bpf: add bpf_snprintf_btf helper

A helper is added to support tracing kernel type information in BPF
using the BPF Type Format (BTF).  Its signature is

long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr,
		      u32 btf_ptr_size, u64 flags);

struct btf_ptr * specifies

- a pointer to the data to be traced;
- the BTF id of the type of data pointed to; or
- a string representation of the type of data pointed to
- a flags field is provided for future use; these flags
  are not to be confused with the BTF_F_* flags
  below that control how the btf_ptr is displayed; the
  flags member of the struct btf_ptr may be used to
  disambiguate types in kernel versus module BTF, etc;
  the main distinction is the flags relate to the type
  and information needed in identifying it; not how it
  is displayed.

For example a BPF program with a struct sk_buff *skb
could do the following:

	static const char skb_type[] = "struct sk_buff";
	static struct btf_ptr b = { };

	b.ptr = skb;
	b.type = skb_type;
	bpf_snprintf_btf(str, sizeof(str), &b, sizeof(b), 0, 0);

Default output looks like this:

(struct sk_buff){
 .transport_header = (__u16)65535,
 .mac_header = (__u16)65535,
 .end = (sk_buff_data_t)192,
 .head = (unsigned char *)0x000000007524fd8b,
 .data = (unsigned char *)0x000000007524fd8b,
 .truesize = (unsigned int)768,
 .users = (refcount_t){
  .refs = (atomic_t){
   .counter = (int)1,
  },
 },
}

Flags modifying display are as follows:

- BTF_F_COMPACT:	no formatting around type information
- BTF_F_NONAME:		no struct/union member names/types
- BTF_F_PTR_RAW:	show raw (unobfuscated) pointer values;
			equivalent to %px.
- BTF_F_ZERO:		show zero-valued struct/union members;
			they are not displayed by default

Signed-off-by: Alan Maguire <[email protected]>

Author: alan-maguire

include/linux/bpf.h

@@ -1795,6 +1795,7 @@ extern const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto;
 extern const struct bpf_func_proto bpf_skc_to_udp6_sock_proto;
 extern const struct bpf_func_proto bpf_copy_from_user_proto;
+extern const struct bpf_func_proto bpf_snprintf_btf_proto;
 
 const struct bpf_func_proto *bpf_tracing_func_proto(
 	enum bpf_func_id func_id, const struct bpf_prog *prog);

include/linux/btf.h

@@ -6,6 +6,7 @@
 
 #include <linux/types.h>
 #include <uapi/linux/btf.h>
+#include <uapi/linux/bpf.h>
 
 #define BTF_TYPE_EMIT(type) ((void)(type *)0)
 
@@ -59,10 +60,10 @@ const struct btf_type *btf_type_id_size(const struct btf *btf,
  *	- BTF_SHOW_UNSAFE: skip use of bpf_probe_read() to safely read
  *	  data before displaying it.
  */
-#define BTF_SHOW_COMPACT	(1ULL << 0)
-#define BTF_SHOW_NONAME		(1ULL << 1)
-#define BTF_SHOW_PTR_RAW	(1ULL << 2)
-#define BTF_SHOW_ZERO		(1ULL << 3)
+#define BTF_SHOW_COMPACT	BTF_F_COMPACT
+#define BTF_SHOW_NONAME		BTF_F_NONAME
+#define BTF_SHOW_PTR_RAW	BTF_F_PTR_RAW
+#define BTF_SHOW_ZERO		BTF_F_ZERO
 #define BTF_SHOW_UNSAFE		(1ULL << 4)
 
