In order to quiesce a CPU on which Isolation might be required, we need to move away all the timers queued on that CPU. There are two types of timers queued on any CPU: ones that are pinned to that CPU and others can run on any CPU but are queued on CPU in question. And we need to migrate only the second type of timers away from the CPU entering quiesce state.

For this we need some basic infrastructure in timer core to identify which timers are pinned and which are not.

Hence, this patch adds another flag bit TIMER_PINNED which will be set only for the timers which are pinned to a CPU.

It also removes 'pinned' parameter of __mod_timer() as it is no more required.

NOTE: One functional change worth mentioning

Existing Behavior: add_timer_on() followed by multiple mod_timer() wouldn't pin the timer on CPU mentioned in add_timer_on()..

New Behavior: add_timer_on() followed by multiple mod_timer() would pin the timer on CPU running mod_timer().

I didn't gave much attention to this as we should call mod_timer_on() for the timers queued with add_timer_on(). Though if required we can simply clear the TIMER_PINNED flag in mod_timer().

Signed-off-by: Viresh Kumar viresh.kumar@linaro.org --- include/linux/timer.h | 10 ++++++---- kernel/timer.c | 27 ++++++++++++++++++++------- 2 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/include/linux/timer.h b/include/linux/timer.h index 8c5a197..2962403 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -49,7 +49,7 @@ extern struct tvec_base boot_tvec_bases; #endif

/* - * Note that all tvec_bases are at least 4 byte aligned and lower two bits + * Note that all tvec_bases are at least 8 byte aligned and lower three bits * of base in timer_list is guaranteed to be zero. Use them for flags. * * A deferrable timer will work normally when the system is busy, but @@ -61,14 +61,18 @@ extern struct tvec_base boot_tvec_bases; * the completion of the running instance from IRQ handlers, for example, * by calling del_timer_sync(). * + * A pinned timer is allowed to run only on the cpu mentioned and shouldn't be + * migrated to any other CPU. + * * Note: The irq disabled callback execution is a special case for * workqueue locking issues. It's not meant for executing random crap * with interrupts disabled. Abuse is monitored! */ #define TIMER_DEFERRABLE 0x1LU #define TIMER_IRQSAFE 0x2LU +#define TIMER_PINNED 0x4LU

-#define TIMER_FLAG_MASK 0x3LU +#define TIMER_FLAG_MASK 0x7LU

#define __TIMER_INITIALIZER(_function, _expires, _data, _flags) { \ .entry = { .prev = TIMER_ENTRY_STATIC }, \ @@ -179,8 +183,6 @@ extern int mod_timer_pinned(struct timer_list *timer, unsigned long expires);

extern void set_timer_slack(struct timer_list *time, int slack_hz);

-#define TIMER_NOT_PINNED 0 -#define TIMER_PINNED 1 /* * The jiffies value which is added to now, when there is no timer * in the timer wheel: diff --git a/kernel/timer.c b/kernel/timer.c index d13eb56..e8bcaff 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -104,6 +104,11 @@ static inline unsigned int tbase_get_irqsafe(struct tvec_base *base) return ((unsigned int)(unsigned long)base & TIMER_IRQSAFE); }

+static inline unsigned int tbase_get_pinned(struct tvec_base *base) +{ + return ((unsigned int)(unsigned long)base & TIMER_PINNED); +} + static inline struct tvec_base *tbase_get_base(struct tvec_base *base) { return ((struct tvec_base *)((unsigned long)base & ~TIMER_FLAG_MASK)); @@ -117,6 +122,13 @@ timer_set_base(struct timer_list *timer, struct tvec_base *new_base) timer->base = (struct tvec_base *)((unsigned long)(new_base) | flags); }

+static inline void +timer_set_flags(struct timer_list *timer, unsigned int flags) +{ + timer->base = (struct tvec_base *)((unsigned long)(timer->base) | + flags); +} + static unsigned long round_jiffies_common(unsigned long j, int cpu, bool force_up) { @@ -742,8 +754,7 @@ static struct tvec_base *lock_timer_base(struct timer_list *timer, }

static inline int -__mod_timer(struct timer_list *timer, unsigned long expires, - bool pending_only, int pinned) +__mod_timer(struct timer_list *timer, unsigned long expires, bool pending_only) { struct tvec_base *base, *new_base; unsigned long flags; @@ -760,7 +771,7 @@ __mod_timer(struct timer_list *timer, unsigned long expires,

debug_activate(timer, expires);

