Release 4.15 kernel/bpf/hashtab.c

/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 * Copyright (c) 2016 Facebook
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 */
#include <linux/bpf.h>
#include <linux/jhash.h>
#include <linux/filter.h>
#include <linux/rculist_nulls.h>
#include "percpu_freelist.h"
#include "bpf_lru_list.h"
#include "map_in_map.h"


#define HTAB_CREATE_FLAG_MASK						\
	(BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE |    \
         BPF_F_RDONLY | BPF_F_WRONLY)


struct bucket {
	
struct hlist_nulls_head head;
	
raw_spinlock_t lock;
};


struct bpf_htab {
	
struct bpf_map map;
	
struct bucket *buckets;
	
void *elems;
	union {
		
struct pcpu_freelist freelist;
		
struct bpf_lru lru;
	};
	
struct htab_elem *__percpu *extra_elems;
	
atomic_t count;	/* number of elements in this hashtable */
	
u32 n_buckets;	/* number of hash buckets */
	
u32 elem_size;	/* size of each element in bytes */
};

/* each htab element is struct htab_elem + key + value */

struct htab_elem {
	union {
		
struct hlist_nulls_node hash_node;
		struct {
			
void *padding;
			union {
				
struct bpf_htab *htab;
				
struct pcpu_freelist_node fnode;
			};
		};
	};
	union {
		
struct rcu_head rcu;
		
struct bpf_lru_node lru_node;
	};
	
u32 hash;
	char key[0] __aligned(8);
};

static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node);



static bool htab_is_lru(const struct bpf_htab *htab)
{
	return htab->map.map_type == BPF_MAP_TYPE_LRU_HASH ||
		htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin KaFai Lau
29
100.00%
2
100.00%
Total
29
100.00%
2
100.00%



static bool htab_is_percpu(const struct bpf_htab *htab)
{
	return htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH ||
		htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin KaFai Lau
29
100.00%
2
100.00%
Total
29
100.00%
2
100.00%



static bool htab_is_prealloc(const struct bpf_htab *htab)
{
	return !(htab->map.map_flags & BPF_F_NO_PREALLOC);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
24
100.00%
1
100.00%
Total
24
100.00%
1
100.00%



static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size,
				     void __percpu *pptr)
{
	*(void __percpu **)(l->key + key_size) = pptr;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
37
100.00%
1
100.00%
Total
37
100.00%
1
100.00%



static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size)
{
	return *(void __percpu **)(l->key + key_size);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
33
100.00%
1
100.00%
Total
33
100.00%
1
100.00%



static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l)
{
	return *(void **)(l->key + roundup(map->key_size, 8));
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin KaFai Lau
40
100.00%
1
100.00%
Total
40
100.00%
1
100.00%



static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i)
{
	return (struct htab_elem *) (htab->elems + i * htab->elem_size);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
34
100.00%
1
100.00%
Total
34
100.00%
1
100.00%



static void htab_free_elems(struct bpf_htab *htab)
{
	int i;

	if (!htab_is_percpu(htab))
		goto free_elems;

	for (i = 0; i < htab->map.max_entries; i++) {
		void __percpu *pptr;

		pptr = htab_elem_get_ptr(get_htab_elem(htab, i),
					 htab->map.key_size);
		free_percpu(pptr);
		cond_resched();
	}
free_elems:
	bpf_map_area_free(htab->elems);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
76
90.48%
1
25.00%
Martin KaFai Lau
4
4.76%
1
25.00%
Eric Dumazet
3
3.57%
1
25.00%
Daniel Borkmann
1
1.19%
1
25.00%
Total
84
100.00%
4
100.00%



static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key,
					  u32 hash)
{
	struct bpf_lru_node *node = bpf_lru_pop_free(&htab->lru, hash);
	struct htab_elem *l;

	if (node) {
		l = container_of(node, struct htab_elem, lru_node);
		memcpy(l->key, key, htab->map.key_size);
		return l;
	}

