diff --git a/CREDITS b/CREDITS
index a7ea8e343836..d78359f5f64d 100644
--- a/CREDITS
+++ b/CREDITS
@@ -518,6 +518,14 @@ N: Zach Brown
 E: zab@zabbo.net
 D: maestro pci sound
 
+M: David Brownell
+D: Kernel engineer, mentor, and friend.  Maintained USB EHCI and
+D: gadget layers, SPI subsystem, GPIO subsystem, and more than a few
+D: device drivers.  His encouragement also helped many engineers get
+D: started working on the Linux kernel.  David passed away in early
+D: 2011, and will be greatly missed.
+W: https://lkml.org/lkml/2011/4/5/36
+
 N: Gary Brubaker
 E: xavyer@ix.netcom.com
 D: USB Serial Empeg Empeg-car Mark I/II Driver
diff --git a/MAINTAINERS b/MAINTAINERS
index 29801f760b6f..fb0294919adc 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -4252,8 +4252,7 @@ F:	drivers/mmc/
 F:	include/linux/mmc/
 
 MULTIMEDIA CARD (MMC) ETC. OVER SPI
-M:	David Brownell <dbrownell@users.sourceforge.net>
-S:	Odd Fixes
+S:	Orphan
 F:	drivers/mmc/host/mmc_spi.c
 F:	include/linux/spi/mmc_spi.h
 
@@ -4603,7 +4602,6 @@ F:	drivers/media/video/omap3isp/*
 
 OMAP USB SUPPORT
 M:	Felipe Balbi <balbi@ti.com>
-M:	David Brownell <dbrownell@users.sourceforge.net>
 L:	linux-usb@vger.kernel.org
 L:	linux-omap@vger.kernel.org
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/balbi/usb.git
@@ -5984,7 +5982,6 @@ F:	Documentation/serial/specialix.txt
 F:	drivers/staging/tty/specialix*
 
 SPI SUBSYSTEM
-M:	David Brownell <dbrownell@users.sourceforge.net>
 M:	Grant Likely <grant.likely@secretlab.ca>
 L:	spi-devel-general@lists.sourceforge.net
 Q:	http://patchwork.kernel.org/project/spi-devel-general/list/
@@ -6432,9 +6429,8 @@ S:	Maintained
 F:	drivers/usb/misc/rio500*
 
 USB EHCI DRIVER
-M:	David Brownell <dbrownell@users.sourceforge.net>
 L:	linux-usb@vger.kernel.org
-S:	Odd Fixes
+S:	Orphan
 F:	Documentation/usb/ehci.txt
 F:	drivers/usb/host/ehci*
 
@@ -6448,10 +6444,9 @@ S:	Maintained
 F:	drivers/media/video/et61x251/
 
 USB GADGET/PERIPHERAL SUBSYSTEM
-M:	David Brownell <dbrownell@users.sourceforge.net>
 L:	linux-usb@vger.kernel.org
 W:	http://www.linux-usb.org/gadget
-S:	Maintained
+S:	Orphan
 F:	drivers/usb/gadget/
 F:	include/linux/usb/gadget*
 
@@ -6492,9 +6487,8 @@ S:	Maintained
 F:	sound/usb/midi.*
 
 USB OHCI DRIVER
-M:	David Brownell <dbrownell@users.sourceforge.net>
 L:	linux-usb@vger.kernel.org
-S:	Odd Fixes
+S:	Orphan
 F:	Documentation/usb/ohci.txt
 F:	drivers/usb/host/ohci*
 
diff --git a/arch/arm/mach-omap1/dma.c b/arch/arm/mach-omap1/dma.c
index d8559344c6e2..f5a52204b89f 100644
--- a/arch/arm/mach-omap1/dma.c
+++ b/arch/arm/mach-omap1/dma.c
@@ -284,14 +284,15 @@ static int __init omap1_system_dma_init(void)
 	dma_base = ioremap(res[0].start, resource_size(&res[0]));
 	if (!dma_base) {
 		pr_err("%s: Unable to ioremap\n", __func__);
-		return -ENODEV;
+		ret = -ENODEV;
+		goto exit_device_put;
 	}
 
 	ret = platform_device_add_resources(pdev, res, ARRAY_SIZE(res));
 	if (ret) {
 		dev_err(&pdev->dev, "%s: Unable to add resources for %s%d\n",
 			__func__, pdev->name, pdev->id);
-		goto exit_device_del;
+		goto exit_device_put;
 	}
 
 	p = kzalloc(sizeof(struct omap_system_dma_plat_info), GFP_KERNEL);
@@ -299,7 +300,7 @@ static int __init omap1_system_dma_init(void)
 		dev_err(&pdev->dev, "%s: Unable to allocate 'p' for %s\n",
 			__func__, pdev->name);
 		ret = -ENOMEM;
-		goto exit_device_put;
+		goto exit_device_del;
 	}
 
 	d = kzalloc(sizeof(struct omap_dma_dev_attr), GFP_KERNEL);
@@ -380,10 +381,10 @@ exit_release_d:
 	kfree(d);
 exit_release_p:
 	kfree(p);
-exit_device_put:
-	platform_device_put(pdev);
 exit_device_del:
 	platform_device_del(pdev);
+exit_device_put:
+	platform_device_put(pdev);
 
 	return ret;
 }
diff --git a/arch/arm/mach-omap2/board-2430sdp.c b/arch/arm/mach-omap2/board-2430sdp.c
index d54969be0a54..5de6eac0a725 100644
--- a/arch/arm/mach-omap2/board-2430sdp.c
+++ b/arch/arm/mach-omap2/board-2430sdp.c
@@ -26,13 +26,13 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/io.h>
+#include <linux/gpio.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
 
-#include <mach/gpio.h>
 #include <plat/board.h>
 #include <plat/common.h>
 #include <plat/gpmc.h>
diff --git a/arch/arm/mach-omap2/board-3430sdp.c b/arch/arm/mach-omap2/board-3430sdp.c
index ae2963a98041..5dac974be625 100644
--- a/arch/arm/mach-omap2/board-3430sdp.c
+++ b/arch/arm/mach-omap2/board-3430sdp.c
@@ -622,19 +622,19 @@ static struct omap_device_pad serial3_pads[] __initdata = {
 			 OMAP_MUX_MODE0),
 };
 
-static struct omap_board_data serial1_data = {
+static struct omap_board_data serial1_data __initdata = {
 	.id		= 0,
 	.pads		= serial1_pads,
 	.pads_cnt	= ARRAY_SIZE(serial1_pads),
 };
 
-static struct omap_board_data serial2_data = {
+static struct omap_board_data serial2_data __initdata = {
 	.id		= 1,
 	.pads		= serial2_pads,
 	.pads_cnt	= ARRAY_SIZE(serial2_pads),
 };
 
-static struct omap_board_data serial3_data = {
+static struct omap_board_data serial3_data __initdata = {
 	.id		= 2,
 	.pads		= serial3_pads,
 	.pads_cnt	= ARRAY_SIZE(serial3_pads),
diff --git a/arch/arm/mach-omap2/board-4430sdp.c b/arch/arm/mach-omap2/board-4430sdp.c
index 73fa90bb6953..63de2d396e2d 100644
--- a/arch/arm/mach-omap2/board-4430sdp.c
+++ b/arch/arm/mach-omap2/board-4430sdp.c
@@ -258,7 +258,7 @@ static struct gpio sdp4430_eth_gpios[] __initdata = {
 	{ ETH_KS8851_IRQ,	GPIOF_IN,		"eth_irq"	},
 };
 
-static int omap_ethernet_init(void)
+static int __init omap_ethernet_init(void)
 {
 	int status;
 
@@ -322,6 +322,7 @@ static struct omap2_hsmmc_info mmc[] = {
 		.gpio_wp	= -EINVAL,
 		.nonremovable   = true,
 		.ocr_mask	= MMC_VDD_29_30,
+		.no_off_init	= true,
 	},
 	{
 		.mmc		= 1,
@@ -681,19 +682,19 @@ static struct omap_device_pad serial4_pads[] __initdata = {
 			 OMAP_PIN_OUTPUT | OMAP_MUX_MODE0),
 };
 
-static struct omap_board_data serial2_data = {
+static struct omap_board_data serial2_data __initdata = {
 	.id		= 1,
 	.pads		= serial2_pads,
 	.pads_cnt	= ARRAY_SIZE(serial2_pads),
 };
 
-static struct omap_board_data serial3_data = {
+static struct omap_board_data serial3_data __initdata = {
 	.id		= 2,
 	.pads		= serial3_pads,
 	.pads_cnt	= ARRAY_SIZE(serial3_pads),
 };
 
-static struct omap_board_data serial4_data = {
+static struct omap_board_data serial4_data __initdata = {
 	.id		= 3,
 	.pads		= serial4_pads,
 	.pads_cnt	= ARRAY_SIZE(serial4_pads),
@@ -729,7 +730,7 @@ static void __init omap_4430sdp_init(void)
 
 	if (omap_rev() == OMAP4430_REV_ES1_0)
 		package = OMAP_PACKAGE_CBL;
-	omap4_mux_init(board_mux, package);
+	omap4_mux_init(board_mux, NULL, package);
 
 	omap_board_config = sdp4430_config;
 	omap_board_config_size = ARRAY_SIZE(sdp4430_config);
diff --git a/arch/arm/mach-omap2/board-apollon.c b/arch/arm/mach-omap2/board-apollon.c
index f3beb8eeef77..b124bdfb4239 100644
--- a/arch/arm/mach-omap2/board-apollon.c
+++ b/arch/arm/mach-omap2/board-apollon.c
@@ -27,13 +27,13 @@
 #include <linux/err.h>
 #include <linux/clk.h>
 #include <linux/smc91x.h>
+#include <linux/gpio.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 
-#include <mach/gpio.h>
 #include <plat/led.h>
 #include <plat/usb.h>
 #include <plat/board.h>
diff --git a/arch/arm/mach-omap2/board-cm-t35.c b/arch/arm/mach-omap2/board-cm-t35.c
index c63115bc1536..77456dec93ea 100644
--- a/arch/arm/mach-omap2/board-cm-t35.c
+++ b/arch/arm/mach-omap2/board-cm-t35.c
@@ -63,8 +63,6 @@
 #define SB_T35_SMSC911X_CS	4
 #define SB_T35_SMSC911X_GPIO	65
 
-#define NAND_BLOCK_SIZE		SZ_128K
-
 #if defined(CONFIG_SMSC911X) || defined(CONFIG_SMSC911X_MODULE)
 #include <linux/smsc911x.h>
 #include <plat/gpmc-smsc911x.h>
diff --git a/arch/arm/mach-omap2/board-cm-t3517.c b/arch/arm/mach-omap2/board-cm-t3517.c
index 08f08e812492..c3a9fd35034a 100644
--- a/arch/arm/mach-omap2/board-cm-t3517.c
+++ b/arch/arm/mach-omap2/board-cm-t3517.c
@@ -48,6 +48,7 @@
 
 #include "mux.h"
 #include "control.h"
+#include "common-board-devices.h"
 
 #if defined(CONFIG_LEDS_GPIO) || defined(CONFIG_LEDS_GPIO_MODULE)
 static struct gpio_led cm_t3517_leds[] = {
@@ -177,7 +178,7 @@ static struct usbhs_omap_board_data cm_t3517_ehci_pdata __initdata = {
 	.reset_gpio_port[2]  = -EINVAL,
 };
 
-static int cm_t3517_init_usbh(void)
+static int __init cm_t3517_init_usbh(void)
 {
 	int err;
 
@@ -203,8 +204,6 @@ static inline int cm_t3517_init_usbh(void)
 #endif
 
 #if defined(CONFIG_MTD_NAND_OMAP2) || defined(CONFIG_MTD_NAND_OMAP2_MODULE)
-#define NAND_BLOCK_SIZE		SZ_128K
-
 static struct mtd_partition cm_t3517_nand_partitions[] = {
 	{
 		.name           = "xloader",
diff --git a/arch/arm/mach-omap2/board-devkit8000.c b/arch/arm/mach-omap2/board-devkit8000.c
index cf520d7dd614..34956ec83296 100644
--- a/arch/arm/mach-omap2/board-devkit8000.c
+++ b/arch/arm/mach-omap2/board-devkit8000.c
@@ -61,8 +61,6 @@
 #include "timer-gp.h"
 #include "common-board-devices.h"
 
-#define NAND_BLOCK_SIZE		SZ_128K
-
 #define OMAP_DM9000_GPIO_IRQ	25
 #define OMAP3_DEVKIT_TS_GPIO	27
 
diff --git a/arch/arm/mach-omap2/board-omap3beagle.c b/arch/arm/mach-omap2/board-omap3beagle.c
index be71426359f2..7f21d24bd437 100644
--- a/arch/arm/mach-omap2/board-omap3beagle.c
+++ b/arch/arm/mach-omap2/board-omap3beagle.c
@@ -54,8 +54,6 @@
 #include "pm.h"
 #include "common-board-devices.h"
 
-#define NAND_BLOCK_SIZE		SZ_128K
-
 /*
  * OMAP3 Beagle revision
  * Run time detection of Beagle revision is done by reading GPIO.
@@ -106,6 +104,9 @@ static void __init omap3_beagle_init_rev(void)
 	beagle_rev = gpio_get_value(171) | (gpio_get_value(172) << 1)
 			| (gpio_get_value(173) << 2);
 
+	gpio_free_array(omap3_beagle_rev_gpios,
+			ARRAY_SIZE(omap3_beagle_rev_gpios));
+
 	switch (beagle_rev) {
 	case 7:
 		printk(KERN_INFO "OMAP3 Beagle Rev: Ax/Bx\n");
@@ -579,6 +580,9 @@ static void __init omap3_beagle_init(void)
 	omap_nand_flash_init(NAND_BUSWIDTH_16, omap3beagle_nand_partitions,
 			     ARRAY_SIZE(omap3beagle_nand_partitions));
 
+	/* Ensure msecure is mux'd to be able to set the RTC. */
+	omap_mux_init_signal("sys_drm_msecure", OMAP_PIN_OFF_OUTPUT_HIGH);
+
 	/* Ensure SDRC pins are mux'd for self-refresh */
 	omap_mux_init_signal("sdrc_cke0", OMAP_PIN_OUTPUT);
 	omap_mux_init_signal("sdrc_cke1", OMAP_PIN_OUTPUT);
diff --git a/arch/arm/mach-omap2/board-omap3pandora.c b/arch/arm/mach-omap2/board-omap3pandora.c
index 1d10736c6d3c..2a0bb4818cae 100644
--- a/arch/arm/mach-omap2/board-omap3pandora.c
+++ b/arch/arm/mach-omap2/board-omap3pandora.c
@@ -30,6 +30,7 @@
 #include <linux/leds.h>
 #include <linux/input.h>
 #include <linux/input/matrix_keypad.h>
+#include <linux/gpio.h>
 #include <linux/gpio_keys.h>
 #include <linux/mmc/host.h>
 #include <linux/mmc/card.h>
@@ -41,7 +42,6 @@
 
 #include <plat/board.h>
 #include <plat/common.h>
-#include <mach/gpio.h>
 #include <mach/hardware.h>
 #include <plat/mcspi.h>
 #include <plat/usb.h>
@@ -57,8 +57,6 @@
 #define PANDORA_WIFI_NRESET_GPIO	23
 #define OMAP3_PANDORA_TS_GPIO		94
 
-#define NAND_BLOCK_SIZE			SZ_128K
-
 static struct mtd_partition omap3pandora_nand_partitions[] = {
 	{
 		.name           = "xloader",
diff --git a/arch/arm/mach-omap2/board-omap3touchbook.c b/arch/arm/mach-omap2/board-omap3touchbook.c
index 82872d7d313b..5f649faf7377 100644
--- a/arch/arm/mach-omap2/board-omap3touchbook.c
+++ b/arch/arm/mach-omap2/board-omap3touchbook.c
@@ -56,8 +56,6 @@
 
 #include <asm/setup.h>
 
-#define NAND_BLOCK_SIZE		SZ_128K
-
 #define OMAP3_AC_GPIO		136
 #define OMAP3_TS_GPIO		162
 #define TB_BL_PWM_TIMER		9
diff --git a/arch/arm/mach-omap2/board-omap4panda.c b/arch/arm/mach-omap2/board-omap4panda.c
index 90485fced973..0cfe2005cb50 100644
--- a/arch/arm/mach-omap2/board-omap4panda.c
+++ b/arch/arm/mach-omap2/board-omap4panda.c
@@ -526,19 +526,19 @@ static struct omap_device_pad serial4_pads[] __initdata = {
 			 OMAP_PIN_OUTPUT | OMAP_MUX_MODE0),
 };
 
-static struct omap_board_data serial2_data = {
+static struct omap_board_data serial2_data __initdata = {
 	.id             = 1,
 	.pads           = serial2_pads,
 	.pads_cnt       = ARRAY_SIZE(serial2_pads),
 };
 
-static struct omap_board_data serial3_data = {
+static struct omap_board_data serial3_data __initdata = {
 	.id             = 2,
 	.pads           = serial3_pads,
 	.pads_cnt       = ARRAY_SIZE(serial3_pads),
 };
 
-static struct omap_board_data serial4_data = {
+static struct omap_board_data serial4_data __initdata = {
 	.id             = 3,
 	.pads           = serial4_pads,
 	.pads_cnt       = ARRAY_SIZE(serial4_pads),
@@ -687,7 +687,7 @@ static void __init omap4_panda_init(void)
 
 	if (omap_rev() == OMAP4430_REV_ES1_0)
 		package = OMAP_PACKAGE_CBL;
-	omap4_mux_init(board_mux, package);
+	omap4_mux_init(board_mux, NULL, package);
 
 	if (wl12xx_set_platform_data(&omap_panda_wlan_data))
 		pr_err("error setting wl12xx data\n");
diff --git a/arch/arm/mach-omap2/board-overo.c b/arch/arm/mach-omap2/board-overo.c
index 1555918e3ffa..175e1ab2b04d 100644
--- a/arch/arm/mach-omap2/board-overo.c
+++ b/arch/arm/mach-omap2/board-overo.c
@@ -24,6 +24,7 @@
 #include <linux/err.h>
 #include <linux/init.h>
 #include <linux/io.h>
+#include <linux/gpio.h>
 #include <linux/kernel.h>
 #include <linux/platform_device.h>
 #include <linux/i2c/twl.h>
@@ -45,7 +46,6 @@
 #include <plat/common.h>
 #include <video/omapdss.h>
 #include <video/omap-panel-generic-dpi.h>
-#include <mach/gpio.h>
 #include <plat/gpmc.h>
 #include <mach/hardware.h>
 #include <plat/nand.h>
@@ -65,8 +65,6 @@
 #define OVERO_GPIO_USBH_CPEN	168
 #define OVERO_GPIO_USBH_NRESET	183
 
-#define NAND_BLOCK_SIZE SZ_128K
-
 #define OVERO_SMSC911X_CS      5
 #define OVERO_SMSC911X_GPIO    176
 #define OVERO_SMSC911X2_CS     4
diff --git a/arch/arm/mach-omap2/board-rx51-peripherals.c b/arch/arm/mach-omap2/board-rx51-peripherals.c
index f6247e71a194..990366726c58 100644
--- a/arch/arm/mach-omap2/board-rx51-peripherals.c
+++ b/arch/arm/mach-omap2/board-rx51-peripherals.c
@@ -488,6 +488,7 @@ static struct regulator_init_data rx51_vmmc2 = {
 		.name			= "V28_A",
 		.min_uV			= 2800000,
 		.max_uV			= 3000000,
+		.always_on		= true, /* due VIO leak to AIC34 VDDs */
 		.apply_uV		= true,
 		.valid_modes_mask	= REGULATOR_MODE_NORMAL
 					| REGULATOR_MODE_STANDBY,
@@ -582,7 +583,7 @@ static int rx51_twlgpio_setup(struct device *dev, unsigned gpio, unsigned n)
 {
 	/* FIXME this gpio setup is just a placeholder for now */
 	gpio_request_one(gpio + 6, GPIOF_OUT_INIT_LOW, "backlight_pwm");
-	gpio_request_one(gpio + 7, GPIOF_OUT_INIT_HIGH, "speaker_en");
+	gpio_request_one(gpio + 7, GPIOF_OUT_INIT_LOW, "speaker_en");
 
 	return 0;
 }
diff --git a/arch/arm/mach-omap2/board-zoom-display.c b/arch/arm/mach-omap2/board-zoom-display.c
index c7c6beb1ec24..d4683ba5f721 100644
--- a/arch/arm/mach-omap2/board-zoom-display.c
+++ b/arch/arm/mach-omap2/board-zoom-display.c
@@ -26,7 +26,7 @@ static struct gpio zoom_lcd_gpios[] __initdata = {
 	{ LCD_PANEL_QVGA_GPIO,	GPIOF_OUT_INIT_HIGH, "lcd qvga"	 },
 };
 
-static void zoom_lcd_panel_init(void)
+static void __init zoom_lcd_panel_init(void)
 {
 	zoom_lcd_gpios[0].gpio = (omap_rev() > OMAP3430_REV_ES3_0) ?
 			LCD_PANEL_RESET_GPIO_PROD :
diff --git a/arch/arm/mach-omap2/common-board-devices.c b/arch/arm/mach-omap2/common-board-devices.c
index e94903b2c65b..94ccf464677b 100644
--- a/arch/arm/mach-omap2/common-board-devices.c
+++ b/arch/arm/mach-omap2/common-board-devices.c
@@ -85,18 +85,18 @@ void __init omap_ads7846_init(int bus_num, int gpio_pendown, int gpio_debounce,
 	struct spi_board_info *spi_bi = &ads7846_spi_board_info;
 	int err;
 
-	err = gpio_request(gpio_pendown, "TS PenDown");
-	if (err) {
-		pr_err("Could not obtain gpio for TS PenDown: %d\n", err);
-		return;
+	if (board_pdata && board_pdata->get_pendown_state) {
+		err = gpio_request_one(gpio_pendown, GPIOF_IN, "TSPenDown");
+		if (err) {
+			pr_err("Couldn't obtain gpio for TSPenDown: %d\n", err);
+			return;
+		}
+		gpio_export(gpio_pendown, 0);
+
+		if (gpio_debounce)
+			gpio_set_debounce(gpio_pendown, gpio_debounce);
 	}
 
-	gpio_direction_input(gpio_pendown);
-	gpio_export(gpio_pendown, 0);
-
-	if (gpio_debounce)
-		gpio_set_debounce(gpio_pendown, gpio_debounce);
-
 	ads7846_config.gpio_pendown = gpio_pendown;
 
 	spi_bi->bus_num	= bus_num;
diff --git a/arch/arm/mach-omap2/common-board-devices.h b/arch/arm/mach-omap2/common-board-devices.h
index eb80b3b0ef47..679719051df5 100644
--- a/arch/arm/mach-omap2/common-board-devices.h
+++ b/arch/arm/mach-omap2/common-board-devices.h
@@ -1,6 +1,8 @@
 #ifndef __OMAP_COMMON_BOARD_DEVICES__
 #define __OMAP_COMMON_BOARD_DEVICES__
 
+#define NAND_BLOCK_SIZE	SZ_128K
+
 struct twl4030_platform_data;
 struct mtd_partition;
 
diff --git a/arch/arm/mach-omap2/devices.c b/arch/arm/mach-omap2/devices.c
index 7b8558564591..5b8ca680ed93 100644
--- a/arch/arm/mach-omap2/devices.c
+++ b/arch/arm/mach-omap2/devices.c
@@ -97,7 +97,7 @@ static int __init omap4_l3_init(void)
 
 	WARN(IS_ERR(od), "could not build omap_device for %s\n", oh_name);
 
-	return PTR_ERR(od);
+	return IS_ERR(od) ? PTR_ERR(od) : 0;
 }
 postcore_initcall(omap4_l3_init);
 
diff --git a/arch/arm/mach-omap2/hsmmc.c b/arch/arm/mach-omap2/hsmmc.c
index b2f30bed5a20..66868c5d5a29 100644
--- a/arch/arm/mach-omap2/hsmmc.c
+++ b/arch/arm/mach-omap2/hsmmc.c
@@ -145,6 +145,7 @@ static void omap4_hsmmc1_after_set_reg(struct device *dev, int slot,
 				 int power_on, int vdd)
 {
 	u32 reg;
+	unsigned long timeout;
 
 	if (power_on) {
 		reg = omap4_ctrl_pad_readl(control_pbias_offset);
@@ -157,9 +158,15 @@ static void omap4_hsmmc1_after_set_reg(struct device *dev, int slot,
 			OMAP4_MMC1_PWRDNZ_MASK |
 			OMAP4_USBC1_ICUSB_PWRDNZ_MASK);
 		omap4_ctrl_pad_writel(reg, control_pbias_offset);
-		/* 4 microsec delay for comparator to generate an error*/
-		udelay(4);
-		reg = omap4_ctrl_pad_readl(control_pbias_offset);
+
+		timeout = jiffies + msecs_to_jiffies(5);
+		do {
+			reg = omap4_ctrl_pad_readl(control_pbias_offset);
+			if (!(reg & OMAP4_MMC1_PBIASLITE_VMODE_ERROR_MASK))
+				break;
+			usleep_range(100, 200);
+		} while (!time_after(jiffies, timeout));
+
 		if (reg & OMAP4_MMC1_PBIASLITE_VMODE_ERROR_MASK) {
 			pr_err("Pbias Voltage is not same as LDO\n");
 			/* Caution : On VMODE_ERROR Power Down MMC IO */
@@ -331,6 +338,9 @@ static int __init omap_hsmmc_pdata_init(struct omap2_hsmmc_info *c,
 	if (c->no_off)
 		mmc->slots[0].no_off = 1;
 
+	if (c->no_off_init)
+		mmc->slots[0].no_regulator_off_init = c->no_off_init;
+
 	if (c->vcc_aux_disable_is_sleep)
 		mmc->slots[0].vcc_aux_disable_is_sleep = 1;
 
diff --git a/arch/arm/mach-omap2/hsmmc.h b/arch/arm/mach-omap2/hsmmc.h
index f119348827d4..f757e78d4d4f 100644
--- a/arch/arm/mach-omap2/hsmmc.h
+++ b/arch/arm/mach-omap2/hsmmc.h
@@ -18,6 +18,7 @@ struct omap2_hsmmc_info {
 	bool	nonremovable;	/* Nonremovable e.g. eMMC */
 	bool	power_saving;	/* Try to sleep or power off when possible */
 	bool	no_off;		/* power_saving and power is not to go off */
+	bool	no_off_init;	/* no power off when not in MMC sleep state */
 	bool	vcc_aux_disable_is_sleep; /* Regulator off remapped to sleep */
 	int	gpio_cd;	/* or -EINVAL */
 	int	gpio_wp;	/* or -EINVAL */
diff --git a/arch/arm/mach-omap2/mux.c b/arch/arm/mach-omap2/mux.c
index a4ab1e364313..c7fb22abc219 100644
--- a/arch/arm/mach-omap2/mux.c
+++ b/arch/arm/mach-omap2/mux.c
@@ -83,6 +83,9 @@ void omap_mux_write(struct omap_mux_partition *partition, u16 val,
 void omap_mux_write_array(struct omap_mux_partition *partition,
 				 struct omap_board_mux *board_mux)
 {
+	if (!board_mux)
+		return;
+
 	while (board_mux->reg_offset != OMAP_MUX_TERMINATOR) {
 		omap_mux_write(partition, board_mux->value,
 			       board_mux->reg_offset);
@@ -906,7 +909,7 @@ static struct omap_mux *omap_mux_get_by_gpio(
 u16 omap_mux_get_gpio(int gpio)
 {
 	struct omap_mux_partition *partition;
-	struct omap_mux *m;
+	struct omap_mux *m = NULL;
 
 	list_for_each_entry(partition, &mux_partitions, node) {
 		m = omap_mux_get_by_gpio(partition, gpio);
diff --git a/arch/arm/mach-omap2/mux.h b/arch/arm/mach-omap2/mux.h
index 137f321c029f..2132308ad1e4 100644
--- a/arch/arm/mach-omap2/mux.h
+++ b/arch/arm/mach-omap2/mux.h
@@ -323,10 +323,12 @@ int omap3_mux_init(struct omap_board_mux *board_mux, int flags);
 
 /**
  * omap4_mux_init() - initialize mux system with board specific set
- * @board_mux:		Board specific mux table
+ * @board_subset:	Board specific mux table
+ * @board_wkup_subset:	Board specific mux table for wakeup instance
  * @flags:		OMAP package type used for the board
  */
-int omap4_mux_init(struct omap_board_mux *board_mux, int flags);
+int omap4_mux_init(struct omap_board_mux *board_subset,
+	struct omap_board_mux *board_wkup_subset, int flags);
 
 /**
  * omap_mux_init - private mux init function, do not call
diff --git a/arch/arm/mach-omap2/mux44xx.c b/arch/arm/mach-omap2/mux44xx.c
index 9a66445112ae..f5a74daab2ff 100644
--- a/arch/arm/mach-omap2/mux44xx.c
+++ b/arch/arm/mach-omap2/mux44xx.c
@@ -1309,7 +1309,8 @@ static struct omap_ball __initdata omap4_wkup_cbl_cbs_ball[] = {
 #define omap4_wkup_cbl_cbs_ball  NULL
 #endif
 
-int __init omap4_mux_init(struct omap_board_mux *board_subset, int flags)
+int __init omap4_mux_init(struct omap_board_mux *board_subset,
+	struct omap_board_mux *board_wkup_subset, int flags)
 {
 	struct omap_ball *package_balls_core;
 	struct omap_ball *package_balls_wkup = omap4_wkup_cbl_cbs_ball;
@@ -1347,7 +1348,7 @@ int __init omap4_mux_init(struct omap_board_mux *board_subset, int flags)
 			    OMAP_MUX_GPIO_IN_MODE3,
 			    OMAP4_CTRL_MODULE_PAD_WKUP_MUX_PBASE,
 			    OMAP4_CTRL_MODULE_PAD_WKUP_MUX_SIZE,
-			    omap4_wkup_muxmodes, NULL, board_subset,
+			    omap4_wkup_muxmodes, NULL, board_wkup_subset,
 			    package_balls_wkup);
 
 	return ret;
diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c
index e03429453ce7..293fa6cd50e1 100644
--- a/arch/arm/mach-omap2/omap_hwmod.c
+++ b/arch/arm/mach-omap2/omap_hwmod.c
@@ -1628,7 +1628,7 @@ int omap_hwmod_for_each(int (*fn)(struct omap_hwmod *oh, void *data),
 			void *data)
 {
 	struct omap_hwmod *temp_oh;
-	int ret;
+	int ret = 0;
 
 	if (!fn)
 		return -EINVAL;
diff --git a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
index abc548a0c98d..e1c69ffe0f69 100644
--- a/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
+++ b/arch/arm/mach-omap2/omap_hwmod_44xx_data.c
@@ -5109,7 +5109,7 @@ static __initdata struct omap_hwmod *omap44xx_hwmods[] = {
 	&omap44xx_iva_seq1_hwmod,
 
 	/* kbd class */
-/*	&omap44xx_kbd_hwmod, */
+	&omap44xx_kbd_hwmod,
 
 	/* mailbox class */
 	&omap44xx_mailbox_hwmod,
diff --git a/arch/arm/mach-omap2/omap_phy_internal.c b/arch/arm/mach-omap2/omap_phy_internal.c
index f47813edd951..58775e3c8476 100644
--- a/arch/arm/mach-omap2/omap_phy_internal.c
+++ b/arch/arm/mach-omap2/omap_phy_internal.c
@@ -56,8 +56,10 @@ int omap4430_phy_init(struct device *dev)
 	/* Power down the phy */
 	__raw_writel(PHY_PD, ctrl_base + CONTROL_DEV_CONF);
 
-	if (!dev)
+	if (!dev) {
+		iounmap(ctrl_base);
 		return 0;
+	}
 
 	phyclk = clk_get(dev, "ocp2scp_usb_phy_ick");
 	if (IS_ERR(phyclk)) {
diff --git a/arch/arm/plat-omap/include/plat/flash.h b/arch/arm/plat-omap/include/plat/flash.h
index 3083195123ea..0d88499b79e9 100644
--- a/arch/arm/plat-omap/include/plat/flash.h
+++ b/arch/arm/plat-omap/include/plat/flash.h
@@ -11,6 +11,7 @@
 
 #include <linux/mtd/map.h>
 
+struct platform_device;
 extern void omap1_set_vpp(struct platform_device *pdev, int enable);
 
 #endif
diff --git a/arch/arm/plat-omap/include/plat/iovmm.h b/arch/arm/plat-omap/include/plat/iovmm.h
index 32a2f6c4d39e..e992b9655fbc 100644
--- a/arch/arm/plat-omap/include/plat/iovmm.h
+++ b/arch/arm/plat-omap/include/plat/iovmm.h
@@ -29,9 +29,6 @@ struct iovm_struct {
  * lower 16 bit is used for h/w and upper 16 bit is for s/w.
  */
 #define IOVMF_SW_SHIFT		16
-#define IOVMF_HW_SIZE		(1 << IOVMF_SW_SHIFT)
-#define IOVMF_HW_MASK		(IOVMF_HW_SIZE - 1)
-#define IOVMF_SW_MASK		(~IOVMF_HW_MASK)UL
 
 /*
  * iovma: h/w flags derived from cam and ram attribute
diff --git a/arch/arm/plat-omap/include/plat/mmc.h b/arch/arm/plat-omap/include/plat/mmc.h
index f38fef9f1310..c7b874186c27 100644
--- a/arch/arm/plat-omap/include/plat/mmc.h
+++ b/arch/arm/plat-omap/include/plat/mmc.h
@@ -101,6 +101,9 @@ struct omap_mmc_platform_data {
 		/* If using power_saving and the MMC power is not to go off */
 		unsigned no_off:1;
 
+		/* eMMC does not handle power off when not in sleep state */
+		unsigned no_regulator_off_init:1;
+
 		/* Regulator off remapped to sleep */
 		unsigned vcc_aux_disable_is_sleep:1;
 
diff --git a/arch/arm/plat-omap/iovmm.c b/arch/arm/plat-omap/iovmm.c
index 51ef43e8def6..83a37c54342f 100644
--- a/arch/arm/plat-omap/iovmm.c
+++ b/arch/arm/plat-omap/iovmm.c
@@ -648,7 +648,6 @@ u32 iommu_vmap(struct iommu *obj, u32 da, const struct sg_table *sgt,
 			return PTR_ERR(va);
 	}
 
-	flags &= IOVMF_HW_MASK;
 	flags |= IOVMF_DISCONT;
 	flags |= IOVMF_MMIO;
 
@@ -706,7 +705,6 @@ u32 iommu_vmalloc(struct iommu *obj, u32 da, size_t bytes, u32 flags)
 	if (!va)
 		return -ENOMEM;
 
-	flags &= IOVMF_HW_MASK;
 	flags |= IOVMF_DISCONT;
 	flags |= IOVMF_ALLOC;
 
@@ -795,7 +793,6 @@ u32 iommu_kmap(struct iommu *obj, u32 da, u32 pa, size_t bytes,
 	if (!va)
 		return -ENOMEM;
 
-	flags &= IOVMF_HW_MASK;
 	flags |= IOVMF_LINEAR;
 	flags |= IOVMF_MMIO;
 
@@ -853,7 +850,6 @@ u32 iommu_kmalloc(struct iommu *obj, u32 da, size_t bytes, u32 flags)
 		return -ENOMEM;
 	pa = virt_to_phys(va);
 
-	flags &= IOVMF_HW_MASK;
 	flags |= IOVMF_LINEAR;
 	flags |= IOVMF_ALLOC;
 
diff --git a/arch/arm/plat-omap/sram.c b/arch/arm/plat-omap/sram.c
index a3f50b34a90d..6af3d0b1f8d0 100644
--- a/arch/arm/plat-omap/sram.c
+++ b/arch/arm/plat-omap/sram.c
@@ -166,7 +166,7 @@ static void __init omap_detect_sram(void)
 		else if (cpu_is_omap1611())
 			omap_sram_size = SZ_256K;
 		else {
-			printk(KERN_ERR "Could not detect SRAM size\n");
+			pr_err("Could not detect SRAM size\n");
 			omap_sram_size = 0x4000;
 		}
 	}
@@ -221,10 +221,10 @@ static void __init omap_map_sram(void)
 	omap_sram_io_desc[0].length = ROUND_DOWN(omap_sram_size, PAGE_SIZE);
 	iotable_init(omap_sram_io_desc, ARRAY_SIZE(omap_sram_io_desc));
 
