[PATCH AUTOSEL 4.19 08/13] netfilter: nf_tables: Allow set back-ends to report partial overlaps on insertion

[PATCH AUTOSEL 4.19 08/13] netfilter: nf_tables: Allow set back-ends to report partial overlaps on insertion

[Sasha Levin]

From: Pablo Neira Ayuso <pablo@netfilter.org>

[ Upstream commit 8c2d45b2b65ca1f215244be1c600236e83f9815f ]

Currently, the -EEXIST return code of ->insert() callbacks is ambiguous: it
might indicate that a given element (including intervals) already exists as
such, or that the new element would clash with existing ones.

If identical elements already exist, the front-end is ignoring this without
returning error, in case NLM_F_EXCL is not set. However, if the new element
can't be inserted due an overlap, we should report this to the user.

To this purpose, allow set back-ends to return -ENOTEMPTY on collision with
existing elements, translate that to -EEXIST, and return that to userspace,
no matter if NLM_F_EXCL was set.

Reported-by: Phil Sutter <phil@nwl.cc>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nf_tables_api.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 5881f66688171..71d6170e60b4f 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4527,6 +4527,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
 				err = -EBUSY;
 			else if (!(nlmsg_flags & NLM_F_EXCL))
 				err = 0;
+		} else if (err == -ENOTEMPTY) {
+			/* ENOTEMPTY reports overlapping between this element
+			 * and an existing one.
+			 */
+			err = -EEXIST;
 		}
 		goto err5;
 	}
-- 
2.20.1

[PATCH AUTOSEL 4.19 09/13] netfilter: nft_set_rbtree: Introduce and use nft_rbtree_interval_start()

[Sasha Levin]

From: Stefano Brivio <sbrivio@redhat.com>

[ Upstream commit 6f7c9caf017be8ab0fe3b99509580d0793bf0833 ]

Replace negations of nft_rbtree_interval_end() with a new helper,
nft_rbtree_interval_start(), wherever this helps to visualise the
problem at hand, that is, for all the occurrences except for the
comparison against given flags in __nft_rbtree_get().

This gets especially useful in the next patch.

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nft_set_rbtree.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 0221510328d4f..84d317418d184 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -36,6 +36,11 @@ static bool nft_rbtree_interval_end(const struct nft_rbtree_elem *rbe)
 	       (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END);
 }
 
+static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe)
+{
+	return !nft_rbtree_interval_end(rbe);
+}
+
 static bool nft_rbtree_equal(const struct nft_set *set, const void *this,
 			     const struct nft_rbtree_elem *interval)
 {
@@ -67,7 +72,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set
 			if (interval &&
 			    nft_rbtree_equal(set, this, interval) &&
 			    nft_rbtree_interval_end(rbe) &&
-			    !nft_rbtree_interval_end(interval))
+			    nft_rbtree_interval_start(interval))
 				continue;
 			interval = rbe;
 		} else if (d > 0)
@@ -92,7 +97,7 @@ 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_rbtree_interval_end(interval)) {
+	    nft_rbtree_interval_start(interval)) {
 		*ext = &interval->ext;
 		return true;
 	}
@@ -221,9 +226,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 			p = &parent->rb_right;
 		else {
 			if (nft_rbtree_interval_end(rbe) &&
-			    !nft_rbtree_interval_end(new)) {
+			    nft_rbtree_interval_start(new)) {
 				p = &parent->rb_left;
-			} else if (!nft_rbtree_interval_end(rbe) &&
+			} else if (nft_rbtree_interval_start(rbe) &&
 				   nft_rbtree_interval_end(new)) {
 				p = &parent->rb_right;
 			} else if (nft_set_elem_active(&rbe->ext, genmask)) {
@@ -314,10 +319,10 @@ static void *nft_rbtree_deactivate(const struct net *net,
 			parent = parent->rb_right;
 		else {
 			if (nft_rbtree_interval_end(rbe) &&
-			    !nft_rbtree_interval_end(this)) {
+			    nft_rbtree_interval_start(this)) {
 				parent = parent->rb_left;
 				continue;
-			} else if (!nft_rbtree_interval_end(rbe) &&
+			} else if (nft_rbtree_interval_start(rbe) &&
 				   nft_rbtree_interval_end(this)) {
 				parent = parent->rb_right;
 				continue;
-- 
2.20.1

[PATCH AUTOSEL 4.19 10/13] netfilter: nft_set_rbtree: Detect partial overlaps on insertion

[Sasha Levin]

From: Stefano Brivio <sbrivio@redhat.com>

[ Upstream commit 7c84d41416d836ef7e533bd4d64ccbdf40c5ac70 ]

...and return -ENOTEMPTY to the front-end in this case, instead of
proceeding. Currently, nft takes care of checking for these cases
and not sending them to the kernel, but if we drop the set_overlap()
call in nft we can end up in situations like:

