bpf: Introduce bpf_arena.

Introduce bpf_arena, which is a sparse shared memory region between the bpf
program and user space.

Use cases:
1. User space mmap-s bpf_arena and uses it as a traditional mmap-ed
   anonymous region, like memcached or any key/value storage. The bpf
   program implements an in-kernel accelerator. XDP prog can search for
   a key in bpf_arena and return a value without going to user space.
2. The bpf program builds arbitrary data structures in bpf_arena (hash
   tables, rb-trees, sparse arrays), while user space consumes it.
3. bpf_arena is a "heap" of memory from the bpf program's point of view.
   The user space may mmap it, but bpf program will not convert pointers
   to user base at run-time to improve bpf program speed.

Initially, the kernel vm_area and user vma are not populated. User space
can fault in pages within the range. While servicing a page fault,
bpf_arena logic will insert a new page into the kernel and user vmas. The
bpf program can allocate pages from that region via
bpf_arena_alloc_pages(). This kernel function will insert pages into the
kernel vm_area. The subsequent fault-in from user space will populate that
page into the user vma. The BPF_F_SEGV_ON_FAULT flag at arena creation time
can be used to prevent fault-in from user space. In such a case, if a page
is not allocated by the bpf program and not present in the kernel vm_area,
the user process will segfault. This is useful for use cases 2 and 3 above.

bpf_arena_alloc_pages() is similar to user space mmap(). It allocates pages
either at a specific address within the arena or allocates a range with the
maple tree. bpf_arena_free_pages() is analogous to munmap(), which frees
pages and removes the range from the kernel vm_area and from user process
vmas.

bpf_arena can be used as a bpf program "heap" of up to 4GB. The speed of
bpf program is more important than ease of sharing with user space. This is
use case 3. In such a case, the BPF_F_NO_USER_CONV flag is recommended.
It will tell the verifier to treat the rX = bpf_arena_cast_user(rY)
instruction as a 32-bit move wX = wY, which will improve bpf prog
performance. Otherwise, bpf_arena_cast_user is translated by JIT to
conditionally add the upper 32 bits of user vm_start (if the pointer is not
NULL) to arena pointers before they are stored into memory. This way, user
space sees them as valid 64-bit pointers.

Diff https://github.com/llvm/llvm-project/pull/84410 enables LLVM BPF
backend generate the bpf_addr_space_cast() instruction to cast pointers
between address_space(1) which is reserved for bpf_arena pointers and
default address space zero. All arena pointers in a bpf program written in
C language are tagged as __attribute__((address_space(1))). Hence, clang
provides helpful diagnostics when pointers cross address space. Libbpf and
the kernel support only address_space == 1. All other address space
identifiers are reserved.

rX = bpf_addr_space_cast(rY, /* dst_as */ 1, /* src_as */ 0) tells the
verifier that rX->type = PTR_TO_ARENA. Any further operations on
PTR_TO_ARENA register have to be in the 32-bit domain. The verifier will
mark load/store through PTR_TO_ARENA with PROBE_MEM32. JIT will generate
them as kern_vm_start + 32bit_addr memory accesses. The behavior is similar
to copy_from_kernel_nofault() except that no address checks are necessary.
The address is guaranteed to be in the 4GB range. If the page is not
present, the destination register is zeroed on read, and the operation is
ignored on write.

rX = bpf_addr_space_cast(rY, 0, 1) tells the verifier that rX->type =
unknown scalar. If arena->map_flags has BPF_F_NO_USER_CONV set, then the
verifier converts such cast instructions to mov32. Otherwise, JIT will emit
native code equivalent to:
rX = (u32)rY;
if (rY)
  rX |= clear_lo32_bits(arena->user_vm_start); /* replace hi32 bits in rX */

