[PATCH 4/5] Reduce assembly code size of exception entry points

[PATCH 4/5] Reduce assembly code size of exception entry points

[Frediano Ziglio]

We just pushed a 8-bytes zero and exception constants are
small so we can just write a single byte saving 3 bytes for
instruction.
With ENDBR64 this reduces the size of the entry point from 32 to 16
bytes (due to alignment).

Signed-off-by: Frediano Ziglio <frediano.ziglio@cloud.com>
---
 xen/arch/x86/x86_64/entry.S | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/xen/arch/x86/x86_64/entry.S b/xen/arch/x86/x86_64/entry.S
index ecdd6e5b47..b6a157d96a 100644
--- a/xen/arch/x86/x86_64/entry.S
+++ b/xen/arch/x86/x86_64/entry.S
@@ -898,28 +898,28 @@ END(handle_exception)
 FUNC(entry_DE)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_DE, 4(%rsp)
+        movb  $X86_EXC_DE, 4(%rsp)
         jmp   handle_exception
 END(entry_DE)
 
 FUNC(entry_MF)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_MF, 4(%rsp)
+        movb  $X86_EXC_MF, 4(%rsp)
         jmp   handle_exception
 END(entry_MF)
 
 FUNC(entry_XM)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_XM, 4(%rsp)
+        movb  $X86_EXC_XM, 4(%rsp)
         jmp   handle_exception
 END(entry_XM)
 
 FUNC(entry_NM)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_NM, 4(%rsp)
+        movb  $X86_EXC_NM, 4(%rsp)
         jmp   handle_exception
 END(entry_NM)
 
@@ -933,28 +933,28 @@ END(entry_DB)
 FUNC(entry_BP)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_BP, 4(%rsp)
+        movb  $X86_EXC_BP, 4(%rsp)
         jmp   handle_exception
 END(entry_BP)
 
 FUNC(entry_OF)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_OF, 4(%rsp)
+        movb  $X86_EXC_OF, 4(%rsp)
         jmp   handle_exception
 END(entry_OF)
 
 FUNC(entry_BR)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_BR, 4(%rsp)
+        movb  $X86_EXC_BR, 4(%rsp)
         jmp   handle_exception
 END(entry_BR)
 
 FUNC(entry_UD)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_UD, 4(%rsp)
+        movb  $X86_EXC_UD, 4(%rsp)
         jmp   handle_exception
 END(entry_UD)
 
-- 
2.34.1

Re: [PATCH 4/5] Reduce assembly code size of exception entry points

[Jan Beulich]

On 05.02.2024 11:48, Frediano Ziglio wrote:
> We just pushed a 8-bytes zero and exception constants are
> small so we can just write a single byte saving 3 bytes for
> instruction.
> With ENDBR64 this reduces the size of the entry point from 32 to 16
> bytes (due to alignment).

Oh, good - when recently touching these entry points, I was thinking
of doing exactly this. Just didn't get to it, yet. However
- since using different size stores can raise performance concerns,
  I'd like to suggest that you mention the fact that we actually
  already have cases of this, in autogen_stubs,
- I'd further like to ask that this conversion then be done consistently
  everywhere, perhaps even including the storing of TRAP_syscall. I find
  it particularly puzzling that you ...

> --- a/xen/arch/x86/x86_64/entry.S
> +++ b/xen/arch/x86/x86_64/entry.S
> @@ -898,28 +898,28 @@ END(handle_exception)
>  FUNC(entry_DE)
>          ENDBR64
>          pushq $0
> -        movl  $X86_EXC_DE, 4(%rsp)
> +        movb  $X86_EXC_DE, 4(%rsp)
>          jmp   handle_exception
>  END(entry_DE)
>  
>  FUNC(entry_MF)
>          ENDBR64
>          pushq $0
> -        movl  $X86_EXC_MF, 4(%rsp)
> +        movb  $X86_EXC_MF, 4(%rsp)
>          jmp   handle_exception
>  END(entry_MF)
>  
>  FUNC(entry_XM)
>          ENDBR64
>          pushq $0
> -        movl  $X86_EXC_XM, 4(%rsp)
> +        movb  $X86_EXC_XM, 4(%rsp)
>          jmp   handle_exception
>  END(entry_XM)
>  
>  FUNC(entry_NM)
>          ENDBR64
>          pushq $0
> -        movl  $X86_EXC_NM, 4(%rsp)
> +        movb  $X86_EXC_NM, 4(%rsp)
>          jmp   handle_exception
>  END(entry_NM)
>  
> @@ -933,28 +933,28 @@ END(entry_DB)

... skip entry_DB here. And even ...

>  FUNC(entry_BP)
>          ENDBR64
>          pushq $0
> -        movl  $X86_EXC_BP, 4(%rsp)
> +        movb  $X86_EXC_BP, 4(%rsp)
>          jmp   handle_exception
>  END(entry_BP)
>  
>  FUNC(entry_OF)
>          ENDBR64
>          pushq $0
> -        movl  $X86_EXC_OF, 4(%rsp)
> +        movb  $X86_EXC_OF, 4(%rsp)
>          jmp   handle_exception
>  END(entry_OF)
>  
>  FUNC(entry_BR)
>          ENDBR64
>          pushq $0
> -        movl  $X86_EXC_BR, 4(%rsp)
> +        movb  $X86_EXC_BR, 4(%rsp)
>          jmp   handle_exception
>  END(entry_BR)
>  
>  FUNC(entry_UD)
>          ENDBR64
>          pushq $0
> -        movl  $X86_EXC_UD, 4(%rsp)
> +        movb  $X86_EXC_UD, 4(%rsp)
>          jmp   handle_exception
>  END(entry_UD)

... entry points below here, where an error code is pushed, will
have zero in the respective field, so these can be converted too.
And entry_NMI isn't any different either. Whereas entry_MC even
exactly matches the pattern you have been following, afaict.

Jan