Re: [RFC Patch]Use ar.kr2 for smp_processor_id

From: Keith Owens <kaos_at_sgi.com>
Date: 2007-02-08 19:40:43
Zou Nan hai (on 08 Feb 2007 13:11:49 +0800) wrote:
>On Thu, 2007-02-08 at 14:55, Keith Owens wrote:
>> Keith Owens (on Thu, 08 Feb 2007 17:37:54 +1100) wrote:
>> Correction: ar.k3 contains the physical address of the per-cpu data
>> area, virtual access to per-cpu data goes via the cpu local TLB and
>> does not rely on an ar.k<n> variable.  ar.k3 is used in the MCA
>> assembler handler, see GET_THIS_PADDR in include/asm-ia64/mca_asm.h
>> and
>> arch/ia64/kernel/mca_asm.S.
>> 
>
> Since MCA is slow path, 
> so I think put smp_processor_id in ar.kr3 is a gain.
>
> We could even optimize get_cpu_var based on this...

(1) Somebody else (not me) gets to fix up and test the MCA handler
    assembler code - lots of luck.

(2) smp_processor_id() in the IA64 kernel is accessed via struct
    thread_info.cpu.  That maps to a simple memory access with code
    like this:

       adds r14=3252,r13
       ;;
       ld4 r15=[r14]

    The stop bits usually get amortized away with other code.
    thread_info.cpu will normally be cached in L1 so reading
    smp_processor_id() is relatively fast.

(3) Reading smp_processor_id() from ar.k3 in the kernel is 10 times
    slower than the existing kernel code.  See the timing program
    below.

(4) If the justification for storing cpu number in ar.k<n> is to speed
    up user space, how can user space tell if the current kernel stores
    the physical address of the per-cpu data in k3 or if it stores the
    cpu number in k3?  Detecting which variant of the kernel is running
    will slow down user space.


Timing results on 'modprobe measure'

init_measure: empty_loop 2000007 cpu_loop 3000011 k3_loop 11999992

module measure.c

-----------------------------------------------------------------------

#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/preempt.h>
#include <asm/kregs.h>
#include <asm/timex.h>

MODULE_LICENSE("GPL");

#define LOOPS 1000000

static int __init init_measure(void)
{
	int loop;
	register int cpu;
	unsigned long start, end, empty_loop, cpu_loop, k3_loop;
	printk("%s: start\n", __FUNCTION__);
	preempt_disable();

	local_irq_disable();
	start = get_cycles();
	barrier();
	for (loop = 0; loop < LOOPS; ++loop) {
		/* ensure that all loops are the same size (2 bundles) */
		asm volatile ("nop 0; nop 0; nop 0;");
		barrier();
	};
	end = get_cycles();
	barrier();
	local_irq_enable();
	empty_loop = end - start;

	local_irq_disable();
	start = get_cycles();
	barrier();
	for (loop = 0; loop < LOOPS; ++loop) {
		/* hand code the read of smp_processor_id() to stop gcc moving
		 * the address calculation outside the loop
		 */
		asm volatile ("adds r14=%0,r13"
			      ";;"
			      "ld4 r15=[r14]"
			      : :
			      "i" (IA64_TASK_SIZE + offsetof(struct thread_info, cpu)) :
			      "r14", "r15" );
		barrier();
	};
	end = get_cycles();
	barrier();
	local_irq_enable();
	cpu_loop = end - start;

	local_irq_disable();
	start = get_cycles();
	barrier();
	for (loop = 0; loop < LOOPS; ++loop) {
		cpu = ia64_get_kr(IA64_KR_PER_CPU_DATA);
		barrier();
	};
	end = get_cycles();
	barrier();
	local_irq_enable();
	k3_loop = end - start;

	preempt_enable();
	printk("%s: empty_loop %ld cpu_loop %ld k3_loop %ld\n", __FUNCTION__, empty_loop, cpu_loop, k3_loop);
	return 0;
}

static void __exit exit_measure(void)
{
	printk("%s: start\n", __FUNCTION__);
	printk("%s: end\n", __FUNCTION__);
}

module_init(init_measure)
module_exit(exit_measure)

-----------------------------------------------------------------------

objdump of the interesting bits (the three loops):

empty loop:

