diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-12 12:56:01 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-10-12 12:56:01 -0700 |
commit | edaa5ddf3833669a25654d42c0fb653dfdd906df (patch) | |
tree | 156c29b0375581dfa7c7e578d8d61924b3eb81b2 | |
parent | 13cb73490f475f8e7669f9288be0bcfa85399b1f (diff) | |
parent | feff2e65efd8d84cf831668e182b2ce73c604bbb (diff) |
Merge tag 'sched-core-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull scheduler updates from Ingo Molnar:
- reorganize & clean up the SD* flags definitions and add a bunch of
sanity checks. These new checks caught quite a few bugs or at least
inconsistencies, resulting in another set of patches.
- rseq updates, add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ
- add a new tracepoint to improve CPU capacity tracking
- improve overloaded SMP system load-balancing behavior
- tweak SMT balancing
- energy-aware scheduling updates
- NUMA balancing improvements
- deadline scheduler fixes and improvements
- CPU isolation fixes
- misc cleanups, simplifications and smaller optimizations
* tag 'sched-core-2020-10-12' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (42 commits)
sched/deadline: Unthrottle PI boosted threads while enqueuing
sched/debug: Add new tracepoint to track cpu_capacity
sched/fair: Tweak pick_next_entity()
rseq/selftests: Test MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ
rseq/selftests,x86_64: Add rseq_offset_deref_addv()
rseq/membarrier: Add MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ
sched/fair: Use dst group while checking imbalance for NUMA balancer
sched/fair: Reduce busy load balance interval
sched/fair: Minimize concurrent LBs between domain level
sched/fair: Reduce minimal imbalance threshold
sched/fair: Relax constraint on task's load during load balance
sched/fair: Remove the force parameter of update_tg_load_avg()
sched/fair: Fix wrong cpu selecting from isolated domain
sched: Remove unused inline function uclamp_bucket_base_value()
sched/rt: Disable RT_RUNTIME_SHARE by default
sched/deadline: Fix stale throttling on de-/boosted tasks
sched/numa: Use runnable_avg to classify node
sched/topology: Move sd_flag_debug out of #ifdef CONFIG_SYSCTL
MAINTAINERS: Add myself as SCHED_DEADLINE reviewer
sched/topology: Move SD_DEGENERATE_GROUPS_MASK out of linux/sched/topology.h
...
-rw-r--r-- | MAINTAINERS | 1 | ||||
-rw-r--r-- | arch/arm/kernel/topology.c | 26 | ||||
-rw-r--r-- | include/linux/sched.h | 5 | ||||
-rw-r--r-- | include/linux/sched/mm.h | 3 | ||||
-rw-r--r-- | include/linux/sched/sd_flags.h | 156 | ||||
-rw-r--r-- | include/linux/sched/topology.h | 37 | ||||
-rw-r--r-- | include/linux/syscalls.h | 2 | ||||
-rw-r--r-- | include/trace/events/sched.h | 4 | ||||
-rw-r--r-- | include/uapi/linux/membarrier.h | 26 | ||||
-rw-r--r-- | kernel/sched/core.c | 13 | ||||
-rw-r--r-- | kernel/sched/deadline.c | 34 | ||||
-rw-r--r-- | kernel/sched/debug.c | 56 | ||||
-rw-r--r-- | kernel/sched/fair.c | 103 | ||||
-rw-r--r-- | kernel/sched/features.h | 2 | ||||
-rw-r--r-- | kernel/sched/membarrier.c | 136 | ||||
-rw-r--r-- | kernel/sched/topology.c | 69 | ||||
-rw-r--r-- | tools/testing/selftests/rseq/param_test.c | 223 | ||||
-rw-r--r-- | tools/testing/selftests/rseq/rseq-x86.h | 57 | ||||
-rwxr-xr-x | tools/testing/selftests/rseq/run_param_test.sh | 2 |
19 files changed, 803 insertions, 152 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 10a54b256ddf..80ee365836da 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15407,6 +15407,7 @@ R: Dietmar Eggemann <dietmar.eggemann@arm.com> (SCHED_NORMAL) R: Steven Rostedt <rostedt@goodmis.org> (SCHED_FIFO/SCHED_RR) R: Ben Segall <bsegall@google.com> (CONFIG_CFS_BANDWIDTH) R: Mel Gorman <mgorman@suse.de> (CONFIG_NUMA_BALANCING) +R: Daniel Bristot de Oliveira <bristot@redhat.com> (SCHED_DEADLINE) L: linux-kernel@vger.kernel.org S: Maintained T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git sched/core diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index b5adaf744630..ef0058de432b 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -178,15 +178,6 @@ static inline void update_cpu_capacity(unsigned int cpuid) {} #endif /* - * The current assumption is that we can power gate each core independently. - * This will be superseded by DT binding once available. - */ -const struct cpumask *cpu_corepower_mask(int cpu) -{ - return &cpu_topology[cpu].thread_sibling; -} - -/* * store_cpu_topology is called at boot when only one cpu is running * and with the mutex cpu_hotplug.lock locked, when several cpus have booted, * which prevents simultaneous write access to cpu_topology array @@ -241,20 +232,6 @@ topology_populated: update_siblings_masks(cpuid); } -static inline int cpu_corepower_flags(void) -{ - return SD_SHARE_PKG_RESOURCES | SD_SHARE_POWERDOMAIN; -} - -static struct sched_domain_topology_level arm_topology[] = { -#ifdef CONFIG_SCHED_MC - { cpu_corepower_mask, cpu_corepower_flags, SD_INIT_NAME(GMC) }, - { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, -#endif - { cpu_cpu_mask, SD_INIT_NAME(DIE) }, - { NULL, }, -}; - /* * init_cpu_topology is called at boot when only one cpu is running * which prevent simultaneous write access to cpu_topology array @@ -265,7 +242,4 @@ void __init init_cpu_topology(void) smp_wmb(); parse_dt_topology(); - - /* Set scheduler topology descriptor */ - set_sched_topology(arm_topology); } diff --git a/include/linux/sched.h b/include/linux/sched.h index 3a3aaf0b7465..d383cf09e78f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1491,9 +1491,10 @@ extern struct pid *cad_pid; /* * Per process flags */ +#define PF_VCPU 0x00000001 /* I'm a virtual CPU */ #define PF_IDLE 0x00000002 /* I am an IDLE thread */ #define PF_EXITING 0x00000004 /* Getting shut down */ -#define PF_VCPU 0x00000010 /* I'm a virtual CPU */ +#define PF_IO_WORKER 0x00000010 /* Task is an IO worker */ #define PF_WQ_WORKER 0x00000020 /* I'm a workqueue worker */ #define PF_FORKNOEXEC 0x00000040 /* Forked but didn't exec */ #define PF_MCE_PROCESS 0x00000080 /* Process policy on mce errors */ @@ -1517,7 +1518,6 @@ extern struct pid *cad_pid; #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */ -#define PF_IO_WORKER 0x20000000 /* Task is an IO worker */ #define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */ #define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */ @@ -2046,6 +2046,7 @@ const struct sched_avg *sched_trace_rq_avg_dl(struct rq *rq); const struct sched_avg *sched_trace_rq_avg_irq(struct rq *rq); int sched_trace_rq_cpu(struct rq *rq); +int sched_trace_rq_cpu_capacity(struct rq *rq); int sched_trace_rq_nr_running(struct rq *rq); const struct cpumask *sched_trace_rd_span(struct root_domain *rd); diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h index f889e332912f..15bfb06f2884 100644 --- a/include/linux/sched/mm.h +++ b/include/linux/sched/mm.h @@ -348,10 +348,13 @@ enum { MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5), + MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ_READY = (1U << 6), + MEMBARRIER_STATE_PRIVATE_EXPEDITED_RSEQ = (1U << 7), }; enum { MEMBARRIER_FLAG_SYNC_CORE = (1U << 0), + MEMBARRIER_FLAG_RSEQ = (1U << 1), }; #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h new file mode 100644 index 000000000000..34b21e971d77 --- /dev/null +++ b/include/linux/sched/sd_flags.h @@ -0,0 +1,156 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * sched-domains (multiprocessor balancing) flag declarations. + */ + +#ifndef SD_FLAG +# error "Incorrect import of SD flags definitions" +#endif + +/* + * Hierarchical metaflags + * + * SHARED_CHILD: These flags are meant to be set from the base domain upwards. + * If a domain has this flag set, all of its children should have it set. This + * is usually because the flag describes some shared resource (all CPUs in that + * domain share the same resource), or because they are tied to a scheduling + * behaviour that we want to disable at some point in the hierarchy for + * scalability reasons. + * + * In those cases it doesn't make sense to have the flag set for a domain but + * not have it in (some of) its children: sched domains ALWAYS span their child + * domains, so operations done with parent domains will cover CPUs in the lower + * child domains. + * + * + * SHARED_PARENT: These flags are meant to be set from the highest domain + * downwards. If a domain has this flag set, all of its parents should have it + * set. This is usually for topology properties that start to appear above a + * certain level (e.g. domain starts spanning CPUs outside of the base CPU's + * socket). + */ +#define SDF_SHARED_CHILD 0x1 +#define SDF_SHARED_PARENT 0x2 + +/* + * Behavioural metaflags + * + * NEEDS_GROUPS: These flags are only relevant if the domain they are set on has + * more than one group. This is usually for balancing flags (load balancing + * involves equalizing a metric between groups), or for flags describing some + * shared resource (which would be shared between groups). + */ +#define SDF_NEEDS_GROUPS 0x4 + +/* + * Balance when about to become idle + * + * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level. + * NEEDS_GROUPS: Load balancing flag. + */ +SD_FLAG(SD_BALANCE_NEWIDLE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) + +/* + * Balance on exec + * + * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level. + * NEEDS_GROUPS: Load balancing flag. + */ +SD_FLAG(SD_BALANCE_EXEC, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) + +/* + * Balance on fork, clone + * + * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level. + * NEEDS_GROUPS: Load balancing flag. + */ +SD_FLAG(SD_BALANCE_FORK, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) + +/* + * Balance on wakeup + * + * SHARED_CHILD: Set from the base domain up to cpuset.sched_relax_domain_level. + * NEEDS_GROUPS: Load balancing flag. + */ +SD_FLAG(SD_BALANCE_WAKE, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) + +/* + * Consider waking task on waking CPU. + * + * SHARED_CHILD: Set from the base domain up to the NUMA reclaim level. + */ +SD_FLAG(SD_WAKE_AFFINE, SDF_SHARED_CHILD) + +/* + * Domain members have different CPU capacities + * + * SHARED_PARENT: Set from the topmost domain down to the first domain where + * asymmetry is detected. + * NEEDS_GROUPS: Per-CPU capacity is asymmetric between groups. + */ +SD_FLAG(SD_ASYM_CPUCAPACITY, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) + +/* + * Domain members share CPU capacity (i.e. SMT) + * + * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share + * CPU capacity. + * NEEDS_GROUPS: Capacity is shared between groups. + */ +SD_FLAG(SD_SHARE_CPUCAPACITY, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) + +/* + * Domain members share CPU package resources (i.e. caches) + * + * SHARED_CHILD: Set from the base domain up until spanned CPUs no longer share + * the same cache(s). + * NEEDS_GROUPS: Caches are shared between groups. + */ +SD_FLAG(SD_SHARE_PKG_RESOURCES, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) + +/* + * Only a single load balancing instance + * + * SHARED_PARENT: Set for all NUMA levels above NODE. Could be set from a + * different level upwards, but it doesn't change that if a + * domain has this flag set, then all of its parents need to have + * it too (otherwise the serialization doesn't make sense). + * NEEDS_GROUPS: No point in preserving domain if it has a single group. + */ +SD_FLAG(SD_SERIALIZE, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) + +/* + * Place