Merge commit 'origin/tracing/core' into rt/trace

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

 			     Event Tracing
 
 		Documentation written by Theodore Ts'o
-			Updated by Li Zefan
+		Updated by Li Zefan and Tom Zanussi
 
 1. Introduction
 ===============
@@ -83,8 +83,199 @@ 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
 =======================================
 
 See The example provided in samples/trace_events
 
+4. Event formats
+================
+
+Each trace event has a 'format' file associated with it that contains
+a description of each field in a logged event.  This information can
+be used to parse the binary trace stream, and is also the place to
+find the field names that can be used in event filters (see section 5).
+
+It also displays the format string that will be used to print the
+event in text mode, along with the event name and ID used for
+profiling.
+
+Every event has a set of 'common' fields associated with it; these are
+the fields prefixed with 'common_'.  The other fields vary between
+events and correspond to the fields defined in the TRACE_EVENT
+definition for that event.
+
+Each field in the format has the form:
+
+     field:field-type field-name; offset:N; size:N;
+
+where offset is the offset of the field in the trace record and size
+is the size of the data item, in bytes.
+
+For example, here's the information displayed for the 'sched_wakeup'
+event:
+
+# cat /debug/tracing/events/sched/sched_wakeup/format
+
+name: sched_wakeup
+ID: 60
+format:
+	field:unsigned short common_type;	offset:0;	size:2;
+	field:unsigned char common_flags;	offset:2;	size:1;
+	field:unsigned char common_preempt_count;	offset:3;	size:1;
+	field:int common_pid;	offset:4;	size:4;
+	field:int common_tgid;	offset:8;	size:4;
+
+	field:char comm[TASK_COMM_LEN];	offset:12;	size:16;
+	field:pid_t pid;	offset:28;	size:4;
+	field:int prio;	offset:32;	size:4;
+	field:int success;	offset:36;	size:4;
+	field:int cpu;	offset:40;	size:4;
+
+print fmt: "task %s:%d [%d] success=%d [%03d]", REC->comm, REC->pid,
+	   REC->prio, REC->success, REC->cpu
+
+This event contains 10 fields, the first 5 common and the remaining 5
+event-specific.  All the fields for this event are numeric, except for
+'comm' which is a string, a distinction important for event filtering.
+
+5. Event filtering
+==================
+
+Trace events can be filtered in the kernel by associating boolean
+'filter expressions' with them.  As soon as an event is logged into
+the trace buffer, its fields are checked against the filter expression
+associated with that event type.  An event with field values that
+'match' the filter will appear in the trace output, and an event whose
+values don't match will be discarded.  An event with no filter
+associated with it matches everything, and is the default when no
+filter has been set for an event.
+
+5.1 Expression syntax
+---------------------
+
+A filter expression consists of one or more 'predicates' that can be
+combined using the logical operators '&&' and '||'.  A predicate is
+simply a clause that compares the value of a field contained within a
+logged event with a constant value and returns either 0 or 1 depending
+on whether the field value matched (1) or didn't match (0):
+
+	  field-name relational-operator value
+
+Parentheses can be used to provide arbitrary logical groupings and
+double-quotes can be used to prevent the shell from interpreting
+operators as shell metacharacters.
+
+The field-names available for use in filters can be found in the
+'format' files for trace events (see section 4).
+
+The relational-operators depend on the type of the field being tested:
+
+The operators available for numeric fields are:
+
+==, !=, <, <=, >, >=
+
+And for string fields they are:
+
+==, !=
+
+Currently, only exact string matches are supported.
+
+Currently, the maximum number of predicates in a filter is 16.
+
+5.2 Setting filters
+-------------------
+
+A filter for an individual event is set by writing a filter expression
+to the 'filter' file for the given event.
+
+For example:
+
+# cd /debug/tracing/events/sched/sched_wakeup
+# echo "common_preempt_count > 4" > filter
+
+A slightly more involved example:
+
+# cd /debug/tracing/events/sched/sched_signal_send
+# echo "((sig >= 10 && sig < 15) || sig == 17) && comm != bash" > filter
+
+If there is an error in the expression, you'll get an 'Invalid
+argument' error when setting it, and the erroneous string along with
+an error message can be seen by looking at the filter e.g.:
+
+# cd /debug/tracing/events/sched/sched_signal_send
+# echo "((sig >= 10 && sig < 15) || dsig == 17) && comm != bash" > filter
+-bash: echo: write error: Invalid argument
+# cat filter
+((sig >= 10 && sig < 15) || dsig == 17) && comm != bash
+^
+parse_error: Field not found
+
+Currently the caret ('^') for an error always appears at the beginning of
+the filter string; the error message should still be useful though
+even without more accurate position info.
+
+5.3 Clearing filters
+--------------------
+
+To clear the filter for an event, write a '0' to the event's filter
+file.
+
+To clear the filters for all events in a subsystem, write a '0' to the
+subsystem's filter file.
+
+5.3 Subsystem filters
+---------------------
+
+For convenience, filters for every event in a subsystem can be set or
+cleared as a group by writing a filter expression into the filter file
+at the root of the subsytem.  Note however, that if a filter for any
+event within the subsystem lacks a field specified in the subsystem
+filter, or if the filter can't be applied for any other reason, the
+filter for that event will retain its previous setting.  This can
+result in an unintended mixture of filters which could lead to
+confusing (to the user who might think different filters are in
+effect) trace output.  Only filters that reference just the common
+fields can be guaranteed to propagate successfully to all events.
+
+Here are a few subsystem filter examples that also illustrate the
+above points:
+
+Clear the filters on all events in the sched subsytem:
+
+# cd /sys/kernel/debug/tracing/events/sched
+# echo 0 > filter
+# cat sched_switch/filter
+none
+# cat sched_wakeup/filter
+none
+
+Set a filter using only common fields for all events in the sched
+subsytem (all events end up with the same filter):
+
+# cd /sys/kernel/debug/tracing/events/sched
+# echo common_pid == 0 > filter
+# cat sched_switch/filter
+common_pid == 0
+# cat sched_wakeup/filter
+common_pid == 0
+
+Attempt to set a filter using a non-common field for all events in the
+sched subsytem (all events but those that have a prev_pid field retain
+their old filters):
+
+# cd /sys/kernel/debug/tracing/events/sched
+# echo prev_pid == 0 > filter
+# cat sched_switch/filter
+prev_pid == 0
+# cat sched_wakeup/filter
+common_pid == 0

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

+" 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/nops.h

@@ -65,6 +65,8 @@
    6: osp nopl 0x00(%eax,%eax,1)
    7: nopl 0x00000000(%eax)
    8: nopl 0x00000000(%eax,%eax,1)
+   Note: All the above are assumed to be a single instruction.
+	There is kernel code that depends on this.
 */
 #define P6_NOP1	GENERIC_NOP1
 #define P6_NOP2	".byte 0x66,0x90\n"

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> 

arch/x86/kernel/entry_64.S

@@ -146,7 +146,7 @@ ENTRY(ftrace_graph_caller)
 END(ftrace_graph_caller)
 
 GLOBAL(return_to_handler)
-	subq  $80, %rsp
+	subq  $24, %rsp
 
 	/* Save the return values */
 	movq %rax, (%rsp)
@@ -155,10 +155,10 @@ GLOBAL(return_to_handler)
 
 	call ftrace_return_to_handler
 
-	movq %rax, 72(%rsp)
+	movq %rax, 16(%rsp)
 	movq 8(%rsp), %rdx
 	movq (%rsp), %rax
-	addq $72, %rsp
+	addq $16, %rsp
 	retq
 #endif
 

arch/x86/kernel/ftrace.c

@@ -417,10 +417,6 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	unsigned long return_hooker = (unsigned long)
 				&return_to_handler;
 
-	/* Nmi's are currently unsupported */
-	if (unlikely(in_nmi()))
-		return;
-
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
@@ -498,37 +494,56 @@ static struct syscall_metadata *find_syscall_meta(unsigned long *syscall)
 
 struct syscall_metadata *syscall_nr_to_meta(int nr)
 {
-	if (!syscalls_metadata || nr >= FTRACE_SYSCALL_MAX || nr < 0)
+	if (!syscalls_metadata || nr >= NR_syscalls || nr < 0)
 		return NULL;
 
 	return syscalls_metadata[nr];
 }
 
-void arch_init_ftrace_syscalls(void)
+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 int __init arch_init_ftrace_syscalls(void)
 {
 	int i;
 	struct syscall_metadata *meta;
 	unsigned long **psys_syscall_table = &sys_call_table;
-	static atomic_t refs;
-
-	if (atomic_inc_return(&refs) != 1)
-		goto end;
 
 	syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
-					FTRACE_SYSCALL_MAX, GFP_KERNEL);
+					NR_syscalls, GFP_KERNEL);
 	if (!syscalls_metadata) {
 		WARN_ON(1);
-		return;
+		return -ENOMEM;
 	}
 
-	for (i = 0; i < FTRACE_SYSCALL_MAX; i++) {
+	for (i = 0; i < NR_syscalls; i++) {
 		meta = find_syscall_meta(psys_syscall_table[i]);
 		syscalls_metadata[i] = meta;
 	}
-	return;
-
-	/* Paranoid: avoid overflow */
-end:
-	atomic_dec(&refs);
+	return 0;
 }
+arch_initcall(arch_init_ftrace_syscalls);
 #endif

arch/x86/kernel/ptrace.c

@@ -35,10 +35,11 @@
 #include <asm/proto.h>
 #include <asm/ds.h>
 
-#include <trace/syscall.h>
-
 #include "tls.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
 enum x86_regset {
 	REGSET_GENERAL,
 	REGSET_FP,
@@ -1497,8 +1498,8 @@ asmregparm long syscall_trace_enter(struct pt_regs *regs)
 	    tracehook_report_syscall_entry(regs))
 		ret = -1L;
 
-	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->orig_ax);
 
 	if (unlikely(current->audit_context)) {
 		if (IS_IA32)
@@ -1523,8 +1524,8 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs)
 	if (unlikely(current->audit_context))
 		audit_syscall_exit(AUDITSC_RESULT(regs->ax), regs->ax);
 
-	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->ax);
 
 	if (test_thread_flag(TIF_SYSCALL_TRACE))
 		tracehook_report_syscall_exit(regs, 0);

arch/x86/kernel/sys_x86_64.c

@@ -18,9 +18,9 @@
 #include <asm/ia32.h>
 #include <asm/syscalls.h>
 
-asmlinkage long sys_mmap(unsigned long addr, unsigned long len,
-		unsigned long prot, unsigned long flags,
-		unsigned long fd, unsigned long off)
+SYSCALL_DEFINE6(mmap, unsigned long, addr, unsigned long, len,
+		unsigned long, prot, unsigned long, flags,
+		unsigned long, fd, unsigned long, off)
 {
 	long error;
 	struct file *file;
@@ -226,7 +226,7 @@ bottomup:
 }
 
 
-asmlinkage long sys_uname(struct new_utsname __user *name)
+SYSCALL_DEFINE1(uname, struct new_utsname __user *, name)
 {
 	int err;
 	down_read(&uts_sem);

include/asm-generic/vmlinux.lds.h

@@ -91,7 +91,8 @@
 #endif
 
 #ifdef CONFIG_FTRACE_MCOUNT_RECORD
-#define MCOUNT_REC()	VMLINUX_SYMBOL(__start_mcount_loc) = .; \
+#define MCOUNT_REC()	. = ALIGN(8);				\
+			VMLINUX_SYMBOL(__start_mcount_loc) = .; \
 			*(__mcount_loc)				\
 			VMLINUX_SYMBOL(__stop_mcount_loc) = .;
 #else
@@ -331,7 +332,6 @@
 	/* __*init sections */						\
 	__init_rodata : AT(ADDR(__init_rodata) - LOAD_OFFSET) {		\
 		*(.ref.rodata)						\
-		MCOUNT_REC()						\
 		DEV_KEEP(init.rodata)					\
 		DEV_KEEP(exit.rodata)					\
 		CPU_KEEP(init.rodata)					\
@@ -455,6 +455,7 @@
 	MEM_DISCARD(init.data)						\
 	KERNEL_CTORS()							\
 	*(.init.rodata)							\
+	MCOUNT_REC()							\
 	DEV_DISCARD(init.rodata)					\
 	CPU_DISCARD(init.rodata)					\
 	MEM_DISCARD(init.rodata)

include/linux/ftrace_event.h

 #ifndef _LINUX_FTRACE_EVENT_H
 #define _LINUX_FTRACE_EVENT_H
 
-#include <linux/trace_seq.h>
 #include <linux/ring_buffer.h>
+#include <linux/trace_seq.h>
 #include <linux/percpu.h>
 
 struct trace_array;
@@ -34,7 +34,7 @@ struct trace_entry {
 	unsigned char		flags;
 	unsigned char		preempt_count;
 	int			pid;
-	int			tgid;
+	int			lock_depth;
 };
 
 #define FTRACE_MAX_EVENT						\
@@ -93,16 +93,22 @@ void tracing_generic_entry_update(struct trace_entry *entry,
 				  unsigned long flags,
 				  int pc);
 struct ring_buffer_event *
-trace_current_buffer_lock_reserve(int type, unsigned long len,
+trace_current_buffer_lock_reserve(struct ring_buffer **current_buffer,
+				  int type, unsigned long len,
 				  unsigned long flags, int pc);
-void trace_current_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_current_buffer_unlock_commit(struct ring_buffer *buffer,
+					struct ring_buffer_event *event,
 					unsigned long flags, int pc);
-void trace_nowake_buffer_unlock_commit(struct ring_buffer_event *event,
+void trace_nowake_buffer_unlock_commit(struct ring_buffer *buffer,
+				       struct ring_buffer_event *event,
 					unsigned long flags, int pc);
-void trace_current_buffer_discard_commit(struct ring_buffer_event *event);
+void trace_current_buffer_discard_commit(struct ring_buffer *buffer,
+					 struct ring_buffer_event *event);
 
 void tracing_record_cmdline(struct task_struct *tsk);
 
+struct event_filter;
+
 struct ftrace_event_call {
 	struct list_head	list;
 	char			*name;
@@ -110,16 +116,18 @@ struct ftrace_event_call {
 	struct dentry		*dir;
 	struct trace_event	*event;
 	int			enabled;
-	int			(*regfunc)(void);
-	void			(*unregfunc)(void);
+	int			(*regfunc)(void *);
+	void			(*unregfunc)(void *);
 	int			id;
 	int			(*raw_init)(void);
-	int			(*show_format)(struct trace_seq *s);
-	int			(*define_fields)(void);
+	int			(*show_format)(struct ftrace_event_call *call,
+					       struct trace_seq *s);
+	int			(*define_fields)(struct ftrace_event_call *);
 	struct list_head	fields;
 	int			filter_active;
-	void			*filter;
+	struct event_filter	*filter;
 	void			*mod;
+	void			*data;
 
 	atomic_t		profile_count;
 	int			(*profile_enable)(struct ftrace_event_call *);
@@ -127,17 +135,27 @@ struct ftrace_event_call {
 };
 
 #define MAX_FILTER_PRED		32
-#define MAX_FILTER_STR_VAL	128
+#define MAX_FILTER_STR_VAL	256	/* Should handle KSYM_SYMBOL_LEN */
 
-extern int init_preds(struct ftrace_event_call *call);
 extern void destroy_preds(struct ftrace_event_call *call);
 extern int filter_match_preds(struct ftrace_event_call *call, void *rec);
-extern int filter_current_check_discard(struct ftrace_event_call *call,
+extern int filter_current_check_discard(struct ring_buffer *buffer,
+					struct ftrace_event_call *call,
 					void *rec,
 					struct ring_buffer_event *event);
 
-extern int trace_define_field(struct ftrace_event_call *call, char *type,
-			      char *name, int offset, int size, int is_signed);
+enum {
+	FILTER_OTHER = 0,
+	FILTER_STATIC_STRING,
+	FILTER_DYN_STRING,
+	FILTER_PTR_STRING,
+};
+
+extern int trace_define_field(struct ftrace_event_call *call,
+			      const char *type, const char *name,
+			      int offset, int size, int is_signed,
+			      int filter_type);
+extern int trace_define_common_fields(struct ftrace_event_call *call);
 
 #define is_signed_type(type)	(((type)(-1)) < 0)
 
@@ -162,11 +180,4 @@ do {									\
 		__trace_printk(ip, fmt, ##args);			\
 } while (0)
 
-#define __common_field(type, item, is_signed)				\
-	ret = trace_define_field(event_call, #type, "common_" #item,	\
-				 offsetof(typeof(field.ent), item),	\
-				 sizeof(field.ent.item), is_signed);	\
-	if (ret)							\
-		return ret;
-
 #endif /* _LINUX_FTRACE_EVENT_H */

include/linux/module.h

@@ -17,10 +17,12 @@
 #include <linux/moduleparam.h>
 #include <linux/marker.h>
 #include <linux/tracepoint.h>
-#include <asm/local.h>
 
+#include <asm/local.h>
 #include <asm/module.h>
 
+#include <trace/events/module.h>
+
 /* Not Yet Implemented */
 #define MODULE_SUPPORTED_DEVICE(name)
 
@@ -462,7 +464,10 @@ static inline local_t *__module_ref_addr(struct module *mod, int cpu)
 static inline void __module_get(struct module *module)
 {
 	if (module) {
-		local_inc(__module_ref_addr(module, get_cpu()));
+		unsigned int cpu = get_cpu();
+		local_inc(__module_ref_addr(module, cpu));
+		trace_module_get(module, _THIS_IP_,
+				 local_read(__module_ref_addr(module, cpu)));
 		put_cpu();
 	}
 }
@@ -473,8 +478,11 @@ static inline int try_module_get(struct module *module)
 
 	if (module) {
 		unsigned int cpu = get_cpu();
-		if (likely(module_is_live(module)))
+		if (likely(module_is_live(module))) {
 			local_inc(__module_ref_addr(module, cpu));
+			trace_module_get(module, _THIS_IP_,
+				local_read(__module_ref_addr(module, cpu)));
+		}
 		else
 			ret = 0;
 		put_cpu();

include/linux/perf_counter.h

@@ -761,6 +761,8 @@ extern int sysctl_perf_counter_mlock;
 extern int sysctl_perf_counter_sample_rate;
 
 extern void perf_counter_init(void);
+extern void perf_tpcounter_event(int event_id, u64 addr, u64 count,
+				 void *record, int entry_size);
 
 #ifndef perf_misc_flags
 #define perf_misc_flags(regs)	(user_mode(regs) ? PERF_EVENT_MISC_USER : \

include/linux/ring_buffer.h

@@ -74,20 +74,6 @@ ring_buffer_event_time_delta(struct ring_buffer_event *event)
 	return event->time_delta;
 }
 
-/*
- * ring_buffer_event_discard can discard any event in the ring buffer.
- *   it is up to the caller to protect against a reader from
- *   consuming it or a writer from wrapping and replacing it.
- *
- * No external protection is needed if this is called before
- * the event is commited. But in that case it would be better to
- * use ring_buffer_discard_commit.
- *
- * Note, if an event that has not been committed is discarded
- * with ring_buffer_event_discard, it must still be committed.
- */
-void ring_buffer_event_discard(struct ring_buffer_event *event);
-
 /*
  * ring_buffer_discard_commit will remove an event that has not
  *   ben committed yet. If this is used, then ring_buffer_unlock_commit
@@ -154,8 +140,17 @@ unsigned long ring_buffer_size(struct ring_buffer *buffer);
 void ring_buffer_reset_cpu(struct ring_buffer *buffer, int cpu);
 void ring_buffer_reset(struct ring_buffer *buffer);
 
+#ifdef CONFIG_RING_BUFFER_ALLOW_SWAP
 int ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
 			 struct ring_buffer *buffer_b, int cpu);
+#else
+static inline int
+ring_buffer_swap_cpu(struct ring_buffer *buffer_a,
+		     struct ring_buffer *buffer_b, int cpu)
+{
+	return -ENODEV;
+}
+#endif
 
 int ring_buffer_empty(struct ring_buffer *buffer);
 int ring_buffer_empty_cpu(struct ring_buffer *buffer, int cpu);
@@ -170,7 +165,6 @@ unsigned long ring_buffer_overruns(struct ring_buffer *buffer);
 unsigned long ring_buffer_entries_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_overrun_cpu(struct ring_buffer *buffer, int cpu);
 unsigned long ring_buffer_commit_overrun_cpu(struct ring_buffer *buffer, int cpu);
-unsigned long ring_buffer_nmi_dropped_cpu(struct ring_buffer *buffer, int cpu);
 
 u64 ring_buffer_time_stamp(struct ring_buffer *buffer, int cpu);
 void ring_buffer_normalize_time_stamp(struct ring_buffer *buffer,

include/linux/syscalls.h

@@ -64,6 +64,7 @@ struct perf_counter_attr;
 #include <linux/sem.h>
 #include <asm/siginfo.h>
 #include <asm/signal.h>
+#include <linux/unistd.h>
 #include <linux/quota.h>
 #include <linux/key.h>
 #include <trace/syscall.h>
@@ -97,6 +98,53 @@ struct perf_counter_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
+#define TRACE_SYS_ENTER_PROFILE(sname)					       \
+static int prof_sysenter_enable_##sname(struct ftrace_event_call *event_call)  \
+{									       \
+	int ret = 0;							       \
+	if (!atomic_inc_return(&event_enter_##sname.profile_count))	       \
+		ret = reg_prof_syscall_enter("sys"#sname);		       \
+	return ret;							       \
+}									       \
+									       \
+static void prof_sysenter_disable_##sname(struct ftrace_event_call *event_call)\
+{									       \
+	if (atomic_add_negative(-1, &event_enter_##sname.profile_count))       \
+		unreg_prof_syscall_enter("sys"#sname);			       \
+}
+
+#define TRACE_SYS_EXIT_PROFILE(sname)					       \
+static int prof_sysexit_enable_##sname(struct ftrace_event_call *event_call)   \
+{									       \
+	int ret = 0;							       \
+	if (!atomic_inc_return(&event_exit_##sname.profile_count))	       \
+		ret = reg_prof_syscall_exit("sys"#sname);		       \
+	return ret;							       \
+}									       \
+									       \
+static void prof_sysexit_disable_##sname(struct ftrace_event_call *event_call) \
+{                                                                              \
+	if (atomic_add_negative(-1, &event_exit_##sname.profile_count))	       \
+		unreg_prof_syscall_exit("sys"#sname);			       \
+}
+
+#define TRACE_SYS_ENTER_PROFILE_INIT(sname)				       \
+	.profile_count = ATOMIC_INIT(-1),				       \
+	.profile_enable = prof_sysenter_enable_##sname,			       \
+	.profile_disable = prof_sysenter_disable_##sname,
+
+#define TRACE_SYS_EXIT_PROFILE_INIT(sname)				       \
+	.profile_count = ATOMIC_INIT(-1),				       \
+	.profile_enable = prof_sysexit_enable_##sname,			       \
+	.profile_disable = prof_sysexit_disable_##sname,
+#else
+#define TRACE_SYS_ENTER_PROFILE(sname)
+#define TRACE_SYS_ENTER_PROFILE_INIT(sname)
+#define TRACE_SYS_EXIT_PROFILE(sname)
+#define TRACE_SYS_EXIT_PROFILE_INIT(sname)
+#endif
+
 #ifdef CONFIG_FTRACE_SYSCALLS
 #define __SC_STR_ADECL1(t, a)		#a
 #define __SC_STR_ADECL2(t, a, ...)	#a, __SC_STR_ADECL1(__VA_ARGS__)
@@ -112,7 +160,81 @@ struct perf_counter_attr;
 #define __SC_STR_TDECL5(t, a, ...)	#t, __SC_STR_TDECL4(__VA_ARGS__)
 #define __SC_STR_TDECL6(t, a, ...)	#t, __SC_STR_TDECL5(__VA_ARGS__)
 
+#define SYSCALL_TRACE_ENTER_EVENT(sname)				\
+	static struct ftrace_event_call event_enter_##sname;		\
+	struct trace_event enter_syscall_print_##sname = {		\
+		.trace                  = print_syscall_enter,		\
+	};								\
+	static int init_enter_##sname(void)				\
+	{								\
+		int num, id;						\
+		num = syscall_name_to_nr("sys"#sname);			\
+		if (num < 0)						\
+			return -ENOSYS;					\
+		id = register_ftrace_event(&enter_syscall_print_##sname);\
+		if (!id)						\
+			return -ENODEV;					\
+		event_enter_##sname.id = id;				\
+		set_syscall_enter_id(num, id);				\
+		INIT_LIST_HEAD(&event_enter_##sname.fields);		\
+		return 0;						\
+	}								\
+	TRACE_SYS_ENTER_PROFILE(sname);					\
+	static struct ftrace_event_call __used				\
+	  __attribute__((__aligned__(4)))				\
+	  __attribute__((section("_ftrace_events")))			\
+	  event_enter_##sname = {					\
+		.name                   = "sys_enter"#sname,		\
+		.system                 = "syscalls",			\
+		.event                  = &event_syscall_enter,		\
+		.raw_init		= init_enter_##sname,		\
+		.show_format		= syscall_enter_format,		\
+		.define_fields		= syscall_enter_define_fields,	\
+		.regfunc		= reg_event_syscall_enter,	\
+		.unregfunc		= unreg_event_syscall_enter,	\
+		.data			= "sys"#sname,			\
+		TRACE_SYS_ENTER_PROFILE_INIT(sname)			\
+	}
+
+#define SYSCALL_TRACE_EXIT_EVENT(sname)					\
+	static struct ftrace_event_call event_exit_##sname;		\
+	struct trace_event exit_syscall_print_##sname = {		\
+		.trace                  = print_syscall_exit,		\
+	};								\
+	static int init_exit_##sname(void)				\
+	{								\
+		int num, id;						\
+		num = syscall_name_to_nr("sys"#sname);			\
+		if (num < 0)						\
+			return -ENOSYS;					\
+		id = register_ftrace_event(&exit_syscall_print_##sname);\
+		if (!id)						\
+			return -ENODEV;					\
+		event_exit_##sname.id = id;				\
+		set_syscall_exit_id(num, id);				\
+		INIT_LIST_HEAD(&event_exit_##sname.fields);		\
+		return 0;						\
+	}								\
+	TRACE_SYS_EXIT_PROFILE(sname);					\
+	static struct ftrace_event_call __used				\
+	  __attribute__((__aligned__(4)))				\
+	  __attribute__((section("_ftrace_events")))			\
+	  event_exit_##sname = {					\
+		.name                   = "sys_exit"#sname,		\
+		.system                 = "syscalls",			\
+		.event                  = &event_syscall_exit,		\
+		.raw_init		= init_exit_##sname,		\
+		.show_format		= syscall_exit_format,		\
+		.define_fields		= syscall_exit_define_fields,	\
+		.regfunc		= reg_event_syscall_exit,	\
+		.unregfunc		= unreg_event_syscall_exit,	\
+		.data			= "sys"#sname,			\
+		TRACE_SYS_EXIT_PROFILE_INIT(sname)			\
+	}
+
 #define SYSCALL_METADATA(sname, nb)				\
+	SYSCALL_TRACE_ENTER_EVENT(sname);			\
+	SYSCALL_TRACE_EXIT_EVENT(sname);			\
 	static const struct syscall_metadata __used		\
 	  __attribute__((__aligned__(4)))			\
 	  __attribute__((section("__syscalls_metadata")))	\
@@ -121,18 +243,23 @@ struct perf_counter_attr;
 		.nb_args 	= nb,				\
 		.types		= types_##sname,		\
 		.args		= args_##sname,			\
-	}
+		.enter_event	= &event_enter_##sname,		\
+		.exit_event	= &event_exit_##sname,		\
+	};
 
