netfilter: ipset fixes, second batch
Subsystems (2)
v3 cover netfilter: ipset fixes, second batch
Hi Pablo,
Here follows the updated patches for the second batch. I left out some potential issues (like torn read in reuse/forceadd cases), those will be handled later.
Best regards,
Jozsef
Jozsef Kadlecsik (7):
netfilter: ipset: Don't use test_bit() in lockless RCU readers in hash
types
netfilter: ipset: Don't use test_bit() in lockless RCU readers in
bitmap types
netfilter: ipset: fix order of kfree_rcu() and rcu_assign_pointer()
netfilter: ipset: exlude gc when resize is in progress
netfilter: ipset: make sure gc is properly stopped
netfilter: ipset: cleanup the add/del backlog when resize failed
netfilter: ipset: rework cidr bookkeeping
net/netfilter/ipset/ip_set_bitmap_gen.h | 4 +- net/netfilter/ipset/ip_set_bitmap_ip.c | 2 +- net/netfilter/ipset/ip_set_bitmap_ipmac.c | 2 +- net/netfilter/ipset/ip_set_bitmap_port.c | 2 +- net/netfilter/ipset/ip_set_core.c | 4 +- net/netfilter/ipset/ip_set_hash_gen.h | 96 ++++++++++++++------ net/netfilter/ipset/ip_set_hash_ipportnet.c | 4 +- net/netfilter/ipset/ip_set_hash_net.c | 4 +- net/netfilter/ipset/ip_set_hash_netiface.c | 4 +- net/netfilter/ipset/ip_set_hash_netnet.c | 8 +- net/netfilter/ipset/ip_set_hash_netport.c | 4 +- net/netfilter/ipset/ip_set_hash_netportnet.c | 8 +- 12 files changed, 90 insertions(+), 52 deletions(-)
Signature · 1 line
2.39.5
PATCH v3 1/7 netfilter: ipset: Don't use test_bit() in lockless RCU readers in hash types
Sashiko pointed out that there are a few lockless RCU readers using test_bit() which is a relaxed atomic operation and provides no memory barrier guarantees. Use test_bit_acquire() instead where the operation may run parallel with add/del/gc, i.e. is not one from the next cases
- protected by region lock
- in a set destroy phase
- in a new/temporary set creation phase
--- net/netfilter/ipset/ip_set_hash_gen.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-)
net/netfilter/ipset/ip_set_hash_gen.h +5 -5
@@ -689,7 +689,7 @@ mtype_resize(struct ip_set *set, bool retried)continue ; pos =smp_load_acquire (&n->pos);for (j =0 ; j < pos; j++) { -if (!test_bit (j, n->used)) +if (!test_bit_acquire (j, n->used))continue ; data =ahash_data (n, j, dsize);if (SET_ELEM_EXPIRED (set, data))
@@ -826,7 +826,7 @@ mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size)continue ; pos =smp_load_acquire (&n->pos);for (j =0 ; j < pos; j++) { -if (!test_bit (j, n->used)) +if (!test_bit_acquire (j, n->used))continue ; data =ahash_data (n, j, set->dsize);if (!SET_ELEM_EXPIRED (set, data))
@@ -1201,7 +1201,7 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,continue ; pos =smp_load_acquire (&n->pos);for (i =0 ; i < pos; i++) { -if (!test_bit (i, n->used)) +if (!test_bit_acquire (i, n->used))continue ; data =ahash_data (n, i, set->dsize);if (!mtype_data_equal (data, d, &multi))
@@ -1259,7 +1259,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, } pos =smp_load_acquire (&n->pos);for (i =0 ; i < pos; i++) { -if (!test_bit (i, n->used)) +if (!test_bit_acquire (i, n->used))continue ; data =ahash_data (n, i, set->dsize);if (!mtype_data_equal (data, d, &multi))
@@ -1396,7 +1396,7 @@ mtype_list(const struct ip_set *set,continue ; pos =smp_load_acquire (&n->pos);for (i =0 ; i < pos; i++) { -if (!test_bit (i, n->used)) +if (!test_bit_acquire (i, n->used))continue ; e =ahash_data (n, i, set->dsize);if (SET_ELEM_EXPIRED (set, e))
Signature · 1 line
2.39.5
PATCH v3 2/7 netfilter: ipset: Don't use test_bit() in lockless RCU readers in bitmap types
In reply to Jozsef KadlecsikThe pair of the patch "netfilter: ipset: Don't use test_bit() in lockless RCU readers in hash types" for the bitmap types.
--- net/netfilter/ipset/ip_set_bitmap_gen.h | 4 +++- net/netfilter/ipset/ip_set_bitmap_ip.c | 2 +- net/netfilter/ipset/ip_set_bitmap_ipmac.c | 2 +- net/netfilter/ipset/ip_set_bitmap_port.c | 2 +- 4 files changed, 6 insertions(+), 4 deletions(-)
net/netfilter/ipset/ip_set_bitmap_gen.h +3 -1
@@ -165,6 +165,7 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,ip_set_init_skbinfo (ext_skbinfo (x, set), ext);/* Activate element */ +smp_mb__before_atomic ();set_bit (e->id, map->members); set->elements++;
@@ -219,7 +220,7 @@ mtype_list(const struct ip_set *set,cond_resched_rcu (); id = cb->args[IPSET_CB_ARG0 ]; x =get_ext (set, map, id); - if (!test_bit(id, map->members) || + if (!test_bit_acquire(id, map->members) || (SET_WITH_TIMEOUT(set) && #ifdef IP_SET_BITMAP_STORED_TIMEOUT mtype_is_filled(x) &&
@@ -278,6 +279,7 @@ mtype_gc(struct timer_list *t) x =get_ext (set, map, id);if (ip_set_timeout_expired (ext_timeout (x, set))) {clear_bit (id, map->members); +smp_mb__after_atomic ();ip_set_ext_destroy (set, x); set->elements--; }
net/netfilter/ipset/ip_set_bitmap_ip.c +1 -1
@@ -67,7 +67,7 @@ static int bitmap_ip_do_test(const struct bitmap_ip_adt_elem *e, struct bitmap_ip *map, size_t dsize) { - return !!test_bit(e->id, map->members); + return !!test_bit_acquire(e->id, map->members); } static int
net/netfilter/ipset/ip_set_bitmap_ipmac.c +1 -1
@@ -86,7 +86,7 @@ bitmap_ipmac_do_test(const struct bitmap_ipmac_adt_elem *e, {const struct bitmap_ipmac_elem *elem; -if (!test_bit (e->id, map->members)) +if (!test_bit_acquire (e->id, map->members))return 0 ; elem =get_const_elem (map->extensions, e->id, dsize);if (e->add_mac && elem->filled ==MAC_FILLED )
net/netfilter/ipset/ip_set_bitmap_port.c +1 -1
@@ -58,7 +58,7 @@ static int bitmap_port_do_test(const struct bitmap_port_adt_elem *e, const struct bitmap_port *map, size_t dsize) { - return !!test_bit(e->id, map->members); + return !!test_bit_acquire(e->id, map->members); } static int
Signature · 1 line
2.39.5
PATCH v3 3/7 netfilter: ipset: fix order of kfree_rcu() and rcu_assign_pointer()
In reply to Jozsef KadlecsikSashiko pointed out that kfree_rcu() was called before rcu_assign_pointer() in handling the comment extension. Fix the order so that rcu_assign_pointer() called first.
--- net/netfilter/ipset/ip_set_core.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
net/netfilter/ipset/ip_set_core.c +2 -2
@@ -351,8 +351,8 @@ ip_set_init_comment(struct ip_set *set, struct ip_set_comment *comment,if (unlikely (c)) { set->ext_size -=sizeof (*c) +strlen (c->str) +1 ; -kfree_rcu (c, rcu);rcu_assign_pointer (comment->c,NULL ); +kfree_rcu (c, rcu); }if (!len)return ;
@@ -393,8 +393,8 @@ ip_set_comment_free(struct ip_set *set, void *ptr)if (unlikely (!c))return ; set->ext_size -=sizeof (*c) +strlen (c->str) +1 ; -kfree_rcu (c, rcu);rcu_assign_pointer (comment->c,NULL ); +kfree_rcu (c, rcu); }typedef void (*destroyer )(struct ip_set *,void *);
Signature · 1 line
2.39.5
PATCH v3 4/7 netfilter: ipset: exlude 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 exclude gc when resizing in progress detected: resizing will destroy the original set anyway, so doing gc on it is unnecessary.
Reported by: Zhengchuan Liang <[email protected]> Reported by: Eulgyu Kim <[email protected]>
--- net/netfilter/ipset/ip_set_hash_gen.h | 20 ++++++++++++++++---- 1 file changed, 16 insertions(+), 4 deletions(-)
net/netfilter/ipset/ip_set_hash_gen.h +16 -4
@@ -84,6 +84,7 @@ struct htable {atomic_t uref;/* References for dumping and gc */ u8 htable_bits;/* size of hash table == 2^htable_bits */ u32 maxelem;/* Maxelem per region */ +spinlock_t gc_lock;/* Lock to exclude gc and resize */ struct ip_set_region *hregion;/* Region locks and ext sizes */ struct hbucket __rcu *bucket[];/* hashtable buckets */ };
@@ -569,7 +570,7 @@ mtype_gc(struct work_struct *work) set = gc->set; h = set->data; -spin_lock_bh (&set->lock); +rcu_read_lock_bh (); t =ipset_dereference_set (h->table, set);atomic_inc (&t->uref); numof_locks =ahash_numof_locks (t->htable_bits);
@@ -580,9 +581,11 @@ mtype_gc(struct work_struct *work) next_run = (IPSET_GC_PERIOD (set->timeout) *HZ ) / numof_locks;if (next_run <HZ /10 ) next_run =HZ /10 ; -spin_unlock_bh (&set->lock); +rcu_read_unlock_bh (); +spin_lock_bh (&t->gc_lock);mtype_gc_do (set, h, t, r); +spin_unlock_bh (&t->gc_lock);if (atomic_dec_and_test (&t->uref) &&atomic_read (&t->ref)) {pr_debug ("Table destroy after resize by expire: %p\n" , t);
@@ -679,6 +682,7 @@ mtype_resize(struct ip_set *set, bool retried)atomic_inc (&orig->uref);pr_debug ("attempt to resize set %s from %u to %u, t %p\n" , set->name, orig->htable_bits, htable_bits, orig); +spin_lock_bh (&orig->gc_lock);for (r =0 ; r <ahash_numof_locks (orig->htable_bits); r++) {/* Expire may replace a hbucket with another one */ rcu_read_lock_bh ();
@@ -692,8 +696,13 @@ mtype_resize(struct ip_set *set, bool retried)if (!test_bit_acquire (j, n->used))continue ; data =ahash_data (n, j, dsize); -if (SET_ELEM_EXPIRED (set, data)) -continue ; +/* Parallel gc is excluded so we copy +* the already expired elements too. +* - If resize succeeds next gc on new +* hash will purge the entries. +* - If resize fails next gc on the +* original hash will do the cleanup. +*/ #ifdef IP_SET_HASH_WITH_NETS /* We have readers running parallel with us, * so the live data cannot be modified.
@@ -755,6 +764,7 @@ mtype_resize(struct ip_set *set, bool retried) }rcu_read_unlock_bh (); } +spin_unlock_bh (&orig->gc_lock);/* There can't be any other writer. */ rcu_assign_pointer (h->table, t);
@@ -792,6 +802,7 @@ mtype_resize(struct ip_set *set, bool retried) cleanup:rcu_read_unlock_bh (); +spin_unlock_bh (&orig->gc_lock);atomic_set (&orig->ref,0 );atomic_dec (&orig->uref);mtype_ahash_destroy (set, t, false);
@@ -1619,6 +1630,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, } t->htable_bits = hbits; t->maxelem = h->maxelem /ahash_numof_locks (hbits); +spin_lock_init (&t->gc_lock);RCU_INIT_POINTER (h->table, t);INIT_LIST_HEAD (&h->ad);
Signature · 1 line
2.39.5
PATCH v3 5/7 netfilter: ipset: make sure gc is properly stopped
In reply to Jozsef KadlecsikSashiko noticed that when destroying a set, cancel_delayed_work_sync() was called while gc calls queue_delayed_work() unconditionally which can lead not to properly shutting down the gc.
--- 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
@@ -609,7 +609,7 @@ mtype_cancel_gc(struct ip_set *set)struct htype *h = set->data;if (SET_WITH_TIMEOUT (set)) -cancel_delayed_work_sync (&h->gc.dwork); +disable_delayed_work_sync (&h->gc.dwork); } static int
Signature · 1 line
2.39.5
PATCH v3 6/7 netfilter: ipset: cleanup the add/del backlog when resize failed
In reply to Jozsef KadlecsikSashiko pointed out that the add/del backlog was not cleaned up when resize failed. Fix it in the corresponding error path.
--- net/netfilter/ipset/ip_set_hash_gen.h | 9 +++++++++ 1 file changed, 9 insertions(+)
net/netfilter/ipset/ip_set_hash_gen.h +9 -0
@@ -803,8 +803,17 @@ mtype_resize(struct ip_set *set, bool retried) cleanup:rcu_read_unlock_bh ();spin_unlock_bh (&orig->gc_lock); + +/* We have to exclude add/del */ +spin_lock_bh (&set->lock);atomic_set (&orig->ref,0 );atomic_dec (&orig->uref); +/* Cleanup the backlog of ADD/DEL elements */ +list_for_each_safe (l, lt, &h->ad) { +list_del (l); +kfree (l); + } +spin_unlock_bh (&set->lock);mtype_ahash_destroy (set, t, false);if (ret == -EAGAIN ) goto retry;
Signature · 1 line
2.39.5
PATCH v3 7/7 netfilter: ipset: rework cidr bookkeeping
In reply to Jozsef KadlecsikAccording to sashiko, the current bookkeeping of cidr values are unsafe on weakly-ordered architectures. Use active/backup cidr tables: at updates the backup table is refreshed and after it is completed, the reference to the tables are swapped.
--- net/netfilter/ipset/ip_set_hash_gen.h | 55 +++++++++++++------- net/netfilter/ipset/ip_set_hash_ipportnet.c | 4 +- net/netfilter/ipset/ip_set_hash_net.c | 4 +- net/netfilter/ipset/ip_set_hash_netiface.c | 4 +- net/netfilter/ipset/ip_set_hash_netnet.c | 8 +-- net/netfilter/ipset/ip_set_hash_netport.c | 4 +- net/netfilter/ipset/ip_set_hash_netportnet.c | 8 +-- 7 files changed, 51 insertions(+), 36 deletions(-)
net/netfilter/ipset/ip_set_hash_gen.h +35 -20
@@ -142,6 +142,8 @@ htable_size(u8 hbits)#define INIT_CIDR (cidr, host_mask) \ DCIDR_PUT(((cidr) ? NCIDR_GET(cidr) : host_mask)) +#define FIRST_CIDR (h, n) \ + h->abnets[h->active][0].cidr[n]#ifdef IP_SET_HASH_WITH_NET0 /* cidr from 0 to HOST_MASK value and c = cidr + 1 */
@@ -305,7 +307,8 @@ struct htype {struct list_head ad;/* Resize add|del backlist */ struct mtype_elem next;/* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_NETS -struct net_prefixes nets[NLEN ];/* book-keeping of prefixes */ +struct net_prefixes abnets[2 ][NLEN ];/* book-keeping of prefixes */ +u8 active;/* active slot */ #endif };
@@ -326,26 +329,31 @@ struct mtype_resize_ad {static void mtype_add_cidr (struct ip_set *set,struct htype *h,u8 cidr,u8 n) { +struct net_prefixes (*anets)[NLEN ] = &h->abnets[h->active]; +struct net_prefixes (*bnets)[NLEN ] = &h->abnets[!h->active];int i, j;spin_lock_bh (&set->lock);/* Add in increasing prefix order, so larger cidr first */ -for (i =0 , j =-1 ; i <NLEN && h->nets[i].cidr[n]; i++) { +for (i =0 , j =-1 ; i <NLEN && (*anets)[i].cidr[n]; i++) {if (j !=-1 ) {continue ; - }else if (h->nets[i].cidr[n] < cidr) { + }else if ((*anets)[i].cidr[n] < cidr) { j = i; - }else if (h->nets[i].cidr[n] == cidr) { - h->nets[CIDR_POS (cidr)].nets[n]++; + }else if ((*anets)[i].cidr[n] == cidr) { + (*anets)[CIDR_POS (cidr)].nets[n]++; goto unlock; } } +memcpy (bnets, anets,sizeof (*bnets));if (j !=-1 ) {for (; i > j; i--) - h->nets[i].cidr[n] = h->nets[i -1 ].cidr[n]; + (*bnets)[i].cidr[n] = (*bnets)[i -1 ].cidr[n]; } - h->nets[i].cidr[n] = cidr; - h->nets[CIDR_POS (cidr)].nets[n] =1 ; + (*bnets)[i].cidr[n] = cidr; + (*bnets)[CIDR_POS (cidr)].nets[n] =1 ; +smp_wmb (); + h->active = !h->active; unlock:spin_unlock_bh (&set->lock); }
@@ -353,18 +361,23 @@ mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n)static void mtype_del_cidr (struct ip_set *set,struct htype *h,u8 cidr,u8 n) { +struct net_prefixes (*anets)[NLEN ] = &h->abnets[h->active]; +struct net_prefixes (*bnets)[NLEN ] = &h->abnets[!h->active];u8 i, j, net_end =NLEN -1 ;spin_lock_bh (&set->lock);for (i =0 ; i <NLEN ; i++) { -if (h->nets[i].cidr[n] != cidr) +if ((*anets)[i].cidr[n] != cidr)continue ; - h->nets[CIDR_POS (cidr)].nets[n]--; -if (h->nets[CIDR_POS (cidr)].nets[n] >0 ) + (*anets)[CIDR_POS (cidr)].nets[n]--; +if ((*anets)[CIDR_POS (cidr)].nets[n] >0 ) goto unlock; -for (j = i; j < net_end && h->nets[j].cidr[n]; j++) - h->nets[j].cidr[n] = h->nets[j +1 ].cidr[n]; - h->nets[j].cidr[n] =0 ; +memcpy (bnets, anets,sizeof (*bnets)); +for (j = i; j < net_end && (*bnets)[j].cidr[n]; j++) + (*bnets)[j].cidr[n] = (*bnets)[j +1 ].cidr[n]; + (*bnets)[j].cidr[n] =0 ; +smp_wmb (); + h->active = !h->active; goto unlock; } unlock:
@@ -422,7 +435,8 @@ mtype_flush(struct ip_set *set)spin_unlock_bh (&t->hregion[r].lock); }#ifdef IP_SET_HASH_WITH_NETS -memset (h->nets,0 ,sizeof (h->nets)); +memset (&h->abnets,0 ,sizeof (h->abnets)); + h->active =0 ;#endif }
@@ -1194,6 +1208,7 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,struct htable *t =rcu_dereference_bh (h->table);struct hbucket *n;struct mtype_elem *data; +struct net_prefixes (*nets)[NLEN ] = &h->abnets[h->active];#if IPSET_NET_COUNT ==2 struct mtype_elem orig = *d;int ret, i, j =0 , k;
@@ -1204,16 +1219,16 @@ mtype_test_cidrs(struct ip_set *set, struct mtype_elem *d,u8 pos;pr_debug ("test by nets\n" ); -for (; j <NLEN && h->nets[j].cidr[0 ] && !multi; j++) { +for (; j <NLEN && (*nets)[j].cidr[0 ] && !multi; j++) {#if IPSET_NET_COUNT ==2 mtype_data_reset_elem (d, &orig); -mtype_data_netmask (d,NCIDR_GET (h->nets[j].cidr[0 ]), false); -for (k =0 ; k <NLEN && h->nets[k].cidr[1 ] && !multi; +mtype_data_netmask (d,NCIDR_GET ((*nets)[j].cidr[0 ]), false); +for (k =0 ; k <NLEN && (*nets)[k].cidr[1 ] && !multi; k++) { -mtype_data_netmask (d,NCIDR_GET (h->nets[k].cidr[1 ]), +mtype_data_netmask (d,NCIDR_GET ((*nets)[k].cidr[1 ]), true);#else -mtype_data_netmask (d,NCIDR_GET (h->nets[j].cidr[0 ])); +mtype_data_netmask (d,NCIDR_GET ((*nets)[j].cidr[0 ]));#endif key =HKEY (d, h->initval, t->htable_bits); n =rcu_dereference_bh (hbucket (t, key));
net/netfilter/ipset/ip_set_hash_ipportnet.c +2 -2
@@ -138,7 +138,7 @@ hash_ipportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,const struct hash_ipportnet4 *h = set->data;ipset_adtfn adtfn = set->variant->adt[adt];struct hash_ipportnet4_elem e = { - .cidr =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ), + .cidr =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ), };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set);
@@ -398,7 +398,7 @@ hash_ipportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,const struct hash_ipportnet6 *h = set->data;ipset_adtfn adtfn = set->variant->adt[adt];struct hash_ipportnet6_elem e = { - .cidr =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ), + .cidr =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ), };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set);
net/netfilter/ipset/ip_set_hash_net.c +2 -2
@@ -117,7 +117,7 @@ hash_net4_kadt(struct ip_set *set, const struct sk_buff *skb,const struct hash_net4 *h = set->data;ipset_adtfn adtfn = set->variant->adt[adt];struct hash_net4_elem e = { - .cidr =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ), + .cidr =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ), };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set);
@@ -291,7 +291,7 @@ hash_net6_kadt(struct ip_set *set, const struct sk_buff *skb,const struct hash_net6 *h = set->data;ipset_adtfn adtfn = set->variant->adt[adt];struct hash_net6_elem e = { - .cidr =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ), + .cidr =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ), };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set);
net/netfilter/ipset/ip_set_hash_netiface.c +2 -2
@@ -161,7 +161,7 @@ hash_netiface4_kadt(struct ip_set *set, const struct sk_buff *skb,struct hash_netiface4 *h = set->data;ipset_adtfn adtfn = set->variant->adt[adt];struct hash_netiface4_elem e = { - .cidr =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ), + .cidr =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ), .elem =1 , };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set);
@@ -382,7 +382,7 @@ hash_netiface6_kadt(struct ip_set *set, const struct sk_buff *skb,struct hash_netiface6 *h = set->data;ipset_adtfn adtfn = set->variant->adt[adt];struct hash_netiface6_elem e = { - .cidr =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ), + .cidr =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ), .elem =1 , };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set);
net/netfilter/ipset/ip_set_hash_netnet.c +4 -4
@@ -149,8 +149,8 @@ hash_netnet4_kadt(struct ip_set *set, const struct sk_buff *skb,struct hash_netnet4_elem e = { };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set); - e.cidr[0 ] =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ); - e.cidr[1 ] =INIT_CIDR (h->nets[0 ].cidr[1 ],HOST_MASK ); + e.cidr[0 ] =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ); + e.cidr[1 ] =INIT_CIDR (FIRST_CIDR (h,1 ),HOST_MASK );if (adt ==IPSET_TEST ) e.ccmp = (HOST_MASK << (sizeof (e.cidr[0 ]) *8 )) |HOST_MASK ;
@@ -388,8 +388,8 @@ hash_netnet6_kadt(struct ip_set *set, const struct sk_buff *skb,struct hash_netnet6_elem e = { };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set); - e.cidr[0 ] =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ); - e.cidr[1 ] =INIT_CIDR (h->nets[0 ].cidr[1 ],HOST_MASK ); + e.cidr[0 ] =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ); + e.cidr[1 ] =INIT_CIDR (FIRST_CIDR (h,1 ),HOST_MASK );if (adt ==IPSET_TEST ) e.ccmp = (HOST_MASK << (sizeof (u8) *8 )) |HOST_MASK ;
net/netfilter/ipset/ip_set_hash_netport.c +2 -2
@@ -133,7 +133,7 @@ hash_netport4_kadt(struct ip_set *set, const struct sk_buff *skb,const struct hash_netport4 *h = set->data;ipset_adtfn adtfn = set->variant->adt[adt];struct hash_netport4_elem e = { - .cidr =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ), + .cidr =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ), };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set);
@@ -353,7 +353,7 @@ hash_netport6_kadt(struct ip_set *set, const struct sk_buff *skb,const struct hash_netport6 *h = set->data;ipset_adtfn adtfn = set->variant->adt[adt];struct hash_netport6_elem e = { - .cidr =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ), + .cidr =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ), };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set);
net/netfilter/ipset/ip_set_hash_netportnet.c +4 -4
@@ -157,8 +157,8 @@ hash_netportnet4_kadt(struct ip_set *set, const struct sk_buff *skb,struct hash_netportnet4_elem e = { };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set); - e.cidr[0 ] =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ); - e.cidr[1 ] =INIT_CIDR (h->nets[0 ].cidr[1 ],HOST_MASK ); + e.cidr[0 ] =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ); + e.cidr[1 ] =INIT_CIDR (FIRST_CIDR (h,1 ),HOST_MASK );if (adt ==IPSET_TEST ) e.ccmp = (HOST_MASK << (sizeof (e.cidr[0 ]) *8 )) |HOST_MASK ;
@@ -452,8 +452,8 @@ hash_netportnet6_kadt(struct ip_set *set, const struct sk_buff *skb,struct hash_netportnet6_elem e = { };struct ip_set_ext ext =IP_SET_INIT_KEXT (skb, opt, set); - e.cidr[0 ] =INIT_CIDR (h->nets[0 ].cidr[0 ],HOST_MASK ); - e.cidr[1 ] =INIT_CIDR (h->nets[0 ].cidr[1 ],HOST_MASK ); + e.cidr[0 ] =INIT_CIDR (FIRST_CIDR (h,0 ),HOST_MASK ); + e.cidr[1 ] =INIT_CIDR (FIRST_CIDR (h,1 ),HOST_MASK );if (adt ==IPSET_TEST ) e.ccmp = (HOST_MASK << (sizeof (u8) *8 )) |HOST_MASK ;
Signature · 1 line
2.39.5
syzbot ci has tested the following series
syzbot ci has tested the following series
[v3] netfilter: ipset fixes, second batch
https://lore.kernel.org/all/[email protected]
* [PATCH v3 1/7] netfilter: ipset: Don't use test_bit() in lockless RCU readers in hash types
* [PATCH v3 2/7] netfilter: ipset: Don't use test_bit() in lockless RCU readers in bitmap types
* [PATCH v3 3/7] netfilter: ipset: fix order of kfree_rcu() and rcu_assign_pointer()
* [PATCH v3 4/7] netfilter: ipset: exlude gc when resize is in progress
* [PATCH v3 5/7] netfilter: ipset: make sure gc is properly stopped
* [PATCH v3 6/7] netfilter: ipset: cleanup the add/del backlog when resize failed
* [PATCH v3 7/7] netfilter: ipset: rework cidr bookkeeping
and found the following issues:
* INFO: trying to register non-static key in hash_ipportip6_resize
* INFO: trying to register non-static key in hash_netport6_resize
* INFO: trying to register non-static key in hash_netportnet6_resize
Full report is available here:
https://ci.syzbot.org/series/7264660b-3f58-4809-9af0-c77ead1aac16
***
INFO: trying to register non-static key in hash_ipportip6_resize
tree: nf-next URL: https://kernel.googlesource.com/pub/scm/linux/kernel/git/netfilter/nf-next.git base: 3b165c2a29cfb6453f26e1ac833ca6afd28d28cf arch: amd64 compiler: Debian clang version 21.1.8 (++20251221033036+2078da43e25a-1~exp1~20251221153213.50), Debian LLD 21.1.8 config: https://ci.syzbot.org/builds/44611eeb-52b4-4b97-8744-2265cbb063fa/config syz repro: https://ci.syzbot.org/findings/c1aaddfd-5ff4-410d-85fa-3c212552d465/syz_repro
INFO: trying to register non-static key.
The code is fine but needs lockdep annotation, or maybe you didn't initialize this object before use? turning off the locking correctness validator.
CPU: 0 UID: 0 PID: 5810 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 assign_lock_key+0x133/0x150 kernel/locking/lockdep.c:984 register_lock_class+0xcc/0x2e0 kernel/locking/lockdep.c:1299 __lock_acquire+0xad/0x2cf0 kernel/locking/lockdep.c:5112 lock_acquire+0x106/0x350 kernel/locking/lockdep.c:5868 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:150 [inline] _raw_spin_lock_bh+0x36/0x50 kernel/locking/spinlock.c:182 spin_lock_bh include/linux/spinlock.h:348 [inline] hash_ipportip6_resize+0x4d4/0x1dd0 net/netfilter/ipset/ip_set_hash_gen.h:699 call_ad+0x463/0xb60 net/netfilter/ipset/ip_set_core.c:1758 ip_set_ad+0x824/0x9d0 net/netfilter/ipset/ip_set_core.c:1842 nfnetlink_rcv_msg+0xc03/0x12c0 net/netfilter/nfnetlink.c:300 netlink_rcv_skb+0x232/0x4b0 net/netlink/af_netlink.c:2556 nfnetlink_rcv+0x2c0/0x27b0 net/netfilter/nfnetlink.c:667 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x75c/0x8e0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x813/0xb40 net/netlink/af_netlink.c:1900 sock_sendmsg_nosec net/socket.c:787 [inline] __sock_sendmsg net/socket.c:802 [inline] ____sys_sendmsg+0x972/0x9f0 net/socket.c:2699 ___sys_sendmsg+0x2a5/0x360 net/socket.c:2753 __sys_sendmsg net/socket.c:2785 [inline] __do_sys_sendmsg net/socket.c:2790 [inline] __se_sys_sendmsg net/socket.c:2788 [inline] __x64_sys_sendmsg+0x1bd/0x2a0 net/socket.c:2788 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x174/0x580 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f4ef2b9ce59 Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f4ef3b42028 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f4ef2e15fa0 RCX: 00007f4ef2b9ce59 RDX: 0000000000000000 RSI: 00002000000002c0 RDI: 0000000000000004 RBP: 00007f4ef2c32d6f R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f4ef2e16038 R14: 00007f4ef2e15fa0 R15: 00007ffd926dea58 </TASK>
***
INFO: trying to register non-static key in hash_netport6_resize
tree: nf-next URL: https://kernel.googlesource.com/pub/scm/linux/kernel/git/netfilter/nf-next.git base: 3b165c2a29cfb6453f26e1ac833ca6afd28d28cf arch: amd64 compiler: Debian clang version 21.1.8 (++20251221033036+2078da43e25a-1~exp1~20251221153213.50), Debian LLD 21.1.8 config: https://ci.syzbot.org/builds/44611eeb-52b4-4b97-8744-2265cbb063fa/config syz repro: https://ci.syzbot.org/findings/60d79dbd-6e73-4ee8-be39-8bea69cb5f52/syz_repro
INFO: trying to register non-static key.
The code is fine but needs lockdep annotation, or maybe you didn't initialize this object before use? turning off the locking correctness validator.
CPU: 0 UID: 0 PID: 5834 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 assign_lock_key+0x133/0x150 kernel/locking/lockdep.c:984 register_lock_class+0xcc/0x2e0 kernel/locking/lockdep.c:1299 __lock_acquire+0xad/0x2cf0 kernel/locking/lockdep.c:5112 lock_acquire+0x106/0x350 kernel/locking/lockdep.c:5868 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:150 [inline] _raw_spin_lock_bh+0x36/0x50 kernel/locking/spinlock.c:182 spin_lock_bh include/linux/spinlock.h:348 [inline] hash_netport6_resize+0x548/0x1d30 net/netfilter/ipset/ip_set_hash_gen.h:699 call_ad+0x463/0xb60 net/netfilter/ipset/ip_set_core.c:1758 ip_set_ad+0x824/0x9d0 net/netfilter/ipset/ip_set_core.c:1842 nfnetlink_rcv_msg+0xc03/0x12c0 net/netfilter/nfnetlink.c:300 netlink_rcv_skb+0x232/0x4b0 net/netlink/af_netlink.c:2556 nfnetlink_rcv+0x2c0/0x27b0 net/netfilter/nfnetlink.c:667 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x75c/0x8e0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x813/0xb40 net/netlink/af_netlink.c:1900 sock_sendmsg_nosec net/socket.c:787 [inline] __sock_sendmsg net/socket.c:802 [inline] ____sys_sendmsg+0x972/0x9f0 net/socket.c:2699 ___sys_sendmsg+0x2a5/0x360 net/socket.c:2753 __sys_sendmsg net/socket.c:2785 [inline] __do_sys_sendmsg net/socket.c:2790 [inline] __se_sys_sendmsg net/socket.c:2788 [inline] __x64_sys_sendmsg+0x1bd/0x2a0 net/socket.c:2788 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x174/0x580 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f5c11d9ce59 Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f5c113dd028 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f5c12016090 RCX: 00007f5c11d9ce59 RDX: 0000000000000090 RSI: 00002000000002c0 RDI: 0000000000000004 RBP: 00007f5c11e32d6f R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f5c12016128 R14: 00007f5c12016090 R15: 00007ffd4124a0a8 </TASK>
***
INFO: trying to register non-static key in hash_netportnet6_resize
tree: nf-next URL: https://kernel.googlesource.com/pub/scm/linux/kernel/git/netfilter/nf-next.git base: 3b165c2a29cfb6453f26e1ac833ca6afd28d28cf arch: amd64 compiler: Debian clang version 21.1.8 (++20251221033036+2078da43e25a-1~exp1~20251221153213.50), Debian LLD 21.1.8 config: https://ci.syzbot.org/builds/44611eeb-52b4-4b97-8744-2265cbb063fa/config syz repro: https://ci.syzbot.org/findings/a0e027e2-8833-4fe6-8f75-2f388682c035/syz_repro
INFO: trying to register non-static key.
