Merge branch 'Add a snprintf eBPF helper'

Florent Revest says:

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

We have a usecase where we want to audit symbol names (if available) in
callback registration hooks. (ex: fentry/nf_register_net_hook)

A few months back, I proposed a bpf_kallsyms_lookup series but it was
decided in the reviews that a more generic helper, bpf_snprintf, would
be more useful.

This series implements the helper according to the feedback received in
https://lore.kernel.org/bpf/20201126165748.1748417-1-revest@google.com/T/#u

- A new arg type guarantees the NULL-termination of string arguments and
  lets us pass format strings in only one arg
- A new helper is implemented using that guarantee. Because the format
  string is known at verification time, the format string validation is
  done by the verifier
- To implement a series of tests for bpf_snprintf, the logic for
  marshalling variadic args in a fixed-size array is reworked as per:
https://lore.kernel.org/bpf/20210310015455.1095207-1-revest@chromium.org/T/#u

---
Changes in v5:
- Fixed the bpf_printf_buf_used counter logic in try_get_fmt_tmp_buf
- Added a couple of extra incorrect specifiers tests
- Call test_snprintf_single__destroy unconditionally
- Fixed a C++-style comment

---
Changes in v4:
- Moved bpf_snprintf, bpf_printf_prepare and bpf_printf_cleanup to
  kernel/bpf/helpers.c so that they get built without CONFIG_BPF_EVENTS
- Added negative test cases (various invalid format strings)
- Renamed put_fmt_tmp_buf() as bpf_printf_cleanup()
- Fixed a mistake that caused temporary buffers to be unconditionally
  freed in bpf_printf_prepare
- Fixed a mistake that caused missing 0 character to be ignored
- Fixed a warning about integer to pointer conversion
- Misc cleanups

---
Changes in v3:
- Simplified temporary buffer acquisition with try_get_fmt_tmp_buf()
- Made zero-termination check more consistent
- Allowed NULL output_buffer
- Simplified the BPF_CAST_FMT_ARG macro
- Three new test cases: number padding, simple string with no arg and
  string length extraction only with a NULL output buffer
- Clarified helper's description for edge cases (eg: str_size == 0)
- Lots of cosmetic changes

---
Changes in v2:
- Extracted the format validation/argument sanitization in a generic way
  for all printf-like helpers.
- bpf_snprintf's str_size can now be 0
- bpf_snprintf is now exposed to all BPF program types
- We now preempt_disable when using a per-cpu temporary buffer
- Addressed a few cosmetic changes
====================
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

include/linux/bpf.h

@@ -309,6 +309,7 @@ enum bpf_arg_type {
 	ARG_PTR_TO_PERCPU_BTF_ID,	/* pointer to in-kernel percpu type */
 	ARG_PTR_TO_FUNC,	/* pointer to a bpf program function */
 	ARG_PTR_TO_STACK_OR_NULL,	/* pointer to stack or NULL */
+	ARG_PTR_TO_CONST_STR,	/* pointer to a null terminated read-only string */
 	__BPF_ARG_TYPE_MAX,
 };
 
@@ -1952,6 +1953,7 @@ 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;
+extern const struct bpf_func_proto bpf_snprintf_proto;
 extern const struct bpf_func_proto bpf_per_cpu_ptr_proto;
 extern const struct bpf_func_proto bpf_this_cpu_ptr_proto;
 extern const struct bpf_func_proto bpf_ktime_get_coarse_ns_proto;
@@ -2077,4 +2079,24 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
 struct btf_id_set;
 bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
 
+enum bpf_printf_mod_type {
+	BPF_PRINTF_INT,
+	BPF_PRINTF_LONG,
+	BPF_PRINTF_LONG_LONG,
+};
+
+/* Workaround for getting va_list handling working with different argument type
+ * combinations generically for 32 and 64 bit archs.
+ */
+#define BPF_CAST_FMT_ARG(arg_nb, args, mod)				\
+	(mod[arg_nb] == BPF_PRINTF_LONG_LONG ||				\
+	 (mod[arg_nb] == BPF_PRINTF_LONG && __BITS_PER_LONG == 64)	\
+	  ? (u64)args[arg_nb]						\
+	  : (u32)args[arg_nb])
+
+int bpf_printf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
+		       u64 *final_args, enum bpf_printf_mod_type *mod,
+		       u32 num_args);
+void bpf_printf_cleanup(void);
+
 #endif /* _LINUX_BPF_H */

