275 files changed, 3179 insertions, 2134 deletions

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/Makefile b/Makefile
index afb8e0d26f2c..0f1db8d90741 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
 VERSION = 3
 PATCHLEVEL = 0
 SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Sneaky Weasel
 
 # *DOCUMENTATION*
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
@@ -85,17 +85,17 @@ 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;
-        }
-
-        gpio_direction_input(gpio_pendown);
-        gpio_export(gpio_pendown, 0);
+        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);
+                if (gpio_debounce)
+                        gpio_set_debounce(gpio_pendown, gpio_debounce);
+        }
 
         ads7846_config.gpio_pendown = gpio_pendown;
 
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/mach-shmobile/board-ap4evb.c b/arch/arm/mach-shmobile/board-ap4evb.c
index 08acb6ec8139..f6b687f61c28 100644
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@@ -249,6 +249,29 @@ static int slot_cn7_get_cd(struct platform_device *pdev)
 {
         return !gpio_get_value(GPIO_PORT41);
 }
+/* MERAM */
+static struct sh_mobile_meram_info meram_info = {
+        .addr_mode      = SH_MOBILE_MERAM_MODE1,
+};
+
+static struct resource meram_resources[] = {
+        [0] = {
+                .name   = "MERAM",
+                .start  = 0xe8000000,
+                .end    = 0xe81fffff,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device meram_device = {
+        .name           = "sh_mobile_meram",
+        .id             = 0,
+        .num_resources  = ARRAY_SIZE(meram_resources),
+        .resource       = meram_resources,
+        .dev            = {
+                .platform_data = &meram_info,
+        },
+};
 
 /* SH_MMCIF */
 static struct resource sh_mmcif_resources[] = {
@@ -447,13 +470,29 @@ const static struct fb_videomode ap4evb_lcdc_modes[] = {
 #endif
         },
 };
+static struct sh_mobile_meram_cfg lcd_meram_cfg = {
+        .icb[0] = {
+                .marker_icb     = 28,
+                .cache_icb      = 24,
+                .meram_offset   = 0x0,
+                .meram_size     = 0x40,
+        },
+        .icb[1] = {
+                .marker_icb     = 29,
+                .cache_icb      = 25,
+                .meram_offset   = 0x40,
+                .meram_size     = 0x40,
+        },
+};
 
 static struct sh_mobile_lcdc_info lcdc_info = {
+        .meram_dev = &meram_info,
         .ch[0] = {
                 .chan = LCDC_CHAN_MAINLCD,
                 .bpp = 16,
                 .lcd_cfg = ap4evb_lcdc_modes,
                 .num_cfg = ARRAY_SIZE(ap4evb_lcdc_modes),
+                .meram_cfg = &lcd_meram_cfg,
         }
 };
 
@@ -724,15 +763,31 @@ static struct platform_device fsi_device = {
 static struct platform_device fsi_ak4643_device = {
         .name           = "sh_fsi2_a_ak4643",
 };
+static struct sh_mobile_meram_cfg hdmi_meram_cfg = {
+        .icb[0] = {
+                .marker_icb     = 30,
+                .cache_icb      = 26,
+                .meram_offset   = 0x80,
+                .meram_size     = 0x100,
+        },
+        .icb[1] = {
+                .marker_icb     = 31,
+                .cache_icb      = 27,
+                .meram_offset   = 0x180,
+                .meram_size     = 0x100,
+        },
+};
 
 static struct sh_mobile_lcdc_info sh_mobile_lcdc1_info = {
         .clock_source = LCDC_CLK_EXTERNAL,
+        .meram_dev = &meram_info,
         .ch[0] = {
                 .chan = LCDC_CHAN_MAINLCD,
                 .bpp = 16,
                 .interface_type = RGB24,
                 .clock_divider = 1,
                 .flags = LCDC_FLAGS_DWPOL,
+                .meram_cfg = &hdmi_meram_cfg,
         }
 };
 
@@ -961,6 +1016,7 @@ static struct platform_device *ap4evb_devices[] __initdata = {
         &csi2_device,
         &ceu_device,
         &ap4evb_camera,
+        &meram_device,
 };
 
 static void __init hdmi_init_pm_clock(void)
diff --git a/arch/arm/mach-shmobile/board-mackerel.c b/arch/arm/mach-shmobile/board-mackerel.c
index 448ddbe43335..776f20560e72 100644
--- a/arch/arm/mach-shmobile/board-mackerel.c
+++ b/arch/arm/mach-shmobile/board-mackerel.c
@@ -39,6 +39,7 @@
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
 #include <linux/mtd/physmap.h>
+#include <linux/pm_runtime.h>
 #include <linux/smsc911x.h>
 #include <linux/sh_intc.h>
 #include <linux/tca6416_keypad.h>
@@ -314,6 +315,30 @@ static struct platform_device smc911x_device = {
         },
 };
 
+/* MERAM */
+static struct sh_mobile_meram_info mackerel_meram_info = {
+        .addr_mode      = SH_MOBILE_MERAM_MODE1,
+};
+
+static struct resource meram_resources[] = {
+        [0] = {
+                .name   = "MERAM",
+                .start  = 0xe8000000,
+                .end    = 0xe81fffff,
+                .flags  = IORESOURCE_MEM,
+        },
+};
+
+static struct platform_device meram_device = {
+        .name           = "sh_mobile_meram",
+        .id             = 0,
+        .num_resources  = ARRAY_SIZE(meram_resources),
+        .resource       = meram_resources,
+        .dev            = {
+                .platform_data = &mackerel_meram_info,
+        },
+};
+
 /* LCDC */
 static struct fb_videomode mackerel_lcdc_modes[] = {
         {
@@ -342,7 +367,23 @@ static int mackerel_get_brightness(void *board_data)
         return gpio_get_value(GPIO_PORT31);
 }
 
+static struct sh_mobile_meram_cfg lcd_meram_cfg = {
+        .icb[0] = {
+                .marker_icb     = 28,
+                .cache_icb      = 24,
+                .meram_offset   = 0x0,
+                .meram_size     = 0x40,
+        },
+        .icb[1] = {
+                .marker_icb     = 29,
+                .cache_icb      = 25,
+                .meram_offset   = 0x40,
+                .meram_size     = 0x40,
+        },
+};
+
 static struct sh_mobile_lcdc_info lcdc_info = {
+        .meram_dev = &mackerel_meram_info,
         .clock_source = LCDC_CLK_BUS,
         .ch[0] = {
                 .chan = LCDC_CHAN_MAINLCD,
@@ -362,6 +403,7 @@ static struct sh_mobile_lcdc_info lcdc_info = {
                         .name = "sh_mobile_lcdc_bl",
                         .max_brightness = 1,
                 },
+                .meram_cfg = &lcd_meram_cfg,
         }
 };
 
@@ -388,8 +430,23 @@ static struct platform_device lcdc_device = {
         },
 };
 
+static struct sh_mobile_meram_cfg hdmi_meram_cfg = {
+        .icb[0] = {
+                .marker_icb     = 30,
+                .cache_icb      = 26,
+                .meram_offset   = 0x80,
+                .meram_size     = 0x100,
+        },
+        .icb[1] = {
+                .marker_icb     = 31,
+                .cache_icb      = 27,
+                .meram_offset   = 0x180,
+                .meram_size     = 0x100,
+        },
+};
 /* HDMI */
 static struct sh_mobile_lcdc_info hdmi_lcdc_info = {
+        .meram_dev = &mackerel_meram_info,
         .clock_source = LCDC_CLK_EXTERNAL,
         .ch[0] = {
                 .chan = LCDC_CHAN_MAINLCD,
@@ -397,6 +454,7 @@ static struct sh_mobile_lcdc_info hdmi_lcdc_info = {
                 .interface_type = RGB24,
                 .clock_divider = 1,
                 .flags = LCDC_FLAGS_DWPOL,
+                .meram_cfg = &hdmi_meram_cfg,
         }
 };
 
@@ -856,6 +914,17 @@ static int slot_cn7_get_cd(struct platform_device *pdev)
 }
 
 /* SDHI0 */
+static irqreturn_t mackerel_sdhi0_gpio_cd(int irq, void *arg)
+{
+        struct device *dev = arg;
+        struct sh_mobile_sdhi_info *info = dev->platform_data;
+        struct tmio_mmc_data *pdata = info->pdata;
+
+        tmio_mmc_cd_wakeup(pdata);
+
+        return IRQ_HANDLED;
+}
+
 static struct sh_mobile_sdhi_info sdhi0_info = {
         .dma_slave_tx   = SHDMA_SLAVE_SDHI0_TX,
         .dma_slave_rx   = SHDMA_SLAVE_SDHI0_RX,
@@ -1150,6 +1219,7 @@ static struct platform_device *mackerel_devices[] __initdata = {
         &mackerel_camera,
         &hdmi_lcdc_device,
         &hdmi_device,
+        &meram_device,
 };
 
 /* Keypad Initialization */
@@ -1238,6 +1308,7 @@ static void __init mackerel_init(void)
 {
         u32 srcr4;
         struct clk *clk;
+        int ret;
 
         sh7372_pinmux_init();
 
@@ -1343,6 +1414,13 @@ static void __init mackerel_init(void)
         gpio_request(GPIO_FN_SDHID0_1, NULL);
         gpio_request(GPIO_FN_SDHID0_0, NULL);
 
+        ret = request_irq(evt2irq(0x3340), mackerel_sdhi0_gpio_cd,
+                          IRQF_TRIGGER_FALLING, "sdhi0 cd", &sdhi0_device.dev);
+        if (!ret)
+                sdhi0_info.tmio_flags |= TMIO_MMC_HAS_COLD_CD;
+        else
+                pr_err("Cannot get IRQ #%d: %d\n", evt2irq(0x3340), ret);
+
 #if !defined(CONFIG_MMC_SH_MMCIF) && !defined(CONFIG_MMC_SH_MMCIF_MODULE)
         /* enable SDHI1 */
         gpio_request(GPIO_FN_SDHICMD1, NULL);
diff --git a/arch/arm/mach-shmobile/clock-sh7372.c b/arch/arm/mach-shmobile/clock-sh7372.c
index d17eb66f4ac2..c0800d83971e 100644
--- a/arch/arm/mach-shmobile/clock-sh7372.c
+++ b/arch/arm/mach-shmobile/clock-sh7372.c
@@ -509,6 +509,7 @@ enum { MSTP001,
        MSTP118, MSTP117, MSTP116, MSTP113,
        MSTP106, MSTP101, MSTP100,
        MSTP223,
+       MSTP218, MSTP217, MSTP216,
        MSTP207, MSTP206, MSTP204, MSTP203, MSTP202, MSTP201, MSTP200,
        MSTP329, MSTP328, MSTP323, MSTP322, MSTP314, MSTP313, MSTP312,
        MSTP423, MSTP415, MSTP413, MSTP411, MSTP410, MSTP406, MSTP403,
@@ -534,6 +535,9 @@ static struct clk mstp_clks[MSTP_NR] = {
         [MSTP101] = MSTP(&div4_clks[DIV4_M1], SMSTPCR1, 1, 0), /* VPU */
         [MSTP100] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 0, 0), /* LCDC0 */
         [MSTP223] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR2, 23, 0), /* SPU2 */
+        [MSTP218] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 18, 0), /* DMAC1 */
+        [MSTP217] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 17, 0), /* DMAC2 */
+        [MSTP216] = MSTP(&div4_clks[DIV4_HP], SMSTPCR2, 16, 0), /* DMAC3 */
         [MSTP207] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 7, 0), /* SCIFA5 */
         [MSTP206] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 6, 0), /* SCIFB */
         [MSTP204] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 4, 0), /* SCIFA0 */
@@ -626,6 +630,9 @@ static struct clk_lookup lookups[] = {
         CLKDEV_DEV_ID("sh_mobile_lcdc_fb.0", &mstp_clks[MSTP100]), /* LCDC0 */
         CLKDEV_DEV_ID("uio_pdrv_genirq.6", &mstp_clks[MSTP223]), /* SPU2DSP0 */
         CLKDEV_DEV_ID("uio_pdrv_genirq.7", &mstp_clks[MSTP223]), /* SPU2DSP1 */
+        CLKDEV_DEV_ID("sh-dma-engine.0", &mstp_clks[MSTP218]), /* DMAC1 */
+        CLKDEV_DEV_ID("sh-dma-engine.1", &mstp_clks[MSTP217]), /* DMAC2 */
+        CLKDEV_DEV_ID("sh-dma-engine.2", &mstp_clks[MSTP216]), /* DMAC3 */
         CLKDEV_DEV_ID("sh-sci.5", &mstp_clks[MSTP207]), /* SCIFA5 */
         CLKDEV_DEV_ID("sh-sci.6", &mstp_clks[MSTP206]), /* SCIFB */
         CLKDEV_DEV_ID("sh-sci.0", &mstp_clks[MSTP204]), /* SCIFA0 */
diff --git a/arch/arm/mach-tegra/board-harmony-power.c b/arch/arm/mach-tegra/board-harmony-power.c
index c84442cabe07..5ad8b2f94f8d 100644
--- a/arch/arm/mach-tegra/board-harmony-power.c
+++ b/arch/arm/mach-tegra/board-harmony-power.c
@@ -24,6 +24,8 @@
 
 #include <mach/irqs.h>
 
+#include "board-harmony.h"
+
 #define PMC_CTRL                0x0
 #define PMC_CTRL_INTR_LOW       (1 << 17)
 
@@ -98,7 +100,7 @@ static struct tps6586x_platform_data tps_platform = {
         .irq_base       = TEGRA_NR_IRQS,
         .num_subdevs    = ARRAY_SIZE(tps_devs),
         .subdevs        = tps_devs,
-        .gpio_base      = TEGRA_NR_GPIOS,
+        .gpio_base      = HARMONY_GPIO_TPS6586X(0),
 };
 
 static struct i2c_board_info __initdata harmony_regulators[] = {
diff --git a/arch/arm/mach-tegra/board-harmony.h b/arch/arm/mach-tegra/board-harmony.h
index 1e57b071f52d..d85142edaf6b 100644
--- a/arch/arm/mach-tegra/board-harmony.h
+++ b/arch/arm/mach-tegra/board-harmony.h
@@ -17,7 +17,8 @@
 #ifndef _MACH_TEGRA_BOARD_HARMONY_H
 #define _MACH_TEGRA_BOARD_HARMONY_H
 
-#define HARMONY_GPIO_WM8903(_x_)        (TEGRA_NR_GPIOS + (_x_))
+#define HARMONY_GPIO_TPS6586X(_x_)      (TEGRA_NR_GPIOS + (_x_))
+#define HARMONY_GPIO_WM8903(_x_)        (HARMONY_GPIO_TPS6586X(4) + (_x_))
 
 #define TEGRA_GPIO_SD2_CD               TEGRA_GPIO_PI5
 #define TEGRA_GPIO_SD2_WP               TEGRA_GPIO_PH1
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/blackfin/lib/strncpy.S b/arch/blackfin/lib/strncpy.S
index f3931d50b4a7..2c07dddac995 100644
--- a/arch/blackfin/lib/strncpy.S
+++ b/arch/blackfin/lib/strncpy.S
@@ -25,7 +25,7 @@
 
 ENTRY(_strncpy)
         CC = R2 == 0;
-        if CC JUMP 4f;
+        if CC JUMP 6f;
 
         P2 = R2 ;       /* size */
         P0 = R0 ;       /* dst*/
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_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_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_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)
+void page_table_free(struct mm_struct *mm, unsigned long *table)
 {
         struct page *page;
-        unsigned long bits;
+        unsigned int bit, mask;
 
-        bits = ((unsigned long) table) & 15;
-        table = (unsigned long *)(((unsigned long) table) ^ bits);
+#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);
-        page->flags ^= bits;
-        if (!(page->flags & FRAG_MASK)) {
+        bit = 1 << ((__pa(table) & ~PAGE_MASK)/(PTRS_PER_PTE*sizeof(pte_t)));
+        spin_lock_bh(&mm->context.list_lock);
+        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 (mask == 0) {
                 pgtable_page_dtor(page);
+                atomic_set(&page->_mapcount, -1);
                 __free_page(page);
         }
 }
 
-void page_table_free(struct mm_struct *mm, unsigned long *table)
+#ifdef CONFIG_HAVE_RCU_TABLE_FREE
+
+static void __page_table_free_rcu(void *table, unsigned bit)
 {
         struct page *page;
-        unsigned long bits;
 
-        bits = (mm->context.has_pgste) ? 3UL : 1UL;
-        bits <<= (__pa(table) & (PAGE_SIZE - 1)) / 256 / sizeof(unsigned long);
+#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);
-        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. */
-                list_del(&page->lru);
-        spin_unlock_bh(&mm->context.list_lock);
-        if (page) {
+        if (atomic_xor_bits(&page->_mapcount, bit) == 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)
+void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table)
 {
-        struct rcu_table_freelist *batch;
+        struct mm_struct *mm;
         struct page *page;
-        unsigned long bits;
+        unsigned int bit, mask;
 
-        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;
-        }
-        batch = rcu_table_freelist_get(mm);
-        if (!batch) {
-                smp_call_function(smp_sync, NULL, 1);
-                page_table_free(mm, table);
-                goto out;
+        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/sh/Kconfig b/arch/sh/Kconfig
index 74495a5ea027..f03338c2f088 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -161,7 +161,7 @@ config ARCH_HAS_CPU_IDLE_WAIT
 
 config NO_IOPORT
         def_bool !PCI
-        depends on !SH_CAYMAN && !SH_SH4202_MICRODEV
+        depends on !SH_CAYMAN && !SH_SH4202_MICRODEV && !SH_SHMIN
 
 config IO_TRAPPED
         bool
diff --git a/arch/sh/boards/mach-ap325rxa/setup.c b/arch/sh/boards/mach-ap325rxa/setup.c
index 618bd566cf53..969421f64a15 100644
--- a/arch/sh/boards/mach-ap325rxa/setup.c
+++ b/arch/sh/boards/mach-ap325rxa/setup.c
@@ -359,37 +359,31 @@ static struct soc_camera_link camera_link = {
         .priv           = &camera_info,
 };
 
-static void dummy_release(struct device *dev)
+static struct platform_device *camera_device;
+
+static void ap325rxa_camera_release(struct device *dev)
 {
+        soc_camera_platform_release(&camera_device);
 }
 
-static struct platform_device camera_device = {
-        .name           = "soc_camera_platform",
-        .dev            = {
-                .platform_data  = &camera_info,
-                .release        = dummy_release,
-        },
-};
-
 static int ap325rxa_camera_add(struct soc_camera_link *icl,
                                struct device *dev)
 {
-        if (icl != &camera_link || camera_probe() <= 0)
-                return -ENODEV;
+        int ret = soc_camera_platform_add(icl, dev, &camera_device, &camera_link,
+                                          ap325rxa_camera_release, 0);
+        if (ret < 0)
+                return ret;
 
-        camera_info.dev = dev;
+        ret = camera_probe();
+        if (ret < 0)
+                soc_camera_platform_del(icl, camera_device, &camera_link);
 
-        return platform_device_register(&camera_device);
+        return ret;
 }
 
 static void ap325rxa_camera_del(struct soc_camera_link *icl)
 {
-        if (icl != &camera_link)
-                return;
-
-        platform_device_unregister(&camera_device);
-        memset(&camera_device.dev.kobj, 0,
-               sizeof(camera_device.dev.kobj));
+        soc_camera_platform_del(icl, camera_device, &camera_link);
 }
 #endif /* CONFIG_I2C */
 
diff --git a/arch/sh/boards/mach-ecovec24/setup.c b/arch/sh/boards/mach-ecovec24/setup.c
index bb13d0e1b964..3a32741cc0ac 100644
--- a/arch/sh/boards/mach-ecovec24/setup.c
+++ b/arch/sh/boards/mach-ecovec24/setup.c
@@ -885,6 +885,9 @@ static struct platform_device sh_mmcif_device = {
         },
         .num_resources  = ARRAY_SIZE(sh_mmcif_resources),
         .resource       = sh_mmcif_resources,
+        .archdata = {
+                .hwblk_id = HWBLK_MMC,
+        },
 };
 #endif
 
diff --git a/arch/sh/include/asm/pgtable.h b/arch/sh/include/asm/pgtable.h
index db85916b9e95..9210e93a92c3 100644
--- a/arch/sh/include/asm/pgtable.h
+++ b/arch/sh/include/asm/pgtable.h
@@ -18,6 +18,7 @@
 #include <asm/pgtable-2level.h>
 #endif
 #include <asm/page.h>
+#include <asm/mmu.h>
 
 #ifndef __ASSEMBLY__
 #include <asm/addrspace.h>
diff --git a/arch/sh/include/asm/ptrace.h b/arch/sh/include/asm/ptrace.h
index 40725b4a8018..88bd6be168a9 100644
--- a/arch/sh/include/asm/ptrace.h
+++ b/arch/sh/include/asm/ptrace.h
@@ -41,7 +41,9 @@
 
 #define user_mode(regs)                 (((regs)->sr & 0x40000000)==0)
 #define kernel_stack_pointer(_regs)     ((unsigned long)(_regs)->regs[15])
-#define GET_USP(regs) ((regs)->regs[15])
+
+#define GET_FP(regs)    ((regs)->regs[14])
+#define GET_USP(regs)   ((regs)->regs[15])
 
 extern void show_regs(struct pt_regs *);
 
@@ -131,7 +133,7 @@ extern void ptrace_triggered(struct perf_event *bp, int nmi,
 
 static inline unsigned long profile_pc(struct pt_regs *regs)
 {
-        unsigned long pc = instruction_pointer(regs);
+        unsigned long pc = regs->pc;
 
         if (virt_addr_uncached(pc))
                 return CAC_ADDR(pc);
diff --git a/arch/sh/include/asm/tlb.h b/arch/sh/include/asm/tlb.h
index 6c308d8b9a50..ec88bfcdf7ce 100644
--- a/arch/sh/include/asm/tlb.h
+++ b/arch/sh/include/asm/tlb.h
@@ -9,6 +9,7 @@
 #include <linux/pagemap.h>
 
 #ifdef CONFIG_MMU
+#include <linux/swap.h>
 #include <asm/pgalloc.h>
 #include <asm/tlbflush.h>
 #include <asm/mmu_context.h>
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7722.h b/arch/sh/include/cpu-sh4/cpu/sh7722.h
index 7a5b8a331b4a..bd0622788d64 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7722.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7722.h
@@ -236,6 +236,7 @@ enum {
 };
 
 enum {
+        SHDMA_SLAVE_INVALID,
         SHDMA_SLAVE_SCIF0_TX,
         SHDMA_SLAVE_SCIF0_RX,
         SHDMA_SLAVE_SCIF1_TX,
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7724.h b/arch/sh/include/cpu-sh4/cpu/sh7724.h
index 7eb435999426..3daef8ecbc63 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7724.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7724.h
@@ -285,6 +285,7 @@ enum {
 };
 
 enum {
+        SHDMA_SLAVE_INVALID,
         SHDMA_SLAVE_SCIF0_TX,
         SHDMA_SLAVE_SCIF0_RX,
         SHDMA_SLAVE_SCIF1_TX,
diff --git a/arch/sh/include/cpu-sh4/cpu/sh7757.h b/arch/sh/include/cpu-sh4/cpu/sh7757.h
index 05b8196c7753..41f9f8b9db73 100644
--- a/arch/sh/include/cpu-sh4/cpu/sh7757.h
+++ b/arch/sh/include/cpu-sh4/cpu/sh7757.h
@@ -252,6 +252,7 @@ enum {
 };
 
 enum {
+        SHDMA_SLAVE_INVALID,
         SHDMA_SLAVE_SDHI_TX,
         SHDMA_SLAVE_SDHI_RX,
         SHDMA_SLAVE_MMCIF_TX,
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index 762a13984bbd..b473f0c06fbc 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -21,6 +21,7 @@
 #include <linux/fs.h>
 #include <linux/ftrace.h>
 #include <linux/hw_breakpoint.h>
+#include <linux/prefetch.h>
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
 #include <asm/system.h>
diff --git a/arch/sh/mm/consistent.c b/arch/sh/mm/consistent.c
index 40733a952402..f251b5f27652 100644
--- a/arch/sh/mm/consistent.c
+++ b/arch/sh/mm/consistent.c
@@ -82,7 +82,7 @@ void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
         void *addr;
 
         addr = __in_29bit_mode() ?
-               (void *)P1SEGADDR((unsigned long)vaddr) : vaddr;
+               (void *)CAC_ADDR((unsigned long)vaddr) : vaddr;
 
         switch (direction) {
         case DMA_FROM_DEVICE:           /* invalidate only */
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/block/blk-ioc.c b/block/blk-ioc.c
index c898049dafd5..342eae9b0d3c 100644
--- a/block/blk-ioc.c
+++ b/block/blk-ioc.c
@@ -21,7 +21,7 @@ static void cfq_dtor(struct io_context *ioc)
         if (!hlist_empty(&ioc->cic_list)) {
                 struct cfq_io_context *cic;
 
-                cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+                cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
                                                                 cic_list);
                 cic->dtor(ioc);
         }
@@ -57,7 +57,7 @@ static void cfq_exit(struct io_context *ioc)
         if (!hlist_empty(&ioc->cic_list)) {
                 struct cfq_io_context *cic;
 
-                cic = list_entry(ioc->cic_list.first, struct cfq_io_context,
+                cic = hlist_entry(ioc->cic_list.first, struct cfq_io_context,
                                                                 cic_list);
                 cic->exit(ioc);
         }
diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c
index 7c52d6888924..3c7b537bf908 100644
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@@ -185,7 +185,7 @@ struct cfq_group {
         int nr_cfqq;
 
         /*
-         * Per group busy queus average. Useful for workload slice calc. We
+         * Per group busy queues average. Useful for workload slice calc. We
          * create the array for each prio class but at run time it is used
          * only for RT and BE class and slot for IDLE class remains unused.
          * This is primarily done to avoid confusion and a gcc warning.
@@ -369,16 +369,16 @@ CFQ_CFQQ_FNS(wait_busy);
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)  \
         blk_add_trace_msg((cfqd)->queue, "cfq%d%c %s " fmt, (cfqq)->pid, \
                         cfq_cfqq_sync((cfqq)) ? 'S' : 'A', \
-                        blkg_path(&(cfqq)->cfqg->blkg), ##args);
+                        blkg_path(&(cfqq)->cfqg->blkg), ##args)
 
 #define cfq_log_cfqg(cfqd, cfqg, fmt, args...)                          \
         blk_add_trace_msg((cfqd)->queue, "%s " fmt,                     \
-                                blkg_path(&(cfqg)->blkg), ##args);      \
+                                blkg_path(&(cfqg)->blkg), ##args)       \
 
