#include <asm/debugreg.h>
#include <asm/nmi.h>
+/*
+ * per-CPU TSS segments. Threads are completely 'soft' on Linux,
+ * no more per-task TSS's. The TSS size is kept cacheline-aligned
+ * so they are allowed to end up in the .data..cacheline_aligned
+ * section. Since TSS's are completely CPU-local, we want them
+ * on exact cacheline boundaries, to eliminate cacheline ping-pong.
+ */
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tss_struct, init_tss) = INIT_TSS;
+
#ifdef CONFIG_X86_64
static DEFINE_PER_CPU(unsigned char, is_idle);
static ATOMIC_NOTIFIER_HEAD(idle_notifier);
fpu_free(&tsk->thread.fpu);
}
-void free_thread_info(struct thread_info *ti)
+void arch_release_task_struct(struct task_struct *tsk)
{
- free_thread_xstate(ti->task);
- free_pages((unsigned long)ti, THREAD_ORDER);
+ free_thread_xstate(tsk);
}
void arch_task_cache_init(void)
#ifdef CONFIG_X86_64
void enter_idle(void)
{
- percpu_write(is_idle, 1);
+ this_cpu_write(is_idle, 1);
atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
}
}
}
-static void do_nothing(void *unused)
-{
-}
-
-/*
- * cpu_idle_wait - Used to ensure that all the CPUs discard old value of
- * pm_idle and update to new pm_idle value. Required while changing pm_idle
- * handler on SMP systems.
- *
- * Caller must have changed pm_idle to the new value before the call. Old
- * pm_idle value will not be used by any CPU after the return of this function.
- */
-void cpu_idle_wait(void)
-{
- smp_mb();
- /* kick all the CPUs so that they exit out of pm_idle */
- smp_call_function(do_nothing, NULL, 1);
-}
-EXPORT_SYMBOL_GPL(cpu_idle_wait);
-
/* Default MONITOR/MWAIT with no hints, used for default C1 state */
static void mwait_idle(void)
{
{
u32 eax, ebx, ecx, edx;
+ /* Use mwait if idle=mwait boot option is given */
if (boot_option_idle_override == IDLE_FORCE_MWAIT)
return 1;
+ /*
+ * Any idle= boot option other than idle=mwait means that we must not
+ * use mwait. Eg: idle=halt or idle=poll or idle=nomwait
+ */
+ if (boot_option_idle_override != IDLE_NO_OVERRIDE)
+ return 0;
+
if (c->cpuid_level < MWAIT_INFO)
return 0;
/* State of each CPU */
DEFINE_PER_CPU(int, cpu_state) = { 0 };
-/* Store all idle threads, this can be reused instead of creating
-* a new thread. Also avoids complicated thread destroy functionality
-* for idle threads.
-*/
#ifdef CONFIG_HOTPLUG_CPU
-/*
- * Needed only for CONFIG_HOTPLUG_CPU because __cpuinitdata is
- * removed after init for !CONFIG_HOTPLUG_CPU.
- */
-static DEFINE_PER_CPU(struct task_struct *, idle_thread_array);
-#define get_idle_for_cpu(x) (per_cpu(idle_thread_array, x))
-#define set_idle_for_cpu(x, p) (per_cpu(idle_thread_array, x) = (p))
-
/*
* We need this for trampoline_base protection from concurrent accesses when
* off- and onlining cores wildly.
