From a194eabe088bcc33ee07eefe3aace2aa3e2a3d25 Mon Sep 17 00:00:00 2001
From: Andrew Turner <andrew@FreeBSD.org>
Date: Tue, 20 Aug 2024 18:14:28 +0100
Subject: [PATCH] arm64: Use store-pair to zero the kernel bss

While this won't be noticed by most users the time to zero the bss
while using instruction tracing in the Arm FVP models (simulators) is
noticeable.

Reduce this time by using a store-pair instruction to double the size
of memory we zero on each iteration of the loop.

Sponsored by:	Arm Ltd
Differential Revision:	https://reviews.freebsd.org/D42733

(cherry picked from commit f1bc3750cf9a6623b0c0861984ef2a8ac966a4e3)
---
 sys/arm64/arm64/locore.S | 2 +-
 sys/conf/ldscript.arm64  | 3 ++-
 2 files changed, 3 insertions(+), 2 deletions(-)

diff --git a/sys/arm64/arm64/locore.S b/sys/arm64/arm64/locore.S
index 3db1d302596..d448f06b258 100644
--- a/sys/arm64/arm64/locore.S
+++ b/sys/arm64/arm64/locore.S
@@ -109,7 +109,7 @@ virtdone:
 	ldr	x15, .Lbss
 	ldr	x14, .Lend
 1:
-	str	xzr, [x15], #8
+	stp	xzr, xzr, [x15], #16
 	cmp	x15, x14
 	b.lo	1b
 
diff --git a/sys/conf/ldscript.arm64 b/sys/conf/ldscript.arm64
index 185b4485e07..21c7dc35d9b 100644
--- a/sys/conf/ldscript.arm64
+++ b/sys/conf/ldscript.arm64
@@ -119,6 +119,7 @@ SECTIONS
   .sdata     : { *(.sdata) }
   _edata  =  .;
   PROVIDE (edata = .);
+  . = ALIGN(16);
   __bss_start = .;
   .sbss      : { *(.sbss) *(.scommon) }
   .bss       :
@@ -126,7 +127,7 @@ SECTIONS
    *(.dynbss)
    *(.bss)
    *(COMMON)
-   . = ALIGN(8);
+   . = ALIGN(16);
    __bss_end = .;
    /* A section for the initial page table, it doesn't need to be in the
       kernel file, however unlike normal .bss entries should not be zeroed