Merge phase #5 (misc) of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

Merges oprofile, timers/hpet, x86/traps, x86/time, and x86/core misc items.

* 'x86-core-v4-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (132 commits)
  x86: change early_ioremap to use slots instead of nesting
  x86: adjust dependencies for CONFIG_X86_CMOV
  dumpstack: x86: various small unification steps, fix
  x86: remove additional_cpus
  x86: remove additional_cpus configurability
  x86: improve UP kernel when CPU-hotplug and SMP is enabled
  dumpstack: x86: various small unification steps
  dumpstack: i386: make kstack= an early boot-param and add oops=panic
  dumpstack: x86: use log_lvl and unify trace formatting
  dumptrace: x86: consistently include loglevel, print stack switch
  dumpstack: x86: add "end" parameter to valid_stack_ptr and print_context_stack
  dumpstack: x86: make printk_address equal
  dumpstack: x86: move die_nmi to dumpstack_32.c
  traps: x86: finalize unification of traps.c
  traps: x86: make traps_32.c and traps_64.c equal
  traps: x86: various noop-changes preparing for unification of traps_xx.c
  traps: x86_64: use task_pid_nr(tsk) instead of tsk->pid in do_general_protection
  traps: i386: expand clear_mem_error and remove from mach_traps.h
  traps: x86_64: make io_check_error equal to the one on i386
  traps: i386: use preempt_conditional_sti/cli in do_int3
  ...

4 files changed, 306 insertions, 138 deletions

diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index b3f5dbc6d88..f3cfb4c7612 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -53,6 +53,11 @@
 
 #define HPET_RANGE_SIZE		1024	/* from HPET spec */
 
+
+/* WARNING -- don't get confused.  These macros are never used
+ * to write the (single) counter, and rarely to read it.
+ * They're badly named; to fix, someday.
+ */
 #if BITS_PER_LONG == 64
 #define	write_counter(V, MC)	writeq(V, MC)
 #define	read_counter(MC)	readq(MC)
@@ -77,7 +82,7 @@ static struct clocksource clocksource_hpet = {
         .rating         = 250,
         .read           = read_hpet,
         .mask           = CLOCKSOURCE_MASK(64),
-        .mult           = 0, /*to be caluclated*/
+	.mult		= 0, /* to be calculated */
         .shift          = 10,
         .flags          = CLOCK_SOURCE_IS_CONTINUOUS,
 };
@@ -86,8 +91,6 @@ static struct clocksource *hpet_clocksource;
 
 /* A lock for concurrent access by app and isr hpet activity. */
 static DEFINE_SPINLOCK(hpet_lock);
-/* A lock for concurrent intermodule access to hpet and isr hpet activity. */
-static DEFINE_SPINLOCK(hpet_task_lock);
 
 #define	HPET_DEV_NAME	(7)
 
@@ -99,7 +102,6 @@ struct hpet_dev {
 	unsigned long hd_irqdata;
 	wait_queue_head_t hd_waitqueue;
 	struct fasync_struct *hd_async_queue;
-	struct hpet_task *hd_task;
 	unsigned int hd_flags;
 	unsigned int hd_irq;
 	unsigned int hd_hdwirq;
@@ -173,11 +175,6 @@ static irqreturn_t hpet_interrupt(int irq, void *data)
 		writel(isr, &devp->hd_hpet->hpet_isr);
 	spin_unlock(&hpet_lock);
 
-	spin_lock(&hpet_task_lock);
-	if (devp->hd_task)
-		devp->hd_task->ht_func(devp->hd_task->ht_data);
-	spin_unlock(&hpet_task_lock);
-
 	wake_up_interruptible(&devp->hd_waitqueue);
 
 	kill_fasync(&devp->hd_async_queue, SIGIO, POLL_IN);
@@ -185,6 +182,67 @@ static irqreturn_t hpet_interrupt(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
+static void hpet_timer_set_irq(struct hpet_dev *devp)
+{
+	unsigned long v;
+	int irq, gsi;
+	struct hpet_timer __iomem *timer;
+
+	spin_lock_irq(&hpet_lock);
+	if (devp->hd_hdwirq) {
+		spin_unlock_irq(&hpet_lock);
+		return;
+	}
+
+	timer = devp->hd_timer;
+
+	/* we prefer level triggered mode */
+	v = readl(&timer->hpet_config);
+	if (!(v & Tn_INT_TYPE_CNF_MASK)) {
+		v |= Tn_INT_TYPE_CNF_MASK;
+		writel(v, &timer->hpet_config);
+	}
+	spin_unlock_irq(&hpet_lock);
+
+	v = (readq(&timer->hpet_config) & Tn_INT_ROUTE_CAP_MASK) >>
+				 Tn_INT_ROUTE_CAP_SHIFT;
+
+	/*
+	 * In PIC mode, skip IRQ0-4, IRQ6-9, IRQ12-15 which is always used by
+	 * legacy device. In IO APIC mode, we skip all the legacy IRQS.
+	 */
+	if (acpi_irq_model == ACPI_IRQ_MODEL_PIC)
+		v &= ~0xf3df;
+	else
+		v &= ~0xffff;
+
+	for (irq = find_first_bit(&v, HPET_MAX_IRQ); irq < HPET_MAX_IRQ;
+		irq = find_next_bit(&v, HPET_MAX_IRQ, 1 + irq)) {
+
+		if (irq >= NR_IRQS) {
+			irq = HPET_MAX_IRQ;
+			break;
+		}
+
+		gsi = acpi_register_gsi(irq, ACPI_LEVEL_SENSITIVE,
+					ACPI_ACTIVE_LOW);
+		if (gsi > 0)
+			break;
+
+		/* FIXME: Setup interrupt source table */
+	}
+
+	if (irq < HPET_MAX_IRQ) {
+		spin_lock_irq(&hpet_lock);
+		v = readl(&timer->hpet_config);
+		v |= irq << Tn_INT_ROUTE_CNF_SHIFT;
+		writel(v, &timer->hpet_config);
+		devp->hd_hdwirq = gsi;
+		spin_unlock_irq(&hpet_lock);
+	}
+	return;
+}
+
 static int hpet_open(struct inode *inode, struct file *file)
 {
 	struct hpet_dev *devp;
@@ -199,8 +257,7 @@ static int hpet_open(struct inode *inode, struct file *file)
 
 	for (devp = NULL, hpetp = hpets; hpetp && !devp; hpetp = hpetp->hp_next)
 		for (i = 0; i < hpetp->hp_ntimer; i++)
-			if (hpetp->hp_dev[i].hd_flags & HPET_OPEN
-			    || hpetp->hp_dev[i].hd_task)
+			if (hpetp->hp_dev[i].hd_flags & HPET_OPEN)
 				continue;
 			else {
 				devp = &hpetp->hp_dev[i];
@@ -219,6 +276,8 @@ static int hpet_open(struct inode *inode, struct file *file)
 	spin_unlock_irq(&hpet_lock);
 	unlock_kernel();
 
+	hpet_timer_set_irq(devp);
+
 	return 0;
 }
 
@@ -441,7 +500,11 @@ static int hpet_ioctl_ieon(struct hpet_dev *devp)
 	devp->hd_irq = irq;
 	t = devp->hd_ireqfreq;
 	v = readq(&timer->hpet_config);
-	g = v | Tn_INT_ENB_CNF_MASK;
+
+	/* 64-bit comparators are not yet supported through the ioctls,
+	 * so force this into 32-bit mode if it supports both modes
+	 */
+	g = v | Tn_32MODE_CNF_MASK | Tn_INT_ENB_CNF_MASK;
 
