linux/kernel/bpf/lpm_trie.c

738 lines
21 KiB
C
Raw Normal View History

// 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>
#include <linux/btf_ids.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_check(trie->root, rcu_read_lock_bh_held());
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_check(node->child[next_bit],
rcu_read_lock_bh_held());
}
if (!found)
return NULL;
return found->data + trie->data_size;
}
static struct lpm_trie_node *lpm_trie_node_alloc(const struct lpm_trie *trie,
const void *value)
{
struct lpm_trie_node *node;
size_t size = sizeof(struct lpm_trie_node) + trie->data_size;
if (value)
size += trie->map.value_size;
bpf: Make non-preallocated allocation low priority GFP_ATOMIC doesn't cooperate well with memcg pressure so far, especially if we allocate too much GFP_ATOMIC memory. For example, when we set the memcg limit to limit a non-preallocated bpf memory, the GFP_ATOMIC can easily break the memcg limit by force charge. So it is very dangerous to use GFP_ATOMIC in non-preallocated case. One way to make it safe is to remove __GFP_HIGH from GFP_ATOMIC, IOW, use (__GFP_ATOMIC | __GFP_KSWAPD_RECLAIM) instead, then it will be limited if we allocate too much memory. There's a plan to completely remove __GFP_ATOMIC in the mm side[1], so let's use GFP_NOWAIT instead. We introduced BPF_F_NO_PREALLOC is because full map pre-allocation is too memory expensive for some cases. That means removing __GFP_HIGH doesn't break the rule of BPF_F_NO_PREALLOC, but has the same goal with it-avoiding issues caused by too much memory. So let's remove it. This fix can also apply to other run-time allocations, for example, the allocation in lpm trie, local storage and devmap. So let fix it consistently over the bpf code It also fixes a typo in the comment. [1]. https://lore.kernel.org/linux-mm/163712397076.13692.4727608274002939094@noble.neil.brown.name/ Cc: Roman Gushchin <roman.gushchin@linux.dev> Cc: Shakeel Butt <shakeelb@google.com> Cc: NeilBrown <neilb@suse.de> Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Reviewed-by: Shakeel Butt <shakeelb@google.com> Link: https://lore.kernel.org/r/20220709154457.57379-2-laoar.shao@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2022-07-09 23:44:56 +08:00
node = bpf_map_kmalloc_node(&trie->map, size, GFP_NOWAIT | __GFP_NOWARN,
trie->map.numa_node);
if (!node)
return NULL;
node->flags = 0;
if (value)
memcpy(node->data + trie->data_size, value,
trie->map.value_size);
return node;
}
/* Called from syscall or from eBPF program */
static int trie_update_elem(struct bpf_map *map,
void *_key, void *value, u64 flags)
{
struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL;
struct lpm_trie_node __rcu **slot;
struct bpf_lpm_trie_key *key = _key;
unsigned long irq_flags;
unsigned int next_bit;
size_t matchlen = 0;
int ret = 0;
if (unlikely(flags > BPF_EXIST))
return -EINVAL;
if (key->prefixlen > trie->max_prefixlen)
return -EINVAL;
spin_lock_irqsave(&trie->lock, irq_flags);
/* Allocate and fill a new node */
if (trie->n_entries == trie->map.max_entries) {
ret = -ENOSPC;
goto out;
}
new_node = lpm_trie_node_alloc(trie, value);
if (!new_node) {
ret = -ENOMEM;
goto out;
}
trie->n_entries++;
new_node->prefixlen = key->prefixlen;
RCU_INIT_POINTER(new_node->child[0], NULL);
RCU_INIT_POINTER(new_node->child[1], NULL);
memcpy(new_node->data, key->data, trie->data_size);
/* Now find a slot to attach the new node. To do that, walk the tree
* from the root and match as many bits as possible for each node until
* we either find an empty slot or a slot that needs to be replaced by
* an intermediate node.
*/
slot = &trie->root;
while ((node = rcu_dereference_protected(*slot,
lockdep_is_held(&trie->lock)))) {
matchlen = longest_prefix_match(trie, node, key);
if (node->prefixlen != matchlen ||
node->prefixlen == key->prefixlen ||
node->prefixlen == trie->max_prefixlen)
break;
next_bit = extract_bit(key->data, node->prefixlen);
slot = &node->child[next_bit];
}
/* If the slot is empty (a free child pointer or an empty root),
* simply assign the @new_node to that slot and be done.
*/
if (!node) {
rcu_assign_pointer(*slot, new_node);
goto out;
}
/* If the slot we picked already exists, replace it with @new_node
* which already has the correct data array set.
*/
if (node->prefixlen == matchlen) {
new_node->child[0] = node->child[0];
new_node->child[1] = node->child[1];
if (!(node->flags & LPM_TREE_NODE_FLAG_IM))
trie->n_entries--;
rcu_assign_pointer(*slot, new_node);
kfree_rcu(node, rcu);
goto out;
}
/* If the new node matches the prefix completely, it must be inserted
* as an ancestor. Simply insert it between @node and *@slot.
*/
if (matchlen == key->prefixlen) {
next_bit = extract_bit(node->data, matchlen);
rcu_assign_pointer(new_node->child[next_bit], node);
rcu_assign_pointer(*slot, new_node);
goto out;
}
im_node = lpm_trie_node_alloc(trie, NULL);
if (!im_node) {
ret = -ENOMEM;
goto out;
}
im_node->prefixlen = matchlen;
im_node->flags |= LPM_TREE_NODE_FLAG_IM;
memcpy(im_node->data, node->data, trie->data_size);
/* Now determine which child to install in which slot */
if (extract_bit(key->data, matchlen)) {
rcu_assign_pointer(im_node->child[0], node);
rcu_assign_pointer(im_node->child[1], new_node);
} else {
rcu_assign_pointer(im_node->child[0], new_node);
rcu_assign_pointer(im_node->child[1], node);
}
/* Finally, assign the intermediate node to the determined slot */
rcu_assign_pointer(*slot, im_node);
out:
if (ret) {
if (new_node)
trie->n_entries--;
kfree(new_node);
kfree(im_node);
}
spin_unlock_irqrestore(&trie->lock, irq_flags);
return ret;
}
/* Called from syscall or from eBPF program */
static int trie_delete_elem(struct bpf_map *map, void *_key)
{
struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
struct bpf_lpm_trie_key *key = _key;
struct lpm_trie_node __rcu **trim, **trim2;
struct lpm_trie_node *node, *parent;
unsigned long irq_flags;
unsigned int next_bit;
size_t matchlen = 0;
int ret = 0;
if (key->prefixlen > trie->max_prefixlen)
return -EINVAL;
spin_lock_irqsave(&trie->lock, irq_flags);
/* Walk the tree looking for an exact key/length match and keeping
* track of the path we traverse. We will need to know the node
* we wish to delete, and the slot that points to the node we want
* to delete. We may also need to know the nodes parent and the
* slot that contains it.
*/
trim = &trie->root;
trim2 = trim;
parent = NULL;
while ((node = rcu_dereference_protected(
*trim, lockdep_is_held(&trie->lock)))) {
matchlen = longest_prefix_match(trie, node, key);
if (node->prefixlen != matchlen ||
node->prefixlen == key->prefixlen)
break;
parent = node;
trim2 = trim;
next_bit = extract_bit(key->data, node->prefixlen);
trim = &node->child[next_bit];
}
if (!node || node->prefixlen != key->prefixlen ||
node->prefixlen != matchlen ||
(node->flags & LPM_TREE_NODE_FLAG_IM)) {
ret = -ENOENT;
goto out;
}
trie->n_entries--;
/* If the node we are removing has two children, 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;
}
/* If the parent of the node we are about to delete is an intermediate
* node, and the deleted node doesn't have any children, we can delete
* the intermediate parent as well and promote its other child
* up the tree. Doing this maintains the invariant that all
* intermediate nodes have exactly 2 children and that there are no
* unnecessary intermediate nodes in the tree.
