[PATCH 3/4] ARM: mm: kill unused TLB_CAN_READ_FROM_L1_CACHE and use ALT_SMP instead

[Will Deacon]

Many ARMv7 cores have hardware page table walkers that can read the L1
cache. This is discoverable from the ID_MMFR3 register, although this
can be expensive to access from the low-level set_pte functions and is a
pain to cache, particularly with multi-cluster systems.

A useful observation is that the multi-processing extensions for ARMv7
require coherent table walks, meaning that we can make use of ALT_SMP
patching in proc-v7-* to patch away the cache flush safely for these
cores.

Reported-by: Albin Tonnerre <Albin.Tonnerre at arm.com>
Signed-off-by: Will Deacon <will.deacon at arm.com>
---
 arch/arm/include/asm/tlbflush.h | 2 +-
 arch/arm/mm/proc-v6.S           | 2 --
 arch/arm/mm/proc-v7-2level.S    | 3 ++-
 arch/arm/mm/proc-v7-3level.S    | 3 ++-
 arch/arm/mm/proc-v7.S           | 4 ++--
 5 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index c7cdb59..42d155e 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -169,7 +169,7 @@
 # define v6wbi_always_flags	(-1UL)
 #endif
 
-#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_DCLEAN | TLB_BARRIER | \
+#define v7wbi_tlb_flags_smp	(TLB_WB | TLB_BARRIER | \
 				 TLB_V6_U_FULL | TLB_V6_U_PAGE | \
 				 TLB_V6_U_ASID | TLB_V6_BP | \
 				 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | \
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index bcaaa8d..a286d47 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -80,12 +80,10 @@ ENTRY(cpu_v6_do_idle)
 	mov	pc, lr
 
 ENTRY(cpu_v6_dcache_clean_area)
-#ifndef TLB_CAN_READ_FROM_L1_CACHE
 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 	add	r0, r0, #D_CACHE_LINE_SIZE
 	subs	r1, r1, #D_CACHE_LINE_SIZE
 	bhi	1b
-#endif
 	mov	pc, lr
 
 /*
diff --git a/arch/arm/mm/proc-v7-2level.S b/arch/arm/mm/proc-v7-2level.S
index 78f520b..9704097 100644
--- a/arch/arm/mm/proc-v7-2level.S
+++ b/arch/arm/mm/proc-v7-2level.S
@@ -110,7 +110,8 @@ ENTRY(cpu_v7_set_pte_ext)
  ARM(	str	r3, [r0, #2048]! )
  THUMB(	add	r0, r0, #2048 )
  THUMB(	str	r3, [r0] )
-	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
+	ALT_SMP(mov	pc,lr)
+	ALT_UP (mcr	p15, 0, r0, c7, c10, 1)		@ flush_pte
 #endif
 	mov	pc, lr
 ENDPROC(cpu_v7_set_pte_ext)
diff --git a/arch/arm/mm/proc-v7-3level.S b/arch/arm/mm/proc-v7-3level.S
index 6ffd78c..363027e 100644
--- a/arch/arm/mm/proc-v7-3level.S
+++ b/arch/arm/mm/proc-v7-3level.S
@@ -73,7 +73,8 @@ ENTRY(cpu_v7_set_pte_ext)
 	tst	r3, #1 << (55 - 32)		@ L_PTE_DIRTY
 	orreq	r2, #L_PTE_RDONLY
 1:	strd	r2, r3, [r0]
-	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte
+	ALT_SMP(mov	pc, lr)
+	ALT_UP (mcr	p15, 0, r0, c7, c10, 1)		@ flush_pte
 #endif
 	mov	pc, lr
 ENDPROC(cpu_v7_set_pte_ext)
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 3a3c015..37716b0 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -75,14 +75,14 @@ ENTRY(cpu_v7_do_idle)
 ENDPROC(cpu_v7_do_idle)
 
 ENTRY(cpu_v7_dcache_clean_area)
-#ifndef TLB_CAN_READ_FROM_L1_CACHE
+	ALT_SMP(mov	pc, lr)			@ MP extensions imply L1 PTW
+	ALT_UP(W(nop))
 	dcache_line_size r2, r3
 1:	mcr	p15, 0, r0, c7, c10, 1		@ clean D entry
 	add	r0, r0, r2
 	subs	r1, r1, r2
 	bhi	1b
 	dsb
-#endif
 	mov	pc, lr
 ENDPROC(cpu_v7_dcache_clean_area)
 
-- 
1.8.0