summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig5
-rw-r--r--arch/x86/include/asm/idle.h1
-rw-r--r--arch/x86/include/asm/iommu.h4
-rw-r--r--arch/x86/kernel/acpi/boot.c5
-rw-r--r--arch/x86/kernel/acpi/sleep.c4
-rw-r--r--arch/x86/kernel/amd_iommu_init.c2
-rw-r--r--arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c3
-rw-r--r--arch/x86/kernel/cpu/cpufreq/powernow-k8.c42
-rw-r--r--arch/x86/kernel/early-quirks.c55
-rw-r--r--arch/x86/kernel/irq.c4
-rw-r--r--arch/x86/kernel/pci-dma.c16
-rw-r--r--arch/x86/kernel/process_64.c7
-rw-r--r--arch/x86/oprofile/backtrace.c3
-rw-r--r--arch/x86/oprofile/nmi_int.c173
-rw-r--r--arch/x86/oprofile/op_counter.h18
-rw-r--r--arch/x86/oprofile/op_model_amd.c59
-rw-r--r--arch/x86/oprofile/op_model_p4.c32
-rw-r--r--arch/x86/oprofile/op_model_ppro.c120
-rw-r--r--arch/x86/oprofile/op_x86_model.h13
19 files changed, 348 insertions, 218 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5b9b123..350bee1 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -116,6 +116,9 @@ config GENERIC_TIME_VSYSCALL
config ARCH_HAS_CPU_RELAX
def_bool y
+config ARCH_HAS_DEFAULT_IDLE
+ def_bool y
+
config ARCH_HAS_CACHE_LINE_SIZE
def_bool y
@@ -1635,6 +1638,8 @@ source "arch/x86/kernel/cpu/cpufreq/Kconfig"
source "drivers/cpuidle/Kconfig"
+source "drivers/idle/Kconfig"
+
endmenu
diff --git a/arch/x86/include/asm/idle.h b/arch/x86/include/asm/idle.h
index 8ed9376..44c89c3 100644
--- a/arch/x86/include/asm/idle.h
+++ b/arch/x86/include/asm/idle.h
@@ -6,6 +6,7 @@
struct notifier_block;
void idle_notifier_register(struct notifier_block *n);
+void idle_notifier_unregister(struct notifier_block *n);
void enter_idle(void);
void exit_idle(void);
diff --git a/arch/x86/include/asm/iommu.h b/arch/x86/include/asm/iommu.h
index 0c770f8..98e28ea 100644
--- a/arch/x86/include/asm/iommu.h
+++ b/arch/x86/include/asm/iommu.h
@@ -7,9 +7,13 @@ extern struct dma_mapping_ops nommu_dma_ops;
extern int force_iommu, no_iommu;
extern int iommu_detected;
extern int dmar_disabled;
+extern int forbid_dac;
extern unsigned long iommu_nr_pages(unsigned long addr, unsigned long len);
+/* 10 seconds */
+#define DMAR_OPERATION_TIMEOUT ((cycles_t) tsc_khz*10*1000)
+
#ifdef CONFIG_GART_IOMMU
extern int gart_iommu_aperture;
extern int gart_iommu_aperture_allowed;
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index 0d1c26a..53b01a1 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -153,12 +153,13 @@ char *__init __acpi_map_table(unsigned long phys, unsigned long size)
}
#ifdef CONFIG_PCI_MMCONFIG
+
+static int acpi_mcfg_64bit_base_addr __initdata = FALSE;
+
/* The physical address of the MMCONFIG aperture. Set from ACPI tables. */
struct acpi_mcfg_allocation *pci_mmcfg_config;
int pci_mmcfg_config_num;
-static int acpi_mcfg_64bit_base_addr __initdata = FALSE;
-
static int __init acpi_mcfg_oem_check(struct acpi_table_mcfg *mcfg)
{
if (!strcmp(mcfg->header.oem_id, "SGI"))
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index c44cd6d..806b4e9 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -22,7 +22,7 @@ unsigned long acpi_realmode_flags;
static unsigned long acpi_realmode;
#if defined(CONFIG_SMP) && defined(CONFIG_64BIT)
-static char temp_stack[10240];
+static char temp_stack[4096];
#endif
/**
@@ -98,7 +98,7 @@ int acpi_save_state_mem(void)
#else /* CONFIG_64BIT */
header->trampoline_segment = setup_trampoline() >> 4;
#ifdef CONFIG_SMP
- stack_start.sp = temp_stack + 4096;
+ stack_start.sp = temp_stack + sizeof(temp_stack);
early_gdt_descr.address =
(unsigned long)get_cpu_gdt_table(smp_processor_id());
#endif
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 4cd8083..0cdcda3 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -212,7 +212,7 @@ static void __init iommu_set_exclusion_range(struct amd_iommu *iommu)
/* Programs the physical address of the device table into the IOMMU hardware */
static void __init iommu_set_device_table(struct amd_iommu *iommu)
