ftrace/x86: Add register_ftrace_direct() for custom trampolines

Enable x86 to allow for register_ftrace_direct(), where a custom trampoline
may be called directly from an ftrace mcount/fentry location.
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>

arch/x86/Kconfig

@@ -158,6 +158,7 @@ config X86
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
+	select HAVE_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
 	select HAVE_EBPF_JIT
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_EISA

arch/x86/include/asm/ftrace.h

@@ -28,6 +28,19 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
 	return addr;
 }
 
+/*
+ * When a ftrace registered caller is tracing a function that is
+ * also set by a register_ftrace_direct() call, it needs to be
+ * differentiated in the ftrace_caller trampoline. To do this, we
+ * place the direct caller in the ORIG_AX part of pt_regs. This
+ * tells the ftrace_caller that there's a direct caller.
+ */
+static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs, unsigned long addr)
+{
+	/* Emulate a call */
+	regs->orig_ax = addr;
+}
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 struct dyn_arch_ftrace {

arch/x86/kernel/ftrace.c

@@ -1042,6 +1042,18 @@ void prepare_ftrace_return(unsigned long self_addr, unsigned long *parent,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
+	/*
+	 * If the return location is actually pointing directly to
+	 * the start of a direct trampoline (if we trace the trampoline
+	 * it will still be offset by MCOUNT_INSN_SIZE), then the
+	 * return address is actually off by one word, and we
+	 * need to adjust for that.
+	 */
+	if (ftrace_find_direct_func(self_addr + MCOUNT_INSN_SIZE)) {
+		self_addr = *parent;
+		parent++;
+	}
+
 	/*
 	 * Protect against fault, even if it shouldn't
 	 * happen. This tool is too much intrusive to

arch/x86/kernel/ftrace_64.S

@@ -88,6 +88,7 @@ EXPORT_SYMBOL(__fentry__)
 	movq %rdi, RDI(%rsp)
 	movq %r8, R8(%rsp)
 	movq %r9, R9(%rsp)
+	movq $0, ORIG_RAX(%rsp)
 	/*
 	 * Save the original RBP. Even though the mcount ABI does not
 	 * require this, it helps out callers.
@@ -114,7 +115,11 @@ EXPORT_SYMBOL(__fentry__)
 	subq $MCOUNT_INSN_SIZE, %rdi
 	.endm
 
-.macro restore_mcount_regs
+.macro restore_mcount_regs save=0
+
+	/* ftrace_regs_caller or frame pointers require this */
+	movq RBP(%rsp), %rbp
+
 	movq R9(%rsp), %r9
 	movq R8(%rsp), %r8
 	movq RDI(%rsp), %rdi
@@ -123,10 +128,7 @@ EXPORT_SYMBOL(__fentry__)
 	movq RCX(%rsp), %rcx
 	movq RAX(%rsp), %rax
 
-	/* ftrace_regs_caller can modify %rbp */
-	movq RBP(%rsp), %rbp
-
-	addq $MCOUNT_REG_SIZE, %rsp
+	addq $MCOUNT_REG_SIZE-\save, %rsp
 
 	.endm
 
@@ -228,10 +230,28 @@ GLOBAL(ftrace_regs_call)
 	movq R10(%rsp), %r10
 	movq RBX(%rsp), %rbx
 
-	restore_mcount_regs
+	movq ORIG_RAX(%rsp), %rax
+	movq %rax, MCOUNT_REG_SIZE-8(%rsp)
+
+	/* If ORIG_RAX is anything but zero, make this a call to that */
+	movq ORIG_RAX(%rsp), %rax
+	cmpq	$0, %rax
+	je	1f
+
+	/* Swap the flags with orig_rax */
+	movq MCOUNT_REG_SIZE(%rsp), %rdi
+	movq %rdi, MCOUNT_REG_SIZE-8(%rsp)
+	movq %rax, MCOUNT_REG_SIZE(%rsp)
+
+	restore_mcount_regs 8
+
+	jmp	2f
+
+1:	restore_mcount_regs
+
 
 	/* Restore flags */
-	popfq
+2:	popfq
 
 	/*
 	 * As this jmp to ftrace_epilogue can be a short jump

include/linux/ftrace.h

@@ -272,6 +272,12 @@ static inline struct ftrace_direct_func *ftrace_find_direct_func(unsigned long a
  * via ftrace (because there's other callbacks besides the
  * direct call), can inform the architecture's trampoline that this
  * routine has a direct caller, and what the caller is.
+ *
+ * For example, in x86, it returns the direct caller
+ * callback function via the regs->orig_ax parameter.
+ * Then in the ftrace trampoline, if this is set, it makes
+ * the return from the trampoline jump to the direct caller
+ * instead of going back to the function it just traced.
  */
 static inline void arch_ftrace_set_direct_caller(struct pt_regs *regs,
 						 unsigned long addr) { }