Merge branch 'pm-next' of ssh://master.kernel.org/pub/scm/linux/kernel/git/khilman/linux-omap-pm into omap-for-linus

196 files changed, 2673 insertions, 1994 deletions

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index cdd2a6e8a3b..8b61c936099 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2175,11 +2175,6 @@ and is between 256 and 4096 characters. It is defined in the file
 	reset_devices	[KNL] Force drivers to reset the underlying device
 			during initialization.
 
-	resource_alloc_from_bottom
-			Allocate new resources from the beginning of available
-			space, not the end.  If you need to use this, please
-			report a bug.
-
 	resume=		[SWSUSP]
 			Specify the partition device for software suspend
 
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 489e9bacd16..41cc7b30d7d 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -379,8 +379,8 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       zero)
 
   bool pm_runtime_suspended(struct device *dev);
-    - return true if the device's runtime PM status is 'suspended', or false
-      otherwise
+    - return true if the device's runtime PM status is 'suspended' and its
+      'power.disable_depth' field is equal to zero, or false otherwise
 
   void pm_runtime_allow(struct device *dev);
     - set the power.runtime_auto flag for the device and decrease its usage
diff --git a/Makefile b/Makefile
index 5aa44278d95..77044b7918a 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 37
-EXTRAVERSION = -rc6
+EXTRAVERSION = -rc7
 NAME = Flesh-Eating Bats with Fangs
 
 # *DOCUMENTATION*
diff --git a/arch/arm/mach-at91/Makefile b/arch/arm/mach-at91/Makefile
index 62d686f0b42..d13add71f72 100644
--- a/arch/arm/mach-at91/Makefile
+++ b/arch/arm/mach-at91/Makefile
@@ -65,7 +65,7 @@ obj-$(CONFIG_MACH_AT91SAM9G20EK) += board-sam9g20ek.o
 obj-$(CONFIG_MACH_CPU9G20)	+= board-cpu9krea.o
 obj-$(CONFIG_MACH_STAMP9G20)	+= board-stamp9g20.o
 obj-$(CONFIG_MACH_PORTUXG20)	+= board-stamp9g20.o
-obj-$(CONFIG_MACH_PCONTROL_G20)	+= board-pcontrol-g20.o
+obj-$(CONFIG_MACH_PCONTROL_G20)	+= board-pcontrol-g20.o board-stamp9g20.o
 
 # AT91SAM9260/AT91SAM9G20 board-specific support
 obj-$(CONFIG_MACH_SNAPPER_9260)	+= board-snapper9260.o
diff --git a/arch/arm/mach-at91/board-pcontrol-g20.c b/arch/arm/mach-at91/board-pcontrol-g20.c
index bba5a560e02..feb65787c30 100644
--- a/arch/arm/mach-at91/board-pcontrol-g20.c
+++ b/arch/arm/mach-at91/board-pcontrol-g20.c
@@ -31,6 +31,7 @@
 
 #include <mach/board.h>
 #include <mach/at91sam9_smc.h>
+#include <mach/stamp9g20.h>
 
 #include "sam9_smc.h"
 #include "generic.h"
@@ -38,11 +39,7 @@
 
 static void __init pcontrol_g20_map_io(void)
 {
-	/* Initialize processor: 18.432 MHz crystal */
-	at91sam9260_initialize(18432000);
-
-	/* DGBU on ttyS0. (Rx, Tx) only TTL -> JTAG connector X7 17,19 ) */
-	at91_register_uart(0, 0, 0);
+	stamp9g20_map_io();
 
 	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS) piggyback  A2 */
 	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS
@@ -54,9 +51,6 @@ static void __init pcontrol_g20_map_io(void)
 
 	/* USART2 on ttyS3. (Rx, Tx)  9bit-Bus  Multidrop-mode  X4 */
 	at91_register_uart(AT91SAM9260_ID_US4, 3, 0);
-
-	/* set serial console to ttyS0 (ie, DBGU) */
-	at91_set_serial_console(0);
 }
 
 
@@ -66,38 +60,6 @@ static void __init init_irq(void)
 }
 
 
-/*
- * NAND flash 512MiB 1,8V 8-bit, sector size 128 KiB
- */
-static struct atmel_nand_data __initdata nand_data = {
-	.ale		= 21,
-	.cle		= 22,
-	.rdy_pin	= AT91_PIN_PC13,
-	.enable_pin	= AT91_PIN_PC14,
-};
-
-/*
- * Bus timings; unit = 7.57ns
- */
-static struct sam9_smc_config __initdata nand_smc_config = {
-	.ncs_read_setup		= 0,
-	.nrd_setup		= 2,
-	.ncs_write_setup	= 0,
-	.nwe_setup		= 2,
-
-	.ncs_read_pulse		= 4,
-	.nrd_pulse		= 4,
-	.ncs_write_pulse	= 4,
-	.nwe_pulse		= 4,
-
-	.read_cycle		= 7,
-	.write_cycle		= 7,
-
-	.mode			= AT91_SMC_READMODE | AT91_SMC_WRITEMODE
-			| AT91_SMC_EXNWMODE_DISABLE | AT91_SMC_DBW_8,
-	.tdf_cycles		= 3,
-};
-
 static struct sam9_smc_config __initdata pcontrol_smc_config[2] = { {
 	.ncs_read_setup		= 16,
 	.nrd_setup		= 18,
@@ -138,14 +100,6 @@ static struct sam9_smc_config __initdata pcontrol_smc_config[2] = { {
 	.tdf_cycles		= 1,
 } };
 
-static void __init add_device_nand(void)
-{
-	/* configure chip-select 3 (NAND) */
-	sam9_smc_configure(3, &nand_smc_config);
-	at91_add_device_nand(&nand_data);
-}
-
-
 static void __init add_device_pcontrol(void)
 {
 	/* configure chip-select 4 (IO compatible to 8051  X4 ) */
@@ -156,23 +110,6 @@ static void __init add_device_pcontrol(void)
 
 
 /*
- * MCI (SD/MMC)
- * det_pin, wp_pin and vcc_pin are not connected
- */
-#if defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_ATMELMCI_MODULE)
-static struct mci_platform_data __initdata mmc_data = {
-	.slot[0] = {
-		.bus_width	= 4,
-	},
-};
-#else
-static struct at91_mmc_data __initdata mmc_data = {
-	.wire4		= 1,
-};
-#endif
-
-
-/*
  * USB Host port
  */
 static struct at91_usbh_data __initdata usbh_data = {
@@ -265,42 +202,13 @@ static struct spi_board_info pcontrol_g20_spi_devices[] = {
 };
 
 
-/*
- * Dallas 1-Wire  DS2431
- */
-static struct w1_gpio_platform_data w1_gpio_pdata = {
-	.pin		= AT91_PIN_PA29,
-	.is_open_drain	= 1,
-};
-
-static struct platform_device w1_device = {
-	.name			= "w1-gpio",
-	.id			= -1,
-	.dev.platform_data	= &w1_gpio_pdata,
-};
-
-static void add_wire1(void)
-{
-	at91_set_GPIO_periph(w1_gpio_pdata.pin, 1);
-	at91_set_multi_drive(w1_gpio_pdata.pin, 1);
-	platform_device_register(&w1_device);
-}
-
-
 static void __init pcontrol_g20_board_init(void)
 {
-	at91_add_device_serial();
-	add_device_nand();
-#if defined(CONFIG_MMC_ATMELMCI) || defined(CONFIG_MMC_ATMELMCI_MODULE)
-	at91_add_device_mci(0, &mmc_data);
-#else
-	at91_add_device_mmc(0, &mmc_data);
-#endif
+	stamp9g20_board_init();
 	at91_add_device_usbh(&usbh_data);
 	at91_add_device_eth(&macb_data);
 	at91_add_device_i2c(pcontrol_g20_i2c_devices,
 		ARRAY_SIZE(pcontrol_g20_i2c_devices));
-	add_wire1();
 	add_device_pcontrol();
 	at91_add_device_spi(pcontrol_g20_spi_devices,
 		ARRAY_SIZE(pcontrol_g20_spi_devices));
diff --git a/arch/arm/mach-at91/board-stamp9g20.c b/arch/arm/mach-at91/board-stamp9g20.c
index 5206eef4a67..f8902b11896 100644
--- a/arch/arm/mach-at91/board-stamp9g20.c
+++ b/arch/arm/mach-at91/board-stamp9g20.c
@@ -32,7 +32,7 @@
 #include "generic.h"
 
 
-static void __init portuxg20_map_io(void)
+void __init stamp9g20_map_io(void)
 {
 	/* Initialize processor: 18.432 MHz crystal */
 	at91sam9260_initialize(18432000);
@@ -40,6 +40,24 @@ static void __init portuxg20_map_io(void)
 	/* DGBU on ttyS0. (Rx & Tx only) */
 	at91_register_uart(0, 0, 0);
 
+	/* set serial console to ttyS0 (ie, DBGU) */
+	at91_set_serial_console(0);
+}
+
+static void __init stamp9g20evb_map_io(void)
+{
+	stamp9g20_map_io();
+
+	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */
+	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS
+						| ATMEL_UART_DTR | ATMEL_UART_DSR
+						| ATMEL_UART_DCD | ATMEL_UART_RI);
+}
+
+static void __init portuxg20_map_io(void)
+{
+	stamp9g20_map_io();
+
 	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */
 	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS
 						| ATMEL_UART_DTR | ATMEL_UART_DSR
@@ -56,26 +74,6 @@ static void __init portuxg20_map_io(void)
 
 	/* USART5 on ttyS6. (Rx, Tx only) */
 	at91_register_uart(AT91SAM9260_ID_US5, 6, 0);
-
-	/* set serial console to ttyS0 (ie, DBGU) */
-	at91_set_serial_console(0);
-}
-
-static void __init stamp9g20_map_io(void)
-{
-	/* Initialize processor: 18.432 MHz crystal */
-	at91sam9260_initialize(18432000);
-
-	/* DGBU on ttyS0. (Rx & Tx only) */
-	at91_register_uart(0, 0, 0);
-
-	/* USART0 on ttyS1. (Rx, Tx, CTS, RTS, DTR, DSR, DCD, RI) */
-	at91_register_uart(AT91SAM9260_ID_US0, 1, ATMEL_UART_CTS | ATMEL_UART_RTS
-						| ATMEL_UART_DTR | ATMEL_UART_DSR
-						| ATMEL_UART_DCD | ATMEL_UART_RI);
-
-	/* set serial console to ttyS0 (ie, DBGU) */
-	at91_set_serial_console(0);
 }
 
 static void __init init_irq(void)
@@ -156,7 +154,7 @@ static struct at91_udc_data __initdata portuxg20_udc_data = {
 	.pullup_pin	= 0,		/* pull-up driven by UDC */
 };
 
-static struct at91_udc_data __initdata stamp9g20_udc_data = {
+static struct at91_udc_data __initdata stamp9g20evb_udc_data = {
 	.vbus_pin	= AT91_PIN_PA22,
 	.pullup_pin	= 0,		/* pull-up driven by UDC */
 };
@@ -190,7 +188,7 @@ static struct gpio_led portuxg20_leds[] = {
 	}
 };
 
-static struct gpio_led stamp9g20_leds[] = {
+static struct gpio_led stamp9g20evb_leds[] = {
 	{
 		.name			= "D8",
 		.gpio			= AT91_PIN_PB18,
@@ -250,7 +248,7 @@ void add_w1(void)
 }
 
 
-static void __init generic_board_init(void)
+void __init stamp9g20_board_init(void)
 {
 	/* Serial */
 	at91_add_device_serial();
@@ -262,34 +260,40 @@ static void __init generic_board_init(void)
 #else
 	at91_add_device_mmc(0, &mmc_data);
 #endif
-	/* USB Host */
-	at91_add_device_usbh(&usbh_data);
-	/* Ethernet */
-	at91_add_device_eth(&macb_data);
-	/* I2C */
-	at91_add_device_i2c(NULL, 0);
 	/* W1 */
 	add_w1();
 }
 
 static void __init portuxg20_board_init(void)
 {
-	generic_board_init();
-	/* SPI */
-	at91_add_device_spi(portuxg20_spi_devices, ARRAY_SIZE(portuxg20_spi_devices));
+	stamp9g20_board_init();
+	/* USB Host */
+	at91_add_device_usbh(&usbh_data);
 	/* USB Device */
 	at91_add_device_udc(&portuxg20_udc_data);
+	/* Ethernet */
+	at91_add_device_eth(&macb_data);
+	/* I2C */
+	at91_add_device_i2c(NULL, 0);
+	/* SPI */
+	at91_add_device_spi(portuxg20_spi_devices, ARRAY_SIZE(portuxg20_spi_devices));
 	/* LEDs */
 	at91_gpio_leds(portuxg20_leds, ARRAY_SIZE(portuxg20_leds));
 }
 
-static void __init stamp9g20_board_init(void)
+static void __init stamp9g20evb_board_init(void)
 {
-	generic_board_init();
+	stamp9g20_board_init();
+	/* USB Host */
+	at91_add_device_usbh(&usbh_data);
 	/* USB Device */
-	at91_add_device_udc(&stamp9g20_udc_data);
+	at91_add_device_udc(&stamp9g20evb_udc_data);
+	/* Ethernet */
+	at91_add_device_eth(&macb_data);
+	/* I2C */
+	at91_add_device_i2c(NULL, 0);
 	/* LEDs */
-	at91_gpio_leds(stamp9g20_leds, ARRAY_SIZE(stamp9g20_leds));
+	at91_gpio_leds(stamp9g20evb_leds, ARRAY_SIZE(stamp9g20evb_leds));
 }
 
 MACHINE_START(PORTUXG20, "taskit PortuxG20")
@@ -305,7 +309,7 @@ MACHINE_START(STAMP9G20, "taskit Stamp9G20")
 	/* Maintainer: taskit GmbH */
 	.boot_params	= AT91_SDRAM_BASE + 0x100,
 	.timer		= &at91sam926x_timer,
-	.map_io		= stamp9g20_map_io,
+	.map_io		= stamp9g20evb_map_io,
 	.init_irq	= init_irq,
-	.init_machine	= stamp9g20_board_init,
+	.init_machine	= stamp9g20evb_board_init,
 MACHINE_END
diff --git a/arch/arm/mach-at91/clock.c b/arch/arm/mach-at91/clock.c
index 7525cee3983..9113da6845f 100644
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@@ -658,7 +658,7 @@ static void __init at91_upll_usbfs_clock_init(unsigned long main_clock)
 	/* Now set uhpck values */
 	uhpck.parent = &utmi_clk;
 	uhpck.pmc_mask = AT91SAM926x_PMC_UHP;
-	uhpck.rate_hz = utmi_clk.parent->rate_hz;
+	uhpck.rate_hz = utmi_clk.rate_hz;
 	uhpck.rate_hz /= 1 + ((at91_sys_read(AT91_PMC_USB) & AT91_PMC_OHCIUSBDIV) >> 8);
 }
 
diff --git a/arch/arm/mach-at91/include/mach/stamp9g20.h b/arch/arm/mach-at91/include/mach/stamp9g20.h
new file mode 100644
index 00000000000..6120f9c46d5
--- /dev/null
+++ b/arch/arm/mach-at91/include/mach/stamp9g20.h
@@ -0,0 +1,7 @@
+#ifndef __MACH_STAMP9G20_H
+#define __MACH_STAMP9G20_H
+
+void stamp9g20_map_io(void);
+void stamp9g20_board_init(void);
+
+#endif
diff --git a/arch/arm/mach-omap2/control.c b/arch/arm/mach-omap2/control.c
index 1fa3294b604..0269bb055b6 100644
--- a/arch/arm/mach-omap2/control.c
+++ b/arch/arm/mach-omap2/control.c
@@ -239,9 +239,19 @@ void omap3_save_scratchpad_contents(void)
 	struct omap3_scratchpad_prcm_block prcm_block_contents;
 	struct omap3_scratchpad_sdrc_block sdrc_block_contents;
 
-	/* Populate the Scratchpad contents */
+	/*
+	 * Populate the Scratchpad contents
+	 *
+	 * The "get_*restore_pointer" functions are used to provide a
+	 * physical restore address where the ROM code jumps while waking
+	 * up from MPU OFF/OSWR state.
+	 * The restore pointer is stored into the scratchpad.
+	 */
 	scratchpad_contents.boot_config_ptr = 0x0;
-	if (omap_rev() != OMAP3430_REV_ES3_0 &&
+	if (cpu_is_omap3630())
+		scratchpad_contents.public_restore_ptr =
+			virt_to_phys(get_omap3630_restore_pointer());
+	else if (omap_rev() != OMAP3430_REV_ES3_0 &&
 					omap_rev() != OMAP3430_REV_ES3_1)
 		scratchpad_contents.public_restore_ptr =
 			virt_to_phys(get_restore_pointer());
@@ -474,4 +484,12 @@ void omap3_control_restore_context(void)
 	omap_ctrl_writel(control_context.csi, OMAP343X_CONTROL_CSI);
 	return;
 }
+
+void omap3630_ctrl_disable_rta(void)
+{
+	if (!cpu_is_omap3630())
+		return;
+	omap_ctrl_writel(OMAP36XX_RTA_DISABLE, OMAP36XX_CONTROL_MEM_RTA_CTRL);
+}
+
 #endif /* CONFIG_ARCH_OMAP3 && CONFIG_PM */
diff --git a/arch/arm/mach-omap2/control.h b/arch/arm/mach-omap2/control.h
index b6c6b7c450b..6e5f7e512ff 100644
--- a/arch/arm/mach-omap2/control.h
+++ b/arch/arm/mach-omap2/control.h
@@ -204,6 +204,10 @@
 #define OMAP343X_CONTROL_WKUP_DEBOBS3 (OMAP343X_CONTROL_GENERAL_WKUP + 0x014)
 #define OMAP343X_CONTROL_WKUP_DEBOBS4 (OMAP343X_CONTROL_GENERAL_WKUP + 0x018)
 
+/* 36xx-only RTA - Retention till Accesss control registers and bits */
+#define OMAP36XX_CONTROL_MEM_RTA_CTRL	0x40C
+#define OMAP36XX_RTA_DISABLE		0x0
+
 /* 34xx D2D idle-related pins, handled by PM core */
 #define OMAP3_PADCONF_SAD2D_MSTANDBY   0x250
 #define OMAP3_PADCONF_SAD2D_IDLEACK    0x254
@@ -270,6 +274,8 @@
 #define OMAP343X_SCRATCHPAD_ROM		(OMAP343X_CTRL_BASE + 0x860)
 #define OMAP343X_SCRATCHPAD		(OMAP343X_CTRL_BASE + 0x910)
 #define OMAP343X_SCRATCHPAD_ROM_OFFSET	0x19C
+#define OMAP343X_SCRATCHPAD_REGADDR(reg)	OMAP2_L4_IO_ADDRESS(\
+						OMAP343X_SCRATCHPAD + reg)
 
 /* AM35XX_CONTROL_IPSS_CLK_CTRL bits */
 #define AM35XX_USBOTG_VBUSP_CLK_SHIFT   0
@@ -347,10 +353,11 @@ extern void omap3_save_scratchpad_contents(void);
 extern void omap3_clear_scratchpad_contents(void);
 extern u32 *get_restore_pointer(void);
 extern u32 *get_es3_restore_pointer(void);
+extern u32 *get_omap3630_restore_pointer(void);
 extern u32 omap3_arm_context[128];
 extern void omap3_control_save_context(void);
 extern void omap3_control_restore_context(void);
-
+extern void omap3630_ctrl_disable_rta(void);
 #else
 #define omap_ctrl_base_get()		0
 #define omap_ctrl_readb(x)		0
diff --git a/arch/arm/mach-omap2/cpuidle34xx.c b/arch/arm/mach-omap2/cpuidle34xx.c
index 0d50b45d041..0fb619c5258 100644
--- a/arch/arm/mach-omap2/cpuidle34xx.c
+++ b/arch/arm/mach-omap2/cpuidle34xx.c
@@ -293,25 +293,26 @@ select_state:
 DEFINE_PER_CPU(struct cpuidle_device, omap3_idle_dev);
 
 /**
- * omap3_cpuidle_update_states - Update the cpuidle states.
+ * omap3_cpuidle_update_states() - Update the cpuidle states
+ * @mpu_deepest_state:	Enable states upto and including this for mpu domain
+ * @core_deepest_state:	Enable states upto and including this for core domain
  *
- * Currently, this function toggles the validity of idle states based upon
- * the flag 'enable_off_mode'. When the flag is set all states are valid.
- * Else, states leading to OFF state set to be invalid.
+ * This goes through the list of states available and enables and disables the
+ * validity of C states based on deepest state that can be achieved for the
+ * variable domain
  */
-void omap3_cpuidle_update_states(void)
+void omap3_cpuidle_update_states(u32 mpu_deepest_state, u32 core_deepest_state)
 {
 	int i;
 
 	for (i = OMAP3_STATE_C1; i < OMAP3_MAX_STATES; i++) {
 		struct omap3_processor_cx *cx = &omap3_power_states[i];
 
-		if (enable_off_mode) {
+		if ((cx->mpu_state >= mpu_deepest_state) &&
+		    (cx->core_state >= core_deepest_state)) {
 			cx->valid = 1;
 		} else {
-			if ((cx->mpu_state == PWRDM_POWER_OFF) ||
-				(cx->core_state	== PWRDM_POWER_OFF))
-				cx->valid = 0;
+			cx->valid = 0;
 		}
 	}
 }
@@ -452,6 +453,18 @@ void omap_init_power_states(void)
 	omap3_power_states[OMAP3_STATE_C7].core_state = PWRDM_POWER_OFF;
 	omap3_power_states[OMAP3_STATE_C7].flags = CPUIDLE_FLAG_TIME_VALID |
 				CPUIDLE_FLAG_CHECK_BM;
+
+	/*
+	 * Erratum i583: implementation for ES rev < Es1.2 on 3630. We cannot
+	 * enable OFF mode in a stable form for previous revisions.
+	 * we disable C7 state as a result.
+	 */
+	if (IS_PM34XX_ERRATUM(PM_SDRC_WAKEUP_ERRATUM_i583)) {
+		omap3_power_states[OMAP3_STATE_C7].valid = 0;
+		cpuidle_params_table[OMAP3_STATE_C7].valid = 0;
+		WARN_ONCE(1, "%s: core off state C7 disabled due to i583\n",
+				__func__);
+	}
 }
 
 struct cpuidle_driver omap3_idle_driver = {
@@ -504,7 +517,10 @@ int __init omap3_idle_init(void)
 		return -EINVAL;
 	dev->state_count = count;
 
-	omap3_cpuidle_update_states();
+	if (enable_off_mode)
+		omap3_cpuidle_update_states(PWRDM_POWER_OFF, PWRDM_POWER_OFF);
+	else
+		omap3_cpuidle_update_states(PWRDM_POWER_RET, PWRDM_POWER_RET);
 
 	if (cpuidle_register_device(dev)) {
 		printk(KERN_ERR "%s: CPUidle register device failed\n",
diff --git a/arch/arm/mach-omap2/pm.c b/arch/arm/mach-omap2/pm.c
index 59ca03b0e69..6ec2ee12272 100644
--- a/arch/arm/mach-omap2/pm.c
+++ b/arch/arm/mach-omap2/pm.c
@@ -143,5 +143,5 @@ static int __init omap2_common_pm_init(void)
 
 	return 0;
 }
-device_initcall(omap2_common_pm_init);
+postcore_initcall(omap2_common_pm_init);
 
diff --git a/arch/arm/mach-omap2/pm.h b/arch/arm/mach-omap2/pm.h
index 0d75bfd1fdb..c04f7b50e26 100644
--- a/arch/arm/mach-omap2/pm.h
+++ b/arch/arm/mach-omap2/pm.h
@@ -58,7 +58,7 @@ extern u32 sleep_while_idle;
 #endif
 
 #if defined(CONFIG_CPU_IDLE)
-extern void omap3_cpuidle_update_states(void);
+extern void omap3_cpuidle_update_states(u32, u32);
 #endif
 
 #if defined(CONFIG_PM_DEBUG) && defined(CONFIG_DEBUG_FS)
@@ -80,9 +80,20 @@ extern void save_secure_ram_context(u32 *addr);
 extern void omap3_save_scratchpad_contents(void);
 
 extern unsigned int omap24xx_idle_loop_suspend_sz;
-extern unsigned int omap34xx_suspend_sz;
 extern unsigned int save_secure_ram_context_sz;
 extern unsigned int omap24xx_cpu_suspend_sz;
 extern unsigned int omap34xx_cpu_suspend_sz;
 
+#define PM_RTA_ERRATUM_i608		(1 << 0)
+#define PM_SDRC_WAKEUP_ERRATUM_i583	(1 << 1)
+
+#if defined(CONFIG_PM) && defined(CONFIG_ARCH_OMAP3)
+extern u16 pm34xx_errata;
+#define IS_PM34XX_ERRATUM(id)		(pm34xx_errata & (id))
+extern void enable_omap3630_toggle_l2_on_restore(void);
+#else
+#define IS_PM34XX_ERRATUM(id)		0
+static inline void enable_omap3630_toggle_l2_on_restore(void) { }
+#endif		/* defined(CONFIG_PM) && defined(CONFIG_ARCH_OMAP3) */
+
 #endif
diff --git a/arch/arm/mach-omap2/pm24xx.c b/arch/arm/mach-omap2/pm24xx.c
index aaeea49b9bd..aea7ced9a2f 100644
--- a/arch/arm/mach-omap2/pm24xx.c
+++ b/arch/arm/mach-omap2/pm24xx.c
@@ -301,14 +301,8 @@ out:
 
 static int omap2_pm_begin(suspend_state_t state)
 {
-	suspend_state = state;
-	return 0;
-}
-
-static int omap2_pm_prepare(void)
-{
-	/* We cannot sleep in idle until we have resumed */
 	disable_hlt();
+	suspend_state = state;
 	return 0;
 }
 
@@ -349,21 +343,15 @@ static int omap2_pm_enter(suspend_state_t state)
 	return ret;
 }
 
-static void omap2_pm_finish(void)
-{
-	enable_hlt();
-}
-
 static void omap2_pm_end(void)
 {
 	suspend_state = PM_SUSPEND_ON;
+	enable_hlt();
 }
 
 static struct platform_suspend_ops omap_pm_ops = {
 	.begin		= omap2_pm_begin,
-	.prepare	= omap2_pm_prepare,
 	.enter		= omap2_pm_enter,
-	.finish		= omap2_pm_finish,
 	.end		= omap2_pm_end,
 	.valid		= suspend_valid_only_mem,
 };
diff --git a/arch/arm/mach-omap2/pm34xx.c b/arch/arm/mach-omap2/pm34xx.c
index 648b8c50d02..c45b4fa1dee 100644
--- a/arch/arm/mach-omap2/pm34xx.c
+++ b/arch/arm/mach-omap2/pm34xx.c
@@ -68,6 +68,9 @@ static inline bool is_suspending(void)
 #define OMAP343X_TABLE_VALUE_OFFSET	   0xc0
 #define OMAP343X_CONTROL_REG_VALUE_OFFSET  0xc8
 
+/* pm34xx errata defined in pm.h */
+u16 pm34xx_errata;
+
 struct power_state {
 	struct powerdomain *pwrdm;
 	u32 next_state;
@@ -143,7 +146,7 @@ static void omap3_core_save_context(void)
 
 	/*
 	 * Force write last pad into memory, as this can fail in some
-	 * cases according to erratas 1.157, 1.185
+	 * cases according to errata 1.157, 1.185
 	 */
 	omap_ctrl_writel(omap_ctrl_readl(OMAP343X_PADCONF_ETK_D14),
 		OMAP343X_CONTROL_MEM_WKUP + 0x2a0);
@@ -430,7 +433,7 @@ void omap_sram_idle(void)
 	/*
 	* On EMU/HS devices ROM code restores a SRDC value
 	* from scratchpad which has automatic self refresh on timeout
-	* of AUTO_CNT = 1 enabled. This takes care of errata 1.142.
+	* of AUTO_CNT = 1 enabled. This takes care of erratum ID i443.
 	* Hence store/restore the SDRC_POWER register here.
 	*/
 	if (omap_rev() >= OMAP3430_REV_ES3_0 &&
@@ -529,12 +532,6 @@ out:
 }
 
 #ifdef CONFIG_SUSPEND
-static int omap3_pm_prepare(void)
-{
-	disable_hlt();
-	return 0;
-}
-
 static int omap3_pm_suspend(void)
 {
 	struct power_state *pwrst;
@@ -597,14 +594,10 @@ static int omap3_pm_enter(suspend_state_t unused)
 	return ret;
 }
 
-static void omap3_pm_finish(void)
-{
-	enable_hlt();
-}
-
 /* Hooks to enable / disable UART interrupts during suspend */
 static int omap3_pm_begin(suspend_state_t state)
 {
+	disable_hlt();
 	suspend_state = state;
 	omap_uart_enable_irqs(0);
 	return 0;
@@ -614,15 +607,14 @@ static void omap3_pm_end(void)
 {
 	suspend_state = PM_SUSPEND_ON;
 	omap_uart_enable_irqs(1);
+	enable_hlt();
 	return;
 }
 
 static struct platform_suspend_ops omap_pm_ops = {
 	.begin		= omap3_pm_begin,
 	.end		= omap3_pm_end,
-	.prepare	= omap3_pm_prepare,
 	.enter		= omap3_pm_enter,
-	.finish		= omap3_pm_finish,
 	.valid		= suspend_valid_only_mem,
 };
 #endif /* CONFIG_SUSPEND */
@@ -925,12 +917,29 @@ void omap3_pm_off_mode_enable(int enable)
 		state = PWRDM_POWER_RET;
 
 #ifdef CONFIG_CPU_IDLE
-	omap3_cpuidle_update_states();
+	/*
+	 * Erratum i583: implementation for ES rev < Es1.2 on 3630. We cannot
+	 * enable OFF mode in a stable form for previous revisions, restrict
+	 * instead to RET
+	 */
+	if (IS_PM34XX_ERRATUM(PM_SDRC_WAKEUP_ERRATUM_i583))
+		omap3_cpuidle_update_states(state, PWRDM_POWER_RET);
+	else
+		omap3_cpuidle_update_states(state, state);
 #endif
 
 	list_for_each_entry(pwrst, &pwrst_list, node) {
-		pwrst->next_state = state;
-		omap_set_pwrdm_state(pwrst->pwrdm, state);
+		if (IS_PM34XX_ERRATUM(PM_SDRC_WAKEUP_ERRATUM_i583) &&
+				pwrst->pwrdm == core_pwrdm &&
+				state == PWRDM_POWER_OFF) {
+			pwrst->next_state = PWRDM_POWER_RET;
+			WARN_ONCE(1,
+				"%s: Core OFF disabled due to errata i583\n",
+				__func__);
+		} else {
+			pwrst->next_state = state;
+		}
+		omap_set_pwrdm_state(pwrst->pwrdm, pwrst->next_state);
 	}
 }
 
@@ -1002,6 +1011,17 @@ void omap_push_sram_idle(void)
 				save_secure_ram_context_sz);
 }
 
+static void __init pm_errata_configure(void)
+{
+	if (cpu_is_omap3630()) {
+		pm34xx_errata |= PM_RTA_ERRATUM_i608;
+		/* Enable the l2 cache toggling in sleep logic */
+		enable_omap3630_toggle_l2_on_restore();
+		if (omap_rev() < OMAP3630_REV_ES1_2)
+			pm34xx_errata |= PM_SDRC_WAKEUP_ERRATUM_i583;
+	}
+}
+
 static int __init omap3_pm_init(void)
 {
 	struct power_state *pwrst, *tmp;
@@ -1011,6 +1031,8 @@ static int __init omap3_pm_init(void)
 	if (!cpu_is_omap34xx())
 		return -ENODEV;
 
+	pm_errata_configure();
+
 	printk(KERN_ERR "Power Management for TI OMAP3.\n");
 
 	/* XXX prcm_setup_regs needs to be before enabling hw
@@ -1058,6 +1080,14 @@ static int __init omap3_pm_init(void)
 	pm_idle = omap3_pm_idle;
 	omap3_idle_init();
 
+	/*
+	 * RTA is disabled during initialization as per erratum i608
+	 * it is safer to disable RTA by the bootloader, but we would like
+	 * to be doubly sure here and prevent any mishaps.
+	 */
+	if (IS_PM34XX_ERRATUM(PM_RTA_ERRATUM_i608))
+		omap3630_ctrl_disable_rta();
+
 	clkdm_add_wkdep(neon_clkdm, mpu_clkdm);
 	if (omap_type() != OMAP2_DEVICE_TYPE_GP) {
 		omap3_secure_ram_storage =
diff --git a/arch/arm/mach-omap2/pm44xx.c b/arch/arm/mach-omap2/pm44xx.c
index 54544b4fc76..6aff9961e35 100644
--- a/arch/arm/mach-omap2/pm44xx.c
+++ b/arch/arm/mach-omap2/pm44xx.c
@@ -31,12 +31,6 @@ struct power_state {
 static LIST_HEAD(pwrst_list);
 
 #ifdef CONFIG_SUSPEND
-static int omap4_pm_prepare(void)
-{
-	disable_hlt();
-	return 0;
-}
-
 static int omap4_pm_suspend(void)
 {
 	do_wfi();
@@ -59,28 +53,22 @@ static int omap4_pm_enter(suspend_state_t suspend_state)
 	return ret;
 }
 
-static void omap4_pm_finish(void)
-{
-	enable_hlt();
-	return;
-}
-
 static int omap4_pm_begin(suspend_state_t state)
 {
+	disable_hlt();
 	return 0;
 }
 
 static void omap4_pm_end(void)
 {
+	enable_hlt();
 	return;
 }
 
 static struct platform_suspend_ops omap_pm_ops = {
 	.begin		= omap4_pm_begin,
 	.end		= omap4_pm_end,
-	.prepare	= omap4_pm_prepare,
 	.enter		= omap4_pm_enter,
-	.finish		= omap4_pm_finish,
 	.valid		= suspend_valid_only_mem,
 };
 #endif /* CONFIG_SUSPEND */
diff --git a/arch/arm/mach-omap2/sdrc.h b/arch/arm/mach-omap2/sdrc.h
index 68f57bb67fc..b3f83799e6c 100644
--- a/arch/arm/mach-omap2/sdrc.h
+++ b/arch/arm/mach-omap2/sdrc.h
@@ -74,5 +74,4 @@ static inline u32 sms_read_reg(u16 reg)
  */
 #define SDRC_MPURATE_LOOPS		96
 
-
 #endif
diff --git a/arch/arm/mach-omap2/sleep34xx.S b/arch/arm/mach-omap2/sleep34xx.S
index 2fb205a7f28..e3b5cd76c54 100644
--- a/arch/arm/mach-omap2/sleep34xx.S
+++ b/arch/arm/mach-omap2/sleep34xx.S
@@ -1,6 +1,4 @@
 /*
- * linux/arch/arm/mach-omap2/sleep.S
- *
  * (C) Copyright 2007
  * Texas Instruments
  * Karthik Dasu <karthik-dp@ti.com>
@@ -26,6 +24,7 @@
  */
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <plat/sram.h>
 #include <mach/io.h>
 
 #include "cm.h"
@@ -33,21 +32,27 @@
 #include "sdrc.h"
 #include "control.h"
 
-#define SDRC_SCRATCHPAD_SEM_V	0xfa00291c
-
-#define PM_PREPWSTST_CORE_V	OMAP34XX_PRM_REGADDR(CORE_MOD, \
-				OMAP3430_PM_PREPWSTST)
-#define PM_PREPWSTST_CORE_P	0x48306AE8
-#define PM_PREPWSTST_MPU_V	OMAP34XX_PRM_REGADDR(MPU_MOD, \
-				OMAP3430_PM_PREPWSTST)
+/*
+ * Registers access definitions
+ */
+#define SDRC_SCRATCHPAD_SEM_OFFS	0xc
+#define SDRC_SCRATCHPAD_SEM_V	OMAP343X_SCRATCHPAD_REGADDR\
+					(SDRC_SCRATCHPAD_SEM_OFFS)
+#define PM_PREPWSTST_CORE_P	OMAP3430_PRM_BASE + CORE_MOD +\
+					OMAP3430_PM_PREPWSTST
 #define PM_PWSTCTRL_MPU_P	OMAP3430_PRM_BASE + MPU_MOD + OMAP2_PM_PWSTCTRL
 #define CM_IDLEST1_CORE_V	OMAP34XX_CM_REGADDR(CORE_MOD, CM_IDLEST1)
-#define SRAM_BASE_P		0x40200000
-#define CONTROL_STAT		0x480022F0
-#define SCRATCHPAD_MEM_OFFS	0x310 /* Move this as correct place is
-				       * available */
-#define SCRATCHPAD_BASE_P	(OMAP343X_CTRL_BASE + OMAP343X_CONTROL_MEM_WKUP\
-						+ SCRATCHPAD_MEM_OFFS)
+#define CM_IDLEST_CKGEN_V	OMAP34XX_CM_REGADDR(PLL_MOD, CM_IDLEST)
+#define SRAM_BASE_P		OMAP3_SRAM_PA
+#define CONTROL_STAT		OMAP343X_CTRL_BASE + OMAP343X_CONTROL_STATUS
+#define CONTROL_MEM_RTA_CTRL	(OMAP343X_CTRL_BASE +\
+					OMAP36XX_CONTROL_MEM_RTA_CTRL)
+
+/* Move this as correct place is available */
+#define SCRATCHPAD_MEM_OFFS	0x310
+#define SCRATCHPAD_BASE_P	(OMAP343X_CTRL_BASE +\
+					OMAP343X_CONTROL_MEM_WKUP +\
+					SCRATCHPAD_MEM_OFFS)
 #define SDRC_POWER_V		OMAP34XX_SDRC_REGADDR(SDRC_POWER)
 #define SDRC_SYSCONFIG_P	(OMAP343X_SDRC_BASE + SDRC_SYSCONFIG)
 #define SDRC_MR_0_P		(OMAP343X_SDRC_BASE + SDRC_MR_0)
@@ -59,48 +64,38 @@
 #define SDRC_DLLA_STATUS_V	OMAP34XX_SDRC_REGADDR(SDRC_DLLA_STATUS)
 #define SDRC_DLLA_CTRL_V	OMAP34XX_SDRC_REGADDR(SDRC_DLLA_CTRL)
 
-        .text
-/* Function to acquire the semaphore in scratchpad */
-ENTRY(lock_scratchpad_sem)
-	stmfd	sp!, {lr}	@ save registers on stack
-wait_sem:
-	mov	r0,#1
-	ldr	r1, sdrc_scratchpad_sem
-wait_loop:
-	ldr	r2, [r1]	@ load the lock value
-	cmp	r2, r0		@ is the lock free ?
-	beq	wait_loop	@ not free...
-	swp	r2, r0, [r1]	@ semaphore free so lock it and proceed
-	cmp	r2, r0		@ did we succeed ?
-	beq	wait_sem	@ no - try again
-	ldmfd	sp!, {pc}	@ restore regs and return
-sdrc_scratchpad_sem:
-        .word SDRC_SCRATCHPAD_SEM_V
-ENTRY(lock_scratchpad_sem_sz)
-        .word   . - lock_scratchpad_sem
 
-        .text
-/* Function to release the scratchpad semaphore */
-ENTRY(unlock_scratchpad_sem)
-	stmfd	sp!, {lr}	@ save registers on stack
-	ldr	r3, sdrc_scratchpad_sem
-	mov	r2,#0
-	str	r2,[r3]
-	ldmfd	sp!, {pc}	@ restore regs and return
-ENTRY(unlock_scratchpad_sem_sz)
-        .word   . - unlock_scratchpad_sem
+/*
+ * API functions
+ */
+
+/*
+ * The "get_*restore_pointer" functions are used to provide a
+ * physical restore address where the ROM code jumps while waking
+ * up from MPU OFF/OSWR state.
+ * The restore pointer is stored into the scratchpad.
+ */
 
 	.text
 /* Function call to get the restore pointer for resume from OFF */
 ENTRY(get_restore_pointer)
-        stmfd   sp!, {lr}     @ save registers on stack
+	stmfd	sp!, {lr}	@ save registers on stack
 	adr	r0, restore
-        ldmfd   sp!, {pc}     @ restore regs and return
+	ldmfd	sp!, {pc}	@ restore regs and return
 ENTRY(get_restore_pointer_sz)
-        .word   . - get_restore_pointer
+	.word	. - get_restore_pointer
 
 	.text
-/* Function call to get the restore pointer for for ES3 to resume from OFF */
+/* Function call to get the restore pointer for 3630 resume from OFF */
+ENTRY(get_omap3630_restore_pointer)
+	stmfd	sp!, {lr}	@ save registers on stack
+	adr	r0, restore_3630
+	ldmfd	sp!, {pc}	@ restore regs and return
+ENTRY(get_omap3630_restore_pointer_sz)
+	.word	. - get_omap3630_restore_pointer
+
+	.text
+/* Function call to get the restore pointer for ES3 to resume from OFF */
 ENTRY(get_es3_restore_pointer)
 	stmfd	sp!, {lr}	@ save registers on stack
 	adr	r0, restore_es3
@@ -108,54 +103,23 @@ ENTRY(get_es3_restore_pointer)
 ENTRY(get_es3_restore_pointer_sz)
 	.word	. - get_es3_restore_pointer
 
-ENTRY(es3_sdrc_fix)
-	ldr	r4, sdrc_syscfg		@ get config addr
-	ldr	r5, [r4]		@ get value
-	tst	r5, #0x100		@ is part access blocked
-	it	eq
-	biceq	r5, r5, #0x100		@ clear bit if set
-	str	r5, [r4]		@ write back change
-	ldr	r4, sdrc_mr_0		@ get config addr
-	ldr	r5, [r4]		@ get value
-	str	r5, [r4]		@ write back change
-	ldr	r4, sdrc_emr2_0		@ get config addr
-	ldr	r5, [r4]		@ get value
-	str	r5, [r4]		@ write back change
-	ldr	r4, sdrc_manual_0	@ get config addr
-	mov	r5, #0x2		@ autorefresh command
-	str	r5, [r4]		@ kick off refreshes
-	ldr	r4, sdrc_mr_1		@ get config addr
-	ldr	r5, [r4]		@ get value
-	str	r5, [r4]		@ write back change
-	ldr	r4, sdrc_emr2_1		@ get config addr
-	ldr	r5, [r4]		@ get value
-	str	r5, [r4]		@ write back change
-	ldr	r4, sdrc_manual_1	@ get config addr
-	mov	r5, #0x2		@ autorefresh command
-	str	r5, [r4]		@ kick off refreshes
-	bx	lr
-sdrc_syscfg:
-	.word	SDRC_SYSCONFIG_P
-sdrc_mr_0:
-	.word	SDRC_MR_0_P
-sdrc_emr2_0:
-	.word	SDRC_EMR2_0_P
-sdrc_manual_0:
-	.word	SDRC_MANUAL_0_P
-sdrc_mr_1:
-	.word	SDRC_MR_1_P
-sdrc_emr2_1:
-	.word	SDRC_EMR2_1_P
-sdrc_manual_1:
-	.word	SDRC_MANUAL_1_P
-ENTRY(es3_sdrc_fix_sz)
-	.word	. - es3_sdrc_fix
+	.text
+/*
+ * L2 cache needs to be toggled for stable OFF mode functionality on 3630.
+ * This function sets up a flag that will allow for this toggling to take
+ * place on 3630. Hopefully some version in the future may not need this.
+ */
+ENTRY(enable_omap3630_toggle_l2_on_restore)
+	stmfd	sp!, {lr}	@ save registers on stack
+	/* Setup so that we will disable and enable l2 */
+	mov	r1, #0x1
+	str	r1, l2dis_3630
+	ldmfd	sp!, {pc}	@ restore regs and return
 
+	.text
 /* Function to call rom code to save secure ram context */
 ENTRY(save_secure_ram_context)
 	stmfd	sp!, {r1-r12, lr}	@ save registers on stack
-save_secure_ram_debug:
-	/* b save_secure_ram_debug */	@ enable to debug save code
 	adr	r3, api_params		@ r3 points to parameters
 	str	r0, [r3,#0x4]		@ r0 has sdram address
 	ldr	r12, high_mask
@@ -185,35 +149,162 @@ ENTRY(save_secure_ram_context_sz)
 	.word	. - save_secure_ram_context
 
 /*
+ * ======================
+ * == Idle entry point ==
+ * ======================
+ */
+
+/*
  * Forces OMAP into idle state
  *
- * omap34xx_suspend() - This bit of code just executes the WFI
- * for normal idles.
+ * omap34xx_cpu_suspend() - This bit of code saves the CPU context if needed
+ * and executes the WFI instruction. Calling WFI effectively changes the
+ * power domains states to the desired target power states.
  *
- * Note: This code get's copied to internal SRAM at boot. When the OMAP
- *	 wakes up it continues execution at the point it went to sleep.
+ *
+ * Notes:
+ * - this code gets copied to internal SRAM at boot and after wake-up
+ *   from OFF mode. The execution pointer in SRAM is _omap_sram_idle.
+ * - when the OMAP wakes up it continues at different execution points
+ *   depending on the low power mode (non-OFF vs OFF modes),
+ *   cf. 'Resume path for xxx mode' comments.
  */
 ENTRY(omap34xx_cpu_suspend)
-	stmfd	sp!, {r0-r12, lr}		@ save registers on stack
-loop:
-	/*b	loop*/	@Enable to debug by stepping through code
-	/* r0 contains restore pointer in sdram */
-	/* r1 contains information about saving context */
-	ldr     r4, sdrc_power          @ read the SDRC_POWER register
-	ldr     r5, [r4]                @ read the contents of SDRC_POWER
-	orr     r5, r5, #0x40           @ enable self refresh on idle req
-	str     r5, [r4]                @ write back to SDRC_POWER register
+	stmfd	sp!, {r0-r12, lr}	@ save registers on stack
+
+	/*
+	 * r0 contains restore pointer in sdram
+	 * r1 contains information about saving context:
+	 *   0 - No context lost
+	 *   1 - Only L1 and logic lost
+	 *   2 - Only L2 lost
+	 *   3 - Both L1 and L2 lost
+	 */
 
+	/* Directly jump to WFI is the context save is not required */
 	cmp	r1, #0x0
-	/* If context save is required, do that and execute wfi */
-	bne	save_context_wfi
+	beq	omap3_do_wfi
+
+	/* Otherwise fall through to the save context code */
+save_context_wfi:
+	mov	r8, r0			@ Store SDRAM address in r8
+	mrc	p15, 0, r5, c1, c0, 1	@ Read Auxiliary Control Register
+	mov	r4, #0x1		@ Number of parameters for restore call
+	stmia	r8!, {r4-r5}		@ Push parameters for restore call
+	mrc	p15, 1, r5, c9, c0, 2	@ Read L2 AUX ctrl register
+	stmia	r8!, {r4-r5}		@ Push parameters for restore call
+
+        /* Check what that target sleep state is from r1 */
+	cmp	r1, #0x2		@ Only L2 lost, no need to save context
+	beq	clean_caches
+
+l1_logic_lost:
+	/* Store sp and spsr to SDRAM */
+	mov	r4, sp
+	mrs	r5, spsr
+	mov	r6, lr
+	stmia	r8!, {r4-r6}
+	/* Save all ARM registers */
+	/* Coprocessor access control register */
+	mrc	p15, 0, r6, c1, c0, 2
+	stmia	r8!, {r6}
+	/* TTBR0, TTBR1 and Translation table base control */
+	mrc	p15, 0, r4, c2, c0, 0
+	mrc	p15, 0, r5, c2, c0, 1
+	mrc	p15, 0, r6, c2, c0, 2
+	stmia	r8!, {r4-r6}
+	/*
+	 * Domain access control register, data fault status register,
+	 * and instruction fault status register
+	 */
+	mrc	p15, 0, r4, c3, c0, 0
+	mrc	p15, 0, r5, c5, c0, 0
+	mrc	p15, 0, r6, c5, c0, 1
+	stmia	r8!, {r4-r6}
+	/*
+	 * Data aux fault status register, instruction aux fault status,
+	 * data fault address register and instruction fault address register
+	 */
+	mrc	p15, 0, r4, c5, c1, 0
+	mrc	p15, 0, r5, c5, c1, 1
+	mrc	p15, 0, r6, c6, c0, 0
+	mrc	p15, 0, r7, c6, c0, 2
+	stmia	r8!, {r4-r7}
+	/*
+	 * user r/w thread and process ID, user r/o thread and process ID,
+	 * priv only thread and process ID, cache size selection
+	 */
+	mrc	p15, 0, r4, c13, c0, 2
+	mrc	p15, 0, r5, c13, c0, 3
+	mrc	p15, 0, r6, c13, c0, 4
+	mrc	p15, 2, r7, c0, c0, 0
+	stmia	r8!, {r4-r7}
+	/* Data TLB lockdown, instruction TLB lockdown registers */
+	mrc	p15, 0, r5, c10, c0, 0
+	mrc	p15, 0, r6, c10, c0, 1
+	stmia	r8!, {r5-r6}
+	/* Secure or non secure vector base address, FCSE PID, Context PID*/
+	mrc	p15, 0, r4, c12, c0, 0
+	mrc	p15, 0, r5, c13, c0, 0
+	mrc	p15, 0, r6, c13, c0, 1
+	stmia	r8!, {r4-r6}
+	/* Primary remap, normal remap registers */
+	mrc	p15, 0, r4, c10, c2, 0
+	mrc	p15, 0, r5, c10, c2, 1
+	stmia	r8!,{r4-r5}
+
+	/* Store current cpsr*/
+	mrs	r2, cpsr
+	stmia	r8!, {r2}
+
+	mrc	p15, 0, r4, c1, c0, 0
+	/* save control register */
+	stmia	r8!, {r4}
+
+clean_caches:
+	/*
+	 * Clean Data or unified cache to POU
+	 * How to invalidate only L1 cache???? - #FIX_ME#
+	 * mcr	p15, 0, r11, c7, c11, 1
+	 */
+	cmp	r1, #0x1 		@ Check whether L2 inval is required
+	beq	omap3_do_wfi
+
+clean_l2:
+	/*
+	 * jump out to kernel flush routine
+	 *  - reuse that code is better
+	 *  - it executes in a cached space so is faster than refetch per-block
+	 *  - should be faster and will change with kernel
+	 *  - 'might' have to copy address, load and jump to it
+	 */
+	ldr	r1, kernel_flush
+	mov	lr, pc
+	bx	r1
+
+omap3_do_wfi:
+	ldr	r4, sdrc_power		@ read the SDRC_POWER register
+	ldr	r5, [r4]		@ read the contents of SDRC_POWER
+	orr	r5, r5, #0x40		@ enable self refresh on idle req
+	str	r5, [r4]		@ write back to SDRC_POWER register
+
 	/* Data memory barrier and Data sync barrier */
 	mov	r1, #0
 	mcr	p15, 0, r1, c7, c10, 4
 	mcr	p15, 0, r1, c7, c10, 5
 
+/*
+ * ===================================
+ * == WFI instruction => Enter idle ==
+ * ===================================
+ */
 	wfi				@ wait for interrupt
 
+/*
+ * ===================================
+ * == Resume path for non-OFF modes ==
+ * ===================================
+ */
 	nop
 	nop
 	nop
@@ -226,9 +317,30 @@ loop:
 	nop
 	bl wait_sdrc_ok
 
-	ldmfd	sp!, {r0-r12, pc}		@ restore regs and return
+/*
+ * ===================================
+ * == Exit point from non-OFF modes ==
+ * ===================================
+ */
+	ldmfd	sp!, {r0-r12, pc}	@ restore regs and return
+
+
+/*
+ * ==============================
+ * == Resume path for OFF mode ==
+ * ==============================
+ */
+
+/*
+ * The restore_* functions are called by the ROM code
+ *  when back from WFI in OFF mode.
+ * Cf. the get_*restore_pointer functions.
+ *
+ *  restore_es3: applies to 34xx >= ES3.0
+ *  restore_3630: applies to 36xx
+ *  restore: common code for 3xxx
+ */
 restore_es3:
-	/*b restore_es3*/		@ Enable to debug restore code
 	ldr	r5, pm_prepwstst_core_p
 	ldr	r4, [r5]
 	and	r4, r4, #0x3
@@ -245,82 +357,117 @@ copy_to_sram:
 	bne	copy_to_sram
 	ldr	r1, sram_base
 	blx	r1
+	b	restore
+
+restore_3630:
+	ldr	r1, pm_prepwstst_core_p
+	ldr	r2, [r1]
+	and	r2, r2, #0x3
+	cmp	r2, #0x0	@ Check if previous power state of CORE is OFF
+	bne	restore
+	/* Disable RTA before giving control */
+	ldr	r1, control_mem_rta
+	mov	r2, #OMAP36XX_RTA_DISABLE
+	str	r2, [r1]
+
+	/* Fall through to common code for the remaining logic */
+
 restore:
-	/* b restore*/  @ Enable to debug restore code
-        /* Check what was the reason for mpu reset and store the reason in r9*/
-        /* 1 - Only L1 and logic lost */
-        /* 2 - Only L2 lost - In this case, we wont be here */
-        /* 3 - Both L1 and L2 lost */
-	ldr     r1, pm_pwstctrl_mpu
+	/*
+	 * Check what was the reason for mpu reset and store the reason in r9:
+	 *  0 - No context lost
+	 *  1 - Only L1 and logic lost
+	 *  2 - Only L2 lost - In this case, we wont be here
+	 *  3 - Both L1 and L2 lost
+	 */
+	ldr	r1, pm_pwstctrl_mpu
 	ldr	r2, [r1]
-	and     r2, r2, #0x3
-	cmp     r2, #0x0	@ Check if target power state was OFF or RET
-        moveq   r9, #0x3        @ MPU OFF => L1 and L2 lost
+	and	r2, r2, #0x3
+	cmp	r2, #0x0	@ Check if target power state was OFF or RET
+	moveq	r9, #0x3	@ MPU OFF => L1 and L2 lost
 	movne	r9, #0x1	@ Only L1 and L2 lost => avoid L2 invalidation
 	bne	logic_l1_restore
+
+	ldr	r0, l2dis_3630
+	cmp	r0, #0x1	@ should we disable L2 on 3630?
+	bne	skipl2dis
+	mrc	p15, 0, r0, c1, c0, 1
+	bic	r0, r0, #2	@ disable L2 cache
+	mcr	p15, 0, r0, c1, c0, 1
+skipl2dis:
 	ldr	r0, control_stat
 	ldr	r1, [r0]
 	and	r1, #0x700
 	cmp	r1, #0x300
 	beq	l2_inv_gp
-	mov	r0, #40		@ set service ID for PPA
-	mov	r12, r0		@ copy secure Service ID in r12
-	mov	r1, #0		@ set task id for ROM code in r1
-	mov	r2, #4		@ set some flags in r2, r6
+	mov	r0, #40			@ set service ID for PPA
+	mov	r12, r0			@ copy secure Service ID in r12
+	mov	r1, #0			@ set task id for ROM code in r1
+	mov	r2, #4			@ set some flags in r2, r6
 	mov	r6, #0xff
 	adr	r3, l2_inv_api_params	@ r3 points to dummy parameters
 	mcr	p15, 0, r0, c7, c10, 4	@ data write barrier
 	mcr	p15, 0, r0, c7, c10, 5	@ data memory barrier
 	.word	0xE1600071		@ call SMI monitor (smi #1)
 	/* Write to Aux control register to set some bits */
-	mov	r0, #42		@ set service ID for PPA
-	mov	r12, r0		@ copy secure Service ID in r12
-	mov	r1, #0		@ set task id for ROM code in r1
-	mov	r2, #4		@ set some flags in r2, r6
+	mov	r0, #42			@ set service ID for PPA
+	mov	r12, r0			@ copy secure Service ID in r12
+	mov	r1, #0			@ set task id for ROM code in r1
+	mov	r2, #4			@ set some flags in r2, r6
 	mov	r6, #0xff
 	ldr	r4, scratchpad_base
-	ldr	r3, [r4, #0xBC]	@ r3 points to parameters
+	ldr	r3, [r4, #0xBC]		@ r3 points to parameters
 	mcr	p15, 0, r0, c7, c10, 4	@ data write barrier
 	mcr	p15, 0, r0, c7, c10, 5	@ data memory barrier
 	.word	0xE1600071		@ call SMI monitor (smi #1)
 
 #ifdef CONFIG_OMAP3_L2_AUX_SECURE_SAVE_RESTORE
 	/* Restore L2 aux control register */
-	@ set service ID for PPA
+					@ set service ID for PPA
 	mov	r0, #CONFIG_OMAP3_L2_AUX_SECURE_SERVICE_SET_ID
-	mov	r12, r0		@ copy service ID in r12
-	mov	r1, #0		@ set task ID for ROM code in r1
-	mov	r2, #4		@ set some flags in r2, r6
+	mov	r12, r0			@ copy service ID in r12
+	mov	r1, #0			@ set task ID for ROM code in r1
+	mov	r2, #4			@ set some flags in r2, r6
 	mov	r6, #0xff
 	ldr	r4, scratchpad_base
 	ldr	r3, [r4, #0xBC]
-	adds	r3, r3, #8	@ r3 points to parameters
+	adds	r3, r3, #8		@ r3 points to parameters
 	mcr	p15, 0, r0, c7, c10, 4	@ data write barrier
 	mcr	p15, 0, r0, c7, c10, 5	@ data memory barrier
 	.word	0xE1600071		@ call SMI monitor (smi #1)
 #endif
 	b	logic_l1_restore
+
 l2_inv_api_params:
-	.word   0x1, 0x00
+	.word	0x1, 0x00
 l2_inv_gp:
 	/* Execute smi to invalidate L2 cache */
-	mov r12, #0x1                         @ set up to invalide L2
-smi:    .word 0xE1600070		@ Call SMI monitor (smieq)
+	mov r12, #0x1			@ set up to invalidate L2
+	.word 0xE1600070		@ Call SMI monitor (smieq)
 	/* Write to Aux control register to set some bits */
 	ldr	r4, scratchpad_base
 	ldr	r3, [r4,#0xBC]
 	ldr	r0, [r3,#4]
 	mov	r12, #0x3
-	.word 0xE1600070	@ Call SMI monitor (smieq)
+	.word	0xE1600070		@ Call SMI monitor (smieq)
 	ldr	r4, scratchpad_base
 	ldr	r3, [r4,#0xBC]
 	ldr	r0, [r3,#12]
 	mov	r12, #0x2
-	.word 0xE1600070	@ Call SMI monitor (smieq)
+	.word	0xE1600070		@ Call SMI monitor (smieq)
 logic_l1_restore:
+	ldr	r1, l2dis_3630
+	cmp	r1, #0x1		@ Test if L2 re-enable needed on 3630
+	bne	skipl2reen
+	mrc	p15, 0, r1, c1, c0, 1
+	orr	r1, r1, #2		@ re-enable L2 cache
+	mcr	p15, 0, r1, c1, c0, 1
+skipl2reen:
 	mov	r1, #0
-	/* Invalidate all instruction caches to PoU
-	 * and flush branch target cache */
+	/*
+	 * Invalidate all instruction caches to PoU
+	 * and flush branch target cache
+	 */
 	mcr	p15, 0, r1, c7, c5, 0
 
 	ldr	r4, scratchpad_base
@@ -341,33 +488,33 @@ logic_l1_restore:
 	MCR p15, 0, r6, c2, c0, 1
 	/* Translation table base control register */
 	MCR p15, 0, r7, c2, c0, 2
-	/*domain access Control Register */
+	/* Domain access Control Register */
 	MCR p15, 0, r8, c3, c0, 0
-	/* data fault status Register */
+	/* Data fault status Register */
 	MCR p15, 0, r9, c5, c0, 0
 
-	ldmia  r3!,{r4-r8}
-	/* instruction fault status Register */
+	ldmia	r3!,{r4-r8}
+	/* Instruction fault status Register */
 	MCR p15, 0, r4, c5, c0, 1
-	/*Data Auxiliary Fault Status Register */
+	/* Data Auxiliary Fault Status Register */
 	MCR p15, 0, r5, c5, c1, 0
-	/*Instruction Auxiliary Fault Status Register*/
+	/* Instruction Auxiliary Fault Status Register*/
 	MCR p15, 0, r6, c5, c1, 1
-	/*Data Fault Address Register */
+	/* Data Fault Address Register */
 	MCR p15, 0, r7, c6, c0, 0
-	/*Instruction Fault Address Register*/
+	/* Instruction Fault Address Register*/
 	MCR p15, 0, r8, c6, c0, 2
-	ldmia  r3!,{r4-r7}
+	ldmia	r3!,{r4-r7}
 
-	/* user r/w thread and process ID */
+	/* User r/w thread and process ID */
 	MCR p15, 0, r4, c13, c0, 2
-	/* user ro thread and process ID */
+	/* User ro thread and process ID */
 	MCR p15, 0, r5, c13, c0, 3
-	/*Privileged only thread and process ID */
+	/* Privileged only thread and process ID */
 	MCR p15, 0, r6, c13, c0, 4
-	/* cache size selection */
+	/* Cache size selection */
 	MCR p15, 2, r7, c0, c0, 0
-	ldmia  r3!,{r4-r8}
+	ldmia	r3!,{r4-r8}
 	/* Data TLB lockdown registers */
 	MCR p15, 0, r4, c10, c0, 0
 	/* Instruction TLB lockdown registers */
@@ -379,26 +526,27 @@ logic_l1_restore:
 	/* Context PID */
 	MCR p15, 0, r8, c13, c0, 1
 
-	ldmia  r3!,{r4-r5}
-	/* primary memory remap register */
+	ldmia	r3!,{r4-r5}
+	/* Primary memory remap register */
 	MCR p15, 0, r4, c10, c2, 0
-	/*normal memory remap register */
+	/* Normal memory remap register */
 	MCR p15, 0, r5, c10, c2, 1
 
 	/* Restore cpsr */
-	ldmia	r3!,{r4}	/*load CPSR from SDRAM*/
-	msr	cpsr, r4	/*store cpsr */
+	ldmia	r3!,{r4}		@ load CPSR from SDRAM
+	msr	cpsr, r4		@ store cpsr
 
 	/* Enabling MMU here */
-	mrc	p15, 0, r7, c2, c0, 2 /* Read TTBRControl */
-	/* Extract N (0:2) bits and decide whether to use TTBR0 or TTBR1*/
+	mrc	p15, 0, r7, c2, c0, 2 	@ Read TTBRControl
+	/* Extract N (0:2) bits and decide whether to use TTBR0 or TTBR1 */
 	and	r7, #0x7
 	cmp	r7, #0x0
 	beq	usettbr0
 ttbr_error:
-	/* More work needs to be done to support N[0:2] value other than 0
-	* So looping here so that the error can be detected
-	*/
+	/*
+	 * More work needs to be done to support N[0:2] value other than 0
+	 * So looping here so that the error can be detected
+	 */
 	b	ttbr_error
 usettbr0:
 	mrc	p15, 0, r2, c2, c0, 0
@@ -406,21 +554,25 @@ usettbr0:
 	and	r2, r5
 	mov	r4, pc
 	ldr	r5, table_index_mask
-	and	r4, r5 /* r4 = 31 to 20 bits of pc */
+	and	r4, r5			@ r4 = 31 to 20 bits of pc
 	/* Extract the value to be written to table entry */
 	ldr	r1, table_entry
-	add	r1, r1, r4 /* r1 has value to be written to table entry*/
+	/* r1 has the value to be written to table entry*/
+	add	r1, r1, r4
 	/* Getting the address of table entry to modify */
 	lsr	r4, #18
-	add	r2, r4 /* r2 has the location which needs to be modified */
+	/* r2 has the location which needs to be modified */
+	add	r2, r4
 	/* Storing previous entry of location being modified */
 	ldr	r5, scratchpad_base
 	ldr	r4, [r2]
 	str	r4, [r5, #0xC0]
 	/* Modify the table entry */
 	str	r1, [r2]
-	/* Storing address of entry being modified
-	 * - will be restored after enabling MMU */
+	/*
+	 * Storing address of entry being modified
+	 * - will be restored after enabling MMU
+	 */
 	ldr	r5, scratchpad_base
 	str	r2, [r5, #0xC4]
 
@@ -429,8 +581,11 @@ usettbr0:
 	mcr	p15, 0, r0, c7, c5, 6	@ Invalidate branch predictor array
 	mcr	p15, 0, r0, c8, c5, 0	@ Invalidate instruction TLB
 	mcr	p15, 0, r0, c8, c6, 0	@ Invalidate data TLB
-	/* Restore control register  but dont enable caches here*/
-	/* Caches will be enabled after restoring MMU table entry */
+	/*
+	 * Restore control register. This enables the MMU.
+	 * The caches and prediction are not enabled here, they
+	 * will be enabled after restoring the MMU table entry.
+	 */
 	ldmia	r3!, {r4}
 	/* Store previous value of control register in scratchpad */
 	str	r4, [r5, #0xC8]
@@ -438,212 +593,144 @@ usettbr0:
 	and	r4, r2
 	mcr	p15, 0, r4, c1, c0, 0
 
-	ldmfd	sp!, {r0-r12, pc}		@ restore regs and return
-save_context_wfi:
-	/*b	save_context_wfi*/	@ enable to debug save code
-	mov	r8, r0 /* Store SDRAM address in r8 */
-	mrc	p15, 0, r5, c1, c0, 1	@ Read Auxiliary Control Register
-	mov	r4, #0x1		@ Number of parameters for restore call
-	stmia	r8!, {r4-r5}		@ Push parameters for restore call
-	mrc	p15, 1, r5, c9, c0, 2	@ Read L2 AUX ctrl register
-	stmia	r8!, {r4-r5}		@ Push parameters for restore call
-        /* Check what that target sleep state is:stored in r1*/
-        /* 1 - Only L1 and logic lost */
-        /* 2 - Only L2 lost */
-        /* 3 - Both L1 and L2 lost */
-	cmp	r1, #0x2 /* Only L2 lost */
-	beq	clean_l2
-	cmp	r1, #0x1 /* L2 retained */
-	/* r9 stores whether to clean L2 or not*/
-	moveq	r9, #0x0 /* Dont Clean L2 */
-	movne	r9, #0x1 /* Clean L2 */
-l1_logic_lost:
-	/* Store sp and spsr to SDRAM */
-	mov	r4, sp
-	mrs	r5, spsr
-	mov	r6, lr
-	stmia	r8!, {r4-r6}
-	/* Save all ARM registers */
-	/* Coprocessor access control register */
-	mrc	p15, 0, r6, c1, c0, 2
-	stmia	r8!, {r6}
-	/* TTBR0, TTBR1 and Translation table base control */
-	mrc	p15, 0, r4, c2, c0, 0
-	mrc	p15, 0, r5, c2, c0, 1
-	mrc	p15, 0, r6, c2, c0, 2
-	stmia	r8!, {r4-r6}
-	/* Domain access control register, data fault status register,
-	and instruction fault status register */
-	mrc	p15, 0, r4, c3, c0, 0
-	mrc	p15, 0, r5, c5, c0, 0
-	mrc	p15, 0, r6, c5, c0, 1
-	stmia	r8!, {r4-r6}
-	/* Data aux fault status register, instruction aux fault status,
-	datat fault address register and instruction fault address register*/
-	mrc	p15, 0, r4, c5, c1, 0
-	mrc	p15, 0, r5, c5, c1, 1
-	mrc	p15, 0, r6, c6, c0, 0
-	mrc	p15, 0, r7, c6, c0, 2
-	stmia	r8!, {r4-r7}
-	/* user r/w thread and process ID, user r/o thread and process ID,
-	priv only thread and process ID, cache size selection */
-	mrc	p15, 0, r4, c13, c0, 2
-	mrc	p15, 0, r5, c13, c0, 3
-	mrc	p15, 0, r6, c13, c0, 4
-	mrc	p15, 2, r7, c0, c0, 0
-	stmia	r8!, {r4-r7}
-	/* Data TLB lockdown, instruction TLB lockdown registers */
-	mrc	p15, 0, r5, c10, c0, 0
-	mrc	p15, 0, r6, c10, c0, 1
-	stmia	r8!, {r5-r6}
-	/* Secure or non secure vector base address, FCSE PID, Context PID*/
-	mrc	p15, 0, r4, c12, c0, 0
-	mrc	p15, 0, r5, c13, c0, 0
-	mrc	p15, 0, r6, c13, c0, 1
-	stmia	r8!, {r4-r6}
-	/* Primary remap, normal remap registers */
-	mrc	p15, 0, r4, c10, c2, 0
-	mrc	p15, 0, r5, c10, c2, 1
-	stmia	r8!,{r4-r5}
+/*
+ * ==============================
+ * == Exit point from OFF mode ==
+ * ==============================
+ */
+	ldmfd	sp!, {r0-r12, pc}	@ restore regs and return
 
-	/* Store current cpsr*/
-	mrs	r2, cpsr
-	stmia	r8!, {r2}
 
-	mrc	p15, 0, r4, c1, c0, 0
-	/* save control register */
-	stmia	r8!, {r4}
-clean_caches:
-	/* Clean Data or unified cache to POU*/
-	/* How to invalidate only L1 cache???? - #FIX_ME# */
-	/* mcr	p15, 0, r11, c7, c11, 1 */
-	cmp	r9, #1 /* Check whether L2 inval is required or not*/
-	bne	skip_l2_inval
-clean_l2:
-	/* read clidr */
-	mrc     p15, 1, r0, c0, c0, 1
-	/* extract loc from clidr */
-	ands    r3, r0, #0x7000000
-	/* left align loc bit field */
-	mov     r3, r3, lsr #23
-	/* if loc is 0, then no need to clean */
-	beq     finished
-	/* start clean at cache level 0 */
-	mov     r10, #0
-loop1:
-	/* work out 3x current cache level */
-	add     r2, r10, r10, lsr #1
-	/* extract cache type bits from clidr*/
-	mov     r1, r0, lsr r2
-	/* mask of the bits for current cache only */
-	and     r1, r1, #7
-	/* see what cache we have at this level */
-	cmp     r1, #2
-	/* skip if no cache, or just i-cache */
-	blt     skip
-	/* select current cache level in cssr */
-	mcr     p15, 2, r10, c0, c0, 0
-	/* isb to sych the new cssr&csidr */
-	isb
-	/* read the new csidr */
-	mrc     p15, 1, r1, c0, c0, 0
-	/* extract the length of the cache lines */
-	and     r2, r1, #7
-	/* add 4 (line length offset) */
-	add     r2, r2, #4
-	ldr     r4, assoc_mask
-	/* find maximum number on the way size */
-	ands    r4, r4, r1, lsr #3
-	/* find bit position of way size increment */
-	clz     r5, r4
-	ldr     r7, numset_mask
-	/* extract max number of the index size*/
-	ands    r7, r7, r1, lsr #13
-loop2:
-	mov     r9, r4
-	/* create working copy of max way size*/
-loop3:
-	/* factor way and cache number into r11 */
-	orr     r11, r10, r9, lsl r5
-	/* factor index number into r11 */
-	orr     r11, r11, r7, lsl r2
-	/*clean & invalidate by set/way */
-	mcr     p15, 0, r11, c7, c10, 2
-	/* decrement the way*/
-	subs    r9, r9, #1
-	bge     loop3
-	/*decrement the index */
-	subs    r7, r7, #1
-	bge     loop2
-skip:
-	add     r10, r10, #2
-	/* increment cache number */
-	cmp     r3, r10
-	bgt     loop1
-finished:
-	/*swith back to cache level 0 */
-	mov     r10, #0
-	/* select current cache level in cssr */
-	mcr     p15, 2, r10, c0, c0, 0
-	isb
-skip_l2_inval:
-	/* Data memory barrier and Data sync barrier */
-	mov     r1, #0
-	mcr     p15, 0, r1, c7, c10, 4
-	mcr     p15, 0, r1, c7, c10, 5
+/*
+ * Internal functions
+ */
 
-	wfi                             @ wait for interrupt
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	nop
-	bl wait_sdrc_ok
-	/* restore regs and return */
-	ldmfd   sp!, {r0-r12, pc}
+/* This function implements the erratum ID i443 WA, applies to 34xx >= ES3.0 */
+	.text
+ENTRY(es3_sdrc_fix)
+	ldr	r4, sdrc_syscfg		@ get config addr
+	ldr	r5, [r4]		@ get value
+	tst	r5, #0x100		@ is part access blocked
+	it	eq
+	biceq	r5, r5, #0x100		@ clear bit if set
+	str	r5, [r4]		@ write back change
+	ldr	r4, sdrc_mr_0		@ get config addr
+	ldr	r5, [r4]		@ get value
+	str	r5, [r4]		@ write back change
+	ldr	r4, sdrc_emr2_0		@ get config addr
+	ldr	r5, [r4]		@ get value
+	str	r5, [r4]		@ write back change
+	ldr	r4, sdrc_manual_0	@ get config addr
+	mov	r5, #0x2		@ autorefresh command
+	str	r5, [r4]		@ kick off refreshes
+	ldr	r4, sdrc_mr_1		@ get config addr
+	ldr	r5, [r4]		@ get value
+	str	r5, [r4]		@ write back change
+	ldr	r4, sdrc_emr2_1		@ get config addr
+	ldr	r5, [r4]		@ get value
+	str	r5, [r4]		@ write back change
+	ldr	r4, sdrc_manual_1	@ get config addr
+	mov	r5, #0x2		@ autorefresh command
+	str	r5, [r4]		@ kick off refreshes
+	bx	lr
+
+sdrc_syscfg:
+	.word	SDRC_SYSCONFIG_P
+sdrc_mr_0:
+	.word	SDRC_MR_0_P
+sdrc_emr2_0:
+	.word	SDRC_EMR2_0_P
+sdrc_manual_0:
+	.word	SDRC_MANUAL_0_P
+sdrc_mr_1:
+	.word	SDRC_MR_1_P
+sdrc_emr2_1:
+	.word	SDRC_EMR2_1_P
+sdrc_manual_1:
+	.word	SDRC_MANUAL_1_P
+ENTRY(es3_sdrc_fix_sz)
+	.word	. - es3_sdrc_fix
+
+/*
+ * This function implements the erratum ID i581 WA:
+ *  SDRC state restore before accessing the SDRAM
+ *
+ * Only used at return from non-OFF mode. For OFF
+ * mode the ROM code configures the SDRC and
+ * the DPLL before calling the restore code directly
+ * from DDR.
+ */
 
 /* Make sure SDRC accesses are ok */
 wait_sdrc_ok:
-        ldr     r4, cm_idlest1_core
-        ldr     r5, [r4]
-        and     r5, r5, #0x2
-        cmp     r5, #0
-        bne     wait_sdrc_ok
-        ldr     r4, sdrc_power
-        ldr     r5, [r4]
-        bic     r5, r5, #0x40
-        str     r5, [r4]
+
+/* DPLL3 must be locked before accessing the SDRC. Maybe the HW ensures this */
+	ldr	r4, cm_idlest_ckgen
+wait_dpll3_lock:
+	ldr	r5, [r4]
+	tst	r5, #1
+	beq	wait_dpll3_lock
+
+	ldr	r4, cm_idlest1_core
+wait_sdrc_ready:
+	ldr	r5, [r4]
+	tst	r5, #0x2
+	bne	wait_sdrc_ready
+	/* allow DLL powerdown upon hw idle req */
+	ldr	r4, sdrc_power
+	ldr	r5, [r4]
+	bic	r5, r5, #0x40
+	str	r5, [r4]
+
+is_dll_in_lock_mode:
+	/* Is dll in lock mode? */
+	ldr	r4, sdrc_dlla_ctrl
+	ldr	r5, [r4]
+	tst	r5, #0x4
+	bxne	lr			@ Return if locked
+	/* wait till dll locks */
+wait_dll_lock_timed:
+	ldr	r4, wait_dll_lock_counter
+	add	r4, r4, #1
+	str	r4, wait_dll_lock_counter
+	ldr	r4, sdrc_dlla_status
+	/* Wait 20uS for lock */
+	mov	r6, #8
 wait_dll_lock:
-        /* Is dll in lock mode? */
-        ldr     r4, sdrc_dlla_ctrl
-        ldr     r5, [r4]
-        tst     r5, #0x4
-        bxne    lr
-        /* wait till dll locks */
-        ldr     r4, sdrc_dlla_status
-        ldr     r5, [r4]
-        and     r5, r5, #0x4
-        cmp     r5, #0x4
-        bne     wait_dll_lock
-        bx      lr
+	subs	r6, r6, #0x1
+	beq	kick_dll
+	ldr	r5, [r4]
+	and	r5, r5, #0x4
+	cmp	r5, #0x4
+	bne	wait_dll_lock
+	bx	lr			@ Return when locked
+
+	/* disable/reenable DLL if not locked */
+kick_dll:
+	ldr	r4, sdrc_dlla_ctrl
+	ldr	r5, [r4]
+	mov	r6, r5
+	bic	r6, #(1<<3)		@ disable dll
+	str	r6, [r4]
+	dsb
+	orr	r6, r6, #(1<<3)		@ enable dll
+	str	r6, [r4]
+	dsb
+	ldr	r4, kick_counter
+	add	r4, r4, #1
+	str	r4, kick_counter
+	b	wait_dll_lock_timed
 
 cm_idlest1_core:
 	.word	CM_IDLEST1_CORE_V
+cm_idlest_ckgen:
+	.word	CM_IDLEST_CKGEN_V
 sdrc_dlla_status:
 	.word	SDRC_DLLA_STATUS_V
 sdrc_dlla_ctrl:
 	.word	SDRC_DLLA_CTRL_V
-pm_prepwstst_core:
-	.word	PM_PREPWSTST_CORE_V
 pm_prepwstst_core_p:
 	.word	PM_PREPWSTST_CORE_P
-pm_prepwstst_mpu:
-	.word	PM_PREPWSTST_MPU_V
 pm_pwstctrl_mpu:
 	.word	PM_PWSTCTRL_MPU_P
 scratchpad_base:
@@ -651,13 +738,7 @@ scratchpad_base:
 sram_base:
 	.word	SRAM_BASE_P + 0x8000
 sdrc_power:
-	.word SDRC_POWER_V
-clk_stabilize_delay:
-	.word 0x000001FF
-assoc_mask:
-	.word	0x3ff
-numset_mask:
-	.word	0x7fff
+	.word	SDRC_POWER_V
 ttbrbit_mask:
 	.word	0xFFFFC000
 table_index_mask:
@@ -668,5 +749,20 @@ cache_pred_disable_mask:
 	.word	0xFFFFE7FB
 control_stat:
 	.word	CONTROL_STAT
+control_mem_rta:
+	.word	CONTROL_MEM_RTA_CTRL
+kernel_flush:
+	.word	v7_flush_dcache_all
+l2dis_3630:
+	.word	0
+	/*
+	 * When exporting to userspace while the counters are in SRAM,
+	 * these 2 words need to be at the end to facilitate retrival!
+	 */
+kick_counter:
+	.word	0
+wait_dll_lock_counter:
+	.word	0
+
 ENTRY(omap34xx_cpu_suspend_sz)
 	.word	. - omap34xx_cpu_suspend
diff --git a/arch/arm/mach-s3c2412/Kconfig b/arch/arm/mach-s3c2412/Kconfig
index fa2e5bffbb8..6983cb4d4ca 100644
--- a/arch/arm/mach-s3c2412/Kconfig
+++ b/arch/arm/mach-s3c2412/Kconfig
@@ -28,9 +28,16 @@ config S3C2412_DMA
 
 config S3C2412_PM
 	bool
+	select S3C2412_PM_SLEEP
 	help
 	  Internal config node to apply S3C2412 power management
 
+config S3C2412_PM_SLEEP
+	bool
+	help
+	  Internal config node to apply sleep for S3C2412 power management.
+	  Can be selected by another SoCs with similar sleep procedure.
+
 # Note, the S3C2412 IOtiming support is in plat-s3c24xx
 
 config S3C2412_CPUFREQ
diff --git a/arch/arm/mach-s3c2412/Makefile b/arch/arm/mach-s3c2412/Makefile
index 530ec46cbae..6c48a91ea39 100644
--- a/arch/arm/mach-s3c2412/Makefile
+++ b/arch/arm/mach-s3c2412/Makefile
@@ -14,7 +14,8 @@ obj-$(CONFIG_CPU_S3C2412)	+= irq.o
 obj-$(CONFIG_CPU_S3C2412)	+= clock.o
 obj-$(CONFIG_CPU_S3C2412)	+= gpio.o
 obj-$(CONFIG_S3C2412_DMA)	+= dma.o
-obj-$(CONFIG_S3C2412_PM)	+= pm.o sleep.o
+obj-$(CONFIG_S3C2412_PM)	+= pm.o
+obj-$(CONFIG_S3C2412_PM_SLEEP)	+= sleep.o
 obj-$(CONFIG_S3C2412_CPUFREQ)	+= cpu-freq.o
 
 # Machine support
diff --git a/arch/arm/mach-s3c2416/Kconfig b/arch/arm/mach-s3c2416/Kconfig
index 27b3e7c9d61..df8d14974c9 100644
--- a/arch/arm/mach-s3c2416/Kconfig
+++ b/arch/arm/mach-s3c2416/Kconfig
@@ -27,6 +27,7 @@ config S3C2416_DMA
 
 config S3C2416_PM
 	bool
+	select S3C2412_PM_SLEEP
 	help
 	  Internal config node to apply S3C2416 power management
 
diff --git a/arch/arm/mach-s5pv210/mach-aquila.c b/arch/arm/mach-s5pv210/mach-aquila.c
index 28677caf361..461aa035afc 100644
--- a/arch/arm/mach-s5pv210/mach-aquila.c
+++ b/arch/arm/mach-s5pv210/mach-aquila.c
@@ -378,6 +378,12 @@ static struct max8998_regulator_data aquila_regulators[] = {
 static struct max8998_platform_data aquila_max8998_pdata = {
 	.num_regulators	= ARRAY_SIZE(aquila_regulators),
 	.regulators	= aquila_regulators,
+	.buck1_set1	= S5PV210_GPH0(3),
+	.buck1_set2	= S5PV210_GPH0(4),
+	.buck2_set3	= S5PV210_GPH0(5),
+	.buck1_max_voltage1 = 1200000,
+	.buck1_max_voltage2 = 1200000,
+	.buck2_max_voltage = 1200000,
 };
 #endif
 
diff --git a/arch/arm/mach-s5pv210/mach-goni.c b/arch/arm/mach-s5pv210/mach-goni.c
index b1dcf964a76..e22d5112fd4 100644
--- a/arch/arm/mach-s5pv210/mach-goni.c
+++ b/arch/arm/mach-s5pv210/mach-goni.c
@@ -518,6 +518,12 @@ static struct max8998_regulator_data goni_regulators[] = {
 static struct max8998_platform_data goni_max8998_pdata = {
 	.num_regulators	= ARRAY_SIZE(goni_regulators),
 	.regulators	= goni_regulators,
+	.buck1_set1	= S5PV210_GPH0(3),
+	.buck1_set2	= S5PV210_GPH0(4),
+	.buck2_set3	= S5PV210_GPH0(5),
+	.buck1_max_voltage1 = 1200000,
+	.buck1_max_voltage2 = 1200000,
+	.buck2_max_voltage = 1200000,
 };
 #endif
 
diff --git a/arch/arm/mach-shmobile/include/mach/entry-macro.S b/arch/arm/mach-shmobile/include/mach/entry-macro.S
index a285d13c741..f428c4db2b6 100644
--- a/arch/arm/mach-shmobile/include/mach/entry-macro.S
+++ b/arch/arm/mach-shmobile/include/mach/entry-macro.S
@@ -1,4 +1,5 @@
 /*
+ * Copyright (C) 2010 Magnus Damm
  * Copyright (C) 2008 Renesas Solutions Corp.
  *
  * This program is free software; you can redistribute it and/or modify
@@ -14,24 +15,45 @@
  * along with this program; if not, write to the Free Software
  * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
-#include <mach/hardware.h>
 #include <mach/irqs.h>
 
+#define INTCA_BASE	0xe6980000
+#define INTFLGA_OFFS	0x00000018 /* accept pending interrupt */
+#define INTEVTA_OFFS	0x00000020 /* vector number of accepted interrupt */
+#define INTLVLA_OFFS	0x00000030 /* priority level of accepted interrupt */
+#define INTLVLB_OFFS	0x00000034 /* previous priority level */
+
 	.macro  disable_fiq
 	.endm
 
 	.macro  get_irqnr_preamble, base, tmp
-	ldr     \base, =INTFLGA
+	ldr     \base, =INTCA_BASE
 	.endm
 
 	.macro  arch_ret_to_user, tmp1, tmp2
 	.endm
 
 	.macro  get_irqnr_and_base, irqnr, irqstat, base, tmp
-	ldr     \irqnr, [\base]
+	/* The single INTFLGA read access below results in the following:
+	 *
+	 * 1. INTLVLB is updated with old priority value from INTLVLA
+	 * 2. Highest priority interrupt is accepted
+	 * 3. INTLVLA is updated to contain priority of accepted interrupt
+	 * 4. Accepted interrupt vector is stored in INTFLGA and INTEVTA
+	 */
+	ldr     \irqnr, [\base, #INTFLGA_OFFS]
+
+	/* Restore INTLVLA with the value saved in INTLVLB.
+	 * This is required to support interrupt priorities properly.
+	 */
+	ldrb	\tmp, [\base, #INTLVLB_OFFS]
+	strb    \tmp, [\base, #INTLVLA_OFFS]
+
+	/* Handle invalid vector number case */
 	cmp	\irqnr, #0
 	beq	1000f
-	/* intevt to irq number */
+
+	/* Convert vector to irq number, same as the evt2irq() macro */
 	lsr	\irqnr, \irqnr, #0x5
 	subs	\irqnr, \irqnr, #16
 
diff --git a/arch/arm/mach-shmobile/include/mach/vmalloc.h b/arch/arm/mach-shmobile/include/mach/vmalloc.h
index 4aecf6e3a85..2b8fd8b942f 100644
--- a/arch/arm/mach-shmobile/include/mach/vmalloc.h
+++ b/arch/arm/mach-shmobile/include/mach/vmalloc.h
@@ -2,6 +2,6 @@
 #define __ASM_MACH_VMALLOC_H
 
 /* Vmalloc at ... - 0xe5ffffff */
-#define VMALLOC_END 0xe6000000
+#define VMALLOC_END 0xe6000000UL
 
 #endif /* __ASM_MACH_VMALLOC_H */
diff --git a/arch/arm/plat-omap/include/plat/sram.h b/arch/arm/plat-omap/include/plat/sram.h
index 5905100b29a..9967d5e855c 100644
--- a/arch/arm/plat-omap/include/plat/sram.h
+++ b/arch/arm/plat-omap/include/plat/sram.h
@@ -11,6 +11,7 @@
 #ifndef __ARCH_ARM_OMAP_SRAM_H
 #define __ARCH_ARM_OMAP_SRAM_H
 
+#ifndef __ASSEMBLY__
 extern void * omap_sram_push(void * start, unsigned long size);
 extern void omap_sram_reprogram_clock(u32 dpllctl, u32 ckctl);
 
@@ -74,4 +75,14 @@ extern void omap_push_sram_idle(void);
 static inline void omap_push_sram_idle(void) {}
 #endif /* CONFIG_PM */
 
+#endif /* __ASSEMBLY__ */
+
+/*
+ * OMAP2+: define the SRAM PA addresses.
+ * Used by the SRAM management code and the idle sleep code.
+ */
+#define OMAP2_SRAM_PA		0x40200000
+#define OMAP3_SRAM_PA           0x40200000
+#define OMAP4_SRAM_PA		0x40300000
+
 #endif
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index 819ea0cfb81..1a686c89d8d 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -41,15 +41,12 @@
 
 #define OMAP1_SRAM_PA		0x20000000
 #define OMAP1_SRAM_VA		VMALLOC_END
-#define OMAP2_SRAM_PA		0x40200000
-#define OMAP2_SRAM_PUB_PA	0x4020f800
+#define OMAP2_SRAM_PUB_PA	(OMAP2_SRAM_PA + 0xf800)
 #define OMAP2_SRAM_VA		0xfe400000
 #define OMAP2_SRAM_PUB_VA	(OMAP2_SRAM_VA + 0x800)
-#define OMAP3_SRAM_PA           0x40200000
 #define OMAP3_SRAM_VA           0xfe400000
-#define OMAP3_SRAM_PUB_PA       0x40208000
+#define OMAP3_SRAM_PUB_PA       (OMAP3_SRAM_PA + 0x8000)
 #define OMAP3_SRAM_PUB_VA       (OMAP3_SRAM_VA + 0x8000)
-#define OMAP4_SRAM_PA		0x40300000
 #define OMAP4_SRAM_VA		0xfe400000
 #define OMAP4_SRAM_PUB_PA	(OMAP4_SRAM_PA + 0x4000)
 #define OMAP4_SRAM_PUB_VA	(OMAP4_SRAM_VA + 0x4000)
diff --git a/arch/arm/plat-s3c24xx/Kconfig b/arch/arm/plat-s3c24xx/Kconfig
index 5a27b1b538f..eb105e61c74 100644
--- a/arch/arm/plat-s3c24xx/Kconfig
+++ b/arch/arm/plat-s3c24xx/Kconfig
@@ -8,7 +8,7 @@ config PLAT_S3C24XX
 	default y
 	select NO_IOPORT
 	select ARCH_REQUIRE_GPIOLIB
-	select S3C_DEVICE_NAND
+	select S3C_DEV_NAND
 	select S3C_GPIO_CFG_S3C24XX
 	help
 	  Base platform code for any Samsung S3C24XX device
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 67a2fa2caa4..0a9b5b8b2a1 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -19,6 +19,8 @@ config MIPS
 	select GENERIC_ATOMIC64 if !64BIT
 	select HAVE_DMA_ATTRS
 	select HAVE_DMA_API_DEBUG
+	select HAVE_GENERIC_HARDIRQS
+	select GENERIC_IRQ_PROBE
 
 menu "Machine selection"
 
@@ -1664,6 +1666,28 @@ config PAGE_SIZE_64KB
 
 endchoice
 
+config FORCE_MAX_ZONEORDER
+	int "Maximum zone order"
+	range 13 64 if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_32KB
+	default "13" if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_32KB
+	range 12 64 if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_16KB
+	default "12" if SYS_SUPPORTS_HUGETLBFS && PAGE_SIZE_16KB
+	range 11 64
+	default "11"
+	help
+	  The kernel memory allocator divides physically contiguous memory
+	  blocks into "zones", where each zone is a power of two number of
+	  pages.  This option selects the largest power of two that the kernel
+	  keeps in the memory allocator.  If you need to allocate very large
+	  blocks of physically contiguous memory, then you may need to
+	  increase this value.
+
+	  This config option is actually maximum order plus one. For example,
+	  a value of 11 means that the largest free memory block is 2^10 pages.
+
+	  The page size is not necessarily 4KB.  Keep this in mind
+	  when choosing a value for this option.
+
 config BOARD_SCACHE
 	bool
 
@@ -1922,20 +1946,6 @@ config CPU_R4400_WORKAROUNDS
 	bool
 
 #
-# Use the generic interrupt handling code in kernel/irq/:
-#
-config GENERIC_HARDIRQS
-	bool
-	default y
-
-config GENERIC_IRQ_PROBE
-	bool
-	default y
-
-config IRQ_PER_CPU
-	bool
-
-#
 # - Highmem only makes sense for the 32-bit kernel.
 # - The current highmem code will only work properly on physically indexed
 #   caches such as R3000, SB1, R7000 or those that look like they're virtually
diff --git a/arch/mips/alchemy/common/platform.c b/arch/mips/alchemy/common/platform.c
index 3691630931d..9e7814db3d0 100644
--- a/arch/mips/alchemy/common/platform.c
+++ b/arch/mips/alchemy/common/platform.c
@@ -27,6 +27,7 @@
 static void alchemy_8250_pm(struct uart_port *port, unsigned int state,
 			    unsigned int old_state)
 {
+#ifdef CONFIG_SERIAL_8250
 	switch (state) {
 	case 0:
 		if ((__raw_readl(port->membase + UART_MOD_CNTRL) & 3) != 3) {
@@ -49,6 +50,7 @@ static void alchemy_8250_pm(struct uart_port *port, unsigned int state,
 		serial8250_do_pm(port, state, old_state);
 		break;
 	}
+#endif
 }
 
 #define PORT(_base, _irq)					\
diff --git a/arch/mips/alchemy/devboards/prom.c b/arch/mips/alchemy/devboards/prom.c
index b30df5c97ad..baeb2138505 100644
--- a/arch/mips/alchemy/devboards/prom.c
+++ b/arch/mips/alchemy/devboards/prom.c
@@ -54,10 +54,9 @@ void __init prom_init(void)
 
 	prom_init_cmdline();
 	memsize_str = prom_getenv("memsize");
-	if (!memsize_str)
+	if (!memsize_str || strict_strtoul(memsize_str, 0, &memsize))
 		memsize = ALCHEMY_BOARD_DEFAULT_MEMSIZE;
-	else
-		strict_strtoul(memsize_str, 0, &memsize);
+
 	add_memory_region(0, memsize, BOOT_MEM_RAM);
 }
 
diff --git a/arch/mips/ar7/clock.c b/arch/mips/ar7/clock.c
index fc0e7154e8d..2ca4ada1c29 100644
--- a/arch/mips/ar7/clock.c
+++ b/arch/mips/ar7/clock.c
@@ -239,12 +239,12 @@ static void tnetd7300_set_clock(u32 shift, struct tnetd7300_clock *clock,
 	calculate(base_clock, frequency, &prediv, &postdiv, &mul);
 
 	writel(((prediv - 1) << PREDIV_SHIFT) | (postdiv - 1), &clock->ctrl);
-	msleep(1);
+	mdelay(1);
 	writel(4, &clock->pll);
 	while (readl(&clock->pll) & PLL_STATUS)
 		;
 	writel(((mul - 1) << MUL_SHIFT) | (0xff << 3) | 0x0e, &clock->pll);
-	msleep(75);
+	mdelay(75);
 }
 
 static void __init tnetd7300_init_clocks(void)
@@ -456,7 +456,7 @@ void clk_put(struct clk *clk)
 }
 EXPORT_SYMBOL(clk_put);
 
-int __init ar7_init_clocks(void)
+void __init ar7_init_clocks(void)
 {
 	switch (ar7_chip_id()) {
 	case AR7_CHIP_7100:
@@ -472,7 +472,4 @@ int __init ar7_init_clocks(void)
 	}
 	/* adjust vbus clock rate */
 	vbus_clk.rate = bus_clk.rate / 2;
-
-	return 0;
 }
-arch_initcall(ar7_init_clocks);
diff --git a/arch/mips/ar7/time.c b/arch/mips/ar7/time.c
index 5fb8a013408..22c93213b23 100644
--- a/arch/mips/ar7/time.c
+++ b/arch/mips/ar7/time.c
@@ -30,6 +30,9 @@ void __init plat_time_init(void)
 {
 	struct clk *cpu_clk;
 
+	/* Initialize ar7 clocks so the CPU clock frequency is correct */
+	ar7_init_clocks();
+
 	cpu_clk = clk_get(NULL, "cpu");
 	if (IS_ERR(cpu_clk)) {
 		printk(KERN_ERR "unable to get cpu clock\n");
diff --git a/arch/mips/bcm47xx/setup.c b/arch/mips/bcm47xx/setup.c
index b1aee33efd1..c95f90bf734 100644
--- a/arch/mips/bcm47xx/setup.c
+++ b/arch/mips/bcm47xx/setup.c
@@ -32,7 +32,6 @@
 #include <asm/reboot.h>
 #include <asm/time.h>
 #include <bcm47xx.h>
-#include <asm/fw/cfe/cfe_api.h>
 #include <asm/mach-bcm47xx/nvram.h>
 
 struct ssb_bus ssb_bcm47xx;
@@ -57,68 +56,112 @@ static void bcm47xx_machine_halt(void)
 		cpu_relax();
 }
 
-static void str2eaddr(char *str, char *dest)
+#define READ_FROM_NVRAM(_outvar, name, buf) \
+	if (nvram_getenv(name, buf, sizeof(buf)) >= 0)\
+		sprom->_outvar = simple_strtoul(buf, NULL, 0);
+
+static void bcm47xx_fill_sprom(struct ssb_sprom *sprom)
 {
-	int i = 0;
+	char buf[100];
+	u32 boardflags;
 
-	if (str == NULL) {
-		memset(dest, 0, 6);
-		return;
-	}
+	memset(sprom, 0, sizeof(struct ssb_sprom));
+
+	sprom->revision = 1; /* Fallback: Old hardware does not define this. */
+	READ_FROM_NVRAM(revision, "sromrev", buf);
+	if (nvram_getenv("il0macaddr", buf, sizeof(buf)) >= 0)
+		nvram_parse_macaddr(buf, sprom->il0mac);
+	if (nvram_getenv("et0macaddr", buf, sizeof(buf)) >= 0)
+		nvram_parse_macaddr(buf, sprom->et0mac);
+	if (nvram_getenv("et1macaddr", buf, sizeof(buf)) >= 0)
+		nvram_parse_macaddr(buf, sprom->et1mac);
+	READ_FROM_NVRAM(et0phyaddr, "et0phyaddr", buf);
+	READ_FROM_NVRAM(et1phyaddr, "et1phyaddr", buf);
+	READ_FROM_NVRAM(et0mdcport, "et0mdcport", buf);
+	READ_FROM_NVRAM(et1mdcport, "et1mdcport", buf);
+	READ_FROM_NVRAM(board_rev, "boardrev", buf);
+	READ_FROM_NVRAM(country_code, "ccode", buf);
+	READ_FROM_NVRAM(ant_available_a, "aa5g", buf);
+	READ_FROM_NVRAM(ant_available_bg, "aa2g", buf);
+	READ_FROM_NVRAM(pa0b0, "pa0b0", buf);
+	READ_FROM_NVRAM(pa0b1, "pa0b1", buf);
+	READ_FROM_NVRAM(pa0b2, "pa0b2", buf);
+	READ_FROM_NVRAM(pa1b0, "pa1b0", buf);
+	READ_FROM_NVRAM(pa1b1, "pa1b1", buf);
+	READ_FROM_NVRAM(pa1b2, "pa1b2", buf);
+	READ_FROM_NVRAM(pa1lob0, "pa1lob0", buf);
+	READ_FROM_NVRAM(pa1lob2, "pa1lob1", buf);
+	READ_FROM_NVRAM(pa1lob1, "pa1lob2", buf);
+	READ_FROM_NVRAM(pa1hib0, "pa1hib0", buf);
+	READ_FROM_NVRAM(pa1hib2, "pa1hib1", buf);
+	READ_FROM_NVRAM(pa1hib1, "pa1hib2", buf);
+	READ_FROM_NVRAM(gpio0, "wl0gpio0", buf);
+	READ_FROM_NVRAM(gpio1, "wl0gpio1", buf);
+	READ_FROM_NVRAM(gpio2, "wl0gpio2", buf);
+	READ_FROM_NVRAM(gpio3, "wl0gpio3", buf);
+	READ_FROM_NVRAM(maxpwr_bg, "pa0maxpwr", buf);
+	READ_FROM_NVRAM(maxpwr_al, "pa1lomaxpwr", buf);
+	READ_FROM_NVRAM(maxpwr_a, "pa1maxpwr", buf);
+	READ_FROM_NVRAM(maxpwr_ah, "pa1himaxpwr", buf);
+	READ_FROM_NVRAM(itssi_a, "pa1itssit", buf);
+	READ_FROM_NVRAM(itssi_bg, "pa0itssit", buf);
+	READ_FROM_NVRAM(tri2g, "tri2g", buf);
+	READ_FROM_NVRAM(tri5gl, "tri5gl", buf);
+	READ_FROM_NVRAM(tri5g, "tri5g", buf);
+	READ_FROM_NVRAM(tri5gh, "tri5gh", buf);
+	READ_FROM_NVRAM(rxpo2g, "rxpo2g", buf);
+	READ_FROM_NVRAM(rxpo5g, "rxpo5g", buf);
+	READ_FROM_NVRAM(rssisav2g, "rssisav2g", buf);
+	READ_FROM_NVRAM(rssismc2g, "rssismc2g", buf);
+	READ_FROM_NVRAM(rssismf2g, "rssismf2g", buf);
+	READ_FROM_NVRAM(bxa2g, "bxa2g", buf);
+	READ_FROM_NVRAM(rssisav5g, "rssisav5g", buf);
+	READ_FROM_NVRAM(rssismc5g, "rssismc5g", buf);
+	READ_FROM_NVRAM(rssismf5g, "rssismf5g", buf);
+	READ_FROM_NVRAM(bxa5g, "bxa5g", buf);
+	READ_FROM_NVRAM(cck2gpo, "cck2gpo", buf);
+	READ_FROM_NVRAM(ofdm2gpo, "ofdm2gpo", buf);
+	READ_FROM_NVRAM(ofdm5glpo, "ofdm5glpo", buf);
+	READ_FROM_NVRAM(ofdm5gpo, "ofdm5gpo", buf);
+	READ_FROM_NVRAM(ofdm5ghpo, "ofdm5ghpo", buf);
 
-	for (;;) {
-		dest[i++] = (char) simple_strtoul(str, NULL, 16);
-		str += 2;
-		if (!*str++ || i == 6)
-			break;
+	if (nvram_getenv("boardflags", buf, sizeof(buf)) >= 0) {
+		boardflags = simple_strtoul(buf, NULL, 0);
+		if (boardflags) {
+			sprom->boardflags_lo = (boardflags & 0x0000FFFFU);
+			sprom->boardflags_hi = (boardflags & 0xFFFF0000U) >> 16;
+		}
+	}
+	if (nvram_getenv("boardflags2", buf, sizeof(buf)) >= 0) {
+		boardflags = simple_strtoul(buf, NULL, 0);
+		if (boardflags) {
+			sprom->boardflags2_lo = (boardflags & 0x0000FFFFU);
+			sprom->boardflags2_hi = (boardflags & 0xFFFF0000U) >> 16;
+		}
 	}
 }
 
 static int bcm47xx_get_invariants(struct ssb_bus *bus,
 				   struct ssb_init_invariants *iv)
 {
-	char buf[100];
+	char buf[20];
 
 	/* Fill boardinfo structure */
 	memset(&(iv->boardinfo), 0 , sizeof(struct ssb_boardinfo));
 
-	if (cfe_getenv("boardvendor", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("boardvendor", buf, sizeof(buf)) >= 0)
+	if (nvram_getenv("boardvendor", buf, sizeof(buf)) >= 0)
+		iv->boardinfo.vendor = (u16)simple_strtoul(buf, NULL, 0);
+	else
+		iv->boardinfo.vendor = SSB_BOARDVENDOR_BCM;
+	if (nvram_getenv("boardtype", buf, sizeof(buf)) >= 0)
 		iv->boardinfo.type = (u16)simple_strtoul(buf, NULL, 0);
-	if (cfe_getenv("boardtype", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("boardtype", buf, sizeof(buf)) >= 0)
-		iv->boardinfo.type = (u16)simple_strtoul(buf, NULL, 0);
-	if (cfe_getenv("boardrev", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("boardrev", buf, sizeof(buf)) >= 0)
+	if (nvram_getenv("boardrev", buf, sizeof(buf)) >= 0)
 		iv->boardinfo.rev = (u16)simple_strtoul(buf, NULL, 0);
 
-	/* Fill sprom structure */
-	memset(&(iv->sprom), 0, sizeof(struct ssb_sprom));
-	iv->sprom.revision = 3;
-
-	if (cfe_getenv("et0macaddr", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et0macaddr", buf, sizeof(buf)) >= 0)
-		str2eaddr(buf, iv->sprom.et0mac);
+	bcm47xx_fill_sprom(&iv->sprom);
 
-	if (cfe_getenv("et1macaddr", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et1macaddr", buf, sizeof(buf)) >= 0)
-		str2eaddr(buf, iv->sprom.et1mac);
-
-	if (cfe_getenv("et0phyaddr", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et0phyaddr", buf, sizeof(buf)) >= 0)
-		iv->sprom.et0phyaddr = simple_strtoul(buf, NULL, 0);
-
-	if (cfe_getenv("et1phyaddr", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et1phyaddr", buf, sizeof(buf)) >= 0)
-		iv->sprom.et1phyaddr = simple_strtoul(buf, NULL, 0);
-
-	if (cfe_getenv("et0mdcport", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et0mdcport", buf, sizeof(buf)) >= 0)
-		iv->sprom.et0mdcport = simple_strtoul(buf, NULL, 10);
-
-	if (cfe_getenv("et1mdcport", buf, sizeof(buf)) >= 0 ||
-	    nvram_getenv("et1mdcport", buf, sizeof(buf)) >= 0)
-		iv->sprom.et1mdcport = simple_strtoul(buf, NULL, 10);
+	if (nvram_getenv("cardbus", buf, sizeof(buf)) >= 0)
+		iv->has_cardbus_slot = !!simple_strtoul(buf, NULL, 10);
 
 	return 0;
 }
@@ -126,12 +169,28 @@ static int bcm47xx_get_invariants(struct ssb_bus *bus,
 void __init plat_mem_setup(void)
 {
 	int err;
+	char buf[100];
+	struct ssb_mipscore *mcore;
 
 	err = ssb_bus_ssbbus_register(&ssb_bcm47xx, SSB_ENUM_BASE,
 				      bcm47xx_get_invariants);
 	if (err)
 		panic("Failed to initialize SSB bus (err %d)\n", err);
 
+	mcore = &ssb_bcm47xx.mipscore;
+	if (nvram_getenv("kernel_args", buf, sizeof(buf)) >= 0) {
+		if (strstr(buf, "console=ttyS1")) {
+			struct ssb_serial_port port;
+
+			printk(KERN_DEBUG "Swapping serial ports!\n");
+			/* swap serial ports */
+			memcpy(&port, &mcore->serial_ports[0], sizeof(port));
+			memcpy(&mcore->serial_ports[0], &mcore->serial_ports[1],
+			       sizeof(port));
+			memcpy(&mcore->serial_ports[1], &port, sizeof(port));
+		}
+	}
+
 	_machine_restart = bcm47xx_machine_restart;
 	_machine_halt = bcm47xx_machine_halt;
 	pm_power_off = bcm47xx_machine_halt;
diff --git a/arch/mips/include/asm/cpu.h b/arch/mips/include/asm/cpu.h
index 06d59dcbe24..86877539c6e 100644
--- a/arch/mips/include/asm/cpu.h
+++ b/arch/mips/include/asm/cpu.h
@@ -111,8 +111,8 @@
  * These are the PRID's for when 23:16 == PRID_COMP_BROADCOM
  */
 
-#define PRID_IMP_BMIPS4KC	0x4000
-#define PRID_IMP_BMIPS32	0x8000
+#define PRID_IMP_BMIPS32_REV4	0x4000
+#define PRID_IMP_BMIPS32_REV8	0x8000
 #define PRID_IMP_BMIPS3300	0x9000
 #define PRID_IMP_BMIPS3300_ALT	0x9100
 #define PRID_IMP_BMIPS3300_BUG	0x0000
diff --git a/arch/mips/include/asm/elf.h b/arch/mips/include/asm/elf.h
index fd1d39eb743..455c0ac7d4e 100644
--- a/arch/mips/include/asm/elf.h
+++ b/arch/mips/include/asm/elf.h
@@ -249,7 +249,8 @@ extern struct mips_abi mips_abi_n32;
 
 #define SET_PERSONALITY(ex)						\
 do {									\
-	set_personality(PER_LINUX);					\
+	if (personality(current->personality) != PER_LINUX)		\
+		set_personality(PER_LINUX);				\
 									\
 	current->thread.abi = &mips_abi;				\
 } while (0)
@@ -296,6 +297,8 @@ do {									\
 
 #define SET_PERSONALITY(ex)						\
 do {									\
+	unsigned int p;							\
+									\
 	clear_thread_flag(TIF_32BIT_REGS);				\
 	clear_thread_flag(TIF_32BIT_ADDR);				\
 									\
@@ -304,7 +307,8 @@ do {									\
 	else								\
 		current->thread.abi = &mips_abi;			\
 									\
-	if (current->personality != PER_LINUX32)			\
+	p = personality(current->personality);				\
+	if (p != PER_LINUX32 && p != PER_LINUX)				\
 		set_personality(PER_LINUX);				\
 } while (0)
 
diff --git a/arch/mips/include/asm/io.h b/arch/mips/include/asm/io.h
index c98bf514ec7..5b017f23e24 100644
--- a/arch/mips/include/asm/io.h
+++ b/arch/mips/include/asm/io.h
@@ -329,10 +329,14 @@ static inline void pfx##write##bwlq(type val,				\
 			"dsrl32	%L0, %L0, 0"			"\n\t"	\
 			"dsll32	%M0, %M0, 0"			"\n\t"	\
 			"or	%L0, %L0, %M0"			"\n\t"	\
+			".set	push"				"\n\t"	\
+			".set	noreorder"			"\n\t"	\
+			".set	nomacro"			"\n\t"	\
 			"sd	%L0, %2"			"\n\t"	\
+			".set	pop"				"\n\t"	\
 			".set	mips0"				"\n"	\
 			: "=r" (__tmp)					\
-			: "0" (__val), "m" (*__mem));			\
+			: "0" (__val), "R" (*__mem));			\
 		if (irq)						\
 			local_irq_restore(__flags);			\
 	} else								\
@@ -355,12 +359,16 @@ static inline type pfx##read##bwlq(const volatile void __iomem *mem)	\
 			local_irq_save(__flags);			\
 		__asm__ __volatile__(					\
 			".set	mips3"		"\t\t# __readq"	"\n\t"	\
+			".set	push"				"\n\t"	\
+			".set	noreorder"			"\n\t"	\
+			".set	nomacro"			"\n\t"	\
 			"ld	%L0, %1"			"\n\t"	\
+			".set	pop"				"\n\t"	\
 			"dsra32	%M0, %L0, 0"			"\n\t"	\
 			"sll	%L0, %L0, 0"			"\n\t"	\
 			".set	mips0"				"\n"	\
 			: "=r" (__val)					\
-			: "m" (*__mem));				\
+			: "R" (*__mem));				\
 		if (irq)						\
 			local_irq_restore(__flags);			\
 	} else {							\
diff --git a/arch/mips/include/asm/mach-ar7/ar7.h b/arch/mips/include/asm/mach-ar7/ar7.h
index 7919d76186b..07d3fadb244 100644
--- a/arch/mips/include/asm/mach-ar7/ar7.h
+++ b/arch/mips/include/asm/mach-ar7/ar7.h
@@ -201,7 +201,6 @@ static inline void ar7_device_off(u32 bit)
 }
 
 int __init ar7_gpio_init(void);
-
-int __init ar7_gpio_init(void);
+void __init ar7_init_clocks(void);
 
 #endif /* __AR7_H__ */
diff --git a/arch/mips/include/asm/mach-bcm47xx/nvram.h b/arch/mips/include/asm/mach-bcm47xx/nvram.h
index c58ebd8bc15..9759588ba3c 100644
--- a/arch/mips/include/asm/mach-bcm47xx/nvram.h
+++ b/arch/mips/include/asm/mach-bcm47xx/nvram.h
@@ -12,6 +12,7 @@
 #define __NVRAM_H
 
 #include <linux/types.h>
+#include <linux/kernel.h>
 
 struct nvram_header {
 	u32 magic;
@@ -36,4 +37,10 @@ struct nvram_header {
 
 extern int nvram_getenv(char *name, char *val, size_t val_len);
 
+static inline void nvram_parse_macaddr(char *buf, u8 *macaddr)
+{
+	sscanf(buf, "%hhx:%hhx:%hhx:%hhx:%hhx:%hhx", &macaddr[0], &macaddr[1],
+	       &macaddr[2], &macaddr[3], &macaddr[4], &macaddr[5]);
+}
+
 #endif
diff --git a/arch/mips/jz4740/board-qi_lb60.c b/arch/mips/jz4740/board-qi_lb60.c
index 5742bb4d78f..5c0a3575877 100644
--- a/arch/mips/jz4740/board-qi_lb60.c
+++ b/arch/mips/jz4740/board-qi_lb60.c
@@ -5,7 +5,7 @@
  *
  * Copyright (c) 2009 Qi Hardware inc.,
  * Author: Xiangfu Liu <xiangfu@qi-hardware.com>
- * Copyright 2010, Lars-Petrer Clausen <lars@metafoo.de>
+ * Copyright 2010, Lars-Peter Clausen <lars@metafoo.de>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 or later
@@ -235,7 +235,7 @@ static const unsigned int qi_lb60_keypad_rows[] = {
 	QI_LB60_GPIO_KEYIN(3),
 	QI_LB60_GPIO_KEYIN(4),
 	QI_LB60_GPIO_KEYIN(5),
-	QI_LB60_GPIO_KEYIN(7),
+	QI_LB60_GPIO_KEYIN(6),
 	QI_LB60_GPIO_KEYIN8,
 };
 
diff --git a/arch/mips/jz4740/platform.c b/arch/mips/jz4740/platform.c
index 95bc2b5b14f..1cc9e544d16 100644
--- a/arch/mips/jz4740/platform.c
+++ b/arch/mips/jz4740/platform.c
@@ -208,7 +208,7 @@ struct platform_device jz4740_i2s_device = {
 
 /* PCM */
 struct platform_device jz4740_pcm_device = {
-	.name		= "jz4740-pcm",
+	.name		= "jz4740-pcm-audio",
 	.id		= -1,
 };
 
diff --git a/arch/mips/jz4740/prom.c b/arch/mips/jz4740/prom.c
index cfeac15eb2e..4a70407f55b 100644
--- a/arch/mips/jz4740/prom.c
+++ b/arch/mips/jz4740/prom.c
@@ -23,7 +23,7 @@
 #include <asm/bootinfo.h>
 #include <asm/mach-jz4740/base.h>
 
-void jz4740_init_cmdline(int argc, char *argv[])
+static __init void jz4740_init_cmdline(int argc, char *argv[])
 {
 	unsigned int count = COMMAND_LINE_SIZE - 1;
 	int i;
diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
index 2f4d7a99bcc..98c5a9737c1 100644
--- a/arch/mips/kernel/cevt-r4k.c
+++ b/arch/mips/kernel/cevt-r4k.c
@@ -32,7 +32,7 @@ static int mips_next_event(unsigned long delta,
 	cnt = read_c0_count();
 	cnt += delta;
 	write_c0_compare(cnt);
-	res = ((int)(read_c0_count() - cnt) > 0) ? -ETIME : 0;
+	res = ((int)(read_c0_count() - cnt) >= 0) ? -ETIME : 0;
 	return res;
 }
 
diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
index 71620e19827..68dae7b6b5d 100644
--- a/arch/mips/kernel/cpu-probe.c
+++ b/arch/mips/kernel/cpu-probe.c
@@ -905,7 +905,8 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 {
 	decode_configs(c);
 	switch (c->processor_id & 0xff00) {
-	case PRID_IMP_BMIPS32:
+	case PRID_IMP_BMIPS32_REV4:
+	case PRID_IMP_BMIPS32_REV8:
 		c->cputype = CPU_BMIPS32;
 		__cpu_name[cpu] = "Broadcom BMIPS32";
 		break;
@@ -933,10 +934,6 @@ static inline void cpu_probe_broadcom(struct cpuinfo_mips *c, unsigned int cpu)
 		__cpu_name[cpu] = "Broadcom BMIPS5000";
 		c->options |= MIPS_CPU_ULRI;
 		break;
-	case PRID_IMP_BMIPS4KC:
-		c->cputype = CPU_4KC;
-		__cpu_name[cpu] = "MIPS 4Kc";
-		break;
 	}
 }
 
diff --git a/arch/mips/kernel/linux32.c b/arch/mips/kernel/linux32.c
index 6343b4a5b83..876a75cc376 100644
--- a/arch/mips/kernel/linux32.c
+++ b/arch/mips/kernel/linux32.c
@@ -251,14 +251,15 @@ SYSCALL_DEFINE5(n32_msgrcv, int, msqid, u32, msgp, size_t, msgsz,
 
 SYSCALL_DEFINE1(32_personality, unsigned long, personality)
 {
+	unsigned int p = personality & 0xffffffff;
 	int ret;
-	personality &= 0xffffffff;
+
 	if (personality(current->personality) == PER_LINUX32 &&
-	    personality == PER_LINUX)
-		personality = PER_LINUX32;
-	ret = sys_personality(personality);
-	if (ret == PER_LINUX32)
-		ret = PER_LINUX;
+	    personality(p) == PER_LINUX)
+		p = (p & ~PER_MASK) | PER_LINUX32;
+	ret = sys_personality(p);
+	if (ret != -1 && personality(ret) == PER_LINUX32)
+		ret = (ret & ~PER_MASK) | PER_LINUX;
 	return ret;
 }
 
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index 99960940d4a..ae167df73dd 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -142,7 +142,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	childregs->regs[7] = 0;	/* Clear error flag */
 
 	childregs->regs[2] = 0;	/* Child gets zero as return value */
-	regs->regs[2] = p->pid;
 
 	if (childregs->cp0_status & ST0_CU0) {
 		childregs->regs[28] = (unsigned long) ti;
diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c
index e000b278f02..9dbe5836895 100644
--- a/arch/mips/kernel/prom.c
+++ b/arch/mips/kernel/prom.c
@@ -100,7 +100,7 @@ void __init device_tree_init(void)
 		return;
 
 	base = virt_to_phys((void *)initial_boot_params);
-	size = initial_boot_params->totalsize;
+	size = be32_to_cpu(initial_boot_params->totalsize);
 
 	/* Before we do anything, lets reserve the dt blob */
 	reserve_mem_mach(base, size);
diff --git a/arch/mips/kernel/smp-mt.c b/arch/mips/kernel/smp-mt.c
index 43e7cdc5ded..c0e81418ba2 100644
--- a/arch/mips/kernel/smp-mt.c
+++ b/arch/mips/kernel/smp-mt.c
@@ -153,7 +153,7 @@ static void __cpuinit vsmp_init_secondary(void)
 {
 	extern int gic_present;
 
-	/* This is Malta specific: IPI,performance and timer inetrrupts */
+	/* This is Malta specific: IPI,performance and timer interrupts */
 	if (gic_present)
 		change_c0_status(ST0_IM, STATUSF_IP3 | STATUSF_IP4 |
 					 STATUSF_IP6 | STATUSF_IP7);
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 8e9fbe75894..e9710430254 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -83,7 +83,8 @@ extern asmlinkage void handle_mcheck(void);
 extern asmlinkage void handle_reserved(void);
 
 extern int fpu_emulator_cop1Handler(struct pt_regs *xcp,
-	struct mips_fpu_struct *ctx, int has_fpu);
+				    struct mips_fpu_struct *ctx, int has_fpu,
+				    void *__user *fault_addr);
 
 void (*board_be_init)(void);
 int (*board_be_handler)(struct pt_regs *regs, int is_fixup);
@@ -661,12 +662,36 @@ asmlinkage void do_ov(struct pt_regs *regs)
 	force_sig_info(SIGFPE, &info, current);
 }
 
+static int process_fpemu_return(int sig, void __user *fault_addr)
+{
+	if (sig == SIGSEGV || sig == SIGBUS) {
+		struct siginfo si = {0};
+		si.si_addr = fault_addr;
+		si.si_signo = sig;
+		if (sig == SIGSEGV) {
+			if (find_vma(current->mm, (unsigned long)fault_addr))
+				si.si_code = SEGV_ACCERR;
+			else
+				si.si_code = SEGV_MAPERR;
+		} else {
+			si.si_code = BUS_ADRERR;
+		}
+		force_sig_info(sig, &si, current);
+		return 1;
+	} else if (sig) {
+		force_sig(sig, current);
+		return 1;
+	} else {
+		return 0;
+	}
+}
+
 /*
  * XXX Delayed fp exceptions when doing a lazy ctx switch XXX
  */
 asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 {
-	siginfo_t info;
+	siginfo_t info = {0};
 
 	if (notify_die(DIE_FP, "FP exception", regs, 0, regs_to_trapnr(regs), SIGFPE)
 	    == NOTIFY_STOP)
@@ -675,6 +700,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 
 	if (fcr31 & FPU_CSR_UNI_X) {
 		int sig;
+		void __user *fault_addr = NULL;
 
 		/*
 		 * Unimplemented operation exception.  If we've got the full
@@ -690,7 +716,8 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 		lose_fpu(1);
 
 		/* Run the emulator */
-		sig = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1);
+		sig = fpu_emulator_cop1Handler(regs, &current->thread.fpu, 1,
+					       &fault_addr);
 
 		/*
 		 * We can't allow the emulated instruction to leave any of
@@ -702,8 +729,7 @@ asmlinkage void do_fpe(struct pt_regs *regs, unsigned long fcr31)
 		own_fpu(1);	/* Using the FPU again.  */
 
 		/* If something went wrong, signal */
-		if (sig)
-			force_sig(sig, current);
+		process_fpemu_return(sig, fault_addr);
 
 		return;
 	} else if (fcr31 & FPU_CSR_INV_X)
@@ -996,11 +1022,11 @@ asmlinkage void do_cpu(struct pt_regs *regs)
 
 		if (!raw_cpu_has_fpu) {
 			int sig;
+			void __user *fault_addr = NULL;
 			sig = fpu_emulator_cop1Handler(regs,
-						&current->thread.fpu, 0);
-			if (sig)
-				force_sig(sig, current);
-			else
+						       &current->thread.fpu,
+						       0, &fault_addr);
+			if (!process_fpemu_return(sig, fault_addr))
 				mt_ase_fp_affinity();
 		}
 
diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c
index 3eb3cde2f66..6a1fdfef8fd 100644
--- a/arch/mips/kernel/vpe.c
+++ b/arch/mips/kernel/vpe.c
@@ -1092,6 +1092,10 @@ static int vpe_open(struct inode *inode, struct file *filp)
 
 	/* this of-course trashes what was there before... */
 	v->pbuffer = vmalloc(P_SIZE);
+	if (!v->pbuffer) {
+		pr_warning("VPE loader: unable to allocate memory\n");
+		return -ENOMEM;
+	}
 	v->plen = P_SIZE;
 	v->load_addr = NULL;
 	v->len = 0;
@@ -1149,10 +1153,9 @@ static int vpe_release(struct inode *inode, struct file *filp)
 	if (ret < 0)
 		v->shared_ptr = NULL;
 
-	// cleanup any temp buffers
-	if (v->pbuffer)
-		vfree(v->pbuffer);
+	vfree(v->pbuffer);
 	v->plen = 0;
+
 	return ret;
 }
 
@@ -1169,11 +1172,6 @@ static ssize_t vpe_write(struct file *file, const char __user * buffer,
 	if (v == NULL)
 		return -ENODEV;
 
-	if (v->pbuffer == NULL) {
-		printk(KERN_ERR "VPE loader: no buffer for program\n");
-		return -ENOMEM;
-	}
-
 	if ((count + v->len) > v->plen) {
 		printk(KERN_WARNING
 		       "VPE loader: elf size too big. Perhaps strip uneeded symbols\n");
diff --git a/arch/mips/lib/memset.S b/arch/mips/lib/memset.S
index 77dc3b20110..606c8a9efe3 100644
--- a/arch/mips/lib/memset.S
+++ b/arch/mips/lib/memset.S
@@ -161,16 +161,16 @@ FEXPORT(__bzero)
 
 .Lfwd_fixup:
 	PTR_L		t0, TI_TASK($28)
-	LONG_L		t0, THREAD_BUADDR(t0)
 	andi		a2, 0x3f
+	LONG_L		t0, THREAD_BUADDR(t0)
 	LONG_ADDU	a2, t1
 	jr		ra
 	 LONG_SUBU	a2, t0
 
 .Lpartial_fixup:
 	PTR_L		t0, TI_TASK($28)
-	LONG_L		t0, THREAD_BUADDR(t0)
 	andi		a2, LONGMASK
+	LONG_L		t0, THREAD_BUADDR(t0)
 	LONG_ADDU	a2, t1
 	jr		ra
 	 LONG_SUBU	a2, t0
diff --git a/arch/mips/loongson/common/env.c b/arch/mips/loongson/common/env.c
index ae4cff97a56..11b193f848f 100644
--- a/arch/mips/loongson/common/env.c
+++ b/arch/mips/loongson/common/env.c
@@ -29,9 +29,9 @@ unsigned long memsize, highmemsize;
 
 #define parse_even_earlier(res, option, p)				\
 do {									\
+	int ret;							\
 	if (strncmp(option, (char *)p, strlen(option)) == 0)		\
-			strict_strtol((char *)p + strlen(option"="),	\
-					10, &res);			\
+		ret = strict_strtol((char *)p + strlen(option"="), 10, &res); \
 } while (0)
 
 void __init prom_init_env(void)
diff --git a/arch/mips/math-emu/cp1emu.c b/arch/mips/math-emu/cp1emu.c
index b2ad1b0910f..d32cb050311 100644
--- a/arch/mips/math-emu/cp1emu.c
+++ b/arch/mips/math-emu/cp1emu.c
@@ -64,7 +64,7 @@ static int fpu_emu(struct pt_regs *, struct mips_fpu_struct *,
 
 #if __mips >= 4 && __mips != 32
 static int fpux_emu(struct pt_regs *,
-	struct mips_fpu_struct *, mips_instruction);
+	struct mips_fpu_struct *, mips_instruction, void *__user *);
 #endif
 
 /* Further private data for which no space exists in mips_fpu_struct */
@@ -208,16 +208,23 @@ static inline int cop1_64bit(struct pt_regs *xcp)
  * Two instructions if the instruction is in a branch delay slot.
  */
 
-static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
+static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
+		       void *__user *fault_addr)
 {
 	mips_instruction ir;
 	unsigned long emulpc, contpc;
 	unsigned int cond;
 
-	if (get_user(ir, (mips_instruction __user *) xcp->cp0_epc)) {
+	if (!access_ok(VERIFY_READ, xcp->cp0_epc, sizeof(mips_instruction))) {
 		MIPS_FPU_EMU_INC_STATS(errors);
+		*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
 		return SIGBUS;
 	}
+	if (__get_user(ir, (mips_instruction __user *) xcp->cp0_epc)) {
+		MIPS_FPU_EMU_INC_STATS(errors);
+		*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
+		return SIGSEGV;
+	}
 
 	/* XXX NEC Vr54xx bug workaround */
 	if ((xcp->cp0_cause & CAUSEF_BD) && !isBranchInstr(&ir))
@@ -245,10 +252,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 #endif
 			return SIGILL;
 		}
-		if (get_user(ir, (mips_instruction __user *) emulpc)) {
+		if (!access_ok(VERIFY_READ, emulpc, sizeof(mips_instruction))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = (mips_instruction __user *)emulpc;
 			return SIGBUS;
 		}
+		if (__get_user(ir, (mips_instruction __user *) emulpc)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = (mips_instruction __user *)emulpc;
+			return SIGSEGV;
+		}
 		/* __compute_return_epc() will have updated cp0_epc */
 		contpc = xcp->cp0_epc;
 		/* In order not to confuse ptrace() et al, tweak context */
@@ -269,10 +282,17 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 		u64 val;
 
 		MIPS_FPU_EMU_INC_STATS(loads);
-		if (get_user(val, va)) {
+
+		if (!access_ok(VERIFY_READ, va, sizeof(u64))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
 			return SIGBUS;
 		}
+		if (__get_user(val, va)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
+			return SIGSEGV;
+		}
 		DITOREG(val, MIPSInst_RT(ir));
 		break;
 	}
@@ -284,10 +304,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 
 		MIPS_FPU_EMU_INC_STATS(stores);
 		DIFROMREG(val, MIPSInst_RT(ir));
-		if (put_user(val, va)) {
+		if (!access_ok(VERIFY_WRITE, va, sizeof(u64))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
 			return SIGBUS;
 		}
+		if (__put_user(val, va)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
+			return SIGSEGV;
+		}
 		break;
 	}
 
@@ -297,10 +323,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 		u32 val;
 
 		MIPS_FPU_EMU_INC_STATS(loads);
-		if (get_user(val, va)) {
+		if (!access_ok(VERIFY_READ, va, sizeof(u32))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
 			return SIGBUS;
 		}
+		if (__get_user(val, va)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
+			return SIGSEGV;
+		}
 		SITOREG(val, MIPSInst_RT(ir));
 		break;
 	}
@@ -312,10 +344,16 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 
 		MIPS_FPU_EMU_INC_STATS(stores);
 		SIFROMREG(val, MIPSInst_RT(ir));
-		if (put_user(val, va)) {
+		if (!access_ok(VERIFY_WRITE, va, sizeof(u32))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
 			return SIGBUS;
 		}
+		if (__put_user(val, va)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = va;
+			return SIGSEGV;
+		}
 		break;
 	}
 
@@ -440,11 +478,18 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 				contpc = (xcp->cp0_epc +
 					(MIPSInst_SIMM(ir) << 2));
 
-				if (get_user(ir,
-				    (mips_instruction __user *) xcp->cp0_epc)) {
+				if (!access_ok(VERIFY_READ, xcp->cp0_epc,
+					       sizeof(mips_instruction))) {
 					MIPS_FPU_EMU_INC_STATS(errors);
+					*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
 					return SIGBUS;
 				}
+				if (__get_user(ir,
+				    (mips_instruction __user *) xcp->cp0_epc)) {
+					MIPS_FPU_EMU_INC_STATS(errors);
+					*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
+					return SIGSEGV;
+				}
 
 				switch (MIPSInst_OPCODE(ir)) {
 				case lwc1_op:
@@ -506,9 +551,8 @@ static int cop1Emulate(struct pt_regs *xcp, struct mips_fpu_struct *ctx)
 
 #if __mips >= 4 && __mips != 32
 	case cop1x_op:{
-		int sig;
-
-		if ((sig = fpux_emu(xcp, ctx, ir)))
+		int sig = fpux_emu(xcp, ctx, ir, fault_addr);
+		if (sig)
 			return sig;
 		break;
 	}
@@ -604,7 +648,7 @@ DEF3OP(nmadd, dp, ieee754dp_mul, ieee754dp_add, ieee754dp_neg);
 DEF3OP(nmsub, dp, ieee754dp_mul, ieee754dp_sub, ieee754dp_neg);
 
 static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
-	mips_instruction ir)
+	mips_instruction ir, void *__user *fault_addr)
 {
 	unsigned rcsr = 0;	/* resulting csr */
 
@@ -624,10 +668,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 				xcp->regs[MIPSInst_FT(ir)]);
 
 			MIPS_FPU_EMU_INC_STATS(loads);
-			if (get_user(val, va)) {
+			if (!access_ok(VERIFY_READ, va, sizeof(u32))) {
 				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
 				return SIGBUS;
 			}
+			if (__get_user(val, va)) {
+				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
+				return SIGSEGV;
+			}
 			SITOREG(val, MIPSInst_FD(ir));
 			break;
 
@@ -638,10 +688,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			MIPS_FPU_EMU_INC_STATS(stores);
 
 			SIFROMREG(val, MIPSInst_FS(ir));
-			if (put_user(val, va)) {
+			if (!access_ok(VERIFY_WRITE, va, sizeof(u32))) {
 				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
 				return SIGBUS;
 			}
+			if (put_user(val, va)) {
+				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
+				return SIGSEGV;
+			}
 			break;
 
 		case madd_s_op:
@@ -701,10 +757,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 				xcp->regs[MIPSInst_FT(ir)]);
 
 			MIPS_FPU_EMU_INC_STATS(loads);
-			if (get_user(val, va)) {
+			if (!access_ok(VERIFY_READ, va, sizeof(u64))) {
 				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
 				return SIGBUS;
 			}
+			if (__get_user(val, va)) {
+				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
+				return SIGSEGV;
+			}
 			DITOREG(val, MIPSInst_FD(ir));
 			break;
 
@@ -714,10 +776,16 @@ static int fpux_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 
 			MIPS_FPU_EMU_INC_STATS(stores);
 			DIFROMREG(val, MIPSInst_FS(ir));
-			if (put_user(val, va)) {
+			if (!access_ok(VERIFY_WRITE, va, sizeof(u64))) {
 				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
 				return SIGBUS;
 			}
+			if (__put_user(val, va)) {
+				MIPS_FPU_EMU_INC_STATS(errors);
+				*fault_addr = va;
+				return SIGSEGV;
+			}
 			break;
 
 		case madd_d_op:
@@ -1242,7 +1310,7 @@ static int fpu_emu(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 }
 
 int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
-	int has_fpu)
+	int has_fpu, void *__user *fault_addr)
 {
 	unsigned long oldepc, prevepc;
 	mips_instruction insn;
@@ -1252,10 +1320,16 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 	do {
 		prevepc = xcp->cp0_epc;
 
-		if (get_user(insn, (mips_instruction __user *) xcp->cp0_epc)) {
+		if (!access_ok(VERIFY_READ, xcp->cp0_epc, sizeof(mips_instruction))) {
 			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
 			return SIGBUS;
 		}
+		if (__get_user(insn, (mips_instruction __user *) xcp->cp0_epc)) {
+			MIPS_FPU_EMU_INC_STATS(errors);
+			*fault_addr = (mips_instruction __user *)xcp->cp0_epc;
+			return SIGSEGV;
+		}
 		if (insn == 0)
 			xcp->cp0_epc += 4;	/* skip nops */
 		else {
@@ -1267,7 +1341,7 @@ int fpu_emulator_cop1Handler(struct pt_regs *xcp, struct mips_fpu_struct *ctx,
 			 */
 			/* convert to ieee library modes */
 			ieee754_csr.rm = ieee_rm[ieee754_csr.rm];
-			sig = cop1Emulate(xcp, ctx);
+			sig = cop1Emulate(xcp, ctx, fault_addr);
 			/* revert to mips rounding mode */
 			ieee754_csr.rm = mips_rm[ieee754_csr.rm];
 		}
diff --git a/arch/mips/mm/dma-default.c b/arch/mips/mm/dma-default.c
index 4fc1a0fbe00..21ea14efb83 100644
--- a/arch/mips/mm/dma-default.c
+++ b/arch/mips/mm/dma-default.c
@@ -288,7 +288,7 @@ int mips_dma_supported(struct device *dev, u64 mask)
 	return plat_dma_supported(dev, mask);
 }
 
-void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 			 enum dma_data_direction direction)
 {
 	BUG_ON(direction == DMA_NONE);
@@ -298,6 +298,8 @@ void mips_dma_cache_sync(struct device *dev, void *vaddr, size_t size,
 		__dma_sync((unsigned long)vaddr, size, direction);
 }
 
+EXPORT_SYMBOL(dma_cache_sync);
+
 static struct dma_map_ops mips_default_dma_map_ops = {
 	.alloc_coherent = mips_dma_alloc_coherent,
 	.free_coherent = mips_dma_free_coherent,
diff --git a/arch/mips/mm/sc-mips.c b/arch/mips/mm/sc-mips.c
index 505fecad468..9cca8de0054 100644
--- a/arch/mips/mm/sc-mips.c
+++ b/arch/mips/mm/sc-mips.c
@@ -68,6 +68,9 @@ static struct bcache_ops mips_sc_ops = {
  */
 static inline int mips_sc_is_activated(struct cpuinfo_mips *c)
 {
+	unsigned int config2 = read_c0_config2();
+	unsigned int tmp;
+
 	/* Check the bypass bit (L2B) */
 	switch (c->cputype) {
 	case CPU_34K:
@@ -83,6 +86,7 @@ static inline int mips_sc_is_activated(struct cpuinfo_mips *c)
 		c->scache.linesz = 2 << tmp;
 	else
 		return 0;
+	return 1;
 }
 
 static inline int __init mips_sc_probe(void)
diff --git a/arch/mips/pmc-sierra/yosemite/py-console.c b/arch/mips/pmc-sierra/yosemite/py-console.c
index b7f1d9c4a8a..434d7b1a8c6 100644
--- a/arch/mips/pmc-sierra/yosemite/py-console.c
+++ b/arch/mips/pmc-sierra/yosemite/py-console.c
@@ -65,11 +65,15 @@ static unsigned char readb_outer_space(unsigned long long phys)
 
 	__asm__ __volatile__ (
 	"	.set	mips3		\n"
+	"	.set	push		\n"
+	"	.set	noreorder	\n"
+	"	.set	nomacro		\n"
 	"	ld	%0, %1		\n"
+	"	.set	pop		\n"
 	"	lbu	%0, (%0)	\n"
 	"	.set	mips0		\n"
 	: "=r" (res)
-	: "m" (vaddr));
+	: "R" (vaddr));
 
 	write_c0_status(sr);
 	ssnop_4();
@@ -89,11 +93,15 @@ static void writeb_outer_space(unsigned long long phys, unsigned char c)
 
 	__asm__ __volatile__ (
 	"	.set	mips3		\n"
+	"	.set	push		\n"
+	"	.set	noreorder	\n"
+	"	.set	nomacro		\n"
 	"	ld	%0, %1		\n"
+	"	.set	pop		\n"
 	"	sb	%2, (%0)	\n"
 	"	.set	mips0		\n"
 	: "=&r" (tmp)
-	: "m" (vaddr), "r" (c));
+	: "R" (vaddr), "r" (c));
 
 	write_c0_status(sr);
 	ssnop_4();
diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c
index c308989fc46..41707a245de 100644
--- a/arch/mips/sibyte/swarm/setup.c
+++ b/arch/mips/sibyte/swarm/setup.c
@@ -82,7 +82,7 @@ int swarm_be_handler(struct pt_regs *regs, int is_fixup)
 enum swarm_rtc_type {
 	RTC_NONE,
 	RTC_XICOR,
-	RTC_M4LT81
+	RTC_M41T81,
 };
 
 enum swarm_rtc_type swarm_rtc_type;
@@ -96,7 +96,7 @@ void read_persistent_clock(struct timespec *ts)
 		sec = xicor_get_time();
 		break;
 
-	case RTC_M4LT81:
+	case RTC_M41T81:
 		sec = m41t81_get_time();
 		break;
 
@@ -115,7 +115,7 @@ int rtc_mips_set_time(unsigned long sec)
 	case RTC_XICOR:
 		return xicor_set_time(sec);
 
-	case RTC_M4LT81:
+	case RTC_M41T81:
 		return m41t81_set_time(sec);
 
 	case RTC_NONE:
@@ -141,7 +141,7 @@ void __init plat_mem_setup(void)
 	if (xicor_probe())
 		swarm_rtc_type = RTC_XICOR;
 	if (m41t81_probe())
-		swarm_rtc_type = RTC_M4LT81;
+		swarm_rtc_type = RTC_M41T81;
 
 #ifdef CONFIG_VT
 	screen_info = (struct screen_info) {
diff --git a/arch/mn10300/kernel/time.c b/arch/mn10300/kernel/time.c
index f860a340acc..75da468090b 100644
--- a/arch/mn10300/kernel/time.c
+++ b/arch/mn10300/kernel/time.c
@@ -40,21 +40,17 @@ unsigned long long sched_clock(void)
 		unsigned long long ll;
 		unsigned l[2];
 	} tsc64, result;
-	unsigned long tsc, tmp;
+	unsigned long tmp;
 	unsigned product[3]; /* 96-bit intermediate value */
 
 	/* cnt32_to_63() is not safe with preemption */
 	preempt_disable();
 
-	/* read the TSC value
-	 */
-	tsc = get_cycles();
-
-	/* expand to 64-bits.
+	/* expand the tsc to 64-bits.
 	 * - sched_clock() must be called once a minute or better or the
 	 *   following will go horribly wrong - see cnt32_to_63()
 	 */
-	tsc64.ll = cnt32_to_63(tsc) & 0x7fffffffffffffffULL;
+	tsc64.ll = cnt32_to_63(get_cycles()) & 0x7fffffffffffffffULL;
 
 	preempt_enable();
 
diff --git a/arch/tile/include/asm/signal.h b/arch/tile/include/asm/signal.h
index c1ee1d61d44..81d92a45cd4 100644
--- a/arch/tile/include/asm/signal.h
+++ b/arch/tile/include/asm/signal.h
@@ -25,7 +25,7 @@
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 struct pt_regs;
-int restore_sigcontext(struct pt_regs *, struct sigcontext __user *, long *);
+int restore_sigcontext(struct pt_regs *, struct sigcontext __user *);
 int setup_sigcontext(struct sigcontext __user *, struct pt_regs *);
 void do_signal(struct pt_regs *regs);
 #endif
diff --git a/arch/tile/kernel/compat_signal.c b/arch/tile/kernel/compat_signal.c
index 543d6a33aa2..dbb0dfc7bec 100644
--- a/arch/tile/kernel/compat_signal.c
+++ b/arch/tile/kernel/compat_signal.c
@@ -290,12 +290,12 @@ long compat_sys_sigaltstack(const struct compat_sigaltstack __user *uss_ptr,
 	return ret;
 }
 
+/* The assembly shim for this function arranges to ignore the return value. */
 long compat_sys_rt_sigreturn(struct pt_regs *regs)
 {
 	struct compat_rt_sigframe __user *frame =
 		(struct compat_rt_sigframe __user *) compat_ptr(regs->sp);
 	sigset_t set;
-	long r0;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
@@ -308,13 +308,13 @@ long compat_sys_rt_sigreturn(struct pt_regs *regs)
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
 
-	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &r0))
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
 		goto badframe;
 
 	if (compat_sys_sigaltstack(&frame->uc.uc_stack, NULL, regs) != 0)
 		goto badframe;
 
-	return r0;
+	return 0;
 
 badframe:
 	force_sig(SIGSEGV, current);
diff --git a/arch/tile/kernel/intvec_32.S b/arch/tile/kernel/intvec_32.S
index f5821626247..5eed4a02bf6 100644
--- a/arch/tile/kernel/intvec_32.S
+++ b/arch/tile/kernel/intvec_32.S
@@ -1342,8 +1342,8 @@ handle_syscall:
 	lw      r20, r20
 
 	/* Jump to syscall handler. */
-	jalr    r20; .Lhandle_syscall_link:
-	FEEDBACK_REENTER(handle_syscall)
+	jalr    r20
+.Lhandle_syscall_link: /* value of "lr" after "jalr r20" above */
 
 	/*
 	 * Write our r0 onto the stack so it gets restored instead
@@ -1352,6 +1352,9 @@ handle_syscall:
 	PTREGS_PTR(r29, PTREGS_OFFSET_REG(0))
 	sw      r29, r0
 
+.Lsyscall_sigreturn_skip:
+	FEEDBACK_REENTER(handle_syscall)
+
 	/* Do syscall trace again, if requested. */
 	lw	r30, r31
 	andi    r30, r30, _TIF_SYSCALL_TRACE
@@ -1536,9 +1539,24 @@ STD_ENTRY_LOCAL(bad_intr)
 	};                                              \
 	STD_ENDPROC(_##x)
 
+/*
+ * Special-case sigreturn to not write r0 to the stack on return.
+ * This is technically more efficient, but it also avoids difficulties
+ * in the 64-bit OS when handling 32-bit compat code, since we must not
+ * sign-extend r0 for the sigreturn return-value case.
+ */
+#define PTREGS_SYSCALL_SIGRETURN(x, reg)                \
+	STD_ENTRY(_##x);                                \
+	addli   lr, lr, .Lsyscall_sigreturn_skip - .Lhandle_syscall_link; \
+	{                                               \
+	 PTREGS_PTR(reg, PTREGS_OFFSET_BASE);           \
+	 j      x                                       \
+	};                                              \
+	STD_ENDPROC(_##x)
+
 PTREGS_SYSCALL(sys_execve, r3)
 PTREGS_SYSCALL(sys_sigaltstack, r2)
-PTREGS_SYSCALL(sys_rt_sigreturn, r0)
+PTREGS_SYSCALL_SIGRETURN(sys_rt_sigreturn, r0)
 PTREGS_SYSCALL(sys_cmpxchg_badaddr, r1)
 
 /* Save additional callee-saves to pt_regs, put address in r4 and jump. */
diff --git a/arch/tile/kernel/process.c b/arch/tile/kernel/process.c
index 8430f45daea..e90eb53173b 100644
--- a/arch/tile/kernel/process.c
+++ b/arch/tile/kernel/process.c
@@ -212,6 +212,13 @@ int copy_thread(unsigned long clone_flags, unsigned long sp,
 	childregs->sp = sp;  /* override with new user stack pointer */
 
 	/*
+	 * If CLONE_SETTLS is set, set "tp" in the new task to "r4",
+	 * which is passed in as arg #5 to sys_clone().
+	 */
+	if (clone_flags & CLONE_SETTLS)
+		childregs->tp = regs->regs[4];
+
+	/*
 	 * Copy the callee-saved registers from the passed pt_regs struct
 	 * into the context-switch callee-saved registers area.
 	 * This way when we start the interrupt-return sequence, the
@@ -539,6 +546,7 @@ struct task_struct *__sched _switch_to(struct task_struct *prev,
 	return __switch_to(prev, next, next_current_ksp0(next));
 }
 
+/* Note there is an implicit fifth argument if (clone_flags & CLONE_SETTLS). */
 SYSCALL_DEFINE5(clone, unsigned long, clone_flags, unsigned long, newsp,
 		void __user *, parent_tidptr, void __user *, child_tidptr,
 		struct pt_regs *, regs)
diff --git a/arch/tile/kernel/signal.c b/arch/tile/kernel/signal.c
index 757407e3669..1260321155f 100644
--- a/arch/tile/kernel/signal.c
+++ b/arch/tile/kernel/signal.c
@@ -52,7 +52,7 @@ SYSCALL_DEFINE3(sigaltstack, const stack_t __user *, uss,
  */
 
 int restore_sigcontext(struct pt_regs *regs,
-		       struct sigcontext __user *sc, long *pr0)
+		       struct sigcontext __user *sc)
 {
 	int err = 0;
 	int i;
@@ -75,17 +75,15 @@ int restore_sigcontext(struct pt_regs *regs,
 
 	regs->faultnum = INT_SWINT_1_SIGRETURN;
 
-	err |= __get_user(*pr0, &sc->gregs[0]);
 	return err;
 }
 
-/* sigreturn() returns long since it restores r0 in the interrupted code. */
+/* The assembly shim for this function arranges to ignore the return value. */
 SYSCALL_DEFINE1(rt_sigreturn, struct pt_regs *, regs)
 {
 	struct rt_sigframe __user *frame =
 		(struct rt_sigframe __user *)(regs->sp);
 	sigset_t set;
-	long r0;
 
 	if (!access_ok(VERIFY_READ, frame, sizeof(*frame)))
 		goto badframe;
@@ -98,13 +96,13 @@ SYSCALL_DEFINE1(rt_sigreturn, struct pt_regs *, regs)
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
 
-	if (restore_sigcontext(regs, &frame->uc.uc_mcontext, &r0))
+	if (restore_sigcontext(regs, &frame->uc.uc_mcontext))
 		goto badframe;
 
 	if (do_sigaltstack(&frame->uc.uc_stack, NULL, regs->sp) == -EFAULT)
 		goto badframe;
 
-	return r0;
+	return 0;
 
 badframe:
 	force_sig(SIGSEGV, current);
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 23f315c9f21..325c05294fc 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -355,7 +355,7 @@ asmlinkage void decompress_kernel(void *rmode, memptr heap,
 	if (heap > 0x3fffffffffffUL)
 		error("Destination address too large");
 #else
-	if (heap > ((-__PAGE_OFFSET-(512<<20)-1) & 0x7fffffff))
+	if (heap > ((-__PAGE_OFFSET-(128<<20)-1) & 0x7fffffff))
 		error("Destination address too large");
 #endif
 #ifndef CONFIG_RELOCATABLE
diff --git a/arch/x86/include/asm/e820.h b/arch/x86/include/asm/e820.h
index 5be1542fbfa..e99d55d74df 100644
--- a/arch/x86/include/asm/e820.h
+++ b/arch/x86/include/asm/e820.h
@@ -72,6 +72,9 @@ struct e820map {
 #define BIOS_BEGIN		0x000a0000
 #define BIOS_END		0x00100000
 
+#define BIOS_ROM_BASE		0xffe00000
+#define BIOS_ROM_END		0xffffffff
+
 #ifdef __KERNEL__
 /* see comment in arch/x86/kernel/e820.c */
 extern struct e820map e820;
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 9e6fe391094..f702f82aa1e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -79,7 +79,7 @@
 #define KVM_NUM_MMU_PAGES (1 << KVM_MMU_HASH_SHIFT)
 #define KVM_MIN_FREE_MMU_PAGES 5
 #define KVM_REFILL_PAGES 25
-#define KVM_MAX_CPUID_ENTRIES 40
+#define KVM_MAX_CPUID_ENTRIES 80
 #define KVM_NR_FIXED_MTRR_REGION 88
 #define KVM_NR_VAR_MTRR 8
 
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 9e13763b609..1e994754d32 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -45,6 +45,7 @@ obj-y			+= pci-dma.o quirks.o i8237.o topology.o kdebugfs.o
 obj-y			+= alternative.o i8253.o pci-nommu.o hw_breakpoint.o
 obj-y			+= tsc.o io_delay.o rtc.o
 obj-y			+= pci-iommu_table.o
+obj-y			+= resource.o
 
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-y				+= process.o
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 3f838d53739..78218135b48 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1389,6 +1389,14 @@ void __cpuinit end_local_APIC_setup(void)
 
 	setup_apic_nmi_watchdog(NULL);
 	apic_pm_activate();
+
+	/*
+	 * Now that local APIC setup is completed for BP, configure the fault
+	 * handling for interrupt remapping.
+	 */
+	if (!smp_processor_id() && intr_remapping_enabled)
+		enable_drhd_fault_handling();
+
 }
 
 #ifdef CONFIG_X86_X2APIC
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 7cc0a721f62..fadcd743a74 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2430,13 +2430,12 @@ static void ack_apic_level(struct irq_data *data)
 {
 	struct irq_cfg *cfg = data->chip_data;
 	int i, do_unmask_irq = 0, irq = data->irq;
-	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long v;
 
 	irq_complete_move(cfg);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	/* If we are moving the irq we need to mask it */
-	if (unlikely(desc->status & IRQ_MOVE_PENDING)) {
+	if (unlikely(irq_to_desc(irq)->status & IRQ_MOVE_PENDING)) {
 		do_unmask_irq = 1;
 		mask_ioapic(cfg);
 	}
@@ -3413,6 +3412,7 @@ dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
 	msg.data |= MSI_DATA_VECTOR(cfg->vector);
 	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+	msg.address_hi = MSI_ADDR_BASE_HI | MSI_ADDR_EXT_DEST_ID(dest);
 
 	dmar_msi_write(irq, &msg);
 
diff --git a/arch/x86/kernel/apic/probe_64.c b/arch/x86/kernel/apic/probe_64.c
index f9e4e6a5407..d8c4a6feb28 100644
--- a/arch/x86/kernel/apic/probe_64.c
+++ b/arch/x86/kernel/apic/probe_64.c
@@ -79,13 +79,6 @@ void __init default_setup_apic_routing(void)
 		/* need to update phys_pkg_id */
 		apic->phys_pkg_id = apicid_phys_pkg_id;
 	}
-
-	/*
-	 * Now that apic routing model is selected, configure the
-	 * fault handling for intr remapping.
-	 */
-	if (intr_remapping_enabled)
-		enable_drhd_fault_handling();
 }
 
 /* Same for both flat and physical. */
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index bcece91dd31..c0dbd9ac24f 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -60,16 +60,18 @@
 #define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
 #endif
 
+/* Number of possible pages in the lowmem region */
+LOWMEM_PAGES = (((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT)
+	
 /* Enough space to fit pagetables for the low memory linear map */
-MAPPING_BEYOND_END = \
-	PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT
+MAPPING_BEYOND_END = PAGE_TABLE_SIZE(LOWMEM_PAGES) << PAGE_SHIFT
 
 /*
  * Worst-case size of the kernel mapping we need to make:
- * the worst-case size of the kernel itself, plus the extra we need
- * to map for the linear map.
+ * a relocatable kernel can live anywhere in lowmem, so we need to be able
+ * to map all of lowmem.
  */
-KERNEL_PAGES = (KERNEL_IMAGE_SIZE + MAPPING_BEYOND_END)>>PAGE_SHIFT
+KERNEL_PAGES = LOWMEM_PAGES
 
 INIT_MAP_SIZE = PAGE_TABLE_SIZE(KERNEL_PAGES) * PAGE_SIZE_asm
 RESERVE_BRK(pagetables, INIT_MAP_SIZE)
@@ -620,13 +622,13 @@ ENTRY(initial_code)
 __PAGE_ALIGNED_BSS
 	.align PAGE_SIZE_asm
 #ifdef CONFIG_X86_PAE
-initial_pg_pmd:
+ENTRY(initial_pg_pmd)
 	.fill 1024*KPMDS,4,0
 #else
 ENTRY(initial_page_table)
 	.fill 1024,4,0
 #endif
-initial_pg_fixmap:
+ENTRY(initial_pg_fixmap)
 	.fill 1024,4,0
 ENTRY(empty_zero_page)
 	.fill 4096,1,0
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ae03cab4352..4ff5968f12d 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -27,6 +27,9 @@
 #define HPET_DEV_FSB_CAP		0x1000
 #define HPET_DEV_PERI_CAP		0x2000
 
+#define HPET_MIN_CYCLES			128
+#define HPET_MIN_PROG_DELTA		(HPET_MIN_CYCLES + (HPET_MIN_CYCLES >> 1))
+
 #define EVT_TO_HPET_DEV(evt) container_of(evt, struct hpet_dev, evt)
 
 /*
@@ -299,8 +302,9 @@ static void hpet_legacy_clockevent_register(void)
 	/* Calculate the min / max delta */
 	hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
 							   &hpet_clockevent);
-	/* 5 usec minimum reprogramming delta. */
-	hpet_clockevent.min_delta_ns = 5000;
+	/* Setup minimum reprogramming delta. */
+	hpet_clockevent.min_delta_ns = clockevent_delta2ns(HPET_MIN_PROG_DELTA,
+							   &hpet_clockevent);
 
 	/*
 	 * Start hpet with the boot cpu mask and make it
@@ -393,22 +397,24 @@ static int hpet_next_event(unsigned long delta,
 	 * the wraparound into account) nor a simple count down event
 	 * mode. Further the write to the comparator register is
 	 * delayed internally up to two HPET clock cycles in certain
-	 * chipsets (ATI, ICH9,10). We worked around that by reading
-	 * back the compare register, but that required another
-	 * workaround for ICH9,10 chips where the first readout after
-	 * write can return the old stale value. We already have a
-	 * minimum delta of 5us enforced, but a NMI or SMI hitting
+	 * chipsets (ATI, ICH9,10). Some newer AMD chipsets have even
+	 * longer delays. We worked around that by reading back the
+	 * compare register, but that required another workaround for
+	 * ICH9,10 chips where the first readout after write can
+	 * return the old stale value. We already had a minimum
+	 * programming delta of 5us enforced, but a NMI or SMI hitting
 	 * between the counter readout and the comparator write can
 	 * move us behind that point easily. Now instead of reading
 	 * the compare register back several times, we make the ETIME
 	 * decision based on the following: Return ETIME if the
-	 * counter value after the write is less than 8 HPET cycles
+	 * counter value after the write is less than HPET_MIN_CYCLES
 	 * away from the event or if the counter is already ahead of
-	 * the event.
+	 * the event. The minimum programming delta for the generic
+	 * clockevents code is set to 1.5 * HPET_MIN_CYCLES.
 	 */
 	res = (s32)(cnt - hpet_readl(HPET_COUNTER));
 
-	return res < 8 ? -ETIME : 0;
+	return res < HPET_MIN_CYCLES ? -ETIME : 0;
 }
 
 static void hpet_legacy_set_mode(enum clock_event_mode mode,
diff --git a/arch/x86/kernel/resource.c b/arch/x86/kernel/resource.c
new file mode 100644
index 00000000000..2a26819bb6a
--- /dev/null
+++ b/arch/x86/kernel/resource.c
@@ -0,0 +1,48 @@
+#include <linux/ioport.h>
+#include <asm/e820.h>
+
+static void resource_clip(struct resource *res, resource_size_t start,
+			  resource_size_t end)
+{
+	resource_size_t low = 0, high = 0;
+
+	if (res->end < start || res->start > end)
+		return;		/* no conflict */
+
+	if (res->start < start)
+		low = start - res->start;
+
+	if (res->end > end)
+		high = res->end - end;
+
+	/* Keep the area above or below the conflict, whichever is larger */
+	if (low > high)
+		res->end = start - 1;
+	else
+		res->start = end + 1;
+}
+
+static void remove_e820_regions(struct resource *avail)
+{
+	int i;
+	struct e820entry *entry;
+
+	for (i = 0; i < e820.nr_map; i++) {
+		entry = &e820.map[i];
+
+		resource_clip(avail, entry->addr,
+			      entry->addr + entry->size - 1);
+	}
+}
+
+void arch_remove_reservations(struct resource *avail)
+{
+	/* Trim out BIOS areas (low 1MB and high 2MB) and E820 regions */
+	if (avail->flags & IORESOURCE_MEM) {
+		if (avail->start < BIOS_END)
+			avail->start = BIOS_END;
+		resource_clip(avail, BIOS_ROM_BASE, BIOS_ROM_END);
+
+		remove_e820_regions(avail);
+	}
+}
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 21c6746338a..85268f8eadf 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -769,7 +769,6 @@ void __init setup_arch(char **cmdline_p)
 
 	x86_init.oem.arch_setup();
 
-	resource_alloc_from_bottom = 0;
 	iomem_resource.end = (1ULL << boot_cpu_data.x86_phys_bits) - 1;
 	setup_memory_map();
 	parse_setup_data();
diff --git a/arch/x86/kernel/xsave.c b/arch/x86/kernel/xsave.c
index 9c253bd65e2..547128546cc 100644
--- a/arch/x86/kernel/xsave.c
+++ b/arch/x86/kernel/xsave.c
@@ -394,7 +394,8 @@ static void __init setup_xstate_init(void)
 	 * Setup init_xstate_buf to represent the init state of
 	 * all the features managed by the xsave
 	 */
-	init_xstate_buf = alloc_bootmem(xstate_size);
+	init_xstate_buf = alloc_bootmem_align(xstate_size,
+					      __alignof__(struct xsave_struct));
 	init_xstate_buf->i387.mxcsr = MXCSR_DEFAULT;
 
 	clts();
diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 1ca12298ffc..b81a9b7c2ca 100644
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -3494,6 +3494,10 @@ static void svm_cpuid_update(struct kvm_vcpu *vcpu)
 static void svm_set_supported_cpuid(u32 func, struct kvm_cpuid_entry2 *entry)
 {
 	switch (func) {
+	case 0x00000001:
+		/* Mask out xsave bit as long as it is not supported by SVM */
+		entry->ecx &= ~(bit(X86_FEATURE_XSAVE));
+		break;
 	case 0x80000001:
 		if (nested)
 			entry->ecx |= (1 << 2); /* Set SVM bit */
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index ff21fdda0c5..81fcbe9515c 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -4227,11 +4227,6 @@ static int vmx_get_lpage_level(void)
 		return PT_PDPE_LEVEL;
 }
 
-static inline u32 bit(int bitno)
-{
-	return 1 << (bitno & 31);
-}
-
 static void vmx_cpuid_update(struct kvm_vcpu *vcpu)
 {
 	struct kvm_cpuid_entry2 *best;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index cdac9e592aa..b989e1f1e5d 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -155,11 +155,6 @@ struct kvm_stats_debugfs_item debugfs_entries[] = {
 
 u64 __read_mostly host_xcr0;
 
-static inline u32 bit(int bitno)
-{
-	return 1 << (bitno & 31);
-}
-
 static void kvm_on_user_return(struct user_return_notifier *urn)
 {
 	unsigned slot;
@@ -4569,9 +4564,11 @@ static void kvm_timer_init(void)
 #ifdef CONFIG_CPU_FREQ
 		struct cpufreq_policy policy;
 		memset(&policy, 0, sizeof(policy));
-		cpufreq_get_policy(&policy, get_cpu());
+		cpu = get_cpu();
+		cpufreq_get_policy(&policy, cpu);
 		if (policy.cpuinfo.max_freq)
 			max_tsc_khz = policy.cpuinfo.max_freq;
+		put_cpu();
 #endif
 		cpufreq_register_notifier(&kvmclock_cpufreq_notifier_block,
 					  CPUFREQ_TRANSITION_NOTIFIER);
@@ -5522,6 +5519,8 @@ int kvm_arch_vcpu_ioctl_set_sregs(struct kvm_vcpu *vcpu,
 
 	mmu_reset_needed |= kvm_read_cr4(vcpu) != sregs->cr4;
 	kvm_x86_ops->set_cr4(vcpu, sregs->cr4);
+	if (sregs->cr4 & X86_CR4_OSXSAVE)
+		update_cpuid(vcpu);
 	if (!is_long_mode(vcpu) && is_pae(vcpu)) {
 		load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3);
 		mmu_reset_needed = 1;
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 2cea414489f..c600da830ce 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -70,6 +70,11 @@ static inline int is_paging(struct kvm_vcpu *vcpu)
 	return kvm_read_cr0_bits(vcpu, X86_CR0_PG);
 }
 
+static inline u32 bit(int bitno)
+{
+	return 1 << (bitno & 31);
+}
+
 void kvm_before_handle_nmi(struct kvm_vcpu *vcpu);
 void kvm_after_handle_nmi(struct kvm_vcpu *vcpu);
 int kvm_inject_realmode_interrupt(struct kvm_vcpu *vcpu, int irq);
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 73b1e1a1f48..4996cf5f73a 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -531,7 +531,10 @@ static void lguest_write_cr3(unsigned long cr3)
 {
 	lguest_data.pgdir = cr3;
 	lazy_hcall1(LHCALL_NEW_PGTABLE, cr3);
-	cr3_changed = true;
+
+	/* These two page tables are simple, linear, and used during boot */
+	if (cr3 != __pa(swapper_pg_dir) && cr3 != __pa(initial_page_table))
+		cr3_changed = true;
 }
 
 static unsigned long lguest_read_cr3(void)
@@ -703,9 +706,9 @@ static void lguest_set_pmd(pmd_t *pmdp, pmd_t pmdval)
  * to forget all of them.  Fortunately, this is very rare.
  *
  * ... except in early boot when the kernel sets up the initial pagetables,
- * which makes booting astonishingly slow: 1.83 seconds!  So we don't even tell
- * the Host anything changed until we've done the first page table switch,
- * which brings boot back to 0.25 seconds.
+ * which makes booting astonishingly slow: 48 seconds!  So we don't even tell
+ * the Host anything changed until we've done the first real page table switch,
+ * which brings boot back to 4.3 seconds.
  */
 static void lguest_set_pte(pte_t *ptep, pte_t pteval)
 {
@@ -1002,7 +1005,7 @@ static void lguest_time_init(void)
 	clockevents_register_device(&lguest_clockevent);
 
 	/* Finally, we unblock the timer interrupt. */
-	enable_lguest_irq(0);
+	clear_bit(0, lguest_data.blocked_interrupts);
 }
 
 /*
@@ -1349,9 +1352,6 @@ __init void lguest_init(void)
 	 */
 	switch_to_new_gdt(0);
 
-	/* We actually boot with all memory mapped, but let's say 128MB. */
-	max_pfn_mapped = (128*1024*1024) >> PAGE_SHIFT;
-
 	/*
 	 * The Host<->Guest Switcher lives at the top of our address space, and
 	 * the Host told us how big it is when we made LGUEST_INIT hypercall:
diff --git a/arch/x86/lguest/i386_head.S b/arch/x86/lguest/i386_head.S
index 4f420c2f2d5..e7d5382ef26 100644
--- a/arch/x86/lguest/i386_head.S
+++ b/arch/x86/lguest/i386_head.S
@@ -4,6 +4,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/processor-flags.h>
+#include <asm/pgtable.h>
 
 /*G:020
  * Our story starts with the kernel booting into startup_32 in
@@ -37,9 +38,113 @@ ENTRY(lguest_entry)
 	/* Set up the initial stack so we can run C code. */
 	movl $(init_thread_union+THREAD_SIZE),%esp
 
+	call init_pagetables
+
 	/* Jumps are relative: we're running __PAGE_OFFSET too low. */
 	jmp lguest_init+__PAGE_OFFSET
 
+/*
+ * Initialize page tables.  This creates a PDE and a set of page
+ * tables, which are located immediately beyond __brk_base.  The variable
+ * _brk_end is set up to point to the first "safe" location.
+ * Mappings are created both at virtual address 0 (identity mapping)
+ * and PAGE_OFFSET for up to _end.
+ *
+ * FIXME: This code is taken verbatim from arch/x86/kernel/head_32.S: they
+ * don't have a stack at this point, so we can't just use call and ret.
+ */
+init_pagetables:
+#if PTRS_PER_PMD > 1
+#define PAGE_TABLE_SIZE(pages) (((pages) / PTRS_PER_PMD) + PTRS_PER_PGD)
+#else
+#define PAGE_TABLE_SIZE(pages) ((pages) / PTRS_PER_PGD)
+#endif
+#define pa(X) ((X) - __PAGE_OFFSET)
+
+/* Enough space to fit pagetables for the low memory linear map */
+MAPPING_BEYOND_END = \
+	PAGE_TABLE_SIZE(((1<<32) - __PAGE_OFFSET) >> PAGE_SHIFT) << PAGE_SHIFT
+#ifdef CONFIG_X86_PAE
+
+	/*
+	 * In PAE mode initial_page_table is statically defined to contain
+	 * enough entries to cover the VMSPLIT option (that is the top 1, 2 or 3
+	 * entries). The identity mapping is handled by pointing two PGD entries
+	 * to the first kernel PMD.
+	 *
+	 * Note the upper half of each PMD or PTE are always zero at this stage.
+	 */
+
+#define KPMDS (((-__PAGE_OFFSET) >> 30) & 3) /* Number of kernel PMDs */
+
+	xorl %ebx,%ebx				/* %ebx is kept at zero */
+
+	movl $pa(__brk_base), %edi
+	movl $pa(initial_pg_pmd), %edx
+	movl $PTE_IDENT_ATTR, %eax
+10:
+	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PMD entry */
+	movl %ecx,(%edx)			/* Store PMD entry */
+						/* Upper half already zero */
+	addl $8,%edx
+	movl $512,%ecx
+11:
+	stosl
+	xchgl %eax,%ebx
+	stosl
+	xchgl %eax,%ebx
+	addl $0x1000,%eax
+	loop 11b
+
+	/*
+	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
+	 */
+	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
+	cmpl %ebp,%eax
+	jb 10b
+1:
+	addl $__PAGE_OFFSET, %edi
+	movl %edi, pa(_brk_end)
+	shrl $12, %eax
+	movl %eax, pa(max_pfn_mapped)
+
+	/* Do early initialization of the fixmap area */
+	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+	movl %eax,pa(initial_pg_pmd+0x1000*KPMDS-8)
+#else	/* Not PAE */
+
+page_pde_offset = (__PAGE_OFFSET >> 20);
+
+	movl $pa(__brk_base), %edi
+	movl $pa(initial_page_table), %edx
+	movl $PTE_IDENT_ATTR, %eax
+10:
+	leal PDE_IDENT_ATTR(%edi),%ecx		/* Create PDE entry */
+	movl %ecx,(%edx)			/* Store identity PDE entry */
+	movl %ecx,page_pde_offset(%edx)		/* Store kernel PDE entry */
+	addl $4,%edx
+	movl $1024, %ecx
+11:
+	stosl
+	addl $0x1000,%eax
+	loop 11b
+	/*
+	 * End condition: we must map up to the end + MAPPING_BEYOND_END.
+	 */
+	movl $pa(_end) + MAPPING_BEYOND_END + PTE_IDENT_ATTR, %ebp
+	cmpl %ebp,%eax
+	jb 10b
+	addl $__PAGE_OFFSET, %edi
+	movl %edi, pa(_brk_end)
+	shrl $12, %eax
+	movl %eax, pa(max_pfn_mapped)
+
+	/* Do early initialization of the fixmap area */
+	movl $pa(initial_pg_fixmap)+PDE_IDENT_ATTR,%eax
+	movl %eax,pa(initial_page_table+0xffc)
+#endif
+	ret
+
 /*G:055
  * We create a macro which puts the assembler code between lgstart_ and lgend_
  * markers.  These templates are put in the .text section: they can't be
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index c4bb261c106..b1805b78842 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -65,21 +65,13 @@ pcibios_align_resource(void *data, const struct resource *res,
 			resource_size_t size, resource_size_t align)
 {
 	struct pci_dev *dev = data;
-	resource_size_t start = round_down(res->end - size + 1, align);
+	resource_size_t start = res->start;
 
 	if (res->flags & IORESOURCE_IO) {
-
-		/*
-		 * If we're avoiding ISA aliases, the largest contiguous I/O
-		 * port space is 256 bytes.  Clearing bits 9 and 10 preserves
-		 * all 256-byte and smaller alignments, so the result will
-		 * still be correctly aligned.
-		 */
-		if (!skip_isa_ioresource_align(dev))
-			start &= ~0x300;
-	} else if (res->flags & IORESOURCE_MEM) {
-		if (start < BIOS_END)
-			start = res->end;	/* fail; no space */
+		if (skip_isa_ioresource_align(dev))
+			return start;
+		if (start & 0x300)
+			start = (start + 0x3ff) & ~0x3ff;
 	}
 	return start;
 }
diff --git a/arch/x86/vdso/Makefile b/arch/x86/vdso/Makefile
index 4a2afa1bac5..b6552b189bc 100644
--- a/arch/x86/vdso/Makefile
+++ b/arch/x86/vdso/Makefile
@@ -25,7 +25,7 @@ targets += vdso.so vdso.so.dbg vdso.lds $(vobjs-y)
 
 export CPPFLAGS_vdso.lds += -P -C
 
-VDSO_LDFLAGS_vdso.lds = -m elf_x86_64 -Wl,-soname=linux-vdso.so.1 \
+VDSO_LDFLAGS_vdso.lds = -m64 -Wl,-soname=linux-vdso.so.1 \
 		      	-Wl,-z,max-page-size=4096 -Wl,-z,common-page-size=4096
 
 $(obj)/vdso.o: $(src)/vdso.S $(obj)/vdso.so
@@ -69,7 +69,7 @@ vdso32.so-$(VDSO32-y)		+= sysenter
 vdso32-images			= $(vdso32.so-y:%=vdso32-%.so)
 
 CPPFLAGS_vdso32.lds = $(CPPFLAGS_vdso.lds)
-VDSO_LDFLAGS_vdso32.lds = -m elf_i386 -Wl,-soname=linux-gate.so.1
+VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-soname=linux-gate.so.1
 
 # This makes sure the $(obj) subdirectory exists even though vdso32/
 # is not a kbuild sub-make subdirectory.
diff --git a/block/blk-map.c b/block/blk-map.c
index 5d5dbe47c22..e663ac2d8e6 100644
--- a/block/blk-map.c
+++ b/block/blk-map.c
@@ -201,12 +201,13 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 	for (i = 0; i < iov_count; i++) {
 		unsigned long uaddr = (unsigned long)iov[i].iov_base;
 
+		if (!iov[i].iov_len)
+			return -EINVAL;
+
 		if (uaddr & queue_dma_alignment(q)) {
 			unaligned = 1;
 			break;
 		}
-		if (!iov[i].iov_len)
-			return -EINVAL;
 	}
 
 	if (unaligned || (q->dma_pad_mask & len) || map_data)
diff --git a/block/blk-merge.c b/block/blk-merge.c
index 77b7c26df6b..74bc4a768f3 100644
--- a/block/blk-merge.c
+++ b/block/blk-merge.c
@@ -21,7 +21,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q,
 		return 0;
 
 	fbio = bio;
-	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+	cluster = blk_queue_cluster(q);
 	seg_size = 0;
 	nr_phys_segs = 0;
 	for_each_bio(bio) {
@@ -87,7 +87,7 @@ EXPORT_SYMBOL(blk_recount_segments);
 static int blk_phys_contig_segment(struct request_queue *q, struct bio *bio,
 				   struct bio *nxt)
 {
-	if (!test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
+	if (!blk_queue_cluster(q))
 		return 0;
 
 	if (bio->bi_seg_back_size + nxt->bi_seg_front_size >
@@ -123,7 +123,7 @@ int blk_rq_map_sg(struct request_queue *q, struct request *rq,
 	int nsegs, cluster;
 
 	nsegs = 0;
-	cluster = test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags);
+	cluster = blk_queue_cluster(q);
 
 	/*
 	 * for each bio in rq
diff --git a/block/blk-settings.c b/block/blk-settings.c
index 701859fb964..36c8c1f2af1 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -126,7 +126,7 @@ void blk_set_default_limits(struct queue_limits *lim)
 	lim->alignment_offset = 0;
 	lim->io_opt = 0;
 	lim->misaligned = 0;
-	lim->no_cluster = 0;
+	lim->cluster = 1;
 }
 EXPORT_SYMBOL(blk_set_default_limits);
 
@@ -229,8 +229,8 @@ void blk_queue_bounce_limit(struct request_queue *q, u64 dma_mask)
 EXPORT_SYMBOL(blk_queue_bounce_limit);
 
 /**
- * blk_queue_max_hw_sectors - set max sectors for a request for this queue
- * @q:  the request queue for the device
+ * blk_limits_max_hw_sectors - set hard and soft limit of max sectors for request
+ * @limits: the queue limits
  * @max_hw_sectors:  max hardware sectors in the usual 512b unit
  *
  * Description:
@@ -244,7 +244,7 @@ EXPORT_SYMBOL(blk_queue_bounce_limit);
  *    per-device basis in /sys/block/<device>/queue/max_sectors_kb.
  *    The soft limit can not exceed max_hw_sectors.
  **/
-void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
+void blk_limits_max_hw_sectors(struct queue_limits *limits, unsigned int max_hw_sectors)
 {
 	if ((max_hw_sectors << 9) < PAGE_CACHE_SIZE) {
 		max_hw_sectors = 1 << (PAGE_CACHE_SHIFT - 9);
@@ -252,9 +252,23 @@ void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_secto
 		       __func__, max_hw_sectors);
 	}
 
-	q->limits.max_hw_sectors = max_hw_sectors;
-	q->limits.max_sectors = min_t(unsigned int, max_hw_sectors,
-				      BLK_DEF_MAX_SECTORS);
+	limits->max_hw_sectors = max_hw_sectors;
+	limits->max_sectors = min_t(unsigned int, max_hw_sectors,
+				    BLK_DEF_MAX_SECTORS);
+}
+EXPORT_SYMBOL(blk_limits_max_hw_sectors);
+
+/**
+ * blk_queue_max_hw_sectors - set max sectors for a request for this queue
+ * @q:  the request queue for the device
+ * @max_hw_sectors:  max hardware sectors in the usual 512b unit
+ *
+ * Description:
+ *    See description for blk_limits_max_hw_sectors().
+ **/
+void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
+{
+	blk_limits_max_hw_sectors(&q->limits, max_hw_sectors);
 }
 EXPORT_SYMBOL(blk_queue_max_hw_sectors);
 
@@ -464,15 +478,6 @@ EXPORT_SYMBOL(blk_queue_io_opt);
 void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b)
 {
 	blk_stack_limits(&t->limits, &b->limits, 0);
-
-	if (!t->queue_lock)
-		WARN_ON_ONCE(1);
-	else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) {
-		unsigned long flags;
-		spin_lock_irqsave(t->queue_lock, flags);
-		queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
-		spin_unlock_irqrestore(t->queue_lock, flags);
-	}
 }
 EXPORT_SYMBOL(blk_queue_stack_limits);
 
@@ -545,7 +550,7 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->io_min = max(t->io_min, b->io_min);
 	t->io_opt = lcm(t->io_opt, b->io_opt);
 
-	t->no_cluster |= b->no_cluster;
+	t->cluster &= b->cluster;
 	t->discard_zeroes_data &= b->discard_zeroes_data;
 
 	/* Physical block size a multiple of the logical block size? */
@@ -641,7 +646,6 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 		       sector_t offset)
 {
 	struct request_queue *t = disk->queue;
-	struct request_queue *b = bdev_get_queue(bdev);
 
 	if (bdev_stack_limits(&t->limits, bdev, offset >> 9) < 0) {
 		char top[BDEVNAME_SIZE], bottom[BDEVNAME_SIZE];
@@ -652,17 +656,6 @@ void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
 		printk(KERN_NOTICE "%s: Warning: Device %s is misaligned\n",
 		       top, bottom);
 	}
-
-	if (!t->queue_lock)
-		WARN_ON_ONCE(1);
-	else if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(t->queue_lock, flags);
-		if (!test_bit(QUEUE_FLAG_CLUSTER, &b->queue_flags))
-			queue_flag_clear(QUEUE_FLAG_CLUSTER, t);
-		spin_unlock_irqrestore(t->queue_lock, flags);
-	}
 }
 EXPORT_SYMBOL(disk_stack_limits);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index 013457f47fd..41fb69150b4 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -119,7 +119,7 @@ static ssize_t queue_max_integrity_segments_show(struct request_queue *q, char *
 
 static ssize_t queue_max_segment_size_show(struct request_queue *q, char *page)
 {
-	if (test_bit(QUEUE_FLAG_CLUSTER, &q->queue_flags))
+	if (blk_queue_cluster(q))
 		return queue_var_show(queue_max_segment_size(q), (page));
 
 	return queue_var_show(PAGE_CACHE_SIZE, (page));
diff --git a/block/blk-throttle.c b/block/blk-throttle.c
index 004be80fd89..381b09bb562 100644
--- a/block/blk-throttle.c
+++ b/block/blk-throttle.c
@@ -355,6 +355,12 @@ throtl_start_new_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw)
 			tg->slice_end[rw], jiffies);
 }
 
+static inline void throtl_set_slice_end(struct throtl_data *td,
+		struct throtl_grp *tg, bool rw, unsigned long jiffy_end)
+{
+	tg->slice_end[rw] = roundup(jiffy_end, throtl_slice);
+}
+
 static inline void throtl_extend_slice(struct throtl_data *td,
 		struct throtl_grp *tg, bool rw, unsigned long jiffy_end)
 {
@@ -391,6 +397,16 @@ throtl_trim_slice(struct throtl_data *td, struct throtl_grp *tg, bool rw)
 	if (throtl_slice_used(td, tg, rw))
 		return;
 
+	/*
+	 * A bio has been dispatched. Also adjust slice_end. It might happen
+	 * that initially cgroup limit was very low resulting in high
+	 * slice_end, but later limit was bumped up and bio was dispached
+	 * sooner, then we need to reduce slice_end. A high bogus slice_end
+	 * is bad because it does not allow new slice to start.
+	 */
+
+	throtl_set_slice_end(td, tg, rw, jiffies + throtl_slice);
+
 	time_elapsed = jiffies - tg->slice_start[rw];
 
 	nr_slices = time_elapsed / throtl_slice;
@@ -709,26 +725,21 @@ static void throtl_process_limit_change(struct throtl_data *td)
 	struct throtl_grp *tg;
 	struct hlist_node *pos, *n;
 
-	/*
-	 * Make sure atomic_inc() effects from
-	 * throtl_update_blkio_group_read_bps(), group of functions are
-	 * visible.
-	 * Is this required or smp_mb__after_atomic_inc() was suffcient
-	 * after the atomic_inc().
-	 */
-	smp_rmb();
 	if (!atomic_read(&td->limits_changed))
 		return;
 
 	throtl_log(td, "limit changed =%d", atomic_read(&td->limits_changed));
 
-	hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) {
-		/*
-		 * Do I need an smp_rmb() here to make sure tg->limits_changed
-		 * update is visible. I am relying on smp_rmb() at the
-		 * beginning of function and not putting a new one here.
-		 */
+	/*
+	 * Make sure updates from throtl_update_blkio_group_read_bps() group
+	 * of functions to tg->limits_changed are visible. We do not
+	 * want update td->limits_changed to be visible but update to
+	 * tg->limits_changed not being visible yet on this cpu. Hence
+	 * the read barrier.
+	 */
+	smp_rmb();
 
+	hlist_for_each_entry_safe(tg, pos, n, &td->tg_list, tg_node) {
 		if (throtl_tg_on_rr(tg) && tg->limits_changed) {
 			throtl_log_tg(td, tg, "limit change rbps=%llu wbps=%llu"
 				" riops=%u wiops=%u", tg->bps[READ],
diff --git a/drivers/block/cciss.c b/drivers/block/cciss.c
index f291587d753..8e0f9256eb5 100644
--- a/drivers/block/cciss.c
+++ b/drivers/block/cciss.c
@@ -2834,6 +2834,8 @@ static int cciss_revalidate(struct gendisk *disk)
 	InquiryData_struct *inq_buff = NULL;
 
 	for (logvol = 0; logvol < CISS_MAX_LUN; logvol++) {
+		if (!h->drv[logvol])
+			continue;
 		if (memcmp(h->drv[logvol]->LunID, drv->LunID,
 			sizeof(drv->LunID)) == 0) {
 			FOUND = 1;
diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c
index 89d8a7cc405..24487d4fb20 100644
--- a/drivers/block/drbd/drbd_receiver.c
+++ b/drivers/block/drbd/drbd_receiver.c
@@ -3627,17 +3627,19 @@ static void drbdd(struct drbd_conf *mdev)
 		}
 
 		shs = drbd_cmd_handler[cmd].pkt_size - sizeof(union p_header);
-		rv = drbd_recv(mdev, &header->h80.payload, shs);
-		if (unlikely(rv != shs)) {
-			dev_err(DEV, "short read while reading sub header: rv=%d\n", rv);
-			goto err_out;
-		}
-
 		if (packet_size - shs > 0 && !drbd_cmd_handler[cmd].expect_payload) {
 			dev_err(DEV, "No payload expected %s l:%d\n", cmdname(cmd), packet_size);
 			goto err_out;
 		}
 
+		if (shs) {
+			rv = drbd_recv(mdev, &header->h80.payload, shs);
+			if (unlikely(rv != shs)) {
+				dev_err(DEV, "short read while reading sub header: rv=%d\n", rv);
+				goto err_out;
+			}
+		}
+
 		rv = drbd_cmd_handler[cmd].function(mdev, cmd, packet_size - shs);
 
 		if (unlikely(!rv)) {
diff --git a/drivers/block/drbd/drbd_req.h b/drivers/block/drbd/drbd_req.h
index 181ea036482..ab2bd09d54b 100644
--- a/drivers/block/drbd/drbd_req.h
+++ b/drivers/block/drbd/drbd_req.h
@@ -339,7 +339,8 @@ static inline int _req_mod(struct drbd_request *req, enum drbd_req_event what)
 }
 
 /* completion of master bio is outside of spinlock.
- * If you need it irqsave, do it your self! */
+ * If you need it irqsave, do it your self!
+ * Which means: don't use from bio endio callback. */
 static inline int req_mod(struct drbd_request *req,
 		enum drbd_req_event what)
 {
diff --git a/drivers/block/drbd/drbd_worker.c b/drivers/block/drbd/drbd_worker.c
index 47d223c2409..34f224b018b 100644
--- a/drivers/block/drbd/drbd_worker.c
+++ b/drivers/block/drbd/drbd_worker.c
@@ -193,8 +193,10 @@ void drbd_endio_sec(struct bio *bio, int error)
  */
 void drbd_endio_pri(struct bio *bio, int error)
 {
+	unsigned long flags;
 	struct drbd_request *req = bio->bi_private;
 	struct drbd_conf *mdev = req->mdev;
+	struct bio_and_error m;
 	enum drbd_req_event what;
 	int uptodate = bio_flagged(bio, BIO_UPTODATE);
 
@@ -220,7 +222,13 @@ void drbd_endio_pri(struct bio *bio, int error)
 	bio_put(req->private_bio);
 	req->private_bio = ERR_PTR(error);
 
-	req_mod(req, what);
+	/* not req_mod(), we need irqsave here! */
+	spin_lock_irqsave(&mdev->req_lock, flags);
+	__req_mod(req, what, &m);
+	spin_unlock_irqrestore(&mdev->req_lock, flags);
+
+	if (m.bio)
+		complete_master_bio(mdev, &m);
 }
 
 int w_read_retry_remote(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index d68d3aa1814..f975d24890f 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -283,16 +283,21 @@ static void sh_cmt_clock_event_program_verify(struct sh_cmt_priv *p,
 	} while (delay);
 }
 
-static void sh_cmt_set_next(struct sh_cmt_priv *p, unsigned long delta)
+static void __sh_cmt_set_next(struct sh_cmt_priv *p, unsigned long delta)
 {
-	unsigned long flags;
-
 	if (delta > p->max_match_value)
 		dev_warn(&p->pdev->dev, "delta out of range\n");
 
-	spin_lock_irqsave(&p->lock, flags);
 	p->next_match_value = delta;
 	sh_cmt_clock_event_program_verify(p, 0);
+}
+
+static void sh_cmt_set_next(struct sh_cmt_priv *p, unsigned long delta)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&p->lock, flags);
+	__sh_cmt_set_next(p, delta);
 	spin_unlock_irqrestore(&p->lock, flags);
 }
 
@@ -359,7 +364,7 @@ static int sh_cmt_start(struct sh_cmt_priv *p, unsigned long flag)
 
 	/* setup timeout if no clockevent */
 	if ((flag == FLAG_CLOCKSOURCE) && (!(p->flags & FLAG_CLOCKEVENT)))
-		sh_cmt_set_next(p, p->max_match_value);
+		__sh_cmt_set_next(p, p->max_match_value);
  out:
 	spin_unlock_irqrestore(&p->lock, flags);
 
@@ -381,7 +386,7 @@ static void sh_cmt_stop(struct sh_cmt_priv *p, unsigned long flag)
 
 	/* adjust the timeout to maximum if only clocksource left */
 	if ((flag == FLAG_CLOCKEVENT) && (p->flags & FLAG_CLOCKSOURCE))
-		sh_cmt_set_next(p, p->max_match_value);
+		__sh_cmt_set_next(p, p->max_match_value);
 
 	spin_unlock_irqrestore(&p->lock, flags);
 }
diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c
index e3f7fc6f956..68f09a86843 100644
--- a/drivers/input/evdev.c
+++ b/drivers/input/evdev.c
@@ -534,76 +534,73 @@ static int handle_eviocgbit(struct input_dev *dev,
 }
 #undef OLD_KEY_MAX
 
-static int evdev_handle_get_keycode(struct input_dev *dev,
-				    void __user *p, size_t size)
+static int evdev_handle_get_keycode(struct input_dev *dev, void __user *p)
 {
-	struct input_keymap_entry ke;
+	struct input_keymap_entry ke = {
+		.len	= sizeof(unsigned int),
+		.flags	= 0,
+	};
+	int __user *ip = (int __user *)p;
 	int error;
 
-	memset(&ke, 0, sizeof(ke));
-
-	if (size == sizeof(unsigned int[2])) {
-		/* legacy case */
-		int __user *ip = (int __user *)p;
+	/* legacy case */
+	if (copy_from_user(ke.scancode, p, sizeof(unsigned int)))
+		return -EFAULT;
 
-		if (copy_from_user(ke.scancode, p, sizeof(unsigned int)))
-			return -EFAULT;
+	error = input_get_keycode(dev, &ke);
+	if (error)
+		return error;
 
-		ke.len = sizeof(unsigned int);
-		ke.flags = 0;
+	if (put_user(ke.keycode, ip + 1))
+		return -EFAULT;
 
-		error = input_get_keycode(dev, &ke);
-		if (error)
-			return error;
+	return 0;
+}
 
-		if (put_user(ke.keycode, ip + 1))
-			return -EFAULT;
+static int evdev_handle_get_keycode_v2(struct input_dev *dev, void __user *p)
+{
+	struct input_keymap_entry ke;
+	int error;
 
-	} else {
-		size = min(size, sizeof(ke));
+	if (copy_from_user(&ke, p, sizeof(ke)))
+		return -EFAULT;
 
-		if (copy_from_user(&ke, p, size))
-			return -EFAULT;
+	error = input_get_keycode(dev, &ke);
+	if (error)
+		return error;
 
-		error = input_get_keycode(dev, &ke);
-		if (error)
-			return error;
+	if (copy_to_user(p, &ke, sizeof(ke)))
+		return -EFAULT;
 
-		if (copy_to_user(p, &ke, size))
-			return -EFAULT;
-	}
 	return 0;
 }
 
-static int evdev_handle_set_keycode(struct input_dev *dev,
-				    void __user *p, size_t size)
+static int evdev_handle_set_keycode(struct input_dev *dev, void __user *p)
 {
-	struct input_keymap_entry ke;
-
-	memset(&ke, 0, sizeof(ke));
+	struct input_keymap_entry ke = {
+		.len	= sizeof(unsigned int),
+		.flags	= 0,
+	};
+	int __user *ip = (int __user *)p;
 
-	if (size == sizeof(unsigned int[2])) {
-		/* legacy case */
-		int __user *ip = (int __user *)p;
+	if (copy_from_user(ke.scancode, p, sizeof(unsigned int)))
+		return -EFAULT;
 
-		if (copy_from_user(ke.scancode, p, sizeof(unsigned int)))
-			return -EFAULT;
+	if (get_user(ke.keycode, ip + 1))
+		return -EFAULT;
 
-		if (get_user(ke.keycode, ip + 1))
-			return -EFAULT;
+	return input_set_keycode(dev, &ke);
+}
 
-		ke.len = sizeof(unsigned int);
-		ke.flags = 0;
+static int evdev_handle_set_keycode_v2(struct input_dev *dev, void __user *p)
+{
+	struct input_keymap_entry ke;
 
-	} else {
-		size = min(size, sizeof(ke));
+	if (copy_from_user(&ke, p, sizeof(ke)))
+		return -EFAULT;
 
-		if (copy_from_user(&ke, p, size))
-			return -EFAULT;
-
-		if (ke.len > sizeof(ke.scancode))
-			return -EINVAL;
-	}
+	if (ke.len > sizeof(ke.scancode))
+		return -EINVAL;
 
 	return input_set_keycode(dev, &ke);
 }
@@ -669,6 +666,18 @@ static long evdev_do_ioctl(struct file *file, unsigned int cmd,
 			return evdev_grab(evdev, client);
 		else
 			return evdev_ungrab(evdev, client);
+
+	case EVIOCGKEYCODE:
+		return evdev_handle_get_keycode(dev, p);
+
+	case EVIOCSKEYCODE:
+		return evdev_handle_set_keycode(dev, p);
+
+	case EVIOCGKEYCODE_V2:
+		return evdev_handle_get_keycode_v2(dev, p);
+
+	case EVIOCSKEYCODE_V2:
+		return evdev_handle_set_keycode_v2(dev, p);
 	}
 
 	size = _IOC_SIZE(cmd);
@@ -708,12 +717,6 @@ static long evdev_do_ioctl(struct file *file, unsigned int cmd,
 			return -EFAULT;
 
 		return error;
-
-	case EVIOC_MASK_SIZE(EVIOCGKEYCODE):
-		return evdev_handle_get_keycode(dev, p, size);
-
-	case EVIOC_MASK_SIZE(EVIOCSKEYCODE):
-		return evdev_handle_set_keycode(dev, p, size);
 	}
 
 	/* Multi-number variable-length handlers */
diff --git a/drivers/input/tablet/wacom_wac.c b/drivers/input/tablet/wacom_wac.c
index 4852b440960..435b0af401e 100644
--- a/drivers/input/tablet/wacom_wac.c
+++ b/drivers/input/tablet/wacom_wac.c
@@ -1436,6 +1436,8 @@ static struct wacom_features wacom_features_0xD2 =
 	{ "Wacom Bamboo Craft",   WACOM_PKGLEN_BBFUN,     14720,  9200, 1023, 63, BAMBOO_PT };
 static struct wacom_features wacom_features_0xD3 =
 	{ "Wacom Bamboo 2FG 6x8", WACOM_PKGLEN_BBFUN,     21648, 13530, 1023, 63, BAMBOO_PT };
+static const struct wacom_features wacom_features_0xD4 =
+	{ "Wacom Bamboo Pen",     WACOM_PKGLEN_BBFUN,     14720,  9200,  255, 63, BAMBOO_PT };
 static struct wacom_features wacom_features_0xD8 =
 	{ "Wacom Bamboo Comic 2FG", WACOM_PKGLEN_BBFUN,   21648, 13530, 1023, 63, BAMBOO_PT };
 static struct wacom_features wacom_features_0xDA =
@@ -1510,6 +1512,7 @@ const struct usb_device_id wacom_ids[] = {
 	{ USB_DEVICE_WACOM(0xD1) },
 	{ USB_DEVICE_WACOM(0xD2) },
 	{ USB_DEVICE_WACOM(0xD3) },
+	{ USB_DEVICE_WACOM(0xD4) },
 	{ USB_DEVICE_WACOM(0xD8) },
 	{ USB_DEVICE_WACOM(0xDA) },
 	{ USB_DEVICE_WACOM(0xDB) },
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 90267f8d64e..4d705cea0f8 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -517,9 +517,8 @@ int dm_set_device_limits(struct dm_target *ti, struct dm_dev *dev,
 	 */
 
 	if (q->merge_bvec_fn && !ti->type->merge)
-		limits->max_sectors =
-			min_not_zero(limits->max_sectors,
-				     (unsigned int) (PAGE_SIZE >> 9));
+		blk_limits_max_hw_sectors(limits,
+					  (unsigned int) (PAGE_SIZE >> 9));
 	return 0;
 }
 EXPORT_SYMBOL_GPL(dm_set_device_limits);
@@ -1131,11 +1130,6 @@ void dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
 	 */
 	q->limits = *limits;
 
-	if (limits->no_cluster)
-		queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);
-	else
-		queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, q);
-
 	if (!dm_table_supports_discards(t))
 		queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
 	else
diff --git a/drivers/md/md.c b/drivers/md/md.c
index e71c5fa527f..175c424f201 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -4295,9 +4295,6 @@ static int md_alloc(dev_t dev, char *name)
 		goto abort;
 	mddev->queue->queuedata = mddev;
 
-	/* Can be unlocked because the queue is new: no concurrency */
-	queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, mddev->queue);
-
 	blk_queue_make_request(mddev->queue, md_make_request);
 
 	disk = alloc_disk(1 << shift);
diff --git a/drivers/media/common/saa7146_hlp.c b/drivers/media/common/saa7146_hlp.c
index 05bde9ccb77..1d1d8d20075 100644
--- a/drivers/media/common/saa7146_hlp.c
+++ b/drivers/media/common/saa7146_hlp.c
@@ -558,7 +558,7 @@ static void saa7146_set_window(struct saa7146_dev *dev, int width, int height, e
 static void saa7146_set_position(struct saa7146_dev *dev, int w_x, int w_y, int w_height, enum v4l2_field field, u32 pixelformat)
 {
 	struct saa7146_vv *vv = dev->vv_data;
-	struct saa7146_format *sfmt = format_by_fourcc(dev, pixelformat);
+	struct saa7146_format *sfmt = saa7146_format_by_fourcc(dev, pixelformat);
 
 	int b_depth = vv->ov_fmt->depth;
 	int b_bpl = vv->ov_fb.fmt.bytesperline;
@@ -702,7 +702,7 @@ static int calculate_video_dma_grab_packed(struct saa7146_dev* dev, struct saa71
 	struct saa7146_vv *vv = dev->vv_data;
 	struct saa7146_video_dma vdma1;
 
-	struct saa7146_format *sfmt = format_by_fourcc(dev,buf->fmt->pixelformat);
+	struct saa7146_format *sfmt = saa7146_format_by_fourcc(dev,buf->fmt->pixelformat);
 
 	int width = buf->fmt->width;
 	int height = buf->fmt->height;
@@ -827,7 +827,7 @@ static int calculate_video_dma_grab_planar(struct saa7146_dev* dev, struct saa71
 	struct saa7146_video_dma vdma2;
 	struct saa7146_video_dma vdma3;
 
-	struct saa7146_format *sfmt = format_by_fourcc(dev,buf->fmt->pixelformat);
+	struct saa7146_format *sfmt = saa7146_format_by_fourcc(dev,buf->fmt->pixelformat);
 
 	int width = buf->fmt->width;
 	int height = buf->fmt->height;
@@ -994,7 +994,7 @@ static void program_capture_engine(struct saa7146_dev *dev, int planar)
 
 void saa7146_set_capture(struct saa7146_dev *dev, struct saa7146_buf *buf, struct saa7146_buf *next)
 {
-	struct saa7146_format *sfmt = format_by_fourcc(dev,buf->fmt->pixelformat);
+	struct saa7146_format *sfmt = saa7146_format_by_fourcc(dev,buf->fmt->pixelformat);
 	struct saa7146_vv *vv = dev->vv_data;
 	u32 vdma1_prot_addr;
 
diff --git a/drivers/media/common/saa7146_video.c b/drivers/media/common/saa7146_video.c
index 741c5732b43..d246910129e 100644
--- a/drivers/media/common/saa7146_video.c
+++ b/drivers/media/common/saa7146_video.c
@@ -84,7 +84,7 @@ static struct saa7146_format formats[] = {
 
 static int NUM_FORMATS = sizeof(formats)/sizeof(struct saa7146_format);
 
-struct saa7146_format* format_by_fourcc(struct saa7146_dev *dev, int fourcc)
+struct saa7146_format* saa7146_format_by_fourcc(struct saa7146_dev *dev, int fourcc)
 {
 	int i, j = NUM_FORMATS;
 
@@ -266,7 +266,7 @@ static int saa7146_pgtable_build(struct saa7146_dev *dev, struct saa7146_buf *bu
 	struct videobuf_dmabuf *dma=videobuf_to_dma(&buf->vb);
 	struct scatterlist *list = dma->sglist;
 	int length = dma->sglen;
-	struct saa7146_format *sfmt = format_by_fourcc(dev,buf->fmt->pixelformat);
+	struct saa7146_format *sfmt = saa7146_format_by_fourcc(dev,buf->fmt->pixelformat);
 
 	DEB_EE(("dev:%p, buf:%p, sg_len:%d\n",dev,buf,length));
 
@@ -408,7 +408,7 @@ static int video_begin(struct saa7146_fh *fh)
 		}
 	}
 
-	fmt = format_by_fourcc(dev,fh->video_fmt.pixelformat);
+	fmt = saa7146_format_by_fourcc(dev,fh->video_fmt.pixelformat);
 	/* we need to have a valid format set here */
 	BUG_ON(NULL == fmt);
 
@@ -460,7 +460,7 @@ static int video_end(struct saa7146_fh *fh, struct file *file)
 		return -EBUSY;
 	}
 
-	fmt = format_by_fourcc(dev,fh->video_fmt.pixelformat);
+	fmt = saa7146_format_by_fourcc(dev,fh->video_fmt.pixelformat);
 	/* we need to have a valid format set here */
 	BUG_ON(NULL == fmt);
 
@@ -536,7 +536,7 @@ static int vidioc_s_fbuf(struct file *file, void *fh, struct v4l2_framebuffer *f
 		return -EPERM;
 
 	/* check args */
-	fmt = format_by_fourcc(dev, fb->fmt.pixelformat);
+	fmt = saa7146_format_by_fourcc(dev, fb->fmt.pixelformat);
 	if (NULL == fmt)
 		return -EINVAL;
 
@@ -760,7 +760,7 @@ static int vidioc_try_fmt_vid_cap(struct file *file, void *fh, struct v4l2_forma
 
 	DEB_EE(("V4L2_BUF_TYPE_VIDEO_CAPTURE: dev:%p, fh:%p\n", dev, fh));
 
-	fmt = format_by_fourcc(dev, f->fmt.pix.pixelformat);
+	fmt = saa7146_format_by_fourcc(dev, f->fmt.pix.pixelformat);
 	if (NULL == fmt)
 		return -EINVAL;
 
@@ -1264,7 +1264,7 @@ static int buffer_prepare(struct videobuf_queue *q,
 		buf->fmt       = &fh->video_fmt;
 		buf->vb.field  = fh->video_fmt.field;
 
-		sfmt = format_by_fourcc(dev,buf->fmt->pixelformat);
+		sfmt = saa7146_format_by_fourcc(dev,buf->fmt->pixelformat);
 
 		release_all_pagetables(dev, buf);
 		if( 0 != IS_PLANAR(sfmt->trans)) {
@@ -1378,7 +1378,7 @@ static int video_open(struct saa7146_dev *dev, struct file *file)
 	fh->video_fmt.pixelformat = V4L2_PIX_FMT_BGR24;
 	fh->video_fmt.bytesperline = 0;
 	fh->video_fmt.field = V4L2_FIELD_ANY;
-	sfmt = format_by_fourcc(dev,fh->video_fmt.pixelformat);
+	sfmt = saa7146_format_by_fourcc(dev,fh->video_fmt.pixelformat);
 	fh->video_fmt.sizeimage = (fh->video_fmt.width * fh->video_fmt.height * sfmt->depth)/8;
 
 	videobuf_queue_sg_init(&fh->video_q, &video_qops,
diff --git a/drivers/media/radio/radio-aimslab.c b/drivers/media/radio/radio-aimslab.c
index 5bf4985daed..05e832f61c3 100644
--- a/drivers/media/radio/radio-aimslab.c
+++ b/drivers/media/radio/radio-aimslab.c
@@ -361,7 +361,7 @@ static int vidioc_s_audio(struct file *file, void *priv,
 
 static const struct v4l2_file_operations rtrack_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops rtrack_ioctl_ops = {
@@ -412,13 +412,6 @@ static int __init rtrack_init(void)
 	rt->vdev.release = video_device_release_empty;
 	video_set_drvdata(&rt->vdev, rt);
 
-	if (video_register_device(&rt->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
-		v4l2_device_unregister(&rt->v4l2_dev);
-		release_region(rt->io, 2);
-		return -EINVAL;
-	}
-	v4l2_info(v4l2_dev, "AIMSlab RadioTrack/RadioReveal card driver.\n");
-
 	/* Set up the I/O locking */
 
 	mutex_init(&rt->lock);
@@ -430,6 +423,13 @@ static int __init rtrack_init(void)
 	sleep_delay(2000000);	/* make sure it's totally down	*/
 	outb(0xc0, rt->io);		/* steady volume, mute card	*/
 
+	if (video_register_device(&rt->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
+		v4l2_device_unregister(&rt->v4l2_dev);
+		release_region(rt->io, 2);
+		return -EINVAL;
+	}
+	v4l2_info(v4l2_dev, "AIMSlab RadioTrack/RadioReveal card driver.\n");
+
 	return 0;
 }
 
diff --git a/drivers/media/radio/radio-aztech.c b/drivers/media/radio/radio-aztech.c
index c2231139362..dd8a6ab0d43 100644
--- a/drivers/media/radio/radio-aztech.c
+++ b/drivers/media/radio/radio-aztech.c
@@ -324,7 +324,7 @@ static int vidioc_s_ctrl(struct file *file, void *priv,
 
 static const struct v4l2_file_operations aztech_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops aztech_ioctl_ops = {
@@ -375,6 +375,8 @@ static int __init aztech_init(void)
 	az->vdev.ioctl_ops = &aztech_ioctl_ops;
 	az->vdev.release = video_device_release_empty;
 	video_set_drvdata(&az->vdev, az);
+	/* mute card - prevents noisy bootups */
+	outb(0, az->io);
 
 	if (video_register_device(&az->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
 		v4l2_device_unregister(v4l2_dev);
@@ -383,8 +385,6 @@ static int __init aztech_init(void)
 	}
 
 	v4l2_info(v4l2_dev, "Aztech radio card driver v1.00/19990224 rkroll@exploits.org\n");
-	/* mute card - prevents noisy bootups */
-	outb(0, az->io);
 	return 0;
 }
 
diff --git a/drivers/media/radio/radio-cadet.c b/drivers/media/radio/radio-cadet.c
index b701ea6e7c7..bc9ad0897c5 100644
--- a/drivers/media/radio/radio-cadet.c
+++ b/drivers/media/radio/radio-cadet.c
@@ -328,11 +328,10 @@ static ssize_t cadet_read(struct file *file, char __user *data, size_t count, lo
 	unsigned char readbuf[RDS_BUFFER];
 	int i = 0;
 
+	mutex_lock(&dev->lock);
 	if (dev->rdsstat == 0) {
-		mutex_lock(&dev->lock);
 		dev->rdsstat = 1;
 		outb(0x80, dev->io);        /* Select RDS fifo */
-		mutex_unlock(&dev->lock);
 		init_timer(&dev->readtimer);
 		dev->readtimer.function = cadet_handler;
 		dev->readtimer.data = (unsigned long)dev;
@@ -340,12 +339,15 @@ static ssize_t cadet_read(struct file *file, char __user *data, size_t count, lo
 		add_timer(&dev->readtimer);
 	}
 	if (dev->rdsin == dev->rdsout) {
+		mutex_unlock(&dev->lock);
 		if (file->f_flags & O_NONBLOCK)
 			return -EWOULDBLOCK;
 		interruptible_sleep_on(&dev->read_queue);
+		mutex_lock(&dev->lock);
 	}
 	while (i < count && dev->rdsin != dev->rdsout)
 		readbuf[i++] = dev->rdsbuf[dev->rdsout++];
+	mutex_unlock(&dev->lock);
 
 	if (copy_to_user(data, readbuf, i))
 		return -EFAULT;
@@ -525,9 +527,11 @@ static int cadet_open(struct file *file)
 {
 	struct cadet *dev = video_drvdata(file);
 
+	mutex_lock(&dev->lock);
 	dev->users++;
 	if (1 == dev->users)
 		init_waitqueue_head(&dev->read_queue);
+	mutex_unlock(&dev->lock);
 	return 0;
 }
 
@@ -535,11 +539,13 @@ static int cadet_release(struct file *file)
 {
 	struct cadet *dev = video_drvdata(file);
 
+	mutex_lock(&dev->lock);
 	dev->users--;
 	if (0 == dev->users) {
 		del_timer_sync(&dev->readtimer);
 		dev->rdsstat = 0;
 	}
+	mutex_unlock(&dev->lock);
 	return 0;
 }
 
@@ -559,7 +565,7 @@ static const struct v4l2_file_operations cadet_fops = {
 	.open		= cadet_open,
 	.release       	= cadet_release,
 	.read		= cadet_read,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 	.poll		= cadet_poll,
 };
 
diff --git a/drivers/media/radio/radio-gemtek-pci.c b/drivers/media/radio/radio-gemtek-pci.c
index 79039674a0e..28fa85ba208 100644
--- a/drivers/media/radio/radio-gemtek-pci.c
+++ b/drivers/media/radio/radio-gemtek-pci.c
@@ -361,7 +361,7 @@ MODULE_DEVICE_TABLE(pci, gemtek_pci_id);
 
 static const struct v4l2_file_operations gemtek_pci_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops gemtek_pci_ioctl_ops = {
@@ -422,11 +422,11 @@ static int __devinit gemtek_pci_probe(struct pci_dev *pdev, const struct pci_dev
 	card->vdev.release = video_device_release_empty;
 	video_set_drvdata(&card->vdev, card);
 
+	gemtek_pci_mute(card);
+
 	if (video_register_device(&card->vdev, VFL_TYPE_RADIO, nr_radio) < 0)
 		goto err_video;
 
-	gemtek_pci_mute(card);
-
 	v4l2_info(v4l2_dev, "Gemtek PCI Radio (rev. %d) found at 0x%04x-0x%04x.\n",
 		pdev->revision, card->iobase, card->iobase + card->length - 1);
 
diff --git a/drivers/media/radio/radio-gemtek.c b/drivers/media/radio/radio-gemtek.c
index 73985f641f0..259936422e4 100644
--- a/drivers/media/radio/radio-gemtek.c
+++ b/drivers/media/radio/radio-gemtek.c
@@ -378,7 +378,7 @@ static int gemtek_probe(struct gemtek *gt)
 
 static const struct v4l2_file_operations gemtek_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static int vidioc_querycap(struct file *file, void *priv,
@@ -577,12 +577,6 @@ static int __init gemtek_init(void)
 	gt->vdev.release = video_device_release_empty;
 	video_set_drvdata(&gt->vdev, gt);
 
-	if (video_register_device(&gt->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
-		v4l2_device_unregister(v4l2_dev);
-		release_region(gt->io, 1);
-		return -EBUSY;
-	}
-
 	/* Set defaults */
 	gt->lastfreq = GEMTEK_LOWFREQ;
 	gt->bu2614data = 0;
@@ -590,6 +584,12 @@ static int __init gemtek_init(void)
 	if (initmute)
 		gemtek_mute(gt);
 
+	if (video_register_device(&gt->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
+		v4l2_device_unregister(v4l2_dev);
+		release_region(gt->io, 1);
+		return -EBUSY;
+	}
+
 	return 0;
 }
 
diff --git a/drivers/media/radio/radio-maestro.c b/drivers/media/radio/radio-maestro.c
index 08f1051979c..6af61bfeb17 100644
--- a/drivers/media/radio/radio-maestro.c
+++ b/drivers/media/radio/radio-maestro.c
@@ -299,7 +299,7 @@ static int vidioc_s_audio(struct file *file, void *priv,
 
 static const struct v4l2_file_operations maestro_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops maestro_ioctl_ops = {
@@ -383,22 +383,20 @@ static int __devinit maestro_probe(struct pci_dev *pdev,
 	dev->vdev.release = video_device_release_empty;
 	video_set_drvdata(&dev->vdev, dev);
 
+	if (!radio_power_on(dev)) {
+		retval = -EIO;
+		goto errfr1;
+	}
+
 	retval = video_register_device(&dev->vdev, VFL_TYPE_RADIO, radio_nr);
 	if (retval) {
 		v4l2_err(v4l2_dev, "can't register video device!\n");
 		goto errfr1;
 	}
 
-	if (!radio_power_on(dev)) {
-		retval = -EIO;
-		goto errunr;
-	}
-
 	v4l2_info(v4l2_dev, "version " DRIVER_VERSION "\n");
 
 	return 0;
-errunr:
-	video_unregister_device(&dev->vdev);
 errfr1:
 	v4l2_device_unregister(v4l2_dev);
 errfr:
diff --git a/drivers/media/radio/radio-maxiradio.c b/drivers/media/radio/radio-maxiradio.c
index 255d40df4b4..6459a220b0d 100644
--- a/drivers/media/radio/radio-maxiradio.c
+++ b/drivers/media/radio/radio-maxiradio.c
@@ -346,7 +346,7 @@ static int vidioc_s_ctrl(struct file *file, void *priv,
 
 static const struct v4l2_file_operations maxiradio_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl          = video_ioctl2,
+	.unlocked_ioctl = video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops maxiradio_ioctl_ops = {
diff --git a/drivers/media/radio/radio-miropcm20.c b/drivers/media/radio/radio-miropcm20.c
index 4ff885445fd..3fb76e3834c 100644
--- a/drivers/media/radio/radio-miropcm20.c
+++ b/drivers/media/radio/radio-miropcm20.c
@@ -33,6 +33,7 @@ struct pcm20 {
 	unsigned long freq;
 	int muted;
 	struct snd_miro_aci *aci;
+	struct mutex lock;
 };
 
 static struct pcm20 pcm20_card = {
@@ -72,7 +73,7 @@ static int pcm20_setfreq(struct pcm20 *dev, unsigned long freq)
 
 static const struct v4l2_file_operations pcm20_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static int vidioc_querycap(struct file *file, void *priv,
@@ -229,7 +230,7 @@ static int __init pcm20_init(void)
 		return -ENODEV;
 	}
 	strlcpy(v4l2_dev->name, "miropcm20", sizeof(v4l2_dev->name));
-
+	mutex_init(&dev->lock);
 
 	res = v4l2_device_register(NULL, v4l2_dev);
 	if (res < 0) {
@@ -242,6 +243,7 @@ static int __init pcm20_init(void)
 	dev->vdev.fops = &pcm20_fops;
 	dev->vdev.ioctl_ops = &pcm20_ioctl_ops;
 	dev->vdev.release = video_device_release_empty;
+	dev->vdev.lock = &dev->lock;
 	video_set_drvdata(&dev->vdev, dev);
 
 	if (video_register_device(&dev->vdev, VFL_TYPE_RADIO, radio_nr) < 0)
diff --git a/drivers/media/radio/radio-rtrack2.c b/drivers/media/radio/radio-rtrack2.c
index a79296aac9a..8d6ea591bd1 100644
--- a/drivers/media/radio/radio-rtrack2.c
+++ b/drivers/media/radio/radio-rtrack2.c
@@ -266,7 +266,7 @@ static int vidioc_s_audio(struct file *file, void *priv,
 
 static const struct v4l2_file_operations rtrack2_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops rtrack2_ioctl_ops = {
@@ -315,6 +315,10 @@ static int __init rtrack2_init(void)
 	dev->vdev.release = video_device_release_empty;
 	video_set_drvdata(&dev->vdev, dev);
 
+	/* mute card - prevents noisy bootups */
+	outb(1, dev->io);
+	dev->muted = 1;
+
 	mutex_init(&dev->lock);
 	if (video_register_device(&dev->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
 		v4l2_device_unregister(v4l2_dev);
@@ -324,10 +328,6 @@ static int __init rtrack2_init(void)
 
 	v4l2_info(v4l2_dev, "AIMSlab Radiotrack II card driver.\n");
 
-	/* mute card - prevents noisy bootups */
-	outb(1, dev->io);
-	dev->muted = 1;
-
 	return 0;
 }
 
diff --git a/drivers/media/radio/radio-sf16fmi.c b/drivers/media/radio/radio-sf16fmi.c
index 985359d18aa..b5a5f89e238 100644
--- a/drivers/media/radio/radio-sf16fmi.c
+++ b/drivers/media/radio/radio-sf16fmi.c
@@ -260,7 +260,7 @@ static int vidioc_s_audio(struct file *file, void *priv,
 
 static const struct v4l2_file_operations fmi_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops fmi_ioctl_ops = {
@@ -382,6 +382,9 @@ static int __init fmi_init(void)
 
 	mutex_init(&fmi->lock);
 
+	/* mute card - prevents noisy bootups */
+	fmi_mute(fmi);
+
 	if (video_register_device(&fmi->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
 		v4l2_device_unregister(v4l2_dev);
 		release_region(fmi->io, 2);
@@ -391,8 +394,6 @@ static int __init fmi_init(void)
 	}
 
 	v4l2_info(v4l2_dev, "card driver at 0x%x\n", fmi->io);
-	/* mute card - prevents noisy bootups */
-	fmi_mute(fmi);
 	return 0;
 }
 
diff --git a/drivers/media/radio/radio-sf16fmr2.c b/drivers/media/radio/radio-sf16fmr2.c
index 52c7bbb32b8..dc3f04c52d5 100644
--- a/drivers/media/radio/radio-sf16fmr2.c
+++ b/drivers/media/radio/radio-sf16fmr2.c
@@ -376,7 +376,7 @@ static int vidioc_s_audio(struct file *file, void *priv,
 
 static const struct v4l2_file_operations fmr2_fops = {
 	.owner          = THIS_MODULE,
-	.ioctl          = video_ioctl2,
+	.unlocked_ioctl = video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops fmr2_ioctl_ops = {
@@ -424,6 +424,10 @@ static int __init fmr2_init(void)
 	fmr2->vdev.release = video_device_release_empty;
 	video_set_drvdata(&fmr2->vdev, fmr2);
 
+	/* mute card - prevents noisy bootups */
+	fmr2_mute(fmr2->io);
+	fmr2_product_info(fmr2);
+
 	if (video_register_device(&fmr2->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
 		v4l2_device_unregister(v4l2_dev);
 		release_region(fmr2->io, 2);
@@ -431,11 +435,6 @@ static int __init fmr2_init(void)
 	}
 
 	v4l2_info(v4l2_dev, "SF16FMR2 radio card driver at 0x%x.\n", fmr2->io);
-	/* mute card - prevents noisy bootups */
-	mutex_lock(&fmr2->lock);
-	fmr2_mute(fmr2->io);
-	fmr2_product_info(fmr2);
-	mutex_unlock(&fmr2->lock);
 	debug_print((KERN_DEBUG "card_type %d\n", fmr2->card_type));
 	return 0;
 }
diff --git a/drivers/media/radio/radio-si4713.c b/drivers/media/radio/radio-si4713.c
index 03829e6818b..726d367ad8d 100644
--- a/drivers/media/radio/radio-si4713.c
+++ b/drivers/media/radio/radio-si4713.c
@@ -53,7 +53,8 @@ struct radio_si4713_device {
 /* radio_si4713_fops - file operations interface */
 static const struct v4l2_file_operations radio_si4713_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	/* Note: locking is done at the subdev level in the i2c driver. */
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 /* Video4Linux Interface */
diff --git a/drivers/media/radio/radio-tea5764.c b/drivers/media/radio/radio-tea5764.c
index 789d2ec66e1..0e71d816c72 100644
--- a/drivers/media/radio/radio-tea5764.c
+++ b/drivers/media/radio/radio-tea5764.c
@@ -142,7 +142,6 @@ struct tea5764_device {
 	struct video_device		*videodev;
 	struct tea5764_regs		regs;
 	struct mutex			mutex;
-	int				users;
 };
 
 /* I2C code related */
@@ -458,41 +457,10 @@ static int vidioc_s_audio(struct file *file, void *priv,
 	return 0;
 }
 
-static int tea5764_open(struct file *file)
-{
-	/* Currently we support only one device */
-	struct tea5764_device *radio = video_drvdata(file);
-
-	mutex_lock(&radio->mutex);
-	/* Only exclusive access */
-	if (radio->users) {
-		mutex_unlock(&radio->mutex);
-		return -EBUSY;
-	}
-	radio->users++;
-	mutex_unlock(&radio->mutex);
-	file->private_data = radio;
-	return 0;
-}
-
-static int tea5764_close(struct file *file)
-{
-	struct tea5764_device *radio = video_drvdata(file);
-
-	if (!radio)
-		return -ENODEV;
-	mutex_lock(&radio->mutex);
-	radio->users--;
-	mutex_unlock(&radio->mutex);
-	return 0;
-}
-
 /* File system interface */
 static const struct v4l2_file_operations tea5764_fops = {
 	.owner		= THIS_MODULE,
-	.open           = tea5764_open,
-	.release        = tea5764_close,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops tea5764_ioctl_ops = {
@@ -527,7 +495,7 @@ static int __devinit tea5764_i2c_probe(struct i2c_client *client,
 	int ret;
 
 	PDEBUG("probe");
-	radio = kmalloc(sizeof(struct tea5764_device), GFP_KERNEL);
+	radio = kzalloc(sizeof(struct tea5764_device), GFP_KERNEL);
 	if (!radio)
 		return -ENOMEM;
 
@@ -555,12 +523,7 @@ static int __devinit tea5764_i2c_probe(struct i2c_client *client,
 
 	i2c_set_clientdata(client, radio);
 	video_set_drvdata(radio->videodev, radio);
-
-	ret = video_register_device(radio->videodev, VFL_TYPE_RADIO, radio_nr);
-	if (ret < 0) {
-		PWARN("Could not register video device!");
-		goto errrel;
-	}
+	radio->videodev->lock = &radio->mutex;
 
 	/* initialize and power off the chip */
 	tea5764_i2c_read(radio);
@@ -568,6 +531,12 @@ static int __devinit tea5764_i2c_probe(struct i2c_client *client,
 	tea5764_mute(radio, 1);
 	tea5764_power_down(radio);
 
+	ret = video_register_device(radio->videodev, VFL_TYPE_RADIO, radio_nr);
+	if (ret < 0) {
+		PWARN("Could not register video device!");
+		goto errrel;
+	}
+
 	PINFO("registered.");
 	return 0;
 errrel:
diff --git a/drivers/media/radio/radio-terratec.c b/drivers/media/radio/radio-terratec.c
index fc1c860fd43..a3266391705 100644
--- a/drivers/media/radio/radio-terratec.c
+++ b/drivers/media/radio/radio-terratec.c
@@ -338,7 +338,7 @@ static int vidioc_s_audio(struct file *file, void *priv,
 
 static const struct v4l2_file_operations terratec_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops terratec_ioctl_ops = {
@@ -389,6 +389,9 @@ static int __init terratec_init(void)
 
 	mutex_init(&tt->lock);
 
+	/* mute card - prevents noisy bootups */
+	tt_write_vol(tt, 0);
+
 	if (video_register_device(&tt->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
 		v4l2_device_unregister(&tt->v4l2_dev);
 		release_region(tt->io, 2);
@@ -396,9 +399,6 @@ static int __init terratec_init(void)
 	}
 
 	v4l2_info(v4l2_dev, "TERRATEC ActivRadio Standalone card driver.\n");
-
-	/* mute card - prevents noisy bootups */
-	tt_write_vol(tt, 0);
 	return 0;
 }
 
diff --git a/drivers/media/radio/radio-timb.c b/drivers/media/radio/radio-timb.c
index b8bb3ef47df..a185610b376 100644
--- a/drivers/media/radio/radio-timb.c
+++ b/drivers/media/radio/radio-timb.c
@@ -34,6 +34,7 @@ struct timbradio {
 	struct v4l2_subdev	*sd_dsp;
 	struct video_device	video_dev;
 	struct v4l2_device	v4l2_dev;
+	struct mutex		lock;
 };
 
 
@@ -142,7 +143,7 @@ static const struct v4l2_ioctl_ops timbradio_ioctl_ops = {
 
 static const struct v4l2_file_operations timbradio_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static int __devinit timbradio_probe(struct platform_device *pdev)
@@ -164,6 +165,7 @@ static int __devinit timbradio_probe(struct platform_device *pdev)
 	}
 
 	tr->pdata = *pdata;
+	mutex_init(&tr->lock);
 
 	strlcpy(tr->video_dev.name, "Timberdale Radio",
 		sizeof(tr->video_dev.name));
@@ -171,6 +173,7 @@ static int __devinit timbradio_probe(struct platform_device *pdev)
 	tr->video_dev.ioctl_ops = &timbradio_ioctl_ops;
 	tr->video_dev.release = video_device_release_empty;
 	tr->video_dev.minor = -1;
+	tr->video_dev.lock = &tr->lock;
 
 	strlcpy(tr->v4l2_dev.name, DRIVER_NAME, sizeof(tr->v4l2_dev.name));
 	err = v4l2_device_register(NULL, &tr->v4l2_dev);
diff --git a/drivers/media/radio/radio-trust.c b/drivers/media/radio/radio-trust.c
index 9d6dcf8af5b..22fa9cc28ab 100644
--- a/drivers/media/radio/radio-trust.c
+++ b/drivers/media/radio/radio-trust.c
@@ -344,7 +344,7 @@ static int vidioc_s_audio(struct file *file, void *priv,
 
 static const struct v4l2_file_operations trust_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops trust_ioctl_ops = {
@@ -396,14 +396,6 @@ static int __init trust_init(void)
 	tr->vdev.release = video_device_release_empty;
 	video_set_drvdata(&tr->vdev, tr);
 
-	if (video_register_device(&tr->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
-		v4l2_device_unregister(v4l2_dev);
-		release_region(tr->io, 2);
-		return -EINVAL;
-	}
-
-	v4l2_info(v4l2_dev, "Trust FM Radio card driver v1.0.\n");
-
 	write_i2c(tr, 2, TDA7318_ADDR, 0x80);	/* speaker att. LF = 0 dB */
 	write_i2c(tr, 2, TDA7318_ADDR, 0xa0);	/* speaker att. RF = 0 dB */
 	write_i2c(tr, 2, TDA7318_ADDR, 0xc0);	/* speaker att. LR = 0 dB */
@@ -418,6 +410,14 @@ static int __init trust_init(void)
 	/* mute card - prevents noisy bootups */
 	tr_setmute(tr, 1);
 
+	if (video_register_device(&tr->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
+		v4l2_device_unregister(v4l2_dev);
+		release_region(tr->io, 2);
+		return -EINVAL;
+	}
+
+	v4l2_info(v4l2_dev, "Trust FM Radio card driver v1.0.\n");
+
 	return 0;
 }
 
diff --git a/drivers/media/radio/radio-typhoon.c b/drivers/media/radio/radio-typhoon.c
index b1f630527dc..8dbbf08f220 100644
--- a/drivers/media/radio/radio-typhoon.c
+++ b/drivers/media/radio/radio-typhoon.c
@@ -317,7 +317,7 @@ static int vidioc_log_status(struct file *file, void *priv)
 
 static const struct v4l2_file_operations typhoon_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops typhoon_ioctl_ops = {
@@ -344,18 +344,18 @@ static int __init typhoon_init(void)
 
 	strlcpy(v4l2_dev->name, "typhoon", sizeof(v4l2_dev->name));
 	dev->io = io;
-	dev->curfreq = dev->mutefreq = mutefreq;
 
 	if (dev->io == -1) {
 		v4l2_err(v4l2_dev, "You must set an I/O address with io=0x316 or io=0x336\n");
 		return -EINVAL;
 	}
 
-	if (dev->mutefreq < 87000 || dev->mutefreq > 108500) {
+	if (mutefreq < 87000 || mutefreq > 108500) {
 		v4l2_err(v4l2_dev, "You must set a frequency (in kHz) used when muting the card,\n");
 		v4l2_err(v4l2_dev, "e.g. with \"mutefreq=87500\" (87000 <= mutefreq <= 108500)\n");
 		return -EINVAL;
 	}
+	dev->curfreq = dev->mutefreq = mutefreq << 4;
 
 	mutex_init(&dev->lock);
 	if (!request_region(dev->io, 8, "typhoon")) {
@@ -378,17 +378,17 @@ static int __init typhoon_init(void)
 	dev->vdev.ioctl_ops = &typhoon_ioctl_ops;
 	dev->vdev.release = video_device_release_empty;
 	video_set_drvdata(&dev->vdev, dev);
+
+	/* mute card - prevents noisy bootups */
+	typhoon_mute(dev);
+
 	if (video_register_device(&dev->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
 		v4l2_device_unregister(&dev->v4l2_dev);
 		release_region(dev->io, 8);
 		return -EINVAL;
 	}
 	v4l2_info(v4l2_dev, "port 0x%x.\n", dev->io);
-	v4l2_info(v4l2_dev, "mute frequency is %lu kHz.\n", dev->mutefreq);
-	dev->mutefreq <<= 4;
-
-	/* mute card - prevents noisy bootups */
-	typhoon_mute(dev);
+	v4l2_info(v4l2_dev, "mute frequency is %lu kHz.\n", mutefreq);
 
 	return 0;
 }
diff --git a/drivers/media/radio/radio-zoltrix.c b/drivers/media/radio/radio-zoltrix.c
index f31eab99c94..af99c5bd88c 100644
--- a/drivers/media/radio/radio-zoltrix.c
+++ b/drivers/media/radio/radio-zoltrix.c
@@ -377,7 +377,7 @@ static int vidioc_s_audio(struct file *file, void *priv,
 static const struct v4l2_file_operations zoltrix_fops =
 {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops zoltrix_ioctl_ops = {
@@ -424,20 +424,6 @@ static int __init zoltrix_init(void)
 		return res;
 	}
 
-	strlcpy(zol->vdev.name, v4l2_dev->name, sizeof(zol->vdev.name));
-	zol->vdev.v4l2_dev = v4l2_dev;
-	zol->vdev.fops = &zoltrix_fops;
-	zol->vdev.ioctl_ops = &zoltrix_ioctl_ops;
-	zol->vdev.release = video_device_release_empty;
-	video_set_drvdata(&zol->vdev, zol);
-
-	if (video_register_device(&zol->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
-		v4l2_device_unregister(v4l2_dev);
-		release_region(zol->io, 2);
-		return -EINVAL;
-	}
-	v4l2_info(v4l2_dev, "Zoltrix Radio Plus card driver.\n");
-
 	mutex_init(&zol->lock);
 
 	/* mute card - prevents noisy bootups */
@@ -452,6 +438,20 @@ static int __init zoltrix_init(void)
 	zol->curvol = 0;
 	zol->stereo = 1;
 
+	strlcpy(zol->vdev.name, v4l2_dev->name, sizeof(zol->vdev.name));
+	zol->vdev.v4l2_dev = v4l2_dev;
+	zol->vdev.fops = &zoltrix_fops;
+	zol->vdev.ioctl_ops = &zoltrix_ioctl_ops;
+	zol->vdev.release = video_device_release_empty;
+	video_set_drvdata(&zol->vdev, zol);
+
+	if (video_register_device(&zol->vdev, VFL_TYPE_RADIO, radio_nr) < 0) {
+		v4l2_device_unregister(v4l2_dev);
+		release_region(zol->io, 2);
+		return -EINVAL;
+	}
+	v4l2_info(v4l2_dev, "Zoltrix Radio Plus card driver.\n");
+
 	return 0;
 }
 
diff --git a/drivers/media/video/arv.c b/drivers/media/video/arv.c
index 31e7a123d19..f989f2820d8 100644
--- a/drivers/media/video/arv.c
+++ b/drivers/media/video/arv.c
@@ -712,7 +712,7 @@ static int ar_initialize(struct ar *ar)
 static const struct v4l2_file_operations ar_fops = {
 	.owner		= THIS_MODULE,
 	.read		= ar_read,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops ar_ioctl_ops = {
diff --git a/drivers/media/video/bt8xx/bttv-driver.c b/drivers/media/video/bt8xx/bttv-driver.c
index a529619e51f..0902ec041c7 100644
--- a/drivers/media/video/bt8xx/bttv-driver.c
+++ b/drivers/media/video/bt8xx/bttv-driver.c
@@ -854,7 +854,6 @@ int check_alloc_btres_lock(struct bttv *btv, struct bttv_fh *fh, int bit)
 		xbits |= RESOURCE_VIDEO_READ | RESOURCE_VIDEO_STREAM;
 
 	/* is it free? */
-	mutex_lock(&btv->lock);
 	if (btv->resources & xbits) {
 		/* no, someone else uses it */
 		goto fail;
@@ -884,11 +883,9 @@ int check_alloc_btres_lock(struct bttv *btv, struct bttv_fh *fh, int bit)
 	/* it's free, grab it */
 	fh->resources  |= bit;
 	btv->resources |= bit;
-	mutex_unlock(&btv->lock);
 	return 1;
 
  fail:
-	mutex_unlock(&btv->lock);
 	return 0;
 }
 
@@ -940,7 +937,6 @@ void free_btres_lock(struct bttv *btv, struct bttv_fh *fh, int bits)
 		/* trying to free ressources not allocated by us ... */
 		printk("bttv: BUG! (btres)\n");
 	}
-	mutex_lock(&btv->lock);
 	fh->resources  &= ~bits;
 	btv->resources &= ~bits;
 
@@ -951,8 +947,6 @@ void free_btres_lock(struct bttv *btv, struct bttv_fh *fh, int bits)
 
 	if (0 == (bits & VBI_RESOURCES))
 		disclaim_vbi_lines(btv);
-
-	mutex_unlock(&btv->lock);
 }
 
 /* ----------------------------------------------------------------------- */
@@ -1713,28 +1707,20 @@ static int bttv_prepare_buffer(struct videobuf_queue *q,struct bttv *btv,
 
 		/* Make sure tvnorm and vbi_end remain consistent
 		   until we're done. */
-		mutex_lock(&btv->lock);
 
 		norm = btv->tvnorm;
 
 		/* In this mode capturing always starts at defrect.top
 		   (default VDELAY), ignoring cropping parameters. */
 		if (btv->vbi_end > bttv_tvnorms[norm].cropcap.defrect.top) {
-			mutex_unlock(&btv->lock);
 			return -EINVAL;
 		}
 
-		mutex_unlock(&btv->lock);
-
 		c.rect = bttv_tvnorms[norm].cropcap.defrect;
 	} else {
-		mutex_lock(&btv->lock);
-
 		norm = btv->tvnorm;
 		c = btv->crop[!!fh->do_crop];
 
-		mutex_unlock(&btv->lock);
-
 		if (width < c.min_scaled_width ||
 		    width > c.max_scaled_width ||
 		    height < c.min_scaled_height)
@@ -1858,7 +1844,6 @@ static int bttv_s_std(struct file *file, void *priv, v4l2_std_id *id)
 	unsigned int i;
 	int err;
 
-	mutex_lock(&btv->lock);
 	err = v4l2_prio_check(&btv->prio, fh->prio);
 	if (err)
 		goto err;
@@ -1874,7 +1859,6 @@ static int bttv_s_std(struct file *file, void *priv, v4l2_std_id *id)
 	set_tvnorm(btv, i);
 
 err:
-	mutex_unlock(&btv->lock);
 
 	return err;
 }
@@ -1898,7 +1882,6 @@ static int bttv_enum_input(struct file *file, void *priv,
 	struct bttv *btv = fh->btv;
 	int rc = 0;
 
-	mutex_lock(&btv->lock);
 	if (i->index >= bttv_tvcards[btv->c.type].video_inputs) {
 		rc = -EINVAL;
 		goto err;
@@ -1928,7 +1911,6 @@ static int bttv_enum_input(struct file *file, void *priv,
 	i->std = BTTV_NORMS;
 
 err:
-	mutex_unlock(&btv->lock);
 
 	return rc;
 }
@@ -1938,9 +1920,7 @@ static int bttv_g_input(struct file *file, void *priv, unsigned int *i)
 	struct bttv_fh *fh = priv;
 	struct bttv *btv = fh->btv;
 
-	mutex_lock(&btv->lock);
 	*i = btv->input;
-	mutex_unlock(&btv->lock);
 
 	return 0;
 }
@@ -1952,7 +1932,6 @@ static int bttv_s_input(struct file *file, void *priv, unsigned int i)
 
 	int err;
 
-	mutex_lock(&btv->lock);
 	err = v4l2_prio_check(&btv->prio, fh->prio);
 	if (unlikely(err))
 		goto err;
@@ -1965,7 +1944,6 @@ static int bttv_s_input(struct file *file, void *priv, unsigned int i)
 	set_input(btv, i, btv->tvnorm);
 
 err:
-	mutex_unlock(&btv->lock);
 	return 0;
 }
 
@@ -1979,7 +1957,6 @@ static int bttv_s_tuner(struct file *file, void *priv,
 	if (unlikely(0 != t->index))
 		return -EINVAL;
 
-	mutex_lock(&btv->lock);
 	if (unlikely(btv->tuner_type == TUNER_ABSENT)) {
 		err = -EINVAL;
 		goto err;
@@ -1995,7 +1972,6 @@ static int bttv_s_tuner(struct file *file, void *priv,
 		btv->audio_mode_gpio(btv, t, 1);
 
 err:
-	mutex_unlock(&btv->lock);
 
 	return 0;
 }
@@ -2006,10 +1982,8 @@ static int bttv_g_frequency(struct file *file, void *priv,
 	struct bttv_fh *fh  = priv;
 	struct bttv *btv = fh->btv;
 
-	mutex_lock(&btv->lock);
 	f->type = btv->radio_user ? V4L2_TUNER_RADIO : V4L2_TUNER_ANALOG_TV;
 	f->frequency = btv->freq;
-	mutex_unlock(&btv->lock);
 
 	return 0;
 }
@@ -2024,7 +1998,6 @@ static int bttv_s_frequency(struct file *file, void *priv,
 	if (unlikely(f->tuner != 0))
 		return -EINVAL;
 
-	mutex_lock(&btv->lock);
 	err = v4l2_prio_check(&btv->prio, fh->prio);
 	if (unlikely(err))
 		goto err;
@@ -2039,7 +2012,6 @@ static int bttv_s_frequency(struct file *file, void *priv,
 	if (btv->has_matchbox && btv->radio_user)
 		tea5757_set_freq(btv, btv->freq);
 err:
-	mutex_unlock(&btv->lock);
 
 	return 0;
 }
@@ -2172,7 +2144,6 @@ limit_scaled_size_lock       (struct bttv_fh *               fh,
 
 	/* Make sure tvnorm, vbi_end and the current cropping parameters
 	   remain consistent until we're done. */
-	mutex_lock(&btv->lock);
 
 	b = &bttv_tvnorms[btv->tvnorm].cropcap.bounds;
 
@@ -2250,7 +2221,6 @@ limit_scaled_size_lock       (struct bttv_fh *               fh,
 	rc = 0; /* success */
 
  fail:
-	mutex_unlock(&btv->lock);
 
 	return rc;
 }
@@ -2282,9 +2252,7 @@ verify_window_lock		(struct bttv_fh *               fh,
 	if (V4L2_FIELD_ANY == field) {
 		__s32 height2;
 
-		mutex_lock(&fh->btv->lock);
 		height2 = fh->btv->crop[!!fh->do_crop].rect.height >> 1;
-		mutex_unlock(&fh->btv->lock);
 		field = (win->w.height > height2)
 			? V4L2_FIELD_INTERLACED
 			: V4L2_FIELD_TOP;
@@ -2360,7 +2328,6 @@ static int setup_window_lock(struct bttv_fh *fh, struct bttv *btv,
 		}
 	}
 
-	mutex_lock(&fh->cap.vb_lock);
 	/* clip against screen */
 	if (NULL != btv->fbuf.base)
 		n = btcx_screen_clips(btv->fbuf.fmt.width, btv->fbuf.fmt.height,
@@ -2391,13 +2358,6 @@ static int setup_window_lock(struct bttv_fh *fh, struct bttv *btv,
 	fh->ov.field    = win->field;
 	fh->ov.setup_ok = 1;
 
-	/*
-	 * FIXME: btv is protected by btv->lock mutex, while btv->init
-	 *	  is protected by fh->cap.vb_lock. This seems to open the
-	 *	  possibility for some race situations. Maybe the better would
-	 *	  be to unify those locks or to use another way to store the
-	 *	  init values that will be consumed by videobuf callbacks
-	 */
 	btv->init.ov.w.width   = win->w.width;
 	btv->init.ov.w.height  = win->w.height;
 	btv->init.ov.field     = win->field;
@@ -2412,7 +2372,6 @@ static int setup_window_lock(struct bttv_fh *fh, struct bttv *btv,
 		bttv_overlay_risc(btv, &fh->ov, fh->ovfmt, new);
 		retval = bttv_switch_overlay(btv,fh,new);
 	}
-	mutex_unlock(&fh->cap.vb_lock);
 	return retval;
 }
 
@@ -2526,9 +2485,7 @@ static int bttv_try_fmt_vid_cap(struct file *file, void *priv,
 	if (V4L2_FIELD_ANY == field) {
 		__s32 height2;
 
-		mutex_lock(&btv->lock);
 		height2 = btv->crop[!!fh->do_crop].rect.height >> 1;
-		mutex_unlock(&btv->lock);
 		field = (f->fmt.pix.height > height2)
 			? V4L2_FIELD_INTERLACED
 			: V4L2_FIELD_BOTTOM;
@@ -2614,7 +2571,6 @@ static int bttv_s_fmt_vid_cap(struct file *file, void *priv,
 	fmt = format_by_fourcc(f->fmt.pix.pixelformat);
 
 	/* update our state informations */
-	mutex_lock(&fh->cap.vb_lock);
 	fh->fmt              = fmt;
 	fh->cap.field        = f->fmt.pix.field;
 	fh->cap.last         = V4L2_FIELD_NONE;
@@ -2623,7 +2579,6 @@ static int bttv_s_fmt_vid_cap(struct file *file, void *priv,
 	btv->init.fmt        = fmt;
 	btv->init.width      = f->fmt.pix.width;
 	btv->init.height     = f->fmt.pix.height;
-	mutex_unlock(&fh->cap.vb_lock);
 
 	return 0;
 }
@@ -2649,11 +2604,9 @@ static int vidiocgmbuf(struct file *file, void *priv, struct video_mbuf *mbuf)
 	unsigned int i;
 	struct bttv_fh *fh = priv;
 
-	mutex_lock(&fh->cap.vb_lock);
 	retval = __videobuf_mmap_setup(&fh->cap, gbuffers, gbufsize,
 				     V4L2_MEMORY_MMAP);
 	if (retval < 0) {
-		mutex_unlock(&fh->cap.vb_lock);
 		return retval;
 	}
 
@@ -2665,7 +2618,6 @@ static int vidiocgmbuf(struct file *file, void *priv, struct video_mbuf *mbuf)
 	for (i = 0; i < gbuffers; i++)
 		mbuf->offsets[i] = i * gbufsize;
 
-	mutex_unlock(&fh->cap.vb_lock);
 	return 0;
 }
 #endif
@@ -2775,10 +2727,8 @@ static int bttv_overlay(struct file *file, void *f, unsigned int on)
 	int retval = 0;
 
 	if (on) {
-		mutex_lock(&fh->cap.vb_lock);
 		/* verify args */
 		if (unlikely(!btv->fbuf.base)) {
-			mutex_unlock(&fh->cap.vb_lock);
 			return -EINVAL;
 		}
 		if (unlikely(!fh->ov.setup_ok)) {
@@ -2787,13 +2737,11 @@ static int bttv_overlay(struct file *file, void *f, unsigned int on)
 		}
 		if (retval)
 			return retval;
-		mutex_unlock(&fh->cap.vb_lock);
 	}
 
 	if (!check_alloc_btres_lock(btv, fh, RESOURCE_OVERLAY))
 		return -EBUSY;
 
-	mutex_lock(&fh->cap.vb_lock);
 	if (on) {
 		fh->ov.tvnorm = btv->tvnorm;
 		new = videobuf_sg_alloc(sizeof(*new));
@@ -2805,7 +2753,6 @@ static int bttv_overlay(struct file *file, void *f, unsigned int on)
 
 	/* switch over */
 	retval = bttv_switch_overlay(btv, fh, new);
-	mutex_unlock(&fh->cap.vb_lock);
 	return retval;
 }
 
@@ -2844,7 +2791,6 @@ static int bttv_s_fbuf(struct file *file, void *f,
 	}
 
 	/* ok, accept it */
-	mutex_lock(&fh->cap.vb_lock);
 	btv->fbuf.base       = fb->base;
 	btv->fbuf.fmt.width  = fb->fmt.width;
 	btv->fbuf.fmt.height = fb->fmt.height;
@@ -2876,7 +2822,6 @@ static int bttv_s_fbuf(struct file *file, void *f,
 			retval = bttv_switch_overlay(btv, fh, new);
 		}
 	}
-	mutex_unlock(&fh->cap.vb_lock);
 	return retval;
 }
 
@@ -2955,7 +2900,6 @@ static int bttv_queryctrl(struct file *file, void *priv,
 	     c->id >= V4L2_CID_PRIVATE_LASTP1))
 		return -EINVAL;
 
-	mutex_lock(&btv->lock);
 	if (!btv->volume_gpio && (c->id == V4L2_CID_AUDIO_VOLUME))
 		*c = no_ctl;
 	else {
@@ -2963,7 +2907,6 @@ static int bttv_queryctrl(struct file *file, void *priv,
 
 		*c = (NULL != ctrl) ? *ctrl : no_ctl;
 	}
-	mutex_unlock(&btv->lock);
 
 	return 0;
 }
@@ -2974,10 +2917,8 @@ static int bttv_g_parm(struct file *file, void *f,
 	struct bttv_fh *fh = f;
 	struct bttv *btv = fh->btv;
 
-	mutex_lock(&btv->lock);
 	v4l2_video_std_frame_period(bttv_tvnorms[btv->tvnorm].v4l2_id,
 				    &parm->parm.capture.timeperframe);
-	mutex_unlock(&btv->lock);
 
 	return 0;
 }
@@ -2993,7 +2934,6 @@ static int bttv_g_tuner(struct file *file, void *priv,
 	if (0 != t->index)
 		return -EINVAL;
 
-	mutex_lock(&btv->lock);
 	t->rxsubchans = V4L2_TUNER_SUB_MONO;
 	bttv_call_all(btv, tuner, g_tuner, t);
 	strcpy(t->name, "Television");
@@ -3005,7 +2945,6 @@ static int bttv_g_tuner(struct file *file, void *priv,
 	if (btv->audio_mode_gpio)
 		btv->audio_mode_gpio(btv, t, 0);
 
-	mutex_unlock(&btv->lock);
 	return 0;
 }
 
@@ -3014,9 +2953,7 @@ static int bttv_g_priority(struct file *file, void *f, enum v4l2_priority *p)
 	struct bttv_fh *fh = f;
 	struct bttv *btv = fh->btv;
 
-	mutex_lock(&btv->lock);
 	*p = v4l2_prio_max(&btv->prio);
-	mutex_unlock(&btv->lock);
 
 	return 0;
 }
@@ -3028,9 +2965,7 @@ static int bttv_s_priority(struct file *file, void *f,
 	struct bttv *btv = fh->btv;
 	int	rc;
 
-	mutex_lock(&btv->lock);
 	rc = v4l2_prio_change(&btv->prio, &fh->prio, prio);
-	mutex_unlock(&btv->lock);
 
 	return rc;
 }
@@ -3045,9 +2980,7 @@ static int bttv_cropcap(struct file *file, void *priv,
 	    cap->type != V4L2_BUF_TYPE_VIDEO_OVERLAY)
 		return -EINVAL;
 
-	mutex_lock(&btv->lock);
 	*cap = bttv_tvnorms[btv->tvnorm].cropcap;
-	mutex_unlock(&btv->lock);
 
 	return 0;
 }
@@ -3065,9 +2998,7 @@ static int bttv_g_crop(struct file *file, void *f, struct v4l2_crop *crop)
 	   inconsistent with fh->width or fh->height and apps
 	   do not expect a change here. */
 
-	mutex_lock(&btv->lock);
 	crop->c = btv->crop[!!fh->do_crop].rect;
-	mutex_unlock(&btv->lock);
 
 	return 0;
 }
@@ -3091,17 +3022,14 @@ static int bttv_s_crop(struct file *file, void *f, struct v4l2_crop *crop)
 	/* Make sure tvnorm, vbi_end and the current cropping
 	   parameters remain consistent until we're done. Note
 	   read() may change vbi_end in check_alloc_btres_lock(). */
-	mutex_lock(&btv->lock);
 	retval = v4l2_prio_check(&btv->prio, fh->prio);
 	if (0 != retval) {
-		mutex_unlock(&btv->lock);
 		return retval;
 	}
 
 	retval = -EBUSY;
 
 	if (locked_btres(fh->btv, VIDEO_RESOURCES)) {
-		mutex_unlock(&btv->lock);
 		return retval;
 	}
 
@@ -3113,7 +3041,6 @@ static int bttv_s_crop(struct file *file, void *f, struct v4l2_crop *crop)
 
 	b_top = max(b->top, btv->vbi_end);
 	if (b_top + 32 >= b_bottom) {
-		mutex_unlock(&btv->lock);
 		return retval;
 	}
 
@@ -3136,12 +3063,8 @@ static int bttv_s_crop(struct file *file, void *f, struct v4l2_crop *crop)
 
 	btv->crop[1] = c;
 
-	mutex_unlock(&btv->lock);
-
 	fh->do_crop = 1;
 
-	mutex_lock(&fh->cap.vb_lock);
-
 	if (fh->width < c.min_scaled_width) {
 		fh->width = c.min_scaled_width;
 		btv->init.width = c.min_scaled_width;
@@ -3158,8 +3081,6 @@ static int bttv_s_crop(struct file *file, void *f, struct v4l2_crop *crop)
 		btv->init.height = c.max_scaled_height;
 	}
 
-	mutex_unlock(&fh->cap.vb_lock);
-
 	return 0;
 }
 
@@ -3227,7 +3148,6 @@ static unsigned int bttv_poll(struct file *file, poll_table *wait)
 		return videobuf_poll_stream(file, &fh->vbi, wait);
 	}
 
-	mutex_lock(&fh->cap.vb_lock);
 	if (check_btres(fh,RESOURCE_VIDEO_STREAM)) {
 		/* streaming capture */
 		if (list_empty(&fh->cap.stream))
@@ -3262,7 +3182,6 @@ static unsigned int bttv_poll(struct file *file, poll_table *wait)
 	else
 		rc = 0;
 err:
-	mutex_unlock(&fh->cap.vb_lock);
 	return rc;
 }
 
@@ -3293,23 +3212,11 @@ static int bttv_open(struct file *file)
 		return -ENOMEM;
 	file->private_data = fh;
 
-	/*
-	 * btv is protected by btv->lock mutex, while btv->init and other
-	 * streaming vars are protected by fh->cap.vb_lock. We need to take
-	 * care of both locks to avoid troubles. However, vb_lock is used also
-	 * inside videobuf, without calling buf->lock. So, it is a very bad
-	 * idea to hold both locks at the same time.
-	 * Let's first copy btv->init at fh, holding cap.vb_lock, and then work
-	 * with the rest of init, holding btv->lock.
-	 */
-	mutex_lock(&fh->cap.vb_lock);
 	*fh = btv->init;
-	mutex_unlock(&fh->cap.vb_lock);
 
 	fh->type = type;
 	fh->ov.setup_ok = 0;
 
-	mutex_lock(&btv->lock);
 	v4l2_prio_open(&btv->prio, &fh->prio);
 
 	videobuf_queue_sg_init(&fh->cap, &bttv_video_qops,
@@ -3317,13 +3224,13 @@ static int bttv_open(struct file *file)
 			    V4L2_BUF_TYPE_VIDEO_CAPTURE,
 			    V4L2_FIELD_INTERLACED,
 			    sizeof(struct bttv_buffer),
-			    fh, NULL);
+			    fh, &btv->lock);
 	videobuf_queue_sg_init(&fh->vbi, &bttv_vbi_qops,
 			    &btv->c.pci->dev, &btv->s_lock,
 			    V4L2_BUF_TYPE_VBI_CAPTURE,
 			    V4L2_FIELD_SEQ_TB,
 			    sizeof(struct bttv_buffer),
-			    fh, NULL);
+			    fh, &btv->lock);
 	set_tvnorm(btv,btv->tvnorm);
 	set_input(btv, btv->input, btv->tvnorm);
 
@@ -3346,7 +3253,6 @@ static int bttv_open(struct file *file)
 	bttv_vbi_fmt_reset(&fh->vbi_fmt, btv->tvnorm);
 
 	bttv_field_count(btv);
-	mutex_unlock(&btv->lock);
 	return 0;
 }
 
@@ -3355,7 +3261,6 @@ static int bttv_release(struct file *file)
 	struct bttv_fh *fh = file->private_data;
 	struct bttv *btv = fh->btv;
 
-	mutex_lock(&btv->lock);
 	/* turn off overlay */
 	if (check_btres(fh, RESOURCE_OVERLAY))
 		bttv_switch_overlay(btv,fh,NULL);
@@ -3381,14 +3286,8 @@ static int bttv_release(struct file *file)
 
 	/* free stuff */
 
-	/*
-	 * videobuf uses cap.vb_lock - we should avoid holding btv->lock,
-	 * otherwise we may have dead lock conditions
-	 */
-	mutex_unlock(&btv->lock);
 	videobuf_mmap_free(&fh->cap);
 	videobuf_mmap_free(&fh->vbi);
-	mutex_lock(&btv->lock);
 	v4l2_prio_close(&btv->prio, fh->prio);
 	file->private_data = NULL;
 	kfree(fh);
@@ -3398,7 +3297,6 @@ static int bttv_release(struct file *file)
 
 	if (!btv->users)
 		audio_mute(btv, 1);
-	mutex_unlock(&btv->lock);
 
 	return 0;
 }
@@ -3502,11 +3400,8 @@ static int radio_open(struct file *file)
 	if (unlikely(!fh))
 		return -ENOMEM;
 	file->private_data = fh;
-	mutex_lock(&fh->cap.vb_lock);
 	*fh = btv->init;
-	mutex_unlock(&fh->cap.vb_lock);
 
-	mutex_lock(&btv->lock);
 	v4l2_prio_open(&btv->prio, &fh->prio);
 
 	btv->radio_user++;
@@ -3514,7 +3409,6 @@ static int radio_open(struct file *file)
 	bttv_call_all(btv, tuner, s_radio);
 	audio_input(btv,TVAUDIO_INPUT_RADIO);
 
-	mutex_unlock(&btv->lock);
 	return 0;
 }
 
@@ -3524,7 +3418,6 @@ static int radio_release(struct file *file)
 	struct bttv *btv = fh->btv;
 	struct rds_command cmd;
 
-	mutex_lock(&btv->lock);
 	v4l2_prio_close(&btv->prio, fh->prio);
 	file->private_data = NULL;
 	kfree(fh);
@@ -3532,7 +3425,6 @@ static int radio_release(struct file *file)
 	btv->radio_user--;
 
 	bttv_call_all(btv, core, ioctl, RDS_CMD_CLOSE, &cmd);
-	mutex_unlock(&btv->lock);
 
 	return 0;
 }
@@ -3561,7 +3453,6 @@ static int radio_g_tuner(struct file *file, void *priv, struct v4l2_tuner *t)
 		return -EINVAL;
 	if (0 != t->index)
 		return -EINVAL;
-	mutex_lock(&btv->lock);
 	strcpy(t->name, "Radio");
 	t->type = V4L2_TUNER_RADIO;
 
@@ -3570,8 +3461,6 @@ static int radio_g_tuner(struct file *file, void *priv, struct v4l2_tuner *t)
 	if (btv->audio_mode_gpio)
 		btv->audio_mode_gpio(btv, t, 0);
 
-	mutex_unlock(&btv->lock);
-
 	return 0;
 }
 
@@ -3692,7 +3581,7 @@ static const struct v4l2_file_operations radio_fops =
 	.open	  = radio_open,
 	.read     = radio_read,
 	.release  = radio_release,
-	.ioctl	  = video_ioctl2,
+	.unlocked_ioctl = video_ioctl2,
 	.poll     = radio_poll,
 };
 
diff --git a/drivers/media/video/bw-qcam.c b/drivers/media/video/bw-qcam.c
index 935e0c9a967..c1193506131 100644
--- a/drivers/media/video/bw-qcam.c
+++ b/drivers/media/video/bw-qcam.c
@@ -860,7 +860,7 @@ static ssize_t qcam_read(struct file *file, char __user *buf,
 
 static const struct v4l2_file_operations qcam_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl          = video_ioctl2,
+	.unlocked_ioctl = video_ioctl2,
 	.read		= qcam_read,
 };
 
diff --git a/drivers/media/video/c-qcam.c b/drivers/media/video/c-qcam.c
index 6e4b19698c1..24fc00965a1 100644
--- a/drivers/media/video/c-qcam.c
+++ b/drivers/media/video/c-qcam.c
@@ -718,7 +718,7 @@ static ssize_t qcam_read(struct file *file, char __user *buf,
 
 static const struct v4l2_file_operations qcam_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 	.read		= qcam_read,
 };
 
diff --git a/drivers/media/video/cafe_ccic.c b/drivers/media/video/cafe_ccic.c
index 260c666ce93..0dfff50891e 100644
--- a/drivers/media/video/cafe_ccic.c
+++ b/drivers/media/video/cafe_ccic.c
@@ -1775,7 +1775,7 @@ static const struct v4l2_file_operations cafe_v4l_fops = {
 	.read = cafe_v4l_read,
 	.poll = cafe_v4l_poll,
 	.mmap = cafe_v4l_mmap,
-	.ioctl = video_ioctl2,
+	.unlocked_ioctl = video_ioctl2,
 };
 
 static const struct v4l2_ioctl_ops cafe_v4l_ioctl_ops = {
diff --git a/drivers/media/video/cx18/cx18-alsa-pcm.c b/drivers/media/video/cx18/cx18-alsa-pcm.c
index 8f55692db36..82d195be919 100644
--- a/drivers/media/video/cx18/cx18-alsa-pcm.c
+++ b/drivers/media/video/cx18/cx18-alsa-pcm.c
@@ -218,7 +218,13 @@ static int snd_cx18_pcm_capture_close(struct snd_pcm_substream *substream)
 static int snd_cx18_pcm_ioctl(struct snd_pcm_substream *substream,
 		     unsigned int cmd, void *arg)
 {
-	return snd_pcm_lib_ioctl(substream, cmd, arg);
+	struct snd_cx18_card *cxsc = snd_pcm_substream_chip(substream);
+	int ret;
+
+	snd_cx18_lock(cxsc);
+	ret = snd_pcm_lib_ioctl(substream, cmd, arg);
+	snd_cx18_unlock(cxsc);
+	return ret;
 }
 
 
diff --git a/drivers/media/video/cx18/cx18-streams.c b/drivers/media/video/cx18/cx18-streams.c
index 9045f1ece0e..ab461e27d9d 100644
--- a/drivers/media/video/cx18/cx18-streams.c
+++ b/drivers/media/video/cx18/cx18-streams.c
@@ -41,7 +41,7 @@ static struct v4l2_file_operations cx18_v4l2_enc_fops = {
 	.read = cx18_v4l2_read,
 	.open = cx18_v4l2_open,
 	/* FIXME change to video_ioctl2 if serialization lock can be removed */
-	.ioctl = cx18_v4l2_ioctl,
+	.unlocked_ioctl = cx18_v4l2_ioctl,
 	.release = cx18_v4l2_close,
 	.poll = cx18_v4l2_enc_poll,
 };
diff --git a/drivers/media/video/et61x251/et61x251_core.c b/drivers/media/video/et61x251/et61x251_core.c
index a5cfc76b40b..bb164099ea2 100644
--- a/drivers/media/video/et61x251/et61x251_core.c
+++ b/drivers/media/video/et61x251/et61x251_core.c
@@ -2530,7 +2530,7 @@ static const struct v4l2_file_operations et61x251_fops = {
 	.owner = THIS_MODULE,
 	.open =    et61x251_open,
 	.release = et61x251_release,
-	.ioctl =   et61x251_ioctl,
+	.unlocked_ioctl =   et61x251_ioctl,
 	.read =    et61x251_read,
 	.poll =    et61x251_poll,
 	.mmap =    et61x251_mmap,
diff --git a/drivers/media/video/gspca/sonixj.c b/drivers/media/video/gspca/sonixj.c
index 330dadc0010..e23de57e2c7 100644
--- a/drivers/media/video/gspca/sonixj.c
+++ b/drivers/media/video/gspca/sonixj.c
@@ -63,7 +63,10 @@ struct sd {
 #define QUALITY_DEF 80
 	u8 jpegqual;			/* webcam quality */
 
+	u8 reg01;
+	u8 reg17;
 	u8 reg18;
+	u8 flags;
 
 	s8 ag_cnt;
 #define AG_CNT_START 13
@@ -96,6 +99,22 @@ enum sensors {
 	SENSOR_SP80708,
 };
 
+/* device flags */
+#define PDN_INV	1		/* inverse pin S_PWR_DN / sn_xxx tables */
+
+/* sn9c1xx definitions */
+/* register 0x01 */
+#define S_PWR_DN	0x01	/* sensor power down */
+#define S_PDN_INV	0x02	/* inverse pin S_PWR_DN */
+#define V_TX_EN		0x04	/* video transfer enable */
+#define LED		0x08	/* output to pin LED */
+#define SCL_SEL_OD	0x20	/* open-drain mode */
+#define SYS_SEL_48M	0x40	/* system clock 0: 24MHz, 1: 48MHz */
+/* register 0x17 */
+#define MCK_SIZE_MASK	0x1f	/* sensor master clock */
+#define SEN_CLK_EN	0x20	/* enable sensor clock */
+#define DEF_EN		0x80	/* defect pixel by 0: soft, 1: hard */
+
 /* V4L2 controls supported by the driver */
 static void setbrightness(struct gspca_dev *gspca_dev);
 static void setcontrast(struct gspca_dev *gspca_dev);
@@ -1755,141 +1774,6 @@ static void po2030n_probe(struct gspca_dev *gspca_dev)
 	}
 }
 
-static void bridge_init(struct gspca_dev *gspca_dev,
-			  const u8 *sn9c1xx)
-{
-	struct sd *sd = (struct sd *) gspca_dev;
-	u8 reg0102[2];
-	const u8 *reg9a;
-	static const u8 reg9a_def[] =
-		{0x00, 0x40, 0x20, 0x00, 0x00, 0x00};
-	static const u8 reg9a_spec[] =
-		{0x00, 0x40, 0x38, 0x30, 0x00, 0x20};
-	static const u8 regd4[] = {0x60, 0x00, 0x00};
-
-	/* sensor clock already enabled in sd_init */
-	/* reg_w1(gspca_dev, 0xf1, 0x00); */
-	reg_w1(gspca_dev, 0x01, sn9c1xx[1]);
-
-	/* configure gpio */
-	reg0102[0] = sn9c1xx[1];
-	reg0102[1] = sn9c1xx[2];
-	if (gspca_dev->audio)
-		reg0102[1] |= 0x04;	/* keep the audio connection */
-	reg_w(gspca_dev, 0x01, reg0102, 2);
-	reg_w(gspca_dev, 0x08, &sn9c1xx[8], 2);
-	reg_w(gspca_dev, 0x17, &sn9c1xx[0x17], 5);
-	switch (sd->sensor) {
-	case SENSOR_GC0307:
-	case SENSOR_OV7660:
-	case SENSOR_PO1030:
-	case SENSOR_PO2030N:
-	case SENSOR_SOI768:
-	case SENSOR_SP80708:
-		reg9a = reg9a_spec;
-		break;
-	default:
-		reg9a = reg9a_def;
-		break;
-	}
-	reg_w(gspca_dev, 0x9a, reg9a, 6);
-
-	reg_w(gspca_dev, 0xd4, regd4, sizeof regd4);
-
-	reg_w(gspca_dev, 0x03, &sn9c1xx[3], 0x0f);
-
-	switch (sd->sensor) {
-	case SENSOR_ADCM1700:
-		reg_w1(gspca_dev, 0x01, 0x43);
-		reg_w1(gspca_dev, 0x17, 0x62);
-		reg_w1(gspca_dev, 0x01, 0x42);
-		reg_w1(gspca_dev, 0x01, 0x42);
-		break;
-	case SENSOR_GC0307:
-		msleep(50);
-		reg_w1(gspca_dev, 0x01, 0x61);
-		reg_w1(gspca_dev, 0x17, 0x22);
-		reg_w1(gspca_dev, 0x01, 0x60);
-		reg_w1(gspca_dev, 0x01, 0x40);
-		msleep(50);
-		break;
-	case SENSOR_MI0360B:
-		reg_w1(gspca_dev, 0x01, 0x61);
-		reg_w1(gspca_dev, 0x17, 0x60);
-		reg_w1(gspca_dev, 0x01, 0x60);
-		reg_w1(gspca_dev, 0x01, 0x40);
-		break;
-	case SENSOR_MT9V111:
-		reg_w1(gspca_dev, 0x01, 0x61);
-		reg_w1(gspca_dev, 0x17, 0x61);
-		reg_w1(gspca_dev, 0x01, 0x60);
-		reg_w1(gspca_dev, 0x01, 0x40);
-		break;
-	case SENSOR_OM6802:
-		msleep(10);
-		reg_w1(gspca_dev, 0x02, 0x73);
-		reg_w1(gspca_dev, 0x17, 0x60);
-		reg_w1(gspca_dev, 0x01, 0x22);
-		msleep(100);
-		reg_w1(gspca_dev, 0x01, 0x62);
-		reg_w1(gspca_dev, 0x17, 0x64);
-		reg_w1(gspca_dev, 0x17, 0x64);
-		reg_w1(gspca_dev, 0x01, 0x42);
-		msleep(10);
-		reg_w1(gspca_dev, 0x01, 0x42);
-		i2c_w8(gspca_dev, om6802_init0[0]);
-		i2c_w8(gspca_dev, om6802_init0[1]);
-		msleep(15);
-		reg_w1(gspca_dev, 0x02, 0x71);
-		msleep(150);
-		break;
-	case SENSOR_OV7630:
-		reg_w1(gspca_dev, 0x01, 0x61);
-		reg_w1(gspca_dev, 0x17, 0xe2);
-		reg_w1(gspca_dev, 0x01, 0x60);
-		reg_w1(gspca_dev, 0x01, 0x40);
-		break;
-	case SENSOR_OV7648:
-		reg_w1(gspca_dev, 0x01, 0x63);
-		reg_w1(gspca_dev, 0x17, 0x20);
-		reg_w1(gspca_dev, 0x01, 0x62);
-		reg_w1(gspca_dev, 0x01, 0x42);
-		break;
-	case SENSOR_PO1030:
-	case SENSOR_SOI768:
-		reg_w1(gspca_dev, 0x01, 0x61);
-		reg_w1(gspca_dev, 0x17, 0x20);
-		reg_w1(gspca_dev, 0x01, 0x60);
-		reg_w1(gspca_dev, 0x01, 0x40);
-		break;
-	case SENSOR_PO2030N:
-	case SENSOR_OV7660:
-		reg_w1(gspca_dev, 0x01, 0x63);
-		reg_w1(gspca_dev, 0x17, 0x20);
-		reg_w1(gspca_dev, 0x01, 0x62);
-		reg_w1(gspca_dev, 0x01, 0x42);
-		break;
-	case SENSOR_SP80708:
-		reg_w1(gspca_dev, 0x01, 0x63);
-		reg_w1(gspca_dev, 0x17, 0x20);
-		reg_w1(gspca_dev, 0x01, 0x62);
-		reg_w1(gspca_dev, 0x01, 0x42);
-		msleep(100);
-		reg_w1(gspca_dev, 0x02, 0x62);
-		break;
-	default:
-/*	case SENSOR_HV7131R: */
-/*	case SENSOR_MI0360: */
-/*	case SENSOR_MO4000: */
-		reg_w1(gspca_dev, 0x01, 0x43);
-		reg_w1(gspca_dev, 0x17, 0x61);
-		reg_w1(gspca_dev, 0x01, 0x42);
-		if (sd->sensor == SENSOR_HV7131R)
-			hv7131r_probe(gspca_dev);
-		break;
-	}
-}
-
 /* this function is called at probe time */
 static int sd_config(struct gspca_dev *gspca_dev,
 			const struct usb_device_id *id)
@@ -1898,7 +1782,8 @@ static int sd_config(struct gspca_dev *gspca_dev,
 	struct cam *cam;
 
 	sd->bridge = id->driver_info >> 16;
-	sd->sensor = id->driver_info;
+	sd->sensor = id->driver_info >> 8;
+	sd->flags = id->driver_info;
 
 	cam = &gspca_dev->cam;
 	if (sd->sensor == SENSOR_ADCM1700) {
@@ -1929,7 +1814,7 @@ static int sd_init(struct gspca_dev *gspca_dev)
 	/* setup a selector by bridge */
 	reg_w1(gspca_dev, 0xf1, 0x01);
 	reg_r(gspca_dev, 0x00, 1);
-	reg_w1(gspca_dev, 0xf1, gspca_dev->usb_buf[0]);
+	reg_w1(gspca_dev, 0xf1, 0x00);
 	reg_r(gspca_dev, 0x00, 1);		/* get sonix chip id */
 	regF1 = gspca_dev->usb_buf[0];
 	if (gspca_dev->usb_err < 0)
@@ -2423,10 +2308,17 @@ static int sd_start(struct gspca_dev *gspca_dev)
 {
 	struct sd *sd = (struct sd *) gspca_dev;
 	int i;
-	u8 reg1, reg17;
+	u8 reg01, reg17;
+	u8 reg0102[2];
 	const u8 *sn9c1xx;
 	const u8 (*init)[8];
+	const u8 *reg9a;
 	int mode;
+	static const u8 reg9a_def[] =
+		{0x00, 0x40, 0x20, 0x00, 0x00, 0x00};
+	static const u8 reg9a_spec[] =
+		{0x00, 0x40, 0x38, 0x30, 0x00, 0x20};
+	static const u8 regd4[] = {0x60, 0x00, 0x00};
 	static const u8 C0[] = { 0x2d, 0x2d, 0x3a, 0x05, 0x04, 0x3f };
 	static const u8 CA[] = { 0x28, 0xd8, 0x14, 0xec };
 	static const u8 CA_adcm1700[] =
@@ -2448,7 +2340,85 @@ static int sd_start(struct gspca_dev *gspca_dev)
 
 	/* initialize the bridge */
 	sn9c1xx = sn_tb[sd->sensor];
-	bridge_init(gspca_dev, sn9c1xx);
+
+	/* sensor clock already enabled in sd_init */
+	/* reg_w1(gspca_dev, 0xf1, 0x00); */
+	reg01 = sn9c1xx[1];
+	if (sd->flags & PDN_INV)
+		reg01 ^= S_PDN_INV;		/* power down inverted */
+	reg_w1(gspca_dev, 0x01, reg01);
+
+	/* configure gpio */
+	reg0102[0] = reg01;
+	reg0102[1] = sn9c1xx[2];
+	if (gspca_dev->audio)
+		reg0102[1] |= 0x04;	/* keep the audio connection */
+	reg_w(gspca_dev, 0x01, reg0102, 2);
+	reg_w(gspca_dev, 0x08, &sn9c1xx[8], 2);
+	reg_w(gspca_dev, 0x17, &sn9c1xx[0x17], 5);
+	switch (sd->sensor) {
+	case SENSOR_GC0307:
+	case SENSOR_OV7660:
+	case SENSOR_PO1030:
+	case SENSOR_PO2030N:
+	case SENSOR_SOI768:
+	case SENSOR_SP80708:
+		reg9a = reg9a_spec;
+		break;
+	default:
+		reg9a = reg9a_def;
+		break;
+	}
+	reg_w(gspca_dev, 0x9a, reg9a, 6);
+
+	reg_w(gspca_dev, 0xd4, regd4, sizeof regd4);
+
+	reg_w(gspca_dev, 0x03, &sn9c1xx[3], 0x0f);
+
+	reg17 = sn9c1xx[0x17];
+	switch (sd->sensor) {
+	case SENSOR_GC0307:
+		msleep(50);		/*fixme: is it useful? */
+		break;
+	case SENSOR_OM6802:
+		msleep(10);
+		reg_w1(gspca_dev, 0x02, 0x73);
+		reg17 |= SEN_CLK_EN;
+		reg_w1(gspca_dev, 0x17, reg17);
+		reg_w1(gspca_dev, 0x01, 0x22);
+		msleep(100);
+		reg01 = SCL_SEL_OD | S_PDN_INV;
+		reg17 &= MCK_SIZE_MASK;
+		reg17 |= 0x04;		/* clock / 4 */
+		break;
+	}
+	reg01 |= SYS_SEL_48M;
+	reg_w1(gspca_dev, 0x01, reg01);
+	reg17 |= SEN_CLK_EN;
+	reg_w1(gspca_dev, 0x17, reg17);
+	reg01 &= ~S_PWR_DN;		/* sensor power on */
+	reg_w1(gspca_dev, 0x01, reg01);
+	reg01 &= ~SYS_SEL_48M;
+	reg_w1(gspca_dev, 0x01, reg01);
+
+	switch (sd->sensor) {
+	case SENSOR_HV7131R:
+		hv7131r_probe(gspca_dev);	/*fixme: is it useful? */
+		break;
+	case SENSOR_OM6802:
+		msleep(10);
+		reg_w1(gspca_dev, 0x01, reg01);
+		i2c_w8(gspca_dev, om6802_init0[0]);
+		i2c_w8(gspca_dev, om6802_init0[1]);
+		msleep(15);
+		reg_w1(gspca_dev, 0x02, 0x71);
+		msleep(150);
+		break;
+	case SENSOR_SP80708:
+		msleep(100);
+		reg_w1(gspca_dev, 0x02, 0x62);
+		break;
+	}
 
 	/* initialize the sensor */
 	i2c_w_seq(gspca_dev, sensor_init[sd->sensor]);
@@ -2476,30 +2446,11 @@ static int sd_start(struct gspca_dev *gspca_dev)
 	}
 	reg_w1(gspca_dev, 0x18, sn9c1xx[0x18]);
 	switch (sd->sensor) {
-	case SENSOR_GC0307:
-		reg17 = 0xa2;
-		break;
-	case SENSOR_MT9V111:
-	case SENSOR_MI0360B:
-		reg17 = 0xe0;
-		break;
-	case SENSOR_ADCM1700:
-	case SENSOR_OV7630:
-		reg17 = 0xe2;
-		break;
-	case SENSOR_OV7648:
-		reg17 = 0x20;
-		break;
-	case SENSOR_OV7660:
-	case SENSOR_SOI768:
-		reg17 = 0xa0;
-		break;
-	case SENSOR_PO1030:
-	case SENSOR_PO2030N:
-		reg17 = 0xa0;
+	case SENSOR_OM6802:
+/*	case SENSOR_OV7648:		* fixme: sometimes */
 		break;
 	default:
-		reg17 = 0x60;
+		reg17 |= DEF_EN;
 		break;
 	}
 	reg_w1(gspca_dev, 0x17, reg17);
@@ -2546,95 +2497,67 @@ static int sd_start(struct gspca_dev *gspca_dev)
 
 	init = NULL;
 	mode = gspca_dev->cam.cam_mode[gspca_dev->curr_mode].priv;
-	if (mode)
-		reg1 = 0x46;	/* 320x240: clk 48Mhz, video trf enable */
-	else
-		reg1 = 0x06;	/* 640x480: clk 24Mhz, video trf enable */
-	reg17 = 0x61;		/* 0x:20: enable sensor clock */
+	reg01 |= SYS_SEL_48M | V_TX_EN;
+	reg17 &= ~MCK_SIZE_MASK;
+	reg17 |= 0x02;			/* clock / 2 */
 	switch (sd->sensor) {
 	case SENSOR_ADCM1700:
 		init = adcm1700_sensor_param1;
-		reg1 = 0x46;
-		reg17 = 0xe2;
 		break;
 	case SENSOR_GC0307:
 		init = gc0307_sensor_param1;
-		reg17 = 0xa2;
-		reg1 = 0x44;
+		break;
+	case SENSOR_HV7131R:
+	case SENSOR_MI0360:
+		if (mode)
+			reg01 |= SYS_SEL_48M;	/* 320x240: clk 48Mhz */
+		else
+			reg01 &= ~SYS_SEL_48M;	/* 640x480: clk 24Mhz */
+		reg17 &= ~MCK_SIZE_MASK;
+		reg17 |= 0x01;			/* clock / 1 */
 		break;
 	case SENSOR_MI0360B:
 		init = mi0360b_sensor_param1;
-		reg1 &= ~0x02;		/* don't inverse pin S_PWR_DN */
-		reg17 = 0xe2;
 		break;
 	case SENSOR_MO4000:
-		if (mode) {
-/*			reg1 = 0x46;	 * 320 clk 48Mhz 60fp/s */
-			reg1 = 0x06;	/* clk 24Mz */
-		} else {
-			reg17 = 0x22;	/* 640 MCKSIZE */
-/*			reg1 = 0x06;	 * 640 clk 24Mz (done) */
+		if (mode) {			/* if 320x240 */
+			reg01 &= ~SYS_SEL_48M;	/* clk 24Mz */
+			reg17 &= ~MCK_SIZE_MASK;
+			reg17 |= 0x01;		/* clock / 1 */
 		}
 		break;
 	case SENSOR_MT9V111:
 		init = mt9v111_sensor_param1;
-		if (mode) {
-			reg1 = 0x04;	/* 320 clk 48Mhz */
-		} else {
-/*			reg1 = 0x06;	 * 640 clk 24Mz (done) */
-			reg17 = 0xc2;
-		}
 		break;
 	case SENSOR_OM6802:
 		init = om6802_sensor_param1;
-		reg17 = 0x64;		/* 640 MCKSIZE */
+		if (!mode) {			/* if 640x480 */
+			reg17 &= ~MCK_SIZE_MASK;
+			reg17 |= 0x01;		/* clock / 4 */
+		}
 		break;
 	case SENSOR_OV7630:
 		init = ov7630_sensor_param1;
-		reg17 = 0xe2;
-		reg1 = 0x44;
 		break;
 	case SENSOR_OV7648:
 		init = ov7648_sensor_param1;
-		reg17 = 0x21;
-/*		reg1 = 0x42;		 * 42 - 46? */
+		reg17 &= ~MCK_SIZE_MASK;
+		reg17 |= 0x01;			/* clock / 1 */
 		break;
 	case SENSOR_OV7660:
 		init = ov7660_sensor_param1;
-		if (sd->bridge == BRIDGE_SN9C120) {
-			if (mode) {		/* 320x240 - 160x120 */
-				reg17 = 0xa2;
-				reg1 = 0x44;	/* 48 Mhz, video trf eneble */
-			}
-		} else {
-			reg17 = 0x22;
-			reg1 = 0x06;	/* 24 Mhz, video trf eneble
-					 * inverse power down */
-		}
 		break;
 	case SENSOR_PO1030:
 		init = po1030_sensor_param1;
-		reg17 = 0xa2;
-		reg1 = 0x44;
 		break;
 	case SENSOR_PO2030N:
 		init = po2030n_sensor_param1;
-		reg1 = 0x46;
-		reg17 = 0xa2;
 		break;
 	case SENSOR_SOI768:
 		init = soi768_sensor_param1;
-		reg1 = 0x44;
-		reg17 = 0xa2;
 		break;
 	case SENSOR_SP80708:
 		init = sp80708_sensor_param1;
-		if (mode) {
-/*??			reg1 = 0x04;	 * 320 clk 48Mhz */
-		} else {
-			reg1 = 0x46;	 /* 640 clk 48Mz */
-			reg17 = 0xa2;
-		}
 		break;
 	}
 
@@ -2684,7 +2607,9 @@ static int sd_start(struct gspca_dev *gspca_dev)
 	setjpegqual(gspca_dev);
 
 	reg_w1(gspca_dev, 0x17, reg17);
-	reg_w1(gspca_dev, 0x01, reg1);
+	reg_w1(gspca_dev, 0x01, reg01);
+	sd->reg01 = reg01;
+	sd->reg17 = reg17;
 
 	sethvflip(gspca_dev);
 	setbrightness(gspca_dev);
@@ -2706,41 +2631,64 @@ static void sd_stopN(struct gspca_dev *gspca_dev)
 		{ 0xa1, 0x21, 0x76, 0x20, 0x00, 0x00, 0x00, 0x10 };
 	static const u8 stopsoi768[] =
 		{ 0xa1, 0x21, 0x12, 0x80, 0x00, 0x00, 0x00, 0x10 };
-	u8 data;
-	const u8 *sn9c1xx;
+	u8 reg01;
+	u8 reg17;
 
-	data = 0x0b;
+	reg01 = sd->reg01;
+	reg17 = sd->reg17 & ~SEN_CLK_EN;
 	switch (sd->sensor) {
+	case SENSOR_ADCM1700:
 	case SENSOR_GC0307:
-		data = 0x29;
+	case SENSOR_PO2030N:
+	case SENSOR_SP80708:
+		reg01 |= LED;
+		reg_w1(gspca_dev, 0x01, reg01);
+		reg01 &= ~(LED | V_TX_EN);
+		reg_w1(gspca_dev, 0x01, reg01);
+/*		reg_w1(gspca_dev, 0x02, 0x??);	 * LED off ? */
 		break;
 	case SENSOR_HV7131R:
+		reg01 &= ~V_TX_EN;
+		reg_w1(gspca_dev, 0x01, reg01);
 		i2c_w8(gspca_dev, stophv7131);
-		data = 0x2b;
 		break;
 	case SENSOR_MI0360:
 	case SENSOR_MI0360B:
+		reg01 &= ~V_TX_EN;
+		reg_w1(gspca_dev, 0x01, reg01);
+/*		reg_w1(gspca_dev, 0x02, 0x40);	  * LED off ? */
 		i2c_w8(gspca_dev, stopmi0360);
-		data = 0x29;
 		break;
-	case SENSOR_OV7648:
-		i2c_w8(gspca_dev, stopov7648);
-		/* fall thru */
 	case SENSOR_MT9V111:
-	case SENSOR_OV7630:
+	case SENSOR_OM6802:
 	case SENSOR_PO1030:
-		data = 0x29;
+		reg01 &= ~V_TX_EN;
+		reg_w1(gspca_dev, 0x01, reg01);
+		break;
+	case SENSOR_OV7630:
+	case SENSOR_OV7648:
+		reg01 &= ~V_TX_EN;
+		reg_w1(gspca_dev, 0x01, reg01);
+		i2c_w8(gspca_dev, stopov7648);
+		break;
+	case SENSOR_OV7660:
+		reg01 &= ~V_TX_EN;
+		reg_w1(gspca_dev, 0x01, reg01);
 		break;
 	case SENSOR_SOI768:
 		i2c_w8(gspca_dev, stopsoi768);
-		data = 0x29;
 		break;
 	}
-	sn9c1xx = sn_tb[sd->sensor];
-	reg_w1(gspca_dev, 0x01, sn9c1xx[1]);
-	reg_w1(gspca_dev, 0x17, sn9c1xx[0x17]);
-	reg_w1(gspca_dev, 0x01, sn9c1xx[1]);
-	reg_w1(gspca_dev, 0x01, data);
+
+	reg01 |= SCL_SEL_OD;
+	reg_w1(gspca_dev, 0x01, reg01);
+	reg01 |= S_PWR_DN;		/* sensor power down */
+	reg_w1(gspca_dev, 0x01, reg01);
+	reg_w1(gspca_dev, 0x17, reg17);
+	reg01 &= ~SYS_SEL_48M;		/* clock 24MHz */
+	reg_w1(gspca_dev, 0x01, reg01);
+	reg01 |= LED;
+	reg_w1(gspca_dev, 0x01, reg01);
 	/* Don't disable sensor clock as that disables the button on the cam */
 	/* reg_w1(gspca_dev, 0xf1, 0x01); */
 }
@@ -2954,14 +2902,18 @@ static const struct sd_desc sd_desc = {
 /* -- module initialisation -- */
 #define BS(bridge, sensor) \
 	.driver_info = (BRIDGE_ ## bridge << 16) \
-			| SENSOR_ ## sensor
+			| (SENSOR_ ## sensor << 8)
+#define BSF(bridge, sensor, flags) \
+	.driver_info = (BRIDGE_ ## bridge << 16) \
+			| (SENSOR_ ## sensor << 8) \
+			| (flags)
 static const __devinitdata struct usb_device_id device_table[] = {
 #if !defined CONFIG_USB_SN9C102 && !defined CONFIG_USB_SN9C102_MODULE
 	{USB_DEVICE(0x0458, 0x7025), BS(SN9C120, MI0360)},
 	{USB_DEVICE(0x0458, 0x702e), BS(SN9C120, OV7660)},
 #endif
-	{USB_DEVICE(0x045e, 0x00f5), BS(SN9C105, OV7660)},
-	{USB_DEVICE(0x045e, 0x00f7), BS(SN9C105, OV7660)},
+	{USB_DEVICE(0x045e, 0x00f5), BSF(SN9C105, OV7660, PDN_INV)},
+	{USB_DEVICE(0x045e, 0x00f7), BSF(SN9C105, OV7660, PDN_INV)},
 	{USB_DEVICE(0x0471, 0x0327), BS(SN9C105, MI0360)},
 	{USB_DEVICE(0x0471, 0x0328), BS(SN9C105, MI0360)},
 	{USB_DEVICE(0x0471, 0x0330), BS(SN9C105, MI0360)},
diff --git a/drivers/media/video/meye.c b/drivers/media/video/meye.c
index 2be23bccd3c..48d2c2419c1 100644
--- a/drivers/media/video/meye.c
+++ b/drivers/media/video/meye.c
@@ -1659,7 +1659,7 @@ static const struct v4l2_file_operations meye_fops = {
 	.open		= meye_open,
 	.release	= meye_release,
 	.mmap		= meye_mmap,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 	.poll		= meye_poll,
 };
 
@@ -1831,12 +1831,6 @@ static int __devinit meye_probe(struct pci_dev *pcidev,
 	msleep(1);
 	mchip_set(MCHIP_MM_INTA, MCHIP_MM_INTA_HIC_1_MASK);
 
-	if (video_register_device(meye.vdev, VFL_TYPE_GRABBER,
-				  video_nr) < 0) {
-		v4l2_err(v4l2_dev, "video_register_device failed\n");
-		goto outvideoreg;
-	}
-
 	mutex_init(&meye.lock);
 	init_waitqueue_head(&meye.proc_list);
 	meye.brightness = 32 << 10;
@@ -1858,6 +1852,12 @@ static int __devinit meye_probe(struct pci_dev *pcidev,
 	sony_pic_camera_command(SONY_PIC_COMMAND_SETCAMERAPICTURE, 0);
 	sony_pic_camera_command(SONY_PIC_COMMAND_SETCAMERAAGC, 48);
 
+	if (video_register_device(meye.vdev, VFL_TYPE_GRABBER,
+				  video_nr) < 0) {
+		v4l2_err(v4l2_dev, "video_register_device failed\n");
+		goto outvideoreg;
+	}
+
 	v4l2_info(v4l2_dev, "Motion Eye Camera Driver v%s.\n",
 	       MEYE_DRIVER_VERSION);
 	v4l2_info(v4l2_dev, "mchip KL5A72002 rev. %d, base %lx, irq %d\n",
diff --git a/drivers/media/video/pms.c b/drivers/media/video/pms.c
index 7129b50757d..7551907f8c2 100644
--- a/drivers/media/video/pms.c
+++ b/drivers/media/video/pms.c
@@ -932,7 +932,7 @@ static ssize_t pms_read(struct file *file, char __user *buf,
 
 static const struct v4l2_file_operations pms_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 	.read           = pms_read,
 };
 
diff --git a/drivers/media/video/sh_vou.c b/drivers/media/video/sh_vou.c
index 4e5a8cf76de..07cf0c6c7c1 100644
--- a/drivers/media/video/sh_vou.c
+++ b/drivers/media/video/sh_vou.c
@@ -75,6 +75,7 @@ struct sh_vou_device {
 	int pix_idx;
 	struct videobuf_buffer *active;
 	enum sh_vou_status status;
+	struct mutex fop_lock;
 };
 
 struct sh_vou_file {
@@ -235,7 +236,7 @@ static void free_buffer(struct videobuf_queue *vq, struct videobuf_buffer *vb)
 	vb->state = VIDEOBUF_NEEDS_INIT;
 }
 
-/* Locking: caller holds vq->vb_lock mutex */
+/* Locking: caller holds fop_lock mutex */
 static int sh_vou_buf_setup(struct videobuf_queue *vq, unsigned int *count,
 			    unsigned int *size)
 {
@@ -257,7 +258,7 @@ static int sh_vou_buf_setup(struct videobuf_queue *vq, unsigned int *count,
 	return 0;
 }
 
-/* Locking: caller holds vq->vb_lock mutex */
+/* Locking: caller holds fop_lock mutex */
 static int sh_vou_buf_prepare(struct videobuf_queue *vq,
 			      struct videobuf_buffer *vb,
 			      enum v4l2_field field)
@@ -306,7 +307,7 @@ static int sh_vou_buf_prepare(struct videobuf_queue *vq,
 	return 0;
 }
 
-/* Locking: caller holds vq->vb_lock mutex and vq->irqlock spinlock */
+/* Locking: caller holds fop_lock mutex and vq->irqlock spinlock */
 static void sh_vou_buf_queue(struct videobuf_queue *vq,
 			     struct videobuf_buffer *vb)
 {
@@ -1190,7 +1191,7 @@ static int sh_vou_open(struct file *file)
 				       V4L2_BUF_TYPE_VIDEO_OUTPUT,
 				       V4L2_FIELD_NONE,
 				       sizeof(struct videobuf_buffer), vdev,
-				       NULL);
+				       &vou_dev->fop_lock);
 
 	return 0;
 }
@@ -1292,7 +1293,7 @@ static const struct v4l2_file_operations sh_vou_fops = {
 	.owner		= THIS_MODULE,
 	.open		= sh_vou_open,
 	.release	= sh_vou_release,
-	.ioctl		= video_ioctl2,
+	.unlocked_ioctl	= video_ioctl2,
 	.mmap		= sh_vou_mmap,
 	.poll		= sh_vou_poll,
 };
@@ -1331,6 +1332,7 @@ static int __devinit sh_vou_probe(struct platform_device *pdev)
 
 	INIT_LIST_HEAD(&vou_dev->queue);
 	spin_lock_init(&vou_dev->lock);
+	mutex_init(&vou_dev->fop_lock);
 	atomic_set(&vou_dev->use_count, 0);
 	vou_dev->pdata = vou_pdata;
 	vou_dev->status = SH_VOU_IDLE;
@@ -1388,6 +1390,7 @@ static int __devinit sh_vou_probe(struct platform_device *pdev)
 		vdev->tvnorms |= V4L2_STD_PAL;
 	vdev->v4l2_dev = &vou_dev->v4l2_dev;
 	vdev->release = video_device_release;
+	vdev->lock = &vou_dev->fop_lock;
 
 	vou_dev->vdev = vdev;
 	video_set_drvdata(vdev, vou_dev);
diff --git a/drivers/media/video/sn9c102/sn9c102_core.c b/drivers/media/video/sn9c102/sn9c102_core.c
index 28e19daadec..f49fbfb7dc1 100644
--- a/drivers/media/video/sn9c102/sn9c102_core.c
+++ b/drivers/media/video/sn9c102/sn9c102_core.c
@@ -3238,7 +3238,7 @@ static const struct v4l2_file_operations sn9c102_fops = {
 	.owner = THIS_MODULE,
 	.open = sn9c102_open,
 	.release = sn9c102_release,
-	.ioctl = sn9c102_ioctl,
+	.unlocked_ioctl = sn9c102_ioctl,
 	.read = sn9c102_read,
 	.poll = sn9c102_poll,
 	.mmap = sn9c102_mmap,
diff --git a/drivers/media/video/uvc/uvc_ctrl.c b/drivers/media/video/uvc/uvc_ctrl.c
index f169f773667..59f8a9ad379 100644
--- a/drivers/media/video/uvc/uvc_ctrl.c
+++ b/drivers/media/video/uvc/uvc_ctrl.c
@@ -785,7 +785,7 @@ static void __uvc_find_control(struct uvc_entity *entity, __u32 v4l2_id,
 	}
 }
 
-struct uvc_control *uvc_find_control(struct uvc_video_chain *chain,
+static struct uvc_control *uvc_find_control(struct uvc_video_chain *chain,
 	__u32 v4l2_id, struct uvc_control_mapping **mapping)
 {
 	struct uvc_control *ctrl = NULL;
@@ -944,6 +944,52 @@ done:
 	return ret;
 }
 
+/*
+ * Mapping V4L2 controls to UVC controls can be straighforward if done well.
+ * Most of the UVC controls exist in V4L2, and can be mapped directly. Some
+ * must be grouped (for instance the Red Balance, Blue Balance and Do White
+ * Balance V4L2 controls use the White Balance Component UVC control) or
+ * otherwise translated. The approach we take here is to use a translation
+ * table for the controls that can be mapped directly, and handle the others
+ * manually.
+ */
+int uvc_query_v4l2_menu(struct uvc_video_chain *chain,
+	struct v4l2_querymenu *query_menu)
+{
+	struct uvc_menu_info *menu_info;
+	struct uvc_control_mapping *mapping;
+	struct uvc_control *ctrl;
+	u32 index = query_menu->index;
+	u32 id = query_menu->id;
+	int ret;
+
+	memset(query_menu, 0, sizeof(*query_menu));
+	query_menu->id = id;
+	query_menu->index = index;
+
+	ret = mutex_lock_interruptible(&chain->ctrl_mutex);
+	if (ret < 0)
+		return -ERESTARTSYS;
+
+	ctrl = uvc_find_control(chain, query_menu->id, &mapping);
+	if (ctrl == NULL || mapping->v4l2_type != V4L2_CTRL_TYPE_MENU) {
+		ret = -EINVAL;
+		goto done;
+	}
+
+	if (query_menu->index >= mapping->menu_count) {
+		ret = -EINVAL;
+		goto done;
+	}
+
+	menu_info = &mapping->menu_info[query_menu->index];
+	strlcpy(query_menu->name, menu_info->name, sizeof query_menu->name);
+
+done:
+	mutex_unlock(&chain->ctrl_mutex);
+	return ret;
+}
+
 
 /* --------------------------------------------------------------------------
  * Control transactions
diff --git a/drivers/media/video/uvc/uvc_queue.c b/drivers/media/video/uvc/uvc_queue.c
index ed6d5449741..f14581bd707 100644
--- a/drivers/media/video/uvc/uvc_queue.c
+++ b/drivers/media/video/uvc/uvc_queue.c
@@ -90,6 +90,39 @@ void uvc_queue_init(struct uvc_video_queue *queue, enum v4l2_buf_type type,
 }
 
 /*
+ * Free the video buffers.
+ *
+ * This function must be called with the queue lock held.
+ */
+static int __uvc_free_buffers(struct uvc_video_queue *queue)
+{
+	unsigned int i;
+
+	for (i = 0; i < queue->count; ++i) {
+		if (queue->buffer[i].vma_use_count != 0)
+			return -EBUSY;
+	}
+
+	if (queue->count) {
+		vfree(queue->mem);
+		queue->count = 0;
+	}
+
+	return 0;
+}
+
+int uvc_free_buffers(struct uvc_video_queue *queue)
+{
+	int ret;
+
+	mutex_lock(&queue->mutex);
+	ret = __uvc_free_buffers(queue);
+	mutex_unlock(&queue->mutex);
+
+	return ret;
+}
+
+/*
  * Allocate the video buffers.
  *
  * Pages are reserved to make sure they will not be swapped, as they will be
@@ -110,7 +143,7 @@ int uvc_alloc_buffers(struct uvc_video_queue *queue, unsigned int nbuffers,
 
 	mutex_lock(&queue->mutex);
 
-	if ((ret = uvc_free_buffers(queue)) < 0)
+	if ((ret = __uvc_free_buffers(queue)) < 0)
 		goto done;
 
 	/* Bail out if no buffers should be allocated. */
@@ -152,28 +185,6 @@ done:
 }
 
 /*
- * Free the video buffers.
- *
- * This function must be called with the queue lock held.
- */
-int uvc_free_buffers(struct uvc_video_queue *queue)
-{
-	unsigned int i;
-
-	for (i = 0; i < queue->count; ++i) {
-		if (queue->buffer[i].vma_use_count != 0)
-			return -EBUSY;
-	}
-
-	if (queue->count) {
-		vfree(queue->mem);
-		queue->count = 0;
-	}
-
-	return 0;
-}
-
-/*
  * Check if buffers have been allocated.
  */
 int uvc_queue_allocated(struct uvc_video_queue *queue)
@@ -369,6 +380,82 @@ done:
 }
 
 /*
+ * VMA operations.
+ */
+static void uvc_vm_open(struct vm_area_struct *vma)
+{
+	struct uvc_buffer *buffer = vma->vm_private_data;
+	buffer->vma_use_count++;
+}
+
+static void uvc_vm_close(struct vm_area_struct *vma)
+{
+	struct uvc_buffer *buffer = vma->vm_private_data;
+	buffer->vma_use_count--;
+}
+
+static const struct vm_operations_struct uvc_vm_ops = {
+	.open		= uvc_vm_open,
+	.close		= uvc_vm_close,
+};
+
+/*
+ * Memory-map a video buffer.
+ *
+ * This function implements video buffers memory mapping and is intended to be
+ * used by the device mmap handler.
+ */
+int uvc_queue_mmap(struct uvc_video_queue *queue, struct vm_area_struct *vma)
+{
+	struct uvc_buffer *uninitialized_var(buffer);
+	struct page *page;
+	unsigned long addr, start, size;
+	unsigned int i;
+	int ret = 0;
+
+	start = vma->vm_start;
+	size = vma->vm_end - vma->vm_start;
+
+	mutex_lock(&queue->mutex);
+
+	for (i = 0; i < queue->count; ++i) {
+		buffer = &queue->buffer[i];
+		if ((buffer->buf.m.offset >> PAGE_SHIFT) == vma->vm_pgoff)
+			break;
+	}
+
+	if (i == queue->count || size != queue->buf_size) {
+		ret = -EINVAL;
+		goto done;
+	}
+
+	/*
+	 * VM_IO marks the area as being an mmaped region for I/O to a
+	 * device. It also prevents the region from being core dumped.
+	 */
+	vma->vm_flags |= VM_IO;
+
+	addr = (unsigned long)queue->mem + buffer->buf.m.offset;
+	while (size > 0) {
+		page = vmalloc_to_page((void *)addr);
+		if ((ret = vm_insert_page(vma, start, page)) < 0)
+			goto done;
+
+		start += PAGE_SIZE;
+		addr += PAGE_SIZE;
+		size -= PAGE_SIZE;
+	}
+
+	vma->vm_ops = &uvc_vm_ops;
+	vma->vm_private_data = buffer;
+	uvc_vm_open(vma);
+
+done:
+	mutex_unlock(&queue->mutex);
+	return ret;
+}
+
+/*
  * Poll the video queue.
  *
  * This function implements video queue polling and is intended to be used by
diff --git a/drivers/media/video/uvc/uvc_v4l2.c b/drivers/media/video/uvc/uvc_v4l2.c
index 6d15de9b520..8cf61e8a634 100644
--- a/drivers/media/video/uvc/uvc_v4l2.c
+++ b/drivers/media/video/uvc/uvc_v4l2.c
@@ -101,40 +101,6 @@ done:
  */
 
 /*
- * Mapping V4L2 controls to UVC controls can be straighforward if done well.
- * Most of the UVC controls exist in V4L2, and can be mapped directly. Some
- * must be grouped (for instance the Red Balance, Blue Balance and Do White
- * Balance V4L2 controls use the White Balance Component UVC control) or
- * otherwise translated. The approach we take here is to use a translation
- * table for the controls that can be mapped directly, and handle the others
- * manually.
- */
-static int uvc_v4l2_query_menu(struct uvc_video_chain *chain,
-	struct v4l2_querymenu *query_menu)
-{
-	struct uvc_menu_info *menu_info;
-	struct uvc_control_mapping *mapping;
-	struct uvc_control *ctrl;
-	u32 index = query_menu->index;
-	u32 id = query_menu->id;
-
-	ctrl = uvc_find_control(chain, query_menu->id, &mapping);
-	if (ctrl == NULL || mapping->v4l2_type != V4L2_CTRL_TYPE_MENU)
-		return -EINVAL;
-
-	if (query_menu->index >= mapping->menu_count)
-		return -EINVAL;
-
-	memset(query_menu, 0, sizeof(*query_menu));
-	query_menu->id = id;
-	query_menu->index = index;
-
-	menu_info = &mapping->menu_info[query_menu->index];
-	strlcpy(query_menu->name, menu_info->name, sizeof query_menu->name);
-	return 0;
-}
-
-/*
  * Find the frame interval closest to the requested frame interval for the
  * given frame format and size. This should be done by the device as part of
  * the Video Probe and Commit negotiation, but some hardware don't implement
@@ -260,12 +226,14 @@ static int uvc_v4l2_try_format(struct uvc_streaming *stream,
 	 * developers test their webcams with the Linux driver as well as with
 	 * the Windows driver).
 	 */
+	mutex_lock(&stream->mutex);
 	if (stream->dev->quirks & UVC_QUIRK_PROBE_EXTRAFIELDS)
 		probe->dwMaxVideoFrameSize =
 			stream->ctrl.dwMaxVideoFrameSize;
 
 	/* Probe the device. */
 	ret = uvc_probe_video(stream, probe);
+	mutex_unlock(&stream->mutex);
 	if (ret < 0)
 		goto done;
 
@@ -289,14 +257,21 @@ done:
 static int uvc_v4l2_get_format(struct uvc_streaming *stream,
 	struct v4l2_format *fmt)
 {
-	struct uvc_format *format = stream->cur_format;
-	struct uvc_frame *frame = stream->cur_frame;
+	struct uvc_format *format;
+	struct uvc_frame *frame;
+	int ret = 0;
 
 	if (fmt->type != stream->type)
 		return -EINVAL;
 
-	if (format == NULL || frame == NULL)
-		return -EINVAL;
+	mutex_lock(&stream->mutex);
+	format = stream->cur_format;
+	frame = stream->cur_frame;
+
+	if (format == NULL || frame == NULL) {
+		ret = -EINVAL;
+		goto done;
+	}
 
 	fmt->fmt.pix.pixelformat = format->fcc;
 	fmt->fmt.pix.width = frame->wWidth;
@@ -307,7 +282,9 @@ static int uvc_v4l2_get_format(struct uvc_streaming *stream,
 	fmt->fmt.pix.colorspace = format->colorspace;
 	fmt->fmt.pix.priv = 0;
 
-	return 0;
+done:
+	mutex_unlock(&stream->mutex);
+	return ret;
 }
 
 static int uvc_v4l2_set_format(struct uvc_streaming *stream,
@@ -321,18 +298,24 @@ static int uvc_v4l2_set_format(struct uvc_streaming *stream,
 	if (fmt->type != stream->type)
 		return -EINVAL;
 
-	if (uvc_queue_allocated(&stream->queue))
-		return -EBUSY;
-
 	ret = uvc_v4l2_try_format(stream, fmt, &probe, &format, &frame);
 	if (ret < 0)
 		return ret;
 
+	mutex_lock(&stream->mutex);
+
+	if (uvc_queue_allocated(&stream->queue)) {
+		ret = -EBUSY;
+		goto done;
+	}
+
 	memcpy(&stream->ctrl, &probe, sizeof probe);
 	stream->cur_format = format;
 	stream->cur_frame = frame;
 
-	return 0;
+done:
+	mutex_unlock(&stream->mutex);
+	return ret;
 }
 
 static int uvc_v4l2_get_streamparm(struct uvc_streaming *stream,
@@ -343,7 +326,10 @@ static int uvc_v4l2_get_streamparm(struct uvc_streaming *stream,
 	if (parm->type != stream->type)
 		return -EINVAL;
 
+	mutex_lock(&stream->mutex);
 	numerator = stream->ctrl.dwFrameInterval;
+	mutex_unlock(&stream->mutex);
+
 	denominator = 10000000;
 	uvc_simplify_fraction(&numerator, &denominator, 8, 333);
 
@@ -370,7 +356,6 @@ static int uvc_v4l2_get_streamparm(struct uvc_streaming *stream,
 static int uvc_v4l2_set_streamparm(struct uvc_streaming *stream,
 		struct v4l2_streamparm *parm)
 {
-	struct uvc_frame *frame = stream->cur_frame;
 	struct uvc_streaming_control probe;
 	struct v4l2_fract timeperframe;
 	uint32_t interval;
@@ -379,28 +364,36 @@ static int uvc_v4l2_set_streamparm(struct uvc_streaming *stream,
 	if (parm->type != stream->type)
 		return -EINVAL;
 
-	if (uvc_queue_streaming(&stream->queue))
-		return -EBUSY;
-
 	if (parm->type == V4L2_BUF_TYPE_VIDEO_CAPTURE)
 		timeperframe = parm->parm.capture.timeperframe;
 	else
 		timeperframe = parm->parm.output.timeperframe;
 
-	memcpy(&probe, &stream->ctrl, sizeof probe);
 	interval = uvc_fraction_to_interval(timeperframe.numerator,
 		timeperframe.denominator);
-
 	uvc_trace(UVC_TRACE_FORMAT, "Setting frame interval to %u/%u (%u).\n",
 		timeperframe.numerator, timeperframe.denominator, interval);
-	probe.dwFrameInterval = uvc_try_frame_interval(frame, interval);
+
+	mutex_lock(&stream->mutex);
+
+	if (uvc_queue_streaming(&stream->queue)) {
+		mutex_unlock(&stream->mutex);
+		return -EBUSY;
+	}
+
+	memcpy(&probe, &stream->ctrl, sizeof probe);
+	probe.dwFrameInterval =
+		uvc_try_frame_interval(stream->cur_frame, interval);
 
 	/* Probe the device with the new settings. */
 	ret = uvc_probe_video(stream, &probe);
-	if (ret < 0)
+	if (ret < 0) {
+		mutex_unlock(&stream->mutex);
 		return ret;
+	}
 
 	memcpy(&stream->ctrl, &probe, sizeof probe);
+	mutex_unlock(&stream->mutex);
 
 	/* Return the actual frame period. */
 	timeperframe.numerator = probe.dwFrameInterval;
@@ -528,11 +521,9 @@ static int uvc_v4l2_release(struct file *file)
 	if (uvc_has_privileges(handle)) {
 		uvc_video_enable(stream, 0);
 
-		mutex_lock(&stream->queue.mutex);
 		if (uvc_free_buffers(&stream->queue) < 0)
 			uvc_printk(KERN_ERR, "uvc_v4l2_release: Unable to "
 					"free buffers.\n");
-		mutex_unlock(&stream->queue.mutex);
 	}
 
 	/* Release the file handle. */
@@ -624,7 +615,7 @@ static long uvc_v4l2_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 	}
 
 	case VIDIOC_QUERYMENU:
-		return uvc_v4l2_query_menu(chain, arg);
+		return uvc_query_v4l2_menu(chain, arg);
 
 	case VIDIOC_G_EXT_CTRLS:
 	{
@@ -905,15 +896,17 @@ static long uvc_v4l2_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 	case VIDIOC_CROPCAP:
 	{
 		struct v4l2_cropcap *ccap = arg;
-		struct uvc_frame *frame = stream->cur_frame;
 
 		if (ccap->type != stream->type)
 			return -EINVAL;
 
 		ccap->bounds.left = 0;
 		ccap->bounds.top = 0;
-		ccap->bounds.width = frame->wWidth;
-		ccap->bounds.height = frame->wHeight;
+
+		mutex_lock(&stream->mutex);
+		ccap->bounds.width = stream->cur_frame->wWidth;
+		ccap->bounds.height = stream->cur_frame->wHeight;
+		mutex_unlock(&stream->mutex);
 
 		ccap->defrect = ccap->bounds;
 
