Merge remote branch 'tip/auto-latest'

Conflicts:
	net/core/dev.c

19 files changed, 506 insertions, 148 deletions

diff --git a/include/asm-generic/hardirq.h b/include/asm-generic/hardirq.h
index 62f59080e5cc..04d0a977cd43 100644
--- a/include/asm-generic/hardirq.h
+++ b/include/asm-generic/hardirq.h
@@ -3,13 +3,13 @@
 
 #include <linux/cache.h>
 #include <linux/threads.h>
-#include <linux/irq.h>
 
 typedef struct {
 	unsigned int __softirq_pending;
 } ____cacheline_aligned irq_cpustat_t;
 
 #include <linux/irq_cpustat.h>	/* Standard mappings for irq_cpustat_t above */
+#include <linux/irq.h>
 
 #ifndef ack_bad_irq
 static inline void ack_bad_irq(unsigned int irq)
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index 9c7ea63729de..6f3c6ae4fe03 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -129,6 +129,10 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres
 #define move_pte(pte, prot, old_addr, new_addr)	(pte)
 #endif
 
+#ifndef flush_tlb_fix_spurious_fault
+#define flush_tlb_fix_spurious_fault(vma, address) flush_tlb_page(vma, address)
+#endif
+
 #ifndef pgprot_noncached
 #define pgprot_noncached(prot)	(prot)
 #endif
diff --git a/include/linux/debug_locks.h b/include/linux/debug_locks.h
index 29b3ce3f2a1d..2833452ea01c 100644
--- a/include/linux/debug_locks.h
+++ b/include/linux/debug_locks.h
@@ -49,7 +49,6 @@ struct task_struct;
 
 #ifdef CONFIG_LOCKDEP
 extern void debug_show_all_locks(void);
-extern void __debug_show_held_locks(struct task_struct *task);
 extern void debug_show_held_locks(struct task_struct *task);
 extern void debug_check_no_locks_freed(const void *from, unsigned long len);
 extern void debug_check_no_locks_held(struct task_struct *task);
@@ -58,10 +57,6 @@ static inline void debug_show_all_locks(void)
 {
 }
 
-static inline void __debug_show_held_locks(struct task_struct *task)
-{
-}
-
 static inline void debug_show_held_locks(struct task_struct *task)
 {
 }
diff --git a/include/linux/dmar.h b/include/linux/dmar.h
index d7cecc90ed34..a20602041511 100644
--- a/include/linux/dmar.h
+++ b/include/linux/dmar.h
@@ -57,15 +57,15 @@ extern int dmar_table_init(void);
 extern int dmar_dev_scope_init(void);
 
 /* Intel IOMMU detection */
-extern void detect_intel_iommu(void);
+extern int detect_intel_iommu(void);
 extern int enable_drhd_fault_handling(void);
 
 extern int parse_ioapics_under_ir(void);
 extern int alloc_iommu(struct dmar_drhd_unit *);
 #else
-static inline void detect_intel_iommu(void)
+static inline int detect_intel_iommu(void)
 {
-	return;
+	return -ENODEV;
 }
 
 static inline int dmar_table_init(void)
diff --git a/include/linux/early_res.h b/include/linux/early_res.h
deleted file mode 100644
index 29c09f57a13c..000000000000
--- a/include/linux/early_res.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef _LINUX_EARLY_RES_H
-#define _LINUX_EARLY_RES_H
-#ifdef __KERNEL__
-
-extern void reserve_early(u64 start, u64 end, char *name);
-extern void reserve_early_overlap_ok(u64 start, u64 end, char *name);
-extern void free_early(u64 start, u64 end);
-void free_early_partial(u64 start, u64 end);
-extern void early_res_to_bootmem(u64 start, u64 end);
-
-void reserve_early_without_check(u64 start, u64 end, char *name);
-u64 find_early_area(u64 ei_start, u64 ei_last, u64 start, u64 end,
-			 u64 size, u64 align);
-u64 find_early_area_size(u64 ei_start, u64 ei_last, u64 start,
-			 u64 *sizep, u64 align);
-u64 find_fw_memmap_area(u64 start, u64 end, u64 size, u64 align);
-u64 get_max_mapped(void);
-#include <linux/range.h>
-int get_free_all_memory_range(struct range **rangep, int nodeid);
-
-#endif /* __KERNEL__ */
-
-#endif /* _LINUX_EARLY_RES_H */
diff --git a/include/linux/ftrace_event.h b/include/linux/ftrace_event.h
index 02b8b24f8f51..8beabb958f61 100644
--- a/include/linux/ftrace_event.h
+++ b/include/linux/ftrace_event.h
@@ -191,8 +191,8 @@ struct ftrace_event_call {
 	unsigned int		flags;
 
 #ifdef CONFIG_PERF_EVENTS
-	int			perf_refcount;
-	struct hlist_head	*perf_events;
+	int				perf_refcount;
+	struct hlist_head __percpu	*perf_events;
 #endif
 };
 
@@ -252,8 +252,8 @@ DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
 
 extern int  perf_trace_init(struct perf_event *event);
 extern void perf_trace_destroy(struct perf_event *event);
-extern int  perf_trace_enable(struct perf_event *event);
-extern void perf_trace_disable(struct perf_event *event);
+extern int  perf_trace_add(struct perf_event *event, int flags);
+extern void perf_trace_del(struct perf_event *event, int flags);
 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);
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a0384a4d1e6f..531495db1708 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -18,6 +18,7 @@
 #include <asm/atomic.h>
 #include <asm/ptrace.h>
 #include <asm/system.h>
+#include <trace/events/irq.h>
 
 /*
  * These correspond to the IORESOURCE_IRQ_* defines in
@@ -407,7 +408,12 @@ asmlinkage void do_softirq(void);
 asmlinkage void __do_softirq(void);
 extern void open_softirq(int nr, void (*action)(struct softirq_action *));
 extern void softirq_init(void);
-#define __raise_softirq_irqoff(nr) do { or_softirq_pending(1UL << (nr)); } while (0)
+static inline void __raise_softirq_irqoff(unsigned int nr)
+{
+	trace_softirq_raise((struct softirq_action *)(unsigned long)nr, NULL);
+	or_softirq_pending(1UL << nr);
+}
+
 extern void raise_softirq_irqoff(unsigned int nr);
 extern void raise_softirq(unsigned int nr);
 extern void wakeup_softirqd(void);
diff --git a/include/linux/irq.h b/include/linux/irq.h
index c03243ad84b4..fff1d77c3753 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -439,12 +439,12 @@ extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
 static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
 							bool boot)
 {
+#ifdef CONFIG_CPUMASK_OFFSTACK
 	gfp_t gfp = GFP_ATOMIC;
 
 	if (boot)
 		gfp = GFP_NOWAIT;
 
-#ifdef CONFIG_CPUMASK_OFFSTACK
 	if (!alloc_cpumask_var_node(&desc->affinity, gfp, node))
 		return false;
 
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index a59faf2b5edd..5096458c7535 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -2,6 +2,7 @@
 #define _LINUX_MEMBLOCK_H
 #ifdef __KERNEL__
 
+#ifdef CONFIG_HAVE_MEMBLOCK
 /*
  * Logical memory blocks.
  *
@@ -16,73 +17,151 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 
-#define MAX_MEMBLOCK_REGIONS 128
+#include <asm/memblock.h>
 
-struct memblock_property {
-	u64 base;
-	u64 size;
-};
+#define INIT_MEMBLOCK_REGIONS	128
+#define MEMBLOCK_ERROR		0
 
 struct memblock_region {
-	unsigned long cnt;
-	u64 size;
-	struct memblock_property region[MAX_MEMBLOCK_REGIONS+1];
+	phys_addr_t base;
+	phys_addr_t size;
+};
+
+struct memblock_type {
+	unsigned long cnt;	/* number of regions */
+	unsigned long max;	/* size of the allocated array */
+	struct memblock_region *regions;
 };
 
 struct memblock {
-	unsigned long debug;
-	u64 rmo_size;
-	struct memblock_region memory;
-	struct memblock_region reserved;
+	phys_addr_t current_limit;
+	phys_addr_t memory_size;	/* Updated by memblock_analyze() */
+	struct memblock_type memory;
+	struct memblock_type reserved;
 };
 
 extern struct memblock memblock;
+extern int memblock_debug;
+extern int memblock_can_resize;
 
-extern void __init memblock_init(void);
-extern void __init memblock_analyze(void);
-extern long memblock_add(u64 base, u64 size);
-extern long memblock_remove(u64 base, u64 size);
-extern long __init memblock_free(u64 base, u64 size);
-extern long __init memblock_reserve(u64 base, u64 size);
-extern u64 __init memblock_alloc_nid(u64 size, u64 align, int nid,
-				u64 (*nid_range)(u64, u64, int *));
-extern u64 __init memblock_alloc(u64 size, u64 align);
-extern u64 __init memblock_alloc_base(u64 size,
-		u64, u64 max_addr);
-extern u64 __init __memblock_alloc_base(u64 size,
-		u64 align, u64 max_addr);
-extern u64 __init memblock_phys_mem_size(void);
-extern u64 memblock_end_of_DRAM(void);
-extern void __init memblock_enforce_memory_limit(u64 memory_limit);
-extern int __init memblock_is_reserved(u64 addr);
-extern int memblock_is_region_reserved(u64 base, u64 size);
-extern int memblock_find(struct memblock_property *res);
+#define memblock_dbg(fmt, ...) \
+	if (memblock_debug) printk(KERN_INFO pr_fmt(fmt), ##__VA_ARGS__)
+
+u64 memblock_find_in_range(u64 start, u64 end, u64 size, u64 align);
+int memblock_free_reserved_regions(void);
+int memblock_reserve_reserved_regions(void);
+
+extern void memblock_init(void);
+extern void memblock_analyze(void);
+extern long memblock_add(phys_addr_t base, phys_addr_t size);
+extern long memblock_remove(phys_addr_t base, phys_addr_t size);
+extern long memblock_free(phys_addr_t base, phys_addr_t size);
+extern long memblock_reserve(phys_addr_t base, phys_addr_t size);
+
+/* The numa aware allocator is only available if
+ * CONFIG_ARCH_POPULATES_NODE_MAP is set
+ */
+extern phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align,
+					int nid);
+extern phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align,
+					    int nid);
+
+extern phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align);
+
+/* Flags for memblock_alloc_base() amd __memblock_alloc_base() */
+#define MEMBLOCK_ALLOC_ANYWHERE	(~(phys_addr_t)0)
+#define MEMBLOCK_ALLOC_ACCESSIBLE	0
+
+extern phys_addr_t memblock_alloc_base(phys_addr_t size,
+					 phys_addr_t align,
+					 phys_addr_t max_addr);
+extern phys_addr_t __memblock_alloc_base(phys_addr_t size,
+					   phys_addr_t align,
+					   phys_addr_t max_addr);
+extern phys_addr_t memblock_phys_mem_size(void);
+extern phys_addr_t memblock_end_of_DRAM(void);
+extern void memblock_enforce_memory_limit(phys_addr_t memory_limit);
+extern int memblock_is_memory(phys_addr_t addr);
+extern int memblock_is_region_memory(phys_addr_t base, phys_addr_t size);
+extern int memblock_is_reserved(phys_addr_t addr);
+extern int memblock_is_region_reserved(phys_addr_t base, phys_addr_t size);
 
 extern void memblock_dump_all(void);
 
