2019-06-04 16:10:45 +08:00
|
|
|
// SPDX-License-Identifier: GPL-2.0-only
|
2017-01-22 00:26:11 +08:00
|
|
|
/*
|
|
|
|
* Longest prefix match list implementation
|
|
|
|
*
|
|
|
|
* Copyright (c) 2016,2017 Daniel Mack
|
|
|
|
* Copyright (c) 2016 David Herrmann
|
|
|
|
*/
|
|
|
|
|
|
|
|
#include <linux/bpf.h>
|
2018-08-12 07:59:17 +08:00
|
|
|
#include <linux/btf.h>
|
2017-01-22 00:26:11 +08:00
|
|
|
#include <linux/err.h>
|
|
|
|
#include <linux/slab.h>
|
|
|
|
#include <linux/spinlock.h>
|
|
|
|
#include <linux/vmalloc.h>
|
|
|
|
#include <net/ipv6.h>
|
2018-08-12 07:59:17 +08:00
|
|
|
#include <uapi/linux/btf.h>
|
2022-04-25 21:32:47 +08:00
|
|
|
#include <linux/btf_ids.h>
|
2017-01-22 00:26:11 +08:00
|
|
|
|
|
|
|
/* 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;
|
2020-02-27 08:17:44 +08:00
|
|
|
u8 data[];
|
2017-01-22 00:26:11 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
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;
|
2020-02-24 22:01:52 +08:00
|
|
|
spinlock_t lock;
|
2017-01-22 00:26:11 +08:00
|
|
|
};
|
|
|
|
|
|
|
|
/* 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)
|
|
|
|
{
|
2018-11-22 13:39:52 +08:00
|
|
|
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;
|
|
|
|
}
|
2017-01-22 00:26:11 +08:00
|
|
|
|
2018-11-22 13:39:52 +08:00
|
|
|
if (trie->data_size >= i + 2) {
|
|
|
|
u16 diff = be16_to_cpu(*(__be16 *)&node->data[i] ^
|
|
|
|
*(__be16 *)&key->data[i]);
|
2017-01-22 00:26:11 +08:00
|
|
|
|
2018-11-22 13:39:52 +08:00
|
|
|
prefixlen += 16 - fls(diff);
|
|
|
|
if (prefixlen >= limit)
|
|
|
|
return limit;
|
|
|
|
if (diff)
|
|
|
|
return prefixlen;
|
|
|
|
i += 2;
|
|
|
|
}
|
2017-01-22 00:26:11 +08:00
|
|
|
|
2018-11-22 13:39:52 +08:00
|
|
|
if (trie->data_size >= i + 1) {
|
|
|
|
prefixlen += 8 - fls(node->data[i] ^ key->data[i]);
|
2017-01-22 00:26:11 +08:00
|
|
|
|
2018-11-22 13:39:52 +08:00
|
|
|
if (prefixlen >= limit)
|
|
|
|
return limit;
|
2017-01-22 00:26:11 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
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 ... */
|
|
|
|
|
2021-06-25 00:05:54 +08:00
|
|
|
for (node = rcu_dereference_check(trie->root, rcu_read_lock_bh_held());
|
|
|
|
node;) {
|
2017-01-22 00:26:11 +08:00
|
|
|
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);
|
2021-06-25 00:05:54 +08:00
|
|
|
node = rcu_dereference_check(node->child[next_bit],
|
|
|
|
rcu_read_lock_bh_held());
|
2017-01-22 00:26:11 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
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,
|
2020-12-02 05:58:39 +08:00
|
|
|
trie->map.numa_node);
|
2017-01-22 00:26:11 +08:00
|
|
|
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 */
|
bpf: return long from bpf_map_ops funcs
This patch changes the return types of bpf_map_ops functions to long, where
previously int was returned. Using long allows for bpf programs to maintain
the sign bit in the absence of sign extension during situations where
inlined bpf helper funcs make calls to the bpf_map_ops funcs and a negative
error is returned.
The definitions of the helper funcs are generated from comments in the bpf
uapi header at `include/uapi/linux/bpf.h`. The return type of these
helpers was previously changed from int to long in commit bdb7b79b4ce8. For
any case where one of the map helpers call the bpf_map_ops funcs that are
still returning 32-bit int, a compiler might not include sign extension
instructions to properly convert the 32-bit negative value a 64-bit
negative value.
For example:
bpf assembly excerpt of an inlined helper calling a kernel function and
checking for a specific error:
; err = bpf_map_update_elem(&mymap, &key, &val, BPF_NOEXIST);
...
46: call 0xffffffffe103291c ; htab_map_update_elem
; if (err && err != -EEXIST) {
4b: cmp $0xffffffffffffffef,%rax ; cmp -EEXIST,%rax
kernel function assembly excerpt of return value from
`htab_map_update_elem` returning 32-bit int:
movl $0xffffffef, %r9d
...
movl %r9d, %eax
...results in the comparison:
cmp $0xffffffffffffffef, $0x00000000ffffffef
Fixes: bdb7b79b4ce8 ("bpf: Switch most helper return values from 32-bit int to 64-bit long")
Tested-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Link: https://lore.kernel.org/r/20230322194754.185781-3-inwardvessel@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-23 03:47:54 +08:00
|
|
|
static long trie_update_elem(struct bpf_map *map,
|
|
|
|
void *_key, void *value, u64 flags)
|
2017-01-22 00:26:11 +08:00
|
|
|
{
|
|
|
|
struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
|
2017-01-24 08:26:46 +08:00
|
|
|
struct lpm_trie_node *node, *im_node = NULL, *new_node = NULL;
|
2017-01-22 00:26:11 +08:00
|
|
|
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;
|
|
|
|
|
2020-02-24 22:01:52 +08:00
|
|
|
spin_lock_irqsave(&trie->lock, irq_flags);
|
2017-01-22 00:26:11 +08:00
|
|
|
|
|
|
|
/* 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);
|
|
|
|
}
|
|
|
|
|
2021-12-29 22:44:22 +08:00
|
|
|
/* Finally, assign the intermediate node to the determined slot */
|
2017-01-22 00:26:11 +08:00
|
|
|
rcu_assign_pointer(*slot, im_node);
|
|
|
|
|
|
|
|
out:
|
|
|
|
if (ret) {
|
|
|
|
if (new_node)
|
|
|
|
trie->n_entries--;
|
|
|
|
|
|
|
|
kfree(new_node);
|
|
|
|
kfree(im_node);
|
|
|
|
}
|
|
|
|
|
2020-02-24 22:01:52 +08:00
|
|
|
spin_unlock_irqrestore(&trie->lock, irq_flags);
|
2017-01-22 00:26:11 +08:00
|
|
|
|
|
|
|
return ret;
|
|
|
|
}
|
|
|
|
|
2017-09-19 03:30:55 +08:00
|
|
|
/* Called from syscall or from eBPF program */
|
bpf: return long from bpf_map_ops funcs
This patch changes the return types of bpf_map_ops functions to long, where
previously int was returned. Using long allows for bpf programs to maintain
the sign bit in the absence of sign extension during situations where
inlined bpf helper funcs make calls to the bpf_map_ops funcs and a negative
error is returned.
The definitions of the helper funcs are generated from comments in the bpf
uapi header at `include/uapi/linux/bpf.h`. The return type of these
helpers was previously changed from int to long in commit bdb7b79b4ce8. For
any case where one of the map helpers call the bpf_map_ops funcs that are
still returning 32-bit int, a compiler might not include sign extension
instructions to properly convert the 32-bit negative value a 64-bit
negative value.
For example:
bpf assembly excerpt of an inlined helper calling a kernel function and
checking for a specific error:
; err = bpf_map_update_elem(&mymap, &key, &val, BPF_NOEXIST);
...
46: call 0xffffffffe103291c ; htab_map_update_elem
; if (err && err != -EEXIST) {
4b: cmp $0xffffffffffffffef,%rax ; cmp -EEXIST,%rax
kernel function assembly excerpt of return value from
`htab_map_update_elem` returning 32-bit int:
movl $0xffffffef, %r9d
...
movl %r9d, %eax
...results in the comparison:
cmp $0xffffffffffffffef, $0x00000000ffffffef
Fixes: bdb7b79b4ce8 ("bpf: Switch most helper return values from 32-bit int to 64-bit long")
Tested-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: JP Kobryn <inwardvessel@gmail.com>
Link: https://lore.kernel.org/r/20230322194754.185781-3-inwardvessel@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2023-03-23 03:47:54 +08:00
|
|
|
static long trie_delete_elem(struct bpf_map *map, void *_key)
|
2017-01-22 00:26:11 +08:00
|
|
|
{
|
2017-09-19 03:30:55 +08:00
|
|
|
struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
|
|
|
|
struct bpf_lpm_trie_key *key = _key;
|
2017-09-22 06:43:29 +08:00
|
|
|
struct lpm_trie_node __rcu **trim, **trim2;
|
|
|
|
struct lpm_trie_node *node, *parent;
|
2017-09-19 03:30:55 +08:00
|
|
|
unsigned long irq_flags;
|
|
|
|
unsigned int next_bit;
|
|
|
|
size_t matchlen = 0;
|
|
|
|
int ret = 0;
|
|
|
|
|
|
|
|
if (key->prefixlen > trie->max_prefixlen)
|
|
|
|
return -EINVAL;
|
|
|
|
|
2020-02-24 22:01:52 +08:00
|
|
|
spin_lock_irqsave(&trie->lock, irq_flags);
|
2017-09-19 03:30:55 +08:00
|
|
|
|
|
|
|
/* Walk the tree looking for an exact key/length match and keeping
|
2017-09-22 06:43:29 +08:00
|
|
|
* 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.
|
2017-09-19 03:30:55 +08:00
|
|
|
*/
|
|
|
|
trim = &trie->root;
|
2017-09-22 06:43:29 +08:00
|
|
|
trim2 = trim;
|
|
|
|
parent = NULL;
|
|
|
|
while ((node = rcu_dereference_protected(
|
|
|
|
*trim, lockdep_is_held(&trie->lock)))) {
|
2017-09-19 03:30:55 +08:00
|
|
|
matchlen = longest_prefix_match(trie, node, key);
|
|
|
|
|
|
|
|
if (node->prefixlen != matchlen ||
|
|
|
|
node->prefixlen == key->prefixlen)
|
|
|
|
break;
|
|
|
|
|
2017-09-22 06:43:29 +08:00
|
|
|
parent = node;
|
|
|
|
trim2 = trim;
|
2017-09-19 03:30:55 +08:00
|
|
|
next_bit = extract_bit(key->data, node->prefixlen);
|
2017-09-22 06:43:29 +08:00
|
|
|
trim = &node->child[next_bit];
|
2017-09-19 03:30:55 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
if (!node || node->prefixlen != key->prefixlen ||
|
2019-02-22 21:19:08 +08:00
|
|
|
node->prefixlen != matchlen ||
|
2017-09-19 03:30:55 +08:00
|
|
|
(node->flags & LPM_TREE_NODE_FLAG_IM)) {
|
|
|
|
ret = -ENOENT;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
|
|
|
trie->n_entries--;
|
|
|
|
|
2017-09-22 06:43:29 +08:00
|
|
|
/* If the node we are removing has two children, simply mark it
|
2017-09-19 03:30:55 +08:00
|
|
|
* as intermediate and we are done.
|
|
|
|
*/
|
2017-09-22 06:43:29 +08:00
|
|
|
if (rcu_access_pointer(node->child[0]) &&
|
2017-09-19 03:30:55 +08:00
|
|
|
rcu_access_pointer(node->child[1])) {
|
|
|
|
node->flags |= LPM_TREE_NODE_FLAG_IM;
|
|
|
|
goto out;
|
|
|
|
}
|
|
|
|
|
2017-09-22 06:43:29 +08:00
|
|
|
/* 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.
