android_kernel_samsung_msm8976/kernel/sched_cpupri.c

209 lines
5.5 KiB
C
Raw Normal View History

/*
* kernel/sched_cpupri.c
*
* CPU priority management
*
* Copyright (C) 2007-2008 Novell
*
* Author: Gregory Haskins <ghaskins@novell.com>
*
* This code tracks the priority of each CPU so that global migration
* decisions are easy to calculate. Each CPU can be in a state as follows:
*
* (INVALID), IDLE, NORMAL, RT1, ... RT99
*
* going from the lowest priority to the highest. CPUs in the INVALID state
* are not eligible for routing. The system maintains this state with
* a 2 dimensional bitmap (the first for priority class, the second for cpus
* in that class). Therefore a typical application without affinity
* restrictions can find a suitable CPU with O(1) complexity (e.g. two bit
* searches). For tasks with affinity restrictions, the algorithm has a
* worst case complexity of O(min(102, nr_domcpus)), though the scenario that
* yields the worst case search is fairly contrived.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; version 2
* of the License.
*/
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/gfp.h>
#include "sched_cpupri.h"
/* Convert between a 140 based task->prio, and our 102 based cpupri */
static int convert_prio(int prio)
{
int cpupri;
if (prio == CPUPRI_INVALID)
cpupri = CPUPRI_INVALID;
else if (prio == MAX_PRIO)
cpupri = CPUPRI_IDLE;
else if (prio >= MAX_RT_PRIO)
cpupri = CPUPRI_NORMAL;
else
cpupri = MAX_RT_PRIO - prio + 1;
return cpupri;
}
#define for_each_cpupri_active(array, idx) \
for_each_set_bit(idx, array, CPUPRI_NR_PRIORITIES)
/**
* cpupri_find - find the best (lowest-pri) CPU in the system
* @cp: The cpupri context
* @p: The task
* @lowest_mask: A mask to fill in with selected CPUs (or NULL)
*
* Note: This function returns the recommended CPUs as calculated during the
* current invocation. By the time the call returns, the CPUs may have in
* fact changed priorities any number of times. While not ideal, it is not
* an issue of correctness since the normal rebalancer logic will correct
* any discrepancies created by racing against the uncertainty of the current
* priority configuration.
*
* Returns: (int)bool - CPUs were found
*/
int cpupri_find(struct cpupri *cp, struct task_struct *p,
struct cpumask *lowest_mask)
{
int idx = 0;
int task_pri = convert_prio(p->prio);
for_each_cpupri_active(cp->pri_active, idx) {
struct cpupri_vec *vec = &cp->pri_to_cpu[idx];
if (idx >= task_pri)
break;
if (cpumask_any_and(&p->cpus_allowed, vec->mask) >= nr_cpu_ids)
continue;
sched: Fix race in cpupri introduced by cpumask_var changes Background: Several race conditions in the scheduler have cropped up recently, which Steven and I have tracked down using ftrace. The most recent one turns out to be a race in how the scheduler determines a suitable migration target for RT tasks, introduced recently with commit: commit 68e74568fbe5854952355e942acca51f138096d9 Date: Tue Nov 25 02:35:13 2008 +1030 sched: convert struct cpupri_vec cpumask_var_t. The original design of cpupri allowed lockless readers to quickly determine a best-estimate target. Races between the pri_active bitmap and the vec->mask were handled in the original code because we would detect and return "0" when this occured. The design was predicated on the *effective* atomicity (*) of caching the result of cpus_and() between the cpus_allowed and the vec->mask. Commit 68e74568 changed the behavior such that vec->mask is accessed multiple times. This introduces a subtle race, the result of which means we can have a result that returns "1", but with an empty bitmap. *) yes, we know cpus_and() is not a locked operator across the entire composite array, but it is implicitly atomic on a per-word basis which is all the design required to work. Implementation: Rather than forgoing the lockless design, or reverting to a stack-based cpumask_t, we simply check for when the race has been encountered and continue processing in the event that the race is hit. This renders the removal race as if the priority bit had been atomically cleared as well, and allows the algorithm to execute correctly. Signed-off-by: Gregory Haskins <ghaskins@novell.com> CC: Rusty Russell <rusty@rustcorp.com.au> CC: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20090730145728.25226.92769.stgit@dev.haskins.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-30 14:57:28 +00:00
if (lowest_mask) {
cpumask_and(lowest_mask, &p->cpus_allowed, vec->mask);
sched: Fix race in cpupri introduced by cpumask_var changes Background: Several race conditions in the scheduler have cropped up recently, which Steven and I have tracked down using ftrace. The most recent one turns out to be a race in how the scheduler determines a suitable migration target for RT tasks, introduced recently with commit: commit 68e74568fbe5854952355e942acca51f138096d9 Date: Tue Nov 25 02:35:13 2008 +1030 sched: convert struct cpupri_vec cpumask_var_t. The original design of cpupri allowed lockless readers to quickly determine a best-estimate target. Races between the pri_active bitmap and the vec->mask were handled in the original code because we would detect and return "0" when this occured. The design was predicated on the *effective* atomicity (*) of caching the result of cpus_and() between the cpus_allowed and the vec->mask. Commit 68e74568 changed the behavior such that vec->mask is accessed multiple times. This introduces a subtle race, the result of which means we can have a result that returns "1", but with an empty bitmap. *) yes, we know cpus_and() is not a locked operator across the entire composite array, but it is implicitly atomic on a per-word basis which is all the design required to work. Implementation: Rather than forgoing the lockless design, or reverting to a stack-based cpumask_t, we simply check for when the race has been encountered and continue processing in the event that the race is hit. This renders the removal race as if the priority bit had been atomically cleared as well, and allows the algorithm to execute correctly. Signed-off-by: Gregory Haskins <ghaskins@novell.com> CC: Rusty Russell <rusty@rustcorp.com.au> CC: Steven Rostedt <srostedt@redhat.com> Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> LKML-Reference: <20090730145728.25226.92769.stgit@dev.haskins.net> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2009-07-30 14:57:28 +00:00
/*
* We have to ensure that we have at least one bit
* still set in the array, since the map could have
* been concurrently emptied between the first and
* second reads of vec->mask. If we hit this
* condition, simply act as though we never hit this
* priority level and continue on.
*/
if (cpumask_any(lowest_mask) >= nr_cpu_ids)
continue;
}
return 1;
}
return 0;
}
/**
* cpupri_set - update the cpu priority setting
* @cp: The cpupri context
* @cpu: The target cpu
* @pri: The priority (INVALID-RT99) to assign to this CPU
*
* Note: Assumes cpu_rq(cpu)->lock is locked
*
* Returns: (void)
*/
void cpupri_set(struct cpupri *cp, int cpu, int newpri)
{
int *currpri = &cp->cpu_to_pri[cpu];
int oldpri = *currpri;
unsigned long flags;
newpri = convert_prio(newpri);
BUG_ON(newpri >= CPUPRI_NR_PRIORITIES);
if (newpri == oldpri)
return;
/*
* If the cpu was currently mapped to a different value, we
* need to map it to the new value then remove the old value.
* Note, we must add the new value first, otherwise we risk the
* cpu being cleared from pri_active, and this cpu could be
* missed for a push or pull.
*/
if (likely(newpri != CPUPRI_INVALID)) {
struct cpupri_vec *vec = &cp->pri_to_cpu[newpri];
raw_spin_lock_irqsave(&vec->lock, flags);
cpumask_set_cpu(cpu, vec->mask);
vec->count++;
if (vec->count == 1)
set_bit(newpri, cp->pri_active);
raw_spin_unlock_irqrestore(&vec->lock, flags);
}
if (likely(oldpri != CPUPRI_INVALID)) {
struct cpupri_vec *vec = &cp->pri_to_cpu[oldpri];
raw_spin_lock_irqsave(&vec->lock, flags);
vec->count--;
if (!vec->count)
clear_bit(oldpri, cp->pri_active);
cpumask_clear_cpu(cpu, vec->mask);
raw_spin_unlock_irqrestore(&vec->lock, flags);
}
*currpri = newpri;
}
/**
* cpupri_init - initialize the cpupri structure
* @cp: The cpupri context
* @bootmem: true if allocations need to use bootmem
*
* Returns: -ENOMEM if memory fails.
*/
int cpupri_init(struct cpupri *cp, bool bootmem)
{
gfp_t gfp = GFP_KERNEL;
int i;
if (bootmem)
gfp = GFP_NOWAIT;
memset(cp, 0, sizeof(*cp));
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++) {
struct cpupri_vec *vec = &cp->pri_to_cpu[i];
raw_spin_lock_init(&vec->lock);
vec->count = 0;
if (!zalloc_cpumask_var(&vec->mask, gfp))
goto cleanup;
}
for_each_possible_cpu(i)
cp->cpu_to_pri[i] = CPUPRI_INVALID;
return 0;
cleanup:
for (i--; i >= 0; i--)
free_cpumask_var(cp->pri_to_cpu[i].mask);
return -ENOMEM;
}
/**
* cpupri_cleanup - clean up the cpupri structure
* @cp: The cpupri context
*/
void cpupri_cleanup(struct cpupri *cp)
{
int i;
for (i = 0; i < CPUPRI_NR_PRIORITIES; i++)
free_cpumask_var(cp->pri_to_cpu[i].mask);
}