The Brain Fuck Scheduler v0.480 by Con Kolivas. A single shared runqueue strict fairness earliest deadline first design. Runqueue insertion is O(log(n)), lookup is O(1), removal is O(k) where k <= 16 Excellent throughput and latency for 1 to many CPUs on desktop and server commodity hardware. Not recommended for 4096 cpus. Scalability is optimal when your workload is equal to the number of CPUs on bfs. ie you should ONLY do make -j4 on quad core, -j2 on dual core and so on. Interactive mode is enabled by default but can be disabled for improved throughput echo 0 > /proc/sys/kernel/interactive Features SCHED_IDLEPRIO and SCHED_ISO scheduling policies as well. You do NOT need to use these policies for good performance, they are purely optional for even better performance in extreme conditions. To run something idleprio, use schedtool like so: schedtool -D -e make -j4 To run something isoprio, use schedtool like so: schedtool -I -e amarok Includes configurable SMT-nice support for better nice level and scheduling policy support across SMT (aka hyperthread) sibling CPUs. Includes accurate sub-tick accounting of tasks so userspace reported cpu usage may be very different if you have very short lived tasks. -ck Index: linux-4.7-bfs/arch/powerpc/platforms/cell/spufs/sched.c =================================================================== --- linux-4.7-bfs.orig/arch/powerpc/platforms/cell/spufs/sched.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/arch/powerpc/platforms/cell/spufs/sched.c 2016-07-29 12:15:37.100601803 +1000 @@ -64,11 +64,6 @@ static struct timer_list spusched_timer; static struct timer_list spuloadavg_timer; /* - * Priority of a normal, non-rt, non-niced'd process (aka nice level 0). - */ -#define NORMAL_PRIO 120 - -/* * Frequency of the spu scheduler tick. By default we do one SPU scheduler * tick for every 10 CPU scheduler ticks. */ Index: linux-4.7-bfs/Documentation/scheduler/sched-BFS.txt =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-4.7-bfs/Documentation/scheduler/sched-BFS.txt 2016-07-29 12:15:37.101601795 +1000 @@ -0,0 +1,357 @@ +BFS - The Brain Fuck Scheduler by Con Kolivas. + +Goals. + +The goal of the Brain Fuck Scheduler, referred to as BFS from here on, is to +completely do away with the complex designs of the past for the cpu process +scheduler and instead implement one that is very simple in basic design. +The main focus of BFS is to achieve excellent desktop interactivity and +responsiveness without heuristics and tuning knobs that are difficult to +understand, impossible to model and predict the effect of, and when tuned to +one workload cause massive detriment to another. + + +Design summary. + +BFS is best described as a single runqueue, O(n) lookup, earliest effective +virtual deadline first design, loosely based on EEVDF (earliest eligible virtual +deadline first) and my previous Staircase Deadline scheduler. Each component +shall be described in order to understand the significance of, and reasoning for +it. The codebase when the first stable version was released was approximately +9000 lines less code than the existing mainline linux kernel scheduler (in +2.6.31). This does not even take into account the removal of documentation and +the cgroups code that is not used. + +Design reasoning. + +The single runqueue refers to the queued but not running processes for the +entire system, regardless of the number of CPUs. The reason for going back to +a single runqueue design is that once multiple runqueues are introduced, +per-CPU or otherwise, there will be complex interactions as each runqueue will +be responsible for the scheduling latency and fairness of the tasks only on its +own runqueue, and to achieve fairness and low latency across multiple CPUs, any +advantage in throughput of having CPU local tasks causes other disadvantages. +This is due to requiring a very complex balancing system to at best achieve some +semblance of fairness across CPUs and can only maintain relatively low latency +for tasks bound to the same CPUs, not across them. To increase said fairness +and latency across CPUs, the advantage of local runqueue locking, which makes +for better scalability, is lost due to having to grab multiple locks. + +A significant feature of BFS is that all accounting is done purely based on CPU +used and nowhere is sleep time used in any way to determine entitlement or +interactivity. Interactivity "estimators" that use some kind of sleep/run +algorithm are doomed to fail to detect all interactive tasks, and to falsely tag +tasks that aren't interactive as being so. The reason for this is that it is +close to impossible to determine that when a task is sleeping, whether it is +doing it voluntarily, as in a userspace application waiting for input in the +form of a mouse click or otherwise, or involuntarily, because it is waiting for +another thread, process, I/O, kernel activity or whatever. Thus, such an +estimator will introduce corner cases, and more heuristics will be required to +cope with those corner cases, introducing more corner cases and failed +interactivity detection and so on. Interactivity in BFS is built into the design +by virtue of the fact that tasks that are waking up have not used up their quota +of CPU time, and have earlier effective deadlines, thereby making it very likely +they will preempt any CPU bound task of equivalent nice level. See below for +more information on the virtual deadline mechanism. Even if they do not preempt +a running task, because the rr interval is guaranteed to have a bound upper +limit on how long a task will wait for, it will be scheduled within a timeframe +that will not cause visible interface jitter. + + +Design details. + +Task insertion. + +BFS inserts tasks into each relevant queue as an O(1) insertion into a double +linked list. On insertion, *every* running queue is checked to see if the newly +queued task can run on any idle queue, or preempt the lowest running task on the +system. This is how the cross-CPU scheduling of BFS achieves significantly lower +latency per extra CPU the system has. In this case the lookup is, in the worst +case scenario, O(n) where n is the number of CPUs on the system. + +Data protection. + +BFS has one single lock protecting the process local data of every task in the +global queue. Thus every insertion, removal and modification of task data in the +global runqueue needs to grab the global lock. However, once a task is taken by +a CPU, the CPU has its own local data copy of the running process' accounting +information which only that CPU accesses and modifies (such as during a +timer tick) thus allowing the accounting data to be updated lockless. Once a +CPU has taken a task to run, it removes it from the global queue. Thus the +global queue only ever has, at most, + + (number of tasks requesting cpu time) - (number of logical CPUs) + 1 + +tasks in the global queue. This value is relevant for the time taken to look up +tasks during scheduling. This will increase if many tasks with CPU affinity set +in their policy to limit which CPUs they're allowed to run on if they outnumber +the number of CPUs. The +1 is because when rescheduling a task, the CPU's +currently running task is put back on the queue. Lookup will be described after +the virtual deadline mechanism is explained. + +Virtual deadline. + +The key to achieving low latency, scheduling fairness, and "nice level" +distribution in BFS is entirely in the virtual deadline mechanism. The related +tunable in BFS is the rr_interval, or "round robin interval". This is the +maximum time two SCHED_OTHER (or SCHED_NORMAL, the common scheduling policy) +tasks of the same nice level will be running for, or looking at it the other +way around, the longest duration two tasks of the same nice level will be +delayed for. When a task requests cpu time, it is given a quota (time_slice) +equal to the rr_interval and a virtual deadline. The virtual deadline is +offset from the current time in jiffies by this equation: + + jiffies + (prio_ratio * rr_interval) + +The prio_ratio is determined as a ratio compared to the baseline of nice -20 +and increases by 10% per nice level. The deadline is a virtual one only in that +no guarantee is placed that a task will actually be scheduled by this time, but +it is used to compare which task should go next. There are three components to +how a task is next chosen. First is time_slice expiration. If a task runs out +of its time_slice, it is descheduled, the time_slice is refilled, and the +deadline reset to that formula above. Second is sleep, where a task no longer +is requesting CPU for whatever reason. The time_slice and deadline are _not_ +adjusted in this case and are just carried over for when the task is next +scheduled. Third is preemption, and that is when a newly waking task is deemed +higher priority than a currently running task on any cpu by virtue of the fact +that it has an earlier virtual deadline than the currently running task. The +earlier deadline is the key to which task is next chosen for the first and +second cases. Once a task is descheduled, it is put back on the queue, and an +O(n) lookup of all queued-but-not-running tasks is done to determine which has +the earliest deadline and that task is chosen to receive CPU next. + +The CPU proportion of different nice tasks works out to be approximately the + + (prio_ratio difference)^2 + +The reason it is squared is that a task's deadline does not change while it is +running unless it runs out of time_slice. Thus, even if the time actually +passes the deadline of another task that is queued, it will not get CPU time +unless the current running task deschedules, and the time "base" (jiffies) is +constantly moving. + +Task lookup. + +BFS has 103 priority queues. 100 of these are dedicated to the static priority +of realtime tasks, and the remaining 3 are, in order of best to worst priority, +SCHED_ISO (isochronous), SCHED_NORMAL, and SCHED_IDLEPRIO (idle priority +scheduling). When a task of these priorities is queued, a bitmap of running +priorities is set showing which of these priorities has tasks waiting for CPU +time. When a CPU is made to reschedule, the lookup for the next task to get +CPU time is performed in the following way: + +First the bitmap is checked to see what static priority tasks are queued. If +any realtime priorities are found, the corresponding queue is checked and the +first task listed there is taken (provided CPU affinity is suitable) and lookup +is complete. If the priority corresponds to a SCHED_ISO task, they are also +taken in FIFO order (as they behave like SCHED_RR). If the priority corresponds +to either SCHED_NORMAL or SCHED_IDLEPRIO, then the lookup becomes O(n). At this +stage, every task in the runlist that corresponds to that priority is checked +to see which has the earliest set deadline, and (provided it has suitable CPU +affinity) it is taken off the runqueue and given the CPU. If a task has an +expired deadline, it is taken and the rest of the lookup aborted (as they are +chosen in FIFO order). + +Thus, the lookup is O(n) in the worst case only, where n is as described +earlier, as tasks may be chosen before the whole task list is looked over. + + +Scalability. + +The major limitations of BFS will be that of scalability, as the separate +runqueue designs will have less lock contention as the number of CPUs rises. +However they do not scale linearly even with separate runqueues as multiple +runqueues will need to be locked concurrently on such designs to be able to +achieve fair CPU balancing, to try and achieve some sort of nice-level fairness +across CPUs, and to achieve low enough latency for tasks on a busy CPU when +other CPUs would be more suited. BFS has the advantage that it requires no +balancing algorithm whatsoever, as balancing occurs by proxy simply because +all CPUs draw off the global runqueue, in priority and deadline order. Despite +the fact that scalability is _not_ the prime concern of BFS, it both shows very +good scalability to smaller numbers of CPUs and is likely a more scalable design +at these numbers of CPUs. + +It also has some very low overhead scalability features built into the design +when it has been deemed their overhead is so marginal that they're worth adding. +The first is the local copy of the running process' data to the CPU it's running +on to allow that data to be updated lockless where possible. Then there is +deference paid to the last CPU a task was running on, by trying that CPU first +when looking for an idle CPU to use the next time it's scheduled. Finally there +is the notion of "sticky" tasks that are flagged when they are involuntarily +descheduled, meaning they still want further CPU time. This sticky flag is +used to bias heavily against those tasks being scheduled on a different CPU +unless that CPU would be otherwise idle. When a cpu frequency governor is used +that scales with CPU load, such as ondemand, sticky tasks are not scheduled +on a different CPU at all, preferring instead to go idle. This means the CPU +they were bound to is more likely to increase its speed while the other CPU +will go idle, thus speeding up total task execution time and likely decreasing +power usage. This is the only scenario where BFS will allow a CPU to go idle +in preference to scheduling a task on the earliest available spare CPU. + +The real cost of migrating a task from one CPU to another is entirely dependant +on the cache footprint of the task, how cache intensive the task is, how long +it's been running on that CPU to take up the bulk of its cache, how big the CPU +cache is, how fast and how layered the CPU cache is, how fast a context switch +is... and so on. In other words, it's close to random in the real world where we +do more than just one sole workload. The only thing we can be sure of is that +it's not free. So BFS uses the principle that an idle CPU is a wasted CPU and +utilising idle CPUs is more important than cache locality, and cache locality +only plays a part after that. + +When choosing an idle CPU for a waking task, the cache locality is determined +according to where the task last ran and then idle CPUs are ranked from best +to worst to choose the most suitable idle CPU based on cache locality, NUMA +node locality and hyperthread sibling business. They are chosen in the +following preference (if idle): + +* Same core, idle or busy cache, idle threads +* Other core, same cache, idle or busy cache, idle threads. +* Same node, other CPU, idle cache, idle threads. +* Same node, other CPU, busy cache, idle threads. +* Same core, busy threads. +* Other core, same cache, busy threads. +* Same node, other CPU, busy threads. +* Other node, other CPU, idle cache, idle threads. +* Other node, other CPU, busy cache, idle threads. +* Other node, other CPU, busy threads. + +This shows the SMT or "hyperthread" awareness in the design as well which will +choose a real idle core first before a logical SMT sibling which already has +tasks on the physical CPU. + +Early benchmarking of BFS suggested scalability dropped off at the 16 CPU mark. +However this benchmarking was performed on an earlier design that was far less +scalable than the current one so it's hard to know how scalable it is in terms +of both CPUs (due to the global runqueue) and heavily loaded machines (due to +O(n) lookup) at this stage. Note that in terms of scalability, the number of +_logical_ CPUs matters, not the number of _physical_ CPUs. Thus, a dual (2x) +quad core (4X) hyperthreaded (2X) machine is effectively a 16X. Newer benchmark +results are very promising indeed. Benchmark contributions are most welcome. + + +Features + +As the initial prime target audience for BFS was the average desktop user, it +was designed to not need tweaking, tuning or have features set to obtain benefit +from it. Thus the number of knobs and features has been kept to an absolute +minimum and should not require extra user input for the vast majority of cases. +There are precisely 2 tunables, and 2 extra scheduling policies. The rr_interval +and iso_cpu tunables, and the SCHED_ISO and SCHED_IDLEPRIO policies. In addition +to this, BFS also uses sub-tick accounting. What BFS does _not_ now feature is +support for CGROUPS. The average user should neither need to know what these +are, nor should they need to be using them to have good desktop behaviour. + +There are two "scheduler" tunables, the round robin interval and the +interactive flag. These can be accessed in + + /proc/sys/kernel/rr_interval + /proc/sys/kernel/interactive + +rr_interval value + +The value is in milliseconds, and the default value is set to 6ms. Valid values +are from 1 to 1000. Decreasing the value will decrease latencies at the cost of +decreasing throughput, while increasing it will improve throughput, but at the +cost of worsening latencies. The accuracy of the rr interval is limited by HZ +resolution of the kernel configuration. Thus, the worst case latencies are +usually slightly higher than this actual value. BFS uses "dithering" to try and +minimise the effect the Hz limitation has. The default value of 6 is not an +arbitrary one. It is based on the fact that humans can detect jitter at +approximately 7ms, so aiming for much lower latencies is pointless under most +circumstances. It is worth noting this fact when comparing the latency +performance of BFS to other schedulers. Worst case latencies being higher than +7ms are far worse than average latencies not being in the microsecond range. +Experimentation has shown that rr intervals being increased up to 300 can +improve throughput but beyond that, scheduling noise from elsewhere prevents +further demonstrable throughput. + +interactive flag + +This is a simple boolean that can be set to 1 or 0, set to 1 by default. This +sacrifices some of the interactive performance by giving tasks a degree of +soft affinity for logical CPUs when it will lead to improved throughput, but +enabling it also sacrifices the completely deterministic nature with respect +to latency that BFS otherwise normally provides, and subsequently leads to +slightly higher latencies and a noticeably less interactive system. + + +Isochronous scheduling. + +Isochronous scheduling is a unique scheduling policy designed to provide +near-real-time performance to unprivileged (ie non-root) users without the +ability to starve the machine indefinitely. Isochronous tasks (which means +"same time") are set using, for example, the schedtool application like so: + + schedtool -I -e amarok + +This will start the audio application "amarok" as SCHED_ISO. How SCHED_ISO works +is that it has a priority level between true realtime tasks and SCHED_NORMAL +which would allow them to preempt all normal tasks, in a SCHED_RR fashion (ie, +if multiple SCHED_ISO tasks are running, they purely round robin at rr_interval +rate). However if ISO tasks run for more than a tunable finite amount of time, +they are then demoted back to SCHED_NORMAL scheduling. This finite amount of +time is the percentage of _total CPU_ available across the machine, configurable +as a percentage in the following "resource handling" tunable (as opposed to a +scheduler tunable): + + /proc/sys/kernel/iso_cpu + +and is set to 70% by default. It is calculated over a rolling 5 second average +Because it is the total CPU available, it means that on a multi CPU machine, it +is possible to have an ISO task running as realtime scheduling indefinitely on +just one CPU, as the other CPUs will be available. Setting this to 100 is the +equivalent of giving all users SCHED_RR access and setting it to 0 removes the +ability to run any pseudo-realtime tasks. + +A feature of BFS is that it detects when an application tries to obtain a +realtime policy (SCHED_RR or SCHED_FIFO) and the caller does not have the +appropriate privileges to use those policies. When it detects this, it will +give the task SCHED_ISO policy instead. Thus it is transparent to the user. +Because some applications constantly set their policy as well as their nice +level, there is potential for them to undo the override specified by the user +on the command line of setting the policy to SCHED_ISO. To counter this, once +a task has been set to SCHED_ISO policy, it needs superuser privileges to set +it back to SCHED_NORMAL. This will ensure the task remains ISO and all child +processes and threads will also inherit the ISO policy. + +Idleprio scheduling. + +Idleprio scheduling is a scheduling policy designed to give out CPU to a task +_only_ when the CPU would be otherwise idle. The idea behind this is to allow +ultra low priority tasks to be run in the background that have virtually no +effect on the foreground tasks. This is ideally suited to distributed computing +clients (like setiathome, folding, mprime etc) but can also be used to start +a video encode or so on without any slowdown of other tasks. To avoid this +policy from grabbing shared resources and holding them indefinitely, if it +detects a state where the task is waiting on I/O, the machine is about to +suspend to ram and so on, it will transiently schedule them as SCHED_NORMAL. As +per the Isochronous task management, once a task has been scheduled as IDLEPRIO, +it cannot be put back to SCHED_NORMAL without superuser privileges. Tasks can +be set to start as SCHED_IDLEPRIO with the schedtool command like so: + + schedtool -D -e ./mprime + +Subtick accounting. + +It is surprisingly difficult to get accurate CPU accounting, and in many cases, +the accounting is done by simply determining what is happening at the precise +moment a timer tick fires off. This becomes increasingly inaccurate as the +timer tick frequency (HZ) is lowered. It is possible to create an application +which uses almost 100% CPU, yet by being descheduled at the right time, records +zero CPU usage. While the main problem with this is that there are possible +security implications, it is also difficult to determine how much CPU a task +really does use. BFS tries to use the sub-tick accounting from the TSC clock, +where possible, to determine real CPU usage. This is not entirely reliable, but +is far more likely to produce accurate CPU usage data than the existing designs +and will not show tasks as consuming no CPU usage when they actually are. Thus, +the amount of CPU reported as being used by BFS will more accurately represent +how much CPU the task itself is using (as is shown for example by the 'time' +application), so the reported values may be quite different to other schedulers. +Values reported as the 'load' are more prone to problems with this design, but +per process values are closer to real usage. When comparing throughput of BFS +to other designs, it is important to compare the actual completed work in terms +of total wall clock time taken and total work done, rather than the reported +"cpu usage". + + +Con Kolivas Tue, 5 Apr 2011 Index: linux-4.7-bfs/Documentation/sysctl/kernel.txt =================================================================== --- linux-4.7-bfs.orig/Documentation/sysctl/kernel.txt 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/Documentation/sysctl/kernel.txt 2016-07-29 12:15:37.101601795 +1000 @@ -39,6 +39,7 @@ show up in /proc/sys/kernel: - hung_task_timeout_secs - hung_task_warnings - kexec_load_disabled +- iso_cpu - kptr_restrict - kstack_depth_to_print [ X86 only ] - l2cr [ PPC only ] @@ -72,6 +73,7 @@ show up in /proc/sys/kernel: - randomize_va_space - real-root-dev ==> Documentation/initrd.txt - reboot-cmd [ SPARC only ] +- rr_interval - rtsig-max - rtsig-nr - sem @@ -401,6 +403,16 @@ kernel stack. ============================================================== +iso_cpu: (BFS CPU scheduler only). + +This sets the percentage cpu that the unprivileged SCHED_ISO tasks can +run effectively at realtime priority, averaged over a rolling five +seconds over the -whole- system, meaning all cpus. + +Set to 70 (percent) by default. + +============================================================== + l2cr: (PPC only) This flag controls the L2 cache of G3 processor boards. If @@ -792,6 +804,20 @@ rebooting. ??? ============================================================== +rr_interval: (BFS CPU scheduler only) + +This is the smallest duration that any cpu process scheduling unit +will run for. Increasing this value can increase throughput of cpu +bound tasks substantially but at the expense of increased latencies +overall. Conversely decreasing it will decrease average and maximum +latencies but at the expense of throughput. This value is in +milliseconds and the default value chosen depends on the number of +cpus available at scheduler initialisation with a minimum of 6. + +Valid values are from 1-1000. + +============================================================== + rtsig-max & rtsig-nr: The file rtsig-max can be used to tune the maximum number Index: linux-4.7-bfs/fs/proc/base.c =================================================================== --- linux-4.7-bfs.orig/fs/proc/base.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/fs/proc/base.c 2016-07-29 12:15:37.101601795 +1000 @@ -505,7 +505,7 @@ static int proc_pid_schedstat(struct seq seq_printf(m, "0 0 0\n"); else seq_printf(m, "%llu %llu %lu\n", - (unsigned long long)task->se.sum_exec_runtime, + (unsigned long long)tsk_seruntime(task), (unsigned long long)task->sched_info.run_delay, task->sched_info.pcount); Index: linux-4.7-bfs/include/linux/init_task.h =================================================================== --- linux-4.7-bfs.orig/include/linux/init_task.h 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/include/linux/init_task.h 2016-09-02 14:58:32.757394520 +1000 @@ -157,8 +157,6 @@ extern struct task_group root_task_group # define INIT_VTIME(tsk) #endif -#define INIT_TASK_COMM "swapper" - #ifdef CONFIG_RT_MUTEXES # define INIT_RT_MUTEXES(tsk) \ .pi_waiters = RB_ROOT, \ @@ -187,6 +185,78 @@ extern struct task_group root_task_group * INIT_TASK is used to set up the first task table, touch at * your own risk!. Base=0, limit=0x1fffff (=2MB) */ +#ifdef CONFIG_SCHED_BFS +#define INIT_TASK_COMM "BFS" +#define INIT_TASK(tsk) \ +{ \ + .state = 0, \ + .stack = &init_thread_info, \ + .usage = ATOMIC_INIT(2), \ + .flags = PF_KTHREAD, \ + .prio = NORMAL_PRIO, \ + .static_prio = MAX_PRIO-20, \ + .normal_prio = NORMAL_PRIO, \ + .deadline = 0, \ + .policy = SCHED_NORMAL, \ + .cpus_allowed = CPU_MASK_ALL, \ + .mm = NULL, \ + .active_mm = &init_mm, \ + .restart_block = { \ + .fn = do_no_restart_syscall, \ + }, \ + .node = NULL, \ + .time_slice = HZ, \ + .tasks = LIST_HEAD_INIT(tsk.tasks), \ + INIT_PUSHABLE_TASKS(tsk) \ + .ptraced = LIST_HEAD_INIT(tsk.ptraced), \ + .ptrace_entry = LIST_HEAD_INIT(tsk.ptrace_entry), \ + .real_parent = &tsk, \ + .parent = &tsk, \ + .children = LIST_HEAD_INIT(tsk.children), \ + .sibling = LIST_HEAD_INIT(tsk.sibling), \ + .group_leader = &tsk, \ + RCU_POINTER_INITIALIZER(real_cred, &init_cred), \ + RCU_POINTER_INITIALIZER(cred, &init_cred), \ + .comm = INIT_TASK_COMM, \ + .thread = INIT_THREAD, \ + .fs = &init_fs, \ + .files = &init_files, \ + .signal = &init_signals, \ + .sighand = &init_sighand, \ + .nsproxy = &init_nsproxy, \ + .pending = { \ + .list = LIST_HEAD_INIT(tsk.pending.list), \ + .signal = {{0}}}, \ + .blocked = {{0}}, \ + .alloc_lock = __SPIN_LOCK_UNLOCKED(tsk.alloc_lock), \ + .journal_info = NULL, \ + .cpu_timers = INIT_CPU_TIMERS(tsk.cpu_timers), \ + .