OpenCloudOS-Kernel/include/trace/trace_events.h

773 lines
22 KiB
C
Raw Normal View History

/*
* Stage 1 of the trace events.
*
* Override the macros in <trace/trace_events.h> to include the following:
*
* struct trace_event_raw_<call> {
* struct trace_entry ent;
* <type> <item>;
* <type2> <item2>[<len>];
* [...]
* };
*
* The <type> <item> is created by the __field(type, item) macro or
* the __array(type2, item2, len) macro.
* We simply do "type item;", and that will create the fields
* in the structure.
*/
#include <linux/trace_events.h>
#ifndef TRACE_SYSTEM_VAR
#define TRACE_SYSTEM_VAR TRACE_SYSTEM
#endif
#define __app__(x, y) str__##x##y
#define __app(x, y) __app__(x, y)
#define TRACE_SYSTEM_STRING __app(TRACE_SYSTEM_VAR,__trace_system_name)
#define TRACE_MAKE_SYSTEM_STR() \
static const char TRACE_SYSTEM_STRING[] = \
__stringify(TRACE_SYSTEM)
TRACE_MAKE_SYSTEM_STR();
tracing: Add TRACE_DEFINE_ENUM() macro to map enums to their values Several tracepoints use the helper functions __print_symbolic() or __print_flags() and pass in enums that do the mapping between the binary data stored and the value to print. This works well for reading the ASCII trace files, but when the data is read via userspace tools such as perf and trace-cmd, the conversion of the binary value to a human string format is lost if an enum is used, as userspace does not have access to what the ENUM is. For example, the tracepoint trace_tlb_flush() has: __print_symbolic(REC->reason, { TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" }, { TLB_REMOTE_SHOOTDOWN, "remote shootdown" }, { TLB_LOCAL_SHOOTDOWN, "local shootdown" }, { TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" }) Which maps the enum values to the strings they represent. But perf and trace-cmd do no know what value TLB_LOCAL_MM_SHOOTDOWN is, and would not be able to map it. With TRACE_DEFINE_ENUM(), developers can place these in the event header files and ftrace will convert the enums to their values: By adding: TRACE_DEFINE_ENUM(TLB_FLUSH_ON_TASK_SWITCH); TRACE_DEFINE_ENUM(TLB_REMOTE_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_MM_SHOOTDOWN); $ cat /sys/kernel/debug/tracing/events/tlb/tlb_flush/format [...] __print_symbolic(REC->reason, { 0, "flush on task switch" }, { 1, "remote shootdown" }, { 2, "local shootdown" }, { 3, "local mm shootdown" }) The above is what userspace expects to see, and tools do not need to be modified to parse them. Link: http://lkml.kernel.org/r/20150403013802.220157513@goodmis.org Cc: Guilherme Cox <cox@computer.org> Cc: Tony Luck <tony.luck@gmail.com> Cc: Xie XiuQi <xiexiuqi@huawei.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-03-25 05:58:09 +08:00
#undef TRACE_DEFINE_ENUM
#define TRACE_DEFINE_ENUM(a) \
static struct trace_enum_map __used __initdata \
__##TRACE_SYSTEM##_##a = \
{ \
.system = TRACE_SYSTEM_STRING, \
.enum_string = #a, \
.enum_value = a \
}; \
static struct trace_enum_map __used \
__attribute__((section("_ftrace_enum_map"))) \
*TRACE_SYSTEM##_##a = &__##TRACE_SYSTEM##_##a
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
/*
* DECLARE_EVENT_CLASS can be used to add a generic function
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
* handlers for events. That is, if all events have the same
* parameters and just have distinct trace points.
* Each tracepoint can be defined with DEFINE_EVENT and that
* will map the DECLARE_EVENT_CLASS to the tracepoint.
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
*
* TRACE_EVENT is a one to one mapping between tracepoint and template.
*/
#undef TRACE_EVENT
#define TRACE_EVENT(name, proto, args, tstruct, assign, print) \
DECLARE_EVENT_CLASS(name, \
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
PARAMS(proto), \
PARAMS(args), \
PARAMS(tstruct), \
PARAMS(assign), \
PARAMS(print)); \
DEFINE_EVENT(name, name, PARAMS(proto), PARAMS(args));
#undef __field
#define __field(type, item) type item;
#undef __field_ext
#define __field_ext(type, item, filter_type) type item;
#undef __field_struct
#define __field_struct(type, item) type item;
#undef __field_struct_ext
#define __field_struct_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) u32 __data_loc_##item;
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __string
#define __string(item, src) __dynamic_array(char, item, -1)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#undef __bitmask
#define __bitmask(item, nr_bits) __dynamic_array(char, item, -1)
#undef TP_STRUCT__entry
#define TP_STRUCT__entry(args...) args
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(name, proto, args, tstruct, assign, print) \
struct trace_event_raw_##name { \
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
struct trace_entry ent; \
tstruct \
char __data[0]; \
}; \
\
static struct trace_event_class event_class_##name;
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args) \
static struct trace_event_call __used \
__attribute__((__aligned__(4))) event_##name
#undef DEFINE_EVENT_FN
#define DEFINE_EVENT_FN(template, name, proto, args, reg, unreg) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
tracing: Move tracepoint callbacks from declaration to definition It's not strictly correct for the tracepoint reg/unreg callbacks to occur when a client is hooking up, because the actual tracepoint may not be present yet. This happens to be fine for syscall, since that's in the core kernel, but it would cause problems for tracepoints defined in a module that hasn't been loaded yet. It also means the reg/unreg has to be EXPORTed for any modules to use the tracepoint (as in SystemTap). This patch removes DECLARE_TRACE_WITH_CALLBACK, and instead introduces DEFINE_TRACE_FN which stores the callbacks in struct tracepoint. The callbacks are used now when the active state of the tracepoint changes in set_tracepoint & disable_tracepoint. This also introduces TRACE_EVENT_FN, so ftrace events can also provide registration callbacks if needed. Signed-off-by: Josh Stone <jistone@redhat.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Jiaying Zhang <jiayingz@google.com> Cc: Martin Bligh <mbligh@google.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> LKML-Reference: <1251150194-1713-4-git-send-email-jistone@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-08-25 05:43:13 +08:00
/* Callbacks are meaningless to ftrace. */
#undef TRACE_EVENT_FN
#define TRACE_EVENT_FN(name, proto, args, tstruct, \
assign, print, reg, unreg) \
TRACE_EVENT(name, PARAMS(proto), PARAMS(args), \
PARAMS(tstruct), PARAMS(assign), PARAMS(print)) \
#undef TRACE_EVENT_FN_COND
#define TRACE_EVENT_FN_COND(name, proto, args, cond, tstruct, \
assign, print, reg, unreg) \
TRACE_EVENT_CONDITION(name, PARAMS(proto), PARAMS(args), PARAMS(cond), \
PARAMS(tstruct), PARAMS(assign), PARAMS(print)) \
tracing: Move tracepoint callbacks from declaration to definition It's not strictly correct for the tracepoint reg/unreg callbacks to occur when a client is hooking up, because the actual tracepoint may not be present yet. This happens to be fine for syscall, since that's in the core kernel, but it would cause problems for tracepoints defined in a module that hasn't been loaded yet. It also means the reg/unreg has to be EXPORTed for any modules to use the tracepoint (as in SystemTap). This patch removes DECLARE_TRACE_WITH_CALLBACK, and instead introduces DEFINE_TRACE_FN which stores the callbacks in struct tracepoint. The callbacks are used now when the active state of the tracepoint changes in set_tracepoint & disable_tracepoint. This also introduces TRACE_EVENT_FN, so ftrace events can also provide registration callbacks if needed. Signed-off-by: Josh Stone <jistone@redhat.com> Cc: Jason Baron <jbaron@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Jiaying Zhang <jiayingz@google.com> Cc: Martin Bligh <mbligh@google.com> Cc: Lai Jiangshan <laijs@cn.fujitsu.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> LKML-Reference: <1251150194-1713-4-git-send-email-jistone@redhat.com> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
2009-08-25 05:43:13 +08:00
#undef TRACE_EVENT_FLAGS
#define TRACE_EVENT_FLAGS(name, value) \
__TRACE_EVENT_FLAGS(name, value)
#undef TRACE_EVENT_PERF_PERM
#define TRACE_EVENT_PERF_PERM(name, expr...) \
__TRACE_EVENT_PERF_PERM(name, expr)
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
/*
* Stage 2 of the trace events.
*
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
* Include the following:
*
* struct trace_event_data_offsets_<call> {
* u32 <item1>;
* u32 <item2>;
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
* [...]
* };
*
* 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>.
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
*/
tracing: Add TRACE_DEFINE_ENUM() macro to map enums to their values Several tracepoints use the helper functions __print_symbolic() or __print_flags() and pass in enums that do the mapping between the binary data stored and the value to print. This works well for reading the ASCII trace files, but when the data is read via userspace tools such as perf and trace-cmd, the conversion of the binary value to a human string format is lost if an enum is used, as userspace does not have access to what the ENUM is. For example, the tracepoint trace_tlb_flush() has: __print_symbolic(REC->reason, { TLB_FLUSH_ON_TASK_SWITCH, "flush on task switch" }, { TLB_REMOTE_SHOOTDOWN, "remote shootdown" }, { TLB_LOCAL_SHOOTDOWN, "local shootdown" }, { TLB_LOCAL_MM_SHOOTDOWN, "local mm shootdown" }) Which maps the enum values to the strings they represent. But perf and trace-cmd do no know what value TLB_LOCAL_MM_SHOOTDOWN is, and would not be able to map it. With TRACE_DEFINE_ENUM(), developers can place these in the event header files and ftrace will convert the enums to their values: By adding: TRACE_DEFINE_ENUM(TLB_FLUSH_ON_TASK_SWITCH); TRACE_DEFINE_ENUM(TLB_REMOTE_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_SHOOTDOWN); TRACE_DEFINE_ENUM(TLB_LOCAL_MM_SHOOTDOWN); $ cat /sys/kernel/debug/tracing/events/tlb/tlb_flush/format [...] __print_symbolic(REC->reason, { 0, "flush on task switch" }, { 1, "remote shootdown" }, { 2, "local shootdown" }, { 3, "local mm shootdown" }) The above is what userspace expects to see, and tools do not need to be modified to parse them. Link: http://lkml.kernel.org/r/20150403013802.220157513@goodmis.org Cc: Guilherme Cox <cox@computer.org> Cc: Tony Luck <tony.luck@gmail.com> Cc: Xie XiuQi <xiexiuqi@huawei.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Reviewed-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2015-03-25 05:58:09 +08:00
#undef TRACE_DEFINE_ENUM
#define TRACE_DEFINE_ENUM(a)
#undef __field
#define __field(type, item)
#undef __field_ext
#define __field_ext(type, item, filter_type)
#undef __field_struct
#define __field_struct(type, item)
#undef __field_struct_ext
#define __field_struct_ext(type, item, filter_type)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __array
#define __array(type, item, len)
#undef __dynamic_array
#define __dynamic_array(type, item, len) u32 item;
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __string
#define __string(item, src) __dynamic_array(char, item, -1)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#undef __bitmask
#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
struct trace_event_data_offsets_##call { \
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
tstruct; \
};
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args)
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
#undef TRACE_EVENT_FLAGS
#define TRACE_EVENT_FLAGS(event, flag)
#undef TRACE_EVENT_PERF_PERM
#define TRACE_EVENT_PERF_PERM(event, expr...)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
/*
* Stage 3 of the trace events.
*
* Override the macros in <trace/trace_events.h> to include the following:
*
* enum print_line_t
* trace_raw_output_<call>(struct trace_iterator *iter, int flags)
* {
* struct trace_seq *s = &iter->seq;
* struct trace_event_raw_<call> *field; <-- defined in stage 1
* struct trace_entry *entry;
* struct trace_seq *p = &iter->tmp_seq;
* int ret;
*
* entry = iter->ent;
*
* if (entry->type != event_<call>->event.type) {
* WARN_ON_ONCE(1);
* return TRACE_TYPE_UNHANDLED;
* }
*
* field = (typeof(field))entry;
*
* trace_seq_init(p);
* ret = trace_seq_printf(s, "%s: ", <call>);
* if (ret)
* ret = trace_seq_printf(s, <TP_printk> "\n");
* if (!ret)
* return TRACE_TYPE_PARTIAL_LINE;
*
* return TRACE_TYPE_HANDLED;
* }
*
* This is the method used to print the raw event to the trace
* output format. Note, this is not needed if the data is read
* in binary.
*/
#undef __entry
#define __entry field
#undef TP_printk
#define TP_printk(fmt, args...) fmt "\n", args
#undef __get_dynamic_array
#define __get_dynamic_array(field) \
((void *)__entry + (__entry->__data_loc_##field & 0xffff))
#undef __get_dynamic_array_len
#define __get_dynamic_array_len(field) \
((__entry->__data_loc_##field >> 16) & 0xffff)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __get_str
#define __get_str(field) (char *)__get_dynamic_array(field)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#undef __get_bitmask
#define __get_bitmask(field) \
({ \
void *__bitmask = __get_dynamic_array(field); \
unsigned int __bitmask_size; \
__bitmask_size = __get_dynamic_array_len(field); \
trace_print_bitmask_seq(p, __bitmask, __bitmask_size); \
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
})
#undef __print_flags
#define __print_flags(flag, delim, flag_array...) \
({ \
static const struct trace_print_flags __flags[] = \
{ flag_array, { -1, NULL }}; \
trace_print_flags_seq(p, delim, flag, __flags); \
})
#undef __print_symbolic
#define __print_symbolic(value, symbol_array...) \
({ \
static const struct trace_print_flags symbols[] = \
{ symbol_array, { -1, NULL }}; \
trace_print_symbols_seq(p, value, symbols); \
})
#undef __print_symbolic_u64
#if BITS_PER_LONG == 32
#define __print_symbolic_u64(value, symbol_array...) \
({ \
static const struct trace_print_flags_u64 symbols[] = \
{ symbol_array, { -1, NULL } }; \
trace_print_symbols_seq_u64(p, value, symbols); \
})
#else
#define __print_symbolic_u64(value, symbol_array...) \
__print_symbolic(value, symbol_array)
#endif
#undef __print_hex
#define __print_hex(buf, buf_len) trace_print_hex_seq(p, buf, buf_len)
#undef __print_array
#define __print_array(array, count, el_size) \
({ \
BUILD_BUG_ON(el_size != 1 && el_size != 2 && \
el_size != 4 && el_size != 8); \
trace_print_array_seq(p, array, count, el_size); \
})
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
static notrace enum print_line_t \
trace_raw_output_##call(struct trace_iterator *iter, int flags, \
struct trace_event *trace_event) \
{ \
struct trace_seq *s = &iter->seq; \
struct trace_seq __maybe_unused *p = &iter->tmp_seq; \
struct trace_event_raw_##call *field; \
int ret; \
\
field = (typeof(field))iter->ent; \
\
ret = trace_raw_output_prep(iter, trace_event); \
if (ret != TRACE_TYPE_HANDLED) \
return ret; \
\
trace_seq_printf(s, print); \
\
return trace_handle_return(s); \
} \
static struct trace_event_functions trace_event_type_funcs_##call = { \
.trace = trace_raw_output_##call, \
};
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \
static notrace enum print_line_t \
trace_raw_output_##call(struct trace_iterator *iter, int flags, \
struct trace_event *event) \
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
{ \
struct trace_event_raw_##template *field; \
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
struct trace_entry *entry; \
struct trace_seq *p = &iter->tmp_seq; \
\
entry = iter->ent; \
\
if (entry->type != event_##call.event.type) { \
WARN_ON_ONCE(1); \
return TRACE_TYPE_UNHANDLED; \
} \
\
field = (typeof(field))entry; \
\
trace_seq_init(p); \
return trace_output_call(iter, #call, print); \
} \
static struct trace_event_functions trace_event_type_funcs_##call = { \
.trace = trace_raw_output_##call, \
};
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
#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), filter_type); \
if (ret) \
return ret;
#undef __field_struct_ext
#define __field_struct_ext(type, item, filter_type) \
ret = trace_define_field(event_call, #type, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
0, filter_type); \
if (ret) \
return ret;
#undef __field
#define __field(type, item) __field_ext(type, item, FILTER_OTHER)
#undef __field_struct
#define __field_struct(type, item) __field_struct_ext(type, item, FILTER_OTHER)
#undef __array
#define __array(type, item, len) \
do { \
tracing: Fix array size mismatch in format string In event format strings, the array size is reported in two locations. One in array subscript and then via the "size:" attribute. The values reported there have a mismatch. For e.g., in sched:sched_switch the prev_comm and next_comm character arrays have subscript values as [32] where as the actual field size is 16. name: sched_switch ID: 301 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1;signed:0; field:int common_pid; offset:4; size:4; signed:1; field:char prev_comm[32]; offset:8; size:16; signed:1; field:pid_t prev_pid; offset:24; size:4; signed:1; field:int prev_prio; offset:28; size:4; signed:1; field:long prev_state; offset:32; size:8; signed:1; field:char next_comm[32]; offset:40; size:16; signed:1; field:pid_t next_pid; offset:56; size:4; signed:1; field:int next_prio; offset:60; size:4; signed:1; After bisection, the following commit was blamed: 92edca0 tracing: Use direct field, type and system names This commit removes the duplication of strings for field->name and field->type assuming that all the strings passed in __trace_define_field() are immutable. This is not true for arrays, where the type string is created in event_storage variable and field->type for all array fields points to event_storage. Use __stringify() to create a string constant for the type string. Also, get rid of event_storage and event_storage_mutex that are not needed anymore. also, an added benefit is that this reduces the overhead of events a bit more: text data bss dec hex filename 8424787 2036472 1302528 11763787 b3804b vmlinux 8420814 2036408 1302528 11759750 b37086 vmlinux.patched Link: http://lkml.kernel.org/r/1392349908-29685-1-git-send-email-vnagarnaik@google.com Cc: Laurent Chavey <chavey@google.com> Cc: stable@vger.kernel.org # 3.10+ Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-02-14 11:51:48 +08:00
char *type_str = #type"["__stringify(len)"]"; \
BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
tracing: Fix array size mismatch in format string In event format strings, the array size is reported in two locations. One in array subscript and then via the "size:" attribute. The values reported there have a mismatch. For e.g., in sched:sched_switch the prev_comm and next_comm character arrays have subscript values as [32] where as the actual field size is 16. name: sched_switch ID: 301 format: field:unsigned short common_type; offset:0; size:2; signed:0; field:unsigned char common_flags; offset:2; size:1; signed:0; field:unsigned char common_preempt_count; offset:3; size:1;signed:0; field:int common_pid; offset:4; size:4; signed:1; field:char prev_comm[32]; offset:8; size:16; signed:1; field:pid_t prev_pid; offset:24; size:4; signed:1; field:int prev_prio; offset:28; size:4; signed:1; field:long prev_state; offset:32; size:8; signed:1; field:char next_comm[32]; offset:40; size:16; signed:1; field:pid_t next_pid; offset:56; size:4; signed:1; field:int next_prio; offset:60; size:4; signed:1; After bisection, the following commit was blamed: 92edca0 tracing: Use direct field, type and system names This commit removes the duplication of strings for field->name and field->type assuming that all the strings passed in __trace_define_field() are immutable. This is not true for arrays, where the type string is created in event_storage variable and field->type for all array fields points to event_storage. Use __stringify() to create a string constant for the type string. Also, get rid of event_storage and event_storage_mutex that are not needed anymore. also, an added benefit is that this reduces the overhead of events a bit more: text data bss dec hex filename 8424787 2036472 1302528 11763787 b3804b vmlinux 8420814 2036408 1302528 11759750 b37086 vmlinux.patched Link: http://lkml.kernel.org/r/1392349908-29685-1-git-send-email-vnagarnaik@google.com Cc: Laurent Chavey <chavey@google.com> Cc: stable@vger.kernel.org # 3.10+ Signed-off-by: Vaibhav Nagarnaik <vnagarnaik@google.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-02-14 11:51:48 +08:00
ret = trace_define_field(event_call, type_str, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), FILTER_OTHER); \
if (ret) \
return ret; \
} while (0);
#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), \
is_signed_type(type), FILTER_OTHER);
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
#undef __string