*/
if (parent && (parent->flags & LPM_TREE_NODE_FLAG_IM) &&
!node->child[0] && !node->child[1]) {
if (node == rcu_access_pointer(parent->child[0]))
rcu_assign_pointer(
*trim2, rcu_access_pointer(parent->child[1]));
else
rcu_assign_pointer(
*trim2, rcu_access_pointer(parent->child[0]));
kfree_rcu(parent, rcu);
kfree_rcu(node, rcu);
goto out;
}
/* The node we are removing has either zero or one child. If there
* is a child, move it into the removed node's slot then delete
* the node. Otherwise just clear the slot and delete the node.
*/
if (node->child[0])
rcu_assign_pointer(*trim, rcu_access_pointer(node->child[0]));
else if (node->child[1])
rcu_assign_pointer(*trim, rcu_access_pointer(node->child[1]));
else
RCU_INIT_POINTER(*trim, NULL);
kfree_rcu(node, rcu);
out:
spin_unlock_irqrestore(&trie->lock, irq_flags);
return ret;
}
#define LPM_DATA_SIZE_MAX 256
#define LPM_DATA_SIZE_MIN 1
#define LPM_VAL_SIZE_MAX (KMALLOC_MAX_SIZE - LPM_DATA_SIZE_MAX - \
sizeof(struct lpm_trie_node))
#define LPM_VAL_SIZE_MIN 1
#define LPM_KEY_SIZE(X) (sizeof(struct bpf_lpm_trie_key) + (X))
#define LPM_KEY_SIZE_MAX LPM_KEY_SIZE(LPM_DATA_SIZE_MAX)
#define LPM_KEY_SIZE_MIN LPM_KEY_SIZE(LPM_DATA_SIZE_MIN)
#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \
BPF_F_ACCESS_MASK)
bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-19 02:28:00 +08:00
static struct bpf_map *trie_alloc(union bpf_attr *attr)
{
struct lpm_trie *trie;
if (!bpf_capable())
return ERR_PTR(-EPERM);
/* check sanity of attributes */
if (attr->max_entries == 0 ||
bpf: Allow selecting numa node during map creation The current map creation API does not allow to provide the numa-node preference. The memory usually comes from where the map-creation-process is running. The performance is not ideal if the bpf_prog is known to always run in a numa node different from the map-creation-process. One of the use case is sharding on CPU to different LRU maps (i.e. an array of LRU maps). Here is the test result of map_perf_test on the INNER_LRU_HASH_PREALLOC test if we force the lru map used by CPU0 to be allocated from a remote numa node: [ The machine has 20 cores. CPU0-9 at node 0. CPU10-19 at node 1 ] ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1628380 events per sec 4:inner_lru_hash_map_perf pre-alloc 1626396 events per sec 3:inner_lru_hash_map_perf pre-alloc 1626144 events per sec 6:inner_lru_hash_map_perf pre-alloc 1621657 events per sec 2:inner_lru_hash_map_perf pre-alloc 1621534 events per sec 1:inner_lru_hash_map_perf pre-alloc 1620292 events per sec 7:inner_lru_hash_map_perf pre-alloc 1613305 events per sec 0:inner_lru_hash_map_perf pre-alloc 1239150 events per sec #<<< After specifying numa node: ># taskset -c 10 ./map_perf_test 512 8 1260000 8000000 5:inner_lru_hash_map_perf pre-alloc 1629627 events per sec 3:inner_lru_hash_map_perf pre-alloc 1628057 events per sec 1:inner_lru_hash_map_perf pre-alloc 1623054 events per sec 6:inner_lru_hash_map_perf pre-alloc 1616033 events per sec 2:inner_lru_hash_map_perf pre-alloc 1614630 events per sec 4:inner_lru_hash_map_perf pre-alloc 1612651 events per sec 7:inner_lru_hash_map_perf pre-alloc 1609337 events per sec 0:inner_lru_hash_map_perf pre-alloc 1619340 events per sec #<<< This patch adds one field, numa_node, to the bpf_attr. Since numa node 0 is a valid node, a new flag BPF_F_NUMA_NODE is also added. The numa_node field is honored if and only if the BPF_F_NUMA_NODE flag is set. Numa node selection is not supported for percpu map. This patch does not change all the kmalloc. F.e. 'htab = kzalloc()' is not changed since the object is small enough to stay in the cache. Signed-off-by: Martin KaFai Lau <kafai@fb.com> Acked-by: Daniel Borkmann <daniel@iogearbox.net> Acked-by: Alexei Starovoitov <ast@fb.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2017-08-19 02:28:00 +08:00
