Hi,
Changes since v2:
- Fix missing EXPORT_SYMBOL_GPL (thanks Wu Fenguang for the report)
- Drop that *_irqsafe naming, use vtime_account_system() as irq safe
and __vtime_account_system() for the raw arch implementation
- Drop local_irq_disable() on s390 kvm guest switch
If you want to test, it is pullable from:
git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
cputime/cleanups-v3
Frederic Weisbecker (5):
vtime: Gather vtime declarations to their own header file
vtime: Make vtime_account_system() irqsafe
kvm: Directly account vtime to system on guest switch
cputime: Specialize irq vtime hooks
cputime: Separate irqtime accounting from generic vtime
arch/ia64/kernel/time.c | 8 +++---
arch/powerpc/kernel/time.c | 4 +-
arch/s390/kernel/vtime.c | 4 +++
arch/s390/kvm/kvm-s390.c | 4 ---
include/linux/hardirq.h | 15 ++-----------
include/linux/kernel_stat.h | 9 +-------
include/linux/kvm_host.h | 12 +++++++++-
include/linux/vtime.h | 47 +++++++++++++++++++++++++++++++++++++++++++
kernel/sched/cputime.c | 20 +++++++++++++----
kernel/softirq.c | 6 ++--
10 files changed, 89 insertions(+), 40 deletions(-)
create mode 100644 include/linux/vtime.h
--
1.7.5.4
These APIs are scattered around and are going to expand a bit.
Let's create a dedicated header file for sanity.
Signed-off-by: Frederic Weisbecker <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Paul Gortmaker <[email protected]>
---
include/linux/hardirq.h | 11 +----------
include/linux/kernel_stat.h | 9 +--------
include/linux/vtime.h | 22 ++++++++++++++++++++++
3 files changed, 24 insertions(+), 18 deletions(-)
create mode 100644 include/linux/vtime.h
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index cab3da3..b083a47 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -4,6 +4,7 @@
#include <linux/preempt.h>
#include <linux/lockdep.h>
#include <linux/ftrace_irq.h>
+#include <linux/vtime.h>
#include <asm/hardirq.h>
/*
@@ -129,16 +130,6 @@ extern void synchronize_irq(unsigned int irq);
# define synchronize_irq(irq) barrier()
#endif
-struct task_struct;
-
-#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
-static inline void vtime_account(struct task_struct *tsk)
-{
-}
-#else
-extern void vtime_account(struct task_struct *tsk);
-#endif
-
#if defined(CONFIG_TINY_RCU) || defined(CONFIG_TINY_PREEMPT_RCU)
static inline void rcu_nmi_enter(void)
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 36d12f0..1865b1f 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -7,6 +7,7 @@
#include <linux/cpumask.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
+#include <linux/vtime.h>
#include <asm/irq.h>
#include <asm/cputime.h>
@@ -130,12 +131,4 @@ extern void account_process_tick(struct task_struct *, int user);
extern void account_steal_ticks(unsigned long ticks);
extern void account_idle_ticks(unsigned long ticks);
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void vtime_task_switch(struct task_struct *prev);
-extern void vtime_account_system(struct task_struct *tsk);
-extern void vtime_account_idle(struct task_struct *tsk);
-#else
-static inline void vtime_task_switch(struct task_struct *prev) { }
-#endif
-
#endif /* _LINUX_KERNEL_STAT_H */
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
new file mode 100644
index 0000000..7199c24
--- /dev/null
+++ b/include/linux/vtime.h
@@ -0,0 +1,22 @@
+#ifndef _LINUX_KERNEL_VTIME_H
+#define _LINUX_KERNEL_VTIME_H
+
+struct task_struct;
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+extern void vtime_task_switch(struct task_struct *prev);
+extern void vtime_account_system(struct task_struct *tsk);
+extern void vtime_account_idle(struct task_struct *tsk);
+#else
+static inline void vtime_task_switch(struct task_struct *prev) { }
+#endif
+
+#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
+static inline void vtime_account(struct task_struct *tsk)
+{
+}
+#else
+extern void vtime_account(struct task_struct *tsk);
+#endif
+
+#endif /* _LINUX_KERNEL_VTIME_H */
--
1.7.5.4
Switching to or from guest context is done on ioctl context.
