diff options
59 files changed, 1906 insertions, 619 deletions
diff --git a/Documentation/scheduler/sched-domains.rst b/Documentation/scheduler/sched-domains.rst index 5c4b7f4f0062..8582fa5e9170 100644 --- a/Documentation/scheduler/sched-domains.rst +++ b/Documentation/scheduler/sched-domains.rst @@ -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. diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c index b8026ec684ba..c8308befdb1e 100644 --- a/arch/arm64/kernel/topology.c +++ b/arch/arm64/kernel/topology.c @@ -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); diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c index 75ebd8d7bd5d..d7e288f3a1e7 100644 --- a/arch/mips/kernel/process.c +++ b/arch/mips/kernel/process.c @@ -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); } } diff --git a/arch/mips/kernel/smp.c b/arch/mips/kernel/smp.c index 48d84d5fcc36..74b9102fd06e 100644 --- a/arch/mips/kernel/smp.c +++ b/arch/mips/kernel/smp.c @@ -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 */ diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c index 75217fb63d7b..9dd5ad1b553d 100644 --- a/arch/s390/pci/pci_irq.c +++ b/arch/s390/pci/pci_irq.c @@ -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); } } diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index f4234575f3fd..488a8e848754 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -218,4 +218,9 @@ static inline void arch_set_max_freq_ratio(bool turbo_disabled) } #endif +#ifdef CONFIG_ACPI_CPPC_LIB +void init_freq_invariance_cppc(void); +#define init_freq_invariance_cppc init_freq_invariance_cppc +#endif + #endif /* _ASM_X86_TOPOLOGY_H */ diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c index 3492aa36bf09..6f7b8cc1bc9f 100644 --- a/arch/x86/kernel/cpuid.c +++ b/arch/x86/kernel/cpuid.c @@ -74,10 +74,9 @@ static ssize_t cpuid_read(struct file *file, char __user *buf, init_completion(&cmd.done); for (; count; count -= 16) { - call_single_data_t csd = { - .func = cpuid_smp_cpuid, - .info = &cmd, - }; + call_single_data_t csd; + + INIT_CSD(&csd, cpuid_smp_cpuid, &cmd); cmd.regs.eax = pos; cmd.regs.ecx = pos >> 32; diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 99bdcebaedfc..9278ed7b564e 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -82,6 +82,10 @@ #include <asm/hw_irq.h> #include <asm/stackprotector.h> +#ifdef CONFIG_ACPI_CPPC_LIB +#include <acpi/cppc_acpi.h> +#endif + /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); @@ -148,7 +152,7 @@ static inline void smpboot_restore_warm_reset_vector(void) *((volatile u32 *)phys_to_virt(TRAMPOLINE_PHYS_LOW)) = 0; } -static void init_freq_invariance(bool secondary); +static void init_freq_invariance(bool secondary, bool cppc_ready); /* * Report back to the Boot Processor during boot time or to the caller processor @@ -186,7 +190,7 @@ static void smp_callin(void) */ set_cpu_sibling_map(raw_smp_processor_id()); - init_freq_invariance(true); + init_freq_invariance(true, false); /* * Get our bogomips. @@ -1341,7 +1345,7 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus) set_sched_topology(x86_topology); set_cpu_sibling_map(0); - init_freq_invariance(false); + init_freq_invariance(false, false); smp_sanity_check(); switch (apic_intr_mode) { @@ -2028,6 +2032,48 @@ out: return true; } +#ifdef CONFIG_ACPI_CPPC_LIB +static bool amd_set_max_freq_ratio(void) +{ + struct cppc_perf_caps perf_caps; + u64 highest_perf, nominal_perf; + u64 perf_ratio; + int rc; + + rc = cppc_get_perf_caps(0, &perf_caps); + if (rc) { + pr_debug("Could not retrieve perf counters (%d)\n", rc); + return false; + } + + highest_perf = perf_caps.highest_perf; + nominal_perf = perf_caps.nominal_perf; + + if (!highest_perf || !nominal_perf) { + pr_debug("Could not retrieve highest or nominal performance\n"); + return false; + } + + perf_ratio = div_u64(highest_perf * SCHED_CAPACITY_SCALE, nominal_perf); + /* midpoint between max_boost and max_P */ + perf_ratio = (perf_ratio + SCHED_CAPACITY_SCALE) >> 1; + if (!perf_ratio) { + pr_debug("Non-zero highest/nominal perf values led to a 0 ratio\n"); + return false; + } + + arch_turbo_freq_ratio = perf_ratio; + arch_set_max_freq_ratio(false); + + return true; +} +#else +static bool amd_set_max_freq_ratio(void) +{ + return false; +} +#endif + static void init_counter_refs(void) { u64 aperf, mperf; @@ -2039,7 +2085,7 @@ static void init_counter_refs(void) this_cpu_write(arch_prev_mperf, mperf); } -static void init_freq_invariance(bool secondary) +static void init_freq_invariance(bool secondary, bool cppc_ready) { bool ret = false; @@ -2055,15 +2101,38 @@ static void init_freq_invariance(bool secondary) if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) ret = intel_set_max_freq_ratio(); + else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) { + if (!cppc_ready) { + return; + } + ret = amd_set_max_freq_ratio(); + } if (ret) { init_counter_refs(); static_branch_enable(&arch_scale_freq_key); + pr_info("Estimated ratio of average max frequency by base frequency (times 1024): %llu\n", arch_max_freq_ratio); } else { pr_debug("Couldn't determine max cpu frequency, necessary for scale-invariant accounting.\n"); } } +#ifdef CONFIG_ACPI_CPPC_LIB +static DEFINE_MUTEX(freq_invariance_lock); + +void init_freq_invariance_cppc(void) +{ + static bool secondary; + + mutex_lock(&freq_invariance_lock); + + init_freq_invariance(secondary, true); + secondary = true; + + mutex_unlock(&freq_invariance_lock); +} +#endif + static void disable_freq_invariance_workfn(struct work_struct *work) { static_branch_disable(&arch_scale_freq_key); @@ -2113,7 +2182,7 @@ error: schedule_work(&disable_freq_invariance_work); } #else -static inline void init_freq_invariance(bool secondary) +static inline void init_freq_invariance(bool secondary, bool cppc_ready) { } #endif /* CONFIG_X86_64 */ diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c index fee8b9c0520c..75a0915b0d01 100644 --- a/arch/x86/lib/msr-smp.c +++ b/arch/x86/lib/msr-smp.c @@ -169,12 +169,11 @@ static void __wrmsr_safe_on_cpu(void *info) int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h) { struct msr_info_completion rv; - call_single_data_t csd = { - .func = __rdmsr_safe_on_cpu, - .info = &rv, - }; + call_single_data_t csd; int err; + INIT_CSD(&csd, __rdmsr_safe_on_cpu, &rv); + memset(&rv, 0, sizeof(rv)); init_completion(&rv.done); rv.msr.msr_no = msr_no; diff --git a/block/blk-mq.c b/block/blk-mq.c index 55bcee5dc032..d35b3c0c876a 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -671,9 +671,7 @@ bool blk_mq_complete_request_remote(struct request *rq) return false; if (blk_mq_complete_need_ipi(rq)) { - rq->csd.func = __blk_mq_complete_request_remote; - rq->csd.info = rq; - rq->csd.flags = 0; + INIT_CSD(&rq->csd, __blk_mq_complete_request_remote, rq); smp_call_function_single_async(rq->mq_ctx->cpu, &rq->csd); } else { if (rq->q->nr_hw_queues > 1) diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c index 7a99b19bb893..a852dc4927f7 100644 --- a/drivers/acpi/cppc_acpi.c +++ b/drivers/acpi/cppc_acpi.c @@ -39,6 +39,7 @@ #include <linux/ktime.h> #include <linux/rwsem.h> #include <linux/wait.h> +#include <linux/topology.h> #include <acpi/cppc_acpi.h> @@ -688,6 +689,10 @@ static bool is_cppc_supported(int revision, int num_ent) * } */ +#ifndef init_freq_invariance_cppc +static inline void init_freq_invariance_cppc(void) { } +#endif + /** * acpi_cppc_processor_probe - Search for per CPU _CPC objects. * @pr: Ptr to acpi_processor containing this CPU's logical ID. @@ -850,6 +855,8 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr) goto out_free; } + init_freq_invariance_cppc(); + kfree(output.pointer); return 0; diff --git a/drivers/cpuidle/coupled.c b/drivers/cpuidle/coupled.c index 04003b90dc49..74068742cef3 100644 --- a/drivers/cpuidle/coupled.c +++ b/drivers/cpuidle/coupled.c @@ -674,8 +674,7 @@ have_coupled: coupled->refcnt++; csd = &per_cpu(cpuidle_coupled_poke_cb, dev->cpu); - csd->func = cpuidle_coupled_handle_poke; - csd->info = (void *)(unsigned long)dev->cpu; + INIT_CSD(csd, cpuidle_coupled_handle_poke, (void *)(unsigned long)dev->cpu); return 0; } diff --git a/drivers/gpu/drm/i915/i915_request.c b/drivers/gpu/drm/i915/i915_request.c index 0e813819b041..5385b081a376 100644 --- a/drivers/gpu/drm/i915/i915_request.c +++ b/drivers/gpu/drm/i915/i915_request.c @@ -197,7 +197,7 @@ __notify_execute_cb(struct i915_request *rq, bool (*fn)(struct irq_work *wrk)) llist_for_each_entry_safe(cb, cn, llist_del_all(&rq->execute_cb), - work.llnode) + work.node.llist) fn(&cb->work); } @@ -460,7 +460,7 @@ __await_execution(struct i915_request *rq, * callback first, then checking the ACTIVE bit, we serialise with * the completed/retired request. */ - if (llist_add(&cb->work.llnode, &signal->execute_cb)) { + if (llist_add(&cb->work.node.llist, &signal->execute_cb)) { if (i915_request_is_active(signal) || __request_in_flight(signal)) __notify_execute_cb_imm(signal); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index 9ef172976b35..37d064193f0f 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -729,13 +729,8 @@ static void liquidio_napi_drv_callback(void *arg) droq->cpu_id == this_cpu) { napi_schedule_irqoff(&droq->napi); } else { - call_single_data_t *csd = &droq->csd; - - csd->func = napi_schedule_wrapper; - csd->info = &droq->napi; - csd->flags = 0; - - smp_call_function_single_async(droq->cpu_id, csd); + INIT_CSD(&droq->csd, napi_schedule_wrapper, &droq->napi); + smp_call_function_single_async(droq->cpu_id, &droq->csd); } } diff --git a/fs/proc/array.c b/fs/proc/array.c index 277f654f289e..a23c3e220a5f 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -383,9 +383,9 @@ static inline void task_context_switch_counts(struct seq_file *m, static void task_cpus_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Cpus_allowed:\t%*pb\n", - cpumask_pr_args(task->cpus_ptr)); + cpumask_pr_args(&task->cpus_mask)); seq_printf(m, "Cpus_allowed_list:\t%*pbl\n", - cpumask_pr_args(task->cpus_ptr)); + cpumask_pr_args(&task->cpus_mask)); } static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm) diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h index bc56287a1ed1..0042ef362511 100644 --- a/include/linux/cpuhotplug.h +++ b/include/linux/cpuhotplug.h @@ -152,6 +152,7 @@ enum cpuhp_state { CPUHP_AP_ONLINE, CPUHP_TEARDOWN_CPU, CPUHP_AP_ONLINE_IDLE, + CPUHP_AP_SCHED_WAIT_EMPTY, CPUHP_AP_SMPBOOT_THREADS, CPUHP_AP_X86_VDSO_VMA_ONLINE, CPUHP_AP_IRQ_AFFINITY_ONLINE, diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index f0d895d6ac39..383684e30f12 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -199,6 +199,11 @@ static inline int cpumask_any_and_distribute(const struct cpumask *src1p, return cpumask_next_and(-1, src1p, src2p); } +static inline int cpumask_any_distribute(const struct cpumask *srcp) +{ + return cpumask_first(srcp); +} + #define for_each_cpu(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) #define for_each_cpu_not(cpu, mask) \ @@ -252,6 +257,7 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu); unsigned int cpumask_local_spread(unsigned int i, int node); int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); +int cpumask_any_distribute(const struct cpumask *srcp); /** * for_each_cpu - iterate over every cpu in a mask diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 30823780c192..ec2a47a81e42 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -14,28 +14,37 @@ */ struct irq_work { - union { - struct __call_single_node node; - struct { - struct llist_node llnode; - atomic_t flags; - }; - }; + struct __call_single_node node; void (*func)(struct irq_work *); }; +#define __IRQ_WORK_INIT(_func, _flags) (struct irq_work){ \ + .node = { .u_flags = (_flags), }, \ + .func = (_func), \ +} + +#define IRQ_WORK_INIT(_func) __IRQ_WORK_INIT(_func, 0) +#define IRQ_WORK_INIT_LAZY(_func) __IRQ_WORK_INIT(_func, IRQ_WORK_LAZY) +#define IRQ_WORK_INIT_HARD(_func) __IRQ_WORK_INIT(_func, IRQ_WORK_HARD_IRQ) + +#define DEFINE_IRQ_WORK(name, _f) \ + struct irq_work name = IRQ_WORK_INIT(_f) + static inline void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *)) { - atomic_set(&work->flags, 0); - work->func = func; + *work = IRQ_WORK_INIT(func); } -#define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { \ - .flags = ATOMIC_INIT(0), \ - .func = (_f) \ +static inline bool irq_work_is_pending(struct irq_work *work) +{ + return atomic_read(&work->node.a_flags) & IRQ_WORK_PENDING; } +static inline bool irq_work_is_busy(struct irq_work *work) +{ + return atomic_read(&work->node.a_flags) & IRQ_WORK_BUSY; +} bool irq_work_queue(struct irq_work *work); bool irq_work_queue_on(struct irq_work *work, int cpu); diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h index 3ed4e8771b64..8de0e1373de7 100644 --- a/include/linux/irqflags.h +++ b/include/linux/irqflags.h @@ -107,14 +107,14 @@ do { \ current->irq_config = 0; \ } while (0) -# define lockdep_irq_work_enter(__work) \ +# define lockdep_irq_work_enter(_flags) \ do { \ - if (!(atomic_read(&__work->flags) & IRQ_WORK_HARD_IRQ))\ + if (!((_flags) & IRQ_WORK_HARD_IRQ)) \ current->irq_config = 1; \ } while (0) -# define lockdep_irq_work_exit(__work) \ +# define lockdep_irq_work_exit(_flags) \ do { \ - if (!(atomic_read(&__work->flags) & IRQ_WORK_HARD_IRQ))\ + if (!((_flags) & IRQ_WORK_HARD_IRQ)) \ current->irq_config = 0; \ } while (0) diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 4b5fd3da5fe8..dbf6018fc312 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -204,6 +204,7 @@ extern int _cond_resched(void); extern void ___might_sleep(const char *file, int line, int preempt_offset); extern void __might_sleep(const char *file, int line, int preempt_offset); extern void __cant_sleep(const char *file, int line, int preempt_offset); +extern void __cant_migrate(const char *file, int line); /** * might_sleep - annotation for functions that can sleep @@ -227,6 +228,18 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset); # define cant_sleep() \ do { __cant_sleep(__FILE__, __LINE__, 0); } while (0) # define sched_annotate_sleep() (current->task_state_change = 0) + +/** + * cant_migrate - annotation for functions that cannot migrate + * + * Will print a stack trace if executed in code which is migratable + */ +# define cant_migrate() \ + do { \ + if (IS_ENABLED(CONFIG_SMP)) \ + __cant_migrate(__FILE__, __LINE__); \ + } while (0) + /** * non_block_start - annotate the start of section where sleeping is prohibited * @@ -251,6 +264,7 @@ extern void __cant_sleep(const char *file, int line, int preempt_offset); int preempt_offset) { } # define might_sleep() do { might_resched(); } while (0) # define cant_sleep() do { } while (0) +# define cant_migrate() do { } while (0) # define sch |