-	printk(KERN_INFO "SRAM: Mapped pa 0x%08lx to va 0x%08lx size: 0x%lx\n",
-	__pfn_to_phys(omap_sram_io_desc[0].pfn),
-	omap_sram_io_desc[0].virtual,
-	       omap_sram_io_desc[0].length);
+	pr_info("SRAM: Mapped pa 0x%08llx to va 0x%08lx size: 0x%lx\n",
+		(long long) __pfn_to_phys(omap_sram_io_desc[0].pfn),
+		omap_sram_io_desc[0].virtual,
+		omap_sram_io_desc[0].length);
 
 	/*
 	 * Normally devicemaps_init() would flush caches and tlb after
@@ -252,7 +252,7 @@ static void __init omap_map_sram(void)
 void *omap_sram_push_address(unsigned long size)
 {
 	if (size > (omap_sram_ceil - (omap_sram_base + SRAM_BOOTLOADER_SZ))) {
-		printk(KERN_ERR "Not enough space in SRAM\n");
+		pr_err("Not enough space in SRAM\n");
 		return NULL;
 	}
 
diff --git a/arch/mn10300/kernel/traps.c b/arch/mn10300/kernel/traps.c
index f03cb278828f..bd3e5e73826e 100644
--- a/arch/mn10300/kernel/traps.c
+++ b/arch/mn10300/kernel/traps.c
@@ -28,7 +28,7 @@
 #include <linux/irq.h>
 #include <asm/processor.h>
 #include <asm/system.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/io.h>
 #include <asm/atomic.h>
 #include <asm/smp.h>
@@ -156,7 +156,7 @@ int die_if_no_fixup(const char *str, struct pt_regs *regs,
 
 	case EXCEP_TRAP:
 	case EXCEP_UNIMPINS:
-		if (get_user(opcode, (uint8_t __user *)regs->pc) != 0)
+		if (probe_kernel_read(&opcode, (u8 *)regs->pc, 1) < 0)
 			break;
 		if (opcode == 0xff) {
 			if (notify_die(DIE_BREAKPOINT, str, regs, code, 0, 0))
diff --git a/arch/mn10300/kernel/vmlinux.lds.S b/arch/mn10300/kernel/vmlinux.lds.S
index 6f702a6ab395..13c4814c29f8 100644
--- a/arch/mn10300/kernel/vmlinux.lds.S
+++ b/arch/mn10300/kernel/vmlinux.lds.S
@@ -44,6 +44,7 @@ SECTIONS
   RO_DATA(PAGE_SIZE)
 
   /* writeable */
+  _sdata = .;     /* Start of rw data section */
   RW_DATA_SECTION(32, PAGE_SIZE, THREAD_SIZE)
   _edata = .;
 
diff --git a/arch/mn10300/mm/cache-dbg-flush-by-reg.S b/arch/mn10300/mm/cache-dbg-flush-by-reg.S
index 665919f2ab62..a775ea5d7cee 100644
--- a/arch/mn10300/mm/cache-dbg-flush-by-reg.S
+++ b/arch/mn10300/mm/cache-dbg-flush-by-reg.S
@@ -120,14 +120,14 @@ debugger_local_cache_flushinv_one:
 	# conditionally purge this line in all ways
 	mov	d1,(L1_CACHE_WAYDISP*0,a0)
 
-debugger_local_cache_flushinv_no_dcache:
+debugger_local_cache_flushinv_one_no_dcache:
 	#
 	# now try to flush the icache
 	#
 	mov	CHCTR,a0
 	movhu	(a0),d0
 	btst	CHCTR_ICEN,d0
-	beq	mn10300_local_icache_inv_range_reg_end
+	beq	debugger_local_cache_flushinv_one_end
 
 	LOCAL_CLI_SAVE(d1)
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 9fab2aa9c2c8..90d77bd078f5 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -89,6 +89,7 @@ config S390
 	select HAVE_GET_USER_PAGES_FAST
 	select HAVE_ARCH_MUTEX_CPU_RELAX
 	select HAVE_ARCH_JUMP_LABEL if !MARCH_G5
+	select HAVE_RCU_TABLE_FREE if SMP
 	select ARCH_INLINE_SPIN_TRYLOCK
 	select ARCH_INLINE_SPIN_TRYLOCK_BH
 	select ARCH_INLINE_SPIN_LOCK
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index f6314af3b354..38e71ebcd3c2 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -17,15 +17,15 @@
 #include <linux/gfp.h>
 #include <linux/mm.h>
 
-#define check_pgt_cache()	do {} while (0)
-
 unsigned long *crst_table_alloc(struct mm_struct *);
 void crst_table_free(struct mm_struct *, unsigned long *);
-void crst_table_free_rcu(struct mm_struct *, unsigned long *);
 
 unsigned long *page_table_alloc(struct mm_struct *);
 void page_table_free(struct mm_struct *, unsigned long *);
-void page_table_free_rcu(struct mm_struct *, unsigned long *);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+void page_table_free_rcu(struct mmu_gather *, unsigned long *);
+void __tlb_remove_table(void *_table);
+#endif
 
 static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
 {
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index e4efacfe1b63..801fbe1d837d 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -293,19 +293,6 @@ extern unsigned long VMALLOC_START;
  * swap pte is 1011 and 0001, 0011, 0101, 0111 are invalid.
  */
 
-/* Page status table bits for virtualization */
-#define RCP_ACC_BITS	0xf000000000000000UL
-#define RCP_FP_BIT	0x0800000000000000UL
-#define RCP_PCL_BIT	0x0080000000000000UL
-#define RCP_HR_BIT	0x0040000000000000UL
-#define RCP_HC_BIT	0x0020000000000000UL
-#define RCP_GR_BIT	0x0004000000000000UL
-#define RCP_GC_BIT	0x0002000000000000UL
-
-/* User dirty / referenced bit for KVM's migration feature */
-#define KVM_UR_BIT	0x0000800000000000UL
-#define KVM_UC_BIT	0x0000400000000000UL
-
 #ifndef __s390x__
 
 /* Bits in the segment table address-space-control-element */
@@ -325,6 +312,19 @@ extern unsigned long VMALLOC_START;
 #define _SEGMENT_ENTRY		(_SEGMENT_ENTRY_PTL)
 #define _SEGMENT_ENTRY_EMPTY	(_SEGMENT_ENTRY_INV)
 
+/* Page status table bits for virtualization */
+#define RCP_ACC_BITS	0xf0000000UL
+#define RCP_FP_BIT	0x08000000UL
+#define RCP_PCL_BIT	0x00800000UL
+#define RCP_HR_BIT	0x00400000UL
+#define RCP_HC_BIT	0x00200000UL
+#define RCP_GR_BIT	0x00040000UL
+#define RCP_GC_BIT	0x00020000UL
+
+/* User dirty / referenced bit for KVM's migration feature */
+#define KVM_UR_BIT	0x00008000UL
+#define KVM_UC_BIT	0x00004000UL
+
 #else /* __s390x__ */
 
 /* Bits in the segment/region table address-space-control-element */
@@ -367,6 +367,19 @@ extern unsigned long VMALLOC_START;
 #define _SEGMENT_ENTRY_LARGE	0x400	/* STE-format control, large page   */
 #define _SEGMENT_ENTRY_CO	0x100	/* change-recording override   */
 
+/* Page status table bits for virtualization */
+#define RCP_ACC_BITS	0xf000000000000000UL
+#define RCP_FP_BIT	0x0800000000000000UL
+#define RCP_PCL_BIT	0x0080000000000000UL
+#define RCP_HR_BIT	0x0040000000000000UL
+#define RCP_HC_BIT	0x0020000000000000UL
+#define RCP_GR_BIT	0x0004000000000000UL
+#define RCP_GC_BIT	0x0002000000000000UL
+
+/* User dirty / referenced bit for KVM's migration feature */
+#define KVM_UR_BIT	0x0000800000000000UL
+#define KVM_UC_BIT	0x0000400000000000UL
+
 #endif /* __s390x__ */
 
 /*
diff --git a/arch/s390/include/asm/qdio.h b/arch/s390/include/asm/qdio.h
index 350e7ee5952d..15c97625df8d 100644
--- a/arch/s390/include/asm/qdio.h
+++ b/arch/s390/include/asm/qdio.h
@@ -139,110 +139,47 @@ struct slib {
 	struct slibe slibe[QDIO_MAX_BUFFERS_PER_Q];
 } __attribute__ ((packed, aligned(2048)));
 
-/**
- * struct sbal_flags - storage block address list flags
- * @last: last entry
- * @cont: contiguous storage
- * @frag: fragmentation
- */
-struct sbal_flags {
-	u8	: 1;
-	u8 last : 1;
-	u8 cont : 1;
-	u8	: 1;
-	u8 frag : 2;
-	u8	: 2;
-} __attribute__ ((packed));
+#define SBAL_EFLAGS_LAST_ENTRY		0x40
+#define SBAL_EFLAGS_CONTIGUOUS		0x20
+#define SBAL_EFLAGS_FIRST_FRAG		0x04
+#define SBAL_EFLAGS_MIDDLE_FRAG		0x08
+#define SBAL_EFLAGS_LAST_FRAG		0x0c
+#define SBAL_EFLAGS_MASK		0x6f
 
-#define SBAL_FLAGS_FIRST_FRAG		0x04000000UL
-#define SBAL_FLAGS_MIDDLE_FRAG		0x08000000UL
-#define SBAL_FLAGS_LAST_FRAG		0x0c000000UL
-#define SBAL_FLAGS_LAST_ENTRY		0x40000000UL
-#define SBAL_FLAGS_CONTIGUOUS		0x20000000UL
-
-#define SBAL_FLAGS0_DATA_CONTINUATION	0x20UL
+#define SBAL_SFLAGS0_PCI_REQ		0x40
+#define SBAL_SFLAGS0_DATA_CONTINUATION	0x20
 
 /* Awesome OpenFCP extensions */
-#define SBAL_FLAGS0_TYPE_STATUS		0x00UL
-#define SBAL_FLAGS0_TYPE_WRITE		0x08UL
-#define SBAL_FLAGS0_TYPE_READ		0x10UL
-#define SBAL_FLAGS0_TYPE_WRITE_READ	0x18UL
-#define SBAL_FLAGS0_MORE_SBALS		0x04UL
-#define SBAL_FLAGS0_COMMAND		0x02UL
-#define SBAL_FLAGS0_LAST_SBAL		0x00UL
-#define SBAL_FLAGS0_ONLY_SBAL		SBAL_FLAGS0_COMMAND
-#define SBAL_FLAGS0_MIDDLE_SBAL		SBAL_FLAGS0_MORE_SBALS
-#define SBAL_FLAGS0_FIRST_SBAL SBAL_FLAGS0_MORE_SBALS | SBAL_FLAGS0_COMMAND
-#define SBAL_FLAGS0_PCI			0x40
-
-/**
- * struct sbal_sbalf_0 - sbal flags for sbale 0
- * @pci: PCI indicator
- * @cont: data continuation
- * @sbtype: storage-block type (FCP)
- */
-struct sbal_sbalf_0 {
-	u8	  : 1;
-	u8 pci	  : 1;
-	u8 cont   : 1;
-	u8 sbtype : 2;
-	u8	  : 3;
-} __attribute__ ((packed));
-
-/**
- * struct sbal_sbalf_1 - sbal flags for sbale 1
- * @key: storage key
- */
-struct sbal_sbalf_1 {
-	u8     : 4;
-	u8 key : 4;
-} __attribute__ ((packed));
-
-/**
- * struct sbal_sbalf_14 - sbal flags for sbale 14
- * @erridx: error index
- */
-struct sbal_sbalf_14 {
-	u8	  : 4;
-	u8 erridx : 4;
-} __attribute__ ((packed));
-
-/**
- * struct sbal_sbalf_15 - sbal flags for sbale 15
- * @reason: reason for error state
- */
-struct sbal_sbalf_15 {
-	u8 reason;
-} __attribute__ ((packed));
-
-/**
- * union sbal_sbalf - storage block address list flags
- * @i0: sbalf0
- * @i1: sbalf1
- * @i14: sbalf14
- * @i15: sblaf15
- * @value: raw value
- */
-union sbal_sbalf {
-	struct sbal_sbalf_0  i0;
-	struct sbal_sbalf_1  i1;
-	struct sbal_sbalf_14 i14;
-	struct sbal_sbalf_15 i15;
-	u8 value;
-};
+#define SBAL_SFLAGS0_TYPE_STATUS	0x00
+#define SBAL_SFLAGS0_TYPE_WRITE		0x08
+#define SBAL_SFLAGS0_TYPE_READ		0x10
+#define SBAL_SFLAGS0_TYPE_WRITE_READ	0x18
+#define SBAL_SFLAGS0_MORE_SBALS		0x04
+#define SBAL_SFLAGS0_COMMAND		0x02
+#define SBAL_SFLAGS0_LAST_SBAL		0x00
+#define SBAL_SFLAGS0_ONLY_SBAL		SBAL_SFLAGS0_COMMAND
+#define SBAL_SFLAGS0_MIDDLE_SBAL	SBAL_SFLAGS0_MORE_SBALS
+#define SBAL_SFLAGS0_FIRST_SBAL (SBAL_SFLAGS0_MORE_SBALS | SBAL_SFLAGS0_COMMAND)
 
 /**
  * struct qdio_buffer_element - SBAL entry
- * @flags: flags
+ * @eflags: SBAL entry flags
+ * @scount: SBAL count
+ * @sflags: whole SBAL flags
  * @length: length
  * @addr: address
 */
 struct qdio_buffer_element {
-	u32 flags;
+	u8 eflags;
+	/* private: */
+	u8 res1;
+	/* public: */
+	u8 scount;
+	u8 sflags;
 	u32 length;
 #ifdef CONFIG_32BIT
 	/* private: */
-	void *reserved;
+	void *res2;
 	/* public: */
 #endif
 	void *addr;
diff --git a/arch/s390/include/asm/tlb.h b/arch/s390/include/asm/tlb.h
index 77eee5477a52..c687a2c83462 100644
--- a/arch/s390/include/asm/tlb.h
+++ b/arch/s390/include/asm/tlb.h
@@ -26,67 +26,60 @@
 #include <linux/swap.h>
 #include <asm/processor.h>
 #include <asm/pgalloc.h>
-#include <asm/smp.h>
 #include <asm/tlbflush.h>
 
 struct mmu_gather {
 	struct mm_struct *mm;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	struct mmu_table_batch *batch;
+#endif
 	unsigned int fullmm;
-	unsigned int nr_ptes;
-	unsigned int nr_pxds;
-	unsigned int max;
-	void **array;
-	void *local[8];
+	unsigned int need_flush;
 };
 
-static inline void __tlb_alloc_page(struct mmu_gather *tlb)
-{
-	unsigned long addr = __get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+struct mmu_table_batch {
+	struct rcu_head		rcu;
+	unsigned int		nr;
+	void			*tables[0];
+};
 
-	if (addr) {
-		tlb->array = (void *) addr;
-		tlb->max = PAGE_SIZE / sizeof(void *);
-	}
-}
+#define MAX_TABLE_BATCH		\
+	((PAGE_SIZE - sizeof(struct mmu_table_batch)) / sizeof(void *))
+
+extern void tlb_table_flush(struct mmu_gather *tlb);
+extern void tlb_remove_table(struct mmu_gather *tlb, void *table);
+#endif
 
 static inline void tlb_gather_mmu(struct mmu_gather *tlb,
 				  struct mm_struct *mm,
 				  unsigned int full_mm_flush)
 {
 	tlb->mm = mm;
-	tlb->max = ARRAY_SIZE(tlb->local);
-	tlb->array = tlb->local;
 	tlb->fullmm = full_mm_flush;
+	tlb->need_flush = 0;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb->batch = NULL;
+#endif
 	if (tlb->fullmm)
 		__tlb_flush_mm(mm);
-	else
-		__tlb_alloc_page(tlb);
-	tlb->nr_ptes = 0;
-	tlb->nr_pxds = tlb->max;
 }
 
 static inline void tlb_flush_mmu(struct mmu_gather *tlb)
 {
-	if (!tlb->fullmm && (tlb->nr_ptes > 0 || tlb->nr_pxds < tlb->max))
-		__tlb_flush_mm(tlb->mm);
-	while (tlb->nr_ptes > 0)
-		page_table_free_rcu(tlb->mm, tlb->array[--tlb->nr_ptes]);
-	while (tlb->nr_pxds < tlb->max)
-		crst_table_free_rcu(tlb->mm, tlb->array[tlb->nr_pxds++]);
+	if (!tlb->need_flush)
+		return;
+	tlb->need_flush = 0;
+	__tlb_flush_mm(tlb->mm);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	tlb_table_flush(tlb);
+#endif
 }
 
 static inline void tlb_finish_mmu(struct mmu_gather *tlb,
 				  unsigned long start, unsigned long end)
 {
 	tlb_flush_mmu(tlb);
-
-	rcu_table_freelist_finish();
-
-	/* keep the page table cache within bounds */
-	check_pgt_cache();
-
-	if (tlb->array != tlb->local)
-		free_pages((unsigned long) tlb->array, 0);
 }
 
 /*
@@ -112,12 +105,11 @@ static inline void tlb_remove_page(struct mmu_gather *tlb, struct page *page)
 static inline void pte_free_tlb(struct mmu_gather *tlb, pgtable_t pte,
 				unsigned long address)
 {
-	if (!tlb->fullmm) {
-		tlb->array[tlb->nr_ptes++] = pte;
-		if (tlb->nr_ptes >= tlb->nr_pxds)
-			tlb_flush_mmu(tlb);
-	} else
-		page_table_free(tlb->mm, (unsigned long *) pte);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	if (!tlb->fullmm)
+		return page_table_free_rcu(tlb, (unsigned long *) pte);
+#endif
+	page_table_free(tlb->mm, (unsigned long *) pte);
 }
 
 /*
@@ -133,12 +125,11 @@ static inline void pmd_free_tlb(struct mmu_gather *tlb, pmd_t *pmd,
 #ifdef __s390x__
 	if (tlb->mm->context.asce_limit <= (1UL << 31))
 		return;
-	if (!tlb->fullmm) {
-		tlb->array[--tlb->nr_pxds] = pmd;
-		if (tlb->nr_ptes >= tlb->nr_pxds)
-			tlb_flush_mmu(tlb);
-	} else
-		crst_table_free(tlb->mm, (unsigned long *) pmd);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	if (!tlb->fullmm)
+		return tlb_remove_table(tlb, pmd);
+#endif
+	crst_table_free(tlb->mm, (unsigned long *) pmd);
 #endif
 }
 
@@ -155,12 +146,11 @@ static inline void pud_free_tlb(struct mmu_gather *tlb, pud_t *pud,
 #ifdef __s390x__
 	if (tlb->mm->context.asce_limit <= (1UL << 42))
 		return;
-	if (!tlb->fullmm) {
-		tlb->array[--tlb->nr_pxds] = pud;
-		if (tlb->nr_ptes >= tlb->nr_pxds)
-			tlb_flush_mmu(tlb);
-	} else
-		crst_table_free(tlb->mm, (unsigned long *) pud);
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+	if (!tlb->fullmm)
+		return tlb_remove_table(tlb, pud);
+#endif
+	crst_table_free(tlb->mm, (unsigned long *) pud);
 #endif
 }
 
diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 30ca85cce314..67345ae7ce8d 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -731,6 +731,7 @@ static int __init kvm_s390_init(void)
 	}
 	memcpy(facilities, S390_lowcore.stfle_fac_list, 16);
 	facilities[0] &= 0xff00fff3f47c0000ULL;
+	facilities[1] &= 0x201c000000000000ULL;
 	return 0;
 }
 
diff --git a/arch/s390/kvm/sie64a.S b/arch/s390/kvm/sie64a.S
index ab0e041ac54c..5faa1b1b23fa 100644
--- a/arch/s390/kvm/sie64a.S
+++ b/arch/s390/kvm/sie64a.S
@@ -93,4 +93,6 @@ sie_err:
 
 	.section __ex_table,"a"
 	.quad	sie_inst,sie_err
+	.quad	sie_exit,sie_err
+	.quad	sie_reenter,sie_err
 	.previous
diff --git a/arch/s390/mm/pgtable.c b/arch/s390/mm/pgtable.c
index b09763fe5da1..37a23c223705 100644
--- a/arch/s390/mm/pgtable.c
+++ b/arch/s390/mm/pgtable.c
@@ -24,94 +24,12 @@
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
 
-struct rcu_table_freelist {
-	struct rcu_head rcu;
-	struct mm_struct *mm;
-	unsigned int pgt_index;
-	unsigned int crst_index;
-	unsigned long *table[0];
-};
-
-#define RCU_FREELIST_SIZE \
-	((PAGE_SIZE - sizeof(struct rcu_table_freelist)) \
-	  / sizeof(unsigned long))
-
-static DEFINE_PER_CPU(struct rcu_table_freelist *, rcu_table_freelist);
-
-static void __page_table_free(struct mm_struct *mm, unsigned long *table);
-
-static struct rcu_table_freelist *rcu_table_freelist_get(struct mm_struct *mm)
-{
-	struct rcu_table_freelist **batchp = &__get_cpu_var(rcu_table_freelist);
-	struct rcu_table_freelist *batch = *batchp;
-
-	if (batch)
-		return batch;
-	batch = (struct rcu_table_freelist *) __get_free_page(GFP_ATOMIC);
-	if (batch) {
-		batch->mm = mm;
-		batch->pgt_index = 0;
-		batch->crst_index = RCU_FREELIST_SIZE;
-		*batchp = batch;
-	}
-	return batch;
-}
-
-static void rcu_table_freelist_callback(struct rcu_head *head)
-{
-	struct rcu_table_freelist *batch =
-		container_of(head, struct rcu_table_freelist, rcu);
-
-	while (batch->pgt_index > 0)
-		__page_table_free(batch->mm, batch->table[--batch->pgt_index]);
-	while (batch->crst_index < RCU_FREELIST_SIZE)
-		crst_table_free(batch->mm, batch->table[batch->crst_index++]);
-	free_page((unsigned long) batch);
-}
-
-void rcu_table_freelist_finish(void)
-{
-	struct rcu_table_freelist **batchp = &get_cpu_var(rcu_table_freelist);
-	struct rcu_table_freelist *batch = *batchp;
-
-	if (!batch)
-		goto out;
-	call_rcu(&batch->rcu, rcu_table_freelist_callback);
-	*batchp = NULL;
-out:
-	put_cpu_var(rcu_table_freelist);
-}
-
-static void smp_sync(void *arg)
-{
-}
-
 #ifndef CONFIG_64BIT
 #define ALLOC_ORDER	1
-#define TABLES_PER_PAGE	4
-#define FRAG_MASK	15UL
-#define SECOND_HALVES	10UL
-
-void clear_table_pgstes(unsigned long *table)
-{
-	clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
-	memset(table + 256, 0, PAGE_SIZE/4);
-	clear_table(table + 512, _PAGE_TYPE_EMPTY, PAGE_SIZE/4);
-	memset(table + 768, 0, PAGE_SIZE/4);
-}
-
+#define FRAG_MASK	0x0f
 #else
 #define ALLOC_ORDER	2
-#define TABLES_PER_PAGE	2
-#define FRAG_MASK	3UL
-#define SECOND_HALVES	2UL
-
-void clear_table_pgstes(unsigned long *table)
-{
-	clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2);
-	memset(table + 256, 0, PAGE_SIZE/2);
-}
-
+#define FRAG_MASK	0x03
 #endif
 
 unsigned long VMALLOC_START = VMALLOC_END - VMALLOC_SIZE;
@@ -140,29 +58,6 @@ void crst_table_free(struct mm_struct *mm, unsigned long *table)
 	free_pages((unsigned long) table, ALLOC_ORDER);
 }
 
-void crst_table_free_rcu(struct mm_struct *mm, unsigned long *table)
-{
-	struct rcu_table_freelist *batch;
-
-	preempt_disable();
-	if (atomic_read(&mm->mm_users) < 2 &&
-	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
-		crst_table_free(mm, table);
-		goto out;
-	}
-	batch = rcu_table_freelist_get(mm);
-	if (!batch) {
-		smp_call_function(smp_sync, NULL, 1);
-		crst_table_free(mm, table);
-		goto out;
-	}
-	batch->table[--batch->crst_index] = table;
-	if (batch->pgt_index >= batch->crst_index)
-		rcu_table_freelist_finish();
-out:
-	preempt_enable();
-}
-
 #ifdef CONFIG_64BIT
 int crst_table_upgrade(struct mm_struct *mm, unsigned long limit)
 {
@@ -238,124 +133,175 @@ void crst_table_downgrade(struct mm_struct *mm, unsigned long limit)
 }
 #endif
 
+static inline unsigned int atomic_xor_bits(atomic_t *v, unsigned int bits)
+{
+	unsigned int old, new;
+
+	do {
+		old = atomic_read(v);
+		new = old ^ bits;
+	} while (atomic_cmpxchg(v, old, new) != old);
+	return new;
+}
+
 /*
  * page table entry allocation/free routines.
  */
+#ifdef CONFIG_PGSTE
+static inline unsigned long *page_table_alloc_pgste(struct mm_struct *mm)
+{
+	struct page *page;
+	unsigned long *table;
+
+	page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
+	if (!page)
+		return NULL;
+	pgtable_page_ctor(page);
+	atomic_set(&page->_mapcount, 3);
+	table = (unsigned long *) page_to_phys(page);
+	clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE/2);
+	clear_table(table + PTRS_PER_PTE, 0, PAGE_SIZE/2);
+	return table;
+}
+
+static inline void page_table_free_pgste(unsigned long *table)
+{
+	struct page *page;
+
+	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	pgtable_page_ctor(page);
+	atomic_set(&page->_mapcount, -1);
+	__free_page(page);
+}
+#endif
+
 unsigned long *page_table_alloc(struct mm_struct *mm)
 {
 	struct page *page;
 	unsigned long *table;
-	unsigned long bits;
+	unsigned int mask, bit;
 
-	bits = (mm->context.has_pgste) ? 3UL : 1UL;
+#ifdef CONFIG_PGSTE
+	if (mm_has_pgste(mm))
+		return page_table_alloc_pgste(mm);
+#endif
+	/* Allocate fragments of a 4K page as 1K/2K page table */
 	spin_lock_bh(&mm->context.list_lock);
-	page = NULL;
+	mask = FRAG_MASK;
 	if (!list_empty(&mm->context.pgtable_list)) {
 		page = list_first_entry(&mm->context.pgtable_list,
 					struct page, lru);
-		if ((page->flags & FRAG_MASK) == ((1UL << TABLES_PER_PAGE) - 1))
-			page = NULL;
+		table = (unsigned long *) page_to_phys(page);
+		mask = atomic_read(&page->_mapcount);
+		mask = mask | (mask >> 4);
 	}
-	if (!page) {
+	if ((mask & FRAG_MASK) == FRAG_MASK) {
 		spin_unlock_bh(&mm->context.list_lock);
 		page = alloc_page(GFP_KERNEL|__GFP_REPEAT);
 		if (!page)
 			return NULL;
 		pgtable_page_ctor(page);
-		page->flags &= ~FRAG_MASK;
+		atomic_set(&page->_mapcount, 1);
 		table = (unsigned long *) page_to_phys(page);
-		if (mm->context.has_pgste)
-			clear_table_pgstes(table);
-		else
-			clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
+		clear_table(table, _PAGE_TYPE_EMPTY, PAGE_SIZE);
 		spin_lock_bh(&mm->context.list_lock);
 		list_add(&page->lru, &mm->context.pgtable_list);
+	} else {
+		for (bit = 1; mask & bit; bit <<= 1)
+			table += PTRS_PER_PTE;
+		mask = atomic_xor_bits(&page->_mapcount, bit);
+		if ((mask & FRAG_MASK) == FRAG_MASK)
+			list_del(&page->lru);
 	}
-	table = (unsigned long *) page_to_phys(page);
-	while (page->flags & bits) {
-		table += 256;
-		bits <<= 1;
-	}
-	page->flags |= bits;
-	if ((page->flags & FRAG_MASK) == ((1UL << TABLES_PER_PAGE) - 1))
-		list_move_tail(&page->lru, &mm->context.pgtable_list);
 	spin_unlock_bh(&mm->context.list_lock);
 	return table;
 }
 
-static void __page_table_free(struct mm_struct *mm, unsigned long *table)
-{
-	struct page *page;
-	unsigned long bits;
-
-	bits = ((unsigned long) table) & 15;
-	table = (unsigned long *)(((unsigned long) table) ^ bits);
-	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
-	page->flags ^= bits;
-	if (!(page->flags & FRAG_MASK)) {
-		pgtable_page_dtor(page);
-		__free_page(page);
-	}
-}
-
 void page_table_free(struct mm_struct *mm, unsigned long *table)
 {
 	struct page *page;
-	unsigned long bits;
+	unsigned int bit, mask;
 
-	bits = (mm->context.has_pgste) ? 3UL : 1UL;
-	bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
+#ifdef CONFIG_PGSTE
+	if (mm_has_pgste(mm))
+		return page_table_free_pgste(table);
+#endif
+	/* Free 1K/2K page table fragment of a 4K page */
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t)));
 	spin_lock_bh(&mm->context.list_lock);
-	page->flags ^= bits;
-	if (page->flags & FRAG_MASK) {
-		/* Page now has some free pgtable fragments. */
-		if (!list_empty(&page->lru))
-			list_move(&page->lru, &mm->context.pgtable_list);
-		page = NULL;
-	} else
-		/* All fragments of the 4K page have been freed. */
+	if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK)
 		list_del(&page->lru);
+	mask = atomic_xor_bits(&page->_mapcount, bit);
+	if (mask & FRAG_MASK)
+		list_add(&page->lru, &mm->context.pgtable_list);
 	spin_unlock_bh(&mm->context.list_lock);
-	if (page) {
+	if (mask == 0) {
 		pgtable_page_dtor(page);
+		atomic_set(&page->_mapcount, -1);
 		__free_page(page);
 	}
 }
 
-void page_table_free_rcu(struct mm_struct *mm, unsigned long *table)
-{
-	struct rcu_table_freelist *batch;
-	struct page *page;
-	unsigned long bits;
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
 
-	preempt_disable();
-	if (atomic_read(&mm->mm_users) < 2 &&
-	    cpumask_equal(mm_cpumask(mm), cpumask_of(smp_processor_id()))) {
-		page_table_free(mm, table);
-		goto out;
+static void __page_table_free_rcu(void *table, unsigned bit)
+{
+	struct page *page;
+
+#ifdef CONFIG_PGSTE
+	if (bit == FRAG_MASK)
+		return page_table_free_pgste(table);
+#endif
+	/* Free 1K/2K page table fragment of a 4K page */
+	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
+	if (atomic_xor_bits(&page->_mapcount, bit) == 0) {
+		pgtable_page_dtor(page);
+		atomic_set(&page->_mapcount, -1);
+		__free_page(page);
 	}
-	batch = rcu_table_freelist_get(mm);
-	if (!batch) {
-		smp_call_function(smp_sync, NULL, 1);
-		page_table_free(mm, table);
-		goto out;
+}
+
+void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table)
+{
+	struct mm_struct *mm;
+	struct page *page;
+	unsigned int bit, mask;
+
+	mm = tlb->mm;
+#ifdef CONFIG_PGSTE
+	if (mm_has_pgste(mm)) {
+		table = (unsigned long *) (__pa(table) | FRAG_MASK);
+		tlb_remove_table(tlb, table);
+		return;
 	}
-	bits = (mm->context.has_pgste) ? 3UL : 1UL;
-	bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
+#endif
+	bit = 1 << ((__pa(table) & ~PAGE_MASK) / (PTRS_PER_PTE*sizeof(pte_t)));
 	page = pfn_to_page(__pa(table) >> PAGE_SHIFT);
 	spin_lock_bh(&mm->context.list_lock);
-	/* Delayed freeing with rcu prevents reuse of pgtable fragments */
-	list_del_init(&page->lru);
+	if ((atomic_read(&page->_mapcount) & FRAG_MASK) != FRAG_MASK)
+		list_del(&page->lru);
+	mask = atomic_xor_bits(&page->_mapcount, bit | (bit << 4));
+	if (mask & FRAG_MASK)
+		list_add_tail(&page->lru, &mm->context.pgtable_list);
 	spin_unlock_bh(&mm->context.list_lock);
-	table = (unsigned long *)(((unsigned long) table) | bits);
-	batch->table[batch->pgt_index++] = table;
-	if (batch->pgt_index >= batch->crst_index)
-		rcu_table_freelist_finish();
-out:
-	preempt_enable();
+	table = (unsigned long *) (__pa(table) | (bit << 4));
+	tlb_remove_table(tlb, table);
 }
 
+void __tlb_remove_table(void *_table)
+{
+	void *table = (void *)((unsigned long) _table & PAGE_MASK);
+	unsigned type = (unsigned long) _table & ~PAGE_MASK;
+
+	if (type)
+		__page_table_free_rcu(table, type);
+	else
+		free_pages((unsigned long) table, ALLOC_ORDER);
+}
+
+#endif
+
 /*
  * switch on pgstes for its userspace process (for kvm)
  */
@@ -369,7 +315,7 @@ int s390_enable_sie(void)
 		return -EINVAL;
 
 	/* Do we have pgstes? if yes, we are done */
-	if (tsk->mm->context.has_pgste)
+	if (mm_has_pgste(tsk->mm))
 		return 0;
 
 	/* lets check if we are allowed to replace the mm */
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index cd8cbeb5fa34..7c3a95e54ec5 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -30,6 +30,7 @@
 #include <asm/proto.h>
 #include <asm/iommu.h>
 #include <asm/gart.h>
+#include <asm/dma.h>
 #include <asm/amd_iommu_proto.h>
 #include <asm/amd_iommu_types.h>
 #include <asm/amd_iommu.h>
@@ -154,6 +155,10 @@ static int iommu_init_device(struct device *dev)
 	pdev = pci_get_bus_and_slot(PCI_BUS(alias), alias & 0xff);
 	if (pdev)
 		dev_data->alias = &pdev->dev;
+	else {
+		kfree(dev_data);
+		return -ENOTSUPP;
+	}
 
 	atomic_set(&dev_data->bind, 0);
 
@@ -163,6 +168,20 @@ static int iommu_init_device(struct device *dev)
 	return 0;
 }
 
+static void iommu_ignore_device(struct device *dev)
+{
+	u16 devid, alias;
+
+	devid = get_device_id(dev);
+	alias = amd_iommu_alias_table[devid];
+
+	memset(&amd_iommu_dev_table[devid], 0, sizeof(struct dev_table_entry));
+	memset(&amd_iommu_dev_table[alias], 0, sizeof(struct dev_table_entry));
+
+	amd_iommu_rlookup_table[devid] = NULL;
+	amd_iommu_rlookup_table[alias] = NULL;
+}
+
 static void iommu_uninit_device(struct device *dev)
 {
 	kfree(dev->archdata.iommu);
@@ -192,7 +211,9 @@ int __init amd_iommu_init_devices(void)
 			continue;
 
 		ret = iommu_init_device(&pdev->dev);
-		if (ret)
+		if (ret == -ENOTSUPP)
+			iommu_ignore_device(&pdev->dev);
+		else if (ret)
 			goto out_free;
 	}
 
@@ -2383,6 +2404,23 @@ static struct dma_map_ops amd_iommu_dma_ops = {
 	.dma_supported = amd_iommu_dma_supported,
 };
 
+static unsigned device_dma_ops_init(void)
+{
+	struct pci_dev *pdev = NULL;
+	unsigned unhandled = 0;
+
+	for_each_pci_dev(pdev) {
+		if (!check_device(&pdev->dev)) {
+			unhandled += 1;
+			continue;
+		}
+
+		pdev->dev.archdata.dma_ops = &amd_iommu_dma_ops;
+	}
+
+	return unhandled;
+}
+
 /*
  * The function which clues the AMD IOMMU driver into dma_ops.
  */
@@ -2395,7 +2433,7 @@ void __init amd_iommu_init_api(void)
 int __init amd_iommu_init_dma_ops(void)
 {
 	struct amd_iommu *iommu;
-	int ret;
+	int ret, unhandled;
 
 	/*
 	 * first allocate a default protection domain for every IOMMU we
@@ -2421,7 +2459,11 @@ int __init amd_iommu_init_dma_ops(void)
 	swiotlb = 0;
 
 	/* Make the driver finally visible to the drivers */
-	dma_ops = &amd_iommu_dma_ops;
+	unhandled = device_dma_ops_init();
+	if (unhandled && max_pfn > MAX_DMA32_PFN) {
+		/* There are unhandled devices - initialize swiotlb for them */
+		swiotlb = 1;
+	}
 
 	amd_iommu_stats_init();
 
diff --git a/arch/x86/kernel/amd_iommu_init.c b/arch/x86/kernel/amd_iommu_init.c
index 9179c21120a8..bfc8453bd98d 100644
--- a/arch/x86/kernel/amd_iommu_init.c
+++ b/arch/x86/kernel/amd_iommu_init.c
@@ -731,8 +731,8 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 {
 	u8 *p = (u8 *)h;
 	u8 *end = p, flags = 0;
-	u16 dev_i, devid = 0, devid_start = 0, devid_to = 0;
-	u32 ext_flags = 0;
+	u16 devid = 0, devid_start = 0, devid_to = 0;
+	u32 dev_i, ext_flags = 0;
 	bool alias = false;
 	struct ivhd_entry *e;
 
@@ -887,7 +887,7 @@ static void __init init_iommu_from_acpi(struct amd_iommu *iommu,
 /* Initializes the device->iommu mapping for the driver */
 static int __init init_iommu_devices(struct amd_iommu *iommu)
 {
-	u16 i;
+	u32 i;
 
 	for (i = iommu->first_device; i <= iommu->last_device; ++i)
 		set_iommu_for_device(iommu, i);
@@ -1177,7 +1177,7 @@ static int __init init_memory_definitions(struct acpi_table_header *table)
  */
 static void init_device_table(void)
 {
-	u16 devid;
+	u32 devid;
 
 	for (devid = 0; devid <= amd_iommu_last_bdf; ++devid) {
 		set_dev_entry_bit(devid, DEV_ENTRY_VALID);
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index d6e2477feb18..6df88c7885c0 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -47,38 +47,40 @@
 #define DstDI       (5<<1)	/* Destination is in ES:(E)DI */
 #define DstMem64    (6<<1)	/* 64bit memory operand */
 #define DstImmUByte (7<<1)	/* 8-bit unsigned immediate operand */
-#define DstMask     (7<<1)
+#define DstDX       (8<<1)	/* Destination is in DX register */
+#define DstMask     (0xf<<1)
 /* Source operand type. */
-#define SrcNone     (0<<4)	/* No source operand. */
-#define SrcReg      (1<<4)	/* Register operand. */
-#define SrcMem      (2<<4)	/* Memory operand. */
-#define SrcMem16    (3<<4)	/* Memory operand (16-bit). */
-#define SrcMem32    (4<<4)	/* Memory operand (32-bit). */
-#define SrcImm      (5<<4)	/* Immediate operand. */
-#define SrcImmByte  (6<<4)	/* 8-bit sign-extended immediate operand. */
-#define SrcOne      (7<<4)	/* Implied '1' */
-#define SrcImmUByte (8<<4)      /* 8-bit unsigned immediate operand. */
-#define SrcImmU     (9<<4)      /* Immediate operand, unsigned */
-#define SrcSI       (0xa<<4)	/* Source is in the DS:RSI */
-#define SrcImmFAddr (0xb<<4)	/* Source is immediate far address */
-#define SrcMemFAddr (0xc<<4)	/* Source is far address in memory */
-#define SrcAcc      (0xd<<4)	/* Source Accumulator */
-#define SrcImmU16   (0xe<<4)    /* Immediate operand, unsigned, 16 bits */
-#define SrcMask     (0xf<<4)
+#define SrcNone     (0<<5)	/* No source operand. */
+#define SrcReg      (1<<5)	/* Register operand. */
+#define SrcMem      (2<<5)	/* Memory operand. */
+#define SrcMem16    (3<<5)	/* Memory operand (16-bit). */
+#define SrcMem32    (4<<5)	/* Memory operand (32-bit). */
+#define SrcImm      (5<<5)	/* Immediate operand. */
+#define SrcImmByte  (6<<5)	/* 8-bit sign-extended immediate operand. */
+#define SrcOne      (7<<5)	/* Implied '1' */
+#define SrcImmUByte (8<<5)      /* 8-bit unsigned immediate operand. */
+#define SrcImmU     (9<<5)      /* Immediate operand, unsigned */
+#define SrcSI       (0xa<<5)	/* Source is in the DS:RSI */
+#define SrcImmFAddr (0xb<<5)	/* Source is immediate far address */
+#define SrcMemFAddr (0xc<<5)	/* Source is far address in memory */
+#define SrcAcc      (0xd<<5)	/* Source Accumulator */
+#define SrcImmU16   (0xe<<5)    /* Immediate operand, unsigned, 16 bits */
+#define SrcDX       (0xf<<5)	/* Source is in DX register */
+#define SrcMask     (0xf<<5)
 /* Generic ModRM decode. */
-#define ModRM       (1<<8)
+#define ModRM       (1<<9)
 /* Destination is only written; never read. */
-#define Mov         (1<<9)
-#define BitOp       (1<<10)
-#define MemAbs      (1<<11)      /* Memory operand is absolute displacement */
-#define String      (1<<12)     /* String instruction (rep capable) */
-#define Stack       (1<<13)     /* Stack instruction (push/pop) */
-#define GroupMask   (7<<14)     /* Opcode uses one of the group mechanisms */
-#define Group       (1<<14)     /* Bits 3:5 of modrm byte extend opcode */
-#define GroupDual   (2<<14)     /* Alternate decoding of mod == 3 */
-#define Prefix      (3<<14)     /* Instruction varies with 66/f2/f3 prefix */
-#define RMExt       (4<<14)     /* Opcode extension in ModRM r/m if mod == 3 */
-#define Sse         (1<<17)     /* SSE Vector instruction */
+#define Mov         (1<<10)
+#define BitOp       (1<<11)
+#define MemAbs      (1<<12)      /* Memory operand is absolute displacement */
+#define String      (1<<13)     /* String instruction (rep capable) */
+#define Stack       (1<<14)     /* Stack instruction (push/pop) */
+#define GroupMask   (7<<15)     /* Opcode uses one of the group mechanisms */
+#define Group       (1<<15)     /* Bits 3:5 of modrm byte extend opcode */
+#define GroupDual   (2<<15)     /* Alternate decoding of mod == 3 */
+#define Prefix      (3<<15)     /* Instruction varies with 66/f2/f3 prefix */
+#define RMExt       (4<<15)     /* Opcode extension in ModRM r/m if mod == 3 */
+#define Sse         (1<<18)     /* SSE Vector instruction */
 /* Misc flags */
 #define Prot        (1<<21) /* instruction generates #UD if not in prot-mode */
 #define VendorSpecific (1<<22) /* Vendor specific instruction */
@@ -3154,8 +3156,8 @@ static struct opcode opcode_table[256] = {
 	I(DstReg | SrcMem | ModRM | Src2Imm, em_imul_3op),
 	I(SrcImmByte | Mov | Stack, em_push),
 	I(DstReg | SrcMem | ModRM | Src2ImmByte, em_imul_3op),
-	D2bvIP(DstDI | Mov | String, ins, check_perm_in), /* insb, insw/insd */
-	D2bvIP(SrcSI | ImplicitOps | String, outs, check_perm_out), /* outsb, outsw/outsd */
+	D2bvIP(DstDI | SrcDX | Mov | String, ins, check_perm_in), /* insb, insw/insd */
+	D2bvIP(SrcSI | DstDX | String, outs, check_perm_out), /* outsb, outsw/outsd */
 	/* 0x70 - 0x7F */
 	X16(D(SrcImmByte)),
 	/* 0x80 - 0x87 */
@@ -3212,8 +3214,8 @@ static struct opcode opcode_table[256] = {
 	/* 0xE8 - 0xEF */
 	D(SrcImm | Stack), D(SrcImm | ImplicitOps),
 	D(SrcImmFAddr | No64), D(SrcImmByte | ImplicitOps),
-	D2bvIP(SrcNone | DstAcc,     in,  check_perm_in),
-	D2bvIP(SrcAcc | ImplicitOps, out, check_perm_out),
+	D2bvIP(SrcDX | DstAcc, in,  check_perm_in),
+	D2bvIP(SrcAcc | DstDX, out, check_perm_out),
 	/* 0xF0 - 0xF7 */
 	N, DI(ImplicitOps, icebp), N, N,
 	DI(ImplicitOps | Priv, hlt), D(ImplicitOps),
@@ -3613,6 +3615,12 @@ done_prefixes:
 		memop.bytes = c->op_bytes + 2;
 		goto srcmem_common;
 		break;
+	case SrcDX:
+		c->src.type = OP_REG;
+		c->src.bytes = 2;
+		c->src.addr.reg = &c->regs[VCPU_REGS_RDX];
+		fetch_register_operand(&c->src);
+		break;
 	}
 
 	if (rc != X86EMUL_CONTINUE)
@@ -3682,6 +3690,12 @@ done_prefixes:
 		c->dst.addr.mem.seg = VCPU_SREG_ES;
 		c->dst.val = 0;
 		break;
+	case DstDX:
+		c->dst.type = OP_REG;
+		c->dst.bytes = 2;
+		c->dst.addr.reg = &c->regs[VCPU_REGS_RDX];
+		fetch_register_operand(&c->dst);
+		break;
 	case ImplicitOps:
 		/* Special instructions do their own operand decoding. */
 	default:
@@ -4027,7 +4041,6 @@ special_insn:
 		break;
 	case 0xec: /* in al,dx */
 	case 0xed: /* in (e/r)ax,dx */
-		c->src.val = c->regs[VCPU_REGS_RDX];
 	do_io_in:
 		if (!pio_in_emulated(ctxt, ops, c->dst.bytes, c->src.val,
 				     &c->dst.val))
@@ -4035,7 +4048,6 @@ special_insn:
 		break;
 	case 0xee: /* out dx,al */
 	case 0xef: /* out dx,(e/r)ax */
-		c->dst.val = c->regs[VCPU_REGS_RDX];
 	do_io_out:
 		ops->pio_out_emulated(ctxt, c->src.bytes, c->dst.val,
 				      &c->src.val, 1);
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 4a7f63143455..2967002a9f82 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -87,32 +87,20 @@ config GPIO_IT8761E
 	  Say yes here to support GPIO functionality of IT8761E super I/O chip.
 
 config GPIO_EXYNOS4
-	bool "Samsung Exynos4 GPIO library support"
-	default y if CPU_EXYNOS4210
-	depends on ARM
-	help
-	  Say yes here to support Samsung Exynos4 series SoCs GPIO library
+	def_bool y
+	depends on CPU_EXYNOS4210
 
 config GPIO_PLAT_SAMSUNG
-	bool "Samsung SoCs GPIO library support"
-	default y if SAMSUNG_GPIOLIB_4BIT
-	depends on ARM
-	help
-	  Say yes here to support Samsung SoCs GPIO library
+	def_bool y
+	depends on SAMSUNG_GPIOLIB_4BIT
 
 config GPIO_S5PC100
-	bool "Samsung S5PC100 GPIO library support"
-	default y if CPU_S5PC100
-	depends on ARM
-	help
-	  Say yes here to support Samsung S5PC100 SoCs GPIO library
+	def_bool y
+	depends on CPU_S5PC100
 
 config GPIO_S5PV210
-	bool "Samsung S5PV210/S5PC110 GPIO library support"
-	default y if CPU_S5PV210
-	depends on ARM
-	help
-	  Say yes here to support Samsung S5PV210/S5PC110 SoCs GPIO library
+	def_bool y
+	depends on CPU_S5PV210
 
 config GPIO_PL061
 	bool "PrimeCell PL061 GPIO support"
diff --git a/drivers/gpio/gpio-exynos4.c b/drivers/gpio/gpio-exynos4.c
index d54ca6adb660..9029835112e7 100644
--- a/drivers/gpio/gpio-exynos4.c
+++ b/drivers/gpio/gpio-exynos4.c
@@ -21,16 +21,37 @@
 #include <plat/gpio-cfg.h>
 #include <plat/gpio-cfg-helpers.h>
 
+int s3c_gpio_setpull_exynos4(struct s3c_gpio_chip *chip,
+				unsigned int off, s3c_gpio_pull_t pull)
+{
+	if (pull == S3C_GPIO_PULL_UP)
+		pull = 3;
+
+	return s3c_gpio_setpull_updown(chip, off, pull);
+}
+
+s3c_gpio_pull_t s3c_gpio_getpull_exynos4(struct s3c_gpio_chip *chip,
+						unsigned int off)
+{
+	s3c_gpio_pull_t pull;
+
+	pull = s3c_gpio_getpull_updown(chip, off);
+	if (pull == 3)
+		pull = S3C_GPIO_PULL_UP;
+
+	return pull;
+}
+
 static struct s3c_gpio_cfg gpio_cfg = {
 	.set_config	= s3c_gpio_setcfg_s3c64xx_4bit,
-	.set_pull	= s3c_gpio_setpull_updown,
-	.get_pull	= s3c_gpio_getpull_updown,
+	.set_pull	= s3c_gpio_setpull_exynos4,
+	.get_pull	= s3c_gpio_getpull_exynos4,
 };
 
 static struct s3c_gpio_cfg gpio_cfg_noint = {
 	.set_config	= s3c_gpio_setcfg_s3c64xx_4bit,
-	.set_pull	= s3c_gpio_setpull_updown,
-	.get_pull	= s3c_gpio_getpull_updown,
+	.set_pull	= s3c_gpio_setpull_exynos4,
+	.get_pull	= s3c_gpio_getpull_exynos4,
 };
 
 /*
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index 6c51191da567..01f74a8459d9 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -432,7 +432,6 @@ static inline void set_24xx_gpio_triggering(struct gpio_bank *bank, int gpio,
 {
 	void __iomem *base = bank->base;
 	u32 gpio_bit = 1 << gpio;
-	u32 val;
 
 	if (cpu_is_omap44xx()) {
 		MOD_REG_BIT(OMAP4_GPIO_LEVELDETECT0, gpio_bit,
@@ -455,15 +454,8 @@ static inline void set_24xx_gpio_triggering(struct gpio_bank *bank, int gpio,
 	}
 	if (likely(!(bank->non_wakeup_gpios & gpio_bit))) {
 		if (cpu_is_omap44xx()) {
-			if (trigger != 0)
-				__raw_writel(1 << gpio, bank->base+
-						OMAP4_GPIO_IRQWAKEN0);
-			else {
-				val = __raw_readl(bank->base +
-							OMAP4_GPIO_IRQWAKEN0);
-				__raw_writel(val & (~(1 << gpio)), bank->base +
-							 OMAP4_GPIO_IRQWAKEN0);
-			}
+			MOD_REG_BIT(OMAP4_GPIO_IRQWAKEN0, gpio_bit,
+				trigger != 0);
 		} else {
 			/*
 			 * GPIO wakeup request can only be generated on edge
@@ -1134,8 +1126,11 @@ static void gpio_irq_shutdown(struct irq_data *d)
 {
 	unsigned int gpio = d->irq - IH_GPIO_BASE;
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
 
+	spin_lock_irqsave(&bank->lock, flags);
 	_reset_gpio(bank, gpio);
+	spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static void gpio_ack_irq(struct irq_data *d)
@@ -1150,9 +1145,12 @@ static void gpio_mask_irq(struct irq_data *d)
 {
 	unsigned int gpio = d->irq - IH_GPIO_BASE;
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
+	unsigned long flags;
 
+	spin_lock_irqsave(&bank->lock, flags);
 	_set_gpio_irqenable(bank, gpio, 0);
 	_set_gpio_triggering(bank, get_gpio_index(gpio), IRQ_TYPE_NONE);
+	spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static void gpio_unmask_irq(struct irq_data *d)
@@ -1161,7 +1159,9 @@ static void gpio_unmask_irq(struct irq_data *d)
 	struct gpio_bank *bank = irq_data_get_irq_chip_data(d);
 	unsigned int irq_mask = 1 << get_gpio_index(gpio);
 	u32 trigger = irqd_get_trigger_type(d);
+	unsigned long flags;
 
+	spin_lock_irqsave(&bank->lock, flags);
 	if (trigger)
 		_set_gpio_triggering(bank, get_gpio_index(gpio), trigger);
 
@@ -1173,6 +1173,7 @@ static void gpio_unmask_irq(struct irq_data *d)
 	}
 
 	_set_gpio_irqenable(bank, gpio, 1);
+	spin_unlock_irqrestore(&bank->lock, flags);
 }
 
 static struct irq_chip gpio_irq_chip = {
@@ -1524,7 +1525,7 @@ static void omap_gpio_mod_init(struct gpio_bank *bank, int id)
 	}
 }
 
-static void __init omap_gpio_chip_init(struct gpio_bank *bank)
+static void __devinit omap_gpio_chip_init(struct gpio_bank *bank)
 {
 	int j;
 	static int gpio;
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 51c2257b11e6..4d46441cbe2d 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -776,7 +776,7 @@ static int i915_error_state(struct seq_file *m, void *unused)
 	seq_printf(m, "  INSTPM: 0x%08x\n", error->instpm);
 	seq_printf(m, "  seqno: 0x%08x\n", error->seqno);
 
-	for (i = 0; i < 16; i++)
+	for (i = 0; i < dev_priv->num_fence_regs; i++)
 		seq_printf(m, "  fence[%d] = %08llx\n", i, error->fence[i]);
 
 	if (error->active_bo)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index ee660355ae68..f63ee162f124 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -716,6 +716,7 @@ typedef struct drm_i915_private {
 	struct intel_fbdev *fbdev;
 
 	struct drm_property *broadcast_rgb_property;
+	struct drm_property *force_audio_property;
 
 	atomic_t forcewake_count;
 } drm_i915_private_t;
@@ -909,13 +910,6 @@ struct drm_i915_file_private {
 	} mm;
 };
 
-enum intel_chip_family {
-	CHIP_I8XX = 0x01,
-	CHIP_I9XX = 0x02,
-	CHIP_I915 = 0x04,
-	CHIP_I965 = 0x08,
-};
-
 #define INTEL_INFO(dev)	(((struct drm_i915_private *) (dev)->dev_private)->info)
 
 #define IS_I830(dev)		((dev)->pci_device == 0x3577)
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 0b2e167d2bce..12d32579b951 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -354,7 +354,7 @@ i915_gem_shmem_pread_fast(struct drm_device *dev,
 		 * page_offset = offset within page
 		 * page_length = bytes to copy for this page
 		 */
-		page_offset = offset & (PAGE_SIZE-1);
+		page_offset = offset_in_page(offset);
 		page_length = remain;
 		if ((page_offset + remain) > PAGE_SIZE)
 			page_length = PAGE_SIZE - page_offset;
@@ -453,9 +453,9 @@ i915_gem_shmem_pread_slow(struct drm_device *dev,
 		 * data_page_offset = offset with data_page_index page.
 		 * page_length = bytes to copy for this page
 		 */
-		shmem_page_offset = offset & ~PAGE_MASK;
+		shmem_page_offset = offset_in_page(offset);
 		data_page_index = data_ptr / PAGE_SIZE - first_data_page;
-		data_page_offset = data_ptr & ~PAGE_MASK;
+		data_page_offset = offset_in_page(data_ptr);
 
 		page_length = remain;
 		if ((shmem_page_offset + page_length) > PAGE_SIZE)
@@ -638,8 +638,8 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 		 * page_offset = offset within page
 		 * page_length = bytes to copy for this page
 		 */
-		page_base = (offset & ~(PAGE_SIZE-1));
-		page_offset = offset & (PAGE_SIZE-1);
+		page_base = offset & PAGE_MASK;
+		page_offset = offset_in_page(offset);
 		page_length = remain;
 		if ((page_offset + remain) > PAGE_SIZE)
 			page_length = PAGE_SIZE - page_offset;
@@ -650,7 +650,6 @@ i915_gem_gtt_pwrite_fast(struct drm_device *dev,
 		 */
 		if (fast_user_write(dev_priv->mm.gtt_mapping, page_base,
 				    page_offset, user_data, page_length))
-
 			return -EFAULT;
 
 		remain -= page_length;
@@ -730,9 +729,9 @@ i915_gem_gtt_pwrite_slow(struct drm_device *dev,
 		 * page_length = bytes to copy for this page
 		 */
 		gtt_page_base = offset & PAGE_MASK;
-		gtt_page_offset = offset & ~PAGE_MASK;
+		gtt_page_offset = offset_in_page(offset);
 		data_page_index = data_ptr / PAGE_SIZE - first_data_page;
-		data_page_offset = data_ptr & ~PAGE_MASK;
+		data_page_offset = offset_in_page(data_ptr);
 
 		page_length = remain;
 		if ((gtt_page_offset + page_length) > PAGE_SIZE)
@@ -791,7 +790,7 @@ i915_gem_shmem_pwrite_fast(struct drm_device *dev,
 		 * page_offset = offset within page
 		 * page_length = bytes to copy for this page
 		 */
-		page_offset = offset & (PAGE_SIZE-1);
+		page_offset = offset_in_page(offset);
 		page_length = remain;
 		if ((page_offset + remain) > PAGE_SIZE)
 			page_length = PAGE_SIZE - page_offset;
@@ -896,9 +895,9 @@ i915_gem_shmem_pwrite_slow(struct drm_device *dev,
 		 * data_page_offset = offset with data_page_index page.
 		 * page_length = bytes to copy for this page
 		 */
-		shmem_page_offset = offset & ~PAGE_MASK;
+		shmem_page_offset = offset_in_page(offset);
 		data_page_index = data_ptr / PAGE_SIZE - first_data_page;
-		data_page_offset = data_ptr & ~PAGE_MASK;
+		data_page_offset = offset_in_page(data_ptr);
 
 		page_length = remain;
 		if ((shmem_page_offset + page_length) > PAGE_SIZE)
@@ -1450,8 +1449,9 @@ i915_gem_get_unfenced_gtt_alignment(struct drm_i915_gem_object *obj)
 	 * edge of an even tile row (where tile rows are counted as if the bo is
 	 * placed in a fenced gtt region).
 	 */
-	if (IS_GEN2(dev) ||
-	    (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev)))
+	if (IS_GEN2(dev))
+		tile_height = 16;
+	else if (obj->tiling_mode == I915_TILING_Y && HAS_128_BYTE_Y_TILING(dev))
 		tile_height = 32;
 	else
 		tile_height = 8;
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index b79619a7b788..b9fafe3b045b 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -517,7 +517,7 @@ irqreturn_t ivybridge_irq_handler(DRM_IRQ_ARGS)
 	if (de_iir & DE_PIPEA_VBLANK_IVB)
 		drm_handle_vblank(dev, 0);
 
-	if (de_iir & DE_PIPEB_VBLANK_IVB);
+	if (de_iir & DE_PIPEB_VBLANK_IVB)
 		drm_handle_vblank(dev, 1);
 
 	/* check event from PCH */
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index e93f93cc7e78..0979d8877880 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -288,6 +288,8 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 		 * This may be a DVI-I connector with a shared DDC
 		 * link between analog and digital outputs, so we
 		 * have to check the EDID input spec of the attached device.
+		 *
+		 * On the other hand, what should we do if it is a broken EDID?
 		 */
 		if (edid != NULL) {
 			is_digital = edid->input & DRM_EDID_INPUT_DIGITAL;
@@ -298,6 +300,8 @@ static bool intel_crt_detect_ddc(struct drm_connector *connector)
 		if (!is_digital) {
 			DRM_DEBUG_KMS("CRT detected via DDC:0x50 [EDID]\n");
 			return true;
+		} else {
+			DRM_DEBUG_KMS("CRT not detected via DDC:0x50 [EDID reports a digital panel]\n");
 		}
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index f553ddfdc168..81a9059b6a94 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -3983,54 +3983,6 @@ static void i830_update_wm(struct drm_device *dev)
 #define ILK_LP0_PLANE_LATENCY		700
 #define ILK_LP0_CURSOR_LATENCY		1300
 
-static bool ironlake_compute_wm0(struct drm_device *dev,
-				 int pipe,
-				 const struct intel_watermark_params *display,
-				 int display_latency_ns,
-				 const struct intel_watermark_params *cursor,
-				 int cursor_latency_ns,
-				 int *plane_wm,
-				 int *cursor_wm)
-{
-	struct drm_crtc *crtc;
-	int htotal, hdisplay, clock, pixel_size;
-	int line_time_us, line_count;
-	int entries, tlb_miss;
-
-	crtc = intel_get_crtc_for_pipe(dev, pipe);
-	if (crtc->fb == NULL || !crtc->enabled)
-		return false;
-
-	htotal = crtc->mode.htotal;
-	hdisplay = crtc->mode.hdisplay;
-	clock = crtc->mode.clock;
-	pixel_size = crtc->fb->bits_per_pixel / 8;
-
-	/* Use the small buffer method to calculate plane watermark */
-	entries = ((clock * pixel_size / 1000) * display_latency_ns) / 1000;
-	tlb_miss = display->fifo_size*display->cacheline_size - hdisplay * 8;
-	if (tlb_miss > 0)
-		entries += tlb_miss;
-	entries = DIV_ROUND_UP(entries, display->cacheline_size);
-	*plane_wm = entries + display->guard_size;
-	if (*plane_wm > (int)display->max_wm)
-		*plane_wm = display->max_wm;
-
-	/* Use the large buffer method to calculate cursor watermark */
-	line_time_us = ((htotal * 1000) / clock);
-	line_count = (cursor_latency_ns / line_time_us + 1000) / 1000;
-	entries = line_count * 64 * pixel_size;
-	tlb_miss = cursor->fifo_size*cursor->cacheline_size - hdisplay * 8;
-	if (tlb_miss > 0)
-		entries += tlb_miss;
-	entries = DIV_ROUND_UP(entries, cursor->cacheline_size);
-	*cursor_wm = entries + cursor->guard_size;
-	if (*cursor_wm > (int)cursor->max_wm)
-		*cursor_wm = (int)cursor->max_wm;
-
-	return true;
-}
-
 /*
  * Check the wm result.
  *
@@ -4139,12 +4091,12 @@ static void ironlake_update_wm(struct drm_device *dev)
 	unsigned int enabled;
 
 	enabled = 0;
-	if (ironlake_compute_wm0(dev, 0,
-				 &ironlake_display_wm_info,
-				 ILK_LP0_PLANE_LATENCY,
-				 &ironlake_cursor_wm_info,
-				 ILK_LP0_CURSOR_LATENCY,
-				 &plane_wm, &cursor_wm)) {
+	if (g4x_compute_wm0(dev, 0,
+			    &ironlake_display_wm_info,
+			    ILK_LP0_PLANE_LATENCY,
+			    &ironlake_cursor_wm_info,
+			    ILK_LP0_CURSOR_LATENCY,
+			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEA_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
 		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
@@ -4153,12 +4105,12 @@ static void ironlake_update_wm(struct drm_device *dev)
 		enabled |= 1;
 	}
 
-	if (ironlake_compute_wm0(dev, 1,
-				 &ironlake_display_wm_info,
-				 ILK_LP0_PLANE_LATENCY,
-				 &ironlake_cursor_wm_info,
-				 ILK_LP0_CURSOR_LATENCY,
-				 &plane_wm, &cursor_wm)) {
+	if (g4x_compute_wm0(dev, 1,
+			    &ironlake_display_wm_info,
+			    ILK_LP0_PLANE_LATENCY,
+			    &ironlake_cursor_wm_info,
+			    ILK_LP0_CURSOR_LATENCY,
+			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEB_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
 		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
@@ -4223,10 +4175,10 @@ static void sandybridge_update_wm(struct drm_device *dev)
 	unsigned int enabled;
 
 	enabled = 0;
-	if (ironlake_compute_wm0(dev, 0,
-				 &sandybridge_display_wm_info, latency,
-				 &sandybridge_cursor_wm_info, latency,
-				 &plane_wm, &cursor_wm)) {
+	if (g4x_compute_wm0(dev, 0,
+			    &sandybridge_display_wm_info, latency,
+			    &sandybridge_cursor_wm_info, latency,
+			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEA_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
 		DRM_DEBUG_KMS("FIFO watermarks For pipe A -"
@@ -4235,10 +4187,10 @@ static void sandybridge_update_wm(struct drm_device *dev)
 		enabled |= 1;
 	}
 
-	if (ironlake_compute_wm0(dev, 1,
-				 &sandybridge_display_wm_info, latency,
-				 &sandybridge_cursor_wm_info, latency,
-				 &plane_wm, &cursor_wm)) {
+	if (g4x_compute_wm0(dev, 1,
+			    &sandybridge_display_wm_info, latency,
+			    &sandybridge_cursor_wm_info, latency,
+			    &plane_wm, &cursor_wm)) {
 		I915_WRITE(WM0_PIPEB_ILK,
 			   (plane_wm << WM0_PIPE_PLANE_SHIFT) | cursor_wm);
 		DRM_DEBUG_KMS("FIFO watermarks For pipe B -"
@@ -7675,6 +7627,7 @@ static void intel_init_display(struct drm_device *dev)
 			dev_priv->display.update_wm = NULL;
 		} else
 			dev_priv->display.update_wm = pineview_update_wm;
+		dev_priv->display.init_clock_gating = gen3_init_clock_gating;
 	} else if (IS_G4X(dev)) {
 		dev_priv->display.update_wm = g4x_update_wm;
 		dev_priv->display.init_clock_gating = g4x_init_clock_gating;
diff --git a/drivers/gpu/drm/i915/intel_dp.c b/drivers/gpu/drm/i915/intel_dp.c
index a4d80314e7f8..391b55f1cc74 100644
--- a/drivers/gpu/drm/i915/intel_dp.c
+++ b/drivers/gpu/drm/i915/intel_dp.c
@@ -59,8 +59,6 @@ struct intel_dp {
 	bool is_pch_edp;
 	uint8_t	train_set[4];
 	uint8_t link_status[DP_LINK_STATUS_SIZE];
-
-	struct drm_property *force_audio_property;
 };
 
 /**
@@ -1702,7 +1700,7 @@ intel_dp_set_property(struct drm_connector *connector,
 	if (ret)
 		return ret;
 
-	if (property == intel_dp->force_audio_property) {
+	if (property == dev_priv->force_audio_property) {
 		int i = val;
 		bool has_audio;
 
@@ -1841,16 +1839,7 @@ bool intel_dpd_is_edp(struct drm_device *dev)
 static void
 intel_dp_add_properties(struct intel_dp *intel_dp, struct drm_connector *connector)
 {
-	struct drm_device *dev = connector->dev;
-
-	intel_dp->force_audio_property =
-		drm_property_create(dev, DRM_MODE_PROP_RANGE, "force_audio", 2);
-	if (intel_dp->force_audio_property) {
-		intel_dp->force_audio_property->values[0] = -1;
-		intel_dp->force_audio_property->values[1] = 1;
-		drm_connector_attach_property(connector, intel_dp->force_audio_property, 0);
-	}
-
+	intel_attach_force_audio_property(connector);
 	intel_attach_broadcast_rgb_property(connector);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 831d7a4a0d18..9ffa61eb4d7e 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -236,6 +236,7 @@ struct intel_unpin_work {
 int intel_ddc_get_modes(struct drm_connector *c, struct i2c_adapter *adapter);
 extern bool intel_ddc_probe(struct intel_encoder *intel_encoder, int ddc_bus);
 
+extern void intel_attach_force_audio_property(struct drm_connector *connector);
 extern void intel_attach_broadcast_rgb_property(struct drm_connector *connector);
 
 extern void intel_crt_init(struct drm_device *dev);
diff --git a/drivers/gpu/drm/i915/intel_hdmi.c b/drivers/gpu/drm/i915/intel_hdmi.c
index f289b8642976..aa0a8e83142e 100644
--- a/drivers/gpu/drm/i915/intel_hdmi.c
+++ b/drivers/gpu/drm/i915/intel_hdmi.c
@@ -45,7 +45,6 @@ struct intel_hdmi {
 	bool has_hdmi_sink;
 	bool has_audio;
 	int force_audio;
-	struct drm_property *force_audio_property;
 };
 
 static struct intel_hdmi *enc_to_intel_hdmi(struct drm_encoder *encoder)
@@ -194,7 +193,7 @@ static int intel_hdmi_mode_valid(struct drm_connector *connector,
 	if (mode->clock > 165000)
 		return MODE_CLOCK_HIGH;
 	if (mode->clock < 20000)
-		return MODE_CLOCK_HIGH;
+		return MODE_CLOCK_LOW;
 
 	if (mode->flags & DRM_MODE_FLAG_DBLSCAN)
 		return MODE_NO_DBLESCAN;
@@ -287,7 +286,7 @@ intel_hdmi_set_property(struct drm_connector *connector,
 	if (ret)
 		return ret;
 
-	if (property == intel_hdmi->force_audio_property) {
+	if (property == dev_priv->force_audio_property) {
 		int i = val;
 		bool has_audio;
 
@@ -365,16 +364,7 @@ static const struct drm_encoder_funcs intel_hdmi_enc_funcs = {
 static void
 intel_hdmi_add_properties(struct intel_hdmi *intel_hdmi, struct drm_connector *connector)
 {
-	struct drm_device *dev = connector->dev;
-
-	intel_hdmi->force_audio_property =
-		drm_property_create(dev, DRM_MODE_PROP_RANGE, "force_audio", 2);
-	if (intel_hdmi->force_audio_property) {
-		intel_hdmi->force_audio_property->values[0] = -1;
-		intel_hdmi->force_audio_property->values[1] = 1;
-		drm_connector_attach_property(connector, intel_hdmi->force_audio_property, 0);
-	}
-
+	intel_attach_force_audio_property(connector);
 	intel_attach_broadcast_rgb_property(connector);
 }
 
diff --git a/drivers/gpu/drm/i915/intel_lvds.c b/drivers/gpu/drm/i915/intel_lvds.c
index 67cb076d271b..b28f7bd9f88a 100644
--- a/drivers/gpu/drm/i915/intel_lvds.c
+++ b/drivers/gpu/drm/i915/intel_lvds.c
@@ -727,6 +727,14 @@ static const struct dmi_system_id intel_no_lvds[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "U800"),
 		},
 	},
+	{
+		.callback = intel_no_lvds_dmi_callback,
+		.ident = "Asus EeeBox PC EB1007",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK Computer INC."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "EB1007"),
+		},
+	},
 
 	{ }	/* terminating entry */
 };
diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c
index 9034dd8f33c7..3b26a3ba02dd 100644
--- a/drivers/gpu/drm/i915/intel_modes.c
+++ b/drivers/gpu/drm/i915/intel_modes.c
@@ -81,6 +81,36 @@ int intel_ddc_get_modes(struct drm_connector *connector,
 	return ret;
 }
 
+static const char *force_audio_names[] = {
+	"off",
+	"auto",
+	"on",
+};
+
+void
+intel_attach_force_audio_property(struct drm_connector *connector)
+{
+	struct drm_device *dev = connector->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct drm_property *prop;
+	int i;
+
+	prop = dev_priv->force_audio_property;
+	if (prop == NULL) {
+		prop = drm_property_create(dev, DRM_MODE_PROP_ENUM,
+					   "audio",
+					   ARRAY_SIZE(force_audio_names));
+		if (prop == NULL)
+			return;
+
+		for (i = 0; i < ARRAY_SIZE(force_audio_names); i++)
+			drm_property_add_enum(prop, i, i-1, force_audio_names[i]);
+
+		dev_priv->force_audio_property = prop;
+	}
+	drm_connector_attach_property(connector, prop, 0);
+}
+
 static const char *broadcast_rgb_names[] = {
 	"Full",
 	"Limited 16:235",
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index 754086f83941..30fe554d8936 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -148,8 +148,6 @@ struct intel_sdvo_connector {
 	int   format_supported_num;
 	struct drm_property *tv_format;
 