 	if (devp->hd_flags & HPET_PERIODIC) {
 		write_counter(t, &timer->hpet_compare);
@@ -451,6 +514,12 @@ static int hpet_ioctl_ieon(struct hpet_dev *devp)
 		v |= Tn_VAL_SET_CNF_MASK;
 		writeq(v, &timer->hpet_config);
 		local_irq_save(flags);
+
+		/* NOTE:  what we modify here is a hidden accumulator
+		 * register supported by periodic-capable comparators.
+		 * We never want to modify the (single) counter; that
+		 * would affect all the comparators.
+		 */
 		m = read_counter(&hpet->hpet_mc);
 		write_counter(t + m + hpetp->hp_delta, &timer->hpet_compare);
 	} else {
@@ -604,57 +673,6 @@ static int hpet_is_known(struct hpet_data *hdp)
 	return 0;
 }
 
-static inline int hpet_tpcheck(struct hpet_task *tp)
-{
-	struct hpet_dev *devp;
-	struct hpets *hpetp;
-
-	devp = tp->ht_opaque;
-
-	if (!devp)
-		return -ENXIO;
-
-	for (hpetp = hpets; hpetp; hpetp = hpetp->hp_next)
-		if (devp >= hpetp->hp_dev
-		    && devp < (hpetp->hp_dev + hpetp->hp_ntimer)
-		    && devp->hd_hpet == hpetp->hp_hpet)
-			return 0;
-
-	return -ENXIO;
-}
-
-#if 0
-int hpet_unregister(struct hpet_task *tp)
-{
-	struct hpet_dev *devp;
-	struct hpet_timer __iomem *timer;
-	int err;
-
-	if ((err = hpet_tpcheck(tp)))
-		return err;
-
-	spin_lock_irq(&hpet_task_lock);
-	spin_lock(&hpet_lock);
-
-	devp = tp->ht_opaque;
-	if (devp->hd_task != tp) {
-		spin_unlock(&hpet_lock);
-		spin_unlock_irq(&hpet_task_lock);
-		return -ENXIO;
-	}
-
-	timer = devp->hd_timer;
-	writeq((readq(&timer->hpet_config) & ~Tn_INT_ENB_CNF_MASK),
-	       &timer->hpet_config);
-	devp->hd_flags &= ~(HPET_IE | HPET_PERIODIC);
-	devp->hd_task = NULL;
-	spin_unlock(&hpet_lock);
-	spin_unlock_irq(&hpet_task_lock);
-
-	return 0;
-}
-#endif  /*  0  */
-
 static ctl_table hpet_table[] = {
 	{
 	 .ctl_name = CTL_UNNUMBERED,
@@ -746,6 +764,7 @@ int hpet_alloc(struct hpet_data *hdp)
 	static struct hpets *last = NULL;
 	unsigned long period;
 	unsigned long long temp;
+	u32 remainder;
 
 	/*
 	 * hpet_alloc can be called by platform dependent code.
@@ -809,9 +828,13 @@ int hpet_alloc(struct hpet_data *hdp)
 		printk("%s %d", i > 0 ? "," : "", hdp->hd_irq[i]);
 	printk("\n");
 
-	printk(KERN_INFO "hpet%u: %u %d-bit timers, %Lu Hz\n",
-	       hpetp->hp_which, hpetp->hp_ntimer,
-	       cap & HPET_COUNTER_SIZE_MASK ? 64 : 32, hpetp->hp_tick_freq);
+	temp = hpetp->hp_tick_freq;
+	remainder = do_div(temp, 1000000);
+	printk(KERN_INFO
+		"hpet%u: %u comparators, %d-bit %u.%06u MHz counter\n",
+		hpetp->hp_which, hpetp->hp_ntimer,
+		cap & HPET_COUNTER_SIZE_MASK ? 64 : 32,
+		(unsigned) temp, remainder);
 
 	mcfg = readq(&hpet->hpet_config);
 	if ((mcfg & HPET_ENABLE_CNF_MASK) == 0) {
@@ -874,8 +897,6 @@ static acpi_status hpet_resources(struct acpi_resource *res, void *data)
 		hdp->hd_address = ioremap(addr.minimum, addr.address_length);
 