  40:	09 08 00 50 00 21 	[MMI]       mov r1=r40
  46:	00 00 00 02 00 e0 	            nop.m 0x0
  4c:	81 6c 64 84       	            adds r15=3272,r13;;
  50:	0a 18 00 1e 10 10 	[MMI]       ld4 r3=[r15];;
  56:	20 08 0c 00 42 00 	            adds r2=1,r3
  5c:	00 00 04 00       	            nop.i 0x0
  60:	0b 00 00 00 01 00 	[MMI]       nop.m 0x0;;
  66:	00 10 3c 20 23 00 	            st4 [r15]=r2
  6c:	00 00 04 00       	            nop.i 0x0;;
  70:	0b 00 00 02 07 00 	[MMI]       rsm 0x4000;;
  76:	50 02 b0 44 08 00 	            mov.m r37=ar.itc
  7c:	00 00 04 00       	            nop.i 0x0;;
  80:	0b 70 fc 78 84 24 	[MMI]       mov r14=999999;;
  86:	00 00 00 02 00 00 	            nop.m 0x0
  8c:	e0 08 aa 00       	            mov.i ar.lc=r14;;
  90:	01 00 00 00 01 00 	[MII]       nop.m 0x0
  96:	00 00 00 02 00 00 	            nop.i 0x0
  9c:	00 00 04 00       	            nop.i 0x0;;
  a0:	10 00 00 00 01 00 	[MIB]       nop.m 0x0
  a6:	00 00 00 02 00 a0 	            nop.i 0x0
  ac:	f0 ff ff 48       	            br.cloop.sptk.few 90 <init_module+0x90>
  b0:	0b 20 01 58 22 04 	[MMI]       mov.m r36=ar.itc;;
  b6:	00 00 04 0c 00 00 	            ssm 0x4000
  bc:	00 00 04 00       	            nop.i 0x0;;
  c0:	0b 00 00 00 30 00 	[MMI]       srlz.d;;

Read smp_processor_id:

  c6:	00 00 04 0e 00 00 	            rsm 0x4000
  cc:	00 00 04 00       	            nop.i 0x0;;
  d0:	01 18 01 58 22 04 	[MII]       mov.m r35=ar.itc
  d6:	00 00 00 02 00 00 	            nop.i 0x0
  dc:	00 00 04 00       	            nop.i 0x0;;
  e0:	0a 40 fc 78 84 24 	[MMI]       mov r8=999999;;
  e6:	00 00 00 02 00 00 	            nop.m 0x0
  ec:	80 08 aa 00       	            mov.i ar.lc=r8
  f0:	0b 70 d0 1a 19 21 	[MMI]       adds r14=3252,r13;;
  f6:	f0 00 38 20 20 00 	            ld4 r15=[r14]
  fc:	00 00 04 00       	            nop.i 0x0;;
 100:	10 00 00 00 01 00 	[MIB]       nop.m 0x0
 106:	00 00 00 02 00 a0 	            nop.i 0x0
 10c:	f0 ff ff 48       	            br.cloop.sptk.few f0 <init_module+0xf0>
 110:	0b 10 01 58 22 04 	[MMI]       mov.m r34=ar.itc;;
 116:	00 00 04 0c 00 00 	            ssm 0x4000
 11c:	00 00 04 00       	            nop.i 0x0;;
 120:	0b 00 00 00 30 00 	[MMI]       srlz.d;;

Read ar.k3:

 126:	00 00 04 0e 00 00 	            rsm 0x4000
 12c:	00 00 04 00       	            nop.i 0x0;;
 130:	01 08 01 58 22 04 	[MII]       mov.m r33=ar.itc
 136:	00 00 00 02 00 00 	            nop.i 0x0
 13c:	00 00 04 00       	            nop.i 0x0;;
 140:	0a 48 fc 78 84 24 	[MMI]       mov r9=999999;;
 146:	00 00 00 02 00 00 	            nop.m 0x0
 14c:	90 08 aa 00       	            mov.i ar.lc=r9
 150:	01 70 00 06 22 04 	[MII]       mov.m r14=ar.k3
 156:	00 00 00 02 00 00 	            nop.i 0x0
 15c:	00 00 04 00       	            nop.i 0x0;;
 160:	10 00 00 00 01 00 	[MIB]       nop.m 0x0
 166:	00 00 00 02 00 a0 	            nop.i 0x0
 16c:	f0 ff ff 48       	            br.cloop.sptk.few 150 <init_module+0x150>
 170:	0b 00 01 58 22 04 	[MMI]       mov.m r32=ar.itc;;
 176:	00 00 04 0c 00 00 	            ssm 0x4000
 17c:	00 00 04 00       	            nop.i 0x0;;
 180:	01 00 00 00 30 00 	[MII]       srlz.d

-
To unsubscribe from this list: send the line "unsubscribe linux-ia64" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Received on Thu Feb 08 21:29:32 2007

This archive was generated by hypermail 2.1.8 : 2007-02-08 21:30:22 EST