Merge tag 'sched-core-2023-06-27' of git://git.kernel.org/pub/scm/lin…

…ux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Scheduler SMP load-balancer improvements:

   - Avoid unnecessary migrations within SMT domains on hybrid systems.

     Problem:

        On hybrid CPU systems, (processors with a mixture of
        higher-frequency SMT cores and lower-frequency non-SMT cores),
        under the old code lower-priority CPUs pulled tasks from the
        higher-priority cores if more than one SMT sibling was busy -
        resulting in many unnecessary task migrations.

     Solution:

        The new code improves the load balancer to recognize SMT cores
        with more than one busy sibling and allows lower-priority CPUs
        to pull tasks, which avoids superfluous migrations and lets
        lower-priority cores inspect all SMT siblings for the busiest
        queue.

   - Implement the 'runnable boosting' feature in the EAS balancer:
     consider CPU contention in frequency, EAS max util & load-balance
     busiest CPU selection.

     This improves CPU utilization for certain workloads, while leaves
     other key workloads unchanged.

  Scheduler infrastructure improvements:

   - Rewrite the scheduler topology setup code by consolidating it into
     the build_sched_topology() helper function and building it
     dynamically on the fly.

   - Resolve the local_clock() vs. noinstr complications by rewriting
     the code: provide separate sched_clock_noinstr() and
     local_clock_noinstr() functions to be used in instrumentation code,
     and make sure it is all instrumentation-safe.

  Fixes:

   - Fix a kthread_park() race with wait_woken()

   - Fix misc wait_task_inactive() bugs unearthed by the -rt merge:
       - Fix UP PREEMPT bug by unifying the SMP and UP implementations
       - Fix task_struct::saved_state handling

   - Fix various rq clock update bugs, unearthed by turning on the rq
     clock debugging code.

   - Fix the PSI WINDOW_MIN_US trigger limit, which was easy to trigger
     by creating enough cgroups, by removing the warnign and restricting
     window size triggers to PSI file write-permission or
     CAP_SYS_RESOURCE.

   - Propagate SMT flags in the topology when removing degenerate domain

   - Fix grub_reclaim() calculation bug in the deadline scheduler code

   - Avoid resetting the min update period when it is unnecessary, in
     psi_trigger_destroy().

   - Don't balance a task to its current running CPU in load_balance(),
     which was possible on certain NUMA topologies with overlapping
     groups.

   - Fix the sched-debug printing of rq->nr_uninterruptible

  Cleanups:

   - Address various -Wmissing-prototype warnings, as a preparation to
     (maybe) enable this warning in the future.

   - Remove unused code

   - Mark more functions __init

   - Fix shadow-variable warnings"

* tag 'sched-core-2023-06-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (50 commits)
  sched/core: Avoid multiple calling update_rq_clock() in __cfsb_csd_unthrottle()
  sched/core: Avoid double calling update_rq_clock() in __balance_push_cpu_stop()
  sched/core: Fixed missing rq clock update before calling set_rq_offline()
  sched/deadline: Update GRUB description in the documentation
  sched/deadline: Fix bandwidth reclaim equation in GRUB
  sched/wait: Fix a kthread_park race with wait_woken()
  sched/topology: Mark set_sched_topology() __init
  sched/fair: Rename variable cpu_util eff_util
  arm64/arch_timer: Fix MMIO byteswap
  sched/fair, cpufreq: Introduce 'runnable boosting'
  sched/fair: Refactor CPU utilization functions
  cpuidle: Use local_clock_noinstr()
  sched/clock: Provide local_clock_noinstr()
  x86/tsc: Provide sched_clock_noinstr()
  clocksource: hyper-v: Provide noinstr sched_clock()
  clocksource: hyper-v: Adjust hv_read_tsc_page_tsc() to avoid special casing U64_MAX
  x86/vdso: Fix gettimeofday masking
  math64: Always inline u128 version of mul_u64_u64_shr()
  s390/time: Provide sched_clock_noinstr()
  loongarch: Provide noinstr sched_clock_read()
  ...

Documentation/scheduler/sched-deadline.rst

@@ -203,12 +203,15 @@ Deadline Task Scheduling
   - Total bandwidth (this_bw): this is the sum of all tasks "belonging" to the
     runqueue, including the tasks in Inactive state.
 
+  - Maximum usable bandwidth (max_bw): This is the maximum bandwidth usable by
+    deadline tasks and is currently set to the RT capacity.
+
 
  The algorithm reclaims the bandwidth of the tasks in Inactive state.
  It does so by decrementing the runtime of the executing task Ti at a pace equal
  to
 
-           dq = -max{ Ui / Umax, (1 - Uinact - Uextra) } dt
+           dq = -(max{ Ui, (Umax - Uinact - Uextra) } / Umax) dt
 
  where:
 

arch/arm64/include/asm/arch_timer.h

@@ -88,13 +88,7 @@ static inline notrace u64 arch_timer_read_cntvct_el0(void)
 
 #define arch_timer_reg_read_stable(reg)					\
 	({								\
-		u64 _val;						\
-									\
-		preempt_disable_notrace();				\
-		_val = erratum_handler(read_ ## reg)();			\
-		preempt_enable_notrace();				\
-									\
-		_val;							\
+		erratum_handler(read_ ## reg)();			\
 	})
 
 /*

arch/arm64/include/asm/io.h

@@ -22,13 +22,13 @@
  * Generic IO read/write.  These perform native-endian accesses.
  */
 #define __raw_writeb __raw_writeb
-static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
+static __always_inline void __raw_writeb(u8 val, volatile void __iomem *addr)
 {
 	asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_writew __raw_writew
-static inline void __raw_writew(u16 val, volatile void __iomem *addr)
+static __always_inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
 	asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr));
 }
@@ -40,13 +40,13 @@ static __always_inline void __raw_writel(u32 val, volatile void __iomem *addr)
 }
 
 #define __raw_writeq __raw_writeq
-static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
+static __always_inline void __raw_writeq(u64 val, volatile void __iomem *addr)
 {
 	asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_readb __raw_readb
-static inline u8 __raw_readb(const volatile void __iomem *addr)
+static __always_inline u8 __raw_readb(const volatile void __iomem *addr)
 {
 	u8 val;
 	asm volatile(ALTERNATIVE("ldrb %w0, [%1]",
@@ -57,7 +57,7 @@ static inline u8 __raw_readb(const volatile void __iomem *addr)
 }
 
 #define __raw_readw __raw_readw
-static inline u16 __raw_readw(const volatile void __iomem *addr)
+static __always_inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
 
@@ -80,7 +80,7 @@ static __always_inline u32 __raw_readl(const volatile void __iomem *addr)
 }
 
 #define __raw_readq __raw_readq
-static inline u64 __raw_readq(const volatile void __iomem *addr)
+static __always_inline u64 __raw_readq(const volatile void __iomem *addr)
 {
 	u64 val;
 	asm volatile(ALTERNATIVE("ldr %0, [%1]",

arch/loongarch/include/asm/loongarch.h

@@ -1167,7 +1167,7 @@ static __always_inline void iocsr_write64(u64 val, u32 reg)
 
 #ifndef __ASSEMBLY__
 
-static inline u64 drdtime(void)
+static __always_inline u64 drdtime(void)
 {
 	int rID = 0;
 	u64 val = 0;

arch/loongarch/kernel/time.c

@@ -190,9 +190,9 @@ static u64 read_const_counter(struct clocksource *clk)
 	return drdtime();
 }
 
-static u64 native_sched_clock(void)
+static noinstr u64 sched_clock_read(void)
 {
-	return read_const_counter(NULL);
+	return drdtime();
 }
 
 static struct clocksource clocksource_const = {
@@ -211,7 +211,7 @@ int __init constant_clocksource_init(void)
 
 	res = clocksource_register_hz(&clocksource_const, freq);
 
-	sched_clock_register(native_sched_clock, 64, freq);
+	sched_clock_register(sched_clock_read, 64, freq);
 
 	pr_info("Constant clock source device register\n");
 

arch/s390/include/asm/timex.h

@@ -63,7 +63,7 @@ static inline int store_tod_clock_ext_cc(union tod_clock *clk)
 	return cc;
 }
 
