Merge commit 'v2.6.35-rc4' into perf/core

Merge reason: Pick up the latest perf fixes

Signed-off-by: Ingo Molnar <mingo@elte.hu>

31 files changed, 144 insertions, 68 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 1f254bd..98922f7 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -955,7 +955,8 @@ config XSCALE_PMU
 	default y
 
 config CPU_HAS_PMU
-	depends on CPU_V6 || CPU_V7 || XSCALE_PMU
+	depends on (CPU_V6 || CPU_V7 || XSCALE_PMU) && \
+		   (!ARCH_OMAP3 || OMAP3_EMU)
 	default y
 	bool
 
diff --git a/arch/arm/include/asm/mach/udc_pxa2xx.h b/arch/arm/include/asm/mach/udc_pxa2xx.h
index f3eabf1..833306e 100644
--- a/arch/arm/include/asm/mach/udc_pxa2xx.h
+++ b/arch/arm/include/asm/mach/udc_pxa2xx.h
@@ -21,8 +21,8 @@ struct pxa2xx_udc_mach_info {
 	 * here.  Note that sometimes the signals go through inverters...
 	 */
 	bool	gpio_vbus_inverted;
-	u16	gpio_vbus;			/* high == vbus present */
+	int	gpio_vbus;			/* high == vbus present */
 	bool	gpio_pullup_inverted;
-	u16	gpio_pullup;			/* high == pullup activated */
+	int	gpio_pullup;			/* high == pullup activated */
 };
 
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 6a89567..7bed3da 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -91,7 +91,11 @@ extern void release_thread(struct task_struct *);
 
 unsigned long get_wchan(struct task_struct *p);
 
+#if __LINUX_ARM_ARCH__ == 6
+#define cpu_relax()			smp_mb()
+#else
 #define cpu_relax()			barrier()
+#endif
 
 /*
  * Create a new kernel thread
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index 5b7cfaf..417c392 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -201,7 +201,7 @@ armpmu_event_update(struct perf_event *event,
 {
 	int shift = 64 - 32;
 	s64 prev_raw_count, new_raw_count;
-	s64 delta;
+	u64 delta;
 
 again:
 	prev_raw_count = local64_read(&hwc->prev_count);
diff --git a/arch/arm/mach-mx3/mach-mx31lilly.c b/arch/arm/mach-mx3/mach-mx31lilly.c
index d3d5877..b2c7f51 100644
--- a/arch/arm/mach-mx3/mach-mx31lilly.c
+++ b/arch/arm/mach-mx3/mach-mx31lilly.c
@@ -115,6 +115,8 @@ static struct platform_device physmap_flash_device = {
 
 /* USB */
 
+#if defined(CONFIG_USB_ULPI)
+
 #define USB_PAD_CFG (PAD_CTL_DRV_MAX | PAD_CTL_SRE_FAST | PAD_CTL_HYS_CMOS | \
 			PAD_CTL_ODE_CMOS | PAD_CTL_100K_PU)
 
@@ -244,10 +246,20 @@ static struct mxc_usbh_platform_data usbh2_pdata = {
 	.flags	= MXC_EHCI_POWER_PINS_ENABLED,
 };
 
-static struct platform_device *devices[] __initdata = {
-	&smsc91x_device,
-	&physmap_flash_device,
-};
+static void lilly1131_usb_init(void)
+{
+	usbotg_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops,
+				USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT);
+	usbh2_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops,
+				USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT);
+
+	mxc_register_device(&mxc_usbh1, &usbh1_pdata);
+	mxc_register_device(&mxc_usbh2, &usbh2_pdata);
+}
+
+#else
+static inline void lilly1131_usb_init(void) {}
+#endif /* CONFIG_USB_ULPI */
 
 /* SPI */
 
@@ -279,6 +291,11 @@ static struct spi_board_info mc13783_dev __initdata = {
 	.platform_data	= &mc13783_pdata,
 };
 
