11 files changed, 1636 insertions, 5 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a9b1875212f6..a7080c86fa76 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -392,10 +392,18 @@ enum bpf_type_flag {
 
 	MEM_UNINIT		= BIT(7 + BPF_BASE_TYPE_BITS),
 
+	/* DYNPTR points to memory local to the bpf program. */
+	DYNPTR_TYPE_LOCAL	= BIT(8 + BPF_BASE_TYPE_BITS),
+
+	/* DYNPTR points to a ringbuf record. */
+	DYNPTR_TYPE_RINGBUF	= BIT(9 + BPF_BASE_TYPE_BITS),
+
 	__BPF_TYPE_FLAG_MAX,
 	__BPF_TYPE_LAST_FLAG	= __BPF_TYPE_FLAG_MAX - 1,
 };
 
+#define DYNPTR_TYPE_FLAG_MASK	(DYNPTR_TYPE_LOCAL | DYNPTR_TYPE_RINGBUF)
+
 /* Max number of base types. */
 #define BPF_BASE_TYPE_LIMIT	(1UL << BPF_BASE_TYPE_BITS)
 
@@ -438,6 +446,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_CONST_STR,	/* pointer to a null terminated read-only string */
 	ARG_PTR_TO_TIMER,	/* pointer to bpf_timer */
 	ARG_PTR_TO_KPTR,	/* pointer to referenced kptr */
+	ARG_PTR_TO_DYNPTR,      /* pointer to bpf_dynptr. See bpf_type_flag for dynptr type */
 	__BPF_ARG_TYPE_MAX,
 
 	/* Extended arg_types. */
@@ -479,6 +488,7 @@ 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 | 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
@@ -2225,6 +2235,9 @@ extern const struct bpf_func_proto bpf_ringbuf_reserve_proto;
 extern const struct bpf_func_proto bpf_ringbuf_submit_proto;
 extern const struct bpf_func_proto bpf_ringbuf_discard_proto;
 extern const struct bpf_func_proto bpf_ringbuf_query_proto;
+extern const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto;
+extern const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto;
+extern const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
@@ -2376,4 +2389,33 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 			u32 **bin_buf, u32 num_args);
 void bpf_bprintf_cleanup(void);
 
+/* the implementation of the opaque uapi struct bpf_dynptr */
+struct bpf_dynptr_kern {
+	void *data;
+	/* Size represents the number of usable bytes of dynptr data.
+	 * If for example the offset is at 4 for a local dynptr whose data is
+	 * of type u64, the number of usable bytes is 4.
+	 *
+	 * The upper 8 bits are reserved. It is as follows:
+	 * Bits 0 - 23 = size
+	 * Bits 24 - 30 = dynptr type
+	 * Bit 31 = whether dynptr is read-only
+	 */
+	u32 size;
+	u32 offset;
+} __aligned(8);
+
+enum bpf_dynptr_type {
+	BPF_DYNPTR_TYPE_INVALID,
+	/* Points to memory that is local to the bpf program */
+	BPF_DYNPTR_TYPE_LOCAL,
+	/* Underlying data is a ringbuf record */
+	BPF_DYNPTR_TYPE_RINGBUF,
+};
+
+void bpf_dynptr_init(struct bpf_dynptr_kern *ptr, void *data,
+		     enum bpf_dynptr_type type, u32 offset, u32 size);
+void bpf_dynptr_set_null(struct bpf_dynptr_kern *ptr);
+int bpf_dynptr_check_size(u32 size);
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 1f1e7f2ea967..e8439f6cbe57 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -72,6 +72,18 @@ struct bpf_reg_state {
 
