[RFC PATCH v2 3/5] x86/entry/64: move switch_to_thread_stack to interrupt helper function

[Dominik Brodowski]

We can also move the SWAPGS and the switch_to_thread_stack to the
interrupt helper function. As we do not want call depths of two,
convert switch_to_thread_stack to a macro.

However, switch_to_thread_stack has another user in entry_64_compat.S,
which currently expects it to be a function. To keep the code changes
in this patch minimal, create a wrapper function.

The switch to a macro means that there is some binary code duplication
if CONFIG_IA32_EMULATION is enabled. Therefore, the size reduction
differs whether CONFIG_IA32_EMULATION is enabled or not:

CONFIG_IA32_EMULATION=y (-0.13k):
   text	   data	    bss	    dec	    hex	filename
  17158	      0	      0	  17158	   4306	entry_64.o-orig
  17028	      0	      0	  17028	   4284	entry_64.o

CONFIG_IA32_EMULATION=n (-0.27k):
   text	   data	    bss	    dec	    hex	filename
  17158	      0	      0	  17158	   4306	entry_64.o-orig
  16883	      0	      0	  16883	   41f3	entry_64.o

Signed-off-by: Dominik Brodowski <linux@xxxxxxxxxxxxxxxxxxxx>
---
 arch/x86/entry/entry_64.S | 64 +++++++++++++++++++++++++++--------------------
 1 file changed, 37 insertions(+), 27 deletions(-)

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 93a9bea6b969..266bfcba3bb5 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -538,6 +538,31 @@ END(irq_entries_start)
 	decl	PER_CPU_VAR(irq_count)
 .endm
 
+/*
+ * Switch to the thread stack.  This is called with the IRET frame and
+ * orig_ax on the stack.  (That is, RDI..R12 are not on the stack and
+ * space has not been allocated for them.)
+ */
+.macro DO_SWITCH_TO_THREAD_STACK
+	pushq	%rdi
+	/* Need to switch before accessing the thread stack. */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+	movq	%rsp, %rdi
+	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+	UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
+
+	pushq	7*8(%rdi)		/* regs->ss */
+	pushq	6*8(%rdi)		/* regs->rsp */
+	pushq	5*8(%rdi)		/* regs->eflags */
+	pushq	4*8(%rdi)		/* regs->cs */
+	pushq	3*8(%rdi)		/* regs->ip */
+	pushq	2*8(%rdi)		/* regs->orig_ax */
+	pushq	8(%rdi)			/* return address */
+	UNWIND_HINT_FUNC
+
+	movq	(%rdi), %rdi
+.endm
+
 /*
  * Interrupt entry/exit.
  *
@@ -545,10 +570,17 @@ END(irq_entries_start)
  *
  * Entry runs with interrupts off.
  */
+/* 8(%rsp): ~(interrupt number) */
 ENTRY(interrupt_helper)
 	UNWIND_HINT_FUNC
 	cld
 
+	testb	$3, CS-ORIG_RAX+8(%rsp)
+	jz	1f
+	SWAPGS
+	DO_SWITCH_TO_THREAD_STACK
+1:
+
 	PUSH_AND_CLEAR_REGS save_ret=1
 	ENCODE_FRAME_POINTER 8
 
@@ -581,12 +613,6 @@ END(interrupt_helper)
 	.macro interrupt func
 	cld
 
-	testb	$3, CS-ORIG_RAX(%rsp)
-	jz	1f
-	SWAPGS
-	call	switch_to_thread_stack
-1:
-
 	call	interrupt_helper
 
 	UNWIND_HINT_REGS indirect=1
@@ -860,33 +886,17 @@ apicinterrupt IRQ_WORK_VECTOR			irq_work_interrupt		smp_irq_work_interrupt
  */
 #define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
 
-/*
- * Switch to the thread stack.  This is called with the IRET frame and
- * orig_ax on the stack.  (That is, RDI..R12 are not on the stack and
- * space has not been allocated for them.)
- */
+#if defined(CONFIG_IA32_EMULATION)
+/* entry_64_compat.S::entry_INT80_compat expects this to be an ASM function */
 ENTRY(switch_to_thread_stack)
 	UNWIND_HINT_FUNC
+	cld
 
-	pushq	%rdi
-	/* Need to switch before accessing the thread stack. */
-	SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
-	movq	%rsp, %rdi
-	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
-	UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
-
-	pushq	7*8(%rdi)		/* regs->ss */
-	pushq	6*8(%rdi)		/* regs->rsp */
-	pushq	5*8(%rdi)		/* regs->eflags */
-	pushq	4*8(%rdi)		/* regs->cs */
-	pushq	3*8(%rdi)		/* regs->ip */
-	pushq	2*8(%rdi)		/* regs->orig_ax */
-	pushq	8(%rdi)			/* return address */
-	UNWIND_HINT_FUNC
+	DO_SWITCH_TO_THREAD_STACK
 
-	movq	(%rdi), %rdi
 	ret
 END(switch_to_thread_stack)
+#endif
 
 .macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
 ENTRY(\sym)
-- 
2.16.1