bpf: Add generic support for lookup batch op

This commit introduces generic support for the bpf_map_lookup_batch.
This implementation can be used by almost all the bpf maps since its core
implementation is relying on the existing map_get_next_key and
map_lookup_elem. The bpf syscall subcommand introduced is:

  BPF_MAP_LOOKUP_BATCH

The UAPI attribute is:

  struct { /* struct used by BPF_MAP_*_BATCH commands */
         __aligned_u64   in_batch;       /* start batch,
                                          * NULL to start from beginning
                                          */
         __aligned_u64   out_batch;      /* output: next start batch */
         __aligned_u64   keys;
         __aligned_u64   values;
         __u32           count;          /* input/output:
                                          * input: # of key/value
                                          * elements
                                          * output: # of filled elements
                                          */
         __u32           map_fd;
         __u64           elem_flags;
         __u64           flags;
  } batch;

in_batch/out_batch are opaque values use to communicate between
user/kernel space, in_batch/out_batch must be of key_size length.

To start iterating from the beginning in_batch must be null,
count is the # of key/value elements to retrieve. Note that the 'keys'
buffer must be a buffer of key_size * count size and the 'values' buffer
must be value_size * count, where value_size must be aligned to 8 bytes
by userspace if it's dealing with percpu maps. 'count' will contain the
number of keys/values successfully retrieved. Note that 'count' is an
input/output variable and it can contain a lower value after a call.

If there's no more entries to retrieve, ENOENT will be returned. If error
is ENOENT, count might be > 0 in case it copied some values but there were
no more entries to retrieve.

Note that if the return code is an error and not -EFAULT,
count indicates the number of elements successfully processed.

Suggested-by: Stanislav Fomichev <sdf@google.com>
Signed-off-by: Brian Vazquez <brianvv@google.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Link: https://lore.kernel.org/bpf/20200115184308.162644-3-brianvv@google.com

2 files changed, 23 insertions, 0 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index aed2bc39d72b..807744ecaa5a 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -44,6 +44,8 @@ struct bpf_map_ops {
 	int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
 	void (*map_release_uref)(struct bpf_map *map);
 	void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key);
+	int (*map_lookup_batch)(struct bpf_map *map, const union bpf_attr *attr,
+				union bpf_attr __user *uattr);
 
 	/* funcs callable from userspace and from eBPF programs */
 	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
@@ -982,6 +984,9 @@ void *bpf_map_area_alloc(u64 size, int numa_node);
 void *bpf_map_area_mmapable_alloc(u64 size, int numa_node);
 void bpf_map_area_free(void *base);
 void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
+int  generic_map_lookup_batch(struct bpf_map *map,
+			      const union bpf_attr *attr,
+			      union bpf_attr __user *uattr);
 
 extern int sysctl_unprivileged_bpf_disabled;
 
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index a88837d4dd18..0721b2c6bb8c 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -107,6 +107,7 @@ enum bpf_cmd {
 	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
 	BPF_MAP_FREEZE,
 	BPF_BTF_GET_NEXT_ID,
+	BPF_MAP_LOOKUP_BATCH,
 };
 
 enum bpf_map_type {
@@ -420,6 +421,23 @@ union bpf_attr {
 		__u64		flags;
 	};
 
+	struct { /* struct used by BPF_MAP_*_BATCH commands */
+		__aligned_u64	in_batch;	/* start batch,
+						 * NULL to start from beginning
+						 */
+		__aligned_u64	out_batch;	/* output: next start batch */
+		__aligned_u64	keys;
+		__aligned_u64	values;
+		__u32		count;		/* input/output:
+						 * input: # of key/value
+						 * elements
+						 * output: # of filled elements
+						 */
+		__u32		map_fd;
+		__u64		elem_flags;
+		__u64		flags;
+	} batch;
+
 	struct { /* anonymous struct used by BPF_PROG_LOAD command */
 		__u32		prog_type;	/* one of enum bpf_prog_type */
 		__u32		insn_cnt;