Commit 9a9f9dd7 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'ebpf_maps' 



Alexei Starovoitov says:

====================
implementation of eBPF maps

v1->v2:
renamed flags for MAP_UPDATE_ELEM command to be more concise,
clarified commit logs and improved comments in patches 1,3,7
per discussions with Daniel

Old v1 cover:

this set of patches adds implementation of HASH and ARRAY types of eBPF maps
which were described in manpage in commit b4fc1a46("Merge branch 'bpf-next'")

The difference vs previous version of these patches from August:
- added 'flags' attribute to BPF_MAP_UPDATE_ELEM
- in HASH type implementation removed per-map kmem_cache.
  I was doing kmem_cache_create() for every map to enable selective slub
  debugging to check for overflows and leaks. Now it's not needed, so just
  use normal kmalloc() for map elements.
- added ARRAY type which was mentioned in manpage, but wasn't public yet
- added map testsuite and removed temporary bits from test_stubs

Note, eBPF programs cannot be attached to events yet.
It will come in the next set.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 1bbf148d 7943c0f3

include/linux/bpf.h

+6 −1
Original line number Diff line number Diff line
@@ -22,7 +22,7 @@ struct bpf_map_ops { 


	/* funcs callable from userspace and from eBPF programs */

	void *(*map_lookup_elem)(struct bpf_map *map, void *key);

	int (*map_update_elem)(struct bpf_map *map, void *key, void *value);

	int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);

	int (*map_delete_elem)(struct bpf_map *map, void *key);

};
@@ -133,4 +133,9 @@ struct bpf_prog *bpf_prog_get(u32 ufd); 
/* verify correctness of eBPF program */

int bpf_check(struct bpf_prog *fp, union bpf_attr *attr);



/* verifier prototypes for helper functions called from eBPF programs */

extern struct bpf_func_proto bpf_map_lookup_elem_proto;

extern struct bpf_func_proto bpf_map_update_elem_proto;

extern struct bpf_func_proto bpf_map_delete_elem_proto;



#endif /* _LINUX_BPF_H */

include/uapi/linux/bpf.h

+12 −1
Original line number Diff line number Diff line
@@ -82,7 +82,7 @@ enum bpf_cmd { 


	/* create or update key/value pair in a given map

	 * err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)

	 * Using attr->map_fd, attr->key, attr->value

	 * Using attr->map_fd, attr->key, attr->value, attr->flags

	 * returns zero or negative error

	 */

	BPF_MAP_UPDATE_ELEM,
@@ -111,12 +111,19 @@ enum bpf_cmd { 


enum bpf_map_type {

	BPF_MAP_TYPE_UNSPEC,

	BPF_MAP_TYPE_HASH,

	BPF_MAP_TYPE_ARRAY,

};



enum bpf_prog_type {

	BPF_PROG_TYPE_UNSPEC,

};



/* flags for BPF_MAP_UPDATE_ELEM command */

#define BPF_ANY		0 /* create new element or update existing */

#define BPF_NOEXIST	1 /* create new element if it didn't exist */

#define BPF_EXIST	2 /* update existing element */



union bpf_attr {

	struct { /* anonymous struct used by BPF_MAP_CREATE command */

		__u32	map_type;	/* one of enum bpf_map_type */
@@ -132,6 +139,7 @@ union bpf_attr { 
			__aligned_u64 value;

			__aligned_u64 next_key;

		};

		__u64		flags;

	};



	struct { /* anonymous struct used by BPF_PROG_LOAD command */
@@ -150,6 +158,9 @@ union bpf_attr { 
 */

enum bpf_func_id {

	BPF_FUNC_unspec,

	BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(&map, &key) */

	BPF_FUNC_map_update_elem, /* int map_update_elem(&map, &key, &value, flags) */

	BPF_FUNC_map_delete_elem, /* int map_delete_elem(&map, &key) */

	__BPF_FUNC_MAX_ID,

};

kernel/bpf/Makefile

+1 −1
Original line number Diff line number Diff line 
obj-y := core.o

obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o

obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o helpers.o

ifdef CONFIG_TEST_BPF

obj-$(CONFIG_BPF_SYSCALL) += test_stub.o

endif

kernel/bpf/arraymap.c

0 → 100644
+151 −0
Original line number Diff line number Diff line 
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com