void cpu_hotplug_driver_lock(void)
{
- mutex_lock(&x86_cpu_hotplug_driver_mutex);
+ mutex_lock(&x86_cpu_hotplug_driver_mutex);
}
void cpu_hotplug_driver_unlock(void)
{
- mutex_unlock(&x86_cpu_hotplug_driver_mutex);
+ mutex_unlock(&x86_cpu_hotplug_driver_mutex);
}
ssize_t arch_cpu_probe(const char *buf, size_t count) { return -1; }
ssize_t arch_cpu_release(const char *buf, size_t count) { return -1; }
-#else
-static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
-#define get_idle_for_cpu(x) (idle_thread_array[(x)])
-#define set_idle_for_cpu(x, p) (idle_thread_array[(x)] = (p))
#endif
/* Number of siblings per CPU package */
identify_secondary_cpu(c);
}
- static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
+ static bool __cpuinit
+ topology_sane(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o, const char *name)
{
- cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
- cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
- cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
- cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
- cpumask_set_cpu(cpu1, cpu_llc_shared_mask(cpu2));
- cpumask_set_cpu(cpu2, cpu_llc_shared_mask(cpu1));
+ int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+
+ return !WARN_ONCE(cpu_to_node(cpu1) != cpu_to_node(cpu2),
+ "sched: CPU #%d's %s-sibling CPU #%d is not on the same node! "
+ "[node: %d != %d]. Ignoring dependency.\n",
+ cpu1, name, cpu2, cpu_to_node(cpu1), cpu_to_node(cpu2));
+ }
+
+ #define link_mask(_m, c1, c2) \
+ do { \
+ cpumask_set_cpu((c1), cpu_##_m##_mask(c2)); \
+ cpumask_set_cpu((c2), cpu_##_m##_mask(c1)); \
+ } while (0)
+
+ static bool __cpuinit match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+ {
+ if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
+ int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+
+ if (c->phys_proc_id == o->phys_proc_id &&
+ per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2) &&
+ c->compute_unit_id == o->compute_unit_id)
+ return topology_sane(c, o, "smt");
+
+ } else if (c->phys_proc_id == o->phys_proc_id &&
+ c->cpu_core_id == o->cpu_core_id) {
+ return topology_sane(c, o, "smt");
+ }
+
+ return false;
+ }
+
+ static bool __cpuinit match_llc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+ {
+ int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
+
+ if (per_cpu(cpu_llc_id, cpu1) != BAD_APICID &&
+ per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2))
+ return topology_sane(c, o, "llc");
+
+ return false;
}
+ static bool __cpuinit match_mc(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
+ {
+ if (c->phys_proc_id == o->phys_proc_id)
+ return topology_sane(c, o, "mc");
+
+ return false;
+ }
void __cpuinit set_cpu_sibling_map(int cpu)
{
- int i;
+ bool has_mc = boot_cpu_data.x86_max_cores > 1;
+ bool has_smt = smp_num_siblings > 1;
struct cpuinfo_x86 *c = &cpu_data(cpu);
+ struct cpuinfo_x86 *o;
+ int i;
cpumask_set_cpu(cpu, cpu_sibling_setup_mask);
- if (smp_num_siblings > 1) {
- for_each_cpu(i, cpu_sibling_setup_mask) {
- struct cpuinfo_x86 *o = &cpu_data(i);
-
- if (cpu_has(c, X86_FEATURE_TOPOEXT)) {
- if (c->phys_proc_id == o->phys_proc_id &&
- per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i) &&
- c->compute_unit_id == o->compute_unit_id)
- link_thread_siblings(cpu, i);
- } else if (c->phys_proc_id == o->phys_proc_id &&
- c->cpu_core_id == o->cpu_core_id) {
- link_thread_siblings(cpu, i);
- }
- }
- } else {
+ if (!has_smt && !has_mc) {
cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
- }
-
- cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
-
- if (__this_cpu_read(cpu_info.x86_max_cores) == 1) {
- cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
+ cpumask_set_cpu(cpu, cpu_llc_shared_mask(cpu));
+ cpumask_set_cpu(cpu, cpu_core_mask(cpu));
c->booted_cores = 1;
return;
}
for_each_cpu(i, cpu_sibling_setup_mask) {
- if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
- per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
- cpumask_set_cpu(i, cpu_llc_shared_mask(cpu));
- cpumask_set_cpu(cpu, cpu_llc_shared_mask(i));
- }
- if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
- cpumask_set_cpu(i, cpu_core_mask(cpu));
- cpumask_set_cpu(cpu, cpu_core_mask(i));
+ o = &cpu_data(i);
+
+ if ((i == cpu) || (has_smt && match_smt(c, o)))
+ link_mask(sibling, cpu, i);
+
+ if ((i == cpu) || (has_mc && match_llc(c, o)))
+ link_mask(llc_shared, cpu, i);
+
+ if ((i == cpu) || (has_mc && match_mc(c, o))) {
+ link_mask(core, cpu, i);
+
/*
* Does this new cpu bringup a new core?
*/
* For perf, we return last level cache shared map.
* And for power savings, we return cpu_core_map
*/
- if ((sched_mc_power_savings || sched_smt_power_savings) &&
- !(cpu_has(c, X86_FEATURE_AMD_DCM)))
+ if (!(cpu_has(c, X86_FEATURE_AMD_DCM)))
return cpu_core_mask(cpu);
else
return cpu_llc_shared_mask(cpu);
return (send_status | accept_status);
}
-struct create_idle {
- struct work_struct work;
- struct task_struct *idle;
- struct completion done;
- int cpu;
-};
-
-static void __cpuinit do_fork_idle(struct work_struct *work)
-{
- struct create_idle *c_idle =
- container_of(work, struct create_idle, work);
-
- c_idle->idle = fork_idle(c_idle->cpu);
- complete(&c_idle->done);
-}
-
/* reduce the number of lines printed when booting a large cpu count system */
static void __cpuinit announce_cpu(int cpu, int apicid)
{
* Returns zero if CPU booted OK, else error code from
* ->wakeup_secondary_cpu.
*/
-static int __cpuinit do_boot_cpu(int apicid, int cpu)
+static int __cpuinit do_boot_cpu(int apicid, int cpu, struct task_struct *idle)
{
unsigned long boot_error = 0;
unsigned long start_ip;
int timeout;
- struct create_idle c_idle = {
- .cpu = cpu,
- .done = COMPLETION_INITIALIZER_ONSTACK(c_idle.done),
- };
-
- INIT_WORK_ONSTACK(&c_idle.work, do_fork_idle);
alternatives_smp_switch(1);
- c_idle.idle = get_idle_for_cpu(cpu);
-
- /*
- * We can't use kernel_thread since we must avoid to
- * reschedule the child.
- */
- if (c_idle.idle) {
- c_idle.idle->thread.sp = (unsigned long) (((struct pt_regs *)
- (THREAD_SIZE + task_stack_page(c_idle.idle))) - 1);
- init_idle(c_idle.idle, cpu);
- goto do_rest;
- }
+ idle->thread.sp = (unsigned long) (((struct pt_regs *)
+ (THREAD_SIZE + task_stack_page(idle))) - 1);
+ per_cpu(current_task, cpu) = idle;
- schedule_work(&c_idle.work);
- wait_for_completion(&c_idle.done);
-
- if (IS_ERR(c_idle.idle)) {
- printk("failed fork for CPU %d\n", cpu);
- destroy_work_on_stack(&c_idle.work);
- return PTR_ERR(c_idle.idle);
- }
-
- set_idle_for_cpu(cpu, c_idle.idle);
-do_rest:
- per_cpu(current_task, cpu) = c_idle.idle;
#ifdef CONFIG_X86_32
/* Stack for startup_32 can be just as for start_secondary onwards */
irq_ctx_init(cpu);
#else
- clear_tsk_thread_flag(c_idle.idle, TIF_FORK);
+ clear_tsk_thread_flag(idle, TIF_FORK);
initial_gs = per_cpu_offset(cpu);
per_cpu(kernel_stack, cpu) =
- (unsigned long)task_stack_page(c_idle.idle) -
+ (unsigned long)task_stack_page(idle) -
KERNEL_STACK_OFFSET + THREAD_SIZE;
#endif
early_gdt_descr.address = (unsigned long)get_cpu_gdt_table(cpu);
initial_code = (unsigned long)start_secondary;
- stack_start = c_idle.idle->thread.sp;
+ stack_start = idle->thread.sp;
/* start_ip had better be page-aligned! */
start_ip = trampoline_address();
*/
smpboot_restore_warm_reset_vector();
}
-
- destroy_work_on_stack(&c_idle.work);
return boot_error;
}
-int __cpuinit native_cpu_up(unsigned int cpu)
+int __cpuinit native_cpu_up(unsigned int cpu, struct task_struct *tidle)
{
int apicid = apic->cpu_present_to_apicid(cpu);
unsigned long flags;
per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
- err = do_boot_cpu(apicid, cpu);
+ err = do_boot_cpu(apicid, cpu, tidle);
if (err) {
pr_debug("do_boot_cpu failed %d\n", err);
return -EIO;
#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */
#define SD_PREFER_LOCAL 0x0040 /* Prefer to keep tasks local to this domain */
#define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */
- #define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */
#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */
#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */
#define SD_ASYM_PACKING 0x0800 /* Place busy groups earlier in the domain */
#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */
#define SD_OVERLAP 0x2000 /* sched_domains of this level overlap */
- enum powersavings_balance_level {
- POWERSAVINGS_BALANCE_NONE = 0, /* No power saving load balance */
- POWERSAVINGS_BALANCE_BASIC, /* Fill one thread/core/package
- * first for long running threads
- */
- POWERSAVINGS_BALANCE_WAKEUP, /* Also bias task wakeups to semi-idle
- * cpu package for power savings
- */
- MAX_POWERSAVINGS_BALANCE_LEVELS
- };
-
- extern int sched_mc_power_savings, sched_smt_power_savings;
-
- static inline int sd_balance_for_mc_power(void)
- {
- if (sched_smt_power_savings)
- return SD_POWERSAVINGS_BALANCE;
-
- if (!sched_mc_power_savings)
- return SD_PREFER_SIBLING;
-
- return 0;
- }
-
- static inline int sd_balance_for_package_power(void)
- {
- if (sched_mc_power_savings | sched_smt_power_savings)
- return SD_POWERSAVINGS_BALANCE;
-
- return SD_PREFER_SIBLING;
- }
-
extern int __weak arch_sd_sibiling_asym_packing(void);
- /*
- * Optimise SD flags for power savings:
- * SD_BALANCE_NEWIDLE helps aggressive task consolidation and power savings.