{
- u32 entry;
+ u64 entry;
BUG_ON(iommu->mmio_base == NULL);
diff --git a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
index c24c4a4..8e48c5d 100644
--- a/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
+++ b/arch/x86/kernel/cpu/cpufreq/acpi-cpufreq.c
@@ -780,6 +780,9 @@ static int __init acpi_cpufreq_init(void)
{
int ret;
+ if (acpi_disabled)
+ return 0;
+
dprintk("acpi_cpufreq_init\n");
ret = acpi_cpufreq_early_init();
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index 008d23b..d3dcd58 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -45,7 +45,6 @@
#endif
#define PFX "powernow-k8: "
-#define BFX PFX "BIOS error: "
#define VERSION "version 2.20.00"
#include "powernow-k8.h"
@@ -536,35 +535,40 @@ static int check_pst_table(struct powernow_k8_data *data, struct pst_s *pst, u8
for (j = 0; j < data->numps; j++) {
if (pst[j].vid > LEAST_VID) {
- printk(KERN_ERR PFX "vid %d invalid : 0x%x\n", j, pst[j].vid);
+ printk(KERN_ERR FW_BUG PFX "vid %d invalid : 0x%x\n",
+ j, pst[j].vid);
return -EINVAL;
}
if (pst[j].vid < data->rvo) { /* vid + rvo >= 0 */
- printk(KERN_ERR BFX "0 vid exceeded with pstate %d\n", j);
+ printk(KERN_ERR FW_BUG PFX "0 vid exceeded with pstate"
+ " %d\n", j);
return -ENODEV;
}
if (pst[j].vid < maxvid + data->rvo) { /* vid + rvo >= maxvid */
- printk(KERN_ERR BFX "maxvid exceeded with pstate %d\n", j);
+ printk(KERN_ERR FW_BUG PFX "maxvid exceeded with pstate"
+ " %d\n", j);
return -ENODEV;
}
if (pst[j].fid > MAX_FID) {
- printk(KERN_ERR BFX "maxfid exceeded with pstate %d\n", j);
+ printk(KERN_ERR FW_BUG PFX "maxfid exceeded with pstate"
+ " %d\n", j);
return -ENODEV;
}
if (j && (pst[j].fid < HI_FID_TABLE_BOTTOM)) {
/* Only first fid is allowed to be in "low" range */
- printk(KERN_ERR BFX "two low fids - %d : 0x%x\n", j, pst[j].fid);
+ printk(KERN_ERR FW_BUG PFX "two low fids - %d : "
+ "0x%x\n", j, pst[j].fid);
return -EINVAL;
}
if (pst[j].fid < lastfid)
lastfid = pst[j].fid;
}
if (lastfid & 1) {
- printk(KERN_ERR BFX "lastfid invalid\n");
+ printk(KERN_ERR FW_BUG PFX "lastfid invalid\n");
return -EINVAL;
}
if (lastfid > LO_FID_TABLE_TOP)
- printk(KERN_INFO BFX "first fid not from lo freq table\n");
+ printk(KERN_INFO FW_BUG PFX "first fid not from lo freq table\n");
return 0;
}
@@ -672,13 +676,13 @@ static int find_psb_table(struct powernow_k8_data *data)
dprintk("table vers: 0x%x\n", psb->tableversion);
if (psb->tableversion != PSB_VERSION_1_4) {
- printk(KERN_ERR BFX "PSB table is not v1.4\n");
+ printk(KERN_ERR FW_BUG PFX "PSB table is not v1.4\n");
return -ENODEV;
}
dprintk("flags: 0x%x\n", psb->flags1);
if (psb->flags1) {
- printk(KERN_ERR BFX "unknown flags\n");
+ printk(KERN_ERR FW_BUG PFX "unknown flags\n");
return -ENODEV;
}
@@ -705,7 +709,7 @@ static int find_psb_table(struct powernow_k8_data *data)
}
}
if (cpst != 1) {
- printk(KERN_ERR BFX "numpst must be 1\n");
+ printk(KERN_ERR FW_BUG PFX "numpst must be 1\n");
return -ENODEV;
}
@@ -1130,17 +1134,19 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
"ACPI Processor module before starting this "
"driver.\n");
#else
- printk(KERN_ERR PFX "Your BIOS does not provide ACPI "
- "_PSS objects in a way that Linux understands. "
- "Please report this to the Linux ACPI maintainers"
- " and complain to your BIOS vendor.\n");
+ printk(KERN_ERR FW_BUG PFX "Your BIOS does not provide"
+ " ACPI _PSS objects in a way that Linux "
+ "understands. Please report this to the Linux "
+ "ACPI maintainers and complain to your BIOS "
+ "vendor.\n");
#endif
kfree(data);
return -ENODEV;
}
if (pol->cpu != 0) {
- printk(KERN_ERR PFX "No ACPI _PSS objects for CPU other than "
- "CPU0. Complain to your BIOS vendor.\n");
+ printk(KERN_ERR FW_BUG PFX "No ACPI _PSS objects for "
+ "CPU other than CPU0. Complain to your BIOS "
+ "vendor.\n");
kfree(data);
return -ENODEV;
}
@@ -1193,7 +1199,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
/* min/max the cpu is capable of */
if (cpufreq_frequency_table_cpuinfo(pol, data->powernow_table)) {
- printk(KERN_ERR PFX "invalid powernow_table\n");
+ printk(KERN_ERR FW_BUG PFX "invalid powernow_table\n");
powernow_k8_cpu_exit_acpi(data);
kfree(data->powernow_table);
kfree(data);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 733c4f8..3ce029f 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -95,7 +95,8 @@ static void __init nvidia_bugs(int num, int slot, int func)
}
-static u32 ati_ixp4x0_rev(int num, int slot, int func)
+#if defined(CONFIG_ACPI) && defined(CONFIG_X86_IO_APIC)
+static u32 __init ati_ixp4x0_rev(int num, int slot, int func)
{
u32 d;
u8 b;
@@ -115,7 +116,6 @@ static u32 ati_ixp4x0_rev(int num, int slot, int func)
static void __init ati_bugs(int num, int slot, int func)
{
-#if defined(CONFIG_ACPI) && defined (CONFIG_X86_IO_APIC)
u32 d;
u8 b;
@@ -138,9 +138,56 @@ static void __init ati_bugs(int num, int slot, int func)
printk(KERN_INFO "If you got timer trouble "
"try acpi_use_timer_override\n");
}
-#endif
}
+static u32 __init ati_sbx00_rev(int num, int slot, int func)
+{
+ u32 old, d;
+
+ d = read_pci_config(num, slot, func, 0x70);
+ old = d;
+ d &= ~(1<<8);
+ write_pci_config(num, slot, func, 0x70, d);
+ d = read_pci_config(num, slot, func, 0x8);
+ d &= 0xff;
+ write_pci_config(num, slot, func, 0x70, old);
+
+ return d;
+}
+
+static void __init ati_bugs_contd(int num, int slot, int func)
+{
+ u32 d, rev;
+
+ if (acpi_use_timer_override)
+ return;
+
+ rev = ati_sbx00_rev(num, slot, func);
+ if (rev > 0x13)
+ return;
+
+ /* check for IRQ0 interrupt swap */
+ d = read_pci_config(num, slot, func, 0x64);
+ if (!(d & (1<<14)))
+ acpi_skip_timer_override = 1;
+
+ if (acpi_skip_timer_override) {
+ printk(KERN_INFO "SB600 revision 0x%x\n", rev);
+ printk(KERN_INFO "Ignoring ACPI timer override.\n");
+ printk(KERN_INFO "If you got timer trouble "
+ "try acpi_use_timer_override\n");
+ }
+}
+#else
+static void __init ati_bugs(int num, int slot, int func)
+{
+}
+
+static void __init ati_bugs_contd(int num, int slot, int func)
+{
+}
+#endif
+
#ifdef CONFIG_DMAR
static void __init intel_g33_dmar(int num, int slot, int func)
{
@@ -176,6 +223,8 @@ static struct chipset early_qrk[] __initdata = {
PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, fix_hypertransport_config },
{ PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_IXP400_SMBUS,
PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs },
+ { PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS,
+ PCI_CLASS_SERIAL_SMBUS, PCI_ANY_ID, 0, ati_bugs_contd },
#ifdef CONFIG_DMAR
{ PCI_VENDOR_ID_INTEL, 0x29c0,
PCI_CLASS_BRIDGE_HOST, PCI_ANY_ID, 0, intel_g33_dmar },
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index ccf6c50..d1d4dc5 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -36,7 +36,7 @@ void ack_bad_irq(unsigned int irq)
}
#ifdef CONFIG_X86_32
-# define irq_stats(x) (&per_cpu(irq_stat,x))
+# define irq_stats(x) (&per_cpu(irq_stat, x))
#else
# define irq_stats(x) cpu_pda(x)
#endif
@@ -113,7 +113,7 @@ int show_interrupts(struct seq_file *p, void *v)
if (i == 0) {
seq_printf(p, " ");
for_each_online_cpu(j)
- seq_printf(p, "CPU%-8d",j);
+ seq_printf(p, "CPU%-8d", j);
seq_putc(p, '\n');
}
diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c
index 1926248..1972266 100644
--- a/arch/x86/kernel/pci-dma.c
+++ b/arch/x86/kernel/pci-dma.c
@@ -9,8 +9,6 @@
#include <asm/calgary.h>
#include <asm/amd_iommu.h>
-static int forbid_dac __read_mostly;
-
struct dma_mapping_ops *dma_ops;
EXPORT_SYMBOL(dma_ops);
@@ -293,17 +291,3 @@ void pci_iommu_shutdown(void)
}
/* Must execute after PCI subsystem */
fs_initcall(pci_iommu_init);
-
-#ifdef CONFIG_PCI
-/* Many VIA bridges seem to corrupt data for DAC. Disable it here */
-
-static __devinit void via_no_dac(struct pci_dev *dev)
-{
- if ((dev->class >> 8) == PCI_CLASS_BRIDGE_PCI && forbid_dac == 0) {
- printk(KERN_INFO "PCI: VIA PCI bridge detected."
- "Disabling DAC.\n");
- forbid_dac = 1;
- }
-}
-DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, PCI_ANY_ID, via_no_dac);
-#endif
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index cd8c0ed..c958120f 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -63,6 +63,13 @@ void idle_notifier_register(struct notifier_block *n)
{
atomic_notifier_chain_register(&idle_notifier, n);
}
+EXPORT_SYMBOL_GPL(idle_notifier_register);
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+ atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_unregister);
void enter_idle(void)
{
diff --git a/arch/x86/oprofile/backtrace.c b/arch/x86/oprofile/backtrace.c
index e2095cb..04df67f 100644
--- a/arch/x86/oprofile/backtrace.c
+++ b/arch/x86/oprofile/backtrace.c
@@ -52,8 +52,7 @@ struct frame_head {
unsigned long ret;
} __attribute__((packed));
-static struct frame_head *
-dump_user_backtrace(struct frame_head * head)
+static struct frame_head *dump_user_backtrace(struct frame_head *head)
{
struct frame_head bufhead[2];
diff --git a/arch/x86/oprofile/nmi_int.c b/arch/x86/oprofile/nmi_int.c
index 57f6c90..022cd41 100644
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@@ -28,85 +28,9 @@ static struct op_x86_model_spec const *model;
static DEFINE_PER_CPU(struct op_msrs, cpu_msrs);
static DEFINE_PER_CPU(unsigned long, saved_lvtpc);
-static int nmi_start(void);
-static void nmi_stop(void);
-static void nmi_cpu_start(void *dummy);
-static void nmi_cpu_stop(void *dummy);
-
/* 0 == registered but off, 1 == registered and on */
static int nmi_enabled = 0;
-#ifdef CONFIG_SMP
-static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action,
- void *data)
-{
- int cpu = (unsigned long)data;
- switch (action) {
- case CPU_DOWN_FAILED:
- case CPU_ONLINE:
- smp_call_function_single(cpu, nmi_cpu_start, NULL, 0);
- break;
- case CPU_DOWN_PREPARE:
- smp_call_function_single(cpu, nmi_cpu_stop, NULL, 1);
- break;
- }
- return NOTIFY_DONE;
-}
-
-static struct notifier_block oprofile_cpu_nb = {
- .notifier_call = oprofile_cpu_notifier
-};
-#endif
-
-#ifdef CONFIG_PM
-
-static int nmi_suspend(struct sys_device *dev, pm_message_t state)
-{
- /* Only one CPU left, just stop that one */
- if (nmi_enabled == 1)
- nmi_cpu_stop(NULL);
- return 0;
-}
-
-static int nmi_resume(struct sys_device *dev)
-{
- if (nmi_enabled == 1)
- nmi_cpu_start(NULL);
- return 0;
-}
-
-static struct sysdev_class oprofile_sysclass = {
- .name = "oprofile",
- .resume = nmi_resume,
- .suspend = nmi_suspend,
-};
-
-static struct sys_device device_oprofile = {
- .id = 0,
- .cls = &oprofile_sysclass,
-};
-
-static int __init init_sysfs(void)
-{
- int error;
-
- error = sysdev_class_register(&oprofile_sysclass);
- if (!error)
- error = sysdev_register(&device_oprofile);
- return error;
-}
-
-static void exit_sysfs(void)
-{
- sysdev_unregister(&device_oprofile);
- sysdev_class_unregister(&oprofile_sysclass);
-}
-
-#else
-#define init_sysfs() do { } while (0)
-#define exit_sysfs() do { } while (0)
-#endif /* CONFIG_PM */
-
static int profile_exceptions_notify(struct notifier_block *self,
unsigned long val, void *data)
{
@@ -361,6 +285,77 @@ static int nmi_create_files(struct super_block *sb, struct dentry *root)
return 0;
}
+#ifdef CONFIG_SMP
+static int oprofile_cpu_notifier(struct notifier_block *b, unsigned long action,
+ void *data)
+{
+ int cpu = (unsigned long)data;
+ switch (action) {
+ case CPU_DOWN_FAILED:
+ case CPU_ONLINE:
+ smp_call_function_single(cpu, nmi_cpu_start, NULL, 0);
+ break;
+ case CPU_DOWN_PREPARE:
+ smp_call_function_single(cpu, nmi_cpu_stop, NULL, 1);
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block oprofile_cpu_nb = {
+ .notifier_call = oprofile_cpu_notifier
+};
+#endif
+
+#ifdef CONFIG_PM
+
+static int nmi_suspend(struct sys_device *dev, pm_message_t state)
+{
+ /* Only one CPU left, just stop that one */
+ if (nmi_enabled == 1)
+ nmi_cpu_stop(NULL);
+ return 0;
+}
+
+static int nmi_resume(struct sys_device *dev)
+{
+ if (nmi_enabled == 1)
+ nmi_cpu_start(NULL);
+ return 0;
+}
+
+static struct sysdev_class oprofile_sysclass = {
+ .name = "oprofile",
+ .resume = nmi_resume,
+ .suspend = nmi_suspend,
+};
+
+static struct sys_device device_oprofile = {
+ .id = 0,
+ .cls = &oprofile_sysclass,
+};
+
+static int __init init_sysfs(void)
+{
+ int error;
+
+ error = sysdev_class_register(&oprofile_sysclass);
+ if (!error)
+ error = sysdev_register(&device_oprofile);
+ return error;
+}
+
+static void exit_sysfs(void)
+{
+ sysdev_unregister(&device_oprofile);
+ sysdev_class_unregister(&oprofile_sysclass);
+}
+
+#else
+#define init_sysfs() do { } while (0)
+#define exit_sysfs() do { } while (0)
+#endif /* CONFIG_PM */
+
static int p4force;
module_param(p4force, int, 0);
@@ -420,9 +415,6 @@ static int __init ppro_init(char **cpu_type)
case 15: case 23:
*cpu_type = "i386/core_2";
break;
- case 26:
- *cpu_type = "i386/core_2";
- break;
default:
/* Unknown */
return 0;
@@ -432,6 +424,16 @@ static int __init ppro_init(char **cpu_type)
return 1;
}
+static int __init arch_perfmon_init(char **cpu_type)
+{
+ if (!cpu_has_arch_perfmon)
+ return 0;
+ *cpu_type = "i386/arch_perfmon";
+ model = &op_arch_perfmon_spec;
+ arch_perfmon_setup_counters();
+ return 1;
+}
+
/* in order to get sysfs right */
static int using_nmi;
@@ -439,7 +441,7 @@ int __init op_nmi_init(struct oprofile_operations *ops)
{
__u8 vendor = boot_cpu_data.x86_vendor;
__u8 family = boot_cpu_data.x86;
- char *cpu_type;
+ char *cpu_type = NULL;
int ret = 0;
if (!cpu_has_apic)
@@ -477,19 +479,20 @@ int __init op_nmi_init(struct oprofile_operations *ops)
switch (family) {
/* Pentium IV */
case 0xf:
- if (!p4_init(&cpu_type))
- return -ENODEV;
+ p4_init(&cpu_type);
break;
/* A P6-class processor */
case 6:
- if (!ppro_init(&cpu_type))
- return -ENODEV;
+ ppro_init(&cpu_type);
break;
default:
- return -ENODEV;
+ break;
}
+
+ if (!cpu_type && !arch_perfmon_init(&cpu_type))
+ return -ENODEV;
break;
default:
diff --git a/arch/x86/oprofile/op_counter.h b/arch/x86/oprofile/op_counter.h
index 2880b15..91b6a11 100644
--- a/arch/x86/oprofile/op_counter.h
+++ b/arch/x86/oprofile/op_counter.h
@@ -6,22 +6,22 @@
*
* @author John Levon
*/
-
+
#ifndef OP_COUNTER_H
#define OP_COUNTER_H
-
+
#define OP_MAX_COUNTER 8
-
+
/* Per-perfctr configuration as set via
* oprofilefs.
*/
struct op_counter_config {
- unsigned long count;
- unsigned long enabled;
- unsigned long event;
- unsigned long kernel;
- unsigned long user;
- unsigned long unit_mask;
+ unsigned long count;
+ unsigned long enabled;
+ unsigned long event;
+ unsigned long kernel;
+ unsigned long user;
+ unsigned long unit_mask;
};
extern struct op_counter_config counter_config[];
diff --git a/arch/x86/oprofile/op_model_amd.c b/arch/x86/oprofile/op_model_amd.c
index d9faf60..5095137 100644
--- a/arch/x86/oprofile/op_model_amd.c
+++ b/arch/x86/oprofile/op_model_amd.c
@@ -67,8 +67,9 @@ static unsigned long reset_value[NUM_COUNTERS];
/* The function interface needs to be fixed, something like add
data. Should then be added to linux/oprofile.h. */
-extern void oprofile_add_ibs_sample(struct pt_regs *const regs,
- unsigned int * const ibs_sample, u8 code);
+extern void
+oprofile_add_ibs_sample(struct pt_regs *const regs,
+ unsigned int *const ibs_sample, int ibs_code);
struct ibs_fetch_sample {
/* MSRC001_1031 IBS Fetch Linear Address Register */
@@ -309,12 +310,15 @@ static void op_amd_start(struct op_msrs const * const msrs)
#ifdef CONFIG_OPROFILE_IBS
if (ibs_allowed && ibs_config.fetch_enabled) {
low = (ibs_config.max_cnt_fetch >> 4) & 0xFFFF;
- high = IBS_FETCH_HIGH_ENABLE;
+ high = ((ibs_config.rand_en & 0x1) << 25) /* bit 57 */
+ + IBS_FETCH_HIGH_ENABLE;
wrmsr(MSR_AMD64_IBSFETCHCTL, low, high);
}
if (ibs_allowed && ibs_config.op_enabled) {
- low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF) + IBS_OP_LOW_ENABLE;
+ low = ((ibs_config.max_cnt_op >> 4) & 0xFFFF)
+ + ((ibs_config.dispatched_ops & 0x1) << 19) /* bit 19 */
+ + IBS_OP_LOW_ENABLE;
high = 0;
wrmsr(MSR_AMD64_IBSOPCTL, low, high);
}
@@ -468,11 +472,10 @@ static void clear_ibs_nmi(void)
on_each_cpu(apic_clear_ibs_nmi_per_cpu, NULL, 1);
}
-static int (*create_arch_files)(struct super_block * sb, struct dentry * root);
+static int (*create_arch_files)(struct super_block *sb, struct dentry *root);
-static int setup_ibs_files(struct super_block * sb, struct dentry * root)
+static int setup_ibs_files(struct super_block *sb, struct dentry *root)
{
- char buf[12];
struct dentry *dir;
int ret = 0;
@@ -494,22 +497,22 @@ static int setup_ibs_files(struct super_block * sb, struct dentry * root)
ibs_config.max_cnt_op = 250000;
ibs_config.op_enabled = 0;
ibs_config.dispatched_ops = 1;
- snprintf(buf, sizeof(buf), "ibs_fetch");
- dir = oprofilefs_mkdir(sb, root, buf);
- oprofilefs_create_ulong(sb, dir, "rand_enable",
- &ibs_config.rand_en);
+
+ dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
oprofilefs_create_ulong(sb, dir, "enable",
- &ibs_config.fetch_enabled);
+ &ibs_config.fetch_enabled);
oprofilefs_create_ulong(sb, dir, "max_count",
- &ibs_config.max_cnt_fetch);
- snprintf(buf, sizeof(buf), "ibs_uops");
- dir = oprofilefs_mkdir(sb, root, buf);
+ &ibs_config.max_cnt_fetch);
+ oprofilefs_create_ulong(sb, dir, "rand_enable",
+ &ibs_config.rand_en);
+
+ dir = oprofilefs_mkdir(sb, root, "ibs_op");
oprofilefs_create_ulong(sb, dir, "enable",
- &ibs_config.op_enabled);
+ &ibs_config.op_enabled);
oprofilefs_create_ulong(sb, dir, "max_count",
- &ibs_config.max_cnt_op);
+ &ibs_config.max_cnt_op);
oprofilefs_create_ulong(sb, dir, "dispatched_ops",
- &ibs_config.dispatched_ops);
+ &ibs_config.dispatched_ops);
return 0;
}
@@ -530,14 +533,14 @@ static void op_amd_exit(void)
#endif
struct op_x86_model_spec const op_amd_spec = {
- .init = op_amd_init,
- .exit = op_amd_exit,
- .num_counters = NUM_COUNTERS,
- .num_controls = NUM_CONTROLS,
- .fill_in_addresses = &op_amd_fill_in_addresses,
- .setup_ctrs = &op_amd_setup_ctrs,
- .check_ctrs = &op_amd_check_ctrs,
- .start = &op_amd_start,
- .stop = &op_amd_stop,
- .shutdown = &op_amd_shutdown
+ .init = op_amd_init,
+ .exit = op_amd_exit,
+ .num_counters = NUM_COUNTERS,
+ .num_controls = NUM_CONTROLS,
+ .fill_in_addresses = &op_amd_fill_in_addresses,
+ .setup_ctrs = &op_amd_setup_ctrs,
+ .check_ctrs = &op_amd_check_ctrs,
+ .start = &op_amd_start,
+ .stop = &op_amd_stop,
+ .shutdown = &op_amd_shutdown
};
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 43ac5af..4c4a51c 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -698,24 +698,24 @@ static void p4_shutdown(struct op_msrs const * const msrs)
#ifdef CONFIG_SMP
struct op_x86_model_spec const op_p4_ht2_spec = {
- .num_counters = NUM_COUNTERS_HT2,
- .num_controls = NUM_CONTROLS_HT2,
- .fill_in_addresses = &p4_fill_in_addresses,
- .setup_ctrs = &p4_setup_ctrs,
- .check_ctrs = &p4_check_ctrs,
- .start = &p4_start,
- .stop = &p4_stop,
- .shutdown = &p4_shutdown
+ .num_counters = NUM_COUNTERS_HT2,
+ .num_controls = NUM_CONTROLS_HT2,
+ .fill_in_addresses = &p4_fill_in_addresses,
+ .setup_ctrs = &p4_setup_ctrs,
+ .check_ctrs = &p4_check_ctrs,
+ .start = &p4_start,
+ .stop = &p4_stop,
+ .shutdown = &p4_shutdown
};
#endif
struct op_x86_model_spec const op_p4_spec = {
- .num_counters = NUM_COUNTERS_NON_HT,
- .num_controls = NUM_CONTROLS_NON_HT,
- .fill_in_addresses = &p4_fill_in_addresses,
- .setup_ctrs = &p4_setup_ctrs,
- .check_ctrs = &p4_check_ctrs,
- .start = &p4_start,
- .stop = &p4_stop,
- .shutdown = &p4_shutdown
+ .num_counters = NUM_COUNTERS_NON_HT,
+ .num_controls = NUM_CONTROLS_NON_HT,
+ .fill_in_addresses = &p4_fill_in_addresses,
+ .setup_ctrs = &p4_setup_ctrs,
+ .check_ctrs = &p4_check_ctrs,
+ .start = &p4_start,
+ .stop = &p4_stop,
+ .shutdown = &p4_shutdown
};
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index eff431f..0620d6d 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -1,32 +1,34 @@
/*
* @file op_model_ppro.h
- * pentium pro / P6 model-specific MSR operations
+ * Family 6 perfmon and architectural perfmon MSR operations
*
* @remark Copyright 2002 OProfile authors
+ * @remark Copyright 2008 Intel Corporation
* @remark Read the file COPYING
*
* @author John Levon
* @author Philippe Elie
* @author Graydon Hoare
+ * @author Andi Kleen
*/
#include <linux/oprofile.h>
+#include <linux/slab.h>
#include <asm/ptrace.h>
#include <asm/msr.h>
#include <asm/apic.h>
#include <asm/nmi.h>
+#include <asm/intel_arch_perfmon.h>
#include "op_x86_model.h"
#include "op_counter.h"
-#define NUM_COUNTERS 2
-#define NUM_CONTROLS 2
+static int num_counters = 2;
+static int counter_width = 32;
#define CTR_IS_RESERVED(msrs, c) (msrs->counters[(c)].addr ? 1 : 0)
#define CTR_READ(l, h, msrs, c) do {rdmsr(msrs->counters[(c)].addr, (l), (h)); } while (0)
-#define CTR_32BIT_WRITE(l, msrs, c) \
- do {wrmsr(msrs->counters[(c)].addr, -(u32)(l), 0); } while (0)
-#define CTR_OVERFLOWED(n) (!((n) & (1U<<31)))
+#define CTR_OVERFLOWED(n) (!((n) & (1U<<(counter_width-1))))
#define CTRL_IS_RESERVED(msrs, c) (msrs->controls[(c)].addr ? 1 : 0)
#define CTRL_READ(l, h, msrs, c) do {rdmsr((msrs->controls[(c)].addr), (l), (h)); } while (0)
@@ -40,20 +42,20 @@
#define CTRL_SET_UM(val, m) (val |= (m << 8))
#define CTRL_SET_EVENT(val, e) (val |= e)
-static unsigned long reset_value[NUM_COUNTERS];
+static u64 *reset_value;
static void ppro_fill_in_addresses(struct op_msrs * const msrs)
{
int i;
- for (i = 0; i < NUM_COUNTERS; i++) {
+ for (i = 0; i < num_counters; i++) {
if (reserve_perfctr_nmi(MSR_P6_PERFCTR0 + i))
msrs->counters[i].addr = MSR_P6_PERFCTR0 + i;
else
msrs->counters[i].addr = 0;
}
- for (i = 0; i < NUM_CONTROLS; i++) {
+ for (i = 0; i < num_counters; i++) {
if (reserve_evntsel_nmi(MSR_P6_EVNTSEL0 + i))
msrs->controls[i].addr = MSR_P6_EVNTSEL0 + i;
else
@@ -67,8 +69,22 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
unsigned int low, high;
int i;
+ if (!reset_value) {
+ reset_value = kmalloc(sizeof(unsigned) * num_counters,
+ GFP_ATOMIC);
+ if (!reset_value)
+ return;
+ }
+
+ if (cpu_has_arch_perfmon) {
+ union cpuid10_eax eax;
+ eax.full = cpuid_eax(0xa);
+ if (counter_width < eax.split.bit_width)
+ counter_width = eax.split.bit_width;
+ }
+
/* clear all counters */
- for (i = 0 ; i < NUM_CONTROLS; ++i) {
+ for (i = 0 ; i < num_counters; ++i) {
if (unlikely(!CTRL_IS_RESERVED(msrs, i)))
continue;
CTRL_READ(low, high, msrs, i);
@@ -77,18 +93,18 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
}
/* avoid a false detection of ctr overflows in NMI handler */
- for (i = 0; i < NUM_COUNTERS; ++i) {
+ for (i = 0; i < num_counters; ++i) {
if (unlikely(!CTR_IS_RESERVED(msrs, i)))
continue;
- CTR_32BIT_WRITE(1, msrs, i);
+ wrmsrl(msrs->counters[i].addr, -1LL);
}
/* enable active counters */
- for (i = 0; i < NUM_COUNTERS; ++i) {
+ for (i = 0; i < num_counters; ++i) {
if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs, i))) {
reset_value[i] = counter_config[i].count;
- CTR_32BIT_WRITE(counter_config[i].count, msrs, i);
+ wrmsrl(msrs->counters[i].addr, -reset_value[i]);
CTRL_READ(low, high, msrs, i);
CTRL_CLEAR(low);
@@ -111,13 +127,13 @@ static int ppro_check_ctrs(struct pt_regs * const regs,
unsigned int low, high;
int i;
- for (i = 0 ; i < NUM_COUNTERS; ++i) {
+ for (i = 0 ; i < num_counters; ++i) {
if (!reset_value[i])
continue;
CTR_READ(low, high, msrs, i);
if (CTR_OVERFLOWED(low)) {
oprofile_add_sample(regs, i);
- CTR_32BIT_WRITE(reset_value[i], msrs, i);
+ wrmsrl(msrs->counters[i].addr, -reset_value[i]);
}
}
@@ -141,7 +157,7 @@ static void ppro_start(struct op_msrs const * const msrs)
unsigned int low, high;
int i;
- for (i = 0; i < NUM_COUNTERS; ++i) {
+ for (i = 0; i < num_counters; ++i) {
if (reset_value[i]) {
CTRL_READ(low, high, msrs, i);
CTRL_SET_ACTIVE(low);
