LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Andi Kleen <ak@suse.de>
To: Stephane Eranian <eranian@hpl.hp.com>,
	patches@x86-64.org, linux-kernel@vger.kernel.org
Subject: [PATCH x86 for review II] [4/39] i386: add idle notifier
Date: Mon, 12 Feb 2007 08:37:50 +0100 (CET)	[thread overview]
Message-ID: <20070212073750.3DBD013D7F@wotan.suse.de> (raw)
In-Reply-To: <20070212837.963446000@suse.de>


From: Stephane Eranian <eranian@hpl.hp.com>

Add a notifier mechanism to the low level idle loop.  You can register a
callback function which gets invoked on entry and exit from the low level idle
loop.  The low level idle loop is defined as the polling loop, low-power call,
or the mwait instruction.  Interrupts processed by the idle thread are not
considered part of the low level loop.

The notifier can be used to measure precisely how much is spent in useless
execution (or low power mode).  The perfmon subsystem uses it to turn on/off
monitoring.

Signed-off-by: stephane eranian <eranian@hpl.hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Andi Kleen <ak@suse.de>

---

 arch/i386/kernel/apic.c          |    4 ++
 arch/i386/kernel/cpu/mcheck/p4.c |    2 +
 arch/i386/kernel/irq.c           |    3 ++
 arch/i386/kernel/process.c       |   53 ++++++++++++++++++++++++++++++++++++++-
 arch/i386/kernel/smp.c           |    2 +
 include/asm-i386/idle.h          |   14 ++++++++++
 include/asm-i386/processor.h     |    8 +++++
 7 files changed, 85 insertions(+), 1 deletion(-)

Index: linux/arch/i386/kernel/apic.c
===================================================================
--- linux.orig/arch/i386/kernel/apic.c
+++ linux/arch/i386/kernel/apic.c
@@ -36,6 +36,7 @@
 #include <asm/hpet.h>
 #include <asm/i8253.h>
 #include <asm/nmi.h>
+#include <asm/idle.h>
 
 #include <mach_apic.h>
 #include <mach_apicdef.h>
@@ -1255,6 +1256,7 @@ fastcall void smp_apic_timer_interrupt(s
 	 * Besides, if we don't timer interrupts ignore the global
 	 * interrupt lock, which is the WrongThing (tm) to do.
 	 */
+	exit_idle();
 	irq_enter();
 	smp_local_timer_interrupt();
 	irq_exit();
@@ -1305,6 +1307,7 @@ fastcall void smp_spurious_interrupt(str
 {
 	unsigned long v;
 
+	exit_idle();
 	irq_enter();
 	/*
 	 * Check if this really is a spurious interrupt and ACK it
@@ -1329,6 +1332,7 @@ fastcall void smp_error_interrupt(struct
 {
 	unsigned long v, v1;
 
+	exit_idle();
 	irq_enter();
 	/* First tickle the hardware, only then report what went on. -- REW */
 	v = apic_read(APIC_ESR);
Index: linux/arch/i386/kernel/cpu/mcheck/p4.c
===================================================================
--- linux.orig/arch/i386/kernel/cpu/mcheck/p4.c
+++ linux/arch/i386/kernel/cpu/mcheck/p4.c
@@ -12,6 +12,7 @@
 #include <asm/system.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
+#include <asm/idle.h>
 
 #include <asm/therm_throt.h>
 
@@ -59,6 +60,7 @@ static void (*vendor_thermal_interrupt)(
 
 fastcall void smp_thermal_interrupt(struct pt_regs *regs)
 {
+	exit_idle();
 	irq_enter();
 	vendor_thermal_interrupt(regs);
 	irq_exit();
Index: linux/arch/i386/kernel/irq.c
===================================================================
--- linux.orig/arch/i386/kernel/irq.c
+++ linux/arch/i386/kernel/irq.c
@@ -19,6 +19,8 @@
 #include <linux/cpu.h>
 #include <linux/delay.h>
 
+#include <asm/idle.h>
+
 DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_internodealigned_in_smp;
 EXPORT_PER_CPU_SYMBOL(irq_stat);
 
@@ -61,6 +63,7 @@ fastcall unsigned int do_IRQ(struct pt_r
 	union irq_ctx *curctx, *irqctx;
 	u32 *isp;
 #endif
+	exit_idle();
 
 	if (unlikely((unsigned)irq >= NR_IRQS)) {
 		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",
Index: linux/arch/i386/kernel/process.c
===================================================================
--- linux.orig/arch/i386/kernel/process.c
+++ linux/arch/i386/kernel/process.c
@@ -48,6 +48,7 @@
 #include <asm/i387.h>
 #include <asm/desc.h>
 #include <asm/vm86.h>
+#include <asm/idle.h>
 #ifdef CONFIG_MATH_EMULATION
 #include <asm/math_emu.h>
 #endif
@@ -80,6 +81,42 @@ void (*pm_idle)(void);
 EXPORT_SYMBOL(pm_idle);
 static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
 
+static ATOMIC_NOTIFIER_HEAD(idle_notifier);
+
+void idle_notifier_register(struct notifier_block *n)
+{
+	atomic_notifier_chain_register(&idle_notifier, n);
+}
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+	atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+
+static DEFINE_PER_CPU(volatile unsigned long, idle_state);
+
+void enter_idle(void)
+{
+	/* needs to be atomic w.r.t. interrupts, not against other CPUs */
+	__set_bit(0, &__get_cpu_var(idle_state));
+	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
+}
+
+static void __exit_idle(void)
+{
+	/* needs to be atomic w.r.t. interrupts, not against other CPUs */
+	if (__test_and_clear_bit(0, &__get_cpu_var(idle_state)) == 0)
+		return;
+	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
+}
+
+void exit_idle(void)
+{
+	if (current->pid)
+		return;
+	__exit_idle();
+}
+
 void disable_hlt(void)
 {
 	hlt_counter++;
@@ -130,6 +167,7 @@ EXPORT_SYMBOL(default_idle);
  */
 static void poll_idle (void)
 {
+	local_irq_enable();
 	cpu_relax();
 }
 
@@ -189,7 +227,16 @@ void cpu_idle(void)
 				play_dead();
 
 			__get_cpu_var(irq_stat).idle_timestamp = jiffies;
+
+			/*
+			 * Idle routines should keep interrupts disabled
+			 * from here on, until they go to idle.
+			 * Otherwise, idle callbacks can misfire.
+			 */
+			local_irq_disable();
+			enter_idle();
 			idle();
+			__exit_idle();
 		}
 		preempt_enable_no_resched();
 		schedule();
@@ -243,7 +290,11 @@ void mwait_idle_with_hints(unsigned long
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();
 		if (!need_resched())
-			__mwait(eax, ecx);
+			__sti_mwait(eax, ecx);
+		else
+			local_irq_enable();
+	} else {
+		local_irq_enable();
 	}
 }
 
Index: linux/arch/i386/kernel/smp.c
===================================================================
--- linux.orig/arch/i386/kernel/smp.c
+++ linux/arch/i386/kernel/smp.c
@@ -23,6 +23,7 @@
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
+#include <asm/idle.h>
 #include <mach_apic.h>
 
 /*
@@ -624,6 +625,7 @@ fastcall void smp_call_function_interrup
 	/*
 	 * At this point the info structure may be out of scope unless wait==1
 	 */
+	exit_idle();
 	irq_enter();
 	(*func)(info);
 	irq_exit();
Index: linux/include/asm-i386/idle.h
===================================================================
--- /dev/null
+++ linux/include/asm-i386/idle.h
@@ -0,0 +1,14 @@
+#ifndef _ASM_I386_IDLE_H
+#define _ASM_I386_IDLE_H 1
+
+#define IDLE_START 1
+#define IDLE_END 2
+
+struct notifier_block;
+void idle_notifier_register(struct notifier_block *n);
+void idle_notifier_unregister(struct notifier_block *n);
+
+void exit_idle(void);
+void enter_idle(void);
+
+#endif
Index: linux/include/asm-i386/processor.h
===================================================================
--- linux.orig/include/asm-i386/processor.h
+++ linux/include/asm-i386/processor.h
@@ -257,6 +257,14 @@ static inline void __mwait(unsigned long
 		: :"a" (eax), "c" (ecx));
 }
 
+static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
+{
+	/* "mwait %eax,%ecx;" */
+	asm volatile(
+		"sti; .byte 0x0f,0x01,0xc9;"
+		: :"a" (eax), "c" (ecx));
+}
+
 extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
 