 #define SYSCALL_DEFINE0(sname)					\
+	SYSCALL_TRACE_ENTER_EVENT(_##sname);			\
+	SYSCALL_TRACE_EXIT_EVENT(_##sname);			\
 	static const struct syscall_metadata __used		\
 	  __attribute__((__aligned__(4)))			\
 	  __attribute__((section("__syscalls_metadata")))	\
 	  __syscall_meta_##sname = {				\
 		.name 		= "sys_"#sname,			\
 		.nb_args 	= 0,				\
+		.enter_event	= &event_enter__##sname,	\
+		.exit_event	= &event_exit__##sname,		\
 	};							\
 	asmlinkage long sys_##sname(void)
-
 #else
 #define SYSCALL_DEFINE0(name)	   asmlinkage long sys_##name(void)
 #endif

include/linux/tracepoint.h

@@ -23,6 +23,8 @@ struct tracepoint;
 struct tracepoint {
 	const char *name;		/* Tracepoint name */
 	int state;			/* State. */
+	void (*regfunc)(void);
+	void (*unregfunc)(void);
 	void **funcs;
 } __attribute__((aligned(32)));		/*
 					 * Aligned on 32 bytes because it is
@@ -78,12 +80,16 @@ struct tracepoint {
 		return tracepoint_probe_unregister(#name, (void *)probe);\
 	}
 
-#define DEFINE_TRACE(name)						\
+
+#define DEFINE_TRACE_FN(name, reg, unreg)				\
 	static const char __tpstrtab_##name[]				\
 	__attribute__((section("__tracepoints_strings"))) = #name;	\
 	struct tracepoint __tracepoint_##name				\
 	__attribute__((section("__tracepoints"), aligned(32))) =	\
-		{ __tpstrtab_##name, 0, NULL }
+		{ __tpstrtab_##name, 0, reg, unreg, NULL }
+
+#define DEFINE_TRACE(name)						\
+	DEFINE_TRACE_FN(name, NULL, NULL);
 
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)				\
 	EXPORT_SYMBOL_GPL(__tracepoint_##name)
@@ -108,6 +114,7 @@ extern void tracepoint_update_probe_range(struct tracepoint *begin,
 		return -ENOSYS;						\
 	}
 
+#define DEFINE_TRACE_FN(name, reg, unreg)
 #define DEFINE_TRACE(name)
 #define EXPORT_TRACEPOINT_SYMBOL_GPL(name)
 #define EXPORT_TRACEPOINT_SYMBOL(name)
@@ -158,6 +165,15 @@ static inline void tracepoint_synchronize_unregister(void)
 
 #define PARAMS(args...) args
 
+#endif /* _LINUX_TRACEPOINT_H */
+
+/*
+ * Note: we keep the TRACE_EVENT outside the include file ifdef protection.
+ *  This is due to the way trace events work. If a file includes two
+ *  trace event headers under one "CREATE_TRACE_POINTS" the first include
+ *  will override the TRACE_EVENT and break the second include.
+ */
+
 #ifndef TRACE_EVENT
 /*
  * For use with the TRACE_EVENT macro:
@@ -259,10 +275,15 @@ static inline void tracepoint_synchronize_unregister(void)
  * can also by used by generic instrumentation like SystemTap), and
  * it is also used to expose a structured trace record in
  * /sys/kernel/debug/tracing/events/.
+ *
+ * A set of (un)registration functions can be passed to the variant
+ * TRACE_EVENT_FN to perform any (un)registration work.
  */
 
 #define TRACE_EVENT(name, proto, args, struct, assign, print)	\
 	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
-#endif
+#define TRACE_EVENT_FN(name, proto, args, struct,		\
+		assign, print, reg, unreg)			\
+	DECLARE_TRACE(name, PARAMS(proto), PARAMS(args))
 
-#endif
+#endif /* ifdef TRACE_EVENT (see note above) */

include/trace/define_trace.h

@@ -26,6 +26,11 @@
 #define TRACE_EVENT(name, proto, args, tstruct, assign, print)	\
 	DEFINE_TRACE(name)
 
+#undef TRACE_EVENT_FN
+#define TRACE_EVENT_FN(name, proto, args, tstruct,		\
+		assign, print, reg, unreg)			\
+	DEFINE_TRACE_FN(name, reg, unreg)
+
 #undef DECLARE_TRACE
 #define DECLARE_TRACE(name, proto, args)	\
 	DEFINE_TRACE(name)
@@ -56,6 +61,8 @@
 #include <trace/ftrace.h>
 #endif
 
+#undef TRACE_EVENT
+#undef TRACE_EVENT_FN
 #undef TRACE_HEADER_MULTI_READ
 
 /* Only undef what we defined in this file */

include/trace/events/block.h

@@ -171,6 +171,7 @@ TRACE_EVENT(block_rq_complete,
 		  (unsigned long long)__entry->sector,
 		  __entry->nr_sector, __entry->errors)
 );
+
 TRACE_EVENT(block_bio_bounce,
 
 	TP_PROTO(struct request_queue *q, struct bio *bio),
@@ -186,7 +187,8 @@ TRACE_EVENT(block_bio_bounce,
 	),
 
 	TP_fast_assign(
-		__entry->dev		= bio->bi_bdev->bd_dev;
+		__entry->dev		= bio->bi_bdev ?
+					  bio->bi_bdev->bd_dev : 0;
 		__entry->sector		= bio->bi_sector;
 		__entry->nr_sector	= bio->bi_size >> 9;
 		blk_fill_rwbs(__entry->rwbs, bio->bi_rw, bio->bi_size);

include/trace/events/module.h

+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM module
+
+#if !defined(_TRACE_MODULE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_MODULE_H
+
+#include <linux/tracepoint.h>
+
+#ifdef CONFIG_MODULES
+
+struct module;
+
+#define show_module_flags(flags) __print_flags(flags, "",	\
+	{ (1UL << TAINT_PROPRIETARY_MODULE),	"P" },		\
+	{ (1UL << TAINT_FORCED_MODULE),		"F" },		\
+	{ (1UL << TAINT_CRAP),			"C" })
+
+TRACE_EVENT(module_load,
+
+	TP_PROTO(struct module *mod),
+
+	TP_ARGS(mod),
+
+	TP_STRUCT__entry(
+		__field(	unsigned int,	taints		)
+		__string(	name,		mod->name	)
+	),
+
+	TP_fast_assign(
+		__entry->taints = mod->taints;
+		__assign_str(name, mod->name);
+	),
+
+	TP_printk("%s %s", __get_str(name), show_module_flags(__entry->taints))
+);
+
+TRACE_EVENT(module_free,
+
+	TP_PROTO(struct module *mod),
+
+	TP_ARGS(mod),
+
+	TP_STRUCT__entry(
+		__string(	name,		mod->name	)
+	),
+
+	TP_fast_assign(
+		__assign_str(name, mod->name);
+	),
+
+	TP_printk("%s", __get_str(name))
+);
+
+TRACE_EVENT(module_get,
+
+	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+
+	TP_ARGS(mod, ip, refcnt),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	ip		)
+		__field(	int,		refcnt		)
+		__string(	name,		mod->name	)
+	),
+
+	TP_fast_assign(
+		__entry->ip	= ip;
+		__entry->refcnt	= refcnt;
+		__assign_str(name, mod->name);
+	),
+
+	TP_printk("%s call_site=%pf refcnt=%d",
+		  __get_str(name), (void *)__entry->ip, __entry->refcnt)
+);
+
+TRACE_EVENT(module_put,
+
+	TP_PROTO(struct module *mod, unsigned long ip, int refcnt),
+
+	TP_ARGS(mod, ip, refcnt),
+
+	TP_STRUCT__entry(
+		__field(	unsigned long,	ip		)
+		__field(	int,		refcnt		)
+		__string(	name,		mod->name	)
+	),
+
+	TP_fast_assign(
+		__entry->ip	= ip;
+		__entry->refcnt	= refcnt;
+		__assign_str(name, mod->name);
+	),
+
+	TP_printk("%s call_site=%pf refcnt=%d",
+		  __get_str(name), (void *)__entry->ip, __entry->refcnt)
+);
+
+TRACE_EVENT(module_request,
+
+	TP_PROTO(char *name, bool wait, unsigned long ip),
+
+	TP_ARGS(name, wait, ip),
+
+	TP_STRUCT__entry(
+		__field(	bool,		wait		)
+		__field(	unsigned long,	ip		)
+		__string(	name,		name		)
+	),
+
+	TP_fast_assign(
+		__entry->wait	= wait;
+		__entry->ip	= ip;
+		__assign_str(name, name);
+	),
+
+	TP_printk("%s wait=%d call_site=%pf",
+		  __get_str(name), (int)__entry->wait, (void *)__entry->ip)
+);
+
+#endif /* CONFIG_MODULES */
+
+#endif /* _TRACE_MODULE_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+

include/trace/events/sched.h

@@ -94,6 +94,7 @@ TRACE_EVENT(sched_wakeup,
 		__field(	pid_t,	pid			)
 		__field(	int,	prio			)
 		__field(	int,	success			)
+		__field(	int,	cpu			)
 	),
 
 	TP_fast_assign(
@@ -101,11 +102,12 @@ TRACE_EVENT(sched_wakeup,
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
 		__entry->success	= success;
+		__entry->cpu		= task_cpu(p);
 	),
 
-	TP_printk("task %s:%d [%d] success=%d",
+	TP_printk("task %s:%d [%d] success=%d [%03d]",
 		  __entry->comm, __entry->pid, __entry->prio,
-		  __entry->success)
+		  __entry->success, __entry->cpu)
 );
 
 /*
@@ -125,6 +127,7 @@ TRACE_EVENT(sched_wakeup_new,
 		__field(	pid_t,	pid			)
 		__field(	int,	prio			)
 		__field(	int,	success			)
+		__field(	int,	cpu			)
 	),
 
 	TP_fast_assign(
@@ -132,11 +135,12 @@ TRACE_EVENT(sched_wakeup_new,
 		__entry->pid		= p->pid;
 		__entry->prio		= p->prio;
 		__entry->success	= success;
+		__entry->cpu		= task_cpu(p);
 	),
 
-	TP_printk("task %s:%d [%d] success=%d",
+	TP_printk("task %s:%d [%d] success=%d [%03d]",
 		  __entry->comm, __entry->pid, __entry->prio,
-		  __entry->success)
+		  __entry->success, __entry->cpu)
 );
 
 /*

include/trace/events/syscalls.h

+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM syscalls
+
+#if !defined(_TRACE_EVENTS_SYSCALLS_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_EVENTS_SYSCALLS_H
+
+#include <linux/tracepoint.h>
+
+#include <asm/ptrace.h>
+#include <asm/syscall.h>
+
+
+#ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
+
+extern void syscall_regfunc(void);
+extern void syscall_unregfunc(void);
+
+TRACE_EVENT_FN(sys_enter,
+
+	TP_PROTO(struct pt_regs *regs, long id),
+
+	TP_ARGS(regs, id),
+
+	TP_STRUCT__entry(
+		__field(	long,		id		)
+		__array(	unsigned long,	args,	6	)
+	),
+
+	TP_fast_assign(
+		__entry->id	= id;
+		syscall_get_arguments(current, regs, 0, 6, __entry->args);
+	),
+
+	TP_printk("NR %ld (%lx, %lx, %lx, %lx, %lx, %lx)",
+		  __entry->id,
+		  __entry->args[0], __entry->args[1], __entry->args[2],
+		  __entry->args[3], __entry->args[4], __entry->args[5]),
+
+	syscall_regfunc, syscall_unregfunc
+);
+
+TRACE_EVENT_FN(sys_exit,
+
+	TP_PROTO(struct pt_regs *regs, long ret),
+
+	TP_ARGS(regs, ret),
+
+	TP_STRUCT__entry(
+		__field(	long,	id	)
+		__field(	long,	ret	)
+	),
+
+	TP_fast_assign(
+		__entry->id	= syscall_get_nr(current, regs);
+		__entry->ret	= ret;
+	),
+
+	TP_printk("NR %ld = %ld",
+		  __entry->id, __entry->ret),
+
+	syscall_regfunc, syscall_unregfunc
+);
+
+#endif /* CONFIG_HAVE_SYSCALL_TRACEPOINTS */
+
+#endif /* _TRACE_EVENTS_SYSCALLS_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
+

include/trace/ftrace.h

@@ -21,11 +21,14 @@
 #undef __field
 #define __field(type, item)		type	item;
 
+#undef __field_ext
+#define __field_ext(type, item, filter_type)	type	item;
+
 #undef __array
 #define __array(type, item, len)	type	item[len];
 
 #undef __dynamic_array
-#define __dynamic_array(type, item, len) unsigned short __data_loc_##item;
+#define __dynamic_array(type, item, len) u32 __data_loc_##item;
 
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
@@ -42,6 +45,16 @@
 	};							\
 	static struct ftrace_event_call event_##name
 
+#undef __cpparg
+#define __cpparg(arg...) arg
+
+/* Callbacks are meaningless to ftrace. */
+#undef TRACE_EVENT_FN
+#define TRACE_EVENT_FN(name, proto, args, tstruct,			\
+		assign, print, reg, unreg)				\
+	TRACE_EVENT(name, __cpparg(proto), __cpparg(args),		\
+		__cpparg(tstruct), __cpparg(assign), __cpparg(print))	\
+
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
 
@@ -51,23 +64,27 @@
  * Include the following:
  *
  * struct ftrace_data_offsets_<call> {
- *	int				<item1>;
- *	int				<item2>;
+ *	u32				<item1>;
+ *	u32				<item2>;
  *	[...]
  * };
  *
- * The __dynamic_array() macro will create each int <item>, this is
+ * The __dynamic_array() macro will create each u32 <item>, this is
  * to keep the offset of each array from the beginning of the event.
+ * The size of an array is also encoded, in the higher 16 bits of <item>.
  */
 
 #undef __field
-#define __field(type, item);
+#define __field(type, item)
+
+#undef __field_ext
+#define __field_ext(type, item, filter_type)
 
 #undef __array
 #define __array(type, item, len)
 
 #undef __dynamic_array
-#define __dynamic_array(type, item, len)	int item;
+#define __dynamic_array(type, item, len)	u32 item;
 
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
@@ -109,6 +126,9 @@
 	if (!ret)							\
 		return 0;
 
+#undef __field_ext
+#define __field_ext(type, item, filter_type)	__field(type, item)
+
 #undef __array
 #define __array(type, item, len)						\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item "[" #len "];\t"	\
@@ -120,7 +140,7 @@
 
 #undef __dynamic_array
 #define __dynamic_array(type, item, len)				       \
-	ret = trace_seq_printf(s, "\tfield:__data_loc " #item ";\t"	       \
+	ret = trace_seq_printf(s, "\tfield:__data_loc " #type "[] " #item ";\t"\
 			       "offset:%u;\tsize:%u;\n",		       \
 			       (unsigned int)offsetof(typeof(field),	       \
 					__data_loc_##item),		       \
@@ -150,7 +170,8 @@
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
 static int								\
-ftrace_format_##call(struct trace_seq *s)				\
+ftrace_format_##call(struct ftrace_event_call *unused,			\
+		      struct trace_seq *s)				\
 {									\
 	struct ftrace_raw_##call field __attribute__((unused));		\
 	int ret = 0;							\
@@ -210,7 +231,7 @@ ftrace_format_##call(struct trace_seq *s)				\
 
 #undef __get_dynamic_array
 #define __get_dynamic_array(field)	\
-		((void *)__entry + __entry->__data_loc_##field)
+		((void *)__entry + (__entry->__data_loc_##field & 0xffff))
 
 #undef __get_str
 #define __get_str(field) (char *)__get_dynamic_array(field)
@@ -263,28 +284,33 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 	
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
-#undef __field
-#define __field(type, item)						\
+#undef __field_ext
+#define __field_ext(type, item, filter_type)				\
 	ret = trace_define_field(event_call, #type, #item,		\
 				 offsetof(typeof(field), item),		\
-				 sizeof(field.item), is_signed_type(type));	\
+				 sizeof(field.item),			\
+				 is_signed_type(type), filter_type);	\
 	if (ret)							\
 		return ret;
 
+#undef __field
+#define __field(type, item)	__field_ext(type, item, FILTER_OTHER)
+
 #undef __array
 #define __array(type, item, len)					\
 	BUILD_BUG_ON(len > MAX_FILTER_STR_VAL);				\
 	ret = trace_define_field(event_call, #type "[" #len "]", #item,	\
 				 offsetof(typeof(field), item),		\
-				 sizeof(field.item), 0);		\
+				 sizeof(field.item), 0, FILTER_OTHER);	\
 	if (ret)							\
 		return ret;
 
 #undef __dynamic_array
 #define __dynamic_array(type, item, len)				       \
-	ret = trace_define_field(event_call, "__data_loc" "[" #type "]", #item,\
-				offsetof(typeof(field), __data_loc_##item),    \
-				 sizeof(field.__data_loc_##item), 0);
+	ret = trace_define_field(event_call, "__data_loc " #type "[]", #item,  \
+				 offsetof(typeof(field), __data_loc_##item),   \
+				 sizeof(field.__data_loc_##item), 0,	       \
+				 FILTER_OTHER);
 
 #undef __string
 #define __string(item, src) __dynamic_array(char, item, -1)
@@ -292,17 +318,14 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
 int									\
-ftrace_define_fields_##call(void)					\
+ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 {									\
 	struct ftrace_raw_##call field;					\
-	struct ftrace_event_call *event_call = &event_##call;		\
 	int ret;							\
 									\
-	__common_field(int, type, 1);					\
-	__common_field(unsigned char, flags, 0);			\
-	__common_field(unsigned char, preempt_count, 0);		\
-	__common_field(int, pid, 1);					\
-	__common_field(int, tgid, 1);					\
+	ret = trace_define_common_fields(event_call);			\
+	if (ret)							\
+		return ret;						\
 									\
 	tstruct;							\
 									\
@@ -321,6 +344,9 @@ ftrace_define_fields_##call(void)					\
 #undef __field
 #define __field(type, item)
 
+#undef __field_ext
+#define __field_ext(type, item, filter_type)
+
 #undef __array
 #define __array(type, item, len)
 
@@ -328,6 +354,7 @@ ftrace_define_fields_##call(void)					\
 #define __dynamic_array(type, item, len)				\
 	__data_offsets->item = __data_size +				\
 			       offsetof(typeof(*entry), __data);	\
+	__data_offsets->item |= (len * sizeof(type)) << 16;		\
 	__data_size += (len) * sizeof(type);
 
 #undef __string
@@ -433,13 +460,15 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
  * {
  *	struct ring_buffer_event *event;
  *	struct ftrace_raw_<call> *entry; <-- defined in stage 1
+ *	struct ring_buffer *buffer;
  *	unsigned long irq_flags;
  *	int pc;
  *
  *	local_save_flags(irq_flags);
  *	pc = preempt_count();
  *
- *	event = trace_current_buffer_lock_reserve(event_<call>.id,
+ *	event = trace_current_buffer_lock_reserve(&buffer,
+ *				  event_<call>.id,
  *				  sizeof(struct ftrace_raw_<call>),
  *				  irq_flags, pc);
  *	if (!event)
@@ -449,7 +478,7 @@ static void ftrace_profile_disable_##call(struct ftrace_event_call *event_call)\
  *	<assign>;  <-- Here we assign the entries by the __field and
  *			__array macros.
  *
- *	trace_current_buffer_unlock_commit(event, irq_flags, pc);
+ *	trace_current_buffer_unlock_commit(buffer, event, irq_flags, pc);
  * }
  *
  * static int ftrace_raw_reg_event_<call>(void)
@@ -541,6 +570,7 @@ static void ftrace_raw_event_##call(proto)				\
 	struct ftrace_event_call *event_call = &event_##call;		\
 	struct ring_buffer_event *event;				\
 	struct ftrace_raw_##call *entry;				\
+	struct ring_buffer *buffer;					\
 	unsigned long irq_flags;					\
 	int __data_size;						\
 	int pc;								\
@@ -550,7 +580,8 @@ static void ftrace_raw_event_##call(proto)				\
 									\
 	__data_size = ftrace_get_offsets_##call(&__data_offsets, args); \
 									\
-	event = trace_current_buffer_lock_reserve(event_##call.id,	\
+	event = trace_current_buffer_lock_reserve(&buffer,		\
+				 event_##call.id,			\
 				 sizeof(*entry) + __data_size,		\
 				 irq_flags, pc);			\
 	if (!event)							\
@@ -562,11 +593,12 @@ static void ftrace_raw_event_##call(proto)				\
 									\
 	{ assign; }							\
 									\
-	if (!filter_current_check_discard(event_call, entry, event))	\
-		trace_nowake_buffer_unlock_commit(event, irq_flags, pc); \
+	if (!filter_current_check_discard(buffer, event_call, entry, event)) \
+		trace_nowake_buffer_unlock_commit(buffer,		\
+						  event, irq_flags, pc); \
 }									\
 									\
-static int ftrace_raw_reg_event_##call(void)				\
+static int ftrace_raw_reg_event_##call(void *ptr)			\
 {									\
 	int ret;							\
 									\
@@ -577,7 +609,7 @@ static int ftrace_raw_reg_event_##call(void)				\
 	return ret;							\
 }									\
 									\
-static void ftrace_raw_unreg_event_##call(void)				\
+static void ftrace_raw_unreg_event_##call(void *ptr)			\
 {									\
 	unregister_trace_##call(ftrace_raw_event_##call);		\
 }									\
@@ -595,7 +627,6 @@ static int ftrace_raw_init_event_##call(void)				\
 		return -ENODEV;						\
 	event_##call.id = id;						\
 	INIT_LIST_HEAD(&event_##call.fields);				\
-	init_preds(&event_##call);					\
 	return 0;							\
 }									\
 									\

include/trace/syscall.h

 #ifndef _TRACE_SYSCALL_H
 #define _TRACE_SYSCALL_H
 
+#include <linux/tracepoint.h>
+#include <linux/unistd.h>
+#include <linux/ftrace_event.h>
+
 #include <asm/ptrace.h>
 
+
 /*
  * A syscall entry in the ftrace syscalls array.
  *
@@ -10,26 +15,49 @@
  * @nb_args: number of parameters it takes
  * @types: list of types as strings
  * @args: list of args as strings (args[i] matches types[i])
+ * @enter_id: associated ftrace enter event id
+ * @exit_id: associated ftrace exit event id
+ * @enter_event: associated syscall_enter trace event
+ * @exit_event: associated syscall_exit trace event
  */
 struct syscall_metadata {
 	const char	*name;
 	int		nb_args;
 	const char	**types;
 	const char	**args;
+	int		enter_id;
+	int		exit_id;
+
+	struct ftrace_event_call *enter_event;
+	struct ftrace_event_call *exit_event;
 };
 
 #ifdef CONFIG_FTRACE_SYSCALLS
-extern void arch_init_ftrace_syscalls(void);
 extern struct syscall_metadata *syscall_nr_to_meta(int nr);
-extern void start_ftrace_syscalls(void);
-extern void stop_ftrace_syscalls(void);
-extern void ftrace_syscall_enter(struct pt_regs *regs);
-extern void ftrace_syscall_exit(struct pt_regs *regs);
-#else
-static inline void start_ftrace_syscalls(void)			{ }
-static inline void stop_ftrace_syscalls(void)			{ }
-static inline void ftrace_syscall_enter(struct pt_regs *regs)	{ }
-static inline void ftrace_syscall_exit(struct pt_regs *regs)	{ }
+extern int syscall_name_to_nr(char *name);
+void set_syscall_enter_id(int num, int id);
+void set_syscall_exit_id(int num, int id);
+extern struct trace_event event_syscall_enter;
+extern struct trace_event event_syscall_exit;
+extern int reg_event_syscall_enter(void *ptr);
+extern void unreg_event_syscall_enter(void *ptr);
+extern int reg_event_syscall_exit(void *ptr);
+extern void unreg_event_syscall_exit(void *ptr);
+extern int syscall_enter_format(struct ftrace_event_call *call,
+				struct trace_seq *s);
+extern int syscall_exit_format(struct ftrace_event_call *call,
+				struct trace_seq *s);
+extern int syscall_enter_define_fields(struct ftrace_event_call *call);
+extern int syscall_exit_define_fields(struct ftrace_event_call *call);
+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
+int reg_prof_syscall_enter(char *name);
+void unreg_prof_syscall_enter(char *name);
+int reg_prof_syscall_exit(char *name);
+void unreg_prof_syscall_exit(char *name);
+
 #endif
 
 #endif /* _TRACE_SYSCALL_H */

kernel/kmod.c

@@ -37,6 +37,8 @@
 #include <linux/suspend.h>
 #include <asm/uaccess.h>
 
+#include <trace/events/module.h>
+
 extern int max_threads;
 
 static struct workqueue_struct *khelper_wq;
@@ -108,6 +110,8 @@ int __request_module(bool wait, const char *fmt, ...)
 		return -ENOMEM;
 	}
 
+	trace_module_request(module_name, wait, _RET_IP_);
+
 	ret = call_usermodehelper(modprobe_path, argv, envp,
 			wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC);
 	atomic_dec(&kmod_concurrent);

kernel/kprobes.c

@@ -103,7 +103,7 @@ static struct kprobe_blackpoint kprobe_blacklist[] = {
 #define INSNS_PER_PAGE	(PAGE_SIZE/(MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
 
 struct kprobe_insn_page {
-	struct hlist_node hlist;
+	struct list_head list;
 	kprobe_opcode_t *insns;		/* Page of instruction slots */
 	char slot_used[INSNS_PER_PAGE];
 	int nused;
@@ -117,7 +117,7 @@ enum kprobe_slot_state {
 };
 
 static DEFINE_MUTEX(kprobe_insn_mutex);	/* Protects kprobe_insn_pages */
-static struct hlist_head kprobe_insn_pages;
+static LIST_HEAD(kprobe_insn_pages);
 static int kprobe_garbage_slots;
 static int collect_garbage_slots(void);
 
@@ -152,10 +152,9 @@ loop_end:
 static kprobe_opcode_t __kprobes *__get_insn_slot(void)
 {
 	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
 
  retry:
-	hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) {
+	list_for_each_entry(kip, &kprobe_insn_pages, list) {
 		if (kip->nused < INSNS_PER_PAGE) {
 			int i;
 			for (i = 0; i < INSNS_PER_PAGE; i++) {
@@ -189,8 +188,8 @@ static kprobe_opcode_t __kprobes *__get_insn_slot(void)
 		kfree(kip);
 		return NULL;
 	}
-	INIT_HLIST_NODE(&kip->hlist);
-	hlist_add_head(&kip->hlist, &kprobe_insn_pages);
+	INIT_LIST_HEAD(&kip->list);
+	list_add(&kip->list, &kprobe_insn_pages);
 	memset(kip->slot_used, SLOT_CLEAN, INSNS_PER_PAGE);
 	kip->slot_used[0] = SLOT_USED;
 	kip->nused = 1;
@@ -219,12 +218,8 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
 		 * so as not to have to set it up again the
 		 * next time somebody inserts a probe.
 		 */
-		hlist_del(&kip->hlist);
-		if (hlist_empty(&kprobe_insn_pages)) {
-			INIT_HLIST_NODE(&kip->hlist);
-			hlist_add_head(&kip->hlist,
-				       &kprobe_insn_pages);
-		} else {
+		if (!list_is_singular(&kprobe_insn_pages)) {
+			list_del(&kip->list);
 			module_free(NULL, kip->insns);
 			kfree(kip);
 		}
@@ -235,14 +230,13 @@ static int __kprobes collect_one_slot(struct kprobe_insn_page *kip, int idx)
 
 static int __kprobes collect_garbage_slots(void)
 {
-	struct kprobe_insn_page *kip;
-	struct hlist_node *pos, *next;
+	struct kprobe_insn_page *kip, *next;
 
 	/* Ensure no-one is preepmted on the garbages */
 	if (check_safety())
 		return -EAGAIN;
 
-	hlist_for_each_entry_safe(kip, pos, next, &kprobe_insn_pages, hlist) {
+	list_for_each_entry_safe(kip, next, &kprobe_insn_pages, list) {
 		int i;
 		if (kip->ngarbage == 0)
 			continue;
@@ -260,19 +254,17 @@ static int __kprobes collect_garbage_slots(void)
 void __kprobes free_insn_slot(kprobe_opcode_t * slot, int dirty)
 {
 	struct kprobe_insn_page *kip;
-	struct hlist_node *pos;
 
 	mutex_lock(&kprobe_insn_mutex);
-	hlist_for_each_entry(kip, pos, &kprobe_insn_pages, hlist) {
+	list_for_each_entry(kip, &kprobe_insn_pages, list) {
 		if (kip->insns <= slot &&
 		    slot < kip->insns + (INSNS_PER_PAGE * MAX_INSN_SIZE)) {
 			int i = (slot - kip->insns) / MAX_INSN_SIZE;
 			if (dirty) {
 				kip->slot_used[i] = SLOT_DIRTY;
 				kip->ngarbage++;
-			} else {
+			} else
 				collect_one_slot(kip, i);
-			}
 			break;
 		}
 	}

kernel/module.c

@@ -55,6 +55,11 @@
 #include <linux/percpu.h>
 #include <linux/kmemleak.h>
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/module.h>
+
+EXPORT_TRACEPOINT_SYMBOL(module_get);
+
 #if 0
 #define DEBUGP printk
 #else
@@ -942,6 +947,8 @@ void module_put(struct module *module)
 	if (module) {
 		unsigned int cpu = get_cpu();
 		local_dec(__module_ref_addr(module, cpu));
+		trace_module_put(module, _RET_IP_,
+				 local_read(__module_ref_addr(module, cpu)));
 		/* Maybe they're waiting for us to drop reference? */
 		if (unlikely(!module_is_live(module)))
 			wake_up_process(module->waiter);
@@ -1497,6 +1504,8 @@ static int __unlink_module(void *_mod)
 /* Free a module, remove from lists, etc (must hold module_mutex). */
 static void free_module(struct module *mod)
 {
+	trace_module_free(mod);
+
 	/* Delete from various lists */
 	stop_machine(__unlink_module, mod, NULL);
 	remove_notes_attrs(mod);
@@ -2364,6 +2373,8 @@ static noinline struct module *load_module(void __user *umod,
 	/* Get rid of temporary copy */
 	vfree(hdr);
 
+	trace_module_load(mod);
+
 	/* Done! */
 	return mod;
 

kernel/trace/Kconfig

@@ -41,7 +41,7 @@ config HAVE_FTRACE_MCOUNT_RECORD
 config HAVE_HW_BRANCH_TRACER
 	bool
 
-config HAVE_FTRACE_SYSCALLS
+config HAVE_SYSCALL_TRACEPOINTS
 	bool
 
 config TRACER_MAX_TRACE
@@ -60,9 +60,14 @@ config EVENT_TRACING
 	bool
 
 config CONTEXT_SWITCH_TRACER
-	select MARKERS
 	bool
 
+config RING_BUFFER_ALLOW_SWAP
+	bool
+	help
+	 Allow the use of ring_buffer_swap_cpu.
+	 Adds a very slight overhead to tracing when enabled.
+
 # All tracer options should select GENERIC_TRACER. For those options that are
 # enabled by all tracers (context switch and event tracer) they select TRACING.
 # This allows those options to appear when no other tracer is selected. But the
@@ -147,6 +152,7 @@ config IRQSOFF_TRACER
 	select TRACE_IRQFLAGS
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
+	select RING_BUFFER_ALLOW_SWAP
 	help
 	  This option measures the time spent in irqs-off critical
 	  sections, with microsecond accuracy.
@@ -168,6 +174,7 @@ config PREEMPT_TRACER
 	depends on PREEMPT
 	select GENERIC_TRACER
 	select TRACER_MAX_TRACE
+	select RING_BUFFER_ALLOW_SWAP
 	help
 	  This option measures the time spent in preemption off critical
 	  sections, with microsecond accuracy.
@@ -211,7 +218,7 @@ config ENABLE_DEFAULT_TRACERS
 
 config FTRACE_SYSCALLS
 	bool "Trace syscalls"
-	depends on HAVE_FTRACE_SYSCALLS
+	depends on HAVE_SYSCALL_TRACEPOINTS
 	select GENERIC_TRACER
 	select KALLSYMS
 	help

kernel/trace/blktrace.c

@@ -65,13 +65,15 @@ static void trace_note(struct blk_trace *bt, pid_t pid, int action,
 {
 	struct blk_io_trace *t;
 	struct ring_buffer_event *event = NULL;
+	struct ring_buffer *buffer = NULL;
 	int pc = 0;
 	int cpu = smp_processor_id();
 	bool blk_tracer = blk_tracer_enabled;
 
 	if (blk_tracer) {
+		buffer = blk_tr->buffer;
 		pc = preempt_count();
-		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + len,
 						  0, pc);
 		if (!event)
@@ -96,7 +98,7 @@ record_it:
 		memcpy((void *) t + sizeof(*t), data, len);
 
 		if (blk_tracer)
-			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+			trace_buffer_unlock_commit(buffer, event, 0, pc);
 	}
 }
 
@@ -179,6 +181,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 {
 	struct task_struct *tsk = current;
 	struct ring_buffer_event *event = NULL;
+	struct ring_buffer *buffer = NULL;
 	struct blk_io_trace *t;
 	unsigned long flags = 0;
 	unsigned long *sequence;
@@ -204,8 +207,9 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes,
 	if (blk_tracer) {
 		tracing_record_cmdline(current);
 
+		buffer = blk_tr->buffer;
 		pc = preempt_count();
-		event = trace_buffer_lock_reserve(blk_tr, TRACE_BLK,
+		event = trace_buffer_lock_reserve(buffer, TRACE_BLK,
 						  sizeof(*t) + pdu_len,
 						  0, pc);
 		if (!event)
@@ -252,7 +256,7 @@ record_it:
 			memcpy((void *) t + sizeof(*t), pdu_data, pdu_len);
 
 		if (blk_tracer) {
-			trace_buffer_unlock_commit(blk_tr, event, 0, pc);
+			trace_buffer_unlock_commit(buffer, event, 0, pc);
 			return;
 		}
 	}

kernel/trace/kmemtrace.c

@@ -183,11 +183,9 @@ static void kmemtrace_stop_probes(void)
 
 static int kmem_trace_init(struct trace_array *tr)
 {
-	int cpu;
 	kmemtrace_array = tr;
 
-	for_each_cpu(cpu, cpu_possible_mask)
-		tracing_reset(tr, cpu);
+	tracing_reset_online_cpus(tr);
 
 	kmemtrace_start_probes();
 
@@ -239,12 +237,52 @@ struct kmemtrace_user_event_alloc {
 };
 
 static enum print_line_t
-kmemtrace_print_alloc_user(struct trace_iterator *iter,
-			   struct kmemtrace_alloc_entry *entry)
+kmemtrace_print_alloc(struct trace_iterator *iter, int flags)
 {
-	struct kmemtrace_user_event_alloc *ev_alloc;
 	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_alloc_entry *entry;
+	int ret;
+
+	trace_assign_type(entry, iter->ent);
+
+	ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu "
+	    "bytes_req %lu bytes_alloc %lu gfp_flags %lu node %d\n",
+	    entry->type_id, (void *)entry->call_site, (unsigned long)entry->ptr,
+	    (unsigned long)entry->bytes_req, (unsigned long)entry->bytes_alloc,
+	    (unsigned long)entry->gfp_flags, entry->node);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_free(struct trace_iterator *iter, int flags)
+{
+	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_free_entry *entry;
+	int ret;
+
+	trace_assign_type(entry, iter->ent);
+
+	ret = trace_seq_printf(s, "type_id %d call_site %pF ptr %lu\n",
+			       entry->type_id, (void *)entry->call_site,
+			       (unsigned long)entry->ptr);
+
+	if (!ret)
+		return TRACE_TYPE_PARTIAL_LINE;
+	return TRACE_TYPE_HANDLED;
+}
+
+static enum print_line_t
+kmemtrace_print_alloc_user(struct trace_iterator *iter, int flags)
+{
+	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_alloc_entry *entry;
 	struct kmemtrace_user_event *ev;
+	struct kmemtrace_user_event_alloc *ev_alloc;
+
+	trace_assign_type(entry, iter->ent);
 
 	ev = trace_seq_reserve(s, sizeof(*ev));
 	if (!ev)
@@ -271,12 +309,14 @@ kmemtrace_print_alloc_user(struct trace_iterator *iter,
 }
 
 static enum print_line_t
-kmemtrace_print_free_user(struct trace_iterator *iter,
-			  struct kmemtrace_free_entry *entry)
+kmemtrace_print_free_user(struct trace_iterator *iter, int flags)
 {
 	struct trace_seq *s = &iter->seq;
+	struct kmemtrace_free_entry *entry;
 	struct kmemtrace_user_event *ev;
 
+	trace_assign_type(entry, iter->ent);
+
 	ev = trace_seq_reserve(s, sizeof(*ev));
 	if (!ev)
 		return TRACE_TYPE_PARTIAL_LINE;
@@ -294,12 +334,14 @@ kmemtrace_print_free_user(struct trace_iterator *iter,
 
 /* The two other following provide a more minimalistic output */
 static enum print_line_t
-kmemtrace_print_alloc_compress(struct trace_iterator *iter,
-					struct kmemtrace_alloc_entry *entry)
+kmemtrace_print_alloc_compress(struct trace_iterator *iter)
 {
+	struct kmemtrace_alloc_entry *entry;
 	struct trace_seq *s = &iter->seq;
 	int ret;
 
+	trace_assign_type(entry, iter->ent);
+
 	/* Alloc entry */
 	ret = trace_seq_printf(s, "  +      ");
 	if (!ret)
@@ -345,29 +387,24 @@ kmemtrace_print_alloc_compress(struct trace_iterator *iter,
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Node */
-	ret = trace_seq_printf(s, "%4d   ", entry->node);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	/* Call site */
-	ret = seq_print_ip_sym(s, entry->call_site, 0);
+	/* Node and call site*/
+	ret = trace_seq_printf(s, "%4d   %pf\n", entry->node,
+						 (void *)entry->call_site);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	if (!trace_seq_printf(s, "\n"))
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	return TRACE_TYPE_HANDLED;
 }
 
 static enum print_line_t
-kmemtrace_print_free_compress(struct trace_iterator *iter,
-			      struct kmemtrace_free_entry *entry)
+kmemtrace_print_free_compress(struct trace_iterator *iter)
 {
+	struct kmemtrace_free_entry *entry;
 	struct trace_seq *s = &iter->seq;
 	int ret;
 
+	trace_assign_type(entry, iter->ent);
+
 	/* Free entry */
 	ret = trace_seq_printf(s, "  -      ");
 	if (!ret)
@@ -401,19 +438,11 @@ kmemtrace_print_free_compress(struct trace_iterator *iter,
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Skip node */
-	ret = trace_seq_printf(s, "       ");
+	/* Skip node and print call site*/
+	ret = trace_seq_printf(s, "       %pf\n", (void *)entry->call_site);
 	if (!ret)
 		return TRACE_TYPE_PARTIAL_LINE;
 
-	/* Call site */
-	ret = seq_print_ip_sym(s, entry->call_site, 0);
-	if (!ret)
-		return TRACE_TYPE_PARTIAL_LINE;
-
-	if (!trace_seq_printf(s, "\n"))
-		return TRACE_TYPE_PARTIAL_LINE;
-
 	return TRACE_TYPE_HANDLED;
 }
 
@@ -421,32 +450,31 @@ static enum print_line_t kmemtrace_print_line(struct trace_iterator *iter)
 {
 	struct trace_entry *entry = iter->ent;
 
-	switch (entry->type) {
-	case TRACE_KMEM_ALLOC: {
-		struct kmemtrace_alloc_entry *field;
-
-		trace_assign_type(field, entry);
-		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
-			return kmemtrace_print_alloc_compress(iter, field);
-		else
-			return kmemtrace_print_alloc_user(iter, field);
-	}
-
-	case TRACE_KMEM_FREE: {
-		struct kmemtrace_free_entry *field;
-
-		trace_assign_type(field, entry);
-		if (kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL)
-			return kmemtrace_print_free_compress(iter, field);
-		else
-			return kmemtrace_print_free_user(iter, field);
-	}
+	if (!(kmem_tracer_flags.val & TRACE_KMEM_OPT_MINIMAL))
+		return TRACE_TYPE_UNHANDLED;
 
+	switch (entry->type) {
+	case TRACE_KMEM_ALLOC:
+		return kmemtrace_print_alloc_compress(iter);
+	case TRACE_KMEM_FREE:
+		return kmemtrace_print_free_compress(iter);
 	default:
 		return TRACE_TYPE_UNHANDLED;
 	}
 }
 
+static struct trace_event kmem_trace_alloc = {
+	.type			= TRACE_KMEM_ALLOC,
+	.trace			= kmemtrace_print_alloc,
+	.binary			= kmemtrace_print_alloc_user,
+};
+
+static struct trace_event kmem_trace_free = {
+	.type			= TRACE_KMEM_FREE,
+	.trace			= kmemtrace_print_free,
+	.binary			= kmemtrace_print_free_user,
+};
+
 static struct tracer kmem_tracer __read_mostly = {
 	.name			= "kmemtrace",
 	.init			= kmem_trace_init,
@@ -463,6 +491,21 @@ void kmemtrace_init(void)
 
 static int __init init_kmem_tracer(void)
 {
-	return register_tracer(&kmem_tracer);
+	if (!register_ftrace_event(&kmem_trace_alloc)) {
+		pr_warning("Warning: could not register kmem events\n");
+		return 1;
+	}
+
+	if (!register_ftrace_event(&kmem_trace_free)) {
+		pr_warning("Warning: could not register kmem events\n");
+		return 1;
+	}
+
+	if (!register_tracer(&kmem_tracer)) {
+		pr_warning("Warning: could not register the kmem tracer\n");
+		return 1;
+	}
+
+	return 0;
 }
 device_initcall(init_kmem_tracer);

kernel/trace/trace_event_profile.c

@@ -5,6 +5,7 @@
  *
  */
 
+#include <linux/module.h>
 #include "trace.h"
 
 int ftrace_profile_enable(int event_id)
@@ -14,7 +15,8 @@ int ftrace_profile_enable(int event_id)
 
 	mutex_lock(&event_mutex);
 	list_for_each_entry(event, &ftrace_events, list) {
-		if (event->id == event_id && event->profile_enable) {
+		if (event->id == event_id && event->profile_enable &&
+		    try_module_get(event->mod)) {
 			ret = event->profile_enable(event);
 			break;
 		}
@@ -32,6 +34,7 @@ void ftrace_profile_disable(int event_id)
 	list_for_each_entry(event, &ftrace_events, list) {
 		if (event->id == event_id) {
 			event->profile_disable(event);
+			module_put(event->mod);
 			break;
 		}
 	}

kernel/trace/trace_functions.c

@@ -288,11 +288,9 @@ static int
 ftrace_trace_onoff_print(struct seq_file *m, unsigned long ip,
 			 struct ftrace_probe_ops *ops, void *data)
 {
-	char str[KSYM_SYMBOL_LEN];
 	long count = (long)data;
 
-	kallsyms_lookup(ip, NULL, NULL, NULL, str);
-	seq_printf(m, "%s:", str);
+	seq_printf(m, "%pf:", (void *)ip);
 
 	if (ops == &traceon_probe_ops)
 		seq_printf(m, "traceon");