- cpu = get_nohz_timer_target(pinned); + cpu = get_nohz_timer_target(tbase_get_pinned(timer->base)); new_base = per_cpu(tvec_bases, cpu);

if (base != new_base) { @@ -802,7 +813,7 @@ out_unlock: */ int mod_timer_pending(struct timer_list *timer, unsigned long expires) { - return __mod_timer(timer, expires, true, TIMER_NOT_PINNED); + return __mod_timer(timer, expires, true); } EXPORT_SYMBOL(mod_timer_pending);

@@ -877,7 +888,7 @@ int mod_timer(struct timer_list *timer, unsigned long expires) if (timer_pending(timer) && timer->expires == expires) return 1;

- return __mod_timer(timer, expires, false, TIMER_NOT_PINNED); + return __mod_timer(timer, expires, false); } EXPORT_SYMBOL(mod_timer);

@@ -905,7 +916,8 @@ int mod_timer_pinned(struct timer_list *timer, unsigned long expires) if (timer->expires == expires && timer_pending(timer)) return 1;

- return __mod_timer(timer, expires, false, TIMER_PINNED); + timer_set_flags(timer, TIMER_PINNED); + return __mod_timer(timer, expires, false); } EXPORT_SYMBOL(mod_timer_pinned);

@@ -944,6 +956,7 @@ void add_timer_on(struct timer_list *timer, int cpu)

timer_stats_timer_set_start_info(timer); BUG_ON(timer_pending(timer) || !timer->function); + timer_set_flags(timer, TIMER_PINNED); spin_lock_irqsave(&base->lock, flags); timer_set_base(timer, base); debug_activate(timer, timer->expires); @@ -1493,7 +1506,7 @@ signed long __sched schedule_timeout(signed long timeout) expire = timeout + jiffies;

setup_timer_on_stack(&timer, process_timeout, (unsigned long)current); - __mod_timer(&timer, expire, false, TIMER_NOT_PINNED); + __mod_timer(&timer, expire, false); schedule(); del_singleshot_timer_sync(&timer);

To isolate CPUs (isolate from timers) from sysfs using cpusets, we need some support from the timer core. i.e. A routine timer_quiesce_cpu() which would migrate away all the unpinned timers, but shouldn't touch the pinned ones.

This patch creates this routine.

Signed-off-by: Viresh Kumar viresh.kumar@linaro.org --- include/linux/timer.h | 3 +++ kernel/timer.c | 54 ++++++++++++++++++++++++++++++++++++++++----------- 2 files changed, 46 insertions(+), 11 deletions(-)

diff --git a/include/linux/timer.h b/include/linux/timer.h index 2962403..1588a4f 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -196,6 +196,9 @@ extern void set_timer_slack(struct timer_list *time, int slack_hz); */ extern unsigned long get_next_timer_interrupt(unsigned long now);

+/* To be used from cpusets, only */ +extern void timer_quiesce_cpu(void *cpup); + /* * Timer-statistics info: */ diff --git a/kernel/timer.c b/kernel/timer.c index 6c3a371..4676a07 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1602,18 +1602,27 @@ static int init_timers_cpu(int cpu) return 0; }

-#ifdef CONFIG_HOTPLUG_CPU -static void migrate_timer_list(struct tvec_base *new_base, struct list_head *head) +#if defined(CONFIG_HOTPLUG_CPU) || defined(CONFIG_CPUSETS) +static void migrate_timer_list(struct tvec_base *new_base, + struct list_head *head, bool remove_pinned) { struct timer_list *timer; + struct list_head pinned_list; int is_pinned;

+ INIT_LIST_HEAD(&pinned_list); + while (!list_empty(head)) { timer = list_first_entry(head, struct timer_list, entry); - /* We ignore the accounting on the dying cpu */ - detach_timer(timer, false);

is_pinned = tbase_get_pinned(timer->base); + if (!remove_pinned && is_pinned) { + list_move_tail(&timer->entry, &pinned_list); + continue; + } else { + /* We ignore the accounting on the dying cpu */ + detach_timer(timer, false); + }

/* Check if CPU still has pinned timers */ if (unlikely(WARN(is_pinned, @@ -1624,15 +1633,18 @@ static void migrate_timer_list(struct tvec_base *new_base, struct list_head *hea timer_set_base(timer, new_base); internal_add_timer(new_base, timer); } + + if (!list_empty(&pinned_list)) + list_splice_tail(&pinned_list, head); }

-static void migrate_timers(int cpu) +/* Migrate timers from 'cpu' to this_cpu */ +static void __migrate_timers(int cpu, bool remove_pinned) { struct tvec_base *old_base; struct tvec_base *new_base; int i;

- BUG_ON(cpu_online(cpu)); old_base = per_cpu(tvec_bases, cpu); new_base = get_cpu_var(tvec_bases); /* @@ -1645,20 +1657,40 @@ static void migrate_timers(int cpu) BUG_ON(old_base->running_timer);

for (i = 0; i < TVR_SIZE; i++) - migrate_timer_list(new_base, old_base->tv1.vec + i); + migrate_timer_list(new_base, old_base->tv1.vec + i, + remove_pinned); for (i = 0; i < TVN_SIZE; i++) { - migrate_timer_list(new_base, old_base->tv2.vec + i); - migrate_timer_list(new_base, old_base->tv3.vec + i); - migrate_timer_list(new_base, old_base->tv4.vec + i); - migrate_timer_list(new_base, old_base->tv5.vec + i); + migrate_timer_list(new_base, old_base->tv2.vec + i, + remove_pinned); + migrate_timer_list(new_base, old_base->tv3.vec + i, + remove_pinned); + migrate_timer_list(new_base, old_base->tv4.vec + i, + remove_pinned); + migrate_timer_list(new_base, old_base->tv5.vec + i, + remove_pinned); }

spin_unlock(&old_base->lock); spin_unlock_irq(&new_base->lock); put_cpu_var(tvec_bases); } +#endif /* CONFIG_HOTPLUG_CPU || CONFIG_CPUSETS */ + +#ifdef CONFIG_HOTPLUG_CPU +static void migrate_timers(int cpu) +{ + BUG_ON(cpu_online(cpu)); + __migrate_timers(cpu, true); +} #endif /* CONFIG_HOTPLUG_CPU */

+#ifdef CONFIG_CPUSETS +void timer_quiesce_cpu(void *cpup) +{ + __migrate_timers(*(int *)cpup, false); +} +#endif /* CONFIG_CPUSETS */ + static int timer_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) {

migrate_hrtimer() is called when a CPU goes down and its timers are required to be migrated to some other CPU. Its the responsibility of the users of the hrtimer to remove it before control reaches to migrate_hrtimer().

As these were the pinned hrtimers, the best we can do is: don't migrate these and report to the user as well.

That's all this patch does.

Signed-off-by: Viresh Kumar viresh.kumar@linaro.org --- kernel/hrtimer.c | 10 ++++++++++ 1 file changed, 10 insertions(+)

diff --git a/kernel/hrtimer.c b/kernel/hrtimer.c index c5a4bf4..853dd8c 100644 --- a/kernel/hrtimer.c +++ b/kernel/hrtimer.c @@ -1640,6 +1640,7 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, { struct hrtimer *timer; struct timerqueue_node *node; + int is_pinned;

while ((node = timerqueue_getnext(&old_base->active))) { timer = container_of(node, struct hrtimer, node); @@ -1652,6 +1653,15 @@ static void migrate_hrtimer_list(struct hrtimer_clock_base *old_base, * under us on another CPU */ __remove_hrtimer(timer, HRTIMER_STATE_MIGRATE, 0); + + is_pinned = timer->state & HRTIMER_STATE_PINNED; + + /* Check if CPU still has pinned timers */ + if (unlikely(WARN(is_pinned, + "%s: can't migrate pinned timer: %p, deactivating it\n", + __func__, timer))) + continue; + timer->base = new_base; /* * Enqueue the timers on the new cpu. This does not

For networking applications, platforms need to provide one CPU per each user space data plane thread. These CPUs shouldn't be interrupted by kernel at all unless userspace has requested for some functionality. Currently, there are background kernel activities that are running on almost every CPU, like: timers/hrtimers/watchdogs/etc, and these are required to be migrated to other CPUs.

To achieve that, this patch adds another option to cpusets, i.e. 'quiesce'. Writing '1' on this file would migrate these unbound/unpinned timers/hrtimers away from the CPUs of the cpuset in question. Also it would disallow addition of any new unpinned timers/hrtimers to isolated CPUs (This would be handled in next patch). Writing '0' will disable isolation of CPUs in current cpuset and unpinned timers/hrtimers would be allowed in future on these CPUs.

Currently, only timers and hrtimers are migrated. This would be followed by other kernel infrastructure later if required.

Signed-off-by: Viresh Kumar viresh.kumar@linaro.org --- Documentation/cgroups/cpusets.txt | 19 ++++++++-- include/linux/cpuset.h | 8 +++++ kernel/cpuset.c | 76 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 101 insertions(+), 2 deletions(-)

diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt index 7740038..8c1078b 100644 --- a/Documentation/cgroups/cpusets.txt +++ b/Documentation/cgroups/cpusets.txt @@ -22,7 +22,8 @@ CONTENTS: 1.6 What is memory spread ? 1.7 What is sched_load_balance ? 1.8 What is sched_relax_domain_level ? - 1.9 How do I use cpusets ? + 1.9 What is quiesce? + 1.10 How do I use cpusets ? 2. Usage Examples and Syntax 2.1 Basic Usage 2.2 Adding/removing cpus @@ -581,7 +582,21 @@ If your situation is: then increasing 'sched_relax_domain_level' would benefit you.

-1.9 How do I use cpusets ? +1.9 What is quiesce ? +-------------------------------------- +We need to migrate away all the background kernel activities (Unbound) for +systems requiring isolation of cores (HPC, Real time, networking, etc). After +creating cpusets, you can write 1 or 0 to cpuset.quiesce file. + +Writing '1': on this file would migrate unbound/unpinned timers and hrtimers +away from the CPUs of the cpuset in question. Also it would disallow addition of +any new unpinned timers & hrtimers to isolated CPUs. + +Writing '0': will disable isolation of CPUs in current cpuset and unpinned +timers/hrtimers would be allowed in future on these CPUs. + + +1.10 How do I use cpusets ? --------------------------

In order to minimize the impact of cpusets on critical kernel diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 3fe661f..1ce0775 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -15,6 +15,13 @@

#ifdef CONFIG_CPUSETS

+extern cpumask_var_t cpuset_quiesced_cpus_mask; + +static inline bool cpu_quiesced(int cpu) +{ + return cpumask_test_cpu(cpu, cpuset_quiesced_cpus_mask); +} + extern int number_of_cpusets; /* How many cpusets are defined in system? */

extern int cpuset_init(void); @@ -123,6 +130,7 @@ static inline void set_mems_allowed(nodemask_t nodemask)

#else /* !CONFIG_CPUSETS */

+static inline bool cpu_quiesced(int cpu) { return 0; } static inline int cpuset_init(void) { return 0; } static inline void cpuset_init_smp(void) {}

diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 4410ac6..256cf11 100644 --- a/kernel/cpuset.c +++ b/kernel/cpuset.c @@ -43,10 +43,12 @@ #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> +#include <linux/tick.h> #include <linux/sched.h> #include <linux/seq_file.h> #include <linux/security.h> #include <linux/slab.h> +#include <linux/smp.h> #include <linux/spinlock.h> #include <linux/stat.h> #include <linux/string.h> @@ -150,6 +152,7 @@ typedef enum { CS_SCHED_LOAD_BALANCE, CS_SPREAD_PAGE, CS_SPREAD_SLAB, + CS_QUIESCE, } cpuset_flagbits_t;

