'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@xxxxxxxxxxxx>
---
include/linux/bpf.h | 8 ++
include/uapi/linux/bpf.h | 25 ++++++
kernel/bpf/syscall.c | 198 ++++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 231 insertions(+)
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 607ca53fe2af..fd1ac4b5ba8b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -9,6 +9,7 @@
#include <uapi/linux/bpf.h>
#include <linux/workqueue.h>
+#include <linux/file.h>
struct bpf_map;
struct nlattr;
@@ -18,6 +19,12 @@ 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 {
@@ -38,5 +45,6 @@ struct bpf_map_type_list {
void bpf_register_map_type(struct bpf_map_type_list *tl);
void bpf_map_put(struct bpf_map *map);
+struct bpf_map *bpf_map_get(struct fd f);
#endif /* _LINUX_BPF_H */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index de21c8ecf0bb..f68edb2681f8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -326,6 +326,31 @@ enum bpf_cmd {
* map is deleted when fd is closed
*/
BPF_MAP_CREATE,
+
+ /* lookup key in a given map
+ * err = bpf_map_lookup_elem(int fd, 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 fd, 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 fd, 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 fd, 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 b929ba7fc48e..c16bf2052c64 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>
static LIST_HEAD(bpf_map_types);
@@ -131,6 +132,189 @@ free_attr:
return err;
}
+/* if error is returned, fd is released.
+ * On success caller should complete fd access with matching fdput()
+ */
+struct bpf_map *bpf_map_get(struct fd f)
+{
+ struct bpf_map *map;
+
+ if (!f.file)
+ return ERR_PTR(-EBADF);
+
+ if (f.file->f_op != &bpf_map_fops) {
+ fdput(f);
+ return ERR_PTR(-EINVAL);
+ }
+
+ map = f.file->private_data;
+
+ return map;
+}
+
+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;
+
+ map = bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = -ENOMEM;
+ key = kmalloc(map->key_size, GFP_USER);
+ if (!key)
+ goto err_put;
+
+ err = -EFAULT;
+ if (copy_from_user(key, ukey, map->key_size) != 0)
+ goto free_key;
+
+ err = -ESRCH;
+ rcu_read_lock();
+ value = map->ops->map_lookup_elem(map, key);
+ if (!value)
+ goto err_unlock;
+
+ err = -EFAULT;
+ if (copy_to_user(uvalue, value, map->value_size) != 0)
+ goto err_unlock;
+
+ err = 0;
+
+err_unlock:
+ rcu_read_unlock();
+free_key:
+ kfree(key);
+err_put:
+ 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;
+
+ map = bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = -ENOMEM;
+ key = kmalloc(map->key_size, GFP_USER);
+ if (!key)
+ goto err_put;
+
+ err = -EFAULT;
+ if (copy_from_user(key, ukey, map->key_size) != 0)
+ goto free_key;
+
+ err = -ENOMEM;
+ value = kmalloc(map->value_size, GFP_USER);
+ if (!value)
+ goto free_key;
+
+ err = -EFAULT;
+ if (copy_from_user(value, uvalue, map->value_size) != 0)
+ goto free_value;
+
+ /* eBPF program that use maps are running under rcu_read_lock(),
+ * therefore all map accessors rely on this fact, so do the same here
+ */
+ rcu_read_lock();
+ err = map->ops->map_update_elem(map, key, value);
+ rcu_read_unlock();
+
+free_value:
+ kfree(value);
+free_key:
+ kfree(key);
+err_put:
+ 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;
+
+ map = bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = -ENOMEM;
+ key = kmalloc(map->key_size, GFP_USER);
+ if (!key)
+ goto err_put;
+
+ err = -EFAULT;
+ if (copy_from_user(key, ukey, map->key_size) != 0)
+ goto free_key;
+
+ rcu_read_lock();
+ err = map->ops->map_delete_elem(map, key);
+ rcu_read_unlock();
+
+free_key:
+ kfree(key);
+err_put:
+ 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;
+
+ map = bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = -ENOMEM;
+ key = kmalloc(map->key_size, GFP_USER);
+ if (!key)
+ goto err_put;
+
+ err = -EFAULT;
+ if (copy_from_user(key, ukey, map->key_size) != 0)
+ goto free_key;
+
+ err = -ENOMEM;
+ next_key = kmalloc(map->key_size, GFP_USER);
+ if (!next_key)
+ goto free_key;
+
+ rcu_read_lock();
+ err = map->ops->map_get_next_key(map, key, next_key);
+ rcu_read_unlock();
+ 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_put:
+ fdput(f);
+ return err;
+}
+
SYSCALL_DEFINE5(bpf, int, cmd, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@@ -150,6 +334,20 @@ 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:
+ if (arg4 != 0)
+ return -EINVAL;
+ 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
--
To unsubscribe from this list: send the line "unsubscribe linux-api" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