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(tsk.pi_lock), \ + .timer_slack_ns = 50000, /* 50 usec default slack */ \ + .pids = { \ + [PIDTYPE_PID] = INIT_PID_LINK(PIDTYPE_PID), \ + [PIDTYPE_PGID] = INIT_PID_LINK(PIDTYPE_PGID), \ + [PIDTYPE_SID] = INIT_PID_LINK(PIDTYPE_SID), \ + }, \ + .thread_group = LIST_HEAD_INIT(tsk.thread_group), \ + .thread_node = LIST_HEAD_INIT(init_signals.thread_head), \ + INIT_IDS \ + INIT_PERF_EVENTS(tsk) \ + INIT_TRACE_IRQFLAGS \ + INIT_LOCKDEP \ + INIT_FTRACE_GRAPH \ + INIT_TRACE_RECURSION \ + INIT_TASK_RCU_PREEMPT(tsk) \ + INIT_TASK_RCU_TASKS(tsk) \ + INIT_CPUSET_SEQ(tsk) \ + INIT_RT_MUTEXES(tsk) \ + INIT_PREV_CPUTIME(tsk) \ + INIT_VTIME(tsk) \ + INIT_NUMA_BALANCING(tsk) \ + INIT_KASAN(tsk) \ +} +#else /* CONFIG_SCHED_BFS */ +#define INIT_TASK_COMM "swapper" #define INIT_TASK(tsk) \ { \ .state = 0, \ @@ -261,7 +331,7 @@ extern struct task_group root_task_group INIT_NUMA_BALANCING(tsk) \ INIT_KASAN(tsk) \ } - +#endif /* CONFIG_SCHED_BFS */ #define INIT_CPU_TIMERS(cpu_timers) \ { \ Index: linux-4.7-bfs/include/linux/ioprio.h =================================================================== --- linux-4.7-bfs.orig/include/linux/ioprio.h 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/include/linux/ioprio.h 2016-07-29 12:15:37.102601788 +1000 @@ -52,6 +52,8 @@ enum { */ static inline int task_nice_ioprio(struct task_struct *task) { + if (iso_task(task)) + return 0; return (task_nice(task) + 20) / 5; } Index: linux-4.7-bfs/include/linux/sched.h =================================================================== --- linux-4.7-bfs.orig/include/linux/sched.h 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/include/linux/sched.h 2016-09-02 14:58:32.757394520 +1000 @@ -59,6 +59,7 @@ struct sched_param { #include #include #include +#include #include @@ -176,7 +177,7 @@ extern void get_iowait_load(unsigned lon extern void calc_global_load(unsigned long ticks); -#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) && !defined(CONFIG_SCHED_BFS) extern void cpu_load_update_nohz_start(void); extern void cpu_load_update_nohz_stop(void); #else @@ -339,8 +340,6 @@ extern void init_idle_bootup_task(struct extern cpumask_var_t cpu_isolated_map; -extern int runqueue_is_locked(int cpu); - #if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) extern void nohz_balance_enter_idle(int cpu); extern void set_cpu_sd_state_idle(void); @@ -1462,9 +1461,11 @@ struct task_struct { unsigned int flags; /* per process flags, defined below */ unsigned int ptrace; +#if defined(CONFIG_SMP) || defined(CONFIG_SCHED_BFS) + int on_cpu; +#endif #ifdef CONFIG_SMP struct llist_node wake_entry; - int on_cpu; unsigned int wakee_flips; unsigned long wakee_flip_decay_ts; struct task_struct *last_wakee; @@ -1472,12 +1473,29 @@ struct task_struct { int wake_cpu; #endif int on_rq; - int prio, static_prio, normal_prio; unsigned int rt_priority; +#ifdef CONFIG_SCHED_BFS + int time_slice; + u64 deadline; + skiplist_node *node; /* Skip list node id */ + u64 last_ran; + u64 sched_time; /* sched_clock time spent running */ +#ifdef CONFIG_SMT_NICE + int smt_bias; /* Policy/nice level bias across smt siblings */ +#endif +#ifdef CONFIG_SMP + bool sticky; /* Soft affined flag */ +#endif +#ifdef CONFIG_HOTPLUG_CPU + bool zerobound; /* Bound to CPU0 for hotplug */ +#endif + unsigned long rt_timeout; +#else /* CONFIG_SCHED_BFS */ const struct sched_class *sched_class; struct sched_entity se; struct sched_rt_entity rt; +#endif #ifdef CONFIG_CGROUP_SCHED struct task_group *sched_task_group; #endif @@ -1598,6 +1616,9 @@ struct task_struct { int __user *clear_child_tid; /* CLONE_CHILD_CLEARTID */ cputime_t utime, stime, utimescaled, stimescaled; +#ifdef CONFIG_SCHED_BFS + unsigned long utime_pc, stime_pc; +#endif cputime_t gtime; struct prev_cputime prev_cputime; #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN @@ -1934,6 +1955,63 @@ extern int arch_task_struct_size __read_ # define arch_task_struct_size (sizeof(struct task_struct)) #endif +#ifdef CONFIG_SCHED_BFS +bool grunqueue_is_locked(void); +void grq_unlock_wait(void); +void cpu_scaling(int cpu); +void cpu_nonscaling(int cpu); +#define tsk_seruntime(t) ((t)->sched_time) +#define tsk_rttimeout(t) ((t)->rt_timeout) + +static inline void tsk_cpus_current(struct task_struct *p) +{ +} + +static inline int runqueue_is_locked(int cpu) +{ + return grunqueue_is_locked(); +} + +void print_scheduler_version(void); + +static inline bool iso_task(struct task_struct *p) +{ + return (p->policy == SCHED_ISO); +} +#else /* CFS */ +extern int runqueue_is_locked(int cpu); +static inline void cpu_scaling(int cpu) +{ +} + +static inline void cpu_nonscaling(int cpu) +{ +} +#define tsk_seruntime(t) ((t)->se.sum_exec_runtime) +#define tsk_rttimeout(t) ((t)->rt.timeout) + +static inline void tsk_cpus_current(struct task_struct *p) +{ + p->nr_cpus_allowed = current->nr_cpus_allowed; +} + +static inline void print_scheduler_version(void) +{ + printk(KERN_INFO"CFS CPU scheduler.\n"); +} + +static inline bool iso_task(struct task_struct *p) +{ + return false; +} + +/* Anyone feel like implementing this? */ +static inline bool above_background_load(void) +{ + return false; +} +#endif /* CONFIG_SCHED_BFS */ + /* Future-safe accessor for struct task_struct's cpus_allowed. */ #define tsk_cpus_allowed(tsk) (&(tsk)->cpus_allowed) @@ -2358,7 +2436,7 @@ static inline int set_cpus_allowed_ptr(s } #endif -#ifdef CONFIG_NO_HZ_COMMON +#if defined(CONFIG_NO_HZ_COMMON) && !defined(CONFIG_SCHED_BFS) void calc_load_enter_idle(void); void calc_load_exit_idle(void); #else @@ -2459,7 +2537,7 @@ extern unsigned long long task_sched_runtime(struct task_struct *task); /* sched_exec is called by processes performing an exec */ -#ifdef CONFIG_SMP +#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_BFS) extern void sched_exec(void); #else #define sched_exec() {} @@ -3287,7 +3365,7 @@ static inline unsigned int task_cpu(cons return 0; } -static inline void set_task_cpu(struct task_struct *p, unsigned int cpu) +static inline void set_task_cpu(struct task_struct *p, int cpu) { } Index: linux-4.7-bfs/init/Kconfig =================================================================== --- linux-4.7-bfs.orig/init/Kconfig 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/init/Kconfig 2016-07-29 12:15:37.103601780 +1000 @@ -28,6 +28,20 @@ config BUILDTIME_EXTABLE_SORT menu "General setup" +config SCHED_BFS + bool "BFS cpu scheduler" + ---help--- + The Brain Fuck CPU Scheduler for excellent interactivity and + responsiveness on the desktop and solid scalability on normal + hardware and commodity servers. Not recommended for 4096 CPUs. + + Currently incompatible with the Group CPU scheduler, and RCU TORTURE + TEST so these options are disabled. + + Say Y here. + default y + + config BROKEN bool @@ -336,7 +350,7 @@ choice # Kind of a stub config for the pure tick based cputime accounting config TICK_CPU_ACCOUNTING bool "Simple tick based cputime accounting" - depends on !S390 && !NO_HZ_FULL + depends on !S390 && !NO_HZ_FULL && !SCHED_BFS help This is the basic tick based cputime accounting that maintains statistics about user, system and idle time spent on per jiffies @@ -361,6 +375,7 @@ config VIRT_CPU_ACCOUNTING_GEN bool "Full dynticks CPU time accounting" depends on HAVE_CONTEXT_TRACKING depends on HAVE_VIRT_CPU_ACCOUNTING_GEN + depends on !SCHED_BFS select VIRT_CPU_ACCOUNTING select CONTEXT_TRACKING help @@ -695,6 +710,7 @@ config RCU_NOCB_CPU bool "Offload RCU callback processing from boot-selected CPUs" depends on TREE_RCU || PREEMPT_RCU depends on RCU_EXPERT || NO_HZ_FULL + depends on !SCHED_BFS default n help Use this option to reduce OS jitter for aggressive HPC or @@ -927,6 +943,7 @@ config NUMA_BALANCING depends on ARCH_SUPPORTS_NUMA_BALANCING depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY depends on SMP && NUMA && MIGRATION + depends on !SCHED_BFS help This option adds support for automatic NUMA aware memory/task placement. The mechanism is quite primitive and is based on migrating memory when @@ -1025,6 +1042,7 @@ config CGROUP_WRITEBACK menuconfig CGROUP_SCHED bool "CPU controller" + depends on !SCHED_BFS default n help This feature lets CPU scheduler recognize task groups and control CPU @@ -1127,6 +1145,7 @@ config CGROUP_DEVICE config CGROUP_CPUACCT bool "Simple CPU accounting controller" + depends on !SCHED_BFS help Provides a simple controller for monitoring the total CPU consumed by the tasks in a cgroup. @@ -1225,6 +1244,7 @@ endif # NAMESPACES config SCHED_AUTOGROUP bool "Automatic process group scheduling" + depends on !SCHED_BFS select CGROUPS select CGROUP_SCHED select FAIR_GROUP_SCHED @@ -1750,38 +1770,8 @@ config COMPAT_BRK On non-ancient distros (post-2000 ones) N is usually a safe choice. -choice - prompt "Choose SLAB allocator" - default SLUB - help - This option allows to select a slab allocator. - -config SLAB - bool "SLAB" - help - The regular slab allocator that is established and known to work - well in all environments. It organizes cache hot objects in - per cpu and per node queues. - config SLUB - bool "SLUB (Unqueued Allocator)" - help - SLUB is a slab allocator that minimizes cache line usage - instead of managing queues of cached objects (SLAB approach). - Per cpu caching is realized using slabs of objects instead - of queues of objects. SLUB can use memory efficiently - and has enhanced diagnostics. SLUB is the default choice for - a slab allocator. - -config SLOB - depends on EXPERT - bool "SLOB (Simple Allocator)" - help - SLOB replaces the stock allocator with a drastically simpler - allocator. SLOB is generally more space efficient but - does not perform as well on large systems. - -endchoice + def_bool y config SLAB_FREELIST_RANDOM default n Index: linux-4.7-bfs/init/main.c =================================================================== --- linux-4.7-bfs.orig/init/main.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/init/main.c 2016-07-29 12:15:37.103601780 +1000 @@ -786,7 +786,6 @@ int __init_or_module do_one_initcall(ini return ret; } - extern initcall_t __initcall_start[]; extern initcall_t __initcall0_start[]; extern initcall_t __initcall1_start[]; @@ -945,6 +944,8 @@ static int __ref kernel_init(void *unuse rcu_end_inkernel_boot(); + print_scheduler_version(); + if (ramdisk_execute_command) { ret = run_init_process(ramdisk_execute_command); if (!ret) Index: linux-4.7-bfs/kernel/delayacct.c =================================================================== --- linux-4.7-bfs.orig/kernel/delayacct.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/kernel/delayacct.c 2016-07-29 12:15:37.103601780 +1000 @@ -104,7 +104,7 @@ int __delayacct_add_tsk(struct taskstats */ t1 = tsk->sched_info.pcount; t2 = tsk->sched_info.run_delay; - t3 = tsk->se.sum_exec_runtime; + t3 = tsk_seruntime(tsk); d->cpu_count += t1; Index: linux-4.7-bfs/kernel/exit.c =================================================================== --- linux-4.7-bfs.orig/kernel/exit.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/kernel/exit.c 2016-07-29 12:15:37.103601780 +1000 @@ -134,7 +134,7 @@ static void __exit_signal(struct task_st sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); - sig->sum_sched_runtime += tsk->se.sum_exec_runtime; + sig->sum_sched_runtime += tsk_seruntime(tsk); sig->nr_threads--; __unhash_process(tsk, group_dead); write_sequnlock(&sig->stats_lock); Index: linux-4.7-bfs/kernel/sysctl.c =================================================================== --- linux-4.7-bfs.orig/kernel/sysctl.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/kernel/sysctl.c 2016-07-29 12:15:37.103601780 +1000 @@ -125,8 +125,13 @@ static int __maybe_unused one = 1; static int __maybe_unused two = 2; static int __maybe_unused four = 4; static unsigned long one_ul = 1; -static int one_hundred = 100; -static int one_thousand = 1000; +static int __read_mostly one_hundred = 100; +static int __read_mostly one_thousand = 1000; +#ifdef CONFIG_SCHED_BFS +extern int rr_interval; +extern int sched_interactive; +extern int sched_iso_cpu; +#endif #ifdef CONFIG_PRINTK static int ten_thousand = 10000; #endif @@ -264,7 +269,7 @@ static struct ctl_table sysctl_base_tabl { } }; -#ifdef CONFIG_SCHED_DEBUG +#if defined(CONFIG_SCHED_DEBUG) && !defined(CONFIG_SCHED_BFS) static int min_sched_granularity_ns = 100000; /* 100 usecs */ static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ static int min_wakeup_granularity_ns; /* 0 usecs */ @@ -281,6 +286,7 @@ static int max_extfrag_threshold = 1000; #endif static struct ctl_table kern_table[] = { +#ifndef CONFIG_SCHED_BFS { .procname = "sched_child_runs_first", .data = &sysctl_sched_child_runs_first, @@ -449,6 +455,7 @@ static struct ctl_table kern_table[] = { .extra1 = &one, }, #endif +#endif /* !CONFIG_SCHED_BFS */ #ifdef CONFIG_PROVE_LOCKING { .procname = "prove_locking", @@ -1006,6 +1013,35 @@ static struct ctl_table kern_table[] = { .proc_handler = proc_dointvec, }, #endif +#ifdef CONFIG_SCHED_BFS + { + .procname = "rr_interval", + .data = &rr_interval, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &one_thousand, + }, + { + .procname = "interactive", + .data = &sched_interactive, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "iso_cpu", + .data = &sched_iso_cpu, + .maxlen = sizeof (int), + .mode = 0644, + .proc_handler = &proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &one_hundred, + }, +#endif #if defined(CONFIG_S390) && defined(CONFIG_SMP) { .procname = "spin_retry", Index: linux-4.7-bfs/lib/Kconfig.debug =================================================================== --- linux-4.7-bfs.orig/lib/Kconfig.debug 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/lib/Kconfig.debug 2016-07-29 12:15:37.104601772 +1000 @@ -1325,7 +1325,7 @@ config RCU_PERF_TEST_RUNNABLE config RCU_TORTURE_TEST tristate "torture tests for RCU" - depends on DEBUG_KERNEL + depends on DEBUG_KERNEL && !SCHED_BFS select TORTURE_TEST select SRCU select TASKS_RCU Index: linux-4.7-bfs/include/linux/jiffies.h =================================================================== --- linux-4.7-bfs.orig/include/linux/jiffies.h 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/include/linux/jiffies.h 2016-07-29 12:15:37.104601772 +1000 @@ -164,7 +164,7 @@ static inline u64 get_jiffies_64(void) * Have the 32 bit jiffies value wrap 5 minutes after boot * so jiffies wrap bugs show up earlier. */ -#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-300*HZ)) +#define INITIAL_JIFFIES ((unsigned long)(unsigned int) (-10*HZ)) /* * Change timeval to jiffies, trying to avoid the Index: linux-4.7-bfs/drivers/cpufreq/cpufreq.c =================================================================== --- linux-4.7-bfs.orig/drivers/cpufreq/cpufreq.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/drivers/cpufreq/cpufreq.c 2016-07-29 12:15:37.104601772 +1000 @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -1930,8 +1931,11 @@ int __cpufreq_driver_target(struct cpufr return -ENODEV; /* Make sure that target_freq is within supported range */ - if (target_freq > policy->max) + if (target_freq >= policy->max) { target_freq = policy->max; + cpu_nonscaling(policy->cpu); + } else + cpu_scaling(policy->cpu); if (target_freq < policy->min) target_freq = policy->min; Index: linux-4.7-bfs/drivers/cpufreq/cpufreq_ondemand.c =================================================================== --- linux-4.7-bfs.orig/drivers/cpufreq/cpufreq_ondemand.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/drivers/cpufreq/cpufreq_ondemand.c 2016-07-29 12:15:37.104601772 +1000 @@ -20,7 +20,7 @@ #include "cpufreq_ondemand.h" /* On-demand governor macros */ -#define DEF_FREQUENCY_UP_THRESHOLD (80) +#define DEF_FREQUENCY_UP_THRESHOLD (63) #define DEF_SAMPLING_DOWN_FACTOR (1) #define MAX_SAMPLING_DOWN_FACTOR (100000) #define MICRO_FREQUENCY_UP_THRESHOLD (95) @@ -134,7 +134,7 @@ static void dbs_freq_increase(struct cpu } /* - * Every sampling_rate, we check, if current idle time is less than 20% + * Every sampling_rate, we check, if current idle time is less than 37% * (default), then we try to increase frequency. Else, we adjust the frequency * proportional to load. */ Index: linux-4.7-bfs/kernel/sched/bfs.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-4.7-bfs/kernel/sched/bfs.c 2016-09-02 14:58:33.514388531 +1000 @@ -0,0 +1,7700 @@ +/* + * kernel/sched/bfs.c, was 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 design 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 + * now Brainfuck deadline scheduling policy by Con Kolivas deletes + * a whole lot of those previous things. + */ + +#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 +#include +#ifdef CONFIG_PARAVIRT +#include +#endif + +#include "cpupri.h" +#include "../workqueue_internal.h" +#include "../smpboot.h" + +#define CREATE_TRACE_POINTS +#include + +#include "bfs_sched.h" + +#define rt_prio(prio) unlikely((prio) < MAX_RT_PRIO) +#define rt_task(p) rt_prio((p)->prio) +#define rt_queue(rq) rt_prio((rq)->rq_prio) +#define batch_task(p) (unlikely((p)->policy == SCHED_BATCH)) +#define is_rt_policy(policy) ((policy) == SCHED_FIFO || \ + (policy) == SCHED_RR) +#define has_rt_policy(p) unlikely(is_rt_policy((p)->policy)) + +#define is_idle_policy(policy) ((policy) == SCHED_IDLEPRIO) +#define idleprio_task(p) unlikely(is_idle_policy((p)->policy)) +#define task_running_idle(p) unlikely((p)->prio == IDLE_PRIO) +#define idle_queue(rq) (unlikely(is_idle_policy((rq)->rq_policy))) + +#define is_iso_policy(policy) ((policy) == SCHED_ISO) +#define iso_task(p) unlikely(is_iso_policy((p)->policy)) +#define iso_queue(rq) unlikely(is_iso_policy((rq)->rq_policy)) +#define task_running_iso(p) unlikely((p)->prio == ISO_PRIO) +#define rq_running_iso(rq) ((rq)->rq_prio == ISO_PRIO) + +#define rq_idle(rq) ((rq)->rq_prio == PRIO_LIMIT) + +#define ISO_PERIOD ((5 * HZ * grq.noc) + 1) + +#define SCHED_PRIO(p) ((p) + MAX_RT_PRIO) +#define STOP_PRIO (MAX_RT_PRIO - 1) + +/* + * Some helpers for converting to/from various scales. Use shifts to get + * approximate multiples of ten for less overhead. + */ +#define JIFFIES_TO_NS(TIME) ((TIME) * (1000000000 / HZ)) +#define JIFFY_NS (1000000000 / HZ) +#define HALF_JIFFY_NS (1000000000 / HZ / 2) +#define HALF_JIFFY_US (1000000 / HZ / 2) +#define MS_TO_NS(TIME) ((TIME) << 20) +#define MS_TO_US(TIME) ((TIME) << 10) +#define NS_TO_MS(TIME) ((TIME) >> 20) +#define NS_TO_US(TIME) ((TIME) >> 10) + +#define RESCHED_US (100) /* Reschedule if less than this many μs left */ + +void print_scheduler_version(void) +{ + printk(KERN_INFO "BFS CPU scheduler v0.480 by Con Kolivas.\n"); +} + +/* + * This is the time all tasks within the same priority round robin. + * Value is in ms and set to a minimum of 6ms. Scales with number of cpus. + * Tunable via /proc interface. + */ +int rr_interval __read_mostly = 6; + +/* Tunable to choose whether to prioritise latency or throughput, simple + * binary yes or no */ + +int sched_interactive __read_mostly = 1; + +/* + * sched_iso_cpu - sysctl which determines the cpu percentage SCHED_ISO tasks + * are allowed to run five seconds as real time tasks. This is the total over + * all online cpus. + */ +int sched_iso_cpu __read_mostly = 70; + +/* + * The relative length of deadline for each priority(nice) level. + */ +static int prio_ratios[NICE_WIDTH] __read_mostly; + +/* + * The quota handed out to tasks of all priority levels when refilling their + * time_slice. + */ +static inline int timeslice(void) +{ + return MS_TO_US(rr_interval); +} + +/* + * The global runqueue data that all CPUs work off. Data is protected either + * by the global grq lock, or the discrete lock that precedes the data in this + * struct. + */ +struct global_rq { + raw_spinlock_t lock; + unsigned long nr_running; + unsigned long nr_uninterruptible; + unsigned long long nr_switches; + unsigned long qnr; /* queued not running */ +#ifdef CONFIG_SMP + cpumask_t cpu_idle_map; + bool idle_cpus; +#endif + int noc; /* num_online_cpus stored and updated when it changes */ + u64 niffies; /* Nanosecond jiffies */ + unsigned long last_jiffy; /* Last jiffy we updated niffies */ + + raw_spinlock_t iso_lock; + int iso_ticks; + bool iso_refractory; + + skiplist_node *node; + skiplist *sl; +}; + +#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; + atomic_t rto_count; + struct rcu_head rcu; + cpumask_var_t span; + cpumask_var_t online; + + /* + * The "RT overload" flag: it gets set if a CPU has more than + * one runnable RT task. + */ + cpumask_var_t rto_mask; + struct cpupri cpupri; +}; + +/* + * 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 /* CONFIG_SMP */ + +/* There can be only one */ +static struct global_rq grq; + +static DEFINE_MUTEX(sched_hotcpu_mutex); + +/* cpus with isolated domains */ +cpumask_var_t cpu_isolated_map; + +DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +#ifdef CONFIG_SMP +struct rq *cpu_rq(int cpu) +{ + return &per_cpu(runqueues, (cpu)); +} +#define task_rq(p) cpu_rq(task_cpu(p)) +#define cpu_curr(cpu) (cpu_rq(cpu)->curr) +/* + * sched_domains_mutex serialises calls to init_sched_domains, + * detach_destroy_domains and partition_sched_domains. + */ +DEFINE_MUTEX(sched_domains_mutex); + +/* + * 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; + +int __weak arch_sd_sibling_asym_packing(void) +{ + return 0*SD_ASYM_PACKING; +} +#else +struct rq *uprq; +#endif /* CONFIG_SMP */ + +static inline void update_rq_clock(struct rq *rq); + +/* + * Sanity check should sched_clock return bogus values. We make sure it does + * not appear to go backwards, and use jiffies to determine the maximum and + * minimum it could possibly have increased, and round down to the nearest + * jiffy when it falls outside this. + */ +static inline void niffy_diff(s64 *niff_diff, int jiff_diff) +{ + unsigned long min_diff, max_diff; + + if (jiff_diff > 1) + min_diff = JIFFIES_TO_NS(jiff_diff - 1); + else + min_diff = 1; + /* Round up to the nearest tick for maximum */ + max_diff = JIFFIES_TO_NS(jiff_diff + 1); + + if (unlikely(*niff_diff < min_diff || *niff_diff > max_diff)) + *niff_diff = min_diff; +} + +#ifdef CONFIG_SMP +static inline int cpu_of(struct rq *rq) +{ + return rq->cpu; +} + +/* + * Niffies are a globally increasing nanosecond counter. Whenever a runqueue + * clock is updated with the grq.lock held, it is an opportunity to update the + * niffies value. Any CPU can update it by adding how much its clock has + * increased since it last updated niffies, minus any added niffies by other + * CPUs. + */ +static inline void update_clocks(struct rq *rq) +{ + s64 ndiff; + long jdiff; + + update_rq_clock(rq); + ndiff = rq->clock - rq->old_clock; + /* old_clock is only updated when we are updating niffies */ + rq->old_clock = rq->clock; + ndiff -= grq.niffies - rq->last_niffy; + jdiff = jiffies - grq.last_jiffy; + niffy_diff(&ndiff, jdiff); + grq.last_jiffy += jdiff; + grq.niffies += ndiff; + rq->last_niffy = grq.niffies; +} +#else /* CONFIG_SMP */ +static inline int cpu_of(struct rq *rq) +{ + return 0; +} + +static inline void update_clocks(struct rq *rq) +{ + s64 ndiff; + long jdiff; + + update_rq_clock(rq); + ndiff = rq->clock - rq->old_clock; + rq->old_clock = rq->clock; + jdiff = jiffies - grq.last_jiffy; + niffy_diff(&ndiff, jdiff); + grq.last_jiffy += jdiff; + grq.niffies += ndiff; +} +#endif + +#include "stats.h" + +#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 +#ifndef finish_arch_post_lock_switch +# define finish_arch_post_lock_switch() do { } while (0) +#endif + +/* + * All common locking functions performed on grq.lock. rq->clock is local to + * the CPU accessing it so it can be modified just with interrupts disabled + * when we're not updating niffies. + * Looking up task_rq must be done under grq.lock to be safe. + */ +static void update_rq_clock_task(struct rq *rq, s64 delta); + +static inline void update_rq_clock(struct rq *rq) +{ + s64 delta = sched_clock_cpu(cpu_of(rq)) - rq->clock; + + if (unlikely(delta < 0)) + return; + rq->clock += delta; + update_rq_clock_task(rq, delta); +} + +static inline bool task_running(struct task_struct *p) +{ + return p->on_cpu; +} + +static inline void grq_lock(void) + __acquires(grq.lock) +{ + raw_spin_lock(&grq.lock); +} + +static inline void grq_unlock(void) + __releases(grq.lock) +{ + raw_spin_unlock(&grq.lock); +} + +static inline void grq_lock_irq(void) + __acquires(grq.lock) +{ + raw_spin_lock_irq(&grq.lock); +} + +static inline void time_lock_grq(struct rq *rq) + __acquires(grq.lock) +{ + grq_lock(); + update_clocks(rq); +} + +static inline void grq_unlock_irq(void) + __releases(grq.lock) +{ + raw_spin_unlock_irq(&grq.lock); +} + +static inline void grq_lock_irqsave(unsigned long *flags) + __acquires(grq.lock) +{ + raw_spin_lock_irqsave(&grq.lock, *flags); +} + +static inline void grq_unlock_irqrestore(unsigned long *flags) + __releases(grq.lock) +{ + raw_spin_unlock_irqrestore(&grq.lock, *flags); +} + +static inline struct rq +*task_grq_lock(struct task_struct *p, unsigned long *flags) + __acquires(grq.lock) +{ + grq_lock_irqsave(flags); + return task_rq(p); +} + +static inline struct rq +*time_task_grq_lock(struct task_struct *p, unsigned long *flags) + __acquires(grq.lock) +{ + struct rq *rq = task_grq_lock(p, flags); + update_clocks(rq); + return rq; +} + +static inline struct rq *task_grq_lock_irq(struct task_struct *p) + __acquires(grq.lock) +{ + grq_lock_irq(); + return task_rq(p); +} + +static inline void time_task_grq_lock_irq(struct task_struct *p) + __acquires(grq.lock) +{ + struct rq *rq = task_grq_lock_irq(p); + update_clocks(rq); +} + +static inline void task_grq_unlock_irq(void) + __releases(grq.lock) +{ + grq_unlock_irq(); +} + +static inline void task_grq_unlock(unsigned long *flags) + __releases(grq.lock) +{ + grq_unlock_irqrestore(flags); +} + +/** + * grunqueue_is_locked + * + * Returns true if the global 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. + */ +bool grunqueue_is_locked(void) +{ + return raw_spin_is_locked(&grq.lock); +} + +void grq_unlock_wait(void) + __releases(grq.lock) +{ + smp_mb(); /* spin-unlock-wait is not a full memory barrier */ + raw_spin_unlock_wait(&grq.lock); +} + +static inline void time_grq_lock(struct rq *rq, unsigned long *flags) + __acquires(grq.lock) +{ + local_irq_save(*flags); + time_lock_grq(rq); +} + +static inline struct rq *__task_grq_lock(struct task_struct *p) + __acquires(grq.lock) +{ + grq_lock(); + return task_rq(p); +} + +static inline void __task_grq_unlock(void) + __releases(grq.lock) +{ + grq_unlock(); +} + +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 */ + grq.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(&grq.lock.dep_map, 0, 0, _THIS_IP_); + + grq_unlock_irq(); +} + +static inline bool deadline_before(u64 deadline, u64 time) +{ + return (deadline < time); +} + +static inline bool deadline_after(u64 deadline, u64 time) +{ + return (deadline > time); +} + +/* + * A task that is not running or queued will not have a node set. + * A task that is queued but not running will have a node set. + * A task that is currently running will have ->on_cpu set but no node set. + */ +static inline bool task_queued(struct task_struct *p) +{ + return p->node; +} + +/* + * Removing from the global runqueue. Enter with grq locked. Deleting a task + * from the skip list is done via the stored node reference in the task struct + * and does not require a full look up. Thus it occurs in O(k) time where k + * is the "level" of the list the task was stored at - usually < 4, max 16. + */ +static void dequeue_task(struct task_struct *p) +{ + skiplist_delnode(grq.node, grq.sl, p->node); + p->node = NULL; + sched_info_dequeued(task_rq(p), p); +} + +/* + * To determine if it's safe for a task of SCHED_IDLEPRIO to actually run as + * an idle task, we ensure none of the following conditions are met. + */ +static bool idleprio_suitable(struct task_struct *p) +{ + return (!freezing(p) && !signal_pending(p) && + !(task_contributes_to_load(p)) && !(p->flags & (PF_EXITING))); +} + +/* + * To determine if a task of SCHED_ISO can run in pseudo-realtime, we check + * that the iso_refractory flag is not set. + */ +static bool isoprio_suitable(void) +{ + return !grq.iso_refractory; +} + +/* + * Adding to the global runqueue. Enter with grq locked. + */ +static void enqueue_task(struct task_struct *p, struct rq *rq) +{ + u64 sl_id; + + if (!rt_task(p)) { + /* Check it hasn't gotten rt from PI */ + if ((idleprio_task(p) && idleprio_suitable(p)) || + (iso_task(p) && isoprio_suitable())) + p->prio = p->normal_prio; + else + p->prio = NORMAL_PRIO; + } + /* + * The sl_id key passed to the skiplist generates a sorted list. + * Realtime and sched iso tasks run FIFO so they only need be sorted + * according to priority. The skiplist will put tasks of the same + * key inserted later in FIFO order. Tasks of sched normal, batch + * and idleprio are sorted according to their deadlines. Idleprio + * tasks are offset by an impossibly large deadline value ensuring + * they get sorted into last positions, but still according to their + * own deadlines. This creates a "landscape" of skiplists running + * from priority 0 realtime in first place to the lowest priority + * idleprio tasks last. Skiplist insertion is an O(log n) process. + */ + if (p->prio <= ISO_PRIO) + sl_id = p->prio; + else { + sl_id = p->deadline; + if (p->prio == IDLE_PRIO) + sl_id |= 0xF000000000000000; + } + p->node = skiplist_insert(grq.node, grq.sl, sl_id, p, grq.niffies); + sched_info_queued(rq, p); +} + +static inline void requeue_task(struct task_struct *p) +{ + sched_info_queued(task_rq(p), p); +} + +/* + * Returns the relative length of deadline all compared to the shortest + * deadline which is that of nice -20. + */ +static inline int task_prio_ratio(struct task_struct *p) +{ + return prio_ratios[TASK_USER_PRIO(p)]; +} + +/* + * task_timeslice - all tasks of all priorities get the exact same timeslice + * length. CPU distribution is handled by giving different deadlines to + * tasks of different priorities. Use 128 as the base value for fast shifts. + */ +static inline int task_timeslice(struct task_struct *p) +{ + return (rr_interval * task_prio_ratio(p) / 128); +} + +static void resched_task(struct task_struct *p); + +static inline void resched_curr(struct rq *rq) +{ + resched_task(rq->curr); +} + +/* + * qnr is the "queued but not running" count which is the total number of + * tasks on the global runqueue list waiting for cpu time but not actually + * currently running on a cpu. + */ +static inline void inc_qnr(void) +{ + grq.qnr++; +} + +static inline void dec_qnr(void) +{ + grq.qnr--; +} + +static inline int queued_notrunning(void) +{ + return grq.qnr; +} + +#ifdef CONFIG_SMP +/* + * The cpu_idle_map stores a bitmap of all the CPUs currently idle to + * allow easy lookup of whether any suitable idle CPUs are available. + * It's cheaper to maintain a binary yes/no if there are any idle CPUs on the + * idle_cpus variable than to do a full bitmask check when we are busy. + */ +static inline void set_cpuidle_map(int cpu) +{ + if (likely(cpu_online(cpu))) { + cpumask_set_cpu(cpu, &grq.cpu_idle_map); + grq.idle_cpus = true; + } +} + +static inline void clear_cpuidle_map(int cpu) +{ + cpumask_clear_cpu(cpu, &grq.cpu_idle_map); + if (cpumask_empty(&grq.cpu_idle_map)) + grq.idle_cpus = false; +} + +static bool suitable_idle_cpus(struct task_struct *p) +{ + if (!grq.idle_cpus) + return false; + return (cpumask_intersects(&p->cpus_allowed, &grq.cpu_idle_map)); +} + +#define CPUIDLE_DIFF_THREAD (1) +#define CPUIDLE_DIFF_CORE (2) +#define CPUIDLE_CACHE_BUSY (4) +#define CPUIDLE_DIFF_CPU (8) +#define CPUIDLE_THREAD_BUSY (16) +#define CPUIDLE_THROTTLED (32) +#define CPUIDLE_DIFF_NODE (64) + +static inline bool scaling_rq(struct rq *rq); + +/* + * The best idle CPU is chosen according to the CPUIDLE ranking above where the + * lowest value would give the most suitable CPU to schedule p onto next. The + * order works out to be the following: + * + * Same thread, idle or busy cache, idle or busy threads + * Other core, same cache, idle or busy cache, idle threads. + * Same node, other CPU, idle cache, idle threads. + * Same node, other CPU, busy cache, idle threads. + * Other core, same cache, busy threads. + * Same node, other CPU, busy threads. + * Other node, other CPU, idle cache, idle threads. + * Other node, other CPU, busy cache, idle threads. + * Other node, other CPU, busy threads. + */ +static int best_mask_cpu(int best_cpu, struct rq *rq, cpumask_t *tmpmask) +{ + int best_ranking = CPUIDLE_DIFF_NODE | CPUIDLE_THROTTLED | + CPUIDLE_THREAD_BUSY | CPUIDLE_DIFF_CPU | CPUIDLE_CACHE_BUSY | + CPUIDLE_DIFF_CORE | CPUIDLE_DIFF_THREAD; + int cpu_tmp; + + if (cpumask_test_cpu(best_cpu, tmpmask)) + goto out; + + for_each_cpu(cpu_tmp, tmpmask) { + int ranking, locality; + struct rq *tmp_rq; + + ranking = 0; + tmp_rq = cpu_rq(cpu_tmp); + + locality = rq->cpu_locality[cpu_tmp]; +#ifdef CONFIG_NUMA + if (locality > 3) + ranking |= CPUIDLE_DIFF_NODE; + else +#endif + if (locality > 2) + ranking |= CPUIDLE_DIFF_CPU; +#ifdef CONFIG_SCHED_MC + else if (locality == 2) + ranking |= CPUIDLE_DIFF_CORE; + else if (!