aboutsummaryrefslogtreecommitdiff
path: root/arch/x86/kernel/cpu
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86/kernel/cpu')
-rw-r--r--arch/x86/kernel/cpu/Makefile7
-rw-r--r--arch/x86/kernel/cpu/amd.c47
-rw-r--r--arch/x86/kernel/cpu/common.c3
-rw-r--r--arch/x86/kernel/cpu/cpu.h1
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c127
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-inject.c20
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c23
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce_intel.c10
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c23
-rw-r--r--arch/x86/kernel/cpu/perf_event.c442
-rw-r--r--arch/x86/kernel/cpu/perf_event.h505
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd.c38
-rw-r--r--arch/x86/kernel/cpu/perf_event_amd_ibs.c294
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c146
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_ds.c79
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c28
-rw-r--r--arch/x86/kernel/cpu/perf_event_p4.c10
-rw-r--r--arch/x86/kernel/cpu/perf_event_p6.c9
18 files changed, 1157 insertions, 655 deletions
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 6042981d030..fe6eb197f84 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -28,10 +28,15 @@ obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o
obj-$(CONFIG_PERF_EVENTS) += perf_event.o
+ifdef CONFIG_PERF_EVENTS
+obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o
+obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_p4.o perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o
+endif
+
obj-$(CONFIG_X86_MCE) += mcheck/
obj-$(CONFIG_MTRR) += mtrr/
-obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o
+obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o perf_event_amd_ibs.o
quiet_cmd_mkcapflags = MKCAP $@
cmd_mkcapflags = $(PERL) $(srctree)/$(src)/mkcapflags.pl $< $@
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index d898fab0e12..46ae4f65fc7 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -1,5 +1,6 @@
#include <linux/init.h>
#include <linux/bitops.h>
+#include <linux/elf.h>
#include <linux/mm.h>
#include <linux/io.h>
@@ -410,6 +411,34 @@ static void __cpuinit early_init_amd_mc(struct cpuinfo_x86 *c)
#endif
}
+static void __cpuinit bsp_init_amd(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
+
+ if (c->x86 > 0x10 ||
+ (c->x86 == 0x10 && c->x86_model >= 0x2)) {
+ u64 val;
+
+ rdmsrl(MSR_K7_HWCR, val);
+ if (!(val & BIT(24)))
+ printk(KERN_WARNING FW_BUG "TSC doesn't count "
+ "with P0 frequency!\n");
+ }
+ }
+
+ if (c->x86 == 0x15) {
+ unsigned long upperbit;
+ u32 cpuid, assoc;
+
+ cpuid = cpuid_edx(0x80000005);
+ assoc = cpuid >> 16 & 0xff;
+ upperbit = ((cpuid >> 24) << 10) / assoc;
+
+ va_align.mask = (upperbit - 1) & PAGE_MASK;
+ va_align.flags = ALIGN_VA_32 | ALIGN_VA_64;
+ }
+}
+
static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
{
u32 dummy;
@@ -445,23 +474,6 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c)
#endif
rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy);
-
- /* We need to do the following only once */
- if (c != &boot_cpu_data)
- return;
-
- if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
-
- if (c->x86 > 0x10 ||
- (c->x86 == 0x10 && c->x86_model >= 0x2)) {
- u64 val;
-
- rdmsrl(MSR_K7_HWCR, val);
- if (!(val & BIT(24)))
- printk(KERN_WARNING FW_BUG "TSC doesn't count "
- "with P0 frequency!\n");
- }
- }
}
static void __cpuinit init_amd(struct cpuinfo_x86 *c)
@@ -683,6 +695,7 @@ static const struct cpu_dev __cpuinitconst amd_cpu_dev = {
.c_size_cache = amd_size_cache,
#endif
.c_early_init = early_init_amd,
+ .c_bsp_init = bsp_init_amd,
.c_init = init_amd,
.c_x86_vendor = X86_VENDOR_AMD,
};
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 62184390a60..ec63df54d13 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -681,6 +681,9 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
filter_cpuid_features(c, false);
setup_smep(c);
+
+ if (this_cpu->c_bsp_init)
+ this_cpu->c_bsp_init(c);
}
void __init early_cpu_init(void)
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index e765633f210..1b22dcc51af 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -18,6 +18,7 @@ struct cpu_dev {
struct cpu_model_info c_models[4];
void (*c_early_init)(struct cpuinfo_x86 *);
+ void (*c_bsp_init)(struct cpuinfo_x86 *);
void (*c_init)(struct cpuinfo_x86 *);
void (*c_identify)(struct cpuinfo_x86 *);
unsigned int (*c_size_cache)(struct cpuinfo_x86 *, unsigned int);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index c105c533ed9..a3b0811693c 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -151,28 +151,17 @@ union _cpuid4_leaf_ecx {
u32 full;
};
-struct amd_l3_cache {
- struct amd_northbridge *nb;
- unsigned indices;
- u8 subcaches[4];
-};
-
-struct _cpuid4_info {
+struct _cpuid4_info_regs {
union _cpuid4_leaf_eax eax;
union _cpuid4_leaf_ebx ebx;
union _cpuid4_leaf_ecx ecx;
unsigned long size;
- struct amd_l3_cache *l3;
- DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
+ struct amd_northbridge *nb;
};
-/* subset of above _cpuid4_info w/o shared_cpu_map */
-struct _cpuid4_info_regs {
- union _cpuid4_leaf_eax eax;
- union _cpuid4_leaf_ebx ebx;
- union _cpuid4_leaf_ecx ecx;
- unsigned long size;
- struct amd_l3_cache *l3;
+struct _cpuid4_info {
+ struct _cpuid4_info_regs base;
+ DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
};
unsigned short num_cache_leaves;
@@ -314,16 +303,23 @@ struct _cache_attr {
/*
* L3 cache descriptors
*/
-static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
+static void __cpuinit amd_calc_l3_indices(struct amd_northbridge *nb)
{
+ struct amd_l3_cache *l3 = &nb->l3_cache;
unsigned int sc0, sc1, sc2, sc3;
u32 val = 0;
- pci_read_config_dword(l3->nb->misc, 0x1C4, &val);
+ pci_read_config_dword(nb->misc, 0x1C4, &val);
/* calculate subcache sizes */
l3->subcaches[0] = sc0 = !(val & BIT(0));
l3->subcaches[1] = sc1 = !(val & BIT(4));
+
+ if (boot_cpu_data.x86 == 0x15) {
+ l3->subcaches[0] = sc0 += !(val & BIT(1));
+ l3->subcaches[1] = sc1 += !(val & BIT(5));
+ }
+
l3->subcaches[2] = sc2 = !(val & BIT(8)) + !(val & BIT(9));
l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
@@ -333,33 +329,16 @@ static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf,
int index)
{
- static struct amd_l3_cache *__cpuinitdata l3_caches;
int node;
/* only for L3, and not in virtualized environments */
- if (index < 3 || amd_nb_num() == 0)
+ if (index < 3)
return;
- /*
- * Strictly speaking, the amount in @size below is leaked since it is
- * never freed but this is done only on shutdown so it doesn't matter.
- */
- if (!l3_caches) {
- int size = amd_nb_num() * sizeof(struct amd_l3_cache);
-
- l3_caches = kzalloc(size, GFP_ATOMIC);
- if (!l3_caches)
- return;
- }
-
node = amd_get_nb_id(smp_processor_id());
-
- if (!l3_caches[node].nb) {
- l3_caches[node].nb = node_to_amd_nb(node);
- amd_calc_l3_indices(&l3_caches[node]);
- }
-
- this_leaf->l3 = &l3_caches[node];
+ this_leaf->nb = node_to_amd_nb(node);
+ if (this_leaf->nb && !this_leaf->nb->l3_cache.indices)
+ amd_calc_l3_indices(this_leaf->nb);
}
/*
@@ -369,11 +348,11 @@ static void __cpuinit amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf,
*
* @returns: the disabled index if used or negative value if slot free.
*/
-int amd_get_l3_disable_slot(struct amd_l3_cache *l3, unsigned slot)
+int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot)
{
unsigned int reg = 0;
- pci_read_config_dword(l3->nb->misc, 0x1BC + slot * 4, &reg);
+ pci_read_config_dword(nb->misc, 0x1BC + slot * 4, &reg);
/* check whether this slot is activated already */
if (reg & (3UL << 30))
@@ -387,11 +366,10 @@ static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
{
int index;
- if (!this_leaf->l3 ||
- !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+ if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
return -EINVAL;
- index = amd_get_l3_disable_slot(this_leaf->l3, slot);
+ index = amd_get_l3_disable_slot(this_leaf->base.nb, slot);
if (index >= 0)
return sprintf(buf, "%d\n", index);
@@ -408,7 +386,7 @@ show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf, \
SHOW_CACHE_DISABLE(0)
SHOW_CACHE_DISABLE(1)
-static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
+static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu,
unsigned slot, unsigned long idx)
{
int i;
@@ -421,10 +399,10 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
for (i = 0; i < 4; i++) {
u32 reg = idx | (i << 20);
- if (!l3->subcaches[i])
+ if (!nb->l3_cache.subcaches[i])
continue;
- pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
+ pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
/*
* We need to WBINVD on a core on the node containing the L3
@@ -434,7 +412,7 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
wbinvd_on_cpu(cpu);
reg |= BIT(31);
- pci_write_config_dword(l3->nb->misc, 0x1BC + slot * 4, reg);
+ pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
}
}
@@ -448,24 +426,24 @@ static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
*
* @return: 0 on success, error status on failure
*/
-int amd_set_l3_disable_slot(struct amd_l3_cache *l3, int cpu, unsigned slot,
+int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu, unsigned slot,
unsigned long index)
{
int ret = 0;
/* check if @slot is already used or the index is already disabled */
- ret = amd_get_l3_disable_slot(l3, slot);
+ ret = amd_get_l3_disable_slot(nb, slot);
if (ret >= 0)
return -EINVAL;
- if (index > l3->indices)
+ if (index > nb->l3_cache.indices)
return -EINVAL;
/* check whether the other slot has disabled the same index already */
- if (index == amd_get_l3_disable_slot(l3, !slot))
+ if (index == amd_get_l3_disable_slot(nb, !slot))
return -EINVAL;
- amd_l3_disable_index(l3, cpu, slot, index);
+ amd_l3_disable_index(nb, cpu, slot, index);
return 0;
}
@@ -480,8 +458,7 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!this_leaf->l3 ||
- !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+ if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
return -EINVAL;
cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
@@ -489,7 +466,7 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
if (strict_strtoul(buf, 10, &val) < 0)
return -EINVAL;
- err = amd_set_l3_disable_slot(this_leaf->l3, cpu, slot, val);
+ err = amd_set_l3_disable_slot(this_leaf->base.nb, cpu, slot, val);
if (err) {
if (err == -EEXIST)
printk(KERN_WARNING "L3 disable slot %d in use!\n",
@@ -518,7 +495,7 @@ static struct _cache_attr cache_disable_1 = __ATTR(cache_disable_1, 0644,
static ssize_t
show_subcaches(struct _cpuid4_info *this_leaf, char *buf, unsigned int cpu)
{
- if (!this_leaf->l3 || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
return -EINVAL;
return sprintf(buf, "%x\n", amd_get_subcaches(cpu));
@@ -533,7 +510,7 @@ store_subcaches(struct _cpuid4_info *this_leaf, const char *buf, size_t count,
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- if (!this_leaf->l3 || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ if (!this_leaf->base.nb || !amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
return -EINVAL;
if (strict_strtoul(buf, 16, &val) < 0)
@@ -769,7 +746,7 @@ static void __cpuinit cache_shared_cpu_map_setup(unsigned int cpu, int index)
return;
}
this_leaf = CPUID4_INFO_IDX(cpu, index);
- num_threads_sharing = 1 + this_leaf->eax.split.num_threads_sharing;
+ num_threads_sharing = 1 + this_leaf->base.eax.split.num_threads_sharing;
if (num_threads_sharing == 1)
cpumask_set_cpu(cpu, to_cpumask(this_leaf->shared_cpu_map));
@@ -820,29 +797,19 @@ static void __cpuinit free_cache_attributes(unsigned int cpu)
for (i = 0; i < num_cache_leaves; i++)
cache_remove_shared_cpu_map(cpu, i);
- kfree(per_cpu(ici_cpuid4_info, cpu)->l3);
kfree(per_cpu(ici_cpuid4_info, cpu));
per_cpu(ici_cpuid4_info, cpu) = NULL;
}
-static int
-__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
-{
- struct _cpuid4_info_regs *leaf_regs =
- (struct _cpuid4_info_regs *)this_leaf;
-
- return cpuid4_cache_lookup_regs(index, leaf_regs);
-}
-
static void __cpuinit get_cpu_leaves(void *_retval)
{
int j, *retval = _retval, cpu = smp_processor_id();
/* Do cpuid and store the results */
for (j = 0; j < num_cache_leaves; j++) {
- struct _cpuid4_info *this_leaf;
- this_leaf = CPUID4_INFO_IDX(cpu, j);
- *retval = cpuid4_cache_lookup(j, this_leaf);
+ struct _cpuid4_info *this_leaf = CPUID4_INFO_IDX(cpu, j);
+
+ *retval = cpuid4_cache_lookup_regs(j, &this_leaf->base);
if (unlikely(*retval < 0)) {
int i;
@@ -900,16 +867,16 @@ static ssize_t show_##file_name(struct _cpuid4_info *this_leaf, char *buf, \
return sprintf(buf, "%lu\n", (unsigned long)this_leaf->object + val); \
}
-show_one_plus(level, eax.split.level, 0);
-show_one_plus(coherency_line_size, ebx.split.coherency_line_size, 1);
-show_one_plus(physical_line_partition, ebx.split.physical_line_partition, 1);
-show_one_plus(ways_of_associativity, ebx.split.ways_of_associativity, 1);
-show_one_plus(number_of_sets, ecx.split.number_of_sets, 1);
+show_one_plus(level, base.eax.split.level, 0);
+show_one_plus(coherency_line_size, base.ebx.split.coherency_line_size, 1);
+show_one_plus(physical_line_partition, base.ebx.split.physical_line_partition, 1);
+show_one_plus(ways_of_associativity, base.ebx.split.ways_of_associativity, 1);
+show_one_plus(number_of_sets, base.ecx.split.number_of_sets, 1);
static ssize_t show_size(struct _cpuid4_info *this_leaf, char *buf,
unsigned int cpu)
{
- return sprintf(buf, "%luK\n", this_leaf->size / 1024);
+ return sprintf(buf, "%luK\n", this_leaf->base.size / 1024);
}
static ssize_t show_shared_cpu_map_func(struct _cpuid4_info *this_leaf,
@@ -946,7 +913,7 @@ static inline ssize_t show_shared_cpu_list(struct _cpuid4_info *leaf, char *buf,
static ssize_t show_type(struct _cpuid4_info *this_leaf, char *buf,
unsigned int cpu)
{
- switch (this_leaf->eax.split.type) {
+ switch (this_leaf->base.eax.split.type) {
case CACHE_TYPE_DATA:
return sprintf(buf, "Data\n");
case CACHE_TYPE_INST:
@@ -1135,7 +1102,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
ktype_cache.default_attrs = default_attrs;
#ifdef CONFIG_AMD_NB
- if (this_leaf->l3)
+ if (this_leaf->base.nb)
ktype_cache.default_attrs = amd_l3_attrs();
#endif
retval = kobject_init_and_add(&(this_object->kobj),
diff --git a/arch/x86/kernel/cpu/mcheck/mce-inject.c b/arch/x86/kernel/cpu/mcheck/mce-inject.c
index 0ed633c5048..6199232161c 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-inject.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-inject.c
@@ -78,27 +78,20 @@ static void raise_exception(struct mce *m, struct pt_regs *pregs)
static cpumask_var_t mce_inject_cpumask;
-static int mce_raise_notify(struct notifier_block *self,
- unsigned long val, void *data)
+static int mce_raise_notify(unsigned int cmd, struct pt_regs *regs)
{
- struct die_args *args = (struct die_args *)data;
int cpu = smp_processor_id();
struct mce *m = &__get_cpu_var(injectm);
- if (val != DIE_NMI || !cpumask_test_cpu(cpu, mce_inject_cpumask))
- return NOTIFY_DONE;
+ if (!cpumask_test_cpu(cpu, mce_inject_cpumask))
+ return NMI_DONE;
cpumask_clear_cpu(cpu, mce_inject_cpumask);
if (m->inject_flags & MCJ_EXCEPTION)
- raise_exception(m, args->regs);
+ raise_exception(m, regs);
else if (m->status)
raise_poll(m);
- return NOTIFY_STOP;
+ return NMI_HANDLED;
}
-static struct notifier_block mce_raise_nb = {
- .notifier_call = mce_raise_notify,
- .priority = NMI_LOCAL_NORMAL_PRIOR,
-};
-
/* Inject mce on current CPU */
static int raise_local(void)
{
@@ -216,7 +209,8 @@ static int inject_init(void)
return -ENOMEM;
printk(KERN_INFO "Machine check injector initialized\n");
mce_chrdev_ops.write = mce_write;
- register_die_notifier(&mce_raise_nb);
+ register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0,
+ "mce_notify");
return 0;
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index ad8d8973a39..7b5063a6ad4 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -913,9 +913,6 @@ void do_machine_check(struct pt_regs *regs, long error_code)
percpu_inc(mce_exception_count);
- if (notify_die(DIE_NMI, "machine check", regs, error_code,
- 18, SIGKILL) == NOTIFY_STOP)
- goto out;
if (!banks)
goto out;
@@ -1145,6 +1142,15 @@ static void mce_start_timer(unsigned long data)
add_timer_on(t, smp_processor_id());
}
+/* Must not be called in IRQ context where del_timer_sync() can deadlock */
+static void mce_timer_delete_all(void)
+{
+ int cpu;
+
+ for_each_online_cpu(cpu)
+ del_timer_sync(&per_cpu(mce_timer, cpu));
+}
+
static void mce_do_trigger(struct work_struct *work)
{
call_usermodehelper(mce_helper, mce_helper_argv, NULL, UMH_NO_WAIT);
@@ -1755,7 +1761,6 @@ static struct syscore_ops mce_syscore_ops = {
static void mce_cpu_restart(void *data)
{
- del_timer_sync(&__get_cpu_var(mce_timer));
if (!mce_available(__this_cpu_ptr(&cpu_info)))
return;
__mcheck_cpu_init_generic();
@@ -1765,16 +1770,15 @@ static void mce_cpu_restart(void *data)
/* Reinit MCEs after user configuration changes */
static void mce_restart(void)
{
+ mce_timer_delete_all();
on_each_cpu(mce_cpu_restart, NULL, 1);
}
/* Toggle features for corrected errors */
-static void mce_disable_ce(void *all)
+static void mce_disable_cmci(void *data)
{
if (!mce_available(__this_cpu_ptr(&cpu_info)))
return;
- if (all)
- del_timer_sync(&__get_cpu_var(mce_timer));
cmci_clear();
}
@@ -1857,7 +1861,8 @@ static ssize_t set_ignore_ce(struct sys_device *s,
if (mce_ignore_ce ^ !!new) {
if (new) {
/* disable ce features */
- on_each_cpu(mce_disable_ce, (void *)1, 1);
+ mce_timer_delete_all();
+ on_each_cpu(mce_disable_cmci, NULL, 1);
mce_ignore_ce = 1;
} else {
/* enable ce features */
@@ -1880,7 +1885,7 @@ static ssize_t set_cmci_disabled(struct sys_device *s,
if (mce_cmci_disabled ^ !!new) {
if (new) {
/* disable cmci */
- on_each_cpu(mce_disable_ce, NULL, 1);
+ on_each_cpu(mce_disable_cmci, NULL, 1);
mce_cmci_disabled = 1;
} else {
/* enable cmci */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index 8694ef56459..38e49bc95ff 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -28,7 +28,7 @@ static DEFINE_PER_CPU(mce_banks_t, mce_banks_owned);
* cmci_discover_lock protects against parallel discovery attempts
* which could race against each other.
*/
-static DEFINE_SPINLOCK(cmci_discover_lock);
+static DEFINE_RAW_SPINLOCK(cmci_discover_lock);
#define CMCI_THRESHOLD 1
@@ -85,7 +85,7 @@ static void cmci_discover(int banks, int boot)
int hdr = 0;
int i;
- spin_lock_irqsave(&cmci_discover_lock, flags);
+ raw_spin_lock_irqsave(&cmci_discover_lock, flags);
for (i = 0; i < banks; i++) {
u64 val;
@@ -116,7 +116,7 @@ static void cmci_discover(int banks, int boot)
WARN_ON(!test_bit(i, __get_cpu_var(mce_poll_banks)));
}
}
- spin_unlock_irqrestore(&cmci_discover_lock, flags);
+ raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
if (hdr)
printk(KERN_CONT "\n");
}
@@ -150,7 +150,7 @@ void cmci_clear(void)
if (!cmci_supported(&banks))
return;
- spin_lock_irqsave(&cmci_discover_lock, flags);
+ raw_spin_lock_irqsave(&cmci_discover_lock, flags);
for (i = 0; i < banks; i++) {
if (!test_bit(i, __get_cpu_var(mce_banks_owned)))
continue;
@@ -160,7 +160,7 @@ void cmci_clear(void)
wrmsrl(MSR_IA32_MCx_CTL2(i), val);
__clear_bit(i, __get_cpu_var(mce_banks_owned));
}
- spin_unlock_irqrestore(&cmci_discover_lock, flags);
+ raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
/*
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index d944bf6c50e..0a630dd4b62 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -11,6 +11,8 @@
*/
#include <linux/types.h>
+#include <linux/time.h>
+#include <linux/clocksource.h>
#include <linux/module.h>
#include <asm/processor.h>
#include <asm/hypervisor.h>
@@ -36,6 +38,25 @@ static bool __init ms_hyperv_platform(void)
!memcmp("Microsoft Hv", hyp_signature, 12);
}
+static cycle_t read_hv_clock(struct clocksource *arg)
+{
+ cycle_t current_tick;
+ /*
+ * Read the partition counter to get the current tick count. This count
+ * is set to 0 when the partition is created and is incremented in
+ * 100 nanosecond units.
+ */
+ rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
+ return current_tick;
+}
+
+static struct clocksource hyperv_cs = {
+ .name = "hyperv_clocksource",
+ .rating = 400, /* use this when running on Hyperv*/
+ .read = read_hv_clock,
+ .mask = CLOCKSOURCE_MASK(64),
+};
+
static void __init ms_hyperv_init_platform(void)
{
/*
@@ -46,6 +67,8 @@ static void __init ms_hyperv_init_platform(void)
printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n",
ms_hyperv.features, ms_hyperv.hints);
+
+ clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100);
}
const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index cfa62ec090e..640891014b2 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -32,6 +32,8 @@
#include <asm/smp.h>
#include <asm/alternative.h>
+#include "perf_event.h"
+
#if 0
#undef wrmsrl
#define wrmsrl(msr, val) \
@@ -43,283 +45,17 @@ do { \
} while (0)
#endif
-/*
- * | NHM/WSM | SNB |
- * register -------------------------------
- * | HT | no HT | HT | no HT |
- *-----------------------------------------
- * offcore | core | core | cpu | core |
- * lbr_sel | core | core | cpu | core |
- * ld_lat | cpu | core | cpu | core |
- *-----------------------------------------
- *
- * Given that there is a small number of shared regs,
- * we can pre-allocate their slot in the per-cpu
- * per-core reg tables.
- */
-enum extra_reg_type {
- EXTRA_REG_NONE = -1, /* not used */
-
- EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */
- EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */
-
- EXTRA_REG_MAX /* number of entries needed */
-};
-
-struct event_constraint {
- union {
- unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
- u64 idxmsk64;
- };
- u64 code;
- u64 cmask;
- int weight;
-};
-
-struct amd_nb {
- int nb_id; /* NorthBridge id */
- int refcnt; /* reference count */
- struct perf_event *owners[X86_PMC_IDX_MAX];
- struct event_constraint event_constraints[X86_PMC_IDX_MAX];
-};
-
-struct intel_percore;
-
-#define MAX_LBR_ENTRIES 16
-
-struct cpu_hw_events {
- /*
- * Generic x86 PMC bits
- */
- struct perf_event *events[X86_PMC_IDX_MAX]; /* in counter order */
- unsigned long active_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
- unsigned long running[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
- int enabled;
-
- int n_events;
- int n_added;
- int n_txn;
- int assign[X86_PMC_IDX_MAX]; /* event to counter assignment */
- u64 tags[X86_PMC_IDX_MAX];
- struct perf_event *event_list[X86_PMC_IDX_MAX]; /* in enabled order */
-
- unsigned int group_flag;
-
- /*
- * Intel DebugStore bits
- */
- struct debug_store *ds;
- u64 pebs_enabled;
-
- /*
- * Intel LBR bits
- */
- int lbr_users;
- void *lbr_context;
- struct perf_branch_stack lbr_stack;
- struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES];
-
- /*
- * manage shared (per-core, per-cpu) registers
- * used on Intel NHM/WSM/SNB
- */
- struct intel_shared_regs *shared_regs;
-
- /*
- * AMD specific bits
- */
- struct amd_nb *amd_nb;
-};
-
-#define __EVENT_CONSTRAINT(c, n, m, w) {\
- { .idxmsk64 = (n) }, \
- .code = (c), \
- .cmask = (m), \
- .weight = (w), \
-}
-
-#define EVENT_CONSTRAINT(c, n, m) \
- __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n))
-
-/*
- * Constraint on the Event code.
- */
-#define INTEL_EVENT_CONSTRAINT(c, n) \
- EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT)
-
-/*
- * Constraint on the Event code + UMask + fixed-mask
- *
- * filter mask to validate fixed counter events.
- * the following filters disqualify for fixed counters:
- * - inv
- * - edge
- * - cnt-mask
- * The other filters are supported by fixed counters.
- * The any-thread option is supported starting with v3.
- */
-#define FIXED_EVENT_CONSTRAINT(c, n) \
- EVENT_CONSTRAINT(c, (1ULL << (32+n)), X86_RAW_EVENT_MASK)
-
-/*
- * Constraint on the Event code + UMask
- */
-#define INTEL_UEVENT_CONSTRAINT(c, n) \
- EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
-
-#define EVENT_CONSTRAINT_END \
- EVENT_CONSTRAINT(0, 0, 0)
-
-#define for_each_event_constraint(e, c) \
- for ((e) = (c); (e)->weight; (e)++)
-
-/*
- * Per register state.
- */
-struct er_account {
- raw_spinlock_t lock; /* per-core: protect structure */
- u64 config; /* extra MSR config */
- u64 reg; /* extra MSR number */
- atomic_t ref; /* reference count */
-};
-
-/*
- * Extra registers for specific events.
- *
- * Some events need large masks and require external MSRs.
