Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <5a2c0731967330e9a3832d531ea4212e223aaead.1685429467.git.Jens.Gustedt@inria.fr>
Date: Tue, 30 May 2023 08:55:27 +0200
From: Jens Gustedt <Jens.Gustedt@...ia.fr>
To: musl@...ts.openwall.com,
	jens.gustedt@...teo.eu
Subject: [C23 printf 2/3] C23: implement the wN length specifiers for printf

These are mandatory for C23 and concern all types for which the
platform has `int_leastN_t` and `uint_leastN_t`. For musl these types
always coincide with `intN_t` and `uintN_t` and are always present for
N equal 8, 16, 32 and 64.

They can be added for general use since all lowercase letters were
previously reserved.

Nevertheless, users that use these modifiers will see a lot of
warnings from compilers in the beginning. This is because the
compilers have not yet integrated this form of a specifier into their
correponding extensions (gcc attributes). So unfortunately also
testing this feature may be a bit noisy for the moment.

The only architecture dependend choice is the type for N == 64, which
may be `long` or `long long`. We just mimick the test that is done in
other places to compare `UINTPTR_MAX` and `UINT64_MAX` to determine
that.
---
 src/stdio/vfprintf.c  | 28 +++++++++++++++++++++++++---
 src/stdio/vfwprintf.c | 28 +++++++++++++++++++++++++---
 2 files changed, 50 insertions(+), 6 deletions(-)

diff --git a/src/stdio/vfprintf.c b/src/stdio/vfprintf.c
index cbc79783..265fb7ad 100644
--- a/src/stdio/vfprintf.c
+++ b/src/stdio/vfprintf.c
@@ -33,7 +33,7 @@
 
 enum {
 	BARE, LPRE, LLPRE, HPRE, HHPRE, BIGLPRE,
-	ZTPRE, JPRE,
+	ZTPRE, JPRE, WPRE,
 	STOP,
 	PTR, INT, UINT, ULLONG,
 	LONG, ULONG,
@@ -57,7 +57,7 @@ static const unsigned char states[]['z'-'A'+1] = {
 		S('s') = PTR, S('S') = PTR, S('p') = UIPTR, S('n') = PTR,
 		S('m') = NOARG,
 		S('l') = LPRE, S('h') = HPRE, S('L') = BIGLPRE,
-		S('z') = ZTPRE, S('j') = JPRE, S('t') = ZTPRE,
+		S('z') = ZTPRE, S('j') = JPRE, S('t') = ZTPRE, S('w') = WPRE,
 	}, { /* 1: l-prefixed */
 		S('b') = ULONG, S('B') = ULONG,
 		S('d') = LONG, S('i') = LONG,
@@ -101,6 +101,12 @@ static const unsigned char states[]['z'-'A'+1] = {
 		S('o') = UMAX, S('u') = UMAX,
 		S('x') = UMAX, S('X') = UMAX,
 		S('n') = PTR,
+	}, { /* 8: w-prefixed */
+		S('b') = UINT, S('B') = UINT,
+		S('d') = INT, S('i') = INT,
+		S('o') = UINT, S('u') = UINT,
+		S('x') = UINT, S('X') = UINT,
+		S('n') = PTR,
 	}
 };
 
@@ -447,7 +453,7 @@ static int printf_core(FILE *f, const char *fmt, va_list *ap, union arg *nl_arg,
 	int w, p, xp;
 	union arg arg;
 	int argpos;
-	unsigned st, ps;
+	unsigned st, ps, width=0;
 	int cnt=0, l=0;
 	size_t i;
 	char buf[sizeof(uintmax_t)*CHAR_BIT+3+LDBL_MANT_DIG/4];
@@ -527,9 +533,25 @@ static int printf_core(FILE *f, const char *fmt, va_list *ap, union arg *nl_arg,
 			if (OOB(*s)) goto inval;
 			ps=st;
 			st=states[st]S(*s++);
+ 			if (st == WPRE) {
+				if (*s == '0') goto inval;
+				width = getint(&s);
+                        }
 		} while (st-1<STOP);
 		if (!st) goto inval;
 
