7 files changed, 157 insertions, 225 deletions

diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 33990fa95af0..35b6879628a0 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -16,6 +16,7 @@ config SUPERH
         select HAVE_ARCH_TRACEHOOK
         select HAVE_DMA_API_DEBUG
         select HAVE_DMA_ATTRS
+        select HAVE_IRQ_WORK
         select HAVE_PERF_EVENTS
         select PERF_USE_VMALLOC
         select HAVE_KERNEL_GZIP
@@ -249,6 +250,11 @@ config ARCH_SHMOBILE
         select PM
         select PM_RUNTIME
 
+config CPU_HAS_PMU
+       depends on CPU_SH4 || CPU_SH4A
+       default y
+       bool
+
 if SUPERH32
 
 choice
@@ -738,6 +744,14 @@ config GUSA_RB
           LLSC, this should be more efficient than the other alternative of
           disabling interrupts around the atomic sequence.
 
+config HW_PERF_EVENTS
+        bool "Enable hardware performance counter support for perf events"
+        depends on PERF_EVENTS && CPU_HAS_PMU
+        default y
+        help
+          Enable hardware performance counter support for perf events. If
+          disabled, perf events will use software events only.
+
 source "drivers/sh/Kconfig"
 
 endmenu
diff --git a/arch/sh/include/asm/perf_event.h b/arch/sh/include/asm/perf_event.h
index 3d0c9f36d150..14308bed7ea5 100644
--- a/arch/sh/include/asm/perf_event.h
+++ b/arch/sh/include/asm/perf_event.h
@@ -26,11 +26,4 @@ extern int register_sh_pmu(struct sh_pmu *);
 extern int reserve_pmc_hardware(void);
 extern void release_pmc_hardware(void);
 
-static inline void set_perf_event_pending(void)
-{
-        /* Nothing to see here, move along. */
-}
-
-#define PERF_EVENT_INDEX_OFFSET 0
-
 #endif /* __ASM_SH_PERF_EVENT_H */
diff --git a/arch/sh/kernel/perf_callchain.c b/arch/sh/kernel/perf_callchain.c
index a9dd3abde28e..d5ca1ef50fa9 100644
--- a/arch/sh/kernel/perf_callchain.c
+++ b/arch/sh/kernel/perf_callchain.c
@@ -14,11 +14,6 @@
 #include <asm/unwinder.h>
 #include <asm/ptrace.h>
 
-static inline void callchain_store(struct perf_callchain_entry *entry, u64 ip)
-{
-        if (entry->nr < PERF_MAX_STACK_DEPTH)
-                entry->ip[entry->nr++] = ip;
-}
 
 static void callchain_warning(void *data, char *msg)
 {
@@ -39,7 +34,7 @@ static void callchain_address(void *data, unsigned long addr, int reliable)
         struct perf_callchain_entry *entry = data;
 
         if (reliable)
-                callchain_store(entry, addr);
+                perf_callchain_store(entry, addr);
 }
 
 static const struct stacktrace_ops callchain_ops = {
@@ -49,47 +44,10 @@ static const struct stacktrace_ops callchain_ops = {
         .address        = callchain_address,
 };
 
-static void
-perf_callchain_kernel(struct pt_regs *regs, struct perf_callchain_entry *entry)
+void
+perf_callchain_kernel(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-        callchain_store(entry, PERF_CONTEXT_KERNEL);
-        callchain_store(entry, regs->pc);
+        perf_callchain_store(entry, regs->pc);
 
         unwind_stack(NULL, regs, NULL, &callchain_ops, entry);
 }
-
-static void
-perf_do_callchain(struct pt_regs *regs, struct perf_callchain_entry *entry)
-{
-        int is_user;
-
-        if (!regs)
-                return;
-
-        is_user = user_mode(regs);
-
-        if (is_user && current->state != TASK_RUNNING)
-                return;
-
-        /*
-         * Only the kernel side is implemented for now.
-         */
-        if (!is_user)
-                perf_callchain_kernel(regs, entry);
-}
-
-/*
- * No need for separate IRQ and NMI entries.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
-{
-        struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
-
-        entry->nr = 0;
-
-        perf_do_callchain(regs, entry);
-
-        return entry;
-}
diff --git a/arch/sh/kernel/perf_event.c b/arch/sh/kernel/perf_event.c
index 7a3dc3567258..5a4b33435650 100644
--- a/arch/sh/kernel/perf_event.c
+++ b/arch/sh/kernel/perf_event.c
@@ -59,6 +59,24 @@ static inline int sh_pmu_initialized(void)
         return !!sh_pmu;
 }
 
+const char *perf_pmu_name(void)
+{
+        if (!sh_pmu)
+                return NULL;
+
+        return sh_pmu->name;
+}
+EXPORT_SYMBOL_GPL(perf_pmu_name);
+
+int perf_num_counters(void)
+{
+        if (!sh_pmu)
+                return 0;
+
+        return sh_pmu->num_events;
+}
+EXPORT_SYMBOL_GPL(perf_num_counters);
+
 /*
  * Release the PMU if this is the last perf_event.
  */
@@ -206,50 +224,80 @@ again:
         local64_add(delta, &event->count);
 }
 
-static void sh_pmu_disable(struct perf_event *event)
+static void sh_pmu_stop(struct perf_event *event, int flags)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         struct hw_perf_event *hwc = &event->hw;
         int idx = hwc->idx;
 
-        clear_bit(idx, cpuc->active_mask);
-        sh_pmu->disable(hwc, idx);
+        if (!(event->hw.state & PERF_HES_STOPPED)) {
+                sh_pmu->disable(hwc, idx);
+                cpuc->events[idx] = NULL;
+                event->hw.state |= PERF_HES_STOPPED;
+        }
+
+        if ((flags & PERF_EF_UPDATE) && !(event->hw.state & PERF_HES_UPTODATE)) {
+                sh_perf_event_update(event, &event->hw, idx);
+                event->hw.state |= PERF_HES_UPTODATE;
+        }
+}
+
+static void sh_pmu_start(struct perf_event *event, int flags)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+        struct hw_perf_event *hwc = &event->hw;
+        int idx = hwc->idx;
+
+        if (WARN_ON_ONCE(idx == -1))
+                return;
+
+        if (flags & PERF_EF_RELOAD)
+                WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
 
-        barrier();
+        cpuc->events[idx] = event;
+        event->hw.state = 0;
+        sh_pmu->enable(hwc, idx);
+}
 
-        sh_perf_event_update(event, &event->hw, idx);
+static void sh_pmu_del(struct perf_event *event, int flags)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
 
-        cpuc->events[idx] = NULL;
-        clear_bit(idx, cpuc->used_mask);
+        sh_pmu_stop(event, PERF_EF_UPDATE);
+        __clear_bit(event->hw.idx, cpuc->used_mask);
 
         perf_event_update_userpage(event);
 }
 
-static int sh_pmu_enable(struct perf_event *event)
+static int sh_pmu_add(struct perf_event *event, int flags)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         struct hw_perf_event *hwc = &event->hw;
         int idx = hwc->idx;
+        int ret = -EAGAIN;
+
+        perf_pmu_disable(event->pmu);
 
-        if (test_and_set_bit(idx, cpuc->used_mask)) {
+        if (__test_and_set_bit(idx, cpuc->used_mask)) {
                 idx = find_first_zero_bit(cpuc->used_mask, sh_pmu->num_events);
                 if (idx == sh_pmu->num_events)
-                        return -EAGAIN;
+                        goto out;
 
-                set_bit(idx, cpuc->used_mask);
+                __set_bit(idx, cpuc->used_mask);
                 hwc->idx = idx;
         }
 
         sh_pmu->disable(hwc, idx);
 
-        cpuc->events[idx] = event;
-        set_bit(idx, cpuc->active_mask);
-
-        sh_pmu->enable(hwc, idx);
+        event->hw.state = PERF_HES_UPTODATE | PERF_HES_STOPPED;
+        if (flags & PERF_EF_START)
+                sh_pmu_start(event, PERF_EF_RELOAD);
 
         perf_event_update_userpage(event);
-
-        return 0;
+        ret = 0;
+out:
+        perf_pmu_enable(event->pmu);
+        return ret;
 }
 
 static void sh_pmu_read(struct perf_event *event)
@@ -257,24 +305,56 @@ static void sh_pmu_read(struct perf_event *event)
         sh_perf_event_update(event, &event->hw, event->hw.idx);
 }
 
-static const struct pmu pmu = {
-        .enable         = sh_pmu_enable,
-        .disable        = sh_pmu_disable,
-        .read           = sh_pmu_read,
-};
-
-const struct pmu *hw_perf_event_init(struct perf_event *event)
+static int sh_pmu_event_init(struct perf_event *event)
 {
-        int err = __hw_perf_event_init(event);
+        int err;
+
+        switch (event->attr.type) {
+        case PERF_TYPE_RAW:
+        case PERF_TYPE_HW_CACHE:
+        case PERF_TYPE_HARDWARE:
+                err = __hw_perf_event_init(event);
+                break;
+
+        default:
+                return -ENOENT;
+        }
+
         if (unlikely(err)) {
                 if (event->destroy)
                         event->destroy(event);
-                return ERR_PTR(err);
         }
 
-        return &pmu;
+        return err;
+}
+
+static void sh_pmu_enable(struct pmu *pmu)
+{
+        if (!sh_pmu_initialized())
+                return;
+
+        sh_pmu->enable_all();
+}
+
+static void sh_pmu_disable(struct pmu *pmu)
+{
+        if (!sh_pmu_initialized())
+                return;
+
+        sh_pmu->disable_all();
 }
 
+static struct pmu pmu = {
+        .pmu_enable     = sh_pmu_enable,
+        .pmu_disable    = sh_pmu_disable,
+        .event_init     = sh_pmu_event_init,
+        .add            = sh_pmu_add,
+        .del            = sh_pmu_del,
+        .start          = sh_pmu_start,
+        .stop           = sh_pmu_stop,
+        .read           = sh_pmu_read,
+};
+
 static void sh_pmu_setup(int cpu)
 {
         struct cpu_hw_events *cpuhw = &per_cpu(cpu_hw_events, cpu);
@@ -299,32 +379,17 @@ sh_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
         return NOTIFY_OK;
 }
 
-void hw_perf_enable(void)
-{
-        if (!sh_pmu_initialized())
-                return;
-
-        sh_pmu->enable_all();
-}
-
-void hw_perf_disable(void)
-{
-        if (!sh_pmu_initialized())
-                return;
-
-        sh_pmu->disable_all();
-}
-
-int __cpuinit register_sh_pmu(struct sh_pmu *pmu)
+int __cpuinit register_sh_pmu(struct sh_pmu *_pmu)
 {
         if (sh_pmu)
                 return -EBUSY;
-        sh_pmu = pmu;
+        sh_pmu = _pmu;
 
-        pr_info("Performance Events: %s support registered\n", pmu->name);
+        pr_info("Performance Events: %s support registered\n", _pmu->name);
 
-        WARN_ON(pmu->num_events > MAX_HWEVENTS);
+        WARN_ON(_pmu->num_events > MAX_HWEVENTS);
 
+        perf_pmu_register(&pmu);
         perf_cpu_notifier(sh_pmu_notifier);
         return 0;
 }
diff --git a/arch/sh/oprofile/Makefile b/arch/sh/oprofile/Makefile
index 4886c5c1786c..e85aae73e3dc 100644
--- a/arch/sh/oprofile/Makefile
+++ b/arch/sh/oprofile/Makefile
@@ -6,4 +6,8 @@ DRIVER_OBJS = $(addprefix ../../../drivers/oprofile/, \
                 oprofilefs.o oprofile_stats.o \
                 timer_int.o )
 
+ifeq ($(CONFIG_HW_PERF_EVENTS),y)
+DRIVER_OBJS += $(addprefix ../../../drivers/oprofile/, oprofile_perf.o)
+endif
+
 oprofile-y      := $(DRIVER_OBJS) common.o backtrace.o
diff --git a/arch/sh/oprofile/common.c b/arch/sh/oprofile/common.c
index ac604937f3ee..e10d89376f9b 100644
--- a/arch/sh/oprofile/common.c
+++ b/arch/sh/oprofile/common.c
@@ -17,114 +17,45 @@
 #include <linux/init.h>
 #include <linux/errno.h>
 #include <linux/smp.h>
+#include <linux/perf_event.h>
 #include <asm/processor.h>
-#include "op_impl.h"
-
-static struct op_sh_model *model;
-
-static struct op_counter_config ctr[20];
 
+#ifdef CONFIG_HW_PERF_EVENTS
 extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth);
 
-static int op_sh_setup(void)
-{
-        /* Pre-compute the values to stuff in the hardware registers.  */
-        model->reg_setup(ctr);
-
-        /* Configure the registers on all cpus.  */
-        on_each_cpu(model->cpu_setup, NULL, 1);
-
-        return 0;
-}
-
-static int op_sh_create_files(struct super_block *sb, struct dentry *root)
+char *op_name_from_perf_id(void)
 {
-        int i, ret = 0;
+        const char *pmu;
+        char buf[20];
+        int size;
 
-        for (i = 0; i < model->num_counters; i++) {
-                struct dentry *dir;
-                char buf[4];
+        pmu = perf_pmu_name();
+        if (!pmu)
+                return NULL;
 
