From 9a1af5f2206bd303ed201c6895c42ac3ac120a20 Mon Sep 17 00:00:00 2001
From: Vladimir Murzin <vladimir.murzin@arm.com>
Date: Tue, 30 Aug 2016 17:30:02 +0100
Subject: [PATCH] ARM: 8606/1: V7M: introduce cache operations

This commit implements the cache operation for V7M.

It is based on V7 counterpart and differs as follows:
- cache operations are memory mapped
- only Thumb instruction set is supported
- we don't handle user access faults

Signed-off-by: Vladimir Murzin <vladimir.murzin@arm.com>
Tested-by: Andras Szemzo <sza@esh.hu>
Tested-by: Joachim Eastwood <manabian@gmail.com>
Tested-by: Alexandre TORGUE <alexandre.torgue@st.com>
Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk>
---
 arch/arm/mm/cache-v7m.S   | 453 ++++++++++++++++++++++++++++++++++++++
 arch/arm/mm/proc-macros.S |  16 ++
 2 files changed, 469 insertions(+)
 create mode 100644 arch/arm/mm/cache-v7m.S

diff --git a/arch/arm/mm/cache-v7m.S b/arch/arm/mm/cache-v7m.S
new file mode 100644
index 000000000000..816a7e44e6f1
--- /dev/null
+++ b/arch/arm/mm/cache-v7m.S
@@ -0,0 +1,453 @@
+/*
+ *  linux/arch/arm/mm/cache-v7m.S
+ *
+ *  Based on linux/arch/arm/mm/cache-v7.S
+ *
+ *  Copyright (C) 2001 Deep Blue Solutions Ltd.
+ *  Copyright (C) 2005 ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ *  This is the "shell" of the ARMv7M processor support.
+ */
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <asm/assembler.h>
+#include <asm/errno.h>
+#include <asm/unwind.h>
+#include <asm/v7m.h>
+
+#include "proc-macros.S"
+
+/* Generic V7M read/write macros for memory mapped cache operations */
+.macro v7m_cache_read, rt, reg
+	movw	\rt, #:lower16:BASEADDR_V7M_SCB + \reg
+	movt	\rt, #:upper16:BASEADDR_V7M_SCB + \reg
+	ldr     \rt, [\rt]
+.endm
+
+.macro v7m_cacheop, rt, tmp, op, c = al
+	movw\c	\tmp, #:lower16:BASEADDR_V7M_SCB + \op
+	movt\c	\tmp, #:upper16:BASEADDR_V7M_SCB + \op
+	str\c	\rt, [\tmp]
+.endm
+
+
+.macro	read_ccsidr, rt
+	v7m_cache_read \rt, V7M_SCB_CCSIDR
+.endm
+
+.macro read_clidr, rt
+	v7m_cache_read \rt, V7M_SCB_CLIDR
+.endm
+
+.macro	write_csselr, rt, tmp
+	v7m_cacheop \rt, \tmp, V7M_SCB_CSSELR
+.endm
+
+/*
+ * dcisw: Invalidate data cache by set/way
+ */
+.macro dcisw, rt, tmp
+	v7m_cacheop \rt, \tmp, V7M_SCB_DCISW
+.endm
+
+/*
+ * dccisw: Clean and invalidate data cache by set/way
+ */
+.macro dccisw, rt, tmp
+	v7m_cacheop \rt, \tmp, V7M_SCB_DCCISW
+.endm
+
+/*
+ * dccimvac: Clean and invalidate data cache line by MVA to PoC.
+ */
+.irp    c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo
+.macro dccimvac\c, rt, tmp
+	v7m_cacheop \rt, \tmp, V7M_SCB_DCCIMVAC, \c
+.endm
+.endr
+
+/*
+ * dcimvac: Invalidate data cache line by MVA to PoC
+ */
+.macro dcimvac, rt, tmp
+	v7m_cacheop \rt, \tmp, V7M_SCB_DCIMVAC
+.endm
+
+/*
+ * dccmvau: Clean data cache line by MVA to PoU
+ */
+.macro dccmvau, rt, tmp
+	v7m_cacheop \rt, \tmp, V7M_SCB_DCCMVAU
+.endm
+
+/*
+ * dccmvac: Clean data cache line by MVA to PoC
+ */
+.macro dccmvac,  rt, tmp
+	v7m_cacheop \rt, \tmp, V7M_SCB_DCCMVAC
+.endm
+
+/*
+ * icimvau: Invalidate instruction caches by MVA to PoU
+ */
+.macro icimvau, rt, tmp
+	v7m_cacheop \rt, \tmp, V7M_SCB_ICIMVAU
+.endm
+
+/*
+ * Invalidate the icache, inner shareable if SMP, invalidate BTB for UP.
+ * rt data ignored by ICIALLU(IS), so can be used for the address
+ */
+.macro invalidate_icache, rt
+	v7m_cacheop \rt, \rt, V7M_SCB_ICIALLU
+	mov \rt, #0
+.endm
+
+/*
+ * Invalidate the BTB, inner shareable if SMP.
+ * rt data ignored by BPIALL, so it can be used for the address
+ */
+.macro invalidate_bp, rt
+	v7m_cacheop \rt, \rt, V7M_SCB_BPIALL
+	mov \rt, #0
+.endm
+
+ENTRY(v7m_invalidate_l1)
+	mov	r0, #0
+
+	write_csselr r0, r1
+	read_ccsidr r0
+
+	movw	r1, #0x7fff
+	and	r2, r1, r0, lsr #13
+
+	movw	r1, #0x3ff
+
+	and	r3, r1, r0, lsr #3      @ NumWays - 1
+	add	r2, r2, #1              @ NumSets
+
+	and	r0, r0, #0x7
+	add	r0, r0, #4      @ SetShift
+
+	clz	r1, r3          @ WayShift
+	add	r4, r3, #1      @ NumWays
+1:	sub	r2, r2, #1      @ NumSets--
+	mov	r3, r4          @ Temp = NumWays
+2:	subs	r3, r3, #1      @ Temp--
+	mov	r5, r3, lsl r1
+	mov	r6, r2, lsl r0
+	orr	r5, r5, r6      @ Reg = (Temp<<WayShift)|(NumSets<<SetShift)
+	dcisw	r5, r6
+	bgt	2b
+	cmp	r2, #0
+	bgt	1b
+	dsb	st
+	isb
+	ret	lr
+ENDPROC(v7m_invalidate_l1)
+
+/*
+ *	v7m_flush_icache_all()
+ *
+ *	Flush the whole I-cache.
+ *
+ *	Registers:
+ *	r0 - set to 0
+ */
+ENTRY(v7m_flush_icache_all)
+	invalidate_icache r0
+	ret	lr
+ENDPROC(v7m_flush_icache_all)
+
+/*
+ *	v7m_flush_dcache_all()
+ *
+ *	Flush the whole D-cache.
+ *
+ *	Corrupted registers: r0-r7, r9-r11
+ */
+ENTRY(v7m_flush_dcache_all)
+	dmb					@ ensure ordering with previous memory accesses
+	read_clidr r0
+	mov	r3, r0, lsr #23			@ move LoC into position
+	ands	r3, r3, #7 << 1			@ extract LoC*2 from clidr
+	beq	finished			@ if loc is 0, then no need to clean
+start_flush_levels:
+	mov	r10, #0				@ start clean at cache level 0
+flush_levels:
+	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
+#ifdef CONFIG_PREEMPT
+	save_and_disable_irqs_notrace r9	@ make cssr&csidr read atomic
+#endif
+	write_csselr r10, r1			@ set current cache level
+	isb					@ isb to sych the new cssr&csidr
+	read_ccsidr r1				@ read the new csidr
+#ifdef CONFIG_PREEMPT
+	restore_irqs_notrace r9
+#endif
+	and	r2, r1, #7			@ extract the length of the cache lines
+	add	r2, r2, #4			@ add 4 (line length offset)
+	movw	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
+	movw	r7, #0x7fff
+	ands	r7, r7, r1, lsr #13		@ extract max number of the index size
+loop1:
+	mov	r9, r7				@ create working copy of max index
+loop2:
+	lsl	r6, r4, r5
+	orr	r11, r10, r6			@ factor way and cache number into r11
+	lsl	r6, r9, r2
+	orr	r11, r11, r6			@ factor index number into r11
+	dccisw	r11, r6				@ clean/invalidate by set/way
+	subs	r9, r9, #1			@ decrement the index
+	bge	loop2
+	subs	r4, r4, #1			@ decrement the way
+	bge	loop1
+skip:
+	add	r10, r10, #2			@ increment cache number
+	cmp	r3, r10
+	bgt	flush_levels
+finished:
+	mov	r10, #0				@ swith back to cache level 0
+	write_csselr r10, r3			@ select current cache level in cssr
+	dsb	st
+	isb
+	ret	lr
+ENDPROC(v7m_flush_dcache_all)
+
+/*
+ *	v7m_flush_cache_all()
+ *
+ *	Flush the entire cache system.
+ *  The data cache flush is now achieved using atomic clean / invalidates
+ *  working outwards from L1 cache. This is done using Set/Way based cache
+ *  maintenance instructions.
+ *  The instruction cache can still be invalidated back to the point of
+ *  unification in a single instruction.
+ *
+ */
+ENTRY(v7m_flush_kern_cache_all)
+	stmfd	sp!, {r4-r7, r9-r11, lr}
+	bl	v7m_flush_dcache_all
+	invalidate_icache r0
+	ldmfd	sp!, {r4-r7, r9-r11, lr}
+	ret	lr
+ENDPROC(v7m_flush_kern_cache_all)
+
+/*
+ *	v7m_flush_cache_all()
+ *
+ *	Flush all TLB entries in a particular address space
+ *
+ *	- mm    - mm_struct describing address space
+ */
+ENTRY(v7m_flush_user_cache_all)
+	/*FALLTHROUGH*/
+
+/*
+ *	v7m_flush_cache_range(start, end, flags)
+ *
+ *	Flush a range of TLB entries in the specified address space.
+ *
+ *	- start - start address (may not be aligned)
+ *	- end   - end address (exclusive, may not be aligned)
+ *	- flags	- vm_area_struct flags describing address space
+ *
+ *	It is assumed that:
+ *	- we have a VIPT cache.
+ */
+ENTRY(v7m_flush_user_cache_range)
+	ret	lr
+ENDPROC(v7m_flush_user_cache_all)
+ENDPROC(v7m_flush_user_cache_range)
+
+/*
+ *	v7m_coherent_kern_range(start,end)
+ *
+ *	Ensure that the I and D caches are coherent within specified
+ *	region.  This is typically used when code has been written to
+ *	a memory region, and will be executed.
+ *
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ *
+ *	It is assumed that:
+ *	- the Icache does not read data from the write buffer
+ */
+ENTRY(v7m_coherent_kern_range)
+	/* FALLTHROUGH */
+
+/*
+ *	v7m_coherent_user_range(start,end)
+ *
+ *	Ensure that the I and D caches are coherent within specified
+ *	region.  This is typically used when code has been written to
+ *	a memory region, and will be executed.
+ *
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ *
+ *	It is assumed that:
+ *	- the Icache does not read data from the write buffer
+ */
+ENTRY(v7m_coherent_user_range)
+ UNWIND(.fnstart		)
+	dcache_line_size r2, r3
+	sub	r3, r2, #1
+	bic	r12, r0, r3
+1:
+/*
+ * We use open coded version of dccmvau otherwise USER() would
+ * point at movw instruction.
+ */
+	dccmvau	r12, r3
+	add	r12, r12, r2
+	cmp	r12, r1
+	blo	1b
+	dsb	ishst
+	icache_line_size r2, r3
+	sub	r3, r2, #1
+	bic	r12, r0, r3
+2:
+	icimvau r12, r3
+	add	r12, r12, r2
+	cmp	r12, r1
+	blo	2b
+	invalidate_bp r0
+	dsb	ishst
+	isb
+	ret	lr
+ UNWIND(.fnend		)
+ENDPROC(v7m_coherent_kern_range)
+ENDPROC(v7m_coherent_user_range)
+
+/*
+ *	v7m_flush_kern_dcache_area(void *addr, size_t size)
+ *
+ *	Ensure that the data held in the page kaddr is written back
+ *	to the page in question.
+ *
+ *	- addr	- kernel address
+ *	- size	- region size
+ */
+ENTRY(v7m_flush_kern_dcache_area)
+	dcache_line_size r2, r3
+	add	r1, r0, r1
+	sub	r3, r2, #1
+	bic	r0, r0, r3
+1:
+	dccimvac r0, r3		@ clean & invalidate D line / unified line
+	add	r0, r0, r2
+	cmp	r0, r1
+	blo	1b
+	dsb	st
+	ret	lr
+ENDPROC(v7m_flush_kern_dcache_area)
+
+/*
+ *	v7m_dma_inv_range(start,end)
+ *
+ *	Invalidate the data cache within the specified region; we will
+ *	be performing a DMA operation in this region and we want to
+ *	purge old data in the cache.
+ *
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+v7m_dma_inv_range:
+	dcache_line_size r2, r3
+	sub	r3, r2, #1
+	tst	r0, r3
+	bic	r0, r0, r3
+	dccimvacne r0, r3
+	subne	r3, r2, #1	@ restore r3, corrupted by v7m's dccimvac
+	tst	r1, r3
+	bic	r1, r1, r3
+	dccimvacne r1, r3
+1:
+	dcimvac r0, r3
+	add	r0, r0, r2
+	cmp	r0, r1
+	blo	1b
+	dsb	st
+	ret	lr
+ENDPROC(v7m_dma_inv_range)
+
+/*
+ *	v7m_dma_clean_range(start,end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+v7m_dma_clean_range:
+	dcache_line_size r2, r3
+	sub	r3, r2, #1
+	bic	r0, r0, r3
+1:
+	dccmvac r0, r3			@ clean D / U line
+	add	r0, r0, r2
+	cmp	r0, r1
+	blo	1b
+	dsb	st
+	ret	lr
+ENDPROC(v7m_dma_clean_range)
+
+/*
+ *	v7m_dma_flush_range(start,end)
+ *	- start   - virtual start address of region
+ *	- end     - virtual end address of region
+ */
+ENTRY(v7m_dma_flush_range)
+	dcache_line_size r2, r3
+	sub	r3, r2, #1
+	bic	r0, r0, r3
+1:
+	dccimvac r0, r3			 @ clean & invalidate D / U line
+	add	r0, r0, r2
+	cmp	r0, r1
+	blo	1b
+	dsb	st
+	ret	lr
+ENDPROC(v7m_dma_flush_range)
+
+/*
+ *	dma_map_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v7m_dma_map_area)
+	add	r1, r1, r0
+	teq	r2, #DMA_FROM_DEVICE
+	beq	v7m_dma_inv_range
+	b	v7m_dma_clean_range
+ENDPROC(v7m_dma_map_area)
+
+/*
+ *	dma_unmap_area(start, size, dir)
+ *	- start	- kernel virtual start address
+ *	- size	- size of region
+ *	- dir	- DMA direction
+ */
+ENTRY(v7m_dma_unmap_area)
+	add	r1, r1, r0
+	teq	r2, #DMA_TO_DEVICE
+	bne	v7m_dma_inv_range
+	ret	lr
+ENDPROC(v7m_dma_unmap_area)
+
+	.globl	v7m_flush_kern_cache_louis
+	.equ	v7m_flush_kern_cache_louis, v7m_flush_kern_cache_all
+
+	__INITDATA
+
+	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
+	define_cache_functions v7m
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index c671f345266a..0d40c285bd86 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -7,6 +7,10 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 
+#ifdef CONFIG_CPU_V7M
+#include <asm/v7m.h>
+#endif
+
 /*
  * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm)
  */
@@ -70,7 +74,13 @@
  * 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
@@ -82,7 +92,13 @@
  * on ARMv7.
  */
 	.macro	icache_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
 	and	\tmp, \tmp, #0xf		@ cache line size encoding
 	mov	\reg, #4			@ bytes per word
 	mov	\reg, \reg, lsl \tmp		@ actual cache line size
-- 
2.34.1