From 1b504bbe7a4a6c251cdc9dcba1fab72234827945 Mon Sep 17 00:00:00 2001
From: Colin Tuckley <colin.tuckley@arm.com>
Date: Sat, 30 May 2009 13:56:12 +0100
Subject: RealView: Add support for the RealView/PBX platform

This is a RealView platform supporting core tiles with ARM11MPCore,
Cortex-A8 or Cortex-A9 (multicore) processors. It has support for MMC,
CompactFlash, PCI-E.

Signed-off-by: Colin Tuckley <colin.tuckley@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm/mm/Kconfig | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'arch/arm/mm')

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 20979564e7ee..76bbcde049b0 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -391,7 +391,7 @@ config CPU_FEROCEON_OLD_ID
 
 # ARMv6
 config CPU_V6
-	bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB
+	bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
 	select CPU_32v6
 	select CPU_ABRT_EV6
 	select CPU_PABRT_NOIFAR
@@ -416,7 +416,7 @@ config CPU_32v6K
 
 # ARMv7
 config CPU_V7
-	bool "Support ARM V7 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB
+	bool "Support ARM V7 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
 	select CPU_32v6K
 	select CPU_32v7
 	select CPU_ABRT_EV7
@@ -747,7 +747,7 @@ config CACHE_FEROCEON_L2_WRITETHROUGH
 config CACHE_L2X0
 	bool "Enable the L2x0 outer cache controller"
 	depends on REALVIEW_EB_ARM11MP || MACH_REALVIEW_PB11MP || MACH_REALVIEW_PB1176 || \
-		   REALVIEW_EB_A9MP || ARCH_MX35 || ARCH_MX31
+		   REALVIEW_EB_A9MP || ARCH_MX35 || ARCH_MX31 || MACH_REALVIEW_PBX
 	default y
 	select OUTER_CACHE
 	help
-- 
cgit v1.2.3


From faa7bc51c11d5bbe440ac04710fd7a3208782000 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Sat, 30 May 2009 14:00:14 +0100
Subject: Check whether the TLB operations need broadcasting on SMP systems

ARMv7 SMP hardware can handle the TLB maintenance operations
broadcasting in hardware so that the software can avoid the costly IPIs.
This patch adds the necessary checks (the MMFR3 CPUID register) to avoid
the broadcasting if already supported by the hardware.

(this patch is based on the work done by Tony Thompson @ ARM)

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm/include/asm/cputype.h  | 25 +++++++++++++++
 arch/arm/include/asm/tlbflush.h | 26 ++++++++++++++--
 arch/arm/kernel/smp.c           | 69 +++++++++++++++++++++++++----------------
 arch/arm/mm/proc-v7.S           |  4 +--
 arch/arm/mm/tlb-v7.S            | 17 ++++++----
 5 files changed, 105 insertions(+), 36 deletions(-)

(limited to 'arch/arm/mm')

diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 7b9d27e749b8..b3e656c6fb78 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -8,6 +8,21 @@
 #define CPUID_TCM	2
 #define CPUID_TLBTYPE	3
 
+#define CPUID_EXT_PFR0	"c1, 0"
+#define CPUID_EXT_PFR1	"c1, 1"
+#define CPUID_EXT_DFR0	"c1, 2"
+#define CPUID_EXT_AFR0	"c1, 3"
+#define CPUID_EXT_MMFR0	"c1, 4"
+#define CPUID_EXT_MMFR1	"c1, 5"
+#define CPUID_EXT_MMFR2	"c1, 6"
+#define CPUID_EXT_MMFR3	"c1, 7"
+#define CPUID_EXT_ISAR0	"c2, 0"
+#define CPUID_EXT_ISAR1	"c2, 1"
+#define CPUID_EXT_ISAR2	"c2, 2"
+#define CPUID_EXT_ISAR3	"c2, 3"
+#define CPUID_EXT_ISAR4	"c2, 4"
+#define CPUID_EXT_ISAR5	"c2, 5"
+
 #ifdef CONFIG_CPU_CP15
 #define read_cpuid(reg)							\
 	({								\
@@ -18,9 +33,19 @@
 		    : "cc");						\
 		__val;							\
 	})
+#define read_cpuid_ext(ext_reg)						\
+	({								\
+		unsigned int __val;					\
+		asm("mrc	p15, 0, %0, c0, " ext_reg		\
+		    : "=r" (__val)					\
+		    :							\
+		    : "cc");						\
+		__val;							\
+	})
 #else
 extern unsigned int processor_id;
 #define read_cpuid(reg) (processor_id)
+#define read_cpuid_ext(reg) 0
 #endif
 
 /*
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index a62218013c78..c964f3fc3bc5 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -40,6 +40,12 @@
 #define TLB_V6_I_ASID	(1 << 18)
 
 #define TLB_BTB		(1 << 28)
+
+/* Unified Inner Shareable TLB operations (ARMv7 MP extensions) */
+#define TLB_V7_UIS_PAGE	(1 << 19)
+#define TLB_V7_UIS_FULL (1 << 20)
+#define TLB_V7_UIS_ASID (1 << 21)
+
 #define TLB_L2CLEAN_FR	(1 << 29)		/* Feroceon */
 #define TLB_DCLEAN	(1 << 30)
 #define TLB_WB		(1 << 31)
@@ -176,9 +182,17 @@
 # define v6wbi_always_flags	(-1UL)
 #endif
 
+#ifdef CONFIG_SMP
+#define v7wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BTB | \
+			 TLB_V7_UIS_FULL | TLB_V7_UIS_PAGE | TLB_V7_UIS_ASID)
+#else
+#define v7wbi_tlb_flags (TLB_WB | TLB_DCLEAN | TLB_BTB | \
+			 TLB_V6_U_FULL | TLB_V6_U_PAGE | TLB_V6_U_ASID)
+#endif
+
 #ifdef CONFIG_CPU_TLB_V7
-# define v7wbi_possible_flags	v6wbi_tlb_flags
-# define v7wbi_always_flags	v6wbi_tlb_flags
+# define v7wbi_possible_flags	v7wbi_tlb_flags
+# define v7wbi_always_flags	v7wbi_tlb_flags
 # ifdef _TLB
 #  define MULTI_TLB 1
 # else
@@ -316,6 +330,8 @@ static inline void local_flush_tlb_all(void)
 		asm("mcr p15, 0, %0, c8, c6, 0" : : "r" (zero) : "cc");
 	if (tlb_flag(TLB_V4_I_FULL | TLB_V6_I_FULL))
 		asm("mcr p15, 0, %0, c8, c5, 0" : : "r" (zero) : "cc");
+	if (tlb_flag(TLB_V7_UIS_FULL))
+		asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc");
 
 	if (tlb_flag(TLB_BTB)) {
 		/* flush the branch target cache */
@@ -351,6 +367,8 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 		asm("mcr p15, 0, %0, c8, c6, 2" : : "r" (asid) : "cc");
 	if (tlb_flag(TLB_V6_I_ASID))
 		asm("mcr p15, 0, %0, c8, c5, 2" : : "r" (asid) : "cc");
+	if (tlb_flag(TLB_V7_UIS_ASID))
+		asm("mcr p15, 0, %0, c8, c3, 2" : : "r" (asid) : "cc");
 
 	if (tlb_flag(TLB_BTB)) {
 		/* flush the branch target cache */
@@ -389,6 +407,8 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (uaddr) : "cc");
 	if (tlb_flag(TLB_V6_I_PAGE))
 		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (uaddr) : "cc");
+	if (tlb_flag(TLB_V7_UIS_PAGE))
+		asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (uaddr) : "cc");
 
 	if (tlb_flag(TLB_BTB)) {
 		/* flush the branch target cache */
@@ -424,6 +444,8 @@ static inline void local_flush_tlb_kernel_page(unsigned long kaddr)
 		asm("mcr p15, 0, %0, c8, c6, 1" : : "r" (kaddr) : "cc");
 	if (tlb_flag(TLB_V6_I_PAGE))
 		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (kaddr) : "cc");
+	if (tlb_flag(TLB_V7_UIS_PAGE))
+		asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (kaddr) : "cc");
 
 	if (tlb_flag(TLB_BTB)) {
 		/* flush the branch target cache */
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 6014dfd22af4..ece658e773a6 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -32,6 +32,7 @@
 #include <asm/processor.h>
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
+#include <asm/cputype.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -545,6 +546,12 @@ struct tlb_args {
 	unsigned long ta_end;
 };
 
+/* all SMP configurations have the extended CPUID registers */
+static inline int tlb_ops_need_broadcast(void)
+{
+	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2;
+}
+
 static inline void ipi_flush_tlb_all(void *ignored)
 {
 	local_flush_tlb_all();
@@ -587,51 +594,61 @@ static inline void ipi_flush_tlb_kernel_range(void *arg)
 
 void flush_tlb_all(void)
 {
-	on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+	if (tlb_ops_need_broadcast())
+		on_each_cpu(ipi_flush_tlb_all, NULL, 1);
+	else
+		local_flush_tlb_all();
 }
 
 void flush_tlb_mm(struct mm_struct *mm)
 {
-	on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, &mm->cpu_vm_mask);
+	if (tlb_ops_need_broadcast())
+		on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, &mm->cpu_vm_mask);
+	else
+		local_flush_tlb_mm(mm);
 }
 
 void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 {
-	struct tlb_args ta;
-
-	ta.ta_vma = vma;
-	ta.ta_start = uaddr;
-
-	on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+	if (tlb_ops_need_broadcast()) {
+		struct tlb_args ta;
+		ta.ta_vma = vma;
+		ta.ta_start = uaddr;
+		on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+	} else
+		local_flush_tlb_page(vma, uaddr);
 }
 
 void flush_tlb_kernel_page(unsigned long kaddr)
 {
-	struct tlb_args ta;
-
-	ta.ta_start = kaddr;
-
-	on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
+	if (tlb_ops_need_broadcast()) {
+		struct tlb_args ta;
+		ta.ta_start = kaddr;
+		on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1);
+	} else
+		local_flush_tlb_kernel_page(kaddr);
 }
 
 void flush_tlb_range(struct vm_area_struct *vma,
                      unsigned long start, unsigned long end)
 {
-	struct tlb_args ta;
-
-	ta.ta_vma = vma;
-	ta.ta_start = start;
-	ta.ta_end = end;
-
-	on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+	if (tlb_ops_need_broadcast()) {
+		struct tlb_args ta;
+		ta.ta_vma = vma;
+		ta.ta_start = start;
+		ta.ta_end = end;
+		on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+	} else
+		local_flush_tlb_range(vma, start, end);
 }
 
 void flush_tlb_kernel_range(unsigned long start, unsigned long end)
 {
-	struct tlb_args ta;
-
-	ta.ta_start = start;
-	ta.ta_end = end;
-
-	on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
+	if (tlb_ops_need_broadcast()) {
+		struct tlb_args ta;
+		ta.ta_start = start;
+		ta.ta_end = end;
+		on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1);
+	} else
+		local_flush_tlb_kernel_range(start, end);
 }
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 3397f1e64d76..c3f737516836 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -176,8 +176,8 @@ cpu_v7_name:
  */
 __v7_setup:
 #ifdef CONFIG_SMP
-	mrc	p15, 0, r0, c1, c0, 1		@ Enable SMP/nAMP mode
-	orr	r0, r0, #(0x1 << 6)
+	mrc	p15, 0, r0, c1, c0, 1		@ Enable SMP/nAMP mode and
+	orr	r0, r0, #(1 << 6) | (1 << 0)	@ TLB ops broadcasting
 	mcr	p15, 0, r0, c1, c0, 1
 #endif
 	adr	r12, __v7_setup_stack		@ the local stack
diff --git a/arch/arm/mm/tlb-v7.S b/arch/arm/mm/tlb-v7.S
index b637e7380ab7..a26a605b73bd 100644
--- a/arch/arm/mm/tlb-v7.S
+++ b/arch/arm/mm/tlb-v7.S
@@ -42,9 +42,11 @@ ENTRY(v7wbi_flush_user_tlb_range)
 	mov	r1, r1, lsl #PAGE_SHIFT
 	vma_vm_flags r2, r2			@ get vma->vm_flags
 1:
-	mcr	p15, 0, r0, c8, c6, 1		@ TLB invalidate D MVA (was 1)
-	tst	r2, #VM_EXEC			@ Executable area ?
-	mcrne	p15, 0, r0, c8, c5, 1		@ TLB invalidate I MVA (was 1)
+#ifdef CONFIG_SMP
+	mcr	p15, 0, r0, c8, c3, 1		@ TLB invalidate U MVA (shareable) 
+#else
+	mcr	p15, 0, r0, c8, c7, 1		@ TLB invalidate U MVA
+#endif
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
@@ -69,8 +71,11 @@ ENTRY(v7wbi_flush_kern_tlb_range)
 	mov	r0, r0, lsl #PAGE_SHIFT
 	mov	r1, r1, lsl #PAGE_SHIFT
 1:
-	mcr	p15, 0, r0, c8, c6, 1		@ TLB invalidate D MVA
-	mcr	p15, 0, r0, c8, c5, 1		@ TLB invalidate I MVA
+#ifdef CONFIG_SMP
+	mcr	p15, 0, r0, c8, c3, 1		@ TLB invalidate U MVA (shareable)
+#else
+	mcr	p15, 0, r0, c8, c7, 1		@ TLB invalidate U MVA
+#endif
 	add	r0, r0, #PAGE_SZ
 	cmp	r0, r1
 	blo	1b
@@ -87,5 +92,5 @@ ENDPROC(v7wbi_flush_kern_tlb_range)
 ENTRY(v7wbi_tlb_fns)
 	.long	v7wbi_flush_user_tlb_range
 	.long	v7wbi_flush_kern_tlb_range
-	.long	v6wbi_tlb_flags
+	.long	v7wbi_tlb_flags
 	.size	v7wbi_tlb_fns, . - v7wbi_tlb_fns
-- 
cgit v1.2.3