(tmp_rq->cache_idle(tmp_rq))) + ranking |= CPUIDLE_CACHE_BUSY; +#endif +#ifdef CONFIG_SCHED_SMT + if (locality == 1) + ranking |= CPUIDLE_DIFF_THREAD; + else if (!(tmp_rq->siblings_idle(tmp_rq))) + ranking |= CPUIDLE_THREAD_BUSY; +#endif + if (scaling_rq(tmp_rq)) + ranking |= CPUIDLE_THROTTLED; + + if (ranking < best_ranking) { + best_cpu = cpu_tmp; + best_ranking = ranking; + } + } +out: + return best_cpu; +} + +static void resched_best_mask(int best_cpu, struct rq *rq, cpumask_t *tmpmask) +{ + best_cpu = best_mask_cpu(best_cpu, rq, tmpmask); + resched_curr(cpu_rq(best_cpu)); +} + +bool cpus_share_cache(int this_cpu, int that_cpu) +{ + struct rq *this_rq = cpu_rq(this_cpu); + + return (this_rq->cpu_locality[that_cpu] < 3); +} + +#ifdef CONFIG_SMT_NICE +static const cpumask_t *thread_cpumask(int cpu); + +/* Find the best real time priority running on any SMT siblings of cpu and if + * none are running, the static priority of the best deadline task running. + * The lookups to the other runqueues is done lockless as the occasional wrong + * value would be harmless. */ +static int best_smt_bias(struct rq *this_rq) +{ + int other_cpu, best_bias = 0; + + for_each_cpu(other_cpu, &this_rq->thread_mask) { + struct rq *rq = cpu_rq(other_cpu); + + if (rq_idle(rq)) + continue; + if (!rq->online) + continue; + if (!rq->rq_mm) + continue; + if (likely(rq->rq_smt_bias > best_bias)) + best_bias = rq->rq_smt_bias; + } + return best_bias; +} + +static int task_prio_bias(struct task_struct *p) +{ + if (rt_task(p)) + return 1 << 30; + else if (task_running_iso(p)) + return 1 << 29; + else if (task_running_idle(p)) + return 0; + return MAX_PRIO - p->static_prio; +} + +static bool smt_always_schedule(struct task_struct __maybe_unused *p, struct rq __maybe_unused *this_rq) +{ + return true; +} + +static bool (*smt_schedule)(struct task_struct *p, struct rq *this_rq) = &smt_always_schedule; + +/* We've already decided p can run on CPU, now test if it shouldn't for SMT + * nice reasons. */ +static bool smt_should_schedule(struct task_struct *p, struct rq *this_rq) +{ + int best_bias, task_bias; + + /* Kernel threads always run */ + if (unlikely(!p->mm)) + return true; + if (rt_task(p)) + return true; + if (!idleprio_suitable(p)) + return true; + best_bias = best_smt_bias(this_rq); + /* The smt siblings are all idle or running IDLEPRIO */ + if (best_bias < 1) + return true; + task_bias = task_prio_bias(p); + if (task_bias < 1) + return false; + if (task_bias >= best_bias) + return true; + /* Dither 25% cpu of normal tasks regardless of nice difference */ + if (best_bias % 4 == 1) + return true; + /* Sorry, you lose */ + return false; +} +#else +#define smt_schedule(p, this_rq) (true) +#endif + +static bool resched_best_idle(struct task_struct *p) +{ + cpumask_t tmpmask; + struct rq *rq; + int best_cpu; + + cpumask_and(&tmpmask, &p->cpus_allowed, &grq.cpu_idle_map); + best_cpu = best_mask_cpu(task_cpu(p), task_rq(p), &tmpmask); + rq = cpu_rq(best_cpu); + if (!smt_schedule(p, rq)) + return false; + resched_curr(rq); + return true; +} + +static inline void resched_suitable_idle(struct task_struct *p) +{ + if (suitable_idle_cpus(p)) + resched_best_idle(p); +} +/* + * Flags to tell us whether this CPU is running a CPU frequency governor that + * has slowed its speed or not. No locking required as the very rare wrongly + * read value would be harmless. + */ +void cpu_scaling(int cpu) +{ + cpu_rq(cpu)->scaling = true; +} + +void cpu_nonscaling(int cpu) +{ + cpu_rq(cpu)->scaling = false; +} + +static inline bool scaling_rq(struct rq *rq) +{ + return rq->scaling; +} + +static inline int locality_diff(int cpu, struct rq *rq) +{ + return rq->cpu_locality[cpu]; +} +#else /* CONFIG_SMP */ +static inline void set_cpuidle_map(int cpu) +{ +} + +static inline void clear_cpuidle_map(int cpu) +{ +} + +static inline bool suitable_idle_cpus(struct task_struct *p) +{ + return uprq->curr == uprq->idle; +} + +static inline void resched_suitable_idle(struct task_struct *p) +{ +} + +void cpu_scaling(int __unused) +{ +} + +void cpu_nonscaling(int __unused) +{ +} + +/* + * Although CPUs can scale in UP, there is nowhere else for tasks to go so this + * always returns 0. + */ +static inline bool scaling_rq(struct rq *rq) +{ + return false; +} + +static inline int locality_diff(int cpu, struct rq *rq) +{ + return 0; +} +#endif /* CONFIG_SMP */ +EXPORT_SYMBOL_GPL(cpu_scaling); +EXPORT_SYMBOL_GPL(cpu_nonscaling); + +static inline int normal_prio(struct task_struct *p) +{ + if (has_rt_policy(p)) + return MAX_RT_PRIO - 1 - p->rt_priority; + if (idleprio_task(p)) + return IDLE_PRIO; + if (iso_task(p)) + return ISO_PRIO; + return NORMAL_PRIO; +} + +/* + * Calculate the current priority, i.e. the priority + * taken into account by the scheduler. This value might + * be boosted by RT tasks as it 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. Enter with grq locked. + */ +static void activate_task(struct task_struct *p, struct rq *rq) +{ + update_clocks(rq); + + /* + * Sleep time is in units of nanosecs, so shift by 20 to get a + * milliseconds-range estimation of the amount of time that the task + * spent sleeping: + */ + if (unlikely(prof_on == SLEEP_PROFILING)) { + if (p->state == TASK_UNINTERRUPTIBLE) + profile_hits(SLEEP_PROFILING, (void *)get_wchan(p), + (rq->clock_task - p->last_ran) >> 20); + } + + p->prio = effective_prio(p); + if (task_contributes_to_load(p)) + grq.nr_uninterruptible--; + enqueue_task(p, rq); + rq->soft_affined++; + p->on_rq = 1; + grq.nr_running++; + inc_qnr(); + cpufreq_trigger(grq.niffies, rq->soft_affined); +} + +static inline void clear_sticky(struct task_struct *p); + +/* + * deactivate_task - If it's running, it's not on the grq and we can just + * decrement the nr_running. Enter with grq locked. + */ +static inline void deactivate_task(struct task_struct *p, struct rq *rq) +{ + if (task_contributes_to_load(p)) + grq.nr_uninterruptible++; + rq->soft_affined--; + p->on_rq = 0; + grq.nr_running--; + clear_sticky(p); + cpufreq_trigger(grq.niffies, rq->soft_affined); +} + +#ifdef CONFIG_SMP +void set_task_cpu(struct task_struct *p, unsigned int cpu) +{ + unsigned int tcpu; +#ifdef CONFIG_LOCKDEP + /* + * The caller should hold grq lock. + */ + WARN_ON_ONCE(debug_locks && !lockdep_is_held(&grq.lock)); +#endif + if ((tcpu = task_cpu(p)) == cpu) + return; + trace_sched_migrate_task(p, cpu); + perf_event_task_migrate(p); + + /* + * After ->cpu is set up to a new value, task_grq_lock(p, ...) can be + * successfully executed on another CPU. We must ensure that updates of + * per-task data have been completed by this moment. + */ + smp_wmb(); + if (p->on_rq) { + /* + * set_task_cpu can be set on other CPUs so call cpufreq_trigger + * explicitly telling it what CPU is being updated as the value + * of soft_affined has changed. + */ + other_cpufreq_trigger(tcpu, grq.niffies, --task_rq(p)->soft_affined); + other_cpufreq_trigger(cpu, grq.niffies, ++cpu_rq(cpu)->soft_affined); + } + task_thread_info(p)->cpu = cpu; +} + +static inline void clear_sticky(struct task_struct *p) +{ + p->sticky = false; +} + +static inline bool task_sticky(struct task_struct *p) +{ + return p->sticky; +} + +/* Reschedule the best idle CPU that is not this one. */ +static void +resched_closest_idle(struct rq *rq, int cpu, struct task_struct *p) +{ + cpumask_t tmpmask; + + cpumask_and(&tmpmask, &p->cpus_allowed, &grq.cpu_idle_map); + cpumask_clear_cpu(cpu, &tmpmask); + if (cpumask_empty(&tmpmask)) + return; + resched_best_mask(cpu, rq, &tmpmask); +} + +/* + * We set the sticky flag on a task that is descheduled involuntarily meaning + * it is awaiting further CPU time. If the last sticky task is still sticky + * but unlucky enough to not be the next task scheduled, we unstick it and try + * to find it an idle CPU. Realtime tasks do not stick to minimise their + * latency at all times. + */ +static inline void +swap_sticky(struct rq *rq, int cpu, struct task_struct *p) +{ + if (rq->sticky_task) { + if (rq->sticky_task == p) { + p->sticky = true; + return; + } + if (task_sticky(rq->sticky_task)) { + clear_sticky(rq->sticky_task); + resched_closest_idle(rq, cpu, rq->sticky_task); + } + } + if (!rt_task(p)) { + p->sticky = true; + rq->sticky_task = p; + } else { + resched_closest_idle(rq, cpu, p); + rq->sticky_task = NULL; + } +} + +static inline void unstick_task(struct rq *rq, struct task_struct *p) +{ + rq->sticky_task = NULL; + clear_sticky(p); +} +#else +static inline void clear_sticky(struct task_struct *p) +{ +} + +static inline bool task_sticky(struct task_struct *p) +{ + return false; +} + +static inline void +swap_sticky(struct rq *rq, int cpu, struct task_struct *p) +{ +} + +static inline void unstick_task(struct rq *rq, struct task_struct *p) +{ +} +#endif + +/* + * Move a task off the global queue and take it to a cpu for it will + * become the running task. + */ +static inline void take_task(int cpu, struct task_struct *p) +{ + set_task_cpu(p, cpu); + dequeue_task(p); + clear_sticky(p); + dec_qnr(); +} + +/* + * Returns a descheduling task to the grq runqueue unless it is being + * deactivated. + */ +static inline void return_task(struct task_struct *p, struct rq *rq, bool deactivate) +{ + if (deactivate) + deactivate_task(p, rq); + else { + inc_qnr(); + enqueue_task(p, rq); + } +} + +/* Enter with grq lock held. We know p is on the local cpu */ +static inline void __set_tsk_resched(struct task_struct *p) +{ + set_tsk_need_resched(p); + set_preempt_need_resched(); +} + +/* + * 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. + */ +void resched_task(struct task_struct *p) +{ + int cpu; + + lockdep_assert_held(&grq.lock); + + if (test_tsk_need_resched(p)) + return; + + set_tsk_need_resched(p); + + cpu = task_cpu(p); + if (cpu == smp_processor_id()) { + set_preempt_need_resched(); + return; + } + + smp_send_reschedule(cpu); +} + +/** + * task_curr - is this task currently executing on a CPU? + * @p: the task in question. + * + * Return: 1 if the task is currently executing. 0 otherwise. + */ +inline int task_curr(const struct task_struct *p) +{ + return cpu_curr(task_cpu(p)) == p; +} + +#ifdef CONFIG_SMP +/* + * 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; + bool running, on_rq; + unsigned long ncsw; + struct rq *rq; + + for (;;) { + 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 this will return false + * if the runqueue has changed and p is actually now + * running somewhere else! + */ + while (task_running(p) && p == rq->curr) { + if (match_state && unlikely(p->state != match_state)) + return 0; + cpu_relax(); + } + + /* + * Ok, time to look more closely! We need the grq + * lock now, to be *sure*. If we're wrong, we'll + * just go back and repeat. + */ + rq = task_grq_lock(p, &flags); + trace_sched_wait_task(p); + running = task_running(p); + on_rq = p->on_rq; + ncsw = 0; + if (!match_state || p->state == match_state) + ncsw = p->nvcsw | LONG_MIN; /* sets MSB */ + task_grq_unlock(&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 was 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)) { + ktime_t to = ktime_set(0, NSEC_PER_SEC / HZ); + + set_current_state(TASK_UNINTERRUPTIBLE); + schedule_hrtimeout(&to, HRTIMER_MODE_REL); + 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 doesn't 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(); +} +EXPORT_SYMBOL_GPL(kick_process); +#endif + +/* + * RT tasks preempt purely on priority. SCHED_NORMAL tasks preempt on the + * basis of earlier deadlines. SCHED_IDLEPRIO don't preempt anything else or + * between themselves, they cooperatively multitask. An idle rq scores as + * prio PRIO_LIMIT so it is always preempted. + */ +static inline bool +can_preempt(struct task_struct *p, int prio, u64 deadline) +{ + /* Better static priority RT task or better policy preemption */ + if (p->prio < prio) + return true; + if (p->prio > prio) + return false; + /* SCHED_NORMAL, BATCH and ISO will preempt based on deadline */ + if (!deadline_before(p->deadline, deadline)) + return false; + return true; +} + +#ifdef CONFIG_SMP +#define cpu_online_map (*(cpumask_t *)cpu_online_mask) +#ifdef CONFIG_HOTPLUG_CPU +/* + * Check to see if there is a task that is affined only to offline CPUs but + * still wants runtime. This happens to kernel threads during suspend/halt and + * disabling of CPUs. + */ +static inline bool online_cpus(struct task_struct *p) +{ + return (likely(cpumask_intersects(&cpu_online_map, &p->cpus_allowed))); +} +#else /* CONFIG_HOTPLUG_CPU */ +/* All available CPUs are always online without hotplug. */ +static inline bool online_cpus(struct task_struct *p) +{ + return true; +} +#endif + +/* + * Check to see if p can run on cpu, and if not, whether there are any online + * CPUs it can run on instead. + */ +static inline bool needs_other_cpu(struct task_struct *p, int cpu) +{ + if (unlikely(!cpumask_test_cpu(cpu, &p->cpus_allowed))) + return true; + return false; +} + +static void try_preempt(struct task_struct *p, struct rq *this_rq) +{ + int cpu, pcpu, highest_prio, highest_cpu; + struct rq *highest_prio_rq = NULL; + u64 latest_deadline; + cpumask_t tmp; + + /* + * We clear the sticky flag here because for a task to have called + * try_preempt with the sticky flag enabled means some complicated + * re-scheduling has occurred and we should ignore the sticky flag. + */ + clear_sticky(p); + + if (suitable_idle_cpus(p) && resched_best_idle(p)) + return; + + /* IDLEPRIO tasks never preempt anything but idle */ + if (p->policy == SCHED_IDLEPRIO) + return; + + if (likely(online_cpus(p))) + cpumask_and(&tmp, &cpu_online_map, &p->cpus_allowed); + else + return; + + /* See if this task can preempt the task on the current CPU first. */ + pcpu = cpu_of(this_rq); + if (!sched_interactive && cpumask_test_cpu(pcpu, &tmp)) { + if (smt_schedule(p, this_rq) && can_preempt(p, this_rq->rq_prio, this_rq->rq_deadline)) { + resched_curr(this_rq); + return; + } + cpumask_clear_cpu(pcpu, &tmp); + } + + highest_prio = latest_deadline = 0; + + /* Now look for the CPU with the latest deadline */ + for_each_cpu(cpu, &tmp) { + struct rq *rq; + int rq_prio; + u64 dl; + + rq = cpu_rq(cpu); + rq_prio = rq->rq_prio; + if (rq_prio < highest_prio) + continue; + + dl = rq->rq_deadline; + if (!sched_interactive && pcpu != cpu) + dl <<= locality_diff(pcpu, rq); + if (rq_prio > highest_prio || + deadline_after(dl, latest_deadline)) { + latest_deadline = dl; + highest_prio = rq_prio; + highest_cpu = cpu; + highest_prio_rq = rq; + } + } + + if (unlikely(!highest_prio_rq)) + return; + if (!smt_schedule(p, highest_prio_rq)) + return; + if (can_preempt(p, highest_prio, latest_deadline)) { + /* + * If we have decided this task should preempt this CPU, + * set the task's CPU to match so there is no discrepancy + * in earliest_deadline_task which biases away tasks with + * a different CPU set. This means waking tasks are + * treated differently to rescheduling tasks in + * interactive mode. + */ + set_task_cpu(p, highest_cpu); + resched_curr(highest_prio_rq); + } +} +static int __set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask, bool check); +#else /* CONFIG_SMP */ +static inline bool needs_other_cpu(struct task_struct *p, int cpu) +{ + return false; +} + +static void try_preempt(struct task_struct *p, struct rq *this_rq) +{ + if (p->policy == SCHED_IDLEPRIO) + return; + if (can_preempt(p, uprq->rq_prio, uprq->rq_deadline)) + resched_curr(uprq); +} + +static inline int __set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask, bool check) +{ + return set_cpus_allowed_ptr(p, new_mask); +} +#endif /* CONFIG_SMP */ + +static void +ttwu_stat(struct task_struct *p, int cpu, int wake_flags) +{ +#ifdef CONFIG_SCHEDSTATS + struct rq *rq = this_rq(); + +#ifdef CONFIG_SMP + int this_cpu = smp_processor_id(); + + if (cpu == this_cpu) + schedstat_inc(rq, ttwu_local); + else { + struct sched_domain *sd; + + rcu_read_lock(); + for_each_domain(this_cpu, sd) { + if (cpumask_test_cpu(cpu, sched_domain_span(sd))) { + schedstat_inc(sd, ttwu_wake_remote); + break; + } + } + rcu_read_unlock(); + } + +#endif /* CONFIG_SMP */ + + schedstat_inc(rq, ttwu_count); +#endif /* CONFIG_SCHEDSTATS */ +} + +void wake_up_if_idle(int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + rcu_read_lock(); + + if (!is_idle_task(rcu_dereference(rq->curr))) + goto out; + + grq_lock_irqsave(&flags); + if (likely(is_idle_task(rq->curr))) + smp_send_reschedule(cpu); + /* Else cpu is not in idle, do nothing here */ + grq_unlock_irqrestore(&flags); + +out: + rcu_read_unlock(); +} + +#ifdef CONFIG_SMP +void scheduler_ipi(void) +{ + /* + * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting + * TIF_NEED_RESCHED remotely (for the first time) will also send + * this IPI. + */ + preempt_fold_need_resched(); +} +#endif + +static inline void ttwu_activate(struct task_struct *p, struct rq *rq, + bool is_sync) +{ + activate_task(p, rq); + + /* + * Sync wakeups (i.e. those types of wakeups where the waker + * has indicated that it will leave the CPU in short order) + * don't trigger a preemption if there are no idle cpus, + * instead waiting for current to deschedule. + */ + if (!is_sync || suitable_idle_cpus(p)) + try_preempt(p, rq); +} + +static inline void ttwu_post_activation(struct task_struct *p, struct rq *rq, + bool success) +{ + trace_sched_wakeup(p); + p->state = TASK_RUNNING; + + /* + * if a worker is waking up, notify workqueue. Note that on BFS, we + * don't really know what cpu it will be, so we fake it for + * wq_worker_waking_up :/ + */ + if ((p->flags & PF_WQ_WORKER) && success) + wq_worker_waking_up(p, cpu_of(rq)); +} + +/* + * wake flags + */ +#define WF_SYNC 0x01 /* waker goes to sleep after wakeup */ +#define WF_FORK 0x02 /* child wakeup after fork */ +#define WF_MIGRATED 0x4 /* internal use, task got migrated */ + +/*** + * try_to_wake_up - wake up a thread + * @p: the thread to be awakened + * @state: the mask of task states that can be woken + * @wake_flags: wake modifier flags (WF_*) + * + * 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. + * + * Return: %true if @p was woken up, %false if it was already running. + * or @state didn't match @p's state. + */ +static bool try_to_wake_up(struct task_struct *p, unsigned int state, + int wake_flags) +{ + bool success = false; + unsigned long flags; + struct rq *rq; + int cpu; + + get_cpu(); + + /* + * If we are going to wake up a thread waiting for CONDITION we + * need to ensure that CONDITION=1 done by the caller can not be + * reordered with p->state check below. This pairs with mb() in + * set_current_state() the waiting thread does. + */ + smp_mb__before_spinlock(); + + /* + * No need to do time_lock_grq as we only need to update the rq clock + * if we activate the task + */ + rq = task_grq_lock(p, &flags); + cpu = task_cpu(p); + + /* state is a volatile long, どうして、分からない */ + if (!((unsigned int)p->state & state)) + goto out_unlock; + + trace_sched_waking(p); + + if (task_queued(p) || task_running(p)) + goto out_running; + + ttwu_activate(p, rq, wake_flags & WF_SYNC); + success = true; + +out_running: + ttwu_post_activation(p, rq, success); +out_unlock: + task_grq_unlock(&flags); + + if (schedstat_enabled()) + ttwu_stat(p, cpu, wake_flags); + + put_cpu(); + + return success; +} + +/** + * try_to_wake_up_local - try to wake up a local task with grq lock held + * @p: the thread to be awakened + * + * Put @p on the run-queue if it's not already there. The caller must + * ensure that grq is locked and, @p is not the current task. + * grq stays locked over invocation. + */ +static void try_to_wake_up_local(struct task_struct *p) +{ + struct rq *rq = task_rq(p); + bool success = false; + + lockdep_assert_held(&grq.lock); + + if (!(p->state & TASK_NORMAL)) + return; + + trace_sched_waking(p); + + if (!task_queued(p)) { + if (likely(!task_running(p))) { + schedstat_inc(rq, ttwu_count); + schedstat_inc(rq, ttwu_local); + } + ttwu_activate(p, rq, false); + if (schedstat_enabled()) + ttwu_stat(p, smp_processor_id(), 0); + success = true; + } + ttwu_post_activation(p, rq, success); +} + +/** + * wake_up_process - Wake up a specific process + * @p: The process to be woken up. + * + * Attempt to wake up the nominated process and move it to the set of runnable + * processes. + * + * Return: 1 if the process was woken up, 0 if it was already running. + * + * It may be assumed that this function implies a write memory barrier before + * changing the task state if and only if any tasks are woken up. + */ +int wake_up_process(struct task_struct *p) +{ + return try_to_wake_up(p, TASK_NORMAL, 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); +} + +static void time_slice_expired(struct task_struct *p); + +/* + * Perform scheduler related setup for a newly forked process p. + * p is forked by current. + */ +int sched_fork(unsigned long __maybe_unused clone_flags, struct task_struct *p) +{ +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&p->preempt_notifiers); +#endif + /* + * The process state is set to the same value of the process executing + * do_fork() code. That is running. 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. + */ + + /* Should be reset in fork.c but done here for ease of bfs patching */ + p->on_rq = + p->utime = + p->stime = + p->utimescaled = + p->stimescaled = + p->sched_time = + p->stime_pc = + p->utime_pc = 0; + + /* + * Revert to default priority/policy on fork if requested. + */ + if (unlikely(p->sched_reset_on_fork)) { + if (p->policy == SCHED_FIFO || p->policy == SCHED_RR) { + p->policy = SCHED_NORMAL; + p->normal_prio = normal_prio(p); + } + + if (PRIO_TO_NICE(p->static_prio) < 0) { + p->static_prio = NICE_TO_PRIO(0); + p->normal_prio = p->static_prio; + } + + /* + * We don't need the reset flag anymore after the fork. It has + * fulfilled its duty: + */ + p->sched_reset_on_fork = 0; + } + + p->node = NULL; +#ifdef CONFIG_SCHED_INFO + if (unlikely(sched_info_on())) + memset(&p->sched_info, 0, sizeof(p->sched_info)); +#endif + p->on_cpu = false; + clear_sticky(p); + init_task_preempt_count(p); + return 0; +} + +#ifdef CONFIG_SCHEDSTATS + +DEFINE_STATIC_KEY_FALSE(sched_schedstats); +static bool __initdata __sched_schedstats = false; + +static void set_schedstats(bool enabled) +{ + if (enabled) + static_branch_enable(&sched_schedstats); + else + static_branch_disable(&sched_schedstats); +} + +void force_schedstat_enabled(void) +{ + if (!schedstat_enabled()) { + pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n"); + static_branch_enable(&sched_schedstats); + } +} + +static int __init setup_schedstats(char *str) +{ + int ret = 0; + if (!str) + goto out; + + /* + * This code is called before jump labels have been set up, so we can't + * change the static branch directly just yet. Instead set a temporary + * variable so init_schedstats() can do it later. + */ + if (!strcmp(str, "enable")) { + __sched_schedstats = true; + ret = 1; + } else if (!strcmp(str, "disable")) { + __sched_schedstats = false; + ret = 1; + } +out: + if (!ret) + pr_warn("Unable to parse schedstats=\n"); + + return ret; +} +__setup("schedstats=", setup_schedstats); + +static void __init init_schedstats(void) +{ + set_schedstats(__sched_schedstats); +} + +#ifdef CONFIG_PROC_SYSCTL +int sysctl_schedstats(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = static_branch_likely(&sched_schedstats); + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + set_schedstats(state); + return err; +} +#endif /* CONFIG_PROC_SYSCTL */ +#else /* !CONFIG_SCHEDSTATS */ +static inline void init_schedstats(void) {} +#endif /* CONFIG_SCHEDSTATS */ + +/* + * 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) +{ + struct task_struct *parent; + unsigned long flags; + struct rq *rq; + + parent = p->parent; + rq = task_grq_lock(p, &flags); + + /* + * Reinit new task deadline as its creator deadline could have changed + * since call to dup_task_struct(). + */ + p->deadline = rq->rq_deadline; + + /* + * If the task is a new process, current and parent are the same. If + * the task is a new thread in the thread group, it will have much more + * in common with current than with the parent. + */ + set_task_cpu(p, task_cpu(rq->curr)); + + /* + * Make sure we do not leak PI boosting priority to the child. + */ + p->prio = rq->curr->normal_prio; + + activate_task(p, rq); + trace_sched_wakeup_new(p); + if (unlikely(p->policy == SCHED_FIFO)) + goto after_ts_init; + + /* + * Share the timeslice between parent and child, thus the + * total amount of pending timeslices in the system doesn't change, + * resulting in more scheduling fairness. If it's negative, it won't + * matter since that's the same as being 0. current's time_slice is + * actually in rq_time_slice when it's running, as is its last_ran + * value. rq->rq_deadline is only modified within schedule() so it + * is always equal to current->deadline. + */ + p->last_ran = rq->rq_last_ran; + if (likely(rq->rq_time_slice >= RESCHED_US * 2)) { + rq->rq_time_slice /= 2; + p->time_slice = rq->rq_time_slice; +after_ts_init: + if (rq->curr == parent && !suitable_idle_cpus(p)) { + /* + * The VM isn't cloned, so we're in a good position to + * do child-runs-first in anticipation of an exec. This + * usually avoids a lot of COW overhead. + */ + __set_tsk_resched(parent); + } else + try_preempt(p, rq); + } else { + if (rq->curr == parent) { + /* + * Forking task has run out of timeslice. Reschedule it and + * start its child with a new time slice and deadline. The + * child will end up running first because its deadline will + * be slightly earlier. + */ + rq->rq_time_slice = 0; + __set_tsk_resched(parent); + } + time_slice_expired(p); + } + task_grq_unlock(&flags); +} + +#ifdef CONFIG_PREEMPT_NOTIFIERS + +static struct static_key preempt_notifier_key = STATIC_KEY_INIT_FALSE; + +void preempt_notifier_inc(void) +{ + static_key_slow_inc(&preempt_notifier_key); +} +EXPORT_SYMBOL_GPL(preempt_notifier_inc); + +void preempt_notifier_dec(void) +{ + static_key_slow_dec(&preempt_notifier_key); +} +EXPORT_SYMBOL_GPL(preempt_notifier_dec); + +/** + * preempt_notifier_register - tell me when current is being preempted & rescheduled + * @notifier: notifier struct to register + */ +void preempt_notifier_register(struct preempt_notifier *notifier) +{ + if (!static_key_false(&preempt_notifier_key)) + WARN(1, "registering preempt_notifier while notifiers disabled\n"); + + 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 *not* 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; + + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) + notifier->ops->sched_in(notifier, raw_smp_processor_id()); +} + +static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ + if (static_key_false(&preempt_notifier_key)) + __fire_sched_in_preempt_notifiers(curr); +} + +static void +__fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ + struct preempt_notifier *notifier; + + hlist_for_each_entry(notifier, &curr->preempt_notifiers, link) + notifier->ops->sched_out(notifier, next); +} + +static __always_inline void +fire_sched_out_preempt_notifiers(struct task_struct *curr, + struct task_struct *next) +{ + if (static_key_false(&preempt_notifier_key)) + __fire_sched_out_preempt_notifiers(curr, next); +} + +#else /* !CONFIG_PREEMPT_NOTIFIERS */ + +static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr) +{ +} + +static inline 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 + * @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) +{ + sched_info_switch(rq, prev, next); + perf_event_task_sched_out(prev, 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.) + * + * The context switch have flipped the stack from under us and restored the + * local variables which were saved when this task called schedule() in the + * past. prev == current is still correct but we need to recalculate this_rq + * because prev may have moved to another CPU. + */ +static struct rq *finish_task_switch(struct task_struct *prev) + __releases(grq.lock) +{ + struct rq *rq = this_rq(); + struct mm_struct *mm = rq->prev_mm; + long prev_state; + + /* + * The previous task will have left us with a preempt_count of 2 + * because it left us after: + * + * schedule() + * preempt_disable(); // 1 + * __schedule() + * raw_spin_lock_irq(&rq->lock) // 2 + * + * Also, see FORK_PREEMPT_COUNT. + */ + if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET, + "corrupted preempt_count: %s/%d/0x%x\n", + current->comm, current->pid, preempt_count())) + preempt_count_set(FORK_PREEMPT_COUNT); + + 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. + * + * We must observe prev->state before clearing prev->on_cpu (in + * finish_lock_switch), otherwise a concurrent wakeup can get prev + * running on another CPU and we could rave with its RUNNING -> DEAD + * transition, resulting in a double drop. + */ + prev_state = prev->state; + vtime_task_switch(prev); + perf_event_task_sched_in(prev, current); + finish_lock_switch(rq, prev); + finish_arch_post_lock_switch(); + + 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); + } + return rq; +} + +/** + * schedule_tail - first thing a freshly forked thread must call. + * @prev: the thread we just switched away from. + */ +asmlinkage __visible void schedule_tail(struct task_struct *prev) + __releases(grq.lock) +{ + struct rq *rq; + + /* + * New tasks start with FORK_PREEMPT_COUNT, see there and + * finish_task_switch() for details. + * + * finish_task_switch() will drop rq->lock() and lower preempt_count + * and the preempt_enable() will end up enabling preemption (on + * PREEMPT_COUNT kernels). + */ + + rq = finish_task_switch(prev); + preempt_enable(); + + 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 __always_inline struct rq * +context_switch(struct rq *rq, struct task_struct *prev, + struct task_struct *next) +{ + struct mm_struct *mm, *oldmm; + + prepare_task_switch(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_start_context_switch(prev); + + if (!mm) { + next->active_mm = oldmm; + atomic_inc(&oldmm->mm_count); + enter_lazy_tlb(oldmm, next); + } else + switch_mm_irqs_off(oldmm, mm, next); + + if (!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: + */ + spin_release(&grq.lock.dep_map, 1, _THIS_IP_); + + /* Here we just switch the register state and the stack. */ + switch_to(prev, next, prev); + barrier(); + + return finish_task_switch(prev); +} + +/* + * nr_running, nr_uninterruptible and nr_context_switches: + * + * externally visible scheduler statistics: current number of runnable + * threads, total number of context switches performed since bootup. All are + * measured without grabbing the grq lock but the occasional inaccurate result + * doesn't matter so long as it's positive. + */ +unsigned long nr_running(void) +{ + long nr = grq.nr_running; + + if (unlikely(nr < 0)) + nr = 0; + return (unsigned long)nr; +} + +static unsigned long nr_uninterruptible(void) +{ + long nu = grq.nr_uninterruptible; + + if (unlikely(nu < 0)) + nu = 0; + return nu; +} + +/* + * Check if only the current task is running on the cpu. + * + * Caution: this function does not check that the caller has disabled + * preemption, thus the result might have a time-of-check-to-time-of-use + * race. The caller is responsible to use it correctly, for example: + * + * - from a non-preemptable section (of course) + * + * - from a thread that is bound to a single CPU + * + * - in a loop with very short iterations (e.g. a polling loop) + */ +bool single_task_running(void) +{ + if (cpu_rq(smp_processor_id())->soft_affined == 1) + return true; + else + return false; +} +EXPORT_SYMBOL(single_task_running); + +unsigned long long nr_context_switches(void) +{ + long long ns = grq.nr_switches; + + /* This is of course impossible */ + if (unlikely(ns < 0)) + ns = 1; + return (unsigned long long)ns; +} + +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_iowait_cpu(int cpu) +{ + struct rq *this = cpu_rq(cpu); + return atomic_read(&this->nr_iowait); +} + +unsigned long nr_active(void) +{ + return nr_running() + nr_uninterruptible(); +} + +/* Beyond a task running on this CPU, load is equal everywhere on BFS, so we + * base it on the number of running or queued tasks with their ->rq pointer + * set to this cpu as being the CPU they're more likely to run on. */ +void get_iowait_load(unsigned long *nr_waiters, unsigned long *load) +{ + struct rq *rq = this_rq(); + + *nr_waiters = atomic_read(&rq->nr_iowait); + *load = rq->soft_affined; +} + +/* Variables and functions for calc_load */ +static unsigned long calc_load_update; +unsigned long avenrun[3]; +EXPORT_SYMBOL(avenrun); + +/** + * get_avenrun - get the load average array + * @loads: pointer to dest load array + * @offset: offset to add + * @shift: shift count to shift the result left + * + * These values are estimates at best, so no need for locking. + */ +void get_avenrun(unsigned long *loads, unsigned long offset, int shift) +{ + loads[0] = (avenrun[0] + offset) << shift; + loads[1] = (avenrun[1] + offset) << shift; + loads[2] = (avenrun[2] + offset) << shift; +} + +static unsigned long +calc_load(unsigned long load, unsigned long exp, unsigned long active) +{ + unsigned long newload; + + newload = load * exp + active * (FIXED_1 - exp); + if (active >= load) + newload += FIXED_1-1; + + return newload / FIXED_1; +} + +/* + * calc_load - update the avenrun load estimates every LOAD_FREQ seconds. + */ +void calc_global_load(unsigned long ticks) +{ + long active; + + if (time_before(jiffies, calc_load_update)) + return; + active = nr_active() * FIXED_1; + + avenrun[0] = calc_load(avenrun[0], EXP_1, active); + avenrun[1] = calc_load(avenrun[1], EXP_5, active); + avenrun[2] = calc_load(avenrun[2], EXP_15, active); + + calc_load_update = jiffies + LOAD_FREQ; +} + +DEFINE_PER_CPU(struct kernel_stat, kstat); +DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat); + +EXPORT_PER_CPU_SYMBOL(kstat); +EXPORT_PER_CPU_SYMBOL(kernel_cpustat); + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + +/* + * There are no locks covering percpu hardirq/softirq time. + * They are only modified in account_system_vtime, on corresponding CPU + * with interrupts disabled. So, writes are safe. + * They are read and saved off onto struct rq in update_rq_clock(). + * This may result in other CPU reading this CPU's irq time and can + * race with irq/account_system_vtime on this CPU. We would either get old + * or new value with a side effect of accounting a slice of irq time to wrong + * task when irq is in progress while we read rq->clock. That is a worthy + * compromise in place of having locks on each irq in account_system_time. + */ +static DEFINE_PER_CPU(u64, cpu_hardirq_time); +static DEFINE_PER_CPU(u64, cpu_softirq_time); + +static DEFINE_PER_CPU(u64, irq_start_time); +static int sched_clock_irqtime; + +void enable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 1; +} + +void disable_sched_clock_irqtime(void) +{ + sched_clock_irqtime = 0; +} + +#ifndef CONFIG_64BIT +static DEFINE_PER_CPU(seqcount_t, irq_time_seq); + +static inline void irq_time_write_begin(void) +{ + __this_cpu_inc(irq_time_seq.sequence); + smp_wmb(); +} + +static inline void irq_time_write_end(void) +{ + smp_wmb(); + __this_cpu_inc(irq_time_seq.sequence); +} + +static inline u64 irq_time_read(int cpu) +{ + u64 irq_time; + unsigned seq; + + do { + seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu)); + irq_time = per_cpu(cpu_softirq_time, cpu) + + per_cpu(cpu_hardirq_time, cpu); + } while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq)); + + return irq_time; +} +#else /* CONFIG_64BIT */ +static inline void irq_time_write_begin(void) +{ +} + +static inline void irq_time_write_end(void) +{ +} + +static inline u64 irq_time_read(int cpu) +{ + return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu); +} +#endif /* CONFIG_64BIT */ + +/* + * Called before incrementing preempt_count on {soft,}irq_enter + * and before decrementing preempt_count on {soft,}irq_exit. + */ +void irqtime_account_irq(struct task_struct *curr) +{ + unsigned long flags; + s64 delta; + int cpu; + + if (!sched_clock_irqtime) + return; + + local_irq_save(flags); + + cpu = smp_processor_id(); + delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time); + __this_cpu_add(irq_start_time, delta); + + irq_time_write_begin(); + /* + * We do not account for softirq time from ksoftirqd here. + * We want to continue accounting softirq time to ksoftirqd thread + * in that case, so as not to confuse scheduler with a special task + * that do not consume any time, but still wants to run. + */ + if (hardirq_count()) + __this_cpu_add(cpu_hardirq_time, delta); + else if (in_serving_softirq() && curr != this_cpu_ksoftirqd()) + __this_cpu_add(cpu_softirq_time, delta); + + irq_time_write_end(); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(irqtime_account_irq); + +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#ifdef CONFIG_PARAVIRT +static inline u64 steal_ticks(u64 steal) +{ + if (unlikely(steal > NSEC_PER_SEC)) + return div_u64(steal, TICK_NSEC); + + return __iter_div_u64_rem(steal, TICK_NSEC, &steal); +} +#endif + +static void update_rq_clock_task(struct rq *rq, s64 delta) +{ +/* + * In theory, the compile should just see 0 here, and optimize out the call + * to sched_rt_avg_update. But I don't trust it... + */ +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + s64 irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time; + + /* + * Since irq_time is only updated on {soft,}irq_exit, we might run into + * this case when a previous update_rq_clock() happened inside a + * {soft,}irq region. + * + * When this happens, we stop ->clock_task and only update the + * prev_irq_time stamp to account for the part that fit, so that a next + * update will consume the rest. This ensures ->clock_task is + * monotonic. + * + * It does however cause some slight miss-attribution of {soft,}irq + * time, a more accurate solution would be to update the irq_time using + * the current rq->clock timestamp, except that would require using + * atomic ops. + */ + if (irq_delta > delta) + irq_delta = delta; + + rq->prev_irq_time += irq_delta; + delta -= irq_delta; +#endif +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + if (static_key_false((¶virt_steal_rq_enabled))) { + s64 steal = paravirt_steal_clock(cpu_of(rq)); + + steal -= rq->prev_steal_time_rq; + + if (unlikely(steal > delta)) + steal = delta; + + rq->prev_steal_time_rq += steal; + + delta -= steal; + } +#endif + + rq->clock_task += delta; +} + +#ifndef nsecs_to_cputime +# define nsecs_to_cputime(__nsecs) nsecs_to_jiffies(__nsecs) +#endif + +#ifdef CONFIG_IRQ_TIME_ACCOUNTING +static void irqtime_account_hi_si(void) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + u64 latest_ns; + + latest_ns = nsecs_to_cputime64(this_cpu_read(cpu_hardirq_time)); + if (latest_ns > cpustat[CPUTIME_IRQ]) + cpustat[CPUTIME_IRQ] += (__force u64)cputime_one_jiffy; + + latest_ns = nsecs_to_cputime64(this_cpu_read(cpu_softirq_time)); + if (latest_ns > cpustat[CPUTIME_SOFTIRQ]) + cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy; +} +#else /* CONFIG_IRQ_TIME_ACCOUNTING */ + +#define sched_clock_irqtime (0) + +static inline void irqtime_account_hi_si(void) +{ +} +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ + +static __always_inline bool steal_account_process_tick(void) +{ +#ifdef CONFIG_PARAVIRT + if (static_key_false(¶virt_steal_enabled)) { + u64 steal; + cputime_t steal_ct; + + steal = paravirt_steal_clock(smp_processor_id()); + steal -= this_rq()->prev_steal_time; + + /* + * cputime_t may be less precise than nsecs (eg: if it's + * based on jiffies). Lets cast the result to cputime + * granularity and account the rest on the next rounds. + */ + steal_ct = nsecs_to_cputime(steal); + this_rq()->prev_steal_time += cputime_to_nsecs(steal_ct); + + account_steal_time(steal_ct); + return steal_ct; + } +#endif + return false; +} + +/* + * Accumulate raw cputime values of dead tasks (sig->[us]time) and live + * tasks (sum on group iteration) belonging to @tsk's group. + */ +void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times) +{ + struct signal_struct *sig = tsk->signal; + cputime_t utime, stime; + struct task_struct *t; + unsigned int seq, nextseq; + unsigned long flags; + + rcu_read_lock(); + /* Attempt a lockless read on the first round. */ + nextseq = 0; + do { + seq = nextseq; + flags = read_seqbegin_or_lock_irqsave(&sig->stats_lock, &seq); + times->utime = sig->utime; + times->stime = sig->stime; + times->sum_exec_runtime = sig->sum_sched_runtime; + + for_each_thread(tsk, t) { + task_cputime(t, &utime, &stime); + times->utime += utime; + times->stime += stime; + times->sum_exec_runtime += task_sched_runtime(t); + } + /* If lockless access failed, take the lock. */ + nextseq = 1; + } while (need_seqretry(&sig->stats_lock, seq)); + done_seqretry_irqrestore(&sig->stats_lock, seq, flags); + rcu_read_unlock(); +} + +/* + * On each tick, see what percentage of that tick was attributed to each + * component and add the percentage to the _pc values. Once a _pc value has + * accumulated one tick's worth, account for that. This means the total + * percentage of load components will always be 128 (pseudo 100) per tick. + */ +static void pc_idle_time(struct rq *rq, struct task_struct *idle, unsigned long pc) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + if (atomic_read(&rq->nr_iowait) > 0) { + rq->iowait_pc += pc; + if (rq->iowait_pc >= 128) { + cpustat[CPUTIME_IOWAIT] += (__force u64)cputime_one_jiffy * rq->iowait_pc / 128; + rq->iowait_pc %= 128; + } + } else { + rq->idle_pc += pc; + if (rq->idle_pc >= 128) { + cpustat[CPUTIME_IDLE] += (__force u64)cputime_one_jiffy * rq->idle_pc / 128; + rq->idle_pc %= 128; + } + } + acct_update_integrals(idle); +} + +static void +pc_system_time(struct rq *rq, struct task_struct *p, int hardirq_offset, + unsigned long pc, unsigned long ns) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + + p->stime_pc += pc; + if (p->stime_pc >= 128) { + int jiffs = p->stime_pc / 128; + + p->stime_pc %= 128; + p->stime += (__force u64)cputime_one_jiffy * jiffs; + p->stimescaled += one_jiffy_scaled * jiffs; + account_group_system_time(p, cputime_one_jiffy * jiffs); + } + p->sched_time += ns; + account_group_exec_runtime(p, ns); + + if (hardirq_count() - hardirq_offset) { + rq->irq_pc += pc; + if (rq->irq_pc >= 128) { + cpustat[CPUTIME_IRQ] += (__force u64)cputime_one_jiffy * rq->irq_pc / 128; + rq->irq_pc %= 128; + } + } else if (in_serving_softirq()) { + rq->softirq_pc += pc; + if (rq->softirq_pc >= 128) { + cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy * rq->softirq_pc / 128; + rq->softirq_pc %= 128; + } + } else { + rq->system_pc += pc; + if (rq->system_pc >= 128) { + cpustat[CPUTIME_SYSTEM] += (__force u64)cputime_one_jiffy * rq->system_pc / 128; + rq->system_pc %= 128; + } + } + acct_update_integrals(p); +} + +static void pc_user_time(struct rq *rq, struct task_struct *p, + unsigned long pc, unsigned long ns) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + cputime_t one_jiffy_scaled = cputime_to_scaled(cputime_one_jiffy); + + p->utime_pc += pc; + if (p->utime_pc >= 128) { + int jiffs = p->utime_pc / 128; + + p->utime_pc %= 128; + p->utime += (__force u64)cputime_one_jiffy * jiffs; + p->utimescaled += one_jiffy_scaled * jiffs; + account_group_user_time(p, cputime_one_jiffy * jiffs); + } + p->sched_time += ns; + account_group_exec_runtime(p, ns); + + if (this_cpu_ksoftirqd() == p) { + /* + * ksoftirqd time do not get accounted in cpu_softirq_time. + * So, we have to handle it separately here. + */ + rq->softirq_pc += pc; + if (rq->softirq_pc >= 128) { + cpustat[CPUTIME_SOFTIRQ] += (__force u64)cputime_one_jiffy * rq->softirq_pc / 128; + rq->softirq_pc %= 128; + } + } + + if (task_nice(p) > 0 || idleprio_task(p)) { + rq->nice_pc += pc; + if (rq->nice_pc >= 128) { + cpustat[CPUTIME_NICE] += (__force u64)cputime_one_jiffy * rq->nice_pc / 128; + rq->nice_pc %= 128; + } + } else { + rq->user_pc += pc; + if (rq->user_pc >= 128) { + cpustat[CPUTIME_USER] += (__force u64)cputime_one_jiffy * rq->user_pc / 128; + rq->user_pc %= 128; + } + } + acct_update_integrals(p); +} + +/* + * Convert nanoseconds to pseudo percentage of one tick. Use 128 for fast + * shifts instead of 100 + */ +#define NS_TO_PC(NS) (NS * 128 / JIFFY_NS) + +/* + * This is called on clock ticks. + * Bank in p->sched_time the ns elapsed since the last tick or switch. + * CPU scheduler quota accounting is also performed here in microseconds. + */ +static void +update_cpu_clock_tick(struct rq *rq, struct task_struct *p) +{ + long account_ns = rq->clock_task - rq->rq_last_ran; + struct task_struct *idle = rq->idle; + unsigned long account_pc; + + if (unlikely(account_ns < 0) || steal_account_process_tick()) + goto ts_account; + + account_pc = NS_TO_PC(account_ns); + + /* Accurate tick timekeeping */ + if (user_mode(get_irq_regs())) + pc_user_time(rq, p, account_pc, account_ns); + else if (p != idle || (irq_count() != HARDIRQ_OFFSET)) + pc_system_time(rq, p, HARDIRQ_OFFSET, + account_pc, account_ns); + else + pc_idle_time(rq, idle, account_pc); + + if (sched_clock_irqtime) + irqtime_account_hi_si(); + +ts_account: + /* time_slice accounting is done in usecs to avoid overflow on 32bit */ + if (rq->rq_policy != SCHED_FIFO && p != idle) { + s64 time_diff = rq->clock - rq->timekeep_clock; + + niffy_diff(&time_diff, 1); + rq->rq_time_slice -= NS_TO_US(time_diff); + } + + rq->rq_last_ran = rq->clock_task; + rq->timekeep_clock = rq->clock; +} + +/* + * This is called on context switches. + * Bank in p->sched_time the ns elapsed since the last tick or switch. + * CPU scheduler quota accounting is also performed here in microseconds. + */ +static void +update_cpu_clock_switch(struct rq *rq, struct task_struct *p) +{ + long account_ns = rq->clock_task - rq->rq_last_ran; + struct task_struct *idle = rq->idle; + unsigned long account_pc; + + if (unlikely(account_ns < 0)) + goto ts_account; + + account_pc = NS_TO_PC(account_ns); + + /* Accurate subtick timekeeping */ + if (p != idle) { + pc_user_time(rq, p, account_pc, account_ns); + } + else + pc_idle_time(rq, idle, account_pc); + +ts_account: + /* time_slice accounting is done in usecs to avoid overflow on 32bit */ + if (rq->rq_policy != SCHED_FIFO && p != idle) { + s64 time_diff = rq->clock - rq->timekeep_clock; + + niffy_diff(&time_diff, 1); + rq->rq_time_slice -= NS_TO_US(time_diff); + } + + rq->rq_last_ran = rq->clock_task; + rq->timekeep_clock = rq->clock; +} + +/* + * Return any ns on the sched_clock that have not yet been accounted in + * @p in case that task is currently running. + * + * Called with task_grq_lock() held. + */ +static inline u64 do_task_delta_exec(struct task_struct *p, struct rq *rq) +{ + u64 ns = 0; + + /* + * Must be ->curr _and_ ->on_rq. If dequeued, we would + * project cycles that may never be accounted to this + * thread, breaking clock_gettime(). + */ + if (p == rq->curr && p->on_rq) { + update_clocks(rq); + ns = rq->clock_task - rq->rq_last_ran; + if (unlikely((s64)ns < 0)) + ns = 0; + } + + return ns; +} + +/* + * Return accounted runtime for the task. + * Return separately the current's pending runtime that have not been + * accounted yet. + * + */ +unsigned long long task_sched_runtime(struct task_struct *p) +{ + unsigned long flags; + struct rq *rq; + u64 ns; + +#if defined(CONFIG_64BIT) && defined(CONFIG_SMP) + /* + * 64-bit doesn't need locks to atomically read a 64bit value. + * So we have a optimization chance when the task's delta_exec is 0. + * Reading ->on_cpu is racy, but this is ok. + * + * If we race with it leaving cpu, we'll take a lock. So we're correct. + * If we race with it entering cpu, unaccounted time is 0. This is + * indistinguishable from the read occurring a few cycles earlier. + * If we see ->on_cpu without ->on_rq, the task is leaving, and has + * been accounted, so we're correct here as well. + */ + if (!p->on_cpu || !p->on_rq) + return tsk_seruntime(p); +#endif + + rq = task_grq_lock(p, &flags); + ns = p->sched_time + do_task_delta_exec(p, rq); + task_grq_unlock(&flags); + + return ns; +} + +/* Compatibility crap */ +void account_user_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ +} + +void account_idle_time(cputime_t cputime) +{ +} + +/* + * 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 + * @cputime_scaled: cputime scaled by cpu frequency + */ +static void account_guest_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + /* Add guest time to process. */ + p->utime += (__force u64)cputime; + p->utimescaled += (__force u64)cputime_scaled; + account_group_user_time(p, cputime); + p->gtime += (__force u64)cputime; + + /* Add guest time to cpustat. */ + if (task_nice(p) > 0) { + cpustat[CPUTIME_NICE] += (__force u64)cputime; + cpustat[CPUTIME_GUEST_NICE] += (__force u64)cputime; + } else { + cpustat[CPUTIME_USER] += (__force u64)cputime; + cpustat[CPUTIME_GUEST] += (__force u64)cputime; + } +} + +/* + * Account system cpu time to a process and desired cpustat field + * @p: the process that the cpu time gets accounted to + * @cputime: the cpu time spent in kernel space since the last update + * @cputime_scaled: cputime scaled by cpu frequency + * @target_cputime64: pointer to cpustat field that has to be updated + */ +static inline +void __account_system_time(struct task_struct *p, cputime_t cputime, + cputime_t cputime_scaled, cputime64_t *target_cputime64) +{ + /* Add system time to process. */ + p->stime += (__force u64)cputime; + p->stimescaled += (__force u64)cputime_scaled; + account_group_system_time(p, cputime); + + /* Add system time to cpustat. */ + *target_cputime64 += (__force u64)cputime; + + /* Account for system time used */ + acct_update_integrals(p); +} + +/* + * 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 + * @cputime_scaled: cputime scaled by cpu frequency + * This is for guest only now. + */ +void account_system_time(struct task_struct *p, int hardirq_offset, + cputime_t cputime, cputime_t cputime_scaled) +{ + + if ((p->flags & PF_VCPU) && (irq_count() - hardirq_offset == 0)) + account_guest_time(p, cputime, cputime_scaled); +} + +/* + * Account for involuntary wait time. + * @steal: the cpu time spent in involuntary wait + */ +void account_steal_time(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + + cpustat[CPUTIME_STEAL] += (__force u64)cputime; +} + +/* + * Account for idle time. + * @cputime: the cpu time spent in idle wait + */ +static void account_idle_times(cputime_t cputime) +{ + u64 *cpustat = kcpustat_this_cpu->cpustat; + struct rq *rq = this_rq(); + + if (atomic_read(&rq->nr_iowait) > 0) + cpustat[CPUTIME_IOWAIT] += (__force u64)cputime; + else + cpustat[CPUTIME_IDLE] += (__force u64)cputime; +} + +#ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE + +void account_process_tick(struct task_struct *p, int user_tick) +{ +} + +/* + * Account multiple ticks of steal time. + * @p: the process from which the cpu time has been stolen + * @ticks: number of stolen ticks + */ +void account_steal_ticks(unsigned long ticks) +{ + account_steal_time(jiffies_to_cputime(ticks)); +} + +/* + * Account multiple ticks of idle time. + * @ticks: number of stolen ticks + */ +void account_idle_ticks(unsigned long ticks) +{ + account_idle_times(jiffies_to_cputime(ticks)); +} +#endif + +static inline void grq_iso_lock(void) + __acquires(grq.iso_lock) +{ + raw_spin_lock(&grq.iso_lock); +} + +static inline void grq_iso_unlock(void) + __releases(grq.iso_lock) +{ + raw_spin_unlock(&grq.iso_lock); +} + +/* + * Functions to test for when SCHED_ISO tasks have used their allocated + * quota as real time scheduling and convert them back to SCHED_NORMAL. + * Where possible, the data is tested lockless, to avoid grabbing iso_lock + * because the occasional inaccurate result won't matter. However the + * tick data is only ever modified under lock. iso_refractory is only simply + * set to 0 or 1 so it's not worth grabbing the lock yet again for that. + */ +static bool set_iso_refractory(void) +{ + grq.iso_refractory = true; + return grq.iso_refractory; +} + +static bool clear_iso_refractory(void) +{ + grq.iso_refractory = false; + return grq.iso_refractory; +} + +/* + * Test if SCHED_ISO tasks have run longer than their alloted period as RT + * tasks and set the refractory flag if necessary. There is 10% hysteresis + * for unsetting the flag. 115/128 is ~90/100 as a fast shift instead of a + * slow division. + */ +static bool test_ret_isorefractory(struct rq *rq) +{ + if (likely(!grq.iso_refractory)) { + if (grq.iso_ticks > ISO_PERIOD * sched_iso_cpu) + return set_iso_refractory(); + } else { + if (grq.iso_ticks < ISO_PERIOD * (sched_iso_cpu * 115 / 128)) + return clear_iso_refractory(); + } + return grq.iso_refractory; +} + +static void iso_tick(void) +{ + grq_iso_lock(); + grq.iso_ticks += 100; + grq_iso_unlock(); +} + +/* No SCHED_ISO task was running so decrease rq->iso_ticks */ +static inline void no_iso_tick(void) +{ + if (grq.iso_ticks) { + grq_iso_lock(); + grq.iso_ticks -= grq.iso_ticks / ISO_PERIOD + 1; + if (unlikely(grq.iso_refractory && grq.iso_ticks < + ISO_PERIOD * (sched_iso_cpu * 115 / 128))) + clear_iso_refractory(); + grq_iso_unlock(); + } +} + +/* This manages tasks that have run out of timeslice during a scheduler_tick */ +static void task_running_tick(struct rq *rq) +{ + struct task_struct *p; + + /* + * If a SCHED_ISO task is running we increment the iso_ticks. In + * order to prevent SCHED_ISO tasks from causing starvation in the + * presence of true RT tasks we account those as iso_ticks as well. + */ + if ((rt_queue(rq) || (iso_queue(rq) && !grq.iso_refractory))) { + if (grq.iso_ticks <= (ISO_PERIOD * 128) - 128) + iso_tick(); + } else + no_iso_tick(); + + if (iso_queue(rq)) { + if (unlikely(test_ret_isorefractory(rq))) { + if (rq_running_iso(rq)) { + /* + * SCHED_ISO task is running as RT and limit + * has been hit. Force it to reschedule as + * SCHED_NORMAL by zeroing its time_slice + */ + rq->rq_time_slice = 0; + } + } + } + + /* SCHED_FIFO tasks never run out of timeslice. */ + if (rq->rq_policy == SCHED_FIFO) + return; + /* + * Tasks that were scheduled in the first half of a tick are not + * allowed to run into the 2nd half of the next tick if they will + * run out of time slice in the interim. Otherwise, if they have + * less than RESCHED_US μs of time slice left they will be rescheduled. + */ + if (rq->dither) { + if (rq->rq_time_slice > HALF_JIFFY_US) + return; + else + rq->rq_time_slice = 0; + } else if (rq->rq_time_slice >= RESCHED_US) + return; + + /* p->time_slice < RESCHED_US. We only modify task_struct under grq lock */ + p = rq->curr; + + grq_lock(); + requeue_task(p); + __set_tsk_resched(p); + grq_unlock(); +} + +/* + * This function gets called by the timer code, with HZ frequency. + * We call it with interrupts disabled. The data modified is all + * local to struct rq so we don't need to grab grq lock. + */ +void scheduler_tick(void) +{ + int cpu __maybe_unused = smp_processor_id(); + struct rq *rq = cpu_rq(cpu); + + sched_clock_tick(); + /* grq lock not grabbed, so only update rq clock */ + update_rq_clock(rq); + update_cpu_clock_tick(rq, rq->curr); + if (!rq_idle(rq)) + task_running_tick(rq); + else { + /* + * Trigger cpufreq update while we're idle. Soft affined will + * be zero unless we have uninterruptible tasks. + */ + cpufreq_trigger(grq.niffies, rq->soft_affined); + no_iso_tick(); + } + rq->last_tick = rq->clock; + perf_event_task_tick(); +} + +#if defined(CONFIG_PREEMPT) && (defined(CONFIG_DEBUG_PREEMPT) || \ + defined(CONFIG_PREEMPT_TRACER)) +/* + * If the value passed in is equal to the current preempt count + * then we just disabled preemption. Start timing the latency. + */ +static inline void preempt_latency_start(int val) +{ + if (preempt_count() == val) { + unsigned long ip = get_lock_parent_ip(); +#ifdef CONFIG_DEBUG_PREEMPT + current->preempt_disable_ip = ip; +#endif + trace_preempt_off(CALLER_ADDR0, ip); + } +} + +void preempt_count_add(int val) +{ +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Underflow? + */ + if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0))) + return; +#endif + __preempt_count_add(val); +#ifdef CONFIG_DEBUG_PREEMPT + /* + * Spinlock count overflowing soon? + */ + DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >= + PREEMPT_MASK - 10); +#endif + preempt_latency_start(val); +} +EXPORT_SYMBOL(preempt_count_add); +NOKPROBE_SYMBOL(preempt_count_add); + +/* + * If the value passed in equals to the current preempt count + * then we just enabled preemption. Stop timing the latency. + */ +static inline void preempt_latency_stop(int val) +{ + if (preempt_count() == val) + trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip()); +} + +void preempt_count_sub(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 + + preempt_latency_stop(val); + __preempt_count_sub(val); +} +EXPORT_SYMBOL(preempt_count_sub); +NOKPROBE_SYMBOL(preempt_count_sub); + +#else +static inline void preempt_latency_start(int val) { } +static inline void preempt_latency_stop(int val) { } +#endif + +/* + * Deadline is "now" in niffies + (offset by priority). Setting the deadline + * is the key to everything. It distributes cpu fairly amongst tasks of the + * same nice value, it proportions cpu according to nice level, it means the + * task that last woke up the longest ago has the earliest deadline, thus + * ensuring that interactive tasks get low latency on wake up. The CPU + * proportion works out to the square of the virtual deadline difference, so + * this equation will give nice 19 3% CPU compared to nice 0. + */ +static inline u64 prio_deadline_diff(int user_prio) +{ + return (prio_ratios[user_prio] * rr_interval * (MS_TO_NS(1) / 128)); +} + +static inline u64 task_deadline_diff(struct task_struct *p) +{ + return prio_deadline_diff(TASK_USER_PRIO(p)); +} + +static inline u64 static_deadline_diff(int static_prio) +{ + return prio_deadline_diff(USER_PRIO(static_prio)); +} + +static inline int longest_deadline_diff(void) +{ + return prio_deadline_diff(39); +} + +static inline int ms_longest_deadline_diff(void) +{ + return NS_TO_MS(longest_deadline_diff()); +} + +/* + * The time_slice is only refilled when it is empty and that is when we set a + * new deadline. + */ +static void time_slice_expired(struct task_struct *p) +{ + p->time_slice = timeslice(); + p->deadline = grq.niffies + task_deadline_diff(p); +#ifdef CONFIG_SMT_NICE + if (!p->mm) + p->smt_bias = 0; + else if (rt_task(p)) + p->smt_bias = 1 << 30; + else if (task_running_iso(p)) + p->smt_bias = 1 << 29; + else if (idleprio_task(p)) { + if (task_running_idle(p)) + p->smt_bias = 0; + else + p->smt_bias = 1; + } else if (--p->smt_bias < 1) + p->smt_bias = MAX_PRIO - p->static_prio; +#endif +} + +/* + * Timeslices below RESCHED_US are considered as good as expired as there's no + * point rescheduling when there's so little time left. SCHED_BATCH tasks + * have been flagged be not latency sensitive and likely to be fully CPU + * bound so every time they're rescheduled they have their time_slice + * refilled, but get a new later deadline to have little effect on + * SCHED_NORMAL tasks. + + */ +static inline void check_deadline(struct task_struct *p) +{ + if (p->time_slice < RESCHED_US || batch_task(p)) + time_slice_expired(p); +} + +#define BITOP_WORD(nr) ((nr) / BITS_PER_LONG) + +/* + * Scheduler queue bitmap specific find next bit. + */ +static inline unsigned long +next_sched_bit(const unsigned long *addr, unsigned long offset) +{ + const unsigned long *p; + unsigned long result; + unsigned long size; + unsigned long tmp; + + size = PRIO_LIMIT; + if (offset >= size) + return size; + + p = addr + BITOP_WORD(offset); + result = offset & ~(BITS_PER_LONG-1); + size -= result; + offset %= BITS_PER_LONG; + if (offset) { + tmp = *(p++); + tmp &= (~0UL << offset); + if (size < BITS_PER_LONG) + goto found_first; + if (tmp) + goto found_middle; + size -= BITS_PER_LONG; + result += BITS_PER_LONG; + } + while (size & ~(BITS_PER_LONG-1)) { + if ((tmp = *(p++))) + goto found_middle; + result += BITS_PER_LONG; + size -= BITS_PER_LONG; + } + if (!size) + return result; + tmp = *p; + +found_first: + tmp &= (~0UL >> (BITS_PER_LONG - size)); + if (tmp == 0UL) /* Are any bits set? */ + return result + size; /* Nope. */ +found_middle: + return result + __ffs(tmp); +} + +/* + * Task selection with skiplists is a simple matter of picking off the first + * task in the sorted list, an O(1) operation. The only time it takes longer + * is if tasks do not have suitable affinity and then we iterate over entries + * till we find the first that does. Worst case here is no tasks with suitable + * affinity and taking O(n). + */ +static inline struct +task_struct *earliest_deadline_task(struct rq *rq, int cpu, struct task_struct *idle) +{ + struct task_struct *edt = idle; + skiplist_node *node = grq.node; + u64 earliest_deadline = ~0ULL; + + while ((node = node->next[0]) != grq.node) { + struct task_struct *p = node->value; + int tcpu; + + /* Make sure affinity is ok */ + if (needs_other_cpu(p, cpu)) + continue; + + if (!smt_schedule(p, rq)) + continue; + + if (!sched_interactive && (tcpu = task_cpu(p)) != cpu) { + u64 dl; + + if (task_sticky(p) && scaling_rq(rq)) + continue; + dl = p->deadline << locality_diff(tcpu, rq); + if (unlikely(!deadline_before(dl, earliest_deadline))) + continue; + earliest_deadline = dl; + edt = p; + /* We continue even though we've found the earliest + * deadline task as the locality offset means there + * may be a better candidate after it. */ + continue; + } + /* This wouldn't happen if we encountered a better deadline from + * another CPU and have already set edt. */ + if (likely(p->deadline < earliest_deadline)) + edt = p; + break; + } + if (likely(edt != idle)) + take_task(cpu, edt); + return edt; +} + +/* + * Print scheduling while atomic bug: + */ +static noinline void __schedule_bug(struct task_struct *prev) +{ + if (oops_in_progress) + return; + + 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); +#ifdef CONFIG_DEBUG_PREEMPT + if (in_atomic_preempt_off()) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif + dump_stack(); + add_taint(TAINT_WARN, LOCKDEP_STILL_OK); +} + +/* + * Various schedule()-time debugging checks and statistics: + */ +static inline void schedule_debug(struct task_struct *prev) +{ +#ifdef CONFIG_SCHED_STACK_END_CHECK + if (task_stack_end_corrupted(prev)) + panic("corrupted stack end detected inside scheduler\n"); +#endif + + if (unlikely(in_atomic_preempt_off())) { + __schedule_bug(prev); + preempt_count_set(PREEMPT_DISABLED); + } + rcu_sleep_check(); + + profile_hit(SCHED_PROFILING, __builtin_return_address(0)); + + schedstat_inc(this_rq(), sched_count); +} + +/* + * The currently running task's information is all stored in rq local data + * which is only modified by the local CPU, thereby allowing the data to be + * changed without grabbing the grq lock. + */ +static inline void set_rq_task(struct rq *rq, struct task_struct *p) +{ + rq->rq_time_slice = p->time_slice; + rq->rq_deadline = p->deadline; + rq->rq_last_ran = p->last_ran = rq->clock_task; + rq->rq_policy = p->policy; + rq->rq_prio = p->prio; +#ifdef CONFIG_SMT_NICE + rq->rq_mm = p->mm; + rq->rq_smt_bias = p->smt_bias; +#endif + if (p != rq->idle) + rq->rq_running = true; + else + rq->rq_running = false; +} + +static void reset_rq_task(struct rq *rq, struct task_struct *p) +{ + rq->rq_policy = p->policy; + rq->rq_prio = p->prio; +#ifdef CONFIG_SMT_NICE + rq->rq_smt_bias = p->smt_bias; +#endif +} + +#ifdef CONFIG_SMT_NICE +static void check_no_siblings(struct rq __maybe_unused *this_rq) {} +static void wake_no_siblings(struct rq __maybe_unused *this_rq) {} +static void (*check_siblings)(struct rq *this_rq) = &check_no_siblings; +static void (*wake_siblings)(struct rq *this_rq) = &wake_no_siblings; + +/* Iterate over smt siblings when we've scheduled a process on cpu and decide + * whether they should continue running or be descheduled. */ +static void check_smt_siblings(struct rq *this_rq) +{ + int other_cpu; + + for_each_cpu(other_cpu, &this_rq->thread_mask) { + struct task_struct *p; + struct rq *rq; + + rq = cpu_rq(other_cpu); + if (rq_idle(rq)) + continue; + if (!rq->online) + continue; + p = rq->curr; + if (!smt_should_schedule(p, this_rq)) { + set_tsk_need_resched(p); + smp_send_reschedule(other_cpu); + } + } +} + +static void wake_smt_siblings(struct rq *this_rq) +{ + int other_cpu; + + if (!queued_notrunning()) + return; + + for_each_cpu(other_cpu, &this_rq->thread_mask) { + struct rq *rq; + + rq = cpu_rq(other_cpu); + if (rq_idle(rq)) { + struct task_struct *p = rq->curr; + + set_tsk_need_resched(p); + smp_send_reschedule(other_cpu); + } + } +} +#else +static void check_siblings(struct rq __maybe_unused *this_rq) {} +static void wake_siblings(struct rq __maybe_unused *this_rq) {} +#endif + +/* + * schedule() is the main scheduler function. + * + * The main means of driving the scheduler and thus entering this function are: + * + * 1. Explicit blocking: mutex, semaphore, waitqueue, etc. + * + * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return + * paths. For example, see arch/x86/entry_64.S. + * + * To drive preemption between tasks, the scheduler sets the flag in timer + * interrupt handler scheduler_tick(). + * + * 3. Wakeups don't really cause entry into schedule(). They add a + * task to the run-queue and that's it. + * + * Now, if the new task added to the run-queue preempts the current + * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets + * called on the nearest possible occasion: + * + * - If the kernel is preemptible (CONFIG_PREEMPT=y): + * + * - in syscall or exception context, at the next outmost + * preempt_enable(). (this might be as soon as the wake_up()'s + * spin_unlock()!) + * + * - in IRQ context, return from interrupt-handler to + * preemptible context + * + * - If the kernel is not preemptible (CONFIG_PREEMPT is not set) + * then at the next: + * + * - cond_resched() call + * - explicit schedule() call + * - return from syscall or exception to user-space + * - return from interrupt-handler to user-space + * + * WARNING: must be called with preemption disabled! + */ +static void __sched notrace __schedule(bool preempt) +{ + struct task_struct *prev, *next, *idle; + unsigned long *switch_count; + bool deactivate = false; + struct rq *rq; + int cpu; + + cpu = smp_processor_id(); + rq = cpu_rq(cpu); + prev = rq->curr; + + /* + * do_exit() calls schedule() with preemption disabled as an exception; + * however we must fix that up, otherwise the next task will see an + * inconsistent (higher) preempt count. + * + * It also avoids the below schedule_debug() test from complaining + * about this. + */ + if (unlikely(prev->state == TASK_DEAD)) + preempt_enable_no_resched_notrace(); + + schedule_debug(prev); + + local_irq_disable(); + rcu_note_context_switch(); + + /* + * Make sure that signal_pending_state()->signal_pending() below + * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE) + * done by the caller to avoid the race with signal_wake_up(). + */ + smp_mb__before_spinlock(); + grq_lock(); + + switch_count = &prev->nivcsw; + if (!preempt && prev->state) { + if (unlikely(signal_pending_state(prev->state, prev))) { + prev->state = TASK_RUNNING; + } else { + deactivate = true; + prev->on_rq = 0; + + /* + * If a worker is going to sleep, notify and + * ask workqueue whether it wants to wake up a + * task to maintain concurrency. If so, wake + * up the task. + */ + if (prev->flags & PF_WQ_WORKER) { + struct task_struct *to_wakeup; + + to_wakeup = wq_worker_sleeping(prev); + if (to_wakeup) { + /* This shouldn't happen, but does */ + if (unlikely(to_wakeup == prev)) + deactivate = false; + else + try_to_wake_up_local(to_wakeup); + } + } + } + switch_count = &prev->nvcsw; + } + + update_clocks(rq); + update_cpu_clock_switch(rq, prev); + if (rq->clock - rq->last_tick > HALF_JIFFY_NS) + rq->dither = false; + else + rq->dither = true; + + clear_tsk_need_resched(prev); + clear_preempt_need_resched(); + + idle = rq->idle; + if (idle != prev) { + /* Update all the information stored on struct rq */ + prev->time_slice = rq->rq_time_slice; + prev->deadline = rq->rq_deadline; + check_deadline(prev); + prev->last_ran = rq->clock_task; + + /* Task changed affinity off this CPU */ + if (likely(!needs_other_cpu(prev, cpu))) { + if (!deactivate) { + if (!queued_notrunning()) { + /* + * We now know prev is the only thing that is + * awaiting CPU so we can bypass rechecking for + * the earliest deadline task and just run it + * again. + */ + set_rq_task(rq, prev); + check_siblings(rq); + grq_unlock_irq(); + goto rerun_prev_unlocked; + } else + swap_sticky(rq, cpu, prev); + } + } + return_task(prev, rq, deactivate); + } + + if (unlikely(!queued_notrunning())) { + /* + * This CPU is now truly idle as opposed to when idle is + * scheduled as a high priority task in its own right. + */ + next = idle; + schedstat_inc(rq, sched_goidle); + set_cpuidle_map(cpu); + } else { + next = earliest_deadline_task(rq, cpu, idle); + if (likely(next->prio != PRIO_LIMIT)) + clear_cpuidle_map(cpu); + else + set_cpuidle_map(cpu); + } + + if (likely(prev != next)) { + /* + * Don't reschedule an idle task or deactivated tasks + */ + if (prev != idle && !deactivate) + resched_suitable_idle(prev); + /* + * Don't stick tasks when a real time task is going to run as + * they may literally get stuck. + */ + if (rt_task(next)) + unstick_task(rq, prev); + set_rq_task(rq, next); + if (next != idle) + check_siblings(rq); + else + wake_siblings(rq); + grq.nr_switches++; + prev->on_cpu = false; + next->on_cpu = true; + rq->curr = next; + ++*switch_count; + + trace_sched_switch(preempt, prev, next); + rq = context_switch(rq, prev, next); /* unlocks the grq */ + cpu = cpu_of(rq); + idle = rq->idle; + } else { + check_siblings(rq); + grq_unlock_irq(); + } + +rerun_prev_unlocked: + return; +} + +static inline void sched_submit_work(struct task_struct *tsk) +{ + if (!tsk->state || tsk_is_pi_blocked(tsk) || + preempt_count() || + signal_pending_state(tsk->state, tsk)) + return; + + /* + * If we are going to sleep and we have plugged IO queued, + * make sure to submit it to avoid deadlocks. + */ + if (blk_needs_flush_plug(tsk)) + blk_schedule_flush_plug(tsk); +} + +asmlinkage __visible void __sched schedule(void) +{ + struct task_struct *tsk = current; + + sched_submit_work(tsk); + do { + preempt_disable(); + __schedule(false); + sched_preempt_enable_no_resched(); + } while (need_resched()); +} + +EXPORT_SYMBOL(schedule); + +#ifdef CONFIG_CONTEXT_TRACKING +asmlinkage __visible void __sched schedule_user(void) +{ + /* + * If we come here after a random call to set_need_resched(), + * or we have been woken up remotely but the IPI has not yet arrived, + * we haven't yet exited the RCU idle mode. Do it here manually until + * we find a better solution. + * + * NB: There are buggy callers of this function. Ideally we + * should warn if prev_state != IN_USER, but that will trigger + * too frequently to make sense yet. + */ + enum ctx_state prev_state = exception_enter(); + schedule(); + exception_exit(prev_state); +} +#endif + +/** + * schedule_preempt_disabled - called with preemption disabled + * + * Returns with preemption disabled. Note: preempt_count must be 1 + */ +void __sched schedule_preempt_disabled(void) +{ + sched_preempt_enable_no_resched(); + schedule(); + preempt_disable(); +} + +static void __sched notrace preempt_schedule_common(void) +{ + do { + /* + * Because the function tracer can trace preempt_count_sub() + * and it also uses preempt_enable/disable_notrace(), if + * NEED_RESCHED is set, the preempt_enable_notrace() called + * by the function tracer will call this function again and + * cause infinite recursion. + * + * Preemption must be disabled here before the function + * tracer can trace. Break up preempt_disable() into two + * calls. One to disable preemption without fear of being + * traced. The other to still record the preemption latency, + * which can also be traced by the function tracer. + */ + preempt_disable_notrace(); + preempt_latency_start(1); + __schedule(true); + preempt_latency_stop(1); + preempt_enable_no_resched_notrace(); + + /* + * Check again in case we missed a preemption opportunity + * between schedule and now. + */ + } while (need_resched()); +} + +#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 __visible void __sched notrace preempt_schedule(void) +{ + /* + * 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(!preemptible())) + return; + + preempt_schedule_common(); +} +NOKPROBE_SYMBOL(preempt_schedule); +EXPORT_SYMBOL(preempt_schedule); + +/** + * preempt_schedule_notrace - preempt_schedule called by tracing + * + * The tracing infrastructure uses preempt_enable_notrace to prevent + * recursion and tracing preempt enabling caused by the tracing + * infrastructure itself. But as tracing can happen in areas coming + * from userspace or just about to enter userspace, a preempt enable + * can occur before user_exit() is called. This will cause the scheduler + * to be called when the system is still in usermode. + * + * To prevent this, the preempt_enable_notrace will use this function + * instead of preempt_schedule() to exit user context if needed before + * calling the scheduler. + */ +asmlinkage __visible void __sched notrace preempt_schedule_notrace(void) +{ + enum ctx_state prev_ctx; + + if (likely(!preemptible())) + return; + + do { + /* + * Because the function tracer can trace preempt_count_sub() + * and it also uses preempt_enable/disable_notrace(), if + * NEED_RESCHED is set, the preempt_enable_notrace() called + * by the function tracer will call this function again and + * cause infinite recursion. + * + * Preemption must be disabled here before the function + * tracer can trace. Break up preempt_disable() into two + * calls. One to disable preemption without fear of being + * traced. The other to still record the preemption latency, + * which can also be traced by the function tracer. + */ + preempt_disable_notrace(); + preempt_latency_start(1); + /* + * Needs preempt disabled in case user_exit() is traced + * and the tracer calls preempt_enable_notrace() causing + * an infinite recursion. + */ + prev_ctx = exception_enter(); + __schedule(true); + exception_exit(prev_ctx); + + preempt_latency_stop(1); + preempt_enable_no_resched_notrace(); + } while (need_resched()); +} +EXPORT_SYMBOL_GPL(preempt_schedule_notrace); + +#endif /* CONFIG_PREEMPT */ + +/* + * 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 __visible void __sched preempt_schedule_irq(void) +{ + enum ctx_state prev_state; + + /* Catch callers which need to be fixed */ + BUG_ON(preempt_count() || !irqs_disabled()); + + prev_state = exception_enter(); + + do { + preempt_disable(); + local_irq_enable(); + __schedule(true); + local_irq_disable(); + sched_preempt_enable_no_resched(); + } while (need_resched()); + + exception_exit(prev_state); +} + +int default_wake_function(wait_queue_t *curr, unsigned mode, int wake_flags, + void *key) +{ + return try_to_wake_up(curr->private, mode, wake_flags); +} +EXPORT_SYMBOL(default_wake_function); + +#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. Call site only calls if the priority of the task changed. + */ +void rt_mutex_setprio(struct task_struct *p, int prio) +{ + unsigned long flags; + int queued, oldprio; + struct rq *rq; + + BUG_ON(prio < 0 || prio > MAX_PRIO); + + rq = task_grq_lock(p, &flags); + + /* + * Idle task boosting is a nono in general. There is one + * exception, when PREEMPT_RT and NOHZ is active: + * + * The idle task calls get_next_timer_interrupt() and holds + * the timer wheel base->lock on the CPU and another CPU wants + * to access the timer (probably to cancel it). We can safely + * ignore the boosting request, as the idle CPU runs this code + * with interrupts disabled and will complete the lock + * protected section without being interrupted. So there is no + * real need to boost. + */ + if (unlikely(p == rq->idle)) { + WARN_ON(p != rq->curr); + WARN_ON(p->pi_blocked_on); + goto out_unlock; + } + + trace_sched_pi_setprio(p, prio); + oldprio = p->prio; + queued = task_queued(p); + if (queued) + dequeue_task(p); + p->prio = prio; + if (task_running(p) && prio > oldprio) + resched_task(p); + if (queued) { + enqueue_task(p, rq); + try_preempt(p, rq); + } + +out_unlock: + task_grq_unlock(&flags); +} + +#endif + +/* + * Adjust the deadline for when the priority is to change, before it's + * changed. + */ +static inline void adjust_deadline(struct task_struct *p, int new_prio) +{ + p->deadline += static_deadline_diff(new_prio) - task_deadline_diff(p); +} + +void set_user_nice(struct task_struct *p, long nice) +{ + int queued, new_static, old_static; + unsigned long flags; + struct rq *rq; + + if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE) + return; + new_static = NICE_TO_PRIO(nice); + /* + * We have to be careful, if called from sys_setpriority(), + * the task might be in the middle of scheduling on another CPU. + */ + rq = time_task_grq_lock(p, &flags); + /* + * 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 + * not SCHED_NORMAL/SCHED_BATCH: + */ + if (has_rt_policy(p)) { + p->static_prio = new_static; + goto out_unlock; + } + queued = task_queued(p); + if (queued) + dequeue_task(p); + + adjust_deadline(p, new_static); + old_static = p->static_prio; + p->static_prio = new_static; + p->prio = effective_prio(p); + + if (queued) { + enqueue_task(p, rq); + if (new_static < old_static) + try_preempt(p, rq); + } else if (task_running(p)) { + reset_rq_task(rq, p); + if (old_static < new_static) + resched_task(p); + } +out_unlock: + task_grq_unlock(&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 = nice_to_rlimit(nice); + + return (nice_rlim <= task_rlimit(p, RLIMIT_NICE) || + 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. + */ + + increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH); + nice = task_nice(current) + increment; + + nice = clamp_val(nice, MIN_NICE, MAX_NICE); + if (increment < 0 && !can_nice(current, nice)) + return -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. + * + * Return: The priority value as seen by users in /proc. + * RT tasks are offset by -100. Normal tasks are centered around 1, value goes + * from 0 (SCHED_ISO) up to 82 (nice +19 SCHED_IDLEPRIO). + */ +int task_prio(const struct task_struct *p) +{ + int delta, prio = p->prio - MAX_RT_PRIO; + + /* rt tasks and iso tasks */ + if (prio <= 0) + goto out; + + /* Convert to ms to avoid overflows */ + delta = NS_TO_MS(p->deadline - grq.niffies); + delta = delta * 40 / ms_longest_deadline_diff(); + if (delta > 0 && delta <= 80) + prio += delta; + if (idleprio_task(p)) + prio += 40; +out: + return prio; +} + +/** + * idle_cpu - is a given cpu idle currently? + * @cpu: the processor in question. + * + * Return: 1 if the CPU is currently idle. 0 otherwise. + */ +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. + * + * Return: The idle task for the cpu @cpu. + */ +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. + * + * The task of @pid, if found. %NULL otherwise. + */ +static inline struct task_struct *find_process_by_pid(pid_t pid) +{ + return pid ? find_task_by_vpid(pid) : current; +} + +/* Actually do priority change: must hold grq lock. */ +static void __setscheduler(struct task_struct *p, struct rq *rq, int policy, + int prio, bool keep_boost) +{ + int oldrtprio, oldprio; + + p->policy = policy; + oldrtprio = p->rt_priority; + p->rt_priority = prio; + p->normal_prio = normal_prio(p); + oldprio = p->prio; + /* + * Keep a potential priority boosting if called from + * sched_setscheduler(). + */ + if (keep_boost) { + /* + * Take priority boosted tasks into account. If the new + * effective priority is unchanged, we just store the new + * normal parameters and do not touch the scheduler class and + * the runqueue. This will be done when the task deboost + * itself. + */ + p->prio = rt_mutex_get_effective_prio(p, p->normal_prio); + } else + p->prio = p->normal_prio; + if (task_running(p)) { + reset_rq_task(rq, p); + /* Resched only if we might now be preempted */ + if (p->prio > oldprio || p->rt_priority > oldrtprio) + resched_task(p); + } +} + +/* + * check the target process has a UID that matches the current process's + */ +static bool check_same_owner(struct task_struct *p) +{ + const struct cred *cred = current_cred(), *pcred; + bool match; + + rcu_read_lock(); + pcred = __task_cred(p); + match = (uid_eq(cred->euid, pcred->euid) || + uid_eq(cred->euid, pcred->uid)); + rcu_read_unlock(); + return match; +} + +static int +__sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param, bool user, bool pi) +{ + struct sched_param zero_param = { .sched_priority = 0 }; + int queued, retval, oldpolicy = -1; + unsigned long flags, rlim_rtprio = 0; + int reset_on_fork; + struct rq *rq; + + /* may grab non-irq protected spin_locks */ + BUG_ON(in_interrupt()); + + if (is_rt_policy(policy) && !capable(CAP_SYS_NICE)) { + unsigned long lflags; + + if (!lock_task_sighand(p, &lflags)) + return -ESRCH; + rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO); + unlock_task_sighand(p, &lflags); + if (rlim_rtprio) + goto recheck; + /* + * If the caller requested an RT policy without having the + * necessary rights, we downgrade the policy to SCHED_ISO. + * We also set the parameter to zero to pass the checks. + */ + policy = SCHED_ISO; + param = &zero_param; + } +recheck: + /* double check policy once rq lock held */ + if (policy < 0) { + reset_on_fork = p->sched_reset_on_fork; + policy = oldpolicy = p->policy; + } else { + reset_on_fork = !!(policy & SCHED_RESET_ON_FORK); + policy &= ~SCHED_RESET_ON_FORK; + + if (!SCHED_RANGE(policy)) + return -EINVAL; + } + + /* + * Valid priorities for SCHED_FIFO and SCHED_RR are + * 1..MAX_USER_RT_PRIO-1, valid priority for SCHED_NORMAL and + * SCHED_BATCH 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 (is_rt_policy(policy) != (param->sched_priority != 0)) + return -EINVAL; + + /* + * Allow unprivileged RT tasks to decrease priority: + */ + if (user && !capable(CAP_SYS_NICE)) { + if (is_rt_policy(policy)) { + unsigned long rlim_rtprio = + task_rlimit(p, RLIMIT_RTPRIO); + + /* 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; + } else { + switch (p->policy) { + /* + * Can only downgrade policies but not back to + * SCHED_NORMAL + */ + case SCHED_ISO: + if (policy == SCHED_ISO) + goto out; + if (policy == SCHED_NORMAL) + return -EPERM; + break; + case SCHED_BATCH: + if (policy == SCHED_BATCH) + goto out; + if (policy != SCHED_IDLEPRIO) + return -EPERM; + break; + case SCHED_IDLEPRIO: + if (policy == SCHED_IDLEPRIO) + goto out; + return -EPERM; + default: + break; + } + } + + /* can't change other user's priorities */ + if (!check_same_owner(p)) + return -EPERM; + + /* Normal users shall not reset the sched_reset_on_fork flag */ + if (p->sched_reset_on_fork && !reset_on_fork) + return -EPERM; + } + + if (user) { + retval = security_task_setscheduler(p); + if (retval) + return retval; + } + + /* + * make sure no PI-waiters arrive (or leave) while we are + * changing the priority of the task: + */ + raw_spin_lock_irqsave(&p->pi_lock, flags); + /* + * To be able to change p->policy safely, the grunqueue lock must be + * held. + */ + rq = __task_grq_lock(p); + + /* + * Changing the policy of the stop threads its a very bad idea + */ + if (p == rq->stop) { + __task_grq_unlock(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + return -EINVAL; + } + + /* + * If not changing anything there's no need to proceed further: + */ + if (unlikely(policy == p->policy && (!is_rt_policy(policy) || + param->sched_priority == p->rt_priority))) { + + __task_grq_unlock(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + return 0; + } + + /* recheck policy now with rq lock held */ + if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) { + policy = oldpolicy = -1; + __task_grq_unlock(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + goto recheck; + } + update_clocks(rq); + p->sched_reset_on_fork = reset_on_fork; + + queued = task_queued(p); + if (queued) + dequeue_task(p); + __setscheduler(p, rq, policy, param->sched_priority, pi); + if (queued) { + enqueue_task(p, rq); + try_preempt(p, rq); + } + __task_grq_unlock(); + raw_spin_unlock_irqrestore(&p->pi_lock, flags); + + if (pi) + rt_mutex_adjust_pi(p); +out: + 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. + * + * Return: 0 on success. An error code otherwise. + * + * NOTE that the task may be already dead. + */ +int sched_setscheduler(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return __sched_setscheduler(p, policy, param, true, true); +} + +EXPORT_SYMBOL_GPL(sched_setscheduler); + +int sched_setattr(struct task_struct *p, const struct sched_attr *attr) +{ + const struct sched_param param = { .sched_priority = attr->sched_priority }; + int policy = attr->sched_policy; + + return __sched_setscheduler(p, policy, ¶m, true, true); +} +EXPORT_SYMBOL_GPL(sched_setattr); + +/** + * 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. + * + * Return: 0 on success. An error code otherwise. + */ +int sched_setscheduler_nocheck(struct task_struct *p, int policy, + const struct sched_param *param) +{ + return __sched_setscheduler(p, policy, param, false, true); +} +EXPORT_SYMBOL_GPL(sched_setscheduler_nocheck); + +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; +} + +/* + * Mimics kernel/events/core.c perf_copy_attr(). + */ +static int sched_copy_attr(struct sched_attr __user *uattr, + struct sched_attr *attr) +{ + u32 size; + int ret; + + if (!access_ok(VERIFY_WRITE, uattr, SCHED_ATTR_SIZE_VER0)) + return -EFAULT; + + /* + * zero the full structure, so that a short copy will be nice. + */ + memset(attr, 0, sizeof(*attr)); + + ret = get_user(size, &uattr->size); + if (ret) + return ret; + + if (size > PAGE_SIZE) /* silly large */ + goto err_size; + + if (!size) /* abi compat */ + size = SCHED_ATTR_SIZE_VER0; + + if (size < SCHED_ATTR_SIZE_VER0) + goto err_size; + + /* + * If we're handed a bigger struct than we know of, + * ensure all the unknown bits are 0 - i.e. new + * user-space does not rely on any kernel feature + * extensions we dont know about yet. + */ + if (size > sizeof(*attr)) { + unsigned char __user *addr; + unsigned char __user *end; + unsigned char val; + + addr = (void __user *)uattr + sizeof(*attr); + end = (void __user *)uattr + size; + + for (; addr < end; addr++) { + ret = get_user(val, addr); + if (ret) + return ret; + if (val) + goto err_size; + } + size = sizeof(*attr); + } + + ret = copy_from_user(attr, uattr, size); + if (ret) + return -EFAULT; + + /* + * XXX: do we want to be lenient like existing syscalls; or do we want + * to be strict and return an error on out-of-bounds values? + */ + attr->sched_nice = clamp(attr->sched_nice, -20, 19); + + /* sched/core.c uses zero here but we already know ret is zero */ + return 0; + +err_size: + put_user(sizeof(*attr), &uattr->size); + return -E2BIG; +} + +/** + * sys_sched_setscheduler - set/change