Merge branch 'for-rmk' of git://git.marvell.com/orion into devel

61 files changed, 1279 insertions, 318 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 28248b5d6a7..646a5d5eb8c 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -394,6 +394,7 @@ config ARCH_KIRKWOOD
 	select CPU_FEROCEON
 	select PCI
 	select GENERIC_GPIO
+	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	select PLAT_ORION
@@ -415,6 +416,7 @@ config ARCH_MV78XX0
 	select CPU_FEROCEON
 	select PCI
 	select GENERIC_GPIO
+	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	select PLAT_ORION
@@ -428,6 +430,7 @@ config ARCH_ORION5X
 	select CPU_FEROCEON
 	select PCI
 	select GENERIC_GPIO
+	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_TIME
 	select GENERIC_CLOCKEVENTS
 	select PLAT_ORION
diff --git a/arch/arm/configs/kirkwood_defconfig b/arch/arm/configs/kirkwood_defconfig
index dcf8153a947..0a1abb978d7 100644
--- a/arch/arm/configs/kirkwood_defconfig
+++ b/arch/arm/configs/kirkwood_defconfig
@@ -182,6 +182,7 @@ CONFIG_ARCH_KIRKWOOD=y
 CONFIG_MACH_DB88F6281_BP=y
 CONFIG_MACH_RD88F6192_NAS=y
 CONFIG_MACH_RD88F6281=y
+CONFIG_MACH_MV88F6281GTW_GE=y
 CONFIG_MACH_SHEEVAPLUG=y
 CONFIG_MACH_TS219=y
 CONFIG_PLAT_ORION=y
@@ -270,7 +271,9 @@ CONFIG_CMDLINE=""
 #
 # CPU Power Management
 #
-# CONFIG_CPU_IDLE is not set
+CONFIG_CPU_IDLE=y
+CONFIG_CPU_IDLE_GOV_LADDER=y
+CONFIG_CPU_IDLE_GOV_MENU=y
 
 #
 # Floating point emulation
diff --git a/arch/arm/configs/orion5x_defconfig b/arch/arm/configs/orion5x_defconfig
index 5b98f764511..9e2385293ec 100644
--- a/arch/arm/configs/orion5x_defconfig
+++ b/arch/arm/configs/orion5x_defconfig
@@ -903,7 +903,8 @@ CONFIG_UNIX98_PTYS=y
 CONFIG_LEGACY_PTYS=y
 CONFIG_LEGACY_PTY_COUNT=16
 # CONFIG_IPMI_HANDLER is not set
-# CONFIG_HW_RANDOM is not set
+CONFIG_HW_RANDOM=m
+CONFIG_HW_RANDOM_TIMERIOMEM=m
 # CONFIG_R3964 is not set
 # CONFIG_APPLICOM is not set
 # CONFIG_RAW_DRIVER is not set
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 6116e4893c0..15f8a092b70 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -114,3 +114,16 @@
 	.align	3;				\
 	.long	9999b,9001f;			\
 	.previous
+
+/*
+ * SMP data memory barrier
+ */
+	.macro	smp_dmb
+#ifdef CONFIG_SMP
+#if __LINUX_ARM_ARCH__ >= 7
+	dmb
+#elif __LINUX_ARM_ARCH__ == 6
+	mcr	p15, 0, r0, c7, c10, 5	@ dmb
+#endif
+#endif
+	.endm
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index ee99723b3a6..16b52f39798 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -44,11 +44,29 @@ static inline void atomic_set(atomic_t *v, int i)
 	: "cc");
 }
 
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned long tmp;
+	int result;
+
+	__asm__ __volatile__("@ atomic_add\n"
+"1:	ldrex	%0, [%2]\n"
+"	add	%0, %0, %3\n"
+"	strex	%1, %0, [%2]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp)
+	: "r" (&v->counter), "Ir" (i)
+	: "cc");
+}
+
 static inline int atomic_add_return(int i, atomic_t *v)
 {
 	unsigned long tmp;
 	int result;
 
+	smp_mb();
+
 	__asm__ __volatile__("@ atomic_add_return\n"
 "1:	ldrex	%0, [%2]\n"
 "	add	%0, %0, %3\n"
@@ -59,14 +77,34 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 
+	smp_mb();
+
 	return result;
 }
 
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned long tmp;
+	int result;
+
+	__asm__ __volatile__("@ atomic_sub\n"
+"1:	ldrex	%0, [%2]\n"
+"	sub	%0, %0, %3\n"
+"	strex	%1, %0, [%2]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp)
+	: "r" (&v->counter), "Ir" (i)
+	: "cc");
+}
+
 static inline int atomic_sub_return(int i, atomic_t *v)
 {
 	unsigned long tmp;
 	int result;
 
+	smp_mb();
+
 	__asm__ __volatile__("@ atomic_sub_return\n"
 "1:	ldrex	%0, [%2]\n"
 "	sub	%0, %0, %3\n"
@@ -77,6 +115,8 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	: "r" (&v->counter), "Ir" (i)
 	: "cc");
 
+	smp_mb();
+
 	return result;
 }
 
@@ -84,6 +124,8 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 {
 	unsigned long oldval, res;
 
+	smp_mb();
+
 	do {
 		__asm__ __volatile__("@ atomic_cmpxchg\n"
 		"ldrex	%1, [%2]\n"
@@ -95,6 +137,8 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 		    : "cc");
 	} while (res);
 
+	smp_mb();
+
 	return oldval;
 }
 
@@ -135,6 +179,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
 
 	return val;
 }
+#define atomic_add(i, v)	(void) atomic_add_return(i, v)
 
 static inline int atomic_sub_return(int i, atomic_t *v)
 {
@@ -148,6 +193,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 
 	return val;
 }
+#define atomic_sub(i, v)	(void) atomic_sub_return(i, v)
 
 static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
@@ -187,10 +233,8 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 }
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
-#define atomic_add(i, v)	(void) atomic_add_return(i, v)
-#define atomic_inc(v)		(void) atomic_add_return(1, v)
-#define atomic_sub(i, v)	(void) atomic_sub_return(i, v)
-#define atomic_dec(v)		(void) atomic_sub_return(1, v)
+#define atomic_inc(v)		atomic_add(1, v)
+#define atomic_dec(v)		atomic_sub(1, v)
 
 #define atomic_inc_and_test(v)	(atomic_add_return(1, v) == 0)
 #define atomic_dec_and_test(v)	(atomic_sub_return(1, v) == 0)
@@ -200,11 +244,10 @@ static inline int atomic_add_unless(atomic_t *v, int a, int u)
 
 #define atomic_add_negative(i,v) (atomic_add_return(i, v) < 0)
 
-/* Atomic operations are already serializing on ARM */
-#define smp_mb__before_atomic_dec()	barrier()
-#define smp_mb__after_atomic_dec()	barrier()
-#define smp_mb__before_atomic_inc()	barrier()
-#define smp_mb__after_atomic_inc()	barrier()
+#define smp_mb__before_atomic_dec()	smp_mb()
+#define smp_mb__after_atomic_dec()	smp_mb()
+#define smp_mb__before_atomic_inc()	smp_mb()
+#define smp_mb__after_atomic_inc()	smp_mb()
 
 #include <asm-generic/atomic.h>
 #endif
diff --git a/arch/arm/include/asm/flat.h b/arch/arm/include/asm/flat.h
index 1d77e51907f..59426a4595c 100644
--- a/arch/arm/include/asm/flat.h
+++ b/arch/arm/include/asm/flat.h
@@ -5,9 +5,6 @@
 #ifndef __ARM_FLAT_H__
 #define __ARM_FLAT_H__
 
-/* An odd number of words will be pushed after this alignment, so
-   deliberately misalign the value.  */
-#define	flat_stack_align(sp)	sp = (void *)(((unsigned long)(sp) - 4) | 4)
 #define	flat_argvp_envp_on_stack()		1
 #define	flat_old_ram_flag(flags)		(flags)
 #define	flat_reloc_valid(reloc, size)		((reloc) <= (size))
diff --git a/arch/arm/include/asm/sizes.h b/arch/arm/include/asm/sizes.h
index ada93a8fc2e..4fc1565e4f9 100644
--- a/arch/arm/include/asm/sizes.h
+++ b/arch/arm/include/asm/sizes.h
@@ -29,6 +29,7 @@
 #define SZ_512				0x00000200
 
 #define SZ_1K                           0x00000400
+#define SZ_2K                           0x00000800
 #define SZ_4K                           0x00001000
 #define SZ_8K                           0x00002000
 #define SZ_16K                          0x00004000
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index bd4dc8ed53d..d65b2f5bf41 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -248,6 +248,8 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 	unsigned int tmp;
 #endif
 
+	smp_mb();
+
 	switch (size) {
 #if __LINUX_ARM_ARCH__ >= 6
 	case 1:
@@ -307,6 +309,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 		__bad_xchg(ptr, size), ret = 0;
 		break;
 	}
+	smp_mb();
 
 	return ret;
 }
@@ -316,6 +319,12 @@ extern void enable_hlt(void);
 
 #include <asm-generic/cmpxchg-local.h>
 
+#if __LINUX_ARM_ARCH__ < 6
+
+#ifdef CONFIG_SMP
+#error "SMP is not supported on this platform"
+#endif
+
 /*
  * cmpxchg_local and cmpxchg64_local are atomic wrt current CPU. Always make
  * them available.
@@ -329,6 +338,173 @@ extern void enable_hlt(void);
 #include <asm-generic/cmpxchg.h>
 #endif
 
+#else	/* __LINUX_ARM_ARCH__ >= 6 */
+
+extern void __bad_cmpxchg(volatile void *ptr, int size);
+
+/*
+ * cmpxchg only support 32-bits operands on ARMv6.
+ */
+
+static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
+				      unsigned long new, int size)
+{
+	unsigned long oldval, res;
+
+	switch (size) {
+#ifdef CONFIG_CPU_32v6K
+	case 1:
+		do {
+			asm volatile("@ __cmpxchg1\n"
+			"	ldrexb	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexbeq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+	case 2:
+		do {
+			asm volatile("@ __cmpxchg1\n"
+			"	ldrexh	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexheq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+#endif /* CONFIG_CPU_32v6K */
+	case 4:
+		do {
+			asm volatile("@ __cmpxchg4\n"
+			"	ldrex	%1, [%2]\n"
+			"	mov	%0, #0\n"
+			"	teq	%1, %3\n"
+			"	strexeq %0, %4, [%2]\n"
+				: "=&r" (res), "=&r" (oldval)
+				: "r" (ptr), "Ir" (old), "r" (new)
+				: "memory", "cc");
+		} while (res);
+		break;
+	default:
+		__bad_cmpxchg(ptr, size);
+		oldval = 0;
+	}
+
+	return oldval;
+}
+
+static inline unsigned long __cmpxchg_mb(volatile void *ptr, unsigned long old,
+					 unsigned long new, int size)
+{
+	unsigned long ret;
+
+	smp_mb();
+	ret = __cmpxchg(ptr, old, new, size);
+	smp_mb();
+
+	return ret;
+}
+
+#define cmpxchg(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg_mb((ptr),			\
+					  (unsigned long)(o),		\
+					  (unsigned long)(n),		\
+					  sizeof(*(ptr))))
+
+static inline unsigned long __cmpxchg_local(volatile void *ptr,
+					    unsigned long old,
+					    unsigned long new, int size)
+{
+	unsigned long ret;
+
+	switch (size) {
+#ifndef CONFIG_CPU_32v6K
+	case 1:
+	case 2:
+		ret = __cmpxchg_local_generic(ptr, old, new, size);
+		break;
+#endif	/* !CONFIG_CPU_32v6K */
+	default:
+		ret = __cmpxchg(ptr, old, new, size);
+	}
+
+	return ret;
+}
+
+#define cmpxchg_local(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg_local((ptr),			\
+				       (unsigned long)(o),		\
+				       (unsigned long)(n),		\
+				       sizeof(*(ptr))))
+
+#ifdef CONFIG_CPU_32v6K
+
+/*
+ * Note : ARMv7-M (currently unsupported by Linux) does not support
+ * ldrexd/strexd. If ARMv7-M is ever supported by the Linux kernel, it should
+ * not be allowed to use __cmpxchg64.
+ */
+static inline unsigned long long __cmpxchg64(volatile void *ptr,
+					     unsigned long long old,
+					     unsigned long long new)
+{
+	register unsigned long long oldval asm("r0");
+	register unsigned long long __old asm("r2") = old;
+	register unsigned long long __new asm("r4") = new;
+	unsigned long res;
+
+	do {
+		asm volatile(
+		"	@ __cmpxchg8\n"
+		"	ldrexd	%1, %H1, [%2]\n"
+		"	mov	%0, #0\n"
+		"	teq	%1, %3\n"
+		"	teqeq	%H1, %H3\n"
+		"	strexdeq %0, %4, %H4, [%2]\n"
+			: "=&r" (res), "=&r" (oldval)
+			: "r" (ptr), "Ir" (__old), "r" (__new)
+			: "memory", "cc");
+	} while (res);
+
+	return oldval;
+}
+
+static inline unsigned long long __cmpxchg64_mb(volatile void *ptr,
+						unsigned long long old,
+						unsigned long long new)
+{
+	unsigned long long ret;
+
+	smp_mb();
+	ret = __cmpxchg64(ptr, old, new);
+	smp_mb();
+
+	return ret;
+}
+
+#define cmpxchg64(ptr,o,n)						\
+	((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
+					    (unsigned long long)(o),	\
+					    (unsigned long long)(n)))
+
+#define cmpxchg64_local(ptr,o,n)					\
+	((__typeof__(*(ptr)))__cmpxchg64((ptr),				\
+					 (unsigned long long)(o),	\
+					 (unsigned long long)(n)))
+
+#else	/* !CONFIG_CPU_32v6K */
+
+#define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
+
+#endif	/* CONFIG_CPU_32v6K */
+
+#endif	/* __LINUX_ARM_ARCH__ >= 6 */
+
 #endif /* __ASSEMBLY__ */
 
 #define arch_align_stack(x) (x)
diff --git a/arch/arm/kernel/elf.c b/arch/arm/kernel/elf.c
index d4a0da1e48f..950391f194c 100644
--- a/arch/arm/kernel/elf.c
+++ b/arch/arm/kernel/elf.c
@@ -78,6 +78,15 @@ int arm_elf_read_implies_exec(const struct elf32_hdr *x, int executable_stack)
 		return 1;
 	if (cpu_architecture() < CPU_ARCH_ARMv6)
 		return 1;
+#if !defined(CONFIG_AEABI) || defined(CONFIG_OABI_COMPAT)
+	/*
+	 * If we have support for OABI programs, we can never allow NX
+	 * support - our signal syscall restart mechanism relies upon
+	 * being able to execute code placed on the user stack.
+	 */
+	return 1;
+#else
 	return 0;
+#endif
 }
 EXPORT_SYMBOL(arm_elf_read_implies_exec);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index d662a2f1fd8..83b1da6b7ba 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -815,10 +815,7 @@ __kuser_helper_start:
  */
 
 __kuser_memory_barrier:				@ 0xffff0fa0
-
-#if __LINUX_ARM_ARCH__ >= 6 && defined(CONFIG_SMP)
-	mcr	p15, 0, r0, c7, c10, 5	@ dmb
-#endif
+	smp_dmb
 	usr_ret	lr
 
 	.align	5
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index 2e787d40d59..c7f2627385e 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -18,12 +18,14 @@
 	mov	r2, #1
 	add	r1, r1, r0, lsr #3	@ Get byte offset
 	mov	r3, r2, lsl r3		@ create mask
+	smp_dmb
 1:	ldrexb	r2, [r1]
 	ands	r0, r2, r3		@ save old value of bit
 	\instr	r2, r2, r3			@ toggle bit
 	strexb	ip, r2, [r1]
 	cmp	ip, #0
 	bne	1b
+	smp_dmb
 	cmp	r0, #0
 	movne	r0, #1
 2:	mov	pc, lr
diff --git a/arch/arm/mach-gemini/include/mach/hardware.h b/arch/arm/mach-gemini/include/mach/hardware.h
index de6752674c0..213a4fcfeb1 100644
--- a/arch/arm/mach-gemini/include/mach/hardware.h
+++ b/arch/arm/mach-gemini/include/mach/hardware.h
@@ -15,10 +15,9 @@
 /*
  * Memory Map definitions
  */
-/* FIXME: Does it really swap SRAM like this? */
 #ifdef CONFIG_GEMINI_MEM_SWAP
 # define GEMINI_DRAM_BASE	0x00000000
-# define GEMINI_SRAM_BASE	0x20000000
+# define GEMINI_SRAM_BASE	0x70000000
 #else
 # define GEMINI_SRAM_BASE	0x00000000
 # define GEMINI_DRAM_BASE	0x10000000
diff --git a/arch/arm/mach-kirkwood/Kconfig b/arch/arm/mach-kirkwood/Kconfig
index b5421cccd7e..25100f7acf4 100644
--- a/arch/arm/mach-kirkwood/Kconfig
+++ b/arch/arm/mach-kirkwood/Kconfig
@@ -20,6 +20,12 @@ config MACH_RD88F6281
 	  Say 'Y' here if you want your kernel to support the
 	  Marvell RD-88F6281 Reference Board.
 
+config MACH_MV88F6281GTW_GE
+	bool "Marvell 88F6281 GTW GE Board"
+	help
+	  Say 'Y' here if you want your kernel to support the
+	  Marvell 88F6281 GTW GE Board.
+
 config MACH_SHEEVAPLUG
 	bool "Marvell SheevaPlug Reference Board"
 	help
diff --git a/arch/arm/mach-kirkwood/Makefile b/arch/arm/mach-kirkwood/Makefile
index 8f03c9b9bdd..9dd680e964d 100644
--- a/arch/arm/mach-kirkwood/Makefile
+++ b/arch/arm/mach-kirkwood/Makefile
@@ -3,5 +3,8 @@ obj-y				+= common.o addr-map.o irq.o pcie.o mpp.o
 obj-$(CONFIG_MACH_DB88F6281_BP)		+= db88f6281-bp-setup.o
 obj-$(CONFIG_MACH_RD88F6192_NAS)	+= rd88f6192-nas-setup.o
 obj-$(CONFIG_MACH_RD88F6281)		+= rd88f6281-setup.o
+obj-$(CONFIG_MACH_MV88F6281GTW_GE)	+= mv88f6281gtw_ge-setup.o
 obj-$(CONFIG_MACH_SHEEVAPLUG)		+= sheevaplug-setup.o
 obj-$(CONFIG_MACH_TS219)		+= ts219-setup.o
+
+obj-$(CONFIG_CPU_IDLE)			+= cpuidle.o
diff --git a/arch/arm/mach-kirkwood/addr-map.c b/arch/arm/mach-kirkwood/addr-map.c
index 5db4f0bbe5e..1da5d1c18ec 100644
--- a/arch/arm/mach-kirkwood/addr-map.c
+++ b/arch/arm/mach-kirkwood/addr-map.c
@@ -20,6 +20,7 @@
  */
 #define TARGET_DDR		0
 #define TARGET_DEV_BUS		1
+#define TARGET_SRAM		3
 #define TARGET_PCIE		4
 #define ATTR_DEV_SPI_ROM	0x1e
 #define ATTR_DEV_BOOT		0x1d
@@ -30,6 +31,7 @@
 #define ATTR_DEV_CS0		0x3e
 #define ATTR_PCIE_IO		0xe0
 #define ATTR_PCIE_MEM		0xe8
+#define ATTR_SRAM		0x01
 
 /*
  * Helpers to get DDR bank info
@@ -48,7 +50,6 @@
 
 
 struct mbus_dram_target_info kirkwood_mbus_dram_info;
-static int __initdata win_alloc_count;
 
 static int __init cpu_win_can_remap(int win)
 {
@@ -112,7 +113,11 @@ void __init kirkwood_setup_cpu_mbus(void)
 	setup_cpu_win(2, KIRKWOOD_NAND_MEM_PHYS_BASE, KIRKWOOD_NAND_MEM_SIZE,
 		      TARGET_DEV_BUS, ATTR_DEV_NAND, -1);
 
-	win_alloc_count = 3;
+	/*
+	 * Setup window for SRAM.
+	 */
+	setup_cpu_win(3, KIRKWOOD_SRAM_PHYS_BASE, KIRKWOOD_SRAM_SIZE,
+		      TARGET_SRAM, ATTR_SRAM, -1);
 
 	/*
 	 * Setup MBUS dram target info.
@@ -140,8 +145,3 @@ void __init kirkwood_setup_cpu_mbus(void)
 	}
 	kirkwood_mbus_dram_info.num_cs = cs;
 }
-
-void __init kirkwood_setup_sram_win(u32 base, u32 size)
-{
-	setup_cpu_win(win_alloc_count++, base, size, 0x03, 0x00, -1);
-}
diff --git a