| 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: <1292980144-28796-5-git-send-email-venki@google.com>
Date: Tue, 21 Dec 2010 17:09:03 -0800
From: Venkatesh Pallipadi <venki@...gle.com>
To: Peter Zijlstra <peterz@...radead.org>, Ingo Molnar <mingo@...e.hu>,
"H. Peter Anvin" <hpa@...or.com>,
Thomas Gleixner <tglx@...utronix.de>,
Balbir Singh <balbir@...ux.vnet.ibm.com>,
Martin Schwidefsky <schwidefsky@...ibm.com>
Cc: linux-kernel@...r.kernel.org, Paul Turner <pjt@...gle.com>,
Eric Dumazet <eric.dumazet@...il.com>,
Shaun Ruffell <sruffell@...ium.com>,
Venkatesh Pallipadi <venki@...gle.com>
Subject: [PATCH 4/5] Export ns irqtimes through /proc/stat -v2
CONFIG_IRQ_TIME_ACCOUNTING adds ns granularity irq time on each CPU.
This info is already used in scheduler to do proper task chargeback
(earlier patches). This patch retro-fits this ns granularity
hardirq and softirq information to /proc/stat irq and softirq fields.
The update is still done on timer tick, where we look at accumulated
ns hardirq/softirq time and account the tick to user/system/irq/hardirq/guest
accordingly.
No new interface added.
Earlier versions looked at adding this as new fields in some /proc
files. This one seems to be the best in terms of impact to existing
apps, even though it has somewhat more kernel code than earlier versions.
Tested-by: Shaun Ruffell <sruffell@...ium.com>
Signed-off-by: Venkatesh Pallipadi <venki@...gle.com>
---
kernel/sched.c | 102 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 files changed, 102 insertions(+), 0 deletions(-)
diff --git a/kernel/sched.c b/kernel/sched.c
index c428017..193b1d0 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2051,8 +2051,40 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
sched_rt_avg_update(rq, irq_delta);
}
+static int irqtime_account_hi_update(void)
+{
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ unsigned long flags;
+ u64 latest_ns;
+ int ret = 0;
+
+ local_irq_save(flags);
+ latest_ns = this_cpu_read(cpu_hardirq_time);
+ if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->irq))
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
+static int irqtime_account_si_update(void)
+{
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+ unsigned long flags;
+ u64 latest_ns;
+ int ret = 0;
+
+ local_irq_save(flags);
+ latest_ns = this_cpu_read(cpu_softirq_time);
+ if (cputime64_gt(nsecs_to_cputime64(latest_ns), cpustat->softirq))
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+#define sched_clock_irqtime (0)
+
static void update_rq_clock_task(struct rq *rq, s64 delta)
{
rq->clock_task += delta;
@@ -3754,6 +3786,65 @@ void account_system_time(struct task_struct *p, int hardirq_offset,
__account_system_time(p, cputime, cputime_scaled, target_cputime64);
}
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+/*
+ * Account a tick to a process and cpustat
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: is the tick from userspace
+ * @rq: the pointer to rq
+ *
+ * Tick demultiplexing follows the order
+ * - pending hardirq update
+ * - pending softirq update
+ * - user_time
+ * - idle_time
+ * - system time
+ * - check for guest_time
+ * - else account as system_time
+ *
+ * Check for hardirq is done both for system and user time as there is
+ * no timer going off while we are on hardirq and hence we may never get an
+ * opportunity to update it solely in system time.
+ * p->stime and friends are only updated on system time and not on irq
+ * softirq as those do not count in task exec_runtime any more.
+ */
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+ struct rq *rq)
+{
+ cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy);
+ cputime64_t tmp = cputime_to_cputime64(cputime_one_jiffy);
+ struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat;
+
+ if (irqtime_account_hi_update()) {
+ cpustat->irq = cputime64_add(cpustat->irq, tmp);
+ } else if (irqtime_account_si_update()) {
+ cpustat->softirq = cputime64_add(cpustat->softirq, tmp);
+ } else if (user_tick) {
+ account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ } else if (p == rq->idle) {
+ account_idle_time(cputime_one_jiffy);
+ } else if (p->flags & PF_VCPU) { /* System time or guest time */
+ account_guest_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ } else {
+ __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+ &cpustat->system);
+ }
+}
+
+static void irqtime_account_idle_ticks(int ticks)
+{
+ int i;
+ struct rq *rq = this_rq();
+
+ for (i = 0; i < ticks; i++)
+ irqtime_account_process_tick(current, 0, rq);
+}
+#else
+static void irqtime_account_idle_ticks(int ticks) {}
+static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
+ struct rq *rq) {}
+#endif
+
/*
* Account for involuntary wait time.
* @steal: the cpu time spent in involuntary wait
@@ -3794,6 +3885,11 @@ 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) {
+ irqtime_account_process_tick(p, user_tick, rq);
+ return;
+ }
+
if (user_tick)
account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
@@ -3819,6 +3915,12 @@ void account_steal_ticks(unsigned long ticks)
*/
void account_idle_ticks(unsigned long ticks)
{
+
+ if (sched_clock_irqtime) {
+ irqtime_account_idle_ticks(ticks);
+ return;
+ }
+
account_idle_time(jiffies_to_cputime(ticks));
}
--
1.7.3.1
--
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