On Mon, Aug 13, 2012 at 07:04:02PM +0200, Borislav Petkov wrote:

On Mon, Aug 13, 2012 at 02:43:34PM +0300, Kirill A. Shutemov wrote:

quoted

$ cat test.c
#include <stdio.h>
#include <sys/mman.h>

#define SIZE 1024*1024*1024

void clear_page_nocache_sse2(void *page) __attribute__((regparm(1)));

int main(int argc, char** argv)
{
        char *p;
        unsigned long i, j;

        p = mmap(NULL, SIZE, PROT_WRITE|PROT_READ,
                        MAP_PRIVATE|MAP_ANONYMOUS|MAP_POPULATE, -1, 0);
        for(j = 0; j < 100; j++) {
                for(i = 0; i < SIZE; i += 4096) {
                        clear_page_nocache_sse2(p + i);
                }
        }

        return 0;
}
$ cat clear_page_nocache_unroll32.S
.globl clear_page_nocache_sse2
.align 4,0x90
clear_page_nocache_sse2:
.cfi_startproc
        mov    %eax,%edx
        xorl   %eax,%eax
        movl   $4096/32,%ecx
        .p2align 4
.Lloop_sse2:
        decl    %ecx
#define PUT(x) movnti %eax,x*4(%edx)
        PUT(0)
        PUT(1)
        PUT(2)
        PUT(3)
        PUT(4)
        PUT(5)
        PUT(6)
        PUT(7)
#undef PUT
        lea     32(%edx),%edx
        jnz     .Lloop_sse2
        nop
        ret
.cfi_endproc
.type clear_page_nocache_sse2, @function
.size clear_page_nocache_sse2, .-clear_page_nocache_sse2
$ cat clear_page_nocache_unroll64.S
.globl clear_page_nocache_sse2
.align 4,0x90
clear_page_nocache_sse2:
.cfi_startproc
        mov    %eax,%edx

This must still be the 32-bit version becaue it segfaults here.

Yes, it's test for 32-bit version.

-- 
 Kirill A. Shutemov