Merge branch 'x86/urgent' of into irq/sparseirq

Reason: Pull in the latest io_apic bugfixes

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

28 files changed, 220 insertions, 75 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 553b7cf..88c97bc 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -271,7 +271,6 @@ config ARCH_AT91
 	bool "Atmel AT91"
 	select ARCH_REQUIRE_GPIOLIB
 	select HAVE_CLK
-	select ARCH_USES_GETTIMEOFFSET
 	help
 	  This enables support for systems based on the Atmel AT91RM9200,
 	  AT91SAM9 and AT91CAP9 processors.
@@ -1051,6 +1050,32 @@ config ARM_ERRATA_460075
 	  ACTLR register. Note that setting specific bits in the ACTLR register
 	  may not be available in non-secure mode.
 
+config ARM_ERRATA_742230
+	bool "ARM errata: DMB operation may be faulty"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for the 742230 Cortex-A9
+	  (r1p0..r2p2) erratum. Under rare circumstances, a DMB instruction
+	  between two write operations may not ensure the correct visibility
+	  ordering of the two writes. This workaround sets a specific bit in
+	  the diagnostic register of the Cortex-A9 which causes the DMB
+	  instruction to behave as a DSB, ensuring the correct behaviour of
+	  the two writes.
+
+config ARM_ERRATA_742231
+	bool "ARM errata: Incorrect hazard handling in the SCU may lead to data corruption"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for the 742231 Cortex-A9
+	  (r2p0..r2p2) erratum. Under certain conditions, specific to the
+	  Cortex-A9 MPCore micro-architecture, two CPUs working in SMP mode,
+	  accessing some data located in the same cache line, may get corrupted
+	  data due to bad handling of the address hazard when the line gets
+	  replaced from one of the CPUs at the same time as another CPU is
+	  accessing it. This workaround sets specific bits in the diagnostic
+	  register of the Cortex-A9 which reduces the linefill issuing
+	  capabilities of the processor.
+
 config PL310_ERRATA_588369
 	bool "Clean & Invalidate maintenance operations do not invalidate clean lines"
 	depends on CACHE_L2X0 && ARCH_OMAP4
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index b23f6bc..65a7c1c 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -116,5 +116,5 @@ CFLAGS_font.o := -Dstatic=
 $(obj)/font.c: $(FONTC)
 	$(call cmd,shipped)
 
-$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile .config
+$(obj)/vmlinux.lds: $(obj)/vmlinux.lds.in arch/arm/boot/Makefile $(KCONFIG_CONFIG)
 	@sed "$(SEDFLAGS)" < $< > $@
diff --git a/arch/arm/common/it8152.c b/arch/arm/common/it8152.c
index 7974baa..1bec96e 100644
--- a/arch/arm/common/it8152.c
+++ b/arch/arm/common/it8152.c
@@ -271,6 +271,14 @@ int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
 		((dma_addr + size - PHYS_OFFSET) >= SZ_64M);
 }
 
+int dma_set_coherent_mask(struct device *dev, u64 mask)
+{
+	if (mask >= PHYS_OFFSET + SZ_64M - 1)
+		return 0;
+
+	return -EIO;
+}
+
 int __init it8152_pci_setup(int nr, struct pci_sys_data *sys)
 {
 	it8152_io.start = IT8152_IO_BASE + 0x12000;
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index ab68cf1..e90b167 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -317,6 +317,10 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_BUFFERABLE)
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+struct file;
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
 #else
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_UNCACHED)
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 1b560825..7885722b 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -48,6 +48,8 @@ work_pending:
 	beq	no_work_pending
 	mov	r0, sp				@ 'regs'
 	mov	r2, why				@ 'syscall'
+	tst	r1, #_TIF_SIGPENDING		@ delivering a signal?
+	movne	why, #0				@ prevent further restarts
 	bl	do_notify_resume
 	b	ret_slow_syscall		@ Check work again
 
diff --git a/arch/arm/mach-at91/at91sam9g45_devices.c b/arch/arm/mach-at91/at91sam9g45_devices.c
index 5e71ccd..1276bab 100644
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@@ -426,7 +426,7 @@ static struct i2c_gpio_platform_data pdata_i2c0 = {
 	.sda_is_open_drain	= 1,
 	.scl_pin		= AT91_PIN_PA21,
 	.scl_is_open_drain	= 1,
-	.udelay			= 2,		/* ~100 kHz */
+	.udelay			= 5,		/* ~100 kHz */
 };
 
 static struct platform_device at91sam9g45_twi0_device = {
@@ -440,7 +440,7 @@ static struct i2c_gpio_platform_data pdata_i2c1 = {
 	.sda_is_open_drain	= 1,
 	.scl_pin		= AT91_PIN_PB11,
 	.scl_is_open_drain	= 1,
-	.udelay			= 2,		/* ~100 kHz */
+	.udelay			= 5,		/* ~100 kHz */
 };
 
 static struct platform_device at91sam9g45_twi1_device = {
diff --git a/arch/arm/mach-davinci/dm355.c b/arch/arm/mach-davinci/dm355.c
index 3d996b6..9be261b 100644
--- a/arch/arm/mach-davinci/dm355.c
+++ b/arch/arm/mach-davinci/dm355.c
@@ -769,8 +769,7 @@ static struct map_desc dm355_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00010000),
 		.length		= SZ_32K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
-		.type		= MT_DEVICE,
+		.type		= MT_MEMORY_NONCACHED,
 	},
 };
 
diff --git a/arch/arm/mach-davinci/dm365.c b/arch/arm/mach-davinci/dm365.c
index 6b6f4c6..7781e35 100644
--- a/arch/arm/mach-davinci/dm365.c
+++ b/arch/arm/mach-davinci/dm365.c
@@ -969,8 +969,7 @@ static struct map_desc dm365_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00010000),
 		.length		= SZ_32K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
-		.type		= MT_DEVICE,
+		.type		= MT_MEMORY_NONCACHED,
 	},
 };
 
diff --git a/arch/arm/mach-davinci/dm644x.c b/arch/arm/mach-davinci/dm644x.c
index 40fec31..5e5b0a7 100644
--- a/arch/arm/mach-davinci/dm644x.c
+++ b/arch/arm/mach-davinci/dm644x.c
@@ -653,8 +653,7 @@ static struct map_desc dm644x_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00008000),
 		.length		= SZ_16K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
-		.type		= MT_DEVICE,
+		.type		= MT_MEMORY_NONCACHED,
 	},
 };
 
diff --git a/arch/arm/mach-davinci/dm646x.c b/arch/arm/mach-davinci/dm646x.c
index e4a3df1..26e8a9c 100644
--- a/arch/arm/mach-davinci/dm646x.c
+++ b/arch/arm/mach-davinci/dm646x.c
@@ -737,8 +737,7 @@ static struct map_desc dm646x_io_desc[] = {
 		.virtual	= SRAM_VIRT,
 		.pfn		= __phys_to_pfn(0x00010000),
 		.length		= SZ_32K,
-		/* MT_MEMORY_NONCACHED requires supersection alignment */
-		.type		= MT_DEVICE,
+		.type		= MT_MEMORY_NONCACHED,
 	},
 };
 
diff --git a/arch/arm/mach-dove/include/mach/io.h b/arch/arm/mach-dove/include/mach/io.h
index 3b3e472..eb4936f 100644
--- a/arch/arm/mach-dove/include/mach/io.h
+++ b/arch/arm/mach-dove/include/mach/io.h
@@ -13,8 +13,8 @@
 
 #define IO_SPACE_LIMIT		0xffffffff
 
-#define __io(a)  ((void __iomem *)(((a) - DOVE_PCIE0_IO_PHYS_BASE) +\
-				   DOVE_PCIE0_IO_VIRT_BASE))
-#define __mem_pci(a)		(a)
+#define __io(a)  	((void __iomem *)(((a) - DOVE_PCIE0_IO_BUS_BASE) + \
+						 DOVE_PCIE0_IO_VIRT_BASE))
+#define __mem_pci(a)	(a)
 
 #endif
diff --git a/arch/arm/mach-ixp4xx/common-pci.c b/arch/arm/mach-ixp4xx/common-pci.c
index 61cd4d6..24498a9 100644
--- a/arch/arm/mach-ixp4xx/common-pci.c
+++ b/arch/arm/mach-ixp4xx/common-pci.c
@@ -503,6 +503,14 @@ struct pci_bus * __devinit ixp4xx_scan_bus(int nr, struct pci_sys_data *sys)
 	return pci_scan_bus(sys->busnr, &ixp4xx_ops, sys);
 }
 
+int dma_set_coherent_mask(struct device *dev, u64 mask)
+{
+	if (mask >= SZ_64M - 1)
+		return 0;
+
+	return -EIO;
+}
+
 EXPORT_SYMBOL(ixp4xx_pci_read);
 EXPORT_SYMBOL(ixp4xx_pci_write);
 
diff --git a/arch/arm/mach-ixp4xx/include/mach/hardware.h b/arch/arm/mach-ixp4xx/include/mach/hardware.h
index f91ca6d..8138371 100644
--- a/arch/arm/mach-ixp4xx/include/mach/hardware.h
+++ b/arch/arm/mach-ixp4xx/include/mach/hardware.h
@@ -26,6 +26,8 @@
 #define PCIBIOS_MAX_MEM		0x4BFFFFFF
 #endif
 
+#define ARCH_HAS_DMA_SET_COHERENT_MASK
+
 #define pcibios_assign_all_busses()	1
 
 /* Register locations and bits */
diff --git a/arch/arm/mach-kirkwood/include/mach/kirkwood.h b/arch/arm/mach-kirkwood/include/mach/kirkwood.h
index 93fc2ec..6e924b3 100644
--- a/arch/arm/mach-kirkwood/include/mach/kirkwood.h
+++ b/arch/arm/mach-kirkwood/include/mach/kirkwood.h
@@ -38,7 +38,7 @@
 
 #define KIRKWOOD_PCIE1_IO_PHYS_BASE	0xf3000000
 #define KIRKWOOD_PCIE1_IO_VIRT_BASE	0xfef00000
-#define KIRKWOOD_PCIE1_IO_BUS_BASE	0x00000000
+#define KIRKWOOD_PCIE1_IO_BUS_BASE	0x00100000
 #define KIRKWOOD_PCIE1_IO_SIZE		SZ_1M
 
 #define KIRKWOOD_PCIE_IO_PHYS_BASE	0xf2000000
diff --git a/arch/arm/mach-kirkwood/pcie.c b/arch/arm/mach-kirkwood/pcie.c
index 55e7f00..513ad31 100644
--- a/arch/arm/mach-kirkwood/pcie.c
+++ b/arch/arm/mach-kirkwood/pcie.c
@@ -117,7 +117,7 @@ static void __init pcie0_ioresources_init(struct pcie_port *pp)
 	 * IORESOURCE_IO
 	 */
 	pp->res[0].name = "PCIe 0 I/O Space";
-	pp->res[0].start = KIRKWOOD_PCIE_IO_PHYS_BASE;
+	pp->res[0].start = KIRKWOOD_PCIE_IO_BUS_BASE;
 	pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE_IO_SIZE - 1;
 	pp->res[0].flags = IORESOURCE_IO;
 
@@ -139,7 +139,7 @@ static void __init pcie1_ioresources_init(struct pcie_port *pp)
 	 * IORESOURCE_IO
 	 */
 	pp->res[0].name = "PCIe 1 I/O Space";
-	pp->res[0].start = KIRKWOOD_PCIE1_IO_PHYS_BASE;
+	pp->res[0].start = KIRKWOOD_PCIE1_IO_BUS_BASE;
 	pp->res[0].end = pp->res[0].start + KIRKWOOD_PCIE1_IO_SIZE - 1;
 	pp->res[0].flags = IORESOURCE_IO;
 
diff --git a/arch/arm/mach-mmp/include/mach/system.h b/arch/arm/mach-mmp/include/mach/system.h
index 4f5b0e0..1a8a25e 100644
--- a/arch/arm/mach-mmp/include/mach/system.h
+++ b/arch/arm/mach-mmp/include/mach/system.h
@@ -9,6 +9,8 @@
 #ifndef __ASM_MACH_SYSTEM_H
 #define __ASM_MACH_SYSTEM_H
 
+#include <mach/cputype.h>
+
 static inline void arch_idle(void)
 {
 	cpu_do_idle();
@@ -16,6 +18,9 @@ static inline void arch_idle(void)
 
 static inline void arch_reset(char mode, const char *cmd)
 {
-	cpu_reset(0);
+	if (cpu_is_pxa168())
+		cpu_reset(0xffff0000);
+	else
+		cpu_reset(0);
 }
 #endif /* __ASM_MACH_SYSTEM_H */
diff --git a/arch/arm/mach-pxa/cpufreq-pxa2xx.c b/arch/arm/mach-pxa/cpufreq-pxa2xx.c
index 50d5939..58093d9 100644
--- a/arch/arm/mach-pxa/cpufreq-pxa2xx.c
+++ b/arch/arm/mach-pxa/cpufreq-pxa2xx.c
@@ -312,8 +312,7 @@ static int pxa_set_target(struct cpufreq_policy *policy,
 	freqs.cpu = policy->cpu;
 
