bpf: add queue and stack maps

Queue/stack maps implement a FIFO/LIFO data storage for ebpf programs.
These maps support peek, pop and push operations that are exposed to eBPF
programs through the new bpf_map[peek/pop/push] helpers.  Those operations
are exposed to userspace applications through the already existing
syscalls in the following way:

BPF_MAP_LOOKUP_ELEM            -> peek
BPF_MAP_LOOKUP_AND_DELETE_ELEM -> pop
BPF_MAP_UPDATE_ELEM            -> push

Queue/stack maps are implemented using a buffer, tail and head indexes,
hence BPF_F_NO_PREALLOC is not supported.

As opposite to other maps, queue and stack do not use RCU for protecting
maps values, the bpf_map[peek/pop] have a ARG_PTR_TO_UNINIT_MAP_VALUE
argument that is a pointer to a memory zone where to save the value of a
map.  Basically the same as ARG_PTR_TO_UNINIT_MEM, but the size has not
be passed as an extra argument.

Our main motivation for implementing queue/stack maps was to keep track
of a pool of elements, like network ports in a SNAT, however we forsee
other use cases, like for exampling saving last N kernel events in a map
and then analysing from userspace.

Signed-off-by: Mauricio Vasquez B <mauricio.vasquez@polito.it>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -39,6 +39,9 @@ struct bpf_map_ops {
 	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
 	int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
 	int (*map_delete_elem)(struct bpf_map *map, void *key);
+	int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags);
+	int (*map_pop_elem)(struct bpf_map *map, void *value);
+	int (*map_peek_elem)(struct bpf_map *map, void *value);
 
 	/* funcs called by prog_array and perf_event_array map */
 	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
@@ -811,6 +814,9 @@ static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map,
 extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
 extern const struct bpf_func_proto bpf_map_update_elem_proto;
 extern const struct bpf_func_proto bpf_map_delete_elem_proto;
+extern const struct bpf_func_proto bpf_map_push_elem_proto;
+extern const struct bpf_func_proto bpf_map_pop_elem_proto;
+extern const struct bpf_func_proto bpf_map_peek_elem_proto;
 
 extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
 extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;

include/linux/bpf_types.h

@@ -69,3 +69,5 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_REUSEPORT_SOCKARRAY, reuseport_array_ops)
 #endif
 #endif
+BPF_MAP_TYPE(BPF_MAP_TYPE_QUEUE, queue_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_STACK, stack_map_ops)

include/uapi/linux/bpf.h

@@ -128,6 +128,8 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_CGROUP_STORAGE,
 	BPF_MAP_TYPE_REUSEPORT_SOCKARRAY,
 	BPF_MAP_TYPE_PERCPU_CGROUP_STORAGE,
+	BPF_MAP_TYPE_QUEUE,
+	BPF_MAP_TYPE_STACK,
 };
 
 enum bpf_prog_type {
@@ -462,6 +464,28 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
+ * int bpf_map_push_elem(struct bpf_map *map, const void *value, u64 flags)
+ * 	Description
+ * 		Push an element *value* in *map*. *flags* is one of:
+ *
+ * 		**BPF_EXIST**
+ * 		If the queue/stack is full, the oldest element is removed to
+ * 		make room for this.
+ * 	Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_pop_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Pop an element from *map*.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
+ * int bpf_map_peek_elem(struct bpf_map *map, void *value)
+ * 	Description
+ * 		Get an element from *map* without removing it.
+ * Return
+ * 		0 on success, or a negative error in case of failure.
+ *
  * int bpf_probe_read(void *dst, u32 size, const void *src)
  * 	Description
  * 		For tracing programs, safely attempt to read *size* bytes from
@@ -2303,7 +2327,10 @@ union bpf_attr {
 	FN(skb_ancestor_cgroup_id),	\
 	FN(sk_lookup_tcp),		\
 	FN(sk_lookup_udp),		\
-	FN(sk_release),
+	FN(sk_release),			\
+	FN(map_push_elem),		\
+	FN(map_pop_elem),		\
+	FN(map_peek_elem),
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
  * function eBPF program intends to call

kernel/bpf/Makefile

@@ -3,7 +3,7 @@ obj-y := core.o
 
 obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o
 obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o
-obj-$(CONFIG_BPF_SYSCALL) += local_storage.o
+obj-$(CONFIG_BPF_SYSCALL) += local_storage.o queue_stack_maps.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o
 obj-$(CONFIG_BPF_SYSCALL) += btf.o
 ifeq ($(CONFIG_NET),y)

kernel/bpf/core.c

@@ -1783,6 +1783,9 @@ BPF_CALL_0(bpf_user_rnd_u32)
 const struct bpf_func_proto bpf_map_lookup_elem_proto __weak;
 const struct bpf_func_proto bpf_map_update_elem_proto __weak;
 const struct bpf_func_proto bpf_map_delete_elem_proto __weak;
+const struct bpf_func_proto bpf_map_push_elem_proto __weak;
+const struct bpf_func_proto bpf_map_pop_elem_proto __weak;
+const struct bpf_func_proto bpf_map_peek_elem_proto __weak;
 
 const struct bpf_func_proto bpf_get_prandom_u32_proto __weak;
 const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak;

kernel/bpf/helpers.c

@@ -76,6 +76,49 @@ const struct bpf_func_proto bpf_map_delete_elem_proto = {
 	.arg2_type	= ARG_PTR_TO_MAP_KEY,
 };
 
+BPF_CALL_3(bpf_map_push_elem, struct bpf_map *, map, void *, value, u64, flags)
+{
+	return map->ops->map_push_elem(map, value, flags);
+}
+
+const struct bpf_func_proto bpf_map_push_elem_proto = {
+	.func		= bpf_map_push_elem,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_MAP_VALUE,
+	.arg3_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_2(bpf_map_pop_elem, struct bpf_map *, map, void *, value)
+{
+	return map->ops->map_pop_elem(map, value);
+}
+
+const struct bpf_func_proto bpf_map_pop_elem_proto = {
+	.func		= bpf_map_pop_elem,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MAP_VALUE,
+};
+
+BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
+{
+	return map->ops->map_peek_elem(map, value);
+}
+
+const struct bpf_func_proto bpf_map_peek_elem_proto = {
+	.func		= bpf_map_pop_elem,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_UNINIT_MAP_VALUE,
+};
+
 const struct bpf_func_proto bpf_get_prandom_u32_proto = {
 	.func		= bpf_user_rnd_u32,
 	.gpl_only	= false,