet edumazet@google.com

commit 0d5b9311baf27bb545f187f12ecfd558220c607d upstream.

Multiple cpus might attempt to insert a new fragment in rhashtable, if for example RPS is buggy, as reported by 배석진 in https://patchwork.ozlabs.org/patch/994601/

We use rhashtable_lookup_get_insert_key() instead of rhashtable_insert_fast() to let cpus losing the race free their own inet_frag_queue and use the one that was inserted by another cpu.

Fixes: 648700f76b03 ("inet: frags: use rhashtables for reassembly units") Signed-off-by: Eric Dumazet edumazet@google.com Reported-by: 배석진 soukjin.bae@samsung.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/inet_fragment.c | 28 +++++++++++++++------------- 1 file changed, 15 insertions(+), 13 deletions(-)

--- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -188,21 +188,22 @@ static struct inet_frag_queue *inet_frag }

static struct inet_frag_queue *inet_frag_create(struct netns_frags *nf, - void *arg) + void *arg, + struct inet_frag_queue **prev) { struct inet_frags *f = nf->f; struct inet_frag_queue *q; - int err;

q = inet_frag_alloc(nf, f, arg); - if (!q) + if (!q) { + *prev = ERR_PTR(-ENOMEM); return NULL; - + } mod_timer(&q->timer, jiffies + nf->timeout);

- err = rhashtable_insert_fast(&nf->rhashtable, &q->node, - f->rhash_params); - if (err < 0) { + *prev = rhashtable_lookup_get_insert_key(&nf->rhashtable, &q->key, + &q->node, f->rhash_params); + if (*prev) { q->flags |= INET_FRAG_COMPLETE; inet_frag_kill(q); inet_frag_destroy(q); @@ -215,17 +216,18 @@ EXPORT_SYMBOL(inet_frag_create); /* TODO : call from rcu_read_lock() and no longer use refcount_inc_not_zero() */ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) { - struct inet_frag_queue *fq; + struct inet_frag_queue *fq = NULL, *prev;

rcu_read_lock(); - fq = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); - if (fq) { + prev = rhashtable_lookup(&nf->rhashtable, key, nf->f->rhash_params); + if (!prev) + fq = inet_frag_create(nf, key, &prev); + if (prev && !IS_ERR(prev)) { + fq = prev; if (!atomic_inc_not_zero(&fq->refcnt)) fq = NULL; - rcu_read_unlock(); - return fq; } rcu_read_unlock(); - return inet_frag_create(nf, key); + return fq; } EXPORT_SYMBOL(inet_frag_find);

4.4-stable review patch. If anyone has any objections, please let me know.

------------------

From: Michal Kubecek mkubecek@suse.cz

commit ade446403bfb79d3528d56071a84b15351a139ad upstream.

Since commit 7969e5c40dfd ("ip: discard IPv4 datagrams with overlapping segments.") IPv4 reassembly code drops the whole queue whenever an overlapping fragment is received. However, the test is written in a way which detects duplicate fragments as overlapping so that in environments with many duplicate packets, fragmented packets may be undeliverable.

Add an extra test and for (potentially) duplicate fragment, only drop the new fragment rather than the whole queue. Only starting offset and length are checked, not the contents of the fragments as that would be too expensive. For similar reason, linear list ("run") of a rbtree node is not iterated, we only check if the new fragment is a subset of the interval covered by existing consecutive fragments.

v2: instead of an exact check iterating through linear list of an rbtree node, only check if the new fragment is subset of the "run" (suggested by Eric Dumazet)

Fixes: 7969e5c40dfd ("ip: discard IPv4 datagrams with overlapping segments.") Signed-off-by: Michal Kubecek mkubecek@suse.cz Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Mao Wenan maowenan@huawei.com [bwh: Backported to 4.4: - goto discard_qp, not err, in case of overlap - Set err earlier variable, as done upstream in commit 0ff89efb5246 "ip: fail fast on IP defrag errors"] Signed-off-by: Ben Hutchings ben.hutchings@codethink.co.uk Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/ipv4/ip_fragment.c | 20 +++++++++++++------- 1 file changed, 13 insertions(+), 7 deletions(-)

--- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -347,10 +347,10 @@ static int ip_frag_queue(struct ipq *qp, struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct rb_node **rbn, *parent; struct sk_buff *skb1, *prev_tail; + int ihl, end, skb1_run_end; struct net_device *dev; unsigned int fragsize; int flags, offset; - int ihl, end; int err = -ENOENT; u8 ecn;

@@ -420,9 +420,12 @@ static int ip_frag_queue(struct ipq *qp, * overlapping fragment, the entire datagram (and any constituent * fragments) MUST be silently discarded. * - * We do the same here for IPv4 (and increment an snmp counter). + * We do the same here for IPv4 (and increment an snmp counter) but + * we do not want to drop the whole queue in response to a duplicate + * fragment. */

+ err = -EINVAL; /* Find out where to put this fragment. */ prev_tail = qp->q.fragments_tail; if (!prev_tail) @@ -444,13 +447,17 @@ static int ip_frag_queue(struct ipq *qp, do { parent = *rbn; skb1 = rb_to_skb(parent); + skb1_run_end = skb1->ip_defrag_offset + + FRAG_CB(skb1)->frag_run_len; if (end <= skb1->ip_defrag_offset) rbn = &parent->rb_left; - else if (offset >= skb1->ip_defrag_offset + - FRAG_CB(skb1)->frag_run_len) + else if (offset >= skb1_run_end) rbn = &parent->rb_right; - else /* Found an overlap with skb1. */ - goto discard_qp; + else if (offset >= skb1->ip_defrag_offset && + end <= skb1_run_end) + goto err; /* No new data, potential duplicate */ + else + goto discard_qp; /* Found an overlap */ } while (*rbn); /* Here we have parent properly set, and rbn pointing to * one of its NULL left/right children. Insert skb. @@ -495,7 +502,6 @@ static int ip_frag_queue(struct ipq *qp,

discard_qp: inet_frag_kill(&qp->q); - err = -EINVAL; IP_INC_STATS_BH(net, IPSTATS_MIB_REASM_OVERLAPS); err: kfree_skb(skb);