Merge branch 'perf-core-for-linus' of...

Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (162 commits)
  tracing/kprobes: unregister_trace_probe needs to be called under mutex
  perf: expose event__process function
  perf events: Fix mmap offset determination
  perf, powerpc: fsl_emb: Restore setting perf_sample_data.period
  perf, powerpc: Convert the FSL driver to use local64_t
  perf tools: Don't keep unreferenced maps when unmaps are detected
  perf session: Invalidate last_match when removing threads from rb_tree
  perf session: Free the ref_reloc_sym memory at the right place
  x86,mmiotrace: Add support for tracing STOS instruction
  perf, sched migration: Librarize task states and event headers helpers
  perf, sched migration: Librarize the GUI class
  perf, sched migration: Make the GUI class client agnostic
  perf, sched migration: Make it vertically scrollable
  perf, sched migration: Parameterize cpu height and spacing
  perf, sched migration: Fix key bindings
  perf, sched migration: Ignore unhandled task states
  perf, sched migration: Handle ignored migrate out events
  perf: New migration tool overview
  tracing: Drop cpparg() macro
  perf: Use tracepoint_synchronize_unregister() to flush any pending tracepoint call
  ...

Fix up trivial conflicts in Makefile and drivers/cpufreq/cpufreq.c

Documentation/ABI/testing/debugfs-kmemtrace

-What:		/sys/kernel/debug/kmemtrace/
-Date:		July 2008
-Contact:	Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
-Description:
-
-In kmemtrace-enabled kernels, the following files are created:
-
-/sys/kernel/debug/kmemtrace/
-	cpu<n>		(0400)	Per-CPU tracing data, see below. (binary)
-	total_overruns	(0400)	Total number of bytes which were dropped from
-				cpu<n> files because of full buffer condition,
-				non-binary. (text)
-	abi_version	(0400)	Kernel's kmemtrace ABI version. (text)
-
-Each per-CPU file should be read according to the relay interface. That is,
-the reader should set affinity to that specific CPU and, as currently done by
-the userspace application (though there are other methods), use poll() with
-an infinite timeout before every read(). Otherwise, erroneous data may be
-read. The binary data has the following _core_ format:
-
-	Event ID	(1 byte)	Unsigned integer, one of:
-		0 - represents an allocation (KMEMTRACE_EVENT_ALLOC)
-		1 - represents a freeing of previously allocated memory
-		    (KMEMTRACE_EVENT_FREE)
-	Type ID		(1 byte)	Unsigned integer, one of:
-		0 - this is a kmalloc() / kfree()
-		1 - this is a kmem_cache_alloc() / kmem_cache_free()
-		2 - this is a __get_free_pages() et al.
-	Event size	(2 bytes)	Unsigned integer representing the
-					size of this event. Used to extend
-					kmemtrace. Discard the bytes you
-					don't know about.
-	Sequence number	(4 bytes)	Signed integer used to reorder data
-					logged on SMP machines. Wraparound
-					must be taken into account, although
-					it is unlikely.
-	Caller address	(8 bytes)	Return address to the caller.
-	Pointer to mem	(8 bytes)	Pointer to target memory area. Can be
-					NULL, but not all such calls might be
-					recorded.
-
-In case of KMEMTRACE_EVENT_ALLOC events, the next fields follow:
-
-	Requested bytes	(8 bytes)	Total number of requested bytes,
-					unsigned, must not be zero.
-	Allocated bytes (8 bytes)	Total number of actually allocated
-					bytes, unsigned, must not be lower
-					than requested bytes.
-	Requested flags	(4 bytes)	GFP flags supplied by the caller.
-	Target CPU	(4 bytes)	Signed integer, valid for event id 1.
-					If equal to -1, target CPU is the same
-					as origin CPU, but the reverse might
-					not be true.
-
-The data is made available in the same endianness the machine has.
-
-Other event ids and type ids may be defined and added. Other fields may be
-added by increasing event size, but see below for details.
-Every modification to the ABI, including new id definitions, are followed
-by bumping the ABI version by one.
-
-Adding new data to the packet (features) is done at the end of the mandatory
-data:
-	Feature size	(2 byte)
-	Feature ID	(1 byte)
-	Feature data	(Feature size - 3 bytes)
-
-
-Users:
-	kmemtrace-user - git://repo.or.cz/kmemtrace-user.git
-

Documentation/kernel-parameters.txt

@@ -1816,6 +1816,8 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	nousb		[USB] Disable the USB subsystem
 
+	nowatchdog	[KNL] Disable the lockup detector.
+
 	nowb		[ARM]
 
 	nox2apic	[X86-64,APIC] Do not enable x2APIC mode.

Documentation/trace/ftrace-design.txt

@@ -13,6 +13,9 @@ Note that this focuses on architecture implementation details only.  If you
 want more explanation of a feature in terms of common code, review the common
 ftrace.txt file.
 
+Ideally, everyone who wishes to retain performance while supporting tracing in
+their kernel should make it all the way to dynamic ftrace support.
+
 
 Prerequisites
 -------------
@@ -215,7 +218,7 @@ An arch may pass in a unique value (frame pointer) to both the entering and
 exiting of a function.  On exit, the value is compared and if it does not
 match, then it will panic the kernel.  This is largely a sanity check for bad
 code generation with gcc.  If gcc for your port sanely updates the frame
-pointer under different opitmization levels, then ignore this option.
+pointer under different optimization levels, then ignore this option.
 
 However, adding support for it isn't terribly difficult.  In your assembly code
 that calls prepare_ftrace_return(), pass the frame pointer as the 3rd argument.
@@ -234,7 +237,7 @@ If you can't trace NMI functions, then skip this option.
 
 
 HAVE_SYSCALL_TRACEPOINTS
----------------------
+------------------------
 
 You need very few things to get the syscalls tracing in an arch.
 
@@ -250,12 +253,152 @@ You need very few things to get the syscalls tracing in an arch.
 HAVE_FTRACE_MCOUNT_RECORD
 -------------------------
 
-See scripts/recordmcount.pl for more info.
+See scripts/recordmcount.pl for more info.  Just fill in the arch-specific
+details for how to locate the addresses of mcount call sites via objdump.
+This option doesn't make much sense without also implementing dynamic ftrace.
 
+
+HAVE_DYNAMIC_FTRACE
+-------------------
+
+You will first need HAVE_FTRACE_MCOUNT_RECORD and HAVE_FUNCTION_TRACER, so
+scroll your reader back up if you got over eager.
+
+Once those are out of the way, you will need to implement:
+	- asm/ftrace.h:
+		- MCOUNT_ADDR
+		- ftrace_call_adjust()
+		- struct dyn_arch_ftrace{}
+	- asm code:
+		- mcount() (new stub)
+		- ftrace_caller()
+		- ftrace_call()
+		- ftrace_stub()
+	- C code:
+		- ftrace_dyn_arch_init()
+		- ftrace_make_nop()
+		- ftrace_make_call()
+		- ftrace_update_ftrace_func()
+
+First you will need to fill out some arch details in your asm/ftrace.h.
+
+Define MCOUNT_ADDR as the address of your mcount symbol similar to:
+	#define MCOUNT_ADDR ((unsigned long)mcount)
+Since no one else will have a decl for that function, you will need to:
+	extern void mcount(void);
+
+You will also need the helper function ftrace_call_adjust().  Most people
+will be able to stub it out like so:
+	static inline unsigned long ftrace_call_adjust(unsigned long addr)
+	{
+		return addr;
+	}
 <details to be filled>
 
+Lastly you will need the custom dyn_arch_ftrace structure.  If you need
+some extra state when runtime patching arbitrary call sites, this is the
+place.  For now though, create an empty struct:
+	struct dyn_arch_ftrace {
+		/* No extra data needed */
+	};
+
+With the header out of the way, we can fill out the assembly code.  While we
+did already create a mcount() function earlier, dynamic ftrace only wants a
+stub function.  This is because the mcount() will only be used during boot
+and then all references to it will be patched out never to return.  Instead,
+the guts of the old mcount() will be used to create a new ftrace_caller()
+function.  Because the two are hard to merge, it will most likely be a lot
+easier to have two separate definitions split up by #ifdefs.  Same goes for
+the ftrace_stub() as that will now be inlined in ftrace_caller().
+
+Before we get confused anymore, let's check out some pseudo code so you can
+implement your own stuff in assembly:
 
-HAVE_DYNAMIC_FTRACE
----------------------
+void mcount(void)
+{
+	return;
+}
+
+void ftrace_caller(void)
+{
+	/* implement HAVE_FUNCTION_TRACE_MCOUNT_TEST if you desire */
+
+	/* save all state needed by the ABI (see paragraph above) */
+
+	unsigned long frompc = ...;
+	unsigned long selfpc = <return address> - MCOUNT_INSN_SIZE;
+
+ftrace_call:
+	ftrace_stub(frompc, selfpc);
+
+	/* restore all state needed by the ABI */
+
+ftrace_stub:
+	return;
+}
+
+This might look a little odd at first, but keep in mind that we will be runtime
+patching multiple things.  First, only functions that we actually want to trace
+will be patched to call ftrace_caller().  Second, since we only have one tracer
+active at a time, we will patch the ftrace_caller() function itself to call the
+specific tracer in question.  That is the point of the ftrace_call label.
+
+With that in mind, let's move on to the C code that will actually be doing the
+runtime patching.  You'll need a little knowledge of your arch's opcodes in
+order to make it through the next section.
+
+Every arch has an init callback function.  If you need to do something early on
+to initialize some state, this is the time to do that.  Otherwise, this simple
+function below should be sufficient for most people:
+
+int __init ftrace_dyn_arch_init(void *data)
+{
+	/* return value is done indirectly via data */
+	*(unsigned long *)data = 0;
+
+	return 0;
+}
+
+There are two functions that are used to do runtime patching of arbitrary
+functions.  The first is used to turn the mcount call site into a nop (which
+is what helps us retain runtime performance when not tracing).  The second is
+used to turn the mcount call site into a call to an arbitrary location (but
+typically that is ftracer_caller()).  See the general function definition in
+linux/ftrace.h for the functions:
+	ftrace_make_nop()
+	ftrace_make_call()
+The rec->ip value is the address of the mcount call site that was collected
+by the scripts/recordmcount.pl during build time.
+
+The last function is used to do runtime patching of the active tracer.  This
+will be modifying the assembly code at the location of the ftrace_call symbol
+inside of the ftrace_caller() function.  So you should have sufficient padding
+at that location to support the new function calls you'll be inserting.  Some
+people will be using a "call" type instruction while others will be using a
+"branch" type instruction.  Specifically, the function is:
+	ftrace_update_ftrace_func()
+
+
+HAVE_DYNAMIC_FTRACE + HAVE_FUNCTION_GRAPH_TRACER
+------------------------------------------------
+
+The function grapher needs a few tweaks in order to work with dynamic ftrace.
+Basically, you will need to:
+	- update:
+		- ftrace_caller()
+		- ftrace_graph_call()
+		- ftrace_graph_caller()
+	- implement:
+		- ftrace_enable_ftrace_graph_caller()
+		- ftrace_disable_ftrace_graph_caller()
 
 <details to be filled>
+Quick notes:
+	- add a nop stub after the ftrace_call location named ftrace_graph_call;
+	  stub needs to be large enough to support a call to ftrace_graph_caller()
+	- update ftrace_graph_caller() to work with being called by the new
+	  ftrace_caller() since some semantics may have changed
+	- ftrace_enable_ftrace_graph_caller() will runtime patch the
+	  ftrace_graph_call location with a call to ftrace_graph_caller()
+	- ftrace_disable_ftrace_graph_caller() will runtime patch the
+	  ftrace_graph_call location with nops

Documentation/trace/kmemtrace.txt

-			kmemtrace - Kernel Memory Tracer
-
-			  by Eduard - Gabriel Munteanu
-			     <eduard.munteanu@linux360.ro>
-
-I. Introduction
-===============
-
-kmemtrace helps kernel developers figure out two things:
-1) how different allocators (SLAB, SLUB etc.) perform
-2) how kernel code allocates memory and how much
-
-To do this, we trace every allocation and export information to the userspace
-through the relay interface. We export things such as the number of requested
-bytes, the number of bytes actually allocated (i.e. including internal
-fragmentation), whether this is a slab allocation or a plain kmalloc() and so
-on.
-
-The actual analysis is performed by a userspace tool (see section III for
-details on where to get it from). It logs the data exported by the kernel,
-processes it and (as of writing this) can provide the following information:
-- the total amount of memory allocated and fragmentation per call-site
-- the amount of memory allocated and fragmentation per allocation
-- total memory allocated and fragmentation in the collected dataset
-- number of cross-CPU allocation and frees (makes sense in NUMA environments)
-
-Moreover, it can potentially find inconsistent and erroneous behavior in
-kernel code, such as using slab free functions on kmalloc'ed memory or
-allocating less memory than requested (but not truly failed allocations).
-
-kmemtrace also makes provisions for tracing on some arch and analysing the
-data on another.
-
-II. Design and goals
-====================
-
-kmemtrace was designed to handle rather large amounts of data. Thus, it uses
-the relay interface to export whatever is logged to userspace, which then
-stores it. Analysis and reporting is done asynchronously, that is, after the
-data is collected and stored. By design, it allows one to log and analyse
-on different machines and different arches.
-
-As of writing this, the ABI is not considered stable, though it might not
-change much. However, no guarantees are made about compatibility yet. When
-deemed stable, the ABI should still allow easy extension while maintaining
-backward compatibility. This is described further in Documentation/ABI.
-
-Summary of design goals:
-	- allow logging and analysis to be done across different machines
-	- be fast and anticipate usage in high-load environments (*)
-	- be reasonably extensible
-	- make it possible for GNU/Linux distributions to have kmemtrace
-	included in their repositories
-
-(*) - one of the reasons Pekka Enberg's original userspace data analysis
-    tool's code was rewritten from Perl to C (although this is more than a
-    simple conversion)
-
-
-III. Quick usage guide
-======================
-
-1) Get a kernel that supports kmemtrace and build it accordingly (i.e. enable
-CONFIG_KMEMTRACE).
-
-2) Get the userspace tool and build it:
-$ git clone git://repo.or.cz/kmemtrace-user.git		# current repository
-$ cd kmemtrace-user/
-$ ./autogen.sh
-$ ./configure
-$ make
-
-3) Boot the kmemtrace-enabled kernel if you haven't, preferably in the
-'single' runlevel (so that relay buffers don't fill up easily), and run
-kmemtrace:
-# '$' does not mean user, but root here.
-$ mount -t debugfs none /sys/kernel/debug
-$ mount -t proc none /proc
-$ cd path/to/kmemtrace-user/
-$ ./kmemtraced
-Wait a bit, then stop it with CTRL+C.
-$ cat /sys/kernel/debug/kmemtrace/total_overruns	# Check if we didn't
-							# overrun, should
-							# be zero.
-$ (Optionally) [Run kmemtrace_check separately on each cpu[0-9]*.out file to
-		check its correctness]
-$ ./kmemtrace-report
-
-Now you should have a nice and short summary of how the allocator performs.
-
-IV. FAQ and known issues
-========================
-
-Q: 'cat /sys/kernel/debug/kmemtrace/total_overruns' is non-zero, how do I fix
-this? Should I worry?
-A: If it's non-zero, this affects kmemtrace's accuracy, depending on how
-large the number is. You can fix it by supplying a higher
-'kmemtrace.subbufs=N' kernel parameter.
----
-
-Q: kmemtrace_check reports errors, how do I fix this? Should I worry?
-A: This is a bug and should be reported. It can occur for a variety of
-reasons:
-	- possible bugs in relay code
-	- possible misuse of relay by kmemtrace
-	- timestamps being collected unorderly
-Or you may fix it yourself and send us a patch.
----
-
-Q: kmemtrace_report shows many errors, how do I fix this? Should I worry?
-A: This is a known issue and I'm working on it. These might be true errors
-in kernel code, which may have inconsistent behavior (e.g. allocating memory
-with kmem_cache_alloc() and freeing it with kfree()). Pekka Enberg pointed
-out this behavior may work with SLAB, but may fail with other allocators.
-
-It may also be due to lack of tracing in some unusual allocator functions.
-
-We don't want bug reports regarding this issue yet.
----
-
-V. See also
-===========
-
-Documentation/kernel-parameters.txt
-Documentation/ABI/testing/debugfs-kmemtrace
-

Documentation/trace/kprobetrace.txt

@@ -42,7 +42,7 @@ Synopsis of kprobe_events
   +|-offs(FETCHARG) : Fetch memory at FETCHARG +|- offs address.(**)
   NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
   FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
-		  (u8/u16/u32/u64/s8/s16/s32/s64) are supported.
+		  (u8/u16/u32/u64/s8/s16/s32/s64) and string are supported.
 
   (*) only for return probe.
   (**) this is useful for fetching a field of data structures.

MAINTAINERS

@@ -3403,13 +3403,6 @@ F:	include/linux/kmemleak.h
 F:	mm/kmemleak.c
 F:	mm/kmemleak-test.c
 
-KMEMTRACE
-M:	Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
-S:	Maintained
-F:	Documentation/trace/kmemtrace.txt
-F:	include/linux/kmemtrace.h
-F:	kernel/trace/kmemtrace.c
-
 KPROBES
 M:	Ananth N Mavinakayanahalli <ananth@in.ibm.com>
 M:	Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
@@ -5685,7 +5678,7 @@ TRACING
 M:	Steven Rostedt <rostedt@goodmis.org>
 M:	Frederic Weisbecker <fweisbec@gmail.com>
 M:	Ingo Molnar <mingo@redhat.com>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git tracing/core
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git perf/core
 S:	Maintained
 F:	Documentation/trace/ftrace.txt
 F:	arch/*/*/*/ftrace.h

Makefile

@@ -420,7 +420,7 @@ endif
 no-dot-config-targets := clean mrproper distclean \
 			 cscope TAGS tags help %docs check% coccicheck \
 			 include/linux/version.h headers_% \
-			 kernelversion
+			 kernelversion %src-pkg
 
 config-targets := 0
 mixed-targets  := 0
@@ -1168,6 +1168,8 @@ distclean: mrproper
 # rpm target kept for backward compatibility
 package-dir	:= $(srctree)/scripts/package
 
+%src-pkg: FORCE
+	$(Q)$(MAKE) $(build)=$(package-dir) $@
 %pkg: include/config/kernel.release FORCE
 	$(Q)$(MAKE) $(build)=$(package-dir) $@
 rpm: include/config/kernel.release FORCE

arch/Kconfig

@@ -151,4 +151,11 @@ config HAVE_MIXED_BREAKPOINTS_REGS
 config HAVE_USER_RETURN_NOTIFIER
 	bool
 
+config HAVE_PERF_EVENTS_NMI
+	bool
+	help
+	  System hardware can generate an NMI using the perf event
+	  subsystem.  Also has support for calculating CPU cycle events
+	  to determine how many clock cycles in a given period.
+
 source "kernel/gcov/Kconfig"

arch/alpha/include/asm/local64.h

+#include <asm-generic/local64.h>

arch/arm/include/asm/local64.h

+#include <asm-generic/local64.h>

arch/arm/kernel/perf_event.c

@@ -164,20 +164,20 @@ armpmu_event_set_period(struct perf_event *event,
 			struct hw_perf_event *hwc,
 			int idx)
 {
-	s64 left = atomic64_read(&hwc->period_left);
+	s64 left = local64_read(&hwc->period_left);
 	s64 period = hwc->sample_period;
 	int ret = 0;
 
 	if (unlikely(left <= -period)) {
 		left = period;
-		atomic64_set(&hwc->period_left, left);
+		local64_set(&hwc->period_left, left);
 		hwc->last_period = period;
 		ret = 1;
 	}
 
 	if (unlikely(left <= 0)) {
 		left += period;
-		atomic64_set(&hwc->period_left, left);
+		local64_set(&hwc->period_left, left);
 		hwc->last_period = period;
 		ret = 1;
 	}
@@ -185,7 +185,7 @@ armpmu_event_set_period(struct perf_event *event,
 	if (left > (s64)armpmu->max_period)
 		left = armpmu->max_period;
 
-	atomic64_set(&hwc->prev_count, (u64)-left);
+	local64_set(&hwc->prev_count, (u64)-left);
 
 	armpmu->write_counter(idx, (u64)(-left) & 0xffffffff);
 
@@ -204,18 +204,18 @@ armpmu_event_update(struct perf_event *event,
 	u64 delta;
 
 again:
-	prev_raw_count = atomic64_read(&hwc->prev_count);
+	prev_raw_count = local64_read(&hwc->prev_count);
 	new_raw_count = armpmu->read_counter(idx);
 
-	if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
 			     new_raw_count) != prev_raw_count)
 		goto again;
 
 	delta = (new_raw_count << shift) - (prev_raw_count << shift);
 	delta >>= shift;
 
-	atomic64_add(delta, &event->count);
-	atomic64_sub(delta, &hwc->period_left);
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);
 
 	return new_raw_count;
 }
@@ -478,7 +478,7 @@ __hw_perf_event_init(struct perf_event *event)
 	if (!hwc->sample_period) {
 		hwc->sample_period  = armpmu->max_period;
 		hwc->last_period    = hwc->sample_period;
-		atomic64_set(&hwc->period_left, hwc->sample_period);
+		local64_set(&hwc->period_left, hwc->sample_period);
 	}
 
 	err = 0;

arch/avr32/include/asm/local64.h

+#include <asm-generic/local64.h>

arch/blackfin/include/asm/local64.h

+#include <asm-generic/local64.h>

arch/cris/include/asm/local64.h

+#include <asm-generic/local64.h>

arch/frv/include/asm/local64.h

+#include <asm-generic/local64.h>

arch/frv/kernel/local64.h

+#include <asm-generic/local64.h>

arch/h8300/include/asm/local64.h

+#include <asm-generic/local64.h>

arch/ia64/include/asm/local64.h

+#include <asm-generic/local64.h>

arch/m32r/include/asm/local64.h

+#include <asm-generic/local64.h>

arch/m68k/include/asm/local64.h

+#include <asm-generic/local64.h>