* [PATCH RFC v2 net-next 07/16] bpf: add lookup/update/delete/iterate methods to BPF maps
From: Alexei Starovoitov @ 2014-07-18 4:19 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Linus Torvalds, Andy Lutomirski, Steven Rostedt,
Daniel Borkmann, Chema Gonzalez, Eric Dumazet, Peter Zijlstra,
Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
H. Peter Anvin, Andrew Morton, Kees Cook, linux-api, netdev,
linux-kernel
In-Reply-To: <1405657206-12060-1-git-send-email-ast@plumgrid.com>
'maps' is a generic storage of different types for sharing data between kernel
and userspace.
The maps are accessed from user space via BPF syscall, which has commands:
- create a map with given type and attributes
fd = bpf_map_create(map_type, struct nlattr *attr, int len)
returns fd or negative error
- lookup key in a given map referenced by fd
err = bpf_map_lookup_elem(int fd, void *key, void *value)
returns zero and stores found elem into value or negative error
- create or update key/value pair in a given map
err = bpf_map_update_elem(int fd, void *key, void *value)
returns zero or negative error
- find and delete element by key in a given map
err = bpf_map_delete_elem(int fd, void *key)
- iterate map elements (based on input key return next_key)
err = bpf_map_get_next_key(int fd, void *key, void *next_key)
- close(fd) deletes the map
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
include/linux/bpf.h | 6 ++
include/uapi/linux/bpf.h | 25 ++++++
kernel/bpf/syscall.c | 209 ++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 240 insertions(+)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 57af236a0eb4..91e2caf8edf9 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -18,6 +18,12 @@ struct bpf_map_ops {
/* funcs callable from userspace (via syscall) */
struct bpf_map *(*map_alloc)(struct nlattr *attrs[BPF_MAP_ATTR_MAX + 1]);
void (*map_free)(struct bpf_map *);
+ int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
+
+ /* 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_delete_elem)(struct bpf_map *map, void *key);
};
struct bpf_map {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index dcc7eb97a64a..5e1bfbc9cdc7 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -308,6 +308,31 @@ enum bpf_cmd {
* map is deleted when fd is closed
*/
BPF_MAP_CREATE,
+
+ /* lookup key in a given map referenced by map_id
+ * err = bpf_map_lookup_elem(int map_id, void *key, void *value)
+ * returns zero and stores found elem into value
+ * or negative error
+ */
+ BPF_MAP_LOOKUP_ELEM,
+
+ /* create or update key/value pair in a given map
+ * err = bpf_map_update_elem(int map_id, void *key, void *value)
+ * returns zero or negative error
+ */
+ BPF_MAP_UPDATE_ELEM,
+
+ /* find and delete elem by key in a given map
+ * err = bpf_map_delete_elem(int map_id, void *key)
+ * returns zero or negative error
+ */
+ BPF_MAP_DELETE_ELEM,
+
+ /* lookup key in a given map and return next key
+ * err = bpf_map_get_elem(int map_id, void *key, void *next_key)
+ * returns zero and stores next key or negative error
+ */
+ BPF_MAP_GET_NEXT_KEY,
};
enum bpf_map_attributes {
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index c4a330642653..ca2be66845b3 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -13,6 +13,7 @@
#include <linux/syscalls.h>
#include <net/netlink.h>
#include <linux/anon_inodes.h>
+#include <linux/file.h>
/* mutex to protect insertion/deletion of map_id in IDR */
static DEFINE_MUTEX(bpf_map_lock);
@@ -209,6 +210,202 @@ free_attr:
return err;
}
+static int get_map_id(struct fd f)
+{
+ struct bpf_map *map;
+
+ if (!f.file)
+ return -EBADF;
+
+ if (f.file->f_op != &bpf_map_fops) {
+ fdput(f);
+ return -EINVAL;
+ }
+
+ map = f.file->private_data;
+
+ return map->map_id;
+}
+
+static int map_lookup_elem(int ufd, void __user *ukey, void __user *uvalue)
+{
+ struct fd f = fdget(ufd);
+ struct bpf_map *map;
+ void *key, *value;
+ int err;
+
+ err = get_map_id(f);
+ if (err < 0)
+ return err;
+
+ rcu_read_lock();
+ map = idr_find(&bpf_map_id_idr, err);
+ err = -EINVAL;
+ if (!map)
+ goto err_unlock;
+
+ err = -ENOMEM;
+ key = kmalloc(map->key_size, GFP_ATOMIC);
+ if (!key)
+ goto err_unlock;
+
+ err = -EFAULT;
+ if (copy_from_user(key, ukey, map->key_size) != 0)
+ goto free_key;
+
+ err = -ESRCH;
+ value = map->ops->map_lookup_elem(map, key);
+ if (!value)
+ goto free_key;
+
+ err = -EFAULT;
+ if (copy_to_user(uvalue, value, map->value_size) != 0)
+ goto free_key;
+
+ err = 0;
+
+free_key:
+ kfree(key);
+err_unlock:
+ rcu_read_unlock();
+ fdput(f);
+ return err;
+}
+
+static int map_update_elem(int ufd, void __user *ukey, void __user *uvalue)
+{
+ struct fd f = fdget(ufd);
+ struct bpf_map *map;
+ void *key, *value;
+ int err;
+
+ err = get_map_id(f);
+ if (err < 0)
+ return err;
+
+ rcu_read_lock();
+ map = idr_find(&bpf_map_id_idr, err);
+ err = -EINVAL;
+ if (!map)
+ goto err_unlock;
+
+ err = -ENOMEM;
+ key = kmalloc(map->key_size, GFP_ATOMIC);
+ if (!key)
+ goto err_unlock;
+
+ err = -EFAULT;
+ if (copy_from_user(key, ukey, map->key_size) != 0)
+ goto free_key;
+
+ err = -ENOMEM;
+ value = kmalloc(map->value_size, GFP_ATOMIC);
+ if (!value)
+ goto free_key;
+
+ err = -EFAULT;
+ if (copy_from_user(value, uvalue, map->value_size) != 0)
+ goto free_value;
+
+ err = map->ops->map_update_elem(map, key, value);
+
+free_value:
+ kfree(value);
+free_key:
+ kfree(key);
+err_unlock:
+ rcu_read_unlock();
+ fdput(f);
+ return err;
+}
+
+static int map_delete_elem(int ufd, void __user *ukey)
+{
+ struct fd f = fdget(ufd);
+ struct bpf_map *map;
+ void *key;
+ int err;
+
+ err = get_map_id(f);
+ if (err < 0)
+ return err;
+
+ rcu_read_lock();
+ map = idr_find(&bpf_map_id_idr, err);
+ err = -EINVAL;
+ if (!map)
+ goto err_unlock;
+
+ err = -ENOMEM;
+ key = kmalloc(map->key_size, GFP_ATOMIC);
+ if (!key)
+ goto err_unlock;
+
+ err = -EFAULT;
+ if (copy_from_user(key, ukey, map->key_size) != 0)
+ goto free_key;
+
+ err = map->ops->map_delete_elem(map, key);
+
+free_key:
+ kfree(key);
+err_unlock:
+ rcu_read_unlock();
+ fdput(f);
+ return err;
+}
+
+static int map_get_next_key(int ufd, void __user *ukey, void __user *unext_key)
+{
+ struct fd f = fdget(ufd);
+ struct bpf_map *map;
+ void *key, *next_key;
+ int err;
+
+ err = get_map_id(f);
+ if (err < 0)
+ return err;
+
+ rcu_read_lock();
+ map = idr_find(&bpf_map_id_idr, err);
+ err = -EINVAL;
+ if (!map)
+ goto err_unlock;
+
+ err = -ENOMEM;
+ key = kmalloc(map->key_size, GFP_ATOMIC);
+ if (!key)
+ goto err_unlock;
+
+ err = -EFAULT;
+ if (copy_from_user(key, ukey, map->key_size) != 0)
+ goto free_key;
+
+ err = -ENOMEM;
+ next_key = kmalloc(map->key_size, GFP_ATOMIC);
+ if (!next_key)
+ goto free_key;
+
+ err = map->ops->map_get_next_key(map, key, next_key);
+ if (err)
+ goto free_next_key;
+
+ err = -EFAULT;
+ if (copy_to_user(unext_key, next_key, map->key_size) != 0)
+ goto free_next_key;
+
+ err = 0;
+
+free_next_key:
+ kfree(next_key);
+free_key:
+ kfree(key);
+err_unlock:
+ rcu_read_unlock();
+ fdput(f);
+ return err;
+}
+
SYSCALL_DEFINE5(bpf, int, cmd, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@@ -219,6 +416,18 @@ SYSCALL_DEFINE5(bpf, int, cmd, unsigned long, arg2, unsigned long, arg3,
case BPF_MAP_CREATE:
return map_create((enum bpf_map_type) arg2,
(struct nlattr __user *) arg3, (int) arg4);
+ case BPF_MAP_LOOKUP_ELEM:
+ return map_lookup_elem((int) arg2, (void __user *) arg3,
+ (void __user *) arg4);
+ case BPF_MAP_UPDATE_ELEM:
+ return map_update_elem((int) arg2, (void __user *) arg3,
+ (void __user *) arg4);
+ case BPF_MAP_DELETE_ELEM:
+ return map_delete_elem((int) arg2, (void __user *) arg3);
+
+ case BPF_MAP_GET_NEXT_KEY:
+ return map_get_next_key((int) arg2, (void __user *) arg3,
+ (void __user *) arg4);
default:
return -EINVAL;
}
--
1.7.9.5
^ permalink raw reply related
* [PATCH RFC v2 net-next 08/16] bpf: add hashtable type of BPF maps
From: Alexei Starovoitov @ 2014-07-18 4:19 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Linus Torvalds, Andy Lutomirski, Steven Rostedt,
Daniel Borkmann, Chema Gonzalez, Eric Dumazet, Peter Zijlstra,
Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
H. Peter Anvin, Andrew Morton, Kees Cook, linux-api, netdev,
linux-kernel
In-Reply-To: <1405657206-12060-1-git-send-email-ast@plumgrid.com>
add new map type: BPF_MAP_TYPE_HASH
and its simple (not auto resizeable) hash table implementation
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
include/uapi/linux/bpf.h | 1 +
kernel/bpf/Makefile | 2 +-
kernel/bpf/hashtab.c | 371 ++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 373 insertions(+), 1 deletion(-)
create mode 100644 kernel/bpf/hashtab.c
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 5e1bfbc9cdc7..3ea11ba053a8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -347,6 +347,7 @@ enum bpf_map_attributes {
enum bpf_map_type {
BPF_MAP_TYPE_UNSPEC,
+ BPF_MAP_TYPE_HASH,
};
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index e9f7334ed07a..558e12712ebc 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1 +1 @@
-obj-y := core.o syscall.o
+obj-y := core.o syscall.o hashtab.o
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
new file mode 100644
index 000000000000..6e481cacbba3
--- /dev/null
+++ b/kernel/bpf/hashtab.c
@@ -0,0 +1,371 @@
+/* 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 <net/netlink.h>
+#include <linux/jhash.h>
+
+struct bpf_htab {
+ struct bpf_map map;
+ struct hlist_head *buckets;
+ struct kmem_cache *elem_cache;
+ char *slab_name;
+ 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;
+ struct bpf_htab *htab;
+ u32 hash;
+ u32 pad;
+ char key[0];
+};
+
+#define HASH_MAX_BUCKETS 1024
+#define BPF_MAP_MAX_KEY_SIZE 256
+static struct bpf_map *htab_map_alloc(struct nlattr *attr[BPF_MAP_ATTR_MAX + 1])
+{
+ struct bpf_htab *htab;
+ int err, i;
+
+ htab = kmalloc(sizeof(*htab), GFP_USER);
+ if (!htab)
+ return ERR_PTR(-ENOMEM);
+
+ /* look for mandatory map attributes */
+ err = -EINVAL;
+ if (!attr[BPF_MAP_KEY_SIZE])
+ goto free_htab;
+ htab->map.key_size = nla_get_u32(attr[BPF_MAP_KEY_SIZE]);
+
+ if (!attr[BPF_MAP_VALUE_SIZE])
+ goto free_htab;
+ htab->map.value_size = nla_get_u32(attr[BPF_MAP_VALUE_SIZE]);
+
+ if (!attr[BPF_MAP_MAX_ENTRIES])
+ goto free_htab;
+ htab->map.max_entries = nla_get_u32(attr[BPF_MAP_MAX_ENTRIES]);
+
+ htab->n_buckets = (htab->map.max_entries <= HASH_MAX_BUCKETS) ?
+ htab->map.max_entries : HASH_MAX_BUCKETS;
+
+ /* hash table size must be power of 2 */
+ if ((htab->n_buckets & (htab->n_buckets - 1)) != 0)
+ goto free_htab;
+
+ err = -E2BIG;
+ if (htab->map.key_size > BPF_MAP_MAX_KEY_SIZE)
+ goto free_htab;
+
+ err = -ENOMEM;
+ htab->buckets = kmalloc(htab->n_buckets * sizeof(struct hlist_head),
+ GFP_USER);
+
+ 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;
+
+ htab->slab_name = kasprintf(GFP_USER, "bpf_htab_%p", htab);
+ if (!htab->slab_name)
+ goto free_buckets;
+
+ htab->elem_cache = kmem_cache_create(htab->slab_name,
+ htab->elem_size, 0, 0, NULL);
+ if (!htab->elem_cache)
+ goto free_slab_name;
+
+ return &htab->map;
+
+free_slab_name:
+ kfree(htab->slab_name);
+free_buckets:
+ kfree(htab->buckets);
+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;
+}
+
+/* Must be called with rcu_read_lock. */
+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;
+
+ 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);
+ else
+ return NULL;
+}
+
+/* Must be called with rcu_read_lock. */
+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;
+ } else {
+ /* 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;
+}
+
+static struct htab_elem *htab_alloc_elem(struct bpf_htab *htab)
+{
+ void *l;
+
+ l = kmem_cache_alloc(htab->elem_cache, GFP_ATOMIC);
+ if (!l)
+ return ERR_PTR(-ENOMEM);
+ return l;
+}
+
+static void free_htab_elem_rcu(struct rcu_head *rcu)
+{
+ struct htab_elem *l = container_of(rcu, struct htab_elem, rcu);
+
+ kmem_cache_free(l->htab->elem_cache, l);
+}
+
+static void release_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
+{
+ l->htab = htab;
+ call_rcu(&l->rcu, free_htab_elem_rcu);
+}
+
+/* Must be called with rcu_read_lock. */
+static int htab_map_update_elem(struct bpf_map *map, void *key, void *value)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct htab_elem *l_new, *l_old;
+ struct hlist_head *head;
+ u32 key_size;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ l_new = htab_alloc_elem(htab);
+ if (IS_ERR(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);
+
+ head = select_bucket(htab, l_new->hash);
+
+ l_old = lookup_elem_raw(head, l_new->hash, key, key_size);
+
+ spin_lock_bh(&htab->lock);
+ 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
+ */
+ spin_unlock_bh(&htab->lock);
+ kmem_cache_free(htab->elem_cache, l_new);
+ return -EFBIG;
+ }
+
+ /* 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);
+ release_htab_elem(htab, l_old);
+ } else {
+ htab->count++;
+ }
+ spin_unlock_bh(&htab->lock);
+
+ return 0;
+}
+
+/* Must be called with rcu_read_lock. */
+static int htab_map_delete_elem(struct bpf_map *map, void *key)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+ struct htab_elem *l;
+ struct hlist_head *head;
+ u32 hash, key_size;
+
+ 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) {
+ spin_lock_bh(&htab->lock);
+ hlist_del_rcu(&l->hash_node);
+ htab->count--;
+ release_htab_elem(htab, l);
+ spin_unlock_bh(&htab->lock);
+ return 0;
+ }
+ return -ESRCH;
+}
+
+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--;
+ kmem_cache_free(htab->elem_cache, l);
+ }
+ }
+}
+
+/* called when map->refcnt goes to zero */
+static void htab_map_free(struct bpf_map *map)
+{
+ struct bpf_htab *htab = container_of(map, struct bpf_htab, map);
+
+ /* wait for all outstanding updates to complete */
+ synchronize_rcu();
+
+ /* kmem_cache_free all htab elements */
+ delete_all_elements(htab);
+
+ /* and destroy cache, which might sleep */
+ kmem_cache_destroy(htab->elem_cache);
+
+ kfree(htab->buckets);
+ kfree(htab->slab_name);
+ 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);
--
1.7.9.5
^ permalink raw reply related
* [PATCH RFC v2 net-next 09/16] bpf: expand BPF syscall with program load/unload
From: Alexei Starovoitov @ 2014-07-18 4:19 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Linus Torvalds, Andy Lutomirski, Steven Rostedt,
Daniel Borkmann, Chema Gonzalez, Eric Dumazet, Peter Zijlstra,
Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
H. Peter Anvin, Andrew Morton, Kees Cook, linux-api, netdev,
linux-kernel
In-Reply-To: <1405657206-12060-1-git-send-email-ast@plumgrid.com>
eBPF programs are safe run-to-completion functions with load/unload
methods from userspace similar to kernel modules.
User space API:
- load eBPF program
fd = bpf_prog_load(bpf_prog_type, struct nlattr *prog, int len)
where 'prog' is a sequence of sections (TEXT, LICENSE, MAP_ASSOC)
TEXT - array of eBPF instructions
LICENSE - must be GPL compatible to call helper functions marked gpl_only
MAP_FIXUP - array of {insn idx, map fd} used by kernel to adjust
imm constants in 'mov' instructions used to access maps
- unload eBPF program
close(fd)
User space example of syscall(__NR_bpf, BPF_PROG_LOAD, prog_type, ...)
follows in later patches
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
include/linux/bpf.h | 33 +++++
include/linux/filter.h | 9 +-
include/uapi/linux/bpf.h | 29 +++++
kernel/bpf/core.c | 5 +-
kernel/bpf/syscall.c | 309 ++++++++++++++++++++++++++++++++++++++++++++++
net/core/filter.c | 9 +-
6 files changed, 388 insertions(+), 6 deletions(-)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 91e2caf8edf9..4967619595cc 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -46,4 +46,37 @@ struct bpf_map_type_list {
void bpf_register_map_type(struct bpf_map_type_list *tl);
struct bpf_map *bpf_map_get(u32 map_id);
+/* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
+ * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL
+ * instructions after verifying
+ */
+struct bpf_func_proto {
+ u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+ bool gpl_only;
+};
+
+struct bpf_verifier_ops {
+ /* return eBPF function prototype for verification */
+ const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
+};
+
+struct bpf_prog_type_list {
+ struct list_head list_node;
+ struct bpf_verifier_ops *ops;
+ enum bpf_prog_type type;
+};
+
+void bpf_register_prog_type(struct bpf_prog_type_list *tl);
+
+struct bpf_prog_info {
+ bool is_gpl_compatible;
+ enum bpf_prog_type prog_type;
+ struct bpf_verifier_ops *ops;
+ u32 *used_maps;
+ u32 used_map_cnt;
+};
+
+void free_bpf_prog_info(struct bpf_prog_info *info);
+struct sk_filter *bpf_prog_get(u32 ufd);
+
#endif /* _LINUX_BPF_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index b43ad6a2b3cf..822b310e75e1 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -30,12 +30,17 @@ struct sock_fprog_kern {
struct sk_buff;
struct sock;
struct seccomp_data;
+struct bpf_prog_info;
struct sk_filter {
atomic_t refcnt;
u32 jited:1, /* Is our filter JIT'ed? */
- len:31; /* Number of filter blocks */
- struct sock_fprog_kern *orig_prog; /* Original BPF program */
+ ebpf:1, /* Is it eBPF program ? */
+ len:30; /* Number of filter blocks */
+ union {
+ struct sock_fprog_kern *orig_prog; /* Original BPF program */
+ struct bpf_prog_info *info;
+ };
struct rcu_head rcu;
unsigned int (*bpf_func)(const struct sk_buff *skb,
const struct bpf_insn *filter);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3ea11ba053a8..06ba71b49f64 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -333,6 +333,13 @@ enum bpf_cmd {
* returns zero and stores next key or negative error
*/
BPF_MAP_GET_NEXT_KEY,
+
+ /* verify and load eBPF program
+ * prog_id = bpf_prog_load(bpf_prog_type, struct nlattr *prog, int len)
+ * prog is a sequence of sections
+ * returns fd or negative error
+ */
+ BPF_PROG_LOAD,
};
enum bpf_map_attributes {
@@ -350,4 +357,26 @@ enum bpf_map_type {
BPF_MAP_TYPE_HASH,
};
+enum bpf_prog_attributes {
+ BPF_PROG_UNSPEC,
+ BPF_PROG_TEXT, /* array of eBPF instructions */
+ BPF_PROG_LICENSE, /* license string */
+ BPF_PROG_MAP_FIXUP, /* array of {insn idx, map fd} to fixup insns */
+ __BPF_PROG_ATTR_MAX,
+};
+#define BPF_PROG_ATTR_MAX (__BPF_PROG_ATTR_MAX - 1)
+#define BPF_PROG_MAX_ATTR_SIZE 65535
+
+enum bpf_prog_type {
+ BPF_PROG_TYPE_UNSPEC,
+};
+
+/* integer value in 'imm' field of BPF_CALL instruction selects which helper
+ * function eBPF program intends to call
+ */
+enum bpf_func_id {
+ BPF_FUNC_unspec,
+ __BPF_FUNC_MAX_ID,
+};
+
#endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 265a02cc822d..e65ecdc36358 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -23,6 +23,7 @@
#include <linux/filter.h>
#include <linux/skbuff.h>
#include <asm/unaligned.h>
+#include <linux/bpf.h>
/* Registers */
#define BPF_R0 regs[BPF_REG_0]
@@ -528,9 +529,11 @@ void sk_filter_select_runtime(struct sk_filter *fp)
}
EXPORT_SYMBOL_GPL(sk_filter_select_runtime);
-/* free internal BPF program */
+/* free internal BPF program, called after RCU grace period */
void sk_filter_free(struct sk_filter *fp)
{
+ if (fp->ebpf)
+ free_bpf_prog_info(fp->info);
bpf_jit_free(fp);
}
EXPORT_SYMBOL_GPL(sk_filter_free);
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ca2be66845b3..9e45ca6b6937 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -14,6 +14,8 @@
#include <net/netlink.h>
#include <linux/anon_inodes.h>
#include <linux/file.h>
+#include <linux/license.h>
+#include <linux/filter.h>
/* mutex to protect insertion/deletion of map_id in IDR */
static DEFINE_MUTEX(bpf_map_lock);
@@ -406,6 +408,310 @@ err_unlock:
return err;
}
+static LIST_HEAD(bpf_prog_types);
+
+static int find_prog_type(enum bpf_prog_type type, struct sk_filter *prog)
+{
+ struct bpf_prog_type_list *tl;
+
+ list_for_each_entry(tl, &bpf_prog_types, list_node) {
+ if (tl->type == type) {
+ prog->info->ops = tl->ops;
+ prog->info->prog_type = type;
+ return 0;
+ }
+ }
+ return -EINVAL;
+}
+
+void bpf_register_prog_type(struct bpf_prog_type_list *tl)
+{
+ list_add(&tl->list_node, &bpf_prog_types);
+}
+
+/* fixup insn->imm field of bpf_call instructions:
+ * if (insn->imm == BPF_FUNC_map_lookup_elem)
+ * insn->imm = bpf_map_lookup_elem - __bpf_call_base;
+ * else if (insn->imm == BPF_FUNC_map_update_elem)
+ * insn->imm = bpf_map_update_elem - __bpf_call_base;
+ * else ...
+ *
+ * this function is called after eBPF program passed verification
+ */
+static void fixup_bpf_calls(struct sk_filter *prog)
+{
+ const struct bpf_func_proto *fn;
+ int i;
+
+ for (i = 0; i < prog->len; i++) {
+ struct bpf_insn *insn = &prog->insnsi[i];
+
+ if (insn->code == (BPF_JMP | BPF_CALL)) {
+ /* we reach here when program has bpf_call instructions
+ * and it passed bpf_check(), means that
+ * ops->get_func_proto must have been supplied, check it
+ */
+ BUG_ON(!prog->info->ops->get_func_proto);
+
+ fn = prog->info->ops->get_func_proto(insn->imm);
+ /* all functions that have prototype and verifier allowed
+ * programs to call them, must be real in-kernel functions
+ */
+ BUG_ON(!fn->func);
+ insn->imm = fn->func - __bpf_call_base;
+ }
+ }
+}
+
+/* fixup instructions that are using map_ids:
+ *
+ * BPF_MOV64_IMM(BPF_REG_1, MAP_ID), // r1 = MAP_ID
+ * BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ *
+ * in the 1st insn kernel replaces MAP_ID with global map_id,
+ * since programs are executing out of different contexts and must use
+ * globally visible ids to access maps
+ *
+ * map_fixup is an array of pairs {insn idx, map ufd}
+ *
+ * kernel resolves ufd -> global map_id and adjusts eBPF instructions
+ */
+static int fixup_bpf_map_id(struct sk_filter *prog, struct nlattr *map_fixup)
+{
+ struct {
+ u32 insn_idx;
+ u32 ufd;
+ } *fixup = nla_data(map_fixup);
+ int fixup_len = nla_len(map_fixup) / sizeof(*fixup);
+ struct bpf_insn *insn;
+ struct fd f;
+ u32 idx;
+ int i, map_id;
+
+ if (fixup_len <= 0)
+ return -EINVAL;
+
+ for (i = 0; i < fixup_len; i++) {
+ idx = fixup[i].insn_idx;
+ if (idx >= prog->len)
+ return -EINVAL;
+
+ insn = &prog->insnsi[idx];
+ if (insn->code != (BPF_ALU64 | BPF_MOV | BPF_K) &&
+ insn->code != (BPF_ALU | BPF_MOV | BPF_K))
+ return -EINVAL;
+
+ f = fdget(fixup[i].ufd);
+
+ map_id = get_map_id(f);
+
+ if (map_id < 0)
+ return map_id;
+
+ insn->imm = map_id;
+ fdput(f);
+ }
+ return 0;
+}
+
+/* free eBPF program auxilary data, called after rcu grace period,
+ * so it's safe to drop refcnt on maps used by this program
+ *
+ * called from sk_filter_release()->sk_filter_release_rcu()->sk_filter_free()
+ */
+void free_bpf_prog_info(struct bpf_prog_info *info)
+{
+ bool found;
+ int i;
+
+ for (i = 0; i < info->used_map_cnt; i++) {
+ found = bpf_map_put(info->used_maps[i]);
+ /* all maps that this program was using should obviously still
+ * be there
+ */
+ BUG_ON(!found);
+ }
+ kfree(info);
+}
+
+static int bpf_prog_release(struct inode *inode, struct file *filp)
+{
+ struct sk_filter *prog = filp->private_data;
+
+ sk_unattached_filter_destroy(prog);
+ return 0;
+}
+
+static const struct file_operations bpf_prog_fops = {
+ .release = bpf_prog_release,
+};
+
+static const struct nla_policy prog_policy[BPF_PROG_ATTR_MAX + 1] = {
+ [BPF_PROG_TEXT] = { .type = NLA_BINARY },
+ [BPF_PROG_LICENSE] = { .type = NLA_NUL_STRING },
+ [BPF_PROG_MAP_FIXUP] = { .type = NLA_BINARY },
+};
+
+static int bpf_prog_load(enum bpf_prog_type type, struct nlattr __user *uattr,
+ int len)
+{
+ struct nlattr *tb[BPF_PROG_ATTR_MAX + 1];
+ struct sk_filter *prog;
+ struct bpf_map *map;
+ struct nlattr *attr;
+ size_t insn_len;
+ int err, i;
+ bool is_gpl;
+
+ if (len <= 0 || len > BPF_PROG_MAX_ATTR_SIZE)
+ return -EINVAL;
+
+ attr = kmalloc(len, GFP_USER);
+ if (!attr)
+ return -ENOMEM;
+
+ /* copy eBPF program from user space */
+ err = -EFAULT;
+ if (copy_from_user(attr, uattr, len) != 0)
+ goto free_attr;
+
+ /* perform basic validation */
+ err = nla_parse(tb, BPF_PROG_ATTR_MAX, attr, len, prog_policy);
+ if (err < 0)
+ goto free_attr;
+
+ err = -EINVAL;
+ /* look for mandatory license string */
+ if (!tb[BPF_PROG_LICENSE])
+ goto free_attr;
+
+ /* eBPF programs must be GPL compatible to use GPL-ed functions */
+ is_gpl = license_is_gpl_compatible(nla_data(tb[BPF_PROG_LICENSE]));
+
+ /* look for mandatory array of eBPF instructions */
+ if (!tb[BPF_PROG_TEXT])
+ goto free_attr;
+
+ insn_len = nla_len(tb[BPF_PROG_TEXT]);
+ if (insn_len % sizeof(struct bpf_insn) != 0 || insn_len <= 0)
+ goto free_attr;
+
+ /* plain sk_filter allocation */
+ err = -ENOMEM;
+ prog = kmalloc(sk_filter_size(insn_len), GFP_USER);
+ if (!prog)
+ goto free_attr;
+
+ prog->len = insn_len / sizeof(struct bpf_insn);
+ memcpy(prog->insns, nla_data(tb[BPF_PROG_TEXT]), insn_len);
+ prog->orig_prog = NULL;
+ prog->jited = 0;
+ prog->ebpf = 0;
+ atomic_set(&prog->refcnt, 1);
+
+ if (tb[BPF_PROG_MAP_FIXUP]) {
+ /* if program is using maps, fixup map_ids */
+ err = fixup_bpf_map_id(prog, tb[BPF_PROG_MAP_FIXUP]);
+ if (err < 0)
+ goto free_prog;
+ }
+
+ /* allocate eBPF related auxilary data */
+ prog->info = kzalloc(sizeof(struct bpf_prog_info), GFP_USER);
+ if (!prog->info)
+ goto free_prog;
+ prog->ebpf = 1;
+ prog->info->is_gpl_compatible = is_gpl;
+
+ /* find program type: socket_filter vs tracing_filter */
+ err = find_prog_type(type, prog);
+ if (err < 0)
+ goto free_prog;
+
+ /* lock maps to prevent any changes to maps, since eBPF program may
+ * use them. In such case bpf_check() will populate prog->used_maps
+ */
+ mutex_lock(&bpf_map_lock);
+
+ /* run eBPF verifier */
+ /* err = bpf_check(prog); */
+
+ if (err == 0 && prog->info->used_maps) {
+ /* program passed verifier and it's using some maps,
+ * hold them
+ */
+ for (i = 0; i < prog->info->used_map_cnt; i++) {
+ map = bpf_map_get(prog->info->used_maps[i]);
+ BUG_ON(!map);
+ atomic_inc(&map->refcnt);
+ }
+ }
+ mutex_unlock(&bpf_map_lock);
+
+ if (err < 0)
+ goto free_prog;
+
+ /* fixup BPF_CALL->imm field */
+ fixup_bpf_calls(prog);
+
+ /* eBPF program is ready to be JITed */
+ sk_filter_select_runtime(prog);
+
+ err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC);
+
+ if (err < 0)
+ /* failed to allocate fd */
+ goto free_prog;
+
+ /* user supplied eBPF prog attributes are no longer needed */
+ kfree(attr);
+
+ return err;
+free_prog:
+ sk_filter_free(prog);
+free_attr:
+ kfree(attr);
+ return err;
+}
+
+static struct sk_filter *get_prog(struct fd f)
+{
+ struct sk_filter *prog;
+
+ if (!f.file)
+ return ERR_PTR(-EBADF);
+
+ if (f.file->f_op != &bpf_prog_fops) {
+ fdput(f);
+ return ERR_PTR(-EINVAL);
+ }
+
+ prog = f.file->private_data;
+
+ return prog;
+}
+
+/* called from sk_attach_filter_ebpf() or from tracing filter attach
+ * pairs with
+ * sk_detach_filter()->sk_filter_uncharge()->sk_filter_release()
+ * or with
+ * sk_unattached_filter_destroy()->sk_filter_release()
+ */
+struct sk_filter *bpf_prog_get(u32 ufd)
+{
+ struct fd f = fdget(ufd);
+ struct sk_filter *prog;
+
+ prog = get_prog(f);
+
+ if (IS_ERR(prog))
+ return prog;
+
+ atomic_inc(&prog->refcnt);
+ fdput(f);
+ return prog;
+}
+
SYSCALL_DEFINE5(bpf, int, cmd, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@@ -428,6 +734,9 @@ SYSCALL_DEFINE5(bpf, int, cmd, unsigned long, arg2, unsigned long, arg3,
case BPF_MAP_GET_NEXT_KEY:
return map_get_next_key((int) arg2, (void __user *) arg3,
(void __user *) arg4);
+ case BPF_PROG_LOAD:
+ return bpf_prog_load((enum bpf_prog_type) arg2,
+ (struct nlattr __user *) arg3, (int) arg4);
default:
return -EINVAL;
}
diff --git a/net/core/filter.c b/net/core/filter.c
index f3b2d5e9fe5f..255dba1bb678 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -835,7 +835,7 @@ static void sk_release_orig_filter(struct sk_filter *fp)
{
struct sock_fprog_kern *fprog = fp->orig_prog;
- if (fprog) {
+ if (!fp->ebpf && fprog) {
kfree(fprog->filter);
kfree(fprog);
}
@@ -867,14 +867,16 @@ static void sk_filter_release(struct sk_filter *fp)
void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)
{
- atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc);
+ if (!fp->ebpf)
+ atomic_sub(sk_filter_size(fp->len), &sk->sk_omem_alloc);
sk_filter_release(fp);
}
void sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
atomic_inc(&fp->refcnt);
- atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc);
+ if (!fp->ebpf)
+ atomic_add(sk_filter_size(fp->len), &sk->sk_omem_alloc);
}
static struct sk_filter *__sk_migrate_realloc(struct sk_filter *fp,
@@ -978,6 +980,7 @@ static struct sk_filter *__sk_prepare_filter(struct sk_filter *fp,
fp->bpf_func = NULL;
fp->jited = 0;
+ fp->ebpf = 0;
err = sk_chk_filter(fp->insns, fp->len);
if (err) {
--
1.7.9.5
^ permalink raw reply related
* [PATCH RFC v2 net-next 10/16] bpf: add eBPF verifier
From: Alexei Starovoitov @ 2014-07-18 4:20 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Linus Torvalds, Andy Lutomirski, Steven Rostedt,
Daniel Borkmann, Chema Gonzalez, Eric Dumazet, Peter Zijlstra,
Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
H. Peter Anvin, Andrew Morton, Kees Cook, linux-api, netdev,
linux-kernel
In-Reply-To: <1405657206-12060-1-git-send-email-ast@plumgrid.com>
Safety of eBPF programs is statically determined by the verifier, which detects:
- loops
- out of range jumps
- unreachable instructions
- invalid instructions
- uninitialized register access
- uninitialized stack access
- misaligned stack access
- out of range stack access
- invalid calling convention
It checks that
- R1-R5 registers statisfy function prototype
- program terminates
- BPF_LD_ABS|IND instructions are only used in socket filters
It is configured with:
- bool (*is_valid_access)(int off, int size, enum bpf_access_type type);
that provides information to the verifer which fields of 'ctx'
are accessible (remember 'ctx' is the first argument to eBPF program)
- const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
reports argument types of kernel helper functions that eBPF program
may call, so that verifier can checks that R1-R5 types match prototype
More details in Documentation/networking/filter.txt
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
Documentation/networking/filter.txt | 233 ++++++
include/linux/bpf.h | 49 ++
include/uapi/linux/bpf.h | 1 +
kernel/bpf/Makefile | 2 +-
kernel/bpf/syscall.c | 2 +-
kernel/bpf/verifier.c | 1520 +++++++++++++++++++++++++++++++++++
6 files changed, 1805 insertions(+), 2 deletions(-)
create mode 100644 kernel/bpf/verifier.c
diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt
index e14e486f69cd..778f763fce10 100644
--- a/Documentation/networking/filter.txt
+++ b/Documentation/networking/filter.txt
@@ -995,6 +995,108 @@ BPF_XADD | BPF_DW | BPF_STX: lock xadd *(u64 *)(dst_reg + off16) += src_reg
Where size is one of: BPF_B or BPF_H or BPF_W or BPF_DW. Note that 1 and
2 byte atomic increments are not supported.
+eBPF verifier
+-------------
+The safety of the eBPF program is determined in two steps.
+
+First step does DAG check to disallow loops and other CFG validation.
+In particular it will detect programs that have unreachable instructions.
+(though classic BPF checker allows them)
+
+Second step starts from the first insn and descends all possible paths.
+It simulates execution of every insn and observes the state change of
+registers and stack.
+
+At the start of the program the register R1 contains a pointer to context
+and has type PTR_TO_CTX.
+If verifier sees an insn that does R2=R1, then R2 has now type
+PTR_TO_CTX as well and can be used on the right hand side of expression.
+If R1=PTR_TO_CTX and insn is R2=R1+R1, then R2=INVALID_PTR,
+since addition of two valid pointers makes invalid pointer.
+
+If register was never written to, it's not readable:
+ bpf_mov R0 = R2
+ bpf_exit
+will be rejected, since R2 is unreadable at the start of the program.
+
+After kernel function call, R1-R5 are reset to unreadable and
+R0 has a return type of the function.
+
+Since R6-R9 are callee saved, their state is preserved across the call.
+ bpf_mov R6 = 1
+ bpf_call foo
+ bpf_mov R0 = R6
+ bpf_exit
+is a correct program. If there was R1 instead of R6, it would have
+been rejected.
+
+Classic BPF register X is mapped to eBPF register R7 inside sk_convert_filter(),
+so that its state is preserved across calls.
+
+load/store instructions are allowed only with registers of valid types, which
+are PTR_TO_CTX, PTR_TO_MAP, PTR_TO_STACK. They are bounds and alignment checked.
+For example:
+ bpf_mov R1 = 1
+ bpf_mov R2 = 2
+ bpf_xadd *(u32 *)(R1 + 3) += R2
+ bpf_exit
+will be rejected, since R1 doesn't have a valid pointer type at the time of
+execution of instruction bpf_xadd.
+
+At the start R1 contains pointer to ctx and R1 type is PTR_TO_CTX.
+ctx is generic. verifier is configured to known what context is for particular
+class of bpf programs. For example, context == skb (for socket filters) and
+ctx == seccomp_data for seccomp filters.
+A callback is used to customize verifier to restrict eBPF program access to only
+certain fields within ctx structure with specified size and alignment.
+
+For example, the following insn:
+ bpf_ld R0 = *(u32 *)(R6 + 8)
+intends to load a word from address R6 + 8 and store it into R0
+If R6=PTR_TO_CTX, via is_valid_access() callback the verifier will know
+that offset 8 of size 4 bytes can be accessed for reading, otherwise
+the verifier will reject the program.
+If R6=PTR_TO_STACK, then access should be aligned and be within
+stack bounds, which are [-MAX_BPF_STACK, 0). In this example offset is 8,
+so it will fail verification, since it's out of bounds.
+
+The verifier will allow eBPF program to read data from stack only after
+it wrote into it.
+Classic BPF verifier does similar check with M[0-15] memory slots.
+For example:
+ bpf_ld R0 = *(u32 *)(R10 - 4)
+ bpf_exit
+is invalid program.
+Though R10 is correct read-only register and has type PTR_TO_STACK
+and R10 - 4 is within stack bounds, there were no stores into that location.
+
+Pointer register spill/fill is tracked as well, since four (R6-R9)
+callee saved registers may not be enough for some programs.
+
+Allowed function calls are customized with bpf_verifier_ops->get_func_proto()
+For example, skb_get_nlattr() function has the following definition:
+ struct bpf_func_proto proto = {RET_INTEGER, PTR_TO_CTX};
+and eBPF verifier will check that this function is always called with first
+argument being 'ctx'. In other words R1 must have type PTR_TO_CTX
+at the time of bpf_call insn.
+After the call register R0 will be set to readable state, so that
+program can access it.
+
+Function calls is a main mechanism to extend functionality of eBPF programs.
+Socket filters may let programs to call one set of functions, whereas tracing
+filters may allow completely different set.
+
+If a function made accessible to eBPF program, it needs to be thought through
+from security point of view. The verifier will guarantee that the function is
+called with valid arguments.
+
+seccomp vs socket filters have different security restrictions for classic BPF.
+Seccomp solves this by two stage verifier: classic BPF verifier is followed
+by seccomp verifier. In case of eBPF one configurable verifier is shared for
+all use cases.
+
+See details of eBPF verifier in kernel/bpf/verifier.c
+
eBPF maps
---------
'maps' is a generic storage of different types for sharing data between kernel
@@ -1064,6 +1166,137 @@ size. It will not let programs pass junk values as 'key' and 'value' to
bpf_map_*_elem() functions, so these functions (implemented in C inside kernel)
can safely access the pointers in all cases.
+Understanding eBPF verifier messages
+------------------------------------
+
+The following are few examples of invalid eBPF programs and verifier error
+messages as seen in the log:
+
+Program with unreachable instructions:
+static struct bpf_insn prog[] = {
+ BPF_EXIT_INSN(),
+ BPF_EXIT_INSN(),
+};
+Error:
+ unreachable insn 1
+
+Program that reads uninitialized register:
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (bf) r0 = r2
+ R2 !read_ok
+
+Program that doesn't initialize R0 before exiting:
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_1),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (bf) r2 = r1
+ 1: (95) exit
+ R0 !read_ok
+
+Program that accesses stack out of bounds:
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, 8, 0),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (7a) *(u64 *)(r10 +8) = 0
+ invalid stack off=8 size=8
+
+Program that doesn't initialize stack before passing its address into function:
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_1, 1),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (bf) r2 = r10
+ 1: (07) r2 += -8
+ 2: (b7) r1 = 1
+ 3: (85) call 1
+ invalid indirect read from stack off -8+0 size 8
+
+Program that uses invalid map_id=2 while calling to map_lookup_elem() function:
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_1, 2),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (7a) *(u64 *)(r10 -8) = 0
+ 1: (bf) r2 = r10
+ 2: (07) r2 += -8
+ 3: (b7) r1 = 2
+ 4: (85) call 1
+ invalid access to map_id=2
+
+Program that doesn't check return value of map_lookup_elem() before accessing
+map element:
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_1, 1),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (7a) *(u64 *)(r10 -8) = 0
+ 1: (bf) r2 = r10
+ 2: (07) r2 += -8
+ 3: (b7) r1 = 1
+ 4: (85) call 1
+ 5: (7a) *(u64 *)(r0 +0) = 0
+ R0 invalid mem access 'map_value_or_null'
+
+Program that correctly checks map_lookup_elem() returned value for NULL, but
+accesses the memory with incorrect alignment:
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_1, 1),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 4, 0),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (7a) *(u64 *)(r10 -8) = 0
+ 1: (bf) r2 = r10
+ 2: (07) r2 += -8
+ 3: (b7) r1 = 1
+ 4: (85) call 1
+ 5: (15) if r0 == 0x0 goto pc+1
+ R0=map_value1 R10=fp
+ 6: (7a) *(u64 *)(r0 +4) = 0
+ misaligned access off 4 size 8
+
+Program that correctly checks map_lookup_elem() returned value for NULL and
+accesses memory with correct alignment in one side of 'if' branch, but fails
+to do so in the other side of 'if' branch:
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ BPF_ALU64_REG(BPF_MOV, BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ BPF_ALU64_IMM(BPF_MOV, BPF_REG_1, 1),
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ BPF_EXIT_INSN(),
+ BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 1),
+ BPF_EXIT_INSN(),
+Error:
+ 0: (7a) *(u64 *)(r10 -8) = 0
+ 1: (bf) r2 = r10
+ 2: (07) r2 += -8
+ 3: (b7) r1 = 1
+ 4: (85) call 1
+ 5: (15) if r0 == 0x0 goto pc+2
+ R0=map_value1 R10=fp
+ 6: (7a) *(u64 *)(r0 +0) = 0
+ 7: (95) exit
+
+ from 5 to 8: R0=imm0 R10=fp
+ 8: (7a) *(u64 *)(r0 +0) = 1
+ R0 invalid mem access 'imm'
+
Testing
-------
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 4967619595cc..b5e90efddfcf 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -46,6 +46,31 @@ struct bpf_map_type_list {
void bpf_register_map_type(struct bpf_map_type_list *tl);
struct bpf_map *bpf_map_get(u32 map_id);
+/* function argument constraints */
+enum bpf_arg_type {
+ ARG_ANYTHING = 0, /* any argument is ok */
+
+ /* the following constraints used to prototype
+ * bpf_map_lookup/update/delete_elem() functions
+ */
+ ARG_CONST_MAP_ID, /* int const argument used as map_id */
+ ARG_PTR_TO_MAP_KEY, /* pointer to stack used as map key */
+ ARG_PTR_TO_MAP_VALUE, /* pointer to stack used as map value */
+
+ /* the following constraints used to prototype bpf_memcmp() and other
+ * functions that access data on eBPF program stack
+ */
+ ARG_PTR_TO_STACK, /* any pointer to eBPF program stack */
+ ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */
+};
+
+/* type of values returned from helper functions */
+enum bpf_return_type {
+ RET_INTEGER, /* function returns integer */
+ RET_VOID, /* function doesn't return anything */
+ RET_PTR_TO_MAP_OR_NULL, /* function returns a pointer to map elem value or NULL */
+};
+
/* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
* to in-kernel helper functions and for adjusting imm32 field in BPF_CALL
* instructions after verifying
@@ -53,11 +78,33 @@ struct bpf_map *bpf_map_get(u32 map_id);
struct bpf_func_proto {
u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
bool gpl_only;
+ enum bpf_return_type ret_type;
+ enum bpf_arg_type arg1_type;
+ enum bpf_arg_type arg2_type;
+ enum bpf_arg_type arg3_type;
+ enum bpf_arg_type arg4_type;
+ enum bpf_arg_type arg5_type;
+};
+
+/* bpf_context is intentionally undefined structure. Pointer to bpf_context is
+ * the first argument to eBPF programs.
+ * For socket filters: 'struct bpf_context *' == 'struct sk_buff *'
+ */
+struct bpf_context;
+
+enum bpf_access_type {
+ BPF_READ = 1,
+ BPF_WRITE = 2
};
struct bpf_verifier_ops {
/* return eBPF function prototype for verification */
const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
+
+ /* return true if 'size' wide access at offset 'off' within bpf_context
+ * with 'type' (read or write) is allowed
+ */
+ bool (*is_valid_access)(int off, int size, enum bpf_access_type type);
};
struct bpf_prog_type_list {
@@ -78,5 +125,7 @@ struct bpf_prog_info {
void free_bpf_prog_info(struct bpf_prog_info *info);
struct sk_filter *bpf_prog_get(u32 ufd);
+/* verify correctness of eBPF program */
+int bpf_check(struct sk_filter *fp);
#endif /* _LINUX_BPF_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 06ba71b49f64..3f288e1d08f1 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -369,6 +369,7 @@ enum bpf_prog_attributes {
enum bpf_prog_type {
BPF_PROG_TYPE_UNSPEC,
+ BPF_PROG_TYPE_SOCKET_FILTER,
};
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 558e12712ebc..95a9035e0f29 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1 +1 @@
-obj-y := core.o syscall.o hashtab.o
+obj-y := core.o syscall.o hashtab.o verifier.o
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9e45ca6b6937..9d441f17548e 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -634,7 +634,7 @@ static int bpf_prog_load(enum bpf_prog_type type, struct nlattr __user *uattr,
mutex_lock(&bpf_map_lock);
/* run eBPF verifier */
- /* err = bpf_check(prog); */
+ err = bpf_check(prog);
if (err == 0 && prog->info->used_maps) {
/* program passed verifier and it's using some maps,
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
new file mode 100644
index 000000000000..0fce771632b4
--- /dev/null
+++ b/kernel/bpf/verifier.c
@@ -0,0 +1,1520 @@
+/* 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/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/capability.h>
+
+/* bpf_check() is a static code analyzer that walks eBPF program
+ * instruction by instruction and updates register/stack state.
+ * All paths of conditional branches are analyzed until 'bpf_exit' insn.
+ *
+ * At the first pass depth-first-search verifies that the BPF program is a DAG.
+ * It rejects the following programs:
+ * - larger than BPF_MAXINSNS insns
+ * - if loop is present (detected via back-edge)
+ * - unreachable insns exist (shouldn't be a forest. program = one function)
+ * - out of bounds or malformed jumps
+ * The second pass is all possible path descent from the 1st insn.
+ * Conditional branch target insns keep a link list of verifier states.
+ * If the state already visited, this path can be pruned.
+ * If it wasn't a DAG, such state prunning would be incorrect, since it would
+ * skip cycles. Since it's analyzing all pathes through the program,
+ * the length of the analysis is limited to 32k insn, which may be hit even
+ * if insn_cnt < 4K, but there are too many branches that change stack/regs.
+ * Number of 'branches to be analyzed' is limited to 1k
+ *
+ * On entry to each instruction, each register has a type, and the instruction
+ * changes the types of the registers depending on instruction semantics.
+ * If instruction is BPF_MOV64_REG(BPF_REG_1, BPF_REG_5), then type of R5 is
+ * copied to R1.
+ *
+ * All registers are 64-bit (even on 32-bit arch)
+ * R0 - return register
+ * R1-R5 argument passing registers
+ * R6-R9 callee saved registers
+ * R10 - frame pointer read-only
+ *
+ * At the start of BPF program the register R1 contains a pointer to bpf_context
+ * and has type PTR_TO_CTX.
+ *
+ * Most of the time the registers have UNKNOWN_VALUE type, which
+ * means the register has some value, but it's not a valid pointer.
+ * Verifier doesn't attemp to track all arithmetic operations on pointers.
+ * The only special case is the sequence:
+ * BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ * BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -20),
+ * 1st insn copies R10 (which has FRAME_PTR) type into R1
+ * and 2nd arithmetic instruction is pattern matched to recognize
+ * that it wants to construct a pointer to some element within stack.
+ * So after 2nd insn, the register R1 has type PTR_TO_STACK
+ * (and -20 constant is saved for further stack bounds checking).
+ * Meaning that this reg is a pointer to stack plus known immediate constant.
+ *
+ * When program is doing load or store insns the type of base register can be:
+ * PTR_TO_MAP, PTR_TO_CTX, FRAME_PTR. These are three pointer types recognized
+ * by check_mem_access() function.
+ *
+ * PTR_TO_MAP means that this register is pointing to 'map element value'
+ * and the range of [ptr, ptr + map's value_size) is accessible.
+ *
+ * registers used to pass pointers to function calls are verified against
+ * function prototypes
+ *
+ * ARG_PTR_TO_MAP_KEY is a function argument constraint.
+ * It means that the register type passed to this function must be
+ * PTR_TO_STACK and it will be used inside the function as
+ * 'pointer to map element key'
+ *
+ * For example the argument constraints for bpf_map_lookup_elem():
+ * .ret_type = RET_PTR_TO_MAP_OR_NULL,
+ * .arg1_type = ARG_CONST_MAP_ID,
+ * .arg2_type = ARG_PTR_TO_MAP_KEY,
+ *
+ * ret_type says that this function returns 'pointer to map elem value or null'
+ * 1st argument is a 'const immediate' value which must be one of valid map_ids.
+ * 2nd argument is a pointer to stack, which will be used inside the function as
+ * a pointer to map element key.
+ *
+ * On the kernel side the helper function looks like:
+ * u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+ * {
+ * struct bpf_map *map;
+ * int map_id = r1;
+ * void *key = (void *) (unsigned long) r2;
+ * void *value;
+ *
+ * here kernel can access 'key' pointer safely, knowing that
+ * [key, key + map->key_size) bytes are valid and were initialized on
+ * the stack of eBPF program.
+ * }
+ *
+ * Corresponding eBPF program looked like:
+ * BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), // after this insn R2 type is FRAME_PTR
+ * BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), // after this insn R2 type is PTR_TO_STACK
+ * BPF_MOV64_IMM(BPF_REG_1, MAP_ID), // after this insn R1 type is CONST_ARG
+ * BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ * here verifier looks a prototype of map_lookup_elem and sees:
+ * .arg1_type == ARG_CONST_MAP_ID and R1->type == CONST_ARG, which is ok so far,
+ * then it goes and finds a map with map_id equal to R1->imm value.
+ * Now verifier knows that this map has key of key_size bytes
+ *
+ * Then .arg2_type == ARG_PTR_TO_MAP_KEY and R2->type == PTR_TO_STACK, ok so far,
+ * Now verifier checks that [R2, R2 + map's key_size) are within stack limits
+ * and were initialized prior to this call.
+ * If it's ok, then verifier allows this BPF_CALL insn and looks at
+ * .ret_type which is RET_PTR_TO_MAP_OR_NULL, so it sets
+ * R0->type = PTR_TO_MAP_OR_NULL which means bpf_map_lookup_elem() function
+ * returns ether pointer to map value or NULL.
+ *
+ * When type PTR_TO_MAP_OR_NULL passes through 'if (reg != 0) goto +off' insn,
+ * the register holding that pointer in the true branch changes state to
+ * PTR_TO_MAP and the same register changes state to CONST_IMM in the false
+ * branch. See check_cond_jmp_op().
+ *
+ * After the call R0 is set to return type of the function and registers R1-R5
+ * are set to NOT_INIT to indicate that they are no longer readable.