/* convenient tests for these bits */ @@ -193,6 +196,14 @@ static inline int is_spread_slab(const struct cpuset *cs) return test_bit(CS_SPREAD_SLAB, &cs->flags); }

+static inline int is_cpu_quiesced(const struct cpuset *cs) +{ + return test_bit(CS_QUIESCE, &cs->flags); +} + +/* Mask of CPUs which have requested isolation */ +cpumask_var_t cpuset_quiesced_cpus_mask; + static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), @@ -1261,6 +1272,53 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) }

/** + * quiesce_cpuset - Move unbound timers/hrtimers away from cpuset.cpus + * @cs: cpuset to be quiesced + * + * For isolating a core with cpusets we require all unbound timers/hrtimers to + * move away from isolated core. We migrate these to one of the CPUs which + * hasn't isolated itself yet. And the CPU is selected by + * smp_call_function_any() routine. + * + * Currently we are only migrating timers and hrtimers away. + */ +static int quiesce_cpuset(struct cpuset *cs, int turning_on) +{ + int from_cpu; + cpumask_t cpumask; + + /* Fail if we are already in the requested state */ + if (!(is_cpu_quiesced(cs) ^ turning_on)) + return -EINVAL; + + if (!turning_on) { + cpumask_andnot(cpuset_quiesced_cpus_mask, + cpuset_quiesced_cpus_mask, cs->cpus_allowed); + return 0; + } + + cpumask_andnot(&cpumask, cpu_online_mask, cs->cpus_allowed); + cpumask_andnot(&cpumask, &cpumask, cpuset_quiesced_cpus_mask); + + if (cpumask_empty(&cpumask)) { + pr_err("%s: Couldn't find a CPU to migrate to\n", __func__); + return -EPERM; + } + + cpumask_or(cpuset_quiesced_cpus_mask, cpuset_quiesced_cpus_mask, + cs->cpus_allowed); + + for_each_cpu(from_cpu, cs->cpus_allowed) { + smp_call_function_any(&cpumask, hrtimer_quiesce_cpu, &from_cpu, + 1); + smp_call_function_any(&cpumask, timer_quiesce_cpu, &from_cpu, + 1); + } + + return 0; +} + +/** * cpuset_change_flag - make a task's spread flags the same as its cpuset's * @tsk: task to be updated * @data: cpuset to @tsk belongs to @@ -1326,6 +1384,9 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, if (err < 0) goto out;

+ if (bit == CS_QUIESCE && quiesce_cpuset(cs, turning_on)) + goto out; + err = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL); if (err < 0) goto out; @@ -1597,6 +1658,7 @@ typedef enum { FILE_MEMORY_PRESSURE, FILE_SPREAD_PAGE, FILE_SPREAD_SLAB, + FILE_CPU_QUIESCE, } cpuset_filetype_t;

static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, @@ -1640,6 +1702,9 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, case FILE_SPREAD_SLAB: retval = update_flag(CS_SPREAD_SLAB, cs, val); break; + case FILE_CPU_QUIESCE: + retval = update_flag(CS_QUIESCE, cs, val); + break; default: retval = -EINVAL; break; @@ -1791,6 +1856,8 @@ static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) return is_spread_page(cs); case FILE_SPREAD_SLAB: return is_spread_slab(cs); + case FILE_CPU_QUIESCE: + return is_cpu_quiesced(cs); default: BUG(); } @@ -1908,6 +1975,13 @@ static struct cftype files[] = { .private = FILE_MEMORY_PRESSURE_ENABLED, },

+ { + .name = "quiesce", + .read_u64 = cpuset_read_u64, + .write_u64 = cpuset_write_u64, + .private = FILE_CPU_QUIESCE, + }, + { } /* terminate */ };

@@ -2065,6 +2139,8 @@ int __init cpuset_init(void) if (!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)) BUG();

+ BUG_ON(!zalloc_cpumask_var(&cpuset_quiesced_cpus_mask, GFP_KERNEL)); + number_of_cpusets = 1; return 0; }