So by the time we call kvm_guest_enter() or kvm_guest_exit()
we know we are not running the idle task.
As a result, we can directly account the cputime using
vtime_account_system().
There are two good reasons to do this:
* We avoid some useless checks on guest switch. It optimizes
a bit this fast path.
* In the case of CONFIG_IRQ_TIME_ACCOUNTING, calling vtime_account()
checks for irq time to account. This is pointless since we know
we are not in an irq on guest switch. This is wasting cpu cycles
for no good reason. vtime_account_system() OTOH is a no-op in
this config option.
* We can remove the irq disable/enable around kvm guest switch in s390.
A further optimization may consist in introducing a vtime_account_guest()
that directly calls account_guest_time().
Signed-off-by: Frederic Weisbecker <[email protected]>
Cc: Tony Luck <[email protected]>
Cc: Fenghua Yu <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: Martin Schwidefsky <[email protected]>
Cc: Avi Kivity <[email protected]>
Cc: Marcelo Tosatti <[email protected]>
Cc: Joerg Roedel <[email protected]>
Cc: Alexander Graf <[email protected]>
Cc: Xiantao Zhang <[email protected]>
Cc: Christian Borntraeger <[email protected]>
Cc: Cornelia Huck <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Paul Gortmaker <[email protected]>
---
arch/s390/kvm/kvm-s390.c | 4 ----
include/linux/kvm_host.h | 12 ++++++++++--
2 files changed, 10 insertions(+), 6 deletions(-)
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index ecced9d..d91a955 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -608,9 +608,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
kvm_s390_deliver_pending_interrupts(vcpu);
vcpu->arch.sie_block->icptcode = 0;
- local_irq_disable();
kvm_guest_enter();
- local_irq_enable();
VCPU_EVENT(vcpu, 6, "entering sie flags %x",
atomic_read(&vcpu->arch.sie_block->cpuflags));
trace_kvm_s390_sie_enter(vcpu,
@@ -629,9 +627,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
vcpu->arch.sie_block->icptcode);
trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
- local_irq_disable();
kvm_guest_exit();
- local_irq_enable();
memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
return rc;
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 93bfc9f..0e2212f 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -737,7 +737,11 @@ static inline int kvm_deassign_device(struct kvm *kvm,
static inline void kvm_guest_enter(void)
{
BUG_ON(preemptible());
- vtime_account(current);
+ /*
+ * This is running in ioctl context so we can avoid
+ * the call to vtime_account() with its unnecessary idle check.
+ */
+ vtime_account_system(current);
current->flags |= PF_VCPU;
/* KVM does not hold any references to rcu protected data when it
* switches CPU into a guest mode. In fact switching to a guest mode
@@ -751,7 +755,11 @@ static inline void kvm_guest_enter(void)
static inline void kvm_guest_exit(void)
{
- vtime_account(current);
+ /*
+ * This is running in ioctl context so we can avoid
+ * the call to vtime_account() with its unnecessary idle check.
+ */
+ vtime_account_system(current);
current->flags &= ~PF_VCPU;
}
--
1.7.5.4
With CONFIG_VIRT_CPU_ACCOUNTING, when vtime_account()
is called in irq entry/exit, we perform a check on the
context: if we are interrupting the idle task we
account the pending cputime to idle, otherwise account
to system time or its sub-areas: tsk->stime, hardirq time,
softirq time, ...
However this check for idle only concerns the hardirq entry
and softirq entry:
* Hardirq may directly interrupt the idle task, in which case
we need to flush the pending CPU time to idle.
* The idle task may be directly interrupted by a softirq if
it calls local_bh_enable(). There is probably no such call
in any idle task but we need to cover every case. Ksoftirqd
is not concerned because the idle time is flushed on context
switch and softirq in the end of hardirq have the idle time
already flushed from the hardirq entry.
In the other cases we always account to system/irq time:
* On hardirq exit we account the time to hardirq time.
* On softirq exit we account the time to softirq time.
To optimize this and avoid the indirect call to vtime_account()
and the checks it performs, specialize the vtime irq APIs and
only perform the check on irq entry. Irq exit can directly call
vtime_account_system().
CONFIG_IRQ_TIME_ACCOUNTING behaviour doesn't change and directly
maps to its own vtime_account() implementation. One may want
to take benefits from the new APIs to optimize irq time accounting
as well in the future.
Signed-off-by: Frederic Weisbecker <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Paul Gortmaker <[email protected]>
---
include/linux/hardirq.h | 4 ++--
include/linux/vtime.h | 25 +++++++++++++++++++++++++
kernel/softirq.c | 6 +++---
3 files changed, 30 insertions(+), 5 deletions(-)
diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index b083a47..624ef3f 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -153,7 +153,7 @@ extern void rcu_nmi_exit(void);
*/
#define __irq_enter() \
do { \
- vtime_account(current); \
+ vtime_account_irq_enter(current); \
add_preempt_count(HARDIRQ_OFFSET); \
trace_hardirq_enter(); \
} while (0)
@@ -169,7 +169,7 @@ extern void irq_enter(void);
#define __irq_exit() \
do { \
trace_hardirq_exit(); \
- vtime_account(current); \
+ vtime_account_irq_exit(current); \
sub_preempt_count(HARDIRQ_OFFSET); \
} while (0)
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index b9fc4f9..c35c022 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -21,4 +21,29 @@ static inline void vtime_account(struct task_struct *tsk)
extern void vtime_account(struct task_struct *tsk);
#endif
+static inline void vtime_account_irq_enter(struct task_struct *tsk)
+{
+ /*
+ * Hardirq can interrupt idle task anytime. So we need vtime_account()
+ * that performs the idle check in CONFIG_VIRT_CPU_ACCOUNTING.
+ * Softirq can also interrupt idle task directly if it calls
+ * local_bh_enable(). Such case probably don't exist but we never know.
+ * Ksoftirqd is not concerned because idle time is flushed on context
+ * switch. Softirqs in the end of hardirqs are also not a problem because
+ * the idle time is flushed on hardirq time already.
+ */
+ vtime_account(tsk);
+}
+
+static inline void vtime_account_irq_exit(struct task_struct *tsk)
+{
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+ /* On hard|softirq exit we always account to hard|softirq cputime */
+ __vtime_account_system(tsk);
+#endif
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+ vtime_account(tsk);
+#endif
+}
+
#endif /* _LINUX_KERNEL_VTIME_H */
diff --git a/kernel/softirq.c b/kernel/softirq.c
index cc96bdc..ed567ba 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -221,7 +221,7 @@ asmlinkage void __do_softirq(void)
current->flags &= ~PF_MEMALLOC;
pending = local_softirq_pending();
- vtime_account(current);
+ vtime_account_irq_enter(current);
__local_bh_disable((unsigned long)__builtin_return_address(0),
SOFTIRQ_OFFSET);
@@ -272,7 +272,7 @@ restart:
lockdep_softirq_exit();
- vtime_account(current);
+ vtime_account_irq_exit(current);
__local_bh_enable(SOFTIRQ_OFFSET);
tsk_restore_flags(current, old_flags, PF_MEMALLOC);
}
@@ -341,7 +341,7 @@ static inline void invoke_softirq(void)
*/
void irq_exit(void)
{
- vtime_account(current);
+ vtime_account_irq_exit(current);
trace_hardirq_exit();
sub_preempt_count(IRQ_EXIT_OFFSET);
if (!in_interrupt() && local_softirq_pending())
--
1.7.5.4
vtime_account() doesn't have the same role in
CONFIG_VIRT_CPU_ACCOUNTING and CONFIG_IRQ_TIME_ACCOUNTING.
In the first case it handles time accounting in any context. In
the second case it only handles irq time accounting.
So when vtime_account() is called from outside vtime_account_irq_*()
this call is pointless to CONFIG_IRQ_TIME_ACCOUNTING.
To fix the confusion, change vtime_account() to irqtime_account_irq()
in CONFIG_IRQ_TIME_ACCOUNTING. This way we ensure future account_vtime()
calls won't waste useless cycles in the irqtime APIs.
