From e454cf5958538666635488030046b6a84a22d447 Mon Sep 17 00:00:00 2001 From: Craig Gallek Date: Mon, 18 Sep 2017 15:30:55 -0400 Subject: bpf: Implement map_delete_elem for BPF_MAP_TYPE_LPM_TRIE This is a simple non-recursive delete operation. It prunes paths of empty nodes in the tree, but it does not try to further compress the tree as nodes are removed. Signed-off-by: Craig Gallek Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/lpm_trie.c | 80 +++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 77 insertions(+), 3 deletions(-) (limited to 'kernel/bpf/lpm_trie.c') diff --git a/kernel/bpf/lpm_trie.c b/kernel/bpf/lpm_trie.c index 1b767844a76f..9d58a576b2ae 100644 --- a/kernel/bpf/lpm_trie.c +++ b/kernel/bpf/lpm_trie.c @@ -389,10 +389,84 @@ out: return ret; } -static int trie_delete_elem(struct bpf_map *map, void *key) +/* Called from syscall or from eBPF program */ +static int trie_delete_elem(struct bpf_map *map, void *_key) { - /* TODO */ - return -ENOSYS; + struct lpm_trie *trie = container_of(map, struct lpm_trie, map); + struct bpf_lpm_trie_key *key = _key; + struct lpm_trie_node __rcu **trim; + struct lpm_trie_node *node; + unsigned long irq_flags; + unsigned int next_bit; + size_t matchlen = 0; + int ret = 0; + + if (key->prefixlen > trie->max_prefixlen) + return -EINVAL; + + raw_spin_lock_irqsave(&trie->lock, irq_flags); + + /* Walk the tree looking for an exact key/length match and keeping + * track of where we could begin trimming the tree. The trim-point + * is the sub-tree along the walk consisting of only single-child + * intermediate nodes and ending at a leaf node that we want to + * remove. + */ + trim = &trie->root; + node = rcu_dereference_protected( + trie->root, lockdep_is_held(&trie->lock)); + while (node) { + matchlen = longest_prefix_match(trie, node, key); + + if (node->prefixlen != matchlen || + node->prefixlen == key->prefixlen) + break; + + next_bit = extract_bit(key->data, node->prefixlen); + /* If we hit a node that has more than one child or is a valid + * prefix itself, do not remove it. Reset the root of the trim + * path to its descendant on our path. + */ + if (!(node->flags & LPM_TREE_NODE_FLAG_IM) || + (node->child[0] && node->child[1])) + trim = &node->child[next_bit]; + node = rcu_dereference_protected( + node->child[next_bit], lockdep_is_held(&trie->lock)); + } + + if (!node || node->prefixlen != key->prefixlen || + (node->flags & LPM_TREE_NODE_FLAG_IM)) { + ret = -ENOENT; + goto out; + } + + trie->n_entries--; + + /* If the node we are removing is not a leaf node, simply mark it + * as intermediate and we are done. + */ + if (rcu_access_pointer(node->child[0]) || + rcu_access_pointer(node->child[1])) { + node->flags |= LPM_TREE_NODE_FLAG_IM; + goto out; + } + + /* trim should now point to the slot holding the start of a path from + * zero or more intermediate nodes to our leaf node for deletion. + */ + while ((node = rcu_dereference_protected( + *trim, lockdep_is_held(&trie->lock)))) { + RCU_INIT_POINTER(*trim, NULL); + trim = rcu_access_pointer(node->child[0]) ? + &node->child[0] : + &node->child[1]; + kfree_rcu(node, rcu); + } + +out: + raw_spin_unlock_irqrestore(&trie->lock, irq_flags); + + return ret; } #define LPM_DATA_SIZE_MAX 256 -- cgit v1.2.3