bpf: add array type of eBPF maps

add new map type BPF_MAP_TYPE_ARRAY and its implementation

- optimized for fastest possible lookup()
  . in the future verifier/JIT may recognize lookup() with constant key
    and optimize it into constant pointer. Can optimize non-constant
    key into direct pointer arithmetic as well, since pointers and
    value_size are constant for the life of the eBPF program.
    In other words array_map_lookup_elem() may be 'inlined' by verifier/JIT
    while preserving concurrent access to this map from user space

- two main use cases for array type:
  . 'global' eBPF variables: array of 1 element with key=0 and value is a
    collection of 'global' variables which programs can use to keep the state
    between events
  . aggregation of tracing events into fixed set of buckets

- all array elements pre-allocated and zero initialized at init time

- key as an index in array and can only be 4 byte

- map_delete_elem() returns EINVAL, since elements cannot be deleted

- map_update_elem() replaces elements in an non-atomic way
  (for atomic updates hashtable type should be used instead)

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 03a01fd609aa2a1bd2e9641cf259ee17a2fcb971..0d662fe75df54792bcb3a6bc7f579deb8e1a4b3d 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -112,6 +112,7 @@ enum bpf_cmd {
 enum bpf_map_type {
        BPF_MAP_TYPE_UNSPEC,
        BPF_MAP_TYPE_HASH,
+       BPF_MAP_TYPE_ARRAY,
 };
 
 enum bpf_prog_type {

diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 2c0ec7f9da781f423486b0770fff57175cfc942a..72ec98ba2d425aa1a6446dcb3cbb987f699e2b0d 100644 (file)
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -1,5 +1,5 @@
 obj-y := core.o
-obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o
+obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o
 ifdef CONFIG_TEST_BPF
 obj-$(CONFIG_BPF_SYSCALL) += test_stub.o
 endif

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
new file mode 100644 (file)
index 0000000..58b80c1
--- /dev/null
+++ b/kernel/bpf/arraymap.c
@@ -0,0 +1,151 @@
+/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+#include <linux/bpf.h>
+#include <linux/err.h>
+#include <linux/vmalloc.h>
+#include <linux/slab.h>
+#include <linux/mm.h>
+
+struct bpf_array {
+       struct bpf_map map;
+       u32 elem_size;
+       char value[0] __aligned(8);
+};
+
+/* Called from syscall */
+static struct bpf_map *array_map_alloc(union bpf_attr *attr)
+{
+       struct bpf_array *array;
+       u32 elem_size;
+
+       /* check sanity of attributes */
+       if (attr->max_entries == 0 || attr->key_size != 4 ||
+           attr->value_size == 0)
+               return ERR_PTR(-EINVAL);
+
+       elem_size = round_up(attr->value_size, 8);
+
+       /* allocate all map elements and zero-initialize them */
+       array = kzalloc(sizeof(*array) + attr->max_entries * elem_size,
+                       GFP_USER | __GFP_NOWARN);
+       if (!array) {
+               array = vzalloc(array->map.max_entries * array->elem_size);
+               if (!array)
+                       return ERR_PTR(-ENOMEM);
+       }
+
+       /* copy mandatory map attributes */
+       array->map.key_size = attr->key_size;
+       array->map.value_size = attr->value_size;
+       array->map.max_entries = attr->max_entries;
+
+       array->elem_size = elem_size;
+
+       return &array->map;
+
+}
+
+/* Called from syscall or from eBPF program */
+static void *array_map_lookup_elem(struct bpf_map *map, void *key)
+{
+       struct bpf_array *array = container_of(map, struct bpf_array, map);
+       u32 index = *(u32 *)key;
+
+       if (index >= array->map.max_entries)
+               return NULL;
+
+       return array->value + array->elem_size * index;
+}
+
+/* Called from syscall */
+static int array_map_get_next_key(struct bpf_map *map, void *key, void *next_key)
+{
+       struct bpf_array *array = container_of(map, struct bpf_array, map);
+       u32 index = *(u32 *)key;
+       u32 *next = (u32 *)next_key;
+
+       if (index >= array->map.max_entries) {
+               *next = 0;
+               return 0;
+       }
+
+       if (index == array->map.max_entries - 1)
+               return -ENOENT;
+
+       *next = index + 1;
+       return 0;
+}
+
+/* Called from syscall or from eBPF program */
+static int array_map_update_elem(struct bpf_map *map, void *key, void *value,
+                                u64 map_flags)
+{
+       struct bpf_array *array = container_of(map, struct bpf_array, map);
+       u32 index = *(u32 *)key;
+
+       if (map_flags > BPF_EXIST)
+               /* unknown flags */
+               return -EINVAL;
+
+       if (index >= array->map.max_entries)
+               /* all elements were pre-allocated, cannot insert a new one */
+               return -E2BIG;
+
+       if (map_flags == BPF_NOEXIST)
+               /* all elemenets already exist */
+               return -EEXIST;
+
+       memcpy(array->value + array->elem_size * index, value, array->elem_size);
+       return 0;
+}
+
+/* Called from syscall or from eBPF program */
+static int array_map_delete_elem(struct bpf_map *map, void *key)
+{
+       return -EINVAL;
+}
+
+/* Called when map->refcnt goes to zero, either from workqueue or from syscall */
+static void array_map_free(struct bpf_map *map)
+{
+       struct bpf_array *array = container_of(map, struct bpf_array, map);
+
+       /* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0,
+        * so the programs (can be more than one that used this map) were
+        * disconnected from events. Wait for outstanding programs to complete
+        * and free the array
+        */
+       synchronize_rcu();
+
+       kvfree(array);
+}
+
+static struct bpf_map_ops array_ops = {
+       .map_alloc = array_map_alloc,
+       .map_free = array_map_free,
+       .map_get_next_key = array_map_get_next_key,
+       .map_lookup_elem = array_map_lookup_elem,
+       .map_update_elem = array_map_update_elem,
+       .map_delete_elem = array_map_delete_elem,
+};
+
+static struct bpf_map_type_list tl = {
+       .ops = &array_ops,
+       .type = BPF_MAP_TYPE_ARRAY,
+};
+
+static int __init register_array_map(void)
+{
+       bpf_register_map_type(&tl);
+       return 0;
+}
+late_initcall(register_array_map);