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: (184 commits)
  perf probe: Clean up probe_point_lazy_walker() return value
  tracing: Fix irqoff selftest expanding max buffer
  tracing: Align 4 byte ints together in struct tracer
  tracing: Export trace_set_clr_event()
  tracing: Explain about unstable clock on resume with ring buffer warning
  ftrace/graph: Trace function entry before updating index
  ftrace: Add .ref.text as one of the safe areas to trace
  tracing: Adjust conditional expression latency formatting.
  tracing: Fix event alignment: skb:kfree_skb
  tracing: Fix event alignment: mce:mce_record
  tracing: Fix event alignment: kvm:kvm_hv_hypercall
  tracing: Fix event alignment: module:module_request
  tracing: Fix event alignment: ftrace:context_switch and ftrace:wakeup
  tracing: Remove lock_depth from event entry
  perf header: Stop using 'self'
  perf session: Use evlist/evsel for managing perf.data attributes
  perf top: Don't let events to eat up whole header line
  perf top: Fix events overflow in top command
  ring-buffer: Remove unused #include <linux/trace_irq.h>
  tracing: Add an 'overwrite' trace_option.
  ...

13 files changed, 77 insertions, 28 deletions

diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index b3bfabc258f3..c1a1216e29ce 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -11,6 +11,7 @@ extern char _sinittext[], _einittext[];
 extern char _end[];
 extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
 extern char __kprobes_text_start[], __kprobes_text_end[];
+extern char __entry_text_start[], __entry_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __start_rodata[], __end_rodata[];
 
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index fe77e3395b40..906c3ceca9a2 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -424,6 +424,12 @@
                 *(.kprobes.text)                                        \
                 VMLINUX_SYMBOL(__kprobes_text_end) = .;
 
+#define ENTRY_TEXT                                                      \
+                ALIGN_FUNCTION();                                       \
+                VMLINUX_SYMBOL(__entry_text_start) = .;                 \
+                *(.entry.text)                                          \
+                VMLINUX_SYMBOL(__entry_text_end) = .;
+
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 #define IRQENTRY_TEXT                                                   \
                 ALIGN_FUNCTION();                                       \
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index ce104e33cd22..e654fa239916 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -474,7 +474,8 @@ struct cgroup_subsys {
                         struct cgroup *old_cgrp, struct task_struct *tsk,
                         bool threadgroup);
         void (*fork)(struct cgroup_subsys *ss, struct task_struct *task);
-        void (*exit)(struct cgroup_subsys *ss, struct task_struct *task);
+        void (*exit)(struct cgroup_subsys *ss, struct cgroup *cgrp,
+                        struct cgroup *old_cgrp, struct task_struct *task);
         int (*populate)(struct cgroup_subsys *ss,
                         struct cgroup *cgrp);
         void (*post_clone)(struct cgroup_subsys *ss, struct cgroup *cgrp);
@@ -626,6 +627,7 @@ bool css_is_ancestor(struct cgroup_subsys_state *cg,
 /* Get id and depth of css */
 unsigned short css_id(struct cgroup_subsys_state *css);
 unsigned short css_depth(struct cgroup_subsys_state *css);
+struct cgroup_subsys_state *cgroup_css_from_dir(struct file *f, int id);
 
 #else /* !CONFIG_CGROUPS */
 
diff --git a/include/linux/cgroup_subsys.h b/include/linux/cgroup_subsys.h
index ccefff02b6cb..cdbfcb8780ec 100644
--- a/include/linux/cgroup_subsys.h
+++ b/include/linux/cgroup_subsys.h
@@ -65,4 +65,8 @@ SUBSYS(net_cls)
 SUBSYS(blkio)
 #endif
 
+#ifdef CONFIG_CGROUP_PERF
+SUBSYS(perf)
+#endif
+
 /* */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index dcd6a7c3a435..ca29e03c1fac 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -428,6 +428,7 @@ extern void unregister_ftrace_graph(void);
 
 extern void ftrace_graph_init_task(struct task_struct *t);
 extern void ftrace_graph_exit_task(struct task_struct *t);
+extern void ftrace_graph_init_idle_task(struct task_struct *t, int cpu);
 
 static inline int task_curr_ret_stack(struct task_struct *t)
 {
@@ -451,6 +452,7 @@ static inline void unpause_graph_tracing(void)
 
 static inline void ftrace_graph_init_task(struct task_struct *t) { }
 static inline void ftrace_graph_exit_task(struct task_struct *t) { }
+static inline void ftrace_graph_init_idle_task(struct task_struct *t, int cpu) { }
 
 static inline int register_ftrace_graph(trace_func_graph_ret_t retfunc,
                           trace_func_graph_ent_t entryfunc)
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 47e3997f7b5c..22b32af1b5ec 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -37,7 +37,6 @@ struct trace_entry {
         unsigned char           flags;
         unsigned char           preempt_count;
         int                     pid;
-        int                     lock_depth;
 };
 
 #define FTRACE_MAX_EVENT                                                \
@@ -208,7 +207,6 @@ struct ftrace_event_call {
 
 #define PERF_MAX_TRACE_SIZE     2048
 
-#define MAX_FILTER_PRED         32
 #define MAX_FILTER_STR_VAL      256     /* Should handle KSYM_SYMBOL_LEN */
 
 extern void destroy_preds(struct ftrace_event_call *call);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index dda5b0a3ff60..614615b8d42b 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -225,8 +225,14 @@ struct perf_event_attr {
         };
 
         __u32                   bp_type;
-        __u64                   bp_addr;
-        __u64                   bp_len;
+        union {
+                __u64           bp_addr;
+                __u64           config1; /* extension of config */
+        };
+        union {
+                __u64           bp_len;
+                __u64           config2; /* extension of config1 */
+        };
 };
 
 /*
@@ -464,6 +470,7 @@ enum perf_callchain_context {
 
 #define PERF_FLAG_FD_NO_GROUP   (1U << 0)
 #define PERF_FLAG_FD_OUTPUT     (1U << 1)
+#define PERF_FLAG_PID_CGROUP    (1U << 2) /* pid=cgroup id, per-cpu mode only */
 
 #ifdef __KERNEL__
 /*
@@ -471,6 +478,7 @@ enum perf_callchain_context {
  */
 
 #ifdef CONFIG_PERF_EVENTS
+# include <linux/cgroup.h>
 # include <asm/perf_event.h>
 # include <asm/local64.h>
 #endif
@@ -539,6 +547,9 @@ struct hw_perf_event {
                         unsigned long   event_base;
                         int             idx;
                         int             last_cpu;
+                        unsigned int    extra_reg;
+                        u64             extra_config;
+                        int             extra_alloc;
                 };
                 struct { /* software */
                         struct hrtimer  hrtimer;
@@ -716,6 +727,22 @@ struct swevent_hlist {
 #define PERF_ATTACH_GROUP       0x02
 #define PERF_ATTACH_TASK        0x04
 
+#ifdef CONFIG_CGROUP_PERF
+/*
+ * perf_cgroup_info keeps track of time_enabled for a cgroup.
+ * This is a per-cpu dynamically allocated data structure.
+ */
+struct perf_cgroup_info {
+        u64 time;
+        u64 timestamp;
+};
+
+struct perf_cgroup {
+        struct cgroup_subsys_state css;
+        struct perf_cgroup_info *info;  /* timing info, one per cpu */
+};
+#endif
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -832,6 +859,11 @@ struct perf_event {
         struct event_filter             *filter;
 #endif
 
+#ifdef CONFIG_CGROUP_PERF
+        struct perf_cgroup              *cgrp; /* cgroup event is attach to */
+        int                             cgrp_defer_enabled;
+#endif
+
 #endif /* CONFIG_PERF_EVENTS */
 };
 
@@ -886,6 +918,7 @@ struct perf_event_context {
         u64                             generation;
         int                             pin_count;
         struct rcu_head                 rcu_head;
+        int                             nr_cgroups; /* cgroup events present */
 };
 
 /*
@@ -905,6 +938,9 @@ struct perf_cpu_context {
         struct list_head                rotation_list;
         int                             jiffies_interval;
         struct pmu                      *active_pmu;
+#ifdef CONFIG_CGROUP_PERF
+        struct perf_cgroup              *cgrp;
+#endif
 };
 
 struct perf_output_handle {
@@ -1040,11 +1076,11 @@ have_event:
         __perf_sw_event(event_id, nr, nmi, regs, addr);
 }
 
-extern atomic_t perf_task_events;
+extern atomic_t perf_sched_events;
 
 static inline void perf_event_task_sched_in(struct task_struct *task)
 {
-        COND_STMT(&perf_task_events, __perf_event_task_sched_in(task));
+        COND_STMT(&perf_sched_events, __perf_event_task_sched_in(task));
 }
 
 static inline
@@ -1052,7 +1088,7 @@ void perf_event_task_sched_out(struct task_struct *task, struct task_struct *nex
 {
         perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
-        COND_STMT(&perf_task_events, __perf_event_task_sched_out(task, next));
+        COND_STMT(&perf_sched_events, __perf_event_task_sched_out(task, next));
 }
 
 extern void perf_event_mmap(struct vm_area_struct *vma);
@@ -1083,6 +1119,10 @@ extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
 
+extern int perf_proc_update_handler(struct ctl_table *table, int write,
+                void __user *buffer, size_t *lenp,
+                loff_t *ppos);
+
 static inline bool perf_paranoid_tracepoint_raw(void)
 {
         return sysctl_perf_event_paranoid > -1;
diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index 8d3a2486544d..ab38ac80b0f9 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -100,6 +100,8 @@ void ring_buffer_free(struct ring_buffer *buffer);
 
 int ring_buffer_resize(struct ring_buffer *buffer, unsigned long size);
 
+void ring_buffer_change_overwrite(struct ring_buffer *buffer, int val);
+
 struct ring_buffer_event *ring_buffer_lock_reserve(struct ring_buffer *buffer,
                                                    unsigned long length);
 int ring_buffer_unlock_commit(struct ring_buffer *buffer,
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 777d8a5ed06b..c57e5278df83 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2578,13 +2578,6 @@ static inline void inc_syscw(struct task_struct *tsk)
 #define TASK_SIZE_OF(tsk)       TASK_SIZE
 #endif
 
-/*
- * Call the function if the target task is executing on a CPU right now:
- */
-extern void task_oncpu_function_call(struct task_struct *p,
-                                     void (*func) (void *info), void *info);
-
-
 #ifdef CONFIG_MM_OWNER
 extern void mm_update_next_owner(struct mm_struct *mm);
 extern void mm_init_owner(struct mm_struct *mm, struct task_struct *p);
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 2d9b79c0f224..4acc6b6088b0 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -133,11 +133,11 @@ extern struct trace_event_functions exit_syscall_print_funcs;
                 .class                  = &event_class_syscall_enter,   \
                 .event.funcs            = &enter_syscall_print_funcs,   \
                 .data                   = (void *)&__syscall_meta_##sname,\
+                .flags                  = TRACE_EVENT_FL_CAP_ANY,       \
         };                                                              \
         static struct ftrace_event_call __used                          \
           __attribute__((section("_ftrace_events")))                    \
-         *__event_enter_##sname = &event_enter_##sname;                 \
-        __TRACE_EVENT_FLAGS(enter_##sname, TRACE_EVENT_FL_CAP_ANY)
+         *__event_enter_##sname = &event_enter_##sname;
 
 #define SYSCALL_TRACE_EXIT_EVENT(sname)                                 \
         static struct syscall_metadata __syscall_meta_##sname;          \
@@ -147,11 +147,11 @@ extern struct trace_event_functions exit_syscall_print_funcs;
                 .class                  = &event_class_syscall_exit,    \
                 .event.funcs            = &exit_syscall_print_funcs,    \
                 .data                   = (void *)&__syscall_meta_##sname,\
+                .flags                  = TRACE_EVENT_FL_CAP_ANY,       \
         };                                                              \
         static struct ftrace_event_call __used                          \
           __attribute__((section("_ftrace_events")))                    \
-        *__event_exit_##sname = &event_exit_##sname;                    \
-        __TRACE_EVENT_FLAGS(exit_##sname, TRACE_EVENT_FL_CAP_ANY)
+        *__event_exit_##sname = &event_exit_##sname;
 
 #define SYSCALL_METADATA(sname, nb)                             \
         SYSCALL_TRACE_ENTER_EVENT(sname);                       \
@@ -159,6 +159,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
         static struct syscall_metadata __used                   \
           __syscall_meta_##sname = {                            \
                 .name           = "sys"#sname,                  \
+                .syscall_nr     = -1,   /* Filled in at boot */ \
                 .nb_args        = nb,                           \
                 .types          = types_##sname,                \
                 .args           = args_##sname,                 \
@@ -176,6 +177,7 @@ extern struct trace_event_functions exit_syscall_print_funcs;
         static struct syscall_metadata __used                   \
           __syscall_meta__##sname = {                           \
                 .name           = "sys_"#sname,                 \
+                .syscall_nr     = -1,   /* Filled in at boot */ \
                 .nb_args        = 0,                            \
                 .enter_event    = &event_enter__##sname,        \
                 .exit_event     = &event_exit__##sname,         \
diff --git a/include/trace/events/mce.h b/include/trace/events/mce.h
index 7eee77895cb3..4cbbcef6baa8 100644
--- a/include/trace/events/mce.h
+++ b/include/trace/events/mce.h
@@ -17,36 +17,36 @@ TRACE_EVENT(mce_record,
         TP_STRUCT__entry(
                 __field(        u64,            mcgcap          )
                 __field(        u64,            mcgstatus       )
-                __field(        u8,             bank            )
                 __field(        u64,            status          )
                 __field(        u64,            addr            )
                 __field(        u64,            misc            )
                 __field(        u64,            ip              )
-                __field(        u8,             cs              )
                 __field(        u64,            tsc             )
                 __field(        u64,            walltime        )
                 __field(        u32,            cpu             )
                 __field(        u32,            cpuid           )
                 __field(        u32,            apicid          )
                 __field(        u32,            socketid        )
+                __field(        u8,             cs              )
+                __field(        u8,             bank            )
                 __field(        u8,             cpuvendor       )
         ),
 
         TP_fast_assign(
                 __entry->mcgcap         = m->mcgcap;
                 __entry->mcgstatus      = m->mcgstatus;
-                __entry->bank           = m->bank;
                 __entry->status         = m->status;
                 __entry->addr           = m->addr;
                 __entry->misc           = m->misc;
                 __entry->ip             = m->ip;
-                __entry->cs             = m->cs;
                 __entry->tsc            = m->tsc;
                 __entry->walltime       = m->time;
                 __entry->cpu            = m->extcpu;
                 __entry->cpuid          = m->cpuid;
                 __entry->apicid         = m->apicid;
                 __entry->socketid       = m->socketid;
+                __entry->cs             = m->cs;
+                __entry->bank           = m->bank;
                 __entry->cpuvendor      = m->cpuvendor;
         ),
 
diff --git a/include/trace/events/module.h b/include/trace/events/module.h
index c6bae36547e5..21a546d27c0c 100644
--- a/include/trace/events/module.h
+++ b/include/trace/events/module.h
@@ -108,14 +108,14 @@ TRACE_EVENT(module_request,
         TP_ARGS(name, wait, ip),
 
         TP_STRUCT__entry(
-                __field(        bool,           wait            )
                 __field(        unsigned long,  ip              )
+                __field(        bool,           wait            )
                 __string(       name,           name            )
         ),
 
         TP_fast_assign(
-                __entry->wait   = wait;
                 __entry->ip     = ip;
+                __entry->wait   = wait;
                 __assign_str(name, name);
         ),
 
@@ -129,4 +129,3 @@ TRACE_EVENT(module_request,
 
 /* This part must be outside protection */
 #include <trace/define_trace.h>
-
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index f10293c41b1e..0c68ae22da22 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -19,14 +19,14 @@ TRACE_EVENT(kfree_skb,
 
         TP_STRUCT__entry(
                 __field(        void *,         skbaddr         )
-                __field(        unsigned short, protocol        )
                 __field(        void *,         location        )
+                __field(        unsigned short, protocol        )
         ),
 
         TP_fast_assign(
                 __entry->skbaddr = skb;
-                __entry->protocol = ntohs(skb->protocol);
                 __entry->location = location;
+                __entry->protocol = ntohs(skb->protocol);
         ),
 
         TP_printk("skbaddr=%p protocol=%u location=%p",