+static struct platform_device *devices[] __initdata = {
+	&smsc91x_device,
+	&physmap_flash_device,
+};
+
 static int mx31lilly_baseboard;
 core_param(mx31lilly_baseboard, mx31lilly_baseboard, int, 0444);
 
@@ -321,13 +338,7 @@ static void __init mx31lilly_board_init(void)
 	platform_add_devices(devices, ARRAY_SIZE(devices));
 
 	/* USB */
-	usbotg_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops,
-				USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT);
-	usbh2_pdata.otg = otg_ulpi_create(&mxc_ulpi_access_ops,
-				USB_OTG_DRV_VBUS | USB_OTG_DRV_VBUS_EXT);
-
-	mxc_register_device(&mxc_usbh1, &usbh1_pdata);
-	mxc_register_device(&mxc_usbh2, &usbh2_pdata);
+	lilly1131_usb_init();
 }
 
 static void __init mx31lilly_timer_init(void)
diff --git a/arch/arm/mach-omap2/board-omap3stalker.c b/arch/arm/mach-omap2/board-omap3stalker.c
index f848ba8..a04cffd 100644
--- a/arch/arm/mach-omap2/board-omap3stalker.c
+++ b/arch/arm/mach-omap2/board-omap3stalker.c
@@ -538,9 +538,7 @@ static void ads7846_dev_init(void)
 		printk(KERN_ERR "can't get ads7846 pen down GPIO\n");
 
 	gpio_direction_input(OMAP3_STALKER_TS_GPIO);
-
-	omap_set_gpio_debounce(OMAP3_STALKER_TS_GPIO, 1);
-	omap_set_gpio_debounce_time(OMAP3_STALKER_TS_GPIO, 0xa);
+	gpio_set_debounce(OMAP3_STALKER_TS_GPIO, 310);
 }
 
 static int ads7846_get_pendown_state(void)
diff --git a/arch/arm/mach-omap2/clock44xx_data.c b/arch/arm/mach-omap2/clock44xx_data.c
index 0280422..e10db7a 100644
--- a/arch/arm/mach-omap2/clock44xx_data.c
+++ b/arch/arm/mach-omap2/clock44xx_data.c
@@ -1369,6 +1369,7 @@ static struct clk emif1_ick = {
 	.ops		= &clkops_omap2_dflt,
 	.enable_reg	= OMAP4430_CM_MEMIF_EMIF_1_CLKCTRL,
 	.enable_bit	= OMAP4430_MODULEMODE_HWCTRL,
+	.flags		= ENABLE_ON_INIT,
 	.clkdm_name	= "l3_emif_clkdm",
 	.parent		= &ddrphy_ck,
 	.recalc		= &followparent_recalc,
@@ -1379,6 +1380,7 @@ static struct clk emif2_ick = {
 	.ops		= &clkops_omap2_dflt,
 	.enable_reg	= OMAP4430_CM_MEMIF_EMIF_2_CLKCTRL,
 	.enable_bit	= OMAP4430_MODULEMODE_HWCTRL,
+	.flags		= ENABLE_ON_INIT,
 	.clkdm_name	= "l3_emif_clkdm",
 	.parent		= &ddrphy_ck,
 	.recalc		= &followparent_recalc,
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index 95c9a5f..b7a4133 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -409,10 +409,11 @@ static int _init_main_clk(struct omap_hwmod *oh)
 		return 0;
 
 	oh->_clk = omap_clk_get_by_name(oh->main_clk);
-	if (!oh->_clk)
+	if (!oh->_clk) {
 		pr_warning("omap_hwmod: %s: cannot clk_get main_clk %s\n",
 			   oh->name, oh->main_clk);
 		return -EINVAL;
+	}
 
 	if (!oh->_clk->clkdm)
 		pr_warning("omap_hwmod: %s: missing clockdomain for %s.\n",
@@ -444,10 +445,11 @@ static int _init_interface_clks(struct omap_hwmod *oh)
 			continue;
 
 		c = omap_clk_get_by_name(os->clk);
-		if (!c)
+		if (!c) {
 			pr_warning("omap_hwmod: %s: cannot clk_get interface_clk %s\n",
 				   oh->name, os->clk);
 			ret = -EINVAL;
+		}
 		os->_clk = c;
 	}
 