 *

 * 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/err.h>

#include <linux/vmalloc.h>

#include <linux/slab.h>

#include <linux/mm.h>



struct bpf_array {

	struct bpf_map map;

	u32 elem_size;

	char value[0] __aligned(8);

};



/* Called from syscall */

static struct bpf_map *array_map_alloc(union bpf_attr *attr)

{

	struct bpf_array *array;

	u32 elem_size;



	/* check sanity of attributes */

	if (attr->max_entries == 0 || attr->key_size != 4 ||

	    attr->value_size == 0)

		return ERR_PTR(-EINVAL);



	elem_size = round_up(attr->value_size, 8);



	/* allocate all map elements and zero-initialize them */

	array = kzalloc(sizeof(*array) + attr->max_entries * elem_size,

			GFP_USER | __GFP_NOWARN);

	if (!array) {

		array = vzalloc(array->map.max_entries * array->elem_size);

		if (!array)

			return ERR_PTR(-ENOMEM);

	}



	/* copy mandatory map attributes */

	array->map.key_size = attr->key_size;

	array->map.value_size = attr->value_size;

	array->map.max_entries = attr->max_entries;



	array->elem_size = elem_size;



	return &array->map;



}



/* Called from syscall or from eBPF program */

static void *array_map_lookup_elem(struct bpf_map *map, void *key)

{

	struct bpf_array *array = container_of(map, struct bpf_array, map);

	u32 index = *(u32 *)key;



	if (index >= array->map.max_entries)

		return NULL;



	return array->value + array->elem_size * index;

}



/* Called from syscall */

static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)

{

	struct bpf_array *array = container_of(map, struct bpf_array, map);

	u32 index = *(u32 *)key;

	u32 *next = (u32 *)next_key;



	if (index >= array->map.max_entries) {

		*next = 0;

		return 0;

	}



	if (index == array->map.max_entries - 1)

		return -ENOENT;



	*next = index + 1;

	return 0;

}



/* Called from syscall or from eBPF program */

static int array_map_update_elem(struct bpf_map *map, void *key, void *value,

				 u64 map_flags)

{

	struct bpf_array *array = container_of(map, struct bpf_array, map);

	u32 index = *(u32 *)key;



	if (map_flags > BPF_EXIST)

		/* unknown flags */

		return -EINVAL;



	if (index >= array->map.max_entries)

		/* all elements were pre-allocated, cannot insert a new one */

		return -E2BIG;



	if (map_flags == BPF_NOEXIST)

		/* all elemenets already exist */

		return -EEXIST;



	memcpy(array->value + array->elem_size * index, value, array->elem_size);

	return 0;

}



/* Called from syscall or from eBPF program */

static int array_map_delete_elem(struct bpf_map *map, void *key)

{

	return -EINVAL;

}



/* Called when map->refcnt goes to zero, either from workqueue or from syscall */

static void array_map_free(struct bpf_map *map)

{

	struct bpf_array *array = container_of(map, struct bpf_array, map);



	/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,

	 * so the programs (can be more than one that used this map) were

	 * disconnected from events. Wait for outstanding programs to complete

	 * and free the array

	 */

	synchronize_rcu();



	kvfree(array);

}



static struct bpf_map_ops array_ops = {

	.map_alloc = array_map_alloc,

	.map_free = array_map_free,

	.map_get_next_key = array_map_get_next_key,

	.map_lookup_elem = array_map_lookup_elem,

	.map_update_elem = array_map_update_elem,

	.map_delete_elem = array_map_delete_elem,

};



static struct bpf_map_type_list tl = {

	.ops = &array_ops,

	.type = BPF_MAP_TYPE_ARRAY,

};



static int __init register_array_map(void)

{

	bpf_register_map_type(&tl);

	return 0;

}

late_initcall(register_array_map);

kernel/bpf/hashtab.c

0 → 100644
+362 −0
Original line number Diff line number Diff line 
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com

 *

 * 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/vmalloc.h>



struct bpf_htab {

	struct bpf_map map;

	struct hlist_head *buckets;

	spinlock_t lock;

	u32 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 {

	struct hlist_node hash_node;

	struct rcu_head rcu;

	u32 hash;

	char key[0] __aligned(8);

};



/* Called from syscall */

static struct bpf_map *htab_map_alloc(union bpf_attr *attr)

{

	struct bpf_htab *htab;

	int err, i;



	htab = kzalloc(sizeof(*htab), GFP_USER);

	if (!htab)

		return ERR_PTR(-ENOMEM);



	/* mandatory map attributes */

	htab->map.key_size = attr->key_size;

	htab->map.value_size = attr->value_size;

	htab->map.max_entries = attr->max_entries;



	/* 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;



	/* 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;



	err = -ENOMEM;

	htab->buckets = kmalloc_array(htab->n_buckets, sizeof(struct hlist_head),

				      GFP_USER | __GFP_NOWARN);



	if (!htab->buckets) {

		htab->buckets = vmalloc(htab->n_buckets * sizeof(struct hlist_head));

		if (!htab->buckets)

			goto free_htab;

	}



	for (i = 0; i < htab->n_buckets; i++)

		INIT_HLIST_HEAD(&htab->buckets[i]);



	spin_lock_init(&htab->lock);

	htab->count = 0;



	htab->elem_size = sizeof(struct htab_elem) +

			  round_up(htab->map.key_size, 8) +

			  htab->map.value_size;

	return &htab->map;



free_htab:

	kfree(htab);

	return ERR_PTR(err);

}



static inline u32 htab_map_hash(const void *key, u32 key_len)

{

	return jhash(key, key_len, 0);

}



static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)

{

	return &htab->buckets[hash & (htab->n_buckets - 1)];

}



static struct htab_elem *lookup_elem_raw(struct hlist_head *head, u32 hash,

					 void *key, u32 key_size)

{

	struct htab_elem *l;



	hlist_for_each_entry_rcu(l, head, hash_node)

		if (l->hash == hash && !memcmp(&l->key, key, key_size))

			return l;



	return NULL;

}



/* Called from syscall or from eBPF program */

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_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_elem_raw(head, hash, key, key_size);



	if (l)

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



	return NULL;

}



/* 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_head *head;

	struct htab_elem *l, *next_l;

	u32 hash, key_size;

	int i;



	WARN_ON_ONCE(!rcu_read_lock_held());



	key_size = map->key_size;



	hash = htab_map_hash(key, key_size);



	head = select_bucket(htab, hash);



	/* lookup the key */

	l = lookup_elem_raw(head, hash, key, key_size);



	if (!l) {

		i = 0;

		goto find_first_elem;

	}



	/* key was found, get next key in the same bucket */

	next_l = hlist_entry_safe(rcu_dereference_raw(hlist_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);

	i++;



find_first_elem:

	/* iterate over buckets */

	for (; i < htab->n_buckets; i++) {

		head = select_bucket(htab, i);



		/* pick first element in the bucket */

		next_l = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),

					  struct htab_elem, hash_node);

		if (next_l) {

			/* if it's not empty, just return it */

			memcpy(next_key, next_l->key, key_size);

			return 0;

		}

	}



	/* itereated over all buckets and all elements */

	return -ENOENT;

}



/* Called from syscall or from eBPF program */

static int htab_map_update_elem(struct bpf_map *map, void *key, void *value,

				u64 map_flags)

{

	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);

	struct htab_elem *l_new, *l_old;

	struct hlist_head *head;

	unsigned long flags;

	u32 key_size;

	int ret;



	if (map_flags > BPF_EXIST)

		/* unknown flags */

		return -EINVAL;



	WARN_ON_ONCE(!rcu_read_lock_held());



	/* allocate new element outside of lock */

	l_new = kmalloc(htab->elem_size, GFP_ATOMIC);

	if (!l_new)

		return -ENOMEM;



	key_size = map->key_size;



	memcpy(l_new->key, key, key_size);

	memcpy(l_new->key + round_up(key_size, 8), value, map->value_size);



	l_new->hash = htab_map_hash(l_new->key, key_size);