 #else
 #define cfq_log_cfqq(cfqd, cfqq, fmt, args...)  \
         blk_add_trace_msg((cfqd)->queue, "cfq%d " fmt, (cfqq)->pid, ##args)
-#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)          do {} while (0);
+#define cfq_log_cfqg(cfqd, cfqg, fmt, args...)          do {} while (0)
 #endif
 #define cfq_log(cfqd, fmt, args...)     \
         blk_add_trace_msg((cfqd)->queue, "cfq " fmt, ##args)
@@ -3786,9 +3786,6 @@ new_queue:
         return 0;
 
 queue_fail:
-        if (cic)
-                put_io_context(cic->ioc);
-
         cfq_schedule_dispatch(cfqd);
         spin_unlock_irqrestore(q->queue_lock, flags);
         cfq_log(cfqd, "set_request fail");
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index e6fc716aca45..f533f3375e24 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -192,7 +192,8 @@ static int sock_xmit(struct nbd_device *lo, int send, void *buf, int size,
                         if (lo->xmit_timeout)
                                 del_timer_sync(&ti);
                 } else
-                        result = kernel_recvmsg(sock, &msg, &iov, 1, size, 0);
+                        result = kernel_recvmsg(sock, &msg, &iov, 1, size,
+                                                msg.msg_flags);
 
                 if (signal_pending(current)) {
                         siginfo_t info;
@@ -753,9 +754,26 @@ static int __init nbd_init(void)
                 return -ENOMEM;
 
         part_shift = 0;
-        if (max_part > 0)
+        if (max_part > 0) {
                 part_shift = fls(max_part);
 
+                /*
+                 * Adjust max_part according to part_shift as it is exported
+                 * to user space so that user can know the max number of
+                 * partition kernel should be able to manage.
+                 *
+                 * Note that -1 is required because partition 0 is reserved
+                 * for the whole disk.
+                 */
+                max_part = (1UL << part_shift) - 1;
+        }
+
+        if ((1UL << part_shift) > DISK_MAX_PARTS)
+                return -EINVAL;
+
+        if (nbds_max > 1UL << (MINORBITS - part_shift))
+                return -EINVAL;
+
         for (i = 0; i < nbds_max; i++) {
                 struct gendisk *disk = alloc_disk(1 << part_shift);
                 if (!disk)
diff --git a/drivers/block/xen-blkback/blkback.c b/drivers/block/xen-blkback/blkback.c
index c73910cc28c9..5cf2993a8338 100644
--- a/drivers/block/xen-blkback/blkback.c
+++ b/drivers/block/xen-blkback/blkback.c
@@ -809,11 +809,13 @@ static int __init xen_blkif_init(void)
  failed_init:
         kfree(blkbk->pending_reqs);
         kfree(blkbk->pending_grant_handles);
-        for (i = 0; i < mmap_pages; i++) {
-                if (blkbk->pending_pages[i])
-                        __free_page(blkbk->pending_pages[i]);
+        if (blkbk->pending_pages) {
+                for (i = 0; i < mmap_pages; i++) {
+                        if (blkbk->pending_pages[i])
+                                __free_page(blkbk->pending_pages[i]);
+                }
+                kfree(blkbk->pending_pages);
         }
-        kfree(blkbk->pending_pages);
         kfree(blkbk);
         blkbk = NULL;
         return rc;
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 34570823355b..6cc0db1bf522 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -357,14 +357,13 @@ static int xen_vbd_create(struct xen_blkif *blkif, blkif_vdev_t handle,
         }
 
         vbd->bdev = bdev;
-        vbd->size = vbd_sz(vbd);
-
         if (vbd->bdev->bd_disk == NULL) {
                 DPRINTK("xen_vbd_create: device %08x doesn't exist.\n",
                         vbd->pdevice);
                 xen_vbd_free(vbd);
                 return -ENOENT;
         }
+        vbd->size = vbd_sz(vbd);
 
         if (vbd->bdev->bd_disk->flags & GENHD_FL_CD || cdrom)
                 vbd->type |= VDISK_CDROM;
diff --git a/drivers/bluetooth/hci_ldisc.c b/drivers/bluetooth/hci_ldisc.c
index b3f01996318f..48ad2a7ab080 100644
--- a/drivers/bluetooth/hci_ldisc.c
+++ b/drivers/bluetooth/hci_ldisc.c
@@ -355,29 +355,24 @@ static void hci_uart_tty_wakeup(struct tty_struct *tty)
  *             flags        pointer to flags for data
  *             count        count of received data in bytes
  *     
- * Return Value:    Number of bytes received
+ * Return Value:    None
  */
-static unsigned int hci_uart_tty_receive(struct tty_struct *tty,
-                const u8 *data, char *flags, int count)
+static void hci_uart_tty_receive(struct tty_struct *tty, const u8 *data, char *flags, int count)
 {
         struct hci_uart *hu = (void *)tty->disc_data;
-        int received;
 
         if (!hu || tty != hu->tty)
-                return -ENODEV;
+                return;
 
         if (!test_bit(HCI_UART_PROTO_SET, &hu->flags))
-                return -EINVAL;
+                return;
 
         spin_lock(&hu->rx_lock);
-        received = hu->proto->recv(hu, (void *) data, count);
-        if (received > 0)
-                hu->hdev->stat.byte_rx += received;
+        hu->proto->recv(hu, (void *) data, count);
+        hu->hdev->stat.byte_rx += count;
         spin_unlock(&hu->rx_lock);
 
         tty_unthrottle(tty);
-
-        return received;
 }
 
 static int hci_uart_register_dev(struct hci_uart *hu)
diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
index 036e5865eb40..dc7c033ef587 100644
--- a/drivers/clocksource/sh_cmt.c
+++ b/drivers/clocksource/sh_cmt.c
@@ -24,7 +24,6 @@
 #include <linux/ioport.h>
 #include <linux/io.h>
 #include <linux/clk.h>
-#include <linux/pm_runtime.h>
 #include <linux/irq.h>
 #include <linux/err.h>
 #include <linux/clocksource.h>
@@ -153,12 +152,10 @@ static int sh_cmt_enable(struct sh_cmt_priv *p, unsigned long *rate)
 {
         int ret;
 
-        /* wake up device and enable clock */
-        pm_runtime_get_sync(&p->pdev->dev);
+        /* enable clock */
         ret = clk_enable(p->clk);
         if (ret) {
                 dev_err(&p->pdev->dev, "cannot enable clock\n");
-                pm_runtime_put_sync(&p->pdev->dev);
                 return ret;
         }
 
@@ -190,9 +187,8 @@ static void sh_cmt_disable(struct sh_cmt_priv *p)
         /* disable interrupts in CMT block */
         sh_cmt_write(p, CMCSR, 0);
 
-        /* stop clock and mark device as idle */
+        /* stop clock */
         clk_disable(p->clk);
-        pm_runtime_put_sync(&p->pdev->dev);
 }
 
 /* private flags */
@@ -664,7 +660,6 @@ static int __devinit sh_cmt_probe(struct platform_device *pdev)
 
         if (p) {
                 dev_info(&pdev->dev, "kept as earlytimer\n");
-                pm_runtime_enable(&pdev->dev);
                 return 0;
         }
 
@@ -679,9 +674,6 @@ static int __devinit sh_cmt_probe(struct platform_device *pdev)
                 kfree(p);
                 platform_set_drvdata(pdev, NULL);
         }
-
-        if (!is_early_platform_device(pdev))
-                pm_runtime_enable(&pdev->dev);
         return ret;
 }
 
diff --git a/drivers/clocksource/sh_tmu.c b/drivers/clocksource/sh_tmu.c
index 17296288a205..808135768617 100644
--- a/drivers/clocksource/sh_tmu.c
+++ b/drivers/clocksource/sh_tmu.c
@@ -25,7 +25,6 @@
 #include <linux/delay.h>
 #include <linux/io.h>
 #include <linux/clk.h>
-#include <linux/pm_runtime.h>
 #include <linux/irq.h>
 #include <linux/err.h>
 #include <linux/clocksource.h>
@@ -110,12 +109,10 @@ static int sh_tmu_enable(struct sh_tmu_priv *p)
 {
         int ret;
 
-        /* wake up device and enable clock */
-        pm_runtime_get_sync(&p->pdev->dev);
+        /* enable clock */
         ret = clk_enable(p->clk);
         if (ret) {
                 dev_err(&p->pdev->dev, "cannot enable clock\n");
-                pm_runtime_put_sync(&p->pdev->dev);
                 return ret;
         }
 
@@ -144,9 +141,8 @@ static void sh_tmu_disable(struct sh_tmu_priv *p)
         /* disable interrupts in TMU block */
         sh_tmu_write(p, TCR, 0x0000);
 
-        /* stop clock and mark device as idle */
+        /* stop clock */
         clk_disable(p->clk);
-        pm_runtime_put_sync(&p->pdev->dev);
 }
 
 static void sh_tmu_set_next(struct sh_tmu_priv *p, unsigned long delta,
@@ -415,7 +411,6 @@ static int __devinit sh_tmu_probe(struct platform_device *pdev)
 
         if (p) {
                 dev_info(&pdev->dev, "kept as earlytimer\n");
-                pm_runtime_enable(&pdev->dev);
                 return 0;
         }
 
@@ -430,9 +425,6 @@ static int __devinit sh_tmu_probe(struct platform_device *pdev)
                 kfree(p);
                 platform_set_drvdata(pdev, NULL);
         }
-
-        if (!is_early_platform_device(pdev))
-                pm_runtime_enable(&pdev->dev);
         return ret;
 }
 
diff --git a/drivers/dma/shdma.c b/drivers/dma/shdma.c
index 636e40925b16..2a638f9f09a2 100644
--- a/drivers/dma/shdma.c
+++ b/drivers/dma/shdma.c
@@ -343,7 +343,7 @@ static int sh_dmae_alloc_chan_resources(struct dma_chan *chan)
 
                 dmae_set_dmars(sh_chan, cfg->mid_rid);
                 dmae_set_chcr(sh_chan, cfg->chcr);
-        } else if ((sh_dmae_readl(sh_chan, CHCR) & 0xf00) != 0x400) {
+        } else {
                 dmae_init(sh_chan);
         }
 
@@ -1144,6 +1144,8 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
         /* platform data */
         shdev->pdata = pdata;
 
+        platform_set_drvdata(pdev, shdev);
+
         pm_runtime_enable(&pdev->dev);
         pm_runtime_get_sync(&pdev->dev);
 
@@ -1256,7 +1258,6 @@ static int __init sh_dmae_probe(struct platform_device *pdev)
 
         pm_runtime_put(&pdev->dev);
 
-        platform_set_drvdata(pdev, shdev);
         dma_async_device_register(&shdev->common);
 
         return err;
@@ -1278,6 +1279,8 @@ rst_err:
 
         if (dmars)
                 iounmap(shdev->dmars);
+
+        platform_set_drvdata(pdev, NULL);
 emapdmars:
         iounmap(shdev->chan_reg);
         synchronize_rcu();
@@ -1316,6 +1319,8 @@ static int __exit sh_dmae_remove(struct platform_device *pdev)
                 iounmap(shdev->dmars);
         iounmap(shdev->chan_reg);
 
+        platform_set_drvdata(pdev, NULL);
+
         synchronize_rcu();
         kfree(shdev);
 
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;
-        }
+        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;
+                }
 
-        switch (dev_priv->card_type) {
-        case NV_50:
                 switch (dev_priv->chipset) {
-                case 0xa3:
-                case 0xa5:
-                case 0xa8:
-                case 0xaf:
-                        nva3_copy_create(dev);
+                case 0x84:
+                case 0x86:
+                case 0x92:
+                case 0x94:
+                case 0x96:
+                case 0xa0:
+                        nv84_crypt_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);
+                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;
-
-        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;
+        u32 temp, toffset, actual_temp = 0;
+
+        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;
+
+                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;
 
-        return (actual_temp * 1000) / 2;
+                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:
@@ -1689,6 +1711,54 @@ static void evergreen_gpu_init(struct radeon_device *rdev)
                 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;
+                break;
         case CHIP_BARTS:
                 rdev->config.evergreen.num_ses = 2;
                 rdev->config.evergreen.max_pipes = 4;
@@ -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 (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 (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]);
+        } 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_device.c b/drivers/gpu/drm/radeon/radeon_device.c
index 5b61364e31f4..d77ede3e67ce 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",
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_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/hwmon/coretemp.c b/drivers/hwmon/coretemp.c
index de3d2465fe24..85e937984ff7 100644
--- a/drivers/hwmon/coretemp.c
+++ b/drivers/hwmon/coretemp.c
@@ -296,7 +296,7 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
                  * If the TjMax is not plausible, an assumption
                  * will be used
                  */
-                if (val > 80 && val < 120) {
+                if (val) {
                         dev_info(dev, "TjMax is %d C.\n", val);
                         return val * 1000;
                 }
@@ -304,24 +304,9 @@ static int get_tjmax(struct cpuinfo_x86 *c, u32 id, struct device *dev)
 
         /*
          * An assumption is made for early CPUs and unreadable MSR.
-         * NOTE: the given value may not be correct.
+         * NOTE: the calculated value may not be correct.
          */
-
-        switch (c->x86_model) {
-        case 0xe:
-        case 0xf:
-        case 0x16:
-        case 0x1a:
-                dev_warn(dev, "TjMax is assumed as 100 C!\n");
-                return 100000;
-        case 0x17:
-        case 0x1c:              /* Atom CPUs */
-                return adjust_tjmax(c, id, dev);
-        default:
-                dev_warn(dev, "CPU (model=0x%x) is not supported yet,"
-                        " using default TjMax of 100C.\n", c->x86_model);
-                return 100000;
-        }
+        return adjust_tjmax(c, id, dev);
 }
 
 static void __devinit get_ucode_rev_on_cpu(void *edx)
@@ -341,7 +326,7 @@ static int get_pkg_tjmax(unsigned int cpu, struct device *dev)
         err = rdmsr_safe_on_cpu(cpu, MSR_IA32_TEMPERATURE_TARGET, &eax, &edx);
         if (!err) {
                 val = (eax >> 16) & 0xff;
-                if (val > 80 && val < 120)
+                if (val)
                         return val * 1000;
         }
         dev_warn(dev, "Unable to read Pkg-TjMax from CPU:%u\n", cpu);
diff --git a/drivers/hwmon/max6642.c b/drivers/hwmon/max6642.c
index 0f9fc40379cd..e855d3b0bd1f 100644
--- a/drivers/hwmon/max6642.c
+++ b/drivers/hwmon/max6642.c
@@ -136,15 +136,29 @@ static int max6642_detect(struct i2c_client *client,
         if (man_id != 0x4D)
                 return -ENODEV;
 
+        /* sanity check */
+        if (i2c_smbus_read_byte_data(client, 0x04) != 0x4D
+            || i2c_smbus_read_byte_data(client, 0x06) != 0x4D
+            || i2c_smbus_read_byte_data(client, 0xff) != 0x4D)
+                return -ENODEV;
+
         /*
          * We read the config and status register, the 4 lower bits in the
          * config register should be zero and bit 5, 3, 1 and 0 should be
          * zero in the status register.
          */
         reg_config = i2c_smbus_read_byte_data(client, MAX6642_REG_R_CONFIG);
+        if ((reg_config & 0x0f) != 0x00)
+                return -ENODEV;
+
+        /* in between, another round of sanity checks */
+        if (i2c_smbus_read_byte_data(client, 0x04) != reg_config
+            || i2c_smbus_read_byte_data(client, 0x06) != reg_config
+            || i2c_smbus_read_byte_data(client, 0xff) != reg_config)
+                return -ENODEV;
+
         reg_status = i2c_smbus_read_byte_data(client, MAX6642_REG_R_STATUS);
-        if (((reg_config & 0x0f) != 0x00) ||
-            ((reg_status & 0x2b) != 0x00))
+        if ((reg_status & 0x2b) != 0x00)
                 return -ENODEV;
 
         strlcpy(info->type, "max6642", I2C_NAME_SIZE);
@@ -246,7 +260,7 @@ static SENSOR_DEVICE_ATTR_2(temp1_max, S_IWUSR | S_IRUGO, show_temp_max,
                             set_temp_max, 0, MAX6642_REG_W_LOCAL_HIGH);
 static SENSOR_DEVICE_ATTR_2(temp2_max, S_IWUSR | S_IRUGO, show_temp_max,
                             set_temp_max, 1, MAX6642_REG_W_REMOTE_HIGH);
-static SENSOR_DEVICE_ATTR(temp_fault, S_IRUGO, show_alarm, NULL, 2);
+static SENSOR_DEVICE_ATTR(temp2_fault, S_IRUGO, show_alarm, NULL, 2);
 static SENSOR_DEVICE_ATTR(temp1_max_alarm, S_IRUGO, show_alarm, NULL, 6);
 static SENSOR_DEVICE_ATTR(temp2_max_alarm, S_IRUGO, show_alarm, NULL, 4);
 
@@ -256,7 +270,7 @@ static struct attribute *max6642_attributes[] = {
         &sensor_dev_attr_temp1_max.dev_attr.attr,
         &sensor_dev_attr_temp2_max.dev_attr.attr,
 
-        &sensor_dev_attr_temp_fault.dev_attr.attr,
+        &sensor_dev_attr_temp2_fault.dev_attr.attr,
         &sensor_dev_attr_temp1_max_alarm.dev_attr.attr,
         &sensor_dev_attr_temp2_max_alarm.dev_attr.attr,
         NULL
diff --git a/drivers/input/serio/serport.c b/drivers/input/serio/serport.c
index f3698967edf6..8755f5f3ad37 100644
--- a/drivers/input/serio/serport.c
+++ b/drivers/input/serio/serport.c
@@ -120,21 +120,17 @@ static void serport_ldisc_close(struct tty_struct *tty)
  * 'interrupt' routine.
  */
 
-static unsigned int serport_ldisc_receive(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void serport_ldisc_receive(struct tty_struct *tty, const unsigned char *cp, char *fp, int count)
 {
         struct serport *serport = (struct serport*) tty->disc_data;
         unsigned long flags;
         unsigned int ch_flags;
-        int ret = 0;
         int i;
 
         spin_lock_irqsave(&serport->lock, flags);
 
-        if (!test_bit(SERPORT_ACTIVE, &serport->flags)) {
-                ret = -EINVAL;
+        if (!test_bit(SERPORT_ACTIVE, &serport->flags))
                 goto out;
-        }
 
         for (i = 0; i < count; i++) {
                 switch (fp[i]) {
@@ -156,8 +152,6 @@ static unsigned int serport_ldisc_receive(struct tty_struct *tty,
 
 out:
         spin_unlock_irqrestore(&serport->lock, flags);
-
-        return ret == 0 ? count : ret;
 }
 
 /*
diff --git a/drivers/isdn/gigaset/ser-gigaset.c b/drivers/isdn/gigaset/ser-gigaset.c
index 1d44d470897c..86a5c4f7775e 100644
--- a/drivers/isdn/gigaset/ser-gigaset.c
+++ b/drivers/isdn/gigaset/ser-gigaset.c
@@ -674,7 +674,7 @@ gigaset_tty_ioctl(struct tty_struct *tty, struct file *file,
  *      cflags  buffer containing error flags for received characters (ignored)
  *      count   number of received characters
  */
-static unsigned int
+static void
 gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf,
                     char *cflags, int count)
 {
@@ -683,12 +683,12 @@ gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf,
         struct inbuf_t *inbuf;
 
         if (!cs)
-                return -ENODEV;
+                return;
         inbuf = cs->inbuf;
         if (!inbuf) {
                 dev_err(cs->dev, "%s: no inbuf\n", __func__);
                 cs_put(cs);
-                return -EINVAL;
+                return;
         }
 
         tail = inbuf->tail;
@@ -725,8 +725,6 @@ gigaset_tty_receive(struct tty_struct *tty, const unsigned char *buf,
         gig_dbg(DEBUG_INTR, "%s-->BH", __func__);
         gigaset_schedule_event(cs);
         cs_put(cs);
-
-        return count;
 }
 
 /*
diff --git a/drivers/misc/ti-st/st_core.c b/drivers/misc/ti-st/st_core.c
index 1a05fe08e2cb..f91f82eabda7 100644
--- a/drivers/misc/ti-st/st_core.c
+++ b/drivers/misc/ti-st/st_core.c
@@ -747,8 +747,8 @@ static void st_tty_close(struct tty_struct *tty)
         pr_debug("%s: done ", __func__);
 }
 
-static unsigned int st_tty_receive(struct tty_struct *tty,
-                const unsigned char *data, char *tty_flags, int count)
+static void st_tty_receive(struct tty_struct *tty, const unsigned char *data,
+                           char *tty_flags, int count)
 {
 #ifdef VERBOSE
         print_hex_dump(KERN_DEBUG, ">in>", DUMP_PREFIX_NONE,
@@ -761,8 +761,6 @@ static unsigned int st_tty_receive(struct tty_struct *tty,
          */
         st_recv(tty->disc_data, data, count);
         pr_debug("done %s", __func__);
-
-        return count;
 }
 
 /* wake-up function called in from the TTY layer
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/net/3c509.c b/drivers/net/3c509.c
index 5f25889e27ef..44b28b2d7003 100644
--- a/drivers/net/3c509.c
+++ b/drivers/net/3c509.c
@@ -185,7 +185,7 @@ static int max_interrupt_work = 10;
 static int nopnp;
 #endif
 
-static int el3_common_init(struct net_device *dev);
+static int __devinit el3_common_init(struct net_device *dev);
 static void el3_common_remove(struct net_device *dev);
 static ushort id_read_eeprom(int index);
 static ushort read_eeprom(int ioaddr, int index);
@@ -395,7 +395,7 @@ static struct isa_driver el3_isa_driver = {
 static int isa_registered;
 
 #ifdef CONFIG_PNP
-static const struct pnp_device_id el3_pnp_ids[] __devinitconst = {
+static struct pnp_device_id el3_pnp_ids[] = {
         { .id = "TCM5090" }, /* 3Com Etherlink III (TP) */
         { .id = "TCM5091" }, /* 3Com Etherlink III */
         { .id = "TCM5094" }, /* 3Com Etherlink III (combo) */
@@ -478,7 +478,7 @@ static int pnp_registered;
 #endif /* CONFIG_PNP */
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id el3_eisa_ids[] __devinitconst = {
+static struct eisa_device_id el3_eisa_ids[] = {
                 { "TCM5090" },
                 { "TCM5091" },
                 { "TCM5092" },
@@ -508,7 +508,7 @@ static int eisa_registered;
 #ifdef CONFIG_MCA
 static int el3_mca_probe(struct device *dev);
 
-static const short el3_mca_adapter_ids[] __devinitconst = {
+static short el3_mca_adapter_ids[] __initdata = {
                 0x627c,
                 0x627d,
                 0x62db,
@@ -517,7 +517,7 @@ static const short el3_mca_adapter_ids[] __devinitconst = {
                 0x0000
 };
 
-static const char *const el3_mca_adapter_names[] __devinitconst = {
+static char *el3_mca_adapter_names[] __initdata = {
                 "3Com 3c529 EtherLink III (10base2)",
                 "3Com 3c529 EtherLink III (10baseT)",
                 "3Com 3c529 EtherLink III (test mode)",
@@ -601,7 +601,7 @@ static void el3_common_remove (struct net_device *dev)
 }
 
 #ifdef CONFIG_MCA
-static int __devinit el3_mca_probe(struct device *device)
+static int __init el3_mca_probe(struct device *device)
 {
         /* Based on Erik Nygren's (nygren@mit.edu) 3c529 patch,
          * heavily modified by Chris Beauregard
@@ -671,7 +671,7 @@ static int __devinit el3_mca_probe(struct device *device)
 #endif /* CONFIG_MCA */
 
 #ifdef CONFIG_EISA
-static int __devinit el3_eisa_probe (struct device *device)
+static int __init el3_eisa_probe (struct device *device)
 {
         short i;
         int ioaddr, irq, if_port;
diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c
index 99f43d275442..8cc22568ebd3 100644
--- a/drivers/net/3c59x.c
+++ b/drivers/net/3c59x.c
@@ -901,14 +901,14 @@ static const struct dev_pm_ops vortex_pm_ops = {
 #endif /* !CONFIG_PM */
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id vortex_eisa_ids[] __devinitconst = {
+static struct eisa_device_id vortex_eisa_ids[] = {
         { "TCM5920", CH_3C592 },
         { "TCM5970", CH_3C597 },
         { "" }
 };
 MODULE_DEVICE_TABLE(eisa, vortex_eisa_ids);
 
-static int __devinit vortex_eisa_probe(struct device *device)
+static int __init vortex_eisa_probe(struct device *device)
 {
         void __iomem *ioaddr;
         struct eisa_device *edev;
diff --git a/drivers/net/caif/caif_serial.c b/drivers/net/caif/caif_serial.c
index 73c7e03617ec..3df0c0f8b8bf 100644
--- a/drivers/net/caif/caif_serial.c
+++ b/drivers/net/caif/caif_serial.c
@@ -167,8 +167,8 @@ static inline void debugfs_tx(struct ser_device *ser, const u8 *data, int size)
 
 #endif
 
-static unsigned int ldisc_receive(struct tty_struct *tty,
-                const u8 *data, char *flags, int count)
+static void ldisc_receive(struct tty_struct *tty, const u8 *data,
+                        char *flags, int count)
 {
         struct sk_buff *skb = NULL;
         struct ser_device *ser;
@@ -215,8 +215,6 @@ static unsigned int ldisc_receive(struct tty_struct *tty,
         } else
                 ++ser->dev->stats.rx_dropped;
         update_tty_status(ser);
-
-        return count;
 }
 
 static int handle_tx(struct ser_device *ser)
diff --git a/drivers/net/can/flexcan.c b/drivers/net/can/flexcan.c
index d4990568baee..17678117ed69 100644
--- a/drivers/net/can/flexcan.c
+++ b/drivers/net/can/flexcan.c
@@ -923,7 +923,7 @@ static int __devinit flexcan_probe(struct platform_device *pdev)
         mem_size = resource_size(mem);
         if (!request_mem_region(mem->start, mem_size, pdev->name)) {
                 err = -EBUSY;
-                goto failed_req;
+                goto failed_get;
         }
 
         base = ioremap(mem->start, mem_size);
@@ -977,9 +977,8 @@ static int __devinit flexcan_probe(struct platform_device *pdev)
         iounmap(base);
  failed_map:
         release_mem_region(mem->start, mem_size);
- failed_req:
-        clk_put(clk);
  failed_get:
+        clk_put(clk);
  failed_clock:
         return err;
 }
diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c
index 75622d54581f..1b49df6b2470 100644
--- a/drivers/net/can/slcan.c
+++ b/drivers/net/can/slcan.c
@@ -425,17 +425,16 @@ static void slc_setup(struct net_device *dev)
  * in parallel
  */
 