include/uapi/linux/bpf.h

@@ -4708,6 +4708,33 @@ union bpf_attr {
  *	Return
  *		The number of traversed map elements for success, **-EINVAL** for
  *		invalid **flags**.
+ *
+ * long bpf_snprintf(char *str, u32 str_size, const char *fmt, u64 *data, u32 data_len)
+ *	Description
+ *		Outputs a string into the **str** buffer of size **str_size**
+ *		based on a format string stored in a read-only map pointed by
+ *		**fmt**.
+ *
+ *		Each format specifier in **fmt** corresponds to one u64 element
+ *		in the **data** array. For strings and pointers where pointees
+ *		are accessed, only the pointer values are stored in the *data*
+ *		array. The *data_len* is the size of *data* in bytes.
+ *
+ *		Formats **%s** and **%p{i,I}{4,6}** require to read kernel
+ *		memory. Reading kernel memory may fail due to either invalid
+ *		address or valid address but requiring a major memory fault. If
+ *		reading kernel memory fails, the string for **%s** will be an
+ *		empty string, and the ip address for **%p{i,I}{4,6}** will be 0.
+ *		Not returning error to bpf program is consistent with what
+ *		**bpf_trace_printk**\ () does for now.
+ *
+ *	Return
+ *		The strictly positive length of the formatted string, including
+ *		the trailing zero character. If the return value is greater than
+ *		**str_size**, **str** contains a truncated string, guaranteed to
+ *		be zero-terminated except when **str_size** is 0.
+ *
+ *		Or **-EBUSY** if the per-CPU memory copy buffer is busy.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -4875,6 +4902,7 @@ union bpf_attr {
 	FN(sock_from_file),		\
 	FN(check_mtu),			\
 	FN(for_each_map_elem),		\
+	FN(snprintf),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

kernel/bpf/helpers.c

@@ -669,6 +669,310 @@ const struct bpf_func_proto bpf_this_cpu_ptr_proto = {
 	.arg1_type	= ARG_PTR_TO_PERCPU_BTF_ID,
 };
 
+static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
+		size_t bufsz)
+{
+	void __user *user_ptr = (__force void __user *)unsafe_ptr;
+
+	buf[0] = 0;
+
+	switch (fmt_ptype) {
+	case 's':
+#ifdef CONFIG_ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
+		if ((unsigned long)unsafe_ptr < TASK_SIZE)
+			return strncpy_from_user_nofault(buf, user_ptr, bufsz);
+		fallthrough;
+#endif
+	case 'k':
+		return strncpy_from_kernel_nofault(buf, unsafe_ptr, bufsz);
+	case 'u':
+		return strncpy_from_user_nofault(buf, user_ptr, bufsz);
+	}
+
+	return -EINVAL;
+}
+
+/* Per-cpu temp buffers which can be used by printf-like helpers for %s or %p
+ */
+#define MAX_PRINTF_BUF_LEN	512
+
+struct bpf_printf_buf {
+	char tmp_buf[MAX_PRINTF_BUF_LEN];
+};
+static DEFINE_PER_CPU(struct bpf_printf_buf, bpf_printf_buf);
+static DEFINE_PER_CPU(int, bpf_printf_buf_used);
+
+static int try_get_fmt_tmp_buf(char **tmp_buf)
+{
+	struct bpf_printf_buf *bufs;
+	int used;
+
+	if (*tmp_buf)
+		return 0;
+
+	preempt_disable();
+	used = this_cpu_inc_return(bpf_printf_buf_used);
+	if (WARN_ON_ONCE(used > 1)) {
+		this_cpu_dec(bpf_printf_buf_used);
+		preempt_enable();
+		return -EBUSY;
+	}
+	bufs = this_cpu_ptr(&bpf_printf_buf);
+	*tmp_buf = bufs->tmp_buf;
+
+	return 0;
+}
+
+void bpf_printf_cleanup(void)
+{
+	if (this_cpu_read(bpf_printf_buf_used)) {
+		this_cpu_dec(bpf_printf_buf_used);
+		preempt_enable();
+	}
+}
+
+/*
+ * bpf_parse_fmt_str - Generic pass on format strings for printf-like helpers
+ *
+ * Returns a negative value if fmt is an invalid format string or 0 otherwise.
+ *
+ * This can be used in two ways:
+ * - Format string verification only: when final_args and mod are NULL
+ * - Arguments preparation: in addition to the above verification, it writes in
+ *   final_args a copy of raw_args where pointers from BPF have been sanitized
+ *   into pointers safe to use by snprintf. This also writes in the mod array
+ *   the size requirement of each argument, usable by BPF_CAST_FMT_ARG for ex.
+ *
+ * In argument preparation mode, if 0 is returned, safe temporary buffers are
+ * allocated and bpf_printf_cleanup should be called to free them after use.
+ */
+int bpf_printf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
+			u64 *final_args, enum bpf_printf_mod_type *mod,
+			u32 num_args)
+{
+	char *unsafe_ptr = NULL, *tmp_buf = NULL, *fmt_end;
+	size_t tmp_buf_len = MAX_PRINTF_BUF_LEN;
+	int err, i, num_spec = 0, copy_size;
+	enum bpf_printf_mod_type cur_mod;
+	u64 cur_arg;
+	char fmt_ptype;
+
+	if (!!final_args != !!mod)
+		return -EINVAL;
+
+	fmt_end = strnchr(fmt, fmt_size, 0);
+	if (!fmt_end)
+		return -EINVAL;
+	fmt_size = fmt_end - fmt;
+
+	for (i = 0; i < fmt_size; i++) {
+		if ((!isprint(fmt[i]) && !isspace(fmt[i])) || !isascii(fmt[i])) {
+			err = -EINVAL;
+			goto cleanup;
+		}
+
+		if (fmt[i] != '%')
+			continue;
+
+		if (fmt[i + 1] == '%') {
+			i++;
+			continue;
+		}
+
+		if (num_spec >= num_args) {
+			err = -EINVAL;
+			goto cleanup;
+		}
+
+		/* The string is zero-terminated so if fmt[i] != 0, we can
+		 * always access fmt[i + 1], in the worst case it will be a 0
+		 */
+		i++;
+
+		/* skip optional "[0 +-][num]" width formatting field */
+		while (fmt[i] == '0' || fmt[i] == '+'  || fmt[i] == '-' ||
+		       fmt[i] == ' ')
+			i++;
+		if (fmt[i] >= '1' && fmt[i] <= '9') {
+			i++;
+			while (fmt[i] >= '0' && fmt[i] <= '9')
+				i++;
+		}
+
+		if (fmt[i] == 'p') {
+			cur_mod = BPF_PRINTF_LONG;
+
+			if ((fmt[i + 1] == 'k' || fmt[i + 1] == 'u') &&
+			    fmt[i + 2] == 's') {
+				fmt_ptype = fmt[i + 1];
+				i += 2;
+				goto fmt_str;
+			}
+
+			if (fmt[i + 1] == 0 || isspace(fmt[i + 1]) ||
+			    ispunct(fmt[i + 1]) || fmt[i + 1] == 'K' ||
+			    fmt[i + 1] == 'x' || fmt[i + 1] == 'B' ||
+			    fmt[i + 1] == 's' || fmt[i + 1] == 'S') {
+				/* just kernel pointers */
+				if (final_args)
+					cur_arg = raw_args[num_spec];
+				goto fmt_next;
+			}
+
+			/* only support "%pI4", "%pi4", "%pI6" and "%pi6". */
