Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following patchset contains Netfilter fixes for net:

1) Fix gcc-10 compilation warning in nf_conntrack, from Arnd Bergmann.

2) Add NF_FLOW_HW_PENDING to avoid races between stats and deletion
   commands, from Paul Blakey.

3) Remove WQ_MEM_RECLAIM from the offload workqueue, from Roi Dayan.

4) Infinite loop when removing nf_conntrack module, from Florian Westphal.

5) Set NF_FLOW_TEARDOWN bit on expiration to avoid races when refreshing
   the timeout from the software path.

6) Missing nft_set_elem_expired() check in the rbtree, from Phil Sutter.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 40 insertions, 9 deletions

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 9f551f3b69c65f..90690e37a56f0e 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -87,7 +87,7 @@ struct nf_conn {
 	struct hlist_node	nat_bysource;
 #endif
 	/* all members below initialized via memset */
-	u8 __nfct_init_offset[0];
+	struct { } __nfct_init_offset;
 
 	/* If we were expected by an expectation, this will be it */
 	struct nf_conn *master;
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index 6bf69652f57df0..c54a7f707e5039 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -127,6 +127,7 @@ enum nf_flow_flags {
 	NF_FLOW_HW_DYING,
 	NF_FLOW_HW_DEAD,
 	NF_FLOW_HW_REFRESH,
+	NF_FLOW_HW_PENDING,
 };
 
 enum flow_offload_type {
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index c4582eb71766a1..1d57b95d348192 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -1519,9 +1519,9 @@ __nf_conntrack_alloc(struct net *net,
 	ct->status = 0;
 	ct->timeout = 0;
 	write_pnet(&ct->ct_net, net);
-	memset(&ct->__nfct_init_offset[0], 0,
+	memset(&ct->__nfct_init_offset, 0,
 	       offsetof(struct nf_conn, proto) -
-	       offsetof(struct nf_conn, __nfct_init_offset[0]));
+	       offsetof(struct nf_conn, __nfct_init_offset));
 
 	nf_ct_zone_add(ct, zone);
 
@@ -2139,8 +2139,19 @@ get_next_corpse(int (*iter)(struct nf_conn *i, void *data),
 		nf_conntrack_lock(lockp);
 		if (*bucket < nf_conntrack_htable_size) {
 			hlist_nulls_for_each_entry(h, n, &nf_conntrack_hash[*bucket], hnnode) {
-				if (NF_CT_DIRECTION(h) != IP_CT_DIR_ORIGINAL)
+				if (NF_CT_DIRECTION(h) != IP_CT_DIR_REPLY)
 					continue;
+				/* All nf_conn objects are added to hash table twice, one
+				 * for original direction tuple, once for the reply tuple.
+				 *
+				 * Exception: In the IPS_NAT_CLASH case, only the reply
+				 * tuple is added (the original tuple already existed for
+				 * a different object).
+				 *
+				 * We only need to call the iterator once for each
+				 * conntrack, so we just use the 'reply' direction
+				 * tuple while iterating.
+				 */
 				ct = nf_ct_tuplehash_to_ctrack(h);
 				if (iter(ct, data))
 					goto found;
diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c
index 4344e572b7f96c..42da6e33727668 100644
--- a/net/netfilter/nf_flow_table_core.c
+++ b/net/netfilter/nf_flow_table_core.c
@@ -284,7 +284,7 @@ static void flow_offload_del(struct nf_flowtable *flow_table,
 
 	if (nf_flow_has_expired(flow))
 		flow_offload_fixup_ct(flow->ct);
-	else if (test_bit(NF_FLOW_TEARDOWN, &flow->flags))
+	else
 		flow_offload_fixup_ct_timeout(flow->ct);
 
 	flow_offload_free(flow);
@@ -361,8 +361,10 @@ static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data)
 {
 	struct nf_flowtable *flow_table = data;
 
-	if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) ||
-	    test_bit(NF_FLOW_TEARDOWN, &flow->flags)) {
+	if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct))
+		set_bit(NF_FLOW_TEARDOWN, &flow->flags);
+
+	if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) {
 		if (test_bit(NF_FLOW_HW, &flow->flags)) {
 			if (!test_bit(NF_FLOW_HW_DYING, &flow->flags))
 				nf_flow_offload_del(flow_table, flow);
diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
index e3b099c14eff64..2276a73ccba24b 100644
--- a/net/netfilter/nf_flow_table_offload.c
+++ b/net/netfilter/nf_flow_table_offload.c
@@ -817,6 +817,7 @@ static void flow_offload_work_handler(struct work_struct *work)
 			WARN_ON_ONCE(1);
 	}
 
+	clear_bit(NF_FLOW_HW_PENDING, &offload->flow->flags);
 	kfree(offload);
 }
 
@@ -831,9 +832,14 @@ nf_flow_offload_work_alloc(struct nf_flowtable *flowtable,
 {
 	struct flow_offload_work *offload;
 
+	if (test_and_set_bit(NF_FLOW_HW_PENDING, &flow->flags))
+		return NULL;
+
 	offload = kmalloc(sizeof(struct flow_offload_work), GFP_ATOMIC);
-	if (!offload)
+	if (!offload) {
+		clear_bit(NF_FLOW_HW_PENDING, &flow->flags);
 		return NULL;
+	}
 
 	offload->cmd = cmd;
 	offload->flow = flow;
@@ -1056,7 +1062,7 @@ static struct flow_indr_block_entry block_ing_entry = {
 int nf_flow_table_offload_init(void)
 {
 	nf_flow_offload_wq  = alloc_workqueue("nf_flow_table_offload",
-					      WQ_UNBOUND | WQ_MEM_RECLAIM, 0);
+					      WQ_UNBOUND, 0);
 	if (!nf_flow_offload_wq)
 		return -ENOMEM;
 
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 3ffef454d4699f..62f416bc05796b 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -79,6 +79,10 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 				parent = rcu_dereference_raw(parent->rb_left);
 				continue;
 			}
+
+			if (nft_set_elem_expired(&rbe->ext))
+				return false;
+
 			if (nft_rbtree_interval_end(rbe)) {
 				if (nft_set_is_anonymous(set))
 					return false;
@@ -94,6 +98,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
+	    !nft_set_elem_expired(&interval->ext) &&
 	    nft_rbtree_interval_start(interval)) {
 		*ext = &interval->ext;
 		return true;
@@ -154,6 +159,9 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set,
 				continue;
 			}
 
+			if (nft_set_elem_expired(&rbe->ext))
+				return false;
+
 			if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) ||
 			    (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) ==
 			    (flags & NFT_SET_ELEM_INTERVAL_END)) {
@@ -170,6 +178,7 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set,
 
 	if (set->flags & NFT_SET_INTERVAL && interval != NULL &&
 	    nft_set_elem_active(&interval->ext, genmask) &&
+	    !nft_set_elem_expired(&interval->ext) &&
 	    ((!nft_rbtree_interval_end(interval) &&
 	      !(flags & NFT_SET_ELEM_INTERVAL_END)) ||
 	     (nft_rbtree_interval_end(interval) &&
@@ -418,6 +427,8 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 		if (iter->count < iter->skip)
 			goto cont;
+		if (nft_set_elem_expired(&rbe->ext))
+			goto cont;
 		if (!nft_set_elem_active(&rbe->ext, iter->genmask))
 			goto cont;