@@ -470,10 +472,11 @@ static int _init_opt_clks(struct omap_hwmod *oh)
 
 	for (i = oh->opt_clks_cnt, oc = oh->opt_clks; i > 0; i--, oc++) {
 		c = omap_clk_get_by_name(oc->clk);
-		if (!c)
+		if (!c) {
 			pr_warning("omap_hwmod: %s: cannot clk_get opt_clk %s\n",
 				   oh->name, oc->clk);
 			ret = -EINVAL;
+		}
 		oc->_clk = c;
 	}
 
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 2e96771..b88737f 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -99,7 +99,7 @@ static void omap3_enable_io_chain(void)
 		/* Do a readback to assure write has been done */
 		prm_read_mod_reg(WKUP_MOD, PM_WKEN);
 
-		while (!(prm_read_mod_reg(WKUP_MOD, PM_WKST) &
+		while (!(prm_read_mod_reg(WKUP_MOD, PM_WKEN) &
 			 OMAP3430_ST_IO_CHAIN_MASK)) {
 			timeout++;
 			if (timeout > 1000) {
@@ -108,7 +108,7 @@ static void omap3_enable_io_chain(void)
 				return;
 			}
 			prm_set_mod_reg_bits(OMAP3430_ST_IO_CHAIN_MASK,
-					     WKUP_MOD, PM_WKST);
+					     WKUP_MOD, PM_WKEN);
 		}
 	}
 }
diff --git a/arch/arm/mach-omap2/usb-ehci.c b/arch/arm/mach-omap2/usb-ehci.c
index c68f799..d72d1ac 100644
--- a/arch/arm/mach-omap2/usb-ehci.c
+++ b/arch/arm/mach-omap2/usb-ehci.c
@@ -20,6 +20,8 @@
 #include <linux/delay.h>
 #include <linux/platform_device.h>
 #include <linux/clk.h>
+#include <linux/dma-mapping.h>
+
 #include <asm/io.h>
 #include <plat/mux.h>
 
diff --git a/arch/arm/mach-pxa/mioa701.c b/arch/arm/mach-pxa/mioa701.c
index d60db87..fa6a708 100644
--- a/arch/arm/mach-pxa/mioa701.c
+++ b/arch/arm/mach-pxa/mioa701.c
@@ -697,7 +697,7 @@ static struct i2c_board_info __initdata mioa701_pi2c_devices[] = {
 };
 
 /* Board I2C devices. */
-static struct i2c_board_info __initdata mioa701_i2c_devices[] = {
+static struct i2c_board_info mioa701_i2c_devices[] = {
 	{
 		I2C_BOARD_INFO("mt9m111", 0x5d),
 	},
diff --git a/arch/arm/mach-pxa/z2.c b/arch/arm/mach-pxa/z2.c
index f5d1ae3..d303c69 100644
--- a/arch/arm/mach-pxa/z2.c
+++ b/arch/arm/mach-pxa/z2.c
@@ -3,8 +3,9 @@
  *
  *  Support for the Zipit Z2 Handheld device.
  *
- *  Author: 	Ken McGuire
- *  Created:	Jan 25, 2009
+ *  Copyright (C) 2009-2010 Marek Vasut <marek.vasut@gmail.com>
+ *
+ *  Based on research and code by: Ken McGuire
  *  Based on mainstone.c as modified for the Zipit Z2.
  *
  *  This program is free software; you can redistribute it and/or modify
@@ -157,21 +158,14 @@ static struct mtd_partition z2_flash_parts[] = {
 	{
 		.name	= "U-Boot Bootloader",
 		.offset	= 0x0,
-		.size	= 0x20000,
-	},
-	{
-		.name	= "Linux Kernel",
-		.offset	= 0x20000,
-		.size	= 0x220000,
-	},
-	{
-		.name	= "Filesystem",
-		.offset	= 0x240000,
-		.size	= 0x5b0000,
-	},
-	{
+		.size	= 0x40000,
+	}, {
 		.name	= "U-Boot Environment",
-		.offset	= 0x7f0000,
+		.offset	= 0x40000,
+		.size	= 0x60000,
+	}, {
+		.name	= "Flash",
+		.offset	= 0x60000,
 		.size	= MTDPART_SIZ_FULL,
 	},
 };
diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig
index ee5e392..b4575ae 100644
--- a/arch/arm/mach-realview/Kconfig
+++ b/arch/arm/mach-realview/Kconfig
@@ -18,6 +18,7 @@ config REALVIEW_EB_ARM11MP
 	bool "Support ARM11MPCore tile"
 	depends on MACH_REALVIEW_EB
 	select CPU_V6
+	select ARCH_HAS_BARRIERS if SMP
 	help
 	  Enable support for the ARM11MPCore tile on the Realview platform.
 
@@ -35,6 +36,7 @@ config MACH_REALVIEW_PB11MP
 	select CPU_V6
 	select ARM_GIC
 	select HAVE_PATA_PLATFORM
+	select ARCH_HAS_BARRIERS if SMP
 	help
 	  Include support for the ARM(R) RealView MPCore Platform Baseboard.
 	  PB11MPCore is a platform with an on-board ARM11MPCore and has
diff --git a/arch/arm/mach-realview/include/mach/barriers.h b/arch/arm/mach-realview/include/mach/barriers.h
new file mode 100644
index 0000000..0c5d749
--- /dev/null
+++ b/arch/arm/mach-realview/include/mach/barriers.h
@@ -0,0 +1,8 @@
+/*
+ * Barriers redefined for RealView ARM11MPCore platforms with L220 cache
+ * controller to work around hardware errata causing the outer_sync()
+ * operation to deadlock the system.
+ */
+#define mb()		dsb()
+#define rmb()		dmb()
+#define wmb()		mb()
diff --git a/arch/arm/mach-realview/realview_eb.c b/arch/arm/mach-realview/realview_eb.c
index 422ccd7..4425018 100644
--- a/arch/arm/mach-realview/realview_eb.c
+++ b/arch/arm/mach-realview/realview_eb.c
@@ -32,6 +32,7 @@
 #include <asm/leds.h>
 #include <asm/mach-types.h>
 #include <asm/pmu.h>
+#include <asm/pgtable.h>
 #include <asm/hardware/gic.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/localtimer.h>
@@ -457,7 +458,7 @@ static void __init realview_eb_init(void)
 
 MACHINE_START(REALVIEW_EB, "ARM-RealView EB")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= REALVIEW_EB_UART0_BASE,
+	.phys_io	= REALVIEW_EB_UART0_BASE & SECTION_MASK,
 	.io_pg_offst	= (IO_ADDRESS(REALVIEW_EB_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.fixup		= realview_fixup,
diff --git a/arch/arm/mach-realview/realview_pb1176.c b/arch/arm/mach-realview/realview_pb1176.c
index 96568eb..099a1f1 100644
--- a/arch/arm/mach-realview/realview_pb1176.c
+++ b/arch/arm/mach-realview/realview_pb1176.c
@@ -32,6 +32,7 @@
 #include <asm/leds.h>
 #include <asm/mach-types.h>
 #include <asm/pmu.h>
+#include <asm/pgtable.h>
 #include <asm/hardware/gic.h>
 #include <asm/hardware/cache-l2x0.h>
 
@@ -351,7 +352,7 @@ static void __init realview_pb1176_init(void)
 
 MACHINE_START(REALVIEW_PB1176, "ARM-RealView PB1176")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= REALVIEW_PB1176_UART0_BASE,
+	.phys_io	= REALVIEW_PB1176_UART0_BASE & SECTION_MASK,
 	.io_pg_offst	= (IO_ADDRESS(REALVIEW_PB1176_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.fixup		= realview_pb1176_fixup,
diff --git a/arch/arm/mach-realview/realview_pb11mp.c b/arch/arm/mach-realview/realview_pb11mp.c
index 7fbefbb..0e07a5c 100644
--- a/arch/arm/mach-realview/realview_pb11mp.c
+++ b/arch/arm/mach-realview/realview_pb11mp.c
@@ -32,6 +32,7 @@
 #include <asm/leds.h>
 #include <asm/mach-types.h>
 #include <asm/pmu.h>
+#include <asm/pgtable.h>
 #include <asm/hardware/gic.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/localtimer.h>
@@ -373,7 +374,7 @@ static void __init realview_pb11mp_init(void)
 
 MACHINE_START(REALVIEW_PB11MP, "ARM-RealView PB11MPCore")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= REALVIEW_PB11MP_UART0_BASE,
+	.phys_io	= REALVIEW_PB11MP_UART0_BASE & SECTION_MASK,
 	.io_pg_offst	= (IO_ADDRESS(REALVIEW_PB11MP_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.fixup		= realview_fixup,
diff --git a/arch/arm/mach-realview/realview_pba8.c b/arch/arm/mach-realview/realview_pba8.c
index d3c113b..ac2f06f 100644
--- a/arch/arm/mach-realview/realview_pba8.c
+++ b/arch/arm/mach-realview/realview_pba8.c
@@ -31,6 +31,7 @@
 #include <asm/leds.h>
 #include <asm/mach-types.h>
 #include <asm/pmu.h>
+#include <asm/pgtable.h>
 #include <asm/hardware/gic.h>
 
 #include <asm/mach/arch.h>
@@ -323,7 +324,7 @@ static void __init realview_pba8_init(void)
 
 MACHINE_START(REALVIEW_PBA8, "ARM-RealView PB-A8")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= REALVIEW_PBA8_UART0_BASE,
+	.phys_io	= REALVIEW_PBA8_UART0_BASE & SECTION_MASK,
 	.io_pg_offst	= (IO_ADDRESS(REALVIEW_PBA8_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.fixup		= realview_fixup,
diff --git a/arch/arm/mach-realview/realview_pbx.c b/arch/arm/mach-realview/realview_pbx.c
index a235ba3..08fd683 100644
--- a/arch/arm/mach-realview/realview_pbx.c
+++ b/arch/arm/mach-realview/realview_pbx.c
@@ -31,6 +31,7 @@
 #include <asm/mach-types.h>
 #include <asm/pmu.h>
 #include <asm/smp_twd.h>
+#include <asm/pgtable.h>
 #include <asm/hardware/gic.h>
 #include <asm/hardware/cache-l2x0.h>
 
@@ -409,7 +410,7 @@ static void __init realview_pbx_init(void)
 
 MACHINE_START(REALVIEW_PBX, "ARM-RealView PBX")
 	/* Maintainer: ARM Ltd/Deep Blue Solutions Ltd */
-	.phys_io	= REALVIEW_PBX_UART0_BASE,
+	.phys_io	= REALVIEW_PBX_UART0_BASE & SECTION_MASK,
 	.io_pg_offst	= (IO_ADDRESS(REALVIEW_PBX_UART0_BASE) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.fixup		= realview_pbx_fixup,
diff --git a/arch/arm/mach-vexpress/ct-ca9x4.c b/arch/arm/mach-vexpress/ct-ca9x4.c
index 9b11eed..6353459 100644
--- a/arch/arm/mach-vexpress/ct-ca9x4.c
+++ b/arch/arm/mach-vexpress/ct-ca9x4.c
@@ -10,6 +10,7 @@
 #include <linux/amba/clcd.h>
 