Signed-off-by: Frederic Weisbecker <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Paul Gortmaker <[email protected]>
---
include/linux/vtime.h | 18 ++++++++----------
kernel/sched/cputime.c | 4 ++--
2 files changed, 10 insertions(+), 12 deletions(-)
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index c35c022..0c2a2d3 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -8,17 +8,18 @@ extern void vtime_task_switch(struct task_struct *prev);
extern void __vtime_account_system(struct task_struct *tsk);
extern void vtime_account_system(struct task_struct *tsk);
extern void __vtime_account_idle(struct task_struct *tsk);
+extern void vtime_account(struct task_struct *tsk);
#else
static inline void vtime_task_switch(struct task_struct *prev) { }
+static inline void __vtime_account_system(struct task_struct *tsk) { }
static inline void vtime_account_system(struct task_struct *tsk) { }
+static inline void vtime_account(struct task_struct *tsk) { }
#endif
-#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
-static inline void vtime_account(struct task_struct *tsk)
-{
-}
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+extern void irqtime_account_irq(struct task_struct *tsk);
#else
-extern void vtime_account(struct task_struct *tsk);
+static inline void irqtime_account_irq(struct task_struct *tsk) { }
#endif
static inline void vtime_account_irq_enter(struct task_struct *tsk)
@@ -33,17 +34,14 @@ static inline void vtime_account_irq_enter(struct task_struct *tsk)
* the idle time is flushed on hardirq time already.
*/
vtime_account(tsk);
+ irqtime_account_irq(tsk);
}
static inline void vtime_account_irq_exit(struct task_struct *tsk)
{
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
/* On hard|softirq exit we always account to hard|softirq cputime */
__vtime_account_system(tsk);
-#endif
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
- vtime_account(tsk);
-#endif
+ irqtime_account_irq(tsk);
}
#endif /* _LINUX_KERNEL_VTIME_H */
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 0359f47..8d859da 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -43,7 +43,7 @@ DEFINE_PER_CPU(seqcount_t, irq_time_seq);
* Called before incrementing preempt_count on {soft,}irq_enter
* and before decrementing preempt_count on {soft,}irq_exit.
*/
-void vtime_account(struct task_struct *curr)
+void irqtime_account_irq(struct task_struct *curr)
{
unsigned long flags;
s64 delta;
@@ -73,7 +73,7 @@ void vtime_account(struct task_struct *curr)
irq_time_write_end();
local_irq_restore(flags);
}
-EXPORT_SYMBOL_GPL(vtime_account);
+EXPORT_SYMBOL_GPL(irqtime_account_irq);
static int irqtime_account_hi_update(void)
{
--
1.7.5.4
vtime_account_system() currently has only one caller with
vtime_account() which is irq safe.
Now we are going to call it from other places like kvm where
irqs are not always disabled by the time we account the cputime.
So let's make it irqsafe. The arch implementation part is now
prefixed with "__".
vtime_account_idle() arch implementation is prefixed accordingly
to stay consistent.
Signed-off-by: Frederic Weisbecker <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Paul Gortmaker <[email protected]>
Cc: Tony Luck <[email protected]>
Cc: Fenghua Yu <[email protected]>
Cc: Benjamin Herrenschmidt <[email protected]>
Cc: Paul Mackerras <[email protected]>
Cc: Martin Schwidefsky <[email protected]>
Cc: Heiko Carstens <[email protected]>
---
arch/ia64/kernel/time.c | 8 ++++----
arch/powerpc/kernel/time.c | 4 ++--
arch/s390/kernel/vtime.c | 4 ++++
include/linux/vtime.h | 4 +++-
kernel/sched/cputime.c | 16 +++++++++++++---
5 files changed, 26 insertions(+), 10 deletions(-)
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index f638821..5e48503 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -106,9 +106,9 @@ void vtime_task_switch(struct task_struct *prev)
struct thread_info *ni = task_thread_info(current);
if (idle_task(smp_processor_id()) != prev)
- vtime_account_system(prev);
+ __vtime_account_system(prev);
else
- vtime_account_idle(prev);
+ __vtime_account_idle(prev);
vtime_account_user(prev);
@@ -135,14 +135,14 @@ static cputime_t vtime_delta(struct task_struct *tsk)
return delta_stime;
}
-void vtime_account_system(struct task_struct *tsk)
+void __vtime_account_system(struct task_struct *tsk)
{
cputime_t delta = vtime_delta(tsk);
account_system_time(tsk, 0, delta, delta);
}
-void vtime_account_idle(struct task_struct *tsk)
+void __vtime_account_idle(struct task_struct *tsk)
{
account_idle_time(vtime_delta(tsk));
}
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index ce4cb77..0db456f 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -336,7 +336,7 @@ static u64 vtime_delta(struct task_struct *tsk,
return delta;
}
-void vtime_account_system(struct task_struct *tsk)
+void __vtime_account_system(struct task_struct *tsk)
{
u64 delta, sys_scaled, stolen;
@@ -346,7 +346,7 @@ void vtime_account_system(struct task_struct *tsk)
account_steal_time(stolen);
}
-void vtime_account_idle(struct task_struct *tsk)
+void __vtime_account_idle(struct task_struct *tsk)
{
u64 delta, sys_scaled, stolen;
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 7903344..783e988 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -140,6 +140,10 @@ void vtime_account(struct task_struct *tsk)
}
EXPORT_SYMBOL_GPL(vtime_account);
+void __vtime_account_system(struct task_struct *tsk)
+__attribute__((alias("vtime_account")));
+EXPORT_SYMBOL_GPL(__vtime_account_system);
+
void __kprobes vtime_stop_cpu(void)
{
struct s390_idle_data *idle = &__get_cpu_var(s390_idle);
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index 7199c24..b9fc4f9 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -5,10 +5,12 @@ struct task_struct;
#ifdef CONFIG_VIRT_CPU_ACCOUNTING
extern void vtime_task_switch(struct task_struct *prev);
+extern void __vtime_account_system(struct task_struct *tsk);
extern void vtime_account_system(struct task_struct *tsk);
-extern void vtime_account_idle(struct task_struct *tsk);
+extern void __vtime_account_idle(struct task_struct *tsk);
#else
static inline void vtime_task_switch(struct task_struct *prev) { }
+static inline void vtime_account_system(struct task_struct *tsk) { }
#endif
#if !defined(CONFIG_VIRT_CPU_ACCOUNTING) && !defined(CONFIG_IRQ_TIME_ACCOUNTING)
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 81b763b..0359f47 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -433,10 +433,20 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
*st = cputime.stime;
}
+void vtime_account_system(struct task_struct *tsk)
+{
+ unsigned long flags;
+
+ local_irq_save(flags);
+ __vtime_account_system(tsk);
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(vtime_account_system);
+
/*
* Archs that account the whole time spent in the idle task
* (outside irq) as idle time can rely on this and just implement
- * vtime_account_system() and vtime_account_idle(). Archs that
+ * __vtime_account_system() and __vtime_account_idle(). Archs that
* have other meaning of the idle time (s390 only includes the
* time spent by the CPU when it's in low power mode) must override
* vtime_account().
@@ -449,9 +459,9 @@ void vtime_account(struct task_struct *tsk)
local_irq_save(flags);
if (in_interrupt() || !is_idle_task(tsk))
- vtime_account_system(tsk);
+ __vtime_account_system(tsk);
else
- vtime_account_idle(tsk);
+ __vtime_account_idle(tsk);
local_irq_restore(flags);
}
--
1.7.5.4
2012/10/25 Frederic Weisbecker <[email protected]>:
> Hi,
>
> Changes since v2:
>
> - Fix missing EXPORT_SYMBOL_GPL (thanks Wu Fenguang for the report)
> - Drop that *_irqsafe naming, use vtime_account_system() as irq safe
> and __vtime_account_system() for the raw arch implementation
> - Drop local_irq_disable() on s390 kvm guest switch
>
> If you want to test, it is pullable from:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git
> cputime/cleanups-v3
It's cputime/cleanups-v4, sorry.
(Adding Christian Borntraeger in Cc)
2012/10/25 Frederic Weisbecker <[email protected]>:
> Switching to or from guest context is done on ioctl context.
