sched: Add book scheduling domain

On top of the SMT and MC scheduling domains this adds the BOOK scheduling
domain. This is useful for NUMA like machines which do not have an interface
which tells which piece of memory is attached to which node or where the
hardware performs striping.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100831082844.253053798@de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1e2a6db2d7dd03466bf850dc5011860c23e8f9c9..b51c53c285b8df7b2ee550f7713759d97f666340 100644 (file)
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -875,6 +875,7 @@ enum sched_domain_level {
        SD_LV_NONE = 0,
        SD_LV_SIBLING,
        SD_LV_MC,
+       SD_LV_BOOK,
        SD_LV_CPU,
        SD_LV_NODE,
        SD_LV_ALLNODES,

diff --git a/include/linux/topology.h b/include/linux/topology.h
index 64e084ff5e5c9a6e68257068821b79110a760f02..b91a40e847d236d9046dc3154a7e7a58ea594776 100644 (file)
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -201,6 +201,12 @@ int arch_update_cpu_topology(void);
        .balance_interval       = 64,                                   \
 }
 
+#ifdef CONFIG_SCHED_BOOK
+#ifndef SD_BOOK_INIT
+#error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!!
+#endif
+#endif /* CONFIG_SCHED_BOOK */
+
 #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 1a0c084b1cf918f88ba79869490f47c2cdfc59f0..26f83e2f1534b4d108be2c7242810177d21e4b76 100644 (file)
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6506,6 +6506,7 @@ struct s_data {
        cpumask_var_t           nodemask;
        cpumask_var_t           this_sibling_map;
        cpumask_var_t           this_core_map;
+       cpumask_var_t           this_book_map;
        cpumask_var_t           send_covered;
        cpumask_var_t           tmpmask;
        struct sched_group      **sched_group_nodes;
@@ -6517,6 +6518,7 @@ enum s_alloc {
        sa_rootdomain,
        sa_tmpmask,
        sa_send_covered,
+       sa_this_book_map,
        sa_this_core_map,
        sa_this_sibling_map,
        sa_nodemask,
@@ -6570,6 +6572,31 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 }
 #endif /* CONFIG_SCHED_MC */
 
+/*
+ * book sched-domains:
+ */
+#ifdef CONFIG_SCHED_BOOK
+static DEFINE_PER_CPU(struct static_sched_domain, book_domains);
+static DEFINE_PER_CPU(struct static_sched_group, sched_group_book);
+
+static int
+cpu_to_book_group(int cpu, const struct cpumask *cpu_map,
+                 struct sched_group **sg, struct cpumask *mask)
+{
+       int group = cpu;
+#ifdef CONFIG_SCHED_MC
+       cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
+       group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_SMT)
+       cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
+       group = cpumask_first(mask);
+#endif
+       if (sg)
+               *sg = &per_cpu(sched_group_book, group).sg;
+       return group;
+}
+#endif /* CONFIG_SCHED_BOOK */
+
 static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);
 
@@ -6578,7 +6605,10 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
                  struct sched_group **sg, struct cpumask *mask)
 {
        int group;
-#ifdef CONFIG_SCHED_MC
+#ifdef CONFIG_SCHED_BOOK
+       cpumask_and(mask, cpu_book_mask(cpu), cpu_map);
+       group = cpumask_first(mask);
+#elif defined(CONFIG_SCHED_MC)
        cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
        group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
@@ -6839,6 +6869,9 @@ SD_INIT_FUNC(CPU)
 #ifdef CONFIG_SCHED_MC
  SD_INIT_FUNC(MC)
 #endif
+#ifdef CONFIG_SCHED_BOOK
+ SD_INIT_FUNC(BOOK)
+#endif
 
 static int default_relax_domain_level = -1;
 
@@ -6888,6 +6921,8 @@ static void __free_domain_allocs(struct s_data *d, enum s_alloc what,
                free_cpumask_var(d->tmpmask); /* fall through */
        case sa_send_covered:
                free_cpumask_var(d->send_covered); /* fall through */
+       case sa_this_book_map:
+               free_cpumask_var(d->this_book_map); /* fall through */
        case sa_this_core_map:
                free_cpumask_var(d->this_core_map); /* fall through */
        case sa_this_sibling_map:
@@ -6934,8 +6969,10 @@ static enum s_alloc __visit_domain_allocation_hell(struct s_data *d,
                return sa_nodemask;
        if (!alloc_cpumask_var(&d->this_core_map, GFP_KERNEL))
                return sa_this_sibling_map;
-       if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+       if (!alloc_cpumask_var(&d->this_book_map, GFP_KERNEL))
                return sa_this_core_map;
+       if (!alloc_cpumask_var(&d->send_covered, GFP_KERNEL))
+               return sa_this_book_map;
        if (!alloc_cpumask_var(&d->tmpmask, GFP_KERNEL))
                return sa_send_covered;
        d->rd = alloc_rootdomain();
@@ -6993,6 +7030,23 @@ static struct sched_domain *__build_cpu_sched_domain(struct s_data *d,
        return sd;
 }
 
+static struct sched_domain *__build_book_sched_domain(struct s_data *d,
+       const struct cpumask *cpu_map, struct sched_domain_attr *attr,
+       struct sched_domain *parent, int i)
+{
+       struct sched_domain *sd = parent;
+#ifdef CONFIG_SCHED_BOOK
+       sd = &per_cpu(book_domains, i).sd;
+       SD_INIT(sd, BOOK);
+       set_domain_attribute(sd, attr);
+       cpumask_and(sched_domain_span(sd), cpu_map, cpu_book_mask(i));
+       sd->parent = parent;
+       parent->child = sd;
+       cpu_to_book_group(i, cpu_map, &sd->groups, d->tmpmask);
+#endif
+       return sd;
+}
+
 static struct sched_domain *__build_mc_sched_domain(struct s_data *d,
        const struct cpumask *cpu_map, struct sched_domain_attr *attr,
        struct sched_domain *parent, int i)
@@ -7049,6 +7103,15 @@ static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
                                                &cpu_to_core_group,
                                                d->send_covered, d->tmpmask);
                break;
+#endif
+#ifdef CONFIG_SCHED_BOOK
+       case SD_LV_BOOK: /* set up book groups */
+               cpumask_and(d->this_book_map, cpu_map, cpu_book_mask(cpu));
+               if (cpu == cpumask_first(d->this_book_map))
+                       init_sched_build_groups(d->this_book_map, cpu_map,
+                                               &cpu_to_book_group,
+                                               d->send_covered, d->tmpmask);
+               break;
 #endif
        case SD_LV_CPU: /* set up physical groups */
                cpumask_and(d->nodemask, cpumask_of_node(cpu), cpu_map);
@@ -7097,12 +7160,14 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 
                sd = __build_numa_sched_domains(&d, cpu_map, attr, i);
                sd = __build_cpu_sched_domain(&d, cpu_map, attr, sd, i);
+               sd = __build_book_sched_domain(&d, cpu_map, attr, sd, i);
                sd = __build_mc_sched_domain(&d, cpu_map, attr, sd, i);
                sd = __build_smt_sched_domain(&d, cpu_map, attr, sd, i);
        }
 
        for_each_cpu(i, cpu_map) {
                build_sched_groups(&d, SD_LV_SIBLING, cpu_map, i);
+               build_sched_groups(&d, SD_LV_BOOK, cpu_map, i);
                build_sched_groups(&d, SD_LV_MC, cpu_map, i);
        }
 
@@ -7133,6 +7198,12 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
                init_sched_groups_power(i, sd);
        }
 #endif
+#ifdef CONFIG_SCHED_BOOK
+       for_each_cpu(i, cpu_map) {
+               sd = &per_cpu(book_domains, i).sd;
+               init_sched_groups_power(i, sd);
+       }
+#endif
 
        for_each_cpu(i, cpu_map) {
                sd = &per_cpu(phys_domains, i).sd;
@@ -7158,6 +7229,8 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
                sd = &per_cpu(cpu_domains, i).sd;
 #elif defined(CONFIG_SCHED_MC)
                sd = &per_cpu(core_domains, i).sd;
+#elif defined(CONFIG_SCHED_BOOK)
+               sd = &per_cpu(book_domains, i).sd;
 #else
                sd = &per_cpu(phys_domains, i).sd;
 #endif