 #include <asm/clkdev.h>
+#include <asm/pgtable.h>
 #include <asm/hardware/arm_timer.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <asm/hardware/gic.h>
@@ -236,7 +237,7 @@ static void ct_ca9x4_init(void)
 }
 
 MACHINE_START(VEXPRESS, "ARM-Versatile Express CA9x4")
-	.phys_io	= V2M_UART0,
+	.phys_io	= V2M_UART0 & SECTION_MASK,
 	.io_pg_offst	= (__MMIO_P2V(V2M_UART0) >> 18) & 0xfffc,
 	.boot_params	= PHYS_OFFSET + 0x00000100,
 	.map_io		= ct_ca9x4_map_io,
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 346ae14..101105e 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -735,6 +735,25 @@ config NEEDS_SYSCALL_FOR_CMPXCHG
 	  Forget about fast user space cmpxchg support.
 	  It is just not possible.
 
+config DMA_CACHE_RWFO
+	bool "Enable read/write for ownership DMA cache maintenance"
+	depends on CPU_V6 && SMP
+	default y
+	help
+	  The Snoop Control Unit on ARM11MPCore does not detect the
+	  cache maintenance operations and the dma_{map,unmap}_area()
+	  functions may leave stale cache entries on other CPUs. By
+	  enabling this option, Read or Write For Ownership in the ARMv6
+	  DMA cache maintenance functions is performed. These LDR/STR
+	  instructions change the cache line state to shared or modified
+	  so that the cache operation has the desired effect.
+
+	  Note that the workaround is only valid on processors that do
+	  not perform speculative loads into the D-cache. For such
+	  processors, if cache maintenance operations are not broadcast
+	  in hardware, other workarounds are needed (e.g. cache
+	  maintenance broadcasting in software via FIQ).
+
 config OUTER_CACHE
 	bool
 
@@ -794,6 +813,8 @@ config ARM_L1_CACHE_SHIFT
 
 config ARM_DMA_MEM_BUFFERABLE
 	bool "Use non-cacheable memory for DMA" if CPU_V6 && !CPU_V7
+	depends on !(MACH_REALVIEW_PB1176 || REALVIEW_EB_ARM11MP || \
+		     MACH_REALVIEW_PB11MP)
 	default y if CPU_V6 || CPU_V7
 	help
 	  Historically, the kernel has used strongly ordered mappings to
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index e46ecd8..86aa689 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -211,8 +211,9 @@ v6_dma_inv_range:
 	mcrne	p15, 0, r1, c7, c15, 1		@ clean & invalidate unified line
 #endif
 1:
-#ifdef CONFIG_SMP
-	str	r0, [r0]			@ write for ownership
+#ifdef CONFIG_DMA_CACHE_RWFO
+	ldr	r2, [r0]			@ read for ownership
+	str	r2, [r0]			@ write for ownership
 #endif
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D line
@@ -234,7 +235,7 @@ v6_dma_inv_range:
 v6_dma_clean_range:
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
-#ifdef CONFIG_SMP
+#ifdef CONFIG_DMA_CACHE_RWFO
 	ldr	r2, [r0]			@ read for ownership
 #endif
 #ifdef HARVARD_CACHE
@@ -257,7 +258,7 @@ v6_dma_clean_range:
 ENTRY(v6_dma_flush_range)
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
-#ifdef CONFIG_SMP
+#ifdef CONFIG_DMA_CACHE_RWFO
 	ldr	r2, [r0]			@ read for ownership
 	str	r2, [r0]			@ write for ownership
 #endif
@@ -283,9 +284,13 @@ ENTRY(v6_dma_map_area)
 	add	r1, r1, r0
 	teq	r2, #DMA_FROM_DEVICE
 	beq	v6_dma_inv_range
+#ifndef CONFIG_DMA_CACHE_RWFO
+	b	v6_dma_clean_range
+#else
 	teq	r2, #DMA_TO_DEVICE
 	beq	v6_dma_clean_range
 	b	v6_dma_flush_range
+#endif
 ENDPROC(v6_dma_map_area)
 
 /*
@@ -295,6 +300,11 @@ ENDPROC(v6_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(v6_dma_unmap_area)
+#ifndef CONFIG_DMA_CACHE_RWFO
+	add	r1, r1, r0
+	teq	r2, #DMA_TO_DEVICE
+	bne	v6_dma_inv_range
+#endif
 	mov	pc, lr
 ENDPROC(v6_dma_unmap_area)
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 13fa536..9e7742f 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -24,15 +24,6 @@
 #include <asm/tlbflush.h>
 #include <asm/sizes.h>
 
-/* Sanity check size */
-#if (CONSISTENT_DMA_SIZE % SZ_2M)
-#error "CONSISTENT_DMA_SIZE must be multiple of 2MiB"
-#endif
-
-#define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
-#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
-#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)
-
 static u64 get_coherent_dma_mask(struct device *dev)
 {
 	u64 mask = ISA_DMA_THRESHOLD;
@@ -123,6 +114,15 @@ static void __dma_free_buffer(struct page *page, size_t size)
 }
 
 #ifdef CONFIG_MMU
+/* Sanity check size */
+#if (CONSISTENT_DMA_SIZE % SZ_2M)
+#error "CONSISTENT_DMA_SIZE must be multiple of 2MiB"
+#endif
+
+#define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
+#define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
+#define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)
+
 /*
  * These are the page tables (2MB each) covering uncached, DMA consistent allocations
  */
diff --git a/arch/arm/plat-omap/dmtimer.c b/arch/arm/plat-omap/dmtimer.c
index c64875f..44bafda 100644
--- a/arch/arm/plat-omap/dmtimer.c
+++ b/arch/arm/plat-omap/dmtimer.c
@@ -541,11 +541,11 @@ void omap_dm_timer_stop(struct omap_dm_timer *timer)
 		  * timer is stopped
 		  */
 		udelay(3500000 / clk_get_rate(timer->fclk) + 1);
-		/* Ack possibly pending interrupt */
-		omap_dm_timer_write_reg(timer, OMAP_TIMER_STAT_REG,
-				OMAP_TIMER_INT_OVERFLOW);
 #endif
 	}
+	/* Ack possibly pending interrupt */
+	omap_dm_timer_write_reg(timer, OMAP_TIMER_STAT_REG,
+			OMAP_TIMER_INT_OVERFLOW);
 }
 EXPORT_SYMBOL_GPL(omap_dm_timer_stop);
 
diff --git a/arch/arm/plat-omap/gpio.c b/arch/arm/plat-omap/gpio.c
index 393e921..9b7e354 100644
--- a/arch/arm/plat-omap/gpio.c
+++ b/arch/arm/plat-omap/gpio.c
@@ -673,6 +673,7 @@ static void _set_gpio_debounce(struct gpio_bank *bank, unsigned gpio,
 		if (cpu_is_omap34xx() || cpu_is_omap44xx())
 			clk_disable(bank->dbck);
 	}
+	bank->dbck_enable_mask = val;
 
 	__raw_writel(val, reg);
 }
diff --git a/arch/arm/plat-omap/iovmm.c b/arch/arm/plat-omap/iovmm.c
index e43983b..8ce0de2 100644
--- a/arch/arm/plat-omap/iovmm.c
+++ b/arch/arm/plat-omap/iovmm.c
@@ -140,8 +140,10 @@ static struct sg_table *sgtable_alloc(const size_t bytes, u32 flags)
 		return ERR_PTR(-ENOMEM);
 
 	err = sg_alloc_table(sgt, nr_entries, GFP_KERNEL);
-	if (err)
+	if (err) {
+		kfree(sgt);
 		return ERR_PTR(err);
+	}
 
 	pr_debug("%s: sgt:%p(%d entries)\n", __func__, sgt, nr_entries);
 
diff --git a/arch/arm/plat-pxa/Makefile b/arch/arm/plat-pxa/Makefile
index 6187edf..a17cc0c 100644
--- a/arch/arm/plat-pxa/Makefile
+++ b/arch/arm/plat-pxa/Makefile
@@ -2,8 +2,9 @@
 # Makefile for code common across different PXA processor families
 #
 
-obj-y	:= dma.o pmu.o
+obj-y	:= dma.o
 
+obj-$(CONFIG_ARCH_PXA)		+= pmu.o
 obj-$(CONFIG_GENERIC_GPIO)	+= gpio.o
 obj-$(CONFIG_PXA3xx)		+= mfp.o
 obj-$(CONFIG_ARCH_MMP)		+= mfp.o
diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c
index 5dfd916..7b3cdc6 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -121,7 +121,7 @@ static inline void down_spin(struct spinaphore *ss)
 	ia64_invala();
 
 	for (;;) {
-		asm volatile ("ld4.c.nc %0=[%1]" : "=r"(serve) : "r"(&ss->serve) : "memory");
+		asm volatile ("ld8.c.nc %0=[%1]" : "=r"(serve) : "r"(&ss->serve) : "memory");
 		if (time_before(t, serve))
 			return;
 		cpu_relax();
diff --git a/arch/um/os-Linux/mem.c b/arch/um/os-Linux/mem.c
index 93a11d7..e696144 100644
--- a/arch/um/os-Linux/mem.c
+++ b/arch/um/os-Linux/mem.c
@@ -10,6 +10,7 @@
 #include <errno.h>
 #include <fcntl.h>
 #include <string.h>
+#include <sys/stat.h>
 #include <sys/mman.h>
 #include <sys/param.h>
 #include "init.h"
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index 611df11..c2897b7 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -102,8 +102,8 @@ static const u64 amd_perfmon_event_map[] =
   [PERF_COUNT_HW_INSTRUCTIONS]		= 0x00c0,
   [PERF_COUNT_HW_CACHE_REFERENCES]	= 0x0080,
   [PERF_COUNT_HW_CACHE_MISSES]		= 0x0081,
-  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c4,
-  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c5,
+  [PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= 0x00c2,
+  [PERF_COUNT_HW_BRANCH_MISSES]		= 0x00c3,
 };
 
 static u64 amd_pmu_event_map(int hw_event)
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 142d70c..725ef4d 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -526,6 +526,7 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs)
 dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 {
 	struct task_struct *tsk = current;
+	int user_icebp = 0;
 	unsigned long dr6;
 	int si_code;
 
@@ -534,6 +535,14 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 	/* Filter out all the reserved bits which are preset to 1 */
 	dr6 &= ~DR6_RESERVED;
 
+	/*
+	 * If dr6 has no reason to give us about the origin of this trap,
+	 * then it's very likely the result of an icebp/int01 trap.
+	 * User wants a sigtrap for that.
+	 */
+	if (!dr6 && user_mode(regs))
+		user_icebp = 1;
+
 	/* Catch kmemcheck conditions first of all! */
 	if ((dr6 & DR_STEP) && kmemcheck_trap(regs))
 		return;
@@ -575,7 +584,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code)
 		regs->flags &= ~X86_EFLAGS_TF;
 	}
 	si_code = get_si_code(tsk->thread.debugreg6);
-	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS))
+	if (tsk->thread.debugreg6 & (DR_STEP | DR_TRAP_BITS) || user_icebp)
 		send_sigtrap(tsk, regs, error_code, si_code);
 	preempt_conditional_cli(regs);