 		if (hpet_is_known(hdp)) {
-			printk(KERN_DEBUG "%s: 0x%lx is busy\n",
-				__func__, hdp->hd_phys_address);
 			iounmap(hdp->hd_address);
 			return AE_ALREADY_EXISTS;
 		}
@@ -891,8 +912,6 @@ static acpi_status hpet_resources(struct acpi_resource *res, void *data)
 						HPET_RANGE_SIZE);
 
 		if (hpet_is_known(hdp)) {
-			printk(KERN_DEBUG "%s: 0x%lx is busy\n",
-				__func__, hdp->hd_phys_address);
 			iounmap(hdp->hd_address);
 			return AE_ALREADY_EXISTS;
 		}
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index 9304c455507..ed982273fb8 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -5,6 +5,7 @@
  * @remark Read the file COPYING
  *
  * @author John Levon <levon@movementarian.org>
+ * @author Barry Kasindorf
  *
  * This is the core of the buffer management. Each
  * CPU buffer is processed and entered into the
@@ -33,7 +34,7 @@
 #include "event_buffer.h"
 #include "cpu_buffer.h"
 #include "buffer_sync.h"
- 
+
 static LIST_HEAD(dying_tasks);
 static LIST_HEAD(dead_tasks);
 static cpumask_t marked_cpus = CPU_MASK_NONE;
@@ -48,10 +49,11 @@ static void process_task_mortuary(void);
  * Can be invoked from softirq via RCU callback due to
  * call_rcu() of the task struct, hence the _irqsave.
  */
-static int task_free_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+task_free_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	unsigned long flags;
-	struct task_struct * task = data;
+	struct task_struct *task = data;
 	spin_lock_irqsave(&task_mortuary, flags);
 	list_add(&task->tasks, &dying_tasks);
 	spin_unlock_irqrestore(&task_mortuary, flags);
@@ -62,13 +64,14 @@ static int task_free_notify(struct notifier_block * self, unsigned long val, voi
 /* The task is on its way out. A sync of the buffer means we can catch
  * any remaining samples for this task.
  */
-static int task_exit_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+task_exit_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	/* To avoid latency problems, we only process the current CPU,
 	 * hoping that most samples for the task are on this CPU
 	 */
 	sync_buffer(raw_smp_processor_id());
-  	return 0;
+	return 0;
 }
 
 
@@ -77,11 +80,12 @@ static int task_exit_notify(struct notifier_block * self, unsigned long val, voi
  * we don't lose any. This does not have to be exact, it's a QoI issue
  * only.
  */
-static int munmap_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+munmap_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 	unsigned long addr = (unsigned long)data;
-	struct mm_struct * mm = current->mm;
-	struct vm_area_struct * mpnt;
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *mpnt;
 
 	down_read(&mm->mmap_sem);
 
@@ -99,11 +103,12 @@ static int munmap_notify(struct notifier_block * self, unsigned long val, void *
 	return 0;
 }
 
- 
+
 /* We need to be told about new modules so we don't attribute to a previously
  * loaded module, or drop the samples on the floor.
  */
-static int module_load_notify(struct notifier_block * self, unsigned long val, void * data)
+static int
+module_load_notify(struct notifier_block *self, unsigned long val, void *data)
 {
 #ifdef CONFIG_MODULES
 	if (val != MODULE_STATE_COMING)
@@ -118,7 +123,7 @@ static int module_load_notify(struct notifier_block * self, unsigned long val, v
 	return 0;
 }
 
- 
+
 static struct notifier_block task_free_nb = {
 	.notifier_call	= task_free_notify,
 };
@@ -135,7 +140,7 @@ static struct notifier_block module_load_nb = {
 	.notifier_call = module_load_notify,
 };
 