 void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj,

include/uapi/linux/bpf.h

@@ -3586,6 +3586,41 @@ union bpf_attr {
  * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to store a string representation of *ptr*->ptr in *str*,
+ *		using *ptr*->type name or *ptr*->type_id.  These values should
+ *		specify the type *ptr*->ptr points to. Traversing that
+ *		data structure using BTF, the type information and values are
+ *		stored in the first *str_size* - 1 bytes of *str*.  Safe copy of
+ *		the pointer data is carried out to avoid kernel crashes during
+ *		operation.  Smaller types can use string space on the stack;
+ *		larger programs can use map data to store the string
+ *		representation.
+ *
+ *		The string can be subsequently shared with userspace via
+ *		bpf_perf_event_output() or ring buffer interfaces.
+ *		bpf_trace_printk() is to be avoided as it places too small
+ *		a limit on string size to be useful.
+ *
+ *		*flags* is a combination of
+ *
+ *		**BTF_F_COMPACT**
+ *			no formatting around type information
+ *		**BTF_F_NONAME**
+ *			no struct/union member names/types
+ *		**BTF_F_PTR_RAW**
+ *			show raw (unobfuscated) pointer values;
+ *			equivalent to printk specifier %px.
+ *		**BTF_F_ZERO**
+ *			show zero-valued struct/union members; they
+ *			are not displayed by default
+ *
+ *	Return
+ *		The number of bytes that were written (or would have been
+ *		written if output had to be truncated due to string size),
+ *		or a negative error in cases of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3737,6 +3772,7 @@ union bpf_attr {
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
 	FN(copy_from_user),		\
+	FN(snprintf_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4845,4 +4881,36 @@ struct bpf_sk_lookup {
 	__u32 local_port;	/* Host byte order */
 };
 
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * additional type string/BTF type id are used to render the pointer
+ * data as the appropriate type via the bpf_snprintf_btf() helper
+ * above.  A flags field - potentially to specify additional details
+ * about the BTF pointer (rather than its mode of display) - is
+ * present for future use.  Display flags - BTF_F_* - are
+ * passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+	void *ptr;
+	const char *type;
+	__u32 type_id;
+	__u32 flags;		/* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ *     - BTF_F_COMPACT: no formatting around type information
+ *     - BTF_F_NONAME: no struct/union member names/types
+ *     - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ *       equivalent to %px.
+ *     - BTF_F_ZERO: show zero-valued struct/union members; they
+ *       are not displayed by default
+ */
+enum {
+	BTF_F_COMPACT	=	(1ULL << 0),
+	BTF_F_NONAME	=	(1ULL << 1),
+	BTF_F_PTR_RAW	=	(1ULL << 2),
+	BTF_F_ZERO	=	(1ULL << 3),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */

kernel/bpf/core.c

@@ -2216,6 +2216,7 @@ const struct bpf_func_proto bpf_get_current_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_current_ancestor_cgroup_id_proto __weak;
 const struct bpf_func_proto bpf_get_local_storage_proto __weak;
 const struct bpf_func_proto bpf_get_ns_current_pid_tgid_proto __weak;
+const struct bpf_func_proto bpf_snprintf_btf_proto __weak;
 
 const struct bpf_func_proto * __weak bpf_get_trace_printk_proto(void)
 {

kernel/bpf/helpers.c

@@ -683,6 +683,10 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		if (!perfmon_capable())
 			return NULL;
 		return bpf_get_trace_printk_proto();
+	case BPF_FUNC_snprintf_btf:
+		if (!perfmon_capable())
+			return NULL;
+		return &bpf_snprintf_btf_proto;
 	case BPF_FUNC_jiffies64:
 		return &bpf_jiffies64_proto;
 	default:

kernel/trace/bpf_trace.c

@@ -7,6 +7,7 @@
 #include <linux/slab.h>
 #include <linux/bpf.h>
 #include <linux/bpf_perf_event.h>
+#include <linux/btf.h>
 #include <linux/filter.h>
 #include <linux/uaccess.h>
 #include <linux/ctype.h>
@@ -16,6 +17,9 @@
 #include <linux/error-injection.h>
 #include <linux/btf_ids.h>
 
+#include <uapi/linux/bpf.h>
+#include <uapi/linux/btf.h>
+
 #include <asm/tlb.h>
 
 #include "trace_probe.h"
@@ -1147,6 +1151,101 @@ static const struct bpf_func_proto bpf_d_path_proto = {
 	.allowed	= bpf_d_path_allowed,
 };
 
+#define BTF_F_ALL	(BTF_F_COMPACT  | BTF_F_NONAME | \
+			 BTF_F_PTR_RAW | BTF_F_ZERO)
+
+static int bpf_btf_printf_prepare(struct btf_ptr *ptr, u32 btf_ptr_size,
+				  u64 flags, const struct btf **btf,
+				  s32 *btf_id)
+{
+	u8 btf_kind = BTF_KIND_TYPEDEF;
+	char type_name[KSYM_NAME_LEN];
+	const struct btf_type *t;
+	const char *btf_type;
+	int ret;
+
+	if (unlikely(flags & ~(BTF_F_ALL)))
+		return -EINVAL;
+
+	if (btf_ptr_size != sizeof(struct btf_ptr))
+		return -EINVAL;
+
+	*btf = bpf_get_btf_vmlinux();
+
+	if (IS_ERR_OR_NULL(*btf))
+		return PTR_ERR(*btf);
+
+	if (ptr->type != NULL) {
+		ret = copy_from_kernel_nofault(type_name, ptr->type,
+					       sizeof(type_name));
+		if (ret)
+			return ret;
+
+		btf_type = type_name;
+
+		if (strncmp(btf_type, "struct ", strlen("struct ")) == 0) {
+			btf_kind = BTF_KIND_STRUCT;
+			btf_type += strlen("struct ");
+		} else if (strncmp(btf_type, "union ", strlen("union ")) == 0) {
+			btf_kind = BTF_KIND_UNION;
+			btf_type += strlen("union ");
+		} else if (strncmp(btf_type, "enum ", strlen("enum ")) == 0) {
+			btf_kind = BTF_KIND_ENUM;
+			btf_type += strlen("enum ");
+		}
+
+		if (strlen(btf_type) == 0)
+			return -EINVAL;
+
+		/* Assume type specified is a typedef as there's not much
+		 * benefit in specifying int types other than wasting time
+		 * on BTF lookups; we optimize for the most useful path.
+		 *
+		 * Fall back to BTF_KIND_INT if this fails.
+		 */
+		*btf_id = btf_find_by_name_kind(*btf, btf_type, btf_kind);
+		if (*btf_id < 0)
+			*btf_id = btf_find_by_name_kind(*btf, btf_type,
+							BTF_KIND_INT);
+	} else if (ptr->type_id > 0)
+		*btf_id = ptr->type_id;
+	else
+		return -EINVAL;
+
+	if (*btf_id > 0)
+		t = btf_type_by_id(*btf, *btf_id);
+	if (*btf_id <= 0 || !t)
+		return -ENOENT;
+
+	return 0;
+}
+
+BPF_CALL_5(bpf_snprintf_btf, char *, str, u32, str_size, struct btf_ptr *, ptr,
+	   u32, btf_ptr_size, u64, flags)
+{
+	const struct btf *btf;
+	s32 btf_id;
+	int ret;
+
+	ret = bpf_btf_printf_prepare(ptr, btf_ptr_size, flags, &btf, &btf_id);
+	if (ret)
+		return ret;
+
+	return btf_type_snprintf_show(btf, btf_id, ptr->ptr, str, str_size,
+				      flags);
+}
+
+const struct bpf_func_proto bpf_snprintf_btf_proto = {
+	.func		= bpf_snprintf_btf,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM,
+	.arg2_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_PTR_TO_MEM,
+	.arg4_type	= ARG_CONST_SIZE,
+	.arg5_type	= ARG_ANYTHING,
+};
+
 const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1233,6 +1332,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_get_task_stack_proto;
 	case BPF_FUNC_copy_from_user:
 		return prog->aux->sleepable ? &bpf_copy_from_user_proto : NULL;
+	case BPF_FUNC_snprintf_btf:
+		return &bpf_snprintf_btf_proto;
 	default:
 		return NULL;
 	}

