Merge tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Cleanups for SCHED_DEADLINE

 - Tracing updates/fixes

 - CPU Accounting fixes

 - First wave of changes to optimize the overhead of the scheduler
   build, from the fast-headers tree - including placeholder *_api.h
   headers for later header split-ups.

 - Preempt-dynamic using static_branch() for ARM64

 - Isolation housekeeping mask rework; preperatory for further changes

 - NUMA-balancing: deal with CPU-less nodes

 - NUMA-balancing: tune systems that have multiple LLC cache domains per
   node (eg. AMD)

 - Updates to RSEQ UAPI in preparation for glibc usage

 - Lots of RSEQ/selftests, for same

 - Add Suren as PSI co-maintainer

* tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (81 commits)
  sched/headers: ARM needs asm/paravirt_api_clock.h too
  sched/numa: Fix boot crash on arm64 systems
  headers/prep: Fix header to build standalone: <linux/psi.h>
  sched/headers: Only include <linux/entry-common.h> when CONFIG_GENERIC_ENTRY=y
  cgroup: Fix suspicious rcu_dereference_check() usage warning
  sched/preempt: Tell about PREEMPT_DYNAMIC on kernel headers
  sched/topology: Remove redundant variable and fix incorrect type in build_sched_domains
  sched/deadline,rt: Remove unused parameter from pick_next_[rt|dl]_entity()
  sched/deadline,rt: Remove unused functions for !CONFIG_SMP
  sched/deadline: Use __node_2_[pdl|dle]() and rb_first_cached() consistently
  sched/deadline: Merge dl_task_can_attach() and dl_cpu_busy()
  sched/deadline: Move bandwidth mgmt and reclaim functions into sched class source file
  sched/deadline: Remove unused def_dl_bandwidth
  sched/tracing: Report TASK_RTLOCK_WAIT tasks as TASK_UNINTERRUPTIBLE
  sched/tracing: Don't re-read p->state when emitting sched_switch event
  sched/rt: Plug rt_mutex_setprio() vs push_rt_task() race
  sched/cpuacct: Remove redundant RCU read lock
  sched/cpuacct: Optimize away RCU read lock
  sched/cpuacct: Fix charge percpu cpuusage
  sched/headers: Reorganize, clean up and optimize kernel/sched/sched.h dependencies
  ...

Documentation/admin-guide/sysctl/kernel.rst

@@ -609,51 +609,7 @@ be migrated to a local memory node.
 The unmapping of pages and trapping faults incur additional overhead that
 ideally is offset by improved memory locality but there is no universal
 guarantee. If the target workload is already bound to NUMA nodes then this
-feature should be disabled. Otherwise, if the system overhead from the
-feature is too high then the rate the kernel samples for NUMA hinting
-faults may be controlled by the `numa_balancing_scan_period_min_ms,
-numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms,
-numa_balancing_scan_size_mb`_, and numa_balancing_settle_count sysctls.
-
-
-numa_balancing_scan_period_min_ms, numa_balancing_scan_delay_ms, numa_balancing_scan_period_max_ms, numa_balancing_scan_size_mb
-===============================================================================================================================
-
-
-Automatic NUMA balancing scans tasks address space and unmaps pages to
-detect if pages are properly placed or if the data should be migrated to a
-memory node local to where the task is running.  Every "scan delay" the task
-scans the next "scan size" number of pages in its address space. When the
-end of the address space is reached the scanner restarts from the beginning.
-
-In combination, the "scan delay" and "scan size" determine the scan rate.
-When "scan delay" decreases, the scan rate increases.  The scan delay and
-hence the scan rate of every task is adaptive and depends on historical
-behaviour. If pages are properly placed then the scan delay increases,
-otherwise the scan delay decreases.  The "scan size" is not adaptive but
-the higher the "scan size", the higher the scan rate.
-
-Higher scan rates incur higher system overhead as page faults must be
-trapped and potentially data must be migrated. However, the higher the scan
-rate, the more quickly a tasks memory is migrated to a local node if the
-workload pattern changes and minimises performance impact due to remote
-memory accesses. These sysctls control the thresholds for scan delays and
-the number of pages scanned.
-
-``numa_balancing_scan_period_min_ms`` is the minimum time in milliseconds to
-scan a tasks virtual memory. It effectively controls the maximum scanning
-rate for each task.
-
-``numa_balancing_scan_delay_ms`` is the starting "scan delay" used for a task
-when it initially forks.
-
-``numa_balancing_scan_period_max_ms`` is the maximum time in milliseconds to
-scan a tasks virtual memory. It effectively controls the minimum scanning
-rate for each task.
-
-``numa_balancing_scan_size_mb`` is how many megabytes worth of pages are
-scanned for a given scan.
-
+feature should be disabled.
 
 oops_all_cpu_backtrace
 ======================

Documentation/scheduler/index.rst

@@ -18,6 +18,7 @@ Linux Scheduler
     sched-nice-design
     sched-rt-group
     sched-stats
+    sched-debug
 
     text_files
 

Documentation/scheduler/sched-debug.rst

@@ -0,0 +1,54 @@
+=================
+Scheduler debugfs
+=================
+
+Booting a kernel with CONFIG_SCHED_DEBUG=y will give access to
+scheduler specific debug files under /sys/kernel/debug/sched. Some of
+those files are described below.
+
+numa_balancing
+==============
+
+`numa_balancing` directory is used to hold files to control NUMA
+balancing feature.  If the system overhead from the feature is too
+high then the rate the kernel samples for NUMA hinting faults may be
+controlled by the `scan_period_min_ms, scan_delay_ms,
+scan_period_max_ms, scan_size_mb` files.
+
+
+scan_period_min_ms, scan_delay_ms, scan_period_max_ms, scan_size_mb
+-------------------------------------------------------------------
+
+Automatic NUMA balancing scans tasks address space and unmaps pages to
+detect if pages are properly placed or if the data should be migrated to a
+memory node local to where the task is running.  Every "scan delay" the task
+scans the next "scan size" number of pages in its address space. When the
+end of the address space is reached the scanner restarts from the beginning.
+
+In combination, the "scan delay" and "scan size" determine the scan rate.
+When "scan delay" decreases, the scan rate increases.  The scan delay and
+hence the scan rate of every task is adaptive and depends on historical
+behaviour. If pages are properly placed then the scan delay increases,
+otherwise the scan delay decreases.  The "scan size" is not adaptive but
+the higher the "scan size", the higher the scan rate.
+
+Higher scan rates incur higher system overhead as page faults must be
+trapped and potentially data must be migrated. However, the higher the scan
+rate, the more quickly a tasks memory is migrated to a local node if the
+workload pattern changes and minimises performance impact due to remote
+memory accesses. These files control the thresholds for scan delays and
+the number of pages scanned.
+
+``scan_period_min_ms`` is the minimum time in milliseconds to scan a
+tasks virtual memory. It effectively controls the maximum scanning
+rate for each task.
+
+``scan_delay_ms`` is the starting "scan delay" used for a task when it
+initially forks.
+
+``scan_period_max_ms`` is the maximum time in milliseconds to scan a
+tasks virtual memory. It effectively controls the minimum scanning
+rate for each task.
+
+``scan_size_mb`` is how many megabytes worth of pages are scanned for
+a given scan.

MAINTAINERS

@@ -15566,6 +15566,7 @@ F:	drivers/net/ppp/pptp.c
 
 PRESSURE STALL INFORMATION (PSI)
 M:	Johannes Weiner <[email protected]>
+M:	Suren Baghdasaryan <[email protected]>
 S:	Maintained
 F:	include/linux/psi*
 F:	kernel/sched/psi.c

arch/Kconfig

@@ -1293,12 +1293,41 @@ config HAVE_STATIC_CALL_INLINE
 
 config HAVE_PREEMPT_DYNAMIC
 	bool
+
+config HAVE_PREEMPT_DYNAMIC_CALL
+	bool
 	depends on HAVE_STATIC_CALL
-	depends on GENERIC_ENTRY
+	select HAVE_PREEMPT_DYNAMIC
+	help
+	   An architecture should select this if it can handle the preemption
+	   model being selected at boot time using static calls.
+
+	   Where an architecture selects HAVE_STATIC_CALL_INLINE, any call to a
+	   preemption function will be patched directly.
+
+	   Where an architecture does not select HAVE_STATIC_CALL_INLINE, any
+	   call to a preemption function will go through a trampoline, and the
+	   trampoline will be patched.
+
+	   It is strongly advised to support inline static call to avoid any
+	   overhead.
+
+config HAVE_PREEMPT_DYNAMIC_KEY
+	bool
+	depends on HAVE_ARCH_JUMP_LABEL && CC_HAS_ASM_GOTO
+	select HAVE_PREEMPT_DYNAMIC
 	help
-	   Select this if the architecture support boot time preempt setting
-	   on top of static calls. It is strongly advised to support inline
-	   static call to avoid any overhead.
+	   An architecture should select this if it can handle the preemption
+	   model being selected at boot time using static keys.
+
+	   Each preemption function will be given an early return based on a
+	   static key. This should have slightly lower overhead than non-inline
+	   static calls, as this effectively inlines each trampoline into the
+	   start of its callee. This may avoid redundant work, and may
+	   integrate better with CFI schemes.
+
+	   This will have greater overhead than using inline static calls as
+	   the call to the preemption function cannot be entirely elided.
 
 config ARCH_WANT_LD_ORPHAN_WARN
 	bool

arch/arm/include/asm/paravirt_api_clock.h

@@ -0,0 +1 @@
+#include <asm/paravirt.h>

arch/arm64/Kconfig

@@ -194,6 +194,7 @@ config ARM64
 	select HAVE_PERF_EVENTS
 	select HAVE_PERF_REGS
 	select HAVE_PERF_USER_STACK_DUMP
+	select HAVE_PREEMPT_DYNAMIC_KEY
 	select HAVE_REGS_AND_STACK_ACCESS_API
 	select HAVE_POSIX_CPU_TIMERS_TASK_WORK
 	select HAVE_FUNCTION_ARG_ACCESS_API

arch/arm64/include/asm/paravirt_api_clock.h

@@ -0,0 +1 @@
+#include <asm/paravirt.h>

arch/arm64/include/asm/preempt.h

@@ -2,6 +2,7 @@
 #ifndef __ASM_PREEMPT_H
 #define __ASM_PREEMPT_H
 
+#include <linux/jump_label.h>
 #include <linux/thread_info.h>
 
 #define PREEMPT_NEED_RESCHED	BIT(32)
@@ -80,10 +81,24 @@ static inline bool should_resched(int preempt_offset)
 }
 
 #ifdef CONFIG_PREEMPTION
+
 void preempt_schedule(void);
-#define __preempt_schedule() preempt_schedule()
 void preempt_schedule_notrace(void);
-#define __preempt_schedule_notrace() preempt_schedule_notrace()
+
+#ifdef CONFIG_PREEMPT_DYNAMIC
+
+DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+void dynamic_preempt_schedule(void);
+#define __preempt_schedule()		dynamic_preempt_schedule()
+void dynamic_preempt_schedule_notrace(void);
+#define __preempt_schedule_notrace()	dynamic_preempt_schedule_notrace()
+
+#else /* CONFIG_PREEMPT_DYNAMIC */
+
+#define __preempt_schedule()		preempt_schedule()
+#define __preempt_schedule_notrace()	preempt_schedule_notrace()
+
+#endif /* CONFIG_PREEMPT_DYNAMIC */
 #endif /* CONFIG_PREEMPTION */
 
 #endif /* __ASM_PREEMPT_H */

arch/arm64/kernel/entry-common.c

@@ -223,9 +223,26 @@ static void noinstr arm64_exit_el1_dbg(struct pt_regs *regs)
 		lockdep_hardirqs_on(CALLER_ADDR0);
 }
 
+#ifdef CONFIG_PREEMPT_DYNAMIC
+DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+#define need_irq_preemption() \
+	(static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
+#else
+#define need_irq_preemption()	(IS_ENABLED(CONFIG_PREEMPTION))
+#endif
+
 static void __sched arm64_preempt_schedule_irq(void)
 {
-	lockdep_assert_irqs_disabled();
+	if (!need_irq_preemption())
+		return;
+
+	/*
+	 * Note: thread_info::preempt_count includes both thread_info::count
+	 * and thread_info::need_resched, and is not equivalent to
+	 * preempt_count().
+	 */
+	if (READ_ONCE(current_thread_info()->preempt_count) != 0)
+		return;
 
 	/*
 	 * DAIF.DA are cleared at the start of IRQ/FIQ handling, and when GIC
@@ -441,14 +458,7 @@ static __always_inline void __el1_irq(struct pt_regs *regs,
 	do_interrupt_handler(regs, handler);
 	irq_exit_rcu();
 
-	/*
-	 * Note: thread_info::preempt_count includes both thread_info::count
-	 * and thread_info::need_resched, and is not equivalent to
-	 * preempt_count().
-	 */
-	if (IS_ENABLED(CONFIG_PREEMPTION) &&
-	    READ_ONCE(current_thread_info()->preempt_count) == 0)
-		arm64_preempt_schedule_irq();
+	arm64_preempt_schedule_irq();
 
 	exit_to_kernel_mode(regs);
 }

arch/x86/Kconfig

@@ -248,7 +248,7 @@ config X86
 	select HAVE_STACK_VALIDATION		if X86_64
 	select HAVE_STATIC_CALL
 	select HAVE_STATIC_CALL_INLINE		if HAVE_STACK_VALIDATION
-	select HAVE_PREEMPT_DYNAMIC
+	select HAVE_PREEMPT_DYNAMIC_CALL
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_UNSTABLE_SCHED_CLOCK

arch/x86/include/asm/paravirt_api_clock.h

@@ -0,0 +1 @@
+#include <asm/paravirt.h>

arch/x86/include/asm/preempt.h

@@ -108,24 +108,26 @@ static __always_inline bool should_resched(int preempt_offset)
 extern asmlinkage void preempt_schedule(void);
 extern asmlinkage void preempt_schedule_thunk(void);
 
-#define __preempt_schedule_func preempt_schedule_thunk
+#define preempt_schedule_dynamic_enabled	preempt_schedule_thunk
+#define preempt_schedule_dynamic_disabled	NULL
 
 extern asmlinkage void preempt_schedule_notrace(void);
 extern asmlinkage void preempt_schedule_notrace_thunk(void);
 
-#define __preempt_schedule_notrace_func preempt_schedule_notrace_thunk
+#define preempt_schedule_notrace_dynamic_enabled	preempt_schedule_notrace_thunk
+#define preempt_schedule_notrace_dynamic_disabled	NULL
 
 #ifdef CONFIG_PREEMPT_DYNAMIC
 
-DECLARE_STATIC_CALL(preempt_schedule, __preempt_schedule_func);
+DECLARE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled);
 
 #define __preempt_schedule() \
 do { \
 	__STATIC_CALL_MOD_ADDRESSABLE(preempt_schedule); \
 	asm volatile ("call " STATIC_CALL_TRAMP_STR(preempt_schedule) : ASM_CALL_CONSTRAINT); \
 } while (0)
 
-DECLARE_STATIC_CALL(preempt_schedule_notrace, __preempt_schedule_notrace_func);
+DECLARE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled);
 
 #define __preempt_schedule_notrace() \
 do { \

arch/x86/kernel/cpu/aperfmperf.c

@@ -91,7 +91,7 @@ unsigned int aperfmperf_get_khz(int cpu)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
-	if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+	if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
 		return 0;
 
 	if (rcu_is_idle_cpu(cpu))
@@ -114,7 +114,7 @@ void arch_freq_prepare_all(void)
 		return;
 
 	for_each_online_cpu(cpu) {
-		if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+		if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
 			continue;
 		if (rcu_is_idle_cpu(cpu))
 			continue; /* Idle CPUs are completely uninteresting. */
@@ -136,7 +136,7 @@ unsigned int arch_freq_get_on_cpu(int cpu)
 	if (!boot_cpu_has(X86_FEATURE_APERFMPERF))
 		return 0;
 
-	if (!housekeeping_cpu(cpu, HK_FLAG_MISC))
+	if (!housekeeping_cpu(cpu, HK_TYPE_MISC))
 		return 0;
 
 	if (aperfmperf_snapshot_cpu(cpu, ktime_get(), true))

arch/x86/kvm/x86.c

@@ -8853,7 +8853,7 @@ int kvm_arch_init(void *opaque)
 	}
 
 	if (pi_inject_timer == -1)
-		pi_inject_timer = housekeeping_enabled(HK_FLAG_TIMER);
+		pi_inject_timer = housekeeping_enabled(HK_TYPE_TIMER);
 #ifdef CONFIG_X86_64
 	pvclock_gtod_register_notifier(&pvclock_gtod_notifier);
 

drivers/base/cpu.c

@@ -275,7 +275,7 @@ static ssize_t print_cpus_isolated(struct device *dev,
 		return -ENOMEM;
 
 	cpumask_andnot(isolated, cpu_possible_mask,
-		       housekeeping_cpumask(HK_FLAG_DOMAIN));
+		       housekeeping_cpumask(HK_TYPE_DOMAIN));
 	len = sysfs_emit(buf, "%*pbl\n", cpumask_pr_args(isolated));
 
 	free_cpumask_var(isolated);

drivers/pci/pci-driver.c

@@ -350,7 +350,6 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 			  const struct pci_device_id *id)
 {
 	int error, node, cpu;
-	int hk_flags = HK_FLAG_DOMAIN | HK_FLAG_WQ;
 	struct drv_dev_and_id ddi = { drv, dev, id };
 
 	/*
@@ -368,17 +367,29 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 	 * device is probed from work_on_cpu() of the Physical device.
 	 */
 	if (node < 0 || node >= MAX_NUMNODES || !node_online(node) ||
-	    pci_physfn_is_probed(dev))
+	    pci_physfn_is_probed(dev)) {
 		cpu = nr_cpu_ids;
-	else
+	} else {
+		cpumask_var_t wq_domain_mask;
+
+		if (!zalloc_cpumask_var(&wq_domain_mask, GFP_KERNEL)) {
+			error = -ENOMEM;
+			goto out;
+		}
+		cpumask_and(wq_domain_mask,
+			    housekeeping_cpumask(HK_TYPE_WQ),
+			    housekeeping_cpumask(HK_TYPE_DOMAIN));
+
 		cpu = cpumask_any_and(cpumask_of_node(node),
-				      housekeeping_cpumask(hk_flags));
+				      wq_domain_mask);
+		free_cpumask_var(wq_domain_mask);
+	}
 
 	if (cpu < nr_cpu_ids)
 		error = work_on_cpu(cpu, local_pci_probe, &ddi);
 	else
 		error = local_pci_probe(&ddi);
-
+out:
 	dev->is_probed = 0;
 	cpu_hotplug_enable();
 	return error;