CCF_100
/
linux-tkg
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity
linux-tkg/linux-tkg-patches/5.4/0005-v5.4_undead-pds099o.patch

8388 lines
224 KiB
Diff
Raw Blame History

From 89067d28ca90681fc6cf108de79b9aedb93dfa9d Mon Sep 17 00:00:00 2001
From: Tk-Glitch <ti3nou@gmail.com>
Date: Mon, 25 Nov 2019 21:46:23 +0100
Subject: PDS 099o, 5.4 rebase
diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 032c7cd3cede..360a229b0abe 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -82,6 +82,7 @@ show up in /proc/sys/kernel:
- randomize_va_space
- real-root-dev ==> Documentation/admin-guide/initrd.rst
- reboot-cmd [ SPARC only ]
+- rr_interval
- rtsig-max
- rtsig-nr
- sched_energy_aware
@@ -105,6 +106,7 @@ show up in /proc/sys/kernel:
- unknown_nmi_panic
- watchdog
- watchdog_thresh
+- yield_type
- version
diff --git a/Documentation/scheduler/sched-PDS-mq.txt b/Documentation/scheduler/sched-PDS-mq.txt
new file mode 100644
index 000000000000..709e86f6487e
--- /dev/null
+++ b/Documentation/scheduler/sched-PDS-mq.txt
@@ -0,0 +1,56 @@
+ Priority and Deadline based Skiplist multiple queue Scheduler
+ -------------------------------------------------------------
+
+CONTENT
+========
+
+ 0. Development
+ 1. Overview
+ 1.1 Design goal
+ 1.2 Design summary
+ 2. Design Detail
+ 2.1 Skip list implementation
+ 2.2 Task preempt
+ 2.3 Task policy, priority and deadline
+ 2.4 Task selection
+ 2.5 Run queue balance
+ 2.6 Task migration
+
+
+0. Development
+==============
+
+Priority and Deadline based Skiplist multiple queue scheduler, referred to as
+PDS from here on, is developed upon the enhancement patchset VRQ(Variable Run
+Queue) for BFS(Brain Fuck Scheduler by Con Kolivas). PDS inherits the existing
+design from VRQ and inspired by the introduction of skiplist data structure
+to the scheduler by Con Kolivas. However, PDS is different from MuQSS(Multiple
+Queue Skiplist Scheduler, the successor after BFS) in many ways.
+
+1. Overview
+===========
+
+1.1 Design goal
+---------------
+
+PDS is designed to make the cpu process scheduler code to be simple, but while
+efficiency and scalable. Be Simple, the scheduler code will be easy to be read
+and the behavious of scheduler will be easy to predict. Be efficiency, the
+scheduler shall be well balance the thoughput performance and task interactivity
+at the same time for different properties the tasks behave. Be scalable, the
+performance of the scheduler should be in good shape with the glowing of
+workload or with the growing of the cpu numbers.
+
+1.2 Design summary
+------------------
+
+PDS is described as a multiple run queues cpu scheduler. Each cpu has its own
+run queue. A heavry customized skiplist is used as the backend data structure
+of the cpu run queue. Tasks in run queue is sorted by priority then virtual
+deadline(simplfy to just deadline from here on). In PDS, balance action among
+run queues are kept as less as possible to reduce the migration cost. Cpumask
+data structure is widely used in cpu affinity checking and cpu preemption/
+selection to make PDS scalable with increasing cpu number.
+
+
+To be continued...
diff --git a/arch/powerpc/platforms/cell/spufs/sched.c b/arch/powerpc/platforms/cell/spufs/sched.c
index f18d5067cd0f..fe489fc01c73 100644
--- a/arch/powerpc/platforms/cell/spufs/sched.c
+++ b/arch/powerpc/platforms/cell/spufs/sched.c
@@ -51,11 +51,6 @@ static struct task_struct *spusched_task;
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.
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 8ef85139553f..9d44d8d78259 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1034,6 +1034,22 @@ config NR_CPUS
config SCHED_SMT
def_bool y if SMP
+config SMT_NICE
+ bool "SMT (Hyperthreading) aware nice priority and policy support"
+ depends on SCHED_PDS && 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"
diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index b66e81c06a57..a294f8f5fd75 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -28,8 +28,8 @@ 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)
diff --git a/drivers/cpufreq/cpufreq_ondemand.c b/drivers/cpufreq/cpufreq_ondemand.c
index dced033875bf..d2cd03766b09 100644
--- a/drivers/cpufreq/cpufreq_ondemand.c
+++ b/drivers/cpufreq/cpufreq_ondemand.c
@@ -18,7 +18,7 @@
#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)
@@ -127,7 +127,7 @@ static void dbs_freq_increase(struct cpufreq_policy *policy, unsigned int freq)
}
/*
- * 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.
*/
diff --git a/fs/proc/base.c b/fs/proc/base.c
index ebea9501afb8..51c9346a69fe 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -477,7 +477,7 @@ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
seq_puts(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);
diff --git a/include/linux/init_task.h b/include/linux/init_task.h
index 2c620d7ac432..1a7987c40c80 100644
--- a/include/linux/init_task.h
+++ b/include/linux/init_task.h
@@ -36,7 +36,11 @@ extern struct cred init_cred;
#define INIT_PREV_CPUTIME(x)
#endif
+#ifdef CONFIG_SCHED_PDS
+#define INIT_TASK_COMM "PDS"
+#else
#define INIT_TASK_COMM "swapper"
+#endif /* !CONFIG_SCHED_PDS */
/* Attach to the init_task data structure for proper alignment */
#ifdef CONFIG_ARCH_TASK_STRUCT_ON_STACK
diff --git a/include/linux/jiffies.h b/include/linux/jiffies.h
index 1b6d31da7cbc..dea181bdb1dd 100644
--- a/include/linux/jiffies.h
+++ b/include/linux/jiffies.h
@@ -171,7 +171,7 @@ 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
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 67a1d86981a9..8268cad4b0a2 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -31,6 +31,7 @@
#include <linux/task_io_accounting.h>
#include <linux/posix-timers.h>
#include <linux/rseq.h>
+#include <linux/skip_list.h>
/* task_struct member predeclarations (sorted alphabetically): */
struct audit_context;
@@ -644,9 +645,13 @@ struct task_struct {
unsigned int flags;
unsigned int ptrace;
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_PDS)
struct llist_node wake_entry;
+#endif
+#if defined(CONFIG_SMP) || defined(CONFIG_SCHED_PDS)
int on_cpu;
+#endif
+#ifdef CONFIG_SMP
#ifdef CONFIG_THREAD_INFO_IN_TASK
/* Current CPU: */
unsigned int cpu;
@@ -655,6 +660,7 @@ struct task_struct {
unsigned long wakee_flip_decay_ts;
struct task_struct *last_wakee;
+#ifndef CONFIG_SCHED_PDS
/*
* recent_used_cpu is initially set as the last CPU used by a task
* that wakes affine another task. Waker/wakee relationships can
@@ -663,6 +669,7 @@ struct task_struct {
* used CPU that may be idle.
*/
int recent_used_cpu;
+#endif /* CONFIG_SCHED_PDS */
int wake_cpu;
#endif
int on_rq;
@@ -672,13 +679,27 @@ struct task_struct {
int normal_prio;
unsigned int rt_priority;
+#ifdef CONFIG_SCHED_PDS
+ int time_slice;
+ u64 deadline;
+ /* skip list level */
+ int sl_level;
+ /* skip list node */
+ struct skiplist_node sl_node;
+ /* 8bits prio and 56bits deadline for quick processing */
+ u64 priodl;
+ u64 last_ran;
+ /* sched_clock time spent running */
+ u64 sched_time;
+#else /* CONFIG_SCHED_PDS */
const struct sched_class *sched_class;
struct sched_entity se;
struct sched_rt_entity rt;
+ struct sched_dl_entity dl;
+#endif
#ifdef CONFIG_CGROUP_SCHED
struct task_group *sched_task_group;
#endif
- struct sched_dl_entity dl;
#ifdef CONFIG_UCLAMP_TASK
/* Clamp values requested for a scheduling entity */
@@ -1283,6 +1304,29 @@ struct task_struct {
*/
};
+#ifdef CONFIG_SCHED_PDS
+void cpu_scaling(int cpu);
+void cpu_nonscaling(int cpu);
+#define tsk_seruntime(t) ((t)->sched_time)
+/* replace the uncertian rt_timeout with 0UL */
+#define tsk_rttimeout(t) (0UL)
+
+#define task_running_idle(p) ((p)->prio == IDLE_PRIO)
+#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)
+
+#define iso_task(p) (false)
+#endif /* CONFIG_SCHED_PDS */
+
static inline struct pid *task_pid(struct task_struct *task)
{
return task->thread_pid;
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index 1aff00b65f3c..a5e5fc2c9170 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -1,5 +1,22 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#ifdef CONFIG_SCHED_PDS
+
+#define __tsk_deadline(p) ((p)->deadline)
+
+static inline int dl_prio(int prio)
+{
+ return 1;
+}
+
+static inline int dl_task(struct task_struct *p)
+{
+ return 1;
+}
+#else
+
+#define __tsk_deadline(p) ((p)->dl.deadline)
+
/*
* SCHED_DEADLINE tasks has negative priorities, reflecting
* the fact that any of them has higher prio than RT and
@@ -19,6 +36,7 @@ static inline int dl_task(struct task_struct *p)
{
return dl_prio(p->prio);
}
+#endif /* CONFIG_SCHED_PDS */
static inline bool dl_time_before(u64 a, u64 b)
{
diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h
index 7d64feafc408..fba04bb91492 100644
--- a/include/linux/sched/prio.h
+++ b/include/linux/sched/prio.h
@@ -20,7 +20,18 @@
*/
#define MAX_USER_RT_PRIO 100
+
+#ifdef CONFIG_SCHED_PDS
+#define ISO_PRIO (MAX_USER_RT_PRIO)
+
+#define MAX_RT_PRIO ((MAX_USER_RT_PRIO) + 1)
+
+#define NORMAL_PRIO (MAX_RT_PRIO)
+#define IDLE_PRIO ((MAX_RT_PRIO) + 1)
+#define PRIO_LIMIT ((IDLE_PRIO) + 1)
+#else /* !CONFIG_SCHED_PDS */
#define MAX_RT_PRIO MAX_USER_RT_PRIO
+#endif /* CONFIG_SCHED_PDS */
#define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH)
#define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2)
diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
index e5af028c08b4..a96012e6f15e 100644
--- a/include/linux/sched/rt.h
+++ b/include/linux/sched/rt.h
@@ -24,8 +24,10 @@ static inline bool task_is_realtime(struct task_struct *tsk)
if (policy == SCHED_FIFO || policy == SCHED_RR)
return true;
+#ifndef CONFIG_SCHED_PDS
if (policy == SCHED_DEADLINE)
return true;
+#endif
return false;
}
diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index 4b1c3b664f51..f186b8119ad6 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -99,7 +99,7 @@ extern long kernel_wait4(pid_t, int __user *, int, struct rusage *);
extern void free_task(struct task_struct *tsk);
/* sched_exec is called by processes performing an exec */
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_PDS)
extern void sched_exec(void);
#else
#define sched_exec() {}
diff --git a/include/linux/skip_list.h b/include/linux/skip_list.h
new file mode 100644
index 000000000000..713fedd8034f
--- /dev/null
+++ b/include/linux/skip_list.h
@@ -0,0 +1,177 @@
+/*
+ Copyright (C) 2016 Alfred Chen.
+
+ Code based on Con Kolivas's skip list implementation for BFS, and
+ which is 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:
+
+This file only provides a infrastructure of skip list.
+
+skiplist_node is embedded into container data structure, to get rid the
+dependency of kmalloc/kfree operation in scheduler code.
+
+A customized search function should be defined using DEFINE_SKIPLIST_INSERT
+macro and be used for skip list insert operation.
+
+Random Level is also not defined in this file, instead, it should be customized
+implemented and set to node->level then pass to the customized skiplist_insert
+function.
+
+Levels start at zero and go up to (NUM_SKIPLIST_LEVEL -1)
+
+NUM_SKIPLIST_LEVEL in this implementation is 8 instead of origin 16,
+considering that there will be 256 entries to enable the top level when using
+random level p=0.5, and that number is more than enough for a run queue usage
+in a scheduler usage. And it also help to reduce the memory usage of the
+embedded skip list node in task_struct to about 50%.
+
+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.
+
+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.
+*/
+#ifndef _LINUX_SKIP_LIST_H
+#define _LINUX_SKIP_LIST_H
+
+#include <linux/kernel.h>
+
+#define NUM_SKIPLIST_LEVEL (8)
+
+struct skiplist_node {
+ int level; /* Levels in this node */
+ struct skiplist_node *next[NUM_SKIPLIST_LEVEL];
+ struct skiplist_node *prev[NUM_SKIPLIST_LEVEL];
+};
+
+#define SKIPLIST_NODE_INIT(name) { 0,\
+ {&name, &name, &name, &name,\
+ &name, &name, &name, &name},\
+ {&name, &name, &name, &name,\
+ &name, &name, &name, &name},\
+ }
+
+static inline void INIT_SKIPLIST_NODE(struct skiplist_node *node)
+{
+ /* only level 0 ->next matters in skiplist_empty()*/
+ WRITE_ONCE(node->next[0], node);
+}
+
+/**
+ * FULL_INIT_SKIPLIST_NODE -- fully init a skiplist_node, expecially for header
+ * @node: the skip list node to be inited.
+ */
+static inline void FULL_INIT_SKIPLIST_NODE(struct skiplist_node *node)
+{
+ int i;
+
+ node->level = 0;
+ for (i = 0; i < NUM_SKIPLIST_LEVEL; i++) {
+ WRITE_ONCE(node->next[i], node);
+ node->prev[i] = node;
+ }
+}
+
+/**
+ * skiplist_empty - test whether a skip list is empty
+ * @head: the skip list to test.
+ */
+static inline int skiplist_empty(const struct skiplist_node *head)
+{
+ return READ_ONCE(head->next[0]) == head;
+}
+
+/**
+ * skiplist_entry - get the struct for this entry
+ * @ptr: the &struct skiplist_node pointer.
+ * @type: the type of the struct this is embedded in.
+ * @member: the name of the skiplist_node within the struct.
+ */
+#define skiplist_entry(ptr, type, member) \
+ container_of(ptr, type, member)
+
+/**
+ * DEFINE_SKIPLIST_INSERT_FUNC -- macro to define a customized skip list insert
+ * function, which takes two parameters, first one is the header node of the
+ * skip list, second one is the skip list node to be inserted
+ * @func_name: the customized skip list insert function name
+ * @search_func: the search function to be used, which takes two parameters,
+ * 1st one is the itrator of skiplist_node in the list, the 2nd is the skip list
+ * node to be inserted, the function should return true if search should be
+ * continued, otherwise return false.
+ * Returns 1 if @node is inserted as the first item of skip list at level zero,
+ * otherwise 0
+ */
+#define DEFINE_SKIPLIST_INSERT_FUNC(func_name, search_func)\
+static inline int func_name(struct skiplist_node *head, struct skiplist_node *node)\
+{\
+ struct skiplist_node *update[NUM_SKIPLIST_LEVEL];\
+ struct skiplist_node *p, *q;\
+ int k = head->level;\
+\
+ p = head;\
+ do {\
+ while (q = p->next[k], q != head && search_func(q, node))\
+ p = q;\
+ update[k] = p;\
+ } while (--k >= 0);\
+\
+ k = node->level;\
+ if (unlikely(k > head->level)) {\
+ node->level = k = ++head->level;\
+ update[k] = head;\
+ }\
+\
+ do {\
+ p = update[k];\
+ q = p->next[k];\
+ node->next[k] = q;\
+ p->next[k] = node;\
+ node->prev[k] = p;\
+ q->prev[k] = node;\
+ } while (--k >= 0);\
+\
+ return (p == head);\
+}
+
+/**
+ * skiplist_del_init -- delete skip list node from a skip list and reset it's
+ * init state
+ * @head: the header node of the skip list to be deleted from.
+ * @node: the skip list node to be deleted, the caller need to ensure @node is
+ * in skip list which @head represent.
+ * Returns 1 if @node is the first item of skip level at level zero, otherwise 0
+ */
+static inline int
+skiplist_del_init(struct skiplist_node *head, struct skiplist_node *node)
+{
+ int l, m = node->level;
+
+ for (l = 0; l <= m; l++) {
+ node->prev[l]->next[l] = node->next[l];
+ node->next[l]->prev[l] = node->prev[l];
+ }
+ if (m == head->level && m > 0) {
+ while (head->next[m] == head && m > 0)
+ m--;
+ head->level = m;
+ }
+ INIT_SKIPLIST_NODE(node);
+
+ return (node->prev[0] == head);
+}
+#endif /* _LINUX_SKIP_LIST_H */
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 25b4fa00bad1..fc0aabdce15f 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -84,7 +84,10 @@ struct clone_args {
#define SCHED_FIFO 1
#define SCHED_RR 2
#define SCHED_BATCH 3
-/* SCHED_ISO: reserved but not implemented yet */
+/* SCHED_ISO: Implemented in BFS/MuQSSPDS only */
+#ifdef CONFIG_SCHED_PDS
+#define SCHED_ISO 4
+#endif
#define SCHED_IDLE 5
#define SCHED_DEADLINE 6
diff --git a/init/Kconfig b/init/Kconfig
index b4daad2bac23..ee3b9957cf3b 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -73,6 +73,21 @@ config THREAD_INFO_IN_TASK
menu "General setup"
+config SCHED_PDS
+ bool "PDS-mq cpu scheduler"
+ help
+ The Priority and Deadline based Skip list multiple queue CPU
+ Scheduler for excellent interactivity and responsiveness on the
+ desktop and solid scalability on normal hardware and commodity
+ servers.
+
+ Currently incompatible with the Group CPU scheduler, and RCU TORTURE
+ TEST so these options are disabled.
+
+ Say Y here.
+ default y
+
+
config BROKEN
bool
@@ -802,6 +817,7 @@ config NUMA_BALANCING
depends on ARCH_SUPPORTS_NUMA_BALANCING
depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
depends on SMP && NUMA && MIGRATION
+ depends on !SCHED_PDS
help
This option adds support for automatic NUMA aware memory/task placement.
The mechanism is quite primitive and is based on migrating memory when
@@ -903,7 +919,7 @@ menuconfig CGROUP_SCHED
bandwidth allocation to such task groups. It uses cgroups to group
tasks.
-if CGROUP_SCHED
+if CGROUP_SCHED && !SCHED_PDS
config FAIR_GROUP_SCHED
bool "Group scheduling for SCHED_OTHER"
depends on CGROUP_SCHED
@@ -1032,6 +1048,7 @@ config CGROUP_DEVICE
config CGROUP_CPUACCT
bool "Simple CPU accounting controller"
+ depends on !SCHED_PDS
help
Provides a simple controller for monitoring the
total CPU consumed by the tasks in a cgroup.
@@ -1150,6 +1167,7 @@ config CHECKPOINT_RESTORE
config SCHED_AUTOGROUP
bool "Automatic process group scheduling"
+ depends on !SCHED_PDS
select CGROUPS
select CGROUP_SCHED
select FAIR_GROUP_SCHED
diff --git a/init/init_task.c b/init/init_task.c
index 9e5cbe5eab7b..89787e2feb60 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -58,6 +58,126 @@ struct task_struct init_task
__init_task_data
#endif
= {
+#ifdef CONFIG_SCHED_PDS
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+ .thread_info = INIT_THREAD_INFO(init_task),
+ .stack_refcount = ATOMIC_INIT(1),
+#endif
+ .state = 0,
+ .stack = init_stack,
+ .usage = ATOMIC_INIT(2),
+ .flags = PF_KTHREAD,
+ .prio = NORMAL_PRIO,
+ .static_prio = MAX_PRIO - 20,
+ .normal_prio = NORMAL_PRIO,
+ .deadline = 0, /* PDS only */
+ .policy = SCHED_NORMAL,
+ .cpus_ptr = &init_task.cpus_mask,
+ .cpus_mask = CPU_MASK_ALL,
+ .nr_cpus_allowed= NR_CPUS,
+ .mm = NULL,
+ .active_mm = &init_mm,
+ .restart_block = {
+ .fn = do_no_restart_syscall,
+ },
+ .sl_level = 0, /* PDS only */
+ .sl_node = SKIPLIST_NODE_INIT(init_task.sl_node), /* PDS only */
+ .time_slice = HZ, /* PDS only */
+ .tasks = LIST_HEAD_INIT(init_task.tasks),
+#ifdef CONFIG_SMP
+ .pushable_tasks = PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO),
+#endif
+#ifdef CONFIG_CGROUP_SCHED
+ .sched_task_group = &root_task_group,
+#endif
+ .ptraced = LIST_HEAD_INIT(init_task.ptraced),
+ .ptrace_entry = LIST_HEAD_INIT(init_task.ptrace_entry),
+ .real_parent = &init_task,
+ .parent = &init_task,
+ .children = LIST_HEAD_INIT(init_task.children),
+ .sibling = LIST_HEAD_INIT(init_task.sibling),
+ .group_leader = &init_task,
+ 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(init_task.pending.list),
+ .signal = {{0}}
+ },
+ .blocked = {{0}},
+ .alloc_lock = __SPIN_LOCK_UNLOCKED(init_task.alloc_lock),
+ .journal_info = NULL,
+ INIT_CPU_TIMERS(init_task)
+ .pi_lock = __RAW_SPIN_LOCK_UNLOCKED(init_task.pi_lock),
+ .timer_slack_ns = 50000, /* 50 usec default slack */
+ .thread_pid = &init_struct_pid,
+ .thread_group = LIST_HEAD_INIT(init_task.thread_group),
+ .thread_node = LIST_HEAD_INIT(init_signals.thread_head),
+#ifdef CONFIG_AUDITSYSCALL
+ .loginuid = INVALID_UID,
+ .sessionid = AUDIT_SID_UNSET,
+#endif
+#ifdef CONFIG_PERF_EVENTS
+ .perf_event_mutex = __MUTEX_INITIALIZER(init_task.perf_event_mutex),
+ .perf_event_list = LIST_HEAD_INIT(init_task.perf_event_list),
+#endif
+#ifdef CONFIG_PREEMPT_RCU
+ .rcu_read_lock_nesting = 0,
+ .rcu_read_unlock_special.s = 0,
+ .rcu_node_entry = LIST_HEAD_INIT(init_task.rcu_node_entry),
+ .rcu_blocked_node = NULL,
+#endif
+#ifdef CONFIG_TASKS_RCU
+ .rcu_tasks_holdout = false,
+ .rcu_tasks_holdout_list = LIST_HEAD_INIT(init_task.rcu_tasks_holdout_list),
+ .rcu_tasks_idle_cpu = -1,
+#endif
+#ifdef CONFIG_CPUSETS
+ .mems_allowed_seq = SEQCNT_ZERO(init_task.mems_allowed_seq),
+#endif
+#ifdef CONFIG_RT_MUTEXES
+ .pi_waiters = RB_ROOT_CACHED,
+ .pi_top_task = NULL,
+#endif
+ INIT_PREV_CPUTIME(init_task)
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
+ .vtime.seqcount = SEQCNT_ZERO(init_task.vtime_seqcount),
+ .vtime.starttime = 0,
+ .vtime.state = VTIME_SYS,
+#endif
+#ifdef CONFIG_NUMA_BALANCING
+ .numa_preferred_nid = -1,
+ .numa_group = NULL,
+ .numa_faults = NULL,
+#endif
+#ifdef CONFIG_KASAN
+ .kasan_depth = 1,
+#endif
+#ifdef CONFIG_TRACE_IRQFLAGS
+ .softirqs_enabled = 1,
+#endif
+#ifdef CONFIG_LOCKDEP
+ .lockdep_recursion = 0,
+#endif
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+ .ret_stack = NULL,
+#endif
+#if defined(CONFIG_TRACING) && defined(CONFIG_PREEMPT)
+ .trace_recursion = 0,
+#endif
+#ifdef CONFIG_LIVEPATCH
+ .patch_state = KLP_UNDEFINED,
+#endif
+#ifdef CONFIG_SECURITY
+ .security = NULL,
+#endif
+#else /* CONFIG_SCHED_PDS */
#ifdef CONFIG_THREAD_INFO_IN_TASK
.thread_info = INIT_THREAD_INFO(init_task),
.stack_refcount = REFCOUNT_INIT(1),
@@ -181,6 +301,7 @@ struct task_struct init_task
#ifdef CONFIG_SECURITY
.security = NULL,
#endif
+#endif /* CONFIG_SCHED_PDS */
};
EXPORT_SYMBOL(init_task);
diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index c87ee6412b36..4045c8532027 100644
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -632,7 +632,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
return ret;
}
-#ifdef CONFIG_SMP
+#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_PDS)
/*
* Helper routine for generate_sched_domains().
* Do cpusets a, b have overlapping effective cpus_allowed masks?
@@ -1007,7 +1007,7 @@ static void rebuild_sched_domains_locked(void)
/* Have scheduler rebuild the domains */
partition_and_rebuild_sched_domains(ndoms, doms, attr);
}
-#else /* !CONFIG_SMP */
+#else /* !CONFIG_SMP || CONFIG_SCHED_PDS */
static void rebuild_sched_domains_locked(void)
{
}
diff --git a/kernel/delayacct.c b/kernel/delayacct.c
index 27725754ac99..769d773c7182 100644
--- a/kernel/delayacct.c
+++ b/kernel/delayacct.c
@@ -106,7 +106,7 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
*/
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;
diff --git a/kernel/exit.c b/kernel/exit.c
index a46a50d67002..58043176b285 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -131,7 +131,7 @@ static void __exit_signal(struct task_struct *tsk)
sig->curr_target = next_thread(tsk);
}
- add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
+ add_device_randomness((const void*) &tsk_seruntime(tsk),
sizeof(unsigned long long));
/*
@@ -152,7 +152,7 @@ static void __exit_signal(struct task_struct *tsk)
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);
diff --git a/kernel/livepatch/transition.c b/kernel/livepatch/transition.c
index cdf318d86dd6..baa525865d5c 100644
--- a/kernel/livepatch/transition.c
+++ b/kernel/livepatch/transition.c
@@ -306,7 +306,11 @@ static bool klp_try_switch_task(struct task_struct *task)
*/
rq = task_rq_lock(task, &flags);
+#ifdef CONFIG_SCHED_PDS
+ if (task_running(task) && task != current) {
+#else
if (task_running(rq, task) && task != current) {
+#endif
snprintf(err_buf, STACK_ERR_BUF_SIZE,
"%s: %s:%d is running\n", __func__, task->comm,
task->pid);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 2874bf556162..fad8a279fdfa 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -229,7 +229,7 @@ static inline bool unlock_rt_mutex_safe(struct rt_mutex *lock,
* Only use with rt_mutex_waiter_{less,equal}()
*/
#define task_to_waiter(p) \
- &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline }
+ &(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = __tsk_deadline(p) }
static inline int
rt_mutex_waiter_less(struct rt_mutex_waiter *left,
@@ -680,7 +680,7 @@ static int rt_mutex_adjust_prio_chain(struct task_struct *task,
* the values of the node being removed.
*/
waiter->prio = task->prio;
- waiter->deadline = task->dl.deadline;
+ waiter->deadline = __tsk_deadline(task);
rt_mutex_enqueue(lock, waiter);
@@ -953,7 +953,7 @@ static int task_blocks_on_rt_mutex(struct rt_mutex *lock,
waiter->task = task;
waiter->lock = lock;
waiter->prio = task->prio;
- waiter->deadline = task->dl.deadline;
+ waiter->deadline = __tsk_deadline(task);
/* Get the top priority waiter on the lock */
if (rt_mutex_has_waiters(lock))
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index 21fb5a5662b5..8ebe4e33fb5f 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -16,15 +16,21 @@ ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
CFLAGS_core.o := $(PROFILING) -fno-omit-frame-pointer
endif
-obj-y += core.o loadavg.o clock.o cputime.o
-obj-y += idle.o fair.o rt.o deadline.o
-obj-y += wait.o wait_bit.o swait.o completion.o
-
-obj-$(CONFIG_SMP) += cpupri.o cpudeadline.o topology.o stop_task.o pelt.o
+ifdef CONFIG_SCHED_PDS
+obj-y += pds.o
+else
+obj-y += core.o
+obj-y += fair.o rt.o deadline.o
+obj-$(CONFIG_SMP) += cpudeadline.o topology.o stop_task.o
obj-$(CONFIG_SCHED_AUTOGROUP) += autogroup.o
-obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_SCHED_DEBUG) += debug.o
obj-$(CONFIG_CGROUP_CPUACCT) += cpuacct.o
+endif
+obj-y += loadavg.o clock.o cputime.o
+obj-y += idle.o
+obj-y += wait.o wait_bit.o swait.o completion.o
+obj-$(CONFIG_SMP) += cpupri.o pelt.o
+obj-$(CONFIG_SCHEDSTATS) += stats.o
obj-$(CONFIG_CPU_FREQ) += cpufreq.o
obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o
obj-$(CONFIG_MEMBARRIER) += membarrier.o
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 86800b4d5453..07f278dc3137 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -185,6 +185,7 @@ static unsigned int get_next_freq(struct sugov_policy *sg_policy,
return cpufreq_driver_resolve_freq(policy, freq);
}
+#ifndef CONFIG_SCHED_PDS
/*
* This function computes an effective utilization for the given CPU, to be
* used for frequency selection given the linear relation: f = u * f_max.
@@ -302,6 +303,13 @@ static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
return schedutil_cpu_util(sg_cpu->cpu, util, max, FREQUENCY_UTIL, NULL);
}
+#else /* CONFIG_SCHED_PDS */
+static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
+{
+ sg_cpu->max = arch_scale_cpu_capacity(sg_cpu->cpu);
+ return sg_cpu->max;
+}
+#endif
/**
* sugov_iowait_reset() - Reset the IO boost status of a CPU.
@@ -445,7 +453,9 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
*/
static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu, struct sugov_policy *sg_policy)
{
+#ifndef CONFIG_SCHED_PDS
if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_dl)
+#endif
sg_policy->limits_changed = true;
}
@@ -688,6 +698,7 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy)
}
ret = sched_setattr_nocheck(thread, &attr);
+
if (ret) {
kthread_stop(thread);
pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__);
@@ -918,6 +929,7 @@ static int __init sugov_register(void)
fs_initcall(sugov_register);
#ifdef CONFIG_ENERGY_MODEL
+#ifndef CONFIG_SCHED_PDS
extern bool sched_energy_update;
extern struct mutex sched_energy_mutex;
@@ -948,4 +960,10 @@ void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
}
}
+#else /* CONFIG_SCHED_PDS */
+void sched_cpufreq_governor_change(struct cpufreq_policy *policy,
+ struct cpufreq_governor *old_gov)
+{
+}
+#endif
#endif
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 46ed4e1383e2..0a9548ee995c 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -122,7 +122,12 @@ void account_user_time(struct task_struct *p, u64 cputime)
p->utime += cputime;
account_group_user_time(p, cputime);
+#ifdef CONFIG_SCHED_PDS
+ index = (task_nice(p) > 0 || task_running_idle(p)) ? CPUTIME_NICE :
+ CPUTIME_USER;
+#else
index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
+#endif
/* Add user time to cpustat. */
task_group_account_field(p, index, cputime);
@@ -146,7 +151,11 @@ void account_guest_time(struct task_struct *p, u64 cputime)
p->gtime += cputime;
/* Add guest time to cpustat. */
+#ifdef CONFIG_SCHED_PDS
+ if (task_nice(p) > 0 || task_running_idle(p)) {
+#else
if (task_nice(p) > 0) {
+#endif
cpustat[CPUTIME_NICE] += cputime;
cpustat[CPUTIME_GUEST_NICE] += cputime;
} else {
@@ -269,7 +278,7 @@ static inline u64 account_other_time(u64 max)
#ifdef CONFIG_64BIT
static inline u64 read_sum_exec_runtime(struct task_struct *t)
{
- return t->se.sum_exec_runtime;
+ return tsk_seruntime(t);
}
#else
static u64 read_sum_exec_runtime(struct task_struct *t)
@@ -279,7 +288,7 @@ static u64 read_sum_exec_runtime(struct task_struct *t)
struct rq *rq;
rq = task_rq_lock(t, &rf);
- ns = t->se.sum_exec_runtime;
+ ns = tsk_seruntime(t);
task_rq_unlock(rq, t, &rf);
return ns;
@@ -663,7 +672,7 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
{
struct task_cputime cputime = {
- .sum_exec_runtime = p->se.sum_exec_runtime,
+ .sum_exec_runtime = tsk_seruntime(p),
};
task_cputime(p, &cputime.utime, &cputime.stime);
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index f65ef1e2f204..454fa7e460e3 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -355,6 +355,7 @@ void cpu_startup_entry(enum cpuhp_state state)
do_idle();
}
+#ifndef CONFIG_SCHED_PDS
/*
* idle-task scheduling class.
*/
@@ -479,3 +480,4 @@ const struct sched_class idle_sched_class = {
.switched_to = switched_to_idle,
.update_curr = update_curr_idle,
};
+#endif
diff --git a/kernel/sched/pds.c b/kernel/sched/pds.c
new file mode 100644
index 000000000000..aefbd9cebcfb
--- /dev/null
+++ b/kernel/sched/pds.c
@@ -0,0 +1,6566 @@
+/*
+ * kernel/sched/pds.c, was kernel/sched.c
+ *
+ * PDS-mq Core kernel scheduler code and related syscalls
+ *
+ * Copyright (C) 1991-2002 Linus Torvalds
+ *
+ * 2009-08-13 Brainfuck deadline scheduling policy by Con Kolivas deletes
+ * a whole lot of those previous things.
+ * 2017-09-06 Priority and Deadline based Skip list multiple queue kernel
+ * scheduler by Alfred Chen.
+ */
+#include "pds_sched.h"
+
+#include <linux/sched/rt.h>
+
+#include <linux/context_tracking.h>
+#include <linux/compat.h>
+#include <linux/blkdev.h>
+#include <linux/delayacct.h>
+#include <linux/freezer.h>
+#include <linux/init_task.h>
+#include <linux/kprobes.h>
+#include <linux/mmu_context.h>
+#include <linux/nmi.h>
+#include <linux/profile.h>
+#include <linux/rcupdate_wait.h>
+#include <linux/security.h>
+#include <linux/syscalls.h>
+#include <linux/wait_bit.h>
+
+#include <linux/kcov.h>
+
+#include <asm/switch_to.h>
+
+#include "../workqueue_internal.h"
+#include "../smpboot.h"
+
+#include "pelt.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/sched.h>
+
+
+#define rt_prio(prio) ((prio) < MAX_RT_PRIO)
+#define rt_task(p) rt_prio((p)->prio)
+#define rt_policy(policy) ((policy) == SCHED_FIFO || \
+ (policy) == SCHED_RR || \
+ (policy) == SCHED_ISO)
+#define task_has_rt_policy(p) (rt_policy((p)->policy))
+
+#define idle_policy(policy) ((policy) == SCHED_IDLE)
+#define idleprio_task(p) unlikely(idle_policy((p)->policy))
+
+#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 US_TO_NS(TIME) ((TIME) << 10)
+
+#define RESCHED_US (100) /* Reschedule if less than this many μs left */
+
+enum {
+ BASE_CPU_AFFINITY_CHK_LEVEL = 1,
+#ifdef CONFIG_SCHED_SMT
+ SMT_CPU_AFFINITY_CHK_LEVEL_SPACE_HOLDER,
+#endif
+#ifdef CONFIG_SCHED_MC
+ MC_CPU_AFFINITY_CHK_LEVEL_SPACE_HOLDER,
+#endif
+ NR_CPU_AFFINITY_CHK_LEVEL
+};
+
+static inline void print_scheduler_version(void)
+{
+ printk(KERN_INFO "pds: PDS-mq CPU Scheduler 0.99o by Alfred Chen and kept alive artificially by Tk-Glitch.\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.
+ */
+#define SCHED_DEFAULT_RR (4)
+int rr_interval __read_mostly = SCHED_DEFAULT_RR;
+
+static int __init rr_interval_set(char *str)
+{
+ u32 rr;
+
+ pr_info("rr_interval: ");
+ if (kstrtouint(str, 0, &rr)) {
+ pr_cont("using default of %u, unable to parse %s\n",
+ rr_interval, str);
+ return 1;
+ }
+
+ rr_interval = rr;
+ pr_cont("%d\n", rr_interval);
+
+ return 1;
+}
+__setup("rr_interval=", rr_interval_set);
+
+
+static const u64 sched_prio2deadline[NICE_WIDTH] = {
+/* -20 */ 6291456, 6920601, 7612661, 8373927, 9211319,
+/* -15 */ 10132450, 11145695, 12260264, 13486290, 14834919,
+/* -10 */ 16318410, 17950251, 19745276, 21719803, 23891783,
+/* -5 */ 26280961, 28909057, 31799962, 34979958, 38477953,
+/* 0 */ 42325748, 46558322, 51214154, 56335569, 61969125,
+/* 5 */ 68166037, 74982640, 82480904, 90728994, 99801893,
+/* 10 */ 109782082, 120760290, 132836319, 146119950, 160731945,
+/* 15 */ 176805139, 194485652, 213934217, 235327638, 258860401
+};
+
+/**
+ * sched_yield_type - Choose what sort of yield sched_yield will perform.
+ * 0: No yield.
+ * 1: Yield only to better priority/deadline tasks. (default)
+ * 2: Expire timeslice and recalculate deadline.
+ */
+int sched_yield_type __read_mostly = 1;
+
+/*
+ * 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);
+}
+
+#ifdef CONFIG_SMP
+enum {
+SCHED_RQ_EMPTY = 0,
+SCHED_RQ_IDLE,
+SCHED_RQ_NORMAL_0,
+SCHED_RQ_NORMAL_1,
+SCHED_RQ_NORMAL_2,
+SCHED_RQ_NORMAL_3,
+SCHED_RQ_NORMAL_4,
+SCHED_RQ_NORMAL_5,
+SCHED_RQ_NORMAL_6,
+SCHED_RQ_NORMAL_7,
+SCHED_RQ_ISO,
+SCHED_RQ_RT,
+NR_SCHED_RQ_QUEUED_LEVEL
+};
+
+static cpumask_t sched_rq_queued_masks[NR_SCHED_RQ_QUEUED_LEVEL]
+____cacheline_aligned_in_smp;
+
+static DECLARE_BITMAP(sched_rq_queued_masks_bitmap, NR_SCHED_RQ_QUEUED_LEVEL)
+____cacheline_aligned_in_smp;
+
+static cpumask_t sched_rq_pending_masks[NR_SCHED_RQ_QUEUED_LEVEL]
+____cacheline_aligned_in_smp;
+
+static DECLARE_BITMAP(sched_rq_pending_masks_bitmap, NR_SCHED_RQ_QUEUED_LEVEL)
+____cacheline_aligned_in_smp;
+
+DEFINE_PER_CPU(cpumask_t [NR_CPU_AFFINITY_CHK_LEVEL], sched_cpu_affinity_chk_masks);
+DEFINE_PER_CPU(cpumask_t *, sched_cpu_llc_start_mask);
+DEFINE_PER_CPU(cpumask_t *, sched_cpu_affinity_chk_end_masks);
+
+#ifdef CONFIG_SCHED_SMT
+DEFINE_PER_CPU(int, sched_sibling_cpu);
+DEFINE_STATIC_KEY_FALSE(sched_smt_present);
+EXPORT_SYMBOL_GPL(sched_smt_present);
+
+static cpumask_t sched_cpu_sg_idle_mask ____cacheline_aligned_in_smp;
+
+#ifdef CONFIG_SMT_NICE
+/*
+ * Preemptible sibling group mask
+ * Which all sibling cpus are running at PRIO_LIMIT or IDLE_PRIO
+ */
+static cpumask_t sched_cpu_psg_mask ____cacheline_aligned_in_smp;
+/*
+ * SMT supressed mask
+ * When a cpu is running task with NORMAL/ISO/RT policy, its sibling cpu
+ * will be supressed to run IDLE priority task.
+ */
+static cpumask_t sched_smt_supressed_mask ____cacheline_aligned_in_smp;
+#endif /* CONFIG_SMT_NICE */
+#endif
+
+static int sched_rq_prio[NR_CPUS] ____cacheline_aligned;
+
+/*
+ * Keep a unique ID per domain (we use the first CPUs number in the cpumask of
+ * the domain), this allows us to quickly tell if two cpus are in the same cache
+ * domain, see cpus_share_cache().
+ */
+DEFINE_PER_CPU(int, sd_llc_id);
+
+int __weak arch_sd_sibling_asym_packing(void)
+{
+ return 0*SD_ASYM_PACKING;
+}
+#else
+struct rq *uprq;
+#endif /* CONFIG_SMP */
+
+static DEFINE_MUTEX(sched_hotcpu_mutex);
+
+DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
+
+#ifndef prepare_arch_switch
+# define prepare_arch_switch(next) do { } while (0)
+#endif
+#ifndef finish_arch_post_lock_switch
+# define finish_arch_post_lock_switch() do { } while (0)
+#endif
+
+/*
+ * Context: p->pi_lock
+ */
+static inline struct rq
+*__task_access_lock(struct task_struct *p, raw_spinlock_t **plock)
+{
+ struct rq *rq;
+ for (;;) {
+ rq = task_rq(p);
+ if (p->on_cpu || task_on_rq_queued(p)) {
+ raw_spin_lock(&rq->lock);
+ if (likely((p->on_cpu || task_on_rq_queued(p))
+ && rq == task_rq(p))) {
+ *plock = &rq->lock;
+ return rq;
+ }
+ raw_spin_unlock(&rq->lock);
+ } else if (task_on_rq_migrating(p)) {
+ do {
+ cpu_relax();
+ } while (unlikely(task_on_rq_migrating(p)));
+ } else {
+ *plock = NULL;
+ return rq;
+ }
+ }
+}
+
+static inline void
+__task_access_unlock(struct task_struct *p, raw_spinlock_t *lock)
+{
+ if (NULL != lock)
+ raw_spin_unlock(lock);
+}
+
+static inline struct rq
+*task_access_lock_irqsave(struct task_struct *p, raw_spinlock_t **plock,
+ unsigned long *flags)
+{
+ struct rq *rq;
+ for (;;) {
+ rq = task_rq(p);
+ if (p->on_cpu || task_on_rq_queued(p)) {
+ raw_spin_lock_irqsave(&rq->lock, *flags);
+ if (likely((p->on_cpu || task_on_rq_queued(p))
+ && rq == task_rq(p))) {
+ *plock = &rq->lock;
+ return rq;
+ }
+ raw_spin_unlock_irqrestore(&rq->lock, *flags);
+ } else if (task_on_rq_migrating(p)) {
+ do {
+ cpu_relax();
+ } while (unlikely(task_on_rq_migrating(p)));
+ } else {
+ raw_spin_lock_irqsave(&p->pi_lock, *flags);
+ if (likely(!p->on_cpu && !p->on_rq &&
+ rq == task_rq(p))) {
+ *plock = &p->pi_lock;
+ return rq;
+ }
+ raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
+ }
+ }
+}
+
+static inline void
+task_access_unlock_irqrestore(struct task_struct *p, raw_spinlock_t *lock,
+ unsigned long *flags)
+{
+ raw_spin_unlock_irqrestore(lock, *flags);
+}
+
+/*
+ * __task_rq_lock - lock the rq @p resides on.
+ */
+struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ struct rq *rq;
+
+ lockdep_assert_held(&p->pi_lock);
+
+ for (;;) {
+ rq = task_rq(p);
+ raw_spin_lock(&rq->lock);
+ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
+ return rq;
+ raw_spin_unlock(&rq->lock);
+
+ while (unlikely(task_on_rq_migrating(p)))
+ cpu_relax();
+ }
+}
+
+/*
+ * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
+ */
+struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+ __acquires(p->pi_lock)
+ __acquires(rq->lock)
+{
+ struct rq *rq;
+
+ for (;;) {
+ raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
+ rq = task_rq(p);
+ raw_spin_lock(&rq->lock);
+ /*
+ * move_queued_task() task_rq_lock()
+ *
+ * ACQUIRE (rq->lock)
+ * [S] ->on_rq = MIGRATING [L] rq = task_rq()
+ * WMB (__set_task_cpu()) ACQUIRE (rq->lock);
+ * [S] ->cpu = new_cpu [L] task_rq()
+ * [L] ->on_rq
+ * RELEASE (rq->lock)
+ *
+ * If we observe the old CPU in task_rq_lock(), the acquire of
+ * the old rq->lock will fully serialize against the stores.
+ *
+ * If we observe the new CPU in task_rq_lock(), the address
+ * dependency headed by '[L] rq = task_rq()' and the acquire
+ * will pair with the WMB to ensure we then also see migrating.
+ */
+ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
+ return rq;
+ }
+ raw_spin_unlock(&rq->lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
+
+ while (unlikely(task_on_rq_migrating(p)))
+ cpu_relax();
+ }
+}
+
+/*
+ * RQ-clock updating methods:
+ */
+
+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...
+ */
+ s64 __maybe_unused steal = 0, irq_delta = 0;
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+ 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((&paravirt_steal_rq_enabled))) {
+ 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;
+
+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
+ if ((irq_delta + steal))
+ update_irq_load_avg(rq, irq_delta + steal);
+#endif
+}
+
+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 void update_task_priodl(struct task_struct *p)
+{
+ p->priodl = (((u64) (p->prio))<<56) | ((p->deadline)>>8);
+}
+
+/*
+ * 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 task_deadline_diff(const struct task_struct *p)
+{
+ return sched_prio2deadline[TASK_USER_PRIO(p)];
+}
+
+static inline u64 static_deadline_diff(int static_prio)
+{
+ return sched_prio2deadline[USER_PRIO(static_prio)];
+}
+
+/*
+ * The time_slice is only refilled when it is empty and that is when we set a
+ * new deadline for non-rt tasks.
+ */
+static inline void time_slice_expired(struct task_struct *p, struct rq *rq)
+{
+ p->time_slice = timeslice();
+ if (p->prio >= NORMAL_PRIO)
+ p->deadline = rq->clock + task_deadline_diff(p);
+
+ update_task_priodl(p);
+}
+
+static inline struct task_struct *rq_first_queued_task(struct rq *rq)
+{
+ struct skiplist_node *node = rq->sl_header.next[0];
+
+ if (node == &rq->sl_header)
+ return rq->idle;
+
+ return skiplist_entry(node, struct task_struct, sl_node);
+}
+
+static inline struct task_struct *rq_second_queued_task(struct rq *rq)
+{
+ struct skiplist_node *node = rq->sl_header.next[0]->next[0];
+
+ if (node == &rq->sl_header)
+ return rq->idle;
+
+ return skiplist_entry(node, struct task_struct, sl_node);
+}
+
+static inline int is_second_in_rq(struct task_struct *p, struct rq *rq)
+{
+ return (p->sl_node.prev[0]->prev[0] == &rq->sl_header);
+}
+
+static const int task_dl_hash_tbl[] = {
+/* 0 4 8 12 */
+ 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1,
+/* 16 20 24 28 */
+ 1, 1, 1, 2, 2, 2, 2, 2, 3, 3, 3, 4, 4, 5, 6, 7
+};
+
+static inline int
+task_deadline_level(const struct task_struct *p, const struct rq *rq)
+{
+ u64 delta = (rq->clock + sched_prio2deadline[39] - p->deadline) >> 23;
+
+ delta = min((size_t)delta, ARRAY_SIZE(task_dl_hash_tbl) - 1);
+ return task_dl_hash_tbl[delta];
+}
+
+/*
+ * cmpxchg based fetch_or, macro so it works for different integer types
+ */
+#define fetch_or(ptr, mask) \
+ ({ \
+ typeof(ptr) _ptr = (ptr); \
+ typeof(mask) _mask = (mask); \
+ typeof(*_ptr) _old, _val = *_ptr; \
+ \
+ for (;;) { \
+ _old = cmpxchg(_ptr, _val, _val | _mask); \
+ if (_old == _val) \
+ break; \
+ _val = _old; \
+ } \
+ _old; \
+})
+
+#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
+/*
+ * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
+ * this avoids any races wrt polling state changes and thereby avoids
+ * spurious IPIs.
+ */
+static bool set_nr_and_not_polling(struct task_struct *p)
+{
+ struct thread_info *ti = task_thread_info(p);
+ return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
+}
+
+/*
+ * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set.
+ *
+ * If this returns true, then the idle task promises to call
+ * sched_ttwu_pending() and reschedule soon.
+ */
+static bool set_nr_if_polling(struct task_struct *p)
+{
+ struct thread_info *ti = task_thread_info(p);
+ typeof(ti->flags) old, val = READ_ONCE(ti->flags);
+
+ for (;;) {
+ if (!(val & _TIF_POLLING_NRFLAG))
+ return false;
+ if (val & _TIF_NEED_RESCHED)
+ return true;
+ old = cmpxchg(&ti->flags, val, val | _TIF_NEED_RESCHED);
+ if (old == val)
+ break;
+ val = old;
+ }
+ return true;
+}
+
+#else
+static bool set_nr_and_not_polling(struct task_struct *p)
+{
+ set_tsk_need_resched(p);
+ return true;
+}
+
+#ifdef CONFIG_SMP
+static bool set_nr_if_polling(struct task_struct *p)
+{
+ return false;
+}
+#endif
+#endif
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_SMT_NICE
+static void resched_cpu_if_curr_is(int cpu, int priority)
+{
+ struct rq *rq = cpu_rq(cpu);
+
+ rcu_read_lock();
+
+ if (rcu_dereference(rq->curr)->prio != priority)
+ goto out;
+
+ if (set_nr_if_polling(rq->idle)) {
+ trace_sched_wake_idle_without_ipi(cpu);
+ } else {
+ if (!do_raw_spin_trylock(&rq->lock))
+ goto out;
+ spin_acquire(&rq->lock.dep_map, SINGLE_DEPTH_NESTING, 1, _RET_IP_);
+
+ if (priority == rq->curr->prio)
+ smp_send_reschedule(cpu);
+ /* Else CPU is not idle, do nothing here */
+
+ spin_release(&rq->lock.dep_map, 1, _RET_IP_);
+ do_raw_spin_unlock(&rq->lock);
+ }
+
+out:
+ rcu_read_unlock();
+}
+#endif /* CONFIG_SMT_NICE */
+
+static inline bool
+__update_cpumasks_bitmap(int cpu, unsigned long *plevel, unsigned long level,
+ cpumask_t cpumasks[], unsigned long bitmap[])
+{
+ if (*plevel == level)
+ return false;
+
+ cpumask_clear_cpu(cpu, cpumasks + *plevel);
+ if (cpumask_empty(cpumasks + *plevel))
+ clear_bit(*plevel, bitmap);
+ cpumask_set_cpu(cpu, cpumasks + level);
+ set_bit(level, bitmap);
+
+ *plevel = level;
+
+ return true;
+}
+
+static inline int
+task_running_policy_level(const struct task_struct *p, const struct rq *rq)
+{
+ int prio = p->prio;
+
+ if (NORMAL_PRIO == prio)
+ return SCHED_RQ_NORMAL_0 + task_deadline_level(p, rq);
+
+ if (ISO_PRIO == prio)
+ return SCHED_RQ_ISO;
+ if (prio < MAX_RT_PRIO)
+ return SCHED_RQ_RT;
+ return PRIO_LIMIT - prio;
+}
+
+static inline void update_sched_rq_queued_masks_normal(struct rq *rq)
+{
+ struct task_struct *p = rq_first_queued_task(rq);
+
+ if (p->prio != NORMAL_PRIO)
+ return;
+
+ __update_cpumasks_bitmap(cpu_of(rq), &rq->queued_level,
+ task_running_policy_level(p, rq),
+ &sched_rq_queued_masks[0],
+ &sched_rq_queued_masks_bitmap[0]);
+}
+
+#ifdef CONFIG_SMT_NICE
+static inline void update_sched_cpu_psg_mask(const int cpu)
+{
+ cpumask_t tmp;
+
+ cpumask_or(&tmp, &sched_rq_queued_masks[SCHED_RQ_EMPTY],
+ &sched_rq_queued_masks[SCHED_RQ_IDLE]);
+ cpumask_and(&tmp, &tmp, cpu_smt_mask(cpu));
+ if (cpumask_equal(&tmp, cpu_smt_mask(cpu)))
+ cpumask_or(&sched_cpu_psg_mask, &sched_cpu_psg_mask,
+ cpu_smt_mask(cpu));
+ else
+ cpumask_andnot(&sched_cpu_psg_mask, &sched_cpu_psg_mask,
+ cpu_smt_mask(cpu));
+}
+#endif
+
+static inline void update_sched_rq_queued_masks(struct rq *rq)
+{
+ int cpu = cpu_of(rq);
+ struct task_struct *p = rq_first_queued_task(rq);
+ unsigned long level;
+#ifdef CONFIG_SCHED_SMT
+ unsigned long last_level = rq->queued_level;
+#endif
+
+ level = task_running_policy_level(p, rq);
+ sched_rq_prio[cpu] = p->prio;
+
+ if (!__update_cpumasks_bitmap(cpu, &rq->queued_level, level,
+ &sched_rq_queued_masks[0],
+ &sched_rq_queued_masks_bitmap[0]))
+ return;
+
+#ifdef CONFIG_SCHED_SMT
+ if (cpu == per_cpu(sched_sibling_cpu, cpu))
+ return;
+
+ if (SCHED_RQ_EMPTY == last_level) {
+ cpumask_andnot(&sched_cpu_sg_idle_mask, &sched_cpu_sg_idle_mask,
+ cpu_smt_mask(cpu));
+ } else if (SCHED_RQ_EMPTY == level) {
+ cpumask_t tmp;
+
+ cpumask_and(&tmp, cpu_smt_mask(cpu),
+ &sched_rq_queued_masks[SCHED_RQ_EMPTY]);
+ if (cpumask_equal(&tmp, cpu_smt_mask(cpu)))
+ cpumask_or(&sched_cpu_sg_idle_mask, cpu_smt_mask(cpu),
+ &sched_cpu_sg_idle_mask);
+ }
+
+#ifdef CONFIG_SMT_NICE
+ if (level <= SCHED_RQ_IDLE && last_level > SCHED_RQ_IDLE) {
+ cpumask_clear_cpu(per_cpu(sched_sibling_cpu, cpu),
+ &sched_smt_supressed_mask);
+ update_sched_cpu_psg_mask(cpu);
+ resched_cpu_if_curr_is(per_cpu(sched_sibling_cpu, cpu), PRIO_LIMIT);
+ } else if (last_level <= SCHED_RQ_IDLE && level > SCHED_RQ_IDLE) {
+ cpumask_set_cpu(per_cpu(sched_sibling_cpu, cpu),
+ &sched_smt_supressed_mask);
+ update_sched_cpu_psg_mask(cpu);
+ resched_cpu_if_curr_is(per_cpu(sched_sibling_cpu, cpu), IDLE_PRIO);
+ }
+#endif /* CONFIG_SMT_NICE */
+#endif
+}
+
+static inline void update_sched_rq_pending_masks(struct rq *rq)
+{
+ unsigned long level;
+ struct task_struct *p = rq_second_queued_task(rq);
+
+ level = task_running_policy_level(p, rq);
+
+ __update_cpumasks_bitmap(cpu_of(rq), &rq->pending_level, level,
+ &sched_rq_pending_masks[0],
+ &sched_rq_pending_masks_bitmap[0]);
+}
+
+#else /* CONFIG_SMP */
+static inline void update_sched_rq_queued_masks(struct rq *rq) {}
+static inline void update_sched_rq_queued_masks_normal(struct rq *rq) {}
+static inline void update_sched_rq_pending_masks(struct rq *rq) {}
+#endif
+
+#ifdef CONFIG_NO_HZ_FULL
+/*
+ * Tick may be needed by tasks in the runqueue depending on their policy and
+ * requirements. If tick is needed, lets send the target an IPI to kick it out
+ * of nohz mode if necessary.
+ */
+static inline void sched_update_tick_dependency(struct rq *rq)
+{
+ int cpu;
+
+ if (!tick_nohz_full_enabled())
+ return;
+
+ cpu = cpu_of(rq);
+
+ if (!tick_nohz_full_cpu(cpu))
+ return;
+
+ if (rq->nr_running < 2)
+ tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED);
+ else
+ tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
+}
+#else /* !CONFIG_NO_HZ_FULL */
+static inline void sched_update_tick_dependency(struct rq *rq) { }
+#endif
+
+/*
+ * Removing from the runqueue. 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.
+ *
+ * Context: rq->lock
+ */
+static inline void dequeue_task(struct task_struct *p, struct rq *rq, int flags)
+{
+ lockdep_assert_held(&rq->lock);
+
+ WARN_ONCE(task_rq(p) != rq, "pds: dequeue task reside on cpu%d from cpu%d\n",
+ task_cpu(p), cpu_of(rq));
+ if (skiplist_del_init(&rq->sl_header, &p->sl_node)) {
+ update_sched_rq_queued_masks(rq);
+ update_sched_rq_pending_masks(rq);
+ } else if (is_second_in_rq(p, rq))
+ update_sched_rq_pending_masks(rq);
+ rq->nr_running--;
+
+ sched_update_tick_dependency(rq);
+ psi_dequeue(p, flags & DEQUEUE_SLEEP);
+
+ sched_info_dequeued(rq, p);
+}
+
+/*
+ * To determine if it's safe for a task of SCHED_IDLE to actually run as
+ * an idle task, we ensure none of the following conditions are met.
+ */
+static inline bool idleprio_suitable(struct task_struct *p)
+{
+ return (!freezing(p) && !signal_pending(p) &&
+ !(task_contributes_to_load(p)) && !(p->flags & (PF_EXITING)));
+}
+
+/*
+ * pds_skiplist_random_level -- Returns a pseudo-random level number for skip
+ * list node which is used in PDS run queue.
+ *
+ * In current implementation, based on testing, the first 8 bits in microseconds
+ * of niffies are suitable for random level population.
+ * find_first_bit() is used to satisfy p = 0.5 between each levels, and there
+ * should be platform hardware supported instruction(known as ctz/clz) to speed
+ * up this function.
+ * The skiplist level for a task is populated when task is created and doesn't
+ * change in task's life time. When task is being inserted into run queue, this
+ * skiplist level is set to task's sl_node->level, the skiplist insert function
+ * may change it based on current level of the skip lsit.
+ */
+static inline int pds_skiplist_random_level(const struct task_struct *p)
+{
+ long unsigned int randseed;
+
+ /*
+ * 1. Some architectures don't have better than microsecond resolution
+ * so mask out ~microseconds as a factor of the random seed for skiplist
+ * insertion.
+ * 2. Use address of task structure pointer as another factor of the
+ * random seed for task burst forking scenario.
+ */
+ randseed = (task_rq(p)->clock ^ (long unsigned int)p) >> 10;
+
+ return find_first_bit(&randseed, NUM_SKIPLIST_LEVEL - 1);
+}
+
+/**
+ * pds_skiplist_task_search -- search function used in PDS run queue skip list
+ * node insert operation.
+ * @it: iterator pointer to the node in the skip list
+ * @node: pointer to the skiplist_node to be inserted
+ *
+ * Returns true if key of @it is less or equal to key value of @node, otherwise
+ * false.
+ */
+static inline bool
+pds_skiplist_task_search(struct skiplist_node *it, struct skiplist_node *node)
+{
+ return (skiplist_entry(it, struct task_struct, sl_node)->priodl <=
+ skiplist_entry(node, struct task_struct, sl_node)->priodl);
+}
+
+/*
+ * Define the skip list insert function for PDS
+ */
+DEFINE_SKIPLIST_INSERT_FUNC(pds_skiplist_insert, pds_skiplist_task_search);
+
+/*
+ * Adding task to the runqueue.
+ *
+ * Context: rq->lock
+ */
+static inline void enqueue_task(struct task_struct *p, struct rq *rq, int flags)
+{
+ lockdep_assert_held(&rq->lock);
+
+ WARN_ONCE(task_rq(p) != rq, "pds: enqueue task reside on cpu%d to cpu%d\n",
+ task_cpu(p), cpu_of(rq));
+
+ p->sl_node.level = p->sl_level;
+ if (pds_skiplist_insert(&rq->sl_header, &p->sl_node)) {
+ update_sched_rq_queued_masks(rq);
+ update_sched_rq_pending_masks(rq);
+ } else if (is_second_in_rq(p, rq))
+ update_sched_rq_pending_masks(rq);
+ rq->nr_running++;
+
+ sched_update_tick_dependency(rq);
+
+ sched_info_queued(rq, p);
+ psi_enqueue(p, flags);
+
+ /*
+ * If in_iowait is set, the code below may not trigger any cpufreq
+ * utilization updates, so do it here explicitly with the IOWAIT flag
+ * passed.
+ */
+ if (p->in_iowait)
+ cpufreq_update_this_cpu(rq, SCHED_CPUFREQ_IOWAIT);
+}
+
+static inline void requeue_task(struct task_struct *p, struct rq *rq)
+{
+ bool b_first, b_second;
+
+ lockdep_assert_held(&rq->lock);
+
+ WARN_ONCE(task_rq(p) != rq, "pds: cpu[%d] requeue task reside on cpu%d\n",
+ cpu_of(rq), task_cpu(p));
+
+ b_first = skiplist_del_init(&rq->sl_header, &p->sl_node);
+ b_second = is_second_in_rq(p, rq);
+
+ p->sl_node.level = p->sl_level;
+ if (pds_skiplist_insert(&rq->sl_header, &p->sl_node) || b_first) {
+ update_sched_rq_queued_masks(rq);
+ update_sched_rq_pending_masks(rq);
+ } else if (is_second_in_rq(p, rq) || b_second)
+ update_sched_rq_pending_masks(rq);
+}
+
+/*
+ * resched_curr - mark rq's current 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_curr(struct rq *rq)
+{
+ struct task_struct *curr = rq->curr;
+ int cpu;
+
+ lockdep_assert_held(&rq->lock);
+
+ if (test_tsk_need_resched(curr))
+ return;
+
+ cpu = cpu_of(rq);
+ if (cpu == smp_processor_id()) {
+ set_tsk_need_resched(curr);
+ set_preempt_need_resched();
+ return;
+ }
+
+ if (set_nr_and_not_polling(curr))
+ smp_send_reschedule(cpu);
+ else
+ trace_sched_wake_idle_without_ipi(cpu);
+}
+
+static inline void check_preempt_curr(struct rq *rq, struct task_struct *p)
+{
+ struct task_struct *curr = rq->curr;
+
+ if (curr->prio == PRIO_LIMIT)
+ resched_curr(rq);
+
+ if (task_running_idle(p))
+ return;
+
+ if (p->priodl < curr->priodl)
+ resched_curr(rq);
+}
+
+#ifdef CONFIG_SCHED_HRTICK
+/*
+ * Use HR-timers to deliver accurate preemption points.
+ */
+
+static void hrtick_clear(struct rq *rq)
+{
+ if (hrtimer_active(&rq->hrtick_timer))
+ hrtimer_cancel(&rq->hrtick_timer);
+}
+
+/*
+ * High-resolution timer tick.
+ * Runs from hardirq context with interrupts disabled.
+ */
+static enum hrtimer_restart hrtick(struct hrtimer *timer)
+{
+ struct rq *rq = container_of(timer, struct rq, hrtick_timer);
+ struct task_struct *p;
+
+ WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
+
+ raw_spin_lock(&rq->lock);
+ p = rq->curr;
+ p->time_slice = 0;
+ resched_curr(rq);
+ raw_spin_unlock(&rq->lock);
+
+ return HRTIMER_NORESTART;
+}
+
+/*
+ * Use hrtick when:
+ * - enabled by features
+ * - hrtimer is actually high res
+ */
+static inline int hrtick_enabled(struct rq *rq)
+{
+ /**
+ * PDS doesn't support sched_feat yet
+ if (!sched_feat(HRTICK))
+ return 0;
+ */
+ if (!cpu_active(cpu_of(rq)))
+ return 0;
+ return hrtimer_is_hres_active(&rq->hrtick_timer);
+}
+
+#ifdef CONFIG_SMP
+
+static void __hrtick_restart(struct rq *rq)
+{
+ struct hrtimer *timer = &rq->hrtick_timer;
+
+ hrtimer_start_expires(timer, HRTIMER_MODE_ABS_PINNED_HARD);
+}
+
+/*
+ * called from hardirq (IPI) context
+ */
+static void __hrtick_start(void *arg)
+{
+ struct rq *rq = arg;
+
+ raw_spin_lock(&rq->lock);
+ __hrtick_restart(rq);
+ rq->hrtick_csd_pending = 0;
+ raw_spin_unlock(&rq->lock);
+}
+
+/*
+ * Called to set the hrtick timer state.
+ *
+ * called with rq->lock held and irqs disabled
+ */
+void hrtick_start(struct rq *rq, u64 delay)
+{
+ struct hrtimer *timer = &rq->hrtick_timer;
+ ktime_t time;
+ s64 delta;
+
+ /*
+ * Don't schedule slices shorter than 10000ns, that just
+ * doesn't make sense and can cause timer DoS.
+ */
+ delta = max_t(s64, delay, 10000LL);
+ time = ktime_add_ns(timer->base->get_time(), delta);
+
+ hrtimer_set_expires(timer, time);
+
+ if (rq == this_rq()) {
+ __hrtick_restart(rq);
+ } else if (!rq->hrtick_csd_pending) {
+ smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
+ rq->hrtick_csd_pending = 1;
+ }
+}
+
+#else
+/*
+ * Called to set the hrtick timer state.
+ *
+ * called with rq->lock held and irqs disabled
+ */
+void hrtick_start(struct rq *rq, u64 delay)
+{
+ /*
+ * Don't schedule slices shorter than 10000ns, that just
+ * doesn't make sense. Rely on vruntime for fairness.
+ */
+ delay = max_t(u64, delay, 10000LL);
+ hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
+ HRTIMER_MODE_REL_PINNED_HARD);
+}
+#endif /* CONFIG_SMP */
+
+static void hrtick_rq_init(struct rq *rq)
+{
+#ifdef CONFIG_SMP
+ rq->hrtick_csd_pending = 0;
+
+ rq->hrtick_csd.flags = 0;
+ rq->hrtick_csd.func = __hrtick_start;
+ rq->hrtick_csd.info = rq;
+#endif
+
+ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
+ rq->hrtick_timer.function = hrtick;
+}
+
+static inline int rq_dither(struct rq *rq)
+{
+ if ((rq->clock - rq->last_tick > HALF_JIFFY_NS) || hrtick_enabled(rq))
+ return 0;
+
+ return HALF_JIFFY_NS;
+}
+
+#else /* CONFIG_SCHED_HRTICK */
+static inline int hrtick_enabled(struct rq *rq)
+{
+ return 0;
+}
+
+static inline void hrtick_clear(struct rq *rq)
+{
+}
+
+static inline void hrtick_rq_init(struct rq *rq)
+{
+}
+
+static inline int rq_dither(struct rq *rq)
+{
+ return (rq->clock - rq->last_tick > HALF_JIFFY_NS)? 0:HALF_JIFFY_NS;
+}
+#endif /* CONFIG_SCHED_HRTICK */
+
+static inline int normal_prio(struct task_struct *p)
+{
+ static const int policy_to_prio[] = {
+ NORMAL_PRIO, /* SCHED_NORMAL */
+ 0, /* SCHED_FIFO */
+ 0, /* SCHED_RR */
+ IDLE_PRIO, /* SCHED_BATCH */
+ ISO_PRIO, /* SCHED_ISO */
+ IDLE_PRIO /* SCHED_IDLE */
+ };
+
+ if (task_has_rt_policy(p))
+ return MAX_RT_PRIO - 1 - p->rt_priority;
+ return policy_to_prio[p->policy];
+}
+
+/*
+ * 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.
+ *
+ * Context: rq->lock
+ */
+static void activate_task(struct task_struct *p, struct rq *rq)
+{
+ if (task_contributes_to_load(p))
+ rq->nr_uninterruptible--;
+ enqueue_task(p, rq, ENQUEUE_WAKEUP);
+ p->on_rq = 1;
+ cpufreq_update_this_cpu(rq, 0);
+}
+
+/*
+ * deactivate_task - remove a task from the runqueue.
+ *
+ * Context: rq->lock
+ */
+static inline void deactivate_task(struct task_struct *p, struct rq *rq)
+{
+ if (task_contributes_to_load(p))
+ rq->nr_uninterruptible++;
+ dequeue_task(p, rq, DEQUEUE_SLEEP);
+ p->on_rq = 0;
+ cpufreq_update_this_cpu(rq, 0);
+}
+
+static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
+{
+#ifdef CONFIG_SMP
+ /*
+ * After ->cpu is set up to a new value, task_access_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();
+
+#ifdef CONFIG_THREAD_INFO_IN_TASK
+ WRITE_ONCE(p->cpu, cpu);
+#else
+ WRITE_ONCE(task_thread_info(p)->cpu, cpu);
+#endif
+#endif
+}
+
+#ifdef CONFIG_SMP
+void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
+{
+#ifdef CONFIG_SCHED_DEBUG
+ /*
+ * We should never call set_task_cpu() on a blocked task,
+ * ttwu() will sort out the placement.
+ */
+ WARN_ON_ONCE(p->state != TASK_RUNNING && p->state != TASK_WAKING &&
+ !p->on_rq);
+#ifdef CONFIG_LOCKDEP
+ /*
+ * The caller should hold either p->pi_lock or rq->lock, when changing
+ * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
+ *
+ * sched_move_task() holds both and thus holding either pins the cgroup,
+ * see task_group().
+ */
+ WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
+ lockdep_is_held(&task_rq(p)->lock)));
+#endif
+ /*
+ * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
+ */
+ WARN_ON_ONCE(!cpu_online(new_cpu));
+#endif
+ if (task_cpu(p) == new_cpu)
+ return;
+ trace_sched_migrate_task(p, new_cpu);
+ rseq_migrate(p);
+ perf_event_task_migrate(p);
+
+ __set_task_cpu(p, new_cpu);
+}
+
+static inline bool is_per_cpu_kthread(struct task_struct *p)
+{
+ return ((p->flags & PF_KTHREAD) && (1 == p->nr_cpus_allowed));
+}
+
+/*
+ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
+ * __set_cpus_allowed_ptr() and select_fallback_rq().
+ */
+static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
+{
+ if (!cpumask_test_cpu(cpu, &p->cpus_mask))
+ return false;
+
+ if (is_per_cpu_kthread(p))
+ return cpu_online(cpu);
+
+ return cpu_active(cpu);
+}
+
+/*
+ * This is how migration works:
+ *
+ * 1) we invoke migration_cpu_stop() on the target CPU using
+ * stop_one_cpu().
+ * 2) stopper starts to run (implicitly forcing the migrated thread
+ * off the CPU)
+ * 3) it checks whether the migrated task is still in the wrong runqueue.
+ * 4) if it's in the wrong runqueue then the migration thread removes
+ * it and puts it into the right queue.
+ * 5) stopper completes and stop_one_cpu() returns and the migration
+ * is done.
+ */
+
+/*
+ * detach_task() -- detach the task for the migration specified in @target_cpu
+ */
+static void detach_task(struct rq *rq, struct task_struct *p, int target_cpu)
+{
+ lockdep_assert_held(&rq->lock);
+
+ WRITE_ONCE(p->on_rq ,TASK_ON_RQ_MIGRATING);
+ if (task_contributes_to_load(p))
+ rq->nr_uninterruptible++;
+ dequeue_task(p, rq, 0);
+
+ set_task_cpu(p, target_cpu);
+}
+
+/*
+ * attach_task() -- attach the task detached by detach_task() to its new rq.
+ */
+static void attach_task(struct rq *rq, struct task_struct *p)
+{
+ lockdep_assert_held(&rq->lock);
+
+ BUG_ON(task_rq(p) != rq);
+
+ if (task_contributes_to_load(p))
+ rq->nr_uninterruptible--;
+ enqueue_task(p, rq, 0);
+ p->on_rq = TASK_ON_RQ_QUEUED;
+ cpufreq_update_this_cpu(rq, 0);
+}
+
+/*
+ * move_queued_task - move a queued task to new rq.
+ *
+ * Returns (locked) new rq. Old rq's lock is released.
+ */
+static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int
+ new_cpu)
+{
+ detach_task(rq, p, new_cpu);
+ raw_spin_unlock(&rq->lock);
+
+ rq = cpu_rq(new_cpu);
+
+ raw_spin_lock(&rq->lock);
+ update_rq_clock(rq);
+
+ attach_task(rq, p);
+
+ check_preempt_curr(rq, p);
+
+ return rq;
+}
+
+struct migration_arg {
+ struct task_struct *task;
+ int dest_cpu;
+};
+
+/*
+ * Move (not current) task off this CPU, onto the destination CPU. We're doing
+ * this because either it can't run here any more (set_cpus_allowed()
+ * away from this CPU, or CPU going down), or because we're
+ * attempting to rebalance this task on exec (sched_exec).
+ *
+ * So we race with normal scheduler movements, but that's OK, as long
+ * as the task is no longer on this CPU.
+ */
+static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int
+ dest_cpu)
+{
+ /* Affinity changed (again). */
+ if (!is_cpu_allowed(p, dest_cpu))
+ return rq;
+
+ update_rq_clock(rq);
+ return move_queued_task(rq, p, dest_cpu);
+}
+
+/*
+ * migration_cpu_stop - this will be executed by a highprio stopper thread
+ * and performs thread migration by bumping thread off CPU then
+ * 'pushing' onto another runqueue.
+ */
+static int migration_cpu_stop(void *data)
+{
+ struct migration_arg *arg = data;
+ struct task_struct *p = arg->task;
+ struct rq *rq = this_rq();
+
+ /*
+ * The original target CPU might have gone down and we might
+ * be on another CPU but it doesn't matter.
+ */
+ local_irq_disable();
+
+ raw_spin_lock(&p->pi_lock);
+ raw_spin_lock(&rq->lock);
+ /*
+ * If task_rq(p) != rq, it cannot be migrated here, because we're
+ * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
+ * we're holding p->pi_lock.
+ */
+ if (task_rq(p) == rq)
+ if (task_on_rq_queued(p))
+ rq = __migrate_task(rq, p, arg->dest_cpu);
+ raw_spin_unlock(&rq->lock);
+ raw_spin_unlock(&p->pi_lock);
+
+ local_irq_enable();
+ return 0;
+}
+
+static inline void
+set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask)
+{
+ cpumask_copy(&p->cpus_mask, new_mask);
+ p->nr_cpus_allowed = cpumask_weight(new_mask);
+}
+
+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
+{
+ set_cpus_allowed_common(p, new_mask);
+}
+#endif
+
+/* Enter with rq 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();
+}
+
+/**
+ * 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;
+ raw_spinlock_t *lock;
+
+ 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 rq
+ * lock now, to be *sure*. If we're wrong, we'll
+ * just go back and repeat.
+ */
+ task_access_lock_irqsave(p, &lock, &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_access_unlock_irqrestore(p, lock, &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 = 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);
+
+/*
+ * ->cpus_mask is protected by both rq->lock and p->pi_lock
+ *
+ * A few notes on cpu_active vs cpu_online:
+ *
+ * - cpu_active must be a subset of cpu_online
+ *
+ * - on CPU-up we allow per-CPU kthreads on the online && !active CPU,
+ * see __set_cpus_allowed_ptr(). At this point the newly online
+ * CPU isn't yet part of the sched domains, and balancing will not
+ * see it.
+ *
+ * - on cpu-down we clear cpu_active() to mask the sched domains and
+ * avoid the load balancer to place new tasks on the to be removed
+ * CPU. Existing tasks will remain running there and will be taken
+ * off.
+ *
+ * This means that fallback selection must not select !active CPUs.
+ * And can assume that any active CPU must be online. Conversely
+ * select_task_rq() below may allow selection of !active CPUs in order
+ * to satisfy the above rules.
+ */
+static int select_fallback_rq(int cpu, struct task_struct *p)
+{
+ int nid = cpu_to_node(cpu);
+ const struct cpumask *nodemask = NULL;
+ enum { cpuset, possible, fail } state = cpuset;
+ int dest_cpu;
+
+ /*
+ * If the node that the CPU is on has been offlined, cpu_to_node()
+ * will return -1. There is no CPU on the node, and we should
+ * select the CPU on the other node.
+ */
+ if (nid != -1) {
+ nodemask = cpumask_of_node(nid);
+
+ /* Look for allowed, online CPU in same node. */
+ for_each_cpu(dest_cpu, nodemask) {
+ if (!cpu_active(dest_cpu))
+ continue;
+ if (cpumask_test_cpu(dest_cpu, &p->cpus_mask))
+ return dest_cpu;
+ }
+ }
+
+ for (;;) {
+ /* Any allowed, online CPU? */
+ for_each_cpu(dest_cpu, &p->cpus_mask) {
+ if (!is_cpu_allowed(p, dest_cpu))
+ continue;
+ goto out;
+ }
+
+ /* No more Mr. Nice Guy. */
+ switch (state) {
+ case cpuset:
+ if (IS_ENABLED(CONFIG_CPUSETS)) {
+ cpuset_cpus_allowed_fallback(p);
+ state = possible;
+ break;
+ }
+ /* Fall-through */
+ case possible:
+ do_set_cpus_allowed(p, cpu_possible_mask);
+ state = fail;
+ break;
+
+ case fail:
+ BUG();
+ break;
+ }
+ }
+
+out:
+ if (state != cpuset) {
+ /*
+ * Don't tell them about moving exiting tasks or
+ * kernel threads (both mm NULL), since they never
+ * leave kernel.
+ */
+ if (p->mm && printk_ratelimit()) {
+ printk_deferred("process %d (%s) no longer affine to cpu%d\n",
+ task_pid_nr(p), p->comm, cpu);
+ }
+ }
+
+ return dest_cpu;
+}
+
+static inline int best_mask_cpu(int cpu, const cpumask_t *cpumask)
+{
+ cpumask_t *mask;
+
+ if (cpumask_test_cpu(cpu, cpumask))
+ return cpu;
+
+ mask = &(per_cpu(sched_cpu_affinity_chk_masks, cpu)[0]);
+ while ((cpu = cpumask_any_and(cpumask, mask)) >= nr_cpu_ids)
+ mask++;
+
+ return cpu;
+}
+
+/*
+ * task_preemptible_rq - return the rq which the given task can preempt on
+ * @p: task wants to preempt CPU
+ * @only_preempt_low_policy: indicate only preempt rq running low policy than @p
+ */
+static inline int
+task_preemptible_rq_idle(struct task_struct *p, cpumask_t *chk_mask)
+{
+ cpumask_t tmp;
+
+#ifdef CONFIG_SCHED_SMT
+ if (cpumask_and(&tmp, chk_mask, &sched_cpu_sg_idle_mask))
+ return best_mask_cpu(task_cpu(p), &tmp);
+#endif
+
+#ifdef CONFIG_SMT_NICE
+ /* Only ttwu on cpu which is not smt supressed */
+ if (cpumask_andnot(&tmp, chk_mask, &sched_smt_supressed_mask)) {
+ cpumask_t t;
+ if (cpumask_and(&t, &tmp, &sched_rq_queued_masks[SCHED_RQ_EMPTY]))
+ return best_mask_cpu(task_cpu(p), &t);
+ return best_mask_cpu(task_cpu(p), &tmp);
+ }
+#endif
+
+ if (cpumask_and(&tmp, chk_mask, &sched_rq_queued_masks[SCHED_RQ_EMPTY]))
+ return best_mask_cpu(task_cpu(p), &tmp);
+ return best_mask_cpu(task_cpu(p), chk_mask);
+}
+
+static inline int
+task_preemptible_rq(struct task_struct *p, cpumask_t *chk_mask,
+ int preempt_level)
+{
+ cpumask_t tmp;
+ int level;
+
+#ifdef CONFIG_SCHED_SMT
+#ifdef CONFIG_SMT_NICE
+ if (cpumask_and(&tmp, chk_mask, &sched_cpu_psg_mask))
+ return best_mask_cpu(task_cpu(p), &tmp);
+#else
+ if (cpumask_and(&tmp, chk_mask, &sched_cpu_sg_idle_mask))
+ return best_mask_cpu(task_cpu(p), &tmp);
+#endif
+#endif
+
+ level = find_first_bit(sched_rq_queued_masks_bitmap,
+ NR_SCHED_RQ_QUEUED_LEVEL);
+
+ while (level < preempt_level) {
+ if (cpumask_and(&tmp, chk_mask, &sched_rq_queued_masks[level]))
+ return best_mask_cpu(task_cpu(p), &tmp);
+
+ level = find_next_bit(sched_rq_queued_masks_bitmap,
+ NR_SCHED_RQ_QUEUED_LEVEL,
+ level + 1);
+ }
+
+ if (unlikely(SCHED_RQ_RT == level &&
+ level == preempt_level &&
+ cpumask_and(&tmp, chk_mask,
+ &sched_rq_queued_masks[SCHED_RQ_RT]))) {
+ unsigned int cpu;
+
+ for_each_cpu (cpu, &tmp)
+ if (p->prio < sched_rq_prio[cpu])
+ return cpu;
+ }
+
+ return best_mask_cpu(task_cpu(p), chk_mask);
+}
+
+/*
+ * wake flags
+ */
+#define WF_SYNC 0x01 /* waker goes to sleep after wakeup */
+#define WF_FORK 0x02 /* child wakeup after fork */
+#define WF_MIGRATED 0x04 /* internal use, task got migrated */
+
+static inline int select_task_rq(struct task_struct *p)
+{
+ cpumask_t chk_mask;
+
+ if (unlikely(!cpumask_and(&chk_mask, &p->cpus_mask, cpu_online_mask)))
+ return select_fallback_rq(task_cpu(p), p);
+
+ /* Check IDLE tasks suitable to run normal priority */
+ if (idleprio_task(p)) {
+ if (idleprio_suitable(p)) {
+ p->prio = p->normal_prio;
+ update_task_priodl(p);
+ return task_preemptible_rq_idle(p, &chk_mask);
+ }
+ p->prio = NORMAL_PRIO;
+ update_task_priodl(p);
+ }
+
+ return task_preemptible_rq(p, &chk_mask,
+ task_running_policy_level(p, this_rq()));
+}
+#else /* CONFIG_SMP */
+static inline int select_task_rq(struct task_struct *p)
+{
+ return 0;
+}
+#endif /* CONFIG_SMP */
+
+static void
+ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
+{
+ struct rq *rq;
+
+ if (!schedstat_enabled())
+ return;
+
+ rq= this_rq();
+
+#ifdef CONFIG_SMP
+ if (cpu == rq->cpu)
+ __schedstat_inc(rq->ttwu_local);
+ else {
+ /** PDS ToDo:
+ * How to do ttwu_wake_remote
+ */
+ }
+#endif /* CONFIG_SMP */
+
+ __schedstat_inc(rq->ttwu_count);
+}
+
+/*
+ * Mark the task runnable and perform wakeup-preemption.
+ */
+static inline void
+ttwu_do_wakeup(struct rq *rq, struct task_struct *p, int wake_flags)
+{
+ p->state = TASK_RUNNING;
+ trace_sched_wakeup(p);
+}
+
+static inline void
+ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
+{
+#ifdef CONFIG_SMP
+ if (p->sched_contributes_to_load)
+ rq->nr_uninterruptible--;
+#endif
+
+ activate_task(p, rq);
+ ttwu_do_wakeup(rq, p, 0);
+}
+
+static int ttwu_remote(struct task_struct *p, int wake_flags)
+{
+ struct rq *rq;
+ raw_spinlock_t *lock;
+ int ret = 0;
+
+ rq = __task_access_lock(p, &lock);
+ if (task_on_rq_queued(p)) {
+ ttwu_do_wakeup(rq, p, wake_flags);
+ ret = 1;
+ }
+ __task_access_unlock(p, lock);
+
+ return ret;
+}
+
+/*
+ * Notes on Program-Order guarantees on SMP systems.
+ *
+ * MIGRATION
+ *
+ * The basic program-order guarantee on SMP systems is that when a task [t]
+ * migrates, all its activity on its old CPU [c0] happens-before any subsequent
+ * execution on its new CPU [c1].
+ *
+ * For migration (of runnable tasks) this is provided by the following means:
+ *
+ * A) UNLOCK of the rq(c0)->lock scheduling out task t
+ * B) migration for t is required to synchronize *both* rq(c0)->lock and
+ * rq(c1)->lock (if not at the same time, then in that order).
+ * C) LOCK of the rq(c1)->lock scheduling in task
+ *
+ * Transitivity guarantees that B happens after A and C after B.
+ * Note: we only require RCpc transitivity.
+ * Note: the CPU doing B need not be c0 or c1
+ *
+ * Example:
+ *
+ * CPU0 CPU1 CPU2
+ *
+ * LOCK rq(0)->lock
+ * sched-out X
+ * sched-in Y
+ * UNLOCK rq(0)->lock
+ *
+ * LOCK rq(0)->lock // orders against CPU0
+ * dequeue X
+ * UNLOCK rq(0)->lock
+ *
+ * LOCK rq(1)->lock
+ * enqueue X
+ * UNLOCK rq(1)->lock
+ *
+ * LOCK rq(1)->lock // orders against CPU2
+ * sched-out Z
+ * sched-in X
+ * UNLOCK rq(1)->lock
+ *
+ *
+ * BLOCKING -- aka. SLEEP + WAKEUP
+ *
+ * For blocking we (obviously) need to provide the same guarantee as for
+ * migration. However the means are completely different as there is no lock
+ * chain to provide order. Instead we do:
+ *
+ * 1) smp_store_release(X->on_cpu, 0)
+ * 2) smp_cond_load_acquire(!X->on_cpu)
+ *
+ * Example:
+ *
+ * CPU0 (schedule) CPU1 (try_to_wake_up) CPU2 (schedule)
+ *
+ * LOCK rq(0)->lock LOCK X->pi_lock
+ * dequeue X
+ * sched-out X
+ * smp_store_release(X->on_cpu, 0);
+ *
+ * smp_cond_load_acquire(&X->on_cpu, !VAL);
+ * X->state = WAKING
+ * set_task_cpu(X,2)
+ *
+ * LOCK rq(2)->lock
+ * enqueue X
+ * X->state = RUNNING
+ * UNLOCK rq(2)->lock
+ *
+ * LOCK rq(2)->lock // orders against CPU1
+ * sched-out Z
+ * sched-in X
+ * UNLOCK rq(2)->lock
+ *
+ * UNLOCK X->pi_lock
+ * UNLOCK rq(0)->lock
+ *
+ *
+ * However; for wakeups there is a second guarantee we must provide, namely we
+ * must observe the state that lead to our wakeup. That is, not only must our
+ * task observe its own prior state, it must also observe the stores prior to
+ * its wakeup.
+ *
+ * This means that any means of doing remote wakeups must order the CPU doing
+ * the wakeup against the CPU the task is going to end up running on. This,
+ * however, is already required for the regular Program-Order guarantee above,
+ * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
+ *
+ */
+
+/***
+ * 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 int try_to_wake_up(struct task_struct *p, unsigned int state,
+ int wake_flags)
+{
+ unsigned long flags;
+ struct rq *rq;
+ int cpu, success = 0;
+
+ /*
+ * 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.
+ */
+ raw_spin_lock_irqsave(&p->pi_lock, flags);
+ smp_mb__after_spinlock();
+ if (!(p->state & state))
+ goto out;
+
+ trace_sched_waking(p);
+
+ /* We're going to change ->state: */
+ success = 1;
+ cpu = task_cpu(p);
+
+ /*
+ * Ensure we load p->on_rq _after_ p->state, otherwise it would
+ * be possible to, falsely, observe p->on_rq == 0 and get stuck
+ * in smp_cond_load_acquire() below.
+ *
+ * sched_ttwu_pending() try_to_wake_up()
+ * STORE p->on_rq = 1 LOAD p->state
+ * UNLOCK rq->lock
+ *
+ * __schedule() (switch to task 'p')
+ * LOCK rq->lock smp_rmb();
+ * smp_mb__after_spinlock();
+ * UNLOCK rq->lock
+ *
+ * [task p]
+ * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
+ *
+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+ * __schedule(). See the comment for smp_mb__after_spinlock().
+ */
+ smp_rmb();
+ if (p->on_rq && ttwu_remote(p, wake_flags))
+ goto stat;
+
+#ifdef CONFIG_SMP
+ /*
+ * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
+ * possible to, falsely, observe p->on_cpu == 0.
+ *
+ * One must be running (->on_cpu == 1) in order to remove oneself
+ * from the runqueue.
+ *
+ * __schedule() (switch to task 'p') try_to_wake_up()
+ * STORE p->on_cpu = 1 LOAD p->on_rq
+ * UNLOCK rq->lock
+ *
+ * __schedule() (put 'p' to sleep)
+ * LOCK rq->lock smp_rmb();
+ * smp_mb__after_spinlock();
+ * STORE p->on_rq = 0 LOAD p->on_cpu
+ *
+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
+ * __schedule(). See the comment for smp_mb__after_spinlock().
+ */
+ smp_rmb();
+
+ /*
+ * If the owning (remote) CPU is still in the middle of schedule() with
+ * this task as prev, wait until its done referencing the task.
+ *
+ * Pairs with the smp_store_release() in finish_task().
+ *
+ * This ensures that tasks getting woken will be fully ordered against
+ * their previous state and preserve Program Order.
+ */
+ smp_cond_load_acquire(&p->on_cpu, !VAL);
+
+ p->sched_contributes_to_load = !!task_contributes_to_load(p);
+ p->state = TASK_WAKING;
+
+ if (p->in_iowait) {
+ delayacct_blkio_end(p);
+ atomic_dec(&task_rq(p)->nr_iowait);
+ }
+
+ if (SCHED_ISO == p->policy && ISO_PRIO != p->prio) {
+ p->prio = ISO_PRIO;
+ p->deadline = 0UL;
+ update_task_priodl(p);
+ }
+
+ cpu = select_task_rq(p);
+
+ if (cpu != task_cpu(p)) {
+ wake_flags |= WF_MIGRATED;
+ psi_ttwu_dequeue(p);
+ set_task_cpu(p, cpu);
+ }
+#else /* CONFIG_SMP */
+ if (p->in_iowait) {
+ delayacct_blkio_end(p);
+ atomic_dec(&task_rq(p)->nr_iowait);
+ }
+#endif
+
+ rq = cpu_rq(cpu);
+ raw_spin_lock(&rq->lock);
+
+ update_rq_clock(rq);
+ ttwu_do_activate(rq, p, wake_flags);
+ check_preempt_curr(rq, p);
+
+ raw_spin_unlock(&rq->lock);
+
+stat:
+ ttwu_stat(p, cpu, wake_flags);
+out:
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+ return 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.
+ *
+ * This function executes a full memory barrier before accessing the task state.
+ */
+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);
+}
+
+/*
+ * 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)
+{
+ unsigned long flags;
+ int cpu = get_cpu();
+ struct rq *rq = this_rq();
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+ INIT_HLIST_HEAD(&p->preempt_notifiers);
+#endif
+ /* Should be reset in fork.c but done here for ease of PDS patching */
+ p->on_cpu =
+ p->on_rq =
+ p->utime =
+ p->stime =
+ p->sched_time = 0;
+
+ p->sl_level = pds_skiplist_random_level(p);
+ INIT_SKIPLIST_NODE(&p->sl_node);
+
+#ifdef CONFIG_COMPACTION
+ p->capture_control = NULL;
+#endif
+
+ /*
+ * We mark the process as NEW here. This guarantees that
+ * nobody will actually run it, and a signal or other external
+ * event cannot wake it up and insert it on the runqueue either.
+ */
+ p->state = TASK_NEW;
+
+ /*
+ * Make sure we do not leak PI boosting priority to the child.
+ */
+ p->prio = current->normal_prio;
+
+ /*
+ * Revert to default priority/policy on fork if requested.
+ */
+ if (unlikely(p->sched_reset_on_fork)) {
+ if (task_has_rt_policy(p)) {
+ p->policy = SCHED_NORMAL;
+ p->static_prio = NICE_TO_PRIO(0);
+ p->rt_priority = 0;
+ } else if (PRIO_TO_NICE(p->static_prio) < 0)
+ p->static_prio = NICE_TO_PRIO(0);
+
+ p->prio = p->normal_prio = normal_prio(p);
+
+ /*
+ * We don't need the reset flag anymore after the fork. It has
+ * fulfilled its duty:
+ */
+ p->sched_reset_on_fork = 0;
+ }
+
+ /*
+ * 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.
+ */
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ rq->curr->time_slice /= 2;
+ p->time_slice = rq->curr->time_slice;
+#ifdef CONFIG_SCHED_HRTICK
+ hrtick_start(rq, US_TO_NS(rq->curr->time_slice));
+#endif
+
+ if (p->time_slice < RESCHED_US) {
+ update_rq_clock(rq);
+ time_slice_expired(p, rq);
+ resched_curr(rq);
+ } else
+ update_task_priodl(p);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+ /*
+ * The child is not yet in the pid-hash so no cgroup attach races,
+ * and the cgroup is pinned to this child due to cgroup_fork()
+ * is ran before sched_fork().
+ *
+ * Silence PROVE_RCU.
+ */
+ raw_spin_lock_irqsave(&p->pi_lock, flags);
+ /*
+ * We're setting the CPU for the first time, we don't migrate,
+ * so use __set_task_cpu().
+ */
+ __set_task_cpu(p, cpu);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+#ifdef CONFIG_SCHED_INFO
+ if (unlikely(sched_info_on()))
+ memset(&p->sched_info, 0, sizeof(p->sched_info));
+#endif
+ init_task_preempt_count(p);
+
+ put_cpu();
+ 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)
+{
+ unsigned long flags;
+ struct rq *rq;
+
+ raw_spin_lock_irqsave(&p->pi_lock, flags);
+
+ p->state = TASK_RUNNING;
+
+ rq = cpu_rq(select_task_rq(p));
+#ifdef CONFIG_SMP
+ /*
+ * Fork balancing, do it here and not earlier because:
+ * - cpus_mask can change in the fork path
+ * - any previously selected CPU might disappear through hotplug
+ * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
+ * as we're not fully set-up yet.
+ */
+ __set_task_cpu(p, cpu_of(rq));
+#endif
+
+ raw_spin_lock(&rq->lock);
+
+ update_rq_clock(rq);
+ activate_task(p, rq);
+ trace_sched_wakeup_new(p);
+ check_preempt_curr(rq, p);
+
+ raw_spin_unlock(&rq->lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+}
+
+#ifdef CONFIG_PREEMPT_NOTIFIERS
+
+static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key);
+
+void preempt_notifier_inc(void)
+{
+ static_branch_inc(&preempt_notifier_key);
+}
+EXPORT_SYMBOL_GPL(preempt_notifier_inc);
+
+void preempt_notifier_dec(void)
+{
+ static_branch_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_branch_unlikely(&preempt_notifier_key))
+ WARN(1, "registering preempt_notifier while notifiers disabled\n");
+
+ hlist_add_head(&notifier->link, &current->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(&notifier->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_branch_unlikely(&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_branch_unlikely(&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 */
+
+static inline void prepare_task(struct task_struct *next)
+{
+ /*
+ * Claim the task as running, we do this before switching to it
+ * such that any running task will have this set.
+ */
+ next->on_cpu = 1;
+}
+
+static inline void finish_task(struct task_struct *prev)
+{
+#ifdef CONFIG_SMP
+ /*
+ * After ->on_cpu is cleared, the task can be moved to a different CPU.
+ * We must ensure this doesn't happen until the switch is completely
+ * finished.
+ *
+ * In particular, the load of prev->state in finish_task_switch() must
+ * happen before this.
+ *
+ * Pairs with the smp_cond_load_acquire() in try_to_wake_up().
+ */
+ smp_store_release(&prev->on_cpu, 0);
+#else
+ prev->on_cpu = 0;
+#endif
+}
+
+static inline void
+prepare_lock_switch(struct rq *rq, struct task_struct *next)
+{
+ /*
+ * 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(&rq->lock.dep_map, 1, _THIS_IP_);
+#ifdef CONFIG_DEBUG_SPINLOCK
+ /* this is a valid case when another task releases the spinlock */
+ rq->lock.owner = next;
+#endif
+}
+
+static inline void finish_lock_switch(struct rq *rq)
+{
+ /*
+ * If we are tracking spinlock dependencies then we have to
+ * fix up the runqueue lock - which gets 'carried over' from
+ * prev into current:
+ */
+ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
+ raw_spin_unlock_irq(&rq->lock);
+}
+
+/**
+ * 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)
+{
+ kcov_prepare_switch(prev);
+ sched_info_switch(rq, prev, next);
+ perf_event_task_sched_out(prev, next);
+ rseq_preempt(prev);
+ fire_sched_out_preempt_notifiers(prev, next);
+ prepare_task(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(rq->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_task), 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_task(prev);
+ finish_lock_switch(rq);
+ finish_arch_post_lock_switch();
+ kcov_finish_switch(current);
+
+ fire_sched_in_preempt_notifiers(current);
+ /*
+ * When switching through a kernel thread, the loop in
+ * membarrier_{private,global}_expedited() may have observed that
+ * kernel thread and not issued an IPI. It is therefore possible to
+ * schedule between user->kernel->user threads without passing though
+ * switch_mm(). Membarrier requires a barrier after storing to
+ * rq->curr, before returning to userspace, so provide them here:
+ *
+ * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
+ * provided by mmdrop(),
+ * - a sync_core for SYNC_CORE.
+ */
+ if (mm) {
+ membarrier_mm_sync_core_before_usermode(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);
+
+ /* Task is done with its stack. */
+ put_task_stack(prev);
+
+ put_task_struct_rcu_user(prev);
+ }
+
+ tick_nohz_task_switch();
+ 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(rq->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);
+
+ calculate_sigpending();
+}
+
+/*
+ * 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)
+{
+ prepare_task_switch(rq, prev, next);
+
+ /*
+ * 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);
+
+ /*
+ * kernel -> kernel lazy + transfer active
+ * user -> kernel lazy + mmgrab() active
+ *
+ * kernel -> user switch + mmdrop() active
+ * user -> user switch
+ */
+ if (!next->mm) { // to kernel
+ enter_lazy_tlb(prev->active_mm, next);
+
+ next->active_mm = prev->active_mm;
+ if (prev->mm) // from user
+ mmgrab(prev->active_mm);
+ else
+ prev->active_mm = NULL;
+ } else { // to user
+ membarrier_switch_mm(rq, prev->active_mm, next->mm);
+ /*
+ * sys_membarrier() requires an smp_mb() between setting
+ * rq->curr / membarrier_switch_mm() and returning to userspace.
+ *
+ * The below provides this either through switch_mm(), or in
+ * case 'prev->active_mm == next->mm' through
+ * finish_task_switch()'s mmdrop().
+ */
+ switch_mm_irqs_off(prev->active_mm, next->mm, next);
+
+ if (!prev->mm) { // from kernel
+ /* will mmdrop() in finish_task_switch(). */
+ rq->prev_mm = prev->active_mm;
+ prev->active_mm = NULL;
+ }
+ }
+
+ prepare_lock_switch(rq, next);
+
+ /* 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.
+ */
+unsigned long nr_running(void)
+{
+ unsigned long i, sum = 0;
+
+ for_each_online_cpu(i)
+ sum += cpu_rq(i)->nr_running;
+
+ return sum;
+}
+
+/*
+ * 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-preemptible 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)
+{
+ return raw_rq()->nr_running == 1;
+}
+EXPORT_SYMBOL(single_task_running);
+
+unsigned long long nr_context_switches(void)
+{
+ int i;
+ unsigned long long sum = 0;
+
+ for_each_possible_cpu(i)
+ sum += cpu_rq(i)->nr_switches;
+
+ return sum;
+}
+
+/*
+ * Consumers of these two interfaces, like for example the cpuidle menu
+ * governor, are using nonsensical data. Preferring shallow idle state selection
+ * for a CPU that has IO-wait which might not even end up running the task when
+ * it does become runnable.
+ */
+
+unsigned long nr_iowait_cpu(int cpu)
+{
+ return atomic_read(&cpu_rq(cpu)->nr_iowait);
+}
+
+/*
+ * IO-wait accounting, and how its mostly bollocks (on SMP).
+ *
+ * The idea behind IO-wait account is to account the idle time that we could
+ * have spend running if it were not for IO. That is, if we were to improve the
+ * storage performance, we'd have a proportional reduction in IO-wait time.
+ *
+ * This all works nicely on UP, where, when a task blocks on IO, we account
+ * idle time as IO-wait, because if the storage were faster, it could've been
+ * running and we'd not be idle.
+ *
+ * This has been extended to SMP, by doing the same for each CPU. This however
+ * is broken.
+ *
+ * Imagine for instance the case where two tasks block on one CPU, only the one
+ * CPU will have IO-wait accounted, while the other has regular idle. Even
+ * though, if the storage were faster, both could've ran at the same time,
+ * utilising both CPUs.
+ *
+ * This means, that when looking globally, the current IO-wait accounting on
+ * SMP is a lower bound, by reason of under accounting.
+ *
+ * Worse, since the numbers are provided per CPU, they are sometimes
+ * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
+ * associated with any one particular CPU, it can wake to another CPU than it
+ * blocked on. This means the per CPU IO-wait number is meaningless.
+ *
+ * Task CPU affinities can make all that even more 'interesting'.
+ */
+
+unsigned long nr_iowait(void)
+{
+ unsigned long i, sum = 0;
+
+ for_each_possible_cpu(i)
+ sum += nr_iowait_cpu(i);
+
+ return sum;
+}
+
+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);
+
+static inline void pds_update_curr(struct rq *rq, struct task_struct *p)
+{
+ s64 ns = rq->clock_task - p->last_ran;
+
+ p->sched_time += ns;
+ account_group_exec_runtime(p, ns);
+
+ /* time_slice accounting is done in usecs to avoid overflow on 32bit */
+ p->time_slice -= NS_TO_US(ns);
+ p->last_ran = rq->clock_task;
+}
+
+/*
+ * 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;
+ raw_spinlock_t *lock;
+ u64 ns;
+
+#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
+ /*
+ * 64-bit doesn't need locks to atomically read a 64-bit 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 || !task_on_rq_queued(p))
+ return tsk_seruntime(p);
+#endif
+
+ rq = task_access_lock_irqsave(p, &lock, &flags);
+ /*
+ * 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 && task_on_rq_queued(p)) {
+ update_rq_clock(rq);
+ pds_update_curr(rq, p);
+ }
+ ns = tsk_seruntime(p);
+ task_access_unlock_irqrestore(p, lock, &flags);
+
+ return ns;
+}
+
+/* This manages tasks that have run out of timeslice during a scheduler_tick */
+static inline void pds_scheduler_task_tick(struct rq *rq)
+{
+ struct task_struct *p = rq->curr;
+
+ if (is_idle_task(p))
+ return;
+
+ pds_update_curr(rq, p);
+
+ cpufreq_update_util(rq, 0);
+
+ /*
+ * 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 (p->time_slice - rq->dither >= RESCHED_US)
+ return;
+
+ /**
+ * p->time_slice < RESCHED_US. We will modify task_struct under
+ * rq lock as p is rq->curr
+ */
+ __set_tsk_resched(p);
+}
+
+#ifdef CONFIG_SMP
+
+#ifdef CONFIG_SCHED_SMT
+static int active_load_balance_cpu_stop(void *data)
+{
+ struct rq *rq = this_rq();
+ struct task_struct *p = data;
+ int cpu;
+ unsigned long flags;
+
+ local_irq_save(flags);
+
+ raw_spin_lock(&p->pi_lock);
+ raw_spin_lock(&rq->lock);
+
+ rq->active_balance = 0;
+ /*
+ * _something_ may have changed the task, double check again
+ */
+ if (task_on_rq_queued(p) && task_rq(p) == rq &&
+ (cpu = cpumask_any_and(&p->cpus_mask, &sched_cpu_sg_idle_mask)) < nr_cpu_ids)
+ rq = __migrate_task(rq, p, cpu);
+
+ raw_spin_unlock(&rq->lock);
+ raw_spin_unlock(&p->pi_lock);
+
+ local_irq_restore(flags);
+
+ return 0;
+}
+
+/* pds_sg_balance_trigger - trigger slibing group balance for @cpu */
+static void pds_sg_balance_trigger(const int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags;
+ struct task_struct *curr;
+
+ if (!raw_spin_trylock_irqsave(&rq->lock, flags))
+ return;
+ curr = rq->curr;
+ if (!is_idle_task(curr) &&
+ cpumask_intersects(&curr->cpus_mask, &sched_cpu_sg_idle_mask)) {
+ int active_balance = 0;
+
+ if (likely(!rq->active_balance)) {
+ rq->active_balance = 1;
+ active_balance = 1;
+ }
+
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+ if (likely(active_balance))
+ stop_one_cpu_nowait(cpu, active_load_balance_cpu_stop,
+ curr, &rq->active_balance_work);
+ } else
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+/*
+ * pds_sg_balance_check - slibing group balance check for run queue @rq
+ */
+static inline void pds_sg_balance_check(const struct rq *rq)
+{
+ cpumask_t chk;
+ int i;
+
+ /* Only online cpu will do sg balance checking */
+ if (unlikely(!rq->online))
+ return;
+
+ /* Only cpu in slibing idle group will do the checking */
+ if (!cpumask_test_cpu(cpu_of(rq), &sched_cpu_sg_idle_mask))
+ return;
+
+ /* Find potential cpus which can migrate the currently running task */
+ if (!cpumask_andnot(&chk, &sched_rq_pending_masks[SCHED_RQ_EMPTY],
+ &sched_rq_queued_masks[SCHED_RQ_EMPTY]))
+ return;
+
+ for_each_cpu(i, &chk) {
+ /* skip the cpu which has idle slibing cpu */
+ if (cpumask_test_cpu(per_cpu(sched_sibling_cpu, i),
+ &sched_rq_queued_masks[SCHED_RQ_EMPTY]))
+ continue;
+ pds_sg_balance_trigger(i);
+ }
+}
+#endif /* CONFIG_SCHED_SMT */
+#endif /* CONFIG_SMP */
+
+/*
+ * This function gets called by the timer code, with HZ frequency.
+ * We call it with interrupts disabled.
+ */
+void scheduler_tick(void)
+{
+ int cpu __maybe_unused = smp_processor_id();
+ struct rq *rq = cpu_rq(cpu);
+
+ sched_clock_tick();
+
+ raw_spin_lock(&rq->lock);
+ update_rq_clock(rq);
+
+ pds_scheduler_task_tick(rq);
+ update_sched_rq_queued_masks_normal(rq);
+ calc_global_load_tick(rq);
+ psi_task_tick(rq);
+
+ rq->last_tick = rq->clock;
+ raw_spin_unlock(&rq->lock);
+
+ perf_event_task_tick();
+}
+
+#ifdef CONFIG_NO_HZ_FULL
+struct tick_work {
+ int cpu;
+ atomic_t state;
+ struct delayed_work work;
+};
+/* Values for ->state, see diagram below. */
+#define TICK_SCHED_REMOTE_OFFLINE 0
+#define TICK_SCHED_REMOTE_OFFLINING 1
+#define TICK_SCHED_REMOTE_RUNNING 2
+
+/*
+ * State diagram for ->state:
+ *
+ *
+ * TICK_SCHED_REMOTE_OFFLINE
+ * | ^
+ * | |
+ * | | sched_tick_remote()
+ * | |
+ * | |
+ * +--TICK_SCHED_REMOTE_OFFLINING
+ * | ^
+ * | |
+ * sched_tick_start() | | sched_tick_stop()
+ * | |
+ * V |
+ * TICK_SCHED_REMOTE_RUNNING
+ *
+ *
+ * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
+ * and sched_tick_start() are happy to leave the state in RUNNING.
+ */
+
+static struct tick_work __percpu *tick_work_cpu;
+
+static void sched_tick_remote(struct work_struct *work)
+{
+ struct delayed_work *dwork = to_delayed_work(work);
+ struct tick_work *twork = container_of(dwork, struct tick_work, work);
+ int cpu = twork->cpu;
+ struct rq *rq = cpu_rq(cpu);
+ struct task_struct *curr;
+ unsigned long flags;
+ u64 delta;
+ int os;
+
+ /*
+ * Handle the tick only if it appears the remote CPU is running in full
+ * dynticks mode. The check is racy by nature, but missing a tick or
+ * having one too much is no big deal because the scheduler tick updates
+ * statistics and checks timeslices in a time-independent way, regardless
+ * of when exactly it is running.
+ */
+ if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+ goto out_requeue;
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ curr = rq->curr;
+
+ if (is_idle_task(curr) || cpu_is_offline(cpu))
+ goto out_unlock;
+
+ update_rq_clock(rq);
+ delta = rq_clock_task(rq) - curr->last_ran;
+
+ /*
+ * Make sure the next tick runs within a reasonable
+ * amount of time.
+ */
+ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+ pds_scheduler_task_tick(rq);
+ update_sched_rq_queued_masks_normal(rq);
+
+out_unlock:
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+out_requeue:
+ /*
+ * Run the remote tick once per second (1Hz). This arbitrary
+ * frequency is large enough to avoid overload but short enough
+ * to keep scheduler internal stats reasonably up to date. But
+ * first update state to reflect hotplug activity if required.
+ */
+ os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
+ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
+ if (os == TICK_SCHED_REMOTE_RUNNING)
+ queue_delayed_work(system_unbound_wq, dwork, HZ);
+}
+
+static void sched_tick_start(int cpu)
+{
+ int os;
+ struct tick_work *twork;
+
+ if (housekeeping_cpu(cpu, HK_FLAG_TICK))
+ return;
+
+ WARN_ON_ONCE(!tick_work_cpu);
+
+ twork = per_cpu_ptr(tick_work_cpu, cpu);
+ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
+ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
+ if (os == TICK_SCHED_REMOTE_OFFLINE) {
+ twork->cpu = cpu;
+ INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
+ queue_delayed_work(system_unbound_wq, &twork->work, HZ);
+ }
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+static void sched_tick_stop(int cpu)
+{
+ struct tick_work *twork;
+
+ if (housekeeping_cpu(cpu, HK_FLAG_TICK))
+ return;
+
+ WARN_ON_ONCE(!tick_work_cpu);
+
+ twork = per_cpu_ptr(tick_work_cpu, cpu);
+ cancel_delayed_work_sync(&twork->work);
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+int __init sched_tick_offload_init(void)
+{
+ tick_work_cpu = alloc_percpu(struct tick_work);
+ BUG_ON(!tick_work_cpu);
+ return 0;
+}
+
+#else /* !CONFIG_NO_HZ_FULL */
+static inline void sched_tick_start(int cpu) { }
+static inline void sched_tick_stop(int cpu) { }
+#endif
+
+#if defined(CONFIG_PREEMPTION) && (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
+
+/*
+ * 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, struct rq *rq)
+{
+ if (rq->idle == p)
+ return;
+
+ pds_update_curr(rq, p);
+
+ if (p->time_slice < RESCHED_US) {
+ time_slice_expired(p, rq);
+ if (SCHED_ISO == p->policy && ISO_PRIO == p->prio) {
+ p->prio = NORMAL_PRIO;
+ p->deadline = rq->clock + task_deadline_diff(p);
+ update_task_priodl(p);
+ }
+ if (SCHED_FIFO != p->policy && task_on_rq_queued(p))
+ requeue_task(p, rq);
+ }
+}
+
+#ifdef CONFIG_SMP
+
+#define SCHED_RQ_NR_MIGRATION (32UL)
+/*
+ * Migrate pending tasks in @rq to @dest_cpu
+ * Will try to migrate mininal of half of @rq nr_running tasks and
+ * SCHED_RQ_NR_MIGRATION to @dest_cpu
+ */
+static inline int
+migrate_pending_tasks(struct rq *rq, struct rq *dest_rq, int filter_prio)
+{
+ struct task_struct *p;
+ int dest_cpu = cpu_of(dest_rq);
+ int nr_migrated = 0;
+ int nr_tries = min((rq->nr_running + 1) / 2, SCHED_RQ_NR_MIGRATION);
+ struct skiplist_node *node = rq->sl_header.next[0];
+
+ while (nr_tries && node != &rq->sl_header) {
+ p = skiplist_entry(node, struct task_struct, sl_node);
+ node = node->next[0];
+
+ if (task_running(p))
+ continue;
+ if (p->prio >= filter_prio)
+ break;
+ if (cpumask_test_cpu(dest_cpu, &p->cpus_mask)) {
+ detach_task(rq, p, dest_cpu);
+ attach_task(dest_rq, p);
+ nr_migrated++;
+ }
+ nr_tries--;
+ /* make a jump */
+ if (node == &rq->sl_header)
+ break;
+ node = node->next[0];
+ }
+
+ return nr_migrated;
+}
+
+static inline int
+take_queued_task_cpumask(struct rq *rq, cpumask_t *chk_mask, int filter_prio)
+{
+ int src_cpu;
+
+ for_each_cpu(src_cpu, chk_mask) {
+ int nr_migrated;
+ struct rq *src_rq = cpu_rq(src_cpu);
+
+ if (!do_raw_spin_trylock(&src_rq->lock)) {
+ if (PRIO_LIMIT == filter_prio)
+ continue;
+ return 0;
+ }
+ spin_acquire(&src_rq->lock.dep_map, SINGLE_DEPTH_NESTING, 1, _RET_IP_);
+
+ update_rq_clock(src_rq);
+ nr_migrated = migrate_pending_tasks(src_rq, rq, filter_prio);
+
+ spin_release(&src_rq->lock.dep_map, 1, _RET_IP_);
+ do_raw_spin_unlock(&src_rq->lock);
+
+ if (nr_migrated || PRIO_LIMIT != filter_prio)
+ return nr_migrated;
+ }
+ return 0;
+}
+
+static inline int take_other_rq_task(struct rq *rq, int cpu, int filter_prio)
+{
+ struct cpumask *affinity_mask, *end;
+ struct cpumask chk;
+
+ if (PRIO_LIMIT == filter_prio) {
+ cpumask_complement(&chk, &sched_rq_pending_masks[SCHED_RQ_EMPTY]);
+#ifdef CONFIG_SMT_NICE
+ {
+ /* also try to take IDLE priority tasks from smt supressed cpu */
+ struct cpumask t;
+ if (cpumask_and(&t, &sched_smt_supressed_mask,
+ &sched_rq_queued_masks[SCHED_RQ_IDLE]))
+ cpumask_or(&chk, &chk, &t);
+ }
+#endif
+ } else if (NORMAL_PRIO == filter_prio) {
+ cpumask_or(&chk, &sched_rq_pending_masks[SCHED_RQ_RT],
+ &sched_rq_pending_masks[SCHED_RQ_ISO]);
+ } else if (IDLE_PRIO == filter_prio) {
+ cpumask_complement(&chk, &sched_rq_pending_masks[SCHED_RQ_EMPTY]);
+ cpumask_andnot(&chk, &chk, &sched_rq_pending_masks[SCHED_RQ_IDLE]);
+ } else
+ cpumask_copy(&chk, &sched_rq_pending_masks[SCHED_RQ_RT]);
+
+ if (cpumask_empty(&chk))
+ return 0;
+
+ affinity_mask = per_cpu(sched_cpu_llc_start_mask, cpu);
+ end = per_cpu(sched_cpu_affinity_chk_end_masks, cpu);
+ do {
+ struct cpumask tmp;
+
+ if (cpumask_and(&tmp, &chk, affinity_mask) &&
+ take_queued_task_cpumask(rq, &tmp, filter_prio))
+ return 1;
+ } while (++affinity_mask < end);
+
+ return 0;
+}
+#endif
+
+static inline struct task_struct *
+choose_next_task(struct rq *rq, int cpu, struct task_struct *prev)
+{
+ struct task_struct *next = rq_first_queued_task(rq);
+
+#ifdef CONFIG_SMT_NICE
+ if (cpumask_test_cpu(cpu, &sched_smt_supressed_mask)) {
+ if (next->prio >= IDLE_PRIO) {
+ if (rq->online &&
+ take_other_rq_task(rq, cpu, IDLE_PRIO))
+ return rq_first_queued_task(rq);
+ return rq->idle;
+ }
+ }
+#endif
+
+#ifdef CONFIG_SMP
+ if (likely(rq->online))
+ if (take_other_rq_task(rq, cpu, next->prio)) {
+ resched_curr(rq);
+ return rq_first_queued_task(rq);
+ }
+#endif
+ return next;
+}
+
+static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
+{
+#ifdef CONFIG_DEBUG_PREEMPT
+ return p->preempt_disable_ip;
+#else
+ return 0;
+#endif
+}
+
+/*
+ * Print scheduling while atomic bug:
+ */
+static noinline void __schedule_bug(struct task_struct *prev)
+{
+ /* Save this before calling printk(), since that will clobber it */
+ unsigned long preempt_disable_ip = get_preempt_disable_ip(current);
+
+ 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);
+ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)
+ && in_atomic_preempt_off()) {
+ pr_err("Preemption disabled at:");
+ print_ip_sym(preempt_disable_ip);
+ pr_cont("\n");
+ }
+ if (panic_on_warn)
+ panic("scheduling while atomic\n");
+
+ 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, bool preempt)
+{
+#ifdef CONFIG_SCHED_STACK_END_CHECK
+ if (task_stack_end_corrupted(prev))
+ panic("corrupted stack end detected inside scheduler\n");
+#endif
+
+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
+ if (!preempt && prev->state && prev->non_block_count) {
+ printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n",
+ prev->comm, prev->pid, prev->non_block_count);
+ dump_stack();
+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
+ }
+#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);
+}
+
+static inline void set_rq_task(struct rq *rq, struct task_struct *p)
+{
+ p->last_ran = rq->clock_task;
+
+#ifdef CONFIG_HIGH_RES_TIMERS
+ if (p != rq->idle)
+ hrtick_start(rq, US_TO_NS(p->time_slice));
+#endif
+ /* update rq->dither */
+ rq->dither = rq_dither(rq);
+}
+
+/*
+ * 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_PREEMPTION=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;
+ unsigned long *switch_count;
+ struct rq *rq;
+ int cpu;
+
+ cpu = smp_processor_id();
+ rq = cpu_rq(cpu);
+ prev = rq->curr;
+
+ schedule_debug(prev, preempt);
+
+ /* by passing sched_feat(HRTICK) checking which PDS doesn't support */
+ hrtick_clear(rq);
+
+ local_irq_disable();
+ rcu_note_context_switch(preempt);
+
+ /*
+ * 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().
+ *
+ * The membarrier system call requires a full memory barrier
+ * after coming from user-space, before storing to rq->curr.
+ */
+ raw_spin_lock(&rq->lock);
+ smp_mb__after_spinlock();
+
+ update_rq_clock(rq);
+
+ switch_count = &prev->nivcsw;
+ if (!preempt && prev->state) {
+ if (signal_pending_state(prev->state, prev)) {
+ prev->state = TASK_RUNNING;
+ } else {
+ deactivate_task(prev, rq);
+
+ if (prev->in_iowait) {
+ atomic_inc(&rq->nr_iowait);
+ delayacct_blkio_start();
+ }
+ }
+ switch_count = &prev->nvcsw;
+ }
+
+ clear_tsk_need_resched(prev);
+ clear_preempt_need_resched();
+
+ check_deadline(prev, rq);
+
+ next = choose_next_task(rq, cpu, prev);
+
+ set_rq_task(rq, next);
+
+ if (prev != next) {
+ if (next->prio == PRIO_LIMIT)
+ schedstat_inc(rq->sched_goidle);
+
+ /*
+ * RCU users of rcu_dereference(rq->curr) may not see
+ * changes to task_struct made by pick_next_task().
+ */
+ RCU_INIT_POINTER(rq->curr, next);
+ /*
+ * The membarrier system call requires each architecture
+ * to have a full memory barrier after updating
+ * rq->curr, before returning to user-space.
+ *
+ * Here are the schemes providing that barrier on the
+ * various architectures:
+ * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
+ * switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
+ * - finish_lock_switch() for weakly-ordered
+ * architectures where spin_unlock is a full barrier,
+ * - switch_to() for arm64 (weakly-ordered, spin_unlock
+ * is a RELEASE barrier),
+ */
+ ++*switch_count;
+ rq->nr_switches++;
+
+ trace_sched_switch(preempt, prev, next);
+
+ /* Also unlocks the rq: */
+ rq = context_switch(rq, prev, next);
+#ifdef CONFIG_SCHED_SMT
+ pds_sg_balance_check(rq);
+#endif
+ } else
+ raw_spin_unlock_irq(&rq->lock);
+}
+
+void __noreturn do_task_dead(void)
+{
+ /* Causes final put_task_struct in finish_task_switch(): */
+ set_special_state(TASK_DEAD);
+
+ /* Tell freezer to ignore us: */
+ current->flags |= PF_NOFREEZE;
+ __schedule(false);
+
+ BUG();
+
+ /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
+ for (;;)
+ cpu_relax();
+}
+
+static inline void sched_submit_work(struct task_struct *tsk)
+{
+ if (!tsk->state || tsk_is_pi_blocked(tsk) ||
+ signal_pending_state(tsk->state, tsk))
+ return;
+
+ /*
+ * If a worker went to sleep, notify and ask workqueue whether
+ * it wants to wake up a task to maintain concurrency.
+ * As this function is called inside the schedule() context,
+ * we disable preemption to avoid it calling schedule() again
+ * in the possible wakeup of a kworker.
+ */
+ if (tsk->flags & PF_WQ_WORKER) {
+ preempt_disable();
+ wq_worker_sleeping(tsk);
+ preempt_enable_no_resched();
+ }
+
+ /*
+ * 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);
+}
+
+static void sched_update_worker(struct task_struct *tsk)
+{
+ if (tsk->flags & PF_WQ_WORKER)
+ wq_worker_running(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());
+ sched_update_worker(tsk);
+}
+EXPORT_SYMBOL(schedule);
+
+/*
+ * synchronize_rcu_tasks() makes sure that no task is stuck in preempted
+ * state (have scheduled out non-voluntarily) by making sure that all
+ * tasks have either left the run queue or have gone into user space.
+ * As idle tasks do not do either, they must not ever be preempted
+ * (schedule out non-voluntarily).
+ *
+ * schedule_idle() is similar to schedule_preempt_disable() except that it
+ * never enables preemption because it does not call sched_submit_work().
+ */
+void __sched schedule_idle(void)
+{
+ /*
+ * As this skips calling sched_submit_work(), which the idle task does
+ * regardless because that function is a nop when the task is in a
+ * TASK_RUNNING state, make sure this isn't used someplace that the
+ * current task can be in any other state. Note, idle is always in the
+ * TASK_RUNNING state.
+ */
+ WARN_ON_ONCE(current->state);
+ do {
+ __schedule(false);
+ } while (need_resched());
+}
+
+#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 != CONTEXT_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_PREEMPTION
+/*
+ * This is the entry point to schedule() from in-kernel preemption
+ * off of preempt_enable.
+ */
+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_PREEMPTION */
+
+/*
+ * 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_entry_t *curr, unsigned mode, int wake_flags,
+ void *key)
+{
+ return try_to_wake_up(curr->private, mode, wake_flags);
+}
+EXPORT_SYMBOL(default_wake_function);
+
+static inline void
+check_task_changed(struct rq *rq, struct task_struct *p)
+{
+ /*
+ * Trigger changes when task priority/deadline modified.
+ */
+ if (task_on_rq_queued(p)) {
+ struct task_struct *first;
+
+ requeue_task(p, rq);
+
+ /* Resched if first queued task not running and not IDLE */
+ if ((first = rq_first_queued_task(rq)) != rq->curr &&
+ !task_running_idle(first))
+ resched_curr(rq);
+ }
+}
+
+#ifdef CONFIG_RT_MUTEXES
+
+static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
+{
+ if (pi_task)
+ prio = min(prio, pi_task->prio);
+
+ return prio;
+}
+
+static inline int rt_effective_prio(struct task_struct *p, int prio)
+{
+ struct task_struct *pi_task = rt_mutex_get_top_task(p);
+
+ return __rt_effective_prio(pi_task, prio);
+}
+
+/*
+ * rt_mutex_setprio - set the current priority of a task
+ * @p: task to boost
+ * @pi_task: donor task
+ *
+ * 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, struct task_struct *pi_task)
+{
+ int prio;
+ struct rq *rq;
+ raw_spinlock_t *lock;
+
+ /* XXX used to be waiter->prio, not waiter->task->prio */
+ prio = __rt_effective_prio(pi_task, p->normal_prio);
+
+ /*
+ * If nothing changed; bail early.
+ */
+ if (p->pi_top_task == pi_task && prio == p->prio)
+ return;
+
+ rq = __task_access_lock(p, &lock);
+ /*
+ * Set under pi_lock && rq->lock, such that the value can be used under
+ * either lock.
+ *
+ * Note that there is loads of tricky to make this pointer cache work
+ * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
+ * ensure a task is de-boosted (pi_task is set to NULL) before the
+ * task is allowed to run again (and can exit). This ensures the pointer
+ * points to a blocked task -- which guaratees the task is present.
+ */
+ p->pi_top_task = pi_task;
+
+ /*
+ * For FIFO/RR we only need to set prio, if that matches we're done.
+ */
+ if (prio == p->prio)
+ goto out_unlock;
+
+ /*
+ * 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, pi_task);
+ p->prio = prio;
+ update_task_priodl(p);
+
+ check_task_changed(rq, p);
+
+out_unlock:
+ __task_access_unlock(p, lock);
+}
+#else
+static inline int rt_effective_prio(struct task_struct *p, int prio)
+{
+ return prio;
+}
+#endif
+
+void set_user_nice(struct task_struct *p, long nice)
+{
+ int new_static;
+ unsigned long flags;
+ struct rq *rq;
+ raw_spinlock_t *lock;
+
+ 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.
+ */
+ raw_spin_lock_irqsave(&p->pi_lock, flags);
+ rq = __task_access_lock(p, &lock);
+
+ /* rq lock may not held!! */
+ update_rq_clock(rq);
+
+ p->static_prio = new_static;
+ /*
+ * 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 (task_has_rt_policy(p))
+ goto out_unlock;
+
+ p->deadline -= task_deadline_diff(p);
+ p->deadline += static_deadline_diff(new_static);
+ p->prio = effective_prio(p);
+ update_task_priodl(p);
+
+ check_task_changed(rq, p);
+out_unlock:
+ __task_access_unlock(p, lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, 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_IDLE).
+ */
+int task_prio(const struct task_struct *p)
+{
+ int level, prio = p->prio - MAX_RT_PRIO;
+ static const int level_to_nice_prio[] = {39, 33, 26, 20, 14, 7, 0, 0};
+
+ /* rt tasks */
+ if (prio <= 0)
+ goto out;
+
+ preempt_disable();
+ level = task_deadline_level(p, this_rq());
+ preempt_enable();
+ prio += level_to_nice_prio[level];
+ if (idleprio_task(p))
+ prio += NICE_WIDTH;
+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;
+}
+
+#ifdef CONFIG_SMP
+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);
+ }
+}
+
+/*
+ * 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;
+ int dest_cpu;
+ unsigned long flags;
+ struct rq *rq;
+ raw_spinlock_t *lock;
+ int ret = 0;
+
+ raw_spin_lock_irqsave(&p->pi_lock, flags);
+ rq = __task_access_lock(p, &lock);
+
+ 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(&p->cpus_mask, new_mask))
+ goto out;
+
+ dest_cpu = cpumask_any_and(cpu_valid_mask, new_mask);
+ if (dest_cpu >= nr_cpu_ids) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ 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) &&
+ p->nr_cpus_allowed != 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) || p->state == TASK_WAKING) {
+ struct migration_arg arg = { p, dest_cpu };
+
+ /* Need help from migration thread: drop lock and wait. */
+ __task_access_unlock(p, lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
+ return 0;
+ }
+ if (task_on_rq_queued(p)) {
+ /*
+ * OK, since we're going to drop the lock immediately
+ * afterwards anyway.
+ */
+ update_rq_clock(rq);
+ rq = move_queued_task(rq, p, dest_cpu);
+ lock = &rq->lock;
+ }
+
+out:
+ __task_access_unlock(p, lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+ 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);
+
+#else
+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
+
+static u64 task_init_deadline(const struct task_struct *p)
+{
+ return task_rq(p)->clock + task_deadline_diff(p);
+}
+
+u64 (* task_init_deadline_func_tbl[])(const struct task_struct *p) = {
+ task_init_deadline, /* SCHED_NORMAL */
+ NULL, /* SCHED_FIFO */
+ NULL, /* SCHED_RR */
+ task_init_deadline, /* SCHED_BATCH */
+ NULL, /* SCHED_ISO */
+ task_init_deadline /* SCHED_IDLE */
+};
+
+/*
+ * sched_setparam() passes in -1 for its policy, to let the functions
+ * it calls know not to change it.
+ */
+#define SETPARAM_POLICY -1
+
+static void __setscheduler_params(struct task_struct *p,
+ const struct sched_attr *attr)
+{
+ int old_policy = p->policy;
+ int policy = attr->sched_policy;
+
+ if (policy == SETPARAM_POLICY)
+ policy = p->policy;
+
+ p->policy = policy;
+
+ /*
+ * allow normal nice value to be set, but will not have any
+ * effect on scheduling until the task not SCHED_NORMAL/
+ * SCHED_BATCH
+ */
+ p->static_prio = NICE_TO_PRIO(attr->sched_nice);
+
+ /*
+ * __sched_setscheduler() ensures attr->sched_priority == 0 when
+ * !rt_policy. Always setting this ensures that things like
+ * getparam()/getattr() don't report silly values for !rt tasks.
+ */
+ p->rt_priority = attr->sched_priority;
+ p->normal_prio = normal_prio(p);
+
+ if (old_policy != policy)
+ p->deadline = (task_init_deadline_func_tbl[p->policy])?
+ task_init_deadline_func_tbl[p->policy](p):0ULL;
+}
+
+/* Actually do priority change: must hold rq lock. */
+static void __setscheduler(struct rq *rq, struct task_struct *p,
+ const struct sched_attr *attr, bool keep_boost)
+{
+ __setscheduler_params(p, attr);
+
+ /*
+ * Keep a potential priority boosting if called from
+ * sched_setscheduler().
+ */
+ p->prio = normal_prio(p);
+ if (keep_boost)
+ p->prio = rt_effective_prio(p, p->prio);
+ update_task_priodl(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,
+ const struct sched_attr *attr, bool user, bool pi)
+{
+ const struct sched_attr dl_squash_attr = {
+ .size = sizeof(struct sched_attr),
+ .sched_policy = SCHED_FIFO,
+ .sched_nice = 0,
+ .sched_priority = 99,
+ };
+ int newprio = MAX_RT_PRIO - 1 - attr->sched_priority;
+ int retval, oldpolicy = -1;
+ int policy = attr->sched_policy;
+ unsigned long flags;
+ struct rq *rq;
+ int reset_on_fork;
+ raw_spinlock_t *lock;
+
+ /* The pi code expects interrupts enabled */
+ BUG_ON(pi && in_interrupt());
+
+ /*
+ * PDS supports SCHED_DEADLINE by squash it as prio 0 SCHED_FIFO
+ */
+ if (unlikely(SCHED_DEADLINE == policy)) {
+ attr = &dl_squash_attr;
+ policy = attr->sched_policy;
+ newprio = MAX_RT_PRIO - 1 - attr->sched_priority;
+ }
+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 = !!(attr->sched_flags & SCHED_RESET_ON_FORK);
+
+ if (policy > SCHED_IDLE)
+ return -EINVAL;
+ }
+
+ if (attr->sched_flags & ~(SCHED_FLAG_ALL))
+ 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 and SCHED_IDLE is 0.
+ */
+ if (attr->sched_priority < 0 ||
+ (p->mm && attr->sched_priority > MAX_USER_RT_PRIO - 1) ||
+ (!p->mm && attr->sched_priority > MAX_RT_PRIO - 1))
+ return -EINVAL;
+ if ((SCHED_RR == policy || SCHED_FIFO == policy) !=
+ (attr->sched_priority != 0))
+ return -EINVAL;
+
+ /*
+ * Allow unprivileged RT tasks to decrease priority:
+ */
+ if (user && !capable(CAP_SYS_NICE)) {
+ if (SCHED_FIFO == policy || SCHED_RR == 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 (attr->sched_priority > p->rt_priority &&
+ attr->sched_priority > rlim_rtprio)
+ return -EPERM;
+ }
+
+ /* 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;
+ }
+
+ if (pi)
+ cpuset_read_lock();
+
+ /*
+ * 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, task_access_lock()
+ * must be called.
+ * IF use task_access_lock() here:
+ * For the task p which is not running, reading rq->stop is
+ * racy but acceptable as ->stop doesn't change much.
+ * An enhancemnet can be made to read rq->stop saftly.
+ */
+ rq = __task_access_lock(p, &lock);
+
+ /*
+ * Changing the policy of the stop threads its a very bad idea
+ */
+ if (p == rq->stop) {
+ retval = -EINVAL;
+ goto unlock;
+ }
+
+ /*
+ * If not changing anything there's no need to proceed further:
+ */
+ if (unlikely(policy == p->policy)) {
+ if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
+ goto change;
+ if (!rt_policy(policy) &&
+ NICE_TO_PRIO(attr->sched_nice) != p->static_prio)
+ goto change;
+
+ p->sched_reset_on_fork = reset_on_fork;
+ retval = 0;
+ goto unlock;
+ }
+change:
+
+ /* Re-check policy now with rq lock held */
+ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
+ policy = oldpolicy = -1;
+ __task_access_unlock(p, lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ if (pi)
+ cpuset_read_unlock();
+ goto recheck;
+ }
+
+ p->sched_reset_on_fork = reset_on_fork;
+
+ if (pi) {
+ /*
+ * 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.
+ */
+ if (rt_effective_prio(p, newprio) == p->prio) {
+ __setscheduler_params(p, attr);
+ retval = 0;
+ goto unlock;
+ }
+ }
+
+ __setscheduler(rq, p, attr, pi);
+
+ check_task_changed(rq, p);
+
+ /* Avoid rq from going away on us: */
+ preempt_disable();
+ __task_access_unlock(p, lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+
+ if (pi) {
+ cpuset_read_unlock();
+ rt_mutex_adjust_pi(p);
+ }
+
+ preempt_enable();
+
+ return 0;
+
+unlock:
+ __task_access_unlock(p, lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
+ if (pi)
+ cpuset_read_unlock();
+ return retval;
+}
+
+static int _sched_setscheduler(struct task_struct *p, int policy,
+ const struct sched_param *param, bool check)
+{
+ struct sched_attr attr = {
+ .sched_policy = policy,
+ .sched_priority = param->sched_priority,
+ .sched_nice = PRIO_TO_NICE(p->static_prio),
+ };
+
+ /* Fixup the legacy SCHED_RESET_ON_FORK hack. */
+ if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
+ attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
+ policy &= ~SCHED_RESET_ON_FORK;
+ attr.sched_policy = policy;
+ }
+
+ return __sched_setscheduler(p, &attr, check, true);
+}
+
+/**
+ * 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);
+}
+
+EXPORT_SYMBOL_GPL(sched_setscheduler);
+
+int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
+{
+ return __sched_setscheduler(p, attr, true, true);
+}
+EXPORT_SYMBOL_GPL(sched_setattr);
+
+int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
+{
+ return __sched_setscheduler(p, attr, false, true);
+}
+
+/**
+ * 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);
+}
+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 (likely(p))
+ get_task_struct(p);
+ rcu_read_unlock();
+
+ if (likely(p)) {
+ retval = sched_setscheduler(p, policy, &lparam);
+ put_task_struct(p);
+ }
+
+ 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;
+
+ /* 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;
+
+ /* ABI compatibility quirk: */
+ if (!size)
+ size = SCHED_ATTR_SIZE_VER0;
+
+ if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE)
+ goto err_size;
+
+ ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
+ if (ret) {
+ if (ret == -E2BIG)
+ goto err_size;
+ return ret;
+ }
+
+ /*
+ * 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.
+ */
+SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param)
+{
+ if (policy < 0)
+ return -EINVAL;
+
+ return do_sched_setscheduler(pid, policy, param);
+}
+
+/**
+ * sys_sched_setparam - set/change the RT priority of a thread
+ * @pid: the pid in question.
+ * @param: structure containing the new RT priority.
+ *
+ * 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 (task_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;
+}
+
+/*
+ * Copy the kernel size attribute structure (which might be larger
+ * than what user-space knows about) to user-space.
+ *
+ * Note that all cases are valid: user-space buffer can be larger or
+ * smaller than the kernel-space buffer. The usual case is that both
+ * have the same size.
+ */
+static int
+sched_attr_copy_to_user(struct sched_attr __user *uattr,
+ struct sched_attr *kattr,
+ unsigned int usize)
+{
+ unsigned int ksize = sizeof(*kattr);
+
+ if (!access_ok(uattr, usize))
+ return -EFAULT;
+
+ /*
+ * sched_getattr() ABI forwards and backwards compatibility:
+ *
+ * If usize == ksize then we just copy everything to user-space and all is good.
+ *
+ * If usize < ksize then we only copy as much as user-space has space for,
+ * this keeps ABI compatibility as well. We skip the rest.
+ *
+ * If usize > ksize then user-space is using a newer version of the ABI,
+ * which part the kernel doesn't know about. Just ignore it - tooling can
+ * detect the kernel's knowledge of attributes from the attr->size value
+ * which is set to ksize in this case.
+ */
+ kattr->size = min(usize, ksize);
+
+ if (copy_to_user(uattr, kattr, kattr->size))
+ return -EFAULT;
+
+ return 0;
+}
+
+/**
+ * sys_sched_getattr - similar to sched_getparam, but with sched_attr
+ * @pid: the pid in question.
+ * @uattr: structure containing the extended parameters.
+ * @usize: sizeof(attr) for fwd/bwd comp.
+ * @flags: for future extension.
+ */
+SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
+ unsigned int, usize, unsigned int, flags)
+{
+ struct sched_attr kattr = { };
+ struct task_struct *p;
+ int retval;
+
+ if (!uattr || pid < 0 || usize > PAGE_SIZE ||
+ usize < 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;
+
+ kattr.sched_policy = p->policy;
+ if (rt_task(p))
+ kattr.sched_priority = p->rt_priority;
+ else
+ kattr.sched_nice = task_nice(p);
+
+#ifdef CONFIG_UCLAMP_TASK
+ kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
+ kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
+#endif
+
+ rcu_read_unlock();
+
+ return sched_attr_copy_to_user(uattr, &kattr, usize);
+
+out_unlock:
+ rcu_read_unlock();
+ return retval;
+}
+
+long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
+{
+ cpumask_var_t cpus_mask, 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_mask, 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_mask);
+ cpumask_and(new_mask, in_mask, cpus_mask);
+again:
+ retval = __set_cpus_allowed_ptr(p, new_mask, true);
+
+ if (!retval) {
+ cpuset_cpus_allowed(p, cpus_mask);
+ if (!cpumask_subset(new_mask, cpus_mask)) {
+ /*
+ * We must have raced with a concurrent cpuset
+ * update. Just reset the cpus_mask to the
+ * cpuset's cpus_mask
+ */
+ cpumask_copy(new_mask, cpus_mask);
+ goto again;
+ }
+ }
+out_unlock:
+ free_cpumask_var(new_mask);
+out_free_cpus_allowed:
+ free_cpumask_var(cpus_mask);
+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,
+ struct cpumask *new_mask)
+{
+ if (len < cpumask_size())
+ cpumask_clear(new_mask);
+ else if (len > cpumask_size())
+ len = cpumask_size();
+
+ 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;
+ raw_spinlock_t *lock;
+ unsigned long flags;
+ int retval;
+
+ 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;
+
+ task_access_lock_irqsave(p, &lock, &flags);
+ cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
+ task_access_unlock_irqrestore(p, lock, &flags);
+
+out_unlock:
+ rcu_read_unlock();
+
+ 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: size of CPU mask copied to user_mask_ptr 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) {
+ unsigned int 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.
+ */
+static void do_sched_yield(void)
+{
+ struct rq *rq;
+ struct rq_flags rf;
+
+ if (!sched_yield_type)
+ return;
+
+ rq = this_rq_lock_irq(&rf);
+
+ if (sched_yield_type > 1) {
+ time_slice_expired(current, rq);
+ requeue_task(current, rq);
+ }
+ schedstat_inc(rq->yld_count);
+
+ /*
+ * Since we are going to call schedule() anyway, there's
+ * no need to preempt or enable interrupts:
+ */
+ preempt_disable();
+ raw_spin_unlock(&rq->lock);
+ sched_preempt_enable_no_resched();
+
+ schedule();
+}
+
+SYSCALL_DEFINE0(sched_yield)
+{
+ do_sched_yield();
+ return 0;
+}
+
+#ifndef CONFIG_PREEMPTION
+int __sched _cond_resched(void)
+{
+ if (should_resched(0)) {
+ preempt_schedule_common();
+ return 1;
+ }
+ rcu_all_qs();
+ return 0;
+}
+EXPORT_SYMBOL(_cond_resched);
+#endif
+
+/*
+ * __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_PREEMPTION. 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);
+
+/**
+ * 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);
+ do_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.
+ *
+ * In PDS, yield_to is not supported.
+ *
+ * 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)
+{
+ return 0;
+}
+EXPORT_SYMBOL_GPL(yield_to);
+
+int io_schedule_prepare(void)
+{
+ int old_iowait = current->in_iowait;
+
+ current->in_iowait = 1;
+ blk_schedule_flush_plug(current);
+
+ return old_iowait;
+}
+
+void io_schedule_finish(int token)
+{
+ current->in_iowait = token;
+}
+
+/*
+ * 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 token;
+ long ret;
+
+ token = io_schedule_prepare();
+ ret = schedule_timeout(timeout);
+ io_schedule_finish(token);
+
+ return ret;
+}
+EXPORT_SYMBOL(io_schedule_timeout);
+
+void io_schedule(void)
+{
+ int token;
+
+ token = io_schedule_prepare();
+ schedule();
+ io_schedule_finish(token);
+}
+EXPORT_SYMBOL(io_schedule);
+
+/**
+ * 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_IDLE:
+ 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_IDLE:
+ ret = 0;
+ break;
+ }
+ return ret;
+}
+
+static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
+{
+ struct task_struct *p;
+ int retval;
+
+ 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;
+ rcu_read_unlock();
+
+ *t = ns_to_timespec64(MS_TO_NS(rr_interval));
+ return 0;
+
+out_unlock:
+ rcu_read_unlock();
+ return retval;
+}
+
+/**
+ * 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 __kernel_timespec __user *, interval)
+{
+ struct timespec64 t;
+ int retval = sched_rr_get_interval(pid, &t);
+
+ if (retval == 0)
+ retval = put_timespec64(&t, interval);
+
+ return retval;
+}
+
+#ifdef CONFIG_COMPAT_32BIT_TIME
+SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid,
+ struct old_timespec32 __user *, interval)
+{
+ struct timespec64 t;
+ int retval = sched_rr_get_interval(pid, &t);
+
+ if (retval == 0)
+ retval = put_old_timespec32(&t, interval);
+ return retval;
+}
+#endif
+
+void sched_show_task(struct task_struct *p)
+{
+ unsigned long free = 0;
+ int ppid;
+
+ if (!try_get_task_stack(p))
+ return;
+
+ printk(KERN_INFO "%-15.15s %c", p->comm, task_state_to_char(p));
+
+ if (p->state == TASK_RUNNING)
+ printk(KERN_CONT " running task ");
+#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);
+ put_task_stack(p);
+}
+EXPORT_SYMBOL_GPL(sched_show_task);
+
+static inline bool
+state_filter_match(unsigned long state_filter, struct task_struct *p)
+{
+ /* no filter, everything matches */
+ if (!state_filter)
+ return true;
+
+ /* filter, but doesn't match */
+ if (!(p->state & state_filter))
+ return false;
+
+ /*
+ * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
+ * TASK_KILLABLE).
+ */
+ if (state_filter == TASK_UNINTERRUPTIBLE && p->state == TASK_IDLE)
+ return false;
+
+ return true;
+}
+
+
+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_match(state_filter, p))
+ sched_show_task(p);
+ }
+
+#ifdef CONFIG_SCHED_DEBUG
+ /* PDS TODO: should support this
+ if (!state_filter)
+ sysrq_sched_debug_show();
+ */
+#endif
+ 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));
+}
+
+/**
+ * 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);
+ raw_spin_lock(&rq->lock);
+ update_rq_clock(rq);
+
+ idle->last_ran = rq->clock_task;
+ idle->state = TASK_RUNNING;
+ idle->flags |= PF_IDLE;
+ /* Setting prio to illegal value shouldn't matter when never queued */
+ idle->prio = PRIO_LIMIT;
+ idle->deadline = rq_clock(rq) + task_deadline_diff(idle);
+ update_task_priodl(idle);
+
+ 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));
+#endif
+
+ /* Silence PROVE_RCU */
+ rcu_read_lock();
+ __set_task_cpu(idle, cpu);
+ rcu_read_unlock();
+
+ rq->idle = idle;
+ rcu_assign_pointer(rq->curr, idle);
+ idle->on_cpu = 1;
+
+ raw_spin_unlock(&rq->lock);
+ 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);
+ vtime_init_idle(idle, cpu);
+#ifdef CONFIG_SMP
+ sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
+#endif
+}
+
+void resched_cpu(int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ if (cpu_online(cpu) || cpu == smp_processor_id())
+ resched_curr(cpu_rq(cpu));
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+}
+
+static bool __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.
+ *
+ * In order to ensure that a pending wakeup will observe our pending
+ * state, even in the failed case, an explicit smp_mb() must be used.
+ */
+ smp_mb__before_atomic();
+ if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
+ return false;
+
+ /*
+ * The head is context local, there can be no concurrency.
+ */
+ *head->lastp = node;
+ head->lastp = &node->next;
+ return true;
+}
+
+/**
+ * wake_q_add() - queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ */
+void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+{
+ if (__wake_q_add(head, task))
+ get_task_struct(task);
+}
+
+/**
+ * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ *
+ * This function is essentially a task-safe equivalent to wake_q_add(). Callers
+ * that already hold reference to @task can call the 'safe' version and trust
+ * wake_q to do the right thing depending whether or not the @task is already
+ * queued for wakeup.
+ */
+void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
+{
+ if (!__wake_q_add(head, task))
+ put_task_struct(task);
+}
+
+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() executes a full barrier, which pairs with
+ * the queueing in wake_q_add() so as not to miss wakeups.
+ */
+ wake_up_process(task);
+ put_task_struct(task);
+ }
+}
+
+#ifdef CONFIG_SMP
+
+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_mask may be changed.
+ */
+ if (p->flags & PF_NO_SETAFFINITY)
+ ret = -EINVAL;
+
+ return ret;
+}
+
+static bool sched_smp_initialized __read_mostly;
+
+#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) {}
+
+/*
+ * 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 cpumask *mask;
+
+ if (!idle_cpu(cpu) && housekeeping_cpu(cpu, HK_FLAG_TIMER))
+ return cpu;
+
+ for (mask = &(per_cpu(sched_cpu_affinity_chk_masks, cpu)[0]);
+ mask < per_cpu(sched_cpu_affinity_chk_end_masks, cpu); mask++)
+ for_each_cpu(i, mask)
+ if (!idle_cpu(i) && housekeeping_cpu(i, HK_FLAG_TIMER))
+ return i;
+
+ if (!housekeeping_cpu(cpu, HK_FLAG_TIMER))
+ cpu = housekeeping_any_cpu(HK_FLAG_TIMER);
+
+ 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 */
+
+#ifdef CONFIG_HOTPLUG_CPU
+/*
+ * Ensures that the idle task is using init_mm right before its CPU goes
+ * offline.
+ */
+void idle_task_exit(void)
+{
+ struct mm_struct *mm = current->active_mm;
+
+ BUG_ON(cpu_online(smp_processor_id()));
+
+ if (mm != &init_mm) {
+ switch_mm(mm, &init_mm, current);
+ current->active_mm = &init_mm;
+ finish_arch_post_lock_switch();
+ }
+ mmdrop(mm);
+}
+
+/*
+ * Migrate all tasks from the rq, sleeping tasks will be migrated by
+ * try_to_wake_up()->select_task_rq().
+ *
+ * Called with rq->lock held even though we'er in stop_machine() and
+ * there's no concurrency possible, we hold the required locks anyway
+ * because of lock validation efforts.
+ */
+static void migrate_tasks(struct rq *dead_rq)
+{
+ struct rq *rq = dead_rq;
+ struct task_struct *p, *stop = rq->stop;
+ struct skiplist_node *node;
+ int count = 0;
+
+ /*
+ * Fudge the rq selection such that the below task selection loop
+ * doesn't get stuck on the currently eligible stop task.
+ *
+ * We're currently inside stop_machine() and the rq is either stuck
+ * in the stop_machine_cpu_stop() loop, or we're executing this code,
+ * either way we should never end up calling schedule() until we're
+ * done here.
+ */
+ rq->stop = NULL;
+
+ node = &rq->sl_header;
+ while ((node = node->next[0]) != &rq->sl_header) {
+ int dest_cpu;
+
+ p = skiplist_entry(node, struct task_struct, sl_node);
+
+ /* skip the running task */
+ if (task_running(p))
+ continue;
+
+ /*
+ * Rules for changing task_struct::cpus_mask are holding
+ * both pi_lock and rq->lock, such that holding either
+ * stabilizes the mask.
+ *
+ * Drop rq->lock is not quite as disastrous as it usually is
+ * because !cpu_active at this point, which means load-balance
+ * will not interfere. Also, stop-machine.
+ */
+ raw_spin_unlock(&rq->lock);
+ raw_spin_lock(&p->pi_lock);
+ raw_spin_lock(&rq->lock);
+
+ /*
+ * Since we're inside stop-machine, _nothing_ should have
+ * changed the task, WARN if weird stuff happened, because in
+ * that case the above rq->lock drop is a fail too.
+ */
+ if (WARN_ON(task_rq(p) != rq || !task_on_rq_queued(p))) {
+ raw_spin_unlock(&p->pi_lock);
+ continue;
+ }
+
+ count++;
+ /* Find suitable destination for @next, with force if needed. */
+ dest_cpu = select_fallback_rq(dead_rq->cpu, p);
+
+ rq = __migrate_task(rq, p, dest_cpu);
+ raw_spin_unlock(&rq->lock);
+ raw_spin_unlock(&p->pi_lock);
+
+ rq = dead_rq;
+ raw_spin_lock(&rq->lock);
+ /* Check queued task all over from the header again */
+ node = &rq->sl_header;
+ }
+
+ rq->stop = stop;
+}
+
+static void set_rq_offline(struct rq *rq)
+{
+ if (rq->online)
+ rq->online = false;
+}
+#endif /* CONFIG_HOTPLUG_CPU */
+
+static void set_rq_online(struct rq *rq)
+{
+ if (!rq->online)
+ rq->online = true;
+}
+
+#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;
+}
+#else /* !CONFIG_SCHED_DEBUG */
+static inline bool sched_debug(void)
+{
+ return false;
+}
+#endif /* CONFIG_SCHED_DEBUG */
+
+#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();
+
+ if (!idle_cpu(smp_processor_id()) || need_resched())
+ return;
+
+ irq_enter();
+ irq_exit();
+}
+
+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;
+
+ if (set_nr_if_polling(rq->idle)) {
+ trace_sched_wake_idle_without_ipi(cpu);
+ } else {
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ if (is_idle_task(rq->curr))
+ smp_send_reschedule(cpu);
+ /* Else CPU is not idle, do nothing here */
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+ }
+
+out:
+ rcu_read_unlock();
+}
+
+bool cpus_share_cache(int this_cpu, int that_cpu)
+{
+ return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
+}
+#endif /* CONFIG_SMP */
+
+/*
+ * 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)
+{
+ if (WARN_ON_ONCE(sched_smp_initialized))
+ return;
+
+ sched_domain_topology = tl;
+}
+
+/*
+ * Initializers for schedule domains
+ * Non-inlined to reduce accumulated stack pressure in build_sched_domains()
+ */
+
+int sched_domain_level_max;
+
+/*
+ * 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)
+{
+ /**
+ * PDS doesn't depend on sched domains, but just keep this api
+ */
+}
+
+/*
+ * used to mark begin/end of suspend/resume:
+ */
+static int num_cpus_frozen;
+
+#ifdef CONFIG_NUMA
+int __read_mostly node_reclaim_distance = RECLAIM_DISTANCE;
+
+/*
+ * sched_numa_find_closest() - given the NUMA topology, find the cpu
+ * closest to @cpu from @cpumask.
+ * cpumask: cpumask to find a cpu from
+ * cpu: cpu to be close to
+ *
+ * returns: cpu, or nr_cpu_ids when nothing found.
+ */
+int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
+{
+ return best_mask_cpu(cpu, cpus);
+}
+#endif /* CONFIG_NUMA */
+
+/*
+ * 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.
+ */
+ partition_sched_domains(1, NULL, NULL);
+ if (--num_cpus_frozen)
+ return;
+ /*
+ * This is the last CPU online operation. So fall through and
+ * restore the original sched domains by considering the
+ * cpuset configurations.
+ */
+ cpuset_force_rebuild();
+ }
+
+ cpuset_update_active_cpus();
+}
+
+static int cpuset_cpu_inactive(unsigned int cpu)
+{
+ if (!cpuhp_tasks_frozen) {
+ cpuset_update_active_cpus();
+ } 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;
+
+#ifdef CONFIG_SCHED_SMT
+ /*
+ * When going up, increment the number of cores with SMT present.
+ */
+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ static_branch_inc_cpuslocked(&sched_smt_present);
+#endif
+ set_cpu_active(cpu, true);
+
+ if (sched_smp_initialized)
+ 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.
+ */
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ set_rq_online(rq);
+ raw_spin_unlock_irqrestore(&rq->lock, 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.
+ *
+ * Do sync before park smpboot threads to take care the rcu boost case.
+ */
+ synchronize_rcu();
+
+#ifdef CONFIG_SCHED_SMT
+ /*
+ * When going down, decrement the number of cores with SMT present.
+ */
+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+ static_branch_dec_cpuslocked(&sched_smt_present);
+#endif
+
+ if (!sched_smp_initialized)
+ return 0;
+
+ ret = cpuset_cpu_inactive(cpu);
+ if (ret) {
+ set_cpu_active(cpu, true);
+ return ret;
+ }
+ return 0;
+}
+
+static void sched_rq_cpu_starting(unsigned int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+
+ rq->calc_load_update = calc_load_update;
+}
+
+int sched_cpu_starting(unsigned int cpu)
+{
+ sched_rq_cpu_starting(cpu);
+ sched_tick_start(cpu);
+ return 0;
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+int sched_cpu_dying(unsigned int cpu)
+{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long flags;
+
+ sched_tick_stop(cpu);
+ raw_spin_lock_irqsave(&rq->lock, flags);
+ set_rq_offline(rq);
+ migrate_tasks(rq);
+ raw_spin_unlock_irqrestore(&rq->lock, flags);
+
+ hrtick_clear(rq);
+ return 0;
+}
+#endif
+
+#ifdef CONFIG_SMP
+static void sched_init_topology_cpumask_early(void)
+{
+ int cpu, level;
+ cpumask_t *tmp;
+
+ for_each_possible_cpu(cpu) {
+ for (level = 0; level < NR_CPU_AFFINITY_CHK_LEVEL; level++) {
+ tmp = &(per_cpu(sched_cpu_affinity_chk_masks, cpu)[level]);
+ cpumask_copy(tmp, cpu_possible_mask);
+ cpumask_clear_cpu(cpu, tmp);
+ }
+ per_cpu(sched_cpu_llc_start_mask, cpu) =
+ &(per_cpu(sched_cpu_affinity_chk_masks, cpu)[0]);
+ per_cpu(sched_cpu_affinity_chk_end_masks, cpu) =
+ &(per_cpu(sched_cpu_affinity_chk_masks, cpu)[1]);
+ }
+}
+
+static void sched_init_topology_cpumask(void)
+{
+ int cpu;
+ cpumask_t *chk;
+
+ for_each_online_cpu(cpu) {
+ chk = &(per_cpu(sched_cpu_affinity_chk_masks, cpu)[0]);
+
+#ifdef CONFIG_SCHED_SMT
+ cpumask_setall(chk);
+ cpumask_clear_cpu(cpu, chk);
+ if (cpumask_and(chk, chk, topology_sibling_cpumask(cpu))) {
+ per_cpu(sched_sibling_cpu, cpu) = cpumask_first(chk);
+ printk(KERN_INFO "pds: cpu #%d affinity check mask - smt 0x%08lx",
+ cpu, (chk++)->bits[0]);
+ }
+#endif
+#ifdef CONFIG_SCHED_MC
+ cpumask_setall(chk);
+ cpumask_clear_cpu(cpu, chk);
+ if (cpumask_and(chk, chk, cpu_coregroup_mask(cpu))) {
+ per_cpu(sched_cpu_llc_start_mask, cpu) = chk;
+ printk(KERN_INFO "pds: cpu #%d affinity check mask - coregroup 0x%08lx",
+ cpu, (chk++)->bits[0]);
+ }
+ cpumask_complement(chk, cpu_coregroup_mask(cpu));
+
+ /**
+ * Set up sd_llc_id per CPU
+ */
+ per_cpu(sd_llc_id, cpu) =
+ cpumask_first(cpu_coregroup_mask(cpu));
+#else
+ per_cpu(sd_llc_id, cpu) =
+ cpumask_first(topology_core_cpumask(cpu));
+
+ per_cpu(sched_cpu_llc_start_mask, cpu) = chk;
+
+ cpumask_setall(chk);
+ cpumask_clear_cpu(cpu, chk);
+#endif /* NOT CONFIG_SCHED_MC */
+ if (cpumask_and(chk, chk, topology_core_cpumask(cpu)))
+ printk(KERN_INFO "pds: cpu #%d affinity check mask - core 0x%08lx",
+ cpu, (chk++)->bits[0]);
+ cpumask_complement(chk, topology_core_cpumask(cpu));
+
+ if (cpumask_and(chk, chk, cpu_online_mask))
+ printk(KERN_INFO "pds: cpu #%d affinity check mask - others 0x%08lx",
+ cpu, (chk++)->bits[0]);
+
+ per_cpu(sched_cpu_affinity_chk_end_masks, cpu) = chk;
+ }
+}
+#endif
+
+void __init sched_init_smp(void)
+{
+ /* Move init over to a non-isolated CPU */
+ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_FLAG_DOMAIN)) < 0)
+ BUG();
+
+ cpumask_copy(&sched_rq_queued_masks[SCHED_RQ_EMPTY], cpu_online_mask);
+
+ sched_init_topology_cpumask();
+
+ 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);
+}
+
+#ifdef CONFIG_CGROUP_SCHED
+/* task group related information */
+struct task_group {
+ struct cgroup_subsys_state css;
+
+ struct rcu_head rcu;
+ struct list_head list;
+
+ struct task_group *parent;
+ struct list_head siblings;
+ struct list_head children;
+};
+
+/*
+ * Default task group.
+ * Every task in system belongs to this group at bootup.