the scheduler policy and RT priority + * @pid: the pid in question. + * @policy: new policy. + * + * Return: 0 on success. An error code otherwise. + * @param: structure containing the new RT priority. + */ +asmlinkage long sys_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); +} + +/* + * sched_setparam() passes in -1 for its policy, to let the functions + * it calls know not to change it. + */ +#define SETPARAM_POLICY -1 + +/** + * sys_sched_setparam - set/change the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the new RT priority. + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param) +{ + return do_sched_setscheduler(pid, SETPARAM_POLICY, param); +} + +/** + * sys_sched_setattr - same as above, but with extended sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + */ +SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, flags) +{ + struct sched_attr attr; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || flags) + return -EINVAL; + + retval = sched_copy_attr(uattr, &attr); + if (retval) + return retval; + + if ((int)attr.sched_policy < 0) + return -EINVAL; + + rcu_read_lock(); + retval = -ESRCH; + p = find_process_by_pid(pid); + if (p != NULL) + retval = sched_setattr(p, &attr); + rcu_read_unlock(); + + return retval; +} + +/** + * sys_sched_getscheduler - get the policy (scheduling class) of a thread + * @pid: the pid in question. + * + * Return: On success, the policy of the thread. Otherwise, a negative error + * code. + */ +SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid) +{ + struct task_struct *p; + int retval = -EINVAL; + + if (pid < 0) + goto out_nounlock; + + retval = -ESRCH; + rcu_read_lock(); + p = find_process_by_pid(pid); + if (p) { + retval = security_task_getscheduler(p); + if (!retval) + retval = p->policy; + } + rcu_read_unlock(); + +out_nounlock: + return retval; +} + +/** + * sys_sched_getscheduler - get the RT priority of a thread + * @pid: the pid in question. + * @param: structure containing the RT priority. + * + * Return: On success, 0 and the RT priority is in @param. Otherwise, an error + * code. + */ +SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param) +{ + struct sched_param lp = { .sched_priority = 0 }; + struct task_struct *p; + int retval = -EINVAL; + + if (!param || pid < 0) + goto out_nounlock; + + rcu_read_lock(); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + if (has_rt_policy(p)) + lp.sched_priority = p->rt_priority; + rcu_read_unlock(); + + /* + * This one might sleep, we cannot do it with a spinlock held ... + */ + retval = copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0; + +out_nounlock: + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +static int sched_read_attr(struct sched_attr __user *uattr, + struct sched_attr *attr, + unsigned int usize) +{ + int ret; + + if (!access_ok(VERIFY_WRITE, uattr, usize)) + return -EFAULT; + + /* + * If we're handed a smaller struct than we know of, + * ensure all the unknown bits are 0 - i.e. old + * user-space does not get uncomplete information. + */ + if (usize < sizeof(*attr)) { + unsigned char *addr; + unsigned char *end; + + addr = (void *)attr + usize; + end = (void *)attr + sizeof(*attr); + + for (; addr < end; addr++) { + if (*addr) + return -EFBIG; + } + + attr->size = usize; + } + + ret = copy_to_user(uattr, attr, attr->size); + if (ret) + return -EFAULT; + + /* sched/core.c uses zero here but we already know ret is zero */ + return ret; +} + +/** + * sys_sched_getattr - similar to sched_getparam, but with sched_attr + * @pid: the pid in question. + * @uattr: structure containing the extended parameters. + * @size: sizeof(attr) for fwd/bwd comp. + * @flags: for future extension. + */ +SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, + unsigned int, size, unsigned int, flags) +{ + struct sched_attr attr = { + .size = sizeof(struct sched_attr), + }; + struct task_struct *p; + int retval; + + if (!uattr || pid < 0 || size > PAGE_SIZE || + size < SCHED_ATTR_SIZE_VER0 || flags) + return -EINVAL; + + rcu_read_lock(); + p = find_process_by_pid(pid); + retval = -ESRCH; + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + attr.sched_policy = p->policy; + if (rt_task(p)) + attr.sched_priority = p->rt_priority; + else + attr.sched_nice = task_nice(p); + + rcu_read_unlock(); + + retval = sched_read_attr(uattr, &attr, size); + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) +{ + cpumask_var_t cpus_allowed, new_mask; + struct task_struct *p; + int retval; + + get_online_cpus(); + rcu_read_lock(); + + p = find_process_by_pid(pid); + if (!p) { + rcu_read_unlock(); + put_online_cpus(); + return -ESRCH; + } + + /* Prevent p going away */ + get_task_struct(p); + rcu_read_unlock(); + + if (p->flags & PF_NO_SETAFFINITY) { + retval = -EINVAL; + goto out_put_task; + } + if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_put_task; + } + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) { + retval = -ENOMEM; + goto out_free_cpus_allowed; + } + retval = -EPERM; + if (!check_same_owner(p)) { + rcu_read_lock(); + if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) { + rcu_read_unlock(); + goto out_unlock; + } + rcu_read_unlock(); + } + + retval = security_task_setscheduler(p); + if (retval) + goto out_unlock; + + cpuset_cpus_allowed(p, cpus_allowed); + cpumask_and(new_mask, in_mask, cpus_allowed); +again: + retval = __set_cpus_allowed_ptr(p, new_mask, true); + + if (!retval) { + cpuset_cpus_allowed(p, cpus_allowed); + if (!cpumask_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 + */ + cpumask_copy(new_mask, cpus_allowed); + goto again; + } + } +out_unlock: + free_cpumask_var(new_mask); +out_free_cpus_allowed: + free_cpumask_var(cpus_allowed); +out_put_task: + 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 + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + cpumask_var_t new_mask; + int retval; + + if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) + return -ENOMEM; + + retval = get_user_cpu_mask(user_mask_ptr, len, new_mask); + if (retval == 0) + retval = sched_setaffinity(pid, new_mask); + free_cpumask_var(new_mask); + return retval; +} + +long sched_getaffinity(pid_t pid, cpumask_t *mask) +{ + struct task_struct *p; + unsigned long flags; + int retval; + + get_online_cpus(); + rcu_read_lock(); + + retval = -ESRCH; + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + grq_lock_irqsave(&flags); + cpumask_and(mask, tsk_cpus_allowed(p), cpu_active_mask); + grq_unlock_irqrestore(&flags); + +out_unlock: + rcu_read_unlock(); + 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 + * + * Return: 0 on success. An error code otherwise. + */ +SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len, + unsigned long __user *, user_mask_ptr) +{ + int ret; + cpumask_var_t mask; + + if ((len * BITS_PER_BYTE) < nr_cpu_ids) + return -EINVAL; + if (len & (sizeof(unsigned long)-1)) + return -EINVAL; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + ret = sched_getaffinity(pid, mask); + if (ret == 0) { + size_t retlen = min_t(size_t, len, cpumask_size()); + + if (copy_to_user(user_mask_ptr, mask, retlen)) + ret = -EFAULT; + else + ret = retlen; + } + free_cpumask_var(mask); + + return ret; +} + +/** + * sys_sched_yield - yield the current processor to other threads. + * + * This function yields the current CPU to other tasks. It does this by + * scheduling away the current task. If it still has the earliest deadline + * it will be scheduled again as the next task. + * + * Return: 0. + */ +SYSCALL_DEFINE0(sched_yield) +{ + struct task_struct *p; + + p = current; + grq_lock_irq(); + schedstat_inc(task_rq(p), yld_count); + requeue_task(p); + + /* + * Since we are going to call schedule() anyway, there's + * no need to preempt or enable interrupts: + */ + __release(grq.lock); + spin_release(&grq.lock.dep_map, 1, _THIS_IP_); + do_raw_spin_unlock(&grq.lock); + sched_preempt_enable_no_resched(); + + schedule(); + + return 0; +} + +int __sched _cond_resched(void) +{ + if (should_resched(0)) { + preempt_schedule_common(); + 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 = should_resched(PREEMPT_LOCK_OFFSET); + int ret = 0; + + lockdep_assert_held(lock); + + if (spin_needbreak(lock) || resched) { + spin_unlock(lock); + if (resched) + preempt_schedule_common(); + 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 (should_resched(SOFTIRQ_DISABLE_OFFSET)) { + local_bh_enable(); + preempt_schedule_common(); + local_bh_disable(); + return 1; + } + return 0; +} +EXPORT_SYMBOL(__cond_resched_softirq); + +/** + * yield - yield the current processor to other threads. + * + * Do not ever use this function, there's a 99% chance you're doing it wrong. + * + * The scheduler is at all times free to pick the calling task as the most + * eligible task to run, if removing the yield() call from your code breaks + * it, its already broken. + * + * Typical broken usage is: + * + * while (!event) + * yield(); + * + * where one assumes that yield() will let 'the other' process run that will + * make event true. If the current task is a SCHED_FIFO task that will never + * happen. Never use yield() as a progress guarantee!! + * + * If you want to use yield() to wait for something, use wait_event(). + * If you want to use yield() to be 'nice' for others, use cond_resched(). + * If you still want to use yield(), do not! + */ +void __sched yield(void) +{ + set_current_state(TASK_RUNNING); + sys_sched_yield(); +} +EXPORT_SYMBOL(yield); + +/** + * yield_to - yield the current processor to another thread in + * your thread group, or accelerate that thread toward the + * processor it's on. + * @p: target task + * @preempt: whether task preemption is allowed or not + * + * It's the caller's job to ensure that the target task struct + * can't go away on us before we can do any checks. + * + * Return: + * true (>0) if we indeed boosted the target task. + * false (0) if we failed to boost the target. + * -ESRCH if there's no task to yield to. + */ +int __sched yield_to(struct task_struct *p, bool preempt) +{ + struct rq *rq, *p_rq; + unsigned long flags; + int yielded = 0; + + rq = this_rq(); + grq_lock_irqsave(&flags); + if (task_running(p) || p->state) { + yielded = -ESRCH; + goto out_unlock; + } + + p_rq = task_rq(p); + yielded = 1; + if (p->deadline > rq->rq_deadline) + p->deadline = rq->rq_deadline; + p->time_slice += rq->rq_time_slice; + rq->rq_time_slice = 0; + if (p->time_slice > timeslice()) + p->time_slice = timeslice(); + if (preempt && rq != p_rq) + resched_curr(p_rq); +out_unlock: + grq_unlock_irqrestore(&flags); + + if (yielded > 0) + schedule(); + return yielded; +} +EXPORT_SYMBOL_GPL(yield_to); + +/* + * 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) + */ + +long __sched io_schedule_timeout(long timeout) +{ + int old_iowait = current->in_iowait; + struct rq *rq; + long ret; + + current->in_iowait = 1; + blk_schedule_flush_plug(current); + + delayacct_blkio_start(); + rq = raw_rq(); + atomic_inc(&rq->nr_iowait); + ret = schedule_timeout(timeout); + current->in_iowait = old_iowait; + atomic_dec(&rq->nr_iowait); + delayacct_blkio_end(); + + return ret; +} +EXPORT_SYMBOL(io_schedule_timeout); + +/** + * sys_sched_get_priority_max - return maximum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the maximum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +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_ISO: + case SCHED_IDLEPRIO: + ret = 0; + break; + } + return ret; +} + +/** + * sys_sched_get_priority_min - return minimum RT priority. + * @policy: scheduling class. + * + * Return: On success, this syscall returns the minimum + * rt_priority that can be used by a given scheduling class. + * On failure, a negative error code is returned. + */ +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_ISO: + case SCHED_IDLEPRIO: + ret = 0; + break; + } + 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. + * + * + * Return: On success, 0 and the timeslice is in @interval. Otherwise, + * an error code. + */ +SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid, + struct timespec __user *, interval) +{ + struct task_struct *p; + unsigned int time_slice; + unsigned long flags; + int retval; + struct timespec t; + + if (pid < 0) + return -EINVAL; + + retval = -ESRCH; + rcu_read_lock(); + p = find_process_by_pid(pid); + if (!p) + goto out_unlock; + + retval = security_task_getscheduler(p); + if (retval) + goto out_unlock; + + grq_lock_irqsave(&flags); + time_slice = p->policy == SCHED_FIFO ? 0 : MS_TO_NS(task_timeslice(p)); + grq_unlock_irqrestore(&flags); + + rcu_read_unlock(); + t = ns_to_timespec(time_slice); + retval = copy_to_user(interval, &t, sizeof(t)) ? -EFAULT : 0; + return retval; + +out_unlock: + rcu_read_unlock(); + return retval; +} + +static const char stat_nam[] = TASK_STATE_TO_CHAR_STR; + +void sched_show_task(struct task_struct *p) +{ + unsigned long free = 0; + int ppid; + unsigned long state = p->state; + + if (state) + state = __ffs(state) + 1; + printk(KERN_INFO "%-15.15s %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 + free = stack_not_used(p); +#endif + ppid = 0; + rcu_read_lock(); + if (pid_alive(p)) + ppid = task_pid_nr(rcu_dereference(p->real_parent)); + rcu_read_unlock(); + printk(KERN_CONT "%5lu %5d %6d 0x%08lx\n", free, + task_pid_nr(p), ppid, + (unsigned long)task_thread_info(p)->flags); + + print_worker_info(KERN_INFO, p); + 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 + rcu_read_lock(); + for_each_process_thread(g, p) { + /* + * reset the NMI-timeout, listing all files on a slow + * console might take a lot of time: + * Also, reset softlockup watchdogs on all CPUs, because + * another CPU might be blocked waiting for us to process + * an IPI. + */ + touch_nmi_watchdog(); + touch_all_softlockup_watchdogs(); + if (!state_filter || (p->state & state_filter)) + sched_show_task(p); + } + + rcu_read_unlock(); + /* + * Only show locks if all tasks are dumped: + */ + if (!state_filter) + debug_show_all_locks(); +} + +void dump_cpu_task(int cpu) +{ + pr_info("Task dump for CPU %d:\n", cpu); + sched_show_task(cpu_curr(cpu)); +} + +#ifdef CONFIG_SMP +void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask) +{ + cpumask_copy(&p->cpus_allowed, new_mask); + p->nr_cpus_allowed = cpumask_weight(new_mask); +} + +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +{ + cpumask_copy(tsk_cpus_allowed(p), new_mask); +} +#endif + +/** + * 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 init_idle(struct task_struct *idle, int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + raw_spin_lock_irqsave(&idle->pi_lock, flags); + time_lock_grq(rq); + idle->last_ran = rq->clock_task; + idle->state = TASK_RUNNING; + /* Setting prio to illegal value shouldn't matter when never queued */ + idle->prio = PRIO_LIMIT; + + kasan_unpoison_task_stack(idle); + +#ifdef CONFIG_SMP + /* + * It's possible that init_idle() gets called multiple times on a task, + * in that case do_set_cpus_allowed() will not do the right thing. + * + * And since this is boot we can forgo the serialisation. + */ + set_cpus_allowed_common(idle, cpumask_of(cpu)); +#ifdef CONFIG_SMT_NICE + idle->smt_bias = 0; +#endif +#endif + set_rq_task(rq, idle); + + /* Silence PROVE_RCU */ + rcu_read_lock(); + set_task_cpu(idle, cpu); + rcu_read_unlock(); + + rq->curr = rq->idle = idle; + idle->on_cpu = 1; + grq_unlock(); + raw_spin_unlock_irqrestore(&idle->pi_lock, flags); + + /* Set the preempt count _outside_ the spinlocks! */ + init_idle_preempt_count(idle, cpu); + + ftrace_graph_init_idle_task(idle, cpu); +#ifdef CONFIG_SMP + sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu); +#endif +} + +int cpuset_cpumask_can_shrink(const struct cpumask __maybe_unused *cur, + const struct cpumask __maybe_unused *trial) +{ + return 1; +} + +int task_can_attach(struct task_struct *p, + const struct cpumask *cs_cpus_allowed) +{ + int ret = 0; + + /* + * Kthreads which disallow setaffinity shouldn't be moved + * to a new cpuset; we don't want to change their cpu + * affinity and isolating such threads by their set of + * allowed nodes is unnecessary. Thus, cpusets are not + * applicable for such threads. This prevents checking for + * success of set_cpus_allowed_ptr() on all attached tasks + * before cpus_allowed may be changed. + */ + if (p->flags & PF_NO_SETAFFINITY) + ret = -EINVAL; + + return ret; +} + +void wake_q_add(struct wake_q_head *head, struct task_struct *task) +{ + struct wake_q_node *node = &task->wake_q; + + /* + * Atomically grab the task, if ->wake_q is !nil already it means + * its already queued (either by us or someone else) and will get the + * wakeup due to that. + * + * This cmpxchg() implies a full barrier, which pairs with the write + * barrier implied by the wakeup in wake_up_q(). + */ + if (cmpxchg(&node->next, NULL, WAKE_Q_TAIL)) + return; + + get_task_struct(task); + + /* + * The head is context local, there can be no concurrency. + */ + *head->lastp = node; + head->lastp = &node->next; +} + +void wake_up_q(struct wake_q_head *head) +{ + struct wake_q_node *node = head->first; + + while (node != WAKE_Q_TAIL) { + struct task_struct *task; + + task = container_of(node, struct task_struct, wake_q); + BUG_ON(!task); + /* task can safely be re-inserted now */ + node = node->next; + task->wake_q.next = NULL; + + /* + * wake_up_process() implies a wmb() to pair with the queueing + * in wake_q_add() so as not to miss wakeups. + */ + wake_up_process(task); + put_task_struct(task); + } +} + +void resched_cpu(int cpu) +{ + unsigned long flags; + + grq_lock_irqsave(&flags); + resched_task(cpu_curr(cpu)); + grq_unlock_irqrestore(&flags); +} + +#ifdef CONFIG_SMP +#ifdef CONFIG_NO_HZ_COMMON +void nohz_balance_enter_idle(int cpu) +{ +} + +void select_nohz_load_balancer(int stop_tick) +{ +} + +void set_cpu_sd_state_idle(void) {} +#if defined(CONFIG_SCHED_MC) || defined(CONFIG_SCHED_SMT) +/** + * lowest_flag_domain - Return lowest sched_domain containing flag. + * @cpu: The cpu whose lowest level of sched domain is to + * be returned. + * @flag: The flag to check for the lowest sched_domain + * for the given cpu. + * + * Returns the lowest sched_domain of a cpu which contains the given flag. + */ +static inline struct sched_domain *lowest_flag_domain(int cpu, int flag) +{ + struct sched_domain *sd; + + for_each_domain(cpu, sd) + if (sd && (sd->flags & flag)) + break; + + return sd; +} + +/** + * for_each_flag_domain - Iterates over sched_domains containing the flag. + * @cpu: The cpu whose domains we're iterating over. + * @sd: variable holding the value of the power_savings_sd + * for cpu. + * @flag: The flag to filter the sched_domains to be iterated. + * + * Iterates over all the scheduler domains for a given cpu that has the 'flag' + * set, starting from the lowest sched_domain to the highest. + */ +#define for_each_flag_domain(cpu, sd, flag) \ + for (sd = lowest_flag_domain(cpu, flag); \ + (sd && (sd->flags & flag)); sd = sd->parent) + +#endif /* (CONFIG_SCHED_MC || CONFIG_SCHED_SMT) */ + +/* + * In the semi idle case, use the nearest busy cpu for migrating timers + * from an idle cpu. This is good for power-savings. + * + * We don't do similar optimization for completely idle system, as + * selecting an idle cpu will add more delays to the timers than intended + * (as that cpu's timer base may not be uptodate wrt jiffies etc). + */ +int get_nohz_timer_target(void) +{ + int i, cpu = smp_processor_id(); + struct sched_domain *sd; + + if (!idle_cpu(cpu) && is_housekeeping_cpu(cpu)) + return cpu; + + rcu_read_lock(); + for_each_domain(cpu, sd) { + for_each_cpu(i, sched_domain_span(sd)) { + if (cpu == i) + continue; + + if (!idle_cpu(i) && is_housekeeping_cpu(i)) { + cpu = i; + cpu = i; + goto unlock; + } + } + } + + if (!is_housekeeping_cpu(cpu)) + cpu = housekeeping_any_cpu(); +unlock: + rcu_read_unlock(); + return cpu; +} + +/* + * 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) +{ + if (cpu == smp_processor_id()) + return; + + set_tsk_need_resched(cpu_rq(cpu)->idle); + smp_send_reschedule(cpu); +} + +void wake_up_nohz_cpu(int cpu) +{ + wake_up_idle_cpu(cpu); +} +#endif /* CONFIG_NO_HZ_COMMON */ + +/* + * 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. + */ +static int __set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask, bool check) +{ + const struct cpumask *cpu_valid_mask = cpu_active_mask; + bool running_wrong = false; + bool queued = false; + unsigned long flags; + struct rq *rq; + int ret = 0; + + rq = task_grq_lock(p, &flags); + + if (p->flags & PF_KTHREAD) { + /* + * Kernel threads are allowed on online && !active CPUs + */ + cpu_valid_mask = cpu_online_mask; + } + + /* + * Must re-check here, to close a race against __kthread_bind(), + * sched_setaffinity() is not guaranteed to observe the flag. + */ + if (check && (p->flags & PF_NO_SETAFFINITY)) { + ret = -EINVAL; + goto out; + } + + if (cpumask_equal(tsk_cpus_allowed(p), new_mask)) + goto out; + + if (!cpumask_intersects(new_mask, cpu_valid_mask)) { + ret = -EINVAL; + goto out; + } + + queued = task_queued(p); + + do_set_cpus_allowed(p, new_mask); + + if (p->flags & PF_KTHREAD) { + /* + * For kernel threads that do indeed end up on online && + * !active we want to ensure they are strict per-cpu threads. + */ + WARN_ON(cpumask_intersects(new_mask, cpu_online_mask) && + !cpumask_intersects(new_mask, cpu_active_mask) && + tsk_nr_cpus_allowed(p) != 1); + } + + /* Can the task run on the task's current CPU? If so, we're done */ + if (cpumask_test_cpu(task_cpu(p), new_mask)) + goto out; + + if (task_running(p)) { + /* Task is running on the wrong cpu now, reschedule it. */ + if (rq == this_rq()) { + set_tsk_need_resched(p); + running_wrong = true; + } else + resched_task(p); + } else + set_task_cpu(p, cpumask_any_and(cpu_valid_mask, new_mask)); + +out: + if (queued) + try_preempt(p, rq); + task_grq_unlock(&flags); + + if (running_wrong) + preempt_schedule_common(); + + return ret; +} + +int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) +{ + return __set_cpus_allowed_ptr(p, new_mask, false); +} +EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); + +static bool sched_smp_initialized __read_mostly; + +#ifdef CONFIG_HOTPLUG_CPU +/* Run through task list and find tasks affined to the dead cpu, then remove + * that cpu from the list, enable cpu0 and set the zerobound flag. */ +static void bind_zero(int src_cpu) +{ + struct task_struct *p, *t; + int bound = 0; + + if (src_cpu == 0) + return; + + do_each_thread(t, p) { + if (cpumask_test_cpu(src_cpu, tsk_cpus_allowed(p))) { + cpumask_clear_cpu(src_cpu, tsk_cpus_allowed(p)); + cpumask_set_cpu(0, tsk_cpus_allowed(p)); + p->zerobound = true; + bound++; + } + clear_sticky(p); + } while_each_thread(t, p); + + if (bound) { + printk(KERN_INFO "Removed affinity for %d processes to cpu %d\n", + bound, src_cpu); + } +} + +/* Find processes with the zerobound flag and reenable their affinity for the + * CPU coming alive. */ +static void unbind_zero(int src_cpu) +{ + int unbound = 0, zerobound = 0; + struct task_struct *p, *t; + + if (src_cpu == 0) + return; + + do_each_thread(t, p) { + if (!p->mm) + p->zerobound = false; + if (p->zerobound) { + unbound++; + cpumask_set_cpu(src_cpu, tsk_cpus_allowed(p)); + /* Once every CPU affinity has been re-enabled, remove + * the zerobound flag */ + if (cpumask_subset(cpu_possible_mask, tsk_cpus_allowed(p))) { + p->zerobound = false; + zerobound++; + } + } + } while_each_thread(t, p); + + if (unbound) { + printk(KERN_INFO "Added affinity for %d processes to cpu %d\n", + unbound, src_cpu); + } + if (zerobound) { + printk(KERN_INFO "Released forced binding to cpu0 for %d processes\n", + zerobound); + } +} + +/* + * 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_irqs_off(mm, &init_mm, current); + finish_arch_post_lock_switch(); + } + mmdrop(mm); +} +#else /* CONFIG_HOTPLUG_CPU */ +static void unbind_zero(int src_cpu) {} +#endif /* CONFIG_HOTPLUG_CPU */ + +void sched_set_stop_task(int cpu, struct task_struct *stop) +{ + struct sched_param stop_param = { .sched_priority = STOP_PRIO }; + struct sched_param start_param = { .sched_priority = 0 }; + struct task_struct *old_stop = cpu_rq(cpu)->stop; + + if (stop) { + /* + * Make it appear like a SCHED_FIFO task, its something + * userspace knows about and won't get confused about. + * + * Also, it will make PI more or less work without too + * much confusion -- but then, stop work should not + * rely on PI working anyway. + */ + sched_setscheduler_nocheck(stop, SCHED_FIFO, &stop_param); + } + + cpu_rq(cpu)->stop = stop; + + if (old_stop) { + /* + * Reset it back to a normal scheduling policy so that + * it can die in pieces. + */ + sched_setscheduler_nocheck(old_stop, SCHED_NORMAL, &start_param); + } +} + +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) + +static struct ctl_table sd_ctl_dir[] = { + { + .procname = "sched_domain", + .mode = 0555, + }, + {} +}; + +static struct ctl_table sd_ctl_root[] = { + { + .procname = "kernel", + .mode = 0555, + .child = sd_ctl_dir, + }, + {} +}; + +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; +} + +#define CPU_LOAD_IDX_MAX 5 +static int min_load_idx = 0; +static int max_load_idx = CPU_LOAD_IDX_MAX-1; + +static void +set_table_entry(struct ctl_table *entry, + const char *procname, void *data, int maxlen, + umode_t mode, proc_handler *proc_handler, + bool load_idx) +{ + entry->procname = procname; + entry->data = data; + entry->maxlen = maxlen; + entry->mode = mode; + entry->proc_handler = proc_handler; + + if (load_idx) { + entry->extra1 = &min_load_idx; + entry->extra2 = &max_load_idx; + } +} + +static struct ctl_table * +sd_alloc_ctl_domain_table(struct sched_domain *sd) +{ + struct ctl_table *table = sd_alloc_ctl_entry(14); + + if (table == NULL) + return NULL; + + set_table_entry(&table[0], "min_interval", &sd->min_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[1], "max_interval", &sd->max_interval, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[2], "busy_idx", &sd->busy_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[3], "idle_idx", &sd->idle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[4], "newidle_idx", &sd->newidle_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[5], "wake_idx", &sd->wake_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[6], "forkexec_idx", &sd->forkexec_idx, + sizeof(int), 0644, proc_dointvec_minmax, true); + set_table_entry(&table[7], "busy_factor", &sd->busy_factor, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[8], "imbalance_pct", &sd->imbalance_pct, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[9], "cache_nice_tries", + &sd->cache_nice_tries, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[10], "flags", &sd->flags, + sizeof(int), 0644, proc_dointvec_minmax, false); + set_table_entry(&table[11], "max_newidle_lb_cost", + &sd->max_newidle_lb_cost, + sizeof(long), 0644, proc_doulongvec_minmax, false); + set_table_entry(&table[12], "name", sd->name, + CORENAME_MAX_SIZE, 0444, proc_dostring, false); + /* &table[13] is terminator */ + + return table; +} + +static struct 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; +void register_sched_domain_sysctl(void) +{ + int i, cpu_num = num_possible_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_possible_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 */ +void unregister_sched_domain_sysctl(void) +{ + 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); +} +#endif /* CONFIG_SYSCTL */ + +static void set_rq_online(struct rq *rq) +{ + if (!rq->online) { + cpumask_set_cpu(cpu_of(rq), rq->rd->online); + rq->online = true; + } +} + +static void set_rq_offline(struct rq *rq) +{ + if (rq->online) { + cpumask_clear_cpu(cpu_of(rq), rq->rd->online); + rq->online = false; + } +} + +static cpumask_var_t sched_domains_tmpmask; /* sched_domains_mutex */ + +#ifdef CONFIG_SCHED_DEBUG + +static __read_mostly int sched_debug_enabled; + +static int __init sched_debug_setup(char *str) +{ + sched_debug_enabled = 1; + + return 0; +} +early_param("sched_debug", sched_debug_setup); + +static inline bool sched_debug(void) +{ + return sched_debug_enabled; +} + +static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level, + struct cpumask *groupmask) +{ + cpumask_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 %*pbl level %s\n", + cpumask_pr_args(sched_domain_span(sd)), sd->name); + + if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) { + printk(KERN_ERR "ERROR: domain->span does not contain " + "CPU%d\n", cpu); + } + + printk(KERN_CONT "\n"); + + if (!cpumask_equal(sched_domain_span(sd), groupmask)) + printk(KERN_ERR "ERROR: groups don't span domain->span\n"); + + if (sd->parent && + !cpumask_subset(groupmask, sched_domain_span(sd->parent))) + 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) +{ + int level = 0; + + if (!sched_debug_enabled) + return; + + if (!sd) { + printk(KERN_DEBUG "CPU%d attaching NULL sched-domain.