- 
+
 static void end_sync(void)
 {
 	end_cpu_work();
@@ -208,14 +213,14 @@ static inline unsigned long fast_get_dcookie(struct path *path)
  * not strictly necessary but allows oprofile to associate
  * shared-library samples with particular applications
  */
-static unsigned long get_exec_dcookie(struct mm_struct * mm)
+static unsigned long get_exec_dcookie(struct mm_struct *mm)
 {
 	unsigned long cookie = NO_COOKIE;
-	struct vm_area_struct * vma;
- 
+	struct vm_area_struct *vma;
+
 	if (!mm)
 		goto out;
- 
+
 	for (vma = mm->mmap; vma; vma = vma->vm_next) {
 		if (!vma->vm_file)
 			continue;
@@ -235,13 +240,14 @@ out:
  * sure to do this lookup before a mm->mmap modification happens so
  * we don't lose track.
  */
-static unsigned long lookup_dcookie(struct mm_struct * mm, unsigned long addr, off_t * offset)
+static unsigned long
+lookup_dcookie(struct mm_struct *mm, unsigned long addr, off_t *offset)
 {
 	unsigned long cookie = NO_COOKIE;
-	struct vm_area_struct * vma;
+	struct vm_area_struct *vma;
 
 	for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
- 
+
 		if (addr < vma->vm_start || addr >= vma->vm_end)
 			continue;
 
@@ -263,9 +269,20 @@ static unsigned long lookup_dcookie(struct mm_struct * mm, unsigned long addr, o
 	return cookie;
 }
 
+static void increment_tail(struct oprofile_cpu_buffer *b)
+{
+	unsigned long new_tail = b->tail_pos + 1;
+
+	rmb();	/* be sure fifo pointers are synchromized */
+
+	if (new_tail < b->buffer_size)
+		b->tail_pos = new_tail;
+	else
+		b->tail_pos = 0;
+}
 
 static unsigned long last_cookie = INVALID_COOKIE;
- 
+
 static void add_cpu_switch(int i)
 {
 	add_event_entry(ESCAPE_CODE);
@@ -278,16 +295,16 @@ static void add_kernel_ctx_switch(unsigned int in_kernel)
 {
 	add_event_entry(ESCAPE_CODE);
 	if (in_kernel)
-		add_event_entry(KERNEL_ENTER_SWITCH_CODE); 
+		add_event_entry(KERNEL_ENTER_SWITCH_CODE);
 	else
-		add_event_entry(KERNEL_EXIT_SWITCH_CODE); 
+		add_event_entry(KERNEL_EXIT_SWITCH_CODE);
 }
- 
+
 static void
-add_user_ctx_switch(struct task_struct const * task, unsigned long cookie)
+add_user_ctx_switch(struct task_struct const *task, unsigned long cookie)
 {
 	add_event_entry(ESCAPE_CODE);
-	add_event_entry(CTX_SWITCH_CODE); 
+	add_event_entry(CTX_SWITCH_CODE);
 	add_event_entry(task->pid);
 	add_event_entry(cookie);
 	/* Another code for daemon back-compat */
@@ -296,7 +313,7 @@ add_user_ctx_switch(struct task_struct const * task, unsigned long cookie)
 	add_event_entry(task->tgid);
 }
 
- 
+
 static void add_cookie_switch(unsigned long cookie)
 {
 	add_event_entry(ESCAPE_CODE);
@@ -304,13 +321,78 @@ static void add_cookie_switch(unsigned long cookie)
 	add_event_entry(cookie);
 }
 
- 
+
 static void add_trace_begin(void)
 {
 	add_event_entry(ESCAPE_CODE);
 	add_event_entry(TRACE_BEGIN_CODE);
 }
 
