[PATCH V2 0/4] sched: add new 'book' scheduling domain

[PATCH V2 0/4] sched: add new 'book' scheduling domain

[Heiko Carstens]

This patch set adds (yet) another scheduling domain to the scheduler. The
reason for this is that the recent (s390) z196 architecture has four cache
levels and uniform memory access (sort of -- see below).
The cpu/cache/memory hierarchy is as follows:

Each cpu has its private L1 (64KB I-cache + 128KB D-cache) and L2 (1.5MB)
cache.
A core consists of four cpus with a 24MB shared L3 cache.
A book consists of six cores with a 192MB shared L4 cache.

The z196 architecture has no SMT.
Also the statement that we have uniform memory access is not entirely
correct. Actually the machine uses memory striping, so it "looks" like
we have UMA until the next slice of memory gets accessed.
However there is no interface which tells us which piece of memory is local
or remote. So we (have to) simplify and assume that the cost of each memory
access with L4 cache miss is the same.

In order to somehow use the information about the cache hierarchy so that
the scheduler can make some decisions that improves cache hits I added the
'BOOK' scheduling domain between the MC and CPU domains.

Also please note that the s390 arch scheduling domain initializers need
tuning:
The line
#define SD_BOOK_INIT SD_CPU_INIT
within the arch support patch is just there so it compiles and until we have
something that really works.


Changes since V1:

Removed powersavings sysfs knob for the new scheduling domain since Peter
objected to it ;)
Actually adding a third sysfs powersavings knob would increase the config
space to 27 possible settings. That's simply too much and indeed no admin
would care about fine tuning that.
What is needed is a single knob which configures the scheduler to do the
'right thing'.
It's up to the powersavings guys to come up with a viable solution here ;)

[PATCH V2 1/4] sched: merge cpu_to_core_group functions

[Heiko Carstens]

[-- Attachment #1: 01-sched-cputocore.diff --]
[-- Type: text/plain, Size: 1634 bytes --]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

Merge and simplify the two cpu_to_core_group variants so that the
resulting function follows the same pattern like cpu_to_phys_group.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---

 kernel/sched.c |   18 +++++-------------
 1 file changed, 5 insertions(+), 13 deletions(-)

diff -urpN linux-2.6/kernel/sched.c linux-2.6-patched/kernel/sched.c
--- linux-2.6/kernel/sched.c	2010-08-30 11:21:32.000000000 +0200
+++ linux-2.6-patched/kernel/sched.c	2010-08-30 11:21:41.000000000 +0200
@@ -6554,31 +6554,23 @@ cpu_to_cpu_group(int cpu, const struct c
 #ifdef CONFIG_SCHED_MC
 static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
-#endif /* CONFIG_SCHED_MC */
 
-#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
 static int
 cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 		  struct sched_group **sg, struct cpumask *mask)
 {
 	int group;
-
+#ifdef CONFIG_SCHED_SMT
 	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
+#else
+	group = cpu;
+#endif
 	if (sg)
 		*sg = &per_cpu(sched_group_core, group).sg;
 	return group;
 }
-#elif defined(CONFIG_SCHED_MC)
-static int
-cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
-		  struct sched_group **sg, struct cpumask *unused)
-{
-	if (sg)
-		*sg = &per_cpu(sched_group_core, cpu).sg;
-	return cpu;
-}
-#endif
+#endif /* CONFIG_SCHED_MC */
 
 static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);

[PATCH V2 2/4] sched: add book scheduling domain

[Heiko Carstens]

[-- Attachment #1: 02-sched-book.diff --]
[-- Type: text/plain, Size: 6665 bytes --]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

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>
---

 include/linux/sched.h    |    1 
 include/linux/topology.h |    6 +++
 kernel/sched.c           |   77 +++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 82 insertions(+), 2 deletions(-)

--- 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,
--- 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!!!
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6508,6 +6508,7 @@ 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;
@@ -6519,6 +6520,7 @@ enum s_alloc {
 	sa_rootdomain,
 	sa_tmpmask,
 	sa_send_covered,
+	sa_this_book_map,
 	sa_this_core_map,
 	sa_this_sibling_map,
 	sa_nodemask,
@@ -6572,6 +6574,31 @@ cpu_to_core_group(int cpu, const struct
 }
 #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);
 
@@ -6580,7 +6607,10 @@ cpu_to_phys_group(int cpu, const struct
 		  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)
@@ -6841,6 +6871,9 @@ 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;
 
@@ -6890,6 +6923,8 @@ static void __free_domain_allocs(struct
 		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:
@@ -6936,8 +6971,10 @@ static enum s_alloc __visit_domain_alloc
 		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();
@@ -6995,6 +7032,23 @@ static struct sched_domain *__build_cpu_
 	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)
@@ -7052,6 +7106,15 @@ static void build_sched_groups(struct s_
 						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);
 		if (!cpumask_empty(d->nodemask))
@@ -7099,12 +7162,14 @@ static int __build_sched_domains(const s
 
 		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);
 	}
 
@@ -7135,6 +7200,12 @@ static int __build_sched_domains(const s
 		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;
@@ -7160,6 +7231,8 @@ static int __build_sched_domains(const s
 		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

[PATCH V2 3/4] topology/sysfs: provide book id and siblings attributes

[Heiko Carstens]

[-- Attachment #1: 03-topology-sysfs-book.diff --]
[-- Type: text/plain, Size: 4483 bytes --]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

Create attributes
/sys/devices/system/cpu/cpuX/topology/book_id
/sys/devices/system/cpu/cpuX/topology/book_siblings
which show the book id and the book siblings of a cpu.

Unlike the attributes for SMT and MC these attributes are only present if
CONFIG_SCHED_BOOK is set. There is no reason to pollute sysfs for every
architecture with unused attributes.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---

 Documentation/cputopology.txt |   23 ++++++++++++++++++++---
 drivers/base/topology.c       |   16 +++++++++++++++-
 2 files changed, 35 insertions(+), 4 deletions(-)

diff -urpN linux-2.6/Documentation/cputopology.txt linux-2.6-patched/Documentation/cputopology.txt
--- linux-2.6/Documentation/cputopology.txt	2010-08-02 00:11:14.000000000 +0200
+++ linux-2.6-patched/Documentation/cputopology.txt	2010-08-30 11:21:42.000000000 +0200
@@ -14,25 +14,39 @@ to /proc/cpuinfo.
 	identifier (rather than the kernel's).  The actual value is
 	architecture and platform dependent.
 
-3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+3) /sys/devices/system/cpu/cpuX/topology/book_id:
+
+	the book ID of cpuX. Typically it is the hardware platform's
+	identifier (rather than the kernel's).	The actual value is
+	architecture and platform dependent.
+
+4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
 	internel kernel map of cpuX's hardware threads within the same
 	core as cpuX
 
-4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
+6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+
+	internal kernel map of cpuX's hardware threads within the same
+	book_id.
+
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 attributes.
+drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
+#define topology_book_id(cpu)
 #define topology_thread_cpumask(cpu)
 #define topology_core_cpumask(cpu)
+#define topology_book_cpumask(cpu)
 
 The type of **_id is int.
 The type of siblings is (const) struct cpumask *.
@@ -45,6 +59,9 @@ not defined by include/asm-XXX/topology.
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
 
+For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
+default definitions for topology_book_id() and topology_book_cpumask().
+
 Additionally, CPU topology information is provided under
 /sys/devices/system/cpu and includes these files.  The internal
 source for the output is in brackets ("[]").
diff -urpN linux-2.6/drivers/base/topology.c linux-2.6-patched/drivers/base/topology.c
--- linux-2.6/drivers/base/topology.c	2010-08-02 00:11:14.000000000 +0200
+++ linux-2.6-patched/drivers/base/topology.c	2010-08-30 11:21:42.000000000 +0200
@@ -45,7 +45,8 @@ static ssize_t show_##name(struct sys_de
 	return sprintf(buf, "%d\n", topology_##name(cpu));	\
 }
 
-#if defined(topology_thread_cpumask) || defined(topology_core_cpumask)
+#if defined(topology_thread_cpumask) || defined(topology_core_cpumask) || \
+    defined(topology_book_cpumask)
 static ssize_t show_cpumap(int type, const struct cpumask *mask, char *buf)
 {
 	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
@@ -114,6 +115,14 @@ define_siblings_show_func(core_cpumask);
 define_one_ro_named(core_siblings, show_core_cpumask);
 define_one_ro_named(core_siblings_list, show_core_cpumask_list);
 
+#ifdef CONFIG_SCHED_BOOK
+define_id_show_func(book_id);
+define_one_ro(book_id);
+define_siblings_show_func(book_cpumask);
+define_one_ro_named(book_siblings, show_book_cpumask);
+define_one_ro_named(book_siblings_list, show_book_cpumask_list);
+#endif
+
 static struct attribute *default_attrs[] = {
 	&attr_physical_package_id.attr,
 	&attr_core_id.attr,
@@ -121,6 +130,11 @@ static struct attribute *default_attrs[]
 	&attr_thread_siblings_list.attr,
 	&attr_core_siblings.attr,
 	&attr_core_siblings_list.attr,
+#ifdef CONFIG_SCHED_BOOK
+	&attr_book_id.attr,
+	&attr_book_siblings.attr,
+	&attr_book_siblings_list.attr,
+#endif
 	NULL
 };
 

[PATCH V2 4/4] topology: add z11 cpu topology support

[Heiko Carstens]

[-- Attachment #1: 04-topology-z196.diff --]
[-- Type: text/plain, Size: 8508 bytes --]

From: Heiko Carstens <heiko.carstens@de.ibm.com>

Use the extended cpu topology information that z11 machines provide
to improve the scheduler's decision making.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
---

 arch/s390/Kconfig                |    7 +
 arch/s390/include/asm/topology.h |   27 +++++--
 arch/s390/kernel/topology.c      |  150 ++++++++++++++++++++++++---------------
 3 files changed, 123 insertions(+), 61 deletions(-)

--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -3,15 +3,32 @@
 
 #include <linux/cpumask.h>
 
-#define mc_capable()	(1)
-
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
-
 extern unsigned char cpu_core_id[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 
+static inline const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+{
+	return &cpu_core_map[cpu];
+}
+
 #define topology_core_id(cpu)		(cpu_core_id[cpu])
 #define topology_core_cpumask(cpu)	(&cpu_core_map[cpu])
+#define mc_capable()			(1)
+
+#ifdef CONFIG_SCHED_BOOK
+
+extern unsigned char cpu_book_id[NR_CPUS];
+extern cpumask_t cpu_book_map[NR_CPUS];
+
+static inline const struct cpumask *cpu_book_mask(unsigned int cpu)
+{
+	return &cpu_book_map[cpu];
+}
+
+#define topology_book_id(cpu)		(cpu_book_id[cpu])
+#define topology_book_cpumask(cpu)	(&cpu_book_map[cpu])
+
+#endif /* CONFIG_SCHED_BOOK */
 
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);
@@ -30,6 +47,8 @@ static inline void s390_init_cpu_topolog
 };
 #endif
 
+#define SD_BOOK_INIT	SD_CPU_INIT
+
 #include <asm-generic/topology.h>
 
 #endif /* _ASM_S390_TOPOLOGY_H */
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -198,6 +198,13 @@ config HOTPLUG_CPU
 	  can be controlled through /sys/devices/system/cpu/cpu#.
 	  Say N if you want to disable CPU hotplug.
 
+config SCHED_BOOK
+	bool "Book scheduler support"
+	depends on SMP
+	help
+	  Book scheduler support improves the CPU scheduler's decision making
+	  when dealing with machines that have several books.
+
 config MATHEMU
 	bool "IEEE FPU emulation"
 	depends on MARCH_G5
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -57,8 +57,8 @@ struct tl_info {
 	union tl_entry tle[0];
 };
 
-struct core_info {
-	struct core_info *next;
+struct mask_info {
+	struct mask_info *next;
 	unsigned char id;
 	cpumask_t mask;
 };
@@ -66,7 +66,6 @@ struct core_info {
 static int topology_enabled;
 static void topology_work_fn(struct work_struct *work);
 static struct tl_info *tl_info;
-static struct core_info core_info;
 static int machine_has_topology;
 static struct timer_list topology_timer;
 static void set_topology_timer(void);
@@ -74,38 +73,37 @@ static DECLARE_WORK(topology_work, topol
 /* topology_lock protects the core linked list */
 static DEFINE_SPINLOCK(topology_lock);
 
+static struct mask_info core_info;
 cpumask_t cpu_core_map[NR_CPUS];
 unsigned char cpu_core_id[NR_CPUS];
 
-static cpumask_t cpu_coregroup_map(unsigned int cpu)
+#ifdef CONFIG_SCHED_BOOK
+static struct mask_info book_info;
+cpumask_t cpu_book_map[NR_CPUS];
+unsigned char cpu_book_id[NR_CPUS];
+#endif
+
+static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 {
-	struct core_info *core = &core_info;
-	unsigned long flags;
 	cpumask_t mask;
 
 	cpus_clear(mask);
 	if (!topology_enabled || !machine_has_topology)
 		return cpu_possible_map;
-	spin_lock_irqsave(&topology_lock, flags);
-	while (core) {
-		if (cpu_isset(cpu, core->mask)) {
-			mask = core->mask;
+	while (info) {
+		if (cpu_isset(cpu, info->mask)) {
+			mask = info->mask;
 			break;
 		}
-		core = core->next;
+		info = info->next;
 	}
-	spin_unlock_irqrestore(&topology_lock, flags);
 	if (cpus_empty(mask))
 		mask = cpumask_of_cpu(cpu);
 	return mask;
 }
 
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
-{
-	return &cpu_core_map[cpu];
-}
-
-static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
+static void add_cpus_to_mask(struct tl_cpu *tl_cpu, struct mask_info *book,
+			     struct mask_info *core)
 {
 	unsigned int cpu;
 
@@ -117,23 +115,35 @@ static void add_cpus_to_core(struct tl_c
 
 		rcpu = CPU_BITS - 1 - cpu + tl_cpu->origin;
 		for_each_present_cpu(lcpu) {
-			if (cpu_logical_map(lcpu) == rcpu) {
-				cpu_set(lcpu, core->mask);
-				cpu_core_id[lcpu] = core->id;
-				smp_cpu_polarization[lcpu] = tl_cpu->pp;
-			}
+			if (cpu_logical_map(lcpu) != rcpu)
+				continue;
+#ifdef CONFIG_SCHED_BOOK
+			cpu_set(lcpu, book->mask);
+			cpu_book_id[lcpu] = book->id;
+#endif
+			cpu_set(lcpu, core->mask);
+			cpu_core_id[lcpu] = core->id;
+			smp_cpu_polarization[lcpu] = tl_cpu->pp;
 		}
 	}
 }
 
-static void clear_cores(void)
+static void clear_masks(void)
 {
-	struct core_info *core = &core_info;
+	struct mask_info *info;
 
-	while (core) {
-		cpus_clear(core->mask);
-		core = core->next;
+	info = &core_info;
+	while (info) {
+		cpus_clear(info->mask);
+		info = info->next;
+	}
+#ifdef CONFIG_SCHED_BOOK
+	info = &book_info;
+	while (info) {
+		cpus_clear(info->mask);
+		info = info->next;
 	}
+#endif
 }
 
 static union tl_entry *next_tle(union tl_entry *tle)
@@ -146,29 +156,36 @@ static union tl_entry *next_tle(union tl
 
 static void tl_to_cores(struct tl_info *info)
 {
+#ifdef CONFIG_SCHED_BOOK
+	struct mask_info *book = &book_info;
+#else
+	struct mask_info *book = NULL;
+#endif
+	struct mask_info *core = &core_info;
 	union tl_entry *tle, *end;
-	struct core_info *core = &core_info;
+
 
 	spin_lock_irq(&topology_lock);
-	clear_cores();
+	clear_masks();
 	tle = info->tle;
 	end = (union tl_entry *)((unsigned long)info + info->length);
 	while (tle < end) {
 		switch (tle->nl) {
-		case 5:
-		case 4:
-		case 3:
+#ifdef CONFIG_SCHED_BOOK
 		case 2:
+			book = book->next;
+			book->id = tle->container.id;
 			break;
+#endif
 		case 1:
 			core = core->next;
 			core->id = tle->container.id;
 			break;
 		case 0:
-			add_cpus_to_core(&tle->cpu, core);
+			add_cpus_to_mask(&tle->cpu, book, core);
 			break;
 		default:
-			clear_cores();
+			clear_masks();
 			machine_has_topology = 0;
 			goto out;
 		}
@@ -221,10 +238,29 @@ int topology_set_cpu_management(int fc)
 
 static void update_cpu_core_map(void)
 {
+	unsigned long flags;
 	int cpu;
 
-	for_each_possible_cpu(cpu)
-		cpu_core_map[cpu] = cpu_coregroup_map(cpu);
+	spin_lock_irqsave(&topology_lock, flags);
+	for_each_possible_cpu(cpu) {
+		cpu_core_map[cpu] = cpu_group_map(&core_info, cpu);
+#ifdef CONFIG_SCHED_BOOK
+		cpu_book_map[cpu] = cpu_group_map(&book_info, cpu);
+#endif
+	}
+	spin_unlock_irqrestore(&topology_lock, flags);
+}
+
+static void store_topology(struct tl_info *info)
+{
+#ifdef CONFIG_SCHED_BOOK
+	int rc;
+
+	rc = stsi(info, 15, 1, 3);
+	if (rc != -ENOSYS)
+		return;
+#endif
+	stsi(info, 15, 1, 2);
 }
 
 int arch_update_cpu_topology(void)
@@ -238,7 +274,7 @@ int arch_update_cpu_topology(void)
 		topology_update_polarization_simple();
 		return 0;
 	}
-	stsi(info, 15, 1, 2);
+	store_topology(info);
 	tl_to_cores(info);
 	update_cpu_core_map();
 	for_each_online_cpu(cpu) {
@@ -299,12 +335,24 @@ out:
 }
 __initcall(init_topology_update);
 
+static void alloc_masks(struct tl_info *info, struct mask_info *mask, int offset)
+{
+	int i, nr_masks;
+
+	nr_masks = info->mag[NR_MAG - offset];
+	for (i = 0; i < info->mnest - offset; i++)
+		nr_masks *= info->mag[NR_MAG - offset - 1 - i];
+	nr_masks = max(nr_masks, 1);
+	for (i = 0; i < nr_masks; i++) {
+		mask->next = alloc_bootmem(sizeof(struct mask_info));
+		mask = mask->next;
+	}
+}
+
 void __init s390_init_cpu_topology(void)
 {
 	unsigned long long facility_bits;
 	struct tl_info *info;
-	struct core_info *core;
-	int nr_cores;
 	int i;
 
 	if (stfle(&facility_bits, 1) <= 0)
@@ -315,25 +363,13 @@ void __init s390_init_cpu_topology(void)
 
 	tl_info = alloc_bootmem_pages(PAGE_SIZE);
 	info = tl_info;
-	stsi(info, 15, 1, 2);
-
-	nr_cores = info->mag[NR_MAG - 2];
-	for (i = 0; i < info->mnest - 2; i++)
-		nr_cores *= info->mag[NR_MAG - 3 - i];
-
+	store_topology(info);
 	pr_info("The CPU configuration topology of the machine is:");
 	for (i = 0; i < NR_MAG; i++)
 		printk(" %d", info->mag[i]);
 	printk(" / %d\n", info->mnest);
-
-	core = &core_info;
-	for (i = 0; i < nr_cores; i++) {
-		core->next = alloc_bootmem(sizeof(struct core_info));
-		core = core->next;
-		if (!core)
-			goto error;
-	}
-	return;
-error:
-	machine_has_topology = 0;
+	alloc_masks(info, &core_info, 2);
+#ifdef CONFIG_SCHED_BOOK
+	alloc_masks(info, &book_info, 3);
+#endif
 }

Re: [PATCH V2 0/4] sched: add new 'book' scheduling domain

[Peter Zijlstra]

On Tue, 2010-08-31 at 10:28 +0200, Heiko Carstens wrote:
> This patch set adds (yet) another scheduling domain to the scheduler. The
> reason for this is that the recent (s390) z196 architecture has four cache
> levels and uniform memory access (sort of -- see below).
> The cpu/cache/memory hierarchy is as follows:
> 
> Each cpu has its private L1 (64KB I-cache + 128KB D-cache) and L2 (1.5MB)
> cache.
> A core consists of four cpus with a 24MB shared L3 cache.
> A book consists of six cores with a 192MB shared L4 cache.
> 
> The z196 architecture has no SMT.
> Also the statement that we have uniform memory access is not entirely
> correct. Actually the machine uses memory striping, so it "looks" like
> we have UMA until the next slice of memory gets accessed.
> However there is no interface which tells us which piece of memory is local
> or remote. So we (have to) simplify and assume that the cost of each memory
> access with L4 cache miss is the same.
> 
> In order to somehow use the information about the cache hierarchy so that
> the scheduler can make some decisions that improves cache hits I added the
> 'BOOK' scheduling domain between the MC and CPU domains.

Took the patches, but the description of the main patch is a bit
wanting, it implies books are useful for NUMA like things when there
isn't any information on where the node boundaries are, which isn't what
you say here, which is that a book is the L4 cache level.

<rant>
Ideally we'd kill all the sd->level stuff and rework the domain creation
like outlined before and simply go by sd->flags domain properties. At
that point you can simply tag this as yet another cache level.
</rant>

[tip:sched/core] sched: Merge cpu_to_core_group functions

[tip-bot for Heiko Carstens]

Commit-ID:  f269893c575167447cc9f6d1867e639fb5b6f0c5
Gitweb:     http://git.kernel.org/tip/f269893c575167447cc9f6d1867e639fb5b6f0c5
Author:     Heiko Carstens <heiko.carstens@de.ibm.com>
AuthorDate: Tue, 31 Aug 2010 10:28:15 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Thu, 9 Sep 2010 20:41:18 +0200

sched: Merge cpu_to_core_group functions

Merge and simplify the two cpu_to_core_group variants so that the
resulting function follows the same pattern like cpu_to_phys_group.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100831082843.953617555@de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 kernel/sched.c |   18 +++++-------------
 1 files changed, 5 insertions(+), 13 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index 8eef8e5..1a0c084 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -6552,31 +6552,23 @@ cpu_to_cpu_group(int cpu, const struct cpumask *cpu_map,
 #ifdef CONFIG_SCHED_MC
 static DEFINE_PER_CPU(struct static_sched_domain, core_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_core);
-#endif /* CONFIG_SCHED_MC */
 
-#if defined(CONFIG_SCHED_MC) && defined(CONFIG_SCHED_SMT)
 static int
 cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 		  struct sched_group **sg, struct cpumask *mask)
 {
 	int group;
-
+#ifdef CONFIG_SCHED_SMT
 	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
+#else
+	group = cpu;
+#endif
 	if (sg)
 		*sg = &per_cpu(sched_group_core, group).sg;
 	return group;
 }
-#elif defined(CONFIG_SCHED_MC)
-static int
-cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
-		  struct sched_group **sg, struct cpumask *unused)
-{
-	if (sg)
-		*sg = &per_cpu(sched_group_core, cpu).sg;
-	return cpu;
-}
-#endif
+#endif /* CONFIG_SCHED_MC */
 
 static DEFINE_PER_CPU(struct static_sched_domain, phys_domains);
 static DEFINE_PER_CPU(struct static_sched_group, sched_group_phys);

[tip:sched/core] sched: Add book scheduling domain

[tip-bot for Heiko Carstens]

Commit-ID:  01a08546af311c065f34727787dd0cc8dc0c216f
Gitweb:     http://git.kernel.org/tip/01a08546af311c065f34727787dd0cc8dc0c216f
Author:     Heiko Carstens <heiko.carstens@de.ibm.com>
AuthorDate: Tue, 31 Aug 2010 10:28:16 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Thu, 9 Sep 2010 20:41:20 +0200

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>
---
 include/linux/sched.h    |    1 +
 include/linux/topology.h |    6 +++
 kernel/sched.c           |   77 ++++++++++++++++++++++++++++++++++++++++++++-
 3 files changed, 82 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1e2a6db..b51c53c 100644
--- 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 64e084f..b91a40e 100644
--- 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 1a0c084..26f83e2 100644
--- 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)
@@ -7050,6 +7104,15 @@ static void build_sched_groups(struct s_data *d, enum sched_domain_level l,
 						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);
 		if (!cpumask_empty(d->nodemask))
@@ -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

[tip:sched/core] topology/sysfs: Provide book id and siblings attributes

[tip-bot for Heiko Carstens]

Commit-ID:  b40d8ed4e42c79f8ed1cf345eed0888f4a2f0678
Gitweb:     http://git.kernel.org/tip/b40d8ed4e42c79f8ed1cf345eed0888f4a2f0678
Author:     Heiko Carstens <heiko.carstens@de.ibm.com>
AuthorDate: Tue, 31 Aug 2010 10:28:17 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Thu, 9 Sep 2010 20:41:25 +0200

topology/sysfs: Provide book id and siblings attributes

Create attributes:

 /sys/devices/system/cpu/cpuX/topology/book_id
 /sys/devices/system/cpu/cpuX/topology/book_siblings

which show the book id and the book siblings of a cpu.

Unlike the attributes for SMT and MC these attributes are only present if
CONFIG_SCHED_BOOK is set. There is no reason to pollute sysfs for every
architecture with unused attributes.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100831082844.435648457@de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 Documentation/cputopology.txt |   23 ++++++++++++++++++++---
 drivers/base/topology.c       |   16 +++++++++++++++-
 2 files changed, 35 insertions(+), 4 deletions(-)

diff --git a/Documentation/cputopology.txt b/Documentation/cputopology.txt
index f1c5c4b..902d315 100644
--- a/Documentation/cputopology.txt
+++ b/Documentation/cputopology.txt
@@ -14,25 +14,39 @@ to /proc/cpuinfo.
 	identifier (rather than the kernel's).  The actual value is
 	architecture and platform dependent.
 
