diff -Nurb linux-2.6.27-590/arch/Kconfig linux-2.6.27-591/arch/Kconfig --- linux-2.6.27-590/arch/Kconfig 2010-02-01 19:42:05.000000000 -0500 +++ linux-2.6.27-591/arch/Kconfig 2010-02-01 19:42:30.000000000 -0500 @@ -13,9 +13,18 @@ If unsure, say N. +config CHOPSTIX + bool "Chopstix (PlanetLab)" + depends on MODULES && OPROFILE + help + Chopstix allows you to monitor various events by summarizing them + in lossy data structures and transferring these data structures + into user space. If in doubt, say "N". + config HAVE_OPROFILE def_bool n + config KPROBES bool "Kprobes" depends on KALLSYMS && MODULES diff -Nurb linux-2.6.27-590/arch/x86/kernel/asm-offsets_32.c linux-2.6.27-591/arch/x86/kernel/asm-offsets_32.c --- linux-2.6.27-590/arch/x86/kernel/asm-offsets_32.c 2008-10-09 18:13:53.000000000 -0400 +++ linux-2.6.27-591/arch/x86/kernel/asm-offsets_32.c 2010-02-01 19:42:30.000000000 -0500 @@ -9,6 +9,7 @@ #include #include #include +#include #include #include #include "sigframe.h" @@ -24,9 +25,20 @@ #include #include "../../../drivers/lguest/lg.h" + +#define STACKOFFSET(sym, str, mem) \ + DEFINE(sym, offsetof(struct str, mem)-sizeof(struct str)); + /* workaround for a warning with -Wmissing-prototypes */ void foo(void); +struct event_spec { + unsigned long pc; + unsigned long dcookie; + unsigned count; + unsigned int number; +}; + void foo(void) { OFFSET(IA32_SIGCONTEXT_ax, sigcontext, ax); @@ -50,6 +62,16 @@ OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id); BLANK(); + STACKOFFSET(TASK_thread, task_struct, thread); + STACKOFFSET(THREAD_esp, thread_struct, sp); + STACKOFFSET(EVENT_event_data, event, event_data); + STACKOFFSET(EVENT_task, event, task); + STACKOFFSET(EVENT_event_type, event, event_type); + STACKOFFSET(SPEC_number, event_spec, number); + DEFINE(EVENT_SIZE, sizeof(struct event)); + DEFINE(SPEC_SIZE, sizeof(struct event_spec)); + DEFINE(SPEC_EVENT_SIZE, sizeof(struct event_spec)+sizeof(struct event)); + OFFSET(TI_task, thread_info, task); OFFSET(TI_exec_domain, thread_info, exec_domain); OFFSET(TI_flags, thread_info, flags); diff -Nurb linux-2.6.27-590/arch/x86/kernel/entry_32.S linux-2.6.27-591/arch/x86/kernel/entry_32.S --- linux-2.6.27-590/arch/x86/kernel/entry_32.S 2008-10-09 18:13:53.000000000 -0400 +++ linux-2.6.27-591/arch/x86/kernel/entry_32.S 2010-02-01 19:42:30.000000000 -0500 @@ -426,6 +426,33 @@ cmpl $(nr_syscalls), %eax jae syscall_badsys syscall_call: + /* Move Chopstix syscall probe here */ + /* Save and clobber: eax, ecx, ebp */ + pushl %eax + pushl %ecx + pushl %ebp + movl %esp, %ebp + subl $SPEC_EVENT_SIZE, %esp + movl rec_event, %ecx + testl %ecx, %ecx + jz carry_on + # struct event is first, just below %ebp + movl %eax, (SPEC_number-EVENT_SIZE)(%ebp) + leal -SPEC_EVENT_SIZE(%ebp), %eax + movl %eax, EVENT_event_data(%ebp) + movl $6, EVENT_event_type(%ebp) + movl rec_event, %edx + movl $1, 4(%esp) + leal -EVENT_SIZE(%ebp), %eax + movl %eax, (%esp) + call rec_event_asm +carry_on: + addl $SPEC_EVENT_SIZE, %esp + popl %ebp + popl %ecx + popl %eax + /* End chopstix */ + call *sys_call_table(,%eax,4) movl %eax,PT_EAX(%esp) # store the return value syscall_exit: diff -Nurb linux-2.6.27-590/arch/x86/mm/fault.c linux-2.6.27-591/arch/x86/mm/fault.c --- linux-2.6.27-590/arch/x86/mm/fault.c 2010-02-01 19:42:05.000000000 -0500 +++ linux-2.6.27-591/arch/x86/mm/fault.c 2010-02-01 19:42:30.000000000 -0500 @@ -79,6 +79,15 @@ #endif } + +extern void (*rec_event)(void *,unsigned int); +struct event_spec { + unsigned long pc; + unsigned long dcookie; + unsigned count; + unsigned char reason; +}; + /* * X86_32 * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch. diff -Nurb linux-2.6.27-590/drivers/oprofile/cpu_buffer.c linux-2.6.27-591/drivers/oprofile/cpu_buffer.c --- linux-2.6.27-590/drivers/oprofile/cpu_buffer.c 2008-10-09 18:13:53.000000000 -0400 +++ linux-2.6.27-591/drivers/oprofile/cpu_buffer.c 2010-02-01 19:42:30.000000000 -0500 @@ -21,6 +21,7 @@ #include #include #include +#include #include "event_buffer.h" #include "cpu_buffer.h" @@ -147,6 +148,17 @@ b->head_pos = 0; } +#ifdef CONFIG_CHOPSTIX + +struct event_spec { + unsigned int pc; + unsigned long dcookie; + unsigned count; +}; + +extern void (*rec_event)(void *,unsigned int); +#endif + static inline void add_sample(struct oprofile_cpu_buffer * cpu_buf, unsigned long pc, unsigned long event) @@ -155,6 +167,7 @@ entry->eip = pc; entry->event = event; increment_head(cpu_buf); + } static inline void @@ -250,8 +263,28 @@ { int is_kernel = !user_mode(regs); unsigned long pc = profile_pc(regs); + int res=0; +#ifdef CONFIG_CHOPSTIX + if (rec_event) { + struct event esig; + struct event_spec espec; + esig.task = current; + espec.pc=pc; + espec.count=1; + esig.event_data=&espec; + esig.event_type=event; /* index in the event array currently set up */ + /* make sure the counters are loaded in the order we want them to show up*/ + (*rec_event)(&esig, 1); + } + else { oprofile_add_ext_sample(pc, regs, event, is_kernel); + } +#else + oprofile_add_ext_sample(pc, regs, event, is_kernel); +#endif + + } void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event) diff -Nurb linux-2.6.27-590/fs/bio.c linux-2.6.27-591/fs/bio.c --- linux-2.6.27-590/fs/bio.c 2008-10-09 18:13:53.000000000 -0400 +++ linux-2.6.27-591/fs/bio.c 2010-02-01 19:42:30.000000000 -0500 @@ -27,6 +27,7 @@ #include #include #include /* for struct sg_iovec */ +#include static struct kmem_cache *bio_slab __read_mostly; @@ -44,6 +45,7 @@ }; #undef BV + /* * fs_bio_set is the bio_set containing bio and iovec memory pools used by * IO code that does not need private memory pools. @@ -1171,6 +1173,14 @@ } } +struct event_spec { + unsigned long pc; + unsigned long dcookie; + unsigned count; + unsigned char reason; +}; + +extern void (*rec_event)(void *,unsigned int); /** * bio_endio - end I/O on a bio * @bio: bio @@ -1192,6 +1202,24 @@ else if (!test_bit(BIO_UPTODATE, &bio->bi_flags)) error = -EIO; +#if 0 + if (rec_event) { + struct event event; + struct event_spec espec; + unsigned long eip; + + espec.reason = 1;/*response */ + + eip = bio->bi_end_io; + event.event_data=&espec; + espec.pc=eip; + event.event_type=3; + /* index in the event array currently set up */ + /* make sure the counters are loaded in the order we want them to show up*/ + (*rec_event)(&event, bytes_done); + } +#endif + if (bio->bi_end_io) bio->bi_end_io(bio, error); } diff -Nurb linux-2.6.27-590/fs/exec.c linux-2.6.27-591/fs/exec.c --- linux-2.6.27-590/fs/exec.c 2010-02-01 19:42:07.000000000 -0500 +++ linux-2.6.27-591/fs/exec.c 2010-02-01 19:42:31.000000000 -0500 @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -698,6 +699,13 @@ goto out; } + #ifdef CONFIG_CHOPSTIX + unsigned long cookie; + extern void (*rec_event)(void *, unsigned int); + if (rec_event && !nd.path.dentry->d_cookie) + get_dcookie(&nd.path, &cookie); + #endif + return file; out_path_put: diff -Nurb linux-2.6.27-590/include/linux/arrays.h linux-2.6.27-591/include/linux/arrays.h --- linux-2.6.27-590/include/linux/arrays.h 1969-12-31 19:00:00.000000000 -0500 +++ linux-2.6.27-591/include/linux/arrays.h 2010-02-01 19:42:31.000000000 -0500 @@ -0,0 +1,36 @@ +#ifndef __ARRAYS_H__ +#define __ARRAYS_H__ +#include + +#define SAMPLING_METHOD_DEFAULT 0 +#define SAMPLING_METHOD_LOG 1 + +/* Every probe has an array handler */ + +/* XXX - Optimize this structure */ + +extern void (*rec_event)(void *,unsigned int); +struct array_handler { + struct list_head link; + unsigned int (*hash_func)(void *); + unsigned int (*sampling_func)(void *,int,void *); + unsigned short size; + unsigned int threshold; + unsigned char **expcount; + unsigned int sampling_method; + unsigned int **arrays; + unsigned int arraysize; + unsigned int num_samples[2]; + void **epoch_samples; /* size-sized lists of samples */ + unsigned int (*serialize)(void *, void *); + unsigned char code[5]; +}; + +struct event { + struct list_head link; + void *event_data; + unsigned int count; + unsigned int event_type; + struct task_struct *task; +}; +#endif diff -Nurb linux-2.6.27-590/include/linux/sched.h linux-2.6.27-591/include/linux/sched.h --- linux-2.6.27-590/include/linux/sched.h 2010-02-01 19:42:07.000000000 -0500 +++ linux-2.6.27-591/include/linux/sched.h 2010-02-01 19:47:30.000000000 -0500 @@ -1133,6 +1133,11 @@ cputime_t utime, stime, utimescaled, stimescaled; cputime_t gtime; cputime_t prev_utime, prev_stime; + + #ifdef CONFIG_CHOPSTIX + unsigned long last_interrupted, last_ran_j; + #endif + unsigned long nvcsw, nivcsw; /* context switch counts */ struct timespec start_time; /* monotonic time */ struct timespec real_start_time; /* boot based time */ diff -Nurb linux-2.6.27-590/include/linux/sched.h.rej linux-2.6.27-591/include/linux/sched.h.rej --- linux-2.6.27-590/include/linux/sched.h.rej 1969-12-31 19:00:00.000000000 -0500 +++ linux-2.6.27-591/include/linux/sched.h.rej 2010-02-01 19:42:31.000000000 -0500 @@ -0,0 +1,19 @@ +*************** +*** 850,855 **** + #endif + unsigned long sleep_avg; + unsigned long long timestamp, last_ran; + unsigned long long sched_time; /* sched_clock time spent running */ + enum sleep_type sleep_type; + +--- 850,859 ---- + #endif + unsigned long sleep_avg; + unsigned long long timestamp, last_ran; ++ #ifdef CONFIG_CHOPSTIX ++ unsigned long last_interrupted, last_ran_j; ++ #endif ++ + unsigned long long sched_time; /* sched_clock time spent running */ + enum sleep_type sleep_type; + diff -Nurb linux-2.6.27-590/kernel/sched.c linux-2.6.27-591/kernel/sched.c --- linux-2.6.27-590/kernel/sched.c 2010-02-01 19:42:07.000000000 -0500 +++ linux-2.6.27-591/kernel/sched.c 2010-02-01 19:47:30.000000000 -0500 @@ -10,7 +10,7 @@ * 1998-11-19 Implemented schedule_timeout() and related stuff * by Andrea Arcangeli * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: - * hybrid priority-list and round-robin design with + * hybrid priority-list and round-robin deventn with * an array-switch method of distributing timeslices * and per-CPU runqueues. Cleanups and useful suggestions * by Davide Libenzi, preemptible kernel bits by Robert Love. @@ -73,12 +73,16 @@ #include #include #include +#include #include #include #include "sched_cpupri.h" +#define INTERRUPTIBLE -1 +#define RUNNING 0 + /* * Convert user-nice values [ -20 ... 0 ... 19 ] * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], @@ -2368,6 +2372,10 @@ INIT_HLIST_HEAD(&p->preempt_notifiers); #endif +#ifdef CONFIG_CHOPSTIX + p->last_ran_j = jiffies; + p->last_interrupted = INTERRUPTIBLE; +#endif /* * We mark the process as running here, but have not actually * inserted it onto the runqueue yet. This guarantees that @@ -4428,6 +4436,29 @@ } } +void (*rec_event)(void *,unsigned int) = NULL; +EXPORT_SYMBOL(rec_event); +#ifdef CONFIG_CHOPSTIX + +struct event_spec { + unsigned long pc; + unsigned long dcookie; + unsigned int count; + unsigned int reason; +}; + +/* To support safe calling from asm */ +asmlinkage void rec_event_asm (struct event *event_signature_in, unsigned int count) { + struct pt_regs *regs; + struct event_spec *es = event_signature_in->event_data; + regs = task_pt_regs(current); + event_signature_in->task=current; + es->pc=regs->ip; + event_signature_in->count=1; + (*rec_event)(event_signature_in, count); +} +#endif + /* * schedule() is the main scheduler function. */ @@ -4482,6 +4513,61 @@ next = pick_next_task(rq, prev); if (likely(prev != next)) { + +#ifdef CONFIG_CHOPSTIX + /* Run only if the Chopstix module so decrees it */ + if (rec_event) { + unsigned long diff; + int sampling_reason; + prev->last_ran_j = jiffies; + if (next->last_interrupted!=INTERRUPTIBLE) { + if (next->last_interrupted!=RUNNING) { + diff = (jiffies-next->last_interrupted); + sampling_reason = 0;/* BLOCKING */ + } + else { + diff = jiffies-next->last_ran_j; + sampling_reason = 1;/* PREEMPTION */ + } + + if (diff >= HZ/10) { + struct event_spec { + unsigned long pc; + unsigned long dcookie; + unsigned int count; + unsigned int reason; + }; + + struct event event; + struct event_spec espec; + struct pt_regs *regs; + regs = task_pt_regs(current); + + espec.reason = sampling_reason; + event.event_data=&espec; + event.task=next; + espec.pc=regs->ip; + event.event_type=2; + /* index in the event array currently set up */ + /* make sure the counters are loaded in the order we want them to show up*/ + (*rec_event)(&event, diff); + } + } + /* next has been elected to run */ + next->last_interrupted=0; + + /* An uninterruptible process just yielded. Record the current jiffy */ + if (prev->state & TASK_UNINTERRUPTIBLE) { + prev->last_interrupted=jiffies; + } + /* An interruptible process just yielded, or it got preempted. + * Mark it as interruptible */ + else if (prev->state & TASK_INTERRUPTIBLE) { + prev->last_interrupted=INTERRUPTIBLE; + } + } +#endif + sched_info_switch(prev, next); rq->nr_switches++; @@ -5369,6 +5455,7 @@ get_task_struct(p); read_unlock(&tasklist_lock); + retval = -EPERM; if ((current->euid != p->euid) && (current->euid != p->uid) && !capable(CAP_SYS_NICE)) diff -Nurb linux-2.6.27-590/kernel/sched.c.orig linux-2.6.27-591/kernel/sched.c.orig --- linux-2.6.27-590/kernel/sched.c.orig 1969-12-31 19:00:00.000000000 -0500 +++ linux-2.6.27-591/kernel/sched.c.orig 2010-02-01 19:43:07.000000000 -0500 @@ -0,0 +1,9326 @@ +/* + * kernel/sched.c + * + * Kernel scheduler and related syscalls + * + * Copyright (C) 1991-2002 Linus Torvalds + * + * 1996-12-23 Modified by Dave Grothe to fix bugs in semaphores and + * make semaphores SMP safe + * 1998-11-19 Implemented schedule_timeout() and related stuff + * by Andrea Arcangeli + * 2002-01-04 New ultra-scalable O(1) scheduler by Ingo Molnar: + * hybrid priority-list and round-robin deventn with + * an array-switch method of distributing timeslices + * and per-CPU runqueues. Cleanups and useful suggestions + * by Davide Libenzi, preemptible kernel bits by Robert Love. + * 2003-09-03 Interactivity tuning by Con Kolivas. + * 2004-04-02 Scheduler domains code by Nick Piggin + * 2007-04-15 Work begun on replacing all interactivity tuning with a + * fair scheduling design by Con Kolivas. + * 2007-05-05 Load balancing (smp-nice) and other improvements + * by Peter Williams + * 2007-05-06 Interactivity improvements to CFS by Mike Galbraith + * 2007-07-01 Group scheduling enhancements by Srivatsa Vaddagiri + * 2007-11-29 RT balancing improvements by Steven Rostedt, Gregory Haskins, + * Thomas Gleixner, Mike Kravetz + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "sched_cpupri.h" + +#define INTERRUPTIBLE -1 +#define RUNNING 0 + +/* + * Convert user-nice values [ -20 ... 0 ... 19 ] + * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ], + * and back. + */ +#define NICE_TO_PRIO(nice) (MAX_RT_PRIO + (nice) + 20) +#define PRIO_TO_NICE(prio) ((prio) - MAX_RT_PRIO - 20) +#define TASK_NICE(p) PRIO_TO_NICE((p)->static_prio) + +/* + * 'User priority' is the nice value converted to something we + * can work with better when scaling various scheduler parameters, + * it's a [ 0 ... 39 ] range. + */ +#define USER_PRIO(p) ((p)-MAX_RT_PRIO) +#define TASK_USER_PRIO(p) USER_PRIO((p)->static_prio) +#define MAX_USER_PRIO (USER_PRIO(MAX_PRIO)) + +/* + * Helpers for converting nanosecond timing to jiffy resolution + */ +#define NS_TO_JIFFIES(TIME) ((unsigned long)(TIME) / (NSEC_PER_SEC / HZ)) + +#define NICE_0_LOAD SCHED_LOAD_SCALE +#define NICE_0_SHIFT SCHED_LOAD_SHIFT + +/* + * These are the 'tuning knobs' of the scheduler: + * + * default timeslice is 100 msecs (used only for SCHED_RR tasks). + * Timeslices get refilled after they expire. + */ +#define DEF_TIMESLICE (100 * HZ / 1000) + +/* + * single value that denotes runtime == period, ie unlimited time. + */ +#define RUNTIME_INF ((u64)~0ULL) + +#ifdef CONFIG_SMP +/* + * Divide a load by a sched group cpu_power : (load / sg->__cpu_power) + * Since cpu_power is a 'constant', we can use a reciprocal divide. + */ +static inline u32 sg_div_cpu_power(const struct sched_group *sg, u32 load) +{ + return reciprocal_divide(load, sg->reciprocal_cpu_power); +} + +/* + * Each time a sched group cpu_power is changed, + * we must compute its reciprocal value + */ +static inline void sg_inc_cpu_power(struct sched_group *sg, u32 val) +{ + sg->__cpu_power += val; + sg->reciprocal_cpu_power = reciprocal_value(sg->__cpu_power); +} +#endif + +static inline int rt_policy(int policy) +{ + if (unlikely(policy == SCHED_FIFO || policy == SCHED_RR)) + return 1; + return 0; +} + +static inline int task_has_rt_policy(struct task_struct *p) +{ + return rt_policy(p->policy); +} + +/* + * This is the priority-queue data structure of the RT scheduling class: + */ +struct rt_prio_array { + DECLARE_BITMAP(bitmap, MAX_RT_PRIO+1); /* include 1 bit for delimiter */ + struct list_head queue[MAX_RT_PRIO]; +}; + +struct rt_bandwidth { + /* nests inside the rq lock: */ + spinlock_t rt_runtime_lock; + ktime_t rt_period; + u64 rt_runtime; + struct hrtimer rt_period_timer; +}; + +static struct rt_bandwidth def_rt_bandwidth; + +static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun); + +static enum hrtimer_restart sched_rt_period_timer(struct hrtimer *timer) +{ + struct rt_bandwidth *rt_b = + container_of(timer, struct rt_bandwidth, rt_period_timer); + ktime_t now; + int overrun; + int idle = 0; + + for (;;) { + now = hrtimer_cb_get_time(timer); + overrun = hrtimer_forward(timer, now, rt_b->rt_period); + + if (!overrun) + break; + + idle = do_sched_rt_period_timer(rt_b, overrun); + } + + return idle ? HRTIMER_NORESTART : HRTIMER_RESTART; +} + +static +void init_rt_bandwidth(struct rt_bandwidth *rt_b, u64 period, u64 runtime) +{ + rt_b->rt_period = ns_to_ktime(period); + rt_b->rt_runtime = runtime; + + spin_lock_init(&rt_b->rt_runtime_lock); + + hrtimer_init(&rt_b->rt_period_timer, + CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rt_b->rt_period_timer.function = sched_rt_period_timer; + rt_b->rt_period_timer.cb_mode = HRTIMER_CB_IRQSAFE_UNLOCKED; +} + +static void start_rt_bandwidth(struct rt_bandwidth *rt_b) +{ + ktime_t now; + + if (rt_b->rt_runtime == RUNTIME_INF) + return; + + if (hrtimer_active(&rt_b->rt_period_timer)) + return; + + spin_lock(&rt_b->rt_runtime_lock); + for (;;) { + if (hrtimer_active(&rt_b->rt_period_timer)) + break; + + now = hrtimer_cb_get_time(&rt_b->rt_period_timer); + hrtimer_forward(&rt_b->rt_period_timer, now, rt_b->rt_period); + hrtimer_start(&rt_b->rt_period_timer, + rt_b->rt_period_timer.expires, + HRTIMER_MODE_ABS); + } + spin_unlock(&rt_b->rt_runtime_lock); +} + +#ifdef CONFIG_RT_GROUP_SCHED +static void destroy_rt_bandwidth(struct rt_bandwidth *rt_b) +{ + hrtimer_cancel(&rt_b->rt_period_timer); +} +#endif + +/* + * sched_domains_mutex serializes calls to arch_init_sched_domains, + * detach_destroy_domains and partition_sched_domains. + */ +static DEFINE_MUTEX(sched_domains_mutex); + +#ifdef CONFIG_GROUP_SCHED + +#include + +struct cfs_rq; + +static LIST_HEAD(task_groups); + +/* task group related information */ +struct task_group { +#ifdef CONFIG_CGROUP_SCHED + struct cgroup_subsys_state css; +#endif + +#ifdef CONFIG_FAIR_GROUP_SCHED + /* schedulable entities of this group on each cpu */ + struct sched_entity **se; + /* runqueue "owned" by this group on each cpu */ + struct cfs_rq **cfs_rq; + unsigned long shares; +#endif + +#ifdef CONFIG_RT_GROUP_SCHED + struct sched_rt_entity **rt_se; + struct rt_rq **rt_rq; + + struct rt_bandwidth rt_bandwidth; +#endif + + struct rcu_head rcu; + struct list_head list; + + struct task_group *parent; + struct list_head siblings; + struct list_head children; +}; + +#ifdef CONFIG_USER_SCHED + +/* + * Root task group. + * Every UID task group (including init_task_group aka UID-0) will + * be a child to this group. + */ +struct task_group root_task_group; + +#ifdef CONFIG_FAIR_GROUP_SCHED +/* Default task group's sched entity on each cpu */ +static DEFINE_PER_CPU(struct sched_entity, init_sched_entity); +/* Default task group's cfs_rq on each cpu */ +static DEFINE_PER_CPU(struct cfs_rq, init_cfs_rq) ____cacheline_aligned_in_smp; +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +#ifdef CONFIG_RT_GROUP_SCHED +static DEFINE_PER_CPU(struct sched_rt_entity, init_sched_rt_entity); +static DEFINE_PER_CPU(struct rt_rq, init_rt_rq) ____cacheline_aligned_in_smp; +#endif /* CONFIG_RT_GROUP_SCHED */ +#else /* !CONFIG_FAIR_GROUP_SCHED */ +#define root_task_group init_task_group +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +/* task_group_lock serializes add/remove of task groups and also changes to + * a task group's cpu shares. + */ +static DEFINE_SPINLOCK(task_group_lock); + +#ifdef CONFIG_FAIR_GROUP_SCHED +#ifdef CONFIG_USER_SCHED +# define INIT_TASK_GROUP_LOAD (2*NICE_0_LOAD) +#else /* !CONFIG_USER_SCHED */ +# define INIT_TASK_GROUP_LOAD NICE_0_LOAD +#endif /* CONFIG_USER_SCHED */ + +/* + * A weight of 0 or 1 can cause arithmetics problems. + * A weight of a cfs_rq is the sum of weights of which entities + * are queued on this cfs_rq, so a weight of a entity should not be + * too large, so as the shares value of a task group. + * (The default weight is 1024 - so there's no practical + * limitation from this.) + */ +#define MIN_SHARES 2 +#define MAX_SHARES (1UL << 18) + +static int init_task_group_load = INIT_TASK_GROUP_LOAD; +#endif + +/* Default task group. + * Every task in system belong to this group at bootup. + */ +struct task_group init_task_group; + +/* return group to which a task belongs */ +static inline struct task_group *task_group(struct task_struct *p) +{ + struct task_group *tg; + +#ifdef CONFIG_USER_SCHED + tg = p->user->tg; +#elif defined(CONFIG_CGROUP_SCHED) + tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id), + struct task_group, css); +#else + tg = &init_task_group; +#endif + return tg; +} + +/* Change a task's cfs_rq and parent entity if it moves across CPUs/groups */ +static inline void set_task_rq(struct task_struct *p, unsigned int cpu) +{ +#ifdef CONFIG_FAIR_GROUP_SCHED + p->se.cfs_rq = task_group(p)->cfs_rq[cpu]; + p->se.parent = task_group(p)->se[cpu]; +#endif + +#ifdef CONFIG_RT_GROUP_SCHED + p->rt.rt_rq = task_group(p)->rt_rq[cpu]; + p->rt.parent = task_group(p)->rt_se[cpu]; +#endif +} + +#else + +static inline void set_task_rq(struct task_struct *p, unsigned int cpu) { } +static inline struct task_group *task_group(struct task_struct *p) +{ + return NULL; +} + +#endif /* CONFIG_GROUP_SCHED */ + +/* CFS-related fields in a runqueue */ +struct cfs_rq { + struct load_weight load; + unsigned long nr_running; + + u64 exec_clock; + u64 min_vruntime; + u64 pair_start; + + struct rb_root tasks_timeline; + struct rb_node *rb_leftmost; + + struct list_head tasks; + struct list_head *balance_iterator; + + /* + * 'curr' points to currently running entity on this cfs_rq. + * It is set to NULL otherwise (i.e when none are currently running). + */ + struct sched_entity *curr, *next; + + unsigned long nr_spread_over; + +#ifdef CONFIG_FAIR_GROUP_SCHED + struct rq *rq; /* cpu runqueue to which this cfs_rq is attached */ + + /* + * leaf cfs_rqs are those that hold tasks (lowest schedulable entity in + * a hierarchy). Non-leaf lrqs hold other higher schedulable entities + * (like users, containers etc.) + * + * leaf_cfs_rq_list ties together list of leaf cfs_rq's in a cpu. This + * list is used during load balance. + */ + struct list_head leaf_cfs_rq_list; + struct task_group *tg; /* group that "owns" this runqueue */ + +#ifdef CONFIG_SMP + /* + * the part of load.weight contributed by tasks + */ + unsigned long task_weight; + + /* + * h_load = weight * f(tg) + * + * Where f(tg) is the recursive weight fraction assigned to + * this group. + */ + unsigned long h_load; + + /* + * this cpu's part of tg->shares + */ + unsigned long shares; + + /* + * load.weight at the time we set shares + */ + unsigned long rq_weight; +#endif +#endif +}; + +/* Real-Time classes' related field in a runqueue: */ +struct rt_rq { + struct rt_prio_array active; + unsigned long rt_nr_running; +#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED + int highest_prio; /* highest queued rt task prio */ +#endif +#ifdef CONFIG_SMP + unsigned long rt_nr_migratory; + int overloaded; +#endif + int rt_throttled; + u64 rt_time; + u64 rt_runtime; + /* Nests inside the rq lock: */ + spinlock_t rt_runtime_lock; + +#ifdef CONFIG_RT_GROUP_SCHED + unsigned long rt_nr_boosted; + + struct rq *rq; + struct list_head leaf_rt_rq_list; + struct task_group *tg; + struct sched_rt_entity *rt_se; +#endif +}; + +#ifdef CONFIG_SMP + +/* + * We add the notion of a root-domain which will be used to define per-domain + * variables. Each exclusive cpuset essentially defines an island domain by + * fully partitioning the member cpus from any other cpuset. Whenever a new + * exclusive cpuset is created, we also create and attach a new root-domain + * object. + * + */ +struct root_domain { + atomic_t refcount; + cpumask_t span; + cpumask_t online; + + /* + * The "RT overload" flag: it gets set if a CPU has more than + * one runnable RT task. + */ + cpumask_t rto_mask; + atomic_t rto_count; +#ifdef CONFIG_SMP + struct cpupri cpupri; +#endif +}; + +/* + * By default the system creates a single root-domain with all cpus as + * members (mimicking the global state we have today). + */ +static struct root_domain def_root_domain; + +#endif + unsigned long norm_time; + unsigned long idle_time; +#ifdef CONFIG_VSERVER_IDLETIME + int idle_skip; +#endif +#ifdef CONFIG_VSERVER_HARDCPU + struct list_head hold_queue; + unsigned long nr_onhold; + int idle_tokens; +#endif + +/* + * This is the main, per-CPU runqueue data structure. + * + * Locking rule: those places that want to lock multiple runqueues + * (such as the load balancing or the thread migration code), lock + * acquire operations must be ordered by ascending &runqueue. + */ +struct rq { + /* runqueue lock: */ + spinlock_t lock; + + /* + * nr_running and cpu_load should be in the same cacheline because + * remote CPUs use both these fields when doing load calculation. + */ + unsigned long nr_running; + #define CPU_LOAD_IDX_MAX 5 + unsigned long cpu_load[CPU_LOAD_IDX_MAX]; + unsigned char idle_at_tick; +#ifdef CONFIG_NO_HZ + unsigned long last_tick_seen; + unsigned char in_nohz_recently; +#endif + /* capture load from *all* tasks on this cpu: */ + struct load_weight load; + unsigned long nr_load_updates; + u64 nr_switches; + + struct cfs_rq cfs; + struct rt_rq rt; + +#ifdef CONFIG_FAIR_GROUP_SCHED + /* list of leaf cfs_rq on this cpu: */ + struct list_head leaf_cfs_rq_list; +#endif +#ifdef CONFIG_RT_GROUP_SCHED + struct list_head leaf_rt_rq_list; +#endif + + /* + * This is part of a global counter where only the total sum + * over all CPUs matters. A task can increase this counter on + * one CPU and if it got migrated afterwards it may decrease + * it on another CPU. Always updated under the runqueue lock: + */ + unsigned long nr_uninterruptible; + + struct task_struct *curr, *idle; + unsigned long next_balance; + struct mm_struct *prev_mm; + + u64 clock; + + atomic_t nr_iowait; + +#ifdef CONFIG_SMP + struct root_domain *rd; + struct sched_domain *sd; + + /* For active balancing */ + int active_balance; + int push_cpu; + /* cpu of this runqueue: */ + int cpu; + int online; + + unsigned long avg_load_per_task; + + struct task_struct *migration_thread; + struct list_head migration_queue; +#endif + +#ifdef CONFIG_SCHED_HRTICK +#ifdef CONFIG_SMP + int hrtick_csd_pending; + struct call_single_data hrtick_csd; +#endif + struct hrtimer hrtick_timer; +#endif + +#ifdef CONFIG_SCHEDSTATS + /* latency stats */ + struct sched_info rq_sched_info; + + /* sys_sched_yield() stats */ + unsigned int yld_exp_empty; + unsigned int yld_act_empty; + unsigned int yld_both_empty; + unsigned int yld_count; + + /* schedule() stats */ + unsigned int sched_switch; + unsigned int sched_count; + unsigned int sched_goidle; + + /* try_to_wake_up() stats */ + unsigned int ttwu_count; + unsigned int ttwu_local; + + /* BKL stats */ + unsigned int bkl_count; +#endif +}; + +static DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); + +static inline void check_preempt_curr(struct rq *rq, struct task_struct *p) +{ + rq->curr->sched_class->check_preempt_curr(rq, p); +} + +static inline int cpu_of(struct rq *rq) +{ +#ifdef CONFIG_SMP + return rq->cpu; +#else + return 0; +#endif +} + +/* + * The domain tree (rq->sd) is protected by RCU's quiescent state transition. + * See detach_destroy_domains: synchronize_sched for details. + * + * The domain tree of any CPU may only be accessed from within + * preempt-disabled sections. + */ +#define for_each_domain(cpu, __sd) \ + for (__sd = rcu_dereference(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) + +#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu))) +#define this_rq() (&__get_cpu_var(runqueues)) +#define task_rq(p) cpu_rq(task_cpu(p)) +#define cpu_curr(cpu) (cpu_rq(cpu)->curr) + +static inline void update_rq_clock(struct rq *rq) +{ + rq->clock = sched_clock_cpu(cpu_of(rq)); +} + +/* + * Tunables that become constants when CONFIG_SCHED_DEBUG is off: + */ +#ifdef CONFIG_SCHED_DEBUG +# define const_debug __read_mostly +#else +# define const_debug static const +#endif + +/** + * runqueue_is_locked + * + * Returns true if the current cpu runqueue is locked. + * This interface allows printk to be called with the runqueue lock + * held and know whether or not it is OK to wake up the klogd. + */ +int runqueue_is_locked(void) +{ + int cpu = get_cpu(); + struct rq *rq = cpu_rq(cpu); + int ret; + + ret = spin_is_locked(&rq->lock); + put_cpu(); + return ret; +} + +/* + * Debugging: various feature bits + */ + +#define SCHED_FEAT(name, enabled) \ + __SCHED_FEAT_##name , + +enum { +#include "sched_features.h" +}; + +#undef SCHED_FEAT + +#define SCHED_FEAT(name, enabled) \ + (1UL << __SCHED_FEAT_##name) * enabled | + +const_debug unsigned int sysctl_sched_features = +#include "sched_features.h" + 0; + +#undef SCHED_FEAT + +#ifdef CONFIG_SCHED_DEBUG +#define SCHED_FEAT(name, enabled) \ + #name , + +static __read_mostly char *sched_feat_names[] = { +#include "sched_features.h" + NULL +}; + +#undef SCHED_FEAT + +static int sched_feat_open(struct inode *inode, struct file *filp) +{ + filp->private_data = inode->i_private; + return 0; +} + +static ssize_t +sched_feat_read(struct file *filp, char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char *buf; + int r = 0; + int len = 0; + int i; + + for (i = 0; sched_feat_names[i]; i++) { + len += strlen(sched_feat_names[i]); + len += 4; + } + + buf = kmalloc(len + 2, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + for (i = 0; sched_feat_names[i]; i++) { + if (sysctl_sched_features & (1UL << i)) + r += sprintf(buf + r, "%s ", sched_feat_names[i]); + else + r += sprintf(buf + r, "NO_%s ", sched_feat_names[i]); + } + + r += sprintf(buf + r, "\n"); + WARN_ON(r >= len + 2); + + r = simple_read_from_buffer(ubuf, cnt, ppos, buf, r); + + kfree(buf); + + return r; +} + +static ssize_t +sched_feat_write(struct file *filp, const char __user *ubuf, + size_t cnt, loff_t *ppos) +{ + char buf[64]; + char *cmp = buf; + int neg = 0; + int i; + + if (cnt > 63) + cnt = 63; + + if (copy_from_user(&buf, ubuf, cnt)) + return -EFAULT; + + buf[cnt] = 0; + + if (strncmp(buf, "NO_", 3) == 0) { + neg = 1; + cmp += 3; + } + + for (i = 0; sched_feat_names[i]; i++) { + int len = strlen(sched_feat_names[i]); + + if (strncmp(cmp, sched_feat_names[i], len) == 0) { + if (neg) + sysctl_sched_features &= ~(1UL << i); + else + sysctl_sched_features |= (1UL << i); + break; + } + } + + if (!sched_feat_names[i]) + return -EINVAL; + + filp->f_pos += cnt; + + return cnt; +} + +static struct file_operations sched_feat_fops = { + .open = sched_feat_open, + .read = sched_feat_read, + .write = sched_feat_write, +}; + +static __init int sched_init_debug(void) +{ + debugfs_create_file("sched_features", 0644, NULL, NULL, + &sched_feat_fops); + + return 0; +} +late_initcall(sched_init_debug); + +#endif + +#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x)) + +/* + * Number of tasks to iterate in a single balance run. + * Limited because this is done with IRQs disabled. + */ +const_debug unsigned int sysctl_sched_nr_migrate = 32; + +/* + * ratelimit for updating the group shares. + * default: 0.25ms + */ +unsigned int sysctl_sched_shares_ratelimit = 250000; + +/* + * period over which we measure -rt task cpu usage in us. + * default: 1s + */ +unsigned int sysctl_sched_rt_period = 1000000; + +static __read_mostly int scheduler_running; + +/* + * part of the period that we allow rt tasks to run in us. + * default: 0.95s + */ +int sysctl_sched_rt_runtime = 950000; + +static inline u64 global_rt_period(void) +{ + return (u64)sysctl_sched_rt_period * NSEC_PER_USEC; +} + +static inline u64 global_rt_runtime(void) +{ + if (sysctl_sched_rt_runtime < 0) + return RUNTIME_INF; + + return (u64)sysctl_sched_rt_runtime * NSEC_PER_USEC; +} + +#ifndef prepare_arch_switch +# define prepare_arch_switch(next) do { } while (0) +#endif +#ifndef finish_arch_switch +# define finish_arch_switch(prev) do { } while (0) +#endif + +static inline int task_current(struct rq *rq, struct task_struct *p) +{ + return rq->curr == p; +} + +#ifndef __ARCH_WANT_UNLOCKED_CTXSW +static inline int task_running(struct rq *rq, struct task_struct *p) +{ + return task_current(rq, p); +} + +static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) +{ +} + +static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) +{ +#ifdef CONFIG_DEBUG_SPINLOCK + /* this is a valid case when another task releases the spinlock */ + rq->lock.owner = current; +#endif + /* + * If we are tracking spinlock dependencies then we have to + * fix up the runqueue lock - which gets 'carried over' from + * prev into current: + */ + spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_); + + spin_unlock_irq(&rq->lock); +} + +#else /* __ARCH_WANT_UNLOCKED_CTXSW */ +static inline int task_running(struct rq *rq, struct task_struct *p) +{ +#ifdef CONFIG_SMP + return p->oncpu; +#else + return task_current(rq, p); +#endif +} + +static inline void prepare_lock_switch(struct rq *rq, struct task_struct *next) +{ +#ifdef CONFIG_SMP + /* + * We can optimise this out completely for !SMP, because the + * SMP rebalancing from interrupt is the only thing that cares + * here. + */ + next->oncpu = 1; +#endif +#ifdef __ARCH_WANT_INTERRUPTS_ON_CTXSW + spin_unlock_irq(&rq->lock); +#else + spin_unlock(&rq->lock); +#endif +} + +static inline void finish_lock_switch(struct rq *rq, struct task_struct *prev) +{ +#ifdef CONFIG_SMP + /* + * After ->oncpu is cleared, the task can be moved to a different CPU. + * We must ensure this doesn't happen until the switch is completely + * finished. + */ + smp_wmb(); + prev->oncpu = 0; +#endif +#ifndef __ARCH_WANT_INTERRUPTS_ON_CTXSW + local_irq_enable(); +#endif +} +#endif /* __ARCH_WANT_UNLOCKED_CTXSW */ + +/* + * __task_rq_lock - lock the runqueue a given task resides on. + * Must be called interrupts disabled. + */ +static inline struct rq *__task_rq_lock(struct task_struct *p) + __acquires(rq->lock) +{ + for (;;) { + struct rq *rq = task_rq(p); + spin_lock(&rq->lock); + if (likely(rq == task_rq(p))) + return rq; + spin_unlock(&rq->lock); + } +} + +/* + * task_rq_lock - lock the runqueue a given task resides on and disable + * interrupts. Note the ordering: we can safely lookup the task_rq without + * explicitly disabling preemption. + */ +static struct rq *task_rq_lock(struct task_struct *p, unsigned long *flags) + __acquires(rq->lock) +{ + struct rq *rq; + + for (;;) { + local_irq_save(*flags); + rq = task_rq(p); + spin_lock(&rq->lock); + if (likely(rq == task_rq(p))) + return rq; + spin_unlock_irqrestore(&rq->lock, *flags); + } +} + +static void __task_rq_unlock(struct rq *rq) + __releases(rq->lock) +{ + spin_unlock(&rq->lock); +} + +static inline void task_rq_unlock(struct rq *rq, unsigned long *flags) + __releases(rq->lock) +{ + spin_unlock_irqrestore(&rq->lock, *flags); +} + +/* + * this_rq_lock - lock this runqueue and disable interrupts. + */ +static struct rq *this_rq_lock(void) + __acquires(rq->lock) +{ + struct rq *rq; + + local_irq_disable(); + rq = this_rq(); + spin_lock(&rq->lock); + + return rq; +} + +#ifdef CONFIG_SCHED_HRTICK +/* + * Use HR-timers to deliver accurate preemption points. + * + * Its all a bit involved since we cannot program an hrt while holding the + * rq->lock. So what we do is store a state in in rq->hrtick_* and ask for a + * reschedule event. + * + * When we get rescheduled we reprogram the hrtick_timer outside of the + * rq->lock. + */ + +/* + * Use hrtick when: + * - enabled by features + * - hrtimer is actually high res + */ +static inline int hrtick_enabled(struct rq *rq) +{ + if (!sched_feat(HRTICK)) + return 0; + if (!cpu_active(cpu_of(rq))) + return 0; + return hrtimer_is_hres_active(&rq->hrtick_timer); +} + +static void hrtick_clear(struct rq *rq) +{ + if (hrtimer_active(&rq->hrtick_timer)) + hrtimer_cancel(&rq->hrtick_timer); +} + +/* + * High-resolution timer tick. + * Runs from hardirq context with interrupts disabled. + */ +static enum hrtimer_restart hrtick(struct hrtimer *timer) +{ + struct rq *rq = container_of(timer, struct rq, hrtick_timer); + + WARN_ON_ONCE(cpu_of(rq) != smp_processor_id()); + + spin_lock(&rq->lock); + update_rq_clock(rq); + rq->curr->sched_class->task_tick(rq, rq->curr, 1); + spin_unlock(&rq->lock); + + return HRTIMER_NORESTART; +} + +#ifdef CONFIG_SMP +/* + * called from hardirq (IPI) context + */ +static void __hrtick_start(void *arg) +{ + struct rq *rq = arg; + + spin_lock(&rq->lock); + hrtimer_restart(&rq->hrtick_timer); + rq->hrtick_csd_pending = 0; + spin_unlock(&rq->lock); +} + +/* + * Called to set the hrtick timer state. + * + * called with rq->lock held and irqs disabled + */ +static void hrtick_start(struct rq *rq, u64 delay) +{ + struct hrtimer *timer = &rq->hrtick_timer; + ktime_t time = ktime_add_ns(timer->base->get_time(), delay); + + timer->expires = time; + + if (rq == this_rq()) { + hrtimer_restart(timer); + } else if (!rq->hrtick_csd_pending) { + __smp_call_function_single(cpu_of(rq), &rq->hrtick_csd); + rq->hrtick_csd_pending = 1; + } +} + +static int +hotplug_hrtick(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + int cpu = (int)(long)hcpu; + + switch (action) { + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + case CPU_DEAD: + case CPU_DEAD_FROZEN: + hrtick_clear(cpu_rq(cpu)); + return NOTIFY_OK; + } + + return NOTIFY_DONE; +} + +static __init void init_hrtick(void) +{ + hotcpu_notifier(hotplug_hrtick, 0); +} +#else +/* + * Called to set the hrtick timer state. + * + * called with rq->lock held and irqs disabled + */ +static void hrtick_start(struct rq *rq, u64 delay) +{ + hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay), HRTIMER_MODE_REL); +} + +static void init_hrtick(void) +{ +} +#endif /* CONFIG_SMP */ + +static void init_rq_hrtick(struct rq *rq) +{ +#ifdef CONFIG_SMP + rq->hrtick_csd_pending = 0; + + rq->hrtick_csd.flags = 0; + rq->hrtick_csd.func = __hrtick_start; + rq->hrtick_csd.info = rq; +#endif + + hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + rq->hrtick_timer.function = hrtick; + rq->hrtick_timer.cb_mode = HRTIMER_CB_IRQSAFE_PERCPU; +} +#else +static inline void hrtick_clear(struct rq *rq) +{ +} + +static inline void init_rq_hrtick(struct rq *rq) +{ +} + +static inline void init_hrtick(void) +{ +} +#endif + +/* + * resched_task - mark a task 'to be rescheduled now'. + * + * On UP this means the setting of the need_resched flag, on SMP it + * might also involve a cross-CPU call to trigger the scheduler on + * the target CPU. + */ +#ifdef CONFIG_SMP + +#ifndef tsk_is_polling +#define tsk_is_polling(t) test_tsk_thread_flag(t, TIF_POLLING_NRFLAG) +#endif + +static void resched_task(struct task_struct *p) +{ + int cpu; + + assert_spin_locked(&task_rq(p)->lock); + + if (unlikely(test_tsk_thread_flag(p, TIF_NEED_RESCHED))) + return; + + set_tsk_thread_flag(p, TIF_NEED_RESCHED); + + cpu = task_cpu(p); + if (cpu == smp_processor_id()) + return; + + /* NEED_RESCHED must be visible before we test polling */ + smp_mb(); + if (!tsk_is_polling(p)) + smp_send_reschedule(cpu); +} + +static void resched_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + if (!spin_trylock_irqsave(&rq->lock, flags)) + return; + resched_task(cpu_curr(cpu)); + spin_unlock_irqrestore(&rq->lock, flags); +} + +#ifdef CONFIG_NO_HZ +/* + * When add_timer_on() enqueues a timer into the timer wheel of an + * idle CPU then this timer might expire before the next timer event + * which is scheduled to wake up that CPU. In case of a completely + * idle system the next event might even be infinite time into the + * future. wake_up_idle_cpu() ensures that the CPU is woken up and + * leaves the inner idle loop so the newly added timer is taken into + * account when the CPU goes back to idle and evaluates the timer + * wheel for the next timer event. + */ +void wake_up_idle_cpu(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (cpu == smp_processor_id()) + return; + + /* + * This is safe, as this function is called with the timer + * wheel base lock of (cpu) held. When the CPU is on the way + * to idle and has not yet set rq->curr to idle then it will + * be serialized on the timer wheel base lock and take the new + * timer into account automatically. + */ + if (rq->curr != rq->idle) + return; + + /* + * We can set TIF_RESCHED on the idle task of the other CPU + * lockless. The worst case is that the other CPU runs the + * idle task through an additional NOOP schedule() + */ + set_tsk_thread_flag(rq->idle, TIF_NEED_RESCHED); + + /* NEED_RESCHED