+ *
+ * load/store alignment is checked:
+ * BPF_STX_MEM(BPF_DW, dest_reg, src_reg, 3)
+ * is rejected, because it's misaligned
+ *
+ * load/store to stack are bounds checked and register spill is tracked
+ * BPF_STX_MEM(BPF_B, BPF_REG_10, src_reg, 0)
+ * is rejected, because it's out of bounds
+ *
+ * load/store to map are bounds checked:
+ * BPF_STX_MEM(BPF_H, dest_reg, src_reg, 8)
+ * is ok, if dest_reg->type == PTR_TO_MAP and
+ * 8 + sizeof(u16) <= map_info->value_size
+ *
+ * load/store to bpf_context are checked against known fields
+ */
+
+#define _(OP) ({ int ret = OP; if (ret < 0) return ret; })
+
+/* types of values stored in eBPF registers */
+enum bpf_reg_type {
+ NOT_INIT = 0, /* nothing was written into register */
+ UNKNOWN_VALUE, /* reg doesn't contain a valid pointer */
+ PTR_TO_CTX, /* reg points to bpf_context */
+ PTR_TO_MAP, /* reg points to map element value */
+ PTR_TO_MAP_OR_NULL, /* points to map element value or NULL */
+ FRAME_PTR, /* reg == frame_pointer */
+ PTR_TO_STACK, /* reg == frame_pointer + imm */
+ CONST_IMM, /* constant integer value */
+};
+
+struct reg_state {
+ enum bpf_reg_type type;
+ int imm;
+};
+
+enum bpf_stack_slot_type {
+ STACK_INVALID, /* nothing was stored in this stack slot */
+ STACK_SPILL, /* 1st byte of register spilled into stack */
+ STACK_SPILL_PART, /* other 7 bytes of register spill */
+ STACK_MISC /* BPF program wrote some data into this slot */
+};
+
+struct bpf_stack_slot {
+ enum bpf_stack_slot_type stype;
+ enum bpf_reg_type type;
+ int imm;
+};
+
+/* state of the program:
+ * type of all registers and stack info
+ */
+struct verifier_state {
+ struct reg_state regs[MAX_BPF_REG];
+ struct bpf_stack_slot stack[MAX_BPF_STACK];
+};
+
+/* linked list of verifier states used to prune search */
+struct verifier_state_list {
+ struct verifier_state state;
+ struct verifier_state_list *next;
+};
+
+/* verifier_state + insn_idx are pushed to stack when branch is encountered */
+struct verifier_stack_elem {
+ /* verifer state is 'st'
+ * before processing instruction 'insn_idx'
+ * and after processing instruction 'prev_insn_idx'
+ */
+ struct verifier_state st;
+ int insn_idx;
+ int prev_insn_idx;
+ struct verifier_stack_elem *next;
+};
+
+#define MAX_USED_MAPS 64 /* max number of maps accessed by one eBPF program */
+
+/* single container for all structs
+ * one verifier_env per bpf_check() call
+ */
+struct verifier_env {
+ struct sk_filter *prog; /* eBPF program being verified */
+ struct verifier_stack_elem *head; /* stack of verifier states to be processed */
+ int stack_size; /* number of states to be processed */
+ struct verifier_state cur_state; /* current verifier state */
+ struct verifier_state_list **branch_landing; /* search prunning optimization */
+ u32 used_maps[MAX_USED_MAPS]; /* array of map_id's used by eBPF program */
+ u32 used_map_cnt; /* number of used maps */
+};
+
+/* verbose verifier prints what it's seeing
+ * bpf_check() is called under map lock, so no race to access this global var
+ */
+static bool verbose_on;
+
+/* when verifier rejects eBPF program, it does a second path with verbose on
+ * to dump the verification trace to the log, so the user can figure out what's
+ * wrong with the program
+ */
+static int verbose(const char *fmt, ...)
+{
+ va_list args;
+ int ret;
+
+ if (!verbose_on)
+ return 0;
+
+ va_start(args, fmt);
+ ret = vprintk(fmt, args);
+ va_end(args);
+ return ret;
+}
+
+/* string representation of 'enum bpf_reg_type' */
+static const char * const reg_type_str[] = {
+ [NOT_INIT] = "?",
+ [UNKNOWN_VALUE] = "inv",
+ [PTR_TO_CTX] = "ctx",
+ [PTR_TO_MAP] = "map_value",
+ [PTR_TO_MAP_OR_NULL] = "map_value_or_null",
+ [FRAME_PTR] = "fp",
+ [PTR_TO_STACK] = "fp",
+ [CONST_IMM] = "imm",
+};
+
+static void pr_cont_verifier_state(struct verifier_env *env)
+{
+ enum bpf_reg_type t;
+ int i;
+
+ for (i = 0; i < MAX_BPF_REG; i++) {
+ t = env->cur_state.regs[i].type;
+ if (t == NOT_INIT)
+ continue;
+ pr_cont(" R%d=%s", i, reg_type_str[t]);
+ if (t == CONST_IMM ||
+ t == PTR_TO_STACK ||
+ t == PTR_TO_MAP_OR_NULL ||
+ t == PTR_TO_MAP)
+ pr_cont("%d", env->cur_state.regs[i].imm);
+ }
+ for (i = 0; i < MAX_BPF_STACK; i++) {
+ if (env->cur_state.stack[i].stype == STACK_SPILL)
+ pr_cont(" fp%d=%s", -MAX_BPF_STACK + i,
+ reg_type_str[env->cur_state.stack[i].type]);
+ }
+ pr_cont("\n");
+}
+
+static const char *const bpf_class_string[] = {
+ "ld", "ldx", "st", "stx", "alu", "jmp", "BUG", "alu64"
+};
+
+static const char *const bpf_alu_string[] = {
+ "+=", "-=", "*=", "/=", "|=", "&=", "<<=", ">>=", "neg",
+ "%=", "^=", "=", "s>>=", "endian", "BUG", "BUG"
+};
+
+static const char *const bpf_ldst_string[] = {
+ "u32", "u16", "u8", "u64"
+};
+
+static const char *const bpf_jmp_string[] = {
+ "jmp", "==", ">", ">=", "&", "!=", "s>", "s>=", "call", "exit"
+};
+
+static void pr_cont_bpf_insn(struct bpf_insn *insn)
+{
+ u8 class = BPF_CLASS(insn->code);
+
+ if (class == BPF_ALU || class == BPF_ALU64) {
+ if (BPF_SRC(insn->code) == BPF_X)
+ pr_cont("(%02x) %sr%d %s %sr%d\n",
+ insn->code, class == BPF_ALU ? "(u32) " : "",
+ insn->dst_reg,
+ bpf_alu_string[BPF_OP(insn->code) >> 4],
+ class == BPF_ALU ? "(u32) " : "",
+ insn->src_reg);
+ else
+ pr_cont("(%02x) %sr%d %s %s%d\n",
+ insn->code, class == BPF_ALU ? "(u32) " : "",
+ insn->dst_reg,
+ bpf_alu_string[BPF_OP(insn->code) >> 4],
+ class == BPF_ALU ? "(u32) " : "",
+ insn->imm);
+ } else if (class == BPF_STX) {
+ if (BPF_MODE(insn->code) == BPF_MEM)
+ pr_cont("(%02x) *(%s *)(r%d %+d) = r%d\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->dst_reg,
+ insn->off, insn->src_reg);
+ else if (BPF_MODE(insn->code) == BPF_XADD)
+ pr_cont("(%02x) lock *(%s *)(r%d %+d) += r%d\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->dst_reg, insn->off,
+ insn->src_reg);
+ else
+ pr_cont("BUG_%02x\n", insn->code);
+ } else if (class == BPF_ST) {
+ if (BPF_MODE(insn->code) != BPF_MEM) {
+ pr_cont("BUG_st_%02x\n", insn->code);
+ return;
+ }
+ pr_cont("(%02x) *(%s *)(r%d %+d) = %d\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->dst_reg,
+ insn->off, insn->imm);
+ } else if (class == BPF_LDX) {
+ if (BPF_MODE(insn->code) != BPF_MEM) {
+ pr_cont("BUG_ldx_%02x\n", insn->code);
+ return;
+ }
+ pr_cont("(%02x) r%d = *(%s *)(r%d %+d)\n",
+ insn->code, insn->dst_reg,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->src_reg, insn->off);
+ } else if (class == BPF_LD) {
+ if (BPF_MODE(insn->code) == BPF_ABS) {
+ pr_cont("(%02x) r0 = *(%s *)skb[%d]\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->imm);
+ } else if (BPF_MODE(insn->code) == BPF_IND) {
+ pr_cont("(%02x) r0 = *(%s *)skb[r%d + %d]\n",
+ insn->code,
+ bpf_ldst_string[BPF_SIZE(insn->code) >> 3],
+ insn->src_reg, insn->imm);
+ } else {
+ pr_cont("BUG_ld_%02x\n", insn->code);
+ return;
+ }
+ } else if (class == BPF_JMP) {
+ u8 opcode = BPF_OP(insn->code);
+
+ if (opcode == BPF_CALL) {
+ pr_cont("(%02x) call %d\n", insn->code, insn->imm);
+ } else if (insn->code == (BPF_JMP | BPF_JA)) {
+ pr_cont("(%02x) goto pc%+d\n",
+ insn->code, insn->off);
+ } else if (insn->code == (BPF_JMP | BPF_EXIT)) {
+ pr_cont("(%02x) exit\n", insn->code);
+ } else if (BPF_SRC(insn->code) == BPF_X) {
+ pr_cont("(%02x) if r%d %s r%d goto pc%+d\n",
+ insn->code, insn->dst_reg,
+ bpf_jmp_string[BPF_OP(insn->code) >> 4],
+ insn->src_reg, insn->off);
+ } else {
+ pr_cont("(%02x) if r%d %s 0x%x goto pc%+d\n",
+ insn->code, insn->dst_reg,
+ bpf_jmp_string[BPF_OP(insn->code) >> 4],
+ insn->imm, insn->off);
+ }
+ } else {
+ pr_cont("(%02x) %s\n", insn->code, bpf_class_string[class]);
+ }
+}
+
+static int pop_stack(struct verifier_env *env, int *prev_insn_idx)
+{
+ struct verifier_stack_elem *elem;
+ int insn_idx;
+
+ if (env->head == NULL)
+ return -1;
+
+ memcpy(&env->cur_state, &env->head->st, sizeof(env->cur_state));
+ insn_idx = env->head->insn_idx;
+ if (prev_insn_idx)
+ *prev_insn_idx = env->head->prev_insn_idx;
+ elem = env->head->next;
+ kfree(env->head);
+ env->head = elem;
+ env->stack_size--;
+ return insn_idx;
+}
+
+static struct verifier_state *push_stack(struct verifier_env *env, int insn_idx,
+ int prev_insn_idx)
+{
+ struct verifier_stack_elem *elem;
+
+ elem = kmalloc(sizeof(struct verifier_stack_elem), GFP_KERNEL);
+ if (!elem)
+ goto err;
+
+ memcpy(&elem->st, &env->cur_state, sizeof(env->cur_state));
+ elem->insn_idx = insn_idx;
+ elem->prev_insn_idx = prev_insn_idx;
+ elem->next = env->head;
+ env->head = elem;
+ env->stack_size++;
+ if (env->stack_size > 1024) {
+ verbose("BPF program is too complex\n");
+ goto err;
+ }
+ return &elem->st;
+err:
+ /* pop all elements and return */
+ while (pop_stack(env, NULL) >= 0);
+ return NULL;
+}
+
+#define CALLER_SAVED_REGS 6
+static const int caller_saved[CALLER_SAVED_REGS] = {
+ BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
+};
+
+static void init_reg_state(struct reg_state *regs)
+{
+ int i;
+
+ for (i = 0; i < MAX_BPF_REG; i++) {
+ regs[i].type = NOT_INIT;
+ regs[i].imm = 0;
+ }
+
+ /* frame pointer */
+ regs[BPF_REG_FP].type = FRAME_PTR;
+
+ /* 1st arg to a function */
+ regs[BPF_REG_1].type = PTR_TO_CTX;
+}
+
+static void mark_reg_unknown_value(struct reg_state *regs, int regno)
+{
+ regs[regno].type = UNKNOWN_VALUE;
+ regs[regno].imm = 0;
+}
+
+static int check_reg_arg(struct reg_state *regs, int regno, bool is_src)
+{
+ if (is_src) {
+ if (regs[regno].type == NOT_INIT) {
+ verbose("R%d !read_ok\n", regno);
+ return -EACCES;
+ }
+ } else {
+ if (regno == BPF_REG_FP)
+ /* frame pointer is read only */
+ return -EACCES;
+ mark_reg_unknown_value(regs, regno);
+ }
+ return 0;
+}
+
+static int bpf_size_to_bytes(int bpf_size)
+{
+ if (bpf_size == BPF_W)
+ return 4;
+ else if (bpf_size == BPF_H)
+ return 2;
+ else if (bpf_size == BPF_B)
+ return 1;
+ else if (bpf_size == BPF_DW)
+ return 8;
+ else
+ return -EACCES;
+}
+
+static int check_stack_write(struct verifier_state *state, int off, int size,
+ int value_regno)
+{
+ struct bpf_stack_slot *slot;
+ int i;
+
+ if (value_regno >= 0 &&
+ (state->regs[value_regno].type == PTR_TO_MAP ||
+ state->regs[value_regno].type == PTR_TO_STACK ||
+ state->regs[value_regno].type == PTR_TO_CTX)) {
+
+ /* register containing pointer is being spilled into stack */
+ if (size != 8) {
+ verbose("invalid size of register spill\n");
+ return -EACCES;
+ }
+
+ slot = &state->stack[MAX_BPF_STACK + off];
+ slot->stype = STACK_SPILL;
+ /* save register state */
+ slot->type = state->regs[value_regno].type;
+ slot->imm = state->regs[value_regno].imm;
+ for (i = 1; i < 8; i++) {
+ slot = &state->stack[MAX_BPF_STACK + off + i];
+ slot->stype = STACK_SPILL_PART;
+ slot->type = UNKNOWN_VALUE;
+ slot->imm = 0;
+ }
+ } else {
+
+ /* regular write of data into stack */
+ for (i = 0; i < size; i++) {
+ slot = &state->stack[MAX_BPF_STACK + off + i];
+ slot->stype = STACK_MISC;
+ slot->type = UNKNOWN_VALUE;
+ slot->imm = 0;
+ }
+ }
+ return 0;
+}
+
+static int check_stack_read(struct verifier_state *state, int off, int size,
+ int value_regno)
+{
+ int i;
+ struct bpf_stack_slot *slot;
+
+ slot = &state->stack[MAX_BPF_STACK + off];
+
+ if (slot->stype == STACK_SPILL) {
+ if (size != 8) {
+ verbose("invalid size of register spill\n");
+ return -EACCES;
+ }
+ for (i = 1; i < 8; i++) {
+ if (state->stack[MAX_BPF_STACK + off + i].stype !=
+ STACK_SPILL_PART) {
+ verbose("corrupted spill memory\n");
+ return -EACCES;
+ }
+ }
+
+ /* restore register state from stack */
+ state->regs[value_regno].type = slot->type;
+ state->regs[value_regno].imm = slot->imm;
+ return 0;
+ } else {
+ for (i = 0; i < size; i++) {
+ if (state->stack[MAX_BPF_STACK + off + i].stype !=
+ STACK_MISC) {
+ verbose("invalid read from stack off %d+%d size %d\n",
+ off, i, size);
+ return -EACCES;
+ }
+ }
+ /* have read misc data from the stack */
+ mark_reg_unknown_value(state->regs, value_regno);
+ return 0;
+ }
+}
+
+static int remember_map_id(struct verifier_env *env, u32 map_id)
+{
+ int i;
+
+ /* check whether we recorded this map_id already */
+ for (i = 0; i < env->used_map_cnt; i++)
+ if (env->used_maps[i] == map_id)
+ return 0;
+
+ if (env->used_map_cnt >= MAX_USED_MAPS)
+ return -E2BIG;
+
+ /* remember this map_id */
+ env->used_maps[env->used_map_cnt++] = map_id;
+ return 0;
+}
+
+static int get_map_info(struct verifier_env *env, u32 map_id,
+ struct bpf_map **map)
+{
+ /* if BPF program contains bpf_map_lookup_elem(map_id, key)
+ * the incorrect map_id will be caught here
+ */
+ *map = bpf_map_get(map_id);
+ if (!*map) {
+ verbose("invalid access to map_id=%d\n", map_id);
+ return -EACCES;
+ }
+
+ _(remember_map_id(env, map_id));
+
+ return 0;
+}
+
+/* check read/write into map element returned by bpf_map_lookup_elem() */
+static int check_map_access(struct verifier_env *env, int regno, int off,
+ int size)
+{
+ struct bpf_map *map;
+ int map_id = env->cur_state.regs[regno].imm;
+
+ _(get_map_info(env, map_id, &map));
+
+ if (off < 0 || off + size > map->value_size) {
+ verbose("invalid access to map_id=%d leaf_size=%d off=%d size=%d\n",
+ map_id, map->value_size, off, size);
+ return -EACCES;
+ }
+ return 0;
+}
+
+/* check access to 'struct bpf_context' fields */
+static int check_ctx_access(struct verifier_env *env, int off, int size,
+ enum bpf_access_type t)
+{
+ if (env->prog->info->ops->is_valid_access &&
+ env->prog->info->ops->is_valid_access(off, size, t))
+ return 0;
+
+ verbose("invalid bpf_context access off=%d size=%d\n", off, size);
+ return -EACCES;
+}
+
+static int check_mem_access(struct verifier_env *env, int regno, int off,
+ int bpf_size, enum bpf_access_type t,
+ int value_regno)
+{
+ struct verifier_state *state = &env->cur_state;
+ int size;
+
+ _(size = bpf_size_to_bytes(bpf_size));
+
+ if (off % size != 0) {
+ verbose("misaligned access off %d size %d\n", off, size);
+ return -EACCES;
+ }
+
+ if (state->regs[regno].type == PTR_TO_MAP) {
+ _(check_map_access(env, regno, off, size));
+ if (t == BPF_READ)
+ mark_reg_unknown_value(state->regs, value_regno);
+ } else if (state->regs[regno].type == PTR_TO_CTX) {
+ _(check_ctx_access(env, off, size, t));
+ if (t == BPF_READ)
+ mark_reg_unknown_value(state->regs, value_regno);
+ } else if (state->regs[regno].type == FRAME_PTR) {
+ if (off >= 0 || off < -MAX_BPF_STACK) {
+ verbose("invalid stack off=%d size=%d\n", off, size);
+ return -EACCES;
+ }
+ if (t == BPF_WRITE)
+ _(check_stack_write(state, off, size, value_regno));
+ else
+ _(check_stack_read(state, off, size, value_regno));
+ } else {
+ verbose("R%d invalid mem access '%s'\n",
+ regno, reg_type_str[state->regs[regno].type]);
+ return -EACCES;
+ }
+ return 0;
+}
+
+/* when register 'regno' is passed into function that will read 'access_size'
+ * bytes from that pointer, make sure that it's within stack boundary
+ * and all elements of stack are initialized
+ */
+static int check_stack_boundary(struct verifier_env *env,
+ int regno, int access_size)
+{
+ struct verifier_state *state = &env->cur_state;
+ struct reg_state *regs = state->regs;
+ int off, i;
+
+ if (regs[regno].type != PTR_TO_STACK)
+ return -EACCES;
+
+ off = regs[regno].imm;
+ if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
+ access_size <= 0) {
+ verbose("invalid stack type R%d off=%d access_size=%d\n",
+ regno, off, access_size);
+ return -EACCES;
+ }
+
+ for (i = 0; i < access_size; i++) {
+ if (state->stack[MAX_BPF_STACK + off + i].stype != STACK_MISC) {
+ verbose("invalid indirect read from stack off %d+%d size %d\n",
+ off, i, access_size);
+ return -EACCES;
+ }
+ }
+ return 0;
+}
+
+static int check_func_arg(struct verifier_env *env, int regno,
+ enum bpf_arg_type arg_type, int *map_id,
+ struct bpf_map **mapp)
+{
+ struct reg_state *reg = env->cur_state.regs + regno;
+ enum bpf_reg_type expected_type;
+
+ if (arg_type == ARG_ANYTHING)
+ return 0;
+
+ if (reg->type == NOT_INIT) {
+ verbose("R%d !read_ok\n", regno);
+ return -EACCES;
+ }
+
+ if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) {
+ expected_type = PTR_TO_STACK;
+ } else if (arg_type == ARG_CONST_MAP_ID || arg_type == ARG_CONST_STACK_SIZE) {
+ expected_type = CONST_IMM;
+ } else {
+ verbose("unsupported arg_type %d\n", arg_type);
+ return -EFAULT;
+ }
+
+ if (reg->type != expected_type) {
+ verbose("R%d type=%s expected=%s\n", regno,
+ reg_type_str[reg->type], reg_type_str[expected_type]);
+ return -EACCES;
+ }
+
+ if (arg_type == ARG_CONST_MAP_ID) {
+ /* bpf_map_xxx(map_id) call: check that map_id is valid */
+ *map_id = reg->imm;
+ _(get_map_info(env, reg->imm, mapp));
+ } else if (arg_type == ARG_PTR_TO_MAP_KEY) {
+ /*
+ * bpf_map_xxx(..., map_id, ..., key) call:
+ * check that [key, key + map->key_size) are within
+ * stack limits and initialized
+ */
+ if (!*mapp) {
+ /*
+ * in function declaration map_id must come before
+ * map_key or map_elem, so that it's verified
+ * and known before we have to check map_key here
+ */
+ verbose("invalid map_id to access map->key\n");
+ return -EACCES;
+ }
+ _(check_stack_boundary(env, regno, (*mapp)->key_size));
+ } else if (arg_type == ARG_PTR_TO_MAP_VALUE) {
+ /*
+ * bpf_map_xxx(..., map_id, ..., value) call:
+ * check [value, value + map->value_size) validity
+ */
+ if (!*mapp) {
+ verbose("invalid map_id to access map->elem\n");
+ return -EACCES;
+ }
+ _(check_stack_boundary(env, regno, (*mapp)->value_size));
+ } else if (arg_type == ARG_CONST_STACK_SIZE) {
+ /*
+ * bpf_xxx(..., buf, len) call will access 'len' bytes
+ * from stack pointer 'buf'. Check it
+ * note: regno == len, regno - 1 == buf
+ */
+ _(check_stack_boundary(env, regno - 1, reg->imm));
+ }
+
+ return 0;
+}
+
+static int check_call(struct verifier_env *env, int func_id)
+{
+ struct verifier_state *state = &env->cur_state;
+ const struct bpf_func_proto *fn = NULL;
+ struct reg_state *regs = state->regs;
+ struct bpf_map *map = NULL;
+ struct reg_state *reg;
+ int map_id = -1;
+ int i;
+
+ /* find function prototype */
+ if (func_id <= 0 || func_id >= __BPF_FUNC_MAX_ID) {
+ verbose("invalid func %d\n", func_id);
+ return -EINVAL;
+ }
+
+ if (env->prog->info->ops->get_func_proto)
+ fn = env->prog->info->ops->get_func_proto(func_id);
+
+ if (!fn) {
+ verbose("unknown func %d\n", func_id);
+ return -EINVAL;
+ }
+
+ /* eBPF programs must be GPL compatible to use GPL-ed functions */
+ if (!env->prog->info->is_gpl_compatible && fn->gpl_only) {
+ verbose("cannot call GPL only function from proprietary program\n");
+ return -EINVAL;
+ }
+
+ /* check args */
+ _(check_func_arg(env, BPF_REG_1, fn->arg1_type, &map_id, &map));
+ _(check_func_arg(env, BPF_REG_2, fn->arg2_type, &map_id, &map));
+ _(check_func_arg(env, BPF_REG_3, fn->arg3_type, &map_id, &map));
+ _(check_func_arg(env, BPF_REG_4, fn->arg4_type, &map_id, &map));
+ _(check_func_arg(env, BPF_REG_5, fn->arg5_type, &map_id, &map));
+
+ /* reset caller saved regs */
+ for (i = 0; i < CALLER_SAVED_REGS; i++) {
+ reg = regs + caller_saved[i];
+ reg->type = NOT_INIT;
+ reg->imm = 0;
+ }
+
+ /* update return register */
+ if (fn->ret_type == RET_INTEGER) {
+ regs[BPF_REG_0].type = UNKNOWN_VALUE;
+ } else if (fn->ret_type == RET_VOID) {
+ regs[BPF_REG_0].type = NOT_INIT;
+ } else if (fn->ret_type == RET_PTR_TO_MAP_OR_NULL) {
+ regs[BPF_REG_0].type = PTR_TO_MAP_OR_NULL;
+ /*
+ * remember map_id, so that check_map_access()
+ * can check 'value_size' boundary of memory access
+ * to map element returned from bpf_map_lookup_elem()
+ */
+ regs[BPF_REG_0].imm = map_id;
+ } else {
+ verbose("unknown return type %d of func %d\n",
+ fn->ret_type, func_id);
+ return -EINVAL;
+ }
+ return 0;
+}
+
+/* check validity of 32-bit and 64-bit arithmetic operations */
+static int check_alu_op(struct reg_state *regs, struct bpf_insn *insn)
+{
+ u8 opcode = BPF_OP(insn->code);
+
+ if (opcode == BPF_END || opcode == BPF_NEG) {
+ if (BPF_SRC(insn->code) != BPF_X)
+ return -EINVAL;
+ /* check src operand */
+ _(check_reg_arg(regs, insn->dst_reg, 1));
+
+ /* check dest operand */
+ _(check_reg_arg(regs, insn->dst_reg, 0));
+
+ } else if (opcode == BPF_MOV) {
+
+ if (BPF_SRC(insn->code) == BPF_X)
+ /* check src operand */
+ _(check_reg_arg(regs, insn->src_reg, 1));
+
+ /* check dest operand */
+ _(check_reg_arg(regs, insn->dst_reg, 0));
+
+ if (BPF_SRC(insn->code) == BPF_X) {
+ if (BPF_CLASS(insn->code) == BPF_ALU64) {
+ /* case: R1 = R2
+ * copy register state to dest reg
+ */
+ regs[insn->dst_reg].type = regs[insn->src_reg].type;
+ regs[insn->dst_reg].imm = regs[insn->src_reg].imm;
+ } else {
+ regs[insn->dst_reg].type = UNKNOWN_VALUE;
+ regs[insn->dst_reg].imm = 0;
+ }
+ } else {
+ /* case: R = imm
+ * remember the value we stored into this reg
+ */
+ regs[insn->dst_reg].type = CONST_IMM;
+ regs[insn->dst_reg].imm = insn->imm;
+ }
+
+ } else { /* all other ALU ops: and, sub, xor, add, ... */
+
+ int stack_relative = 0;
+
+ if (BPF_SRC(insn->code) == BPF_X)
+ /* check src1 operand */
+ _(check_reg_arg(regs, insn->src_reg, 1));
+
+ /* check src2 operand */
+ _(check_reg_arg(regs, insn->dst_reg, 1));
+
+ if ((opcode == BPF_MOD || opcode == BPF_DIV) &&
+ BPF_SRC(insn->code) == BPF_K && insn->imm == 0) {
+ verbose("div by zero\n");
+ return -EINVAL;
+ }
+
+ if (opcode == BPF_ADD && BPF_CLASS(insn->code) == BPF_ALU64 &&
+ regs[insn->dst_reg].type == FRAME_PTR &&
+ BPF_SRC(insn->code) == BPF_K)
+ stack_relative = 1;
+
+ /* check dest operand */
+ _(check_reg_arg(regs, insn->dst_reg, 0));
+
+ if (stack_relative) {
+ regs[insn->dst_reg].type = PTR_TO_STACK;
+ regs[insn->dst_reg].imm = insn->imm;
+ }
+ }
+
+ return 0;
+}
+
+static int check_cond_jmp_op(struct verifier_env *env,
+ struct bpf_insn *insn, int *insn_idx)
+{
+ struct reg_state *regs = env->cur_state.regs;
+ struct verifier_state *other_branch;
+ u8 opcode = BPF_OP(insn->code);
+
+ if (BPF_SRC(insn->code) == BPF_X)
+ /* check src1 operand */
+ _(check_reg_arg(regs, insn->src_reg, 1));
+
+ /* check src2 operand */
+ _(check_reg_arg(regs, insn->dst_reg, 1));
+
+ /* detect if R == 0 where R was initialized to zero earlier */
+ if (BPF_SRC(insn->code) == BPF_K &&
+ (opcode == BPF_JEQ || opcode == BPF_JNE) &&
+ regs[insn->dst_reg].type == CONST_IMM &&
+ regs[insn->dst_reg].imm == insn->imm) {
+ if (opcode == BPF_JEQ) {
+ /* if (imm == imm) goto pc+off;
+ * only follow the goto, ignore fall-through
+ */
+ *insn_idx += insn->off;
+ return 0;
+ } else {
+ /* if (imm != imm) goto pc+off;
+ * only follow fall-through branch, since
+ * that's where the program will go
+ */
+ return 0;
+ }
+ }
+
+ other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx);
+ if (!other_branch)
+ return -EFAULT;
+
+ /* detect if R == 0 where R is returned value from bpf_map_lookup_elem() */
+ if (BPF_SRC(insn->code) == BPF_K &&
+ insn->imm == 0 && (opcode == BPF_JEQ ||
+ opcode == BPF_JNE) &&
+ regs[insn->dst_reg].type == PTR_TO_MAP_OR_NULL) {
+ if (opcode == BPF_JEQ) {
+ /* next fallthrough insn can access memory via
+ * this register
+ */
+ regs[insn->dst_reg].type = PTR_TO_MAP;
+ /* branch targer cannot access it, since reg == 0 */
+ other_branch->regs[insn->dst_reg].type = CONST_IMM;
+ other_branch->regs[insn->dst_reg].imm = 0;
+ } else {
+ other_branch->regs[insn->dst_reg].type = PTR_TO_MAP;
+ regs[insn->dst_reg].type = CONST_IMM;
+ regs[insn->dst_reg].imm = 0;
+ }
+ } else if (BPF_SRC(insn->code) == BPF_K &&
+ (opcode == BPF_JEQ || opcode == BPF_JNE)) {
+
+ if (opcode == BPF_JEQ) {
+ /* detect if (R == imm) goto
+ * and in the target state recognize that R = imm
+ */
+ other_branch->regs[insn->dst_reg].type = CONST_IMM;
+ other_branch->regs[insn->dst_reg].imm = insn->imm;
+ } else {
+ /* detect if (R != imm) goto
+ * and in the fall-through state recognize that R = imm
+ */
+ regs[insn->dst_reg].type = CONST_IMM;
+ regs[insn->dst_reg].imm = insn->imm;
+ }
+ }
+ if (verbose_on)
+ pr_cont_verifier_state(env);
+ return 0;
+}
+
+/* verify safety of LD_ABS|LD_IND instructions:
+ * - they can only appear in the programs where ctx == skb
+ * - since they are wrappers of function calls, they scratch R1-R5 registers,
+ * preserve R6-R9, and store return value into R0
+ *
+ * Implicit input:
+ * ctx == skb == R6 == CTX
+ *
+ * Explicit input:
+ * SRC == any register
+ * IMM == 32-bit immediate
+ *
+ * Output:
+ * R0 - 8/16/32-bit skb data converted to cpu endianness
+ */
+
+static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn)
+{
+ struct reg_state *regs = env->cur_state.regs;
+ u8 mode = BPF_MODE(insn->code);
+ struct reg_state *reg;
+ int i;
+
+ if (mode != BPF_ABS && mode != BPF_IND)
+ return -EINVAL;
+
+ if (env->prog->info->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) {
+ verbose("BPF_LD_ABS|IND instructions are only allowed in socket filters\n");
+ return -EINVAL;
+ }
+
+ /* check whether implicit source operand (register R6) is readable */
+ _(check_reg_arg(regs, BPF_REG_6, 1));
+
+ if (regs[BPF_REG_6].type != PTR_TO_CTX) {
+ verbose("at the time of BPF_LD_ABS|IND R6 != pointer to skb\n");
+ return -EINVAL;
+ }
+
+ if (mode == BPF_IND)
+ /* check explicit source operand */
+ _(check_reg_arg(regs, insn->src_reg, 1));
+
+ /* reset caller saved regs to unreadable */
+ for (i = 0; i < CALLER_SAVED_REGS; i++) {
+ reg = regs + caller_saved[i];
+ reg->type = NOT_INIT;
+ reg->imm = 0;
+ }
+
+ /* mark destination R0 register as readable, since it contains
+ * the value fetched from the packet
+ */
+ regs[BPF_REG_0].type = UNKNOWN_VALUE;
+ return 0;
+}
+
+/* non-recursive DFS pseudo code
+ * 1 procedure DFS-iterative(G,v):
+ * 2 label v as discovered
+ * 3 let S be a stack
+ * 4 S.push(v)
+ * 5 while S is not empty
+ * 6 t <- S.pop()
+ * 7 if t is what we're looking for:
+ * 8 return t
+ * 9 for all edges e in G.adjacentEdges(t) do
+ * 10 if edge e is already labelled
+ * 11 continue with the next edge
+ * 12 w <- G.adjacentVertex(t,e)
+ * 13 if vertex w is not discovered and not explored
+ * 14 label e as tree-edge
+ * 15 label w as discovered
+ * 16 S.push(w)
+ * 17 continue at 5
+ * 18 else if vertex w is discovered
+ * 19 label e as back-edge
+ * 20 else
+ * 21 // vertex w is explored
+ * 22 label e as forward- or cross-edge
+ * 23 label t as explored
+ * 24 S.pop()
+ *
+ * convention:
+ * 1 - discovered
+ * 2 - discovered and 1st branch labelled
+ * 3 - discovered and 1st and 2nd branch labelled
+ * 4 - explored
+ */
+
+#define STATE_END ((struct verifier_state_list *)-1)
+
+#define PUSH_INT(I) \
+ do { \
+ if (cur_stack >= insn_cnt) { \
+ ret = -E2BIG; \
+ goto free_st; \
+ } \
+ stack[cur_stack++] = I; \
+ } while (0)
+
+#define PEEK_INT() \
+ ({ \
+ int _ret; \
+ if (cur_stack == 0) \
+ _ret = -1; \
+ else \
+ _ret = stack[cur_stack - 1]; \
+ _ret; \
+ })
+
+#define POP_INT() \
+ ({ \
+ int _ret; \
+ if (cur_stack == 0) \
+ _ret = -1; \
+ else \
+ _ret = stack[--cur_stack]; \
+ _ret; \
+ })
+
+#define PUSH_INSN(T, W, E) \
+ do { \
+ int w = W; \
+ if (E == 1 && st[T] >= 2) \
+ break; \
+ if (E == 2 && st[T] >= 3) \
+ break; \
+ if (w >= insn_cnt) { \
+ ret = -EACCES; \
+ goto free_st; \
+ } \
+ if (E == 2) \
+ /* mark branch target for state pruning */ \
+ env->branch_landing[w] = STATE_END; \
+ if (st[w] == 0) { \
+ /* tree-edge */ \
+ st[T] = 1 + E; \
+ st[w] = 1; /* discovered */ \
+ PUSH_INT(w); \
+ goto peak_stack; \
+ } else if (st[w] == 1 || st[w] == 2 || st[w] == 3) { \
+ verbose("back-edge from insn %d to %d\n", t, w); \
+ ret = -EINVAL; \
+ goto free_st; \
+ } else if (st[w] == 4) { \
+ /* forward- or cross-edge */ \
+ st[T] = 1 + E; \
+ } else { \
+ verbose("insn state internal bug\n"); \
+ ret = -EFAULT; \
+ goto free_st; \
+ } \
+ } while (0)
+
+/* non-recursive depth-first-search to detect loops in BPF program
+ * loop == back-edge in directed graph
+ */
+static int check_cfg(struct verifier_env *env)
+{
+ struct bpf_insn *insns = env->prog->insnsi;
+ int insn_cnt = env->prog->len;
+ int cur_stack = 0;
+ int *stack;
+ int ret = 0;
+ int *st;
+ int i, t;
+
+ if (insns[insn_cnt - 1].code != (BPF_JMP | BPF_EXIT)) {
+ verbose("last insn is not a 'ret'\n");
+ return -EINVAL;
+ }
+
+ st = kzalloc(sizeof(int) * insn_cnt, GFP_KERNEL);
+ if (!st)
+ return -ENOMEM;
+
+ stack = kzalloc(sizeof(int) * insn_cnt, GFP_KERNEL);
+ if (!stack) {
+ kfree(st);
+ return -ENOMEM;
+ }
+
+ st[0] = 1; /* mark 1st insn as discovered */
+ PUSH_INT(0);
+
+peak_stack:
+ while ((t = PEEK_INT()) != -1) {
+ if (insns[t].code == (BPF_JMP | BPF_EXIT))
+ goto mark_explored;
+
+ if (BPF_CLASS(insns[t].code) == BPF_JMP) {
+ u8 opcode = BPF_OP(insns[t].code);
+
+ if (opcode == BPF_CALL) {
+ PUSH_INSN(t, t + 1, 1);
+ } else if (opcode == BPF_JA) {
+ if (BPF_SRC(insns[t].code) != BPF_X) {
+ ret = -EINVAL;
+ goto free_st;
+ }
+ PUSH_INSN(t, t + insns[t].off + 1, 1);
+ } else {
+ PUSH_INSN(t, t + 1, 1);
+ PUSH_INSN(t, t + insns[t].off + 1, 2);
+ }
+ /* tell verifier to check for equivalent verifier states
+ * after every call and jump
+ */
+ env->branch_landing[t + 1] = STATE_END;
+ } else {
+ PUSH_INSN(t, t + 1, 1);
+ }
+
+mark_explored:
+ st[t] = 4; /* explored */
+ if (POP_INT() == -1) {
+ verbose("pop_int internal bug\n");
+ ret = -EFAULT;
+ goto free_st;
+ }
+ }
+
+
+ for (i = 0; i < insn_cnt; i++) {
+ if (st[i] != 4) {
+ verbose("unreachable insn %d\n", i);
+ ret = -EINVAL;
+ goto free_st;
+ }
+ }
+
+free_st:
+ kfree(st);
+ kfree(stack);
+ return ret;
+}
+
+/* compare two verifier states
+ *
+ * all states stored in state_list are known to be valid, since
+ * verifier reached 'bpf_exit' instruction through them
+ *
+ * this function is called when verifier exploring different branches of
+ * execution popped from the state stack. If it sees an old state that has
+ * more strict register state and more strict stack state then this execution
+ * branch doesn't need to be explored further, since verifier already
+ * concluded that more strict state leads to valid finish.
+ *
+ * Therefore two states are equivalent if register state is more conservative
+ * and explored stack state is more conservative than the current one.
+ * Example:
+ * explored current
+ * (slot1=INV slot2=MISC) == (slot1=MISC slot2=MISC)
+ * (slot1=MISC slot2=MISC) != (slot1=INV slot2=MISC)
+ *
+ * In other words if current stack state (one being explored) has more
+ * valid slots than old one that already passed validation, it means
+ * the verifier can stop exploring and conclude that current state is valid too
+ *
+ * Similarly with registers. If explored state has register type as invalid
+ * whereas register type in current state is meaningful, it means that
+ * the current state will reach 'bpf_exit' instruction safely
+ */
+static bool states_equal(struct verifier_state *old, struct verifier_state *cur)
+{
+ int i;
+
+ for (i = 0; i < MAX_BPF_REG; i++) {
+ if (memcmp(&old->regs[i], &cur->regs[i],
+ sizeof(old->regs[0])) != 0) {
+ if (old->regs[i].type == NOT_INIT ||
+ old->regs[i].type == UNKNOWN_VALUE)
+ continue;
+ return false;
+ }
+ }
+
+ for (i = 0; i < MAX_BPF_STACK; i++) {
+ if (memcmp(&old->stack[i], &cur->stack[i],
+ sizeof(old->stack[0])) != 0) {
+ if (old->stack[i].stype == STACK_INVALID)
+ continue;
+ return false;
+ }
+ }
+ return true;
+}
+
+static int is_state_visited(struct verifier_env *env, int insn_idx)
+{
+ struct verifier_state_list *new_sl;
+ struct verifier_state_list *sl;
+
+ sl = env->branch_landing[insn_idx];
+ if (!sl)
+ /* no branch jump to this insn, ignore it */
+ return 0;
+
+ while (sl != STATE_END) {
+ if (states_equal(&sl->state, &env->cur_state))
+ /* reached equivalent register/stack state,
+ * prune the search
+ */
+ return 1;
+ sl = sl->next;
+ }
+ new_sl = kmalloc(sizeof(struct verifier_state_list), GFP_KERNEL);
+
+ if (!new_sl)
+ /* ignore ENOMEM, it doesn't affect correctness */
+ return 0;
+
+ /* add new state to the head of linked list */
+ memcpy(&new_sl->state, &env->cur_state, sizeof(env->cur_state));
+ new_sl->next = env->branch_landing[insn_idx];
+ env->branch_landing[insn_idx] = new_sl;
+ return 0;
+}
+
+static int do_check(struct verifier_env *env)
+{
+ struct verifier_state *state = &env->cur_state;
+ struct bpf_insn *insns = env->prog->insnsi;
+ struct reg_state *regs = state->regs;
+ int insn_cnt = env->prog->len;
+ int insn_idx, prev_insn_idx = 0;
+ int insn_processed = 0;
+ bool do_print_state = false;
+
+ init_reg_state(regs);
+ insn_idx = 0;
+ for (;;) {
+ struct bpf_insn *insn;
+ u8 class;
+
+ if (insn_idx >= insn_cnt) {
+ verbose("invalid insn idx %d insn_cnt %d\n",
+ insn_idx, insn_cnt);
+ return -EFAULT;
+ }
+
+ insn = &insns[insn_idx];
+ class = BPF_CLASS(insn->code);
+
+ if (++insn_processed > 32768) {
+ verbose("BPF program is too large. Proccessed %d insn\n",
+ insn_processed);
+ return -E2BIG;
+ }
+
+ if (is_state_visited(env, insn_idx)) {
+ if (verbose_on) {
+ if (do_print_state)
+ pr_cont("\nfrom %d to %d: safe\n",
+ prev_insn_idx, insn_idx);
+ else
+ pr_cont("%d: safe\n", insn_idx);
+ }
+ goto process_bpf_exit;
+ }
+
+ if (verbose_on && do_print_state) {
+ pr_cont("\nfrom %d to %d:", prev_insn_idx, insn_idx);
+ pr_cont_verifier_state(env);
+ do_print_state = false;
+ }
+
+ if (verbose_on) {
+ pr_cont("%d: ", insn_idx);
+ pr_cont_bpf_insn(insn);
+ }
+
+ if (class == BPF_ALU || class == BPF_ALU64) {
+ _(check_alu_op(regs, insn));
+
+ } else if (class == BPF_LDX) {
+ if (BPF_MODE(insn->code) != BPF_MEM)
+ return -EINVAL;
+
+ /* check src operand */
+ _(check_reg_arg(regs, insn->src_reg, 1));
+
+ _(check_mem_access(env, insn->src_reg, insn->off,
+ BPF_SIZE(insn->code), BPF_READ,
+ insn->dst_reg));
+
+ /* dest reg state will be updated by mem_access */
+
+ } else if (class == BPF_STX) {
+ /* check src1 operand */
+ _(check_reg_arg(regs, insn->src_reg, 1));
+ /* check src2 operand */
+ _(check_reg_arg(regs, insn->dst_reg, 1));
+ _(check_mem_access(env, insn->dst_reg, insn->off,
+ BPF_SIZE(insn->code), BPF_WRITE,
+ insn->src_reg));
+
+ } else if (class == BPF_ST) {
+ if (BPF_MODE(insn->code) != BPF_MEM)
+ return -EINVAL;
+ /* check src operand */
+ _(check_reg_arg(regs, insn->dst_reg, 1));
+ _(check_mem_access(env, insn->dst_reg, insn->off,
+ BPF_SIZE(insn->code), BPF_WRITE,
+ -1));
+
+ } else if (class == BPF_JMP) {
+ u8 opcode = BPF_OP(insn->code);
+
+ if (opcode == BPF_CALL) {
+ _(check_call(env, insn->imm));
+ } else if (opcode == BPF_JA) {
+ if (BPF_SRC(insn->code) != BPF_X)
+ return -EINVAL;
+ insn_idx += insn->off + 1;
+ continue;
+ } else if (opcode == BPF_EXIT) {
+ /* eBPF calling convetion is such that R0 is used
+ * to return the value from eBPF program.
+ * Make sure that it's readable at this time
+ * of bpf_exit, which means that program wrote
+ * something into it earlier
+ */
+ _(check_reg_arg(regs, BPF_REG_0, 1));
+process_bpf_exit:
+ insn_idx = pop_stack(env, &prev_insn_idx);
+ if (insn_idx < 0) {
+ break;
+ } else {
+ do_print_state = true;
+ continue;
+ }
+ } else {
+ _(check_cond_jmp_op(env, insn, &insn_idx));
+ }
+ } else if (class == BPF_LD) {
+ _(check_ld_abs(env, insn));
+ } else {
+ verbose("unknown insn class %d\n", class);
+ return -EINVAL;
+ }
+
+ insn_idx++;
+ }
+
+ return 0;
+}
+
+static void free_states(struct verifier_env *env, int insn_cnt)
+{
+ struct verifier_state_list *sl, *sln;
+ int i;
+
+ for (i = 0; i < insn_cnt; i++) {
+ sl = env->branch_landing[i];
+
+ if (sl)
+ while (sl != STATE_END) {
+ sln = sl->next;
+ kfree(sl);
+ sl = sln;
+ }
+ }
+
+ kfree(env->branch_landing);
+}
+
+int bpf_check(struct sk_filter *prog)
+{
+ struct verifier_env *env;
+ int ret;
+
+ if (prog->len <= 0 || prog->len > BPF_MAXINSNS)
+ return -E2BIG;
+
+ env = kzalloc(sizeof(struct verifier_env), GFP_KERNEL);
+ if (!env)
+ return -ENOMEM;
+
+ verbose_on = false;
+retry:
+ env->prog = prog;
+ env->branch_landing = kcalloc(prog->len,
+ sizeof(struct verifier_state_list *),
+ GFP_KERNEL);
+
+ if (!env->branch_landing) {
+ kfree(env);
+ return -ENOMEM;
+ }
+
+ ret = check_cfg(env);
+ if (ret < 0)
+ goto free_env;
+
+ ret = do_check(env);
+
+free_env:
+ while (pop_stack(env, NULL) >= 0);
+ free_states(env, prog->len);
+
+ if (ret < 0 && !verbose_on && capable(CAP_SYS_ADMIN)) {
+ /* verification failed, redo it with verbose on */
+ memset(env, 0, sizeof(struct verifier_env));
+ verbose_on = true;
+ goto retry;
+ }
+
+ if (ret == 0 && env->used_map_cnt) {
+ /* if program passed verifier, update used_maps in bpf_prog_info */
+ prog->info->used_maps = kmalloc_array(env->used_map_cnt,
+ sizeof(u32), GFP_KERNEL);
+ if (!prog->info->used_maps) {
+ kfree(env);
+ return -ENOMEM;
+ }
+ memcpy(prog->info->used_maps, env->used_maps,
+ sizeof(u32) * env->used_map_cnt);
+ prog->info->used_map_cnt = env->used_map_cnt;
+ }
+
+ kfree(env);
+ return ret;
+}
--
1.7.9.5
^ permalink raw reply related
* [PATCH RFC v2 net-next 11/16] bpf: allow eBPF programs to use maps
From: Alexei Starovoitov @ 2014-07-18 4:20 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Linus Torvalds, Andy Lutomirski, Steven Rostedt,
Daniel Borkmann, Chema Gonzalez, Eric Dumazet, Peter Zijlstra,
Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
H. Peter Anvin, Andrew Morton, Kees Cook, linux-api, netdev,
linux-kernel
In-Reply-To: <1405657206-12060-1-git-send-email-ast@plumgrid.com>
expose bpf_map_lookup_elem(), bpf_map_update_elem(), bpf_map_delete_elem()
map accessors to eBPF programs
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
include/linux/bpf.h | 5 +++
include/uapi/linux/bpf.h | 3 ++
kernel/bpf/syscall.c | 85 ++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 93 insertions(+)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b5e90efddfcf..a7566afbe23b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -128,4 +128,9 @@ struct sk_filter *bpf_prog_get(u32 ufd);
/* verify correctness of eBPF program */
int bpf_check(struct sk_filter *fp);
+/* in-kernel helper functions called from eBPF programs */
+u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
+
#endif /* _LINUX_BPF_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 3f288e1d08f1..06e0f63055fb 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -377,6 +377,9 @@ enum bpf_prog_type {
*/
enum bpf_func_id {
BPF_FUNC_unspec,
+ BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(map_id, void *key) */
+ BPF_FUNC_map_update_elem, /* int map_update_elem(map_id, void *key, void *value) */
+ BPF_FUNC_map_delete_elem, /* int map_delete_elem(map_id, void *key) */
__BPF_FUNC_MAX_ID,
};
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 9d441f17548e..2d6e6a171594 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -741,3 +741,88 @@ SYSCALL_DEFINE5(bpf, int, cmd, unsigned long, arg2, unsigned long, arg3,
return -EINVAL;
}
}
+
+/* called from eBPF program under rcu lock
+ *
+ * if kernel subsystem is allowing eBPF programs to call this function,
+ * inside its own verifier_ops->get_func_proto() callback it should return
+ * (struct bpf_func_proto) {
+ * .ret_type = PTR_TO_MAP_CONDITIONAL,
+ * .arg1_type = CONST_ARG_MAP_ID,
+ * .arg2_type = PTR_TO_STACK_IMM_MAP_KEY,
+ * }
+ * so that eBPF verifier properly checks the arguments
+ */
+u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ struct bpf_map *map;
+ int map_id = r1;
+ void *key = (void *) (unsigned long) r2;
+ void *value;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ map = idr_find(&bpf_map_id_idr, map_id);
+ /* eBPF verifier guarantees that map_id is valid for the life of
+ * the program
+ */
+ BUG_ON(!map);
+
+ value = map->ops->map_lookup_elem(map, key);
+
+ return (unsigned long) value;
+}
+
+/* called from eBPF program under rcu lock
+ *
+ * if kernel subsystem is allowing eBPF programs to call this function,
+ * inside its own verifier_ops->get_func_proto() callback it should return
+ * (struct bpf_func_proto) {
+ * .ret_type = RET_INTEGER,
+ * .arg1_type = CONST_ARG_MAP_ID,
+ * .arg2_type = PTR_TO_STACK_IMM_MAP_KEY,
+ * .arg3_type = PTR_TO_STACK_IMM_MAP_VALUE,
+ * }
+ * so that eBPF verifier properly checks the arguments
+ */
+u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ struct bpf_map *map;
+ int map_id = r1;
+ void *key = (void *) (unsigned long) r2;
+ void *value = (void *) (unsigned long) r3;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ map = idr_find(&bpf_map_id_idr, map_id);
+ /* eBPF verifier guarantees that map_id is valid */
+ BUG_ON(!map);
+
+ return map->ops->map_update_elem(map, key, value);
+}
+
+/* called from eBPF program under rcu lock
+ *
+ * if kernel subsystem is allowing eBPF programs to call this function,
+ * inside its own verifier_ops->get_func_proto() callback it should return
+ * (struct bpf_func_proto) {
+ * .ret_type = RET_INTEGER,
+ * .arg1_type = CONST_ARG_MAP_ID,
+ * .arg2_type = PTR_TO_STACK_IMM_MAP_KEY,
+ * }
+ * so that eBPF verifier properly checks the arguments
+ */
+u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ struct bpf_map *map;
+ int map_id = r1;
+ void *key = (void *) (unsigned long) r2;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ map = idr_find(&bpf_map_id_idr, map_id);
+ /* eBPF verifier guarantees that map_id is valid */
+ BUG_ON(!map);
+
+ return map->ops->map_delete_elem(map, key);
+}
--
1.7.9.5
^ permalink raw reply related
* [PATCH RFC v2 net-next 12/16] net: sock: allow eBPF programs to be attached to sockets
From: Alexei Starovoitov @ 2014-07-18 4:20 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Linus Torvalds, Andy Lutomirski, Steven Rostedt,
Daniel Borkmann, Chema Gonzalez, Eric Dumazet, Peter Zijlstra,
Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
H. Peter Anvin, Andrew Morton, Kees Cook, linux-api, netdev,
linux-kernel
In-Reply-To: <1405657206-12060-1-git-send-email-ast@plumgrid.com>
introduce new setsockopt() command:
int fd;
setsockopt(sock, SOL_SOCKET, SO_ATTACH_FILTER_EBPF, &fd, sizeof(fd))
fd is associated with eBPF program priorly loaded via:
fd = syscall(__NR_bpf, BPF_PROG_LOAD, BPF_PROG_TYPE_SOCKET_FILTER,
&prog, sizeof(prog));
setsockopt() calls bpf_prog_get() which increment refcnt of the program,
so it doesn't get unloaded while socket is using the program.
The same eBPF program can be attached to different sockets.