	return NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin KaFai Lau
79
100.00%
1
100.00%
Total
79
100.00%
1
100.00%



static int prealloc_init(struct bpf_htab *htab)
{
	u32 num_entries = htab->map.max_entries;
	int err = -ENOMEM, i;

	if (!htab_is_percpu(htab) && !htab_is_lru(htab))
		num_entries += num_possible_cpus();

	htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries,
					 htab->map.numa_node);
	if (!htab->elems)
		return -ENOMEM;

	if (!htab_is_percpu(htab))
		goto skip_percpu_elems;

	for (i = 0; i < num_entries; i++) {
		u32 size = round_up(htab->map.value_size, 8);
		void __percpu *pptr;

		pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN);
		if (!pptr)
			goto free_elems;
		htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size,
				  pptr);
		cond_resched();
	}

skip_percpu_elems:
	if (htab_is_lru(htab))
		err = bpf_lru_init(&htab->lru,
				   htab->map.map_flags & BPF_F_NO_COMMON_LRU,
				   offsetof(struct htab_elem, hash) -
				   offsetof(struct htab_elem, lru_node),
				   htab_lru_map_delete_node,
				   htab);
	else
		err = pcpu_freelist_init(&htab->freelist);

	if (err)
		goto free_elems;

	if (htab_is_lru(htab))
		bpf_lru_populate(&htab->lru, htab->elems,
				 offsetof(struct htab_elem, lru_node),
				 htab->elem_size, num_entries);
	else
		pcpu_freelist_populate(&htab->freelist,
				       htab->elems + offsetof(struct htab_elem, fnode),
				       htab->elem_size, num_entries);

	return 0;

free_elems:
	htab_free_elems(htab);
	return err;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
208
68.87%
3
37.50%
Martin KaFai Lau
90
29.80%
3
37.50%
Eric Dumazet
3
0.99%
1
12.50%
Daniel Borkmann
1
0.33%
1
12.50%
Total
302
100.00%
8
100.00%



static void prealloc_destroy(struct bpf_htab *htab)
{
	htab_free_elems(htab);

	if (htab_is_lru(htab))
		bpf_lru_destroy(&htab->lru);
	else
		pcpu_freelist_destroy(&htab->freelist);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin KaFai Lau
40
100.00%
1
100.00%
Total
40
100.00%
1
100.00%



static int alloc_extra_elems(struct bpf_htab *htab)
{
	struct htab_elem *__percpu *pptr, *l_new;
	struct pcpu_freelist_node *l;
	int cpu;

	pptr = __alloc_percpu_gfp(sizeof(struct htab_elem *), 8,
				  GFP_USER | __GFP_NOWARN);
	if (!pptr)
		return -ENOMEM;

	for_each_possible_cpu(cpu) {
		l = pcpu_freelist_pop(&htab->freelist);
		/* pop will succeed, since prealloc_init()
                 * preallocated extra num_possible_cpus elements
                 */
		l_new = container_of(l, struct htab_elem, fnode);
		*per_cpu_ptr(pptr, cpu) = l_new;
	}
	htab->extra_elems = pptr;
	return 0;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
104
100.00%
2
100.00%
Total
104
100.00%
2
100.00%

/* Called from syscall */


static struct bpf_map *htab_map_alloc(union bpf_attr *attr)
{
	bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH ||
		       attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
	bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH ||
		    attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH);
	/* percpu_lru means each cpu has its own LRU list.
         * it is different from BPF_MAP_TYPE_PERCPU_HASH where
         * the map's value itself is percpu.  percpu_lru has
         * nothing to do with the map's value.
         */
	bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU);
	bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC);
	int numa_node = bpf_map_attr_numa_node(attr);
	struct bpf_htab *htab;
	int err, i;
	u64 cost;

	BUILD_BUG_ON(offsetof(struct htab_elem, htab) !=
		     offsetof(struct htab_elem, hash_node.pprev));
	BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) !=
		     offsetof(struct htab_elem, hash_node.pprev));

	if (lru && !capable(CAP_SYS_ADMIN))
		/* LRU implementation is much complicated than other
                 * maps.  Hence, limit to CAP_SYS_ADMIN for now.
                 */
		return ERR_PTR(-EPERM);

	if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK)
		/* reserved bits should not be used */
		return ERR_PTR(-EINVAL);

	if (!lru && percpu_lru)
		return ERR_PTR(-EINVAL);

	if (lru && !prealloc)
		return ERR_PTR(-ENOTSUPP);

	if (numa_node != NUMA_NO_NODE && (percpu || percpu_lru))
		return ERR_PTR(-EINVAL);

	htab = kzalloc(sizeof(*htab), GFP_USER);
	if (!htab)
		return ERR_PTR(-ENOMEM);

	/* mandatory map attributes */
	htab->map.map_type = attr->map_type;
	htab->map.key_size = attr->key_size;
	htab->map.value_size = attr->value_size;
	htab->map.max_entries = attr->max_entries;
	htab->map.map_flags = attr->map_flags;
	htab->map.numa_node = numa_node;

	/* check sanity of attributes.
         * value_size == 0 may be allowed in the future to use map as a set
         */
	err = -EINVAL;
	if (htab->map.max_entries == 0 || htab->map.key_size == 0 ||
	    htab->map.value_size == 0)
		goto free_htab;

	if (percpu_lru) {
		/* ensure each CPU's lru list has >=1 elements.
                 * since we are at it, make each lru list has the same
                 * number of elements.
                 */
		htab->map.max_entries = roundup(attr->max_entries,
						num_possible_cpus());
		if (htab->map.max_entries < attr->max_entries)
			htab->map.max_entries = rounddown(attr->max_entries,
							  num_possible_cpus());
	}

	/* hash table size must be power of 2 */
	htab->n_buckets = roundup_pow_of_two(htab->map.max_entries);

	err = -E2BIG;
	if (htab->map.key_size > MAX_BPF_STACK)
		/* eBPF programs initialize keys on stack, so they cannot be
                 * larger than max stack size
                 */
		goto free_htab;

	if (htab->map.value_size >= KMALLOC_MAX_SIZE -
	    MAX_BPF_STACK - sizeof(struct htab_elem))
		/* if value_size is bigger, the user space won't be able to
                 * access the elements via bpf syscall. This check also makes
                 * sure that the elem_size doesn't overflow and it's
                 * kmalloc-able later in htab_map_update_elem()
                 */
		goto free_htab;

	htab->elem_size = sizeof(struct htab_elem) +
			  round_up(htab->map.key_size, 8);
	if (percpu)
		htab->elem_size += sizeof(void *);
	else
		htab->elem_size += round_up(htab->map.value_size, 8);

	/* prevent zero size kmalloc and check for u32 overflow */
	if (htab->n_buckets == 0 ||
	    htab->n_buckets > U32_MAX / sizeof(struct bucket))
		goto free_htab;

	cost = (u64) htab->n_buckets * sizeof(struct bucket) +
	       (u64) htab->elem_size * htab->map.max_entries;

	if (percpu)
		cost += (u64) round_up(htab->map.value_size, 8) *
			num_possible_cpus() * htab->map.max_entries;
	else
	       cost += (u64) htab->elem_size * num_possible_cpus();

	if (cost >= U32_MAX - PAGE_SIZE)
		/* make sure page count doesn't overflow */
		goto free_htab;

	htab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT;

	/* if map size is larger than memlock limit, reject it early */
	err = bpf_map_precharge_memlock(htab->map.pages);
	if (err)
		goto free_htab;

	err = -ENOMEM;
	htab->buckets = bpf_map_area_alloc(htab->n_buckets *
					   sizeof(struct bucket),
					   htab->map.numa_node);
	if (!htab->buckets)
		goto free_htab;

	for (i = 0; i < htab->n_buckets; i++) {
		INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i);
		raw_spin_lock_init(&htab->buckets[i].lock);
	}

	if (prealloc) {
		err = prealloc_init(htab);
		if (err)
			goto free_buckets;

		if (!percpu && !lru) {
			/* lru itself can remove the least used element, so
                         * there is no need for an extra elem during map_update.
                         */
			err = alloc_extra_elems(htab);
			if (err)
				goto free_prealloc;
		}
	}

	return &htab->map;

free_prealloc:
	prealloc_destroy(htab);
free_buckets:
	bpf_map_area_free(htab->buckets);
free_htab:
	kfree(htab);
	return ERR_PTR(err);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
575
72.15%
9
52.94%
Martin KaFai Lau
205
25.72%
3
17.65%
Lei Ming
13
1.63%
2
11.76%
Daniel Borkmann
2
0.25%
1
5.88%
Yang Shi
1
0.13%
1
5.88%
Michal Hocko
1
0.13%
1
5.88%
Total
797
100.00%
17
100.00%



static inline u32 htab_map_hash(const void *key, u32 key_len)
{
	return jhash(key, key_len, 0);
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
25
100.00%
1
100.00%
Total
25
100.00%
1
100.00%



static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
{
	return &htab->buckets[hash & (htab->n_buckets - 1)];
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
32
94.12%
1
50.00%
Lei Ming
2
5.88%
1
50.00%
Total
34
100.00%
2
100.00%



static inline struct hlist_nulls_head *select_bucket(struct bpf_htab *htab, u32 hash)
{
	return &__select_bucket(htab, hash)->head;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Lei Ming
27
96.43%
1
50.00%
Alexei Starovoitov
1
3.57%
1
50.00%
Total
28
100.00%
2
100.00%

/* this lookup function can only be called with bucket lock taken */


static struct htab_elem *lookup_elem_raw(struct hlist_nulls_head *head, u32 hash,
					 void *key, u32 key_size)
{
	struct hlist_nulls_node *n;
	struct htab_elem *l;

	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
		if (l->hash == hash && !memcmp(&l->key, key, key_size))
			return l;

	return NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
70
100.00%
2
100.00%
Total
70
100.00%
2
100.00%

/* can be called without bucket lock. it will repeat the loop in
 * the unlikely event when elements moved from one bucket into another
 * while link list is being walked
 */


static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head,
					       u32 hash, void *key,
					       u32 key_size, u32 n_buckets)
{
	struct hlist_nulls_node *n;
	struct htab_elem *l;

again:
	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
		if (l->hash == hash && !memcmp(&l->key, key, key_size))
			return l;

	if (unlikely(get_nulls_value(n) != (hash & (n_buckets - 1))))
		goto again;

	return NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
98
100.00%
1
100.00%
Total
98
100.00%
1
100.00%

/* Called from syscall or from eBPF program directly, so
 * arguments have to match bpf_map_lookup_elem() exactly.
 * The return value is adjusted by BPF instructions
 * in htab_map_gen_lookup().
 */


static void *__htab_map_lookup_elem(struct bpf_map *map, void *key)
{
	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
	struct hlist_nulls_head *head;
	struct htab_elem *l;
	u32 hash, key_size;

	/* Must be called with rcu_read_lock. */
	WARN_ON_ONCE(!rcu_read_lock_held());

	key_size = map->key_size;

	hash = htab_map_hash(key, key_size);

	head = select_bucket(htab, hash);

	l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);

	return l;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
98
100.00%
3
100.00%
Total
98
100.00%
3
100.00%



static void *htab_map_lookup_elem(struct bpf_map *map, void *key)
{
	struct htab_elem *l = __htab_map_lookup_elem(map, key);

	if (l)
		return l->key + round_up(map->key_size, 8);

	return NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
49
100.00%
2
100.00%
Total
49
100.00%
2
100.00%

/* inline bpf_map_lookup_elem() call.
 * Instead of:
 * bpf_prog
 *   bpf_map_lookup_elem
 *     map->ops->map_lookup_elem
 *       htab_map_lookup_elem
 *         __htab_map_lookup_elem
 * do:
 * bpf_prog
 *   __htab_map_lookup_elem
 */


static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf)
{
	struct bpf_insn *insn = insn_buf;
	const int ret = BPF_REG_0;

	*insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem);
	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1);
	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
				offsetof(struct htab_elem, key) +
				round_up(map->key_size, 8));
	return insn - insn_buf;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Alexei Starovoitov
103
100.00%
1
100.00%
Total
103
100.00%
1
100.00%



static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key)
{
	struct htab_elem *l = __htab_map_lookup_elem(map, key);

	if (l) {
		bpf_lru_node_set_ref(&l->lru_node);
		return l->key + round_up(map->key_size, 8);
	}

	return NULL;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin KaFai Lau
39
66.10%
1
50.00%
Alexei Starovoitov
20
33.90%
1
50.00%
Total
59
100.00%
2
100.00%



static u32 htab_lru_map_gen_lookup(struct bpf_map *map,
				   struct bpf_insn *insn_buf)
{
	struct bpf_insn *insn = insn_buf;
	const int ret = BPF_REG_0;
	const int ref_reg = BPF_REG_1;

	*insn++ = BPF_EMIT_CALL((u64 (*)(u64, u64, u64, u64, u64))__htab_map_lookup_elem);
	*insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4);
	*insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret,
			      offsetof(struct htab_elem, lru_node) +
			      offsetof(struct bpf_lru_node, ref));
	*insn++ = BPF_JMP_IMM(BPF_JNE, ref_reg, 0, 1);
	*insn++ = BPF_ST_MEM(BPF_B, ret,
			     offsetof(struct htab_elem, lru_node) +
			     offsetof(struct bpf_lru_node, ref),
			     1);
	*insn++ = BPF_ALU64_IMM(BPF_ADD, ret,
				offsetof(struct htab_elem, key) +
				round_up(map->key_size, 8));
	return insn - insn_buf;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin KaFai Lau
182
100.00%
2
100.00%
Total
182
100.00%
2
100.00%

/* It is called from the bpf_lru_list when the LRU needs to delete
 * older elements from the htab.
 */


static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node)
{
	struct bpf_htab *htab = (struct bpf_htab *)arg;
	struct htab_elem *l = NULL, *tgt_l;
	struct hlist_nulls_head *head;
	struct hlist_nulls_node *n;
	unsigned long flags;
	struct bucket *b;

	tgt_l = container_of(node, struct htab_elem, lru_node);
	b = __select_bucket(htab, tgt_l->hash);
	head = &b->head;

	raw_spin_lock_irqsave(&b->lock, flags);

	hlist_nulls_for_each_entry_rcu(l, n, head, hash_node)
		if (l == tgt_l) {
			hlist_nulls_del_rcu(&l->hash_node);
			break;
		}

	raw_spin_unlock_irqrestore(&b->lock, flags);

	return l == tgt_l;
}

Contributors
Person
Tokens
Prop
Commits
CommitProp
Martin KaFai Lau
109
78.99%
1
33.33%
Alexei Starovoitov
29
21.01%
2
66.67%
Total
138
100.00%
3
100.00%

/* Called from syscall */


static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
{
	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
	struct hlist_nulls_head *head;
	struct htab_elem *l, *next_l;
	u32 hash, key_size;
	int i = 0;

	WARN_ON_ONCE(!rcu_read_lock_held());

	key_size = map->key_size;

	if (!key)
		goto find_first_elem;

	hash = htab_map_hash(key, key_size);

	head = select_bucket(htab, hash);

	/* lookup the key */
	l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets);

	if (!l)
		goto find_first_elem;

	/* key was found, get next key in the same bucket */
	next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)),
				  struct htab_elem, hash_node);

	if (next_l) {
		/* if next elem in this hash list is non-zero, just return it */
		memcpy(next_key, next_l->key, key_size);
		return 0;
	}

	/* no more elements in this hash list, go to the next bucket */
	i = hash & (htab->n_buckets - 1)