-static inline u64
-memblock_size_bytes(struct memblock_region *type, unsigned long region_nr)
+/* Provided by the architecture */
+extern phys_addr_t memblock_nid_range(phys_addr_t start, phys_addr_t end, int *nid);
+extern int memblock_memory_can_coalesce(phys_addr_t addr1, phys_addr_t size1,
+				   phys_addr_t addr2, phys_addr_t size2);
+
+/**
+ * memblock_set_current_limit - Set the current allocation limit to allow
+ *                         limiting allocations to what is currently
+ *                         accessible during boot
+ * @limit: New limit value (physical address)
+ */
+extern void memblock_set_current_limit(phys_addr_t limit);
+
+
+/*
+ * pfn conversion functions
+ *
+ * While the memory MEMBLOCKs should always be page aligned, the reserved
+ * MEMBLOCKs may not be. This accessor attempt to provide a very clear
+ * idea of what they return for such non aligned MEMBLOCKs.
+ */
+
+/**
+ * memblock_region_base_pfn - Return the lowest pfn intersecting with the region
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_base_pfn(const struct memblock_region *reg)
 {
-	return type->region[region_nr].size;
+	return reg->base >> PAGE_SHIFT;
 }
-static inline u64
-memblock_size_pages(struct memblock_region *type, unsigned long region_nr)
+
+/**
+ * memblock_region_last_pfn - Return the highest pfn intersecting with the region
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_last_pfn(const struct memblock_region *reg)
 {
-	return memblock_size_bytes(type, region_nr) >> PAGE_SHIFT;
+	return (reg->base + reg->size - 1) >> PAGE_SHIFT;
 }
-static inline u64
-memblock_start_pfn(struct memblock_region *type, unsigned long region_nr)
+
+/**
+ * memblock_region_end_pfn - Return the pfn of the first page following the region
+ *                      but not intersecting it
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_end_pfn(const struct memblock_region *reg)
 {
-	return type->region[region_nr].base >> PAGE_SHIFT;
+	return memblock_region_last_pfn(reg) + 1;
 }
-static inline u64
-memblock_end_pfn(struct memblock_region *type, unsigned long region_nr)
+
+/**
+ * memblock_region_pages - Return the number of pages covering a region
+ * @reg: memblock_region structure
+ */
+static inline unsigned long memblock_region_pages(const struct memblock_region *reg)
 {
-	return memblock_start_pfn(type, region_nr) +
-	       memblock_size_pages(type, region_nr);
+	return memblock_region_end_pfn(reg) - memblock_region_end_pfn(reg);
 }
 
-#include <asm/memblock.h>
+#define for_each_memblock(memblock_type, region)					\
+	for (region = memblock.memblock_type.regions;				\
+	     region < (memblock.memblock_type.regions + memblock.memblock_type.cnt);	\
+	     region++)
+
+
+#ifdef ARCH_DISCARD_MEMBLOCK
+#define __init_memblock __init
+#define __initdata_memblock __initdata
+#else
+#define __init_memblock
+#define __initdata_memblock
+#endif
+
+#endif /* CONFIG_HAVE_MEMBLOCK */
 
 #endif /* __KERNEL__ */
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 74949fbef8c6..7687228dd3b7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1175,6 +1175,8 @@ extern void free_bootmem_with_active_regions(int nid,
 						unsigned long max_low_pfn);
 int add_from_early_node_map(struct range *range, int az,
 				   int nr_range, int nid);
+u64 __init find_memory_core_early(int nid, u64 size, u64 align,
+					u64 goal, u64 limit);
 void *__alloc_memory_core_early(int nodeid, u64 size, u64 align,
 				 u64 goal, u64 limit);
 typedef int (*work_fn_t)(unsigned long, unsigned long, void *);
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index ce2dc655cd1d..ab20d119a85d 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -139,6 +139,18 @@
 	__aligned(PAGE_SIZE)
 
 /*
+ * Declaration/definition used for large per-CPU variables that must be
+ * aligned to something larger than the pagesize.
+ */
+#define DECLARE_PER_CPU_MULTIPAGE_ALIGNED(type, name, size)		\
+	DECLARE_PER_CPU_SECTION(type, name, "..page_aligned")		\
+	__aligned(size)
+
+#define DEFINE_PER_CPU_MULTIPAGE_ALIGNED(type, name, size)		\
+	DEFINE_PER_CPU_SECTION(type, name, "..page_aligned")		\
+	__aligned(size)
+
+/*
  * Intermodule exports for per-CPU variables.  sparse forgets about
  * address space across EXPORT_SYMBOL(), change EXPORT_SYMBOL() to
  * noop if __CHECKER__.
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 716f99b682c1..61b1e2d760fd 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -529,7 +529,6 @@ struct hw_perf_event {
 			int		last_cpu;
 		};
 		struct { /* software */
-			s64		remaining;
 			struct hrtimer	hrtimer;
 		};
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
@@ -539,6 +538,7 @@ struct hw_perf_event {
 		};
 #endif
 	};
+	int				state;
 	local64_t			prev_count;
 	u64				sample_period;
 	u64				last_period;
@@ -550,6 +550,13 @@ 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 +568,70 @@ 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 */
 };
 
 /**
@@ -669,7 +710,7 @@ 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;
@@ -763,12 +804,19 @@ 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 +856,12 @@ 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 +869,9 @@ 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 +887,20 @@ struct perf_output_handle {
 
 #ifdef CONFIG_PERF_EVENTS
 
-/*
- * Set by architecture code:
- */
-extern int perf_max_events;
-
-extern const struct pmu *hw_perf_event_init(struct perf_event *event);
+extern int perf_pmu_register(struct pmu *pmu);
+extern void perf_pmu_unregister(struct pmu *pmu);
 
 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 perf_event_delayed_put(struct task_struct *task);
 extern void set_perf_event_pending(void);
 extern void perf_event_do_pending(void);
 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 +908,7 @@ 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 +959,7 @@ 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];
@@ -976,7 +1008,21 @@ 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 +1065,19 @@ 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_delayed_put(struct task_struct *task)	{ }
 static inline void perf_event_do_pending(void)				{ }
 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 +1100,7 @@ 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) \
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e18473f0eb78..d3e6a3dc9e76 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -875,6 +875,7 @@ enum sched_domain_level {
 	SD_LV_NONE = 0,
 	SD_LV_SIBLING,
 	SD_LV_MC,
+	SD_LV_BOOK,
 	SD_LV_CPU,
 	SD_LV_NODE,
 	SD_LV_ALLNODES,
@@ -1160,6 +1161,13 @@ struct sched_rt_entity {
 
 struct rcu_node;
 
+enum perf_event_task_context {
+	perf_invalid_context = -1,
+	perf_hw_context = 0,
+	perf_sw_context,
+	perf_nr_task_contexts,
+};
+
 struct task_struct {
 	volatile long state;	/* -1 unrunnable, 0 runnable, >0 stopped */
 	void *stack;
@@ -1433,7 +1441,7 @@ struct task_struct {
 	struct futex_pi_state *pi_state_cache;
 #endif
 #ifdef CONFIG_PERF_EVENTS
-	struct perf_event_context *perf_event_ctxp;
+	struct perf_event_context *perf_event_ctxp[perf_nr_task_contexts];
 	struct mutex perf_event_mutex;
 	struct list_head perf_event_list;
 #endif
@@ -1683,8 +1691,6 @@ extern void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *
 /*
  * Per process flags
  */
-#define PF_ALIGNWARN	0x00000001	/* Print alignment warning msgs */
-					/* Not implemented yet, only for 486*/
 #define PF_STARTING	0x00000002	/* being created */
 #define PF_EXITING	0x00000004	/* getting shut down */
 #define PF_EXITPIDONE	0x00000008	/* pi exit done on shut down */
diff --git a/include/linux/topology.h b/include/linux/topology.h
index 64e084ff5e5c..b91a40e847d2 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -201,6 +201,12 @@ int arch_update_cpu_topology(void);
 	.balance_interval	= 64,					\
 }
 
+#ifdef CONFIG_SCHED_BOOK
+#ifndef SD_BOOK_INIT
+#error Please define an appropriate SD_BOOK_INIT in include/asm/topology.h!!!
+#endif
+#endif /* CONFIG_SCHED_BOOK */
+
 #ifdef CONFIG_NUMA
 #ifndef SD_NODE_INIT
 #error Please define an appropriate SD_NODE_INIT in include/asm/topology.h!!!
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
index 0e4cfb694fe7..6fa7cbab7d93 100644
--- a/include/trace/events/irq.h
+++ b/include/trace/events/irq.h
@@ -5,7 +5,9 @@
 #define _TRACE_IRQ_H
 
 #include <linux/tracepoint.h>
-#include <linux/interrupt.h>
+
+struct irqaction;
+struct softirq_action;
 
 #define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq }
 #define show_softirq_name(val)				\
@@ -93,7 +95,10 @@ DECLARE_EVENT_CLASS(softirq,
 	),
 
 	TP_fast_assign(
-		__entry->vec = (int)(h - vec);
+		if (vec)
+			__entry->vec = (int)(h - vec);
+		else
+			__entry->vec = (int)(long)h;
 	),
 
 	TP_printk("vec=%d [action=%s]", __entry->vec,
@@ -136,6 +141,23 @@ DEFINE_EVENT(softirq, softirq_exit,
 	TP_ARGS(h, vec)
 );
 
+/**
+ * softirq_raise - called immediately when a softirq is raised
+ * @h: pointer to struct softirq_action
+ * @vec: pointer to first struct softirq_action in softirq_vec array
+ *
+ * The @h parameter contains a pointer to the softirq vector number which is
+ * raised. @vec is NULL and it means @h includes vector number not
+ * softirq_action. When used in combination with the softirq_entry tracepoint
+ * we can determine the softirq raise latency.
+ */
+DEFINE_EVENT(softirq, softirq_raise,
+
+	TP_PROTO(struct softirq_action *h, struct softirq_action *vec),
+
+	TP_ARGS(h, vec)
+);
+
 #endif /*  _TRACE_IRQ_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/napi.h b/include/trace/events/napi.h
index 188deca2f3c7..8fe1e93f531d 100644
--- a/include/trace/events/napi.h
+++ b/include/trace/events/napi.h
@@ -6,10 +6,31 @@
 
 #include <linux/netdevice.h>
 #include <linux/tracepoint.h>
+#include <linux/ftrace.h>
+
+#define NO_DEV "(no_device)"
+
+TRACE_EVENT(napi_poll,
 
-DECLARE_TRACE(napi_poll,
 	TP_PROTO(struct napi_struct *napi),
-	TP_ARGS(napi));
+
+	TP_ARGS(napi),
+
+	TP_STRUCT__entry(
+		__field(	struct napi_struct *,	napi)
+		__string(	dev_name, napi->dev ? napi->dev->name : NO_DEV)
+	),
+
+	TP_fast_assign(
+		__entry->napi = napi;
+		__assign_str(dev_name, napi->dev ? napi->dev->name : NO_DEV);
+	),
+
+	TP_printk("napi poll on napi struct %p for device %s",
+		__entry->napi, __get_str(dev_name))
+);
+
+#undef NO_DEV
 
 #endif /* _TRACE_NAPI_H_ */
 
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
new file mode 100644
index 000000000000..5f247f5ffc56
--- /dev/null
+++ b/include/trace/events/net.h
@@ -0,0 +1,82 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM net
+
+#if !defined(_TRACE_NET_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_NET_H
+
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/ip.h>
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(net_dev_xmit,
+
+	TP_PROTO(struct sk_buff *skb,
+		 int rc),
+
+	TP_ARGS(skb, rc),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__field(	int,		rc		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__entry->rc = rc;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u rc=%d",
+		__get_str(name), __entry->skbaddr, __entry->len, __entry->rc)
+);
+
+DECLARE_EVENT_CLASS(net_dev_template,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,		skbaddr		)
+		__field(	unsigned int,	len		)
+		__string(	name,		skb->dev->name	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+		__entry->len = skb->len;
+		__assign_str(name, skb->dev->name);
+	),
+
+	TP_printk("dev=%s skbaddr=%p len=%u",
+		__get_str(name), __entry->skbaddr, __entry->len)
+)
+
+DEFINE_EVENT(net_dev_template, net_dev_queue,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_receive_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+
+DEFINE_EVENT(net_dev_template, netif_rx,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb)
+);
+#endif /* _TRACE_NET_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/include/trace/events/power.h b/include/trace/events/power.h
index 35a2a6e7bf1e..286784d69b8f 100644
--- a/include/trace/events/power.h
+++ b/include/trace/events/power.h
@@ -10,12 +10,17 @@
 #ifndef _TRACE_POWER_ENUM_
 #define _TRACE_POWER_ENUM_
 enum {
-	POWER_NONE = 0,
-	POWER_CSTATE = 1,
-	POWER_PSTATE = 2,
+	POWER_NONE	= 0,
+	POWER_CSTATE	= 1,	/* C-State */
+	POWER_PSTATE	= 2,	/* Fequency change or DVFS */
+	POWER_SSTATE	= 3,	/* Suspend */
 };
 #endif
 
+/*
+ * The power events are used for cpuidle & suspend (power_start, power_end)
+ *  and for cpufreq (power_frequency)
+ */
 DECLARE_EVENT_CLASS(power,
 
 	TP_PROTO(unsigned int type, unsigned int state, unsigned int cpu_id),
@@ -70,6 +75,85 @@ TRACE_EVENT(power_end,
 
 );
 
+/*
+ * The clock events are used for clock enable/disable and for
+ *  clock rate change
+ */
+DECLARE_EVENT_CLASS(clock,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+	),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_enable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_disable,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+DEFINE_EVENT(clock, clock_set_rate,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
+/*
+ * The power domain events are used for power domains transitions
+ */
+DECLARE_EVENT_CLASS(power_domain,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id),
+
+	TP_STRUCT__entry(
+		__string(       name,           name            )
+		__field(        u64,            state           )
+		__field(        u64,            cpu_id          )
+	),
+
+	TP_fast_assign(
+		__assign_str(name, name);
+		__entry->state = state;
+		__entry->cpu_id = cpu_id;
+),
+
+	TP_printk("%s state=%lu cpu_id=%lu", __get_str(name),
+		(unsigned long)__entry->state, (unsigned long)__entry->cpu_id)
+);
+
+DEFINE_EVENT(power_domain, power_domain_target,
+
+	TP_PROTO(const char *name, unsigned int state, unsigned int cpu_id),
+
+	TP_ARGS(name, state, cpu_id)
+);
+
 #endif /* _TRACE_POWER_H */
 
 /* This part must be outside protection */
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 4b2be6dc76f0..75ce9d500d8e 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -35,6 +35,23 @@ TRACE_EVENT(kfree_skb,
 		__entry->skbaddr, __entry->protocol, __entry->location)
 );
 
+TRACE_EVENT(consume_skb,
+
+	TP_PROTO(struct sk_buff *skb),
+
+	TP_ARGS(skb),
+
+	TP_STRUCT__entry(
+		__field(	void *,	skbaddr	)
+	),
+
+	TP_fast_assign(
+		__entry->skbaddr = skb;
+	),
+
+	TP_printk("skbaddr=%p", __entry->skbaddr)
+);
+
 TRACE_EVENT(skb_copy_datagram_iovec,
 
 	TP_PROTO(const struct sk_buff *skb, int len),