must be visible before we test polling */ + smp_mb(); + if (!tsk_is_polling(rq->idle)) + smp_send_reschedule(cpu); +} +#endif /* CONFIG_NO_HZ */ + +#else /* !CONFIG_SMP */ +static void resched_task(struct task_struct *p) +{ + assert_spin_locked(&task_rq(p)->lock); + set_tsk_need_resched(p); +} +#endif /* CONFIG_SMP */ + +#if BITS_PER_LONG == 32 +# define WMULT_CONST (~0UL) +#else +# define WMULT_CONST (1UL << 32) +#endif + +#define WMULT_SHIFT 32 + +/* + * Shift right and round: + */ +#define SRR(x, y) (((x) + (1UL << ((y) - 1))) >> (y)) + +/* + * delta *= weight / lw + */ +static unsigned long +calc_delta_mine(unsigned long delta_exec, unsigned long weight, + struct load_weight *lw) +{ + u64 tmp; + + if (!lw->inv_weight) { + if (BITS_PER_LONG > 32 && unlikely(lw->weight >= WMULT_CONST)) + lw->inv_weight = 1; + else + lw->inv_weight = 1 + (WMULT_CONST-lw->weight/2) + / (lw->weight+1); + } + + tmp = (u64)delta_exec * weight; + /* + * Check whether we'd overflow the 64-bit multiplication: + */ + if (unlikely(tmp > WMULT_CONST)) + tmp = SRR(SRR(tmp, WMULT_SHIFT/2) * lw->inv_weight, + WMULT_SHIFT/2); + else + tmp = SRR(tmp * lw->inv_weight, WMULT_SHIFT); + + return (unsigned long)min(tmp, (u64)(unsigned long)LONG_MAX); +} + +static inline void update_load_add(struct load_weight *lw, unsigned long inc) +{ + lw->weight += inc; + lw->inv_weight = 0; +} + +static inline void update_load_sub(struct load_weight *lw, unsigned long dec) +{ + lw->weight -= dec; + lw->inv_weight = 0; +} + +/* + * To aid in avoiding the subversion of "niceness" due to uneven distribution + * of tasks with abnormal "nice" values across CPUs the contribution that + * each task makes to its run queue's load is weighted according to its + * scheduling class and "nice" value. For SCHED_NORMAL tasks this is just a + * scaled version of the new time slice allocation that they receive on time + * slice expiry etc. + */ + +#define WEIGHT_IDLEPRIO 2 +#define WMULT_IDLEPRIO (1 << 31) + +/* + * Nice levels are multiplicative, with a gentle 10% change for every + * nice level changed. I.e. when a CPU-bound task goes from nice 0 to + * nice 1, it will get ~10% less CPU time than another CPU-bound task + * that remained on nice 0. + * + * The "10% effect" is relative and cumulative: from _any_ nice level, + * if you go up 1 level, it's -10% CPU usage, if you go down 1 level + * it's +10% CPU usage. (to achieve that we use a multiplier of 1.25. + * If a task goes up by ~10% and another task goes down by ~10% then + * the relative distance between them is ~25%.) + */ +static const int prio_to_weight[40] = { + /* -20 */ 88761, 71755, 56483, 46273, 36291, + /* -15 */ 29154, 23254, 18705, 14949, 11916, + /* -10 */ 9548, 7620, 6100, 4904, 3906, + /* -5 */ 3121, 2501, 1991, 1586, 1277, + /* 0 */ 1024, 820, 655, 526, 423, + /* 5 */ 335, 272, 215, 172, 137, + /* 10 */ 110, 87, 70, 56, 45, + /* 15 */ 36, 29, 23, 18, 15, +}; + +/* + * Inverse (2^32/x) values of the prio_to_weight[] array, precalculated. + * + * In cases where the weight does not change often, we can use the + * precalculated inverse to speed up arithmetics by turning divisions + * into multiplications: + */ +static const u32 prio_to_wmult[40] = { + /* -20 */ 48388, 59856, 76040, 92818, 118348, + /* -15 */ 147320, 184698, 229616, 287308, 360437, + /* -10 */ 449829, 563644, 704093, 875809, 1099582, + /* -5 */ 1376151, 1717300, 2157191, 2708050, 3363326, + /* 0 */ 4194304, 5237765, 6557202, 8165337, 10153587, + /* 5 */ 12820798, 15790321, 19976592, 24970740, 31350126, + /* 10 */ 39045157, 49367440, 61356676, 76695844, 95443717, + /* 15 */ 119304647, 148102320, 186737708, 238609294, 286331153, +}; + +static void activate_task(struct rq *rq, struct task_struct *p, int wakeup); + +/* + * runqueue iterator, to support SMP load-balancing between different + * scheduling classes, without having to expose their internal data + * structures to the load-balancing proper: + */ +struct rq_iterator { + void *arg; + struct task_struct *(*start)(void *); + struct task_struct *(*next)(void *); +}; + +#ifdef CONFIG_SMP +static unsigned long +balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, struct sched_domain *sd, + enum cpu_idle_type idle, int *all_pinned, + int *this_best_prio, struct rq_iterator *iterator); + +static int +iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, + struct sched_domain *sd, enum cpu_idle_type idle, + struct rq_iterator *iterator); +#endif + +#ifdef CONFIG_CGROUP_CPUACCT +static void cpuacct_charge(struct task_struct *tsk, u64 cputime); +#else +static inline void cpuacct_charge(struct task_struct *tsk, u64 cputime) {} +#endif + +static inline void inc_cpu_load(struct rq *rq, unsigned long load) +{ + update_load_add(&rq->load, load); +} + +static inline void dec_cpu_load(struct rq *rq, unsigned long load) +{ + update_load_sub(&rq->load, load); +} + +#ifdef CONFIG_SMP +static unsigned long source_load(int cpu, int type); +static unsigned long target_load(int cpu, int type); +static int task_hot(struct task_struct *p, u64 now, struct sched_domain *sd); + +static unsigned long cpu_avg_load_per_task(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + + if (rq->nr_running) + rq->avg_load_per_task = rq->load.weight / rq->nr_running; + + return rq->avg_load_per_task; +} + +#ifdef CONFIG_FAIR_GROUP_SCHED + +typedef void (*tg_visitor)(struct task_group *, int, struct sched_domain *); + +/* + * Iterate the full tree, calling @down when first entering a node and @up when + * leaving it for the final time. + */ +static void +walk_tg_tree(tg_visitor down, tg_visitor up, int cpu, struct sched_domain *sd) +{ + struct task_group *parent, *child; + + rcu_read_lock(); + parent = &root_task_group; +down: + (*down)(parent, cpu, sd); + list_for_each_entry_rcu(child, &parent->children, siblings) { + parent = child; + goto down; + +up: + continue; + } + (*up)(parent, cpu, sd); + + child = parent; + parent = parent->parent; + if (parent) + goto up; + rcu_read_unlock(); +} + +static void __set_se_shares(struct sched_entity *se, unsigned long shares); + +/* + * Calculate and set the cpu's group shares. + */ +static void +__update_group_shares_cpu(struct task_group *tg, int cpu, + unsigned long sd_shares, unsigned long sd_rq_weight) +{ + int boost = 0; + unsigned long shares; + unsigned long rq_weight; + + if (!tg->se[cpu]) + return; + + rq_weight = tg->cfs_rq[cpu]->load.weight; + + /* + * If there are currently no tasks on the cpu pretend there is one of + * average load so that when a new task gets to run here it will not + * get delayed by group starvation. + */ + if (!rq_weight) { + boost = 1; + rq_weight = NICE_0_LOAD; + } + + if (unlikely(rq_weight > sd_rq_weight)) + rq_weight = sd_rq_weight; + + /* + * \Sum shares * rq_weight + * shares = ----------------------- + * \Sum rq_weight + * + */ + shares = (sd_shares * rq_weight) / (sd_rq_weight + 1); + + /* + * record the actual number of shares, not the boosted amount. + */ + tg->cfs_rq[cpu]->shares = boost ? 0 : shares; + tg->cfs_rq[cpu]->rq_weight = rq_weight; + + if (shares < MIN_SHARES) + shares = MIN_SHARES; + else if (shares > MAX_SHARES) + shares = MAX_SHARES; + + __set_se_shares(tg->se[cpu], shares); +} + +/* + * Re-compute the task group their per cpu shares over the given domain. + * This needs to be done in a bottom-up fashion because the rq weight of a + * parent group depends on the shares of its child groups. + */ +static void +tg_shares_up(struct task_group *tg, int cpu, struct sched_domain *sd) +{ + unsigned long rq_weight = 0; + unsigned long shares = 0; + int i; + + for_each_cpu_mask(i, sd->span) { + rq_weight += tg->cfs_rq[i]->load.weight; + shares += tg->cfs_rq[i]->shares; + } + + if ((!shares && rq_weight) || shares > tg->shares) + shares = tg->shares; + + if (!sd->parent || !(sd->parent->flags & SD_LOAD_BALANCE)) + shares = tg->shares; + + if (!rq_weight) + rq_weight = cpus_weight(sd->span) * NICE_0_LOAD; + + for_each_cpu_mask(i, sd->span) { + struct rq *rq = cpu_rq(i); + unsigned long flags; + + spin_lock_irqsave(&rq->lock, flags); + __update_group_shares_cpu(tg, i, shares, rq_weight); + spin_unlock_irqrestore(&rq->lock, flags); + } +} + +/* + * Compute the cpu's hierarchical load factor for each task group. + * This needs to be done in a top-down fashion because the load of a child + * group is a fraction of its parents load. + */ +static void +tg_load_down(struct task_group *tg, int cpu, struct sched_domain *sd) +{ + unsigned long load; + + if (!tg->parent) { + load = cpu_rq(cpu)->load.weight; + } else { + load = tg->parent->cfs_rq[cpu]->h_load; + load *= tg->cfs_rq[cpu]->shares; + load /= tg->parent->cfs_rq[cpu]->load.weight + 1; + } + + tg->cfs_rq[cpu]->h_load = load; +} + +static void +tg_nop(struct task_group *tg, int cpu, struct sched_domain *sd) +{ +} + +static void update_shares(struct sched_domain *sd) +{ + u64 now = cpu_clock(raw_smp_processor_id()); + s64 elapsed = now - sd->last_update; + + if (elapsed >= (s64)(u64)sysctl_sched_shares_ratelimit) { + sd->last_update = now; + walk_tg_tree(tg_nop, tg_shares_up, 0, sd); + } +} + +static void update_shares_locked(struct rq *rq, struct sched_domain *sd) +{ + spin_unlock(&rq->lock); + update_shares(sd); + spin_lock(&rq->lock); +} + +static void update_h_load(int cpu) +{ + walk_tg_tree(tg_load_down, tg_nop, cpu, NULL); +} + +#else + +static inline void update_shares(struct sched_domain *sd) +{ +} + +static inline void update_shares_locked(struct rq *rq, struct sched_domain *sd) +{ +} + +#endif + +#endif + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void cfs_rq_set_shares(struct cfs_rq *cfs_rq, unsigned long shares) +{ +#ifdef CONFIG_SMP + cfs_rq->shares = shares; +#endif +} +#endif + +#include "sched_stats.h" +#include "sched_idletask.c" +#include "sched_fair.c" +#include "sched_rt.c" +#ifdef CONFIG_SCHED_DEBUG +# include "sched_debug.c" +#endif + +#define sched_class_highest (&rt_sched_class) +#define for_each_class(class) \ + for (class = sched_class_highest; class; class = class->next) + +static void inc_nr_running(struct rq *rq) +{ + rq->nr_running++; +} + +static void dec_nr_running(struct rq *rq) +{ + rq->nr_running--; +} + +static void set_load_weight(struct task_struct *p) +{ + if (task_has_rt_policy(p)) { + p->se.load.weight = prio_to_weight[0] * 2; + p->se.load.inv_weight = prio_to_wmult[0] >> 1; + return; + } + + /* + * SCHED_IDLE tasks get minimal weight: + */ + if (p->policy == SCHED_IDLE) { + p->se.load.weight = WEIGHT_IDLEPRIO; + p->se.load.inv_weight = WMULT_IDLEPRIO; + return; + } + + p->se.load.weight = prio_to_weight[p->static_prio - MAX_RT_PRIO]; + p->se.load.inv_weight = prio_to_wmult[p->static_prio - MAX_RT_PRIO]; +} + +static void update_avg(u64 *avg, u64 sample) +{ + s64 diff = sample - *avg; + *avg += diff >> 3; +} + +static void enqueue_task(struct rq *rq, struct task_struct *p, int wakeup) +{ + // BUG_ON(p->state & TASK_ONHOLD); + sched_info_queued(p); + p->sched_class->enqueue_task(rq, p, wakeup); + p->se.on_rq = 1; +} + +static void dequeue_task(struct rq *rq, struct task_struct *p, int sleep) +{ + if (sleep && p->se.last_wakeup) { + update_avg(&p->se.avg_overlap, + p->se.sum_exec_runtime - p->se.last_wakeup); + p->se.last_wakeup = 0; + } + + sched_info_dequeued(p); + p->sched_class->dequeue_task(rq, p, sleep); + p->se.on_rq = 0; +} + +/* + * __normal_prio - return the priority that is based on the static prio + */ +static inline int __normal_prio(struct task_struct *p) +{ + return p->static_prio; +} + +/* + * Calculate the expected normal priority: i.e. priority + * without taking RT-inheritance into account. Might be + * boosted by interactivity modifiers. Changes upon fork, + * setprio syscalls, and whenever the interactivity + * estimator recalculates. + */ +static inline int normal_prio(struct task_struct *p) +{ + int prio; + + if (task_has_rt_policy(p)) + prio = MAX_RT_PRIO-1 - p->rt_priority; + else + prio = __normal_prio(p); + return prio; +} + +/* + * Calculate the current priority, i.e. the priority + * taken into account by the scheduler. This value might + * be boosted by RT tasks, or might be boosted by + * interactivity modifiers. Will be RT if the task got + * RT-boosted. If not then it returns p->normal_prio. + */ +static int effective_prio(struct task_struct *p) +{ + p->normal_prio = normal_prio(p); + /* + * If we are RT tasks or we were boosted to RT priority, + * keep the priority unchanged. Otherwise, update priority + * to the normal priority: + */ + if (!rt_prio(p->prio)) + return p->normal_prio; + return p->prio; +} + +/* + * activate_task - move a task to the runqueue. + */ +static void activate_task(struct rq *rq, struct task_struct *p, int wakeup) +{ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible--; + + enqueue_task(rq, p, wakeup); + inc_nr_running(rq); +} + +/* + * deactivate_task - remove a task from the runqueue. + */ +static void deactivate_task(struct rq *rq, struct task_struct *p, int sleep) +{ + if (task_contributes_to_load(p)) + rq->nr_uninterruptible++; + + dequeue_task(rq, p, sleep); + dec_nr_running(rq); +} + +/** + * task_curr - is this task currently executing on a CPU? + * @p: the task in question. + */ +inline int task_curr(const struct task_struct *p) +{ + return cpu_curr(task_cpu(p)) == p; +} + +static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu) +{ + set_task_rq(p, cpu); +#ifdef CONFIG_SMP + /* + * After ->cpu is set up to a new value, task_rq_lock(p, ...) can be + * successfuly executed on another CPU. We must ensure that updates of + * per-task data have been completed by this moment. + */ + smp_wmb(); + task_thread_info(p)->cpu = cpu; +#endif +} + +static inline void check_class_changed(struct rq *rq, struct task_struct *p, + const struct sched_class *prev_class, + int oldprio, int running) +{ + if (prev_class != p->sched_class) { + if (prev_class->switched_from) + prev_class->switched_from(rq, p, running); + p->sched_class->switched_to(rq, p, running); + } else + p->sched_class->prio_changed(rq, p, oldprio, running); +} + +#ifdef CONFIG_SMP + +/* Used instead of source_load when we know the type == 0 */ +static unsigned long weighted_cpuload(const int cpu) +{ + return cpu_rq(cpu)->load.weight; +} + +/* + * Is this task likely cache-hot: + */ +static int +task_hot(struct task_struct *p, u64 now, struct sched_domain *sd) +{ + s64 delta; + + /* + * Buddy candidates are cache hot: + */ + if (sched_feat(CACHE_HOT_BUDDY) && (&p->se == cfs_rq_of(&p->se)->next)) + return 1; + + if (p->sched_class != &fair_sched_class) + return 0; + + if (sysctl_sched_migration_cost == -1) + return 1; + if (sysctl_sched_migration_cost == 0) + return 0; + + delta = now - p->se.exec_start; + + return delta < (s64)sysctl_sched_migration_cost; +} + + +void set_task_cpu(struct task_struct *p, unsigned int new_cpu) +{ + int old_cpu = task_cpu(p); + struct rq *old_rq = cpu_rq(old_cpu), *new_rq = cpu_rq(new_cpu); + struct cfs_rq *old_cfsrq = task_cfs_rq(p), + *new_cfsrq = cpu_cfs_rq(old_cfsrq, new_cpu); + u64 clock_offset; + + clock_offset = old_rq->clock - new_rq->clock; + +#ifdef CONFIG_SCHEDSTATS + if (p->se.wait_start) + p->se.wait_start -= clock_offset; + if (p->se.sleep_start) + p->se.sleep_start -= clock_offset; + if (p->se.block_start) + p->se.block_start -= clock_offset; + if (old_cpu != new_cpu) { + schedstat_inc(p, se.nr_migrations); + if (task_hot(p, old_rq->clock, NULL)) + schedstat_inc(p, se.nr_forced2_migrations); + } +#endif + p->se.vruntime -= old_cfsrq->min_vruntime - + new_cfsrq->min_vruntime; + + __set_task_cpu(p, new_cpu); +} + +struct migration_req { + struct list_head list; + + struct task_struct *task; + int dest_cpu; + + struct completion done; +}; + +#include "sched_mon.h" + + +/* + * The task's runqueue lock must be held. + * Returns true if you have to wait for migration thread. + */ +static int +migrate_task(struct task_struct *p, int dest_cpu, struct migration_req *req) +{ + struct rq *rq = task_rq(p); + + vxm_migrate_task(p, rq, dest_cpu); + /* + * If the task is not on a runqueue (and not running), then + * it is sufficient to simply update the task's cpu field. + */ + if (!p->se.on_rq && !task_running(rq, p)) { + set_task_cpu(p, dest_cpu); + return 0; + } + + init_completion(&req->done); + req->task = p; + req->dest_cpu = dest_cpu; + list_add(&req->list, &rq->migration_queue); + + return 1; +} + +/* + * wait_task_inactive - wait for a thread to unschedule. + * + * If @match_state is nonzero, it's the @p->state value just checked and + * not expected to change. If it changes, i.e. @p might have woken up, + * then return zero. When we succeed in waiting for @p to be off its CPU, + * we return a positive number (its total switch count). If a second call + * a short while later returns the same number, the caller can be sure that + * @p has remained unscheduled the whole time. + * + * The caller must ensure that the task *will* unschedule sometime soon, + * else this function might spin for a *long* time. This function can't + * be called with interrupts off, or it may introduce deadlock with + * smp_call_function() if an IPI is sent by the same process we are + * waiting to become inactive. + */ +unsigned long wait_task_inactive(struct task_struct *p, long match_state) +{ + unsigned long flags; + int running, on_rq; + unsigned long ncsw; + struct rq *rq; + + for (;;) { + /* + * We do the initial early heuristics without holding + * any task-queue locks at all. We'll only try to get + * the runqueue lock when things look like they will + * work out! + */ + rq = task_rq(p); + + /* + * If the task is actively running on another CPU + * still, just relax and busy-wait without holding + * any locks. + * + * NOTE! Since we don't hold any locks, it's not + * even sure that "rq" stays as the right runqueue! + * But we don't care, since "task_running()" will + * return false if the runqueue has changed and p + * is actually now running somewhere else! + */ + while (task_running(rq, p)) { + if (match_state && unlikely(p->state != match_state)) + return 0; + cpu_relax(); + } + + /* + * Ok, time to look more closely! We need the rq + * lock now, to be *sure*. If we're wrong, we'll + * just go back and repeat. + */ + rq = task_rq_lock(p, &flags); + running = task_running(rq, p); + on_rq = p->se.on_rq; + ncsw = 0; + if (!match_state || p->state == match_state) { + ncsw = p->nivcsw + p->nvcsw; + if (unlikely(!ncsw)) + ncsw = 1; + } + task_rq_unlock(rq, &flags); + + /* + * If it changed from the expected state, bail out now. + */ + if (unlikely(!ncsw)) + break; + + /* + * Was it really running after all now that we + * checked with the proper locks actually held? + * + * Oops. Go back and try again.. + */ + if (unlikely(running)) { + cpu_relax(); + continue; + } + + /* + * It's not enough that it's not actively running, + * it must be off the runqueue _entirely_, and not + * preempted! + * + * So if it wa still runnable (but just not actively + * running right now), it's preempted, and we should + * yield - it could be a while. + */ + if (unlikely(on_rq)) { + schedule_timeout_uninterruptible(1); + continue; + } + + /* + * Ahh, all good. It wasn't running, and it wasn't + * runnable, which means that it will never become + * running in the future either. We're all done! + */ + break; + } + + return ncsw; +} + +/*** + * kick_process - kick a running thread to enter/exit the kernel + * @p: the to-be-kicked thread + * + * Cause a process which is running on another CPU to enter + * kernel-mode, without any delay. (to get signals handled.) + * + * NOTE: this function doesnt have to take the runqueue lock, + * because all it wants to ensure is that the remote task enters + * the kernel. If the IPI races and the task has been migrated + * to another CPU then no harm is done and the purpose has been + * achieved as well. + */ +void kick_process(struct task_struct *p) +{ + int cpu; + + preempt_disable(); + cpu = task_cpu(p); + if ((cpu != smp_processor_id()) && task_curr(p)) + smp_send_reschedule(cpu); + preempt_enable(); +} + +/* + * Return a low guess at the load of a migration-source cpu weighted + * according to the scheduling class and "nice" value. + * + * We want to under-estimate the load of migration sources, to + * balance conservatively. + */ +static unsigned long source_load(int cpu, int type) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long total = weighted_cpuload(cpu); + + if (type == 0 || !sched_feat(LB_BIAS)) + return total; + + return min(rq->cpu_load[type-1], total); +} + +/* + * Return a high guess at the load of a migration-target cpu weighted + * according to the scheduling class and "nice" value. + */ +static unsigned long target_load(int cpu, int type) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long total = weighted_cpuload(cpu); + + if (type == 0 || !sched_feat(LB_BIAS)) + return total; + + return max(rq->cpu_load[type-1], total); +} + +/* + * find_idlest_group finds and returns the least busy CPU group within the + * domain. + */ +static struct sched_group * +find_idlest_group(struct sched_domain *sd, struct task_struct *p, int this_cpu) +{ + struct sched_group *idlest = NULL, *this = NULL, *group = sd->groups; + unsigned long min_load = ULONG_MAX, this_load = 0; + int load_idx = sd->forkexec_idx; + int imbalance = 100 + (sd->imbalance_pct-100)/2; + + do { + unsigned long load, avg_load; + int local_group; + int i; + + /* Skip over this group if it has no CPUs allowed */ + if (!cpus_intersects(group->cpumask, p->cpus_allowed)) + continue; + + local_group = cpu_isset(this_cpu, group->cpumask); + + /* Tally up the load of all CPUs in the group */ + avg_load = 0; + + for_each_cpu_mask_nr(i, group->cpumask) { + /* Bias balancing toward cpus of our domain */ + if (local_group) + load = source_load(i, load_idx); + else + load = target_load(i, load_idx); + + avg_load += load; + } + + /* Adjust by relative CPU power of the group */ + avg_load = sg_div_cpu_power(group, + avg_load * SCHED_LOAD_SCALE); + + if (local_group) { + this_load = avg_load; + this = group; + } else if (avg_load < min_load) { + min_load = avg_load; + idlest = group; + } + } while (group = group->next, group != sd->groups); + + if (!idlest || 100*this_load < imbalance*min_load) + return NULL; + return idlest; +} + +/* + * find_idlest_cpu - find the idlest cpu among the cpus in group. + */ +static int +find_idlest_cpu(struct sched_group *group, struct task_struct *p, int this_cpu, + cpumask_t *tmp) +{ + unsigned long load, min_load = ULONG_MAX; + int idlest = -1; + int i; + + /* Traverse only the allowed CPUs */ + cpus_and(*tmp, group->cpumask, p->cpus_allowed); + + for_each_cpu_mask_nr(i, *tmp) { + load = weighted_cpuload(i); + + if (load < min_load || (load == min_load && i == this_cpu)) { + min_load = load; + idlest = i; + } + } + + return idlest; +} + +/* + * sched_balance_self: balance the current task (running on cpu) in domains + * that have the 'flag' flag set. In practice, this is SD_BALANCE_FORK and + * SD_BALANCE_EXEC. + * + * Balance, ie. select the least loaded group. + * + * Returns the target CPU number, or the same CPU if no balancing is needed. + * + * preempt must be disabled. + */ +static int sched_balance_self(int cpu, int flag) +{ + struct task_struct *t = current; + struct sched_domain *tmp, *sd = NULL; + + for_each_domain(cpu, tmp) { + /* + * If power savings logic is enabled for a domain, stop there. + */ + if (tmp->flags & SD_POWERSAVINGS_BALANCE) + break; + if (tmp->flags & flag) + sd = tmp; + } + + if (sd) + update_shares(sd); + + while (sd) { + cpumask_t span, tmpmask; + struct sched_group *group; + int new_cpu, weight; + + if (!(sd->flags & flag)) { + sd = sd->child; + continue; + } + + span = sd->span; + group = find_idlest_group(sd, t, cpu); + if (!group) { + sd = sd->child; + continue; + } + + new_cpu = find_idlest_cpu(group, t, cpu, &tmpmask); + if (new_cpu == -1 || new_cpu == cpu) { + /* Now try balancing at a lower domain level of cpu */ + sd = sd->child; + continue; + } + + /* Now try balancing at a lower domain level of new_cpu */ + cpu = new_cpu; + sd = NULL; + weight = cpus_weight(span); + for_each_domain(cpu, tmp) { + if (weight <= cpus_weight(tmp->span)) + break; + if (tmp->flags & flag) + sd = tmp; + } + /* while loop will break here if sd == NULL */ + } + + return cpu; +} + +#endif /* CONFIG_SMP */ + +/*** + * try_to_wake_up - wake up a thread + * @p: the to-be-woken-up thread + * @state: the mask of task states that can be woken + * @sync: do a synchronous wakeup? + * + * Put it on the run-queue if it's not already there. The "current" + * thread is always on the run-queue (except when the actual + * re-schedule is in progress), and as such you're allowed to do + * the simpler "current->state = TASK_RUNNING" to mark yourself + * runnable without the overhead of this. + * + * returns failure only if the task is already active. + */ +static int try_to_wake_up(struct task_struct *p, unsigned int state, int sync) +{ + int cpu, orig_cpu, this_cpu, success = 0; + unsigned long flags; + long old_state; + struct rq *rq; + + if (!sched_feat(SYNC_WAKEUPS)) + sync = 0; + +#ifdef CONFIG_SMP + if (sched_feat(LB_WAKEUP_UPDATE)) { + struct sched_domain *sd; + + this_cpu = raw_smp_processor_id(); + cpu = task_cpu(p); + + for_each_domain(this_cpu, sd) { + if (cpu_isset(cpu, sd->span)) { + update_shares(sd); + break; + } + } + } +#endif + + smp_wmb(); + rq = task_rq_lock(p, &flags); + old_state = p->state; + if (!(old_state & state)) + goto out; + + if (p->se.on_rq) + goto out_running; + + cpu = task_cpu(p); + orig_cpu = cpu; + this_cpu = smp_processor_id(); + +#ifdef CONFIG_SMP + if (unlikely(task_running(rq, p))) + goto out_activate; + + cpu = p->sched_class->select_task_rq(p, sync); + if (cpu != orig_cpu) { + set_task_cpu(p, cpu); + task_rq_unlock(rq, &flags); + /* might preempt at this point */ + rq = task_rq_lock(p, &flags); + old_state = p->state; + + /* we need to unhold suspended tasks + if (old_state & TASK_ONHOLD) { + vx_unhold_task(p, rq); + old_state = p->state; + } */ + if (!(old_state & state)) + goto out; + if (p->se.on_rq) + goto out_running; + + this_cpu = smp_processor_id(); + cpu = task_cpu(p); + } + +#ifdef CONFIG_SCHEDSTATS + schedstat_inc(rq, ttwu_count); + if (cpu == this_cpu) + schedstat_inc(rq, ttwu_local); + else { + struct sched_domain *sd; + for_each_domain(this_cpu, sd) { + if (cpu_isset(cpu, sd->span)) { + schedstat_inc(sd, ttwu_wake_remote); + break; + } + } + } +#endif /* CONFIG_SCHEDSTATS */ + +out_activate: +#endif /* CONFIG_SMP */ + schedstat_inc(p, se.nr_wakeups); + if (sync) + schedstat_inc(p, se.nr_wakeups_sync); + if (orig_cpu != cpu) + schedstat_inc(p, se.nr_wakeups_migrate); + if (cpu == this_cpu) + schedstat_inc(p, se.nr_wakeups_local); + else + schedstat_inc(p, se.nr_wakeups_remote); + update_rq_clock(rq); + activate_task(rq, p, 1); + success = 1; + +out_running: + trace_mark(kernel_sched_wakeup, + "pid %d state %ld ## rq %p task %p rq->curr %p", + p->pid, p->state, rq, p, rq->curr); + check_preempt_curr(rq, p); + + p->state = TASK_RUNNING; +#ifdef CONFIG_SMP + if (p->sched_class->task_wake_up) + p->sched_class->task_wake_up(rq, p); +#endif +out: + current->se.last_wakeup = current->se.sum_exec_runtime; + + task_rq_unlock(rq, &flags); + + return success; +} + +int wake_up_process(struct task_struct *p) +{ + return try_to_wake_up(p, TASK_ALL, 0); +} +EXPORT_SYMBOL(wake_up_process); + +int wake_up_state(struct task_struct *p, unsigned int state) +{ + return try_to_wake_up(p, state, 0); +} + +/* + * Perform scheduler related setup for a newly forked process p. + * p is forked by current. + * + * __sched_fork() is basic setup used by init_idle() too: + */ +static void __sched_fork(struct task_struct *p) +{ + p->se.exec_start = 0; + p->se.sum_exec_runtime = 0; + p->se.prev_sum_exec_runtime = 0; + p->se.last_wakeup = 0; + p->se.avg_overlap = 0; + +#ifdef CONFIG_SCHEDSTATS + p->se.wait_start = 0; + p->se.sum_sleep_runtime = 0; + p->se.sleep_start = 0; + p->se.block_start = 0; + p->se.sleep_max = 0; + p->se.block_max = 0; + p->se.exec_max = 0; + p->se.slice_max = 0; + p->se.wait_max = 0; +#endif + + INIT_LIST_HEAD(&p->rt.run_list); + p->se.on_rq = 0; + INIT_LIST_HEAD(&p->se.group_node); + +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&p->preempt_notifiers); +#endif + + /* + * We mark the process as running here, but have not actually + * inserted it onto the runqueue yet. This guarantees that + * nobody will actually run it, and a signal or other external + * event cannot wake it up and insert it on the runqueue either. + */ + p->state = TASK_RUNNING; +} + +/* + * fork()/clone()-time setup: + */ +void sched_fork(struct task_struct *p, int clone_flags) +{ + int cpu = get_cpu(); + + __sched_fork(p); + +#ifdef CONFIG_SMP + cpu = sched_balance_self(cpu, SD_BALANCE_FORK); +#endif + set_task_cpu(p, cpu); + + /* + * Make sure we do not leak PI boosting priority to the child: + */ + p->prio = current->normal_prio; + if (!rt_prio(p->prio)) + p->sched_class = &fair_sched_class; + +#if defined(CONFIG_SCHEDSTATS) || defined(CONFIG_TASK_DELAY_ACCT) + if (likely(sched_info_on())) + memset(&p->sched_info, 0, sizeof(p->sched_info)); +#endif +#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) + p->oncpu = 0; +#endif +#ifdef CONFIG_PREEMPT + /* Want to start with kernel preemption disabled. */ + task_thread_info(p)->preempt_count = 1; +#endif + put_cpu(); +} + +/* + * wake_up_new_task - wake up a newly created task for the first time. + * + * This function will do some initial scheduler statistics housekeeping + * that must be done for every newly created context, then puts the task + * on the runqueue and wakes it. + */ +void wake_up_new_task(struct task_struct *p, unsigned long clone_flags) +{ + unsigned long flags; + struct rq *rq; + + rq = task_rq_lock(p, &flags); + BUG_ON(p->state != TASK_RUNNING); + update_rq_clock(rq); + + p->prio = effective_prio(p); + + if (!p->sched_class->task_new || !current->se.on_rq) { + activate_task(rq, p, 0); + } else { + /* + * Let the scheduling class do new task startup + * management (if any): + */ + p->sched_class->task_new(rq, p); + inc_nr_running(rq); + } + trace_mark(kernel_sched_wakeup_new, + "pid %d state %ld ## rq %p task %p rq->curr %p", + p->pid, p->state, rq, p, rq->curr); + check_preempt_curr(rq, p); +#ifdef CONFIG_SMP + if (p->sched_class->task_wake_up) + p->sched_class->task_wake_up(rq, p); +#endif + task_rq_unlock(rq, &flags); +} + +#ifdef CONFIG_PREEMPT_NOTIFIERS + +/** + * preempt_notifier_register - tell me when current is being being preempted & rescheduled + * @notifier: notifier struct to register + */ +void preempt_notifier_register(struct preempt_notifier *notifier) +{ + hlist_add_head(¬ifier->link, ¤t->preempt_notifiers); +} +EXPORT_SYMBOL_GPL(preempt_notifier_register); + +/** + * preempt_notifier_unregister - no longer interested in preemption notifications + * @notifier: notifier struct to unregister + * + * This is safe to call from within a preemption notifier. + */ +void preempt_notifier_unregister(struct preempt_notifier *notifier) +{ + hlist_del(¬ifier->link); +} +EXPORT_SYMBOL_GPL(preempt_notifier_unregister); + +static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ + struct preempt_notifier *notifier; + struct hlist_node *node; + + hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) + notifier->ops->sched_in(notifier, raw_smp_processor_id()); +} + +static void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ + struct preempt_notifier *notifier; + struct hlist_node *node; + + hlist_for_each_entry(notifier, node, &curr->preempt_notifiers, link) + notifier->ops->sched_out(notifier, next); +} + +#else /* !CONFIG_PREEMPT_NOTIFIERS */ + +static void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ +} + +static void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ +} + +#endif /* CONFIG_PREEMPT_NOTIFIERS */ + +/** + * prepare_task_switch - prepare to switch tasks + * @rq: the runqueue preparing to switch + * @prev: the current task that is being switched out + * @next: the task we are going to switch to. + * + * This is called with the rq lock held and interrupts off. It must + * be paired with a subsequent finish_task_switch after the context + * switch. + * + * prepare_task_switch sets up locking and calls architecture specific + * hooks. + */ +static inline void +prepare_task_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + fire_sched_out_preempt_notifiers(prev, next); + prepare_lock_switch(rq, next); + prepare_arch_switch(next); +} + +/** + * finish_task_switch - clean up after a task-switch + * @rq: runqueue associated with task-switch + * @prev: the thread we just switched away from. + * + * finish_task_switch must be called after the context switch, paired + * with a prepare_task_switch call before the context switch. + * finish_task_switch will reconcile locking set up by prepare_task_switch, + * and do any other architecture-specific cleanup actions. + * + * Note that we may have delayed dropping an mm in context_switch(). If + * so, we finish that here outside of the runqueue lock. (Doing it + * with the lock held can cause deadlocks; see schedule() for + * details.) + */ +static void finish_task_switch(struct rq *rq, struct task_struct *prev) + __releases(rq->lock) +{ + struct mm_struct *mm = rq->prev_mm; + long prev_state; + + rq->prev_mm = NULL; + + /* + * A task struct has one reference for the use as "current". + * If a task dies, then it sets TASK_DEAD in tsk->state and calls + * schedule one last time. The schedule call will never return, and + * the scheduled task must drop that reference. + * The test for TASK_DEAD must occur while the runqueue locks are + * still held, otherwise prev could be scheduled on another cpu, die + * there before we look at prev->state, and then the reference would + * be dropped twice. + * Manfred Spraul + */ + prev_state = prev->state; + finish_arch_switch(prev); + finish_lock_switch(rq, prev); +#ifdef CONFIG_SMP + if (current->sched_class->post_schedule) + current->sched_class->post_schedule(rq); +#endif + + fire_sched_in_preempt_notifiers(current); + if (mm) + mmdrop(mm); + if (unlikely(prev_state == TASK_DEAD)) { + /* + * Remove function-return probe instances associated with this + * task and put them back on the free list. + */ + kprobe_flush_task(prev); + put_task_struct(prev); + } +} + +/** + * schedule_tail - first thing a freshly forked thread must call. + * @prev: the thread we just switched away from. + */ +asmlinkage void schedule_tail(struct task_struct *prev) + __releases(rq->lock) +{ + struct rq *rq = this_rq(); + + finish_task_switch(rq, prev); +#ifdef __ARCH_WANT_UNLOCKED_CTXSW + /* In this case, finish_task_switch does not reenable preemption */ + preempt_enable(); +#endif + if (current->set_child_tid) + put_user(task_pid_vnr(current), current->set_child_tid); +} + +/* + * context_switch - switch to the new MM and the new + * thread's register state. + */ +static inline void +context_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + struct mm_struct *mm, *oldmm; + + prepare_task_switch(rq, prev, next); + trace_mark(kernel_sched_schedule, + "prev_pid %d next_pid %d prev_state %ld " + "## rq %p prev %p next %p", + prev->pid, next->pid, prev->state, + rq, prev, next); + mm = next->mm; + oldmm = prev->active_mm; + /* + * For paravirt, this is coupled with an exit in switch_to to + * combine the page table reload and the switch backend into + * one hypercall. + */ + arch_enter_lazy_cpu_mode(); + + if (unlikely(!mm)) { + next->active_mm = oldmm; + atomic_inc(&oldmm->mm_count); + enter_lazy_tlb(oldmm, next); + } else + switch_mm(oldmm, mm, next); + + if (unlikely(!prev->mm)) { + prev->active_mm = NULL; + rq->prev_mm = oldmm; + } + /* + * Since the runqueue lock will be released by the next + * task (which is an invalid locking op but in the case + * of the scheduler it's an obvious special-case), so we + * do an early lockdep release here: + */ +#ifndef __ARCH_WANT_UNLOCKED_CTXSW + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); +#endif + + /* Here we just switch the register state and the stack. */ + switch_to(prev, next, prev); + + barrier(); + /* + * this_rq must be evaluated again because prev may have moved + * CPUs since it called schedule(), thus the 'rq' on its stack + * frame will be invalid. + */ + finish_task_switch(this_rq(), prev); +} + +/* + * nr_running, nr_uninterruptible and nr_context_switches: + * + * externally visible scheduler statistics: current number of runnable + * threads, current number of uninterruptible-sleeping threads, total + * number of context switches performed since bootup. + */ +unsigned long nr_running(void) +{ + unsigned long i, sum = 0; + + for_each_online_cpu(i) + sum += cpu_rq(i)->nr_running; + + return sum; +} + +unsigned long nr_uninterruptible(void) +{ + unsigned long i, sum = 0; + + for_each_possible_cpu(i) + sum += cpu_rq(i)->nr_uninterruptible; + + /* + * Since we read the counters lockless, it might be slightly + * inaccurate. Do not allow it to go below zero though: + */ + if (unlikely((long)sum < 0)) + sum = 0; + + return sum; +} + +unsigned long long nr_context_switches(void) +{ + int i; + unsigned long long sum = 0; + + for_each_possible_cpu(i) + sum += cpu_rq(i)->nr_switches; + + return sum; +} + +unsigned long nr_iowait(void) +{ + unsigned long i, sum = 0; + + for_each_possible_cpu(i) + sum += atomic_read(&cpu_rq(i)->nr_iowait); + + return sum; +} + +unsigned long nr_active(void) +{ + unsigned long i, running = 0, uninterruptible = 0; + + for_each_online_cpu(i) { + running += cpu_rq(i)->nr_running; + uninterruptible += cpu_rq(i)->nr_uninterruptible; + } + + if (unlikely((long)uninterruptible < 0)) + uninterruptible = 0; + + return running + uninterruptible; +} + +/* + * Update rq->cpu_load[] statistics. This function is usually called every + * scheduler tick (TICK_NSEC). + */ +static void update_cpu_load(struct rq *this_rq) +{ + unsigned long this_load = this_rq->load.weight; + int i, scale; + + this_rq->nr_load_updates++; + + /* Update our load: */ + for (i = 0, scale = 1; i < CPU_LOAD_IDX_MAX; i++, scale += scale) { + unsigned long old_load, new_load; + + /* scale is effectively 1 << i now, and >> i divides by scale */ + + old_load = this_rq->cpu_load[i]; + new_load = this_load; + /* + * Round up the averaging division if load is increasing. This + * prevents us from getting stuck on 9 if the load is 10, for + * example. + */ + if (new_load > old_load) + new_load += scale-1; + this_rq->cpu_load[i] = (old_load*(scale-1) + new_load) >> i; + } +} + +#ifdef CONFIG_SMP + +/* + * double_rq_lock - safely lock two runqueues + * + * Note this does not disable interrupts like task_rq_lock, + * you need to do so manually before calling. + */ +static void double_rq_lock(struct rq *rq1, struct rq *rq2) + __acquires(rq1->lock) + __acquires(rq2->lock) +{ + BUG_ON(!irqs_disabled()); + if (rq1 == rq2) { + spin_lock(&rq1->lock); + __acquire(rq2->lock); /* Fake it out ;) */ + } else { + if (rq1 < rq2) { + spin_lock(&rq1->lock); + spin_lock_nested(&rq2->lock, SINGLE_DEPTH_NESTING); + } else { + spin_lock(&rq2->lock); + spin_lock_nested(&rq1->lock, SINGLE_DEPTH_NESTING); + } + } + update_rq_clock(rq1); + update_rq_clock(rq2); +} + +/* + * double_rq_unlock - safely unlock two runqueues + * + * Note this does not restore interrupts like task_rq_unlock, + * you need to do so manually after calling. + */ +static void double_rq_unlock(struct rq *rq1, struct rq *rq2) + __releases(rq1->lock) + __releases(rq2->lock) +{ + spin_unlock(&rq1->lock); + if (rq1 != rq2) + spin_unlock(&rq2->lock); + else + __release(rq2->lock); +} + +/* + * double_lock_balance - lock the busiest runqueue, this_rq is locked already. + */ +static int double_lock_balance(struct rq *this_rq, struct rq *busiest) + __releases(this_rq->lock) + __acquires(busiest->lock) + __acquires(this_rq->lock) +{ + int ret = 0; + + if (unlikely(!irqs_disabled())) { + /* printk() doesn't work good under rq->lock */ + spin_unlock(&this_rq->lock); + BUG_ON(1); + } + if (unlikely(!spin_trylock(&busiest->lock))) { + if (busiest < this_rq) { + spin_unlock(&this_rq->lock); + spin_lock(&busiest->lock); + spin_lock_nested(&this_rq->lock, SINGLE_DEPTH_NESTING); + ret = 1; + } else + spin_lock_nested(&busiest->lock, SINGLE_DEPTH_NESTING); + } + return ret; +} + +static void double_unlock_balance(struct rq *this_rq, struct rq *busiest) + __releases(busiest->lock) +{ + spin_unlock(&busiest->lock); + lock_set_subclass(&this_rq->lock.dep_map, 0, _RET_IP_); +} + +/* + * If dest_cpu is allowed for this process, migrate the task to it. + * This is accomplished by forcing the cpu_allowed mask to only + * allow dest_cpu, which will force the cpu onto dest_cpu. Then + * the cpu_allowed mask is restored. + */ +static void sched_migrate_task(struct task_struct *p, int dest_cpu) +{ + struct migration_req req; + unsigned long flags; + struct rq *rq; + + rq = task_rq_lock(p, &flags); + if (!cpu_isset(dest_cpu, p->cpus_allowed) + || unlikely(!cpu_active(dest_cpu))) + goto out; + + /* force the process onto the specified CPU */ + if (migrate_task(p, dest_cpu, &req)) { + /* Need to wait for migration thread (might exit: take ref). */ + struct task_struct *mt = rq->migration_thread; + + get_task_struct(mt); + task_rq_unlock(rq, &flags); + wake_up_process(mt); + put_task_struct(mt); + wait_for_completion(&req.done); + + return; + } +out: + task_rq_unlock(rq, &flags); +} + +/* + * sched_exec - execve() is a valuable balancing opportunity, because at + * this point