[PATCH v2 4/4] ARM: decompressor: switch to by-VA cache maintenance for v7 cores

[Ard Biesheuvel <ardb@kernel.org>]

Update the v7 cache_clean_flush routine to take into account the
memory range passed in r0/r1, and perform cache maintenance by
virtual address on this range instead of set/way maintenance, which
is inappropriate for the purpose of maintaining the cached state of
memory contents.

Since this removes any use of the stack in the implementation of
cache_clean_flush(), we can also drop some code that manages the
value of the stack pointer before calling it.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/arm/boot/compressed/head.S | 83 +++++++-------------
 1 file changed, 30 insertions(+), 53 deletions(-)

diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 5060a623e0d7..90de5404f402 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -524,11 +524,6 @@ dtb_check_done:
 
 		ldr	r1, [sp], #4		@ end of target region
 		ldr	r0, [sp], #4		@ start of target region
-#ifndef CONFIG_ZBOOT_ROM
-		/* cache_clean_flush may use the stack, so relocate it */
-		add	sp, sp, r6
-#endif
-
 		bl	cache_clean_flush
 
 		badr	r0, restart
@@ -685,6 +680,24 @@ params:		ldr	r0, =0x10000100		@ params_phys for RPC
 		.align
 #endif
 
+/*
+ * dcache_line_size - get the minimum D-cache line size from the CTR register
+ * on ARMv7.
+ */
+	.macro	dcache_line_size, reg, tmp
+#ifdef CONFIG_CPU_V7M
+	movw	\tmp, #:lower16:BASEADDR_V7M_SCB + V7M_SCB_CTR
+	movt	\tmp, #:upper16:BASEADDR_V7M_SCB + V7M_SCB_CTR
+	ldr     \tmp, [\tmp]
+#else
+	mrc	p15, 0, \tmp, c0, c0, 1		@ read ctr
+#endif
+	lsr	\tmp, \tmp, #16
+	and	\tmp, \tmp, #0xf		@ cache line size encoding
+	mov	\reg, #4			@ bytes per word
+	mov	\reg, \reg, lsl \tmp		@ actual cache line size
+	.endm
+
 /*
  * Turn on the cache.  We need to setup some page tables so that we
  * can have both the I and D caches on.
@@ -1177,8 +1190,6 @@ __armv7_mmu_cache_off:
 		bic	r0, r0, #0x000c
 #endif
 		mcr	p15, 0, r0, c1, c0	@ turn MMU and cache off
-		mov	r12, lr
-		bl	__armv7_mmu_cache_flush
 		mov	r0, #0
 #ifdef CONFIG_MMU
 		mcr	p15, 0, r0, c8, c7, 0	@ invalidate whole TLB
@@ -1186,7 +1197,7 @@ __armv7_mmu_cache_off:
 		mcr	p15, 0, r0, c7, c5, 6	@ invalidate BTC
 		mcr	p15, 0, r0, c7, c10, 4	@ DSB
 		mcr	p15, 0, r0, c7, c5, 4	@ ISB
-		mov	pc, r12
+		mov	pc, lr
 
 /*
  * Clean and flush the cache to maintain consistency.
@@ -1202,6 +1213,7 @@ __armv7_mmu_cache_off:
 		.align	5
 cache_clean_flush:
 		mov	r3, #16
+		mov	r11, r1
 		b	call_cache_fn
 
 __armv4_mpu_cache_flush:
@@ -1252,51 +1264,16 @@ __armv7_mmu_cache_flush:
 		mcr	p15, 0, r10, c7, c14, 0	@ clean+invalidate D
 		b	iflush
 hierarchical:
-		mcr	p15, 0, r10, c7, c10, 5	@ DMB
-		stmfd	sp!, {r0-r7, r9-r11}
-		mrc	p15, 1, r0, c0, c0, 1	@ read clidr
-		ands	r3, r0, #0x7000000	@ extract loc from clidr
-		mov	r3, r3, lsr #23		@ left align loc bit field
-		beq	finished		@ if loc is 0, then no need to clean
-		mov	r10, #0			@ start clean at cache level 0
-loop1:
-		add	r2, r10, r10, lsr #1	@ work out 3x current cache level
-		mov	r1, r0, lsr r2		@ extract cache type bits from clidr
-		and	r1, r1, #7		@ mask of the bits for current cache only
-		cmp	r1, #2			@ see what cache we have at this level
-		blt	skip			@ skip if no cache, or just i-cache
-		mcr	p15, 2, r10, c0, c0, 0	@ select current cache level in cssr
-		mcr	p15, 0, r10, c7, c5, 4	@ isb to sych the new cssr&csidr
-		mrc	p15, 1, r1, c0, c0, 0	@ read the new csidr
-		and	r2, r1, #7		@ extract the length of the cache lines
-		add	r2, r2, #4		@ add 4 (line length offset)
-		ldr	r4, =0x3ff
-		ands	r4, r4, r1, lsr #3	@ find maximum number on the way size
-		clz	r5, r4			@ find bit position of way size increment
-		ldr	r7, =0x7fff
-		ands	r7, r7, r1, lsr #13	@ extract max number of the index size
-loop2:
-		mov	r9, r4			@ create working copy of max way size
-loop3:
- ARM(		orr	r11, r10, r9, lsl r5	) @ factor way and cache number into r11
- ARM(		orr	r11, r11, r7, lsl r2	) @ factor index number into r11
- THUMB(		lsl	r6, r9, r5		)
- THUMB(		orr	r11, r10, r6		) @ factor way and cache number into r11
- THUMB(		lsl	r6, r7, r2		)
- THUMB(		orr	r11, r11, r6		) @ factor index number into r11
-		mcr	p15, 0, r11, c7, c14, 2	@ clean & invalidate by set/way
-		subs	r9, r9, #1		@ decrement the way
-		bge	loop3
-		subs	r7, r7, #1		@ decrement the index
-		bge	loop2
-skip:
-		add	r10, r10, #2		@ increment cache number
-		cmp	r3, r10
-		bgt	loop1
-finished:
-		ldmfd	sp!, {r0-r7, r9-r11}
-		mov	r10, #0			@ switch back to cache level 0
-		mcr	p15, 2, r10, c0, c0, 0	@ select current cache level in cssr
+		dcache_line_size r1, r2		@ r1 := dcache min line size
+		sub	r2, r1, #1		@ r2 := line size mask
+		bic	r0, r0, r2		@ round down start to line size
+		sub	r11, r11, #1		@ end address is exclusive
+		bic	r11, r11, r2		@ round down end to line size
+0:		cmp	r0, r11			@ finished?
+		bgt	iflush
+		mcr	p15, 0, r0, c7, c14, 1	@ Dcache clean/invalidate by VA
+		add	r0, r0, r1
+		b	0b
 iflush:
 		mcr	p15, 0, r10, c7, c10, 4	@ DSB
 		mcr	p15, 0, r10, c7, c5, 0	@ invalidate I+BTB
-- 
2.17.1