 		u32 mem_size; /* for PTR_TO_MEM | PTR_TO_MEM_OR_NULL */
 
+		/* For dynptr stack slots */
+		struct {
+			enum bpf_dynptr_type type;
+			/* A dynptr is 16 bytes so it takes up 2 stack slots.
+			 * We need to track which slot is the first slot
+			 * to protect against cases where the user may try to
+			 * pass in an address starting at the second slot of the
+			 * dynptr.
+			 */
+			bool first_slot;
+		} dynptr;
+
 		/* Max size from any of the above. */
 		struct {
 			unsigned long raw1;
@@ -88,6 +100,8 @@ struct bpf_reg_state {
 	 * for the purpose of tracking that it's freed.
 	 * For PTR_TO_SOCKET this is used to share which pointers retain the
 	 * same reference to the socket, to determine proper reference freeing.
+	 * For stack slots that are dynptrs, this is used to track references to
+	 * the dynptr to determine proper reference freeing.
 	 */
 	u32 id;
 	/* PTR_TO_SOCKET and PTR_TO_TCP_SOCK could be a ptr returned
@@ -174,9 +188,15 @@ enum bpf_stack_slot_type {
 	STACK_SPILL,      /* register spilled into stack */
 	STACK_MISC,	  /* BPF program wrote some data into this slot */
 	STACK_ZERO,	  /* BPF program wrote constant zero */
+	/* A dynptr is stored in this stack slot. The type of dynptr
+	 * is stored in bpf_stack_state->spilled_ptr.dynptr.type
+	 */
+	STACK_DYNPTR,
 };
 
 #define BPF_REG_SIZE 8	/* size of eBPF register in bytes */
+#define BPF_DYNPTR_SIZE		sizeof(struct bpf_dynptr_kern)
+#define BPF_DYNPTR_NR_SLOTS		(BPF_DYNPTR_SIZE / BPF_REG_SIZE)
 
 struct bpf_stack_state {
 	struct bpf_reg_state spilled_ptr;
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 56688bee20d9..f4009dbdf62d 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -5178,6 +5178,77 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ *	Description
+ *		Get a dynptr to local memory *data*.
+ *
+ *		*data* must be a ptr to a map value.
+ *		The maximum *size* supported is DYNPTR_MAX_SIZE.
+ *		*flags* is currently unused.
+ *	Return
+ *		0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
+ *		-EINVAL if flags is not 0.
+ *
+ * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ *	Description
+ *		Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ *		through the dynptr interface. *flags* must be 0.
+ *
+ *		Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ *		bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ *		reservation fails. This is enforced by the verifier.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ *	Description
+ *		Submit reserved ring buffer sample, pointed to by *data*,
+ *		through the dynptr interface. This is a no-op if the dynptr is
+ *		invalid/null.
+ *
+ *		For more information on *flags*, please see
+ *		'bpf_ringbuf_submit'.
+ *	Return
+ *		Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ *	Description
+ *		Discard reserved ring buffer sample through the dynptr
+ *		interface. This is a no-op if the dynptr is invalid/null.
+ *
+ *		For more information on *flags*, please see
+ *		'bpf_ringbuf_discard'.
+ *	Return
+ *		Nothing. Always succeeds.
+ *
+ * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset)
+ *	Description
+ *		Read *len* bytes from *src* into *dst*, starting from *offset*
+ *		into *src*.
+ *	Return
+ *		0 on success, -E2BIG if *offset* + *len* exceeds the length
+ *		of *src*'s data, -EINVAL if *src* is an invalid dynptr.
+ *
+ * long bpf_dynptr_write(struct bpf_dynptr *dst, u32 offset, void *src, u32 len)
+ *	Description
+ *		Write *len* bytes from *src* into *dst*, starting from *offset*
+ *		into *dst*.
+ *	Return
+ *		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),			\
@@ -5377,6 +5448,13 @@ union bpf_attr {
 	FN(kptr_xchg),			\
 	FN(map_lookup_percpu_elem),     \
 	FN(skc_to_mptcp_sock),		\
+	FN(dynptr_from_mem),		\
+	FN(ringbuf_reserve_dynptr),	\
+	FN(ringbuf_submit_dynptr),	\
+	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
@@ -6528,6 +6606,11 @@ struct bpf_timer {
 	__u64 :64;
 } __attribute__((aligned(8)));
 