-	struct drm_property *force_audio_property;
-
 	/* add the property for the SDVO-TV */
 	struct drm_property *left;
 	struct drm_property *right;
@@ -1712,7 +1710,7 @@ intel_sdvo_set_property(struct drm_connector *connector,
 	if (ret)
 		return ret;
 
-	if (property == intel_sdvo_connector->force_audio_property) {
+	if (property == dev_priv->force_audio_property) {
 		int i = val;
 		bool has_audio;
 
@@ -2037,15 +2035,7 @@ intel_sdvo_add_hdmi_properties(struct intel_sdvo_connector *connector)
 {
 	struct drm_device *dev = connector->base.base.dev;
 
-	connector->force_audio_property =
-		drm_property_create(dev, DRM_MODE_PROP_RANGE, "force_audio", 2);
-	if (connector->force_audio_property) {
-		connector->force_audio_property->values[0] = -1;
-		connector->force_audio_property->values[1] = 1;
-		drm_connector_attach_property(&connector->base.base,
-					      connector->force_audio_property, 0);
-	}
-
+	intel_attach_force_audio_property(&connector->base.base);
 	if (INTEL_INFO(dev)->gen >= 4 && IS_MOBILE(dev))
 		intel_attach_broadcast_rgb_property(&connector->base.base);
 }
diff --git a/drivers/gpu/drm/nouveau/nouveau_hw.c b/drivers/gpu/drm/nouveau/nouveau_hw.c
index 053edf9d2f67..ba896e54b799 100644
--- a/drivers/gpu/drm/nouveau/nouveau_hw.c
+++ b/drivers/gpu/drm/nouveau/nouveau_hw.c
@@ -900,6 +900,7 @@ nv_save_state_ext(struct drm_device *dev, int head,
 	}
 	/* NV11 and NV20 don't have this, they stop at 0x52. */
 	if (nv_gf4_disp_arch(dev)) {
+		rd_cio_state(dev, head, regp, NV_CIO_CRE_42);
 		rd_cio_state(dev, head, regp, NV_CIO_CRE_53);
 		rd_cio_state(dev, head, regp, NV_CIO_CRE_54);
 
@@ -1003,6 +1004,7 @@ nv_load_state_ext(struct drm_device *dev, int head,
 			nouveau_wait_eq(dev, 650000000, NV_PRMCIO_INP0__COLOR, 0x8, 0x0);
 		}
 
+		wr_cio_state(dev, head, regp, NV_CIO_CRE_42);
 		wr_cio_state(dev, head, regp, NV_CIO_CRE_53);
 		wr_cio_state(dev, head, regp, NV_CIO_CRE_54);
 
diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.c b/drivers/gpu/drm/nouveau/nouveau_mem.c
index 2960f583dc38..5ee14d216ce8 100644
--- a/drivers/gpu/drm/nouveau/nouveau_mem.c
+++ b/drivers/gpu/drm/nouveau/nouveau_mem.c
@@ -397,7 +397,7 @@ nouveau_mem_vram_init(struct drm_device *dev)
 		if (pci_dma_supported(dev->pdev, DMA_BIT_MASK(40)))
 			dma_bits = 40;
 	} else
-	if (drm_pci_device_is_pcie(dev) &&
+	if (0 && drm_pci_device_is_pcie(dev) &&
 	    dev_priv->chipset  > 0x40 &&
 	    dev_priv->chipset != 0x45) {
 		if (pci_dma_supported(dev->pdev, DMA_BIT_MASK(39)))
@@ -868,7 +868,9 @@ nouveau_gart_manager_del(struct ttm_mem_type_manager *man,
 		nouveau_vm_unmap(&node->tmp_vma);
 		nouveau_vm_put(&node->tmp_vma);
 	}
+
 	mem->mm_node = NULL;
+	kfree(node);
 }
 
 static int
diff --git a/drivers/gpu/drm/nouveau/nouveau_sgdma.c b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
index c77111eca6ac..82fad914e648 100644
--- a/drivers/gpu/drm/nouveau/nouveau_sgdma.c
+++ b/drivers/gpu/drm/nouveau/nouveau_sgdma.c
@@ -458,7 +458,7 @@ nouveau_sgdma_init(struct drm_device *dev)
 		dev_priv->gart_info.type = NOUVEAU_GART_HW;
 		dev_priv->gart_info.func = &nv50_sgdma_backend;
 	} else
-	if (drm_pci_device_is_pcie(dev) &&
+	if (0 && drm_pci_device_is_pcie(dev) &&
 	    dev_priv->chipset > 0x40 && dev_priv->chipset != 0x45) {
 		if (nv44_graph_class(dev)) {
 			dev_priv->gart_info.func = &nv44_sgdma_backend;
diff --git a/drivers/gpu/drm/nouveau/nouveau_state.c b/drivers/gpu/drm/nouveau/nouveau_state.c
index 38ea662568c1..80218887e0a0 100644
--- a/drivers/gpu/drm/nouveau/nouveau_state.c
+++ b/drivers/gpu/drm/nouveau/nouveau_state.c
@@ -371,6 +371,7 @@ static int nouveau_init_engine_ptrs(struct drm_device *dev)
 		engine->vram.flags_valid	= nv50_vram_flags_valid;
 		break;
 	case 0xC0:
+	case 0xD0:
 		engine->instmem.init		= nvc0_instmem_init;
 		engine->instmem.takedown	= nvc0_instmem_takedown;
 		engine->instmem.suspend		= nvc0_instmem_suspend;
@@ -563,68 +564,68 @@ nouveau_card_init(struct drm_device *dev)
 	if (ret)
 		goto out_timer;
 
-	switch (dev_priv->card_type) {
-	case NV_04:
-		nv04_graph_create(dev);
-		break;
-	case NV_10:
-		nv10_graph_create(dev);
-		break;
-	case NV_20:
-	case NV_30:
-		nv20_graph_create(dev);
-		break;
-	case NV_40:
-		nv40_graph_create(dev);
-		break;
-	case NV_50:
-		nv50_graph_create(dev);
-		break;
-	case NV_C0:
-		nvc0_graph_create(dev);
-		break;
-	default:
-		break;
-	}
-
-	switch (dev_priv->chipset) {
-	case 0x84:
-	case 0x86:
-	case 0x92:
-	case 0x94:
-	case 0x96:
-	case 0xa0:
-		nv84_crypt_create(dev);
-		break;
-	}
-
-	switch (dev_priv->card_type) {
-	case NV_50:
-		switch (dev_priv->chipset) {
-		case 0xa3:
-		case 0xa5:
-		case 0xa8:
-		case 0xaf:
-			nva3_copy_create(dev);
+	if (!nouveau_noaccel) {
+		switch (dev_priv->card_type) {
+		case NV_04:
+			nv04_graph_create(dev);
+			break;
+		case NV_10:
+			nv10_graph_create(dev);
+			break;
+		case NV_20:
+		case NV_30:
+			nv20_graph_create(dev);
+			break;
+		case NV_40:
+			nv40_graph_create(dev);
+			break;
+		case NV_50:
+			nv50_graph_create(dev);
+			break;
+		case NV_C0:
+			nvc0_graph_create(dev);
+			break;
+		default:
 			break;
 		}
-		break;
-	case NV_C0:
-		nvc0_copy_create(dev, 0);
-		nvc0_copy_create(dev, 1);
-		break;
-	default:
-		break;
-	}
 
-	if (dev_priv->card_type == NV_40)
-		nv40_mpeg_create(dev);
-	else
-	if (dev_priv->card_type == NV_50 &&
-	    (dev_priv->chipset < 0x98 || dev_priv->chipset == 0xa0))
-		nv50_mpeg_create(dev);
+		switch (dev_priv->chipset) {
+		case 0x84:
+		case 0x86:
+		case 0x92:
+		case 0x94:
+		case 0x96:
+		case 0xa0:
+			nv84_crypt_create(dev);
+			break;
+		}
+
+		switch (dev_priv->card_type) {
+		case NV_50:
+			switch (dev_priv->chipset) {
+			case 0xa3:
+			case 0xa5:
+			case 0xa8:
+			case 0xaf:
+				nva3_copy_create(dev);
+				break;
+			}
+			break;
+		case NV_C0:
+			nvc0_copy_create(dev, 0);
+			nvc0_copy_create(dev, 1);
+			break;
+		default:
+			break;
+		}
+
+		if (dev_priv->card_type == NV_40)
+			nv40_mpeg_create(dev);
+		else
+		if (dev_priv->card_type == NV_50 &&
+		    (dev_priv->chipset < 0x98 || dev_priv->chipset == 0xa0))
+			nv50_mpeg_create(dev);
 
-	if (!nouveau_noaccel) {
 		for (e = 0; e < NVOBJ_ENGINE_NR; e++) {
 			if (dev_priv->eng[e]) {
 				ret = dev_priv->eng[e]->init(dev, e);
@@ -922,6 +923,7 @@ int nouveau_load(struct drm_device *dev, unsigned long flags)
 		dev_priv->card_type = NV_50;
 		break;
 	case 0xc0:
+	case 0xd0:
 		dev_priv->card_type = NV_C0;
 		break;
 	default:
diff --git a/drivers/gpu/drm/nouveau/nouveau_vm.c b/drivers/gpu/drm/nouveau/nouveau_vm.c
index 0059e6f58a8b..519a6b4bba46 100644
--- a/drivers/gpu/drm/nouveau/nouveau_vm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_vm.c
@@ -58,6 +58,7 @@ nouveau_vm_map_at(struct nouveau_vma *vma, u64 delta, struct nouveau_mem *node)
 			num -= len;
 			pte += len;
 			if (unlikely(end >= max)) {
+				phys += len << (bits + 12);
 				pde++;
 				pte = 0;
 			}
diff --git a/drivers/gpu/drm/nouveau/nv04_crtc.c b/drivers/gpu/drm/nouveau/nv04_crtc.c
index 3c78bc81357e..f1a3ae491995 100644
--- a/drivers/gpu/drm/nouveau/nv04_crtc.c
+++ b/drivers/gpu/drm/nouveau/nv04_crtc.c
@@ -376,7 +376,10 @@ nv_crtc_mode_set_vga(struct drm_crtc *crtc, struct drm_display_mode *mode)
 	 */
 
 	/* framebuffer can be larger than crtc scanout area. */
-	regp->CRTC[NV_CIO_CRE_RPC0_INDEX] = XLATE(fb->pitch / 8, 8, NV_CIO_CRE_RPC0_OFFSET_10_8);
+	regp->CRTC[NV_CIO_CRE_RPC0_INDEX] =
+		XLATE(fb->pitch / 8, 8, NV_CIO_CRE_RPC0_OFFSET_10_8);
+	regp->CRTC[NV_CIO_CRE_42] =
+		XLATE(fb->pitch / 8, 11, NV_CIO_CRE_42_OFFSET_11);
 	regp->CRTC[NV_CIO_CRE_RPC1_INDEX] = mode->crtc_hdisplay < 1280 ?
 					    MASK(NV_CIO_CRE_RPC1_LARGE) : 0x00;
 	regp->CRTC[NV_CIO_CRE_LSR_INDEX] = XLATE(horizBlankEnd, 6, NV_CIO_CRE_LSR_HBE_6) |
@@ -824,8 +827,11 @@ nv04_crtc_do_mode_set_base(struct drm_crtc *crtc,
 	regp->CRTC[NV_CIO_CR_OFFSET_INDEX] = drm_fb->pitch >> 3;
 	regp->CRTC[NV_CIO_CRE_RPC0_INDEX] =
 		XLATE(drm_fb->pitch >> 3, 8, NV_CIO_CRE_RPC0_OFFSET_10_8);
+	regp->CRTC[NV_CIO_CRE_42] =
+		XLATE(drm_fb->pitch / 8, 11, NV_CIO_CRE_42_OFFSET_11);
 	crtc_wr_cio_state(crtc, regp, NV_CIO_CRE_RPC0_INDEX);
 	crtc_wr_cio_state(crtc, regp, NV_CIO_CR_OFFSET_INDEX);
+	crtc_wr_cio_state(crtc, regp, NV_CIO_CRE_42);
 
 	/* Update the framebuffer location. */
 	regp->fb_start = nv_crtc->fb.offset & ~3;
diff --git a/drivers/gpu/drm/nouveau/nvreg.h b/drivers/gpu/drm/nouveau/nvreg.h
index fe0f253089ac..bbfb1a68fb11 100644
--- a/drivers/gpu/drm/nouveau/nvreg.h
+++ b/drivers/gpu/drm/nouveau/nvreg.h
@@ -277,6 +277,8 @@
 #		define NV_CIO_CRE_EBR_VDE_11		2:2
 #		define NV_CIO_CRE_EBR_VRS_11		4:4
 #		define NV_CIO_CRE_EBR_VBS_11		6:6
+#	define NV_CIO_CRE_42			0x42
+#		define NV_CIO_CRE_42_OFFSET_11		6:6
 #	define NV_CIO_CRE_43			0x43
 #	define NV_CIO_CRE_44			0x44	/* head control */
 #	define NV_CIO_CRE_CSB			0x45	/* colour saturation boost */
diff --git a/drivers/gpu/drm/radeon/Kconfig b/drivers/gpu/drm/radeon/Kconfig
index 9746fee59f56..ea92bbe3ed37 100644
--- a/drivers/gpu/drm/radeon/Kconfig
+++ b/drivers/gpu/drm/radeon/Kconfig
@@ -28,11 +28,4 @@ config DRM_RADEON_KMS
 	  The kernel will also perform security check on command stream
 	  provided by the user, we want to catch and forbid any illegal use
 	  of the GPU such as DMA into random system memory or into memory
-	  not owned by the process supplying the command stream. This part
-	  of the code is still incomplete and this why we propose that patch
-	  as a staging driver addition, future security might forbid current
-	  experimental userspace to run.
-
-	  This code support the following hardware : R1XX,R2XX,R3XX,R4XX,R5XX
-	  (radeon up to X1950). Works is underway to provide support for R6XX,
-	  R7XX and newer hardware (radeon from HD2XXX to HD4XXX).
+	  not owned by the process supplying the command stream.
diff --git a/drivers/gpu/drm/radeon/atombios_crtc.c b/drivers/gpu/drm/radeon/atombios_crtc.c
index ec848787d7d9..84a69e7fa11e 100644
--- a/drivers/gpu/drm/radeon/atombios_crtc.c
+++ b/drivers/gpu/drm/radeon/atombios_crtc.c
@@ -1045,7 +1045,7 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	uint64_t fb_location;
 	uint32_t fb_format, fb_pitch_pixels, tiling_flags;
 	u32 fb_swap = EVERGREEN_GRPH_ENDIAN_SWAP(EVERGREEN_GRPH_ENDIAN_NONE);
-	u32 tmp;
+	u32 tmp, viewport_w, viewport_h;
 	int r;
 
 	/* no fb bound */
@@ -1171,8 +1171,10 @@ static int dce4_crtc_do_set_base(struct drm_crtc *crtc,
 	y &= ~1;
 	WREG32(EVERGREEN_VIEWPORT_START + radeon_crtc->crtc_offset,
 	       (x << 16) | y);
+	viewport_w = crtc->mode.hdisplay;
+	viewport_h = (crtc->mode.vdisplay + 1) & ~1;
 	WREG32(EVERGREEN_VIEWPORT_SIZE + radeon_crtc->crtc_offset,
-	       (crtc->mode.hdisplay << 16) | crtc->mode.vdisplay);
+	       (viewport_w << 16) | viewport_h);
 
 	/* pageflip setup */
 	/* make sure flip is at vb rather than hb */
@@ -1213,7 +1215,7 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	uint64_t fb_location;
 	uint32_t fb_format, fb_pitch_pixels, tiling_flags;
 	u32 fb_swap = R600_D1GRPH_SWAP_ENDIAN_NONE;
-	u32 tmp;
+	u32 tmp, viewport_w, viewport_h;
 	int r;
 
 	/* no fb bound */
@@ -1338,8 +1340,10 @@ static int avivo_crtc_do_set_base(struct drm_crtc *crtc,
 	y &= ~1;
 	WREG32(AVIVO_D1MODE_VIEWPORT_START + radeon_crtc->crtc_offset,
 	       (x << 16) | y);
+	viewport_w = crtc->mode.hdisplay;
+	viewport_h = (crtc->mode.vdisplay + 1) & ~1;
 	WREG32(AVIVO_D1MODE_VIEWPORT_SIZE + radeon_crtc->crtc_offset,
-	       (crtc->mode.hdisplay << 16) | crtc->mode.vdisplay);
+	       (viewport_w << 16) | viewport_h);
 
 	/* pageflip setup */
 	/* make sure flip is at vb rather than hb */
diff --git a/drivers/gpu/drm/radeon/cayman_blit_shaders.c b/drivers/gpu/drm/radeon/cayman_blit_shaders.c
index e148ab04b80b..7b4eeb7b4a8c 100644
--- a/drivers/gpu/drm/radeon/cayman_blit_shaders.c
+++ b/drivers/gpu/drm/radeon/cayman_blit_shaders.c
@@ -39,17 +39,335 @@
 
 const u32 cayman_default_state[] =
 {
-	/* XXX fill in additional blit state */
+	0xc0066900,
+	0x00000000,
+	0x00000060, /* DB_RENDER_CONTROL */
+	0x00000000, /* DB_COUNT_CONTROL */
+	0x00000000, /* DB_DEPTH_VIEW */
+	0x0000002a, /* DB_RENDER_OVERRIDE */
+	0x00000000, /* DB_RENDER_OVERRIDE2 */
+	0x00000000, /* DB_HTILE_DATA_BASE */
 
 	0xc0026900,
-	0x00000316,
-	0x0000000e, /* VGT_VERTEX_REUSE_BLOCK_CNTL */
-	0x00000010, /*  */
+	0x0000000a,
+	0x00000000, /* DB_STENCIL_CLEAR */
+	0x00000000, /* DB_DEPTH_CLEAR */
+
+	0xc0036900,
+	0x0000000f,
+	0x00000000, /* DB_DEPTH_INFO */
+	0x00000000, /* DB_Z_INFO */
+	0x00000000, /* DB_STENCIL_INFO */
+
+	0xc0016900,
+	0x00000080,
+	0x00000000, /* PA_SC_WINDOW_OFFSET */
+
+	0xc00d6900,
+	0x00000083,
+	0x0000ffff, /* PA_SC_CLIPRECT_RULE */
+	0x00000000, /* PA_SC_CLIPRECT_0_TL */
+	0x20002000, /* PA_SC_CLIPRECT_0_BR */
+	0x00000000,
+	0x20002000,
+	0x00000000,
+	0x20002000,
+	0x00000000,
+	0x20002000,
+	0xaaaaaaaa, /* PA_SC_EDGERULE */
+	0x00000000, /* PA_SU_HARDWARE_SCREEN_OFFSET */
+	0x0000000f, /* CB_TARGET_MASK */
+	0x0000000f, /* CB_SHADER_MASK */
+
+	0xc0226900,
+	0x00000094,
+	0x80000000, /* PA_SC_VPORT_SCISSOR_0_TL */
+	0x20002000, /* PA_SC_VPORT_SCISSOR_0_BR */
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x80000000,
+	0x20002000,
+	0x00000000, /* PA_SC_VPORT_ZMIN_0 */
+	0x3f800000, /* PA_SC_VPORT_ZMAX_0 */
+
+	0xc0016900,
+	0x000000d4,
+	0x00000000, /* SX_MISC */
 
 	0xc0026900,
 	0x000000d9,
 	0x00000000, /* CP_RINGID */
 	0x00000000, /* CP_VMID */
+
+	0xc0096900,
+	0x00000100,
+	0x00ffffff, /* VGT_MAX_VTX_INDX */
+	0x00000000, /* VGT_MIN_VTX_INDX */
+	0x00000000, /* VGT_INDX_OFFSET */
+	0x00000000, /* VGT_MULTI_PRIM_IB_RESET_INDX */
+	0x00000000, /* SX_ALPHA_TEST_CONTROL */
+	0x00000000, /* CB_BLEND_RED */
+	0x00000000, /* CB_BLEND_GREEN */
+	0x00000000, /* CB_BLEND_BLUE */
+	0x00000000, /* CB_BLEND_ALPHA */
+
+	0xc0016900,
+	0x00000187,
+	0x00000100, /* SPI_VS_OUT_ID_0 */
+
+	0xc0026900,
+	0x00000191,
+	0x00000100, /* SPI_PS_INPUT_CNTL_0 */
+	0x00000101, /* SPI_PS_INPUT_CNTL_1 */
+
+	0xc0016900,
+	0x000001b1,
+	0x00000000, /* SPI_VS_OUT_CONFIG */
+
+	0xc0106900,
+	0x000001b3,
+	0x20000001, /* SPI_PS_IN_CONTROL_0 */
+	0x00000000, /* SPI_PS_IN_CONTROL_1 */
+	0x00000000, /* SPI_INTERP_CONTROL_0 */
+	0x00000000, /* SPI_INPUT_Z */
+	0x00000000, /* SPI_FOG_CNTL */
+	0x00100000, /* SPI_BARYC_CNTL */
+	0x00000000, /* SPI_PS_IN_CONTROL_2 */
+	0x00000000, /* SPI_COMPUTE_INPUT_CNTL */
+	0x00000000, /* SPI_COMPUTE_NUM_THREAD_X */
+	0x00000000, /* SPI_COMPUTE_NUM_THREAD_Y */
+	0x00000000, /* SPI_COMPUTE_NUM_THREAD_Z */
+	0x00000000, /* SPI_GPR_MGMT */
+	0x00000000, /* SPI_LDS_MGMT */
+	0x00000000, /* SPI_STACK_MGMT */
+	0x00000000, /* SPI_WAVE_MGMT_1 */
+	0x00000000, /* SPI_WAVE_MGMT_2 */
+
+	0xc0016900,
+	0x000001e0,
+	0x00000000, /* CB_BLEND0_CONTROL */
+
+	0xc00e6900,
+	0x00000200,
+	0x00000000, /* DB_DEPTH_CONTROL */
+	0x00000000, /* DB_EQAA */
+	0x00cc0010, /* CB_COLOR_CONTROL */
+	0x00000210, /* DB_SHADER_CONTROL */
+	0x00010000, /* PA_CL_CLIP_CNTL */
+	0x00000004, /* PA_SU_SC_MODE_CNTL */
+	0x00000100, /* PA_CL_VTE_CNTL */
+	0x00000000, /* PA_CL_VS_OUT_CNTL */
+	0x00000000, /* PA_CL_NANINF_CNTL */
+	0x00000000, /* PA_SU_LINE_STIPPLE_CNTL */
+	0x00000000, /* PA_SU_LINE_STIPPLE_SCALE */
+	0x00000000, /* PA_SU_PRIM_FILTER_CNTL */
+	0x00000000, /*  */
+	0x00000000, /*  */
+
+	0xc0026900,
+	0x00000229,
+	0x00000000, /* SQ_PGM_START_FS */
+	0x00000000,
+
+	0xc0016900,
+	0x0000023b,
+	0x00000000, /* SQ_LDS_ALLOC_PS */
+
+	0xc0066900,
+	0x00000240,
+	0x00000000, /* SQ_ESGS_RING_ITEMSIZE */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+
+	0xc0046900,
+	0x00000247,
+	0x00000000, /* SQ_GS_VERT_ITEMSIZE */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+
+	0xc0116900,
+	0x00000280,
+	0x00000000, /* PA_SU_POINT_SIZE */
+	0x00000000, /* PA_SU_POINT_MINMAX */
+	0x00000008, /* PA_SU_LINE_CNTL */
+	0x00000000, /* PA_SC_LINE_STIPPLE */
+	0x00000000, /* VGT_OUTPUT_PATH_CNTL */
+	0x00000000, /* VGT_HOS_CNTL */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000, /* VGT_GS_MODE */
+
+	0xc0026900,
+	0x00000292,
+	0x00000000, /* PA_SC_MODE_CNTL_0 */
+	0x00000000, /* PA_SC_MODE_CNTL_1 */
+
+	0xc0016900,
+	0x000002a1,
+	0x00000000, /* VGT_PRIMITIVEID_EN */
+
+	0xc0016900,
+	0x000002a5,
+	0x00000000, /* VGT_MULTI_PRIM_IB_RESET_EN */
+
+	0xc0026900,
+	0x000002a8,
+	0x00000000, /* VGT_INSTANCE_STEP_RATE_0 */
+	0x00000000,
+
+	0xc0026900,
+	0x000002ad,
+	0x00000000, /* VGT_REUSE_OFF */
+	0x00000000,
+
+	0xc0016900,
+	0x000002d5,
+	0x00000000, /* VGT_SHADER_STAGES_EN */
+
+	0xc0016900,
+	0x000002dc,
+	0x0000aa00, /* DB_ALPHA_TO_MASK */
+
+	0xc0066900,
+	0x000002de,
+	0x00000000, /* PA_SU_POLY_OFFSET_DB_FMT_CNTL */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+
+	0xc0026900,
+	0x000002e5,
+	0x00000000, /* VGT_STRMOUT_CONFIG */
+	0x00000000,
+
+	0xc01b6900,
+	0x000002f5,
+	0x76543210, /* PA_SC_CENTROID_PRIORITY_0 */
+	0xfedcba98, /* PA_SC_CENTROID_PRIORITY_1 */
+	0x00000000, /* PA_SC_LINE_CNTL */
+	0x00000000, /* PA_SC_AA_CONFIG */
+	0x00000005, /* PA_SU_VTX_CNTL */
+	0x3f800000, /* PA_CL_GB_VERT_CLIP_ADJ */
+	0x3f800000, /* PA_CL_GB_VERT_DISC_ADJ */
+	0x3f800000, /* PA_CL_GB_HORZ_CLIP_ADJ */
+	0x3f800000, /* PA_CL_GB_HORZ_DISC_ADJ */
+	0x00000000, /* PA_SC_AA_SAMPLE_LOCS_PIXEL_X0Y0_0 */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0xffffffff, /* PA_SC_AA_MASK_X0Y0_X1Y0 */
+	0xffffffff,
+
+	0xc0026900,
+	0x00000316,
+	0x0000000e, /* VGT_VERTEX_REUSE_BLOCK_CNTL */
+	0x00000010, /*  */
 };
 
+const u32 cayman_vs[] =
+{
+	0x00000004,
+	0x80400400,
+	0x0000a03c,
+	0x95000688,
+	0x00004000,
+	0x15000688,
+	0x00000000,
+	0x88000000,
+	0x04000000,
+	0x67961001,
+#ifdef __BIG_ENDIAN
+	0x00020000,
+#else
+	0x00000000,
+#endif
+	0x00000000,
+	0x04000000,
+	0x67961000,
+#ifdef __BIG_ENDIAN
+	0x00020008,
+#else
+	0x00000008,
+#endif
+	0x00000000,
+};
+
+const u32 cayman_ps[] =
+{
+	0x00000004,
+	0xa00c0000,
+	0x00000008,
+	0x80400000,
+	0x00000000,
+	0x95000688,
+	0x00000000,
+	0x88000000,
+	0x00380400,
+	0x00146b10,
+	0x00380000,
+	0x20146b10,
+	0x00380400,
+	0x40146b00,
+	0x80380000,
+	0x60146b00,
+	0x00000010,
+	0x000d1000,
+	0xb0800000,
+	0x00000000,
+};
+
+const u32 cayman_ps_size = ARRAY_SIZE(cayman_ps);
+const u32 cayman_vs_size = ARRAY_SIZE(cayman_vs);
 const u32 cayman_default_size = ARRAY_SIZE(cayman_default_state);
diff --git a/drivers/gpu/drm/radeon/cayman_blit_shaders.h b/drivers/gpu/drm/radeon/cayman_blit_shaders.h
index 33b75e5d0fa4..f5d0e9a60267 100644
--- a/drivers/gpu/drm/radeon/cayman_blit_shaders.h
+++ b/drivers/gpu/drm/radeon/cayman_blit_shaders.h
@@ -25,8 +25,11 @@
 #ifndef CAYMAN_BLIT_SHADERS_H
 #define CAYMAN_BLIT_SHADERS_H
 
+extern const u32 cayman_ps[];
+extern const u32 cayman_vs[];
 extern const u32 cayman_default_state[];
 
+extern const u32 cayman_ps_size, cayman_vs_size;
 extern const u32 cayman_default_size;
 
 #endif
diff --git a/drivers/gpu/drm/radeon/evergreen.c b/drivers/gpu/drm/radeon/evergreen.c
index 7c37638095f7..98ea597bc76d 100644
--- a/drivers/gpu/drm/radeon/evergreen.c
+++ b/drivers/gpu/drm/radeon/evergreen.c
@@ -88,21 +88,39 @@ u32 evergreen_page_flip(struct radeon_device *rdev, int crtc_id, u64 crtc_base)
 /* get temperature in millidegrees */
 int evergreen_get_temp(struct radeon_device *rdev)
 {
-	u32 temp = (RREG32(CG_MULT_THERMAL_STATUS) & ASIC_T_MASK) >>
-		ASIC_T_SHIFT;
-	u32 actual_temp = 0;
+	u32 temp, toffset, actual_temp = 0;
 
-	if (temp & 0x400)
-		actual_temp = -256;
-	else if (temp & 0x200)
-		actual_temp = 255;
-	else if (temp & 0x100) {
-		actual_temp = temp & 0x1ff;
-		actual_temp |= ~0x1ff;
-	} else
-		actual_temp = temp & 0xff;
+	if (rdev->family == CHIP_JUNIPER) {
+		toffset = (RREG32(CG_THERMAL_CTRL) & TOFFSET_MASK) >>
+			TOFFSET_SHIFT;
+		temp = (RREG32(CG_TS0_STATUS) & TS0_ADC_DOUT_MASK) >>
+			TS0_ADC_DOUT_SHIFT;
 
-	return (actual_temp * 1000) / 2;
+		if (toffset & 0x100)
+			actual_temp = temp / 2 - (0x200 - toffset);
+		else
+			actual_temp = temp / 2 + toffset;
+
+		actual_temp = actual_temp * 1000;
+
+	} else {
+		temp = (RREG32(CG_MULT_THERMAL_STATUS) & ASIC_T_MASK) >>
+			ASIC_T_SHIFT;
+
+		if (temp & 0x400)
+			actual_temp = -256;
+		else if (temp & 0x200)
+			actual_temp = 255;
+		else if (temp & 0x100) {
+			actual_temp = temp & 0x1ff;
+			actual_temp |= ~0x1ff;
+		} else
+			actual_temp = temp & 0xff;
+
+		actual_temp = (actual_temp * 1000) / 2;
+	}
+
+	return actual_temp;
 }
 
 int sumo_get_temp(struct radeon_device *rdev)
@@ -1415,6 +1433,8 @@ static u32 evergreen_get_tile_pipe_to_backend_map(struct radeon_device *rdev,
 	case CHIP_CEDAR:
 	case CHIP_REDWOOD:
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 	case CHIP_TURKS:
 	case CHIP_CAICOS:
 		force_no_swizzle = false;
@@ -1544,6 +1564,8 @@ static void evergreen_program_channel_remap(struct radeon_device *rdev)
 	case CHIP_REDWOOD:
 	case CHIP_CEDAR:
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 	case CHIP_TURKS:
 	case CHIP_CAICOS:
 	default:
@@ -1685,6 +1707,54 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 		rdev->config.evergreen.max_hw_contexts = 4;
 		rdev->config.evergreen.sq_num_cf_insts = 1;
 
+		rdev->config.evergreen.sc_prim_fifo_size = 0x40;
+		rdev->config.evergreen.sc_hiz_tile_fifo_size = 0x30;
+		rdev->config.evergreen.sc_earlyz_tile_fifo_size = 0x130;
+		break;
+	case CHIP_SUMO:
+		rdev->config.evergreen.num_ses = 1;
+		rdev->config.evergreen.max_pipes = 4;
+		rdev->config.evergreen.max_tile_pipes = 2;
+		if (rdev->pdev->device == 0x9648)
+			rdev->config.evergreen.max_simds = 3;
+		else if ((rdev->pdev->device == 0x9647) ||
+			 (rdev->pdev->device == 0x964a))
+			rdev->config.evergreen.max_simds = 4;
+		else
+			rdev->config.evergreen.max_simds = 5;
+		rdev->config.evergreen.max_backends = 2 * rdev->config.evergreen.num_ses;
+		rdev->config.evergreen.max_gprs = 256;
+		rdev->config.evergreen.max_threads = 248;
+		rdev->config.evergreen.max_gs_threads = 32;
+		rdev->config.evergreen.max_stack_entries = 256;
+		rdev->config.evergreen.sx_num_of_sets = 4;
+		rdev->config.evergreen.sx_max_export_size = 256;
+		rdev->config.evergreen.sx_max_export_pos_size = 64;
+		rdev->config.evergreen.sx_max_export_smx_size = 192;
+		rdev->config.evergreen.max_hw_contexts = 8;
+		rdev->config.evergreen.sq_num_cf_insts = 2;
+
+		rdev->config.evergreen.sc_prim_fifo_size = 0x40;
+		rdev->config.evergreen.sc_hiz_tile_fifo_size = 0x30;
+		rdev->config.evergreen.sc_earlyz_tile_fifo_size = 0x130;
+		break;
+	case CHIP_SUMO2:
+		rdev->config.evergreen.num_ses = 1;
+		rdev->config.evergreen.max_pipes = 4;
+		rdev->config.evergreen.max_tile_pipes = 4;
+		rdev->config.evergreen.max_simds = 2;
+		rdev->config.evergreen.max_backends = 1 * rdev->config.evergreen.num_ses;
+		rdev->config.evergreen.max_gprs = 256;
+		rdev->config.evergreen.max_threads = 248;
+		rdev->config.evergreen.max_gs_threads = 32;
+		rdev->config.evergreen.max_stack_entries = 512;
+		rdev->config.evergreen.sx_num_of_sets = 4;
+		rdev->config.evergreen.sx_max_export_size = 256;
+		rdev->config.evergreen.sx_max_export_pos_size = 64;
+		rdev->config.evergreen.sx_max_export_smx_size = 192;
+		rdev->config.evergreen.max_hw_contexts = 8;
+		rdev->config.evergreen.sq_num_cf_insts = 2;
+
 		rdev->config.evergreen.sc_prim_fifo_size = 0x40;
 		rdev->config.evergreen.sc_hiz_tile_fifo_size = 0x30;
 		rdev->config.evergreen.sc_earlyz_tile_fifo_size = 0x130;
@@ -2039,6 +2109,8 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 	switch (rdev->family) {
 	case CHIP_CEDAR:
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 	case CHIP_CAICOS:
 		/* no vertex cache */
 		sq_config &= ~VC_ENABLE;
@@ -2060,6 +2132,8 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 	switch (rdev->family) {
 	case CHIP_CEDAR:
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 		ps_thread_count = 96;
 		break;
 	default:
@@ -2099,6 +2173,8 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
 	switch (rdev->family) {
 	case CHIP_CEDAR:
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 	case CHIP_CAICOS:
 		vgt_cache_invalidation = CACHE_INVALIDATION(TC_ONLY);
 		break;
diff --git a/drivers/gpu/drm/radeon/evergreen_blit_kms.c b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
index ba06a69c6de8..57f3bc17b87e 100644
--- a/drivers/gpu/drm/radeon/evergreen_blit_kms.c
+++ b/drivers/gpu/drm/radeon/evergreen_blit_kms.c
@@ -31,6 +31,7 @@
 
 #include "evergreend.h"
 #include "evergreen_blit_shaders.h"
+#include "cayman_blit_shaders.h"
 
