Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (123 commits)
  perf: Remove the nmi parameter from the oprofile_perf backend
  x86, perf: Make copy_from_user_nmi() a library function
  perf: Remove perf_event_attr::type check
  x86, perf: P4 PMU - Fix typos in comments and style cleanup
  perf tools: Make test use the preset debugfs path
  perf tools: Add automated tests for events parsing
  perf tools: De-opt the parse_events function
  perf script: Fix display of IP address for non-callchain path
  perf tools: Fix endian conversion reading event attr from file header
  perf tools: Add missing 'node' alias to the hw_cache[] array
  perf probe: Support adding probes on offline kernel modules
  perf probe: Add probed module in front of function
  perf probe: Introduce debuginfo to encapsulate dwarf information
  perf-probe: Move dwarf library routines to dwarf-aux.{c, h}
  perf probe: Remove redundant dwarf functions
  perf probe: Move strtailcmp to string.c
  perf probe: Rename DIE_FIND_CB_FOUND to DIE_FIND_CB_END
  tracing/kprobe: Update symbol reference when loading module
  tracing/kprobes: Support module init function probing
  kprobes: Return -ENOENT if probe point doesn't exist
  ...

6 files changed, 54 insertions, 55 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 9d88e1cb5dbb..f0c0e8a47ae6 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -19,6 +19,8 @@
 
 #include <asm/ftrace.h>
 
+struct ftrace_hash;
+
 #ifdef CONFIG_FUNCTION_TRACER
 
 extern int ftrace_enabled;
@@ -29,8 +31,6 @@ ftrace_enable_sysctl(struct ctl_table *table, int write,
 
 typedef void (*ftrace_func_t)(unsigned long ip, unsigned long parent_ip);
 
-struct ftrace_hash;
-
 enum {
         FTRACE_OPS_FL_ENABLED           = 1 << 0,
         FTRACE_OPS_FL_GLOBAL            = 1 << 1,
@@ -123,7 +123,8 @@ stack_trace_sysctl(struct ctl_table *table, int write,
 struct ftrace_func_command {
         struct list_head        list;
         char                    *name;
-        int                     (*func)(char *func, char *cmd,
+        int                     (*func)(struct ftrace_hash *hash,
+                                        char *func, char *cmd,
                                         char *params, int enable);
 };
 
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 59d3ef100eb9..96efa6794ea5 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -76,6 +76,7 @@ struct trace_iterator {
         struct trace_entry      *ent;
         unsigned long           lost_events;
         int                     leftover;
+        int                     ent_size;
         int                     cpu;
         u64                     ts;
 
@@ -129,6 +130,10 @@ void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
 void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
                                        struct ring_buffer_event *event,
                                         unsigned long flags, int pc);
+void trace_nowake_buffer_unlock_commit_regs(struct ring_buffer *buffer,
+                                            struct ring_buffer_event *event,
+                                            unsigned long flags, int pc,
+                                            struct pt_regs *regs);
 void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
                                          struct ring_buffer_event *event);
 
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index d1e55fed2c7d..6ae9c631a1be 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -73,6 +73,7 @@ static inline unsigned long hw_breakpoint_len(struct perf_event *bp)
 extern struct perf_event *
 register_user_hw_breakpoint(struct perf_event_attr *attr,
                             perf_overflow_handler_t triggered,
+                            void *context,
                             struct task_struct *tsk);
 
 /* FIXME: only change from the attr, and don't unregister */
@@ -85,11 +86,13 @@ modify_user_hw_breakpoint(struct perf_event *bp, struct perf_event_attr *attr);
 extern struct perf_event *
 register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
                                 perf_overflow_handler_t triggered,
+                                void *context,
                                 int cpu);
 
 extern struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
-                            perf_overflow_handler_t triggered);
+                            perf_overflow_handler_t triggered,
+                            void *context);
 