- * Keep default SD flags if sched_{smt,mc}_power_saving=0
- */
-
- static inline int sd_power_saving_flags(void)
- {
- if (sched_mc_power_savings | sched_smt_power_savings)
- return SD_BALANCE_NEWIDLE;
-
- return 0;
- }
-
struct sched_group_power {
atomic_t ref;
/*
* execve */
unsigned in_iowait:1;
+ /* task may not gain privileges */
+ unsigned no_new_privs:1;
/* Revert to default priority/policy when forking */
unsigned sched_reset_on_fork:1;
uid_t loginuid;
unsigned int sessionid;
#endif
- seccomp_t seccomp;
+ struct seccomp seccomp;
/* Thread group tracking */
u32 parent_exec_id;
INIT_LIST_HEAD(&p->rcu_node_entry);
}
+static inline void rcu_switch_from(struct task_struct *prev)
+{
+ if (prev->rcu_read_lock_nesting != 0)
+ rcu_preempt_note_context_switch();
+}
+
#else
static inline void rcu_copy_process(struct task_struct *p)
{
}
+static inline void rcu_switch_from(struct task_struct *prev)
+{
+}
+
#endif
#ifdef CONFIG_SMP
*/
extern unsigned long long notrace sched_clock(void);
/*
- * See the comment in kernel/sched_clock.c
+ * See the comment in kernel/sched/clock.c
*/
extern u64 cpu_clock(int cpu);
extern u64 local_clock(void);
* Below are the 3 major initializers used in building sched_domains:
* SD_SIBLING_INIT, for SMT domains
* SD_CPU_INIT, for SMP domains
- * SD_NODE_INIT, for NUMA domains
*
* Any architecture that cares to do any tuning to these values should do so
* by defining their own arch-specific initializer in include/asm/topology.h.
| 0*SD_BALANCE_WAKE \
| 1*SD_WAKE_AFFINE \
| 1*SD_SHARE_CPUPOWER \
- | 0*SD_POWERSAVINGS_BALANCE \
| 1*SD_SHARE_PKG_RESOURCES \
| 0*SD_SERIALIZE \
| 0*SD_PREFER_SIBLING \
| 0*SD_SHARE_CPUPOWER \
| 1*SD_SHARE_PKG_RESOURCES \
| 0*SD_SERIALIZE \
- | sd_balance_for_mc_power() \
- | sd_power_saving_flags() \
, \
.last_balance = jiffies, \
.balance_interval = 1, \
| 0*SD_SHARE_CPUPOWER \
| 0*SD_SHARE_PKG_RESOURCES \
| 0*SD_SERIALIZE \
- | sd_balance_for_package_power() \
- | sd_power_saving_flags() \
, \
.last_balance = jiffies, \
.balance_interval = 1, \
}
#endif
- /* sched_domains SD_ALLNODES_INIT for NUMA machines */
- #define SD_ALLNODES_INIT (struct sched_domain) { \
- .min_interval = 64, \
- .max_interval = 64*num_online_cpus(), \
- .busy_factor = 128, \
- .imbalance_pct = 133, \
- .cache_nice_tries = 1, \
- .busy_idx = 3, \
- .idle_idx = 3, \
- .flags = 1*SD_LOAD_BALANCE \
- | 1*SD_BALANCE_NEWIDLE \
- | 0*SD_BALANCE_EXEC \
- | 0*SD_BALANCE_FORK \
- | 0*SD_BALANCE_WAKE \
- | 0*SD_WAKE_AFFINE \
- | 0*SD_SHARE_CPUPOWER \
- | 0*SD_POWERSAVINGS_BALANCE \
- | 0*SD_SHARE_PKG_RESOURCES \
- | 1*SD_SERIALIZE \
- | 0*SD_PREFER_SIBLING \
- , \
- .last_balance = jiffies, \
- .balance_interval = 64, \
- }
-
- #ifndef SD_NODES_PER_DOMAIN
- #define SD_NODES_PER_DOMAIN 16
- #endif
-
#ifdef CONFIG_SCHED_BOOK
#ifndef SD_BOOK_INIT
#error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!!
#endif
#endif /* CONFIG_SCHED_BOOK */
- #ifdef CONFIG_NUMA
- #ifndef SD_NODE_INIT
- #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!!
