Merge branches 'einj', 'intel_idle', 'misc', 'srat' and 'turbostat-ivb' into release
diff --git a/Documentation/acpi/apei/einj.txt b/Documentation/acpi/apei/einj.txt
index 5cc699b..e7cc363 100644
--- a/Documentation/acpi/apei/einj.txt
+++ b/Documentation/acpi/apei/einj.txt
@@ -47,20 +47,53 @@
- param1
This file is used to set the first error parameter value. Effect of
- parameter depends on error_type specified. For memory error, this is
- physical memory address. Only available if param_extension module
- parameter is specified.
+ parameter depends on error_type specified.
- param2
This file is used to set the second error parameter value. Effect of
- parameter depends on error_type specified. For memory error, this is
- physical memory address mask. Only available if param_extension
- module parameter is specified.
+ parameter depends on error_type specified.
-Injecting parameter support is a BIOS version specific extension, that
-is, it only works on some BIOS version. If you want to use it, please
-make sure your BIOS version has the proper support and specify
-"param_extension=y" in module parameter.
+BIOS versions based in the ACPI 4.0 specification have limited options
+to control where the errors are injected. Your BIOS may support an
+extension (enabled with the param_extension=1 module parameter, or
+boot command line einj.param_extension=1). This allows the address
+and mask for memory injections to be specified by the param1 and
+param2 files in apei/einj.
+
+BIOS versions using the ACPI 5.0 specification have more control over
+the target of the injection. For processor related errors (type 0x1,
+0x2 and 0x4) the APICID of the target should be provided using the
+param1 file in apei/einj. For memory errors (type 0x8, 0x10 and 0x20)
+the address is set using param1 with a mask in param2 (0x0 is equivalent
+to all ones). For PCI express errors (type 0x40, 0x80 and 0x100) the
+segment, bus, device and function are specified using param1:
+
+ 31 24 23 16 15 11 10 8 7 0
+ +-------------------------------------------------+
+ | segment | bus | device | function | reserved |
+ +-------------------------------------------------+
+
+An ACPI 5.0 BIOS may also allow vendor specific errors to be injected.
+In this case a file named vendor will contain identifying information
+from the BIOS that hopefully will allow an application wishing to use
+the vendor specific extension to tell that they are running on a BIOS
+that supports it. All vendor extensions have the 0x80000000 bit set in
+error_type. A file vendor_flags controls the interpretation of param1
+and param2 (1 = PROCESSOR, 2 = MEMORY, 4 = PCI). See your BIOS vendor
+documentation for details (and expect changes to this API if vendors
+creativity in using this feature expands beyond our expectations).
+
+Example:
+# cd /sys/kernel/debug/apei/einj
+# cat available_error_type # See which errors can be injected
+0x00000002 Processor Uncorrectable non-fatal
+0x00000008 Memory Correctable
+0x00000010 Memory Uncorrectable non-fatal
+# echo 0x12345000 > param1 # Set memory address for injection
+# echo 0xfffffffffffff000 > param2 # Mask - anywhere in this page
+# echo 0x8 > error_type # Choose correctable memory error
+# echo 1 > error_inject # Inject now
+
For more information about EINJ, please refer to ACPI specification
-version 4.0, section 17.5.
+version 4.0, section 17.5 and ACPI 5.0, section 18.6.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 81c287f..c6a56d8 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1035,6 +1035,11 @@
By default, super page will be supported if Intel IOMMU
has the capability. With this option, super page will
not be supported.
+
+ intel_idle.max_cstate= [KNL,HW,ACPI,X86]
+ 0 disables intel_idle and fall back on acpi_idle.
+ 1 to 6 specify maximum depth of C-state.
+
intremap= [X86-64, Intel-IOMMU]
on enable Interrupt Remapping (default)
off disable Interrupt Remapping
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index bfb4d01..5207035 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -429,22 +429,24 @@
static struct acpi_table_slit __initdata *slit_table;
cpumask_t early_cpu_possible_map = CPU_MASK_NONE;
-static int get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa)
+static int __init
+get_processor_proximity_domain(struct acpi_srat_cpu_affinity *pa)
{
int pxm;
pxm = pa->proximity_domain_lo;
- if (ia64_platform_is("sn2"))
+ if (ia64_platform_is("sn2") || acpi_srat_revision >= 2)
pxm += pa->proximity_domain_hi[0] << 8;
return pxm;
}
-static int get_memory_proximity_domain(struct acpi_srat_mem_affinity *ma)
+static int __init
+get_memory_proximity_domain(struct acpi_srat_mem_affinity *ma)
{
int pxm;
pxm = ma->proximity_domain;
- if (!ia64_platform_is("sn2"))
+ if (!ia64_platform_is("sn2") && acpi_srat_revision <= 1)
pxm &= 0xff;
return pxm;
diff --git a/arch/x86/mm/srat.c b/arch/x86/mm/srat.c
index 81dbfde..7efd0c6 100644
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -104,6 +104,8 @@
if ((pa->flags & ACPI_SRAT_CPU_ENABLED) == 0)
return;
pxm = pa->proximity_domain_lo;
+ if (acpi_srat_revision >= 2)
+ pxm |= *((unsigned int*)pa->proximity_domain_hi) << 8;
node = setup_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains %x\n", pxm);
@@ -155,6 +157,8 @@
start = ma->base_address;
end = start + ma->length;
pxm = ma->proximity_domain;
+ if (acpi_srat_revision <= 1)
+ pxm &= 0xff;
node = setup_node(pxm);
if (node < 0) {
printk(KERN_ERR "SRAT: Too many proximity domains.\n");
diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c
index 6e6512e..5b898d4 100644
--- a/drivers/acpi/apei/einj.c
+++ b/drivers/acpi/apei/einj.c
@@ -43,6 +43,42 @@
#define FIRMWARE_TIMEOUT (1 * NSEC_PER_MSEC)
/*
+ * ACPI version 5 provides a SET_ERROR_TYPE_WITH_ADDRESS action.
+ */
+static int acpi5;
+
+struct set_error_type_with_address {
+ u32 type;
+ u32 vendor_extension;
+ u32 flags;
+ u32 apicid;
+ u64 memory_address;
+ u64 memory_address_range;
+ u32 pcie_sbdf;
+};
+enum {
+ SETWA_FLAGS_APICID = 1,
+ SETWA_FLAGS_MEM = 2,
+ SETWA_FLAGS_PCIE_SBDF = 4,
+};
+
+/*
+ * Vendor extensions for platform specific operations
+ */
+struct vendor_error_type_extension {
+ u32 length;
+ u32 pcie_sbdf;
+ u16 vendor_id;
+ u16 device_id;
+ u8 rev_id;
+ u8 reserved[3];
+};
+
+static u32 vendor_flags;
+static struct debugfs_blob_wrapper vendor_blob;
+static char vendor_dev[64];
+
+/*
* Some BIOSes allow parameters to the SET_ERROR_TYPE entries in the
* EINJ table through an unpublished extension. Use with caution as
* most will ignore the parameter and make their own choice of address
@@ -103,7 +139,14 @@
*/
static DEFINE_MUTEX(einj_mutex);
-static struct einj_parameter *einj_param;
+static void *einj_param;
+
+#ifndef readq
+static inline __u64 readq(volatile void __iomem *addr)
+{
+ return ((__u64)readl(addr+4) << 32) + readl(addr);
+}
+#endif
#ifndef writeq
static inline void writeq(__u64 val, volatile void __iomem *addr)
@@ -158,10 +201,31 @@
return 0;
}
-static u64 einj_get_parameter_address(void)
+static void check_vendor_extension(u64 paddr,
+ struct set_error_type_with_address *v5param)
+{
+ int offset = readl(&v5param->vendor_extension);
+ struct vendor_error_type_extension *v;
+ u32 sbdf;
+
+ if (!offset)
+ return;
+ v = ioremap(paddr + offset, sizeof(*v));
+ if (!v)
+ return;
+ sbdf = readl(&v->pcie_sbdf);
+ sprintf(vendor_dev, "%x:%x:%x.%x vendor_id=%x device_id=%x rev_id=%x\n",
+ sbdf >> 24, (sbdf >> 16) & 0xff,
+ (sbdf >> 11) & 0x1f, (sbdf >> 8) & 0x7,
+ readw(&v->vendor_id), readw(&v->device_id),
+ readb(&v->rev_id));
+ iounmap(v);
+}
+
+static void *einj_get_parameter_address(void)
{
int i;
- u64 paddr = 0;
+ u64 paddrv4 = 0, paddrv5 = 0;
struct acpi_whea_header *entry;
entry = EINJ_TAB_ENTRY(einj_tab);
@@ -170,12 +234,40 @@
entry->instruction == ACPI_EINJ_WRITE_REGISTER &&
entry->register_region.space_id ==
ACPI_ADR_SPACE_SYSTEM_MEMORY)
- memcpy(&paddr, &entry->register_region.address,
- sizeof(paddr));
+ memcpy(&paddrv4, &entry->register_region.address,
+ sizeof(paddrv4));
+ if (entry->action == ACPI_EINJ_SET_ERROR_TYPE_WITH_ADDRESS &&
+ entry->instruction == ACPI_EINJ_WRITE_REGISTER &&
+ entry->register_region.space_id ==
+ ACPI_ADR_SPACE_SYSTEM_MEMORY)
+ memcpy(&paddrv5, &entry->register_region.address,
+ sizeof(paddrv5));
entry++;
}
+ if (paddrv5) {
+ struct set_error_type_with_address *v5param;
- return paddr;
+ v5param = ioremap(paddrv5, sizeof(*v5param));
+ if (v5param) {
+ acpi5 = 1;
+ check_vendor_extension(paddrv5, v5param);
+ return v5param;
+ }
+ }
+ if (paddrv4) {
+ struct einj_parameter *v4param;
+
+ v4param = ioremap(paddrv4, sizeof(*v4param));
+ if (!v4param)
+ return 0;
+ if (readq(&v4param->reserved1) || readq(&v4param->reserved2)) {
+ iounmap(v4param);
+ return 0;
+ }
+ return v4param;
+ }
+
+ return 0;
}
/* do sanity check to trigger table */
@@ -340,12 +432,56 @@
if (rc)
return rc;
apei_exec_ctx_set_input(&ctx, type);
- rc = apei_exec_run(&ctx, ACPI_EINJ_SET_ERROR_TYPE);
- if (rc)
- return rc;
- if (einj_param) {
- writeq(param1, &einj_param->param1);
- writeq(param2, &einj_param->param2);
+ if (acpi5) {
+ struct set_error_type_with_address *v5param = einj_param;
+
+ writel(type, &v5param->type);
+ if (type & 0x80000000) {
+ switch (vendor_flags) {
+ case SETWA_FLAGS_APICID:
+ writel(param1, &v5param->apicid);
+ break;
+ case SETWA_FLAGS_MEM:
+ writeq(param1, &v5param->memory_address);
+ writeq(param2, &v5param->memory_address_range);
+ break;
+ case SETWA_FLAGS_PCIE_SBDF:
+ writel(param1, &v5param->pcie_sbdf);
+ break;
+ }
+ writel(vendor_flags, &v5param->flags);
+ } else {
+ switch (type) {
+ case ACPI_EINJ_PROCESSOR_CORRECTABLE:
+ case ACPI_EINJ_PROCESSOR_UNCORRECTABLE:
+ case ACPI_EINJ_PROCESSOR_FATAL:
+ writel(param1, &v5param->apicid);
+ writel(SETWA_FLAGS_APICID, &v5param->flags);
+ break;
+ case ACPI_EINJ_MEMORY_CORRECTABLE:
+ case ACPI_EINJ_MEMORY_UNCORRECTABLE:
+ case ACPI_EINJ_MEMORY_FATAL:
+ writeq(param1, &v5param->memory_address);
+ writeq(param2, &v5param->memory_address_range);
+ writel(SETWA_FLAGS_MEM, &v5param->flags);
+ break;
+ case ACPI_EINJ_PCIX_CORRECTABLE:
+ case ACPI_EINJ_PCIX_UNCORRECTABLE:
+ case ACPI_EINJ_PCIX_FATAL:
+ writel(param1, &v5param->pcie_sbdf);
+ writel(SETWA_FLAGS_PCIE_SBDF, &v5param->flags);
+ break;
+ }
+ }
+ } else {
+ rc = apei_exec_run(&ctx, ACPI_EINJ_SET_ERROR_TYPE);
+ if (rc)
+ return rc;
+ if (einj_param) {
+ struct einj_parameter *v4param = einj_param;
+ writeq(param1, &v4param->param1);
+ writeq(param2, &v4param->param2);
+ }
}
rc = apei_exec_run(&ctx, ACPI_EINJ_EXECUTE_OPERATION);
if (rc)
@@ -455,15 +591,25 @@
{
int rc;
u32 available_error_type = 0;
+ u32 tval, vendor;
+
+ /*
+ * Vendor defined types have 0x80000000 bit set, and
+ * are not enumerated by ACPI_EINJ_GET_ERROR_TYPE
+ */
+ vendor = val & 0x80000000;
+ tval = val & 0x7fffffff;
/* Only one error type can be specified */
- if (val & (val - 1))
+ if (tval & (tval - 1))
return -EINVAL;
- rc = einj_get_available_error_type(&available_error_type);
- if (rc)
- return rc;
- if (!(val & available_error_type))
- return -EINVAL;
+ if (!vendor) {
+ rc = einj_get_available_error_type(&available_error_type);
+ if (rc)
+ return rc;
+ if (!(val & available_error_type))
+ return -EINVAL;
+ }
error_type = val;
return 0;
@@ -502,7 +648,6 @@
static int __init einj_init(void)
{
int rc;
- u64 param_paddr;
acpi_status status;
struct dentry *fentry;
struct apei_exec_context ctx;
@@ -555,23 +700,30 @@
rc = apei_exec_pre_map_gars(&ctx);
if (rc)
goto err_release;
- if (param_extension) {
- param_paddr = einj_get_parameter_address();
- if (param_paddr) {
- einj_param = ioremap(param_paddr, sizeof(*einj_param));
- rc = -ENOMEM;
- if (!einj_param)
- goto err_unmap;
- fentry = debugfs_create_x64("param1", S_IRUSR | S_IWUSR,
- einj_debug_dir, &error_param1);
- if (!fentry)
- goto err_unmap;
- fentry = debugfs_create_x64("param2", S_IRUSR | S_IWUSR,
- einj_debug_dir, &error_param2);
- if (!fentry)
- goto err_unmap;
- } else
- pr_warn(EINJ_PFX "Parameter extension is not supported.\n");
+
+ einj_param = einj_get_parameter_address();
+ if ((param_extension || acpi5) && einj_param) {
+ fentry = debugfs_create_x64("param1", S_IRUSR | S_IWUSR,
+ einj_debug_dir, &error_param1);
+ if (!fentry)
+ goto err_unmap;
+ fentry = debugfs_create_x64("param2", S_IRUSR | S_IWUSR,
+ einj_debug_dir, &error_param2);
+ if (!fentry)
+ goto err_unmap;
+ }
+
+ if (vendor_dev[0]) {
+ vendor_blob.data = vendor_dev;
+ vendor_blob.size = strlen(vendor_dev);
+ fentry = debugfs_create_blob("vendor", S_IRUSR,
+ einj_debug_dir, &vendor_blob);
+ if (!fentry)
+ goto err_unmap;
+ fentry = debugfs_create_x32("vendor_flags", S_IRUSR | S_IWUSR,
+ einj_debug_dir, &vendor_flags);
+ if (!fentry)
+ goto err_unmap;
}
pr_info(EINJ_PFX "Error INJection is initialized.\n");
diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c
index 3b5c318..e56f3be 100644
--- a/drivers/acpi/numa.c
+++ b/drivers/acpi/numa.c
@@ -45,6 +45,8 @@
static int node_to_pxm_map[MAX_NUMNODES]
= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
+unsigned char acpi_srat_revision __initdata;
+
int pxm_to_node(int pxm)
{
if (pxm < 0)
@@ -255,9 +257,13 @@
static int __init acpi_parse_srat(struct acpi_table_header *table)
{
+ struct acpi_table_srat *srat;
if (!table)
return -EINVAL;
+ srat = (struct acpi_table_srat *)table;
+ acpi_srat_revision = srat->header.revision;
+
/* Real work done in acpi_table_parse_srat below. */
return 0;
diff --git a/drivers/acpi/processor_core.c b/drivers/acpi/processor_core.c
index 3a0428e..c850de4 100644
--- a/drivers/acpi/processor_core.c
+++ b/drivers/acpi/processor_core.c
@@ -173,8 +173,30 @@
apic_id = map_mat_entry(handle, type, acpi_id);
if (apic_id == -1)
apic_id = map_madt_entry(type, acpi_id);
- if (apic_id == -1)
- return apic_id;
+ if (apic_id == -1) {
+ /*
+ * On UP processor, there is no _MAT or MADT table.
+ * So above apic_id is always set to -1.
+ *
+ * BIOS may define multiple CPU handles even for UP processor.
+ * For example,
+ *
+ * Scope (_PR)
+ * {
+ * Processor (CPU0, 0x00, 0x00000410, 0x06) {}
+ * Processor (CPU1, 0x01, 0x00000410, 0x06) {}
+ * Processor (CPU2, 0x02, 0x00000410, 0x06) {}
+ * Processor (CPU3, 0x03, 0x00000410, 0x06) {}
+ * }
+ *
+ * Ignores apic_id and always return 0 for CPU0's handle.
+ * Return -1 for other CPU's handle.
+ */
+ if (acpi_id == 0)
+ return acpi_id;
+ else
+ return apic_id;
+ }
#ifdef CONFIG_SMP
for_each_possible_cpu(i) {
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 9d7bc9f..b9cbd9b 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -82,7 +82,7 @@
static int acpi_processor_add(struct acpi_device *device);
static int acpi_processor_remove(struct acpi_device *device, int type);
static void acpi_processor_notify(struct acpi_device *device, u32 event);
-static acpi_status acpi_processor_hotadd_init(acpi_handle handle, int *p_cpu);
+static acpi_status acpi_processor_hotadd_init(struct acpi_processor *pr);
static int acpi_processor_handle_eject(struct acpi_processor *pr);
@@ -324,10 +324,8 @@
* they are physically not present.
*/
if (pr->id == -1) {
- if (ACPI_FAILURE
- (acpi_processor_hotadd_init(pr->handle, &pr->id))) {
+ if (ACPI_FAILURE(acpi_processor_hotadd_init(pr)))
return -ENODEV;
- }
}
/*
* On some boxes several processors use the same processor bus id.
@@ -539,6 +537,7 @@
thermal_cooling_device_unregister(pr->cdev);
err_power_exit:
acpi_processor_power_exit(pr, device);
+ sysfs_remove_link(&device->dev.kobj, "sysdev");
err_free_cpumask:
free_cpumask_var(pr->throttling.shared_cpu_map);
@@ -720,18 +719,19 @@
return (AE_OK);
}
-static acpi_status acpi_processor_hotadd_init(acpi_handle handle, int *p_cpu)
+static acpi_status acpi_processor_hotadd_init(struct acpi_processor *pr)
{
+ acpi_handle handle = pr->handle;
if (!is_processor_present(handle)) {
return AE_ERROR;
}
- if (acpi_map_lsapic(handle, p_cpu))
+ if (acpi_map_lsapic(handle, &pr->id))
return AE_ERROR;
- if (arch_register_cpu(*p_cpu)) {
- acpi_unmap_lsapic(*p_cpu);
+ if (arch_register_cpu(pr->id)) {
+ acpi_unmap_lsapic(pr->id);
return AE_ERROR;
}
@@ -748,7 +748,7 @@
return (0);
}
#else
-static acpi_status acpi_processor_hotadd_init(acpi_handle handle, int *p_cpu)
+static acpi_status acpi_processor_hotadd_init(struct acpi_processor *pr)
{
return AE_ERROR;
}
@@ -827,8 +827,6 @@
acpi_bus_unregister_driver(&acpi_processor_driver);
- cpuidle_unregister_driver(&acpi_idle_driver);
-
return;
}
diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c
index 5d2f8e1..20bce51 100644
--- a/drivers/idle/intel_idle.c
+++ b/drivers/idle/intel_idle.c
@@ -197,7 +197,7 @@
.enter = &intel_idle },
};
-static int get_driver_data(int cstate)
+static long get_driver_data(int cstate)
{
int driver_data;
switch (cstate) {
@@ -232,6 +232,7 @@
* @drv: cpuidle driver
* @index: index of cpuidle state
*
+ * Must be called under local_irq_disable().
