x86: Add IRQ_TIME_ACCOUNTING

Commit: e82b8e4ea4f3dffe6e7939f90e78da675fcc450e upstream

This patch adds IRQ_TIME_ACCOUNTING option on x86 and runtime enables it
when TSC is enabled.

This change just enables fine grained irq time accounting, isn't used yet.
Following patches use it for different purposes.

Signed-off-by: Venkatesh Pallipadi <venki@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <1286237003-12406-6-git-send-email-venki@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 8d16a0013343d01fecc13ed9a8dd3d40210c5a8c..c840e7d6c4a46aff10fc344e5230b91a9d6a79b0 100644 (file)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2578,6 +2578,10 @@ and is between 256 and 4096 characters. It is defined in the file
                        disables clocksource verification at runtime.
                        Used to enable high-resolution timer mode on older
                        hardware, and in virtualized environment.
+                       [x86] noirqtime: Do not use TSC to do irq accounting.
+                       Used to run time disable IRQ_TIME_ACCOUNTING on any
+                       platforms where RDTSC is slow and this accounting
+                       can add overhead.
 
        turbografx.map[2|3]=    [HW,JOY]
                        TurboGraFX parallel port interface

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index cb5a57c610751cc58692cc80d1c8b24a29c7182b..73ae02a44cc2e79f23a8fb9d34735c8f5345caee 100644 (file)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -753,6 +753,17 @@ config SCHED_MC
          making when dealing with multi-core CPU chips at a cost of slightly
          increased overhead in some places. If unsure say N here.
 
+config IRQ_TIME_ACCOUNTING
+       bool "Fine granularity task level IRQ time accounting"
+       default n
+       ---help---
+         Select this option to enable fine granularity task irq time
+         accounting. This is done by reading a timestamp on each
+         transitions between softirq and hardirq state, so there can be a
+         small performance impact.
+
+         If in doubt, say N here.
+
 source "kernel/Kconfig.preempt"
 
 config X86_UP_APIC

diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index aaefa71888cbedde0947060496a38b4cbf63103b..bc0754350994ad9612c29010eee8241374027a58 100644 (file)
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -104,10 +104,14 @@ int __init notsc_setup(char *str)
 
 __setup("notsc", notsc_setup);
 
+static int no_sched_irq_time;
+
 static int __init tsc_setup(char *str)
 {
        if (!strcmp(str, "reliable"))
                tsc_clocksource_reliable = 1;
+       if (!strncmp(str, "noirqtime", 9))
+               no_sched_irq_time = 1;
        return 1;
 }
 
@@ -802,6 +806,7 @@ void mark_tsc_unstable(char *reason)
        if (!tsc_unstable) {
                tsc_unstable = 1;
                sched_clock_stable = 0;
+               disable_sched_clock_irqtime();
                printk(KERN_INFO "Marking TSC unstable due to %s\n", reason);
                /* Change only the rating, when not registered */
                if (clocksource_tsc.mult)
@@ -990,6 +995,9 @@ void __init tsc_init(void)
        /* now allow native_sched_clock() to use rdtsc */
        tsc_disabled = 0;
 
+       if (!no_sched_irq_time)
+               enable_sched_clock_irqtime();
+
        lpj = ((u64)tsc_khz * 1000);
        do_div(lpj, HZ);
        lpj_fine = lpj;