+#ifdef CONFIG_OPROFILE_IBS
+
+#define IBS_FETCH_CODE_SIZE	2
+#define IBS_OP_CODE_SIZE	5
+#define IBS_EIP(offset)				\
+	(((struct op_sample *)&cpu_buf->buffer[(offset)])->eip)
+#define IBS_EVENT(offset)				\
+	(((struct op_sample *)&cpu_buf->buffer[(offset)])->event)
+
+/*
+ * 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)
+{
+	unsigned long rip;
+	int i, count;
+	unsigned long ibs_cookie = 0;
+	off_t offset;
+
+	increment_tail(cpu_buf);	/* move to RIP entry */
+
+	rip = IBS_EIP(cpu_buf->tail_pos);
+
+#ifdef __LP64__
+	rip += IBS_EVENT(cpu_buf->tail_pos) << 32;
+#endif
+
+	if (mm) {
+		ibs_cookie = lookup_dcookie(mm, rip, &offset);
+
+		if (ibs_cookie == NO_COOKIE)
+			offset = rip;
+		if (ibs_cookie == INVALID_COOKIE) {
+			atomic_inc(&oprofile_stats.sample_lost_no_mapping);
+			offset = rip;
+		}
+		if (ibs_cookie != last_cookie) {
+			add_cookie_switch(ibs_cookie);
+			last_cookie = ibs_cookie;
+		}
+	} else
+		offset = rip;
+
+	add_event_entry(ESCAPE_CODE);
+	add_event_entry(code);
+	add_event_entry(offset);	/* Offset from Dcookie */
+
+	/* we send the Dcookie offset, but send the raw Linear Add also*/
+	add_event_entry(IBS_EIP(cpu_buf->tail_pos));
+	add_event_entry(IBS_EVENT(cpu_buf->tail_pos));
+
+	if (code == IBS_FETCH_CODE)
+		count = IBS_FETCH_CODE_SIZE;	/*IBS FETCH is 2 int64s*/
+	else
+		count = IBS_OP_CODE_SIZE;	/*IBS OP is 5 int64s*/
+
+	for (i = 0; i < count; i++) {
+		increment_tail(cpu_buf);
+		add_event_entry(IBS_EIP(cpu_buf->tail_pos));
+		add_event_entry(IBS_EVENT(cpu_buf->tail_pos));
+	}
+}
+
+#endif
 
 static void add_sample_entry(unsigned long offset, unsigned long event)
 {
@@ -319,13 +401,13 @@ static void add_sample_entry(unsigned long offset, unsigned long event)
 }
 
 
-static int add_us_sample(struct mm_struct * mm, struct op_sample * s)
+static int add_us_sample(struct mm_struct *mm, struct op_sample *s)
 {
 	unsigned long cookie;
 	off_t offset;
- 
- 	cookie = lookup_dcookie(mm, s->eip, &offset);
- 
+
+	cookie = lookup_dcookie(mm, s->eip, &offset);
+
 	if (cookie == INVALID_COOKIE) {
 		atomic_inc(&oprofile_stats.sample_lost_no_mapping);
 		return 0;
@@ -341,13 +423,13 @@ static int add_us_sample(struct mm_struct * mm, struct op_sample * s)
 	return 1;
 }
 
- 
+
 /* Add a sample to the global event buffer. If possible the
  * sample is converted into a persistent dentry/offset pair
  * for later lookup from userspace.
  */
 static int
-add_sample(struct mm_struct * mm, struct op_sample * s, int in_kernel)
+add_sample(struct mm_struct *mm, struct op_sample *s, int in_kernel)
 {
 	if (in_kernel) {
 		add_sample_entry(s->eip, s->event);
@@ -359,9 +441,9 @@ add_sample(struct mm_struct * mm, struct op_sample * s, int in_kernel)
 	}
 	return 0;
 }
- 
 
-static void release_mm(struct mm_struct * mm)
+
+static void release_mm(struct mm_struct *mm)
 {
 	if (!mm)
 		return;
@@ -370,9 +452,9 @@ static void release_mm(struct mm_struct * mm)
 }
 
