| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <1465353004-15044-3-git-send-email-riel@redhat.com>
Date: Tue, 7 Jun 2016 22:30:01 -0400
From: riel@...hat.com
To: linux-kernel@...r.kernel.org
Cc: kernellwp@...il.com, mingo@...nel.org, peterz@...radead.org,
tglx@...utronix.de, fweisbec@...hat.com
Subject: [PATCH 2/5] nohz,cputime: remove VTIME_GEN vtime irq time code
From: Rik van Riel <riel@...hat.com>
The CONFIG_VIRT_CPU_ACCOUNTING_GEN irq time tracking code does not
appear to currently work right.
On CPUs that are nohz_full, people typically do not assign IRQs.
On the housekeeping CPU (when a system is booted up with nohz_full),
sampling should work ok to determine irq and softirq time use, but
that only covers the housekeeping CPU itself, not the other
non-nohz_full CPUs.
On CPUs that are nohz_idle (the typical way a distro kernel is
booted), irq time is not accounted at all while the CPU is idle,
due to the lack of timer ticks.
Remove the VTIME_GEN vtime irq time code. The next patch will
allow NO_HZ_FULL kernels to use the IRQ_TIME_ACCOUNTING code.
Signed-off-by: Rik van Riel <riel@...hat.com>
---
include/linux/vtime.h | 32 +++++++++++++----------------
kernel/sched/cputime.c | 55 ++++++++++++++++++++++++++++----------------------
2 files changed, 45 insertions(+), 42 deletions(-)
diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index fa2196990f84..3b384bf5ce1a 100644
--- a/include/linux/vtime.h
+++ b/include/linux/vtime.h
@@ -64,17 +64,6 @@ extern void vtime_account_system(struct task_struct *tsk);
extern void vtime_account_idle(struct task_struct *tsk);
extern void vtime_account_user(struct task_struct *tsk);
-#ifdef __ARCH_HAS_VTIME_ACCOUNT
-extern void vtime_account_irq_enter(struct task_struct *tsk);
-#else
-extern void vtime_common_account_irq_enter(struct task_struct *tsk);
-static inline void vtime_account_irq_enter(struct task_struct *tsk)
-{
- if (vtime_accounting_cpu_enabled())
- vtime_common_account_irq_enter(tsk);
-}
-#endif /* __ARCH_HAS_VTIME_ACCOUNT */
-
#else /* !CONFIG_VIRT_CPU_ACCOUNTING */
static inline void vtime_task_switch(struct task_struct *prev) { }
@@ -85,13 +74,8 @@ static inline void vtime_account_irq_enter(struct task_struct *tsk) { }
#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
extern void arch_vtime_task_switch(struct task_struct *tsk);
-extern void vtime_gen_account_irq_exit(struct task_struct *tsk);
-
-static inline void vtime_account_irq_exit(struct task_struct *tsk)
-{
- if (vtime_accounting_cpu_enabled())
- vtime_gen_account_irq_exit(tsk);
-}
+static inline void vtime_account_irq_enter(struct task_struct *tsk) { }
+static inline void vtime_account_irq_exit(struct task_struct *tsk) { }
extern void vtime_user_enter(struct task_struct *tsk);
@@ -113,6 +97,18 @@ static inline void vtime_user_exit(struct task_struct *tsk) { }
static inline void vtime_guest_enter(struct task_struct *tsk) { }
static inline void vtime_guest_exit(struct task_struct *tsk) { }
static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { }
+
+#ifdef __ARCH_HAS_VTIME_ACCOUNT
+extern void vtime_account_irq_enter(struct task_struct *tsk);
+#else
+extern void vtime_common_account_irq_enter(struct task_struct *tsk);
+static inline void vtime_account_irq_enter(struct task_struct *tsk)
+{
+ if (vtime_accounting_cpu_enabled())
+ vtime_common_account_irq_enter(tsk);
+}
+#endif /* __ARCH_HAS_VTIME_ACCOUNT */
