[PATCH 4/5 v3] ftrace/x86_32: Clean up ftrace_regs_caller

[Steven Rostedt]

[ I'll wait to post the full v3 series in case there is more comments ]

From: "Steven Rostedt (VMware)" <rostedt@xxxxxxxxxxx>

When ftrace_regs_caller was created, it was designed to preserve flags as
much as possible as it needed to act just like a breakpoint triggered on the
same location. But the design is over complicated as it treated all
operations as modifying flags. But push, mov and lea do not modify flags.
This means the code can become more simplified by allowing flags to be
stored further down.

Making ftrace_regs_caller simpler will also be useful in implementing fentry
logic.

Link: http://lkml.kernel.org/r/20170316135328.36123c3e@xxxxxxxxxxxxxxxxxx
[ simpler logic to save flags ]
Suggested-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Reviewed-by: Masami Hiramatsu <mhiramat@xxxxxxxxxx>
Signed-off-by: Steven Rostedt (VMware) <rostedt@xxxxxxxxxxx>
---
 arch/x86/kernel/ftrace_32.S | 42 ++++++++++++++++++++++--------------------
 1 file changed, 22 insertions(+), 20 deletions(-)

diff --git a/arch/x86/kernel/ftrace_32.S b/arch/x86/kernel/ftrace_32.S
index 6f855df..691897e 100644
--- a/arch/x86/kernel/ftrace_32.S
+++ b/arch/x86/kernel/ftrace_32.S
@@ -55,23 +55,27 @@ WEAK(ftrace_stub)
 END(ftrace_caller)
 
 ENTRY(ftrace_regs_caller)
-	pushf	/* push flags before compare (in cs location) */
-
 	/*
 	 * i386 does not save SS and ESP when coming from kernel.
 	 * Instead, to get sp, &regs->sp is used (see ptrace.h).
 	 * Unfortunately, that means eflags must be at the same location
 	 * as the current return ip is. We move the return ip into the
-	 * ip location, and move flags into the return ip location.
-	 */
-	pushl	4(%esp)				/* save return ip into ip slot */
-
+	 * regs->ip location, and move flags into the return ip location.
+	 */
+	pushl	$__KERNEL_CS
+	pushl	4(%esp)				/* Save the return ip */
 	pushl	$0				/* Load 0 into orig_ax */
 	pushl	%gs
 	pushl	%fs
 	pushl	%es
 	pushl	%ds
 	pushl	%eax
+
+	/* Get flags and place them into the return ip slot */
+	pushf
+	popl	%eax
+	movl	%eax, 8*4(%esp)
+
 	pushl	%ebp
 	pushl	%edi
 	pushl	%esi
@@ -79,11 +83,6 @@ ENTRY(ftrace_regs_caller)
 	pushl	%ecx
 	pushl	%ebx
 
-	movl	13*4(%esp), %eax		/* Get the saved flags */
-	movl	%eax, 14*4(%esp)		/* Move saved flags into regs->flags location */
-						/* clobbering return ip */
-	movl	$__KERNEL_CS, 13*4(%esp)
-
 	movl	12*4(%esp), %eax		/* Load ip (1st parameter) */
 	subl	$MCOUNT_INSN_SIZE, %eax		/* Adjust ip */
 	movl	0x4(%ebp), %edx			/* Load parent ip (2nd parameter) */
@@ -94,10 +93,14 @@ GLOBAL(ftrace_regs_call)
 	call	ftrace_stub
 
 	addl	$4, %esp			/* Skip pt_regs */
-	movl	14*4(%esp), %eax		/* Move flags back into cs */
-	movl	%eax, 13*4(%esp)		/* Needed to keep addl	from modifying flags */
-	movl	12*4(%esp), %eax		/* Get return ip from regs->ip */
-	movl	%eax, 14*4(%esp)		/* Put return ip back for ret */
+
+	/* Since we don't care about cs, move flags there to simplify return */
+	movl	14*4(%esp), %eax
+	movl	%eax, 13*4(%esp)
+
+	/* Move return ip back to its original location */
+	movl	12*4(%esp), %eax
+	movl	%eax, 14*4(%esp)
 
 	popl	%ebx
 	popl	%ecx
@@ -110,12 +113,11 @@ GLOBAL(ftrace_regs_call)
 	popl	%es
 	popl	%fs
 	popl	%gs
-	addl	$8, %esp			/* Skip orig_ax and ip */
-	popf					/* Pop flags at end (no addl to corrupt flags) */
-	jmp	.Lftrace_ret
+	addl	$8, %esp			/* Skip orig_ax and old ip */
 
-	popf
-	jmp	ftrace_stub
+	popf					/* flags is in the cs location */
+
+	jmp	.Lftrace_ret
 #else /* ! CONFIG_DYNAMIC_FTRACE */
 
 ENTRY(mcount)
-- 
2.9.3