+ */
+struct task_group root_task_group;
+LIST_HEAD(task_groups);
+
+/* Cacheline aligned slab cache for task_group */
+static struct kmem_cache *task_group_cache __read_mostly;
+#endif /* CONFIG_CGROUP_SCHED */
+
+void __init sched_init(void)
+{
+ int i;
+ struct rq *rq;
+
+ print_scheduler_version();
+
+ wait_bit_init();
+
+#ifdef CONFIG_SMP
+ for (i = 0; i < NR_SCHED_RQ_QUEUED_LEVEL; i++)
+ cpumask_clear(&sched_rq_queued_masks[i]);
+ cpumask_setall(&sched_rq_queued_masks[SCHED_RQ_EMPTY]);
+ set_bit(SCHED_RQ_EMPTY, sched_rq_queued_masks_bitmap);
+
+ cpumask_setall(&sched_rq_pending_masks[SCHED_RQ_EMPTY]);
+ set_bit(SCHED_RQ_EMPTY, sched_rq_pending_masks_bitmap);
+#else
+ uprq = &per_cpu(runqueues, 0);
+#endif
+
+#ifdef CONFIG_CGROUP_SCHED
+ task_group_cache = KMEM_CACHE(task_group, 0);
+
+ list_add(&root_task_group.list, &task_groups);
+ INIT_LIST_HEAD(&root_task_group.children);
+ INIT_LIST_HEAD(&root_task_group.siblings);
+#endif /* CONFIG_CGROUP_SCHED */
+ for_each_possible_cpu(i) {
+ rq = cpu_rq(i);
+ FULL_INIT_SKIPLIST_NODE(&rq->sl_header);
+ raw_spin_lock_init(&rq->lock);
+ rq->dither = 0;
+ rq->nr_running = rq->nr_uninterruptible = 0;
+ rq->calc_load_active = 0;
+ rq->calc_load_update = jiffies + LOAD_FREQ;
+#ifdef CONFIG_SMP
+ rq->online = false;
+ rq->cpu = i;
+
+ rq->queued_level = SCHED_RQ_EMPTY;
+ rq->pending_level = SCHED_RQ_EMPTY;
+#ifdef CONFIG_SCHED_SMT
+ per_cpu(sched_sibling_cpu, i) = i;
+ rq->active_balance = 0;
+#endif
+#endif
+ rq->nr_switches = 0;
+ atomic_set(&rq->nr_iowait, 0);
+ hrtick_rq_init(rq);
+ }
+#ifdef CONFIG_SMP
+ /* Set rq->online for cpu 0 */
+ cpu_rq(0)->online = true;
+#endif
+
+ /*
+ * The boot idle thread does lazy MMU switching as well:
+ */
+ mmgrab(&init_mm);
+ 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());
+
+ calc_load_update = jiffies + LOAD_FREQ;
+
+#ifdef CONFIG_SMP
+ idle_thread_set_boot_cpu();
+
+ sched_init_topology_cpumask_early();
+#endif /* SMP */
+
+ init_schedstats();
+
+ psi_init();
+}
+
+#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)
+{
+ /* Ratelimiting timestamp: */
+ static unsigned long prev_jiffy;
+
+ unsigned long preempt_disable_ip;
+
+ /* WARN_ON_ONCE() by default, no rate limit required: */
+ rcu_sleep_check();
+
+ if ((preempt_count_equals(preempt_offset) && !irqs_disabled() &&
+ !is_idle_task(current) && !current->non_block_count) ||
+ system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
+ oops_in_progress)
+ return;
+ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+ return;
+ prev_jiffy = jiffies;
+
+ /* Save this before calling printk(), since that will clobber it: */
+ preempt_disable_ip = get_preempt_disable_ip(current);
+
+ 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, non_block: %d, pid: %d, name: %s\n",
+ in_atomic(), irqs_disabled(), current->non_block_count,
+ 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(preempt_disable_ip);
+ pr_cont("\n");
+ }
+#endif
+ dump_stack();
+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
+}
+EXPORT_SYMBOL(___might_sleep);
+
+void __cant_sleep(const char *file, int line, int preempt_offset)
+{
+ static unsigned long prev_jiffy;
+
+ if (irqs_disabled())
+ return;
+
+ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
+ return;
+
+ if (preempt_count() > preempt_offset)
+ return;
+
+ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
+ return;
+ prev_jiffy = jiffies;
+
+ printk(KERN_ERR "BUG: assuming atomic 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);
+
+ debug_show_held_locks(current);
+ dump_stack();
+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
+}
+EXPORT_SYMBOL_GPL(__cant_sleep);
+#endif
+
+#ifdef CONFIG_MAGIC_SYSRQ
+void normalize_rt_tasks(void)
+{
+ struct task_struct *g, *p;
+ struct sched_attr attr = {
+ .sched_policy = SCHED_NORMAL,
+ };
+
+ read_lock(&tasklist_lock);
+ for_each_process_thread(g, p) {
+ /*
+ * Only normalize user tasks:
+ */
+ if (p->flags & PF_KTHREAD)
+ continue;
+
+ if (!rt_task(p)) {
+ /*
+ * Renice negative nice level userspace
+ * tasks back to 0:
+ */
+ if (task_nice(p) < 0)
+ set_user_nice(p, 0);
+ continue;
+ }
+
+ __sched_setscheduler(p, &attr, false, false);
+ }
+ read_unlock(&tasklist_lock);
+}
+#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
+/**
+ * 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 ia64_set_curr_task(int cpu, struct task_struct *p)
+{
+ cpu_curr(cpu) = p;
+}
+
+#endif
+
+#ifdef CONFIG_SCHED_DEBUG
+void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
+ struct seq_file *m)
+{}
+
+void proc_sched_set_task(struct task_struct *p)
+{}
+#endif
+
+#ifdef CONFIG_CGROUP_SCHED
+static void sched_free_group(struct task_group *tg)
+{
+ kmem_cache_free(task_group_cache, tg);
+}
+
+/* allocate runqueue etc for a new task group */
+struct task_group *sched_create_group(struct task_group *parent)
+{
+ struct task_group *tg;
+
+ tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
+ if (!tg)
+ return ERR_PTR(-ENOMEM);
+
+ return tg;
+}
+
+void sched_online_group(struct task_group *tg, struct task_group *parent)
+{
+}
+
+/* rcu callback to free various structures associated with a task group */
+static void sched_free_group_rcu(struct rcu_head *rhp)
+{
+ /* Now it should be safe to free those cfs_rqs */
+ sched_free_group(container_of(rhp, struct task_group, rcu));
+}
+
+void sched_destroy_group(struct task_group *tg)
+{
+ /* Wait for possible concurrent references to cfs_rqs complete */
+ call_rcu(&tg->rcu, sched_free_group_rcu);
+}
+
+void sched_offline_group(struct task_group *tg)
+{
+}
+
+static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
+{
+ return css ? container_of(css, struct task_group, css) : NULL;
+}
+
+static struct cgroup_subsys_state *
+cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+ struct task_group *parent = css_tg(parent_css);
+ struct task_group *tg;
+
+ if (!parent) {
+ /* This is early initialization for the top cgroup */
+ return &root_task_group.css;
+ }
+
+ tg = sched_create_group(parent);
+ if (IS_ERR(tg))
+ return ERR_PTR(-ENOMEM);
+ return &tg->css;
+}
+
+/* Expose task group only after completing cgroup initialization */
+static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
+{
+ struct task_group *tg = css_tg(css);
+ struct task_group *parent = css_tg(css->parent);
+
+ if (parent)
+ sched_online_group(tg, parent);
+ return 0;
+}
+
+static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
+{
+ struct task_group *tg = css_tg(css);
+
+ sched_offline_group(tg);
+}
+
+static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
+{
+ struct task_group *tg = css_tg(css);
+
+ /*
+ * Relies on the RCU grace period between css_released() and this.
+ */
+ sched_free_group(tg);
+}
+
+static void cpu_cgroup_fork(struct task_struct *task)
+{
+}
+
+static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
+{
+ return 0;
+}
+
+static void cpu_cgroup_attach(struct cgroup_taskset *tset)
+{
+}
+
+static struct cftype cpu_legacy_files[] = {
+ { } /* Terminate */
+};
+
+static struct cftype cpu_files[] = {
+ { } /* terminate */
+};
+
+static int cpu_extra_stat_show(struct seq_file *sf,
+ struct cgroup_subsys_state *css)
+{
+ return 0;
+}
+
+struct cgroup_subsys cpu_cgrp_subsys = {
+ .css_alloc = cpu_cgroup_css_alloc,
+ .css_online = cpu_cgroup_css_online,
+ .css_released = cpu_cgroup_css_released,
+ .css_free = cpu_cgroup_css_free,
+ .css_extra_stat_show = cpu_extra_stat_show,
+ .fork = cpu_cgroup_fork,
+ .can_attach = cpu_cgroup_can_attach,
+ .attach = cpu_cgroup_attach,
+ .legacy_cftypes = cpu_files,
+ .legacy_cftypes = cpu_legacy_files,
+ .dfl_cftypes = cpu_files,
+ .early_init = true,
+ .threaded = true,
+};
+#endif /* CONFIG_CGROUP_SCHED */
+
+#undef CREATE_TRACE_POINTS
diff --git a/kernel/sched/pds_sched.h b/kernel/sched/pds_sched.h
new file mode 100644
index 000000000000..b3926a8425b2
--- /dev/null
+++ b/kernel/sched/pds_sched.h
@@ -0,0 +1,474 @@
+#ifndef PDS_SCHED_H
+#define PDS_SCHED_H
+
+#include <linux/sched.h>
+
+#include <linux/sched/clock.h>
+#include <linux/sched/cpufreq.h>
+#include <linux/sched/cputime.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/init.h>
+#include <linux/sched/isolation.h>
+#include <linux/sched/loadavg.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/nohz.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/stat.h>
+#include <linux/sched/sysctl.h>
+#include <linux/sched/task.h>
+#include <linux/sched/topology.h>
+#include <linux/sched/wake_q.h>
+
+#include <uapi/linux/sched/types.h>
+
+#include <linux/cgroup.h>
+#include <linux/cpufreq.h>
+#include <linux/cpuidle.h>
+#include <linux/cpuset.h>
+#include <linux/ctype.h>
+#include <linux/kthread.h>
+#include <linux/livepatch.h>
+#include <linux/membarrier.h>
+#include <linux/proc_fs.h>
+#include <linux/psi.h>
+#include <linux/slab.h>
+#include <linux/stop_machine.h>
+#include <linux/suspend.h>
+#include <linux/swait.h>
+#include <linux/syscalls.h>
+#include <linux/tsacct_kern.h>
+
+#include <asm/tlb.h>
+
+#ifdef CONFIG_PARAVIRT
+# include <asm/paravirt.h>
+#endif
+
+#include "cpupri.h"
+
+/* task_struct::on_rq states: */
+#define TASK_ON_RQ_QUEUED 1
+#define TASK_ON_RQ_MIGRATING 2
+
+static inline int task_on_rq_queued(struct task_struct *p)
+{
+ return p->on_rq == TASK_ON_RQ_QUEUED;
+}
+
+static inline int task_on_rq_migrating(struct task_struct *p)
+{
+ return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING;
+}
+
+/*
+ * This is the main, per-CPU runqueue data structure.
+ * This data should only be modified by the local cpu.
+ */
+struct rq {
+ /* runqueue lock: */
+ raw_spinlock_t lock;
+
+ struct task_struct *curr, *idle, *stop;
+ struct mm_struct *prev_mm;
+
+ struct skiplist_node sl_header;
+
+ /* switch count */
+ u64 nr_switches;
+
+ atomic_t nr_iowait;
+
+#ifdef CONFIG_MEMBARRIER
+ int membarrier_state;
+#endif
+
+#ifdef CONFIG_SMP
+ int cpu; /* cpu of this runqueue */
+ bool online;
+
+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
+ struct sched_avg avg_irq;
+#endif
+
+ unsigned long queued_level;
+ unsigned long pending_level;
+
+#ifdef CONFIG_SCHED_SMT
+ int active_balance;
+ struct cpu_stop_work active_balance_work;
+#endif
+#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 */
+
+ /* calc_load related fields */
+ unsigned long calc_load_update;
+ long calc_load_active;
+
+ u64 clock, last_tick;
+ u64 clock_task;
+ int dither;
+
+ unsigned long nr_running;
+ unsigned long nr_uninterruptible;
+
+#ifdef CONFIG_SCHED_HRTICK
+#ifdef CONFIG_SMP
+ int hrtick_csd_pending;
+ call_single_data_t hrtick_csd;
+#endif
+ struct hrtimer hrtick_timer;
+#endif
+
+#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
+};
+
+extern unsigned long calc_load_update;
+extern atomic_long_t calc_load_tasks;
+
+extern void calc_global_load_tick(struct rq *this_rq);
+extern long calc_load_fold_active(struct rq *this_rq, long adjust);
+
+#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 cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
+#define this_rq() this_cpu_ptr(&runqueues)
+#define raw_rq() raw_cpu_ptr(&runqueues)
+#define task_rq(p) cpu_rq(task_cpu(p))
+#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
+
+#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
+
+#endif /* CONFIG_SMP */
+
+#ifndef arch_scale_freq_capacity
+static __always_inline
+unsigned long arch_scale_freq_capacity(int cpu)
+{
+ return SCHED_CAPACITY_SCALE;
+}
+#endif
+
+static inline u64 __rq_clock_broken(struct rq *rq)
+{
+ return READ_ONCE(rq->clock);
+}
+
+static inline u64 rq_clock(struct rq *rq)
+{
+ /*
+ * Relax lockdep_assert_held() checking as in VRQ, call to
+ * sched_info_xxxx() may not held rq->lock
+ * lockdep_assert_held(&rq->lock);
+ */
+ return rq->clock;
+}
+
+static inline u64 rq_clock_task(struct rq *rq)
+{
+ /*
+ * Relax lockdep_assert_held() checking as in VRQ, call to
+ * sched_info_xxxx() may not held rq->lock
+ * lockdep_assert_held(&rq->lock);
+ */
+ return rq->clock_task;
+}
+
+/*
+ * {de,en}queue flags:
+ *
+ * DEQUEUE_SLEEP - task is no longer runnable
+ * ENQUEUE_WAKEUP - task just became runnable
+ *
+ */
+
+#define DEQUEUE_SLEEP 0x01
+
+#define ENQUEUE_WAKEUP 0x01
+
+
+/*
+ * Below are scheduler API which using in other kernel code
+ * It use the dummy rq_flags
+ * ToDo : PDS need to support these APIs for compatibility with mainline
+ * scheduler code.
+ */
+struct rq_flags {
+ unsigned long flags;
+};
+
+struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+ __acquires(rq->lock);
+
+struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
+ __acquires(p->pi_lock)
+ __acquires(rq->lock);
+
+static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ raw_spin_unlock(&rq->lock);
+}
+
+static inline void
+task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
+ __releases(rq->lock)
+ __releases(p->pi_lock)
+{
+ raw_spin_unlock(&rq->lock);
+ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
+}
+
+static inline void
+rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
+ __releases(rq->lock)
+{
+ raw_spin_unlock_irq(&rq->lock);
+}
+
+static inline struct rq *
+this_rq_lock_irq(struct rq_flags *rf)
+ __acquires(rq->lock)
+{
+ struct rq *rq;
+
+ local_irq_disable();
+ rq = this_rq();
+ raw_spin_lock(&rq->lock);
+
+ return rq;
+}
+
+static inline bool task_running(struct task_struct *p)
+{
+ return p->on_cpu;
+}
+
+extern struct static_key_false sched_schedstats;
+
+static inline void sched_ttwu_pending(void) { }
+
+#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
+
+static inline int cpu_of(const struct rq *rq)
+{
+#ifdef CONFIG_SMP
+ return rq->cpu;
+#else
+ return 0;
+#endif
+}
+
+#include "stats.h"
+
+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
+struct irqtime {
+ u64 total;
+ u64 tick_delta;
+ u64 irq_start_time;
+ struct u64_stats_sync sync;
+};
+
+DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
+
+/*
+ * Returns the irqtime minus the softirq time computed by ksoftirqd.
+ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
+ * and never move forward.
+ */
+static inline u64 irq_time_read(int cpu)
+{
+ struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
+ unsigned int seq;
+ u64 total;
+
+ do {
+ seq = __u64_stats_fetch_begin(&irqtime->sync);
+ total = irqtime->total;
+ } while (__u64_stats_fetch_retry(&irqtime->sync, seq));
+
+ return total;
+}
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
+
+#ifdef CONFIG_CPU_FREQ
+DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
+
+/**
+ * cpufreq_update_util - Take a note about CPU utilization changes.
+ * @rq: Runqueue to carry out the update for.
+ * @flags: Update reason flags.
+ *
+ * This function is called by the scheduler on the CPU whose utilization is
+ * being updated.
+ *
+ * It can only be called from RCU-sched read-side critical sections.
+ *
+ * The way cpufreq is currently arranged requires it to evaluate the CPU
+ * performance state (frequency/voltage) on a regular basis to prevent it from
+ * being stuck in a completely inadequate performance level for too long.
+ * That is not guaranteed to happen if the updates are only triggered from CFS
+ * and DL, though, because they may not be coming in if only RT tasks are
+ * active all the time (or there are RT tasks only).
+ *
+ * As a workaround for that issue, this function is called periodically by the
+ * RT sched class to trigger extra cpufreq updates to prevent it from stalling,
+ * but that really is a band-aid. Going forward it should be replaced with
+ * solutions targeted more specifically at RT tasks.
+ */
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
+{
+ struct update_util_data *data;
+
+ data = rcu_dereference_sched(*this_cpu_ptr(&cpufreq_update_util_data));
+ if (data)
+ data->func(data, rq_clock(rq), flags);
+}
+
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags)
+{
+ if (cpu_of(rq) == smp_processor_id())
+ cpufreq_update_util(rq, flags);
+}
+#else
+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) {}
+static inline void cpufreq_update_this_cpu(struct rq *rq, unsigned int flags) {}
+#endif /* CONFIG_CPU_FREQ */
+
+#ifdef CONFIG_NO_HZ_FULL
+extern int __init sched_tick_offload_init(void);
+#else
+static inline int sched_tick_offload_init(void) { return 0; }
+#endif
+
+#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
+
+extern void schedule_idle(void);
+
+/*
+ * !! For sched_setattr_nocheck() (kernel) only !!
+ *
+ * This is actually gross. :(
+ *
+ * It is used to make schedutil kworker(s) higher priority than SCHED_DEADLINE
+ * tasks, but still be able to sleep. We need this on platforms that cannot
+ * atomically change clock frequency. Remove once fast switching will be
+ * available on such platforms.
+ *
+ * SUGOV stands for SchedUtil GOVernor.
+ */
+#define SCHED_FLAG_SUGOV 0x10000000
+
+#ifdef CONFIG_MEMBARRIER
+/*
+ * The scheduler provides memory barriers required by membarrier between:
+ * - prior user-space memory accesses and store to rq->membarrier_state,
+ * - store to rq->membarrier_state and following user-space memory accesses.
+ * In the same way it provides those guarantees around store to rq->curr.
+ */
+static inline void membarrier_switch_mm(struct rq *rq,
+ struct mm_struct *prev_mm,
+ struct mm_struct *next_mm)
+{
+ int membarrier_state;
+
+ if (prev_mm == next_mm)
+ return;
+
+ membarrier_state = atomic_read(&next_mm->membarrier_state);
+ if (READ_ONCE(rq->membarrier_state) == membarrier_state)
+ return;
+
+ WRITE_ONCE(rq->membarrier_state, membarrier_state);
+}
+#else
+static inline void membarrier_switch_mm(struct rq *rq,
+ struct mm_struct *prev_mm,
+ struct mm_struct *next_mm)
+{
+}
+#endif
+
+#ifdef CONFIG_NUMA
+extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu);
+#else
+static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
+{
+ return nr_cpu_ids;
+}
+#endif
+#endif /* PDS_SCHED_H */
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index a96db50d40e0..d3d12baa9036 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -236,6 +236,7 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runna
WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
}
+#ifndef CONFIG_SCHED_PDS
/*
* sched_entity:
*
@@ -352,6 +353,7 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
return 0;
}
+#endif
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
/*
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index afff644da065..26d6b47fc156 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -1,11 +1,13 @@
#ifdef CONFIG_SMP
#include "sched-pelt.h"
+#ifndef CONFIG_SCHED_PDS
int __update_load_avg_blocked_se(u64 now, struct sched_entity *se);
int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se);
int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq);
int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
+#endif
#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
int update_irq_load_avg(struct rq *rq, u64 running);
@@ -17,6 +19,7 @@ update_irq_load_avg(struct rq *rq, u64 running)
}
#endif
+#ifndef CONFIG_SCHED_PDS
/*
* When a task is dequeued, its estimated utilization should not be update if
* its util_avg has not been updated at least once.
@@ -137,9 +140,11 @@ static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
return rq_clock_pelt(rq_of(cfs_rq));
}
#endif
+#endif /* CONFIG_SCHED_PDS */
#else
+#ifndef CONFIG_SCHED_PDS
static inline int
update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
{
@@ -157,6 +162,7 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
{
return 0;
}
+#endif
static inline int
update_irq_load_avg(struct rq *rq, u64 running)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c8870c5bd7df..4fc9f2ead4d2 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2,6 +2,10 @@
/*
* Scheduler internal types and methods:
*/
+#ifdef CONFIG_SCHED_PDS
+#include "pds_sched.h"
+#else
+
#include <linux/sched.h>
#include <linux/sched/autogroup.h>
@@ -2496,3 +2500,4 @@ static inline void membarrier_switch_mm(struct rq *rq,
{
}
#endif
+#endif /* !CONFIG_SCHED_PDS */
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 750fb3c67eed..45bd43942575 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -22,8 +22,10 @@ static int show_schedstat(struct seq_file *seq, void *v)
} else {
struct rq *rq;
#ifdef CONFIG_SMP
+#ifndef CONFIG_SCHED_PDS
struct sched_domain *sd;
int dcount = 0;
+#endif
#endif
cpu = (unsigned long)(v - 2);
rq = cpu_rq(cpu);
@@ -40,6 +42,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
seq_printf(seq, "\n");
#ifdef CONFIG_SMP
+#ifndef CONFIG_SCHED_PDS
/* domain-specific stats */
rcu_read_lock();
for_each_domain(cpu, sd) {
@@ -68,6 +71,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
sd->ttwu_move_balance);
}
rcu_read_unlock();
+#endif
#endif
}
return 0;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index b6f2f35d0bcf..204933ebc95a 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -130,8 +130,12 @@ static int __maybe_unused four = 4;
static unsigned long zero_ul;
static unsigned long one_ul = 1;
static unsigned long long_max = LONG_MAX;
-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_PDS
+extern int rr_interval;
+extern int sched_yield_type;
+#endif
#ifdef CONFIG_PRINTK
static int ten_thousand = 10000;
#endif
@@ -300,7 +304,7 @@ static struct ctl_table sysctl_base_table[] = {
{ }
};
-#ifdef CONFIG_SCHED_DEBUG
+#if defined(CONFIG_SCHED_DEBUG) && !defined(CONFIG_SCHED_PDS)
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 */
@@ -317,6 +321,7 @@ static int max_extfrag_threshold = 1000;
#endif
static struct ctl_table kern_table[] = {
+#ifndef CONFIG_SCHED_PDS
{
.procname = "sched_child_runs_first",
.data = &sysctl_sched_child_runs_first,
@@ -498,6 +503,7 @@ static struct ctl_table kern_table[] = {
.extra2 = SYSCTL_ONE,
},
#endif
+#endif /* !CONFIG_SCHED_PDS */
#ifdef CONFIG_PROVE_LOCKING
{
.procname = "prove_locking",
@@ -1070,6 +1076,26 @@ static struct ctl_table kern_table[] = {
.proc_handler = proc_dointvec,
},
#endif
+#ifdef CONFIG_SCHED_PDS
+ {
+ .procname = "rr_interval",
+ .data = &rr_interval,
+ .maxlen = sizeof (int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .extra1 = SYSCTL_ONE,
+ .extra2 = &one_thousand,
+ },
+ {
+ .procname = "yield_type",
+ .data = &sched_yield_type,
+ .maxlen = sizeof (int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = &two,
+ },
+#endif
#if defined(CONFIG_S390) && defined(CONFIG_SMP)
{
.procname = "spin_retry",
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 42d512fcfda2..71af3cd30ccc 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -226,7 +226,7 @@ static void task_sample_cputime(struct task_struct *p, u64 *samples)
u64 stime, utime;
task_cputime(p, &utime, &stime);
- store_samples(samples, stime, utime, p->se.sum_exec_runtime);
+ store_samples(samples, stime, utime, tsk_seruntime(p));
}
static void proc_sample_cputime_atomic(struct task_cputime_atomic *at,
@@ -796,6 +796,7 @@ static void collect_posix_cputimers(struct posix_cputimers *pct, u64 *samples,
}
}
+#ifndef CONFIG_SCHED_PDS
static inline void check_dl_overrun(struct task_struct *tsk)
{
if (tsk->dl.dl_overrun) {
@@ -803,6 +804,7 @@ static inline void check_dl_overrun(struct task_struct *tsk)
__group_send_sig_info(SIGXCPU, SEND_SIG_PRIV, tsk);
}
}
+#endif
static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard)
{
@@ -830,8 +832,10 @@ static void check_thread_timers(struct task_struct *tsk,
u64 samples[CPUCLOCK_MAX];
unsigned long soft;
+#ifndef CONFIG_SCHED_PDS
if (dl_task(tsk))
check_dl_overrun(tsk);
+#endif
if (expiry_cache_is_inactive(pct))
return;
@@ -845,7 +849,7 @@ static void check_thread_timers(struct task_struct *tsk,
soft = task_rlimit(tsk, RLIMIT_RTTIME);
if (soft != RLIM_INFINITY) {
/* Task RT timeout is accounted in jiffies. RTTIME is usec */
- unsigned long rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ);
+ unsigned long rttime = tsk_rttimeout(tsk) * (USEC_PER_SEC / HZ);
unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME);
/* At the hard limit, send SIGKILL. No further action. */
@@ -1099,8 +1103,10 @@ static inline bool fastpath_timer_check(struct task_struct *tsk)
return true;
}
+#ifndef CONFIG_SCHED_PDS
if (dl_task(tsk) && tsk->dl.dl_overrun)
return true;
+#endif
return false;
}
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 69ee8ef12cee..3eaa2a21caa4 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -1048,10 +1048,15 @@ static int trace_wakeup_test_thread(void *data)
{
/* Make this a -deadline thread */
static const struct sched_attr attr = {
+#ifdef CONFIG_SCHED_PDS
+ /* 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;
Reference in New Issue View Git Blame Copy Permalink