\n", cpu); + return; + } + + printk(KERN_DEBUG "CPU%d attaching sched-domain:\n", cpu); + + for (;;) { + if (sched_domain_debug_one(sd, cpu, level, sched_domains_tmpmask)) + break; + level++; + sd = sd->parent; + if (!sd) + break; + } +} +#else /* !CONFIG_SCHED_DEBUG */ +# define sched_domain_debug(sd, cpu) do { } while (0) +static inline bool sched_debug(void) +{ + return false; +} +#endif /* CONFIG_SCHED_DEBUG */ + +static int sd_degenerate(struct sched_domain *sd) +{ + if (cpumask_weight(sched_domain_span(sd)) == 1) + return 1; + + /* Following flags don't use groups */ + if (sd->flags & (SD_WAKE_AFFINE)) + 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 (!cpumask_equal(sched_domain_span(sd), sched_domain_span(parent))) + return 0; + + if (~cflags & pflags) + return 0; + + return 1; +} + +static void free_rootdomain(struct rcu_head *rcu) +{ + struct root_domain *rd = container_of(rcu, struct root_domain, rcu); + + cpupri_cleanup(&rd->cpupri); + free_cpumask_var(rd->rto_mask); + free_cpumask_var(rd->online); + free_cpumask_var(rd->span); + kfree(rd); +} + +static void rq_attach_root(struct rq *rq, struct root_domain *rd) +{ + struct root_domain *old_rd = NULL; + unsigned long flags; + + grq_lock_irqsave(&flags); + + if (rq->rd) { + old_rd = rq->rd; + + if (cpumask_test_cpu(rq->cpu, old_rd->online)) + set_rq_offline(rq); + + cpumask_clear_cpu(rq->cpu, old_rd->span); + + /* + * If we dont want to free the old_rd yet then + * set old_rd to NULL to skip the freeing later + * in this function: + */ + if (!atomic_dec_and_test(&old_rd->refcount)) + old_rd = NULL; + } + + atomic_inc(&rd->refcount); + rq->rd = rd; + + cpumask_set_cpu(rq->cpu, rd->span); + if (cpumask_test_cpu(rq->cpu, cpu_active_mask)) + set_rq_online(rq); + + grq_unlock_irqrestore(&flags); + + if (old_rd) + call_rcu_sched(&old_rd->rcu, free_rootdomain); +} + +static int init_rootdomain(struct root_domain *rd) +{ + memset(rd, 0, sizeof(*rd)); + + if (!zalloc_cpumask_var(&rd->span, GFP_KERNEL)) + goto out; + if (!zalloc_cpumask_var(&rd->online, GFP_KERNEL)) + goto free_span; + if (!zalloc_cpumask_var(&rd->rto_mask, GFP_KERNEL)) + goto free_online; + + if (cpupri_init(&rd->cpupri) != 0) + goto free_rto_mask; + return 0; + +free_rto_mask: + free_cpumask_var(rd->rto_mask); +free_online: + free_cpumask_var(rd->online); +free_span: + free_cpumask_var(rd->span); +out: + return -ENOMEM; +} + +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; + + if (init_rootdomain(rd) != 0) { + kfree(rd); + return NULL; + } + + return rd; +} + +static void free_sched_domain(struct rcu_head *rcu) +{ + struct sched_domain *sd = container_of(rcu, struct sched_domain, rcu); + + kfree(sd); +} + +static void destroy_sched_domain(struct sched_domain *sd, int cpu) +{ + call_rcu(&sd->rcu, free_sched_domain); +} + +static void destroy_sched_domains(struct sched_domain *sd, int cpu) +{ + for (; sd; sd = sd->parent) + destroy_sched_domain(sd, cpu); +} + +/* + * 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; + /* + * Transfer SD_PREFER_SIBLING down in case of a + * degenerate parent; the spans match for this + * so the property transfers. + */ + if (parent->flags & SD_PREFER_SIBLING) + tmp->flags |= SD_PREFER_SIBLING; + destroy_sched_domain(parent, cpu); + } else + tmp = tmp->parent; + } + + if (sd && sd_degenerate(sd)) { + tmp = sd; + sd = sd->parent; + destroy_sched_domain(tmp, cpu); + if (sd) + sd->child = NULL; + } + + sched_domain_debug(sd, cpu); + + rq_attach_root(rq, rd); + tmp = rq->sd; + rcu_assign_pointer(rq->sd, sd); + destroy_sched_domains(tmp, cpu); +} + +/* Setup the mask of cpus configured for isolated domains */ +static int __init isolated_cpu_setup(char *str) +{ + int ret; + + alloc_bootmem_cpumask_var(&cpu_isolated_map); + ret = cpulist_parse(str, cpu_isolated_map); + if (ret) { + pr_err("sched: Error, all isolcpus= values must be between 0 and %d\n", nr_cpu_ids); + return 0; + } + return 1; +} + +__setup("isolcpus=", isolated_cpu_setup); + +struct s_data { + struct sched_domain ** __percpu sd; + struct root_domain *rd; +}; + +enum s_alloc { + sa_rootdomain, + sa_sd, + sa_sd_storage, + sa_none, +}; + +/* + * Initializers for schedule domains + * Non-inlined to reduce accumulated stack pressure in build_sched_domains() + */ + +static int default_relax_domain_level = -1; +int sched_domain_level_max; + +static int __init setup_relax_domain_level(char *str) +{ + if (kstrtoint(str, 0, &default_relax_domain_level)) + pr_warn("Unable to set relax_domain_level\n"); + + 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_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } else { + /* turn on idle balance on this domain */ + sd->flags |= (SD_BALANCE_WAKE|SD_BALANCE_NEWIDLE); + } +} + +static void __sdt_free(const struct cpumask *cpu_map); +static int __sdt_alloc(const struct cpumask *cpu_map); + +static void __free_domain_allocs(struct s_data *d, enum s_alloc what, + const struct cpumask *cpu_map) +{ + switch (what) { + case sa_rootdomain: + if (!atomic_read(&d->rd->refcount)) + free_rootdomain(&d->rd->rcu); /* fall through */ + case sa_sd: + free_percpu(d->sd); /* fall through */ + case sa_sd_storage: + __sdt_free(cpu_map); /* fall through */ + case sa_none: + break; + } +} + +static enum s_alloc __visit_domain_allocation_hell(struct s_data *d, + const struct cpumask *cpu_map) +{ + memset(d, 0, sizeof(*d)); + + if (__sdt_alloc(cpu_map)) + return sa_sd_storage; + d->sd = alloc_percpu(struct sched_domain *); + if (!d->sd) + return sa_sd_storage; + d->rd = alloc_rootdomain(); + if (!d->rd) + return sa_sd; + return sa_rootdomain; +} + +/* + * NULL the sd_data elements we've used to build the sched_domain + * structure so that the subsequent __free_domain_allocs() + * will not free the data we're using. + */ +static void claim_allocations(int cpu, struct sched_domain *sd) +{ + struct sd_data *sdd = sd->private; + + WARN_ON_ONCE(*per_cpu_ptr(sdd->sd, cpu) != sd); + *per_cpu_ptr(sdd->sd, cpu) = NULL; +} + +#ifdef CONFIG_NUMA +static int sched_domains_numa_levels; +static int *sched_domains_numa_distance; +static struct cpumask ***sched_domains_numa_masks; +static int sched_domains_curr_level; +#endif + +/* + * SD_flags allowed in topology descriptions. + * + * SD_SHARE_CPUCAPACITY - describes SMT topologies + * SD_SHARE_PKG_RESOURCES - describes shared caches + * SD_NUMA - describes NUMA topologies + * SD_SHARE_POWERDOMAIN - describes shared power domain + * + * Odd one out: + * SD_ASYM_PACKING - describes SMT quirks + */ +#define TOPOLOGY_SD_FLAGS \ + (SD_SHARE_CPUCAPACITY | \ + SD_SHARE_PKG_RESOURCES | \ + SD_NUMA | \ + SD_ASYM_PACKING | \ + SD_SHARE_POWERDOMAIN) + +static struct sched_domain * +sd_init(struct sched_domain_topology_level *tl, int cpu) +{ + struct sched_domain *sd = *per_cpu_ptr(tl->data.sd, cpu); + int sd_weight, sd_flags = 0; + +#ifdef CONFIG_NUMA + /* + * Ugly hack to pass state to sd_numa_mask()... + */ + sched_domains_curr_level = tl->numa_level; +#endif + + sd_weight = cpumask_weight(tl->mask(cpu)); + + if (tl->sd_flags) + sd_flags = (*tl->sd_flags)(); + if (WARN_ONCE(sd_flags & ~TOPOLOGY_SD_FLAGS, + "wrong sd_flags in topology description\n")) + sd_flags &= ~TOPOLOGY_SD_FLAGS; + + *sd = (struct sched_domain){ + .min_interval = sd_weight, + .max_interval = 2*sd_weight, + .busy_factor = 32, + .imbalance_pct = 125, + + .cache_nice_tries = 0, + .busy_idx = 0, + .idle_idx = 0, + .newidle_idx = 0, + .wake_idx = 0, + .forkexec_idx = 0, + + .flags = 1*SD_LOAD_BALANCE + | 1*SD_BALANCE_NEWIDLE + | 1*SD_BALANCE_EXEC + | 1*SD_BALANCE_FORK + | 0*SD_BALANCE_WAKE + | 1*SD_WAKE_AFFINE + | 0*SD_SHARE_CPUCAPACITY + | 0*SD_SHARE_PKG_RESOURCES + | 0*SD_SERIALIZE + | 0*SD_PREFER_SIBLING + | 0*SD_NUMA + | sd_flags + , + + .last_balance = jiffies, + .balance_interval = sd_weight, + .smt_gain = 0, + .max_newidle_lb_cost = 0, + .next_decay_max_lb_cost = jiffies, +#ifdef CONFIG_SCHED_DEBUG + .name = tl->name, +#endif + }; + + /* + * Convert topological properties into behaviour. + */ + + if (sd->flags & SD_SHARE_CPUCAPACITY) { + sd->flags |= SD_PREFER_SIBLING; + sd->imbalance_pct = 110; + sd->smt_gain = 1178; /* ~15% */ + + } else if (sd->flags & SD_SHARE_PKG_RESOURCES) { + sd->imbalance_pct = 117; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + +#ifdef CONFIG_NUMA + } else if (sd->flags & SD_NUMA) { + sd->cache_nice_tries = 2; + sd->busy_idx = 3; + sd->idle_idx = 2; + + sd->flags |= SD_SERIALIZE; + if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) { + sd->flags &= ~(SD_BALANCE_EXEC | + SD_BALANCE_FORK | + SD_WAKE_AFFINE); + } + +#endif + } else { + sd->flags |= SD_PREFER_SIBLING; + sd->cache_nice_tries = 1; + sd->busy_idx = 2; + sd->idle_idx = 1; + } + + sd->private = &tl->data; + + return sd; +} + +/* + * Topology list, bottom-up. + */ +static struct sched_domain_topology_level default_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) }, +#endif +#ifdef CONFIG_SCHED_MC + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + +static struct sched_domain_topology_level *sched_domain_topology = + default_topology; + +#define for_each_sd_topology(tl) \ + for (tl = sched_domain_topology; tl->mask; tl++) + +void set_sched_topology(struct sched_domain_topology_level *tl) +{ + sched_domain_topology = tl; +} + +#ifdef CONFIG_NUMA + +static const struct cpumask *sd_numa_mask(int cpu) +{ + return sched_domains_numa_masks[sched_domains_curr_level][cpu_to_node(cpu)]; +} + +static void sched_numa_warn(const char *str) +{ + static int done = false; + int i,j; + + if (done) + return; + + done = true; + + printk(KERN_WARNING "ERROR: %s\n\n", str); + + for (i = 0; i < nr_node_ids; i++) { + printk(KERN_WARNING " "); + for (j = 0; j < nr_node_ids; j++) + printk(KERN_CONT "%02d ", node_distance(i,j)); + printk(KERN_CONT "\n"); + } + printk(KERN_WARNING "\n"); +} + +static bool find_numa_distance(int distance) +{ + int i; + + if (distance == node_distance(0, 0)) + return true; + + for (i = 0; i < sched_domains_numa_levels; i++) { + if (sched_domains_numa_distance[i] == distance) + return true; + } + + return false; +} + +static void sched_init_numa(void) +{ + int next_distance, curr_distance = node_distance(0, 0); + struct sched_domain_topology_level *tl; + int level = 0; + int i, j, k; + + sched_domains_numa_distance = kzalloc(sizeof(int) * nr_node_ids, GFP_KERNEL); + if (!sched_domains_numa_distance) + return; + + /* + * O(nr_nodes^2) deduplicating selection sort -- in order to find the + * unique distances in the node_distance() table. + * + * Assumes node_distance(0,j) includes all distances in + * node_distance(i,j) in order to avoid cubic time. + */ + next_distance = curr_distance; + for (i = 0; i < nr_node_ids; i++) { + for (j = 0; j < nr_node_ids; j++) { + for (k = 0; k < nr_node_ids; k++) { + int distance = node_distance(i, k); + + if (distance > curr_distance && + (distance < next_distance || + next_distance == curr_distance)) + next_distance = distance; + + /* + * While not a strong assumption it would be nice to know + * about cases where if node A is connected to B, B is not + * equally connected to A. + */ + if (sched_debug() && node_distance(k, i) != distance) + sched_numa_warn("Node-distance not symmetric"); + + if (sched_debug() && i && !find_numa_distance(distance)) + sched_numa_warn("Node-0 not representative"); + } + if (next_distance != curr_distance) { + sched_domains_numa_distance[level++] = next_distance; + sched_domains_numa_levels = level; + curr_distance = next_distance; + } else break; + } + + /* + * In case of sched_debug() we verify the above assumption. + */ + if (!sched_debug()) + break; + } + /* + * 'level' contains the number of unique distances, excluding the + * identity distance node_distance(i,i). + * + * The sched_domains_numa_distance[] array includes the actual distance + * numbers. + */ + + /* + * Here, we should temporarily reset sched_domains_numa_levels to 0. + * If it fails to allocate memory for array sched_domains_numa_masks[][], + * the array will contain less then 'level' members. This could be + * dangerous when we use it to iterate array sched_domains_numa_masks[][] + * in other functions. + * + * We reset it to 'level' at the end of this function. + */ + sched_domains_numa_levels = 0; + + sched_domains_numa_masks = kzalloc(sizeof(void *) * level, GFP_KERNEL); + if (!sched_domains_numa_masks) + return; + + /* + * Now for each level, construct a mask per node which contains all + * cpus of nodes that are that many hops away from us. + */ + for (i = 0; i < level; i++) { + sched_domains_numa_masks[i] = + kzalloc(nr_node_ids * sizeof(void *), GFP_KERNEL); + if (!sched_domains_numa_masks[i]) + return; + + for (j = 0; j < nr_node_ids; j++) { + struct cpumask *mask = kzalloc(cpumask_size(), GFP_KERNEL); + if (!mask) + return; + + sched_domains_numa_masks[i][j] = mask; + + for_each_node(k) { + if (node_distance(j, k) > sched_domains_numa_distance[i]) + continue; + + cpumask_or(mask, mask, cpumask_of_node(k)); + } + } + } + + /* Compute default topology size */ + for (i = 0; sched_domain_topology[i].mask; i++); + + tl = kzalloc((i + level + 1) * + sizeof(struct sched_domain_topology_level), GFP_KERNEL); + if (!tl) + return; + + /* + * Copy the default topology bits.. + */ + for (i = 0; sched_domain_topology[i].mask; i++) + tl[i] = sched_domain_topology[i]; + + /* + * .. and append 'j' levels of NUMA goodness. + */ + for (j = 0; j < level; i++, j++) { + tl[i] = (struct sched_domain_topology_level){ + .mask = sd_numa_mask, + .sd_flags = cpu_numa_flags, + .flags = SDTL_OVERLAP, + .numa_level = j, + SD_INIT_NAME(NUMA) + }; + } + + sched_domain_topology = tl; + + sched_domains_numa_levels = level; +} + +static void sched_domains_numa_masks_set(int cpu) +{ + int node = cpu_to_node(cpu); + int i, j; + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) { + if (node_distance(j, node) <= sched_domains_numa_distance[i]) + cpumask_set_cpu(cpu, sched_domains_numa_masks[i][j]); + } + } +} + +static void sched_domains_numa_masks_clear(int cpu) +{ + int i, j; + + for (i = 0; i < sched_domains_numa_levels; i++) { + for (j = 0; j < nr_node_ids; j++) + cpumask_clear_cpu(cpu, sched_domains_numa_masks[i][j]); + } +} + +#else +static inline void sched_init_numa(void) { } +static void sched_domains_numa_masks_set(unsigned int cpu) { } +static void sched_domains_numa_masks_clear(unsigned int cpu) { } +#endif /* CONFIG_NUMA */ + +static int __sdt_alloc(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + sdd->sd = alloc_percpu(struct sched_domain *); + if (!sdd->sd) + return -ENOMEM; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + + sd = kzalloc_node(sizeof(struct sched_domain) + cpumask_size(), + GFP_KERNEL, cpu_to_node(j)); + if (!sd) + return -ENOMEM; + + *per_cpu_ptr(sdd->sd, j) = sd; + } + } + + return 0; +} + +static void __sdt_free(const struct cpumask *cpu_map) +{ + struct sched_domain_topology_level *tl; + int j; + + for_each_sd_topology(tl) { + struct sd_data *sdd = &tl->data; + + for_each_cpu(j, cpu_map) { + struct sched_domain *sd; + + if (sdd->sd) { + sd = *per_cpu_ptr(sdd->sd, j); + kfree(*per_cpu_ptr(sdd->sd, j)); + } + } + free_percpu(sdd->sd); + sdd->sd = NULL; + } +} + +struct sched_domain *build_sched_domain(struct sched_domain_topology_level *tl, + const struct cpumask *cpu_map, struct sched_domain_attr *attr, + struct sched_domain *child, int cpu) +{ + struct sched_domain *sd = sd_init(tl, cpu); + if (!sd) + return child; + + cpumask_and(sched_domain_span(sd), cpu_map, tl->mask(cpu)); + if (child) { + sd->level = child->level + 1; + sched_domain_level_max = max(sched_domain_level_max, sd->level); + child->parent = sd; + sd->child = child; + + if (!cpumask_subset(sched_domain_span(child), + sched_domain_span(sd))) { + pr_err("BUG: arch topology borken\n"); +#ifdef CONFIG_SCHED_DEBUG + pr_err(" the %s domain not a subset of the %s domain\n", + child->name, sd->name); +#endif + /* Fixup, ensure @sd has at least @child cpus. */ + cpumask_or(sched_domain_span(sd), + sched_domain_span(sd), + sched_domain_span(child)); + } + + } + set_domain_attribute(sd, attr); + + return sd; +} + +/* + * Build sched domains for a given set of cpus and attach the sched domains + * to the individual cpus + */ +static int build_sched_domains(const struct cpumask *cpu_map, + struct sched_domain_attr *attr) +{ + enum s_alloc alloc_state; + struct sched_domain *sd; + struct s_data d; + int i, ret = -ENOMEM; + + alloc_state = __visit_domain_allocation_hell(&d, cpu_map); + if (alloc_state != sa_rootdomain) + goto error; + + /* Set up domains for cpus specified by the cpu_map. */ + for_each_cpu(i, cpu_map) { + struct sched_domain_topology_level *tl; + + sd = NULL; + for_each_sd_topology(tl) { + sd = build_sched_domain(tl, cpu_map, attr, sd, i); + if (tl == sched_domain_topology) + *per_cpu_ptr(d.sd, i) = sd; + if (tl->flags & SDTL_OVERLAP) + sd->flags |= SD_OVERLAP; + if (cpumask_equal(cpu_map, sched_domain_span(sd))) + break; + } + } + + /* Calculate CPU capacity for physical packages and nodes */ + for (i = nr_cpumask_bits-1; i >= 0; i--) { + if (!cpumask_test_cpu(i, cpu_map)) + continue; + + for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) { + claim_allocations(i, sd); + } + } + + /* Attach the domains */ + rcu_read_lock(); + for_each_cpu(i, cpu_map) { + sd = *per_cpu_ptr(d.sd, i); + cpu_attach_domain(sd, d.rd, i); + } + rcu_read_unlock(); + + ret = 0; +error: + __free_domain_allocs(&d, alloc_state, cpu_map); + return ret; +} + +static cpumask_var_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) fails, then fallback to a single sched domain, + * as determined by the single cpumask fallback_doms. + */ +static cpumask_var_t fallback_doms; + +/* + * arch_update_cpu_topology lets virtualized architectures update the + * cpu core maps. It is supposed to return 1 if the topology changed + * or 0 if it stayed the same. + */ +int __weak arch_update_cpu_topology(void) +{ + return 0; +} + +cpumask_var_t *alloc_sched_domains(unsigned int ndoms) +{ + int i; + cpumask_var_t *doms; + + doms = kmalloc(sizeof(*doms) * ndoms, GFP_KERNEL); + if (!doms) + return NULL; + for (i = 0; i < ndoms; i++) { + if (!alloc_cpumask_var(&doms[i], GFP_KERNEL)) { + free_sched_domains(doms, i); + return NULL; + } + } + return doms; +} + +void free_sched_domains(cpumask_var_t doms[], unsigned int ndoms) +{ + unsigned int i; + for (i = 0; i < ndoms; i++) + free_cpumask_var(doms[i]); + kfree(doms); +} + +/* + * 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 init_sched_domains(const struct cpumask *cpu_map) +{ + int err; + + arch_update_cpu_topology(); + ndoms_cur = 1; + doms_cur = alloc_sched_domains(ndoms_cur); + if (!doms_cur) + doms_cur = &fallback_doms; + cpumask_andnot(doms_cur[0], cpu_map, cpu_isolated_map); + err = build_sched_domains(doms_cur[0], NULL); + register_sched_domain_sysctl(); + + return err; +} + +/* + * 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 struct cpumask *cpu_map) +{ + int i; + + rcu_read_lock(); + for_each_cpu(i, cpu_map) + cpu_attach_domain(NULL, &def_root_domain, i); + rcu_read_unlock(); +} + +/* 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_var_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 allocated using + * alloc_sched_domains. This routine takes ownership of it and will + * free_sched_domains it when done with it. If the caller failed the + * alloc 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_mask. + * 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_var_t doms_new[], + struct sched_domain_attr *dattr_new) +{ + int i, j, n; + int new_topology; + + mutex_lock(&sched_domains_mutex); + + /* always unregister in case we don't destroy any domains */ + unregister_sched_domain_sysctl(); + + /* Let architecture update cpu core mappings. */ + new_topology = arch_update_cpu_topology(); + + n = doms_new ? ndoms_new : 0; + + /* Destroy deleted domains */ + for (i = 0; i < ndoms_cur; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_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: + ; + } + + n = ndoms_cur; + if (doms_new == NULL) { + n = 0; + doms_new = &fallback_doms; + cpumask_andnot(doms_new[0], cpu_active_mask, cpu_isolated_map); + WARN_ON_ONCE(dattr_new); + } + + /* Build new domains */ + for (i = 0; i < ndoms_new; i++) { + for (j = 0; j < n && !new_topology; j++) { + if (cpumask_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) + free_sched_domains(doms_cur, ndoms_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); +} + +static int num_cpus_frozen; /* used to mark begin/end of suspend/resume */ + +/* + * Update cpusets according to cpu_active mask. If cpusets are + * disabled, cpuset_update_active_cpus() becomes a simple wrapper + * around partition_sched_domains(). + * + * If we come here as part of a suspend/resume, don't touch cpusets because we + * want to restore it back to its original state upon resume anyway. + */ +static void cpuset_cpu_active(void) +{ + if (cpuhp_tasks_frozen) { + /* + * num_cpus_frozen tracks how many CPUs are involved in suspend + * resume sequence. As long as this is not the last online + * operation in the resume sequence, just build a single sched + * domain, ignoring cpusets. + */ + num_cpus_frozen--; + if (likely(num_cpus_frozen)) { + partition_sched_domains(1, NULL, NULL); + return; + } + /* + * This is the last CPU online operation. So fall through and + * restore the original sched domains by considering the + * cpuset configurations. + */ + } + + cpuset_update_active_cpus(true); +} + +static int cpuset_cpu_inactive(unsigned int cpu) +{ + if (!cpuhp_tasks_frozen) { + cpuset_update_active_cpus(false); + } else { + num_cpus_frozen++; + partition_sched_domains(1, NULL, NULL); + } + return 0; +} + +int sched_cpu_activate(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + set_cpu_active(cpu, true); + + if (sched_smp_initialized) { + sched_domains_numa_masks_set(cpu); + cpuset_cpu_active(); + } + + /* + * Put the rq online, if not already. This happens: + * + * 1) In the early boot process, because we build the real domains + * after all cpus have been brought up. + * + * 2) At runtime, if cpuset_cpu_active() fails to rebuild the + * domains. + */ + grq_lock_irqsave(&flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_online(rq); + } + unbind_zero(cpu); + grq.noc = num_online_cpus(); + grq_unlock_irqrestore(&flags); + + return 0; +} + +int sched_cpu_deactivate(unsigned int cpu) +{ + int ret; + + set_cpu_active(cpu, false); + /* + * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU + * users of this state to go away such that all new such users will + * observe it. + * + * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might + * not imply sync_sched(), so wait for both. + * + * Do sync before park smpboot threads to take care the rcu boost case. + */ + if (IS_ENABLED(CONFIG_PREEMPT)) + synchronize_rcu_mult(call_rcu, call_rcu_sched); + else + synchronize_rcu(); + + if (!sched_smp_initialized) + return 0; + + ret = cpuset_cpu_inactive(cpu); + if (ret) { + set_cpu_active(cpu, true); + return ret; + } + sched_domains_numa_masks_clear(cpu); + return 0; +} + +int sched_cpu_starting(unsigned int __maybe_unused cpu) +{ + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +int sched_cpu_dying(unsigned int cpu) +{ + struct rq *rq = cpu_rq(cpu); + unsigned long flags; + + grq_lock_irqsave(&flags); + if (rq->rd) { + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_offline(rq); + } + bind_zero(cpu); + grq.noc = num_online_cpus(); + grq_unlock_irqrestore(&flags); + + return 0; +} +#endif + +#if defined(CONFIG_SCHED_SMT) || defined(CONFIG_SCHED_MC) +/* + * Cheaper version of the below functions in case support for SMT and MC is + * compiled in but CPUs have no siblings. + */ +static bool sole_cpu_idle(struct rq *rq) +{ + return rq_idle(rq); +} +#endif +#ifdef CONFIG_SCHED_SMT +static const cpumask_t *thread_cpumask(int cpu) +{ + return topology_sibling_cpumask(cpu); +} +/* All this CPU's SMT siblings are idle */ +static bool siblings_cpu_idle(struct rq *rq) +{ + return cpumask_subset(&rq->thread_mask, &grq.cpu_idle_map); +} +#endif +#ifdef CONFIG_SCHED_MC +static const cpumask_t *core_cpumask(int cpu) +{ + return topology_core_cpumask(cpu); +} +/* All this CPU's shared cache siblings are idle */ +static bool cache_cpu_idle(struct rq *rq) +{ + return cpumask_subset(&rq->core_mask, &grq.cpu_idle_map); +} +#endif + +enum sched_domain_level { + SD_LV_NONE = 0, + SD_LV_SIBLING, + SD_LV_MC, + SD_LV_BOOK, + SD_LV_CPU, + SD_LV_NODE, + SD_LV_ALLNODES, + SD_LV_MAX +}; + +void __init sched_init_smp(void) +{ + struct sched_domain *sd; + int cpu, other_cpu; + + cpumask_var_t non_isolated_cpus; + + alloc_cpumask_var(&non_isolated_cpus, GFP_KERNEL); + alloc_cpumask_var(&fallback_doms, GFP_KERNEL); + + sched_init_numa(); + + /* + * There's no userspace yet to cause hotplug operations; hence all the + * cpu masks are stable and all blatant races in the below code cannot + * happen. + */ + mutex_lock(&sched_domains_mutex); + init_sched_domains(cpu_active_mask); + cpumask_andnot(non_isolated_cpus, cpu_possible_mask, cpu_isolated_map); + if (cpumask_empty(non_isolated_cpus)) + cpumask_set_cpu(smp_processor_id(), non_isolated_cpus); + mutex_unlock(&sched_domains_mutex); + + /* Move init over to a non-isolated CPU */ + if (set_cpus_allowed_ptr(current, non_isolated_cpus) < 0) + BUG(); + free_cpumask_var(non_isolated_cpus); + + mutex_lock(&sched_domains_mutex); + grq_lock_irq(); + /* + * Set up the relative cache distance of each online cpu from each + * other in a simple array for quick lookup. Locality is determined + * by the closest sched_domain that CPUs are separated by. CPUs with + * shared cache in SMT and MC are treated as local. Separate CPUs + * (within the same package or physically) within the same node are + * treated as not local. CPUs not even in the same domain (different + * nodes) are treated as very distant. + */ + for_each_online_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + + /* First check if this cpu is in the same node */ + for_each_domain(cpu, sd) { + if (sd->level > SD_LV_NODE) + continue; + /* Set locality to local node if not already found lower */ + for_each_cpu(other_cpu, sched_domain_span(sd)) { + if (rq->cpu_locality[other_cpu] > 3) + rq->cpu_locality[other_cpu] = 3; + } + } + + /* + * Each runqueue has its own function in case it doesn't have + * siblings of its own allowing mixed topologies. + */ +#ifdef CONFIG_SCHED_MC + for_each_cpu(other_cpu, core_cpumask(cpu)) { + if (rq->cpu_locality[other_cpu] > 2) + rq->cpu_locality[other_cpu] = 2; + } + if (cpumask_weight(core_cpumask(cpu)) > 1) { + cpumask_copy(&rq->core_mask, core_cpumask(cpu)); + cpumask_clear_cpu(cpu, &rq->core_mask); + rq->cache_idle = cache_cpu_idle; + } +#endif +#ifdef CONFIG_SCHED_SMT + for_each_cpu(other_cpu, thread_cpumask(cpu)) + rq->cpu_locality[other_cpu] = 1; + if (cpumask_weight(thread_cpumask(cpu)) > 1) { + cpumask_copy(&rq->thread_mask, thread_cpumask(cpu)); + cpumask_clear_cpu(cpu, &rq->thread_mask); + rq->siblings_idle = siblings_cpu_idle; + } +#endif + } +#ifdef CONFIG_SMT_NICE + check_siblings = &check_smt_siblings; + wake_siblings = &wake_smt_siblings; + smt_schedule = &smt_should_schedule; +#endif + grq_unlock_irq(); + mutex_unlock(&sched_domains_mutex); + + for_each_online_cpu(cpu) { + struct rq *rq = cpu_rq(cpu); + for_each_online_cpu(other_cpu) { + if (other_cpu <= cpu) + continue; + printk(KERN_DEBUG "BFS LOCALITY CPU %d to %d: %d\n", cpu, other_cpu, rq->cpu_locality[other_cpu]); + } + } + sched_smp_initialized = true; +} +#else +void __init sched_init_smp(void) +{ +} +#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); +} + +void __init sched_init(void) +{ +#ifdef CONFIG_SMP + int cpu_ids; +#endif + int i; + struct rq *rq; + + prio_ratios[0] = 128; + for (i = 1 ; i < NICE_WIDTH ; i++) + prio_ratios[i] = prio_ratios[i - 1] * 11 / 10; + + raw_spin_lock_init(&grq.lock); + grq.nr_running = grq.nr_uninterruptible = grq.nr_switches = 0; + grq.niffies = 0; + grq.last_jiffy = jiffies; + raw_spin_lock_init(&grq.iso_lock); + grq.iso_ticks = 0; + grq.iso_refractory = false; + grq.noc = 1; + grq.node = skiplist_init(); + grq.sl = new_skiplist(grq.node); + +#ifdef CONFIG_SMP + init_defrootdomain(); + grq.qnr = grq.idle_cpus = 0; + cpumask_clear(&grq.cpu_idle_map); +#else + uprq = &per_cpu(runqueues, 0); +#endif + for_each_possible_cpu(i) { + rq = cpu_rq(i); + rq->grq_lock = &grq.lock; + rq->user_pc = rq->nice_pc = rq->softirq_pc = rq->system_pc = + rq->iowait_pc = rq->idle_pc = 0; + rq->dither = false; +#ifdef CONFIG_SMP + rq->sticky_task = NULL; + rq->last_niffy = 0; + rq->sd = NULL; + rq->rd = NULL; + rq->online = false; + rq->cpu = i; + rq_attach_root(rq, &def_root_domain); +#endif + atomic_set(&rq->nr_iowait, 0); + } + +#ifdef CONFIG_SMP + cpu_ids = i; + /* + * Set the base locality for cpu cache distance calculation to + * "distant" (3). Make sure the distance from a CPU to itself is 0. + */ + for_each_possible_cpu(i) { + int j; + + rq = cpu_rq(i); +#ifdef CONFIG_SCHED_SMT + rq->siblings_idle = sole_cpu_idle; +#endif +#ifdef CONFIG_SCHED_MC + rq->cache_idle = sole_cpu_idle; +#endif + rq->cpu_locality = kmalloc(cpu_ids * sizeof(int *), GFP_ATOMIC); + for_each_possible_cpu(j) { + if (i == j) + rq->cpu_locality[j] = 0; + else + rq->cpu_locality[j] = 4; + } + } +#endif + +#ifdef CONFIG_PREEMPT_NOTIFIERS + INIT_HLIST_HEAD(&init_task.preempt_notifiers); +#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()); + +#ifdef CONFIG_SMP + zalloc_cpumask_var(&sched_domains_tmpmask, GFP_NOWAIT); + /* May be allocated at isolcpus cmdline parse time */ + if (cpu_isolated_map == NULL) + zalloc_cpumask_var(&cpu_isolated_map, GFP_NOWAIT); + idle_thread_set_boot_cpu(); +#endif /* SMP */ + + init_schedstats(); +} + +#ifdef CONFIG_DEBUG_ATOMIC_SLEEP +static inline int preempt_count_equals(int preempt_offset) +{ + int nested = preempt_count() + rcu_preempt_depth(); + + return (nested == preempt_offset); +} + +void __might_sleep(const char *file, int line, int preempt_offset) +{ + /* + * Blocking primitives will set (and therefore destroy) current->state, + * since we will exit with TASK_RUNNING make sure we enter with it, + * otherwise we will destroy state. + */ + WARN_ONCE(current->state != TASK_RUNNING && current->task_state_change, + "do not call blocking ops when !TASK_RUNNING; " + "state=%lx set at [<%p>] %pS\n", + current->state, + (void *)current->task_state_change, + (void *)current->task_state_change); + + ___might_sleep(file, line, preempt_offset); +} +EXPORT_SYMBOL(__might_sleep); + +void ___might_sleep(const char *file, int line, int preempt_offset) +{ + static unsigned long prev_jiffy; /* ratelimiting */ + + rcu_sleep_check(); /* WARN_ON_ONCE() by default, no rate limit reqd. */ + if ((preempt_count_equals(preempt_offset) && !irqs_disabled() && + !is_idle_task(current)) || + system_state != SYSTEM_RUNNING || oops_in_progress) + return; + 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(KERN_ERR + "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n", + in_atomic(), irqs_disabled(), + current->pid, current->comm); + + if (task_stack_end_corrupted(current)) + printk(KERN_EMERG "Thread overran stack, or stack corrupted\n"); + + debug_show_held_locks(current); + if (irqs_disabled()) + print_irqtrace_events(current); +#ifdef CONFIG_DEBUG_PREEMPT + if (!preempt_count_equals(preempt_offset)) { + pr_err("Preemption disabled at:"); + print_ip_sym(current->preempt_disable_ip); + pr_cont("\n"); + } +#endif + dump_stack(); +} +EXPORT_SYMBOL(___might_sleep); +#endif + +#ifdef CONFIG_MAGIC_SYSRQ +static inline void normalise_rt_tasks(void) +{ + struct task_struct *g, *p; + unsigned long flags; + struct rq *rq; + int queued; + + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + /* + * Only normalize user tasks: + */ + if (p->flags & PF_KTHREAD) + continue; + + if (!rt_task(p) && !iso_task(p)) + continue; + + rq = task_grq_lock(p, &flags); + queued = task_queued(p); + if (queued) + dequeue_task(p); + __setscheduler(p, rq, SCHED_NORMAL, 0, false); + if (queued) { + enqueue_task(p, rq); + try_preempt(p, rq); + } + + task_grq_unlock(&flags); + } + read_unlock(&tasklist_lock); +} + +void normalize_rt_tasks(void) +{ + normalise_rt_tasks(); +} +#endif /* CONFIG_MAGIC_SYSRQ */ + +#if defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) +/* + * These functions are only useful for the IA64 MCA handling, or kdb. + * + * 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! + * + * Return: The current task for @cpu. + */ +struct task_struct *curr_task(int cpu) +{ + return cpu_curr(cpu); +} + +#endif /* defined(CONFIG_IA64) || defined(CONFIG_KGDB_KDB) */ + +#ifdef CONFIG_IA64 +/** + * 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 synchronised, 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 + +/* + * Use precise platform statistics if available: + */ +#ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + *ut = p->utime; + *st = p->stime; +} +EXPORT_SYMBOL_GPL(task_cputime_adjusted); + +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + + *ut = cputime.utime; + *st = cputime.stime; +} + +void vtime_account_system_irqsafe(struct task_struct *tsk) +{ + unsigned long flags; + + local_irq_save(flags); + vtime_account_system(tsk); + local_irq_restore(flags); +} +EXPORT_SYMBOL_GPL(vtime_account_system_irqsafe); + +#ifndef __ARCH_HAS_VTIME_TASK_SWITCH +void vtime_task_switch(struct task_struct *prev) +{ + if (is_idle_task(prev)) + vtime_account_idle(prev); + else + vtime_account_system(prev); + + vtime_account_user(prev); + arch_vtime_task_switch(prev); +} +#endif + +#else +/* + * Perform (stime * rtime) / total, but avoid multiplication overflow by + * losing precision when the numbers are big. + */ +static cputime_t scale_stime(u64 stime, u64 rtime, u64 total) +{ + u64 scaled; + + for (;;) { + /* Make sure "rtime" is the bigger of stime/rtime */ + if (stime > rtime) { + u64 tmp = rtime; rtime = stime; stime = tmp; + } + + /* Make sure 'total' fits in 32 bits */ + if (total >> 32) + goto drop_precision; + + /* Does rtime (and thus stime) fit in 32 bits? */ + if (!