Merge branch 'perf/core' into perf/urgent

Merge reason: Switch from pre-merge topical split to the post-merge urgent track

Signed-off-by: Ingo Molnar <mingo@elte.hu>

23 files changed, 192 insertions, 112 deletions

diff --git a/include/drm/nouveau_drm.h b/include/drm/nouveau_drm.h
index 1e67c441ea82..f745948b61e4 100644
--- a/include/drm/nouveau_drm.h
+++ b/include/drm/nouveau_drm.h
@@ -77,6 +77,7 @@ struct drm_nouveau_gpuobj_free {
 #define NOUVEAU_GETPARAM_PCI_PHYSICAL    10
 #define NOUVEAU_GETPARAM_CHIPSET_ID      11
 #define NOUVEAU_GETPARAM_VM_VRAM_BASE    12
+#define NOUVEAU_GETPARAM_GRAPH_UNITS     13
 struct drm_nouveau_getparam {
 	uint64_t param;
 	uint64_t value;
diff --git a/include/drm/vmwgfx_drm.h b/include/drm/vmwgfx_drm.h
index 2be7e1249b6f..c7645f480d12 100644
--- a/include/drm/vmwgfx_drm.h
+++ b/include/drm/vmwgfx_drm.h
@@ -68,7 +68,8 @@
 #define DRM_VMW_PARAM_NUM_FREE_STREAMS 1
 #define DRM_VMW_PARAM_3D               2
 #define DRM_VMW_PARAM_FIFO_OFFSET      3
-
+#define DRM_VMW_PARAM_HW_CAPS          4
+#define DRM_VMW_PARAM_FIFO_CAPS        5
 
 /**
  * struct drm_vmw_getparam_arg
@@ -181,6 +182,8 @@ struct drm_vmw_context_arg {
  * The size of the array should equal the total number of mipmap levels.
  * @shareable: Boolean whether other clients (as identified by file descriptors)
  * may reference this surface.
+ * @scanout: Boolean whether the surface is intended to be used as a
+ * scanout.
  *
  * Input data to the DRM_VMW_CREATE_SURFACE Ioctl.
  * Output data from the DRM_VMW_REF_SURFACE Ioctl.
@@ -192,7 +195,7 @@ struct drm_vmw_surface_create_req {
 	uint32_t mip_levels[DRM_VMW_MAX_SURFACE_FACES];
 	uint64_t size_addr;
 	int32_t shareable;
-	uint32_t pad64;
+	int32_t scanout;
 };
 
 /**
@@ -295,17 +298,28 @@ union drm_vmw_surface_reference_arg {
  *
  * @commands: User-space address of a command buffer cast to an uint64_t.
  * @command-size: Size in bytes of the command buffer.
+ * @throttle-us: Sleep until software is less than @throttle_us
+ * microseconds ahead of hardware. The driver may round this value
+ * to the nearest kernel tick.
  * @fence_rep: User-space address of a struct drm_vmw_fence_rep cast to an
  * uint64_t.
+ * @version: Allows expanding the execbuf ioctl parameters without breaking
+ * backwards compatibility, since user-space will always tell the kernel
+ * which version it uses.
+ * @flags: Execbuf flags. None currently.
  *
  * Argument to the DRM_VMW_EXECBUF Ioctl.
  */
 
+#define DRM_VMW_EXECBUF_VERSION 0
+
 struct drm_vmw_execbuf_arg {
 	uint64_t commands;
 	uint32_t command_size;
-	uint32_t pad64;
+	uint32_t throttle_us;
 	uint64_t fence_rep;
+	 uint32_t version;
+	 uint32_t flags;
 };
 
 /**
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index ab94335b4bb9..6816be6c3f77 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -1,5 +1,9 @@
 /*
- *  linux/include/asm-arm/hardware/amba.h
+ *  linux/include/amba/bus.h
+ *
+ *  This device type deals with ARM PrimeCells and anything else that
+ *  presents a proper CID (0xB105F00D) at the end of the I/O register
+ *  region or that is derived from a PrimeCell.
  *
  *  Copyright (C) 2003 Deep Blue Solutions Ltd, All Rights Reserved.
  *
diff --git a/include/linux/ata.h b/include/linux/ata.h
index 38a6948ce0c2..20f31567ccee 100644
--- a/include/linux/ata.h
+++ b/include/linux/ata.h
@@ -647,9 +647,9 @@ static inline int ata_id_has_large_logical_sectors(const u16 *id)
 	return id[ATA_ID_SECTOR_SIZE] & (1 << 13);
 }
 
-static inline u8 ata_id_logical_per_physical_sectors(const u16 *id)
+static inline u16 ata_id_logical_per_physical_sectors(const u16 *id)
 {
-	return id[ATA_ID_SECTOR_SIZE] & 0xf;
+	return 1 << (id[ATA_ID_SECTOR_SIZE] & 0xf);
 }
 
 static inline int ata_id_has_lba48(const u16 *id)
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index c05a29cb9bb2..25b8b2f33ae9 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -25,7 +25,7 @@
 static __inline__ int get_bitmask_order(unsigned int count)
 {
 	int order;
-	
+
 	order = fls(count);
 	return order;	/* We could be slightly more clever with -1 here... */
 }
@@ -33,7 +33,7 @@ static __inline__ int get_bitmask_order(unsigned int count)
 static __inline__ int get_count_order(unsigned int count)
 {
 	int order;
-	
+
 	order = fls(count) - 1;
 	if (count & (count - 1))
 		order++;
@@ -45,6 +45,31 @@ static inline unsigned long hweight_long(unsigned long w)
 	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
 }
 
+/*
+ * Clearly slow versions of the hweightN() functions, their benefit is
+ * of course compile time evaluation of constant arguments.
+ */
+#define HWEIGHT8(w)					\
+      (	BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) +	\
+	(!!((w) & (1ULL << 0))) +			\
+	(!!((w) & (1ULL << 1))) +			\
+	(!!((w) & (1ULL << 2))) +			\
+	(!!((w) & (1ULL << 3))) +			\
+	(!!((w) & (1ULL << 4))) +			\
+	(!!((w) & (1ULL << 5))) +			\
+	(!!((w) & (1ULL << 6))) +			\
+	(!!((w) & (1ULL << 7)))	)
+
+#define HWEIGHT16(w) (HWEIGHT8(w)  + HWEIGHT8((w) >> 8))
+#define HWEIGHT32(w) (HWEIGHT16(w) + HWEIGHT16((w) >> 16))
+#define HWEIGHT64(w) (HWEIGHT32(w) + HWEIGHT32((w) >> 32))
+
+/*
+ * Type invariant version that simply casts things to the
+ * largest type.
+ */
+#define HWEIGHT(w)   HWEIGHT64((u64)(w))
+
 /**
  * rol32 - rotate a 32-bit value left
  * @word: value to rotate
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5c8018977efa..1896e868854f 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -461,8 +461,7 @@ struct request_queue
 #define QUEUE_FLAG_NONROT      14	/* non-rotational device (SSD) */
 #define QUEUE_FLAG_VIRT        QUEUE_FLAG_NONROT /* paravirt device */
 #define QUEUE_FLAG_IO_STAT     15	/* do IO stats */
-#define QUEUE_FLAG_CQ	       16	/* hardware does queuing */
-#define QUEUE_FLAG_DISCARD     17	/* supports DISCARD */
+#define QUEUE_FLAG_DISCARD     16	/* supports DISCARD */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
 				 (1 << QUEUE_FLAG_CLUSTER) |		\
@@ -586,7 +585,6 @@ enum {
 
 #define blk_queue_plugged(q)	test_bit(QUEUE_FLAG_PLUGGED, &(q)->queue_flags)
 #define blk_queue_tagged(q)	test_bit(QUEUE_FLAG_QUEUED, &(q)->queue_flags)
-#define blk_queue_queuing(q)	test_bit(QUEUE_FLAG_CQ, &(q)->queue_flags)
 #define blk_queue_stopped(q)	test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags)
 #define blk_queue_nomerges(q)	test_bit(QUEUE_FLAG_NOMERGES, &(q)->queue_flags)
 #define blk_queue_nonrot(q)	test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags)
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index 5be3dab4a695..188fcae10a99 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -15,6 +15,7 @@
 # define __acquire(x)	__context__(x,1)
 # define __release(x)	__context__(x,-1)
 # define __cond_lock(x,c)	((c) ? ({ __acquire(x); 1; }) : 0)
+# define __percpu	__attribute__((noderef, address_space(3)))
 extern void __chk_user_ptr(const volatile void __user *);
 extern void __chk_io_ptr(const volatile void __iomem *);
 #else
@@ -32,6 +33,7 @@ extern void __chk_io_ptr(const volatile void __iomem *);
 # define __acquire(x) (void)0
 # define __release(x) (void)0
 # define __cond_lock(x,c) (c)
+# define __percpu
 #endif
 