busy tasks earlier in the domain + * + * SHARED_CHILD: Usually set on the SMT level. Technically could be set further + * up, but currently assumed to be set from the base domain + * upwards (see update_top_cache_domain()). + * NEEDS_GROUPS: Load balancing flag. + */ +SD_FLAG(SD_ASYM_PACKING, SDF_SHARED_CHILD | SDF_NEEDS_GROUPS) + +/* + * Prefer to place tasks in a sibling domain + * + * Set up until domains start spanning NUMA nodes. Close to being a SHARED_CHILD + * flag, but cleared below domains with SD_ASYM_CPUCAPACITY. + * + * NEEDS_GROUPS: Load balancing flag. + */ +SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS) + +/* + * sched_groups of this level overlap + * + * SHARED_PARENT: Set for all NUMA levels above NODE. + * NEEDS_GROUPS: Overlaps can only exist with more than one group. + */ +SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) + +/* + * Cross-node balancing + * + * SHARED_PARENT: Set for all NUMA levels above NODE. + * NEEDS_GROUPS: No point in preserving domain if it has a single group. + */ +SD_FLAG(SD_NUMA, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 820511289857..9ef7bf686a9f 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -11,20 +11,29 @@ */ #ifdef CONFIG_SMP -#define SD_BALANCE_NEWIDLE 0x0001 /* Balance when about to become idle */ -#define SD_BALANCE_EXEC 0x0002 /* Balance on exec */ -#define SD_BALANCE_FORK 0x0004 /* Balance on fork, clone */ -#define SD_BALANCE_WAKE 0x0008 /* Balance on wakeup */ -#define SD_WAKE_AFFINE 0x0010 /* Wake task to waking CPU */ -#define SD_ASYM_CPUCAPACITY 0x0020 /* Domain members have different CPU capacities */ -#define SD_SHARE_CPUCAPACITY 0x0040 /* Domain members share CPU capacity */ -#define SD_SHARE_POWERDOMAIN 0x0080 /* Domain members share power domain */ -#define SD_SHARE_PKG_RESOURCES 0x0100 /* Domain members share CPU pkg resources */ -#define SD_SERIALIZE 0x0200 /* Only a single load balancing instance */ -#define SD_ASYM_PACKING 0x0400 /* Place busy groups earlier in the domain */ -#define SD_PREFER_SIBLING 0x0800 /* Prefer to place tasks in a sibling domain */ -#define SD_OVERLAP 0x1000 /* sched_domains of this level overlap */ -#define SD_NUMA 0x2000 /* cross-node balancing */ +/* Generate SD flag indexes */ +#define SD_FLAG(name, mflags) __##name, +enum { + #include <linux/sched/sd_flags.h> + __SD_FLAG_CNT, +}; +#undef SD_FLAG +/* Generate SD flag bits */ +#define SD_FLAG(name, mflags) name = 1 << __##name, +enum { + #include <linux/sched/sd_flags.h> +}; +#undef SD_FLAG + +#ifdef CONFIG_SCHED_DEBUG + +struct sd_flag_debug { + unsigned int meta_flags; + char *name; +}; +extern const struct sd_flag_debug sd_flag_debug[]; + +#endif #ifdef CONFIG_SCHED_SMT static inline int cpu_smt_flags(void) diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 75ac7f8ae93c..06db09875aa4 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -974,7 +974,7 @@ asmlinkage long sys_execveat(int dfd, const char __user *filename, const char __user *const __user *argv, const char __user *const __user *envp, int flags); asmlinkage long sys_userfaultfd(int flags); -asmlinkage long sys_membarrier(int cmd, int flags); +asmlinkage long sys_membarrier(int cmd, unsigned int flags, int cpu_id); asmlinkage long sys_mlock2(unsigned long start, size_t len, int flags); asmlinkage long sys_copy_file_range(int fd_in, loff_t __user *off_in, int fd_out, loff_t __user *off_out, diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h index fec25b9cfbaf..c96a4337afe6 100644 --- a/include/trace/events/sched.h +++ b/include/trace/events/sched.h @@ -630,6 +630,10 @@ DECLARE_TRACE(pelt_se_tp, TP_PROTO(struct sched_entity *se), TP_ARGS(se)); +DECLARE_TRACE(sched_cpu_capacity_tp, + TP_PROTO(struct rq *rq), + TP_ARGS(rq)); + DECLARE_TRACE(sched_overutilized_tp, TP_PROTO(struct root_domain *rd, bool