#define __string(item, src) __dynamic_array(char, item, -1)
tracing/events: provide string with undefined size support This patch provides the support for dynamic size strings on event tracing. The key concept is to use a structure with an ending char array field of undefined size and use such ability to allocate the minimal size on the ring buffer to make one or more string entries fit inside, as opposite to a fixed length strings with upper bound. The strings themselves are represented using fields which have an offset value from the beginning of the entry. This patch provides three new macros: __string(item, src) This one declares a string to the structure inside TP_STRUCT__entry. You need to provide the name of the string field and the source that will be copied inside. This will also add the dynamic size of the string needed for the ring buffer entry allocation. A stack allocated structure is used to temporarily store the offset of each strings, avoiding double calls to strlen() on each event insertion. __get_str(field) This one will give you a pointer to the string you have created. This is an abstract helper to resolve the absolute address given the field name which is a relative address from the beginning of the trace_structure. __assign_str(dst, src) Use this macro to automatically perform the string copy from src to dst. src must be a variable to assign and dst is the name of a __string field. Example on how to use it: TRACE_EVENT(my_event, TP_PROTO(char *src1, char *src2), TP_ARGS(src1, src2), TP_STRUCT__entry( __string(str1, src1) __string(str2, src2) ), TP_fast_assign( __assign_str(str1, src1); __assign_str(str2, src2); ), TP_printk("%s %s", __get_str(src1), __get_str(src2)) ) Of course you can mix-up any __field or __array inside this TRACE_EVENT. The position of the __string or __assign_str doesn't matter. Changes in v2: Address the suggestion of Steven Rostedt: drop the opening_string() macro and redefine __ending_string() to get the size of the string to be copied instead of overwritting the whole ring buffer allocation. Changes in v3: Address other suggestions of Steven Rostedt and Peter Zijlstra with some changes: drop the __ending_string and the need to have only one string field. Use offsets instead of absolute addresses. [ Impact: allow more compact memory usage for string tracing ] Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Steven Rostedt <rostedt@goodmis.org> Cc: Li Zefan <lizf@cn.fujitsu.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
2009-04-19 10:51:29 +08:00
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
#undef __bitmask
#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, func, print) \
static int notrace __init \
trace_event_define_fields_##call(struct trace_event_call *event_call) \
{ \
struct trace_event_raw_##call field; \
int ret; \
\
tstruct; \
\
return ret; \
}
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args)
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
/*
* remember the offset of each array from the beginning of the event.
*/
#undef __entry
#define __entry entry
#undef __field
#define __field(type, item)
#undef __field_ext
#define __field_ext(type, item, filter_type)
#undef __field_struct
#define __field_struct(type, item)
#undef __field_struct_ext
#define __field_struct_ext(type, item, filter_type)
#undef __array
#define __array(type, item, len)
#undef __dynamic_array
#define __dynamic_array(type, item, len) \
__item_length = (len) * sizeof(type); \
__data_offsets->item = __data_size + \
offsetof(typeof(*entry), __data); \
__data_offsets->item |= __item_length << 16; \
__data_size += __item_length;
#undef __string
tracing: Allow events to have NULL strings If an TRACE_EVENT() uses __assign_str() or __get_str on a NULL pointer then the following oops will happen: BUG: unable to handle kernel NULL pointer dereference at (null) IP: [<c127a17b>] strlen+0x10/0x1a *pde = 00000000 ^M Oops: 0000 [#1] PREEMPT SMP Modules linked in: CPU: 1 PID: 0 Comm: swapper/1 Not tainted 3.13.0-rc1-test+ #2 Hardware name: /DG965MQ, BIOS MQ96510J.86A.0372.2006.0605.1717 06/05/2006^M task: f5cde9f0 ti: f5e5e000 task.ti: f5e5e000 EIP: 0060:[<c127a17b>] EFLAGS: 00210046 CPU: 1 EIP is at strlen+0x10/0x1a EAX: 00000000 EBX: c2472da8 ECX: ffffffff EDX: c2472da8 ESI: c1c5e5fc EDI: 00000000 EBP: f5e5fe84 ESP: f5e5fe80 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068 CR0: 8005003b CR2: 00000000 CR3: 01f32000 CR4: 000007d0 Stack: f5f18b90 f5e5feb8 c10687a8 0759004f 00000005 00000005 00000005 00200046 00000002 00000000 c1082a93 f56c7e28 c2472da8 c1082a93 