From 1e9f28fa1eb9773bf65bae08288c6a0a38eef4a7 Mon Sep 17 00:00:00 2001 From: "Siddha, Suresh B" Date: Mon, 27 Mar 2006 01:15:22 -0800 Subject: [PATCH] [PATCH] sched: new sched domain for representing multi-core Add a new sched domain for representing multi-core with shared caches between cores. Consider a dual package system, each package containing two cores and with last level cache shared between cores with in a package. If there are two runnable processes, with this appended patch those two processes will be scheduled on different packages. On such systems, with this patch we have observed 8% perf improvement with specJBB(2 warehouse) benchmark and 35% improvement with CFP2000 rate(with 2 users). This new domain will come into play only on multi-core systems with shared caches. On other systems, this sched domain will be removed by domain degeneration code. This new domain can be also used for implementing power savings policy (see OLS 2005 CMP kernel scheduler paper for more details.. I will post another patch for power savings policy soon) Most of the arch/* file changes are for cpu_coregroup_map() implementation. Signed-off-by: Suresh Siddha Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/i386/Kconfig | 9 ++++ arch/i386/kernel/cpu/common.c | 10 ++-- arch/i386/kernel/cpu/intel_cacheinfo.c | 22 +++++++- arch/i386/kernel/smpboot.c | 24 +++++++++ arch/x86_64/Kconfig | 9 ++++ arch/x86_64/kernel/setup.c | 3 +- arch/x86_64/kernel/smpboot.c | 24 +++++++++ include/asm-i386/processor.h | 5 ++ include/asm-i386/topology.h | 2 + include/asm-x86_64/processor.h | 4 ++ include/asm-x86_64/smp.h | 1 + include/asm-x86_64/topology.h | 2 + include/linux/topology.h | 9 ++++ kernel/sched.c | 73 ++++++++++++++++++++++++-- 14 files changed, 186 insertions(+), 11 deletions(-) diff --git a/arch/i386/Kconfig b/arch/i386/Kconfig index f7db71d0b913..f17bd1d2707e 100644 --- a/arch/i386/Kconfig +++ b/arch/i386/Kconfig @@ -231,6 +231,15 @@ config SCHED_SMT cost of slightly increased overhead in some places. If unsure say N here. +config SCHED_MC + bool "Multi-core scheduler support" + depends on SMP + default y + help + Multi-core scheduler support improves the CPU scheduler's decision + making when dealing with multi-core CPU chips at a cost of slightly + increased overhead in some places. If unsure say N here. + source "kernel/Kconfig.preempt" config X86_UP_APIC diff --git a/arch/i386/kernel/cpu/common.c b/arch/i386/kernel/cpu/common.c index 7e3d6b6a4e96..a06a49075f10 100644 --- a/arch/i386/kernel/cpu/common.c +++ b/arch/i386/kernel/cpu/common.c @@ -266,7 +266,7 @@ static void __init early_cpu_detect(void) void __cpuinit generic_identify(struct cpuinfo_x86 * c) { u32 tfms, xlvl; - int junk; + int ebx; if (have_cpuid_p()) { /* Get vendor name */ @@ -282,7 +282,7 @@ void __cpuinit generic_identify(struct cpuinfo_x86 * c) /* Intel-defined flags: level 0x00000001 */ if ( c->cpuid_level >= 0x00000001 ) { u32 capability, excap; - cpuid(0x00000001, &tfms, &junk, &excap, &capability); + cpuid(0x00000001, &tfms, &ebx, &excap, &capability); c->x86_capability[0] = capability; c->x86_capability[4] = excap; c->x86 = (tfms >> 8) & 15; @@ -292,6 +292,11 @@ void __cpuinit generic_identify(struct cpuinfo_x86 * c) if (c->x86 >= 0x6) c->x86_model += ((tfms >> 16) & 0xF) << 4; c->x86_mask = tfms & 15; +#ifdef CONFIG_SMP + c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0); +#else + c->apicid = (ebx >> 24) & 0xFF; +#endif } else { /* Have CPUID level 0 only - unheard of */ c->x86 = 4; @@ -474,7 +479,6 @@ void __cpuinit detect_ht(struct cpuinfo_x86 *c) cpuid(1, &eax, &ebx, &ecx, &edx); - c->apicid = phys_pkg_id((ebx >> 24) & 0xFF, 0); if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY)) return; diff --git a/arch/i386/kernel/cpu/intel_cacheinfo.c b/arch/i386/kernel/cpu/intel_cacheinfo.c index ce61921369e5..7e7fd4e67dd0 100644 --- a/arch/i386/kernel/cpu/intel_cacheinfo.c +++ b/arch/i386/kernel/cpu/intel_cacheinfo.c @@ -173,6 +173,10 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) unsigned int trace = 0, l1i = 0, l1d = 0, l2 = 0, l3 = 0; /* Cache sizes */ unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */ unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */ + unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb; +#ifdef CONFIG_SMP + unsigned int cpu = (c == &boot_cpu_data) ? 0 : (c - cpu_data); +#endif if (c->cpuid_level > 3) { static int is_initialized; @@ -205,9 +209,15 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) break; case 2: new_l2 = this_leaf.size/1024; + num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + l2_id = c->apicid >> index_msb; break; case 3: new_l3 = this_leaf.size/1024; + num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing; + index_msb = get_count_order(num_threads_sharing); + l3_id = c->apicid >> index_msb; break; default: break; @@ -273,11 +283,19 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c) if (new_l1i) l1i = new_l1i; - if (new_l2) + if (new_l2) { l2 = new_l2; +#ifdef CONFIG_SMP + cpu_llc_id[cpu] = l2_id; +#endif + } - if (new_l3) + if (new_l3) { l3 = new_l3; +#ifdef CONFIG_SMP + cpu_llc_id[cpu] = l3_id; +#endif + } if ( trace ) printk (KERN_INFO "CPU: Trace cache: %dK uops", trace); diff --git a/arch/i386/kernel/smpboot.c b/arch/i386/kernel/smpboot.c index 82371d83bfa9..a6969903f2d6 100644 --- a/arch/i386/kernel/smpboot.c +++ b/arch/i386/kernel/smpboot.c @@ -72,6 +72,9 @@ int phys_proc_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID}; /* Core ID of each logical CPU */ int cpu_core_id[NR_CPUS] __read_mostly = {[0 ... NR_CPUS-1] = BAD_APICID}; +/* Last level cache ID of each logical CPU */ +int cpu_llc_id[NR_CPUS] __cpuinitdata = {[0 ... NR_CPUS-1] = BAD_APICID}; + /* representing HT siblings of each logical CPU */ cpumask_t cpu_sibling_map[NR_CPUS] __read_mostly; EXPORT_SYMBOL(cpu_sibling_map); @@ -440,6 +443,18 @@ static void __devinit smp_callin(void) static int cpucount; +/* maps the cpu to the sched domain representing multi-core */ +cpumask_t cpu_coregroup_map(int cpu) +{ + struct cpuinfo_x86 *c = cpu_data + cpu; + /* + * For perf, we return last level cache shared map. + * TBD: when power saving sched policy is added, we will return + * cpu_core_map when power saving policy is enabled + */ + return c->llc_shared_map; +} + /* representing cpus for which sibling maps can be computed */ static cpumask_t cpu_sibling_setup_map; @@ -459,12 +474,16 @@ set_cpu_sibling_map(int cpu) cpu_set(cpu, cpu_sibling_map[i]); cpu_set(i, cpu_core_map[cpu]); cpu_set(cpu, cpu_core_map[i]); + cpu_set(i, c[cpu].llc_shared_map); + cpu_set(cpu, c[i].llc_shared_map); } } } else { cpu_set(cpu, cpu_sibling_map[cpu]); } + cpu_set(cpu, c[cpu].llc_shared_map); + if (current_cpu_data.x86_max_cores == 1) { cpu_core_map[cpu] = cpu_sibling_map[cpu]; c[cpu].booted_cores = 1; @@ -472,6 +491,11 @@ set_cpu_sibling_map(int cpu) } for_each_cpu_mask(i, cpu_sibling_setup_map) { + if (cpu_llc_id[cpu] != BAD_APICID && + cpu_llc_id[cpu] == cpu_llc_id[i]) { + cpu_set(i, c[cpu].llc_shared_map); + cpu_set(cpu, c[i].llc_shared_map); + } if (phys_proc_id[cpu] == phys_proc_id[i]) { cpu_set(i, cpu_core_map[cpu]); cpu_set(cpu, cpu_core_map[i]); diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig index 45efe0ca88f8..1cb4aa241c8c 100644 --- a/arch/x86_64/Kconfig +++ b/arch/x86_64/Kconfig @@ -250,6 +250,15 @@ config SCHED_SMT cost of slightly increased overhead in some places. If unsure say N here. +config SCHED_MC + bool "Multi-core scheduler support" + depends on SMP + default y + help + Multi-core scheduler support improves the CPU scheduler's decision + making when dealing with multi-core CPU chips at a cost of slightly + increased overhead in some places. If unsure say N here. + source "kernel/Kconfig.preempt" config NUMA diff --git a/arch/x86_64/kernel/setup.c b/arch/x86_64/kernel/setup.c index a57eec8311a7..d1f3e9272c05 100644 --- a/arch/x86_64/kernel/setup.c +++ b/arch/x86_64/kernel/setup.c @@ -962,7 +962,6 @@ static void __cpuinit detect_ht(struct cpuinfo_x86 *c) cpuid(1, &eax, &ebx, &ecx, &edx); - c->apicid = phys_pkg_id(0); if (!cpu_has(c, X86_FEATURE_HT) || cpu_has(c, X86_FEATURE_CMP_LEGACY)) return; @@ -1171,6 +1170,8 @@ void __cpuinit identify_cpu(struct cpuinfo_x86 *c) c->x86_capability[2] = cpuid_edx(0x80860001); } + c->apicid = phys_pkg_id(0); + /* * Vendor-specific initialization. In this section we * canonicalize the feature flags, meaning if there are diff --git a/arch/x86_64/kernel/smpboot.c b/arch/x86_64/kernel/smpboot.c index 66e98659d077..ea48fa638070 100644 --- a/arch/x86_64/kernel/smpboot.c +++ b/arch/x86_64/kernel/smpboot.c @@ -68,6 +68,9 @@ u8 phys_proc_id[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID }; /* core ID of each logical CPU */ u8 cpu_core_id[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = BAD_APICID }; +/* Last level cache ID of each logical CPU */ +u8 cpu_llc_id[NR_CPUS] __cpuinitdata = {[0 ... NR_CPUS-1] = BAD_APICID}; + /* Bitmask of currently online CPUs */ cpumask_t cpu_online_map __read_mostly; @@ -445,6 +448,18 @@ void __cpuinit smp_callin(void) cpu_set(cpuid, cpu_callin_map); } +/* maps the cpu to the sched domain representing multi-core */ +cpumask_t cpu_coregroup_map(int cpu) +{ + struct cpuinfo_x86 *c = cpu_data + cpu; + /* + * For perf, we return last level cache shared map. + * TBD: when power saving sched policy is added, we will return + * cpu_core_map when power saving policy is enabled + */ + return c->llc_shared_map; +} + /* representing cpus for which sibling maps can be computed */ static cpumask_t cpu_sibling_setup_map; @@ -463,12 +478,16 @@ static inline void set_cpu_sibling_map(int cpu) cpu_set(cpu, cpu_sibling_map[i]); cpu_set(i, cpu_core_map[cpu]); cpu_set(cpu, cpu_core_map[i]); + cpu_set(i, c[cpu].llc_shared_map); + cpu_set(cpu, c[i].llc_shared_map); } } } else { cpu_set(cpu, cpu_sibling_map[cpu]); } + cpu_set(cpu, c[cpu].llc_shared_map); + if (current_cpu_data.x86_max_cores == 1) { cpu_core_map[cpu] = cpu_sibling_map[cpu]; c[cpu].booted_cores = 1; @@ -476,6 +495,11 @@ static inline void set_cpu_sibling_map(int cpu) } for_each_cpu_mask(i, cpu_sibling_setup_map) { + if (cpu_llc_id[cpu] != BAD_APICID && + cpu_llc_id[cpu] == cpu_llc_id[i]) { + cpu_set(i, c[cpu].llc_shared_map); + cpu_set(cpu, c[i].llc_shared_map); + } if (phys_proc_id[cpu] == phys_proc_id[i]) { cpu_set(i, cpu_core_map[cpu]); cpu_set(cpu, cpu_core_map[i]); diff --git a/include/asm-i386/processor.h b/include/asm-i386/processor.h index feca5d961e2b..af4bfd012475 100644 --- a/include/asm-i386/processor.h +++ b/include/asm-i386/processor.h @@ -20,6 +20,7 @@ #include #include #include +#include /* flag for disabling the tsc */ extern int tsc_disable; @@ -67,6 +68,9 @@ struct cpuinfo_x86 { char pad0; int x86_power; unsigned long loops_per_jiffy; +#ifdef CONFIG_SMP + cpumask_t llc_shared_map; /* cpus sharing the last level cache */ +#endif unsigned char x86_max_cores; /* cpuid returned max cores value */ unsigned char booted_cores; /* number of cores as seen by OS */ unsigned char apicid; @@ -103,6 +107,7 @@ extern struct cpuinfo_x86 cpu_data[]; extern int phys_proc_id[NR_CPUS]; extern int cpu_core_id[NR_CPUS]; +extern int cpu_llc_id[NR_CPUS]; extern char ignore_fpu_irq; extern void identify_cpu(struct cpuinfo_x86 *); diff --git a/include/asm-i386/topology.h b/include/asm-i386/topology.h index aa958c6ee83e..b94e5eeef917 100644 --- a/include/asm-i386/topology.h +++ b/include/asm-i386/topology.h @@ -112,4 +112,6 @@ extern unsigned long node_remap_size[]; #endif /* CONFIG_NUMA */ +extern cpumask_t cpu_coregroup_map(int cpu); + #endif /* _ASM_I386_TOPOLOGY_H */ diff --git a/include/asm-x86_64/processor.h b/include/asm-x86_64/processor.h index 8c8d88c036ed..1aa2cee43344 100644 --- a/include/asm-x86_64/processor.h +++ b/include/asm-x86_64/processor.h @@ -20,6 +20,7 @@ #include #include #include +#include #define TF_MASK 0x00000100 #define IF_MASK 0x00000200 @@ -65,6 +66,9 @@ struct cpuinfo_x86 { __u32 x86_power; __u32 extended_cpuid_level; /* Max extended CPUID function supported */ unsigned long loops_per_jiffy; +#ifdef CONFIG_SMP + cpumask_t llc_shared_map; /* cpus sharing the last level cache */ +#endif __u8 apicid; __u8 booted_cores; /* number of cores as seen by OS */ } ____cacheline_aligned; diff --git a/include/asm-x86_64/smp.h b/include/asm-x86_64/smp.h index 9ccbb2cfd5c0..a4fdaeb5c397 100644 --- a/include/asm-x86_64/smp.h +++ b/include/asm-x86_64/smp.h @@ -56,6 +56,7 @@ extern cpumask_t cpu_sibling_map[NR_CPUS]; extern cpumask_t cpu_core_map[NR_CPUS]; extern u8 phys_proc_id[NR_CPUS]; extern u8 cpu_core_id[NR_CPUS]; +extern u8 cpu_llc_id[NR_CPUS]; #define SMP_TRAMPOLINE_BASE 0x6000 diff --git a/include/asm-x86_64/topology.h b/include/asm-x86_64/topology.h index c642f5d9882d..9db54e9d17bb 100644 --- a/include/asm-x86_64/topology.h +++ b/include/asm-x86_64/topology.h @@ -68,4 +68,6 @@ extern int __node_distance(int, int); #include +extern cpumask_t cpu_coregroup_map(int cpu); + #endif diff --git a/include/linux/topology.h b/include/linux/topology.h index e8eb0040ce3a..a305ae2e44b6 100644 --- a/include/linux/topology.h +++ b/include/linux/topology.h @@ -164,6 +164,15 @@ .nr_balance_failed = 0, \ } +#ifdef CONFIG_SCHED_MC +#ifndef SD_MC_INIT +/* for now its same as SD_CPU_INIT. + * TBD: Tune Domain parameters! + */ +#define SD_MC_INIT SD_CPU_INIT +#endif +#endif + #ifdef CONFIG_NUMA #ifndef SD_NODE_INIT #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!! diff --git a/kernel/sched.c b/kernel/sched.c index a96a05d23262..8a8b71b5751b 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -5574,11 +5574,31 @@ static int cpu_to_cpu_group(int cpu) } #endif +#ifdef CONFIG_SCHED_MC +static DEFINE_PER_CPU(struct sched_domain, core_domains); +static struct sched_group sched_group_core[NR_CPUS]; +#endif + +#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT) +static int cpu_to_core_group(int cpu) +{ + return first_cpu(cpu_sibling_map[cpu]); +} +#elif defined(CONFIG_SCHED_MC) +static int cpu_to_core_group(int cpu) +{ + return cpu; +} +#endif + static DEFINE_PER_CPU(struct sched_domain, phys_domains); static struct sched_group sched_group_phys[NR_CPUS]; static int cpu_to_phys_group(int cpu) { -#ifdef CONFIG_SCHED_SMT +#if defined(CONFIG_SCHED_MC) + cpumask_t mask = cpu_coregroup_map(cpu); + return first_cpu(mask); +#elif defined(CONFIG_SCHED_SMT) return first_cpu(cpu_sibling_map[cpu]); #else return cpu; @@ -5676,6 +5696,17 @@ void build_sched_domains(const cpumask_t *cpu_map) sd->parent = p; sd->groups = &sched_group_phys[group]; +#ifdef CONFIG_SCHED_MC + p = sd; + sd = &per_cpu(core_domains, i); + group = cpu_to_core_group(i); + *sd = SD_MC_INIT; + sd->span = cpu_coregroup_map(i); + cpus_and(sd->span, sd->span, *cpu_map); + sd->parent = p; + sd->groups = &sched_group_core[group]; +#endif + #ifdef CONFIG_SCHED_SMT p = sd; sd = &per_cpu(cpu_domains, i); @@ -5701,6 +5732,19 @@ void build_sched_domains(const cpumask_t *cpu_map) } #endif +#ifdef CONFIG_SCHED_MC + /* Set up multi-core groups */ + for_each_cpu_mask(i, *cpu_map) { + cpumask_t this_core_map = cpu_coregroup_map(i); + cpus_and(this_core_map, this_core_map, *cpu_map); + if (i != first_cpu(this_core_map)) + continue; + init_sched_build_groups(sched_group_core, this_core_map, + &cpu_to_core_group); + } +#endif + + /* Set up physical groups */ for (i = 0; i < MAX_NUMNODES; i++) { cpumask_t nodemask = node_to_cpumask(i); @@ -5797,11 +5841,31 @@ void build_sched_domains(const cpumask_t *cpu_map) power = SCHED_LOAD_SCALE; sd->groups->cpu_power = power; #endif +#ifdef CONFIG_SCHED_MC + sd = &per_cpu(core_domains, i); + power = SCHED_LOAD_SCALE + (cpus_weight(sd->groups->cpumask)-1) + * SCHED_LOAD_SCALE / 10; + sd->groups->cpu_power = power; + sd = &per_cpu(phys_domains, i); + + /* + * This has to be < 2 * SCHED_LOAD_SCALE + * Lets keep it SCHED_LOAD_SCALE, so that + * while calculating NUMA group's cpu_power + * we can simply do + * numa_group->cpu_power += phys_group->cpu_power; + * + * See "only add power once for each physical pkg" + * comment below + */ + sd->groups->cpu_power = SCHED_LOAD_SCALE; +#else sd = &per_cpu(phys_domains, i); power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE * (cpus_weight(sd->groups->cpumask)-1) / 10; sd->groups->cpu_power = power; +#endif #ifdef CONFIG_NUMA sd = &per_cpu(allnodes_domains, i); @@ -5823,7 +5887,6 @@ void build_sched_domains(const cpumask_t *cpu_map) next_sg: for_each_cpu_mask(j, sg->cpumask) { struct sched_domain *sd; - int power; sd = &per_cpu(phys_domains, j); if (j != first_cpu(sd->groups->cpumask)) { @@ -5833,10 +5896,8 @@ next_sg: */ continue; } - power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE * - (cpus_weight(sd->groups->cpumask)-1) / 10; - sg->cpu_power += power; + sg->cpu_power += sd->groups->cpu_power; } sg = sg->next; if (sg != sched_group_nodes[i]) @@ -5849,6 +5910,8 @@ next_sg: struct sched_domain *sd; #ifdef CONFIG_SCHED_SMT sd = &per_cpu(cpu_domains, i); +#elif defined(CONFIG_SCHED_MC) + sd = &per_cpu(core_domains, i); #else sd = &per_cpu(phys_domains, i); #endif