Re: [PATCH v2 next 00/11] tools/nolibc: Enhance printf()

[David Laight <david.laight.linux@gmail.com>]

On Fri,  6 Feb 2026 19:11:10 +0000
david.laight.linux@gmail.com wrote:

> From: David Laight <david.laight.linux@gmail.com>
> 
> Update printf() so that it handles almost all the non-fp formats.
> In particular:
> - Left alignment.
> - Zero padding.
> - Field precision.
> - Variable field width and precision.
> - Width modifiers q, L, t and z.
> - Conversion specifiers i and X (X generates lower case).
> About the only things that are missing are octal and floating point.

Since it is pretty much a re-write, a copy of the new version:

/* printf(). Supports most of the normal integer and string formats.
 *  - %[#0-+ ][width|*[.precision|*]][{l,t,z,ll,L,j,q}]{d,i,u,c,x,X,p,s,m,%}
 *  - %% generates a single %
 *  - %m outputs strerror(errno).
 *  - # only affects %x and prepends 0x to non-zero values.
 *  - %o (octal) isn't supported.
 *  - %X outputs a..f the same as %x.
 *  - No support for wide characters.
 *  - invalid formats are copied to the output buffer.
 */

/* This code uses 'flag' variables that are indexed by the low 6 bits
 * of characters to optimise checks for multiple characters.
 *
 * _NOLIBC_PF_FLAGS_CONTAIN(flags, 'a', 'b'. ...)
 * returns non-zero if the bit for any of the specified characters is set.
 *
 * _NOLIBC_PF_CHAR_IS_ONE_OF(ch, 'a', 'b'. ...)
 * returns the flag bit for ch if it is one of the specified characters.
 * All the characters must be in the same 32 character block (non-alphabetic,
 * upper case, or lower case) of the ASCII character set.)
 */
#define _NOLIBC_PF_FLAG(ch) (1u << ((ch) & 0x1f))
#define _NOLIBC_PF_FLAG_NZ(ch) ((ch) ? _NOLIBC_PF_FLAG(ch) : 0)
#define _NOLIBC_PF_FLAG8(cmp_1, cmp_2, cmp_3, cmp_4, cmp_5, cmp_6, cmp_7, cmp_8, ...) \
	(_NOLIBC_PF_FLAG_NZ(cmp_1) | _NOLIBC_PF_FLAG_NZ(cmp_2) | \
	 _NOLIBC_PF_FLAG_NZ(cmp_3) | _NOLIBC_PF_FLAG_NZ(cmp_4) | \
	 _NOLIBC_PF_FLAG_NZ(cmp_5) | _NOLIBC_PF_FLAG_NZ(cmp_6) | \
	 _NOLIBC_PF_FLAG_NZ(cmp_7) | _NOLIBC_PF_FLAG_NZ(cmp_8))
#define _NOLIBC_PF_FLAGS_CONTAIN(flags, ...) \
	((flags) & _NOLIBC_PF_FLAG8(__VA_ARGS__, 0, 0, 0, 0, 0, 0, 0))
#define _NOLIBC_PF_CHAR_IS_ONE_OF(ch, cmp_1, ...) \
	(ch < (cmp_1 & ~0x1f) || ch > (cmp_1 | 0x1f) ? 0 : \
		_NOLIBC_PF_FLAGS_CONTAIN(_NOLIBC_PF_FLAG(ch), cmp_1, __VA_ARGS__))

typedef int (*__nolibc_printf_cb)(void *state, const char *buf, size_t size);

static __attribute__((unused, format(printf, 3, 0)))
int __nolibc_printf(__nolibc_printf_cb cb, void *state, const char *fmt, va_list args)
{
	char ch;
	int len, written, width, precision;
	unsigned int flags, ch_flag;
	char tmpbuf[32 + 24];
	const char *outstr;

	written = 0;
	while (1) {
		outstr = fmt;
		ch = *fmt++;
		if (!ch)
			break;

		width = 0;
		flags = 0;
		if (ch != '%') {
			while (*fmt && *fmt != '%')
				fmt++;
			len = fmt - outstr;
		} else {
			/* we're in a format sequence */

			ch = *fmt++;

			/* Conversion flag characters */
			for (;; ch = *fmt++) {
				ch_flag = _NOLIBC_PF_CHAR_IS_ONE_OF(ch, ' ', '#', '+', '-', '0');
				if (!ch_flag)
					break;
				flags |= ch_flag;
			}