 #ifdef __KERNEL__
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b1bcb275b596..ebb1cd5bc241 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -729,6 +729,7 @@ struct inode {
 	uid_t			i_uid;
 	gid_t			i_gid;
 	dev_t			i_rdev;
+	unsigned int		i_blkbits;
 	u64			i_version;
 	loff_t			i_size;
 #ifdef __NEED_I_SIZE_ORDERED
@@ -738,7 +739,6 @@ struct inode {
 	struct timespec		i_mtime;
 	struct timespec		i_ctime;
 	blkcnt_t		i_blocks;
-	unsigned int		i_blkbits;
 	unsigned short          i_bytes;
 	umode_t			i_mode;
 	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index 0b4f97d24d7f..eb054ae95605 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -134,6 +134,8 @@ extern void
 unregister_ftrace_function_probe_func(char *glob, struct ftrace_probe_ops *ops);
 extern void unregister_ftrace_function_probe_all(char *glob);
 
+extern int ftrace_text_reserved(void *start, void *end);
+
 enum {
 	FTRACE_FL_FREE		= (1 << 0),
 	FTRACE_FL_FAILED	= (1 << 1),
@@ -141,7 +143,6 @@ enum {
 	FTRACE_FL_ENABLED	= (1 << 3),
 	FTRACE_FL_NOTRACE	= (1 << 4),
 	FTRACE_FL_CONVERTED	= (1 << 5),
-	FTRACE_FL_FROZEN	= (1 << 6),
 };
 
 struct dyn_ftrace {
@@ -250,6 +251,10 @@ static inline int unregister_ftrace_command(char *cmd_name)
 {
 	return -EINVAL;
 }
+static inline int ftrace_text_reserved(void *start, void *end)
+{
+	return 0;
+}
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 /* totally disable ftrace - can not re-enable after this */
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 2233c98d80df..cd95919d9ff3 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -5,6 +5,7 @@
 #include <linux/trace_seq.h>
 #include <linux/percpu.h>
 #include <linux/hardirq.h>
+#include <linux/perf_event.h>
 
 struct trace_array;
 struct tracer;
@@ -138,9 +139,6 @@ struct ftrace_event_call {
 
 #define FTRACE_MAX_PROFILE_SIZE	2048
 
-extern char *perf_trace_buf;
-extern char *perf_trace_buf_nmi;
-
 #define MAX_FILTER_PRED		32
 #define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
 
@@ -188,13 +186,27 @@ do {									\
 		__trace_printk(ip, fmt, ##args);			\
 } while (0)
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 struct perf_event;
 extern int ftrace_profile_enable(int event_id);
 extern void ftrace_profile_disable(int event_id);
 extern int ftrace_profile_set_filter(struct perf_event *event, int event_id,
 				     char *filter_str);
 extern void ftrace_profile_free_filter(struct perf_event *event);
+extern void *
+ftrace_perf_buf_prepare(int size, unsigned short type, int *rctxp,
+			 unsigned long *irq_flags);
+
+static inline void
+ftrace_perf_buf_submit(void *raw_data, int size, int rctx, u64 addr,
+		       u64 count, unsigned long irq_flags)
+{
+	struct trace_entry *entry = raw_data;
+
+	perf_tp_event(entry->type, addr, count, raw_data, size);
+	perf_swevent_put_recursion_context(rctx);
+	local_irq_restore(irq_flags);
+}
 #endif
 
 #endif /* _LINUX_FTRACE_EVENT_H */
diff --git a/include/linux/hw_breakpoint.h b/include/linux/hw_breakpoint.h
index 5977b724f7c6..c70d27af03f9 100644
--- a/include/linux/hw_breakpoint.h
+++ b/include/linux/hw_breakpoint.h
@@ -66,14 +66,14 @@ register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
 				perf_overflow_handler_t	triggered,
 				int cpu);
 
-extern struct perf_event **
+extern struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered);
 
 extern int register_perf_hw_breakpoint(struct perf_event *bp);
 extern int __register_perf_hw_breakpoint(struct perf_event *bp);
 extern void unregister_hw_breakpoint(struct perf_event *bp);
-extern void unregister_wide_hw_breakpoint(struct perf_event **cpu_events);
+extern void unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events);
 
 extern int dbg_reserve_bp_slot(struct perf_event *bp);
 extern int dbg_release_bp_slot(struct perf_event *bp);
@@ -100,7 +100,7 @@ static inline struct perf_event *
 register_wide_hw_breakpoint_cpu(struct perf_event_attr *attr,
 				perf_overflow_handler_t	 triggered,
 				int cpu)		{ return NULL; }
-static inline struct perf_event **
+static inline struct perf_event * __percpu *
 register_wide_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered)	{ return NULL; }
 static inline int
@@ -109,7 +109,7 @@ static inline int
 __register_perf_hw_breakpoint(struct perf_event *bp) 	{ return -ENOSYS; }
 static inline void unregister_hw_breakpoint(struct perf_event *bp)	{ }
 static inline void
-unregister_wide_hw_breakpoint(struct perf_event **cpu_events)		{ }
+unregister_wide_hw_breakpoint(struct perf_event * __percpu *cpu_events)	{ }
 static inline int
 reserve_bp_slot(struct perf_event *bp)			{return -ENOSYS; }
 static inline void release_bp_slot(struct perf_event *bp) 		{ }
diff --git a/include/linux/ima.h b/include/linux/ima.h
index 99dc6d5cf7e5..975837e7d6c0 100644
--- a/include/linux/ima.h
+++ b/include/linux/ima.h
@@ -17,7 +17,7 @@ struct linux_binprm;
 extern int ima_bprm_check(struct linux_binprm *bprm);
 extern int ima_inode_alloc(struct inode *inode);
 extern void ima_inode_free(struct inode *inode);
-extern int ima_path_check(struct path *path, int mask);
+extern int ima_file_check(struct file *file, int mask);
 extern void ima_file_free(struct file *file);
 extern int ima_file_mmap(struct file *file, unsigned long prot);
 extern void ima_counts_get(struct file *file);
@@ -38,7 +38,7 @@ static inline void ima_inode_free(struct inode *inode)
 	return;
 }
 
-static inline int ima_path_check(struct path *path, int mask)
+static inline int ima_file_check(struct file *file, int mask)
 {
 	return 0;
 }
diff --git a/include/linux/input.h b/include/linux/input.h
index 735ceaf1bc2d..663208afb64c 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -376,6 +376,7 @@ struct input_absinfo {
 #define KEY_DISPLAY_OFF		245	/* display device to off state */
 
 #define KEY_WIMAX		246
+#define KEY_RFKILL		247	/* Key that controls all radios */
 
 /* Range 248 - 255 is reserved for special needs of AT keyboard driver */
 
diff --git a/include/linux/kfifo.h b/include/linux/kfifo.h
index 6f6c5f300af6..bc0fc795bd35 100644
--- a/include/linux/kfifo.h
+++ b/include/linux/kfifo.h
@@ -124,7 +124,7 @@ extern __must_check unsigned int kfifo_out_peek(struct kfifo *fifo,
  */
 static inline bool kfifo_initialized(struct kfifo *fifo)
 {
-	return fifo->buffer != 0;
+	return fifo->buffer != NULL;
 }
 
 /**
diff --git a/include/linux/list.h b/include/linux/list.h
index 969f6e92d089..5d9c6558e8ab 100644
--- a/include/linux/list.h
+++ b/include/linux/list.h
@@ -206,6 +206,20 @@ static inline int list_empty_careful(const struct list_head *head)
 }
 
 /**
+ * list_rotate_left - rotate the list to the left
+ * @head: the head of the list
+ */
+static inline void list_rotate_left(struct list_head *head)
+{
+	struct list_head *first;
+
+	if (!list_empty(head)) {
+		first = head->next;
+		list_move_tail(first, head);
+	}
+}
+
+/**
  * list_is_singular - tests whether a list has just one entry.
  * @head: the list to test.
  */
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a177698d95e2..90e0521b1690 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -288,7 +288,7 @@ struct perf_event_mmap_page {
 };
 
 #define PERF_RECORD_MISC_CPUMODE_MASK		(3 << 0)
-#define PERF_RECORD_MISC_CPUMODE_UNKNOWN		(0 << 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)
@@ -354,8 +354,8 @@ enum perf_event_type {
 	 *	u64				stream_id;
 	 * };
 	 */
-	PERF_RECORD_THROTTLE		= 5,
-	PERF_RECORD_UNTHROTTLE		= 6,
+	PERF_RECORD_THROTTLE			= 5,
+	PERF_RECORD_UNTHROTTLE			= 6,
 
 	/*
 	 * struct {
@@ -369,10 +369,10 @@ enum perf_event_type {
 
 	/*
 	 * struct {
-	 * 	struct perf_event_header	header;
-	 * 	u32				pid, tid;
+	 *	struct perf_event_header	header;
+	 *	u32				pid, tid;
 	 *
-	 * 	struct read_format		values;
+	 *	struct read_format		values;
 	 * };
 	 */
 	PERF_RECORD_READ			= 8,
@@ -410,7 +410,7 @@ enum perf_event_type {
 	 *	  char                  data[size];}&& PERF_SAMPLE_RAW
 	 * };
 	 */
-	PERF_RECORD_SAMPLE		= 9,
+	PERF_RECORD_SAMPLE			= 9,
 
 	PERF_RECORD_MAX,			/* non-ABI */
 };
@@ -476,18 +476,19 @@ struct hw_perf_event {
 	union {
 		struct { /* hardware */
 			u64		config;
+			u64		last_tag;
 			unsigned long	config_base;
 			unsigned long	event_base;
 			int		idx;
+			int		last_cpu;
 		};
 		struct { /* software */
 			s64		remaining;
 			struct hrtimer	hrtimer;
 		};
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
-		union { /* breakpoint */
-			struct arch_hw_breakpoint	info;
-		};
+		/* breakpoint */
+		struct arch_hw_breakpoint	info;
 #endif
 	};
 	atomic64_t			prev_count;
@@ -496,9 +497,8 @@ struct hw_perf_event {
 	atomic64_t			period_left;
 	u64				interrupts;
 
-	u64				freq_count;
-	u64				freq_interrupts;
-	u64				freq_stamp;
+	u64				freq_time_stamp;
+	u64				freq_count_stamp;
 #endif
 };
 
@@ -510,6 +510,8 @@ struct perf_event;
 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);
 };
@@ -563,6 +565,10 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *, int,
 					struct perf_sample_data *,
 					struct pt_regs *regs);
 
+enum perf_group_flag {
+	PERF_GROUP_SOFTWARE = 0x1,
+};
+
 /**
  * struct perf_event - performance event kernel representation:
  */
@@ -572,6 +578,7 @@ struct perf_event {
 	struct list_head		event_entry;
 	struct list_head		sibling_list;
 	int				nr_siblings;
+	int				group_flags;
 	struct perf_event		*group_leader;
 	struct perf_event		*output;
 	const struct pmu		*pmu;
@@ -656,7 +663,7 @@ struct perf_event {
 
 	perf_overflow_handler_t		overflow_handler;
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_EVENT_TRACING
 	struct event_filter		*filter;
 #endif
 
@@ -681,7 +688,8 @@ struct perf_event_context {
 	 */
 	struct mutex			mutex;
 
-	struct list_head		group_list;
+	struct list_head		pinned_groups;
+	struct list_head		flexible_groups;
 	struct list_head		event_list;
 	int				nr_events;
 	int				nr_active;
@@ -744,10 +752,9 @@ extern int perf_max_events;
 
 extern const struct pmu *hw_perf_event_init(struct perf_event *event);
 
-extern void perf_event_task_sched_in(struct task_struct *task, int cpu);
-extern void perf_event_task_sched_out(struct task_struct *task,
-					struct task_struct *next, int cpu);
-extern void perf_event_task_tick(struct task_struct *task, int cpu);
+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);
@@ -762,7 +769,7 @@ 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, int cpu);
+	       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 *
@@ -850,9 +857,23 @@ extern int sysctl_perf_event_paranoid;
 extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
 
+static inline bool perf_paranoid_tracepoint_raw(void)
+{
+	return sysctl_perf_event_paranoid > -1;
+}
+
+static inline bool perf_paranoid_cpu(void)
+{
+	return sysctl_perf_event_paranoid > 0;
+}
+
+static inline bool perf_paranoid_kernel(void)
+{
+	return sysctl_perf_event_paranoid > 1;
+}
+
 extern void perf_event_init(void);
-extern void perf_tp_event(int event_id, u64 addr, u64 count,
-				 void *record, int entry_size);
+extern void perf_tp_event(int event_id, u64 addr, u64 count, void *record, int entry_size);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
 #ifndef perf_misc_flags
@@ -873,12 +894,12 @@ extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 #else
 static inline void
-perf_event_task_sched_in(struct task_struct *task, int cpu)		{ }
+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, int cpu)		{ }
+			    struct task_struct *next)			{ }
 static inline void
-perf_event_task_tick(struct task_struct *task, int cpu)			{ }
+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)	{ }
@@ -893,13 +914,13 @@ static inline void
 perf_sw_event(u32 event_id, u64 nr, int nmi,
 		     struct pt_regs *regs, u64 addr)			{ }
 static inline void
-perf_bp_event(struct perf_event *event, void *data)		{ }
+perf_bp_event(struct perf_event *event, void *data)			{ }
 
 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)		{ }
 static inline void perf_event_init(void)				{ }
-static inline int  perf_swevent_get_recursion_context(void)  { return -1; }
+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)		{ }
diff --git a/include/linux/sched.h b/include/linux/sched.h
index abdfacc58653..78efe7c485ac 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -310,6 +310,7 @@ extern void sched_show_task(struct task_struct *p);
 #ifdef CONFIG_DETECT_SOFTLOCKUP
 extern void softlockup_tick(void);
 extern void touch_softlockup_watchdog(void);
+extern void touch_softlockup_watchdog_sync(void);
 extern void touch_all_softlockup_watchdogs(void);
 extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
 				    void __user *buffer,
@@ -323,6 +324,9 @@ static inline void softlockup_tick(void)
 static inline void touch_softlockup_watchdog(void)
 {
 }
+static inline void touch_softlockup_watchdog_sync(void)
+{
+}
 static inline void touch_all_softlockup_watchdogs(void)
 {
 }
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 207466a49f3d..feee739afe21 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -99,7 +99,7 @@ struct perf_event_attr;
 #define __SC_TEST5(t5, a5, ...)	__SC_TEST(t5); __SC_TEST4(__VA_ARGS__)
 #define __SC_TEST6(t6, a6, ...)	__SC_TEST(t6); __SC_TEST5(__VA_ARGS__)
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 
 #define TRACE_SYS_ENTER_PROFILE_INIT(sname)				       \
 	.profile_enable = prof_sysenter_enable,				       \
@@ -113,7 +113,7 @@ struct perf_event_attr;
 #define TRACE_SYS_ENTER_PROFILE_INIT(sname)
 #define TRACE_SYS_EXIT_PROFILE(sname)
 #define TRACE_SYS_EXIT_PROFILE_INIT(sname)
-#endif
+#endif /* CONFIG_PERF_EVENTS */
 
 #ifdef CONFIG_FTRACE_SYSCALLS
 #define __SC_STR_ADECL1(t, a)		#a
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index ba1ba0c5efd1..63d449807d9b 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -11,6 +11,8 @@ struct nf_conntrack_ecache;
 struct netns_ct {
 	atomic_t		count;
 	unsigned int		expect_count;
+	unsigned int		htable_size;
+	struct kmem_cache	*nf_conntrack_cachep;
 	struct hlist_nulls_head	*hash;
 	struct hlist_head	*expect_hash;
 	struct hlist_nulls_head	unconfirmed;
@@ -28,5 +30,6 @@ struct netns_ct {
 #endif
 	int			hash_vmalloc;
 	int			expect_vmalloc;
+	char			*slabname;
 };
 #endif
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 2eb3814d6258..9a4b8b714079 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -40,6 +40,7 @@ struct netns_ipv4 {
 	struct xt_table		*iptable_security;
 	struct xt_table		*nat_table;
 	struct hlist_head	*nat_bysource;
+	unsigned int		nat_htable_size;
 	int			nat_vmalloced;
 #endif
 
diff --git a/include/trace/events/lock.h b/include/trace/events/lock.h
index a870ba125aa8..5c1dcfc16c60 100644
--- a/include/trace/events/lock.h
+++ b/include/trace/events/lock.h
@@ -20,14 +20,17 @@ TRACE_EVENT(lock_acquire,
 	TP_STRUCT__entry(
 		__field(unsigned int, flags)
 		__string(name, lock->name)
+		__field(void *, lockdep_addr)
 	),
 