	/* bpf_map_update_elem() can be called in_irq() */

	spin_lock_irqsave(&htab->lock, flags);



	head = select_bucket(htab, l_new->hash);



	l_old = lookup_elem_raw(head, l_new->hash, key, key_size);



	if (!l_old && unlikely(htab->count >= map->max_entries)) {

		/* if elem with this 'key' doesn't exist and we've reached

		 * max_entries limit, fail insertion of new elem

		 */

		ret = -E2BIG;

		goto err;

	}



	if (l_old && map_flags == BPF_NOEXIST) {

		/* elem already exists */

		ret = -EEXIST;

		goto err;

	}



	if (!l_old && map_flags == BPF_EXIST) {

		/* elem doesn't exist, cannot update it */

		ret = -ENOENT;

		goto err;

	}



	/* add new element to the head of the list, so that concurrent

	 * search will find it before old elem

	 */

	hlist_add_head_rcu(&l_new->hash_node, head);

	if (l_old) {

		hlist_del_rcu(&l_old->hash_node);

		kfree_rcu(l_old, rcu);

	} else {

		htab->count++;

	}

	spin_unlock_irqrestore(&htab->lock, flags);



	return 0;

err:

	spin_unlock_irqrestore(&htab->lock, flags);

	kfree(l_new);

	return ret;

}



/* Called from syscall or from eBPF program */

static int htab_map_delete_elem(struct bpf_map *map, void *key)

{

	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);

	struct hlist_head *head;

	struct htab_elem *l;

	unsigned long flags;

	u32 hash, key_size;

	int ret = -ENOENT;



	WARN_ON_ONCE(!rcu_read_lock_held());



	key_size = map->key_size;



	hash = htab_map_hash(key, key_size);



	spin_lock_irqsave(&htab->lock, flags);



	head = select_bucket(htab, hash);



	l = lookup_elem_raw(head, hash, key, key_size);



	if (l) {

		hlist_del_rcu(&l->hash_node);

		htab->count--;

		kfree_rcu(l, rcu);

		ret = 0;

	}



	spin_unlock_irqrestore(&htab->lock, flags);

	return ret;

}



static void delete_all_elements(struct bpf_htab *htab)

{

	int i;



	for (i = 0; i < htab->n_buckets; i++) {

		struct hlist_head *head = select_bucket(htab, i);

		struct hlist_node *n;

		struct htab_elem *l;



		hlist_for_each_entry_safe(l, n, head, hash_node) {

			hlist_del_rcu(&l->hash_node);

			htab->count--;

			kfree(l);

		}

	}

}



/* Called when map->refcnt goes to zero, either from workqueue or from syscall */

static void htab_map_free(struct bpf_map *map)

{

	struct bpf_htab *htab = container_of(map, struct bpf_htab, map);



	/* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,

	 * so the programs (can be more than one that used this map) were

	 * disconnected from events. Wait for outstanding critical sections in

	 * these programs to complete

	 */

	synchronize_rcu();



	/* some of kfree_rcu() callbacks for elements of this map may not have

	 * executed. It's ok. Proceed to free residual elements and map itself

	 */

	delete_all_elements(htab);

	kvfree(htab->buckets);

	kfree(htab);

}



static struct bpf_map_ops htab_ops = {

	.map_alloc = htab_map_alloc,

	.map_free = htab_map_free,

	.map_get_next_key = htab_map_get_next_key,

	.map_lookup_elem = htab_map_lookup_elem,

	.map_update_elem = htab_map_update_elem,

	.map_delete_elem = htab_map_delete_elem,

};



static struct bpf_map_type_list tl = {

	.ops = &htab_ops,

	.type = BPF_MAP_TYPE_HASH,

};



static int __init register_htab_map(void)

{

	bpf_register_map_type(&tl);

	return 0;

}

late_initcall(register_htab_map);

CRA Git | Maintained and supported by SUSTech CRA and CCSE