5 files changed, 182 insertions, 121 deletions

diff --git a/arch/sparc/kernel/Makefile b/arch/sparc/kernel/Makefile
index 0c2dc1f24a9a..599398fbbc7c 100644
--- a/arch/sparc/kernel/Makefile
+++ b/arch/sparc/kernel/Makefile
@@ -119,3 +119,5 @@ obj-$(CONFIG_COMPAT)    += $(audit--y)
 
 pc--$(CONFIG_PERF_EVENTS) := perf_event.o
 obj-$(CONFIG_SPARC64)   += $(pc--y)
+
+obj-$(CONFIG_SPARC64)   += jump_label.o
diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c
new file mode 100644
index 000000000000..ea2dafc93d78
--- /dev/null
+++ b/arch/sparc/kernel/jump_label.c
@@ -0,0 +1,47 @@
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/mutex.h>
+#include <linux/cpu.h>
+
+#include <linux/jump_label.h>
+#include <linux/memory.h>
+
+#ifdef HAVE_JUMP_LABEL
+
+void arch_jump_label_transform(struct jump_entry *entry,
+                               enum jump_label_type type)
+{
+        u32 val;
+        u32 *insn = (u32 *) (unsigned long) entry->code;
+
+        if (type == JUMP_LABEL_ENABLE) {
+                s32 off = (s32)entry->target - (s32)entry->code;
+
+#ifdef CONFIG_SPARC64
+                /* ba,pt %xcc, . + (off << 2) */
+                val = 0x10680000 | ((u32) off >> 2);
+#else
+                /* ba . + (off << 2) */
+                val = 0x10800000 | ((u32) off >> 2);
+#endif
+        } else {
+                val = 0x01000000;
+        }
+
+        get_online_cpus();
+        mutex_lock(&text_mutex);
+        *insn = val;
+        flushi(insn);
+        mutex_unlock(&text_mutex);
+        put_online_cpus();
+}
+
+void arch_jump_label_text_poke_early(jump_label_t addr)
+{
+        u32 *insn_p = (u32 *) (unsigned long) addr;
+
+        *insn_p = 0x01000000;
+        flushi(insn_p);
+}
+
+#endif
diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c
index f848aadf54dc..ee3c7dde8d9f 100644
--- a/arch/sparc/kernel/module.c
+++ b/arch/sparc/kernel/module.c
@@ -18,6 +18,9 @@
 #include <asm/spitfire.h>
 
 #ifdef CONFIG_SPARC64
+
+#include <linux/jump_label.h>
+
 static void *module_map(unsigned long size)
 {
         struct vm_struct *area;
@@ -227,6 +230,9 @@ int module_finalize(const Elf_Ehdr *hdr,
                     const Elf_Shdr *sechdrs,
                     struct module *me)
 {
+        /* make jump label nops */
+        jump_label_apply_nops(me);
+
         /* Cheetah's I-cache is fully coherent.  */
         if (tlb_type == spitfire) {
                 unsigned long va;
diff --git a/arch/sparc/kernel/pcr.c b/arch/sparc/kernel/pcr.c
index c4a6a50b4849..b87873c0e8ea 100644
--- a/arch/sparc/kernel/pcr.c
+++ b/arch/sparc/kernel/pcr.c
@@ -7,7 +7,7 @@
 #include <linux/init.h>
 #include <linux/irq.h>
 
-#include <linux/perf_event.h>
+#include <linux/irq_work.h>
 #include <linux/ftrace.h>
 
 #include <asm/pil.h>
@@ -43,14 +43,14 @@ void __irq_entry deferred_pcr_work_irq(int irq, struct pt_regs *regs)
 
         old_regs = set_irq_regs(regs);
         irq_enter();
-#ifdef CONFIG_PERF_EVENTS
-        perf_event_do_pending();
+#ifdef CONFIG_IRQ_WORK
+        irq_work_run();
 #endif
         irq_exit();
         set_irq_regs(old_regs);
 }
 
-void set_perf_event_pending(void)
+void arch_irq_work_raise(void)
 {
         set_softint(1 << PIL_DEFERRED_PCR_WORK);
 }
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index 6318e622cfb0..0d6deb55a2ae 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -658,13 +658,16 @@ static u64 maybe_change_configuration(struct cpu_hw_events *cpuc, u64 pcr)
 
                 enc = perf_event_get_enc(cpuc->events[i]);
                 pcr &= ~mask_for_index(idx);
-                pcr |= event_encoding(enc, idx);
+                if (hwc->state & PERF_HES_STOPPED)
+                        pcr |= nop_for_index(idx);
+                else
+                        pcr |= event_encoding(enc, idx);
         }
 out:
         return pcr;
 }
 
-void hw_perf_enable(void)
+static void sparc_pmu_enable(struct pmu *pmu)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         u64 pcr;
@@ -691,7 +694,7 @@ void hw_perf_enable(void)
         pcr_ops->write(cpuc->pcr);
 }
 
-void hw_perf_disable(void)
+static void sparc_pmu_disable(struct pmu *pmu)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         u64 val;
@@ -710,19 +713,65 @@ void hw_perf_disable(void)
         pcr_ops->write(cpuc->pcr);
 }
 
-static void sparc_pmu_disable(struct perf_event *event)
+static int active_event_index(struct cpu_hw_events *cpuc,
+                              struct perf_event *event)
+{
+        int i;
+
+        for (i = 0; i < cpuc->n_events; i++) {
+                if (cpuc->event[i] == event)
+                        break;
+        }
+        BUG_ON(i == cpuc->n_events);
+        return cpuc->current_idx[i];
+}
+
+static void sparc_pmu_start(struct perf_event *event, int flags)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+        int idx = active_event_index(cpuc, event);
+
+        if (flags & PERF_EF_RELOAD) {
+                WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE));
+                sparc_perf_event_set_period(event, &event->hw, idx);
+        }
+
+        event->hw.state = 0;
+
+        sparc_pmu_enable_event(cpuc, &event->hw, idx);
+}
+
+static void sparc_pmu_stop(struct perf_event *event, int flags)
+{
+        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
+        int idx = active_event_index(cpuc, event);
+
+        if (!(event->hw.state & PERF_HES_STOPPED)) {
+                sparc_pmu_disable_event(cpuc, &event->hw, idx);
+                event->hw.state |= PERF_HES_STOPPED;
+        }
+
+        if (!(event->hw.state & PERF_HES_UPTODATE) && (flags & PERF_EF_UPDATE)) {
+                sparc_perf_event_update(event, &event->hw, idx);
+                event->hw.state |= PERF_HES_UPTODATE;
+        }
+}
+
+static void sparc_pmu_del(struct perf_event *event, int _flags)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-        struct hw_perf_event *hwc = &event->hw;
         unsigned long flags;
         int i;
 
         local_irq_save(flags);
-        perf_disable();
+        perf_pmu_disable(event->pmu);
 
         for (i = 0; i < cpuc->n_events; i++) {
                 if (event == cpuc->event[i]) {
-                        int idx = cpuc->current_idx[i];
+                        /* Absorb the final count and turn off the
+                         * event.
+                         */
+                        sparc_pmu_stop(event, PERF_EF_UPDATE);
 
                         /* Shift remaining entries down into
                          * the existing slot.
@@ -734,13 +783,6 @@ static void sparc_pmu_disable(struct perf_event *event)
                                         cpuc->current_idx[i];
                         }
 
-                        /* Absorb the final count and turn off the
-                         * event.
-                         */
-                        sparc_pmu_disable_event(cpuc, hwc, idx);
-                        barrier();
-                        sparc_perf_event_update(event, hwc, idx);
-
                         perf_event_update_userpage(event);
 
                         cpuc->n_events--;
@@ -748,23 +790,10 @@ static void sparc_pmu_disable(struct perf_event *event)
                 }
         }
 
-        perf_enable();
+        perf_pmu_enable(event->pmu);
         local_irq_restore(flags);
 }
 
-static int active_event_index(struct cpu_hw_events *cpuc,
-                              struct perf_event *event)
-{
-        int i;
-
-        for (i = 0; i < cpuc->n_events; i++) {
-                if (cpuc->event[i] == event)
-                        break;
-        }
-        BUG_ON(i == cpuc->n_events);
-        return cpuc->current_idx[i];
-}
-
 static void sparc_pmu_read(struct perf_event *event)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
@@ -774,15 +803,6 @@ static void sparc_pmu_read(struct perf_event *event)
         sparc_perf_event_update(event, hwc, idx);
 }
 
-static void sparc_pmu_unthrottle(struct perf_event *event)
-{
-        struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
-        int idx = active_event_index(cpuc, event);
-        struct hw_perf_event *hwc = &event->hw;
-
-        sparc_pmu_enable_event(cpuc, hwc, idx);
-}
-
 static atomic_t active_events = ATOMIC_INIT(0);
 static DEFINE_MUTEX(pmc_grab_mutex);
 
@@ -877,7 +897,7 @@ static int sparc_check_constraints(struct perf_event **evts,
         if (!n_ev)
                 return 0;
 
-        if (n_ev > perf_max_events)
+        if (n_ev > MAX_HWEVENTS)
                 return -1;
 
         msk0 = perf_event_get_msk(events[0]);
@@ -984,23 +1004,27 @@ static int collect_events(struct perf_event *group, int max_count,
         return n;
 }
 
-static int sparc_pmu_enable(struct perf_event *event)
+static int sparc_pmu_add(struct perf_event *event, int ef_flags)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         int n0, ret = -EAGAIN;
         unsigned long flags;
 
         local_irq_save(flags);
-        perf_disable();
+        perf_pmu_disable(event->pmu);
 
         n0 = cpuc->n_events;
-        if (n0 >= perf_max_events)
+        if (n0 >= MAX_HWEVENTS)
                 goto out;
 
         cpuc->event[n0] = event;
         cpuc->events[n0] = event->hw.event_base;
         cpuc->current_idx[n0] = PIC_NO_INDEX;
 
+        event->hw.state = PERF_HES_UPTODATE;
+        if (!(ef_flags & PERF_EF_START))
+                event->hw.state |= PERF_HES_STOPPED;
+
         /*
          * If group events scheduling transaction was started,
          * skip the schedulability test here, it will be peformed
@@ -1020,12 +1044,12 @@ nocheck:
 
         ret = 0;
 out:
-        perf_enable();
+        perf_pmu_enable(event->pmu);
         local_irq_restore(flags);
         return ret;
 }
 
-static int __hw_perf_event_init(struct perf_event *event)
+static int sparc_pmu_event_init(struct perf_event *event)
 {
         struct perf_event_attr *attr = &event->attr;
         struct perf_event *evts[MAX_HWEVENTS];
@@ -1038,22 +1062,33 @@ static int __hw_perf_event_init(struct perf_event *event)
         if (atomic_read(&nmi_active) < 0)
                 return -ENODEV;
 
-        pmap = NULL;
-        if (attr->type == PERF_TYPE_HARDWARE) {
+        switch (attr->type) {
+        case PERF_TYPE_HARDWARE:
                 if (attr->config >= sparc_pmu->max_events)
                         return -EINVAL;
                 pmap = sparc_pmu->event_map(attr->config);
-        } else if (attr->type == PERF_TYPE_HW_CACHE) {
+                break;
+
+        case PERF_TYPE_HW_CACHE:
                 pmap = sparc_map_cache_event(attr->config);
                 if (IS_ERR(pmap))
                         return PTR_ERR(pmap);
-        } else if (attr->type != PERF_TYPE_RAW)
-                return -EOPNOTSUPP;
+                break;
+
+        case PERF_TYPE_RAW:
+                pmap = NULL;
+                break;
+
+        default:
+                return -ENOENT;
+
+        }
 
         if (pmap) {
                 hwc->event_base = perf_event_encode(pmap);
         } else {
-                /* User gives us "(encoding << 16) | pic_mask" for
+                /*
+                 * User gives us "(encoding << 16) | pic_mask" for
                  * PERF_TYPE_RAW events.
                  */
                 hwc->event_base = attr->config;
@@ -1071,7 +1106,7 @@ static int __hw_perf_event_init(struct perf_event *event)
         n = 0;
         if (event->group_leader != event) {
                 n = collect_events(event->group_leader,
-                                   perf_max_events - 1,
+                                   MAX_HWEVENTS - 1,
                                    evts, events, current_idx_dmy);
                 if (n < 0)
                         return -EINVAL;
@@ -1107,10 +1142,11 @@ static int __hw_perf_event_init(struct perf_event *event)
  * Set the flag to make pmu::enable() not perform the
  * schedulability test, it will be performed at commit time
  */
-static void sparc_pmu_start_txn(const struct pmu *pmu)
+static void sparc_pmu_start_txn(struct pmu *pmu)
 {
         struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
+        perf_pmu_disable(pmu);
         cpuhw->group_flag |= PERF_EVENT_TXN;
 }
 
@@ -1119,11 +1155,12 @@ static void sparc_pmu_start_txn(const struct pmu *pmu)
  * Clear the flag and pmu::enable() will perform the
  * schedulability test.
  */
-static void sparc_pmu_cancel_txn(const struct pmu *pmu)
+static void sparc_pmu_cancel_txn(struct pmu *pmu)
 {
         struct cpu_hw_events *cpuhw = &__get_cpu_var(cpu_hw_events);
 
         cpuhw->group_flag &= ~PERF_EVENT_TXN;
+        perf_pmu_enable(pmu);
 }
 
 /*
@@ -1131,7 +1168,7 @@ static void sparc_pmu_cancel_txn(const struct pmu *pmu)
  * Perform the group schedulability test as a whole
  * Return 0 if success
  */
-static int sparc_pmu_commit_txn(const struct pmu *pmu)
+static int sparc_pmu_commit_txn(struct pmu *pmu)
 {
         struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events);
         int n;
@@ -1147,28 +1184,24 @@ static int sparc_pmu_commit_txn(const struct pmu *pmu)
                 return -EAGAIN;
 
         cpuc->group_flag &= ~PERF_EVENT_TXN;
+        perf_pmu_enable(pmu);
         return 0;
 }
 
-static const struct pmu pmu = {
-        .enable         = sparc_pmu_enable,
-        .disable        = sparc_pmu_disable,
+static struct pmu pmu = {
+        .pmu_enable     = sparc_pmu_enable,
+        .pmu_disable    = sparc_pmu_disable,
+        .event_init     = sparc_pmu_event_init,
+        .add            = sparc_pmu_add,
+        .del            = sparc_pmu_del,
+        .start          = sparc_pmu_start,
+        .stop           = sparc_pmu_stop,
         .read           = sparc_pmu_read,
-        .unthrottle     = sparc_pmu_unthrottle,
         .start_txn      = sparc_pmu_start_txn,
         .cancel_txn     = sparc_pmu_cancel_txn,
         .commit_txn     = sparc_pmu_commit_txn,
 };
 
-const struct pmu *hw_perf_event_init(struct perf_event *event)
-{
-        int err = __hw_perf_event_init(event);
-
-        if (err)
-                return ERR_PTR(err);
-        return &pmu;
-}
-
 void perf_event_print_debug(void)
 {
         unsigned long flags;
@@ -1244,7 +1277,7 @@ static int __kprobes perf_event_nmi_handler(struct notifier_block *self,
                         continue;
 
                 if (perf_event_overflow(event, 1, &data, regs))
-                        sparc_pmu_disable_event(cpuc, hwc, idx);
+                        sparc_pmu_stop(event, 0);
         }
 
         return NOTIFY_STOP;
@@ -1285,28 +1318,21 @@ void __init init_hw_perf_events(void)
 
         pr_cont("Supported PMU type is '%s'\n", sparc_pmu_type);
 
-        /* All sparc64 PMUs currently have 2 events.  */
-        perf_max_events = 2;
-
+        perf_pmu_register(&pmu);
         register_die_notifier(&perf_event_nmi_notifier);
 }
 
-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 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)
 {
         unsigned long ksp, fp;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
         int graph = 0;
 #endif
 
-        callchain_store(entry, PERF_CONTEXT_KERNEL);
-        callchain_store(entry, regs->tpc);
+        stack_trace_flush();
+
+        perf_callchain_store(entry, regs->tpc);
 
         ksp = regs->u_regs[UREG_I6];
         fp = ksp + STACK_BIAS;
@@ -1330,13 +1356,13 @@ static void perf_callchain_kernel(struct pt_regs *regs,
                         pc = sf->callers_pc;
                         fp = (unsigned long)sf->fp + STACK_BIAS;
                 }
-                callchain_store(entry, pc);
+                perf_callchain_store(entry, pc);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
                 if ((pc + 8UL) == (unsigned long) &return_to_handler) {
                         int index = current->curr_ret_stack;
                         if (current->ret_stack && index >= graph) {
                                 pc = current->ret_stack[index - graph].ret;
-                                callchain_store(entry, pc);
+                                perf_callchain_store(entry, pc);
                                 graph++;
                         }
                 }
@@ -1344,13 +1370,12 @@ static void perf_callchain_kernel(struct pt_regs *regs,
         } while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_64(struct pt_regs *regs,
-                                   struct perf_callchain_entry *entry)
+static void perf_callchain_user_64(struct perf_callchain_entry *entry,
+                                   struct pt_regs *regs)
 {
         unsigned long ufp;
 
-        callchain_store(entry, PERF_CONTEXT_USER);
-        callchain_store(entry, regs->tpc);
+        perf_callchain_store(entry, regs->tpc);
 
         ufp = regs->u_regs[UREG_I6] + STACK_BIAS;
         do {
@@ -1363,17 +1388,16 @@ static void perf_callchain_user_64(struct pt_regs *regs,
 
                 pc = sf.callers_pc;
                 ufp = (unsigned long)sf.fp + STACK_BIAS;
-                callchain_store(entry, pc);
+                perf_callchain_store(entry, pc);
         } while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-static void perf_callchain_user_32(struct pt_regs *regs,
-                                   struct perf_callchain_entry *entry)
+static void perf_callchain_user_32(struct perf_callchain_entry *entry,
+                                   struct pt_regs *regs)
 {
         unsigned long ufp;
 
-        callchain_store(entry, PERF_CONTEXT_USER);
-        callchain_store(entry, regs->tpc);
+        perf_callchain_store(entry, regs->tpc);
 
         ufp = regs->u_regs[UREG_I6] & 0xffffffffUL;
         do {
@@ -1386,34 +1410,16 @@ static void perf_callchain_user_32(struct pt_regs *regs,
 
                 pc = sf.callers_pc;
                 ufp = (unsigned long)sf.fp;
-                callchain_store(entry, pc);
+                perf_callchain_store(entry, pc);
         } while (entry->nr < PERF_MAX_STACK_DEPTH);
 }
 
-/* Like powerpc we can't get PMU interrupts within the PMU handler,
- * so no need for separate NMI and IRQ chains as on x86.
- */
-static DEFINE_PER_CPU(struct perf_callchain_entry, callchain);
-
-struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
+void
+perf_callchain_user(struct perf_callchain_entry *entry, struct pt_regs *regs)
 {
-        struct perf_callchain_entry *entry = &__get_cpu_var(callchain);
-
-        entry->nr = 0;
-        if (!user_mode(regs)) {
-                stack_trace_flush();
-                perf_callchain_kernel(regs, entry);
-                if (current->mm)
-                        regs = task_pt_regs(current);
-                else
-                        regs = NULL;
-        }
-        if (regs) {
-                flushw_user();
-                if (test_thread_flag(TIF_32BIT))
-                        perf_callchain_user_32(regs, entry);
-                else
-                        perf_callchain_user_64(regs, entry);
-        }
-        return entry;
+        flushw_user();
+        if (test_thread_flag(TIF_32BIT))
+                perf_callchain_user_32(entry, regs);
+        else
+                perf_callchain_user_64(entry, regs);
 }