x86: use invd instead of wbinvd in real mode start code
PATCH 1/1 x86: use invd instead of wbinvd in real mode start code
I do not know why the boot code immediately after the system reset should write-back the cache content. I think the cache invalidation should be enough.
I tested this commit with qemu-x86_defconfig, and it worked for me.
---
arch/x86/cpu/start.S | 2 +- arch/x86/cpu/start16.S | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
arch/x86/cpu/start.S +1 -1
@@ -50,7 +50,7 @@ _x86boot_start: movl %cr0, %eax orl $(X86_CR0_NW | X86_CR0_CD), %eax movl %eax, %cr0 - wbinvd + invd /* * Zero the BIST (Built-In Self Test) value since we don't have it.
arch/x86/cpu/start16.S +1 -1
@@ -28,7 +28,7 @@ start16: movl %cr0, %eax orl $(X86_CR0_NW | X86_CR0_CD), %eax movl %eax, %cr0 - wbinvd + invd /* load the temporary Global Descriptor Table */ data32 cs lidt idt_ptr
Signature · 1 line
2.17.1
PATCH 1/1 x86: use invd instead of wbinvd in real mode start code
Quoted 5 lines · Masahiro Yamada
I do not know why the boot code immediately after the system reset should write-back the cache content. I think the cache invalidation should be enough.
Quoted 8 lines
I tested this commit with qemu-x86_defconfig, and it worked for me.
Signed-off-by Masahiro Yamada <[email protected]>---
arch/x86/cpu/start.S | 2 +- arch/x86/cpu/start16.S | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
PATCH 1/1 x86: use invd instead of wbinvd in real mode start code
In reply to Masahiro YamadaQuoted 5 lines · Masahiro Yamada
I do not know why the boot code immediately after the system reset should write-back the cache content. I think the cache invalidation should be enough.
Quoted 9 lines
I tested this commit with qemu-x86_defconfig, and it worked for me.
Signed-off-by Masahiro Yamada <[email protected]>---
arch/x86/cpu/start.S | 2 +- arch/x86/cpu/start16.S | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)
PATCH 1/1 x86: use invd instead of wbinvd in real mode start code
Quoted 12 lines · Bin Meng
Quoted 10 lines · Masahiro Yamada
I do not know why the boot code immediately after the system reset should write-back the cache content. I think the cache invalidation should be enough.
I tested this commit with qemu-x86_defconfig, and it worked for me.
Signed-off-by Masahiro Yamada <[email protected]>---
Quoted 7 lines
Quoted 4 lines
arch/x86/cpu/start.S | 2 +- arch/x86/cpu/start16.S | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-)Reviewed-by Bin Meng <[email protected]>Tested-by Bin Meng <[email protected]>
applied to u-boot-x86, thanks!