 	TP_fast_assign(
 		__entry->flags = (trylock ? 1 : 0) | (read ? 2 : 0);
 		__assign_str(name, lock->name);
+		__entry->lockdep_addr = lock;
 	),
 
-	TP_printk("%s%s%s", (__entry->flags & 1) ? "try " : "",
+	TP_printk("%p %s%s%s", __entry->lockdep_addr,
+		  (__entry->flags & 1) ? "try " : "",
 		  (__entry->flags & 2) ? "read " : "",
 		  __get_str(name))
 );
@@ -40,13 +43,16 @@ TRACE_EVENT(lock_release,
 
 	TP_STRUCT__entry(
 		__string(name, lock->name)
+		__field(void *, lockdep_addr)
 	),
 
 	TP_fast_assign(
 		__assign_str(name, lock->name);
+		__entry->lockdep_addr = lock;
 	),
 
-	TP_printk("%s", __get_str(name))
+	TP_printk("%p %s",
+		  __entry->lockdep_addr, __get_str(name))
 );
 
 #ifdef CONFIG_LOCK_STAT
@@ -59,13 +65,16 @@ TRACE_EVENT(lock_contended,
 
 	TP_STRUCT__entry(
 		__string(name, lock->name)
+		__field(void *, lockdep_addr)
 	),
 
 	TP_fast_assign(
 		__assign_str(name, lock->name);
+		__entry->lockdep_addr = lock;
 	),
 
-	TP_printk("%s", __get_str(name))
+	TP_printk("%p %s",
+		  __entry->lockdep_addr, __get_str(name))
 );
 
 TRACE_EVENT(lock_acquired,
@@ -75,16 +84,18 @@ TRACE_EVENT(lock_acquired,
 
 	TP_STRUCT__entry(
 		__string(name, lock->name)
-		__field(unsigned long, wait_usec)
-		__field(unsigned long, wait_nsec_rem)
+		__field(s64, wait_nsec)
+		__field(void *, lockdep_addr)
 	),
+
 	TP_fast_assign(
 		__assign_str(name, lock->name);
-		__entry->wait_nsec_rem = do_div(waittime, NSEC_PER_USEC);
-		__entry->wait_usec = (unsigned long) waittime;
+		__entry->wait_nsec = waittime;
+		__entry->lockdep_addr = lock;
 	),
-	TP_printk("%s (%lu.%03lu us)", __get_str(name), __entry->wait_usec,
-				       __entry->wait_nsec_rem)
+	TP_printk("%p %s (%llu ns)", __entry->lockdep_addr,
+		  __get_str(name),
+		  __entry->wait_nsec)
 );
 
 #endif
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index c6fe03e902ca..f2c09e4d656c 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -499,7 +499,7 @@ static inline int ftrace_get_offsets_##call(				\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 
 /*
  * Generate the functions needed for tracepoint perf_event support.
@@ -542,7 +542,7 @@ static void ftrace_profile_disable_##name(struct ftrace_event_call *unused)\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#endif
+#endif /* CONFIG_PERF_EVENTS */
 
 /*
  * Stage 4 of the trace events.
@@ -627,7 +627,7 @@ static void ftrace_profile_disable_##name(struct ftrace_event_call *unused)\
  *
  */
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 
 #define _TRACE_PROFILE_INIT(call)					\
 	.profile_enable = ftrace_profile_enable_##call,			\
@@ -635,7 +635,7 @@ static void ftrace_profile_disable_##name(struct ftrace_event_call *unused)\
 
 #else
 #define _TRACE_PROFILE_INIT(call)
-#endif
+#endif /* CONFIG_PERF_EVENTS */
 
 #undef __entry
 #define __entry entry
@@ -835,7 +835,7 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
  * }
  */
 
-#ifdef CONFIG_EVENT_PROFILE
+#ifdef CONFIG_PERF_EVENTS
 
 #undef __perf_addr
 #define __perf_addr(a) __addr = (a)
@@ -850,22 +850,12 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
 			    proto)					\
 {									\
 	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
-	extern int perf_swevent_get_recursion_context(void);		\
-	extern void perf_swevent_put_recursion_context(int rctx);	\
-	extern void perf_tp_event(int, u64, u64, void *, int);		\
 	struct ftrace_raw_##call *entry;				\
 	u64 __addr = 0, __count = 1;					\
 	unsigned long irq_flags;					\
-	struct trace_entry *ent;					\
 	int __entry_size;						\
 	int __data_size;						\
-	char *trace_buf;						\
-	char *raw_data;							\
-	int __cpu;							\
 	int rctx;							\
-	int pc;								\
-									\
-	pc = preempt_count();						\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
@@ -875,42 +865,16 @@ ftrace_profile_templ_##call(struct ftrace_event_call *event_call,	\
 	if (WARN_ONCE(__entry_size > FTRACE_MAX_PROFILE_SIZE,		\
 		      "profile buffer not large enough"))		\
 		return;							\
-									\
-	local_irq_save(irq_flags);					\
-									\
-	rctx = perf_swevent_get_recursion_context();			\
-	if (rctx < 0)							\
-		goto end_recursion;					\
-									\
-	__cpu = smp_processor_id();					\
-									\
-	if (in_nmi())							\
-		trace_buf = rcu_dereference(perf_trace_buf_nmi);	\
-	else								\
-		trace_buf = rcu_dereference(perf_trace_buf);		\
-									\
-	if (!trace_buf)							\
-		goto end;						\
-									\
-	raw_data = per_cpu_ptr(trace_buf, __cpu);			\
-									\
-	*(u64 *)(&raw_data[__entry_size - sizeof(u64)]) = 0ULL;		\
-	entry = (struct ftrace_raw_##call *)raw_data;			\
-	ent = &entry->ent;						\
-	tracing_generic_entry_update(ent, irq_flags, pc);		\
-	ent->type = event_call->id;					\
-									\
+	entry = (struct ftrace_raw_##call *)ftrace_perf_buf_prepare(	\
+		__entry_size, event_call->id, &rctx, &irq_flags);	\
+	if (!entry)							\
+		return;							\
 	tstruct								\
 									\
 	{ assign; }							\
 									\
-	perf_tp_event(event_call->id, __addr, __count, entry,		\
-			     __entry_size);				\
-									\
-end:									\
-	perf_swevent_put_recursion_context(rctx);			\
-end_recursion:								\
-	local_irq_restore(irq_flags);					\
+	ftrace_perf_buf_submit(entry, __entry_size, rctx, __addr,	\
+			       __count, irq_flags);			\
 }
 
 #undef DEFINE_EVENT
@@ -927,7 +891,7 @@ static void ftrace_profile_##call(proto)			\
 	DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
-#endif /* CONFIG_EVENT_PROFILE */
+#endif /* CONFIG_PERF_EVENTS */
 
 #undef _TRACE_PROFILE_INIT
 
diff --git a/include/trace/syscall.h b/include/trace/syscall.h
index 961fda3556bb..3d463dcef298 100644
--- a/include/trace/syscall.h
+++ b/include/trace/syscall.h
@@ -49,12 +49,12 @@ ftrace_format_syscall(struct ftrace_event_call *call, struct trace_seq *s);
 enum print_line_t print_syscall_enter(struct trace_iterator *iter, int flags);
 enum print_line_t print_syscall_exit(struct trace_iterator *iter, int flags);
 #endif
-#ifdef CONFIG_EVENT_PROFILE
+
+#ifdef CONFIG_PERF_EVENTS
 int prof_sysenter_enable(struct ftrace_event_call *call);
 void prof_sysenter_disable(struct ftrace_event_call *call);
 int prof_sysexit_enable(struct ftrace_event_call *call);
 void prof_sysexit_disable(struct ftrace_event_call *call);
-
 #endif
 
 #endif /* _TRACE_SYSCALL_H */