Program exit automatically closes socket which calls sk_filter_uncharge()
which decrements refcnt of eBPF program
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
arch/alpha/include/uapi/asm/socket.h | 2 +
arch/avr32/include/uapi/asm/socket.h | 2 +
arch/cris/include/uapi/asm/socket.h | 2 +
arch/frv/include/uapi/asm/socket.h | 2 +
arch/ia64/include/uapi/asm/socket.h | 2 +
arch/m32r/include/uapi/asm/socket.h | 2 +
arch/mips/include/uapi/asm/socket.h | 2 +
arch/mn10300/include/uapi/asm/socket.h | 2 +
arch/parisc/include/uapi/asm/socket.h | 2 +
arch/powerpc/include/uapi/asm/socket.h | 2 +
arch/s390/include/uapi/asm/socket.h | 2 +
arch/sparc/include/uapi/asm/socket.h | 2 +
arch/xtensa/include/uapi/asm/socket.h | 2 +
include/linux/filter.h | 1 +
include/uapi/asm-generic/socket.h | 2 +
net/core/filter.c | 112 ++++++++++++++++++++++++++++++++
net/core/sock.c | 13 ++++
17 files changed, 154 insertions(+)
diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 3de1394bcab8..8c83c376b5ba 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -87,4 +87,6 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index 6e6cd159924b..498ef7220466 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -80,4 +80,6 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* _UAPI__ASM_AVR32_SOCKET_H */
diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h
index ed94e5ed0a23..0d5120724780 100644
--- a/arch/cris/include/uapi/asm/socket.h
+++ b/arch/cris/include/uapi/asm/socket.h
@@ -82,6 +82,8 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index ca2c6e6f31c6..81fba267c285 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -80,5 +80,7 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index a1b49bac7951..9cbb2e82fa7c 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -89,4 +89,6 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index 6c9a24b3aefa..587ac2fb4106 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -80,4 +80,6 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index a14baa218c76..ab1aed2306db 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -98,4 +98,6 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index 6aa3ce1854aa..1c4f916d0ef1 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -80,4 +80,6 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index fe35ceacf0e7..d189bb79ca07 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -79,4 +79,6 @@
#define SO_BPF_EXTENSIONS 0x4029
+#define SO_ATTACH_FILTER_EBPF 0x402a
+
#endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index a9c3e2e18c05..88488f24ae7f 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -87,4 +87,6 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index e031332096d7..c5f26af90366 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -86,4 +86,6 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index 54d9608681b6..667ed3fa63f2 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -76,6 +76,8 @@
#define SO_BPF_EXTENSIONS 0x0032
+#define SO_ATTACH_FILTER_EBPF 0x0033
+
/* Security levels - as per NRL IPv6 - don't actually do anything */
#define SO_SECURITY_AUTHENTICATION 0x5001
#define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 39acec0cf0b1..24f3e4434979 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -91,4 +91,6 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* _XTENSA_SOCKET_H */
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 822b310e75e1..5a310ed28fbb 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -73,6 +73,7 @@ int sk_unattached_filter_create(struct sk_filter **pfp,
void sk_unattached_filter_destroy(struct sk_filter *fp);
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
+int sk_attach_filter_ebpf(u32 ufd, struct sock *sk);
int sk_detach_filter(struct sock *sk);
int sk_chk_filter(const struct sock_filter *filter, unsigned int flen);
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index ea0796bdcf88..f41844e9ac07 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -82,4 +82,6 @@
#define SO_BPF_EXTENSIONS 48
+#define SO_ATTACH_FILTER_EBPF 49
+
#endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/net/core/filter.c b/net/core/filter.c
index 255dba1bb678..ea929fed67b4 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -44,6 +44,7 @@
#include <linux/ratelimit.h>
#include <linux/seccomp.h>
#include <linux/if_vlan.h>
+#include <linux/bpf.h>
/**
* sk_filter - run a packet through a socket filter
@@ -1117,6 +1118,117 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
}
EXPORT_SYMBOL_GPL(sk_attach_filter);
+int sk_attach_filter_ebpf(u32 ufd, struct sock *sk)
+{
+ struct sk_filter *fp, *old_fp;
+
+ if (sock_flag(sk, SOCK_FILTER_LOCKED))
+ return -EPERM;
+
+ fp = bpf_prog_get(ufd);
+ if (!fp)
+ return -EINVAL;
+
+ if (fp->info->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) {
+ /* valid fd, but invalid program type */
+ sk_filter_release(fp);
+ return -EINVAL;
+ }
+
+ old_fp = rcu_dereference_protected(sk->sk_filter,
+ sock_owned_by_user(sk));
+ rcu_assign_pointer(sk->sk_filter, fp);
+
+ if (old_fp)
+ sk_filter_uncharge(sk, old_fp);
+
+ return 0;
+}
+
+static struct bpf_func_proto sock_filter_funcs[] = {
+ [BPF_FUNC_map_lookup_elem] = {
+ .func = bpf_map_lookup_elem,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_OR_NULL,
+ .arg1_type = ARG_CONST_MAP_ID,
+ .arg2_type = ARG_PTR_TO_MAP_KEY,
+ },
+ [BPF_FUNC_map_update_elem] = {
+ .func = bpf_map_update_elem,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_ID,
+ .arg2_type = ARG_PTR_TO_MAP_KEY,
+ .arg3_type = ARG_PTR_TO_MAP_VALUE,
+ },
+ [BPF_FUNC_map_delete_elem] = {
+ .func = bpf_map_delete_elem,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_ID,
+ .arg2_type = ARG_PTR_TO_MAP_KEY,
+ },
+};
+
+/* allow socket filters to call
+ * bpf_map_lookup_elem(), bpf_map_update_elem(), bpf_map_delete_elem()
+ */
+static const struct bpf_func_proto *sock_filter_func_proto(enum bpf_func_id func_id)
+{
+ if (func_id < 0 || func_id >= ARRAY_SIZE(sock_filter_funcs))
+ return NULL;
+ return &sock_filter_funcs[func_id];
+}
+
+static const struct bpf_context_access {
+ int size;
+ enum bpf_access_type type;
+} sock_filter_ctx_access[] = {
+ [offsetof(struct sk_buff, mark)] = {
+ FIELD_SIZEOF(struct sk_buff, mark), BPF_READ
+ },
+ [offsetof(struct sk_buff, protocol)] = {
+ FIELD_SIZEOF(struct sk_buff, protocol), BPF_READ
+ },
+ [offsetof(struct sk_buff, queue_mapping)] = {
+ FIELD_SIZEOF(struct sk_buff, queue_mapping), BPF_READ
+ },
+};
+
+/* allow socket filters to access to 'mark', 'protocol' and 'queue_mapping'
+ * fields of 'struct sk_buff'
+ */
+static bool sock_filter_is_valid_access(int off, int size, enum bpf_access_type type)
+{
+ const struct bpf_context_access *access;
+
+ if (off < 0 || off >= ARRAY_SIZE(sock_filter_ctx_access))
+ return false;
+
+ access = &sock_filter_ctx_access[off];
+ if (access->size == size && (access->type & type))
+ return true;
+
+ return false;
+}
+
+static struct bpf_verifier_ops sock_filter_ops = {
+ .get_func_proto = sock_filter_func_proto,
+ .is_valid_access = sock_filter_is_valid_access,
+};
+
+static struct bpf_prog_type_list tl = {
+ .ops = &sock_filter_ops,
+ .type = BPF_PROG_TYPE_SOCKET_FILTER,
+};
+
+static int __init register_sock_filter_ops(void)
+{
+ bpf_register_prog_type(&tl);
+ return 0;
+}
+late_initcall(register_sock_filter_ops);
+
int sk_detach_filter(struct sock *sk)
{
int ret = -ENOENT;
diff --git a/net/core/sock.c b/net/core/sock.c
index 026e01f70274..005d5683ef5c 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -895,6 +895,19 @@ set_rcvbuf:
}
break;
+ case SO_ATTACH_FILTER_EBPF:
+ ret = -EINVAL;
+ if (optlen == sizeof(u32)) {
+ u32 ufd;
+
+ ret = -EFAULT;
+ if (copy_from_user(&ufd, optval, sizeof(ufd)))
+ break;
+
+ ret = sk_attach_filter_ebpf(ufd, sk);
+ }
+ break;
+
case SO_DETACH_FILTER:
ret = sk_detach_filter(sk);
break;
--
1.7.9.5
^ permalink raw reply related
* [PATCH RFC v2 net-next 13/16] tracing: allow eBPF programs to be attached to events
From: Alexei Starovoitov @ 2014-07-18 4:20 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Linus Torvalds, Andy Lutomirski, Steven Rostedt,
Daniel Borkmann, Chema Gonzalez, Eric Dumazet, Peter Zijlstra,
Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
H. Peter Anvin, Andrew Morton, Kees Cook, linux-api, netdev,
linux-kernel
In-Reply-To: <1405657206-12060-1-git-send-email-ast@plumgrid.com>
User interface:
fd = open("/sys/kernel/debug/tracing/__event__/filter")
write(fd, "bpf_123")
where 123 is process local FD associated with eBPF program previously loaded.
__event__ is static tracepoint event.
(kprobe events will be supported in the future patches)
Once program is successfully attached to tracepoint event, the tracepoint
will be auto-enabled
close(fd)
auto-disables tracepoint event and detaches eBPF program from it
eBPF programs can call in-kernel helper functions to:
- lookup/update/delete elements in maps
- memcmp
- trace_printk
- load_pointer
- dump_stack
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
include/linux/ftrace_event.h | 5 +
include/trace/bpf_trace.h | 29 +++++
include/trace/ftrace.h | 10 ++
include/uapi/linux/bpf.h | 5 +
kernel/trace/Kconfig | 1 +
kernel/trace/Makefile | 1 +
kernel/trace/bpf_trace.c | 212 ++++++++++++++++++++++++++++++++++++
kernel/trace/trace.h | 3 +
kernel/trace/trace_events.c | 36 +++++-
kernel/trace/trace_events_filter.c | 72 +++++++++++-
10 files changed, 372 insertions(+), 2 deletions(-)
create mode 100644 include/trace/bpf_trace.h
create mode 100644 kernel/trace/bpf_trace.c
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index cff3106ffe2c..de313bd9a434 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -237,6 +237,7 @@ enum {
TRACE_EVENT_FL_WAS_ENABLED_BIT,
TRACE_EVENT_FL_USE_CALL_FILTER_BIT,
TRACE_EVENT_FL_TRACEPOINT_BIT,
+ TRACE_EVENT_FL_BPF_BIT,
};
/*
@@ -259,6 +260,7 @@ enum {
TRACE_EVENT_FL_WAS_ENABLED = (1 << TRACE_EVENT_FL_WAS_ENABLED_BIT),
TRACE_EVENT_FL_USE_CALL_FILTER = (1 << TRACE_EVENT_FL_USE_CALL_FILTER_BIT),
TRACE_EVENT_FL_TRACEPOINT = (1 << TRACE_EVENT_FL_TRACEPOINT_BIT),
+ TRACE_EVENT_FL_BPF = (1 << TRACE_EVENT_FL_BPF_BIT),
};
struct ftrace_event_call {
@@ -536,6 +538,9 @@ event_trigger_unlock_commit_regs(struct ftrace_event_file *file,
event_triggers_post_call(file, tt);
}
+struct bpf_context;
+void trace_filter_call_bpf(struct event_filter *filter, struct bpf_context *ctx);
+
enum {
FILTER_OTHER = 0,
FILTER_STATIC_STRING,
diff --git a/include/trace/bpf_trace.h b/include/trace/bpf_trace.h
new file mode 100644
index 000000000000..2122437f1317
--- /dev/null
+++ b/include/trace/bpf_trace.h
@@ -0,0 +1,29 @@
+/* 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.
+ */
+#ifndef _LINUX_KERNEL_BPF_TRACE_H
+#define _LINUX_KERNEL_BPF_TRACE_H
+
+/* For tracing filters save first six arguments of tracepoint events.
+ * On 64-bit architectures argN fields will match one to one to arguments passed
+ * to tracepoint events.
+ * On 32-bit architectures u64 arguments to events will be seen into two
+ * consecutive argN, argN+1 fields. Pointers, u32, u16, u8, bool types will
+ * match one to one
+ */
+struct bpf_context {
+ unsigned long arg1;
+ unsigned long arg2;
+ unsigned long arg3;
+ unsigned long arg4;
+ unsigned long arg5;
+ unsigned long arg6;
+};
+
+/* call from ftrace_raw_event_*() to copy tracepoint arguments into ctx */
+void populate_bpf_context(struct bpf_context *ctx, ...);
+
+#endif /* _LINUX_KERNEL_BPF_TRACE_H */
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 26b4f2e13275..ad4987ac68bb 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -17,6 +17,7 @@
*/
#include <linux/ftrace_event.h>
+#include <trace/bpf_trace.h>
/*
* DECLARE_EVENT_CLASS can be used to add a generic function
@@ -634,6 +635,15 @@ ftrace_raw_event_##call(void *__data, proto) \
if (ftrace_trigger_soft_disabled(ftrace_file)) \
return; \
\
+ if (unlikely(ftrace_file->flags & FTRACE_EVENT_FL_FILTERED) && \
+ unlikely(ftrace_file->event_call->flags & TRACE_EVENT_FL_BPF)) { \
+ struct bpf_context __ctx; \
+ \
+ populate_bpf_context(&__ctx, args, 0, 0, 0, 0, 0); \
+ trace_filter_call_bpf(ftrace_file->filter, &__ctx); \
+ return; \
+ } \
+ \
__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
\
entry = ftrace_event_buffer_reserve(&fbuffer, ftrace_file, \
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 06e0f63055fb..cedcf9a0db53 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -370,6 +370,7 @@ enum bpf_prog_attributes {
enum bpf_prog_type {
BPF_PROG_TYPE_UNSPEC,
BPF_PROG_TYPE_SOCKET_FILTER,
+ BPF_PROG_TYPE_TRACING_FILTER,
};
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -380,6 +381,10 @@ enum bpf_func_id {
BPF_FUNC_map_lookup_elem, /* void *map_lookup_elem(map_id, void *key) */
BPF_FUNC_map_update_elem, /* int map_update_elem(map_id, void *key, void *value) */
BPF_FUNC_map_delete_elem, /* int map_delete_elem(map_id, void *key) */
+ BPF_FUNC_load_pointer, /* void *bpf_load_pointer(void *unsafe_ptr) */
+ BPF_FUNC_memcmp, /* int bpf_memcmp(void *unsafe_ptr, void *safe_ptr, int size) */
+ BPF_FUNC_dump_stack, /* void bpf_dump_stack(void) */
+ BPF_FUNC_printk, /* int bpf_printk(const char *fmt, int fmt_size, ...) */
__BPF_FUNC_MAX_ID,
};
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index d4409356f40d..e36d42876634 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -80,6 +80,7 @@ config FTRACE_NMI_ENTER
config EVENT_TRACING
select CONTEXT_SWITCH_TRACER
+ depends on NET
bool
config CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 2611613f14f1..a0fcfd97101d 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -52,6 +52,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
endif
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
obj-$(CONFIG_EVENT_TRACING) += trace_events_trigger.o
+obj-$(CONFIG_EVENT_TRACING) += bpf_trace.o
obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
obj-$(CONFIG_TRACEPOINTS) += power-traces.o
ifeq ($(CONFIG_PM_RUNTIME),y)
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
new file mode 100644
index 000000000000..7263491be792
--- /dev/null
+++ b/kernel/trace/bpf_trace.c
@@ -0,0 +1,212 @@
+/* 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.
+ */
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <linux/filter.h>
+#include <linux/uaccess.h>
+#include <trace/bpf_trace.h>
+#include "trace.h"
+
+/* call from ftrace_raw_event_*() to copy tracepoint arguments into ctx */
+void populate_bpf_context(struct bpf_context *ctx, ...)
+{
+ va_list args;
+
+ va_start(args, ctx);
+
+ ctx->arg1 = va_arg(args, unsigned long);
+ ctx->arg2 = va_arg(args, unsigned long);
+ ctx->arg3 = va_arg(args, unsigned long);
+ ctx->arg4 = va_arg(args, unsigned long);
+ ctx->arg5 = va_arg(args, unsigned long);
+ ctx->arg6 = va_arg(args, unsigned long);
+
+ va_end(args);
+}
+EXPORT_SYMBOL_GPL(populate_bpf_context);
+
+/* called from eBPF program with rcu lock held */
+static u64 bpf_load_ptr(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ void *unsafe_ptr = (void *) r1;
+ void *ptr = NULL;
+
+ probe_kernel_read(&ptr, unsafe_ptr, sizeof(void *));
+ return (u64) (unsigned long) ptr;
+}
+
+static u64 bpf_memcmp(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ void *unsafe_ptr = (void *) r1;
+ void *safe_ptr = (void *) r2;
+ u32 size = (u32) r3;
+ char buf[64];
+ int err;
+
+ if (size < 64) {
+ err = probe_kernel_read(buf, unsafe_ptr, size);
+ if (err)
+ return err;
+ return memcmp(buf, safe_ptr, size);
+ }
+ return -1;
+}
+
+static u64 bpf_dump_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
+{
+ trace_dump_stack(0);
+ return 0;
+}
+
+/* limited printk()
+ * only %d %u %x conversion specifiers allowed
+ */
+static u64 bpf_printk(u64 r1, u64 fmt_size, u64 r3, u64 r4, u64 r5)
+{
+ char *fmt = (char *) r1;
+ int fmt_cnt = 0;
+ int i;
+
+ /* bpf_check() guarantees that fmt points to bpf program stack and
+ * fmt_size bytes of it were initialized by bpf program
+ */
+ if (fmt[fmt_size - 1] != 0)
+ return -EINVAL;
+
+ /* check format string for allowed specifiers */
+ for (i = 0; i < fmt_size; i++)
+ if (fmt[i] == '%') {
+ if (i + 1 >= fmt_size)
+ return -EINVAL;
+ if (fmt[i + 1] != 'd' && fmt[i + 1] != 'u' &&
+ fmt[i + 1] != 'x')
+ return -EINVAL;
+ fmt_cnt++;
+ }
+
+ if (fmt_cnt > 3)
+ return -EINVAL;
+
+ return __trace_printk((unsigned long) __builtin_return_address(3), fmt,
+ (u32) r3, (u32) r4, (u32) r5);
+}
+
+static struct bpf_func_proto tracing_filter_funcs[] = {
+ [BPF_FUNC_load_pointer] = {
+ .func = bpf_load_ptr,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ },
+ [BPF_FUNC_memcmp] = {
+ .func = bpf_memcmp,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_ANYTHING,
+ .arg2_type = ARG_PTR_TO_STACK,
+ .arg3_type = ARG_CONST_STACK_SIZE,
+ },
+ [BPF_FUNC_dump_stack] = {
+ .func = bpf_dump_stack,
+ .gpl_only = false,
+ .ret_type = RET_VOID,
+ },
+ [BPF_FUNC_printk] = {
+ .func = bpf_printk,
+ .gpl_only = true,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_STACK,
+ .arg2_type = ARG_CONST_STACK_SIZE,
+ },
+ [BPF_FUNC_map_lookup_elem] = {
+ .func = bpf_map_lookup_elem,
+ .gpl_only = false,
+ .ret_type = RET_PTR_TO_MAP_OR_NULL,
+ .arg1_type = ARG_CONST_MAP_ID,
+ .arg2_type = ARG_PTR_TO_MAP_KEY,
+ },
+ [BPF_FUNC_map_update_elem] = {
+ .func = bpf_map_update_elem,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_ID,
+ .arg2_type = ARG_PTR_TO_MAP_KEY,
+ .arg3_type = ARG_PTR_TO_MAP_VALUE,
+ },
+ [BPF_FUNC_map_delete_elem] = {
+ .func = bpf_map_delete_elem,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_CONST_MAP_ID,
+ .arg2_type = ARG_PTR_TO_MAP_KEY,
+ },
+};
+
+static const struct bpf_func_proto *tracing_filter_func_proto(enum bpf_func_id func_id)
+{
+ if (func_id < 0 || func_id >= ARRAY_SIZE(tracing_filter_funcs))
+ return NULL;
+ return &tracing_filter_funcs[func_id];
+}
+
+static const struct bpf_context_access {
+ int size;
+ enum bpf_access_type type;
+} tracing_filter_ctx_access[] = {
+ [offsetof(struct bpf_context, arg1)] = {
+ FIELD_SIZEOF(struct bpf_context, arg1),
+ BPF_READ
+ },
+ [offsetof(struct bpf_context, arg2)] = {
+ FIELD_SIZEOF(struct bpf_context, arg2),
+ BPF_READ
+ },
+ [offsetof(struct bpf_context, arg3)] = {
+ FIELD_SIZEOF(struct bpf_context, arg3),
+ BPF_READ
+ },
+ [offsetof(struct bpf_context, arg4)] = {
+ FIELD_SIZEOF(struct bpf_context, arg4),
+ BPF_READ
+ },
+ [offsetof(struct bpf_context, arg5)] = {
+ FIELD_SIZEOF(struct bpf_context, arg5),
+ BPF_READ
+ },
+};
+
+static bool tracing_filter_is_valid_access(int off, int size, enum bpf_access_type type)
+{
+ const struct bpf_context_access *access;
+
+ if (off < 0 || off >= ARRAY_SIZE(tracing_filter_ctx_access))
+ return false;
+
+ access = &tracing_filter_ctx_access[off];
+ if (access->size == size && (access->type & type))
+ return true;
+
+ return false;
+}
+
+static struct bpf_verifier_ops tracing_filter_ops = {
+ .get_func_proto = tracing_filter_func_proto,
+ .is_valid_access = tracing_filter_is_valid_access,
+};
+
+static struct bpf_prog_type_list tl = {
+ .ops = &tracing_filter_ops,
+ .type = BPF_PROG_TYPE_TRACING_FILTER,
+};
+
+static int __init register_tracing_filter_ops(void)
+{
+ bpf_register_prog_type(&tl);
+ return 0;
+}
+late_initcall(register_tracing_filter_ops);
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 9258f5a815db..bb7c6a19ead5 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -984,12 +984,15 @@ struct ftrace_event_field {
int is_signed;
};
+struct sk_filter;
+
struct event_filter {
int n_preds; /* Number assigned */
int a_preds; /* allocated */
struct filter_pred *preds;
struct filter_pred *root;
char *filter_string;
+ struct sk_filter *prog;
};
struct event_subsystem {
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index f99e0b3bca8c..de79c27a0a42 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -1048,6 +1048,26 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
return r;
}
+static int event_filter_release(struct inode *inode, struct file *filp)
+{
+ struct ftrace_event_file *file;
+ char buf[2] = "0";
+
+ mutex_lock(&event_mutex);
+ file = event_file_data(filp);
+ if (file) {
+ if (file->event_call->flags & TRACE_EVENT_FL_BPF) {
+ /* auto-disable the filter */
+ ftrace_event_enable_disable(file, 0);
+
+ /* if BPF filter was used, clear it on fd close */
+ apply_event_filter(file, buf);
+ }
+ }
+ mutex_unlock(&event_mutex);
+ return 0;
+}
+
static ssize_t
event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
loff_t *ppos)
@@ -1071,10 +1091,23 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
mutex_lock(&event_mutex);
file = event_file_data(filp);
- if (file)
+ if (file) {
err = apply_event_filter(file, buf);
+ if (!err && file->event_call->flags & TRACE_EVENT_FL_BPF)
+ /* once filter is applied, auto-enable it */
+ ftrace_event_enable_disable(file, 1);
+ }
+
mutex_unlock(&event_mutex);
+ if (file && file->event_call->flags & TRACE_EVENT_FL_BPF) {
+ /*
+ * allocate per-cpu printk buffers, since eBPF program
+ * might be calling bpf_trace_printk
+ */
+ trace_printk_init_buffers();
+ }
+
free_page((unsigned long) buf);
if (err < 0)
return err;
@@ -1325,6 +1358,7 @@ static const struct file_operations ftrace_event_filter_fops = {
.open = tracing_open_generic,
.read = event_filter_read,
.write = event_filter_write,
+ .release = event_filter_release,
.llseek = default_llseek,
};
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 8a8631926a07..a27526fae0fe 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -23,6 +23,9 @@
#include <linux/mutex.h>
#include <linux/perf_event.h>
#include <linux/slab.h>
+#include <linux/bpf.h>
+#include <trace/bpf_trace.h>
+#include <linux/filter.h>
#include "trace.h"
#include "trace_output.h"
@@ -535,6 +538,16 @@ static int filter_match_preds_cb(enum move_type move, struct filter_pred *pred,
return WALK_PRED_DEFAULT;
}
+void trace_filter_call_bpf(struct event_filter *filter, struct bpf_context *ctx)
+{
+ BUG_ON(!filter || !filter->prog);
+
+ rcu_read_lock();
+ SK_RUN_FILTER(filter->prog, (void *) ctx);
+ rcu_read_unlock();
+}
+EXPORT_SYMBOL_GPL(trace_filter_call_bpf);
+
/* return 1 if event matches, 0 otherwise (discard) */
int filter_match_preds(struct event_filter *filter, void *rec)
{
@@ -794,6 +807,8 @@ static void __free_filter(struct event_filter *filter)
if (!filter)
return;
+ if (filter->prog)
+ sk_unattached_filter_destroy(filter->prog);
__free_preds(filter);
kfree(filter->filter_string);
kfree(filter);
@@ -1898,6 +1913,48 @@ static int create_filter_start(char *filter_str, bool set_str,
return err;
}
+static int create_filter_bpf(char *filter_str, struct event_filter **filterp)
+{
+ struct event_filter *filter;
+ struct sk_filter *prog;
+ long ufd;
+ int err = 0;
+
+ *filterp = NULL;
+
+ filter = __alloc_filter();
+ if (!filter)
+ return -ENOMEM;
+
+ err = replace_filter_string(filter, filter_str);
+ if (err)
+ goto free_filter;
+
+ err = kstrtol(filter_str + 4, 0, &ufd);
+ if (err)
+ goto free_filter;
+
+ err = -ESRCH;
+ prog = bpf_prog_get(ufd);
+ if (!prog)
+ goto free_filter;
+
+ filter->prog = prog;
+
+ err = -EINVAL;
+ if (prog->info->prog_type != BPF_PROG_TYPE_TRACING_FILTER)
+ /* prog_id is valid, but it's not a tracing filter program */
+ goto free_filter;
+
+ *filterp = filter;
+
+ return 0;
+
+free_filter:
+ __free_filter(filter);
+ return err;
+}
+
static void create_filter_finish(struct filter_parse_state *ps)
{
if (ps) {
@@ -2007,7 +2064,20 @@ int apply_event_filter(struct ftrace_event_file *file, char *filter_string)
return 0;
}
- err = create_filter(call, filter_string, true, &filter);
+ /*
+ * 'bpf_123' string is a request to attach eBPF program with id == 123
+ * also accept 'bpf 123', 'bpf.123', 'bpf-123' variants
+ */
+ if (memcmp(filter_string, "bpf", 3) == 0 && filter_string[3] != 0 &&
+ filter_string[4] != 0) {
+ err = create_filter_bpf(filter_string, &filter);
+ if (!err)
+ call->flags |= TRACE_EVENT_FL_BPF;
+ } else {
+ err = create_filter(call, filter_string, true, &filter);
+ if (!err)
+ call->flags &= ~TRACE_EVENT_FL_BPF;
+ }
/*
* Always swap the call filter with the new filter
--
1.7.9.5
^ permalink raw reply related
* [PATCH RFC v2 net-next 14/16] samples: bpf: add mini eBPF library to manipulate maps and programs
From: Alexei Starovoitov @ 2014-07-18 4:20 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Linus Torvalds, Andy Lutomirski, Steven Rostedt,
Daniel Borkmann, Chema Gonzalez, Eric Dumazet, Peter Zijlstra,
Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
H. Peter Anvin, Andrew Morton, Kees Cook, linux-api, netdev,
linux-kernel
In-Reply-To: <1405657206-12060-1-git-send-email-ast@plumgrid.com>
the library includes a trivial set of BPF syscall wrappers:
int bpf_create_map(int key_size, int value_size, int max_entries);
int bpf_update_elem(int fd, void *key, void *value);
int bpf_lookup_elem(int fd, void *key, void *value);
int bpf_delete_elem(int fd, void *key);
int bpf_get_next_key(int fd, void *key, void *next_key);
int bpf_prog_load(enum bpf_prog_type prog_type,
const struct sock_filter_int *insns, int insn_len,
const char *license,
const struct bpf_map_fixup *fixups, int fixup_len);
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
samples/bpf/libbpf.c | 109 ++++++++++++++++++++++++++++++++++++++++++++++++++
samples/bpf/libbpf.h | 22 ++++++++++
2 files changed, 131 insertions(+)
create mode 100644 samples/bpf/libbpf.c
create mode 100644 samples/bpf/libbpf.h
diff --git a/samples/bpf/libbpf.c b/samples/bpf/libbpf.c
new file mode 100644
index 000000000000..5460d1f3ad43
--- /dev/null
+++ b/samples/bpf/libbpf.c
@@ -0,0 +1,109 @@
+/* eBPF mini library */
+#include <stdlib.h>
+#include <linux/unistd.h>
+#include <unistd.h>
+#include <string.h>
+#include <linux/netlink.h>
+#include <linux/bpf.h>
+#include <errno.h>
+#include "libbpf.h"
+
+struct nlattr_u32 {
+ __u16 nla_len;
+ __u16 nla_type;
+ __u32 val;
+};
+
+int bpf_create_map(int key_size, int value_size, int max_entries)
+{
+ struct nlattr_u32 attr[] = {
+ {
+ .nla_len = sizeof(struct nlattr_u32),
+ .nla_type = BPF_MAP_KEY_SIZE,
+ .val = key_size,
+ },
+ {
+ .nla_len = sizeof(struct nlattr_u32),
+ .nla_type = BPF_MAP_VALUE_SIZE,
+ .val = value_size,
+ },
+ {
+ .nla_len = sizeof(struct nlattr_u32),
+ .nla_type = BPF_MAP_MAX_ENTRIES,
+ .val = max_entries,
+ },
+ };
+
+ return syscall(__NR_bpf, BPF_MAP_CREATE, BPF_MAP_TYPE_HASH, attr, sizeof(attr));
+}
+
+
+int bpf_update_elem(int fd, void *key, void *value)
+{
+ return syscall(__NR_bpf, BPF_MAP_UPDATE_ELEM, fd, key, value);
+}
+
+int bpf_lookup_elem(int fd, void *key, void *value)
+{
+ return syscall(__NR_bpf, BPF_MAP_LOOKUP_ELEM, fd, key, value);
+}
+
+int bpf_delete_elem(int fd, void *key)
+{
+ return syscall(__NR_bpf, BPF_MAP_DELETE_ELEM, fd, key);
+}
+
+int bpf_get_next_key(int fd, void *key, void *next_key)
+{
+ return syscall(__NR_bpf, BPF_MAP_GET_NEXT_KEY, fd, key, next_key);
+}
+
+#define ROUND_UP(x, n) (((x) + (n) - 1u) & ~((n) - 1u))
+
+int bpf_prog_load(enum bpf_prog_type prog_type,
+ const struct bpf_insn *insns, int prog_len,
+ const char *license,
+ const struct bpf_map_fixup *fixups, int fixup_len)
+{
+ int nlattr_size, license_len, err;
+ void *nlattr, *ptr;
+
+ license_len = strlen(license) + 1;
+ nlattr_size = sizeof(struct nlattr) + prog_len + sizeof(struct nlattr) +
+ ROUND_UP(license_len, 4) + sizeof(struct nlattr) +
+ fixup_len;
+
+ ptr = nlattr = malloc(nlattr_size);
+
+ *(struct nlattr *) ptr = (struct nlattr) {
+ .nla_len = prog_len + sizeof(struct nlattr),
+ .nla_type = BPF_PROG_TEXT,
+ };
+ ptr += sizeof(struct nlattr);
+
+ memcpy(ptr, insns, prog_len);
+ ptr += prog_len;
+
+ *(struct nlattr *) ptr = (struct nlattr) {
+ .nla_len = ROUND_UP(license_len, 4) + sizeof(struct nlattr),
+ .nla_type = BPF_PROG_LICENSE,
+ };
+ ptr += sizeof(struct nlattr);
+
+ memcpy(ptr, license, license_len);
+ ptr += ROUND_UP(license_len, 4);
+
+ *(struct nlattr *) ptr = (struct nlattr) {
+ .nla_len = fixup_len + sizeof(struct nlattr),
+ .nla_type = BPF_PROG_MAP_FIXUP,
+ };
+ ptr += sizeof(struct nlattr);
+
+ memcpy(ptr, fixups, fixup_len);
+ ptr += fixup_len;
+
+ err = syscall(__NR_bpf, BPF_PROG_LOAD, prog_type, nlattr, nlattr_size);
+
+ free(nlattr);
+ return err;
+}
diff --git a/samples/bpf/libbpf.h b/samples/bpf/libbpf.h
new file mode 100644
index 000000000000..07f668e3dac0
--- /dev/null
+++ b/samples/bpf/libbpf.h
@@ -0,0 +1,22 @@
+/* eBPF mini library */
+#ifndef __LIBBPF_H
+#define __LIBBPF_H
+
+struct bpf_insn;
+
+int bpf_create_map(int key_size, int value_size, int max_entries);
+int bpf_update_elem(int fd, void *key, void *value);
+int bpf_lookup_elem(int fd, void *key, void *value);
+int bpf_delete_elem(int fd, void *key);
+int bpf_get_next_key(int fd, void *key, void *next_key);
+
+struct bpf_map_fixup {
+ int insn_idx;
+ int fd;
+};
+int bpf_prog_load(enum bpf_prog_type prog_type,
+ const struct bpf_insn *insns, int insn_len,
+ const char *license,
+ const struct bpf_map_fixup *fixups, int fixup_len);
+
+#endif
--
1.7.9.5
^ permalink raw reply related
* [PATCH RFC v2 net-next 15/16] samples: bpf: example of stateful socket filtering
From: Alexei Starovoitov @ 2014-07-18 4:20 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Linus Torvalds, Andy Lutomirski, Steven Rostedt,
Daniel Borkmann, Chema Gonzalez, Eric Dumazet, Peter Zijlstra,
Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
H. Peter Anvin, Andrew Morton, Kees Cook, linux-api, netdev,
linux-kernel
In-Reply-To: <1405657206-12060-1-git-send-email-ast@plumgrid.com>
this socket filter example does:
- creates a hashtable in kernel with key 4 bytes and value 8 bytes
- populates map[6] = 0; map[17] = 0; // 6 - tcp_proto, 17 - udp_proto
- loads eBPF program:
r0 = skb[14 + 9]; // load one byte of ip->proto
*(u32*)(fp - 4) = r0;
value = bpf_map_lookup_elem(map_id, fp - 4);
if (value)
(*(u64*)value) += 1;
- attaches this program to eth0 raw socket
- every second user space reads map[6] and map[17] to see how many
TCP and UDP packets were seen on eth0
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
samples/bpf/.gitignore | 1 +
samples/bpf/Makefile | 13 ++++
samples/bpf/sock_example.c | 161 ++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 175 insertions(+)
create mode 100644 samples/bpf/.gitignore
create mode 100644 samples/bpf/Makefile
create mode 100644 samples/bpf/sock_example.c
diff --git a/samples/bpf/.gitignore b/samples/bpf/.gitignore
new file mode 100644
index 000000000000..5465c6e92a00
--- /dev/null
+++ b/samples/bpf/.gitignore
@@ -0,0 +1 @@
+sock_example
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
new file mode 100644
index 000000000000..95c990151644
--- /dev/null
+++ b/samples/bpf/Makefile
@@ -0,0 +1,13 @@
+# kbuild trick to avoid linker error. Can be omitted if a module is built.
