* [PATCH v10 1/3] powerpc: Detect the presence of big-cores via "ibm,thread-groups"
2018-10-11 5:33 [PATCH v10 0/3] powerpc: Detection and scheduler optimization for POWER9 bigcore Gautham R. Shenoy
@ 2018-10-11 5:33 ` Gautham R. Shenoy
2018-10-12 6:58 ` Srikar Dronamraju
2018-10-15 4:01 ` [v10, 1/3] powerpc: Detect the presence of big-cores via "ibm, thread-groups" Michael Ellerman
2018-10-11 5:33 ` [PATCH v10 2/3] powerpc: Use cpu_smallcore_sibling_mask at SMT level on bigcores Gautham R. Shenoy
2018-10-11 5:33 ` [PATCH v10 3/3] powerpc/cacheinfo: Report the correct shared_cpu_map on big-cores Gautham R. Shenoy
2 siblings, 2 replies; 7+ messages in thread
From: Gautham R. Shenoy @ 2018-10-11 5:33 UTC (permalink / raw)
To: Dave Hansen, Aneesh Kumar K.V, Srikar Dronamraju,
Michael Ellerman, Benjamin Herrenschmidt, Michael Neuling,
Vaidyanathan Srinivasan, Akshay Adiga, Shilpasri G Bhat,
Oliver O'Halloran, Nicholas Piggin, Murilo Opsfelder Araujo,
Anton Blanchard
Cc: linuxppc-dev, linux-kernel, Gautham R. Shenoy
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
On IBM POWER9, the device tree exposes a property array identifed by
"ibm,thread-groups" which will indicate which groups of threads share
a particular set of resources.
As of today we only have one form of grouping identifying the group of
threads in the core that share the L1 cache, translation cache and
instruction data flow.
This patch adds helper functions to parse the contents of
"ibm,thread-groups" and populate a per-cpu variable to cache
information about siblings of each CPU that share the L1, traslation
cache and instruction data-flow.
It also defines a new global variable named "has_big_cores" which
indicates if the cores on this configuration have multiple groups of
threads that share L1 cache.
For each online CPU, it maintains a cpu_smallcore_mask, which
indicates the online siblings which share the L1-cache with it.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/cputhreads.h | 2 +
arch/powerpc/include/asm/smp.h | 11 ++
arch/powerpc/kernel/smp.c | 222 ++++++++++++++++++++++++++++++++++
3 files changed, 235 insertions(+)
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index d71a909..deb99fd 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -23,11 +23,13 @@
extern int threads_per_core;
extern int threads_per_subcore;
extern int threads_shift;
+extern bool has_big_cores;
extern cpumask_t threads_core_mask;
#else
#define threads_per_core 1
#define threads_per_subcore 1
#define threads_shift 0
+#define has_big_cores 0
#define threads_core_mask (*get_cpu_mask(0))
#endif
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index 95b66a0..4169574 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -100,6 +100,7 @@ static inline void set_hard_smp_processor_id(int cpu, int phys)
DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DECLARE_PER_CPU(cpumask_var_t, cpu_l2_cache_map);
DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
static inline struct cpumask *cpu_sibling_mask(int cpu)
{
@@ -116,6 +117,11 @@ static inline struct cpumask *cpu_l2_cache_mask(int cpu)
return per_cpu(cpu_l2_cache_map, cpu);
}
+static inline struct cpumask *cpu_smallcore_mask(int cpu)
+{
+ return per_cpu(cpu_smallcore_map, cpu);
+}
+
extern int cpu_to_core_id(int cpu);
/* Since OpenPIC has only 4 IPIs, we use slightly different message numbers.
@@ -166,6 +172,11 @@ static inline const struct cpumask *cpu_sibling_mask(int cpu)
return cpumask_of(cpu);
}
+static inline const struct cpumask *cpu_smallcore_mask(int cpu)
+{
+ return cpumask_of(cpu);
+}
+
#endif /* CONFIG_SMP */
#ifdef CONFIG_PPC64
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 61c1fad..22a14a9 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -74,14 +74,32 @@
#endif
struct thread_info *secondary_ti;
+bool has_big_cores;
DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_smallcore_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_l2_cache_map);
DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
+EXPORT_SYMBOL_GPL(has_big_cores);
+
+#define MAX_THREAD_LIST_SIZE 8
+#define THREAD_GROUP_SHARE_L1 1
+struct thread_groups {
+ unsigned int property;
+ unsigned int nr_groups;
+ unsigned int threads_per_group;
+ unsigned int thread_list[MAX_THREAD_LIST_SIZE];
+};
+
+/*
+ * On big-cores system, cpu_l1_cache_map for each CPU corresponds to
+ * the set its siblings that share the L1-cache.
+ */
+DEFINE_PER_CPU(cpumask_var_t, cpu_l1_cache_map);
/* SMP operations for this machine */
struct smp_ops_t *smp_ops;
@@ -674,6 +692,185 @@ static void set_cpus_unrelated(int i, int j,
}
#endif
+/*
+ * parse_thread_groups: Parses the "ibm,thread-groups" device tree
+ * property for the CPU device node @dn and stores
+ * the parsed output in the thread_groups
+ * structure @tg if the ibm,thread-groups[0]
+ * matches @property.
+ *
+ * @dn: The device node of the CPU device.
+ * @tg: Pointer to a thread group structure into which the parsed
+ * output of "ibm,thread-groups" is stored.
+ * @property: The property of the thread-group that the caller is
+ * interested in.
+ *
+ * ibm,thread-groups[0..N-1] array defines which group of threads in
+ * the CPU-device node can be grouped together based on the property.
+ *
+ * ibm,thread-groups[0] tells us the property based on which the
+ * threads are being grouped together. If this value is 1, it implies
+ * that the threads in the same group share L1, translation cache.
+ *
+ * ibm,thread-groups[1] tells us how many such thread groups exist.
+ *
+ * ibm,thread-groups[2] tells us the number of threads in each such
+ * group.
+ *
+ * ibm,thread-groups[3..N-1] is the list of threads identified by
+ * "ibm,ppc-interrupt-server#s" arranged as per their membership in
+ * the grouping.
+ *
+ * Example: If ibm,thread-groups = [1,2,4,5,6,7,8,9,10,11,12] it
+ * implies that there are 2 groups of 4 threads each, where each group
+ * of threads share L1, translation cache.
+ *
+ * The "ibm,ppc-interrupt-server#s" of the first group is {5,6,7,8}
+ * and the "ibm,ppc-interrupt-server#s" of the second group is {9, 10,
+ * 11, 12} structure
+ *
+ * Returns 0 on success, -EINVAL if the property does not exist,
+ * -ENODATA if property does not have a value, and -EOVERFLOW if the
+ * property data isn't large enough.
+ */
+static int parse_thread_groups(struct device_node *dn,
+ struct thread_groups *tg,
+ unsigned int property)
+{
+ int i;
+ u32 thread_group_array[3 + MAX_THREAD_LIST_SIZE];
+ u32 *thread_list;
+ size_t total_threads;
+ int ret;
+
+ ret = of_property_read_u32_array(dn, "ibm,thread-groups",
+ thread_group_array, 3);
+ if (ret)
+ return ret;
+
+ tg->property = thread_group_array[0];
+ tg->nr_groups = thread_group_array[1];
+ tg->threads_per_group = thread_group_array[2];
+ if (tg->property != property ||
+ tg->nr_groups < 1 ||
+ tg->threads_per_group < 1)
+ return -ENODATA;
+
+ total_threads = tg->nr_groups * tg->threads_per_group;
+
+ ret = of_property_read_u32_array(dn, "ibm,thread-groups",
+ thread_group_array,
+ 3 + total_threads);
+ if (ret)
+ return ret;
+
+ thread_list = &thread_group_array[3];
+
+ for (i = 0 ; i < total_threads; i++)
+ tg->thread_list[i] = thread_list[i];
+
+ return 0;
+}
+
+/*
+ * get_cpu_thread_group_start : Searches the thread group in tg->thread_list
+ * that @cpu belongs to.
+ *
+ * @cpu : The logical CPU whose thread group is being searched.
+ * @tg : The thread-group structure of the CPU node which @cpu belongs
+ * to.
+ *
+ * Returns the index to tg->thread_list that points to the the start
+ * of the thread_group that @cpu belongs to.
+ *
+ * Returns -1 if cpu doesn't belong to any of the groups pointed to by
+ * tg->thread_list.
+ */
+static int get_cpu_thread_group_start(int cpu, struct thread_groups *tg)
+{
+ int hw_cpu_id = get_hard_smp_processor_id(cpu);
+ int i, j;
+
+ for (i = 0; i < tg->nr_groups; i++) {
+ int group_start = i * tg->threads_per_group;
+
+ for (j = 0; j < tg->threads_per_group; j++) {
+ int idx = group_start + j;
+
+ if (tg->thread_list[idx] == hw_cpu_id)
+ return group_start;
+ }
+ }
+
+ return -1;
+}
+
+static int init_cpu_l1_cache_map(int cpu)
+
+{
+ struct device_node *dn = of_get_cpu_node(cpu, NULL);
+ struct thread_groups tg = {.property = 0,
+ .nr_groups = 0,
+ .threads_per_group = 0};
+ int first_thread = cpu_first_thread_sibling(cpu);
+ int i, cpu_group_start = -1, err = 0;
+
+ if (!dn)
+ return -ENODATA;
+
+ err = parse_thread_groups(dn, &tg, THREAD_GROUP_SHARE_L1);
+ if (err)
+ goto out;
+
+ zalloc_cpumask_var_node(&per_cpu(cpu_l1_cache_map, cpu),
+ GFP_KERNEL,
+ cpu_to_node(cpu));
+
+ cpu_group_start = get_cpu_thread_group_start(cpu, &tg);
+
+ if (unlikely(cpu_group_start == -1)) {
+ WARN_ON_ONCE(1);
+ err = -ENODATA;
+ goto out;
+ }
+
+ for (i = first_thread; i < first_thread + threads_per_core; i++) {
+ int i_group_start = get_cpu_thread_group_start(i, &tg);
+
+ if (unlikely(i_group_start == -1)) {
+ WARN_ON_ONCE(1);
+ err = -ENODATA;
+ goto out;
+ }
+
+ if (i_group_start == cpu_group_start)
+ cpumask_set_cpu(i, per_cpu(cpu_l1_cache_map, cpu));
+ }
+
+out:
+ of_node_put(dn);
+ return err;
+}
+
+static int init_big_cores(void)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu) {
+ int err = init_cpu_l1_cache_map(cpu);
+
+ if (err)
+ return err;
+
+ zalloc_cpumask_var_node(&per_cpu(cpu_smallcore_map, cpu),
+ GFP_KERNEL,
+ cpu_to_node(cpu));
+ }
+
+ has_big_cores = true;
+ return 0;
+}
+
void __init smp_prepare_cpus(unsigned int max_cpus)
{
unsigned int cpu;
@@ -712,6 +909,12 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid));
cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid));
+ init_big_cores();
+ if (has_big_cores) {
+ cpumask_set_cpu(boot_cpuid,
+ cpu_smallcore_mask(boot_cpuid));
+ }
+
if (smp_ops && smp_ops->probe)
smp_ops->probe();
}
@@ -995,10 +1198,28 @@ static void remove_cpu_from_masks(int cpu)
set_cpus_unrelated(cpu, i, cpu_core_mask);
set_cpus_unrelated(cpu, i, cpu_l2_cache_mask);
set_cpus_unrelated(cpu, i, cpu_sibling_mask);
+ if (has_big_cores)
+ set_cpus_unrelated(cpu, i, cpu_smallcore_mask);
}
}
#endif
+static inline void add_cpu_to_smallcore_masks(int cpu)
+{
+ struct cpumask *this_l1_cache_map = per_cpu(cpu_l1_cache_map, cpu);
+ int i, first_thread = cpu_first_thread_sibling(cpu);
+
+ if (!has_big_cores)
+ return;
+
+ cpumask_set_cpu(cpu, cpu_smallcore_mask(cpu));
+
+ for (i = first_thread; i < first_thread + threads_per_core; i++) {
+ if (cpu_online(i) && cpumask_test_cpu(i, this_l1_cache_map))
+ set_cpus_related(i, cpu, cpu_smallcore_mask);
+ }
+}
+
static void add_cpu_to_masks(int cpu)
{
int first_thread = cpu_first_thread_sibling(cpu);
@@ -1015,6 +1236,7 @@ static void add_cpu_to_masks(int cpu)
if (cpu_online(i))
set_cpus_related(i, cpu, cpu_sibling_mask);
+ add_cpu_to_smallcore_masks(cpu);
/*
* Copy the thread sibling mask into the cache sibling mask
* and mark any CPUs that share an L2 with this CPU.
--
1.9.4
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH v10 2/3] powerpc: Use cpu_smallcore_sibling_mask at SMT level on bigcores
2018-10-11 5:33 [PATCH v10 0/3] powerpc: Detection and scheduler optimization for POWER9 bigcore Gautham R. Shenoy
2018-10-11 5:33 ` [PATCH v10 1/3] powerpc: Detect the presence of big-cores via "ibm,thread-groups" Gautham R. Shenoy
@ 2018-10-11 5:33 ` Gautham R. Shenoy
2018-10-12 7:00 ` Srikar Dronamraju
2018-10-11 5:33 ` [PATCH v10 3/3] powerpc/cacheinfo: Report the correct shared_cpu_map on big-cores Gautham R. Shenoy
2 siblings, 1 reply; 7+ messages in thread
From: Gautham R. Shenoy @ 2018-10-11 5:33 UTC (permalink / raw)
To: Dave Hansen, Aneesh Kumar K.V, Srikar Dronamraju,
Michael Ellerman, Benjamin Herrenschmidt, Michael Neuling,
Vaidyanathan Srinivasan, Akshay Adiga, Shilpasri G Bhat,
Oliver O'Halloran, Nicholas Piggin, Murilo Opsfelder Araujo,
Anton Blanchard
Cc: linuxppc-dev, linux-kernel, Gautham R. Shenoy
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
POWER9 SMT8 cores consist of two groups of threads, where threads in
each group shares L1-cache. The scheduler is not aware of this
distinction as the current sched-domain hierarchy has all the threads
of the core defined at the SMT domain.
SMT [Thread siblings of the SMT8 core]
DIE [CPUs in the same die]
NUMA [All the CPUs in the system]
Due to this, we can observe run-to-run variance when we run a
multi-threaded benchmark bound to a single core based on how the
scheduler spreads the software threads across the two groups in the
core.
We fix this in this patch by defining each group of threads which
share L1-cache to be the SMT level. The group of threads in the SMT8
core is defined to be the CACHE level. The sched-domain hierarchy
after this patch will be :
SMT [Thread siblings in the core that share L1 cache]
CACHE [Thread siblings that are in the SMT8 core]
DIE [CPUs in the same die]
NUMA [All the CPUs in the system]
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/kernel/smp.c | 19 ++++++++++++++++++-
1 file changed, 18 insertions(+), 1 deletion(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 22a14a9..356751e 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1266,6 +1266,7 @@ static void add_cpu_to_masks(int cpu)
void start_secondary(void *unused)
{
unsigned int cpu = smp_processor_id();
+ struct cpumask *(*sibling_mask)(int) = cpu_sibling_mask;
mmgrab(&init_mm);
current->active_mm = &init_mm;
@@ -1291,11 +1292,13 @@ void start_secondary(void *unused)
/* Update topology CPU masks */
add_cpu_to_masks(cpu);
+ if (has_big_cores)
+ sibling_mask = cpu_smallcore_mask;
/*
* Check for any shared caches. Note that this must be done on a
* per-core basis because one core in the pair might be disabled.
*/
- if (!cpumask_equal(cpu_l2_cache_mask(cpu), cpu_sibling_mask(cpu)))
+ if (!cpumask_equal(cpu_l2_cache_mask(cpu), sibling_mask(cpu)))
shared_caches = true;
set_numa_node(numa_cpu_lookup_table[cpu]);
@@ -1362,6 +1365,13 @@ static const struct cpumask *shared_cache_mask(int cpu)
return cpu_l2_cache_mask(cpu);
}
+#ifdef CONFIG_SCHED_SMT
+static const struct cpumask *smallcore_smt_mask(int cpu)
+{
+ return cpu_smallcore_mask(cpu);
+}
+#endif
+
static struct sched_domain_topology_level power9_topology[] = {
#ifdef CONFIG_SCHED_SMT
{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
@@ -1389,6 +1399,13 @@ void __init smp_cpus_done(unsigned int max_cpus)
shared_proc_topology_init();
dump_numa_cpu_topology();
+#ifdef CONFIG_SCHED_SMT
+ if (has_big_cores) {
+ pr_info("Using small cores at SMT level\n");
+ power9_topology[0].mask = smallcore_smt_mask;
+ powerpc_topology[0].mask = smallcore_smt_mask;
+ }
+#endif
/*
* If any CPU detects that it's sharing a cache with another CPU then
* use the deeper topology that is aware of this sharing.
--
1.9.4
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH v10 3/3] powerpc/cacheinfo: Report the correct shared_cpu_map on big-cores
2018-10-11 5:33 [PATCH v10 0/3] powerpc: Detection and scheduler optimization for POWER9 bigcore Gautham R. Shenoy
2018-10-11 5:33 ` [PATCH v10 1/3] powerpc: Detect the presence of big-cores via "ibm,thread-groups" Gautham R. Shenoy
2018-10-11 5:33 ` [PATCH v10 2/3] powerpc: Use cpu_smallcore_sibling_mask at SMT level on bigcores Gautham R. Shenoy
@ 2018-10-11 5:33 ` Gautham R. Shenoy
2 siblings, 0 replies; 7+ messages in thread
From: Gautham R. Shenoy @ 2018-10-11 5:33 UTC (permalink / raw)
To: Dave Hansen, Aneesh Kumar K.V, Srikar Dronamraju,
Michael Ellerman, Benjamin Herrenschmidt, Michael Neuling,
Vaidyanathan Srinivasan, Akshay Adiga, Shilpasri G Bhat,
Oliver O'Halloran, Nicholas Piggin, Murilo Opsfelder Araujo,
Anton Blanchard
Cc: linuxppc-dev, linux-kernel, Gautham R. Shenoy
From: "Gautham R. Shenoy" <ego@linux.vnet.ibm.com>
Currently on POWER9 SMT8 cores systems, in sysfs, we report the
shared_cache_map for L1 caches (both data and instruction) to be the
cpu-ids of the threads in SMT8 cores. This is incorrect since on
POWER9 SMT8 cores there are two groups of threads, each of which
shares its own L1 cache.
This patch addresses this by reporting the shared_cpu_map correctly in
sysfs for L1 caches.
Before the patch
/sys/devices/system/cpu/cpu0/cache/index0/shared_cpu_map : 000000ff
/sys/devices/system/cpu/cpu0/cache/index1/shared_cpu_map : 000000ff
/sys/devices/system/cpu/cpu1/cache/index0/shared_cpu_map : 000000ff
/sys/devices/system/cpu/cpu1/cache/index1/shared_cpu_map : 000000ff
After the patch
/sys/devices/system/cpu/cpu0/cache/index0/shared_cpu_map : 00000055
/sys/devices/system/cpu/cpu0/cache/index1/shared_cpu_map : 00000055
/sys/devices/system/cpu/cpu1/cache/index0/shared_cpu_map : 000000aa
/sys/devices/system/cpu/cpu1/cache/index1/shared_cpu_map : 000000aa
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/kernel/cacheinfo.c | 37 +++++++++++++++++++++++++++++++++++--
1 file changed, 35 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index a8f20e5..be57bd0 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -20,6 +20,8 @@
#include <linux/percpu.h>
#include <linux/slab.h>
#include <asm/prom.h>
+#include <asm/cputhreads.h>
+#include <asm/smp.h>
#include "cacheinfo.h"
@@ -627,17 +629,48 @@ static ssize_t level_show(struct kobject *k, struct kobj_attribute *attr, char *
static struct kobj_attribute cache_level_attr =
__ATTR(level, 0444, level_show, NULL);
+static unsigned int index_dir_to_cpu(struct cache_index_dir *index)
+{
+ struct kobject *index_dir_kobj = &index->kobj;
+ struct kobject *cache_dir_kobj = index_dir_kobj->parent;
+ struct kobject *cpu_dev_kobj = cache_dir_kobj->parent;
+ struct device *dev = kobj_to_dev(cpu_dev_kobj);
+
+ return dev->id;
+}
+
+/*
+ * On big-core systems, each core has two groups of CPUs each of which
+ * has its own L1-cache. The thread-siblings which share l1-cache with
+ * @cpu can be obtained via cpu_smallcore_mask().
+ */
+static const struct cpumask *get_big_core_shared_cpu_map(int cpu, struct cache *cache)
+{
+ if (cache->level == 1)
+ return cpu_smallcore_mask(cpu);
+
+ return &cache->shared_cpu_map;
+}
+
static ssize_t shared_cpu_map_show(struct kobject *k, struct kobj_attribute *attr, char *buf)
{
struct cache_index_dir *index;
struct cache *cache;
- int ret;
+ const struct cpumask *mask;
+ int ret, cpu;
index = kobj_to_cache_index_dir(k);
cache = index->cache;
+ if (has_big_cores) {
+ cpu = index_dir_to_cpu(index);
+ mask = get_big_core_shared_cpu_map(cpu, cache);
+ } else {
+ mask = &cache->shared_cpu_map;
+ }
+
ret = scnprintf(buf, PAGE_SIZE - 1, "%*pb\n",
- cpumask_pr_args(&cache->shared_cpu_map));
+ cpumask_pr_args(mask));
buf[ret++] = '\n';
buf[ret] = '\0';
return ret;
--
1.9.4
^ permalink raw reply related [flat|nested] 7+ messages in thread