bpf: add 'flags' attribute to BPF_MAP_UPDATE_ELEM command

the current meaning of BPF_MAP_UPDATE_ELEM syscall command is:
either update existing map element or create a new one.
Initially the plan was to add a new command to handle the case of
'create new element if it didn't exist', but 'flags' style looks
cleaner and overall diff is much smaller (more code reused), so add 'flags'
attribute to BPF_MAP_UPDATE_ELEM command with the following meaning:
 #define BPF_ANY	0 /* create new element or update existing */
 #define BPF_NOEXIST	1 /* create new element if it didn't exist */
 #define BPF_EXIST	2 /* update existing element */

bpf_update_elem(fd, key, value, BPF_NOEXIST) call can fail with EEXIST
if element already exists.

bpf_update_elem(fd, key, value, BPF_EXIST) can fail with ENOENT
if element doesn't exist.

Userspace will call it as:
int bpf_update_elem(int fd, void *key, void *value, __u64 flags)
{
    union bpf_attr attr = {
        .map_fd = fd,
        .key = ptr_to_u64(key),
        .value = ptr_to_u64(value),
        .flags = flags;
    };

    return bpf(BPF_MAP_UPDATE_ELEM, &attr, sizeof(attr));
}

First two bits of 'flags' are used to encode style of bpf_update_elem() command.
Bits 2-63 are reserved for future use.

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

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 3cf91754a957e5f509bf5f97050a559cab048878..51e9242e4803fa446bc0a8e4f2cc80421146ce18 100644 (file)
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -22,7 +22,7 @@ struct bpf_map_ops {
 
        /* funcs callable from userspace and from eBPF programs */
        void *(*map_lookup_elem)(struct bpf_map *map, void *key);
-       int (*map_update_elem)(struct bpf_map *map, void *key, void *value);
+       int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
        int (*map_delete_elem)(struct bpf_map *map, void *key);
 };
 

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d18316f9e9c488b07f66a3dee1493336d9970d98..3e9e1b77f29d9f02ee5e694ea61f118213c9e063 100644 (file)
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -82,7 +82,7 @@ enum bpf_cmd {
 
        /* create or update key/value pair in a given map
         * err = bpf(BPF_MAP_UPDATE_ELEM, union bpf_attr *attr, u32 size)
-        * Using attr->map_fd, attr->key, attr->value
+        * Using attr->map_fd, attr->key, attr->value, attr->flags
         * returns zero or negative error
         */
        BPF_MAP_UPDATE_ELEM,
@@ -117,6 +117,11 @@ enum bpf_prog_type {
        BPF_PROG_TYPE_UNSPEC,
 };
 
+/* flags for BPF_MAP_UPDATE_ELEM command */
+#define BPF_ANY                0 /* create new element or update existing */
+#define BPF_NOEXIST    1 /* create new element if it didn't exist */
+#define BPF_EXIST      2 /* update existing element */
+
 union bpf_attr {
        struct { /* anonymous struct used by BPF_MAP_CREATE command */
                __u32   map_type;       /* one of enum bpf_map_type */
@@ -132,6 +137,7 @@ union bpf_attr {
                        __aligned_u64 value;
                        __aligned_u64 next_key;
                };
+               __u64           flags;
        };
 
        struct { /* anonymous struct used by BPF_PROG_LOAD command */

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index ba61c8c160321ea6f333c560a9dc1e55f8b83632..c0d03bf317a2b526560f5aa3aa59f7bbdfeb4c26 100644 (file)
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -190,7 +190,7 @@ err_put:
        return err;
 }
 
-#define BPF_MAP_UPDATE_ELEM_LAST_FIELD value
+#define BPF_MAP_UPDATE_ELEM_LAST_FIELD flags
 
 static int map_update_elem(union bpf_attr *attr)
 {
@@ -231,7 +231,7 @@ static int map_update_elem(union bpf_attr *attr)
         * 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);
+       err = map->ops->map_update_elem(map, key, value, attr->flags);
        rcu_read_unlock();
 
 free_value: