Not sure to which tree this should go. The scheduler one may be.
Anyway if you're fine with it, it is pullable at:
git://github.com/fweisbec/linux-dynticks.git
virt-cputime
This is only built tested on the relevant archs.
I wish we could do more vtime cputime accounting consolidation
but archs do the things pretty differently although I bet the
behaviour could be more unified.
Frederic Weisbecker (4):
cputime: Generalize CONFIG_VIRT_CPU_ACCOUNTING
sched: Move cputime code to its own file
cputime: Consolidate vtime handling on context switch
s390: Remove leftover account_tick_vtime() header
arch/Kconfig | 3 +
arch/ia64/Kconfig | 12 +-
arch/ia64/include/asm/switch_to.h | 8 -
arch/ia64/kernel/time.c | 4 +-
arch/powerpc/include/asm/time.h | 6 -
arch/powerpc/kernel/process.c | 3 -
arch/powerpc/kernel/time.c | 6 +
arch/powerpc/platforms/Kconfig.cputype | 16 +-
arch/s390/Kconfig | 5 +-
arch/s390/include/asm/switch_to.h | 4 -
arch/s390/kernel/vtime.c | 4 +-
include/linux/kernel_stat.h | 6 +
init/Kconfig | 13 +
kernel/sched/Makefile | 2 +-
kernel/sched/core.c | 552 +-------------------------------
kernel/sched/cputime.c | 497 ++++++++++++++++++++++++++++
kernel/sched/sched.h | 63 ++++
17 files changed, 600 insertions(+), 604 deletions(-)
create mode 100644 kernel/sched/cputime.c
--
1.7.5.4
S390, ia64 and powerpc all define their own version
of CONFIG_VIRT_CPU_ACCOUNTING. Generalize the config
and its description to a single place to avoid
duplication.
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: Martin Schwidefsky <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Peter Zijlstra <[email protected]>
---
arch/Kconfig | 3 +++
arch/ia64/Kconfig | 12 +-----------
arch/powerpc/platforms/Kconfig.cputype | 16 +---------------
arch/s390/Kconfig | 5 ++---
init/Kconfig | 13 +++++++++++++
5 files changed, 20 insertions(+), 29 deletions(-)
diff --git a/arch/Kconfig b/arch/Kconfig
index 8c3d957..ff712af 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -274,4 +274,7 @@ config SECCOMP_FILTER
See Documentation/prctl/seccomp_filter.txt for details.
+config HAVE_VIRT_CPU_ACCOUNTING
+ bool
+
source "kernel/gcov/Kconfig"
diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig
index 8186ec5..509af14 100644
--- a/arch/ia64/Kconfig
+++ b/arch/ia64/Kconfig
@@ -25,6 +25,7 @@ config IA64
select HAVE_GENERIC_HARDIRQS
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
+ select HAVE_VIRT_CPU_ACCOUNTING
select ARCH_DISCARD_MEMBLOCK
select GENERIC_IRQ_PROBE
select GENERIC_PENDING_IRQ if SMP
@@ -341,17 +342,6 @@ config FORCE_MAX_ZONEORDER
default "17" if HUGETLB_PAGE
default "11"
-config VIRT_CPU_ACCOUNTING
- bool "Deterministic task and CPU time accounting"
- default n
- help
- Select this option to enable more accurate task and CPU time
- accounting. This is done by reading a CPU counter on each
- kernel entry and exit and on transitions within the kernel
- between system, softirq and hardirq state, so there is a
- small performance impact.
- If in doubt, say N here.
-
config SMP
bool "Symmetric multi-processing support"
select USE_GENERIC_SMP_HELPERS
diff --git a/arch/powerpc/platforms/Kconfig.cputype b/arch/powerpc/platforms/Kconfig.cputype
index 61c9550..2a896de 100644
--- a/arch/powerpc/platforms/Kconfig.cputype
+++ b/arch/powerpc/platforms/Kconfig.cputype
@@ -1,6 +1,7 @@
config PPC64
bool "64-bit kernel"
default n
+ select HAVE_VIRT_CPU_ACCOUNTING
help
This option selects whether a 32-bit or a 64-bit kernel
will be built.
@@ -333,21 +334,6 @@ config PPC_MM_SLICES
default y if (!PPC_FSL_BOOK3E && PPC64 && HUGETLB_PAGE) || (PPC_STD_MMU_64 && PPC_64K_PAGES)
default n
-config VIRT_CPU_ACCOUNTING
- bool "Deterministic task and CPU time accounting"
- depends on PPC64
- default y
- help
- Select this option to enable more accurate task and CPU time
- accounting. This is done by reading a CPU counter on each
- kernel entry and exit and on transitions within the kernel
- between system, softirq and hardirq state, so there is a
- small performance impact. This also enables accounting of
- stolen time on logically-partitioned systems running on
- IBM POWER5-based machines.
-
- If in doubt, say Y here.
-
config PPC_HAVE_PMU_SUPPORT
bool
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index a39b469..351aa40 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -49,9 +49,6 @@ config GENERIC_LOCKBREAK
config PGSTE
def_bool y if KVM
-config VIRT_CPU_ACCOUNTING
- def_bool y
-
config ARCH_SUPPORTS_DEBUG_PAGEALLOC
def_bool y
@@ -88,6 +85,8 @@ config S390
select HAVE_MEMBLOCK
select HAVE_MEMBLOCK_NODE_MAP
select HAVE_CMPXCHG_LOCAL
+ select HAVE_VIRT_CPU_ACCOUNTING
+ select VIRT_CPU_ACCOUNTING
select ARCH_DISCARD_MEMBLOCK
select ARCH_INLINE_SPIN_TRYLOCK
select ARCH_INLINE_SPIN_TRYLOCK_BH
diff --git a/init/Kconfig b/init/Kconfig
index d07dcf9..d3f04e1 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -267,6 +267,19 @@ config POSIX_MQUEUE_SYSCTL
depends on SYSCTL
default y
+config VIRT_CPU_ACCOUNTING
+ bool "Deterministic task and CPU time accounting"
+ depends on HAVE_VIRT_CPU_ACCOUNTING
+ default y if PPC64
+ help
+ Select this option to enable more accurate task and CPU time
+ accounting. This is done by reading a CPU counter on each
+ kernel entry and exit and on transitions within the kernel
+ between system, softirq and hardirq state, so there is a
+ small performance impact. This also enables accounting of
+ stolen time on logically-partitioned systems running on
+ IBM POWER5-based machines.
+
config BSD_PROCESS_ACCT
bool "BSD Process Accounting"
help
--
1.7.5.4
The archs that implement virtual cputime accounting all
flush the cputime of a task when it gets descheduled
and sometimes set up some ground initialization for the
next task to account its cputime.
These archs all put their own hooks in their context
switch callbacks and handle the off-case themselves.
Consolidate this by creating a new account_switch_vtime()
callback called in generic code right after a context switch
and that these archs must implement to flush the prev task
cputime and initialize the next task cputime related state.
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: Martin Schwidefsky <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Peter Zijlstra <[email protected]>
---
arch/ia64/include/asm/switch_to.h | 8 --------
arch/ia64/kernel/time.c | 4 ++--
arch/powerpc/include/asm/time.h | 6 ------
arch/powerpc/kernel/process.c | 3 ---
arch/powerpc/kernel/time.c | 6 ++++++
arch/s390/include/asm/switch_to.h | 2 --
arch/s390/kernel/vtime.c | 4 ++--
include/linux/kernel_stat.h | 6 ++++++
kernel/sched/core.c | 1 +
9 files changed, 17 insertions(+), 23 deletions(-)
diff --git a/arch/ia64/include/asm/switch_to.h b/arch/ia64/include/asm/switch_to.h
index cb2412f..d38c7ea 100644
--- a/arch/ia64/include/asm/switch_to.h
+++ b/arch/ia64/include/asm/switch_to.h
@@ -30,13 +30,6 @@ extern struct task_struct *ia64_switch_to (void *next_task);
extern void ia64_save_extra (struct task_struct *task);
extern void ia64_load_extra (struct task_struct *task);
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct *next);
-# define IA64_ACCOUNT_ON_SWITCH(p,n) ia64_account_on_switch(p,n)
-#else
-# define IA64_ACCOUNT_ON_SWITCH(p,n)
-#endif
-
#ifdef CONFIG_PERFMON
DECLARE_PER_CPU(unsigned long, pfm_syst_info);
# define PERFMON_IS_SYSWIDE() (__get_cpu_var(pfm_syst_info) & 0x1)
@@ -49,7 +42,6 @@ extern void ia64_account_on_switch (struct task_struct *prev, struct task_struct
|| PERFMON_IS_SYSWIDE())
#define __switch_to(prev,next,last) do { \
- IA64_ACCOUNT_ON_SWITCH(prev, next); \
if (IA64_HAS_EXTRA_STATE(prev)) \
ia64_save_extra(prev); \
if (IA64_HAS_EXTRA_STATE(next)) \
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index ecc904b..6247197 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -88,10 +88,10 @@ extern cputime_t cycle_to_cputime(u64 cyc);
* accumulated times to the current process, and to prepare accounting on
* the next process.
*/
-void ia64_account_on_switch(struct task_struct *prev, struct task_struct *next)
+void account_switch_vtime(struct task_struct *prev)
{
struct thread_info *pi = task_thread_info(prev);
- struct thread_info *ni = task_thread_info(next);
+ struct thread_info *ni = task_thread_info(current);
cputime_t delta_stime, delta_utime;
__u64 now;
diff --git a/arch/powerpc/include/asm/time.h b/arch/powerpc/include/asm/time.h
index 3b4b4a8..c1f2676 100644
--- a/arch/powerpc/include/asm/time.h
+++ b/arch/powerpc/include/asm/time.h
@@ -197,12 +197,6 @@ struct cpu_usage {
DECLARE_PER_CPU(struct cpu_usage, cpu_usage_array);
-#if defined(CONFIG_VIRT_CPU_ACCOUNTING)
-#define account_process_vtime(tsk) account_process_tick(tsk, 0)
-#else
-#define account_process_vtime(tsk) do { } while (0)
-#endif
-
extern void secondary_cpu_time_init(void);
DECLARE_PER_CPU(u64, decrementers_next_tb);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 710f400..d73fa99 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -514,9 +514,6 @@ struct task_struct *__switch_to(struct task_struct *prev,
local_irq_save(flags);
- account_system_vtime(current);
- account_process_vtime(current);
-
/*
* We can't take a PMU exception inside _switch() since there is a
* window where the kernel stack SLB and the kernel stack are out
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index be171ee..49da7f0 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -366,6 +366,12 @@ void account_process_tick(struct task_struct *tsk, int user_tick)
account_user_time(tsk, utime, utimescaled);
}
+void account_switch_vtime(struct task_struct *prev)
+{
+ account_system_vtime(prev);
+ account_process_tick(prev, 0);
+}
+
#else /* ! CONFIG_VIRT_CPU_ACCOUNTING */
#define calc_cputime_factors()
#endif
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index f223068..e7f9b3d 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -89,12 +89,10 @@ static inline void restore_access_regs(unsigned int *acrs)
prev = __switch_to(prev,next); \
} while (0)
-extern void account_vtime(struct task_struct *, struct task_struct *);
extern void account_tick_vtime(struct task_struct *);
#define finish_arch_switch(prev) do { \
set_fs(current->thread.mm_segment); \
- account_vtime(prev, current); \
} while (0)
#endif /* __ASM_SWITCH_TO_H */
diff --git a/arch/s390/kernel/vtime.c b/arch/s390/kernel/vtime.c
index 39ebff5..506e9bd 100644
--- a/arch/s390/kernel/vtime.c
+++ b/arch/s390/kernel/vtime.c
@@ -86,7 +86,7 @@ static void do_account_vtime(struct task_struct *tsk, int hardirq_offset)
}
}
-void account_vtime(struct task_struct *prev, struct task_struct *next)
+void account_switch_vtime(struct task_struct *prev)
{
struct thread_info *ti;
@@ -94,7 +94,7 @@ void account_vtime(struct task_struct *prev, struct task_struct *next)
ti = task_thread_info(prev);
ti->user_timer = S390_lowcore.user_timer;
ti->system_timer = S390_lowcore.system_timer;
- ti = task_thread_info(next);
+ ti = task_thread_info(current);
S390_lowcore.user_timer = ti->user_timer;
S390_lowcore.system_timer = ti->system_timer;
}
diff --git a/include/linux/kernel_stat.h b/include/linux/kernel_stat.h
index 2fbd905..bbe5d15 100644
--- a/include/linux/kernel_stat.h
+++ b/include/linux/kernel_stat.h
@@ -130,4 +130,10 @@ 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 account_switch_vtime(struct task_struct *prev);
+#else
+static inline void account_switch_vtime(struct task_struct *prev) { }
+#endif
+
#endif /* _LINUX_KERNEL_STAT_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4f89f42..d34a150 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1796,6 +1796,7 @@ static void finish_task_switch(struct rq *rq, struct task_struct *prev)
* Manfred Spraul <[email protected]>
*/
prev_state = prev->state;
+ account_switch_vtime(prev);
finish_arch_switch(prev);
#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
local_irq_disable();
--
1.7.5.4
The function doesn't seem to exist anymore.
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: Martin Schwidefsky <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Peter Zijlstra <[email protected]>
---
arch/s390/include/asm/switch_to.h | 2 --
1 files changed, 0 insertions(+), 2 deletions(-)
diff --git a/arch/s390/include/asm/switch_to.h b/arch/s390/include/asm/switch_to.h
index e7f9b3d..314cc94 100644
--- a/arch/s390/include/asm/switch_to.h
+++ b/arch/s390/include/asm/switch_to.h
@@ -89,8 +89,6 @@ static inline void restore_access_regs(unsigned int *acrs)
prev = __switch_to(prev,next); \
} while (0)
-extern void account_tick_vtime(struct task_struct *);
-
#define finish_arch_switch(prev) do { \
set_fs(current->thread.mm_segment); \
} while (0)
--
1.7.5.4
Extract cputime code from the giant sched/core.c and
put it in its own file. This make it easier to deal with
this particular area and de-bloat a bit more core.c
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: Martin Schwidefsky <[email protected]>
Cc: Heiko Carstens <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Thomas Gleixner <[email protected]>
Cc: Peter Zijlstra <[email protected]>
---
kernel/sched/Makefile | 2 +-
kernel/sched/core.c | 551 +-----------------------------------------------
kernel/sched/cputime.c | 497 +++++++++++++++++++++++++++++++++++++++++++
kernel/sched/sched.h | 63 ++++++
4 files changed, 563 insertions(+), 550 deletions(-)
create mode 100644 kernel/sched/cputime.c
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 173ea52..f06d249 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -11,7 +11,7 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
endif
-obj-y += core.o clock.o idle_task.o fair.o rt.o stop_task.o
+obj-y += core.o clock.o cputime.o idle_task.o fair.o rt.o stop_task.o
obj-$(CONFIG_SMP) += cpupri.o
obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o
obj-$(CONFIG_SCHEDSTATS) += stats.o
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d5594a4..4f89f42 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -740,126 +740,6 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
dequeue_task(rq, p, flags);
}
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-
-/*
- * There are no locks covering percpu hardirq/softirq time.
- * They are only modified in account_system_vtime, on corresponding CPU
- * with interrupts disabled. So, writes are safe.
- * They are read and saved off onto struct rq in update_rq_clock().
- * This may result in other CPU reading this CPU's irq time and can
- * race with irq/account_system_vtime on this CPU. We would either get old
- * or new value with a side effect of accounting a slice of irq time to wrong
- * task when irq is in progress while we read rq->clock. That is a worthy
- * compromise in place of having locks on each irq in account_system_time.
- */
-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;
-}
-
-void disable_sched_clock_irqtime(void)
-{
- sched_clock_irqtime = 0;
-}
-
-#ifndef CONFIG_64BIT
-static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
-
-static inline void irq_time_write_begin(void)
-{
- __this_cpu_inc(irq_time_seq.sequence);
- smp_wmb();
-}
-
-static inline void irq_time_write_end(void)
-{
- smp_wmb();
- __this_cpu_inc(irq_time_seq.sequence);
-}
-
-static inline u64 irq_time_read(int cpu)
-{
- u64 irq_time;
- unsigned seq;
-
- do {
- seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
- irq_time = per_cpu(cpu_softirq_time, cpu) +
- per_cpu(cpu_hardirq_time, cpu);
- } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
-
- return irq_time;
-}
-#else /* CONFIG_64BIT */
-static inline void irq_time_write_begin(void)
-{
-}
-
-static inline void irq_time_write_end(void)
-{
-}
-
-static inline u64 irq_time_read(int cpu)
-{
- return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
-}
-#endif /* CONFIG_64BIT */
-
-/*
- * Called before incrementing preempt_count on {soft,}irq_enter
- * and before decrementing preempt_count on {soft,}irq_exit.
- */
-void account_system_vtime(struct task_struct *curr)
-{
- unsigned long flags;
- s64 delta;
- int cpu;
-
- if (!sched_clock_irqtime)
- return;
-
- local_irq_save(flags);
-
- cpu = smp_processor_id();
- delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
- __this_cpu_add(irq_start_time, delta);
-
- irq_time_write_begin();
- /*
- * 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 (hardirq_count())
- __this_cpu_add(cpu_hardirq_time, delta);
- else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
- __this_cpu_add(cpu_softirq_time, delta);
-
- irq_time_write_end();
- local_irq_restore(flags);
-}
-EXPORT_SYMBOL_GPL(account_system_vtime);
-
-#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-#ifdef CONFIG_PARAVIRT
-static inline u64 steal_ticks(u64 steal)
-{
- if (unlikely(steal > NSEC_PER_SEC))
- return div_u64(steal, TICK_NSEC);
-
- return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
-}
-#endif
-
static void update_rq_clock_task(struct rq *rq, s64 delta)
{
/*
@@ -920,43 +800,6 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
#endif
}
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-static int irqtime_account_hi_update(void)
-{
- u64 *cpustat = kcpustat_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 (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ])
- ret = 1;
- local_irq_restore(flags);
- return ret;
-}
-
-static int irqtime_account_si_update(void)
-{
- u64 *cpustat = kcpustat_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 (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ])
- ret = 1;
- local_irq_restore(flags);
- return ret;
-}
-
-#else /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-#define sched_clock_irqtime (0)
-
-#endif
-
void sched_set_stop_task(int cpu, struct task_struct *stop)
{
struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
@@ -2679,398 +2522,6 @@ unsigned long long task_sched_runtime(struct task_struct *p)
return ns;
}
-#ifdef CONFIG_CGROUP_CPUACCT
-struct cgroup_subsys cpuacct_subsys;
-struct cpuacct root_cpuacct;
-#endif
-
-static inline void task_group_account_field(struct task_struct *p, int index,
- u64 tmp)
-{
-#ifdef CONFIG_CGROUP_CPUACCT
- struct kernel_cpustat *kcpustat;
- struct cpuacct *ca;
-#endif
- /*
- * Since all updates are sure to touch the root cgroup, we
- * get ourselves ahead and touch it first. If the root cgroup
- * is the only cgroup, then nothing else should be necessary.
- *
- */
- __get_cpu_var(kernel_cpustat).cpustat[index] += tmp;
-
-#ifdef CONFIG_CGROUP_CPUACCT
- if (unlikely(!cpuacct_subsys.active))
- return;
-
- rcu_read_lock();
- ca = task_ca(p);
- while (ca && (ca != &root_cpuacct)) {
- kcpustat = this_cpu_ptr(ca->cpustat);
- kcpustat->cpustat[index] += tmp;
- ca = parent_ca(ca);
- }
- rcu_read_unlock();
-#endif
-}
-
-
-/*
- * Account user cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in user space since the last update
- * @cputime_scaled: cputime scaled by cpu frequency
- */
-void account_user_time(struct task_struct *p, cputime_t cputime,
- cputime_t cputime_scaled)
-{
- int index;
-
- /* Add user time to process. */
- p->utime += cputime;
- p->utimescaled += cputime_scaled;
- account_group_user_time(p, cputime);
-
- index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
-
- /* Add user time to cpustat. */
- task_group_account_field(p, index, (__force u64) cputime);
-
- /* Account for user time used */
- acct_update_integrals(p);
-}
-
-/*
- * Account guest cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in virtual machine since the last update
- * @cputime_scaled: cputime scaled by cpu frequency
- */
-static void account_guest_time(struct task_struct *p, cputime_t cputime,
- cputime_t cputime_scaled)
-{
- u64 *cpustat = kcpustat_this_cpu->cpustat;
-
- /* Add guest time to process. */
- p->utime += cputime;
- p->utimescaled += cputime_scaled;
- account_group_user_time(p, cputime);
- p->gtime += cputime;
-
- /* Add guest time to cpustat. */
- if (TASK_NICE(p) > 0) {
- cpustat[CPUTIME_NICE] += (__force u64) cputime;
- cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
- } else {
- cpustat[CPUTIME_USER] += (__force u64) cputime;
- cpustat[CPUTIME_GUEST] += (__force u64) cputime;
- }
-}
-
-/*
- * Account system cpu time to a process and desired cpustat field
- * @p: the process that the cpu time gets accounted to
- * @cputime: the cpu time spent in kernel space since the last update
- * @cputime_scaled: cputime scaled by cpu frequency
- * @target_cputime64: pointer to cpustat field that has to be updated
- */
-static inline
-void __account_system_time(struct task_struct *p, cputime_t cputime,
- cputime_t cputime_scaled, int index)
-{
- /* Add system time to process. */
- p->stime += cputime;
- p->stimescaled += cputime_scaled;
- account_group_system_time(p, cputime);
-
- /* Add system time to cpustat. */
- task_group_account_field(p, index, (__force u64) cputime);
-
- /* Account for system time used */
- acct_update_integrals(p);
-}
-
-/*
- * Account system cpu time to a process.
- * @p: the process that the cpu time gets accounted to
- * @hardirq_offset: the offset to subtract from hardirq_count()
- * @cputime: the cpu time spent in kernel space since the last update
- * @cputime_scaled: cputime scaled by cpu frequency
- */
-void account_system_time(struct task_struct *p, int hardirq_offset,
- cputime_t cputime, cputime_t cputime_scaled)
-{
- int index;
-
- if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
- account_guest_time(p, cputime, cputime_scaled);
- return;
- }
-
- if (hardirq_count() - hardirq_offset)
- index = CPUTIME_IRQ;
- else if (in_serving_softirq())
- index = CPUTIME_SOFTIRQ;
- else
- index = CPUTIME_SYSTEM;
-
- __account_system_time(p, cputime, cputime_scaled, index);
-}
-
-/*
- * Account for involuntary wait time.
- * @cputime: the cpu time spent in involuntary wait
- */
-void account_steal_time(cputime_t cputime)
-{
- u64 *cpustat = kcpustat_this_cpu->cpustat;
-
- cpustat[CPUTIME_STEAL] += (__force u64) cputime;
-}
-
-/*
- * Account for idle time.
- * @cputime: the cpu time spent in idle wait
- */
-void account_idle_time(cputime_t cputime)
-{
- u64 *cpustat = kcpustat_this_cpu->cpustat;
- struct rq *rq = this_rq();
-
- if (atomic_read(&rq->nr_iowait) > 0)
- cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
- else
- cpustat[CPUTIME_IDLE] += (__force u64) cputime;
-}
-
-static __always_inline bool steal_account_process_tick(void)
-{
-#ifdef CONFIG_PARAVIRT
- if (static_key_false(¶virt_steal_enabled)) {
- u64 steal, st = 0;
-
- steal = paravirt_steal_clock(smp_processor_id());
- steal -= this_rq()->prev_steal_time;
-
- st = steal_ticks(steal);
- this_rq()->prev_steal_time += st * TICK_NSEC;
-
- account_steal_time(st);
- return st;
- }
-#endif
- return false;
-}
-
-#ifndef CONFIG_VIRT_CPU_ACCOUNTING
-
-#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);
- u64 *cpustat = kcpustat_this_cpu->cpustat;
-
- if (steal_account_process_tick())
- return;
-
- if (irqtime_account_hi_update()) {
- cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
- } else if (irqtime_account_si_update()) {
- cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
- } else if (this_cpu_ksoftirqd() == p) {
- /*
- * ksoftirqd time do not get accounted in cpu_softirq_time.
- * So, we have to handle it separately here.
- * Also, p->stime needs to be updated for ksoftirqd.
- */
- __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
- CPUTIME_SOFTIRQ);
- } 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,
- CPUTIME_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 /* CONFIG_IRQ_TIME_ACCOUNTING */
-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 /* CONFIG_IRQ_TIME_ACCOUNTING */
-
-/*
- * Account a single tick of cpu time.
- * @p: the process that the cpu time gets accounted to
- * @user_tick: indicates if the tick is a user or a system tick
- */
-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 (steal_account_process_tick())
- return;
-
- if (user_tick)
- account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
- else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
- account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
- one_jiffy_scaled);
- else
- account_idle_time(cputime_one_jiffy);
-}
-
-/*
- * Account multiple ticks of steal time.
- * @p: the process from which the cpu time has been stolen
- * @ticks: number of stolen ticks
- */
-void account_steal_ticks(unsigned long ticks)
-{
- account_steal_time(jiffies_to_cputime(ticks));
-}
-
-/*
- * Account multiple ticks of idle time.
- * @ticks: number of stolen 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));
-}
-
-#endif
-
-/*
- * Use precise platform statistics if available:
- */
-#ifdef CONFIG_VIRT_CPU_ACCOUNTING
-void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
-{
- *ut = p->utime;
- *st = p->stime;
-}
-
-void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
-{
- struct task_cputime cputime;
-
- thread_group_cputime(p, &cputime);
-
- *ut = cputime.utime;
- *st = cputime.stime;
-}
-#else
-
-#ifndef nsecs_to_cputime
-# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs)
-#endif
-
-void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
-{
- cputime_t rtime, utime = p->utime, total = utime + p->stime;
-
- /*
- * Use CFS's precise accounting:
- */
- rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
-
- if (total) {
- u64 temp = (__force u64) rtime;
-
- temp *= (__force u64) utime;
- do_div(temp, (__force u32) total);
- utime = (__force cputime_t) temp;
- } else
- utime = rtime;
-
- /*
- * Compare with previous values, to keep monotonicity:
- */
- p->prev_utime = max(p->prev_utime, utime);
- p->prev_stime = max(p->prev_stime, rtime - p->prev_utime);
-
- *ut = p->prev_utime;
- *st = p->prev_stime;
-}
-
-/*
- * Must be called with siglock held.
- */
-void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
-{
- struct signal_struct *sig = p->signal;
- struct task_cputime cputime;
- cputime_t rtime, utime, total;
-
- thread_group_cputime(p, &cputime);
-
- total = cputime.utime + cputime.stime;
- rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
-
- if (total) {
- u64 temp = (__force u64) rtime;
-
- temp *= (__force u64) cputime.utime;
- do_div(temp, (__force u32) total);
- utime = (__force cputime_t) temp;
- } else
- utime = rtime;
-
- sig->prev_utime = max(sig->prev_utime, utime);
- sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime);
-
- *ut = sig->prev_utime;
- *st = sig->prev_stime;
-}
-#endif
-
/*
* This function gets called by the timer code, with HZ frequency.
* We call it with interrupts disabled.
@@ -8175,6 +7626,8 @@ struct cgroup_subsys cpu_cgroup_subsys = {
* ([email protected]).
*/
+struct cpuacct root_cpuacct;
+
/* create a new cpu accounting group */
static struct cgroup_subsys_state *cpuacct_create(struct cgroup *cgrp)
{
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
new file mode 100644
index 0000000..fd5bd01
--- /dev/null
+++ b/kernel/sched/cputime.c
@@ -0,0 +1,497 @@
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/tsacct_kern.h>
+#include <linux/kernel_stat.h>
+#include "sched.h"
+
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+
+/*
+ * There are no locks covering percpu hardirq/softirq time.
+ * They are only modified in account_system_vtime, on corresponding CPU
+ * with interrupts disabled. So, writes are safe.
+ * They are read and saved off onto struct rq in update_rq_clock().
+ * This may result in other CPU reading this CPU's irq time and can
+ * race with irq/account_system_vtime on this CPU. We would either get old
+ * or new value with a side effect of accounting a slice of irq time to wrong
+ * task when irq is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each irq in account_system_time.
+ */
+DEFINE_PER_CPU(u64, cpu_hardirq_time);
+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;
+}
+
+void disable_sched_clock_irqtime(void)
+{
+ sched_clock_irqtime = 0;
+}
+
+#ifndef CONFIG_64BIT
+DEFINE_PER_CPU(seqcount_t, irq_time_seq);
+#endif /* CONFIG_64BIT */
+
+/*
+ * Called before incrementing preempt_count on {soft,}irq_enter
+ * and before decrementing preempt_count on {soft,}irq_exit.
+ */
+void account_system_vtime(struct task_struct *curr)
+{
+ unsigned long flags;
+ s64 delta;
+ int cpu;
+
+ if (!sched_clock_irqtime)
+ return;
+
+ local_irq_save(flags);
+
+ cpu = smp_processor_id();
+ delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
+ __this_cpu_add(irq_start_time, delta);
+
+ irq_time_write_begin();
+ /*
+ * 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 (hardirq_count())
+ __this_cpu_add(cpu_hardirq_time, delta);
+ else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+ __this_cpu_add(cpu_softirq_time, delta);
+
+ irq_time_write_end();
+ local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(account_system_vtime);
+
+static int irqtime_account_hi_update(void)
+{
+ u64 *cpustat = kcpustat_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 (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_IRQ])
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
+static int irqtime_account_si_update(void)
+{
+ u64 *cpustat = kcpustat_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 (nsecs_to_cputime64(latest_ns) > cpustat[CPUTIME_SOFTIRQ])
+ ret = 1;
+ local_irq_restore(flags);
+ return ret;
+}
+
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+#define sched_clock_irqtime (0)
+
+#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */
+
+static inline void task_group_account_field(struct task_struct *p, int index,
+ u64 tmp)
+{
+#ifdef CONFIG_CGROUP_CPUACCT
+ struct kernel_cpustat *kcpustat;
+ struct cpuacct *ca;
+#endif
+ /*
+ * Since all updates are sure to touch the root cgroup, we
+ * get ourselves ahead and touch it first. If the root cgroup
+ * is the only cgroup, then nothing else should be necessary.
+ *
+ */
+ __get_cpu_var(kernel_cpustat).cpustat[index] += tmp;
+
+#ifdef CONFIG_CGROUP_CPUACCT
+ if (unlikely(!cpuacct_subsys.active))
+ return;
+
+ rcu_read_lock();
+ ca = task_ca(p);
+ while (ca && (ca != &root_cpuacct)) {
+ kcpustat = this_cpu_ptr(ca->cpustat);
+ kcpustat->cpustat[index] += tmp;
+ ca = parent_ca(ca);
+ }
+ rcu_read_unlock();
+#endif
+}
+
+/*
+ * Account user cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in user space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+void account_user_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled)
+{
+ int index;
+
+ /* Add user time to process. */
+ p->utime += cputime;
+ p->utimescaled += cputime_scaled;
+ account_group_user_time(p, cputime);
+
+ index = (TASK_NICE(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
+
+ /* Add user time to cpustat. */
+ task_group_account_field(p, index, (__force u64) cputime);
+
+ /* Account for user time used */
+ acct_update_integrals(p);
+}
+
+/*
+ * Account guest cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in virtual machine since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+static void account_guest_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+ /* Add guest time to process. */
+ p->utime += cputime;
+ p->utimescaled += cputime_scaled;
+ account_group_user_time(p, cputime);
+ p->gtime += cputime;
+
+ /* Add guest time to cpustat. */
+ if (TASK_NICE(p) > 0) {
+ cpustat[CPUTIME_NICE] += (__force u64) cputime;
+ cpustat[CPUTIME_GUEST_NICE] += (__force u64) cputime;
+ } else {
+ cpustat[CPUTIME_USER] += (__force u64) cputime;
+ cpustat[CPUTIME_GUEST] += (__force u64) cputime;
+ }
+}
+
+/*
+ * Account system cpu time to a process and desired cpustat field
+ * @p: the process that the cpu time gets accounted to
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ * @target_cputime64: pointer to cpustat field that has to be updated
+ */
+static inline
+void __account_system_time(struct task_struct *p, cputime_t cputime,
+ cputime_t cputime_scaled, int index)
+{
+ /* Add system time to process. */
+ p->stime += cputime;
+ p->stimescaled += cputime_scaled;
+ account_group_system_time(p, cputime);
+
+ /* Add system time to cpustat. */
+ task_group_account_field(p, index, (__force u64) cputime);
+
+ /* Account for system time used */
+ acct_update_integrals(p);
+}
+
+/*
+ * Account system cpu time to a process.
+ * @p: the process that the cpu time gets accounted to
+ * @hardirq_offset: the offset to subtract from hardirq_count()
+ * @cputime: the cpu time spent in kernel space since the last update
+ * @cputime_scaled: cputime scaled by cpu frequency
+ */
+void account_system_time(struct task_struct *p, int hardirq_offset,
+ cputime_t cputime, cputime_t cputime_scaled)
+{
+ int index;
+
+ if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) {
+ account_guest_time(p, cputime, cputime_scaled);
+ return;
+ }
+
+ if (hardirq_count() - hardirq_offset)
+ index = CPUTIME_IRQ;
+ else if (in_serving_softirq())
+ index = CPUTIME_SOFTIRQ;
+ else
+ index = CPUTIME_SYSTEM;
+
+ __account_system_time(p, cputime, cputime_scaled, index);
+}
+
+/*
+ * Account for involuntary wait time.
+ * @cputime: the cpu time spent in involuntary wait
+ */
+void account_steal_time(cputime_t cputime)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+ cpustat[CPUTIME_STEAL] += (__force u64) cputime;
+}
+
+/*
+ * Account for idle time.
+ * @cputime: the cpu time spent in idle wait
+ */
+void account_idle_time(cputime_t cputime)
+{
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+ struct rq *rq = this_rq();
+
+ if (atomic_read(&rq->nr_iowait) > 0)
+ cpustat[CPUTIME_IOWAIT] += (__force u64) cputime;
+ else
+ cpustat[CPUTIME_IDLE] += (__force u64) cputime;
+}
+
+static __always_inline bool steal_account_process_tick(void)
+{
+#ifdef CONFIG_PARAVIRT
+ if (static_key_false(¶virt_steal_enabled)) {
+ u64 steal, st = 0;
+
+ steal = paravirt_steal_clock(smp_processor_id());
+ steal -= this_rq()->prev_steal_time;
+
+ st = steal_ticks(steal);
+ this_rq()->prev_steal_time += st * TICK_NSEC;
+
+ account_steal_time(st);
+ return st;
+ }
+#endif
+ return false;
+}
+
+#ifndef CONFIG_VIRT_CPU_ACCOUNTING
+
+#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);
+ u64 *cpustat = kcpustat_this_cpu->cpustat;
+
+ if (steal_account_process_tick())
+ return;
+
+ if (irqtime_account_hi_update()) {
+ cpustat[CPUTIME_IRQ] += (__force u64) cputime_one_jiffy;
+ } else if (irqtime_account_si_update()) {
+ cpustat[CPUTIME_SOFTIRQ] += (__force u64) cputime_one_jiffy;
+ } else if (this_cpu_ksoftirqd() == p) {
+ /*
+ * ksoftirqd time do not get accounted in cpu_softirq_time.
+ * So, we have to handle it separately here.
+ * Also, p->stime needs to be updated for ksoftirqd.
+ */
+ __account_system_time(p, cputime_one_jiffy, one_jiffy_scaled,
+ CPUTIME_SOFTIRQ);
+ } 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,
+ CPUTIME_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 /* CONFIG_IRQ_TIME_ACCOUNTING */
+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 /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+/*
+ * Account a single tick of cpu time.
+ * @p: the process that the cpu time gets accounted to
+ * @user_tick: indicates if the tick is a user or a system tick
+ */
+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 (steal_account_process_tick())
+ return;
+
+ if (user_tick)
+ account_user_time(p, cputime_one_jiffy, one_jiffy_scaled);
+ else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
+ account_system_time(p, HARDIRQ_OFFSET, cputime_one_jiffy,
+ one_jiffy_scaled);
+ else
+ account_idle_time(cputime_one_jiffy);
+}
+
+/*
+ * Account multiple ticks of steal time.
+ * @p: the process from which the cpu time has been stolen
+ * @ticks: number of stolen ticks
+ */
+void account_steal_ticks(unsigned long ticks)
+{
+ account_steal_time(jiffies_to_cputime(ticks));
+}
+
+/*
+ * Account multiple ticks of idle time.
+ * @ticks: number of stolen 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));
+}
+
+#endif
+
+/*
+ * Use precise platform statistics if available:
+ */
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+ *ut = p->utime;
+ *st = p->stime;
+}
+
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+ struct task_cputime cputime;
+
+ thread_group_cputime(p, &cputime);
+
+ *ut = cputime.utime;
+ *st = cputime.stime;
+}
+#else
+
+#ifndef nsecs_to_cputime
+# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs)
+#endif
+
+void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+ cputime_t rtime, utime = p->utime, total = utime + p->stime;
+
+ /*
+ * Use CFS's precise accounting:
+ */
+ rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
+
+ if (total) {
+ u64 temp = (__force u64) rtime;
+
+ temp *= (__force u64) utime;
+ do_div(temp, (__force u32) total);
+ utime = (__force cputime_t) temp;
+ } else
+ utime = rtime;
+
+ /*
+ * Compare with previous values, to keep monotonicity:
+ */
+ p->prev_utime = max(p->prev_utime, utime);
+ p->prev_stime = max(p->prev_stime, rtime - p->prev_utime);
+
+ *ut = p->prev_utime;
+ *st = p->prev_stime;
+}
+
+/*
+ * Must be called with siglock held.
+ */
+void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
+{
+ struct signal_struct *sig = p->signal;
+ struct task_cputime cputime;
+ cputime_t rtime, utime, total;
+
+ thread_group_cputime(p, &cputime);
+
+ total = cputime.utime + cputime.stime;
+ rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
+
+ if (total) {
+ u64 temp = (__force u64) rtime;
+
+ temp *= (__force u64) cputime.utime;
+ do_div(temp, (__force u32) total);
+ utime = (__force cputime_t) temp;
+ } else
+ utime = rtime;
+
+ sig->prev_utime = max(sig->prev_utime, utime);
+ sig->prev_stime = max(sig->prev_stime, rtime - sig->prev_utime);
+
+ *ut = sig->prev_utime;
+ *st = sig->prev_stime;
+}
+#endif
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6d52cea..197a20b 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -890,6 +890,9 @@ struct cpuacct {
struct kernel_cpustat __percpu *cpustat;
};
+extern struct cgroup_subsys cpuacct_subsys;
+extern struct cpuacct root_cpuacct;
+
/* return cpu accounting group corresponding to this container */
static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp)
{
@@ -916,6 +919,16 @@ extern void cpuacct_charge(struct task_struct *tsk, u64 cputime);
static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {}
#endif
+#ifdef CONFIG_PARAVIRT
+static inline u64 steal_ticks(u64 steal)
+{
+ if (unlikely(steal > NSEC_PER_SEC))
+ return div_u64(steal, TICK_NSEC);
+
+ return __iter_div_u64_rem(steal, TICK_NSEC, &steal);
+}
+#endif
+
static inline void inc_nr_running(struct rq *rq)
{
rq->nr_running++;
@@ -1157,4 +1170,54 @@ enum rq_nohz_flag_bits {
};
#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+
+DECLARE_PER_CPU(u64, cpu_hardirq_time);
+DECLARE_PER_CPU(u64, cpu_softirq_time);
+
+#ifndef CONFIG_64BIT
+DECLARE_PER_CPU(seqcount_t, irq_time_seq);
+
+static inline void irq_time_write_begin(void)
+{
+ __this_cpu_inc(irq_time_seq.sequence);
+ smp_wmb();
+}
+
+static inline void irq_time_write_end(void)
+{
+ smp_wmb();
+ __this_cpu_inc(irq_time_seq.sequence);
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+ u64 irq_time;
+ unsigned seq;
+
+ do {
+ seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
+ irq_time = per_cpu(cpu_softirq_time, cpu) +
+ per_cpu(cpu_hardirq_time, cpu);
+ } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
+
+ return irq_time;
+}
+#else /* CONFIG_64BIT */
+static inline void irq_time_write_begin(void)
+{
+}
+
+static inline void irq_time_write_end(void)
+{
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+ return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
+}
+#endif /* CONFIG_64BIT */
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
#endif
--
1.7.5.4
> This is only built tested on the relevant archs.
Built and run on ia64 ... seems to work (but I don't have any
tests that really show the difference between having this turned
on/off :-( )
-Tony
On Tue, 2012-06-19 at 15:43 +0200, Frederic Weisbecker wrote:
>
> I wish we could do more vtime cputime accounting consolidation
> but archs do the things pretty differently although I bet the
> behaviour could be more unified.
>
Yes.. so s390,ia64 use thread_info, ppc uses their paca (arch private
precursor to per-cpu data).
So I understand why s390,ia64 want the sched hook, but I don't see why
ppc would need it, their account_process_tick() can fold whatever they
need on the tick.
So I think reworking s390,ia64 to use per-cpu storage should get rid of
this switch hook altogether.
Now everybody using VIRT_CPU_ACCOUNTING has the
syscall/__irq_{enter,exit} hooks and uses 64bit cputime_t.
IRQ_TIME_ACCOUNTING only has the __irq_{enter,exit} hook and uses
unsigned long cputime_t, it adds cputime_one_jiffy every tick when the
per-cpu counter is ahead of the cputime.
We could merge both and do away with the 64bit cputime thing by keeping
a (2nd) per-cpu kernel_cpustat which we fill with optional syscall/irq
hooks and have account_process_tick() first check if any of the
fine-grained fields overflow and if not, fall back to the regular tick
accounting (much like an extended irqtime_account_process_tick).
This would merge the fine-grain and tick based code-paths and do away
with the whole cputime_t mess, it would also merge the VIRT and IRQ
paths and make Frederic's optional syscall accounting trivial.
Or am I missing something obvious here? -- its late after all.
I'll try and write some code tomorrow.
2012/6/21 Peter Zijlstra <[email protected]>:
> On Tue, 2012-06-19 at 15:43 +0200, Frederic Weisbecker wrote:
>>
>> I wish we could do more vtime cputime accounting consolidation
>> but archs do the things pretty differently although I bet the
>> behaviour could be more unified.
>>
> Yes.. so s390,ia64 use thread_info, ppc uses their paca (arch private
> precursor to per-cpu data).
>
> So I understand why s390,ia64 want the sched hook, but I don't see why
> ppc would need it, their account_process_tick() can fold whatever they
> need on the tick.
I think in any case you need to flush the time on a descheduling task otherwise
its pending time will be accounted later to the next task when it
receives an irq.
So I fear we still need that sched switch hook even with per cpu data. This
may be a simple account_system_vtime() call.
> So I think reworking s390,ia64 to use per-cpu storage should get rid of
> this switch hook altogether.
>
>
> Now everybody using VIRT_CPU_ACCOUNTING has the
> syscall/__irq_{enter,exit} hooks and uses 64bit cputime_t.
>
> IRQ_TIME_ACCOUNTING only has the __irq_{enter,exit} hook and uses
> unsigned long cputime_t, it adds cputime_one_jiffy every tick when the
> per-cpu counter is ahead of the cputime.
>
>
> We could merge both and do away with the 64bit cputime thing by keeping
> a (2nd) per-cpu kernel_cpustat which we fill with optional syscall/irq
> hooks and have account_process_tick() first check if any of the
> fine-grained fields overflow and if not, fall back to the regular tick
> accounting (much like an extended irqtime_account_process_tick).
>
>
> This would merge the fine-grain and tick based code-paths and do away
> with the whole cputime_t mess, it would also merge the VIRT and IRQ
> paths and make Frederic's optional syscall accounting trivial.
>
> Or am I missing something obvious here? -- its late after all.
No that looks pretty sensible.
> I'll try and write some code tomorrow.
Thanks!
On Thu, 21 Jun 2012 02:46:29 +0200
Frederic Weisbecker <[email protected]> wrote:
> 2012/6/21 Peter Zijlstra <[email protected]>:
> > On Tue, 2012-06-19 at 15:43 +0200, Frederic Weisbecker wrote:
> >>
> >> I wish we could do more vtime cputime accounting consolidation
> >> but archs do the things pretty differently although I bet the
> >> behaviour could be more unified.
> >>
> > Yes.. so s390,ia64 use thread_info, ppc uses their paca (arch private
> > precursor to per-cpu data).
s390 uses the prefix page / lowcore to accumulate some accounting information.
Which basically is per-cpu data with the advantage that it is accessible with
at address 0-8191 for each cpu. The entry code does not have to load a pointer
to get to that page, I would prefer NOT to use per-cpu data here.
> > So I understand why s390,ia64 want the sched hook, but I don't see why
> > ppc would need it, their account_process_tick() can fold whatever they
> > need on the tick.
>
> I think in any case you need to flush the time on a descheduling task otherwise
> its pending time will be accounted later to the next task when it
> receives an irq.
>
> So I fear we still need that sched switch hook even with per cpu data. This
> may be a simple account_system_vtime() call.
Indeed, the scheduler hook is needed to add the accumulated values to the
correct task.
> > So I think reworking s390,ia64 to use per-cpu storage should get rid of
> > this switch hook altogether.
If we get rid of the switch hook then the quality of the accounting numbers
will get significantly worse. Think of the scenario of a long running
background process and a task that repeatedly wakes up for a very short
time. Without the scheduler hook chances are good that the background task
is accounted all the accumulated user time.
--
blue skies,
Martin.
"Reality continues to ruin my life." - Calvin.
On Thu, 2012-06-21 at 02:46 +0200, Frederic Weisbecker wrote:
> > So I understand why s390,ia64 want the sched hook, but I don't see why
> > ppc would need it, their account_process_tick() can fold whatever they
> > need on the tick.
>
> I think in any case you need to flush the time on a descheduling task otherwise
> its pending time will be accounted later to the next task when it
> receives an irq.
>
> So I fear we still need that sched switch hook even with per cpu data. This
> may be a simple account_system_vtime() call.
Did I miss a per-task something in there?
On Thu, 2012-06-21 at 10:30 +0200, Peter Zijlstra wrote:
> On Thu, 2012-06-21 at 02:46 +0200, Frederic Weisbecker wrote:
> > > So I understand why s390,ia64 want the sched hook, but I don't see why
> > > ppc would need it, their account_process_tick() can fold whatever they
> > > need on the tick.
> >
> > I think in any case you need to flush the time on a descheduling task otherwise
> > its pending time will be accounted later to the next task when it
> > receives an irq.
> >
> > So I fear we still need that sched switch hook even with per cpu data. This
> > may be a simple account_system_vtime() call.
>
> Did I miss a per-task something in there?
Gah yeah.. I was staring too hard at the arch code and missed the task
accounting in the core code.
OK, so that switch hook stays :-)
On Thu, 2012-06-21 at 09:58 +0200, Martin Schwidefsky wrote:
> On Thu, 21 Jun 2012 02:46:29 +0200
> Frederic Weisbecker <[email protected]> wrote:
>
> > 2012/6/21 Peter Zijlstra <[email protected]>:
> > > On Tue, 2012-06-19 at 15:43 +0200, Frederic Weisbecker wrote:
> > >>
> > >> I wish we could do more vtime cputime accounting consolidation
> > >> but archs do the things pretty differently although I bet the
> > >> behaviour could be more unified.
> > >>
> > > Yes.. so s390,ia64 use thread_info, ppc uses their paca (arch private
> > > precursor to per-cpu data).
>
> s390 uses the prefix page / lowcore to accumulate some accounting information.
> Which basically is per-cpu data with the advantage that it is accessible with
> at address 0-8191 for each cpu. The entry code does not have to load a pointer
> to get to that page, I would prefer NOT to use per-cpu data here.
Yeah, same for ppc and their paca, I just meant to put the data in
per-cpu (your lowcore and ppc's paca qualify) storage instead of
per-task.
But seeing as I completely overlooked the per-task accounting this
doesn't matter anyway.
There being the per-task accounting also completely wrecks the proposal
I outlined. That only works if its only per-cpu accounting.
The alternative is going full 64bit ns and having the tick fallback do
TICK_NSEC increments. 32bit args that don't do VIRT_TIME or IRQ_TIME
won't like that though :/
So yeah, I did miss something obvious.. no cookies for me.
On Thu, Jun 21, 2012 at 02:04:24PM +0200, Peter Zijlstra wrote:
> On Thu, 2012-06-21 at 09:58 +0200, Martin Schwidefsky wrote:
> > On Thu, 21 Jun 2012 02:46:29 +0200
> > Frederic Weisbecker <[email protected]> wrote:
> >
> > > 2012/6/21 Peter Zijlstra <[email protected]>:
> > > > On Tue, 2012-06-19 at 15:43 +0200, Frederic Weisbecker wrote:
> > > >>
> > > >> I wish we could do more vtime cputime accounting consolidation
> > > >> but archs do the things pretty differently although I bet the
> > > >> behaviour could be more unified.
> > > >>
> > > > Yes.. so s390,ia64 use thread_info, ppc uses their paca (arch private
> > > > precursor to per-cpu data).
> >
> > s390 uses the prefix page / lowcore to accumulate some accounting information.
> > Which basically is per-cpu data with the advantage that it is accessible with
> > at address 0-8191 for each cpu. The entry code does not have to load a pointer
> > to get to that page, I would prefer NOT to use per-cpu data here.
>
> Yeah, same for ppc and their paca, I just meant to put the data in
> per-cpu (your lowcore and ppc's paca qualify) storage instead of
> per-task.
>
> But seeing as I completely overlooked the per-task accounting this
> doesn't matter anyway.
>
> There being the per-task accounting also completely wrecks the proposal
> I outlined. That only works if its only per-cpu accounting.
>
> The alternative is going full 64bit ns and having the tick fallback do
> TICK_NSEC increments. 32bit args that don't do VIRT_TIME or IRQ_TIME
> won't like that though :/
>
> So yeah, I did miss something obvious.. no cookies for me.
Yeah but the idea of a dynamic switching between tick based accounting
and virtual based one (account_system_vtime()) is still valuable to me.
That of course only makes sense if the arch uses some kind of "on-demand"
virtual accounting. Like using TIF flags for syscall slow path and jump
labels for exception hooks. Although in the longer term we should rather
hook on the syscall fastpath, but you get the idea.
How does that sound?
Another way would be to make the adaptive tickless thing depend on
the traditional CONFIG_VIRT_CPU_TIME. So it's simply enabled all the
time and we don't care. But we need syscalls/exceptions hooks for RCU
anyway, which is why I think an on-demand thing could make sense because
both RCU and vtime could use these on-demand hooks.
2012/7/9 Frederic Weisbecker <[email protected]>:
> On Tue, Jun 19, 2012 at 03:43:07PM +0200, Frederic Weisbecker wrote:
>> Not sure to which tree this should go. The scheduler one may be.
>> Anyway if you're fine with it, it is pullable at:
>>
>> git://github.com/fweisbec/linux-dynticks.git
>> virt-cputime
>
> Ping. Are you guys fine with the patchset?
Re-ping :)