From ba3c02636a0743a62cb50b920d36e1c046ab88cf Mon Sep 17 00:00:00 2001
From: Tony Thompson <Anthony.Thompson@arm.com>
Date: Sat, 30 May 2009 14:00:15 +0100
Subject: ARMv7: Mark the PTWs inner WBWA on SMP and WB on UP

There are additional bits to set for the ARMv7 SMP extensions in the
TTBR registers. The IRGN bits order is counter-intuitive but it allows
software built for the ARMv7 base architecture to run on an
implementation with the MP extensions.

Signed-off-by: Tony Thompson <Anthony.Thompson@arm.com>
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm/mm/proc-v7.S | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'arch/arm/mm')

diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index c3f737516836..a18aace32990 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -19,17 +19,23 @@
 
 #include "proc-macros.S"
 
-#define TTB_C		(1 << 0)
 #define TTB_S		(1 << 1)
 #define TTB_RGN_NC	(0 << 3)
 #define TTB_RGN_OC_WBWA	(1 << 3)
 #define TTB_RGN_OC_WT	(2 << 3)
 #define TTB_RGN_OC_WB	(3 << 3)
+#define TTB_NOS		(1 << 5)
+#define TTB_IRGN_NC	((0 << 0) | (0 << 6))
+#define TTB_IRGN_WBWA	((0 << 0) | (1 << 6))
+#define TTB_IRGN_WT	((1 << 0) | (0 << 6))
+#define TTB_IRGN_WB	((1 << 0) | (1 << 6))
 
 #ifndef CONFIG_SMP
-#define TTB_FLAGS	TTB_C|TTB_RGN_OC_WB		@ mark PTWs cacheable, outer WB
+/* PTWs cacheable, inner WB not shareable, outer WB not shareable */
+#define TTB_FLAGS	TTB_IRGN_WB|TTB_RGN_OC_WB
 #else
-#define TTB_FLAGS	TTB_C|TTB_S|TTB_RGN_OC_WBWA	@ mark PTWs cacheable and shared, outer WBWA
+/* PTWs cacheable, inner WBWA shareable, outer WBWA not shareable */
+#define TTB_FLAGS	TTB_IRGN_WBWA|TTB_S|TTB_NOS|TTB_RGN_OC_WBWA
 #endif
 
 ENTRY(cpu_v7_proc_init)
-- 
cgit v1.2.3


From 213fb2a8ee81ec106b9b370a07ccad575e9d3748 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Sat, 30 May 2009 14:00:16 +0100
Subject: ARMv7: Enable the SWP instruction

The SWP instruction has been deprecated starting with the ARMv6
architecture. On ARMv7 processors with the multiprocessor extensions
(like Cortex-A9), this instruction is disabled by default but it can be
enabled by setting bit 10 in the System Control register. Note that
setting this bit is safe even if the ARMv7 processor has the SWP
instruction enabled by default.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm/mm/proc-v7.S | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'arch/arm/mm')

diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index a18aace32990..095b69f5a833 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -232,14 +232,14 @@ __v7_setup:
 ENDPROC(__v7_setup)
 
 	/*   AT
-	 *  TFR   EV X F   I D LR
-	 * .EEE ..EE PUI. .T.T 4RVI ZFRS BLDP WCAM
+	 *  TFR   EV X F   I D LR    S
+	 * .EEE ..EE PUI. .T.T 4RVI ZWRS BLDP WCAM
 	 * rxxx rrxx xxx0 0101 xxxx xxxx x111 xxxx < forced
-	 *    1    0 110       0011 1.00 .111 1101 < we want
+	 *    1    0 110       0011 1100 .111 1101 < we want
 	 */
 	.type	v7_crval, #object
 v7_crval:
-	crval	clear=0x0120c302, mmuset=0x10c0387d, ucset=0x00c0187c
+	crval	clear=0x0120c302, mmuset=0x10c03c7d, ucset=0x00c01c7c
 
 __v7_setup_stack:
 	.space	4 * 11				@ 11 registers
-- 
cgit v1.2.3


From 23d1c515d8fc6d74bea442a4b687c3b5b8627ec4 Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Sat, 30 May 2009 14:00:16 +0100
Subject: ARMv7: Document the PRRR and NMRR registers setting

This patch adds a comment to the proc-v7.S file for the setting of the
PRRR and NMRR registers. It also sets the PRRR[13:12] bits to 0
(corresponding to the reserved TEX[0]CB encoding 110) to be consistent
with the documentation.

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm/mm/proc-v7.S | 32 ++++++++++++++++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

(limited to 'arch/arm/mm')

diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 095b69f5a833..0a8ffd3c03fd 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -219,8 +219,36 @@ __v7_setup:
 	mov	r10, #0x1f			@ domains 0, 1 = manager
 	mcr	p15, 0, r10, c3, c0, 0		@ load domain access register
 #endif
-	ldr	r5, =0xff0aa1a8
-	ldr	r6, =0x40e040e0
+	/*
+	 * Memory region attributes with SCTLR.TRE=1
+	 *
+	 *   n = TEX[0],C,B
+	 *   TR = PRRR[2n+1:2n]		- memory type
+	 *   IR = NMRR[2n+1:2n]		- inner cacheable property
+	 *   OR = NMRR[2n+17:2n+16]	- outer cacheable property
+	 *
+	 *			n	TR	IR	OR
+	 *   UNCACHED		000	00
+	 *   BUFFERABLE		001	10	00	00
+	 *   WRITETHROUGH	010	10	10	10
+	 *   WRITEBACK		011	10	11	11
+	 *   reserved		110
+	 *   WRITEALLOC		111	10	01	01
+	 *   DEV_SHARED		100	01
+	 *   DEV_NONSHARED	100	01
+	 *   DEV_WC		001	10
+	 *   DEV_CACHED		011	10
+	 *
+	 * Other attributes:
+	 *
+	 *   DS0 = PRRR[16] = 0		- device shareable property
+	 *   DS1 = PRRR[17] = 1		- device shareable property
+	 *   NS0 = PRRR[18] = 0		- normal shareable property
+	 *   NS1 = PRRR[19] = 1		- normal shareable property
+	 *   NOS = PRRR[24+n] = 1	- not outer shareable
+	 */
+	ldr	r5, =0xff0a81a8			@ PRRR
+	ldr	r6, =0x40e040e0			@ NMRR
 	mcr	p15, 0, r5, c10, c2, 0		@ write PRRR
 	mcr	p15, 0, r6, c10, c2, 1		@ write NMRR
 	adr	r5, v7_crval
-- 
cgit v1.2.3


From 26584853a44c58f3d6ac7360d697a2ddcd1a3efa Mon Sep 17 00:00:00 2001
From: Catalin Marinas <catalin.marinas@arm.com>
Date: Sat, 30 May 2009 14:00:18 +0100
Subject: Add core support for ARMv6/v7 big-endian

Starting with ARMv6, the CPUs support the BE-8 variant of big-endian
(byte-invariant). This patch adds the core support:

- setting of the BE-8 mode via the CPSR.E register for both kernel and
  user threads
- big-endian page table walking
- REV used to rotate instructions read from memory during fault
  processing as they are still little-endian format
- Kconfig and Makefile support for BE-8. The --be8 option must be passed
  to the final linking stage to convert the instructions to
  little-endian

Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 arch/arm/Makefile                 |  3 +++
 arch/arm/boot/compressed/Makefile |  5 ++++-
 arch/arm/boot/compressed/head.S   |  6 ++++++
 arch/arm/include/asm/processor.h  |  1 +
 arch/arm/include/asm/ptrace.h     | 10 ++++++++++
 arch/arm/kernel/entry-armv.S      |  3 +++
 arch/arm/kernel/entry-common.S    |  3 +++
 arch/arm/kernel/process.c         |  2 +-
 arch/arm/mm/Kconfig               | 14 ++++++++++++++
 arch/arm/mm/abort-ev6.S           |  3 +++
 arch/arm/mm/proc-v6.S             |  3 +++
 arch/arm/mm/proc-v7.S             |  3 +++
 12 files changed, 54 insertions(+), 2 deletions(-)

(limited to 'arch/arm/mm')

diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index e84729bf13d4..1167a4e8c7a8 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -11,6 +11,9 @@
 # Copyright (C) 1995-2001 by Russell King
 
 LDFLAGS_vmlinux	:=-p --no-undefined -X
+ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
+LDFLAGS_vmlinux	+= --be8
+endif
 CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
 OBJCOPYFLAGS	:=-O binary -R .note -R .note.gnu.build-id -R .comment -S
 GZFLAGS		:=-9
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index fbe5eef1f6c9..ce39dc540085 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -40,7 +40,7 @@ ifeq ($(CONFIG_PXA_SHARPSL),y)
 OBJS		+= head-sharpsl.o
 endif
 
-ifeq ($(CONFIG_CPU_BIG_ENDIAN),y)
+ifeq ($(CONFIG_CPU_ENDIAN_BE32),y)
 ifeq ($(CONFIG_CPU_CP15),y)
 OBJS		+= big-endian.o
 else
@@ -78,6 +78,9 @@ EXTRA_AFLAGS  := -Wa,-march=all
 # linker symbols.  We only define initrd_phys and params_phys if the
 # machine class defined the corresponding makefile variable.
 LDFLAGS_vmlinux := --defsym zreladdr=$(ZRELADDR)
+ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
+LDFLAGS_vmlinux += --be8
+endif
 ifneq ($(INITRD_PHYS),)
 LDFLAGS_vmlinux += --defsym initrd_phys=$(INITRD_PHYS)
 endif
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index b371fba1b954..01d49be3b2ca 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -438,6 +438,9 @@ __armv4_mmu_cache_on:
 		mrc	p15, 0, r0, c1, c0, 0	@ read control reg
 		orr	r0, r0, #0x5000		@ I-cache enable, RR cache replacement
 		orr	r0, r0, #0x0030
+#ifdef CONFIG_CPU_ENDIAN_BE8
+		orr	r0, r0, #1 << 25	@ big-endian page tables
+#endif
 		bl	__common_mmu_cache_on
 		mov	r0, #0
 		mcr	p15, 0, r0, c8, c7, 0	@ flush I,D TLBs
@@ -455,6 +458,9 @@ __armv7_mmu_cache_on:
 		mrc	p15, 0, r0, c1, c0, 0	@ read control reg
 		orr	r0, r0, #0x5000		@ I-cache enable, RR cache replacement
 		orr	r0, r0, #0x003c		@ write buffer
+#ifdef CONFIG_CPU_ENDIAN_BE8
+		orr	r0, r0, #1 << 25	@ big-endian page tables
+#endif
 		orrne	r0, r0, #1		@ MMU enabled
 		movne	r1, #-1
 		mcrne	p15, 0, r3, c2, c0, 0	@ load page table pointer
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 1845892260e7..6a89567ffc5b 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -71,6 +71,7 @@ struct thread_struct {
 		regs->ARM_cpsr = USR26_MODE;				\
 	if (elf_hwcap & HWCAP_THUMB && pc & 1)				\
 		regs->ARM_cpsr |= PSR_T_BIT;				\
+	regs->ARM_cpsr |= PSR_ENDSTATE;					\
 	regs->ARM_pc = pc & ~1;		/* pc */			\
 	regs->ARM_sp = sp;		/* sp */			\
 	regs->ARM_r2 = stack[2];	/* r2 (envp) */			\
diff --git a/arch/arm/include/asm/ptrace.h b/arch/arm/include/asm/ptrace.h
index 4a4290f7b4a2..67b833c9b6b9 100644
--- a/arch/arm/include/asm/ptrace.h
+++ b/arch/arm/include/asm/ptrace.h
@@ -50,6 +50,7 @@
 #define PSR_F_BIT	0x00000040
 #define PSR_I_BIT	0x00000080
 #define PSR_A_BIT	0x00000100
+#define PSR_E_BIT	0x00000200
 #define PSR_J_BIT	0x01000000
 #define PSR_Q_BIT	0x08000000
 #define PSR_V_BIT	0x10000000
@@ -72,6 +73,15 @@
 #define PSR_IT_MASK	0x0600fc00	/* If-Then execution state mask */
 #define PSR_ENDIAN_MASK	0x00000200	/* Endianness state mask */
 
+/*
+ * Default endianness state
+ */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define PSR_ENDSTATE	PSR_E_BIT
+#else
+#define PSR_ENDSTATE	0
+#endif
+
 #ifndef __ASSEMBLY__
 
 /*
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index d662a2f1fd85..9d7ce4377c5e 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -482,6 +482,9 @@ __und_usr:
 	subeq	r4, r2, #4			@ ARM instr at LR - 4
 	subne	r4, r2, #2			@ Thumb instr at LR - 2
 1:	ldreqt	r0, [r4]
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	reveq	r0, r0				@ little endian instruction
+#endif
 	beq	call_fpe
 	@ Thumb instruction
 #if __LINUX_ARM_ARCH__ >= 7
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index b55cb0331809..366e5097a41a 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -210,6 +210,9 @@ ENTRY(vector_swi)
   A710(	teq	ip, #0x0f000000						)
   A710(	bne	.Larm710bug						)
 #endif
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	rev	r10, r10			@ little endian instruction
+#endif
 
 #elif defined(CONFIG_AEABI)
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index c3265a2e7cd4..1585423699ee 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -365,7 +365,7 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 	regs.ARM_r2 = (unsigned long)fn;
 	regs.ARM_r3 = (unsigned long)do_exit;
 	regs.ARM_pc = (unsigned long)kernel_thread_helper;
-	regs.ARM_cpsr = SVC_MODE;
+	regs.ARM_cpsr = SVC_MODE | PSR_ENDSTATE;
 
 	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
 }
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 76bbcde049b0..a25f34bd99da 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -639,6 +639,20 @@ config CPU_BIG_ENDIAN
 	  port must properly enable any big-endian related features
 	  of your chipset/board/processor.
 
+config CPU_ENDIAN_BE8
+	bool
+	depends on CPU_BIG_ENDIAN
+	default CPU_V6 || CPU_V7
+	help
+	  Support for the BE-8 (big-endian) mode on ARMv6 and ARMv7 processors.
+
+config CPU_ENDIAN_BE32
+	bool
+	depends on CPU_BIG_ENDIAN
+	default !CPU_ENDIAN_BE8
+	help
+	  Support for the BE-32 (big-endian) mode on pre-ARMv6 processors.
+
 config CPU_HIGH_VECTOR
 	depends on !MMU && CPU_CP15 && !CPU_ARM740T
 	bool "Select the High exception vector"
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 6f7e70907e44..f332df7f0d37 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -37,6 +37,9 @@ ENTRY(v6_early_abort)
 	movne	pc, lr
 	do_thumb_abort
 	ldreq	r3, [r2]			@ read aborted ARM instruction
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	reveq	r3, r3
+#endif
 	do_ldrd_abort
 	tst	r3, #1 << 20			@ L = 0 -> write
 	orreq	r1, r1, #1 << 11		@ yes.
diff --git a/arch/arm/mm/proc-v6.S b/arch/arm/mm/proc-v6.S
index 087e239704df..524ddae92595 100644
--- a/arch/arm/mm/proc-v6.S
+++ b/arch/arm/mm/proc-v6.S
@@ -170,6 +170,9 @@ __v6_setup:
 #endif /* CONFIG_MMU */
 	adr	r5, v6_crval
 	ldmia	r5, {r5, r6}
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	orr	r6, r6, #1 << 25		@ big-endian page tables
+#endif
 	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 0a8ffd3c03fd..4f8486475a79 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -253,6 +253,9 @@ __v7_setup:
 	mcr	p15, 0, r6, c10, c2, 1		@ write NMRR
 	adr	r5, v7_crval
 	ldmia	r5, {r5, r6}
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	orr	r6, r6, #1 << 25		@ big-endian page tables
+#endif
    	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them
-- 
cgit v1.2.3