netfilter: ipset fixes
Subsystems (2)
cover netfilter: ipset fixes
Hi Pablo,
Here follows the tentative fixes for the current list of ipset related issues. I'll take into account sashiko reports and after that submit the final versions. Thanks!
Best regards,
Jozsef
Jozsef Kadlecsik (5):
netfilter: ipset: Fix data race between add and list header in all
hash types
netfilter: ipset: Fix data race between add and dump in all hash types
netfilter: ipset: annotate "pos" for concurrent readers/writers
netfilter: ipset: skip gc when resize is in progress
netfilter: ipset: fix order of usage counters
net/netfilter/ipset/ip_set_core.c | 4 +- net/netfilter/ipset/ip_set_hash_gen.h | 69 +++++++++++++++++---------- 2 files changed, 47 insertions(+), 26 deletions(-)
Signature · 1 line
2.39.5
PATCH 1/5 netfilter: ipset: Fix data race between add and list header in all hash types
The "ipset list -terse" command is actually a dump operation which may run parallel with "ipset add" commands, which can trigger an internal resizing of the hash type of sets just being dumped. However, dumping just the header part of the set was not protected against underlying resizing. Fix it by protecting the header dumping part as well.
--- net/netfilter/ipset/ip_set_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/netfilter/ipset/ip_set_core.c +2 -2
@@ -1648,13 +1648,13 @@ ip_set_dump_do(struct sk_buff *skb, struct netlink_callback *cb)if (cb->args[IPSET_CB_PROTO ] >IPSET_PROTOCOL_MIN &&nla_put_net16 (skb,IPSET_ATTR_INDEX ,htons (index))) goto nla_put_failure; +if (set->variant->uref) + set->variant->uref (set, cb, true); ret = set->variant->head (set, skb);if (ret <0 ) goto release_refcount;if (dump_flags &IPSET_FLAG_LIST_HEADER ) goto next_set; -if (set->variant->uref) - set->variant->uref (set, cb, true); fallthrough;default : ret = set->variant->list (set, skb, cb);
Signature · 1 line
2.39.5
PATCH 2/5 netfilter: ipset: Fix data race between add and dump in all hash types
In reply to Jozsef KadlecsikWhen adding a new entry to the next position in the existing hash bucket, the position index was incremented too early and parallel dump could read it before the entry was populated with the value. Move the setting of the position index after populating the entry.
v2: Position counting fixed, noticed by Florian Westphal.
--- net/netfilter/ipset/ip_set_hash_gen.h | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-)
net/netfilter/ipset/ip_set_hash_gen.h +5 -2
@@ -844,7 +844,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,const struct mtype_elem *d = value;struct mtype_elem *data;struct hbucket *n, *old =ERR_PTR (-ENOENT ); -int i, j =-1 , ret; +int i, j =-1 , npos =0 , ret;bool flag_exist = flags &IPSET_FLAG_EXIST ;bool deleted = false, forceadd = false, reuse = false;u32 r, key, multi =0 , elements, maxelem;
@@ -889,6 +889,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,ext_size (AHASH_INIT_SIZE , set->dsize); goto copy_elem; } + npos = n->pos;for (i =0 ; i < n->pos; i++) {if (!test_bit (i, n->used)) {/* Reuse first deleted entry */
@@ -962,7 +963,8 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, } copy_elem: - j = n->pos++; + j = npos; + npos = n->pos +1 ; data =ahash_data (n, j, set->dsize); copy_data: t->hregion[r].elements++;
@@ -985,6 +987,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,if (SET_WITH_TIMEOUT (set))ip_set_timeout_set (ext_timeout (data, set), ext->timeout);smp_mb__before_atomic (); + n->pos = npos;set_bit (j, n->used);if (old !=ERR_PTR (-ENOENT )) {rcu_assign_pointer (hbucket (t, key), n);
Signature · 1 line
2.39.5
PATCH 3/5 netfilter: ipset: annotate "pos" for concurrent readers/writers
In reply to Jozsef KadlecsikThe "pos" structure member of struct hbucket stores the first free slot in the hash bucket of a hash type of set and there are concurrent readers/writers. Annotate accesses properly.
