lib: vsprintf: optimize put_dec_trunc8()

If you're going to have a conditional branch after each 32x32->64-bit
multiply, might as well shrink the code and make it a loop.

This also avoids using the long multiply for small integers.

(This leaves the comments in a confusing state, but that's a separate
patch to make review easier.)

Signed-off-by: George Spelvin <linux@horizon.com>
Cc: Denys Vlasenko <vda.linux@googlemail.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 8cb7635b2ce305118b7491506122ba4bf5afa522..f58fc4b1eaf0765bf190c538330cb91a986970c8 100644 (file)
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -174,20 +174,12 @@ char *put_dec_trunc8(char *buf, unsigned r)
        unsigned q;
 
        /* Copy of previous function's body with added early returns */
-       q      = (r * (uint64_t)0x1999999a) >> 32;
-       *buf++ = (r - 10 * q) + '0'; /* 2 */
-       if (q == 0)
-               return buf;
-       r      = (q * (uint64_t)0x1999999a) >> 32;
-       *buf++ = (q - 10 * r) + '0'; /* 3 */
-       if (r == 0)
-               return buf;
-       q      = (r * (uint64_t)0x1999999a) >> 32;
-       *buf++ = (r - 10 * q) + '0'; /* 4 */
-       if (q == 0)
-               return buf;
-       r      = (q * (uint64_t)0x1999999a) >> 32;
-       *buf++ = (q - 10 * r) + '0'; /* 5 */
+       while (r >= 10000) {
+               q = r + '0';
+               r  = (r * (uint64_t)0x1999999a) >> 32;
+               *buf++ = q - 10*r;
+       }
+
        if (r == 0)
                return buf;
        q      = (r * 0x199a) >> 16;