summaryrefslogtreecommitdiffstats
path: root/arch/x86/kernel/cpu
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-05-18 08:49:13 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-05-18 08:49:13 -0700
commit07d77759c95d899b84f8e473a01cff001019dd5f (patch)
treed039fa6b38475868ebf2bd63ec14f49031d3f0b2 /arch/x86/kernel/cpu
parentb7723f9d21d8d6043e63f5e3e412f321f5f1900c (diff)
parent3998d095354d2a3062bdaa821ef07a1e1c82873c (diff)
Merge branch 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'x86-cpu-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: x86, hypervisor: add missing <linux/module.h> Modify the VMware balloon driver for the new x86_hyper API x86, hypervisor: Export the x86_hyper* symbols x86: Clean up the hypervisor layer x86, HyperV: fix up the license to mshyperv.c x86: Detect running on a Microsoft HyperV system x86, cpu: Make APERF/MPERF a normal table-driven flag x86, k8: Fix build error when K8_NB is disabled x86, cacheinfo: Disable index in all four subcaches x86, cacheinfo: Make L3 cache info per node x86, cacheinfo: Reorganize AMD L3 cache structure x86, cacheinfo: Turn off L3 cache index disable feature in virtualized environments x86, cacheinfo: Unify AMD L3 cache index disable checking cpufreq: Unify sysfs attribute definition macros powernow-k8: Fix frequency reporting x86, cpufreq: Add APERF/MPERF support for AMD processors x86: Unify APERF/MPERF support powernow-k8: Add core performance boost support x86, cpu: Add AMD core boosting feature flag to /proc/cpuinfo Fix up trivial conflicts in arch/x86/kernel/cpu/intel_cacheinfo.c and drivers/cpufreq/cpufreq_ondemand.c
Diffstat (limited to 'arch/x86/kernel/cpu')
-rw-r--r--arch/x86/kernel/cpu/Makefile2
-rw-r--r--arch/x86/kernel/cpu/addon_cpuid_features.c14
-rw-r--r--arch/x86/kernel/cpu/cpufreq/Makefile4
-rw-r--r--arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c44
-rw-r--r--arch/x86/kernel/cpu/cpufreq/mperf.c51
-rw-r--r--arch/x86/kernel/cpu/cpufreq/mperf.h9
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k8.c169
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k8.h2
-rw-r--r--arch/x86/kernel/cpu/hypervisor.c52
-rw-r--r--arch/x86/kernel/cpu/intel.c6
-rw-r--r--arch/x86/kernel/cpu/intel_cacheinfo.c177
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c55
-rw-r--r--arch/x86/kernel/cpu/vmware.c38
13 files changed, 467 insertions, 156 deletions
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index c202b62f367..3a785da34b6 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -14,7 +14,7 @@ CFLAGS_common.o := $(nostackp)
obj-y := intel_cacheinfo.o addon_cpuid_features.o
obj-y += proc.o capflags.o powerflags.o common.o
-obj-y += vmware.o hypervisor.o sched.o
+obj-y += vmware.o hypervisor.o sched.o mshyperv.o
obj-$(CONFIG_X86_32) += bugs.o cmpxchg.o
obj-$(CONFIG_X86_64) += bugs_64.o
diff --git a/arch/x86/kernel/cpu/addon_cpuid_features.c b/arch/x86/kernel/cpu/addon_cpuid_features.c
index 97ad79cdf68..10fa5684a66 100644
--- a/arch/x86/kernel/cpu/addon_cpuid_features.c
+++ b/arch/x86/kernel/cpu/addon_cpuid_features.c
@@ -30,12 +30,14 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c)
const struct cpuid_bit *cb;
static const struct cpuid_bit __cpuinitconst cpuid_bits[] = {
- { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 },
- { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 },
- { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a },
- { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a },
- { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a },
- { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a },
+ { X86_FEATURE_IDA, CR_EAX, 1, 0x00000006 },
+ { X86_FEATURE_ARAT, CR_EAX, 2, 0x00000006 },
+ { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006 },
+ { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007 },
+ { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a },
+ { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a },
+ { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a },
+ { X86_FEATURE_NRIPS, CR_EDX, 3, 0x8000000a },
{ 0, 0, 0, 0 }
};
diff --git a/arch/x86/kernel/cpu/cpufreq/Makefile b/arch/x86/kernel/cpu/cpufreq/Makefile
