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>
Signed-off-by: Andi Kleen <ak@linux.intel.com>
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 c74ff6f980dc050e89ff009c350211f4bebc0e87..713c58944da6a3962ee4c552d7ce16cbecf8f727 100644 (file)
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2672,6 +2672,10 @@ 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 f942bb713a3d96c2c1e348760a7c3208db519807..d2b82109a3fac18ddbcd29cda53a38649e6f6274 100644 (file)
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -797,6 +797,17 @@ 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 4094ae0fac3cd10372256e0560a64f392a9bd3ff..97cdbe8b732cd3bf1b8a50a1af5334ce1f0cd7d7 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;