From 9520b1a1b5f7a34888e14de3cf2ee0ee5344e9fe Mon Sep 17 00:00:00 2001
From: Nicolas Pitre <nicolas.pitre@linaro.org>
Date: Thu, 24 Aug 2017 15:54:47 -0400
Subject: [PATCH] ARM: head-common.S: speed up startup code

Let's use optimized routines such as memcpy to copy .data and memzero
to clear .bss in the startup code instead of doing it one word at a
time. Those routines don't use any global data so they're safe to use
even if .data and .bss segments are not initialized.

In the .data copy case a temporary stack is installed in the .bss area
as the actual kernel stack is located within the copied data area. The
XIP kernel linker script ensures a 8 byte alignment for that purpose.

Finally, make the .data copy and related pointers surrounded by
CONFIG_XIP_KERNEL to make it obvious what it is all about. This will
allow for further cleanups in the non-XIP linker script.

Signed-off-by: Nicolas Pitre <nico@linaro.org>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Tested-by: Chris Brandt <Chris.Brandt@renesas.com>
---
 arch/arm/kernel/head-common.S     | 72 ++++++++++++++++++-------------
 arch/arm/kernel/vmlinux-xip.lds.S |  2 +-
 2 files changed, 43 insertions(+), 31 deletions(-)

diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 8733012d231f..bf9c4e38eced 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -79,47 +79,59 @@ ENDPROC(__vet_atags)
  */
 	__INIT
 __mmap_switched:
-	adr	r3, __mmap_switched_data
 
-	ldmia	r3!, {r4, r5, r6, r7}
-	cmp	r4, r5				@ Copy data segment if needed
-1:	cmpne	r5, r6
-	ldrne	fp, [r4], #4
-	strne	fp, [r5], #4
-	bne	1b
+	mov	r7, r1
+	mov	r8, r2
+	mov	r10, r0
 
-	mov	fp, #0				@ Clear BSS (and zero fp)
-1:	cmp	r6, r7
-	strcc	fp, [r6],#4
-	bcc	1b
+	adr	r4, __mmap_switched_data
+	mov	fp, #0
 
- ARM(	ldmia	r3, {r4, r5, r6, r7, sp})
- THUMB(	ldmia	r3, {r4, r5, r6, r7}	)
- THUMB(	ldr	sp, [r3, #16]		)
-	str	r9, [r4]			@ Save processor ID
-	str	r1, [r5]			@ Save machine type
-	str	r2, [r6]			@ Save atags pointer
-	cmp	r7, #0
-	strne	r0, [r7]			@ Save control register values
+#ifdef CONFIG_XIP_KERNEL
+   ARM(	ldmia	r4!, {r0, r1, r2, sp} )
+ THUMB(	ldmia	r4!, {r0, r1, r2, r3} )
+ THUMB(	mov	sp, r3 )
+	sub	r2, r2, r1
+	bl	memcpy				@ copy .data to RAM
+#endif
+
+   ARM(	ldmia	r4!, {r0, r1, sp} )
+ THUMB(	ldmia	r4!, {r0, r1, r3} )
+ THUMB(	mov	sp, r3 )
+	sub	r1, r1, r0
+	bl	__memzero			@ clear .bss
+
+	ldmia	r4, {r0, r1, r2, r3}
+	str	r9, [r0]			@ Save processor ID
+	str	r7, [r1]			@ Save machine type
+	str	r8, [r2]			@ Save atags pointer
+	cmp	r3, #0
+	strne	r10, [r3]			@ Save control register values
 	b	start_kernel
 ENDPROC(__mmap_switched)
 
 	.align	2
 	.type	__mmap_switched_data, %object
 __mmap_switched_data:
-	.long	__data_loc			@ r4
-	.long	_sdata				@ r5
-	.long	__bss_start			@ r6
-	.long	_end				@ r7
-	.long	processor_id			@ r4
-	.long	__machine_arch_type		@ r5
-	.long	__atags_pointer			@ r6
-#ifdef CONFIG_CPU_CP15
-	.long	cr_alignment			@ r7
-#else
-	.long	0				@ r7
+#ifdef CONFIG_XIP_KERNEL
+	.long	_sdata				@ r0
+	.long	__data_loc			@ r1
+	.long	_edata_loc			@ r2
+	.long	__bss_stop			@ sp (temporary stack in .bss)
 #endif
+
+	.long	__bss_start			@ r0
+	.long	__bss_stop			@ r1
 	.long	init_thread_union + THREAD_START_SP @ sp
+
+	.long	processor_id			@ r0
+	.long	__machine_arch_type		@ r1
+	.long	__atags_pointer			@ r2
+#ifdef CONFIG_CPU_CP15
+	.long	cr_alignment			@ r3
+#else
+	.long	0				@ r3
+#endif
 	.size	__mmap_switched_data, . - __mmap_switched_data
 
 /*
diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S
index 8265b116218d..1598caada3bb 100644
--- a/arch/arm/kernel/vmlinux-xip.lds.S
+++ b/arch/arm/kernel/vmlinux-xip.lds.S
@@ -301,7 +301,7 @@ SECTIONS
 	}
 #endif
 
-	BSS_SECTION(0, 0, 0)
+	BSS_SECTION(0, 0, 8)
 	_end = .;
 
 	STABS_DEBUG