+			if ((fmt[i + 1] != 'i' && fmt[i + 1] != 'I') ||
+			    (fmt[i + 2] != '4' && fmt[i + 2] != '6')) {
+				err = -EINVAL;
+				goto cleanup;
+			}
+
+			i += 2;
+			if (!final_args)
+				goto fmt_next;
+
+			if (try_get_fmt_tmp_buf(&tmp_buf)) {
+				err = -EBUSY;
+				goto out;
+			}
+
+			copy_size = (fmt[i + 2] == '4') ? 4 : 16;
+			if (tmp_buf_len < copy_size) {
+				err = -ENOSPC;
+				goto cleanup;
+			}
+
+			unsafe_ptr = (char *)(long)raw_args[num_spec];
+			err = copy_from_kernel_nofault(tmp_buf, unsafe_ptr,
+						       copy_size);
+			if (err < 0)
+				memset(tmp_buf, 0, copy_size);
+			cur_arg = (u64)(long)tmp_buf;
+			tmp_buf += copy_size;
+			tmp_buf_len -= copy_size;
+
+			goto fmt_next;
+		} else if (fmt[i] == 's') {
+			cur_mod = BPF_PRINTF_LONG;
+			fmt_ptype = fmt[i];
+fmt_str:
+			if (fmt[i + 1] != 0 &&
+			    !isspace(fmt[i + 1]) &&
+			    !ispunct(fmt[i + 1])) {
+				err = -EINVAL;
+				goto cleanup;
+			}
+
+			if (!final_args)
+				goto fmt_next;
+
+			if (try_get_fmt_tmp_buf(&tmp_buf)) {
+				err = -EBUSY;
+				goto out;
+			}
+
+			if (!tmp_buf_len) {
+				err = -ENOSPC;
+				goto cleanup;
+			}
+
+			unsafe_ptr = (char *)(long)raw_args[num_spec];
+			err = bpf_trace_copy_string(tmp_buf, unsafe_ptr,
+						    fmt_ptype, tmp_buf_len);
+			if (err < 0) {
+				tmp_buf[0] = '\0';
+				err = 1;
+			}
+
+			cur_arg = (u64)(long)tmp_buf;
+			tmp_buf += err;
+			tmp_buf_len -= err;
+
+			goto fmt_next;
+		}
+
+		cur_mod = BPF_PRINTF_INT;
+
+		if (fmt[i] == 'l') {
+			cur_mod = BPF_PRINTF_LONG;
+			i++;
+		}
+		if (fmt[i] == 'l') {
+			cur_mod = BPF_PRINTF_LONG_LONG;
+			i++;
+		}
+
+		if (fmt[i] != 'i' && fmt[i] != 'd' && fmt[i] != 'u' &&
+		    fmt[i] != 'x' && fmt[i] != 'X') {
+			err = -EINVAL;
+			goto cleanup;
+		}
+
+		if (final_args)
+			cur_arg = raw_args[num_spec];
+fmt_next:
+		if (final_args) {
+			mod[num_spec] = cur_mod;
+			final_args[num_spec] = cur_arg;
+		}
+		num_spec++;
+	}
+
+	err = 0;
+cleanup:
+	if (err)
+		bpf_printf_cleanup();
+out:
+	return err;
+}
+
+#define MAX_SNPRINTF_VARARGS		12
+
+BPF_CALL_5(bpf_snprintf, char *, str, u32, str_size, char *, fmt,
+	   const void *, data, u32, data_len)
+{
+	enum bpf_printf_mod_type mod[MAX_SNPRINTF_VARARGS];
+	u64 args[MAX_SNPRINTF_VARARGS];
+	int err, num_args;
+
+	if (data_len % 8 || data_len > MAX_SNPRINTF_VARARGS * 8 ||
+	    (data_len && !data))
+		return -EINVAL;
+	num_args = data_len / 8;
+
+	/* ARG_PTR_TO_CONST_STR guarantees that fmt is zero-terminated so we
+	 * can safely give an unbounded size.
+	 */
+	err = bpf_printf_prepare(fmt, UINT_MAX, data, args, mod, num_args);
+	if (err < 0)
+		return err;
+
+	/* Maximumly we can have MAX_SNPRINTF_VARARGS parameters, just give
+	 * all of them to snprintf().
+	 */
+	err = snprintf(str, str_size, fmt, BPF_CAST_FMT_ARG(0, args, mod),
+		BPF_CAST_FMT_ARG(1, args, mod), BPF_CAST_FMT_ARG(2, args, mod),
+		BPF_CAST_FMT_ARG(3, args, mod), BPF_CAST_FMT_ARG(4, args, mod),
+		BPF_CAST_FMT_ARG(5, args, mod), BPF_CAST_FMT_ARG(6, args, mod),
+		BPF_CAST_FMT_ARG(7, args, mod), BPF_CAST_FMT_ARG(8, args, mod),
+		BPF_CAST_FMT_ARG(9, args, mod), BPF_CAST_FMT_ARG(10, args, mod),
+		BPF_CAST_FMT_ARG(11, args, mod));
+
+	bpf_printf_cleanup();
+
+	return err + 1;
+}
+
+const struct bpf_func_proto bpf_snprintf_proto = {
+	.func		= bpf_snprintf,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_MEM_OR_NULL,
+	.arg2_type	= ARG_CONST_SIZE_OR_ZERO,
+	.arg3_type	= ARG_PTR_TO_CONST_STR,
+	.arg4_type	= ARG_PTR_TO_MEM_OR_NULL,
+	.arg5_type	= ARG_CONST_SIZE_OR_ZERO,
+};
+
 const struct bpf_func_proto bpf_get_current_task_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_proto __weak;
 const struct bpf_func_proto bpf_probe_read_user_str_proto __weak;
@@ -757,6 +1061,8 @@ bpf_base_func_proto(enum bpf_func_id func_id)
 		return &bpf_probe_read_kernel_str_proto;
 	case BPF_FUNC_snprintf_btf:
 		return &bpf_snprintf_btf_proto;
+	case BPF_FUNC_snprintf:
+		return &bpf_snprintf_proto;
 	default:
 		return NULL;
 	}

