Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rric/oprofile

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rric/oprofile: (21 commits)
  OProfile: Fix buffer synchronization for IBS
  oprofile: hotplug cpu fix
  oprofile: fixing whitespaces in arch/x86/oprofile/*
  oprofile: fixing whitespaces in arch/x86/oprofile/*
  oprofile: fixing whitespaces in drivers/oprofile/*
  x86/oprofile: add the logic for enabling additional IBS bits
  x86/oprofile: reordering functions in nmi_int.c
  x86/oprofile: removing unused function parameter in add_ibs_begin()
  oprofile: more whitespace fixes
  oprofile: whitespace fixes
  OProfile: Rename IBS sysfs dir into "ibs_op"
  OProfile: Rework string handling in setup_ibs_files()
  OProfile: Rework oprofile_add_ibs_sample() function
  oprofile: discover counters for op ppro too
  oprofile: Implement Intel architectural perfmon support
  oprofile: Don't report Nehalem as core_2
  oprofile: drop const in num counters field
  Revert "Oprofile Multiplexing Patch"
  x86, oprofile: BUG: using smp_processor_id() in preemptible code
  x86/oprofile: fix on_each_cpu build error
  ...

Manually fixed trivial conflicts in
	drivers/oprofile/{cpu_buffer.c,event_buffer.h}

arch/alpha/oprofile/common.c

@@ -106,7 +106,7 @@ op_axp_stop(void)
 }
 
 static int
-op_axp_create_files(struct super_block * sb, struct dentry * root)
+op_axp_create_files(struct super_block *sb, struct dentry *root)
 {
 	int i;
 

arch/ia64/oprofile/init.c

@@ -12,11 +12,11 @@
 #include <linux/init.h>
 #include <linux/errno.h>
  
-extern int perfmon_init(struct oprofile_operations * ops);
+extern int perfmon_init(struct oprofile_operations *ops);
 extern void perfmon_exit(void);
 extern void ia64_backtrace(struct pt_regs * const regs, unsigned int depth);
 
-int __init oprofile_arch_init(struct oprofile_operations * ops)
+int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
 	int ret = -ENODEV;
 

arch/ia64/oprofile/perfmon.c

@@ -56,7 +56,7 @@ static pfm_buffer_fmt_t oprofile_fmt = {
 };
 
 
-static char * get_cpu_type(void)
+static char *get_cpu_type(void)
 {
 	__u8 family = local_cpu_data->family;
 
@@ -75,7 +75,7 @@ static char * get_cpu_type(void)
 
 static int using_perfmon;
 
-int perfmon_init(struct oprofile_operations * ops)
+int perfmon_init(struct oprofile_operations *ops)
 {
 	int ret = pfm_register_buffer_fmt(&oprofile_fmt);
 	if (ret)

arch/m32r/oprofile/init.c

@@ -12,7 +12,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 
-int __init oprofile_arch_init(struct oprofile_operations * ops)
+int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
 	return -ENODEV;
 }

arch/mips/oprofile/common.c

@@ -32,7 +32,7 @@ static int op_mips_setup(void)
         return 0;
 }
 
-static int op_mips_create_files(struct super_block * sb, struct dentry * root)
+static int op_mips_create_files(struct super_block *sb, struct dentry *root)
 {
 	int i;
 

arch/mips/oprofile/op_impl.h

@@ -27,7 +27,7 @@ struct op_counter_config {
 /* Per-architecture configury and hooks.  */
 struct op_mips_model {
 	void (*reg_setup) (struct op_counter_config *);
-	void (*cpu_setup) (void * dummy);
+	void (*cpu_setup) (void *dummy);
 	int (*init)(void);
 	void (*exit)(void);
 	void (*cpu_start)(void *args);

arch/mips/oprofile/op_model_rm9000.c

@@ -80,7 +80,7 @@ static void rm9000_cpu_stop(void *args)
 	write_c0_perfcontrol(0);
 }
 
