[Xen-devel] [PATCH 5/5] x86/boot: Move/copy sections more efficiently

[Andrew Cooper <andrew.cooper3@xxxxxxxxxx>]

Both the trampoline copy and BSS initialise can be performed more efficiently
by using 4-byte varients of the string operations.

The ALIGN(STACK_SIZE) actually belongs with .bss.stack_aligned, but __init_end
still needs page alignment because of the init sections being freed and
returned to the domheap after boot.

Signed-off-by: Andrew Cooper <andrew.cooper3@xxxxxxxxxx>
CC: Jan Beulich <JBeulich@xxxxxxxx>
---
 xen/arch/x86/boot/head.S |    9 +++++----
 xen/arch/x86/xen.lds.S   |    5 ++++-
 2 files changed, 9 insertions(+), 5 deletions(-)

diff --git a/xen/arch/x86/boot/head.S b/xen/arch/x86/boot/head.S
index cfd59dc..604c515 100644
--- a/xen/arch/x86/boot/head.S
+++ b/xen/arch/x86/boot/head.S
@@ -128,7 +128,8 @@ __start:
         mov     $sym_phys(__bss_end),%ecx
         sub     %edi,%ecx
         xor     %eax,%eax
-        rep     stosb
+        shr     $2,%ecx
+        rep     stosl
 
         /* Interrogate CPU extended features via CPUID. */
         mov     $0x80000000,%eax
@@ -198,8 +199,8 @@ __start:
 
         /* Copy bootstrap trampoline to low memory, below 1MB. */
         mov     $sym_phys(trampoline_start),%esi
-        mov     $trampoline_end - trampoline_start,%ecx
-        rep     movsb
+        mov     $((trampoline_end - trampoline_start) / 4),%ecx
+        rep     movsl
 
         /* Jump into the relocated trampoline. */
         lret
@@ -211,6 +212,6 @@ reloc:
 
 ENTRY(trampoline_start)
 #include "trampoline.S"
-GLOBAL(trampoline_end)
+ENTRY(trampoline_end)
 
 #include "x86_64.S"
diff --git a/xen/arch/x86/xen.lds.S b/xen/arch/x86/xen.lds.S
index 8295ecf..b49c031 100644
--- a/xen/arch/x86/xen.lds.S
+++ b/xen/arch/x86/xen.lds.S
@@ -153,11 +153,13 @@ SECTIONS
        __xsm_initcall_start = .;
        *(.xsm_initcall.init)
        __xsm_initcall_end = .;
+
+       . = ALIGN(PAGE_SIZE);
   } :text
-  . = ALIGN(STACK_SIZE);
   __init_end = .;
 
   .bss : {                     /* BSS */
+       . = ALIGN(STACK_SIZE);
        __bss_start = .;
        *(.bss.stack_aligned)
        . = ALIGN(PAGE_SIZE);
@@ -170,6 +172,7 @@ SECTIONS
        *(.bss.percpu.read_mostly)
        . = ALIGN(SMP_CACHE_BYTES);
        __per_cpu_data_end = .;
+       . = ALIGN(8);
        __bss_end = .;
   } :text
   _end = . ;
-- 
1.7.10.4


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel