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

* 'tracing-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (105 commits)
  ring-buffer: only enable ring_buffer_swap_cpu when needed
  ring-buffer: check for swapped buffers in start of committing
  tracing: report error in trace if we fail to swap latency buffer
  tracing: add trace_array_printk for internal tracers to use
  tracing: pass around ring buffer instead of tracer
  tracing: make tracing_reset safe for external use
  tracing: use timestamp to determine start of latency traces
  tracing: Remove mentioning of legacy latency_trace file from documentation
  tracing/filters: Defer pred allocation, fix memory leak
  tracing: remove users of tracing_reset
  tracing: disable buffers and synchronize_sched before resetting
  tracing: disable update max tracer while reading trace
  tracing: print out start and stop in latency traces
  ring-buffer: disable all cpu buffers when one finds a problem
  ring-buffer: do not count discarded events
  ring-buffer: remove ring_buffer_event_discard
  ring-buffer: fix ring_buffer_read crossing pages
  ring-buffer: remove unnecessary cpu_relax
  ring-buffer: do not swap buffers during a commit
  ring-buffer: do not reset while in a commit
  ...

Documentation/kernel-parameters.txt

@@ -2480,6 +2480,11 @@ and is between 256 and 4096 characters. It is defined in the file
 	trace_buf_size=nn[KMG]
 			[FTRACE] will set tracing buffer size.
 
+	trace_event=[event-list]
+			[FTRACE] Set and start specified trace events in order
+			to facilitate early boot debugging.
+			See also Documentation/trace/events.txt
+
 	trix=		[HW,OSS] MediaTrix AudioTrix Pro
 			Format:
 			<io>,<irq>,<dma>,<dma2>,<sb_io>,<sb_irq>,<sb_dma>,<mpu_io>,<mpu_irq>

Documentation/trace/events.txt

@@ -83,6 +83,15 @@ When reading one of these enable files, there are four results:
  X - there is a mixture of events enabled and disabled
  ? - this file does not affect any event
 
+2.3 Boot option
+---------------
+
+In order to facilitate early boot debugging, use boot option:
+
+	trace_event=[event-list]
+
+The format of this boot option is the same as described in section 2.1.
+
 3. Defining an event-enabled tracepoint
 =======================================
 

Documentation/trace/ftrace.txt

@@ -85,26 +85,19 @@ of ftrace. Here is a list of some of the key files:
 	This file holds the output of the trace in a human
 	readable format (described below).
 
-  latency_trace:
-
-	This file shows the same trace but the information
-	is organized more to display possible latencies
-	in the system (described below).
-
   trace_pipe:
 
 	The output is the same as the "trace" file but this
 	file is meant to be streamed with live tracing.
-	Reads from this file will block until new data
-	is retrieved. Unlike the "trace" and "latency_trace"
-	files, this file is a consumer. This means reading
-	from this file causes sequential reads to display
-	more current data. Once data is read from this
-	file, it is consumed, and will not be read
-	again with a sequential read. The "trace" and
-	"latency_trace" files are static, and if the
-	tracer is not adding more data, they will display
-	the same information every time they are read.
+	Reads from this file will block until new data is
+	retrieved.  Unlike the "trace" file, this file is a
+	consumer. This means reading from this file causes
+	sequential reads to display more current data. Once
+	data is read from this file, it is consumed, and
+	will not be read again with a sequential read. The
+	"trace" file is static, and if the tracer is not
+	adding more data,they will display the same
+	information every time they are read.
 
   trace_options:
 
@@ -117,10 +110,10 @@ of ftrace. Here is a list of some of the key files:
 	Some of the tracers record the max latency.
 	For example, the time interrupts are disabled.
 	This time is saved in this file. The max trace
-	will also be stored, and displayed by either
-	"trace" or "latency_trace".  A new max trace will
-	only be recorded if the latency is greater than
-	the value in this file. (in microseconds)
+	will also be stored, and displayed by "trace".
+	A new max trace will only be recorded if the
+	latency is greater than the value in this
+	file. (in microseconds)
 
   buffer_size_kb:
 
@@ -210,7 +203,7 @@ Here is the list of current tracers that may be configured.
 	the trace with the longest max latency.
 	See tracing_max_latency. When a new max is recorded,
 	it replaces the old trace. It is best to view this
-	trace via the latency_trace file.
+	trace with the latency-format option enabled.
 
   "preemptoff"
 
@@ -307,8 +300,8 @@ the lowest priority thread (pid 0).
 Latency trace format
 --------------------
 
-For traces that display latency times, the latency_trace file
-gives somewhat more information to see why a latency happened.
+When the latency-format option is enabled, the trace file gives
+somewhat more information to see why a latency happened.
 Here is a typical trace.
 
 # tracer: irqsoff
@@ -380,9 +373,10 @@ explains which is which.
 
 The above is mostly meaningful for kernel developers.
 
-  time: This differs from the trace file output. The trace file output
-	includes an absolute timestamp. The timestamp used by the
-	latency_trace file is relative to the start of the trace.
+  time: When the latency-format option is enabled, the trace file
+	output includes a timestamp relative to the start of the
+	trace. This differs from the output when latency-format
+	is disabled, which includes an absolute timestamp.
 
   delay: This is just to help catch your eye a bit better. And
 	 needs to be fixed to be only relative to the same CPU.
@@ -440,7 +434,8 @@ Here are the available options:
   sym-addr:
    bash-4000  [01]  1477.606694: simple_strtoul <c0339346>
 
-  verbose - This deals with the latency_trace file.
+  verbose - This deals with the trace file when the
+            latency-format option is enabled.
 
     bash  4000 1 0 00000000 00010a95 [58127d26] 1720.415ms \
     (+0.000ms): simple_strtoul (strict_strtoul)
@@ -472,7 +467,7 @@ Here are the available options:
 		the app is no longer running
 
 		The lookup is performed when you read
-		trace,trace_pipe,latency_trace. Example:
+		trace,trace_pipe. Example:
 
 		a.out-1623  [000] 40874.465068: /root/a.out[+0x480] <-/root/a.out[+0
 x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
@@ -481,6 +476,11 @@ x494] <- /root/a.out[+0x4a8] <- /lib/libc-2.7.so[+0x1e1a6]
 	       every scheduling event. Will add overhead if
 	       there's a lot of tasks running at once.
 
+  latency-format - This option changes the trace. When
+                   it is enabled, the trace displays
+                   additional information about the
+                   latencies, as described in "Latency
+                   trace format".
 
 sched_switch
 ------------
@@ -596,12 +596,13 @@ To reset the maximum, echo 0 into tracing_max_latency. Here is
 an example:
 
  # echo irqsoff > current_tracer
+ # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
  # echo 1 > tracing_enabled
  # ls -ltr
  [...]
  # echo 0 > tracing_enabled
- # cat latency_trace
+ # cat trace
 # tracer: irqsoff
 #
 irqsoff latency trace v1.1.5 on 2.6.26
@@ -703,12 +704,13 @@ which preemption was disabled. The control of preemptoff tracer
 is much like the irqsoff tracer.
 
  # echo preemptoff > current_tracer
+ # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
  # echo 1 > tracing_enabled
  # ls -ltr
  [...]
  # echo 0 > tracing_enabled
- # cat latency_trace
+ # cat trace
 # tracer: preemptoff
 #
 preemptoff latency trace v1.1.5 on 2.6.26-rc8
@@ -850,12 +852,13 @@ Again, using this trace is much like the irqsoff and preemptoff
 tracers.
 
  # echo preemptirqsoff > current_tracer
+ # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
  # echo 1 > tracing_enabled
  # ls -ltr
  [...]
  # echo 0 > tracing_enabled
- # cat latency_trace
+ # cat trace
 # tracer: preemptirqsoff
 #
 preemptirqsoff latency trace v1.1.5 on 2.6.26-rc8
@@ -1012,11 +1015,12 @@ Instead of performing an 'ls', we will run 'sleep 1' under
 'chrt' which changes the priority of the task.
 
  # echo wakeup > current_tracer
+ # echo latency-format > trace_options
  # echo 0 > tracing_max_latency
  # echo 1 > tracing_enabled
  # chrt -f 5 sleep 1
  # echo 0 > tracing_enabled
- # cat latency_trace
+ # cat trace
 # tracer: wakeup
 #
 wakeup latency trace v1.1.5 on 2.6.26-rc8

Documentation/trace/function-graph-fold.vim

@@ -0,0 +1,42 @@
+" Enable folding for ftrace function_graph traces.
+"
+" To use, :source this file while viewing a function_graph trace, or use vim's
+" -S option to load from the command-line together with a trace.  You can then
+" use the usual vim fold commands, such as "za", to open and close nested
+" functions.  While closed, a fold will show the total time taken for a call,
+" as would normally appear on the line with the closing brace.  Folded
+" functions will not include finish_task_switch(), so folding should remain
+" relatively sane even through a context switch.
+"
+" Note that this will almost certainly only work well with a
+" single-CPU trace (e.g. trace-cmd report --cpu 1).
+
+function! FunctionGraphFoldExpr(lnum)
+  let line = getline(a:lnum)
+  if line[-1:] == '{'
+    if line =~ 'finish_task_switch() {$'
+      return '>1'
+    endif
+    return 'a1'
+  elseif line[-1:] == '}'
+    return 's1'
+  else
+    return '='
+  endif
+endfunction
+
+function! FunctionGraphFoldText()
+  let s = split(getline(v:foldstart), '|', 1)
+  if getline(v:foldend+1) =~ 'finish_task_switch() {$'
+    let s[2] = ' task switch  '
+  else
+    let e = split(getline(v:foldend), '|', 1)
+    let s[2] = e[2]
+  endif
+  return join(s, '|')
+endfunction
+
+setlocal foldexpr=FunctionGraphFoldExpr(v:lnum)
+setlocal foldtext=FunctionGraphFoldText()
+setlocal foldcolumn=12
+setlocal foldmethod=expr

arch/s390/Kconfig

@@ -84,7 +84,7 @@ config S390
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_FTRACE_MCOUNT_RECORD
-	select HAVE_FTRACE_SYSCALLS
+	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_DEFAULT_NO_SPIN_MUTEXES

arch/s390/defconfig

@@ -900,7 +900,7 @@ CONFIG_HAVE_FUNCTION_GRAPH_TRACER=y
 CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
-CONFIG_HAVE_FTRACE_SYSCALLS=y
+CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
 CONFIG_TRACING_SUPPORT=y
 CONFIG_FTRACE=y
 # CONFIG_FUNCTION_TRACER is not set

arch/s390/include/asm/thread_info.h

@@ -92,7 +92,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_SYSCALL_TRACE	8	/* syscall trace active */
 #define TIF_SYSCALL_AUDIT	9	/* syscall auditing active */
 #define TIF_SECCOMP		10	/* secure computing */
-#define TIF_SYSCALL_FTRACE	11	/* ftrace syscall instrumentation */
+#define TIF_SYSCALL_TRACEPOINT	11	/* syscall tracepoint instrumentation */
 #define TIF_USEDFPU		16	/* FPU was used by this task this quantum (SMP) */
 #define TIF_POLLING_NRFLAG	17	/* true if poll_idle() is polling 
 					   TIF_NEED_RESCHED */
@@ -111,7 +111,7 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_TRACE	(1<<TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1<<TIF_SYSCALL_AUDIT)
 #define _TIF_SECCOMP		(1<<TIF_SECCOMP)
-#define _TIF_SYSCALL_FTRACE	(1<<TIF_SYSCALL_FTRACE)
+#define _TIF_SYSCALL_TRACEPOINT	(1<<TIF_SYSCALL_TRACEPOINT)
 #define _TIF_USEDFPU		(1<<TIF_USEDFPU)
 #define _TIF_POLLING_NRFLAG	(1<<TIF_POLLING_NRFLAG)
 #define _TIF_31BIT		(1<<TIF_31BIT)

arch/s390/kernel/entry.S

@@ -54,7 +54,7 @@ _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 		 _TIF_MCCK_PENDING)
 _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \
-		_TIF_SECCOMP>>8 | _TIF_SYSCALL_FTRACE>>8)
+		_TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8)
 
 STACK_SHIFT = PAGE_SHIFT + THREAD_ORDER
 STACK_SIZE  = 1 << STACK_SHIFT

arch/s390/kernel/entry64.S

@@ -57,7 +57,7 @@ _TIF_WORK_SVC = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 _TIF_WORK_INT = (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_NEED_RESCHED | \
 		 _TIF_MCCK_PENDING)
 _TIF_SYSCALL = (_TIF_SYSCALL_TRACE>>8 | _TIF_SYSCALL_AUDIT>>8 | \
-		_TIF_SECCOMP>>8 | _TIF_SYSCALL_FTRACE>>8)
+		_TIF_SECCOMP>>8 | _TIF_SYSCALL_TRACEPOINT>>8)
 
 #define BASED(name) name-system_call(%r13)
 

arch/s390/kernel/ftrace.c

@@ -220,6 +220,29 @@ struct syscall_metadata *syscall_nr_to_meta(int nr)
 	return syscalls_metadata[nr];
 }
 
+int syscall_name_to_nr(char *name)
+{
+	int i;
+
+	if (!syscalls_metadata)
+		return -1;
+	for (i = 0; i < NR_syscalls; i++)
+		if (syscalls_metadata[i])
+			if (!strcmp(syscalls_metadata[i]->name, name))
+				return i;
+	return -1;
+}
+
+void set_syscall_enter_id(int num, int id)
+{
+	syscalls_metadata[num]->enter_id = id;
+}
+
+void set_syscall_exit_id(int num, int id)
+{
+	syscalls_metadata[num]->exit_id = id;
+}
+
 static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
 {
 	struct syscall_metadata *start;
@@ -237,24 +260,19 @@ static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
 	return NULL;
 }
 
-void arch_init_ftrace_syscalls(void)
+static int __init arch_init_ftrace_syscalls(void)
 {
 	struct syscall_metadata *meta;
 	int i;
-	static atomic_t refs;
-
-	if (atomic_inc_return(&refs) != 1)
-		goto out;
 	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) * NR_syscalls,
 				    GFP_KERNEL);
 	if (!syscalls_metadata)
-		goto out;
+		return -ENOMEM;
 	for (i = 0; i < NR_syscalls; i++) {
 		meta = find_syscall_meta((unsigned long)sys_call_table[i]);
 		syscalls_metadata[i] = meta;
 	}
-	return;
-out:
-	atomic_dec(&refs);
+	return 0;
 }
+arch_initcall(arch_init_ftrace_syscalls);
 #endif

arch/s390/kernel/ptrace.c

@@ -51,6 +51,9 @@
 #include "compat_ptrace.h"
 #endif
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
 enum s390_regset {
 	REGSET_GENERAL,
 	REGSET_FP,
@@ -661,8 +664,8 @@ asmlinkage long do_syscall_trace_enter(struct pt_regs *regs)
 		ret = -1;
 	}
 
-	if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
-		ftrace_syscall_enter(regs);
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_enter(regs, regs->gprs[2]);
 
 	if (unlikely(current->audit_context))
 		audit_syscall_entry(is_compat_task() ?
@@ -679,8 +682,8 @@ asmlinkage void do_syscall_trace_exit(struct pt_regs *regs)
 		audit_syscall_exit(AUDITSC_RESULT(regs->gprs[2]),
 				   regs->gprs[2]);
 
-	if (unlikely(test_thread_flag(TIF_SYSCALL_FTRACE)))
-		ftrace_syscall_exit(regs);
+	if (unlikely(test_thread_flag(TIF_SYSCALL_TRACEPOINT)))
+		trace_sys_exit(regs, regs->gprs[2]);
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, 0);

arch/x86/Kconfig

@@ -38,7 +38,7 @@ config X86
 	select HAVE_FUNCTION_GRAPH_FP_TEST
 	select HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	select HAVE_FTRACE_NMI_ENTER if DYNAMIC_FTRACE
-	select HAVE_FTRACE_SYSCALLS
+	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_KVM
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK

arch/x86/configs/i386_defconfig

@@ -2355,7 +2355,7 @@ CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_HAVE_HW_BRANCH_TRACER=y
-CONFIG_HAVE_FTRACE_SYSCALLS=y
+CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
 CONFIG_TRACING_SUPPORT=y

arch/x86/configs/x86_64_defconfig

@@ -2329,7 +2329,7 @@ CONFIG_HAVE_FUNCTION_TRACE_MCOUNT_TEST=y
 CONFIG_HAVE_DYNAMIC_FTRACE=y
 CONFIG_HAVE_FTRACE_MCOUNT_RECORD=y
 CONFIG_HAVE_HW_BRANCH_TRACER=y
-CONFIG_HAVE_FTRACE_SYSCALLS=y
+CONFIG_HAVE_SYSCALL_TRACEPOINTS=y
 CONFIG_RING_BUFFER=y
 CONFIG_TRACING=y
 CONFIG_TRACING_SUPPORT=y

arch/x86/include/asm/ftrace.h

@@ -28,13 +28,6 @@
 
 #endif
 
-/* FIXME: I don't want to stay hardcoded */
-#ifdef CONFIG_X86_64
-# define FTRACE_SYSCALL_MAX     296
-#else
-# define FTRACE_SYSCALL_MAX     333
-#endif
-
 #ifdef CONFIG_FUNCTION_TRACER
 #define MCOUNT_ADDR		((long)(mcount))
 #define MCOUNT_INSN_SIZE	5 /* sizeof mcount call */

arch/x86/include/asm/thread_info.h

@@ -95,7 +95,7 @@ struct thread_info {
 #define TIF_DEBUGCTLMSR		25	/* uses thread_struct.debugctlmsr */
 #define TIF_DS_AREA_MSR		26      /* uses thread_struct.ds_area_msr */
 #define TIF_LAZY_MMU_UPDATES	27	/* task is updating the mmu lazily */
-#define TIF_SYSCALL_FTRACE	28	/* for ftrace syscall instrumentation */
+#define TIF_SYSCALL_TRACEPOINT	28	/* syscall tracepoint instrumentation */
 
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
@@ -118,17 +118,17 @@ struct thread_info {
 #define _TIF_DEBUGCTLMSR	(1 << TIF_DEBUGCTLMSR)
 #define _TIF_DS_AREA_MSR	(1 << TIF_DS_AREA_MSR)
 #define _TIF_LAZY_MMU_UPDATES	(1 << TIF_LAZY_MMU_UPDATES)
-#define _TIF_SYSCALL_FTRACE	(1 << TIF_SYSCALL_FTRACE)
+#define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 
 /* work to do in syscall_trace_enter() */
 #define _TIF_WORK_SYSCALL_ENTRY	\
-	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_FTRACE |	\
-	 _TIF_SYSCALL_AUDIT | _TIF_SECCOMP | _TIF_SINGLESTEP)
+	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_EMU | _TIF_SYSCALL_AUDIT |	\
+	 _TIF_SECCOMP | _TIF_SINGLESTEP | _TIF_SYSCALL_TRACEPOINT)
 
 /* work to do in syscall_trace_leave() */
 #define _TIF_WORK_SYSCALL_EXIT	\
 	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | _TIF_SINGLESTEP |	\
-	 _TIF_SYSCALL_FTRACE)
+	 _TIF_SYSCALL_TRACEPOINT)
 
 /* work to do on interrupt/exception return */
 #define _TIF_WORK_MASK							\
@@ -137,7 +137,8 @@ struct thread_info {
 	   _TIF_SINGLESTEP|_TIF_SECCOMP|_TIF_SYSCALL_EMU))
 
 /* work to do on any return to user space */
-#define _TIF_ALLWORK_MASK ((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_FTRACE)
+#define _TIF_ALLWORK_MASK						\
+	((0x0000FFFF & ~_TIF_SECCOMP) | _TIF_SYSCALL_TRACEPOINT)
 
 /* Only used for 64 bit */
 #define _TIF_DO_NOTIFY_MASK						\

arch/x86/include/asm/unistd_32.h

@@ -345,6 +345,8 @@
 
 #ifdef __KERNEL__
 
+#define NR_syscalls 337
+
 #define __ARCH_WANT_IPC_PARSE_VERSION
 #define __ARCH_WANT_OLD_READDIR
 #define __ARCH_WANT_OLD_STAT

arch/x86/include/asm/unistd_64.h

@@ -688,6 +688,12 @@ __SYSCALL(__NR_perf_counter_open, sys_perf_counter_open)
 #endif	/* __NO_STUBS */
 
 #ifdef __KERNEL__
+
+#ifndef COMPILE_OFFSETS
+#include <asm/asm-offsets.h>
+#define NR_syscalls (__NR_syscall_max + 1)
+#endif
+
 /*
  * "Conditional" syscalls
  *

arch/x86/kernel/asm-offsets_64.c

@@ -3,6 +3,7 @@
  * This code generates raw asm output which is post-processed to extract
  * and format the required data.
  */
+#define COMPILE_OFFSETS
 
 #include <linux/crypto.h>
 #include <linux/sched.h>