!(attr->map_flags & BPF_F_NO_PREALLOC) ||
attr->map_flags & ~LPM_CREATE_FLAG_MASK ||
!bpf_map_flags_access_ok(attr->map_flags) ||
attr->key_size < LPM_KEY_SIZE_MIN ||
attr->key_size > LPM_KEY_SIZE_MAX ||
attr->value_size < LPM_VAL_SIZE_MIN ||
attr->value_size > LPM_VAL_SIZE_MAX)
return ERR_PTR(-EINVAL);
trie = bpf_map_area_alloc(sizeof(*trie), NUMA_NO_NODE);
if (!trie)
return ERR_PTR(-ENOMEM);
/* copy mandatory map attributes */
bpf_map_init_from_attr(&trie->map, attr);
trie->data_size = attr->key_size -
offsetof(struct bpf_lpm_trie_key, data);
trie->max_prefixlen = trie->data_size * 8;
spin_lock_init(&trie->lock);
return &trie->map;
}
static void trie_free(struct bpf_map *map)
{
struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
struct lpm_trie_node __rcu **slot;
struct lpm_trie_node *node;
/* Always start at the root and walk down to a node that has no
* children. Then free that node, nullify its reference in the parent
* and start over.
*/
for (;;) {
slot = &trie->root;
for (;;) {
bpf: fix rcu lockdep warning for lpm_trie map_free callback Commit 9a3efb6b661f ("bpf: fix memory leak in lpm_trie map_free callback function") fixed a memory leak and removed unnecessary locks in map_free callback function. Unfortrunately, it introduced a lockdep warning. When lockdep checking is turned on, running tools/testing/selftests/bpf/test_lpm_map will have: [ 98.294321] ============================= [ 98.294807] WARNING: suspicious RCU usage [ 98.295359] 4.16.0-rc2+ #193 Not tainted [ 98.295907] ----------------------------- [ 98.296486] /home/yhs/work/bpf/kernel/bpf/lpm_trie.c:572 suspicious rcu_dereference_check() usage! [ 98.297657] [ 98.297657] other info that might help us debug this: [ 98.297657] [ 98.298663] [ 98.298663] rcu_scheduler_active = 2, debug_locks = 1 [ 98.299536] 2 locks held by kworker/2:1/54: [ 98.300152] #0: ((wq_completion)"events"){+.+.}, at: [<00000000196bc1f0>] process_one_work+0x157/0x5c0 [ 98.301381] #1: ((work_completion)(&map->work)){+.+.}, at: [<00000000196bc1f0>] process_one_work+0x157/0x5c0 Since actual trie tree removal happens only after no other accesses to the tree are possible, replacing rcu_dereference_protected(*slot, lockdep_is_held(&trie->lock)) with rcu_dereference_protected(*slot, 1) fixed the issue. Fixes: 9a3efb6b661f ("bpf: fix memory leak in lpm_trie map_free callback function") Reported-by: Eric Dumazet <edumazet@google.com> Suggested-by: Eric Dumazet <edumazet@google.com> Signed-off-by: Yonghong Song <yhs@fb.com> Reviewed-by: Eric Dumazet <edumazet@google.com> Acked-by: David S. Miller <davem@davemloft.net> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
2018-02-23 02:10:35 +08:00
node = rcu_dereference_protected(*slot, 1);
if (!node)
goto out;
if (rcu_access_pointer(node->child[0])) {
slot = &node->child[0];
continue;
}
if (rcu_access_pointer(node->child[1])) {
slot = &node->child[1];
continue;
}
kfree(node);
RCU_INIT_POINTER(*slot, NULL);
break;
}
}
out:
bpf_map_area_free(trie);
