diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-06-03 14:00:15 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-06-03 14:00:15 -0700 |
commit | c84a1e32ee58fc1cc9d3fd42619b917cce67e30a (patch) | |
tree | d3e5bed273f747e7c9e399864219bea76f4c30ea /arch | |
parent | 3d521f9151dacab566904d1f57dcb3e7080cdd8f (diff) | |
parent | 096aa33863a5e48de52d2ff30e0801b7487944f4 (diff) | |
download | op-kernel-dev-c84a1e32ee58fc1cc9d3fd42619b917cce67e30a.zip op-kernel-dev-c84a1e32ee58fc1cc9d3fd42619b917cce67e30a.tar.gz |
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into next
Pull scheduler updates from Ingo Molnar:
"The main scheduling related changes in this cycle were:
- various sched/numa updates, for better performance
- tree wide cleanup of open coded nice levels
- nohz fix related to rq->nr_running use
- cpuidle changes and continued consolidation to improve the
kernel/sched/idle.c high level idle scheduling logic. As part of
this effort I pulled cpuidle driver changes from Rafael as well.
- standardized idle polling amongst architectures
- continued work on preparing better power/energy aware scheduling
- sched/rt updates
- misc fixlets and cleanups"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (49 commits)
sched/numa: Decay ->wakee_flips instead of zeroing
sched/numa: Update migrate_improves/degrades_locality()
sched/numa: Allow task switch if load imbalance improves
sched/rt: Fix 'struct sched_dl_entity' and dl_task_time() comments, to match the current upstream code
sched: Consolidate open coded implementations of nice level frobbing into nice_to_rlimit() and rlimit_to_nice()
sched: Initialize rq->age_stamp on processor start
sched, nohz: Change rq->nr_running to always use wrappers
sched: Fix the rq->next_balance logic in rebalance_domains() and idle_balance()
sched: Use clamp() and clamp_val() to make sys_nice() more readable
sched: Do not zero sg->cpumask and sg->sgp->power in build_sched_groups()
sched/numa: Fix initialization of sched_domain_topology for NUMA
sched: Call select_idle_sibling() when not affine_sd
sched: Simplify return logic in sched_read_attr()
sched: Simplify return logic in sched_copy_attr()
sched: Fix exec_start/task_hot on migrated tasks
arm64: Remove TIF_POLLING_NRFLAG
metag: Remove TIF_POLLING_NRFLAG
sched/idle: Make cpuidle_idle_call() void
sched/idle: Reflow cpuidle_idle_call()
sched/idle: Delay clearing the polling bit
...
Diffstat (limited to 'arch')
-rw-r--r-- | arch/alpha/include/asm/thread_info.h | 4 | ||||
-rw-r--r-- | arch/arm/kernel/topology.c | 26 | ||||
-rw-r--r-- | arch/arm64/include/asm/thread_info.h | 2 | ||||
-rw-r--r-- | arch/ia64/include/asm/thread_info.h | 3 | ||||
-rw-r--r-- | arch/ia64/include/asm/topology.h | 24 | ||||
-rw-r--r-- | arch/metag/include/asm/thread_info.h | 6 | ||||
-rw-r--r-- | arch/powerpc/kernel/smp.c | 31 | ||||
-rw-r--r-- | arch/s390/include/asm/topology.h | 13 | ||||
-rw-r--r-- | arch/s390/kernel/topology.c | 20 | ||||
-rw-r--r-- | arch/tile/include/asm/thread_info.h | 3 | ||||
-rw-r--r-- | arch/tile/include/asm/topology.h | 33 | ||||
-rw-r--r-- | arch/x86/include/asm/thread_info.h | 4 | ||||
-rw-r--r-- | arch/x86/kernel/apm_32.c | 11 |
13 files changed, 80 insertions, 100 deletions
diff --git a/arch/alpha/include/asm/thread_info.h b/arch/alpha/include/asm/thread_info.h index 3d6ce6d..48bbea6 100644 --- a/arch/alpha/include/asm/thread_info.h +++ b/arch/alpha/include/asm/thread_info.h @@ -73,12 +73,14 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define TIF_SYSCALL_AUDIT 4 /* syscall audit active */ #define TIF_DIE_IF_KERNEL 9 /* dik recursion lock */ #define TIF_MEMDIE 13 /* is terminating due to OOM killer */ +#define TIF_POLLING_NRFLAG 14 /* idle is polling for TIF_NEED_RESCHED */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) #define _TIF_SIGPENDING (1<<TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED) #define _TIF_NOTIFY_RESUME (1<<TIF_NOTIFY_RESUME) #define _TIF_SYSCALL_AUDIT (1<<TIF_SYSCALL_AUDIT) +#define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG) /* Work to do on interrupt/exception return. */ #define _TIF_WORK_MASK (_TIF_SIGPENDING | _TIF_NEED_RESCHED | \ @@ -92,8 +94,6 @@ register struct thread_info *__current_thread_info __asm__("$8"); #define TS_UAC_NOFIX 0x0002 /* ! flags as they match */ #define TS_UAC_SIGBUS 0x0004 /* ! userspace part of 'osf_sysinfo' */ #define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal() */ -#define TS_POLLING 0x0010 /* idle task polling need_resched, - skip sending interrupt */ #ifndef __ASSEMBLY__ #define HAVE_SET_RESTORE_SIGMASK 1 diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c index 0bc94b1..71e1fec 100644 --- a/arch/arm/kernel/topology.c +++ b/arch/arm/kernel/topology.c @@ -185,6 +185,15 @@ const struct cpumask *cpu_coregroup_mask(int cpu) return &cpu_topology[cpu].core_sibling; } +/* + * 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; +} + static void update_siblings_masks(unsigned int cpuid) { struct cputopo_arm *cpu_topo, *cpuid_topo = &cpu_topology[cpuid]; @@ -266,6 +275,20 @@ void store_cpu_topology(unsigned int cpuid) cpu_topology[cpuid].socket_id, mpidr); } +static inline const 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 @@ -289,4 +312,7 @@ void __init init_cpu_topology(void) smp_wmb(); parse_dt_topology(); + + /* Set scheduler topology descriptor */ + set_sched_topology(arm_topology); } diff --git a/arch/arm64/include/asm/thread_info.h b/arch/arm64/include/asm/thread_info.h index 720e70b..7b8e3a2 100644 --- a/arch/arm64/include/asm/thread_info.h +++ b/arch/arm64/include/asm/thread_info.h @@ -95,13 +95,11 @@ static inline struct thread_info *current_thread_info(void) * TIF_NEED_RESCHED - rescheduling necessary * TIF_NOTIFY_RESUME - callback before returning to user * TIF_USEDFPU - FPU was used by this task this quantum (SMP) - * TIF_POLLING_NRFLAG - true if poll_idle() is polling TIF_NEED_RESCHED */ #define TIF_SIGPENDING 0 #define TIF_NEED_RESCHED 1 #define TIF_NOTIFY_RESUME 2 /* callback before returning to user */ #define TIF_SYSCALL_TRACE 8 -#define TIF_POLLING_NRFLAG 16 #define TIF_MEMDIE 18 /* is terminating due to OOM killer */ #define TIF_FREEZE 19 #define TIF_RESTORE_SIGMASK 20 diff --git a/arch/ia64/include/asm/thread_info.h b/arch/ia64/include/asm/thread_info.h index 5957cf6..5b17418 100644 --- a/arch/ia64/include/asm/thread_info.h +++ b/arch/ia64/include/asm/thread_info.h @@ -107,6 +107,7 @@ struct thread_info { #define TIF_MCA_INIT 18 /* this task is processing MCA or INIT */ #define TIF_DB_DISABLED 19 /* debug trap disabled for fsyscall */ #define TIF_RESTORE_RSE 21 /* user RBS is newer than kernel RBS */ +#define TIF_POLLING_NRFLAG 22 /* idle is polling for TIF_NEED_RESCHED */ #define _TIF_SYSCALL_TRACE (1 << TIF_SYSCALL_TRACE) #define _TIF_SYSCALL_AUDIT (1 << TIF_SYSCALL_AUDIT) @@ -118,6 +119,7 @@ struct thread_info { #define _TIF_MCA_INIT (1 << TIF_MCA_INIT) #define _TIF_DB_DISABLED (1 << TIF_DB_DISABLED) #define _TIF_RESTORE_RSE (1 << TIF_RESTORE_RSE) +#define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) /* "work to do on user-return" bits */ #define TIF_ALLWORK_MASK (_TIF_SIGPENDING|_TIF_NOTIFY_RESUME|_TIF_SYSCALL_AUDIT|\ @@ -125,7 +127,6 @@ struct thread_info { /* like TIF_ALLWORK_BITS but sans TIF_SYSCALL_TRACE or TIF_SYSCALL_AUDIT */ #define TIF_WORK_MASK (TIF_ALLWORK_MASK&~(_TIF_SYSCALL_TRACE|_TIF_SYSCALL_AUDIT)) -#define TS_POLLING 1 /* true if in idle loop and not sleeping */ #define TS_RESTORE_SIGMASK 2 /* restore signal mask in do_signal() */ #ifndef __ASSEMBLY__ diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h index 5cb55a1..3202aa7 100644 --- a/arch/ia64/include/asm/topology.h +++ b/arch/ia64/include/asm/topology.h @@ -46,30 +46,6 @@ void build_cpu_to_node_map(void); -#define SD_CPU_INIT (struct sched_domain) { \ - .parent = NULL, \ - .child = NULL, \ - .groups = NULL, \ - .min_interval = 1, \ - .max_interval = 4, \ - .busy_factor = 64, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 2, \ - .busy_idx = 2, \ - .idle_idx = 1, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - .flags = SD_LOAD_BALANCE \ - | SD_BALANCE_NEWIDLE \ - | SD_BALANCE_EXEC \ - | SD_BALANCE_FORK \ - | SD_WAKE_AFFINE, \ - .last_balance = jiffies, \ - .balance_interval = 1, \ - .nr_balance_failed = 0, \ -} - #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP diff --git a/arch/metag/include/asm/thread_info.h b/arch/metag/include/asm/thread_info.h index b19e9c5..4771133 100644 --- a/arch/metag/include/asm/thread_info.h +++ b/arch/metag/include/asm/thread_info.h @@ -117,10 +117,8 @@ static inline int kstack_end(void *addr) #define TIF_SECCOMP 5 /* secure computing */ #define TIF_RESTORE_SIGMASK 6 /* restore signal mask in do_signal() */ #define TIF_NOTIFY_RESUME 7 /* callback before returning to user */ -#define TIF_POLLING_NRFLAG 8 /* true if poll_idle() is polling - TIF_NEED_RESCHED */ -#define TIF_MEMDIE 9 /* is terminating due to OOM killer */ -#define TIF_SYSCALL_TRACEPOINT 10 /* syscall tracepoint instrumentation */ +#define TIF_MEMDIE 8 /* is terminating due to OOM killer */ +#define TIF_SYSCALL_TRACEPOINT 9 /* syscall tracepoint instrumentation */ #define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE) diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c index e2a4232..10ffffe 100644 --- a/arch/powerpc/kernel/smp.c +++ b/arch/powerpc/kernel/smp.c @@ -766,6 +766,28 @@ int setup_profiling_timer(unsigned int multiplier) return 0; } +#ifdef CONFIG_SCHED_SMT +/* cpumask of CPUs with asymetric SMT dependancy */ +static const int powerpc_smt_flags(void) +{ + int flags = SD_SHARE_CPUPOWER | SD_SHARE_PKG_RESOURCES; + + if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { + printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); + flags |= SD_ASYM_PACKING; + } + return flags; +} +#endif + +static struct sched_domain_topology_level powerpc_topology[] = { +#ifdef CONFIG_SCHED_SMT + { cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) }, +#endif + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + void __init smp_cpus_done(unsigned int max_cpus) { cpumask_var_t old_mask; @@ -790,15 +812,8 @@ void __init smp_cpus_done(unsigned int max_cpus) dump_numa_cpu_topology(); -} + set_sched_topology(powerpc_topology); -int arch_sd_sibling_asym_packing(void) -{ - if (cpu_has_feature(CPU_FTR_ASYM_SMT)) { - printk_once(KERN_INFO "Enabling Asymmetric SMT scheduling\n"); - return SD_ASYM_PACKING; - } - return 0; } #ifdef CONFIG_HOTPLUG_CPU diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h index 05425b1..56af530 100644 --- a/arch/s390/include/asm/topology.h +++ b/arch/s390/include/asm/topology.h @@ -26,21 +26,12 @@ extern struct cpu_topology_s390 cpu_topology[NR_CPUS]; #define mc_capable() 1 -static inline const struct cpumask *cpu_coregroup_mask(int cpu) -{ - return &cpu_topology[cpu].core_mask; -} - -static inline const struct cpumask *cpu_book_mask(int cpu) -{ - return &cpu_topology[cpu].book_mask; -} - int topology_cpu_init(struct cpu *); int topology_set_cpu_management(int fc); void topology_schedule_update(void); void store_topology(struct sysinfo_15_1_x *info); void topology_expect_change(void); +const struct cpumask *cpu_coregroup_mask(int cpu); #else /* CONFIG_SCHED_BOOK */ @@ -64,8 +55,6 @@ static inline void s390_init_cpu_topology(void) }; #endif -#define SD_BOOK_INIT SD_CPU_INIT - #include <asm-generic/topology.h> #endif /* _ASM_S390_TOPOLOGY_H */ diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index fa3b8cd..355a16c 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -445,6 +445,23 @@ int topology_cpu_init(struct cpu *cpu) return sysfs_create_group(&cpu->dev.kobj, &topology_cpu_attr_group); } +const struct cpumask *cpu_coregroup_mask(int cpu) +{ + return &cpu_topology[cpu].core_mask; +} + +static const struct cpumask *cpu_book_mask(int cpu) +{ + return &cpu_topology[cpu].book_mask; +} + +static struct sched_domain_topology_level s390_topology[] = { + { cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) }, + { cpu_book_mask, SD_INIT_NAME(BOOK) }, + { cpu_cpu_mask, SD_INIT_NAME(DIE) }, + { NULL, }, +}; + static int __init topology_init(void) { if (!MACHINE_HAS_TOPOLOGY) { @@ -453,6 +470,9 @@ static int __init topology_init(void) } set_topology_timer(); out: + + set_sched_topology(s390_topology); + return device_create_file(cpu_subsys.dev_root, &dev_attr_dispatching); } device_initcall(topology_init); diff --git a/arch/tile/include/asm/thread_info.h b/arch/tile/include/asm/thread_info.h index 729aa10..d767ff9 100644 --- a/arch/tile/include/asm/thread_info.h +++ b/arch/tile/include/asm/thread_info.h @@ -129,6 +129,7 @@ extern void _cpu_idle(void); #define TIF_MEMDIE 7 /* OOM killer at work */ #define TIF_NOTIFY_RESUME 8 /* callback before returning to user */ #define TIF_SYSCALL_TRACEPOINT 9 /* syscall tracepoint instrumentation */ +#define TIF_POLLING_NRFLAG 10 /* idle is polling for TIF_NEED_RESCHED */ #define _TIF_SIGPENDING (1<<TIF_SIGPENDING) #define _TIF_NEED_RESCHED (1<<TIF_NEED_RESCHED) @@ -140,6 +141,7 @@ extern void _cpu_idle(void); #define _TIF_MEMDIE (1<<TIF_MEMDIE) #define _TIF_NOTIFY_RESUME (1<<TIF_NOTIFY_RESUME) #define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT) +#define _TIF_POLLING_NRFLAG (1<<TIF_POLLING_NRFLAG) /* Work to do on any return to user space. */ #define _TIF_ALLWORK_MASK \ @@ -162,7 +164,6 @@ extern void _cpu_idle(void); #ifdef __tilegx__ #define TS_COMPAT 0x0001 /* 32-bit compatibility mode */ #endif -#define TS_POLLING 0x0004 /* in idle loop but not sleeping */ #define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal */ #ifndef __ASSEMBLY__ diff --git a/arch/tile/include/asm/topology.h b/arch/tile/include/asm/topology.h index d15c0d8..9383118 100644 --- a/arch/tile/include/asm/topology.h +++ b/arch/tile/include/asm/topology.h @@ -44,39 +44,6 @@ static inline const struct cpumask *cpumask_of_node(int node) /* For now, use numa node -1 for global allocation. */ #define pcibus_to_node(bus) ((void)(bus), -1) -/* - * TILE architecture has many cores integrated in one processor, so we need - * setup bigger balance_interval for both CPU/NODE scheduling domains to - * reduce process scheduling costs. - */ - -/* sched_domains SD_CPU_INIT for TILE architecture */ -#define SD_CPU_INIT (struct sched_domain) { \ - .min_interval = 4, \ - .max_interval = 128, \ - .busy_factor = 64, \ - .imbalance_pct = 125, \ - .cache_nice_tries = 1, \ - .busy_idx = 2, \ - .idle_idx = 1, \ - .newidle_idx = 0, \ - .wake_idx = 0, \ - .forkexec_idx = 0, \ - \ - .flags = 1*SD_LOAD_BALANCE \ - | 1*SD_BALANCE_NEWIDLE \ - | 1*SD_BALANCE_EXEC \ - | 1*SD_BALANCE_FORK \ - | 0*SD_BALANCE_WAKE \ - | 0*SD_WAKE_AFFINE \ - | 0*SD_SHARE_CPUPOWER \ - | 0*SD_SHARE_PKG_RESOURCES \ - | 0*SD_SERIALIZE \ - , \ - .last_balance = jiffies, \ - .balance_interval = 32, \ -} - /* By definition, we create nodes based on online memory. */ #define node_has_online_mem(nid) 1 diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 47e5de2..8540538 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -83,6 +83,7 @@ struct thread_info { #define TIF_FORK 18 /* ret_from_fork */ #define TIF_NOHZ 19 /* in adaptive nohz mode */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ +#define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */ @@ -106,6 +107,7 @@ struct thread_info { #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_FORK (1 << TIF_FORK) #define _TIF_NOHZ (1 << TIF_NOHZ) +#define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP) @@ -191,8 +193,6 @@ static inline struct thread_info *current_thread_info(void) * have to worry about atomic accesses. */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ -#define TS_POLLING 0x0004 /* idle task polling need_resched, - skip sending interrupt */ #define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal() */ #ifndef __ASSEMBLY__ diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 3ab0343..f3a1f04 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -844,21 +844,10 @@ static int apm_do_idle(void) int polling; int err = 0; - polling = !!(current_thread_info()->status & TS_POLLING); - if (polling) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - } if (!need_resched()) { idled = 1; ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err); } - if (polling) - current_thread_info()->status |= TS_POLLING; if (!idled) return 0; |