+		if (ps == WPRE) switch (width) {
+		case 8:   ps = HHPRE; st = (st == UINT) ? UCHAR  : ((st == INT) ? CHAR  : PTR); break;
+		case 16:  ps = HPRE;  st = (st == UINT) ? USHORT : ((st == INT) ? SHORT : PTR); break;
+		case 32:  ps = BARE;  break;
+#if UINTPTR_MAX >= UINT64_MAX
+		case 64:  ps = LPRE;  st = (st == UINT) ? ULONG  : ((st == INT) ? LONG  : PTR); break;
+#else
+		case 64:  ps = LLPRE; st = (st == UINT) ? ULLONG : ((st == INT) ? LLONG : PTR); break;
+#endif
+		default:  goto inval;
+		}
+
 		/* Check validity of argument type (nl/normal) */
 		if (st==NOARG) {
 			if (argpos>=0) goto inval;
diff --git a/src/stdio/vfwprintf.c b/src/stdio/vfwprintf.c
index dbc93f74..c3e81d2a 100644
--- a/src/stdio/vfwprintf.c
+++ b/src/stdio/vfwprintf.c
@@ -26,7 +26,7 @@
 
 enum {
 	BARE, LPRE, LLPRE, HPRE, HHPRE, BIGLPRE,
-	ZTPRE, JPRE,
+	ZTPRE, JPRE, WPRE,
 	STOP,
 	PTR, INT, UINT, ULLONG,
 	LONG, ULONG,
@@ -50,7 +50,7 @@ static const unsigned char states[]['z'-'A'+1] = {
 		S('s') = PTR, S('S') = PTR, S('p') = UIPTR, S('n') = PTR,
 		S('m') = NOARG,
 		S('l') = LPRE, S('h') = HPRE, S('L') = BIGLPRE,
-		S('z') = ZTPRE, S('j') = JPRE, S('t') = ZTPRE,
+		S('z') = ZTPRE, S('j') = JPRE, S('t') = ZTPRE, S('w') = WPRE,
 	}, { /* 1: l-prefixed */
 		S('b') = ULONG, S('B') = ULONG,
 		S('d') = LONG, S('i') = LONG,
@@ -94,6 +94,12 @@ static const unsigned char states[]['z'-'A'+1] = {
 		S('o') = UMAX, S('u') = UMAX,
 		S('x') = UMAX, S('X') = UMAX,
 		S('n') = PTR,
+	}, { /* 8: w-prefixed */
+		S('b') = UINT, S('B') = UINT,
+		S('d') = INT, S('i') = INT,
+		S('o') = UINT, S('u') = UINT,
+		S('x') = UINT, S('X') = UINT,
+		S('n') = PTR,
 	}
 };
 
@@ -163,7 +169,7 @@ static int wprintf_core(FILE *f, const wchar_t *fmt, va_list *ap, union arg *nl_
 	int w, p, xp;
 	union arg arg;
 	int argpos;
-	unsigned st, ps;
+	unsigned st, ps, width=0;
 	int cnt=0, l=0;
 	int i;
 	int t;
@@ -242,9 +248,25 @@ static int wprintf_core(FILE *f, const wchar_t *fmt, va_list *ap, union arg *nl_
 			if (OOB(*s)) goto inval;
 			ps=st;
 			st=states[st]S(*s++);
+ 			if (st == WPRE) {
+				if (*s == L'0') goto inval;
+				width = getint(&s);
+                        }
 		} while (st-1<STOP);
 		if (!st) goto inval;
 
+		if (ps == WPRE) switch (width) {
+		case 8:   ps = HHPRE; st = (st == UINT) ? UCHAR  : ((st == INT) ? CHAR  : PTR); break;
+		case 16:  ps = HPRE;  st = (st == UINT) ? USHORT : ((st == INT) ? SHORT : PTR); break;
+		case 32:  ps = BARE;  break;
+#if UINTPTR_MAX >= UINT64_MAX
+		case 64:  ps = LPRE;  st = (st == UINT) ? ULONG  : ((st == INT) ? LONG  : PTR); break;
+#else
+		case 64:  ps = LLPRE; st = (st == UINT) ? ULLONG : ((st == INT) ? LLONG : PTR); break;
+#endif
+		default:  goto inval;
+		}
+
 		/* Check validity of argument type (nl/normal) */
 		if (st==NOARG) {
 			if (argpos>=0) goto inval;
-- 
2.34.1

Powered by blists - more mailing lists

Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.