kernel/bpf/verifier.c

@@ -4787,6 +4787,7 @@ static const struct bpf_reg_types spin_lock_types = { .types = { PTR_TO_MAP_VALU
 static const struct bpf_reg_types percpu_btf_ptr_types = { .types = { PTR_TO_PERCPU_BTF_ID } };
 static const struct bpf_reg_types func_ptr_types = { .types = { PTR_TO_FUNC } };
 static const struct bpf_reg_types stack_ptr_types = { .types = { PTR_TO_STACK } };
+static const struct bpf_reg_types const_str_ptr_types = { .types = { PTR_TO_MAP_VALUE } };
 
 static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_MAP_KEY]		= &map_key_value_types,
@@ -4817,6 +4818,7 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
 	[ARG_PTR_TO_PERCPU_BTF_ID]	= &percpu_btf_ptr_types,
 	[ARG_PTR_TO_FUNC]		= &func_ptr_types,
 	[ARG_PTR_TO_STACK_OR_NULL]	= &stack_ptr_types,
+	[ARG_PTR_TO_CONST_STR]		= &const_str_ptr_types,
 };
 
 static int check_reg_type(struct bpf_verifier_env *env, u32 regno,
@@ -5067,6 +5069,45 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
 		if (err)
 			return err;
 		err = check_ptr_alignment(env, reg, 0, size, true);
+	} else if (arg_type == ARG_PTR_TO_CONST_STR) {
+		struct bpf_map *map = reg->map_ptr;
+		int map_off;
+		u64 map_addr;
+		char *str_ptr;
+
+		if (reg->type != PTR_TO_MAP_VALUE || !map ||
+		    !bpf_map_is_rdonly(map)) {
+			verbose(env, "R%d does not point to a readonly map'\n", regno);
+			return -EACCES;
+		}
+
+		if (!tnum_is_const(reg->var_off)) {
+			verbose(env, "R%d is not a constant address'\n", regno);
+			return -EACCES;
+		}
+
+		if (!map->ops->map_direct_value_addr) {
+			verbose(env, "no direct value access support for this map type\n");
+			return -EACCES;
+		}
+
+		err = check_map_access(env, regno, reg->off,
+				       map->value_size - reg->off, false);
+		if (err)
+			return err;
+
+		map_off = reg->off + reg->var_off.value;
+		err = map->ops->map_direct_value_addr(map, &map_addr, map_off);
+		if (err) {
+			verbose(env, "direct value access on string failed\n");
+			return err;
+		}
+
+		str_ptr = (char *)(long)(map_addr);
+		if (!strnchr(str_ptr + map_off, map->value_size - map_off, 0)) {
+			verbose(env, "string is not zero-terminated\n");
+			return -EINVAL;
+		}
 	}
 
 	return err;
@@ -5877,6 +5918,41 @@ static int check_reference_leak(struct bpf_verifier_env *env)
 	return state->acquired_refs ? -EINVAL : 0;
 }
 
+static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
+				   struct bpf_reg_state *regs)
+{
+	struct bpf_reg_state *fmt_reg = &regs[BPF_REG_3];
+	struct bpf_reg_state *data_len_reg = &regs[BPF_REG_5];
+	struct bpf_map *fmt_map = fmt_reg->map_ptr;
+	int err, fmt_map_off, num_args;
+	u64 fmt_addr;
+	char *fmt;
+
+	/* data must be an array of u64 */
+	if (data_len_reg->var_off.value % 8)
+		return -EINVAL;
+	num_args = data_len_reg->var_off.value / 8;
+
+	/* fmt being ARG_PTR_TO_CONST_STR guarantees that var_off is const
+	 * and map_direct_value_addr is set.
+	 */
+	fmt_map_off = fmt_reg->off + fmt_reg->var_off.value;
+	err = fmt_map->ops->map_direct_value_addr(fmt_map, &fmt_addr,
+						  fmt_map_off);
+	if (err)
+		return err;
+	fmt = (char *)(long)fmt_addr + fmt_map_off;
+
+	/* We are also guaranteed that fmt+fmt_map_off is NULL terminated, we
+	 * can focus on validating the format specifiers.
+	 */
+	err = bpf_printf_prepare(fmt, UINT_MAX, NULL, NULL, NULL, num_args);
+	if (err < 0)
+		verbose(env, "Invalid format string\n");
+
+	return err;
+}
+
 static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			     int *insn_idx_p)
 {
@@ -5991,6 +6067,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 			return -EINVAL;
 	}
 
+	if (func_id == BPF_FUNC_snprintf) {
+		err = check_bpf_snprintf_call(env, regs);
+		if (err < 0)
+			return err;
+	}
+
 	/* reset caller saved regs */
 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
 		mark_reg_not_init(env, regs, caller_saved[i]);