 /* from system description table in BIOS.  Mostly for MCA use, but

  parent reply	other threads:[~2007-02-12  7:50 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-02-12  7:37 [PATCH x86 for review II] [1/39] i386: move startup_32() in text.head section Andi Kleen
2007-02-12  7:37 ` [PATCH x86 for review II] [2/39] x86_64: Break init() in two parts to avoid MODPOST warnings Andi Kleen
2007-02-12  7:37 ` [PATCH x86 for review II] [3/39] i386: arch/i386/kernel/cpu/mcheck/mce.c should #include <asm/mce.h> Andi Kleen
2007-02-12  7:37 ` Andi Kleen [this message]
2007-02-12  7:37 ` [PATCH x86 for review II] [5/39] i386: improve sched_clock() on i686 Andi Kleen
2007-02-12  7:37 ` [PATCH x86 for review II] [6/39] i386: romsignature/checksum cleanup Andi Kleen
2007-02-12  7:37 ` [PATCH x86 for review II] [7/39] x86_64: Fix fake numa for x86_64 machines with big IO hole Andi Kleen
2007-02-12  7:37 ` [PATCH x86 for review II] [8/39] x86_64: Remove fastcall references in x86_64 code Andi Kleen
2007-02-12  7:37 ` [PATCH x86 for review II] [9/39] x86_64: Use constant instead of raw number in x86_64 ioperm.c Andi Kleen
2007-02-12  7:37 ` [PATCH x86 for review II] [10/39] x86_64: Handle 32 bit PerfMon Counter writes cleanly in x86_64 nmi_watchdog Andi Kleen
2007-02-12  7:37 ` [PATCH x86 for review II] [11/39] i386: Handle 32 bit PerfMon Counter writes cleanly in i386 nmi_watchdog Andi Kleen
2007-02-12  7:37 ` [PATCH x86 for review II] [12/39] i386: Handle 32 bit PerfMon Counter writes cleanly in oprofile Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [13/39] i386: CONFIG_PHYSICAL_ALIGN limited to 4M? Andi Kleen
2007-02-13  6:36   ` Rene Herman
2007-02-12  7:38 ` [PATCH x86 for review II] [14/39] x86_64: cleanup Doc/x86_64/ files Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [15/39] x86_64: list x86_64 quilt tree Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [16/39] x86: simplify notify_page_fault() Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [17/39] x86_64: Tighten mce_amd driver MSR reads Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [18/39] x86_64: Allow to run a program when a machine check event is detected Andi Kleen
2007-02-12  7:54   ` Oliver Neukum
2007-02-12  8:04     ` Andi Kleen
2007-02-12  8:11       ` Bauke Jan Douma
2007-02-12 15:05       ` [patches] " Pavel Machek
2007-02-12  7:38 ` [PATCH x86 for review II] [19/39] x86_64: remove get_pmd() Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [20/39] i386: Small cleanup to TLB flush code Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [21/39] i386: rdmsr_on_cpu, wrmsr_on_cpu Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [22/39] x86_64: Kconfig typos Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [23/39] i386: use smp_call_function_single() Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [24/39] " Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [25/39] x86_64: Fix preprocessor condition Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [26/39] i386: fix 32-bit ioctls on x64_32 Andi Kleen
2007-02-12 13:24   ` Giuliano Procida
2007-02-12 22:28     ` Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [27/39] i386: APM on i386 Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [28/39] i386: fix size_or_mask and size_and_mask Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [29/39] x86_64: - Ignore long SMI interrupts in clock calibration code - update 1 Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [30/39] x86_64: Check return value of putreg in PTRACE_SETREGS Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [31/39] x86_64: Unexport __supported_pte_mask Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [32/39] x86_64: x86_64 - Fix FS/GS registers for VT execution Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [33/39] x86_64: Fix off by one error in IOMMU boundary checking Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [34/39] i386: Use stack arguments for calling into EFI Andi Kleen
2007-02-12 19:45   ` Frédéric RISS
2007-02-12  7:38 ` [PATCH x86 for review II] [35/39] x86_64: Don't reserve ROMs Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [36/39] x86_64: define dma noncoherent API functions Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [37/39] x86_64: robustify bad_dma_address handling Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [38/39] x86: fix laptop bootup hang in init_acpi() Andi Kleen
2007-02-12  7:38 ` [PATCH x86 for review II] [39/39] i386: All Transmeta CPUs have constant TSCs Andi Kleen

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=20070212073750.3DBD013D7F@wotan.suse.de \
    --to=ak@suse.de \
    --cc=eranian@hpl.hp.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=patches@x86-64.org \
    --subject='Re: [PATCH x86 for review II] [4/39] i386: add idle notifier' \
    /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

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).