scripts/bpf_helpers_doc.py

@@ -433,6 +433,7 @@ class PrinterHelpers(Printer):
             'struct sk_msg_md',
             'struct xdp_md',
             'struct path',
+            'struct btf_ptr',
     ]
     known_types = {
             '...',
@@ -474,6 +475,7 @@ class PrinterHelpers(Printer):
             'struct udp6_sock',
             'struct task_struct',
             'struct path',
+            'struct btf_ptr',
     }
     mapped_types = {
             'u8': '__u8',

tools/include/uapi/linux/bpf.h

@@ -3586,6 +3586,41 @@ union bpf_attr {
  * 		the data in *dst*. This is a wrapper of **copy_from_user**\ ().
  * 	Return
  * 		0 on success, or a negative error in case of failure.
+ *
+ * long bpf_snprintf_btf(char *str, u32 str_size, struct btf_ptr *ptr, u32 btf_ptr_size, u64 flags)
+ *	Description
+ *		Use BTF to store a string representation of *ptr*->ptr in *str*,
+ *		using *ptr*->type name or *ptr*->type_id.  These values should
+ *		specify the type *ptr*->ptr points to. Traversing that
+ *		data structure using BTF, the type information and values are
+ *		stored in the first *str_size* - 1 bytes of *str*.  Safe copy of
+ *		the pointer data is carried out to avoid kernel crashes during
+ *		operation.  Smaller types can use string space on the stack;
+ *		larger programs can use map data to store the string
+ *		representation.
+ *
+ *		The string can be subsequently shared with userspace via
+ *		bpf_perf_event_output() or ring buffer interfaces.
+ *		bpf_trace_printk() is to be avoided as it places too small
+ *		a limit on string size to be useful.
+ *
+ *		*flags* is a combination of
+ *
+ *		**BTF_F_COMPACT**
+ *			no formatting around type information
+ *		**BTF_F_NONAME**
+ *			no struct/union member names/types
+ *		**BTF_F_PTR_RAW**
+ *			show raw (unobfuscated) pointer values;
+ *			equivalent to printk specifier %px.
+ *		**BTF_F_ZERO**
+ *			show zero-valued struct/union members; they
+ *			are not displayed by default
+ *
+ *	Return
+ *		The number of bytes that were written (or would have been
+ *		written if output had to be truncated due to string size),
+ *		or a negative error in cases of failure.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3737,6 +3772,7 @@ union bpf_attr {
 	FN(inode_storage_delete),	\
 	FN(d_path),			\
 	FN(copy_from_user),		\
+	FN(snprintf_btf),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4845,4 +4881,36 @@ struct bpf_sk_lookup {
 	__u32 local_port;	/* Host byte order */
 };
 
+/*
+ * struct btf_ptr is used for typed pointer representation; the
+ * additional type string/BTF type id are used to render the pointer
+ * data as the appropriate type via the bpf_snprintf_btf() helper
+ * above.  A flags field - potentially to specify additional details
+ * about the BTF pointer (rather than its mode of display) - is
+ * present for future use.  Display flags - BTF_F_* - are
+ * passed to bpf_snprintf_btf separately.
+ */
+struct btf_ptr {
+	void *ptr;
+	const char *type;
+	__u32 type_id;
+	__u32 flags;		/* BTF ptr flags; unused at present. */
+};
+
+/*
+ * Flags to control bpf_snprintf_btf() behaviour.
+ *     - BTF_F_COMPACT: no formatting around type information
+ *     - BTF_F_NONAME: no struct/union member names/types
+ *     - BTF_F_PTR_RAW: show raw (unobfuscated) pointer values;
+ *       equivalent to %px.
+ *     - BTF_F_ZERO: show zero-valued struct/union members; they
+ *       are not displayed by default
+ */
+enum {
+	BTF_F_COMPACT	=	(1ULL << 0),
+	BTF_F_NONAME	=	(1ULL << 1),
+	BTF_F_PTR_RAW	=	(1ULL << 2),
+	BTF_F_ZERO	=	(1ULL << 3),
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */