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/x86/oprofile/backtrace.c

@@ -52,8 +52,7 @@ struct frame_head {
 	unsigned long ret;
 } __attribute__((packed));
 
-static struct frame_head *
+static struct frame_head *dump_user_backtrace(struct frame_head *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))
+			p4_init(&cpu_type);
-				return -ENODEV;
 			break;
 
 			/* A P6-class processor */
 		case 6:
-			if (!ppro_init(&cpu_type))
+			ppro_init(&cpu_type);
-				return -ENODEV;
 			break;
 
 		default:
-			return -ENODEV;
+			break;
 		}
+
+		if (!cpu_type && !arch_perfmon_init(&cpu_type))
+			return -ENODEV;
 		break;
 
 	default:

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,
+extern void
-				    unsigned int * const ibs_sample, u8 code);
+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);
 	}
@@ -472,7 +476,6 @@ static int (*create_arch_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;
 
@@ -494,16 +497,16 @@ 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, "rand_enable",
-				&ibs_config.rand_en);
 	oprofilefs_create_ulong(sb, dir, "enable",
 				&ibs_config.fetch_enabled);
 	oprofilefs_create_ulong(sb, dir, "max_count",
 				&ibs_config.max_cnt_fetch);
-	snprintf(buf,  sizeof(buf), "ibs_uops");
+	oprofilefs_create_ulong(sb, dir, "rand_enable",
-	dir = oprofilefs_mkdir(sb, root, buf);
+				&ibs_config.rand_en);
+
+	dir = oprofilefs_mkdir(sb, root, "ibs_op");
 	oprofilefs_create_ulong(sb, dir, "enable",
 				&ibs_config.op_enabled);
 	oprofilefs_create_ulong(sb, dir, "max_count",

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
+static int num_counters = 2;
-#define NUM_CONTROLS 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)	\
+#define CTR_OVERFLOWED(n) (!((n) & (1U<<(counter_width-1))))
-	do {wrmsr(msrs->counters[(c)].addr, -(u32)(l), 0); } while (0)
-#define CTR_OVERFLOWED(n) (!((n) & (1U<<31)))
 
 #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);
@@ -169,20 +185,24 @@ 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 = {
+struct op_x86_model_spec op_ppro_spec = {
-	.num_counters = NUM_COUNTERS,
+	.num_counters		= 2,	/* can be overriden */
-	.num_controls = NUM_CONTROLS,
+	.num_controls		= 2,	/* dito */
 	.fill_in_addresses	= &ppro_fill_in_addresses,
 	.setup_ctrs		= &ppro_setup_ctrs,
 	.check_ctrs		= &ppro_check_ctrs,
@@ -190,3 +210,45 @@ struct op_x86_model_spec const op_ppro_spec = {
 	.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

@@ -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 num_counters;
-	unsigned int const num_controls;
+	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,
+				add_ibs_begin(cpu_buf, IBS_FETCH_CODE, mm);
-					IBS_FETCH_CODE, in_kernel, mm);
 			} else if (s->event == IBS_OP_BEGIN) {
 				state = sb_bt_start;
-				add_ibs_begin(cpu_buf,
+				add_ibs_begin(cpu_buf, IBS_OP_CODE, mm);
-					IBS_OP_CODE, in_kernel, mm);
 #endif
 			} else {
 				struct mm_struct *oldmm = mm;

drivers/oprofile/cpu_buffer.c

@@ -39,7 +39,7 @@ void free_cpu_buffers(void)
 {
 	int i;
 
-	for_each_online_cpu(i) {
+	for_each_possible_cpu(i) {
 		vfree(per_cpu(cpu_buffer, i).buffer);
 		per_cpu(cpu_buffer, i).buffer = NULL;
 	}
@@ -64,7 +64,7 @@ int alloc_cpu_buffers(void)
 
 	unsigned long buffer_size = fs_cpu_buffer_size;
 
-	for_each_online_cpu(i) {
+	for_each_possible_cpu(i) {
 		struct oprofile_cpu_buffer *b = &per_cpu(cpu_buffer, i);
 
 		b->buffer = vmalloc_node(sizeof(struct op_sample) * buffer_size,
@@ -271,20 +271,22 @@ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
 #ifdef CONFIG_OPROFILE_IBS
 
 #define MAX_IBS_SAMPLE_SIZE 14
-static int log_ibs_sample(struct oprofile_cpu_buffer *cpu_buf,
+
-	unsigned long pc, int is_kernel, unsigned  int *ibs, int ibs_code)
+void oprofile_add_ibs_sample(struct pt_regs *const regs,
+			     unsigned int *const ibs_sample, int ibs_code)
 {
+	int is_kernel = !user_mode(regs);
+	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
 	struct task_struct *task;
 
 	cpu_buf->sample_received++;
 
 	if (nr_available_slots(cpu_buf) < MAX_IBS_SAMPLE_SIZE) {
+		/* we can't backtrace since we lost the source of this event */
 		cpu_buf->sample_lost_overflow++;
-		return 0;
+		return;
 	}
 
-	is_kernel = !!is_kernel;
-
 	/* notice a switch from user->kernel or vice versa */
 	if (cpu_buf->last_is_kernel != is_kernel) {
 		cpu_buf->last_is_kernel = is_kernel;
@@ -294,7 +296,6 @@ static int log_ibs_sample(struct oprofile_cpu_buffer *cpu_buf,
 	/* notice a task switch */
 	if (!is_kernel) {
 		task = current;
-
 		if (cpu_buf->last_task != task) {
 			cpu_buf->last_task = task;
 			add_code(cpu_buf, (unsigned long)task);
@@ -302,36 +303,17 @@ static int log_ibs_sample(struct oprofile_cpu_buffer *cpu_buf,
 	}
 
 	add_code(cpu_buf, ibs_code);
-	add_sample(cpu_buf, ibs[0], ibs[1]);
+	add_sample(cpu_buf, ibs_sample[0], ibs_sample[1]);
-	add_sample(cpu_buf, ibs[2], ibs[3]);
+	add_sample(cpu_buf, ibs_sample[2], ibs_sample[3]);
-	add_sample(cpu_buf, ibs[4], ibs[5]);
+	add_sample(cpu_buf, ibs_sample[4], ibs_sample[5]);
 
 	if (ibs_code == IBS_OP_BEGIN) {
-	add_sample(cpu_buf, ibs[6], ibs[7]);
+		add_sample(cpu_buf, ibs_sample[6], ibs_sample[7]);
-	add_sample(cpu_buf, ibs[8], ibs[9]);
+		add_sample(cpu_buf, ibs_sample[8], ibs_sample[9]);
-	add_sample(cpu_buf, ibs[10], ibs[11]);
+		add_sample(cpu_buf, ibs_sample[10], ibs_sample[11]);
 	}
 
-	return 1;
+	if (backtrace_depth)
-}
-
-void oprofile_add_ibs_sample(struct pt_regs *const regs,
-				unsigned int * const ibs_sample, u8 code)
-{
-	int is_kernel = !user_mode(regs);
-	unsigned long pc = profile_pc(regs);
-
-	struct oprofile_cpu_buffer *cpu_buf =
-			 &per_cpu(cpu_buffer, smp_processor_id());
-
-	if (!backtrace_depth) {
-		log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code);
-		return;
-	}
-
-	/* if log_sample() fails we can't backtrace since we lost the source
-	* of this event */
-	if (log_ibs_sample(cpu_buf, pc, is_kernel, ibs_sample, code))
 		oprofile_ops.backtrace(regs, backtrace_depth);
 }
 
@@ -381,6 +363,11 @@ static void wq_sync_buffer(struct work_struct *work)
 	if (b->cpu != smp_processor_id()) {
 		printk(KERN_DEBUG "WQ on CPU%d, prefer CPU%d\n",
 		       smp_processor_id(), b->cpu);
+
+		if (!cpu_online(b->cpu)) {
+			cancel_delayed_work(&b->work);
+			return;
+		}
 	}
 	sync_buffer(b->cpu);