[RFC 04/17] x86/asm/64: Simplify reg restore code in the standard IRET paths

[Andy Lutomirski]

The old code restored all the registers with movq instead of pop.
In theory, this was done because some CPUs have higher movq
throughput, but any gain there would be tiny and is almost certainly
outweighed by the higher text size.

This saves 96 bytes of text.

Signed-off-by: Andy Lutomirski <luto@xxxxxxxxxx>
---
 arch/x86/entry/calling.h  |  9 +++++++++
 arch/x86/entry/entry_64.S | 28 ++++++++++++++++++++++------
 2 files changed, 31 insertions(+), 6 deletions(-)

diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 05ed3d393da7..0a2c73fe2cfc 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -147,6 +147,15 @@ For 32-bit we have the following conventions - kernel is built with
 	movq 5*8+\offset(%rsp), %rbx
 	.endm
 
+	.macro POP_EXTRA_REGS
+	popq %r15
+	popq %r14
+	popq %r13
+	popq %r12
+	popq %rbp
+	popq %rbx
+	.endm
+
 	.macro RESTORE_C_REGS_HELPER rstor_rax=1, rstor_rcx=1, rstor_r11=1, rstor_r8910=1, rstor_rdx=1
 	.if \rstor_r11
 	movq 6*8(%rsp), %r11
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 2cd01ed9cd59..7f1a83b17b4a 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -521,9 +521,17 @@ GLOBAL(retint_user)
 
 GLOBAL(swapgs_restore_regs_and_return_to_usermode)
 	SWAPGS
-	RESTORE_EXTRA_REGS
-	RESTORE_C_REGS
-	REMOVE_PT_GPREGS_FROM_STACK 8
+	POP_EXTRA_REGS
+	popq	%r11
+	popq	%r10
+	popq	%r9
+	popq	%r8
+	popq	%rax
+	popq	%rcx
+	popq	%rdx
+	popq	%rsi
+	popq	%rdi
+	addq	$8, %rsp
 	INTERRUPT_RETURN
 
 
@@ -546,9 +554,17 @@ retint_kernel:
 	TRACE_IRQS_IRETQ
 
 GLOBAL(restore_regs_and_return_to_kernel)
-	RESTORE_EXTRA_REGS
-	RESTORE_C_REGS
-	REMOVE_PT_GPREGS_FROM_STACK 8
+	POP_EXTRA_REGS
+	popq	%r11
+	popq	%r10
+	popq	%r9
+	popq	%r8
+	popq	%rax
+	popq	%rcx
+	popq	%rdx
+	popq	%rsi
+	popq	%rdi
+	addq	$8, %rsp
 	INTERRUPT_RETURN
 
 ENTRY(native_iret)
-- 
2.13.5