 extern int register_perf_hw_breakpoint(struct perf_event *bp);
 extern int __register_perf_hw_breakpoint(struct perf_event *bp);
@@ -115,6 +118,7 @@ static inline int __init init_hw_breakpoint(void) { return 0; }
 static inline struct perf_event *
 register_user_hw_breakpoint(struct perf_event_attr *attr,
                             perf_overflow_handler_t triggered,
+                            void *context,
                             struct task_struct *tsk)    { return NULL; }
 static inline int
 modify_user_hw_breakpoint(struct perf_event *bp,
@@ -122,10 +126,12 @@ modify_user_hw_breakpoint(struct perf_event *bp,
 static inline struct perf_event *
 register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
                                 perf_overflow_handler_t  triggered,
+                                void *context,
                                 int cpu)                { return NULL; }
 static inline struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
-                            perf_overflow_handler_t triggered)  { return NULL; }
+                            perf_overflow_handler_t triggered,
+                            void *context)              { return NULL; }
 static inline int
 register_perf_hw_breakpoint(struct perf_event *bp)      { return -ENOSYS; }
 static inline int
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e0786e35f247..3f2711ccf910 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -61,7 +61,7 @@ enum perf_hw_id {
 /*
  * Generalized hardware cache events:
  *
- *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU } x
+ *       { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x
  *       { read, write, prefetch } x
  *       { accesses, misses }
  */
@@ -72,6 +72,7 @@ enum perf_hw_cache_id {
         PERF_COUNT_HW_CACHE_DTLB                = 3,
         PERF_COUNT_HW_CACHE_ITLB                = 4,
         PERF_COUNT_HW_CACHE_BPU                 = 5,
+        PERF_COUNT_HW_CACHE_NODE                = 6,
 
         PERF_COUNT_HW_CACHE_MAX,                /* non-ABI */
 };
@@ -536,6 +537,16 @@ struct perf_branch_stack {
 
 struct task_struct;
 
+/*
+ * extra PMU register associated with an event
+ */
+struct hw_perf_event_extra {
+        u64             config; /* register value */
+        unsigned int    reg;    /* register address or index */
+        int             alloc;  /* extra register already allocated */
+        int             idx;    /* index in shared_regs->regs[] */
+};
+
 /**
  * struct hw_perf_event - performance event hardware details:
  */
@@ -549,9 +560,7 @@ struct hw_perf_event {
                         unsigned long   event_base;
                         int             idx;
                         int             last_cpu;
-                        unsigned int    extra_reg;
-                        u64             extra_config;
-                        int             extra_alloc;
+                        struct hw_perf_event_extra extra_reg;
                 };
                 struct { /* software */
                         struct hrtimer  hrtimer;
@@ -680,36 +689,9 @@ enum perf_event_active_state {
 };
 
 struct file;
-
-#define PERF_BUFFER_WRITABLE            0x01
-
-struct perf_buffer {
-        atomic_t                        refcount;
-        struct rcu_head                 rcu_head;
-#ifdef CONFIG_PERF_USE_VMALLOC
-        struct work_struct              work;
-        int                             page_order;     /* allocation order  */
-#endif
-        int                             nr_pages;       /* nr of data pages  */
-        int                             writable;       /* are we writable   */
-
-        atomic_t                        poll;           /* POLL_ for wakeups */
-
-        local_t                         head;           /* write position    */
-        local_t                         nest;           /* nested writers    */
-        local_t                         events;         /* event limit       */
-        local_t                         wakeup;         /* wakeup stamp      */
-        local_t                         lost;           /* nr records lost   */
-
-        long                            watermark;      /* wakeup watermark  */
-
-        struct perf_event_mmap_page     *user_page;
-        void                            *data_pages[0];
-};
-
 struct perf_sample_data;
 
-typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
+typedef void (*perf_overflow_handler_t)(struct perf_event *,
                                         struct perf_sample_data *,
                                         struct pt_regs *regs);
 
@@ -745,6 +727,8 @@ struct perf_cgroup {
 };
 #endif
 
+struct ring_buffer;
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -834,7 +818,7 @@ struct perf_event {
         atomic_t                        mmap_count;
         int                             mmap_locked;
         struct user_struct              *mmap_user;
-        struct perf_buffer              *buffer;
+        struct ring_buffer              *rb;
 
         /* poll related */
         wait_queue_head_t               waitq;
@@ -855,6 +839,7 @@ struct perf_event {
         u64                             id;
 
         perf_overflow_handler_t         overflow_handler;
+        void                            *overflow_handler_context;
 
 #ifdef CONFIG_EVENT_TRACING
         struct ftrace_event_call        *tp_event;
@@ -919,8 +904,8 @@ struct perf_event_context {
         u64                             parent_gen;
         u64                             generation;
         int                             pin_count;
-        struct rcu_head                 rcu_head;
         int                             nr_cgroups; /* cgroup events present */
+        struct rcu_head                 rcu_head;
 };
 
 /*
@@ -945,13 +930,11 @@ struct perf_cpu_context {
 
 struct perf_output_handle {
         struct perf_event               *event;
-        struct perf_buffer              *buffer;
+        struct ring_buffer              *rb;
         unsigned long                   wakeup;
         unsigned long                   size;
         void                            *addr;
         int                             page;
-        int                             nmi;
-        int                             sample;
 };
 