 #define DI_PT_RECTLIST        0x11
 #define DI_INDEX_SIZE_16_BIT  0x0
@@ -152,6 +153,8 @@ set_vtx_resource(struct radeon_device *rdev, u64 gpu_addr)
 
 	if ((rdev->family == CHIP_CEDAR) ||
 	    (rdev->family == CHIP_PALM) ||
+	    (rdev->family == CHIP_SUMO) ||
+	    (rdev->family == CHIP_SUMO2) ||
 	    (rdev->family == CHIP_CAICOS))
 		cp_set_surface_sync(rdev,
 				    PACKET3_TC_ACTION_ENA, 48, gpu_addr);
@@ -199,6 +202,16 @@ static void
 set_scissors(struct radeon_device *rdev, int x1, int y1,
 	     int x2, int y2)
 {
+	/* workaround some hw bugs */
+	if (x2 == 0)
+		x1 = 1;
+	if (y2 == 0)
+		y1 = 1;
+	if (rdev->family == CHIP_CAYMAN) {
+		if ((x2 == 1) && (y2 == 1))
+			x2 = 2;
+	}
+
 	radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONTEXT_REG, 2));
 	radeon_ring_write(rdev, (PA_SC_SCREEN_SCISSOR_TL - PACKET3_SET_CONTEXT_REG_START) >> 2);
 	radeon_ring_write(rdev, (x1 << 0) | (y1 << 16));
@@ -255,238 +268,284 @@ set_default_state(struct radeon_device *rdev)
 	u64 gpu_addr;
 	int dwords;
 
-	switch (rdev->family) {
-	case CHIP_CEDAR:
-	default:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 96;
-		num_vs_threads = 16;
-		num_gs_threads = 16;
-		num_es_threads = 16;
-		num_hs_threads = 16;
-		num_ls_threads = 16;
-		num_ps_stack_entries = 42;
-		num_vs_stack_entries = 42;
-		num_gs_stack_entries = 42;
-		num_es_stack_entries = 42;
-		num_hs_stack_entries = 42;
-		num_ls_stack_entries = 42;
-		break;
-	case CHIP_REDWOOD:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 20;
-		num_gs_threads = 20;
-		num_es_threads = 20;
-		num_hs_threads = 20;
-		num_ls_threads = 20;
-		num_ps_stack_entries = 42;
-		num_vs_stack_entries = 42;
-		num_gs_stack_entries = 42;
-		num_es_stack_entries = 42;
-		num_hs_stack_entries = 42;
-		num_ls_stack_entries = 42;
-		break;
-	case CHIP_JUNIPER:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 20;
-		num_gs_threads = 20;
-		num_es_threads = 20;
-		num_hs_threads = 20;
-		num_ls_threads = 20;
-		num_ps_stack_entries = 85;
-		num_vs_stack_entries = 85;
-		num_gs_stack_entries = 85;
-		num_es_stack_entries = 85;
-		num_hs_stack_entries = 85;
-		num_ls_stack_entries = 85;
-		break;
-	case CHIP_CYPRESS:
-	case CHIP_HEMLOCK:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 20;
-		num_gs_threads = 20;
-		num_es_threads = 20;
-		num_hs_threads = 20;
-		num_ls_threads = 20;
-		num_ps_stack_entries = 85;
-		num_vs_stack_entries = 85;
-		num_gs_stack_entries = 85;
-		num_es_stack_entries = 85;
-		num_hs_stack_entries = 85;
-		num_ls_stack_entries = 85;
-		break;
-	case CHIP_PALM:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 96;
-		num_vs_threads = 16;
-		num_gs_threads = 16;
-		num_es_threads = 16;
-		num_hs_threads = 16;
-		num_ls_threads = 16;
-		num_ps_stack_entries = 42;
-		num_vs_stack_entries = 42;
-		num_gs_stack_entries = 42;
-		num_es_stack_entries = 42;
-		num_hs_stack_entries = 42;
-		num_ls_stack_entries = 42;
-		break;
-	case CHIP_BARTS:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 20;
-		num_gs_threads = 20;
-		num_es_threads = 20;
-		num_hs_threads = 20;
-		num_ls_threads = 20;
-		num_ps_stack_entries = 85;
-		num_vs_stack_entries = 85;
-		num_gs_stack_entries = 85;
-		num_es_stack_entries = 85;
-		num_hs_stack_entries = 85;
-		num_ls_stack_entries = 85;
-		break;
-	case CHIP_TURKS:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 20;
-		num_gs_threads = 20;
-		num_es_threads = 20;
-		num_hs_threads = 20;
-		num_ls_threads = 20;
-		num_ps_stack_entries = 42;
-		num_vs_stack_entries = 42;
-		num_gs_stack_entries = 42;
-		num_es_stack_entries = 42;
-		num_hs_stack_entries = 42;
-		num_ls_stack_entries = 42;
-		break;
-	case CHIP_CAICOS:
-		num_ps_gprs = 93;
-		num_vs_gprs = 46;
-		num_temp_gprs = 4;
-		num_gs_gprs = 31;
-		num_es_gprs = 31;
-		num_hs_gprs = 23;
-		num_ls_gprs = 23;
-		num_ps_threads = 128;
-		num_vs_threads = 10;
-		num_gs_threads = 10;
-		num_es_threads = 10;
-		num_hs_threads = 10;
-		num_ls_threads = 10;
-		num_ps_stack_entries = 42;
-		num_vs_stack_entries = 42;
-		num_gs_stack_entries = 42;
-		num_es_stack_entries = 42;
-		num_hs_stack_entries = 42;
-		num_ls_stack_entries = 42;
-		break;
-	}
-
-	if ((rdev->family == CHIP_CEDAR) ||
-	    (rdev->family == CHIP_PALM) ||
-	    (rdev->family == CHIP_CAICOS))
-		sq_config = 0;
-	else
-		sq_config = VC_ENABLE;
-
-	sq_config |= (EXPORT_SRC_C |
-		      CS_PRIO(0) |
-		      LS_PRIO(0) |
-		      HS_PRIO(0) |
-		      PS_PRIO(0) |
-		      VS_PRIO(1) |
-		      GS_PRIO(2) |
-		      ES_PRIO(3));
-
-	sq_gpr_resource_mgmt_1 = (NUM_PS_GPRS(num_ps_gprs) |
-				  NUM_VS_GPRS(num_vs_gprs) |
-				  NUM_CLAUSE_TEMP_GPRS(num_temp_gprs));
-	sq_gpr_resource_mgmt_2 = (NUM_GS_GPRS(num_gs_gprs) |
-				  NUM_ES_GPRS(num_es_gprs));
-	sq_gpr_resource_mgmt_3 = (NUM_HS_GPRS(num_hs_gprs) |
-				  NUM_LS_GPRS(num_ls_gprs));
-	sq_thread_resource_mgmt = (NUM_PS_THREADS(num_ps_threads) |
-				   NUM_VS_THREADS(num_vs_threads) |
-				   NUM_GS_THREADS(num_gs_threads) |
-				   NUM_ES_THREADS(num_es_threads));
-	sq_thread_resource_mgmt_2 = (NUM_HS_THREADS(num_hs_threads) |
-				     NUM_LS_THREADS(num_ls_threads));
-	sq_stack_resource_mgmt_1 = (NUM_PS_STACK_ENTRIES(num_ps_stack_entries) |
-				    NUM_VS_STACK_ENTRIES(num_vs_stack_entries));
-	sq_stack_resource_mgmt_2 = (NUM_GS_STACK_ENTRIES(num_gs_stack_entries) |
-				    NUM_ES_STACK_ENTRIES(num_es_stack_entries));
-	sq_stack_resource_mgmt_3 = (NUM_HS_STACK_ENTRIES(num_hs_stack_entries) |
-				    NUM_LS_STACK_ENTRIES(num_ls_stack_entries));
-
 	/* set clear context state */
 	radeon_ring_write(rdev, PACKET3(PACKET3_CLEAR_STATE, 0));
 	radeon_ring_write(rdev, 0);
 
-	/* disable dyn gprs */
-	radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONFIG_REG, 1));
-	radeon_ring_write(rdev, (SQ_DYN_GPR_CNTL_PS_FLUSH_REQ - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(rdev, 0);
+	if (rdev->family < CHIP_CAYMAN) {
+		switch (rdev->family) {
+		case CHIP_CEDAR:
+		default:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 96;
+			num_vs_threads = 16;
+			num_gs_threads = 16;
+			num_es_threads = 16;
+			num_hs_threads = 16;
+			num_ls_threads = 16;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		case CHIP_REDWOOD:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 20;
+			num_gs_threads = 20;
+			num_es_threads = 20;
+			num_hs_threads = 20;
+			num_ls_threads = 20;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		case CHIP_JUNIPER:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 20;
+			num_gs_threads = 20;
+			num_es_threads = 20;
+			num_hs_threads = 20;
+			num_ls_threads = 20;
+			num_ps_stack_entries = 85;
+			num_vs_stack_entries = 85;
+			num_gs_stack_entries = 85;
+			num_es_stack_entries = 85;
+			num_hs_stack_entries = 85;
+			num_ls_stack_entries = 85;
+			break;
+		case CHIP_CYPRESS:
+		case CHIP_HEMLOCK:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 20;
+			num_gs_threads = 20;
+			num_es_threads = 20;
+			num_hs_threads = 20;
+			num_ls_threads = 20;
+			num_ps_stack_entries = 85;
+			num_vs_stack_entries = 85;
+			num_gs_stack_entries = 85;
+			num_es_stack_entries = 85;
+			num_hs_stack_entries = 85;
+			num_ls_stack_entries = 85;
+			break;
+		case CHIP_PALM:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 96;
+			num_vs_threads = 16;
+			num_gs_threads = 16;
+			num_es_threads = 16;
+			num_hs_threads = 16;
+			num_ls_threads = 16;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		case CHIP_SUMO:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 96;
+			num_vs_threads = 25;
+			num_gs_threads = 25;
+			num_es_threads = 25;
+			num_hs_threads = 25;
+			num_ls_threads = 25;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		case CHIP_SUMO2:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 96;
+			num_vs_threads = 25;
+			num_gs_threads = 25;
+			num_es_threads = 25;
+			num_hs_threads = 25;
+			num_ls_threads = 25;
+			num_ps_stack_entries = 85;
+			num_vs_stack_entries = 85;
+			num_gs_stack_entries = 85;
+			num_es_stack_entries = 85;
+			num_hs_stack_entries = 85;
+			num_ls_stack_entries = 85;
+			break;
+		case CHIP_BARTS:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 20;
+			num_gs_threads = 20;
+			num_es_threads = 20;
+			num_hs_threads = 20;
+			num_ls_threads = 20;
+			num_ps_stack_entries = 85;
+			num_vs_stack_entries = 85;
+			num_gs_stack_entries = 85;
+			num_es_stack_entries = 85;
+			num_hs_stack_entries = 85;
+			num_ls_stack_entries = 85;
+			break;
+		case CHIP_TURKS:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 20;
+			num_gs_threads = 20;
+			num_es_threads = 20;
+			num_hs_threads = 20;
+			num_ls_threads = 20;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		case CHIP_CAICOS:
+			num_ps_gprs = 93;
+			num_vs_gprs = 46;
+			num_temp_gprs = 4;
+			num_gs_gprs = 31;
+			num_es_gprs = 31;
+			num_hs_gprs = 23;
+			num_ls_gprs = 23;
+			num_ps_threads = 128;
+			num_vs_threads = 10;
+			num_gs_threads = 10;
+			num_es_threads = 10;
+			num_hs_threads = 10;
+			num_ls_threads = 10;
+			num_ps_stack_entries = 42;
+			num_vs_stack_entries = 42;
+			num_gs_stack_entries = 42;
+			num_es_stack_entries = 42;
+			num_hs_stack_entries = 42;
+			num_ls_stack_entries = 42;
+			break;
+		}
 
-	/* SQ config */
-	radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONFIG_REG, 11));
-	radeon_ring_write(rdev, (SQ_CONFIG - PACKET3_SET_CONFIG_REG_START) >> 2);
-	radeon_ring_write(rdev, sq_config);
-	radeon_ring_write(rdev, sq_gpr_resource_mgmt_1);
-	radeon_ring_write(rdev, sq_gpr_resource_mgmt_2);
-	radeon_ring_write(rdev, sq_gpr_resource_mgmt_3);
-	radeon_ring_write(rdev, 0);
-	radeon_ring_write(rdev, 0);
-	radeon_ring_write(rdev, sq_thread_resource_mgmt);
-	radeon_ring_write(rdev, sq_thread_resource_mgmt_2);
-	radeon_ring_write(rdev, sq_stack_resource_mgmt_1);
-	radeon_ring_write(rdev, sq_stack_resource_mgmt_2);
-	radeon_ring_write(rdev, sq_stack_resource_mgmt_3);
+		if ((rdev->family == CHIP_CEDAR) ||
+		    (rdev->family == CHIP_PALM) ||
+		    (rdev->family == CHIP_SUMO) ||
+		    (rdev->family == CHIP_SUMO2) ||
+		    (rdev->family == CHIP_CAICOS))
+			sq_config = 0;
+		else
+			sq_config = VC_ENABLE;
+
+		sq_config |= (EXPORT_SRC_C |
+			      CS_PRIO(0) |
+			      LS_PRIO(0) |
+			      HS_PRIO(0) |
+			      PS_PRIO(0) |
+			      VS_PRIO(1) |
+			      GS_PRIO(2) |
+			      ES_PRIO(3));
+
+		sq_gpr_resource_mgmt_1 = (NUM_PS_GPRS(num_ps_gprs) |
+					  NUM_VS_GPRS(num_vs_gprs) |
+					  NUM_CLAUSE_TEMP_GPRS(num_temp_gprs));
+		sq_gpr_resource_mgmt_2 = (NUM_GS_GPRS(num_gs_gprs) |
+					  NUM_ES_GPRS(num_es_gprs));
+		sq_gpr_resource_mgmt_3 = (NUM_HS_GPRS(num_hs_gprs) |
+					  NUM_LS_GPRS(num_ls_gprs));
+		sq_thread_resource_mgmt = (NUM_PS_THREADS(num_ps_threads) |
+					   NUM_VS_THREADS(num_vs_threads) |
+					   NUM_GS_THREADS(num_gs_threads) |
+					   NUM_ES_THREADS(num_es_threads));
+		sq_thread_resource_mgmt_2 = (NUM_HS_THREADS(num_hs_threads) |
+					     NUM_LS_THREADS(num_ls_threads));
+		sq_stack_resource_mgmt_1 = (NUM_PS_STACK_ENTRIES(num_ps_stack_entries) |
+					    NUM_VS_STACK_ENTRIES(num_vs_stack_entries));
+		sq_stack_resource_mgmt_2 = (NUM_GS_STACK_ENTRIES(num_gs_stack_entries) |
+					    NUM_ES_STACK_ENTRIES(num_es_stack_entries));
+		sq_stack_resource_mgmt_3 = (NUM_HS_STACK_ENTRIES(num_hs_stack_entries) |
+					    NUM_LS_STACK_ENTRIES(num_ls_stack_entries));
+
+		/* disable dyn gprs */
+		radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONFIG_REG, 1));
+		radeon_ring_write(rdev, (SQ_DYN_GPR_CNTL_PS_FLUSH_REQ - PACKET3_SET_CONFIG_REG_START) >> 2);
+		radeon_ring_write(rdev, 0);
+
+		/* SQ config */
+		radeon_ring_write(rdev, PACKET3(PACKET3_SET_CONFIG_REG, 11));
+		radeon_ring_write(rdev, (SQ_CONFIG - PACKET3_SET_CONFIG_REG_START) >> 2);
+		radeon_ring_write(rdev, sq_config);
+		radeon_ring_write(rdev, sq_gpr_resource_mgmt_1);
+		radeon_ring_write(rdev, sq_gpr_resource_mgmt_2);
+		radeon_ring_write(rdev, sq_gpr_resource_mgmt_3);
+		radeon_ring_write(rdev, 0);
+		radeon_ring_write(rdev, 0);
+		radeon_ring_write(rdev, sq_thread_resource_mgmt);
+		radeon_ring_write(rdev, sq_thread_resource_mgmt_2);
+		radeon_ring_write(rdev, sq_stack_resource_mgmt_1);
+		radeon_ring_write(rdev, sq_stack_resource_mgmt_2);
+		radeon_ring_write(rdev, sq_stack_resource_mgmt_3);
+	}
 
 	/* CONTEXT_CONTROL */
 	radeon_ring_write(rdev, 0xc0012800);
@@ -560,7 +619,10 @@ int evergreen_blit_init(struct radeon_device *rdev)
 	mutex_init(&rdev->r600_blit.mutex);
 	rdev->r600_blit.state_offset = 0;
 
-	rdev->r600_blit.state_len = evergreen_default_size;
+	if (rdev->family < CHIP_CAYMAN)
+		rdev->r600_blit.state_len = evergreen_default_size;
+	else
+		rdev->r600_blit.state_len = cayman_default_size;
 
 	dwords = rdev->r600_blit.state_len;
 	while (dwords & 0xf) {
@@ -572,11 +634,17 @@ int evergreen_blit_init(struct radeon_device *rdev)
 	obj_size = ALIGN(obj_size, 256);
 
 	rdev->r600_blit.vs_offset = obj_size;
-	obj_size += evergreen_vs_size * 4;
+	if (rdev->family < CHIP_CAYMAN)
+		obj_size += evergreen_vs_size * 4;
+	else
+		obj_size += cayman_vs_size * 4;
 	obj_size = ALIGN(obj_size, 256);
 
 	rdev->r600_blit.ps_offset = obj_size;
-	obj_size += evergreen_ps_size * 4;
+	if (rdev->family < CHIP_CAYMAN)
+		obj_size += evergreen_ps_size * 4;
+	else
+		obj_size += cayman_ps_size * 4;
 	obj_size = ALIGN(obj_size, 256);
 
 	r = radeon_bo_create(rdev, obj_size, PAGE_SIZE, true, RADEON_GEM_DOMAIN_VRAM,
@@ -599,16 +667,29 @@ int evergreen_blit_init(struct radeon_device *rdev)
 		return r;
 	}
 
-	memcpy_toio(ptr + rdev->r600_blit.state_offset,
-		    evergreen_default_state, rdev->r600_blit.state_len * 4);
+	if (rdev->family < CHIP_CAYMAN) {
+		memcpy_toio(ptr + rdev->r600_blit.state_offset,
+			    evergreen_default_state, rdev->r600_blit.state_len * 4);
 
-	if (num_packet2s)
-		memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4),
-			    packet2s, num_packet2s * 4);
-	for (i = 0; i < evergreen_vs_size; i++)
-		*(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(evergreen_vs[i]);
-	for (i = 0; i < evergreen_ps_size; i++)
-		*(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(evergreen_ps[i]);
+		if (num_packet2s)
+			memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4),
+				    packet2s, num_packet2s * 4);
+		for (i = 0; i < evergreen_vs_size; i++)
+			*(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(evergreen_vs[i]);
+		for (i = 0; i < evergreen_ps_size; i++)
+			*(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(evergreen_ps[i]);
+	} else {
+		memcpy_toio(ptr + rdev->r600_blit.state_offset,
+			    cayman_default_state, rdev->r600_blit.state_len * 4);
+
+		if (num_packet2s)
+			memcpy_toio(ptr + rdev->r600_blit.state_offset + (rdev->r600_blit.state_len * 4),
+				    packet2s, num_packet2s * 4);
+		for (i = 0; i < cayman_vs_size; i++)
+			*(u32 *)((unsigned long)ptr + rdev->r600_blit.vs_offset + i * 4) = cpu_to_le32(cayman_vs[i]);
+		for (i = 0; i < cayman_ps_size; i++)
+			*(u32 *)((unsigned long)ptr + rdev->r600_blit.ps_offset + i * 4) = cpu_to_le32(cayman_ps[i]);
+	}
 	radeon_bo_kunmap(rdev->r600_blit.shader_obj);
 	radeon_bo_unreserve(rdev->r600_blit.shader_obj);
 
diff --git a/drivers/gpu/drm/radeon/evergreend.h b/drivers/gpu/drm/radeon/evergreend.h
index f37e91ee8a11..1636e3449825 100644
--- a/drivers/gpu/drm/radeon/evergreend.h
+++ b/drivers/gpu/drm/radeon/evergreend.h
@@ -168,10 +168,16 @@
 #define		SE_DB_BUSY					(1 << 30)
 #define		SE_CB_BUSY					(1 << 31)
 /* evergreen */
+#define	CG_THERMAL_CTRL					0x72c
+#define		TOFFSET_MASK			        0x00003FE0
+#define		TOFFSET_SHIFT			        5
 #define	CG_MULT_THERMAL_STATUS				0x740
 #define		ASIC_T(x)			        ((x) << 16)
-#define		ASIC_T_MASK			        0x7FF0000
+#define		ASIC_T_MASK			        0x07FF0000
 #define		ASIC_T_SHIFT			        16
+#define	CG_TS0_STATUS					0x760
+#define		TS0_ADC_DOUT_MASK			0x000003FF
+#define		TS0_ADC_DOUT_SHIFT			0
 /* APU */
 #define	CG_THERMAL_STATUS			        0x678
 
diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c
index b205ba1cdd8f..16caafeadf5e 100644
--- a/drivers/gpu/drm/radeon/ni.c
+++ b/drivers/gpu/drm/radeon/ni.c
@@ -1387,14 +1387,12 @@ static int cayman_startup(struct radeon_device *rdev)
 		return r;
 	cayman_gpu_init(rdev);
 
-#if 0
-	r = cayman_blit_init(rdev);
+	r = evergreen_blit_init(rdev);
 	if (r) {
-		cayman_blit_fini(rdev);
+		evergreen_blit_fini(rdev);
 		rdev->asic->copy = NULL;
 		dev_warn(rdev->dev, "failed blitter (%d) falling back to memcpy\n", r);
 	}
-#endif
 
 	/* allocate wb buffer */
 	r = radeon_wb_init(rdev);
@@ -1452,7 +1450,7 @@ int cayman_resume(struct radeon_device *rdev)
 
 int cayman_suspend(struct radeon_device *rdev)
 {
-	/* int r; */
+	int r;
 
 	/* FIXME: we should wait for ring to be empty */
 	cayman_cp_enable(rdev, false);
@@ -1461,14 +1459,13 @@ int cayman_suspend(struct radeon_device *rdev)
 	radeon_wb_disable(rdev);
 	cayman_pcie_gart_disable(rdev);
 
-#if 0
 	/* unpin shaders bo */
 	r = radeon_bo_reserve(rdev->r600_blit.shader_obj, false);
 	if (likely(r == 0)) {
 		radeon_bo_unpin(rdev->r600_blit.shader_obj);
 		radeon_bo_unreserve(rdev->r600_blit.shader_obj);
 	}
-#endif
+
 	return 0;
 }
 
@@ -1580,7 +1577,7 @@ int cayman_init(struct radeon_device *rdev)
 
 void cayman_fini(struct radeon_device *rdev)
 {
-	/* cayman_blit_fini(rdev); */
+	evergreen_blit_fini(rdev);
 	cayman_cp_fini(rdev);
 	r600_irq_fini(rdev);
 	radeon_wb_fini(rdev);
diff --git a/drivers/gpu/drm/radeon/r600.c b/drivers/gpu/drm/radeon/r600.c
index 6f27593901c7..d74d4d71437f 100644
--- a/drivers/gpu/drm/radeon/r600.c
+++ b/drivers/gpu/drm/radeon/r600.c
@@ -87,6 +87,10 @@ MODULE_FIRMWARE("radeon/CYPRESS_rlc.bin");
 MODULE_FIRMWARE("radeon/PALM_pfp.bin");
 MODULE_FIRMWARE("radeon/PALM_me.bin");
 MODULE_FIRMWARE("radeon/SUMO_rlc.bin");
+MODULE_FIRMWARE("radeon/SUMO_pfp.bin");
+MODULE_FIRMWARE("radeon/SUMO_me.bin");
+MODULE_FIRMWARE("radeon/SUMO2_pfp.bin");
+MODULE_FIRMWARE("radeon/SUMO2_me.bin");
 
 int r600_debugfs_mc_info_init(struct radeon_device *rdev);
 
@@ -2024,6 +2028,14 @@ int r600_init_microcode(struct radeon_device *rdev)
 		chip_name = "PALM";
 		rlc_chip_name = "SUMO";
 		break;
+	case CHIP_SUMO:
+		chip_name = "SUMO";
+		rlc_chip_name = "SUMO";
+		break;
+	case CHIP_SUMO2:
+		chip_name = "SUMO2";
+		rlc_chip_name = "SUMO";
+		break;
 	default: BUG();
 	}
 
diff --git a/drivers/gpu/drm/radeon/r600_cs.c b/drivers/gpu/drm/radeon/r600_cs.c
index fd18be9871ab..909bda8dd550 100644
--- a/drivers/gpu/drm/radeon/r600_cs.c
+++ b/drivers/gpu/drm/radeon/r600_cs.c
@@ -71,20 +71,21 @@ struct r600_cs_track {
 	u64			db_bo_mc;
 };
 
-#define FMT_8_BIT(fmt, vc) [fmt] = { 1, 1, 1, vc }
-#define FMT_16_BIT(fmt, vc) [fmt] = { 1, 1, 2, vc }
-#define FMT_24_BIT(fmt) [fmt] = { 1, 1, 3, 0 }
-#define FMT_32_BIT(fmt, vc) [fmt] = { 1, 1, 4, vc }
-#define FMT_48_BIT(fmt) [fmt] = { 1, 1, 6, 0 }
-#define FMT_64_BIT(fmt, vc) [fmt] = { 1, 1, 8, vc }
-#define FMT_96_BIT(fmt) [fmt] = { 1, 1, 12, 0 }
-#define FMT_128_BIT(fmt, vc) [fmt] = { 1, 1, 16, vc }
+#define FMT_8_BIT(fmt, vc)   [fmt] = { 1, 1, 1, vc, CHIP_R600 }
+#define FMT_16_BIT(fmt, vc)  [fmt] = { 1, 1, 2, vc, CHIP_R600 }
+#define FMT_24_BIT(fmt)      [fmt] = { 1, 1, 3,  0, CHIP_R600 }
+#define FMT_32_BIT(fmt, vc)  [fmt] = { 1, 1, 4, vc, CHIP_R600 }
+#define FMT_48_BIT(fmt)      [fmt] = { 1, 1, 6,  0, CHIP_R600 }
+#define FMT_64_BIT(fmt, vc)  [fmt] = { 1, 1, 8, vc, CHIP_R600 }
+#define FMT_96_BIT(fmt)      [fmt] = { 1, 1, 12, 0, CHIP_R600 }
+#define FMT_128_BIT(fmt, vc) [fmt] = { 1, 1, 16,vc, CHIP_R600 }
 
 struct gpu_formats {
 	unsigned blockwidth;
 	unsigned blockheight;
 	unsigned blocksize;
 	unsigned valid_color;
+	enum radeon_family min_family;
 };
 
 static const struct gpu_formats color_formats_table[] = {
@@ -154,7 +155,11 @@ static const struct gpu_formats color_formats_table[] = {
 	[V_038004_FMT_BC3] = { 4, 4, 16, 0 },
 	[V_038004_FMT_BC4] = { 4, 4, 8, 0 },
 	[V_038004_FMT_BC5] = { 4, 4, 16, 0},
+	[V_038004_FMT_BC6] = { 4, 4, 16, 0, CHIP_CEDAR}, /* Evergreen-only */
+	[V_038004_FMT_BC7] = { 4, 4, 16, 0, CHIP_CEDAR}, /* Evergreen-only */
 
+	/* The other Evergreen formats */
+	[V_038004_FMT_32_AS_32_32_32_32] = { 1, 1, 4, 0, CHIP_CEDAR},
 };
 
 static inline bool fmt_is_valid_color(u32 format)
@@ -168,11 +173,14 @@ static inline bool fmt_is_valid_color(u32 format)
 	return false;
 }
 
-static inline bool fmt_is_valid_texture(u32 format)
+static inline bool fmt_is_valid_texture(u32 format, enum radeon_family family)
 {
 	if (format >= ARRAY_SIZE(color_formats_table))
 		return false;
 	
+	if (family < color_formats_table[format].min_family)
+		return false;
+
 	if (color_formats_table[format].blockwidth > 0)
 		return true;
 
@@ -1325,7 +1333,7 @@ static inline int r600_check_texture_resource(struct radeon_cs_parser *p,  u32 i
 		return -EINVAL;
 	}
 	format = G_038004_DATA_FORMAT(word1);
-	if (!fmt_is_valid_texture(format)) {
+	if (!fmt_is_valid_texture(format, p->family)) {
 		dev_warn(p->dev, "%s:%d texture invalid format %d\n",
 			 __func__, __LINE__, format);
 		return -EINVAL;
diff --git a/drivers/gpu/drm/radeon/r600d.h b/drivers/gpu/drm/radeon/r600d.h
index b2b944bcd05a..f140a0d5cb54 100644
--- a/drivers/gpu/drm/radeon/r600d.h
+++ b/drivers/gpu/drm/radeon/r600d.h
@@ -1309,6 +1309,9 @@
 #define     V_038004_FMT_BC3                           0x00000033
 #define     V_038004_FMT_BC4                           0x00000034
 #define     V_038004_FMT_BC5                           0x00000035
+#define     V_038004_FMT_BC6                           0x00000036
+#define     V_038004_FMT_BC7                           0x00000037
+#define     V_038004_FMT_32_AS_32_32_32_32             0x00000038
 #define R_038010_SQ_TEX_RESOURCE_WORD4_0             0x038010
 #define   S_038010_FORMAT_COMP_X(x)                    (((x) & 0x3) << 0)
 #define   G_038010_FORMAT_COMP_X(x)                    (((x) >> 0) & 0x3)
diff --git a/drivers/gpu/drm/radeon/radeon_asic.c b/drivers/gpu/drm/radeon/radeon_asic.c
index d948265db87e..9bd162fc9b0c 100644
--- a/drivers/gpu/drm/radeon/radeon_asic.c
+++ b/drivers/gpu/drm/radeon/radeon_asic.c
@@ -906,9 +906,9 @@ static struct radeon_asic cayman_asic = {
 	.get_vblank_counter = &evergreen_get_vblank_counter,
 	.fence_ring_emit = &r600_fence_ring_emit,
 	.cs_parse = &evergreen_cs_parse,
-	.copy_blit = NULL,
-	.copy_dma = NULL,
-	.copy = NULL,
+	.copy_blit = &evergreen_copy_blit,
+	.copy_dma = &evergreen_copy_blit,
+	.copy = &evergreen_copy_blit,
 	.get_engine_clock = &radeon_atom_get_engine_clock,
 	.set_engine_clock = &radeon_atom_set_engine_clock,
 	.get_memory_clock = &radeon_atom_get_memory_clock,
@@ -1020,6 +1020,8 @@ int radeon_asic_init(struct radeon_device *rdev)
 		rdev->asic = &evergreen_asic;
 		break;
 	case CHIP_PALM:
+	case CHIP_SUMO:
+	case CHIP_SUMO2:
 		rdev->asic = &sumo_asic;
 		break;
 	case CHIP_BARTS:
diff --git a/drivers/gpu/drm/radeon/radeon_cs.c b/drivers/gpu/drm/radeon/radeon_cs.c
index 8c1916941871..fae00c0d75aa 100644
--- a/drivers/gpu/drm/radeon/radeon_cs.c
+++ b/drivers/gpu/drm/radeon/radeon_cs.c
@@ -228,6 +228,7 @@ int radeon_cs_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
 	parser.filp = filp;
 	parser.rdev = rdev;
 	parser.dev = rdev->dev;
+	parser.family = rdev->family;
 	r = radeon_cs_parser_init(&parser, data);
 	if (r) {
 		DRM_ERROR("Failed to initialize parser !\n");
diff --git a/drivers/gpu/drm/radeon/radeon_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 5b61364e31f4..e680501c78ea 100644
--- a/drivers/gpu/drm/radeon/radeon_device.c
+++ b/drivers/gpu/drm/radeon/radeon_device.c
@@ -82,6 +82,8 @@ static const char radeon_family_name[][16] = {
 	"CYPRESS",
 	"HEMLOCK",
 	"PALM",
+	"SUMO",
+	"SUMO2",
 	"BARTS",
 	"TURKS",
 	"CAICOS",
@@ -752,6 +754,7 @@ int radeon_device_init(struct radeon_device *rdev,
 	dma_bits = rdev->need_dma32 ? 32 : 40;
 	r = pci_set_dma_mask(rdev->pdev, DMA_BIT_MASK(dma_bits));
 	if (r) {
+		rdev->need_dma32 = true;
 		printk(KERN_WARNING "radeon: No suitable DMA available.\n");
 	}
 
diff --git a/drivers/gpu/drm/radeon/radeon_display.c b/drivers/gpu/drm/radeon/radeon_display.c
index ae247eec87c0..292f73f0ddbd 100644
--- a/drivers/gpu/drm/radeon/radeon_display.c
+++ b/drivers/gpu/drm/radeon/radeon_display.c
@@ -264,6 +264,8 @@ static void radeon_unpin_work_func(struct work_struct *__work)
 		radeon_bo_unreserve(work->old_rbo);
 	} else
 		DRM_ERROR("failed to reserve buffer after flip\n");
+
+	drm_gem_object_unreference_unlocked(&work->old_rbo->gem_base);
 	kfree(work);
 }
 
@@ -371,6 +373,8 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 	new_radeon_fb = to_radeon_framebuffer(fb);
 	/* schedule unpin of the old buffer */
 	obj = old_radeon_fb->obj;
+	/* take a reference to the old object */
+	drm_gem_object_reference(obj);
 	rbo = gem_to_radeon_bo(obj);
 	work->old_rbo = rbo;
 	INIT_WORK(&work->work, radeon_unpin_work_func);
@@ -378,12 +382,9 @@ static int radeon_crtc_page_flip(struct drm_crtc *crtc,
 	/* We borrow the event spin lock for protecting unpin_work */
 	spin_lock_irqsave(&dev->event_lock, flags);
 	if (radeon_crtc->unpin_work) {
-		spin_unlock_irqrestore(&dev->event_lock, flags);
-		kfree(work);
-		radeon_fence_unref(&fence);
-
 		DRM_DEBUG_DRIVER("flip queue: crtc already busy\n");
-		return -EBUSY;
+		r = -EBUSY;
+		goto unlock_free;
 	}
 	radeon_crtc->unpin_work = work;
 	radeon_crtc->deferred_flip_completion = 0;
@@ -497,6 +498,8 @@ pflip_cleanup1:
 pflip_cleanup:
 	spin_lock_irqsave(&dev->event_lock, flags);
 	radeon_crtc->unpin_work = NULL;
+unlock_free:
+	drm_gem_object_unreference_unlocked(old_radeon_fb->obj);
 	spin_unlock_irqrestore(&dev->event_lock, flags);
 	radeon_fence_unref(&fence);
 	kfree(work);
diff --git a/drivers/gpu/drm/radeon/radeon_drv.c b/drivers/gpu/drm/radeon/radeon_drv.c
index 1d330606292f..73dfbe8e5f9e 100644
--- a/drivers/gpu/drm/radeon/radeon_drv.c
+++ b/drivers/gpu/drm/radeon/radeon_drv.c
@@ -113,7 +113,7 @@ int radeon_benchmarking = 0;
 int radeon_testing = 0;
 int radeon_connector_table = 0;
 int radeon_tv = 1;
-int radeon_audio = 1;
+int radeon_audio = 0;
 int radeon_disp_priority = 0;
 int radeon_hw_i2c = 0;
 int radeon_pcie_gen2 = 0;
@@ -151,7 +151,7 @@ module_param_named(connector_table, radeon_connector_table, int, 0444);
 MODULE_PARM_DESC(tv, "TV enable (0 = disable)");
 module_param_named(tv, radeon_tv, int, 0444);
 
-MODULE_PARM_DESC(audio, "Audio enable (0 = disable)");
+MODULE_PARM_DESC(audio, "Audio enable (1 = enable)");
 module_param_named(audio, radeon_audio, int, 0444);
 
 MODULE_PARM_DESC(disp_priority, "Display Priority (0 = auto, 1 = normal, 2 = high)");
diff --git a/drivers/gpu/drm/radeon/radeon_encoders.c b/drivers/gpu/drm/radeon/radeon_encoders.c
index 1b557554696e..03f124d626c2 100644
--- a/drivers/gpu/drm/radeon/radeon_encoders.c
+++ b/drivers/gpu/drm/radeon/radeon_encoders.c
@@ -954,10 +954,15 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 	int dp_lane_count = 0;
 	int connector_object_id = 0;
 	int igp_lane_info = 0;
+	int dig_encoder = dig->dig_encoder;
 
-	if (action == ATOM_TRANSMITTER_ACTION_INIT)
+	if (action == ATOM_TRANSMITTER_ACTION_INIT) {
 		connector = radeon_get_connector_for_encoder_init(encoder);
-	else
+		/* just needed to avoid bailing in the encoder check.  the encoder
+		 * isn't used for init
+		 */
+		dig_encoder = 0;
+	} else
 		connector = radeon_get_connector_for_encoder(encoder);
 
 	if (connector) {
@@ -973,7 +978,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 	}
 
 	/* no dig encoder assigned */
-	if (dig->dig_encoder == -1)
+	if (dig_encoder == -1)
 		return;
 
 	if (atombios_get_encoder_mode(encoder) == ATOM_ENCODER_MODE_DP)
@@ -1023,7 +1028,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 
 		if (dig->linkb)
 			args.v3.acConfig.ucLinkSel = 1;
-		if (dig->dig_encoder & 1)
+		if (dig_encoder & 1)
 			args.v3.acConfig.ucEncoderSel = 1;
 
 		/* Select the PLL for the PHY
@@ -1073,7 +1078,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 				args.v3.acConfig.fDualLinkConnector = 1;
 		}
 	} else if (ASIC_IS_DCE32(rdev)) {
-		args.v2.acConfig.ucEncoderSel = dig->dig_encoder;
+		args.v2.acConfig.ucEncoderSel = dig_encoder;
 		if (dig->linkb)
 			args.v2.acConfig.ucLinkSel = 1;
 
@@ -1100,7 +1105,7 @@ atombios_dig_transmitter_setup(struct drm_encoder *encoder, int action, uint8_t
 	} else {
 		args.v1.ucConfig = ATOM_TRANSMITTER_CONFIG_CLKSRC_PPLL;
 
-		if (dig->dig_encoder)
+		if (dig_encoder)
 			args.v1.ucConfig |= ATOM_TRANSMITTER_CONFIG_DIG2_ENCODER;
 		else
 			args.v1.ucConfig |= ATOM_TRANSMITTER_CONFIG_DIG1_ENCODER;
diff --git a/drivers/gpu/drm/radeon/radeon_family.h b/drivers/gpu/drm/radeon/radeon_family.h
index 6f1d9e563e77..ec2f1ea84f81 100644
--- a/drivers/gpu/drm/radeon/radeon_family.h
+++ b/drivers/gpu/drm/radeon/radeon_family.h
@@ -81,6 +81,8 @@ enum radeon_family {
 	CHIP_CYPRESS,
 	CHIP_HEMLOCK,
 	CHIP_PALM,
+	CHIP_SUMO,
+	CHIP_SUMO2,
 	CHIP_BARTS,
 	CHIP_TURKS,
 	CHIP_CAICOS,
diff --git a/drivers/gpu/drm/radeon/radeon_pm.c b/drivers/gpu/drm/radeon/radeon_pm.c
index 86eda1ea94df..aaa19dc418a0 100644
--- a/drivers/gpu/drm/radeon/radeon_pm.c
+++ b/drivers/gpu/drm/radeon/radeon_pm.c
@@ -487,6 +487,7 @@ static int radeon_hwmon_init(struct radeon_device *rdev)
 	case THERMAL_TYPE_RV6XX:
 	case THERMAL_TYPE_RV770:
 	case THERMAL_TYPE_EVERGREEN:
+	case THERMAL_TYPE_NI:
 	case THERMAL_TYPE_SUMO:
 		rdev->pm.int_hwmon_dev = hwmon_device_register(rdev->dev);
 		if (IS_ERR(rdev->pm.int_hwmon_dev)) {
diff --git a/drivers/gpu/drm/radeon/reg_srcs/r600 b/drivers/gpu/drm/radeon/reg_srcs/r600
index 92f1900dc7ca..ea49752ee99c 100644
--- a/drivers/gpu/drm/radeon/reg_srcs/r600
+++ b/drivers/gpu/drm/radeon/reg_srcs/r600
@@ -758,6 +758,5 @@ r600 0x9400
 0x00009714 VC_ENHANCE
 0x00009830 DB_DEBUG
 0x00009838 DB_WATERMARKS
-0x00028D28 DB_SRESULTS_COMPARE_STATE0
 0x00028D44 DB_ALPHA_TO_MASK
 0x00009700 VC_CNTL
diff --git a/drivers/media/dvb/dvb-usb/anysee.c b/drivers/media/dvb/dvb-usb/anysee.c
index 4dc1ca333236..7c327b54308e 100644
--- a/drivers/media/dvb/dvb-usb/anysee.c
+++ b/drivers/media/dvb/dvb-usb/anysee.c
@@ -60,8 +60,6 @@ static int anysee_ctrl_msg(struct dvb_usb_device *d, u8 *sbuf, u8 slen,
 	int act_len, ret;
 	u8 buf[64];
 
-	if (slen > sizeof(buf))
-		slen = sizeof(buf);
 	memcpy(&buf[0], sbuf, slen);
 	buf[60] = state->seq++;
 
@@ -180,30 +178,37 @@ static int anysee_master_xfer(struct i2c_adapter *adap, struct i2c_msg *msg,
 {
 	struct dvb_usb_device *d = i2c_get_adapdata(adap);
 	int ret = 0, inc, i = 0;
+	u8 buf[52]; /* 4 + 48 (I2C WR USB command header + I2C WR max) */
 
 	if (mutex_lock_interruptible(&d->i2c_mutex) < 0)
 		return -EAGAIN;
 
 	while (i < num) {
 		if (num > i + 1 && (msg[i+1].flags & I2C_M_RD)) {
-			u8 buf[6];
+			if (msg[i].len > 2 || msg[i+1].len > 60) {
+				ret = -EOPNOTSUPP;
+				break;
+			}
 			buf[0] = CMD_I2C_READ;
 			buf[1] = (msg[i].addr << 1) | 0x01;
 			buf[2] = msg[i].buf[0];
 			buf[3] = msg[i].buf[1];
 			buf[4] = msg[i].len-1;
 			buf[5] = msg[i+1].len;
-			ret = anysee_ctrl_msg(d, buf, sizeof(buf), msg[i+1].buf,
+			ret = anysee_ctrl_msg(d, buf, 6, msg[i+1].buf,
 				msg[i+1].len);
 			inc = 2;
 		} else {
-			u8 buf[4+msg[i].len];
+			if (msg[i].len > 48) {
+				ret = -EOPNOTSUPP;
+				break;
+			}
 			buf[0] = CMD_I2C_WRITE;
 			buf[1] = (msg[i].addr << 1);
 			buf[2] = msg[i].len;
 			buf[3] = 0x01;
 			memcpy(&buf[4], msg[i].buf, msg[i].len);
-			ret = anysee_ctrl_msg(d, buf, sizeof(buf), NULL, 0);
+			ret = anysee_ctrl_msg(d, buf, 4 + msg[i].len, NULL, 0);
 			inc = 1;
 		}
 		if (ret)
diff --git a/drivers/media/media-devnode.c b/drivers/media/media-devnode.c
index af5263c6625a..7b42ace419d9 100644
--- a/drivers/media/media-devnode.c
+++ b/drivers/media/media-devnode.c
@@ -213,14 +213,14 @@ int __must_check media_devnode_register(struct media_devnode *mdev)
 
 	/* Part 1: Find a free minor number */
 	mutex_lock(&media_devnode_lock);
-	minor = find_next_zero_bit(media_devnode_nums, 0, MEDIA_NUM_DEVICES);
+	minor = find_next_zero_bit(media_devnode_nums, MEDIA_NUM_DEVICES, 0);
 	if (minor == MEDIA_NUM_DEVICES) {
 		mutex_unlock(&media_devnode_lock);
 		printk(KERN_ERR "could not get a free minor\n");
 		return -ENFILE;
 	}
 
-	set_bit(mdev->minor, media_devnode_nums);
+	set_bit(minor, media_devnode_nums);
 	mutex_unlock(&media_devnode_lock);
 
 	mdev->minor = minor;
diff --git a/drivers/media/video/gspca/coarse_expo_autogain.h b/drivers/media/video/gspca/coarse_expo_autogain.h
deleted file mode 100644
index 1cb9d941eaf6..000000000000
--- a/drivers/media/video/gspca/coarse_expo_autogain.h
+++ /dev/null
@@ -1,116 +0,0 @@
-/*
- * Auto gain algorithm for camera's with a coarse exposure control
- *
- * Copyright (C) 2010 Hans de Goede <hdegoede@redhat.com>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
- */
-
-/* Autogain + exposure algorithm for cameras with a coarse exposure control
-   (usually this means we can only control the clockdiv to change exposure)
-   As changing the clockdiv so that the fps drops from 30 to 15 fps for
-   example, will lead to a huge exposure change (it effectively doubles),
-   this algorithm normally tries to only adjust the gain (between 40 and
-   80 %) and if that does not help, only then changes exposure. This leads
-   to a much more stable image then using the knee algorithm which at
-   certain points of the knee graph will only try to adjust exposure,
-   which leads to oscilating as one exposure step is huge.
-
-   Note this assumes that the sd struct for the cam in question has
-   exp_too_high_cnt and exp_too_high_cnt int members for use by this function.
-
-   Returns 0 if no changes were made, 1 if the gain and or exposure settings
-   where changed. */
-static int gspca_coarse_grained_expo_autogain(struct gspca_dev *gspca_dev,
-	int avg_lum, int desired_avg_lum, int deadzone)
-{
-	int i, steps, gain, orig_gain, exposure, orig_exposure;
-	int gain_low, gain_high;
-	const struct ctrl *gain_ctrl = NULL;
-	const struct ctrl *exposure_ctrl = NULL;
-	struct sd *sd = (struct sd *) gspca_dev;
-	int retval = 0;
-
-	for (i = 0; i < gspca_dev->sd_desc->nctrls; i++) {
-		if (gspca_dev->ctrl_dis & (1 << i))
-			continue;
-		if (gspca_dev->sd_desc->ctrls[i].qctrl.id == V4L2_CID_GAIN)
-			gain_ctrl = &gspca_dev->sd_desc->ctrls[i];
-		if (gspca_dev->sd_desc->ctrls[i].qctrl.id == V4L2_CID_EXPOSURE)
-			exposure_ctrl = &gspca_dev->sd_desc->ctrls[i];
-	}
-	if (!gain_ctrl || !exposure_ctrl) {
-		PDEBUG(D_ERR, "Error: gspca_coarse_grained_expo_autogain "
-			"called on cam without gain or exposure");
-		return 0;
-	}
-
-	if (gain_ctrl->get(gspca_dev, &gain) ||
-	    exposure_ctrl->get(gspca_dev, &exposure))
-		return 0;
-
-	orig_gain = gain;
-	orig_exposure = exposure;
-	gain_low =
-		(gain_ctrl->qctrl.maximum - gain_ctrl->qctrl.minimum) / 5 * 2;
-	gain_low += gain_ctrl->qctrl.minimum;
-	gain_high =
-		(gain_ctrl->qctrl.maximum - gain_ctrl->qctrl.minimum) / 5 * 4;
-	gain_high += gain_ctrl->qctrl.minimum;
-
-	/* If we are of a multiple of deadzone, do multiple steps to reach the
-	   desired lumination fast (with the risc of a slight overshoot) */
-	steps = (desired_avg_lum - avg_lum) / deadzone;
-
-	PDEBUG(D_FRAM, "autogain: lum: %d, desired: %d, steps: %d",
-		avg_lum, desired_avg_lum, steps);
-
-	if ((gain + steps) > gain_high &&
-	    sd->exposure < exposure_ctrl->qctrl.maximum) {
-		gain = gain_high;
-		sd->exp_too_low_cnt++;
-	} else if ((gain + steps) < gain_low &&
-		   sd->exposure > exposure_ctrl->qctrl.minimum) {
-		gain = gain_low;
-		sd->exp_too_high_cnt++;
-	} else {
-		gain += steps;
-		if (gain > gain_ctrl->qctrl.maximum)
-			gain = gain_ctrl->qctrl.maximum;
-		else if (gain < gain_ctrl->qctrl.minimum)
-			gain = gain_ctrl->qctrl.minimum;
-		sd->exp_too_high_cnt = 0;
-		sd->exp_too_low_cnt = 0;
-	}
-
-	if (sd->exp_too_high_cnt > 3) {
-		exposure--;
-		sd->exp_too_high_cnt = 0;
-	} else if (sd->exp_too_low_cnt > 3) {
-		exposure++;
-		sd->exp_too_low_cnt = 0;
-	}
-
-	if (gain != orig_gain) {
-		gain_ctrl->set(gspca_dev, gain);
-		retval = 1;
-	}
-	if (exposure != orig_exposure) {
-		exposure_ctrl->set(gspca_dev, exposure);
-		retval = 1;
-	}
-
-	return retval;
-}
diff --git a/drivers/media/video/gspca/ov519.c b/drivers/media/video/gspca/ov519.c
index 36a46fc78734..057e287b9152 100644
--- a/drivers/media/video/gspca/ov519.c
+++ b/drivers/media/video/gspca/ov519.c
@@ -609,7 +609,7 @@ static const struct v4l2_pix_format ovfx2_ov3610_mode[] = {
  * buffers, there are some pretty strict real time constraints for
  * isochronous transfer for larger frame sizes).
  */
-/*jfm: this value works well for 1600x1200, but not 800x600 - see isoc_init */
+/*jfm: this value does not work for 800x600 - see isoc_init */
 #define OVFX2_BULK_SIZE (13 * 4096)
 
 /* I2C registers */
@@ -3307,6 +3307,7 @@ static int sd_config(struct gspca_dev *gspca_dev,
 
 	gspca_dev->cam.ctrls = sd->ctrls;
 	sd->quality = QUALITY_DEF;
+	sd->frame_rate = 15;
 
 	return 0;
 }
@@ -3469,7 +3470,6 @@ static int sd_init(struct gspca_dev *gspca_dev)
 				ARRAY_SIZE(init_519_ov7660));
 		write_i2c_regvals(sd, norm_7660, ARRAY_SIZE(norm_7660));
 		sd->gspca_dev.curr_mode = 1;	/* 640x480 */
-		sd->frame_rate = 15;
 		ov519_set_mode(sd);
 		ov519_set_fr(sd);
 		sd->ctrls[COLORS].max = 4;	/* 0..4 */
@@ -3511,7 +3511,7 @@ static int sd_isoc_init(struct gspca_dev *gspca_dev)
 
 	switch (sd->bridge) {
 	case BRIDGE_OVFX2:
-		if (gspca_dev->width == 1600)
+		if (gspca_dev->width != 800)
 			gspca_dev->cam.bulk_size = OVFX2_BULK_SIZE;
 		else
 			gspca_dev->cam.bulk_size = 7 * 4096;
@@ -4478,7 +4478,7 @@ static void ovfx2_pkt_scan(struct gspca_dev *gspca_dev,
 	gspca_frame_add(gspca_dev, INTER_PACKET, data, len);
 
 	/* A short read signals EOF */
-	if (len < OVFX2_BULK_SIZE) {
+	if (len < gspca_dev->cam.bulk_size) {
 		/* If the frame is short, and it is one of the first ones
 		   the sensor and bridge are still syncing, so drop it. */
 		if (sd->first_frame) {
diff --git a/drivers/media/video/gspca/sonixj.c b/drivers/media/video/gspca/sonixj.c
index 6415aff5cbd1..81b8a600783b 100644
--- a/drivers/media/video/gspca/sonixj.c
+++ b/drivers/media/video/gspca/sonixj.c
@@ -60,7 +60,7 @@ struct sd {
 
 	u32 pktsz;			/* (used by pkt_scan) */
 	u16 npkt;
-	u8 nchg;
+	s8 nchg;
 	s8 short_mark;
 
 	u8 quality;			/* image quality */
diff --git a/drivers/media/video/gspca/stv06xx/stv06xx_hdcs.h b/drivers/media/video/gspca/stv06xx/stv06xx_hdcs.h
index b538dce96f78..a14a84a5079b 100644
--- a/drivers/media/video/gspca/stv06xx/stv06xx_hdcs.h
+++ b/drivers/media/video/gspca/stv06xx/stv06xx_hdcs.h
@@ -125,7 +125,7 @@
 #define HDCS_SLEEP_MODE		(1 << 1)
 
 #define HDCS_DEFAULT_EXPOSURE	48
-#define HDCS_DEFAULT_GAIN	128
+#define HDCS_DEFAULT_GAIN	50
 
 static int hdcs_probe_1x00(struct sd *sd);
 static int hdcs_probe_1020(struct sd *sd);
diff --git a/drivers/media/video/ivtv/ivtv-driver.c b/drivers/media/video/ivtv/ivtv-driver.c
index a4e4dfdbc2f2..0fb75524484d 100644
--- a/drivers/media/video/ivtv/ivtv-driver.c
+++ b/drivers/media/video/ivtv/ivtv-driver.c
@@ -1328,6 +1328,8 @@ int ivtv_init_on_first_open(struct ivtv *itv)
 	if (!itv->has_cx23415)
 		write_reg_sync(0x03, IVTV_REG_DMACONTROL);
 
+	ivtv_s_std_enc(itv, &itv->tuner_std);
+
 	/* Default interrupts enabled. For the PVR350 this includes the
 	   decoder VSYNC interrupt, which is always on. It is not only used
 	   during decoding but also by the OSD.
@@ -1336,12 +1338,10 @@ int ivtv_init_on_first_open(struct ivtv *itv)
 	if (itv->v4l2_cap & V4L2_CAP_VIDEO_OUTPUT) {
 		ivtv_clear_irq_mask(itv, IVTV_IRQ_MASK_INIT | IVTV_IRQ_DEC_VSYNC);
 		ivtv_set_osd_alpha(itv);
-	}
-	else
+		ivtv_s_std_dec(itv, &itv->tuner_std);
+	} else {
 		ivtv_clear_irq_mask(itv, IVTV_IRQ_MASK_INIT);
-
-	/* For cards with video out, this call needs interrupts enabled */
-	ivtv_s_std(NULL, &fh, &itv->tuner_std);
+	}
 
 	/* Setup initial controls */
 	cx2341x_handler_setup(&itv->cxhdl);
diff --git a/drivers/media/video/ivtv/ivtv-firmware.c b/drivers/media/video/ivtv/ivtv-firmware.c
index 14a1cea1d70d..02c5adebf517 100644
--- a/drivers/media/video/ivtv/ivtv-firmware.c
+++ b/drivers/media/video/ivtv/ivtv-firmware.c
@@ -280,8 +280,6 @@ int ivtv_firmware_restart(struct ivtv *itv)
 {
 	int rc = 0;
 	v4l2_std_id std;
-	struct ivtv_open_id fh;
-	fh.itv = itv;
 
 	if (itv->v4l2_cap & V4L2_CAP_VIDEO_OUTPUT)
 		/* Display test image during restart */
@@ -301,14 +299,19 @@ int ivtv_firmware_restart(struct ivtv *itv)
 	/* Allow settings to reload */
 	ivtv_mailbox_cache_invalidate(itv);
 
-	/* Restore video standard */
+	/* Restore encoder video standard */
 	std = itv->std;
 	itv->std = 0;
-	ivtv_s_std(NULL, &fh, &std);
+	ivtv_s_std_enc(itv, &std);
 
 	if (itv->v4l2_cap & V4L2_CAP_VIDEO_OUTPUT) {
 		ivtv_init_mpeg_decoder(itv);
 
+		/* Restore decoder video standard */
+		std = itv->std_out;
+		itv->std_out = 0;
+		ivtv_s_std_dec(itv, &std);
+
 		/* Restore framebuffer if active */
 		if (itv->ivtvfb_restore)
 			itv->ivtvfb_restore(itv);
diff --git a/drivers/media/video/ivtv/ivtv-ioctl.c b/drivers/media/video/ivtv/ivtv-ioctl.c
index 1689783cd19a..f9e347dae739 100644
--- a/drivers/media/video/ivtv/ivtv-ioctl.c
+++ b/drivers/media/video/ivtv/ivtv-ioctl.c
@@ -1071,28 +1071,8 @@ static int ivtv_g_std(struct file *file, void *fh, v4l2_std_id *std)
 	return 0;
 }
 
-int ivtv_s_std(struct file *file, void *fh, v4l2_std_id *std)
+void ivtv_s_std_enc(struct ivtv *itv, v4l2_std_id *std)
 {
-	DEFINE_WAIT(wait);
-	struct ivtv *itv = fh2id(fh)->itv;
-	struct yuv_playback_info *yi = &itv->yuv_info;
-	int f;
-
-	if ((*std & V4L2_STD_ALL) == 0)
-		return -EINVAL;
-
-	if (*std == itv->std)
-		return 0;
-
-	if (test_bit(IVTV_F_I_RADIO_USER, &itv->i_flags) ||
-	    atomic_read(&itv->capturing) > 0 ||
-	    atomic_read(&itv->decoding) > 0) {
-		/* Switching standard would turn off the radio or mess
-		   with already running streams, prevent that by
-		   returning EBUSY. */
-		return -EBUSY;
-	}
-
 	itv->std = *std;
 	itv->is_60hz = (*std & V4L2_STD_525_60) ? 1 : 0;
 	itv->is_50hz = !itv->is_60hz;
@@ -1106,48 +1086,79 @@ int ivtv_s_std(struct file *file, void *fh, v4l2_std_id *std)
 	if (itv->hw_flags & IVTV_HW_CX25840)
 		itv->vbi.sliced_decoder_line_size = itv->is_60hz ? 272 : 284;
 
-	IVTV_DEBUG_INFO("Switching standard to %llx.\n", (unsigned long long)itv->std);
-
 	/* Tuner */
 	ivtv_call_all(itv, core, s_std, itv->std);
+}
 
-	if (itv->v4l2_cap & V4L2_CAP_VIDEO_OUTPUT) {
-		/* set display standard */
-		itv->std_out = *std;
-		itv->is_out_60hz = itv->is_60hz;
-		itv->is_out_50hz = itv->is_50hz;
-		ivtv_call_all(itv, video, s_std_output, itv->std_out);
+void ivtv_s_std_dec(struct ivtv *itv, v4l2_std_id *std)
+{
+	struct yuv_playback_info *yi = &itv->yuv_info;
+	DEFINE_WAIT(wait);
+	int f;
 
-		/*
-		 * The next firmware call is time sensitive. Time it to
-		 * avoid risk of a hard lock, by trying to ensure the call
-		 * happens within the first 100 lines of the top field.
-		 * Make 4 attempts to sync to the decoder before giving up.
-		 */
-		for (f = 0; f < 4; f++) {
-			prepare_to_wait(&itv->vsync_waitq, &wait,
-					TASK_UNINTERRUPTIBLE);
-			if ((read_reg(IVTV_REG_DEC_LINE_FIELD) >> 16) < 100)
-				break;
-			schedule_timeout(msecs_to_jiffies(25));
-		}
-		finish_wait(&itv->vsync_waitq, &wait);
+	/* set display standard */
+	itv->std_out = *std;
+	itv->is_out_60hz = (*std & V4L2_STD_525_60) ? 1 : 0;
+	itv->is_out_50hz = !itv->is_out_60hz;
+	ivtv_call_all(itv, video, s_std_output, itv->std_out);
 
-		if (f == 4)
-			IVTV_WARN("Mode change failed to sync to decoder\n");
-
-		ivtv_vapi(itv, CX2341X_DEC_SET_STANDARD, 1, itv->is_out_50hz);
-		itv->main_rect.left = itv->main_rect.top = 0;
-		itv->main_rect.width = 720;
-		itv->main_rect.height = itv->cxhdl.height;
-		ivtv_vapi(itv, CX2341X_OSD_SET_FRAMEBUFFER_WINDOW, 4,
-			720, itv->main_rect.height, 0, 0);
-		yi->main_rect = itv->main_rect;
-		if (!itv->osd_info) {
-			yi->osd_full_w = 720;
-			yi->osd_full_h = itv->is_out_50hz ? 576 : 480;
-		}
+	/*
+	 * The next firmware call is time sensitive. Time it to
+	 * avoid risk of a hard lock, by trying to ensure the call
+	 * happens within the first 100 lines of the top field.
+	 * Make 4 attempts to sync to the decoder before giving up.
+	 */
+	for (f = 0; f < 4; f++) {
+		prepare_to_wait(&itv->vsync_waitq, &wait,
+				TASK_UNINTERRUPTIBLE);
+		if ((read_reg(IVTV_REG_DEC_LINE_FIELD) >> 16) < 100)
+			break;
+		schedule_timeout(msecs_to_jiffies(25));
 	}
+	finish_wait(&itv->vsync_waitq, &wait);
+
+	if (f == 4)
+		IVTV_WARN("Mode change failed to sync to decoder\n");
+
+	ivtv_vapi(itv, CX2341X_DEC_SET_STANDARD, 1, itv->is_out_50hz);
+	itv->main_rect.left = 0;
+	itv->main_rect.top = 0;
+	itv->main_rect.width = 720;
+	itv->main_rect.height = itv->is_out_50hz ? 576 : 480;
+	ivtv_vapi(itv, CX2341X_OSD_SET_FRAMEBUFFER_WINDOW, 4,
+		720, itv->main_rect.height, 0, 0);
+	yi->main_rect = itv->main_rect;
+	if (!itv->osd_info) {
+		yi->osd_full_w = 720;
+		yi->osd_full_h = itv->is_out_50hz ? 576 : 480;
+	}
+}
+
+int ivtv_s_std(struct file *file, void *fh, v4l2_std_id *std)
+{
+	struct ivtv *itv = fh2id(fh)->itv;
+
+	if ((*std & V4L2_STD_ALL) == 0)
+		return -EINVAL;
+
+	if (*std == itv->std)
+		return 0;
+
+	if (test_bit(IVTV_F_I_RADIO_USER, &itv->i_flags) ||
+	    atomic_read(&itv->capturing) > 0 ||
+	    atomic_read(&itv->decoding) > 0) {
+		/* Switching standard would mess with already running
+		   streams, prevent that by returning EBUSY. */
+		return -EBUSY;
+	}
+
+	IVTV_DEBUG_INFO("Switching standard to %llx.\n",
+		(unsigned long long)itv->std);
+
+	ivtv_s_std_enc(itv, std);
+	if (itv->v4l2_cap & V4L2_CAP_VIDEO_OUTPUT)
+		ivtv_s_std_dec(itv, std);
+
 	return 0;
 }
 
diff --git a/drivers/media/video/ivtv/ivtv-ioctl.h b/drivers/media/video/ivtv/ivtv-ioctl.h
index 58f003412afd..89185caeafae 100644
--- a/drivers/media/video/ivtv/ivtv-ioctl.h
+++ b/drivers/media/video/ivtv/ivtv-ioctl.h
@@ -27,7 +27,8 @@ u16 ivtv_get_service_set(struct v4l2_sliced_vbi_format *fmt);
 void ivtv_set_osd_alpha(struct ivtv *itv);
 int ivtv_set_speed(struct ivtv *itv, int speed);
 void ivtv_set_funcs(struct video_device *vdev);
-int ivtv_s_std(struct file *file, void *fh, v4l2_std_id *std);
+void ivtv_s_std_enc(struct ivtv *itv, v4l2_std_id *std);
+void ivtv_s_std_dec(struct ivtv *itv, v4l2_std_id *std);
 int ivtv_s_frequency(struct file *file, void *fh, struct v4l2_frequency *vf);
 int ivtv_s_input(struct file *file, void *fh, unsigned int inp);
 long ivtv_v4l2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
diff --git a/drivers/media/video/ivtv/ivtv-streams.c b/drivers/media/video/ivtv/ivtv-streams.c
index 942683336555..e7794dc1330e 100644
--- a/drivers/media/video/ivtv/ivtv-streams.c
+++ b/drivers/media/video/ivtv/ivtv-streams.c
@@ -589,7 +589,7 @@ int ivtv_start_v4l2_encode_stream(struct ivtv_stream *s)
 		v4l2_subdev_call(itv->sd_audio, audio, s_stream, 1);
 		/* Avoid unpredictable PCI bus hang - disable video clocks */
 		v4l2_subdev_call(itv->sd_video, video, s_stream, 0);
-		ivtv_msleep_timeout(300, 1);
+		ivtv_msleep_timeout(300, 0);
 		ivtv_vapi(itv, CX2341X_ENC_INITIALIZE_INPUT, 0);
 		v4l2_subdev_call(itv->sd_video, video, s_stream, 1);
 	}
@@ -834,7 +834,7 @@ int ivtv_stop_v4l2_encode_stream(struct ivtv_stream *s, int gop_end)
 		}
 
 		/* Handle any pending interrupts */
-		ivtv_msleep_timeout(100, 1);
+		ivtv_msleep_timeout(100, 0);
 	}
 
 	atomic_dec(&itv->capturing);
diff --git a/drivers/media/video/ivtv/ivtv-vbi.c b/drivers/media/video/ivtv/ivtv-vbi.c
index b6eb51ce7735..293db806d936 100644
--- a/drivers/media/video/ivtv/ivtv-vbi.c
+++ b/drivers/media/video/ivtv/ivtv-vbi.c
@@ -71,7 +71,7 @@ static void ivtv_set_wss(struct ivtv *itv, int enabled, int mode)
 	   Turning this signal on and off can confuse certain
 	   TVs. As far as I can tell there is no reason not to
 	   transmit this signal. */
-	if ((itv->std & V4L2_STD_625_50) && !enabled) {
+	if ((itv->std_out & V4L2_STD_625_50) && !enabled) {
 		enabled = 1;
 		mode = 0x08;  /* 4x3 full format */
 	}
diff --git a/drivers/media/video/ivtv/ivtvfb.c b/drivers/media/video/ivtv/ivtvfb.c
index 17247451c693..6b7c9c823330 100644
--- a/drivers/media/video/ivtv/ivtvfb.c
+++ b/drivers/media/video/ivtv/ivtvfb.c
@@ -247,7 +247,7 @@ static int ivtvfb_set_osd_coords(struct ivtv *itv, const struct ivtv_osd_coords
 
 static int ivtvfb_set_display_window(struct ivtv *itv, struct v4l2_rect *ivtv_window)
 {
-	int osd_height_limit = itv->is_50hz ? 576 : 480;
+	int osd_height_limit = itv->is_out_50hz ? 576 : 480;
 
 	/* Only fail if resolution too high, otherwise fudge the start coords. */
 	if ((ivtv_window->height > osd_height_limit) || (ivtv_window->width > IVTV_OSD_MAX_WIDTH))
@@ -471,9 +471,9 @@ static int ivtvfb_ioctl(struct fb_info *info, unsigned int cmd, unsigned long ar
 			vblank.flags = FB_VBLANK_HAVE_COUNT |FB_VBLANK_HAVE_VCOUNT |
 					FB_VBLANK_HAVE_VSYNC;
 			trace = read_reg(IVTV_REG_DEC_LINE_FIELD) >> 16;
-			if (itv->is_50hz && trace > 312)
+			if (itv->is_out_50hz && trace > 312)
 				trace -= 312;
-			else if (itv->is_60hz && trace > 262)
+			else if (itv->is_out_60hz && trace > 262)
 				trace -= 262;
 			if (trace == 1)
 				vblank.flags |= FB_VBLANK_VSYNCING;
@@ -656,7 +656,7 @@ static int _ivtvfb_check_var(struct fb_var_screeninfo *var, struct ivtv *itv)
 	IVTVFB_DEBUG_INFO("ivtvfb_check_var\n");
 
 	/* Set base references for mode calcs. */
-	if (itv->is_50hz) {
+	if (itv->is_out_50hz) {
 		pixclock = 84316;
 		hlimit = 776;
 		vlimit = 591;
@@ -784,12 +784,12 @@ static int _ivtvfb_check_var(struct fb_var_screeninfo *var, struct ivtv *itv)
 	   If the margins are too large, just center the screen
 	   (enforcing margins causes too many problems) */
 
-	if (var->left_margin + var->xres > IVTV_OSD_MAX_WIDTH + 1) {
+	if (var->left_margin + var->xres > IVTV_OSD_MAX_WIDTH + 1)
 		var->left_margin = 1 + ((IVTV_OSD_MAX_WIDTH - var->xres) / 2);
-	}
-	if (var->upper_margin + var->yres > (itv->is_50hz ? 577 : 481)) {
-		var->upper_margin = 1 + (((itv->is_50hz ? 576 : 480) - var->yres) / 2);
-	}
+
+	if (var->upper_margin + var->yres > (itv->is_out_50hz ? 577 : 481))
+		var->upper_margin = 1 + (((itv->is_out_50hz ? 576 : 480) -
+			var->yres) / 2);
 
 	/* Maintain overall 'size' for a constant refresh rate */
 	var->right_margin = hlimit - var->left_margin - var->xres;
@@ -836,7 +836,12 @@ static int ivtvfb_pan_display(struct fb_var_screeninfo *var, struct fb_info *inf
 	u32 osd_pan_index;
 	struct ivtv *itv = (struct ivtv *) info->par;
 
-	osd_pan_index = (var->xoffset + (var->yoffset * var->xres_virtual))*var->bits_per_pixel/8;
+	if (var->yoffset + info->var.yres > info->var.yres_virtual ||
+	    var->xoffset + info->var.xres > info->var.xres_virtual)
+		return -EINVAL;
+
+	osd_pan_index = var->yoffset * info->fix.line_length
+		      + var->xoffset * info->var.bits_per_pixel / 8;
 	write_reg(osd_pan_index, 0x02A0C);
 
 	/* Pass this info back the yuv handler */
@@ -1003,19 +1008,21 @@ static int ivtvfb_init_vidmode(struct ivtv *itv)
 	/* Hardware coords start at 0, user coords start at 1. */
 	osd_left--;
 
-	start_window.left = osd_left >= 0 ? osd_left : ((IVTV_OSD_MAX_WIDTH - start_window.width) / 2);
+	start_window.left = osd_left >= 0 ?
+		 osd_left : ((IVTV_OSD_MAX_WIDTH - start_window.width) / 2);
 
 	oi->display_byte_stride =
 			start_window.width * oi->bytes_per_pixel;
 
 	/* Vertical size & position */
 
-	max_height = itv->is_50hz ? 576 : 480;
+	max_height = itv->is_out_50hz ? 576 : 480;
 
 	if (osd_yres > max_height)
 		osd_yres = max_height;
 
-	start_window.height = osd_yres ? osd_yres : itv->is_50hz ? 480 : 400;
+	start_window.height = osd_yres ?
+		osd_yres : itv->is_out_50hz ? 480 : 400;
 
 	/* Check vertical start (osd_upper). */
 	if (osd_upper + start_window.height > max_height + 1) {
diff --git a/drivers/media/video/omap3isp/isp.c b/drivers/media/video/omap3isp/isp.c
index 472a69359e60..c9fd04ee70a8 100644
--- a/drivers/media/video/omap3isp/isp.c
+++ b/drivers/media/video/omap3isp/isp.c
@@ -391,7 +391,7 @@ static inline void isp_isr_dbg(struct isp_device *isp, u32 irqstatus)
 	};
 	int i;
 
-	dev_dbg(isp->dev, "");
+	dev_dbg(isp->dev, "ISP IRQ: ");
 
 	for (i = 0; i < ARRAY_SIZE(name); i++) {
 		if ((1 << i) & irqstatus)
diff --git a/drivers/media/video/soc_camera.c b/drivers/media/video/soc_camera.c
index 398864370267..4e4d4122d9a6 100644
--- a/drivers/media/video/soc_camera.c
+++ b/drivers/media/video/soc_camera.c
@@ -1512,7 +1512,7 @@ static int video_dev_create(struct soc_camera_device *icd)
  */
 static int soc_camera_video_start(struct soc_camera_device *icd)
 {
-	struct device_type *type = icd->vdev->dev.type;
+	const struct device_type *type = icd->vdev->dev.type;
 	int ret;
 
 	if (!icd->dev.parent)
diff --git a/drivers/media/video/uvc/uvc_entity.c b/drivers/media/video/uvc/uvc_entity.c
index ede7852bb1df..c3ab0c813be2 100644
--- a/drivers/media/video/uvc/uvc_entity.c
+++ b/drivers/media/video/uvc/uvc_entity.c
@@ -30,7 +30,7 @@ static int uvc_mc_register_entity(struct uvc_video_chain *chain,
 	struct uvc_entity *remote;
 	unsigned int i;
 	u8 remote_pad;
-	int ret;
+	int ret = 0;
 
 	for (i = 0; i < entity->num_pads; ++i) {
 		struct media_entity *source;
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 259ece047afc..5b2e2155b413 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -435,6 +435,9 @@ static int omap_hsmmc_reg_get(struct omap_hsmmc_host *host)
 		reg = regulator_get(host->dev, "vmmc_aux");
 		host->vcc_aux = IS_ERR(reg) ? NULL : reg;
 
+		/* For eMMC do not power off when not in sleep state */
+		if (mmc_slot(host).no_regulator_off_init)
+			return 0;
 		/*
 		* UGLY HACK:  workaround regulator framework bugs.
 		* When the bootloader leaves a supply active, it's
diff --git a/drivers/s390/cio/qdio_main.c b/drivers/s390/cio/qdio_main.c
index 55e8f721e38a..570d4da10696 100644
--- a/drivers/s390/cio/qdio_main.c
+++ b/drivers/s390/cio/qdio_main.c
@@ -416,7 +416,7 @@ static void process_buffer_error(struct qdio_q *q, int count)
 
 	/* special handling for no target buffer empty */
 	if ((!q->is_input_q &&
-	    (q->sbal[q->first_to_check]->element[15].flags & 0xff) == 0x10)) {
+	    (q->sbal[q->first_to_check]->element[15].sflags) == 0x10)) {
 		qperf_inc(q, target_full);
 		DBF_DEV_EVENT(DBF_INFO, q->irq_ptr, "OUTFULL FTC:%02x",
 			      q->first_to_check);
@@ -427,8 +427,8 @@ static void process_buffer_error(struct qdio_q *q, int count)
 	DBF_ERROR((q->is_input_q) ? "IN:%2d" : "OUT:%2d", q->nr);
 	DBF_ERROR("FTC:%3d C:%3d", q->first_to_check, count);
 	DBF_ERROR("F14:%2x F15:%2x",
-		  q->sbal[q->first_to_check]->element[14].flags & 0xff,
-		  q->sbal[q->first_to_check]->element[15].flags & 0xff);
+		  q->sbal[q->first_to_check]->element[14].sflags,
+		  q->sbal[q->first_to_check]->element[15].sflags);
 
 	/*
 	 * Interrupts may be avoided as long as the error is present
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 55c6aa1c9704..d3cee33e554c 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -361,7 +361,7 @@ enum qeth_header_ids {
 
 static inline int qeth_is_last_sbale(struct qdio_buffer_element *sbale)
 {
-	return (sbale->flags & SBAL_FLAGS_LAST_ENTRY);
+	return (sbale->eflags & SBAL_EFLAGS_LAST_ENTRY);
 }
 
 enum qeth_qdio_buffer_states {
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index 503678a30981..dd08f7b42fb8 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -890,7 +890,7 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
 	struct sk_buff *skb;
 
 	/* is PCI flag set on buffer? */
-	if (buf->buffer->element[0].flags & 0x40)
+	if (buf->buffer->element[0].sflags & SBAL_SFLAGS0_PCI_REQ)
 		atomic_dec(&queue->set_pci_flags_count);
 
 	skb = skb_dequeue(&buf->skb_list);
@@ -906,9 +906,11 @@ static void qeth_clear_output_buffer(struct qeth_qdio_out_q *queue,
 		buf->is_header[i] = 0;
 		buf->buffer->element[i].length = 0;
 		buf->buffer->element[i].addr = NULL;
-		buf->buffer->element[i].flags = 0;
+		buf->buffer->element[i].eflags = 0;
+		buf->buffer->element[i].sflags = 0;
 	}
-	buf->buffer->element[15].flags = 0;
+	buf->buffer->element[15].eflags = 0;
+	buf->buffer->element[15].sflags = 0;
 	buf->next_element_to_fill = 0;
 	atomic_set(&buf->state, QETH_QDIO_BUF_EMPTY);
 }
@@ -2368,9 +2370,10 @@ static int qeth_init_input_buffer(struct qeth_card *card,
 		buf->buffer->element[i].length = PAGE_SIZE;
 		buf->buffer->element[i].addr =  pool_entry->elements[i];
 		if (i == QETH_MAX_BUFFER_ELEMENTS(card) - 1)
-			buf->buffer->element[i].flags = SBAL_FLAGS_LAST_ENTRY;
+			buf->buffer->element[i].eflags = SBAL_EFLAGS_LAST_ENTRY;
 		else
-			buf->buffer->element[i].flags = 0;
+			buf->buffer->element[i].eflags = 0;
+		buf->buffer->element[i].sflags = 0;
 	}
 	return 0;
 }
@@ -2718,11 +2721,11 @@ int qeth_check_qdio_errors(struct qeth_card *card, struct qdio_buffer *buf,
 	if (qdio_error) {
 		QETH_CARD_TEXT(card, 2, dbftext);
 		QETH_CARD_TEXT_(card, 2, " F15=%02X",
-			       buf->element[15].flags & 0xff);
+			       buf->element[15].sflags);
 		QETH_CARD_TEXT_(card, 2, " F14=%02X",
-			       buf->element[14].flags & 0xff);
+			       buf->element[14].sflags);
 		QETH_CARD_TEXT_(card, 2, " qerr=%X", qdio_error);
-		if ((buf->element[15].flags & 0xff) == 0x12) {
+		if ((buf->element[15].sflags) == 0x12) {
 			card->stats.rx_dropped++;
 			return 0;
 		} else
@@ -2798,7 +2801,7 @@ EXPORT_SYMBOL_GPL(qeth_queue_input_buffer);
 static int qeth_handle_send_error(struct qeth_card *card,
 		struct qeth_qdio_out_buffer *buffer, unsigned int qdio_err)
 {
-	int sbalf15 = buffer->buffer->element[15].flags & 0xff;
+	int sbalf15 = buffer->buffer->element[15].sflags;
 
 	QETH_CARD_TEXT(card, 6, "hdsnderr");
 	if (card->info.type == QETH_CARD_TYPE_IQD) {
@@ -2907,8 +2910,8 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 
 	for (i = index; i < index + count; ++i) {
 		buf = &queue->bufs[i % QDIO_MAX_BUFFERS_PER_Q];
-		buf->buffer->element[buf->next_element_to_fill - 1].flags |=
-				SBAL_FLAGS_LAST_ENTRY;
+		buf->buffer->element[buf->next_element_to_fill - 1].eflags |=
+				SBAL_EFLAGS_LAST_ENTRY;
 
 		if (queue->card->info.type == QETH_CARD_TYPE_IQD)
 			continue;
@@ -2921,7 +2924,7 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 				/* it's likely that we'll go to packing
 				 * mode soon */
 				atomic_inc(&queue->set_pci_flags_count);
-				buf->buffer->element[0].flags |= 0x40;
+				buf->buffer->element[0].sflags |= SBAL_SFLAGS0_PCI_REQ;
 			}
 		} else {
 			if (!atomic_read(&queue->set_pci_flags_count)) {
@@ -2934,7 +2937,7 @@ static void qeth_flush_buffers(struct qeth_qdio_out_q *queue, int index,
 				 * further send was requested by the stack
 				 */
 				atomic_inc(&queue->set_pci_flags_count);
-				buf->buffer->element[0].flags |= 0x40;
+				buf->buffer->element[0].sflags |= SBAL_SFLAGS0_PCI_REQ;
 			}
 		}
 	}
@@ -3180,20 +3183,20 @@ static inline void __qeth_fill_buffer(struct sk_buff *skb,
 		if (!length) {
 			if (first_lap)
 				if (skb_shinfo(skb)->nr_frags)
-					buffer->element[element].flags =
-						SBAL_FLAGS_FIRST_FRAG;
+					buffer->element[element].eflags =
+						SBAL_EFLAGS_FIRST_FRAG;
 				else
-					buffer->element[element].flags = 0;
+					buffer->element[element].eflags = 0;
 			else
-				buffer->element[element].flags =
-				    SBAL_FLAGS_MIDDLE_FRAG;
+				buffer->element[element].eflags =
+				    SBAL_EFLAGS_MIDDLE_FRAG;
 		} else {
 			if (first_lap)
-				buffer->element[element].flags =
-				    SBAL_FLAGS_FIRST_FRAG;
+				buffer->element[element].eflags =
+				    SBAL_EFLAGS_FIRST_FRAG;
 			else
-				buffer->element[element].flags =
-				    SBAL_FLAGS_MIDDLE_FRAG;
+				buffer->element[element].eflags =
+				    SBAL_EFLAGS_MIDDLE_FRAG;
 		}
 		data += length_here;
 		element++;
@@ -3205,12 +3208,12 @@ static inline void __qeth_fill_buffer(struct sk_buff *skb,
 		buffer->element[element].addr = (char *)page_to_phys(frag->page)
 			+ frag->page_offset;
 		buffer->element[element].length = frag->size;
-		buffer->element[element].flags = SBAL_FLAGS_MIDDLE_FRAG;
+		buffer->element[element].eflags = SBAL_EFLAGS_MIDDLE_FRAG;
 		element++;
 	}
 
-	if (buffer->element[element - 1].flags)
-		buffer->element[element - 1].flags = SBAL_FLAGS_LAST_FRAG;
+	if (buffer->element[element - 1].eflags)
+		buffer->element[element - 1].eflags = SBAL_EFLAGS_LAST_FRAG;
 	*next_element_to_fill = element;
 }
 
@@ -3234,7 +3237,7 @@ static inline int qeth_fill_buffer(struct qeth_qdio_out_q *queue,
 		/*fill first buffer entry only with header information */
 		buffer->element[element].addr = skb->data;
 		buffer->element[element].length = hdr_len;
-		buffer->element[element].flags = SBAL_FLAGS_FIRST_FRAG;
+		buffer->element[element].eflags = SBAL_EFLAGS_FIRST_FRAG;
 		buf->next_element_to_fill++;
 		skb->data += hdr_len;
 		skb->len  -= hdr_len;
@@ -3246,7 +3249,7 @@ static inline int qeth_fill_buffer(struct qeth_qdio_out_q *queue,
 		buffer->element[element].addr = hdr;
 		buffer->element[element].length = sizeof(struct qeth_hdr) +
 							hd_len;
-		buffer->element[element].flags = SBAL_FLAGS_FIRST_FRAG;
+		buffer->element[element].eflags = SBAL_EFLAGS_FIRST_FRAG;
 		buf->is_header[element] = 1;
 		buf->next_element_to_fill++;
 	}
diff --git a/drivers/s390/scsi/zfcp_fsf.c b/drivers/s390/scsi/zfcp_fsf.c
index 8512b5c0ef82..022fb6a8cb83 100644
--- a/drivers/s390/scsi/zfcp_fsf.c
+++ b/drivers/s390/scsi/zfcp_fsf.c
@@ -640,7 +640,7 @@ static struct fsf_qtcb *zfcp_qtcb_alloc(mempool_t *pool)
 }
 
 static struct zfcp_fsf_req *zfcp_fsf_req_create(struct zfcp_qdio *qdio,
-						u32 fsf_cmd, u32 sbtype,
+						u32 fsf_cmd, u8 sbtype,
 						mempool_t *pool)
 {
 	struct zfcp_adapter *adapter = qdio->adapter;
@@ -841,7 +841,7 @@ struct zfcp_fsf_req *zfcp_fsf_abort_fcp_cmnd(struct scsi_cmnd *scmnd)
 	if (zfcp_qdio_sbal_get(qdio))
 		goto out;
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_ABORT_FCP_CMND,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.scsi_abort);
 	if (IS_ERR(req)) {
 		req = NULL;
@@ -1012,7 +1012,7 @@ int zfcp_fsf_send_ct(struct zfcp_fc_wka_port *wka_port,
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_SEND_GENERIC,
-				  SBAL_FLAGS0_TYPE_WRITE_READ, pool);
+				  SBAL_SFLAGS0_TYPE_WRITE_READ, pool);
 
 	if (IS_ERR(req)) {
 		ret = PTR_ERR(req);
@@ -1110,7 +1110,7 @@ int zfcp_fsf_send_els(struct zfcp_adapter *adapter, u32 d_id,
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_SEND_ELS,
-				  SBAL_FLAGS0_TYPE_WRITE_READ, NULL);
+				  SBAL_SFLAGS0_TYPE_WRITE_READ, NULL);
 
 	if (IS_ERR(req)) {
 		ret = PTR_ERR(req);
@@ -1156,7 +1156,7 @@ int zfcp_fsf_exchange_config_data(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_EXCHANGE_CONFIG_DATA,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1198,7 +1198,7 @@ int zfcp_fsf_exchange_config_data_sync(struct zfcp_qdio *qdio,
 		goto out_unlock;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_EXCHANGE_CONFIG_DATA,
-				  SBAL_FLAGS0_TYPE_READ, NULL);
+				  SBAL_SFLAGS0_TYPE_READ, NULL);
 
 	if (IS_ERR(req)) {
 		retval = PTR_ERR(req);
@@ -1250,7 +1250,7 @@ int zfcp_fsf_exchange_port_data(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_EXCHANGE_PORT_DATA,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1296,7 +1296,7 @@ int zfcp_fsf_exchange_port_data_sync(struct zfcp_qdio *qdio,
 		goto out_unlock;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_EXCHANGE_PORT_DATA,
-				  SBAL_FLAGS0_TYPE_READ, NULL);
+				  SBAL_SFLAGS0_TYPE_READ, NULL);
 
 	if (IS_ERR(req)) {
 		retval = PTR_ERR(req);
@@ -1412,7 +1412,7 @@ int zfcp_fsf_open_port(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_OPEN_PORT_WITH_DID,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1478,7 +1478,7 @@ int zfcp_fsf_close_port(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_CLOSE_PORT,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1553,7 +1553,7 @@ int zfcp_fsf_open_wka_port(struct zfcp_fc_wka_port *wka_port)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_OPEN_PORT_WITH_DID,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1606,7 +1606,7 @@ int zfcp_fsf_close_wka_port(struct zfcp_fc_wka_port *wka_port)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_CLOSE_PORT,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1698,7 +1698,7 @@ int zfcp_fsf_close_physical_port(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_CLOSE_PHYSICAL_PORT,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1812,7 +1812,7 @@ int zfcp_fsf_open_lun(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_OPEN_LUN,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -1901,7 +1901,7 @@ int zfcp_fsf_close_lun(struct zfcp_erp_action *erp_action)
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_CLOSE_LUN,
-				  SBAL_FLAGS0_TYPE_READ,
+				  SBAL_SFLAGS0_TYPE_READ,
 				  qdio->adapter->pool.erp_req);
 
 	if (IS_ERR(req)) {
@@ -2161,7 +2161,7 @@ int zfcp_fsf_fcp_cmnd(struct scsi_cmnd *scsi_cmnd)
 {
 	struct zfcp_fsf_req *req;
 	struct fcp_cmnd *fcp_cmnd;
-	unsigned int sbtype = SBAL_FLAGS0_TYPE_READ;
+	u8 sbtype = SBAL_SFLAGS0_TYPE_READ;
 	int real_bytes, retval = -EIO, dix_bytes = 0;
 	struct scsi_device *sdev = scsi_cmnd->device;
 	struct zfcp_scsi_dev *zfcp_sdev = sdev_to_zfcp(sdev);
@@ -2181,7 +2181,7 @@ int zfcp_fsf_fcp_cmnd(struct scsi_cmnd *scsi_cmnd)
 	}
 
 	if (scsi_cmnd->sc_data_direction == DMA_TO_DEVICE)
-		sbtype = SBAL_FLAGS0_TYPE_WRITE;
+		sbtype = SBAL_SFLAGS0_TYPE_WRITE;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_FCP_CMND,
 				  sbtype, adapter->pool.scsi_req);
@@ -2280,7 +2280,7 @@ struct zfcp_fsf_req *zfcp_fsf_fcp_task_mgmt(struct scsi_cmnd *scmnd,
 		goto out;
 
 	req = zfcp_fsf_req_create(qdio, FSF_QTCB_FCP_CMND,
-				  SBAL_FLAGS0_TYPE_WRITE,
+				  SBAL_SFLAGS0_TYPE_WRITE,
 				  qdio->adapter->pool.scsi_req);
 
 	if (IS_ERR(req)) {
@@ -2328,17 +2328,18 @@ struct zfcp_fsf_req *zfcp_fsf_control_file(struct zfcp_adapter *adapter,
 	struct zfcp_qdio *qdio = adapter->qdio;
 	struct zfcp_fsf_req *req = NULL;
 	struct fsf_qtcb_bottom_support *bottom;
-	int direction, retval = -EIO, bytes;
+	int retval = -EIO, bytes;
+	u8 direction;
 
 	if (!(adapter->adapter_features & FSF_FEATURE_CFDC))
 		return ERR_PTR(-EOPNOTSUPP);
 
 	switch (fsf_cfdc->command) {
 	case FSF_QTCB_DOWNLOAD_CONTROL_FILE:
-		direction = SBAL_FLAGS0_TYPE_WRITE;
+		direction = SBAL_SFLAGS0_TYPE_WRITE;
 		break;
 	case FSF_QTCB_UPLOAD_CONTROL_FILE:
-		direction = SBAL_FLAGS0_TYPE_READ;
+		direction = SBAL_SFLAGS0_TYPE_READ;
 		break;
 	default:
 		return ERR_PTR(-EINVAL);
@@ -2413,7 +2414,7 @@ void zfcp_fsf_reqid_check(struct zfcp_qdio *qdio, int sbal_idx)
 		fsf_req->qdio_req.sbal_response = sbal_idx;
 		zfcp_fsf_req_complete(fsf_req);
 
-		if (likely(sbale->flags & SBAL_FLAGS_LAST_ENTRY))
+		if (likely(sbale->eflags & SBAL_EFLAGS_LAST_ENTRY))
 			break;
 	}
 }
diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c
index 98e97d90835b..d9c40ea73eef 100644
--- a/drivers/s390/scsi/zfcp_qdio.c
+++ b/drivers/s390/scsi/zfcp_qdio.c
@@ -124,7 +124,7 @@ zfcp_qdio_sbal_chain(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req)
 
 	/* set last entry flag in current SBALE of current SBAL */
 	sbale = zfcp_qdio_sbale_curr(qdio, q_req);
-	sbale->flags |= SBAL_FLAGS_LAST_ENTRY;
+	sbale->eflags |= SBAL_EFLAGS_LAST_ENTRY;
 
 	/* don't exceed last allowed SBAL */
 	if (q_req->sbal_last == q_req->sbal_limit)
@@ -132,7 +132,7 @@ zfcp_qdio_sbal_chain(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req)
 
 	/* set chaining flag in first SBALE of current SBAL */
 	sbale = zfcp_qdio_sbale_req(qdio, q_req);
-	sbale->flags |= SBAL_FLAGS0_MORE_SBALS;
+	sbale->sflags |= SBAL_SFLAGS0_MORE_SBALS;
 
 	/* calculate index of next SBAL */
 	q_req->sbal_last++;
@@ -147,7 +147,7 @@ zfcp_qdio_sbal_chain(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req)
 
 	/* set storage-block type for new SBAL */
 	sbale = zfcp_qdio_sbale_curr(qdio, q_req);
-	sbale->flags |= q_req->sbtype;
+	sbale->sflags |= q_req->sbtype;
 
 	return sbale;
 }
@@ -177,7 +177,7 @@ int zfcp_qdio_sbals_from_sg(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req,
 
 	/* set storage-block type for this request */
 	sbale = zfcp_qdio_sbale_req(qdio, q_req);
-	sbale->flags |= q_req->sbtype;
+	sbale->sflags |= q_req->sbtype;
 
 	for (; sg; sg = sg_next(sg)) {
 		sbale = zfcp_qdio_sbale_next(qdio, q_req);
@@ -384,7 +384,8 @@ int zfcp_qdio_open(struct zfcp_qdio *qdio)
 	for (cc = 0; cc < QDIO_MAX_BUFFERS_PER_Q; cc++) {
 		sbale = &(qdio->res_q[cc]->element[0]);
 		sbale->length = 0;
-		sbale->flags = SBAL_FLAGS_LAST_ENTRY;
+		sbale->eflags = SBAL_EFLAGS_LAST_ENTRY;
+		sbale->sflags = 0;
 		sbale->addr = NULL;
 	}
 
diff --git a/drivers/s390/scsi/zfcp_qdio.h b/drivers/s390/scsi/zfcp_qdio.h
index 2297d8d3e947..54e22ace012b 100644
--- a/drivers/s390/scsi/zfcp_qdio.h
+++ b/drivers/s390/scsi/zfcp_qdio.h
@@ -67,7 +67,7 @@ struct zfcp_qdio {
  * @qdio_outb_usage: usage of outbound queue
  */
 struct zfcp_qdio_req {
-	u32	sbtype;
+	u8	sbtype;
 	u8	sbal_number;
 	u8	sbal_first;
 	u8	sbal_last;
@@ -116,7 +116,7 @@ zfcp_qdio_sbale_curr(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req)
  */
 static inline
 void zfcp_qdio_req_init(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req,
-			unsigned long req_id, u32 sbtype, void *data, u32 len)
+			unsigned long req_id, u8 sbtype, void *data, u32 len)
 {
 	struct qdio_buffer_element *sbale;
 	int count = min(atomic_read(&qdio->req_q_free),
@@ -131,7 +131,8 @@ void zfcp_qdio_req_init(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req,
 
 	sbale = zfcp_qdio_sbale_req(qdio, q_req);
 	sbale->addr = (void *) req_id;
-	sbale->flags = SBAL_FLAGS0_COMMAND | sbtype;
+	sbale->eflags = 0;
+	sbale->sflags = SBAL_SFLAGS0_COMMAND | sbtype;
 
 	if (unlikely(!data))
 		return;
@@ -173,7 +174,7 @@ void zfcp_qdio_set_sbale_last(struct zfcp_qdio *qdio,
 	struct qdio_buffer_element *sbale;
 
 	sbale = zfcp_qdio_sbale_curr(qdio, q_req);
-	sbale->flags |= SBAL_FLAGS_LAST_ENTRY;
+	sbale->eflags |= SBAL_EFLAGS_LAST_ENTRY;
 }
 
 /**
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index f1a7918d71aa..6c9b7cd6778a 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -413,8 +413,7 @@ static void flush_to_ldisc(struct work_struct *work)
 	spin_lock_irqsave(&tty->buf.lock, flags);
 
 	if (!test_and_set_bit(TTY_FLUSHING, &tty->flags)) {
-		struct tty_buffer *head, *tail = tty->buf.tail;
-		int seen_tail = 0;
+		struct tty_buffer *head;
 		while ((head = tty->buf.head) != NULL) {
 			int count;
 			char *char_buf;
@@ -424,15 +423,6 @@ static void flush_to_ldisc(struct work_struct *work)
 			if (!count) {
 				if (head->next == NULL)
 					break;
-				/*
-				  There's a possibility tty might get new buffer
-				  added during the unlock window below. We could
-				  end up spinning in here forever hogging the CPU
-				  completely. To avoid this let's have a rest each
-				  time we processed the tail buffer.
-				*/
-				if (tail == head)
-					seen_tail = 1;
 				tty->buf.head = head->next;
 				tty_buffer_free(tty, head);
 				continue;
@@ -442,7 +432,7 @@ static void flush_to_ldisc(struct work_struct *work)
 			   line discipline as we want to empty the queue */
 			if (test_bit(TTY_FLUSHPENDING, &tty->flags))
 				break;
-			if (!tty->receive_room || seen_tail)
+			if (!tty->receive_room)
 				break;
 			if (count > tty->receive_room)
 				count = tty->receive_room;
diff --git a/drivers/video/arcfb.c b/drivers/video/arcfb.c
index 3ec4923c2d84..c22e8d39a2cb 100644
--- a/drivers/video/arcfb.c
+++ b/drivers/video/arcfb.c
@@ -515,11 +515,10 @@ static int __devinit arcfb_probe(struct platform_device *dev)
 
 	/* We need a flat backing store for the Arc's
 	   less-flat actual paged framebuffer */
-	if (!(videomemory = vmalloc(videomemorysize)))
+	videomemory = vzalloc(videomemorysize);
+	if (!videomemory)
 		return retval;
 
-	memset(videomemory, 0, videomemorysize);
-
 	info = framebuffer_alloc(sizeof(struct arcfb_par), &dev->dev);
 	if (!info)
 		goto err;
diff --git a/drivers/video/bf537-lq035.c b/drivers/video/bf537-lq035.c
index 47c21fb2c82f..bea53c1a4950 100644
--- a/drivers/video/bf537-lq035.c
+++ b/drivers/video/bf537-lq035.c
@@ -789,6 +789,7 @@ static int __devinit bfin_lq035_probe(struct platform_device *pdev)
 	i2c_add_driver(&ad5280_driver);
 
 	memset(&props, 0, sizeof(props));
+	props.type = BACKLIGHT_RAW;
 	props.max_brightness = MAX_BRIGHENESS;
 	bl_dev = backlight_device_register("bf537-bl", NULL, NULL,
 					   &bfin_lq035fb_bl_ops, &props);
diff --git a/drivers/video/broadsheetfb.c b/drivers/video/broadsheetfb.c
index ebda6876d3a9..377dde3d5bfc 100644
--- a/drivers/video/broadsheetfb.c
+++ b/drivers/video/broadsheetfb.c
@@ -1101,12 +1101,10 @@ static int __devinit broadsheetfb_probe(struct platform_device *dev)
 
 	videomemorysize = roundup((dpyw*dpyh), PAGE_SIZE);
 
-	videomemory = vmalloc(videomemorysize);
+	videomemory = vzalloc(videomemorysize);
 	if (!videomemory)
 		goto err_fb_rel;
 
-	memset(videomemory, 0, videomemorysize);
-
 	info->screen_base = (char *)videomemory;
 	info->fbops = &broadsheetfb_ops;
 
diff --git a/drivers/video/efifb.c b/drivers/video/efifb.c
index fb205843c2c7..69c49dfce9cf 100644
--- a/drivers/video/efifb.c
+++ b/drivers/video/efifb.c
@@ -16,6 +16,8 @@
 #include <linux/pci.h>
 #include <video/vga.h>
 
+static bool request_mem_succeeded = false;
+
 static struct fb_var_screeninfo efifb_defined __devinitdata = {
 	.activate		= FB_ACTIVATE_NOW,
 	.height			= -1,
@@ -281,7 +283,9 @@ static void efifb_destroy(struct fb_info *info)
 {
 	if (info->screen_base)
 		iounmap(info->screen_base);
-	release_mem_region(info->apertures->ranges[0].base, info->apertures->ranges[0].size);
+	if (request_mem_succeeded)
+		release_mem_region(info->apertures->ranges[0].base,
+				   info->apertures->ranges[0].size);
 	framebuffer_release(info);
 }
 
@@ -326,14 +330,13 @@ static int __init efifb_setup(char *options)
 	return 0;
 }
 
-static int __devinit efifb_probe(struct platform_device *dev)
+static int __init efifb_probe(struct platform_device *dev)
 {
 	struct fb_info *info;
 	int err;
 	unsigned int size_vmode;
 	unsigned int size_remap;
 	unsigned int size_total;
-	int request_succeeded = 0;
 
 	if (!screen_info.lfb_depth)
 		screen_info.lfb_depth = 32;
@@ -387,7 +390,7 @@ static int __devinit efifb_probe(struct platform_device *dev)
 	efifb_fix.smem_len = size_remap;
 
 	if (request_mem_region(efifb_fix.smem_start, size_remap, "efifb")) {
-		request_succeeded = 1;
+		request_mem_succeeded = true;
 	} else {
 		/* We cannot make this fatal. Sometimes this comes from magic
 		   spaces our resource handlers simply don't know about */
@@ -413,7 +416,7 @@ static int __devinit efifb_probe(struct platform_device *dev)
 	info->apertures->ranges[0].base = efifb_fix.smem_start;
 	info->apertures->ranges[0].size = size_remap;
 
-	info->screen_base = ioremap(efifb_fix.smem_start, efifb_fix.smem_len);
+	info->screen_base = ioremap_wc(efifb_fix.smem_start, efifb_fix.smem_len);
 	if (!info->screen_base) {
 		printk(KERN_ERR "efifb: abort, cannot ioremap video memory "
 				"0x%x @ 0x%lx\n",
@@ -491,13 +494,12 @@ err_unmap:
 err_release_fb:
 	framebuffer_release(info);
 err_release_mem:
-	if (request_succeeded)
+	if (request_mem_succeeded)
 		release_mem_region(efifb_fix.smem_start, size_total);
 	return err;
 }
 
 static struct platform_driver efifb_driver = {
-	.probe	= efifb_probe,
 	.driver	= {
 		.name	= "efifb",
 	},
@@ -528,13 +530,21 @@ static int __init efifb_init(void)
 	if (!screen_info.lfb_linelength)
 		return -ENODEV;
 
-	ret = platform_driver_register(&efifb_driver);
+	ret = platform_device_register(&efifb_device);
+	if (ret)
+		return ret;
 
-	if (!ret) {
-		ret = platform_device_register(&efifb_device);
-		if (ret)
-			platform_driver_unregister(&efifb_driver);
+	/*
+	 * This is not just an optimization.  We will interfere
+	 * with a real driver if we get reprobed, so don't allow
+	 * it.
+	 */
+	ret = platform_driver_probe(&efifb_driver, efifb_probe);
+	if (ret) {
+		platform_device_unregister(&efifb_driver);
+		return ret;
 	}
+
 	return ret;
 }
 module_init(efifb_init);
diff --git a/drivers/video/hecubafb.c b/drivers/video/hecubafb.c
index 1b94643ecbcf..fbef15f7a218 100644
--- a/drivers/video/hecubafb.c
+++ b/drivers/video/hecubafb.c
@@ -231,11 +231,10 @@ static int __devinit hecubafb_probe(struct platform_device *dev)
 
 	videomemorysize = (DPY_W*DPY_H)/8;
 
-	if (!(videomemory = vmalloc(videomemorysize)))
+	videomemory = vzalloc(videomemorysize);
+	if (!videomemory)
 		return retval;
 
-	memset(videomemory, 0, videomemorysize);
-
 	info = framebuffer_alloc(sizeof(struct hecubafb_par), &dev->dev);
 	if (!info)
 		goto err_fballoc;
diff --git a/drivers/video/imxfb.c b/drivers/video/imxfb.c
index d2ccfd6e662c..f135dbead07d 100644
--- a/drivers/video/imxfb.c
+++ b/drivers/video/imxfb.c
@@ -856,10 +856,10 @@ failed_platform_init:
 		dma_free_writecombine(&pdev->dev,fbi->map_size,fbi->map_cpu,
 			fbi->map_dma);
 failed_map:
-	clk_put(fbi->clk);
-failed_getclock:
 	iounmap(fbi->regs);
 failed_ioremap:
+	clk_put(fbi->clk);
+failed_getclock:
 	release_mem_region(res->start, resource_size(res));
 failed_req:
 	kfree(info->pseudo_palette);
diff --git a/drivers/video/metronomefb.c b/drivers/video/metronomefb.c
index ed64edfd2c43..97d45e5115e2 100644
--- a/drivers/video/metronomefb.c
+++ b/drivers/video/metronomefb.c
@@ -628,12 +628,10 @@ static int __devinit metronomefb_probe(struct platform_device *dev)
 	/* we need to add a spare page because our csum caching scheme walks
 	 * to the end of the page */
 	videomemorysize = PAGE_SIZE + (fw * fh);
-	videomemory = vmalloc(videomemorysize);
+	videomemory = vzalloc(videomemorysize);
 	if (!videomemory)
 		goto err_fb_rel;
 
-	memset(videomemory, 0, videomemorysize);
-
 	info->screen_base = (char __force __iomem *)videomemory;
 	info->fbops = &metronomefb_ops;
 
diff --git a/drivers/video/modedb.c b/drivers/video/modedb.c
index 48c3ea8652b6..cb175fe7abc0 100644
--- a/drivers/video/modedb.c
+++ b/drivers/video/modedb.c
@@ -1128,3 +1128,4 @@ EXPORT_SYMBOL(fb_find_best_mode);
 EXPORT_SYMBOL(fb_find_nearest_mode);
 EXPORT_SYMBOL(fb_videomode_to_modelist);
 EXPORT_SYMBOL(fb_find_mode);
+EXPORT_SYMBOL(fb_find_mode_cvt);
diff --git a/drivers/video/pxa168fb.c b/drivers/video/pxa168fb.c
index 35f61dd0cb3a..bb95ec56d25d 100644
--- a/drivers/video/pxa168fb.c
+++ b/drivers/video/pxa168fb.c
@@ -623,19 +623,21 @@ static int __devinit pxa168fb_probe(struct platform_device *pdev)
 	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (res == NULL) {
 		dev_err(&pdev->dev, "no IO memory defined\n");
-		return -ENOENT;
+		ret = -ENOENT;
+		goto failed_put_clk;
 	}
 
 	irq = platform_get_irq(pdev, 0);
 	if (irq < 0) {
 		dev_err(&pdev->dev, "no IRQ defined\n");
-		return -ENOENT;
+		ret = -ENOENT;
+		goto failed_put_clk;
 	}
 
 	info = framebuffer_alloc(sizeof(struct pxa168fb_info), &pdev->dev);
 	if (info == NULL) {
-		clk_put(clk);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto failed_put_clk;
 	}
 
 	/* Initialize private data */
@@ -671,7 +673,7 @@ static int __devinit pxa168fb_probe(struct platform_device *pdev)
 	fbi->reg_base = ioremap_nocache(res->start, resource_size(res));
 	if (fbi->reg_base == NULL) {
 		ret = -ENOMEM;
-		goto failed;
+		goto failed_free_info;
 	}
 
 	/*
@@ -683,7 +685,7 @@ static int __devinit pxa168fb_probe(struct platform_device *pdev)
 						&fbi->fb_start_dma, GFP_KERNEL);
 	if (info->screen_base == NULL) {
 		ret = -ENOMEM;
-		goto failed;
+		goto failed_free_info;
 	}
 
 	info->fix.smem_start = (unsigned long)fbi->fb_start_dma;
@@ -772,8 +774,9 @@ failed_free_clk:
 failed_free_fbmem:
 	dma_free_coherent(fbi->dev, info->fix.smem_len,
 			info->screen_base, fbi->fb_start_dma);
-failed:
+failed_free_info:
 	kfree(info);
+failed_put_clk:
 	clk_put(clk);
 
 	dev_err(&pdev->dev, "frame buffer device init failed with %d\n", ret);
diff --git a/drivers/video/savage/savagefb_driver.c b/drivers/video/savage/savagefb_driver.c
index 3b7f2f5bae71..4de541ca9c52 100644
--- a/drivers/video/savage/savagefb_driver.c
+++ b/drivers/video/savage/savagefb_driver.c
@@ -2237,6 +2237,22 @@ static int __devinit savagefb_probe(struct pci_dev* dev,
 				 &info->modelist);
 #endif
 	info->var = savagefb_var800x600x8;
+	/* if a panel was detected, default to a CVT mode instead */
+	if (par->SavagePanelWidth) {
+		struct fb_videomode cvt_mode;
+
+		memset(&cvt_mode, 0, sizeof(cvt_mode));
+		cvt_mode.xres = par->SavagePanelWidth;
+		cvt_mode.yres = par->SavagePanelHeight;
+		cvt_mode.refresh = 60;
+		/* FIXME: if we know there is only the panel
+		 * we can enable reduced blanking as well */
+		if (fb_find_mode_cvt(&cvt_mode, 0, 0))
+			printk(KERN_WARNING "No CVT mode found for panel\n");
+		else if (fb_find_mode(&info->var, info, NULL, NULL, 0,
+				      &cvt_mode, 0) != 3)
+			info->var = savagefb_var800x600x8;
+	}
 
 	if (mode_option) {
 		fb_find_mode(&info->var, info, mode_option,
diff --git a/drivers/video/sh_mobile_lcdcfb.c b/drivers/video/sh_mobile_lcdcfb.c
index 404c03b4b7c7..019dbd3f12b2 100644
--- a/drivers/video/sh_mobile_lcdcfb.c
+++ b/drivers/video/sh_mobile_lcdcfb.c
@@ -470,7 +470,7 @@ static int sh_mobile_lcdc_start(struct sh_mobile_lcdc_priv *priv)
 	unsigned long tmp;
 	int bpp = 0;
 	unsigned long ldddsr;
-	int k, m;
+	int k, m, ret;
 
 	/* enable clocks before accessing the hardware */
 	for (k = 0; k < ARRAY_SIZE(priv->ch); k++) {
@@ -540,7 +540,7 @@ static int sh_mobile_lcdc_start(struct sh_mobile_lcdc_priv *priv)
 
 		board_cfg = &ch->cfg.board_cfg;
 		if (board_cfg->setup_sys) {
-			int ret = board_cfg->setup_sys(board_cfg->board_data,
+			ret = board_cfg->setup_sys(board_cfg->board_data,
 						ch, &sh_mobile_lcdc_sys_bus_ops);
 			if (ret)
 				return ret;
diff --git a/drivers/video/vga16fb.c b/drivers/video/vga16fb.c
index 53b2c5aae067..305c975b1787 100644
--- a/drivers/video/vga16fb.c
+++ b/drivers/video/vga16fb.c
@@ -1265,9 +1265,11 @@ static void vga16fb_imageblit(struct fb_info *info, const struct fb_image *image
 
 static void vga16fb_destroy(struct fb_info *info)
 {
+	struct platform_device *dev = container_of(info->device, struct platform_device, dev);
 	iounmap(info->screen_base);
 	fb_dealloc_cmap(&info->cmap);
 	/* XXX unshare VGA regions */
+	platform_set_drvdata(dev, NULL);
 	framebuffer_release(info);
 }
 
diff --git a/drivers/video/xen-fbfront.c b/drivers/video/xen-fbfront.c
index a20218c2fda8..beac52fc1c0e 100644
--- a/drivers/video/xen-fbfront.c
+++ b/drivers/video/xen-fbfront.c
@@ -395,10 +395,9 @@ static int __devinit xenfb_probe(struct xenbus_device *dev,
 	spin_lock_init(&info->dirty_lock);
 	spin_lock_init(&info->resize_lock);
 
-	info->fb = vmalloc(fb_size);
+	info->fb = vzalloc(fb_size);
 	if (info->fb == NULL)
 		goto error_nomem;
-	memset(info->fb, 0, fb_size);
 
 	info->nr_pages = (fb_size + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 117e74e3604b..0bb4ebbb71b7 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -825,7 +825,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	} else {
 		char b[BDEVNAME_SIZE];
 
-		s->s_flags = flags;
+		s->s_flags = flags | MS_NOSEC;
 		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
 		error = btrfs_fill_super(s, fs_devices, data,
 					 flags & MS_SILENT ? 1 : 0);
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 7257752b6d5d..7018e1d8902d 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -102,7 +102,7 @@ static int fat_ioctl_set_attributes(struct file *file, u32 __user *user_attr)
 		if (attr & ATTR_SYS)
 			inode->i_flags |= S_IMMUTABLE;
 		else
-			inode->i_flags &= S_IMMUTABLE;
+			inode->i_flags &= ~S_IMMUTABLE;
 	}
 
 	fat_save_attrs(inode, attr);
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index cc6ec4b2f0ff..38f84cd48b67 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -921,6 +921,8 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	if (sb->s_flags & MS_MANDLOCK)
 		goto err;
 
+	sb->s_flags &= ~MS_NOSEC;
+
 	if (!parse_fuse_opt((char *) data, &d, is_bdev))
 		goto err;
 
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 2792a790e50b..1c1336e7b3b2 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -663,14 +663,19 @@ static void glock_work_func(struct work_struct *work)
 		drop_ref = 1;
 	}
 	spin_lock(&gl->gl_spin);
-	if (test_and_clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
 	    gl->gl_state != LM_ST_UNLOCKED &&
 	    gl->gl_demote_state != LM_ST_EXCLUSIVE) {
 		unsigned long holdtime, now = jiffies;
+
 		holdtime = gl->gl_tchange + gl->gl_ops->go_min_hold_time;
 		if (time_before(now, holdtime))
 			delay = holdtime - now;
-		set_bit(delay ? GLF_PENDING_DEMOTE : GLF_DEMOTE, &gl->gl_flags);
+
+		if (!delay) {
+			clear_bit(GLF_PENDING_DEMOTE, &gl->gl_flags);
+			set_bit(GLF_DEMOTE, &gl->gl_flags);
+		}
 	}
 	run_queue(gl, 0);
 	spin_unlock(&gl->gl_spin);
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index 278e3fb40b71..583636f745e5 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -1123,7 +1123,7 @@ int lmLogOpen(struct super_block *sb)
 	bdev = blkdev_get_by_dev(sbi->logdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
 				 log);
 	if (IS_ERR(bdev)) {
-		rc = -PTR_ERR(bdev);
+		rc = PTR_ERR(bdev);
 		goto free;
 	}
 
diff --git a/fs/namei.c b/fs/namei.c
index e2e4e8d032ee..9802345df5e7 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -2624,6 +2624,10 @@ static long do_rmdir(int dfd, const char __user *pathname)
 	error = PTR_ERR(dentry);
 	if (IS_ERR(dentry))
 		goto exit2;
+	if (!dentry->d_inode) {
+		error = -ENOENT;
+		goto exit3;
+	}
 	error = mnt_want_write(nd.path.mnt);
 	if (error)
 		goto exit3;
@@ -2709,11 +2713,10 @@ static long do_unlinkat(int dfd, const char __user *pathname)
 	error = PTR_ERR(dentry);
 	if (!IS_ERR(dentry)) {
 		/* Why not before? Because we want correct error value */
-		if (nd.last.name[nd.last.len])
-			goto slashes;
 		inode = dentry->d_inode;
-		if (inode)
-			ihold(inode);
+		if (nd.last.name[nd.last.len] || !inode)
+			goto slashes;
+		ihold(inode);
 		error = mnt_want_write(nd.path.mnt);
 		if (error)
 			goto exit2;
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index cdbaf5e97308..56f61027236b 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1072,7 +1072,7 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 
 	sb->s_magic = OCFS2_SUPER_MAGIC;
 
-	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
+	sb->s_flags = (sb->s_flags & ~(MS_POSIXACL | MS_NOSEC)) |
 		((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ? MS_POSIXACL : 0);
 
 	/* Hard readonly mode only if: bdev_read_only, MS_RDONLY,
diff --git a/fs/super.c b/fs/super.c
index c75593953c52..ab3d672db0de 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -822,7 +822,7 @@ struct dentry *mount_bdev(struct file_system_type *fs_type,
 	} else {
 		char b[BDEVNAME_SIZE];
 
-		s->s_flags = flags;
+		s->s_flags = flags | MS_NOSEC;
 		s->s_mode = mode;
 		strlcpy(s->s_id, bdevname(bdev, b), sizeof(s->s_id));
 		sb_set_blocksize(s, block_size(bdev));
diff --git a/include/drm/drm_pciids.h b/include/drm/drm_pciids.h
index f04b2a3b0f49..e08f344c6cff 100644
--- a/include/drm/drm_pciids.h
+++ b/include/drm/drm_pciids.h
@@ -467,6 +467,17 @@
 	{0x1002, 0x9614, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9615, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9616, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS780|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9640, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9641, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9642, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9643, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9644, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9645, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO2|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x9647, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+	{0x1002, 0x9648, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+	{0x1002, 0x964a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
+	{0x1002, 0x964e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
+	{0x1002, 0x964f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_SUMO|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP},\
 	{0x1002, 0x9710, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9711, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
 	{0x1002, 0x9712, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_RS880|RADEON_IS_MOBILITY|RADEON_NEW_MEMMAP|RADEON_IS_IGP}, \
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c55d6b7cd5d6..646a1836152a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -208,6 +208,7 @@ struct inodes_stat_t {
 #define MS_KERNMOUNT	(1<<22) /* this is a kern_mount call */
 #define MS_I_VERSION	(1<<23) /* Update inode I_version field */
 #define MS_STRICTATIME	(1<<24) /* Always perform atime updates */
+#define MS_NOSEC	(1<<28)
 #define MS_BORN		(1<<29)
 #define MS_ACTIVE	(1<<30)
 #define MS_NOUSER	(1<<31)
@@ -2591,7 +2592,7 @@ static inline int is_sxid(mode_t mode)
 
 static inline void inode_has_no_xattr(struct inode *inode)
 {
-	if (!is_sxid(inode->i_mode))
+	if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & MS_NOSEC))
 		inode->i_flags |= S_NOSEC;
 }
 
diff --git a/include/linux/irqreturn.h b/include/linux/irqreturn.h
index 819acaaac3f5..714ba08dc092 100644
--- a/include/linux/irqreturn.h
+++ b/include/linux/irqreturn.h
@@ -8,9 +8,9 @@
  * @IRQ_WAKE_THREAD	handler requests to wake the handler thread
  */
 enum irqreturn {
-	IRQ_NONE,
-	IRQ_HANDLED,
-	IRQ_WAKE_THREAD,
+	IRQ_NONE		= (0 << 0),
+	IRQ_HANDLED		= (1 << 0),
+	IRQ_WAKE_THREAD		= (1 << 1),
 };
 
 typedef enum irqreturn irqreturn_t;
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 3412684ce5d5..e0786e35f247 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -137,14 +137,14 @@ enum perf_event_sample_format {
  *
  * struct read_format {
  *	{ u64		value;
- *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
- *	  { u64		time_running; } && PERF_FORMAT_RUNNING
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		id;           } && PERF_FORMAT_ID
  *	} && !PERF_FORMAT_GROUP
  *
  *	{ u64		nr;
- *	  { u64		time_enabled; } && PERF_FORMAT_ENABLED
- *	  { u64		time_running; } && PERF_FORMAT_RUNNING
+ *	  { u64		time_enabled; } && PERF_FORMAT_TOTAL_TIME_ENABLED
+ *	  { u64		time_running; } && PERF_FORMAT_TOTAL_TIME_RUNNING
  *	  { u64		value;
  *	    { u64	id;           } && PERF_FORMAT_ID
  *	  }		cntr[nr];
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2a8621c4be1e..a837b20ba190 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1063,6 +1063,7 @@ struct sched_domain;
  */
 #define WF_SYNC		0x01		/* waker goes to sleep after wakup */
 #define WF_FORK		0x02		/* child wakeup after fork */
+#define WF_MIGRATED	0x04		/* internal use, task got migrated */
 
 #define ENQUEUE_WAKEUP		1
 #define ENQUEUE_HEAD		2
diff --git a/include/media/v4l2-dev.h b/include/media/v4l2-dev.h
index 93e96fb93452..c7c40f1d2624 100644
--- a/include/media/v4l2-dev.h
+++ b/include/media/v4l2-dev.h
@@ -128,8 +128,8 @@ struct video_device
 	struct mutex *lock;
 };
 
-#define media_entity_to_video_device(entity) \
-	container_of(entity, struct video_device, entity)
+#define media_entity_to_video_device(__e) \
+	container_of(__e, struct video_device, entity)
 /* dev to video-device */
 #define to_video_device(cd) container_of(cd, struct video_device, dev)
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index d863b3c057bb..9efe7108ccaf 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7402,26 +7402,12 @@ static int __perf_cgroup_move(void *info)
 	return 0;
 }
 
-static void perf_cgroup_move(struct task_struct *task)
+static void
+perf_cgroup_attach_task(struct cgroup *cgrp, struct task_struct *task)
 {
 	task_function_call(task, __perf_cgroup_move, task);
 }
 
-static void perf_cgroup_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
-		struct cgroup *old_cgrp, struct task_struct *task,
-		bool threadgroup)
-{
-	perf_cgroup_move(task);
-	if (threadgroup) {
-		struct task_struct *c;
-		rcu_read_lock();
-		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
-			perf_cgroup_move(c);
-		}
-		rcu_read_unlock();
-	}
-}
-
 static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
 		struct cgroup *old_cgrp, struct task_struct *task)
 {
@@ -7433,7 +7419,7 @@ static void perf_cgroup_exit(struct cgroup_subsys *ss, struct cgroup *cgrp,
 	if (!(task->flags & PF_EXITING))
 		return;
 
-	perf_cgroup_move(task);
+	perf_cgroup_attach_task(cgrp, task);
 }
 
 struct cgroup_subsys perf_subsys = {
@@ -7442,6 +7428,6 @@ struct cgroup_subsys perf_subsys = {
 	.create		= perf_cgroup_create,
 	.destroy	= perf_cgroup_destroy,
 	.exit		= perf_cgroup_exit,
-	.attach		= perf_cgroup_attach,
+	.attach_task	= perf_cgroup_attach_task,
 };
 #endif /* CONFIG_CGROUP_PERF */
diff --git a/kernel/irq/handle.c b/kernel/irq/handle.c
index 90cb55f6d7eb..470d08c82bbe 100644
--- a/kernel/irq/handle.c
+++ b/kernel/irq/handle.c
@@ -132,12 +132,6 @@ handle_irq_event_percpu(struct irq_desc *desc, struct irqaction *action)
 
 		switch (res) {
 		case IRQ_WAKE_THREAD:
-			/*
-			 * Set result to handled so the spurious check
-			 * does not trigger.
-			 */
-			res = IRQ_HANDLED;
-
 			/*
 			 * Catch drivers which return WAKE_THREAD but
 			 * did not set up a thread function
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 886e80347b32..4c60a50e66b2 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -257,13 +257,11 @@ int __init early_irq_init(void)
 	count = ARRAY_SIZE(irq_desc);
 
 	for (i = 0; i < count; i++) {
-		desc[i].irq_data.irq = i;
-		desc[i].irq_data.chip = &no_irq_chip;
 		desc[i].kstat_irqs = alloc_percpu(unsigned int);
-		irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS);
-		alloc_masks(desc + i, GFP_KERNEL, node);
-		desc_smp_init(desc + i, node);
+		alloc_masks(&desc[i], GFP_KERNEL, node);
+		raw_spin_lock_init(&desc[i].lock);
 		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
+		desc_set_defaults(i, &desc[i], node);
 	}
 	return arch_early_irq_init();
 }
@@ -346,6 +344,12 @@ irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
 	if (!cnt)
 		return -EINVAL;
 
+	if (irq >= 0) {
+		if (from > irq)
+			return -EINVAL;
+		from = irq;
+	}
+
 	mutex_lock(&sparse_irq_lock);
 
 	start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS,
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index f7ce0021e1c4..d64bafb1afd0 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -723,13 +723,16 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
  * context. So we need to disable bh here to avoid deadlocks and other
  * side effects.
  */
-static void
+static irqreturn_t
 irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
 {
+	irqreturn_t ret;
+
 	local_bh_disable();
-	action->thread_fn(action->irq, action->dev_id);
+	ret = action->thread_fn(action->irq, action->dev_id);
 	irq_finalize_oneshot(desc, action, false);
 	local_bh_enable();
+	return ret;
 }
 
 /*
@@ -737,10 +740,14 @@ irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
  * preemtible - many of them need to sleep and wait for slow busses to
  * complete.
  */
-static void irq_thread_fn(struct irq_desc *desc, struct irqaction *action)
+static irqreturn_t irq_thread_fn(struct irq_desc *desc,
+		struct irqaction *action)
 {
-	action->thread_fn(action->irq, action->dev_id);
+	irqreturn_t ret;
+
+	ret = action->thread_fn(action->irq, action->dev_id);
 	irq_finalize_oneshot(desc, action, false);
+	return ret;
 }
 
 /*
@@ -753,7 +760,8 @@ static int irq_thread(void *data)
 	};
 	struct irqaction *action = data;
 	struct irq_desc *desc = irq_to_desc(action->irq);
-	void (*handler_fn)(struct irq_desc *desc, struct irqaction *action);
+	irqreturn_t (*handler_fn)(struct irq_desc *desc,
+			struct irqaction *action);
 	int wake;
 
 	if (force_irqthreads & test_bit(IRQTF_FORCED_THREAD,
@@ -783,8 +791,12 @@ static int irq_thread(void *data)
 			desc->istate |= IRQS_PENDING;
 			raw_spin_unlock_irq(&desc->lock);
 		} else {
+			irqreturn_t action_ret;
+
 			raw_spin_unlock_irq(&desc->lock);
-			handler_fn(desc, action);
+			action_ret = handler_fn(desc, action);
+			if (!noirqdebug)
+				note_interrupt(action->irq, desc, action_ret);
 		}
 
 		wake = atomic_dec_and_test(&desc->threads_active);
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index dfbd550401b2..aa57d5da18c1 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -167,6 +167,13 @@ out:
 		  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);
 }
 
+static inline int bad_action_ret(irqreturn_t action_ret)
+{
+	if (likely(action_ret <= (IRQ_HANDLED | IRQ_WAKE_THREAD)))
+		return 0;
+	return 1;
+}
+
 /*
  * If 99,900 of the previous 100,000 interrupts have not been handled
  * then assume that the IRQ is stuck in some manner. Drop a diagnostic
@@ -182,7 +189,7 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc,
 	struct irqaction *action;
 	unsigned long flags;
 
-	if (action_ret != IRQ_HANDLED && action_ret != IRQ_NONE) {
+	if (bad_action_ret(action_ret)) {
 		printk(KERN_ERR "irq event %d: bogus return value %x\n",
 				irq, action_ret);
 	} else {
@@ -201,10 +208,11 @@ __report_bad_irq(unsigned int irq, struct irq_desc *desc,
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	action = desc->action;
 	while (action) {
-		printk(KERN_ERR "[<%p>]", action->handler);
-		print_symbol(" (%s)",
-			(unsigned long)action->handler);
-		printk("\n");
+		printk(KERN_ERR "[<%p>] %pf", action->handler, action->handler);
+		if (action->thread_fn)
+			printk(KERN_CONT " threaded [<%p>] %pf",
+					action->thread_fn, action->thread_fn);
+		printk(KERN_CONT "\n");
 		action = action->next;
 	}
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -262,7 +270,16 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 	if (desc->istate & IRQS_POLL_INPROGRESS)
 		return;
 
-	if (unlikely(action_ret != IRQ_HANDLED)) {
+	/* we get here again via the threaded handler */
+	if (action_ret == IRQ_WAKE_THREAD)
+		return;
+
+	if (bad_action_ret(action_ret)) {
+		report_bad_irq(irq, desc, action_ret);
+		return;
+	}
+
+	if (unlikely(action_ret == IRQ_NONE)) {
 		/*
 		 * If we are seeing only the odd spurious IRQ caused by
 		 * bus asynchronicity then don't eventually trigger an error,
@@ -274,8 +291,6 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		else
 			desc->irqs_unhandled++;
 		desc->last_unhandled = jiffies;
-		if (unlikely(action_ret != IRQ_NONE))
-			report_bad_irq(irq, desc, action_ret);
 	}
 
 	if (unlikely(try_misrouted_irq(irq, desc, action_ret))) {
diff --git a/kernel/lockdep.c b/kernel/lockdep.c
index 63437d065ac8..298c9276dfdb 100644
--- a/kernel/lockdep.c
+++ b/kernel/lockdep.c
@@ -3426,7 +3426,7 @@ int lock_is_held(struct lockdep_map *lock)
 	int ret = 0;
 
 	if (unlikely(current->lockdep_recursion))
-		return ret;
+		return 1; /* avoid false negative lockdep_assert_held() */
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
diff --git a/kernel/sched.c b/kernel/sched.c
index cbb3a0eee58e..3f2e502d609b 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -605,10 +605,10 @@ static inline int cpu_of(struct rq *rq)
 /*
  * Return the group to which this tasks belongs.
  *
- * We use task_subsys_state_check() and extend the RCU verification
- * with lockdep_is_held(&p->pi_lock) because cpu_cgroup_attach()
- * holds that lock for each task it moves into the cgroup. Therefore
- * by holding that lock, we pin the task to the current cgroup.
+ * We use task_subsys_state_check() and extend the RCU verification with
+ * pi->lock and rq->lock because cpu_cgroup_attach() holds those locks for each
+ * task it moves into the cgroup. Therefore by holding either of those locks,
+ * we pin the task to the current cgroup.
  */
 static inline struct task_group *task_group(struct task_struct *p)
 {
@@ -616,7 +616,8 @@ static inline struct task_group *task_group(struct task_struct *p)
 	struct cgroup_subsys_state *css;
 
 	css = task_subsys_state_check(p, cpu_cgroup_subsys_id,
-			lockdep_is_held(&p->pi_lock));
+			lockdep_is_held(&p->pi_lock) ||
+			lockdep_is_held(&task_rq(p)->lock));
 	tg = container_of(css, struct task_group, css);
 
 	return autogroup_task_group(p, tg);
@@ -2200,6 +2201,16 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 			!(task_thread_info(p)->preempt_count & PREEMPT_ACTIVE));
 
 #ifdef CONFIG_LOCKDEP
+	/*
+	 * The caller should hold either p->pi_lock or rq->lock, when changing
+	 * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
+	 *
+	 * sched_move_task() holds both and thus holding either pins the cgroup,
+	 * see set_task_rq().
+	 *
+	 * Furthermore, all task_rq users should acquire both locks, see
+	 * task_rq_lock().
+	 */
 	WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
 				      lockdep_is_held(&task_rq(p)->lock)));
 #endif
@@ -2447,6 +2458,10 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 		}
 		rcu_read_unlock();
 	}
+
+	if (wake_flags & WF_MIGRATED)
+		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
+
 #endif /* CONFIG_SMP */
 
 	schedstat_inc(rq, ttwu_count);
@@ -2455,9 +2470,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 	if (wake_flags & WF_SYNC)
 		schedstat_inc(p, se.statistics.nr_wakeups_sync);
 
-	if (cpu != task_cpu(p))
-		schedstat_inc(p, se.statistics.nr_wakeups_migrate);
-
 #endif /* CONFIG_SCHEDSTATS */
 }
 
@@ -2600,6 +2612,7 @@ static void ttwu_queue(struct task_struct *p, int cpu)
 
 #if defined(CONFIG_SMP)
 	if (sched_feat(TTWU_QUEUE) && cpu != smp_processor_id()) {
+		sched_clock_cpu(cpu); /* sync clocks x-cpu */
 		ttwu_queue_remote(p, cpu);
 		return;
 	}
@@ -2674,8 +2687,10 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
 		p->sched_class->task_waking(p);
 
 	cpu = select_task_rq(p, SD_BALANCE_WAKE, wake_flags);
-	if (task_cpu(p) != cpu)
+	if (task_cpu(p) != cpu) {
+		wake_flags |= WF_MIGRATED;
 		set_task_cpu(p, cpu);
+	}
 #endif /* CONFIG_SMP */
 
 	ttwu_queue(p, cpu);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 4fc92445a29c..f175d98bd355 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -938,6 +938,12 @@ static struct ctl_table kern_table[] = {
 	},
 #endif
 #ifdef CONFIG_PERF_EVENTS
+	/*
+	 * User-space scripts rely on the existence of this file
+	 * as a feature check for perf_events being enabled.
+	 *
+	 * So it's an ABI, do not remove!
+	 */
 	{
 		.procname	= "perf_event_paranoid",
 		.data		= &sysctl_perf_event_paranoid,
diff --git a/kernel/time/clockevents.c b/kernel/time/clockevents.c
index c027d4f602f1..e4c699dfa4e8 100644
--- a/kernel/time/clockevents.c
+++ b/kernel/time/clockevents.c
@@ -182,7 +182,10 @@ void clockevents_register_device(struct clock_event_device *dev)
 	unsigned long flags;
 
 	BUG_ON(dev->mode != CLOCK_EVT_MODE_UNUSED);
-	BUG_ON(!dev->cpumask);
+	if (!dev->cpumask) {
+		WARN_ON(num_possible_cpus() > 1);
+		dev->cpumask = cpumask_of(smp_processor_id());
+	}
 
 	raw_spin_lock_irqsave(&clockevents_lock, flags);
 
diff --git a/kernel/timer.c b/kernel/timer.c
index fd6198692b57..8cff36119e4d 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -749,16 +749,15 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
 	unsigned long expires_limit, mask;
 	int bit;
 
-	expires_limit = expires;
-
 	if (timer->slack >= 0) {
 		expires_limit = expires + timer->slack;
 	} else {
-		unsigned long now = jiffies;
+		long delta = expires - jiffies;
 
-		/* No slack, if already expired else auto slack 0.4% */
-		if (time_after(expires, now))
-			expires_limit = expires + (expires - now)/256;
+		if (delta < 256)
+			return expires;
+
+		expires_limit = expires + delta / 256;
 	}
 	mask = expires ^ expires_limit;
 	if (mask == 0)
@@ -795,6 +794,8 @@ unsigned long apply_slack(struct timer_list *timer, unsigned long expires)
  */
 int mod_timer(struct timer_list *timer, unsigned long expires)
 {
+	expires = apply_slack(timer, expires);
+
 	/*
 	 * This is a common optimization triggered by the
 	 * networking code - if the timer is re-modified
@@ -803,8 +804,6 @@ int mod_timer(struct timer_list *timer, unsigned long expires)
 	if (timer_pending(timer) && timer->expires == expires)
 		return 1;
 
-	expires = apply_slack(timer, expires);
-
 	return __mod_timer(timer, expires, false, TIMER_NOT_PINNED);
 }
 EXPORT_SYMBOL(mod_timer);
diff --git a/mm/filemap.c b/mm/filemap.c
index d7b10578a64b..a8251a8d3457 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2000,7 +2000,7 @@ int file_remove_suid(struct file *file)
 		error = security_inode_killpriv(dentry);
 	if (!error && killsuid)
 		error = __remove_suid(dentry, killsuid);
-	if (!error)
+	if (!error && (inode->i_sb->s_flags & MS_NOSEC))
 		inode->i_flags |= S_NOSEC;
 
 	return error;
diff --git a/tools/perf/builtin-test.c b/tools/perf/builtin-test.c
index b67186228c89..2da9162262b0 100644
--- a/tools/perf/builtin-test.c
+++ b/tools/perf/builtin-test.c
@@ -474,7 +474,7 @@ static int test__basic_mmap(void)
 	unsigned int nr_events[nsyscalls],
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
-	int sample_size = perf_sample_size(attr.sample_type);
+	int sample_size = __perf_evsel__sample_size(attr.sample_type);
 
 	for (i = 0; i < nsyscalls; ++i) {
 		char name[64];
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 0fe9adf76379..3c1b8a632101 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -35,22 +35,6 @@ const char *perf_event__name(unsigned int id)
 	return perf_event__names[id];
 }
 
-int perf_sample_size(u64 sample_type)
-{
-	u64 mask = sample_type & PERF_SAMPLE_MASK;
-	int size = 0;
-	int i;
-
-	for (i = 0; i < 64; i++) {
-		if (mask & (1ULL << i))
-			size++;
-	}
-
-	size *= sizeof(u64);
-
-	return size;
-}
-
 static struct perf_sample synth_sample = {
 	.pid	   = -1,
 	.tid	   = -1,
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index c08332871408..1d7f66488a88 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -82,8 +82,6 @@ struct perf_sample {
 	struct ip_callchain *callchain;
 };
 
-int perf_sample_size(u64 sample_type);
-
 #define BUILD_ID_SIZE 20
 
 struct build_id_event {
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 50aa34879c33..b021ea9265c3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -12,7 +12,6 @@
 #include "evlist.h"
 #include "evsel.h"
 #include "util.h"
-#include "debug.h"
 
 #include <sys/mman.h>
 
@@ -257,19 +256,15 @@ int perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 	return evlist->mmap != NULL ? 0 : -ENOMEM;
 }
 
-static int __perf_evlist__mmap(struct perf_evlist *evlist, struct perf_evsel *evsel,
+static int __perf_evlist__mmap(struct perf_evlist *evlist,
 			       int idx, int prot, int mask, int fd)
 {
 	evlist->mmap[idx].prev = 0;
 	evlist->mmap[idx].mask = mask;
 	evlist->mmap[idx].base = mmap(NULL, evlist->mmap_len, prot,
 				      MAP_SHARED, fd, 0);
-	if (evlist->mmap[idx].base == MAP_FAILED) {
-		if (evlist->cpus->map[idx] == -1 && evsel->attr.inherit)
-			ui__warning("Inherit is not allowed on per-task "
-				    "events using mmap.\n");
+	if (evlist->mmap[idx].base == MAP_FAILED)
 		return -1;
-	}
 
 	perf_evlist__add_pollfd(evlist, fd);
 	return 0;
@@ -289,7 +284,7 @@ static int perf_evlist__mmap_per_cpu(struct perf_evlist *evlist, int prot, int m
 
 				if (output == -1) {
 					output = fd;
-					if (__perf_evlist__mmap(evlist, evsel, cpu,
+					if (__perf_evlist__mmap(evlist, cpu,
 								prot, mask, output) < 0)
 						goto out_unmap;
 				} else {
@@ -329,7 +324,7 @@ static int perf_evlist__mmap_per_thread(struct perf_evlist *evlist, int prot, in
 
 			if (output == -1) {
 				output = fd;
-				if (__perf_evlist__mmap(evlist, evsel, thread,
+				if (__perf_evlist__mmap(evlist, thread,
 							prot, mask, output) < 0)
 					goto out_unmap;
 			} else {
@@ -460,33 +455,46 @@ int perf_evlist__set_filters(struct perf_evlist *evlist)
 	return 0;
 }
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist)
+bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist)
 {
-	struct perf_evsel *pos;
-	u64 type = 0;
+	struct perf_evsel *pos, *first;
 
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (!type)
-			type = pos->attr.sample_type;
-		else if (type != pos->attr.sample_type)
-			die("non matching sample_type");
+	pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	list_for_each_entry_continue(pos, &evlist->entries, node) {
+		if (first->attr.sample_type != pos->attr.sample_type)
+			return false;
 	}
 
-	return type;
+	return true;
+}
+
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *first;
+
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return first->attr.sample_type;
+}
+
+bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist)
+{
+	struct perf_evsel *pos, *first;
+
+	pos = first = list_entry(evlist->entries.next, struct perf_evsel, node);
+
+	list_for_each_entry_continue(pos, &evlist->entries, node) {
+		if (first->attr.sample_id_all != pos->attr.sample_id_all)
+			return false;
+	}
+
+	return true;
 }
 
 bool perf_evlist__sample_id_all(const struct perf_evlist *evlist)
 {
-	bool value = false, first = true;
-	struct perf_evsel *pos;
+	struct perf_evsel *first;
 
-	list_for_each_entry(pos, &evlist->entries, node) {
-		if (first) {
-			value = pos->attr.sample_id_all;
-			first = false;
-		} else if (value != pos->attr.sample_id_all)
-			die("non matching sample_id_all");
-	}
-
-	return value;
+	first = list_entry(evlist->entries.next, struct perf_evsel, node);
+	return first->attr.sample_id_all;
 }
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 0a1ef1f051f0..b2b862374f37 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -66,7 +66,9 @@ int perf_evlist__create_maps(struct perf_evlist *evlist, pid_t target_pid,
 void perf_evlist__delete_maps(struct perf_evlist *evlist);
 int perf_evlist__set_filters(struct perf_evlist *evlist);
 
-u64 perf_evlist__sample_type(struct perf_evlist *evlist);
-bool perf_evlist__sample_id_all(const struct perf_evlist *evlist);
+u64 perf_evlist__sample_type(const struct perf_evlist *evlist);
+bool perf_evlist__sample_id_all(const const struct perf_evlist *evlist);
 
+bool perf_evlist__valid_sample_type(const struct perf_evlist *evlist);
+bool perf_evlist__valid_sample_id_all(const struct perf_evlist *evlist);
 #endif /* __PERF_EVLIST_H */
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index cca29ededb5b..0239eb87b232 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -15,6 +15,22 @@
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
+int __perf_evsel__sample_size(u64 sample_type)
+{
+	u64 mask = sample_type & PERF_SAMPLE_MASK;
+	int size = 0;
+	int i;
+
+	for (i = 0; i < 64; i++) {
+		if (mask & (1ULL << i))
+			size++;
+	}
+
+	size *= sizeof(u64);
+
+	return size;
+}
+
 void perf_evsel__init(struct perf_evsel *evsel,
 		      struct perf_event_attr *attr, int idx)
 {
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index f79bb2c09a6c..7e9366e4490b 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -149,4 +149,11 @@ static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read(evsel, ncpus, nthreads, true);
 }
 
+int __perf_evsel__sample_size(u64 sample_type);
+
+static inline int perf_evsel__sample_size(struct perf_evsel *evsel)
+{
+	return __perf_evsel__sample_size(evsel->attr.sample_type);
+}
+
 #endif /* __PERF_EVSEL_H */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 69436b3200a4..a9ac0504aabd 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -674,7 +674,7 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	struct perf_evlist *evlist = &pevlist->evlist;
 	union perf_event *event;
 	int sample_id_all = 1, cpu;
-	static char *kwlist[] = {"sample_id_all", NULL, NULL};
+	static char *kwlist[] = {"cpu", "sample_id_all", NULL, NULL};
 	int err;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
@@ -692,16 +692,14 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 
 		first = list_entry(evlist->entries.next, struct perf_evsel, node);
 		err = perf_event__parse_sample(event, first->attr.sample_type,
-					       perf_sample_size(first->attr.sample_type),
+					       perf_evsel__sample_size(first),
 					       sample_id_all, &pevent->sample);
-		if (err) {
-			pr_err("Can't parse sample, err = %d\n", err);
-			goto end;
-		}
-
+		if (err)
+			return PyErr_Format(PyExc_OSError,
+					    "perf: can't parse sample, err=%d", err);
 		return pyevent;
 	}
-end:
+
 	Py_INCREF(Py_None);
 	return Py_None;
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 64500fc78799..f5a8fbdd3f76 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -58,6 +58,16 @@ static int perf_session__open(struct perf_session *self, bool force)
 		goto out_close;
 	}
 
+	if (!perf_evlist__valid_sample_type(self->evlist)) {
+		pr_err("non matching sample_type");
+		goto out_close;
+	}
+
+	if (!perf_evlist__valid_sample_id_all(self->evlist)) {
+		pr_err("non matching sample_id_all");
+		goto out_close;
+	}
+
 	self->size = input_stat.st_size;
 	return 0;
 
@@ -97,7 +107,7 @@ out:
 void perf_session__update_sample_type(struct perf_session *self)
 {
 	self->sample_type = perf_evlist__sample_type(self->evlist);
-	self->sample_size = perf_sample_size(self->sample_type);
+	self->sample_size = __perf_evsel__sample_size(self->sample_type);
 	self->sample_id_all = perf_evlist__sample_id_all(self->evlist);
 	perf_session__id_header_size(self);
 }
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 22cdb960660a..96ebc0679415 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -467,12 +467,8 @@ static struct kvm *kvm_create_vm(void)
 		if (!kvm->buses[i])
 			goto out_err;
 	}
+
 	spin_lock_init(&kvm->mmu_lock);
-
-	r = kvm_init_mmu_notifier(kvm);
-	if (r)
-		goto out_err;
-
 	kvm->mm = current->mm;
 	atomic_inc(&kvm->mm->mm_count);
 	kvm_eventfd_init(kvm);
@@ -480,6 +476,11 @@ static struct kvm *kvm_create_vm(void)
 	mutex_init(&kvm->irq_lock);
 	mutex_init(&kvm->slots_lock);
 	atomic_set(&kvm->users_count, 1);
+
+	r = kvm_init_mmu_notifier(kvm);
+	if (r)
+		goto out_err;
+
 	raw_spin_lock(&kvm_lock);
 	list_add(&kvm->vm_list, &vm_list);
 	raw_spin_unlock(&kvm_lock);
@@ -651,7 +652,9 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	/* We can read the guest memory with __xxx_user() later on. */
 	if (user_alloc &&
 	    ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
-	     !access_ok(VERIFY_WRITE, mem->userspace_addr, mem->memory_size)))
+	     !access_ok(VERIFY_WRITE,
+			(void __user *)(unsigned long)mem->userspace_addr,
+			mem->memory_size)))
 		goto out;
 	if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS)
 		goto out;