tools/include/uapi/linux/bpf.h

@@ -4708,6 +4708,33 @@ union bpf_attr {
  *	Return
  *		The number of traversed map elements for success, **-EINVAL** for
  *		invalid **flags**.
+ *
+ * long bpf_snprintf(char *str, u32 str_size, const char *fmt, u64 *data, u32 data_len)
+ *	Description
+ *		Outputs a string into the **str** buffer of size **str_size**
+ *		based on a format string stored in a read-only map pointed by
+ *		**fmt**.
+ *
+ *		Each format specifier in **fmt** corresponds to one u64 element
+ *		in the **data** array. For strings and pointers where pointees
+ *		are accessed, only the pointer values are stored in the *data*
+ *		array. The *data_len* is the size of *data* in bytes.
+ *
+ *		Formats **%s** and **%p{i,I}{4,6}** require to read kernel
+ *		memory. Reading kernel memory may fail due to either invalid
+ *		address or valid address but requiring a major memory fault. If
+ *		reading kernel memory fails, the string for **%s** will be an
+ *		empty string, and the ip address for **%p{i,I}{4,6}** will be 0.
+ *		Not returning error to bpf program is consistent with what
+ *		**bpf_trace_printk**\ () does for now.
+ *
+ *	Return
+ *		The strictly positive length of the formatted string, including
+ *		the trailing zero character. If the return value is greater than
+ *		**str_size**, **str** contains a truncated string, guaranteed to
+ *		be zero-terminated except when **str_size** is 0.
+ *
+ *		Or **-EBUSY** if the per-CPU memory copy buffer is busy.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -4875,6 +4902,7 @@ union bpf_attr {
 	FN(sock_from_file),		\
 	FN(check_mtu),			\
 	FN(for_each_map_elem),		\
+	FN(snprintf),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

tools/lib/bpf/bpf_tracing.h

@@ -413,20 +413,56 @@ typeof(name(0)) name(struct pt_regs *ctx)				    \
 }									    \
 static __always_inline typeof(name(0)) ____##name(struct pt_regs *ctx, ##args)
 
+#define ___bpf_fill0(arr, p, x) do {} while (0)
+#define ___bpf_fill1(arr, p, x) arr[p] = x
+#define ___bpf_fill2(arr, p, x, args...) arr[p] = x; ___bpf_fill1(arr, p + 1, args)
+#define ___bpf_fill3(arr, p, x, args...) arr[p] = x; ___bpf_fill2(arr, p + 1, args)
+#define ___bpf_fill4(arr, p, x, args...) arr[p] = x; ___bpf_fill3(arr, p + 1, args)
+#define ___bpf_fill5(arr, p, x, args...) arr[p] = x; ___bpf_fill4(arr, p + 1, args)
+#define ___bpf_fill6(arr, p, x, args...) arr[p] = x; ___bpf_fill5(arr, p + 1, args)
+#define ___bpf_fill7(arr, p, x, args...) arr[p] = x; ___bpf_fill6(arr, p + 1, args)
+#define ___bpf_fill8(arr, p, x, args...) arr[p] = x; ___bpf_fill7(arr, p + 1, args)
+#define ___bpf_fill9(arr, p, x, args...) arr[p] = x; ___bpf_fill8(arr, p + 1, args)
+#define ___bpf_fill10(arr, p, x, args...) arr[p] = x; ___bpf_fill9(arr, p + 1, args)
+#define ___bpf_fill11(arr, p, x, args...) arr[p] = x; ___bpf_fill10(arr, p + 1, args)
+#define ___bpf_fill12(arr, p, x, args...) arr[p] = x; ___bpf_fill11(arr, p + 1, args)
+#define ___bpf_fill(arr, args...) \
+	___bpf_apply(___bpf_fill, ___bpf_narg(args))(arr, 0, args)
+
 /*
  * BPF_SEQ_PRINTF to wrap bpf_seq_printf to-be-printed values
  * in a structure.
  */
-#define BPF_SEQ_PRINTF(seq, fmt, args...)				    \
-	({								    \
-		_Pragma("GCC diagnostic push")				    \
-		_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	    \
-		static const char ___fmt[] = fmt;			    \
-		unsigned long long ___param[] = { args };		    \
-		_Pragma("GCC diagnostic pop")				    \
-		int ___ret = bpf_seq_printf(seq, ___fmt, sizeof(___fmt),    \
-					    ___param, sizeof(___param));    \
-		___ret;							    \
-	})
+#define BPF_SEQ_PRINTF(seq, fmt, args...)			\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_seq_printf(seq, ___fmt, sizeof(___fmt),		\
+		       ___param, sizeof(___param));		\
+})
+
+/*
+ * BPF_SNPRINTF wraps the bpf_snprintf helper with variadic arguments instead of
+ * an array of u64.
+ */
+#define BPF_SNPRINTF(out, out_size, fmt, args...)		\
+({								\
+	static const char ___fmt[] = fmt;			\
+	unsigned long long ___param[___bpf_narg(args)];		\
+								\
+	_Pragma("GCC diagnostic push")				\
+	_Pragma("GCC diagnostic ignored \"-Wint-conversion\"")	\
+	___bpf_fill(___param, args);				\
+	_Pragma("GCC diagnostic pop")				\
+								\
+	bpf_snprintf(out, out_size, ___fmt,			\
+		     ___param, sizeof(___param));		\
+})
 
 #endif

tools/testing/selftests/bpf/prog_tests/snprintf.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Google LLC. */
+
+#include <test_progs.h>
+#include "test_snprintf.skel.h"
+#include "test_snprintf_single.skel.h"
+
+#define EXP_NUM_OUT  "-8 9 96 -424242 1337 DABBAD00"
+#define EXP_NUM_RET  sizeof(EXP_NUM_OUT)
+
+#define EXP_IP_OUT   "127.000.000.001 0000:0000:0000:0000:0000:0000:0000:0001"
+#define EXP_IP_RET   sizeof(EXP_IP_OUT)
+
+/* The third specifier, %pB, depends on compiler inlining so don't check it */
+#define EXP_SYM_OUT  "schedule schedule+0x0/"
+#define MIN_SYM_RET  sizeof(EXP_SYM_OUT)
+
+/* The third specifier, %p, is a hashed pointer which changes on every reboot */
+#define EXP_ADDR_OUT "0000000000000000 ffff00000add4e55 "
+#define EXP_ADDR_RET sizeof(EXP_ADDR_OUT "unknownhashedptr")
+
+#define EXP_STR_OUT  "str1 longstr"
+#define EXP_STR_RET  sizeof(EXP_STR_OUT)
+
+#define EXP_OVER_OUT "%over"
+#define EXP_OVER_RET 10
+
+#define EXP_PAD_OUT "    4 000"
+#define EXP_PAD_RET 900007
+
+#define EXP_NO_ARG_OUT "simple case"
+#define EXP_NO_ARG_RET 12
+
+#define EXP_NO_BUF_RET 29
+
+void test_snprintf_positive(void)
+{
+	char exp_addr_out[] = EXP_ADDR_OUT;
+	char exp_sym_out[]  = EXP_SYM_OUT;
+	struct test_snprintf *skel;
+
+	skel = test_snprintf__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "skel_open"))
+		return;
+
+	if (!ASSERT_OK(test_snprintf__attach(skel), "skel_attach"))
+		goto cleanup;
+
+	/* trigger tracepoint */
+	usleep(1);
+
+	ASSERT_STREQ(skel->bss->num_out, EXP_NUM_OUT, "num_out");
+	ASSERT_EQ(skel->bss->num_ret, EXP_NUM_RET, "num_ret");
+
+	ASSERT_STREQ(skel->bss->ip_out, EXP_IP_OUT, "ip_out");
+	ASSERT_EQ(skel->bss->ip_ret, EXP_IP_RET, "ip_ret");
+
+	ASSERT_OK(memcmp(skel->bss->sym_out, exp_sym_out,
+			 sizeof(exp_sym_out) - 1), "sym_out");
+	ASSERT_LT(MIN_SYM_RET, skel->bss->sym_ret, "sym_ret");
+
+	ASSERT_OK(memcmp(skel->bss->addr_out, exp_addr_out,
+			 sizeof(exp_addr_out) - 1), "addr_out");
+	ASSERT_EQ(skel->bss->addr_ret, EXP_ADDR_RET, "addr_ret");
+
+	ASSERT_STREQ(skel->bss->str_out, EXP_STR_OUT, "str_out");
+	ASSERT_EQ(skel->bss->str_ret, EXP_STR_RET, "str_ret");
+
+	ASSERT_STREQ(skel->bss->over_out, EXP_OVER_OUT, "over_out");
+	ASSERT_EQ(skel->bss->over_ret, EXP_OVER_RET, "over_ret");
+
+	ASSERT_STREQ(skel->bss->pad_out, EXP_PAD_OUT, "pad_out");
+	ASSERT_EQ(skel->bss->pad_ret, EXP_PAD_RET, "pad_ret");
+
+	ASSERT_STREQ(skel->bss->noarg_out, EXP_NO_ARG_OUT, "no_arg_out");
+	ASSERT_EQ(skel->bss->noarg_ret, EXP_NO_ARG_RET, "no_arg_ret");
+
+	ASSERT_EQ(skel->bss->nobuf_ret, EXP_NO_BUF_RET, "no_buf_ret");
+
+cleanup:
+	test_snprintf__destroy(skel);
+}
+
+#define min(a, b) ((a) < (b) ? (a) : (b))
+
+/* Loads an eBPF object calling bpf_snprintf with up to 10 characters of fmt */
+static int load_single_snprintf(char *fmt)
+{
+	struct test_snprintf_single *skel;
+	int ret;
+
+	skel = test_snprintf_single__open();
+	if (!skel)
+		return -EINVAL;
+
+	memcpy(skel->rodata->fmt, fmt, min(strlen(fmt) + 1, 10));
+
+	ret = test_snprintf_single__load(skel);
+	test_snprintf_single__destroy(skel);
+
+	return ret;
+}
+
+void test_snprintf_negative(void)
+{
+	ASSERT_OK(load_single_snprintf("valid %d"), "valid usage");
+
+	ASSERT_ERR(load_single_snprintf("0123456789"), "no terminating zero");
+	ASSERT_ERR(load_single_snprintf("%d %d"), "too many specifiers");
+	ASSERT_ERR(load_single_snprintf("%pi5"), "invalid specifier 1");
+	ASSERT_ERR(load_single_snprintf("%a"), "invalid specifier 2");
+	ASSERT_ERR(load_single_snprintf("%"), "invalid specifier 3");
+	ASSERT_ERR(load_single_snprintf("%12345678"), "invalid specifier 4");
+	ASSERT_ERR(load_single_snprintf("%--------"), "invalid specifier 5");
+	ASSERT_ERR(load_single_snprintf("\x80"), "non ascii character");
+	ASSERT_ERR(load_single_snprintf("\x1"), "non printable character");
+}
+
+void test_snprintf(void)
+{
+	if (test__start_subtest("snprintf_positive"))
+		test_snprintf_positive();
+	if (test__start_subtest("snprintf_negative"))
+		test_snprintf_negative();
+}