-static unsigned int slcan_receive_buf(struct tty_struct *tty,
+static void slcan_receive_buf(struct tty_struct *tty,
                               const unsigned char *cp, char *fp, int count)
 {
         struct slcan *sl = (struct slcan *) tty->disc_data;
-        int bytes = count;
 
         if (!sl || sl->magic != SLCAN_MAGIC || !netif_running(sl->dev))
-                return -ENODEV;
+                return;
 
         /* Read the characters out of the buffer */
-        while (bytes--) {
+        while (count--) {
                 if (fp && *fp++) {
                         if (!test_and_set_bit(SLF_ERROR, &sl->flags))
                                 sl->dev->stats.rx_errors++;
@@ -444,8 +443,6 @@ static unsigned int slcan_receive_buf(struct tty_struct *tty,
                 }
                 slcan_unesc(sl, *cp++);
         }
-
-        return count;
 }
 
 /************************************
diff --git a/drivers/net/davinci_emac.c b/drivers/net/davinci_emac.c
index 29a4f06fbfcf..dcc4a170b0f3 100644
--- a/drivers/net/davinci_emac.c
+++ b/drivers/net/davinci_emac.c
@@ -1781,8 +1781,8 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
         ndev = alloc_etherdev(sizeof(struct emac_priv));
         if (!ndev) {
                 dev_err(&pdev->dev, "error allocating net_device\n");
-                clk_put(emac_clk);
-                return -ENOMEM;
+                rc = -ENOMEM;
+                goto free_clk;
         }
 
         platform_set_drvdata(pdev, ndev);
@@ -1796,7 +1796,8 @@ static int __devinit davinci_emac_probe(struct platform_device *pdev)
         pdata = pdev->dev.platform_data;
         if (!pdata) {
                 dev_err(&pdev->dev, "no platform data\n");
-                return -ENODEV;
+                rc = -ENODEV;
+                goto probe_quit;
         }
 
         /* MAC addr and PHY mask , RMII enable info from platform_data */
@@ -1929,8 +1930,9 @@ no_dma:
         iounmap(priv->remap_addr);
 
 probe_quit:
-        clk_put(emac_clk);
         free_netdev(ndev);
+free_clk:
+        clk_put(emac_clk);
         return rc;
 }
 
diff --git a/drivers/net/depca.c b/drivers/net/depca.c
index 17654059922d..8b0084d17c8c 100644
--- a/drivers/net/depca.c
+++ b/drivers/net/depca.c
@@ -331,18 +331,18 @@ static struct {
                          "DE422",\
                          ""}
 
-static const char* const depca_signature[] __devinitconst = DEPCA_SIGNATURE;
+static char* __initdata depca_signature[] = DEPCA_SIGNATURE;
 
 enum depca_type {
         DEPCA, de100, de101, de200, de201, de202, de210, de212, de422, unknown
 };
 
-static const char depca_string[] = "depca";
+static char depca_string[] = "depca";
 
 static int depca_device_remove (struct device *device);
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id depca_eisa_ids[] __devinitconst = {
+static struct eisa_device_id depca_eisa_ids[] = {
         { "DEC4220", de422 },
         { "" }
 };
@@ -367,19 +367,19 @@ static struct eisa_driver depca_eisa_driver = {
 #define DE210_ID 0x628d
 #define DE212_ID 0x6def
 
-static const short depca_mca_adapter_ids[] __devinitconst = {
+static short depca_mca_adapter_ids[] = {
         DE210_ID,
         DE212_ID,
         0x0000
 };
 
-static const char *depca_mca_adapter_name[] = {
+static char *depca_mca_adapter_name[] = {
         "DEC EtherWORKS MC Adapter (DE210)",
         "DEC EtherWORKS MC Adapter (DE212)",
         NULL
 };
 
-static const enum depca_type depca_mca_adapter_type[] = {
+static enum depca_type depca_mca_adapter_type[] = {
         de210,
         de212,
         0
@@ -541,9 +541,10 @@ static void SetMulticastFilter(struct net_device *dev);
 static int load_packet(struct net_device *dev, struct sk_buff *skb);
 static void depca_dbg_open(struct net_device *dev);
 
-static const u_char de1xx_irq[] __devinitconst = { 2, 3, 4, 5, 7, 9, 0 };
-static const u_char de2xx_irq[] __devinitconst = { 5, 9, 10, 11, 15, 0 };
-static const u_char de422_irq[] __devinitconst = { 5, 9, 10, 11, 0 };
+static u_char de1xx_irq[] __initdata = { 2, 3, 4, 5, 7, 9, 0 };
+static u_char de2xx_irq[] __initdata = { 5, 9, 10, 11, 15, 0 };
+static u_char de422_irq[] __initdata = { 5, 9, 10, 11, 0 };
+static u_char *depca_irq;
 
 static int irq;
 static int io;
@@ -579,7 +580,7 @@ static const struct net_device_ops depca_netdev_ops = {
         .ndo_validate_addr      = eth_validate_addr,
 };
 
-static int __devinit depca_hw_init (struct net_device *dev, struct device *device)
+static int __init depca_hw_init (struct net_device *dev, struct device *device)
 {
         struct depca_private *lp;
         int i, j, offset, netRAM, mem_len, status = 0;
@@ -747,7 +748,6 @@ static int __devinit depca_hw_init (struct net_device *dev, struct device *devic
         if (dev->irq < 2) {
                 unsigned char irqnum;
                 unsigned long irq_mask, delay;
-                const u_char *depca_irq;
 
                 irq_mask = probe_irq_on();
 
@@ -770,7 +770,6 @@ static int __devinit depca_hw_init (struct net_device *dev, struct device *devic
                         break;
 
                 default:
-                        depca_irq = NULL;
                         break;  /* Not reached */
                 }
 
@@ -1303,7 +1302,7 @@ static void SetMulticastFilter(struct net_device *dev)
         }
 }
 
-static int __devinit depca_common_init (u_long ioaddr, struct net_device **devp)
+static int __init depca_common_init (u_long ioaddr, struct net_device **devp)
 {
         int status = 0;
 
@@ -1334,7 +1333,7 @@ static int __devinit depca_common_init (u_long ioaddr, struct net_device **devp)
 /*
 ** Microchannel bus I/O device probe
 */
-static int __devinit depca_mca_probe(struct device *device)
+static int __init depca_mca_probe(struct device *device)
 {
         unsigned char pos[2];
         unsigned char where;
@@ -1458,7 +1457,7 @@ static int __devinit depca_mca_probe(struct device *device)
 ** ISA bus I/O device probe
 */
 
-static void __devinit depca_platform_probe (void)
+static void __init depca_platform_probe (void)
 {
         int i;
         struct platform_device *pldev;
@@ -1498,7 +1497,7 @@ static void __devinit depca_platform_probe (void)
         }
 }
 
-static enum depca_type __devinit depca_shmem_probe (ulong *mem_start)
+static enum depca_type __init depca_shmem_probe (ulong *mem_start)
 {
         u_long mem_base[] = DEPCA_RAM_BASE_ADDRESSES;
         enum depca_type adapter = unknown;
@@ -1559,7 +1558,7 @@ static int __devinit depca_isa_probe (struct platform_device *device)
 */
 
 #ifdef CONFIG_EISA
-static int __devinit depca_eisa_probe (struct device *device)
+static int __init depca_eisa_probe (struct device *device)
 {
         enum depca_type adapter = unknown;
         struct eisa_device *edev;
@@ -1630,7 +1629,7 @@ static int __devexit depca_device_remove (struct device *device)
 ** and Boot (readb) ROM. This will also give us a clue to the network RAM
 ** base address.
 */
-static int __devinit DepcaSignature(char *name, u_long base_addr)
+static int __init DepcaSignature(char *name, u_long base_addr)
 {
         u_int i, j, k;
         void __iomem *ptr;
diff --git a/drivers/net/dm9000.c b/drivers/net/dm9000.c
index fbaff3584bd4..ee597e676ee5 100644
--- a/drivers/net/dm9000.c
+++ b/drivers/net/dm9000.c
@@ -1157,9 +1157,6 @@ dm9000_open(struct net_device *dev)
 
         irqflags |= IRQF_SHARED;
 
-        if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
-                return -EAGAIN;
-
         /* GPIO0 on pre-activate PHY, Reg 1F is not set by reset */
         iow(db, DM9000_GPR, 0); /* REG_1F bit0 activate phyxcer */
         mdelay(1); /* delay needs by DM9000B */
@@ -1168,6 +1165,9 @@ dm9000_open(struct net_device *dev)
         dm9000_reset(db);
         dm9000_init_dm9000(dev);
 
+        if (request_irq(dev->irq, dm9000_interrupt, irqflags, dev->name, dev))
+                return -EAGAIN;
+
         /* Init driver variable */
         db->dbug_cnt = 0;
 
diff --git a/drivers/net/hamradio/6pack.c b/drivers/net/hamradio/6pack.c
index 992089639ea4..3e5d0b6b6516 100644
--- a/drivers/net/hamradio/6pack.c
+++ b/drivers/net/hamradio/6pack.c
@@ -456,7 +456,7 @@ out:
  * a block of 6pack data has been received, which can now be decapsulated
  * and sent on to some IP layer for further processing.
  */
-static unsigned int sixpack_receive_buf(struct tty_struct *tty,
+static void sixpack_receive_buf(struct tty_struct *tty,
         const unsigned char *cp, char *fp, int count)
 {
         struct sixpack *sp;
@@ -464,11 +464,11 @@ static unsigned int sixpack_receive_buf(struct tty_struct *tty,
         int count1;
 
         if (!count)
-                return 0;
+                return;
 
         sp = sp_get(tty);
         if (!sp)
-                return -ENODEV;
+                return;
 
         memcpy(buf, cp, count < sizeof(buf) ? count : sizeof(buf));
 
@@ -487,8 +487,6 @@ static unsigned int sixpack_receive_buf(struct tty_struct *tty,
 
         sp_put(sp);
         tty_unthrottle(tty);
-
-        return count1;
 }
 
 /*
diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c
index 0e4f23531140..4c628393c8b1 100644
--- a/drivers/net/hamradio/mkiss.c
+++ b/drivers/net/hamradio/mkiss.c
@@ -923,14 +923,13 @@ static long mkiss_compat_ioctl(struct tty_struct *tty, struct file *file,
  * a block of data has been received, which can now be decapsulated
  * and sent on to the AX.25 layer for further processing.
  */
-static unsigned int mkiss_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void mkiss_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+        char *fp, int count)
 {
         struct mkiss *ax = mkiss_get(tty);
-        int bytes = count;
 
         if (!ax)
-                return -ENODEV;
+                return;
 
         /*
          * Argh! mtu change time! - costs us the packet part received
@@ -940,7 +939,7 @@ static unsigned int mkiss_receive_buf(struct tty_struct *tty,
                 ax_changedmtu(ax);
 
         /* Read the characters out of the buffer */
-        while (bytes--) {
+        while (count--) {
                 if (fp != NULL && *fp++) {
                         if (!test_and_set_bit(AXF_ERROR, &ax->flags))
                                 ax->dev->stats.rx_errors++;
@@ -953,8 +952,6 @@ static unsigned int mkiss_receive_buf(struct tty_struct *tty,
 
         mkiss_put(ax);
         tty_unthrottle(tty);
-
-        return count;
 }
 
 /*
diff --git a/drivers/net/hp100.c b/drivers/net/hp100.c
index c52a1df5d922..8e10d2f6a5ad 100644
--- a/drivers/net/hp100.c
+++ b/drivers/net/hp100.c
@@ -188,14 +188,14 @@ struct hp100_private {
  *  variables
  */
 #ifdef CONFIG_ISA
-static const char *const hp100_isa_tbl[] __devinitconst = {
+static const char *hp100_isa_tbl[] = {
         "HWPF150", /* HP J2573 rev A */
         "HWP1950", /* HP J2573 */
 };
 #endif
 
 #ifdef CONFIG_EISA
-static const struct eisa_device_id hp100_eisa_tbl[] __devinitconst = {
+static struct eisa_device_id hp100_eisa_tbl[] = {
         { "HWPF180" }, /* HP J2577 rev A */
         { "HWP1920" }, /* HP 27248B */
         { "HWP1940" }, /* HP J2577 */
@@ -336,7 +336,7 @@ static __devinit const char *hp100_read_id(int ioaddr)
 }
 
 #ifdef CONFIG_ISA
-static __devinit int hp100_isa_probe1(struct net_device *dev, int ioaddr)
+static __init int hp100_isa_probe1(struct net_device *dev, int ioaddr)
 {
         const char *sig;
         int i;
@@ -372,7 +372,7 @@ static __devinit int hp100_isa_probe1(struct net_device *dev, int ioaddr)
  * EISA and PCI are handled by device infrastructure.
  */
 
-static int  __devinit hp100_isa_probe(struct net_device *dev, int addr)
+static int  __init hp100_isa_probe(struct net_device *dev, int addr)
 {
         int err = -ENODEV;
 
@@ -396,7 +396,7 @@ static int  __devinit hp100_isa_probe(struct net_device *dev, int addr)
 #endif /* CONFIG_ISA */
 
 #if !defined(MODULE) && defined(CONFIG_ISA)
-struct net_device * __devinit hp100_probe(int unit)
+struct net_device * __init hp100_probe(int unit)
 {
         struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private));
         int err;
@@ -2843,7 +2843,7 @@ static void cleanup_dev(struct net_device *d)
 }
 
 #ifdef CONFIG_EISA
-static int __devinit hp100_eisa_probe (struct device *gendev)
+static int __init hp100_eisa_probe (struct device *gendev)
 {
         struct net_device *dev = alloc_etherdev(sizeof(struct hp100_private));
         struct eisa_device *edev = to_eisa_device(gendev);
diff --git a/drivers/net/ibmlana.c b/drivers/net/ibmlana.c
index 136d7544cc33..a7d6cad32953 100644
--- a/drivers/net/ibmlana.c
+++ b/drivers/net/ibmlana.c
@@ -895,12 +895,12 @@ static int ibmlana_irq;
 static int ibmlana_io;
 static int startslot;           /* counts through slots when probing multiple devices */
 
-static const short ibmlana_adapter_ids[] __devinitconst = {
+static short ibmlana_adapter_ids[] __initdata = {
         IBM_LANA_ID,
         0x0000
 };
 
-static const char *const ibmlana_adapter_names[] __devinitconst = {
+static char *ibmlana_adapter_names[] __devinitdata = {
         "IBM LAN Adapter/A",
         NULL
 };
diff --git a/drivers/net/irda/irtty-sir.c b/drivers/net/irda/irtty-sir.c
index 035861d8acb1..3352b2443e58 100644
--- a/drivers/net/irda/irtty-sir.c
+++ b/drivers/net/irda/irtty-sir.c
@@ -216,23 +216,23 @@ static int irtty_do_write(struct sir_dev *dev, const unsigned char *ptr, size_t
  * usbserial:   urb-complete-interrupt / softint
  */
 
-static unsigned int irtty_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void irtty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                              char *fp, int count) 
 {
         struct sir_dev *dev;
         struct sirtty_cb *priv = tty->disc_data;
         int     i;
 
-        IRDA_ASSERT(priv != NULL, return -ENODEV;);
-        IRDA_ASSERT(priv->magic == IRTTY_MAGIC, return -EINVAL;);
+        IRDA_ASSERT(priv != NULL, return;);
+        IRDA_ASSERT(priv->magic == IRTTY_MAGIC, return;);
 
         if (unlikely(count==0))         /* yes, this happens */
-                return 0;
+                return;
 
         dev = priv->dev;
         if (!dev) {
                 IRDA_WARNING("%s(), not ready yet!\n", __func__);
-                return -ENODEV;
+                return;
         }
 
         for (i = 0; i < count; i++) {
@@ -242,13 +242,11 @@ static unsigned int irtty_receive_buf(struct tty_struct *tty,
                 if (fp && *fp++) { 
                         IRDA_DEBUG(0, "Framing or parity error!\n");
                         sirdev_receive(dev, NULL, 0);   /* notify sir_dev (updating stats) */
-                        return -EINVAL;
+                        return;
                 }
         }
 
         sirdev_receive(dev, cp, count);
-
-        return count;
 }
 
 /*
diff --git a/drivers/net/irda/smsc-ircc2.c b/drivers/net/irda/smsc-ircc2.c
index 69b5707db369..8800e1fe4129 100644
--- a/drivers/net/irda/smsc-ircc2.c
+++ b/drivers/net/irda/smsc-ircc2.c
@@ -222,19 +222,19 @@ static void smsc_ircc_set_transceiver_for_speed(struct smsc_ircc_cb *self, u32 s
 static void smsc_ircc_sir_wait_hw_transmitter_finish(struct smsc_ircc_cb *self);
 
 /* Probing */
-static int smsc_ircc_look_for_chips(void);
-static const struct smsc_chip * smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type);
-static int smsc_superio_flat(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
-static int smsc_superio_paged(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
-static int smsc_superio_fdc(unsigned short cfg_base);
-static int smsc_superio_lpc(unsigned short cfg_base);
+static int __init smsc_ircc_look_for_chips(void);
+static const struct smsc_chip * __init smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type);
+static int __init smsc_superio_flat(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
+static int __init smsc_superio_paged(const struct smsc_chip *chips, unsigned short cfg_base, char *type);
+static int __init smsc_superio_fdc(unsigned short cfg_base);
+static int __init smsc_superio_lpc(unsigned short cfg_base);
 #ifdef CONFIG_PCI
-static int preconfigure_smsc_chip(struct smsc_ircc_subsystem_configuration *conf);
-static int preconfigure_through_82801(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
-static void preconfigure_ali_port(struct pci_dev *dev,
+static int __init preconfigure_smsc_chip(struct smsc_ircc_subsystem_configuration *conf);
+static int __init preconfigure_through_82801(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
+static void __init preconfigure_ali_port(struct pci_dev *dev,
                                          unsigned short port);
-static int preconfigure_through_ali(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
-static int smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
+static int __init preconfigure_through_ali(struct pci_dev *dev, struct smsc_ircc_subsystem_configuration *conf);
+static int __init smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
                                                     unsigned short ircc_fir,
                                                     unsigned short ircc_sir,
                                                     unsigned char ircc_dma,
@@ -366,7 +366,7 @@ static inline void register_bank(int iobase, int bank)
 }
 
 /* PNP hotplug support */
-static const struct pnp_device_id smsc_ircc_pnp_table[] __devinitconst = {
+static const struct pnp_device_id smsc_ircc_pnp_table[] = {
         { .id = "SMCf010", .driver_data = 0 },
         /* and presumably others */
         { }
@@ -515,7 +515,7 @@ static const struct net_device_ops smsc_ircc_netdev_ops = {
  *    Try to open driver instance
  *
  */
-static int __devinit smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma, u8 irq)
+static int __init smsc_ircc_open(unsigned int fir_base, unsigned int sir_base, u8 dma, u8 irq)
 {
         struct smsc_ircc_cb *self;
         struct net_device *dev;
@@ -2273,7 +2273,7 @@ static int __init smsc_superio_paged(const struct smsc_chip *chips, unsigned sho
 }
 
 
-static int __devinit smsc_access(unsigned short cfg_base, unsigned char reg)
+static int __init smsc_access(unsigned short cfg_base, unsigned char reg)
 {
         IRDA_DEBUG(1, "%s\n", __func__);
 
@@ -2281,7 +2281,7 @@ static int __devinit smsc_access(unsigned short cfg_base, unsigned char reg)
         return inb(cfg_base) != reg ? -1 : 0;
 }
 
-static const struct smsc_chip * __devinit smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type)
+static const struct smsc_chip * __init smsc_ircc_probe(unsigned short cfg_base, u8 reg, const struct smsc_chip *chip, char *type)
 {
         u8 devid, xdevid, rev;
 
@@ -2406,7 +2406,7 @@ static int __init smsc_superio_lpc(unsigned short cfg_base)
 #ifdef CONFIG_PCI
 #define PCIID_VENDOR_INTEL 0x8086
 #define PCIID_VENDOR_ALI 0x10b9
-static const struct smsc_ircc_subsystem_configuration subsystem_configurations[] __devinitconst = {
+static struct smsc_ircc_subsystem_configuration subsystem_configurations[] __initdata = {
         /*
          * Subsystems needing entries:
          * 0x10b9:0x1533 0x103c:0x0850 HP nx9010 family
@@ -2532,7 +2532,7 @@ static const struct smsc_ircc_subsystem_configuration subsystem_configurations[]
  * (FIR port, SIR port, FIR DMA, FIR IRQ)
  * through the chip configuration port.
  */
-static int __devinit preconfigure_smsc_chip(struct
+static int __init preconfigure_smsc_chip(struct
                                          smsc_ircc_subsystem_configuration
                                          *conf)
 {
@@ -2633,7 +2633,7 @@ static int __devinit preconfigure_smsc_chip(struct
  * or Intel 82801DB/DBL (ICH4/ICH4-L) LPC Interface Bridge.
  * They all work the same way!
  */
-static int __devinit preconfigure_through_82801(struct pci_dev *dev,
+static int __init preconfigure_through_82801(struct pci_dev *dev,
                                              struct
                                              smsc_ircc_subsystem_configuration
                                              *conf)
@@ -2786,7 +2786,7 @@ static int __devinit preconfigure_through_82801(struct pci_dev *dev,
  * This is based on reverse-engineering since ALi does not
  * provide any data sheet for the 1533 chip.
  */
-static void __devinit preconfigure_ali_port(struct pci_dev *dev,
+static void __init preconfigure_ali_port(struct pci_dev *dev,
                                          unsigned short port)
 {
         unsigned char reg;
@@ -2824,7 +2824,7 @@ static void __devinit preconfigure_ali_port(struct pci_dev *dev,
         IRDA_MESSAGE("Activated ALi 1533 ISA bridge port 0x%04x.\n", port);
 }
 
-static int __devinit preconfigure_through_ali(struct pci_dev *dev,
+static int __init preconfigure_through_ali(struct pci_dev *dev,
                                            struct
                                            smsc_ircc_subsystem_configuration
                                            *conf)
@@ -2837,7 +2837,7 @@ static int __devinit preconfigure_through_ali(struct pci_dev *dev,
         return preconfigure_smsc_chip(conf);
 }
 
-static int __devinit smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
+static int __init smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
                                                     unsigned short ircc_fir,
                                                     unsigned short ircc_sir,
                                                     unsigned char ircc_dma,
@@ -2849,7 +2849,7 @@ static int __devinit smsc_ircc_preconfigure_subsystems(unsigned short ircc_cfg,
         int ret = 0;
 
         for_each_pci_dev(dev) {
-                const struct smsc_ircc_subsystem_configuration *conf;
+                struct smsc_ircc_subsystem_configuration *conf;
 
                 /*
                  * Cache the subsystem vendor/device:
diff --git a/drivers/net/ks8842.c b/drivers/net/ks8842.c
index 4d40626b3bfa..fc12ac0d9f2e 100644
--- a/drivers/net/ks8842.c
+++ b/drivers/net/ks8842.c
@@ -661,7 +661,7 @@ static void ks8842_rx_frame(struct net_device *netdev,
 
         /* check the status */
         if ((status & RXSR_VALID) && !(status & RXSR_ERROR)) {
-                struct sk_buff *skb = netdev_alloc_skb_ip_align(netdev, len);
+                struct sk_buff *skb = netdev_alloc_skb_ip_align(netdev, len + 3);
 
                 if (skb) {
 
diff --git a/drivers/net/ne3210.c b/drivers/net/ne3210.c
index e8984b0ca521..243ed2aee88e 100644
--- a/drivers/net/ne3210.c
+++ b/drivers/net/ne3210.c
@@ -80,20 +80,17 @@ static void ne3210_block_output(struct net_device *dev, int count, const unsigne
 
 #define NE3210_DEBUG    0x0
 
-static const unsigned char irq_map[] __devinitconst =
-        { 15, 12, 11, 10, 9, 7, 5, 3 };
-static const unsigned int shmem_map[] __devinitconst =
-        { 0xff0, 0xfe0, 0xfff0, 0xd8, 0xffe0, 0xffc0, 0xd0, 0x0 };
-static const char *const ifmap[] __devinitconst =
-        { "UTP", "?", "BNC", "AUI" };
-static const int ifmap_val[] __devinitconst = {
+static unsigned char irq_map[] __initdata = {15, 12, 11, 10, 9, 7, 5, 3};
+static unsigned int shmem_map[] __initdata = {0xff0, 0xfe0, 0xfff0, 0xd8, 0xffe0, 0xffc0, 0xd0, 0x0};
+static const char *ifmap[] __initdata = {"UTP", "?", "BNC", "AUI"};
+static int ifmap_val[] __initdata = {
                 IF_PORT_10BASET,
                 IF_PORT_UNKNOWN,
                 IF_PORT_10BASE2,
                 IF_PORT_AUI,
 };
 
-static int __devinit ne3210_eisa_probe (struct device *device)
+static int __init ne3210_eisa_probe (struct device *device)
 {
         unsigned long ioaddr, phys_mem;
         int i, retval, port_index;
@@ -316,7 +313,7 @@ static void ne3210_block_output(struct net_device *dev, int count,
         memcpy_toio(shmem, buf, count);
 }
 
-static const struct eisa_device_id ne3210_ids[] __devinitconst = {
+static struct eisa_device_id ne3210_ids[] = {
         { "EGL0101" },
         { "NVL1801" },
         { "" },
diff --git a/drivers/net/ppp_async.c b/drivers/net/ppp_async.c
index 53872d7d7382..a1b82c9c67d2 100644
--- a/drivers/net/ppp_async.c
+++ b/drivers/net/ppp_async.c
@@ -340,7 +340,7 @@ ppp_asynctty_poll(struct tty_struct *tty, struct file *file, poll_table *wait)
 }
 
 /* May sleep, don't call from interrupt level or with interrupts disabled */
-static unsigned int
+static void
 ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf,
                   char *cflags, int count)
 {
@@ -348,7 +348,7 @@ ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf,
         unsigned long flags;
 
         if (!ap)
-                return -ENODEV;
+                return;
         spin_lock_irqsave(&ap->recv_lock, flags);
         ppp_async_input(ap, buf, cflags, count);
         spin_unlock_irqrestore(&ap->recv_lock, flags);
@@ -356,8 +356,6 @@ ppp_asynctty_receive(struct tty_struct *tty, const unsigned char *buf,
                 tasklet_schedule(&ap->tsk);
         ap_put(ap);
         tty_unthrottle(tty);
-
-        return count;
 }
 
 static void
diff --git a/drivers/net/ppp_synctty.c b/drivers/net/ppp_synctty.c
index 0815790a5cf9..2573f525f11c 100644
--- a/drivers/net/ppp_synctty.c
+++ b/drivers/net/ppp_synctty.c
@@ -381,7 +381,7 @@ ppp_sync_poll(struct tty_struct *tty, struct file *file, poll_table *wait)
 }
 
 /* May sleep, don't call from interrupt level or with interrupts disabled */
-static unsigned int
+static void
 ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf,
                   char *cflags, int count)
 {
@@ -389,7 +389,7 @@ ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf,
         unsigned long flags;
 
         if (!ap)
-                return -ENODEV;
+                return;
         spin_lock_irqsave(&ap->recv_lock, flags);
         ppp_sync_input(ap, buf, cflags, count);
         spin_unlock_irqrestore(&ap->recv_lock, flags);
@@ -397,8 +397,6 @@ ppp_sync_receive(struct tty_struct *tty, const unsigned char *buf,
                 tasklet_schedule(&ap->tsk);
         sp_put(ap);
         tty_unthrottle(tty);
-
-        return count;
 }
 
 static void
diff --git a/drivers/net/slip.c b/drivers/net/slip.c
index 584809c656d5..8ec1a9a0bb9a 100644
--- a/drivers/net/slip.c
+++ b/drivers/net/slip.c
@@ -670,17 +670,16 @@ static void sl_setup(struct net_device *dev)
  * in parallel
  */
 
-static unsigned int slip_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void slip_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                                                        char *fp, int count)
 {
         struct slip *sl = tty->disc_data;
-        int bytes = count;
 
         if (!sl || sl->magic != SLIP_MAGIC || !netif_running(sl->dev))
-                return -ENODEV;
+                return;
 
         /* Read the characters out of the buffer */
-        while (bytes--) {
+        while (count--) {
                 if (fp && *fp++) {
                         if (!test_and_set_bit(SLF_ERROR, &sl->flags))
                                 sl->dev->stats.rx_errors++;
@@ -694,8 +693,6 @@ static unsigned int slip_receive_buf(struct tty_struct *tty,
 #endif
                         slip_unesc(sl, *cp++);
         }
-
-        return count;
 }
 
 /************************************
diff --git a/drivers/net/smc-mca.c b/drivers/net/smc-mca.c
index 0f29f261fcfe..d07c39cb4daf 100644
--- a/drivers/net/smc-mca.c
+++ b/drivers/net/smc-mca.c
@@ -156,7 +156,7 @@ static const struct {
    { 14, 15 }
 };
 
-static const short smc_mca_adapter_ids[] __devinitconst = {
+static short smc_mca_adapter_ids[] __initdata = {
         0x61c8,
         0x61c9,
         0x6fc0,
@@ -168,7 +168,7 @@ static const short smc_mca_adapter_ids[] __devinitconst = {
         0x0000
 };
 
-static const char *const smc_mca_adapter_names[] __devinitconst = {
+static char *smc_mca_adapter_names[] __initdata = {
         "SMC Ethercard PLUS Elite/A BNC/AUI (WD8013EP/A)",
         "SMC Ethercard PLUS Elite/A UTP/AUI (WD8013WP/A)",
         "WD Ethercard PLUS/A (WD8003E/A or WD8003ET/A)",
@@ -199,7 +199,7 @@ static const struct net_device_ops ultramca_netdev_ops = {
 #endif
 };
 
-static int __devinit ultramca_probe(struct device *gen_dev)
+static int __init ultramca_probe(struct device *gen_dev)
 {
         unsigned short ioaddr;
         struct net_device *dev;
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index f4b01c638a33..a1f9f9eef37d 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -5774,7 +5774,7 @@ static void tg3_skb_error_unmap(struct tg3_napi *tnapi,
                          dma_unmap_addr(txb, mapping),
                          skb_headlen(skb),
                          PCI_DMA_TODEVICE);
-        for (i = 0; i <= last; i++) {
+        for (i = 0; i < last; i++) {
                 skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 
                 entry = NEXT_TX(entry);
diff --git a/drivers/net/tokenring/madgemc.c b/drivers/net/tokenring/madgemc.c
index 1313aa1315f0..2bedc0ace812 100644
--- a/drivers/net/tokenring/madgemc.c
+++ b/drivers/net/tokenring/madgemc.c
@@ -727,7 +727,7 @@ static int __devexit madgemc_remove(struct device *device)
         return 0;
 }
 
-static const short madgemc_adapter_ids[] __devinitconst = {
+static short madgemc_adapter_ids[] __initdata = {
         0x002d,
         0x0000
 };
diff --git a/drivers/net/tulip/de4x5.c b/drivers/net/tulip/de4x5.c
index 45144d5bd11b..efaa1d69b720 100644
--- a/drivers/net/tulip/de4x5.c
+++ b/drivers/net/tulip/de4x5.c
@@ -1995,7 +1995,7 @@ SetMulticastFilter(struct net_device *dev)
 
 static u_char de4x5_irq[] = EISA_ALLOWED_IRQ_LIST;
 
-static int __devinit de4x5_eisa_probe (struct device *gendev)
+static int __init de4x5_eisa_probe (struct device *gendev)
 {
         struct eisa_device *edev;
         u_long iobase;
@@ -2097,7 +2097,7 @@ static int __devexit de4x5_eisa_remove (struct device *device)
         return 0;
 }
 
-static const struct eisa_device_id de4x5_eisa_ids[] __devinitconst = {
+static struct eisa_device_id de4x5_eisa_ids[] = {
         { "DEC4250", 0 },       /* 0 is the board name index... */
         { "" }
 };
diff --git a/drivers/net/usb/catc.c b/drivers/net/usb/catc.c
index d7221c4a5dcf..8056f8a27c6a 100644
--- a/drivers/net/usb/catc.c
+++ b/drivers/net/usb/catc.c
@@ -495,7 +495,7 @@ static void catc_ctrl_run(struct catc *catc)
         if (!q->dir && q->buf && q->len)
                 memcpy(catc->ctrl_buf, q->buf, q->len);
 
-        if ((status = usb_submit_urb(catc->ctrl_urb, GFP_KERNEL)))
+        if ((status = usb_submit_urb(catc->ctrl_urb, GFP_ATOMIC)))
                 err("submit(ctrl_urb) status %d", status);
 }
 
diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index cdd3ae486109..f33ca6aa29e9 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -54,7 +54,7 @@
 #include <linux/usb/usbnet.h>
 #include <linux/usb/cdc.h>
 
-#define DRIVER_VERSION                          "24-May-2011"
+#define DRIVER_VERSION                          "01-June-2011"
 
 /* CDC NCM subclass 3.2.1 */
 #define USB_CDC_NCM_NDP16_LENGTH_MIN            0x10
@@ -1234,6 +1234,7 @@ static struct usb_driver cdc_ncm_driver = {
         .disconnect = cdc_ncm_disconnect,
         .suspend = usbnet_suspend,
         .resume = usbnet_resume,
+        .reset_resume = usbnet_resume,
         .supports_autosuspend = 1,
 };
 
diff --git a/drivers/net/wan/x25_asy.c b/drivers/net/wan/x25_asy.c
index 40398bf7d036..24297b274cd4 100644
--- a/drivers/net/wan/x25_asy.c
+++ b/drivers/net/wan/x25_asy.c
@@ -517,18 +517,17 @@ static int x25_asy_close(struct net_device *dev)
  * and sent on to some IP layer for further processing.
  */
 
-static unsigned int x25_asy_receive_buf(struct tty_struct *tty,
+static void x25_asy_receive_buf(struct tty_struct *tty,
                                 const unsigned char *cp, char *fp, int count)
 {
         struct x25_asy *sl = tty->disc_data;
-        int bytes = count;
 
         if (!sl || sl->magic != X25_ASY_MAGIC || !netif_running(sl->dev))
                 return;
 
 
         /* Read the characters out of the buffer */
-        while (bytes--) {
+        while (count--) {
                 if (fp && *fp++) {
                         if (!test_and_set_bit(SLF_ERROR, &sl->flags))
                                 sl->dev->stats.rx_errors++;
@@ -537,8 +536,6 @@ static unsigned int x25_asy_receive_buf(struct tty_struct *tty,
                 }
                 x25_asy_unesc(sl, *cp++);
         }
-
-        return count;
 }
 
 /*
diff --git a/drivers/net/wireless/ath/ath9k/Kconfig b/drivers/net/wireless/ath/ath9k/Kconfig
index d9ff8413ab9a..d9c08c619a3a 100644
--- a/drivers/net/wireless/ath/ath9k/Kconfig
+++ b/drivers/net/wireless/ath/ath9k/Kconfig
@@ -26,7 +26,6 @@ config ATH9K
 config ATH9K_PCI
         bool "Atheros ath9k PCI/PCIe bus support"
         depends on ATH9K && PCI
-        default PCI
         ---help---
           This option enables the PCI bus support in ath9k.
 
diff --git a/drivers/net/wireless/ath/ath9k/ar9002_calib.c b/drivers/net/wireless/ath/ath9k/ar9002_calib.c
index 015d97439935..2d4c0910295b 100644
--- a/drivers/net/wireless/ath/ath9k/ar9002_calib.c
+++ b/drivers/net/wireless/ath/ath9k/ar9002_calib.c
@@ -829,7 +829,7 @@ static bool ar9002_hw_init_cal(struct ath_hw *ah, struct ath9k_channel *chan)
         if (AR_SREV_9271(ah)) {
                 if (!ar9285_hw_cl_cal(ah, chan))
                         return false;
-        } else if (AR_SREV_9285_12_OR_LATER(ah)) {
+        } else if (AR_SREV_9285(ah) && AR_SREV_9285_12_OR_LATER(ah)) {
                 if (!ar9285_hw_clc(ah, chan))
                         return false;
         } else {
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
index 0ca7635d0669..ff8150e46f0e 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c
@@ -4645,10 +4645,16 @@ static void ar9003_hw_set_power_per_rate_table(struct ath_hw *ah,
         case 1:
                 break;
         case 2:
-                scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+                if (scaledPower > REDUCE_SCALED_POWER_BY_TWO_CHAIN)
+                        scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+                else
+                        scaledPower = 0;
                 break;
         case 3:
-                scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+                if (scaledPower > REDUCE_SCALED_POWER_BY_THREE_CHAIN)
+                        scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+                else
+                        scaledPower = 0;
                 break;
         }
 
diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.c b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
index eee23ecd118a..892c48b15434 100644
--- a/drivers/net/wireless/ath/ath9k/ar9003_phy.c
+++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.c
@@ -1381,3 +1381,25 @@ void ar9003_hw_bb_watchdog_dbg_info(struct ath_hw *ah)
                 "==== BB update: done ====\n\n");
 }
 EXPORT_SYMBOL(ar9003_hw_bb_watchdog_dbg_info);
+
+void ar9003_hw_disable_phy_restart(struct ath_hw *ah)
+{
+        u32 val;
+
+        /* While receiving unsupported rate frame rx state machine
+         * gets into a state 0xb and if phy_restart happens in that
+         * state, BB would go hang. If RXSM is in 0xb state after
+         * first bb panic, ensure to disable the phy_restart.
+         */
+        if (!((MS(ah->bb_watchdog_last_status,
+                  AR_PHY_WATCHDOG_RX_OFDM_SM) == 0xb) ||
+            ah->bb_hang_rx_ofdm))
+                return;
+
+        ah->bb_hang_rx_ofdm = true;
+        val = REG_READ(ah, AR_PHY_RESTART);
+        val &= ~AR_PHY_RESTART_ENA;
+
+        REG_WRITE(ah, AR_PHY_RESTART, val);
+}
+EXPORT_SYMBOL(ar9003_hw_disable_phy_restart);
diff --git a/drivers/net/wireless/ath/ath9k/eeprom_9287.c b/drivers/net/wireless/ath/ath9k/eeprom_9287.c
index 7856f0d4512d..343fc9f946db 100644
--- a/drivers/net/wireless/ath/ath9k/eeprom_9287.c
+++ b/drivers/net/wireless/ath/ath9k/eeprom_9287.c
@@ -524,10 +524,16 @@ static void ath9k_hw_set_ar9287_power_per_rate_table(struct ath_hw *ah,
         case 1:
                 break;
         case 2:
-                scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+                if (scaledPower > REDUCE_SCALED_POWER_BY_TWO_CHAIN)
+                        scaledPower -= REDUCE_SCALED_POWER_BY_TWO_CHAIN;
+                else
+                        scaledPower = 0;
                 break;
         case 3:
-                scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+                if (scaledPower > REDUCE_SCALED_POWER_BY_THREE_CHAIN)
+                        scaledPower -= REDUCE_SCALED_POWER_BY_THREE_CHAIN;
+                else
+                        scaledPower = 0;
                 break;
         }
         scaledPower = max((u16)0, scaledPower);
diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c
index 72543ce8f616..1be7c8bbef84 100644
--- a/drivers/net/wireless/ath/ath9k/hw.c
+++ b/drivers/net/wireless/ath/ath9k/hw.c
@@ -1555,9 +1555,12 @@ int ath9k_hw_reset(struct ath_hw *ah, struct ath9k_channel *chan,
         if (ah->btcoex_hw.enabled)
                 ath9k_hw_btcoex_enable(ah);
 
-        if (AR_SREV_9300_20_OR_LATER(ah))
+        if (AR_SREV_9300_20_OR_LATER(ah)) {
                 ar9003_hw_bb_watchdog_config(ah);
 
+                ar9003_hw_disable_phy_restart(ah);
+        }
+
         ath9k_hw_apply_gpio_override(ah);
 
         return 0;
diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h
index 57435ce62792..4b157c53d1a8 100644
--- a/drivers/net/wireless/ath/ath9k/hw.h
+++ b/drivers/net/wireless/ath/ath9k/hw.h
@@ -842,6 +842,7 @@ struct ath_hw {
 
         u32 bb_watchdog_last_status;
         u32 bb_watchdog_timeout_ms; /* in ms, 0 to disable */
+        u8 bb_hang_rx_ofdm; /* true if bb hang due to rx_ofdm */
 
         unsigned int paprd_target_power;
         unsigned int paprd_training_power;
@@ -990,6 +991,7 @@ void ar9002_hw_enable_wep_aggregation(struct ath_hw *ah);
 void ar9003_hw_bb_watchdog_config(struct ath_hw *ah);
 void ar9003_hw_bb_watchdog_read(struct ath_hw *ah);
 void ar9003_hw_bb_watchdog_dbg_info(struct ath_hw *ah);
+void ar9003_hw_disable_phy_restart(struct ath_hw *ah);
 void ar9003_paprd_enable(struct ath_hw *ah, bool val);
 void ar9003_paprd_populate_single_table(struct ath_hw *ah,
                                         struct ath9k_hw_cal_data *caldata,
diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c
index a198ee374b05..2ca351fe6d3c 100644
--- a/drivers/net/wireless/ath/ath9k/main.c
+++ b/drivers/net/wireless/ath/ath9k/main.c
@@ -670,7 +670,8 @@ void ath9k_tasklet(unsigned long data)
         u32 status = sc->intrstatus;
         u32 rxmask;
 
-        if (status & ATH9K_INT_FATAL) {
+        if ((status & ATH9K_INT_FATAL) ||
+            (status & ATH9K_INT_BB_WATCHDOG)) {
                 ath_reset(sc, true);
                 return;
         }
@@ -737,6 +738,7 @@ irqreturn_t ath_isr(int irq, void *dev)
 {
 #define SCHED_INTR (                            \
                 ATH9K_INT_FATAL |               \
+                ATH9K_INT_BB_WATCHDOG |         \
                 ATH9K_INT_RXORN |               \
                 ATH9K_INT_RXEOL |               \
                 ATH9K_INT_RX |                  \
diff --git a/drivers/net/wireless/ath/ath9k/rc.c b/drivers/net/wireless/ath/ath9k/rc.c
index 17542214c93f..ba7f36ab0a74 100644
--- a/drivers/net/wireless/ath/ath9k/rc.c
+++ b/drivers/net/wireless/ath/ath9k/rc.c
@@ -689,7 +689,8 @@ static void ath_rc_rate_set_series(const struct ath_rate_table *rate_table,
 
         if (WLAN_RC_PHY_HT(rate_table->info[rix].phy)) {
                 rate->flags |= IEEE80211_TX_RC_MCS;
-                if (WLAN_RC_PHY_40(rate_table->info[rix].phy))
+                if (WLAN_RC_PHY_40(rate_table->info[rix].phy) &&
+                    conf_is_ht40(&txrc->hw->conf))
                         rate->flags |= IEEE80211_TX_RC_40_MHZ_WIDTH;
                 if (WLAN_RC_PHY_SGI(rate_table->info[rix].phy))
                         rate->flags |= IEEE80211_TX_RC_SHORT_GI;
diff --git a/drivers/net/wireless/b43/phy_n.c b/drivers/net/wireless/b43/phy_n.c
index 9ed65157bef5..05960ddde24e 100644
--- a/drivers/net/wireless/b43/phy_n.c
+++ b/drivers/net/wireless/b43/phy_n.c
@@ -3093,7 +3093,7 @@ static int b43_nphy_cal_tx_iq_lo(struct b43_wldev *dev,
         int freq;
         bool avoid = false;
         u8 length;
-        u16 tmp, core, type, count, max, numb, last, cmd;
+        u16 tmp, core, type, count, max, numb, last = 0, cmd;
         const u16 *table;
         bool phy6or5x;
 
diff --git a/drivers/net/wireless/iwlegacy/iwl-4965-lib.c b/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
index 7e5e85a017b5..a7a4739880dc 100644
--- a/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
+++ b/drivers/net/wireless/iwlegacy/iwl-4965-lib.c
@@ -628,11 +628,11 @@ void iwl4965_rx_reply_rx(struct iwl_priv *priv,
 
         /* rx_status carries information about the packet to mac80211 */
         rx_status.mactime = le64_to_cpu(phy_res->timestamp);
+        rx_status.band = (phy_res->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ?
+                                IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
         rx_status.freq =
                 ieee80211_channel_to_frequency(le16_to_cpu(phy_res->channel),
                                                         rx_status.band);
-        rx_status.band = (phy_res->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ?
-                                IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ;
         rx_status.rate_idx =
                 iwl4965_hwrate_to_mac80211_idx(rate_n_flags, rx_status.band);
         rx_status.flag = 0;
diff --git a/drivers/net/wireless/iwlegacy/iwl-4965.c b/drivers/net/wireless/iwlegacy/iwl-4965.c
index f5433c74b845..f9db25bb35c3 100644
--- a/drivers/net/wireless/iwlegacy/iwl-4965.c
+++ b/drivers/net/wireless/iwlegacy/iwl-4965.c
@@ -1543,7 +1543,7 @@ static void iwl4965_temperature_calib(struct iwl_priv *priv)
         s32 temp;
 
         temp = iwl4965_hw_get_temperature(priv);
-        if (temp < 0)
+        if (IWL_TX_POWER_TEMPERATURE_OUT_OF_RANGE(temp))
                 return;
 
         if (priv->temperature != temp) {
diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c
index f8c710db6e6f..fda6fe08cf91 100644
--- a/drivers/net/wireless/iwlwifi/iwl-6000.c
+++ b/drivers/net/wireless/iwlwifi/iwl-6000.c
@@ -603,19 +603,27 @@ struct iwl_cfg iwl6050_2abg_cfg = {
         IWL_DEVICE_6050,
 };
 
+#define IWL_DEVICE_6150                                         \
+        .fw_name_pre = IWL6050_FW_PRE,                          \
+        .ucode_api_max = IWL6050_UCODE_API_MAX,                 \
+        .ucode_api_min = IWL6050_UCODE_API_MIN,                 \
+        .ops = &iwl6150_ops,                                    \
+        .eeprom_ver = EEPROM_6150_EEPROM_VERSION,               \
+        .eeprom_calib_ver = EEPROM_6150_TX_POWER_VERSION,       \
+        .base_params = &iwl6050_base_params,                    \
+        .need_dc_calib = true,                                  \
+        .led_mode = IWL_LED_BLINK,                              \
+        .internal_wimax_coex = true
+
 struct iwl_cfg iwl6150_bgn_cfg = {
         .name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BGN",
-        .fw_name_pre = IWL6050_FW_PRE,
-        .ucode_api_max = IWL6050_UCODE_API_MAX,
-        .ucode_api_min = IWL6050_UCODE_API_MIN,
-        .eeprom_ver = EEPROM_6150_EEPROM_VERSION,
-        .eeprom_calib_ver = EEPROM_6150_TX_POWER_VERSION,
-        .ops = &iwl6150_ops,
-        .base_params = &iwl6050_base_params,
+        IWL_DEVICE_6150,
         .ht_params = &iwl6000_ht_params,
-        .need_dc_calib = true,
-        .led_mode = IWL_LED_RF_STATE,
-        .internal_wimax_coex = true,
+};
+
+struct iwl_cfg iwl6150_bg_cfg = {
+        .name = "Intel(R) Centrino(R) Wireless-N + WiMAX 6150 BG",
+        IWL_DEVICE_6150,
 };
 
 struct iwl_cfg iwl6000_3agn_cfg = {
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c
index 11c6c1169e78..a662adcb2adb 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.c
@@ -3831,11 +3831,11 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = {
 
 /* 6150 WiFi/WiMax Series */
         {IWL_PCI_DEVICE(0x0885, 0x1305, iwl6150_bgn_cfg)},
-        {IWL_PCI_DEVICE(0x0885, 0x1306, iwl6150_bgn_cfg)},
+        {IWL_PCI_DEVICE(0x0885, 0x1307, iwl6150_bg_cfg)},
         {IWL_PCI_DEVICE(0x0885, 0x1325, iwl6150_bgn_cfg)},
-        {IWL_PCI_DEVICE(0x0885, 0x1326, iwl6150_bgn_cfg)},
+        {IWL_PCI_DEVICE(0x0885, 0x1327, iwl6150_bg_cfg)},
         {IWL_PCI_DEVICE(0x0886, 0x1315, iwl6150_bgn_cfg)},
-        {IWL_PCI_DEVICE(0x0886, 0x1316, iwl6150_bgn_cfg)},
+        {IWL_PCI_DEVICE(0x0886, 0x1317, iwl6150_bg_cfg)},
 
 /* 1000 Series WiFi */
         {IWL_PCI_DEVICE(0x0083, 0x1205, iwl1000_bgn_cfg)},
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.h b/drivers/net/wireless/iwlwifi/iwl-agn.h
index 2495fe7a58cb..d1716844002e 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.h
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.h
@@ -89,6 +89,7 @@ extern struct iwl_cfg iwl6000_3agn_cfg;
 extern struct iwl_cfg iwl6050_2agn_cfg;
 extern struct iwl_cfg iwl6050_2abg_cfg;
 extern struct iwl_cfg iwl6150_bgn_cfg;
+extern struct iwl_cfg iwl6150_bg_cfg;
 extern struct iwl_cfg iwl1000_bgn_cfg;
 extern struct iwl_cfg iwl1000_bg_cfg;
 extern struct iwl_cfg iwl100_bgn_cfg;
diff --git a/drivers/net/wireless/libertas/cmd.c b/drivers/net/wireless/libertas/cmd.c
index 84566db486d2..71c8f3fccfa1 100644
--- a/drivers/net/wireless/libertas/cmd.c
+++ b/drivers/net/wireless/libertas/cmd.c
@@ -994,6 +994,8 @@ static void lbs_submit_command(struct lbs_private *priv,
         cmd = cmdnode->cmdbuf;
 
         spin_lock_irqsave(&priv->driver_lock, flags);
+        priv->seqnum++;
+        cmd->seqnum = cpu_to_le16(priv->seqnum);
         priv->cur_cmd = cmdnode;
         spin_unlock_irqrestore(&priv->driver_lock, flags);
 
@@ -1621,11 +1623,9 @@ struct cmd_ctrl_node *__lbs_cmd_async(struct lbs_private *priv,
         /* Copy the incoming command to the buffer */
         memcpy(cmdnode->cmdbuf, in_cmd, in_cmd_size);
 
-        /* Set sequence number, clean result, move to buffer */
-        priv->seqnum++;
+        /* Set command, clean result, move to buffer */
         cmdnode->cmdbuf->command = cpu_to_le16(command);
         cmdnode->cmdbuf->size    = cpu_to_le16(in_cmd_size);
-        cmdnode->cmdbuf->seqnum  = cpu_to_le16(priv->seqnum);
         cmdnode->cmdbuf->result  = 0;
 
         lbs_deb_host("PREP_CMD: command 0x%04x\n", command);
diff --git a/drivers/net/wireless/mwifiex/sdio.h b/drivers/net/wireless/mwifiex/sdio.h
index a0e9bc5253e0..4e97e90aa399 100644
--- a/drivers/net/wireless/mwifiex/sdio.h
+++ b/drivers/net/wireless/mwifiex/sdio.h
@@ -167,8 +167,8 @@
 /* Rx unit register */
 #define CARD_RX_UNIT_REG                0x63
 
-/* Event header Len*/
-#define MWIFIEX_EVENT_HEADER_LEN           8
+/* Event header len w/o 4 bytes of interface header */
+#define MWIFIEX_EVENT_HEADER_LEN           4
 
 /* Max retry number of CMD53 write */
 #define MAX_WRITE_IOMEM_RETRY           2
diff --git a/drivers/net/wireless/rt2x00/Kconfig b/drivers/net/wireless/rt2x00/Kconfig
index 9def1e5369a1..b2f8b8fd4d2d 100644
--- a/drivers/net/wireless/rt2x00/Kconfig
+++ b/drivers/net/wireless/rt2x00/Kconfig
@@ -166,7 +166,6 @@ config RT2800USB_RT35XX
 config RT2800USB_RT53XX
        bool "rt2800usb - Include support for rt53xx devices (EXPERIMENTAL)"
        depends on EXPERIMENTAL
-       default y
        ---help---
          This adds support for rt53xx wireless chipset family to the
          rt2800pci driver.
diff --git a/drivers/net/wireless/rtlwifi/pci.c b/drivers/net/wireless/rtlwifi/pci.c
index a40952845436..89100e7c553b 100644
--- a/drivers/net/wireless/rtlwifi/pci.c
+++ b/drivers/net/wireless/rtlwifi/pci.c
@@ -669,11 +669,6 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
                                                          &rx_status,
                                                          (u8 *) pdesc, skb);
 