The code is fine but needs lockdep annotation, or maybe you didn't initialize this object before use? turning off the locking correctness validator.
CPU: 0 UID: 0 PID: 5880 Comm: syz.0.17 Not tainted syzkaller #0 PREEMPT(full) Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.2-debian-1.16.2-1 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0xe8/0x150 lib/dump_stack.c:120 assign_lock_key+0x133/0x150 kernel/locking/lockdep.c:984 register_lock_class+0xcc/0x2e0 kernel/locking/lockdep.c:1299 __lock_acquire+0xad/0x2cf0 kernel/locking/lockdep.c:5112 lock_acquire+0x106/0x350 kernel/locking/lockdep.c:5868 __raw_spin_lock_bh include/linux/spinlock_api_smp.h:150 [inline] _raw_spin_lock_bh+0x36/0x50 kernel/locking/spinlock.c:182 spin_lock_bh include/linux/spinlock.h:348 [inline] hash_netportnet6_resize+0x5aa/0x2040 net/netfilter/ipset/ip_set_hash_gen.h:699 call_ad+0x463/0xb60 net/netfilter/ipset/ip_set_core.c:1758 ip_set_ad+0x824/0x9d0 net/netfilter/ipset/ip_set_core.c:1842 nfnetlink_rcv_msg+0xc03/0x12c0 net/netfilter/nfnetlink.c:300 netlink_rcv_skb+0x232/0x4b0 net/netlink/af_netlink.c:2556 nfnetlink_rcv+0x2c0/0x27b0 net/netfilter/nfnetlink.c:667 netlink_unicast_kernel net/netlink/af_netlink.c:1319 [inline] netlink_unicast+0x75c/0x8e0 net/netlink/af_netlink.c:1345 netlink_sendmsg+0x813/0xb40 net/netlink/af_netlink.c:1900 sock_sendmsg_nosec net/socket.c:787 [inline] __sock_sendmsg net/socket.c:802 [inline] ____sys_sendmsg+0x972/0x9f0 net/socket.c:2699 ___sys_sendmsg+0x2a5/0x360 net/socket.c:2753 __sys_sendmsg net/socket.c:2785 [inline] __do_sys_sendmsg net/socket.c:2790 [inline] __se_sys_sendmsg net/socket.c:2788 [inline] __x64_sys_sendmsg+0x1bd/0x2a0 net/socket.c:2788 do_syscall_x64 arch/x86/entry/syscall_64.c:63 [inline] do_syscall_64+0x174/0x580 arch/x86/entry/syscall_64.c:94 entry_SYSCALL_64_after_hwframe+0x77/0x7f RIP: 0033:0x7f9c00b9ce59 Code: ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e8 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007f9c01a82028 EFLAGS: 00000246 ORIG_RAX: 000000000000002e RAX: ffffffffffffffda RBX: 00007f9c00e15fa0 RCX: 00007f9c00b9ce59 RDX: 0000000000000000 RSI: 00002000000002c0 RDI: 0000000000000004 RBP: 00007f9c00c32d6f R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 00007f9c00e16038 R14: 00007f9c00e15fa0 R15: 00007ffe8ca45b58 </TASK>
***
If these findings have caused you to resend the series or submit a separate fix, please add the following tag to your commit message:
---
This report is generated by a bot. It may contain errors. syzbot ci engineers can be reached at [email protected].
To test a patch for this bug, please reply with #syz test (should be on a separate line).
The patch should be attached to the email.
Note: arguments like custom git repos and branches are not supported.