- * Those extra MSRs end up being shared for all events on
- * a PMU and sometimes between PMU of sibling HT threads.
- * In either case, the kernel needs to handle conflicting
- * accesses to those extra, shared, regs. The data structure
- * to manage those registers is stored in cpu_hw_event.
- */
-struct extra_reg {
- unsigned int event;
- unsigned int msr;
- u64 config_mask;
- u64 valid_mask;
- int idx; /* per_xxx->regs[] reg index */
-};
-
-#define EVENT_EXTRA_REG(e, ms, m, vm, i) { \
- .event = (e), \
- .msr = (ms), \
- .config_mask = (m), \
- .valid_mask = (vm), \
- .idx = EXTRA_REG_##i \
- }
-
-#define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \
- EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx)
-
-#define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0)
-
-union perf_capabilities {
- struct {
- u64 lbr_format : 6;
- u64 pebs_trap : 1;
- u64 pebs_arch_reg : 1;
- u64 pebs_format : 4;
- u64 smm_freeze : 1;
- };
- u64 capabilities;
-};
-
-/*
- * struct x86_pmu - generic x86 pmu
- */
-struct x86_pmu {
- /*
- * Generic x86 PMC bits
- */
- const char *name;
- int version;
- int (*handle_irq)(struct pt_regs *);
- void (*disable_all)(void);
- void (*enable_all)(int added);
- void (*enable)(struct perf_event *);
- void (*disable)(struct perf_event *);
- int (*hw_config)(struct perf_event *event);
- int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
- unsigned eventsel;
- unsigned perfctr;
- u64 (*event_map)(int);
- int max_events;
- int num_counters;
- int num_counters_fixed;
- int cntval_bits;
- u64 cntval_mask;
- int apic;
- u64 max_period;
- struct event_constraint *
- (*get_event_constraints)(struct cpu_hw_events *cpuc,
- struct perf_event *event);
-
- void (*put_event_constraints)(struct cpu_hw_events *cpuc,
- struct perf_event *event);
- struct event_constraint *event_constraints;
- void (*quirks)(void);
- int perfctr_second_write;
-
- int (*cpu_prepare)(int cpu);
- void (*cpu_starting)(int cpu);
- void (*cpu_dying)(int cpu);
- void (*cpu_dead)(int cpu);
-
- /*
- * Intel Arch Perfmon v2+
- */
- u64 intel_ctrl;
- union perf_capabilities intel_cap;
+struct x86_pmu x86_pmu __read_mostly;
- /*
- * Intel DebugStore bits
- */
- int bts, pebs;
- int bts_active, pebs_active;
- int pebs_record_size;
- void (*drain_pebs)(struct pt_regs *regs);
- struct event_constraint *pebs_constraints;
-
- /*
- * Intel LBR
- */
- unsigned long lbr_tos, lbr_from, lbr_to; /* MSR base regs */
- int lbr_nr; /* hardware stack size */
-
- /*
- * Extra registers for events
- */
- struct extra_reg *extra_regs;
- unsigned int er_flags;
-};
-
-#define ERF_NO_HT_SHARING 1
-#define ERF_HAS_RSP_1 2
-
-static struct x86_pmu x86_pmu __read_mostly;
-
-static DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
+DEFINE_PER_CPU(struct cpu_hw_events, cpu_hw_events) = {
.enabled = 1,
};
-static int x86_perf_event_set_period(struct perf_event *event);
-
-/*
- * Generalized hw caching related hw_event table, filled
- * in on a per model basis. A value of 0 means
- * 'not supported', -1 means 'hw_event makes no sense on
- * this CPU', any other value means the raw hw_event
- * ID.
- */
-
-#define C(x) PERF_COUNT_HW_CACHE_##x
-
-static u64 __read_mostly hw_cache_event_ids
+u64 __read_mostly hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
[PERF_COUNT_HW_CACHE_RESULT_MAX];
-static u64 __read_mostly hw_cache_extra_regs
+u64 __read_mostly hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_M