| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1328808329-27427-1-git-send-email-dmitry.antipov@linaro.org>
Date: Thu, 9 Feb 2012 09:25:29 -0800
From: Dmitry Antipov <dmitry.antipov@...aro.org>
To: linux-kernel@...r.kernel.org
Cc: Russell King <linux@....linux.org.uk>,
Rusty Russell <rusty@...tcorp.com.au>,
Ingo Molnar <mingo@...hat.com>,
Yong Zhang <yong.zhang0@...il.com>,
Venki Pallipadi <venki@...gle.com>, x86@...nel.org,
linux-arm-kernel@...ts.infradead.org, linaro-dev@...ts.linaro.org,
patches@...aro.org, Dmitry Antipov <dmitry.antipov@...aro.org>
Subject: [PATCH] sched: generalize CONFIG_IRQ_TIME_ACCOUNTING for X86 and ARM
Generalize CONFIG_IRQ_TIME_ACCOUNTING between X86 and
ARM, move "noirqtime=" option to common debugging code.
For a bit of backward compatibility, X86-specific option
"tsc=noirqtime" is preserved, but issues a warning.
Suggested-by: Yong Zhang <yong.zhang0@...il.com>
Suggested-by: Russell King <rmk+kernel@....linux.org.uk>
Suggested-by: Venki Pallipadi <venki@...gle.com>
Signed-off-by: Dmitry Antipov <dmitry.antipov@...aro.org>
---
Documentation/kernel-parameters.txt | 9 +++++----
arch/arm/kernel/sched_clock.c | 2 ++
arch/x86/Kconfig | 11 -----------
arch/x86/kernel/tsc.c | 12 ++++++------
include/linux/sched.h | 17 ++++++++++-------
kernel/sched/core.c | 20 +++++++++++---------
lib/Kconfig.debug | 12 ++++++++++++
7 files changed, 46 insertions(+), 37 deletions(-)
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 033d4e6..666d20e 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1790,6 +1790,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
noirqdebug [X86-32] Disables the code which attempts to detect and
disable unhandled interrupt sources.
+ noirqtime [X86,ARM] Used to run time disable IRQ_TIME_ACCOUNTING,
+ should give a negligible performance improvement.
+
no_timer_check [X86,APIC] Disables the code which tests for
broken timer IRQ sources.
@@ -2636,10 +2639,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
as the stability checks done at bootup. 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.
+ [x86] noirqtime: obsoleted by "noirqtime" generic option,
+ see it's documentation for details.
turbografx.map[2|3]= [HW,JOY]
TurboGraFX parallel port interface
diff --git a/arch/arm/kernel/sched_clock.c b/arch/arm/kernel/sched_clock.c
index 5416c7c..30b5f89 100644
--- a/arch/arm/kernel/sched_clock.c
+++ b/arch/arm/kernel/sched_clock.c
@@ -144,6 +144,8 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
*/
cd.epoch_ns = 0;
+ enable_sched_clock_irqtime();
+
pr_debug("Registered %pF as sched_clock source\n", read);
}
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5bed94e..4759676 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -805,17 +805,6 @@ 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 a62c201..f1b2b63 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -103,14 +103,15 @@ 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;
+ if (!strncmp(str, "noirqtime", 9)) {
+ printk(KERN_WARNING "tsc: tsc=noirqtime is "
+ "obsolete, use noirqtime instead\n");
+ disable_sched_clock_irqtime();
+ }
return 1;
}
@@ -978,8 +979,7 @@ 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();
+ enable_sched_clock_irqtime();
lpj = ((u64)tsc_khz * 1000);
do_div(lpj, HZ);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 7d379a6..9b13f79 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1961,13 +1961,16 @@ extern void sched_clock_idle_wakeup_event(u64 delta_ns);
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-/*
- * An i/f to runtime opt-in for irq time accounting based off of sched_clock.
- * The reason for this explicit opt-in is not to have perf penalty with
- * slow sched_clocks.
- */
-extern void enable_sched_clock_irqtime(void);
-extern void disable_sched_clock_irqtime(void);
+extern int sched_clock_irqtime;
+static inline void enable_sched_clock_irqtime(void)
+{
+ if (sched_clock_irqtime == -1)
+ sched_clock_irqtime = 1;
+}
+static inline void disable_sched_clock_irqtime(void)
+{
+ sched_clock_irqtime = 0;
+}
#else
static inline void enable_sched_clock_irqtime(void) {}
static inline void disable_sched_clock_irqtime(void) {}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 5255c9d..a7ec043 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -757,18 +757,20 @@ static DEFINE_PER_CPU(u64, cpu_hardirq_time);
static DEFINE_PER_CPU(u64, cpu_softirq_time);
static DEFINE_PER_CPU(u64, irq_start_time);
-static int sched_clock_irqtime;
-void enable_sched_clock_irqtime(void)
-{
- sched_clock_irqtime = 1;
-}
+/* -1 if not initialized, 0 if disabled with "noirqtime" kernel option
+ * or after unstable clock was detected, 1 if enabled and active.
+ */
+int sched_clock_irqtime = -1;
-void disable_sched_clock_irqtime(void)
+static int __init irqtime_setup(char *str)
{
sched_clock_irqtime = 0;
+ return 1;
}
+__setup("noirqtime", irqtime_setup);
+
#ifndef CONFIG_64BIT
static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
@@ -822,7 +824,7 @@ void account_system_vtime(struct task_struct *curr)
s64 delta;
int cpu;
- if (!sched_clock_irqtime)
+ if (sched_clock_irqtime < 1)
return;
local_irq_save(flags);
@@ -2853,7 +2855,7 @@ void account_process_tick(struct task_struct *p, int user_tick)
cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
struct rq *rq = this_rq();
- if (sched_clock_irqtime) {
+ if (sched_clock_irqtime > 0) {
irqtime_account_process_tick(p, user_tick, rq);
return;
}
@@ -2887,7 +2889,7 @@ void account_steal_ticks(unsigned long ticks)
void account_idle_ticks(unsigned long ticks)
{
- if (sched_clock_irqtime) {
+ if (sched_clock_irqtime > 0) {
irqtime_account_idle_ticks(ticks);
return;
}
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 8745ac7..236e814 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -299,6 +299,18 @@ config SCHEDSTATS
application, you can say N to avoid the very slight overhead
this adds.
+config IRQ_TIME_ACCOUNTING
+ bool "Fine granularity task level IRQ time accounting"
+ depends on X86 || ARM
+ 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.
+
config TIMER_STATS
bool "Collect kernel timers statistics"
depends on DEBUG_KERNEL && PROC_FS
--
1.7.7.6
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists