Initial import

6 files changed, 1862 insertions, 0 deletions

diff --git a/arch/s390/oprofile/Makefile b/arch/s390/oprofile/Makefile
new file mode 100644
index 000000000..1bd230171
--- /dev/null
+++ b/arch/s390/oprofile/Makefile
@@ -0,0 +1,10 @@
+obj-$(CONFIG_OPROFILE) += oprofile.o
+
+DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
+		oprof.o cpu_buffer.o buffer_sync.o \
+		event_buffer.o oprofile_files.o \
+		oprofilefs.o oprofile_stats.o  \
+		timer_int.o )
+
+oprofile-y :=	$(DRIVER_OBJS) init.o backtrace.o
+oprofile-y +=	hwsampler.o
diff --git a/arch/s390/oprofile/backtrace.c b/arch/s390/oprofile/backtrace.c
new file mode 100644
index 000000000..8a6811b2c
--- /dev/null
+++ b/arch/s390/oprofile/backtrace.c
@@ -0,0 +1,77 @@
+/*
+ * S390 Version
+ *   Copyright IBM Corp. 2005
+ *   Author(s): Andreas Krebbel <Andreas.Krebbel@de.ibm.com>
+ */
+
+#include <linux/oprofile.h>
+
+#include <asm/processor.h> /* for struct stack_frame */
+
+static unsigned long
+__show_trace(unsigned int *depth, unsigned long sp,
+	     unsigned long low, unsigned long high)
+{
+	struct stack_frame *sf;
+	struct pt_regs *regs;
+
+	while (*depth) {
+		sp = sp & PSW_ADDR_INSN;
+		if (sp < low || sp > high - sizeof(*sf))
+			return sp;
+		sf = (struct stack_frame *) sp;
+		(*depth)--;
+		oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN);
+
+		/* Follow the backchain.  */
+		while (*depth) {
+			low = sp;
+			sp = sf->back_chain & PSW_ADDR_INSN;
+			if (!sp)
+				break;
+			if (sp <= low || sp > high - sizeof(*sf))
+				return sp;
+			sf = (struct stack_frame *) sp;
+			(*depth)--;
+			oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN);
+
+		}
+
+		if (*depth == 0)
+			break;
+
+		/* Zero backchain detected, check for interrupt frame.  */
+		sp = (unsigned long) (sf + 1);
+		if (sp <= low || sp > high - sizeof(*regs))
+			return sp;
+		regs = (struct pt_regs *) sp;
+		(*depth)--;
+		oprofile_add_trace(sf->gprs[8] & PSW_ADDR_INSN);
+		low = sp;
+		sp = regs->gprs[15];
+	}
+	return sp;
+}
+
+void s390_backtrace(struct pt_regs * const regs, unsigned int depth)
+{
+	unsigned long head;
+	struct stack_frame* head_sf;
+
+	if (user_mode(regs))
+		return;
+
+	head = regs->gprs[15];
+	head_sf = (struct stack_frame*)head;
+
+	if (!head_sf->back_chain)
+		return;
+
+	head = head_sf->back_chain;
+
+	head = __show_trace(&depth, head, S390_lowcore.async_stack - ASYNC_SIZE,
+			    S390_lowcore.async_stack);
+
+	__show_trace(&depth, head, S390_lowcore.thread_info,
+		     S390_lowcore.thread_info + THREAD_SIZE);
+}
diff --git a/arch/s390/oprofile/hwsampler.c b/arch/s390/oprofile/hwsampler.c
new file mode 100644
index 000000000..ff9b4eb34
--- /dev/null
+++ b/arch/s390/oprofile/hwsampler.c
@@ -0,0 +1,1178 @@
+/*
+ * Copyright IBM Corp. 2010
+ * Author: Heinz Graalfs <graalfs@de.ibm.com>
+ */
+
+#include <linux/kernel_stat.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/smp.h>
+#include <linux/errno.h>
+#include <linux/workqueue.h>
+#include <linux/interrupt.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/semaphore.h>
+#include <linux/oom.h>
+#include <linux/oprofile.h>
+
+#include <asm/facility.h>
+#include <asm/cpu_mf.h>
+#include <asm/irq.h>
+
+#include "hwsampler.h"
+#include "op_counter.h"
+
+#define MAX_NUM_SDB 511
+#define MIN_NUM_SDB 1
+
+DECLARE_PER_CPU(struct hws_cpu_buffer, sampler_cpu_buffer);
+
+struct hws_execute_parms {
+	void *buffer;
+	signed int rc;
+};
+
+DEFINE_PER_CPU(struct hws_cpu_buffer, sampler_cpu_buffer);
+EXPORT_PER_CPU_SYMBOL(sampler_cpu_buffer);
+
+static DEFINE_MUTEX(hws_sem);
+static DEFINE_MUTEX(hws_sem_oom);
+
+static unsigned char hws_flush_all;
+static unsigned int hws_oom;
+static unsigned int hws_alert;
+static struct workqueue_struct *hws_wq;
+
+static unsigned int hws_state;
+enum {
+	HWS_INIT = 1,
+	HWS_DEALLOCATED,
+	HWS_STOPPED,
+	HWS_STARTED,
+	HWS_STOPPING };
+
+/* set to 1 if called by kernel during memory allocation */
+static unsigned char oom_killer_was_active;
+/* size of SDBT and SDB as of allocate API */
+static unsigned long num_sdbt = 100;
+static unsigned long num_sdb = 511;
+/* sampling interval (machine cycles) */
+static unsigned long interval;
+
+static unsigned long min_sampler_rate;
+static unsigned long max_sampler_rate;
+
+static void execute_qsi(void *parms)
+{
+	struct hws_execute_parms *ep = parms;
+
+	ep->rc = qsi(ep->buffer);
+}
+
+static void execute_ssctl(void *parms)
+{
+	struct hws_execute_parms *ep = parms;
+
+	ep->rc = lsctl(ep->buffer);
+}
+
+static int smp_ctl_ssctl_stop(int cpu)
+{
+	int rc;
+	struct hws_execute_parms ep;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	cb->ssctl.es = 0;
+	cb->ssctl.cs = 0;
+
+	ep.buffer = &cb->ssctl;
+	smp_call_function_single(cpu, execute_ssctl, &ep, 1);
+	rc = ep.rc;
+	if (rc) {
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF SSCTL failed.\n", cpu);
+		dump_stack();
+	}
+
+	ep.buffer = &cb->qsi;
+	smp_call_function_single(cpu, execute_qsi, &ep, 1);
+
+	if (cb->qsi.es || cb->qsi.cs) {
+		printk(KERN_EMERG "CPUMF sampling did not stop properly.\n");
+		dump_stack();
+	}
+
+	return rc;
+}
+
+static int smp_ctl_ssctl_deactivate(int cpu)
+{
+	int rc;
+	struct hws_execute_parms ep;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	cb->ssctl.es = 1;
+	cb->ssctl.cs = 0;
+
+	ep.buffer = &cb->ssctl;
+	smp_call_function_single(cpu, execute_ssctl, &ep, 1);
+	rc = ep.rc;
+	if (rc)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF SSCTL failed.\n", cpu);
+
+	ep.buffer = &cb->qsi;
+	smp_call_function_single(cpu, execute_qsi, &ep, 1);
+
+	if (cb->qsi.cs)
+		printk(KERN_EMERG "CPUMF sampling was not set inactive.\n");
+
+	return rc;
+}
+
+static int smp_ctl_ssctl_enable_activate(int cpu, unsigned long interval)
+{
+	int rc;
+	struct hws_execute_parms ep;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	cb->ssctl.h = 1;
+	cb->ssctl.tear = cb->first_sdbt;
+	cb->ssctl.dear = *(unsigned long *) cb->first_sdbt;
+	cb->ssctl.interval = interval;
+	cb->ssctl.es = 1;
+	cb->ssctl.cs = 1;
+
+	ep.buffer = &cb->ssctl;
+	smp_call_function_single(cpu, execute_ssctl, &ep, 1);
+	rc = ep.rc;
+	if (rc)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF SSCTL failed.\n", cpu);
+
+	ep.buffer = &cb->qsi;
+	smp_call_function_single(cpu, execute_qsi, &ep, 1);
+	if (ep.rc)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF QSI failed.\n", cpu);
+
+	return rc;
+}
+
+static int smp_ctl_qsi(int cpu)
+{
+	struct hws_execute_parms ep;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	ep.buffer = &cb->qsi;
+	smp_call_function_single(cpu, execute_qsi, &ep, 1);
+
+	return ep.rc;
+}
+
+static void hws_ext_handler(struct ext_code ext_code,
+			    unsigned int param32, unsigned long param64)
+{
+	struct hws_cpu_buffer *cb = this_cpu_ptr(&sampler_cpu_buffer);
+
+	if (!(param32 & CPU_MF_INT_SF_MASK))
+		return;
+
+	if (!hws_alert)
+		return;
+
+	inc_irq_stat(IRQEXT_CMS);
+	atomic_xchg(&cb->ext_params, atomic_read(&cb->ext_params) | param32);
+
+	if (hws_wq)
+		queue_work(hws_wq, &cb->worker);
+}
+
+static void worker(struct work_struct *work);
+
+static void add_samples_to_oprofile(unsigned cpu, unsigned long *,
+				unsigned long *dear);
+
+static void init_all_cpu_buffers(void)
+{
+	int cpu;
+	struct hws_cpu_buffer *cb;
+
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		memset(cb, 0, sizeof(struct hws_cpu_buffer));
+	}
+}
+
+static void prepare_cpu_buffers(void)
+{
+	struct hws_cpu_buffer *cb;
+	int cpu;
+
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		atomic_set(&cb->ext_params, 0);
+		cb->worker_entry = 0;
+		cb->sample_overflow = 0;
+		cb->req_alert = 0;
+		cb->incorrect_sdbt_entry = 0;
+		cb->invalid_entry_address = 0;
+		cb->loss_of_sample_data = 0;
+		cb->sample_auth_change_alert = 0;
+		cb->finish = 0;
+		cb->oom = 0;
+		cb->stop_mode = 0;
+	}
+}
+
+/*
+ * allocate_sdbt() - allocate sampler memory
+ * @cpu: the cpu for which sampler memory is allocated
+ *
+ * A 4K page is allocated for each requested SDBT.
+ * A maximum of 511 4K pages are allocated for the SDBs in each of the SDBTs.
+ * Set ALERT_REQ mask in each SDBs trailer.
+ * Returns zero if successful, <0 otherwise.
+ */
+static int allocate_sdbt(int cpu)
+{
+	int j, k, rc;
+	unsigned long *sdbt;
+	unsigned long  sdb;
+	unsigned long *tail;
+	unsigned long *trailer;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	if (cb->first_sdbt)
+		return -EINVAL;
+
+	sdbt = NULL;
+	tail = sdbt;
+
+	for (j = 0; j < num_sdbt; j++) {
+		sdbt = (unsigned long *)get_zeroed_page(GFP_KERNEL);
+
+		mutex_lock(&hws_sem_oom);
+		/* OOM killer might have been activated */
+		barrier();
+		if (oom_killer_was_active || !sdbt) {
+			if (sdbt)
+				free_page((unsigned long)sdbt);
+
+			goto allocate_sdbt_error;
+		}
+		if (cb->first_sdbt == 0)
+			cb->first_sdbt = (unsigned long)sdbt;
+
+		/* link current page to tail of chain */
+		if (tail)
+			*tail = (unsigned long)(void *)sdbt + 1;
+
+		mutex_unlock(&hws_sem_oom);
+
+		for (k = 0; k < num_sdb; k++) {
+			/* get and set SDB page */
+			sdb = get_zeroed_page(GFP_KERNEL);
+
+			mutex_lock(&hws_sem_oom);
+			/* OOM killer might have been activated */
+			barrier();
+			if (oom_killer_was_active || !sdb) {
+				if (sdb)
+					free_page(sdb);
+
+				goto allocate_sdbt_error;
+			}
+			*sdbt = sdb;
+			trailer = trailer_entry_ptr(*sdbt);
+			*trailer = SDB_TE_ALERT_REQ_MASK;
+			sdbt++;
+			mutex_unlock(&hws_sem_oom);
+		}
+		tail = sdbt;
+	}
+	mutex_lock(&hws_sem_oom);
+	if (oom_killer_was_active)
+		goto allocate_sdbt_error;
+
+	rc = 0;
+	if (tail)
+		*tail = (unsigned long)
+			((void *)cb->first_sdbt) + 1;
+
+allocate_sdbt_exit:
+	mutex_unlock(&hws_sem_oom);
+	return rc;
+
+allocate_sdbt_error:
+	rc = -ENOMEM;
+	goto allocate_sdbt_exit;
+}
+
+/*
+ * deallocate_sdbt() - deallocate all sampler memory
+ *
+ * For each online CPU all SDBT trees are deallocated.
+ * Returns the number of freed pages.
+ */
+static int deallocate_sdbt(void)
+{
+	int cpu;
+	int counter;
+
+	counter = 0;
+
+	for_each_online_cpu(cpu) {
+		unsigned long start;
+		unsigned long sdbt;
+		unsigned long *curr;
+		struct hws_cpu_buffer *cb;
+
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+		if (!cb->first_sdbt)
+			continue;
+
+		sdbt = cb->first_sdbt;
+		curr = (unsigned long *) sdbt;
+		start = sdbt;
+
+		/* we'll free the SDBT after all SDBs are processed... */
+		while (1) {
+			if (!*curr || !sdbt)
+				break;
+
+			/* watch for link entry reset if found */
+			if (is_link_entry(curr)) {
+				curr = get_next_sdbt(curr);
+				if (sdbt)
+					free_page(sdbt);
+
+				/* we are done if we reach the start */
+				if ((unsigned long) curr == start)
+					break;
+				else
+					sdbt = (unsigned long) curr;
+			} else {
+				/* process SDB pointer */
+				if (*curr) {
+					free_page(*curr);
+					curr++;
+				}
+			}
+			counter++;
+		}
+		cb->first_sdbt = 0;
+	}
+	return counter;
+}
+
+static int start_sampling(int cpu)
+{
+	int rc;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	rc = smp_ctl_ssctl_enable_activate(cpu, interval);
+	if (rc) {
+		printk(KERN_INFO "hwsampler: CPU %d ssctl failed.\n", cpu);
+		goto start_exit;
+	}
+
+	rc = -EINVAL;
+	if (!cb->qsi.es) {
+		printk(KERN_INFO "hwsampler: CPU %d ssctl not enabled.\n", cpu);
+		goto start_exit;
+	}
+
+	if (!cb->qsi.cs) {
+		printk(KERN_INFO "hwsampler: CPU %d ssctl not active.\n", cpu);
+		goto start_exit;
+	}
+
+	printk(KERN_INFO
+		"hwsampler: CPU %d, CPUMF Sampling started, interval %lu.\n",
+		cpu, interval);
+
+	rc = 0;
+
+start_exit:
+	return rc;
+}
+
+static int stop_sampling(int cpu)
+{
+	unsigned long v;
+	int rc;
+	struct hws_cpu_buffer *cb;
+
+	rc = smp_ctl_qsi(cpu);
+	WARN_ON(rc);
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	if (!rc && !cb->qsi.es)
+		printk(KERN_INFO "hwsampler: CPU %d, already stopped.\n", cpu);
+
+	rc = smp_ctl_ssctl_stop(cpu);
+	if (rc) {
+		printk(KERN_INFO "hwsampler: CPU %d, ssctl stop error %d.\n",
+				cpu, rc);
+		goto stop_exit;
+	}
+
+	printk(KERN_INFO "hwsampler: CPU %d, CPUMF Sampling stopped.\n", cpu);
+
+stop_exit:
+	v = cb->req_alert;
+	if (v)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF Request alert,"
+				" count=%lu.\n", cpu, v);
+
+	v = cb->loss_of_sample_data;
+	if (v)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF Loss of sample data,"
+				" count=%lu.\n", cpu, v);
+
+	v = cb->invalid_entry_address;
+	if (v)
+		printk(KERN_ERR "hwsampler: CPU %d CPUMF Invalid entry address,"
+				" count=%lu.\n", cpu, v);
+
+	v = cb->incorrect_sdbt_entry;
+	if (v)
+		printk(KERN_ERR
+				"hwsampler: CPU %d CPUMF Incorrect SDBT address,"
+				" count=%lu.\n", cpu, v);
+
+	v = cb->sample_auth_change_alert;
+	if (v)
+		printk(KERN_ERR
+				"hwsampler: CPU %d CPUMF Sample authorization change,"
+				" count=%lu.\n", cpu, v);
+
+	return rc;
+}
+
+static int check_hardware_prerequisites(void)
+{
+	if (!test_facility(68))
+		return -EOPNOTSUPP;
+	return 0;
+}
+/*
+ * hws_oom_callback() - the OOM callback function
+ *
+ * In case the callback is invoked during memory allocation for the
+ *  hw sampler, all obtained memory is deallocated and a flag is set
+ *  so main sampler memory allocation can exit with a failure code.
+ * In case the callback is invoked during sampling the hw sampler
+ *  is deactivated for all CPUs.
+ */
+static int hws_oom_callback(struct notifier_block *nfb,
+	unsigned long dummy, void *parm)
+{
+	unsigned long *freed;
+	int cpu;
+	struct hws_cpu_buffer *cb;
+
+	freed = parm;
+
+	mutex_lock(&hws_sem_oom);
+
+	if (hws_state == HWS_DEALLOCATED) {
+		/* during memory allocation */
+		if (oom_killer_was_active == 0) {
+			oom_killer_was_active = 1;
+			*freed += deallocate_sdbt();
+		}
+	} else {
+		int i;
+		cpu = get_cpu();
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+		if (!cb->oom) {
+			for_each_online_cpu(i) {
+				smp_ctl_ssctl_deactivate(i);
+				cb->oom = 1;
+			}
+			cb->finish = 1;
+
+			printk(KERN_INFO
+				"hwsampler: CPU %d, OOM notify during CPUMF Sampling.\n",
+				cpu);
+		}
+	}
+
+	mutex_unlock(&hws_sem_oom);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block hws_oom_notifier = {
+	.notifier_call = hws_oom_callback
+};
+
+static int hws_cpu_callback(struct notifier_block *nfb,
+	unsigned long action, void *hcpu)
+{
+	/* We do not have sampler space available for all possible CPUs.
+	   All CPUs should be online when hw sampling is activated. */
+	return (hws_state <= HWS_DEALLOCATED) ? NOTIFY_OK : NOTIFY_BAD;
+}
+
+static struct notifier_block hws_cpu_notifier = {
+	.notifier_call = hws_cpu_callback
+};
+
+/**
+ * hwsampler_deactivate() - set hardware sampling temporarily inactive
+ * @cpu:  specifies the CPU to be set inactive.
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_deactivate(unsigned int cpu)
+{
+	/*
+	 * Deactivate hw sampling temporarily and flush the buffer
+	 * by pushing all the pending samples to oprofile buffer.
+	 *
+	 * This function can be called under one of the following conditions:
+	 *     Memory unmap, task is exiting.
+	 */
+	int rc;
+	struct hws_cpu_buffer *cb;
+
+	rc = 0;
+	mutex_lock(&hws_sem);
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	if (hws_state == HWS_STARTED) {
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+		if (cb->qsi.cs) {
+			rc = smp_ctl_ssctl_deactivate(cpu);
+			if (rc) {
+				printk(KERN_INFO
+				"hwsampler: CPU %d, CPUMF Deactivation failed.\n", cpu);
+				cb->finish = 1;
+				hws_state = HWS_STOPPING;
+			} else  {
+				hws_flush_all = 1;
+				/* Add work to queue to read pending samples.*/
+				queue_work_on(cpu, hws_wq, &cb->worker);
+			}
+		}
+	}
+	mutex_unlock(&hws_sem);
+
+	if (hws_wq)
+		flush_workqueue(hws_wq);
+
+	return rc;
+}
+
+/**
+ * hwsampler_activate() - activate/resume hardware sampling which was deactivated
+ * @cpu:  specifies the CPU to be set active.
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_activate(unsigned int cpu)
+{
+	/*
+	 * Re-activate hw sampling. This should be called in pair with
+	 * hwsampler_deactivate().
+	 */
+	int rc;
+	struct hws_cpu_buffer *cb;
+
+	rc = 0;
+	mutex_lock(&hws_sem);
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	if (hws_state == HWS_STARTED) {
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+		if (!cb->qsi.cs) {
+			hws_flush_all = 0;
+			rc = smp_ctl_ssctl_enable_activate(cpu, interval);
+			if (rc) {
+				printk(KERN_ERR
+				"CPU %d, CPUMF activate sampling failed.\n",
+					 cpu);
+			}
+		}
+	}
+
+	mutex_unlock(&hws_sem);
+
+	return rc;
+}
+
+static int check_qsi_on_setup(void)
+{
+	int rc;
+	unsigned int cpu;
+	struct hws_cpu_buffer *cb;
+
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+		if (rc)
+			return -EOPNOTSUPP;
+
+		if (!cb->qsi.as) {
+			printk(KERN_INFO "hwsampler: CPUMF sampling is not authorized.\n");
+			return -EINVAL;
+		}
+
+		if (cb->qsi.es) {
+			printk(KERN_WARNING "hwsampler: CPUMF is still enabled.\n");
+			rc = smp_ctl_ssctl_stop(cpu);
+			if (rc)
+				return -EINVAL;
+
+			printk(KERN_INFO
+				"CPU %d, CPUMF Sampling stopped now.\n", cpu);
+		}
+	}
+	return 0;
+}
+
+static int check_qsi_on_start(void)
+{
+	unsigned int cpu;
+	int rc;
+	struct hws_cpu_buffer *cb;
+
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+
+		if (!cb->qsi.as)
+			return -EINVAL;
+
+		if (cb->qsi.es)
+			return -EINVAL;
+
+		if (cb->qsi.cs)
+			return -EINVAL;
+	}
+	return 0;
+}
+
+static void worker_on_start(unsigned int cpu)
+{
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	cb->worker_entry = cb->first_sdbt;
+}
+
+static int worker_check_error(unsigned int cpu, int ext_params)
+{
+	int rc;
+	unsigned long *sdbt;
+	struct hws_cpu_buffer *cb;
+
+	rc = 0;
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+	sdbt = (unsigned long *) cb->worker_entry;
+
+	if (!sdbt || !*sdbt)
+		return -EINVAL;
+
+	if (ext_params & CPU_MF_INT_SF_PRA)
+		cb->req_alert++;
+
+	if (ext_params & CPU_MF_INT_SF_LSDA)
+		cb->loss_of_sample_data++;
+
+	if (ext_params & CPU_MF_INT_SF_IAE) {
+		cb->invalid_entry_address++;
+		rc = -EINVAL;
+	}
+
+	if (ext_params & CPU_MF_INT_SF_ISE) {
+		cb->incorrect_sdbt_entry++;
+		rc = -EINVAL;
+	}
+
+	if (ext_params & CPU_MF_INT_SF_SACA) {
+		cb->sample_auth_change_alert++;
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+static void worker_on_finish(unsigned int cpu)
+{
+	int rc, i;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	if (cb->finish) {
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+		if (cb->qsi.es) {
+			printk(KERN_INFO
+				"hwsampler: CPU %d, CPUMF Stop/Deactivate sampling.\n",
+				cpu);
+			rc = smp_ctl_ssctl_stop(cpu);
+			if (rc)
+				printk(KERN_INFO
+					"hwsampler: CPU %d, CPUMF Deactivation failed.\n",
+					cpu);
+
+			for_each_online_cpu(i) {
+				if (i == cpu)
+					continue;
+				if (!cb->finish) {
+					cb->finish = 1;
+					queue_work_on(i, hws_wq,
+						&cb->worker);
+				}
+			}
+		}
+	}
+}
+
+static void worker_on_interrupt(unsigned int cpu)
+{
+	unsigned long *sdbt;
+	unsigned char done;
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	sdbt = (unsigned long *) cb->worker_entry;
+
+	done = 0;
+	/* do not proceed if stop was entered,
+	 * forget the buffers not yet processed */
+	while (!done && !cb->stop_mode) {
+		unsigned long *trailer;
+		struct hws_trailer_entry *te;
+		unsigned long *dear = 0;
+
+		trailer = trailer_entry_ptr(*sdbt);
+		/* leave loop if no more work to do */
+		if (!(*trailer & SDB_TE_BUFFER_FULL_MASK)) {
+			done = 1;
+			if (!hws_flush_all)
+				continue;
+		}
+
+		te = (struct hws_trailer_entry *)trailer;
+		cb->sample_overflow += te->overflow;
+
+		add_samples_to_oprofile(cpu, sdbt, dear);
+
+		/* reset trailer */
+		xchg((unsigned char *) te, 0x40);
+
+		/* advance to next sdb slot in current sdbt */
+		sdbt++;
+		/* in case link bit is set use address w/o link bit */
+		if (is_link_entry(sdbt))
+			sdbt = get_next_sdbt(sdbt);
+
+		cb->worker_entry = (unsigned long)sdbt;
+	}
+}
+
+static void add_samples_to_oprofile(unsigned int cpu, unsigned long *sdbt,
+		unsigned long *dear)
+{
+	struct hws_basic_entry *sample_data_ptr;
+	unsigned long *trailer;
+
+	trailer = trailer_entry_ptr(*sdbt);
+	if (dear) {
+		if (dear > trailer)
+			return;
+		trailer = dear;
+	}
+
+	sample_data_ptr = (struct hws_basic_entry *)(*sdbt);
+
+	while ((unsigned long *)sample_data_ptr < trailer) {
+		struct pt_regs *regs = NULL;
+		struct task_struct *tsk = NULL;
+
+		/*
+		 * Check sampling mode, 1 indicates basic (=customer) sampling
+		 * mode.
+		 */
+		if (sample_data_ptr->def != 1) {
+			/* sample slot is not yet written */
+			break;
+		} else {
+			/* make sure we don't use it twice,
+			 * the next time the sampler will set it again */
+			sample_data_ptr->def = 0;
+		}
+
+		/* Get pt_regs. */
+		if (sample_data_ptr->P == 1) {
+			/* userspace sample */
+			unsigned int pid = sample_data_ptr->prim_asn;
+			if (!counter_config.user)
+				goto skip_sample;
+			rcu_read_lock();
+			tsk = pid_task(find_vpid(pid), PIDTYPE_PID);
+			if (tsk)
+				regs = task_pt_regs(tsk);
+			rcu_read_unlock();
+		} else {
+			/* kernelspace sample */
+			if (!counter_config.kernel)
+				goto skip_sample;
+			regs = task_pt_regs(current);
+		}
+
+		mutex_lock(&hws_sem);
+		oprofile_add_ext_hw_sample(sample_data_ptr->ia, regs, 0,
+				!sample_data_ptr->P, tsk);
+		mutex_unlock(&hws_sem);
+	skip_sample:
+		sample_data_ptr++;
+	}
+}
+
+static void worker(struct work_struct *work)
+{
+	unsigned int cpu;
+	int ext_params;
+	struct hws_cpu_buffer *cb;
+
+	cb = container_of(work, struct hws_cpu_buffer, worker);
+	cpu = smp_processor_id();
+	ext_params = atomic_xchg(&cb->ext_params, 0);
+
+	if (!cb->worker_entry)
+		worker_on_start(cpu);
+
+	if (worker_check_error(cpu, ext_params))
+		return;
+
+	if (!cb->finish)
+		worker_on_interrupt(cpu);
+
+	if (cb->finish)
+		worker_on_finish(cpu);
+}
+
+/**
+ * hwsampler_allocate() - allocate memory for the hardware sampler
+ * @sdbt:  number of SDBTs per online CPU (must be > 0)
+ * @sdb:   number of SDBs per SDBT (minimum 1, maximum 511)
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_allocate(unsigned long sdbt, unsigned long sdb)
+{
+	int cpu, rc;
+	mutex_lock(&hws_sem);
+
+	rc = -EINVAL;
+	if (hws_state != HWS_DEALLOCATED)
+		goto allocate_exit;
+
+	if (sdbt < 1)
+		goto allocate_exit;
+
+	if (sdb > MAX_NUM_SDB || sdb < MIN_NUM_SDB)
+		goto allocate_exit;
+
+	num_sdbt = sdbt;
+	num_sdb = sdb;
+
+	oom_killer_was_active = 0;
+	register_oom_notifier(&hws_oom_notifier);
+
+	for_each_online_cpu(cpu) {
+		if (allocate_sdbt(cpu)) {
+			unregister_oom_notifier(&hws_oom_notifier);
+			goto allocate_error;
+		}
+	}
+	unregister_oom_notifier(&hws_oom_notifier);
+	if (oom_killer_was_active)
+		goto allocate_error;
+
+	hws_state = HWS_STOPPED;
+	rc = 0;
+
+allocate_exit:
+	mutex_unlock(&hws_sem);
+	return rc;
+
+allocate_error:
+	rc = -ENOMEM;
+	printk(KERN_ERR "hwsampler: CPUMF Memory allocation failed.\n");
+	goto allocate_exit;
+}
+
+/**
+ * hwsampler_deallocate() - deallocate hardware sampler memory
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_deallocate(void)
+{
+	int rc;
+
+	mutex_lock(&hws_sem);
+
+	rc = -EINVAL;
+	if (hws_state != HWS_STOPPED)
+		goto deallocate_exit;
+
+	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+	hws_alert = 0;
+	deallocate_sdbt();
+
+	hws_state = HWS_DEALLOCATED;
+	rc = 0;
+
+deallocate_exit:
+	mutex_unlock(&hws_sem);
+
+	return rc;
+}
+
+unsigned long hwsampler_query_min_interval(void)
+{
+	return min_sampler_rate;
+}
+
+unsigned long hwsampler_query_max_interval(void)
+{
+	return max_sampler_rate;
+}
+
+unsigned long hwsampler_get_sample_overflow_count(unsigned int cpu)
+{
+	struct hws_cpu_buffer *cb;
+
+	cb = &per_cpu(sampler_cpu_buffer, cpu);
+
+	return cb->sample_overflow;
+}
+
+int hwsampler_setup(void)
+{
+	int rc;
+	int cpu;
+	struct hws_cpu_buffer *cb;
+
+	mutex_lock(&hws_sem);
+
+	rc = -EINVAL;
+	if (hws_state)
+		goto setup_exit;
+
+	hws_state = HWS_INIT;
+
+	init_all_cpu_buffers();
+
+	rc = check_hardware_prerequisites();
+	if (rc)
+		goto setup_exit;
+
+	rc = check_qsi_on_setup();
+	if (rc)
+		goto setup_exit;
+
+	rc = -EINVAL;
+	hws_wq = create_workqueue("hwsampler");
+	if (!hws_wq)
+		goto setup_exit;
+
+	register_cpu_notifier(&hws_cpu_notifier);
+
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		INIT_WORK(&cb->worker, worker);
+		rc = smp_ctl_qsi(cpu);
+		WARN_ON(rc);
+		if (min_sampler_rate != cb->qsi.min_sampl_rate) {
+			if (min_sampler_rate) {
+				printk(KERN_WARNING
+					"hwsampler: different min sampler rate values.\n");
+				if (min_sampler_rate < cb->qsi.min_sampl_rate)
+					min_sampler_rate =
+						cb->qsi.min_sampl_rate;
+			} else
+				min_sampler_rate = cb->qsi.min_sampl_rate;
+		}
+		if (max_sampler_rate != cb->qsi.max_sampl_rate) {
+			if (max_sampler_rate) {
+				printk(KERN_WARNING
+					"hwsampler: different max sampler rate values.\n");
+				if (max_sampler_rate > cb->qsi.max_sampl_rate)
+					max_sampler_rate =
+						cb->qsi.max_sampl_rate;
+			} else
+				max_sampler_rate = cb->qsi.max_sampl_rate;
+		}
+	}
+	register_external_irq(EXT_IRQ_MEASURE_ALERT, hws_ext_handler);
+
+	hws_state = HWS_DEALLOCATED;
+	rc = 0;
+
+setup_exit:
+	mutex_unlock(&hws_sem);
+	return rc;
+}
+
+int hwsampler_shutdown(void)
+{
+	int rc;
+
+	mutex_lock(&hws_sem);
+
+	rc = -EINVAL;
+	if (hws_state == HWS_DEALLOCATED || hws_state == HWS_STOPPED) {
+		mutex_unlock(&hws_sem);
+
+		if (hws_wq)
+			flush_workqueue(hws_wq);
+
+		mutex_lock(&hws_sem);
+
+		if (hws_state == HWS_STOPPED) {
+			irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+			hws_alert = 0;
+			deallocate_sdbt();
+		}
+		if (hws_wq) {
+			destroy_workqueue(hws_wq);
+			hws_wq = NULL;
+		}
+
+		unregister_external_irq(EXT_IRQ_MEASURE_ALERT, hws_ext_handler);
+		hws_state = HWS_INIT;
+		rc = 0;
+	}
+	mutex_unlock(&hws_sem);
+
+	unregister_cpu_notifier(&hws_cpu_notifier);
+
+	return rc;
+}
+
+/**
+ * hwsampler_start_all() - start hardware sampling on all online CPUs
+ * @rate:  specifies the used interval when samples are taken
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_start_all(unsigned long rate)
+{
+	int rc, cpu;
+
+	mutex_lock(&hws_sem);
+
+	hws_oom = 0;
+
+	rc = -EINVAL;
+	if (hws_state != HWS_STOPPED)
+		goto start_all_exit;
+
+	interval = rate;
+
+	/* fail if rate is not valid */
+	if (interval < min_sampler_rate || interval > max_sampler_rate)
+		goto start_all_exit;
+
+	rc = check_qsi_on_start();
+	if (rc)
+		goto start_all_exit;
+
+	prepare_cpu_buffers();
+
+	for_each_online_cpu(cpu) {
+		rc = start_sampling(cpu);
+		if (rc)
+			break;
+	}
+	if (rc) {
+		for_each_online_cpu(cpu) {
+			stop_sampling(cpu);
+		}
+		goto start_all_exit;
+	}
+	hws_state = HWS_STARTED;
+	rc = 0;
+
+start_all_exit:
+	mutex_unlock(&hws_sem);
+
+	if (rc)
+		return rc;
+
+	register_oom_notifier(&hws_oom_notifier);
+	hws_oom = 1;
+	hws_flush_all = 0;
+	/* now let them in, 1407 CPUMF external interrupts */
+	hws_alert = 1;
+	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+
+	return 0;
+}
+
+/**
+ * hwsampler_stop_all() - stop hardware sampling on all online CPUs
+ *
+ * Returns 0 on success, !0 on failure.