the task has the smallest effective memory and cache footprint. + */ +void sched_exec(void) +{ + int new_cpu, this_cpu = get_cpu(); + new_cpu = sched_balance_self(this_cpu, SD_BALANCE_EXEC); + put_cpu(); + if (new_cpu != this_cpu) + sched_migrate_task(current, new_cpu); +} + +/* + * pull_task - move a task from a remote runqueue to the local runqueue. + * Both runqueues must be locked. + */ +static void pull_task(struct rq *src_rq, struct task_struct *p, + struct rq *this_rq, int this_cpu) +{ + deactivate_task(src_rq, p, 0); + set_task_cpu(p, this_cpu); + activate_task(this_rq, p, 0); + /* + * Note that idle threads have a prio of MAX_PRIO, for this test + * to be always true for them. + */ + check_preempt_curr(this_rq, p); +} + +/* + * can_migrate_task - may task p from runqueue rq be migrated to this_cpu? + */ +static +int can_migrate_task(struct task_struct *p, struct rq *rq, int this_cpu, + struct sched_domain *sd, enum cpu_idle_type idle, + int *all_pinned) +{ + /* + * We do not migrate tasks that are: + * 1) running (obviously), or + * 2) cannot be migrated to this CPU due to cpus_allowed, or + * 3) are cache-hot on their current CPU. + */ + if (!cpu_isset(this_cpu, p->cpus_allowed)) { + schedstat_inc(p, se.nr_failed_migrations_affine); + return 0; + } + *all_pinned = 0; + + if (task_running(rq, p)) { + schedstat_inc(p, se.nr_failed_migrations_running); + return 0; + } + + /* + * Aggressive migration if: + * 1) task is cache cold, or + * 2) too many balance attempts have failed. + */ + + if (!task_hot(p, rq->clock, sd) || + sd->nr_balance_failed > sd->cache_nice_tries) { +#ifdef CONFIG_SCHEDSTATS + if (task_hot(p, rq->clock, sd)) { + schedstat_inc(sd, lb_hot_gained[idle]); + schedstat_inc(p, se.nr_forced_migrations); + } +#endif + return 1; + } + + if (task_hot(p, rq->clock, sd)) { + schedstat_inc(p, se.nr_failed_migrations_hot); + return 0; + } + return 1; +} + +static unsigned long +balance_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, struct sched_domain *sd, + enum cpu_idle_type idle, int *all_pinned, + int *this_best_prio, struct rq_iterator *iterator) +{ + int loops = 0, pulled = 0, pinned = 0; + struct task_struct *p; + long rem_load_move = max_load_move; + + if (max_load_move == 0) + goto out; + + pinned = 1; + + /* + * Start the load-balancing iterator: + */ + p = iterator->start(iterator->arg); +next: + if (!p || loops++ > sysctl_sched_nr_migrate) + goto out; + + if ((p->se.load.weight >> 1) > rem_load_move || + !can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) { + p = iterator->next(iterator->arg); + goto next; + } + + pull_task(busiest, p, this_rq, this_cpu); + pulled++; + rem_load_move -= p->se.load.weight; + + /* + * We only want to steal up to the prescribed amount of weighted load. + */ + if (rem_load_move > 0) { + if (p->prio < *this_best_prio) + *this_best_prio = p->prio; + p = iterator->next(iterator->arg); + goto next; + } +out: + /* + * Right now, this is one of only two places pull_task() is called, + * so we can safely collect pull_task() stats here rather than + * inside pull_task(). + */ + schedstat_add(sd, lb_gained[idle], pulled); + + if (all_pinned) + *all_pinned = pinned; + + return max_load_move - rem_load_move; +} + +/* + * move_tasks tries to move up to max_load_move weighted load from busiest to + * this_rq, as part of a balancing operation within domain "sd". + * Returns 1 if successful and 0 otherwise. + * + * Called with both runqueues locked. + */ +static int move_tasks(struct rq *this_rq, int this_cpu, struct rq *busiest, + unsigned long max_load_move, + struct sched_domain *sd, enum cpu_idle_type idle, + int *all_pinned) +{ + const struct sched_class *class = sched_class_highest; + unsigned long total_load_moved = 0; + int this_best_prio = this_rq->curr->prio; + + do { + total_load_moved += + class->load_balance(this_rq, this_cpu, busiest, + max_load_move - total_load_moved, + sd, idle, all_pinned, &this_best_prio); + class = class->next; + + if (idle == CPU_NEWLY_IDLE && this_rq->nr_running) + break; + + } while (class && max_load_move > total_load_moved); + + return total_load_moved > 0; +} + +static int +iter_move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, + struct sched_domain *sd, enum cpu_idle_type idle, + struct rq_iterator *iterator) +{ + struct task_struct *p = iterator->start(iterator->arg); + int pinned = 0; + + while (p) { + if (can_migrate_task(p, busiest, this_cpu, sd, idle, &pinned)) { + pull_task(busiest, p, this_rq, this_cpu); + /* + * Right now, this is only the second place pull_task() + * is called, so we can safely collect pull_task() + * stats here rather than inside pull_task(). + */ + schedstat_inc(sd, lb_gained[idle]); + + return 1; + } + p = iterator->next(iterator->arg); + } + + return 0; +} + +/* + * move_one_task tries to move exactly one task from busiest to this_rq, as + * part of active balancing operations within "domain". + * Returns 1 if successful and 0 otherwise. + * + * Called with both runqueues locked. + */ +static int move_one_task(struct rq *this_rq, int this_cpu, struct rq *busiest, + struct sched_domain *sd, enum cpu_idle_type idle) +{ + const struct sched_class *class; + + for (class = sched_class_highest; class; class = class->next) + if (class->move_one_task(this_rq, this_cpu, busiest, sd, idle)) + return 1; + + return 0; +} + +/* + * find_busiest_group finds and returns the busiest CPU group within the + * domain. It calculates and returns the amount of weighted load which + * should be moved to restore balance via the imbalance parameter. + */ +static struct sched_group * +find_busiest_group(struct sched_domain *sd, int this_cpu, + unsigned long *imbalance, enum cpu_idle_type idle, + int *sd_idle, const cpumask_t *cpus, int *balance) +{ + struct sched_group *busiest = NULL, *this = NULL, *group = sd->groups; + unsigned long max_load, avg_load, total_load, this_load, total_pwr; + unsigned long max_pull; + unsigned long busiest_load_per_task, busiest_nr_running; + unsigned long this_load_per_task, this_nr_running; + int load_idx, group_imb = 0; +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) + int power_savings_balance = 1; + unsigned long leader_nr_running = 0, min_load_per_task = 0; + unsigned long min_nr_running = ULONG_MAX; + struct sched_group *group_min = NULL, *group_leader = NULL; +#endif + + max_load = this_load = total_load = total_pwr = 0; + busiest_load_per_task = busiest_nr_running = 0; + this_load_per_task = this_nr_running = 0; + + if (idle == CPU_NOT_IDLE) + load_idx = sd->busy_idx; + else if (idle == CPU_NEWLY_IDLE) + load_idx = sd->newidle_idx; + else + load_idx = sd->idle_idx; + + do { + unsigned long load, group_capacity, max_cpu_load, min_cpu_load; + int local_group; + int i; + int __group_imb = 0; + unsigned int balance_cpu = -1, first_idle_cpu = 0; + unsigned long sum_nr_running, sum_weighted_load; + unsigned long sum_avg_load_per_task; + unsigned long avg_load_per_task; + + local_group = cpu_isset(this_cpu, group->cpumask); + + if (local_group) + balance_cpu = first_cpu(group->cpumask); + + /* Tally up the load of all CPUs in the group */ + sum_weighted_load = sum_nr_running = avg_load = 0; + sum_avg_load_per_task = avg_load_per_task = 0; + + max_cpu_load = 0; + min_cpu_load = ~0UL; + + for_each_cpu_mask_nr(i, group->cpumask) { + struct rq *rq; + + if (!cpu_isset(i, *cpus)) + continue; + + rq = cpu_rq(i); + + if (*sd_idle && rq->nr_running) + *sd_idle = 0; + + /* Bias balancing toward cpus of our domain */ + if (local_group) { + if (idle_cpu(i) && !first_idle_cpu) { + first_idle_cpu = 1; + balance_cpu = i; + } + + load = target_load(i, load_idx); + } else { + load = source_load(i, load_idx); + if (load > max_cpu_load) + max_cpu_load = load; + if (min_cpu_load > load) + min_cpu_load = load; + } + + avg_load += load; + sum_nr_running += rq->nr_running; + sum_weighted_load += weighted_cpuload(i); + + sum_avg_load_per_task += cpu_avg_load_per_task(i); + } + + /* + * First idle cpu or the first cpu(busiest) in this sched group + * is eligible for doing load balancing at this and above + * domains. In the newly idle case, we will allow all the cpu's + * to do the newly idle load balance. + */ + if (idle != CPU_NEWLY_IDLE && local_group && + balance_cpu != this_cpu && balance) { + *balance = 0; + goto ret; + } + + total_load += avg_load; + total_pwr += group->__cpu_power; + + /* Adjust by relative CPU power of the group */ + avg_load = sg_div_cpu_power(group, + avg_load * SCHED_LOAD_SCALE); + + + /* + * Consider the group unbalanced when the imbalance is larger + * than the average weight of two tasks. + * + * APZ: with cgroup the avg task weight can vary wildly and + * might not be a suitable number - should we keep a + * normalized nr_running number somewhere that negates + * the hierarchy? + */ + avg_load_per_task = sg_div_cpu_power(group, + sum_avg_load_per_task * SCHED_LOAD_SCALE); + + if ((max_cpu_load - min_cpu_load) > 2*avg_load_per_task) + __group_imb = 1; + + group_capacity = group->__cpu_power / SCHED_LOAD_SCALE; + + if (local_group) { + this_load = avg_load; + this = group; + this_nr_running = sum_nr_running; + this_load_per_task = sum_weighted_load; + } else if (avg_load > max_load && + (sum_nr_running > group_capacity || __group_imb)) { + max_load = avg_load; + busiest = group; + busiest_nr_running = sum_nr_running; + busiest_load_per_task = sum_weighted_load; + group_imb = __group_imb; + } + +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) + /* + * Busy processors will not participate in power savings + * balance. + */ + if (idle == CPU_NOT_IDLE || + !(sd->flags & SD_POWERSAVINGS_BALANCE)) + goto group_next; + + /* + * If the local group is idle or completely loaded + * no need to do power savings balance at this domain + */ + if (local_group && (this_nr_running >= group_capacity || + !this_nr_running)) + power_savings_balance = 0; + + /* + * If a group is already running at full capacity or idle, + * don't include that group in power savings calculations + */ + if (!power_savings_balance || sum_nr_running >= group_capacity + || !sum_nr_running) + goto group_next; + + /* + * Calculate the group which has the least non-idle load. + * This is the group from where we need to pick up the load + * for saving power + */ + if ((sum_nr_running < min_nr_running) || + (sum_nr_running == min_nr_running && + first_cpu(group->cpumask) < + first_cpu(group_min->cpumask))) { + group_min = group; + min_nr_running = sum_nr_running; + min_load_per_task = sum_weighted_load / + sum_nr_running; + } + + /* + * Calculate the group which is almost near its + * capacity but still has some space to pick up some load + * from other group and save more power + */ + if (sum_nr_running <= group_capacity - 1) { + if (sum_nr_running > leader_nr_running || + (sum_nr_running == leader_nr_running && + first_cpu(group->cpumask) > + first_cpu(group_leader->cpumask))) { + group_leader = group; + leader_nr_running = sum_nr_running; + } + } +group_next: +#endif + group = group->next; + } while (group != sd->groups); + + if (!busiest || this_load >= max_load || busiest_nr_running == 0) + goto out_balanced; + + avg_load = (SCHED_LOAD_SCALE * total_load) / total_pwr; + + if (this_load >= avg_load || + 100*max_load <= sd->imbalance_pct*this_load) + goto out_balanced; + + busiest_load_per_task /= busiest_nr_running; + if (group_imb) + busiest_load_per_task = min(busiest_load_per_task, avg_load); + + /* + * We're trying to get all the cpus to the average_load, so we don't + * want to push ourselves above the average load, nor do we wish to + * reduce the max loaded cpu below the average load, as either of these + * actions would just result in more rebalancing later, and ping-pong + * tasks around. Thus we look for the minimum possible imbalance. + * Negative imbalances (*we* are more loaded than anyone else) will + * be counted as no imbalance for these purposes -- we can't fix that + * by pulling tasks to us. Be careful of negative numbers as they'll + * appear as very large values with unsigned longs. + */ + if (max_load <= busiest_load_per_task) + goto out_balanced; + + /* + * In the presence of smp nice balancing, certain scenarios can have + * max load less than avg load(as we skip the groups at or below + * its cpu_power, while calculating max_load..) + */ + if (max_load < avg_load) { + *imbalance = 0; + goto small_imbalance; + } + + /* Don't want to pull so many tasks that a group would go idle */ + max_pull = min(max_load - avg_load, max_load - busiest_load_per_task); + + /* How much load to actually move to equalise the imbalance */ + *imbalance = min(max_pull * busiest->__cpu_power, + (avg_load - this_load) * this->__cpu_power) + / SCHED_LOAD_SCALE; + + /* + * if *imbalance is less than the average load per runnable task + * there is no gaurantee that any tasks will be moved so we'll have + * a think about bumping its value to force at least one task to be + * moved + */ + if (*imbalance < busiest_load_per_task) { + unsigned long tmp, pwr_now, pwr_move; + unsigned int imbn; + +small_imbalance: + pwr_move = pwr_now = 0; + imbn = 2; + if (this_nr_running) { + this_load_per_task /= this_nr_running; + if (busiest_load_per_task > this_load_per_task) + imbn = 1; + } else + this_load_per_task = cpu_avg_load_per_task(this_cpu); + + if (max_load - this_load + 2*busiest_load_per_task >= + busiest_load_per_task * imbn) { + *imbalance = busiest_load_per_task; + return busiest; + } + + /* + * OK, we don't have enough imbalance to justify moving tasks, + * however we may be able to increase total CPU power used by + * moving them. + */ + + pwr_now += busiest->__cpu_power * + min(busiest_load_per_task, max_load); + pwr_now += this->__cpu_power * + min(this_load_per_task, this_load); + pwr_now /= SCHED_LOAD_SCALE; + + /* Amount of load we'd subtract */ + tmp = sg_div_cpu_power(busiest, + busiest_load_per_task * SCHED_LOAD_SCALE); + if (max_load > tmp) + pwr_move += busiest->__cpu_power * + min(busiest_load_per_task, max_load - tmp); + + /* Amount of load we'd add */ + if (max_load * busiest->__cpu_power < + busiest_load_per_task * SCHED_LOAD_SCALE) + tmp = sg_div_cpu_power(this, + max_load * busiest->__cpu_power); + else + tmp = sg_div_cpu_power(this, + busiest_load_per_task * SCHED_LOAD_SCALE); + pwr_move += this->__cpu_power * + min(this_load_per_task, this_load + tmp); + pwr_move /= SCHED_LOAD_SCALE; + + /* Move if we gain throughput */ + if (pwr_move > pwr_now) + *imbalance = busiest_load_per_task; + } + + return busiest; + +out_balanced: +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) + if (idle == CPU_NOT_IDLE || !(sd->flags & SD_POWERSAVINGS_BALANCE)) + goto ret; + + if (this == group_leader && group_leader != group_min) { + *imbalance = min_load_per_task; + return group_min; + } +#endif +ret: + *imbalance = 0; + return NULL; +} + +/* + * find_busiest_queue - find the busiest runqueue among the cpus in group. + */ +static struct rq * +find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle, + unsigned long imbalance, const cpumask_t *cpus) +{ + struct rq *busiest = NULL, *rq; + unsigned long max_load = 0; + int i; + + for_each_cpu_mask_nr(i, group->cpumask) { + unsigned long wl; + + if (!cpu_isset(i, *cpus)) + continue; + + rq = cpu_rq(i); + wl = weighted_cpuload(i); + + if (rq->nr_running == 1 && wl > imbalance) + continue; + + if (wl > max_load) { + max_load = wl; + busiest = rq; + } + } + + return busiest; +} + +/* + * Max backoff if we encounter pinned tasks. Pretty arbitrary value, but + * so long as it is large enough. + */ +#define MAX_PINNED_INTERVAL 512 + +/* + * Check this_cpu to ensure it is balanced within domain. Attempt to move + * tasks if there is an imbalance. + */ +static int load_balance(int this_cpu, struct rq *this_rq, + struct sched_domain *sd, enum cpu_idle_type idle, + int *balance, cpumask_t *cpus) +{ + int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0; + struct sched_group *group; + unsigned long imbalance; + struct rq *busiest; + unsigned long flags; + + cpus_setall(*cpus); + + /* + * When power savings policy is enabled for the parent domain, idle + * sibling can pick up load irrespective of busy siblings. In this case, + * let the state of idle sibling percolate up as CPU_IDLE, instead of + * portraying it as CPU_NOT_IDLE. + */ + if (idle != CPU_NOT_IDLE && sd->flags & SD_SHARE_CPUPOWER && + !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) + sd_idle = 1; + + schedstat_inc(sd, lb_count[idle]); + +redo: + update_shares(sd); + group = find_busiest_group(sd, this_cpu, &imbalance, idle, &sd_idle, + cpus, balance); + + if (*balance == 0) + goto out_balanced; + + if (!group) { + schedstat_inc(sd, lb_nobusyg[idle]); + goto out_balanced; + } + + busiest = find_busiest_queue(group, idle, imbalance, cpus); + if (!busiest) { + schedstat_inc(sd, lb_nobusyq[idle]); + goto out_balanced; + } + + BUG_ON(busiest == this_rq); + + schedstat_add(sd, lb_imbalance[idle], imbalance); + + ld_moved = 0; + if (busiest->nr_running > 1) { + /* + * Attempt to move tasks. If find_busiest_group has found + * an imbalance but busiest->nr_running <= 1, the group is + * still unbalanced. ld_moved simply stays zero, so it is + * correctly treated as an imbalance. + */ + local_irq_save(flags); + double_rq_lock(this_rq, busiest); + ld_moved = move_tasks(this_rq, this_cpu, busiest, + imbalance, sd, idle, &all_pinned); + double_rq_unlock(this_rq, busiest); + local_irq_restore(flags); + + /* + * some other cpu did the load balance for us. + */ + if (ld_moved && this_cpu != smp_processor_id()) + resched_cpu(this_cpu); + + /* All tasks on this runqueue were pinned by CPU affinity */ + if (unlikely(all_pinned)) { + cpu_clear(cpu_of(busiest), *cpus); + if (!cpus_empty(*cpus)) + goto redo; + goto out_balanced; + } + } + + if (!ld_moved) { + schedstat_inc(sd, lb_failed[idle]); + sd->nr_balance_failed++; + + if (unlikely(sd->nr_balance_failed > sd->cache_nice_tries+2)) { + + spin_lock_irqsave(&busiest->lock, flags); + + /* don't kick the migration_thread, if the curr + * task on busiest cpu can't be moved to this_cpu + */ + if (!cpu_isset(this_cpu, busiest->curr->cpus_allowed)) { + spin_unlock_irqrestore(&busiest->lock, flags); + all_pinned = 1; + goto out_one_pinned; + } + + if (!busiest->active_balance) { + busiest->active_balance = 1; + busiest->push_cpu = this_cpu; + active_balance = 1; + } + spin_unlock_irqrestore(&busiest->lock, flags); + if (active_balance) + wake_up_process(busiest->migration_thread); + + /* + * We've kicked active balancing, reset the failure + * counter. + */ + sd->nr_balance_failed = sd->cache_nice_tries+1; + } + } else + sd->nr_balance_failed = 0; + + if (likely(!active_balance)) { + /* We were unbalanced, so reset the balancing interval */ + sd->balance_interval = sd->min_interval; + } else { + /* + * If we've begun active balancing, start to back off. This + * case may not be covered by the all_pinned logic if there + * is only 1 task on the busy runqueue (because we don't call + * move_tasks). + */ + if (sd->balance_interval < sd->max_interval) + sd->balance_interval *= 2; + } + + if (!ld_moved && !sd_idle && sd->flags & SD_SHARE_CPUPOWER && + !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) + ld_moved = -1; + + goto out; + +out_balanced: + schedstat_inc(sd, lb_balanced[idle]); + + sd->nr_balance_failed = 0; + +out_one_pinned: + /* tune up the balancing interval */ + if ((all_pinned && sd->balance_interval < MAX_PINNED_INTERVAL) || + (sd->balance_interval < sd->max_interval)) + sd->balance_interval *= 2; + + if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && + !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) + ld_moved = -1; + else + ld_moved = 0; +out: + if (ld_moved) + update_shares(sd); + return ld_moved; +} + +/* + * Check this_cpu to ensure it is balanced within domain. Attempt to move + * tasks if there is an imbalance. + * + * Called from schedule when this_rq is about to become idle (CPU_NEWLY_IDLE). + * this_rq is locked. + */ +static int +load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd, + cpumask_t *cpus) +{ + struct sched_group *group; + struct rq *busiest = NULL; + unsigned long imbalance; + int ld_moved = 0; + int sd_idle = 0; + int all_pinned = 0; + + cpus_setall(*cpus); + + /* + * When power savings policy is enabled for the parent domain, idle + * sibling can pick up load irrespective of busy siblings. In this case, + * let the state of idle sibling percolate up as IDLE, instead of + * portraying it as CPU_NOT_IDLE. + */ + if (sd->flags & SD_SHARE_CPUPOWER && + !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) + sd_idle = 1; + + schedstat_inc(sd, lb_count[CPU_NEWLY_IDLE]); +redo: + update_shares_locked(this_rq, sd); + group = find_busiest_group(sd, this_cpu, &imbalance, CPU_NEWLY_IDLE, + &sd_idle, cpus, NULL); + if (!group) { + schedstat_inc(sd, lb_nobusyg[CPU_NEWLY_IDLE]); + goto out_balanced; + } + + busiest = find_busiest_queue(group, CPU_NEWLY_IDLE, imbalance, cpus); + if (!busiest) { + schedstat_inc(sd, lb_nobusyq[CPU_NEWLY_IDLE]); + goto out_balanced; + } + + BUG_ON(busiest == this_rq); + + schedstat_add(sd, lb_imbalance[CPU_NEWLY_IDLE], imbalance); + + ld_moved = 0; + if (busiest->nr_running > 1) { + /* Attempt to move tasks */ + double_lock_balance(this_rq, busiest); + /* this_rq->clock is already updated */ + update_rq_clock(busiest); + ld_moved = move_tasks(this_rq, this_cpu, busiest, + imbalance, sd, CPU_NEWLY_IDLE, + &all_pinned); + double_unlock_balance(this_rq, busiest); + + if (unlikely(all_pinned)) { + cpu_clear(cpu_of(busiest), *cpus); + if (!cpus_empty(*cpus)) + goto redo; + } + } + + if (!ld_moved) { + schedstat_inc(sd, lb_failed[CPU_NEWLY_IDLE]); + if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && + !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) + return -1; + } else + sd->nr_balance_failed = 0; + + update_shares_locked(this_rq, sd); + return ld_moved; + +out_balanced: + schedstat_inc(sd, lb_balanced[CPU_NEWLY_IDLE]); + if (!sd_idle && sd->flags & SD_SHARE_CPUPOWER && + !test_sd_parent(sd, SD_POWERSAVINGS_BALANCE)) + return -1; + sd->nr_balance_failed = 0; + + return 0; +} + +/* + * idle_balance is called by schedule() if this_cpu is about to become + * idle. Attempts to pull tasks from other CPUs. + */ +static void idle_balance(int this_cpu, struct rq *this_rq) +{ + struct sched_domain *sd; + int pulled_task = -1; + unsigned long next_balance = jiffies + HZ; + cpumask_t tmpmask; + + for_each_domain(this_cpu, sd) { + unsigned long interval; + + if (!(sd->flags & SD_LOAD_BALANCE)) + continue; + + if (sd->flags & SD_BALANCE_NEWIDLE) + /* If we've pulled tasks over stop searching: */ + pulled_task = load_balance_newidle(this_cpu, this_rq, + sd, &tmpmask); + + interval = msecs_to_jiffies(sd->balance_interval); + if (time_after(next_balance, sd->last_balance + interval)) + next_balance = sd->last_balance + interval; + if (pulled_task) + break; + } + if (pulled_task || time_after(jiffies, this_rq->next_balance)) { + /* + * We are going idle. next_balance may be set based on + * a busy processor. So reset next_balance. + */ + this_rq->next_balance = next_balance; + } +} + +/* + * active_load_balance is run by migration threads. It pushes running tasks + * off the busiest CPU onto idle CPUs. It requires at least 1 task to be + * running on each physical CPU where possible, and avoids physical / + * logical imbalances. + * + * Called with busiest_rq locked. + */ +static void active_load_balance(struct rq *busiest_rq, int busiest_cpu) +{ + int target_cpu = busiest_rq->push_cpu; + struct sched_domain *sd; + struct rq *target_rq; + + /* Is there any task to move? */ + if (busiest_rq->nr_running <= 1) + return; + + target_rq = cpu_rq(target_cpu); + + /* + * This condition is "impossible", if it occurs + * we need to fix it. Originally reported by + * Bjorn Helgaas on a 128-cpu setup. + */ + BUG_ON(busiest_rq == target_rq); + + /* move a task from busiest_rq to target_rq */ + double_lock_balance(busiest_rq, target_rq); + update_rq_clock(busiest_rq); + update_rq_clock(target_rq); + + /* Search for an sd spanning us and the target CPU. */ + for_each_domain(target_cpu, sd) { + if ((sd->flags & SD_LOAD_BALANCE) && + cpu_isset(busiest_cpu, sd->span)) + break; + } + + if (likely(sd)) { + schedstat_inc(sd, alb_count); + + if (move_one_task(target_rq, target_cpu, busiest_rq, + sd, CPU_IDLE)) + schedstat_inc(sd, alb_pushed); + else + schedstat_inc(sd, alb_failed); + } + double_unlock_balance(busiest_rq, target_rq); +} + +#ifdef CONFIG_NO_HZ +static struct { + atomic_t load_balancer; + cpumask_t cpu_mask; +} nohz ____cacheline_aligned = { + .load_balancer = ATOMIC_INIT(-1), + .cpu_mask = CPU_MASK_NONE, +}; + +/* + * This routine will try to nominate the ilb (idle load balancing) + * owner among the cpus whose ticks are stopped. ilb owner will do the idle + * load balancing on behalf of all those cpus. If all the cpus in the system + * go into this tickless mode, then there will be no ilb owner (as there is + * no need for one) and all the cpus will sleep till the next wakeup event + * arrives... + * + * For the ilb owner, tick is not stopped. And this tick will be used + * for idle load balancing. ilb owner will still be part of + * nohz.cpu_mask.. + * + * While stopping the tick, this cpu will become the ilb owner if there + * is no other owner. And will be the owner till that cpu becomes busy + * or if all cpus in the system stop their ticks at which point + * there is no need for ilb owner. + * + * When the ilb owner becomes busy, it nominates another owner, during the + * next busy scheduler_tick() + */ +int select_nohz_load_balancer(int stop_tick) +{ + int cpu = smp_processor_id(); + + if (stop_tick) { + cpu_set(cpu, nohz.cpu_mask); + cpu_rq(cpu)->in_nohz_recently = 1; + + /* + * If we are going offline and still the leader, give up! + */ + if (!cpu_active(cpu) && + atomic_read(&nohz.load_balancer) == cpu) { + if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) + BUG(); + return 0; + } + + /* time for ilb owner also to sleep */ + if (cpus_weight(nohz.cpu_mask) == num_online_cpus()) { + if (atomic_read(&nohz.load_balancer) == cpu) + atomic_set(&nohz.load_balancer, -1); + return 0; + } + + if (atomic_read(&nohz.load_balancer) == -1) { + /* make me the ilb owner */ + if (atomic_cmpxchg(&nohz.load_balancer, -1, cpu) == -1) + return 1; + } else if (atomic_read(&nohz.load_balancer) == cpu) + return 1; + } else { + if (!cpu_isset(cpu, nohz.cpu_mask)) + return 0; + + cpu_clear(cpu, nohz.cpu_mask); + + if (atomic_read(&nohz.load_balancer) == cpu) + if (atomic_cmpxchg(&nohz.load_balancer, cpu, -1) != cpu) + BUG(); + } + return 0; +} +#endif + +static DEFINE_SPINLOCK(balancing); + +/* + * It checks each scheduling domain to see if it is due to be balanced, + * and initiates a balancing operation if so. + * + * Balancing parameters are set up in arch_init_sched_domains. + */ +static void rebalance_domains(int cpu, enum cpu_idle_type idle) +{ + int balance = 1; + struct rq *rq = cpu_rq(cpu); + unsigned long interval; + struct sched_domain *sd; + /* Earliest time when we have to do rebalance again */ + unsigned long next_balance = jiffies + 60*HZ; + int update_next_balance = 0; + int need_serialize; + cpumask_t tmp; + + for_each_domain(cpu, sd) { + if (!(sd->flags & SD_LOAD_BALANCE)) + continue; + + interval = sd->balance_interval; + if (idle != CPU_IDLE) + interval *= sd->busy_factor; + + /* scale ms to jiffies */ + interval = msecs_to_jiffies(interval); + if (unlikely(!interval)) + interval = 1; + if (interval > HZ*NR_CPUS/10) + interval = HZ*NR_CPUS/10; + + need_serialize = sd->flags & SD_SERIALIZE; + + if (need_serialize) { + if (!spin_trylock(&balancing)) + goto out; + } + + if (time_after_eq(jiffies, sd->last_balance + interval)) { + if (load_balance(cpu, rq, sd, idle, &balance, &tmp)) { + /* + * We've pulled tasks over so either we're no + * longer idle, or one of our SMT siblings is + * not idle. + */ + idle = CPU_NOT_IDLE; + } + sd->last_balance = jiffies; + } + if (need_serialize) + spin_unlock(&balancing); +out: + if (time_after(next_balance, sd->last_balance + interval)) { + next_balance = sd->last_balance + interval; + update_next_balance = 1; + } + + /* + * Stop the load balance at this level. There is another + * CPU in our sched group which is doing load balancing more + * actively. + */ + if (!balance) + break; + } + + /* + * next_balance will be updated only when there is a need. + * When the cpu is attached to null domain for ex, it will not be + * updated. + */ + if (likely(update_next_balance)) + rq->next_balance = next_balance; +} + +/* + * run_rebalance_domains is triggered when needed from the scheduler tick. + * In CONFIG_NO_HZ case, the idle load balance owner will do the + * rebalancing for all the cpus for whom scheduler ticks are stopped. + */ +static void run_rebalance_domains(struct softirq_action *h) +{ + int this_cpu = smp_processor_id(); + struct rq *this_rq = cpu_rq(this_cpu); + enum cpu_idle_type idle = this_rq->idle_at_tick ? + CPU_IDLE : CPU_NOT_IDLE; + + rebalance_domains(this_cpu, idle); + +#ifdef CONFIG_NO_HZ + /* + * If this cpu is the owner for idle load balancing, then do the + * balancing on behalf of the other idle cpus whose ticks are + * stopped. + */ + if (this_rq->idle_at_tick && + atomic_read(&nohz.load_balancer) == this_cpu) { + cpumask_t cpus = nohz.cpu_mask; + struct rq *rq; + int balance_cpu; + + cpu_clear(this_cpu, cpus); + for_each_cpu_mask_nr(balance_cpu, cpus) { + /* + * If this cpu gets work to do, stop the load balancing + * work being done for other cpus. Next load + * balancing owner will pick it up. + */ + if (need_resched()) + break; + + rebalance_domains(balance_cpu, CPU_IDLE); + + rq = cpu_rq(balance_cpu); + if (time_after(this_rq->next_balance, rq->next_balance)) + this_rq->next_balance = rq->next_balance; + } + } +#endif +} + +/* + * Trigger the SCHED_SOFTIRQ if it is time to do periodic load balancing. + * + * In case of CONFIG_NO_HZ, this is the place where we nominate a new + * idle load balancing owner or decide to stop the periodic load balancing, + * if the whole system is idle. + */ +static inline void trigger_load_balance(struct rq *rq, int cpu) +{ +#ifdef CONFIG_NO_HZ + /* + * If we were in the nohz mode recently and busy at the current + * scheduler tick, then check if we need to nominate new idle + * load balancer. + */ + if (rq->in_nohz_recently && !rq->idle_at_tick) { + rq->in_nohz_recently = 0; + + if (atomic_read(&nohz.load_balancer) == cpu) { + cpu_clear(cpu, nohz.cpu_mask); + atomic_set(&nohz.load_balancer, -1); + } + + if (atomic_read(&nohz.load_balancer) == -1) { + /* + * simple selection for now: Nominate the + * first cpu in the nohz list to be the next + * ilb owner. + * + * TBD: Traverse the sched domains and nominate + * the nearest cpu in the nohz.cpu_mask. + */ + int ilb = first_cpu(nohz.cpu_mask); + + if (ilb < nr_cpu_ids) + resched_cpu(ilb); + } + } + + /* + * If this cpu is idle and doing idle load balancing for all the + * cpus with ticks stopped, is it time for that to stop? + */ + if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) == cpu && + cpus_weight(nohz.cpu_mask) == num_online_cpus()) { + resched_cpu(cpu); + return; + } + + /* + * If this cpu is idle and the idle load balancing is done by + * someone else, then no need raise the SCHED_SOFTIRQ + */ + if (rq->idle_at_tick && atomic_read(&nohz.load_balancer) != cpu && + cpu_isset(cpu, nohz.cpu_mask)) + return; +#endif + if (time_after_eq(jiffies, rq->next_balance)) + raise_softirq(SCHED_SOFTIRQ); +} + +#else /* CONFIG_SMP */ + +/* + * on UP we do not need to balance between CPUs: + */ +static inline void idle_balance(int cpu, struct rq *rq) +{ +} + +#endif + +DEFINE_PER_CPU(struct kernel_stat, kstat); + +EXPORT_PER_CPU_SYMBOL(kstat); + +/* + * Return p->sum_exec_runtime plus any more ns on the sched_clock + * that have not yet been banked in case the task is currently running. + */ +unsigned long long task_sched_runtime(struct task_struct *p) +{ + unsigned long flags; + u64 ns, delta_exec; + struct rq *rq; + + rq = task_rq_lock(p, &flags); + ns = p->se.sum_exec_runtime; + if (task_current(rq, p)) { + update_rq_clock(rq); + delta_exec = rq->clock - p->se.exec_start; + if ((s64)delta_exec > 0) + ns += delta_exec; + } + task_rq_unlock(rq, &flags); + + return ns; +} + +/* + * Account user cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in user space since the last update + */ +void account_user_time(struct task_struct *p, cputime_t cputime) +{ + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + struct vx_info *vxi = p->vx_info; /* p is _always_ current */ + cputime64_t tmp; + int nice = (TASK_NICE(p) > 0); + + p->utime = cputime_add(p->utime, cputime); + vx_account_user(vxi, cputime, nice); + + /* Add user time to cpustat. */ + tmp = cputime_to_cputime64(cputime); + if (nice) + cpustat->nice = cputime64_add(cpustat->nice, tmp); + else + cpustat->user = cputime64_add(cpustat->user, tmp); + /* Account for user time used */ + acct_update_integrals(p); +} + +/* + * Account guest cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in virtual machine since the last update + */ +static void account_guest_time(struct task_struct *p, cputime_t cputime) +{ + cputime64_t tmp; + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + + tmp = cputime_to_cputime64(cputime); + + p->utime = cputime_add(p->utime, cputime); + p->gtime = cputime_add(p->gtime, cputime); + + cpustat->user = cputime64_add(cpustat->user, tmp); + cpustat->guest = cputime64_add(cpustat->guest, tmp); +} + +/* + * Account scaled user cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in user space since the last update + */ +void account_user_time_scaled(struct task_struct *p, cputime_t cputime) +{ + p->utimescaled = cputime_add(p->utimescaled, cputime); +} + +/* + * Account system cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @hardirq_offset: the offset to subtract from hardirq_count() + * @cputime: the cpu time spent in kernel space since the last update + */ +void account_system_time(struct task_struct *p, int hardirq_offset, + cputime_t cputime) +{ + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + struct vx_info *vxi = p->vx_info; /* p is _always_ current */ + struct rq *rq = this_rq(); + cputime64_t tmp; + + if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) { + account_guest_time(p, cputime); + return; + } + + p->stime = cputime_add(p->stime, cputime); + vx_account_system(vxi, cputime, (p == rq->idle)); + + /* Add system time to cpustat. */ + tmp = cputime_to_cputime64(cputime); + if (hardirq_count() - hardirq_offset) + cpustat->irq = cputime64_add(cpustat->irq, tmp); + else if (softirq_count()) + cpustat->softirq = cputime64_add(cpustat->softirq, tmp); + else if (p != rq->idle) + cpustat->system = cputime64_add(cpustat->system, tmp); + else if (atomic_read(&rq->nr_iowait) > 0) + cpustat->iowait = cputime64_add(cpustat->iowait, tmp); + else + cpustat->idle = cputime64_add(cpustat->idle, tmp); + /* Account for system time used */ + acct_update_integrals(p); +} + +/* + * Account scaled system cpu time to a process. + * @p: the process that the cpu time gets accounted to + * @hardirq_offset: the offset to subtract from hardirq_count() + * @cputime: the cpu time spent in kernel space since the last update + */ +void account_system_time_scaled(struct task_struct *p, cputime_t cputime) +{ + p->stimescaled = cputime_add(p->stimescaled, cputime); +} + +/* + * Account for involuntary wait time. + * @p: the process from which the cpu time has been stolen + * @steal: the cpu time spent in involuntary wait + */ +void account_steal_time(struct task_struct *p, cputime_t steal) +{ + struct cpu_usage_stat *cpustat = &kstat_this_cpu.cpustat; + cputime64_t tmp = cputime_to_cputime64(steal); + struct rq *rq = this_rq(); + + if (p == rq->idle) { + p->stime = cputime_add(p->stime, steal); + if (atomic_read(&rq->nr_iowait) > 0) + cpustat->iowait = cputime64_add(cpustat->iowait, tmp); + else + cpustat->idle = cputime64_add(cpustat->idle, tmp); + } else + cpustat->steal = cputime64_add(cpustat->steal, tmp); +} + +/* + * Use precise platform statistics if available: + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING +cputime_t task_utime(struct task_struct *p) +{ + return p->utime; +} + +cputime_t task_stime(struct task_struct *p) +{ + return p->stime; +} +#else +cputime_t task_utime(struct task_struct *p) +{ + clock_t utime = cputime_to_clock_t(p->utime), + total = utime + cputime_to_clock_t(p->stime); + u64 temp; + + /* + * Use CFS's precise accounting: + */ + temp = (u64)nsec_to_clock_t(p->se.sum_exec_runtime); + + if (total) { + temp *= utime; + do_div(temp, total); + } + utime = (clock_t)temp; + + p->prev_utime = max(p->prev_utime, clock_t_to_cputime(utime)); + return p->prev_utime; +} + +cputime_t task_stime(struct task_struct *p) +{ + clock_t stime; + + /* + * Use CFS's precise accounting. (we subtract utime from + * the total, to make sure the total observed by userspace + * grows monotonically - apps rely on that): + */ + stime = nsec_to_clock_t(p->se.sum_exec_runtime) - + cputime_to_clock_t(task_utime(p)); + + if (stime >= 0) + p->prev_stime = max(p->prev_stime, clock_t_to_cputime(stime)); + + return p->prev_stime; +} +#endif + +inline cputime_t task_gtime(struct task_struct *p) +{ + return p->gtime; +} + +/* + * This function gets called by the timer code, with HZ frequency. + * We call it with interrupts disabled. + * + * It also gets called by the fork code, when changing the parent's + * timeslices. + */ +void scheduler_tick(void) +{ + int cpu = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + struct task_struct *curr = rq->curr; + + sched_clock_tick(); + + spin_lock(&rq->lock); + update_rq_clock(rq); + update_cpu_load(rq); + curr->sched_class->task_tick(rq, curr, 0); + spin_unlock(&rq->lock); + +#ifdef CONFIG_SMP + rq->idle_at_tick = idle_cpu(cpu); + trigger_load_balance(rq, cpu); +#endif +} + +#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) + +static inline unsigned long get_parent_ip(unsigned long addr) +{ + if (in_lock_functions(addr)) { + addr = CALLER_ADDR2; + if (in_lock_functions(addr)) + addr = CALLER_ADDR3; + } + return addr; +} + +void __kprobes add_preempt_count(int val) +{ +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) + return; +#endif + preempt_count() += val; +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Spinlock count overflowing soon? + */ + DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= + PREEMPT_MASK - 10); +#endif + if (preempt_count() == val) + trace_preempt_off(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); +} +EXPORT_SYMBOL(add_preempt_count); + +void __kprobes sub_preempt_count(int val) +{ +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON(val > preempt_count())) + return; + /* + * Is the spinlock portion underflowing? + */ + if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) && + !(preempt_count() & PREEMPT_MASK))) + return; +#endif + + if (preempt_count() == val) + trace_preempt_on(CALLER_ADDR0, get_parent_ip(CALLER_ADDR1)); + preempt_count() -= val; +} +EXPORT_SYMBOL(sub_preempt_count); + +#endif + +/* + * Print scheduling while atomic bug: + */ +static noinline void __schedule_bug(struct task_struct *prev) +{ + struct pt_regs *regs = get_irq_regs(); + + printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n", + prev->comm, prev->pid, preempt_count()); + + debug_show_held_locks(prev); + print_modules(); + if (irqs_disabled()) + print_irqtrace_events(prev); + + if (regs) + show_regs(regs); + else + dump_stack(); +} + +/* + * Various schedule()-time debugging checks and statistics: + */ +static inline void schedule_debug(struct task_struct *prev) +{ + /* + * Test if we are atomic. Since do_exit() needs to call into + * schedule() atomically, we ignore that path for now. + * Otherwise, whine if we are scheduling when we should not be. + */ + if (unlikely(in_atomic_preempt_off() && !prev->exit_state)) + __schedule_bug(prev); + + profile_hit(SCHED_PROFILING, __builtin_return_address(0)); + + schedstat_inc(this_rq(), sched_count); +#ifdef CONFIG_SCHEDSTATS + if (unlikely(prev->lock_depth >= 0)) { + schedstat_inc(this_rq(), bkl_count); + schedstat_inc(prev, sched_info.bkl_count); + } +#endif +} + +/* + * Pick up the highest-prio task: + */ +static inline struct task_struct * +pick_next_task(struct rq *rq, struct task_struct *prev) +{ + const struct sched_class *class; + struct task_struct *p; + + /* + * Optimization: we know that if all tasks are in + * the fair class we can call that function directly: + */ + if (likely(rq->nr_running == rq->cfs.nr_running)) { + p = fair_sched_class.pick_next_task(rq); + if (likely(p)) + return p; + } + + class = sched_class_highest; + for ( ; ; ) { + p = class->pick_next_task(rq); + if (p) + return p; + /* + * Will never be NULL as the idle class always + * returns a non-NULL p: + */ + class = class->next; + } +} + +void (*rec_event)(void *,unsigned int) = NULL; +EXPORT_SYMBOL(rec_event); +#ifdef CONFIG_CHOPSTIX + +struct event_spec { + unsigned long pc; + unsigned long dcookie; + unsigned int count; + unsigned int reason; +}; + +/* To support safe calling from asm */ +asmlinkage void rec_event_asm (struct event *event_signature_in, unsigned int count) { + struct pt_regs *regs; + struct event_spec *es = event_signature_in->event_data; + regs = task_pt_regs(current); + event_signature_in->task=current; + es->pc=regs->ip; + event_signature_in->count=1; + (*rec_event)(event_signature_in, count); +} +#endif + +/* + * schedule() is the main scheduler function. + */ +asmlinkage void __sched schedule(void) +{ + struct task_struct *prev, *next; + unsigned long *switch_count; + struct rq *rq; + int cpu; + +need_resched: + preempt_disable(); + cpu = smp_processor_id(); + rq = cpu_rq(cpu); + rcu_qsctr_inc(cpu); + prev = rq->curr; + switch_count = &prev->nivcsw; + + release_kernel_lock(prev); +need_resched_nonpreemptible: + + schedule_debug(prev); + + if (sched_feat(HRTICK)) + hrtick_clear(rq); + + /* + * Do the rq-clock update outside the rq lock: + */ + local_irq_disable(); + update_rq_clock(rq); + spin_lock(&rq->lock); + clear_tsk_need_resched(prev); + + if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { + if (unlikely(signal_pending_state(prev->state, prev))) + prev->state = TASK_RUNNING; + else + deactivate_task(rq, prev, 1); + switch_count = &prev->nvcsw; + } + +#ifdef CONFIG_SMP + if (prev->sched_class->pre_schedule) + prev->sched_class->pre_schedule(rq, prev); +#endif + + if (unlikely(!rq->nr_running)) + idle_balance(cpu, rq); + + prev->sched_class->put_prev_task(rq, prev); + next = pick_next_task(rq, prev); + + if (likely(prev != next)) { + sched_info_switch(prev, next); + + rq->nr_switches++; + rq->curr = next; + ++*switch_count; + + context_switch(rq, prev, next); /* unlocks the rq */ + /* + * the context switch might have flipped the stack from under + * us, hence refresh the local variables. + */ + cpu = smp_processor_id(); + rq = cpu_rq(cpu); + } else + spin_unlock_irq(&rq->lock); + + if (unlikely(reacquire_kernel_lock(current) < 0)) + goto need_resched_nonpreemptible; + + preempt_enable_no_resched(); + if (unlikely(test_thread_flag(TIF_NEED_RESCHED))) + goto need_resched; +} +EXPORT_SYMBOL(schedule); + +#ifdef CONFIG_PREEMPT +/* + * this is the entry point to schedule() from in-kernel preemption + * off of preempt_enable. Kernel preemptions off return from interrupt + * occur there and call schedule directly. + */ +asmlinkage void __sched preempt_schedule(void) +{ + struct thread_info *ti = current_thread_info(); + + /* + * If there is a non-zero preempt_count or interrupts are disabled, + * we do not want to preempt the current task. Just return.. + */ + if (likely(ti->preempt_count || irqs_disabled())) + return; + + do { + add_preempt_count(PREEMPT_ACTIVE); + schedule(); + sub_preempt_count(PREEMPT_ACTIVE); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (unlikely(test_thread_flag(TIF_NEED_RESCHED))); +} +EXPORT_SYMBOL(preempt_schedule); + +/* + * this is the entry point to schedule() from kernel preemption + * off of irq context. + * Note, that this is called and return with irqs disabled. This will + * protect us against recursive calling from irq. + */ +asmlinkage void __sched preempt_schedule_irq(void) +{ + struct thread_info *ti = current_thread_info(); + + /* Catch callers which need to be fixed */ + BUG_ON(ti->preempt_count || !irqs_disabled()); + + do { + add_preempt_count(PREEMPT_ACTIVE); + local_irq_enable(); + schedule(); + local_irq_disable(); + sub_preempt_count(PREEMPT_ACTIVE); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + barrier(); + } while (unlikely(test_thread_flag(TIF_NEED_RESCHED))); +} + +#endif /* CONFIG_PREEMPT */ + +int default_wake_function(wait_queue_t *curr, unsigned mode, int sync, + void *key) +{ + return try_to_wake_up(curr->private, mode, sync); +} +EXPORT_SYMBOL(default_wake_function); + +/* + * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just + * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve + * number) then we wake all the non-exclusive tasks and one exclusive task. + * + * There are circumstances in which we can try to wake a task which has already + * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns + * zero in this (rare) case, and we handle it by continuing to scan the queue. + */ +static void __wake_up_common(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, int sync, void *key) +{ + wait_queue_t *curr, *next; + + list_for_each_entry_safe(curr, next, &q->task_list, task_list) { + unsigned flags = curr->flags; + + if (curr->func(curr, mode, sync, key) && + (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive) + break; + } +} + +/** + * __wake_up - wake up threads blocked on a waitqueue. + * @q: the waitqueue + * @mode: which threads + * @nr_exclusive: how many wake-one or wake-many threads to wake up + * @key: is directly passed to the wakeup function + */ +void __wake_up(wait_queue_head_t *q, unsigned int mode, + int nr_exclusive, void *key) +{ + unsigned long flags; + + spin_lock_irqsave(&q->lock, flags); + __wake_up_common(q, mode, nr_exclusive, 0, key); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL(__wake_up); + +/* + * Same as __wake_up but called with the spinlock in wait_queue_head_t held. + */ +void __wake_up_locked(wait_queue_head_t *q, unsigned int mode) +{ + __wake_up_common(q, mode, 1, 0, NULL); +} + +/** + * __wake_up_sync - wake up threads blocked on a waitqueue. + * @q: the waitqueue + * @mode: which threads + * @nr_exclusive: how many wake-one or wake-many threads to wake up + * + * The sync wakeup differs that the waker knows that it will schedule + * away soon, so while the target thread will be woken up, it will not + * be migrated to another CPU - ie. the two threads are 'synchronized' + * with each other. This can prevent needless bouncing between CPUs. + * + * On UP it can prevent extra preemption. + */ +void +__wake_up_sync(wait_queue_head_t *q, unsigned int mode, int nr_exclusive) +{ + unsigned long flags; + int sync = 1; + + if (unlikely(!q)) + return; + + if (unlikely(!nr_exclusive)) + sync = 0; + + spin_lock_irqsave(&q->lock, flags); + __wake_up_common(q, mode, nr_exclusive, sync, NULL); + spin_unlock_irqrestore(&q->lock, flags); +} +EXPORT_SYMBOL_GPL(__wake_up_sync); /* For internal use only */ + +void complete(struct completion *x) +{ + unsigned long flags; + + spin_lock_irqsave(&x->wait.lock, flags); + x->done++; + __wake_up_common(&x->wait, TASK_NORMAL, 1, 0, NULL); + spin_unlock_irqrestore(&x->wait.lock, flags); +} +EXPORT_SYMBOL(complete); + +void complete_all(struct completion *x) +{ + unsigned long flags; + + spin_lock_irqsave(&x->wait.lock, flags); + x->done += UINT_MAX/2; + __wake_up_common(&x->wait, TASK_NORMAL, 0, 0, NULL); + spin_unlock_irqrestore(&x->wait.lock, flags); +} +EXPORT_SYMBOL(complete_all); + +static inline long __sched +do_wait_for_common(struct completion *x, long timeout, int state) +{ + if (!x->done) { + DECLARE_WAITQUEUE(wait, current); + + wait.flags |= WQ_FLAG_EXCLUSIVE; + __add_wait_queue_tail(&x->wait, &wait); + do { + if ((state == TASK_INTERRUPTIBLE && + signal_pending(current)) || + (state == TASK_KILLABLE && + fatal_signal_pending(current))) { + timeout = -ERESTARTSYS; + break; + } + __set_current_state(state); + spin_unlock_irq(&x->wait.lock); + timeout = schedule_timeout(timeout); + spin_lock_irq(&x->wait.lock); + } while (!x->done && timeout); + __remove_wait_queue(&x->wait, &wait); + if (!x->done) + return timeout; + } + x->done--; + return timeout ?: 1; +} + +static long __sched +wait_for_common(struct completion *x, long timeout, int state) +{ + might_sleep(); + + spin_lock_irq(&x->wait.lock); + timeout = do_wait_for_common(x, timeout, state); + spin_unlock_irq(&x->wait.lock); + return timeout; +} + +void __sched wait_for_completion(struct completion *x) +{ + wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion); + +unsigned long __sched +wait_for_completion_timeout(struct completion *x, unsigned long timeout) +{ + return wait_for_common(x, timeout, TASK_UNINTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_timeout); + +int __sched wait_for_completion_interruptible(struct completion *x) +{ + long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_INTERRUPTIBLE); + if (t == -ERESTARTSYS) + return t; + return 0; +} +EXPORT_SYMBOL(wait_for_completion_interruptible); + +unsigned long __sched +wait_for_completion_interruptible_timeout(struct completion *x, + unsigned long timeout) +{ + return wait_for_common(x, timeout, TASK_INTERRUPTIBLE); +} +EXPORT_SYMBOL(wait_for_completion_interruptible_timeout); + +int __sched wait_for_completion_killable(struct completion *x) +{ + long t = wait_for_common(x, MAX_SCHEDULE_TIMEOUT, TASK_KILLABLE); + if (t == -ERESTARTSYS) + return t; + return 0; +} +EXPORT_SYMBOL(wait_for_completion_killable); + +/** + * try_wait_for_completion - try to decrement a completion without blocking + * @x: completion structure + * + * Returns: 0 if a decrement cannot be done without blocking + * 1 if a decrement succeeded. + * + * If a completion is being used as a counting completion, + * attempt to decrement the counter without blocking. This + * enables us to avoid waiting if the resource the completion + * is protecting is not available. + */ +bool try_wait_for_completion(struct completion *x) +{ + int ret = 1; + + spin_lock_irq(&x->wait.lock); + if (!x->done) + ret = 0; + else + x->done--; + spin_unlock_irq(&x->wait.lock); + return ret; +} +EXPORT_SYMBOL(try_wait_for_completion); + +/** + * completion_done - Test to see if a completion has any waiters + * @x: completion structure + * + * Returns: 0 if there are waiters (wait_for_completion() in progress) + * 1 if there are no waiters. + * + */ +bool completion_done(struct completion *x) +{ + int ret = 1; + + spin_lock_irq(&x->wait.lock); + if (!x->done) + ret = 0; + spin_unlock_irq(&x->wait.lock); + return ret; +} +EXPORT_SYMBOL(completion_done); + +static long __sched +sleep_on_common(wait_queue_head_t *q, int state, long timeout) +{ + unsigned long flags; + wait_queue_t wait; + + init_waitqueue_entry(&wait, current); + + __set_current_state(state); + + spin_lock_irqsave(&q->lock, flags); + __add_wait_queue(q, &wait); + spin_unlock(&q->lock); + timeout = schedule_timeout(timeout); + spin_lock_irq(&q->lock); + __remove_wait_queue(q, &wait); + spin_unlock_irqrestore(&q->lock, flags); + + return timeout; +} + +void __sched interruptible_sleep_on(wait_queue_head_t *q) +{ + sleep_on_common(q, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); +} +EXPORT_SYMBOL(interruptible_sleep_on); + +long __sched +interruptible_sleep_on_timeout(wait_queue_head_t *q, long timeout) +{ + return sleep_on_common(q, TASK_INTERRUPTIBLE, timeout); +} +EXPORT_SYMBOL(interruptible_sleep_on_timeout); + +void __sched sleep_on(wait_queue_head_t *q) +{ + sleep_on_common(q, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT); +} +EXPORT_SYMBOL(sleep_on); + +long __sched sleep_on_timeout(wait_queue_head_t *q, long timeout) +{ + return sleep_on_common(q, TASK_UNINTERRUPTIBLE, timeout); +} +EXPORT_SYMBOL(sleep_on_timeout); + +#ifdef CONFIG_RT_MUTEXES + +/* + * rt_mutex_setprio - set the current priority of a task + * @p: task + * @prio: prio value (kernel-internal form) + * + * This function changes the 'effective' priority of a task. It does + * not touch ->normal_prio like __setscheduler(). + * + * Used by the rt_mutex code to implement priority inheritance logic. + */ +void rt_mutex_setprio(struct task_struct *p, int prio) +{ + unsigned long flags; + int oldprio, on_rq, running; + struct rq *rq; + const struct sched_class *prev_class = p->sched_class; + + BUG_ON(prio < 0 || prio > MAX_PRIO); + + rq = task_rq_lock(p, &flags); + update_rq_clock(rq); + + oldprio = p->prio; + on_rq = p->se.on_rq; + running = task_current(rq, p); + if (on_rq) + dequeue_task(rq, p, 0); + if (running) + p->sched_class->put_prev_task(rq, p); + + if (rt_prio(prio)) + p->sched_class = &rt_sched_class; + else + p->sched_class = &fair_sched_class; + + p->prio = prio; + + if (running) + p->sched_class->set_curr_task(rq); + if (on_rq) { + enqueue_task(rq, p, 0); + + check_class_changed(rq, p, prev_class, oldprio, running); + } + task_rq_unlock(rq, &flags); +} + +#endif + +void set_user_nice(struct task_struct *p, long nice) +{ + int old_prio, delta, on_rq; + unsigned long flags; + struct rq *rq; + + if (TASK_NICE(p) == nice || nice < -20 || nice > 19) + return; + /* + * We have to be careful, if called from sys_setpriority(), + * the task might be in the middle of scheduling on another CPU. + */ + rq = task_rq_lock(p, &flags); + update_rq_clock(rq); + /* + * The RT priorities are set via sched_setscheduler(), but we still + * allow the 'normal' nice value to be set - but as expected + * it wont have any effect on scheduling until the task is + * SCHED_FIFO/SCHED_RR: + */ + if (task_has_rt_policy(p)) { + p->static_prio = NICE_TO_PRIO(nice); + goto out_unlock; + } + on_rq = p->se.on_rq; + if (on_rq) + dequeue_task(rq, p, 0); + + p->static_prio = NICE_TO_PRIO(nice); + set_load_weight(p); + old_prio = p->prio; + p->prio = effective_prio(p); + delta = p->prio - old_prio; + + if (on_rq) { + enqueue_task(rq, p, 0); + /* + * If the task increased its priority or is running and + * lowered its priority, then reschedule its CPU: + */ + if (delta < 0 || (delta > 0 && task_running(rq, p))) + resched_task(rq->curr); + } +out_unlock: + task_rq_unlock(rq, &flags); +} +EXPORT_SYMBOL(set_user_nice); + +/* + * can_nice - check if a task can reduce its nice value + * @p: task + * @nice: nice value + */ +int can_nice(const struct task_struct *p, const int nice) +{ + /* convert nice value [19,-20] to rlimit style value [1,40] */ + int nice_rlim = 20 - nice; + + return (nice_rlim <= p->signal->rlim[RLIMIT_NICE].rlim_cur || + capable(CAP_SYS_NICE)); +} + +#ifdef __ARCH_WANT_SYS_NICE + +/* + * sys_nice - change the priority of the current process. + * @increment: priority increment + * + * sys_setpriority is a more generic, but much slower function that + * does similar things. + */ +SYSCALL_DEFINE1(nice, int, increment) +{ + long nice, retval; + + /* + * Setpriority might change our priority at the same moment. + * We don't have to worry. Conceptually one call occurs first + * and we have a single winner. + */ + if (increment < -40) + increment = -40; + if (increment > 40) + increment = 40; + + nice = PRIO_TO_NICE(current->static_prio) + increment; + if (nice < -20) + nice = -20; + if (nice > 19) + nice = 19; + + if (increment < 0 && !can_nice(current, nice)) + return vx_flags(VXF_IGNEG_NICE, 0) ? 0 : -EPERM; + + retval = security_task_setnice(current, nice); + if (retval) + return retval; + + set_user_nice(current, nice); + return 0; +} + +#endif + +/** + * task_prio - return the priority value of a given task. + * @p: the task in question. + * + * This is the priority value as seen by users in /proc. + * RT tasks are offset by -200. Normal tasks are centered + * around 0, value goes from -16 to +15. + */ +int task_prio(const struct task_struct *p) +{ + return p->prio - MAX_RT_PRIO; +} + +/** + * task_nice - return the nice value of a given task. + * @p: the task in question. + */ +int task_nice(const struct task_struct *p) +{ + return TASK_NICE(p); +} +EXPORT_SYMBOL(task_nice); + +/** + * idle_cpu - is a given cpu idle currently? + * @cpu: the processor in question. + */ +int idle_cpu(int cpu) +{ + return cpu_curr(cpu) == cpu_rq(cpu)->idle; +} + +/** + * idle_task - return the idle task for a given cpu. + * @cpu: the processor in question. + */ +struct task_struct *idle_task(int cpu) +{ + return cpu_rq(cpu)->idle; +} + +/** + * find_process_by_pid - find a process with a matching PID value. + * @pid: the pid in question. + */ +static struct task_struct *find_process_by_pid(pid_t pid) +{ + return pid ? find_task_by_vpid(pid) : current; +} + +/* Actually do priority change: must hold rq lock. */ +static void +__setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) +{ + BUG_ON(p->se.on_rq); + + p->policy = policy; + switch (p->policy) { + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_IDLE: + p->sched_class = &fair_sched_class; + break; + case SCHED_FIFO: + case SCHED_RR: + p->sched_class = &rt_sched_class; + break; + } + + p->rt_priority = prio; + p->normal_prio = normal_prio(p); + /* we are holding p->pi_lock already */ + p->prio = rt_mutex_getprio(p); + set_load_weight(p); +} + +static int __sched_setscheduler(struct task_struct *p, int policy, + struct sched_param *param, bool user) +{ + int retval, oldprio, oldpolicy = -1, on_rq, running; + unsigned long flags; + const struct sched_class *prev_class = p->sched_class; + struct rq *rq; + + /* may grab non-irq protected spin_locks */ + BUG_ON(in_interrupt()); +recheck: + /* double check policy once rq lock held */ + if (policy < 0) + policy = oldpolicy = p->policy; + else if (policy != SCHED_FIFO && policy != SCHED_RR && + policy != SCHED_NORMAL && policy != SCHED_BATCH && + policy != SCHED_IDLE) + return -EINVAL; + /* + * Valid priorities for SCHED_FIFO and SCHED_RR are + * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL, + * SCHED_BATCH and SCHED_IDLE is 0. + */ + if (param->sched_priority < 0 || + (p->mm && param->sched_priority > MAX_USER_RT_PRIO-1) || + (!p->mm && param->sched_priority > MAX_RT_PRIO-1)) + return -EINVAL; + if (rt_policy(policy) != (param->sched_priority != 0)) + return -EINVAL; + + /* + * Allow unprivileged RT tasks to decrease priority: + */ + if (user && !capable(CAP_SYS_NICE)) { + if (rt_policy(policy)) { + unsigned long rlim_rtprio; + + if (!lock_task_sighand(p, &flags)) + return -ESRCH; + rlim_rtprio = p->signal->rlim[RLIMIT_RTPRIO].rlim_cur; + unlock_task_sighand(p, &flags); + + /* can't set/change the rt policy */ + if (policy != p->policy && !rlim_rtprio) + return -EPERM; + + /* can't increase priority */ + if (param->sched_priority > p->rt_priority && + param->sched_priority > rlim_rtprio) + return -EPERM; + } + /* + * Like positive nice levels, dont allow tasks to + * move out of SCHED_IDLE either: + */ + if (p->policy == SCHED_IDLE && policy != SCHED_IDLE) + return -EPERM; + + /* can't change other user's priorities */ + if ((current->euid != p->euid) && + (current->euid != p->uid)) + return -EPERM; + } + + if (user) { +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Do not allow realtime tasks into groups that have no runtime + * assigned. + */ + if (rt_policy(policy) && task_group(p)->rt_bandwidth.rt_runtime == 0) + return -EPERM; +#endif + + retval = security_task_setscheduler(p, policy, param); + if (retval) + return retval; + } + + /* + * make sure no PI-waiters arrive (or leave) while we are + * changing the priority of the task: + */ + spin_lock_irqsave(&p->pi_lock, flags); + /* + * To be able to change p->policy safely, the apropriate + * runqueue lock must be held. + */ + rq = __task_rq_lock(p); + /* recheck policy now with rq lock held */ + if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { + policy = oldpolicy = -1; + __task_rq_unlock(rq); + spin_unlock_irqrestore(&p->pi_lock, flags); + goto recheck; + } + update_rq_clock(rq); + on_rq = p->se.on_rq; + running = task_current(rq, p); + if (on_rq) + deactivate_task(rq, p, 0); + if (running) + p->sched_class->put_prev_task(rq, p); + + oldprio = p->prio; + __setscheduler(rq, p, policy, param->sched_priority); + + if (running) + p->sched_class->set_curr_task(rq); + if (on_rq) { + activate_task(rq, p, 0); + + check_class_changed(rq, p, prev_class, oldprio, running); + } + __task_rq_unlock(rq); + spin_unlock_irqrestore(&p->pi_lock, flags); + + rt_mutex_adjust_pi(p); + + return 0; +} + +/** + * sched_setscheduler - change the scheduling policy and/or RT priority of a thread. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * NOTE that the task may be already dead. + */ +int sched_setscheduler(struct task_struct *p, int policy, + struct sched_param *param) +{ + return __sched_setscheduler(p, policy, param, true); +} +EXPORT_SYMBOL_GPL(sched_setscheduler); + +/** + * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace. + * @p: the task in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + * + * Just like sched_setscheduler, only don't bother checking if the + * current context has permission. For example, this is needed in + * stop_machine(): we create temporary high priority worker threads, + * but our caller might not have that capability. + */ +int sched_setscheduler_nocheck(struct task_struct *p, int policy, + struct sched_param *param) +{ + return __sched_setscheduler(p, policy, param, false); +} + +static int +do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param) +{ + struct sched_param lparam; + struct task_struct *p; + int retval; + + if (!param || pid < 0) + return -EINVAL; + if (copy_from_user(&lparam, param, sizeof(struct sched_param))) + return -EFAULT; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (p != NULL) + retval = sched_setscheduler(p, policy, &lparam); + rcu_read_unlock(); + + return retval; +} + +/** + * sys_sched_setscheduler - set/change the scheduler policy and RT priority + * @pid: the pid in question. + * @policy: new policy. + * @param: structure containing the new RT priority. + */ +SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, + struct sched_param __user *, param) +{ + /* negative values for policy are not valid */ + if (policy < 0) + return -EINVAL; + + return do_sched_setscheduler(pid, policy, param); +} + +/** + * sys_sched_setparam - set/change the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the new RT priority. + */ +SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) +{ + return do_sched_setscheduler(pid, -1, param); +} + +/** + * sys_sched_getscheduler - get the policy (scheduling class) of a thread + * @pid: the pid in question. + */ +SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) +{ + struct task_struct *p; + int retval; + + if (pid < 0) + return -EINVAL; + + retval = -ESRCH; + read_lock(&tasklist_lock); + p = find_process_by_pid(pid); + if (p) { + retval = security_task_getscheduler(p); + if (!retval) + retval = p->policy; + } + read_unlock(&tasklist_lock); + return retval; +} + +/** + * sys_sched_getscheduler - get the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the RT priority. + */ +SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) +{ + struct sched_param lp; + struct task_struct *p; + int retval; + + if (!param || pid < 0) + return -EINVAL; + + read_lock(&tasklist_lock); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + lp.sched_priority = p->rt_priority; + read_unlock(&tasklist_lock); + + /* + * This one might sleep, we cannot do it with a spinlock held ... + */ + retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; + + return retval; + +out_unlock: + read_unlock(&tasklist_lock); + return retval; +} + +long sched_setaffinity(pid_t pid, const cpumask_t *in_mask) +{ + cpumask_t cpus_allowed; + cpumask_t new_mask = *in_mask; + struct task_struct *p; + int retval; + + get_online_cpus(); + read_lock(&tasklist_lock); + + p = find_process_by_pid(pid); + if (!p) { + read_unlock(&tasklist_lock); + put_online_cpus(); + return -ESRCH; + } + + /* + * It is not safe to call set_cpus_allowed with the + * tasklist_lock held. We will bump the task_struct's + * usage count and then drop tasklist_lock. + */ + get_task_struct(p); + read_unlock(&tasklist_lock); + + + retval = -EPERM; + if ((current->euid != p->euid) && (current->euid != p->uid) && + !capable(CAP_SYS_NICE)) + goto out_unlock; + + retval = security_task_setscheduler(p, 0, NULL); + if (retval) + goto out_unlock; + + cpuset_cpus_allowed(p, &cpus_allowed); + cpus_and(new_mask, new_mask, cpus_allowed); + again: + retval = set_cpus_allowed_ptr(p, &new_mask); + + if (!retval) { + cpuset_cpus_allowed(p, &cpus_allowed); + if (!cpus_subset(new_mask, cpus_allowed)) { + /* + * We must have raced with a concurrent cpuset + * update. Just reset the cpus_allowed to the + * cpuset's cpus_allowed + */ + new_mask = cpus_allowed; + goto again; + } + } +out_unlock: + put_task_struct(p); + put_online_cpus(); + return retval; +} + +static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len, + cpumask_t *new_mask) +{ + if (len < sizeof(cpumask_t)) { + memset(new_mask, 0, sizeof(cpumask_t)); + } else if (len > sizeof(cpumask_t)) { + len = sizeof(cpumask_t); + } + return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0; +} + +/** + * sys_sched_setaffinity - set the cpu affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to the new cpu mask + */ +SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + cpumask_t new_mask; + int retval; + + retval = get_user_cpu_mask(user_mask_ptr, len, &new_mask); + if (retval) + return retval; + + return sched_setaffinity(pid, &new_mask); +} + +long sched_getaffinity(pid_t pid, cpumask_t *mask) +{ + struct task_struct *p; + int retval; + + get_online_cpus(); + read_lock(&tasklist_lock); + + retval = -ESRCH; + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + cpus_and(*mask, p->cpus_allowed, cpu_online_map); + +out_unlock: + read_unlock(&tasklist_lock); + put_online_cpus(); + + return retval; +} + +/** + * sys_sched_getaffinity - get the cpu affinity of a process + * @pid: pid of the process + * @len: length in bytes of the bitmask pointed to by user_mask_ptr + * @user_mask_ptr: user-space pointer to hold the current cpu mask + */ +SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + int ret; + cpumask_t mask; + + if (len < sizeof(cpumask_t)) + return -EINVAL; + + ret = sched_getaffinity(pid, &mask); + if (ret < 0) + return ret; + + if (copy_to_user(user_mask_ptr, &mask, sizeof(cpumask_t))) + return -EFAULT; + + return sizeof(cpumask_t); +} + +/** + * sys_sched_yield - yield the current processor to other threads. + * + * This function yields the current CPU to other tasks. If there are no + * other threads running on this CPU then this function will return. + */ +SYSCALL_DEFINE0(sched_yield) +{ + struct rq *rq = this_rq_lock(); + + schedstat_inc(rq, yld_count); + current->sched_class->yield_task(rq); + + /* + * Since we are going to call schedule() anyway, there's + * no need to preempt or enable interrupts: + */ + __release(rq->lock); + spin_release(&rq->lock.dep_map, 1, _THIS_IP_); + _raw_spin_unlock(&rq->lock); + preempt_enable_no_resched(); + + schedule(); + + return 0; +} + +static void __cond_resched(void) +{ +#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP + __might_sleep(__FILE__, __LINE__); +#endif + /* + * The BKS might be reacquired before we have dropped + * PREEMPT_ACTIVE, which could trigger a second + * cond_resched() call. + */ + do { + add_preempt_count(PREEMPT_ACTIVE); + schedule(); + sub_preempt_count(PREEMPT_ACTIVE); + } while (need_resched()); +} + +int __sched _cond_resched(void) +{ + if (need_resched() && !(preempt_count() & PREEMPT_ACTIVE) && + system_state == SYSTEM_RUNNING) { + __cond_resched(); + return 1; + } + return 0; +} +EXPORT_SYMBOL(_cond_resched); + +/* + * cond_resched_lock() - if a reschedule is pending, drop the given lock, + * call schedule, and on return reacquire the lock. + * + * This works OK both with and without CONFIG_PREEMPT. We do strange low-level + * operations here to prevent schedule() from being called twice (once via + * spin_unlock(), once by hand). + */ +int cond_resched_lock(spinlock_t *lock) +{ + int resched = need_resched() && system_state == SYSTEM_RUNNING; + int ret = 0; + + if (spin_needbreak(lock) || resched) { + spin_unlock(lock); + if (resched && need_resched()) + __cond_resched(); + else + cpu_relax(); + ret = 1; + spin_lock(lock); + } + return ret; +} +EXPORT_SYMBOL(cond_resched_lock); + +int __sched cond_resched_softirq(void) +{ + BUG_ON(!in_softirq()); + + if (need_resched() && system_state == SYSTEM_RUNNING) { + local_bh_enable(); + __cond_resched(); + local_bh_disable(); + return 1; + } + return 0; +} +EXPORT_SYMBOL(cond_resched_softirq); + +/** + * yield - yield the current processor to other threads. + * + * This is a shortcut for kernel-space yielding - it marks the + * thread runnable and calls sys_sched_yield(). + */ +void __sched yield(void) +{ + set_current_state(TASK_RUNNING); + sys_sched_yield(); +} +EXPORT_SYMBOL(yield); + +/* + * This task is about to go to sleep on IO. Increment rq->nr_iowait so + * that process accounting knows that this is a task in IO wait state. + * + * But don't do that if it is a deliberate, throttling IO wait (this task + * has set its backing_dev_info: the queue against which it should throttle) + */ +void __sched io_schedule(void) +{ + struct rq *rq = &__raw_get_cpu_var(runqueues); + + delayacct_blkio_start(); + atomic_inc(&rq->nr_iowait); + schedule(); + atomic_dec(&rq->nr_iowait); + delayacct_blkio_end(); +} +EXPORT_SYMBOL(io_schedule); + +long __sched io_schedule_timeout(long timeout) +{ + struct rq *rq = &__raw_get_cpu_var(runqueues); + long ret; + + delayacct_blkio_start(); + atomic_inc(&rq->nr_iowait); + ret = schedule_timeout(timeout); + atomic_dec(&rq->nr_iowait); + delayacct_blkio_end(); + return ret; +} + +/** + * sys_sched_get_priority_max - return maximum RT priority. + * @policy: scheduling class. + * + * this syscall returns the maximum rt_priority that can be used + * by a given scheduling class. + */ +SYSCALL_DEFINE1(sched_get_priority_max, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = MAX_USER_RT_PRIO-1; + break; + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_IDLE: + ret = 0; + break; + } + return ret; +} + +/** + * sys_sched_get_priority_min - return minimum RT priority. + * @policy: scheduling class. + * + * this syscall returns the minimum rt_priority that can be used + * by a given scheduling class. + */ +SYSCALL_DEFINE1(sched_get_priority_min, int, policy) +{ + int ret = -EINVAL; + + switch (policy) { + case SCHED_FIFO: + case SCHED_RR: + ret = 1; + break; + case SCHED_NORMAL: + case SCHED_BATCH: + case SCHED_IDLE: + ret = 0; + } + return ret; +} + +/** + * sys_sched_rr_get_interval - return the default timeslice of a process. + * @pid: pid of the process. + * @interval: userspace pointer to the timeslice value. + * + * this syscall writes the default timeslice value of a given process + * into the user-space timespec buffer. A value of '0' means infinity. + */ +SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, + struct timespec __user *, interval) +{ + struct task_struct *p; + unsigned int time_slice; + int retval; + struct timespec t; + + if (pid < 0) + return -EINVAL; + + retval = -ESRCH; + read_lock(&tasklist_lock); + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + /* + * Time slice is 0 for SCHED_FIFO tasks and for SCHED_OTHER + * tasks that are on an otherwise idle runqueue: + */ + time_slice = 0; + if (p->policy == SCHED_RR) { + time_slice = DEF_TIMESLICE; + } else if (p->policy != SCHED_FIFO) { + struct sched_entity *se = &p->se; + unsigned long flags; + struct rq *rq; + + rq = task_rq_lock(p, &flags); + if (rq->cfs.load.weight) + time_slice = NS_TO_JIFFIES(sched_slice(&rq->cfs, se)); + task_rq_unlock(rq, &flags); + } + read_unlock(&tasklist_lock); + jiffies_to_timespec(time_slice, &t); + retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; + return retval; + +out_unlock: + read_unlock(&tasklist_lock); + return retval; +} + +static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; + +void sched_show_task(struct task_struct *p) +{ + unsigned long free = 0; + unsigned state; + + state = p->state ? __ffs(p->state) + 1 : 0; + printk(KERN_INFO "%-13.13s %c", p->comm, + state < sizeof(stat_nam) - 1 ? stat_nam[state] : '?'); +#if BITS_PER_LONG == 32 + if (state == TASK_RUNNING) + printk(KERN_CONT " running "); + else + printk(KERN_CONT " %08lx ", thread_saved_pc(p)); +#else + if (state == TASK_RUNNING) + printk(KERN_CONT " running task "); + else + printk(KERN_CONT " %016lx ", thread_saved_pc(p)); +#endif +#ifdef CONFIG_DEBUG_STACK_USAGE + { + unsigned long *n = end_of_stack(p); + while (!*n) + n++; + free = (unsigned long)n - (unsigned long)end_of_stack(p); + } +#endif + printk(KERN_CONT "%5lu %5d %6d\n", free, + task_pid_nr(p), task_pid_nr(p->real_parent)); + + show_stack(p, NULL); +} + +void show_state_filter(unsigned long state_filter) +{ + struct task_struct *g, *p; + +#if BITS_PER_LONG == 32 + printk(KERN_INFO + " task PC stack pid father\n"); +#else + printk(KERN_INFO + " task PC stack pid father\n"); +#endif + read_lock(&tasklist_lock); + do_each_thread(g, p) { + /* + * reset the NMI-timeout, listing all files on a slow + * console might take alot of time: + */ + touch_nmi_watchdog(); + if (!state_filter || (p->state & state_filter)) + sched_show_task(p); + } while_each_thread(g, p); + + touch_all_softlockup_watchdogs(); + +#ifdef CONFIG_SCHED_DEBUG + sysrq_sched_debug_show(); +#endif + read_unlock(&tasklist_lock); + /* + * Only show locks if all tasks are dumped: + */ + if (state_filter == -1) + debug_show_all_locks(); +} + +void __cpuinit init_idle_bootup_task(struct task_struct *idle) +{ + idle->sched_class = &idle_sched_class; +} + +/** + * init_idle - set up an idle thread for a given CPU + * @idle: task in question + * @cpu: cpu the idle task belongs to + * + * NOTE: this function does not set the idle thread's NEED_RESCHED + * flag, to make booting more robust. + */ +void __cpuinit init_idle(struct task_struct *idle, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + __sched_fork(idle); + idle->se.exec_start = sched_clock(); + + idle->prio = idle->normal_prio = MAX_PRIO; + idle->cpus_allowed = cpumask_of_cpu(cpu); + __set_task_cpu(idle, cpu); + + spin_lock_irqsave(&rq->lock, flags); + rq->curr = rq->idle = idle; +#if defined(CONFIG_SMP) && defined(__ARCH_WANT_UNLOCKED_CTXSW) + idle->oncpu = 1; +#endif + spin_unlock_irqrestore(&rq->lock, flags); + + /* Set the preempt count _outside_ the spinlocks! */ +#if defined(CONFIG_PREEMPT) + task_thread_info(idle)->preempt_count = (idle->lock_depth >= 0); +#else + task_thread_info(idle)->preempt_count = 0; +#endif + /* + * The idle tasks have their own, simple scheduling class: + */ + idle->sched_class = &idle_sched_class; +} + +/* + * In a system that switches off the HZ timer nohz_cpu_mask + * indicates which cpus entered this state. This is used + * in the rcu update to wait only for active cpus. For system + * which do not switch off the HZ timer nohz_cpu_mask should + * always be CPU_MASK_NONE. + */ +cpumask_t nohz_cpu_mask = CPU_MASK_NONE; + +/* + * Increase the granularity value when there are more CPUs, + * because with more CPUs the 'effective latency' as visible + * to users decreases. But the relationship is not linear, + * so pick a second-best guess by going with the log2 of the + * number of CPUs. + * + * This idea comes from the SD scheduler of Con Kolivas: + */ +static inline void sched_init_granularity(void) +{ + unsigned int factor = 1 + ilog2(num_online_cpus()); + const unsigned long limit = 200000000; + + sysctl_sched_min_granularity *= factor; + if (sysctl_sched_min_granularity > limit) + sysctl_sched_min_granularity = limit; + + sysctl_sched_latency *= factor; + if (sysctl_sched_latency > limit) + sysctl_sched_latency = limit; + + sysctl_sched_wakeup_granularity *= factor; + + sysctl_sched_shares_ratelimit *= factor; +} + +#ifdef CONFIG_SMP +/* + * This is how migration works: + * + * 1) we queue a struct migration_req structure in the source CPU's + * runqueue and wake up that CPU's migration thread. + * 2) we down() the locked semaphore => thread blocks. + * 3) migration thread wakes up (implicitly it forces the migrated + * thread off the CPU) + * 4) it gets the migration request and checks whether the migrated + * task is still in the wrong runqueue. + * 5) if it's in the wrong runqueue then the migration thread removes + * it and puts it into the right queue. + * 6) migration thread up()s the semaphore. + * 7) we wake up and the migration is done. + */ + +/* + * Change a given task's CPU affinity. Migrate the thread to a + * proper CPU and schedule it away if the CPU it's executing on + * is removed from the allowed bitmask. + * + * NOTE: the caller must have a valid reference to the task, the + * task must not exit() & deallocate itself prematurely. The + * call is not atomic; no spinlocks may be held. + */ +int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask) +{ + struct migration_req req; + unsigned long flags; + struct rq *rq; + int ret = 0; + + rq = task_rq_lock(p, &flags); + if (!cpus_intersects(*new_mask, cpu_online_map)) { + ret = -EINVAL; + goto out; + } + + if (unlikely((p->flags & PF_THREAD_BOUND) && p != current && + !cpus_equal(p->cpus_allowed, *new_mask))) { + ret = -EINVAL; + goto out; + } + + if (p->sched_class->set_cpus_allowed) + p->sched_class->set_cpus_allowed(p, new_mask); + else { + p->cpus_allowed = *new_mask; + p->rt.nr_cpus_allowed = cpus_weight(*new_mask); + } + + /* Can the task run on the task's current CPU? If so, we're done */ + if (cpu_isset(task_cpu(p), *new_mask)) + goto out; + + if (migrate_task(p, any_online_cpu(*new_mask), &req)) { + /* Need help from migration thread: drop lock and wait. */ + task_rq_unlock(rq, &flags); + wake_up_process(rq->migration_thread); + wait_for_completion(&req.done); + tlb_migrate_finish(p->mm); + return 0; + } +out: + task_rq_unlock(rq, &flags); + + return ret; +} +EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); + +/* + * Move (not current) task off this cpu, onto dest cpu. We're doing + * this because either it can't run here any more (set_cpus_allowed() + * away from this CPU, or CPU going down), or because we're + * attempting to rebalance this task on exec (sched_exec). + * + * So we race with normal scheduler movements, but that's OK, as long + * as the task is no longer on this CPU. + * + * Returns non-zero if task was successfully migrated. + */ +static int __migrate_task(struct task_struct *p, int src_cpu, int dest_cpu) +{ + struct rq *rq_dest, *rq_src; + int ret = 0, on_rq; + + if (unlikely(!cpu_active(dest_cpu))) + return ret; + + rq_src = cpu_rq(src_cpu); + rq_dest = cpu_rq(dest_cpu); + + double_rq_lock(rq_src, rq_dest); + /* Already moved. */ + if (task_cpu(p) != src_cpu) + goto done; + /* Affinity changed (again). */ + if (!cpu_isset(dest_cpu, p->cpus_allowed)) + goto fail; + + on_rq = p->se.on_rq; + if (on_rq) + deactivate_task(rq_src, p, 0); + + set_task_cpu(p, dest_cpu); + if (on_rq) { + activate_task(rq_dest, p, 0); + check_preempt_curr(rq_dest, p); + } +done: + ret = 1; +fail: + double_rq_unlock(rq_src, rq_dest); + return ret; +} + +/* + * migration_thread - this is a highprio system thread that performs + * thread migration by bumping thread off CPU then 'pushing' onto + * another runqueue. + */ +static int migration_thread(void *data) +{ + int cpu = (long)data; + struct rq *rq; + + rq = cpu_rq(cpu); + BUG_ON(rq->migration_thread != current); + + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + struct migration_req *req; + struct list_head *head; + + spin_lock_irq(&rq->lock); + + if (cpu_is_offline(cpu)) { + spin_unlock_irq(&rq->lock); + goto wait_to_die; + } + + if (rq->active_balance) { + active_load_balance(rq, cpu); + rq->active_balance = 0; + } + + head = &rq->migration_queue; + + if (list_empty(head)) { + spin_unlock_irq(&rq->lock); + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + continue; + } + req = list_entry(head->next, struct migration_req, list); + list_del_init(head->next); + + spin_unlock(&rq->lock); + __migrate_task(req->task, cpu, req->dest_cpu); + local_irq_enable(); + + complete(&req->done); + } + __set_current_state(TASK_RUNNING); + return 0; + +wait_to_die: + /* Wait for kthread_stop */ + set_current_state(TASK_INTERRUPTIBLE); + while (!kthread_should_stop()) { + schedule(); + set_current_state(TASK_INTERRUPTIBLE); + } + __set_current_state(TASK_RUNNING); + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU + +static int __migrate_task_irq(struct task_struct *p, int src_cpu, int dest_cpu) +{ + int ret; + + local_irq_disable(); + ret = __migrate_task(p, src_cpu, dest_cpu); + local_irq_enable(); + return ret; +} + +/* + * Figure out where task on dead CPU should go, use force if necessary. + * NOTE: interrupts should be disabled by the caller + */ +static void move_task_off_dead_cpu(int dead_cpu, struct task_struct *p) +{ + unsigned long flags; + cpumask_t mask; + struct rq *rq; + int dest_cpu; + + do { + /* On same node? */ + mask = node_to_cpumask(cpu_to_node(dead_cpu)); + cpus_and(mask, mask, p->cpus_allowed); + dest_cpu = any_online_cpu(mask); + + /* On any allowed CPU? */ + if (dest_cpu >= nr_cpu_ids) + dest_cpu = any_online_cpu(p->cpus_allowed); + + /* No more Mr. Nice Guy. */ + if (dest_cpu >= nr_cpu_ids) { + cpumask_t cpus_allowed; + + cpuset_cpus_allowed_locked(p, &cpus_allowed); + /* + * Try to stay on the same cpuset, where the + * current cpuset may be a subset of all cpus. + * The cpuset_cpus_allowed_locked() variant of + * cpuset_cpus_allowed() will not block. It must be + * called within calls to cpuset_lock/cpuset_unlock. + */ + rq = task_rq_lock(p, &flags); + p->cpus_allowed = cpus_allowed; + dest_cpu = any_online_cpu(p->cpus_allowed); + task_rq_unlock(rq, &flags); + + /* + * Don't tell them about moving exiting tasks or + * kernel threads (both mm NULL), since they never + * leave kernel. + */ + if (p->mm && printk_ratelimit()) { + printk(KERN_INFO "process %d (%s) no " + "longer affine to cpu%d\n", + task_pid_nr(p), p->comm, dead_cpu); + } + } + } while (!