@@ -156,7 +172,7 @@ static void ppro_stop(struct op_msrs const * const msrs)
unsigned int low, high;
int i;
- for (i = 0; i < NUM_COUNTERS; ++i) {
+ for (i = 0; i < num_counters; ++i) {
if (!reset_value[i])
continue;
CTRL_READ(low, high, msrs, i);
@@ -169,24 +185,70 @@ static void ppro_shutdown(struct op_msrs const * const msrs)
{
int i;
- for (i = 0 ; i < NUM_COUNTERS ; ++i) {
+ for (i = 0 ; i < num_counters ; ++i) {
if (CTR_IS_RESERVED(msrs, i))
release_perfctr_nmi(MSR_P6_PERFCTR0 + i);
}
- for (i = 0 ; i < NUM_CONTROLS ; ++i) {
+ for (i = 0 ; i < num_counters ; ++i) {
if (CTRL_IS_RESERVED(msrs, i))
release_evntsel_nmi(MSR_P6_EVNTSEL0 + i);
}
+ if (reset_value) {
+ kfree(reset_value);
+ reset_value = NULL;
+ }
}
-struct op_x86_model_spec const op_ppro_spec = {
- .num_counters = NUM_COUNTERS,
- .num_controls = NUM_CONTROLS,
- .fill_in_addresses = &ppro_fill_in_addresses,
- .setup_ctrs = &ppro_setup_ctrs,
- .check_ctrs = &ppro_check_ctrs,
- .start = &ppro_start,
- .stop = &ppro_stop,
- .shutdown = &ppro_shutdown
+struct op_x86_model_spec op_ppro_spec = {
+ .num_counters = 2, /* can be overriden */
+ .num_controls = 2, /* dito */
+ .fill_in_addresses = &ppro_fill_in_addresses,
+ .setup_ctrs = &ppro_setup_ctrs,
+ .check_ctrs = &ppro_check_ctrs,
+ .start = &ppro_start,
+ .stop = &ppro_stop,
+ .shutdown = &ppro_shutdown
+};
+
+/*
+ * Architectural performance monitoring.
+ *
+ * Newer Intel CPUs (Core1+) have support for architectural
+ * events described in CPUID 0xA. See the IA32 SDM Vol3b.18 for details.
+ * The advantage of this is that it can be done without knowing about
+ * the specific CPU.
+ */
+
+void arch_perfmon_setup_counters(void)
+{
+ union cpuid10_eax eax;
+
+ eax.full = cpuid_eax(0xa);
+
+ /* Workaround for BIOS bugs in 6/15. Taken from perfmon2 */
+ if (eax.split.version_id == 0 && current_cpu_data.x86 == 6 &&
+ current_cpu_data.x86_model == 15) {
+ eax.split.version_id = 2;
+ eax.split.num_counters = 2;
+ eax.split.bit_width = 40;
+ }
+
+ num_counters = eax.split.num_counters;
+
+ op_arch_perfmon_spec.num_counters = num_counters;
+ op_arch_perfmon_spec.num_controls = num_counters;
+ op_ppro_spec.num_counters = num_counters;
+ op_ppro_spec.num_controls = num_counters;
+}
+
+struct op_x86_model_spec op_arch_perfmon_spec = {
+ /* num_counters/num_controls filled in at runtime */
+ .fill_in_addresses = &ppro_fill_in_addresses,
+ /* user space does the cpuid check for available events */
+ .setup_ctrs = &ppro_setup_ctrs,
+ .check_ctrs = &ppro_check_ctrs,
+ .start = &ppro_start,
+ .stop = &ppro_stop,
+ .shutdown = &ppro_shutdown
};
diff --git a/arch/x86/oprofile/op_x86_model.h b/arch/x86/oprofile/op_x86_model.h
index 05a0261..825e790 100644
--- a/arch/x86/oprofile/op_x86_model.h
+++ b/arch/x86/oprofile/op_x86_model.h
@@ -22,8 +22,8 @@ struct op_msr {
};
struct op_msrs {
- struct op_msr * counters;
- struct op_msr * controls;
+ struct op_msr *counters;
+ struct op_msr *controls;
};
struct pt_regs;
@@ -34,8 +34,8 @@ struct pt_regs;
struct op_x86_model_spec {
int (*init)(struct oprofile_operations *ops);
void (*exit)(void);
- unsigned int const num_counters;
- unsigned int const num_controls;
+ unsigned int num_counters;
+ unsigned int num_controls;
void (*fill_in_addresses)(struct op_msrs * const msrs);
void (*setup_ctrs)(struct op_msrs const * const msrs);
int (*check_ctrs)(struct pt_regs * const regs,
@@ -45,9 +45,12 @@ struct op_x86_model_spec {
void (*shutdown)(struct op_msrs const * const msrs);
};
-extern struct op_x86_model_spec const op_ppro_spec;
+extern struct op_x86_model_spec op_ppro_spec;
extern struct op_x86_model_spec const op_p4_spec;
extern struct op_x86_model_spec const op_p4_ht2_spec;
extern struct op_x86_model_spec const op_amd_spec;
+extern struct op_x86_model_spec op_arch_perfmon_spec;
+
+extern void arch_perfmon_setup_counters(void);
#endif /* OP_X86_MODEL_H */
generated by cgit v0.10.2 at 2024-11-12 22:24:45 (GMT)