 #ifdef CONFIG_PERF_EVENTS
@@ -972,13 +955,15 @@ 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 int perf_event_refresh(struct perf_event *event, int refresh);
 extern void perf_event_update_userpage(struct perf_event *event);
 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,
                                 struct task_struct *task,
-                                perf_overflow_handler_t callback);
+                                perf_overflow_handler_t callback,
+                                void *context);
 extern u64 perf_event_read_value(struct perf_event *event,
                                  u64 *enabled, u64 *running);
 
@@ -1018,7 +1003,7 @@ extern void perf_prepare_sample(struct perf_event_header *header,
                                 struct perf_event *event,
                                 struct pt_regs *regs);
 
-extern int perf_event_overflow(struct perf_event *event, int nmi,
+extern int perf_event_overflow(struct perf_event *event,
                                  struct perf_sample_data *data,
                                  struct pt_regs *regs);
 
@@ -1037,7 +1022,7 @@ static inline int is_software_event(struct perf_event *event)
 
 extern struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
 
-extern void __perf_sw_event(u32, u64, int, struct pt_regs *, u64);
+extern void __perf_sw_event(u32, u64, struct pt_regs *, u64);
 
 #ifndef perf_arch_fetch_caller_regs
 static inline void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip) { }
@@ -1059,7 +1044,7 @@ static inline void perf_fetch_caller_regs(struct pt_regs *regs)
 }
 
 static __always_inline void
-perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
+perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)
 {
         struct pt_regs hot_regs;
 
@@ -1068,7 +1053,7 @@ perf_sw_event(u32 event_id, u64 nr, int nmi, struct pt_regs *regs, u64 addr)
                         perf_fetch_caller_regs(&hot_regs);
                         regs = &hot_regs;
                 }
-                __perf_sw_event(event_id, nr, nmi, regs, addr);
+                __perf_sw_event(event_id, nr, regs, addr);
         }
 }
 
@@ -1082,7 +1067,7 @@ 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)
 {
-        perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
+        perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, NULL, 0);
 
         __perf_event_task_sched_out(task, next);
 }
@@ -1143,8 +1128,7 @@ extern void perf_bp_event(struct perf_event *event, void *data);
 #endif
 
 extern int perf_output_begin(struct perf_output_handle *handle,
-                             struct perf_event *event, unsigned int size,
-                             int nmi, int sample);
+                             struct perf_event *event, unsigned int size);
 extern void perf_output_end(struct perf_output_handle *handle);
 extern void perf_output_copy(struct perf_output_handle *handle,
                              const void *buf, unsigned int len);
@@ -1166,10 +1150,13 @@ static inline void perf_event_delayed_put(struct task_struct *task)	{ }
 static inline void perf_event_print_debug(void)                         { }
 static inline int perf_event_task_disable(void)                         { return -EINVAL; }
 static inline int perf_event_task_enable(void)                          { return -EINVAL; }
+static inline int perf_event_refresh(struct perf_event *event, int refresh)
+{
+        return -EINVAL;
+}
 
 static inline void
-perf_sw_event(u32 event_id, u64 nr, int nmi,
-                     struct pt_regs *regs, u64 addr)                    { }
+perf_sw_event(u32 event_id, u64 nr, struct pt_regs *regs, u64 addr)     { }
 static inline void
 perf_bp_event(struct perf_event *event, void *data)                     { }
 
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index ab38ac80b0f9..b891de96000f 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -169,7 +169,7 @@ void ring_buffer_set_clock(struct ring_buffer *buffer,
 size_t ring_buffer_page_len(void *page);
 
 
-void *ring_buffer_alloc_read_page(struct ring_buffer *buffer);
+void *ring_buffer_alloc_read_page(struct ring_buffer *buffer, int cpu);
 void ring_buffer_free_read_page(struct ring_buffer *buffer, void *data);
 int ring_buffer_read_page(struct ring_buffer *buffer, void **data_page,
                           size_t len, int cpu, int full);
diff --git a/include/linux/stacktrace.h b/include/linux/stacktrace.h
index 25310f1d7f37..115b570e3bff 100644
--- a/include/linux/stacktrace.h
+++ b/include/linux/stacktrace.h
@@ -14,8 +14,8 @@ struct stack_trace {
 };
 
 extern void save_stack_trace(struct stack_trace *trace);
-extern void save_stack_trace_regs(struct stack_trace *trace,
-                                  struct pt_regs *regs);
+extern void save_stack_trace_regs(struct pt_regs *regs,
+                                  struct stack_trace *trace);
 extern void save_stack_trace_tsk(struct task_struct *tsk,
                                 struct stack_trace *trace);