-                        pci_unmap_single(rtlpci->pdev,
-                                         *((dma_addr_t *) skb->cb),
-                                         rtlpci->rxbuffersize,
-                                         PCI_DMA_FROMDEVICE);
-
                         skb_put(skb, rtlpriv->cfg->ops->get_desc((u8 *) pdesc,
                                                          false,
                                                          HW_DESC_RXPKT_LEN));
@@ -690,6 +685,21 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
                         hdr = rtl_get_hdr(skb);
                         fc = rtl_get_fc(skb);
 
+                        /* try for new buffer - if allocation fails, drop
+                         * frame and reuse old buffer
+                         */
+                        new_skb = dev_alloc_skb(rtlpci->rxbuffersize);
+                        if (unlikely(!new_skb)) {
+                                RT_TRACE(rtlpriv, (COMP_INTR | COMP_RECV),
+                                         DBG_DMESG,
+                                         ("can't alloc skb for rx\n"));
+                                goto done;
+                        }
+                        pci_unmap_single(rtlpci->pdev,
+                                         *((dma_addr_t *) skb->cb),
+                                         rtlpci->rxbuffersize,
+                                         PCI_DMA_FROMDEVICE);
+
                         if (!stats.crc || !stats.hwerror) {
                                 memcpy(IEEE80211_SKB_RXCB(skb), &rx_status,
                                        sizeof(rx_status));
@@ -758,15 +768,7 @@ static void _rtl_pci_rx_interrupt(struct ieee80211_hw *hw)
                                 rtl_lps_leave(hw);
                         }
 
-                        new_skb = dev_alloc_skb(rtlpci->rxbuffersize);
-                        if (unlikely(!new_skb)) {
-                                RT_TRACE(rtlpriv, (COMP_INTR | COMP_RECV),
-                                         DBG_DMESG,
-                                         ("can't alloc skb for rx\n"));
-                                goto done;
-                        }
                         skb = new_skb;
-                        /*skb->dev = dev; */
 
                         rtlpci->rx_ring[rx_queue_idx].rx_buf[rtlpci->
                                                              rx_ring
@@ -1113,6 +1115,13 @@ static int _rtl_pci_init_rx_ring(struct ieee80211_hw *hw)
 
                 rtlpci->rx_ring[rx_queue_idx].idx = 0;
 
+                /* If amsdu_8k is disabled, set buffersize to 4096. This
+                 * change will reduce memory fragmentation.
+                 */
+                if (rtlpci->rxbuffersize > 4096 &&
+                    rtlpriv->rtlhal.disable_amsdu_8k)
+                        rtlpci->rxbuffersize = 4096;
+
                 for (i = 0; i < rtlpci->rxringcount; i++) {
                         struct sk_buff *skb =
                             dev_alloc_skb(rtlpci->rxbuffersize);
diff --git a/drivers/net/wireless/wl12xx/conf.h b/drivers/net/wireless/wl12xx/conf.h
index 1ab6c86aac40..c83fefb6662f 100644
--- a/drivers/net/wireless/wl12xx/conf.h
+++ b/drivers/net/wireless/wl12xx/conf.h
@@ -1157,6 +1157,9 @@ struct conf_sched_scan_settings {
         /* time to wait on the channel for passive scans (in TUs) */
         u32 dwell_time_passive;
 
+        /* time to wait on the channel for DFS scans (in TUs) */
+        u32 dwell_time_dfs;
+
         /* number of probe requests to send on each channel in active scans */
         u8 num_probe_reqs;
 
diff --git a/drivers/net/wireless/wl12xx/main.c b/drivers/net/wireless/wl12xx/main.c
index bc00e52f6445..e6497dc669df 100644
--- a/drivers/net/wireless/wl12xx/main.c
+++ b/drivers/net/wireless/wl12xx/main.c
@@ -311,6 +311,7 @@ static struct conf_drv_settings default_conf = {
                 .min_dwell_time_active = 8,
                 .max_dwell_time_active = 30,
                 .dwell_time_passive    = 100,
+                .dwell_time_dfs        = 150,
                 .num_probe_reqs        = 2,
                 .rssi_threshold        = -90,
                 .snr_threshold         = 0,
diff --git a/drivers/net/wireless/wl12xx/scan.c b/drivers/net/wireless/wl12xx/scan.c
index f37e5a391976..56f76abc754d 100644
--- a/drivers/net/wireless/wl12xx/scan.c
+++ b/drivers/net/wireless/wl12xx/scan.c
@@ -331,16 +331,22 @@ wl1271_scan_get_sched_scan_channels(struct wl1271 *wl,
         struct conf_sched_scan_settings *c = &wl->conf.sched_scan;
         int i, j;
         u32 flags;
+        bool force_passive = !req->n_ssids;
 
         for (i = 0, j = start;
              i < req->n_channels && j < MAX_CHANNELS_ALL_BANDS;
              i++) {
                 flags = req->channels[i]->flags;
 
-                if (!(flags & IEEE80211_CHAN_DISABLED) &&
-                    ((flags & IEEE80211_CHAN_PASSIVE_SCAN) == passive) &&
-                    ((flags & IEEE80211_CHAN_RADAR) == radar) &&
-                    (req->channels[i]->band == band)) {
+                if (force_passive)
+                        flags |= IEEE80211_CHAN_PASSIVE_SCAN;
+
+                if ((req->channels[i]->band == band) &&
+                    !(flags & IEEE80211_CHAN_DISABLED) &&
+                    (!!(flags & IEEE80211_CHAN_RADAR) == radar) &&
+                    /* if radar is set, we ignore the passive flag */
+                    (radar ||
+                     !!(flags & IEEE80211_CHAN_PASSIVE_SCAN) == passive)) {
                         wl1271_debug(DEBUG_SCAN, "band %d, center_freq %d ",
                                      req->channels[i]->band,
                                      req->channels[i]->center_freq);
@@ -350,7 +356,12 @@ wl1271_scan_get_sched_scan_channels(struct wl1271 *wl,
                         wl1271_debug(DEBUG_SCAN, "max_power %d",
                                      req->channels[i]->max_power);
 
-                        if (flags & IEEE80211_CHAN_PASSIVE_SCAN) {
+                        if (flags & IEEE80211_CHAN_RADAR) {
+                                channels[j].flags |= SCAN_CHANNEL_FLAGS_DFS;
+                                channels[j].passive_duration =
+                                        cpu_to_le16(c->dwell_time_dfs);
+                        }
+                        else if (flags & IEEE80211_CHAN_PASSIVE_SCAN) {
                                 channels[j].passive_duration =
                                         cpu_to_le16(c->dwell_time_passive);
                         } else {
@@ -359,7 +370,7 @@ wl1271_scan_get_sched_scan_channels(struct wl1271 *wl,
                                 channels[j].max_duration =
                                         cpu_to_le16(c->max_dwell_time_active);
                         }
-                        channels[j].tx_power_att = req->channels[j]->max_power;
+                        channels[j].tx_power_att = req->channels[i]->max_power;
                         channels[j].channel = req->channels[i]->hw_value;
 
                         j++;
@@ -386,7 +397,11 @@ wl1271_scan_sched_scan_channels(struct wl1271 *wl,
                 wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
                                                     IEEE80211_BAND_2GHZ,
                                                     false, false, idx);
-        idx += cfg->active[0];
+        /*
+         * 5GHz channels always start at position 14, not immediately
+         * after the last 2.4GHz channel
+         */
+        idx = 14;
 
         cfg->passive[1] =
                 wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
@@ -394,22 +409,23 @@ wl1271_scan_sched_scan_channels(struct wl1271 *wl,
                                                     false, true, idx);
         idx += cfg->passive[1];
 
-        cfg->active[1] =
+        cfg->dfs =
                 wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
                                                     IEEE80211_BAND_5GHZ,
-                                                    false, false, 14);
-        idx += cfg->active[1];
+                                                    true, true, idx);
+        idx += cfg->dfs;
 
-        cfg->dfs =
+        cfg->active[1] =
                 wl1271_scan_get_sched_scan_channels(wl, req, cfg->channels,
                                                     IEEE80211_BAND_5GHZ,
-                                                    true, false, idx);
-        idx += cfg->dfs;
+                                                    false, false, idx);
+        idx += cfg->active[1];
 
         wl1271_debug(DEBUG_SCAN, "    2.4GHz: active %d passive %d",
                      cfg->active[0], cfg->passive[0]);
         wl1271_debug(DEBUG_SCAN, "    5GHz: active %d passive %d",
                      cfg->active[1], cfg->passive[1]);
+        wl1271_debug(DEBUG_SCAN, "    DFS: %d", cfg->dfs);
 
         return idx;
 }
@@ -421,6 +437,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
         struct wl1271_cmd_sched_scan_config *cfg = NULL;
         struct conf_sched_scan_settings *c = &wl->conf.sched_scan;
         int i, total_channels, ret;
+        bool force_passive = !req->n_ssids;
 
         wl1271_debug(DEBUG_CMD, "cmd sched_scan scan config");
 
@@ -444,7 +461,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
         for (i = 0; i < SCAN_MAX_CYCLE_INTERVALS; i++)
                 cfg->intervals[i] = cpu_to_le32(req->interval);
 
-        if (req->ssids[0].ssid_len && req->ssids[0].ssid) {
+        if (!force_passive && req->ssids[0].ssid_len && req->ssids[0].ssid) {
                 cfg->filter_type = SCAN_SSID_FILTER_SPECIFIC;
                 cfg->ssid_len = req->ssids[0].ssid_len;
                 memcpy(cfg->ssid, req->ssids[0].ssid,
@@ -461,7 +478,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
                 goto out;
         }
 
-        if (cfg->active[0]) {
+        if (!force_passive && cfg->active[0]) {
                 ret = wl1271_cmd_build_probe_req(wl, req->ssids[0].ssid,
                                                  req->ssids[0].ssid_len,
                                                  ies->ie[IEEE80211_BAND_2GHZ],
@@ -473,7 +490,7 @@ int wl1271_scan_sched_scan_config(struct wl1271 *wl,
                 }
         }
 
-        if (cfg->active[1]) {
+        if (!force_passive && cfg->active[1]) {
                 ret = wl1271_cmd_build_probe_req(wl,  req->ssids[0].ssid,
                                                  req->ssids[0].ssid_len,
                                                  ies->ie[IEEE80211_BAND_5GHZ],
diff --git a/drivers/net/wireless/wl12xx/scan.h b/drivers/net/wireless/wl12xx/scan.h
index c83319579ca3..a0b6c5d67b07 100644
--- a/drivers/net/wireless/wl12xx/scan.h
+++ b/drivers/net/wireless/wl12xx/scan.h
@@ -137,6 +137,9 @@ enum {
         SCAN_BSS_TYPE_ANY,
 };
 
+#define SCAN_CHANNEL_FLAGS_DFS          BIT(0)
+#define SCAN_CHANNEL_FLAGS_DFS_ENABLED  BIT(1)
+
 struct conn_scan_ch_params {
         __le16 min_duration;
         __le16 max_duration;
diff --git a/drivers/net/wireless/zd1211rw/zd_usb.c b/drivers/net/wireless/zd1211rw/zd_usb.c
index 0e819943b9e4..631194d49828 100644
--- a/drivers/net/wireless/zd1211rw/zd_usb.c
+++ b/drivers/net/wireless/zd1211rw/zd_usb.c
@@ -1533,6 +1533,31 @@ static void __exit usb_exit(void)
 module_init(usb_init);
 module_exit(usb_exit);
 
+static int zd_ep_regs_out_msg(struct usb_device *udev, void *data, int len,
+                              int *actual_length, int timeout)
+{
+        /* In USB 2.0 mode EP_REGS_OUT endpoint is interrupt type. However in
+         * USB 1.1 mode endpoint is bulk. Select correct type URB by endpoint
+         * descriptor.
+         */
+        struct usb_host_endpoint *ep;
+        unsigned int pipe;
+
+        pipe = usb_sndintpipe(udev, EP_REGS_OUT);
+        ep = usb_pipe_endpoint(udev, pipe);
+        if (!ep)
+                return -EINVAL;
+
+        if (usb_endpoint_xfer_int(&ep->desc)) {
+                return usb_interrupt_msg(udev, pipe, data, len,
+                                         actual_length, timeout);
+        } else {
+                pipe = usb_sndbulkpipe(udev, EP_REGS_OUT);
+                return usb_bulk_msg(udev, pipe, data, len, actual_length,
+                                    timeout);
+        }
+}
+
 static int usb_int_regs_length(unsigned int count)
 {
         return sizeof(struct usb_int_regs) + count * sizeof(struct reg_data);
@@ -1648,15 +1673,14 @@ int zd_usb_ioread16v(struct zd_usb *usb, u16 *values,
 
         udev = zd_usb_to_usbdev(usb);
         prepare_read_regs_int(usb);
-        r = usb_interrupt_msg(udev, usb_sndintpipe(udev, EP_REGS_OUT),
-                              req, req_len, &actual_req_len, 50 /* ms */);
+        r = zd_ep_regs_out_msg(udev, req, req_len, &actual_req_len, 50 /*ms*/);
         if (r) {
                 dev_dbg_f(zd_usb_dev(usb),
-                        "error in usb_interrupt_msg(). Error number %d\n", r);
+                        "error in zd_ep_regs_out_msg(). Error number %d\n", r);
                 goto error;
         }
         if (req_len != actual_req_len) {
-                dev_dbg_f(zd_usb_dev(usb), "error in usb_interrupt_msg()\n"
+                dev_dbg_f(zd_usb_dev(usb), "error in zd_ep_regs_out_msg()\n"
                         " req_len %d != actual_req_len %d\n",
                         req_len, actual_req_len);
                 r = -EIO;
@@ -1818,9 +1842,17 @@ int zd_usb_iowrite16v_async(struct zd_usb *usb, const struct zd_ioreq16 *ioreqs,
                 rw->value = cpu_to_le16(ioreqs[i].value);
         }
 
-        usb_fill_int_urb(urb, udev, usb_sndintpipe(udev, EP_REGS_OUT),
-                         req, req_len, iowrite16v_urb_complete, usb,
-                         ep->desc.bInterval);
+        /* In USB 2.0 mode endpoint is interrupt type. However in USB 1.1 mode
+         * endpoint is bulk. Select correct type URB by endpoint descriptor.
+         */
+        if (usb_endpoint_xfer_int(&ep->desc))
+                usb_fill_int_urb(urb, udev, usb_sndintpipe(udev, EP_REGS_OUT),
+                                 req, req_len, iowrite16v_urb_complete, usb,
+                                 ep->desc.bInterval);
+        else
+                usb_fill_bulk_urb(urb, udev, usb_sndbulkpipe(udev, EP_REGS_OUT),
+                                  req, req_len, iowrite16v_urb_complete, usb);
+
         urb->transfer_flags |= URB_FREE_BUFFER;
 
         /* Submit previous URB */
@@ -1924,15 +1956,14 @@ int zd_usb_rfwrite(struct zd_usb *usb, u32 value, u8 bits)
         }
 
         udev = zd_usb_to_usbdev(usb);
-        r = usb_interrupt_msg(udev, usb_sndintpipe(udev, EP_REGS_OUT),
-                              req, req_len, &actual_req_len, 50 /* ms */);
+        r = zd_ep_regs_out_msg(udev, req, req_len, &actual_req_len, 50 /*ms*/);
         if (r) {
                 dev_dbg_f(zd_usb_dev(usb),
-                        "error in usb_interrupt_msg(). Error number %d\n", r);
+                        "error in zd_ep_regs_out_msg(). Error number %d\n", r);
                 goto out;
         }
         if (req_len != actual_req_len) {
-                dev_dbg_f(zd_usb_dev(usb), "error in usb_interrupt_msg()"
+                dev_dbg_f(zd_usb_dev(usb), "error in zd_ep_regs_out_msg()"
                         " req_len %d != actual_req_len %d\n",
                         req_len, actual_req_len);
                 r = -EIO;
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/scsi/scsi_scan.c b/drivers/scsi/scsi_scan.c
index 58584dc0724a..44e8ca398efa 100644
--- a/drivers/scsi/scsi_scan.c
+++ b/drivers/scsi/scsi_scan.c
@@ -297,7 +297,7 @@ static struct scsi_device *scsi_alloc_sdev(struct scsi_target *starget,
                 kfree(sdev);
                 goto out;
         }
-
+        blk_get_queue(sdev->request_queue);
         sdev->request_queue->queuedata = sdev;
         scsi_adjust_queue_depth(sdev, 0, sdev->host->cmd_per_lun);
 
diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c
index e63912510fb9..e0bd3f790fca 100644
--- a/drivers/scsi/scsi_sysfs.c
+++ b/drivers/scsi/scsi_sysfs.c
@@ -322,6 +322,7 @@ static void scsi_device_dev_release_usercontext(struct work_struct *work)
                 kfree(evt);
         }
 
+        blk_put_queue(sdev->request_queue);
         /* NULL queue means the device can't be used */
         sdev->request_queue = NULL;
 
diff --git a/drivers/tty/n_gsm.c b/drivers/tty/n_gsm.c
index a4c42a75a3bf..09e8c7d53af3 100644
--- a/drivers/tty/n_gsm.c
+++ b/drivers/tty/n_gsm.c
@@ -2128,8 +2128,8 @@ static void gsmld_detach_gsm(struct tty_struct *tty, struct gsm_mux *gsm)
         gsm->tty = NULL;
 }
 
-static unsigned int gsmld_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void gsmld_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                              char *fp, int count)
 {
         struct gsm_mux *gsm = tty->disc_data;
         const unsigned char *dp;
@@ -2162,8 +2162,6 @@ static unsigned int gsmld_receive_buf(struct tty_struct *tty,
         }
         /* FASYNC if needed ? */
         /* If clogged call tty_throttle(tty); */
-
-        return count;
 }
 
 /**
diff --git a/drivers/tty/n_hdlc.c b/drivers/tty/n_hdlc.c
index cac666314aef..cea56033b34c 100644
--- a/drivers/tty/n_hdlc.c
+++ b/drivers/tty/n_hdlc.c
@@ -188,8 +188,8 @@ static unsigned int n_hdlc_tty_poll(struct tty_struct *tty, struct file *filp,
                                     poll_table *wait);
 static int n_hdlc_tty_open(struct tty_struct *tty);
 static void n_hdlc_tty_close(struct tty_struct *tty);
-static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
-                const __u8 *cp, char *fp, int count);
+static void n_hdlc_tty_receive(struct tty_struct *tty, const __u8 *cp,
+                               char *fp, int count);
 static void n_hdlc_tty_wakeup(struct tty_struct *tty);
 
 #define bset(p,b)       ((p)[(b) >> 5] |= (1 << ((b) & 0x1f)))
@@ -509,8 +509,8 @@ static void n_hdlc_tty_wakeup(struct tty_struct *tty)
  * Called by tty low level driver when receive data is available. Data is
  * interpreted as one HDLC frame.
  */
-static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
-                const __u8 *data, char *flags, int count)
+static void n_hdlc_tty_receive(struct tty_struct *tty, const __u8 *data,
+                               char *flags, int count)
 {
         register struct n_hdlc *n_hdlc = tty2n_hdlc (tty);
         register struct n_hdlc_buf *buf;
@@ -521,20 +521,20 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
                 
         /* This can happen if stuff comes in on the backup tty */
         if (!n_hdlc || tty != n_hdlc->tty)
-                return -ENODEV;
+                return;
                 
         /* verify line is using HDLC discipline */
         if (n_hdlc->magic != HDLC_MAGIC) {
                 printk("%s(%d) line not using HDLC discipline\n",
                         __FILE__,__LINE__);
-                return -EINVAL;
+                return;
         }
         
         if ( count>maxframe ) {
                 if (debuglevel >= DEBUG_LEVEL_INFO)     
                         printk("%s(%d) rx count>maxframesize, data discarded\n",
                                __FILE__,__LINE__);
-                return -EINVAL;
+                return;
         }
 
         /* get a free HDLC buffer */    
@@ -550,7 +550,7 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
                 if (debuglevel >= DEBUG_LEVEL_INFO)     
                         printk("%s(%d) no more rx buffers, data discarded\n",
                                __FILE__,__LINE__);
-                return -EINVAL;
+                return;
         }
                 
         /* copy received data to HDLC buffer */
@@ -565,8 +565,6 @@ static unsigned int n_hdlc_tty_receive(struct tty_struct *tty,
         if (n_hdlc->tty->fasync != NULL)
                 kill_fasync (&n_hdlc->tty->fasync, SIGIO, POLL_IN);
 
-        return count;
-
 }       /* end of n_hdlc_tty_receive() */
 
 /**
diff --git a/drivers/tty/n_r3964.c b/drivers/tty/n_r3964.c
index a4bc39c21a43..5c6c31459a2f 100644
--- a/drivers/tty/n_r3964.c
+++ b/drivers/tty/n_r3964.c
@@ -139,8 +139,8 @@ static int r3964_ioctl(struct tty_struct *tty, struct file *file,
 static void r3964_set_termios(struct tty_struct *tty, struct ktermios *old);
 static unsigned int r3964_poll(struct tty_struct *tty, struct file *file,
                 struct poll_table_struct *wait);
-static unsigned int r3964_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count);
+static void r3964_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                char *fp, int count);
 
 static struct tty_ldisc_ops tty_ldisc_N_R3964 = {
         .owner = THIS_MODULE,
@@ -1239,8 +1239,8 @@ static unsigned int r3964_poll(struct tty_struct *tty, struct file *file,
         return result;
 }
 
-static unsigned int r3964_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void r3964_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                        char *fp, int count)
 {
         struct r3964_info *pInfo = tty->disc_data;
         const unsigned char *p;
@@ -1257,8 +1257,6 @@ static unsigned int r3964_receive_buf(struct tty_struct *tty,
                 }
 
         }
-
-        return count;
 }
 
 MODULE_LICENSE("GPL");
diff --git a/drivers/tty/n_tty.c b/drivers/tty/n_tty.c
index 95d0a9c2dd13..0ad32888091c 100644
--- a/drivers/tty/n_tty.c
+++ b/drivers/tty/n_tty.c
@@ -81,6 +81,38 @@ static inline int tty_put_user(struct tty_struct *tty, unsigned char x,
         return put_user(x, ptr);
 }
 
+/**
+ *      n_tty_set__room -       receive space
+ *      @tty: terminal
+ *
+ *      Called by the driver to find out how much data it is
+ *      permitted to feed to the line discipline without any being lost
+ *      and thus to manage flow control. Not serialized. Answers for the
+ *      "instant".
+ */
+
+static void n_tty_set_room(struct tty_struct *tty)
+{
+        /* tty->read_cnt is not read locked ? */
+        int     left = N_TTY_BUF_SIZE - tty->read_cnt - 1;
+        int old_left;
+
+        /*
+         * If we are doing input canonicalization, and there are no
+         * pending newlines, let characters through without limit, so
+         * that erase characters will be handled.  Other excess
+         * characters will be beeped.
+         */
+        if (left <= 0)
+                left = tty->icanon && !tty->canon_data;
+        old_left = tty->receive_room;
+        tty->receive_room = left;
+
+        /* Did this open up the receive buffer? We may need to flip */
+        if (left && !old_left)
+                schedule_work(&tty->buf.work);
+}
+
 static void put_tty_queue_nolock(unsigned char c, struct tty_struct *tty)
 {
         if (tty->read_cnt < N_TTY_BUF_SIZE) {
@@ -152,6 +184,7 @@ static void reset_buffer_flags(struct tty_struct *tty)
 
         tty->canon_head = tty->canon_data = tty->erasing = 0;
         memset(&tty->read_flags, 0, sizeof tty->read_flags);
+        n_tty_set_room(tty);
         check_unthrottle(tty);
 }
 
@@ -1327,19 +1360,17 @@ static void n_tty_write_wakeup(struct tty_struct *tty)
  *      calls one at a time and in order (or using flush_to_ldisc)
  */
 
-static unsigned int n_tty_receive_buf(struct tty_struct *tty,
-                const unsigned char *cp, char *fp, int count)
+static void n_tty_receive_buf(struct tty_struct *tty, const unsigned char *cp,
+                              char *fp, int count)
 {
         const unsigned char *p;
         char *f, flags = TTY_NORMAL;
         int     i;
         char    buf[64];
         unsigned long cpuflags;
-        int left;
-        int ret = 0;
 
         if (!tty->read_buf)
-                return 0;
+                return;
 
         if (tty->real_raw) {
                 spin_lock_irqsave(&tty->read_lock, cpuflags);
@@ -1349,7 +1380,6 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
                 memcpy(tty->read_buf + tty->read_head, cp, i);
                 tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1);
                 tty->read_cnt += i;
-                ret += i;
                 cp += i;
                 count -= i;
 
@@ -1359,10 +1389,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
                 memcpy(tty->read_buf + tty->read_head, cp, i);
                 tty->read_head = (tty->read_head + i) & (N_TTY_BUF_SIZE-1);
                 tty->read_cnt += i;
-                ret += i;
                 spin_unlock_irqrestore(&tty->read_lock, cpuflags);
         } else {
-                ret = count;
                 for (i = count, p = cp, f = fp; i; i--, p++) {
                         if (f)
                                 flags = *f++;
@@ -1390,6 +1418,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
                         tty->ops->flush_chars(tty);
         }
 
+        n_tty_set_room(tty);
+
         if ((!tty->icanon && (tty->read_cnt >= tty->minimum_to_wake)) ||
                 L_EXTPROC(tty)) {
                 kill_fasync(&tty->fasync, SIGIO, POLL_IN);
@@ -1402,12 +1432,8 @@ static unsigned int n_tty_receive_buf(struct tty_struct *tty,
          * mode.  We don't want to throttle the driver if we're in
          * canonical mode and don't have a newline yet!
          */
-        left = N_TTY_BUF_SIZE - tty->read_cnt - 1;
-
-        if (left < TTY_THRESHOLD_THROTTLE)
+        if (tty->receive_room < TTY_THRESHOLD_THROTTLE)
                 tty_throttle(tty);
-
-        return ret;
 }
 
 int is_ignored(int sig)
@@ -1451,6 +1477,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
         if (test_bit(TTY_HW_COOK_IN, &tty->flags)) {
                 tty->raw = 1;
                 tty->real_raw = 1;
+                n_tty_set_room(tty);
                 return;
         }
         if (I_ISTRIP(tty) || I_IUCLC(tty) || I_IGNCR(tty) ||
@@ -1503,6 +1530,7 @@ static void n_tty_set_termios(struct tty_struct *tty, struct ktermios *old)
                 else
                         tty->real_raw = 0;
         }
+        n_tty_set_room(tty);
         /* The termios change make the tty ready for I/O */
         wake_up_interruptible(&tty->write_wait);
         wake_up_interruptible(&tty->read_wait);
@@ -1784,6 +1812,8 @@ do_it_again:
                                 retval = -ERESTARTSYS;
                                 break;
                         }
+                        /* FIXME: does n_tty_set_room need locking ? */
+                        n_tty_set_room(tty);
                         timeout = schedule_timeout(timeout);
                         continue;
                 }
@@ -1855,8 +1885,10 @@ do_it_again:
                  * longer than TTY_THRESHOLD_UNTHROTTLE in canonical mode,
                  * we won't get any more characters.
                  */
-                if (n_tty_chars_in_buffer(tty) <= TTY_THRESHOLD_UNTHROTTLE)
+                if (n_tty_chars_in_buffer(tty) <= TTY_THRESHOLD_UNTHROTTLE) {
+                        n_tty_set_room(tty);
                         check_unthrottle(tty);
+                }
 
                 if (b - buf >= minimum)
                         break;
@@ -1878,6 +1910,7 @@ do_it_again:
         } else if (test_and_clear_bit(TTY_PUSH, &tty->flags))
                  goto do_it_again;
 
+        n_tty_set_room(tty);
         return retval;
 }
 
diff --git a/drivers/tty/tty_buffer.c b/drivers/tty/tty_buffer.c
index 46de2e075dac..f1a7918d71aa 100644
--- a/drivers/tty/tty_buffer.c
+++ b/drivers/tty/tty_buffer.c
@@ -416,7 +416,6 @@ static void flush_to_ldisc(struct work_struct *work)
                 struct tty_buffer *head, *tail = tty->buf.tail;
                 int seen_tail = 0;
                 while ((head = tty->buf.head) != NULL) {
-                        int copied;
                         int count;
                         char *char_buf;
                         unsigned char *flag_buf;
@@ -443,19 +442,17 @@ 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)
+                                break;
+                        if (count > tty->receive_room)
+                                count = tty->receive_room;
                         char_buf = head->char_buf_ptr + head->read;
                         flag_buf = head->flag_buf_ptr + head->read;
+                        head->read += count;
                         spin_unlock_irqrestore(&tty->buf.lock, flags);
-                        copied = disc->ops->receive_buf(tty, char_buf,
+                        disc->ops->receive_buf(tty, char_buf,
                                                         flag_buf, count);
                         spin_lock_irqsave(&tty->buf.lock, flags);
-
-                        head->read += copied;
-
-                        if (copied == 0 || seen_tail) {
-                                schedule_work(&tty->buf.work);
-                                break;
-                        }
                 }
                 clear_bit(TTY_FLUSHING, &tty->flags);
         }
diff --git a/drivers/tty/vt/selection.c b/drivers/tty/vt/selection.c
index 67b1d0d7c8ac..fb864e7fcd13 100644
--- a/drivers/tty/vt/selection.c
+++ b/drivers/tty/vt/selection.c
@@ -332,7 +332,8 @@ int paste_selection(struct tty_struct *tty)
                         continue;
                 }
                 count = sel_buffer_lth - pasted;
-                count = tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
+                count = min(count, tty->receive_room);
+                tty->ldisc->ops->receive_buf(tty, sel_buffer + pasted,
                                                                 NULL, count);
                 pasted += count;
         }
diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c
index 1b125c224dcf..2278dad886e2 100644
--- a/drivers/usb/core/inode.c
+++ b/drivers/usb/core/inode.c
@@ -389,7 +389,6 @@ static int usbfs_rmdir(struct inode *dir, struct dentry *dentry)
         mutex_unlock(&inode->i_mutex);
         if (!error)
                 d_delete(dentry);
-        dput(dentry);
         return error;
 }
 
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/block_dev.c b/fs/block_dev.c
index 1f2b19978333..1a2421f908f0 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -1272,8 +1272,8 @@ int blkdev_get(struct block_device *bdev, fmode_t mode, void *holder)
                  * individual writeable reference is too fragile given the
                  * way @mode is used in blkdev_get/put().
                  */
-                if ((disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE) &&
-                    !res && (mode & FMODE_WRITE) && !bdev->bd_write_holder) {
+                if (!res && (mode & FMODE_WRITE) && !bdev->bd_write_holder &&
+                    (disk->flags & GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE)) {
                         bdev->bd_write_holder = true;
                         disk_block_events(disk);
                 }
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 93b1aa932014..52d7eca8c7bf 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -121,9 +121,6 @@ struct btrfs_inode {
          */
         u64 index_cnt;
 
-        /* the start of block group preferred for allocations. */
-        u64 block_group;
-
         /* the fsync log has some corner cases that mean we have to check
          * directories to see if any unlinks have been done before
          * the directory was logged.  See tree-log.c for all the
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index b0e18d986e0a..d84089349c82 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -43,8 +43,6 @@ struct btrfs_path *btrfs_alloc_path(void)
 {
         struct btrfs_path *path;
         path = kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
-        if (path)
-                path->reada = 1;
         return path;
 }
 
@@ -1224,6 +1222,7 @@ static void reada_for_search(struct btrfs_root *root,
         u64 search;
         u64 target;
         u64 nread = 0;
+        u64 gen;
         int direction = path->reada;
         struct extent_buffer *eb;
         u32 nr;
@@ -1251,6 +1250,15 @@ static void reada_for_search(struct btrfs_root *root,
         nritems = btrfs_header_nritems(node);
         nr = slot;
         while (1) {
+                if (!node->map_token) {
+                        unsigned long offset = btrfs_node_key_ptr_offset(nr);
+                        map_private_extent_buffer(node, offset,
+                                                  sizeof(struct btrfs_key_ptr),
+                                                  &node->map_token,
+                                                  &node->kaddr,
+                                                  &node->map_start,
+                                                  &node->map_len, KM_USER1);
+                }
                 if (direction < 0) {
                         if (nr == 0)
                                 break;
@@ -1268,14 +1276,23 @@ static void reada_for_search(struct btrfs_root *root,
                 search = btrfs_node_blockptr(node, nr);
                 if ((search <= target && target - search <= 65536) ||
                     (search > target && search - target <= 65536)) {
-                        readahead_tree_block(root, search, blocksize,
-                                     btrfs_node_ptr_generation(node, nr));
+                        gen = btrfs_node_ptr_generation(node, nr);
+                        if (node->map_token) {
+                                unmap_extent_buffer(node, node->map_token,
+                                                    KM_USER1);
+                                node->map_token = NULL;
+                        }
+                        readahead_tree_block(root, search, blocksize, gen);
                         nread += blocksize;
                 }
                 nscan++;
                 if ((nread > 65536 || nscan > 32))
                         break;
         }
+        if (node->map_token) {
+                unmap_extent_buffer(node, node->map_token, KM_USER1);
+                node->map_token = NULL;
+        }
 }
 
 /*
@@ -1648,9 +1665,6 @@ again:
                 }
 cow_done:
                 BUG_ON(!cow && ins_len);
-                if (level != btrfs_header_level(b))
-                        WARN_ON(1);
-                level = btrfs_header_level(b);
 
                 p->nodes[level] = b;
                 if (!p->skip_locking)
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 6c093fa98f61..378b5b4443f3 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -930,7 +930,6 @@ struct btrfs_fs_info {
          * is required instead of the faster short fsync log commits
          */
         u64 last_trans_log_full_commit;
-        u64 open_ioctl_trans;
         unsigned long mount_opt:20;
         unsigned long compress_type:4;
         u64 max_inline;
@@ -947,7 +946,6 @@ struct btrfs_fs_info {
         struct super_block *sb;
         struct inode *btree_inode;
         struct backing_dev_info bdi;
-        struct mutex trans_mutex;
         struct mutex tree_log_mutex;
         struct mutex transaction_kthread_mutex;
         struct mutex cleaner_mutex;
@@ -968,6 +966,7 @@ struct btrfs_fs_info {
         struct rw_semaphore subvol_sem;
         struct srcu_struct subvol_srcu;
 
+        spinlock_t trans_lock;
         struct list_head trans_list;
         struct list_head hashers;
         struct list_head dead_roots;
@@ -980,6 +979,7 @@ struct btrfs_fs_info {
         atomic_t async_submit_draining;
         atomic_t nr_async_bios;
         atomic_t async_delalloc_pages;
+        atomic_t open_ioctl_trans;
 
         /*
          * this is used by the balancing code to wait for all the pending
@@ -1044,6 +1044,7 @@ struct btrfs_fs_info {
         int closing;
         int log_root_recovering;
         int enospc_unlink;
+        int trans_no_join;
 
         u64 total_pinned;
 
@@ -1065,7 +1066,6 @@ struct btrfs_fs_info {
         struct reloc_control *reloc_ctl;
 
         spinlock_t delalloc_lock;
-        spinlock_t new_trans_lock;
         u64 delalloc_bytes;
 
         /* data_alloc_cluster is only used in ssd mode */
@@ -1340,6 +1340,7 @@ struct btrfs_ioctl_defrag_range_args {
 #define BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED (1 << 14)
 #define BTRFS_MOUNT_ENOSPC_DEBUG         (1 << 15)
 #define BTRFS_MOUNT_AUTO_DEFRAG         (1 << 16)
+#define BTRFS_MOUNT_INODE_MAP_CACHE     (1 << 17)
 
 #define btrfs_clear_opt(o, opt)         ((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)           ((o) |= BTRFS_MOUNT_##opt)
@@ -2238,6 +2239,9 @@ int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
 void btrfs_block_rsv_release(struct btrfs_root *root,
                              struct btrfs_block_rsv *block_rsv,
                              u64 num_bytes);
+int btrfs_truncate_reserve_metadata(struct btrfs_trans_handle *trans,
+                                    struct btrfs_root *root,
+                                    struct btrfs_block_rsv *rsv);
 int btrfs_set_block_group_ro(struct btrfs_root *root,
                              struct btrfs_block_group_cache *cache);
 int btrfs_set_block_group_rw(struct btrfs_root *root,
@@ -2350,6 +2354,15 @@ int btrfs_drop_subtree(struct btrfs_trans_handle *trans,
                         struct btrfs_root *root,
                         struct extent_buffer *node,
                         struct extent_buffer *parent);
+static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
+{
+        /*
+         * Get synced with close_ctree()
+         */
+        smp_mb();
+        return fs_info->closing;
+}
+
 /* root-item.c */
 int btrfs_find_root_ref(struct btrfs_root *tree_root,
                         struct btrfs_path *path,
@@ -2512,8 +2525,7 @@ int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
 int btrfs_writepages(struct address_space *mapping,
                      struct writeback_control *wbc);
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
-                             struct btrfs_root *new_root,
-                             u64 new_dirid, u64 alloc_hint);
+                             struct btrfs_root *new_root, u64 new_dirid);
 int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
                          size_t size, struct bio *bio, unsigned long bio_flags);
 
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 01e29503a54b..6462c29d2d37 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -678,6 +678,7 @@ static int btrfs_batch_insert_items(struct btrfs_trans_handle *trans,
         INIT_LIST_HEAD(&head);
 
         next = item;
+        nitems = 0;
 
         /*
          * count the number of the continuous items that we can insert in batch
@@ -1129,7 +1130,7 @@ static void btrfs_async_run_delayed_node_done(struct btrfs_work *work)
         delayed_node = async_node->delayed_node;
         root = delayed_node->root;
 
-        trans = btrfs_join_transaction(root, 0);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans))
                 goto free_path;
 
@@ -1572,8 +1573,7 @@ static void fill_stack_inode_item(struct btrfs_trans_handle *trans,
         btrfs_set_stack_inode_transid(inode_item, trans->transid);
         btrfs_set_stack_inode_rdev(inode_item, inode->i_rdev);
         btrfs_set_stack_inode_flags(inode_item, BTRFS_I(inode)->flags);
-        btrfs_set_stack_inode_block_group(inode_item,
-                                          BTRFS_I(inode)->block_group);
+        btrfs_set_stack_inode_block_group(inode_item, 0);
 
         btrfs_set_stack_timespec_sec(btrfs_inode_atime(inode_item),
                                      inode->i_atime.tv_sec);
@@ -1595,7 +1595,7 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
                                struct btrfs_root *root, struct inode *inode)
 {
         struct btrfs_delayed_node *delayed_node;
-        int ret;
+        int ret = 0;
 
         delayed_node = btrfs_get_or_create_delayed_node(inode);
         if (IS_ERR(delayed_node))
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 98b6a71decba..a203d363184d 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -1505,24 +1505,24 @@ static int transaction_kthread(void *arg)
                 vfs_check_frozen(root->fs_info->sb, SB_FREEZE_WRITE);
                 mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
-                spin_lock(&root->fs_info->new_trans_lock);
+                spin_lock(&root->fs_info->trans_lock);
                 cur = root->fs_info->running_transaction;
                 if (!cur) {
-                        spin_unlock(&root->fs_info->new_trans_lock);
+                        spin_unlock(&root->fs_info->trans_lock);
                         goto sleep;
                 }
 
                 now = get_seconds();
                 if (!cur->blocked &&
                     (now < cur->start_time || now - cur->start_time < 30)) {
-                        spin_unlock(&root->fs_info->new_trans_lock);
+                        spin_unlock(&root->fs_info->trans_lock);
                         delay = HZ * 5;
                         goto sleep;
                 }
                 transid = cur->transid;
-                spin_unlock(&root->fs_info->new_trans_lock);
+                spin_unlock(&root->fs_info->trans_lock);
 
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
                 BUG_ON(IS_ERR(trans));
                 if (transid == trans->transid) {
                         ret = btrfs_commit_transaction(trans, root);
@@ -1613,7 +1613,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         INIT_LIST_HEAD(&fs_info->ordered_operations);
         INIT_LIST_HEAD(&fs_info->caching_block_groups);
         spin_lock_init(&fs_info->delalloc_lock);
-        spin_lock_init(&fs_info->new_trans_lock);
+        spin_lock_init(&fs_info->trans_lock);
         spin_lock_init(&fs_info->ref_cache_lock);
         spin_lock_init(&fs_info->fs_roots_radix_lock);
         spin_lock_init(&fs_info->delayed_iput_lock);
@@ -1645,6 +1645,7 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         fs_info->max_inline = 8192 * 1024;
         fs_info->metadata_ratio = 0;
         fs_info->defrag_inodes = RB_ROOT;
+        fs_info->trans_no_join = 0;
 
         fs_info->thread_pool_size = min_t(unsigned long,
                                           num_online_cpus() + 2, 8);
@@ -1709,7 +1710,6 @@ struct btrfs_root *open_ctree(struct super_block *sb,
         fs_info->do_barriers = 1;
 
 
-        mutex_init(&fs_info->trans_mutex);
         mutex_init(&fs_info->ordered_operations_mutex);
         mutex_init(&fs_info->tree_log_mutex);
         mutex_init(&fs_info->chunk_mutex);
@@ -2479,13 +2479,13 @@ int btrfs_commit_super(struct btrfs_root *root)
         down_write(&root->fs_info->cleanup_work_sem);
         up_write(&root->fs_info->cleanup_work_sem);
 
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
         ret = btrfs_commit_transaction(trans, root);
         BUG_ON(ret);
         /* run commit again to drop the original snapshot */
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
         btrfs_commit_transaction(trans, root);
@@ -3024,10 +3024,13 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
 
         WARN_ON(1);
 
-        mutex_lock(&root->fs_info->trans_mutex);
         mutex_lock(&root->fs_info->transaction_kthread_mutex);
 
+        spin_lock(&root->fs_info->trans_lock);
         list_splice_init(&root->fs_info->trans_list, &list);
+        root->fs_info->trans_no_join = 1;
+        spin_unlock(&root->fs_info->trans_lock);
+
         while (!list_empty(&list)) {
                 t = list_entry(list.next, struct btrfs_transaction, list);
                 if (!t)
@@ -3052,23 +3055,18 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
                 t->blocked = 0;
                 if (waitqueue_active(&root->fs_info->transaction_wait))
                         wake_up(&root->fs_info->transaction_wait);
-                mutex_unlock(&root->fs_info->trans_mutex);
 
-                mutex_lock(&root->fs_info->trans_mutex);
                 t->commit_done = 1;
                 if (waitqueue_active(&t->commit_wait))
                         wake_up(&t->commit_wait);
-                mutex_unlock(&root->fs_info->trans_mutex);
-
-                mutex_lock(&root->fs_info->trans_mutex);
 
                 btrfs_destroy_pending_snapshots(t);
 
                 btrfs_destroy_delalloc_inodes(root);
 
-                spin_lock(&root->fs_info->new_trans_lock);
+                spin_lock(&root->fs_info->trans_lock);
                 root->fs_info->running_transaction = NULL;
-                spin_unlock(&root->fs_info->new_trans_lock);
+                spin_unlock(&root->fs_info->trans_lock);
 
                 btrfs_destroy_marked_extents(root, &t->dirty_pages,
                                              EXTENT_DIRTY);
@@ -3082,8 +3080,10 @@ static int btrfs_cleanup_transaction(struct btrfs_root *root)
                 kmem_cache_free(btrfs_transaction_cachep, t);
         }
 
+        spin_lock(&root->fs_info->trans_lock);
+        root->fs_info->trans_no_join = 0;
+        spin_unlock(&root->fs_info->trans_lock);
         mutex_unlock(&root->fs_info->transaction_kthread_mutex);
-        mutex_unlock(&root->fs_info->trans_mutex);
 
         return 0;
 }
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index 169bd62ce776..5b9b6b6df242 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -348,7 +348,7 @@ static int caching_kthread(void *data)
          */
         path->skip_locking = 1;
         path->search_commit_root = 1;
-        path->reada = 2;
+        path->reada = 1;
 
         key.objectid = last;
         key.offset = 0;
@@ -366,8 +366,7 @@ again:
         nritems = btrfs_header_nritems(leaf);
 
         while (1) {
-                smp_mb();
-                if (fs_info->closing > 1) {
+                if (btrfs_fs_closing(fs_info) > 1) {
                         last = (u64)-1;
                         break;
                 }
@@ -379,15 +378,18 @@ again:
                         if (ret)
                                 break;
 
-                        caching_ctl->progress = last;
-                        btrfs_release_path(path);
-                        up_read(&fs_info->extent_commit_sem);
-                        mutex_unlock(&caching_ctl->mutex);
-                        if (btrfs_transaction_in_commit(fs_info))
-                                schedule_timeout(1);
-                        else
+                        if (need_resched() ||
+                            btrfs_next_leaf(extent_root, path)) {
+                                caching_ctl->progress = last;
+                                btrfs_release_path(path);
+                                up_read(&fs_info->extent_commit_sem);
+                                mutex_unlock(&caching_ctl->mutex);
                                 cond_resched();
-                        goto again;
+                                goto again;
+                        }
+                        leaf = path->nodes[0];
+                        nritems = btrfs_header_nritems(leaf);
+                        continue;
                 }
 
                 if (key.objectid < block_group->key.objectid) {
@@ -3065,7 +3067,7 @@ again:
                         spin_unlock(&data_sinfo->lock);
 alloc:
                         alloc_target = btrfs_get_alloc_profile(root, 1);
-                        trans = btrfs_join_transaction(root, 1);
+                        trans = btrfs_join_transaction(root);
                         if (IS_ERR(trans))
                                 return PTR_ERR(trans);
 
@@ -3091,9 +3093,10 @@ alloc:
 
                 /* commit the current transaction and try again */
 commit_trans:
-                if (!committed && !root->fs_info->open_ioctl_trans) {
+                if (!committed &&
+                    !atomic_read(&root->fs_info->open_ioctl_trans)) {
                         committed = 1;
-                        trans = btrfs_join_transaction(root, 1);
+                        trans = btrfs_join_transaction(root);
                         if (IS_ERR(trans))
                                 return PTR_ERR(trans);
                         ret = btrfs_commit_transaction(trans, root);
@@ -3472,7 +3475,7 @@ again:
                 goto out;
 
         ret = -ENOSPC;
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans))
                 goto out;
         ret = btrfs_commit_transaction(trans, root);
@@ -3699,7 +3702,7 @@ int btrfs_block_rsv_check(struct btrfs_trans_handle *trans,
                 if (trans)
                         return -EAGAIN;
 
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
                 BUG_ON(IS_ERR(trans));
                 ret = btrfs_commit_transaction(trans, root);
                 return 0;
@@ -3837,6 +3840,37 @@ static void release_global_block_rsv(struct btrfs_fs_info *fs_info)
         WARN_ON(fs_info->chunk_block_rsv.reserved > 0);
 }
 
+int btrfs_truncate_reserve_metadata(struct btrfs_trans_handle *trans,
+                                    struct btrfs_root *root,
+                                    struct btrfs_block_rsv *rsv)
+{
+        struct btrfs_block_rsv *trans_rsv = &root->fs_info->trans_block_rsv;
+        u64 num_bytes;
+        int ret;
+
+        /*
+         * Truncate should be freeing data, but give us 2 items just in case it
+         * needs to use some space.  We may want to be smarter about this in the
+         * future.
+         */
+        num_bytes = btrfs_calc_trans_metadata_size(root, 2);
+
+        /* We already have enough bytes, just return */
+        if (rsv->reserved >= num_bytes)
+                return 0;
+
+        num_bytes -= rsv->reserved;
+
+        /*
+         * You should have reserved enough space before hand to do this, so this
+         * should not fail.
+         */
+        ret = block_rsv_migrate_bytes(trans_rsv, rsv, num_bytes);
+        BUG_ON(ret);
+
+        return 0;
+}
+
 int btrfs_trans_reserve_metadata(struct btrfs_trans_handle *trans,
                                  struct btrfs_root *root,
                                  int num_items)
@@ -3877,23 +3911,18 @@ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
         struct btrfs_block_rsv *dst_rsv = root->orphan_block_rsv;
 
         /*
-         * one for deleting orphan item, one for updating inode and
-         * two for calling btrfs_truncate_inode_items.
-         *
-         * btrfs_truncate_inode_items is a delete operation, it frees
-         * more space than it uses in most cases. So two units of
-         * metadata space should be enough for calling it many times.
-         * If all of the metadata space is used, we can commit
-         * transaction and use space it freed.
+         * We need to hold space in order to delete our orphan item once we've
+         * added it, so this takes the reservation so we can release it later
+         * when we are truly done with the orphan item.
          */
-        u64 num_bytes = btrfs_calc_trans_metadata_size(root, 4);
+        u64 num_bytes = btrfs_calc_trans_metadata_size(root, 1);
         return block_rsv_migrate_bytes(src_rsv, dst_rsv, num_bytes);
 }
 
 void btrfs_orphan_release_metadata(struct inode *inode)
 {
         struct btrfs_root *root = BTRFS_I(inode)->root;
-        u64 num_bytes = btrfs_calc_trans_metadata_size(root, 4);
+        u64 num_bytes = btrfs_calc_trans_metadata_size(root, 1);
         btrfs_block_rsv_release(root, root->orphan_block_rsv, num_bytes);
 }
 
@@ -4987,6 +5016,15 @@ have_block_group:
                 if (unlikely(block_group->ro))
                         goto loop;
 
+                spin_lock(&block_group->free_space_ctl->tree_lock);
+                if (cached &&
+                    block_group->free_space_ctl->free_space <
+                    num_bytes + empty_size) {
+                        spin_unlock(&block_group->free_space_ctl->tree_lock);
+                        goto loop;
+                }
+                spin_unlock(&block_group->free_space_ctl->tree_lock);
+
                 /*
                  * Ok we want to try and use the cluster allocator, so lets look
                  * there, unless we are on LOOP_NO_EMPTY_SIZE, since we will
@@ -5150,6 +5188,7 @@ checks:
                         btrfs_add_free_space(block_group, offset,
                                              search_start - offset);
                 BUG_ON(offset > search_start);
+                btrfs_put_block_group(block_group);
                 break;
 loop:
                 failed_cluster_refill = false;
@@ -5242,14 +5281,7 @@ loop:
                 ret = -ENOSPC;
         } else if (!ins->objectid) {
                 ret = -ENOSPC;
-        }
-
-        /* we found what we needed */
-        if (ins->objectid) {
-                if (!(data & BTRFS_BLOCK_GROUP_DATA))
-                        trans->block_group = block_group->key.objectid;
-
-                btrfs_put_block_group(block_group);
+        } else if (ins->objectid) {
                 ret = 0;
         }
 
@@ -6526,7 +6558,7 @@ int btrfs_set_block_group_ro(struct btrfs_root *root,
 
         BUG_ON(cache->ro);
 
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         BUG_ON(IS_ERR(trans));
 
         alloc_flags = update_block_group_flags(root, cache->flags);
@@ -6882,6 +6914,7 @@ int btrfs_read_block_groups(struct btrfs_root *root)
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+        path->reada = 1;
 
         cache_gen = btrfs_super_cache_generation(&root->fs_info->super_copy);
         if (cache_gen != 0 &&
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index c5d9fbb92bc3..7055d11c1efd 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -1476,7 +1476,7 @@ u64 count_range_bits(struct extent_io_tree *tree,
                         if (total_bytes >= max_bytes)
                                 break;
                         if (!found) {
-                                *start = state->start;
+                                *start = max(cur_start, state->start);
                                 found = 1;
                         }
                         last = state->end;
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index c6a22d783c35..fa4ef18b66b1 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -129,7 +129,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
         if (!btrfs_test_opt(root, AUTO_DEFRAG))
                 return 0;
 
-        if (root->fs_info->closing)
+        if (btrfs_fs_closing(root->fs_info))
                 return 0;
 
         if (BTRFS_I(inode)->in_defrag)
@@ -144,7 +144,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
         if (!defrag)
                 return -ENOMEM;
 
-        defrag->ino = inode->i_ino;
+        defrag->ino = btrfs_ino(inode);
         defrag->transid = transid;
         defrag->root = root->root_key.objectid;
 
@@ -229,7 +229,7 @@ int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info)
                 first_ino = defrag->ino + 1;
                 rb_erase(&defrag->rb_node, &fs_info->defrag_inodes);
 
-                if (fs_info->closing)
+                if (btrfs_fs_closing(fs_info))
                         goto next_free;
 
                 spin_unlock(&fs_info->defrag_inodes_lock);
@@ -1480,14 +1480,12 @@ int btrfs_sync_file(struct file *file, int datasync)
          * the current transaction, we can bail out now without any
          * syncing
          */
-        mutex_lock(&root->fs_info->trans_mutex);
+        smp_mb();
         if (BTRFS_I(inode)->last_trans <=
             root->fs_info->last_trans_committed) {
                 BTRFS_I(inode)->last_trans = 0;
-                mutex_unlock(&root->fs_info->trans_mutex);
                 goto out;
         }
-        mutex_unlock(&root->fs_info->trans_mutex);
 
