[PATCH v2 3/5] x86: Move per cpu cpu_sibling_map to a field in struct cpuinfo_x86

From: Kevin Winchester
Date: Tue Feb 21 2012 - 20:46:22 EST

This simplifies the various code paths using this field as it
groups the per-cpu data together.

Acked-by: Borislav Petkov <bp@xxxxxxxxx>
Signed-off-by: Kevin Winchester <kjwinchester@xxxxxxxxx>
---
arch/x86/include/asm/perf_event_p4.h | 2 +-
arch/x86/include/asm/processor.h | 2 ++
arch/x86/include/asm/smp.h | 6 ------
arch/x86/include/asm/topology.h | 2 +-
arch/x86/kernel/cpu/intel_cacheinfo.c | 4 ++--
arch/x86/kernel/smpboot.c | 27 +++++++++++----------------
arch/x86/oprofile/op_model_p4.c | 5 +----
arch/x86/xen/smp.c | 1 -
drivers/cpufreq/p4-clockmod.c | 4 +---
drivers/cpufreq/speedstep-ich.c | 6 +++---
drivers/hwmon/coretemp.c | 6 +-----
11 files changed, 23 insertions(+), 42 deletions(-)

diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h
index 4f7e67e..29a65c2 100644
--- a/arch/x86/include/asm/perf_event_p4.h
+++ b/arch/x86/include/asm/perf_event_p4.h
@@ -189,7 +189,7 @@ static inline int p4_ht_thread(int cpu)
{
#ifdef CONFIG_SMP
if (smp_num_siblings == 2)
- return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
+ return cpu != cpumask_first(&cpu_data(cpu).sibling_map));
#endif
return 0;
}
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 2ba6d0e..266eaee 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -113,6 +113,8 @@ struct cpuinfo_x86 {
/* CPUs sharing the last level cache: */
cpumask_t llc_shared_map;
u16 llc_id;
+ /* representing HT siblings of each logical CPU */
+ cpumask_t sibling_map;
} __attribute__((__aligned__(SMP_CACHE_BYTES)));

#define X86_VENDOR_INTEL 0
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 40d1c96..b5e7cd2 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -31,15 +31,9 @@ static inline bool cpu_has_ht_siblings(void)
return has_siblings;
}

-DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
DECLARE_PER_CPU(int, cpu_number);

-static inline struct cpumask *cpu_sibling_mask(int cpu)
-{
- return per_cpu(cpu_sibling_map, cpu);
-}
-
static inline struct cpumask *cpu_core_mask(int cpu)
{
return per_cpu(cpu_core_map, cpu);
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index b9676ae..5297acbf 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -161,7 +161,7 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
#define topology_physical_package_id(cpu) (cpu_data(cpu).phys_proc_id)
#define topology_core_id(cpu) (cpu_data(cpu).cpu_core_id)
#define topology_core_cpumask(cpu) (per_cpu(cpu_core_map, cpu))
-#define topology_thread_cpumask(cpu) (per_cpu(cpu_sibling_map, cpu))
+#define topology_thread_cpumask(cpu) (&cpu_data(cpu).sibling_map)

/* indicates that pointers to the topology cpumask_t maps are valid */
#define arch_provides_topology_pointers yes
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 5ddd6ef..7787d33 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -739,11 +739,11 @@ static int __cpuinit cache_shared_amd_cpu_map_setup(unsigned int cpu, int index)
}
} else if ((c->x86 == 0x15) && ((index == 1) || (index == 2))) {
ret = 1;
- for_each_cpu(i, cpu_sibling_mask(cpu)) {
+ for_each_cpu(i, &c->sibling_map) {
if (!per_cpu(ici_cpuid4_info, i))
continue;
this_leaf = CPUID4_INFO_IDX(i, index);
- for_each_cpu(sibling, cpu_sibling_mask(cpu)) {
+ for_each_cpu(sibling, &c->sibling_map) {
if (!cpu_online(sibling))
continue;
set_bit(sibling, this_leaf->shared_cpu_map);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fb2ef30..991d17b 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -116,10 +116,6 @@ static struct task_struct *idle_thread_array[NR_CPUS] __cpuinitdata ;
int smp_num_siblings = 1;
EXPORT_SYMBOL(smp_num_siblings);

-/* representing HT siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
-EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
-
/* representing HT and core siblings of each logical CPU */
DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
EXPORT_PER_CPU_SYMBOL(cpu_core_map);
@@ -328,8 +324,8 @@ void __cpuinit smp_store_cpu_info(int id)

static void __cpuinit link_thread_siblings(int cpu1, int cpu2)
{
- cpumask_set_cpu(cpu1, cpu_sibling_mask(cpu2));
- cpumask_set_cpu(cpu2, cpu_sibling_mask(cpu1));
+ cpumask_set_cpu(cpu1, &cpu_data(cpu2).sibling_map);
+ cpumask_set_cpu(cpu2, &cpu_data(cpu1).sibling_map);
cpumask_set_cpu(cpu1, cpu_core_mask(cpu2));
cpumask_set_cpu(cpu2, cpu_core_mask(cpu1));
cpumask_set_cpu(cpu1, &cpu_data(cpu2).llc_shared_map);
@@ -359,13 +355,13 @@ void __cpuinit set_cpu_sibling_map(int cpu)
}
}
} else {
- cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
+ cpumask_set_cpu(cpu, &c->sibling_map);
}

cpumask_set_cpu(cpu, &c->llc_shared_map);

if (__this_cpu_read(cpu_info.x86_max_cores) == 1) {
- cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
+ cpumask_copy(cpu_core_mask(cpu), &c->sibling_map);
c->booted_cores = 1;
return;
}
@@ -383,12 +379,12 @@ void __cpuinit set_cpu_sibling_map(int cpu)
/*
* Does this new cpu bringup a new core?
*/
- if (cpumask_weight(cpu_sibling_mask(cpu)) == 1) {
+ if (cpumask_weight(&c->sibling_map) == 1) {
/*
* for each core in package, increment
* the booted_cores for this new cpu
*/
- if (cpumask_first(cpu_sibling_mask(i)) == i)
+ if (cpumask_first(&o->sibling_map) == i)
c->booted_cores++;
/*
* increment the core count for all
@@ -910,7 +906,7 @@ static __init void disable_smp(void)
physid_set_mask_of_physid(boot_cpu_physical_apicid, &phys_cpu_present_map);
else
physid_set_mask_of_physid(0, &phys_cpu_present_map);
- cpumask_set_cpu(0, cpu_sibling_mask(0));
+ cpumask_set_cpu(0, &cpu_data(0).sibling_map);
cpumask_set_cpu(0, cpu_core_mask(0));
}

@@ -1048,7 +1044,6 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)

current_thread_info()->cpu = 0; /* needed? */
for_each_possible_cpu(i) {
- zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
}
set_cpu_sibling_map(0);
@@ -1243,13 +1238,13 @@ static void remove_siblinginfo(int cpu)
/*/
* last thread sibling in this cpu core going down
*/
- if (cpumask_weight(cpu_sibling_mask(cpu)) == 1)
+ if (cpumask_weight(&c->sibling_map) == 1)
cpu_data(sibling).booted_cores--;
}

- for_each_cpu(sibling, cpu_sibling_mask(cpu))
- cpumask_clear_cpu(cpu, cpu_sibling_mask(sibling));
- cpumask_clear(cpu_sibling_mask(cpu));
+ for_each_cpu(sibling, &c->sibling_map)
+ cpumask_clear_cpu(cpu, &c->sibling_map);
+ cpumask_clear(&c->sibling_map);
cpumask_clear(cpu_core_mask(cpu));
c->phys_proc_id = 0;
c->cpu_core_id = 0;
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 98ab130..ae3503e 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -370,11 +370,8 @@ static struct p4_event_binding p4_events[NUM_EVENTS] = {
or "odd" part of all the divided resources. */
static unsigned int get_stagger(void)
{
-#ifdef CONFIG_SMP
int cpu = smp_processor_id();
- return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
-#endif
- return 0;
+ return cpu != cpumask_first(&cpu_data(cpu).sibling_map);
}


diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index b9f7a86..00f32c0 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -223,7 +223,6 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
cpu_data(0).x86_max_cores = 1;

for_each_possible_cpu(i) {
- zalloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
zalloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
}
set_cpu_sibling_map(0);
diff --git a/drivers/cpufreq/p4-clockmod.c b/drivers/cpufreq/p4-clockmod.c
index 6be3e07..a14b9b0 100644
--- a/drivers/cpufreq/p4-clockmod.c
+++ b/drivers/cpufreq/p4-clockmod.c
@@ -203,9 +203,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
int cpuid = 0;
unsigned int i;

-#ifdef CONFIG_SMP
- cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
-#endif
+ cpumask_copy(policy->cpus, &c->sibling_map);

/* Errata workaround */
cpuid = (c->x86 << 8) | (c->x86_model << 4) | c->x86_mask;
diff --git a/drivers/cpufreq/speedstep-ich.c b/drivers/cpufreq/speedstep-ich.c
index a748ce7..630926a 100644
--- a/drivers/cpufreq/speedstep-ich.c
+++ b/drivers/cpufreq/speedstep-ich.c
@@ -326,14 +326,14 @@ static void get_freqs_on_cpu(void *_get_freqs)

static int speedstep_cpu_init(struct cpufreq_policy *policy)
{
+ struct cpuinfo_x86 *c = &cpu_data(policy->cpu);
int result;
unsigned int policy_cpu, speed;
struct get_freqs gf;

/* only run on CPU to be set, or on its sibling */
-#ifdef CONFIG_SMP
- cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
-#endif
+ cpumask_copy(policy->cpus, c->sibling_map);
+
policy_cpu = cpumask_any_and(policy->cpus, cpu_online_mask);

/* detect low and high frequency and transition latency */
diff --git a/drivers/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index a6c6ec3..fdf1590 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -61,11 +61,7 @@ MODULE_PARM_DESC(tjmax, "TjMax value in degrees Celsius");
#define TO_CORE_ID(cpu) cpu_data(cpu).cpu_core_id
#define TO_ATTR_NO(cpu) (TO_CORE_ID(cpu) + BASE_SYSFS_ATTR_NO)

-#ifdef CONFIG_SMP
-#define for_each_sibling(i, cpu) for_each_cpu(i, cpu_sibling_mask(cpu))
-#else
-#define for_each_sibling(i, cpu) for (i = 0; false; )
-#endif
+#define for_each_sibling(i, cpu) for_each_cpu(i, &cpu_data(cpu).sibling_map)

/*
* Per-Core Temperature Data
--
1.7.9

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/