svn commit: r352485 - stable/12/sys/arm64/arm64

[Alan Cox]

Author: alc
Date: Wed Sep 18 14:38:42 2019
New Revision: 352485
URL: https://svnweb.freebsd.org/changeset/base/352485

Log:
  MFC r349768
    Restructure cache_handle_range to avoid repeated barriers.  Specifically,
    restructure cache_handle_range so that all of the data cache operations are
    performed before any instruction cache operations.  Then, we only need one
    barrier between the data and instruction cache operations and one barrier
    after the instruction cache operations.
  
    On an Amazon EC2 a1.2xlarge instance, this simple change reduces the time
    for a "make -j8 buildworld" by 9%.

Modified:
  stable/12/sys/arm64/arm64/cpufunc_asm.S
Directory Properties:
  stable/12/   (props changed)

Modified: stable/12/sys/arm64/arm64/cpufunc_asm.S
==============================================================================
--- stable/12/sys/arm64/arm64/cpufunc_asm.S	Wed Sep 18 14:27:09 2019	(r352484)
+++ stable/12/sys/arm64/arm64/cpufunc_asm.S	Wed Sep 18 14:38:42 2019	(r352485)
@@ -47,7 +47,7 @@ __FBSDID("$FreeBSD$");
 
 /*
  * Macro to handle the cache. This takes the start address in x0, length
- * in x1. It will corrupt x0, x1, x2, and x3.
+ * in x1. It will corrupt x0, x1, x2, x3, and x4.
  */
 .macro cache_handle_range dcop = 0, ic = 0, icop = 0
 .if \ic == 0
@@ -60,17 +60,23 @@ __FBSDID("$FreeBSD$");
 	and	x2, x0, x4		/* Get the low bits of the address */
 	add	x1, x1, x2		/* Add these to the size */
 	bic	x0, x0, x4		/* Clear the low bit of the address */
-1:
-	dc	\dcop, x0
-	dsb	ish
 .if \ic != 0
-	ic	\icop, x0
-	dsb	ish
+	mov	x2, x0			/* Save the address */
+	mov	x4, x1			/* Save the size */
 .endif
+1:
+	dc	\dcop, x0
 	add	x0, x0, x3		/* Move to the next line */
 	subs	x1, x1, x3		/* Reduce the size */
 	b.hi	1b			/* Check if we are done */
+	dsb	ish
 .if \ic != 0
+2:
+	ic	\icop, x2
+	add	x2, x2, x3		/* Move to the next line */
+	subs	x4, x4, x3		/* Reduce the size */
+	b.hi	2b			/* Check if we are done */
+	dsb	ish
 	isb
 .endif
 .endm