overutilized), TP_ARGS(rd, overutilized)); diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h index 5891d7614c8c..737605897f36 100644 --- a/include/uapi/linux/membarrier.h +++ b/include/uapi/linux/membarrier.h @@ -114,6 +114,26 @@ * If this command is not implemented by an * architecture, -EINVAL is returned. * Returns 0 on success. + * @MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ: + * Ensure the caller thread, upon return from + * system call, that all its running thread + * siblings have any currently running rseq + * critical sections restarted if @flags + * parameter is 0; if @flags parameter is + * MEMBARRIER_CMD_FLAG_CPU, + * then this operation is performed only + * on CPU indicated by @cpu_id. If this command is + * not implemented by an architecture, -EINVAL + * is returned. A process needs to register its + * intent to use the private expedited rseq + * command prior to using it, otherwise + * this command returns -EPERM. + * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ: + * Register the process intent to use + * MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ. + * If this command is not implemented by an + * architecture, -EINVAL is returned. + * Returns 0 on success. * @MEMBARRIER_CMD_SHARED: * Alias to MEMBARRIER_CMD_GLOBAL. Provided for * header backward compatibility. @@ -131,9 +151,15 @@ enum membarrier_cmd { MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4), MEMBARRIER_CMD_PRIVATE_EXPEDITED_SYNC_CORE = (1 << 5), MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_SYNC_CORE = (1 << 6), + MEMBARRIER_CMD_PRIVATE_EXPEDITED_RSEQ = (1 << 7), + MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED_RSEQ = (1 << 8), /* Alias for header backward compatibility. */ MEMBARRIER_CMD_SHARED = MEMBARRIER_CMD_GLOBAL, }; +enum membarrier_cmd_flag { + MEMBARRIER_CMD_FLAG_CPU = (1 << 0), +}; + #endif /* _UAPI_LINUX_MEMBARRIER_H */ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 2d95dc3f4644..8160ab5263f8 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -36,6 +36,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_rt_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_dl_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_se_tp); +EXPORT_TRACEPOINT_SYMBOL_GPL(sched_cpu_capacity_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_overutilized_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_cfs_tp); EXPORT_TRACEPOINT_SYMBOL_GPL(sched_util_est_se_tp); @@ -940,11 +941,6 @@ static inline unsigned int uclamp_bucket_id(unsigned int clamp_value) return clamp_value / UCLAMP_BUCKET_DELTA; } -static inline unsigned int uclamp_bucket_base_value(unsigned int clamp_value) -{ - return UCLAMP_BUCKET_DELTA * uclamp_bucket_id(clamp_value); -} - static inline unsigned int uclamp_none(enum uclamp_id clamp_id) { if (clamp_id == UCLAMP_MIN) @@ -4551,9 +4547,12 @@ void __noreturn do_task_dead(void) static inline void sched_submit_work(struct task_struct *tsk) { + unsigned int task_flags; + if (!tsk->state) return; + task_flags = tsk->flags; /* * If a worker went to sleep, notify and ask workqueue whether * it wants to wake up a task to maintain concurrency. @@ -4562,9 +4561,9 @@ static inline void sched_submit_work(struct task_struct *tsk) * in the possible wakeup of a kworker and because wq_worker_sleeping() * requires it. */ - if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER)) { + if (task_flags & (PF_WQ_WORKER | PF_IO_WORKER)) { preempt_disable(); - if (tsk->flags & PF_WQ_WORKER) + if (task_flags & PF_WQ_WORKER) wq_worker_sleeping(tsk); else io_wq_worker_sleeping(tsk); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 3862a28cd05d..6d93f4518734 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1525,14 +1525,38 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) */ if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) { pi_se = &pi_task->dl; + /* + * Because of delays in the detection of the overrun of a + * thread's runtime, it might be the case that a thread + * goes to sleep in a rt mutex with negative runtime. As + * a consequence, the thread will be throttled. + * + * While waiting for the mutex, this thread can also be + * boosted via PI, resulting in a thread that is throttled + * and boosted at the same time. + * + * In this case, the boost overrides the throttle. + */ + if (p->dl.dl_throttled) { + /* + * The replenish timer needs to be canceled. No + * problem if it fires concurrently: boosted threads + * are ignored in dl_task_timer(). + */ + hrtimer_try_to_cancel(&p->dl.dl_timer); + p->dl.dl_throttled = 0; + } } else if (!dl_prio(p->normal_prio)) { /* - * Special case in which we have a !SCHED_DEADLINE task - * that is going to be deboosted, but exceeds its - * runtime while doing so. No point in replenishing - * it, as it's going to return back to its original - * scheduling class after this. + * Special case in which we have a !SCHED_DEADLINE task that is going + * to be deboosted, but exceeds its runtime while doing so. No point in + * replenishing it, as it's going to return back to its original + * scheduling class after this. If it has been throttled, we need to + * clear the flag, otherwise the task may wake up as throttled after + * being boosted again with no means to replenish the runtime and clear + * the throttle. */ + p->dl.dl_throttled = 0; BUG_ON(!p->dl.dl_boosted || flags != ENQUEUE_REPLENISH); return; } diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c index 36c54265bb2b..0655524700d2 100644 --- a/kernel/sched/debug.c +++ b/kernel/sched/debug.c @@ -245,6 +245,60 @@ set_table_entry(struct ctl_table *entry, entry->proc_handler = proc_handler; } +static int sd_ctl_doflags(struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) +{ + unsigned long flags = *(unsigned long *)table->data; + size_t data_size = 0; + size_t len = 0; + char *tmp; + int idx; + + if (write) + return 0; + + for_each_set_bit(idx, &flags, __SD_FLAG_CNT) { + char *name = sd_flag_debug[idx].name; + + /* Name plus whitespace */ + data_size += strlen(name) + 1; + } + + if (*ppos > data_size) { + *lenp = 0; + return 0; + } + + tmp = kcalloc(data_size + 1, sizeof(*tmp), GFP_KERNEL); + if (!tmp) + return -ENOMEM; + + for_each_set_bit(idx, &flags, __SD_FLAG_CNT) { + char *name = sd_flag_debug[idx].name; + + len += snprintf(tmp + len, strlen(name) + 2, "%s ", name); + } + + tmp += *ppos; + len -= *ppos; + + if (len > *lenp) + len = *lenp; + if (len) + memcpy(buffer, tmp, len); + if (len < *lenp) { + ((char *)buffer)[len] = '\n'; + len++; + } + + *lenp = len; + *ppos += len; + + kfree(tmp); + + return 0; +} + static struct ctl_table * sd_alloc_ctl_domain_table(struct sched_domain *sd) { @@ -258,7 +312,7 @@ sd_alloc_ctl_domain_table(struct sched_domain *sd) set_table_entry(&table[2], "busy_factor", &sd->busy_factor, sizeof(int), 0644, proc_dointvec_minmax); set_table_entry(&table[3], "imbalance_pct", &sd->imbalance_pct, sizeof(int), 0644, proc_dointvec_minmax); set_table_entry(&table[4], "cache_nice_tries", &sd->cache_nice_tries, sizeof(int), 0644, proc_dointvec_minmax); - set_table_entry(&table[5], "flags", &sd->flags, sizeof(int), 0444, proc_dointvec_minmax); + set_table_entry(&table[5], "flags", &sd->flags, sizeof(int), 0444, sd_ctl_doflags); set_table_entry(&table[6], "max_newidle_lb_cost", &sd->max_newidle_lb_cost, sizeof(long), 0644, proc_doulongvec_minmax); set_table_entry(&table[7], "name", sd->name, CORENAME_MAX_SIZE, 0444, proc_dostring); /* &table[8] is terminator */ diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1a68a0536add..aa4c6227cd6d 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -831,7 +831,7 @@ void init_entity_runnable_average(struct sched_entity *se) void post_init_entity_util_avg(struct task_struct *p) { } -static void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) +static void update_tg_load_avg(struct cfs_rq *cfs_rq) { } #endif /* CONFIG_SMP */ @@ -1504,6 +1504,7 @@ enum numa_type { /* Cached statistics for all CPUs within a node */ struct numa_stats { unsigned long load; + unsigned long runnable; unsigned long util; /* Total compute capacity of CPUs on a node */ unsigned long compute_capacity; @@ -1547,19 +1548,22 @@ struct task_numa_env { }; static unsigned long cpu_load(struct rq *rq); +static unsigned long cpu_runnable(struct rq *rq); static unsigned long cpu_util(int cpu); -static inline long adjust_numa_imbalance(int imbalance, int src_nr_running); +static inline long adjust_numa_imbalance(int imbalance, int nr_running); static inline enum numa_type numa_classify(unsigned int imbalance_pct, struct numa_stats *ns) { if ((ns->nr_running > ns->weight) && - ((ns->compute_capacity * 100) < (ns->util * imbalance_pct))) + (((ns->compute_capacity * 100) < (ns->util * imbalance_pct)) || + ((ns->compute_capacity * imbalance_pct) < (ns->runnable * 100)))) return node_overloaded; if ((ns->nr_running < ns->weight) || - ((ns->compute_capacity * 100) > (ns->util * imbalance_pct))) + (((ns->compute_capacity * 100) > (ns->util * imbalance_pct)) && + ((ns->compute_capacity * imbalance_pct) > (ns->runnable * 100)))) return node_has_spare; return node_fully_busy; @@ -1610,6 +1614,7 @@ static void update_numa_stats(struct task_numa_env *env, struct rq *rq = cpu_rq(cpu); ns->load += cpu_load(rq); + ns->runnable += cpu_runnable(rq); ns->util += cpu_util(cpu); ns->nr_running += rq->cfs.h_nr_running; ns->compute_capacity += capacity_of(cpu); @@ -1925,7 +1930,7 @@ static void task_numa_find_cpu(struct task_numa_env *env, src_running = env->src_stats.nr_running - 1; dst_running = env->dst_stats.nr_running + 1; imbalance = max(0, dst_running - src_running); - imbalance = adjust_numa_imbalance(imbalance, src_running); + imbalance = adjust_numa_imbalance(imbalance, dst_running); /* Use idle CPU if there is no imbalance */ if (!imbalance) { @@ -3084,7 +3089,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, /* commit outstanding execution time */ if (cfs_rq->curr == se) update_curr(cfs_rq); - account_entity_dequeue(cfs_rq, se); + update_load_sub(&cfs_rq->load, se->load.weight); } dequeue_load_avg(cfs_rq, se); @@ -3100,7 +3105,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, enqueue_load_avg(cfs_rq, se); if (se->on_rq) - account_entity_enqueue(cfs_rq, se); + update_load_add(&cfs_rq->load, se->load.weight); } @@ -3288,7 +3293,6 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) /** * update_tg_load_avg - update the tg's load avg * @cfs_rq: the cfs_rq whose avg changed - * @force: update regardless of how small the difference * * This function 'ensures': tg->load_avg := \Sum tg->cfs_rq[]->avg.load. * However, because tg->load_avg is a global value there are performance @@ -3300,7 +3304,7 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags) * * Updating tg's load_avg is necessary before update_cfs_share(). */ -static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) +static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) { long delta = cfs_rq->avg.load_avg - cfs_rq->tg_load_avg_contrib; @@ -3310,7 +3314,7 @@ static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) if (cfs_rq->tg == &root_task_group) return; - if (force || abs(delta) > cfs_rq->tg_load_avg_contrib / 64) { + if (abs(delta) > cfs_rq->tg_load_avg_contrib / 64) { atomic_long_add(delta, &cfs_rq->tg->load_avg); cfs_rq->tg_load_avg_contrib = cfs_rq->avg.load_avg; } @@ -3612,7 +3616,7 @@ static inline bool skip_blocked_update(struct sched_entity *se) #else /* CONFIG_FAIR_GROUP_SCHED */ -static inline void update_tg_load_avg(struct cfs_rq *cfs_rq, int