+obj- := dummy.o
+
+# List of programs to build
+hostprogs-y := sock_example
+
+sock_example-objs := sock_example.o libbpf.o
+
+# Tell kbuild to always build the programs
+always := $(hostprogs-y)
+
+HOSTCFLAGS_libbpf.o += -I$(objtree)/usr/include
+HOSTCFLAGS_sock_example.o += -I$(objtree)/usr/include
diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c
new file mode 100644
index 000000000000..9b23b2b7e9d0
--- /dev/null
+++ b/samples/bpf/sock_example.c
@@ -0,0 +1,161 @@
+/* eBPF example program:
+ * - creates a hashtable in kernel with key 4 bytes and value 8 bytes
+ *
+ * - populates map[6] = 0; map[17] = 0; // 6 - tcp_proto, 17 - udp_proto
+ *
+ * - loads eBPF program:
+ * r0 = skb[14 + 9]; // load one byte of ip->proto
+ * *(u32*)(fp - 4) = r0;
+ * value = bpf_map_lookup_elem(map_id, fp - 4);
+ * if (value)
+ * (*(u64*)value) += 1;
+ *
+ * - attaches this program to eth0 raw socket
+ *
+ * - every second user space reads map[6] and map[17] to see how many
+ * TCP and UDP packets were seen on eth0
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <asm-generic/socket.h>
+#include <linux/netlink.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <linux/sockios.h>
+#include <linux/if_packet.h>
+#include <linux/bpf.h>
+#include <errno.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <linux/unistd.h>
+#include <string.h>
+#include <linux/filter.h>
+#include <stdlib.h>
+#include <arpa/inet.h>
+#include "libbpf.h"
+
+static int open_raw_sock(const char *name)
+{
+ struct sockaddr_ll sll;
+ struct packet_mreq mr;
+ struct ifreq ifr;
+ int sock;
+
+ sock = socket(PF_PACKET, SOCK_RAW | SOCK_NONBLOCK | SOCK_CLOEXEC, htons(ETH_P_ALL));
+ if (sock < 0) {
+ printf("cannot open socket!\n");
+ return -1;
+ }
+
+ memset(&ifr, 0, sizeof(ifr));
+ strncpy((char *)ifr.ifr_name, name, IFNAMSIZ);
+ if (ioctl(sock, SIOCGIFINDEX, &ifr) < 0) {
+ printf("ioctl: %s\n", strerror(errno));
+ close(sock);
+ return -1;
+ }
+
+ memset(&sll, 0, sizeof(sll));
+ sll.sll_family = AF_PACKET;
+ sll.sll_ifindex = ifr.ifr_ifindex;
+ sll.sll_protocol = htons(ETH_P_ALL);
+ if (bind(sock, (struct sockaddr *)&sll, sizeof(sll)) < 0) {
+ printf("bind: %s\n", strerror(errno));
+ close(sock);
+ return -1;
+ }
+
+ memset(&mr, 0, sizeof(mr));
+ mr.mr_ifindex = ifr.ifr_ifindex;
+ mr.mr_type = PACKET_MR_PROMISC;
+ if (setsockopt(sock, SOL_PACKET, PACKET_ADD_MEMBERSHIP, &mr, sizeof(mr)) < 0) {
+ printf("set_promisc: %s\n", strerror(errno));
+ close(sock);
+ return -1;
+ }
+ return sock;
+}
+
+static int test_sock(void)
+{
+ static struct bpf_insn prog[] = {
+ BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ BPF_LD_ABS(BPF_B, 14 + 9 /* R0 = ip->proto */),
+ BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -4), /* *(u32 *)(fp - 4) = r0 */
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), /* r2 = fp - 4 */
+ BPF_MOV64_IMM(BPF_REG_1, 0), /* r1 = MAP_ID */
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */
+ BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
+ BPF_MOV64_IMM(BPF_REG_0, 0), /* r0 = 0 */
+ BPF_EXIT_INSN(),
+ };
+ static struct bpf_map_fixup fixup[1];
+
+ int sock = -1, map_fd, prog_fd, i, key;
+ long long value = 0, tcp_cnt, udp_cnt;
+
+ map_fd = bpf_create_map(sizeof(key), sizeof(value), 2);
+ if (map_fd < 0) {
+ printf("failed to create map '%s'\n", strerror(errno));
+ /* must have been left from previous aborted run, delete it */
+ goto cleanup;
+ }
+
+ key = 6; /* tcp */
+ if (bpf_update_elem(map_fd, &key, &value) < 0) {
+ printf("update err key=%d\n", key);
+ goto cleanup;
+ }
+
+ key = 17; /* udp */
+ if (bpf_update_elem(map_fd, &key, &value) < 0) {
+ printf("update err key=%d\n", key);
+ goto cleanup;
+ }
+
+ fixup[0].insn_idx = 5;
+ fixup[0].fd = map_fd;
+
+ prog_fd = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, prog, sizeof(prog),
+ "GPL", fixup, sizeof(fixup));
+ if (prog_fd < 0) {
+ printf("failed to load prog '%s'\n", strerror(errno));
+ goto cleanup;
+ }
+
+ sock = open_raw_sock("eth0");
+
+ if (setsockopt(sock, SOL_SOCKET, SO_ATTACH_FILTER_EBPF, &prog_fd, sizeof(prog_fd)) < 0) {
+ printf("setsockopt %d\n", errno);
+ goto cleanup;
+ }
+
+ for (i = 0; i < 10; i++) {
+ key = 6;
+ if (bpf_lookup_elem(map_fd, &key, &tcp_cnt) < 0) {
+ printf("lookup err\n");
+ break;
+ }
+ key = 17;
+ if (bpf_lookup_elem(map_fd, &key, &udp_cnt) < 0) {
+ printf("lookup err\n");
+ break;
+ }
+ printf("TCP %lld UDP %lld packets\n", tcp_cnt, udp_cnt);
+ sleep(1);
+ }
+
+cleanup:
+ /* maps, programs, raw sockets will auto cleanup on process exit */
+
+ return 0;
+}
+
+int main(void)
+{
+ test_sock();
+ return 0;
+}
--
1.7.9.5
^ permalink raw reply related
* [PATCH RFC v2 net-next 16/16] samples: bpf: example of tracing filters with eBPF
From: Alexei Starovoitov @ 2014-07-18 4:20 UTC (permalink / raw)
To: David S. Miller
Cc: Ingo Molnar, Linus Torvalds, Andy Lutomirski, Steven Rostedt,
Daniel Borkmann, Chema Gonzalez, Eric Dumazet, Peter Zijlstra,
Arnaldo Carvalho de Melo, Jiri Olsa, Thomas Gleixner,
H. Peter Anvin, Andrew Morton, Kees Cook, linux-api, netdev,
linux-kernel
In-Reply-To: <1405657206-12060-1-git-send-email-ast@plumgrid.com>
simple packet drop monitor:
- in-kernel eBPF program attaches to kfree_skb() event and records number
of packet drops at given location
- userspace iterates over the map every second and prints stats
Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
---
samples/bpf/Makefile | 4 +-
samples/bpf/dropmon.c | 134 +++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 137 insertions(+), 1 deletion(-)
create mode 100644 samples/bpf/dropmon.c
diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
index 95c990151644..8e3dfa0c25e4 100644
--- a/samples/bpf/Makefile
+++ b/samples/bpf/Makefile
@@ -2,12 +2,14 @@
obj- := dummy.o
# List of programs to build
-hostprogs-y := sock_example
+hostprogs-y := sock_example dropmon
sock_example-objs := sock_example.o libbpf.o
+dropmon-objs := dropmon.o libbpf.o
# Tell kbuild to always build the programs
always := $(hostprogs-y)
HOSTCFLAGS_libbpf.o += -I$(objtree)/usr/include
HOSTCFLAGS_sock_example.o += -I$(objtree)/usr/include
+HOSTCFLAGS_dropmon.o += -I$(objtree)/usr/include
diff --git a/samples/bpf/dropmon.c b/samples/bpf/dropmon.c
new file mode 100644
index 000000000000..d3d38832fc74
--- /dev/null
+++ b/samples/bpf/dropmon.c
@@ -0,0 +1,134 @@
+/* simple packet drop monitor:
+ * - in-kernel eBPF program attaches to kfree_skb() event and records number
+ * of packet drops at given location
+ * - userspace iterates over the map every second and prints stats
+ */
+#include <stdio.h>
+#include <unistd.h>
+#include <asm-generic/socket.h>
+#include <linux/netlink.h>
+#include <net/ethernet.h>
+#include <net/if.h>
+#include <linux/sockios.h>
+#include <linux/if_packet.h>
+#include <linux/bpf.h>
+#include <errno.h>
+#include <sys/socket.h>
+#include <sys/ioctl.h>
+#include <linux/unistd.h>
+#include <string.h>
+#include <linux/filter.h>
+#include <stdlib.h>
+#include <arpa/inet.h>
+#include <sys/types.h>
+#include <sys/stat.h>
+#include <fcntl.h>
+#include <stdbool.h>
+#include "libbpf.h"
+
+#define TRACEPOINT "/sys/kernel/debug/tracing/events/skb/kfree_skb/"
+
+static int write_to_file(const char *file, const char *str, bool keep_open)
+{
+ int fd, err;
+
+ fd = open(file, O_WRONLY);
+ err = write(fd, str, strlen(str));
+ (void) err;
+
+ if (keep_open) {
+ return fd;
+ } else {
+ close(fd);
+ return -1;
+ }
+}
+
+static int dropmon(void)
+{
+ /* the following eBPF program is equivalent to C:
+ * void filter(struct bpf_context *ctx)
+ * {
+ * long loc = ctx->arg2;
+ * long init_val = 1;
+ * void *value;
+ *
+ * value = bpf_map_lookup_elem(MAP_ID, &loc);
+ * if (value) {
+ * (*(long *) value) += 1;
+ * } else {
+ * bpf_map_update_elem(MAP_ID, &loc, &init_val);
+ * }
+ * }
+ */
+ static struct bpf_insn prog[] = {
+ BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_1, 8), /* r2 = *(u64 *)(r1 + 8) */
+ BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -8), /* *(u64 *)(fp - 8) = r2 */
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), /* r2 = fp - 8 */
+ BPF_MOV64_IMM(BPF_REG_1, 0), /* r1 = MAP_ID */
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_lookup_elem),
+ BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+ BPF_MOV64_IMM(BPF_REG_1, 1), /* r1 = 1 */
+ BPF_RAW_INSN(BPF_STX | BPF_XADD | BPF_DW, BPF_REG_0, BPF_REG_1, 0, 0), /* xadd r0 += r1 */
+ BPF_EXIT_INSN(),
+ BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 1), /* *(u64 *)(fp - 16) = 1 */
+ BPF_MOV64_REG(BPF_REG_3, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_3, -16), /* r3 = fp - 16 */
+ BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), /* r2 = fp - 8 */
+ BPF_MOV64_IMM(BPF_REG_1, 0), /* r1 = MAP_ID */
+ BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_map_update_elem),
+ BPF_EXIT_INSN(),
+ };
+
+ static struct bpf_map_fixup fixup[2];
+ long long key, next_key, value = 0;
+ int prog_fd, map_fd, i;
+ char fmt[32];
+
+ map_fd = bpf_create_map(sizeof(key), sizeof(value), 1024);
+ if (map_fd < 0) {
+ printf("failed to create map '%s'\n", strerror(errno));
+ goto cleanup;
+ }
+
+ fixup[0].insn_idx = 4;
+ fixup[0].fd = map_fd;
+ fixup[1].insn_idx = 15;
+ fixup[1].fd = map_fd;
+
+ prog_fd = bpf_prog_load(BPF_PROG_TYPE_TRACING_FILTER, prog,
+ sizeof(prog), "GPL", fixup, sizeof(fixup));
+ if (prog_fd < 0) {
+ printf("failed to load prog '%s'\n", strerror(errno));
+ return -1;
+ }
+
+ sprintf(fmt, "bpf_%d", prog_fd);
+
+ write_to_file(TRACEPOINT "filter", fmt, true);
+
+ for (i = 0; i < 10; i++) {
+ key = 0;
+ while (bpf_get_next_key(map_fd, &key, &next_key) == 0) {
+ bpf_lookup_elem(map_fd, &next_key, &value);
+ printf("location 0x%llx count %lld\n", next_key, value);
+ key = next_key;
+ }
+ if (key)
+ printf("\n");
+ sleep(1);
+ }
+
+cleanup:
+ /* maps, programs, tracepoint filters will auto cleanup on process exit */
+
+ return 0;
+}
+
+int main(void)
+{
+ dropmon();
+ return 0;
+}
--
1.7.9.5
^ permalink raw reply related
* Re: [net-next PATCH v2 0/3] Broadcast/Multicast rate limit via Ethtool Coalesce
From: Mugunthan V N @ 2014-07-18 5:37 UTC (permalink / raw)
To: David Laight, David Miller
Cc: netdev-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-api-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
In-Reply-To: <063D6719AE5E284EB5DD2968C1650D6D172768B0-VkEWCZq2GCInGFn1LkZF6NBPR1lH4CV8@public.gmane.org>
On Thursday 17 July 2014 06:23 PM, David Laight wrote:
>> From: Mugunthan V N
>> On Thursday 10 July 2014 05:14 AM, David Miller wrote:
>>> From: Mugunthan V N <mugunthanvnm-l0cyMroinI0@public.gmane.org>
>>> Date: Wed, 9 Jul 2014 12:44:07 +0530
>>>
>>>> A system/cpu can be loaded by a hacker with flooding of broadcast or
>>>> multicast packets, to prevent this some Ethernet controllers like CPSW
>>>> provide a mechanism to limit the broadcast/multicast packet rate via
>>>> hardware limiters. This patch series enables this feature via
>>>> Ethtool Coalesce.
>>> This is pretty bogus if you ask me.
>>>
>>> What is the difference from accepting a high rate of unicast packets?
>>> I say it is no different.
>>>
>>> Therefore, this feature makes no sense to me at all.
>> Any packet storm can cause an endpoint some issues. Typically packet
>> storms will cause the system CPU to thrash resulting is very low system
>> performance.
>>
>> Unicast storms only target a single destination end station, it can be
>> easily mitigated by the host adding a blocking entry in the LUT for each
>> aggressor.
>>
>> Broadcast and multicast target multiple end stations, or an entire
>> network, not only can it cause CPU thrashing, it can result in loss of
>> other broadcast and multicast services. The rate limiting feature allow
>> the broadcast and or multicast traffic to be dropped if the rates are
>> too high. This eliminates the CPU thrashing issue. It also allows the
>> system to analyze the aggressors and block them for future transgressions.
> Rate limiting multicast traffic will definitely cause the loss of multicast
> services.
When a system apply the rate limit, the system should expect to miss
some of the broadcast/multicast packet depending on the rate limit it
applies.
>
> My experience of broadcast storms is that many of the ethernet switches
> (probably especially the cheap ones) end up using a much slower software?
> path for broadcasts. In a broadcast storm they start discarding normal
> traffic - to point where a single ssh session becomes unusable.
> This is true even when isolated from the storm by a 10M hub.
>
> Broadcast storms are probably mostly caused by network topology issues.
> Especially is switches are sending traffic to 'all ports' while resetting
> the spanning tree tables.
>
This is one more example where broadcast/multicast rate limit can be used.
Regards
Mugunthan V N
^ permalink raw reply
* [PATCH v13 0/8] MADV_FREE support
From: Minchan Kim @ 2014-07-18 6:52 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-kernel-u79uwXL29TY76Z2rM5mHXA,
linux-mm-Bw31MaZKKs3YtjvyW6yDsg, Michael Kerrisk, Linux API,
Hugh Dickins, Johannes Weiner, Rik van Riel, KOSAKI Motohiro,
Mel Gorman, Jason Evans, Zhang Yanfei, Kirill A. Shutemov,
Minchan Kim
This patch enable MADV_FREE hint for madvise syscall, which have
been supported by other OSes. [PATCH 1] includes the details.
[1] support MADVISE_FREE for !THP page so if VM encounter
THP page in syscall context, it splits THP page.
[2-7] is to preparing to call madvise syscall without THP plitting
[8] enable THP page support for MADV_FREE.
* from v12
* Fix - skip to mark free pte on try_to_free_swap failed page - Kirill
* Add more Acked-by from arch maintainers and Kirill
* From v11
* Fix arm build - Steve
* Separate patch for arm and arm64 - Steve
* Remove unnecessary check - Kirill
* Skip non-vm_normal page - Kirill
* Add Acked-by - Zhang
* Sparc64 build fix
* Pagetable walker THP handling fix
* From v10
* Add Acked-by from arch stuff(x86, s390)
* Pagewalker based pagetable working - Kirill
* Fix try_to_unmap_one broken with hwpoison - Kirill
* Use VM_BUG_ON_PAGE in madvise_free_pmd - Kirill
* Fix pgtable-3level.h for arm - Steve
* From v9
* Add Acked-by - Rik
* Add THP page support - Kirill
* From v8
* Rebased-on v3.16-rc2-mmotm-2014-06-25-16-44
* From v7
* Rebased-on next-20140613
* From v6
* Remove page from swapcache in syscal time
* Move utility functions from memory.c to madvise.c - Johannes
* Rename untilify functtions - Johannes
* Remove unnecessary checks from vmscan.c - Johannes
* Rebased-on v3.15-rc5-mmotm-2014-05-16-16-56
* Drop Reviewe-by because there was some changes since then.
* From v5
* Fix PPC problem which don't flush TLB - Rik
* Remove unnecessary lazyfree_range stub function - Rik
* Rebased on v3.15-rc5
* From v4
* Add Reviewed-by: Zhang Yanfei
* Rebase on v3.15-rc1-mmotm-2014-04-15-16-14
* From v3
* Add "how to work part" in description - Zhang
* Add page_discardable utility function - Zhang
* Clean up
* From v2
* Remove forceful dirty marking of swap-readed page - Johannes
* Remove deactivation logic of lazyfreed page
* Rebased on 3.14
* Remove RFC tag
* From v1
* Use custom page table walker for madvise_free - Johannes
* Remove PG_lazypage flag - Johannes
* Do madvise_dontneed instead of madvise_freein swapless system
Minchan Kim (8):
[1] mm: support madvise(MADV_FREE)
[2] x86: add pmd_[dirty|mkclean] for THP
[3] sparc: add pmd_[dirty|mkclean] for THP
[4] powerpc: add pmd_[dirty|mkclean] for THP
[5] s390: add pmd_[dirty|mkclean] for THP
[6] arm: add pmd_[dirty|mkclean] for THP
[7] arm64: add pmd_[dirty|mkclean] for THP
[8] mm: Don't split THP page when syscall is called
arch/arm/include/asm/pgtable-3level.h | 3 +
arch/arm64/include/asm/pgtable.h | 2 +
arch/powerpc/include/asm/pgtable-ppc64.h | 2 +
arch/s390/include/asm/pgtable.h | 12 +++
arch/sparc/include/asm/pgtable_64.h | 16 ++++
arch/x86/include/asm/pgtable.h | 10 ++
include/linux/huge_mm.h | 4 +
include/linux/rmap.h | 9 +-
include/linux/vm_event_item.h | 1 +
include/uapi/asm-generic/mman-common.h | 1 +
mm/huge_memory.c | 35 +++++++
mm/madvise.c | 159 +++++++++++++++++++++++++++++++
mm/rmap.c | 46 ++++++++-
mm/vmscan.c | 64 +++++++++----
mm/vmstat.c | 1 +
15 files changed, 345 insertions(+), 20 deletions(-)
--
2.0.0
^ permalink raw reply
* [PATCH v13 1/8] mm: support madvise(MADV_FREE)
From: Minchan Kim @ 2014-07-18 6:52 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-kernel, linux-mm, Michael Kerrisk, Linux API, Hugh Dickins,
Johannes Weiner, Rik van Riel, KOSAKI Motohiro, Mel Gorman,
Jason Evans, Zhang Yanfei, Kirill A. Shutemov, Minchan Kim
In-Reply-To: <1405666386-15095-1-git-send-email-minchan@kernel.org>
Linux doesn't have an ability to free pages lazy while other OS
already have been supported that named by madvise(MADV_FREE).
The gain is clear that kernel can discard freed pages rather than
swapping out or OOM if memory pressure happens.
Without memory pressure, freed pages would be reused by userspace
without another additional overhead(ex, page fault + allocation
+ zeroing).
How to work is following as.
When madvise syscall is called, VM clears dirty bit of ptes of
the range. If memory pressure happens, VM checks dirty bit of
page table and if it found still "clean", it means it's a
"lazyfree pages" so VM could discard the page instead of swapping out.
Once there was store operation for the page before VM peek a page
to reclaim, dirty bit is set so VM can swap out the page instead of
discarding.