+struct bpf_dynptr {
+	__u64 :64;
+	__u64 :64;
+} __attribute__((aligned(8)));
+
 struct bpf_sysctl {
 	__u32	write;		/* Sysctl is being read (= 0) or written (= 1).
 				 * Allows 1,2,4-byte read, but no write.
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index bad96131a510..225806a02efb 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -1412,6 +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;
@@ -1460,12 +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;
 	}
diff --git a/kernel/bpf/ringbuf.c b/kernel/bpf/ringbuf.c
index 311264ab80c4..ded4faeca192 100644
--- a/kernel/bpf/ringbuf.c
+++ b/kernel/bpf/ringbuf.c
@@ -475,3 +475,81 @@ const struct bpf_func_proto bpf_ringbuf_query_proto = {
 	.arg1_type	= ARG_CONST_MAP_PTR,
 	.arg2_type	= ARG_ANYTHING,
 };
+
+BPF_CALL_4(bpf_ringbuf_reserve_dynptr, struct bpf_map *, map, u32, size, u64, flags,
+	   struct bpf_dynptr_kern *, ptr)
+{
+	struct bpf_ringbuf_map *rb_map;
+	void *sample;
+	int err;
+
+	if (unlikely(flags)) {
+		bpf_dynptr_set_null(ptr);
+		return -EINVAL;
+	}
+
+	err = bpf_dynptr_check_size(size);
+	if (err) {
+		bpf_dynptr_set_null(ptr);
+		return err;
+	}
+
+	rb_map = container_of(map, struct bpf_ringbuf_map, map);
+
+	sample = __bpf_ringbuf_reserve(rb_map->rb, size);
+	if (!sample) {
+		bpf_dynptr_set_null(ptr);
+		return -EINVAL;
+	}
+
+	bpf_dynptr_init(ptr, sample, BPF_DYNPTR_TYPE_RINGBUF, 0, size);
+
+	return 0;
+}
+
+const struct bpf_func_proto bpf_ringbuf_reserve_dynptr_proto = {
+	.func		= bpf_ringbuf_reserve_dynptr,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_CONST_MAP_PTR,
+	.arg2_type	= ARG_ANYTHING,
+	.arg3_type	= ARG_ANYTHING,
+	.arg4_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | MEM_UNINIT,
+};
+
+BPF_CALL_2(bpf_ringbuf_submit_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags)
+{
+	if (!ptr->data)
+		return 0;
+
+	bpf_ringbuf_commit(ptr->data, flags, false /* discard */);
+
+	bpf_dynptr_set_null(ptr);
+
+	return 0;
+}
+
+const struct bpf_func_proto bpf_ringbuf_submit_dynptr_proto = {
+	.func		= bpf_ringbuf_submit_dynptr,
+	.ret_type	= RET_VOID,
+	.arg1_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE,
+	.arg2_type	= ARG_ANYTHING,
+};
+
+BPF_CALL_2(bpf_ringbuf_discard_dynptr, struct bpf_dynptr_kern *, ptr, u64, flags)
+{
+	if (!ptr->data)
+		return 0;
+
+	bpf_ringbuf_commit(ptr->data, flags, true /* discard */);
+
+	bpf_dynptr_set_null(ptr);
+
+	return 0;
+}
+
+const struct bpf_func_proto bpf_ringbuf_discard_dynptr_proto = {
+	.func		= bpf_ringbuf_discard_dynptr,
+	.ret_type	= RET_VOID,
+	.arg1_type	= ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_RINGBUF | OBJ_RELEASE,
+	.arg2_type	= ARG_ANYTHING,
+};
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 45153cbc2bd6..aedac2ac02b9 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -187,6 +187,9 @@ struct bpf_verifier_stack_elem {
 					  POISON_POINTER_DELTA))
 #define BPF_MAP_PTR(X)		((struct bpf_map *)((X) & ~BPF_MAP_PTR_UNPRIV))
 
+static int acquire_reference_state(struct bpf_verifier_env *env, int insn_idx);
+static int release_reference(struct bpf_verifier_env *env, int ref_obj_id);
+
 static bool bpf_map_ptr_poisoned(const struct bpf_insn_aux_data *aux)
 {
 	return BPF_MAP_PTR(aux->map_ptr_state) == BPF_MAP_PTR_POISON;
@@ -259,6 +262,7 @@ struct bpf_call_arg_meta {
 	u32 ret_btf_id;
 	u32 subprogno;
 	struct bpf_map_value_off_desc *kptr_off_desc;
+	u8 uninit_dynptr_regno;
 };
 
 struct btf *btf_vmlinux;
@@ -581,6 +585,7 @@ static char slot_type_char[] = {
 	[STACK_SPILL]	= 'r',
 	[STACK_MISC]	= 'm',
 	[STACK_ZERO]	= '0',
+	[STACK_DYNPTR]	= 'd',
 };
 
 static void print_liveness(struct bpf_verifier_env *env,
@@ -596,6 +601,25 @@ static void print_liveness(struct bpf_verifier_env *env,
 		verbose(env, "D");
 }
 
