ARM: mm: implement LoUIS API for cache maintenance ops

ARM v7 architecture introduced the concept of cache levels and related
control registers. New processors like A7 and A15 embed an L2 unified cache
controller that becomes part of the cache level hierarchy. Some operations in
the kernel like cpu_suspend and __cpu_disable do not require a flush of the
entire cache hierarchy to DRAM but just the cache levels belonging to the
Level of Unification Inner Shareable (LoUIS), which in most of ARM v7 systems
correspond to L1.

The current cache flushing API used in cpu_suspend and __cpu_disable,
flush_cache_all(), ends up flushing the whole cache hierarchy since for
v7 it cleans and invalidates all cache levels up to Level of Coherency
(LoC) which cripples system performance when used in hot paths like hotplug
and cpuidle.

Therefore a new kernel cache maintenance API must be added to cope with
latest ARM system requirements.

This patch adds flush_cache_louis() to the ARM kernel cache maintenance API.

This function cleans and invalidates all data cache levels up to the
Level of Unification Inner Shareable (LoUIS) and invalidates the instruction
cache for processors that support it (> v7).

This patch also creates an alias of the cache LoUIS function to flush_kern_all
for all processor versions prior to v7, so that the current cache flushing
behaviour is unchanged for those processors.

v7 cache maintenance code implements a cache LoUIS function that cleans and
invalidates the D-cache up to LoUIS and invalidates the I-cache, according
to the new API.

Reviewed-by: Santosh Shilimkar <santosh.shilimkar@ti.com>
Reviewed-by: Nicolas Pitre <nico@linaro.org>
Signed-off-by: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Tested-by: Shawn Guo <shawn.guo@linaro.org>

24 files changed, 113 insertions, 0 deletions

diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index e4448e16046..e1489c54cd1 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -49,6 +49,13 @@
  *
  *		Unconditionally clean and invalidate the entire cache.
  *
+ *     flush_kern_louis()
+ *
+ *             Flush data cache levels up to the level of unification
+ *             inner shareable and invalidate the I-cache.
+ *             Only needed from v7 onwards, falls back to flush_cache_all()
+ *             for all other processor versions.
+ *
  *	flush_user_all()
  *
  *		Clean and invalidate all user space cache entries
@@ -97,6 +104,7 @@
 struct cpu_cache_fns {
 	void (*flush_icache_all)(void);
 	void (*flush_kern_all)(void);
+	void (*flush_kern_louis)(void);
 	void (*flush_user_all)(void);
 	void (*flush_user_range)(unsigned long, unsigned long, unsigned int);
 
@@ -119,6 +127,7 @@ extern struct cpu_cache_fns cpu_cache;
 
 #define __cpuc_flush_icache_all		cpu_cache.flush_icache_all
 #define __cpuc_flush_kern_all		cpu_cache.flush_kern_all
+#define __cpuc_flush_kern_louis		cpu_cache.flush_kern_louis
 #define __cpuc_flush_user_all		cpu_cache.flush_user_all
 #define __cpuc_flush_user_range		cpu_cache.flush_user_range
 #define __cpuc_coherent_kern_range	cpu_cache.coherent_kern_range
@@ -139,6 +148,7 @@ extern struct cpu_cache_fns cpu_cache;
 
 extern void __cpuc_flush_icache_all(void);
 extern void __cpuc_flush_kern_all(void);
+extern void __cpuc_flush_kern_louis(void);
 extern void __cpuc_flush_user_all(void);
 extern void __cpuc_flush_user_range(unsigned long, unsigned long, unsigned int);
 extern void __cpuc_coherent_kern_range(unsigned long, unsigned long);
@@ -204,6 +214,11 @@ static inline void __flush_icache_all(void)
 	__flush_icache_preferred();
 }
 
+/*
+ * Flush caches up to Level of Unification Inner Shareable
+ */
+#define flush_cache_louis()		__cpuc_flush_kern_louis()
+
 #define flush_cache_all()		__cpuc_flush_kern_all()
 
 static inline void vivt_flush_cache_mm(struct mm_struct *mm)
diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
index 7e30874377e..2d6a7de87a8 100644
--- a/arch/arm/include/asm/glue-cache.h
+++ b/arch/arm/include/asm/glue-cache.h
@@ -132,6 +132,7 @@
 #ifndef MULTI_CACHE
 #define __cpuc_flush_icache_all		__glue(_CACHE,_flush_icache_all)
 #define __cpuc_flush_kern_all		__glue(_CACHE,_flush_kern_cache_all)
+#define __cpuc_flush_kern_louis		__glue(_CACHE,_flush_kern_cache_louis)
 #define __cpuc_flush_user_all		__glue(_CACHE,_flush_user_cache_all)
 #define __cpuc_flush_user_range		__glue(_CACHE,_flush_user_cache_range)
 #define __cpuc_coherent_kern_range	__glue(_CACHE,_coherent_kern_range)
diff --git a/arch/arm/mm/cache-fa.S b/arch/arm/mm/cache-fa.S
index 07201637109..e505befe51b 100644
--- a/arch/arm/mm/cache-fa.S
+++ b/arch/arm/mm/cache-fa.S
@@ -240,6 +240,9 @@ ENTRY(fa_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(fa_dma_unmap_area)
 
+	.globl	fa_flush_kern_cache_louis
+	.equ	fa_flush_kern_cache_louis, fa_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v3.S b/arch/arm/mm/cache-v3.S
index 52e35f32eef..8a3fadece8d 100644
--- a/arch/arm/mm/cache-v3.S
+++ b/arch/arm/mm/cache-v3.S
@@ -128,6 +128,9 @@ ENTRY(v3_dma_map_area)
 ENDPROC(v3_dma_unmap_area)
 ENDPROC(v3_dma_map_area)
 
+	.globl	v3_flush_kern_cache_louis
+	.equ	v3_flush_kern_cache_louis, v3_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v4.S b/arch/arm/mm/cache-v4.S
index 022135d2b7e..43e5d77be67 100644
--- a/arch/arm/mm/cache-v4.S
+++ b/arch/arm/mm/cache-v4.S
@@ -140,6 +140,9 @@ ENTRY(v4_dma_map_area)
 ENDPROC(v4_dma_unmap_area)
 ENDPROC(v4_dma_map_area)
 
+	.globl	v4_flush_kern_cache_louis
+	.equ	v4_flush_kern_cache_louis, v4_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v4wb.S b/arch/arm/mm/cache-v4wb.S
index 8f1eeae340c..cd494532140 100644
--- a/arch/arm/mm/cache-v4wb.S
+++ b/arch/arm/mm/cache-v4wb.S
@@ -251,6 +251,9 @@ ENTRY(v4wb_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(v4wb_dma_unmap_area)
 
+	.globl	v4wb_flush_kern_cache_louis
+	.equ	v4wb_flush_kern_cache_louis, v4wb_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v4wt.S b/arch/arm/mm/cache-v4wt.S
index b34a5f908a8..11e5e5838bc 100644
--- a/arch/arm/mm/cache-v4wt.S
+++ b/arch/arm/mm/cache-v4wt.S
@@ -196,6 +196,9 @@ ENTRY(v4wt_dma_map_area)
 ENDPROC(v4wt_dma_unmap_area)
 ENDPROC(v4wt_dma_map_area)
 
+	.globl	v4wt_flush_kern_cache_louis
+	.equ	v4wt_flush_kern_cache_louis, v4wt_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index 4b10760c56d..d8fd4d4bd3d 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -326,6 +326,9 @@ ENTRY(v6_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(v6_dma_unmap_area)
 
+	.globl	v6_flush_kern_cache_louis
+	.equ	v6_flush_kern_cache_louis, v6_flush_kern_cache_all
+
 	__INITDATA
 
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 39e3fb3db80..d1fa2f66d8c 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -33,6 +33,24 @@ ENTRY(v7_flush_icache_all)
 	mov	pc, lr
 ENDPROC(v7_flush_icache_all)
 
+ /*
+ *     v7_flush_dcache_louis()
+ *
+ *     Flush the D-cache up to the Level of Unification Inner Shareable
+ *
+ *     Corrupted registers: r0-r7, r9-r11 (r6 only in Thumb mode)
+ */
+
+ENTRY(v7_flush_dcache_louis)
+	dmb					@ ensure ordering with previous memory accesses
+	mrc	p15, 1, r0, c0, c0, 1		@ read clidr, r0 = clidr
+	ands	r3, r0, #0xe00000		@ extract LoUIS from clidr
+	mov	r3, r3, lsr #20			@ r3 = LoUIS * 2
+	moveq	pc, lr				@ return if level == 0
+	mov	r10, #0				@ r10 (starting level) = 0
+	b	loop1				@ start flushing cache levels
+ENDPROC(v7_flush_dcache_louis)
+
 /*
  *	v7_flush_dcache_all()
  *
@@ -120,6 +138,24 @@ ENTRY(v7_flush_kern_cache_all)
 	mov	pc, lr
 ENDPROC(v7_flush_kern_cache_all)
 
+ /*
+ *     v7_flush_kern_cache_louis(void)
+ *
+ *     Flush the data cache up to Level of Unification Inner Shareable.
+ *     Invalidate the I-cache to the point of unification.
+ */
+ENTRY(v7_flush_kern_cache_louis)
+ ARM(	stmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
+ THUMB(	stmfd	sp!, {r4-r7, r9-r11, lr}	)
+	bl	v7_flush_dcache_louis
+	mov	r0, #0
+	ALT_SMP(mcr	p15, 0, r0, c7, c1, 0)	@ invalidate I-cache inner shareable
+	ALT_UP(mcr	p15, 0, r0, c7, c5, 0)	@ I+BTB cache invalidate
+ ARM(	ldmfd	sp!, {r4-r5, r7, r9-r11, lr}	)
+ THUMB(	ldmfd	sp!, {r4-r7, r9-r11, lr}	)
+	mov	pc, lr
+ENDPROC(v7_flush_kern_cache_louis)
+
 /*
  *	v7_flush_cache_all()
  *
diff --git a/arch/arm/mm/proc-arm1020.S b/arch/arm/mm/proc-arm1020.S
index 0650bb87c1e..2bb61e703d6 100644
--- a/arch/arm/mm/proc-arm1020.S
+++ b/arch/arm/mm/proc-arm1020.S
@@ -368,6 +368,9 @@ ENTRY(arm1020_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm1020_dma_unmap_area)
 
+	.globl	arm1020_flush_kern_cache_louis
+	.equ	arm1020_flush_kern_cache_louis, arm1020_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm1020
 
diff --git a/arch/arm/mm/proc-arm1020e.S b/arch/arm/mm/proc-arm1020e.S
index 4188478325a..8f96aa40f51 100644
--- a/arch/arm/mm/proc-arm1020e.S
+++ b/arch/arm/mm/proc-arm1020e.S
@@ -354,6 +354,9 @@ ENTRY(arm1020e_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm1020e_dma_unmap_area)
 
+	.globl	arm1020e_flush_kern_cache_louis
+	.equ	arm1020e_flush_kern_cache_louis, arm1020e_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm1020e
 
diff --git a/arch/arm/mm/proc-arm1022.S b/arch/arm/mm/proc-arm1022.S
index 33c68824bff..8ebe4a469a2 100644
--- a/arch/arm/mm/proc-arm1022.S
+++ b/arch/arm/mm/proc-arm1022.S
@@ -343,6 +343,9 @@ ENTRY(arm1022_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm1022_dma_unmap_area)
 
+	.globl	arm1022_flush_kern_cache_louis
+	.equ	arm1022_flush_kern_cache_louis, arm1022_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm1022
 
diff --git a/arch/arm/mm/proc-arm1026.S b/arch/arm/mm/proc-arm1026.S
index fbc1d5fc24d..093fc7e520c 100644
--- a/arch/arm/mm/proc-arm1026.S
+++ b/arch/arm/mm/proc-arm1026.S
@@ -337,6 +337,9 @@ ENTRY(arm1026_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm1026_dma_unmap_area)
 
+	.globl	arm1026_flush_kern_cache_louis
+	.equ	arm1026_flush_kern_cache_louis, arm1026_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm1026
 
diff --git a/arch/arm/mm/proc-arm920.S b/arch/arm/mm/proc-arm920.S
index 1a8c138eb89..2c3b9421ab5 100644
--- a/arch/arm/mm/proc-arm920.S
+++ b/arch/arm/mm/proc-arm920.S
@@ -319,6 +319,9 @@ ENTRY(arm920_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm920_dma_unmap_area)
 
+	.globl	arm920_flush_kern_cache_louis
+	.equ	arm920_flush_kern_cache_louis, arm920_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm920
 #endif
diff --git a/arch/arm/mm/proc-arm922.S b/arch/arm/mm/proc-arm922.S
index 4c44d7e1c3c..4464c49d744 100644
--- a/arch/arm/mm/proc-arm922.S
+++ b/arch/arm/mm/proc-arm922.S
@@ -321,6 +321,9 @@ ENTRY(arm922_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm922_dma_unmap_area)
 
+	.globl	arm922_flush_kern_cache_louis
+	.equ	arm922_flush_kern_cache_louis, arm922_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm922
 #endif
diff --git a/arch/arm/mm/proc-arm925.S b/arch/arm/mm/proc-arm925.S
index ec5b1180994..281eb9b9c1d 100644
--- a/arch/arm/mm/proc-arm925.S
+++ b/arch/arm/mm/proc-arm925.S
@@ -376,6 +376,9 @@ ENTRY(arm925_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm925_dma_unmap_area)
 
+	.globl	arm925_flush_kern_cache_louis
+	.equ	arm925_flush_kern_cache_louis, arm925_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm925
 
diff --git a/arch/arm/mm/proc-arm926.S b/arch/arm/mm/proc-arm926.S
index c31e62c606c..f1803f7e297 100644
--- a/arch/arm/mm/proc-arm926.S
+++ b/arch/arm/mm/proc-arm926.S
@@ -339,6 +339,9 @@ ENTRY(arm926_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm926_dma_unmap_area)
 
+	.globl	arm926_flush_kern_cache_louis
+	.equ	arm926_flush_kern_cache_louis, arm926_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm926
 
diff --git a/arch/arm/mm/proc-arm940.S b/arch/arm/mm/proc-arm940.S
index a613a7dd714..8da189d4a40 100644
--- a/arch/arm/mm/proc-arm940.S
+++ b/arch/arm/mm/proc-arm940.S
@@ -267,6 +267,9 @@ ENTRY(arm940_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm940_dma_unmap_area)
 
+	.globl	arm940_flush_kern_cache_louis
+	.equ	arm940_flush_kern_cache_louis, arm940_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm940
 
diff --git a/arch/arm/mm/proc-arm946.S b/arch/arm/mm/proc-arm946.S
index 9f4f2999fdd..f666cf34075 100644
--- a/arch/arm/mm/proc-arm946.S
+++ b/arch/arm/mm/proc-arm946.S
@@ -310,6 +310,9 @@ ENTRY(arm946_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(arm946_dma_unmap_area)
 
+	.globl	arm946_flush_kern_cache_louis
+	.equ	arm946_flush_kern_cache_louis, arm946_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions arm946
 
diff --git a/arch/arm/mm/proc-feroceon.S b/arch/arm/mm/proc-feroceon.S
index 23a8e4c7f2b..85e5e3baa3d 100644
--- a/arch/arm/mm/proc-feroceon.S
+++ b/arch/arm/mm/proc-feroceon.S
@@ -415,6 +415,9 @@ ENTRY(feroceon_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(feroceon_dma_unmap_area)
 
+	.globl	feroceon_flush_kern_cache_louis
+	.equ	feroceon_flush_kern_cache_louis, feroceon_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions feroceon
 
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 2d8ff3ad86d..b29a2265af0 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -299,6 +299,7 @@ ENTRY(\name\()_processor_functions)
 ENTRY(\name\()_cache_fns)
 	.long	\name\()_flush_icache_all
 	.long	\name\()_flush_kern_cache_all
+	.long   \name\()_flush_kern_cache_louis
 	.long	\name\()_flush_user_cache_all
 	.long	\name\()_flush_user_cache_range
 	.long	\name\()_coherent_kern_range
diff --git a/arch/arm/mm/proc-mohawk.S b/arch/arm/mm/proc-mohawk.S
index fbb2124a547..82f9cdc751d 100644
--- a/arch/arm/mm/proc-mohawk.S
+++ b/arch/arm/mm/proc-mohawk.S
@@ -303,6 +303,9 @@ ENTRY(mohawk_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(mohawk_dma_unmap_area)
 
+	.globl	mohawk_flush_kern_cache_louis
+	.equ	mohawk_flush_kern_cache_louis, mohawk_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions mohawk
 
diff --git a/arch/arm/mm/proc-xsc3.S b/arch/arm/mm/proc-xsc3.S
index b0d57869da2..eb93d6487f3 100644
--- a/arch/arm/mm/proc-xsc3.S
+++ b/arch/arm/mm/proc-xsc3.S
@@ -337,6 +337,9 @@ ENTRY(xsc3_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(xsc3_dma_unmap_area)
 
+	.globl	xsc3_flush_kern_cache_louis
+	.equ	xsc3_flush_kern_cache_louis, xsc3_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions xsc3
 
diff --git a/arch/arm/mm/proc-xscale.S b/arch/arm/mm/proc-xscale.S
index 4ffebaa595e..b5ea31d6daa 100644
--- a/arch/arm/mm/proc-xscale.S
+++ b/arch/arm/mm/proc-xscale.S
@@ -410,6 +410,9 @@ ENTRY(xscale_dma_unmap_area)
 	mov	pc, lr
 ENDPROC(xscale_dma_unmap_area)
 
+	.globl	xscale_flush_kern_cache_louis
+	.equ	xscale_flush_kern_cache_louis, xscale_flush_kern_cache_all
+
 	@ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S)
 	define_cache_functions xscale