-static irqreturn_t rm9000_perfcount_handler(int irq, void * dev_id)
+static irqreturn_t rm9000_perfcount_handler(int irq, void *dev_id)
 {
 	unsigned int control = read_c0_perfcontrol();
 	struct pt_regs *regs = get_irq_regs();

arch/parisc/oprofile/init.c

@@ -12,7 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/oprofile.h>
 
-int __init oprofile_arch_init(struct oprofile_operations * ops)
+int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
 	return -ENODEV;
 }

arch/powerpc/oprofile/op_model_cell.c

@@ -404,7 +404,7 @@ set_count_mode(u32 kernel, u32 user)
 	}
 }
 
-static inline void enable_ctr(u32 cpu, u32 ctr, u32 * pm07_cntrl)
+static inline void enable_ctr(u32 cpu, u32 ctr, u32 *pm07_cntrl)
 {
 
 	pm07_cntrl[ctr] |= CBE_PM_CTR_ENABLE;

arch/sparc/oprofile/init.c

@@ -12,7 +12,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
  
-int __init oprofile_arch_init(struct oprofile_operations * ops)
+int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
 	return -ENODEV;
 }

arch/sparc64/oprofile/init.c

@@ -12,7 +12,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
  
-int __init oprofile_arch_init(struct oprofile_operations * ops)
+int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
 	return -ENODEV;
 }

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];
 

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:

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[];

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);
+
+	dir = oprofilefs_mkdir(sb, root, "ibs_fetch");
+	oprofilefs_create_ulong(sb, dir, "enable",
+				&ibs_config.fetch_enabled);
+	oprofilefs_create_ulong(sb, dir, "max_count",
+				&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.fetch_enabled);
+				&ibs_config.op_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);
-	oprofilefs_create_ulong(sb, dir, "enable",
-		&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
 };

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
 };

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
 };

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 */

drivers/oprofile/buffer_sync.c

@@ -41,7 +41,6 @@ static cpumask_t marked_cpus = CPU_MASK_NONE;
 static DEFINE_SPINLOCK(task_mortuary);
 static void process_task_mortuary(void);
 
-
 /* Take ownership of the task struct and place it on the
  * list for processing. Only after two full buffer syncs
  * does the task eventually get freed, because by then
@@ -341,7 +340,7 @@ static void add_trace_begin(void)
  * Add IBS fetch and op entries to event buffer
  */
 static void add_ibs_begin(struct oprofile_cpu_buffer *cpu_buf, int code,
-	int in_kernel, struct mm_struct *mm)
+			  struct mm_struct *mm)
 {
 	unsigned long rip;
 	int i, count;
@@ -565,9 +564,11 @@ void sync_buffer(int cpu)
 	struct task_struct *new;
 	unsigned long cookie = 0;
 	int in_kernel = 1;
-	unsigned int i;
 	sync_buffer_state state = sb_buffer_start;
+#ifndef CONFIG_OPROFILE_IBS
+	unsigned int i;
 	unsigned long available;
+#endif
 
 	mutex_lock(&buffer_mutex);
 
@@ -575,9 +576,13 @@ void sync_buffer(int cpu)
 
 	/* Remember, only we can modify tail_pos */
 
+#ifndef CONFIG_OPROFILE_IBS
 	available = get_slots(cpu_buf);
 
 	for (i = 0; i < available; ++i) {
+#else
+	while (get_slots(cpu_buf)) {
+#endif
 		struct op_sample *s = &cpu_buf->buffer[cpu_buf->tail_pos];
 
 		if (is_code(s->eip)) {
@@ -593,12 +598,10 @@ void sync_buffer(int cpu)
 #ifdef CONFIG_OPROFILE_IBS
 			} else if (s->event == IBS_FETCH_BEGIN) {
 				state = sb_bt_start;
-				add_ibs_begin(cpu_buf,
-					IBS_FETCH_CODE, in_kernel, mm);
+				add_ibs_begin(cpu_buf, IBS_FETCH_CODE, mm);
 			} else if (s->event == IBS_OP_BEGIN) {
 				state = sb_bt_start;
-				add_ibs_begin(cpu_buf,
-					IBS_OP_CODE, in_kernel, mm);
+				add_ibs_begin(cpu_buf, IBS_OP_CODE, mm);
 #endif
 			} else {
 				struct mm_struct *oldmm = mm;

drivers/oprofile/buffer_sync.h

@@ -9,13 +9,13 @@
 
 #ifndef OPROFILE_BUFFER_SYNC_H
 #define OPROFILE_BUFFER_SYNC_H
- 
+
 /* add the necessary profiling hooks */
 int sync_start(void);
 
 /* remove the hooks */
 void sync_stop(void);
- 
+
 /* sync the given CPU's buffer */
 void sync_buffer(int cpu);