s390/perf,oprofile: Share sampling facility

Introduce reserve/release functions to share the sampling facility
between perf and oprofile.
Also improve error handling for the sampling facility support in perf.

Signed-off-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

arch/s390/include/asm/perf_event.h

@@ -52,5 +52,9 @@ extern unsigned long perf_misc_flags(struct pt_regs *regs);
 #define TEAR_REG(hwc)		((hwc)->last_tag)
 #define SAMPL_RATE(hwc)		((hwc)->event_base)
 
+/* Perf hardware reserve and release functions */
+int perf_reserve_sampling(void);
+void perf_release_sampling(void);
+
 #endif /* CONFIG_64BIT */
 #endif /* _ASM_S390_PERF_EVENT_H */

arch/s390/kernel/perf_cpum_sf.c

@@ -260,16 +260,12 @@ static int sf_disable(void)
 
 #define PMC_INIT      0
 #define PMC_RELEASE   1
+#define PMC_FAILURE   2
 static void setup_pmc_cpu(void *flags)
 {
 	int err;
 	struct cpu_hw_sf *cpusf = &__get_cpu_var(cpu_hw_sf);
 
-	/* XXX Improve error handling and pass a flag in the *flags
-	 *     variable to indicate failures.  Alternatively, ignore
-	 *     (print) errors here and let the PMU functions fail if
-	 *     the per-cpu PMU_F_RESERVED flag is not.
-	 */
 	err = 0;
 	switch (*((int *) flags)) {
 	case PMC_INIT:
@@ -299,6 +295,8 @@ static void setup_pmc_cpu(void *flags)
 				    "setup_pmc_cpu: released: cpuhw=%p\n", cpusf);
 		break;
 	}
+	if (err)
+		*((int *) flags) |= PMC_FAILURE;
 }
 
 static void release_pmc_hardware(void)
@@ -307,13 +305,22 @@ static void release_pmc_hardware(void)
 
 	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 	on_each_cpu(setup_pmc_cpu, &flags, 1);
+	perf_release_sampling();
 }
 
 static int reserve_pmc_hardware(void)
 {
 	int flags = PMC_INIT;
+	int err;
 
+	err = perf_reserve_sampling();
+	if (err)
+		return err;
 	on_each_cpu(setup_pmc_cpu, &flags, 1);
+	if (flags & PMC_FAILURE) {
+		release_pmc_hardware();
+		return -ENODEV;
+	}
 	irq_subclass_register(IRQ_SUBCLASS_MEASUREMENT_ALERT);
 
 	return 0;

arch/s390/kernel/perf_event.c

@@ -208,3 +208,33 @@ ssize_t cpumf_events_sysfs_show(struct device *dev,
 	return sprintf(page, "event=0x%04llx,name=%s\n",
 		       pmu_attr->id, attr->attr.name);
 }
+
+/* Reserve/release functions for sharing perf hardware */
+static DEFINE_SPINLOCK(perf_hw_owner_lock);
+static void *perf_sampling_owner;
+
+int perf_reserve_sampling(void)
+{
+	int err;
+
+	err = 0;
+	spin_lock(&perf_hw_owner_lock);
+	if (perf_sampling_owner) {
+		pr_warn("The sampling facility is already reserved by %p\n",
+			perf_sampling_owner);
+		err = -EBUSY;
+	} else
+		perf_sampling_owner = __builtin_return_address(0);
+	spin_unlock(&perf_hw_owner_lock);
+	return err;
+}
+EXPORT_SYMBOL(perf_reserve_sampling);
+
+void perf_release_sampling(void)
+{
+	spin_lock(&perf_hw_owner_lock);
+	WARN_ON(!perf_sampling_owner);
+	perf_sampling_owner = NULL;
+	spin_unlock(&perf_hw_owner_lock);
+}
+EXPORT_SYMBOL(perf_release_sampling);

arch/s390/oprofile/hwsampler.c

@@ -41,6 +41,7 @@ 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;
@@ -182,6 +183,9 @@ static void hws_ext_handler(struct ext_code ext_code,
 	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);
 
@@ -941,6 +945,7 @@ int hwsampler_deallocate(void)
 		goto deallocate_exit;
 
 	irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+	hws_alert = 0;
 	deallocate_sdbt();
 
 	hws_state = HWS_DEALLOCATED;
@@ -1055,6 +1060,7 @@ int hwsampler_shutdown(void)
 
 		if (hws_state == HWS_STOPPED) {
 			irq_subclass_unregister(IRQ_SUBCLASS_MEASUREMENT_ALERT);
+			hws_alert = 0;
 			deallocate_sdbt();
 		}
 		if (hws_wq) {
@@ -1129,6 +1135,7 @@ start_all_exit:
 	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;

arch/s390/oprofile/init.c

@@ -10,6 +10,7 @@
  */
 
 #include <linux/oprofile.h>
+#include <linux/perf_event.h>
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/fs.h>
@@ -67,6 +68,21 @@ 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;
@@ -76,13 +92,13 @@ static int oprofile_hwsampler_start(void)
 	if (!hwsampler_running)
 		return timer_ops.start();
 
-	retval = hwsampler_allocate(oprofile_sdbt_blocks, oprofile_sdb_blocks);
+	retval = perf_reserve_sampling();
 	if (retval)
 		return retval;
 
-	retval = hwsampler_start_all(oprofile_hw_interval);
+	retval = __oprofile_hwsampler_start();
 	if (retval)
-		hwsampler_deallocate();
+		perf_release_sampling();
 
 	return retval;
 }
@@ -96,6 +112,7 @@ static void oprofile_hwsampler_stop(void)
 
 	hwsampler_stop_all();
 	hwsampler_deallocate();
+	perf_release_sampling();
 	return;
 }