|
2017-09-19 03:30:55 +08:00
|
|
|
*/
|
2017-09-22 06:43:29 +08:00
|
|
|
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);
|
2017-09-19 03:30:55 +08:00
|
|
|
kfree_rcu(node, rcu);
|
2017-09-22 06:43:29 +08:00
|
|
|
goto out;
|
2017-09-19 03:30:55 +08:00
|
|
|
}
|
|
|
|
|
2017-09-22 06:43:29 +08:00
|
|
|
/* 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);
|
|
|
|
|
2017-09-19 03:30:55 +08:00
|
|
|
out:
|
2020-02-24 22:01:52 +08:00
|
|
|
spin_unlock_irqrestore(&trie->lock, irq_flags);
|
2017-09-19 03:30:55 +08:00
|
|
|
|
|
|
|
return ret;
|
2017-01-22 00:26:11 +08:00
|
|
|
}
|
|
|
|
|
2017-02-08 08:19:43 +08:00
|
|
|
#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)
|
|
|
|
|
2017-10-19 04:00:22 +08:00
|
|
|
#define LPM_CREATE_FLAG_MASK (BPF_F_NO_PREALLOC | BPF_F_NUMA_NODE | \
|
bpf: add program side {rd, wr}only support for maps
This work adds two new map creation flags BPF_F_RDONLY_PROG
and BPF_F_WRONLY_PROG in order to allow for read-only or
write-only BPF maps from a BPF program side.
Today we have BPF_F_RDONLY and BPF_F_WRONLY, but this only
applies to system call side, meaning the BPF program has full
read/write access to the map as usual while bpf(2) calls with
map fd can either only read or write into the map depending
on the flags. BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG allows
for the exact opposite such that verifier is going to reject
program loads if write into a read-only map or a read into a
write-only map is detected. For read-only map case also some
helpers are forbidden for programs that would alter the map
state such as map deletion, update, etc. As opposed to the two
BPF_F_RDONLY / BPF_F_WRONLY flags, BPF_F_RDONLY_PROG as well
as BPF_F_WRONLY_PROG really do correspond to the map lifetime.
We've enabled this generic map extension to various non-special
maps holding normal user data: array, hash, lru, lpm, local
storage, queue and stack. Further generic map types could be
followed up in future depending on use-case. Main use case
here is to forbid writes into .rodata map values from verifier
side.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-10 05:20:05 +08:00
|
|
|
BPF_F_ACCESS_MASK)
|
2017-08-19 02:28:00 +08:00
|
|
|
|
2017-01-22 00:26:11 +08:00
|
|
|
static struct bpf_map *trie_alloc(union bpf_attr *attr)
|
|
|
|
{
|
|
|
|
struct lpm_trie *trie;
|
|
|
|
|
2020-05-14 07:03:54 +08:00
|
|
|
if (!bpf_capable())
|
2017-01-22 00:26:11 +08:00
|
|
|
return ERR_PTR(-EPERM);
|
|
|
|
|
|
|
|
/* check sanity of attributes */
|
|
|
|
if (attr->max_entries == 0 ||
|
2017-08-19 02:28:00 +08:00
|
|
|
!(attr->map_flags & BPF_F_NO_PREALLOC) ||
|
|
|
|
attr->map_flags & ~LPM_CREATE_FLAG_MASK ||
|
bpf: add program side {rd, wr}only support for maps
This work adds two new map creation flags BPF_F_RDONLY_PROG
and BPF_F_WRONLY_PROG in order to allow for read-only or
write-only BPF maps from a BPF program side.
Today we have BPF_F_RDONLY and BPF_F_WRONLY, but this only
applies to system call side, meaning the BPF program has full
read/write access to the map as usual while bpf(2) calls with
map fd can either only read or write into the map depending
on the flags. BPF_F_RDONLY_PROG and BPF_F_WRONLY_PROG allows
for the exact opposite such that verifier is going to reject
program loads if write into a read-only map or a read into a
write-only map is detected. For read-only map case also some
helpers are forbidden for programs that would alter the map
state such as map deletion, update, etc. As opposed to the two
BPF_F_RDONLY / BPF_F_WRONLY flags, BPF_F_RDONLY_PROG as well
as BPF_F_WRONLY_PROG really do correspond to the map lifetime.
We've enabled this generic map extension to various non-special
maps holding normal user data: array, hash, lru, lpm, local
storage, queue and stack. Further generic map types could be
followed up in future depending on use-case. Main use case
here is to forbid writes into .rodata map values from verifier
side.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2019-04-10 05:20:05 +08:00
|
|
|
!bpf_map_flags_access_ok(attr->map_flags) ||
|
2017-02-08 08:19:43 +08:00
|
|
|
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)
|
2017-01-22 00:26:11 +08:00
|
|
|
return ERR_PTR(-EINVAL);
|
|
|
|
|
2022-08-10 23:18:29 +08:00
|
|
|
trie = bpf_map_area_alloc(sizeof(*trie), NUMA_NO_NODE);
|
2017-01-22 00:26:11 +08:00
|
|
|
if (!trie)
|
|
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
|
|
|
|
/* copy mandatory map attributes */
|
2018-01-12 12:29:06 +08:00
|
|
|
bpf_map_init_from_attr(&trie->map, attr);
|
2017-01-22 00:26:11 +08:00
|
|
|
trie->data_size = attr->key_size -
|
|
|
|
offsetof(struct bpf_lpm_trie_key, data);
|
|
|
|
trie->max_prefixlen = trie->data_size * 8;
|
|
|
|
|
2020-02-24 22:01:52 +08:00
|
|
|
spin_lock_init(&trie->lock);
|
2017-01-22 00:26:11 +08:00
|
|
|
|
|
|
|
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 (;;) {
|
2018-02-23 02:10:35 +08:00
|
|
|
node = rcu_dereference_protected(*slot, 1);
|
2017-01-22 00:26:11 +08:00
|
|
|
if (!node)
|
2018-02-14 11:00:21 +08:00
|
|
|
goto out;
|
2017-01-22 00:26:11 +08:00
|
|
|
|
|
|
|
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;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-02-14 11:00:21 +08:00
|
|
|
out:
|
2022-08-10 23:18:29 +08:00
|
|
|
bpf_map_area_free(trie);
|
2017-01-22 00:26:11 +08:00
|
|
|
}
|
|
|
|
|
2018-01-19 07:08:50 +08:00
|
|
|
static int trie_get_next_key(struct bpf_map *map, void *_key, void *_next_key)
|
2017-03-06 01:41:08 +08:00
|
|
|
{
|
2018-01-27 07:06:07 +08:00
|
|
|
struct lpm_trie_node *node, *next_node = NULL, *parent, *search_root;
|
2018-01-19 07:08:50 +08:00
|
|
|
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 */
|
2018-01-27 07:06:07 +08:00
|
|
|
search_root = rcu_dereference(trie->root);
|
|
|
|
if (!search_root)
|
2018-01-19 07:08:50 +08:00
|
|
|
return -ENOENT;
|
|
|
|
|
|
|
|
/* For invalid key, find the leftmost node in the trie */
|
2018-01-27 07:06:07 +08:00
|
|
|
if (!key || key->prefixlen > trie->max_prefixlen)
|
2018-01-19 07:08:50 +08:00
|
|
|
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);
|
2018-01-19 07:08:50 +08:00
|
|
|
if (!node_stack)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
/* Try to find the exact node for the given key */
|
2018-01-27 07:06:07 +08:00
|
|
|
for (node = search_root; node;) {
|
2018-01-19 07:08:50 +08:00
|
|
|
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 ||
|
2018-01-27 07:06:07 +08:00
|
|
|
(node->flags & LPM_TREE_NODE_FLAG_IM))
|
2018-01-19 07:08:50 +08:00
|
|
|
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];
|
2018-01-27 07:06:07 +08:00
|
|
|
if (rcu_dereference(parent->child[0]) == node) {
|
|
|
|
search_root = rcu_dereference(parent->child[1]);
|
|
|
|
if (search_root)
|
|
|
|
goto find_leftmost;
|
2018-01-19 07:08:50 +08:00
|
|
|
}
|
|
|
|
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.
