netfilter: nf_tables: use timestamp to check for set element timeout

[ Upstream commit 7395dfacfff65e9938ac0889dafa1ab01e987d15 ]

Add a timestamp field at the beginning of the transaction, store it
in the nftables per-netns area.

Update set backend .insert, .deactivate and sync gc path to use the
timestamp, this avoids that an element expires while control plane
transaction is still unfinished.

.lookup and .update, which are used from packet path, still use the
current time to check if the element has expired. And .get path and dump
also since this runs lockless under rcu read size lock. Then, there is
async gc which also needs to check the current time since it runs
asynchronously from a workqueue.

Fixes: c3e1b005ed1c ("netfilter: nf_tables: add set element timeout support")
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 4e8ecabc5f25cc5db474c864bee2ee89819e9e1c..62013d018411567b6e3aa0ccbeab5d4fb28b0d7b 100644 (file)
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -798,10 +798,16 @@ static inline struct nft_set_elem_expr *nft_set_ext_expr(const struct nft_set_ex
        return nft_set_ext(ext, NFT_SET_EXT_EXPRESSIONS);
 }
 
-static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
+static inline bool __nft_set_elem_expired(const struct nft_set_ext *ext,
+                                         u64 tstamp)
 {
        return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) &&
-              time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext));
+              time_after_eq64(tstamp, *nft_set_ext_expiration(ext));
+}
+
+static inline bool nft_set_elem_expired(const struct nft_set_ext *ext)
+{
+       return __nft_set_elem_expired(ext, get_jiffies_64());
 }
 
 static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set,
@@ -1750,6 +1756,7 @@ struct nftables_pernet {
        struct list_head        notify_list;
        struct mutex            commit_mutex;
        u64                     table_handle;
+       u64                     tstamp;
        unsigned int            base_seq;
        unsigned int            gc_seq;
        u8                      validate_state;
@@ -1762,6 +1769,11 @@ static inline struct nftables_pernet *nft_pernet(const struct net *net)
        return net_generic(net, nf_tables_net_id);
 }
 
+static inline u64 nft_net_tstamp(const struct net *net)
+{
+       return nft_pernet(net)->tstamp;
+}
+
 #define __NFT_REDUCE_READONLY  1UL
 #define NFT_REDUCE_READONLY    (void *)__NFT_REDUCE_READONLY
 

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 0e07f110a539bf4a24d202e81252e9f27a4e7c85..04c5aa4debc740725572fcd887fabb781b904fab 100644 (file)
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -9744,6 +9744,7 @@ dead_elem:
 struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
 {
        struct nft_set_elem_catchall *catchall, *next;
+       u64 tstamp = nft_net_tstamp(gc->net);
        const struct nft_set *set = gc->set;
        struct nft_elem_priv *elem_priv;
        struct nft_set_ext *ext;
@@ -9753,7 +9754,7 @@ struct nft_trans_gc *nft_trans_gc_catchall_sync(struct nft_trans_gc *gc)
        list_for_each_entry_safe(catchall, next, &set->catchall_list, list) {
                ext = nft_set_elem_ext(set, catchall->elem);
 
-               if (!nft_set_elem_expired(ext))
+               if (!__nft_set_elem_expired(ext, tstamp))
                        continue;
 
                gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);
@@ -10539,6 +10540,7 @@ static bool nf_tables_valid_genid(struct net *net, u32 genid)
        bool genid_ok;
 
        mutex_lock(&nft_net->commit_mutex);
+       nft_net->tstamp = get_jiffies_64();
 
        genid_ok = genid == 0 || nft_net->base_seq == genid;
        if (!genid_ok)

diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c
index 6c2061bfdae6c361c530088ca51aa2790d850ba4..6968a3b342367c6c0cb0df7523fdfd5864038802 100644 (file)
--- a/net/netfilter/nft_set_hash.c
+++ b/net/netfilter/nft_set_hash.c
@@ -36,6 +36,7 @@ struct nft_rhash_cmp_arg {
        const struct nft_set            *set;
        const u32                       *key;
        u8                              genmask;
+       u64                             tstamp;
 };
 
 static inline u32 nft_rhash_key(const void *data, u32 len, u32 seed)
@@ -62,7 +63,7 @@ static inline int nft_rhash_cmp(struct rhashtable_compare_arg *arg,
                return 1;
        if (nft_set_elem_is_dead(&he->ext))
                return 1;
-       if (nft_set_elem_expired(&he->ext))
+       if (__nft_set_elem_expired(&he->ext, x->tstamp))
                return 1;
        if (!nft_set_elem_active(&he->ext, x->genmask))
                return 1;
@@ -87,6 +88,7 @@ bool nft_rhash_lookup(const struct net *net, const struct nft_set *set,
                .genmask = nft_genmask_cur(net),
                .set     = set,
                .key     = key,
+               .tstamp  = get_jiffies_64(),
        };
 
        he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -106,6 +108,7 @@ nft_rhash_get(const struct net *net, const struct nft_set *set,
                .genmask = nft_genmask_cur(net),
                .set     = set,
                .key     = elem->key.val.data,
+               .tstamp  = get_jiffies_64(),
        };
 
        he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -131,6 +134,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key,
                .genmask = NFT_GENMASK_ANY,
                .set     = set,
                .key     = key,
+               .tstamp  = get_jiffies_64(),
        };
 
        he = rhashtable_lookup(&priv->ht, &arg, nft_rhash_params);
@@ -175,6 +179,7 @@ static int nft_rhash_insert(const struct net *net, const struct nft_set *set,
                .genmask = nft_genmask_next(net),
                .set     = set,
                .key     = elem->key.val.data,
+               .tstamp  = nft_net_tstamp(net),
        };
        struct nft_rhash_elem *prev;
 
@@ -216,6 +221,7 @@ nft_rhash_deactivate(const struct net *net, const struct nft_set *set,
                .genmask = nft_genmask_next(net),
                .set     = set,
                .key     = elem->key.val.data,
+               .tstamp  = nft_net_tstamp(net),
        };
 
        rcu_read_lock();

diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
index a65617cd8e2e5a086473236d414ff20ed96d5995..ffce43e14561af07c57dda049e5b25236f65750d 100644 (file)
--- a/net/netfilter/nft_set_pipapo.c
+++ b/net/netfilter/nft_set_pipapo.c
@@ -504,6 +504,7 @@ out:
  * @set:       nftables API set representation
  * @data:      Key data to be matched against existing elements
  * @genmask:   If set, check that element is active in given genmask
+ * @tstamp:    timestamp to check for expired elements
  *
  * This is essentially the same as the lookup function, except that it matches
  * key data against the uncommitted copy and doesn't use preallocated maps for
@@ -513,7 +514,8 @@ out:
  */
 static struct nft_pipapo_elem *pipapo_get(const struct net *net,
                                          const struct nft_set *set,
-                                         const u8 *data, u8 genmask)
+                                         const u8 *data, u8 genmask,
+                                         u64 tstamp)
 {
        struct nft_pipapo_elem *ret = ERR_PTR(-ENOENT);
        struct nft_pipapo *priv = nft_set_priv(set);
@@ -566,7 +568,7 @@ next_match:
                        goto out;
 
                if (last) {
-                       if (nft_set_elem_expired(&f->mt[b].e->ext))
+                       if (__nft_set_elem_expired(&f->mt[b].e->ext, tstamp))
                                goto next_match;
                        if ((genmask &&
                             !nft_set_elem_active(&f->mt[b].e->ext, genmask)))
@@ -606,7 +608,7 @@ nft_pipapo_get(const struct net *net, const struct nft_set *set,
        struct nft_pipapo_elem *e;
 
        e = pipapo_get(net, set, (const u8 *)elem->key.val.data,
-                      nft_genmask_cur(net));
+                      nft_genmask_cur(net), get_jiffies_64());
        if (IS_ERR(e))
                return ERR_CAST(e);
 
@@ -1173,6 +1175,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
        struct nft_pipapo_match *m = priv->clone;
        u8 genmask = nft_genmask_next(net);
        struct nft_pipapo_elem *e, *dup;
+       u64 tstamp = nft_net_tstamp(net);
        struct nft_pipapo_field *f;
        const u8 *start_p, *end_p;
        int i, bsize_max, err = 0;
@@ -1182,7 +1185,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
        else
                end = start;
 
-       dup = pipapo_get(net, set, start, genmask);
+       dup = pipapo_get(net, set, start, genmask, tstamp);
        if (!IS_ERR(dup)) {
                /* Check if we already have the same exact entry */
                const struct nft_data *dup_key, *dup_end;
@@ -1204,7 +1207,7 @@ static int nft_pipapo_insert(const struct net *net, const struct nft_set *set,
 
        if (PTR_ERR(dup) == -ENOENT) {
                /* Look for partially overlapping entries */
-               dup = pipapo_get(net, set, end, nft_genmask_next(net));
+               dup = pipapo_get(net, set, end, nft_genmask_next(net), tstamp);
        }
 
        if (PTR_ERR(dup) != -ENOENT) {
@@ -1560,6 +1563,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
 {
        struct nft_pipapo *priv = nft_set_priv(set);
        struct net *net = read_pnet(&set->net);
+       u64 tstamp = nft_net_tstamp(net);
        int rules_f0, first_rule = 0;
        struct nft_pipapo_elem *e;
        struct nft_trans_gc *gc;
@@ -1594,7 +1598,7 @@ static void pipapo_gc(struct nft_set *set, struct nft_pipapo_match *m)
                /* synchronous gc never fails, there is no need to set on
                 * NFT_SET_ELEM_DEAD_BIT.
                 */
-               if (nft_set_elem_expired(&e->ext)) {
+               if (__nft_set_elem_expired(&e->ext, tstamp)) {
                        priv->dirty = true;
 
                        gc = nft_trans_gc_queue_sync(gc, GFP_ATOMIC);
@@ -1769,7 +1773,7 @@ static void *pipapo_deactivate(const struct net *net, const struct nft_set *set,
 {
        struct nft_pipapo_elem *e;
 
-       e = pipapo_get(net, set, data, nft_genmask_next(net));
+       e = pipapo_get(net, set, data, nft_genmask_next(net), nft_net_tstamp(net));
        if (IS_ERR(e))
                return NULL;
 

diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index baa3fea4fe65c8f938e665a7fb6b0e4fc0f8f9ad..5fd74f993988f0c8478cd7258355c4eea90cc2e4 100644 (file)
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -313,6 +313,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
        struct nft_rbtree *priv = nft_set_priv(set);
        u8 cur_genmask = nft_genmask_cur(net);
        u8 genmask = nft_genmask_next(net);
+       u64 tstamp = nft_net_tstamp(net);
        int d;
 
        /* Descend the tree to search for an existing element greater than the
@@ -360,7 +361,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
                /* perform garbage collection to avoid bogus overlap reports
                 * but skip new elements in this transaction.
                 */
-               if (nft_set_elem_expired(&rbe->ext) &&
+               if (__nft_set_elem_expired(&rbe->ext, tstamp) &&
                    nft_set_elem_active(&rbe->ext, cur_genmask)) {
                        const struct nft_rbtree_elem *removed_end;
 
@@ -551,6 +552,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
        const struct nft_rbtree *priv = nft_set_priv(set);
        const struct rb_node *parent = priv->root.rb_node;
        u8 genmask = nft_genmask_next(net);
+       u64 tstamp = nft_net_tstamp(net);
        int d;
 
        while (parent != NULL) {
@@ -571,7 +573,7 @@ nft_rbtree_deactivate(const struct net *net, const struct nft_set *set,
                                   nft_rbtree_interval_end(this)) {
                                parent = parent->rb_right;
                                continue;
-                       } else if (nft_set_elem_expired(&rbe->ext)) {
+                       } else if (__nft_set_elem_expired(&rbe->ext, tstamp)) {
                                break;
                        } else if (!nft_set_elem_active(&rbe->ext, genmask)) {
                                parent = parent->rb_left;
@@ -624,9 +626,10 @@ static void nft_rbtree_gc(struct nft_set *set)
 {
        struct nft_rbtree *priv = nft_set_priv(set);
        struct nft_rbtree_elem *rbe, *rbe_end = NULL;
+       struct net *net = read_pnet(&set->net);
+       u64 tstamp = nft_net_tstamp(net);
        struct rb_node *node, *next;
        struct nft_trans_gc *gc;
-       struct net *net;
 
        set  = nft_set_container_of(priv);
        net  = read_pnet(&set->net);
@@ -648,7 +651,7 @@ static void nft_rbtree_gc(struct nft_set *set)
                        rbe_end = rbe;
                        continue;
                }
-               if (!nft_set_elem_expired(&rbe->ext))
+               if (!__nft_set_elem_expired(&rbe->ext, tstamp))
                        continue;
 
                gc = nft_trans_gc_queue_sync(gc, GFP_KERNEL);