}
static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)
{
struct lpm_trie_node *node, *next_node = NULL, *parent, *search_root;
struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
struct bpf_lpm_trie_key *key = _key, *next_key = _next_key;
struct lpm_trie_node **node_stack = NULL;
int err = 0, stack_ptr = -1;
unsigned int next_bit;
size_t matchlen;
/* The get_next_key follows postorder. For the 4 node example in
* the top of this file, the trie_get_next_key() returns the following
* one after another:
* 192.168.0.0/24
* 192.168.1.0/24
* 192.168.128.0/24
* 192.168.0.0/16
*
* The idea is to return more specific keys before less specific ones.
*/
/* Empty trie */
search_root = rcu_dereference(trie->root);
if (!search_root)
return -ENOENT;
/* For invalid key, find the leftmost node in the trie */
if (!key || key->prefixlen > trie->max_prefixlen)
goto find_leftmost;
treewide: kmalloc() -> kmalloc_array() The kmalloc() function has a 2-factor argument form, kmalloc_array(). This patch replaces cases of: kmalloc(a * b, gfp) with: kmalloc_array(a * b, gfp) as well as handling cases of: kmalloc(a * b * c, gfp) with: kmalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kmalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kmalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The tools/ directory was manually excluded, since it has its own implementation of kmalloc(). The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kmalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kmalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kmalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kmalloc( - sizeof(u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kmalloc( - sizeof(char) * COUNT + COUNT , ...) | kmalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kmalloc + kmalloc_array ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kmalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kmalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kmalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kmalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kmalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kmalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kmalloc(C1 * C2 * C3, ...) | kmalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kmalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kmalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kmalloc(sizeof(THING) * C2, ...) | kmalloc(sizeof(TYPE) * C2, ...) | kmalloc(C1 * C2 * C3, ...) | kmalloc(C1 * C2, ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kmalloc + kmalloc_array ( - (E1) * E2 + E1, E2 , ...) | - kmalloc + kmalloc_array ( - (E1) * (E2) + E1, E2 , ...) | - kmalloc + kmalloc_array ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
2018-06-13 04:55:00 +08:00
node_stack = kmalloc_array(trie->max_prefixlen,
sizeof(struct lpm_trie_node *),
GFP_ATOMIC | __GFP_NOWARN);
if (!node_stack)
return -ENOMEM;
/* Try to find the exact node for the given key */
for (node = search_root; node;) {
node_stack[++stack_ptr] = 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);
node = rcu_dereference(node->child[next_bit]);
}
if (!node || node->prefixlen != key->prefixlen ||
(node->flags & LPM_TREE_NODE_FLAG_IM))
goto find_leftmost;
/* The node with the exactly-matching key has been found,
* find the first node in postorder after the matched node.