__migrate_task_irq(p, dead_cpu, dest_cpu)); +} + +/* + * While a dead CPU has no uninterruptible tasks queued at this point, + * it might still have a nonzero ->nr_uninterruptible counter, because + * for performance reasons the counter is not stricly tracking tasks to + * their home CPUs. So we just add the counter to another CPU's counter, + * to keep the global sum constant after CPU-down: + */ +static void migrate_nr_uninterruptible(struct rq *rq_src) +{ + struct rq *rq_dest = cpu_rq(any_online_cpu(*CPU_MASK_ALL_PTR)); + unsigned long flags; + + local_irq_save(flags); + double_rq_lock(rq_src, rq_dest); + rq_dest->nr_uninterruptible += rq_src->nr_uninterruptible; + rq_src->nr_uninterruptible = 0; + double_rq_unlock(rq_src, rq_dest); + local_irq_restore(flags); +} + +/* Run through task list and migrate tasks from the dead cpu. */ +static void migrate_live_tasks(int src_cpu) +{ + struct task_struct *p, *t; + + read_lock(&tasklist_lock); + + do_each_thread(t, p) { + if (p == current) + continue; + + if (task_cpu(p) == src_cpu) + move_task_off_dead_cpu(src_cpu, p); + } while_each_thread(t, p); + + read_unlock(&tasklist_lock); +} + +/* + * Schedules idle task to be the next runnable task on current CPU. + * It does so by boosting its priority to highest possible. + * Used by CPU offline code. + */ +void sched_idle_next(void) +{ + int this_cpu = smp_processor_id(); + struct rq *rq = cpu_rq(this_cpu); + struct task_struct *p = rq->idle; + unsigned long flags; + + /* cpu has to be offline */ + BUG_ON(cpu_online(this_cpu)); + + /* + * Strictly not necessary since rest of the CPUs are stopped by now + * and interrupts disabled on the current cpu. + */ + spin_lock_irqsave(&rq->lock, flags); + + __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); + + update_rq_clock(rq); + activate_task(rq, p, 0); + + spin_unlock_irqrestore(&rq->lock, flags); +} + +/* + * Ensures that the idle task is using init_mm right before its cpu goes + * offline. + */ +void idle_task_exit(void) +{ + struct mm_struct *mm = current->active_mm; + + BUG_ON(cpu_online(smp_processor_id())); + + if (mm != &init_mm) + switch_mm(mm, &init_mm, current); + mmdrop(mm); +} + +/* called under rq->lock with disabled interrupts */ +static void migrate_dead(unsigned int dead_cpu, struct task_struct *p) +{ + struct rq *rq = cpu_rq(dead_cpu); + + /* Must be exiting, otherwise would be on tasklist. */ + BUG_ON(!p->exit_state); + + /* Cannot have done final schedule yet: would have vanished. */ + BUG_ON(p->state == TASK_DEAD); + + get_task_struct(p); + + /* + * Drop lock around migration; if someone else moves it, + * that's OK. No task can be added to this CPU, so iteration is + * fine. + */ + spin_unlock_irq(&rq->lock); + move_task_off_dead_cpu(dead_cpu, p); + spin_lock_irq(&rq->lock); + + put_task_struct(p); +} + +/* release_task() removes task from tasklist, so we won't find dead tasks. */ +static void migrate_dead_tasks(unsigned int dead_cpu) +{ + struct rq *rq = cpu_rq(dead_cpu); + struct task_struct *next; + + for ( ; ; ) { + if (!rq->nr_running) + break; + update_rq_clock(rq); + next = pick_next_task(rq, rq->curr); + if (!next) + break; + next->sched_class->put_prev_task(rq, next); + migrate_dead(dead_cpu, next); + + } +} +#endif /* CONFIG_HOTPLUG_CPU */ + +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) + +static struct ctl_table sd_ctl_dir[] = { + { + .procname = "sched_domain", + .mode = 0555, + }, + {0, }, +}; + +static struct ctl_table sd_ctl_root[] = { + { + .ctl_name = CTL_KERN, + .procname = "kernel", + .mode = 0555, + .child = sd_ctl_dir, + }, + {0, }, +}; + +static struct ctl_table *sd_alloc_ctl_entry(int n) +{ + struct ctl_table *entry = + kcalloc(n, sizeof(struct ctl_table), GFP_KERNEL); + + return entry; +} + +static void sd_free_ctl_entry(struct ctl_table **tablep) +{ + struct ctl_table *entry; + + /* + * In the intermediate directories, both the child directory and + * procname are dynamically allocated and could fail but the mode + * will always be set. In the lowest directory the names are + * static strings and all have proc handlers. + */ + for (entry = *tablep; entry->mode; entry++) { + if (entry->child) + sd_free_ctl_entry(&entry->child); + if (entry->proc_handler == NULL) + kfree(entry->procname); + } + + kfree(*tablep); + *tablep = NULL; +} + +static void +set_table_entry(struct ctl_table *entry, + const char *procname, void *data, int maxlen, + mode_t mode, proc_handler *proc_handler) +{ + entry->procname = procname; + entry->data = data; + entry->maxlen = maxlen; + entry->mode = mode; + entry->proc_handler = proc_handler; +} + +static struct ctl_table * +sd_alloc_ctl_domain_table(struct sched_domain *sd) +{ + struct ctl_table *table = sd_alloc_ctl_entry(12); + + if (table == NULL) + return NULL; + + set_table_entry(&table[0], "min_interval", &sd->min_interval, + sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[1], "max_interval", &sd->max_interval, + sizeof(long), 0644, proc_doulongvec_minmax); + set_table_entry(&table[2], "busy_idx", &sd->busy_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[3], "idle_idx", &sd->idle_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[5], "wake_idx", &sd->wake_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[7], "busy_factor", &sd->busy_factor, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[9], "cache_nice_tries", + &sd->cache_nice_tries, + sizeof(int), 0644, proc_dointvec_minmax); + set_table_entry(&table[10], "flags", &sd->flags, + sizeof(int), 0644, proc_dointvec_minmax); + /* &table[11] is terminator */ + + return table; +} + +static ctl_table *sd_alloc_ctl_cpu_table(int cpu) +{ + struct ctl_table *entry, *table; + struct sched_domain *sd; + int domain_num = 0, i; + char buf[32]; + + for_each_domain(cpu, sd) + domain_num++; + entry = table = sd_alloc_ctl_entry(domain_num + 1); + if (table == NULL) + return NULL; + + i = 0; + for_each_domain(cpu, sd) { + snprintf(buf, 32, "domain%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_domain_table(sd); + entry++; + i++; + } + return table; +} + +static struct ctl_table_header *sd_sysctl_header; +static void register_sched_domain_sysctl(void) +{ + int i, cpu_num = num_online_cpus(); + struct ctl_table *entry = sd_alloc_ctl_entry(cpu_num + 1); + char buf[32]; + + WARN_ON(sd_ctl_dir[0].child); + sd_ctl_dir[0].child = entry; + + if (entry == NULL) + return; + + for_each_online_cpu(i) { + snprintf(buf, 32, "cpu%d", i); + entry->procname = kstrdup(buf, GFP_KERNEL); + entry->mode = 0555; + entry->child = sd_alloc_ctl_cpu_table(i); + entry++; + } + + WARN_ON(sd_sysctl_header); + sd_sysctl_header = register_sysctl_table(sd_ctl_root); +} + +/* may be called multiple times per register */ +static void unregister_sched_domain_sysctl(void) +{ + if (sd_sysctl_header) + unregister_sysctl_table(sd_sysctl_header); + sd_sysctl_header = NULL; + if (sd_ctl_dir[0].child) + sd_free_ctl_entry(&sd_ctl_dir[0].child); +} +#else +static void register_sched_domain_sysctl(void) +{ +} +static void unregister_sched_domain_sysctl(void) +{ +} +#endif + +static void set_rq_online(struct rq *rq) +{ + if (!rq->online) { + const struct sched_class *class; + + cpu_set(rq->cpu, rq->rd->online); + rq->online = 1; + + for_each_class(class) { + if (class->rq_online) + class->rq_online(rq); + } + } +} + +static void set_rq_offline(struct rq *rq) +{ + if (rq->online) { + const struct sched_class *class; + + for_each_class(class) { + if (class->rq_offline) + class->rq_offline(rq); + } + + cpu_clear(rq->cpu, rq->rd->online); + rq->online = 0; + } +} + +/* + * migration_call - callback that gets triggered when a CPU is added. + * Here we can start up the necessary migration thread for the new CPU. + */ +static int __cpuinit +migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) +{ + struct task_struct *p; + int cpu = (long)hcpu; + unsigned long flags; + struct rq *rq; + + switch (action) { + + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + p = kthread_create(migration_thread, hcpu, "migration/%d", cpu); + if (IS_ERR(p)) + return NOTIFY_BAD; + kthread_bind(p, cpu); + /* Must be high prio: stop_machine expects to yield to it. */ + rq = task_rq_lock(p, &flags); + __setscheduler(rq, p, SCHED_FIFO, MAX_RT_PRIO-1); + task_rq_unlock(rq, &flags); + cpu_rq(cpu)->migration_thread = p; + break; + + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + /* Strictly unnecessary, as first user will wake it. */ + wake_up_process(cpu_rq(cpu)->migration_thread); + + /* Update our root-domain */ + rq = cpu_rq(cpu); + spin_lock_irqsave(&rq->lock, flags); + if (rq->rd) { + BUG_ON(!cpu_isset(cpu, rq->rd->span)); + + set_rq_online(rq); + } + spin_unlock_irqrestore(&rq->lock, flags); + break; + +#ifdef CONFIG_HOTPLUG_CPU + case CPU_UP_CANCELED: + case CPU_UP_CANCELED_FROZEN: + if (!cpu_rq(cpu)->migration_thread) + break; + /* Unbind it from offline cpu so it can run. Fall thru. */ + kthread_bind(cpu_rq(cpu)->migration_thread, + any_online_cpu(cpu_online_map)); + kthread_stop(cpu_rq(cpu)->migration_thread); + cpu_rq(cpu)->migration_thread = NULL; + break; + + case CPU_DEAD: + case CPU_DEAD_FROZEN: + cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */ + migrate_live_tasks(cpu); + rq = cpu_rq(cpu); + kthread_stop(rq->migration_thread); + rq->migration_thread = NULL; + /* Idle task back to normal (off runqueue, low prio) */ + spin_lock_irq(&rq->lock); + update_rq_clock(rq); + deactivate_task(rq, rq->idle, 0); + rq->idle->static_prio = MAX_PRIO; + __setscheduler(rq, rq->idle, SCHED_NORMAL, 0); + rq->idle->sched_class = &idle_sched_class; + migrate_dead_tasks(cpu); + spin_unlock_irq(&rq->lock); + cpuset_unlock(); + migrate_nr_uninterruptible(rq); + BUG_ON(rq->nr_running != 0); + + /* + * No need to migrate the tasks: it was best-effort if + * they didn't take sched_hotcpu_mutex. Just wake up + * the requestors. + */ + spin_lock_irq(&rq->lock); + while (!list_empty(&rq->migration_queue)) { + struct migration_req *req; + + req = list_entry(rq->migration_queue.next, + struct migration_req, list); + list_del_init(&req->list); + spin_unlock_irq(&rq->lock); + complete(&req->done); + spin_lock_irq(&rq->lock); + } + spin_unlock_irq(&rq->lock); + break; + + case CPU_DYING: + case CPU_DYING_FROZEN: + /* Update our root-domain */ + rq = cpu_rq(cpu); + spin_lock_irqsave(&rq->lock, flags); + if (rq->rd) { + BUG_ON(!cpu_isset(cpu, rq->rd->span)); + set_rq_offline(rq); + } + spin_unlock_irqrestore(&rq->lock, flags); + break; +#endif + } + return NOTIFY_OK; +} + +/* Register at highest priority so that task migration (migrate_all_tasks) + * happens before everything else. + */ +static struct notifier_block __cpuinitdata migration_notifier = { + .notifier_call = migration_call, + .priority = 10 +}; + +static int __init migration_init(void) +{ + void *cpu = (void *)(long)smp_processor_id(); + int err; + + /* Start one for the boot CPU: */ + err = migration_call(&migration_notifier, CPU_UP_PREPARE, cpu); + BUG_ON(err == NOTIFY_BAD); + migration_call(&migration_notifier, CPU_ONLINE, cpu); + register_cpu_notifier(&migration_notifier); + + return err; +} +early_initcall(migration_init); +#endif + +#ifdef CONFIG_SMP + +#ifdef CONFIG_SCHED_DEBUG + +static inline const char *sd_level_to_string(enum sched_domain_level lvl) +{ + switch (lvl) { + case SD_LV_NONE: + return "NONE"; + case SD_LV_SIBLING: + return "SIBLING"; + case SD_LV_MC: + return "MC"; + case SD_LV_CPU: + return "CPU"; + case SD_LV_NODE: + return "NODE"; + case SD_LV_ALLNODES: + return "ALLNODES"; + case SD_LV_MAX: + return "MAX"; + + } + return "MAX"; +} + +static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, + cpumask_t *groupmask) +{ + struct sched_group *group = sd->groups; + char str[256]; + + cpulist_scnprintf(str, sizeof(str), sd->span); + cpus_clear(*groupmask); + + printk(KERN_DEBUG "%*s domain %d: ", level, "", level); + + if (!(sd->flags & SD_LOAD_BALANCE)) { + printk("does not load-balance\n"); + if (sd->parent) + printk(KERN_ERR "ERROR: !SD_LOAD_BALANCE domain" + " has parent"); + return -1; + } + + printk(KERN_CONT "span %s level %s\n", + str, sd_level_to_string(sd->level)); + + if (!cpu_isset(cpu, sd->span)) { + printk(KERN_ERR "ERROR: domain->span does not contain " + "CPU%d\n", cpu); + } + if (!cpu_isset(cpu, group->cpumask)) { + printk(KERN_ERR "ERROR: domain->groups does not contain" + " CPU%d\n", cpu); + } + + printk(KERN_DEBUG "%*s groups:", level + 1, ""); + do { + if (!group) { + printk("\n"); + printk(KERN_ERR "ERROR: group is NULL\n"); + break; + } + + if (!group->__cpu_power) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: domain->cpu_power not " + "set\n"); + break; + } + + if (!cpus_weight(group->cpumask)) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: empty group\n"); + break; + } + + if (cpus_intersects(*groupmask, group->cpumask)) { + printk(KERN_CONT "\n"); + printk(KERN_ERR "ERROR: repeated CPUs\n"); + break; + } + + cpus_or(*groupmask, *groupmask, group->cpumask); + + cpulist_scnprintf(str, sizeof(str), group->cpumask); + printk(KERN_CONT " %s", str); + + group = group->next; + } while (group != sd->groups); + printk(KERN_CONT "\n"); + + if (!cpus_equal(sd->span, *groupmask)) + printk(KERN_ERR "ERROR: groups don't span domain->span\n"); + + if (sd->parent && !cpus_subset(*groupmask, sd->parent->span)) + printk(KERN_ERR "ERROR: parent span is not a superset " + "of domain->span\n"); + return 0; +} + +static void sched_domain_debug(struct sched_domain *sd, int cpu) +{ + cpumask_t *groupmask; + int level = 0; + + if (!sd) { + printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); + return; + } + + printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + + groupmask = kmalloc(sizeof(cpumask_t), GFP_KERNEL); + if (!groupmask) { + printk(KERN_DEBUG "Cannot load-balance (out of memory)\n"); + return; + } + + for (;;) { + if (sched_domain_debug_one(sd, cpu, level, groupmask)) + break; + level++; + sd = sd->parent; + if (!sd) + break; + } + kfree(groupmask); +} +#else /* !CONFIG_SCHED_DEBUG */ +# define sched_domain_debug(sd, cpu) do { } while (0) +#endif /* CONFIG_SCHED_DEBUG */ + +static int sd_degenerate(struct sched_domain *sd) +{ + if (cpus_weight(sd->span) == 1) + return 1; + + /* Following flags need at least 2 groups */ + if (sd->flags & (SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_SHARE_CPUPOWER | + SD_SHARE_PKG_RESOURCES)) { + if (sd->groups != sd->groups->next) + return 0; + } + + /* Following flags don't use groups */ + if (sd->flags & (SD_WAKE_IDLE | + SD_WAKE_AFFINE | + SD_WAKE_BALANCE)) + return 0; + + return 1; +} + +static int +sd_parent_degenerate(struct sched_domain *sd, struct sched_domain *parent) +{ + unsigned long cflags = sd->flags, pflags = parent->flags; + + if (sd_degenerate(parent)) + return 1; + + if (!cpus_equal(sd->span, parent->span)) + return 0; + + /* Does parent contain flags not in child? */ + /* WAKE_BALANCE is a subset of WAKE_AFFINE */ + if (cflags & SD_WAKE_AFFINE) + pflags &= ~SD_WAKE_BALANCE; + /* Flags needing groups don't count if only 1 group in parent */ + if (parent->groups == parent->groups->next) { + pflags &= ~(SD_LOAD_BALANCE | + SD_BALANCE_NEWIDLE | + SD_BALANCE_FORK | + SD_BALANCE_EXEC | + SD_SHARE_CPUPOWER | + SD_SHARE_PKG_RESOURCES); + } + if (~cflags & pflags) + return 0; + + return 1; +} + +static void rq_attach_root(struct rq *rq, struct root_domain *rd) +{ + unsigned long flags; + + spin_lock_irqsave(&rq->lock, flags); + + if (rq->rd) { + struct root_domain *old_rd = rq->rd; + + if (cpu_isset(rq->cpu, old_rd->online)) + set_rq_offline(rq); + + cpu_clear(rq->cpu, old_rd->span); + + if (atomic_dec_and_test(&old_rd->refcount)) + kfree(old_rd); + } + + atomic_inc(&rd->refcount); + rq->rd = rd; + + cpu_set(rq->cpu, rd->span); + if (cpu_isset(rq->cpu, cpu_online_map)) + set_rq_online(rq); + + spin_unlock_irqrestore(&rq->lock, flags); +} + +static void init_rootdomain(struct root_domain *rd) +{ + memset(rd, 0, sizeof(*rd)); + + cpus_clear(rd->span); + cpus_clear(rd->online); + + cpupri_init(&rd->cpupri); +} + +static void init_defrootdomain(void) +{ + init_rootdomain(&def_root_domain); + atomic_set(&def_root_domain.refcount, 1); +} + +static struct root_domain *alloc_rootdomain(void) +{ + struct root_domain *rd; + + rd = kmalloc(sizeof(*rd), GFP_KERNEL); + if (!rd) + return NULL; + + init_rootdomain(rd); + + return rd; +} + +/* + * Attach the domain 'sd' to 'cpu' as its base domain. Callers must + * hold the hotplug lock. + */ +static void +cpu_attach_domain(struct sched_domain *sd, struct root_domain *rd, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + struct sched_domain *tmp; + + /* Remove the sched domains which do not contribute to scheduling. */ + for (tmp = sd; tmp; ) { + struct sched_domain *parent = tmp->parent; + if (!parent) + break; + + if (sd_parent_degenerate(tmp, parent)) { + tmp->parent = parent->parent; + if (parent->parent) + parent->parent->child = tmp; + } else + tmp = tmp->parent; + } + + if (sd && sd_degenerate(sd)) { + sd = sd->parent; + if (sd) + sd->child = NULL; + } + + sched_domain_debug(sd, cpu); + + rq_attach_root(rq, rd); + rcu_assign_pointer(rq->sd, sd); +} + +/* cpus with isolated domains */ +static cpumask_t cpu_isolated_map = CPU_MASK_NONE; + +/* Setup the mask of cpus configured for isolated domains */ +static int __init isolated_cpu_setup(char *str) +{ + static int __initdata ints[NR_CPUS]; + int i; + + str = get_options(str, ARRAY_SIZE(ints), ints); + cpus_clear(cpu_isolated_map); + for (i = 1; i <= ints[0]; i++) + if (ints[i] < NR_CPUS) + cpu_set(ints[i], cpu_isolated_map); + return 1; +} + +__setup("isolcpus=", isolated_cpu_setup); + +/* + * init_sched_build_groups takes the cpumask we wish to span, and a pointer + * to a function which identifies what group(along with sched group) a CPU + * belongs to. The return value of group_fn must be a >= 0 and < NR_CPUS + * (due to the fact that we keep track of groups covered with a cpumask_t). + * + * init_sched_build_groups will build a circular linked list of the groups + * covered by the given span, and will set each group's ->cpumask correctly, + * and ->cpu_power to 0. + */ +static void +init_sched_build_groups(const cpumask_t *span, const cpumask_t *cpu_map, + int (*group_fn)(int cpu, const cpumask_t *cpu_map, + struct sched_group **sg, + cpumask_t *tmpmask), + cpumask_t *covered, cpumask_t *tmpmask) +{ + struct sched_group *first = NULL, *last = NULL; + int i; + + cpus_clear(*covered); + + for_each_cpu_mask_nr(i, *span) { + struct sched_group *sg; + int group = group_fn(i, cpu_map, &sg, tmpmask); + int j; + + if (cpu_isset(i, *covered)) + continue; + + cpus_clear(sg->cpumask); + sg->__cpu_power = 0; + + for_each_cpu_mask_nr(j, *span) { + if (group_fn(j, cpu_map, NULL, tmpmask) != group) + continue; + + cpu_set(j, *covered); + cpu_set(j, sg->cpumask); + } + if (!first) + first = sg; + if (last) + last->next = sg; + last = sg; + } + last->next = first; +} + +#define SD_NODES_PER_DOMAIN 16 + +#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 = 0; + + 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; + } + } + + 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, cpumask_t *span) +{ + nodemask_t used_nodes; + node_to_cpumask_ptr(nodemask, node); + int i; + + cpus_clear(*span); + nodes_clear(used_nodes); + + cpus_or(*span, *span, *nodemask); + node_set(node, used_nodes); + + for (i = 1; i < SD_NODES_PER_DOMAIN; i++) { + int next_node = find_next_best_node(node, &used_nodes); + + node_to_cpumask_ptr_next(nodemask, next_node); + cpus_or(*span, *span, *nodemask); + } +} +#endif /* CONFIG_NUMA */ + +int sched_smt_power_savings = 0, sched_mc_power_savings = 0; + +/* + * SMT sched-domains: + */ +#ifdef CONFIG_SCHED_SMT +static DEFINE_PER_CPU(struct sched_domain, cpu_domains); +static DEFINE_PER_CPU(struct sched_group, sched_group_cpus); + +static int +cpu_to_cpu_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg, + cpumask_t *unused) +{ + if (sg) + *sg = &per_cpu(sched_group_cpus, cpu); + return cpu; +} +#endif /* CONFIG_SCHED_SMT */ + +/* + * multi-core sched-domains: + */ +#ifdef CONFIG_SCHED_MC +static DEFINE_PER_CPU(struct sched_domain, core_domains); +static DEFINE_PER_CPU(struct sched_group, sched_group_core); +#endif /* CONFIG_SCHED_MC */ + +#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT) +static int +cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg, + cpumask_t *mask) +{ + int group; + + *mask = per_cpu(cpu_sibling_map, cpu); + cpus_and(*mask, *mask, *cpu_map); + group = first_cpu(*mask); + if (sg) + *sg = &per_cpu(sched_group_core, group); + return group; +} +#elif defined(CONFIG_SCHED_MC) +static int +cpu_to_core_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg, + cpumask_t *unused) +{ + if (sg) + *sg = &per_cpu(sched_group_core, cpu); + return cpu; +} +#endif + +static DEFINE_PER_CPU(struct sched_domain, phys_domains); +static DEFINE_PER_CPU(struct sched_group, sched_group_phys); + +static int +cpu_to_phys_group(int cpu, const cpumask_t *cpu_map, struct sched_group **sg, + cpumask_t *mask) +{ + int group; +#ifdef CONFIG_SCHED_MC + *mask = cpu_coregroup_map(cpu); + cpus_and(*mask, *mask, *cpu_map); + group = first_cpu(*mask); +#elif defined(CONFIG_SCHED_SMT) + *mask = per_cpu(cpu_sibling_map, cpu); + cpus_and(*mask, *mask, *cpu_map); + group = first_cpu(*mask); +#else + group = cpu; +#endif + if (sg) + *sg = &per_cpu(sched_group_phys, group); + return group; +} + +#ifdef CONFIG_NUMA +/* + * The init_sched_build_groups can't handle what we want to do with node + * groups, so roll our own. Now each node has its own list of groups which + * gets dynamically allocated. + */ +static DEFINE_PER_CPU(struct sched_domain, node_domains); +static struct sched_group ***sched_group_nodes_bycpu; + +static DEFINE_PER_CPU(struct sched_domain, allnodes_domains); +static DEFINE_PER_CPU(struct sched_group, sched_group_allnodes); + +static int cpu_to_allnodes_group(int cpu, const cpumask_t *cpu_map, + struct sched_group **sg, cpumask_t *nodemask) +{ + int group; + + *nodemask = node_to_cpumask(cpu_to_node(cpu)); + cpus_and(*nodemask, *nodemask, *cpu_map); + group = first_cpu(*nodemask); + + if (sg) + *sg = &per_cpu(sched_group_allnodes, group); + return group; +} + +static void init_numa_sched_groups_power(struct sched_group *group_head) +{ + struct sched_group *sg = group_head; + int j; + + if (!sg) + return; + do { + for_each_cpu_mask_nr(j, sg->cpumask) { + struct sched_domain *sd; + + sd = &per_cpu(phys_domains, j); + if (j != first_cpu(sd->groups->cpumask)) { + /* + * Only add "power" once for each + * physical package. + */ + continue; + } + + sg_inc_cpu_power(sg, sd->groups->__cpu_power); + } + sg = sg->next; + } while (sg != group_head); +} +#endif /* CONFIG_NUMA */ + +#ifdef CONFIG_NUMA +/* Free memory allocated for various sched_group structures */ +static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask) +{ + int cpu, i; + + for_each_cpu_mask_nr(cpu, *cpu_map) { + struct sched_group **sched_group_nodes + = sched_group_nodes_bycpu[cpu]; + + if (!sched_group_nodes) + continue; + + for (i = 0; i < nr_node_ids; i++) { + struct sched_group *oldsg, *sg = sched_group_nodes[i]; + + *nodemask = node_to_cpumask(i); + cpus_and(*nodemask, *nodemask, *cpu_map); + if (cpus_empty(*nodemask)) + continue; + + if (sg == NULL) + continue; + sg = sg->next; +next_sg: + oldsg = sg; + sg = sg->next; + kfree(oldsg); + if (oldsg != sched_group_nodes[i]) + goto next_sg; + } + kfree(sched_group_nodes); + sched_group_nodes_bycpu[cpu] = NULL; + } +} +#else /* !CONFIG_NUMA */ +static void free_sched_groups(const cpumask_t *cpu_map, cpumask_t *nodemask) +{ +} +#endif /* CONFIG_NUMA */ + +/* + * Initialize sched groups cpu_power. + * + * cpu_power indicates the capacity of sched group, which is used while + * distributing the load between different sched groups in a sched domain. + * Typically cpu_power for all the groups in a sched domain will be same unless + * there are asymmetries in the topology. If there are asymmetries, group + * having more cpu_power will pickup more load compared to the group having + * less cpu_power. + * + * cpu_power will be a multiple of SCHED_LOAD_SCALE. This multiple represents + * the maximum number of tasks a group can handle in the presence of other idle + * or lightly loaded groups in the same sched domain. + */ +static void init_sched_groups_power(int cpu, struct sched_domain *sd) +{ + struct sched_domain *child; + struct sched_group *group; + + WARN_ON(!sd || !sd->groups); + + if (cpu != first_cpu(sd->groups->cpumask)) + return; + + child = sd->child; + + sd->groups->__cpu_power = 0; + + /* + * For perf policy, if the groups in child domain share resources + * (for example cores sharing some portions of the cache hierarchy + * or SMT), then set this domain groups cpu_power such that each group + * can handle only one task, when there are other idle groups in the + * same sched domain. + */ + if (!child || (!(sd->flags & SD_POWERSAVINGS_BALANCE) && + (child->flags & + (SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES)))) { + sg_inc_cpu_power(sd->groups, SCHED_LOAD_SCALE); + return; + } + + /* + * add cpu_power of each child group to this groups cpu_power + */ + group = child->groups; + do { + sg_inc_cpu_power(sd->groups, group->__cpu_power); + group = group->next; + } while (group != child->groups); +} + +/* + * Initializers for schedule domains + * Non-inlined to reduce accumulated stack pressure in build_sched_domains() + */ + +#define SD_INIT(sd, type) sd_init_##type(sd) +#define SD_INIT_FUNC(type) \ +static noinline void sd_init_##type(struct sched_domain *sd) \ +{ \ + memset(sd, 0, sizeof(*sd)); \ + *sd = SD_##type##_INIT; \ + sd->level = SD_LV_##type; \ +} + +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 +#ifdef CONFIG_SCHED_MC + SD_INIT_FUNC(MC) +#endif + +/* + * To minimize stack usage kmalloc room for cpumasks and share the + * space as the usage in build_sched_domains() dictates. Used only + * if the amount of space is significant. + */ +struct allmasks { + cpumask_t tmpmask; /* make this one first */ + union { + cpumask_t nodemask; + cpumask_t this_sibling_map; + cpumask_t this_core_map; + }; + cpumask_t send_covered; + +#ifdef CONFIG_NUMA + cpumask_t domainspan; + cpumask_t covered; + cpumask_t notcovered; +#endif +}; + +#if NR_CPUS > 128 +#define SCHED_CPUMASK_ALLOC 1 +#define SCHED_CPUMASK_FREE(v) kfree(v) +#define SCHED_CPUMASK_DECLARE(v) struct allmasks *v +#else +#define SCHED_CPUMASK_ALLOC 0 +#define SCHED_CPUMASK_FREE(v) +#define SCHED_CPUMASK_DECLARE(v) struct allmasks _v, *v = &_v +#endif + +#define SCHED_CPUMASK_VAR(v, a) cpumask_t *v = (cpumask_t *) \ + ((unsigned long)(a) + offsetof(struct allmasks, v)) + +static int default_relax_domain_level = -1; + +static int __init setup_relax_domain_level(char *str) +{ + unsigned long val; + + val = simple_strtoul(str, NULL, 0); + if (val < SD_LV_MAX) + default_relax_domain_level = val; + + return 1; +} +__setup("relax_domain_level=", setup_relax_domain_level); + +static void set_domain_attribute(struct sched_domain *sd, + struct sched_domain_attr *attr) +{ + int request; + + if (!attr || attr->relax_domain_level < 0) { + if (default_relax_domain_level < 0) + return; + else + request = default_relax_domain_level; + } else + request = attr->relax_domain_level; + if (request < sd->level) { + /* turn off idle balance on this domain */ + sd->flags &= ~(SD_WAKE_IDLE|SD_BALANCE_NEWIDLE); + } else { + /* turn on idle balance on this domain */ + sd->flags |= (SD_WAKE_IDLE_FAR|SD_BALANCE_NEWIDLE); + } +} + +/* + * Build sched domains for a given set of cpus and attach the sched domains + * to the individual cpus + */ +static int __build_sched_domains(const cpumask_t *cpu_map, + struct sched_domain_attr *attr) +{ + int i; + struct root_domain *rd; + SCHED_CPUMASK_DECLARE(allmasks); + cpumask_t *tmpmask; +#ifdef CONFIG_NUMA + struct sched_group **sched_group_nodes = NULL; + int sd_allnodes = 0; + + /* + * Allocate the per-node list of sched groups + */ + sched_group_nodes = kcalloc(nr_node_ids, sizeof(struct sched_group *), + GFP_KERNEL); + if (!sched_group_nodes) { + printk(KERN_WARNING "Can not alloc sched group node list\n"); + return -ENOMEM; + } +#endif + + rd = alloc_rootdomain(); + if (!rd) { + printk(KERN_WARNING "Cannot alloc root domain\n"); +#ifdef CONFIG_NUMA + kfree(sched_group_nodes); +#endif + return -ENOMEM; + } + +#if SCHED_CPUMASK_ALLOC + /* get space for all scratch cpumask variables */ + allmasks = kmalloc(sizeof(*allmasks), GFP_KERNEL); + if (!allmasks) { + printk(KERN_WARNING "Cannot alloc cpumask array\n"); + kfree(rd); +#ifdef CONFIG_NUMA + kfree(sched_group_nodes); +#endif + return -ENOMEM; + } +#endif + tmpmask = (cpumask_t *)allmasks; + + +#ifdef CONFIG_NUMA + sched_group_nodes_bycpu[first_cpu(*cpu_map)] = sched_group_nodes; +#endif + + /* + * Set up domains for cpus specified by the cpu_map. + */ + for_each_cpu_mask_nr(i, *cpu_map) { + struct sched_domain *sd = NULL, *p; + SCHED_CPUMASK_VAR(nodemask, allmasks); + + *nodemask = node_to_cpumask(cpu_to_node(i)); + cpus_and(*nodemask, *nodemask, *cpu_map); + +#ifdef CONFIG_NUMA + if (cpus_weight(*cpu_map) > + SD_NODES_PER_DOMAIN*cpus_weight(*nodemask)) { + sd = &per_cpu(allnodes_domains, i); + SD_INIT(sd, ALLNODES); + set_domain_attribute(sd, attr); + sd->span = *cpu_map; + cpu_to_allnodes_group(i, cpu_map, &sd->groups, tmpmask); + p = sd; + sd_allnodes = 1; + } else + p = NULL; + + sd = &per_cpu(node_domains, i); + SD_INIT(sd, NODE); + set_domain_attribute(sd, attr); + sched_domain_node_span(cpu_to_node(i), &sd->span); + sd->parent = p; + if (p) + p->child = sd; + cpus_and(sd->span, sd->span, *cpu_map); +#endif + + p = sd; + sd = &per_cpu(phys_domains, i); + SD_INIT(sd, CPU); + set_domain_attribute(sd, attr); + sd->span = *nodemask; + sd->parent = p; + if (p) + p->child = sd; + cpu_to_phys_group(i, cpu_map, &sd->groups, tmpmask); + +#ifdef CONFIG_SCHED_MC + p = sd; + sd = &per_cpu(core_domains, i); + SD_INIT(sd, MC); + set_domain_attribute(sd, attr); + sd->span = cpu_coregroup_map(i); + cpus_and(sd->span, sd->span, *cpu_map); + sd->parent = p; + p->child = sd; + cpu_to_core_group(i, cpu_map, &sd->groups, tmpmask); +#endif + +#ifdef CONFIG_SCHED_SMT + p = sd; + sd = &per_cpu(cpu_domains, i); + SD_INIT(sd, SIBLING); + set_domain_attribute(sd, attr); + sd->span = per_cpu(cpu_sibling_map, i); + cpus_and(sd->span, sd->span, *cpu_map); + sd->parent = p; + p->child = sd; + cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask); +#endif + } + +#ifdef CONFIG_SCHED_SMT + /* Set up CPU (sibling) groups */ + for_each_cpu_mask_nr(i, *cpu_map) { + SCHED_CPUMASK_VAR(this_sibling_map, allmasks); + SCHED_CPUMASK_VAR(send_covered, allmasks); + + *this_sibling_map = per_cpu(cpu_sibling_map, i); + cpus_and(*this_sibling_map, *this_sibling_map, *cpu_map); + if (i != first_cpu(*this_sibling_map)) + continue; + + init_sched_build_groups(this_sibling_map, cpu_map, + &cpu_to_cpu_group, + send_covered, tmpmask); + } +#endif + +#ifdef CONFIG_SCHED_MC + /* Set up multi-core groups */ + for_each_cpu_mask_nr(i, *cpu_map) { + SCHED_CPUMASK_VAR(this_core_map, allmasks); + SCHED_CPUMASK_VAR(send_covered, allmasks); + + *this_core_map = cpu_coregroup_map(i); + cpus_and(*this_core_map, *this_core_map, *cpu_map); + if (i != first_cpu(*this_core_map)) + continue; + + init_sched_build_groups(this_core_map, cpu_map, + &cpu_to_core_group, + send_covered, tmpmask); + } +#endif + + /* Set up physical groups */ + for (i = 0; i < nr_node_ids; i++) { + SCHED_CPUMASK_VAR(nodemask, allmasks); + SCHED_CPUMASK_VAR(send_covered, allmasks); + + *nodemask = node_to_cpumask(i); + cpus_and(*nodemask, *nodemask, *cpu_map); + if (cpus_empty(*nodemask)) + continue; + + init_sched_build_groups(nodemask, cpu_map, + &cpu_to_phys_group, + send_covered, tmpmask); + } + +#ifdef CONFIG_NUMA + /* Set up node groups */ + if (sd_allnodes) { + SCHED_CPUMASK_VAR(send_covered, allmasks); + + init_sched_build_groups(cpu_map, cpu_map, + &cpu_to_allnodes_group, + send_covered, tmpmask); + } + + for (i = 0; i < nr_node_ids; i++) { + /* Set up node groups */ + struct sched_group *sg, *prev; + SCHED_CPUMASK_VAR(nodemask, allmasks); + SCHED_CPUMASK_VAR(domainspan, allmasks); + SCHED_CPUMASK_VAR(covered, allmasks); + int j; + + *nodemask = node_to_cpumask(i); + cpus_clear(*covered); + + cpus_and(*nodemask, *nodemask, *cpu_map); + if (cpus_empty(*nodemask)) { + sched_group_nodes[i] = NULL; + continue; + } + + sched_domain_node_span(i, domainspan); + cpus_and(*domainspan, *domainspan, *cpu_map); + + sg = kmalloc_node(sizeof(struct sched_group), GFP_KERNEL, i); + if (!sg) { + printk(KERN_WARNING "Can not alloc domain group for " + "node %d\n", i); + goto error; + } + sched_group_nodes[i] = sg; + for_each_cpu_mask_nr(j, *nodemask) { + struct sched_domain *sd; + + sd = &per_cpu(node_domains, j); + sd->groups = sg; + } + sg->__cpu_power = 0; + sg->cpumask = *nodemask; + sg->next = sg; + cpus_or(*covered, *covered, *nodemask); + prev = sg; + + for (j = 0; j < nr_node_ids; j++) { + SCHED_CPUMASK_VAR(notcovered, allmasks); + int n = (i + j) % nr_node_ids; + node_to_cpumask_ptr(pnodemask, n); + + cpus_complement(*notcovered, *covered); + cpus_and(*tmpmask, *notcovered, *cpu_map); + cpus_and(*tmpmask, *tmpmask, *domainspan); + if (cpus_empty(*tmpmask)) + break; + + cpus_and(*tmpmask, *tmpmask, *pnodemask); + if (cpus_empty(*tmpmask)) + continue; + + sg = kmalloc_node(sizeof(struct sched_group), + GFP_KERNEL, i); + if (!sg) { + printk(KERN_WARNING + "Can not alloc domain group for node %d\n", j); + goto error; + } + sg->__cpu_power = 0; + sg->cpumask = *tmpmask; + sg->next = prev->next; + cpus_or(*covered, *covered, *tmpmask); + prev->next = sg; + prev = sg; + } + } +#endif + + /* Calculate CPU power for physical packages and nodes */ +#ifdef CONFIG_SCHED_SMT + for_each_cpu_mask_nr(i, *cpu_map) { + struct sched_domain *sd = &per_cpu(cpu_domains, i); + + init_sched_groups_power(i, sd); + } +#endif +#ifdef CONFIG_SCHED_MC + for_each_cpu_mask_nr(i, *cpu_map) { + struct sched_domain *sd = &per_cpu(core_domains, i); + + init_sched_groups_power(i, sd); + } +#endif + + for_each_cpu_mask_nr(i, *cpu_map) { + struct sched_domain *sd = &per_cpu(phys_domains, i); + + init_sched_groups_power(i, sd); + } + +#ifdef CONFIG_NUMA + for (i = 0; i < nr_node_ids; i++) + init_numa_sched_groups_power(sched_group_nodes[i]); + + if (sd_allnodes) { + struct sched_group *sg; + + cpu_to_allnodes_group(first_cpu(*cpu_map), cpu_map, &sg, + tmpmask); + init_numa_sched_groups_power(sg); + } +#endif + + /* Attach the domains */ + for_each_cpu_mask_nr(i, *cpu_map) { + struct sched_domain *sd; +#ifdef CONFIG_SCHED_SMT + sd = &per_cpu(cpu_domains, i); +#elif defined(CONFIG_SCHED_MC) + sd = &per_cpu(core_domains, i); +#else + sd = &per_cpu(phys_domains, i); +#endif + cpu_attach_domain(sd, rd, i); + } + + SCHED_CPUMASK_FREE((void *)allmasks); + return 0; + +#ifdef CONFIG_NUMA +error: + free_sched_groups(cpu_map, tmpmask); + SCHED_CPUMASK_FREE((void *)allmasks); + return -ENOMEM; +#endif +} + +static int build_sched_domains(const cpumask_t *cpu_map) +{ + return __build_sched_domains(cpu_map, NULL); +} + +static cpumask_t *doms_cur; /* current sched domains */ +static int ndoms_cur; /* number of sched domains in 'doms_cur' */ +static struct sched_domain_attr *dattr_cur; + /* attribues of custom domains in 'doms_cur' */ + +/* + * Special case: If a kmalloc of a doms_cur partition (array of + * cpumask_t) fails, then fallback to a single sched domain, + * as determined by the single cpumask_t fallback_doms. + */ +static cpumask_t fallback_doms; + +void __attribute__((weak)) arch_update_cpu_topology(void) +{ +} + +/* + * Set up scheduler domains and groups. Callers must hold the hotplug lock. + * For now this just excludes isolated cpus, but could be used to + * exclude other special cases in the future. + */ +static int arch_init_sched_domains(const cpumask_t *cpu_map) +{ + int err; + + arch_update_cpu_topology(); + ndoms_cur = 1; + doms_cur = kmalloc(sizeof(cpumask_t), GFP_KERNEL); + if (!doms_cur) + doms_cur = &fallback_doms; + cpus_andnot(*doms_cur, *cpu_map, cpu_isolated_map); + dattr_cur = NULL; + err = build_sched_domains(doms_cur); + register_sched_domain_sysctl(); + + return err; +} + +static void arch_destroy_sched_domains(const cpumask_t *cpu_map, + cpumask_t *tmpmask) +{ + free_sched_groups(cpu_map, tmpmask); +} + +/* + * Detach sched domains from a group of cpus specified in cpu_map + * These cpus will now be attached to the NULL domain + */ +static void detach_destroy_domains(const cpumask_t *cpu_map) +{ + cpumask_t tmpmask; + int i; + + unregister_sched_domain_sysctl(); + + for_each_cpu_mask_nr(i, *cpu_map) + cpu_attach_domain(NULL, &def_root_domain, i); + synchronize_sched(); + arch_destroy_sched_domains(cpu_map, &tmpmask); +} + +/* handle null as "default" */ +static int dattrs_equal(struct sched_domain_attr *cur, int idx_cur, + struct sched_domain_attr *new, int idx_new) +{ + struct sched_domain_attr tmp; + + /* fast path */ + if (!new && !cur) + return 1; + + tmp = SD_ATTR_INIT; + return !memcmp(cur ? (cur + idx_cur) : &tmp, + new ? (new + idx_new) : &tmp, + sizeof(struct sched_domain_attr)); +} + +/* + * Partition sched domains as specified by the 'ndoms_new' + * cpumasks in the array doms_new[] of cpumasks. This compares + * doms_new[] to the current sched domain partitioning, doms_cur[]. + * It destroys each deleted domain and builds each new domain. + * + * 'doms_new' is an array of cpumask_t's of length 'ndoms_new'. + * The masks don't intersect (don't overlap.) We should setup one + * sched domain for each mask. CPUs not in any of the cpumasks will + * not be load balanced. If the same cpumask appears both in the + * current 'doms_cur' domains and in the new 'doms_new', we can leave + * it as it is. + * + * The passed in 'doms_new' should be kmalloc'd. This routine takes + * ownership of it and will kfree it when done with it. If the caller + * failed the kmalloc call, then it can pass in doms_new == NULL && + * ndoms_new == 1, and partition_sched_domains() will fallback to + * the single partition 'fallback_doms', it also forces the domains + * to be rebuilt. + * + * If doms_new == NULL it will be replaced with cpu_online_map. + * ndoms_new == 0 is a special case for destroying existing domains, + * and it will not create the default domain. + * + * Call with hotplug lock held + */ +void partition_sched_domains(int ndoms_new, cpumask_t *doms_new, + struct sched_domain_attr *dattr_new) +{ + int i, j, n; + + mutex_lock(&sched_domains_mutex); + + /* always unregister in case we don't destroy any domains */ + unregister_sched_domain_sysctl(); + + n = doms_new ? ndoms_new : 0; + + /* Destroy deleted domains */ + for (i = 0; i < ndoms_cur; i++) { + for (j = 0; j < n; j++) { + if (cpus_equal(doms_cur[i], doms_new[j]) + && dattrs_equal(dattr_cur, i, dattr_new, j)) + goto match1; + } + /* no match - a current sched domain not in new doms_new[] */ + detach_destroy_domains(doms_cur + i); +match1: + ; + } + + if (doms_new == NULL) { + ndoms_cur = 0; + doms_new = &fallback_doms; + cpus_andnot(doms_new[0], cpu_online_map, cpu_isolated_map); + dattr_new = NULL; + } + + /* Build new domains */ + for (i = 0; i < ndoms_new; i++) { + for (j = 0; j < ndoms_cur; j++) { + if (cpus_equal(doms_new[i], doms_cur[j]) + && dattrs_equal(dattr_new, i, dattr_cur, j)) + goto match2; + } + /* no match - add a new doms_new */ + __build_sched_domains(doms_new + i, + dattr_new ? dattr_new + i : NULL); +match2: + ; + } + + /* Remember the new sched domains */ + if (doms_cur != &fallback_doms) + kfree(doms_cur); + kfree(dattr_cur); /* kfree(NULL) is safe */ + doms_cur = doms_new; + dattr_cur = dattr_new; + ndoms_cur = ndoms_new; + + register_sched_domain_sysctl(); + + mutex_unlock(&sched_domains_mutex); +} + +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) +int arch_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(); + + return 0; +} + +static ssize_t sched_power_savings_store(const char *buf, size_t count, int smt) +{ + int ret; + + if (buf[0] != '0' && buf[0] != '1') + return -EINVAL; + + if (smt) + sched_smt_power_savings = (buf[0] == '1'); + else + sched_mc_power_savings = (buf[0] == '1'); + + ret = arch_reinit_sched_domains(); + + return ret ? ret : count; +} + +#ifdef CONFIG_SCHED_MC +static ssize_t sched_mc_power_savings_show(struct sysdev_class *class, + char *page) +{ + return sprintf(page, "%u\n", sched_mc_power_savings); +} +static ssize_t sched_mc_power_savings_store(struct sysdev_class *class, + const char *buf, size_t count) +{ + return sched_power_savings_store(buf, count, 0); +} +static SYSDEV_CLASS_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 sysdev_class *dev, + char *page) +{ + return sprintf(page, "%u\n", sched_smt_power_savings); +} +static ssize_t sched_smt_power_savings_store(struct sysdev_class *dev, + const char *buf, size_t count) +{ + return sched_power_savings_store(buf, count, 1); +} +static SYSDEV_CLASS_ATTR(sched_smt_power_savings, 0644, + sched_smt_power_savings_show, + sched_smt_power_savings_store); +#endif + +int sched_create_sysfs_power_savings_entries(struct sysdev_class *cls) +{ + int err = 0; + +#ifdef CONFIG_SCHED_SMT + if (smt_capable()) + err = sysfs_create_file(&cls->kset.kobj, + &attr_sched_smt_power_savings.attr); +#endif +#ifdef CONFIG_SCHED_MC + if (!err && mc_capable()) + err = sysfs_create_file(&cls->kset.kobj, + &attr_sched_mc_power_savings.attr); +#endif + return err; +} +#endif /* CONFIG_SCHED_MC || CONFIG_SCHED_SMT */ + +#ifndef CONFIG_CPUSETS +/* + * Add online and remove offline CPUs from the scheduler domains. + * When cpusets are enabled they take over this function. + */ +static int update_sched_domains(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + switch (action) { + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + case CPU_DEAD: + case CPU_DEAD_FROZEN: + partition_sched_domains(1, NULL, NULL); + return NOTIFY_OK; + + default: + return NOTIFY_DONE; + } +} +#endif + +static int update_runtime(struct notifier_block *nfb, + unsigned long action, void *hcpu) +{ + int cpu = (int)(long)hcpu; + + switch (action) { + case CPU_DOWN_PREPARE: + case CPU_DOWN_PREPARE_FROZEN: + disable_runtime(cpu_rq(cpu)); + return NOTIFY_OK; + + case CPU_DOWN_FAILED: + case CPU_DOWN_FAILED_FROZEN: + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + enable_runtime(cpu_rq(cpu)); + return NOTIFY_OK; + + default: + return NOTIFY_DONE; + } +} + +void __init sched_init_smp(void) +{ + cpumask_t non_isolated_cpus; + +#if defined(CONFIG_NUMA) + sched_group_nodes_bycpu = kzalloc(nr_cpu_ids * sizeof(void **), + GFP_KERNEL); + BUG_ON(sched_group_nodes_bycpu == NULL); +#endif + get_online_cpus(); + mutex_lock(&sched_domains_mutex); + arch_init_sched_domains(&cpu_online_map); + cpus_andnot(non_isolated_cpus, cpu_possible_map, cpu_isolated_map); + if (cpus_empty(non_isolated_cpus)) + cpu_set(smp_processor_id(), non_isolated_cpus); + mutex_unlock(&sched_domains_mutex); + put_online_cpus(); + +#ifndef CONFIG_CPUSETS + /* XXX: Theoretical race here - CPU may be hotplugged now */ + hotcpu_notifier(update_sched_domains, 0); +#endif + + /* RT runtime code needs to handle some hotplug events */ + hotcpu_notifier(update_runtime, 0); + + init_hrtick(); + + /* Move init over to a non-isolated CPU */ + if (set_cpus_allowed_ptr(current, &non_isolated_cpus) < 0) + BUG(); + sched_init_granularity(); +} +#else +void __init sched_init_smp(void) +{ + sched_init_granularity(); +} +#endif /* CONFIG_SMP */ + +int in_sched_functions(unsigned long addr) +{ + return in_lock_functions(addr) || + (addr >= (unsigned long)__sched_text_start + && addr < (unsigned long)__sched_text_end); +} + +static void init_cfs_rq(struct cfs_rq *cfs_rq, struct rq *rq) +{ + cfs_rq->tasks_timeline = RB_ROOT; + INIT_LIST_HEAD(&cfs_rq->tasks); +#ifdef CONFIG_FAIR_GROUP_SCHED + cfs_rq->rq = rq; +#endif + cfs_rq->min_vruntime = (u64)(-(1LL << 20)); +} + +static void init_rt_rq(struct rt_rq *rt_rq, struct rq *rq) +{ + struct rt_prio_array *array; + int i; + + array = &rt_rq->active; + for (i = 0; i < MAX_RT_PRIO; i++) { + INIT_LIST_HEAD(array->queue + i); + __clear_bit(i, array->bitmap); + } + /* delimiter for bitsearch: */ + __set_bit(MAX_RT_PRIO, array->bitmap); + +#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED + rt_rq->highest_prio = MAX_RT_PRIO; +#endif +#ifdef CONFIG_SMP + rt_rq->rt_nr_migratory = 0; + rt_rq->overloaded = 0; +#endif + + rt_rq->rt_time = 0; + rt_rq->rt_throttled = 0; + rt_rq->rt_runtime = 0; + spin_lock_init(&rt_rq->rt_runtime_lock); + +#ifdef CONFIG_RT_GROUP_SCHED + rt_rq->rt_nr_boosted = 0; + rt_rq->rq = rq; +#endif +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void init_tg_cfs_entry(struct task_group *tg, struct cfs_rq *cfs_rq, + struct sched_entity *se, int cpu, int add, + struct sched_entity *parent) +{ + struct rq *rq = cpu_rq(cpu); + tg->cfs_rq[cpu] = cfs_rq; + init_cfs_rq(cfs_rq, rq); + cfs_rq->tg = tg; + if (add) + list_add(&cfs_rq->leaf_cfs_rq_list, &rq->leaf_cfs_rq_list); + + tg->se[cpu] = se; + /* se could be NULL for init_task_group */ + if (!se) + return; + + if (!parent) + se->cfs_rq = &rq->cfs; + else + se->cfs_rq = parent->my_q; + + se->my_q = cfs_rq; + se->load.weight = tg->shares; + se->load.inv_weight = 0; + se->parent = parent; +} +#endif + +#ifdef CONFIG_RT_GROUP_SCHED +static void init_tg_rt_entry(struct task_group *tg, struct rt_rq *rt_rq, + struct sched_rt_entity *rt_se, int cpu, int add, + struct sched_rt_entity *parent) +{ + struct rq *rq = cpu_rq(cpu); + + tg->rt_rq[cpu] = rt_rq; + init_rt_rq(rt_rq, rq); + rt_rq->tg = tg; + rt_rq->rt_se = rt_se; + rt_rq->rt_runtime = tg->rt_bandwidth.rt_runtime; + if (add) + list_add(&rt_rq->leaf_rt_rq_list, &rq->leaf_rt_rq_list); + + tg->rt_se[cpu] = rt_se; + if (!rt_se) + return; + + if (!parent) + rt_se->rt_rq = &rq->rt; + else + rt_se->rt_rq = parent->my_q; + + rt_se->my_q = rt_rq; + rt_se->parent = parent; + INIT_LIST_HEAD(&rt_se->run_list); +} +#endif + +void __init sched_init(void) +{ + int i, j; + unsigned long alloc_size = 0, ptr; + +#ifdef CONFIG_FAIR_GROUP_SCHED + alloc_size += 2 * nr_cpu_ids * sizeof(void **); +#endif +#ifdef CONFIG_RT_GROUP_SCHED + alloc_size += 2 * nr_cpu_ids * sizeof(void **); +#endif +#ifdef CONFIG_USER_SCHED + alloc_size *= 2; +#endif + /* + * As sched_init() is called before page_alloc is setup, + * we use alloc_bootmem(). + */ + if (alloc_size) { + ptr = (unsigned long)alloc_bootmem(alloc_size); + +#ifdef CONFIG_FAIR_GROUP_SCHED + init_task_group.se = (struct sched_entity **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + + init_task_group.cfs_rq = (struct cfs_rq **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + +#ifdef CONFIG_USER_SCHED + root_task_group.se = (struct sched_entity **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + + root_task_group.cfs_rq = (struct cfs_rq **)ptr; + ptr += nr_cpu_ids * sizeof(void **); +#endif /* CONFIG_USER_SCHED */ +#endif /* CONFIG_FAIR_GROUP_SCHED */ +#ifdef CONFIG_RT_GROUP_SCHED + init_task_group.rt_se = (struct sched_rt_entity **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + + init_task_group.rt_rq = (struct rt_rq **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + +#ifdef CONFIG_USER_SCHED + root_task_group.rt_se = (struct sched_rt_entity **)ptr; + ptr += nr_cpu_ids * sizeof(void **); + + root_task_group.rt_rq = (struct rt_rq **)ptr; + ptr += nr_cpu_ids * sizeof(void **); +#endif /* CONFIG_USER_SCHED */ +#endif /* CONFIG_RT_GROUP_SCHED */ + } + +#ifdef CONFIG_SMP + init_defrootdomain(); +#endif + + init_rt_bandwidth(&def_rt_bandwidth, + global_rt_period(), global_rt_runtime()); + +#ifdef CONFIG_RT_GROUP_SCHED + init_rt_bandwidth(&init_task_group.rt_bandwidth, + global_rt_period(), global_rt_runtime()); +#ifdef CONFIG_USER_SCHED + init_rt_bandwidth(&root_task_group.rt_bandwidth, + global_rt_period(), RUNTIME_INF); +#endif /* CONFIG_USER_SCHED */ +#endif /* CONFIG_RT_GROUP_SCHED */ + +#ifdef CONFIG_GROUP_SCHED + list_add(&init_task_group.list, &task_groups); + INIT_LIST_HEAD(&init_task_group.children); + +#ifdef CONFIG_USER_SCHED + INIT_LIST_HEAD(&root_task_group.children); + init_task_group.parent = &root_task_group; + list_add(&init_task_group.siblings, &root_task_group.children); +#endif /* CONFIG_USER_SCHED */ +#endif /* CONFIG_GROUP_SCHED */ + + for_each_possible_cpu(i) { + struct rq *rq; + + rq = cpu_rq(i); + spin_lock_init(&rq->lock); + rq->nr_running = 0; + init_cfs_rq(&rq->cfs, rq); + init_rt_rq(&rq->rt, rq); +#ifdef CONFIG_FAIR_GROUP_SCHED + init_task_group.shares = init_task_group_load; + INIT_LIST_HEAD(&rq->leaf_cfs_rq_list); +#ifdef CONFIG_CGROUP_SCHED + /* + * How much cpu bandwidth does init_task_group get? + * + * In case of task-groups formed thr' the cgroup filesystem, it + * gets 100% of the cpu resources in the system. This overall + * system cpu resource is divided among the tasks of + * init_task_group and its child task-groups in a fair manner, + * based on each entity's (task or task-group's) weight + * (se->load.weight). + * + * In other words, if init_task_group has 10 tasks of weight + * 1024) and two child groups A0 and A1 (of weight 1024 each), + * then A0's share of the cpu resource is: + * + * A0's bandwidth = 1024 / (10*1024 + 1024 + 1024) = 8.33% + * + * We achieve this by letting init_task_group's tasks sit + * directly in rq->cfs (i.e init_task_group->se[] = NULL). + */ + init_tg_cfs_entry(&init_task_group, &rq->cfs, NULL, i, 1, NULL); +#elif defined CONFIG_USER_SCHED + root_task_group.shares = NICE_0_LOAD; + init_tg_cfs_entry(&root_task_group, &rq->cfs, NULL, i, 0, NULL); + /* + * In case of task-groups formed thr' the user id of tasks, + * init_task_group represents tasks belonging to root user. + * Hence it forms a sibling of all subsequent groups formed. + * In this case, init_task_group gets only a fraction of overall + * system cpu resource, based on the weight assigned to root + * user's cpu share (INIT_TASK_GROUP_LOAD). This is accomplished + * by letting tasks of init_task_group sit in a separate cfs_rq + * (init_cfs_rq) and having one entity represent this group of + * tasks in rq->cfs (i.e init_task_group->se[] != NULL). + */ + init_tg_cfs_entry(&init_task_group, + &per_cpu(init_cfs_rq, i), + &per_cpu(init_sched_entity, i), i, 1, + root_task_group.se[i]); + +#endif +#endif /* CONFIG_FAIR_GROUP_SCHED */ + + rq->rt.rt_runtime = def_rt_bandwidth.rt_runtime; +#ifdef CONFIG_RT_GROUP_SCHED + INIT_LIST_HEAD(&rq->leaf_rt_rq_list); +#ifdef CONFIG_CGROUP_SCHED + init_tg_rt_entry(&init_task_group, &rq->rt, NULL, i, 1, NULL); +#elif defined CONFIG_USER_SCHED + init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, 0, NULL); + init_tg_rt_entry(&init_task_group, + &per_cpu(init_rt_rq, i), + &per_cpu(init_sched_rt_entity, i), i, 1, + root_task_group.rt_se[i]); +#endif +#endif + + for (j = 0; j < CPU_LOAD_IDX_MAX; j++) + rq->cpu_load[j] = 0; +#ifdef CONFIG_SMP + rq->sd = NULL; + rq->rd = NULL; + rq->active_balance = 0; + rq->next_balance = jiffies; + rq->push_cpu = 0; + rq->cpu = i; + rq->online = 0; + rq->migration_thread = NULL; + INIT_LIST_HEAD(&rq->migration_queue); + rq_attach_root(rq, &def_root_domain); +#endif + init_rq_hrtick(rq); + atomic_set(&rq->nr_iowait, 0); + } + + set_load_weight(&init_task); + +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&init_task.preempt_notifiers); +#endif + +#ifdef CONFIG_SMP + open_softirq(SCHED_SOFTIRQ, run_rebalance_domains); +#endif + +#ifdef CONFIG_RT_MUTEXES + plist_head_init(&init_task.pi_waiters, &init_task.pi_lock); +#endif + + /* + * The boot idle thread does lazy MMU switching as well: + */ + atomic_inc(&init_mm.mm_count); + enter_lazy_tlb(&init_mm, current); + + /* + * Make us the idle thread. Technically, schedule() should not be + * called from this thread, however somewhere below it might be, + * but because we are the idle thread, we just pick up running again + * when this runqueue becomes "idle". + */ + init_idle(current, smp_processor_id()); + /* + * During early bootup we pretend to be a normal task: + */ + current->sched_class = &fair_sched_class; + + scheduler_running = 1; +} + +#ifdef CONFIG_DEBUG_SPINLOCK_SLEEP +void __might_sleep(char *file, int line) +{ +#ifdef in_atomic + static unsigned long prev_jiffy; /* ratelimiting */ + + if ((in_atomic() || irqs_disabled()) && + system_state == SYSTEM_RUNNING && !oops_in_progress) { + if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy) + return; + prev_jiffy = jiffies; + printk(KERN_ERR "BUG: sleeping function called from invalid" + " context at %s:%d\n", file, line); + printk("in_atomic():%d, irqs_disabled():%d\n", + in_atomic(), irqs_disabled()); + debug_show_held_locks(current); + if (irqs_disabled()) + print_irqtrace_events(current); + dump_stack(); + } +#endif +} +EXPORT_SYMBOL(__might_sleep); +#endif + +#ifdef CONFIG_MAGIC_SYSRQ +static void normalize_task(struct rq *rq, struct task_struct *p) +{ + int on_rq; + + update_rq_clock(rq); + on_rq = p->se.on_rq; + if (on_rq) + deactivate_task(rq, p, 0); + __setscheduler(rq, p, SCHED_NORMAL, 0); + if (on_rq) { + activate_task(rq, p, 0); + resched_task(rq->curr); + } +} + +void normalize_rt_tasks(void) +{ + struct task_struct *g, *p; + unsigned long flags; + struct rq *rq; + + read_lock_irqsave(&tasklist_lock, flags); + do_each_thread(g, p) { + /* + * Only normalize user tasks: + */ + if (!p->mm) + continue; + + p->se.exec_start = 0; +#ifdef CONFIG_SCHEDSTATS + p->se.wait_start = 0; + p->se.sleep_start = 0; + p->se.block_start = 0; +#endif + + if (!rt_task(p)) { + /* + * Renice negative nice level userspace + * tasks back to 0: + */ + if (TASK_NICE(p) < 0 && p->mm) + set_user_nice(p, 0); + continue; + } + + spin_lock(&p->pi_lock); + rq = __task_rq_lock(p); + + normalize_task(rq, p); + + __task_rq_unlock(rq); + spin_unlock(&p->pi_lock); + } while_each_thread(g, p); + + read_unlock_irqrestore(&tasklist_lock, flags); +} + +#endif /* CONFIG_MAGIC_SYSRQ */ + +#ifdef CONFIG_IA64 +/* + * These functions are only useful for the IA64 MCA handling. + * + * They can only be called when the whole system has been + * stopped - every CPU needs to be quiescent, and no scheduling + * activity can take place. Using them for anything else would + * be a serious bug, and as a result, they aren't even visible + * under any other configuration. + */ + +/** + * curr_task - return the current task for a given cpu. + * @cpu: the processor in question. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + */ +struct task_struct *curr_task(int cpu) +{ + return cpu_curr(cpu); +} + +/** + * set_curr_task - set the current task for a given cpu. + * @cpu: the processor in question. + * @p: the task pointer to set. + * + * Description: This function must only be used when non-maskable interrupts + * are serviced on a separate stack. It allows the architecture to switch the + * notion of the current task on a cpu in a non-blocking manner. This function + * must be called with all CPU's synchronized, and interrupts disabled, the + * and caller must save the original value of the current task (see + * curr_task() above) and restore that value before reenabling interrupts and + * re-starting the system. + * + * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED! + */ +void set_curr_task(int cpu, struct task_struct *p) +{ + cpu_curr(cpu) = p; +} + +#endif + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void free_fair_sched_group(struct task_group *tg) +{ + int i; + + for_each_possible_cpu(i) { + if (tg->cfs_rq) + kfree(tg->cfs_rq[i]); + if (tg->se) + kfree(tg->se[i]); + } + + kfree(tg->cfs_rq); + kfree(tg->se); +} + +static +int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) +{ + struct cfs_rq *cfs_rq; + struct sched_entity *se, *parent_se; + struct rq *rq; + int i; + + tg->cfs_rq = kzalloc(sizeof(cfs_rq) * nr_cpu_ids, GFP_KERNEL); + if (!tg->cfs_rq) + goto err; + tg->se = kzalloc(sizeof(se) * nr_cpu_ids, GFP_KERNEL); + if (!tg->se) + goto err; + + tg->shares = NICE_0_LOAD; + + for_each_possible_cpu(i) { + rq = cpu_rq(i); + + cfs_rq = kmalloc_node(sizeof(struct cfs_rq), + GFP_KERNEL|__GFP_ZERO, cpu_to_node(i)); + if (!cfs_rq) + goto err; + + se = kmalloc_node(sizeof(struct sched_entity), + GFP_KERNEL|__GFP_ZERO, cpu_to_node(i)); + if (!se) + goto err; + + parent_se = parent ? parent->se[i] : NULL; + init_tg_cfs_entry(tg, cfs_rq, se, i, 0, parent_se); + } + + return 1; + + err: + return 0; +} + +static inline void register_fair_sched_group(struct task_group *tg, int cpu) +{ + list_add_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list, + &cpu_rq(cpu)->leaf_cfs_rq_list); +} + +static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) +{ + list_del_rcu(&tg->cfs_rq[cpu]->leaf_cfs_rq_list); +} +#else /* !CONFG_FAIR_GROUP_SCHED */ +static inline void free_fair_sched_group(struct task_group *tg) +{ +} + +static inline +int alloc_fair_sched_group(struct task_group *tg, struct task_group *parent) +{ + return 1; +} + +static inline void register_fair_sched_group(struct task_group *tg, int cpu) +{ +} + +static inline void unregister_fair_sched_group(struct task_group *tg, int cpu) +{ +} +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +#ifdef CONFIG_RT_GROUP_SCHED +static void free_rt_sched_group(struct task_group *tg) +{ + int i; + + destroy_rt_bandwidth(&tg->rt_bandwidth); + + for_each_possible_cpu(i) { + if (tg->rt_rq) + kfree(tg->rt_rq[i]); + if (tg->rt_se) + kfree(tg->rt_se[i]); + } + + kfree(tg->rt_rq); + kfree(tg->rt_se); +} + +static +int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) +{ + struct rt_rq *rt_rq; + struct sched_rt_entity *rt_se, *parent_se; + struct rq *rq; + int i; + + tg->rt_rq = kzalloc(sizeof(rt_rq) * nr_cpu_ids, GFP_KERNEL); + if (!tg->rt_rq) + goto err; + tg->rt_se = kzalloc(sizeof(rt_se) * nr_cpu_ids, GFP_KERNEL); + if (!tg->rt_se) + goto err; + + init_rt_bandwidth(&tg->rt_bandwidth, + ktime_to_ns(def_rt_bandwidth.rt_period), 0); + + for_each_possible_cpu(i) { + rq = cpu_rq(i); + + rt_rq = kmalloc_node(sizeof(struct rt_rq), + GFP_KERNEL|__GFP_ZERO, cpu_to_node(i)); + if (!rt_rq) + goto err; + + rt_se = kmalloc_node(sizeof(struct sched_rt_entity), + GFP_KERNEL|__GFP_ZERO, cpu_to_node(i)); + if (!rt_se) + goto err; + + parent_se = parent ? parent->rt_se[i] : NULL; + init_tg_rt_entry(tg, rt_rq, rt_se, i, 0, parent_se); + } + + return 1; + + err: + return 0; +} + +static inline void register_rt_sched_group(struct task_group *tg, int cpu) +{ + list_add_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list, + &cpu_rq(cpu)->leaf_rt_rq_list); +} + +static inline void unregister_rt_sched_group(struct task_group *tg, int cpu) +{ + list_del_rcu(&tg->rt_rq[cpu]->leaf_rt_rq_list); +} +#else /* !CONFIG_RT_GROUP_SCHED */ +static inline void free_rt_sched_group(struct task_group *tg) +{ +} + +static inline +int alloc_rt_sched_group(struct task_group *tg, struct task_group *parent) +{ + return 1; +} + +static inline void register_rt_sched_group(struct task_group *tg, int cpu) +{ +} + +static inline void unregister_rt_sched_group(struct task_group *tg, int cpu) +{ +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +#ifdef CONFIG_GROUP_SCHED +static void free_sched_group(struct task_group *tg) +{ + free_fair_sched_group(tg); + free_rt_sched_group(tg); + kfree(tg); +} + +/* allocate runqueue etc for a new task group */ +struct task_group *sched_create_group(struct task_group *parent) +{ + struct task_group *tg; + unsigned long flags; + int i; + + tg = kzalloc(sizeof(*tg), GFP_KERNEL); + if (!tg) + return ERR_PTR(-ENOMEM); + + if (!alloc_fair_sched_group(tg, parent)) + goto err; + + if (!alloc_rt_sched_group(tg, parent)) + goto err; + + spin_lock_irqsave(&task_group_lock, flags); + for_each_possible_cpu(i) { + register_fair_sched_group(tg, i); + register_rt_sched_group(tg, i); + } + list_add_rcu(&tg->list, &task_groups); + + WARN_ON(!parent); /* root should already exist */ + + tg->parent = parent; + INIT_LIST_HEAD(&tg->children); + list_add_rcu(&tg->siblings, &parent->children); + spin_unlock_irqrestore(&task_group_lock, flags); + + return tg; + +err: + free_sched_group(tg); + return ERR_PTR(-ENOMEM); +} + +/* rcu callback to free various structures associated with a task group */ +static void free_sched_group_rcu(struct rcu_head *rhp) +{ + /* now it should be safe to free those cfs_rqs */ + free_sched_group(container_of(rhp, struct task_group, rcu)); +} + +/* Destroy runqueue etc associated with a task group */ +void sched_destroy_group(struct task_group *tg) +{ + unsigned long flags; + int i; + + spin_lock_irqsave(&task_group_lock, flags); + for_each_possible_cpu(i) { + unregister_fair_sched_group(tg, i); + unregister_rt_sched_group(tg, i); + } + list_del_rcu(&tg->list); + list_del_rcu(&tg->siblings); + spin_unlock_irqrestore(&task_group_lock, flags); + + /* wait for possible concurrent references to cfs_rqs complete */ + call_rcu(&tg->rcu, free_sched_group_rcu); +} + +/* change task's runqueue when it moves between groups. + * The caller of this function should have put the task in its new group + * by now. This function just updates tsk->se.cfs_rq and tsk->se.parent to + * reflect its new group. + */ +void sched_move_task(struct task_struct *tsk) +{ + int on_rq, running; + unsigned long flags; + struct rq *rq; + + rq = task_rq_lock(tsk, &flags); + + update_rq_clock(rq); + + running = task_current(rq, tsk); + on_rq = tsk->se.on_rq; + + if (on_rq) + dequeue_task(rq, tsk, 0); + if (unlikely(running)) + tsk->sched_class->put_prev_task(rq, tsk); + + set_task_rq(tsk, task_cpu(tsk)); + +#ifdef CONFIG_FAIR_GROUP_SCHED + if (tsk->sched_class->moved_group) + tsk->sched_class->moved_group(tsk); +#endif + + if (unlikely(running)) + tsk->sched_class->set_curr_task(rq); + if (on_rq) + enqueue_task(rq, tsk, 0); + + task_rq_unlock(rq, &flags); +} +#endif /* CONFIG_GROUP_SCHED */ + +#ifdef CONFIG_FAIR_GROUP_SCHED +static void __set_se_shares(struct sched_entity *se, unsigned long shares) +{ + struct cfs_rq *cfs_rq = se->cfs_rq; + int on_rq; + + on_rq = se->on_rq; + if (on_rq) + dequeue_entity(cfs_rq, se, 0); + + se->load.weight = shares; + se->load.inv_weight = 0; + + if (on_rq) + enqueue_entity(cfs_rq, se, 0); +} + +static void set_se_shares(struct sched_entity *se, unsigned long shares) +{ + struct cfs_rq *cfs_rq = se->cfs_rq; + struct rq *rq = cfs_rq->rq; + unsigned long flags; + + spin_lock_irqsave(&rq->lock, flags); + __set_se_shares(se, shares); + spin_unlock_irqrestore(&rq->lock, flags); +} + +static DEFINE_MUTEX(shares_mutex); + +int sched_group_set_shares(struct task_group *tg, unsigned long shares) +{ + int i; + unsigned long flags; + + /* + * We can't change the weight of the root cgroup. + */ + if (!tg->se[0]) + return -EINVAL; + + if (shares < MIN_SHARES) + shares = MIN_SHARES; + else if (shares > MAX_SHARES) + shares = MAX_SHARES; + + mutex_lock(&shares_mutex); + if (tg->shares == shares) + goto done; + + spin_lock_irqsave(&task_group_lock, flags); + for_each_possible_cpu(i) + unregister_fair_sched_group(tg, i); + list_del_rcu(&tg->siblings); + spin_unlock_irqrestore(&task_group_lock, flags); + + /* wait for any ongoing reference to this group to finish */ + synchronize_sched(); + + /* + * Now we are free to modify the group's share on each cpu + * w/o tripping rebalance_share or load_balance_fair. + */ + tg->shares = shares; + for_each_possible_cpu(i) { + /* + * force a rebalance + */ + cfs_rq_set_shares(tg->cfs_rq[i], 0); + set_se_shares(tg->se[i], shares); + } + + /* + * Enable load balance activity on this group, by inserting it back on + * each cpu's rq->leaf_cfs_rq_list. + */ + spin_lock_irqsave(&task_group_lock, flags); + for_each_possible_cpu(i) + register_fair_sched_group(tg, i); + list_add_rcu(&tg->siblings, &tg->parent->children); + spin_unlock_irqrestore(&task_group_lock, flags); +done: + mutex_unlock(&shares_mutex); + return 0; +} + +unsigned long sched_group_shares(struct task_group *tg) +{ + return tg->shares; +} +#endif + +#ifdef CONFIG_RT_GROUP_SCHED +/* + * Ensure that the real time constraints are schedulable. + */ +static DEFINE_MUTEX(rt_constraints_mutex); + +static unsigned long to_ratio(u64 period, u64 runtime) +{ + if (runtime == RUNTIME_INF) + return 1ULL << 16; + + return div64_u64(runtime << 16, period); +} + +#ifdef CONFIG_CGROUP_SCHED +static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) +{ + struct task_group *tgi, *parent = tg->parent; + unsigned long total = 0; + + if (!parent) { + if (global_rt_period() < period) + return 0; + + return to_ratio(period, runtime) < + to_ratio(global_rt_period(), global_rt_runtime()); + } + + if (ktime_to_ns(parent->rt_bandwidth.rt_period) < period) + return 0; + + rcu_read_lock(); + list_for_each_entry_rcu(tgi, &parent->children, siblings) { + if (tgi == tg) + continue; + + total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period), + tgi->rt_bandwidth.rt_runtime); + } + rcu_read_unlock(); + + return total + to_ratio(period, runtime) <= + to_ratio(ktime_to_ns(parent->rt_bandwidth.rt_period), + parent->rt_bandwidth.rt_runtime); +} +#elif defined CONFIG_USER_SCHED +static int __rt_schedulable(struct task_group *tg, u64 period, u64 runtime) +{ + struct task_group *tgi; + unsigned long total = 0; + unsigned long global_ratio = + to_ratio(global_rt_period(), global_rt_runtime()); + + rcu_read_lock(); + list_for_each_entry_rcu(tgi, &task_groups, list) { + if (tgi == tg) + continue; + + total += to_ratio(ktime_to_ns(tgi->rt_bandwidth.rt_period), + tgi->rt_bandwidth.rt_runtime); + } + rcu_read_unlock(); + + return total + to_ratio(period, runtime) < global_ratio; +} +#endif + +/* Must be called with tasklist_lock held */ +static inline int tg_has_rt_tasks(struct task_group *tg) +{ + struct task_struct *g, *p; + do_each_thread(g, p) { + if (rt_task(p) && rt_rq_of_se(&p->rt)->tg == tg) + return 1; + } while_each_thread(g, p); + return 0; +} + +static int tg_set_bandwidth(struct task_group *tg, + u64 rt_period, u64 rt_runtime) +{ + int i, err = 0; + + mutex_lock(&rt_constraints_mutex); + read_lock(&tasklist_lock); + if (rt_runtime == 0 && tg_has_rt_tasks(tg)) { + err = -EBUSY; + goto unlock; + } + if (!__rt_schedulable(tg, rt_period, rt_runtime)) { + err = -EINVAL; + goto unlock; + } + + spin_lock_irq(&tg->rt_bandwidth.rt_runtime_lock); + tg->rt_bandwidth.rt_period = ns_to_ktime(rt_period); + tg->rt_bandwidth.rt_runtime = rt_runtime; + + for_each_possible_cpu(i) { + struct rt_rq *rt_rq = tg->rt_rq[i]; + + spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = rt_runtime; + spin_unlock(&rt_rq->rt_runtime_lock); + } + spin_unlock_irq(&tg->rt_bandwidth.rt_runtime_lock); + unlock: + read_unlock(&tasklist_lock); + mutex_unlock(&rt_constraints_mutex); + + return err; +} + +int sched_group_set_rt_runtime(struct task_group *tg, long rt_runtime_us) +{ + u64 rt_runtime, rt_period; + + rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); + rt_runtime = (u64)rt_runtime_us * NSEC_PER_USEC; + if (rt_runtime_us < 0) + rt_runtime = RUNTIME_INF; + + return tg_set_bandwidth(tg, rt_period, rt_runtime); +} + +long sched_group_rt_runtime(struct task_group *tg) +{ + u64 rt_runtime_us; + + if (tg->rt_bandwidth.rt_runtime == RUNTIME_INF) + return -1; + + rt_runtime_us = tg->rt_bandwidth.rt_runtime; + do_div(rt_runtime_us, NSEC_PER_USEC); + return rt_runtime_us; +} + +int sched_group_set_rt_period(struct task_group *tg, long rt_period_us) +{ + u64 rt_runtime, rt_period; + + rt_period = (u64)rt_period_us * NSEC_PER_USEC; + rt_runtime = tg->rt_bandwidth.rt_runtime; + + if (rt_period == 0) + return -EINVAL; + + return tg_set_bandwidth(tg, rt_period, rt_runtime); +} + +long sched_group_rt_period(struct task_group *tg) +{ + u64 rt_period_us; + + rt_period_us = ktime_to_ns(tg->rt_bandwidth.rt_period); + do_div(rt_period_us, NSEC_PER_USEC); + return rt_period_us; +} + +static int sched_rt_global_constraints(void) +{ + struct task_group *tg = &root_task_group; + u64 rt_runtime, rt_period; + int ret = 0; + + if (sysctl_sched_rt_period <= 0) + return -EINVAL; + + rt_period = ktime_to_ns(tg->rt_bandwidth.rt_period); + rt_runtime = tg->rt_bandwidth.rt_runtime; + + mutex_lock(&rt_constraints_mutex); + if (!__rt_schedulable(tg, rt_period, rt_runtime)) + ret = -EINVAL; + mutex_unlock(&rt_constraints_mutex); + + return ret; +} +#else /* !CONFIG_RT_GROUP_SCHED */ +static int sched_rt_global_constraints(void) +{ + unsigned long flags; + int i; + + if (sysctl_sched_rt_period <= 0) + return -EINVAL; + + spin_lock_irqsave(&def_rt_bandwidth.rt_runtime_lock, flags); + for_each_possible_cpu(i) { + struct rt_rq *rt_rq = &cpu_rq(i)->rt; + + spin_lock(&rt_rq->rt_runtime_lock); + rt_rq->rt_runtime = global_rt_runtime(); + spin_unlock(&rt_rq->rt_runtime_lock); + } + spin_unlock_irqrestore(&def_rt_bandwidth.rt_runtime_lock, flags); + + return 0; +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +int sched_rt_handler(struct ctl_table *table, int write, + struct file *filp, void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + int old_period, old_runtime; + static DEFINE_MUTEX(mutex); + + mutex_lock(&mutex); + old_period = sysctl_sched_rt_period; + old_runtime = sysctl_sched_rt_runtime; + + ret = proc_dointvec(table, write, filp, buffer, lenp, ppos); + + if (!ret && write) { + ret = sched_rt_global_constraints(); + if (ret) { + sysctl_sched_rt_period = old_period; + sysctl_sched_rt_runtime = old_runtime; + } else { + def_rt_bandwidth.rt_runtime = global_rt_runtime(); + def_rt_bandwidth.rt_period = + ns_to_ktime(global_rt_period()); + } + } + mutex_unlock(&mutex); + + return ret; +} + +#ifdef CONFIG_CGROUP_SCHED + +/* return corresponding task_group object of a cgroup */ +static inline struct task_group *cgroup_tg(struct cgroup *cgrp) +{ + return container_of(cgroup_subsys_state(cgrp, cpu_cgroup_subsys_id), + struct task_group, css); +} + +static struct cgroup_subsys_state * +cpu_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct task_group *tg, *parent; + + if (!cgrp->parent) { + /* This is early initialization for the top cgroup */ + init_task_group.css.cgroup = cgrp; + return &init_task_group.css; + } + + parent = cgroup_tg(cgrp->parent); + tg = sched_create_group(parent); + if (IS_ERR(tg)) + return ERR_PTR(-ENOMEM); + + /* Bind the cgroup to task_group object we just created */ + tg->css.cgroup = cgrp; + + return &tg->css; +} + +static void +cpu_cgroup_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct task_group *tg = cgroup_tg(cgrp); + + sched_destroy_group(tg); +} + +static int +cpu_cgroup_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct task_struct *tsk) +{ +#ifdef CONFIG_RT_GROUP_SCHED + /* Don't accept realtime tasks when there is no way for them to run */ + if (rt_task(tsk) && cgroup_tg(cgrp)->rt_bandwidth.rt_runtime == 0) + return -EINVAL; +#else + /* We don't support RT-tasks being in separate groups */ + if (tsk->sched_class != &fair_sched_class) + return -EINVAL; +#endif + + return 0; +} + +static void +cpu_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp, + struct cgroup *old_cont, struct task_struct *tsk) +{ + sched_move_task(tsk); +} + +#ifdef CONFIG_FAIR_GROUP_SCHED +static int cpu_shares_write_u64(struct cgroup *cgrp, struct cftype *cftype, + u64 shareval) +{ + return sched_group_set_shares(cgroup_tg(cgrp), shareval); +} + +static u64 cpu_shares_read_u64(struct cgroup *cgrp, struct cftype *cft) +{ + struct task_group *tg = cgroup_tg(cgrp); + + return (u64) tg->shares; +} +#endif /* CONFIG_FAIR_GROUP_SCHED */ + +#ifdef CONFIG_RT_GROUP_SCHED +static int cpu_rt_runtime_write(struct cgroup *cgrp, struct cftype *cft, + s64 val) +{ + return sched_group_set_rt_runtime(cgroup_tg(cgrp), val); +} + +static s64 cpu_rt_runtime_read(struct cgroup *cgrp, struct cftype *cft) +{ + return sched_group_rt_runtime(cgroup_tg(cgrp)); +} + +static int cpu_rt_period_write_uint(struct cgroup *cgrp, struct cftype *cftype, + u64 rt_period_us) +{ + return sched_group_set_rt_period(cgroup_tg(cgrp), rt_period_us); +} + +static u64 cpu_rt_period_read_uint(struct cgroup *cgrp, struct cftype *cft) +{ + return sched_group_rt_period(cgroup_tg(cgrp)); +} +#endif /* CONFIG_RT_GROUP_SCHED */ + +static struct cftype cpu_files[] = { +#ifdef CONFIG_FAIR_GROUP_SCHED + { + .name = "shares", + .read_u64 = cpu_shares_read_u64, + .write_u64 = cpu_shares_write_u64, + }, +#endif +#ifdef CONFIG_RT_GROUP_SCHED + { + .name = "rt_runtime_us", + .read_s64 = cpu_rt_runtime_read, + .write_s64 = cpu_rt_runtime_write, + }, + { + .name = "rt_period_us", + .read_u64 = cpu_rt_period_read_uint, + .write_u64 = cpu_rt_period_write_uint, + }, +#endif +}; + +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, + .destroy = cpu_cgroup_destroy, + .can_attach = cpu_cgroup_can_attach, + .attach = cpu_cgroup_attach, + .populate = cpu_cgroup_populate, + .subsys_id = cpu_cgroup_subsys_id, + .early_init = 1, +}; + +#endif /* CONFIG_CGROUP_SCHED */ + +#ifdef CONFIG_CGROUP_CPUACCT + +/* + * CPU accounting code for task groups. + * + * Based on the work by Paul Menage (menage@google.com) and Balbir Singh + * (balbir@in.ibm.com). + */ + +/* track cpu usage of a group of tasks */ +struct cpuacct { + struct cgroup_subsys_state css; + /* cpuusage holds pointer to a u64-type object on every cpu */ + u64 *cpuusage; +}; + +struct cgroup_subsys cpuacct_subsys; + +/* return cpu accounting group corresponding to this container */ +static inline struct cpuacct *cgroup_ca(struct cgroup *cgrp) +{ + return container_of(cgroup_subsys_state(cgrp, cpuacct_subsys_id), + struct cpuacct, css); +} + +/* return cpu accounting group to which this task belongs */ +static inline struct cpuacct *task_ca(struct task_struct *tsk) +{ + return container_of(task_subsys_state(tsk, cpuacct_subsys_id), + struct cpuacct, css); +} + +/* create a new cpu accounting group */ +static struct cgroup_subsys_state *cpuacct_create( + struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct cpuacct *ca = kzalloc(sizeof(*ca), GFP_KERNEL); + + if (!ca) + return ERR_PTR(-ENOMEM); + + ca->cpuusage = alloc_percpu(u64); + if (!ca->cpuusage) { + kfree(ca); + return ERR_PTR(-ENOMEM); + } + + return &ca->css; +} + +/* destroy an existing cpu accounting group */ +static void +cpuacct_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + + free_percpu(ca->cpuusage); + kfree(ca); +} + +/* return total cpu usage (in nanoseconds) of a group */ +static u64 cpuusage_read(struct cgroup *cgrp, struct cftype *cft) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + u64 totalcpuusage = 0; + int i; + + for_each_possible_cpu(i) { + u64 *cpuusage = percpu_ptr(ca->cpuusage, i); + + /* + * Take rq->lock to make 64-bit addition safe on 32-bit + * platforms. + */ + spin_lock_irq(&cpu_rq(i)->lock); + totalcpuusage += *cpuusage; + spin_unlock_irq(&cpu_rq(i)->lock); + } + + return totalcpuusage; +} + +static int cpuusage_write(struct cgroup *cgrp, struct cftype *cftype, + u64 reset) +{ + struct cpuacct *ca = cgroup_ca(cgrp); + int err = 0; + int i; + + if (reset) { + err = -EINVAL; + goto out; + } + + for_each_possible_cpu(i) { + u64 *cpuusage = percpu_ptr(ca->cpuusage, i); + + spin_lock_irq(&cpu_rq(i)->lock); + *cpuusage = 0; + spin_unlock_irq(&cpu_rq(i)->lock); + } +out: + return err; +} + +static struct cftype files[] = { + { + .name = "usage", + .read_u64 = cpuusage_read, + .write_u64 = cpuusage_write, + }, +}; + +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. + * + * called with rq->lock held. + */ +static void cpuacct_charge(struct task_struct *tsk, u64 cputime) +{ + struct cpuacct *ca; + + if (!cpuacct_subsys.active) + return; + + ca = task_ca(tsk); + if (ca) { + u64 *cpuusage = percpu_ptr(ca->cpuusage, task_cpu(tsk)); + + *cpuusage += cputime; + } +} + +struct cgroup_subsys cpuacct_subsys = { + .name = "cpuacct", + .create = cpuacct_create, + .destroy = cpuacct_destroy, + .populate = cpuacct_populate, + .subsys_id = cpuacct_subsys_id, +}; +#endif /* CONFIG_CGROUP_CPUACCT */ diff -Nurb linux-2.6.27-590/kernel/sched.c.rej linux-2.6.27-591/kernel/sched.c.rej --- linux-2.6.27-590/kernel/sched.c.rej 1969-12-31 19:00:00.000000000 -0500 +++ linux-2.6.27-591/kernel/sched.c.rej 2010-02-01 19:43:07.000000000 -0500 @@ -0,0 +1,258 @@ +*************** +*** 23,28 **** + #include + #include + #include + #include + #include + #include +--- 23,29 ---- + #include + #include + #include ++ #include + #include + #include + #include +*************** +*** 451,456 **** + + repeat_lock_task: + rq = task_rq(p); + spin_lock(&rq->lock); + if (unlikely(rq != task_rq(p))) { + spin_unlock(&rq->lock); +--- 455,461 ---- + + repeat_lock_task: + rq = task_rq(p); ++ + spin_lock(&rq->lock); + if (unlikely(rq != task_rq(p))) { + spin_unlock(&rq->lock); +*************** +*** 1761,1766 **** + * event cannot wake it up and insert it on the runqueue either. + */ + p->state = TASK_RUNNING; + + /* + * Make sure we do not leak PI boosting priority to the child: +--- 1766,1786 ---- + * event cannot wake it up and insert it on the runqueue either. + */ + p->state = TASK_RUNNING; ++ #ifdef CONFIG_CHOPSTIX ++ /* The jiffy of last interruption */ ++ if (p->state & TASK_UNINTERRUPTIBLE) { ++ p->last_interrupted=jiffies; ++ } ++ else ++ if (p->state & TASK_INTERRUPTIBLE) { ++ p->last_interrupted=INTERRUPTIBLE; ++ } ++ else ++ p->last_interrupted=RUNNING; ++ ++ /* The jiffy of last execution */ ++ p->last_ran_j=jiffies; ++ #endif + + /* + * Make sure we do not leak PI boosting priority to the child: +*************** +*** 3628,3633 **** + + #endif + + static inline int interactive_sleep(enum sleep_type sleep_type) + { + return (sleep_type == SLEEP_INTERACTIVE || +--- 3648,3654 ---- + + #endif + ++ + static inline int interactive_sleep(enum sleep_type sleep_type) + { + return (sleep_type == SLEEP_INTERACTIVE || +*************** +*** 3637,3652 **** + /* + * schedule() is the main scheduler function. + */ + asmlinkage void __sched schedule(void) + { + struct task_struct *prev, *next; + struct prio_array *array; + struct list_head *queue; + unsigned long long now; +- unsigned long run_time; + int cpu, idx, new_prio; + long *switch_count; + struct rq *rq; + + /* + * Test if we are atomic. Since do_exit() needs to call into +--- 3658,3685 ---- + /* + * schedule() is the main scheduler function. + */ ++ ++ #ifdef CONFIG_CHOPSTIX ++ extern void (*rec_event)(void *,unsigned int); ++ struct event_spec { ++ unsigned long pc; ++ unsigned long dcookie; ++ unsigned int count; ++ unsigned int reason; ++ }; ++ #endif ++ + asmlinkage void __sched schedule(void) + { + struct task_struct *prev, *next; + struct prio_array *array; + struct list_head *queue; + unsigned long long now; ++ unsigned long run_time, diff; + int cpu, idx, new_prio; + long *switch_count; + struct rq *rq; ++ int sampling_reason; + + /* + * Test if we are atomic. Since do_exit() needs to call into +*************** +*** 3700,3705 **** + switch_count = &prev->nivcsw; + if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { + switch_count = &prev->nvcsw; + if (unlikely((prev->state & TASK_INTERRUPTIBLE) && + unlikely(signal_pending(prev)))) + prev->state = TASK_RUNNING; +--- 3733,3739 ---- + switch_count = &prev->nivcsw; + if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) { + switch_count = &prev->nvcsw; ++ + if (unlikely((prev->state & TASK_INTERRUPTIBLE) && + unlikely(signal_pending(prev)))) + prev->state = TASK_RUNNING; +*************** +*** 3709,3714 **** + vx_uninterruptible_inc(prev); + } + deactivate_task(prev, rq); + } + } + +--- 3743,3759 ---- + vx_uninterruptible_inc(prev); + } + deactivate_task(prev, rq); ++ #ifdef CONFIG_CHOPSTIX ++ /* An uninterruptible process just yielded. Record the current jiffie */ ++ if (prev->state & TASK_UNINTERRUPTIBLE) { ++ prev->last_interrupted=jiffies; ++ } ++ /* An interruptible process just yielded, or it got preempted. ++ * Mark it as interruptible */ ++ else if (prev->state & TASK_INTERRUPTIBLE) { ++ prev->last_interrupted=INTERRUPTIBLE; ++ } ++ #endif + } + } + +*************** +*** 3785,3790 **** + prev->sleep_avg = 0; + prev->timestamp = prev->last_ran = now; + + sched_info_switch(prev, next); + if (likely(prev != next)) { + next->timestamp = next->last_ran = now; +--- 3830,3869 ---- + prev->sleep_avg = 0; + prev->timestamp = prev->last_ran = now; + ++ #ifdef CONFIG_CHOPSTIX ++ /* Run only if the Chopstix module so decrees it */ ++ if (rec_event) { ++ prev->last_ran_j = jiffies; ++ if (next->last_interrupted!=INTERRUPTIBLE) { ++ if (next->last_interrupted!