                        /* Width and precision */
			for (;; ch = *fmt++) {
				if (ch == '*') {
					precision = va_arg(args, unsigned int);
					ch = *fmt++;
				} else {
					for (precision = 0; ch >= '0' && ch <= '9'; ch = *fmt++)
						precision = precision * 10 + (ch - '0');
				}
				if (_NOLIBC_PF_FLAGS_CONTAIN(flags, '.'))
					break;
				width = precision;
				if (ch != '.') {
					/* Default precision for strings */
					precision = INT_MAX;
					break;
				}
				flags |= _NOLIBC_PF_FLAG('.');
			}

			/* Length modifier.
			 * They miss the conversion flags characters " #+-0" so can go into flags.
			 * Change both L and ll to q.
			 */
			if (ch == 'L')
				ch = 'q';
			ch_flag = _NOLIBC_PF_CHAR_IS_ONE_OF(ch, 'l', 't', 'z', 'j', 'q');
			if (ch_flag != 0) {
				if (ch == 'l' && fmt[0] == 'l') {
					fmt++;
					ch_flag = _NOLIBC_PF_FLAG('q');
				}
				flags |= ch_flag;
				ch = *fmt++;
			}

			/* Conversion specifiers. */

			/* Numeric and pointer conversion specifiers.
			 *
			 * Use an explicit bound check (rather than _NOLIBC_PF_CHAR_IS_ONE_OF())
			 * so that 'X' can be allowed through.
			 * 'X' gets treated and 'x' because _NOLIBC_PF_FLAG() returns the same
			 * value for both.
			 */
			if ((ch < 'a' || ch > 'z') && ch != 'X')
				goto non_numeric_conversion;

			/* We need to check for "%p" or "%#x" later, merging here gives better code.
			 * But '#' collides with 'c' so shift right.
			 */
			ch_flag = _NOLIBC_PF_FLAG(ch) | (flags & _NOLIBC_PF_FLAG('#')) >> 1;
			if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag, 'c', 'd', 'i', 'u', 'x', 'p', 's')) {
				unsigned long long v;
				long long signed_v;
				char *out = tmpbuf + 32;
				int sign = 0;

				/* 'long' is needed for pointer/string conversions and ltz lengths.
				 * A single test can be used provided 'p' (the same bit as '0')
				 * is masked from flags.
				 */
				if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag | (flags & ~_NOLIBC_PF_FLAG('p')),
							     'p', 's', 'l', 't', 'z')) {
					v = va_arg(args, unsigned long);
					signed_v = (long)v;
				} else if (_NOLIBC_PF_FLAGS_CONTAIN(flags, 'j', 'q')) {
					v = va_arg(args, unsigned long long);
					signed_v = v;
				} else {
					v = va_arg(args, unsigned int);
					signed_v = (int)v;
				}

				if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag, 'c')) {
					/* "%c" - single character. */
					tmpbuf[0] = v;
					len = 1;
					outstr = tmpbuf;
					goto do_output;
				}

				if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag, 's')) {
					/* "%s" - character string. */
					if (!v) {
						outstr = "(null)";
						/* Match glibc, nothing output if precision too small */
						len = precision >= 6 ? 6 : 0;
						goto do_output;
					}
					outstr = (void *)v;
do_strnlen_output:
					len = strnlen(outstr, precision);
					goto do_output;
				}

				if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag, 'd', 'i')) {
					/* "%d" and "%i" - signed decimal numbers. */
					if (signed_v < 0) {
						sign = '-';
						v = -(signed_v + 1);
						v++;
					} else if (_NOLIBC_PF_FLAGS_CONTAIN(flags, '+')) {
						sign = '+';
					} else if (_NOLIBC_PF_FLAGS_CONTAIN(flags, ' ')) {
						sign = ' ';
					}
				}

				if (v == 0) {
					/* There are special rules for zero. */
					if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag, 'p')) {
						/* "%p" match glibc, precision is ignored */
						outstr = "(nil)";
						len = 5;
						goto do_output;
					}
					if (!precision) {
						/* Explicit %nn.0d, no digits output */
						len = 0;
						goto prepend_sign;
					}
					/* All formats (including "%#x") just output "0". */
					*out = '0';
					len = 1;
				} else {
					/* Convert the number to ascii in the required base. */
					if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag, 'd', 'i', 'u')) {
						/* Base 10 */
						len = u64toa_r(v, out);
					} else {
						/* Base 16 */
						if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag, 'p', '#' - 1)) {
							/* "%p" and "%#x" need "0x" prepending. */
							sign = 'x' | '0' << 8;
						}
						len = u64toh_r(v, out);
					}
				}

				/* Add zero padding */
				if (_NOLIBC_PF_FLAGS_CONTAIN(flags, '0', '.')) {
					if (!_NOLIBC_PF_FLAGS_CONTAIN(flags, '.')) {
						if (_NOLIBC_PF_FLAGS_CONTAIN(flags, '-'))
							/* Left justify overrides zero pad */
							goto prepend_sign;
						/* eg "%05d", Zero pad to field width less sign */
						precision = width;
						if (sign) {
							precision--;
							if (sign >= 256)
								precision--;
						}
					}
					if (precision > 30)
						/* Don't run off the start of tmpbuf[] */
						precision = 30;
					for (; len < precision; len++) {
						/* Stop gcc generating horrid code and memset().
						 * This is OPTIMIZER_HIDE_VAR() from compiler.h.
						 */
						__asm__ volatile("" : "=r"(len) : "0"(len));
						*--out = '0';
					}
				}

prepend_sign:
				/* Add 0, 1 or 2 ("0x") sign characters left of any zero padding */
				for (; sign; sign >>= 8) {
					len++;
					*--out = sign;
				}
				outstr = out;
				goto do_output;
			}

non_numeric_conversion:
			if (ch == 'm') {
#ifdef NOLIBC_IGNORE_ERRNO
				outstr = "unknown error";
				len = __builtin_strlen(outstr);
#else
				outstr = strerror(errno);
				goto do_strnlen_output;
#endif /* NOLIBC_IGNORE_ERRNO */
			} else {
				if (ch != '%') {
					/* Invalid format: back up to output the format characters */
					fmt = outstr + 1;
					/* and output a '%' now. */
				}
				/* %% is documented as a 'conversion specifier'.
				 * Any flags, precision or length modifier are ignored.
				 */
				len = 1;
				width = 0;
				outstr = fmt - 1;
			}
		}

do_output:
		written += len;

		/* An OPTIMIZER_HIDE_VAR() seems to stop gcc back-merging this
		 * code into one of the conditionals above.
		 */
		__asm__ volatile("" : "=r"(len) : "0"(len));

		/* Output 'left pad', 'value' then 'right pad'. */
		width -= len;
		flags = _NOLIBC_PF_FLAGS_CONTAIN(flags, '-');
		if (flags && cb(state, outstr, len) != 0)
			return -1;
		while (width > 0) {
			int pad_len = ((width - 1) & 15) + 1;
			width -= pad_len;
			written += pad_len;
			if (cb(state, "                ", pad_len) != 0)
				return -1;
		}
		if (!flags && cb(state, outstr, len) != 0)
			return -1;
	}

	/* Flush/terminate any buffer. */
	if (cb(state, NULL, 0) != 0)
		return -1;

	return written;
}

struct __nolibc_fprintf_cb_state {
	FILE *stream;
	unsigned int buf_offset;
	char buf[128];
};

static int __nolibc_fprintf_cb(void *v_state, const char *buf, size_t size)
{
	struct __nolibc_fprintf_cb_state *state = v_state;
	unsigned int off = state->buf_offset;

	if (off + size > sizeof(state->buf) || buf == NULL) {
		state->buf_offset = 0;
		if (off && _fwrite(state->buf, off, state->stream))
			return -1;
		if (size > sizeof(state->buf))
			return _fwrite(buf, size, state->stream);
		off = 0;
	}

	if (size) {
		state->buf_offset = off + size;
		memcpy(state->buf + off, buf, size);
	}
	return 0;
}

...

struct __nolibc_sprintf_cb_state {
	char *buf;
	size_t size;
};

static int __nolibc_sprintf_cb(void *v_state, const char *buf, size_t size)
{
	struct __nolibc_sprintf_cb_state *state = v_state;
	char *tgt;

	if (size >= state->size) {
		if (state->size <= 1)
			return 0;
		size = state->size - 1;
	}
	tgt = state->buf;
	if (size) {
		state->size -= size;
		state->buf = tgt + size;
		memcpy(tgt, buf, size);
	} else {
		/* In particular from cb(NULL, 0) at the end of __nolibc_printf(). */
		*tgt = '\0';
	}
	return 0;
}