printf: drastically reduce stack usage without [long] double args

internally, printf always works with the maximal-size supported
integer and floating point formats. however, the space needed to
format a floating point number is proportional to the mantissa and
exponent ranges. on archs where long double is larger than double,
knowing that the actual value fit in double allows us to use a much
smaller buffer, roughly 1/16 the size.

as a bonus, making the working buffer a VLA whose dimension depends on
the format specifier prevents the compiler from lifting the stack
adjustment to the top of printf_core. this makes it so printf calls
without floating point arguments do not waste even the smaller amount
of stack space needed for double, making it much more practical to use
printf in tightly stack-constrained environments.

src/stdio/vfprintf.c

@@ -178,10 +178,14 @@ static char *fmt_u(uintmax_t x, char *s)
 typedef char compiler_defines_long_double_incorrectly[9-(int)sizeof(long double)];
 #endif
 
-static int fmt_fp(FILE *f, long double y, int w, int p, int fl, int t)
+static int fmt_fp(FILE *f, long double y, int w, int p, int fl, int t, int ps)
 {
-	uint32_t big[(LDBL_MANT_DIG+28)/29 + 1          // mantissa expansion
-		+ (LDBL_MAX_EXP+LDBL_MANT_DIG+28+8)/9]; // exponent expansion
+	int bufsize = (ps==BIGLPRE)
+		? (LDBL_MANT_DIG+28)/29 + 1 +          // mantissa expansion
+		  (LDBL_MAX_EXP+LDBL_MANT_DIG+28+8)/9  // exponent expansion
+		: (DBL_MANT_DIG+28)/29 + 1 +
+		  (DBL_MAX_EXP+DBL_MANT_DIG+28+8)/9;
+	uint32_t big[bufsize];
 	uint32_t *a, *d, *r, *z;
 	int e2=0, e, i, j, l;
 	char buf[9+LDBL_MANT_DIG/4], *s;
@@ -618,7 +622,7 @@ static int printf_core(FILE *f, const char *fmt, va_list *ap, union arg *nl_arg,
 		case 'e': case 'f': case 'g': case 'a':
 		case 'E': case 'F': case 'G': case 'A':
 			if (xp && p<0) goto overflow;
-			l = fmt_fp(f, arg.f, w, p, fl, t);
+			l = fmt_fp(f, arg.f, w, p, fl, t, ps);
 			if (l<0) goto overflow;
 			continue;
 		}