+ */
+int hwsampler_stop_all(void)
+{
+	int tmp_rc, rc, cpu;
+	struct hws_cpu_buffer *cb;
+
+	mutex_lock(&hws_sem);
+
+	rc = 0;
+	if (hws_state == HWS_INIT) {
+		mutex_unlock(&hws_sem);
+		return 0;
+	}
+	hws_state = HWS_STOPPING;
+	mutex_unlock(&hws_sem);
+
+	for_each_online_cpu(cpu) {
+		cb = &per_cpu(sampler_cpu_buffer, cpu);
+		cb->stop_mode = 1;
+		tmp_rc = stop_sampling(cpu);
+		if (tmp_rc)
+			rc = tmp_rc;
+	}
+
+	if (hws_wq)
+		flush_workqueue(hws_wq);
+
+	mutex_lock(&hws_sem);
+	if (hws_oom) {
+		unregister_oom_notifier(&hws_oom_notifier);
+		hws_oom = 0;
+	}
+	hws_state = HWS_STOPPED;
+	mutex_unlock(&hws_sem);
+
+	return rc;
+}
diff --git a/arch/s390/oprofile/hwsampler.h b/arch/s390/oprofile/hwsampler.h
new file mode 100644
index 000000000..a483d06f2
--- /dev/null
+++ b/arch/s390/oprofile/hwsampler.h
@@ -0,0 +1,63 @@
+/*
+ * CPUMF HW sampler functions and internal structures
+ *
+ *    Copyright IBM Corp. 2010
+ *    Author(s): Heinz Graalfs <graalfs@de.ibm.com>
+ */
+
+#ifndef HWSAMPLER_H_
+#define HWSAMPLER_H_
+
+#include <linux/workqueue.h>
+#include <asm/cpu_mf.h>
+
+struct hws_ssctl_request_block     /* SET SAMPLING CONTROLS req block   */
+{ /* bytes 0 - 7  Bit(s) */
+	unsigned int s:1;           /* 0: maximum buffer indicator       */
+	unsigned int h:1;           /* 1: part. level reserved for VM use*/
+	unsigned long b2_53:52;     /* 2-53: zeros                       */
+	unsigned int es:1;          /* 54: sampling enable control       */
+	unsigned int b55_61:7;      /* 55-61: - zeros                    */
+	unsigned int cs:1;          /* 62: sampling activation control   */
+	unsigned int b63:1;         /* 63: zero                          */
+	unsigned long interval;     /* 8-15: sampling interval           */
+	unsigned long tear;         /* 16-23: TEAR contents              */
+	unsigned long dear;         /* 24-31: DEAR contents              */
+	/* 32-63:                                                        */
+	unsigned long rsvrd1;       /* reserved                          */
+	unsigned long rsvrd2;       /* reserved                          */
+	unsigned long rsvrd3;       /* reserved                          */
+	unsigned long rsvrd4;       /* reserved                          */
+};
+
+struct hws_cpu_buffer {
+	unsigned long first_sdbt;       /* @ of 1st SDB-Table for this CP*/
+	unsigned long worker_entry;
+	unsigned long sample_overflow;  /* taken from SDB ...            */
+	struct hws_qsi_info_block qsi;
+	struct hws_ssctl_request_block ssctl;
+	struct work_struct worker;
+	atomic_t ext_params;
+	unsigned long req_alert;
+	unsigned long loss_of_sample_data;
+	unsigned long invalid_entry_address;
+	unsigned long incorrect_sdbt_entry;
+	unsigned long sample_auth_change_alert;
+	unsigned int finish:1;
+	unsigned int oom:1;
+	unsigned int stop_mode:1;
+};
+
+int hwsampler_setup(void);
+int hwsampler_shutdown(void);
+int hwsampler_allocate(unsigned long sdbt, unsigned long sdb);
+int hwsampler_deallocate(void);
+unsigned long hwsampler_query_min_interval(void);
+unsigned long hwsampler_query_max_interval(void);
+int hwsampler_start_all(unsigned long interval);
+int hwsampler_stop_all(void);
+int hwsampler_deactivate(unsigned int cpu);
+int hwsampler_activate(unsigned int cpu);
+unsigned long hwsampler_get_sample_overflow_count(unsigned int cpu);
+
+#endif /*HWSAMPLER_H_*/
diff --git a/arch/s390/oprofile/init.c b/arch/s390/oprofile/init.c
new file mode 100644
index 000000000..bc927a09a
--- /dev/null
+++ b/arch/s390/oprofile/init.c
@@ -0,0 +1,513 @@
+/*
+ * S390 Version
+ *   Copyright IBM Corp. 2002, 2011
+ *   Author(s): Thomas Spatzier (tspat@de.ibm.com)
+ *   Author(s): Mahesh Salgaonkar (mahesh@linux.vnet.ibm.com)
+ *   Author(s): Heinz Graalfs (graalfs@linux.vnet.ibm.com)
+ *   Author(s): Andreas Krebbel (krebbel@linux.vnet.ibm.com)
+ *
+ * @remark Copyright 2002-2011 OProfile authors
+ */
+
+#include <linux/oprofile.h>
+#include <linux/perf_event.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <asm/processor.h>
+
+#include "../../../drivers/oprofile/oprof.h"
+
+extern void s390_backtrace(struct pt_regs * const regs, unsigned int depth);
+
+#include "hwsampler.h"
+#include "op_counter.h"
+
+#define DEFAULT_INTERVAL	4127518
+
+#define DEFAULT_SDBT_BLOCKS	1
+#define DEFAULT_SDB_BLOCKS	511
+
+static unsigned long oprofile_hw_interval = DEFAULT_INTERVAL;
+static unsigned long oprofile_min_interval;
+static unsigned long oprofile_max_interval;
+
+static unsigned long oprofile_sdbt_blocks = DEFAULT_SDBT_BLOCKS;
+static unsigned long oprofile_sdb_blocks = DEFAULT_SDB_BLOCKS;
+
+static int hwsampler_enabled;
+static int hwsampler_running;	/* start_mutex must be held to change */
+static int hwsampler_available;
+
+static struct oprofile_operations timer_ops;
+
+struct op_counter_config counter_config;
+
+enum __force_cpu_type {
+	reserved = 0,		/* do not force */
+	timer,
+};
+static int force_cpu_type;
+
+static int set_cpu_type(const char *str, struct kernel_param *kp)
+{
+	if (!strcmp(str, "timer")) {
+		force_cpu_type = timer;
+		printk(KERN_INFO "oprofile: forcing timer to be returned "
