[PATCH 08/12] housekeeping: Introduce housekeeping flags

From: Frederic Weisbecker
Date: Thu Oct 26 2017 - 22:43:18 EST


Before we implement isolcpus under housekeeping, we need the isolation
features to be more finegrained. For example some people want nohz_full
without the full scheduler isolation, others want full scheduler
isolation without nohz_full.

So let's cut all these isolation features piecewise, at the risk of
overcutting it right now. We can still merge some flags later if they
always make sense together.

Signed-off-by: Frederic Weisbecker <frederic@xxxxxxxxxx>
Cc: Chris Metcalf <cmetcalf@xxxxxxxxxxxx>
Cc: Christoph Lameter <cl@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Luiz Capitulino <lcapitulino@xxxxxxxxxx>
Cc: Mike Galbraith <efault@xxxxxx>
Cc: Paul E. McKenney <paulmck@xxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rik van Riel <riel@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Wanpeng Li <kernellwp@xxxxxxxxx>
---
drivers/net/ethernet/tile/tilegx.c | 4 ++--
include/linux/sched/isolation.h | 26 +++++++++++++++++---------
kernel/rcu/tree_plugin.h | 2 +-
kernel/rcu/update.c | 2 +-
kernel/sched/core.c | 8 ++++----
kernel/sched/fair.c | 2 +-
kernel/sched/isolation.c | 26 +++++++++++++++-----------
kernel/watchdog.c | 3 ++-
8 files changed, 43 insertions(+), 30 deletions(-)

diff --git a/drivers/net/ethernet/tile/tilegx.c b/drivers/net/ethernet/tile/tilegx.c
index 27a3272..b3e5816 100644
--- a/drivers/net/ethernet/tile/tilegx.c
+++ b/drivers/net/ethernet/tile/tilegx.c
@@ -2270,8 +2270,8 @@ static int __init tile_net_init_module(void)
tile_net_dev_init(name, mac);

if (!network_cpus_init())
- cpumask_and(&network_cpus_map, housekeeping_cpumask(),
- cpu_online_mask);
+ cpumask_and(&network_cpus_map,
+ housekeeping_cpumask(HK_FLAG_MISC), cpu_online_mask);

return 0;
}
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index 93ac2367..9bb753e 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -5,35 +5,43 @@
#include <linux/init.h>
#include <linux/tick.h>

+enum hk_flags {
+ HK_FLAG_TIMER = 1,
+ HK_FLAG_RCU = (1 << 1),
+ HK_FLAG_MISC = (1 << 2),
+ HK_FLAG_SCHED = (1 << 3),
+};
+
#ifdef CONFIG_CPU_ISOLATION
DECLARE_STATIC_KEY_FALSE(housekeeping_overriden);
-extern int housekeeping_any_cpu(void);
-extern const struct cpumask *housekeeping_cpumask(void);
-extern void housekeeping_affine(struct task_struct *t);
-extern bool housekeeping_test_cpu(int cpu);
+extern int housekeeping_any_cpu(enum hk_flags flags);
+extern const struct cpumask *housekeeping_cpumask(enum hk_flags flags);
+extern void housekeeping_affine(struct task_struct *t, enum hk_flags flags);
+extern bool housekeeping_test_cpu(int cpu, enum hk_flags flags);
extern void __init housekeeping_init(void);

#else

-static inline int housekeeping_any_cpu(void)
+static inline int housekeeping_any_cpu(enum hk_flags flags)
{
return smp_processor_id();
}

-static inline const struct cpumask *housekeeping_cpumask(void)
+static inline const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
{
return cpu_possible_mask;
}

-static inline void housekeeping_affine(struct task_struct *t) { }
+static inline void housekeeping_affine(struct task_struct *t,
+ enum hk_flags flags) { }
static inline void housekeeping_init(void) { }
#endif /* CONFIG_CPU_ISOLATION */

-static inline bool housekeeping_cpu(int cpu)
+static inline bool housekeeping_cpu(int cpu, enum hk_flags flags)
{
#ifdef CONFIG_CPU_ISOLATION
if (static_branch_unlikely(&housekeeping_overriden))
- return housekeeping_test_cpu(cpu);
+ return housekeeping_test_cpu(cpu, flags);
#endif
return true;
}
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index c7632f5..34125d2 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -2584,7 +2584,7 @@ static void rcu_bind_gp_kthread(void)

if (!tick_nohz_full_enabled())
return;
- housekeeping_affine(current);
+ housekeeping_affine(current, HK_FLAG_RCU);
}

/* Record the current task on dyntick-idle entry. */
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 79abeb0..e3e60ef 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -719,7 +719,7 @@ static int __noreturn rcu_tasks_kthread(void *arg)
LIST_HEAD(rcu_tasks_holdouts);

/* Run on housekeeping CPUs by default. Sysadm can move if desired. */
- housekeeping_affine(current);
+ housekeeping_affine(current, HK_FLAG_RCU);

/*
* Each pass through the following loop makes one check for
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d0fb448d..2210c02 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -527,7 +527,7 @@ int get_nohz_timer_target(void)
int i, cpu = smp_processor_id();
struct sched_domain *sd;

- if (!idle_cpu(cpu) && housekeeping_cpu(cpu))
+ if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER))
return cpu;

rcu_read_lock();
@@ -536,15 +536,15 @@ int get_nohz_timer_target(void)
if (cpu == i)
continue;

- if (!idle_cpu(i) && housekeeping_cpu(i)) {
+ if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER)) {
cpu = i;
goto unlock;
}
}
}

- if (!housekeeping_cpu(cpu))
- cpu = housekeeping_any_cpu();
+ if (!housekeeping_cpu(cpu, HK_FLAG_TIMER))
+ cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
unlock:
rcu_read_unlock();
return cpu;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cdece8f..f755de8 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9027,7 +9027,7 @@ void nohz_balance_enter_idle(int cpu)
return;

/* Spare idle load balancing on CPUs that don't want to be disturbed: */
- if (!housekeeping_cpu(cpu))
+ if (!housekeeping_cpu(cpu, HK_FLAG_SCHED))
return;

if (test_bit(NOHZ_TICK_STOPPED, nohz_flags(cpu)))
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index bb8ba19..37a138a 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -15,37 +15,39 @@
DEFINE_STATIC_KEY_FALSE(housekeeping_overriden);
EXPORT_SYMBOL_GPL(housekeeping_overriden);
static cpumask_var_t housekeeping_mask;
+static unsigned int housekeeping_flags;

-int housekeeping_any_cpu(void)
+int housekeeping_any_cpu(enum hk_flags flags)
{
if (static_branch_unlikely(&housekeeping_overriden))
- return cpumask_any_and(housekeeping_mask, cpu_online_mask);
-
+ if (housekeeping_flags & flags)
+ return cpumask_any_and(housekeeping_mask, cpu_online_mask);
return smp_processor_id();
}
EXPORT_SYMBOL_GPL(housekeeping_any_cpu);

-const struct cpumask *housekeeping_cpumask(void)
+const struct cpumask *housekeeping_cpumask(enum hk_flags flags)
{
if (static_branch_unlikely(&housekeeping_overriden))
- return housekeeping_mask;
-
+ if (housekeeping_flags & flags)
+ return housekeeping_mask;
return cpu_possible_mask;
}
EXPORT_SYMBOL_GPL(housekeeping_cpumask);

-void housekeeping_affine(struct task_struct *t)
+void housekeeping_affine(struct task_struct *t, enum hk_flags flags)
{
if (static_branch_unlikely(&housekeeping_overriden))
- set_cpus_allowed_ptr(t, housekeeping_mask);
+ if (housekeeping_flags & flags)
+ set_cpus_allowed_ptr(t, housekeeping_mask);
}
EXPORT_SYMBOL_GPL(housekeeping_affine);

-bool housekeeping_test_cpu(int cpu)
+bool housekeeping_test_cpu(int cpu, enum hk_flags flags)
{
if (static_branch_unlikely(&housekeeping_overriden))
- return cpumask_test_cpu(cpu, housekeeping_mask);
-
+ if (housekeeping_flags & flags)
+ return cpumask_test_cpu(cpu, housekeeping_mask);
return true;
}
EXPORT_SYMBOL_GPL(housekeeping_test_cpu);
@@ -65,6 +67,8 @@ void __init housekeeping_init(void)
cpumask_andnot(housekeeping_mask,
cpu_possible_mask, tick_nohz_full_mask);

+ housekeeping_flags = HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC;
+
static_branch_enable(&housekeeping_overriden);

/* We need at least one CPU to handle housekeeping work */
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index 562652c..e9e2ebb 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -777,7 +777,8 @@ void __init lockup_detector_init(void)
if (tick_nohz_full_enabled())
pr_info("Disabling watchdog on nohz_full cores by default\n");

- cpumask_copy(&watchdog_cpumask, housekeeping_cpumask());
+ cpumask_copy(&watchdog_cpumask,
+ housekeeping_cpumask(HK_FLAG_TIMER));

if (!watchdog_nmi_probe())
nmi_watchdog_available = true;
--
2.7.4