 # nft add table t
 # nft add set t s '{ type inet_service ; flags interval ; }'
 # nft add element t s '{ 1 - 5 }'
 # nft add element t s '{ 6 - 10 }'
 # nft add element t s '{ 4 - 7 }'
 # nft list set t s
 table ip t {
 	set s {
 		type inet_service
 		flags interval
 		elements = { 1-3, 4-5, 6-7 }
 	}
 }

This change has the primary purpose of making the behaviour
consistent with nft_set_pipapo, but is also functional to avoid
inconsistent behaviour if userspace sends overlapping elements for
any reason.

v2: When we meet the same key data in the tree, as start element while
    inserting an end element, or as end element while inserting a start
    element, actually check that the existing element is active, before
    resetting the overlap flag (Pablo Neira Ayuso)

Signed-off-by: Stefano Brivio <sbrivio@redhat.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/netfilter/nft_set_rbtree.c | 70 ++++++++++++++++++++++++++++++++--
 1 file changed, 67 insertions(+), 3 deletions(-)

diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index 84d317418d184..1769e8c473e11 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -210,8 +210,43 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 	u8 genmask = nft_genmask_next(net);
 	struct nft_rbtree_elem *rbe;
 	struct rb_node *parent, **p;
+	bool overlap = false;
 	int d;
 
+	/* Detect overlaps as we descend the tree. Set the flag in these cases:
+	 *
+	 * a1. |__ _ _?  >|__ _ _  (insert start after existing start)
+	 * a2. _ _ __>|  ?_ _ __|  (insert end before existing end)
+	 * a3. _ _ ___|  ?_ _ _>|  (insert end after existing end)
+	 * a4. >|__ _ _   _ _ __|  (insert start before existing end)
+	 *
+	 * and clear it later on, as we eventually reach the points indicated by
+	 * '?' above, in the cases described below. We'll always meet these
+	 * later, locally, due to tree ordering, and overlaps for the intervals
+	 * that are the closest together are always evaluated last.
+	 *
+	 * b1. |__ _ _!  >|__ _ _  (insert start after existing end)
+	 * b2. _ _ __>|  !_ _ __|  (insert end before existing start)
+	 * b3. !_____>|            (insert end after existing start)
+	 *
+	 * Case a4. resolves to b1.:
+	 * - if the inserted start element is the leftmost, because the '0'
+	 *   element in the tree serves as end element
+	 * - otherwise, if an existing end is found. Note that end elements are
+	 *   always inserted after corresponding start elements.
+	 *
+	 * For a new, rightmost pair of elements, we'll hit cases b1. and b3.,
+	 * in that order.
+	 *
+	 * The flag is also cleared in two special cases:
+	 *
+	 * b4. |__ _ _!|<_ _ _   (insert start right before existing end)
+	 * b5. |__ _ >|!__ _ _   (insert end right after existing start)
+	 *
+	 * which always happen as last step and imply that no further
+	 * overlapping is possible.
+	 */
+
 	parent = NULL;
 	p = &priv->root.rb_node;
 	while (*p != NULL) {
@@ -220,17 +255,42 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 		d = memcmp(nft_set_ext_key(&rbe->ext),
 			   nft_set_ext_key(&new->ext),
 			   set->klen);
-		if (d < 0)
+		if (d < 0) {
 			p = &parent->rb_left;
-		else if (d > 0)
+
+			if (nft_rbtree_interval_start(new)) {
+				overlap = nft_rbtree_interval_start(rbe) &&
+					  nft_set_elem_active(&rbe->ext,
+							      genmask);
+			} else {
+				overlap = nft_rbtree_interval_end(rbe) &&
+					  nft_set_elem_active(&rbe->ext,
+							      genmask);
+			}
+		} else if (d > 0) {
 			p = &parent->rb_right;
-		else {
+
+			if (nft_rbtree_interval_end(new)) {
+				overlap = nft_rbtree_interval_end(rbe) &&
+					  nft_set_elem_active(&rbe->ext,
+							      genmask);
+			} else if (nft_rbtree_interval_end(rbe) &&
+				   nft_set_elem_active(&rbe->ext, genmask)) {
+				overlap = true;
+			}
+		} else {
 			if (nft_rbtree_interval_end(rbe) &&
 			    nft_rbtree_interval_start(new)) {
 				p = &parent->rb_left;
+
+				if (nft_set_elem_active(&rbe->ext, genmask))
+					overlap = false;
 			} else if (nft_rbtree_interval_start(rbe) &&
 				   nft_rbtree_interval_end(new)) {
 				p = &parent->rb_right;
+
+				if (nft_set_elem_active(&rbe->ext, genmask))
+					overlap = false;
 			} else if (nft_set_elem_active(&rbe->ext, genmask)) {
 				*ext = &rbe->ext;
 				return -EEXIST;
@@ -239,6 +299,10 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set,
 			}
 		}
 	}
+
+	if (overlap)
+		return -ENOTEMPTY;
+
 	rb_link_node_rcu(&new->node, parent, p);
 	rb_insert_color(&new->node, &priv->root);
 	return 0;
-- 
2.20.1