--- v8
+++ v4
@@ -8,31 +8,39 @@
threads in the core that share the L1 cache, translation cache and
instruction data flow.
-This patch
-
- 1) Defines the helper function to parse the contents of
- "ibm,thread-groups".
-
- 2) On boot, it parses the "ibm,thread-groups" property and caches
- the CPU-threads sharing the L1 cache in a per-cpu variable named
- cpu_l1_cache_map.
-
- 3) Initializes a global variable named "has_big_cores" on
- big-core systems.
-
- 4) Each time a CPU is onlined, it initializes the
- cpu_smallcore_mask which contains the online siblings of the
- CPU that share the L1 cache with this CPU.
+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>
---
- arch/powerpc/include/asm/cputhreads.h | 2 +
- arch/powerpc/include/asm/smp.h | 6 +
- arch/powerpc/kernel/smp.c | 221 ++++++++++++++++++++++++++++++++++
- 3 files changed, 229 insertions(+)
-
+ Documentation/ABI/testing/sysfs-devices-system-cpu | 8 ++
+ arch/powerpc/include/asm/cputhreads.h | 22 +++
+ arch/powerpc/kernel/setup-common.c | 154 +++++++++++++++++++++
+ arch/powerpc/kernel/sysfs.c | 35 +++++
+ 4 files changed, 219 insertions(+)
+
+diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
+index 9c5e7732..41adf1d 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: 24-Jul-2018
++KernelVersion: v4.18.0
++Contact: Gautham R. Shenoy <ego@linux.vnet.ibm.com>
++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..deb99fd 100644
+index d71a909..33226d7 100644
--- a/arch/powerpc/include/asm/cputhreads.h
+++ b/arch/powerpc/include/asm/cputhreads.h
@@ -23,11 +23,13 @@
@@ -49,52 +57,11 @@
#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..4439893 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);
+@@ -69,12 +71,32 @@ static inline cpumask_t cpu_online_cores_map(void)
+ return cpu_thread_mask_to_cores(cpu_online_mask);
}
-+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.
-diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
-index 61c1fad..15095110 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;
@@ -102,30 +69,57 @@
+ 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 +692,184 @@ static void set_cpus_unrelated(int i, int j,
- }
+ #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);
++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)
++{
++ 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..989edc1 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 +435,152 @@ 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.
++ * structure @tg.
+ *
+ * @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.
++ * output of "ibm,thread-groups" is stored.
+ *
+ * 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.
@@ -155,10 +149,10 @@
+ * -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 parse_thread_groups(struct device_node *dn,
++ struct thread_groups *tg)
++{
++ unsigned int nr_groups, threads_per_group, property;
+ int i;
+ u32 thread_group_array[3 + MAX_THREAD_LIST_SIZE];
+ u32 *thread_list;
@@ -167,31 +161,67 @@
+
+ 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;
++ goto out_err;
++
++ property = thread_group_array[0];
++ nr_groups = thread_group_array[1];
++ threads_per_group = thread_group_array[2];
++ total_threads = nr_groups * threads_per_group;
+
+ ret = of_property_read_u32_array(dn, "ibm,thread-groups",
+ thread_group_array,
+ 3 + total_threads);
+ if (ret)
-+ return ret;
++ goto out_err;
+
+ thread_list = &thread_group_array[3];
+
+ for (i = 0 ; i < total_threads; i++)
+ tg->thread_list[i] = thread_list[i];
+
++ tg->property = property;
++ tg->nr_groups = nr_groups;
++ tg->threads_per_group = threads_per_group;
++
+ 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))
++ return false;
++
++ if (tg->property != 1)
++ return false;
++
++ if (tg->nr_groups < 1)
++ return false;
++
++ return true;
+}
+
+/*
@@ -208,7 +238,7 @@
+ * 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 get_cpu_thread_group_start(int cpu, struct thread_groups *tg)
+{
+ int hw_cpu_id = get_hard_smp_processor_id(cpu);
+ int i, j;
@@ -227,123 +257,95 @@
+ return -1;
+}
+
-+static int init_cpu_l1_cache_map(int cpu)
-+
-+{
-+ struct device_node *dn = of_get_cpu_node(cpu, NULL);
+ /**
+ * setup_cpu_maps - initialize the following cpu maps:
+ * cpu_possible_mask
+@@ -457,6 +605,7 @@ 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 +616,7 @@ 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 +655,10 @@ 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..f5717de 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 +1026,33 @@ 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 first_thread = cpu_first_thread_sibling(cpu);
-+ int i, cpu_group_start = -1, err = 0;
-+
-+ if (!dn)
++ int i, j;
++ ssize_t ret = 0;
++
++ if (parse_thread_groups(dn, &tg))
+ 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)
++ 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)
{
- unsigned int cpu;
-@@ -712,6 +908,12 @@ 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 +1197,28 @@ 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);
+ int cpu, r;
+@@ -1048,6 +1076,13 @@ 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);
++ }
+ }
}
- }
- #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 +1235,7 @@ 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.
+ r = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "powerpc/topology:online",
--
1.9.4