@@ -930,8 +923,6 @@ static long uvc_v4l2_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 	case VIDIOC_REQBUFS:
 	{
 		struct v4l2_requestbuffers *rb = arg;
-		unsigned int bufsize =
-			stream->ctrl.dwMaxVideoFrameSize;
 
 		if (rb->type != stream->type ||
 		    rb->memory != V4L2_MEMORY_MMAP)
@@ -940,7 +931,10 @@ static long uvc_v4l2_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 		if ((ret = uvc_acquire_privileges(handle)) < 0)
 			return ret;
 
-		ret = uvc_alloc_buffers(&stream->queue, rb->count, bufsize);
+		mutex_lock(&stream->mutex);
+		ret = uvc_alloc_buffers(&stream->queue, rb->count,
+					stream->ctrl.dwMaxVideoFrameSize);
+		mutex_unlock(&stream->mutex);
 		if (ret < 0)
 			return ret;
 
@@ -988,7 +982,9 @@ static long uvc_v4l2_do_ioctl(struct file *file, unsigned int cmd, void *arg)
 		if (!uvc_has_privileges(handle))
 			return -EBUSY;
 
+		mutex_lock(&stream->mutex);
 		ret = uvc_video_enable(stream, 1);
+		mutex_unlock(&stream->mutex);
 		if (ret < 0)
 			return ret;
 		break;
@@ -1068,79 +1064,14 @@ static ssize_t uvc_v4l2_read(struct file *file, char __user *data,
 	return -EINVAL;
 }
 
-/*
- * VMA operations.
- */
-static void uvc_vm_open(struct vm_area_struct *vma)
-{
-	struct uvc_buffer *buffer = vma->vm_private_data;
-	buffer->vma_use_count++;
-}
-
-static void uvc_vm_close(struct vm_area_struct *vma)
-{
-	struct uvc_buffer *buffer = vma->vm_private_data;
-	buffer->vma_use_count--;
-}
-
-static const struct vm_operations_struct uvc_vm_ops = {
-	.open		= uvc_vm_open,
-	.close		= uvc_vm_close,
-};
-
 static int uvc_v4l2_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct uvc_fh *handle = file->private_data;
 	struct uvc_streaming *stream = handle->stream;
-	struct uvc_video_queue *queue = &stream->queue;
-	struct uvc_buffer *uninitialized_var(buffer);
-	struct page *page;
-	unsigned long addr, start, size;
-	unsigned int i;
-	int ret = 0;
 
 	uvc_trace(UVC_TRACE_CALLS, "uvc_v4l2_mmap\n");
 
-	start = vma->vm_start;
-	size = vma->vm_end - vma->vm_start;
-
-	mutex_lock(&queue->mutex);
-
-	for (i = 0; i < queue->count; ++i) {
-		buffer = &queue->buffer[i];
-		if ((buffer->buf.m.offset >> PAGE_SHIFT) == vma->vm_pgoff)
-			break;
-	}
-
-	if (i == queue->count || size != queue->buf_size) {
-		ret = -EINVAL;
-		goto done;
-	}
-
-	/*
-	 * VM_IO marks the area as being an mmaped region for I/O to a
-	 * device. It also prevents the region from being core dumped.
-	 */
-	vma->vm_flags |= VM_IO;
-
-	addr = (unsigned long)queue->mem + buffer->buf.m.offset;
-	while (size > 0) {
-		page = vmalloc_to_page((void *)addr);
-		if ((ret = vm_insert_page(vma, start, page)) < 0)
-			goto done;
-
-		start += PAGE_SIZE;
-		addr += PAGE_SIZE;
-		size -= PAGE_SIZE;
-	}
-
-	vma->vm_ops = &uvc_vm_ops;
-	vma->vm_private_data = buffer;
-	uvc_vm_open(vma);
-
-done:
-	mutex_unlock(&queue->mutex);
-	return ret;
+	return uvc_queue_mmap(&stream->queue, vma);
 }
 
 static unsigned int uvc_v4l2_poll(struct file *file, poll_table *wait)
@@ -1157,7 +1088,7 @@ const struct v4l2_file_operations uvc_fops = {
 	.owner		= THIS_MODULE,
 	.open		= uvc_v4l2_open,
 	.release	= uvc_v4l2_release,
-	.ioctl		= uvc_v4l2_ioctl,
+	.unlocked_ioctl	= uvc_v4l2_ioctl,
 	.read		= uvc_v4l2_read,
 	.mmap		= uvc_v4l2_mmap,
 	.poll		= uvc_v4l2_poll,
diff --git a/drivers/media/video/uvc/uvc_video.c b/drivers/media/video/uvc/uvc_video.c
index 5555f010283..5673d673504 100644
--- a/drivers/media/video/uvc/uvc_video.c
+++ b/drivers/media/video/uvc/uvc_video.c
@@ -293,8 +293,6 @@ int uvc_probe_video(struct uvc_streaming *stream,
 	unsigned int i;
 	int ret;
 
-	mutex_lock(&stream->mutex);
-
 	/* Perform probing. The device should adjust the requested values
 	 * according to its capabilities. However, some devices, namely the
 	 * first generation UVC Logitech webcams, don't implement the Video
@@ -346,7 +344,6 @@ int uvc_probe_video(struct uvc_streaming *stream,
 	}
 
 done:
-	mutex_unlock(&stream->mutex);
 	return ret;
 }
 
diff --git a/drivers/media/video/uvc/uvcvideo.h b/drivers/media/video/uvc/uvcvideo.h
index d97cf6d6a4f..45f01e7e13d 100644
--- a/drivers/media/video/uvc/uvcvideo.h
+++ b/drivers/media/video/uvc/uvcvideo.h
@@ -436,7 +436,9 @@ struct uvc_streaming {
 	struct uvc_streaming_control ctrl;
 	struct uvc_format *cur_format;
 	struct uvc_frame *cur_frame;
-
+	/* Protect access to ctrl, cur_format, cur_frame and hardware video
+	 * probe control.
+	 */
 	struct mutex mutex;
 
 	unsigned int frozen : 1;
@@ -574,6 +576,8 @@ extern int uvc_queue_enable(struct uvc_video_queue *queue, int enable);
 extern void uvc_queue_cancel(struct uvc_video_queue *queue, int disconnect);
 extern struct uvc_buffer *uvc_queue_next_buffer(struct uvc_video_queue *queue,
 		struct uvc_buffer *buf);
+extern int uvc_queue_mmap(struct uvc_video_queue *queue,
+		struct vm_area_struct *vma);
 extern unsigned int uvc_queue_poll(struct uvc_video_queue *queue,
 		struct file *file, poll_table *wait);
 extern int uvc_queue_allocated(struct uvc_video_queue *queue);
@@ -606,10 +610,10 @@ extern int uvc_status_suspend(struct uvc_device *dev);
 extern int uvc_status_resume(struct uvc_device *dev);
 
 /* Controls */
-extern struct uvc_control *uvc_find_control(struct uvc_video_chain *chain,
-		__u32 v4l2_id, struct uvc_control_mapping **mapping);
 extern int uvc_query_v4l2_ctrl(struct uvc_video_chain *chain,
 		struct v4l2_queryctrl *v4l2_ctrl);
+extern int uvc_query_v4l2_menu(struct uvc_video_chain *chain,
+		struct v4l2_querymenu *query_menu);
 
 extern int uvc_ctrl_add_mapping(struct uvc_video_chain *chain,
 		const struct uvc_control_mapping *mapping);
diff --git a/drivers/media/video/v4l2-dev.c b/drivers/media/video/v4l2-dev.c
index 03f7f4670e9..359e23290a7 100644
--- a/drivers/media/video/v4l2-dev.c
+++ b/drivers/media/video/v4l2-dev.c
@@ -186,12 +186,12 @@ static ssize_t v4l2_read(struct file *filp, char __user *buf,
 		size_t sz, loff_t *off)
 {
 	struct video_device *vdev = video_devdata(filp);
-	int ret = -EIO;
+	int ret = -ENODEV;
 
 	if (!vdev->fops->read)
 		return -EINVAL;
-	if (vdev->lock)
-		mutex_lock(vdev->lock);
+	if (vdev->lock && mutex_lock_interruptible(vdev->lock))
+		return -ERESTARTSYS;
 	if (video_is_registered(vdev))
 		ret = vdev->fops->read(filp, buf, sz, off);
 	if (vdev->lock)
@@ -203,12 +203,12 @@ static ssize_t v4l2_write(struct file *filp, const char __user *buf,
 		size_t sz, loff_t *off)
 {
 	struct video_device *vdev = video_devdata(filp);
-	int ret = -EIO;
+	int ret = -ENODEV;
 
 	if (!vdev->fops->write)
 		return -EINVAL;
-	if (vdev->lock)
-		mutex_lock(vdev->lock);
+	if (vdev->lock && mutex_lock_interruptible(vdev->lock))
+		return -ERESTARTSYS;
 	if (video_is_registered(vdev))
 		ret = vdev->fops->write(filp, buf, sz, off);
 	if (vdev->lock)
@@ -219,10 +219,10 @@ static ssize_t v4l2_write(struct file *filp, const char __user *buf,
 static unsigned int v4l2_poll(struct file *filp, struct poll_table_struct *poll)
 {
 	struct video_device *vdev = video_devdata(filp);
-	int ret = DEFAULT_POLLMASK;
+	int ret = POLLERR | POLLHUP;
 
 	if (!vdev->fops->poll)
-		return ret;
+		return DEFAULT_POLLMASK;
 	if (vdev->lock)
 		mutex_lock(vdev->lock);
 	if (video_is_registered(vdev))
@@ -238,20 +238,45 @@ static long v4l2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	int ret = -ENODEV;
 
 	if (vdev->fops->unlocked_ioctl) {
-		if (vdev->lock)
-			mutex_lock(vdev->lock);
+		if (vdev->lock && mutex_lock_interruptible(vdev->lock))
+			return -ERESTARTSYS;
 		if (video_is_registered(vdev))
 			ret = vdev->fops->unlocked_ioctl(filp, cmd, arg);
 		if (vdev->lock)
 			mutex_unlock(vdev->lock);
 	} else if (vdev->fops->ioctl) {
-		/* TODO: convert all drivers to unlocked_ioctl */
+		/* This code path is a replacement for the BKL. It is a major
+		 * hack but it will have to do for those drivers that are not
+		 * yet converted to use unlocked_ioctl.
+		 *
+		 * There are two options: if the driver implements struct
+		 * v4l2_device, then the lock defined there is used to
+		 * serialize the ioctls. Otherwise the v4l2 core lock defined
+		 * below is used. This lock is really bad since it serializes
+		 * completely independent devices.
+		 *
+		 * Both variants suffer from the same problem: if the driver
+		 * sleeps, then it blocks all ioctls since the lock is still
+		 * held. This is very common for VIDIOC_DQBUF since that
+		 * normally waits for a frame to arrive. As a result any other
+		 * ioctl calls will proceed very, very slowly since each call
+		 * will have to wait for the VIDIOC_QBUF to finish. Things that
+		 * should take 0.01s may now take 10-20 seconds.
+		 *
+		 * The workaround is to *not* take the lock for VIDIOC_DQBUF.
+		 * This actually works OK for videobuf-based drivers, since
+		 * videobuf will take its own internal lock.
+		 */
 		static DEFINE_MUTEX(v4l2_ioctl_mutex);
+		struct mutex *m = vdev->v4l2_dev ?
+			&vdev->v4l2_dev->ioctl_lock : &v4l2_ioctl_mutex;
 
-		mutex_lock(&v4l2_ioctl_mutex);
+		if (cmd != VIDIOC_DQBUF && mutex_lock_interruptible(m))
+			return -ERESTARTSYS;
 		if (video_is_registered(vdev))
 			ret = vdev->fops->ioctl(filp, cmd, arg);
-		mutex_unlock(&v4l2_ioctl_mutex);
+		if (cmd != VIDIOC_DQBUF)
+			mutex_unlock(m);
 	} else
 		ret = -ENOTTY;
 
@@ -265,8 +290,8 @@ static int v4l2_mmap(struct file *filp, struct vm_area_struct *vm)
 
 	if (!vdev->fops->mmap)
 		return ret;
-	if (vdev->lock)
-		mutex_lock(vdev->lock);
+	if (vdev->lock && mutex_lock_interruptible(vdev->lock))
+		return -ERESTARTSYS;
 	if (video_is_registered(vdev))
 		ret = vdev->fops->mmap(filp, vm);
 	if (vdev->lock)
@@ -284,7 +309,7 @@ static int v4l2_open(struct inode *inode, struct file *filp)
 	mutex_lock(&videodev_lock);
 	vdev = video_devdata(filp);
 	/* return ENODEV if the video device has already been removed. */
-	if (vdev == NULL) {
+	if (vdev == NULL || !video_is_registered(vdev)) {
 		mutex_unlock(&videodev_lock);
 		return -ENODEV;
 	}
@@ -292,8 +317,10 @@ static int v4l2_open(struct inode *inode, struct file *filp)
 	video_get(vdev);
 	mutex_unlock(&videodev_lock);
 	if (vdev->fops->open) {
-		if (vdev->lock)
-			mutex_lock(vdev->lock);
+		if (vdev->lock && mutex_lock_interruptible(vdev->lock)) {
+			ret = -ERESTARTSYS;
+			goto err;
+		}
 		if (video_is_registered(vdev))
 			ret = vdev->fops->open(filp);
 		else
@@ -302,6 +329,7 @@ static int v4l2_open(struct inode *inode, struct file *filp)
 			mutex_unlock(vdev->lock);
 	}
 
+err:
 	/* decrease the refcount in case of an error */
 	if (ret)
 		video_put(vdev);
@@ -596,7 +624,12 @@ void video_unregister_device(struct video_device *vdev)
 	if (!vdev || !video_is_registered(vdev))
 		return;
 
+	mutex_lock(&videodev_lock);
+	/* This must be in a critical section to prevent a race with v4l2_open.
+	 * Once this bit has been cleared video_get may never be called again.
+	 */
 	clear_bit(V4L2_FL_REGISTERED, &vdev->flags);
+	mutex_unlock(&videodev_lock);
 	device_unregister(&vdev->dev);
 }
 EXPORT_SYMBOL(video_unregister_device);
diff --git a/drivers/media/video/v4l2-device.c b/drivers/media/video/v4l2-device.c
index 0b08f96b74a..7fe6f92af48 100644
--- a/drivers/media/video/v4l2-device.c
+++ b/drivers/media/video/v4l2-device.c
@@ -35,6 +35,7 @@ int v4l2_device_register(struct device *dev, struct v4l2_device *v4l2_dev)
 
 	INIT_LIST_HEAD(&v4l2_dev->subdevs);
 	spin_lock_init(&v4l2_dev->lock);
+	mutex_init(&v4l2_dev->ioctl_lock);
 	v4l2_dev->dev = dev;
 	if (dev == NULL) {
 		/* If dev == NULL, then name must be filled in by the caller */
diff --git a/drivers/media/video/w9966.c b/drivers/media/video/w9966.c
index 635420d8d84..019ee206cbe 100644
--- a/drivers/media/video/w9966.c
+++ b/drivers/media/video/w9966.c
@@ -815,7 +815,7 @@ out:
 
 static const struct v4l2_file_operations w9966_fops = {
 	.owner		= THIS_MODULE,
-	.ioctl          = video_ioctl2,
+	.unlocked_ioctl = video_ioctl2,
 	.read           = w9966_v4l_read,
 };
 
diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c
index 003170ea2e3..69546e9213d 100644
--- a/drivers/pci/bus.c
+++ b/drivers/pci/bus.c
@@ -64,77 +64,6 @@ void pci_bus_remove_resources(struct pci_bus *bus)
 	}
 }
 
-static bool pci_bus_resource_better(struct resource *res1, bool pos1,
-				    struct resource *res2, bool pos2)
-{
-	/* If exactly one is positive decode, always prefer that one */
-	if (pos1 != pos2)
-		return pos1 ? true : false;
-
-	/* Prefer the one that contains the highest address */
-	if (res1->end != res2->end)
-		return (res1->end > res2->end) ? true : false;
-
-	/* Otherwise, prefer the one with highest "center of gravity" */
-	if (res1->start != res2->start)
-		return (res1->start > res2->start) ? true : false;
-
-	/* Otherwise, choose one arbitrarily (but consistently) */
-	return (res1 > res2) ? true : false;
-}
-
-static bool pci_bus_resource_positive(struct pci_bus *bus, struct resource *res)
-{
-	struct pci_bus_resource *bus_res;
-
-	/*
-	 * This relies on the fact that pci_bus.resource[] refers to P2P or
-	 * CardBus bridge base/limit registers, which are always positively
-	 * decoded.  The pci_bus.resources list contains host bridge or
-	 * subtractively decoded resources.
-	 */
-	list_for_each_entry(bus_res, &bus->resources, list) {
-		if (bus_res->res == res)
-			return (bus_res->flags & PCI_SUBTRACTIVE_DECODE) ?
-				false : true;
-	}
-	return true;
-}
-
-/*
- * Find the next-best bus resource after the cursor "res".  If the cursor is
- * NULL, return the best resource.  "Best" means that we prefer positive
- * decode regions over subtractive decode, then those at higher addresses.
- */
-static struct resource *pci_bus_find_resource_prev(struct pci_bus *bus,
-						   unsigned int type,
-						   struct resource *res)
-{
-	bool res_pos, r_pos, prev_pos = false;
-	struct resource *r, *prev = NULL;
-	int i;
-
-	res_pos = pci_bus_resource_positive(bus, res);
-	pci_bus_for_each_resource(bus, r, i) {
-		if (!r)
-			continue;
-
-		if ((r->flags & IORESOURCE_TYPE_BITS) != type)
-			continue;
-
-		r_pos = pci_bus_resource_positive(bus, r);
-		if (!res || pci_bus_resource_better(res, res_pos, r, r_pos)) {
-			if (!prev || pci_bus_resource_better(r, r_pos,
-							     prev, prev_pos)) {
-				prev = r;
-				prev_pos = r_pos;
-			}
-		}
-	}
-
-	return prev;
-}
-
 /**
  * pci_bus_alloc_resource - allocate a resource from a parent bus
  * @bus: PCI bus
@@ -160,10 +89,9 @@ pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
 					  resource_size_t),
 		void *alignf_data)
 {
-	int ret = -ENOMEM;
+	int i, ret = -ENOMEM;
 	struct resource *r;
 	resource_size_t max = -1;
-	unsigned int type = res->flags & IORESOURCE_TYPE_BITS;
 
 	type_mask |= IORESOURCE_IO | IORESOURCE_MEM;
 
@@ -171,9 +99,10 @@ pci_bus_alloc_resource(struct pci_bus *bus, struct resource *res,
 	if (!(res->flags & IORESOURCE_MEM_64))
 		max = PCIBIOS_MAX_MEM_32;
 
-	/* Look for space at highest addresses first */
-	r = pci_bus_find_resource_prev(bus, type, NULL);
-	for ( ; r; r = pci_bus_find_resource_prev(bus, type, r)) {
+	pci_bus_for_each_resource(bus, r, i) {
+		if (!r)
+			continue;
+
 		/* type_mask must match */
 		if ((res->flags ^ r->flags) & type_mask)
 			continue;
diff --git a/drivers/pci/dmar.c b/drivers/pci/dmar.c
index 0157708d474..09933eb9126 100644
--- a/drivers/pci/dmar.c
+++ b/drivers/pci/dmar.c
@@ -1417,6 +1417,11 @@ int __init enable_drhd_fault_handling(void)
 			       (unsigned long long)drhd->reg_base_addr, ret);
 			return -1;
 		}
+
+		/*
+		 * Clear any previous faults.
+		 */
+		dmar_fault(iommu->irq, iommu);
 	}
 
 	return 0;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 6f9350cabbd..53a786fd0d4 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2329,6 +2329,9 @@ static void __devinit nvbridge_check_legacy_irq_routing(struct pci_dev *dev)
 {
 	u32 cfg;
 
+	if (!pci_find_capability(dev, PCI_CAP_ID_HT))
+		return;
+
 	pci_read_config_dword(dev, 0x74, &cfg);
 
 	if (cfg & ((1 << 2) | (1 << 15))) {
@@ -2764,6 +2767,29 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_m
 DECLARE_PCI_FIXUP_RESUME_EARLY(PCI_VENDOR_ID_RICOH, PCI_DEVICE_ID_RICOH_R5C832, ricoh_mmc_fixup_r5c832);
 #endif /*CONFIG_MMC_RICOH_MMC*/
 
+#if defined(CONFIG_DMAR) || defined(CONFIG_INTR_REMAP)
+#define VTUNCERRMSK_REG	0x1ac
+#define VTD_MSK_SPEC_ERRORS	(1 << 31)
+/*
+ * This is a quirk for masking vt-d spec defined errors to platform error
+ * handling logic. With out this, platforms using Intel 7500, 5500 chipsets
+ * (and the derivative chipsets like X58 etc) seem to generate NMI/SMI (based
+ * on the RAS config settings of the platform) when a vt-d fault happens.
+ * The resulting SMI caused the system to hang.
+ *
+ * VT-d spec related errors are already handled by the VT-d OS code, so no
+ * need to report the same error through other channels.
+ */
+static void vtd_mask_spec_errors(struct pci_dev *dev)
+{
+	u32 word;
+
+	pci_read_config_dword(dev, VTUNCERRMSK_REG, &word);
+	pci_write_config_dword(dev, VTUNCERRMSK_REG, word | VTD_MSK_SPEC_ERRORS);
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x342e, vtd_mask_spec_errors);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x3c28, vtd_mask_spec_errors);
+#endif
 
 static void pci_do_fixups(struct pci_dev *dev, struct pci_fixup *f,
 			  struct pci_fixup *end)
diff --git a/drivers/scsi/scsi_lib.c b/drivers/scsi/scsi_lib.c
index 5b6bbaea59f..4a3842212c5 100644
--- a/drivers/scsi/scsi_lib.c
+++ b/drivers/scsi/scsi_lib.c
@@ -1637,9 +1637,8 @@ struct request_queue *__scsi_alloc_queue(struct Scsi_Host *shost,
 
 	blk_queue_max_segment_size(q, dma_get_max_seg_size(dev));
 
-	/* New queue, no concurrency on queue_flags */
 	if (!shost->use_clustering)
-		queue_flag_clear_unlocked(QUEUE_FLAG_CLUSTER, q);
+		q->limits.cluster = 0;
 
 	/*
 	 * set a reasonable default alignment on word boundaries: the
diff --git a/drivers/staging/cx25821/cx25821-video.c b/drivers/staging/cx25821/cx25821-video.c
index e7f1d5778ce..52389308f33 100644
--- a/drivers/staging/cx25821/cx25821-video.c
+++ b/drivers/staging/cx25821/cx25821-video.c
@@ -92,7 +92,7 @@ int cx25821_get_format_size(void)
 	return ARRAY_SIZE(formats);
 }
 
-struct cx25821_fmt *format_by_fourcc(unsigned int fourcc)
+struct cx25821_fmt *cx25821_format_by_fourcc(unsigned int fourcc)
 {
 	unsigned int i;
 
@@ -848,7 +848,7 @@ static int video_open(struct file *file)
        pix_format =
 	   (dev->channels[ch_id].pixel_formats ==
 	    PIXEL_FRMT_411) ? V4L2_PIX_FMT_Y41P : V4L2_PIX_FMT_YUYV;
-       fh->fmt = format_by_fourcc(pix_format);
+       fh->fmt = cx25821_format_by_fourcc(pix_format);
 
        v4l2_prio_open(&dev->channels[ch_id].prio, &fh->prio);
 
@@ -1010,7 +1010,7 @@ static int vidioc_s_fmt_vid_cap(struct file *file, void *priv,
        if (0 != err)
 	       return err;
 
-       fh->fmt = format_by_fourcc(f->fmt.pix.pixelformat);
+       fh->fmt = cx25821_format_by_fourcc(f->fmt.pix.pixelformat);
        fh->vidq.field = f->fmt.pix.field;
 
        /* check if width and height is valid based on set standard */
@@ -1119,7 +1119,7 @@ int cx25821_vidioc_try_fmt_vid_cap(struct file *file, void *priv, struct v4l2_fo
 	enum v4l2_field field;
 	unsigned int maxw, maxh;
 
-	fmt = format_by_fourcc(f->fmt.pix.pixelformat);
+	fmt = cx25821_format_by_fourcc(f->fmt.pix.pixelformat);
 	if (NULL == fmt)
 		return -EINVAL;
 
diff --git a/drivers/staging/cx25821/cx25821-video.h b/drivers/staging/cx25821/cx25821-video.h
index cc6034b1a95..a2415d33235 100644
--- a/drivers/staging/cx25821/cx25821-video.h
+++ b/drivers/staging/cx25821/cx25821-video.h
@@ -87,7 +87,7 @@ extern unsigned int vid_limit;
 
 #define FORMAT_FLAGS_PACKED       0x01
 extern struct cx25821_fmt formats[];
-extern struct cx25821_fmt *format_by_fourcc(unsigned int fourcc);
+extern struct cx25821_fmt *cx25821_format_by_fourcc(unsigned int fourcc);
 extern struct cx25821_data timeout_data[MAX_VID_CHANNEL_NUM];
 
 extern void cx25821_dump_video_queue(struct cx25821_dev *dev,
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index 81b46585edf..c5f8e5bda2b 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -716,8 +716,8 @@ static void __gsm_data_queue(struct gsm_dlci *dlci, struct gsm_msg *msg)
 		if (msg->len < 128)
 			*--dp = (msg->len << 1) | EA;
 		else {
-			*--dp = ((msg->len & 127) << 1) | EA;
-			*--dp = (msg->len >> 6) & 0xfe;
+			*--dp = (msg->len >> 7);	/* bits 7 - 15 */
+			*--dp = (msg->len & 127) << 1;	/* bits 0 - 6 */
 		}
 	}
 
@@ -968,6 +968,8 @@ static void gsm_control_reply(struct gsm_mux *gsm, int cmd, u8 *data,
 {
 	struct gsm_msg *msg;
 	msg = gsm_data_alloc(gsm, 0, dlen + 2, gsm->ftype);
+	if (msg == NULL)
+		return;
 	msg->data[0] = (cmd & 0xFE) << 1 | EA;	/* Clear C/R */
 	msg->data[1] = (dlen << 1) | EA;
 	memcpy(msg->data + 2, data, dlen);
diff --git a/drivers/usb/core/Kconfig b/drivers/usb/core/Kconfig
index 9eed5b52d9d..bcc24779ba0 100644
--- a/drivers/usb/core/Kconfig
+++ b/drivers/usb/core/Kconfig
@@ -107,11 +107,19 @@ config USB_SUSPEND
 	  If you are unsure about this, say N here.
 
 config USB_OTG
-	bool
+	bool "OTG support"
 	depends on USB && EXPERIMENTAL
 	depends on USB_SUSPEND
 	default n
+	help
+	  The most notable feature of USB OTG is support for a
+	  "Dual-Role" device, which can act as either a device
+	  or a host. The initial role is decided by the type of
+	  plug inserted and can be changed later when two dual
+	  role devices talk to each other.
 
+	  Select this only if your board has Mini-AB/Micro-AB
+	  connector.
 
 config USB_OTG_WHITELIST
 	bool "Rely on OTG Targeted Peripherals List"
diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 7b5cc16e4a0..8572dad5ecb 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1047,9 +1047,9 @@ composite_unbind(struct usb_gadget *gadget)
 		kfree(cdev->req->buf);
 		usb_ep_free_request(gadget->ep0, cdev->req);
 	}
+	device_remove_file(&gadget->dev, &dev_attr_suspended);
 	kfree(cdev);
 	set_gadget_data(gadget, NULL);
-	device_remove_file(&gadget->dev, &dev_attr_suspended);
 	composite = NULL;
 }
 
@@ -1107,14 +1107,6 @@ static int composite_bind(struct usb_gadget *gadget)
 	 */
 	usb_ep_autoconfig_reset(cdev->gadget);
 
-	/* standardized runtime overrides for device ID data */
-	if (idVendor)
-		cdev->desc.idVendor = cpu_to_le16(idVendor);
-	if (idProduct)
-		cdev->desc.idProduct = cpu_to_le16(idProduct);
-	if (bcdDevice)
-		cdev->desc.bcdDevice = cpu_to_le16(bcdDevice);
-
 	/* composite gadget needs to assign strings for whole device (like
 	 * serial number), register function drivers, potentially update
 	 * power state and consumption, etc
@@ -1126,6 +1118,14 @@ static int composite_bind(struct usb_gadget *gadget)
 	cdev->desc = *composite->dev;
 	cdev->desc.bMaxPacketSize0 = gadget->ep0->maxpacket;
 
+	/* standardized runtime overrides for device ID data */
+	if (idVendor)
+		cdev->desc.idVendor = cpu_to_le16(idVendor);
+	if (idProduct)
+		cdev->desc.idProduct = cpu_to_le16(idProduct);
+	if (bcdDevice)
+		cdev->desc.bcdDevice = cpu_to_le16(bcdDevice);
+
 	/* stirng overrides */
 	if (iManufacturer || !cdev->desc.iManufacturer) {
 		if (!iManufacturer && !composite->iManufacturer &&
diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
index 0fae58ef8af..1d0f45f0e7a 100644
--- a/drivers/usb/host/xhci-mem.c
+++ b/drivers/usb/host/xhci-mem.c
@@ -1680,6 +1680,7 @@ static void xhci_add_in_port(struct xhci_hcd *xhci, unsigned int num_ports,
 				xhci->port_array[i] = (u8) -1;
 			}
 			/* FIXME: Should we disable the port? */
+			continue;
 		}
 		xhci->port_array[i] = major_revision;
 		if (major_revision == 0x03)
@@ -1758,16 +1759,20 @@ static int xhci_setup_port_arrays(struct xhci_hcd *xhci, gfp_t flags)
 			return -ENOMEM;
 
 		port_index = 0;
-		for (i = 0; i < num_ports; i++)
-			if (xhci->port_array[i] != 0x03) {
-				xhci->usb2_ports[port_index] =
-					&xhci->op_regs->port_status_base +
-					NUM_PORT_REGS*i;
-				xhci_dbg(xhci, "USB 2.0 port at index %u, "
-						"addr = %p\n", i,
-						xhci->usb2_ports[port_index]);
-				port_index++;
-			}
+		for (i = 0; i < num_ports; i++) {
+			if (xhci->port_array[i] == 0x03 ||
+					xhci->port_array[i] == 0 ||
+					xhci->port_array[i] == -1)
+				continue;
+
+			xhci->usb2_ports[port_index] =
+				&xhci->op_regs->port_status_base +
+				NUM_PORT_REGS*i;
+			xhci_dbg(xhci, "USB 2.0 port at index %u, "
+					"addr = %p\n", i,
+					xhci->usb2_ports[port_index]);
+			port_index++;
+		}
 	}
 	if (xhci->num_usb3_ports) {
 		xhci->usb3_ports = kmalloc(sizeof(*xhci->usb3_ports)*
diff --git a/drivers/usb/misc/uss720.c b/drivers/usb/misc/uss720.c
index 796e2f68f74..4ff21587ab0 100644
--- a/drivers/usb/misc/uss720.c
+++ b/drivers/usb/misc/uss720.c
@@ -3,7 +3,7 @@
 /*
  *	uss720.c  --  USS720 USB Parport Cable.
  *
- *	Copyright (C) 1999, 2005
+ *	Copyright (C) 1999, 2005, 2010
  *	    Thomas Sailer (t.sailer@alumni.ethz.ch)
  *
  *	This program is free software; you can redistribute it and/or modify
@@ -776,6 +776,8 @@ static const struct usb_device_id uss720_table[] = {
 	{ USB_DEVICE(0x0557, 0x2001) },
 	{ USB_DEVICE(0x0729, 0x1284) },
 	{ USB_DEVICE(0x1293, 0x0002) },
+	{ USB_DEVICE(0x1293, 0x0002) },
+	{ USB_DEVICE(0x050d, 0x0002) },
 	{ }						/* Terminating entry */
 };
 
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 6a50965e23f..2dec5001352 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -796,6 +796,7 @@ static struct usb_device_id id_table_combined [] = {
 	{ USB_DEVICE(FTDI_VID, FTDI_SCIENCESCOPE_LOGBOOKML_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SCIENCESCOPE_LS_LOGBOOK_PID) },
 	{ USB_DEVICE(FTDI_VID, FTDI_SCIENCESCOPE_HS_LOGBOOK_PID) },
+	{ USB_DEVICE(FTDI_VID, FTDI_DOTEC_PID) },
 	{ USB_DEVICE(QIHARDWARE_VID, MILKYMISTONE_JTAGSERIAL_PID),
 		.driver_info = (kernel_ulong_t)&ftdi_jtag_quirk },
 	{ },					/* Optional parameter entry */
diff --git a/drivers/usb/serial/ftdi_sio_ids.h b/drivers/usb/serial/ftdi_sio_ids.h
index 1286f1e23d8..bf086728548 100644
--- a/drivers/usb/serial/ftdi_sio_ids.h
+++ b/drivers/usb/serial/ftdi_sio_ids.h
@@ -1081,6 +1081,11 @@
 #define MJSG_HD_RADIO_PID	0x937C
 
 /*
+ * D.O.Tec products (http://www.directout.eu)
+ */
+#define FTDI_DOTEC_PID 0x9868
+
+/*
  * Xverve Signalyzer tools (http://www.signalyzer.com/)
  */
 #define XVERVE_SIGNALYZER_ST_PID	0xBCA0
diff --git a/drivers/usb/storage/unusual_devs.h b/drivers/usb/storage/unusual_devs.h
index 6ccdd3dd525..fcc1e32ce25 100644
--- a/drivers/usb/storage/unusual_devs.h
+++ b/drivers/usb/storage/unusual_devs.h
@@ -481,6 +481,13 @@ UNUSUAL_DEV(  0x04e8, 0x507c, 0x0220, 0x0220,
 		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
 		US_FL_MAX_SECTORS_64),
 
+/* Reported by Vitaly Kuznetsov <vitty@altlinux.ru> */
+UNUSUAL_DEV(  0x04e8, 0x5122, 0x0000, 0x9999,
+		"Samsung",
+		"YP-CP3",
+		USB_SC_DEVICE, USB_PR_DEVICE, NULL,
+		US_FL_MAX_SECTORS_64 | US_FL_BULK_IGNORE_TAG),
+
 /* Entry and supporting patch by Theodore Kilgore <kilgota@auburn.edu>.
  * Device uses standards-violating 32-byte Bulk Command Block Wrappers and
  * reports itself as "Proprietary SCSI Bulk." Cf. device entry 0x084d:0x0011.
diff --git a/drivers/video/omap/Kconfig b/drivers/video/omap/Kconfig
index 455c6055325..083c8fe53e2 100644
--- a/drivers/video/omap/Kconfig
+++ b/drivers/video/omap/Kconfig
@@ -1,7 +1,7 @@
 config FB_OMAP
 	tristate "OMAP frame buffer support (EXPERIMENTAL)"
-	depends on FB && ARCH_OMAP && (OMAP2_DSS = "n")
-
+	depends on FB && (OMAP2_DSS = "n")
+	depends on ARCH_OMAP1 || ARCH_OMAP2 || ARCH_OMAP3
 	select FB_CFB_FILLRECT
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
diff --git a/drivers/video/omap2/vram.c b/drivers/video/omap2/vram.c
index 2fd7e5271be..9441e2eb3de 100644
--- a/drivers/video/omap2/vram.c
+++ b/drivers/video/omap2/vram.c
@@ -551,7 +551,7 @@ void __init omap_vram_reserve_sdram_memblock(void)
 	if (!size)
 		return;
 
-	size = PAGE_ALIGN(size);
+	size = ALIGN(size, SZ_2M);
 
 	if (paddr) {
 		if (paddr & ~PAGE_MASK) {
@@ -576,7 +576,7 @@ void __init omap_vram_reserve_sdram_memblock(void)
 			return;
 		}
 	} else {
-		paddr = memblock_alloc(size, PAGE_SIZE);
+		paddr = memblock_alloc(size, SZ_2M);
 	}
 
 	memblock_free(paddr, size);
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 6f044447359..659f532d26a 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -166,7 +166,7 @@ static struct dentry *btrfs_fh_to_dentry(struct super_block *sb, struct fid *fh,
 static struct dentry *btrfs_get_parent(struct dentry *child)
 {
 	struct inode *dir = child->d_inode;
-	static struct dentry *dentry;
+	struct dentry *dentry;
 	struct btrfs_root *root = BTRFS_I(dir)->root;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 158c700fdca..d902948a90d 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -40,7 +40,8 @@ int ceph_init_dentry(struct dentry *dentry)
 	if (dentry->d_fsdata)
 		return 0;
 
-	if (ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
+	if (dentry->d_parent == NULL ||   /* nfs fh_to_dentry */
+	    ceph_snap(dentry->d_parent->d_inode) == CEPH_NOSNAP)
 		dentry->d_op = &ceph_dentry_ops;
 	else if (ceph_snap(dentry->d_parent->d_inode) == CEPH_SNAPDIR)
 		dentry->d_op = &ceph_snapdir_dentry_ops;
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 8d79b8912e3..7d0e4a82d89 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -282,7 +282,8 @@ int ceph_release(struct inode *inode, struct file *file)
 static int striped_read(struct inode *inode,
 			u64 off, u64 len,
 			struct page **pages, int num_pages,
-			int *checkeof, bool align_to_pages)
+			int *checkeof, bool align_to_pages,
+			unsigned long buf_align)
 {
 	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
 	struct ceph_inode_info *ci = ceph_inode(inode);
@@ -307,7 +308,7 @@ static int striped_read(struct inode *inode,
 
 more:
 	if (align_to_pages)
-		page_align = (pos - io_align) & ~PAGE_MASK;
+		page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
 	else
 		page_align = pos & ~PAGE_MASK;
 	this_len = left;
@@ -376,16 +377,18 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
 	struct inode *inode = file->f_dentry->d_inode;
 	struct page **pages;
 	u64 off = *poff;
-	int num_pages = calc_pages_for(off, len);
-	int ret;
+	int num_pages, ret;
 
 	dout("sync_read on file %p %llu~%u %s\n", file, off, len,
 	     (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");
 
-	if (file->f_flags & O_DIRECT)
-		pages = ceph_get_direct_page_vector(data, num_pages);
-	else
+	if (file->f_flags & O_DIRECT) {
+		num_pages = calc_pages_for((unsigned long)data, len);
+		pages = ceph_get_direct_page_vector(data, num_pages, true);
+	} else {
+		num_pages = calc_pages_for(off, len);
 		pages = ceph_alloc_page_vector(num_pages, GFP_NOFS);
+	}
 	if (IS_ERR(pages))
 		return PTR_ERR(pages);
 
@@ -400,7 +403,8 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
 		goto done;
 
 	ret = striped_read(inode, off, len, pages, num_pages, checkeof,
-			   file->f_flags & O_DIRECT);
+			   file->f_flags & O_DIRECT,
+			   (unsigned long)data & ~PAGE_MASK);
 
 	if (ret >= 0 && (file->f_flags & O_DIRECT) == 0)
 		ret = ceph_copy_page_vector_to_user(pages, data, off, ret);
@@ -409,7 +413,7 @@ static ssize_t ceph_sync_read(struct file *file, char __user *data,
 
 done:
 	if (file->f_flags & O_DIRECT)
-		ceph_put_page_vector(pages, num_pages);
+		ceph_put_page_vector(pages, num_pages, true);
 	else
 		ceph_release_page_vector(pages, num_pages);
 	dout("sync_read result %d\n", ret);
@@ -456,6 +460,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
 	int do_sync = 0;
 	int check_caps = 0;
 	int page_align, io_align;
+	unsigned long buf_align;
 	int ret;
 	struct timespec mtime = CURRENT_TIME;
 
@@ -471,6 +476,7 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
 		pos = *offset;
 
 	io_align = pos & ~PAGE_MASK;
+	buf_align = (unsigned long)data & ~PAGE_MASK;
 
 	ret = filemap_write_and_wait_range(inode->i_mapping, pos, pos + left);
 	if (ret < 0)
@@ -496,12 +502,15 @@ static ssize_t ceph_sync_write(struct file *file, const char __user *data,
 	 */
 more:
 	len = left;
-	if (file->f_flags & O_DIRECT)
+	if (file->f_flags & O_DIRECT) {
 		/* write from beginning of first page, regardless of
 		   io alignment */
-		page_align = (pos - io_align) & ~PAGE_MASK;
-	else
+		page_align = (pos - io_align + buf_align) & ~PAGE_MASK;
+		num_pages = calc_pages_for((unsigned long)data, len);
+	} else {
 		page_align = pos & ~PAGE_MASK;
+		num_pages = calc_pages_for(pos, len);
+	}
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 				    ceph_vino(inode), pos, &len,
 				    CEPH_OSD_OP_WRITE, flags,
@@ -512,10 +521,8 @@ more:
 	if (!req)
 		return -ENOMEM;
 
-	num_pages = calc_pages_for(pos, len);
-
 	if (file->f_flags & O_DIRECT) {
-		pages = ceph_get_direct_page_vector(data, num_pages);
+		pages = ceph_get_direct_page_vector(data, num_pages, false);
 		if (IS_ERR(pages)) {
 			ret = PTR_ERR(pages);
 			goto out;
@@ -565,7 +572,7 @@ more:
 	}
 
 	if (file->f_flags & O_DIRECT)
-		ceph_put_page_vector(pages, num_pages);
+		ceph_put_page_vector(pages, num_pages, false);
 	else if (file->f_flags & O_SYNC)
 		ceph_release_page_vector(pages, num_pages);
 
diff --git a/fs/namei.c b/fs/namei.c
index 5362af9b737..4ff7ca53053 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1748,6 +1748,9 @@ struct file *do_filp_open(int dfd, const char *pathname,
 	if (!(open_flag & O_CREAT))
 		mode = 0;
 
+	/* Must never be set by userspace */
+	open_flag &= ~FMODE_NONOTIFY;
+
 	/*
 	 * O_SYNC is implemented as __O_SYNC|O_DSYNC.  As many places only
 	 * check for O_DSYNC if the need any syncing at all we enforce it's
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 33ad25ddd5c..caf9a6a3fb5 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -176,7 +176,6 @@ int nilfs_gccache_wait_and_mark_dirty(struct buffer_head *bh)
 int nilfs_init_gcinode(struct inode *inode)
 {
 	struct nilfs_inode_info *ii = NILFS_I(inode);
-	struct the_nilfs *nilfs = NILFS_SB(inode->i_sb)->s_nilfs;
 
 	inode->i_mode = S_IFREG;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
@@ -186,14 +185,6 @@ int nilfs_init_gcinode(struct inode *inode)
 	ii->i_flags = 0;
 	nilfs_bmap_init_gc(ii->i_bmap);
 
-	/*
-	 * Add the inode to GC inode list. Garbage Collection
-	 * is serialized and no two processes manipulate the
-	 * list simultaneously.
-	 */
-	igrab(inode);
-	list_add(&NILFS_I(inode)->i_dirty, &nilfs->ns_gc_inodes);
-
 	return 0;
 }
 
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index e00d9457c25..b185e937a33 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -337,6 +337,7 @@ static int nilfs_ioctl_move_blocks(struct super_block *sb,
 				   struct nilfs_argv *argv, void *buf)
 {
 	size_t nmembs = argv->v_nmembs;
+	struct the_nilfs *nilfs = NILFS_SB(sb)->s_nilfs;
 	struct inode *inode;
 	struct nilfs_vdesc *vdesc;
 	struct buffer_head *bh, *n;
@@ -353,6 +354,17 @@ static int nilfs_ioctl_move_blocks(struct super_block *sb,
 			ret = PTR_ERR(inode);
 			goto failed;
 		}
+		if (list_empty(&NILFS_I(inode)->i_dirty)) {
+			/*
+			 * Add the inode to GC inode list. Garbage Collection
+			 * is serialized and no two processes manipulate the
+			 * list simultaneously.
+			 */
+			igrab(inode);
+			list_add(&NILFS_I(inode)->i_dirty,
+				 &nilfs->ns_gc_inodes);
+		}
+
 		do {
 			ret = nilfs_ioctl_move_inode_block(inode, vdesc,
 							   &buffers);
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index b04f88eed09..f35794b97e8 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -92,7 +92,11 @@ static int fanotify_get_response_from_access(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	wait_event(group->fanotify_data.access_waitq, event->response);
+	wait_event(group->fanotify_data.access_waitq, event->response ||
+				atomic_read(&group->fanotify_data.bypass_perm));
+
+	if (!event->response) /* bypass_perm set */
+		return 0;
 
 	/* userspace responded, convert to something usable */
 	spin_lock(&event->lock);
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 063224812b7..8b61220cffc 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -106,20 +106,29 @@ static int create_fd(struct fsnotify_group *group, struct fsnotify_event *event)
 	return client_fd;
 }
 
-static ssize_t fill_event_metadata(struct fsnotify_group *group,
+static int fill_event_metadata(struct fsnotify_group *group,
 				   struct fanotify_event_metadata *metadata,
 				   struct fsnotify_event *event)
 {
+	int ret = 0;
+
 	pr_debug("%s: group=%p metadata=%p event=%p\n", __func__,
 		 group, metadata, event);
 
 	metadata->event_len = FAN_EVENT_METADATA_LEN;
+	metadata->metadata_len = FAN_EVENT_METADATA_LEN;
 	metadata->vers = FANOTIFY_METADATA_VERSION;
 	metadata->mask = event->mask & FAN_ALL_OUTGOING_EVENTS;
 	metadata->pid = pid_vnr(event->tgid);
-	metadata->fd = create_fd(group, event);
+	if (unlikely(event->mask & FAN_Q_OVERFLOW))
+		metadata->fd = FAN_NOFD;
+	else {
+		metadata->fd = create_fd(group, event);
+		if (metadata->fd < 0)
+			ret = metadata->fd;
+	}
 
-	return metadata->fd;
+	return ret;
 }
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
@@ -200,7 +209,7 @@ static int prepare_for_access_response(struct fsnotify_group *group,
 
 	mutex_lock(&group->fanotify_data.access_mutex);
 
-	if (group->fanotify_data.bypass_perm) {
+	if (atomic_read(&group->fanotify_data.bypass_perm)) {
 		mutex_unlock(&group->fanotify_data.access_mutex);
 		kmem_cache_free(fanotify_response_event_cache, re);
 		event->response = FAN_ALLOW;
@@ -257,24 +266,34 @@ static ssize_t copy_event_to_user(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	fd = fill_event_metadata(group, &fanotify_event_metadata, event);
-	if (fd < 0)
-		return fd;
+	ret = fill_event_metadata(group, &fanotify_event_metadata, event);
+	if (ret < 0)
+		goto out;
 
+	fd = fanotify_event_metadata.fd;
 	ret = prepare_for_access_response(group, event, fd);
 	if (ret)
 		goto out_close_fd;
 
 	ret = -EFAULT;
-	if (copy_to_user(buf, &fanotify_event_metadata, FAN_EVENT_METADATA_LEN))
+	if (copy_to_user(buf, &fanotify_event_metadata,
+			 fanotify_event_metadata.event_len))
 		goto out_kill_access_response;
 
-	return FAN_EVENT_METADATA_LEN;
+	return fanotify_event_metadata.event_len;
 
 out_kill_access_response:
 	remove_access_response(group, event, fd);
 out_close_fd:
-	sys_close(fd);
+	if (fd != FAN_NOFD)
+		sys_close(fd);
+out:
+#ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
+	if (event->mask & FAN_ALL_PERM_EVENTS) {
+		event->response = FAN_DENY;
+		wake_up(&group->fanotify_data.access_waitq);
+	}
+#endif
 	return ret;
 }
 
@@ -382,7 +401,7 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 
 	mutex_lock(&group->fanotify_data.access_mutex);
 
-	group->fanotify_data.bypass_perm = true;
+	atomic_inc(&group->fanotify_data.bypass_perm);
 
 	list_for_each_entry_safe(re, lre, &group->fanotify_data.access_list, list) {
 		pr_debug("%s: found group=%p re=%p event=%p\n", __func__, group,
@@ -586,11 +605,10 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
 {
 	struct fsnotify_mark *fsn_mark;
 	__u32 added;
+	int ret = 0;
 
 	fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
 	if (!fsn_mark) {
-		int ret;
-
 		if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
 			return -ENOSPC;
 
@@ -600,17 +618,16 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
 
 		fsnotify_init_mark(fsn_mark, fanotify_free_mark);
 		ret = fsnotify_add_mark(fsn_mark, group, NULL, mnt, 0);
-		if (ret) {
-			fanotify_free_mark(fsn_mark);
-			return ret;
-		}
+		if (ret)
+			goto err;
 	}
 	added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
-	fsnotify_put_mark(fsn_mark);
+
 	if (added & ~mnt->mnt_fsnotify_mask)
 		fsnotify_recalc_vfsmount_mask(mnt);
-
-	return 0;
+err:
+	fsnotify_put_mark(fsn_mark);
+	return ret;
 }
 
 static int fanotify_add_inode_mark(struct fsnotify_group *group,
@@ -619,6 +636,7 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
 {
 	struct fsnotify_mark *fsn_mark;
 	__u32 added;
+	int ret = 0;
 
 	pr_debug("%s: group=%p inode=%p\n", __func__, group, inode);
 
@@ -634,8 +652,6 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
 
 	fsn_mark = fsnotify_find_inode_mark(group, inode);
 	if (!fsn_mark) {
-		int ret;
-
 		if (atomic_read(&group->num_marks) > group->fanotify_data.max_marks)
 			return -ENOSPC;
 
@@ -645,16 +661,16 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
 
 		fsnotify_init_mark(fsn_mark, fanotify_free_mark);
 		ret = fsnotify_add_mark(fsn_mark, group, inode, NULL, 0);
-		if (ret) {
-			fanotify_free_mark(fsn_mark);
-			return ret;
-		}
+		if (ret)
+			goto err;
 	}
 	added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
-	fsnotify_put_mark(fsn_mark);
+
 	if (added & ~inode->i_fsnotify_mask)
 		fsnotify_recalc_inode_mask(inode);
-	return 0;
+err:
+	fsnotify_put_mark(fsn_mark);
+	return ret;
 }
 
 /* fanotify syscalls */
@@ -687,8 +703,10 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 
 	/* fsnotify_alloc_group takes a ref.  Dropped in fanotify_release */
 	group = fsnotify_alloc_group(&fanotify_fsnotify_ops);
-	if (IS_ERR(group))
+	if (IS_ERR(group)) {
+		free_uid(user);
 		return PTR_ERR(group);
+	}
 
 	group->fanotify_data.user = user;
 	atomic_inc(&user->fanotify_listeners);
@@ -698,6 +716,7 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	mutex_init(&group->fanotify_data.access_mutex);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
+	atomic_set(&group->fanotify_data.bypass_perm, 0);
 #endif
 	switch (flags & FAN_ALL_CLASS_BITS) {
 	case FAN_CLASS_NOTIF:
@@ -764,8 +783,10 @@ SYSCALL_DEFINE(fanotify_mark)(int fanotify_fd, unsigned int flags,
 	if (flags & ~FAN_ALL_MARK_FLAGS)
 		return -EINVAL;
 	switch (flags & (FAN_MARK_ADD | FAN_MARK_REMOVE | FAN_MARK_FLUSH)) {
-	case FAN_MARK_ADD:
+	case FAN_MARK_ADD:		/* fallthrough */
 	case FAN_MARK_REMOVE:
+		if (!mask)
+			return -EINVAL;
 	case FAN_MARK_FLUSH:
 		break;
 	default:
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 444c305a468..4cd5d5d78f9 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -752,6 +752,7 @@ SYSCALL_DEFINE1(inotify_init1, int, flags)
 	if (ret >= 0)
 		return ret;
 
+	fsnotify_put_group(group);
 	atomic_dec(&user->inotify_devs);
 out_free_uid:
 	free_uid(user);
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index aae86fd10c4..36ab42c9bb9 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -250,7 +250,7 @@ struct queue_limits {
 
 	unsigned char		misaligned;
 	unsigned char		discard_misaligned;
-	unsigned char		no_cluster;
+	unsigned char		cluster;
 	signed char		discard_zeroes_data;
 };
 
@@ -380,7 +380,6 @@ struct request_queue
 #endif
 };
 
-#define QUEUE_FLAG_CLUSTER	0	/* cluster several segments into 1 */
 #define QUEUE_FLAG_QUEUED	1	/* uses generic tag queueing */
 #define QUEUE_FLAG_STOPPED	2	/* queue is stopped */
 #define	QUEUE_FLAG_SYNCFULL	3	/* read queue has been filled */
@@ -403,7 +402,6 @@ struct request_queue
 #define QUEUE_FLAG_SECDISCARD  19	/* supports SECDISCARD */
 
 #define QUEUE_FLAG_DEFAULT	((1 << QUEUE_FLAG_IO_STAT) |		\
-				 (1 << QUEUE_FLAG_CLUSTER) |		\
 				 (1 << QUEUE_FLAG_STACKABLE)	|	\
 				 (1 << QUEUE_FLAG_SAME_COMP)	|	\
 				 (1 << QUEUE_FLAG_ADD_RANDOM))
@@ -510,6 +508,11 @@ static inline void queue_flag_clear(unsigned int flag, struct request_queue *q)
 
 #define rq_data_dir(rq)		((rq)->cmd_flags & 1)
 
+static inline unsigned int blk_queue_cluster(struct request_queue *q)
+{
+	return q->limits.cluster;
+}
+
 /*
  * We regard a request as sync, if either a read or a sync write
  */
@@ -805,6 +808,7 @@ extern struct request_queue *blk_init_allocated_queue(struct request_queue *,
 extern void blk_cleanup_queue(struct request_queue *);
 extern void blk_queue_make_request(struct request_queue *, make_request_fn *);
 extern void blk_queue_bounce_limit(struct request_queue *, u64);
+extern void blk_limits_max_hw_sectors(struct queue_limits *, unsigned int);
 extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int);
 extern void blk_queue_max_segments(struct request_queue *, unsigned short);
 extern void blk_queue_max_segment_size(struct request_queue *, unsigned int);
diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h
index 266ab929123..499dfe982a0 100644
--- a/include/linux/bootmem.h
+++ b/include/linux/bootmem.h
@@ -105,6 +105,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat,
 
 #define alloc_bootmem(x) \
 	__alloc_bootmem(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
+#define alloc_bootmem_align(x, align) \
+	__alloc_bootmem(x, align, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_nopanic(x) \
 	__alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS))
 #define alloc_bootmem_pages(x) \
diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h
index 9e76d35670d..72c72bfccb8 100644
--- a/include/linux/ceph/libceph.h
+++ b/include/linux/ceph/libceph.h
@@ -227,8 +227,10 @@ extern int ceph_open_session(struct ceph_client *client);
 extern void ceph_release_page_vector(struct page **pages, int num_pages);
 
 extern struct page **ceph_get_direct_page_vector(const char __user *data,
-						 int num_pages);
-extern void ceph_put_page_vector(struct page **pages, int num_pages);
+						 int num_pages,
+						 bool write_page);
+extern void ceph_put_page_vector(struct page **pages, int num_pages,
+				 bool dirty);
 extern void ceph_release_page_vector(struct page **pages, int num_pages);
 extern struct page **ceph_alloc_page_vector(int num_pages, gfp_t flags);
 extern int ceph_copy_user_to_page_vector(struct page **pages,
diff --git a/include/linux/cnt32_to_63.h b/include/linux/cnt32_to_63.h
index 7605fdd1eb6..e3d8bf26e5e 100644
--- a/include/linux/cnt32_to_63.h
+++ b/include/linux/cnt32_to_63.h
@@ -61,13 +61,31 @@ union cnt32_to_63 {
  *
  * 2) this code must not be preempted for a duration longer than the
  *    32-bit counter half period minus the longest period between two
- *    calls to this code.
+ *    calls to this code;
  *
  * Those requirements ensure proper update to the state bit in memory.
  * This is usually not a problem in practice, but if it is then a kernel
  * timer should be scheduled to manage for this code to be executed often
  * enough.
  *
+ * And finally:
+ *
+ * 3) the cnt_lo argument must be seen as a globally incrementing value,
+ *    meaning that it should be a direct reference to the counter data which
+ *    can be evaluated according to a specific ordering within the macro,
+ *    and not the result of a previous evaluation stored in a variable.
+ *
+ * For example, this is wrong:
+ *
+ *	u32 partial = get_hw_count();
+ *	u64 full = cnt32_to_63(partial);
+ *	return full;
+ *
+ * This is fine:
+ *
+ *	u64 full = cnt32_to_63(get_hw_count());
+ *	return full;
+ *
  * Note that the top bit (bit 63) in the returned value should be considered
  * as garbage.  It is not cleared here because callers are likely to use a
  * multiplier on the returned value which can get rid of the top bit
diff --git a/include/linux/fanotify.h b/include/linux/fanotify.h
index 0f0121467fc..6c6133f76e1 100644
--- a/include/linux/fanotify.h
+++ b/include/linux/fanotify.h
@@ -83,11 +83,13 @@
 				 FAN_ALL_PERM_EVENTS |\
 				 FAN_Q_OVERFLOW)
 
-#define FANOTIFY_METADATA_VERSION	2
+#define FANOTIFY_METADATA_VERSION	3
 
 struct fanotify_event_metadata {
 	__u32 event_len;
-	__u32 vers;
+	__u8 vers;
+	__u8 reserved;
+	__u16 metadata_len;
 	__aligned_u64 mask;
 	__s32 fd;
 	__s32 pid;
@@ -96,11 +98,13 @@ struct fanotify_event_metadata {
 struct fanotify_response {
 	__s32 fd;
 	__u32 response;
-} __attribute__ ((packed));
+};
 
 /* Legit userspace responses to a _PERM event */
 #define FAN_ALLOW	0x01
 #define FAN_DENY	0x02
+/* No fd set in event */
+#define FAN_NOFD	-1
 
 /* Helper functions to deal with fanotify_event_metadata buffers */
 #define FAN_EVENT_METADATA_LEN (sizeof(struct fanotify_event_metadata))
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 5c185fa2708..b10bcdeaef7 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -235,9 +235,6 @@ static inline void fsnotify_open(struct file *file)
 	if (S_ISDIR(inode->i_mode))
 		mask |= FS_ISDIR;
 
-	/* FMODE_NONOTIFY must never be set from user */
-	file->f_mode &= ~FMODE_NONOTIFY;
-
 	fsnotify_parent(path, NULL, mask);
 	fsnotify(inode, mask, path, FSNOTIFY_EVENT_PATH, NULL, 0);
 }
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 0a68f924f06..7380763595d 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -166,7 +166,7 @@ struct fsnotify_group {
 			struct mutex access_mutex;
 			struct list_head access_list;
 			wait_queue_head_t access_waitq;
-			bool bypass_perm; /* protected by access_mutex */
+			atomic_t bypass_perm;
 #endif /* CONFIG_FANOTIFY_ACCESS_PERMISSIONS */
 			int f_flags;
 			unsigned int max_marks;
diff --git a/include/linux/input.h b/include/linux/input.h
index a8af21d42bc..9777668883b 100644
--- a/include/linux/input.h
+++ b/include/linux/input.h
@@ -104,8 +104,10 @@ struct input_keymap_entry {
 #define EVIOCGREP		_IOR('E', 0x03, unsigned int[2])	/* get repeat settings */
 #define EVIOCSREP		_IOW('E', 0x03, unsigned int[2])	/* set repeat settings */
 
-#define EVIOCGKEYCODE		_IOR('E', 0x04, struct input_keymap_entry)	/* get keycode */
-#define EVIOCSKEYCODE		_IOW('E', 0x04, struct input_keymap_entry)	/* set keycode */
+#define EVIOCGKEYCODE		_IOR('E', 0x04, unsigned int[2])        /* get keycode */
+#define EVIOCGKEYCODE_V2	_IOR('E', 0x04, struct input_keymap_entry)
+#define EVIOCSKEYCODE		_IOW('E', 0x04, unsigned int[2])        /* set keycode */
+#define EVIOCSKEYCODE_V2	_IOW('E', 0x04, struct input_keymap_entry)
 
 #define EVIOCGNAME(len)		_IOC(_IOC_READ, 'E', 0x06, len)		/* get device name */
 #define EVIOCGPHYS(len)		_IOC(_IOC_READ, 'E', 0x07, len)		/* get physical location */
diff --git a/include/linux/ioport.h b/include/linux/ioport.h
index d377ea815d4..e9bb22cba76 100644
--- a/include/linux/ioport.h
+++ b/include/linux/ioport.h
@@ -112,7 +112,6 @@ struct resource_list {
 /* PC/ISA/whatever - the normal PC address spaces: IO and memory */
 extern struct resource ioport_resource;
 extern struct resource iomem_resource;
-extern int resource_alloc_from_bottom;
 
 extern struct resource *request_resource_conflict(struct resource *root, struct resource *new);
 extern int request_resource(struct resource *root, struct resource *new);
@@ -124,6 +123,7 @@ extern void reserve_region_with_split(struct resource *root,
 extern struct resource *insert_resource_conflict(struct resource *parent, struct resource *new);
 extern int insert_resource(struct resource *parent, struct resource *new);
 extern void insert_resource_expand_to_fit(struct resource *root, struct resource *new);
+extern void arch_remove_reservations(struct resource *avail);
 extern int allocate_resource(struct resource *root, struct resource *new,
 			     resource_size_t size, resource_size_t min,
 			     resource_size_t max, resource_size_t align,
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index de2c41758e2..4f1279e105e 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -887,6 +887,7 @@ struct perf_cpu_context {
 	int				exclusive;
 	struct list_head		rotation_list;
 	int				jiffies_interval;
+	struct pmu			*active_pmu;
 };
 
 struct perf_output_handle {
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 3ec2358f869..d19f1cca7f7 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -77,7 +77,8 @@ static inline void device_set_run_wake(struct device *dev, bool enable)
 
 static inline bool pm_runtime_suspended(struct device *dev)
 {
-	return dev->power.runtime_status == RPM_SUSPENDED;
+	return dev->power.runtime_status == RPM_SUSPENDED
+		&& !dev->power.disable_depth;
 }
 
 static inline void pm_runtime_mark_last_busy(struct device *dev)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2c79e921a68..223874538b3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -143,7 +143,7 @@ extern unsigned long nr_iowait_cpu(int cpu);
 extern unsigned long this_cpu_load(void);
 
 
-extern void calc_global_load(void);
+extern void calc_global_load(unsigned long ticks);
 
 extern unsigned long get_parent_ip(unsigned long addr);
 
diff --git a/include/linux/ssb/ssb_driver_gige.h b/include/linux/ssb/ssb_driver_gige.h
index 942e3873690..eba52a10053 100644
--- a/include/linux/ssb/ssb_driver_gige.h
+++ b/include/linux/ssb/ssb_driver_gige.h
@@ -96,16 +96,21 @@ static inline bool ssb_gige_must_flush_posted_writes(struct pci_dev *pdev)
 	return 0;
 }
 
-extern char * nvram_get(const char *name);
+#ifdef CONFIG_BCM47XX
+#include <asm/mach-bcm47xx/nvram.h>
 /* Get the device MAC address */
 static inline void ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr)
 {
-#ifdef CONFIG_BCM47XX
-	char *res = nvram_get("et0macaddr");
-	if (res)
-		memcpy(macaddr, res, 6);
-#endif
+	char buf[20];
+	if (nvram_getenv("et0macaddr", buf, sizeof(buf)) < 0)
+		return;
+	nvram_parse_macaddr(buf, macaddr);
 }
+#else
+static inline void ssb_gige_get_macaddr(struct pci_dev *pdev, u8 *macaddr)
+{
+}
+#endif
 
 extern int ssb_gige_pcibios_plat_dev_init(struct ssb_device *sdev,
 					  struct pci_dev *pdev);
diff --git a/include/media/saa7146.h b/include/media/saa7146.h
index 7a9f76ecbbb..ac7ce00f39c 100644
--- a/include/media/saa7146.h
+++ b/include/media/saa7146.h
@@ -161,7 +161,7 @@ extern struct list_head saa7146_devices;
 extern struct mutex saa7146_devices_lock;
 int saa7146_register_extension(struct saa7146_extension*);
 int saa7146_unregister_extension(struct saa7146_extension*);
-struct saa7146_format* format_by_fourcc(struct saa7146_dev *dev, int fourcc);
+struct saa7146_format* saa7146_format_by_fourcc(struct saa7146_dev *dev, int fourcc);
 int saa7146_pgtable_alloc(struct pci_dev *pci, struct saa7146_pgtable *pt);
 void saa7146_pgtable_free(struct pci_dev *pci, struct saa7146_pgtable *pt);
 int saa7146_pgtable_build_single(struct pci_dev *pci, struct saa7146_pgtable *pt, struct scatterlist *list, int length );
diff --git a/include/media/v4l2-device.h b/include/media/v4l2-device.h
index 6648036b728..b16f307d471 100644
--- a/include/media/v4l2-device.h
+++ b/include/media/v4l2-device.h
@@ -51,6 +51,8 @@ struct v4l2_device {
 			unsigned int notification, void *arg);
 	/* The control handler. May be NULL. */
 	struct v4l2_ctrl_handler *ctrl_handler;
+	/* BKL replacement mutex. Temporary solution only. */
+	struct mutex ioctl_lock;
 };
 
 /* Initialize v4l2_dev and make dev->driver_data point to v4l2_dev.
diff --git a/kernel/fork.c b/kernel/fork.c
index 3b159c5991b..5447dc7defa 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -273,6 +273,7 @@ static struct task_struct *dup_task_struct(struct task_struct *orig)
 
 	setup_thread_stack(tsk, orig);
 	clear_user_return_notifier(tsk);
+	clear_tsk_need_resched(tsk);
 	stackend = end_of_stack(tsk);
 	*stackend = STACK_END_MAGIC;	/* for overflow detection */
 
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index eac7e336433..2870feee81d 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -3824,6 +3824,8 @@ static void perf_event_task_event(struct perf_task_event *task_event)
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->active_pmu != pmu)
+			goto next;
 		perf_event_task_ctx(&cpuctx->ctx, task_event);
 
 		ctx = task_event->task_ctx;
@@ -3959,6 +3961,8 @@ static void perf_event_comm_event(struct perf_comm_event *comm_event)
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->active_pmu != pmu)
+			goto next;
 		perf_event_comm_ctx(&cpuctx->ctx, comm_event);
 
 		ctxn = pmu->task_ctx_nr;
@@ -4144,6 +4148,8 @@ got_name:
 	rcu_read_lock();
 	list_for_each_entry_rcu(pmu, &pmus, entry) {
 		cpuctx = get_cpu_ptr(pmu->pmu_cpu_context);
+		if (cpuctx->active_pmu != pmu)
+			goto next;
 		perf_event_mmap_ctx(&cpuctx->ctx, mmap_event,
 					vma->vm_flags & VM_EXEC);
 
@@ -4713,7 +4719,7 @@ static int perf_swevent_init(struct perf_event *event)
 		break;
 	}
 
-	if (event_id > PERF_COUNT_SW_MAX)
+	if (event_id >= PERF_COUNT_SW_MAX)
 		return -ENOENT;
 
 	if (!event->parent) {
@@ -5145,20 +5151,36 @@ static void *find_pmu_context(int ctxn)
 	return NULL;
 }
 
-static void free_pmu_context(void * __percpu cpu_context)
+static void update_pmu_context(struct pmu *pmu, struct pmu *old_pmu)
 {
-	struct pmu *pmu;
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct perf_cpu_context *cpuctx;
+
+		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+
+		if (cpuctx->active_pmu == old_pmu)
+			cpuctx->active_pmu = pmu;
+	}
+}
+
+static void free_pmu_context(struct pmu *pmu)
+{
+	struct pmu *i;
 
 	mutex_lock(&pmus_lock);
 	/*
 	 * Like a real lame refcount.
 	 */
-	list_for_each_entry(pmu, &pmus, entry) {
-		if (pmu->pmu_cpu_context == cpu_context)
+	list_for_each_entry(i, &pmus, entry) {
+		if (i->pmu_cpu_context == pmu->pmu_cpu_context) {
+			update_pmu_context(i, pmu);
 			goto out;
+		}
 	}
 
-	free_percpu(cpu_context);
+	free_percpu(pmu->pmu_cpu_context);
 out:
 	mutex_unlock(&pmus_lock);
 }
@@ -5190,6 +5212,7 @@ int perf_pmu_register(struct pmu *pmu)
 		cpuctx->ctx.pmu = pmu;
 		cpuctx->jiffies_interval = 1;
 		INIT_LIST_HEAD(&cpuctx->rotation_list);
+		cpuctx->active_pmu = pmu;
 	}
 
 got_cpu_context:
@@ -5241,7 +5264,7 @@ void perf_pmu_unregister(struct pmu *pmu)
 	synchronize_rcu();
 
 	free_percpu(pmu->pmu_disable_count);
-	free_pmu_context(pmu->pmu_cpu_context);
+	free_pmu_context(pmu);
 }
 
 struct pmu *perf_init_event(struct perf_event *event)
diff --git a/kernel/power/swap.c b/kernel/power/swap.c
index baf667bb279..8c7e4832b9b 100644
--- a/kernel/power/swap.c
+++ b/kernel/power/swap.c
@@ -30,7 +30,7 @@
 
 #include "power.h"
 
-#define HIBERNATE_SIG	"LINHIB0001"
+#define HIBERNATE_SIG	"S1SUSPEND"
 
 /*
  *	The swap map is a data structure used for keeping track of each page
diff --git a/kernel/power/user.c b/kernel/power/user.c
index 1b2ea31e6bd..c36c3b9e8a8 100644
--- a/kernel/power/user.c
+++ b/kernel/power/user.c
@@ -137,7 +137,7 @@ static int snapshot_release(struct inode *inode, struct file *filp)
 	free_all_swap_pages(data->swap);
 	if (data->frozen)
 		thaw_processes();
-	pm_notifier_call_chain(data->mode == O_WRONLY ?
+	pm_notifier_call_chain(data->mode == O_RDONLY ?
 			PM_POST_HIBERNATION : PM_POST_RESTORE);
 	atomic_inc(&snapshot_device_available);
 
diff --git a/kernel/resource.c b/kernel/resource.c
index 9fad33efd0d..798e2fae2a0 100644
--- a/kernel/resource.c
+++ b/kernel/resource.c
@@ -40,23 +40,6 @@ EXPORT_SYMBOL(iomem_resource);
 
 static DEFINE_RWLOCK(resource_lock);
 
-/*
- * By default, we allocate free space bottom-up.  The architecture can request
- * top-down by clearing this flag.  The user can override the architecture's
- * choice with the "resource_alloc_from_bottom" kernel boot option, but that
- * should only be a debugging tool.
- */
-int resource_alloc_from_bottom = 1;
-
-static __init int setup_alloc_from_bottom(char *s)
-{
-	printk(KERN_INFO
-	       "resource: allocating from bottom-up; please report a bug\n");
-	resource_alloc_from_bottom = 1;
-	return 0;
-}
-early_param("resource_alloc_from_bottom", setup_alloc_from_bottom);
-
 static void *r_next(struct seq_file *m, void *v, loff_t *pos)
 {
 	struct resource *p = v;
@@ -374,6 +357,10 @@ int __weak page_is_ram(unsigned long pfn)
 	return walk_system_ram_range(pfn, 1, NULL, __is_ram) == 1;
 }
 
+void __weak arch_remove_reservations(struct resource *avail)
+{
+}
+
 static resource_size_t simple_align_resource(void *data,
 					     const struct resource *avail,
 					     resource_size_t size,
@@ -397,74 +384,7 @@ static bool resource_contains(struct resource *res1, struct resource *res2)
 }
 
 /*
- * Find the resource before "child" in the sibling list of "root" children.
- */
-static struct resource *find_sibling_prev(struct resource *root, struct resource *child)
-{
-	struct resource *this;
-
-	for (this = root->child; this; this = this->sibling)
-		if (this->sibling == child)
-			return this;
-
-	return NULL;
-}
-
-/*
  * Find empty slot in the resource tree given range and alignment.
- * This version allocates from the end of the root resource first.
- */
-static int find_resource_from_top(struct resource *root, struct resource *new,
-				  resource_size_t size, resource_size_t min,
-				  resource_size_t max, resource_size_t align,
-				  resource_size_t (*alignf)(void *,
-						   const struct resource *,
-						   resource_size_t,
-						   resource_size_t),
-				  void *alignf_data)
-{
-	struct resource *this;
-	struct resource tmp, avail, alloc;
-
-	tmp.start = root->end;
-	tmp.end = root->end;
-
-	this = find_sibling_prev(root, NULL);
-	for (;;) {
-		if (this) {
-			if (this->end < root->end)
-				tmp.start = this->end + 1;
-		} else
-			tmp.start = root->start;
-
-		resource_clip(&tmp, min, max);
-
-		/* Check for overflow after ALIGN() */
-		avail = *new;
-		avail.start = ALIGN(tmp.start, align);
-		avail.end = tmp.end;
-		if (avail.start >= tmp.start) {
-			alloc.start = alignf(alignf_data, &avail, size, align);
-			alloc.end = alloc.start + size - 1;
-			if (resource_contains(&avail, &alloc)) {
-				new->start = alloc.start;
-				new->end = alloc.end;
-				return 0;
-			}
-		}
-
-		if (!this || this->start == root->start)
-			break;
-
-		tmp.end = this->start - 1;
-		this = find_sibling_prev(root, this);
-	}
-	return -EBUSY;
-}
-
-/*
- * Find empty slot in the resource tree given range and alignment.
- * This version allocates from the beginning of the root resource first.
  */
 static int find_resource(struct resource *root, struct resource *new,
 			 resource_size_t size, resource_size_t min,
@@ -478,23 +398,24 @@ static int find_resource(struct resource *root, struct resource *new,
 	struct resource *this = root->child;
 	struct resource tmp = *new, avail, alloc;
 
+	tmp.flags = new->flags;
 	tmp.start = root->start;
 	/*
-	 * Skip past an allocated resource that starts at 0, since the
-	 * assignment of this->start - 1 to tmp->end below would cause an
-	 * underflow.
+	 * Skip past an allocated resource that starts at 0, since the assignment
+	 * of this->start - 1 to tmp->end below would cause an underflow.
 	 */
 	if (this && this->start == 0) {
 		tmp.start = this->end + 1;
 		this = this->sibling;
 	}
-	for (;;) {
+	for(;;) {
 		if (this)
 			tmp.end = this->start - 1;
 		else
 			tmp.end = root->end;
 
 		resource_clip(&tmp, min, max);
+		arch_remove_reservations(&tmp);
 
 		/* Check for overflow after ALIGN() */
 		avail = *new;
@@ -509,10 +430,8 @@ static int find_resource(struct resource *root, struct resource *new,
 				return 0;
 			}
 		}
-
 		if (!this)
 			break;
-
 		tmp.start = this->end + 1;
 		this = this->sibling;
 	}
@@ -545,10 +464,7 @@ int allocate_resource(struct resource *root, struct resource *new,
 		alignf = simple_align_resource;
 
 	write_lock(&resource_lock);
-	if (resource_alloc_from_bottom)
-		err = find_resource(root, new, size, min, max, align, alignf, alignf_data);
-	else
-		err = find_resource_from_top(root, new, size, min, max, align, alignf, alignf_data);
+	err = find_resource(root, new, size, min, max, align, alignf, alignf_data);
 	if (err >= 0 && __request_resource(root, new))
 		err = -EBUSY;
 	write_unlock(&resource_lock);
diff --git a/kernel/sched.c b/kernel/sched.c
index dc91a4d09ac..297d1a0eedb 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -636,22 +636,18 @@ static inline struct task_group *task_group(struct task_struct *p)
 
 #endif /* CONFIG_CGROUP_SCHED */
 
-static u64 irq_time_cpu(int cpu);
-static void sched_irq_time_avg_update(struct rq *rq, u64 irq_time);
+static void update_rq_clock_task(struct rq *rq, s64 delta);
 
-inline void update_rq_clock(struct rq *rq)
+static void update_rq_clock(struct rq *rq)
 {
-	if (!rq->skip_clock_update) {
-		int cpu = cpu_of(rq);
-		u64 irq_time;
+	s64 delta;
 
-		rq->clock = sched_clock_cpu(cpu);
-		irq_time = irq_time_cpu(cpu);
-		if (rq->clock - irq_time > rq->clock_task)
-			rq->clock_task = rq->clock - irq_time;
+	if (rq->skip_clock_update)
+		return;
 
-		sched_irq_time_avg_update(rq, irq_time);
-	}
+	delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
+	rq->clock += delta;
+	update_rq_clock_task(rq, delta);
 }
 
 /*
@@ -1924,10 +1920,9 @@ static void deactivate_task(struct rq *rq, struct task_struct *p, int flags)
  * They are read and saved off onto struct rq in update_rq_clock().
  * This may result in other CPU reading this CPU's irq time and can
  * race with irq/account_system_vtime on this CPU. We would either get old
- * or new value (or semi updated value on 32 bit) with a side effect of
- * accounting a slice of irq time to wrong task when irq is in progress
- * while we read rq->clock. That is a worthy compromise in place of having
- * locks on each irq in account_system_time.
+ * or new value with a side effect of accounting a slice of irq time to wrong
+ * task when irq is in progress while we read rq->clock. That is a worthy
+ * compromise in place of having locks on each irq in account_system_time.
  */
 static DEFINE_PER_CPU(u64, cpu_hardirq_time);
 static DEFINE_PER_CPU(u64, cpu_softirq_time);
@@ -1945,19 +1940,58 @@ void disable_sched_clock_irqtime(void)
 	sched_clock_irqtime = 0;
 }
 
-static u64 irq_time_cpu(int cpu)
+#ifndef CONFIG_64BIT
+static DEFINE_PER_CPU(seqcount_t, irq_time_seq);
+
+static inline void irq_time_write_begin(void)
 {
-	if (!sched_clock_irqtime)
-		return 0;
+	__this_cpu_inc(irq_time_seq.sequence);
+	smp_wmb();
+}
+
+static inline void irq_time_write_end(void)
+{
+	smp_wmb();
+	__this_cpu_inc(irq_time_seq.sequence);
+}
+
+static inline u64 irq_time_read(int cpu)
+{
+	u64 irq_time;
+	unsigned seq;
 
+	do {
+		seq = read_seqcount_begin(&per_cpu(irq_time_seq, cpu));
+		irq_time = per_cpu(cpu_softirq_time, cpu) +
+			   per_cpu(cpu_hardirq_time, cpu);
+	} while (read_seqcount_retry(&per_cpu(irq_time_seq, cpu), seq));
+
+	return irq_time;
+}
+#else /* CONFIG_64BIT */
+static inline void irq_time_write_begin(void)
+{
+}
+
+static inline void irq_time_write_end(void)
+{
+}
+
+static inline u64 irq_time_read(int cpu)
+{
 	return per_cpu(cpu_softirq_time, cpu) + per_cpu(cpu_hardirq_time, cpu);
 }
+#endif /* CONFIG_64BIT */
 
+/*
+ * Called before incrementing preempt_count on {soft,}irq_enter
+ * and before decrementing preempt_count on {soft,}irq_exit.
+ */
 void account_system_vtime(struct task_struct *curr)
 {
 	unsigned long flags;
+	s64 delta;
 	int cpu;
-	u64 now, delta;
 
 	if (!sched_clock_irqtime)
 		return;
@@ -1965,9 +1999,10 @@ void account_system_vtime(struct task_struct *curr)
 	local_irq_save(flags);
 
 	cpu = smp_processor_id();
-	now = sched_clock_cpu(cpu);
-	delta = now - per_cpu(irq_start_time, cpu);
-	per_cpu(irq_start_time, cpu) = now;
+	delta = sched_clock_cpu(cpu) - __this_cpu_read(irq_start_time);
+	__this_cpu_add(irq_start_time, delta);
+
+	irq_time_write_begin();
 	/*
 	 * We do not account for softirq time from ksoftirqd here.
 	 * We want to continue accounting softirq time to ksoftirqd thread
@@ -1975,33 +2010,55 @@ void account_system_vtime(struct task_struct *curr)
 	 * that do not consume any time, but still wants to run.
 	 */
 	if (hardirq_count())
-		per_cpu(cpu_hardirq_time, cpu) += delta;
+		__this_cpu_add(cpu_hardirq_time, delta);
 	else if (in_serving_softirq() && !(curr->flags & PF_KSOFTIRQD))
-		per_cpu(cpu_softirq_time, cpu) += delta;
+		__this_cpu_add(cpu_softirq_time, delta);
 
+	irq_time_write_end();
 	local_irq_restore(flags);
 }
 EXPORT_SYMBOL_GPL(account_system_vtime);
 
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
-	if (sched_clock_irqtime && sched_feat(NONIRQ_POWER)) {
-		u64 delta_irq = curr_irq_time - rq->prev_irq_time;
-		rq->prev_irq_time = curr_irq_time;
-		sched_rt_avg_update(rq, delta_irq);
-	}
+	s64 irq_delta;
+
+	irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
+
+	/*
+	 * Since irq_time is only updated on {soft,}irq_exit, we might run into
+	 * this case when a previous update_rq_clock() happened inside a
+	 * {soft,}irq region.
+	 *
+	 * When this happens, we stop ->clock_task and only update the
+	 * prev_irq_time stamp to account for the part that fit, so that a next
+	 * update will consume the rest. This ensures ->clock_task is
+	 * monotonic.
+	 *
+	 * It does however cause some slight miss-attribution of {soft,}irq
+	 * time, a more accurate solution would be to update the irq_time using
+	 * the current rq->clock timestamp, except that would require using
+	 * atomic ops.
+	 */
+	if (irq_delta > delta)
+		irq_delta = delta;
+
+	rq->prev_irq_time += irq_delta;
+	delta -= irq_delta;
+	rq->clock_task += delta;
+
+	if (irq_delta && sched_feat(NONIRQ_POWER))
+		sched_rt_avg_update(rq, irq_delta);
 }
 
-#else
+#else /* CONFIG_IRQ_TIME_ACCOUNTING */
 
-static u64 irq_time_cpu(int cpu)
+static void update_rq_clock_task(struct rq *rq, s64 delta)
 {
-	return 0;
+	rq->clock_task += delta;
 }
 
-static void sched_irq_time_avg_update(struct rq *rq, u64 curr_irq_time) { }
-
-#endif
+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
 #include "sched_idletask.c"
 #include "sched_fair.c"
@@ -2129,7 +2186,7 @@ static void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags)
 	 * A queue event has occurred, and we're going to schedule.  In
 	 * this case, we can save a useless back to back clock update.
 	 */
-	if (test_tsk_need_resched(rq->curr))
+	if (rq->curr->se.on_rq && test_tsk_need_resched(rq->curr))
 		rq->skip_clock_update = 1;
 }
 
@@ -3119,6 +3176,15 @@ static long calc_load_fold_active(struct rq *this_rq)
 	return delta;
 }
 
+static unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+	load *= exp;
+	load += active * (FIXED_1 - exp);
+	load += 1UL << (FSHIFT - 1);
+	return load >> FSHIFT;
+}
+
 #ifdef CONFIG_NO_HZ
 /*
  * For NO_HZ we delay the active fold to the next LOAD_FREQ update.
@@ -3148,6 +3214,128 @@ static long calc_load_fold_idle(void)
 
 	return delta;
 }
+
+/**
+ * fixed_power_int - compute: x^n, in O(log n) time
+ *
+ * @x:         base of the power
+ * @frac_bits: fractional bits of @x
+ * @n:         power to raise @x to.
+ *
+ * By exploiting the relation between the definition of the natural power
+ * function: x^n := x*x*...*x (x multiplied by itself for n times), and
+ * the binary encoding of numbers used by computers: n := \Sum n_i * 2^i,
+ * (where: n_i \elem {0, 1}, the binary vector representing n),
+ * we find: x^n := x^(\Sum n_i * 2^i) := \Prod x^(n_i * 2^i), which is
+ * of course trivially computable in O(log_2 n), the length of our binary
+ * vector.
+ */
+static unsigned long
+fixed_power_int(unsigned long x, unsigned int frac_bits, unsigned int n)
+{
+	unsigned long result = 1UL << frac_bits;
+
+	if (n) for (;;) {
+		if (n & 1) {
+			result *= x;
+			result += 1UL << (frac_bits - 1);
+			result >>= frac_bits;
+		}
+		n >>= 1;
+		if (!n)
+			break;
+		x *= x;
+		x += 1UL << (frac_bits - 1);
+		x >>= frac_bits;
+	}
+
+	return result;
+}
+
+/*
+ * a1 = a0 * e + a * (1 - e)
+ *
+ * a2 = a1 * e + a * (1 - e)
+ *    = (a0 * e + a * (1 - e)) * e + a * (1 - e)
+ *    = a0 * e^2 + a * (1 - e) * (1 + e)
+ *
+ * a3 = a2 * e + a * (1 - e)
+ *    = (a0 * e^2 + a * (1 - e) * (1 + e)) * e + a * (1 - e)
+ *    = a0 * e^3 + a * (1 - e) * (1 + e + e^2)
+ *
+ *  ...
+ *
+ * an = a0 * e^n + a * (1 - e) * (1 + e + ... + e^n-1) [1]
+ *    = a0 * e^n + a * (1 - e) * (1 - e^n)/(1 - e)
+ *    = a0 * e^n + a * (1 - e^n)
+ *
+ * [1] application of the geometric series:
+ *
+ *              n         1 - x^(n+1)
+ *     S_n := \Sum x^i = -------------
+ *             i=0          1 - x
+ */
+static unsigned long
+calc_load_n(unsigned long load, unsigned long exp,
+	    unsigned long active, unsigned int n)
+{
+
+	return calc_load(load, fixed_power_int(exp, FSHIFT, n), active);
+}
+
+/*
+ * NO_HZ can leave us missing all per-cpu ticks calling
+ * calc_load_account_active(), but since an idle CPU folds its delta into
+ * calc_load_tasks_idle per calc_load_account_idle(), all we need to do is fold
+ * in the pending idle delta if our idle period crossed a load cycle boundary.
+ *
+ * Once we've updated the global active value, we need to apply the exponential
+ * weights adjusted to the number of cycles missed.
+ */
+static void calc_global_nohz(unsigned long ticks)
+{
+	long delta, active, n;
+
+	if (time_before(jiffies, calc_load_update))
+		return;
+
+	/*
+	 * If we crossed a calc_load_update boundary, make sure to fold
+	 * any pending idle changes, the respective CPUs might have
+	 * missed the tick driven calc_load_account_active() update
+	 * due to NO_HZ.
+	 */
+	delta = calc_load_fold_idle();
+	if (delta)
+		atomic_long_add(delta, &calc_load_tasks);
+
+	/*
+	 * If we were idle for multiple load cycles, apply them.
+	 */
+	if (ticks >= LOAD_FREQ) {
+		n = ticks / LOAD_FREQ;
+
+		active = atomic_long_read(&calc_load_tasks);
+		active = active > 0 ? active * FIXED_1 : 0;
+
+		avenrun[0] = calc_load_n(avenrun[0], EXP_1, active, n);
+		avenrun[1] = calc_load_n(avenrun[1], EXP_5, active, n);
+		avenrun[2] = calc_load_n(avenrun[2], EXP_15, active, n);
+
+		calc_load_update += n * LOAD_FREQ;
+	}
+
+	/*
+	 * Its possible the remainder of the above division also crosses
+	 * a LOAD_FREQ period, the regular check in calc_global_load()
+	 * which comes after this will take care of that.
+	 *
+	 * Consider us being 11 ticks before a cycle completion, and us
+	 * sleeping for 4*LOAD_FREQ + 22 ticks, then the above code will
+	 * age us 4 cycles, and the test in calc_global_load() will
+	 * pick up the final one.
+	 */
+}
 #else
 static void calc_load_account_idle(struct rq *this_rq)
 {
@@ -3157,6 +3345,10 @@ static inline long calc_load_fold_idle(void)
 {
 	return 0;
 }
+
+static void calc_global_nohz(unsigned long ticks)
+{
+}
 #endif
 
 /**
@@ -3174,24 +3366,17 @@ void get_avenrun(unsigned long *loads, unsigned long offset, int shift)
 	loads[2] = (avenrun[2] + offset) << shift;
 }
 
-static unsigned long
-calc_load(unsigned long load, unsigned long exp, unsigned long active)
-{
-	load *= exp;
-	load += active * (FIXED_1 - exp);
-	return load >> FSHIFT;
-}
-
 /*
  * calc_load - update the avenrun load estimates 10 ticks after the
  * CPUs have updated calc_load_tasks.
  */
-void calc_global_load(void)
+void calc_global_load(unsigned long ticks)
 {
-	unsigned long upd = calc_load_update + 10;
 	long active;
 
-	if (time_before(jiffies, upd))
+	calc_global_nohz(ticks);
+
+	if (time_before(jiffies, calc_load_update + 10))
 		return;
 
 	active = atomic_long_read(&calc_load_tasks);
@@ -3845,7 +4030,6 @@ static void put_prev_task(struct rq *rq, struct task_struct *prev)
 {
 	if (prev->se.on_rq)
 		update_rq_clock(rq);
-	rq->skip_clock_update = 0;
 	prev->sched_class->put_prev_task(rq, prev);
 }
 
@@ -3903,7 +4087,6 @@ need_resched_nonpreemptible:
 		hrtick_clear(rq);
 
 	raw_spin_lock_irq(&rq->lock);
-	clear_tsk_need_resched(prev);
 
 	switch_count = &prev->nivcsw;
 	if (prev->state && !(preempt_count() & PREEMPT_ACTIVE)) {
@@ -3935,6 +4118,8 @@ need_resched_nonpreemptible:
 
 	put_prev_task(rq, prev);
 	next = pick_next_task(rq);
+	clear_tsk_need_resched(prev);
+	rq->skip_clock_update = 0;
 
 	if (likely(prev != next)) {
 		sched_info_switch(prev, next);
diff --git a/kernel/timer.c b/kernel/timer.c
index 68a9ae7679b..353b9227c2e 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -1252,6 +1252,12 @@ unsigned long get_next_timer_interrupt(unsigned long now)
 	struct tvec_base *base = __get_cpu_var(tvec_bases);
 	unsigned long expires;
 
+	/*
+	 * Pretend that there is no timer pending if the cpu is offline.
+	 * Possible pending timers will be migrated later to an active cpu.
+	 */
+	if (cpu_is_offline(smp_processor_id()))
+		return now + NEXT_TIMER_MAX_DELTA;
 	spin_lock(&base->lock);
 	if (time_before_eq(base->next_timer, base->timer_jiffies))
 		base->next_timer = __next_timer_interrupt(base);
@@ -1319,7 +1325,7 @@ void do_timer(unsigned long ticks)
 {
 	jiffies_64 += ticks;
 	update_wall_time();
-	calc_global_load();
+	calc_global_load(ticks);
 }
 
 #ifdef __ARCH_WANT_SYS_ALARM
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c380612273b..f8cf959bad4 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2338,11 +2338,19 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
 	return count;
 }
 
+static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
+{
+	if (file->f_mode & FMODE_READ)
+		return seq_lseek(file, offset, origin);
+	else
+		return 0;
+}
+
 static const struct file_operations tracing_fops = {
 	.open		= tracing_open,
 	.read		= seq_read,
 	.write		= tracing_write_stub,
-	.llseek		= seq_lseek,
+	.llseek		= tracing_seek,
 	.release	= tracing_release,
 };
 
diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c
index 1c7a2ec4f3c..b6ff4a1519a 100644
--- a/net/ceph/messenger.c
+++ b/net/ceph/messenger.c
@@ -97,11 +97,9 @@ struct workqueue_struct *ceph_msgr_wq;
 int ceph_msgr_init(void)
 {
 	ceph_msgr_wq = create_workqueue("ceph-msgr");
-	if (IS_ERR(ceph_msgr_wq)) {
-		int ret = PTR_ERR(ceph_msgr_wq);
-		pr_err("msgr_init failed to create workqueue: %d\n", ret);
-		ceph_msgr_wq = NULL;
-		return ret;
+	if (!ceph_msgr_wq) {
+		pr_err("msgr_init failed to create workqueue\n");
+		return -ENOMEM;
 	}
 	return 0;
 }
diff --git a/net/ceph/pagevec.c b/net/ceph/pagevec.c
index ac34feeb2b3..1a040e64c69 100644
--- a/net/ceph/pagevec.c
+++ b/net/ceph/pagevec.c
@@ -13,7 +13,7 @@
  * build a vector of user pages
  */
 struct page **ceph_get_direct_page_vector(const char __user *data,
-					  int num_pages)
+					  int num_pages, bool write_page)
 {
 	struct page **pages;
 	int rc;
@@ -24,24 +24,27 @@ struct page **ceph_get_direct_page_vector(const char __user *data,
 
 	down_read(&current->mm->mmap_sem);
 	rc = get_user_pages(current, current->mm, (unsigned long)data,
-			    num_pages, 0, 0, pages, NULL);
+			    num_pages, write_page, 0, pages, NULL);
 	up_read(&current->mm->mmap_sem);
-	if (rc < 0)
+	if (rc < num_pages)
 		goto fail;
 	return pages;
 
 fail:
-	kfree(pages);
+	ceph_put_page_vector(pages, rc > 0 ? rc : 0, false);
 	return ERR_PTR(rc);
 }
 EXPORT_SYMBOL(ceph_get_direct_page_vector);
 
-void ceph_put_page_vector(struct page **pages, int num_pages)
+void ceph_put_page_vector(struct page **pages, int num_pages, bool dirty)
 {
 	int i;
 
-	for (i = 0; i < num_pages; i++)
+	for (i = 0; i < num_pages; i++) {
+		if (dirty)
+			set_page_dirty_lock(pages[i]);
 		put_page(pages[i]);
+	}
 	kfree(pages);
 }
 EXPORT_SYMBOL(ceph_put_page_vector);
diff --git a/scripts/recordmcount.h b/scripts/recordmcount.h
index 58e933a2054..39667174971 100644
--- a/scripts/recordmcount.h
+++ b/scripts/recordmcount.h
@@ -119,7 +119,7 @@ static uint_t (*Elf_r_sym)(Elf_Rel const *rp) = fn_ELF_R_SYM;
 
 static void fn_ELF_R_INFO(Elf_Rel *const rp, unsigned sym, unsigned type)
 {
-	rp->r_info = ELF_R_INFO(sym, type);
+	rp->r_info = _w(ELF_R_INFO(sym, type));
 }
 static void (*Elf_r_info)(Elf_Rel *const rp, unsigned sym, unsigned type) = fn_ELF_R_INFO;
 
diff --git a/scripts/tags.sh b/scripts/tags.sh
index 8509bb51293..bbbe584d449 100755
--- a/scripts/tags.sh
+++ b/scripts/tags.sh
@@ -125,7 +125,9 @@ exuberant()
 	-I DEFINE_TRACE,EXPORT_TRACEPOINT_SYMBOL,EXPORT_TRACEPOINT_SYMBOL_GPL \
 	--extra=+f --c-kinds=-px                                \
 	--regex-asm='/^ENTRY\(([^)]*)\).*/\1/'                  \
-	--regex-c='/^SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/sys_\1/'
+	--regex-c='/^SYSCALL_DEFINE[[:digit:]]?\(([^,)]*).*/sys_\1/' \
+	--regex-c++='/^TRACE_EVENT\(([^,)]*).*/trace_\1/'		\
+	--regex-c++='/^DEFINE_EVENT\(([^,)]*).*/trace_\1/'
 
 	all_kconfigs | xargs $1 -a                              \
 	--langdef=kconfig --language-force=kconfig              \
diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
index 2d7d7de8498..427da45d790 100644
--- a/sound/pci/hda/patch_realtek.c
+++ b/sound/pci/hda/patch_realtek.c
@@ -10830,7 +10830,8 @@ static int alc_auto_add_mic_boost(struct hda_codec *codec)
 {
 	struct alc_spec *spec = codec->spec;
 	struct auto_pin_cfg *cfg = &spec->autocfg;
-	int i, err;
+	int i, err, type;
+	int type_idx = 0;
 	hda_nid_t nid;
 
 	for (i = 0; i < cfg->num_inputs; i++) {
@@ -10839,9 +10840,15 @@ static int alc_auto_add_mic_boost(struct hda_codec *codec)
 		nid = cfg->inputs[i].pin;
 		if (get_wcaps(codec, nid) & AC_WCAP_IN_AMP) {
 			char label[32];
+			type = cfg->inputs[i].type;
+			if (i > 0 && type == cfg->inputs[i - 1].type)
+				type_idx++;
+			else
+				type_idx = 0;
 			snprintf(label, sizeof(label), "%s Boost",
 				 hda_get_autocfg_input_label(codec, cfg, i));
-			err = add_control(spec, ALC_CTL_WIDGET_VOL, label, 0,
+			err = add_control(spec, ALC_CTL_WIDGET_VOL, label,
+					  type_idx,
 				  HDA_COMPOSE_AMP_VAL(nid, 3, 0, HDA_INPUT));
 			if (err < 0)
 				return err;
@@ -14800,6 +14807,8 @@ static int alc269_resume(struct hda_codec *codec)
 enum {
 	ALC269_FIXUP_SONY_VAIO,
 	ALC269_FIXUP_DELL_M101Z,
+	ALC269_FIXUP_LENOVO_EDGE14,
+	ALC269_FIXUP_ASUS_G73JW,
 };
 
 static const struct alc_fixup alc269_fixups[] = {
@@ -14817,11 +14826,22 @@ static const struct alc_fixup alc269_fixups[] = {
 			{}
 		}
 	},
+	[ALC269_FIXUP_LENOVO_EDGE14] = {
+		.sku = ALC_FIXUP_SKU_IGNORE,
+	},
+	[ALC269_FIXUP_ASUS_G73JW] = {
+		.pins = (const struct alc_pincfg[]) {
+			{ 0x17, 0x99130111 }, /* subwoofer */
+			{ }
+		}
+	},
 };
 
 static struct snd_pci_quirk alc269_fixup_tbl[] = {
 	SND_PCI_QUIRK_VENDOR(0x104d, "Sony VAIO", ALC269_FIXUP_SONY_VAIO),
 	SND_PCI_QUIRK(0x1028, 0x0470, "Dell M101z", ALC269_FIXUP_DELL_M101Z),
+	SND_PCI_QUIRK(0x17aa, 0x21b8, "Thinkpad Edge 14", ALC269_FIXUP_LENOVO_EDGE14),
+	SND_PCI_QUIRK(0x1043, 0x1a13, "Asus G73Jw", ALC269_FIXUP_ASUS_G73JW),
 	{}
 };
 
diff --git a/sound/soc/codecs/wm8580.c b/sound/soc/codecs/wm8580.c
index 879dff2714d..8725d4e7543 100644
--- a/sound/soc/codecs/wm8580.c
+++ b/sound/soc/codecs/wm8580.c
@@ -161,7 +161,7 @@
 static const u16 wm8580_reg[] = {
 	0x0121, 0x017e, 0x007d, 0x0014, /*R3*/
 	0x0121, 0x017e, 0x007d, 0x0194, /*R7*/
-	0x001c, 0x0002, 0x0002, 0x00c2, /*R11*/
+	0x0010, 0x0002, 0x0002, 0x00c2, /*R11*/
 	0x0182, 0x0082, 0x000a, 0x0024, /*R15*/
 	0x0009, 0x0000, 0x00ff, 0x0000, /*R19*/
 	0x00ff, 0x00ff, 0x00ff, 0x00ff, /*R23*/
diff --git a/sound/soc/codecs/wm8904.c b/sound/soc/codecs/wm8904.c
index fca60a0b57b..9001cc48ba1 100644
--- a/sound/soc/codecs/wm8904.c
+++ b/sound/soc/codecs/wm8904.c
@@ -818,7 +818,8 @@ static int wm8904_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8904_priv *wm8904 = snd_soc_codec_get_drvdata(codec);
 
-	return wm8904->deemph;
+	ucontrol->value.enumerated.item[0] = wm8904->deemph;
+	return 0;
 }
 
 static int wm8904_put_deemph(struct snd_kcontrol *kcontrol,
diff --git a/sound/soc/codecs/wm8955.c b/sound/soc/codecs/wm8955.c
index f89ad6c9a80..9cbab8e1de0 100644
--- a/sound/soc/codecs/wm8955.c
+++ b/sound/soc/codecs/wm8955.c
@@ -380,7 +380,8 @@ static int wm8955_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8955_priv *wm8955 = snd_soc_codec_get_drvdata(codec);
 
-	return wm8955->deemph;
+	ucontrol->value.enumerated.item[0] = wm8955->deemph;
+	return 0;
 }
 
 static int wm8955_put_deemph(struct snd_kcontrol *kcontrol,
diff --git a/sound/soc/codecs/wm8960.c b/sound/soc/codecs/wm8960.c
index 8d5efb333c3..21986c42272 100644
--- a/sound/soc/codecs/wm8960.c
+++ b/sound/soc/codecs/wm8960.c
@@ -138,7 +138,8 @@ static int wm8960_get_deemph(struct snd_kcontrol *kcontrol,
 	struct snd_soc_codec *codec = snd_kcontrol_chip(kcontrol);
 	struct wm8960_priv *wm8960 = snd_soc_codec_get_drvdata(codec);
 
-	return wm8960->deemph;
+	ucontrol->value.enumerated.item[0] = wm8960->deemph;
+	return 0;
 }
 
 static int wm8960_put_deemph(struct snd_kcontrol *kcontrol,
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 75ed6491222..c721502833b 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -944,6 +944,9 @@ static int dapm_power_widgets(struct snd_soc_codec *codec, int event)
 		case SND_SOC_DAPM_STREAM_RESUME:
 			sys_power = 1;
 			break;
+		case SND_SOC_DAPM_STREAM_STOP:
+			sys_power = !!codec->active;
+			break;
 		case SND_SOC_DAPM_STREAM_SUSPEND:
 			sys_power = 0;
 			break;