|
|
|
|
*/
|
2018-01-27 07:06:07 +08:00
|
|
|
for (node = search_root; node;) {
|
2019-06-09 03:54:19 +08:00
|
|
|
if (node->flags & LPM_TREE_NODE_FLAG_IM) {
|
|
|
|
node = rcu_dereference(node->child[0]);
|
|
|
|
} else {
|
2018-01-19 07:08:50 +08:00
|
|
|
next_node = node;
|
2019-06-09 03:54:19 +08:00
|
|
|
node = rcu_dereference(node->child[0]);
|
|
|
|
if (!node)
|
|
|
|
node = rcu_dereference(next_node->child[1]);
|
|
|
|
}
|
2018-01-19 07:08:50 +08:00
|
|
|
}
|
|
|
|
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;
|
2017-03-06 01:41:08 +08:00
|
|
|
}
|
|
|
|
|
2018-08-12 07:59:17 +08:00
|
|
|
static int trie_check_btf(const struct bpf_map *map,
|
2018-12-11 07:43:00 +08:00
|
|
|
const struct btf *btf,
|
2018-08-12 07:59:17 +08:00
|
|
|
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;
|
|
|
|
}
|
|
|
|
|
2023-03-05 20:45:59 +08:00
|
|
|
static u64 trie_mem_usage(const struct bpf_map *map)
|
|
|
|
{
|
|
|
|
struct lpm_trie *trie = container_of(map, struct lpm_trie, map);
|
|
|
|
u64 elem_size;
|
|
|
|
|
|
|
|
elem_size = sizeof(struct lpm_trie_node) + trie->data_size +
|
|
|
|
trie->map.value_size;
|
|
|
|
return elem_size * READ_ONCE(trie->n_entries);
|
|
|
|
}
|
|
|
|
|
2022-04-25 21:32:47 +08:00
|
|
|
BTF_ID_LIST_SINGLE(trie_map_btf_ids, struct, lpm_trie)
|
2017-04-11 21:34:58 +08:00
|
|
|
const struct bpf_map_ops trie_map_ops = {
|
2020-08-28 09:18:06 +08:00
|
|
|
.map_meta_equal = bpf_map_meta_equal,
|
2017-01-22 00:26:11 +08:00
|
|
|
.map_alloc = trie_alloc,
|
|
|
|
.map_free = trie_free,
|
2017-03-06 01:41:08 +08:00
|
|
|
.map_get_next_key = trie_get_next_key,
|
2017-01-22 00:26:11 +08:00
|
|
|
.map_lookup_elem = trie_lookup_elem,
|
|
|
|
.map_update_elem = trie_update_elem,
|
|
|
|
.map_delete_elem = trie_delete_elem,
|
2021-03-23 10:50:53 +08:00
|
|
|
.map_lookup_batch = generic_map_lookup_batch,
|
|
|
|
.map_update_batch = generic_map_update_batch,
|
|
|
|
.map_delete_batch = generic_map_delete_batch,
|
2018-08-12 07:59:17 +08:00
|
|
|
.map_check_btf = trie_check_btf,
|
2023-03-05 20:45:59 +08:00
|
|
|
.map_mem_usage = trie_mem_usage,
|
2022-04-25 21:32:47 +08:00
|
|
|
.map_btf_id = &trie_map_btf_ids[0],
|
2017-01-22 00:26:11 +08:00
|
|
|
};
|