--- net/netfilter/ipset/ip_set_hash_gen.h | 64 ++++++++++++++++----------- 1 file changed, 38 insertions(+), 26 deletions(-)
net/netfilter/ipset/ip_set_hash_gen.h +38 -26
@@ -386,8 +386,9 @@ static void mtype_ext_cleanup(struct ip_set *set, struct hbucket *n) { int i; +u8 pos =smp_load_acquire (&n->pos); -for (i =0 ; i < n->pos; i++) +for (i =0 ; i < pos; i++)if (test_bit (i, n->used))ip_set_ext_destroy (set,ahash_data (n, i, set->dsize)); }
@@ -490,7 +491,7 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r)#ifdef IP_SET_HASH_WITH_NETS u8 k;#endif -u8 htable_bits = t->htable_bits; +u8 pos, htable_bits = t->htable_bits;spin_lock_bh (&t->hregion[r].lock); for (i = ahash_bucket_start(r, htable_bits);
@@ -498,7 +499,8 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) n =__ipset_dereference (hbucket (t, i));if (!n)continue ; -for (j =0 , d =0 ; j < n->pos; j++) { + pos =smp_load_acquire (&n->pos); +for (j =0 , d =0 ; j < pos; j++) {if (!test_bit (j, n->used)) { d++;continue ;
@@ -534,7 +536,7 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r)/* Still try to delete expired elements. */ continue ; tmp->size = n->size -AHASH_INIT_SIZE ; -for (j =0 , d =0 ; j < n->pos; j++) { +for (j =0 , d =0 ; j < pos; j++) {if (!test_bit (j, n->used))continue ; data =ahash_data (n, j, dsize);
@@ -623,7 +625,7 @@ mtype_resize(struct ip_set *set, bool retried) {struct htype *h = set->data;struct htable *t, *orig; -u8 htable_bits; +u8 pos, htable_bits;size_t hsize, dsize = set->dsize;#ifdef IP_SET_HASH_WITH_NETS u8 flags;
@@ -685,7 +687,8 @@ mtype_resize(struct ip_set *set, bool retried) n =__ipset_dereference (hbucket (orig, i));if (!n)continue ; -for (j =0 ; j < n->pos; j++) { + pos =smp_load_acquire (&n->pos); +for (j =0 ; j < pos; j++) {if (!test_bit (j, n->used))continue ; data =ahash_data (n, j, dsize);
@@ -809,9 +812,10 @@ mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) {struct htype *h = set->data;const struct htable *t; -u32 i, j, r;struct hbucket *n;struct mtype_elem *data; +u32 i, j, r; +u8 pos; t =rcu_dereference_bh (h->table);for (r =0 ; r <ahash_numof_locks (t->htable_bits); r++) {
@@ -820,7 +824,8 @@ mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) n =rcu_dereference_bh (hbucket (t, i));if (!n)continue ; -for (j =0 ; j < n->pos; j++) { + pos =smp_load_acquire (&n->pos); +for (j =0 ; j < pos; j++) {if (!test_bit (j, n->used))continue ; data =ahash_data (n, j, set->dsize);
@@ -844,10 +849,11 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,const struct mtype_elem *d = value;struct mtype_elem *data;struct hbucket *n, *old =ERR_PTR (-ENOENT ); -int i, j =-1 , npos =0 , ret; +int i, j =-1 , ret;bool flag_exist = flags &IPSET_FLAG_EXIST ;bool deleted = false, forceadd = false, reuse = false;u32 r, key, multi =0 , elements, maxelem; +u8 npos =0 ;rcu_read_lock_bh (); t =rcu_dereference_bh (h->table);
@@ -889,8 +895,8 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,ext_size (AHASH_INIT_SIZE , set->dsize); goto copy_elem; } - npos = n->pos; -for (i =0 ; i < n->pos; i++) { + npos =smp_load_acquire (&n->pos);; +for (i =0 ; i < npos; i++) {if (!test_bit (i, n->used)) {/* Reuse first deleted entry */ if (j ==-1 ) {
@@ -934,7 +940,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,if (elements >= maxelem) goto set_full;/* Create a new slot */ -if (n->pos >= n->size) { +if (npos >= n->size) {#ifdef IP_SET_HASH_WITH_MULTI if (h->bucketsize >=AHASH_MAX_TUNED ) goto set_full;
