ftrace/x86: Add dynamic allocated trampoline for ftrace_ops

The current method of handling multiple function callbacks is to register
a list function callback that calls all the other callbacks based on
their hash tables and compare it to the function that the callback was
called on. But this is very inefficient.

For example, if you are tracing all functions in the kernel and then
add a kprobe to a function such that the kprobe uses ftrace, the
mcount trampoline will switch from calling the function trace callback
to calling the list callback that will iterate over all registered
ftrace_ops (in this case, the function tracer and the kprobes callback).
That means for every function being traced it checks the hash of the
ftrace_ops for function tracing and kprobes, even though the kprobes
is only set at a single function. The kprobes ftrace_ops is checked
for every function being traced!

Instead of calling the list function for functions that are only being
traced by a single callback, we can call a dynamically allocated
trampoline that calls the callback directly. The function graph tracer
already uses a direct call trampoline when it is being traced by itself
but it is not dynamically allocated. It's trampoline is static in the
kernel core. The infrastructure that called the function graph trampoline
can also be used to call a dynamically allocated one.

For now, only ftrace_ops that are not dynamically allocated can have
a trampoline. That is, users such as function tracer or stack tracer.
kprobes and perf allocate their ftrace_ops, and until there's a safe
way to free the trampoline, it can not be used. The dynamically allocated
ftrace_ops may, although, use the trampoline if the kernel is not
compiled with CONFIG_PREEMPT. But that will come later.

Tested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Tested-by: Jiri Kosina <jkosina@suse.cz>
Signed-off-by: Steven Rostedt <rostedt@goodmis.org>

1 files changed, 21 insertions, 4 deletions

diff --git a/arch/x86/kernel/mcount_64.S b/arch/x86/kernel/mcount_64.S
index c73aecf10d34..42f0cdd20baf 100644
--- a/arch/x86/kernel/mcount_64.S
+++ b/arch/x86/kernel/mcount_64.S
@@ -28,9 +28,11 @@ ENTRY(function_hook)
 END(function_hook)
 
 /* skip is set if stack has been adjusted */
-.macro ftrace_caller_setup skip=0
+.macro ftrace_caller_setup trace_label skip=0
 	MCOUNT_SAVE_FRAME \skip
 
+	/* Save this location */
+GLOBAL(\trace_label)
 	/* Load the ftrace_ops into the 3rd parameter */
 	movq function_trace_op(%rip), %rdx
 
@@ -46,7 +48,7 @@ END(function_hook)
 .endm
 
 ENTRY(ftrace_caller)
-	ftrace_caller_setup
+	ftrace_caller_setup ftrace_caller_op_ptr
 	/* regs go into 4th parameter (but make it NULL) */
 	movq $0, %rcx
 
@@ -54,7 +56,14 @@ GLOBAL(ftrace_call)
 	call ftrace_stub
 
 	MCOUNT_RESTORE_FRAME
-ftrace_return:
+
+	/*
+	 * The copied trampoline must call ftrace_return as it
+	 * still may need to call the function graph tracer.
+	 */
+GLOBAL(ftrace_caller_end)
+
+GLOBAL(ftrace_return)
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 GLOBAL(ftrace_graph_call)
@@ -70,7 +79,7 @@ ENTRY(ftrace_regs_caller)
 	pushfq
 
 	/* skip=8 to skip flags saved in SS */
-	ftrace_caller_setup 8
+	ftrace_caller_setup ftrace_regs_caller_op_ptr 8
 
 	/* Save the rest of pt_regs */
 	movq %r15, R15(%rsp)
@@ -122,6 +131,14 @@ GLOBAL(ftrace_regs_call)
 	/* Restore flags */
 	popfq
 
+	/*
+	 * As this jmp to ftrace_return can be a short jump
+	 * it must not be copied into the trampoline.
+	 * The trampoline will add the code to jump
+	 * to the return.
+	 */
+GLOBAL(ftrace_regs_caller_end)
+
 	jmp ftrace_return
 
 	popfq