+static int get_spi(s32 off)
+{
+	return (-off - 1) / BPF_REG_SIZE;
+}
+
+static bool is_spi_bounds_valid(struct bpf_func_state *state, int spi, int nr_slots)
+{
+	int allocated_slots = state->allocated_stack / BPF_REG_SIZE;
+
+	/* We need to check that slots between [spi - nr_slots + 1, spi] are
+	 * within [0, allocated_stack).
+	 *
+	 * Please note that the spi grows downwards. For example, a dynptr
+	 * takes the size of two stack slots; the first slot will be at
+	 * spi and the second slot will be at spi - 1.
+	 */
+	return spi - nr_slots + 1 >= 0 && spi < allocated_slots;
+}
+
 static struct bpf_func_state *func(struct bpf_verifier_env *env,
 				   const struct bpf_reg_state *reg)
 {
@@ -647,6 +671,132 @@ static void mark_verifier_state_scratched(struct bpf_verifier_env *env)
 	env->scratched_stack_slots = ~0ULL;
 }
 
+static enum bpf_dynptr_type arg_to_dynptr_type(enum bpf_arg_type arg_type)
+{
+	switch (arg_type & DYNPTR_TYPE_FLAG_MASK) {
+	case DYNPTR_TYPE_LOCAL:
+		return BPF_DYNPTR_TYPE_LOCAL;
+	case DYNPTR_TYPE_RINGBUF:
+		return BPF_DYNPTR_TYPE_RINGBUF;
+	default:
+		return BPF_DYNPTR_TYPE_INVALID;
+	}
+}
+
+static bool dynptr_type_refcounted(enum bpf_dynptr_type type)
+{
+	return type == BPF_DYNPTR_TYPE_RINGBUF;
+}
+
+static int mark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+				   enum bpf_arg_type arg_type, int insn_idx)
+{
+	struct bpf_func_state *state = func(env, reg);
+	enum bpf_dynptr_type type;
+	int spi, i, id;
+
+	spi = get_spi(reg->off);
+
+	if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS))
+		return -EINVAL;
+
+	for (i = 0; i < BPF_REG_SIZE; i++) {
+		state->stack[spi].slot_type[i] = STACK_DYNPTR;
+		state->stack[spi - 1].slot_type[i] = STACK_DYNPTR;
+	}
+
+	type = arg_to_dynptr_type(arg_type);
+	if (type == BPF_DYNPTR_TYPE_INVALID)
+		return -EINVAL;
+
+	state->stack[spi].spilled_ptr.dynptr.first_slot = true;
+	state->stack[spi].spilled_ptr.dynptr.type = type;
+	state->stack[spi - 1].spilled_ptr.dynptr.type = type;
+
+	if (dynptr_type_refcounted(type)) {
+		/* The id is used to track proper releasing */
+		id = acquire_reference_state(env, insn_idx);
+		if (id < 0)
+			return id;
+
+		state->stack[spi].spilled_ptr.id = id;
+		state->stack[spi - 1].spilled_ptr.id = id;
+	}
+
+	return 0;
+}
+
+static int unmark_stack_slots_dynptr(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
+{
+	struct bpf_func_state *state = func(env, reg);
+	int spi, i;
+
+	spi = get_spi(reg->off);
+
+	if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS))
+		return -EINVAL;
+
+	for (i = 0; i < BPF_REG_SIZE; i++) {
+		state->stack[spi].slot_type[i] = STACK_INVALID;
+		state->stack[spi - 1].slot_type[i] = STACK_INVALID;
+	}
+
+	/* Invalidate any slices associated with this dynptr */
+	if (dynptr_type_refcounted(state->stack[spi].spilled_ptr.dynptr.type)) {
+		release_reference(env, state->stack[spi].spilled_ptr.id);
+		state->stack[spi].spilled_ptr.id = 0;
+		state->stack[spi - 1].spilled_ptr.id = 0;
+	}
+
+	state->stack[spi].spilled_ptr.dynptr.first_slot = false;
+	state->stack[spi].spilled_ptr.dynptr.type = 0;
+	state->stack[spi - 1].spilled_ptr.dynptr.type = 0;
+
+	return 0;
+}
+
+static bool is_dynptr_reg_valid_uninit(struct bpf_verifier_env *env, struct bpf_reg_state *reg)
+{
+	struct bpf_func_state *state = func(env, reg);
+	int spi = get_spi(reg->off);
+	int i;
+
+	if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS))
+		return true;
+
+	for (i = 0; i < BPF_REG_SIZE; i++) {
+		if (state->stack[spi].slot_type[i] == STACK_DYNPTR ||
+		    state->stack[spi - 1].slot_type[i] == STACK_DYNPTR)
+			return false;
+	}
+
+	return true;
+}
+
+static bool is_dynptr_reg_valid_init(struct bpf_verifier_env *env, struct bpf_reg_state *reg,
+				     enum bpf_arg_type arg_type)
+{
+	struct bpf_func_state *state = func(env, reg);
+	int spi = get_spi(reg->off);
+	int i;
+
+	if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) ||
+	    !state->stack[spi].spilled_ptr.dynptr.first_slot)
+		return false;
+
+	for (i = 0; i < BPF_REG_SIZE; i++) {
+		if (state->stack[spi].slot_type[i] != STACK_DYNPTR ||
+		    state->stack[spi - 1].slot_type[i] != STACK_DYNPTR)
+			return false;
+	}
+
+	/* ARG_PTR_TO_DYNPTR takes any type of dynptr */
+	if (arg_type == ARG_PTR_TO_DYNPTR)
+		return true;
+
+	return state->stack[spi].spilled_ptr.dynptr.type == arg_to_dynptr_type(arg_type);
+}
+
 /* The reg state of a pointer or a bounded scalar was saved when
  * it was spilled to the stack.
  */
@@ -5400,6 +5550,11 @@ static bool arg_type_is_release(enum bpf_arg_type type)
 	return type & OBJ_RELEASE;
 }
 
+static bool arg_type_is_dynptr(enum bpf_arg_type type)
+{
+	return base_type(type) == ARG_PTR_TO_DYNPTR;
+}
+
 static int int_ptr_type_to_size(enum bpf_arg_type type)
 {
 	if (type == ARG_PTR_TO_INT)
@@ -5539,6 +5694,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_CONST_STR]		= &const_str_ptr_types,
 	[ARG_PTR_TO_TIMER]		= &timer_types,
 	[ARG_PTR_TO_KPTR]		= &kptr_types,
+	[ARG_PTR_TO_DYNPTR]		= &stack_ptr_types,
 };
 
 static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
@@ -5628,8 +5784,13 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 	bool fixed_off_ok = false;
 
 	switch ((u32)type) {
-	case SCALAR_VALUE:
 	/* Pointer types where reg offset is explicitly allowed: */
+	case PTR_TO_STACK:
+		if (arg_type_is_dynptr(arg_type) && reg->off % BPF_REG_SIZE) {
+			verbose(env, "cannot pass in dynptr at an offset\n");
+			return -EINVAL;
+		}
+		fallthrough;
 	case PTR_TO_PACKET:
 	case PTR_TO_PACKET_META:
 	case PTR_TO_MAP_KEY:
@@ -5639,7 +5800,7 @@ int check_func_arg_reg_off(struct bpf_verifier_env *env,
 	case PTR_TO_MEM | MEM_ALLOC:
 	case PTR_TO_BUF:
 	case PTR_TO_BUF | MEM_RDONLY:
-	case PTR_TO_STACK:
+	case SCALAR_VALUE:
 		/* Some of the argument types nevertheless require a
 		 * zero register offset.
 		 */
@@ -5671,6 +5832,14 @@ 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)
@@ -5725,7 +5894,16 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 
 skip_type_check:
 	if (arg_type_is_release(arg_type)) {
-		if (!reg->ref_obj_id && !register_is_null(reg)) {
+		if (arg_type_is_dynptr(arg_type)) {
+			struct bpf_func_state *state = func(env, reg);
+			int spi = get_spi(reg->off);
+
+			if (!is_spi_bounds_valid(state, spi, BPF_DYNPTR_NR_SLOTS) ||
+			    !state->stack[spi].spilled_ptr.id) {
+				verbose(env, "arg %d is an unacquired reference\n", regno);
+				return -EINVAL;
+			}
+		} else if (!reg->ref_obj_id && !register_is_null(reg)) {
 			verbose(env, "R%d must be referenced when passed to release function\n",
 				regno);
 			return -EINVAL;
@@ -5837,6 +6015,40 @@ skip_type_check:
 		bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO);
 