         /*
          * ok we haven't committed the transaction yet, lets do a commit
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 70d45795d758..ad144736a5fd 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -98,7 +98,7 @@ struct inode *lookup_free_space_inode(struct btrfs_root *root,
                 return inode;
 
         spin_lock(&block_group->lock);
-        if (!root->fs_info->closing) {
+        if (!btrfs_fs_closing(root->fs_info)) {
                 block_group->inode = igrab(inode);
                 block_group->iref = 1;
         }
@@ -402,7 +402,14 @@ int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
                                 spin_lock(&ctl->tree_lock);
                                 ret = link_free_space(ctl, e);
                                 spin_unlock(&ctl->tree_lock);
-                                BUG_ON(ret);
+                                if (ret) {
+                                        printk(KERN_ERR "Duplicate entries in "
+                                               "free space cache, dumping\n");
+                                        kunmap(page);
+                                        unlock_page(page);
+                                        page_cache_release(page);
+                                        goto free_cache;
+                                }
                         } else {
                                 e->bitmap = kzalloc(PAGE_CACHE_SIZE, GFP_NOFS);
                                 if (!e->bitmap) {
@@ -419,6 +426,14 @@ int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
                                 ctl->op->recalc_thresholds(ctl);
                                 spin_unlock(&ctl->tree_lock);
                                 list_add_tail(&e->list, &bitmaps);
+                                if (ret) {
+                                        printk(KERN_ERR "Duplicate entries in "
+                                               "free space cache, dumping\n");
+                                        kunmap(page);
+                                        unlock_page(page);
+                                        page_cache_release(page);
+                                        goto free_cache;
+                                }
                         }
 
                         num_entries--;
@@ -478,8 +493,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
          * If we're unmounting then just return, since this does a search on the
          * normal root and not the commit root and we could deadlock.
          */
-        smp_mb();
-        if (fs_info->closing)
+        if (btrfs_fs_closing(fs_info))
                 return 0;
 
         /*
@@ -575,10 +589,25 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 
         num_pages = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >>
                 PAGE_CACHE_SHIFT;
+
+        /* Since the first page has all of our checksums and our generation we
+         * need to calculate the offset into the page that we can start writing
+         * our entries.
+         */
+        first_page_offset = (sizeof(u32) * num_pages) + sizeof(u64);
+
         filemap_write_and_wait(inode->i_mapping);
         btrfs_wait_ordered_range(inode, inode->i_size &
                                  ~(root->sectorsize - 1), (u64)-1);
 
+        /* make sure we don't overflow that first page */
+        if (first_page_offset + sizeof(struct btrfs_free_space_entry) >= PAGE_CACHE_SIZE) {
+                /* this is really the same as running out of space, where we also return 0 */
+                printk(KERN_CRIT "Btrfs: free space cache was too big for the crc page\n");
+                ret = 0;
+                goto out_update;
+        }
+
         /* We need a checksum per page. */
         crc = checksums = kzalloc(sizeof(u32) * num_pages, GFP_NOFS);
         if (!crc)
@@ -590,12 +619,6 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
                 return -1;
         }
 
-        /* Since the first page has all of our checksums and our generation we
-         * need to calculate the offset into the page that we can start writing
-         * our entries.
-         */
-        first_page_offset = (sizeof(u32) * num_pages) + sizeof(u64);
-
         /* Get the cluster for this block_group if it exists */
         if (block_group && !list_empty(&block_group->cluster_list))
                 cluster = list_entry(block_group->cluster_list.next,
@@ -857,12 +880,14 @@ int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
         ret = 1;
 
 out_free:
+        kfree(checksums);
+        kfree(pages);
+
+out_update:
         if (ret != 1) {
                 invalidate_inode_pages2_range(inode->i_mapping, 0, index);
                 BTRFS_I(inode)->generation = 0;
         }
-        kfree(checksums);
-        kfree(pages);
         btrfs_update_inode(trans, root, inode);
         return ret;
 }
@@ -963,10 +988,16 @@ static int tree_insert_offset(struct rb_root *root, u64 offset,
                          * logically.
                          */
                         if (bitmap) {
-                                WARN_ON(info->bitmap);
+                                if (info->bitmap) {
+                                        WARN_ON_ONCE(1);
+                                        return -EEXIST;
+                                }
                                 p = &(*p)->rb_right;
                         } else {
-                                WARN_ON(!info->bitmap);
+                                if (!info->bitmap) {
+                                        WARN_ON_ONCE(1);
+                                        return -EEXIST;
+                                }
                                 p = &(*p)->rb_left;
                         }
                 }
@@ -2481,7 +2512,7 @@ struct inode *lookup_free_ino_inode(struct btrfs_root *root,
                 return inode;
 
         spin_lock(&root->cache_lock);
-        if (!root->fs_info->closing)
+        if (!btrfs_fs_closing(root->fs_info))
                 root->cache_inode = igrab(inode);
         spin_unlock(&root->cache_lock);
 
@@ -2504,12 +2535,14 @@ int load_free_ino_cache(struct btrfs_fs_info *fs_info, struct btrfs_root *root)
         int ret = 0;
         u64 root_gen = btrfs_root_generation(&root->root_item);
 
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return 0;
+
         /*
          * If we're unmounting then just return, since this does a search on the
          * normal root and not the commit root and we could deadlock.
          */
-        smp_mb();
-        if (fs_info->closing)
+        if (btrfs_fs_closing(fs_info))
                 return 0;
 
         path = btrfs_alloc_path();
@@ -2543,6 +2576,9 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
         struct inode *inode;
         int ret;
 
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return 0;
+
         inode = lookup_free_ino_inode(root, path);
         if (IS_ERR(inode))
                 return 0;
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 3262cd17a12f..b4087e0fa871 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -38,6 +38,9 @@ static int caching_kthread(void *data)
         int slot;
         int ret;
 
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return 0;
+
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
@@ -59,8 +62,7 @@ again:
                 goto out;
 
         while (1) {
-                smp_mb();
-                if (fs_info->closing)
+                if (btrfs_fs_closing(fs_info))
                         goto out;
 
                 leaf = path->nodes[0];
@@ -141,6 +143,9 @@ static void start_caching(struct btrfs_root *root)
         int ret;
         u64 objectid;
 
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return;
+
         spin_lock(&root->cache_lock);
         if (root->cached != BTRFS_CACHE_NO) {
                 spin_unlock(&root->cache_lock);
@@ -178,6 +183,9 @@ static void start_caching(struct btrfs_root *root)
 
 int btrfs_find_free_ino(struct btrfs_root *root, u64 *objectid)
 {
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return btrfs_find_free_objectid(root, objectid);
+
 again:
         *objectid = btrfs_find_ino_for_alloc(root);
 
@@ -201,6 +209,10 @@ void btrfs_return_ino(struct btrfs_root *root, u64 objectid)
 {
         struct btrfs_free_space_ctl *ctl = root->free_ino_ctl;
         struct btrfs_free_space_ctl *pinned = root->free_ino_pinned;
+
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return;
+
 again:
         if (root->cached == BTRFS_CACHE_FINISHED) {
                 __btrfs_add_free_space(ctl, objectid, 1);
@@ -250,6 +262,9 @@ void btrfs_unpin_free_ino(struct btrfs_root *root)
         struct rb_node *n;
         u64 count;
 
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return;
+
         while (1) {
                 n = rb_first(rbroot);
                 if (!n)
@@ -388,9 +403,24 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
         int prealloc;
         bool retry = false;
 
+        /* only fs tree and subvol/snap needs ino cache */
+        if (root->root_key.objectid != BTRFS_FS_TREE_OBJECTID &&
+            (root->root_key.objectid < BTRFS_FIRST_FREE_OBJECTID ||
+             root->root_key.objectid > BTRFS_LAST_FREE_OBJECTID))
+                return 0;
+
+        /* Don't save inode cache if we are deleting this root */
+        if (btrfs_root_refs(&root->root_item) == 0 &&
+            root != root->fs_info->tree_root)
+                return 0;
+
+        if (!btrfs_test_opt(root, INODE_MAP_CACHE))
+                return 0;
+
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+
 again:
         inode = lookup_free_ino_inode(root, path);
         if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 39a9d5750efd..ebf95f7a44d6 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -138,7 +138,6 @@ static noinline int insert_inline_extent(struct btrfs_trans_handle *trans,
                 return -ENOMEM;
 
         path->leave_spinning = 1;
-        btrfs_set_trans_block_group(trans, inode);
 
         key.objectid = btrfs_ino(inode);
         key.offset = start;
@@ -426,9 +425,8 @@ again:
                 }
         }
         if (start == 0) {
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
                 BUG_ON(IS_ERR(trans));
-                btrfs_set_trans_block_group(trans, inode);
                 trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
                 /* lets try to make an inline extent */
@@ -623,8 +621,9 @@ retry:
                             async_extent->start + async_extent->ram_size - 1,
                             GFP_NOFS);
 
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
                 BUG_ON(IS_ERR(trans));
+                trans->block_rsv = &root->fs_info->delalloc_block_rsv;
                 ret = btrfs_reserve_extent(trans, root,
                                            async_extent->compressed_size,
                                            async_extent->compressed_size,
@@ -793,9 +792,8 @@ static noinline int cow_file_range(struct inode *inode,
         int ret = 0;
 
         BUG_ON(is_free_space_inode(root, inode));
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         BUG_ON(IS_ERR(trans));
-        btrfs_set_trans_block_group(trans, inode);
         trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
         num_bytes = (end - start + blocksize) & ~(blocksize - 1);
@@ -1077,10 +1075,12 @@ static noinline int run_delalloc_nocow(struct inode *inode,
         nolock = is_free_space_inode(root, inode);
 
         if (nolock)
-                trans = btrfs_join_transaction_nolock(root, 1);
+                trans = btrfs_join_transaction_nolock(root);
         else
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
+
         BUG_ON(IS_ERR(trans));
+        trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
         cow_start = (u64)-1;
         cur_offset = start;
@@ -1519,8 +1519,6 @@ static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
 {
         struct btrfs_ordered_sum *sum;
 
-        btrfs_set_trans_block_group(trans, inode);
-
         list_for_each_entry(sum, list, list) {
                 btrfs_csum_file_blocks(trans,
                        BTRFS_I(inode)->root->fs_info->csum_root, sum);
@@ -1735,11 +1733,10 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
                 ret = btrfs_ordered_update_i_size(inode, 0, ordered_extent);
                 if (!ret) {
                         if (nolock)
-                                trans = btrfs_join_transaction_nolock(root, 1);
+                                trans = btrfs_join_transaction_nolock(root);
                         else
-                                trans = btrfs_join_transaction(root, 1);
+                                trans = btrfs_join_transaction(root);
                         BUG_ON(IS_ERR(trans));
-                        btrfs_set_trans_block_group(trans, inode);
                         trans->block_rsv = &root->fs_info->delalloc_block_rsv;
                         ret = btrfs_update_inode(trans, root, inode);
                         BUG_ON(ret);
@@ -1752,11 +1749,10 @@ static int btrfs_finish_ordered_io(struct inode *inode, u64 start, u64 end)
                          0, &cached_state, GFP_NOFS);
 
         if (nolock)
-                trans = btrfs_join_transaction_nolock(root, 1);
+                trans = btrfs_join_transaction_nolock(root);
         else
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
         BUG_ON(IS_ERR(trans));
-        btrfs_set_trans_block_group(trans, inode);
         trans->block_rsv = &root->fs_info->delalloc_block_rsv;
 
         if (test_bit(BTRFS_ORDERED_COMPRESSED, &ordered_extent->flags))
@@ -2431,7 +2427,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
                                         (u64)-1);
 
         if (root->orphan_block_rsv || root->orphan_item_inserted) {
-                trans = btrfs_join_transaction(root, 1);
+                trans = btrfs_join_transaction(root);
                 if (!IS_ERR(trans))
                         btrfs_end_transaction(trans, root);
         }
@@ -2511,12 +2507,12 @@ static void btrfs_read_locked_inode(struct inode *inode)
         struct btrfs_root *root = BTRFS_I(inode)->root;
         struct btrfs_key location;
         int maybe_acls;
-        u64 alloc_group_block;
         u32 rdev;
         int ret;
 
         path = btrfs_alloc_path();
         BUG_ON(!path);
+        path->leave_spinning = 1;
         memcpy(&location, &BTRFS_I(inode)->location, sizeof(location));
 
         ret = btrfs_lookup_inode(NULL, root, path, &location, 0);
@@ -2526,6 +2522,12 @@ static void btrfs_read_locked_inode(struct inode *inode)
         leaf = path->nodes[0];
         inode_item = btrfs_item_ptr(leaf, path->slots[0],
                                     struct btrfs_inode_item);
+        if (!leaf->map_token)
+                map_private_extent_buffer(leaf, (unsigned long)inode_item,
+                                          sizeof(struct btrfs_inode_item),
+                                          &leaf->map_token, &leaf->kaddr,
+                                          &leaf->map_start, &leaf->map_len,
+                                          KM_USER1);
 
         inode->i_mode = btrfs_inode_mode(leaf, inode_item);
         inode->i_nlink = btrfs_inode_nlink(leaf, inode_item);
@@ -2555,8 +2557,6 @@ static void btrfs_read_locked_inode(struct inode *inode)
         BTRFS_I(inode)->index_cnt = (u64)-1;
         BTRFS_I(inode)->flags = btrfs_inode_flags(leaf, inode_item);
 
-        alloc_group_block = btrfs_inode_block_group(leaf, inode_item);
-
         /*
          * try to precache a NULL acl entry for files that don't have
          * any xattrs or acls
@@ -2566,8 +2566,11 @@ static void btrfs_read_locked_inode(struct inode *inode)
         if (!maybe_acls)
                 cache_no_acl(inode);
 
-        BTRFS_I(inode)->block_group = btrfs_find_block_group(root, 0,
-                                                alloc_group_block, 0);
+        if (leaf->map_token) {
+                unmap_extent_buffer(leaf, leaf->map_token, KM_USER1);
+                leaf->map_token = NULL;
+        }
+
         btrfs_free_path(path);
         inode_item = NULL;
 
@@ -2647,7 +2650,7 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
         btrfs_set_inode_transid(leaf, item, trans->transid);
         btrfs_set_inode_rdev(leaf, item, inode->i_rdev);
         btrfs_set_inode_flags(leaf, item, BTRFS_I(inode)->flags);
-        btrfs_set_inode_block_group(leaf, item, BTRFS_I(inode)->block_group);
+        btrfs_set_inode_block_group(leaf, item, 0);
 
         if (leaf->map_token) {
                 unmap_extent_buffer(leaf, leaf->map_token, KM_USER1);
@@ -3004,8 +3007,6 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, dir);
-
         btrfs_record_unlink_dir(trans, dir, dentry->d_inode, 0);
 
         ret = btrfs_unlink_inode(trans, root, dir, dentry->d_inode,
@@ -3094,8 +3095,6 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, dir);
-
         if (unlikely(btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
                 err = btrfs_unlink_subvol(trans, root, dir,
                                           BTRFS_I(inode)->location.objectid,
@@ -3514,7 +3513,6 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
                                 err = PTR_ERR(trans);
                                 break;
                         }
-                        btrfs_set_trans_block_group(trans, inode);
 
                         err = btrfs_drop_extents(trans, inode, cur_offset,
                                                  cur_offset + hole_size,
@@ -3650,7 +3648,6 @@ void btrfs_evict_inode(struct inode *inode)
         while (1) {
                 trans = btrfs_start_transaction(root, 0);
                 BUG_ON(IS_ERR(trans));
-                btrfs_set_trans_block_group(trans, inode);
                 trans->block_rsv = root->orphan_block_rsv;
 
                 ret = btrfs_block_rsv_check(trans, root,
@@ -4133,7 +4130,8 @@ static int btrfs_real_readdir(struct file *filp, void *dirent,
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
-        path->reada = 2;
+
+        path->reada = 1;
 
         if (key_type == BTRFS_DIR_INDEX_KEY) {
                 INIT_LIST_HEAD(&ins_list);
@@ -4268,18 +4266,16 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
         if (BTRFS_I(inode)->dummy_inode)
                 return 0;
 
-        smp_mb();
-        if (root->fs_info->closing && is_free_space_inode(root, inode))
+        if (btrfs_fs_closing(root->fs_info) && is_free_space_inode(root, inode))
                 nolock = true;
 
         if (wbc->sync_mode == WB_SYNC_ALL) {
                 if (nolock)
-                        trans = btrfs_join_transaction_nolock(root, 1);
+                        trans = btrfs_join_transaction_nolock(root);
                 else
-                        trans = btrfs_join_transaction(root, 1);
+                        trans = btrfs_join_transaction(root);
                 if (IS_ERR(trans))
                         return PTR_ERR(trans);
-                btrfs_set_trans_block_group(trans, inode);
                 if (nolock)
                         ret = btrfs_end_transaction_nolock(trans, root);
                 else
@@ -4303,9 +4299,8 @@ void btrfs_dirty_inode(struct inode *inode, int flags)
         if (BTRFS_I(inode)->dummy_inode)
                 return;
 
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         BUG_ON(IS_ERR(trans));
-        btrfs_set_trans_block_group(trans, inode);
 
         ret = btrfs_update_inode(trans, root, inode);
         if (ret && ret == -ENOSPC) {
@@ -4319,7 +4314,6 @@ void btrfs_dirty_inode(struct inode *inode, int flags)
                                        PTR_ERR(trans));
                         return;
                 }
-                btrfs_set_trans_block_group(trans, inode);
 
                 ret = btrfs_update_inode(trans, root, inode);
                 if (ret) {
@@ -4418,8 +4412,8 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
                                      struct btrfs_root *root,
                                      struct inode *dir,
                                      const char *name, int name_len,
-                                     u64 ref_objectid, u64 objectid,
-                                     u64 alloc_hint, int mode, u64 *index)
+                                     u64 ref_objectid, u64 objectid, int mode,
+                                     u64 *index)
 {
         struct inode *inode;
         struct btrfs_inode_item *inode_item;
@@ -4472,8 +4466,6 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
                 owner = 0;
         else
                 owner = 1;
-        BTRFS_I(inode)->block_group =
-                        btrfs_find_block_group(root, 0, alloc_hint, owner);
 
         key[0].objectid = objectid;
         btrfs_set_key_type(&key[0], BTRFS_INODE_ITEM_KEY);
@@ -4629,15 +4621,13 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, dir);
-
         err = btrfs_find_free_ino(root, &objectid);
         if (err)
                 goto out_unlock;
 
         inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
                                 dentry->d_name.len, btrfs_ino(dir), objectid,
-                                BTRFS_I(dir)->block_group, mode, &index);
+                                mode, &index);
         if (IS_ERR(inode)) {
                 err = PTR_ERR(inode);
                 goto out_unlock;
@@ -4649,7 +4639,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
                 goto out_unlock;
         }
 
-        btrfs_set_trans_block_group(trans, inode);
         err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
         if (err)
                 drop_inode = 1;
@@ -4658,8 +4647,6 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
                 init_special_inode(inode, inode->i_mode, rdev);
                 btrfs_update_inode(trans, root, inode);
         }
-        btrfs_update_inode_block_group(trans, inode);
-        btrfs_update_inode_block_group(trans, dir);
 out_unlock:
         nr = trans->blocks_used;
         btrfs_end_transaction_throttle(trans, root);
@@ -4692,15 +4679,13 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, dir);
-
         err = btrfs_find_free_ino(root, &objectid);
         if (err)
                 goto out_unlock;
 
         inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
                                 dentry->d_name.len, btrfs_ino(dir), objectid,
-                                BTRFS_I(dir)->block_group, mode, &index);
+                                mode, &index);
         if (IS_ERR(inode)) {
                 err = PTR_ERR(inode);
                 goto out_unlock;
@@ -4712,7 +4697,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
                 goto out_unlock;
         }
 
-        btrfs_set_trans_block_group(trans, inode);
         err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
         if (err)
                 drop_inode = 1;
@@ -4723,8 +4707,6 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
                 inode->i_op = &btrfs_file_inode_operations;
                 BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
         }
-        btrfs_update_inode_block_group(trans, inode);
-        btrfs_update_inode_block_group(trans, dir);
 out_unlock:
         nr = trans->blocks_used;
         btrfs_end_transaction_throttle(trans, root);
@@ -4771,8 +4753,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 
         btrfs_inc_nlink(inode);
         inode->i_ctime = CURRENT_TIME;
-
-        btrfs_set_trans_block_group(trans, dir);
         ihold(inode);
 
         err = btrfs_add_nondir(trans, dir, dentry, inode, 1, index);
@@ -4781,7 +4761,6 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
                 drop_inode = 1;
         } else {
                 struct dentry *parent = dget_parent(dentry);
-                btrfs_update_inode_block_group(trans, dir);
                 err = btrfs_update_inode(trans, root, inode);
                 BUG_ON(err);
                 btrfs_log_new_name(trans, inode, NULL, parent);
@@ -4818,7 +4797,6 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
         trans = btrfs_start_transaction(root, 5);
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
-        btrfs_set_trans_block_group(trans, dir);
 
         err = btrfs_find_free_ino(root, &objectid);
         if (err)
@@ -4826,8 +4804,7 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
         inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
                                 dentry->d_name.len, btrfs_ino(dir), objectid,
-                                BTRFS_I(dir)->block_group, S_IFDIR | mode,
-                                &index);
+                                S_IFDIR | mode, &index);
         if (IS_ERR(inode)) {
                 err = PTR_ERR(inode);
                 goto out_fail;
@@ -4841,7 +4818,6 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
         inode->i_op = &btrfs_dir_inode_operations;
         inode->i_fop = &btrfs_dir_file_operations;
-        btrfs_set_trans_block_group(trans, inode);
 
         btrfs_i_size_write(inode, 0);
         err = btrfs_update_inode(trans, root, inode);
@@ -4855,8 +4831,6 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 
         d_instantiate(dentry, inode);
         drop_on_err = 0;
-        btrfs_update_inode_block_group(trans, inode);
-        btrfs_update_inode_block_group(trans, dir);
 
 out_fail:
         nr = trans->blocks_used;
@@ -4989,7 +4963,15 @@ again:
 
         if (!path) {
                 path = btrfs_alloc_path();
-                BUG_ON(!path);
+                if (!path) {
+                        err = -ENOMEM;
+                        goto out;
+                }
+                /*
+                 * Chances are we'll be called again, so go ahead and do
+                 * readahead
+                 */
+                path->reada = 1;
         }
 
         ret = btrfs_lookup_file_extent(trans, root, path,
@@ -5130,8 +5112,10 @@ again:
                                 kunmap(page);
                                 free_extent_map(em);
                                 em = NULL;
+
                                 btrfs_release_path(path);
-                                trans = btrfs_join_transaction(root, 1);
+                                trans = btrfs_join_transaction(root);
+
                                 if (IS_ERR(trans))
                                         return ERR_CAST(trans);
                                 goto again;
@@ -5375,7 +5359,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
                 btrfs_drop_extent_cache(inode, start, start + len - 1, 0);
         }
 
-        trans = btrfs_join_transaction(root, 0);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans))
                 return ERR_CAST(trans);
 
@@ -5611,7 +5595,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
                  * to make sure the current transaction stays open
                  * while we look for nocow cross refs
                  */
-                trans = btrfs_join_transaction(root, 0);
+                trans = btrfs_join_transaction(root);
                 if (IS_ERR(trans))
                         goto must_cow;
 
@@ -5750,7 +5734,7 @@ again:
 
         BUG_ON(!ordered);
 
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans)) {
                 err = -ENOMEM;
                 goto out;
@@ -6500,6 +6484,7 @@ out:
 static int btrfs_truncate(struct inode *inode)
 {
         struct btrfs_root *root = BTRFS_I(inode)->root;
+        struct btrfs_block_rsv *rsv;
         int ret;
         int err = 0;
         struct btrfs_trans_handle *trans;
@@ -6513,28 +6498,80 @@ static int btrfs_truncate(struct inode *inode)
         btrfs_wait_ordered_range(inode, inode->i_size & (~mask), (u64)-1);
         btrfs_ordered_update_i_size(inode, inode->i_size, NULL);
 
-        trans = btrfs_start_transaction(root, 5);
-        if (IS_ERR(trans))
-                return PTR_ERR(trans);
+        /*
+         * Yes ladies and gentelment, this is indeed ugly.  The fact is we have
+         * 3 things going on here
+         *
+         * 1) We need to reserve space for our orphan item and the space to
+         * delete our orphan item.  Lord knows we don't want to have a dangling
+         * orphan item because we didn't reserve space to remove it.
+         *
+         * 2) We need to reserve space to update our inode.
+         *
+         * 3) We need to have something to cache all the space that is going to
+         * be free'd up by the truncate operation, but also have some slack
+         * space reserved in case it uses space during the truncate (thank you
+         * very much snapshotting).
+         *
+         * And we need these to all be seperate.  The fact is we can use alot of
+         * space doing the truncate, and we have no earthly idea how much space
+         * we will use, so we need the truncate reservation to be seperate so it
+         * doesn't end up using space reserved for updating the inode or
+         * removing the orphan item.  We also need to be able to stop the
+         * transaction and start a new one, which means we need to be able to
+         * update the inode several times, and we have no idea of knowing how
+         * many times that will be, so we can't just reserve 1 item for the
+         * entirety of the opration, so that has to be done seperately as well.
+         * Then there is the orphan item, which does indeed need to be held on
+         * to for the whole operation, and we need nobody to touch this reserved
+         * space except the orphan code.
+         *
+         * So that leaves us with
+         *
+         * 1) root->orphan_block_rsv - for the orphan deletion.
+         * 2) rsv - for the truncate reservation, which we will steal from the
+         * transaction reservation.
+         * 3) fs_info->trans_block_rsv - this will have 1 items worth left for
+         * updating the inode.
+         */
+        rsv = btrfs_alloc_block_rsv(root);
+        if (!rsv)
+                return -ENOMEM;
+        btrfs_add_durable_block_rsv(root->fs_info, rsv);
+
+        trans = btrfs_start_transaction(root, 4);
+        if (IS_ERR(trans)) {
+                err = PTR_ERR(trans);
+                goto out;
+        }
 
-        btrfs_set_trans_block_group(trans, inode);
+        /*
+         * Reserve space for the truncate process.  Truncate should be adding
+         * space, but if there are snapshots it may end up using space.
+         */
+        ret = btrfs_truncate_reserve_metadata(trans, root, rsv);
+        BUG_ON(ret);
 
         ret = btrfs_orphan_add(trans, inode);
         if (ret) {
                 btrfs_end_transaction(trans, root);
-                return ret;
+                goto out;
         }
 
         nr = trans->blocks_used;
         btrfs_end_transaction(trans, root);
         btrfs_btree_balance_dirty(root, nr);
 