 
-static struct mm_struct * take_tasks_mm(struct task_struct * task)
+static struct mm_struct *take_tasks_mm(struct task_struct *task)
 {
-	struct mm_struct * mm = get_task_mm(task);
+	struct mm_struct *mm = get_task_mm(task);
 	if (mm)
 		down_read(&mm->mmap_sem);
 	return mm;
@@ -383,10 +465,10 @@ static inline int is_code(unsigned long val)
 {
 	return val == ESCAPE_CODE;
 }
- 
+
 
 /* "acquire" as many cpu buffer slots as we can */
-static unsigned long get_slots(struct oprofile_cpu_buffer * b)
+static unsigned long get_slots(struct oprofile_cpu_buffer *b)
 {
 	unsigned long head = b->head_pos;
 	unsigned long tail = b->tail_pos;
@@ -412,19 +494,6 @@ static unsigned long get_slots(struct oprofile_cpu_buffer * b)
 }
 
 
-static void increment_tail(struct oprofile_cpu_buffer * b)
-{
-	unsigned long new_tail = b->tail_pos + 1;
-
-	rmb();
-
-	if (new_tail < b->buffer_size)
-		b->tail_pos = new_tail;
-	else
-		b->tail_pos = 0;
-}
-
-
 /* Move tasks along towards death. Any tasks on dead_tasks
  * will definitely have no remaining references in any
  * CPU buffers at this point, because we use two lists,
@@ -435,8 +504,8 @@ static void process_task_mortuary(void)
 {
 	unsigned long flags;
 	LIST_HEAD(local_dead_tasks);
-	struct task_struct * task;
-	struct task_struct * ttask;
+	struct task_struct *task;
+	struct task_struct *ttask;
 
 	spin_lock_irqsave(&task_mortuary, flags);
 
@@ -493,7 +562,7 @@ void sync_buffer(int cpu)
 {
 	struct oprofile_cpu_buffer *cpu_buf = &per_cpu(cpu_buffer, cpu);
 	struct mm_struct *mm = NULL;
-	struct task_struct * new;
+	struct task_struct *new;
 	unsigned long cookie = 0;
 	int in_kernel = 1;
 	unsigned int i;
@@ -501,7 +570,7 @@ void sync_buffer(int cpu)
 	unsigned long available;
 
 	mutex_lock(&buffer_mutex);
- 
+
 	add_cpu_switch(cpu);
 
 	/* Remember, only we can modify tail_pos */
@@ -509,8 +578,8 @@ void sync_buffer(int cpu)
 	available = get_slots(cpu_buf);
 
 	for (i = 0; i < available; ++i) {
-		struct op_sample * s = &cpu_buf->buffer[cpu_buf->tail_pos];
- 
+		struct op_sample *s = &cpu_buf->buffer[cpu_buf->tail_pos];
+
 		if (is_code(s->eip)) {
 			if (s->event <= CPU_IS_KERNEL) {
 				/* kernel/userspace switch */
@@ -521,8 +590,18 @@ void sync_buffer(int cpu)
 			} else if (s->event == CPU_TRACE_BEGIN) {
 				state = sb_bt_start;
 				add_trace_begin();
+#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);
+			} else if (s->event == IBS_OP_BEGIN) {
+				state = sb_bt_start;
+				add_ibs_begin(cpu_buf,
+					IBS_OP_CODE, in_kernel, mm);
+#endif
 			} else {
-				struct mm_struct * oldmm = mm;
+				struct mm_struct *oldmm = mm;
 
 				/* userspace context switch */
 				new = (struct task_struct *)s->event;
@@ -533,13 +612,11 @@ void sync_buffer(int cpu)
 					cookie = get_exec_dcookie(mm);
 				add_user_ctx_switch(new, cookie);
 			}
-		} else {
-			if (state >= sb_bt_start &&
-			    !add_sample(mm, s, in_kernel)) {
-				if (state == sb_bt_start) {
-					state = sb_bt_ignore;
-					atomic_inc(&oprofile_stats.bt_lost_no_mapping);
-				}
+		} else if (state >= sb_bt_start &&
+			   !add_sample(mm, s, in_kernel)) {
+			if (state == sb_bt_start) {
+				state = sb_bt_ignore;
+				atomic_inc(&oprofile_stats.bt_lost_no_mapping);
 			}
 		}
 
