lib/vsprintf.c: eliminate some branches
Since FORMAT_TYPE_INT is simply 1 more than FORMAT_TYPE_UINT, and
similarly for BYTE/UBYTE, SHORT/USHORT, LONG/ULONG, we can eliminate a few
instructions by making SIGN have the value 1 instead of 2, and then use
arithmetic instead of branches for computing the right spec->type. It's a
little hacky, but certainly in the same spirit as SMALL needing to have
the value 0x20. For example for the spec->qualifier == 'l' case, gcc now
generates
75e: 0f b6 53 01 movzbl 0x1(%rbx),%edx
762: 83 e2 01 and $0x1,%edx
765: 83 c2 09 add $0x9,%edx
768: 88 13 mov %dl,(%rbx)
instead of
763: 0f b6 53 01 movzbl 0x1(%rbx),%edx
767: 83 e2 02 and $0x2,%edx
76a: 80 fa 01 cmp $0x1,%dl
76d: 19 d2 sbb %edx,%edx
76f: 83 c2 0a add $0xa,%edx
772: 88 13 mov %dl,(%rbx)
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Tejun Heo <tj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index b235c96..318d583 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -340,8 +340,8 @@
return len;
}
-#define ZEROPAD 1 /* pad with zero */
-#define SIGN 2 /* unsigned/signed long */
+#define SIGN 1 /* unsigned/signed, must be 1 */
+#define ZEROPAD 2 /* pad with zero */
#define PLUS 4 /* show plus */
#define SPACE 8 /* space if plus */
#define LEFT 16 /* left justified */
@@ -447,7 +447,7 @@
spec.precision = i;
/* leading space padding */
spec.field_width -= spec.precision;
- if (!(spec.flags & (ZEROPAD+LEFT))) {
+ if (!(spec.flags & (ZEROPAD | LEFT))) {
while (--spec.field_width >= 0) {
if (buf < end)
*buf = ' ';
@@ -1738,29 +1738,21 @@
if (spec->qualifier == 'L')
spec->type = FORMAT_TYPE_LONG_LONG;
else if (spec->qualifier == 'l') {
- if (spec->flags & SIGN)
- spec->type = FORMAT_TYPE_LONG;
- else
- spec->type = FORMAT_TYPE_ULONG;
+ BUILD_BUG_ON(FORMAT_TYPE_ULONG + SIGN != FORMAT_TYPE_LONG);
+ spec->type = FORMAT_TYPE_ULONG + (spec->flags & SIGN);
} else if (_tolower(spec->qualifier) == 'z') {
spec->type = FORMAT_TYPE_SIZE_T;
} else if (spec->qualifier == 't') {
spec->type = FORMAT_TYPE_PTRDIFF;
} else if (spec->qualifier == 'H') {
- if (spec->flags & SIGN)
- spec->type = FORMAT_TYPE_BYTE;
- else
- spec->type = FORMAT_TYPE_UBYTE;
+ BUILD_BUG_ON(FORMAT_TYPE_UBYTE + SIGN != FORMAT_TYPE_BYTE);
+ spec->type = FORMAT_TYPE_UBYTE + (spec->flags & SIGN);
} else if (spec->qualifier == 'h') {
- if (spec->flags & SIGN)
- spec->type = FORMAT_TYPE_SHORT;
- else
- spec->type = FORMAT_TYPE_USHORT;
+ BUILD_BUG_ON(FORMAT_TYPE_USHORT + SIGN != FORMAT_TYPE_SHORT);
+ spec->type = FORMAT_TYPE_USHORT + (spec->flags & SIGN);
} else {
- if (spec->flags & SIGN)
- spec->type = FORMAT_TYPE_INT;
- else
- spec->type = FORMAT_TYPE_UINT;
+ BUILD_BUG_ON(FORMAT_TYPE_UINT + SIGN != FORMAT_TYPE_INT);
+ spec->type = FORMAT_TYPE_UINT + (spec->flags & SIGN);
}
return ++fmt - start;