=RUNNING) { ++ diff = (jiffies-next->last_interrupted); ++ sampling_reason = 0;/* BLOCKING */ ++ } ++ else { ++ diff = jiffies-next->last_ran_j; ++ sampling_reason = 1;/* PREEMPTION */ ++ } ++ ++ if (diff >= HZ/10) { ++ struct event event; ++ struct event_spec espec; ++ struct pt_regs *regs; ++ regs = task_pt_regs(current); ++ ++ espec.reason = sampling_reason; ++ event.event_data=&espec; ++ event.task=next; ++ espec.pc=regs->eip; ++ event.event_type=2; ++ /* index in the event array currently set up */ ++ /* make sure the counters are loaded in the order we want them to show up*/ ++ (*rec_event)(&event, diff); ++ } ++ } ++ /* next has been elected to run */ ++ next->last_interrupted=0; ++ } ++ #endif + sched_info_switch(prev, next); + if (likely(prev != next)) { + next->timestamp = next->last_ran = now; +*************** +*** 5737,5742 **** + jiffies_to_timespec(p->policy == SCHED_FIFO ? + 0 : task_timeslice(p), &t); + read_unlock(&tasklist_lock); + retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; + out_nounlock: + return retval; +--- 5817,5823 ---- + jiffies_to_timespec(p->policy == SCHED_FIFO ? + 0 : task_timeslice(p), &t); + read_unlock(&tasklist_lock); ++ + retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; + out_nounlock: + return retval; +*************** +*** 7980,7982 **** + } + + #endif +--- 8061,8080 ---- + } + + #endif ++ ++ #ifdef CONFIG_CHOPSTIX ++ void (*rec_event)(void *,unsigned int) = NULL; ++ ++ /* To support safe calling from asm */ ++ asmlinkage void rec_event_asm (struct event *event_signature_in, unsigned int count) { ++ struct pt_regs *regs; ++ struct event_spec *es = event_signature_in->event_data; ++ regs = task_pt_regs(current); ++ event_signature_in->task=current; ++ es->pc=regs->eip; ++ event_signature_in->count=1; ++ (*rec_event)(event_signature_in, count); ++ } ++ EXPORT_SYMBOL(rec_event); ++ EXPORT_SYMBOL(in_sched_functions); ++ #endif diff -Nurb linux-2.6.27-590/mm/memory.c linux-2.6.27-591/mm/memory.c --- linux-2.6.27-590/mm/memory.c 2010-02-01 19:42:07.000000000 -0500 +++ linux-2.6.27-591/mm/memory.c 2010-02-01 19:43:07.000000000 -0500 @@ -61,6 +61,7 @@ #include #include +#include #include "internal.h" @@ -2690,6 +2691,15 @@ return ret; } +extern void (*rec_event)(void *,unsigned int); +struct event_spec { + unsigned long pc; + unsigned long dcookie; + unsigned count; + unsigned char reason; +}; + + /* * By the time we get here, we already hold the mm semaphore */ @@ -2719,6 +2729,24 @@ if (!pte) return VM_FAULT_OOM; +#ifdef CONFIG_CHOPSTIX + if (rec_event) { + struct event event; + struct event_spec espec; + struct pt_regs *regs; + unsigned int pc; + regs = task_pt_regs(current); + pc = regs->ip & (unsigned int) ~4095; + + espec.reason = 0; /* alloc */ + event.event_data=&espec; + event.task = current; + espec.pc=pc; + event.event_type=5; + (*rec_event)(&event, 1); + } +#endif + return handle_pte_fault(mm, vma, address, pte, pmd, write_access); } diff -Nurb linux-2.6.27-590/mm/memory.c.orig linux-2.6.27-591/mm/memory.c.orig --- linux-2.6.27-590/mm/memory.c.orig 1969-12-31 19:00:00.000000000 -0500 +++ linux-2.6.27-591/mm/memory.c.orig 2010-02-01 19:42:07.000000000 -0500 @@ -0,0 +1,3035 @@ +/* + * linux/mm/memory.c + * + * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds + */ + +/* + * demand-loading started 01.12.91 - seems it is high on the list of + * things wanted, and it should be easy to implement. - Linus + */ + +/* + * Ok, demand-loading was easy, shared pages a little bit tricker. Shared + * pages started 02.12.91, seems to work. - Linus. + * + * Tested sharing by executing about 30 /bin/sh: under the old kernel it + * would have taken more than the 6M I have free, but it worked well as + * far as I could see. + * + * Also corrected some "invalidate()"s - I wasn't doing enough of them. + */ + +/* + * Real VM (paging to/from disk) started 18.12.91. Much more work and + * thought has to go into this. Oh, well.. + * 19.12.91 - works, somewhat. Sometimes I get faults, don't know why. + * Found it. Everything seems to work now. + * 20.12.91 - Ok, making the swap-device changeable like the root. + */ + +/* + * 05.04.94 - Multi-page memory management added for v1.1. + * Idea by Alex Bligh (alex@cconcepts.co.uk) + * + * 16.07.99 - Support of BIGMEM added by Gerhard Wichert, Siemens AG + * (Gerhard.Wichert@pdb.siemens.de) + * + * Aug/Sep 2004 Changed to four level page tables (Andi Kleen) + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include +#include +#include + +#include +#include + +#include "internal.h" + +#ifndef CONFIG_NEED_MULTIPLE_NODES +/* use the per-pgdat data instead for discontigmem - mbligh */ +unsigned long max_mapnr; +struct page *mem_map; + +EXPORT_SYMBOL(max_mapnr); +EXPORT_SYMBOL(mem_map); +#endif + +unsigned long num_physpages; +/* + * A number of key systems in x86 including ioremap() rely on the assumption + * that high_memory defines the upper bound on direct map memory, then end + * of ZONE_NORMAL. Under CONFIG_DISCONTIG this means that max_low_pfn and + * highstart_pfn must be the same; there must be no gap between ZONE_NORMAL + * and ZONE_HIGHMEM. + */ +void * high_memory; + +EXPORT_SYMBOL(num_physpages); +EXPORT_SYMBOL(high_memory); + +/* + * Randomize the address space (stacks, mmaps, brk, etc.). + * + * ( When CONFIG_COMPAT_BRK=y we exclude brk from randomization, + * as ancient (libc5 based) binaries can segfault. ) + */ +int randomize_va_space __read_mostly = +#ifdef CONFIG_COMPAT_BRK + 1; +#else + 2; +#endif + +static int __init disable_randmaps(char *s) +{ + randomize_va_space = 0; + return 1; +} +__setup("norandmaps", disable_randmaps); + + +/* + * If a p?d_bad entry is found while walking page tables, report + * the error, before resetting entry to p?d_none. Usually (but + * very seldom) called out from the p?d_none_or_clear_bad macros. + */ + +void pgd_clear_bad(pgd_t *pgd) +{ + pgd_ERROR(*pgd); + pgd_clear(pgd); +} + +void pud_clear_bad(pud_t *pud) +{ + pud_ERROR(*pud); + pud_clear(pud); +} + +void pmd_clear_bad(pmd_t *pmd) +{ + pmd_ERROR(*pmd); + pmd_clear(pmd); +} + +/* + * Note: this doesn't free the actual pages themselves. That + * has been handled earlier when unmapping all the memory regions. + */ +static void free_pte_range(struct mmu_gather *tlb, pmd_t *pmd) +{ + pgtable_t token = pmd_pgtable(*pmd); + pmd_clear(pmd); + pte_free_tlb(tlb, token); + tlb->mm->nr_ptes--; +} + +static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + pmd_t *pmd; + unsigned long next; + unsigned long start; + + start = addr; + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if (pmd_none_or_clear_bad(pmd)) + continue; + free_pte_range(tlb, pmd); + } while (pmd++, addr = next, addr != end); + + start &= PUD_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= PUD_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + + pmd = pmd_offset(pud, start); + pud_clear(pud); + pmd_free_tlb(tlb, pmd); +} + +static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + pud_t *pud; + unsigned long next; + unsigned long start; + + start = addr; + pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(pud)) + continue; + free_pmd_range(tlb, pud, addr, next, floor, ceiling); + } while (pud++, addr = next, addr != end); + + start &= PGDIR_MASK; + if (start < floor) + return; + if (ceiling) { + ceiling &= PGDIR_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + return; + + pud = pud_offset(pgd, start); + pgd_clear(pgd); + pud_free_tlb(tlb, pud); +} + +/* + * This function frees user-level page tables of a process. + * + * Must be called with pagetable lock held. + */ +void free_pgd_range(struct mmu_gather *tlb, + unsigned long addr, unsigned long end, + unsigned long floor, unsigned long ceiling) +{ + pgd_t *pgd; + unsigned long next; + unsigned long start; + + /* + * The next few lines have given us lots of grief... + * + * Why are we testing PMD* at this top level? Because often + * there will be no work to do at all, and we'd prefer not to + * go all the way down to the bottom just to discover that. + * + * Why all these "- 1"s? Because 0 represents both the bottom + * of the address space and the top of it (using -1 for the + * top wouldn't help much: the masks would do the wrong thing). + * The rule is that addr 0 and floor 0 refer to the bottom of + * the address space, but end 0 and ceiling 0 refer to the top + * Comparisons need to use "end - 1" and "ceiling - 1" (though + * that end 0 case should be mythical). + * + * Wherever addr is brought up or ceiling brought down, we must + * be careful to reject "the opposite 0" before it confuses the + * subsequent tests. But what about where end is brought down + * by PMD_SIZE below? no, end can't go down to 0 there. + * + * Whereas we round start (addr) and ceiling down, by different + * masks at different levels, in order to test whether a table + * now has no other vmas using it, so can be freed, we don't + * bother to round floor or end up - the tests don't need that. + */ + + addr &= PMD_MASK; + if (addr < floor) { + addr += PMD_SIZE; + if (!addr) + return; + } + if (ceiling) { + ceiling &= PMD_MASK; + if (!ceiling) + return; + } + if (end - 1 > ceiling - 1) + end -= PMD_SIZE; + if (addr > end - 1) + return; + + start = addr; + pgd = pgd_offset(tlb->mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) + continue; + free_pud_range(tlb, pgd, addr, next, floor, ceiling); + } while (pgd++, addr = next, addr != end); +} + +void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *vma, + unsigned long floor, unsigned long ceiling) +{ + while (vma) { + struct vm_area_struct *next = vma->vm_next; + unsigned long addr = vma->vm_start; + + /* + * Hide vma from rmap and vmtruncate before freeing pgtables + */ + anon_vma_unlink(vma); + unlink_file_vma(vma); + + if (is_vm_hugetlb_page(vma)) { + hugetlb_free_pgd_range(tlb, addr, vma->vm_end, + floor, next? next->vm_start: ceiling); + } else { + /* + * Optimization: gather nearby vmas into one call down + */ + while (next && next->vm_start <= vma->vm_end + PMD_SIZE + && !is_vm_hugetlb_page(next)) { + vma = next; + next = vma->vm_next; + anon_vma_unlink(vma); + unlink_file_vma(vma); + } + free_pgd_range(tlb, addr, vma->vm_end, + floor, next? next->vm_start: ceiling); + } + vma = next; + } +} + +int __pte_alloc(struct mm_struct *mm, pmd_t *pmd, unsigned long address) +{ + pgtable_t new = pte_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + /* + * Ensure all pte setup (eg. pte page lock and page clearing) are + * visible before the pte is made visible to other CPUs by being + * put into page tables. + * + * The other side of the story is the pointer chasing in the page + * table walking code (when walking the page table without locking; + * ie. most of the time). Fortunately, these data accesses consist + * of a chain of data-dependent loads, meaning most CPUs (alpha + * being the notable exception) will already guarantee loads are + * seen in-order. See the alpha page table accessors for the + * smp_read_barrier_depends() barriers in page table walking code. + */ + smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */ + + spin_lock(&mm->page_table_lock); + if (!pmd_present(*pmd)) { /* Has another populated it ? */ + mm->nr_ptes++; + pmd_populate(mm, pmd, new); + new = NULL; + } + spin_unlock(&mm->page_table_lock); + if (new) + pte_free(mm, new); + return 0; +} + +int __pte_alloc_kernel(pmd_t *pmd, unsigned long address) +{ + pte_t *new = pte_alloc_one_kernel(&init_mm, address); + if (!new) + return -ENOMEM; + + smp_wmb(); /* See comment in __pte_alloc */ + + spin_lock(&init_mm.page_table_lock); + if (!pmd_present(*pmd)) { /* Has another populated it ? */ + pmd_populate_kernel(&init_mm, pmd, new); + new = NULL; + } + spin_unlock(&init_mm.page_table_lock); + if (new) + pte_free_kernel(&init_mm, new); + return 0; +} + +static inline void add_mm_rss(struct mm_struct *mm, int file_rss, int anon_rss) +{ + if (file_rss) + add_mm_counter(mm, file_rss, file_rss); + if (anon_rss) + add_mm_counter(mm, anon_rss, anon_rss); +} + +/* + * This function is called to print an error when a bad pte + * is found. For example, we might have a PFN-mapped pte in + * a region that doesn't allow it. + * + * The calling function must still handle the error. + */ +static void print_bad_pte(struct vm_area_struct *vma, pte_t pte, + unsigned long vaddr) +{ + printk(KERN_ERR "Bad pte = %08llx, process = %s, " + "vm_flags = %lx, vaddr = %lx\n", + (long long)pte_val(pte), + (vma->vm_mm == current->mm ? current->comm : "???"), + vma->vm_flags, vaddr); + dump_stack(); +} + +static inline int is_cow_mapping(unsigned int flags) +{ + return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; +} + +/* + * vm_normal_page -- This function gets the "struct page" associated with a pte. + * + * "Special" mappings do not wish to be associated with a "struct page" (either + * it doesn't exist, or it exists but they don't want to touch it). In this + * case, NULL is returned here. "Normal" mappings do have a struct page. + * + * There are 2 broad cases. Firstly, an architecture may define a pte_special() + * pte bit, in which case this function is trivial. Secondly, an architecture + * may not have a spare pte bit, which requires a more complicated scheme, + * described below. + * + * A raw VM_PFNMAP mapping (ie. one that is not COWed) is always considered a + * special mapping (even if there are underlying and valid "struct pages"). + * COWed pages of a VM_PFNMAP are always normal. + * + * The way we recognize COWed pages within VM_PFNMAP mappings is through the + * rules set up by "remap_pfn_range()": the vma will have the VM_PFNMAP bit + * set, and the vm_pgoff will point to the first PFN mapped: thus every special + * mapping will always honor the rule + * + * pfn_of_page == vma->vm_pgoff + ((addr - vma->vm_start) >> PAGE_SHIFT) + * + * And for normal mappings this is false. + * + * This restricts such mappings to be a linear translation from virtual address + * to pfn. To get around this restriction, we allow arbitrary mappings so long + * as the vma is not a COW mapping; in that case, we know that all ptes are + * special (because none can have been COWed). + * + * + * In order to support COW of arbitrary special mappings, we have VM_MIXEDMAP. + * + * VM_MIXEDMAP mappings can likewise contain memory with or without "struct + * page" backing, however the difference is that _all_ pages with a struct + * page (that is, those where pfn_valid is true) are refcounted and considered + * normal pages by the VM. The disadvantage is that pages are refcounted + * (which can be slower and simply not an option for some PFNMAP users). The + * advantage is that we don't have to follow the strict linearity rule of + * PFNMAP mappings in order to support COWable mappings. + * + */ +#ifdef __HAVE_ARCH_PTE_SPECIAL +# define HAVE_PTE_SPECIAL 1 +#else +# define HAVE_PTE_SPECIAL 0 +#endif +struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, + pte_t pte) +{ + unsigned long pfn; + + if (HAVE_PTE_SPECIAL) { + if (likely(!pte_special(pte))) { + VM_BUG_ON(!pfn_valid(pte_pfn(pte))); + return pte_page(pte); + } + VM_BUG_ON(!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))); + return NULL; + } + + /* !HAVE_PTE_SPECIAL case follows: */ + + pfn = pte_pfn(pte); + + if (unlikely(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))) { + if (vma->vm_flags & VM_MIXEDMAP) { + if (!pfn_valid(pfn)) + return NULL; + goto out; + } else { + unsigned long off; + off = (addr - vma->vm_start) >> PAGE_SHIFT; + if (pfn == vma->vm_pgoff + off) + return NULL; + if (!is_cow_mapping(vma->vm_flags)) + return NULL; + } + } + + VM_BUG_ON(!pfn_valid(pfn)); + + /* + * NOTE! We still have PageReserved() pages in the page tables. + * + * eg. VDSO mappings can cause them to exist. + */ +out: + return pfn_to_page(pfn); +} + +/* + * copy one vm_area from one task to the other. Assumes the page tables + * already present in the new task to be cleared in the whole range + * covered by this vma. + */ + +static inline void +copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *vma, + unsigned long addr, int *rss) +{ + unsigned long vm_flags = vma->vm_flags; + pte_t pte = *src_pte; + struct page *page; + + /* pte contains position in swap or file, so copy. */ + if (unlikely(!pte_present(pte))) { + if (!pte_file(pte)) { + swp_entry_t entry = pte_to_swp_entry(pte); + + swap_duplicate(entry); + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both parent + * and child to be set to read. + */ + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + set_pte_at(src_mm, addr, src_pte, pte); + } + } + goto out_set_pte; + } + + /* + * If it's a COW mapping, write protect it both + * in the parent and the child + */ + if (is_cow_mapping(vm_flags)) { + ptep_set_wrprotect(src_mm, addr, src_pte); + pte = pte_wrprotect(pte); + } + + /* + * If it's a shared mapping, mark it clean in + * the child + */ + if (vm_flags & VM_SHARED) + pte = pte_mkclean(pte); + pte = pte_mkold(pte); + + page = vm_normal_page(vma, addr, pte); + if (page) { + get_page(page); + page_dup_rmap(page, vma, addr); + rss[!!PageAnon(page)]++; + } + +out_set_pte: + set_pte_at(dst_mm, addr, dst_pte, pte); +} + +static int copy_pte_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pmd_t *dst_pmd, pmd_t *src_pmd, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + pte_t *src_pte, *dst_pte; + spinlock_t *src_ptl, *dst_ptl; + int progress = 0; + int rss[2]; + + if (!vx_rss_avail(dst_mm, ((end - addr)/PAGE_SIZE + 1))) + return -ENOMEM; + +again: + rss[1] = rss[0] = 0; + dst_pte = pte_alloc_map_lock(dst_mm, dst_pmd, addr, &dst_ptl); + if (!dst_pte) + return -ENOMEM; + src_pte = pte_offset_map_nested(src_pmd, addr); + src_ptl = pte_lockptr(src_mm, src_pmd); + spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); + arch_enter_lazy_mmu_mode(); + + do { + /* + * We are holding two locks at this point - either of them + * could generate latencies in another task on another CPU. + */ + if (progress >= 32) { + progress = 0; + if (need_resched() || + spin_needbreak(src_ptl) || spin_needbreak(dst_ptl)) + break; + } + if (pte_none(*src_pte)) { + progress++; + continue; + } + copy_one_pte(dst_mm, src_mm, dst_pte, src_pte, vma, addr, rss); + progress += 8; + } while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end); + + arch_leave_lazy_mmu_mode(); + spin_unlock(src_ptl); + pte_unmap_nested(src_pte - 1); + add_mm_rss(dst_mm, rss[0], rss[1]); + pte_unmap_unlock(dst_pte - 1, dst_ptl); + cond_resched(); + if (addr != end) + goto again; + return 0; +} + +static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pud_t *dst_pud, pud_t *src_pud, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + pmd_t *src_pmd, *dst_pmd; + unsigned long next; + + dst_pmd = pmd_alloc(dst_mm, dst_pud, addr); + if (!dst_pmd) + return -ENOMEM; + src_pmd = pmd_offset(src_pud, addr); + do { + next = pmd_addr_end(addr, end); + if (pmd_none_or_clear_bad(src_pmd)) + continue; + if (copy_pte_range(dst_mm, src_mm, dst_pmd, src_pmd, + vma, addr, next)) + return -ENOMEM; + } while (dst_pmd++, src_pmd++, addr = next, addr != end); + return 0; +} + +static inline int copy_pud_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + pgd_t *dst_pgd, pgd_t *src_pgd, struct vm_area_struct *vma, + unsigned long addr, unsigned long end) +{ + pud_t *src_pud, *dst_pud; + unsigned long next; + + dst_pud = pud_alloc(dst_mm, dst_pgd, addr); + if (!dst_pud) + return -ENOMEM; + src_pud = pud_offset(src_pgd, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(src_pud)) + continue; + if (copy_pmd_range(dst_mm, src_mm, dst_pud, src_pud, + vma, addr, next)) + return -ENOMEM; + } while (dst_pud++, src_pud++, addr = next, addr != end); + return 0; +} + +int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, + struct vm_area_struct *vma) +{ + pgd_t *src_pgd, *dst_pgd; + unsigned long next; + unsigned long addr = vma->vm_start; + unsigned long end = vma->vm_end; + int ret; + + /* + * Don't copy ptes where a page fault will fill them correctly. + * Fork becomes much lighter when there are big shared or private + * readonly mappings. The tradeoff is that copy_page_range is more + * efficient than faulting. + */ + if (!(vma->vm_flags & (VM_HUGETLB|VM_NONLINEAR|VM_PFNMAP|VM_INSERTPAGE))) { + if (!vma->anon_vma) + return 0; + } + + if (is_vm_hugetlb_page(vma)) + return copy_hugetlb_page_range(dst_mm, src_mm, vma); + + /* + * We need to invalidate the secondary MMU mappings only when + * there could be a permission downgrade on the ptes of the + * parent mm. And a permission downgrade will only happen if + * is_cow_mapping() returns true. + */ + if (is_cow_mapping(vma->vm_flags)) + mmu_notifier_invalidate_range_start(src_mm, addr, end); + + ret = 0; + dst_pgd = pgd_offset(dst_mm, addr); + src_pgd = pgd_offset(src_mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(src_pgd)) + continue; + if (unlikely(copy_pud_range(dst_mm, src_mm, dst_pgd, src_pgd, + vma, addr, next))) { + ret = -ENOMEM; + break; + } + } while (dst_pgd++, src_pgd++, addr = next, addr != end); + + if (is_cow_mapping(vma->vm_flags)) + mmu_notifier_invalidate_range_end(src_mm, + vma->vm_start, end); + return ret; +} + +static unsigned long zap_pte_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pmd_t *pmd, + unsigned long addr, unsigned long end, + long *zap_work, struct zap_details *details) +{ + struct mm_struct *mm = tlb->mm; + pte_t *pte; + spinlock_t *ptl; + int file_rss = 0; + int anon_rss = 0; + + pte = pte_offset_map_lock(mm, pmd, addr, &ptl); + arch_enter_lazy_mmu_mode(); + do { + pte_t ptent = *pte; + if (pte_none(ptent)) { + (*zap_work)--; + continue; + } + + (*zap_work) -= PAGE_SIZE; + + if (pte_present(ptent)) { + struct page *page; + + page = vm_normal_page(vma, addr, ptent); + if (unlikely(details) && page) { + /* + * unmap_shared_mapping_pages() wants to + * invalidate cache without truncating: + * unmap shared but keep private pages. + */ + if (details->check_mapping && + details->check_mapping != page->mapping) + continue; + /* + * Each page->index must be checked when + * invalidating or truncating nonlinear. + */ + if (details->nonlinear_vma && + (page->index < details->first_index || + page->index > details->last_index)) + continue; + } + ptent = ptep_get_and_clear_full(mm, addr, pte, + tlb->fullmm); + tlb_remove_tlb_entry(tlb, pte, addr); + if (unlikely(!page)) + continue; + if (unlikely(details) && details->nonlinear_vma + && linear_page_index(details->nonlinear_vma, + addr) != page->index) + set_pte_at(mm, addr, pte, + pgoff_to_pte(page->index)); + if (PageAnon(page)) + anon_rss--; + else { + if (pte_dirty(ptent)) + set_page_dirty(page); + if (pte_young(ptent)) + SetPageReferenced(page); + file_rss--; + } + page_remove_rmap(page, vma); + tlb_remove_page(tlb, page); + continue; + } + /* + * If details->check_mapping, we leave swap entries; + * if details->nonlinear_vma, we leave file entries. + */ + if (unlikely(details)) + continue; + if (!pte_file(ptent)) + free_swap_and_cache(pte_to_swp_entry(ptent)); + pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); + } while (pte++, addr += PAGE_SIZE, (addr != end && *zap_work > 0)); + + add_mm_rss(mm, file_rss, anon_rss); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(pte - 1, ptl); + + return addr; +} + +static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pud_t *pud, + unsigned long addr, unsigned long end, + long *zap_work, struct zap_details *details) +{ + pmd_t *pmd; + unsigned long next; + + pmd = pmd_offset(pud, addr); + do { + next = pmd_addr_end(addr, end); + if (pmd_none_or_clear_bad(pmd)) { + (*zap_work)--; + continue; + } + next = zap_pte_range(tlb, vma, pmd, addr, next, + zap_work, details); + } while (pmd++, addr = next, (addr != end && *zap_work > 0)); + + return addr; +} + +static inline unsigned long zap_pud_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, pgd_t *pgd, + unsigned long addr, unsigned long end, + long *zap_work, struct zap_details *details) +{ + pud_t *pud; + unsigned long next; + + pud = pud_offset(pgd, addr); + do { + next = pud_addr_end(addr, end); + if (pud_none_or_clear_bad(pud)) { + (*zap_work)--; + continue; + } + next = zap_pmd_range(tlb, vma, pud, addr, next, + zap_work, details); + } while (pud++, addr = next, (addr != end && *zap_work > 0)); + + return addr; +} + +static unsigned long unmap_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end, + long *zap_work, struct zap_details *details) +{ + pgd_t *pgd; + unsigned long next; + + if (details && !details->check_mapping && !details->nonlinear_vma) + details = NULL; + + BUG_ON(addr >= end); + tlb_start_vma(tlb, vma); + pgd = pgd_offset(vma->vm_mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) { + (*zap_work)--; + continue; + } + next = zap_pud_range(tlb, vma, pgd, addr, next, + zap_work, details); + } while (pgd++, addr = next, (addr != end && *zap_work > 0)); + tlb_end_vma(tlb, vma); + + return addr; +} + +#ifdef CONFIG_PREEMPT +# define ZAP_BLOCK_SIZE (8 * PAGE_SIZE) +#else +/* No preempt: go for improved straight-line efficiency */ +# define ZAP_BLOCK_SIZE (1024 * PAGE_SIZE) +#endif + +/** + * unmap_vmas - unmap a range of memory covered by a list of vma's + * @tlbp: address of the caller's struct mmu_gather + * @vma: the starting vma + * @start_addr: virtual address at which to start unmapping + * @end_addr: virtual address at which to end unmapping + * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here + * @details: details of nonlinear truncation or shared cache invalidation + * + * Returns the end address of the unmapping (restart addr if interrupted). + * + * Unmap all pages in the vma list. + * + * We aim to not hold locks for too long (for scheduling latency reasons). + * So zap pages in ZAP_BLOCK_SIZE bytecounts. This means we need to + * return the ending mmu_gather to the caller. + * + * Only addresses between `start' and `end' will be unmapped. + * + * The VMA list must be sorted in ascending virtual address order. + * + * unmap_vmas() assumes that the caller will flush the whole unmapped address + * range after unmap_vmas() returns. So the only responsibility here is to + * ensure that any thus-far unmapped pages are flushed before unmap_vmas() + * drops the lock and schedules. + */ +unsigned long unmap_vmas(struct mmu_gather **tlbp, + struct vm_area_struct *vma, unsigned long start_addr, + unsigned long end_addr, unsigned long *nr_accounted, + struct zap_details *details) +{ + long zap_work = ZAP_BLOCK_SIZE; + unsigned long tlb_start = 0; /* For tlb_finish_mmu */ + int tlb_start_valid = 0; + unsigned long start = start_addr; + spinlock_t *i_mmap_lock = details? details->i_mmap_lock: NULL; + int fullmm = (*tlbp)->fullmm; + struct mm_struct *mm = vma->vm_mm; + + mmu_notifier_invalidate_range_start(mm, start_addr, end_addr); + for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) { + unsigned long end; + + start = max(vma->vm_start, start_addr); + if (start >= vma->vm_end) + continue; + end = min(vma->vm_end, end_addr); + if (end <= vma->vm_start) + continue; + + if (vma->vm_flags & VM_ACCOUNT) + *nr_accounted += (end - start) >> PAGE_SHIFT; + + while (start != end) { + if (!tlb_start_valid) { + tlb_start = start; + tlb_start_valid = 1; + } + + if (unlikely(is_vm_hugetlb_page(vma))) { + /* + * It is undesirable to test vma->vm_file as it + * should be non-null for valid hugetlb area. + * However, vm_file will be NULL in the error + * cleanup path of do_mmap_pgoff. When + * hugetlbfs ->mmap method fails, + * do_mmap_pgoff() nullifies vma->vm_file + * before calling this function to clean up. + * Since no pte has actually been setup, it is + * safe to do nothing in this case. + */ + if (vma->vm_file) { + unmap_hugepage_range(vma, start, end, NULL); + zap_work -= (end - start) / + pages_per_huge_page(hstate_vma(vma)); + } + + start = end; + } else + start = unmap_page_range(*tlbp, vma, + start, end, &zap_work, details); + + if (zap_work > 0) { + BUG_ON(start != end); + break; + } + + tlb_finish_mmu(*tlbp, tlb_start, start); + + if (need_resched() || + (i_mmap_lock && spin_needbreak(i_mmap_lock))) { + if (i_mmap_lock) { + *tlbp = NULL; + goto out; + } + cond_resched(); + } + + *tlbp = tlb_gather_mmu(vma->vm_mm, fullmm); + tlb_start_valid = 0; + zap_work = ZAP_BLOCK_SIZE; + } + } +out: + mmu_notifier_invalidate_range_end(mm, start_addr, end_addr); + return start; /* which is now the end (or restart) address */ +} + +/** + * zap_page_range - remove user pages in a given range + * @vma: vm_area_struct holding the applicable pages + * @address: starting address of pages to zap + * @size: number of bytes to zap + * @details: details of nonlinear truncation or shared cache invalidation + */ +unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, + unsigned long size, struct zap_details *details) +{ + struct mm_struct *mm = vma->vm_mm; + struct mmu_gather *tlb; + unsigned long end = address + size; + unsigned long nr_accounted = 0; + + lru_add_drain(); + tlb = tlb_gather_mmu(mm, 0); + update_hiwater_rss(mm); + end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details); + if (tlb) + tlb_finish_mmu(tlb, address, end); + return end; +} + +/** + * zap_vma_ptes - remove ptes mapping the vma + * @vma: vm_area_struct holding ptes to be zapped + * @address: starting address of pages to zap + * @size: number of bytes to zap + * + * This function only unmaps ptes assigned to VM_PFNMAP vmas. + * + * The entire address range must be fully contained within the vma. + * + * Returns 0 if successful. + */ +int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, + unsigned long size) +{ + if (address < vma->vm_start || address + size > vma->vm_end || + !(vma->vm_flags & VM_PFNMAP)) + return -1; + zap_page_range(vma, address, size, NULL); + return 0; +} +EXPORT_SYMBOL_GPL(zap_vma_ptes); + +/* + * Do a quick page-table lookup for a single page. + */ +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int flags) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep, pte; + spinlock_t *ptl; + struct page *page; + struct mm_struct *mm = vma->vm_mm; + + page = follow_huge_addr(mm, address, flags & FOLL_WRITE); + if (!IS_ERR(page)) { + BUG_ON(flags & FOLL_GET); + goto out; + } + + page = NULL; + pgd = pgd_offset(mm, address); + if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + goto no_page_table; + + pud = pud_offset(pgd, address); + if (pud_none(*pud)) + goto no_page_table; + if (pud_huge(*pud)) { + BUG_ON(flags & FOLL_GET); + page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); + goto out; + } + if (unlikely(pud_bad(*pud))) + goto no_page_table; + + pmd = pmd_offset(pud, address); + if (pmd_none(*pmd)) + goto no_page_table; + if (pmd_huge(*pmd)) { + BUG_ON(flags & FOLL_GET); + page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); + goto out; + } + if (unlikely(pmd_bad(*pmd))) + goto no_page_table; + + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + + pte = *ptep; + if (!pte_present(pte)) + goto no_page; + if ((flags & FOLL_WRITE) && !pte_write(pte)) + goto unlock; + page = vm_normal_page(vma, address, pte); + if (unlikely(!page)) + goto bad_page; + + if (flags & FOLL_GET) + get_page(page); + if (flags & FOLL_TOUCH) { + if ((flags & FOLL_WRITE) && + !pte_dirty(pte) && !PageDirty(page)) + set_page_dirty(page); + mark_page_accessed(page); + } +unlock: + pte_unmap_unlock(ptep, ptl); +out: + return page; + +bad_page: + pte_unmap_unlock(ptep, ptl); + return ERR_PTR(-EFAULT); + +no_page: + pte_unmap_unlock(ptep, ptl); + if (!pte_none(pte)) + return page; + /* Fall through to ZERO_PAGE handling */ +no_page_table: + /* + * When core dumping an enormous anonymous area that nobody + * has touched so far, we don't want to allocate page tables. + */ + if (flags & FOLL_ANON) { + page = ZERO_PAGE(0); + if (flags & FOLL_GET) + get_page(page); + BUG_ON(flags & FOLL_WRITE); + } + return page; +} + +/* Can we do the FOLL_ANON optimization? */ +static inline int use_zero_page(struct vm_area_struct *vma) +{ + /* + * We don't want to optimize FOLL_ANON for make_pages_present() + * when it tries to page in a VM_LOCKED region. As to VM_SHARED, + * we want to get the page from the page tables to make sure + * that we serialize and update with any other user of that + * mapping. + */ + if (vma->vm_flags & (VM_LOCKED | VM_SHARED)) + return 0; + /* + * And if we have a fault routine, it's not an anonymous region. + */ + return !vma->vm_ops || !vma->vm_ops->fault; +} + +int get_user_pages(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, int len, int write, int force, + struct page **pages, struct vm_area_struct **vmas) +{ + int i; + unsigned int vm_flags; + + if (len <= 0) + return 0; + /* + * Require read or write permissions. + * If 'force' is set, we only require the "MAY" flags. + */ + vm_flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); + vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); + i = 0; + + do { + struct vm_area_struct *vma; + unsigned int foll_flags; + + vma = find_extend_vma(mm, start); + if (!vma && in_gate_area(tsk, start)) { + unsigned long pg = start & PAGE_MASK; + struct vm_area_struct *gate_vma = get_gate_vma(tsk); + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + if (write) /* user gate pages are read-only */ + return i ? : -EFAULT; + if (pg > TASK_SIZE) + pgd = pgd_offset_k(pg); + else + pgd = pgd_offset_gate(mm, pg); + BUG_ON(pgd_none(*pgd)); + pud = pud_offset(pgd, pg); + BUG_ON(pud_none(*pud)); + pmd = pmd_offset(pud, pg); + if (pmd_none(*pmd)) + return i ? : -EFAULT; + pte = pte_offset_map(pmd, pg); + if (pte_none(*pte)) { + pte_unmap(pte); + return i ? : -EFAULT; + } + if (pages) { + struct page *page = vm_normal_page(gate_vma, start, *pte); + pages[i] = page; + if (page) + get_page(page); + } + pte_unmap(pte); + if (vmas) + vmas[i] = gate_vma; + i++; + start += PAGE_SIZE; + len--; + continue; + } + + if (!vma || (vma->vm_flags & (VM_IO | VM_PFNMAP)) + || !(vm_flags & vma->vm_flags)) + return i ? : -EFAULT; + + if (is_vm_hugetlb_page(vma)) { + i = follow_hugetlb_page(mm, vma, pages, vmas, + &start, &len, i, write); + continue; + } + + foll_flags = FOLL_TOUCH; + if (pages) + foll_flags |= FOLL_GET; + if (!write && use_zero_page(vma)) + foll_flags |= FOLL_ANON; + + do { + struct page *page; + + /* + * If tsk is ooming, cut off its access to large memory + * allocations. It has a pending SIGKILL, but it can't + * be processed until returning to user space. + */ + if (unlikely(test_tsk_thread_flag(tsk, TIF_MEMDIE))) + return i ? i : -ENOMEM; + + if (write) + foll_flags |= FOLL_WRITE; + + cond_resched(); + while (!(page = follow_page(vma, start, foll_flags))) { + int ret; + ret = handle_mm_fault(mm, vma, start, + foll_flags & FOLL_WRITE); + if (ret & VM_FAULT_ERROR) { + if (ret & VM_FAULT_OOM) + return i ? i : -ENOMEM; + else if (ret & VM_FAULT_SIGBUS) + return i ? i : -EFAULT; + BUG(); + } + if (ret & VM_FAULT_MAJOR) + tsk->maj_flt++; + else + tsk->min_flt++; + + /* + * The VM_FAULT_WRITE bit tells us that + * do_wp_page has broken COW when necessary, + * even if maybe_mkwrite decided not to set + * pte_write. We can thus safely do subsequent + * page lookups as if they were reads. + */ + if (ret & VM_FAULT_WRITE) + foll_flags &= ~FOLL_WRITE; + + cond_resched(); + } + if (IS_ERR(page)) + return i ? i : PTR_ERR(page); + if (pages) { + pages[i] = page; + + flush_anon_page(vma, page, start); + flush_dcache_page(page); + } + if (vmas) + vmas[i] = vma; + i++; + start += PAGE_SIZE; + len--; + } while (len && start < vma->vm_end); + } while (len); + return i; +} +EXPORT_SYMBOL(get_user_pages); + +pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr, + spinlock_t **ptl) +{ + pgd_t * pgd = pgd_offset(mm, addr); + pud_t * pud = pud_alloc(mm, pgd, addr); + if (pud) { + pmd_t * pmd = pmd_alloc(mm, pud, addr); + if (pmd) + return pte_alloc_map_lock(mm, pmd, addr, ptl); + } + return NULL; +} + +/* + * This is the old fallback for page remapping. + * + * For historical reasons, it only allows reserved pages. Only + * old drivers should use this, and they needed to mark their + * pages reserved for the old functions anyway. + */ +static int insert_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page, pgprot_t prot) +{ + struct mm_struct *mm = vma->vm_mm; + int retval; + pte_t *pte; + spinlock_t *ptl; + + retval = mem_cgroup_charge(page, mm, GFP_KERNEL); + if (retval) + goto out; + + retval = -EINVAL; + if (PageAnon(page)) + goto out_uncharge; + retval = -ENOMEM; + flush_dcache_page(page); + pte = get_locked_pte(mm, addr, &ptl); + if (!pte) + goto out_uncharge; + retval = -EBUSY; + if (!pte_none(*pte)) + goto out_unlock; + + /* Ok, finally just insert the thing.. */ + get_page(page); + inc_mm_counter(mm, file_rss); + page_add_file_rmap(page); + set_pte_at(mm, addr, pte, mk_pte(page, prot)); + + retval = 0; + pte_unmap_unlock(pte, ptl); + return retval; +out_unlock: + pte_unmap_unlock(pte, ptl); +out_uncharge: + mem_cgroup_uncharge_page(page); +out: + return retval; +} + +/** + * vm_insert_page - insert single page into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @page: source kernel page + * + * This allows drivers to insert individual pages they've allocated + * into a user vma. + * + * The page has to be a nice clean _individual_ kernel allocation. + * If you allocate a compound page, you need to have marked it as + * such (__GFP_COMP), or manually just split the page up yourself + * (see split_page()). + * + * NOTE! Traditionally this was done with "remap_pfn_range()" which + * took an arbitrary page protection parameter. This doesn't allow + * that. Your vma protection will have to be set up correctly, which + * means that if you want a shared writable mapping, you'd better + * ask for a shared writable mapping! + * + * The page does not need to be reserved. + */ +int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, + struct page *page) +{ + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; + if (!page_count(page)) + return -EINVAL; + vma->vm_flags |= VM_INSERTPAGE; + return insert_page(vma, addr, page, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_page); + +static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t prot) +{ + struct mm_struct *mm = vma->vm_mm; + int retval; + pte_t *pte, entry; + spinlock_t *ptl; + + retval = -ENOMEM; + pte = get_locked_pte(mm, addr, &ptl); + if (!pte) + goto out; + retval = -EBUSY; + if (!pte_none(*pte)) + goto out_unlock; + + /* Ok, finally just insert the thing.. */ + entry = pte_mkspecial(pfn_pte(pfn, prot)); + set_pte_at(mm, addr, pte, entry); + update_mmu_cache(vma, addr, entry); /* XXX: why not for insert_page? */ + + retval = 0; +out_unlock: + pte_unmap_unlock(pte, ptl); +out: + return retval; +} + +/** + * vm_insert_pfn - insert single pfn into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * + * Similar to vm_inert_page, this allows drivers to insert individual pages + * they've allocated into a user vma. Same comments apply. + * + * This function should only be called from a vm_ops->fault handler, and + * in that case the handler should return NULL. + * + * vma cannot be a COW mapping. + * + * As this is called only for pages that do not currently exist, we + * do not need to flush old virtual caches or the TLB. + */ +int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) +{ + /* + * Technically, architectures with pte_special can avoid all these + * restrictions (same for remap_pfn_range). However we would like + * consistency in testing and feature parity among all, so we should + * try to keep these invariants in place for everybody. + */ + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == + (VM_PFNMAP|VM_MIXEDMAP)); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); + BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; + return insert_pfn(vma, addr, pfn, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_pfn); + +int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) +{ + BUG_ON(!