bpf: Add skb dynptrs

Add skb dynptrs, which are dynptrs whose underlying pointer points
to a skb. The dynptr acts on skb data. skb dynptrs have two main
benefits. One is that they allow operations on sizes that are not
statically known at compile-time (eg variable-sized accesses).
Another is that parsing the packet data through dynptrs (instead of
through direct access of skb->data and skb->data_end) can be more
ergonomic and less brittle (eg does not need manual if checking for
being within bounds of data_end).

For bpf prog types that don't support writes on skb data, the dynptr is
read-only (bpf_dynptr_write() will return an error)

For reads and writes through the bpf_dynptr_read() and bpf_dynptr_write()
interfaces, reading and writing from/to data in the head as well as from/to
non-linear paged buffers is supported. Data slices through the
bpf_dynptr_data API are not supported; instead bpf_dynptr_slice() and
bpf_dynptr_slice_rdwr() (added in subsequent commit) should be used.

For examples of how skb dynptrs can be used, please see the attached
selftests.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Link: https://lore.kernel.org/r/20230301154953.641654-8-joannelkoong@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

3 files changed, 141 insertions, 14 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 84cca8473873..ef2d8969ed1f 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -207,6 +207,11 @@ enum btf_kfunc_hook {
 	BTF_KFUNC_HOOK_TRACING,
 	BTF_KFUNC_HOOK_SYSCALL,
 	BTF_KFUNC_HOOK_FMODRET,
+	BTF_KFUNC_HOOK_CGROUP_SKB,
+	BTF_KFUNC_HOOK_SCHED_ACT,
+	BTF_KFUNC_HOOK_SK_SKB,
+	BTF_KFUNC_HOOK_SOCKET_FILTER,
+	BTF_KFUNC_HOOK_LWT,
 	BTF_KFUNC_HOOK_MAX,
 };
 
@@ -7708,6 +7713,19 @@ static int bpf_prog_type_to_kfunc_hook(enum bpf_prog_type prog_type)
 		return BTF_KFUNC_HOOK_TRACING;
 	case BPF_PROG_TYPE_SYSCALL:
 		return BTF_KFUNC_HOOK_SYSCALL;
+	case BPF_PROG_TYPE_CGROUP_SKB:
+		return BTF_KFUNC_HOOK_CGROUP_SKB;
+	case BPF_PROG_TYPE_SCHED_ACT:
+		return BTF_KFUNC_HOOK_SCHED_ACT;
+	case BPF_PROG_TYPE_SK_SKB:
+		return BTF_KFUNC_HOOK_SK_SKB;
+	case BPF_PROG_TYPE_SOCKET_FILTER:
+		return BTF_KFUNC_HOOK_SOCKET_FILTER;
+	case BPF_PROG_TYPE_LWT_OUT:
+	case BPF_PROG_TYPE_LWT_IN:
+	case BPF_PROG_TYPE_LWT_XMIT:
+	case BPF_PROG_TYPE_LWT_SEG6LOCAL:
+		return BTF_KFUNC_HOOK_LWT;
 	default:
 		return BTF_KFUNC_HOOK_MAX;
 	}
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index abdcc52f90a6..e8e2414d1587 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1420,11 +1420,21 @@ static bool bpf_dynptr_is_rdonly(const struct bpf_dynptr_kern *ptr)
 	return ptr->size & DYNPTR_RDONLY_BIT;
 }
 
+void bpf_dynptr_set_rdonly(struct bpf_dynptr_kern *ptr)
+{
+	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 enum bpf_dynptr_type bpf_dynptr_get_type(const struct bpf_dynptr_kern *ptr)
+{
+	return (ptr->size & ~(DYNPTR_RDONLY_BIT)) >> DYNPTR_TYPE_SHIFT;
+}
+
 u32 bpf_dynptr_get_size(const struct bpf_dynptr_kern *ptr)
 {
 	return ptr->size & DYNPTR_SIZE_MASK;
@@ -1497,6 +1507,7 @@ static const struct bpf_func_proto bpf_dynptr_from_mem_proto = {
 BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern *, src,
 	   u32, offset, u64, flags)
 {
+	enum bpf_dynptr_type type;
 	int err;
 
 	if (!src->data || flags)
@@ -1506,13 +1517,23 @@ BPF_CALL_5(bpf_dynptr_read, void *, dst, u32, len, const struct bpf_dynptr_kern
 	if (err)
 		return err;
 
-	/* Source and destination may possibly overlap, hence use memmove to
-	 * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr
-	 * pointing to overlapping PTR_TO_MAP_VALUE regions.
-	 */
-	memmove(dst, src->data + src->offset + offset, len);
+	type = bpf_dynptr_get_type(src);
 
