| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20260206191121.3602-7-david.laight.linux@gmail.com>
Date: Fri, 6 Feb 2026 19:11:16 +0000
From: david.laight.linux@...il.com
To: Willy Tarreau <w@....eu>,
Thomas Weißschuh <linux@...ssschuh.net>,
linux-kernel@...r.kernel.org,
Cheng Li <lechain@...il.com>
Cc: David Laight <david.laight.linux@...il.com>
Subject: [PATCH v2 next 06/11] tools/nolibc/printf: Use bit-masks to hold requested flag, length and conversion chars
From: David Laight <david.laight.linux@...il.com>
Use flags bits (1u << (ch & 31)) for the flags, length modifiers, and
conversion specifiers.
This makes it easy to test for multiple values at once.
Detect the conversion flags " #+-0" although they are currently all ignored.
Add support for length modifiers 't' and 'z' (both long) and 'q' and 'L'
(both long long).
Add support for "%i" (the same as %d").
Unconditionally generate the signed values (for %d) to remove a second
set of checks for the size.
Signed-off-by: David Laight <david.laight.linux@...il.com>
---
Changes for v2:
- Use #defines to make the code a lot more readable.
- Include the changes from the old patch 10 that used masks for the
conversion specifiers.
- Detect all the valid flag characters even though they are not implemented.
- Support for left justifying field is moved to patch 7.
tools/include/nolibc/stdio.h | 151 ++++++++++++++++++++++++-----------
1 file changed, 103 insertions(+), 48 deletions(-)
diff --git a/tools/include/nolibc/stdio.h b/tools/include/nolibc/stdio.h
index bb54f488c228..b14cf8224403 100644
--- a/tools/include/nolibc/stdio.h
+++ b/tools/include/nolibc/stdio.h
@@ -240,19 +240,44 @@ char *fgets(char *s, int size, FILE *stream)
}
-/* minimal printf(). It supports the following formats:
- * - %[l*]{d,u,c,x,p}
- * - %s
- * - unknown modifiers are ignored.
+/* simple printf(). It supports the following formats:
+ * - %[-][width][{l,t,z,ll,L,j,q}]{d,u,c,x,p,s,m,%}
+ * - %%
+ * - 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 lpref, ch;
- unsigned long long v;
+ char ch;
unsigned int written, width;
+ unsigned int flags, ch_flag;
size_t len;
char tmpbuf[21];
const char *outstr;
@@ -265,6 +290,7 @@ int __nolibc_printf(__nolibc_printf_cb cb, void *state, const char *fmt, va_list
break;
width = 0;
+ flags = 0;
if (ch != '%') {
while (*fmt && *fmt != '%')
fmt++;
@@ -274,6 +300,14 @@ int __nolibc_printf(__nolibc_printf_cb cb, void *state, const char *fmt, va_list
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 */
while (ch >= '0' && ch <= '9') {
width *= 10;
@@ -282,62 +316,77 @@ int __nolibc_printf(__nolibc_printf_cb cb, void *state, const char *fmt, va_list
ch = *fmt++;
}
- /* Length modifiers */
- if (ch == 'l') {
- lpref = 1;
- ch = *fmt++;
- if (ch == 'l') {
- lpref = 2;
- ch = *fmt++;
+ /* 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');
}
- } else if (ch == 'j') {
- /* intmax_t is long long */
- lpref = 2;
+ flags |= ch_flag;
ch = *fmt++;
- } else {
- lpref = 0;
}
- if (ch == 'c' || ch == 'd' || ch == 'u' || ch == 'x' || ch == 'p') {
+ /* Conversion specifiers. */
+
+ /* Numeric conversion specifiers. */
+ ch_flag = _NOLIBC_PF_CHAR_IS_ONE_OF(ch, 'c', 'd', 'i', 'u', 'x', 'p');
+ if (ch_flag != 0) {
+ unsigned long long v;
+ long long signed_v;
char *out = tmpbuf;
- if (ch == 'p')
+ /* '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', 'l', 't', 'z')) {
v = va_arg(args, unsigned long);
- else if (lpref) {
- if (lpref > 1)
- v = va_arg(args, unsigned long long);
- else
- v = va_arg(args, unsigned long);
- } else
+ 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 (ch == 'd') {
- /* sign-extend the value */
- if (lpref == 0)
- v = (long long)(int)v;
- else if (lpref == 1)
- v = (long long)(long)v;
+ if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag, 'c')) {
+ /* "%c" - single character. */
+ tmpbuf[0] = v;
+ len = 1;
+ outstr = tmpbuf;
+ goto do_output;
}
- switch (ch) {
- case 'c':
- out[0] = v;
- out[1] = 0;
- break;
- case 'd':
- i64toa_r(v, out);
- break;
- case 'u':
+ if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag, 'd', 'i')) {
+ /* "%d" and "%i" - signed decimal numbers. */
+ if (signed_v < 0) {
+ *out++ = '-';
+ v = -(signed_v + 1);
+ v++;
+ }
+ }
+
+ /* Convert the number to ascii in the required base. */
+ if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag, 'd', 'i', 'u')) {
+ /* Base 10 */
u64toa_r(v, out);
- break;
- case 'p':
- *(out++) = '0';
- *(out++) = 'x';
- __nolibc_fallthrough;
- default: /* 'x' and 'p' above */
+ } else {
+ /* Base 16 */
+ if (_NOLIBC_PF_FLAGS_CONTAIN(ch_flag, 'p')) {
+ *(out++) = '0';
+ *(out++) = 'x';
+ }
u64toh_r(v, out);
- break;
}
+
outstr = tmpbuf;
}
else if (ch == 's') {
@@ -366,8 +415,14 @@ int __nolibc_printf(__nolibc_printf_cb cb, void *state, const char *fmt, va_list
len = strlen(outstr);
}
+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));
+
while (width > len) {
unsigned int pad_len = ((width - len - 1) & 15) + 1;
width -= pad_len;
--
2.39.5
Powered by blists - more mailing lists