tools/testing/selftests/bpf/progs/test_snprintf.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Google LLC. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+char num_out[64] = {};
+long num_ret = 0;
+
+char ip_out[64] = {};
+long ip_ret = 0;
+
+char sym_out[64] = {};
+long sym_ret = 0;
+
+char addr_out[64] = {};
+long addr_ret = 0;
+
+char str_out[64] = {};
+long str_ret = 0;
+
+char over_out[6] = {};
+long over_ret = 0;
+
+char pad_out[10] = {};
+long pad_ret = 0;
+
+char noarg_out[64] = {};
+long noarg_ret = 0;
+
+long nobuf_ret = 0;
+
+extern const void schedule __ksym;
+
+SEC("raw_tp/sys_enter")
+int handler(const void *ctx)
+{
+	/* Convenient values to pretty-print */
+	const __u8 ex_ipv4[] = {127, 0, 0, 1};
+	const __u8 ex_ipv6[] = {0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1};
+	static const char str1[] = "str1";
+	static const char longstr[] = "longstr";
+
+	/* Integer types */
+	num_ret  = BPF_SNPRINTF(num_out, sizeof(num_out),
+				"%d %u %x %li %llu %lX",
+				-8, 9, 150, -424242, 1337, 0xDABBAD00);
+	/* IP addresses */
+	ip_ret   = BPF_SNPRINTF(ip_out, sizeof(ip_out), "%pi4 %pI6",
+				&ex_ipv4, &ex_ipv6);
+	/* Symbol lookup formatting */
+	sym_ret  = BPF_SNPRINTF(sym_out,  sizeof(sym_out), "%ps %pS %pB",
+				&schedule, &schedule, &schedule);
+	/* Kernel pointers */
+	addr_ret = BPF_SNPRINTF(addr_out, sizeof(addr_out), "%pK %px %p",
+				0, 0xFFFF00000ADD4E55, 0xFFFF00000ADD4E55);
+	/* Strings embedding */
+	str_ret  = BPF_SNPRINTF(str_out, sizeof(str_out), "%s %+05s",
+				str1, longstr);
+	/* Overflow */
+	over_ret = BPF_SNPRINTF(over_out, sizeof(over_out), "%%overflow");
+	/* Padding of fixed width numbers */
+	pad_ret = BPF_SNPRINTF(pad_out, sizeof(pad_out), "%5d %0900000X", 4, 4);
+	/* No args */
+	noarg_ret = BPF_SNPRINTF(noarg_out, sizeof(noarg_out), "simple case");
+	/* No buffer */
+	nobuf_ret = BPF_SNPRINTF(NULL, 0, "only interested in length %d", 60);
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";

tools/testing/selftests/bpf/progs/test_snprintf_single.c

+// SPDX-License-Identifier: GPL-2.0
+/* Copyright (c) 2021 Google LLC. */
+
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+/* The format string is filled from the userspace such that loading fails */
+static const char fmt[10];
+
+SEC("raw_tp/sys_enter")
+int handler(const void *ctx)
+{
+	unsigned long long arg = 42;
+
+	bpf_snprintf(NULL, 0, fmt, &arg, sizeof(arg));
+
+	return 0;
+}
+
+char _license[] SEC("license") = "GPL";