-	return 0;
+	switch (type) {
+	case BPF_DYNPTR_TYPE_LOCAL:
+	case BPF_DYNPTR_TYPE_RINGBUF:
+		/* Source and destination may possibly overlap, hence use memmove to
+		 * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr
+		 * pointing to overlapping PTR_TO_MAP_VALUE regions.
+		 */
+		memmove(dst, src->data + src->offset + offset, len);
+		return 0;
+	case BPF_DYNPTR_TYPE_SKB:
+		return __bpf_skb_load_bytes(src->data, src->offset + offset, dst, len);
+	default:
+		WARN_ONCE(true, "bpf_dynptr_read: unknown dynptr type %d\n", type);
+		return -EFAULT;
+	}
 }
 
 static const struct bpf_func_proto bpf_dynptr_read_proto = {
@@ -1529,22 +1550,36 @@ static const struct bpf_func_proto bpf_dynptr_read_proto = {
 BPF_CALL_5(bpf_dynptr_write, const struct bpf_dynptr_kern *, dst, u32, offset, void *, src,
 	   u32, len, u64, flags)
 {
+	enum bpf_dynptr_type type;
 	int err;
 
-	if (!dst->data || flags || bpf_dynptr_is_rdonly(dst))
+	if (!dst->data || bpf_dynptr_is_rdonly(dst))
 		return -EINVAL;
 
 	err = bpf_dynptr_check_off_len(dst, offset, len);
 	if (err)
 		return err;
 
-	/* Source and destination may possibly overlap, hence use memmove to
-	 * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr
-	 * pointing to overlapping PTR_TO_MAP_VALUE regions.
-	 */
-	memmove(dst->data + dst->offset + offset, src, len);
+	type = bpf_dynptr_get_type(dst);
 
-	return 0;
+	switch (type) {
+	case BPF_DYNPTR_TYPE_LOCAL:
+	case BPF_DYNPTR_TYPE_RINGBUF:
+		if (flags)
+			return -EINVAL;
+		/* Source and destination may possibly overlap, hence use memmove to
+		 * copy the data. E.g. bpf_dynptr_from_mem may create two dynptr
+		 * pointing to overlapping PTR_TO_MAP_VALUE regions.
+		 */
+		memmove(dst->data + dst->offset + offset, src, len);
+		return 0;
+	case BPF_DYNPTR_TYPE_SKB:
+		return __bpf_skb_store_bytes(dst->data, dst->offset + offset, src, len,
+					     flags);
+	default:
+		WARN_ONCE(true, "bpf_dynptr_write: unknown dynptr type %d\n", type);
+		return -EFAULT;
+	}
 }
 
 static const struct bpf_func_proto bpf_dynptr_write_proto = {
@@ -1560,6 +1595,7 @@ static const struct bpf_func_proto bpf_dynptr_write_proto = {
 
 BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u32, len)
 {
+	enum bpf_dynptr_type type;
 	int err;
 
 	if (!ptr->data)
@@ -1572,7 +1608,19 @@ BPF_CALL_3(bpf_dynptr_data, const struct bpf_dynptr_kern *, ptr, u32, offset, u3
 	if (bpf_dynptr_is_rdonly(ptr))
 		return 0;
 
-	return (unsigned long)(ptr->data + ptr->offset + offset);
+	type = bpf_dynptr_get_type(ptr);
+
+	switch (type) {
+	case BPF_DYNPTR_TYPE_LOCAL:
+	case BPF_DYNPTR_TYPE_RINGBUF:
+		return (unsigned long)(ptr->data + ptr->offset + offset);
+	case BPF_DYNPTR_TYPE_SKB:
+		/* skb dynptrs should use bpf_dynptr_slice / bpf_dynptr_slice_rdwr */
+		return 0;
+	default:
+		WARN_ONCE(true, "bpf_dynptr_data: unknown dynptr type %d\n", type);
+		return 0;
+	}
 }
 
 static const struct bpf_func_proto bpf_dynptr_data_proto = {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index d052aa5800de..4f5fce16543b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -750,6 +750,8 @@ static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type)
 		return BPF_DYNPTR_TYPE_LOCAL;
 	case DYNPTR_TYPE_RINGBUF:
 		return BPF_DYNPTR_TYPE_RINGBUF;
+	case DYNPTR_TYPE_SKB:
+		return BPF_DYNPTR_TYPE_SKB;
 	default:
 		return BPF_DYNPTR_TYPE_INVALID;
 	}
@@ -6295,6 +6297,9 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
 			case DYNPTR_TYPE_RINGBUF:
 				err_extra = "ringbuf";
 				break;
+			case DYNPTR_TYPE_SKB:
+				err_extra = "skb ";
+				break;
 			default:
 				err_extra = "<unknown>";
 				break;
@@ -6737,6 +6742,24 @@ static int dynptr_ref_obj_id(struct bpf_verifier_env *env, struct bpf_reg_state
 	return state->stack[spi].spilled_ptr.ref_obj_id;
 }
 
