Commit 2d722f6d authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge branch 'sched-core-for-linus' of git://

Pull scheduler updates from Ingo Molnar:
 "The main changes:

   - load-calculation cleanups and improvements, by Alex Shi
   - various nohz related tidying up of statisics, by Frederic
   - factor out /proc functions to kernel/sched/proc.c, by Paul
   - simplify the RT policy scheduler, by Kirill Tkhai
   - various fixes and cleanups"

* 'sched-core-for-linus' of git:// (42 commits)
  sched/debug: Remove CONFIG_FAIR_GROUP_SCHED mask
  sched/debug: Fix formatting of /proc/<PID>/sched
  sched: Fix typo in struct sched_avg member description
  sched/fair: Fix typo describing flags in enqueue_entity
  sched/debug: Add load-tracking statistics to task
  sched: Change get_rq_runnable_load() to static and inline
  sched/tg: Remove tg.load_weight
  sched/cfs_rq: Change atomic64_t removed_load to atomic_long_t
  sched/tg: Use 'unsigned long' for load variable in task group
  sched: Change cfs_rq load avg to unsigned long
  sched: Consider runnable load average in move_tasks()
  sched: Compute runnable load avg in cpu_load and cpu_avg_load_per_task
  sched: Update cpu load after task_tick
  sched: Fix sleep time double accounting in enqueue entity
  sched: Set an initial value of runnable avg for new forked task
  sched: Move a few runnable tg variables into CONFIG_SMP
  Revert "sched: Introduce temporary FAIR_GROUP_SCHED dependency for load-tracking"
  sched: Don't mix use of typedef ctl_table and struct ctl_table
  sched: Remove WARN_ON(!sd) from init_sched_groups_power()
  sched: Fix memory leakage in build_sched_groups()
parents f0bb4c0a 2fd1b487
......@@ -373,7 +373,7 @@ can become very uneven.
1.7 What is sched_load_balance ?
The kernel scheduler (kernel/sched.c) automatically load balances
The kernel scheduler (kernel/sched/core.c) automatically load balances
tasks. If one CPU is underutilized, kernel code running on that
CPU will look for tasks on other more overloaded CPUs and move those
tasks to itself, within the constraints of such placement mechanisms
......@@ -384,7 +384,7 @@ priority back.
__rt_mutex_adjust_prio examines the result of rt_mutex_getprio, and if the
result does not equal the task's current priority, then rt_mutex_setprio
is called to adjust the priority of the task to the new priority.
Note that rt_mutex_setprio is defined in kernel/sched.c to implement the
Note that rt_mutex_setprio is defined in kernel/sched/core.c to implement the
actual change in priority.
It is interesting to note that __rt_mutex_adjust_prio can either increase
......@@ -25,7 +25,7 @@ is treated as one entity. The load of a group is defined as the sum of the
load of each of its member CPUs, and only when the load of a group becomes
out of balance are tasks moved between groups.
In kernel/sched.c, trigger_load_balance() is run periodically on each CPU
In kernel/sched/core.c, trigger_load_balance() is run periodically on each CPU
through scheduler_tick(). It raises a softirq after the next regularly scheduled
rebalancing event for the current runqueue has arrived. The actual load
balancing workhorse, run_rebalance_domains()->rebalance_domains(), is then run
......@@ -62,7 +62,7 @@ struct sched_domain fields, SD_FLAG_*, SD_*_INIT to get an idea of
the specifics and what to tune.
Architectures may retain the regular override the default SD_*_INIT flags
while using the generic domain builder in kernel/sched.c if they wish to
while using the generic domain builder in kernel/sched/core.c if they wish to
retain the traditional SMT->SMP->NUMA topology (or some subset of that). This
can be done by #define'ing ARCH_HASH_SCHED_TUNE.
......@@ -137,7 +137,7 @@ don't block on each other (and thus there is no dead-lock wrt interrupts.
But when you do the write-lock, you have to use the irq-safe version.
For an example of being clever with rw-locks, see the "waitqueue_lock"
handling in kernel/sched.c - nothing ever _changes_ a wait-queue from
handling in kernel/sched/core.c - nothing ever _changes_ a wait-queue from
within an interrupt, they only read the queue in order to know whom to
wake up. So read-locks are safe (which is good: they are very common
indeed), while write-locks need to protect themselves against interrupts.
......@@ -3127,7 +3127,7 @@
at process_kern.c:156
#3 0x1006a052 in switch_to (prev=0x50072000, next=0x507e8000, last=0x50072000)
at process_kern.c:161
#4 0x10001d12 in schedule () at sched.c:777
#4 0x10001d12 in schedule () at core.c:777
#5 0x1006a744 in __down (sem=0x507d241c) at semaphore.c:71
#6 0x1006aa10 in __down_failed () at semaphore.c:157
#7 0x1006c5d8 in segv_handler (sc=0x5006e940) at trap_user.c:174
......@@ -3191,7 +3191,7 @@
at process_kern.c:161
161 _switch_to(prev, next);
#4 0x10001d12 in schedule () at sched.c:777
#4 0x10001d12 in schedule () at core.c:777
777 switch_to(prev, next, prev);
#5 0x1006a744 in __down (sem=0x507d241c) at semaphore.c:71
......@@ -341,7 +341,7 @@ unsigned long get_wchan(struct task_struct *p)
* is actually quite ugly. It might be possible to
* determine the frame size automatically at build
* time by doing this:
* - compile sched.c
* - compile sched/core.c
* - disassemble the resulting sched.o
* - look for 'sub sp,??' shortly after '<schedule>:'
......@@ -17,7 +17,7 @@ static inline unsigned long cris_swapnwbrlz(unsigned long w)
in another register:
! __asm__ ("swapnwbr %2\n\tlz %2,%0"
! : "=r,r" (res), "=r,X" (dummy) : "1,0" (w));
confuses gcc (sched.c, gcc from cris-dist-1.14). */
confuses gcc (core.c, gcc from cris-dist-1.14). */
unsigned long res;
__asm__ ("swapnwbr %0 \n\t"
......@@ -1035,7 +1035,7 @@ END(ia64_delay_loop)
* Return a CPU-local timestamp in nano-seconds. This timestamp is
* NOT synchronized across CPUs its return value must never be
* compared against the values returned on another CPU. The usage in
* kernel/sched.c ensures that.
* kernel/sched/core.c ensures that.
* The return-value of sched_clock() is NOT supposed to wrap-around.
* If it did, it would cause some scheduling hiccups (at the worst).
......@@ -27,12 +27,12 @@ unsigned long mt_fpemul_threshold;
* FPU affinity with the user's requested processor affinity.
* This code is 98% identical with the sys_sched_setaffinity()
* and sys_sched_getaffinity() system calls, and should be
* updated when kernel/sched.c changes.
* updated when kernel/sched/core.c changes.
* find_process_by_pid - find a process with a matching PID value.
* used in sys_sched_set/getaffinity() in kernel/sched.c, so
* used in sys_sched_set/getaffinity() in kernel/sched/core.c, so
* cloned here.
static inline struct task_struct *find_process_by_pid(pid_t pid)
......@@ -476,8 +476,9 @@ einval: li v0, -ENOSYS
* For FPU affinity scheduling on MIPS MT processors, we need to
* intercept sys_sched_xxxaffinity() calls until we get a proper hook
* in kernel/sched.c. Considered only temporary we only support these
* hooks for the 32-bit kernel - there is no MIPS64 MT processor atm.
* in kernel/sched/core.c. Considered only temporary we only support
* these hooks for the 32-bit kernel - there is no MIPS64 MT processor
* atm.
sys mipsmt_sys_sched_setaffinity 3
sys mipsmt_sys_sched_getaffinity 3
......@@ -38,7 +38,7 @@ extern void drop_cop(unsigned long acop, struct mm_struct *mm);
* switch_mm is the entry point called from the architecture independent
* code in kernel/sched.c
* code in kernel/sched/core.c
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
......@@ -225,7 +225,7 @@ extern int do_work_pending(struct pt_regs *regs, u32 flags);
* Return saved (kernel) PC of a blocked thread.
* Only used in a printk() in kernel/sched.c, so don't work too hard.
* Only used in a printk() in kernel/sched/core.c, so don't work too hard.
#define thread_saved_pc(t) ((t)->thread.pc)
......@@ -442,7 +442,7 @@ void _KBacktraceIterator_init_current(struct KBacktraceIterator *kbt, ulong pc,
regs_to_pt_regs(&regs, pc, lr, sp, r52));
/* This is called only from kernel/sched.c, with esp == NULL */
/* This is called only from kernel/sched/core.c, with esp == NULL */
void show_stack(struct task_struct *task, unsigned long *esp)
struct KBacktraceIterator kbt;
......@@ -39,7 +39,7 @@ void show_trace(struct task_struct *task, unsigned long * stack)
static const int kstack_depth_to_print = 24;
/* This recently started being used in arch-independent code too, as in
* kernel/sched.c.*/
* kernel/sched/core.c.*/
void show_stack(struct task_struct *task, unsigned long *esp)
unsigned long *stack;
......@@ -5,7 +5,7 @@
* (C) Copyright 2001 Linus Torvalds
* Atomic wait-for-completion handler data structures.
* See kernel/sched.c for details.
* See kernel/sched/core.c for details.
#include <linux/wait.h>
......@@ -822,7 +822,7 @@ static inline void perf_restore_debug_store(void) { }
#define perf_output_put(handle, x) perf_output_copy((handle), &(x), sizeof(x))
* This has to have a higher priority than migration_notifier in sched.c.
* This has to have a higher priority than migration_notifier in sched/core.c.
#define perf_cpu_notifier(fn) \
do { \
......@@ -924,7 +924,7 @@ struct load_weight {
struct sched_avg {
* These sums represent an infinite geometric series and so are bound
* above by 1024/(1-y). Thus we only need a u32 to store them for for all
* above by 1024/(1-y). Thus we only need a u32 to store them for all
* choices of y < 1-2^(-32)*1024.
u32 runnable_avg_sum, runnable_avg_period;
......@@ -994,12 +994,7 @@ struct sched_entity {
struct cfs_rq *my_q;
* Load-tracking only depends on SMP, FAIR_GROUP_SCHED dependency below may be
* removed when useful for applications beyond shares distribution (e.g.
* load-balance).
#if defined(CONFIG_SMP) && defined(CONFIG_FAIR_GROUP_SCHED)
/* Per-entity load-tracking */
struct sched_avg avg;
......@@ -67,7 +67,7 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
#else /* DEBUG_SPINLOCK */
#define arch_spin_is_locked(lock) ((void)(lock), 0)
/* for sched.c and kernel_lock.c: */
/* for sched/core.c and kernel_lock.c: */
# define arch_spin_lock(lock) do { barrier(); (void)(lock); } while (0)
# define arch_spin_lock_flags(lock, flags) do { barrier(); (void)(lock); } while (0)
# define arch_spin_unlock(lock) do { barrier(); (void)(lock); } while (0)
......@@ -361,7 +361,7 @@ __SYSCALL(__NR_syslog, sys_syslog)
#define __NR_ptrace 117
__SYSCALL(__NR_ptrace, sys_ptrace)
/* kernel/sched.c */
/* kernel/sched/core.c */
#define __NR_sched_setparam 118
__SYSCALL(__NR_sched_setparam, sys_sched_setparam)
#define __NR_sched_setscheduler 119
......@@ -540,7 +540,7 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr,
* This function builds a partial partition of the systems CPUs
* A 'partial partition' is a set of non-overlapping subsets whose
* union is a subset of that set.
* The output of this function needs to be passed to kernel/sched.c
* The output of this function needs to be passed to kernel/sched/core.c
* partition_sched_domains() routine, which will rebuild the scheduler's
* load balancing domains (sched domains) as specified by that partial
* partition.
......@@ -569,7 +569,7 @@ static void update_domain_attr_tree(struct sched_domain_attr *dattr,
* is a subset of one of these domains, while there are as
* many such domains as possible, each as small as possible.
* doms - Conversion of 'csa' to an array of cpumasks, for passing to
* the kernel/sched.c routine partition_sched_domains() in a
* the kernel/sched/core.c routine partition_sched_domains() in a
* convenient format, that can be easily compared to the prior
* value to determine what partition elements (sched domains)
* were changed (added or removed.)
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment