[PATCH bpf-next v5 5/6] bpf: Add dynptr data slices

[Joanne Koong <joannelkoong@gmail.com>]

This patch adds a new helper function

void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len);

which returns a pointer to the underlying data of a dynptr. *len*
must be a statically known value. The bpf program may access the returned
data slice as a normal buffer (eg can do direct reads and writes), since
the verifier associates the length with the returned pointer, and
enforces that no out of bounds accesses occur.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
---
 include/linux/bpf.h            |  4 ++++
 include/uapi/linux/bpf.h       | 12 ++++++++++++
 kernel/bpf/helpers.c           | 28 ++++++++++++++++++++++++++++
 kernel/bpf/verifier.c          | 27 +++++++++++++++++++++++++++
 tools/include/uapi/linux/bpf.h | 12 ++++++++++++
 5 files changed, 83 insertions(+)

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index dce532393f3d..ddf97b12e180 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -398,6 +398,9 @@ enum bpf_type_flag {
 	/* DYNPTR points to a ringbuf record. */
 	DYNPTR_TYPE_RINGBUF	= BIT(9 + BPF_BASE_TYPE_BITS),
 
+	/* MEM is memory owned by a dynptr */
+	MEM_DYNPTR		= BIT(10 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
@@ -488,6 +491,7 @@ enum bpf_return_type {
 	RET_PTR_TO_TCP_SOCK_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_TCP_SOCK,
 	RET_PTR_TO_SOCK_COMMON_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_SOCK_COMMON,
 	RET_PTR_TO_ALLOC_MEM_OR_NULL	= PTR_MAYBE_NULL | MEM_ALLOC | RET_PTR_TO_ALLOC_MEM,
+	RET_PTR_TO_DYNPTR_MEM_OR_NULL	= PTR_MAYBE_NULL | MEM_DYNPTR | RET_PTR_TO_ALLOC_MEM,
 	RET_PTR_TO_BTF_ID_OR_NULL	= PTR_MAYBE_NULL | RET_PTR_TO_BTF_ID,
 
 	/* This must be the last entry. Its purpose is to ensure the enum is
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index d11603c5b87a..89d0932255ab 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5232,6 +5232,17 @@ union bpf_attr {
  *		0 on success, -E2BIG if *offset* + *len* exceeds the length
  *		of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
  *		is a read-only dynptr.
+ *
+ * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len)
+ *	Description
+ *		Get a pointer to the underlying dynptr data.
+ *
+ *		*len* must be a statically known value. The returned data slice
+ *		is invalidated whenever the dynptr is invalidated.
+ *	Return
+ *		Pointer to the underlying dynptr data, NULL if the dynptr is
+ *		read-only, if the dynptr is invalid, or if the offset and length
+ *		is out of bounds.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5436,6 +5447,7 @@ union bpf_attr {
 	FN(ringbuf_discard_dynptr),	\
 	FN(dynptr_read),		\
 	FN(dynptr_write),		\
+	FN(dynptr_data),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 726a4164ceca..47b36c4f71de 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1549,6 +1549,32 @@ const struct bpf_func_proto bpf_dynptr_write_proto = {
 	.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;
@@ -1615,6 +1641,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		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;
 	}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4b502b8a369e..79c68e28ae5a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -567,6 +567,8 @@ static const char *reg_type_str(struct bpf_verifier_env *env,
 		strncpy(prefix, "rdonly_", 32);
 	if (type & MEM_ALLOC)
 		strncpy(prefix, "alloc_", 32);
+	if (type & MEM_DYNPTR)
+		strncpy(prefix, "dynptr_", 32);
 	if (type & MEM_USER)
 		strncpy(prefix, "user_", 32);
 	if (type & MEM_PERCPU)
@@ -5640,6 +5642,7 @@ static const struct bpf_reg_types mem_types = {
 		PTR_TO_MAP_VALUE,
 		PTR_TO_MEM,
 		PTR_TO_MEM | MEM_ALLOC,
+		PTR_TO_MEM | MEM_DYNPTR,
 		PTR_TO_BUF,
 	},
 };
@@ -5803,6 +5806,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 	case PTR_TO_MEM:
 	case PTR_TO_MEM | MEM_RDONLY:
 	case PTR_TO_MEM | MEM_ALLOC:
+	case PTR_TO_MEM | MEM_DYNPTR:
 	case PTR_TO_BUF:
 	case PTR_TO_BUF | MEM_RDONLY:
 	case SCALAR_VALUE:
@@ -5837,6 +5841,14 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 	return __check_ptr_off_reg(env, reg, regno, fixed_off_ok);
 }
 
+static u32 stack_slot_get_id(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
+{
+	struct bpf_func_state *state = func(env, reg);
+	int spi = get_spi(reg->off);
+
+	return state->stack[spi].spilled_ptr.id;
+}
+
 static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 			  struct bpf_call_arg_meta *meta,
 			  const struct bpf_func_proto *fn)
@@ -7383,6 +7395,21 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		regs[BPF_REG_0].id = id;
 		/* For release_reference() */
 		regs[BPF_REG_0].ref_obj_id = id;
+	} else if (func_id == BPF_FUNC_dynptr_data) {
+		int dynptr_id = 0, i;
+
+		/* Find the id of the dynptr we're acquiring a reference to */
+		for (i = 0; i < MAX_BPF_FUNC_REG_ARGS; i++) {
+			if (arg_type_is_dynptr(fn->arg_type[i])) {
+				if (dynptr_id) {
+					verbose(env, "verifier internal error: multiple dynptr args in func\n");
+					return -EFAULT;
+				}
+				dynptr_id = stack_slot_get_id(env, &regs[BPF_REG_1 + i]);
+			}
+		}
+		/* For release_reference() */
+		regs[BPF_REG_0].ref_obj_id = dynptr_id;
 	}
 
 	do_refine_retval_range(regs, fn->ret_type, func_id, &meta);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index d11603c5b87a..89d0932255ab 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5232,6 +5232,17 @@ union bpf_attr {
  *		0 on success, -E2BIG if *offset* + *len* exceeds the length
  *		of *dst*'s data, -EINVAL if *dst* is an invalid dynptr or if *dst*
  *		is a read-only dynptr.
+ *
+ * void *bpf_dynptr_data(struct bpf_dynptr *ptr, u32 offset, u32 len)
+ *	Description
+ *		Get a pointer to the underlying dynptr data.
+ *
+ *		*len* must be a statically known value. The returned data slice
+ *		is invalidated whenever the dynptr is invalidated.
+ *	Return
+ *		Pointer to the underlying dynptr data, NULL if the dynptr is
+ *		read-only, if the dynptr is invalid, or if the offset and length
+ *		is out of bounds.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5436,6 +5447,7 @@ union bpf_attr {
 	FN(ringbuf_discard_dynptr),	\
 	FN(dynptr_read),		\
 	FN(dynptr_write),		\
+	FN(dynptr_data),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
-- 
2.30.2