x86,64: Simplify save_regs()

The save_regs function that saves the regs on low level
irq entry is complicated because of the fact it changes
its stack in the middle and also because it manipulates
data allocated in the caller frame and accesses there
are directly calculated from callee rsp value with the
return address in the middle of the way.

This complicates the static stack offsets calculation and
require more dynamic ones. It also needs a save/restore
of the function's return address.

To simplify and optimize this, turn save_regs() into a
macro.

Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jan Beulich <JBeulich@novell.com>

arch/x86/kernel/entry_64.S

@@ -297,27 +297,22 @@ ENDPROC(native_usergs_sysret64)
 	.endm
 
 /* save partial stack frame */
-	.pushsection .kprobes.text, "ax"
-ENTRY(save_args)
-	XCPT_FRAME
+	.macro SAVE_ARGS_IRQ
 	cld
-	/*
-	 * start from rbp in pt_regs and jump over
-	 * return address.
-	 */
-	movq_cfi rdi, RDI+8-RBP
-	movq_cfi rsi, RSI+8-RBP
-	movq_cfi rdx, RDX+8-RBP
-	movq_cfi rcx, RCX+8-RBP
-	movq_cfi rax, RAX+8-RBP
-	movq_cfi  r8,  R8+8-RBP
-	movq_cfi  r9,  R9+8-RBP
-	movq_cfi r10, R10+8-RBP
-	movq_cfi r11, R11+8-RBP
-
-	leaq -RBP+8(%rsp),%rdi	/* arg1 for handler */
-	movq_cfi rbp, 8		/* push %rbp */
-	leaq 8(%rsp), %rbp		/* mov %rsp, %ebp */
+	/* start from rbp in pt_regs and jump over */
+	movq_cfi rdi, RDI-RBP
+	movq_cfi rsi, RSI-RBP
+	movq_cfi rdx, RDX-RBP
+	movq_cfi rcx, RCX-RBP
+	movq_cfi rax, RAX-RBP
+	movq_cfi  r8,  R8-RBP
+	movq_cfi  r9,  R9-RBP
+	movq_cfi r10, R10-RBP
+	movq_cfi r11, R11-RBP
+
+	leaq -RBP(%rsp),%rdi	/* arg1 for handler */
+	movq_cfi rbp, 0		/* push %rbp */
+	movq %rsp, %rbp
 	testl $3, CS(%rdi)
 	je 1f
 	SWAPGS
@@ -329,19 +324,14 @@ ENTRY(save_args)
 	 */
 1:	incl PER_CPU_VAR(irq_count)
 	jne 2f
-	popq_cfi %rax			/* move return address... */
 	mov PER_CPU_VAR(irq_stack_ptr),%rsp
 	EMPTY_FRAME 0
 	pushq_cfi %rbp			/* backlink for unwinder */
-	pushq_cfi %rax			/* ... to the new stack */
 	/*
 	 * We entered an interrupt context - irqs are off:
 	 */
 2:	TRACE_IRQS_OFF
-	ret
-	CFI_ENDPROC
-END(save_args)
-	.popsection
+	.endm
 
 ENTRY(save_rest)
 	PARTIAL_FRAME 1 REST_SKIP+8
@@ -791,7 +781,7 @@ END(interrupt)
 	/* reserve pt_regs for scratch regs and rbp */
 	subq $ORIG_RAX-RBP, %rsp
 	CFI_ADJUST_CFA_OFFSET ORIG_RAX-RBP
-	call save_args
+	SAVE_ARGS_IRQ
 	PARTIAL_FRAME 0
 	call \func
 	.endm