* [PATCH v7 1/2] powerpc: Detect the presence of big-cores via "ibm,thread-groups"
2018-08-20 5:41 [PATCH v7 0/2] powerpc: Detection and scheduler optimization for POWER9 bigcore Gautham R. Shenoy
@ 2018-08-20 5:41 ` Gautham R. Shenoy
2018-08-20 17:59 ` Srikar Dronamraju
2018-08-29 7:04 ` Michael Neuling
2018-08-20 5:41 ` [PATCH v7 2/2] powerpc: Use cpu_smallcore_sibling_mask at SMT level on bigcores Gautham R. Shenoy
1 sibling, 2 replies; 7+ messages in thread
From: Gautham R. Shenoy @ 2018-08-20 5:41 UTC (permalink / raw)
To: 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 defines the helper function to parse the contents of
"ibm,thread-groups" and a new structure to contain the parsed output.
The patch also creates the sysfs file named "small_core_siblings" that
returns the physical ids of the threads in the core that share the L1
cache, translation cache and instruction data flow.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
Documentation/ABI/testing/sysfs-devices-system-cpu | 8 ++
arch/powerpc/include/asm/cputhreads.h | 25 ++++
arch/powerpc/kernel/setup-common.c | 151 +++++++++++++++++++++
arch/powerpc/kernel/sysfs.c | 38 ++++++
4 files changed, 222 insertions(+)
diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index 9c5e7732..b09b051 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -487,3 +487,11 @@ Description: Information about CPU vulnerabilities
"Not affected" CPU is not affected by the vulnerability
"Vulnerable" CPU is affected and no mitigation in effect
"Mitigation: $M" CPU is affected and mitigation $M is in effect
+
+What: /sys/devices/system/cpu/cpu[0-9]+/small_core_siblings
+Date: Aug-2018
+KernelVersion: v4.19.0
+Contact: Linux for PowerPC mailing list <linuxppc-dev@ozlabs.org>
+Description: List of Physical ids of CPUs which share the L1 cache,
+ translation cache and instruction data-flow with this CPU.
+Values: Comma separated list of decimal integers.
diff --git a/arch/powerpc/include/asm/cputhreads.h b/arch/powerpc/include/asm/cputhreads.h
index d71a909..cb8b4a4 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
@@ -69,12 +71,35 @@ static inline cpumask_t cpu_online_cores_map(void)
return cpu_thread_mask_to_cores(cpu_online_mask);
}
+#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];
+};
+
#ifdef CONFIG_SMP
int cpu_core_index_of_thread(int cpu);
int cpu_first_thread_of_core(int core);
+int parse_thread_groups(struct device_node *dn, struct thread_groups *tg,
+ unsigned property);
+int get_cpu_thread_group_start(int cpu, struct thread_groups *tg);
#else
static inline int cpu_core_index_of_thread(int cpu) { return cpu; }
static inline int cpu_first_thread_of_core(int core) { return core; }
+static inline int parse_thread_groups(struct device_node *dn,
+ struct thread_groups *tg,
+ unsigned property)
+{
+ return -ENODATA;
+}
+
+static inline int get_cpu_thread_group_start(int cpu, struct thread_groups *tg)
+{
+ return -1;
+}
#endif
static inline int cpu_thread_in_core(int cpu)
diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
index 40b44bb..272dbe5 100644
--- a/arch/powerpc/kernel/setup-common.c
+++ b/arch/powerpc/kernel/setup-common.c
@@ -402,10 +402,12 @@ void __init check_for_initrd(void)
#ifdef CONFIG_SMP
int threads_per_core, threads_per_subcore, threads_shift;
+bool has_big_cores;
cpumask_t threads_core_mask;
EXPORT_SYMBOL_GPL(threads_per_core);
EXPORT_SYMBOL_GPL(threads_per_subcore);
EXPORT_SYMBOL_GPL(threads_shift);
+EXPORT_SYMBOL_GPL(has_big_cores);
EXPORT_SYMBOL_GPL(threads_core_mask);
static void __init cpu_init_thread_core_maps(int tpc)
@@ -433,6 +435,150 @@ static void __init cpu_init_thread_core_maps(int tpc)
u32 *cpu_to_phys_id = NULL;
+/*
+ * 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.
+ */
+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)
+ goto out_err;
+
+ ret = -ENODATA;
+ 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)
+ goto out_err;
+
+ 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)
+ goto out_err;
+
+ thread_list = &thread_group_array[3];
+
+ for (i = 0 ; i < total_threads; i++)
+ tg->thread_list[i] = thread_list[i];
+
+ return 0;
+out_err:
+ tg->property = 0;
+ tg->nr_groups = 0;
+ tg->threads_per_group = 0;
+ return ret;
+}
+
+/*
+ * dt_has_big_core : Parses the device tree property
+ * "ibm,thread-groups" for device node pointed by @dn
+ * and stores the parsed output in the structure
+ * pointed to by @tg. Then checks if the output in
+ * @tg corresponds to a big-core.
+ *
+ * @dn: Device node pointer of the CPU node being checked for a
+ * big-core.
+ * @tg: Pointer to thread_groups struct in which parsed output of
+ * "ibm,thread-groups" is recorded.
+ *
+ * Returns true if the @dn points to a big-core.
+ * Returns false if there is an error in parsing "ibm,thread-groups"
+ * or the parsed output doesn't correspond to a big-core.
+ */
+static inline bool dt_has_big_core(struct device_node *dn,
+ struct thread_groups *tg)
+{
+ if (parse_thread_groups(dn, tg, THREAD_GROUP_SHARE_L1))
+ return false;
+
+ return true;
+}
+
+/*
+ * 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.
+ */
+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;
+}
+
/**
* setup_cpu_maps - initialize the following cpu maps:
* cpu_possible_mask
@@ -457,6 +603,7 @@ void __init smp_setup_cpu_maps(void)
int cpu = 0;
int nthreads = 1;
+ has_big_cores = true;
DBG("smp_setup_cpu_maps()\n");
cpu_to_phys_id = __va(memblock_alloc(nr_cpu_ids * sizeof(u32),
@@ -467,6 +614,7 @@ void __init smp_setup_cpu_maps(void)
const __be32 *intserv;
__be32 cpu_be;
int j, len;
+ struct thread_groups tg;
DBG(" * %pOF...\n", dn);
@@ -505,6 +653,9 @@ void __init smp_setup_cpu_maps(void)
cpu++;
}
+ if (has_big_cores && !dt_has_big_core(dn, &tg))
+ has_big_cores = false;
+
if (cpu >= nr_cpu_ids) {
of_node_put(dn);
break;
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index 755dc98..83fd26b 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -18,6 +18,7 @@
#include <asm/smp.h>
#include <asm/pmc.h>
#include <asm/firmware.h>
+#include <asm/cputhreads.h>
#include "cacheinfo.h"
#include "setup.h"
@@ -1025,6 +1026,36 @@ static ssize_t show_physical_id(struct device *dev,
}
static DEVICE_ATTR(physical_id, 0444, show_physical_id, NULL);
+static ssize_t show_small_core_siblings(struct device *dev,
+ struct device_attribute *attr,
+ char *buf)
+{
+ struct cpu *cpu = container_of(dev, struct cpu, dev);
+ struct device_node *dn = of_get_cpu_node(cpu->dev.id, NULL);
+ struct thread_groups tg;
+ int i, j, err;
+ ssize_t ret = 0;
+
+ err = parse_thread_groups(dn, &tg, THREAD_GROUP_SHARE_L1);
+ of_node_put(dn);
+
+ if (err)
+ return -ENODATA;
+
+ i = get_cpu_thread_group_start(cpu->dev.id, &tg);
+
+ if (i == -1)
+ return -ENODATA;
+
+ for (j = 0; j < tg.threads_per_group - 1; j++)
+ ret += sprintf(buf + ret, "%d,", tg.thread_list[i + j]);
+
+ ret += sprintf(buf + ret, "%d\n", tg.thread_list[i + j]);
+
+ return ret;
+}
+static DEVICE_ATTR(small_core_siblings, 0444, show_small_core_siblings, NULL);
+
static int __init topology_init(void)
{
int cpu, r;
@@ -1048,6 +1079,13 @@ static int __init topology_init(void)
register_cpu(c, cpu);
device_create_file(&c->dev, &dev_attr_physical_id);
+
+ if (has_big_cores) {
+ const struct device_attribute *attr =
+ &dev_attr_small_core_siblings;
+
+ device_create_file(&c->dev, attr);
+ }
}
}
r = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/topology:online",
--
1.9.4
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH v7 2/2] powerpc: Use cpu_smallcore_sibling_mask at SMT level on bigcores
2018-08-20 5:41 [PATCH v7 0/2] powerpc: Detection and scheduler optimization for POWER9 bigcore Gautham R. Shenoy
2018-08-20 5:41 ` [PATCH v7 1/2] powerpc: Detect the presence of big-cores via "ibm,thread-groups" Gautham R. Shenoy
@ 2018-08-20 5:41 ` Gautham R. Shenoy
2018-08-20 18:05 ` Srikar Dronamraju
1 sibling, 1 reply; 7+ messages in thread
From: Gautham R. Shenoy @ 2018-08-20 5:41 UTC (permalink / raw)
To: 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>
Each of the SMT4 cores forming a big-core are more or less independent
units. Thus when multiple tasks are scheduled to run on the fused
core, we get the best performance when the tasks are spread across the
pair of SMT4 cores.
This patch achieves this by setting the SMT level mask to correspond
to the smallcore sibling mask on big-core systems. This patch also
ensures that while checked for shared-caches on big-core system, we
use the smallcore_sibling_mask to compare with the l2_cache_mask.
This ensure that the CACHE level sched-domain is created, whose groups
correspond to the threads of the big-core.
With this patch, the SMT sched-domain with SMT=8,4,2 on big-core
systems are as follows:
1) ppc64_cpu --smt=8
CPU0 attaching sched-domain(s):
domain-0: span=0,2,4,6 level=SMT
groups: 0:{ span=0 cap=294 }, 2:{ span=2 cap=294 },
4:{ span=4 cap=294 }, 6:{ span=6 cap=294 }
CPU1 attaching sched-domain(s):
domain-0: span=1,3,5,7 level=SMT
groups: 1:{ span=1 cap=294 }, 3:{ span=3 cap=294 },
5:{ span=5 cap=294 }, 7:{ span=7 cap=294 }
2) ppc64_cpu --smt=4
CPU0 attaching sched-domain(s):
domain-0: span=0,2 level=SMT
groups: 0:{ span=0 cap=589 }, 2:{ span=2 cap=589 }
CPU1 attaching sched-domain(s):
domain-0: span=1,3 level=SMT
groups: 1:{ span=1 cap=589 }, 3:{ span=3 cap=589 }
3) ppc64_cpu --smt=2
SMT domain is a trivial domain consisting of just
1 CPU. Hence this domain gets collapsed leaving only CACHE, DIE and
NUMA domains.
Signed-off-by: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
---
arch/powerpc/kernel/smp.c | 136 +++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 134 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 4794d6b..00f60a8 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -76,6 +76,7 @@
struct thread_info *secondary_ti;
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);
@@ -83,6 +84,23 @@
EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
+/*
+ * On big-cores system, cpu_l1_cache_map for each CPU corresponds to
+ * the set its siblings that share the l1-cache. This map is
+ * initialized the first time the CPU comes online, and subsequently
+ * remains unchanged.
+ *
+ * parse_success records if there has been an error in parsing the
+ * "ibm,thread-groups" property which tells us which set of siblings
+ * share the l1-cache with the CPU.
+ */
+struct small_core_sibling {
+ cpumask_var_t cpu_l1_cache_map;
+ bool parse_success;
+};
+
+DEFINE_PER_CPU(struct small_core_sibling, small_core);
+
/* SMP operations for this machine */
struct smp_ops_t *smp_ops;
@@ -91,6 +109,11 @@
int smt_enabled_at_boot = 1;
+static inline struct cpumask *cpu_smallcore_mask(int cpu)
+{
+ return per_cpu(cpu_smallcore_map, cpu);
+}
+
/*
* Returns 1 if the specified cpu should be brought up during boot.
* Used to inhibit booting threads if they've been disabled or
@@ -670,6 +693,18 @@ static void set_cpus_unrelated(int i, int j,
}
#endif
+static inline void alloc_small_core_data(int cpu)
+{
+ struct small_core_sibling *this_small_core;
+
+ zalloc_cpumask_var_node(&per_cpu(cpu_smallcore_map, cpu),
+ GFP_KERNEL, cpu_to_node(cpu));
+
+ this_small_core = &per_cpu(small_core, cpu);
+ zalloc_cpumask_var_node(&this_small_core->cpu_l1_cache_map,
+ GFP_KERNEL, cpu_to_node(cpu));
+}
+
void __init smp_prepare_cpus(unsigned int max_cpus)
{
unsigned int cpu;
@@ -701,12 +736,19 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
set_cpu_numa_mem(cpu,
local_memory_node(numa_cpu_lookup_table[cpu]));
}
+
+ if (has_big_cores)
+ alloc_small_core_data(cpu);
}
/* Init the cpumasks so the boot CPU is related to itself */
cpumask_set_cpu(boot_cpuid, cpu_sibling_mask(boot_cpuid));
cpumask_set_cpu(boot_cpuid, cpu_l2_cache_mask(boot_cpuid));
cpumask_set_cpu(boot_cpuid, cpu_core_mask(boot_cpuid));
+ if (has_big_cores) {
+ cpumask_set_cpu(boot_cpuid,
+ cpu_smallcore_mask(boot_cpuid));
+ }
if (smp_ops && smp_ops->probe)
smp_ops->probe();
@@ -991,10 +1033,83 @@ 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 init_small_core_data(int cpu,
+ struct small_core_sibling *cpu_sc)
+{
+ struct device_node *dn;
+ int first_thread = cpu_first_thread_sibling(cpu);
+ int i, cpu_group_start = -1;
+ struct thread_groups tg;
+
+ cpumask_set_cpu(cpu, cpu_sc->cpu_l1_cache_map);
+
+ dn = of_get_cpu_node(cpu, NULL);
+ if (unlikely(!dn)) {
+ WARN_ON(1);
+ goto out;
+ }
+
+ if (unlikely(parse_thread_groups(dn, &tg,
+ THREAD_GROUP_SHARE_L1))) {
+ WARN_ON(1);
+ goto out;
+ }
+
+ cpu_group_start = get_cpu_thread_group_start(cpu, &tg);
+
+ if (unlikely(cpu_group_start == -1)) {
+ WARN_ON(1);
+ 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(1);
+ goto out;
+ }
+
+ if (i_group_start == cpu_group_start)
+ cpumask_set_cpu(i, cpu_sc->cpu_l1_cache_map);
+ }
+
+ cpu_sc->parse_success = true;
+out:
+ of_node_put(dn);
+}
+
+static inline void add_cpu_to_smallcore_masks(int cpu)
+{
+ struct small_core_sibling *this_small_core = &per_cpu(small_core, cpu);
+ int i, first_thread = cpu_first_thread_sibling(cpu);
+
+ if (!has_big_cores)
+ return;
+
+ if (unlikely(cpumask_empty(this_small_core->cpu_l1_cache_map)))
+ init_small_core_data(cpu, this_small_core);
+
+ cpumask_set_cpu(cpu, cpu_smallcore_mask(cpu));
+
+ for (i = first_thread; i < first_thread + threads_per_core; i++) {
+ if (unlikely(!this_small_core->parse_success)) {
+ /* Fallback to siblings of the big-core */
+ set_cpus_related(i, cpu, cpu_smallcore_mask);
+ continue;
+ }
+
+ if (cpumask_test_cpu(i, this_small_core->cpu_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);
@@ -1006,11 +1121,11 @@ static void add_cpu_to_masks(int cpu)
* add it to it's own thread sibling mask.
*/
cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
-
for (i = first_thread; i < first_thread + threads_per_core; i++)
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.
@@ -1040,6 +1155,7 @@ 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;
@@ -1065,11 +1181,13 @@ 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]);
@@ -1136,6 +1254,13 @@ 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) },
@@ -1158,6 +1283,13 @@ void __init smp_cpus_done(unsigned int max_cpus)
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