+
#endif
#ifdef CONFIG_IRQ_TIME_ACCOUNTING
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 4bd6d1b774ab..2f862dfdb520 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -103,10 +103,10 @@ static unsigned long irqtime_account_si_update(void)
u64 softirq;
local_irq_save(flags);
- delta = this_cpu_read(cpu_softirq_time) - cpustat[CPUTIME_SOFTIRQ];
- si_jiffies = cputime_to_jiffies(delta);
+ softirq = this_cpu_read(cpu_softirq_time) - cpustat[CPUTIME_SOFTIRQ];
+ si_jiffies = cputime_to_jiffies(softirq);
if (si_jiffies)
- cpustat[CPUSTIME_SOFTIRQ] += jiffies_to_cputime(si_jiffies);
+ cpustat[CPUTIME_SOFTIRQ] += jiffies_to_cputime(si_jiffies);
local_irq_restore(flags);
return si_jiffies;
}
@@ -115,6 +115,16 @@ static unsigned long irqtime_account_si_update(void)
#define sched_clock_irqtime (0)
+static unsigned long irqtime_account_hi_update(void)
+{
+ return 0;
+}
+
+static unsigned long irqtime_account_si_update(void)
+{
+ return 0;
+}
+
#endif /* !CONFIG_IRQ_TIME_ACCOUNTING */
static inline void task_group_account_field(struct task_struct *p, int index,
@@ -346,7 +356,6 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
{
cputime_t scaled = cputime_to_scaled(cputime_one_jiffy);
u64 cputime = (__force u64) cputime_one_jiffy;
- u64 *cpustat = kcpustat_this_cpu->cpustat;
unsigned long other;
/*
@@ -703,16 +712,26 @@ static cputime_t get_vtime_delta(struct task_struct *tsk)
return jiffies_to_cputime(delta);
}
+/* Account per-cpu irq, softirq, and steal time. Not accounted to a task. */
+static cputime_t __vtime_account_other(void)
+{
+ unsigned long ticks;
+
+ ticks = steal_account_process_tick();
+ ticks += irqtime_account_hi_update();
+ ticks += irqtime_account_si_update();
+
+ return jiffies_to_cputime(ticks);
+}
+
static void __vtime_account_system(struct task_struct *tsk)
{
- cputime_t steal_time;
cputime_t delta_cpu = get_vtime_delta(tsk);
- unsigned long delta_st = steal_account_process_tick();
- steal_time = jiffies_to_cputime(delta_st);
+ cputime_t other = __vtime_account_other();
- if (steal_time >= delta_cpu)
+ if (other >= delta_cpu)
return;
- delta_cpu -= steal_time;
+ delta_cpu -= other;
account_system_time(tsk, irq_count(), delta_cpu, cputime_to_scaled(delta_cpu));
}
@@ -726,16 +745,6 @@ void vtime_account_system(struct task_struct *tsk)
write_seqcount_end(&tsk->vtime_seqcount);
}
-void vtime_gen_account_irq_exit(struct task_struct *tsk)
-{
- write_seqcount_begin(&tsk->vtime_seqcount);
- if (vtime_delta(tsk))
- __vtime_account_system(tsk);
- if (context_tracking_in_user())
- tsk->vtime_snap_whence = VTIME_USER;
- write_seqcount_end(&tsk->vtime_seqcount);
-}
-
void vtime_account_user(struct task_struct *tsk)
{
cputime_t delta_cpu;
@@ -743,16 +752,14 @@ void vtime_account_user(struct task_struct *tsk)
write_seqcount_begin(&tsk->vtime_seqcount);
tsk->vtime_snap_whence = VTIME_SYS;
if (vtime_delta(tsk)) {
- cputime_t steal_time;
- unsigned long delta_st = steal_account_process_tick();
+ cputime_t other = __vtime_account_other();
delta_cpu = get_vtime_delta(tsk);
- steal_time = jiffies_to_cputime(delta_st);
- if (steal_time >= delta_cpu) {
+ if (other >= delta_cpu) {
write_seqcount_end(&tsk->vtime_seqcount);
return;
}
- delta_cpu -= steal_time;
+ delta_cpu -= other;
account_user_time(tsk, delta_cpu, cputime_to_scaled(delta_cpu));
}
write_seqcount_end(&tsk->vtime_seqcount);
--
2.5.5
Powered by blists - more mailing lists