> So by the time we call kvm_guest_enter() or kvm_guest_exit()
> we know we are not running the idle task.
>
> As a result, we can directly account the cputime using
> vtime_account_system().
>
> There are two good reasons to do this:
>
> * We avoid some useless checks on guest switch. It optimizes
> a bit this fast path.
>
> * In the case of CONFIG_IRQ_TIME_ACCOUNTING, calling vtime_account()
> checks for irq time to account. This is pointless since we know
> we are not in an irq on guest switch. This is wasting cpu cycles
> for no good reason. vtime_account_system() OTOH is a no-op in
> this config option.
>
> * We can remove the irq disable/enable around kvm guest switch in s390.
>
> A further optimization may consist in introducing a vtime_account_guest()
> that directly calls account_guest_time().
>
> Signed-off-by: Frederic Weisbecker <[email protected]>
> Cc: Tony Luck <[email protected]>
> Cc: Fenghua Yu <[email protected]>
> Cc: Benjamin Herrenschmidt <[email protected]>
> Cc: Paul Mackerras <[email protected]>
> Cc: Heiko Carstens <[email protected]>
> Cc: Martin Schwidefsky <[email protected]>
> Cc: Avi Kivity <[email protected]>
> Cc: Marcelo Tosatti <[email protected]>
> Cc: Joerg Roedel <[email protected]>
> Cc: Alexander Graf <[email protected]>
> Cc: Xiantao Zhang <[email protected]>
> Cc: Christian Borntraeger <[email protected]>
> Cc: Cornelia Huck <[email protected]>
> Cc: Peter Zijlstra <[email protected]>
> Cc: Ingo Molnar <[email protected]>
> Cc: Thomas Gleixner <[email protected]>
> Cc: Steven Rostedt <[email protected]>
> Cc: Paul Gortmaker <[email protected]>
> ---
> arch/s390/kvm/kvm-s390.c | 4 ----
> include/linux/kvm_host.h | 12 ++++++++++--
> 2 files changed, 10 insertions(+), 6 deletions(-)
>
> diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
> index ecced9d..d91a955 100644
> --- a/arch/s390/kvm/kvm-s390.c
> +++ b/arch/s390/kvm/kvm-s390.c
> @@ -608,9 +608,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
> kvm_s390_deliver_pending_interrupts(vcpu);
>
> vcpu->arch.sie_block->icptcode = 0;
> - local_irq_disable();
> kvm_guest_enter();
> - local_irq_enable();
> VCPU_EVENT(vcpu, 6, "entering sie flags %x",
> atomic_read(&vcpu->arch.sie_block->cpuflags));
> trace_kvm_s390_sie_enter(vcpu,
> @@ -629,9 +627,7 @@ static int __vcpu_run(struct kvm_vcpu *vcpu)
> VCPU_EVENT(vcpu, 6, "exit sie icptcode %d",
> vcpu->arch.sie_block->icptcode);
> trace_kvm_s390_sie_exit(vcpu, vcpu->arch.sie_block->icptcode);
> - local_irq_disable();
> kvm_guest_exit();
> - local_irq_enable();
>
> memcpy(&vcpu->run->s.regs.gprs[14], &vcpu->arch.sie_block->gg14, 16);
> return rc;
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 93bfc9f..0e2212f 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -737,7 +737,11 @@ static inline int kvm_deassign_device(struct kvm *kvm,
> static inline void kvm_guest_enter(void)
> {
> BUG_ON(preemptible());
> - vtime_account(current);
> + /*
> + * This is running in ioctl context so we can avoid
> + * the call to vtime_account() with its unnecessary idle check.
> + */
> + vtime_account_system(current);
> current->flags |= PF_VCPU;
> /* KVM does not hold any references to rcu protected data when it
> * switches CPU into a guest mode. In fact switching to a guest mode
> @@ -751,7 +755,11 @@ static inline void kvm_guest_enter(void)
>
> static inline void kvm_guest_exit(void)
> {
> - vtime_account(current);
> + /*
> + * This is running in ioctl context so we can avoid
> + * the call to vtime_account() with its unnecessary idle check.
> + */
> + vtime_account_system(current);
> current->flags &= ~PF_VCPU;
> }
>
> --
> 1.7.5.4
>
Ingo,
Please pull the latest cputime cleanups that can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git tags/cputime-cleanups-for-mingo
for you to fetch changes up to 3e1df4f506836e6bea1ab61cf88c75c8b1840643:
cputime: Separate irqtime accounting from generic vtime (2012-10-29 21:31:32 +0100)
It is based on top of tip:sched/core of today.
Tested on x86 and powerpc. Built-tested only on ia64 and s390.
Thanks.
----------------------------------------------------------------
Cputime cleanups and optimizations:
* Gather vtime headers that were a bit scattered around
* Separate irqtime and vtime namespaces that were
colliding, resulting in useless calls to irqtime accounting.
* Slightly optimize irq and guest vtime accounting.
Signed-off-by: Frederic Weisbecker <[email protected]>
----------------------------------------------------------------
Frederic Weisbecker (5):
vtime: Gather vtime declarations to their own header file
vtime: Make vtime_account_system() irqsafe
kvm: Directly account vtime to system on guest switch
cputime: Specialize irq vtime hooks
cputime: Separate irqtime accounting from generic vtime
arch/ia64/kernel/time.c | 8 ++++----
arch/powerpc/kernel/time.c | 4 ++--
arch/s390/kernel/vtime.c | 4 ++++
arch/s390/kvm/kvm-s390.c | 4 ----
include/linux/hardirq.h | 15 +++-----------
include/linux/kernel_stat.h | 9 +--------
include/linux/kvm_host.h | 12 +++++++++--
include/linux/vtime.h | 47 +++++++++++++++++++++++++++++++++++++++++++
kernel/sched/cputime.c | 20 +++++++++++++-----
kernel/softirq.c | 6 +++---
10 files changed, 89 insertions(+), 40 deletions(-)
create mode 100644 include/linux/vtime.h
* Frederic Weisbecker <[email protected]> wrote:
> Ingo,
>
> Please pull the latest cputime cleanups that can be found at:
>
> git://git.kernel.org/pub/scm/linux/kernel/git/frederic/linux-dynticks.git tags/cputime-cleanups-for-mingo
>
> for you to fetch changes up to 3e1df4f506836e6bea1ab61cf88c75c8b1840643:
>
> cputime: Separate irqtime accounting from generic vtime (2012-10-29 21:31:32 +0100)
>
> It is based on top of tip:sched/core of today.
>
> Tested on x86 and powerpc. Built-tested only on ia64 and s390.
>
> Thanks.
>
> ----------------------------------------------------------------
> Cputime cleanups and optimizations:
>
> * Gather vtime headers that were a bit scattered around
>
> * Separate irqtime and vtime namespaces that were
> colliding, resulting in useless calls to irqtime accounting.
>
> * Slightly optimize irq and guest vtime accounting.
>
> Signed-off-by: Frederic Weisbecker <[email protected]>
>
> ----------------------------------------------------------------
> Frederic Weisbecker (5):
> vtime: Gather vtime declarations to their own header file
> vtime: Make vtime_account_system() irqsafe
> kvm: Directly account vtime to system on guest switch
> cputime: Specialize irq vtime hooks
> cputime: Separate irqtime accounting from generic vtime
>
> arch/ia64/kernel/time.c | 8 ++++----
> arch/powerpc/kernel/time.c | 4 ++--
> arch/s390/kernel/vtime.c | 4 ++++
> arch/s390/kvm/kvm-s390.c | 4 ----
> include/linux/hardirq.h | 15 +++-----------
> include/linux/kernel_stat.h | 9 +--------
> include/linux/kvm_host.h | 12 +++++++++--
> include/linux/vtime.h | 47 +++++++++++++++++++++++++++++++++++++++++++
> kernel/sched/cputime.c | 20 +++++++++++++-----
> kernel/softirq.c | 6 +++---
> 10 files changed, 89 insertions(+), 40 deletions(-)
> create mode 100644 include/linux/vtime.h
Pulled, thanks Frederic!
Ingo