- #endif
-
- #endif /* CONFIG_NUMA */
-
#ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID
DECLARE_PER_CPU(int, numa_node);
#ifndef set_numa_node
static inline void set_numa_node(int node)
{
- percpu_write(numa_node, node);
+ this_cpu_write(numa_node, node);
}
#endif
#ifndef set_numa_mem
static inline void set_numa_mem(int node)
{
- percpu_write(_numa_mem_, node);
+ this_cpu_write(_numa_mem_, node);
}
#endif
#include "sched.h"
#include "../workqueue_sched.h"
+#include "../smpboot.h"
#define CREATE_TRACE_POINTS
#include <trace/events/sched.h>
}
#endif
- void update_cpu_load(struct rq *this_rq);
-
static void set_load_weight(struct task_struct *p)
{
int prio = p->static_prio - MAX_RT_PRIO;
struct task_struct *next)
{
sched_info_switch(prev, next);
- perf_event_task_sched_out(prev, next);
+ perf_event_task_sched(prev, next);
fire_sched_out_preempt_notifiers(prev, next);
prepare_lock_switch(rq, next);
prepare_arch_switch(next);
*/
prev_state = prev->state;
finish_arch_switch(prev);
-#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
- local_irq_disable();
-#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
- perf_event_task_sched_in(prev, current);
-#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW
- local_irq_enable();
-#endif /* __ARCH_WANT_INTERRUPTS_ON_CTXSW */
finish_lock_switch(rq, prev);
finish_arch_post_lock_switch();
#endif
/* Here we just switch the register state and the stack. */
+ rcu_switch_from(prev);
switch_to(prev, next, prev);
barrier();
* scheduler tick (TICK_NSEC). With tickless idle this will not be called
* every tick. We fix it up based on jiffies.
*/
- void update_cpu_load(struct rq *this_rq)
+ static void __update_cpu_load(struct rq *this_rq, unsigned long this_load,
+ unsigned long pending_updates)
{
- unsigned long this_load = this_rq->load.weight;
- unsigned long curr_jiffies = jiffies;
- unsigned long pending_updates;
int i, scale;
this_rq->nr_load_updates++;
- /* Avoid repeated calls on same jiffy, when moving in and out of idle */
- if (curr_jiffies == this_rq->last_load_update_tick)
- return;
-
- pending_updates = curr_jiffies - this_rq->last_load_update_tick;
- this_rq->last_load_update_tick = curr_jiffies;
-
/* Update our load: */
this_rq->cpu_load[0] = this_load; /* Fasttrack for idx 0 */
for (i = 1, scale = 2; i < CPU_LOAD_IDX_MAX; i++, scale += scale) {
sched_avg_update(this_rq);
}
+ /*
+ * Called from nohz_idle_balance() to update the load ratings before doing the
+ * idle balance.
+ */
+ void update_idle_cpu_load(struct rq *this_rq)
+ {
+ unsigned long curr_jiffies = jiffies;
+ unsigned long load = this_rq->load.weight;
+ unsigned long pending_updates;
+
+ /*
+ * Bloody broken means of dealing with nohz, but better than nothing..
+ * jiffies is updated by one cpu, another cpu can drift wrt the jiffy
+ * update and see 0 difference the one time and 2 the next, even though
+ * we ticked at roughtly the same rate.
+ *
+ * Hence we only use this from nohz_idle_balance() and skip this
+ * nonsense when called from the scheduler_tick() since that's
+ * guaranteed a stable rate.
+ */
+ if (load || curr_jiffies == this_rq->last_load_update_tick)
+ return;
+
+ pending_updates = curr_jiffies - this_rq->last_load_update_tick;
+ this_rq->last_load_update_tick = curr_jiffies;
+
+ __update_cpu_load(this_rq, load, pending_updates);
+ }
+
+ /*
+ * Called from scheduler_tick()
+ */
static void update_cpu_load_active(struct rq *this_rq)
{
- update_cpu_load(this_rq);
+ /*
+ * See the mess in update_idle_cpu_load().
+ */
+ this_rq->last_load_update_tick = jiffies;
+ __update_cpu_load(this_rq, this_rq->load.weight, 1);
calc_load_account_active(this_rq);
}
if (irqs_disabled())
print_irqtrace_events(prev);
dump_stack();
+ add_taint(TAINT_WARN);
}
/*
break;
}
- if (cpumask_intersects(groupmask, sched_group_cpus(group))) {
+ if (!(sd->flags & SD_OVERLAP) &&
+ cpumask_intersects(groupmask, sched_group_cpus(group))) {
printk(KERN_CONT "\n");
printk(KERN_ERR "ERROR: repeated CPUs\n");
break;
__setup("isolcpus=", isolated_cpu_setup);
- #ifdef CONFIG_NUMA
-
- /**
- * find_next_best_node - find the next node to include in a sched_domain
- * @node: node whose sched_domain we're building
- * @used_nodes: nodes already in the sched_domain
- *
- * Find the next node to include in a given scheduling domain. Simply
- * finds the closest node not already in the @used_nodes map.
- *
- * Should use nodemask_t.
- */
- static int find_next_best_node(int node, nodemask_t *used_nodes)
- {
- int i, n, val, min_val, best_node = -1;
-
- min_val = INT_MAX;
-
- for (i = 0; i < nr_node_ids; i++) {
- /* Start at @node */
- n = (node + i) % nr_node_ids;
-
- if (!nr_cpus_node(n))
- continue;
-
- /* Skip already used nodes */
- if (node_isset(n, *used_nodes))
- continue;
-
- /* Simple min distance search */
- val = node_distance(node, n);
-
- if (val < min_val) {
- min_val = val;
- best_node = n;
- }
- }
-
- if (best_node != -1)
- node_set(best_node, *used_nodes);
- return best_node;
- }
-
- /**
- * sched_domain_node_span - get a cpumask for a node's sched_domain
- * @node: node whose cpumask we're constructing
- * @span: resulting cpumask
- *
- * Given a node, construct a good cpumask for its sched_domain to span. It
- * should be one that prevents unnecessary balancing, but also spreads tasks
- * out optimally.
- */
- static void sched_domain_node_span(int node, struct cpumask *span)
- {
- nodemask_t used_nodes;
- int i;
-
- cpumask_clear(span);
- nodes_clear(used_nodes);
-
- cpumask_or(span, span, cpumask_of_node(node));
- node_set(node, used_nodes);
-
- for (i = 1; i < SD_NODES_PER_DOMAIN; i++) {
- int next_node = find_next_best_node(node, &used_nodes);
- if (next_node < 0)
- break;
- cpumask_or(span, span, cpumask_of_node(next_node));
- }
- }
-
- static const struct cpumask *cpu_node_mask(int cpu)
- {
- lockdep_assert_held(&sched_domains_mutex);
-
- sched_domain_node_span(cpu_to_node(cpu), sched_domains_tmpmask);
-
- return sched_domains_tmpmask;
- }
-
- static const struct cpumask *cpu_allnodes_mask(int cpu)
- {
- return cpu_possible_mask;
- }
- #endif /* CONFIG_NUMA */
-
static const struct cpumask *cpu_cpu_mask(int cpu)
{
return cpumask_of_node(cpu_to_node(cpu));
}
- int sched_smt_power_savings = 0, sched_mc_power_savings = 0;
-
struct sd_data {
struct sched_domain **__percpu sd;
struct sched_group **__percpu sg;
sched_domain_init_f init;
sched_domain_mask_f mask;
int flags;
+ int numa_level;
struct sd_data data;
};
}
SD_INIT_FUNC(CPU)
- #ifdef CONFIG_NUMA
- SD_INIT_FUNC(ALLNODES)
- SD_INIT_FUNC(NODE)
- #endif
#ifdef CONFIG_SCHED_SMT
SD_INIT_FUNC(SIBLING)
#endif
{ sd_init_BOOK, cpu_book_mask, },
#endif
{ sd_init_CPU, cpu_cpu_mask, },
- #ifdef CONFIG_NUMA
- { sd_init_NODE, cpu_node_mask, SDTL_OVERLAP, },
- { sd_init_ALLNODES, cpu_allnodes_mask, },
- #endif
{ NULL, },
};
static struct sched_domain_topology_level *sched_domain_topology = default_topology;
+ #ifdef CONFIG_NUMA
+
+ static int sched_domains_numa_levels;
+ static int sched_domains_numa_scale;
+ static int *sched_domains_numa_distance;
+ static struct cpumask ***sched_domains_numa_masks;
+ static int sched_domains_curr_level;
+
+ static inline int sd_local_flags(int level)
+ {
+ if (sched_domains_numa_distance[level] > REMOTE_DISTANCE)
+ return 0;
+
+ return SD_BALANCE_EXEC | SD_BALANCE_FORK | SD_WAKE_AFFINE;
+ }
+
+ static struct sched_domain *
+ sd_numa_init(struct sched_domain_topology_level *tl, int cpu)
+ {
+ struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu);
+ int level = tl->numa_level;
+ int sd_weight = cpumask_weight(
+ sched_domains_numa_masks[level][cpu_to_node(cpu)]);
+
+ *sd = (struct sched_domain){
+ .min_interval = sd_weight,
+ .max_interval = 2*sd_weight,
+ .busy_factor = 32,
+ .imbalance_pct = 125,
+ .cache_nice_tries = 2,
+ .busy_idx = 3,
+ .idle_idx = 2,
+ .newidle_idx = 0,
+ .wake_idx = 0,
+ .forkexec_idx = 0,
+
+ .flags = 1*SD_LOAD_BALANCE
+ | 1*SD_BALANCE_NEWIDLE
+ | 0*SD_BALANCE_EXEC
+ | 0*SD_BALANCE_FORK
+ | 0*SD_BALANCE_WAKE
+ | 0*SD_WAKE_AFFINE
+ | 0*SD_PREFER_LOCAL
+ | 0*SD_SHARE_CPUPOWER
+ | 0*SD_SHARE_PKG_RESOURCES
+ | 1*SD_SERIALIZE
+ | 0*SD_PREFER_SIBLING
+ | sd_local_flags(level)
+ ,
+ .last_balance = jiffies,
+ .balance_interval = sd_weight,
+ };
+ SD_INIT_NAME(sd, NUMA);
+ sd->private = &tl->data;
+
+ /*
+ * Ugly hack to pass state to sd_numa_mask()...
+ */
+ sched_domains_curr_level = tl->numa_level;
+
+ return sd;
+ }
+
+ static const struct cpumask *sd_numa_mask(int cpu)
+ {
+ return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)];
+ }
+
+ static void sched_init_numa(void)
+ {
+ int next_distance, curr_distance = node_distance(0, 0);
+ struct sched_domain_topology_level *tl;
+ int level = 0;
+ int i, j, k;
+
+ sched_domains_numa_scale = curr_distance;
+ sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL);
+ if (!sched_domains_numa_distance)
+ return;
+
+ /*
+ * O(nr_nodes^2) deduplicating selection sort -- in order to find the
+ * unique distances in the node_distance() table.
+ *
+ * Assumes node_distance(0,j) includes all distances in
+ * node_distance(i,j) in order to avoid cubic time.
+ *
+ * XXX: could be optimized to O(n log n) by using sort()
+ */
+ next_distance = curr_distance;
+ for (i = 0; i < nr_node_ids; i++) {
+ for (j = 0; j < nr_node_ids; j++) {
+ int distance = node_distance(0, j);
+ if (distance > curr_distance &&
+ (distance < next_distance ||
+ next_distance == curr_distance))
+ next_distance = distance;
+ }
+ if (next_distance != curr_distance) {
+ sched_domains_numa_distance[level++] = next_distance;
+ sched_domains_numa_levels = level;
+ curr_distance = next_distance;
+ } else break;
+ }
+ /*
+ * 'level' contains the number of unique distances, excluding the
+ * identity distance node_distance(i,i).
+ *
+ * The sched_domains_nume_distance[] array includes the actual distance
+ * numbers.
+ */
+
+ sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL);
+ if (!sched_domains_numa_masks)
+ return;
+
+ /*
+ * Now for each level, construct a mask per node which contains all
+ * cpus of nodes that are that many hops away from us.
+ */
+ for (i = 0; i < level; i++) {
+ sched_domains_numa_masks[i] =
+ kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL);
+ if (!sched_domains_numa_masks[i])
+ return;
+
+ for (j = 0; j < nr_node_ids; j++) {
+ struct cpumask *mask = kzalloc_node(cpumask_size(), GFP_KERNEL, j);
+ if (!mask)
+ return;
+
+ sched_domains_numa_masks[i][j] = mask;
+
+ for (k = 0; k < nr_node_ids; k++) {
+ if (node_distance(j, k) > sched_domains_numa_distance[i])
+ continue;
+
+ cpumask_or(mask, mask, cpumask_of_node(k));
+ }
+ }
+ }
+
+ tl = kzalloc((ARRAY_SIZE(default_topology) + level) *
+ sizeof(struct sched_domain_topology_level), GFP_KERNEL);
+ if (!tl)
+ return;
+
+ /*
+ * Copy the default topology bits..
+ */
+ for (i = 0; default_topology[i].init; i++)
+ tl[i] = default_topology[i];
+
+ /*
+ * .. and append 'j' levels of NUMA goodness.
+ */
+ for (j = 0; j < level; i++, j++) {
+ tl[i] = (struct sched_domain_topology_level){
+ .init = sd_numa_init,
+ .mask = sd_numa_mask,
+ .flags = SDTL_OVERLAP,
+ .numa_level = j,
+ };
+ }
+
+ sched_domain_topology = tl;
+ }
+ #else
+ static inline void sched_init_numa(void)
+ {
+ }
+ #endif /* CONFIG_NUMA */
+
static int __sdt_alloc(const struct cpumask *cpu_map)
{
struct sched_domain_topology_level *tl;
mutex_unlock(&sched_domains_mutex);
}
- #if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT)
- static void reinit_sched_domains(void)
- {
- get_online_cpus();
-
- /* Destroy domains first to force the rebuild */
- partition_sched_domains(0, NULL, NULL);
-
- rebuild_sched_domains();
- put_online_cpus();
- }
-
- static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt)
- {
- unsigned int level = 0;
-
- if (sscanf(buf, "%u", &level) != 1)
- return -EINVAL;
-
- /*
- * level is always be positive so don't check for
- * level < POWERSAVINGS_BALANCE_NONE which is 0
- * What happens on 0 or 1 byte write,
- * need to check for count as well?
- */
-
- if (level >= MAX_POWERSAVINGS_BALANCE_LEVELS)
- return -EINVAL;
-
- if (smt)
- sched_smt_power_savings = level;
- else
- sched_mc_power_savings = level;
-
- reinit_sched_domains();
-
- return count;
- }
-
- #ifdef CONFIG_SCHED_MC
- static ssize_t sched_mc_power_savings_show(struct device *dev,
- struct device_attribute *attr,
- char *buf)
- {
- return sprintf(buf, "%u\n", sched_mc_power_savings);
- }
- static ssize_t sched_mc_power_savings_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
- {
- return sched_power_savings_store(buf, count, 0);
- }
- static DEVICE_ATTR(sched_mc_power_savings, 0644,
- sched_mc_power_savings_show,
- sched_mc_power_savings_store);
- #endif
-
- #ifdef CONFIG_SCHED_SMT
- static ssize_t sched_smt_power_savings_show(struct device *dev,
- struct device_attribute *attr,
- char *buf)
- {
- return sprintf(buf, "%u\n", sched_smt_power_savings);
- }
- static ssize_t sched_smt_power_savings_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
- {
- return sched_power_savings_store(buf, count, 1);
- }
- static DEVICE_ATTR(sched_smt_power_savings, 0644,
- sched_smt_power_savings_show,
- sched_smt_power_savings_store);
- #endif
-
- int __init sched_create_sysfs_power_savings_entries(struct device *dev)
- {
- int err = 0;
-
- #ifdef CONFIG_SCHED_SMT
- if (smt_capable())
- err = device_create_file(dev, &dev_attr_sched_smt_power_savings);
- #endif
- #ifdef CONFIG_SCHED_MC
- if (!err && mc_capable())
- err = device_create_file(dev, &dev_attr_sched_mc_power_savings);
- #endif
- return err;
- }
- #endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */
-
/*
* Update cpusets according to cpu_active mask. If cpusets are
* disabled, cpuset_update_active_cpus() becomes a simple wrapper
alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL);
alloc_cpumask_var(&fallback_doms, GFP_KERNEL);
+ sched_init_numa();
+
get_online_cpus();
mutex_lock(&sched_domains_mutex);
init_sched_domains(cpu_active_mask);
/* May be allocated at isolcpus cmdline parse time */
if (cpu_isolated_map == NULL)
zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT);
+ idle_thread_set_boot_cpu();
#endif
init_sched_fair_class();
.write_u64 = cpu_rt_period_write_uint,
},
#endif
+ { } /* terminate */
};
-static int cpu_cgroup_populate(struct cgroup_subsys *ss, struct cgroup *cont)
-{
- return cgroup_add_files(cont, ss, cpu_files, ARRAY_SIZE(cpu_files));
-}
-
struct cgroup_subsys cpu_cgroup_subsys = {
.name = "cpu",
.create = cpu_cgroup_create,
.can_attach = cpu_cgroup_can_attach,
.attach = cpu_cgroup_attach,
.exit = cpu_cgroup_exit,
- .populate = cpu_cgroup_populate,
.subsys_id = cpu_cgroup_subsys_id,
+ .base_cftypes = cpu_files,
.early_init = 1,
};
.name = "stat",
.read_map = cpuacct_stats_show,
},
+ { } /* terminate */
};
-static int cpuacct_populate(struct cgroup_subsys *ss, struct cgroup *cgrp)
-{
- return cgroup_add_files(cgrp, ss, files, ARRAY_SIZE(files));
-}
-
/*
* charge this task's execution time to its accounting group.
*
.name = "cpuacct",
.create = cpuacct_create,
.destroy = cpuacct_destroy,
- .populate = cpuacct_populate,
.subsys_id = cpuacct_subsys_id,
+ .base_cftypes = files,
};
#endif /* CONFIG_CGROUP_CPUACCT */