(vma->vm_flags & VM_MIXEDMAP)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return -EFAULT; + + /* + * If we don't have pte special, then we have to use the pfn_valid() + * based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must* + * refcount the page if pfn_valid is true (hence insert_page rather + * than insert_pfn). + */ + if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) { + struct page *page; + + page = pfn_to_page(pfn); + return insert_page(vma, addr, page, vma->vm_page_prot); + } + return insert_pfn(vma, addr, pfn, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_mixed); + +/* + * maps a range of physical memory into the requested pages. the old + * mappings are removed. any references to nonexistent pages results + * in null mappings (currently treated as "copy-on-access") + */ +static int remap_pte_range(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + pte_t *pte; + spinlock_t *ptl; + + pte = pte_alloc_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return -ENOMEM; + arch_enter_lazy_mmu_mode(); + do { + BUG_ON(!pte_none(*pte)); + set_pte_at(mm, addr, pte, pte_mkspecial(pfn_pte(pfn, prot))); + pfn++; + } while (pte++, addr += PAGE_SIZE, addr != end); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(pte - 1, ptl); + return 0; +} + +static inline int remap_pmd_range(struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + pmd_t *pmd; + unsigned long next; + + pfn -= addr >> PAGE_SHIFT; + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return -ENOMEM; + do { + next = pmd_addr_end(addr, end); + if (remap_pte_range(mm, pmd, addr, next, + pfn + (addr >> PAGE_SHIFT), prot)) + return -ENOMEM; + } while (pmd++, addr = next, addr != end); + return 0; +} + +static inline int remap_pud_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + unsigned long pfn, pgprot_t prot) +{ + pud_t *pud; + unsigned long next; + + pfn -= addr >> PAGE_SHIFT; + pud = pud_alloc(mm, pgd, addr); + if (!pud) + return -ENOMEM; + do { + next = pud_addr_end(addr, end); + if (remap_pmd_range(mm, pud, addr, next, + pfn + (addr >> PAGE_SHIFT), prot)) + return -ENOMEM; + } while (pud++, addr = next, addr != end); + return 0; +} + +/** + * remap_pfn_range - remap kernel memory to userspace + * @vma: user vma to map to + * @addr: target user address to start at + * @pfn: physical address of kernel memory + * @size: size of map area + * @prot: page protection flags for this mapping + * + * Note: this is only safe if the mm semaphore is held when called. + */ +int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, unsigned long size, pgprot_t prot) +{ + pgd_t *pgd; + unsigned long next; + unsigned long end = addr + PAGE_ALIGN(size); + struct mm_struct *mm = vma->vm_mm; + int err; + + /* + * Physically remapped pages are special. Tell the + * rest of the world about it: + * VM_IO tells people not to look at these pages + * (accesses can have side effects). + * VM_RESERVED is specified all over the place, because + * in 2.4 it kept swapout's vma scan off this vma; but + * in 2.6 the LRU scan won't even find its pages, so this + * flag means no more than count its pages in reserved_vm, + * and omit it from core dump, even when VM_IO turned off. + * VM_PFNMAP tells the core MM that the base pages are just + * raw PFN mappings, and do not have a "struct page" associated + * with them. + * + * There's a horrible special case to handle copy-on-write + * behaviour that some programs depend on. We mark the "original" + * un-COW'ed pages by matching them up with "vma->vm_pgoff". + */ + if (is_cow_mapping(vma->vm_flags)) { + if (addr != vma->vm_start || end != vma->vm_end) + return -EINVAL; + vma->vm_pgoff = pfn; + } + + vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; + + BUG_ON(addr >= end); + pfn -= addr >> PAGE_SHIFT; + pgd = pgd_offset(mm, addr); + flush_cache_range(vma, addr, end); + do { + next = pgd_addr_end(addr, end); + err = remap_pud_range(mm, pgd, addr, next, + pfn + (addr >> PAGE_SHIFT), prot); + if (err) + break; + } while (pgd++, addr = next, addr != end); + return err; +} +EXPORT_SYMBOL(remap_pfn_range); + +static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) +{ + pte_t *pte; + int err; + pgtable_t token; + spinlock_t *uninitialized_var(ptl); + + pte = (mm == &init_mm) ? + pte_alloc_kernel(pmd, addr) : + pte_alloc_map_lock(mm, pmd, addr, &ptl); + if (!pte) + return -ENOMEM; + + BUG_ON(pmd_huge(*pmd)); + + token = pmd_pgtable(*pmd); + + do { + err = fn(pte, token, addr, data); + if (err) + break; + } while (pte++, addr += PAGE_SIZE, addr != end); + + if (mm != &init_mm) + pte_unmap_unlock(pte-1, ptl); + return err; +} + +static int apply_to_pmd_range(struct mm_struct *mm, pud_t *pud, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) +{ + pmd_t *pmd; + unsigned long next; + int err; + + BUG_ON(pud_huge(*pud)); + + pmd = pmd_alloc(mm, pud, addr); + if (!pmd) + return -ENOMEM; + do { + next = pmd_addr_end(addr, end); + err = apply_to_pte_range(mm, pmd, addr, next, fn, data); + if (err) + break; + } while (pmd++, addr = next, addr != end); + return err; +} + +static int apply_to_pud_range(struct mm_struct *mm, pgd_t *pgd, + unsigned long addr, unsigned long end, + pte_fn_t fn, void *data) +{ + pud_t *pud; + unsigned long next; + int err; + + pud = pud_alloc(mm, pgd, addr); + if (!pud) + return -ENOMEM; + do { + next = pud_addr_end(addr, end); + err = apply_to_pmd_range(mm, pud, addr, next, fn, data); + if (err) + break; + } while (pud++, addr = next, addr != end); + return err; +} + +/* + * Scan a region of virtual memory, filling in page tables as necessary + * and calling a provided function on each leaf page table. + */ +int apply_to_page_range(struct mm_struct *mm, unsigned long addr, + unsigned long size, pte_fn_t fn, void *data) +{ + pgd_t *pgd; + unsigned long next; + unsigned long start = addr, end = addr + size; + int err; + + BUG_ON(addr >= end); + mmu_notifier_invalidate_range_start(mm, start, end); + pgd = pgd_offset(mm, addr); + do { + next = pgd_addr_end(addr, end); + err = apply_to_pud_range(mm, pgd, addr, next, fn, data); + if (err) + break; + } while (pgd++, addr = next, addr != end); + mmu_notifier_invalidate_range_end(mm, start, end); + return err; +} +EXPORT_SYMBOL_GPL(apply_to_page_range); + +/* + * handle_pte_fault chooses page fault handler according to an entry + * which was read non-atomically. Before making any commitment, on + * those architectures or configurations (e.g. i386 with PAE) which + * might give a mix of unmatched parts, do_swap_page and do_file_page + * must check under lock before unmapping the pte and proceeding + * (but do_wp_page is only called after already making such a check; + * and do_anonymous_page and do_no_page can safely check later on). + */ +static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, + pte_t *page_table, pte_t orig_pte) +{ + int same = 1; +#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT) + if (sizeof(pte_t) > sizeof(unsigned long)) { + spinlock_t *ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + same = pte_same(*page_table, orig_pte); + spin_unlock(ptl); + } +#endif + pte_unmap(page_table); + return same; +} + +/* + * Do pte_mkwrite, but only if the vma says VM_WRITE. We do this when + * servicing faults for write access. In the normal case, do always want + * pte_mkwrite. But get_user_pages can cause write faults for mappings + * that do not have writing enabled, when used by access_process_vm. + */ +static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma) +{ + if (likely(vma->vm_flags & VM_WRITE)) + pte = pte_mkwrite(pte); + return pte; +} + +static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) +{ + /* + * If the source page was a PFN mapping, we don't have + * a "struct page" for it. We do a best-effort copy by + * just copying from the original user address. If that + * fails, we just zero-fill it. Live with it. + */ + if (unlikely(!src)) { + void *kaddr = kmap_atomic(dst, KM_USER0); + void __user *uaddr = (void __user *)(va & PAGE_MASK); + + /* + * This really shouldn't fail, because the page is there + * in the page tables. But it might just be unreadable, + * in which case we just give up and fill the result with + * zeroes. + */ + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) + memset(kaddr, 0, PAGE_SIZE); + kunmap_atomic(kaddr, KM_USER0); + flush_dcache_page(dst); + } else + copy_user_highpage(dst, src, va, vma); +} + +/* + * This routine handles present pages, when users try to write + * to a shared page. It is done by copying the page to a new address + * and decrementing the shared-page counter for the old page. + * + * Note that this routine assumes that the protection checks have been + * done by the caller (the low-level page fault routine in most cases). + * Thus we can safely just mark it writable once we've done any necessary + * COW. + * + * We also mark the page dirty at this point even though the page will + * change only once the write actually happens. This avoids a few races, + * and potentially makes it more efficient. + * + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), with pte both mapped and locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. + */ +static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + spinlock_t *ptl, pte_t orig_pte) +{ + struct page *old_page, *new_page; + pte_t entry; + int reuse = 0, ret = 0; + int page_mkwrite = 0; + struct page *dirty_page = NULL; + + old_page = vm_normal_page(vma, address, orig_pte); + if (!old_page) { + /* + * VM_MIXEDMAP !pfn_valid() case + * + * We should not cow pages in a shared writeable mapping. + * Just mark the pages writable as we can't do any dirty + * accounting on raw pfn maps. + */ + if ((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED)) + goto reuse; + goto gotten; + } + + /* + * Take out anonymous pages first, anonymous shared vmas are + * not dirty accountable. + */ + if (PageAnon(old_page)) { + if (trylock_page(old_page)) { + reuse = can_share_swap_page(old_page); + unlock_page(old_page); + } + } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == + (VM_WRITE|VM_SHARED))) { + /* + * Only catch write-faults on shared writable pages, + * read-only shared pages can get COWed by + * get_user_pages(.write=1, .force=1). + */ + if (vma->vm_ops && vma->vm_ops->page_mkwrite) { + /* + * Notify the address space that the page is about to + * become writable so that it can prohibit this or wait + * for the page to get into an appropriate state. + * + * We do this without the lock held, so that it can + * sleep if it needs to. + */ + page_cache_get(old_page); + pte_unmap_unlock(page_table, ptl); + + if (vma->vm_ops->page_mkwrite(vma, old_page) < 0) + goto unwritable_page; + + /* + * Since we dropped the lock we need to revalidate + * the PTE as someone else may have changed it. If + * they did, we just return, as we can count on the + * MMU to tell us if they didn't also make it writable. + */ + page_table = pte_offset_map_lock(mm, pmd, address, + &ptl); + page_cache_release(old_page); + if (!pte_same(*page_table, orig_pte)) + goto unlock; + + page_mkwrite = 1; + } + dirty_page = old_page; + get_page(dirty_page); + reuse = 1; + } + + if (reuse) { +reuse: + flush_cache_page(vma, address, pte_pfn(orig_pte)); + entry = pte_mkyoung(orig_pte); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + if (ptep_set_access_flags(vma, address, page_table, entry,1)) + update_mmu_cache(vma, address, entry); + ret |= VM_FAULT_WRITE; + goto unlock; + } + + /* + * Ok, we need to copy. Oh, well.. + */ + page_cache_get(old_page); +gotten: + pte_unmap_unlock(page_table, ptl); + + if (unlikely(anon_vma_prepare(vma))) + goto oom; + VM_BUG_ON(old_page == ZERO_PAGE(0)); + new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); + if (!new_page) + goto oom; + cow_user_page(new_page, old_page, address, vma); + __SetPageUptodate(new_page); + + if (mem_cgroup_charge(new_page, mm, GFP_KERNEL)) + goto oom_free_new; + + /* + * Re-check the pte - we dropped the lock + */ + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + if (likely(pte_same(*page_table, orig_pte))) { + if (old_page) { + if (!PageAnon(old_page)) { + dec_mm_counter(mm, file_rss); + inc_mm_counter(mm, anon_rss); + } + } else + inc_mm_counter(mm, anon_rss); + flush_cache_page(vma, address, pte_pfn(orig_pte)); + entry = mk_pte(new_page, vma->vm_page_prot); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + /* + * Clear the pte entry and flush it first, before updating the + * pte with the new entry. This will avoid a race condition + * seen in the presence of one thread doing SMC and another + * thread doing COW. + */ + ptep_clear_flush_notify(vma, address, page_table); + set_pte_at(mm, address, page_table, entry); + update_mmu_cache(vma, address, entry); + lru_cache_add_active(new_page); + page_add_new_anon_rmap(new_page, vma, address); + + if (old_page) { + /* + * Only after switching the pte to the new page may + * we remove the mapcount here. Otherwise another + * process may come and find the rmap count decremented + * before the pte is switched to the new page, and + * "reuse" the old page writing into it while our pte + * here still points into it and can be read by other + * threads. + * + * The critical issue is to order this + * page_remove_rmap with the ptp_clear_flush above. + * Those stores are ordered by (if nothing else,) + * the barrier present in the atomic_add_negative + * in page_remove_rmap. + * + * Then the TLB flush in ptep_clear_flush ensures that + * no process can access the old page before the + * decremented mapcount is visible. And the old page + * cannot be reused until after the decremented + * mapcount is visible. So transitively, TLBs to + * old page will be flushed before it can be reused. + */ + page_remove_rmap(old_page, vma); + } + + /* Free the old page.. */ + new_page = old_page; + ret |= VM_FAULT_WRITE; + } else + mem_cgroup_uncharge_page(new_page); + + if (new_page) + page_cache_release(new_page); + if (old_page) + page_cache_release(old_page); +unlock: + pte_unmap_unlock(page_table, ptl); + if (dirty_page) { + if (vma->vm_file) + file_update_time(vma->vm_file); + + /* + * Yes, Virginia, this is actually required to prevent a race + * with clear_page_dirty_for_io() from clearing the page dirty + * bit after it clear all dirty ptes, but before a racing + * do_wp_page installs a dirty pte. + * + * do_no_page is protected similarly. + */ + wait_on_page_locked(dirty_page); + set_page_dirty_balance(dirty_page, page_mkwrite); + put_page(dirty_page); + } + return ret; +oom_free_new: + page_cache_release(new_page); +oom: + if (old_page) + page_cache_release(old_page); + return VM_FAULT_OOM; + +unwritable_page: + page_cache_release(old_page); + return VM_FAULT_SIGBUS; +} + +/* + * Helper functions for unmap_mapping_range(). + * + * __ Notes on dropping i_mmap_lock to reduce latency while unmapping __ + * + * We have to restart searching the prio_tree whenever we drop the lock, + * since the iterator is only valid while the lock is held, and anyway + * a later vma might be split and reinserted earlier while lock dropped. + * + * The list of nonlinear vmas could be handled more efficiently, using + * a placeholder, but handle it in the same way until a need is shown. + * It is important to search the prio_tree before nonlinear list: a vma + * may become nonlinear and be shifted from prio_tree to nonlinear list + * while the lock is dropped; but never shifted from list to prio_tree. + * + * In order to make forward progress despite restarting the search, + * vm_truncate_count is used to mark a vma as now dealt with, so we can + * quickly skip it next time around. Since the prio_tree search only + * shows us those vmas affected by unmapping the range in question, we + * can't efficiently keep all vmas in step with mapping->truncate_count: + * so instead reset them all whenever it wraps back to 0 (then go to 1). + * mapping->truncate_count and vma->vm_truncate_count are protected by + * i_mmap_lock. + * + * In order to make forward progress despite repeatedly restarting some + * large vma, note the restart_addr from unmap_vmas when it breaks out: + * and restart from that address when we reach that vma again. It might + * have been split or merged, shrunk or extended, but never shifted: so + * restart_addr remains valid so long as it remains in the vma's range. + * unmap_mapping_range forces truncate_count to leap over page-aligned + * values so we can save vma's restart_addr in its truncate_count field. + */ +#define is_restart_addr(truncate_count) (!((truncate_count) & ~PAGE_MASK)) + +static void reset_vma_truncate_counts(struct address_space *mapping) +{ + struct vm_area_struct *vma; + struct prio_tree_iter iter; + + vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX) + vma->vm_truncate_count = 0; + list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list) + vma->vm_truncate_count = 0; +} + +static int unmap_mapping_range_vma(struct vm_area_struct *vma, + unsigned long start_addr, unsigned long end_addr, + struct zap_details *details) +{ + unsigned long restart_addr; + int need_break; + + /* + * files that support invalidating or truncating portions of the + * file from under mmaped areas must have their ->fault function + * return a locked page (and set VM_FAULT_LOCKED in the return). + * This provides synchronisation against concurrent unmapping here. + */ + +again: + restart_addr = vma->vm_truncate_count; + if (is_restart_addr(restart_addr) && start_addr < restart_addr) { + start_addr = restart_addr; + if (start_addr >= end_addr) { + /* Top of vma has been split off since last time */ + vma->vm_truncate_count = details->truncate_count; + return 0; + } + } + + restart_addr = zap_page_range(vma, start_addr, + end_addr - start_addr, details); + need_break = need_resched() || spin_needbreak(details->i_mmap_lock); + + if (restart_addr >= end_addr) { + /* We have now completed this vma: mark it so */ + vma->vm_truncate_count = details->truncate_count; + if (!need_break) + return 0; + } else { + /* Note restart_addr in vma's truncate_count field */ + vma->vm_truncate_count = restart_addr; + if (!need_break) + goto again; + } + + spin_unlock(details->i_mmap_lock); + cond_resched(); + spin_lock(details->i_mmap_lock); + return -EINTR; +} + +static inline void unmap_mapping_range_tree(struct prio_tree_root *root, + struct zap_details *details) +{ + struct vm_area_struct *vma; + struct prio_tree_iter iter; + pgoff_t vba, vea, zba, zea; + +restart: + vma_prio_tree_foreach(vma, &iter, root, + details->first_index, details->last_index) { + /* Skip quickly over those we have already dealt with */ + if (vma->vm_truncate_count == details->truncate_count) + continue; + + vba = vma->vm_pgoff; + vea = vba + ((vma->vm_end - vma->vm_start) >> PAGE_SHIFT) - 1; + /* Assume for now that PAGE_CACHE_SHIFT == PAGE_SHIFT */ + zba = details->first_index; + if (zba < vba) + zba = vba; + zea = details->last_index; + if (zea > vea) + zea = vea; + + if (unmap_mapping_range_vma(vma, + ((zba - vba) << PAGE_SHIFT) + vma->vm_start, + ((zea - vba + 1) << PAGE_SHIFT) + vma->vm_start, + details) < 0) + goto restart; + } +} + +static inline void unmap_mapping_range_list(struct list_head *head, + struct zap_details *details) +{ + struct vm_area_struct *vma; + + /* + * In nonlinear VMAs there is no correspondence between virtual address + * offset and file offset. So we must perform an exhaustive search + * across *all* the pages in each nonlinear VMA, not just the pages + * whose virtual address lies outside the file truncation point. + */ +restart: + list_for_each_entry(vma, head, shared.vm_set.list) { + /* Skip quickly over those we have already dealt with */ + if (vma->vm_truncate_count == details->truncate_count) + continue; + details->nonlinear_vma = vma; + if (unmap_mapping_range_vma(vma, vma->vm_start, + vma->vm_end, details) < 0) + goto restart; + } +} + +/** + * unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file. + * @mapping: the address space containing mmaps to be unmapped. + * @holebegin: byte in first page to unmap, relative to the start of + * the underlying file. This will be rounded down to a PAGE_SIZE + * boundary. Note that this is different from vmtruncate(), which + * must keep the partial page. In contrast, we must get rid of + * partial pages. + * @holelen: size of prospective hole in bytes. This will be rounded + * up to a PAGE_SIZE boundary. A holelen of zero truncates to the + * end of the file. + * @even_cows: 1 when truncating a file, unmap even private COWed pages; + * but 0 when invalidating pagecache, don't throw away private data. + */ +void unmap_mapping_range(struct address_space *mapping, + loff_t const holebegin, loff_t const holelen, int even_cows) +{ + struct zap_details details; + pgoff_t hba = holebegin >> PAGE_SHIFT; + pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; + + /* Check for overflow. */ + if (sizeof(holelen) > sizeof(hlen)) { + long long holeend = + (holebegin + holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; + if (holeend & ~(long long)ULONG_MAX) + hlen = ULONG_MAX - hba + 1; + } + + details.check_mapping = even_cows? NULL: mapping; + details.nonlinear_vma = NULL; + details.first_index = hba; + details.last_index = hba + hlen - 1; + if (details.last_index < details.first_index) + details.last_index = ULONG_MAX; + details.i_mmap_lock = &mapping->i_mmap_lock; + + spin_lock(&mapping->i_mmap_lock); + + /* Protect against endless unmapping loops */ + mapping->truncate_count++; + if (unlikely(is_restart_addr(mapping->truncate_count))) { + if (mapping->truncate_count == 0) + reset_vma_truncate_counts(mapping); + mapping->truncate_count++; + } + details.truncate_count = mapping->truncate_count; + + if (unlikely(!prio_tree_empty(&mapping->i_mmap))) + unmap_mapping_range_tree(&mapping->i_mmap, &details); + if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) + unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); + spin_unlock(&mapping->i_mmap_lock); +} +EXPORT_SYMBOL(unmap_mapping_range); + +/** + * vmtruncate - unmap mappings "freed" by truncate() syscall + * @inode: inode of the file used + * @offset: file offset to start truncating + * + * NOTE! We have to be ready to update the memory sharing + * between the file and the memory map for a potential last + * incomplete page. Ugly, but necessary. + */ +int vmtruncate(struct inode * inode, loff_t offset) +{ + if (inode->i_size < offset) { + unsigned long limit; + + limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur; + if (limit != RLIM_INFINITY && offset > limit) + goto out_sig; + if (offset > inode->i_sb->s_maxbytes) + goto out_big; + i_size_write(inode, offset); + } else { + struct address_space *mapping = inode->i_mapping; + + /* + * truncation of in-use swapfiles is disallowed - it would + * cause subsequent swapout to scribble on the now-freed + * blocks. + */ + if (IS_SWAPFILE(inode)) + return -ETXTBSY; + i_size_write(inode, offset); + + /* + * unmap_mapping_range is called twice, first simply for + * efficiency so that truncate_inode_pages does fewer + * single-page unmaps. However after this first call, and + * before truncate_inode_pages finishes, it is possible for + * private pages to be COWed, which remain after + * truncate_inode_pages finishes, hence the second + * unmap_mapping_range call must be made for correctness. + */ + unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); + truncate_inode_pages(mapping, offset); + unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1); + } + + if (inode->i_op && inode->i_op->truncate) + inode->i_op->truncate(inode); + return 0; + +out_sig: + send_sig(SIGXFSZ, current, 0); +out_big: + return -EFBIG; +} +EXPORT_SYMBOL(vmtruncate); + +int vmtruncate_range(struct inode *inode, loff_t offset, loff_t end) +{ + struct address_space *mapping = inode->i_mapping; + + /* + * If the underlying filesystem is not going to provide + * a way to truncate a range of blocks (punch a hole) - + * we should return failure right now. + */ + if (!inode->i_op || !inode->i_op->truncate_range) + return -ENOSYS; + + mutex_lock(&inode->i_mutex); + down_write(&inode->i_alloc_sem); + unmap_mapping_range(mapping, offset, (end - offset), 1); + truncate_inode_pages_range(mapping, offset, end); + unmap_mapping_range(mapping, offset, (end - offset), 1); + inode->i_op->truncate_range(inode, offset, end); + up_write(&inode->i_alloc_sem); + mutex_unlock(&inode->i_mutex); + + return 0; +} + +/* + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. + */ +static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + int write_access, pte_t orig_pte) +{ + spinlock_t *ptl; + struct page *page; + swp_entry_t entry; + pte_t pte; + int ret = 0; + + if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) + goto out; + + entry = pte_to_swp_entry(orig_pte); + if (is_migration_entry(entry)) { + migration_entry_wait(mm, pmd, address); + goto out; + } + delayacct_set_flag(DELAYACCT_PF_SWAPIN); + page = lookup_swap_cache(entry); + if (!page) { + grab_swap_token(); /* Contend for token _before_ read-in */ + page = swapin_readahead(entry, + GFP_HIGHUSER_MOVABLE, vma, address); + if (!page) { + /* + * Back out if somebody else faulted in this pte + * while we released the pte lock. + */ + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + if (likely(pte_same(*page_table, orig_pte))) + ret = VM_FAULT_OOM; + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + goto unlock; + } + + /* Had to read the page from swap area: Major fault */ + ret = VM_FAULT_MAJOR; + count_vm_event(PGMAJFAULT); + } + + if (mem_cgroup_charge(page, mm, GFP_KERNEL)) { + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + ret = VM_FAULT_OOM; + goto out; + } + + if (!vx_rss_avail(mm, 1)) { + ret = VM_FAULT_OOM; + goto out; + } + + mark_page_accessed(page); + lock_page(page); + delayacct_clear_flag(DELAYACCT_PF_SWAPIN); + + /* + * Back out if somebody else already faulted in this pte. + */ + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + if (unlikely(!pte_same(*page_table, orig_pte))) + goto out_nomap; + + if (unlikely(!PageUptodate(page))) { + ret = VM_FAULT_SIGBUS; + goto out_nomap; + } + + /* The page isn't present yet, go ahead with the fault. */ + + inc_mm_counter(mm, anon_rss); + pte = mk_pte(page, vma->vm_page_prot); + if (write_access && can_share_swap_page(page)) { + pte = maybe_mkwrite(pte_mkdirty(pte), vma); + write_access = 0; + } + + flush_icache_page(vma, page); + set_pte_at(mm, address, page_table, pte); + page_add_anon_rmap(page, vma, address); + + swap_free(entry); + if (vm_swap_full()) + remove_exclusive_swap_page(page); + unlock_page(page); + + if (write_access) { + ret |= do_wp_page(mm, vma, address, page_table, pmd, ptl, pte); + if (ret & VM_FAULT_ERROR) + ret &= VM_FAULT_ERROR; + goto out; + } + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(vma, address, pte); +unlock: + pte_unmap_unlock(page_table, ptl); +out: + return ret; +out_nomap: + mem_cgroup_uncharge_page(page); + pte_unmap_unlock(page_table, ptl); + unlock_page(page); + page_cache_release(page); + return ret; +} + +/* + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. + */ +static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + int write_access) +{ + struct page *page; + spinlock_t *ptl; + pte_t entry; + + /* Allocate our own private page. */ + pte_unmap(page_table); + + if (!vx_rss_avail(mm, 1)) + goto oom; + if (unlikely(anon_vma_prepare(vma))) + goto oom; + page = alloc_zeroed_user_highpage_movable(vma, address); + if (!page) + goto oom; + __SetPageUptodate(page); + + if (mem_cgroup_charge(page, mm, GFP_KERNEL)) + goto oom_free_page; + + entry = mk_pte(page, vma->vm_page_prot); + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + if (!pte_none(*page_table)) + goto release; + inc_mm_counter(mm, anon_rss); + lru_cache_add_active(page); + page_add_new_anon_rmap(page, vma, address); + set_pte_at(mm, address, page_table, entry); + + /* No need to invalidate - it was non-present before */ + update_mmu_cache(vma, address, entry); +unlock: + pte_unmap_unlock(page_table, ptl); + return 0; +release: + mem_cgroup_uncharge_page(page); + page_cache_release(page); + goto unlock; +oom_free_page: + page_cache_release(page); +oom: + return VM_FAULT_OOM; +} + +/* + * __do_fault() tries to create a new page mapping. It aggressively + * tries to share with existing pages, but makes a separate copy if + * the FAULT_FLAG_WRITE is set in the flags parameter in order to avoid + * the next page fault. + * + * As this is called only for pages that do not currently exist, we + * do not need to flush old virtual caches or the TLB. + * + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), and pte neither mapped nor locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. + */ +static int __do_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pmd_t *pmd, + pgoff_t pgoff, unsigned int flags, pte_t orig_pte) +{ + pte_t *page_table; + spinlock_t *ptl; + struct page *page; + pte_t entry; + int anon = 0; + struct page *dirty_page = NULL; + struct vm_fault vmf; + int ret; + int page_mkwrite = 0; + + vmf.virtual_address = (void __user *)(address & PAGE_MASK); + vmf.pgoff = pgoff; + vmf.flags = flags; + vmf.page = NULL; + + ret = vma->vm_ops->fault(vma, &vmf); + if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) + return ret; + + /* + * For consistency in subsequent calls, make the faulted page always + * locked. + */ + if (unlikely(!(ret & VM_FAULT_LOCKED))) + lock_page(vmf.page); + else + VM_BUG_ON(!PageLocked(vmf.page)); + + /* + * Should we do an early C-O-W break? + */ + page = vmf.page; + if (flags & FAULT_FLAG_WRITE) { + if (!(vma->vm_flags & VM_SHARED)) { + anon = 1; + if (unlikely(anon_vma_prepare(vma))) { + ret = VM_FAULT_OOM; + goto out; + } + page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, + vma, address); + if (!page) { + ret = VM_FAULT_OOM; + goto out; + } + copy_user_highpage(page, vmf.page, address, vma); + __SetPageUptodate(page); + } else { + /* + * If the page will be shareable, see if the backing + * address space wants to know that the page is about + * to become writable + */ + if (vma->vm_ops->page_mkwrite) { + unlock_page(page); + if (vma->vm_ops->page_mkwrite(vma, page) < 0) { + ret = VM_FAULT_SIGBUS; + anon = 1; /* no anon but release vmf.page */ + goto out_unlocked; + } + lock_page(page); + /* + * XXX: this is not quite right (racy vs + * invalidate) to unlock and relock the page + * like this, however a better fix requires + * reworking page_mkwrite locking API, which + * is better done later. + */ + if (!page->mapping) { + ret = 0; + anon = 1; /* no anon but release vmf.page */ + goto out; + } + page_mkwrite = 1; + } + } + + } + + if (mem_cgroup_charge(page, mm, GFP_KERNEL)) { + ret = VM_FAULT_OOM; + goto out; + } + + page_table = pte_offset_map_lock(mm, pmd, address, &ptl); + + /* + * This silly early PAGE_DIRTY setting removes a race + * due to the bad i386 page protection. But it's valid + * for other architectures too. + * + * Note that if write_access is true, we either now have + * an exclusive copy of the page, or this is a shared mapping, + * so we can make it writable and dirty to avoid having to + * handle that later. + */ + /* Only go through if we didn't race with anybody else... */ + if (likely(pte_same(*page_table, orig_pte))) { + flush_icache_page(vma, page); + entry = mk_pte(page, vma->vm_page_prot); + if (flags & FAULT_FLAG_WRITE) + entry = maybe_mkwrite(pte_mkdirty(entry), vma); + set_pte_at(mm, address, page_table, entry); + if (anon) { + inc_mm_counter(mm, anon_rss); + lru_cache_add_active(page); + page_add_new_anon_rmap(page, vma, address); + } else { + inc_mm_counter(mm, file_rss); + page_add_file_rmap(page); + if (flags & FAULT_FLAG_WRITE) { + dirty_page = page; + get_page(dirty_page); + } + } + + /* no need to invalidate: a not-present page won't be cached */ + update_mmu_cache(vma, address, entry); + } else { + mem_cgroup_uncharge_page(page); + if (anon) + page_cache_release(page); + else + anon = 1; /* no anon but release faulted_page */ + } + + pte_unmap_unlock(page_table, ptl); + +out: + unlock_page(vmf.page); +out_unlocked: + if (anon) + page_cache_release(vmf.page); + else if (dirty_page) { + if (vma->vm_file) + file_update_time(vma->vm_file); + + set_page_dirty_balance(dirty_page, page_mkwrite); + put_page(dirty_page); + } + + return ret; +} + +static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + int write_access, pte_t orig_pte) +{ + pgoff_t pgoff = (((address & PAGE_MASK) + - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + unsigned int flags = (write_access ? FAULT_FLAG_WRITE : 0); + + pte_unmap(page_table); + return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); +} + +/* + * Fault of a previously existing named mapping. Repopulate the pte + * from the encoded file_pte if possible. This enables swappable + * nonlinear vmas. + * + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. + */ +static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, pte_t *page_table, pmd_t *pmd, + int write_access, pte_t orig_pte) +{ + unsigned int flags = FAULT_FLAG_NONLINEAR | + (write_access ? FAULT_FLAG_WRITE : 0); + pgoff_t pgoff; + + if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) + return 0; + + if (unlikely(!(vma->vm_flags & VM_NONLINEAR) || + !(vma->vm_flags & VM_CAN_NONLINEAR))) { + /* + * Page table corrupted: show pte and kill process. + */ + print_bad_pte(vma, orig_pte, address); + return VM_FAULT_OOM; + } + + pgoff = pte_to_pgoff(orig_pte); + return __do_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); +} + +/* + * These routines also need to handle stuff like marking pages dirty + * and/or accessed for architectures that don't do it in hardware (most + * RISC architectures). The early dirtying is also good on the i386. + * + * There is also a hook called "update_mmu_cache()" that architectures + * with external mmu caches can use to update those (ie the Sparc or + * PowerPC hashed page tables that act as extended TLBs). + * + * We enter with non-exclusive mmap_sem (to exclude vma changes, + * but allow concurrent faults), and pte mapped but not yet locked. + * We return with mmap_sem still held, but pte unmapped and unlocked. + */ +static inline int handle_pte_fault(struct mm_struct *mm, + struct vm_area_struct *vma, unsigned long address, + pte_t *pte, pmd_t *pmd, int write_access) +{ + pte_t entry; + spinlock_t *ptl; + int ret = 0, type = VXPT_UNKNOWN; + + entry = *pte; + if (!pte_present(entry)) { + if (pte_none(entry)) { + if (vma->vm_ops) { + if (likely(vma->vm_ops->fault)) + return do_linear_fault(mm, vma, address, + pte, pmd, write_access, entry); + } + return do_anonymous_page(mm, vma, address, + pte, pmd, write_access); + } + if (pte_file(entry)) + return do_nonlinear_fault(mm, vma, address, + pte, pmd, write_access, entry); + return do_swap_page(mm, vma, address, + pte, pmd, write_access, entry); + } + + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + if (unlikely(!pte_same(*pte, entry))) + goto unlock; + if (write_access) { + if (!pte_write(entry)) { + ret = do_wp_page(mm, vma, address, + pte, pmd, ptl, entry); + type = VXPT_WRITE; + goto out; + } + entry = pte_mkdirty(entry); + } + entry = pte_mkyoung(entry); + if (ptep_set_access_flags(vma, address, pte, entry, write_access)) { + update_mmu_cache(vma, address, entry); + } else { + /* + * This is needed only for protection faults but the arch code + * is not yet telling us if this is a protection fault or not. + * This still avoids useless tlb flushes for .text page faults + * with threads. + */ + if (write_access) + flush_tlb_page(vma, address); + } +unlock: + pte_unmap_unlock(pte, ptl); + ret = 0; +out: + vx_page_fault(mm, vma, type, ret); + return ret; +} + +/* + * By the time we get here, we already hold the mm semaphore + */ +int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, + unsigned long address, int write_access) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *pte; + + __set_current_state(TASK_RUNNING); + + count_vm_event(PGFAULT); + + if (unlikely(is_vm_hugetlb_page(vma))) + return hugetlb_fault(mm, vma, address, write_access); + + pgd = pgd_offset(mm, address); + pud = pud_alloc(mm, pgd, address); + if (!pud) + return VM_FAULT_OOM; + pmd = pmd_alloc(mm, pud, address); + if (!pmd) + return VM_FAULT_OOM; + pte = pte_alloc_map(mm, pmd, address); + if (!pte) + return VM_FAULT_OOM; + + return handle_pte_fault(mm, vma, address, pte, pmd, write_access); +} + +#ifndef __PAGETABLE_PUD_FOLDED +/* + * Allocate page upper directory. + * We've already handled the fast-path in-line. + */ +int __pud_alloc(struct mm_struct *mm, pgd_t *pgd, unsigned long address) +{ + pud_t *new = pud_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + smp_wmb(); /* See comment in __pte_alloc */ + + spin_lock(&mm->page_table_lock); + if (pgd_present(*pgd)) /* Another has populated it */ + pud_free(mm, new); + else + pgd_populate(mm, pgd, new); + spin_unlock(&mm->page_table_lock); + return 0; +} +#endif /* __PAGETABLE_PUD_FOLDED */ + +#ifndef __PAGETABLE_PMD_FOLDED +/* + * Allocate page middle directory. + * We've already handled the fast-path in-line. + */ +int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) +{ + pmd_t *new = pmd_alloc_one(mm, address); + if (!new) + return -ENOMEM; + + smp_wmb(); /* See comment in __pte_alloc */ + + spin_lock(&mm->page_table_lock); +#ifndef __ARCH_HAS_4LEVEL_HACK + if (pud_present(*pud)) /* Another has populated it */ + pmd_free(mm, new); + else + pud_populate(mm, pud, new); +#else + if (pgd_present(*pud)) /* Another has populated it */ + pmd_free(mm, new); + else + pgd_populate(mm, pud, new); +#endif /* __ARCH_HAS_4LEVEL_HACK */ + spin_unlock(&mm->page_table_lock); + return 0; +} +#endif /* __PAGETABLE_PMD_FOLDED */ + +int make_pages_present(unsigned long addr, unsigned long end) +{ + int ret, len, write; + struct vm_area_struct * vma; + + vma = find_vma(current->mm, addr); + if (!vma) + return -ENOMEM; + write = (vma->vm_flags & VM_WRITE) != 0; + BUG_ON(addr >= end); + BUG_ON(end > vma->vm_end); + len = DIV_ROUND_UP(end, PAGE_SIZE) - addr/PAGE_SIZE; + ret = get_user_pages(current, current->mm, addr, + len, write, 0, NULL, NULL); + if (ret < 0) { + /* + SUS require strange return value to mlock + - invalid addr generate to ENOMEM. + - out of memory should generate EAGAIN. + */ + if (ret == -EFAULT) + ret = -ENOMEM; + else if (ret == -ENOMEM) + ret = -EAGAIN; + return ret; + } + return ret == len ? 0 : -ENOMEM; +} + +#if !defined(__HAVE_ARCH_GATE_AREA) + +#if defined(AT_SYSINFO_EHDR) +static struct vm_area_struct gate_vma; + +static int __init gate_vma_init(void) +{ + gate_vma.vm_mm = NULL; + gate_vma.vm_start = FIXADDR_USER_START; + gate_vma.vm_end = FIXADDR_USER_END; + gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; + gate_vma.vm_page_prot = __P101; + /* + * Make sure the vDSO gets into every core dump. + * Dumping its contents makes post-mortem fully interpretable later + * without matching up the same kernel and hardware config to see + * what PC values meant. + */ + gate_vma.vm_flags |= VM_ALWAYSDUMP; + return 0; +} +__initcall(gate_vma_init); +#endif + +struct vm_area_struct *get_gate_vma(struct task_struct *tsk) +{ +#ifdef AT_SYSINFO_EHDR + return &gate_vma; +#else + return NULL; +#endif +} + +int in_gate_area_no_task(unsigned long addr) +{ +#ifdef AT_SYSINFO_EHDR + if ((addr >= FIXADDR_USER_START) && (addr < FIXADDR_USER_END)) + return 1; +#endif + return 0; +} + +#endif /* __HAVE_ARCH_GATE_AREA */ + +#ifdef CONFIG_HAVE_IOREMAP_PROT +static resource_size_t follow_phys(struct vm_area_struct *vma, + unsigned long address, unsigned int flags, + unsigned long *prot) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd; + pte_t *ptep, pte; + spinlock_t *ptl; + resource_size_t phys_addr = 0; + struct mm_struct *mm = vma->vm_mm; + + VM_BUG_ON(!(vma->vm_flags & (VM_IO | VM_PFNMAP))); + + pgd = pgd_offset(mm, address); + if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) + goto no_page_table; + + pud = pud_offset(pgd, address); + if (pud_none(*pud) || unlikely(pud_bad(*pud))) + goto no_page_table; + + pmd = pmd_offset(pud, address); + if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd))) + goto no_page_table; + + /* We cannot handle huge page PFN maps. Luckily they don't exist. */ + if (pmd_huge(*pmd)) + goto no_page_table; + + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + if (!ptep) + goto out; + + pte = *ptep; + if (!pte_present(pte)) + goto unlock; + if ((flags & FOLL_WRITE) && !pte_write(pte)) + goto unlock; + phys_addr = pte_pfn(pte); + phys_addr <<= PAGE_SHIFT; /* Shift here to avoid overflow on PAE */ + + *prot = pgprot_val(pte_pgprot(pte)); + +unlock: + pte_unmap_unlock(ptep, ptl); +out: + return phys_addr; +no_page_table: + return 0; +} + +int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, + void *buf, int len, int write) +{ + resource_size_t phys_addr; + unsigned long prot = 0; + void *maddr; + int offset = addr & (PAGE_SIZE-1); + + if (!(vma->vm_flags & (VM_IO | VM_PFNMAP))) + return -EINVAL; + + phys_addr = follow_phys(vma, addr, write, &prot); + + if (!phys_addr) + return -EINVAL; + + maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot); + if (write) + memcpy_toio(maddr + offset, buf, len); + else + memcpy_fromio(buf, maddr + offset, len); + iounmap(maddr); + + return len; +} +#endif + +/* + * Access another process' address space. + * Source/target buffer must be kernel space, + * Do not walk the page table directly, use get_user_pages + */ +int access_process_vm(struct task_struct *tsk, unsigned long addr, void *buf, int len, int write) +{ + struct mm_struct *mm; + struct vm_area_struct *vma; + void *old_buf = buf; + + mm = get_task_mm(tsk); + if (!mm) + return 0; + + down_read(&mm->mmap_sem); + /* ignore errors, just check how much was successfully transferred */ + while (len) { + int bytes, ret, offset; + void *maddr; + struct page *page = NULL; + + ret = get_user_pages(tsk, mm, addr, 1, + write, 1, &page, &vma); + if (ret <= 0) { + /* + * Check if this is a VM_IO | VM_PFNMAP VMA, which + * we can access using slightly different code. + */ +#ifdef CONFIG_HAVE_IOREMAP_PROT + vma = find_vma(mm, addr); + if (!vma) + break; + if (vma->vm_ops && vma->vm_ops->access) + ret = vma->vm_ops->access(vma, addr, buf, + len, write); + if (ret <= 0) +#endif + break; + bytes = ret; + } else { + bytes = len; + offset = addr & (PAGE_SIZE-1); + if (bytes > PAGE_SIZE-offset) + bytes = PAGE_SIZE-offset; + + maddr = kmap(page); + if (write) { + copy_to_user_page(vma, page, addr, + maddr + offset, buf, bytes); + set_page_dirty_lock(page); + } else { + copy_from_user_page(vma, page, addr, + buf, maddr + offset, bytes); + } + kunmap(page); + page_cache_release(page); + } + len -= bytes; + buf += bytes; + addr += bytes; + } + up_read(&mm->mmap_sem); + mmput(mm); + + return buf - old_buf; +} + +/* + * Print the name of a VMA. + */ +void print_vma_addr(char *prefix, unsigned long ip) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + + /* + * Do not print if we are in atomic + * contexts (in exception stacks, etc.): + */ + if (preempt_count()) + return; + + down_read(&mm->mmap_sem); + vma = find_vma(mm, ip); + if (vma && vma->vm_file) { + struct file *f = vma->vm_file; + char *buf = (char *)__get_free_page(GFP_KERNEL); + if (buf) { + char *p, *s; + + p = d_path(&f->f_path, buf, PAGE_SIZE); + if (IS_ERR(p)) + p = "?"; + s = strrchr(p, '/'); + if (s) + p = s+1; + printk("%s%s[%lx+%lx]", prefix, p, + vma->vm_start, + vma->vm_end - vma->vm_start); + free_page((unsigned long)buf); + } + } + up_read(¤t->mm->mmap_sem); +} diff -Nurb linux-2.6.27-590/mm/slab.c linux-2.6.27-591/mm/slab.c --- linux-2.6.27-590/mm/slab.c 2010-02-01 19:42:07.000000000 -0500 +++ linux-2.6.27-591/mm/slab.c 2010-02-01 19:43:07.000000000 -0500 @@ -110,6 +110,7 @@ #include #include #include +#include #include #include @@ -248,6 +249,14 @@ void *addr; }; +extern void (*rec_event)(void *,unsigned int); +struct event_spec { + unsigned long pc; + unsigned long dcookie; + unsigned count; + unsigned char reason; +}; + /* * struct array_cache * @@ -3469,6 +3478,19 @@ local_irq_restore(save_flags); objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller); prefetchw(objp); +#ifdef CONFIG_CHOPSTIX + if (rec_event && objp) { + struct event event; + struct event_spec espec; + + espec.reason = 0; /* alloc */ + event.event_data=&espec; + event.task = current; + espec.pc=caller; + event.event_type=5; + (*rec_event)(&event, cachep->buffer_size); + } +#endif if (unlikely((flags & __GFP_ZERO) && objp)) memset(objp, 0, obj_size(cachep)); @@ -3578,12 +3600,26 @@ * Release an obj back to its cache. If the obj has a constructed state, it must * be in this state _before_ it is released. Called with disabled ints. */ -static inline void __cache_free(struct kmem_cache *cachep, void *objp) +static inline void __cache_free(struct kmem_cache *cachep, void *objp, void *caller) { struct array_cache *ac = cpu_cache_get(cachep); check_irq_off(); - objp = cache_free_debugcheck(cachep, objp, __builtin_return_address(0)); + objp = cache_free_debugcheck(cachep, objp, caller); + #ifdef CONFIG_CHOPSTIX + if (rec_event && objp) { + struct event event; + struct event_spec espec; + + espec.reason = 1; /* free */ + event.event_data=&espec; + event.task = current; + espec.pc=caller; + event.event_type=4; + (*rec_event)(&event, cachep->buffer_size); + } + #endif + vx_slab_free(cachep); /* @@ -3714,6 +3750,7 @@ void *caller) { struct kmem_cache *cachep; + void *ret; /* If you want to save a few bytes .text space: replace * __ with kmem_. @@ -3741,10 +3778,17 @@ EXPORT_SYMBOL(__kmalloc_track_caller); #else +#ifdef CONFIG_CHOPSTIX +void *__kmalloc(size_t size, gfp_t flags) +{ + return __do_kmalloc(size, flags, __builtin_return_address(0)); +} +#else void *__kmalloc(size_t size, gfp_t flags) { return __do_kmalloc(size, flags, NULL); } +#endif EXPORT_SYMBOL(__kmalloc); #endif @@ -3764,7 +3808,7 @@ debug_check_no_locks_freed(objp, obj_size(cachep)); if (!(cachep->flags & SLAB_DEBUG_OBJECTS)) debug_check_no_obj_freed(objp, obj_size(cachep)); - __cache_free(cachep, objp); + __cache_free(cachep, objp,__builtin_return_address(0)); local_irq_restore(flags); } EXPORT_SYMBOL(kmem_cache_free); @@ -3790,7 +3834,7 @@ c = virt_to_cache(objp); debug_check_no_locks_freed(objp, obj_size(c)); debug_check_no_obj_freed(objp, obj_size(c)); - __cache_free(c, (void *)objp); + __cache_free(c, (void *)objp,__builtin_return_address(0)); local_irq_restore(flags); } EXPORT_SYMBOL(kfree);