index 1840c0a5170..bd54bf67e6f 100644
--- a/arch/x86/kernel/cpu/cpufreq/Makefile
+++ b/arch/x86/kernel/cpu/cpufreq/Makefile
@@ -2,8 +2,8 @@
# K8 systems. ACPI is preferred to all other hardware-specific drivers.
# speedstep-* is preferred over p4-clockmod.
-obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o
-obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o
+obj-$(CONFIG_X86_POWERNOW_K8) += powernow-k8.o mperf.o
+obj-$(CONFIG_X86_ACPI_CPUFREQ) += acpi-cpufreq.o mperf.o
obj-$(CONFIG_X86_PCC_CPUFREQ) += pcc-cpufreq.o
obj-$(CONFIG_X86_POWERNOW_K6) += powernow-k6.o
obj-$(CONFIG_X86_POWERNOW_K7) += powernow-k7.o
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index 459168083b7..1d3cddaa40e 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -46,6 +46,7 @@
#include <asm/msr.h>
#include <asm/processor.h>
#include <asm/cpufeature.h>
+#include "mperf.h"
#define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, \
"acpi-cpufreq", msg)
@@ -71,8 +72,6 @@ struct acpi_cpufreq_data {
static DEFINE_PER_CPU(struct acpi_cpufreq_data *, acfreq_data);
-static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf);
-
/* acpi_perf_data is a pointer to percpu data. */
static struct acpi_processor_performance *acpi_perf_data;
@@ -240,45 +239,6 @@ static u32 get_cur_val(const struct cpumask *mask)
return cmd.val;
}
-/* Called via smp_call_function_single(), on the target CPU */
-static void read_measured_perf_ctrs(void *_cur)
-{
- struct aperfmperf *am = _cur;
-
- get_aperfmperf(am);
-}
-
-/*
- * Return the measured active (C0) frequency on this CPU since last call
- * to this function.
- * Input: cpu number
- * Return: Average CPU frequency in terms of max frequency (zero on error)
- *
- * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance
- * over a period of time, while CPU is in C0 state.
- * IA32_MPERF counts at the rate of max advertised frequency
- * IA32_APERF counts at the rate of actual CPU frequency
- * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and
- * no meaning should be associated with absolute values of these MSRs.
- */
-static unsigned int get_measured_perf(struct cpufreq_policy *policy,
- unsigned int cpu)
-{
- struct aperfmperf perf;
- unsigned long ratio;
- unsigned int retval;
-
- if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
- return 0;
-
- ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf);
- per_cpu(acfreq_old_perf, cpu) = perf;
-
- retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
-
- return retval;
-}
-
static unsigned int get_cur_freq_on_cpu(unsigned int cpu)
{
struct acpi_cpufreq_data *data = per_cpu(acfreq_data, cpu);
@@ -702,7 +662,7 @@ static int acpi_cpufreq_cpu_init(struct cpufreq_policy *policy)
/* Check for APERF/MPERF support in hardware */
if (cpu_has(c, X86_FEATURE_APERFMPERF))
- acpi_cpufreq_driver.getavg = get_measured_perf;
+ acpi_cpufreq_driver.getavg = cpufreq_get_measured_perf;
dprintk("CPU%u - ACPI performance management activated.\n", cpu);
for (i = 0; i < perf->state_count; i++)
diff --git a/arch/x86/kernel/cpu/cpufreq/mperf.c b/arch/x86/kernel/cpu/cpufreq/mperf.c
new file mode 100644
index 00000000000..911e193018a
--- /dev/null
+++ b/arch/x86/kernel/cpu/cpufreq/mperf.c
@@ -0,0 +1,51 @@
+#include <linux/kernel.h>
+#include <linux/smp.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/cpufreq.h>
+#include <linux/slab.h>
+
+#include "mperf.h"
+
+static DEFINE_PER_CPU(struct aperfmperf, acfreq_old_perf);
+
+/* Called via smp_call_function_single(), on the target CPU */
+static void read_measured_perf_ctrs(void *_cur)
+{
+ struct aperfmperf *am = _cur;
+
+ get_aperfmperf(am);
+}
+
+/*
+ * Return the measured active (C0) frequency on this CPU since last call
+ * to this function.
+ * Input: cpu number
+ * Return: Average CPU frequency in terms of max frequency (zero on error)
+ *
+ * We use IA32_MPERF and IA32_APERF MSRs to get the measured performance
+ * over a period of time, while CPU is in C0 state.
+ * IA32_MPERF counts at the rate of max advertised frequency
+ * IA32_APERF counts at the rate of actual CPU frequency
+ * Only IA32_APERF/IA32_MPERF ratio is architecturally defined and
+ * no meaning should be associated with absolute values of these MSRs.
+ */
+unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy,
+ unsigned int cpu)
+{
+ struct aperfmperf perf;
+ unsigned long ratio;
+ unsigned int retval;
+
+ if (smp_call_function_single(cpu, read_measured_perf_ctrs, &perf, 1))
+ return 0;
+
+ ratio = calc_aperfmperf_ratio(&per_cpu(acfreq_old_perf, cpu), &perf);
+ per_cpu(acfreq_old_perf, cpu) = perf;
+
+ retval = (policy->cpuinfo.max_freq * ratio) >> APERFMPERF_SHIFT;
+
+ return retval;
+}
+EXPORT_SYMBOL_GPL(cpufreq_get_measured_perf);
+MODULE_LICENSE("GPL");
diff --git a/arch/x86/kernel/cpu/cpufreq/mperf.h b/arch/x86/kernel/cpu/cpufreq/mperf.h
new file mode 100644
index 00000000000..5dbf2950dc2
--- /dev/null
+++ b/arch/x86/kernel/cpu/cpufreq/mperf.h
@@ -0,0 +1,9 @@
+/*
+ * (c) 2010 Advanced Micro Devices, Inc.
+ * Your use of this code is subject to the terms and conditions of the
+ * GNU general public license version 2. See "COPYING" or
+ * http://www.gnu.org/licenses/gpl.html
+ */
+
+unsigned int cpufreq_get_measured_perf(struct cpufreq_policy *policy,
+ unsigned int cpu);
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index b6215b9798e..6f3dc8fbbfd 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1,6 +1,5 @@
-
/*
- * (c) 2003-2006 Advanced Micro Devices, Inc.
+ * (c) 2003-2010 Advanced Micro Devices, Inc.
* Your use of this code is subject to the terms and conditions of the
* GNU general public license version 2. See "COPYING" or
* http://www.gnu.org/licenses/gpl.html
@@ -46,6 +45,7 @@
#define PFX "powernow-k8: "
#define VERSION "version 2.20.00"
#include "powernow-k8.h"
+#include "mperf.h"
/* serialize freq changes */
static DEFINE_MUTEX(fidvid_mutex);
@@ -54,6 +54,12 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
static int cpu_family = CPU_OPTERON;
+/* core performance boost */
+static bool cpb_capable, cpb_enabled;
+static struct msr __percpu *msrs;
+
+static struct cpufreq_driver cpufreq_amd64_driver;
+
#ifndef CONFIG_SMP
static inline const struct cpumask *cpu_core_mask(int cpu)
{
@@ -1249,6 +1255,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
struct powernow_k8_data *data;
struct init_on_cpu init_on_cpu;
int rc;
+ struct cpuinfo_x86 *c = &cpu_data(pol->cpu);
if (!cpu_online(pol->cpu))
return -ENODEV;
@@ -1323,6 +1330,10 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
return -EINVAL;
}
+ /* Check for APERF/MPERF support in hardware */
+ if (cpu_has(c, X86_FEATURE_APERFMPERF))
+ cpufreq_amd64_driver.getavg = cpufreq_get_measured_perf;
+
cpufreq_frequency_table_get_attr(data->powernow_table, pol->cpu);
if (cpu_family == CPU_HW_PSTATE)
@@ -1394,8 +1405,77 @@ out:
return khz;
}
+static void _cpb_toggle_msrs(bool t)
+{
+ int cpu;
+
+ get_online_cpus();
+
+ rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs);
+
+ for_each_cpu(cpu, cpu_online_mask) {
+ struct msr *reg = per_cpu_ptr(msrs, cpu);
+ if (t)
+ reg->l &= ~BIT(25);
+ else
+ reg->l |= BIT(25);
+ }
+ wrmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs);
+
+ put_online_cpus();
+}
+
+/*
+ * Switch on/off core performance boosting.
+ *
+ * 0=disable
+ * 1=enable.
+ */
+static void cpb_toggle(bool t)
+{
+ if (!cpb_capable)
+ return;
+
+ if (t && !cpb_enabled) {
+ cpb_enabled = true;
+ _cpb_toggle_msrs(t);
+ printk(KERN_INFO PFX "Core Boosting enabled.\n");
+ } else if (!t && cpb_enabled) {
+ cpb_enabled = false;
+ _cpb_toggle_msrs(t);
+ printk(KERN_INFO PFX "Core Boosting disabled.\n");
+ }
+}
+
+static ssize_t store_cpb(struct cpufreq_policy *policy, const char *buf,
+ size_t count)
+{
+ int ret = -EINVAL;
+ unsigned long val = 0;
+
+ ret = strict_strtoul(buf, 10, &val);
+ if (!ret && (val == 0 || val == 1) && cpb_capable)
+ cpb_toggle(val);
+ else
+ return -EINVAL;
+
+ return count;
+}
+
+static ssize_t show_cpb(struct cpufreq_policy *policy, char *buf)
+{
+ return sprintf(buf, "%u\n", cpb_enabled);
+}
+
+#define define_one_rw(_name) \
+static struct freq_attr _name = \
+__ATTR(_name, 0644, show_##_name, store_##_name)
+
+define_one_rw(cpb);
+
static struct freq_attr *powernow_k8_attr[] = {
&cpufreq_freq_attr_scaling_available_freqs,
+ &cpb,
NULL,
};
@@ -1411,10 +1491,51 @@ static struct cpufreq_driver cpufreq_amd64_driver = {
.attr = powernow_k8_attr,
};
+/*
+ * Clear the boost-disable flag on the CPU_DOWN path so that this cpu
+ * cannot block the remaining ones from boosting. On the CPU_UP path we
+ * simply keep the boost-disable flag in sync with the current global
+ * state.
+ */
+static int __cpuinit cpb_notify(struct notifier_block *nb, unsigned long action,
+ void *hcpu)
+{
+ unsigned cpu = (long)hcpu;
+ u32 lo, hi;
+
+ switch (action) {
+ case CPU_UP_PREPARE:
+ case CPU_UP_PREPARE_FROZEN:
+
+ if (!cpb_enabled) {
+ rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
+ lo |= BIT(25);
+ wrmsr_on_cpu(cpu, MSR_K7_HWCR, lo, hi);
+ }
+ break;
+
+ case CPU_DOWN_PREPARE:
+ case CPU_DOWN_PREPARE_FROZEN:
+ rdmsr_on_cpu(cpu, MSR_K7_HWCR, &lo, &hi);
+ lo &= ~BIT(25);
+ wrmsr_on_cpu(cpu, MSR_K7_HWCR, lo, hi);
+ break;
+
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata cpb_nb = {
+ .notifier_call = cpb_notify,
+};
+
/* driver entry point for init */
static int __cpuinit powernowk8_init(void)
{
- unsigned int i, supported_cpus = 0;
+ unsigned int i, supported_cpus = 0, cpu;
for_each_online_cpu(i) {
int rc;
@@ -1423,15 +1544,36 @@ static int __cpuinit powernowk8_init(void)
supported_cpus++;
}
- if (supported_cpus == num_online_cpus()) {
- printk(KERN_INFO PFX "Found %d %s "
- "processors (%d cpu cores) (" VERSION ")\n",
- num_online_nodes(),
- boot_cpu_data.x86_model_id, supported_cpus);
- return cpufreq_register_driver(&cpufreq_amd64_driver);
+ if (supported_cpus != num_online_cpus())
+ return -ENODEV;
+
+ printk(KERN_INFO PFX "Found %d %s (%d cpu cores) (" VERSION ")\n",
+ num_online_nodes(), boot_cpu_data.x86_model_id, supported_cpus);
+
+ if (boot_cpu_has(X86_FEATURE_CPB)) {
+
+ cpb_capable = true;
+
+ register_cpu_notifier(&cpb_nb);
+
+ msrs = msrs_alloc();
+ if (!msrs) {
+ printk(KERN_ERR "%s: Error allocating msrs!\n", __func__);
+ return -ENOMEM;
+ }
+
+ rdmsr_on_cpus(cpu_online_mask, MSR_K7_HWCR, msrs);
+
+ for_each_cpu(cpu, cpu_online_mask) {
+ struct msr *reg = per_cpu_ptr(msrs, cpu);
+ cpb_enabled |= !(!!(reg->l & BIT(25)));
+ }
+
+ printk(KERN_INFO PFX "Core Performance Boosting: %s.\n",
+ (cpb_enabled ? "on" : "off"));
}
- return -ENODEV;
+ return cpufreq_register_driver(&cpufreq_amd64_driver);
}
/* driver entry point for term */
@@ -1439,6 +1581,13 @@ static void __exit powernowk8_exit(void)
{
dprintk("exit\n");
+ if (boot_cpu_has(X86_FEATURE_CPB)) {
+ msrs_free(msrs);
+ msrs = NULL;
+
+ unregister_cpu_notifier(&cpb_nb);
+ }
+
cpufreq_unregister_driver(&cpufreq_amd64_driver);
}
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
index 02ce824073c..df3529b1c02 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.h
@@ -5,7 +5,6 @@
* http://www.gnu.org/licenses/gpl.html
*/
-
enum pstate {
HW_PSTATE_INVALID = 0xff,
HW_PSTATE_0 = 0,
@@ -55,7 +54,6 @@ struct powernow_k8_data {
struct cpumask *available_cores;
};
-
/* processor's cpuid instruction support */
#define CPUID_PROCESSOR_SIGNATURE 1 /* function 1 */
#define CPUID_XFAM 0x0ff00000 /* extended family */
diff --git a/arch/x86/kernel/cpu/hypervisor.c b/arch/x86/kernel/cpu/hypervisor.c
index 08be922de33..dd531cc56a8 100644
--- a/arch/x86/kernel/cpu/hypervisor.c
+++ b/arch/x86/kernel/cpu/hypervisor.c
@@ -21,37 +21,55 @@
*
*/
+#include <linux/module.h>
#include <asm/processor.h>
-#include <asm/vmware.h>
#include <asm/hypervisor.h>
-static inline void __cpuinit
-detect_hypervisor_vendor(struct cpuinfo_x86 *c)
+/*
+ * Hypervisor detect order. This is specified explicitly here because
+ * some hypervisors might implement compatibility modes for other
+ * hypervisors and therefore need to be detected in specific sequence.
+ */
+static const __initconst struct hypervisor_x86 * const hypervisors[] =
{
- if (vmware_platform())
- c->x86_hyper_vendor = X86_HYPER_VENDOR_VMWARE;
- else
- c->x86_hyper_vendor = X86_HYPER_VENDOR_NONE;
-}
+ &x86_hyper_vmware,
+ &x86_hyper_ms_hyperv,
+};
-static inline void __cpuinit
-hypervisor_set_feature_bits(struct cpuinfo_x86 *c)
+const struct hypervisor_x86 *x86_hyper;
+EXPORT_SYMBOL(x86_hyper);
+
+static inline void __init
+detect_hypervisor_vendor(void)
{
- if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE) {
- vmware_set_feature_bits(c);
- return;
+ const struct hypervisor_x86 *h, * const *p;
+
+ for (p = hypervisors; p < hypervisors + ARRAY_SIZE(hypervisors); p++) {
+ h = *p;
+ if (h->detect()) {
+ x86_hyper = h;
+ printk(KERN_INFO "Hypervisor detected: %s\n", h->name);
+ break;
+ }
}
}
void __cpuinit init_hypervisor(struct cpuinfo_x86 *c)
{
- detect_hypervisor_vendor(c);
- hypervisor_set_feature_bits(c);
+ if (x86_hyper && x86_hyper->set_cpu_features)
+ x86_hyper->set_cpu_features(c);
}
void __init init_hypervisor_platform(void)
{
+
+ detect_hypervisor_vendor();
+
+ if (!x86_hyper)
+ return;
+
init_hypervisor(&boot_cpu_data);
- if (boot_cpu_data.x86_hyper_vendor == X86_HYPER_VENDOR_VMWARE)
- vmware_platform_setup();
+
+ if (x86_hyper->init_platform)
+ x86_hyper->init_platform();
}
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index f5e5390d345..85f69cdeae1 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -372,12 +372,6 @@ static void __cpuinit init_intel(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_ARCH_PERFMON);
}
- if (c->cpuid_level > 6) {
- unsigned ecx = cpuid_ecx(6);
- if (ecx & 0x01)
- set_cpu_cap(c, X86_FEATURE_APERFMPERF);
- }
-
if (cpu_has_xmm2)
set_cpu_cap(c, X86_FEATURE_LFENCE_RDTSC);
if (cpu_has_ds) {
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 95962a93f99..33eae2062cf 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -148,13 +148,19 @@ union _cpuid4_leaf_ecx {
u32 full;
};
+struct amd_l3_cache {
+ struct pci_dev *dev;
+ bool can_disable;
+ unsigned indices;
+ u8 subcaches[4];
+};
+
struct _cpuid4_info {
union _cpuid4_leaf_eax eax;
union _cpuid4_leaf_ebx ebx;
union _cpuid4_leaf_ecx ecx;
unsigned long size;
- bool can_disable;
- unsigned int l3_indices;
+ struct amd_l3_cache *l3;
DECLARE_BITMAP(shared_cpu_map, NR_CPUS);
};
@@ -164,8 +170,7 @@ struct _cpuid4_info_regs {
union _cpuid4_leaf_ebx ebx;
union _cpuid4_leaf_ecx ecx;
unsigned long size;
- bool can_disable;
- unsigned int l3_indices;
+ struct amd_l3_cache *l3;
};
unsigned short num_cache_leaves;
@@ -302,91 +307,163 @@ struct _cache_attr {
};
#ifdef CONFIG_CPU_SUP_AMD
-static unsigned int __cpuinit amd_calc_l3_indices(void)
+
+/*
+ * L3 cache descriptors
+ */
+static struct amd_l3_cache **__cpuinitdata l3_caches;
+
+static void __cpuinit amd_calc_l3_indices(struct amd_l3_cache *l3)
{
- /*
- * We're called over smp_call_function_single() and therefore
- * are on the correct cpu.
- */
- int cpu = smp_processor_id();
- int node = cpu_to_node(cpu);
- struct pci_dev *dev = node_to_k8_nb_misc(node);
unsigned int sc0, sc1, sc2, sc3;
u32 val = 0;
- pci_read_config_dword(dev, 0x1C4, &val);
+ pci_read_config_dword(l3->dev, 0x1C4, &val);
/* calculate subcache sizes */
- sc0 = !(val & BIT(0));
- sc1 = !(val & BIT(4));
- sc2 = !(val & BIT(8)) + !(val & BIT(9));
- sc3 = !(val & BIT(12)) + !(val & BIT(13));
+ l3->subcaches[0] = sc0 = !(val & BIT(0));
+ l3->subcaches[1] = sc1 = !(val & BIT(4));
+ l3->subcaches[2] = sc2 = !(val & BIT(8)) + !(val & BIT(9));
+ l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
+
+ l3->indices = (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1;
+}
+
+static struct amd_l3_cache * __cpuinit amd_init_l3_cache(int node)
+{
+ struct amd_l3_cache *l3;
+ struct pci_dev *dev = node_to_k8_nb_misc(node);
- return (max(max(max(sc0, sc1), sc2), sc3) << 10) - 1;
+ l3 = kzalloc(sizeof(struct amd_l3_cache), GFP_ATOMIC);
+ if (!l3) {
+ printk(KERN_WARNING "Error allocating L3 struct\n");
+ return NULL;
+ }
+
+ l3->dev = dev;
+
+ amd_calc_l3_indices(l3);
+
+ return l3;
}
static void __cpuinit
amd_check_l3_disable(int index, struct _cpuid4_info_regs *this_leaf)
{
- if (index < 3)
+ int node;
+
+ if (boot_cpu_data.x86 != 0x10)
return;
- if (boot_cpu_data.x86 == 0x11)
+ if (index < 3)
return;
/* see errata #382 and #388 */
- if ((boot_cpu_data.x86 == 0x10) &&
- ((boot_cpu_data.x86_model < 0x8) ||
- (boot_cpu_data.x86_mask < 0x1)))
+ if (boot_cpu_data.x86_model < 0x8)
return;
+ if ((boot_cpu_data.x86_model == 0x8 ||
+ boot_cpu_data.x86_model == 0x9)
+ &&
+ boot_cpu_data.x86_mask < 0x1)
+ return;
+
/* not in virtualized environments */
if (num_k8_northbridges == 0)
return;
- this_leaf->can_disable = true;
- this_leaf->l3_indices = amd_calc_l3_indices();
+ /*
+ * 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 = num_k8_northbridges * 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]) {
+ l3_caches[node] = amd_init_l3_cache(node);
+ l3_caches[node]->can_disable = true;
+ }
+
+ WARN_ON(!l3_caches[node]);
+
+ this_leaf->l3 = l3_caches[node];
}
static ssize_t show_cache_disable(struct _cpuid4_info *this_leaf, char *buf,
- unsigned int index)
+ unsigned int slot)
{
- int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
- int node = amd_get_nb_id(cpu);
- struct pci_dev *dev = node_to_k8_nb_misc(node);
+ struct pci_dev *dev = this_leaf->l3->dev;
unsigned int reg = 0;
- if (!this_leaf->can_disable)
+ if (!this_leaf->l3 || !this_leaf->l3->can_disable)
return -EINVAL;
if (!dev)
return -EINVAL;
- pci_read_config_dword(dev, 0x1BC + index * 4, &reg);
+ pci_read_config_dword(dev, 0x1BC + slot * 4, &reg);
return sprintf(buf, "0x%08x\n", reg);
}
-#define SHOW_CACHE_DISABLE(index) \
+#define SHOW_CACHE_DISABLE(slot) \
static ssize_t \
-show_cache_disable_##index(struct _cpuid4_info *this_leaf, char *buf) \
+show_cache_disable_##slot(struct _cpuid4_info *this_leaf, char *buf) \
{ \
- return show_cache_disable(this_leaf, buf, index); \
+ return show_cache_disable(this_leaf, buf, slot); \
}
SHOW_CACHE_DISABLE(0)
SHOW_CACHE_DISABLE(1)
+static void amd_l3_disable_index(struct amd_l3_cache *l3, int cpu,
+ unsigned slot, unsigned long idx)
+{
+ int i;
+
+ idx |= BIT(30);
+
+ /*
+ * disable index in all 4 subcaches
+ */
+ for (i = 0; i < 4; i++) {
+ u32 reg = idx | (i << 20);
+
+ if (!l3->subcaches[i])
+ continue;
+
+ pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg);
+
+ /*
+ * We need to WBINVD on a core on the node containing the L3
+ * cache which indices we disable therefore a simple wbinvd()
+ * is not sufficient.
