On many cores, udiv with a large value is slow, expand instead
the division out to be what GCC would have generated for the
divide by 1000.
On ThunderX, the speeds up gettimeofday by 5%.
Signed-off-by: Andrew Pinski <apin...@cavium.com>
---
arch/arm64/kernel/vdso/gettimeofday.S | 20 ++++++++++++++++----
1 files changed, 16 insertions(+), 4 deletions(-)
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S
b/arch/arm64/kernel/vdso/gettimeofday.S
index efa79e8..e5caef9 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -64,10 +64,22 @@ ENTRY(__kernel_gettimeofday)
bl __do_get_tspec
seqcnt_check w9, 1b
- /* Convert ns to us. */
- mov x13, #1000
- lsl x13, x13, x12
- udiv x11, x11, x13
+ /* Undo the shift. */
+ lsr x11, x11, x12
+
+ /* Convert ns to us (division by 1000 by using multiply high).
+ * This is how GCC converts the division by 1000 into.
+ * This is faster than divide on most cores.
+ */
+ mov x13, 63439
+ movk x13, 0xe353, lsl 16
+ lsr x11, x11, 3
+ movk x13, 0x9ba5, lsl 32
+ movk x13, 0x20c4, lsl 48
+ /* x13 = 0x20c49ba5e353f7cf */
+ umulh x11, x11, x13
+ lsr x11, x11, 4
+
stp x10, x11, [x0, #TVAL_TV_SEC]
2:
/* If tz is NULL, return 0. */
--
1.7.2.5