force) {} +static inline void update_tg_load_avg(struct cfs_rq *cfs_rq) {} static inline int propagate_entity_load_avg(struct sched_entity *se) { @@ -3800,13 +3804,13 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s * IOW we're enqueueing a task on a new CPU. */ attach_entity_load_avg(cfs_rq, se); - update_tg_load_avg(cfs_rq, 0); + update_tg_load_avg(cfs_rq); } else if (decayed) { cfs_rq_util_change(cfs_rq, 0); if (flags & UPDATE_TG) - update_tg_load_avg(cfs_rq, 0); + update_tg_load_avg(cfs_rq); } } @@ -4461,17 +4465,17 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr) se = second; } - /* - * Prefer last buddy, try to return the CPU to a preempted task. - */ - if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) - se = cfs_rq->last; - - /* - * Someone really wants this to run. If it's not unfair, run it. - */ - if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) + if (cfs_rq->next && wakeup_preempt_entity(cfs_rq->next, left) < 1) { + /* + * Someone really wants this to run. If it's not unfair, run it. + */ se = cfs_rq->next; + } else if (cfs_rq->last && wakeup_preempt_entity(cfs_rq->last, left) < 1) { + /* + * Prefer last buddy, try to return the CPU to a preempted task. + */ + se = cfs_rq->last; + } clear_buddies(cfs_rq, se); @@ -6075,7 +6079,7 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int /* * Scan the local SMT mask for idle CPUs. */ -static int select_idle_smt(struct task_struct *p, int target) +static int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { int cpu; @@ -6083,7 +6087,8 @@ static int select_idle_smt(struct task_struct *p, int target) return -1; for_each_cpu(cpu, cpu_smt_mask(target)) { - if (!cpumask_test_cpu(cpu, p->cpus_ptr)) + if (!cpumask_test_cpu(cpu, p->cpus_ptr) || + !cpumask_test_cpu(cpu, sched_domain_span(sd))) continue; if (available_idle_cpu(cpu) || sched_idle_cpu(cpu)) return cpu; @@ -6099,7 +6104,7 @@ static inline int select_idle_core(struct task_struct *p, struct sched_domain *s return -1; } -static inline int select_idle_smt(struct task_struct *p, int target) +static inline int select_idle_smt(struct task_struct *p, struct sched_domain *sd, int target) { return -1; } @@ -6274,7 +6279,7 @@ symmetric: if ((unsigned)i < nr_cpumask_bits) return i; - i = select_idle_smt(p, target); + i = select_idle_smt(p, sd, target); if ((unsigned)i < nr_cpumask_bits) return i; @@ -6594,7 +6599,8 @@ static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu) util = cpu_util_next(cpu, p, cpu); cpu_cap = capacity_of(cpu); - spare_cap = cpu_cap - util; + spare_cap = cpu_cap; + lsub_positive(&spare_cap, util); /* * Skip CPUs that cannot satisfy the capacity request. @@ -7402,6 +7408,10 @@ static int task_hot(struct task_struct *p, struct lb_env *env) if (unlikely(task_has_idle_policy(p))) return 0; + /* SMT siblings share cache */ + if (env->sd->flags & SD_SHARE_CPUCAPACITY) + return 0; + /* * Buddy candidates are cache hot: */ @@ -7669,8 +7679,8 @@ static int detach_tasks(struct lb_env *env) * scheduler fails to find a good waiting task to * migrate. */ - if (load/2 > env->imbalance && - env->sd->nr_balance_failed <= env->sd->cache_nice_tries) + + if ((load >> env->sd->nr_balance_failed) > env->imbalance) goto next; env->imbalance -= load; @@ -7887,7 +7897,7 @@ static bool __update_blocked_fair(struct rq *rq, bool *done) struct sched_entity *se; if (update_cfs_rq_load_avg(cfs_rq_clock_pelt(cfs_rq), cfs_rq)) { - update_tg_load_avg(cfs_rq, 0); + update_tg_load_avg(cfs_rq); if (cfs_rq == &rq->cfs) decayed = true; @@ -8098,6 +8108,8 @@ static void update_cpu_capacity(struct sched_domain *sd, int cpu) capacity = 1; cpu_rq(cpu)->cpu_capacity = capacity; + trace_sched_cpu_capacity_tp(cpu_rq(cpu)); + sdg->sgc->capacity = capacity; sdg->sgc->min_capacity = capacity; sdg->sgc->max_capacity = capacity; @@ -8957,7 +8969,7 @@ next_group: |