f5e5fee4 c106bc61^M 00000000 c1082a93 00000000 00000000 00000001 00200046 00200082 00000000 Call Trace: [<c10687a8>] ftrace_raw_event_lock+0x39/0xc0 [<c1082a93>] ? ktime_get+0x29/0x69 [<c1082a93>] ? ktime_get+0x29/0x69 [<c106bc61>] lock_release+0x57/0x1a5 [<c1082a93>] ? ktime_get+0x29/0x69 [<c10824dd>] read_seqcount_begin.constprop.7+0x4d/0x75 [<c1082a93>] ? ktime_get+0x29/0x69^M [<c1082a93>] ktime_get+0x29/0x69 [<c108a46a>] __tick_nohz_idle_enter+0x1e/0x426 [<c10690e8>] ? lock_release_holdtime.part.19+0x48/0x4d [<c10bc184>] ? time_hardirqs_off+0xe/0x28 [<c1068c82>] ? trace_hardirqs_off_caller+0x3f/0xaf [<c108a8cb>] tick_nohz_idle_enter+0x59/0x62 [<c1079242>] cpu_startup_entry+0x64/0x192 [<c102299c>] start_secondary+0x277/0x27c Code: 90 89 c6 89 d0 88 c4 ac 38 e0 74 09 84 c0 75 f7 be 01 00 00 00 89 f0 48 5e 5d c3 55 89 e5 57 66 66 66 66 90 83 c9 ff 89 c7 31 c0 <f2> ae f7 d1 8d 41 ff 5f 5d c3 55 89 e5 57 66 66 66 66 90 31 ff EIP: [<c127a17b>] strlen+0x10/0x1a SS:ESP 0068:f5e5fe80 CR2: 0000000000000000 ---[ end trace 01bc47bf519ec1b2 ]--- New tracepoints have been added that have allowed for NULL pointers being assigned to strings. To fix this, change the TRACE_EVENT() code to check for NULL and if it is, it will assign "(null)" to it instead (similar to what glibc printf does). Reported-by: Shuah Khan <shuah.kh@samsung.com> Reported-by: Jovi Zhangwei <jovi.zhangwei@gmail.com> Link: http://lkml.kernel.org/r/CAGdX0WFeEuy+DtpsJzyzn0343qEEjLX97+o1VREFkUEhndC+5Q@mail.gmail.com Link: http://lkml.kernel.org/r/528D6972.9010702@samsung.com Fixes: 9cbf117662e2 ("tracing/events: provide string with undefined size support") Cc: stable@vger.kernel.org # 2.6.31+ Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-11-26 22:22:54 +08:00
#define __string(item, src) __dynamic_array(char, item, \
strlen((src) ? (const char *)(src) : "(null)") + 1)
tracing: Add __bitmask() macro to trace events to cpumasks and other bitmasks Being able to show a cpumask of events can be useful as some events may affect only some CPUs. There is no standard way to record the cpumask and converting it to a string is rather expensive during the trace as traces happen in hotpaths. It would be better to record the raw event mask and be able to parse it at print time. The following macros were added for use with the TRACE_EVENT() macro: __bitmask() __assign_bitmask() __get_bitmask() To test this, I added this to the sched_migrate_task event, which looked like this: TRACE_EVENT(sched_migrate_task, TP_PROTO(struct task_struct *p, int dest_cpu, const struct cpumask *cpus), TP_ARGS(p, dest_cpu, cpus), TP_STRUCT__entry( __array( char, comm, TASK_COMM_LEN ) __field( pid_t, pid ) __field( int, prio ) __field( int, orig_cpu ) __field( int, dest_cpu ) __bitmask( cpumask, num_possible_cpus() ) ), TP_fast_assign( memcpy(__entry->comm, p->comm, TASK_COMM_LEN); __entry->pid = p->pid; __entry->prio = p->prio; __entry->orig_cpu = task_cpu(p); __entry->dest_cpu = dest_cpu; __assign_bitmask(cpumask, cpumask_bits(cpus), num_possible_cpus()); ), TP_printk("comm=%s pid=%d prio=%d orig_cpu=%d dest_cpu=%d cpumask=%s", __entry->comm, __entry->pid, __entry->prio, __entry->orig_cpu, __entry->dest_cpu, __get_bitmask(cpumask)) ); With the output of: ksmtuned-3613 [003] d..2 485.220508: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=3 dest_cpu=2 cpumask=00000000,0000000f migration/1-13 [001] d..5 485.221202: sched_migrate_task: comm=ksmtuned pid=3614 prio=120 orig_cpu=1 dest_cpu=0 cpumask=00000000,0000000f awk-3615 [002] d.H5 485.221747: sched_migrate_task: comm=rcu_preempt pid=7 prio=120 orig_cpu=0 dest_cpu=1 cpumask=00000000,000000ff migration/2-18 [002] d..5 485.222062: sched_migrate_task: comm=ksmtuned pid=3615 prio=120 orig_cpu=2 dest_cpu=3 cpumask=00000000,0000000f Link: http://lkml.kernel.org/r/1399377998-14870-6-git-send-email-javi.merino@arm.com Link: http://lkml.kernel.org/r/20140506132238.22e136d1@gandalf.local.home Suggested-by: Javi Merino <javi.merino@arm.com> Tested-by: Javi Merino <javi.merino@arm.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2014-05-07 01:10:24 +08:00
/*
* __bitmask_size_in_bytes_raw is the number of bytes needed to hold
* num_possible_cpus().
*/
#define __bitmask_size_in_bytes_raw(nr_bits) \
(((nr_bits) + 7) / 8)
#define __bitmask_size_in_longs(nr_bits) \
((__bitmask_size_in_bytes_raw(nr_bits) + \
((BITS_PER_LONG / 8) - 1)) / (BITS_PER_LONG / 8))
/*
* __bitmask_size_in_bytes is the number of bytes needed to hold
* num_possible_cpus() padded out to the nearest long. This is what
* is saved in the buffer, just to be consistent.