*/
static int intel_idle(struct cpuidle_device *dev,
struct cpuidle_driver *drv, int index)
@@ -247,8 +248,6 @@
cstate = (((eax) >> MWAIT_SUBSTATE_SIZE) & MWAIT_CSTATE_MASK) + 1;
- local_irq_disable();
-
/*
* leave_mm() to avoid costly and often unnecessary wakeups
* for flushing the user TLB's associated with the active mm.
@@ -348,7 +347,8 @@
cpuid(CPUID_MWAIT_LEAF, &eax, &ebx, &ecx, &mwait_substates);
if (!(ecx & CPUID5_ECX_EXTENSIONS_SUPPORTED) ||
- !(ecx & CPUID5_ECX_INTERRUPT_BREAK))
+ !(ecx & CPUID5_ECX_INTERRUPT_BREAK) ||
+ !mwait_substates)
return -ENODEV;
pr_debug(PREFIX "MWAIT substates: 0x%x\n", mwait_substates);
@@ -394,7 +394,7 @@
if (boot_cpu_has(X86_FEATURE_ARAT)) /* Always Reliable APIC Timer */
lapic_timer_reliable_states = LAPIC_TIMER_ALWAYS_RELIABLE;
else {
- smp_call_function(__setup_broadcast_timer, (void *)true, 1);
+ on_each_cpu(__setup_broadcast_timer, (void *)true, 1);
register_cpu_notifier(&setup_broadcast_notifier);
}
@@ -471,71 +471,67 @@
}
if (auto_demotion_disable_flags)
- smp_call_function(auto_demotion_disable, NULL, 1);
+ on_each_cpu(auto_demotion_disable, NULL, 1);
return 0;
}
/*
- * intel_idle_cpuidle_devices_init()
+ * intel_idle_cpu_init()
* allocate, initialize, register cpuidle_devices
+ * @cpu: cpu/core to initialize
*/
-static int intel_idle_cpuidle_devices_init(void)
+int intel_idle_cpu_init(int cpu)
{
- int i, cstate;
+ int cstate;
struct cpuidle_device *dev;
- intel_idle_cpuidle_devices = alloc_percpu(struct cpuidle_device);
- if (intel_idle_cpuidle_devices == NULL)
- return -ENOMEM;
+ dev = per_cpu_ptr(intel_idle_cpuidle_devices, cpu);
- for_each_online_cpu(i) {
- dev = per_cpu_ptr(intel_idle_cpuidle_devices, i);
+ dev->state_count = 1;
- dev->state_count = 1;
+ for (cstate = 1; cstate < MWAIT_MAX_NUM_CSTATES; ++cstate) {
+ int num_substates;
- for (cstate = 1; cstate < MWAIT_MAX_NUM_CSTATES; ++cstate) {
- int num_substates;
+ if (cstate > max_cstate) {
+ printk(PREFIX "max_cstate %d reached\n",
+ max_cstate);
+ break;
+ }
- if (cstate > max_cstate) {
- printk(PREFIX "max_cstate %d reached\n",
- max_cstate);
- break;
- }
+ /* does the state exist in CPUID.MWAIT? */
+ num_substates = (mwait_substates >> ((cstate) * 4))
+ & MWAIT_SUBSTATE_MASK;
+ if (num_substates == 0)
+ continue;
+ /* is the state not enabled? */
+ if (cpuidle_state_table[cstate].enter == NULL)
+ continue;
- /* does the state exist in CPUID.MWAIT? */
- num_substates = (mwait_substates >> ((cstate) * 4))
- & MWAIT_SUBSTATE_MASK;
- if (num_substates == 0)
- continue;
- /* is the state not enabled? */
- if (cpuidle_state_table[cstate].enter == NULL) {
- continue;
- }
-
- dev->states_usage[dev->state_count].driver_data =
- (void *)get_driver_data(cstate);
+ dev->states_usage[dev->state_count].driver_data =
+ (void *)get_driver_data(cstate);
dev->state_count += 1;
}
+ dev->cpu = cpu;
- dev->cpu = i;
- if (cpuidle_register_device(dev)) {
- pr_debug(PREFIX "cpuidle_register_device %d failed!\n",
- i);
- intel_idle_cpuidle_devices_uninit();
- return -EIO;
- }
+ if (cpuidle_register_device(dev)) {
+ pr_debug(PREFIX "cpuidle_register_device %d failed!\n", cpu);
+ intel_idle_cpuidle_devices_uninit();
+ return -EIO;
}
+ if (auto_demotion_disable_flags)
+ smp_call_function_single(cpu, auto_demotion_disable, NULL, 1);
+
return 0;
}
static int __init intel_idle_init(void)
{
- int retval;
+ int retval, i;
/* Do not load intel_idle at all for now if idle= is passed */
if (boot_option_idle_override != IDLE_NO_OVERRIDE)
@@ -553,10 +549,16 @@
return retval;
}
- retval = intel_idle_cpuidle_devices_init();
- if (retval) {
- cpuidle_unregister_driver(&intel_idle_driver);
- return retval;
+ intel_idle_cpuidle_devices = alloc_percpu(struct cpuidle_device);
+ if (intel_idle_cpuidle_devices == NULL)
+ return -ENOMEM;
+
+ for_each_online_cpu(i) {
+ retval = intel_idle_cpu_init(i);
+ if (retval) {
+ cpuidle_unregister_driver(&intel_idle_driver);
+ return retval;
+ }
}
return 0;
@@ -568,7 +570,7 @@
cpuidle_unregister_driver(&intel_idle_driver);
if (lapic_timer_reliable_states != LAPIC_TIMER_ALWAYS_RELIABLE) {
- smp_call_function(__setup_broadcast_timer, (void *)false, 1);
+ on_each_cpu(__setup_broadcast_timer, (void *)false, 1);
unregister_cpu_notifier(&setup_broadcast_notifier);
}
diff --git a/include/acpi/acpi_numa.h b/include/acpi/acpi_numa.h
index 1739726..451823c 100644
--- a/include/acpi/acpi_numa.h
+++ b/include/acpi/acpi_numa.h
@@ -15,6 +15,7 @@
extern int node_to_pxm(int);
extern void __acpi_map_pxm_to_node(int, int);
extern int acpi_map_pxm_to_node(int);
+extern unsigned char acpi_srat_revision;
#endif /* CONFIG_ACPI_NUMA */
#endif /* __ACP_NUMA_H */
diff --git a/include/linux/cpuidle.h b/include/linux/cpuidle.h
index 7408af8..93df66e 100644
--- a/include/linux/cpuidle.h
+++ b/include/linux/cpuidle.h
@@ -188,7 +188,14 @@
extern int cpuidle_register_governor(struct cpuidle_governor *gov);
extern void cpuidle_unregister_governor(struct cpuidle_governor *gov);
+#ifdef CONFIG_INTEL_IDLE
+extern int intel_idle_cpu_init(int cpu);
#else
+static inline int intel_idle_cpu_init(int cpu) { return -1; }
+#endif
+
+#else
+static inline int intel_idle_cpu_init(int cpu) { return -1; }
static inline int cpuidle_register_governor(struct cpuidle_governor *gov)
{return 0;}
diff --git a/tools/power/x86/turbostat/turbostat.c b/tools/power/x86/turbostat/turbostat.c
index 3c6f780..310d3dd 100644
--- a/tools/power/x86/turbostat/turbostat.c
+++ b/tools/power/x86/turbostat/turbostat.c
@@ -811,6 +811,8 @@
case 0x2C: /* Westmere EP - Gulftown */
case 0x2A: /* SNB */
case 0x2D: /* SNB Xeon */
+ case 0x3A: /* IVB */
+ case 0x3D: /* IVB Xeon */
return 1;
case 0x2E: /* Nehalem-EX Xeon - Beckton */
case 0x2F: /* Westmere-EX Xeon - Eagleton */