 		err = check_mem_size_reg(env, reg, regno, zero_size_allowed, meta);
+	} else if (arg_type_is_dynptr(arg_type)) {
+		if (arg_type & MEM_UNINIT) {
+			if (!is_dynptr_reg_valid_uninit(env, reg)) {
+				verbose(env, "Dynptr has to be an uninitialized dynptr\n");
+				return -EINVAL;
+			}
+
+			/* We only support one dynptr being uninitialized at the moment,
+			 * which is sufficient for the helper functions we have right now.
+			 */
+			if (meta->uninit_dynptr_regno) {
+				verbose(env, "verifier internal error: multiple uninitialized dynptr args\n");
+				return -EFAULT;
+			}
+
+			meta->uninit_dynptr_regno = regno;
+		} else if (!is_dynptr_reg_valid_init(env, reg, arg_type)) {
+			const char *err_extra = "";
+
+			switch (arg_type & DYNPTR_TYPE_FLAG_MASK) {
+			case DYNPTR_TYPE_LOCAL:
+				err_extra = "local ";
+				break;
+			case DYNPTR_TYPE_RINGBUF:
+				err_extra = "ringbuf ";
+				break;
+			default:
+				break;
+			}
+
+			verbose(env, "Expected an initialized %sdynptr as arg #%d\n",
+				err_extra, arg + 1);
+			return -EINVAL;
+		}
 	} else if (arg_type_is_alloc_size(arg_type)) {
 		if (!tnum_is_const(reg->var_off)) {
 			verbose(env, "R%d is not a known constant'\n",
@@ -5958,7 +6170,10 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_MAP_TYPE_RINGBUF:
 		if (func_id != BPF_FUNC_ringbuf_output &&
 		    func_id != BPF_FUNC_ringbuf_reserve &&
-		    func_id != BPF_FUNC_ringbuf_query)
+		    func_id != BPF_FUNC_ringbuf_query &&
+		    func_id != BPF_FUNC_ringbuf_reserve_dynptr &&
+		    func_id != BPF_FUNC_ringbuf_submit_dynptr &&
+		    func_id != BPF_FUNC_ringbuf_discard_dynptr)
 			goto error;
 		break;
 	case BPF_MAP_TYPE_STACK_TRACE:
@@ -6074,6 +6289,9 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env,
 	case BPF_FUNC_ringbuf_output:
 	case BPF_FUNC_ringbuf_reserve:
 	case BPF_FUNC_ringbuf_query:
+	case BPF_FUNC_ringbuf_reserve_dynptr:
+	case BPF_FUNC_ringbuf_submit_dynptr:
+	case BPF_FUNC_ringbuf_discard_dynptr:
 		if (map->map_type != BPF_MAP_TYPE_RINGBUF)
 			goto error;
 		break;
@@ -6970,9 +7188,27 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 
 	regs = cur_regs(env);
 
+	if (meta.uninit_dynptr_regno) {
+		/* we write BPF_DW bits (8 bytes) at a time */
+		for (i = 0; i < BPF_DYNPTR_SIZE; i += 8) {
+			err = check_mem_access(env, insn_idx, meta.uninit_dynptr_regno,
+					       i, BPF_DW, BPF_WRITE, -1, false);
+			if (err)
+				return err;
+		}
+
+		err = mark_stack_slots_dynptr(env, &regs[meta.uninit_dynptr_regno],
+					      fn->arg_type[meta.uninit_dynptr_regno - BPF_REG_1],
+					      insn_idx);
+		if (err)
+			return err;
+	}
+
 	if (meta.release_regno) {
 		err = -EINVAL;
-		if (meta.ref_obj_id)
+		if (arg_type_is_dynptr(fn->arg_type[meta.release_regno - BPF_REG_1]))
+			err = unmark_stack_slots_dynptr(env, &regs[meta.release_regno]);
+		else if (meta.ref_obj_id)
 			err = release_reference(env, meta.ref_obj_id);
 		/* meta.ref_obj_id can only be 0 if register that is meant to be
 		 * released is NULL, which must be > R0.
@@ -7022,6 +7258,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 		err = __check_func_call(env, insn, insn_idx_p, meta.subprogno,
 					set_loop_callback_state);
 		break;
+	case BPF_FUNC_dynptr_from_mem:
+		if (regs[BPF_REG_1].type != PTR_TO_MAP_VALUE) {
+			verbose(env, "Unsupported reg type %s for bpf_dynptr_from_mem data\n",
+				reg_type_str(env, regs[BPF_REG_1].type));
+			return -EACCES;
+		}
 	}
 
 	if (err)
@@ -7150,6 +7392,21 @@ 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/scripts/bpf_doc.py b/scripts/bpf_doc.py
index d5452f7eb996..855b937e7585 100755
--- a/scripts/bpf_doc.py
+++ b/scripts/bpf_doc.py
@@ -634,6 +634,7 @@ class PrinterHelpers(Printer):
             'struct file',
             'struct bpf_timer',
             'struct mptcp_sock',
+            'struct bpf_dynptr',
     ]
     known_types = {
             '...',
@@ -684,6 +685,7 @@ class PrinterHelpers(Printer):
             'struct file',
             'struct bpf_timer',
             'struct mptcp_sock',
+            'struct bpf_dynptr',
     }
     mapped_types = {
             'u8': '__u8',
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 56688bee20d9..f4009dbdf62d 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -5178,6 +5178,77 @@ union bpf_attr {
  *		Dynamically cast a *sk* pointer to a *mptcp_sock* pointer.
  *	Return
  *		*sk* if casting is valid, or **NULL** otherwise.
+ *
+ * long bpf_dynptr_from_mem(void *data, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ *	Description
+ *		Get a dynptr to local memory *data*.
+ *
+ *		*data* must be a ptr to a map value.
+ *		The maximum *size* supported is DYNPTR_MAX_SIZE.
+ *		*flags* is currently unused.
+ *	Return
+ *		0 on success, -E2BIG if the size exceeds DYNPTR_MAX_SIZE,
+ *		-EINVAL if flags is not 0.
+ *
+ * long bpf_ringbuf_reserve_dynptr(void *ringbuf, u32 size, u64 flags, struct bpf_dynptr *ptr)
+ *	Description
+ *		Reserve *size* bytes of payload in a ring buffer *ringbuf*
+ *		through the dynptr interface. *flags* must be 0.
+ *
+ *		Please note that a corresponding bpf_ringbuf_submit_dynptr or
+ *		bpf_ringbuf_discard_dynptr must be called on *ptr*, even if the
+ *		reservation fails. This is enforced by the verifier.
+ *	Return
+ *		0 on success, or a negative error in case of failure.
+ *
+ * void bpf_ringbuf_submit_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ *	Description
+ *		Submit reserved ring buffer sample, pointed to by *data*,
+ *		through the dynptr interface. This is a no-op if the dynptr is
+ *		invalid/null.
+ *
+ *		For more information on *flags*, please see
+ *		'bpf_ringbuf_submit'.
+ *	Return
+ *		Nothing. Always succeeds.
+ *
+ * void bpf_ringbuf_discard_dynptr(struct bpf_dynptr *ptr, u64 flags)
+ *	Description
+ *		Discard reserved ring buffer sample through the dynptr
+ *		interface. This is a no-op if the dynptr is invalid/null.
+ *
+ *		For more information on *flags*, please see
+ *		'bpf_ringbuf_discard'.
+ *	Return
+ *		Nothing. Always succeeds.
+ *
+ * long bpf_dynptr_read(void *dst, u32 len, struct bpf_dynptr *src, u32 offset)
+ *	Description
+ *		Read *len* bytes from *src* into *dst*, starting from *offset*
+ *		into *src*.
+ *	Return
+ *		0 on success, -E2BIG if *offset* + *len* exceeds the length
+ *		of *src*'s data, -EINVAL if *src* is an invalid dynptr.
+ *
+ * long bpf_dynptr_write(struct bpf_dynptr *dst,