*/
node = node_stack[stack_ptr];
while (stack_ptr > 0) {
parent = node_stack[stack_ptr - 1];
if (rcu_dereference(parent->child[0]) == node) {
search_root = rcu_dereference(parent->child[1]);
if (search_root)
goto find_leftmost;
}
if (!(parent->flags & LPM_TREE_NODE_FLAG_IM)) {
next_node = parent;
goto do_copy;
}
node = parent;
stack_ptr--;
}
/* did not find anything */
err = -ENOENT;
goto free_stack;
find_leftmost:
/* Find the leftmost non-intermediate node, all intermediate nodes
* have exact two children, so this function will never return NULL.
*/
for (node = search_root; node;) {
if (node->flags & LPM_TREE_NODE_FLAG_IM) {
node = rcu_dereference(node->child[0]);
} else {
next_node = node;
node = rcu_dereference(node->child[0]);
if (!node)
node = rcu_dereference(next_node->child[1]);
}
}
do_copy:
next_key->prefixlen = next_node->prefixlen;
memcpy((void *)next_key + offsetof(struct bpf_lpm_trie_key, data),
next_node->data, trie->data_size);
free_stack:
kfree(node_stack);
return err;
}
static int trie_check_btf(const struct bpf_map *map,
const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type)
{
/* Keys must have struct bpf_lpm_trie_key embedded. */
return BTF_INFO_KIND(key_type->info) != BTF_KIND_STRUCT ?
-EINVAL : 0;
}
BTF_ID_LIST_SINGLE(trie_map_btf_ids, struct, lpm_trie)
const struct bpf_map_ops trie_map_ops = {
bpf: Add map_meta_equal map ops Some properties of the inner map is used in the verification time. When an inner map is inserted to an outer map at runtime, bpf_map_meta_equal() is currently used to ensure those properties of the inserting inner map stays the same as the verification time. In particular, the current bpf_map_meta_equal() checks max_entries which turns out to be too restrictive for most of the maps which do not use max_entries during the verification time. It limits the use case that wants to replace a smaller inner map with a larger inner map. There are some maps do use max_entries during verification though. For example, the map_gen_lookup in array_map_ops uses the max_entries to generate the inline lookup code. To accommodate differences between maps, the map_meta_equal is added to bpf_map_ops. Each map-type can decide what to check when its map is used as an inner map during runtime. Also, some map types cannot be used as an inner map and they are currently black listed in bpf_map_meta_alloc() in map_in_map.c. It is not unusual that the new map types may not aware that such blacklist exists. This patch enforces an explicit opt-in and only allows a map to be used as an inner map if it has implemented the map_meta_equal ops. It is based on the discussion in [1]. All maps that support inner map has its map_meta_equal points to bpf_map_meta_equal in this patch. A later patch will relax the max_entries check for most maps. bpf_types.h counts 28 map types. This patch adds 23 ".map_meta_equal" by using coccinelle. -5 for BPF_MAP_TYPE_PROG_ARRAY BPF_MAP_TYPE_(PERCPU)_CGROUP_STORAGE BPF_MAP_TYPE_STRUCT_OPS BPF_MAP_TYPE_ARRAY_OF_MAPS BPF_MAP_TYPE_HASH_OF_MAPS The "if (inner_map->inner_map_meta)" check in bpf_map_meta_alloc() is moved such that the same error is returned. [1]: https://lore.kernel.org/bpf/20200522022342.899756-1-kafai@fb.com/ Signed-off-by: Martin KaFai Lau <kafai@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/bpf/20200828011806.1970400-1-kafai@fb.com
2020-08-28 09:18:06 +08:00
.map_meta_equal = bpf_map_meta_equal,
.map_alloc = trie_alloc,
.map_free = trie_free,
.map_get_next_key = trie_get_next_key,
.map_lookup_elem = trie_lookup_elem,
.map_update_elem = trie_update_elem,
.map_delete_elem = trie_delete_elem,
.map_lookup_batch = generic_map_lookup_batch,
.map_update_batch = generic_map_update_batch,
.map_delete_batch = generic_map_delete_batch,
.map_check_btf = trie_check_btf,
.map_btf_id = &trie_map_btf_ids[0],
};