-3) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
+3) /sys/devices/system/cpu/cpuX/topology/book_id:
+
+	the book ID of cpuX. Typically it is the hardware platform's
+	identifier (rather than the kernel's).	The actual value is
+	architecture and platform dependent.
+
+4) /sys/devices/system/cpu/cpuX/topology/thread_siblings:
 
 	internel kernel map of cpuX's hardware threads within the same
 	core as cpuX
 
-4) /sys/devices/system/cpu/cpuX/topology/core_siblings:
+5) /sys/devices/system/cpu/cpuX/topology/core_siblings:
 
 	internal kernel map of cpuX's hardware threads within the same
 	physical_package_id.
 
+6) /sys/devices/system/cpu/cpuX/topology/book_siblings:
+
+	internal kernel map of cpuX's hardware threads within the same
+	book_id.
+
 To implement it in an architecture-neutral way, a new source file,
-drivers/base/topology.c, is to export the 4 attributes.
+drivers/base/topology.c, is to export the 4 or 6 attributes. The two book
+related sysfs files will only be created if CONFIG_SCHED_BOOK is selected.
 
 For an architecture to support this feature, it must define some of
 these macros in include/asm-XXX/topology.h:
 #define topology_physical_package_id(cpu)
 #define topology_core_id(cpu)
+#define topology_book_id(cpu)
 #define topology_thread_cpumask(cpu)
 #define topology_core_cpumask(cpu)
+#define topology_book_cpumask(cpu)
 
 The type of **_id is int.
 The type of siblings is (const) struct cpumask *.
@@ -45,6 +59,9 @@ not defined by include/asm-XXX/topology.h:
 3) thread_siblings: just the given CPU
 4) core_siblings: just the given CPU
 
+For architectures that don't support books (CONFIG_SCHED_BOOK) there are no
+default definitions for topology_book_id() and topology_book_cpumask().
+
 Additionally, CPU topology information is provided under
 /sys/devices/system/cpu and includes these files.  The internal
 source for the output is in brackets ("[]").
diff --git a/drivers/base/topology.c b/drivers/base/topology.c
index 9fc630c..f6f37a0 100644
--- a/drivers/base/topology.c
+++ b/drivers/base/topology.c
@@ -45,7 +45,8 @@ static ssize_t show_##name(struct sys_device *dev,		\
 	return sprintf(buf, "%d\n", topology_##name(cpu));	\
 }
 
-#if defined(topology_thread_cpumask) || defined(topology_core_cpumask)
+#if defined(topology_thread_cpumask) || defined(topology_core_cpumask) || \
+    defined(topology_book_cpumask)
 static ssize_t show_cpumap(int type, const struct cpumask *mask, char *buf)
 {
 	ptrdiff_t len = PTR_ALIGN(buf + PAGE_SIZE - 1, PAGE_SIZE) - buf;
@@ -114,6 +115,14 @@ define_siblings_show_func(core_cpumask);
 define_one_ro_named(core_siblings, show_core_cpumask);
 define_one_ro_named(core_siblings_list, show_core_cpumask_list);
 
+#ifdef CONFIG_SCHED_BOOK
+define_id_show_func(book_id);
+define_one_ro(book_id);
+define_siblings_show_func(book_cpumask);
+define_one_ro_named(book_siblings, show_book_cpumask);
+define_one_ro_named(book_siblings_list, show_book_cpumask_list);
+#endif
+
 static struct attribute *default_attrs[] = {
 	&attr_physical_package_id.attr,
 	&attr_core_id.attr,
@@ -121,6 +130,11 @@ static struct attribute *default_attrs[] = {
 	&attr_thread_siblings_list.attr,
 	&attr_core_siblings.attr,
 	&attr_core_siblings_list.attr,
+#ifdef CONFIG_SCHED_BOOK
+	&attr_book_id.attr,
+	&attr_book_siblings.attr,
+	&attr_book_siblings_list.attr,
+#endif
 	NULL
 };
 

[tip:sched/core] topology, s390: Add z11 cpu topology support

[tip-bot for Heiko Carstens]

Commit-ID:  4cb14bc8c54f8489251d5cba8328cb410ead0cea
Gitweb:     http://git.kernel.org/tip/4cb14bc8c54f8489251d5cba8328cb410ead0cea
Author:     Heiko Carstens <heiko.carstens@de.ibm.com>
AuthorDate: Tue, 31 Aug 2010 10:28:18 +0200
Committer:  Ingo Molnar <mingo@elte.hu>
CommitDate: Thu, 9 Sep 2010 20:41:55 +0200

topology, s390: Add z11 cpu topology support

Use the extended cpu topology information that z11 machines provide
to improve the scheduler's decision making.

Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100831082844.604956770@de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
---
 arch/s390/Kconfig                |    7 ++
 arch/s390/include/asm/topology.h |   27 ++++++-
 arch/s390/kernel/topology.c      |  150 +++++++++++++++++++++++--------------
 3 files changed, 123 insertions(+), 61 deletions(-)

diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index f0777a4..74a2f1b 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -198,6 +198,13 @@ config HOTPLUG_CPU
 	  can be controlled through /sys/devices/system/cpu/cpu#.
 	  Say N if you want to disable CPU hotplug.
 
+config SCHED_BOOK
+	bool "Book scheduler support"
+	depends on SMP
+	help
+	  Book scheduler support improves the CPU scheduler's decision making
+	  when dealing with machines that have several books.
+
 config MATHEMU
 	bool "IEEE FPU emulation"
 	depends on MARCH_G5
diff --git a/arch/s390/include/asm/topology.h b/arch/s390/include/asm/topology.h
index 831bd03..051107a 100644
--- a/arch/s390/include/asm/topology.h
+++ b/arch/s390/include/asm/topology.h
@@ -3,15 +3,32 @@
 
 #include <linux/cpumask.h>
 
-#define mc_capable()	(1)
-
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu);
-
 extern unsigned char cpu_core_id[NR_CPUS];
 extern cpumask_t cpu_core_map[NR_CPUS];
 
+static inline const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
+{
+	return &cpu_core_map[cpu];
+}
+
 #define topology_core_id(cpu)		(cpu_core_id[cpu])
 #define topology_core_cpumask(cpu)	(&cpu_core_map[cpu])
+#define mc_capable()			(1)
+
+#ifdef CONFIG_SCHED_BOOK
+
+extern unsigned char cpu_book_id[NR_CPUS];
+extern cpumask_t cpu_book_map[NR_CPUS];
+
+static inline const struct cpumask *cpu_book_mask(unsigned int cpu)
+{
+	return &cpu_book_map[cpu];
+}
+
+#define topology_book_id(cpu)		(cpu_book_id[cpu])
+#define topology_book_cpumask(cpu)	(&cpu_book_map[cpu])
+
+#endif /* CONFIG_SCHED_BOOK */
 
 int topology_set_cpu_management(int fc);
 void topology_schedule_update(void);
@@ -30,6 +47,8 @@ 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 bcef007..13559c9 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -57,8 +57,8 @@ struct tl_info {
 	union tl_entry tle[0];
 };
 
-struct core_info {
-	struct core_info *next;
+struct mask_info {
+	struct mask_info *next;
 	unsigned char id;
 	cpumask_t mask;
 };
@@ -66,7 +66,6 @@ struct core_info {
 static int topology_enabled;
 static void topology_work_fn(struct work_struct *work);
 static struct tl_info *tl_info;
-static struct core_info core_info;
 static int machine_has_topology;
 static struct timer_list topology_timer;
 static void set_topology_timer(void);
@@ -74,38 +73,37 @@ static DECLARE_WORK(topology_work, topology_work_fn);
 /* topology_lock protects the core linked list */
 static DEFINE_SPINLOCK(topology_lock);
 
+static struct mask_info core_info;
 cpumask_t cpu_core_map[NR_CPUS];
 unsigned char cpu_core_id[NR_CPUS];
 
-static cpumask_t cpu_coregroup_map(unsigned int cpu)
+#ifdef CONFIG_SCHED_BOOK
+static struct mask_info book_info;
+cpumask_t cpu_book_map[NR_CPUS];
+unsigned char cpu_book_id[NR_CPUS];
+#endif
+
+static cpumask_t cpu_group_map(struct mask_info *info, unsigned int cpu)
 {
-	struct core_info *core = &core_info;
-	unsigned long flags;
 	cpumask_t mask;
 
 	cpus_clear(mask);
 	if (!topology_enabled || !machine_has_topology)
 		return cpu_possible_map;
-	spin_lock_irqsave(&topology_lock, flags);
-	while (core) {
-		if (cpu_isset(cpu, core->mask)) {
-			mask = core->mask;
+	while (info) {
+		if (cpu_isset(cpu, info->mask)) {
+			mask = info->mask;
 			break;
 		}
-		core = core->next;
+		info = info->next;
 	}
-	spin_unlock_irqrestore(&topology_lock, flags);
 	if (cpus_empty(mask))
 		mask = cpumask_of_cpu(cpu);
 	return mask;
 }
 
-const struct cpumask *cpu_coregroup_mask(unsigned int cpu)
-{
-	return &cpu_core_map[cpu];
-}
-
-static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
+static void add_cpus_to_mask(struct tl_cpu *tl_cpu, struct mask_info *book,
+			     struct mask_info *core)
 {
 	unsigned int cpu;
 
@@ -117,23 +115,35 @@ static void add_cpus_to_core(struct tl_cpu *tl_cpu, struct core_info *core)
 
 		rcpu = CPU_BITS - 1 - cpu + tl_cpu->origin;
 		for_each_present_cpu(lcpu) {
-			if (cpu_logical_map(lcpu) == rcpu) {
-				cpu_set(lcpu, core->mask);
-				cpu_core_id[lcpu] = core->id;
-				smp_cpu_polarization[lcpu] = tl_cpu->pp;
-			}
+			if (cpu_logical_map(lcpu) != rcpu)
+				continue;
+#ifdef CONFIG_SCHED_BOOK
+			cpu_set(lcpu, book->mask);
+			cpu_book_id[lcpu] = book->id;
+#endif
+			cpu_set(lcpu, core->mask);
+			cpu_core_id[lcpu] = core->id;
+			smp_cpu_polarization[lcpu] = tl_cpu->pp;
 		}
 	}
 }
 
-static void clear_cores(void)
+static void clear_masks(void)
 {
-	struct core_info *core = &core_info;
+	struct mask_info *info;
 
-	while (core) {
-		cpus_clear(core->mask);
-		core = core->next;
+	info = &core_info;
+	while (info) {
+		cpus_clear(info->mask);
+		info = info->next;
+	}
+#ifdef CONFIG_SCHED_BOOK
+	info = &book_info;
+	while (info) {
+		cpus_clear(info->mask);
+		info = info->next;
 	}
+#endif
 }
 
 static union tl_entry *next_tle(union tl_entry *tle)
@@ -146,29 +156,36 @@ static union tl_entry *next_tle(union tl_entry *tle)
 
 static void tl_to_cores(struct tl_info *info)
 {
+#ifdef CONFIG_SCHED_BOOK
+	struct mask_info *book = &book_info;
+#else
+	struct mask_info *book = NULL;
+#endif
+	struct mask_info *core = &core_info;
 	union tl_entry *tle, *end;
-	struct core_info *core = &core_info;
+
 
 	spin_lock_irq(&topology_lock);
-	clear_cores();
+	clear_masks();
 	tle = info->tle;
 	end = (union tl_entry *)((unsigned long)info + info->length);
 	while (tle < end) {
 		switch (tle->nl) {
-		case 5:
-		case 4:
-		case 3:
+#ifdef CONFIG_SCHED_BOOK
 		case 2:
+			book = book->next;
+			book->id = tle->container.id;
 			break;
+#endif
 		case 1:
 			core = core->next;
 			core->id = tle->container.id;
 			break;
 		case 0:
-			add_cpus_to_core(&tle->cpu, core);
+			add_cpus_to_mask(&tle->cpu, book, core);
 			break;
 		default:
-			clear_cores();
+			clear_masks();
 			machine_has_topology = 0;
 			goto out;
 		}
@@ -221,10 +238,29 @@ int topology_set_cpu_management(int fc)
 
 static void update_cpu_core_map(void)
 {
+	unsigned long flags;
 	int cpu;
 
-	for_each_possible_cpu(cpu)
-		cpu_core_map[cpu] = cpu_coregroup_map(cpu);
+	spin_lock_irqsave(&topology_lock, flags);
+	for_each_possible_cpu(cpu) {
+		cpu_core_map[cpu] = cpu_group_map(&core_info, cpu);
+#ifdef CONFIG_SCHED_BOOK
+		cpu_book_map[cpu] = cpu_group_map(&book_info, cpu);
+#endif
+	}
+	spin_unlock_irqrestore(&topology_lock, flags);
+}
+
+static void store_topology(struct tl_info *info)
+{
+#ifdef CONFIG_SCHED_BOOK
+	int rc;
+
+	rc = stsi(info, 15, 1, 3);
+	if (rc != -ENOSYS)
+		return;
+#endif
+	stsi(info, 15, 1, 2);
 }
 
 int arch_update_cpu_topology(void)
@@ -238,7 +274,7 @@ int arch_update_cpu_topology(void)
 		topology_update_polarization_simple();
 		return 0;
 	}
-	stsi(info, 15, 1, 2);
+	store_topology(info);
 	tl_to_cores(info);
 	update_cpu_core_map();
 	for_each_online_cpu(cpu) {
@@ -299,12 +335,24 @@ out:
 }
 __initcall(init_topology_update);
 
+static void alloc_masks(struct tl_info *info, struct mask_info *mask, int offset)
+{
+	int i, nr_masks;
+
+	nr_masks = info->mag[NR_MAG - offset];
+	for (i = 0; i < info->mnest - offset; i++)
+		nr_masks *= info->mag[NR_MAG - offset - 1 - i];
+	nr_masks = max(nr_masks, 1);
+	for (i = 0; i < nr_masks; i++) {
+		mask->next = alloc_bootmem(sizeof(struct mask_info));
+		mask = mask->next;
+	}
+}
+
 void __init s390_init_cpu_topology(void)
 {
 	unsigned long long facility_bits;
 	struct tl_info *info;
-	struct core_info *core;
-	int nr_cores;
 	int i;
 
 	if (stfle(&facility_bits, 1) <= 0)
@@ -315,25 +363,13 @@ void __init s390_init_cpu_topology(void)
 
 	tl_info = alloc_bootmem_pages(PAGE_SIZE);
 	info = tl_info;
-	stsi(info, 15, 1, 2);
-
-	nr_cores = info->mag[NR_MAG - 2];
-	for (i = 0; i < info->mnest - 2; i++)
-		nr_cores *= info->mag[NR_MAG - 3 - i];
-
+	store_topology(info);
 	pr_info("The CPU configuration topology of the machine is:");
 	for (i = 0; i < NR_MAG; i++)
 		printk(" %d", info->mag[i]);
 	printk(" / %d\n", info->mnest);
-
-	core = &core_info;
-	for (i = 0; i < nr_cores; i++) {
-		core->next = alloc_bootmem(sizeof(struct core_info));
-		core = core->next;
-		if (!core)
-			goto error;
-	}
-	return;
-error:
-	machine_has_topology = 0;
+	alloc_masks(info, &core_info, 2);
+#ifdef CONFIG_SCHED_BOOK
+	alloc_masks(info, &book_info, 3);
+#endif
 }