Firstly, heavy users would be general allocators(ex, jemalloc,
tcmalloc and hope glibc supports it) and jemalloc/tcmalloc already
have supported the feature for other OS(ex, FreeBSD)
barrios@blaptop:~/benchmark/ebizzy$ lscpu
Architecture: x86_64
CPU op-mode(s): 32-bit, 64-bit
Byte Order: Little Endian
CPU(s): 4
On-line CPU(s) list: 0-3
Thread(s) per core: 2
Core(s) per socket: 2
Socket(s): 1
NUMA node(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 42
Stepping: 7
CPU MHz: 2801.000
BogoMIPS: 5581.64
Virtualization: VT-x
L1d cache: 32K
L1i cache: 32K
L2 cache: 256K
L3 cache: 4096K
NUMA node0 CPU(s): 0-3
ebizzy benchmark(./ebizzy -S 10 -n 512)
vanilla-jemalloc MADV_free-jemalloc
1 thread
records: 10 records: 10
avg: 7682.10 avg: 15306.10
std: 62.35(0.81%) std: 347.99(2.27%)
max: 7770.00 max: 15622.00
min: 7598.00 min: 14772.00
2 thread
records: 10 records: 10
avg: 12747.50 avg: 24171.00
std: 792.06(6.21%) std: 895.18(3.70%)
max: 13337.00 max: 26023.00
min: 10535.00 min: 23152.00
4 thread
records: 10 records: 10
avg: 16474.60 avg: 33717.90
std: 1496.45(9.08%) std: 2008.97(5.96%)
max: 17877.00 max: 35958.00
min: 12224.00 min: 29565.00
8 thread
records: 10 records: 10
avg: 16778.50 avg: 33308.10
std: 825.53(4.92%) std: 1668.30(5.01%)
max: 17543.00 max: 36010.00
min: 14576.00 min: 29577.00
16 thread
records: 10 records: 10
avg: 20614.40 avg: 35516.30
std: 602.95(2.92%) std: 1283.65(3.61%)
max: 21753.00 max: 37178.00
min: 19605.00 min: 33217.00
32 thread
records: 10 records: 10
avg: 22771.70 avg: 36018.50
std: 598.94(2.63%) std: 1046.76(2.91%)
max: 24035.00 max: 37266.00
min: 22108.00 min: 34149.00
In summary, MADV_FREE is about 2 time faster than MADV_DONTNEED.
Cc: Michael Kerrisk <mtk.manpages@gmail.com>
Cc: Linux API <linux-api@vger.kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Jason Evans <je@fb.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
include/linux/rmap.h | 9 ++-
include/linux/vm_event_item.h | 1 +
include/uapi/asm-generic/mman-common.h | 1 +
mm/madvise.c | 140 +++++++++++++++++++++++++++++++++
mm/rmap.c | 42 +++++++++-
mm/vmscan.c | 40 ++++++++--
mm/vmstat.c | 1 +
7 files changed, 222 insertions(+), 12 deletions(-)
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index be574506e6a9..0ba377b97a38 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -75,6 +75,7 @@ enum ttu_flags {
TTU_UNMAP = 1, /* unmap mode */
TTU_MIGRATION = 2, /* migration mode */
TTU_MUNLOCK = 4, /* munlock mode */
+ TTU_FREE = 8, /* free mode */
TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */
TTU_IGNORE_ACCESS = (1 << 9), /* don't age */
@@ -181,7 +182,8 @@ static inline void page_dup_rmap(struct page *page)
* Called from mm/vmscan.c to handle paging out
*/
int page_referenced(struct page *, int is_locked,
- struct mem_cgroup *memcg, unsigned long *vm_flags);
+ struct mem_cgroup *memcg, unsigned long *vm_flags,
+ int *is_dirty);
#define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
@@ -260,9 +262,12 @@ int rmap_walk(struct page *page, struct rmap_walk_control *rwc);
static inline int page_referenced(struct page *page, int is_locked,
struct mem_cgroup *memcg,
- unsigned long *vm_flags)
+ unsigned long *vm_flags,
+ int *is_pte_dirty)
{
*vm_flags = 0;
+ if (is_pte_dirty)
+ *is_pte_dirty = 0;
return 0;
}
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index ced92345c963..e2d3fb1e9814 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -25,6 +25,7 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
FOR_ALL_ZONES(PGALLOC),
PGFREE, PGACTIVATE, PGDEACTIVATE,
PGFAULT, PGMAJFAULT,
+ PGLAZYFREED,
FOR_ALL_ZONES(PGREFILL),
FOR_ALL_ZONES(PGSTEAL_KSWAPD),
FOR_ALL_ZONES(PGSTEAL_DIRECT),
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index ddc3b36f1046..7a94102b7a02 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -34,6 +34,7 @@
#define MADV_SEQUENTIAL 2 /* expect sequential page references */
#define MADV_WILLNEED 3 /* will need these pages */
#define MADV_DONTNEED 4 /* don't need these pages */
+#define MADV_FREE 5 /* free pages only if memory pressure */
/* common parameters: try to keep these consistent across architectures */
#define MADV_REMOVE 9 /* remove these pages & resources */
diff --git a/mm/madvise.c b/mm/madvise.c
index 0938b30da4ab..a21584235bb6 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -19,6 +19,14 @@
#include <linux/blkdev.h>
#include <linux/swap.h>
#include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
+
+#include <asm/tlb.h>
+
+struct madvise_free_private {
+ struct vm_area_struct *vma;
+ struct mmu_gather *tlb;
+};
/*
* Any behaviour which results in changes to the vma->vm_flags needs to
@@ -31,6 +39,7 @@ static int madvise_need_mmap_write(int behavior)
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
+ case MADV_FREE:
return 0;
default:
/* be safe, default to 1. list exceptions explicitly */
@@ -251,6 +260,128 @@ static long madvise_willneed(struct vm_area_struct *vma,
return 0;
}
+static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
+ unsigned long end, struct mm_walk *walk)
+
+{
+ struct madvise_free_private *fp = walk->private;
+ struct mmu_gather *tlb = fp->tlb;
+ struct mm_struct *mm = tlb->mm;
+ struct vm_area_struct *vma = fp->vma;
+ spinlock_t *ptl;
+ pte_t *pte, ptent;
+ struct page *page;
+
+ split_huge_page_pmd(vma, addr, pmd);
+ if (pmd_trans_unstable(pmd))
+ return 0;
+
+ pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
+ arch_enter_lazy_mmu_mode();
+ for (; addr != end; pte++, addr += PAGE_SIZE) {
+ ptent = *pte;
+
+ if (!pte_present(ptent))
+ continue;
+
+ page = vm_normal_page(vma, addr, ptent);
+ if (!page)
+ continue;
+
+ if (PageSwapCache(page)) {
+ if (!trylock_page(page))
+ continue;
+
+ if (!try_to_free_swap(page)) {
+ unlock_page(page);
+ continue;
+ }
+
+ ClearPageDirty(page);
+ unlock_page(page);
+ }
+
+ /*
+ * Some of architecture(ex, PPC) don't update TLB
+ * with set_pte_at and tlb_remove_tlb_entry so for
+ * the portability, remap the pte with old|clean
+ * after pte clearing.
+ */
+ ptent = ptep_get_and_clear_full(mm, addr, pte,
+ tlb->fullmm);
+ ptent = pte_mkold(ptent);
+ ptent = pte_mkclean(ptent);
+ set_pte_at(mm, addr, pte, ptent);
+ tlb_remove_tlb_entry(tlb, pte, addr);
+ }
+ arch_leave_lazy_mmu_mode();
+ pte_unmap_unlock(pte - 1, ptl);
+ cond_resched();
+ return 0;
+}
+
+static void madvise_free_page_range(struct mmu_gather *tlb,
+ struct vm_area_struct *vma,
+ unsigned long addr, unsigned long end)
+{
+ struct madvise_free_private fp = {
+ .vma = vma,
+ .tlb = tlb,
+ };
+
+ struct mm_walk free_walk = {
+ .pmd_entry = madvise_free_pte_range,
+ .mm = vma->vm_mm,
+ .private = &fp,
+ };
+
+ BUG_ON(addr >= end);
+ tlb_start_vma(tlb, vma);
+ walk_page_range(addr, end, &free_walk);
+ tlb_end_vma(tlb, vma);
+}
+
+static int madvise_free_single_vma(struct vm_area_struct *vma,
+ unsigned long start_addr, unsigned long end_addr)
+{
+ unsigned long start, end;
+ struct mm_struct *mm = vma->vm_mm;
+ struct mmu_gather tlb;
+
+ if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP))
+ return -EINVAL;
+
+ /* MADV_FREE works for only anon vma at the moment */
+ if (vma->vm_file)
+ return -EINVAL;
+
+ start = max(vma->vm_start, start_addr);
+ if (start >= vma->vm_end)
+ return -EINVAL;
+ end = min(vma->vm_end, end_addr);
+ if (end <= vma->vm_start)
+ return -EINVAL;
+
+ lru_add_drain();
+ tlb_gather_mmu(&tlb, mm, start, end);
+ update_hiwater_rss(mm);
+
+ mmu_notifier_invalidate_range_start(mm, start, end);
+ madvise_free_page_range(&tlb, vma, start, end);
+ mmu_notifier_invalidate_range_end(mm, start, end);
+ tlb_finish_mmu(&tlb, start, end);
+
+ return 0;
+}
+
+static long madvise_free(struct vm_area_struct *vma,
+ struct vm_area_struct **prev,
+ unsigned long start, unsigned long end)
+{
+ *prev = vma;
+ return madvise_free_single_vma(vma, start, end);
+}
+
/*
* Application no longer needs these pages. If the pages are dirty,
* it's OK to just throw them away. The app will be more careful about
@@ -381,6 +512,14 @@ madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
return madvise_remove(vma, prev, start, end);
case MADV_WILLNEED:
return madvise_willneed(vma, prev, start, end);
+ case MADV_FREE:
+ /*
+ * XXX: In this implementation, MADV_FREE works like
+ * MADV_DONTNEED on swapless system or full swap.
+ */
+ if (get_nr_swap_pages() > 0)
+ return madvise_free(vma, prev, start, end);
+ /* passthrough */
case MADV_DONTNEED:
return madvise_dontneed(vma, prev, start, end);
default:
@@ -400,6 +539,7 @@ madvise_behavior_valid(int behavior)
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
+ case MADV_FREE:
#ifdef CONFIG_KSM
case MADV_MERGEABLE:
case MADV_UNMERGEABLE:
diff --git a/mm/rmap.c b/mm/rmap.c
index 3e8491c504f8..04c181133890 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -663,6 +663,7 @@ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
}
struct page_referenced_arg {
+ int dirtied;
int mapcount;
int referenced;
unsigned long vm_flags;
@@ -677,6 +678,7 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
struct mm_struct *mm = vma->vm_mm;
spinlock_t *ptl;
int referenced = 0;
+ int dirty = 0;
struct page_referenced_arg *pra = arg;
if (unlikely(PageTransHuge(page))) {
@@ -700,6 +702,11 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
/* go ahead even if the pmd is pmd_trans_splitting() */
if (pmdp_clear_flush_young_notify(vma, address, pmd))
referenced++;
+
+ /*
+ * In this implmentation, MADV_FREE doesn't support THP free
+ */
+ dirty++;
spin_unlock(ptl);
} else {
pte_t *pte;
@@ -729,6 +736,10 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
if (likely(!(vma->vm_flags & VM_SEQ_READ)))
referenced++;
}
+
+ if (pte_dirty(*pte))
+ dirty++;
+
pte_unmap_unlock(pte, ptl);
}
@@ -737,6 +748,9 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
pra->vm_flags |= vma->vm_flags;
}
+ if (dirty)
+ pra->dirtied++;
+
pra->mapcount--;
if (!pra->mapcount)
return SWAP_SUCCESS; /* To break the loop */
@@ -761,6 +775,7 @@ static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg)
* @is_locked: caller holds lock on the page
* @memcg: target memory cgroup
* @vm_flags: collect encountered vma->vm_flags who actually referenced the page
+ * @is_pte_dirty: ptes which have marked dirty bit - used for lazyfree page
*
* Quick test_and_clear_referenced for all mappings to a page,
* returns the number of ptes which referenced the page.
@@ -768,7 +783,8 @@ static bool invalid_page_referenced_vma(struct vm_area_struct *vma, void *arg)
int page_referenced(struct page *page,
int is_locked,
struct mem_cgroup *memcg,
- unsigned long *vm_flags)
+ unsigned long *vm_flags,
+ int *is_pte_dirty)
{
int ret;
int we_locked = 0;
@@ -783,6 +799,9 @@ int page_referenced(struct page *page,
};
*vm_flags = 0;
+ if (is_pte_dirty)
+ *is_pte_dirty = 0;
+
if (!page_mapped(page))
return 0;
@@ -810,6 +829,9 @@ int page_referenced(struct page *page,
if (we_locked)
unlock_page(page);
+ if (is_pte_dirty)
+ *is_pte_dirty = pra.dirtied;
+
return pra.referenced;
}
@@ -1128,6 +1150,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
spinlock_t *ptl;
int ret = SWAP_AGAIN;
enum ttu_flags flags = (enum ttu_flags)arg;
+ int dirty = 0;
pte = page_check_address(page, mm, address, &ptl, 0);
if (!pte)
@@ -1157,7 +1180,8 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
pteval = ptep_clear_flush(vma, address, pte);
/* Move the dirty bit to the physical page now the pte is gone. */
- if (pte_dirty(pteval))
+ dirty = pte_dirty(pteval);
+ if (dirty)
set_page_dirty(page);
/* Update high watermark before we lower rss */
@@ -1186,6 +1210,19 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
swp_entry_t entry = { .val = page_private(page) };
pte_t swp_pte;
+ if (flags & TTU_FREE) {
+ VM_BUG_ON_PAGE(PageSwapCache(page), page);
+ if (!dirty && !PageDirty(page)) {
+ /* It's a freeable page by MADV_FREE */
+ dec_mm_counter(mm, MM_ANONPAGES);
+ goto discard;
+ } else {
+ set_pte_at(mm, address, pte, pteval);
+ ret = SWAP_FAIL;
+ goto out_unmap;
+ }
+ }
+
if (PageSwapCache(page)) {
/*
* Store the swap location in the pte.
@@ -1227,6 +1264,7 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
} else
dec_mm_counter(mm, MM_FILEPAGES);
+discard:
page_remove_rmap(page);
page_cache_release(page);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 27432baea971..598e2ade21f7 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -710,13 +710,17 @@ enum page_references {
};
static enum page_references page_check_references(struct page *page,
- struct scan_control *sc)
+ struct scan_control *sc,
+ bool *freeable)
{
int referenced_ptes, referenced_page;
unsigned long vm_flags;
+ int pte_dirty;
+
+ VM_BUG_ON_PAGE(!PageLocked(page), page);
referenced_ptes = page_referenced(page, 1, sc->target_mem_cgroup,
- &vm_flags);
+ &vm_flags, &pte_dirty);
referenced_page = TestClearPageReferenced(page);
/*
@@ -757,6 +761,10 @@ static enum page_references page_check_references(struct page *page,
return PAGEREF_KEEP;
}
+ if (PageAnon(page) && !pte_dirty && !PageSwapCache(page) &&
+ !PageDirty(page))
+ *freeable = true;
+
/* Reclaim if clean, defer dirty pages to writeback */
if (referenced_page && !PageSwapBacked(page))
return PAGEREF_RECLAIM_CLEAN;
@@ -825,6 +833,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
int may_enter_fs;
enum page_references references = PAGEREF_RECLAIM_CLEAN;
bool dirty, writeback;
+ bool freeable = false;
cond_resched();
@@ -947,7 +956,8 @@ static unsigned long shrink_page_list(struct list_head *page_list,
}
if (!force_reclaim)
- references = page_check_references(page, sc);
+ references = page_check_references(page, sc,
+ &freeable);
switch (references) {
case PAGEREF_ACTIVATE:
@@ -963,7 +973,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
* Anonymous process memory has backing store?
* Try to allocate it some swap space here.
*/
- if (PageAnon(page) && !PageSwapCache(page)) {
+ if (PageAnon(page) && !PageSwapCache(page) && !freeable) {
if (!(sc->gfp_mask & __GFP_IO))
goto keep_locked;
if (!add_to_swap(page, page_list))
@@ -978,8 +988,9 @@ static unsigned long shrink_page_list(struct list_head *page_list,
* The page is mapped into the page tables of one or more
* processes. Try to unmap it here.
*/
- if (page_mapped(page) && mapping) {
- switch (try_to_unmap(page, ttu_flags)) {
+ if (page_mapped(page) && (mapping || freeable)) {
+ switch (try_to_unmap(page,
+ freeable ? TTU_FREE : ttu_flags)) {
case SWAP_FAIL:
goto activate_locked;
case SWAP_AGAIN:
@@ -987,7 +998,20 @@ static unsigned long shrink_page_list(struct list_head *page_list,
case SWAP_MLOCK:
goto cull_mlocked;
case SWAP_SUCCESS:
- ; /* try to free the page below */
+ /* try to free the page below */
+ if (!freeable)
+ break;
+ /*
+ * Freeable anon page doesn't have mapping
+ * due to skipping of swapcache so we free
+ * page in here rather than __remove_mapping.
+ */
+ VM_BUG_ON_PAGE(PageSwapCache(page), page);
+ if (!page_freeze_refs(page, 1))
+ goto keep_locked;
+ __clear_page_locked(page);
+ count_vm_event(PGLAZYFREED);
+ goto free_it;
}
}
@@ -1727,7 +1751,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
}
if (page_referenced(page, 0, sc->target_mem_cgroup,
- &vm_flags)) {
+ &vm_flags, NULL)) {
nr_rotated += hpage_nr_pages(page);
/*
* Identify referenced, file-backed active pages and
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 7e036f9db098..5414b8a88641 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -811,6 +811,7 @@ const char * const vmstat_text[] = {
"pgfault",
"pgmajfault",
+ "pglazyfreed",
TEXTS_FOR_ZONES("pgrefill")
TEXTS_FOR_ZONES("pgsteal_kswapd")
--
2.0.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v13 2/8] x86: add pmd_[dirty|mkclean] for THP
From: Minchan Kim @ 2014-07-18 6:53 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-kernel, linux-mm, Michael Kerrisk, Linux API, Hugh Dickins,
Johannes Weiner, Rik van Riel, KOSAKI Motohiro, Mel Gorman,
Jason Evans, Zhang Yanfei, Kirill A. Shutemov, Minchan Kim,
Thomas Gleixner, Ingo Molnar, H. Peter Anvin, x86
In-Reply-To: <1405666386-15095-1-git-send-email-minchan@kernel.org>
MADV_FREE needs pmd_dirty and pmd_mkclean for detecting recent
overwrite of the contents since MADV_FREE syscall is called for
THP page.
This patch adds pmd_dirty and pmd_mkclean for THP page MADV_FREE
support.
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Acked-by: Zhang Yanfei <zhangyanfei@cn.fujitsu.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
arch/x86/include/asm/pgtable.h | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 0ec056012618..329865799653 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -104,6 +104,11 @@ static inline int pmd_young(pmd_t pmd)
return pmd_flags(pmd) & _PAGE_ACCESSED;
}
+static inline int pmd_dirty(pmd_t pmd)
+{
+ return pmd_flags(pmd) & _PAGE_DIRTY;
+}
+
static inline int pte_write(pte_t pte)
{
return pte_flags(pte) & _PAGE_RW;
@@ -267,6 +272,11 @@ static inline pmd_t pmd_mkold(pmd_t pmd)
return pmd_clear_flags(pmd, _PAGE_ACCESSED);
}
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+ return pmd_clear_flags(pmd, _PAGE_DIRTY);
+}
+
static inline pmd_t pmd_wrprotect(pmd_t pmd)
{
return pmd_clear_flags(pmd, _PAGE_RW);
--
2.0.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v13 3/8] sparc: add pmd_[dirty|mkclean] for THP
From: Minchan Kim @ 2014-07-18 6:53 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-kernel, linux-mm, Michael Kerrisk, Linux API, Hugh Dickins,
Johannes Weiner, Rik van Riel, KOSAKI Motohiro, Mel Gorman,
Jason Evans, Zhang Yanfei, Kirill A. Shutemov, Minchan Kim,
David S. Miller, sparclinux
In-Reply-To: <1405666386-15095-1-git-send-email-minchan@kernel.org>
MADV_FREE needs pmd_dirty and pmd_mkclean for detecting recent
overwrite of the contents since MADV_FREE syscall is called for
THP page.
This patch adds pmd_dirty and pmd_mkclean for THP page MADV_FREE
support.
Cc: "David S. Miller" <davem@davemloft.net>
Cc: sparclinux@vger.kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
arch/sparc/include/asm/pgtable_64.h | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/arch/sparc/include/asm/pgtable_64.h b/arch/sparc/include/asm/pgtable_64.h
index 3770bf5c6e1b..b80a309d7e00 100644
--- a/arch/sparc/include/asm/pgtable_64.h
+++ b/arch/sparc/include/asm/pgtable_64.h
@@ -666,6 +666,13 @@ static inline unsigned long pmd_young(pmd_t pmd)
return pte_young(pte);
}
+static inline int pmd_dirty(pmd_t pmd)
+{
+ pte_t pte = __pte(pmd_val(pmd));
+
+ return pte_dirty(pte);
+}
+
static inline unsigned long pmd_write(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
@@ -723,6 +730,15 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
return __pmd(pte_val(pte));
}
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+ pte_t pte = __pte(pmd_val(pmd));
+
+ pte = pte_mkclean(pte);
+
+ return __pmd(pte_val(pte));
+}
+
static inline pmd_t pmd_mkyoung(pmd_t pmd)
{
pte_t pte = __pte(pmd_val(pmd));
--
2.0.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v13 4/8] powerpc: add pmd_[dirty|mkclean] for THP
From: Minchan Kim @ 2014-07-18 6:53 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-kernel, linux-mm, Michael Kerrisk, Linux API, Hugh Dickins,
Johannes Weiner, Rik van Riel, KOSAKI Motohiro, Mel Gorman,
Jason Evans, Zhang Yanfei, Kirill A. Shutemov, Minchan Kim,
Benjamin Herrenschmidt, Paul Mackerras, Aneesh Kumar K.V,
linuxppc-dev
In-Reply-To: <1405666386-15095-1-git-send-email-minchan@kernel.org>
MADV_FREE needs pmd_dirty and pmd_mkclean for detecting recent
overwrite of the contents since MADV_FREE syscall is called for
THP page.
This patch adds pmd_dirty and pmd_mkclean for THP page MADV_FREE
support.
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: "Aneesh Kumar K.V" <aneesh.kumar@linux.vnet.ibm.com>
Cc: linuxppc-dev@lists.ozlabs.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
arch/powerpc/include/asm/pgtable-ppc64.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/powerpc/include/asm/pgtable-ppc64.h b/arch/powerpc/include/asm/pgtable-ppc64.h
index eb9261024f51..c9a4bbe8e179 100644
--- a/arch/powerpc/include/asm/pgtable-ppc64.h
+++ b/arch/powerpc/include/asm/pgtable-ppc64.h
@@ -468,9 +468,11 @@ static inline pte_t *pmdp_ptep(pmd_t *pmd)
#define pmd_pfn(pmd) pte_pfn(pmd_pte(pmd))
#define pmd_young(pmd) pte_young(pmd_pte(pmd))
+#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd))
#define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd)))
#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd)))
#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd)))
+#define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd)))
#define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd)))
#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd)))
--
2.0.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v13 5/8] s390: add pmd_[dirty|mkclean] for THP
From: Minchan Kim @ 2014-07-18 6:53 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-kernel, linux-mm, Michael Kerrisk, Linux API, Hugh Dickins,
Johannes Weiner, Rik van Riel, KOSAKI Motohiro, Mel Gorman,
Jason Evans, Zhang Yanfei, Kirill A. Shutemov, Minchan Kim,
Martin Schwidefsky, Heiko Carstens, Dominik Dingel,
Christian Borntraeger, linux-s390
In-Reply-To: <1405666386-15095-1-git-send-email-minchan@kernel.org>
MADV_FREE needs pmd_dirty and pmd_mkclean for detecting recent
overwrite of the contents since MADV_FREE syscall is called for
THP page but for s390 pmds only referenced bit is available
because there is no free bit left in the pmd entry for the
software dirty bit so this patch adds dumb pmd_dirty which
returns always true by suggesting by Martin.
They finally find a solution in future.
http://marc.info/?l=linux-api&m=140440328820808&w=2
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Dominik Dingel <dingel@linux.vnet.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: linux-s390@vger.kernel.org
Acked-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
arch/s390/include/asm/pgtable.h | 12 ++++++++++++
1 file changed, 12 insertions(+)
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index fcba5e03839f..9862fcb0592b 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -1586,6 +1586,18 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
return pmd;
}
+static inline int pmd_dirty(pmd_t pmd)
+{
+ /* No dirty bit in the segment table entry */
+ return 1;
+}
+
+static inline pmd_t pmd_mkclean(pmd_t pmd)
+{
+ /* No dirty bit in the segment table entry */
+ return pmd;
+}
+
#define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG
static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp)
--
2.0.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v13 6/8] arm: add pmd_[dirty|mkclean] for THP
From: Minchan Kim @ 2014-07-18 6:53 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-kernel, linux-mm, Michael Kerrisk, Linux API, Hugh Dickins,
Johannes Weiner, Rik van Riel, KOSAKI Motohiro, Mel Gorman,
Jason Evans, Zhang Yanfei, Kirill A. Shutemov, Minchan Kim,
Catalin Marinas, Will Deacon, Steve Capper, Russell King,
linux-arm-kernel
In-Reply-To: <1405666386-15095-1-git-send-email-minchan@kernel.org>
MADV_FREE needs pmd_dirty and pmd_mkclean for detecting recent
overwrite of the contents since MADV_FREE syscall is called for
THP page.
This patch adds pmd_dirty and pmd_mkclean for THP page MADV_FREE
support.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: linux-arm-kernel@lists.infradead.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
arch/arm/include/asm/pgtable-3level.h | 3 +++
1 file changed, 3 insertions(+)
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 85c60adc8b60..830f84f2d277 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -220,6 +220,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
#define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
#endif
+#define pmd_dirty(pmd) (pmd_val(pmd) & PMD_SECT_DIRTY)
+
#define PMD_BIT_FUNC(fn,op) \
static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
@@ -228,6 +230,7 @@ PMD_BIT_FUNC(mkold, &= ~PMD_SECT_AF);
PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
PMD_BIT_FUNC(mkwrite, &= ~PMD_SECT_RDONLY);
PMD_BIT_FUNC(mkdirty, |= PMD_SECT_DIRTY);
+PMD_BIT_FUNC(mkclean, &= ~PMD_SECT_DIRTY);
PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF);
#define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
--
2.0.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v13 7/8] arm64: add pmd_[dirty|mkclean] for THP
From: Minchan Kim @ 2014-07-18 6:53 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-kernel, linux-mm, Michael Kerrisk, Linux API, Hugh Dickins,
Johannes Weiner, Rik van Riel, KOSAKI Motohiro, Mel Gorman,
Jason Evans, Zhang Yanfei, Kirill A. Shutemov, Minchan Kim,
Catalin Marinas, Will Deacon, Steve Capper, Russell King,
linux-arm-kernel
In-Reply-To: <1405666386-15095-1-git-send-email-minchan@kernel.org>
MADV_FREE needs pmd_dirty and pmd_mkclean for detecting recent
overwrite of the contents since MADV_FREE syscall is called for
THP page.
This patch adds pmd_dirty and pmd_mkclean for THP page MADV_FREE
support.
