Merge branch 'tip/tracing/core4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/core

Documentation/trace/ftrace-design.txt

@@ -0,0 +1,233 @@
+		function tracer guts
+		====================
+
+Introduction
+------------
+
+Here we will cover the architecture pieces that the common function tracing
+code relies on for proper functioning.  Things are broken down into increasing
+complexity so that you can start simple and at least get basic functionality.
+
+Note that this focuses on architecture implementation details only.  If you
+want more explanation of a feature in terms of common code, review the common
+ftrace.txt file.
+
+
+Prerequisites
+-------------
+
+Ftrace relies on these features being implemented:
+ STACKTRACE_SUPPORT - implement save_stack_trace()
+ TRACE_IRQFLAGS_SUPPORT - implement include/asm/irqflags.h
+
+
+HAVE_FUNCTION_TRACER
+--------------------
+
+You will need to implement the mcount and the ftrace_stub functions.
+
+The exact mcount symbol name will depend on your toolchain.  Some call it
+"mcount", "_mcount", or even "__mcount".  You can probably figure it out by
+running something like:
+	$ echo 'main(){}' | gcc -x c -S -o - - -pg | grep mcount
+	        call    mcount
+We'll make the assumption below that the symbol is "mcount" just to keep things
+nice and simple in the examples.
+
+Keep in mind that the ABI that is in effect inside of the mcount function is
+*highly* architecture/toolchain specific.  We cannot help you in this regard,
+sorry.  Dig up some old documentation and/or find someone more familiar than
+you to bang ideas off of.  Typically, register usage (argument/scratch/etc...)
+is a major issue at this point, especially in relation to the location of the
+mcount call (before/after function prologue).  You might also want to look at
+how glibc has implemented the mcount function for your architecture.  It might
+be (semi-)relevant.
+
+The mcount function should check the function pointer ftrace_trace_function
+to see if it is set to ftrace_stub.  If it is, there is nothing for you to do,
+so return immediately.  If it isn't, then call that function in the same way
+the mcount function normally calls __mcount_internal -- the first argument is
+the "frompc" while the second argument is the "selfpc" (adjusted to remove the
+size of the mcount call that is embedded in the function).
+
+For example, if the function foo() calls bar(), when the bar() function calls
+mcount(), the arguments mcount() will pass to the tracer are:
+	"frompc" - the address bar() will use to return to foo()
+	"selfpc" - the address bar() (with _mcount() size adjustment)
+
+Also keep in mind that this mcount function will be called *a lot*, so
+optimizing for the default case of no tracer will help the smooth running of
+your system when tracing is disabled.  So the start of the mcount function is
+typically the bare min with checking things before returning.  That also means
+the code flow should usually kept linear (i.e. no branching in the nop case).
+This is of course an optimization and not a hard requirement.
+
+Here is some pseudo code that should help (these functions should actually be
+implemented in assembly):
+
+void ftrace_stub(void)
+{
+	return;
+}
+
+void mcount(void)
+{
+	/* save any bare state needed in order to do initial checking */
+
+	extern void (*ftrace_trace_function)(unsigned long, unsigned long);
+	if (ftrace_trace_function != ftrace_stub)
+		goto do_trace;
+
+	/* restore any bare state */
+
+	return;
+
+do_trace:
+
+	/* save all state needed by the ABI (see paragraph above) */
+
+	unsigned long frompc = ...;
+	unsigned long selfpc = <return address> - MCOUNT_INSN_SIZE;
+	ftrace_trace_function(frompc, selfpc);
+
+	/* restore all state needed by the ABI */
+}
+
+Don't forget to export mcount for modules !
+extern void mcount(void);
+EXPORT_SYMBOL(mcount);
+
+
+HAVE_FUNCTION_TRACE_MCOUNT_TEST
+-------------------------------
+
+This is an optional optimization for the normal case when tracing is turned off
+in the system.  If you do not enable this Kconfig option, the common ftrace
+code will take care of doing the checking for you.
+
+To support this feature, you only need to check the function_trace_stop
+variable in the mcount function.  If it is non-zero, there is no tracing to be
+done at all, so you can return.
+
+This additional pseudo code would simply be:
+void mcount(void)
+{
+	/* save any bare state needed in order to do initial checking */
+
++	if (function_trace_stop)
++		return;
+
+	extern void (*ftrace_trace_function)(unsigned long, unsigned long);
+	if (ftrace_trace_function != ftrace_stub)
+...
+
+
+HAVE_FUNCTION_GRAPH_TRACER
+--------------------------
+
+Deep breath ... time to do some real work.  Here you will need to update the
+mcount function to check ftrace graph function pointers, as well as implement
+some functions to save (hijack) and restore the return address.
+
+The mcount function should check the function pointers ftrace_graph_return
+(compare to ftrace_stub) and ftrace_graph_entry (compare to
+ftrace_graph_entry_stub).  If either of those are not set to the relevant stub
+function, call the arch-specific function ftrace_graph_caller which in turn
+calls the arch-specific function prepare_ftrace_return.  Neither of these
+function names are strictly required, but you should use them anyways to stay
+consistent across the architecture ports -- easier to compare & contrast
+things.
+
+The arguments to prepare_ftrace_return are slightly different than what are
+passed to ftrace_trace_function.  The second argument "selfpc" is the same,
+but the first argument should be a pointer to the "frompc".  Typically this is
+located on the stack.  This allows the function to hijack the return address
+temporarily to have it point to the arch-specific function return_to_handler.
+That function will simply call the common ftrace_return_to_handler function and
+that will return the original return address with which, you can return to the
+original call site.
+
+Here is the updated mcount pseudo code:
+void mcount(void)
+{
+...
+	if (ftrace_trace_function != ftrace_stub)
+		goto do_trace;
+
++#ifdef CONFIG_FUNCTION_GRAPH_TRACER
++	extern void (*ftrace_graph_return)(...);
++	extern void (*ftrace_graph_entry)(...);
++	if (ftrace_graph_return != ftrace_stub ||
++	    ftrace_graph_entry != ftrace_graph_entry_stub)
++		ftrace_graph_caller();
++#endif
+
+	/* restore any bare state */
+...
+
+Here is the pseudo code for the new ftrace_graph_caller assembly function:
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+void ftrace_graph_caller(void)
+{
+	/* save all state needed by the ABI */
+
+	unsigned long *frompc = &...;
+	unsigned long selfpc = <return address> - MCOUNT_INSN_SIZE;
+	prepare_ftrace_return(frompc, selfpc);
+
+	/* restore all state needed by the ABI */
+}
+#endif
+
+For information on how to implement prepare_ftrace_return(), simply look at
+the x86 version.  The only architecture-specific piece in it is the setup of
+the fault recovery table (the asm(...) code).  The rest should be the same
+across architectures.
+
+Here is the pseudo code for the new return_to_handler assembly function.  Note
+that the ABI that applies here is different from what applies to the mcount
+code.  Since you are returning from a function (after the epilogue), you might
+be able to skimp on things saved/restored (usually just registers used to pass
+return values).
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+void return_to_handler(void)
+{
+	/* save all state needed by the ABI (see paragraph above) */
+
+	void (*original_return_point)(void) = ftrace_return_to_handler();
+
+	/* restore all state needed by the ABI */
+
+	/* this is usually either a return or a jump */
+	original_return_point();
+}
+#endif
+
+
+HAVE_FTRACE_NMI_ENTER
+---------------------
+
+If you can't trace NMI functions, then skip this option.
+
+<details to be filled>
+
+
+HAVE_FTRACE_SYSCALLS
+---------------------
+
+<details to be filled>
+
+
+HAVE_FTRACE_MCOUNT_RECORD
+-------------------------
+
+See scripts/recordmcount.pl for more info.
+
+<details to be filled>
+
+
+HAVE_DYNAMIC_FTRACE
+---------------------
+
+<details to be filled>

Documentation/trace/ftrace.txt

@@ -26,6 +26,12 @@ disabled, and more (ftrace allows for tracer plugins, which
 means that the list of tracers can always grow).
 
 
+Implementation Details
+----------------------
+
+See ftrace-design.txt for details for arch porters and such.
+
+
 The File System
 ---------------
 

include/linux/kprobes.h

@@ -48,13 +48,13 @@
 #define KPROBE_HIT_SSDONE	0x00000008
 
 /* Attach to insert probes on any functions which should be ignored*/
-#define __kprobes	__attribute__((__section__(".kprobes.text"))) notrace
+#define __kprobes	__attribute__((__section__(".kprobes.text")))
 #else /* CONFIG_KPROBES */
 typedef int kprobe_opcode_t;
 struct arch_specific_insn {
 	int dummy;
 };
-#define __kprobes	notrace
+#define __kprobes
 #endif /* CONFIG_KPROBES */
 
 struct kprobe;

include/trace/ftrace.h

@@ -239,9 +239,9 @@ ftrace_format_##call(struct ftrace_event_call *unused,			\
 #undef __print_flags
 #define __print_flags(flag, delim, flag_array...)			\
 	({								\
-		static const struct trace_print_flags flags[] =		\
+		static const struct trace_print_flags __flags[] =	\
 			{ flag_array, { -1, NULL }};			\
-		ftrace_print_flags_seq(p, delim, flag, flags);		\
+		ftrace_print_flags_seq(p, delim, flag, __flags);	\
 	})
 
 #undef __print_symbolic
@@ -254,7 +254,7 @@ ftrace_format_##call(struct ftrace_event_call *unused,			\
 
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, assign, print)		\
-enum print_line_t							\
+static enum print_line_t						\
 ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 {									\
 	struct trace_seq *s = &iter->seq;				\
@@ -317,7 +317,7 @@ ftrace_raw_output_##call(struct trace_iterator *iter, int flags)	\
 
 #undef TRACE_EVENT
 #define TRACE_EVENT(call, proto, args, tstruct, func, print)		\
-int									\
+static int								\
 ftrace_define_fields_##call(struct ftrace_event_call *event_call)	\
 {									\
 	struct ftrace_raw_##call field;					\

kernel/trace/Kconfig

@@ -11,12 +11,18 @@ config NOP_TRACER
 
 config HAVE_FTRACE_NMI_ENTER
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config HAVE_FUNCTION_TRACER
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config HAVE_FUNCTION_GRAPH_TRACER
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config HAVE_FUNCTION_GRAPH_FP_TEST
 	bool
@@ -28,21 +34,25 @@ config HAVE_FUNCTION_GRAPH_FP_TEST
 config HAVE_FUNCTION_TRACE_MCOUNT_TEST
 	bool
 	help
-	 This gets selected when the arch tests the function_trace_stop
+	  See Documentation/trace/ftrace-implementation.txt
-	 variable at the mcount call site. Otherwise, this variable
-	 is tested by the called function.
 
 config HAVE_DYNAMIC_FTRACE
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config HAVE_FTRACE_MCOUNT_RECORD
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config HAVE_HW_BRANCH_TRACER
 	bool
 
 config HAVE_SYSCALL_TRACEPOINTS
 	bool
+	help
+	  See Documentation/trace/ftrace-implementation.txt
 
 config TRACER_MAX_TRACE
 	bool
@@ -469,6 +479,18 @@ config FTRACE_STARTUP_TEST
 	  functioning properly. It will do tests on all the configured
 	  tracers of ftrace.
 
+config EVENT_TRACE_TEST_SYSCALLS
+	bool "Run selftest on syscall events"
+	depends on FTRACE_STARTUP_TEST
+	help
+	 This option will also enable testing every syscall event.
+	 It only enables the event and disables it and runs various loads
+	 with the event enabled. This adds a bit more time for kernel boot
+	 up since it runs this on every system call defined.
+
+	 TBD - enable a way to actually call the syscalls as we test their
+	       events
+
 config MMIOTRACE
 	bool "Memory mapped IO tracing"
 	depends on HAVE_MMIOTRACE_SUPPORT && PCI

kernel/trace/ftrace.c

@@ -2062,9 +2062,9 @@ __unregister_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops,
 	int i, len = 0;
 	char *search;
 
-	if (glob && (strcmp(glob, "*") || !strlen(glob)))
+	if (glob && (strcmp(glob, "*") == 0 || !strlen(glob)))
 		glob = NULL;
-	else {
+	else if (glob) {
 		int not;
 
 		type = ftrace_setup_glob(glob, strlen(glob), &search, &not);

kernel/trace/trace_clock.c

@@ -66,10 +66,14 @@ u64 notrace trace_clock(void)
  * Used by plugins that need globally coherent timestamps.
  */
 
-static u64 prev_trace_clock_time;
+/* keep prev_time and lock in the same cacheline. */
-
+static struct {
-static raw_spinlock_t trace_clock_lock ____cacheline_aligned_in_smp =
+	u64 prev_time;
-	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+	raw_spinlock_t lock;
+} trace_clock_struct ____cacheline_aligned_in_smp =
+	{
+		.lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED,
+	};
 
 u64 notrace trace_clock_global(void)
 {
@@ -88,19 +92,19 @@ u64 notrace trace_clock_global(void)
 	if (unlikely(in_nmi()))
 		goto out;
 
-	__raw_spin_lock(&trace_clock_lock);
+	__raw_spin_lock(&trace_clock_struct.lock);
 
 	/*
 	 * TODO: if this happens often then maybe we should reset
-	 * my_scd->clock to prev_trace_clock_time+1, to make sure
+	 * my_scd->clock to prev_time+1, to make sure
 	 * we start ticking with the local clock from now on?
 	 */
-	if ((s64)(now - prev_trace_clock_time) < 0)
+	if ((s64)(now - trace_clock_struct.prev_time) < 0)
-		now = prev_trace_clock_time + 1;
+		now = trace_clock_struct.prev_time + 1;
 
-	prev_trace_clock_time = now;
+	trace_clock_struct.prev_time = now;
 
-	__raw_spin_unlock(&trace_clock_lock);
+	__raw_spin_unlock(&trace_clock_struct.lock);
 
  out:
 	raw_local_irq_restore(flags);

kernel/trace/trace_entries.h

@@ -78,7 +78,7 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
 		__field_desc(	int,		graph_ent,	depth		)
 	),
 
-	F_printk("--> %lx (%d)", __entry->graph_ent.func, __entry->depth)
+	F_printk("--> %lx (%d)", __entry->func, __entry->depth)
 );
 
 /* Function return entry */
@@ -97,8 +97,8 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
 
 	F_printk("<-- %lx (%d) (start: %llx  end: %llx) over: %d",
 		 __entry->func, __entry->depth,
-		 __entry->calltime, __entry->rettim,
+		 __entry->calltime, __entry->rettime,
-		 __entrty->depth)
+		 __entry->depth)
 );
 
 /*
@@ -116,15 +116,6 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
 	__field(	unsigned char,	next_state	)	\
 	__field(	unsigned int,	next_cpu	)
 
-#if 0
-FTRACE_ENTRY_STRUCT_ONLY(ctx_switch_entry,
-
-	F_STRUCT(
-		FTRACE_CTX_FIELDS
-	)
-);
-#endif
-
 FTRACE_ENTRY(context_switch, ctx_switch_entry,
 
 	TRACE_CTX,
@@ -133,7 +124,7 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry,
 		FTRACE_CTX_FIELDS
 	),
 
-	F_printk(b"%u:%u:%u  ==> %u:%u:%u [%03u]",
+	F_printk("%u:%u:%u  ==> %u:%u:%u [%03u]",
 		 __entry->prev_pid, __entry->prev_prio, __entry->prev_state,
 		 __entry->next_pid, __entry->next_prio, __entry->next_state,
 		 __entry->next_cpu
@@ -257,8 +248,8 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
 		__field_desc(	unsigned char,	rw,	width	)
 	),
 
-	F_printk("%lx %lx %lx %d %lx %lx",
+	F_printk("%lx %lx %lx %d %x %x",
-		 __entry->phs, __entry->value, __entry->pc,
+		 (unsigned long)__entry->phys, __entry->value, __entry->pc,
 		 __entry->map_id, __entry->opcode, __entry->width)
 );
 
@@ -275,8 +266,8 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
 		__field_desc(	unsigned char,	map,	opcode	)
 	),
 
-	F_printk("%lx %lx %lx %d %lx",
+	F_printk("%lx %lx %lx %d %x",
-		 __entry->phs, __entry->virt, __entry->len,
+		 (unsigned long)__entry->phys, __entry->virt, __entry->len,
 		 __entry->map_id, __entry->opcode)
 );
 
@@ -370,7 +361,7 @@ FTRACE_ENTRY(kmem_alloc, kmemtrace_alloc_entry,
 		__field(	int,			node		)
 	),
 
-	F_printk("type:%u call_site:%lx ptr:%p req:%lu alloc:%lu"
+	F_printk("type:%u call_site:%lx ptr:%p req:%zi alloc:%zi"
 		 " flags:%x node:%d",
 		 __entry->type_id, __entry->call_site, __entry->ptr,
 		 __entry->bytes_req, __entry->bytes_alloc,

kernel/trace/trace_events.c

@@ -1154,7 +1154,7 @@ static int trace_module_notify(struct notifier_block *self,
 }
 #endif /* CONFIG_MODULES */
 
-struct notifier_block trace_module_nb = {
+static struct notifier_block trace_module_nb = {
 	.notifier_call = trace_module_notify,
 	.priority = 0,
 };
@@ -1326,6 +1326,18 @@ static __init void event_trace_self_tests(void)
 		if (!call->regfunc)
 			continue;
 
+/*
+ * Testing syscall events here is pretty useless, but
+ * we still do it if configured. But this is time consuming.
+ * What we really need is a user thread to perform the
+ * syscalls as we test.
+ */
+#ifndef CONFIG_EVENT_TRACE_TEST_SYSCALLS
+		if (call->system &&
+		    strcmp(call->system, "syscalls") == 0)
+			continue;
+#endif
+
 		pr_info("Testing event %s: ", call->name);
 
 		/*

kernel/trace/trace_export.c

@@ -22,6 +22,47 @@
 #undef __field_struct
 #define __field_struct(type, item)
 
+#undef __field
+#define __field(type, item)				type item;
+
+#undef __field_desc
+#define __field_desc(type, container, item)		type item;
+
+#undef __array
+#define __array(type, item, size)			type item[size];
+
+#undef __array_desc
+#define __array_desc(type, container, item, size)	type item[size];
+
+#undef __dynamic_array
+#define __dynamic_array(type, item)			type item[];
+
+#undef F_STRUCT
+#define F_STRUCT(args...)				args
+
+#undef F_printk
+#define F_printk(fmt, args...) fmt, args
+
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print)	\
+struct ____ftrace_##name {					\
+	tstruct							\
+};								\
+static void __used ____ftrace_check_##name(void)		\
+{								\
+	struct ____ftrace_##name *__entry = NULL;		\
+								\
+	/* force cmpile-time check on F_printk() */		\
+	printk(print);						\
+}
+
+#undef FTRACE_ENTRY_DUP
+#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print)	\
+	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
+
+#include "trace_entries.h"
+
+
 #undef __field
 #define __field(type, item)						\
 	ret = trace_seq_printf(s, "\tfield:" #type " " #item ";\t"	\
@@ -88,10 +129,6 @@ ftrace_format_##name(struct ftrace_event_call *unused,			\
 	return ret;							\
 }
 
-#undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print)	\
-	FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
-
 #include "trace_entries.h"
 
 
@@ -172,32 +209,6 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call)	\
 #undef __dynamic_array
 #define __dynamic_array(type, item)
 
-
-#undef TRACE_ZERO_CHAR
-#define TRACE_ZERO_CHAR(arg)
-
-#undef TRACE_FIELD
-#define TRACE_FIELD(type, item, assign)\
-	entry->item = assign;
-
-#undef TRACE_FIELD
-#define TRACE_FIELD(type, item, assign)\
-	entry->item = assign;
-
-#undef TRACE_FIELD_SIGN
-#define TRACE_FIELD_SIGN(type, item, assign, is_signed)	\
-	TRACE_FIELD(type, item, assign)
-
-#undef TP_CMD
-#define TP_CMD(cmd...)	cmd
-
-#undef TRACE_ENTRY
-#define TRACE_ENTRY	entry
-
-#undef TRACE_FIELD_SPECIAL
-#define TRACE_FIELD_SPECIAL(type_item, item, len, cmd)	\
-	cmd;
-
 #undef FTRACE_ENTRY
 #define FTRACE_ENTRY(call, struct_name, type, tstruct, print)		\
 static int ftrace_raw_init_event_##call(void);				\