+static enum bpf_dynptr_type dynptr_get_type(struct bpf_verifier_env *env,
+					    struct bpf_reg_state *reg)
+{
+	struct bpf_func_state *state = func(env, reg);
+	int spi;
+
+	if (reg->type == CONST_PTR_TO_DYNPTR)
+		return reg->dynptr.type;
+
+	spi = __get_spi(reg->off);
+	if (spi < 0) {
+		verbose(env, "verifier internal error: invalid spi when querying dynptr type\n");
+		return BPF_DYNPTR_TYPE_INVALID;
+	}
+
+	return state->stack[spi].spilled_ptr.dynptr.type;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			  struct bpf_call_arg_meta *meta,
 			  const struct bpf_func_proto *fn,
@@ -8383,6 +8406,27 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 
 		break;
 	}
+	case BPF_FUNC_dynptr_write:
+	{
+		enum bpf_dynptr_type dynptr_type;
+		struct bpf_reg_state *reg;
+
+		reg = get_dynptr_arg_reg(env, fn, regs);
+		if (!reg)
+			return -EFAULT;
+
+		dynptr_type = dynptr_get_type(env, reg);
+		if (dynptr_type == BPF_DYNPTR_TYPE_INVALID)
+			return -EFAULT;
+
+		if (dynptr_type == BPF_DYNPTR_TYPE_SKB)
+			/* this will trigger clear_all_pkt_pointers(), which will
+			 * invalidate all dynptr slices associated with the skb
+			 */
+			changes_data = true;
+
+		break;
+	}
 	case BPF_FUNC_user_ringbuf_drain:
 		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
 					set_user_ringbuf_callback_state);
@@ -8898,6 +8942,7 @@ enum special_kfunc_type {
 	KF_bpf_rbtree_remove,
 	KF_bpf_rbtree_add,
 	KF_bpf_rbtree_first,
+	KF_bpf_dynptr_from_skb,
 };
 
 BTF_SET_START(special_kfunc_set)
@@ -8912,6 +8957,7 @@ BTF_ID(func, bpf_rdonly_cast)
 BTF_ID(func, bpf_rbtree_remove)
 BTF_ID(func, bpf_rbtree_add)
 BTF_ID(func, bpf_rbtree_first)
+BTF_ID(func, bpf_dynptr_from_skb)
 BTF_SET_END(special_kfunc_set)
 
 BTF_ID_LIST(special_kfunc_list)
@@ -8928,6 +8974,7 @@ BTF_ID(func, bpf_rcu_read_unlock)
 BTF_ID(func, bpf_rbtree_remove)
 BTF_ID(func, bpf_rbtree_add)
 BTF_ID(func, bpf_rbtree_first)
+BTF_ID(func, bpf_dynptr_from_skb)
 
 static bool is_kfunc_bpf_rcu_read_lock(struct bpf_kfunc_call_arg_meta *meta)
 {
@@ -9682,6 +9729,9 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
 			if (is_kfunc_arg_uninit(btf, &args[i]))
 				dynptr_arg_type |= MEM_UNINIT;
 
+			if (meta->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb])
+				dynptr_arg_type |= DYNPTR_TYPE_SKB;
+
 			ret = process_dynptr_func(env, regno, insn_idx, dynptr_arg_type);
 			if (ret < 0)
 				return ret;
@@ -16356,6 +16406,17 @@ static int fixup_kfunc_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 		   desc->func_id == special_kfunc_list[KF_bpf_rdonly_cast]) {
 		insn_buf[0] = BPF_MOV64_REG(BPF_REG_0, BPF_REG_1);
 		*cnt = 1;
+	} else if (desc->func_id == special_kfunc_list[KF_bpf_dynptr_from_skb]) {
+		bool seen_direct_write = env->seen_direct_write;
+		bool is_rdonly = !may_access_direct_pkt_data(env, NULL, BPF_WRITE);
+
+		if (is_rdonly)
+			insn->imm = BPF_CALL_IMM(bpf_dynptr_from_skb_rdonly);
+
+		/* restore env->seen_direct_write to its original value, since
+		 * may_access_direct_pkt_data mutates it
+		 */
+		env->seen_direct_write = seen_direct_write;
 	}
 	return 0;
 }