*/
#define __bitmask_size_in_bytes(nr_bits) \
(__bitmask_size_in_longs(nr_bits) * (BITS_PER_LONG / 8))
#undef __bitmask
#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, \
__bitmask_size_in_longs(nr_bits))
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
static inline notrace int trace_event_get_offsets_##call( \
struct trace_event_data_offsets_##call *__data_offsets, proto) \
{ \
int __data_size = 0; \
int __maybe_unused __item_length; \
struct trace_event_raw_##call __maybe_unused *entry; \
\
tstruct; \
\
return __data_size; \
}
tracing: Create new TRACE_EVENT_TEMPLATE There are some places in the kernel that define several tracepoints and they are all identical besides the name. The code to enable, disable and record is created for every trace point even if most of the code is identical. This patch adds TRACE_EVENT_TEMPLATE that lets the developer create a template TRACE_EVENT and create trace points with DEFINE_EVENT, which is based off of a given template. Each trace point used by this will share most of the code, and bring down the size of the kernel when there are several duplicate events. Usage is: TRACE_EVENT_TEMPLATE(name, proto, args, tstruct, assign, print); Which would be the same as defining a normal TRACE_EVENT. To create the trace events that the trace points will use: DEFINE_EVENT(template, name, proto, args) is done. The template is the name of the TRACE_EVENT_TEMPLATE to use. The name is the name of the trace point. The parameters proto and args must be the same as the proto and args of the template. If they are not the same, then a compile error will result. I tried hard removing this duplication but the C preprocessor is not powerful enough (or my CPP magic experience points is not at a high enough level) to not need them. A lot of trace events are coming in with new XFS development. Most of the trace points are identical except for the name. The following shows the advantage of having TRACE_EVENT_TEMPLATE: $ size fs/xfs/xfs.o.* text data bss dec hex filename 452114 2788 3520 458422 6feb6 fs/xfs/xfs.o.old 638482 38116 3744 680342 a6196 fs/xfs/xfs.o.template 996954 38116 4480 1039550 fdcbe fs/xfs/xfs.o.trace xfs.o.old is without any tracepoints. xfs.o.template uses the new TRACE_EVENT_TEMPLATE. xfs.o.trace uses the current TRACE_EVENT macros. Requested-by: Christoph Hellwig <hch@lst.de> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:27:27 +08:00
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, name, proto, args)
tracing: Create new DEFINE_EVENT_PRINT After creating the TRACE_EVENT_TEMPLATE I started to look at other trace points to see what duplication was made. I noticed that there are several trace points where they are almost identical except for the name and the output format. Since TRACE_EVENT_TEMPLATE was successful in bringing down the size of trace events, I added a DEFINE_EVENT_PRINT. DEFINE_EVENT_PRINT is used just like DEFINE_EVENT is. That is, the DEFINE_EVENT_PRINT also uses a TRACE_EVENT_TEMPLATE, but it allows the developer to overwrite the print format. If there are two or more TRACE_EVENTS that are identical except for the name and print, then they can be converted to use a TRACE_EVENT_TEMPLATE. Since the TRACE_EVENT_TEMPLATE already does the print output, the first trace event would have its print format held in the TRACE_EVENT_TEMPLATE and be defined with a DEFINE_EVENT. The rest will use the DEFINE_EVENT_PRINT and override the print format. Converting the sched trace points to both DEFINE_EVENT and DEFINE_EVENT_PRINT. Five were converted to DEFINE_EVENT and two were converted to DEFINE_EVENT_PRINT. I was able to get the following: $ size kernel/sched.o-* text data bss dec hex filename 79299 6776 2520 88595 15a13 kernel/sched.o-notrace 101941 11896 2584 116421 1c6c5 kernel/sched.o-templ 104779 11896 2584 119259 1d1db kernel/sched.o-trace sched.o-notrace is the scheduler compiled with no trace points. sched.o-templ is with the use of DEFINE_EVENT and DEFINE_EVENT_PRINT sched.o-trace is the current trace events. Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2009-11-19 09:36:26 +08:00
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print) \
DEFINE_EVENT(template, name, PARAMS(proto), PARAMS(args))
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
/*
* Stage 4 of the trace events.
*
* Override the macros in <trace/trace_events.h> to include the following:
*
* For those macros defined with TRACE_EVENT:
*
* static struct trace_event_call event_<call>;
*
* static void trace_event_raw_event_<call>(void *__data, proto)
* {
* struct trace_event_file *trace_file = __data;
* struct trace_event_call *event_call = trace_file->event_call;
* struct trace_event_data_offsets_<call> __maybe_unused __data_offsets;
* unsigned long eflags = trace_file->flags;
* enum event_trigger_type __tt = ETT_NONE;
* struct ring_buffer_event *event;
* struct trace_event_raw_<call> *entry; <-- defined in stage 1
* struct ring_buffer *buffer;
* unsigned long irq_flags;
* int __data_size;
* int pc;
*
* if (!(eflags & EVENT_FILE_FL_TRIGGER_COND)) {
* if (eflags & EVENT_FILE_FL_TRIGGER_MODE)
* event_triggers_call(trace_file, NULL);
* if (eflags & EVENT_FILE_FL_SOFT_DISABLED)
* return;
* }
*
* local_save_flags(irq_flags);
* pc = preempt_count();
*
* __data_size = trace_event_get_offsets_<call>(&__data_offsets, args);
*
* event = trace_event_buffer_lock_reserve(&buffer, trace_file,
* event_<call>->event.type,
* sizeof(*entry) + __data_size,
* irq_flags, pc);
* if (!event)
* return;
* entry = ring_buffer_event_data(event);
*
* { <assign>; } <-- Here we assign the entries by the __field and
* __array macros.
*
* if (eflags & EVENT_FILE_FL_TRIGGER_COND)
* __tt = event_triggers_call(trace_file, entry);
*
* if (test_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT,
* &trace_file->flags))
* ring_buffer_discard_commit(buffer, event);
* else if (!filter_check_discard(trace_file, entry, buffer, event))
* trace_buffer_unlock_commit(buffer, event, irq_flags, pc);
*
* if (__tt)
* event_triggers_post_call(trace_file, __tt);
* }
*
* static struct trace_event ftrace_event_type_<call> = {
* .trace = trace_raw_output_<call>, <-- stage 2
* };
*
* static char print_fmt_<call>[] = <TP_printk>;
*
* static struct trace_event_class __used event_class_<template> = {
* .system = "<system>",
* .define_fields = trace_event_define_fields_<call>,
* .fields = LIST_HEAD_INIT(event_class_##call.fields),
* .raw_init = trace_event_raw_init,
* .probe = trace_event_raw_event_##call,
* .reg = trace_event_reg,
* };
*
* static struct trace_event_call event_<call> = {
* .class = event_class_<template>,
* {
* .tp = &__tracepoint_<call>,
* },
* .event = &ftrace_event_type_<call>,
* .print_fmt = print_fmt_<call>,
* .flags = TRACE_EVENT_FL_TRACEPOINT,
* };
* // its only safe to use pointers when doing linker tricks to
* // create an array.
* static struct trace_event_call __used
* __attribute__((section("_ftrace_events"))) *__event_<call> = &event_<call>;
*
*/
#ifdef CONFIG_PERF_EVENTS
#define _TRACE_PERF_PROTO(call, proto) \
static notrace void \
perf_trace_##call(void *__data, proto);
#define _TRACE_PERF_INIT(call) \
.perf_probe = perf_trace_##call,
#else
#define _TRACE_PERF_PROTO(call, proto)
#define _TRACE_PERF_INIT(call)
#endif /* CONFIG_PERF_EVENTS */
#undef __entry
#define __entry entry
#undef __field
#define __field(type, item)
#undef __field_struct
#define __field_struct(type, item)
#undef __array
#define __array(type, item, len)
#undef __dynamic_array
#define __dynamic_array(type, item, len) \
__entry->__data_loc_##item = __data_offsets.item;
#undef __string
#define __string(item, src) __dynamic_array(char, item, -1)
#undef __assign_str
#define __assign_str(dst, src) \
strcpy(__get_str(dst), (src) ? (const char *)(src) : "(null)");
#undef __bitmask
#define __bitmask(item, nr_bits) __dynamic_array(unsigned long, item, -1)
#undef __get_bitmask
#define __get_bitmask(field) (char *)__get_dynamic_array(field)
#undef __assign_bitmask
#define __assign_bitmask(dst, src, nr_bits) \
memcpy(__get_bitmask(dst), (src), __bitmask_size_in_bytes(nr_bits))
#undef TP_fast_assign
#define TP_fast_assign(args...) args
#undef __perf_addr
#define __perf_addr(a) (a)
#undef __perf_count
#define __perf_count(c) (c)
#undef __perf_task
#define __perf_task(t) (t)
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
\
static notrace void \
trace_event_raw_event_##call(void *__data, proto) \
{ \
struct trace_event_file *trace_file = __data; \
struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\
struct trace_event_buffer fbuffer; \
struct trace_event_raw_##call *entry; \
int __data_size; \
\
if (trace_trigger_soft_disabled(trace_file)) \
return; \
\
__data_size = trace_event_get_offsets_##call(&__data_offsets, args); \
\
entry = trace_event_buffer_reserve(&fbuffer, trace_file, \
sizeof(*entry) + __data_size); \
\
if (!entry) \
return; \
\
tstruct \
\
{ assign; } \
\
trace_event_buffer_commit(&fbuffer); \
}
/*
* The ftrace_test_probe is compiled out, it is only here as a build time check
* to make sure that if the tracepoint handling changes, the ftrace probe will
* fail to compile unless it too is updated.
*/
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
static inline void ftrace_test_probe_##call(void) \
{ \
check_trace_callback_type_##call(trace_event_raw_event_##template); \
}
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, name, proto, args, print)
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
#undef __entry
#define __entry REC
#undef __print_flags
#undef __print_symbolic
#undef __print_hex
#undef __get_dynamic_array
#undef __get_dynamic_array_len
#undef __get_str
#undef __get_bitmask
#undef __print_array
#undef TP_printk
#define TP_printk(fmt, args...) "\"" fmt "\", " __stringify(args)
#undef DECLARE_EVENT_CLASS
#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
_TRACE_PERF_PROTO(call, PARAMS(proto)); \
static char print_fmt_##call[] = print; \
static struct trace_event_class __used __refdata event_class_##call = { \
.system = TRACE_SYSTEM_STRING, \
.define_fields = trace_event_define_fields_##call, \
.fields = LIST_HEAD_INIT(event_class_##call.fields),\
.raw_init = trace_event_raw_init, \
.probe = trace_event_raw_event_##call, \
.reg = trace_event_reg, \
_TRACE_PERF_INIT(call) \
};
#undef DEFINE_EVENT
#define DEFINE_EVENT(template, call, proto, args) \
\
static struct trace_event_call __used event_##call = { \
.class = &event_class_##template, \
{ \
.tp = &__tracepoint_##call, \
}, \
.event.funcs = &trace_event_type_funcs_##template, \
.print_fmt = print_fmt_##template, \
.flags = TRACE_EVENT_FL_TRACEPOINT, \
}; \
static struct trace_event_call __used \
__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
#undef DEFINE_EVENT_PRINT
#define DEFINE_EVENT_PRINT(template, call, proto, args, print) \
\
static char print_fmt_##call[] = print; \
\
static struct trace_event_call __used event_##call = { \
.class = &event_class_##template, \
{ \
.tp = &__tracepoint_##call, \
}, \
.event.funcs = &trace_event_type_funcs_##call, \
.print_fmt = print_fmt_##call, \
.flags = TRACE_EVENT_FL_TRACEPOINT, \
}; \
static struct trace_event_call __used \
__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call
#include TRACE_INCLUDE(TRACE_INCLUDE_FILE)