diff --git a/drivers/oprofile/cpu_buffer.c b/drivers/oprofile/cpu_buffer.c
index 7ba78e6d210..e1bd5a937f6 100644
--- a/drivers/oprofile/cpu_buffer.c
+++ b/drivers/oprofile/cpu_buffer.c
@@ -5,6 +5,7 @@
  * @remark Read the file COPYING
  *
  * @author John Levon <levon@movementarian.org>
+ * @author Barry Kasindorf <barry.kasindorf@amd.com>
  *
  * Each CPU has a local buffer that stores PC value/event
  * pairs. We also log context switches when we notice them.
@@ -209,7 +210,7 @@ static int log_sample(struct oprofile_cpu_buffer * cpu_buf, unsigned long pc,
 	return 1;
 }
 
-static int oprofile_begin_trace(struct oprofile_cpu_buffer * cpu_buf)
+static int oprofile_begin_trace(struct oprofile_cpu_buffer *cpu_buf)
 {
 	if (nr_available_slots(cpu_buf) < 4) {
 		cpu_buf->sample_lost_overflow++;
@@ -254,6 +255,75 @@ void oprofile_add_sample(struct pt_regs * const regs, unsigned long event)
 	oprofile_add_ext_sample(pc, regs, event, is_kernel);
 }
 
+#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)
+{
+	struct task_struct *task;
+
+	cpu_buf->sample_received++;
+
+	if (nr_available_slots(cpu_buf) < MAX_IBS_SAMPLE_SIZE) {
+		cpu_buf->sample_lost_overflow++;
+		return 0;
+	}
+
+	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;
+		add_code(cpu_buf, is_kernel);
+	}
+
+	/* 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);
+		}
+	}
+
+	add_code(cpu_buf, ibs_code);
+	add_sample(cpu_buf, ibs[0], ibs[1]);
+	add_sample(cpu_buf, ibs[2], ibs[3]);
+	add_sample(cpu_buf, ibs[4], ibs[5]);
+
+	if (ibs_code == IBS_OP_BEGIN) {
+	add_sample(cpu_buf, ibs[6], ibs[7]);
+	add_sample(cpu_buf, ibs[8], ibs[9]);
+	add_sample(cpu_buf, ibs[10], ibs[11]);
+	}
+
+	return 1;
+}
+
+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);
+}
+
+#endif
+
 void oprofile_add_pc(unsigned long pc, int is_kernel, unsigned long event)
 {
 	struct oprofile_cpu_buffer *cpu_buf = &__get_cpu_var(cpu_buffer);
@@ -296,7 +366,7 @@ static void wq_sync_buffer(struct work_struct *work)
 	struct oprofile_cpu_buffer * b =
 		container_of(work, struct oprofile_cpu_buffer, work.work);
 	if (b->cpu != smp_processor_id()) {
-		printk("WQ on CPU%d, prefer CPU%d\n",
+		printk(KERN_DEBUG "WQ on CPU%d, prefer CPU%d\n",
 		       smp_processor_id(), b->cpu);
 	}
 	sync_buffer(b->cpu);
diff --git a/drivers/oprofile/cpu_buffer.h b/drivers/oprofile/cpu_buffer.h
index c3e366b5226..9c44d004da6 100644
--- a/drivers/oprofile/cpu_buffer.h
+++ b/drivers/oprofile/cpu_buffer.h
@@ -55,5 +55,7 @@ void cpu_buffer_reset(struct oprofile_cpu_buffer * cpu_buf);
 /* transient events for the CPU buffer -> event buffer */
 #define CPU_IS_KERNEL 1
 #define CPU_TRACE_BEGIN 2
+#define IBS_FETCH_BEGIN 3
+#define IBS_OP_BEGIN    4
 
 #endif /* OPROFILE_CPU_BUFFER_H */