Commit adb35e8d authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip 

Pull scheduler updates from Thomas Gleixner:

 - migrate_disable/enable() support which originates from the RT tree
   and is now a prerequisite for the new preemptible kmap_local() API
   which aims to replace kmap_atomic().

 - A fair amount of topology and NUMA related improvements

 - Improvements for the frequency invariant calculations

 - Enhanced robustness for the global CPU priority tracking and decision
   making

 - The usual small fixes and enhancements all over the place

* tag 'sched-core-2020-12-14' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (61 commits)
  sched/fair: Trivial correction of the newidle_balance() comment
  sched/fair: Clear SMT siblings after determining the core is not idle
  sched: Fix kernel-doc markup
  x86: Print ratio freq_max/freq_base used in frequency invariance calculations
  x86, sched: Use midpoint of max_boost and max_P for frequency invariance on AMD EPYC
  x86, sched: Calculate frequency invariance for AMD systems
  irq_work: Optimize irq_work_single()
  smp: Cleanup smp_call_function*()
  irq_work: Cleanup
  sched: Limit the amount of NUMA imbalance that can exist at fork time
  sched/numa: Allow a floating imbalance between NUMA nodes
  sched: Avoid unnecessary calculation of load imbalance at clone time
  sched/numa: Rename nr_running and break out the magic number
  sched: Make migrate_disable/enable() independent of RT
  sched/topology: Condition EAS enablement on FIE support
  arm64: Rebuild sched domains on invariance status changes
  sched/topology,schedutil: Wrap sched domains rebuild
  sched/uclamp: Allow to reset a task uclamp constraint value
  sched/core: Fix typos in comments
  Documentation: scheduler: fix information on arch SD flags, sched_domain and sched_debug
  ...
parents 533369b1 5b78f2dc

Documentation/scheduler/sched-domains.rst

+11 −15
Original line number Diff line number Diff line
@@ -65,21 +65,17 @@ of the SMP domain will span the entire machine, with each group having the 
cpumask of a node. Or, you could do multi-level NUMA or Opteron, for example,

might have just one domain covering its one NUMA level.



The implementor should read comments in include/linux/sched.h:

struct sched_domain fields, SD_FLAG_*, SD_*_INIT to get an idea of

the specifics and what to tune.

The implementor should read comments in include/linux/sched/sd_flags.h:

SD_* to get an idea of the specifics and what to tune for the SD flags

of a sched_domain.



Architectures may retain the regular override the default SD_*_INIT flags

while using the generic domain builder in kernel/sched/core.c if they wish to

retain the traditional SMT->SMP->NUMA topology (or some subset of that). This

can be done by #define'ing ARCH_HASH_SCHED_TUNE.



Alternatively, the architecture may completely override the generic domain

builder by #define'ing ARCH_HASH_SCHED_DOMAIN, and exporting your

arch_init_sched_domains function. This function will attach domains to all

CPUs using cpu_attach_domain.

Architectures may override the generic domain builder and the default SD flags

for a given topology level by creating a sched_domain_topology_level array and

calling set_sched_topology() with this array as the parameter.



The sched-domains debugging infrastructure can be enabled by enabling

CONFIG_SCHED_DEBUG. This enables an error checking parse of the sched domains

which should catch most possible errors (described above). It also prints out

the domain structure in a visual format.
 
CONFIG_SCHED_DEBUG and adding 'sched_debug' to your cmdline. If you forgot to

tweak your cmdline, you can also flip the /sys/kernel/debug/sched_debug

knob. This enables an error checking parse of the sched domains which should

catch most possible errors (described above). It also prints out the domain

structure in a visual format.

arch/arm64/kernel/topology.c

+10 −0
Original line number Diff line number Diff line
@@ -223,6 +223,7 @@ static DEFINE_STATIC_KEY_FALSE(amu_fie_key); 


static int __init init_amu_fie(void)

{

	bool invariance_status = topology_scale_freq_invariant();

	cpumask_var_t valid_cpus;

	bool have_policy = false;

	int ret = 0;
@@ -269,6 +270,15 @@ static int __init init_amu_fie(void) 
	if (!topology_scale_freq_invariant())

		static_branch_disable(&amu_fie_key);



	/*

	 * Task scheduler behavior depends on frequency invariance support,

	 * either cpufreq or counter driven. If the support status changes as

	 * a result of counter initialisation and use, retrigger the build of

	 * scheduling domains to ensure the information is propagated properly.

