ftrace: Add recording of functions that caused recursion

This adds CONFIG_FTRACE_RECORD_RECURSION that will record to a file "recursed_functions" all the functions that caused recursion while a callback to the function tracer was running. Link: https://lkml.kernel.org/r/[email protected] Cc: Masami Hiramatsu <[email protected]> Cc: Andrew Morton <[email protected]> Cc: Peter Zijlstra <[email protected]> Cc: Ingo Molnar <[email protected]> Cc: Jonathan Corbet <[email protected]> Cc: Guo Ren <[email protected]> Cc: "James E.J. Bottomley" <[email protected]> Cc: Helge Deller <[email protected]> Cc: Michael Ellerman <[email protected]> Cc: Benjamin Herrenschmidt <[email protected]> Cc: Paul Mackerras <[email protected]> Cc: Heiko Carstens <[email protected]> Cc: Vasily Gorbik <[email protected]> Cc: Christian Borntraeger <[email protected]> Cc: Thomas Gleixner <[email protected]> Cc: Borislav Petkov <[email protected]> Cc: [email protected] Cc: "H. Peter Anvin" <[email protected]> Cc: Kees Cook <[email protected]> Cc: Anton Vorontsov <[email protected]> Cc: Colin Cross <[email protected]> Cc: Tony Luck <[email protected]> Cc: Josh Poimboeuf <[email protected]> Cc: Jiri Kosina <[email protected]> Cc: Miroslav Benes <[email protected]> Cc: Petr Mladek <[email protected]> Cc: Joe Lawrence <[email protected]> Cc: Kamalesh Babulal <[email protected]> Cc: Mauro Carvalho Chehab <[email protected]> Cc: Sebastian Andrzej Siewior <[email protected]> Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Cc: [email protected] Signed-off-by: Steven Rostedt (VMware) <[email protected]>
sm00th · Nov 6, 2020 · 773c167 · 773c167
1 parent a25d036
commit 773c167
Show file tree

Hide file tree

Showing 17 changed files with 306 additions and 20 deletions.
diff --git a/Documentation/trace/ftrace-uses.rst b/Documentation/trace/ftrace-uses.rst
@@ -118,7 +118,7 @@ can help in this regard. If you start your code with:
 
 	int bit;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 
@@ -130,7 +130,9 @@ The code in between will be safe to use, even if it ends up calling a
 function that the callback is tracing. Note, on success,
 ftrace_test_recursion_trylock() will disable preemption, and the
 ftrace_test_recursion_unlock() will enable it again (if it was previously
-enabled).
+enabled). The instruction pointer (ip) and its parent (parent_ip) is passed to
+ftrace_test_recursion_trylock() to record where the recursion happened
+(if CONFIG_FTRACE_RECORD_RECURSION is set).
 
 Alternatively, if the FTRACE_OPS_FL_RECURSION flag is set on the ftrace_ops
 (as explained below), then a helper trampoline will be used to test

diff --git a/arch/csky/kernel/probes/ftrace.c b/arch/csky/kernel/probes/ftrace.c
@@ -18,7 +18,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	struct kprobe *p;
 	struct kprobe_ctlblk *kcb;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 

diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
@@ -210,7 +210,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	struct kprobe *p;
 	int bit;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 

diff --git a/arch/powerpc/kernel/kprobes-ftrace.c b/arch/powerpc/kernel/kprobes-ftrace.c
@@ -20,7 +20,7 @@ void kprobe_ftrace_handler(unsigned long nip, unsigned long parent_nip,
 	struct kprobe_ctlblk *kcb;
 	int bit;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(nip, parent_nip);
 	if (bit < 0)
 		return;
 

diff --git a/arch/s390/kernel/ftrace.c b/arch/s390/kernel/ftrace.c
@@ -204,7 +204,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	struct kprobe *p;
 	int bit;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 

diff --git a/arch/x86/kernel/kprobes/ftrace.c b/arch/x86/kernel/kprobes/ftrace.c
@@ -20,7 +20,7 @@ void kprobe_ftrace_handler(unsigned long ip, unsigned long parent_ip,
 	struct kprobe_ctlblk *kcb;
 	int bit;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 

diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c
@@ -41,7 +41,7 @@ static void notrace pstore_ftrace_call(unsigned long ip,
 	if (unlikely(oops_in_progress))
 		return;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 

diff --git a/include/linux/trace_recursion.h b/include/linux/trace_recursion.h
@@ -91,6 +91,9 @@ enum {
 	 * not be correct. Allow for a single recursion to cover this case.
 	 */
 	TRACE_TRANSITION_BIT,
+
+	/* Used to prevent recursion recording from recursing. */
+	TRACE_RECORD_RECURSION_BIT,
 };
 
 #define trace_recursion_set(bit)	do { (current)->trace_recursion |= (1<<(bit)); } while (0)
@@ -142,7 +145,22 @@ static __always_inline int trace_get_context_bit(void)
 			pc & HARDIRQ_MASK ? TRACE_CTX_IRQ : TRACE_CTX_SOFTIRQ;
 }
 
-static __always_inline int trace_test_and_set_recursion(int start, int max)
+#ifdef CONFIG_FTRACE_RECORD_RECURSION
+extern void ftrace_record_recursion(unsigned long ip, unsigned long parent_ip);
+# define do_ftrace_record_recursion(ip, pip)				\
+	do {								\
+		if (!trace_recursion_test(TRACE_RECORD_RECURSION_BIT)) { \
+			trace_recursion_set(TRACE_RECORD_RECURSION_BIT); \
+			ftrace_record_recursion(ip, pip);		\
+			trace_recursion_clear(TRACE_RECORD_RECURSION_BIT); \
+		}							\
+	} while (0)
+#else
+# define do_ftrace_record_recursion(ip, pip)	do { } while (0)
+#endif
+
+static __always_inline int trace_test_and_set_recursion(unsigned long ip, unsigned long pip,
+							int start, int max)
 {
 	unsigned int val = current->trace_recursion;
 	int bit;
@@ -158,8 +176,10 @@ static __always_inline int trace_test_and_set_recursion(int start, int max)
 		 * a switch between contexts. Allow for a single recursion.
 		 */
 		bit = TRACE_TRANSITION_BIT;
-		if (trace_recursion_test(bit))
+		if (trace_recursion_test(bit)) {
+			do_ftrace_record_recursion(ip, pip);
 			return -1;
+		}
 		trace_recursion_set(bit);
 		barrier();
 		return bit + 1;
@@ -199,9 +219,10 @@ static __always_inline void trace_clear_recursion(int bit)
  * Returns: -1 if a recursion happened.
  *           >= 0 if no recursion
  */
-static __always_inline int ftrace_test_recursion_trylock(void)
+static __always_inline int ftrace_test_recursion_trylock(unsigned long ip,
+							 unsigned long parent_ip)
 {
-	return trace_test_and_set_recursion(TRACE_FTRACE_START, TRACE_FTRACE_MAX);
+	return trace_test_and_set_recursion(ip, parent_ip, TRACE_FTRACE_START, TRACE_FTRACE_MAX);
 }
 
 /**

diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c
@@ -49,7 +49,7 @@ static void notrace klp_ftrace_handler(unsigned long ip,
 
 	ops = container_of(fops, struct klp_ops, fops);
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (WARN_ON_ONCE(bit < 0))
 		return;
 	/*

diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
@@ -727,6 +727,31 @@ config TRACE_EVAL_MAP_FILE
 
 	If unsure, say N.
 
+config FTRACE_RECORD_RECURSION
+	bool "Record functions that recurse in function tracing"
+	depends on FUNCTION_TRACER
+	help
+	  All callbacks that attach to the function tracing have some sort
+	  of protection against recursion. Even though the protection exists,
+	  it adds overhead. This option will create a file in the tracefs
+	  file system called "recursed_functions" that will list the functions
+	  that triggered a recursion.
+
+	  This will add more overhead to cases that have recursion.
+
+	  If unsure, say N
+
+config FTRACE_RECORD_RECURSION_SIZE
+	int "Max number of recursed functions to record"
+	default	128
+	depends on FTRACE_RECORD_RECURSION
+	help
+	  This defines the limit of number of functions that can be
+	  listed in the "recursed_functions" file, that lists all
+	  the functions that caused a recursion to happen.
+	  This file can be reset, but the limit can not change in
+	  size at runtime.
+
 config GCOV_PROFILE_FTRACE
 	bool "Enable GCOV profiling on ftrace subsystem"
 	depends on GCOV_KERNEL

diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
@@ -92,6 +92,7 @@ obj-$(CONFIG_DYNAMIC_EVENTS) += trace_dynevent.o
 obj-$(CONFIG_PROBE_EVENTS) += trace_probe.o
 obj-$(CONFIG_UPROBE_EVENTS) += trace_uprobe.o
 obj-$(CONFIG_BOOTTIME_TRACING) += trace_boot.o
+obj-$(CONFIG_FTRACE_RECORD_RECURSION) += trace_recursion_record.o
 
 obj-$(CONFIG_TRACEPOINT_BENCHMARK) += trace_benchmark.o
 

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
@@ -6918,7 +6918,7 @@ __ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip,
 	struct ftrace_ops *op;
 	int bit;
 
-	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
+	bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX);
 	if (bit < 0)
 		return;
 
@@ -6993,7 +6993,7 @@ static void ftrace_ops_assist_func(unsigned long ip, unsigned long parent_ip,
 {
 	int bit;
 
-	bit = trace_test_and_set_recursion(TRACE_LIST_START, TRACE_LIST_MAX);
+	bit = trace_test_and_set_recursion(ip, parent_ip, TRACE_LIST_START, TRACE_LIST_MAX);
 	if (bit < 0)
 		return;
 

diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
@@ -447,7 +447,7 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
 	if ((unsigned long)ops->private != smp_processor_id())
 		return;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 

diff --git a/kernel/trace/trace_functions.c b/kernel/trace/trace_functions.c
@@ -141,7 +141,7 @@ function_trace_call(unsigned long ip, unsigned long parent_ip,
 	if (unlikely(!tr->function_enabled))
 		return;
 
-	bit = ftrace_test_recursion_trylock();
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
 	if (bit < 0)
 		return;
 

diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
@@ -353,8 +353,8 @@ static inline const char *kretprobed(const char *name)
 }
 #endif /* CONFIG_KRETPROBES */
 
-static void
-seq_print_sym(struct trace_seq *s, unsigned long address, bool offset)
+void
+trace_seq_print_sym(struct trace_seq *s, unsigned long address, bool offset)
 {
 #ifdef CONFIG_KALLSYMS
 	char str[KSYM_SYMBOL_LEN];
@@ -420,7 +420,7 @@ seq_print_ip_sym(struct trace_seq *s, unsigned long ip, unsigned long sym_flags)
 		goto out;
 	}
 
-	seq_print_sym(s, ip, sym_flags & TRACE_ITER_SYM_OFFSET);
+	trace_seq_print_sym(s, ip, sym_flags & TRACE_ITER_SYM_OFFSET);
 
 	if (sym_flags & TRACE_ITER_SYM_ADDR)
 		trace_seq_printf(s, " <" IP_FMT ">", ip);

diff --git a/kernel/trace/trace_output.h b/kernel/trace/trace_output.h
@@ -16,6 +16,7 @@ extern int
 seq_print_ip_sym(struct trace_seq *s, unsigned long ip,
 		unsigned long sym_flags);
 
+extern void trace_seq_print_sym(struct trace_seq *s, unsigned long address, bool offset);
 extern int trace_print_context(struct trace_iterator *iter);
 extern int trace_print_lat_context(struct trace_iterator *iter);