Re: per-thread global variables

["J.A. Magallon" <jamagallon@able.es>]

On 2002.07.13 J.A. Magallon wrote:
>
>>
>>Which goes to show they weren't planning for clone like performance. A
>>single unshared page means two seperate mm structs, two sets of page
>>tables and switches causing TLB flushes. All because
>>
>>	movl %esp, %eax
>>	andl $ffff8000, %eax
>>	
>>and casting that is 'hard'
>>

It can be done even arch-independent (__builtin_frame_address is at least
since 2.96):

#include <sched.h>
#include <signal.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
#include <malloc.h>
#include <sys/user.h>

#define MAXT 4

// User definable
#define STACK_PAGES 8
#define PRIV_PAGES 1
//

#define STACK_SIZE (STACK_PAGES*PAGE_SIZE)
#define PRIV_SIZE (PRIV_PAGES*PAGE_SIZE)
#define TOTAL_PAGES (STACK_PAGES+PRIV_PAGES)
#define TOTAL_SIZE (TOTAL_PAGES*PAGE_SIZE)
#define TOTAL_MASK (~(TOTAL_SIZE-1))

void* getpriv();
#define self() (*(int*)getpriv())
#define setself(k) do { *(int*)getpriv() = k; } while(0)

int slave(void *arg);
void f();

int main(int argc,char** argv)
{
	void*	stack[MAXT];
	int		i;

	for (i=0; i<MAXT; i++)
	{
		stack[i] = memalign(TOTAL_SIZE,TOTAL_SIZE);
		clone(slave,stack[i]+STACK_SIZE-1,CLONE_VM|SIGCHLD,(void*)i);
	}
	for (i=0; i<MAXT; i++)
		wait(0);

	for (i=0; i<MAXT; i++)
		free(stack[i]);

	return 0;
}

void* getpriv()
{
	void* frame = __builtin_frame_address(0);
	void* priv = (void*)((unsigned long)frame&TOTAL_MASK);

	return priv+(ptrdiff_t)STACK_SIZE;
}

int slave(void *arg)
{
	setself((int)arg);
	printf("priv=%p\n",getpriv());
	printf("self=%d\n",self());

	f();

	return 0;
}

void f()
{
	printf("f self=%d\n",self());
}

Code for getpriv():

getpriv:
    pushl   %ebp
    subl    $8, %esp
    movl    %ebp, 4(%esp)
    movl    4(%esp), %eax
    andl    $-36864, %eax
    movl    %eax, (%esp)
    movl    (%esp), %eax
    addl    $32768, %eax
    addl    $8, %esp
    popl    %ebp
    ret

So it does not look too slow. I could do also sysconf(_SC_PAGESIZE), but
that adds a function call everywhere. Indeed it will be safer.

And you could fill private area before clone(), so children do not have to
worry about anything like setself(). Yup, it would be nicer...

Thanks for everything !!!

-- 
J.A. Magallon             \   Software is like sex: It's better when it's free
mailto:jamagallon@able.es  \                    -- Linus Torvalds, FSF T-shirt
Linux werewolf 2.4.19-rc1-jam3, Mandrake Linux 8.3 (Cooker) for i586
gcc (GCC) 3.1.1 (Mandrake Linux 8.3 3.1.1-0.7mdk)