The existing rbtree implementation uses singleton elements to represent
ranges, however, userspace provides a set size according to the number
of ranges in the set.
Adjust provided userspace set size to the number of singleton elements
in the kernel by multiplying the range by two.
Check if the no-match all-zero element is already in the set, in such
case release one slot in the set size.
Fixes: 0ed6389c483d ("netfilter: nf_tables: rename set implementations")
Signed-off-by: Pablo Neira Ayuso <pablo@xxxxxxxxxxxxx>
---
v2: make no assumptions on no-match all-zero element which was
inconditionally added in the previous patch, check instead if it
is present in the set, then adjust the available element slots
by one accordingly.
@Florian: Would you rebase your
netfilter: nf_tables: export set count and backend name to userspace
on top of this patch? The idea would be to use .usize to expose the
set size through 'nft list ruleset' as we discussed, instead of only
displaying this via --debug. Thanks.
include/net/netfilter/nf_tables.h | 3 ++
net/netfilter/nf_tables_api.c | 49 +++++++++++++++++++++++++++++--
net/netfilter/nft_set_rbtree.c | 43 +++++++++++++++++++++++++++
3 files changed, 93 insertions(+), 2 deletions(-)
diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
index 0027beca5cd5..7dcea247f853 100644
--- a/include/net/netfilter/nf_tables.h
+++ b/include/net/netfilter/nf_tables.h
@@ -495,6 +495,9 @@ struct nft_set_ops {
const struct nft_set *set,
const struct nft_set_elem *elem,
unsigned int flags);
+ u32 (*ksize)(u32 size);
+ u32 (*usize)(u32 size);
+ u32 (*adjust_maxsize)(const struct nft_set *set);
void (*commit)(struct nft_set *set);
void (*abort)(const struct nft_set *set);
u64 (*privsize)(const struct nlattr * const nla[],
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index f7ca7165e66e..c9a1d1565e89 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -4752,6 +4752,14 @@ static int nf_tables_fill_set_concat(struct sk_buff *skb,
return 0;
}
+static u32 nft_set_userspace_size(const struct nft_set_ops *ops, u32 size)
+{
+ if (ops->usize)
+ return ops->usize(size);
+
+ return size;
+}
+
static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
const struct nft_set *set, u16 event, u16 flags)
{
@@ -4822,7 +4830,8 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx,
if (!nest)
goto nla_put_failure;
if (set->size &&
- nla_put_be32(skb, NFTA_SET_DESC_SIZE, htonl(set->size)))
+ nla_put_be32(skb, NFTA_SET_DESC_SIZE,
+ htonl(nft_set_userspace_size(set->ops, set->size))))
goto nla_put_failure;
if (set->field_count > 1 &&
@@ -5190,6 +5199,15 @@ static bool nft_set_is_same(const struct nft_set *set,
return true;
}
+static u32 nft_set_kernel_size(const struct nft_set_ops *ops,
+ const struct nft_set_desc *desc)
+{
+ if (ops->ksize)
+ return ops->ksize(desc->size);
+
+ return desc->size;
+}
+
static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
const struct nlattr * const nla[])
{
@@ -5372,6 +5390,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
if (err < 0)
return err;
+ if (desc.size)
+ desc.size = nft_set_kernel_size(set->ops, &desc);
+
err = 0;
if (!nft_set_is_same(set, &desc, exprs, num_exprs, flags)) {
NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]);
@@ -5394,6 +5415,9 @@ static int nf_tables_newset(struct sk_buff *skb, const struct nfnl_info *info,
if (IS_ERR(ops))
return PTR_ERR(ops);
+ if (desc.size)
+ desc.size = nft_set_kernel_size(ops, &desc);
+
udlen = 0;
if (nla[NFTA_SET_USERDATA])
udlen = nla_len(nla[NFTA_SET_USERDATA]);
@@ -7050,6 +7074,27 @@ static bool nft_setelem_valid_key_end(const struct nft_set *set,
return true;
}
+static u32 nft_set_maxsize(const struct nft_set *set)
+{
+ u32 maxsize, delta;
+
+ if (!set->size)
+ return UINT_MAX;
+
+ if (set->ops->adjust_maxsize)
+ delta = set->ops->adjust_maxsize(set);
+ else
+ delta = 0;
+
+ if (check_add_overflow(set->size, set->ndeact, &maxsize))
+ return UINT_MAX;
+
+ if (check_add_overflow(maxsize, delta, &maxsize))
+ return UINT_MAX;
+
+ return maxsize;
+}
+
static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
const struct nlattr *attr, u32 nlmsg_flags)
{
@@ -7422,7 +7467,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
}
if (!(flags & NFT_SET_ELEM_CATCHALL)) {
- unsigned int max = set->size ? set->size + set->ndeact : UINT_MAX;
+ unsigned int max = nft_set_maxsize(set);
if (!atomic_add_unless(&set->nelems, 1, max)) {
err = -ENFILE;
diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c
index b7ea21327549..2e8ef16ff191 100644
--- a/net/netfilter/nft_set_rbtree.c
+++ b/net/netfilter/nft_set_rbtree.c
@@ -750,6 +750,46 @@ static void nft_rbtree_gc_init(const struct nft_set *set)
priv->last_gc = jiffies;
}
+/* rbtree stores ranges as singleton elements, each range is composed of two
+ * elements ...
+ */
+static u32 nft_rbtree_ksize(u32 size)
+{
+ return size * 2;
+}
+
+/* ... hide this detail to userspace. */
+static u32 nft_rbtree_usize(u32 size)
+{
+ if (!size)
+ return 0;
+
+ return size / 2;
+}
+
+static u32 nft_rbtree_adjust_maxsize(const struct nft_set *set)
+{
+ struct nft_rbtree *priv = nft_set_priv(set);
+ struct nft_rbtree_elem *rbe;
+ struct rb_node *node;
+ const void *key;
+
+ node = rb_last(&priv->root);
+ if (!node)
+ return 0;
+
+ rbe = rb_entry(node, struct nft_rbtree_elem, node);
+ if (!nft_rbtree_interval_end(rbe))
+ return 0;
+
+ key = nft_set_ext_key(&rbe->ext);
+ if (memchr(key, 1, set->klen))
+ return 0;
+
+ /* this is the all-zero no-match element. */
+ return 1;
+}
+
const struct nft_set_type nft_set_rbtree_type = {
.features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT,
.ops = {
@@ -768,5 +808,8 @@ const struct nft_set_type nft_set_rbtree_type = {
.lookup = nft_rbtree_lookup,
.walk = nft_rbtree_walk,
.get = nft_rbtree_get,
+ .ksize = nft_rbtree_ksize,
+ .usize = nft_rbtree_usize,
+ .adjust_maxsize = nft_rbtree_adjust_maxsize,
},
};
--
2.30.2
