Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
pull-request: bpf-next 2022-05-23

We've added 113 non-merge commits during the last 26 day(s) which contain
a total of 121 files changed, 7425 insertions(+), 1586 deletions(-).

The main changes are:

1) Speed up symbol resolution for kprobes multi-link attachments, from Jiri Olsa.

2) Add BPF dynamic pointer infrastructure e.g. to allow for dynamically sized ringbuf
   reservations without extra memory copies, from Joanne Koong.

3) Big batch of libbpf improvements towards libbpf 1.0 release, from Andrii Nakryiko.

4) Add BPF link iterator to traverse links via seq_file ops, from Dmitrii Dolgov.

5) Add source IP address to BPF tunnel key infrastructure, from Kaixi Fan.

6) Refine unprivileged BPF to disable only object-creating commands, from Alan Maguire.

7) Fix JIT blinding of ld_imm64 when they point to subprogs, from Alexei Starovoitov.

8) Add BPF access to mptcp_sock structures and their meta data, from Geliang Tang.

9) Add new BPF helper for access to remote CPU's BPF map elements, from Feng Zhou.

10) Allow attaching 64-bit cookie to BPF link of fentry/fexit/fmod_ret, from Kui-Feng Lee.

11) Follow-ups to typed pointer support in BPF maps, from Kumar Kartikeya Dwivedi.

12) Add busy-poll test cases to the XSK selftest suite, from Magnus Karlsson.

13) Improvements in BPF selftest test_progs subtest output, from Mykola Lysenko.

14) Fill bpf_prog_pack allocator areas with illegal instructions, from Song Liu.

15) Add generic batch operations for BPF map-in-map cases, from Takshak Chahande.

16) Make bpf_jit_enable more user friendly when permanently on 1, from Tiezhu Yang.

17) Fix an array overflow in bpf_trampoline_get_progs(), from Yuntao Wang.

====================

Link: https://lore.kernel.org/r/20220523223805.27931-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

1 files changed, 197 insertions, 2 deletions

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 3e709fed5306..225806a02efb 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -103,7 +103,7 @@ const struct bpf_func_proto bpf_map_pop_elem_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_UNINIT_MAP_VALUE,
+	.arg2_type	= ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
 };
 
 BPF_CALL_2(bpf_map_peek_elem, struct bpf_map *, map, void *, value)
@@ -116,7 +116,23 @@ const struct bpf_func_proto bpf_map_peek_elem_proto = {
 	.gpl_only	= false,
 	.ret_type	= RET_INTEGER,
 	.arg1_type	= ARG_CONST_MAP_PTR,
-	.arg2_type	= ARG_PTR_TO_UNINIT_MAP_VALUE,
+	.arg2_type	= ARG_PTR_TO_MAP_VALUE | MEM_UNINIT,
+};
+
+BPF_CALL_3(bpf_map_lookup_percpu_elem, struct bpf_map *, map, void *, key, u32, cpu)
+{
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	return (unsigned long) map->ops->map_lookup_percpu_elem(map, key, cpu);
+}
+
+const struct bpf_func_proto bpf_map_lookup_percpu_elem_proto = {
+	.func		= bpf_map_lookup_percpu_elem,
+	.gpl_only	= false,
+	.pkt_access	= true,
+	.ret_type	= RET_PTR_TO_MAP_VALUE_OR_NULL,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_PTR_TO_MAP_KEY,
+	.arg3_type	= ARG_ANYTHING,
 };
 
 const struct bpf_func_proto bpf_get_prandom_u32_proto = {
@@ -1396,6 +1412,169 @@ const struct bpf_func_proto bpf_kptr_xchg_proto = {
 	.arg2_btf_id  = BPF_PTR_POISON,
 };
 
+/* Since the upper 8 bits of dynptr->size is reserved, the
+ * maximum supported size is 2^24 - 1.
+ */
+#define DYNPTR_MAX_SIZE	((1UL << 24) - 1)
+#define DYNPTR_TYPE_SHIFT	28
+#define DYNPTR_SIZE_MASK	0xFFFFFF
+#define DYNPTR_RDONLY_BIT	BIT(31)
+
+static bool bpf_dynptr_is_rdonly(struct bpf_dynptr_kern *ptr)
+{
+	return ptr->size & DYNPTR_RDONLY_BIT;
+}
+
+static void bpf_dynptr_set_type(struct bpf_dynptr_kern *ptr, enum bpf_dynptr_type type)
+{
+	ptr->size |= type << DYNPTR_TYPE_SHIFT;
+}
+
+static u32 bpf_dynptr_get_size(struct bpf_dynptr_kern *ptr)
+{
+	return ptr->size & DYNPTR_SIZE_MASK;
+}
+
+int bpf_dynptr_check_size(u32 size)
+{
+	return size > DYNPTR_MAX_SIZE ? -E2BIG : 0;
+}
+
+void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
+		     enum bpf_dynptr_type type, u32 offset, u32 size)
+{
+	ptr->data = data;
+	ptr->offset = offset;
+	ptr->size = size;
+	bpf_dynptr_set_type(ptr, type);
+}
+
+void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr)
+{
+	memset(ptr, 0, sizeof(*ptr));
+}
+
+static int bpf_dynptr_check_off_len(struct bpf_dynptr_kern *ptr, u32 offset, u32 len)
+{
+	u32 size = bpf_dynptr_get_size(ptr);
+
+	if (len > size || offset > size - len)
+		return -E2BIG;
+
+	return 0;
+}
+
+BPF_CALL_4(bpf_dynptr_from_mem, void *, data, u32, size, u64, flags, struct bpf_dynptr_kern *, ptr)
+{
+	int err;
+
+	err = bpf_dynptr_check_size(size);
+	if (err)
+		goto error;
+
+	/* flags is currently unsupported */
+	if (flags) {
+		err = -EINVAL;
+		goto error;
+	}
+
+	bpf_dynptr_init(ptr, data, BPF_DYNPTR_TYPE_LOCAL, 0, size);
+
+	return 0;
+
+error:
+	bpf_dynptr_set_null(ptr);
+	return err;
+}
+
+const struct bpf_func_proto bpf_dynptr_from_mem_proto = {
+	.func		= bpf_dynptr_from_mem,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_LOCAL | MEM_UNINIT,
+};
+
+BPF_CALL_4(bpf_dynptr_read, void *, dst, u32, len, struct bpf_dynptr_kern *, src, u32, offset)
+{
+	int err;
+
+	if (!src->data)
+		return -EINVAL;
+
+	err = bpf_dynptr_check_off_len(src, offset, len);
+	if (err)
+		return err;
+
+	memcpy(dst, src->data + src->offset + offset, len);
+
+	return 0;
+}
+
+const struct bpf_func_proto bpf_dynptr_read_proto = {
+	.func		= bpf_dynptr_read,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_UNINIT_MEM,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg3_type	= ARG_PTR_TO_DYNPTR,
+	.arg4_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_4(bpf_dynptr_write, struct bpf_dynptr_kern *, dst, u32, offset, void *, src, u32, len)
+{
+	int err;
+
+	if (!dst->data || bpf_dynptr_is_rdonly(dst))
+		return -EINVAL;
+
+	err = bpf_dynptr_check_off_len(dst, offset, len);
+	if (err)
+		return err;
+
+	memcpy(dst->data + dst->offset + offset, src, len);
+
+	return 0;
+}
+
+const struct bpf_func_proto bpf_dynptr_write_proto = {
+	.func		= bpf_dynptr_write,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_DYNPTR,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_PTR_TO_MEM | MEM_RDONLY,
+	.arg4_type	= ARG_CONST_SIZE_OR_ZERO,
+};
+
+BPF_CALL_3(bpf_dynptr_data, struct bpf_dynptr_kern *, ptr, u32, offset, u32, len)
+{
+	int err;
+
+	if (!ptr->data)
+		return 0;
+
+	err = bpf_dynptr_check_off_len(ptr, offset, len);
+	if (err)
+		return 0;
+
+	if (bpf_dynptr_is_rdonly(ptr))
+		return 0;
+
+	return (unsigned long)(ptr->data + ptr->offset + offset);
+}
+
+const struct bpf_func_proto bpf_dynptr_data_proto = {
+	.func		= bpf_dynptr_data,
+	.gpl_only	= false,
+	.ret_type	= RET_PTR_TO_DYNPTR_MEM_OR_NULL,
+	.arg1_type	= ARG_PTR_TO_DYNPTR,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_CONST_ALLOC_SIZE_OR_ZERO,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_get_current_task_btf_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
@@ -1420,6 +1599,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_map_pop_elem_proto;
 	case BPF_FUNC_map_peek_elem:
 		return &bpf_map_peek_elem_proto;
+	case BPF_FUNC_map_lookup_percpu_elem:
+		return &bpf_map_lookup_percpu_elem_proto;
 	case BPF_FUNC_get_prandom_u32:
 		return &bpf_get_prandom_u32_proto;
 	case BPF_FUNC_get_smp_processor_id:
@@ -1442,12 +1623,26 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_ringbuf_discard_proto;
 	case BPF_FUNC_ringbuf_query:
 		return &bpf_ringbuf_query_proto;
+	case BPF_FUNC_ringbuf_reserve_dynptr:
+		return &bpf_ringbuf_reserve_dynptr_proto;
+	case BPF_FUNC_ringbuf_submit_dynptr:
+		return &bpf_ringbuf_submit_dynptr_proto;
+	case BPF_FUNC_ringbuf_discard_dynptr:
+		return &bpf_ringbuf_discard_dynptr_proto;
 	case BPF_FUNC_for_each_map_elem:
 		return &bpf_for_each_map_elem_proto;
 	case BPF_FUNC_loop:
 		return &bpf_loop_proto;
 	case BPF_FUNC_strncmp:
 		return &bpf_strncmp_proto;
+	case BPF_FUNC_dynptr_from_mem:
+		return &bpf_dynptr_from_mem_proto;
+	case BPF_FUNC_dynptr_read:
+		return &bpf_dynptr_read_proto;
+	case BPF_FUNC_dynptr_write:
+		return &bpf_dynptr_write_proto;
+	case BPF_FUNC_dynptr_data:
+		return &bpf_dynptr_data_proto;
 	default:
 		break;
 	}