-                snprintf(buf, sizeof(buf), "%d", i);
-                dir = oprofilefs_mkdir(sb, root, buf);
+        size = snprintf(buf, sizeof(buf), "sh/%s", pmu);
+        if (size > -1 && size < sizeof(buf))
+                return buf;
 
-                ret |= oprofilefs_create_ulong(sb, dir, "enabled", &ctr[i].enabled);
-                ret |= oprofilefs_create_ulong(sb, dir, "event", &ctr[i].event);
-                ret |= oprofilefs_create_ulong(sb, dir, "kernel", &ctr[i].kernel);
-                ret |= oprofilefs_create_ulong(sb, dir, "user", &ctr[i].user);
-
-                if (model->create_files)
-                        ret |= model->create_files(sb, dir);
-                else
-                        ret |= oprofilefs_create_ulong(sb, dir, "count", &ctr[i].count);
-
-                /* Dummy entries */
-                ret |= oprofilefs_create_ulong(sb, dir, "unit_mask", &ctr[i].unit_mask);
-        }
-
-        return ret;
+        return NULL;
 }
 
-static int op_sh_start(void)
+int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
-        /* Enable performance monitoring for all counters.  */
-        on_each_cpu(model->cpu_start, NULL, 1);
+        ops->backtrace = sh_backtrace;
 
-        return 0;
+        return oprofile_perf_init(ops);
 }
 
-static void op_sh_stop(void)
+void __exit oprofile_arch_exit(void)
 {
-        /* Disable performance monitoring for all counters.  */
-        on_each_cpu(model->cpu_stop, NULL, 1);
+        oprofile_perf_exit();
 }
-
+#else
 int __init oprofile_arch_init(struct oprofile_operations *ops)
 {
-        struct op_sh_model *lmodel = NULL;
-        int ret;
-
-        /*
-         * Always assign the backtrace op. If the counter initialization
-         * fails, we fall back to the timer which will still make use of
-         * this.
-         */
-        ops->backtrace = sh_backtrace;
-
-        /*
-         * XXX
-         *
-         * All of the SH7750/SH-4A counters have been converted to perf,
-         * this infrastructure hook is left for other users until they've
-         * had a chance to convert over, at which point all of this
-         * will be deleted.
-         */
-
-        if (!lmodel)
-                return -ENODEV;
-        if (!(current_cpu_data.flags & CPU_HAS_PERF_COUNTER))
-                return -ENODEV;
-
-        ret = lmodel->init();
-        if (unlikely(ret != 0))
-                return ret;
-
-        model = lmodel;
-
-        ops->setup              = op_sh_setup;
-        ops->create_files       = op_sh_create_files;
-        ops->start              = op_sh_start;
-        ops->stop               = op_sh_stop;
-        ops->cpu_type           = lmodel->cpu_type;
-
-        printk(KERN_INFO "oprofile: using %s performance monitoring.\n",
-               lmodel->cpu_type);
-
-        return 0;
-}
-
-void oprofile_arch_exit(void)
-{
-        if (model && model->exit)
-                model->exit();
+        pr_info("oprofile: hardware counters not available\n");
+        return -ENODEV;
 }
+void __exit oprofile_arch_exit(void) {}
+#endif /* CONFIG_HW_PERF_EVENTS */
diff --git a/arch/sh/oprofile/op_impl.h b/arch/sh/oprofile/op_impl.h
deleted file mode 100644
index 1244479ceb29..000000000000
--- a/arch/sh/oprofile/op_impl.h
+++ /dev/null
@@ -1,33 +0,0 @@
-#ifndef __OP_IMPL_H
-#define __OP_IMPL_H
-
-/* Per-counter configuration as set via oprofilefs.  */
-struct op_counter_config {
-        unsigned long enabled;
-        unsigned long event;
-
-        unsigned long count;
-
-        /* Dummy values for userspace tool compliance */
-        unsigned long kernel;
-        unsigned long user;
-        unsigned long unit_mask;
-};
-
-/* Per-architecture configury and hooks.  */
-struct op_sh_model {
-        void (*reg_setup)(struct op_counter_config *);
-        int (*create_files)(struct super_block *sb, struct dentry *dir);
-        void (*cpu_setup)(void *dummy);
-        int (*init)(void);
-        void (*exit)(void);
-        void (*cpu_start)(void *args);
-        void (*cpu_stop)(void *args);
-        char *cpu_type;
-        unsigned char num_counters;
-};
-
-/* arch/sh/oprofile/common.c */
-extern void sh_backtrace(struct pt_regs * const regs, unsigned int depth);
-
-#endif /* __OP_IMPL_H */