+		                 "as cpu type\n");
+	} else {
+		force_cpu_type = 0;
+	}
+
+	return 0;
+}
+module_param_call(cpu_type, set_cpu_type, NULL, NULL, 0);
+MODULE_PARM_DESC(cpu_type, "Force legacy basic mode sampling"
+		           "(report cpu_type \"timer\"");
+
+static int __oprofile_hwsampler_start(void)
+{
+	int retval;
+
+	retval = hwsampler_allocate(oprofile_sdbt_blocks, oprofile_sdb_blocks);
+	if (retval)
+		return retval;
+
+	retval = hwsampler_start_all(oprofile_hw_interval);
+	if (retval)
+		hwsampler_deallocate();
+
+	return retval;
+}
+
+static int oprofile_hwsampler_start(void)
+{
+	int retval;
+
+	hwsampler_running = hwsampler_enabled;
+
+	if (!hwsampler_running)
+		return timer_ops.start();
+
+	retval = perf_reserve_sampling();
+	if (retval)
+		return retval;
+
+	retval = __oprofile_hwsampler_start();
+	if (retval)
+		perf_release_sampling();
+
+	return retval;
+}
+
+static void oprofile_hwsampler_stop(void)
+{
+	if (!hwsampler_running) {
+		timer_ops.stop();
+		return;
+	}
+
+	hwsampler_stop_all();
+	hwsampler_deallocate();
+	perf_release_sampling();
+	return;
+}
+
+/*
+ * File ops used for:
+ * /dev/oprofile/0/enabled
+ * /dev/oprofile/hwsampling/hwsampler  (cpu_type = timer)
+ */
+
+static ssize_t hwsampler_read(struct file *file, char __user *buf,
+		size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(hwsampler_enabled, buf, count, offset);
+}
+
+static ssize_t hwsampler_write(struct file *file, char const __user *buf,
+		size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval <= 0)
+		return retval;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	if (oprofile_started)
+		/*
+		 * save to do without locking as we set
+		 * hwsampler_running in start() when start_mutex is
+		 * held
+		 */
+		return -EBUSY;
+
+	hwsampler_enabled = val;
+
+	return count;
+}
+
+static const struct file_operations hwsampler_fops = {
+	.read		= hwsampler_read,
+	.write		= hwsampler_write,
+};
+
+/*
+ * File ops used for:
+ * /dev/oprofile/0/count
+ * /dev/oprofile/hwsampling/hw_interval  (cpu_type = timer)
+ *
+ * Make sure that the value is within the hardware range.
+ */
+
+static ssize_t hw_interval_read(struct file *file, char __user *buf,
+				size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(oprofile_hw_interval, buf,
+					count, offset);
+}
+
+static ssize_t hw_interval_write(struct file *file, char const __user *buf,
+				 size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval <= 0)
+		return retval;
+	if (val < oprofile_min_interval)
+		oprofile_hw_interval = oprofile_min_interval;
+	else if (val > oprofile_max_interval)
+		oprofile_hw_interval = oprofile_max_interval;
+	else
+		oprofile_hw_interval = val;
+
+	return count;
+}
+
+static const struct file_operations hw_interval_fops = {
+	.read		= hw_interval_read,
+	.write		= hw_interval_write,
+};
+
+/*
+ * File ops used for:
+ * /dev/oprofile/0/event
+ * Only a single event with number 0 is supported with this counter.
+ *
+ * /dev/oprofile/0/unit_mask
+ * This is a dummy file needed by the user space tools.
+ * No value other than 0 is accepted or returned.
+ */
+
+static ssize_t hwsampler_zero_read(struct file *file, char __user *buf,
+				    size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(0, buf, count, offset);
+}
+
+static ssize_t hwsampler_zero_write(struct file *file, char const __user *buf,
+				     size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval <= 0)
+		return retval;
+	if (val != 0)
+		return -EINVAL;
+	return count;
+}
+
+static const struct file_operations zero_fops = {
+	.read		= hwsampler_zero_read,
+	.write		= hwsampler_zero_write,
+};
+
+/* /dev/oprofile/0/kernel file ops.  */
+
+static ssize_t hwsampler_kernel_read(struct file *file, char __user *buf,
+				     size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(counter_config.kernel,
+					buf, count, offset);
+}
+
+static ssize_t hwsampler_kernel_write(struct file *file, char const __user *buf,
+				      size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval <= 0)
+		return retval;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	counter_config.kernel = val;
+
+	return count;
+}
+
+static const struct file_operations kernel_fops = {
+	.read		= hwsampler_kernel_read,
+	.write		= hwsampler_kernel_write,
+};
+
+/* /dev/oprofile/0/user file ops. */
+
+static ssize_t hwsampler_user_read(struct file *file, char __user *buf,
+				   size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(counter_config.user,
+					buf, count, offset);
+}
+
+static ssize_t hwsampler_user_write(struct file *file, char const __user *buf,
+				    size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval <= 0)
+		return retval;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	counter_config.user = val;
+
+	return count;
+}
+
+static const struct file_operations user_fops = {
+	.read		= hwsampler_user_read,
+	.write		= hwsampler_user_write,
+};
+
+
+/*
+ * File ops used for: /dev/oprofile/timer/enabled
+ * The value always has to be the inverted value of hwsampler_enabled. So
+ * no separate variable is created. That way we do not need locking.
