Merge branch 'perf/core' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip into trace/tip/tracing/core-6

Conflicts:
	include/trace/ftrace.h
	kernel/trace/trace_kprobe.c

Acked-by: Masami Hiramatsu <mhiramat@redhat.com>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

12 files changed, 142 insertions, 94 deletions

diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index e0ae83bbd9cc..41e46330d9be 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -519,18 +519,6 @@ extern enum ftrace_dump_mode ftrace_dump_on_oops;
 #define INIT_TRACE_RECURSION
 #endif
 
-#ifdef CONFIG_HW_BRANCH_TRACER
-
-void trace_hw_branch(u64 from, u64 to);
-void trace_hw_branch_oops(void);
-
-#else /* CONFIG_HW_BRANCH_TRACER */
-
-static inline void trace_hw_branch(u64 from, u64 to) {}
-static inline void trace_hw_branch_oops(void) {}
-
-#endif /* CONFIG_HW_BRANCH_TRACER */
-
 #ifdef CONFIG_FTRACE_SYSCALLS
 
 unsigned long arch_syscall_addr(int nr);
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index c70d27af03f9..a2d6ea49ec56 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -9,9 +9,22 @@ enum {
 };
 
 enum {
-	HW_BREAKPOINT_R = 1,
-	HW_BREAKPOINT_W = 2,
-	HW_BREAKPOINT_X = 4,
+	HW_BREAKPOINT_EMPTY	= 0,
+	HW_BREAKPOINT_R		= 1,
+	HW_BREAKPOINT_W		= 2,
+	HW_BREAKPOINT_RW	= HW_BREAKPOINT_R | HW_BREAKPOINT_W,
+	HW_BREAKPOINT_X		= 4,
+	HW_BREAKPOINT_INVALID   = HW_BREAKPOINT_RW | HW_BREAKPOINT_X,
+};
+
+enum bp_type_idx {
+	TYPE_INST 	= 0,
+#ifdef CONFIG_HAVE_MIXED_BREAKPOINTS_REGS
+	TYPE_DATA	= 0,
+#else
+	TYPE_DATA	= 1,
+#endif
+	TYPE_MAX
 };
 
 #ifdef __KERNEL__
@@ -34,6 +47,12 @@ static inline void hw_breakpoint_init(struct perf_event_attr *attr)
 	attr->sample_period = 1;
 }
 
+static inline void ptrace_breakpoint_init(struct perf_event_attr *attr)
+{
+	hw_breakpoint_init(attr);
+	attr->exclude_kernel = 1;
+}
+
 static inline unsigned long hw_breakpoint_addr(struct perf_event *bp)
 {
 	return bp->attr.bp_addr;
diff --git a/include/linux/i2c.h b/include/linux/i2c.h
index 0a5da639b327..6ed1d59bfb1e 100644
--- a/include/linux/i2c.h
+++ b/include/linux/i2c.h
@@ -355,6 +355,8 @@ struct i2c_adapter {
 	int nr;
 	char name[48];
 	struct completion dev_released;
+
+	struct list_head userspace_clients;
 };
 #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev)
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 462acaf36f3a..fb19bb92b809 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -19,7 +19,6 @@ struct anon_vma;
 struct file_ra_state;
 struct user_struct;
 struct writeback_control;
-struct rlimit;
 
 #ifndef CONFIG_DISCONTIGMEM          /* Don't use mapnrs, do it properly */
 extern unsigned long max_mapnr;
@@ -1449,9 +1448,6 @@ int vmemmap_populate_basepages(struct page *start_page,
 int vmemmap_populate(struct page *start_page, unsigned long pages, int node);
 void vmemmap_populate_print_last(void);
 
-extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
-				 size_t size);
-extern void refund_locked_memory(struct mm_struct *mm, size_t size);
 
 enum mf_flags {
 	MF_COUNT_INCREASED = 1 << 0,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c8e375440403..3fd5c82e0e18 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -203,8 +203,19 @@ struct perf_event_attr {
 				enable_on_exec :  1, /* next exec enables     */
 				task           :  1, /* trace fork/exit       */
 				watermark      :  1, /* wakeup_watermark      */
-
-				__reserved_1   : 49;
+				/*
+				 * precise_ip:
+				 *
+				 *  0 - SAMPLE_IP can have arbitrary skid
+				 *  1 - SAMPLE_IP must have constant skid
+				 *  2 - SAMPLE_IP requested to have 0 skid
+				 *  3 - SAMPLE_IP must have 0 skid
+				 *
+				 *  See also PERF_RECORD_MISC_EXACT_IP
+				 */
+				precise_ip     :  2, /* skid constraint       */
+
+				__reserved_1   : 47;
 
 	union {
 		__u32		wakeup_events;	  /* wakeup every n events */
@@ -287,11 +298,24 @@ struct perf_event_mmap_page {
 	__u64	data_tail;		/* user-space written tail */
 };
 
-#define PERF_RECORD_MISC_CPUMODE_MASK		(3 << 0)
+#define PERF_RECORD_MISC_CPUMODE_MASK		(7 << 0)
 #define PERF_RECORD_MISC_CPUMODE_UNKNOWN	(0 << 0)
 #define PERF_RECORD_MISC_KERNEL			(1 << 0)
 #define PERF_RECORD_MISC_USER			(2 << 0)
 #define PERF_RECORD_MISC_HYPERVISOR		(3 << 0)
+#define PERF_RECORD_MISC_GUEST_KERNEL		(4 << 0)
+#define PERF_RECORD_MISC_GUEST_USER		(5 << 0)
+
+/*
+ * Indicates that the content of PERF_SAMPLE_IP points to
+ * the actual instruction that triggered the event. See also
+ * perf_event_attr::precise_ip.
+ */
+#define PERF_RECORD_MISC_EXACT_IP		(1 << 14)
+/*
+ * Reserve the last bit to indicate some extended misc field
+ */
+#define PERF_RECORD_MISC_EXT_RESERVED		(1 << 15)
 
 struct perf_event_header {
 	__u32	type;
@@ -439,6 +463,12 @@ enum perf_callchain_context {
 # include <asm/perf_event.h>
 #endif
 
+struct perf_guest_info_callbacks {
+	int (*is_in_guest) (void);
+	int (*is_user_mode) (void);
+	unsigned long (*get_guest_ip) (void);
+};
+
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 #include <asm/hw_breakpoint.h>
 #endif
@@ -468,6 +498,17 @@ struct perf_raw_record {
 	void				*data;
 };
 
+struct perf_branch_entry {
+	__u64				from;
+	__u64				to;
+	__u64				flags;
+};
+
+struct perf_branch_stack {
+	__u64				nr;
+	struct perf_branch_entry	entries[0];
+};
+
 struct task_struct;
 
 /**
@@ -506,6 +547,8 @@ struct hw_perf_event {
 
 struct perf_event;
 
+#define PERF_EVENT_TXN_STARTED 1
+
 /**
  * struct pmu - generic performance monitoring unit
  */
@@ -516,6 +559,16 @@ struct pmu {
 	void (*stop)			(struct perf_event *event);
 	void (*read)			(struct perf_event *event);
 	void (*unthrottle)		(struct perf_event *event);
+
+	/*
+	 * group events scheduling is treated as a transaction,
+	 * add group events as a whole and perform one schedulability test.
+	 * If test fails, roll back the whole group
+	 */
+
+	void (*start_txn)	(const struct pmu *pmu);
+	void (*cancel_txn)	(const struct pmu *pmu);
+	int  (*commit_txn)	(const struct pmu *pmu);
 };
 
 /**
@@ -571,6 +624,14 @@ enum perf_group_flag {
 	PERF_GROUP_SOFTWARE = 0x1,
 };
 
+#define SWEVENT_HLIST_BITS	8
+#define SWEVENT_HLIST_SIZE	(1 << SWEVENT_HLIST_BITS)
+
+struct swevent_hlist {
+	struct hlist_head	heads[SWEVENT_HLIST_SIZE];
+	struct rcu_head		rcu_head;
+};
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -579,6 +640,7 @@ struct perf_event {
 	struct list_head		group_entry;
 	struct list_head		event_entry;
 	struct list_head		sibling_list;
+	struct hlist_node		hlist_entry;
 	int				nr_siblings;
 	int				group_flags;
 	struct perf_event		*group_leader;
@@ -726,6 +788,9 @@ struct perf_cpu_context {
 	int				active_oncpu;
 	int				max_pertask;
 	int				exclusive;
+	struct swevent_hlist		*swevent_hlist;
+	struct mutex			hlist_mutex;
+	int				hlist_refcount;
 
 	/*
 	 * Recursion avoidance:
@@ -769,9 +834,6 @@ extern void perf_disable(void);
 extern void perf_enable(void);
 extern int perf_event_task_disable(void);
 extern int perf_event_task_enable(void);
-extern int hw_perf_group_sched_in(struct perf_event *group_leader,
-	       struct perf_cpu_context *cpuctx,
-	       struct perf_event_context *ctx);
 extern void perf_event_update_userpage(struct perf_event *event);
 extern int perf_event_release_kernel(struct perf_event *event);
 extern struct perf_event *
@@ -902,6 +964,10 @@ static inline void perf_event_mmap(struct vm_area_struct *vma)
 		__perf_event_mmap(vma);
 }
 
+extern struct perf_guest_info_callbacks *perf_guest_cbs;
+extern int perf_register_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
+extern int perf_unregister_guest_info_callbacks(struct perf_guest_info_callbacks *callbacks);
+
 extern void perf_event_comm(struct task_struct *tsk);
 extern void perf_event_fork(struct task_struct *tsk);
 
@@ -971,6 +1037,11 @@ perf_sw_event(u32 event_id, u64 nr, int nmi,
 static inline void
 perf_bp_event(struct perf_event *event, void *data)			{ }
 
+static inline int perf_register_guest_info_callbacks
+(struct perf_guest_info_callbacks *callbacks) { return 0; }
+static inline int perf_unregister_guest_info_callbacks
+(struct perf_guest_info_callbacks *callbacks) { return 0; }
+
 static inline void perf_event_mmap(struct vm_area_struct *vma)		{ }
 static inline void perf_event_comm(struct task_struct *tsk)		{ }
 static inline void perf_event_fork(struct task_struct *tsk)		{ }
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index e1fb60729979..4272521e29e9 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -345,18 +345,6 @@ static inline void user_single_step_siginfo(struct task_struct *tsk,
 #define arch_ptrace_stop(code, info)		do { } while (0)
 #endif
 
-#ifndef arch_ptrace_untrace
-/*
- * Do machine-specific work before untracing child.
- *
- * This is called for a normal detach as well as from ptrace_exit()
- * when the tracing task dies.
- *
- * Called with write_lock(&tasklist_lock) held.
- */
-#define arch_ptrace_untrace(task)		do { } while (0)
-#endif
-
 extern int task_current_syscall(struct task_struct *target, long *callno,
 				unsigned long args[6], unsigned int maxargs,
 				unsigned long *sp, unsigned long *pc);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dfea40574b2a..2a5b146fbaf9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -99,7 +99,6 @@ struct futex_pi_state;
 struct robust_list_head;
 struct bio_list;
 struct fs_struct;
-struct bts_context;
 struct perf_event_context;
 
 /*
@@ -1275,12 +1274,6 @@ struct task_struct {
 	struct list_head ptraced;
 	struct list_head ptrace_entry;
 
-	/*
-	 * This is the tracer handle for the ptrace BTS extension.
-	 * This field actually belongs to the ptracer task.
-	 */
-	struct bts_context *bts;
-
 	/* PID/PID hash table linkage. */
 	struct pid_link pids[PIDTYPE_MAX];
 	struct list_head thread_group;
@@ -2127,10 +2120,8 @@ extern void set_task_comm(struct task_struct *tsk, char *from);
 extern char *get_task_comm(char *to, struct task_struct *tsk);
 
 #ifdef CONFIG_SMP
-extern void wait_task_context_switch(struct task_struct *p);
 extern unsigned long wait_task_inactive(struct task_struct *, long match_state);
 #else
-static inline void wait_task_context_switch(struct task_struct *p) {}
 static inline unsigned long wait_task_inactive(struct task_struct *p,
 					       long match_state)
 {
diff --git a/include/linux/usb.h b/include/linux/usb.h
index ce1323c4e47c..739f1fd1cc15 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1085,7 +1085,7 @@ typedef void (*usb_complete_t)(struct urb *);
  * Alternatively, drivers may pass the URB_NO_xxx_DMA_MAP transfer flags,
  * which tell the host controller driver that no such mapping is needed since
  * the device driver is DMA-aware.  For example, a device driver might
- * allocate a DMA buffer with usb_buffer_alloc() or call usb_buffer_map().
+ * allocate a DMA buffer with usb_alloc_coherent() or call usb_buffer_map().
  * When these transfer flags are provided, host controller drivers will
  * attempt to use the dma addresses found in the transfer_dma and/or
  * setup_dma fields rather than determining a dma address themselves.
@@ -1366,11 +1366,23 @@ static inline int usb_urb_dir_out(struct urb *urb)
 	return (urb->transfer_flags & URB_DIR_MASK) == URB_DIR_OUT;
 }
 
-void *usb_buffer_alloc(struct usb_device *dev, size_t size,
+void *usb_alloc_coherent(struct usb_device *dev, size_t size,
 	gfp_t mem_flags, dma_addr_t *dma);
-void usb_buffer_free(struct usb_device *dev, size_t size,
+void usb_free_coherent(struct usb_device *dev, size_t size,
 	void *addr, dma_addr_t dma);
 
+/* Compatible macros while we switch over */
+static inline void *usb_buffer_alloc(struct usb_device *dev, size_t size,
+				     gfp_t mem_flags, dma_addr_t *dma)
+{
+	return usb_alloc_coherent(dev, size, mem_flags, dma);
+}
+static inline void usb_buffer_free(struct usb_device *dev, size_t size,
+				   void *addr, dma_addr_t dma)
+{
+	return usb_free_coherent(dev, size, addr, dma);
+}
+
 #if 0
 struct urb *usb_buffer_map(struct urb *urb);
 void usb_buffer_dmasync(struct urb *urb);
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index ff3017744711..597f8e27aaf6 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -778,6 +778,7 @@ int sctp_user_addto_chunk(struct sctp_chunk *chunk, int off, int len,
 			  struct iovec *data);
 void sctp_chunk_free(struct sctp_chunk *);
 void  *sctp_addto_chunk(struct sctp_chunk *, int len, const void *data);
+void  *sctp_addto_chunk_fixed(struct sctp_chunk *, int len, const void *data);
 struct sctp_chunk *sctp_chunkify(struct sk_buff *,
 				 const struct sctp_association *,
 				 struct sock *);
diff --git a/include/net/sock.h b/include/net/sock.h
index b4603cd54fcd..1ad6435f252e 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -74,7 +74,7 @@
 					printk(KERN_DEBUG msg); } while (0)
 #else
 /* Validate arguments and do nothing */
-static void inline int __attribute__ ((format (printf, 2, 3)))
+static inline void __attribute__ ((format (printf, 2, 3)))
 SOCK_DEBUG(struct sock *sk, const char *msg, ...)
 {
 }
diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index 5c1dcfc16c60..2821b86de63b 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -35,15 +35,15 @@ TRACE_EVENT(lock_acquire,
 		  __get_str(name))
 );
 
-TRACE_EVENT(lock_release,
+DECLARE_EVENT_CLASS(lock,
 
-	TP_PROTO(struct lockdep_map *lock, int nested, unsigned long ip),
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-	TP_ARGS(lock, nested, ip),
+	TP_ARGS(lock, ip),
 
 	TP_STRUCT__entry(
-		__string(name, lock->name)
-		__field(void *, lockdep_addr)
+		__string(	name, 	lock->name	)
+		__field(	void *, lockdep_addr	)
 	),
 
 	TP_fast_assign(
@@ -51,51 +51,30 @@ TRACE_EVENT(lock_release,
 		__entry->lockdep_addr = lock;
 	),
 
-	TP_printk("%p %s",
-		  __entry->lockdep_addr, __get_str(name))
+	TP_printk("%p %s",  __entry->lockdep_addr, __get_str(name))
 );
 
-#ifdef CONFIG_LOCK_STAT
-
-TRACE_EVENT(lock_contended,
+DEFINE_EVENT(lock, lock_release,
 
 	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-	TP_ARGS(lock, ip),
+	TP_ARGS(lock, ip)
+);
 
-	TP_STRUCT__entry(
-		__string(name, lock->name)
-		__field(void *, lockdep_addr)
-	),
+#ifdef CONFIG_LOCK_STAT
 
-	TP_fast_assign(
-		__assign_str(name, lock->name);
-		__entry->lockdep_addr = lock;
-	),
+DEFINE_EVENT(lock, lock_contended,
 
-	TP_printk("%p %s",
-		  __entry->lockdep_addr, __get_str(name))
-);
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-TRACE_EVENT(lock_acquired,
-	TP_PROTO(struct lockdep_map *lock, unsigned long ip, s64 waittime),
+	TP_ARGS(lock, ip)
+);
 
-	TP_ARGS(lock, ip, waittime),
+DEFINE_EVENT(lock, lock_acquired,
 
-	TP_STRUCT__entry(
-		__string(name, lock->name)
-		__field(s64, wait_nsec)
-		__field(void *, lockdep_addr)
-	),
+	TP_PROTO(struct lockdep_map *lock, unsigned long ip),
 
-	TP_fast_assign(
-		__assign_str(name, lock->name);
-		__entry->wait_nsec = waittime;
-		__entry->lockdep_addr = lock;
-	),
-	TP_printk("%p %s (%llu ns)", __entry->lockdep_addr,
-		  __get_str(name),
-		  __entry->wait_nsec)
+	TP_ARGS(lock, ip)
 );
 
 #endif
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 4866c109fa9a..e0e8daa6767e 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -695,13 +695,15 @@ perf_trace_##call(void *__data, proto)					\
 	struct ftrace_event_call *event_call = __data;			\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
 	struct ftrace_raw_##call *entry;				\
+	struct pt_regs *__regs = &get_cpu_var(perf_trace_regs);		\
 	u64 __addr = 0, __count = 1;					\
 	unsigned long irq_flags;					\
-	struct pt_regs *__regs;						\
 	int __entry_size;						\
 	int __data_size;						\
 	int rctx;							\
 									\
+	perf_fetch_caller_regs(__regs, 1);				\
+									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
 			     sizeof(u64));				\
@@ -709,20 +711,19 @@ perf_trace_##call(void *__data, proto)					\
 									\
 	if (WARN_ONCE(__entry_size > PERF_MAX_TRACE_SIZE,		\
 		      "profile buffer not large enough"))		\
-		return;							\
+		goto out;						\
 	entry = (struct ftrace_raw_##call *)perf_trace_buf_prepare(	\
 		__entry_size, event_call->event.type, &rctx, &irq_flags); \
 	if (!entry)							\
-		return;							\
+		goto out;						\
 	tstruct								\
 									\
 	{ assign; }							\
 									\
-	__regs = &__get_cpu_var(perf_trace_regs);			\
-	perf_fetch_caller_regs(__regs, 2);				\
-									\
 	perf_trace_buf_submit(entry, __entry_size, rctx, __addr,	\
 			       __count, irq_flags, __regs);		\
+ out:									\
+	put_cpu_var(perf_trace_regs);					\
 }
 
 /*