path: root/kernel/bpf/lpm_trie.c

// SPDX-License-Identifier: GPL-2.0-only
/*
 * Longest prefix match list implementation
 *
 * Copyright (c) 2016,2017 Daniel Mack
 * Copyright (c) 2016 David Herrmann
 */

#include <linux/bpf.h>
#include <linux/btf.h>
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <net/ipv6.h>
#include <uapi/linux/btf.h>

/* Intermediate node */
#define LPM_TREE_NODE_FLAG_IM BIT(0)

struct lpm_trie_node;

struct lpm_trie_node {
	struct rcu_head rcu;
	struct lpm_trie_node __rcu	*child[2];
	u32				prefixlen;
	u32				flags;
	u8				data[];
};

struct lpm_trie {
	struct bpf_map			map;
	struct lpm_trie_node __rcu	*root;
	size_t				n_entries;
	size_t				max_prefixlen;
	size_t				data_size;
	spinlock_t			lock;
};

/* This trie implements a longest prefix match algorithm that can be used to
 * match IP addresses to a stored set of ranges.
 *
 * Data stored in @data of struct bpf_lpm_key and struct lpm_trie_node is
 * interpreted as big endian, so data[0] stores the most significant byte.
 *
 * Match ranges are internally stored in instances of struct lpm_trie_node
 * which each contain their prefix length as well as two pointers that may
 * lead to more nodes containing more specific matches. Each node also stores
 * a value that is defined by and returned to userspace via the update_elem
 * and lookup functions.
 *
 * For instance, let's start with a trie that was created with a prefix length
 * of 32, so it can be used for IPv4 addresses, and one single element that
 * matches 192.168.0.0/16. The data array would hence contain
 * [0xc0, 0xa8, 0x00, 0x00] in big-endian notation. This documentation will
 * stick to IP-address notation for readability though.
 *
 * As the trie is empty initially, the new node (1) will be places as root
 * node, denoted as (R) in the example below. As there are no other node, both
 * child pointers are %NULL.
 *
 *              +----------------+
 *              |       (1)  (R) |
 *              | 192.168.0.0/16 |
 *              |    value: 1    |
 *              |   [0]    [1]   |
 *              +----------------+
 *
 * Next, let's add a new node (2) matching 192.168.0.0/24. As there is already
 * a node with the same data and a smaller prefix (ie, a less specific one),
 * node (2) will become a child of (1). In child index depends on the next bit
 * that is outside of what (1) matches, and that bit is 0, so (2) will be
 * child[0] of (1):
 *
 *              +----------------+
 *              |       (1)  (R) |
 *              | 192.168.0.0/16 |
 *              |    value: 1    |
 *              |   [0]    [1]   |
 *              +----------------+
 *                   |
 *    +----------------+
 *    |       (2)      |
 *    | 192.168.0.0/24 |
 *    |    value: 2    |
 *    |   [0]    [1]   |
 *    +----------------+
 *
 * The child[1] slot of (1) could be filled with another node which has bit #17
 * (the next bit after the ones that (1) matches on) set to 1. For instance,
 * 192.168.128.0/24:
 *
 *              +----------------+
 *              |       (1)  (R) |
 *              | 192.168.0.0/16 |
 *              |    value: 1    |
 *              |   [0]    [1]   |
 *              +----------------+
 *                   |      |
 *    +----------------+  +------------------+
 *    |       (2)      |  |        (3)       |
 *    | 192.168.0.0/24 |  | 192.168.128.0/24 |
 *    |    value: 2    |  |     value: 3     |
 *    |   [0]    [1]   |  |    [0]    [1]    |
 *    +----------------+  +------------------+
 *
 * Let's add another node (4) to the game for 192.168.1.0/24. In order to place
 * it, node (1) is looked at first, and because (4) of the semantics laid out
 * above (bit #17 is 0), it would normally be attached to (1) as child[0].
 * However, that slot is already allocated, so a new node is needed in between.
 * That node does not have a value attached to it and it will never be
 * returned to users as result of a lookup. It is only there to differentiate
 * the traversal further. It will get a prefix as wide as necessary to
 * distinguish its two children:
 *
 *                      +----------------+
 *                      |       (1)  (R) |
 *                      | 192.168.0.0/16 |
 *                      |    value: 1    |
 *                      |   [0]    [1]   |
 *                      +----------------+
 *                           |      |
 *            +----------------+  +------------------+
 *            |       (4)  (I) |  |        (3)       |
 *            | 192.168.0.0/23 |  | 192.168.128.0/24 |
 *            |    value: ---  |  |     value: 3     |
 *            |   [0]    [1]   |  |    [0]    [1]    |
 *            +----------------+  +------------------+
 *                 |      |
 *  +----------------+  +----------------+
 *  |       (2)      |  |       (5)      |
 *  | 192.168.0.0/24 |  | 192.168.1.0/24 |
 *  |    value: 2    |  |     value: 5   |
 *  |   [0]    [1]   |  |   [0]    [1]   |
 *  +----------------+  +----------------+
 *
 * 192.168.1.1/32 would be a child of (5) etc.
 *
 * An intermediate node will be turned into a 'real' node on demand. In the
 * example above, (4) would be re-used if 192.168.0.0/23 is added to the trie.
 *
 * A fully populated trie would have a height of 32 nodes, as the trie was
 * created with a prefix length of 32.
 *
 * The lookup starts at the root node. If the current node matches and if there
 * is a child that can be used to become more specific, the trie is traversed
 * downwards. The last node in the traversal that is a non-intermediate one is
 * returned.
 */

static inline int extract_bit(const u8 *data, size_t index)
{
	return !!(data[index / 8] & (1 << (7 - (index % 8))));
}

/**
 * longest_prefix_match() - determine the longest prefix
 * @trie:	The trie to get internal sizes from
 * @node:	The node to operate on
 * @key:	The key to compare to @node
 *
 * Determine the longest prefix of @node that matches the bits in @key.
 */
static size_t longest_prefix_match(const struct lpm_trie *trie,
				   const struct lpm_trie_node *node,
				   const struct bpf_lpm_trie_key *key)
{
	u32 limit = min(node->prefixlen, key->prefixlen);
	u32 prefixlen = 0, i = 0;

	BUILD_BUG_ON(offsetof(struct lpm_trie_node, data) % sizeof(u32));
	BUILD_BUG_ON(offsetof(struct bpf_lpm_trie_key, data) % sizeof(u32));

#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && defined(CONFIG_64BIT)

	/* data_size >= 16 has very small probability.
	 * We do not use a loop for optimal code generation.
	 */
	if (trie->data_size >= 8) {
		u64 diff = be64_to_cpu(*(__be64 *)node->data ^
				       *(__be64 *)key->data);

		prefixlen = 64 - fls64(diff);
		if (prefixlen >= limit)
			return limit;
		if (diff)
			return prefixlen;
		i = 8;
	}
#endif

	while (trie->data_size >= i + 4) {
		u32 diff = be32_to_cpu(*(__be32 *)&node->data[i] ^
				       *(__be32 *)&key->data[i]);

		prefixlen += 32 - fls(diff);
		if (prefixlen >= limit)
			return limit;
		if (diff)
			return prefixlen;
		i += 4;
	}

	if (trie->data_size >= i + 2) {
		u16 diff = be16_to_cpu(*(__be16 *)&node->data[i] ^
				       *(__be16 *)&key->data[i]);

		prefixlen += 16 - fls(diff);
		if (prefixlen >= limit)
			return limit;
		if (diff)
			return prefixlen;
		i += 2;
	}

	if (trie->data_size >= i + 1) {
		prefixlen += 8 - fls(node->data[i] ^ key->data[i]);

		if (prefixlen >= limit)
			return limit;
	}

	return prefixlen;
}

/* Called from syscall or from eBPF program */
static void *trie_lookup_elem(struct bpf_map *map, void *_key)
{
	struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
	struct lpm_trie_node *node, *found = NULL;
	struct bpf_lpm_trie_key *key = _key;

	/* Start walking the trie from the root node ... */

	for (node = rcu_dereference(trie->root); node;) {
		unsigned int next_bit;
		size_t matchlen;

		/* Determine the longest prefix of @node that matches @key.
		 * If it's the maximum possible prefix for this trie, we have
		 * an exact match and can return it directly.
		 */
		matchlen = longest_prefix_match(trie, node, key);
		if (matchlen == trie->max_prefixlen) {
			found = node;
			break;
		}

		/* If the number of bits that match is smaller than the prefix
		 * length of @node, bail out and return the node we have seen
		 * last in the traversal (ie, the parent).
		 */
		if (matchlen < node->prefixlen)
			break;

		/* Consider this node as return candidate unless it is an
		 * artificially added intermediate one.
		 */
		if (!(node->flags & LPM_TREE_NODE_FLAG_IM))
			found = node;

		/* If the node match is fully satisfied, let's see if we can
		 * become more specific. Determine the next bit in the key and
		 * traverse down.
		 */
		next_bit = extract_bit(key->data, node->prefixlen);
		node = rcu_dereference(node