+ */
+
+static ssize_t timer_enabled_read(struct file *file, char __user *buf,
+				  size_t count, loff_t *offset)
+{
+	return oprofilefs_ulong_to_user(!hwsampler_enabled, buf, count, offset);
+}
+
+static ssize_t timer_enabled_write(struct file *file, char const __user *buf,
+				   size_t count, loff_t *offset)
+{
+	unsigned long val;
+	int retval;
+
+	if (*offset)
+		return -EINVAL;
+
+	retval = oprofilefs_ulong_from_user(&val, buf, count);
+	if (retval <= 0)
+		return retval;
+
+	if (val != 0 && val != 1)
+		return -EINVAL;
+
+	/* Timer cannot be disabled without having hardware sampling.  */
+	if (val == 0 && !hwsampler_available)
+		return -EINVAL;
+
+	if (oprofile_started)
+		/*
+		 * save to do without locking as we set
+		 * hwsampler_running in start() when start_mutex is
+		 * held
+		 */
+		return -EBUSY;
+
+	hwsampler_enabled = !val;
+
+	return count;
+}
+
+static const struct file_operations timer_enabled_fops = {
+	.read		= timer_enabled_read,
+	.write		= timer_enabled_write,
+};
+
+
+static int oprofile_create_hwsampling_files(struct dentry *root)
+{
+	struct dentry *dir;
+
+	dir = oprofilefs_mkdir(root, "timer");
+	if (!dir)
+		return -EINVAL;
+
+	oprofilefs_create_file(dir, "enabled", &timer_enabled_fops);
+
+	if (!hwsampler_available)
+		return 0;
+
+	/* reinitialize default values */
+	hwsampler_enabled = 1;
+	counter_config.kernel = 1;
+	counter_config.user = 1;
+
+	if (!force_cpu_type) {
+		/*
+		 * Create the counter file system.  A single virtual
+		 * counter is created which can be used to
+		 * enable/disable hardware sampling dynamically from
+		 * user space.  The user space will configure a single
+		 * counter with a single event.  The value of 'event'
+		 * and 'unit_mask' are not evaluated by the kernel code
+		 * and can only be set to 0.
+		 */
+
+		dir = oprofilefs_mkdir(root, "0");
+		if (!dir)
+			return -EINVAL;
+
+		oprofilefs_create_file(dir, "enabled", &hwsampler_fops);
+		oprofilefs_create_file(dir, "event", &zero_fops);
+		oprofilefs_create_file(dir, "count", &hw_interval_fops);
+		oprofilefs_create_file(dir, "unit_mask", &zero_fops);
+		oprofilefs_create_file(dir, "kernel", &kernel_fops);
+		oprofilefs_create_file(dir, "user", &user_fops);
+		oprofilefs_create_ulong(dir, "hw_sdbt_blocks",
+					&oprofile_sdbt_blocks);
+
+	} else {
+		/*
+		 * Hardware sampling can be used but the cpu_type is
+		 * forced to timer in order to deal with legacy user
+		 * space tools.  The /dev/oprofile/hwsampling fs is
+		 * provided in that case.
+		 */
+		dir = oprofilefs_mkdir(root, "hwsampling");
+		if (!dir)
+			return -EINVAL;
+
+		oprofilefs_create_file(dir, "hwsampler",
+				       &hwsampler_fops);
+		oprofilefs_create_file(dir, "hw_interval",
+				       &hw_interval_fops);
+		oprofilefs_create_ro_ulong(dir, "hw_min_interval",
+					   &oprofile_min_interval);
+		oprofilefs_create_ro_ulong(dir, "hw_max_interval",
+					   &oprofile_max_interval);
+		oprofilefs_create_ulong(dir, "hw_sdbt_blocks",
+					&oprofile_sdbt_blocks);
+	}
+	return 0;
+}
+
+static int oprofile_hwsampler_init(struct oprofile_operations *ops)
+{
+	/*
+	 * Initialize the timer mode infrastructure as well in order
+	 * to be able to switch back dynamically.  oprofile_timer_init
+	 * is not supposed to fail.
+	 */
+	if (oprofile_timer_init(ops))
+		BUG();
+
+	memcpy(&timer_ops, ops, sizeof(timer_ops));
+	ops->create_files = oprofile_create_hwsampling_files;
+
+	/*
+	 * If the user space tools do not support newer cpu types,
+	 * the force_cpu_type module parameter
+	 * can be used to always return \"timer\" as cpu type.
+	 */
+	if (force_cpu_type != timer) {
+		struct cpuid id;
+
+		get_cpu_id (&id);
+
+		switch (id.machine) {
+		case 0x2097: case 0x2098: ops->cpu_type = "s390/z10"; break;
+		case 0x2817: case 0x2818: ops->cpu_type = "s390/z196"; break;
+		case 0x2827: case 0x2828: ops->cpu_type = "s390/zEC12"; break;
+		default: return -ENODEV;
+		}
+	}
+
+	if (hwsampler_setup())
+		return -ENODEV;
+
+	/*
+	 * Query the range for the sampling interval from the
+	 * hardware.
+	 */
+	oprofile_min_interval = hwsampler_query_min_interval();
+	if (oprofile_min_interval == 0)
+		return -ENODEV;
+	oprofile_max_interval = hwsampler_query_max_interval();
+	if (oprofile_max_interval == 0)
+		return -ENODEV;
+
+	/* The initial value should be sane */
+	if (oprofile_hw_interval < oprofile_min_interval)
+		oprofile_hw_interval = oprofile_min_interval;
+	if (oprofile_hw_interval > oprofile_max_interval)
+		oprofile_hw_interval = oprofile_max_interval;
+
+	printk(KERN_INFO "oprofile: System z hardware sampling "
+	       "facility found.\n");
+
+	ops->start = oprofile_hwsampler_start;
+	ops->stop = oprofile_hwsampler_stop;
+
+	return 0;
+}
+
+static void oprofile_hwsampler_exit(void)
+{
+	hwsampler_shutdown();
+}
+
+int __init oprofile_arch_init(struct oprofile_operations *ops)
+{
+	ops->backtrace = s390_backtrace;
+
+	/*
+	 * -ENODEV is not reported to the caller.  The module itself
+         * will use the timer mode sampling as fallback and this is
+         * always available.
+	 */
+	hwsampler_available = oprofile_hwsampler_init(ops) == 0;
+
+	return 0;
+}
+
+void oprofile_arch_exit(void)
+{
+	oprofile_hwsampler_exit();
+}
diff --git a/arch/s390/oprofile/op_counter.h b/arch/s390/oprofile/op_counter.h
new file mode 100644
index 000000000..61b2531ee
--- /dev/null
+++ b/arch/s390/oprofile/op_counter.h
@@ -0,0 +1,21 @@
+/*
+ *   Copyright IBM Corp. 2011
+ *   Author(s): Andreas Krebbel (krebbel@linux.vnet.ibm.com)
+ *
+ * @remark Copyright 2011 OProfile authors
+ */
+
+#ifndef OP_COUNTER_H
+#define OP_COUNTER_H
+
+struct op_counter_config {
+	/* `enabled' maps to the hwsampler_file variable.  */
+	/* `count' maps to the oprofile_hw_interval variable.  */
+	/* `event' and `unit_mask' are unused. */
+	unsigned long kernel;
+	unsigned long user;
+};
+
+extern struct op_counter_config counter_config;
+
+#endif /* OP_COUNTER_H */