x86: align per-cpu section to configured cache bytes

This matches the fix for a bug seen on x86-64.  Test booted on old hardware
that had 32 byte cachelines to begin with.

Signed-off-by: Zach Brown <zach.brown@oracle.com>
Signed-off-by: Sam Ravnborg <sam@ravnborg.org>

arch/i386/kernel/vmlinux.lds.S

@@ -7,6 +7,7 @@
 #include <asm-generic/vmlinux.lds.h>
 #include <asm/thread_info.h>
 #include <asm/page.h>
+#include <asm/cache.h>
 
 OUTPUT_FORMAT("elf32-i386", "elf32-i386", "elf32-i386")
 OUTPUT_ARCH(i386)
@@ -115,7 +116,7 @@ SECTIONS
   __initramfs_start = .;
   .init.ramfs : AT(ADDR(.init.ramfs) - LOAD_OFFSET) { *(.init.ramfs) }
   __initramfs_end = .;
-  . = ALIGN(32);
+  . = ALIGN(L1_CACHE_BYTES);
   __per_cpu_start = .;
   .data.percpu  : AT(ADDR(.data.percpu) - LOAD_OFFSET) { *(.data.percpu) }
   __per_cpu_end = .;