After such conversion, the pointer becomes a valid user pointer within
bpf_arena range. The user process can access data structures created in
bpf_arena without any additional computations. For example, a linked list
built by a bpf program can be walked natively by user space.
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Reviewed-by: Barret Rhoden <brho@google.com>
Link: https://lore.kernel.org/bpf/20240308010812.89848-2-alexei.starovoitov@gmail.com

include/linux/bpf.h

@@ -37,6 +37,7 @@ struct perf_event;
 struct bpf_prog;
 struct bpf_prog_aux;
 struct bpf_map;
+struct bpf_arena;
 struct sock;
 struct seq_file;
 struct btf;
@@ -528,8 +529,8 @@ void bpf_list_head_free(const struct btf_field *field, void *list_head,
 			struct bpf_spin_lock *spin_lock);
 void bpf_rb_root_free(const struct btf_field *field, void *rb_root,
 		      struct bpf_spin_lock *spin_lock);
-
-
+u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena);
+u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena);
 int bpf_obj_name_cpy(char *dst, const char *src, unsigned int size);
 
 struct bpf_offload_dev;
@@ -2215,6 +2216,8 @@ int  generic_map_delete_batch(struct bpf_map *map,
 struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
 struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id);
 
+int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid,
+			unsigned long nr_pages, struct page **page_array);
 #ifdef CONFIG_MEMCG_KMEM
 void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags,
 			   int node);

include/linux/bpf_types.h

@@ -132,6 +132,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_STRUCT_OPS, bpf_struct_ops_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_RINGBUF, ringbuf_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_BLOOM_FILTER, bloom_filter_map_ops)
 BPF_MAP_TYPE(BPF_MAP_TYPE_USER_RINGBUF, user_ringbuf_map_ops)
+BPF_MAP_TYPE(BPF_MAP_TYPE_ARENA, arena_map_ops)
 
 BPF_LINK_TYPE(BPF_LINK_TYPE_RAW_TRACEPOINT, raw_tracepoint)
 BPF_LINK_TYPE(BPF_LINK_TYPE_TRACING, tracing)

include/uapi/linux/bpf.h

@@ -1009,6 +1009,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_BLOOM_FILTER,
 	BPF_MAP_TYPE_USER_RINGBUF,
 	BPF_MAP_TYPE_CGRP_STORAGE,
+	BPF_MAP_TYPE_ARENA,
 	__MAX_BPF_MAP_TYPE
 };
 
@@ -1396,6 +1397,12 @@ enum {
 
 /* BPF token FD is passed in a corresponding command's token_fd field */
 	BPF_F_TOKEN_FD          = (1U << 16),
+
+/* When user space page faults in bpf_arena send SIGSEGV instead of inserting new page */
+	BPF_F_SEGV_ON_FAULT	= (1U << 17),
+
+/* Do not translate kernel bpf_arena pointers to user pointers */
+	BPF_F_NO_USER_CONV	= (1U << 18),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -1467,6 +1474,9 @@ union bpf_attr {
 		 * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
 		 * number of hash functions (if 0, the bloom filter will default
 		 * to using 5 hash functions).
+		 *
+		 * BPF_MAP_TYPE_ARENA - contains the address where user space
+		 * is going to mmap() the arena. It has to be page aligned.
 		 */
 		__u64	map_extra;
 

kernel/bpf/Makefile

@@ -15,6 +15,9 @@ obj-${CONFIG_BPF_LSM}	  += bpf_inode_storage.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o
 obj-$(CONFIG_BPF_JIT) += trampoline.o
 obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o
+ifeq ($(CONFIG_MMU)$(CONFIG_64BIT),yy)
+obj-$(CONFIG_BPF_SYSCALL) += arena.o
+endif
 obj-$(CONFIG_BPF_JIT) += dispatcher.o
 ifeq ($(CONFIG_NET),y)
 obj-$(CONFIG_BPF_SYSCALL) += devmap.o

kernel/bpf/core.c

@@ -2976,6 +2976,17 @@ void __weak arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp,
 {
 }
 
+/* for configs without MMU or 32-bit */
+__weak const struct bpf_map_ops arena_map_ops;
+__weak u64 bpf_arena_get_user_vm_start(struct bpf_arena *arena)
+{
+	return 0;
+}
+__weak u64 bpf_arena_get_kern_vm_start(struct bpf_arena *arena)
+{
+	return 0;
+}
+
 #ifdef CONFIG_BPF_SYSCALL
 static int __init bpf_global_ma_init(void)
 {

kernel/bpf/syscall.c

@@ -164,6 +164,7 @@ static int bpf_map_update_value(struct bpf_map *map, struct file *map_file,
 	if (bpf_map_is_offloaded(map)) {
 		return bpf_map_offload_update_elem(map, key, value, flags);
 	} else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+		   map->map_type == BPF_MAP_TYPE_ARENA ||
 		   map->map_type == BPF_MAP_TYPE_STRUCT_OPS) {
 		return map->ops->map_update_elem(map, key, value, flags);
 	} else if (map->map_type == BPF_MAP_TYPE_SOCKHASH ||
@@ -479,6 +480,39 @@ static void bpf_map_release_memcg(struct bpf_map *map)
 }
 #endif
 
+int bpf_map_alloc_pages(const struct bpf_map *map, gfp_t gfp, int nid,
+			unsigned long nr_pages, struct page **pages)
+{
+	unsigned long i, j;
+	struct page *pg;
+	int ret = 0;
+#ifdef CONFIG_MEMCG_KMEM
+	struct mem_cgroup *memcg, *old_memcg;
+
+	memcg = bpf_map_get_memcg(map);
+	old_memcg = set_active_memcg(memcg);
+#endif
+	for (i = 0; i < nr_pages; i++) {
+		pg = alloc_pages_node(nid, gfp | __GFP_ACCOUNT, 0);
+
+		if (pg) {
+			pages[i] = pg;
+			continue;
+		}
+		for (j = 0; j < i; j++)
+			__free_page(pages[j]);
+		ret = -ENOMEM;
+		break;
+	}
+
+#ifdef CONFIG_MEMCG_KMEM
+	set_active_memcg(old_memcg);
+	mem_cgroup_put(memcg);
+#endif
+	return ret;
+}
+
+
 static int btf_field_cmp(const void *a, const void *b)
 {
 	const struct btf_field *f1 = a, *f2 = b;
@@ -1176,6 +1210,7 @@ static int map_create(union bpf_attr *attr)
 	}
 
 	if (attr->map_type != BPF_MAP_TYPE_BLOOM_FILTER &&
+	    attr->map_type != BPF_MAP_TYPE_ARENA &&
 	    attr->map_extra != 0)
 		return -EINVAL;
 
@@ -1265,6 +1300,7 @@ static int map_create(union bpf_attr *attr)
 	case BPF_MAP_TYPE_LRU_PERCPU_HASH:
 	case BPF_MAP_TYPE_STRUCT_OPS:
 	case BPF_MAP_TYPE_CPUMAP:
+	case BPF_MAP_TYPE_ARENA:
 		if (!bpf_token_capable(token, CAP_BPF))
 			goto put_token;
 		break;

kernel/bpf/verifier.c

@@ -18108,6 +18108,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env,
 		case BPF_MAP_TYPE_CGRP_STORAGE:
 		case BPF_MAP_TYPE_QUEUE:
 		case BPF_MAP_TYPE_STACK:
+		case BPF_MAP_TYPE_ARENA:
 			break;
 		default:
 			verbose(env,

tools/include/uapi/linux/bpf.h

@@ -1009,6 +1009,7 @@ enum bpf_map_type {
 	BPF_MAP_TYPE_BLOOM_FILTER,
 	BPF_MAP_TYPE_USER_RINGBUF,
 	BPF_MAP_TYPE_CGRP_STORAGE,
+	BPF_MAP_TYPE_ARENA,
 	__MAX_BPF_MAP_TYPE
 };
 
@@ -1396,6 +1397,12 @@ enum {
 
 /* BPF token FD is passed in a corresponding command's token_fd field */
 	BPF_F_TOKEN_FD          = (1U << 16),
+
+/* When user space page faults in bpf_arena send SIGSEGV instead of inserting new page */
+	BPF_F_SEGV_ON_FAULT	= (1U << 17),
+
+/* Do not translate kernel bpf_arena pointers to user pointers */
+	BPF_F_NO_USER_CONV	= (1U << 18),
 };
 
 /* Flags for BPF_PROG_QUERY. */
@@ -1467,6 +1474,9 @@ union bpf_attr {
 		 * BPF_MAP_TYPE_BLOOM_FILTER - the lowest 4 bits indicate the
 		 * number of hash functions (if 0, the bloom filter will default
 		 * to using 5 hash functions).
+		 *
+		 * BPF_MAP_TYPE_ARENA - contains the address where user space
+		 * is going to mmap() the arena. It has to be page aligned.
 		 */
 		__u64	map_extra;