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 87bd529..fec4ab4 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);

For networking applications platforms need to provide one CPU per each user space data plane thread. These CPUs should not be interrupted by kernel at all unless userspace has requested for some syscalls. 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/workqueues away from the CPUs of the cpuset in question. Writing '0' has no effect and this file can't be read from userspace as we aren't maintaining a state here.

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

Suggested-by: Peter Zijlstra peterz@infradead.org Signed-off-by: Viresh Kumar viresh.kumar@linaro.org --- kernel/cpuset.c | 56 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 56 insertions(+)

diff --git a/kernel/cpuset.c b/kernel/cpuset.c index 3d54c41..1b79ae6 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 */ @@ -1208,6 +1211,44 @@ static int update_relax_domain_level(struct cpuset *cs, s64 val) return 0; }

+void timer_quiesce_cpu(void *cpu); + +/** + * quiesce_cpuset - Move unbound timers/workqueues away from cpuset.cpus + * @cs: cpuset to be quiesced + * + * For isolating a core with cpusets we require all unbound timers/workqueues to + * move away for isolated core. For simplicity, currently we migrate these to + * the first online CPU which is not part of tick_nohz_full_mask. + * + * Currently we are only migrating timers away. + */ +void quiesce_cpuset(struct cpuset *cs) +{ + int from_cpu, to_cpu; + cpumask_t cpumask; + + cpumask_andnot(&cpumask, cpu_online_mask, cs->cpus_allowed); + +#ifdef CONFIG_NO_HZ_FULL + cpumask_andnot(&cpumask, &cpumask, tick_nohz_full_mask); +#endif + + if (cpumask_empty(&cpumask)) { + pr_err("%s: Couldn't find a CPU to migrate to\n", __func__); + return; + } + + to_cpu = cpumask_first(&cpumask); + + for_each_cpu(from_cpu, cs->cpus_allowed) { + pr_debug("%s: Migrating from CPU:%d to CPU:%d\n", __func__, + from_cpu, to_cpu); + smp_call_function_single(to_cpu, timer_quiesce_cpu, + (void *)from_cpu, true); + } +} + /** * update_tasks_flags - update the spread flags of tasks in the cpuset. * @cs: the cpuset in which each task's spread flags needs to be changed @@ -1244,6 +1285,11 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int spread_flag_changed; int err;

+ if (bit == CS_QUIESCE && turning_on) { + quiesce_cpuset(cs); + return 0; + } + trialcs = alloc_trial_cpuset(cs); if (!trialcs) return -ENOMEM; @@ -1526,6 +1572,7 @@ 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, @@ -1569,6 +1616,9 @@ 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; @@ -1837,6 +1887,12 @@ static struct cftype files[] = { .private = FILE_MEMORY_PRESSURE_ENABLED, },

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