Merge branch 'percpu-for-linus' into percpu-for-next

Conflicts:
	arch/sparc/kernel/smp_64.c
	arch/x86/kernel/cpu/perf_counter.c
	arch/x86/kernel/setup_percpu.c
	drivers/cpufreq/cpufreq_ondemand.c
	mm/percpu.c

Conflicts in core and arch percpu codes are mostly from commit
ed78e1e078dd44249f88b1dd8c76dafb39567161 which substituted many
num_possible_cpus() with nr_cpu_ids.  As for-next branch has moved all
the first chunk allocators into mm/percpu.c, the changes are moved
from arch code to mm/percpu.c.

Signed-off-by: Tejun Heo <tj@kernel.org>

10 files changed, 188 insertions, 97 deletions

diff --git a/include/trace/events/block.h b/include/trace/events/block.h
index d6b05f42dd4..9a74b468a22 100644
--- a/include/trace/events/block.h
+++ b/include/trace/events/block.h
@@ -1,3 +1,6 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM block
+
 #if !defined(_TRACE_BLOCK_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_BLOCK_H
 
@@ -5,9 +8,6 @@
 #include <linux/blkdev.h>
 #include <linux/tracepoint.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM block
-
 TRACE_EVENT(block_rq_abort,
 
 	TP_PROTO(struct request_queue *q, struct request *rq),
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index acf4cc9cd36..7d8b5bc7418 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -1,9 +1,9 @@
-#if !defined(_TRACE_EXT4_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_EXT4_H
-
 #undef TRACE_SYSTEM
 #define TRACE_SYSTEM ext4
 
+#if !defined(_TRACE_EXT4_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_EXT4_H
+
 #include <linux/writeback.h>
 #include "../../../fs/ext4/ext4.h"
 #include "../../../fs/ext4/mballoc.h"
@@ -34,7 +34,8 @@ TRACE_EVENT(ext4_free_inode,
 
 	TP_printk("dev %s ino %lu mode %d uid %u gid %u blocks %llu",
 		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->mode,
-		  __entry->uid, __entry->gid, __entry->blocks)
+		  __entry->uid, __entry->gid,
+		  (unsigned long long) __entry->blocks)
 );
 
 TRACE_EVENT(ext4_request_inode,
@@ -189,7 +190,7 @@ TRACE_EVENT(ext4_journalled_write_end,
 		  __entry->copied)
 );
 
-TRACE_EVENT(ext4_da_writepage,
+TRACE_EVENT(ext4_writepage,
 	TP_PROTO(struct inode *inode, struct page *page),
 
 	TP_ARGS(inode, page),
@@ -341,49 +342,6 @@ TRACE_EVENT(ext4_da_write_end,
 		  __entry->copied)
 );
 
-TRACE_EVENT(ext4_normal_writepage,
-	TP_PROTO(struct inode *inode, struct page *page),
-
-	TP_ARGS(inode, page),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	pgoff_t, index			)
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->index	= page->index;
-	),
-
-	TP_printk("dev %s ino %lu page_index %lu",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index)
-);
-
-TRACE_EVENT(ext4_journalled_writepage,
-	TP_PROTO(struct inode *inode, struct page *page),
-
-	TP_ARGS(inode, page),
-
-	TP_STRUCT__entry(
-		__field(	dev_t,	dev			)
-		__field(	ino_t,	ino			)
-		__field(	pgoff_t, index			)
-
-	),
-
-	TP_fast_assign(
-		__entry->dev	= inode->i_sb->s_dev;
-		__entry->ino	= inode->i_ino;
-		__entry->index	= page->index;
-	),
-
-	TP_printk("dev %s ino %lu page_index %lu",
-		  jbd2_dev_to_name(__entry->dev), __entry->ino, __entry->index)
-);
-
 TRACE_EVENT(ext4_discard_blocks,
 	TP_PROTO(struct super_block *sb, unsigned long long blk,
 			unsigned long long count),
diff --git a/include/trace/events/irq.h b/include/trace/events/irq.h
index b0c7ede55eb..1cb0c3aa11e 100644
--- a/include/trace/events/irq.h
+++ b/include/trace/events/irq.h
@@ -1,12 +1,12 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM irq
+
 #if !defined(_TRACE_IRQ_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_IRQ_H
 
 #include <linux/tracepoint.h>
 #include <linux/interrupt.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM irq
-
 #define softirq_name(sirq) { sirq##_SOFTIRQ, #sirq }
 #define show_softirq_name(val)			\
 	__print_symbolic(val,			\
diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h
index 845b0b4b48f..10813fa0c8d 100644
--- a/include/trace/events/jbd2.h
+++ b/include/trace/events/jbd2.h
@@ -1,12 +1,12 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM jbd2
+
 #if !defined(_TRACE_JBD2_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_JBD2_H
 
 #include <linux/jbd2.h>
 #include <linux/tracepoint.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM jbd2
-
 TRACE_EVENT(jbd2_checkpoint,
 
 	TP_PROTO(journal_t *journal, int result),
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index 9baba50d651..1493c541f9c 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -1,12 +1,12 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM kmem
+
 #if !defined(_TRACE_KMEM_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_KMEM_H
 
 #include <linux/types.h>
 #include <linux/tracepoint.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM kmem
-
 /*
  * The order of these masks is important. Matching masks will be seen
  * first and the left over flags will end up showing by themselves.
diff --git a/include/trace/events/lockdep.h b/include/trace/events/lockdep.h
index 0e956c9dfd7..bcf1d209a00 100644
--- a/include/trace/events/lockdep.h
+++ b/include/trace/events/lockdep.h
@@ -1,12 +1,12 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM lockdep
+
 #if !defined(_TRACE_LOCKDEP_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_LOCKDEP_H
 
 #include <linux/lockdep.h>
 #include <linux/tracepoint.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM lockdep
-
 #ifdef CONFIG_LOCKDEP
 
 TRACE_EVENT(lock_acquire,
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 24ab5bcff7b..8949bb7eb08 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -1,12 +1,12 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM sched
+
 #if !defined(_TRACE_SCHED_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_SCHED_H
 
 #include <linux/sched.h>
 #include <linux/tracepoint.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM sched
-
 /*
  * Tracepoint for calling kthread_stop, performed to end a kthread:
  */
diff --git a/include/trace/events/skb.h b/include/trace/events/skb.h
index 1e8fabb57c0..e499863b966 100644
--- a/include/trace/events/skb.h
+++ b/include/trace/events/skb.h
@@ -1,12 +1,12 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM skb
+
 #if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_SKB_H
 
 #include <linux/skbuff.h>
 #include <linux/tracepoint.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM skb
-
 /*
  * Tracepoint for free an sk_buff:
  */
diff --git a/include/trace/events/workqueue.h b/include/trace/events/workqueue.h
index 035f1bff288..fcfd9a1e4b9 100644
--- a/include/trace/events/workqueue.h
+++ b/include/trace/events/workqueue.h
@@ -1,3 +1,6 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM workqueue
+
 #if !defined(_TRACE_WORKQUEUE_H) || defined(TRACE_HEADER_MULTI_READ)
 #define _TRACE_WORKQUEUE_H
 
@@ -5,9 +8,6 @@
 #include <linux/sched.h>
 #include <linux/tracepoint.h>
 
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM workqueue
-
 TRACE_EVENT(workqueue_insertion,
 
 	TP_PROTO(struct task_struct *wq_thread, struct work_struct *work),
diff --git a/include/trace/ftrace.h b/include/trace/ftrace.h
index 1867553c61e..f64fbaae781 100644
--- a/include/trace/ftrace.h
+++ b/include/trace/ftrace.h
@@ -144,6 +144,9 @@
 #undef TP_fast_assign
 #define TP_fast_assign(args...) args
 
+#undef TP_perf_assign
+#define TP_perf_assign(args...)
+
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
 static int								\
@@ -345,6 +348,56 @@ static inline int ftrace_get_offsets_##call(				\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+#ifdef CONFIG_EVENT_PROFILE
+
+/*
+ * Generate the functions needed for tracepoint perf_counter support.
+ *
+ * NOTE: The insertion profile callback (ftrace_profile_<call>) is defined later
+ *
+ * static int ftrace_profile_enable_<call>(struct ftrace_event_call *event_call)
+ * {
+ * 	int ret = 0;
+ *
+ * 	if (!atomic_inc_return(&event_call->profile_count))
+ * 		ret = register_trace_<call>(ftrace_profile_<call>);
+ *
+ * 	return ret;
+ * }
+ *
+ * static void ftrace_profile_disable_<call>(struct ftrace_event_call *event_call)
+ * {
+ * 	if (atomic_add_negative(-1, &event->call->profile_count))
+ * 		unregister_trace_<call>(ftrace_profile_<call>);
+ * }
+ *
+ */
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+									\
+static void ftrace_profile_##call(proto);				\
+									\
+static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
+{									\
+	int ret = 0;							\
+									\
+	if (!atomic_inc_return(&event_call->profile_count))		\
+		ret = register_trace_##call(ftrace_profile_##call);	\
+									\
+	return ret;							\
+}									\
+									\
+static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
+{									\
+	if (atomic_add_negative(-1, &event_call->profile_count))	\
+		unregister_trace_##call(ftrace_profile_##call);		\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+
+#endif
+
 /*
  * Stage 4 of the trace events.
  *
@@ -447,28 +500,6 @@ static inline int ftrace_get_offsets_##call(				\
 #define TP_FMT(fmt, args...)	fmt "\n", ##args
 
 #ifdef CONFIG_EVENT_PROFILE
-#define _TRACE_PROFILE(call, proto, args)				\
-static void ftrace_profile_##call(proto)				\
-{									\
-	extern void perf_tpcounter_event(int);				\
-	perf_tpcounter_event(event_##call.id);				\
-}									\
-									\
-static int ftrace_profile_enable_##call(struct ftrace_event_call *event_call) \
-{									\
-	int ret = 0;							\
-									\
-	if (!atomic_inc_return(&event_call->profile_count))		\
-		ret = register_trace_##call(ftrace_profile_##call);	\
-									\
-	return ret;							\
-}									\
-									\
-static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
-{									\
-	if (atomic_add_negative(-1, &event_call->profile_count))	\
-		unregister_trace_##call(ftrace_profile_##call);		\
-}
 
 #define _TRACE_PROFILE_INIT(call)					\
 	.profile_count = ATOMIC_INIT(-1),				\
@@ -476,7 +507,6 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
 	.profile_disable = ftrace_profile_disable_##call,
 
 #else
-#define _TRACE_PROFILE(call, proto, args)
 #define _TRACE_PROFILE_INIT(call)
 #endif
 
@@ -502,7 +532,6 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
 
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
-_TRACE_PROFILE(call, PARAMS(proto), PARAMS(args))			\
 									\
 static struct ftrace_event_call event_##call;				\
 									\
@@ -586,6 +615,110 @@ __attribute__((section("_ftrace_events"))) event_##call = {		\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#undef _TRACE_PROFILE
+/*
+ * Define the insertion callback to profile events
+ *
+ * The job is very similar to ftrace_raw_event_<call> except that we don't
+ * insert in the ring buffer but in a perf counter.
+ *
+ * static void ftrace_profile_<call>(proto)
+ * {
+ *	struct ftrace_data_offsets_<call> __maybe_unused __data_offsets;
+ *	struct ftrace_event_call *event_call = &event_<call>;
+ *	extern void perf_tpcounter_event(int, u64, u64, void *, int);
+ *	struct ftrace_raw_##call *entry;
+ *	u64 __addr = 0, __count = 1;
+ *	unsigned long irq_flags;
+ *	int __entry_size;
+ *	int __data_size;
+ *	int pc;
+ *
+ *	local_save_flags(irq_flags);
+ *	pc = preempt_count();
+ *
+ *	__data_size = ftrace_get_offsets_<call>(&__data_offsets, args);
+ *
+ *	// Below we want to get the aligned size by taking into account
+ *	// the u32 field that will later store the buffer size
+ *	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),
+ *			     sizeof(u64));
+ *	__entry_size -= sizeof(u32);
+ *
+ *	do {
+ *		char raw_data[__entry_size]; <- allocate our sample in the stack
+ *		struct trace_entry *ent;
+ *
+ *		zero dead bytes from alignment to avoid stack leak to userspace:
+ *
+ *		*(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;
+ *
+ *		<tstruct> <- do some jobs with dynamic arrays
+ *
+ *		<assign>  <- affect our values
+ *
+ *		perf_tpcounter_event(event_call->id, __addr, __count, entry,
+ *			     __entry_size);  <- submit them to perf counter
+ *	} while (0);
+ *
+ * }
+ */
+
+#ifdef CONFIG_EVENT_PROFILE
+
+#undef __perf_addr
+#define __perf_addr(a) __addr = (a)
+
+#undef __perf_count
+#define __perf_count(c) __count = (c)
+
+#undef TRACE_EVENT
+#define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
+static void ftrace_profile_##call(proto)				\
+{									\
+	struct ftrace_data_offsets_##call __maybe_unused __data_offsets;\
+	struct ftrace_event_call *event_call = &event_##call;		\
+	extern void perf_tpcounter_event(int, u64, u64, void *, int);	\
+	struct ftrace_raw_##call *entry;				\
+	u64 __addr = 0, __count = 1;					\
+	unsigned long irq_flags;					\
+	int __entry_size;						\
+	int __data_size;						\
+	int pc;								\
+									\
+	local_save_flags(irq_flags);					\
+	pc = preempt_count();						\
+									\
+	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
+	__entry_size = ALIGN(__data_size + sizeof(*entry) + sizeof(u32),\
+			     sizeof(u64));				\
+	__entry_size -= sizeof(u32);					\
+									\
+	do {								\
+		char raw_data[__entry_size];				\
+		struct trace_entry *ent;				\
+									\
+		*(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;				\
+									\
+		tstruct							\
+									\
+		{ assign; }						\
+									\
+		perf_tpcounter_event(event_call->id, __addr, __count, entry,\
+			     __entry_size);				\
+	} while (0);							\
+									\
+}
+
+#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
+#endif /* CONFIG_EVENT_PROFILE */
+
 #undef _TRACE_PROFILE_INIT