@@ -963,8 +969,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, } copy_elem: - j = npos; - npos = n->pos +1 ; + j = npos++; data =ahash_data (n, j, set->dsize); copy_data: t->hregion[r].elements++;
@@ -986,8 +991,8 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,/* Must come last for the case when timed out entry is reused */ if (SET_WITH_TIMEOUT (set))ip_set_timeout_set (ext_timeout (data, set), ext->timeout); -smp_mb__before_atomic (); - n->pos = npos; +/* Ensure all data writes are visible before updating position */ +smp_store_release (&n->pos, npos);set_bit (j, n->used);if (old !=ERR_PTR (-ENOENT )) {rcu_assign_pointer (hbucket (t, key), n);
@@ -1046,6 +1051,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,int i, j, k, r, ret = -IPSET_ERR_EXIST ;u32 key, multi =0 ;size_t dsize = set->dsize; +u8 pos;/* Userspace add and resize is excluded by the mutex. * Kernespace add does not trigger resize.
@@ -1061,7 +1067,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, n =rcu_dereference_bh (hbucket (t, key));if (!n) goto out; -for (i =0 , k =0 ; i < n->pos; i++) { + pos =smp_load_acquire (&n->pos); +for (i =0 , k =0 ; i < pos; i++) {if (!test_bit (i, n->used)) { k++;continue ;
@@ -1074,9 +1081,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, ret =0 ;clear_bit (i, n->used); -smp_mb__after_atomic (); -if (i +1 == n->pos) - n->pos--; +if (i +1 == pos) +smp_store_release (&n->pos, --pos) t->hregion[r].elements--;#ifdef IP_SET_HASH_WITH_NETS for (j =0 ; j <IPSET_NET_COUNT ; j++)
@@ -1097,11 +1103,11 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, x->flags = flags; } } -for (; i < n->pos; i++) { +for (; i < pos; i++) {if (!test_bit (i, n->used)) k++; } -if (n->pos ==0 && k ==0 ) { +if (pos ==0 && k ==0 ) { t->hregion[r].ext_size -=ext_size (n->size, dsize);rcu_assign_pointer (hbucket (t, key),NULL );kfree_rcu (n, rcu);
@@ -1112,7 +1118,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext,if (!tmp) goto out; tmp->size = n->size -AHASH_INIT_SIZE ; -for (j =0 , k =0 ; j < n->pos; j++) { +for (j =0 , k =0 ; j < pos; j++) {if (!test_bit (j, n->used))continue ; data =ahash_data (n, j, dsize);
@@ -1173,6 +1179,7 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,int ret, i, j =0 ;#endif u32 key, multi =0 ; +u8 pos;pr_debug ("test by nets\n" );for (; j <NLEN && h->nets[j].cidr[0 ] && !multi; j++) {
@@ -1190,7 +1197,8 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d, n =rcu_dereference_bh (hbucket (t, key));if (!n)continue ; -for (i =0 ; i < n->pos; i++) { + pos =smp_load_acquire (&n->pos); +for (i =0 ; i < pos; i++) {if (!test_bit (i, n->used))continue ; data =ahash_data (n, i, set->dsize);
@@ -1224,6 +1232,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext,struct mtype_elem *data;int i, ret =0 ;u32 key, multi =0 ; +u8 pos;rcu_read_lock_bh (); t =rcu_dereference_bh (h->table);
@@ -1246,7 +1255,8 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, ret =0 ; goto out; } -for (i =0 ; i < n->pos; i++) { + pos =smp_load_acquire (&n->pos); +for (i =0 ; i < pos; i++) {if (!test_bit (i, n->used))continue ; data =ahash_data (n, i, set->dsize);
@@ -1363,6 +1373,7 @@ mtype_list(const struct ip_set *set,/* We assume that one hash bucket fills into one page */ void *incomplete;int i, ret =0 ; +u8 pos; atd =nla_nest_start (skb,IPSET_ATTR_ADT );if (!atd)
@@ -1381,7 +1392,8 @@ mtype_list(const struct ip_set *set, cb->args[IPSET_CB_ARG0], t, n);if (!n)continue ; -for (i =0 ; i < n->pos; i++) { + pos =smp_load_acquire (&n->pos); +for (i =0 ; i < pos; i++) {if (!test_bit (i, n->used))continue ; e =ahash_data (n, i, set->dsize);
Signature · 1 line
2.39.5
PATCH 4/5 netfilter: ipset: skip gc when resize is in progress
In reply to Jozsef KadlecsikZhengchuan Liang reported that because resize does not copy the comment extension into the resized set but uses it's pointer, ongoing gc can free the extension in the original set which then results stale pointer in the resized one. The proposed patch was to recreate the extensions for every element in the resized set. It is both expensive and wastes memory, so better skip gc when resizing in progress detected: resizing will destroy the original set anyway, so doing gc on it unnecessary.
Reported by: Zhengchuan Liang <[email protected]>
--- net/netfilter/ipset/ip_set_hash_gen.h | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
net/netfilter/ipset/ip_set_hash_gen.h +7 -1
@@ -508,6 +508,8 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) data =ahash_data (n, j, dsize);if (!ip_set_timeout_expired (ext_timeout (data, set)))continue ; +if (atomic_read (&t->ref)) + goto resize_in_progress;pr_debug ("expired %u/%u\n" , i, j);clear_bit (j, n->used);smp_mb__after_atomic ();
@@ -552,6 +554,7 @@ mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r)kfree_rcu (n, rcu); } } +resize_in_progress:spin_unlock_bh (&t->hregion[r].lock); }
@@ -672,7 +675,10 @@ mtype_resize(struct ip_set *set, bool retried)spin_lock_init (&t->hregion[i].lock);/* There can't be another parallel resizing, -* but dumping, gc, kernel side add/del are possible +* but dumping, kernel side add/del are possible. +* gc must detect ongoing resize when comments are in use +* in order not to free the comment extension area shared +* between the original and resized sets. */ orig =ipset_dereference_bh_nfnl (h->table);atomic_set (&orig->ref,1 );
Signature · 1 line
2.39.5
PATCH 5/5 netfilter: ipset: fix order of usage counters
In reply to Jozsef KadlecsikEulgyu Kim reported a slab-use-after-free issue when resizing a set and gc runs in parallel. Resizing may run parallel with already running gc or gc can start but notice that resizing started. The operation which finishes last must destroy the original set. The logic for the testing is: "I was the last user of the set and it was resized". However setting the counters in resizing was: "the set will be resized and I'm going to use the set". That created a small racing window at the testing phase. Fix the order in the resizing functions.
Reported by: Eulgyu Kim <[email protected]>
--- net/netfilter/ipset/ip_set_hash_gen.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/netfilter/ipset/ip_set_hash_gen.h +1 -1
@@ -681,8 +681,8 @@ mtype_resize(struct ip_set *set, bool retried)* between the original and resized sets. */ orig =ipset_dereference_bh_nfnl (h->table); -atomic_set (&orig->ref,1 );atomic_inc (&orig->uref); +atomic_set (&orig->ref,1 );pr_debug ("attempt to resize set %s from %u to %u, t %p\n" , set->name, orig->htable_bits, htable_bits, orig);for (r =0 ; r <ahash_numof_locks (orig->htable_bits); r++) {
Signature · 1 line
2.39.5