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Steve Capper <steve.capper@linaro.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: linux-arm-kernel@lists.infradead.org
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
arch/arm64/include/asm/pgtable.h | 2 ++
1 file changed, 2 insertions(+)
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index e0ccceb317d9..41dfe3c7260c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -240,10 +240,12 @@ static inline pmd_t pte_pmd(pte_t pte)
#endif
#define pmd_young(pmd) pte_young(pmd_pte(pmd))
+#define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd))
#define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd)))
#define pmd_mksplitting(pmd) pte_pmd(pte_mkspecial(pmd_pte(pmd)))
#define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd)))
#define pmd_mkwrite(pmd) pte_pmd(pte_mkwrite(pmd_pte(pmd)))
+#define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd)))
#define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd)))
#define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd)))
#define pmd_mknotpresent(pmd) (__pmd(pmd_val(pmd) & ~PMD_TYPE_MASK))
--
2.0.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCH v13 8/8] mm: Don't split THP page when syscall is called
From: Minchan Kim @ 2014-07-18 6:53 UTC (permalink / raw)
To: Andrew Morton
Cc: linux-kernel, linux-mm, Michael Kerrisk, Linux API, Hugh Dickins,
Johannes Weiner, Rik van Riel, KOSAKI Motohiro, Mel Gorman,
Jason Evans, Zhang Yanfei, Kirill A. Shutemov, Minchan Kim,
Andrea Arcangeli
In-Reply-To: <1405666386-15095-1-git-send-email-minchan@kernel.org>
We don't need to split THP page when MADV_FREE syscall is
called. It could be done when VM decide really frees it so
we could avoid unnecessary THP split.
Cc: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Minchan Kim <minchan@kernel.org>
---
include/linux/huge_mm.h | 4 ++++
mm/huge_memory.c | 35 +++++++++++++++++++++++++++++++++++
mm/madvise.c | 21 ++++++++++++++++++++-
mm/rmap.c | 8 ++++++--
mm/vmscan.c | 28 ++++++++++++++++++----------
5 files changed, 83 insertions(+), 13 deletions(-)
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 63579cb8d3dc..25a961256d9f 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -19,6 +19,9 @@ extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
unsigned long addr,
pmd_t *pmd,
unsigned int flags);
+extern int madvise_free_huge_pmd(struct mmu_gather *tlb,
+ struct vm_area_struct *vma,
+ pmd_t *pmd, unsigned long addr);
extern int zap_huge_pmd(struct mmu_gather *tlb,
struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr);
@@ -56,6 +59,7 @@ extern pmd_t *page_check_address_pmd(struct page *page,
unsigned long address,
enum page_check_address_pmd_flag flag,
spinlock_t **ptl);
+extern int pmd_freeable(pmd_t pmd);
#define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT)
#define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 02559efd9827..c238a19a648f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1384,6 +1384,36 @@ out:
return 0;
}
+int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
+ pmd_t *pmd, unsigned long addr)
+
+{
+ spinlock_t *ptl;
+ struct mm_struct *mm = tlb->mm;
+ int ret = 1;
+
+ if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+ struct page *page;
+ pmd_t orig_pmd;
+
+ orig_pmd = pmdp_get_and_clear(mm, addr, pmd);
+
+ /* No hugepage in swapcache */
+ page = pmd_page(orig_pmd);
+ VM_BUG_ON_PAGE(PageSwapCache(page), page);
+
+ orig_pmd = pmd_mkold(orig_pmd);
+ orig_pmd = pmd_mkclean(orig_pmd);
+
+ set_pmd_at(mm, addr, pmd, orig_pmd);
+ tlb_remove_pmd_tlb_entry(tlb, pmd, addr);
+ spin_unlock(ptl);
+ ret = 0;
+ }
+
+ return ret;
+}
+
int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
pmd_t *pmd, unsigned long addr)
{
@@ -1620,6 +1650,11 @@ unlock:
return NULL;
}
+int pmd_freeable(pmd_t pmd)
+{
+ return !pmd_dirty(pmd);
+}
+
static int __split_huge_page_splitting(struct page *page,
struct vm_area_struct *vma,
unsigned long address)
diff --git a/mm/madvise.c b/mm/madvise.c
index a21584235bb6..84badee5f46d 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -271,8 +271,26 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
spinlock_t *ptl;
pte_t *pte, ptent;
struct page *page;
+ unsigned long next;
+
+ next = pmd_addr_end(addr, end);
+ if (pmd_trans_huge(*pmd)) {
+ if (next - addr != HPAGE_PMD_SIZE) {
+#ifdef CONFIG_DEBUG_VM
+ if (!rwsem_is_locked(&mm->mmap_sem)) {
+ pr_err("%s: mmap_sem is unlocked! addr=0x%lx end=0x%lx vma->vm_start=0x%lx vma->vm_end=0x%lx\n",
+ __func__, addr, end,
+ vma->vm_start,
+ vma->vm_end);
+ BUG();
+ }
+#endif
+ split_huge_page_pmd(vma, addr, pmd);
+ } else if (!madvise_free_huge_pmd(tlb, vma, pmd, addr))
+ goto next;
+ /* fall through */
+ }
- split_huge_page_pmd(vma, addr, pmd);
if (pmd_trans_unstable(pmd))
return 0;
@@ -316,6 +334,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
}
arch_leave_lazy_mmu_mode();
pte_unmap_unlock(pte - 1, ptl);
+next:
cond_resched();
return 0;
}
diff --git a/mm/rmap.c b/mm/rmap.c
index 04c181133890..9c407576ff8e 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -704,9 +704,13 @@ static int page_referenced_one(struct page *page, struct vm_area_struct *vma,
referenced++;
/*
- * In this implmentation, MADV_FREE doesn't support THP free
+ * Use pmd_freeable instead of raw pmd_dirty because in some
+ * of architecture, pmd_dirty is not defined unless
+ * CONFIG_TRANSPARNTE_HUGE is enabled
*/
- dirty++;
+ if (!pmd_freeable(*pmd))
+ dirty++;
+
spin_unlock(ptl);
} else {
pte_t *pte;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 598e2ade21f7..b1428bdad88e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -973,17 +973,25 @@ static unsigned long shrink_page_list(struct list_head *page_list,
* Anonymous process memory has backing store?
* Try to allocate it some swap space here.
*/
- if (PageAnon(page) && !PageSwapCache(page) && !freeable) {
- if (!(sc->gfp_mask & __GFP_IO))
- goto keep_locked;
- if (!add_to_swap(page, page_list))
- goto activate_locked;
- may_enter_fs = 1;
-
- /* Adding to swap updated mapping */
- mapping = page_mapping(page);
+ if (PageAnon(page) && !PageSwapCache(page)) {
+ if (!freeable) {
+ if (!(sc->gfp_mask & __GFP_IO))
+ goto keep_locked;
+ if (!add_to_swap(page, page_list))
+ goto activate_locked;
+ may_enter_fs = 1;
+ /* Adding to swap updated mapping */
+ mapping = page_mapping(page);
+ } else {
+ if (likely(!PageTransHuge(page)))
+ goto unmap;
+ /* try_to_unmap isn't aware of THP page */
+ if (unlikely(split_huge_page_to_list(page,
+ page_list)))
+ goto keep_locked;
+ }
}
-
+unmap:
/*
* The page is mapped into the page tables of one or more
* processes. Try to unmap it here.
--
2.0.0
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* Re: [PATCH v13 6/8] arm: add pmd_[dirty|mkclean] for THP
From: Will Deacon @ 2014-07-18 8:48 UTC (permalink / raw)
To: Minchan Kim
Cc: Andrew Morton,
linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org,
linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, Michael Kerrisk,
Linux API, Hugh Dickins, Johannes Weiner, Rik van Riel,
KOSAKI Motohiro, Mel Gorman, Jason Evans, Zhang Yanfei,
Kirill A. Shutemov, Catalin Marinas, Steve Capper, Russell King,
linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org
In-Reply-To: <1405666386-15095-7-git-send-email-minchan-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
On Fri, Jul 18, 2014 at 07:53:04AM +0100, Minchan Kim wrote:
> MADV_FREE needs pmd_dirty and pmd_mkclean for detecting recent
> overwrite of the contents since MADV_FREE syscall is called for
> THP page.
>
> This patch adds pmd_dirty and pmd_mkclean for THP page MADV_FREE
> support.
>
> Cc: Catalin Marinas <catalin.marinas-5wv7dgnIgG8@public.gmane.org>
> Cc: Will Deacon <will.deacon-5wv7dgnIgG8@public.gmane.org>
> Cc: Steve Capper <steve.capper-QSEj5FYQhm4dnm+yROfE0A@public.gmane.org>
> Cc: Russell King <linux-lFZ/pmaqli7XmaaqVzeoHQ@public.gmane.org>
> Cc: linux-arm-kernel-IAPFreCvJWM7uuMidbF8XUB+6BGkLq7r@public.gmane.org
> Signed-off-by: Minchan Kim <minchan-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org>
> ---
> arch/arm/include/asm/pgtable-3level.h | 3 +++
> 1 file changed, 3 insertions(+)
>
> diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
> index 85c60adc8b60..830f84f2d277 100644
> --- a/arch/arm/include/asm/pgtable-3level.h
> +++ b/arch/arm/include/asm/pgtable-3level.h
> @@ -220,6 +220,8 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
> #define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
> #endif
>
> +#define pmd_dirty(pmd) (pmd_val(pmd) & PMD_SECT_DIRTY)
> +
> #define PMD_BIT_FUNC(fn,op) \
> static inline pmd_t pmd_##fn(pmd_t pmd) { pmd_val(pmd) op; return pmd; }
>
> @@ -228,6 +230,7 @@ PMD_BIT_FUNC(mkold, &= ~PMD_SECT_AF);
> PMD_BIT_FUNC(mksplitting, |= PMD_SECT_SPLITTING);
> PMD_BIT_FUNC(mkwrite, &= ~PMD_SECT_RDONLY);
> PMD_BIT_FUNC(mkdirty, |= PMD_SECT_DIRTY);
> +PMD_BIT_FUNC(mkclean, &= ~PMD_SECT_DIRTY);
> PMD_BIT_FUNC(mkyoung, |= PMD_SECT_AF);
>
> #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT))
Looks fine to me, but again, it would be great if Steve can take a look too.
Will
^ permalink raw reply
* Re: [PATCH, RFC -v2] random: introduce getrandom(2) system call
From: Florian Weimer @ 2014-07-18 9:39 UTC (permalink / raw)
To: Theodore Ts'o, Linux Kernel Developers List
Cc: linux-crypto-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, beck-7YlrpqBBQ3VAfugRpC6u6w
In-Reply-To: <1405633100-4889-1-git-send-email-tytso-3s7WtUTddSA@public.gmane.org>
On 07/17/2014 11:38 PM, Theodore Ts'o wrote:
> If the GRND_RANDOM flags bit is set, then draw from the
> /dev/random pool instead of the /dev/urandom pool. The
> /dev/random pool is limited based on the entropy that can be
> obtained from environmental noise, so if there is insufficient
> entropy, the requested number of bytes may not be returned.
> If there is no entropy available at all, getrandom(2) will
> either block, or return an error with errno set to EAGAIN if
> the GRND_NONBLOCK bit is set in flags.
Can we get a GRND_INIT flag or something like that which means
"block/return EAGAIN until the kernel pool is initialized"? Thanks.
(See the previous discussion about pool initialization.)
--
Florian Weimer / Red Hat Product Security
^ permalink raw reply
* Re: [PATCH, RFC -v2] random: introduce getrandom(2) system call
From: Theodore Ts'o @ 2014-07-18 10:21 UTC (permalink / raw)
To: Florian Weimer
Cc: Linux Kernel Developers List, linux-crypto-u79uwXL29TY76Z2rM5mHXA,
linux-api-u79uwXL29TY76Z2rM5mHXA, beck-7YlrpqBBQ3VAfugRpC6u6w
In-Reply-To: <53C8EB45.20304-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
On Fri, Jul 18, 2014 at 11:39:17AM +0200, Florian Weimer wrote:
> On 07/17/2014 11:38 PM, Theodore Ts'o wrote:
> > If the GRND_RANDOM flags bit is set, then draw from the
> > /dev/random pool instead of the /dev/urandom pool. The
> > /dev/random pool is limited based on the entropy that can be
> > obtained from environmental noise, so if there is insufficient
> > entropy, the requested number of bytes may not be returned.
> > If there is no entropy available at all, getrandom(2) will
> > either block, or return an error with errno set to EAGAIN if
> > the GRND_NONBLOCK bit is set in flags.
>
> Can we get a GRND_INIT flag or something like that which means "block/return
> EAGAIN until the kernel pool is initialized"? Thanks.
This is a mandatory, non-optional feature of getrandom(2).
It will always block or return EAGAIN until it has sufficient entropy.
This is true both for the GRND_RANDOM or !GRND_RANDOM modes.
There are already people whining about how they can't use this
interface to get best efforts randomness for srand(). I'm not
planning meeting their request; non-crypto code which wants to use
random() or rand() can either use the standard getpid()/time()
mechanisms to initialize their PRNG, or they can try to open
/dev/urandom and do things the old fashioned way. Cry me a river.....
Cheers,
- Ted
P.S. Because the ARM architecture does not guarantee a cycle counter
(and apparently using the cycle counter when it is not present cause a
crash, and there's apparently no way to determine whether the cycle
counter is present), entropy collection on ARM is a problem, and so
this new behaviour may be problematic on some architectures,
especially if some part of the system like systemd wants to use
getrandom(2) in very early boot.
However, this is a new interface, so if it causes problems on ARM and
other broken architectures, tough noogies. Hopefully this will
gradually increase pressure on the ARM folks to fix their broken
CPU architectuure specification...
^ permalink raw reply
* [tytso-DPNOqEs/LNQ@public.gmane.org: [PATCH, RFC -v3] random: introduce getrandom(2) system call]
From: Theodore Ts'o @ 2014-07-18 12:56 UTC (permalink / raw)
To: linux-api-u79uwXL29TY76Z2rM5mHXA
[-- Attachment #1: Type: text/plain, Size: 61 bytes --]
Apologies, screwed up the e-mail address again.
- Ted
[-- Attachment #2: Type: message/rfc822, Size: 16855 bytes --]
From: "Theodore Ts'o" <tytso-DPNOqEs/LNQ@public.gmane.org>
To: linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
Cc: linux-abi-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-crypto-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, beck-7YlrpqBBQ3VAfugRpC6u6w@public.gmane.org, deraadt-VON6Tr2NNtkmbxgs1yVkuA@public.gmane.org, "Theodore Ts'o" <tytso-3s7WtUTddSA@public.gmane.org>
Subject: [PATCH, RFC -v3] random: introduce getrandom(2) system call
Date: Fri, 18 Jul 2014 05:59:24 -0400
Message-ID: <1405677564-16802-1-git-send-email-tytso-3s7WtUTddSA@public.gmane.org>
The getrandom(2) system call was requested by the LibreSSL Portable
developers. It is analoguous to the getentropy(2) system call in
OpenBSD.
The rationale of this system call is to provide resiliance against
file descriptor exhaustion attacks, where the attacker consumes all
available file descriptors, forcing the use of the fallback code where
/dev/[u]random is not available. Since the fallback code is often not
well-tested, it is better to eliminate this potential failure mode
entirely.
The other feature provided by this new system call is the ability to
request randomness from the /dev/urandom entropy pool, but to block
until at least 128 bits of entropy has been accumulated in the
/dev/urandom entropy pool. Historically, the emphasis in the
/dev/urandom development has been to ensure that urandom pool is
initialized as quickly as possible after system boot, and preferably
before the init scripts start execution.
This is because changing /dev/urandom reads to block represents an
interface change that could potentially break userspace which is not
acceptable. In practice, on most x86 desktop and server systems, in
general the entropy pool can be initialized before it is needed (and
in modern kernels, we will printk a warning message if not). However,
on an embedded system, this may not be the case. And so with this new
interface, we can provide the functionality of blocking until the
urandom pool has been initialized. Any userspace program which uses
this new functionality must take care to assure that if it is used
during the boot process, that it will not cause the init scripts or
other portions of the system startup to hang indefinitely.
SYNOPSIS
#include <linux/random.h>
int getrandom(void *buf, size_t buflen, unsigned int flags);
DESCRIPTION
The system call getrandom() fills the buffer pointed to by buf
with up to buflen random bytes which can be used to seed user
space random number generators (i.e., DRBG's) or for other
cryptographic processes. It should not be used Monte Carlo
simulations or for other probabilistic sampling applications.
If the GRND_RANDOM flags bit is set, then draw from the
/dev/random pool instead of the /dev/urandom pool. The
/dev/random pool is limited based on the entropy that can be
obtained from environmental noise, so if there is insufficient
entropy, the requested number of bytes may not be returned.
If there is no entropy available at all, getrandom(2) will
either block, or return an error with errno set to EAGAIN if
the GRND_NONBLOCK bit is set in flags.
If the GRND_RANDOM bit is not set, then the /dev/urandom pool
will be used. Unlike using read(2) to fetch data from
/dev/urandom, if the urandom pool has not been sufficiently
initialized, getrandom(2) will block or return -1 with the
errno set to EGAIN if the GRND_NONBLOCK bit is set in flags.
The getentropy(2) system call in OpenBSD can be emulated using
the following function:
int getentropy(void *buf, size_t buflen)
{
int ret;
if (buflen > 256)
goto failure;
ret = getrandom(buf, buflen, 0);
if (ret < 0)
return ret;
if (ret != buflen)
failure:
errno = EIO;
return -1;
}
return 0;
}
RETURN VALUE
On success, the number of bytes that was filled in the buf is
returned. This may not be all the bytes requested by the
caller via buflen if insufficient entropy was present in the
/dev/random pool, or if the system call was interrupted by a
signal.
On error, -1 is returned, and errno is set appropriately.
ERRORS
EINVAL An invalid flag was passed to getrandom(2)
EFAULT buf is outside the accessible address space.
EAGAIN The requested entropy was not available, and the
getentropy(2) would have blocked if GRND_BLOCK flag
was set.
EINTR While blocked waiting for entropy, the call was
interrupted by a signal handler; see the description
of how interrupted read(2) calls on "slow" devices
are handled with and without the SA_RESTART flag
in the signal(7) man page.
NOTES
For small requests (buflen <= 256) getrandom(2) will not
return EINTR when reading from the urandom pool once the
entropy pool has been initialized, and it will return all of
the bytes that have been requested. This is the recommended
way to use getrandom(2), and is designed for compatibility
with OpenBSD's getentropy() system call.
However, if you are using GRND_RANDOM, then getrandom(2) may
block until the entropy accounting determines that sufficient
environmental noise has been gathered such that getrandom(2)
will be operating as a NRBG instead of a DRBG for those people
who are working in the NIST SP 800-90 regime. Since it may
block for a long time, these guarantees do *not* apply. The
user may want to interrupt a hanging process using a signal,
so blocking until all of the requested bytes are returned
would be unfriendly.
For this reason, the user of getrandom(2) MUST always check
the return value, in case it returns some error, or if fewer
bytes than requested was returned. In the case of
!GRND_RANDOM and small request, the latter should never
happen, but the careful userspace code (and all crypto code
should be careful) should check for this anyway!
Signed-off-by: Theodore Ts'o <tytso-3s7WtUTddSA@public.gmane.org>
Reviewed-by: Zach Brown <zab-ugsP4Wv/S6ZeoWH0uzbU5w@public.gmane.org>
---
The change in the v3 version of the commit was to eliminate potential
short reads and EINTR returns when reading from urandom (once the
urandom pool is initialized). This was based on comments and requests
from Theo de Raadt. See the NOTES section in the suggested man page for
a more in-depth discussion of the issues involved.
arch/x86/syscalls/syscall_32.tbl | 1 +
arch/x86/syscalls/syscall_64.tbl | 1 +
drivers/char/random.c | 42 ++++++++++++++++++++++++++++++++++++---
include/linux/syscalls.h | 3 +++
include/uapi/asm-generic/unistd.h | 4 +++-
include/uapi/linux/random.h | 9 +++++++++
6 files changed, 56 insertions(+), 4 deletions(-)
diff --git a/arch/x86/syscalls/syscall_32.tbl b/arch/x86/syscalls/syscall_32.tbl
index d6b8679..f484e39 100644
--- a/arch/x86/syscalls/syscall_32.tbl
+++ b/arch/x86/syscalls/syscall_32.tbl
@@ -360,3 +360,4 @@
351 i386 sched_setattr sys_sched_setattr
352 i386 sched_getattr sys_sched_getattr
353 i386 renameat2 sys_renameat2
+354 i386 getrandom sys_getrandom
diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index ec255a1..6705032 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -323,6 +323,7 @@
314 common sched_setattr sys_sched_setattr
315 common sched_getattr sys_sched_getattr
316 common renameat2 sys_renameat2
+317 common getrandom sys_getrandom
#
# x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/drivers/char/random.c b/drivers/char/random.c
index aa22fe5..91dd57e 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -258,6 +258,8 @@
#include <linux/kmemcheck.h>
#include <linux/workqueue.h>
#include <linux/irq.h>
+#include <linux/syscalls.h>
+#include <linux/completion.h>
#include <asm/processor.h>
#include <asm/uaccess.h>
@@ -469,6 +471,8 @@ static struct entropy_store nonblocking_pool = {
push_to_pool),
};
+static DECLARE_COMPLETION(urandom_initialized);
+
static __u32 const twist_table[8] = {
0x00000000, 0x3b6e20c8, 0x76dc4190, 0x4db26158,
0xedb88320, 0xd6d6a3e8, 0x9b64c2b0, 0xa00ae278 };
@@ -657,6 +661,7 @@ retry:
r->entropy_total = 0;
if (r == &nonblocking_pool) {
prandom_reseed_late();
+ complete_all(&urandom_initialized);
pr_notice("random: %s pool is initialized\n", r->name);
}
}
@@ -1174,13 +1179,14 @@ static ssize_t extract_entropy_user(struct entropy_store *r, void __user *buf,
{
ssize_t ret = 0, i;
__u8 tmp[EXTRACT_SIZE];
+ int large_request = (nbytes > 256);
trace_extract_entropy_user(r->name, nbytes, ENTROPY_BITS(r), _RET_IP_);
xfer_secondary_pool(r, nbytes);
nbytes = account(r, nbytes, 0, 0);
while (nbytes) {
- if (need_resched()) {
+ if (large_request && need_resched()) {
if (signal_pending(current)) {
if (ret == 0)
ret = -ERESTARTSYS;
@@ -1355,7 +1361,7 @@ static int arch_random_refill(void)
}
static ssize_t
-random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
+_random_read(int nonblock, char __user *buf, size_t nbytes)
{
ssize_t n;
@@ -1379,7 +1385,7 @@ random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
if (arch_random_refill())
continue;
- if (file->f_flags & O_NONBLOCK)
+ if (nonblock)
return -EAGAIN;
wait_event_interruptible(random_read_wait,
@@ -1391,6 +1397,12 @@ random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
}
static ssize_t
+random_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
+{
+ return _random_read(file->f_flags & O_NONBLOCK, buf, nbytes);
+}
+
+static ssize_t
urandom_read(struct file *file, char __user *buf, size_t nbytes, loff_t *ppos)
{
int ret;
@@ -1533,6 +1545,30 @@ const struct file_operations urandom_fops = {
.llseek = noop_llseek,
};
+SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
+ unsigned int, flags)
+{
+ int r;
+
+ if (flags & ~(GRND_NONBLOCK|GRND_RANDOM))
+ return -EINVAL;
+
+ if (count > INT_MAX)
+ count = INT_MAX;
+
+ if (flags & GRND_RANDOM)
+ return _random_read(flags & GRND_NONBLOCK, buf, count);
+ if (flags & GRND_NONBLOCK) {
+ if (!completion_done(&urandom_initialized))
+ return -EAGAIN;
+ } else {
+ r = wait_for_completion_interruptible(&urandom_initialized);
+ if (r)
+ return r;
+ }
+ return urandom_read(NULL, buf, count, NULL);
+}
+
/***************************************************************
* Random UUID interface
*
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index b0881a0..cd82f72f 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -866,4 +866,7 @@ asmlinkage long sys_process_vm_writev(pid_t pid,
asmlinkage long sys_kcmp(pid_t pid1, pid_t pid2, int type,
unsigned long idx1, unsigned long idx2);
asmlinkage long sys_finit_module(int fd, const char __user *uargs, int flags);
+asmlinkage long sys_getrandom(char __user * buf, size_t count,
+ unsigned int flags);
+
#endif
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 3336406..2926b1d 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -699,9 +699,11 @@ __SYSCALL(__NR_sched_setattr, sys_sched_setattr)
__SYSCALL(__NR_sched_getattr, sys_sched_getattr)
#define __NR_renameat2 276
__SYSCALL(__NR_renameat2, sys_renameat2)
+#define __NR_getrandom 277
+__SYSCALL(__NR_getrandom, sys_getrandom)
#undef __NR_syscalls
-#define __NR_syscalls 277
+#define __NR_syscalls 278
/*
* All syscalls below here should go away really,
diff --git a/include/uapi/linux/random.h b/include/uapi/linux/random.h
index fff3528..3f93d16 100644
--- a/include/uapi/linux/random.h
+++ b/include/uapi/linux/random.h
@@ -40,4 +40,13 @@ struct rand_pool_info {
__u32 buf[0];
};
+/*
+ * Flags for getrandom(2)
+ *
+ * GRND_NONBLOCK Don't block and return EAGAIN instead
+ * GRND_RANDOM Use the /dev/random pool instead of /dev/urandom
+ */
+#define GRND_NONBLOCK 0x0001
+#define GRND_RANDOM 0x0002
+
#endif /* _UAPI_LINUX_RANDOM_H */
--
2.0.0
^ permalink raw reply related
* Re: [tytso-DPNOqEs/LNQ@public.gmane.org: [PATCH, RFC -v3] random: introduce getrandom(2) system call]
From: Arnd Bergmann @ 2014-07-18 13:16 UTC (permalink / raw)
To: Theodore Ts'o; +Cc: linux-api-u79uwXL29TY76Z2rM5mHXA
In-Reply-To: <20140718125606.GH1491-AKGzg7BKzIDYtjvyW6yDsg@public.gmane.org>
On Friday 18 July 2014 08:56:06 Theodore Ts'o wrote:
>
> The change in the v3 version of the commit was to eliminate potential
> short reads and EINTR returns when reading from urandom (once the
> urandom pool is initialized). This was based on comments and requests
> from Theo de Raadt. See the NOTES section in the suggested man page for
> a more in-depth discussion of the issues involved.
I think there is a problem with the completion:
> @@ -657,6 +661,7 @@ retry:
> r->entropy_total = 0;
> if (r == &nonblocking_pool) {
> prandom_reseed_late();
> + complete_all(&urandom_initialized);
> pr_notice("random: %s pool is initialized\n", r->name);
> }
> }
complete_all() sets the 'done' part of the completion to 'UINT_MAX/2',
which is enough to ensure that everyone waiting for the completion
at a given time will wake up, but a completion should not
be reused without calling init_completion again after a call to
complete_all().
> +SYSCALL_DEFINE3(getrandom, char __user *, buf, size_t, count,
> + unsigned int, flags)
> +{
> + int r;
> +
> + if (flags & ~(GRND_NONBLOCK|GRND_RANDOM))
> + return -EINVAL;
> +
> + if (count > INT_MAX)
> + count = INT_MAX;
> +
> + if (flags & GRND_RANDOM)
> + return _random_read(flags & GRND_NONBLOCK, buf, count);
> + if (flags & GRND_NONBLOCK) {
> + if (!completion_done(&urandom_initialized))
> + return -EAGAIN;
> + } else {
> + r = wait_for_completion_interruptible(&urandom_initialized);
> + if (r)
> + return r;
> + }
> + return urandom_read(NULL, buf, count, NULL);
> +}
> +
However, here you can get called an arbitrary number of times.
It seems entirely possible than an attacker can manage to call
this function 2 billion times. Assuming a latency of 1 microsecond
per syscall, that would take about half an hour. After that, you
never again get any urandom data out of the syscall.
I think you are better off using a plain wait_event() here.
Arnd
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox