tracing/probes: Add fprobe events for tracing function entry and exit.

Add fprobe events for tracing function entry and exit instead of kprobe
events. With this change, we can continue to trace function entry/exit
even if the CONFIG_KPROBES_ON_FTRACE is not available. Since
CONFIG_KPROBES_ON_FTRACE requires the CONFIG_DYNAMIC_FTRACE_WITH_REGS,
it is not available if the architecture only supports
CONFIG_DYNAMIC_FTRACE_WITH_ARGS. And that means kprobe events can not
probe function entry/exit effectively on such architecture.
But this can be solved if the dynamic events supports fprobe events.

The fprobe event is a new dynamic events which is only for the function
(symbol) entry and exit. This event accepts non register fetch arguments
so that user can trace the function arguments and return values.

The fprobe events syntax is here;

 f[:[GRP/][EVENT]] FUNCTION [FETCHARGS]
 f[MAXACTIVE][:[GRP/][EVENT]] FUNCTION%return [FETCHARGS]

E.g.

 # echo 'f vfs_read $arg1'  >> dynamic_events
 # echo 'f vfs_read%return $retval'  >> dynamic_events
 # cat dynamic_events
 f:fprobes/vfs_read__entry vfs_read arg1=$arg1
 f:fprobes/vfs_read__exit vfs_read%return arg1=$retval
 # echo 1 > events/fprobes/enable
 # head -n 20 trace | tail
 #           TASK-PID     CPU#  |||||  TIMESTAMP  FUNCTION
 #              | |         |   |||||     |         |
              sh-142     [005] ...1.   448.386420: vfs_read__entry: (vfs_read+0x4/0x340) arg1=0xffff888007f7c540
              sh-142     [005] .....   448.386436: vfs_read__exit: (ksys_read+0x75/0x100 <- vfs_read) arg1=0x1
              sh-142     [005] ...1.   448.386451: vfs_read__entry: (vfs_read+0x4/0x340) arg1=0xffff888007f7c540
              sh-142     [005] .....   448.386458: vfs_read__exit: (ksys_read+0x75/0x100 <- vfs_read) arg1=0x1
              sh-142     [005] ...1.   448.386469: vfs_read__entry: (vfs_read+0x4/0x340) arg1=0xffff888007f7c540
              sh-142     [005] .....   448.386476: vfs_read__exit: (ksys_read+0x75/0x100 <- vfs_read) arg1=0x1
              sh-142     [005] ...1.   448.602073: vfs_read__entry: (vfs_read+0x4/0x340) arg1=0xffff888007f7c540
              sh-142     [005] .....   448.602089: vfs_read__exit: (ksys_read+0x75/0x100 <- vfs_read) arg1=0x1

Link: https://lore.kernel.org/all/168507469754.913472.6112857614708350210.stgit@mhiramat.roam.corp.google.com/

Reported-by: kernel test robot <[email protected]>
Link: https://lore.kernel.org/all/[email protected]/
Signed-off-by: Masami Hiramatsu (Google) <[email protected]>

Author: mhiramat

include/linux/fprobe.h

@@ -66,6 +66,7 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter
 int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num);
 int register_fprobe_syms(struct fprobe *fp, const char **syms, int num);
 int unregister_fprobe(struct fprobe *fp);
+bool fprobe_is_registered(struct fprobe *fp);
 #else
 static inline int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter)
 {
@@ -83,6 +84,10 @@ static inline int unregister_fprobe(struct fprobe *fp)
 {
 	return -EOPNOTSUPP;
 }
+static inline bool fprobe_is_registered(struct fprobe *fp)
+{
+	return false;
+}
 #endif
 
 /**

include/linux/trace_events.h

@@ -318,6 +318,7 @@ enum {
 	TRACE_EVENT_FL_KPROBE_BIT,
 	TRACE_EVENT_FL_UPROBE_BIT,
 	TRACE_EVENT_FL_EPROBE_BIT,
+	TRACE_EVENT_FL_FPROBE_BIT,
 	TRACE_EVENT_FL_CUSTOM_BIT,
 };
 
@@ -332,6 +333,7 @@ enum {
  *  KPROBE        - Event is a kprobe
  *  UPROBE        - Event is a uprobe
  *  EPROBE        - Event is an event probe
+ *  FPROBE        - Event is an function probe
  *  CUSTOM        - Event is a custom event (to be attached to an exsiting tracepoint)
  *                   This is set when the custom event has not been attached
  *                   to a tracepoint yet, then it is cleared when it is.
@@ -346,6 +348,7 @@ enum {
 	TRACE_EVENT_FL_KPROBE		= (1 << TRACE_EVENT_FL_KPROBE_BIT),
 	TRACE_EVENT_FL_UPROBE		= (1 << TRACE_EVENT_FL_UPROBE_BIT),
 	TRACE_EVENT_FL_EPROBE		= (1 << TRACE_EVENT_FL_EPROBE_BIT),
+	TRACE_EVENT_FL_FPROBE		= (1 << TRACE_EVENT_FL_FPROBE_BIT),
 	TRACE_EVENT_FL_CUSTOM		= (1 << TRACE_EVENT_FL_CUSTOM_BIT),
 };
 

kernel/trace/Kconfig

@@ -650,6 +650,20 @@ config BLK_DEV_IO_TRACE
 
 	  If unsure, say N.
 
+config FPROBE_EVENTS
+	depends on FPROBE
+	depends on HAVE_REGS_AND_STACK_ACCESS_API
+	bool "Enable fprobe-based dynamic events"
+	select TRACING
+	select PROBE_EVENTS
+	select DYNAMIC_EVENTS
+	default y
+	help
+	  This allows user to add tracing events on the function entry and
+	  exit via ftrace interface. The syntax is same as the kprobe events
+	  and the kprobe events on function entry and exit will be
+	  transparently converted to this fprobe events.
+
 config KPROBE_EVENTS
 	depends on KPROBES
 	depends on HAVE_REGS_AND_STACK_ACCESS_API

kernel/trace/Makefile

@@ -104,6 +104,7 @@ obj-$(CONFIG_BOOTTIME_TRACING) += trace_boot.o
 obj-$(CONFIG_FTRACE_RECORD_RECURSION) += trace_recursion_record.o
 obj-$(CONFIG_FPROBE) += fprobe.o
 obj-$(CONFIG_RETHOOK) += rethook.o
+obj-$(CONFIG_FPROBE_EVENTS) += trace_fprobe.o
 
 obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
 obj-$(CONFIG_RV) += rv/

kernel/trace/fprobe.c

@@ -348,6 +348,14 @@ int register_fprobe_syms(struct fprobe *fp, const char **syms, int num)
 }
 EXPORT_SYMBOL_GPL(register_fprobe_syms);
 
+bool fprobe_is_registered(struct fprobe *fp)
+{
+	if (!fp || (fp->ops.saved_func != fprobe_handler &&
+		    fp->ops.saved_func != fprobe_kprobe_handler))
+		return false;
+	return true;
+}
+
 /**
  * unregister_fprobe() - Unregister fprobe from ftrace
  * @fp: A fprobe data structure to be unregistered.
@@ -360,8 +368,7 @@ int unregister_fprobe(struct fprobe *fp)
 {
 	int ret;
 
-	if (!fp || (fp->ops.saved_func != fprobe_handler &&
-		    fp->ops.saved_func != fprobe_kprobe_handler))
+	if (!fprobe_is_registered(fp))
 		return -EINVAL;
 
 	/*

kernel/trace/trace.c

@@ -5672,10 +5672,16 @@ static const char readme_msg[] =
 	"  uprobe_events\t\t- Create/append/remove/show the userspace dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
-#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS) || \
+    defined(CONFIG_FPROBE_EVENTS)
 	"\t  accepts: event-definitions (one definition per line)\n"
+#if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
 	"\t   Format: p[:[<group>/][<event>]] <place> [<args>]\n"
 	"\t           r[maxactive][:[<group>/][<event>]] <place> [<args>]\n"
+#endif
+#ifdef CONFIG_FPROBE_EVENTS
+	"\t           f[:[<group>/][<event>]] <func-name>[%return] [<args>]\n"
+#endif
 #ifdef CONFIG_HIST_TRIGGERS
 	"\t           s:[synthetic/]<event> <field> [<field>]\n"
 #endif

kernel/trace/trace.h

@@ -148,6 +148,17 @@ struct kretprobe_trace_entry_head {
 	unsigned long		ret_ip;
 };
 
+struct fentry_trace_entry_head {
+	struct trace_entry	ent;
+	unsigned long		ip;
+};
+
+struct fexit_trace_entry_head {
+	struct trace_entry	ent;
+	unsigned long		func;
+	unsigned long		ret_ip;
+};
+
 #define TRACE_BUF_SIZE		1024
 
 struct trace_array;