| 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
| ||
|
Date: Wed, 25 Nov 2020 03:15:41 +0100
From: Frederic Weisbecker <frederic@...nel.org>
To: Thomas Gleixner <tglx@...utronix.de>
Cc: LKML <linux-kernel@...r.kernel.org>,
Frederic Weisbecker <frederic@...nel.org>,
Tony Luck <tony.luck@...el.com>,
Peter Zijlstra <peterz@...radead.org>,
Vasily Gorbik <gor@...ux.ibm.com>,
Michael Ellerman <mpe@...erman.id.au>,
Benjamin Herrenschmidt <benh@...nel.crashing.org>,
Paul Mackerras <paulus@...ba.org>,
Christian Borntraeger <borntraeger@...ibm.com>,
Fenghua Yu <fenghua.yu@...el.com>,
Heiko Carstens <hca@...ux.ibm.com>
Subject: [RFC PATCH 3/4] sched/irqtime: Move irqtime entry accounting after irq offset incrementation
IRQ time entry is currently accounted before HARDIRQ_OFFSET or
SOFTIRQ_OFFSET are incremented. This is convenient to decide to which
index the cputime to account is dispatched.
Unfortunately it prevents tick_irq_enter() from being called under
HARDIRQ_OFFSET because tick_irq_enter() has to be called before the IRQ
entry accounting due to the necessary clock catch up. As a result we
don't benefit from appropriate lockdep coverage on tick_irq_enter().
To prepare for fixing this, move the IRQ entry cputime accounting after
the preempt offset is incremented. This requires the cputime dispatch
code to handle the extra offset.
Signed-off-by: Frederic Weisbecker <frederic@...nel.org>
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Tony Luck <tony.luck@...el.com>
Cc: Fenghua Yu <fenghua.yu@...el.com>
Cc: Michael Ellerman <mpe@...erman.id.au>
Cc: Benjamin Herrenschmidt <benh@...nel.crashing.org>
Cc: Paul Mackerras <paulus@...ba.org>
Cc: Heiko Carstens <hca@...ux.ibm.com>
Cc: Vasily Gorbik <gor@...ux.ibm.com>
Cc: Christian Borntraeger <borntraeger@...ibm.com>
---
include/linux/hardirq.h | 4 +--
include/linux/vtime.h | 10 +++++---
kernel/sched/cputime.c | 56 ++++++++++++++++++++++++++++++-----------
kernel/softirq.c | 2 +-
4 files changed, 51 insertions(+), 21 deletions(-)
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index 754f67ac4326..02499c10fbf7 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -32,9 +32,9 @@ static __always_inline void rcu_irq_enter_check_tick(void)
*/
#define __irq_enter() \
do { \
+ preempt_count_add(HARDIRQ_OFFSET); \
+ lockdep_hardirq_enter(); \
account_irq_enter_time(current); \
- preempt_count_add(HARDIRQ_OFFSET); \
- lockdep_hardirq_enter(); \
} while (0)
/*
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index f827b38c3bb7..cad8ff530273 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -96,21 +96,23 @@ static inline void vtime_flush(struct task_struct *tsk) { }
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-extern void irqtime_account_irq(struct task_struct *tsk);
+extern void irqtime_account_enter(struct task_struct *tsk);
+extern void irqtime_account_exit(struct task_struct *tsk);
#else
-static inline void irqtime_account_irq(struct task_struct *tsk) { }
+static inline void irqtime_account_enter(struct task_struct *tsk) { }
+static inline void irqtime_account_exit(struct task_struct *tsk) { }
#endif
static inline void account_irq_enter_time(struct task_struct *tsk)
{
vtime_account_irq_enter(tsk);
- irqtime_account_irq(tsk);
+ irqtime_account_enter(tsk);
}
static inline void account_irq_exit_time(struct task_struct *tsk)
{
vtime_account_irq_exit(tsk);
- irqtime_account_irq(tsk);
+ irqtime_account_exit(tsk);
}
#endif /* _LINUX_KERNEL_VTIME_H */
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 6fa81cc33fec..82623d97667c 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -43,23 +43,49 @@ static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
u64_stats_update_end(&irqtime->sync);
}
-/*
- * Called before incrementing preempt_count on {soft,}irq_enter
- * and before decrementing preempt_count on {soft,}irq_exit.
- */
-void irqtime_account_irq(struct task_struct *curr)
+static s64 irqtime_get_delta(struct irqtime *irqtime)
{
- struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+ int cpu = smp_processor_id();
s64 delta;
- int cpu;
- if (!sched_clock_irqtime)
- return;
-
- cpu = smp_processor_id();
delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
irqtime->irq_start_time += delta;
+ return delta;
+}
+
+/* Called after incrementing preempt_count on {soft,}irq_enter */
+void irqtime_account_enter(struct task_struct *curr)
+{
+ struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+ u64 delta;
+
+ if (!sched_clock_irqtime)
+ return;
+
+ delta = irqtime_get_delta(irqtime);
+ /*
+ * We do not account for softirq time from ksoftirqd here.
+ * We want to continue accounting softirq time to ksoftirqd thread
+ * in that case, so as not to confuse scheduler with a special task
+ * that do not consume any time, but still wants to run.
+ */
+ if ((irq_count() == (SOFTIRQ_OFFSET | HARDIRQ_OFFSET)) &&
+ curr != this_cpu_ksoftirqd())
+ irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
+}
+EXPORT_SYMBOL_GPL(irqtime_account_enter);
+
+/* Called before decrementing preempt_count on {soft,}irq_exit */
+void irqtime_account_exit(struct task_struct *curr)
+{
+ struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+ u64 delta;
+
+ if (!sched_clock_irqtime)
+ return;
+
+ delta = irqtime_get_delta(irqtime);
/*
* We do not account for softirq time from ksoftirqd here.
* We want to continue accounting softirq time to ksoftirqd thread
@@ -71,7 +97,7 @@ void irqtime_account_irq(struct task_struct *curr)
else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
}
-EXPORT_SYMBOL_GPL(irqtime_account_irq);
+EXPORT_SYMBOL_GPL(irqtime_account_exit);
static u64 irqtime_tick_accounted(u64 maxtime)
{
@@ -428,9 +454,11 @@ void vtime_task_switch(struct task_struct *prev)
*/
void vtime_account_irq_enter(struct task_struct *tsk)
{
- if (hardirq_count()) {
+ WARN_ON_ONCE(in_task());
+
+ if (hardirq_count() > HARDIRQ_OFFSET) {
vtime_account_hardirq(tsk);
- } else if (in_serving_softirq()) {
+ } else if (hardirq_count() && in_serving_softirq()) {
vtime_account_softirq(tsk);
} else if (is_idle_task(tsk)) {
vtime_account_idle(tsk);
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 617009ccd82c..24254c41bb7c 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -315,9 +315,9 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
current->flags &= ~PF_MEMALLOC;
pending = local_softirq_pending();
- account_irq_enter_time(current);
__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
+ account_irq_enter_time(current);
in_hardirq = lockdep_softirq_start();
restart:
--
2.25.1
Powered by blists - more mailing lists