From: Rusty Russell <rusty@rustcorp.com.au>
To: Andi Kleen <ak@muc.de>
Cc: lkml - Kernel Mailing List <linux-kernel@vger.kernel.org>,
virtualization <virtualization@lists.osdl.org>,
Jeremy Fitzhardinge <jeremy@goop.org>
Subject: [PATCH 6/7] (Optional) implement smp_processor_id() as a per-cpu var
Date: Fri, 22 Sep 2006 22:00:51 +1000 [thread overview]
Message-ID: <1158926451.26261.18.camel@localhost.localdomain> (raw)
In-Reply-To: <1158926386.26261.17.camel@localhost.localdomain>
This implements smp_processor_id() as a per-cpu variable. The generic
code expects it in thread_info still, so we can't remove it from
there, but reducing smp_processor_id() from 9 bytes/3 insns to 6
bytes/1 insn is a nice micro-optimization.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Index: ak-pda-gs/arch/i386/kernel/smpboot.c
===================================================================
--- ak-pda-gs.orig/arch/i386/kernel/smpboot.c 2006-09-20 19:55:07.000000000 +1000
+++ ak-pda-gs/arch/i386/kernel/smpboot.c 2006-09-20 22:36:06.000000000 +1000
@@ -105,6 +105,9 @@
DEFINE_PER_CPU(unsigned long, this_cpu_off);
EXPORT_PER_CPU_SYMBOL(this_cpu_off);
+DEFINE_PER_CPU(u32, processor_id);
+EXPORT_PER_CPU_SYMBOL(processor_id);
+
/*
* Trampoline 80x86 program as an array.
*/
@@ -1355,6 +1358,7 @@
struct Xgt_desc_struct *cpu_gdt_descr = &per_cpu(cpu_gdt_descr, cpu);
per_cpu(this_cpu_off, cpu) = __per_cpu_offset[cpu];
+ per_cpu(processor_id, cpu) = cpu;
setup_percpu_descriptor(&gdt[GDT_ENTRY_PERCPU], __per_cpu_offset[cpu]);
cpu_gdt_descr->address = (unsigned long)gdt;
cpu_gdt_descr->size = GDT_SIZE - 1;
Index: ak-pda-gs/include/asm-i386/smp.h
===================================================================
--- ak-pda-gs.orig/include/asm-i386/smp.h 2006-09-20 20:20:50.000000000 +1000
+++ ak-pda-gs/include/asm-i386/smp.h 2006-09-20 22:36:22.000000000 +1000
@@ -8,6 +8,7 @@
#include <linux/kernel.h>
#include <linux/threads.h>
#include <linux/cpumask.h>
+#include <asm/percpu.h>
#endif
#ifdef CONFIG_X86_LOCAL_APIC
@@ -56,7 +57,8 @@
* from the initial startup. We map APIC_BASE very early in page_setup(),
* so this is correct in the x86 case.
*/
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+DECLARE_PER_CPU(u32, processor_id);
+#define raw_smp_processor_id() x86_read_percpu(processor_id)
extern cpumask_t cpu_callout_map;
extern cpumask_t cpu_callin_map;
Index: ak-pda-gs/arch/i386/kernel/cpu/common.c
===================================================================
--- ak-pda-gs.orig/arch/i386/kernel/cpu/common.c 2006-09-20 21:28:28.000000000 +1000
+++ ak-pda-gs/arch/i386/kernel/cpu/common.c 2006-09-20 22:37:17.000000000 +1000
@@ -597,7 +597,7 @@
*/
void __cpuinit cpu_init(void)
{
- int cpu = smp_processor_id();
+ unsigned int cpu = current->thread_info->cpu;
struct tss_struct * t = &per_cpu(init_tss, cpu);
struct thread_struct *thread = ¤t->thread;
struct desc_struct *gdt;
--
Help! Save Australia from the worst of the DMCA: http://linux.org.au/law
next prev parent reply other threads:[~2006-09-22 12:00 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2006-09-22 11:51 [PATCH 0/7] Using %gs for per-cpu areas on x86 Rusty Russell
2006-09-22 11:53 ` [PATCH 1/7] Use per-cpu GDT tables from early in boot Rusty Russell
2006-09-22 11:55 ` [PATCH 2/7] Rusty Russell
2006-09-22 11:56 ` [PATCH 3/7] Update sys_vm86 to cope with changed pt_regs and %gs usage Rusty Russell
2006-09-22 11:58 ` [PATCH 4/7] Fix places where using %gs changes the usermode ABI Rusty Russell
2006-09-22 11:59 ` [PATCH 5/7] Use %gs for per-cpu sections in kernel Rusty Russell
2006-09-22 12:00 ` Rusty Russell [this message]
2006-09-22 12:01 ` [PATCH 7/7] (Optional) implement current as a per-cpu var Rusty Russell
2006-09-25 5:29 ` Rusty Russell
2006-09-25 5:27 ` [PATCH 6/7] (Optional) implement smp_processor_id() " Rusty Russell
2006-09-22 12:32 ` [PATCH 5/7] Use %gs for per-cpu sections in kernel Andi Kleen
2006-09-22 22:43 ` Jeremy Fitzhardinge
2006-09-22 23:52 ` Andi Kleen
2006-09-23 4:51 ` Rusty Russell
2006-09-23 8:17 ` Andi Kleen
2006-09-23 8:55 ` Rusty Russell
2006-09-22 22:39 ` Jeremy Fitzhardinge
2006-09-23 4:31 ` Rusty Russell
2006-09-25 1:03 ` Jeremy Fitzhardinge
2006-09-25 1:16 ` Rusty Russell
2006-09-25 1:36 ` Jeremy Fitzhardinge
2006-09-25 2:51 ` Rusty Russell
2006-09-25 5:25 ` Jeremy Fitzhardinge
2006-09-25 6:03 ` Rusty Russell
2006-09-25 6:25 ` Jeremy Fitzhardinge
2006-09-25 23:33 ` Rusty Russell
2006-09-23 8:13 ` Andi Kleen
2006-09-25 1:07 ` Jeremy Fitzhardinge
2006-09-25 1:20 ` Rusty Russell
2006-09-25 5:26 ` Rusty Russell
2006-09-22 22:24 ` [PATCH 2/7] Jeremy Fitzhardinge
2006-09-23 4:36 ` Rusty Russell
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1158926451.26261.18.camel@localhost.localdomain \
--to=rusty@rustcorp.com.au \
--cc=ak@muc.de \
--cc=jeremy@goop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=virtualization@lists.osdl.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).