+ */
+ wbinvd_on_cpu(cpu);
+
+ reg |= BIT(31);
+ pci_write_config_dword(l3->dev, 0x1BC + slot * 4, reg);
+ }
+}
+
+
static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
- const char *buf, size_t count, unsigned int index)
+ const char *buf, size_t count,
+ unsigned int slot)
{
+ struct pci_dev *dev = this_leaf->l3->dev;
int cpu = cpumask_first(to_cpumask(this_leaf->shared_cpu_map));
- int node = amd_get_nb_id(cpu);
- struct pci_dev *dev = node_to_k8_nb_misc(node);
unsigned long val = 0;
#define SUBCACHE_MASK (3UL << 20)
#define SUBCACHE_INDEX 0xfff
- if (!this_leaf->can_disable)
+ if (!this_leaf->l3 || !this_leaf->l3->can_disable)
return -EINVAL;
if (!capable(CAP_SYS_ADMIN))
@@ -400,26 +477,20 @@ static ssize_t store_cache_disable(struct _cpuid4_info *this_leaf,
/* do not allow writes outside of allowed bits */
if ((val & ~(SUBCACHE_MASK | SUBCACHE_INDEX)) ||
- ((val & SUBCACHE_INDEX) > this_leaf->l3_indices))
+ ((val & SUBCACHE_INDEX) > this_leaf->l3->indices))
return -EINVAL;
- val |= BIT(30);
- pci_write_config_dword(dev, 0x1BC + index * 4, val);
- /*
- * We need to WBINVD on a core on the node containing the L3 cache which
- * indices we disable therefore a simple wbinvd() is not sufficient.
- */
- wbinvd_on_cpu(cpu);
- pci_write_config_dword(dev, 0x1BC + index * 4, val | BIT(31));
+ amd_l3_disable_index(this_leaf->l3, cpu, slot, val);
+
return count;
}
-#define STORE_CACHE_DISABLE(index) \
+#define STORE_CACHE_DISABLE(slot) \
static ssize_t \
-store_cache_disable_##index(struct _cpuid4_info *this_leaf, \
+store_cache_disable_##slot(struct _cpuid4_info *this_leaf, \
const char *buf, size_t count) \
{ \
- return store_cache_disable(this_leaf, buf, count, index); \
+ return store_cache_disable(this_leaf, buf, count, slot); \
}
STORE_CACHE_DISABLE(0)
STORE_CACHE_DISABLE(1)
@@ -447,8 +518,7 @@ __cpuinit cpuid4_cache_lookup_regs(int index,
if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
amd_cpuid4(index, &eax, &ebx, &ecx);
- if (boot_cpu_data.x86 >= 0x10)
- amd_check_l3_disable(index, this_leaf);
+ amd_check_l3_disable(index, this_leaf);
} else {
cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
}
@@ -705,6 +775,7 @@ 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;
}
@@ -989,7 +1060,7 @@ static int __cpuinit cache_add_dev(struct sys_device * sys_dev)
this_leaf = CPUID4_INFO_IDX(cpu, i);
- if (this_leaf->can_disable)
+ if (this_leaf->l3 && this_leaf->l3->can_disable)
ktype_cache.default_attrs = default_l3_attrs;
else
ktype_cache.default_attrs = default_attrs;
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
new file mode 100644
index 00000000000..16f41bbe46b
--- /dev/null
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -0,0 +1,55 @@
+/*
+ * HyperV Detection code.
+ *
+ * Copyright (C) 2010, Novell, Inc.
+ * Author : K. Y. Srinivasan <ksrinivasan@novell.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <asm/processor.h>
+#include <asm/hypervisor.h>
+#include <asm/hyperv.h>
+#include <asm/mshyperv.h>
+
+struct ms_hyperv_info ms_hyperv;
+
+static bool __init ms_hyperv_platform(void)
+{
+ u32 eax;
+ u32 hyp_signature[3];
+
+ if (!boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ return false;
+
+ cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS,
+ &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]);
+
+ return eax >= HYPERV_CPUID_MIN &&
+ eax <= HYPERV_CPUID_MAX &&
+ !memcmp("Microsoft Hv", hyp_signature, 12);
+}
+
+static void __init ms_hyperv_init_platform(void)
+{
+ /*
+ * Extract the features and hints
+ */
+ ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
+ ms_hyperv.hints = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
+
+ printk(KERN_INFO "HyperV: features 0x%x, hints 0x%x\n",
+ ms_hyperv.features, ms_hyperv.hints);
+}
+
+const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = {
+ .name = "Microsoft HyperV",
+ .detect = ms_hyperv_platform,
+ .init_platform = ms_hyperv_init_platform,
+};
+EXPORT_SYMBOL(x86_hyper_ms_hyperv);
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index dfdb4dba232..b9d1ff58844 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -24,8 +24,8 @@
#include <linux/dmi.h>
#include <linux/module.h>
#include <asm/div64.h>
-#include <asm/vmware.h>
#include <asm/x86_init.h>
+#include <asm/hypervisor.h>
#define CPUID_VMWARE_INFO_LEAF 0x40000000
#define VMWARE_HYPERVISOR_MAGIC 0x564D5868
@@ -65,7 +65,7 @@ static unsigned long vmware_get_tsc_khz(void)
return tsc_hz;
}
-void __init vmware_platform_setup(void)
+static void __init vmware_platform_setup(void)
{
uint32_t eax, ebx, ecx, edx;
@@ -83,26 +83,22 @@ void __init vmware_platform_setup(void)
* serial key should be enough, as this will always have a VMware
* specific string when running under VMware hypervisor.
*/
-int vmware_platform(void)
+static bool __init vmware_platform(void)
{
if (cpu_has_hypervisor) {
- unsigned int eax, ebx, ecx, edx;
- char hyper_vendor_id[13];
-
- cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &ebx, &ecx, &edx);
- memcpy(hyper_vendor_id + 0, &ebx, 4);
- memcpy(hyper_vendor_id + 4, &ecx, 4);
- memcpy(hyper_vendor_id + 8, &edx, 4);
- hyper_vendor_id[12] = '\0';
- if (!strcmp(hyper_vendor_id, "VMwareVMware"))
- return 1;
+ unsigned int eax;
+ unsigned int hyper_vendor_id[3];
+
+ cpuid(CPUID_VMWARE_INFO_LEAF, &eax, &hyper_vendor_id[0],
+ &hyper_vendor_id[1], &hyper_vendor_id[2]);
+ if (!memcmp(hyper_vendor_id, "VMwareVMware", 12))
+ return true;
} else if (dmi_available && dmi_name_in_serial("VMware") &&
__vmware_platform())
- return 1;
+ return true;
- return 0;
+ return false;
}
-EXPORT_SYMBOL(vmware_platform);
/*
* VMware hypervisor takes care of exporting a reliable TSC to the guest.
@@ -116,8 +112,16 @@ EXPORT_SYMBOL(vmware_platform);
* so that the kernel could just trust the hypervisor with providing a
* reliable virtual TSC that is suitable for timekeeping.
*/
-void __cpuinit vmware_set_feature_bits(struct cpuinfo_x86 *c)
+static void __cpuinit vmware_set_cpu_features(struct cpuinfo_x86 *c)
{
set_cpu_cap(c, X86_FEATURE_CONSTANT_TSC);
set_cpu_cap(c, X86_FEATURE_TSC_RELIABLE);
}
+
+const __refconst struct hypervisor_x86 x86_hyper_vmware = {
+ .name = "VMware",
+ .detect = vmware_platform,
+ .set_cpu_features = vmware_set_cpu_features,
+ .init_platform = vmware_platform_setup,
+};
+EXPORT_SYMBOL(x86_hyper_vmware);