(rtime >> 32)) + break; + + /* Can we just balance rtime/stime rather than dropping bits? */ + if (stime >> 31) + goto drop_precision; + + /* We can grow stime and shrink rtime and try to make them both fit */ + stime <<= 1; + rtime >>= 1; + continue; + +drop_precision: + /* We drop from rtime, it has more bits than stime */ + rtime >>= 1; + total >>= 1; + } + + /* + * Make sure gcc understands that this is a 32x32->64 multiply, + * followed by a 64/32->64 divide. + */ + scaled = div_u64((u64) (u32) stime * (u64) (u32) rtime, (u32)total); + return (__force cputime_t) scaled; +} + +/* + * Adjust tick based cputime random precision against scheduler + * runtime accounting. + */ +static void cputime_adjust(struct task_cputime *curr, + struct prev_cputime *prev, + cputime_t *ut, cputime_t *st) +{ + cputime_t rtime, stime, utime, total; + + stime = curr->stime; + total = stime + curr->utime; + + /* + * Tick based cputime accounting depend on random scheduling + * timeslices of a task to be interrupted or not by the timer. + * Depending on these circumstances, the number of these interrupts + * may be over or under-optimistic, matching the real user and system + * cputime with a variable precision. + * + * Fix this by scaling these tick based values against the total + * runtime accounted by the CFS scheduler. + */ + rtime = nsecs_to_cputime(curr->sum_exec_runtime); + + /* + * Update userspace visible utime/stime values only if actual execution + * time is bigger than already exported. Note that can happen, that we + * provided bigger values due to scaling inaccuracy on big numbers. + */ + if (prev->stime + prev->utime >= rtime) + goto out; + + if (total) { + stime = scale_stime((__force u64)stime, + (__force u64)rtime, (__force u64)total); + utime = rtime - stime; + } else { + stime = rtime; + utime = 0; + } + + /* + * If the tick based count grows faster than the scheduler one, + * the result of the scaling may go backward. + * Let's enforce monotonicity. + */ + prev->stime = max(prev->stime, stime); + prev->utime = max(prev->utime, utime); + +out: + *ut = prev->utime; + *st = prev->stime; +} + +void task_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime = { + .sum_exec_runtime = tsk_seruntime(p), + }; + + task_cputime(p, &cputime.utime, &cputime.stime); + cputime_adjust(&cputime, &p->prev_cputime, ut, st); +} +EXPORT_SYMBOL_GPL(task_cputime_adjusted); + +/* + * Must be called with siglock held. + */ +void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut, cputime_t *st) +{ + struct task_cputime cputime; + + thread_group_cputime(p, &cputime); + cputime_adjust(&cputime, &p->signal->prev_cputime, ut, st); +} +#endif + +void init_idle_bootup_task(struct task_struct *idle) +{} + +#ifdef CONFIG_SCHED_DEBUG +void proc_sched_show_task(struct task_struct *p, struct seq_file *m) +{} + +void proc_sched_set_task(struct task_struct *p) +{} +#endif + +#ifdef CONFIG_SMP +#define SCHED_LOAD_SHIFT (10) +#define SCHED_LOAD_SCALE (1L << SCHED_LOAD_SHIFT) + +unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu) +{ + return SCHED_LOAD_SCALE; +} + +unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu) +{ + unsigned long weight = cpumask_weight(sched_domain_span(sd)); + unsigned long smt_gain = sd->smt_gain; + + smt_gain /= weight; + + return smt_gain; +} +#endif Index: linux-4.7-bfs/include/uapi/linux/sched.h =================================================================== --- linux-4.7-bfs.orig/include/uapi/linux/sched.h 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/include/uapi/linux/sched.h 2016-07-29 12:15:37.107601749 +1000 @@ -36,9 +36,16 @@ #define SCHED_FIFO 1 #define SCHED_RR 2 #define SCHED_BATCH 3 -/* SCHED_ISO: reserved but not implemented yet */ +/* SCHED_ISO: Implemented on BFS only */ #define SCHED_IDLE 5 +#ifdef CONFIG_SCHED_BFS +#define SCHED_ISO 4 +#define SCHED_IDLEPRIO SCHED_IDLE +#define SCHED_MAX (SCHED_IDLEPRIO) +#define SCHED_RANGE(policy) ((policy) <= SCHED_MAX) +#else /* CONFIG_SCHED_BFS */ #define SCHED_DEADLINE 6 +#endif /* CONFIG_SCHED_BFS */ /* Can be ORed in to make sure the process is reverted back to SCHED_NORMAL on fork */ #define SCHED_RESET_ON_FORK 0x40000000 Index: linux-4.7-bfs/drivers/cpufreq/cpufreq_conservative.c =================================================================== --- linux-4.7-bfs.orig/drivers/cpufreq/cpufreq_conservative.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/drivers/cpufreq/cpufreq_conservative.c 2016-07-29 12:15:37.107601749 +1000 @@ -31,8 +31,8 @@ struct cs_dbs_tuners { }; /* Conservative governor macros */ -#define DEF_FREQUENCY_UP_THRESHOLD (80) -#define DEF_FREQUENCY_DOWN_THRESHOLD (20) +#define DEF_FREQUENCY_UP_THRESHOLD (63) +#define DEF_FREQUENCY_DOWN_THRESHOLD (26) #define DEF_FREQUENCY_STEP (5) #define DEF_SAMPLING_DOWN_FACTOR (1) #define MAX_SAMPLING_DOWN_FACTOR (10) Index: linux-4.7-bfs/kernel/time/Kconfig =================================================================== --- linux-4.7-bfs.orig/kernel/time/Kconfig 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/kernel/time/Kconfig 2016-07-29 12:15:37.107601749 +1000 @@ -89,7 +89,7 @@ config NO_HZ_IDLE config NO_HZ_FULL bool "Full dynticks system (tickless)" # NO_HZ_COMMON dependency - depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS + depends on !ARCH_USES_GETTIMEOFFSET && GENERIC_CLOCKEVENTS && !SCHED_BFS # We need at least one periodic CPU for timekeeping depends on SMP depends on HAVE_CONTEXT_TRACKING Index: linux-4.7-bfs/kernel/sched/Makefile =================================================================== --- linux-4.7-bfs.orig/kernel/sched/Makefile 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/kernel/sched/Makefile 2016-07-29 12:15:37.107601749 +1000 @@ -15,13 +15,18 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer endif +ifdef CONFIG_SCHED_BFS +obj-y += bfs.o clock.o +else obj-y += core.o loadavg.o clock.o cputime.o obj-y += idle_task.o fair.o rt.o deadline.o stop_task.o -obj-y += wait.o swait.o completion.o idle.o -obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o +obj-$(CONFIG_SMP) += cpudeadline.o obj-$(CONFIG_SCHED_AUTOGROUP) += auto_group.o -obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_SCHED_DEBUG) += debug.o obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o +endif +obj-y += wait.o swait.o completion.o idle.o +obj-$(CONFIG_SMP) += cpupri.o +obj-$(CONFIG_SCHEDSTATS) += stats.o obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o Index: linux-4.7-bfs/kernel/sched/bfs_sched.h =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-4.7-bfs/kernel/sched/bfs_sched.h 2016-09-02 14:58:33.392389494 +1000 @@ -0,0 +1,234 @@ +#include +#include +#include + +#ifndef BFS_SCHED_H +#define BFS_SCHED_H + +/* + * This is the main, per-CPU runqueue data structure. + * This data should only be modified by the local cpu. + */ +struct rq { + struct task_struct *curr, *idle, *stop; + struct mm_struct *prev_mm; + + /* Pointer to grq spinlock */ + raw_spinlock_t *grq_lock; + + /* Stored data about rq->curr to work outside grq lock */ + u64 rq_deadline; + unsigned int rq_policy; + int rq_time_slice; + u64 rq_last_ran; + int rq_prio; + bool rq_running; /* There is a task running */ + int soft_affined; /* Running or queued tasks with this set as their rq */ +#ifdef CONFIG_SMT_NICE + struct mm_struct *rq_mm; + int rq_smt_bias; /* Policy/nice level bias across smt siblings */ +#endif + /* Accurate timekeeping data */ + u64 timekeep_clock; + unsigned long user_pc, nice_pc, irq_pc, softirq_pc, system_pc, + iowait_pc, idle_pc; + atomic_t nr_iowait; + +#ifdef CONFIG_SMP + int cpu; /* cpu of this runqueue */ + bool online; + bool scaling; /* This CPU is managed by a scaling CPU freq governor */ + struct task_struct *sticky_task; + + struct root_domain *rd; + struct sched_domain *sd; + int *cpu_locality; /* CPU relative cache distance */ +#ifdef CONFIG_SCHED_SMT + cpumask_t thread_mask; + bool (*siblings_idle)(struct rq *rq); + /* See if all smt siblings are idle */ +#endif /* CONFIG_SCHED_SMT */ +#ifdef CONFIG_SCHED_MC + cpumask_t core_mask; + bool (*cache_idle)(struct rq *rq); + /* See if all cache siblings are idle */ +#endif /* CONFIG_SCHED_MC */ + u64 last_niffy; /* Last time this RQ updated grq.niffies */ +#endif /* CONFIG_SMP */ +#ifdef CONFIG_IRQ_TIME_ACCOUNTING + u64 prev_irq_time; +#endif /* CONFIG_IRQ_TIME_ACCOUNTING */ +#ifdef CONFIG_PARAVIRT + u64 prev_steal_time; +#endif /* CONFIG_PARAVIRT */ +#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING + u64 prev_steal_time_rq; +#endif /* CONFIG_PARAVIRT_TIME_ACCOUNTING */ + + u64 clock, old_clock, last_tick; + u64 clock_task; + bool dither; + +#ifdef CONFIG_SCHEDSTATS + + /* latency stats */ + struct sched_info rq_sched_info; + unsigned long long rq_cpu_time; + /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */ + + /* sys_sched_yield() stats */ + 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; +#endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_CPU_IDLE + /* Must be inspected within a rcu lock section */ + struct cpuidle_state *idle_state; +#endif +}; + +#ifdef CONFIG_SMP +struct rq *cpu_rq(int cpu); +#endif + +#ifndef CONFIG_SMP +extern struct rq *uprq; +#define cpu_rq(cpu) (uprq) +#define this_rq() (uprq) +#define raw_rq() (uprq) +#define task_rq(p) (uprq) +#define cpu_curr(cpu) ((uprq)->curr) +#else /* CONFIG_SMP */ +DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues); +#define this_rq() this_cpu_ptr(&runqueues) +#define raw_rq() raw_cpu_ptr(&runqueues) +#endif /* CONFIG_SMP */ + +static inline u64 __rq_clock_broken(struct rq *rq) +{ + return READ_ONCE(rq->clock); +} + +static inline u64 rq_clock(struct rq *rq) +{ + lockdep_assert_held(rq->grq_lock); + return rq->clock; +} + +static inline u64 rq_clock_task(struct rq *rq) +{ + lockdep_assert_held(rq->grq_lock); + return rq->clock_task; +} + +extern struct mutex sched_domains_mutex; +extern struct static_key_false sched_schedstats; + +#define rcu_dereference_check_sched_domain(p) \ + rcu_dereference_check((p), \ + lockdep_is_held(&sched_domains_mutex)) + +/* + * 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_check_sched_domain(cpu_rq(cpu)->sd); __sd; __sd = __sd->parent) + +#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL) +void register_sched_domain_sysctl(void); +void unregister_sched_domain_sysctl(void); +#else +static inline void register_sched_domain_sysctl(void) +{ +} +static inline void unregister_sched_domain_sysctl(void) +{ +} +#endif + +static inline void sched_ttwu_pending(void) { } + +static inline int task_on_rq_queued(struct task_struct *p) +{ + return p->on_rq; +} + +#ifdef CONFIG_SMP + +extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask); + +#endif + +#ifdef CONFIG_CPU_IDLE +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ + rq->idle_state = idle_state; +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + WARN_ON(!rcu_read_lock_held()); + return rq->idle_state; +} +#else +static inline void idle_set_state(struct rq *rq, + struct cpuidle_state *idle_state) +{ +} + +static inline struct cpuidle_state *idle_get_state(struct rq *rq) +{ + return NULL; +} +#endif + +#ifdef CONFIG_CPU_FREQ +DECLARE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); + +static inline void cpufreq_trigger(u64 time, unsigned long util) +{ + struct update_util_data *data; + + data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data)); + if (data) + data->func(data, time, util, 1); +} + +static inline void other_cpufreq_trigger(int cpu, u64 time, unsigned long util) +{ + struct update_util_data *data; + + data = rcu_dereference_sched(*per_cpu_ptr(&cpufreq_update_util_data, cpu)); + if (data) + data->func(data, time, util, 1); +} +#else +static inline void cpufreq_trigger(u64 time, unsigned long util) +{ +} +static inline void other_cpufreq_trigger(int cpu, u64 time, unsigned long util) +{ +} +#endif /* CONFIG_CPU_FREQ */ + +#ifdef arch_scale_freq_capacity +#ifndef arch_scale_freq_invariant +#define arch_scale_freq_invariant() (true) +#endif +#else /* arch_scale_freq_capacity */ +#define arch_scale_freq_invariant() (false) +#endif + +#endif /* BFS_SCHED_H */ Index: linux-4.7-bfs/kernel/sched/stats.c =================================================================== --- linux-4.7-bfs.orig/kernel/sched/stats.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/kernel/sched/stats.c 2016-07-29 12:15:37.107601749 +1000 @@ -4,7 +4,11 @@ #include #include +#ifndef CONFIG_SCHED_BFS #include "sched.h" +#else +#include "bfs_sched.h" +#endif /* * bump this up when changing the output format or the meaning of an existing Index: linux-4.7-bfs/arch/x86/Kconfig =================================================================== --- linux-4.7-bfs.orig/arch/x86/Kconfig 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/arch/x86/Kconfig 2016-07-29 12:15:37.108601741 +1000 @@ -916,10 +916,26 @@ config SCHED_SMT depends on SMP ---help--- SMT scheduler support improves the CPU scheduler's decision making - when dealing with Intel Pentium 4 chips with HyperThreading at a + when dealing with Intel P4/Core 2 chips with HyperThreading at a cost of slightly increased overhead in some places. If unsure say N here. +config SMT_NICE + bool "SMT (Hyperthreading) aware nice priority and policy support" + depends on SCHED_BFS && SCHED_SMT + default y + ---help--- + Enabling Hyperthreading on Intel CPUs decreases the effectiveness + of the use of 'nice' levels and different scheduling policies + (e.g. realtime) due to sharing of CPU power between hyperthreads. + SMT nice support makes each logical CPU aware of what is running on + its hyperthread siblings, maintaining appropriate distribution of + CPU according to nice levels and scheduling policies at the expense + of slightly increased overhead. + + If unsure say Y here. + + config SCHED_MC def_bool y prompt "Multi-core scheduler support" @@ -2001,7 +2017,7 @@ config HOTPLUG_CPU config BOOTPARAM_HOTPLUG_CPU0 bool "Set default setting of cpu0_hotpluggable" default n - depends on HOTPLUG_CPU + depends on HOTPLUG_CPU && !SCHED_BFS ---help--- Set whether default state of cpu0_hotpluggable is on or off. @@ -2030,7 +2046,7 @@ config BOOTPARAM_HOTPLUG_CPU0 config DEBUG_HOTPLUG_CPU0 def_bool n prompt "Debug CPU0 hotplug" - depends on HOTPLUG_CPU + depends on HOTPLUG_CPU && !SCHED_BFS ---help--- Enabling this option offlines CPU0 (if CPU0 can be offlined) as soon as possible and boots up userspace with CPU0 offlined. User Index: linux-4.7-bfs/include/linux/sched/prio.h =================================================================== --- linux-4.7-bfs.orig/include/linux/sched/prio.h 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/include/linux/sched/prio.h 2016-07-29 12:15:37.108601741 +1000 @@ -19,8 +19,20 @@ */ #define MAX_USER_RT_PRIO 100 + +#ifdef CONFIG_SCHED_BFS +/* Note different MAX_RT_PRIO */ +#define MAX_RT_PRIO (MAX_USER_RT_PRIO + 1) + +#define ISO_PRIO (MAX_RT_PRIO) +#define NORMAL_PRIO (MAX_RT_PRIO + 1) +#define IDLE_PRIO (MAX_RT_PRIO + 2) +#define PRIO_LIMIT ((IDLE_PRIO) + 1) +#else /* CONFIG_SCHED_BFS */ #define MAX_RT_PRIO MAX_USER_RT_PRIO +#endif /* CONFIG_SCHED_BFS */ + #define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH) #define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2) Index: linux-4.7-bfs/drivers/cpufreq/intel_pstate.c =================================================================== --- linux-4.7-bfs.orig/drivers/cpufreq/intel_pstate.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/drivers/cpufreq/intel_pstate.c 2016-07-29 12:15:37.108601741 +1000 @@ -853,8 +853,13 @@ static u64 atom_get_val(struct cpudata * vid_fp = clamp_t(int32_t, vid_fp, cpudata->vid.min, cpudata->vid.max); vid = ceiling_fp(vid_fp); - if (pstate > cpudata->pstate.max_pstate) - vid = cpudata->vid.turbo; + if (pstate < cpudata->pstate.max_pstate) + cpu_scaling(cpudata->cpu); + else { + if (pstate > cpudata->pstate.max_pstate) + vid = cpudata->vid.turbo; + cpu_nonscaling(cpudata->cpu); + } return val | vid; } Index: linux-4.7-bfs/kernel/sched/idle.c =================================================================== --- linux-4.7-bfs.orig/kernel/sched/idle.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/kernel/sched/idle.c 2016-07-29 12:15:37.108601741 +1000 @@ -14,7 +14,11 @@ #include +#ifdef CONFIG_SCHED_BFS +#include "bfs_sched.h" +#else #include "sched.h" +#endif /** * sched_idle_set_state - Record idle state for the current CPU. Index: linux-4.7-bfs/kernel/time/posix-cpu-timers.c =================================================================== --- linux-4.7-bfs.orig/kernel/time/posix-cpu-timers.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/kernel/time/posix-cpu-timers.c 2016-07-29 12:15:37.108601741 +1000 @@ -447,7 +447,7 @@ static void cleanup_timers(struct list_h */ void posix_cpu_timers_exit(struct task_struct *tsk) { - add_device_randomness((const void*) &tsk->se.sum_exec_runtime, + add_device_randomness((const void*) &tsk_seruntime(tsk), sizeof(unsigned long long)); cleanup_timers(tsk->cpu_timers); @@ -848,7 +848,7 @@ static void check_thread_timers(struct t tsk_expires->virt_exp = expires_to_cputime(expires); tsk_expires->sched_exp = check_timers_list(++timers, firing, - tsk->se.sum_exec_runtime); + tsk_seruntime(tsk)); /* * Check for the special case thread timers. @@ -859,7 +859,7 @@ static void check_thread_timers(struct t READ_ONCE(sig->rlim[RLIMIT_RTTIME].rlim_max); if (hard != RLIM_INFINITY && - tsk->rt.timeout > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { + tsk_rttimeout(tsk) > DIV_ROUND_UP(hard, USEC_PER_SEC/HZ)) { /* * At the hard limit, we just die. * No need to calculate anything else now. @@ -867,7 +867,7 @@ static void check_thread_timers(struct t __group_send_sig_info(SIGKILL, SEND_SIG_PRIV, tsk); return; } - if (tsk->rt.timeout > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) { + if (tsk_rttimeout(tsk) > DIV_ROUND_UP(soft, USEC_PER_SEC/HZ)) { /* * At the soft limit, send a SIGXCPU every second. */ @@ -1115,7 +1115,7 @@ static inline int fastpath_timer_check(s struct task_cputime task_sample; task_cputime(tsk, &task_sample.utime, &task_sample.stime); - task_sample.sum_exec_runtime = tsk->se.sum_exec_runtime; + task_sample.sum_exec_runtime = tsk_seruntime(tsk); if (task_cputime_expired(&task_sample, &tsk->cputime_expires)) return 1; } Index: linux-4.7-bfs/kernel/trace/trace_selftest.c =================================================================== --- linux-4.7-bfs.orig/kernel/trace/trace_selftest.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/kernel/trace/trace_selftest.c 2016-07-29 12:15:37.108601741 +1000 @@ -1039,10 +1039,15 @@ static int trace_wakeup_test_thread(void { /* Make this a -deadline thread */ static const struct sched_attr attr = { +#ifdef CONFIG_SCHED_BFS + /* No deadline on BFS, use RR */ + .sched_policy = SCHED_RR, +#else .sched_policy = SCHED_DEADLINE, .sched_runtime = 100000ULL, .sched_deadline = 10000000ULL, .sched_period = 10000000ULL +#endif }; struct wakeup_test_data *x = data; Index: linux-4.7-bfs/kernel/sched/cpufreq.c =================================================================== --- linux-4.7-bfs.orig/kernel/sched/cpufreq.c 2016-07-29 12:15:37.110601725 +1000 +++ linux-4.7-bfs/kernel/sched/cpufreq.c 2016-07-29 12:15:37.109601733 +1000 @@ -9,7 +9,11 @@ * published by the Free Software Foundation. */ +#ifdef CONFIG_SCHED_BFS +#include "bfs_sched.h" +#else #include "sched.h" +#endif DEFINE_PER_CPU(struct update_util_data *, cpufreq_update_util_data); Index: linux-4.7-bfs/kernel/sched/cpufreq_schedutil.c =================================================================== --- linux-4.7-bfs.orig/kernel/sched/cpufreq_schedutil.c 2016-07-26 10:17:36.067881684 +1000 +++ linux-4.7-bfs/kernel/sched/cpufreq_schedutil.c 2016-07-29 13:35:52.076892385 +1000 @@ -16,7 +16,11 @@ #include #include +#ifdef CONFIG_SCHED_BFS +#include "bfs_sched.h" +#else #include "sched.h" +#endif struct sugov_tunables { struct gov_attr_set attr_set; Index: linux-4.7-bfs/kernel/skip_lists.c =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-4.7-bfs/kernel/skip_lists.c 2016-09-02 14:58:32.632395513 +1000 @@ -0,0 +1,148 @@ +/* + Copyright (C) 2011,2016 Con Kolivas. + + Code based on example originally by William Pugh. + +Skip Lists are a probabilistic alternative to balanced trees, as +described in the June 1990 issue of CACM and were invented by +William Pugh in 1987. + +A couple of comments about this implementation: +The routine randomLevel has been hard-coded to generate random +levels using p=0.25. It can be easily changed. + +The insertion routine has been implemented so as to use the +dirty hack described in the CACM paper: if a random level is +generated that is more than the current maximum level, the +current maximum level plus one is used instead. + +Levels start at zero and go up to MaxLevel (which is equal to + (MaxNumberOfLevels-1). + +The routines defined in this file are: + +init: defines slnode + +new_skiplist: returns a new, empty list + +randomLevel: Returns a random level based on a u64 random seed passed to it. +In BFS, the "niffy" time is used for this purpose. + +insert(l,key, value): inserts the binding (key, value) into l. This operation +occurs in O(log n) time. + +delnode(slnode, l, node): deletes any binding of key from the l based on the +actual node value. This operation occurs in O(k) time where k is the +number of levels of the node in question (max 16). The original delete +function occurred in O(log n) time and involved a search. + +BFS Notes: In this implementation of skiplists, there are bidirectional +next/prev pointers and the insert function returns a pointer to the actual +node the value is stored. The key here is chosen by the scheduler so as to +sort tasks according to the priority list requirements and is no longer used +by the scheduler after insertion. The scheduler lookup, however, occurs in +O(1) time because it is always the first item in the level 0 linked list. +Since the task struct stores a copy of the node pointer upon skiplist_insert, +it can also remove it much faster than the original implementation with the +aid of prev<->next pointer manipulation and no searching. + +*/ + +#include +#include + +#define MaxNumberOfLevels 16 /* Fit within a uint8_t */ +#define MaxLevel (MaxNumberOfLevels - 1) +#define newNode kmalloc(sizeof(skiplist_node), GFP_ATOMIC) + +skiplist_node *skiplist_init(void) +{ + skiplist_node *slnode = newNode; + int i; + + BUG_ON(!slnode); + slnode->key = 0xFFFFFFFFFFFFFFFF; + slnode->level = 0; + slnode->value = NULL; + for (i = 0; i < MaxNumberOfLevels; i++) + slnode->next[i] = slnode->prev[i] = slnode; + return slnode; +} + +skiplist *new_skiplist(skiplist_node *slnode) +{ + skiplist *l = kmalloc(sizeof(skiplist), GFP_ATOMIC); + + BUG_ON(!l); + l->level = 0; + l->header = slnode; + return l; +} + +void free_skiplist(skiplist_node *slnode, skiplist *l) +{ + skiplist_node *p, *q; + + p = l->header; + do { + q = p->next[0]; + p->next[0]->prev[0] = q->prev[0]; + kfree(p); + p = q; + } while (p != slnode); + kfree(l); +} + +static inline uint8_t randomLevel(u64 randseed) +{ + return randseed & 0xF; +} + +skiplist_node *skiplist_insert(skiplist_node *slnode, skiplist *l, keyType key, valueType value, u64 randseed) +{ + skiplist_node *update[MaxNumberOfLevels]; + skiplist_node *p, *q; + int k = l->level; + + p = slnode; + do { + while (q = p->next[k], q->key <= key) + p = q; + update[k] = p; + } while (--k >= 0); + + k = randomLevel(randseed); + if (k > l->level) { + k = ++l->level; + update[k] = slnode; + } + + q = newNode; + q->level = k; + q->key = key; + q->value = value; + do { + p = update[k]; + q->next[k] = p->next[k]; + p->next[k] = q; + q->prev[k] = p; + q->next[k]->prev[k] = q; + } while (--k >= 0); + return q; +} + +void skiplist_delnode(skiplist_node *slnode, skiplist *l, skiplist_node *node) +{ + int k, m = node->level; + + for (k = 0; k <= m; k++) { + node->prev[k]->next[k] = node->next[k]; + node->next[k]->prev[k] = node->prev[k]; + } + kfree(node); + if (m == l->level) { + while (l->header->next[m] == slnode && l->header->prev[m] == slnode && m > 0) + m--; + l->level = m; + } +} Index: linux-4.7-bfs/include/linux/skip_lists.h =================================================================== --- /dev/null 1970-01-01 00:00:00.000000000 +0000 +++ linux-4.7-bfs/include/linux/skip_lists.h 2016-09-02 14:58:32.633395506 +1000 @@ -0,0 +1,26 @@ +#ifndef _LINUX_SKIP_LISTS_H +#define _LINUX_SKIP_LISTS_H +typedef u64 keyType; +typedef void *valueType; + +typedef struct nodeStructure skiplist_node; + +struct nodeStructure { + uint8_t level; /* Levels in this structure */ + keyType key; + valueType value; + skiplist_node *next[16]; + skiplist_node *prev[16]; +}; + +typedef struct listStructure { + uint8_t level; /* Maximum level of the list + (1 more than the number of levels in the list) */ + skiplist_node *header; /* pointer to header */ +} skiplist; + +skiplist_node *skiplist_init(void); +skiplist *new_skiplist(skiplist_node *slnode); +skiplist_node *skiplist_insert(skiplist_node *slnode, skiplist *l, keyType key, valueType value, u64 randseed); +void skiplist_delnode(skiplist_node *slnode, skiplist *l, skiplist_node *node); +#endif /* _LINUX_SKIP_LISTS_H */ Index: linux-4.7-bfs/kernel/Makefile =================================================================== --- linux-4.7-bfs.orig/kernel/Makefile 2016-09-02 14:58:32.635395490 +1000 +++ linux-4.7-bfs/kernel/Makefile 2016-09-02 14:58:32.633395506 +1000 @@ -9,7 +9,7 @@ obj-y = fork.o exec_domain.o panic.o extable.o params.o \ kthread.o sys_ni.o nsproxy.o \ notifier.o ksysfs.o cred.o reboot.o \ - async.o range.o smpboot.o + async.o range.o smpboot.o skip_lists.o obj-$(CONFIG_MULTIUSER) += groups.o