Merge tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler udpates from Ingo Molnar:

 - Changes to core scheduling facilities:

    - Add "Core Scheduling" via CONFIG_SCHED_CORE=y, which enables
      coordinated scheduling across SMT siblings. This is a much
      requested feature for cloud computing platforms, to allow the
      flexible utilization of SMT siblings, without exposing untrusted
      domains to information leaks & side channels, plus to ensure more
      deterministic computing performance on SMT systems used by
      heterogenous workloads.

      There are new prctls to set core scheduling groups, which allows
      more flexible management of workloads that can share siblings.

    - Fix task->state access anti-patterns that may result in missed
      wakeups and rename it to ->__state in the process to catch new
      abuses.

 - Load-balancing changes:

    - Tweak newidle_balance for fair-sched, to improve 'memcache'-like
      workloads.

    - "Age" (decay) average idle time, to better track & improve
      workloads such as 'tbench'.

    - Fix & improve energy-aware (EAS) balancing logic & metrics.

    - Fix & improve the uclamp metrics.

    - Fix task migration (taskset) corner case on !CONFIG_CPUSET.

    - Fix RT and deadline utilization tracking across policy changes

    - Introduce a "burstable" CFS controller via cgroups, which allows
      bursty CPU-bound workloads to borrow a bit against their future
      quota to improve overall latencies & batching. Can be tweaked via
      /sys/fs/cgroup/cpu/<X>/cpu.cfs_burst_us.

    - Rework assymetric topology/capacity detection & handling.

 - Scheduler statistics & tooling:

    - Disable delayacct by default, but add a sysctl to enable it at
      runtime if tooling needs it. Use static keys and other
      optimizations to make it more palatable.

    - Use sched_clock() in delayacct, instead of ktime_get_ns().

 - Misc cleanups and fixes.

* tag 'sched-core-2021-06-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (72 commits)
  sched/doc: Update the CPU capacity asymmetry bits
  sched/topology: Rework CPU capacity asymmetry detection
  sched/core: Introduce SD_ASYM_CPUCAPACITY_FULL sched_domain flag
  psi: Fix race between psi_trigger_create/destroy
  sched/fair: Introduce the burstable CFS controller
  sched/uclamp: Fix uclamp_tg_restrict()
  sched/rt: Fix Deadline utilization tracking during policy change
  sched/rt: Fix RT utilization tracking during policy change
  sched: Change task_struct::state
  sched,arch: Remove unused TASK_STATE offsets
  sched,timer: Use __set_current_state()
  sched: Add get_current_state()
  sched,perf,kvm: Fix preemption condition
  sched: Introduce task_is_running()
  sched: Unbreak wakeups
  sched/fair: Age the average idle time
  sched/cpufreq: Consider reduced CPU capacity in energy calculation
  sched/fair: Take thermal pressure into account while estimating energy
  thermal/cpufreq_cooling: Update offline CPUs per-cpu thermal_pressure
  sched/fair: Return early from update_tg_cfs_load() if delta == 0
  ...

6 files changed, 15 insertions, 23 deletions

diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index c3aa8d6ccee3..2e5670446991 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -117,7 +117,7 @@ struct menu_device {
 	int		interval_ptr;
 };
 
-static inline int which_bucket(u64 duration_ns, unsigned long nr_iowaiters)
+static inline int which_bucket(u64 duration_ns, unsigned int nr_iowaiters)
 {
 	int bucket = 0;
 
@@ -150,7 +150,7 @@ static inline int which_bucket(u64 duration_ns, unsigned long nr_iowaiters)
  * to be, the higher this multiplier, and thus the higher
  * the barrier to go to an expensive C state.
  */
-static inline int performance_multiplier(unsigned long nr_iowaiters)
+static inline int performance_multiplier(unsigned int nr_iowaiters)
 {
 	/* for IO wait tasks (per cpu!) we add 10x each */
 	return 1 + 10 * nr_iowaiters;
@@ -270,7 +270,7 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 	unsigned int predicted_us;
 	u64 predicted_ns;
 	u64 interactivity_req;
-	unsigned long nr_iowaiters;
+	unsigned int nr_iowaiters;
 	ktime_t delta, delta_tick;
 	int i, idx;
 
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index ca2aedd8ee7d..190e714cb565 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -2328,7 +2328,7 @@ static bool md_in_flight_bios(struct mapped_device *md)
 	return sum != 0;
 }
 
-static int dm_wait_for_bios_completion(struct mapped_device *md, long task_state)
+static int dm_wait_for_bios_completion(struct mapped_device *md, unsigned int task_state)
 {
 	int r = 0;
 	DEFINE_WAIT(wait);
@@ -2351,7 +2351,7 @@ static int dm_wait_for_bios_completion(struct mapped_device *md, long task_state
 	return r;
 }
 
-static int dm_wait_for_completion(struct mapped_device *md, long task_state)
+static int dm_wait_for_completion(struct mapped_device *md, unsigned int task_state)
 {
 	int r = 0;
 
@@ -2478,7 +2478,7 @@ static void unlock_fs(struct mapped_device *md)
  * are being added to md->deferred list.
  */
 static int __dm_suspend(struct mapped_device *md, struct dm_table *map,
-			unsigned suspend_flags, long task_state,
+			unsigned suspend_flags, unsigned int task_state,
 			int dmf_suspended_flag)
 {
 	bool do_lockfs = suspend_flags & DM_SUSPEND_LOCKFS_FLAG;
diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c
index ab9b02574a15..0a6b8112b535 100644
--- a/drivers/net/ethernet/qualcomm/qca_spi.c
+++ b/drivers/net/ethernet/qualcomm/qca_spi.c
@@ -653,8 +653,7 @@ qcaspi_intr_handler(int irq, void *data)
 	struct qcaspi *qca = data;
 
 	qca->intr_req++;
-	if (qca->spi_thread &&
-	    qca->spi_thread->state != TASK_RUNNING)
+	if (qca->spi_thread)
 		wake_up_process(qca->spi_thread);
 
 	return IRQ_HANDLED;
@@ -777,8 +776,7 @@ qcaspi_netdev_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	netif_trans_update(dev);
 
-	if (qca->spi_thread &&
-	    qca->spi_thread->state != TASK_RUNNING)
+	if (qca->spi_thread)
 		wake_up_process(qca->spi_thread);
 
 	return NETDEV_TX_OK;
diff --git a/drivers/thermal/cpufreq_cooling.c b/drivers/thermal/cpufreq_cooling.c
index eeb4e4b76c0b..43b1ae8a7789 100644
--- a/drivers/thermal/cpufreq_cooling.c
+++ b/drivers/thermal/cpufreq_cooling.c
@@ -478,7 +478,7 @@ static int cpufreq_set_cur_state(struct thermal_cooling_device *cdev,
 	ret = freq_qos_update_request(&cpufreq_cdev->qos_req, frequency);
 	if (ret >= 0) {
 		cpufreq_cdev->cpufreq_state = state;
-		cpus = cpufreq_cdev->policy->cpus;
+		cpus = cpufreq_cdev->policy->related_cpus;
 		max_capacity = arch_scale_cpu_capacity(cpumask_first(cpus));
 		capacity = frequency * max_capacity;
 		capacity /= cpufreq_cdev->policy->cpuinfo.max_freq;
diff --git a/drivers/usb/gadget/udc/max3420_udc.c b/drivers/usb/gadget/udc/max3420_udc.c
index 35179543c327..34f4db554977 100644
--- a/drivers/usb/gadget/udc/max3420_udc.c
+++ b/drivers/usb/gadget/udc/max3420_udc.c
@@ -509,8 +509,7 @@ static irqreturn_t max3420_vbus_handler(int irq, void *dev_id)
 			     ? USB_STATE_POWERED : USB_STATE_NOTATTACHED);
 	spin_unlock_irqrestore(&udc->lock, flags);
 
-	if (udc->thread_task &&
-	    udc->thread_task->state != TASK_RUNNING)
+	if (udc->thread_task)
 		wake_up_process(udc->thread_task);
 
 	return IRQ_HANDLED;
@@ -529,8 +528,7 @@ static irqreturn_t max3420_irq_handler(int irq, void *dev_id)
 	}
 	spin_unlock_irqrestore(&udc->lock, flags);
 
-	if (udc->thread_task &&
-	    udc->thread_task->state != TASK_RUNNING)
+	if (udc->thread_task)
 		wake_up_process(udc->thread_task);
 
 	return IRQ_HANDLED;
@@ -1093,8 +1091,7 @@ static int max3420_wakeup(struct usb_gadget *gadget)
 
 	spin_unlock_irqrestore(&udc->lock, flags);
 
-	if (udc->thread_task &&
-	    udc->thread_task->state != TASK_RUNNING)
+	if (udc->thread_task)
 		wake_up_process(udc->thread_task);
 	return ret;
 }
@@ -1117,8 +1114,7 @@ static int max3420_udc_start(struct usb_gadget *gadget,
 	udc->todo |= UDC_START;
 	spin_unlock_irqrestore(&udc->lock, flags);
 
-	if (udc->thread_task &&
-	    udc->thread_task->state != TASK_RUNNING)
+	if (udc->thread_task)
 		wake_up_process(udc->thread_task);
 
 	return 0;
@@ -1137,8 +1133,7 @@ static int max3420_udc_stop(struct usb_gadget *gadget)
 	udc->todo |= UDC_START;
 	spin_unlock_irqrestore(&udc->lock, flags);
 
-	if (udc->thread_task &&
-	    udc->thread_task->state != TASK_RUNNING)
+	if (udc->thread_task)
 		wake_up_process(udc->thread_task);
 
 	return 0;
diff --git a/drivers/usb/host/max3421-hcd.c b/drivers/usb/host/max3421-hcd.c
index afd9174d83b1..e7a8e0609853 100644
--- a/drivers/usb/host/max3421-hcd.c
+++ b/drivers/usb/host/max3421-hcd.c
@@ -1169,8 +1169,7 @@ max3421_irq_handler(int irq, void *dev_id)
 	struct spi_device *spi = to_spi_device(hcd->self.controller);
 	struct max3421_hcd *max3421_hcd = hcd_to_max3421(hcd);
 
-	if (max3421_hcd->spi_thread &&
-	    max3421_hcd->spi_thread->state != TASK_RUNNING)
+	if (max3421_hcd->spi_thread)
 		wake_up_process(max3421_hcd->spi_thread);
 	if (!test_and_set_bit(ENABLE_IRQ, &max3421_hcd->todo))
 		disable_irq_nosync(spi->irq);