 	if (freq_debug)
-		pr_debug(KERN_INFO "Changing CPU frequency to %d Mhz, "
-			 "(SDRAM %d Mhz)\n",
+		pr_debug("Changing CPU frequency to %d Mhz, (SDRAM %d Mhz)\n",
 			 freqs.new / 1000, (pxa_freq_settings[idx].div2) ?
 			 (new_freq_mem / 2000) : (new_freq_mem / 1000));
 
diff --git a/arch/arm/mach-pxa/include/mach/hardware.h b/arch/arm/mach-pxa/include/mach/hardware.h
index 7f64d24..814f145 100644
--- a/arch/arm/mach-pxa/include/mach/hardware.h
+++ b/arch/arm/mach-pxa/include/mach/hardware.h
@@ -264,23 +264,35 @@
  * <= 0x2 for pxa21x/pxa25x/pxa26x/pxa27x
  * == 0x3 for pxa300/pxa310/pxa320
  */
+#if defined(CONFIG_PXA25x) || defined(CONFIG_PXA27x)
 #define __cpu_is_pxa2xx(id)				\
 	({						\
 		unsigned int _id = (id) >> 13 & 0x7;	\
 		_id <= 0x2;				\
 	 })
+#else
+#define __cpu_is_pxa2xx(id)	(0)
+#endif
 
+#ifdef CONFIG_PXA3xx
 #define __cpu_is_pxa3xx(id)				\
 	({						\
 		unsigned int _id = (id) >> 13 & 0x7;	\
 		_id == 0x3;				\
 	 })
+#else
+#define __cpu_is_pxa3xx(id)	(0)
+#endif
 
+#if defined(CONFIG_CPU_PXA930) || defined(CONFIG_CPU_PXA935)
 #define __cpu_is_pxa93x(id)				\
 	({						\
 		unsigned int _id = (id) >> 4 & 0xfff;	\
 		_id == 0x683 || _id == 0x693;		\
 	 })
+#else
+#define __cpu_is_pxa93x(id)	(0)
+#endif
 
 #define cpu_is_pxa2xx()					\
 	({						\
@@ -309,7 +321,7 @@ extern unsigned long get_clock_tick_rate(void);
 #define PCIBIOS_MIN_IO		0
 #define PCIBIOS_MIN_MEM		0
 #define pcibios_assign_all_busses()	1
+#define ARCH_HAS_DMA_SET_COHERENT_MASK
 #endif
 
-
 #endif  /* _ASM_ARCH_HARDWARE_H */
diff --git a/arch/arm/mach-pxa/include/mach/io.h b/arch/arm/mach-pxa/include/mach/io.h
index 262691f..fdca3be 100644
--- a/arch/arm/mach-pxa/include/mach/io.h
+++ b/arch/arm/mach-pxa/include/mach/io.h
@@ -6,6 +6,8 @@
 #ifndef __ASM_ARM_ARCH_IO_H
 #define __ASM_ARM_ARCH_IO_H
 
+#include <mach/hardware.h>
+
 #define IO_SPACE_LIMIT 0xffffffff
 
 /*
diff --git a/arch/arm/mach-pxa/palm27x.c b/arch/arm/mach-pxa/palm27x.c
index 77ad6d3..405b92a 100644
--- a/arch/arm/mach-pxa/palm27x.c
+++ b/arch/arm/mach-pxa/palm27x.c
@@ -469,9 +469,13 @@ static struct i2c_board_info __initdata palm27x_pi2c_board_info[] = {
 	},
 };
 
+static struct i2c_pxa_platform_data palm27x_i2c_power_info = {
+	.use_pio	= 1,
+};
+
 void __init palm27x_pmic_init(void)
 {
 	i2c_register_board_info(1, ARRAY_AND_SIZE(palm27x_pi2c_board_info));
-	pxa27x_set_i2c_power_info(NULL);
+	pxa27x_set_i2c_power_info(&palm27x_i2c_power_info);
 }
 #endif
diff --git a/arch/arm/mach-pxa/vpac270.c b/arch/arm/mach-pxa/vpac270.c
index c9b747c..37d6173 100644
--- a/arch/arm/mach-pxa/vpac270.c
+++ b/arch/arm/mach-pxa/vpac270.c
@@ -240,6 +240,7 @@ static void __init vpac270_onenand_init(void) {}
 #if defined(CONFIG_MMC_PXA) || defined(CONFIG_MMC_PXA_MODULE)
 static struct pxamci_platform_data vpac270_mci_platform_data = {
 	.ocr_mask		= MMC_VDD_32_33 | MMC_VDD_33_34,
+	.gpio_power		= -1,
 	.gpio_card_detect	= GPIO53_VPAC270_SD_DETECT_N,
 	.gpio_card_ro		= GPIO52_VPAC270_SD_READONLY,
 	.detect_delay_ms	= 200,
diff --git a/arch/arm/mach-u300/include/mach/gpio.h b/arch/arm/mach-u300/include/mach/gpio.h
index 7b1fc98..d5a71ab 100644
--- a/arch/arm/mach-u300/include/mach/gpio.h
+++ b/arch/arm/mach-u300/include/mach/gpio.h
@@ -273,6 +273,9 @@ extern void gpio_pullup(unsigned gpio, int value);
 extern int gpio_get_value(unsigned gpio);
 extern void gpio_set_value(unsigned gpio, int value);
 
+#define gpio_get_value_cansleep gpio_get_value
+#define gpio_set_value_cansleep gpio_set_value
+
 /* wrappers to sleep-enable the previous two functions */
 static inline unsigned gpio_to_irq(unsigned gpio)
 {
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index 577df6c..efb1270 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -227,7 +227,13 @@ static void ct_ca9x4_init(void)
 	int i;
 
 #ifdef CONFIG_CACHE_L2X0
-	l2x0_init(MMIO_P2V(CT_CA9X4_L2CC), 0x00000000, 0xfe0fffff);
+	void __iomem *l2x0_base = MMIO_P2V(CT_CA9X4_L2CC);
+
+	/* set RAM latencies to 1 cycle for this core tile. */
+	writel(0, l2x0_base + L2X0_TAG_LATENCY_CTRL);
+	writel(0, l2x0_base + L2X0_DATA_LATENCY_CTRL);
+
+	l2x0_init(l2x0_base, 0x00400000, 0xfe0fffff);
 #endif
 
 	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
diff --git a/arch/arm/mm/alignment.c b/arch/arm/mm/alignment.c
index d073b64..724ba3b 100644
--- a/arch/arm/mm/alignment.c
+++ b/arch/arm/mm/alignment.c
@@ -885,8 +885,23 @@ do_alignment(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 
 	if (ai_usermode & UM_SIGNAL)
 		force_sig(SIGBUS, current);
-	else
-		set_cr(cr_no_alignment);
+	else {
+		/*
+		 * We're about to disable the alignment trap and return to
+		 * user space.  But if an interrupt occurs before actually
+		 * reaching user space, then the IRQ vector entry code will
+		 * notice that we were still in kernel space and therefore
+		 * the alignment trap won't be re-enabled in that case as it
+		 * is presumed to be always on from kernel space.
+		 * Let's prevent that race by disabling interrupts here (they
+		 * are disabled on the way back to user space anyway in
+		 * entry-common.S) and disable the alignment trap only if
+		 * there is no work pending for this thread.
+		 */
+		raw_local_irq_disable();
+		if (!(current_thread_info()->flags & _TIF_WORK_MASK))
+			set_cr(cr_no_alignment);
+	}
 
 	return 0;
 }
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6e1c4f6..6a3a2d0 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -15,6 +15,7 @@
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
+#include <linux/fs.h>
 
 #include <asm/cputype.h>
 #include <asm/sections.h>
@@ -246,6 +247,9 @@ static struct mem_type mem_types[] = {
 		.domain    = DOMAIN_USER,
 	},
 	[MT_MEMORY] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+				L_PTE_USER | L_PTE_EXEC,
+		.prot_l1   = PMD_TYPE_TABLE,
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
 		.domain    = DOMAIN_KERNEL,
 	},
@@ -254,6 +258,9 @@ static struct mem_type mem_types[] = {
 		.domain    = DOMAIN_KERNEL,
 	},
 	[MT_MEMORY_NONCACHED] = {
+		.prot_pte  = L_PTE_PRESENT | L_PTE_YOUNG | L_PTE_DIRTY |
+				L_PTE_USER | L_PTE_EXEC | L_PTE_MT_BUFFERABLE,
+		.prot_l1   = PMD_TYPE_TABLE,
 		.prot_sect = PMD_TYPE_SECT | PMD_SECT_AP_WRITE,
 		.domain    = DOMAIN_KERNEL,
 	},
@@ -411,9 +418,12 @@ static void __init build_mem_type_table(void)
 	 * Enable CPU-specific coherency if supported.
 	 * (Only available on XSC3 at the moment.)
 	 */
-	if (arch_is_coherent() && cpu_is_xsc3())
+	if (arch_is_coherent() && cpu_is_xsc3()) {
 		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
-
+		mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
+		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
+	}
 	/*
 	 * ARMv6 and above have extended page tables.
 	 */
@@ -438,7 +448,9 @@ static void __init build_mem_type_table(void)
 		mem_types[MT_DEVICE_CACHED].prot_sect |= PMD_SECT_S;
 		mem_types[MT_DEVICE_CACHED].prot_pte |= L_PTE_SHARED;
 		mem_types[MT_MEMORY].prot_sect |= PMD_SECT_S;
+		mem_types[MT_MEMORY].prot_pte |= L_PTE_SHARED;
 		mem_types[MT_MEMORY_NONCACHED].prot_sect |= PMD_SECT_S;
+		mem_types[MT_MEMORY_NONCACHED].prot_pte |= L_PTE_SHARED;
 #endif
 	}
 
@@ -475,6 +487,8 @@ static void __init build_mem_type_table(void)
 	mem_types[MT_LOW_VECTORS].prot_l1 |= ecc_mask;
 	mem_types[MT_HIGH_VECTORS].prot_l1 |= ecc_mask;
 	mem_types[MT_MEMORY].prot_sect |= ecc_mask | cp->pmd;
+	mem_types[MT_MEMORY].prot_pte |= kern_pgprot;
+	mem_types[MT_MEMORY_NONCACHED].prot_sect |= ecc_mask;
 	mem_types[MT_ROM].prot_sect |= cp->pmd;
 
 	switch (cp->pmd) {
@@ -498,6 +512,19 @@ static void __init build_mem_type_table(void)
 	}
 }
 
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+			      unsigned long size, pgprot_t vma_prot)
+{
+	if (!pfn_valid(pfn))
+		return pgprot_noncached(vma_prot);
+	else if (file->f_flags & O_SYNC)
+		return pgprot_writecombine(vma_prot);
+	return vma_prot;
+}
+EXPORT_SYMBOL(phys_mem_access_prot);
+#endif
+
 #define vectors_base()	(vectors_high() ? 0xffff0000 : 0)
 
 static void __init *early_alloc(unsigned long sz)
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 6a8506d..7563ff0 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -186,13 +186,14 @@ cpu_v7_name:
  *	It is assumed that:
  *	- cache type register is implemented
  */
-__v7_setup:
+__v7_ca9mp_setup:
 #ifdef CONFIG_SMP
 	mrc	p15, 0, r0, c1, c0, 1
 	tst	r0, #(1 << 6)			@ SMP/nAMP mode enabled?
 	orreq	r0, r0, #(1 << 6) | (1 << 0)	@ Enable SMP/nAMP mode and
 	mcreq	p15, 0, r0, c1, c0, 1		@ TLB ops broadcasting
 #endif
+__v7_setup:
 	adr	r12, __v7_setup_stack		@ the local stack
 	stmia	r12, {r0-r5, r7, r9, r11, lr}
 	bl	v7_flush_dcache_all
@@ -201,11 +202,16 @@ __v7_setup:
 	mrc	p15, 0, r0, c0, c0, 0		@ read main ID register
 	and	r10, r0, #0xff000000		@ ARM?
 	teq	r10, #0x41000000
-	bne	2f
+	bne	3f
 	and	r5, r0, #0x00f00000		@ variant
 	and	r6, r0, #0x0000000f		@ revision
-	orr	r0, r6, r5, lsr #20-4		@ combine variant and revision
+	orr	r6, r6, r5, lsr #20-4		@ combine variant and revision
+	ubfx	r0, r0, #4, #12			@ primary part number
 
+	/* Cortex-A8 Errata */
+	ldr	r10, =0x00000c08		@ Cortex-A8 primary part number
+	teq	r0, r10
+	bne	2f
 #ifdef CONFIG_ARM_ERRATA_430973
 	teq	r5, #0x00100000			@ only present in r1p*
 	mrceq	p15, 0, r10, c1, c0, 1		@ read aux control register
@@ -213,21 +219,42 @@ __v7_setup:
 	mcreq	p15, 0, r10, c1, c0, 1		@ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_458693
-	teq	r0, #0x20			@ only present in r2p0
+	teq	r6, #0x20			@ only present in r2p0
 	mrceq	p15, 0, r10, c1, c0, 1		@ read aux control register
 	orreq	r10, r10, #(1 << 5)		@ set L1NEON to 1
 	orreq	r10, r10, #(1 << 9)		@ set PLDNOP to 1
 	mcreq	p15, 0, r10, c1, c0, 1		@ write aux control register
 #endif
 #ifdef CONFIG_ARM_ERRATA_460075
-	teq	r0, #0x20			@ only present in r2p0
+	teq	r6, #0x20			@ only present in r2p0
 	mrceq	p15, 1, r10, c9, c0, 2		@ read L2 cache aux ctrl register
 	tsteq	r10, #1 << 22
 	orreq	r10, r10, #(1 << 22)		@ set the Write Allocate disable bit
 	mcreq	p15, 1, r10, c9, c0, 2		@ write the L2 cache aux ctrl register
 #endif
+	b	3f
+
+	/* Cortex-A9 Errata */
+2:	ldr	r10, =0x00000c09		@ Cortex-A9 primary part number
+	teq	r0, r10
+	bne	3f
+#ifdef CONFIG_ARM_ERRATA_742230
+	cmp	r6, #0x22			@ only present up to r2p2
+	mrcle	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orrle	r10, r10, #1 << 4		@ set bit #4
+	mcrle	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
+#ifdef CONFIG_ARM_ERRATA_742231
+	teq	r6, #0x20			@ present in r2p0
+	teqne	r6, #0x21			@ present in r2p1
+	teqne	r6, #0x22			@ present in r2p2
+	mrceq	p15, 0, r10, c15, c0, 1		@ read diagnostic register
+	orreq	r10, r10, #1 << 12		@ set bit #12
+	orreq	r10, r10, #1 << 22		@ set bit #22
+	mcreq	p15, 0, r10, c15, c0, 1		@ write diagnostic register
+#endif
 
-2:	mov	r10, #0
+3:	mov	r10, #0
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r10, c7, c5, 0		@ I+BTB cache invalidate
 #endif
@@ -323,6 +350,29 @@ cpu_elf_name:
 
 	.section ".proc.info.init", #alloc, #execinstr
 
+	.type   __v7_ca9mp_proc_info, #object
+__v7_ca9mp_proc_info:
+	.long	0x410fc090		@ Required ID value
+	.long	0xff0ffff0		@ Mask for ID
+	.long   PMD_TYPE_SECT | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ | \
+		PMD_FLAGS
+	.long   PMD_TYPE_SECT | \
+		PMD_SECT_XN | \
+		PMD_SECT_AP_WRITE | \
+		PMD_SECT_AP_READ
+	b	__v7_ca9mp_setup
+	.long	cpu_arch_name
+	.long	cpu_elf_name
+	.long	HWCAP_SWP|HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT|HWCAP_EDSP
+	.long	cpu_v7_name
+	.long	v7_processor_functions
+	.long	v7wbi_tlb_fns
+	.long	v6_user_fns
+	.long	v7_cache_fns
+	.size	__v7_ca9mp_proc_info, . - __v7_ca9mp_proc_info
+
 	/*
 	 * Match any ARMv7 processor core.
 	 */
diff --git a/arch/arm/plat-nomadik/timer.c b/arch/arm/plat-nomadik/timer.c
index ea3ca86..aedf9c1 100644
--- a/arch/arm/plat-nomadik/timer.c
+++ b/arch/arm/plat-nomadik/timer.c
@@ -1,5 +1,5 @@
 /*
- *  linux/arch/arm/mach-nomadik/timer.c
+ *  linux/arch/arm/plat-nomadik/timer.c
  *
  * Copyright (C) 2008 STMicroelectronics
  * Copyright (C) 2010 Alessandro Rubini
@@ -75,7 +75,7 @@ static void nmdk_clkevt_mode(enum clock_event_mode mode,
 		cr = readl(mtu_base + MTU_CR(1));
 		writel(0, mtu_base + MTU_LR(1));
 		writel(cr | MTU_CRn_ENA, mtu_base + MTU_CR(1));
-		writel(0x2, mtu_base + MTU_IMSC);
+		writel(1 << 1, mtu_base + MTU_IMSC);
 		break;
 	case CLOCK_EVT_MODE_SHUTDOWN:
 	case CLOCK_EVT_MODE_UNUSED:
@@ -131,25 +131,23 @@ void __init nmdk_timer_init(void)
 {
 	unsigned long rate;
 	struct clk *clk0;
-	struct clk *clk1;
-	u32 cr;
+	u32 cr = MTU_CRn_32BITS;
 
 	clk0 = clk_get_sys("mtu0", NULL);
 	BUG_ON(IS_ERR(clk0));
 
-	clk1 = clk_get_sys("mtu1", NULL);
-	BUG_ON(IS_ERR(clk1));
-
 	clk_enable(clk0);
-	clk_enable(clk1);
 
 	/*
-	 * Tick rate is 2.4MHz for Nomadik and 110MHz for ux500:
-	 * use a divide-by-16 counter if it's more than 16MHz
+	 * Tick rate is 2.4MHz for Nomadik and 2.4Mhz, 100MHz or 133 MHz
+	 * for ux500.
+	 * Use a divide-by-16 counter if the tick rate is more than 32MHz.
+	 * At 32 MHz, the timer (with 32 bit counter) can be programmed
+	 * to wake-up at a max 127s a head in time. Dividing a 2.4 MHz timer
+	 * with 16 gives too low timer resolution.
 	 */
-	cr = MTU_CRn_32BITS;;
 	rate = clk_get_rate(clk0);
-	if (rate > 16 << 20) {
+	if (rate > 32000000) {
 		rate /= 16;
 		cr |= MTU_CRn_PRESCALE_16;
 	} else {
@@ -170,15 +168,8 @@ void __init nmdk_timer_init(void)
 		pr_err("timer: failed to initialize clock source %s\n",
 		       nmdk_clksrc.name);
 
-	/* Timer 1 is used for events, fix according to rate */
-	cr = MTU_CRn_32BITS;
-	rate = clk_get_rate(clk1);
-	if (rate > 16 << 20) {
-		rate /= 16;
-		cr |= MTU_CRn_PRESCALE_16;
-	} else {
-		cr |= MTU_CRn_PRESCALE_1;
-	}
+	/* Timer 1 is used for events */
+
 	clockevents_calc_mult_shift(&nmdk_clkevt, rate, MTU_MIN_RANGE);
 
 	writel(cr | MTU_CRn_ONESHOT, mtu_base + MTU_CR(1)); /* off, currently */
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index 226b2e8..10b3b4c 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -220,20 +220,7 @@ void __init omap_map_sram(void)
 	if (omap_sram_size == 0)
 		return;
 
-	if (cpu_is_omap24xx()) {
-		omap_sram_io_desc[0].virtual = OMAP2_SRAM_VA;
-
-		base = OMAP2_SRAM_PA;
-		base = ROUND_DOWN(base, PAGE_SIZE);
-		omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
-	}
-
 	if (cpu_is_omap34xx()) {
-		omap_sram_io_desc[0].virtual = OMAP3_SRAM_VA;
-		base = OMAP3_SRAM_PA;
-		base = ROUND_DOWN(base, PAGE_SIZE);
-		omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
-
 		/*
 		 * SRAM must be marked as non-cached on OMAP3 since the
 		 * CORE DPLL M2 divider change code (in SRAM) runs with the
@@ -244,13 +231,11 @@ void __init omap_map_sram(void)
 		omap_sram_io_desc[0].type = MT_MEMORY_NONCACHED;
 	}
 
-	if (cpu_is_omap44xx()) {
-		omap_sram_io_desc[0].virtual = OMAP4_SRAM_VA;
-		base = OMAP4_SRAM_PA;
-		base = ROUND_DOWN(base, PAGE_SIZE);
-		omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
-	}
-	omap_sram_io_desc[0].length = 1024 * 1024;	/* Use section desc */
+	omap_sram_io_desc[0].virtual = omap_sram_base;
+	base = omap_sram_start;
+	base = ROUND_DOWN(base, PAGE_SIZE);
+	omap_sram_io_desc[0].pfn = __phys_to_pfn(base);
+	omap_sram_io_desc[0].length = ROUND_DOWN(omap_sram_size, PAGE_SIZE);
 	iotable_init(omap_sram_io_desc, ARRAY_SIZE(omap_sram_io_desc));
 
 	printk(KERN_INFO "SRAM: Mapped pa 0x%08lx to va 0x%08lx size: 0x%lx\n",