-static inline void store_tod_clock_ext(union tod_clock *tod)
+static __always_inline void store_tod_clock_ext(union tod_clock *tod)
 {
 	asm volatile("stcke %0" : "=Q" (*tod) : : "cc");
 }
@@ -177,7 +177,7 @@ static inline void local_tick_enable(unsigned long comp)
 
 typedef unsigned long cycles_t;
 
-static inline unsigned long get_tod_clock(void)
+static __always_inline unsigned long get_tod_clock(void)
 {
 	union tod_clock clk;
 
@@ -204,6 +204,11 @@ void init_cpu_timer(void);
 
 extern union tod_clock tod_clock_base;
 
+static __always_inline unsigned long __get_tod_clock_monotonic(void)
+{
+	return get_tod_clock() - tod_clock_base.tod;
+}
+
 /**
  * get_clock_monotonic - returns current time in clock rate units
  *
@@ -216,7 +221,7 @@ static inline unsigned long get_tod_clock_monotonic(void)
 	unsigned long tod;
 
 	preempt_disable_notrace();
-	tod = get_tod_clock() - tod_clock_base.tod;
+	tod = __get_tod_clock_monotonic();
 	preempt_enable_notrace();
 	return tod;
 }
@@ -240,7 +245,7 @@ static inline unsigned long get_tod_clock_monotonic(void)
  * -> ns = (th * 125) + ((tl * 125) >> 9);
  *
  */
-static inline unsigned long tod_to_ns(unsigned long todval)
+static __always_inline unsigned long tod_to_ns(unsigned long todval)
 {
 	return ((todval >> 9) * 125) + (((todval & 0x1ff) * 125) >> 9);
 }

arch/s390/kernel/time.c

@@ -102,6 +102,11 @@ void __init time_early_init(void)
 			((long) qui.old_leap * 4096000000L);
 }
 
+unsigned long long noinstr sched_clock_noinstr(void)
+{
+	return tod_to_ns(__get_tod_clock_monotonic());
+}
+
 /*
  * Scheduler clock - returns current time in nanosec units.
  */

arch/x86/include/asm/mshyperv.h

@@ -257,6 +257,11 @@ void hv_set_register(unsigned int reg, u64 value);
 u64 hv_get_non_nested_register(unsigned int reg);
 void hv_set_non_nested_register(unsigned int reg, u64 value);
 
+static __always_inline u64 hv_raw_get_register(unsigned int reg)
+{
+	return __rdmsr(reg);
+}
+
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}

arch/x86/include/asm/vdso/gettimeofday.h

@@ -231,22 +231,27 @@ static u64 vread_pvclock(void)
 		ret = __pvclock_read_cycles(pvti, rdtsc_ordered());
 	} while (pvclock_read_retry(pvti, version));
 
-	return ret;
+	return ret & S64_MAX;
 }
 #endif
 
 #ifdef CONFIG_HYPERV_TIMER
 static u64 vread_hvclock(void)
 {
-	return hv_read_tsc_page(&hvclock_page);
+	u64 tsc, time;
+
+	if (hv_read_tsc_page_tsc(&hvclock_page, &tsc, &time))
+		return time & S64_MAX;
+
+	return U64_MAX;
 }
 #endif
 
 static inline u64 __arch_get_hw_counter(s32 clock_mode,
 					const struct vdso_data *vd)
 {
 	if (likely(clock_mode == VDSO_CLOCKMODE_TSC))
-		return (u64)rdtsc_ordered();
+		return (u64)rdtsc_ordered() & S64_MAX;
 	/*
 	 * For any memory-mapped vclock type, we need to make sure that gcc
 	 * doesn't cleverly hoist a load before the mode check.  Otherwise we
@@ -284,6 +289,9 @@ static inline bool arch_vdso_clocksource_ok(const struct vdso_data *vd)
  * which can be invalidated asynchronously and indicate invalidation by
  * returning U64_MAX, which can be effectively tested by checking for a
  * negative value after casting it to s64.
+ *
+ * This effectively forces a S64_MAX mask on the calculations, unlike the
+ * U64_MAX mask normally used by x86 clocksources.
  */
 static inline bool arch_vdso_cycles_ok(u64 cycles)
 {
@@ -303,18 +311,29 @@ static inline bool arch_vdso_cycles_ok(u64 cycles)
  * @last. If not then use @last, which is the base time of the current
  * conversion period.
  *
- * This variant also removes the masking of the subtraction because the
- * clocksource mask of all VDSO capable clocksources on x86 is U64_MAX
- * which would result in a pointless operation. The compiler cannot
- * optimize it away as the mask comes from the vdso data and is not compile
- * time constant.
+ * This variant also uses a custom mask because while the clocksource mask of
+ * all the VDSO capable clocksources on x86 is U64_MAX, the above code uses
+ * U64_MASK as an exception value, additionally arch_vdso_cycles_ok() above
+ * declares everything with the MSB/Sign-bit set as invalid. Therefore the
+ * effective mask is S64_MAX.
  */
 static __always_inline
 u64 vdso_calc_delta(u64 cycles, u64 last, u64 mask, u32 mult)
 {
-	if (cycles > last)
-		return (cycles - last) * mult;
-	return 0;
+	/*
+	 * Due to the MSB/Sign-bit being used as invald marker (see
+	 * arch_vdso_cycles_valid() above), the effective mask is S64_MAX.
+	 */
+	u64 delta = (cycles - last) & S64_MAX;
+
+	/*
+	 * Due to the above mentioned TSC wobbles, filter out negative motion.
+	 * Per the above masking, the effective sign bit is now bit 62.
+	 */
+	if (unlikely(delta & (1ULL << 62)))
+		return 0;
+
+	return delta * mult;
 }
 #define vdso_calc_delta vdso_calc_delta
 

arch/x86/kernel/itmt.c

@@ -165,32 +165,19 @@ int arch_asym_cpu_priority(int cpu)
 
 /**
  * sched_set_itmt_core_prio() - Set CPU priority based on ITMT
- * @prio:	Priority of cpu core
- * @core_cpu:	The cpu number associated with the core
+ * @prio:	Priority of @cpu
+ * @cpu:	The CPU number
  *
  * The pstate driver will find out the max boost frequency
  * and call this function to set a priority proportional
- * to the max boost frequency. CPU with higher boost
+ * to the max boost frequency. CPUs with higher boost
  * frequency will receive higher priority.
  *
  * No need to rebuild sched domain after updating
  * the CPU priorities. The sched domains have no
  * dependency on CPU priorities.
  */
-void sched_set_itmt_core_prio(int prio, int core_cpu)
+void sched_set_itmt_core_prio(int prio, int cpu)
 {
-	int cpu, i = 1;
-
-	for_each_cpu(cpu, topology_sibling_cpumask(core_cpu)) {
-		int smt_prio;
-
-		/*
-		 * Ensure that the siblings are moved to the end
-		 * of the priority chain and only used when
-		 * all other high priority cpus are out of capacity.
-		 */
-		smt_prio = prio * smp_num_siblings / (i * i);
-		per_cpu(sched_core_priority, cpu) = smt_prio;
-		i++;
-	}
+	per_cpu(sched_core_priority, cpu) = prio;
 }

arch/x86/kernel/kvmclock.c

@@ -71,7 +71,7 @@ static int kvm_set_wallclock(const struct timespec64 *now)
 	return -ENODEV;
 }
 
-static noinstr u64 kvm_clock_read(void)
+static u64 kvm_clock_read(void)
 {
 	u64 ret;
 
@@ -88,7 +88,7 @@ static u64 kvm_clock_get_cycles(struct clocksource *cs)
 
 static noinstr u64 kvm_sched_clock_read(void)
 {
-	return kvm_clock_read() - kvm_sched_clock_offset;
+	return pvclock_clocksource_read_nowd(this_cpu_pvti()) - kvm_sched_clock_offset;
 }
 
 static inline void kvm_sched_clock_init(bool stable)