1 files changed, 148 insertions, 74 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 716f99b682c1..40150f345982 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -486,6 +486,8 @@ struct perf_guest_info_callbacks {
 #include <linux/workqueue.h>
 #include <linux/ftrace.h>
 #include <linux/cpu.h>
+#include <linux/irq_work.h>
+#include <linux/jump_label_ref.h>
 #include <asm/atomic.h>
 #include <asm/local.h>
 
@@ -529,16 +531,22 @@ struct hw_perf_event {
                         int             last_cpu;
                 };
                 struct { /* software */
-                        s64             remaining;
                         struct hrtimer  hrtimer;
                 };
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
                 struct { /* breakpoint */
                         struct arch_hw_breakpoint       info;
                         struct list_head                bp_list;
+                        /*
+                         * Crufty hack to avoid the chicken and egg
+                         * problem hw_breakpoint has with context
+                         * creation and event initalization.
+                         */
+                        struct task_struct              *bp_target;
                 };
 #endif
         };
+        int                             state;
         local64_t                       prev_count;
         u64                             sample_period;
         u64                             last_period;
@@ -550,6 +558,13 @@ struct hw_perf_event {
 #endif
 };
 
+/*
+ * hw_perf_event::state flags
+ */
+#define PERF_HES_STOPPED        0x01 /* the counter is stopped */
+#define PERF_HES_UPTODATE       0x02 /* event->count up-to-date */
+#define PERF_HES_ARCH           0x04
+
 struct perf_event;
 
 /*
@@ -561,36 +576,70 @@ struct perf_event;
  * struct pmu - generic performance monitoring unit
  */
 struct pmu {
-        int (*enable)                   (struct perf_event *event);
-        void (*disable)                 (struct perf_event *event);
-        int (*start)                    (struct perf_event *event);
-        void (*stop)                    (struct perf_event *event);
-        void (*read)                    (struct perf_event *event);
-        void (*unthrottle)              (struct perf_event *event);
+        struct list_head                entry;
+
+        int * __percpu                  pmu_disable_count;
+        struct perf_cpu_context * __percpu pmu_cpu_context;
+        int                             task_ctx_nr;
 
         /*
-         * Group events scheduling is treated as a transaction, add group
-         * events as a whole and perform one schedulability test. If the test
-         * fails, roll back the whole group
+         * Fully disable/enable this PMU, can be used to protect from the PMI
+         * as well as for lazy/batch writing of the MSRs.
          */
+        void (*pmu_enable)              (struct pmu *pmu); /* optional */
+        void (*pmu_disable)             (struct pmu *pmu); /* optional */
 
         /*
-         * Start the transaction, after this ->enable() doesn't need
-         * to do schedulability tests.
+         * Try and initialize the event for this PMU.
+         * Should return -ENOENT when the @event doesn't match this PMU.
          */
-        void (*start_txn)       (const struct pmu *pmu);
+        int (*event_init)               (struct perf_event *event);
+
+#define PERF_EF_START   0x01            /* start the counter when adding    */
+#define PERF_EF_RELOAD  0x02            /* reload the counter when starting */
+#define PERF_EF_UPDATE  0x04            /* update the counter when stopping */
+
         /*
-         * If ->start_txn() disabled the ->enable() schedulability test
+         * Adds/Removes a counter to/from the PMU, can be done inside
+         * a transaction, see the ->*_txn() methods.
+         */
+        int  (*add)                     (struct perf_event *event, int flags);
+        void (*del)                     (struct perf_event *event, int flags);
+
+        /*
+         * Starts/Stops a counter present on the PMU. The PMI handler
+         * should stop the counter when perf_event_overflow() returns
+         * !0. ->start() will be used to continue.
+         */
+        void (*start)                   (struct perf_event *event, int flags);
+        void (*stop)                    (struct perf_event *event, int flags);
+
+        /*
+         * Updates the counter value of the event.
+         */
+        void (*read)                    (struct perf_event *event);
+
+        /*
+         * Group events scheduling is treated as a transaction, add
+         * group events as a whole and perform one schedulability test.
+         * If the test fails, roll back the whole group
+         *
+         * Start the transaction, after this ->add() doesn't need to
+         * do schedulability tests.
+         */
+        void (*start_txn)       (struct pmu *pmu); /* optional */
+        /*
+         * If ->start_txn() disabled the ->add() schedulability test
          * then ->commit_txn() is required to perform one. On success
          * the transaction is closed. On error the transaction is kept
          * open until ->cancel_txn() is called.
          */
-        int  (*commit_txn)      (const struct pmu *pmu);
+        int  (*commit_txn)      (struct pmu *pmu); /* optional */
         /*
-         * Will cancel the transaction, assumes ->disable() is called for
-         * each successfull ->enable() during the transaction.
+         * Will cancel the transaction, assumes ->del() is called
+         * for each successfull ->add() during the transaction.
          */
-        void (*cancel_txn)      (const struct pmu *pmu);
+        void (*cancel_txn)      (struct pmu *pmu); /* optional */
 };
 
 /**
@@ -631,11 +680,6 @@ struct perf_buffer {
         void                            *data_pages[0];
 };
 
-struct perf_pending_entry {
-        struct perf_pending_entry *next;
-        void (*func)(struct perf_pending_entry *);
-};
-
 struct perf_sample_data;
 
 typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
@@ -656,6 +700,7 @@ struct swevent_hlist {
 
 #define PERF_ATTACH_CONTEXT     0x01
 #define PERF_ATTACH_GROUP       0x02
+#define PERF_ATTACH_TASK        0x04
 
 /**
  * struct perf_event - performance event kernel representation:
@@ -669,7 +714,7 @@ struct perf_event {
         int                             nr_siblings;
         int                             group_flags;
         struct perf_event               *group_leader;
-        const struct pmu                *pmu;
+        struct pmu                      *pmu;
 
         enum perf_event_active_state    state;
         unsigned int                    attach_state;
@@ -702,6 +747,16 @@ struct perf_event {
         u64                             tstamp_running;
         u64                             tstamp_stopped;
 
+        /*
+         * timestamp shadows the actual context timing but it can
+         * be safely used in NMI interrupt context. It reflects the
+         * context time as it was when the event was last scheduled in.
+         *
+         * ctx_time already accounts for ctx->timestamp. Therefore to
+         * compute ctx_time for a sample, simply add perf_clock().
+         */
+        u64                             shadow_ctx_time;
+
         struct perf_event_attr          attr;
         struct hw_perf_event            hw;
 
@@ -743,7 +798,7 @@ struct perf_event {
         int                             pending_wakeup;
         int                             pending_kill;
         int                             pending_disable;
-        struct perf_pending_entry       pending;
+        struct irq_work                 pending;
 
         atomic_t                        event_limit;
 
@@ -763,12 +818,19 @@ struct perf_event {
 #endif /* CONFIG_PERF_EVENTS */
 };
 
+enum perf_event_context_type {
+        task_context,
+        cpu_context,
+};
+
 /**
  * struct perf_event_context - event context structure
  *
  * Used as a container for task events and CPU events as well:
  */
 struct perf_event_context {
+        enum perf_event_context_type    type;
+        struct pmu                      *pmu;
         /*
          * Protect the states of the events in the list,
          * nr_active, and the list:
@@ -808,6 +870,12 @@ struct perf_event_context {
         struct rcu_head                 rcu_head;
 };
 
+/*
+ * Number of contexts where an event can trigger:
+ *      task, softirq, hardirq, nmi.
+ */
+#define PERF_NR_CONTEXTS        4
+
 /**
  * struct perf_event_cpu_context - per cpu event context structure
  */
@@ -815,18 +883,9 @@ struct perf_cpu_context {
         struct perf_event_context       ctx;
         struct perf_event_context       *task_ctx;
         int                             active_oncpu;
-        int                             max_pertask;
         int                             exclusive;
-        struct swevent_hlist            *swevent_hlist;
-        struct mutex                    hlist_mutex;
-        int                             hlist_refcount;
-
-        /*
-         * Recursion avoidance:
-         *
-         * task, softirq, irq, nmi context
-         */
-        int                             recursion[4];
+        struct list_head                rotation_list;
+        int                             jiffies_interval;
 };
 
 struct perf_output_handle {
@@ -842,26 +901,34 @@ struct perf_output_handle {
 
 #ifdef CONFIG_PERF_EVENTS
 
-/*
- * Set by architecture code:
- */
-extern int perf_max_events;
+extern int perf_pmu_register(struct pmu *pmu);
+extern void perf_pmu_unregister(struct pmu *pmu);
+
+extern int perf_num_counters(void);
+extern const char *perf_pmu_name(void);
+extern void __perf_event_task_sched_in(struct task_struct *task);
+extern void __perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
 
-extern const struct pmu *hw_perf_event_init(struct perf_event *event);
+extern atomic_t perf_task_events;
+
+static inline void perf_event_task_sched_in(struct task_struct *task)
+{
+        COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
+}
+
+static inline
+void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next)
+{
+        COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+}
 
-extern void perf_event_task_sched_in(struct task_struct *task);
-extern void perf_event_task_sched_out(struct task_struct *task, struct task_struct *next);
-extern void perf_event_task_tick(struct task_struct *task);
 extern int perf_event_init_task(struct task_struct *child);
 extern void perf_event_exit_task(struct task_struct *child);
 extern void perf_event_free_task(struct task_struct *task);
-extern void set_perf_event_pending(void);
-extern void perf_event_do_pending(void);
+extern void perf_event_delayed_put(struct task_struct *task);
 extern void perf_event_print_debug(void);
-extern void __perf_disable(void);
-extern bool __perf_enable(void);
-extern void perf_disable(void);
-extern void perf_enable(void);
+extern void perf_pmu_disable(struct pmu *pmu);
+extern void perf_pmu_enable(struct pmu *pmu);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
 extern void perf_event_update_userpage(struct perf_event *event);
@@ -869,7 +936,7 @@ extern int perf_event_release_kernel(struct perf_event *event);
 extern struct perf_event *
 perf_event_create_kernel_counter(struct perf_event_attr *attr,
                                 int cpu,
-                                pid_t pid,
+                                struct task_struct *task,
                                 perf_overflow_handler_t callback);
 extern u64 perf_event_read_value(struct perf_event *event,
                                  u64 *enabled, u64 *running);
@@ -920,14 +987,7 @@ extern int perf_event_overflow(struct perf_event *event, int nmi,
  */
 static inline int is_software_event(struct perf_event *event)
 {
-        switch (event->attr.type) {
-        case PERF_TYPE_SOFTWARE:
-        case PERF_TYPE_TRACEPOINT:
-        /* for now the breakpoint stuff also works as software event */
-        case PERF_TYPE_BREAKPOINT:
-                return 1;
-        }
-        return 0;
+        return event->pmu->task_ctx_nr == perf_sw_context;
 }
 
 extern atomic_t perf_swevent_enabled[PERF_COUNT_SW_MAX];
@@ -954,18 +1014,20 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs)
         perf_arch_fetch_caller_regs(regs, CALLER_ADDR0);
 }
 
-static inline void
+static __always_inline void
 perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
 {
-        if (atomic_read(&perf_swevent_enabled[event_id])) {
-                struct pt_regs hot_regs;
-
-                if (!regs) {
-                        perf_fetch_caller_regs(&hot_regs);
-                        regs = &hot_regs;
-                }
-                __perf_sw_event(event_id, nr, nmi, regs, addr);
+        struct pt_regs hot_regs;
+
+        JUMP_LABEL(&perf_swevent_enabled[event_id], have_event);
+        return;
+
+have_event:
+        if (!regs) {
+                perf_fetch_caller_regs(&hot_regs);
+                regs = &hot_regs;
         }
+        __perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);
@@ -976,7 +1038,21 @@ extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks
 extern void perf_event_comm(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
 
-extern struct perf_callchain_entry *perf_callchain(struct pt_regs *regs);
+/* Callchains */
+DECLARE_PER_CPU(struct perf_callchain_entry, perf_callchain_entry);
+
+extern void perf_callchain_user(struct perf_callchain_entry *entry,
+                                struct pt_regs *regs);
+extern void perf_callchain_kernel(struct perf_callchain_entry *entry,
+                                  struct pt_regs *regs);
+
+
+static inline void
+perf_callchain_store(struct perf_callchain_entry *entry, u64 ip)
+{
+        if (entry->nr < PERF_MAX_STACK_DEPTH)
+                entry->ip[entry->nr++] = ip;
+}
 
 extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
@@ -1019,21 +1095,18 @@ extern int perf_swevent_get_recursion_context(void);
 extern void perf_swevent_put_recursion_context(int rctx);
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
+extern void perf_event_task_tick(void);
 #else
 static inline void
 perf_event_task_sched_in(struct task_struct *task)                      { }
 static inline void
 perf_event_task_sched_out(struct task_struct *task,
                             struct task_struct *next)                   { }
-static inline void
-perf_event_task_tick(struct task_struct *task)                          { }
 static inline int perf_event_init_task(struct task_struct *child)       { return 0; }
 static inline void perf_event_exit_task(struct task_struct *child)      { }
 static inline void perf_event_free_task(struct task_struct *task)       { }
-static inline void perf_event_do_pending(void)                          { }
+static inline void perf_event_delayed_put(struct task_struct *task)     { }
 static inline void perf_event_print_debug(void)                         { }
-static inline void perf_disable(void)                                   { }
-static inline void perf_enable(void)                                    { }
 static inline int perf_event_task_disable(void)                         { return -EINVAL; }
 static inline int perf_event_task_enable(void)                          { return -EINVAL; }
 
@@ -1056,6 +1129,7 @@ static inline int  perf_swevent_get_recursion_context(void)		{ return -1; }
 static inline void perf_swevent_put_recursion_context(int rctx)         { }
 static inline void perf_event_enable(struct perf_event *event)          { }
 static inline void perf_event_disable(struct perf_event *event)         { }
+static inline void perf_event_task_tick(void)                           { }
 #endif
 
 #define perf_output_put(handle, x) \