From 244b2c5ca8b14627e4a17755e5922221e121c771 Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Wed, 09 Oct 2024 06:15:07 +0000
Subject: [PATCH] change system file
---
kernel/kernel/cpu.c | 829 ++++++++++++++++++++++++++++++++++++++++++++++------------
1 files changed, 655 insertions(+), 174 deletions(-)
diff --git a/kernel/kernel/cpu.c b/kernel/kernel/cpu.c
index 51b17e4..09d8ee3 100644
--- a/kernel/kernel/cpu.c
+++ b/kernel/kernel/cpu.c
@@ -10,6 +10,7 @@
#include <linux/notifier.h>
#include <linux/sched/signal.h>
#include <linux/sched/hotplug.h>
+#include <linux/sched/isolation.h>
#include <linux/sched/task.h>
#include <linux/sched/smt.h>
#include <linux/unistd.h>
@@ -30,13 +31,21 @@
#include <linux/smpboot.h>
#include <linux/relay.h>
#include <linux/slab.h>
+#include <linux/scs.h>
#include <linux/percpu-rwsem.h>
#include <linux/cpuset.h>
+#include <linux/random.h>
+#include <uapi/linux/sched/types.h>
#include <trace/events/power.h>
#define CREATE_TRACE_POINTS
#include <trace/events/cpuhp.h>
+#undef CREATE_TRACE_POINTS
+#include <trace/hooks/sched.h>
+#include <trace/hooks/cpu.h>
+
+#include "sched/sched.h"
#include "smpboot.h"
/**
@@ -63,7 +72,6 @@
bool rollback;
bool single;
bool bringup;
- bool booted_once;
struct hlist_node *node;
struct hlist_node *last;
enum cpuhp_state cb_state;
@@ -76,6 +84,10 @@
static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = {
.fail = CPUHP_INVALID,
};
+
+#ifdef CONFIG_SMP
+cpumask_t cpus_booted_once_mask;
+#endif
#if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
static struct lockdep_map cpuhp_state_up_map =
@@ -269,11 +281,13 @@
{
mutex_lock(&cpu_add_remove_lock);
}
+EXPORT_SYMBOL_GPL(cpu_maps_update_begin);
void cpu_maps_update_done(void)
{
mutex_unlock(&cpu_add_remove_lock);
}
+EXPORT_SYMBOL_GPL(cpu_maps_update_done);
/*
* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
@@ -327,6 +341,16 @@
percpu_rwsem_assert_held(&cpu_hotplug_lock);
}
+static void lockdep_acquire_cpus_lock(void)
+{
+ rwsem_acquire(&cpu_hotplug_lock.dep_map, 0, 0, _THIS_IP_);
+}
+
+static void lockdep_release_cpus_lock(void)
+{
+ rwsem_release(&cpu_hotplug_lock.dep_map, _THIS_IP_);
+}
+
/*
* Wait for currently running CPU hotplug operations to complete (if any) and
* disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects
@@ -356,6 +380,17 @@
cpu_maps_update_done();
}
EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
+
+#else
+
+static void lockdep_acquire_cpus_lock(void)
+{
+}
+
+static void lockdep_release_cpus_lock(void)
+{
+}
+
#endif /* CONFIG_HOTPLUG_CPU */
/*
@@ -369,8 +404,7 @@
void __init cpu_smt_disable(bool force)
{
- if (cpu_smt_control == CPU_SMT_FORCE_DISABLED ||
- cpu_smt_control == CPU_SMT_NOT_SUPPORTED)
+ if (!cpu_smt_possible())
return;
if (force) {
@@ -410,11 +444,19 @@
/*
* On x86 it's required to boot all logical CPUs at least once so
* that the init code can get a chance to set CR4.MCE on each
- * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any
+ * CPU. Otherwise, a broadcasted MCE observing CR4.MCE=0b on any
* core will shutdown the machine.
*/
- return !per_cpu(cpuhp_state, cpu).booted_once;
+ return !cpumask_test_cpu(cpu, &cpus_booted_once_mask);
}
+
+/* Returns true if SMT is not supported of forcefully (irreversibly) disabled */
+bool cpu_smt_possible(void)
+{
+ return cpu_smt_control != CPU_SMT_FORCE_DISABLED &&
+ cpu_smt_control != CPU_SMT_NOT_SUPPORTED;
+}
+EXPORT_SYMBOL_GPL(cpu_smt_possible);
#else
static inline bool cpu_smt_allowed(unsigned int cpu) { return true; }
#endif
@@ -501,7 +543,7 @@
/*
* SMT soft disabling on X86 requires to bring the CPU out of the
* BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The
- * CPU marked itself as booted_once in cpu_notify_starting() so the
+ * CPU marked itself as booted_once in notify_cpu_starting() so the
* cpu_smt_allowed() check will now return false if this is not the
* primary sibling.
*/
@@ -518,6 +560,12 @@
{
struct task_struct *idle = idle_thread_get(cpu);
int ret;
+
+ /*
+ * Reset stale stack state from the last time this CPU was online.
+ */
+ scs_task_reset(idle);
+ kasan_unpoison_task_stack(idle);
/*
* Some architectures have to walk the irq descriptors to
@@ -640,6 +688,12 @@
*/
smp_mb();
+ /*
+ * The BP holds the hotplug lock, but we're now running on the AP,
+ * ensure that anybody asserting the lock is held, will actually find
+ * it so.
+ */
+ lockdep_acquire_cpus_lock();
cpuhp_lock_acquire(bringup);
if (st->single) {
@@ -685,6 +739,7 @@
}
cpuhp_lock_release(bringup);
+ lockdep_release_cpus_lock();
if (!st->should_run)
complete_ap_thread(st, bringup);
@@ -876,15 +931,6 @@
int err, cpu = smp_processor_id();
int ret;
-#ifdef CONFIG_PREEMPT_RT_BASE
- /*
- * If any tasks disabled migration before we got here,
- * go back and sleep again.
- */
- if (cpu_nr_pinned(cpu))
- return -EAGAIN;
-#endif
-
/* Ensure this CPU doesn't handle any more interrupts. */
err = __cpu_disable();
if (err < 0)
@@ -907,14 +953,12 @@
/* Give up timekeeping duties */
tick_handover_do_timer();
+ /* Remove CPU from timer broadcasting */
+ tick_offline_cpu(cpu);
/* Park the stopper thread */
stop_machine_park(cpu);
return 0;
}
-
-#ifdef CONFIG_PREEMPT_RT_BASE
-struct task_struct *takedown_cpu_task;
-#endif
static int takedown_cpu(unsigned int cpu)
{
@@ -930,39 +974,11 @@
*/
irq_lock_sparse();
-#ifdef CONFIG_PREEMPT_RT_BASE
- WARN_ON_ONCE(takedown_cpu_task);
- takedown_cpu_task = current;
-
-again:
- /*
- * If a task pins this CPU after we pass this check, take_cpu_down
- * will return -EAGAIN.
- */
- for (;;) {
- int nr_pinned;
-
- set_current_state(TASK_UNINTERRUPTIBLE);
- nr_pinned = cpu_nr_pinned(cpu);
- if (nr_pinned == 0)
- break;
- schedule();
- }
- set_current_state(TASK_RUNNING);
-#endif
-
/*
* So now all preempt/rcu users must observe !cpu_active().
*/
err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu));
-#ifdef CONFIG_PREEMPT_RT_BASE
- if (err == -EAGAIN)
- goto again;
-#endif
if (err) {
-#ifdef CONFIG_PREEMPT_RT_BASE
- takedown_cpu_task = NULL;
-#endif
/* CPU refused to die */
irq_unlock_sparse();
/* Unpark the hotplug thread so we can rollback there */
@@ -981,9 +997,6 @@
wait_for_ap_thread(st, false);
BUG_ON(st->state != CPUHP_AP_IDLE_DEAD);
-#ifdef CONFIG_PREEMPT_RT_BASE
- takedown_cpu_task = NULL;
-#endif
/* Interrupts are moved away from the dying cpu, reenable alloc/free */
irq_unlock_sparse();
@@ -1049,7 +1062,7 @@
struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
int prev_state, ret = 0;
- if (num_online_cpus() == 1)
+ if (num_active_cpus() == 1 && cpu_active(cpu))
return -EBUSY;
if (!cpu_present(cpu))
@@ -1112,7 +1125,7 @@
return _cpu_down(cpu, 0, target);
}
-static int do_cpu_down(unsigned int cpu, enum cpuhp_state target)
+static int cpu_down(unsigned int cpu, enum cpuhp_state target)
{
int err;
@@ -1122,11 +1135,315 @@
return err;
}
-int cpu_down(unsigned int cpu)
+/**
+ * cpu_device_down - Bring down a cpu device
+ * @dev: Pointer to the cpu device to offline
+ *
+ * This function is meant to be used by device core cpu subsystem only.
+ *
+ * Other subsystems should use remove_cpu() instead.
+ */
+int cpu_device_down(struct device *dev)
{
- return do_cpu_down(cpu, CPUHP_OFFLINE);
+ return cpu_down(dev->id, CPUHP_OFFLINE);
}
-EXPORT_SYMBOL(cpu_down);
+
+int remove_cpu(unsigned int cpu)
+{
+ int ret;
+
+ lock_device_hotplug();
+ ret = device_offline(get_cpu_device(cpu));
+ unlock_device_hotplug();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(remove_cpu);
+
+int __pause_drain_rq(struct cpumask *cpus)
+{
+ unsigned int cpu;
+ int err = 0;
+
+ /*
+ * Disabling preemption avoids that one of the stopper, started from
+ * sched_cpu_drain_rq(), blocks firing draining for the whole cpumask.
+ */
+ preempt_disable();
+ for_each_cpu(cpu, cpus) {
+ err = sched_cpu_drain_rq(cpu);
+ if (err)
+ break;
+ }
+ preempt_enable();
+
+ return err;
+}
+
+void __wait_drain_rq(struct cpumask *cpus)
+{
+ unsigned int cpu;
+
+ for_each_cpu(cpu, cpus)
+ sched_cpu_drain_rq_wait(cpu);
+}
+
+/* if rt task, set to cfs and return previous prio */
+static int pause_reduce_prio(void)
+{
+ int prev_prio = -1;
+
+ if (current->prio < MAX_RT_PRIO) {
+ struct sched_param param = { .sched_priority = 0 };
+
+ prev_prio = current->prio;
+ sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m);
+ }
+
+ return prev_prio;
+}
+
+/* if previous prio was set, restore */
+static void pause_restore_prio(int prev_prio)
+{
+ if (prev_prio >= 0 && prev_prio < MAX_RT_PRIO) {
+ struct sched_param param = { .sched_priority = MAX_RT_PRIO-1-prev_prio };
+
+ sched_setscheduler_nocheck(current, SCHED_FIFO, ¶m);
+ }
+}
+
+int pause_cpus(struct cpumask *cpus)
+{
+ int err = 0;
+ int cpu;
+ u64 start_time = 0;
+ int prev_prio;
+
+ start_time = sched_clock();
+
+ cpu_maps_update_begin();
+
+ if (cpu_hotplug_disabled) {
+ err = -EBUSY;
+ goto err_cpu_maps_update;
+ }
+
+ /* Pausing an already inactive CPU isn't an error */
+ cpumask_and(cpus, cpus, cpu_active_mask);
+
+ for_each_cpu(cpu, cpus) {
+ if (!cpu_online(cpu) || dl_bw_check_overflow(cpu) ||
+ get_cpu_device(cpu)->offline_disabled == true) {
+ err = -EBUSY;
+ goto err_cpu_maps_update;
+ }
+ }
+
+ if (cpumask_weight(cpus) >= num_active_cpus()) {
+ err = -EBUSY;
+ goto err_cpu_maps_update;
+ }
+
+ if (cpumask_empty(cpus))
+ goto err_cpu_maps_update;
+
+ /*
+ * Lazy migration:
+ *
+ * We do care about how fast a CPU can go idle and stay this in this
+ * state. If we try to take the cpus_write_lock() here, we would have
+ * to wait for a few dozens of ms, as this function might schedule.
+ * However, we can, as a first step, flip the active mask and migrate
+ * anything currently on the run-queue, to give a chance to the paused
+ * CPUs to reach quickly an idle state. There's a risk meanwhile for
+ * another CPU to observe an out-of-date active_mask or to incompletely
+ * update a cpuset. Both problems would be resolved later in the slow
+ * path, which ensures active_mask synchronization, triggers a cpuset
+ * rebuild and migrate any task that would have escaped the lazy
+ * migration.
+ */
+ for_each_cpu(cpu, cpus)
+ set_cpu_active(cpu, false);
+ err = __pause_drain_rq(cpus);
+ if (err) {
+ __wait_drain_rq(cpus);
+ for_each_cpu(cpu, cpus)
+ set_cpu_active(cpu, true);
+ goto err_cpu_maps_update;
+ }
+
+ prev_prio = pause_reduce_prio();
+
+ /*
+ * Slow path deactivation:
+ *
+ * Now that paused CPUs are most likely idle, we can go through a
+ * complete scheduler deactivation.
+ *
+ * The cpu_active_mask being already set and cpus_write_lock calling
+ * synchronize_rcu(), we know that all preempt-disabled and RCU users
+ * will observe the updated value.
+ */
+ cpus_write_lock();
+
+ __wait_drain_rq(cpus);
+
+ cpuhp_tasks_frozen = 0;
+
+ if (sched_cpus_deactivate_nosync(cpus)) {
+ err = -EBUSY;
+ goto err_cpus_write_unlock;
+ }
+
+ err = __pause_drain_rq(cpus);
+ __wait_drain_rq(cpus);
+ if (err) {
+ for_each_cpu(cpu, cpus)
+ sched_cpu_activate(cpu);
+ goto err_cpus_write_unlock;
+ }
+
+ /*
+ * Even if living on the side of the regular HP path, pause is using
+ * one of the HP step (CPUHP_AP_ACTIVE). This should be reflected on the
+ * current state of the CPU.
+ */
+ for_each_cpu(cpu, cpus) {
+ struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+
+ st->state = CPUHP_AP_ACTIVE - 1;
+ st->target = st->state;
+ }
+
+err_cpus_write_unlock:
+ cpus_write_unlock();
+ pause_restore_prio(prev_prio);
+err_cpu_maps_update:
+ cpu_maps_update_done();
+
+ trace_cpuhp_pause(cpus, start_time, 1);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(pause_cpus);
+
+int resume_cpus(struct cpumask *cpus)
+{
+ unsigned int cpu;
+ int err = 0;
+ u64 start_time = 0;
+ int prev_prio;
+
+ start_time = sched_clock();
+
+ cpu_maps_update_begin();
+
+ if (cpu_hotplug_disabled) {
+ err = -EBUSY;
+ goto err_cpu_maps_update;
+ }
+
+ /* Resuming an already active CPU isn't an error */
+ cpumask_andnot(cpus, cpus, cpu_active_mask);
+
+ for_each_cpu(cpu, cpus) {
+ if (!cpu_online(cpu)) {
+ err = -EBUSY;
+ goto err_cpu_maps_update;
+ }
+ }
+
+ if (cpumask_empty(cpus))
+ goto err_cpu_maps_update;
+
+ for_each_cpu(cpu, cpus)
+ set_cpu_active(cpu, true);
+
+ trace_android_rvh_resume_cpus(cpus, &err);
+ if (err)
+ goto err_cpu_maps_update;
+
+ prev_prio = pause_reduce_prio();
+
+ /* Lazy Resume. Build domains through schedule a workqueue on
+ * resuming cpu. This is so that the resuming cpu can work more
+ * early, and cannot add additional load to other busy cpu.
+ */
+ cpuset_update_active_cpus_affine(cpumask_first(cpus));
+
+ cpus_write_lock();
+
+ cpuhp_tasks_frozen = 0;
+
+ if (sched_cpus_activate(cpus)) {
+ err = -EBUSY;
+ goto err_cpus_write_unlock;
+ }
+
+ /*
+ * see pause_cpus.
+ */
+ for_each_cpu(cpu, cpus) {
+ struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+
+ st->state = CPUHP_ONLINE;
+ st->target = st->state;
+ }
+
+err_cpus_write_unlock:
+ cpus_write_unlock();
+ pause_restore_prio(prev_prio);
+err_cpu_maps_update:
+ cpu_maps_update_done();
+
+ trace_cpuhp_pause(cpus, start_time, 0);
+
+ return err;
+}
+EXPORT_SYMBOL_GPL(resume_cpus);
+
+void smp_shutdown_nonboot_cpus(unsigned int primary_cpu)
+{
+ unsigned int cpu;
+ int error;
+
+ cpu_maps_update_begin();
+
+ /*
+ * Make certain the cpu I'm about to reboot on is online.
+ *
+ * This is inline to what migrate_to_reboot_cpu() already do.
+ */
+ if (!cpu_online(primary_cpu))
+ primary_cpu = cpumask_first(cpu_online_mask);
+
+ for_each_online_cpu(cpu) {
+ if (cpu == primary_cpu)
+ continue;
+
+ error = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+ if (error) {
+ pr_err("Failed to offline CPU%d - error=%d",
+ cpu, error);
+ break;
+ }
+ }
+
+ /*
+ * Ensure all but the reboot CPU are offline.
+ */
+ BUG_ON(num_online_cpus() > 1);
+
+ /*
+ * Make sure the CPUs won't be enabled by someone else after this
+ * point. Kexec will reboot to a new kernel shortly resetting
+ * everything along the way.
+ */
+ cpu_hotplug_disabled++;
+
+ cpu_maps_update_done();
+}
#else
#define takedown_cpu NULL
@@ -1146,7 +1463,7 @@
int ret;
rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */
- st->booted_once = true;
+ cpumask_set_cpu(cpu, &cpus_booted_once_mask);
while (st->state < target) {
st->state++;
ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL);
@@ -1180,6 +1497,25 @@
complete_ap_thread(st, true);
}
+static int switch_to_rt_policy(void)
+{
+ struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
+ unsigned int policy = current->policy;
+
+ if (policy == SCHED_NORMAL)
+ /* Switch to SCHED_FIFO from SCHED_NORMAL. */
+ return sched_setscheduler_nocheck(current, SCHED_FIFO, ¶m);
+ else
+ return 1;
+}
+
+static int switch_to_fair_policy(void)
+{
+ struct sched_param param = { .sched_priority = 0 };
+
+ return sched_setscheduler_nocheck(current, SCHED_NORMAL, ¶m);
+}
+
/* Requires cpu_add_remove_lock to be held */
static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
{
@@ -1195,8 +1531,8 @@
}
/*
- * The caller of do_cpu_up might have raced with another
- * caller. Ignore it for now.
+ * The caller of cpu_up() might have raced with another
+ * caller. Nothing to do.
*/
if (st->state >= target)
goto out;
@@ -1241,9 +1577,10 @@
return ret;
}
-static int do_cpu_up(unsigned int cpu, enum cpuhp_state target)
+static int cpu_up(unsigned int cpu, enum cpuhp_state target)
{
int err = 0;
+ int switch_err;
if (!cpu_possible(cpu)) {
pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n",
@@ -1254,9 +1591,23 @@
return -EINVAL;
}
+ trace_android_vh_cpu_up(cpu);
+
+ /*
+ * CPU hotplug operations consists of many steps and each step
+ * calls a callback of core kernel subsystem. CPU hotplug-in
+ * operation may get preempted by other CFS tasks and whole
+ * operation of cpu hotplug in CPU gets delayed. Switch the
+ * current task to SCHED_FIFO from SCHED_NORMAL, so that
+ * hotplug in operation may complete quickly in heavy loaded
+ * conditions and new CPU will start handle the workload.
+ */
+
+ switch_err = switch_to_rt_policy();
+
err = try_online_node(cpu_to_node(cpu));
if (err)
- return err;
+ goto switch_out;
cpu_maps_update_begin();
@@ -1272,14 +1623,76 @@
err = _cpu_up(cpu, 0, target);
out:
cpu_maps_update_done();
+switch_out:
+ if (!switch_err) {
+ switch_err = switch_to_fair_policy();
+ if (switch_err)
+ pr_err("Hotplug policy switch err=%d Task %s pid=%d\n",
+ switch_err, current->comm, current->pid);
+ }
+
return err;
}
-int cpu_up(unsigned int cpu)
+/**
+ * cpu_device_up - Bring up a cpu device
+ * @dev: Pointer to the cpu device to online
+ *
+ * This function is meant to be used by device core cpu subsystem only.
+ *
+ * Other subsystems should use add_cpu() instead.
+ */
+int cpu_device_up(struct device *dev)
{
- return do_cpu_up(cpu, CPUHP_ONLINE);
+ return cpu_up(dev->id, CPUHP_ONLINE);
}
-EXPORT_SYMBOL_GPL(cpu_up);
+
+int add_cpu(unsigned int cpu)
+{
+ int ret;
+
+ lock_device_hotplug();
+ ret = device_online(get_cpu_device(cpu));
+ unlock_device_hotplug();
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(add_cpu);
+
+/**
+ * bringup_hibernate_cpu - Bring up the CPU that we hibernated on
+ * @sleep_cpu: The cpu we hibernated on and should be brought up.
+ *
+ * On some architectures like arm64, we can hibernate on any CPU, but on
+ * wake up the CPU we hibernated on might be offline as a side effect of
+ * using maxcpus= for example.
+ */
+int bringup_hibernate_cpu(unsigned int sleep_cpu)
+{
+ int ret;
+
+ if (!cpu_online(sleep_cpu)) {
+ pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n");
+ ret = cpu_up(sleep_cpu, CPUHP_ONLINE);
+ if (ret) {
+ pr_err("Failed to bring hibernate-CPU up!\n");
+ return ret;
+ }
+ }
+ return 0;
+}
+
+void bringup_nonboot_cpus(unsigned int setup_max_cpus)
+{
+ unsigned int cpu;
+
+ for_each_present_cpu(cpu) {
+ if (num_online_cpus() >= setup_max_cpus)
+ break;
+ if (!cpu_online(cpu))
+ cpu_up(cpu, CPUHP_ONLINE);
+ }
+}
#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_var_t frozen_cpus;
@@ -1289,8 +1702,15 @@
int cpu, error = 0;
cpu_maps_update_begin();
- if (!cpu_online(primary))
+ if (primary == -1) {
primary = cpumask_first(cpu_online_mask);
+ if (!housekeeping_cpu(primary, HK_FLAG_TIMER))
+ primary = housekeeping_any_cpu(HK_FLAG_TIMER);
+ } else {
+ if (!cpu_online(primary))
+ primary = cpumask_first(cpu_online_mask);
+ }
+
/*
* We take down all of the non-boot CPUs in one shot to avoid races
* with the userspace trying to use the CPU hotplug at the same time
@@ -1301,6 +1721,13 @@
for_each_online_cpu(cpu) {
if (cpu == primary)
continue;
+
+ if (pm_wakeup_pending()) {
+ pr_info("Wakeup pending. Abort CPU freeze\n");
+ error = -EBUSY;
+ break;
+ }
+
trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
error = _cpu_down(cpu, 1, CPUHP_OFFLINE);
trace_suspend_resume(TPS("CPU_OFF"), cpu, false);
@@ -1319,8 +1746,8 @@
/*
* Make sure the CPUs won't be enabled by someone else. We need to do
- * this even in case of failure as all disable_nonboot_cpus() users are
- * supposed to do enable_nonboot_cpus() on the failure path.
+ * this even in case of failure as all freeze_secondary_cpus() users are
+ * supposed to do thaw_secondary_cpus() on the failure path.
*/
cpu_hotplug_disabled++;
@@ -1328,15 +1755,15 @@
return error;
}
-void __weak arch_enable_nonboot_cpus_begin(void)
+void __weak arch_thaw_secondary_cpus_begin(void)
{
}
-void __weak arch_enable_nonboot_cpus_end(void)
+void __weak arch_thaw_secondary_cpus_end(void)
{
}
-void enable_nonboot_cpus(void)
+void thaw_secondary_cpus(void)
{
int cpu, error;
struct device *cpu_device;
@@ -1349,7 +1776,7 @@
pr_info("Enabling non-boot CPUs ...\n");
- arch_enable_nonboot_cpus_begin();
+ arch_thaw_secondary_cpus_begin();
for_each_cpu(cpu, frozen_cpus) {
trace_suspend_resume(TPS("CPU_ON"), cpu, true);
@@ -1368,7 +1795,7 @@
pr_warn("Error taking CPU%d up: %d\n", cpu, error);
}
- arch_enable_nonboot_cpus_end();
+ arch_thaw_secondary_cpus_end();
cpumask_clear(frozen_cpus);
out:
@@ -1434,6 +1861,22 @@
int __boot_cpu_id;
+/* Horrific hacks because we can't add more to cpuhp_hp_states. */
+static int random_and_perf_prepare_fusion(unsigned int cpu)
+{
+#ifdef CONFIG_PERF_EVENTS
+ perf_event_init_cpu(cpu);
+#endif
+ random_prepare_cpu(cpu);
+ return 0;
+}
+static int random_and_workqueue_online_fusion(unsigned int cpu)
+{
+ workqueue_online_cpu(cpu);
+ random_online_cpu(cpu);
+ return 0;
+}
+
#endif /* CONFIG_SMP */
/* Boot processor state steps */
@@ -1452,7 +1895,7 @@
},
[CPUHP_PERF_PREPARE] = {
.name = "perf:prepare",
- .startup.single = perf_event_init_cpu,
+ .startup.single = random_and_perf_prepare_fusion,
.teardown.single = perf_event_exit_cpu,
},
[CPUHP_WORKQUEUE_PREP] = {
@@ -1568,7 +2011,7 @@
},
[CPUHP_AP_WORKQUEUE_ONLINE] = {
.name = "workqueue:online",
- .startup.single = workqueue_online_cpu,
+ .startup.single = random_and_workqueue_online_fusion,
.teardown.single = workqueue_offline_cpu,
},
[CPUHP_AP_RCUTREE_ONLINE] = {
@@ -1979,6 +2422,78 @@
}
EXPORT_SYMBOL(__cpuhp_remove_state);
+#ifdef CONFIG_HOTPLUG_SMT
+static void cpuhp_offline_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = true;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
+}
+
+static void cpuhp_online_cpu_device(unsigned int cpu)
+{
+ struct device *dev = get_cpu_device(cpu);
+
+ dev->offline = false;
+ /* Tell user space about the state change */
+ kobject_uevent(&dev->kobj, KOBJ_ONLINE);
+}
+
+int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ for_each_online_cpu(cpu) {
+ if (topology_is_primary_thread(cpu))
+ continue;
+ ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
+ if (ret)
+ break;
+ /*
+ * As this needs to hold the cpu maps lock it's impossible
+ * to call device_offline() because that ends up calling
+ * cpu_down() which takes cpu maps lock. cpu maps lock
+ * needs to be held as this might race against in kernel
+ * abusers of the hotplug machinery (thermal management).
+ *
+ * So nothing would update device:offline state. That would
+ * leave the sysfs entry stale and prevent onlining after
+ * smt control has been changed to 'off' again. This is
+ * called under the sysfs hotplug lock, so it is properly
+ * serialized against the regular offline usage.
+ */
+ cpuhp_offline_cpu_device(cpu);
+ }
+ if (!ret)
+ cpu_smt_control = ctrlval;
+ cpu_maps_update_done();
+ return ret;
+}
+
+int cpuhp_smt_enable(void)
+{
+ int cpu, ret = 0;
+
+ cpu_maps_update_begin();
+ cpu_smt_control = CPU_SMT_ENABLED;
+ for_each_present_cpu(cpu) {
+ /* Skip online CPUs and CPUs on offline nodes */
+ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+ continue;
+ ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+ if (ret)
+ break;
+ /* See comment in cpuhp_smt_disable() */
+ cpuhp_online_cpu_device(cpu);
+ }
+ cpu_maps_update_done();
+ return ret;
+}
+#endif
+
#if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU)
static ssize_t show_cpuhp_state(struct device *dev,
struct device_attribute *attr, char *buf)
@@ -2021,9 +2536,11 @@
goto out;
if (st->state < target)
- ret = do_cpu_up(dev->id, target);
- else
- ret = do_cpu_down(dev->id, target);
+ ret = cpu_up(dev->id, target);
+ else if (st->state > target)
+ ret = cpu_down(dev->id, target);
+ else if (WARN_ON(st->target != target))
+ st->target = target;
out:
unlock_device_hotplug();
return ret ? ret : count;
@@ -2133,92 +2650,9 @@
#ifdef CONFIG_HOTPLUG_SMT
-static const char *smt_states[] = {
- [CPU_SMT_ENABLED] = "on",
- [CPU_SMT_DISABLED] = "off",
- [CPU_SMT_FORCE_DISABLED] = "forceoff",
- [CPU_SMT_NOT_SUPPORTED] = "notsupported",
-};
-
static ssize_t
-show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
-{
- return snprintf(buf, PAGE_SIZE - 2, "%s\n", smt_states[cpu_smt_control]);
-}
-
-static void cpuhp_offline_cpu_device(unsigned int cpu)
-{
- struct device *dev = get_cpu_device(cpu);
-
- dev->offline = true;
- /* Tell user space about the state change */
- kobject_uevent(&dev->kobj, KOBJ_OFFLINE);
-}
-
-static void cpuhp_online_cpu_device(unsigned int cpu)
-{
- struct device *dev = get_cpu_device(cpu);
-
- dev->offline = false;
- /* Tell user space about the state change */
- kobject_uevent(&dev->kobj, KOBJ_ONLINE);
-}
-
-int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
-{
- int cpu, ret = 0;
-
- cpu_maps_update_begin();
- for_each_online_cpu(cpu) {
- if (topology_is_primary_thread(cpu))
- continue;
- ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE);
- if (ret)
- break;
- /*
- * As this needs to hold the cpu maps lock it's impossible
- * to call device_offline() because that ends up calling
- * cpu_down() which takes cpu maps lock. cpu maps lock
- * needs to be held as this might race against in kernel
- * abusers of the hotplug machinery (thermal management).
- *
- * So nothing would update device:offline state. That would
- * leave the sysfs entry stale and prevent onlining after
- * smt control has been changed to 'off' again. This is
- * called under the sysfs hotplug lock, so it is properly
- * serialized against the regular offline usage.
- */
- cpuhp_offline_cpu_device(cpu);
- }
- if (!ret)
- cpu_smt_control = ctrlval;
- cpu_maps_update_done();
- return ret;
-}
-
-int cpuhp_smt_enable(void)
-{
- int cpu, ret = 0;
-
- cpu_maps_update_begin();
- cpu_smt_control = CPU_SMT_ENABLED;
- for_each_present_cpu(cpu) {
- /* Skip online CPUs and CPUs on offline nodes */
- if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
- continue;
- ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
- if (ret)
- break;
- /* See comment in cpuhp_smt_disable() */
- cpuhp_online_cpu_device(cpu);
- }
- cpu_maps_update_done();
- return ret;
-}
-
-static ssize_t
-store_smt_control(struct device *dev, struct device_attribute *attr,
- const char *buf, size_t count)
+__store_smt_control(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
{
int ctrlval, ret;
@@ -2256,14 +2690,44 @@
unlock_device_hotplug();
return ret ? ret : count;
}
+
+#else /* !CONFIG_HOTPLUG_SMT */
+static ssize_t
+__store_smt_control(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ return -ENODEV;
+}
+#endif /* CONFIG_HOTPLUG_SMT */
+
+static const char *smt_states[] = {
+ [CPU_SMT_ENABLED] = "on",
+ [CPU_SMT_DISABLED] = "off",
+ [CPU_SMT_FORCE_DISABLED] = "forceoff",
+ [CPU_SMT_NOT_SUPPORTED] = "notsupported",
+ [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented",
+};
+
+static ssize_t
+show_smt_control(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ const char *state = smt_states[cpu_smt_control];
+
+ return snprintf(buf, PAGE_SIZE - 2, "%s\n", state);
+}
+
+static ssize_t
+store_smt_control(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ return __store_smt_control(dev, attr, buf, count);
+}
static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control);
static ssize_t
show_smt_active(struct device *dev, struct device_attribute *attr, char *buf)
{
- bool active = topology_max_smt_threads() > 1;
-
- return snprintf(buf, PAGE_SIZE - 2, "%d\n", active);
+ return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active());
}
static DEVICE_ATTR(active, 0444, show_smt_active, NULL);
@@ -2279,21 +2743,17 @@
NULL
};
-static int __init cpu_smt_state_init(void)
+static int __init cpu_smt_sysfs_init(void)
{
return sysfs_create_group(&cpu_subsys.dev_root->kobj,
&cpuhp_smt_attr_group);
}
-#else
-static inline int cpu_smt_state_init(void) { return 0; }
-#endif
-
static int __init cpuhp_sysfs_init(void)
{
int cpu, ret;
- ret = cpu_smt_state_init();
+ ret = cpu_smt_sysfs_init();
if (ret)
return ret;
@@ -2314,7 +2774,7 @@
return 0;
}
device_initcall(cpuhp_sysfs_init);
-#endif
+#endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */
/*
* cpu_bit_bitmap[] is a special, "compressed" data structure that
@@ -2361,8 +2821,8 @@
struct cpumask __cpu_active_mask __read_mostly;
EXPORT_SYMBOL(__cpu_active_mask);
-struct cpumask __cpu_isolated_mask __read_mostly;
-EXPORT_SYMBOL(__cpu_isolated_mask);
+atomic_t __num_online_cpus __read_mostly;
+EXPORT_SYMBOL(__num_online_cpus);
void init_cpu_present(const struct cpumask *src)
{
@@ -2377,6 +2837,27 @@
void init_cpu_online(const struct cpumask *src)
{
cpumask_copy(&__cpu_online_mask, src);
+}
+
+void set_cpu_online(unsigned int cpu, bool online)
+{
+ /*
+ * atomic_inc/dec() is required to handle the horrid abuse of this
+ * function by the reboot and kexec code which invoke it from
+ * IPI/NMI broadcasts when shutting down CPUs. Invocation from
+ * regular CPU hotplug is properly serialized.
+ *
+ * Note, that the fact that __num_online_cpus is of type atomic_t
+ * does not protect readers which are not serialized against
+ * concurrent hotplug operations.
+ */
+ if (online) {
+ if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask))
+ atomic_inc(&__num_online_cpus);
+ } else {
+ if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask))
+ atomic_dec(&__num_online_cpus);
+ }
}
/*
@@ -2403,7 +2884,7 @@
void __init boot_cpu_hotplug_init(void)
{
#ifdef CONFIG_SMP
- this_cpu_write(cpuhp_state.booted_once, true);
+ cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask);
#endif
this_cpu_write(cpuhp_state.state, CPUHP_ONLINE);
}
--
Gitblit v1.6.2