	 */

	if (invariance_status != topology_scale_freq_invariant())

		rebuild_sched_domains_energy();



free_valid_mask:

	free_cpumask_var(valid_cpus);

arch/mips/kernel/process.c

+3 −2
Original line number Diff line number Diff line
@@ -702,7 +702,6 @@ unsigned long arch_align_stack(unsigned long sp) 
	return sp & ALMASK;

}



static DEFINE_PER_CPU(call_single_data_t, backtrace_csd);

static struct cpumask backtrace_csd_busy;



static void handle_backtrace(void *info)
@@ -711,6 +710,9 @@ static void handle_backtrace(void *info) 
	cpumask_clear_cpu(smp_processor_id(), &backtrace_csd_busy);

}



static DEFINE_PER_CPU(call_single_data_t, backtrace_csd) =

	CSD_INIT(handle_backtrace, NULL);



static void raise_backtrace(cpumask_t *mask)

{

	call_single_data_t *csd;
@@ -730,7 +732,6 @@ static void raise_backtrace(cpumask_t *mask) 
		}



		csd = &per_cpu(backtrace_csd, cpu);

		csd->func = handle_backtrace;

		smp_call_function_single_async(cpu, csd);

	}

}

arch/mips/kernel/smp.c

+6 −19
Original line number Diff line number Diff line
@@ -687,36 +687,23 @@ EXPORT_SYMBOL(flush_tlb_one); 


#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST



static DEFINE_PER_CPU(call_single_data_t, tick_broadcast_csd);



void tick_broadcast(const struct cpumask *mask)

{

	call_single_data_t *csd;

	int cpu;



	for_each_cpu(cpu, mask) {

		csd = &per_cpu(tick_broadcast_csd, cpu);

		smp_call_function_single_async(cpu, csd);

	}

}



static void tick_broadcast_callee(void *info)

{

	tick_receive_broadcast();

}



static int __init tick_broadcast_init(void)

static DEFINE_PER_CPU(call_single_data_t, tick_broadcast_csd) =

	CSD_INIT(tick_broadcast_callee, NULL);



void tick_broadcast(const struct cpumask *mask)

{

	call_single_data_t *csd;

	int cpu;



	for (cpu = 0; cpu < NR_CPUS; cpu++) {

	for_each_cpu(cpu, mask) {

		csd = &per_cpu(tick_broadcast_csd, cpu);

		csd->func = tick_broadcast_callee;

		smp_call_function_single_async(cpu, csd);

	}



	return 0;

}

early_initcall(tick_broadcast_init);



#endif /* CONFIG_GENERIC_CLOCKEVENTS_BROADCAST */

arch/s390/pci/pci_irq.c

+1 −3
Original line number Diff line number Diff line
@@ -179,9 +179,7 @@ static void zpci_handle_fallback_irq(void) 
		if (atomic_inc_return(&cpu_data->scheduled) > 1)

			continue;



		cpu_data->csd.func = zpci_handle_remote_irq;

		cpu_data->csd.info = &cpu_data->scheduled;

		cpu_data->csd.flags = 0;

		INIT_CSD(&cpu_data->csd, zpci_handle_remote_irq, &cpu_data->scheduled);

		smp_call_function_single_async(cpu, &cpu_data->csd);

	}

}

CRA Git | Maintained and supported by SUSTech CRA and CCSE