-        /* Now start a transaction for the truncate */
-        trans = btrfs_start_transaction(root, 0);
-        if (IS_ERR(trans))
-                return PTR_ERR(trans);
-        btrfs_set_trans_block_group(trans, inode);
-        trans->block_rsv = root->orphan_block_rsv;
+        /*
+         * Ok so we've already migrated our bytes over for the truncate, so here
+         * just reserve the one slot we need for updating the inode.
+         */
+        trans = btrfs_start_transaction(root, 1);
+        if (IS_ERR(trans)) {
+                err = PTR_ERR(trans);
+                goto out;
+        }
+        trans->block_rsv = rsv;
 
         /*
          * setattr is responsible for setting the ordered_data_close flag,
@@ -6558,24 +6595,17 @@ static int btrfs_truncate(struct inode *inode)
 
         while (1) {
                 if (!trans) {
-                        trans = btrfs_start_transaction(root, 0);
-                        if (IS_ERR(trans))
-                                return PTR_ERR(trans);
-                        btrfs_set_trans_block_group(trans, inode);
-                        trans->block_rsv = root->orphan_block_rsv;
-                }
+                        trans = btrfs_start_transaction(root, 3);
+                        if (IS_ERR(trans)) {
+                                err = PTR_ERR(trans);
+                                goto out;
+                        }
 
-                ret = btrfs_block_rsv_check(trans, root,
-                                            root->orphan_block_rsv, 0, 5);
-                if (ret == -EAGAIN) {
-                        ret = btrfs_commit_transaction(trans, root);
-                        if (ret)
-                                return ret;
-                        trans = NULL;
-                        continue;
-                } else if (ret) {
-                        err = ret;
-                        break;
+                        ret = btrfs_truncate_reserve_metadata(trans, root,
+                                                              rsv);
+                        BUG_ON(ret);
+
+                        trans->block_rsv = rsv;
                 }
 
                 ret = btrfs_truncate_inode_items(trans, root, inode,
@@ -6586,6 +6616,7 @@ static int btrfs_truncate(struct inode *inode)
                         break;
                 }
 
+                trans->block_rsv = &root->fs_info->trans_block_rsv;
                 ret = btrfs_update_inode(trans, root, inode);
                 if (ret) {
                         err = ret;
@@ -6599,6 +6630,7 @@ static int btrfs_truncate(struct inode *inode)
         }
 
         if (ret == 0 && inode->i_nlink > 0) {
+                trans->block_rsv = root->orphan_block_rsv;
                 ret = btrfs_orphan_del(trans, inode);
                 if (ret)
                         err = ret;
@@ -6610,15 +6642,20 @@ static int btrfs_truncate(struct inode *inode)
                 ret = btrfs_orphan_del(NULL, inode);
         }
 
+        trans->block_rsv = &root->fs_info->trans_block_rsv;
         ret = btrfs_update_inode(trans, root, inode);
         if (ret && !err)
                 err = ret;
 
         nr = trans->blocks_used;
         ret = btrfs_end_transaction_throttle(trans, root);
+        btrfs_btree_balance_dirty(root, nr);
+
+out:
+        btrfs_free_block_rsv(root, rsv);
+
         if (ret && !err)
                 err = ret;
-        btrfs_btree_balance_dirty(root, nr);
 
         return err;
 }
@@ -6627,15 +6664,14 @@ static int btrfs_truncate(struct inode *inode)
  * create a new subvolume directory/inode (helper for the ioctl).
  */
 int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
-                             struct btrfs_root *new_root,
-                             u64 new_dirid, u64 alloc_hint)
+                             struct btrfs_root *new_root, u64 new_dirid)
 {
         struct inode *inode;
         int err;
         u64 index = 0;
 
         inode = btrfs_new_inode(trans, new_root, NULL, "..", 2, new_dirid,
-                                new_dirid, alloc_hint, S_IFDIR | 0700, &index);
+                                new_dirid, S_IFDIR | 0700, &index);
         if (IS_ERR(inode))
                 return PTR_ERR(inode);
         inode->i_op = &btrfs_dir_inode_operations;
@@ -6748,21 +6784,6 @@ void btrfs_destroy_inode(struct inode *inode)
                 spin_unlock(&root->fs_info->ordered_extent_lock);
         }
 
-        if (root == root->fs_info->tree_root) {
-                struct btrfs_block_group_cache *block_group;
-
-                block_group = btrfs_lookup_block_group(root->fs_info,
-                                                BTRFS_I(inode)->block_group);
-                if (block_group && block_group->inode == inode) {
-                        spin_lock(&block_group->lock);
-                        block_group->inode = NULL;
-                        spin_unlock(&block_group->lock);
-                        btrfs_put_block_group(block_group);
-                } else if (block_group) {
-                        btrfs_put_block_group(block_group);
-                }
-        }
-
         spin_lock(&root->orphan_lock);
         if (!list_empty(&BTRFS_I(inode)->i_orphan)) {
                 printk(KERN_INFO "BTRFS: inode %llu still on the orphan list\n",
@@ -6948,8 +6969,6 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
                 goto out_notrans;
         }
 
-        btrfs_set_trans_block_group(trans, new_dir);
-
         if (dest != root)
                 btrfs_record_root_in_trans(trans, dest);
 
@@ -7131,16 +7150,13 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, dir);
-
         err = btrfs_find_free_ino(root, &objectid);
         if (err)
                 goto out_unlock;
 
         inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
                                 dentry->d_name.len, btrfs_ino(dir), objectid,
-                                BTRFS_I(dir)->block_group, S_IFLNK|S_IRWXUGO,
-                                &index);
+                                S_IFLNK|S_IRWXUGO, &index);
         if (IS_ERR(inode)) {
                 err = PTR_ERR(inode);
                 goto out_unlock;
@@ -7152,7 +7168,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
                 goto out_unlock;
         }
 
-        btrfs_set_trans_block_group(trans, inode);
         err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
         if (err)
                 drop_inode = 1;
@@ -7163,8 +7178,6 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
                 inode->i_op = &btrfs_file_inode_operations;
                 BTRFS_I(inode)->io_tree.ops = &btrfs_extent_io_ops;
         }
-        btrfs_update_inode_block_group(trans, inode);
-        btrfs_update_inode_block_group(trans, dir);
         if (drop_inode)
                 goto out_unlock;
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 85e818ce00c5..ac37040e426a 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -243,7 +243,7 @@ static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
                 ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
         }
 
-        trans = btrfs_join_transaction(root, 1);
+        trans = btrfs_join_transaction(root);
         BUG_ON(IS_ERR(trans));
 
         ret = btrfs_update_inode(trans, root, inode);
@@ -414,8 +414,7 @@ static noinline int create_subvol(struct btrfs_root *root,
 
         btrfs_record_root_in_trans(trans, new_root);
 
-        ret = btrfs_create_subvol_root(trans, new_root, new_dirid,
-                                       BTRFS_I(dir)->block_group);
+        ret = btrfs_create_subvol_root(trans, new_root, new_dirid);
         /*
          * insert the directory item
          */
@@ -707,16 +706,17 @@ static int find_new_extents(struct btrfs_root *root,
         struct btrfs_file_extent_item *extent;
         int type;
         int ret;
+        u64 ino = btrfs_ino(inode);
 
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
 
-        min_key.objectid = inode->i_ino;
+        min_key.objectid = ino;
         min_key.type = BTRFS_EXTENT_DATA_KEY;
         min_key.offset = *off;
 
-        max_key.objectid = inode->i_ino;
+        max_key.objectid = ino;
         max_key.type = (u8)-1;
         max_key.offset = (u64)-1;
 
@@ -727,7 +727,7 @@ static int find_new_extents(struct btrfs_root *root,
                                            path, 0, newer_than);
                 if (ret != 0)
                         goto none;
-                if (min_key.objectid != inode->i_ino)
+                if (min_key.objectid != ino)
                         goto none;
                 if (min_key.type != BTRFS_EXTENT_DATA_KEY)
                         goto none;
@@ -2489,12 +2489,10 @@ static long btrfs_ioctl_trans_start(struct file *file)
         if (ret)
                 goto out;
 
-        mutex_lock(&root->fs_info->trans_mutex);
-        root->fs_info->open_ioctl_trans++;
-        mutex_unlock(&root->fs_info->trans_mutex);
+        atomic_inc(&root->fs_info->open_ioctl_trans);
 
         ret = -ENOMEM;
-        trans = btrfs_start_ioctl_transaction(root, 0);
+        trans = btrfs_start_ioctl_transaction(root);
         if (IS_ERR(trans))
                 goto out_drop;
 
@@ -2502,9 +2500,7 @@ static long btrfs_ioctl_trans_start(struct file *file)
         return 0;
 
 out_drop:
-        mutex_lock(&root->fs_info->trans_mutex);
-        root->fs_info->open_ioctl_trans--;
-        mutex_unlock(&root->fs_info->trans_mutex);
+        atomic_dec(&root->fs_info->open_ioctl_trans);
         mnt_drop_write(file->f_path.mnt);
 out:
         return ret;
@@ -2738,9 +2734,7 @@ long btrfs_ioctl_trans_end(struct file *file)
 
         btrfs_end_transaction(trans, root);
 
-        mutex_lock(&root->fs_info->trans_mutex);
-        root->fs_info->open_ioctl_trans--;
-        mutex_unlock(&root->fs_info->trans_mutex);
+        atomic_dec(&root->fs_info->open_ioctl_trans);
 
         mnt_drop_write(file->f_path.mnt);
         return 0;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index ca38eca70af0..b1ef27cc673b 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -677,6 +677,8 @@ struct backref_node *build_backref_tree(struct reloc_control *rc,
                 err = -ENOMEM;
                 goto out;
         }
+        path1->reada = 1;
+        path2->reada = 2;
 
         node = alloc_backref_node(cache);
         if (!node) {
@@ -1999,6 +2001,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+        path->reada = 1;
 
         reloc_root = root->reloc_root;
         root_item = &reloc_root->root_item;
@@ -2139,10 +2142,10 @@ int prepare_to_merge(struct reloc_control *rc, int err)
         u64 num_bytes = 0;
         int ret;
 
-        mutex_lock(&root->fs_info->trans_mutex);
+        spin_lock(&root->fs_info->trans_lock);
         rc->merging_rsv_size += root->nodesize * (BTRFS_MAX_LEVEL - 1) * 2;
         rc->merging_rsv_size += rc->nodes_relocated * 2;
-        mutex_unlock(&root->fs_info->trans_mutex);
+        spin_unlock(&root->fs_info->trans_lock);
 again:
         if (!err) {
                 num_bytes = rc->merging_rsv_size;
@@ -2152,7 +2155,7 @@ again:
                         err = ret;
         }
 
-        trans = btrfs_join_transaction(rc->extent_root, 1);
+        trans = btrfs_join_transaction(rc->extent_root);
         if (IS_ERR(trans)) {
                 if (!err)
                         btrfs_block_rsv_release(rc->extent_root,
@@ -2211,9 +2214,9 @@ int merge_reloc_roots(struct reloc_control *rc)
         int ret;
 again:
         root = rc->extent_root;
-        mutex_lock(&root->fs_info->trans_mutex);
+        spin_lock(&root->fs_info->trans_lock);
         list_splice_init(&rc->reloc_roots, &reloc_roots);
-        mutex_unlock(&root->fs_info->trans_mutex);
+        spin_unlock(&root->fs_info->trans_lock);
 
         while (!list_empty(&reloc_roots)) {
                 found = 1;
@@ -3236,7 +3239,7 @@ truncate:
                 goto out;
         }
 
-        trans = btrfs_join_transaction(root, 0);
+        trans = btrfs_join_transaction(root);
         if (IS_ERR(trans)) {
                 btrfs_free_path(path);
                 ret = PTR_ERR(trans);
@@ -3300,6 +3303,7 @@ static int find_data_references(struct reloc_control *rc,
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+        path->reada = 1;
 
         root = read_fs_root(rc->extent_root->fs_info, ref_root);
         if (IS_ERR(root)) {
@@ -3586,17 +3590,17 @@ next:
 static void set_reloc_control(struct reloc_control *rc)
 {
         struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
-        mutex_lock(&fs_info->trans_mutex);
+        spin_lock(&fs_info->trans_lock);
         fs_info->reloc_ctl = rc;
-        mutex_unlock(&fs_info->trans_mutex);
+        spin_unlock(&fs_info->trans_lock);
 }
 
 static void unset_reloc_control(struct reloc_control *rc)
 {
         struct btrfs_fs_info *fs_info = rc->extent_root->fs_info;
-        mutex_lock(&fs_info->trans_mutex);
+        spin_lock(&fs_info->trans_lock);
         fs_info->reloc_ctl = NULL;
-        mutex_unlock(&fs_info->trans_mutex);
+        spin_unlock(&fs_info->trans_lock);
 }
 
 static int check_extent_flags(u64 flags)
@@ -3645,7 +3649,7 @@ int prepare_to_relocate(struct reloc_control *rc)
         rc->create_reloc_tree = 1;
         set_reloc_control(rc);
 
-        trans = btrfs_join_transaction(rc->extent_root, 1);
+        trans = btrfs_join_transaction(rc->extent_root);
         BUG_ON(IS_ERR(trans));
         btrfs_commit_transaction(trans, rc->extent_root);
         return 0;
@@ -3668,6 +3672,7 @@ static noinline_for_stack int relocate_block_group(struct reloc_control *rc)
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+        path->reada = 1;
 
         ret = prepare_to_relocate(rc);
         if (ret) {
@@ -3834,7 +3839,7 @@ restart:
         btrfs_block_rsv_release(rc->extent_root, rc->block_rsv, (u64)-1);
 
         /* get rid of pinned extents */
-        trans = btrfs_join_transaction(rc->extent_root, 1);
+        trans = btrfs_join_transaction(rc->extent_root);
         if (IS_ERR(trans))
                 err = PTR_ERR(trans);
         else
@@ -4093,6 +4098,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
         path = btrfs_alloc_path();
         if (!path)
                 return -ENOMEM;
+        path->reada = -1;
 
         key.objectid = BTRFS_TREE_RELOC_OBJECTID;
         key.type = BTRFS_ROOT_ITEM_KEY;
@@ -4159,7 +4165,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 
         set_reloc_control(rc);
 
-        trans = btrfs_join_transaction(rc->extent_root, 1);
+        trans = btrfs_join_transaction(rc->extent_root);
         if (IS_ERR(trans)) {
                 unset_reloc_control(rc);
                 err = PTR_ERR(trans);
@@ -4193,7 +4199,7 @@ int btrfs_recover_relocation(struct btrfs_root *root)
 
         unset_reloc_control(rc);
 
-        trans = btrfs_join_transaction(rc->extent_root, 1);
+        trans = btrfs_join_transaction(rc->extent_root);
         if (IS_ERR(trans))
                 err = PTR_ERR(trans);
         else
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 6dfed0c27ac3..df50fd1eca8f 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -117,33 +117,37 @@ static void scrub_free_csums(struct scrub_dev *sdev)
         }
 }
 
+static void scrub_free_bio(struct bio *bio)
+{
+        int i;
+        struct page *last_page = NULL;
+
+        if (!bio)
+                return;
+
+        for (i = 0; i < bio->bi_vcnt; ++i) {
+                if (bio->bi_io_vec[i].bv_page == last_page)
+                        continue;
+                last_page = bio->bi_io_vec[i].bv_page;
+                __free_page(last_page);
+        }
+        bio_put(bio);
+}
+
 static noinline_for_stack void scrub_free_dev(struct scrub_dev *sdev)
 {
         int i;
-        int j;
-        struct page *last_page;
 
         if (!sdev)
                 return;
 
         for (i = 0; i < SCRUB_BIOS_PER_DEV; ++i) {
                 struct scrub_bio *sbio = sdev->bios[i];
-                struct bio *bio;
 
                 if (!sbio)
                         break;
 
-                bio = sbio->bio;
-                if (bio) {
-                        last_page = NULL;
-                        for (j = 0; j < bio->bi_vcnt; ++j) {
-                                if (bio->bi_io_vec[j].bv_page == last_page)
-                                        continue;
-                                last_page = bio->bi_io_vec[j].bv_page;
-                                __free_page(last_page);
-                        }
-                        bio_put(bio);
-                }
+                scrub_free_bio(sbio->bio);
                 kfree(sbio);
         }
 
@@ -156,8 +160,6 @@ struct scrub_dev *scrub_setup_dev(struct btrfs_device *dev)
 {
         struct scrub_dev *sdev;
         int             i;
-        int             j;
-        int             ret;
         struct btrfs_fs_info *fs_info = dev->dev_root->fs_info;
 
         sdev = kzalloc(sizeof(*sdev), GFP_NOFS);
@@ -165,7 +167,6 @@ struct scrub_dev *scrub_setup_dev(struct btrfs_device *dev)
                 goto nomem;
         sdev->dev = dev;
         for (i = 0; i < SCRUB_BIOS_PER_DEV; ++i) {
-                struct bio *bio;
                 struct scrub_bio *sbio;
 
                 sbio = kzalloc(sizeof(*sbio), GFP_NOFS);
@@ -173,32 +174,10 @@ struct scrub_dev *scrub_setup_dev(struct btrfs_device *dev)
                         goto nomem;
                 sdev->bios[i] = sbio;
 
-                bio = bio_kmalloc(GFP_NOFS, SCRUB_PAGES_PER_BIO);
-                if (!bio)
-                        goto nomem;
-
                 sbio->index = i;
                 sbio->sdev = sdev;
-                sbio->bio = bio;
                 sbio->count = 0;
                 sbio->work.func = scrub_checksum;
-                bio->bi_private = sdev->bios[i];
-                bio->bi_end_io = scrub_bio_end_io;
-                bio->bi_sector = 0;
-                bio->bi_bdev = dev->bdev;
-                bio->bi_size = 0;
-
-                for (j = 0; j < SCRUB_PAGES_PER_BIO; ++j) {
-                        struct page *page;
-                        page = alloc_page(GFP_NOFS);
-                        if (!page)
-                                goto nomem;
-
-                        ret = bio_add_page(bio, page, PAGE_SIZE, 0);
-                        if (!ret)
-                                goto nomem;
-                }
-                WARN_ON(bio->bi_vcnt != SCRUB_PAGES_PER_BIO);
 
                 if (i != SCRUB_BIOS_PER_DEV-1)
                         sdev->bios[i]->next_free = i + 1;
@@ -369,9 +348,6 @@ static int scrub_fixup_io(int rw, struct block_device *bdev, sector_t sector,
         int ret;
         DECLARE_COMPLETION_ONSTACK(complete);
 
-        /* we are going to wait on this IO */
-        rw |= REQ_SYNC;
-
         bio = bio_alloc(GFP_NOFS, 1);
         bio->bi_bdev = bdev;
         bio->bi_sector = sector;
@@ -380,6 +356,7 @@ static int scrub_fixup_io(int rw, struct block_device *bdev, sector_t sector,
         bio->bi_private = &complete;
         submit_bio(rw, bio);
 
+        /* this will also unplug the queue */
         wait_for_completion(&complete);
 
         ret = !test_bit(BIO_UPTODATE, &bio->bi_flags);
@@ -394,6 +371,7 @@ static void scrub_bio_end_io(struct bio *bio, int err)
         struct btrfs_fs_info *fs_info = sdev->dev->dev_root->fs_info;
 
         sbio->err = err;
+        sbio->bio = bio;
 
         btrfs_queue_worker(&fs_info->scrub_workers, &sbio->work);
 }
@@ -453,6 +431,8 @@ static void scrub_checksum(struct btrfs_work *work)
         }
 
 out:
+        scrub_free_bio(sbio->bio);
+        sbio->bio = NULL;
         spin_lock(&sdev->list_lock);
         sbio->next_free = sdev->first_free;
         sdev->first_free = sbio->index;
@@ -583,25 +563,50 @@ static int scrub_checksum_super(struct scrub_bio *sbio, void *buffer)
 static int scrub_submit(struct scrub_dev *sdev)
 {
         struct scrub_bio *sbio;
+        struct bio *bio;
+        int i;
 
         if (sdev->curr == -1)
                 return 0;
 
         sbio = sdev->bios[sdev->curr];
 
-        sbio->bio->bi_sector = sbio->physical >> 9;
-        sbio->bio->bi_size = sbio->count * PAGE_SIZE;
-        sbio->bio->bi_next = NULL;
-        sbio->bio->bi_flags |= 1 << BIO_UPTODATE;
-        sbio->bio->bi_comp_cpu = -1;
-        sbio->bio->bi_bdev = sdev->dev->bdev;
+        bio = bio_alloc(GFP_NOFS, sbio->count);
+        if (!bio)
+                goto nomem;
+
+        bio->bi_private = sbio;
+        bio->bi_end_io = scrub_bio_end_io;
+        bio->bi_bdev = sdev->dev->bdev;
+        bio->bi_sector = sbio->physical >> 9;
+
+        for (i = 0; i < sbio->count; ++i) {
+                struct page *page;
+                int ret;
+
+                page = alloc_page(GFP_NOFS);
+                if (!page)
+                        goto nomem;
+
+                ret = bio_add_page(bio, page, PAGE_SIZE, 0);
+                if (!ret) {
+                        __free_page(page);
+                        goto nomem;
+                }
+        }
+
         sbio->err = 0;
         sdev->curr = -1;
         atomic_inc(&sdev->in_flight);
 
-        submit_bio(0, sbio->bio);
+        submit_bio(READ, bio);
 
         return 0;
+
+nomem:
+        scrub_free_bio(bio);
+
+        return -ENOMEM;
 }
 
 static int scrub_page(struct scrub_dev *sdev, u64 logical, u64 len,
@@ -633,7 +638,11 @@ again:
                 sbio->logical = logical;
         } else if (sbio->physical + sbio->count * PAGE_SIZE != physical ||
                    sbio->logical + sbio->count * PAGE_SIZE != logical) {
-                scrub_submit(sdev);
+                int ret;
+
+                ret = scrub_submit(sdev);
+                if (ret)
+                        return ret;
                 goto again;
         }
         sbio->spag[sbio->count].flags = flags;
@@ -645,8 +654,13 @@ again:
                 memcpy(sbio->spag[sbio->count].csum, csum, sdev->csum_size);
         }
         ++sbio->count;
-        if (sbio->count == SCRUB_PAGES_PER_BIO || force)
-                scrub_submit(sdev);
+        if (sbio->count == SCRUB_PAGES_PER_BIO || force) {
+                int ret;
+
+                ret = scrub_submit(sdev);
+                if (ret)
+                        return ret;
+        }
 
         return 0;
 }
@@ -727,6 +741,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_dev *sdev,
         struct btrfs_root *root = fs_info->extent_root;
         struct btrfs_root *csum_root = fs_info->csum_root;
         struct btrfs_extent_item *extent;
+        struct blk_plug plug;
         u64 flags;
         int ret;
         int slot;
@@ -831,6 +846,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_dev *sdev,
          * the scrub. This might currently (crc32) end up to be about 1MB
          */
         start_stripe = 0;
+        blk_start_plug(&plug);
 again:
         logical = base + offset + start_stripe * increment;
         for (i = start_stripe; i < nstripes; ++i) {
@@ -972,6 +988,7 @@ next:
         scrub_submit(sdev);
 
 out:
+        blk_finish_plug(&plug);
         btrfs_free_path(path);
         return ret < 0 ? ret : 0;
 }
@@ -1166,7 +1183,7 @@ int btrfs_scrub_dev(struct btrfs_root *root, u64 devid, u64 start, u64 end,
         int ret;
         struct btrfs_device *dev;
 
-        if (root->fs_info->closing)
+        if (btrfs_fs_closing(root->fs_info))
                 return -EINVAL;
 
         /*
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 9b2e7e5bc3ef..0bb4ebbb71b7 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -161,7 +161,8 @@ enum {
         Opt_compress_type, Opt_compress_force, Opt_compress_force_type,
         Opt_notreelog, Opt_ratio, Opt_flushoncommit, Opt_discard,
         Opt_space_cache, Opt_clear_cache, Opt_user_subvol_rm_allowed,
-        Opt_enospc_debug, Opt_subvolrootid, Opt_defrag, Opt_err,
+        Opt_enospc_debug, Opt_subvolrootid, Opt_defrag,
+        Opt_inode_cache, Opt_err,
 };
 
 static match_table_t tokens = {
@@ -193,6 +194,7 @@ static match_table_t tokens = {
         {Opt_enospc_debug, "enospc_debug"},
         {Opt_subvolrootid, "subvolrootid=%d"},
         {Opt_defrag, "autodefrag"},
+        {Opt_inode_cache, "inode_cache"},
         {Opt_err, NULL},
 };
 
@@ -361,6 +363,10 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
                         printk(KERN_INFO "btrfs: enabling disk space caching\n");
                         btrfs_set_opt(info->mount_opt, SPACE_CACHE);
                         break;
+                case Opt_inode_cache:
+                        printk(KERN_INFO "btrfs: enabling inode map caching\n");
+                        btrfs_set_opt(info->mount_opt, INODE_MAP_CACHE);
+                        break;
                 case Opt_clear_cache:
                         printk(KERN_INFO "btrfs: force clearing of disk cache\n");
                         btrfs_set_opt(info->mount_opt, CLEAR_CACHE);
@@ -819,7 +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/btrfs/transaction.c b/fs/btrfs/transaction.c
index dc80f7156923..dd719662340e 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -35,6 +35,7 @@ static noinline void put_transaction(struct btrfs_transaction *transaction)
 {
         WARN_ON(atomic_read(&transaction->use_count) == 0);
         if (atomic_dec_and_test(&transaction->use_count)) {
+                BUG_ON(!list_empty(&transaction->list));
                 memset(transaction, 0, sizeof(*transaction));
                 kmem_cache_free(btrfs_transaction_cachep, transaction);
         }
@@ -49,46 +50,72 @@ static noinline void switch_commit_root(struct btrfs_root *root)
 /*
  * either allocate a new transaction or hop into the existing one
  */
-static noinline int join_transaction(struct btrfs_root *root)
+static noinline int join_transaction(struct btrfs_root *root, int nofail)
 {
         struct btrfs_transaction *cur_trans;
+
+        spin_lock(&root->fs_info->trans_lock);
+        if (root->fs_info->trans_no_join) {
+                if (!nofail) {
+                        spin_unlock(&root->fs_info->trans_lock);
+                        return -EBUSY;
+                }
+        }
+
         cur_trans = root->fs_info->running_transaction;
-        if (!cur_trans) {
-                cur_trans = kmem_cache_alloc(btrfs_transaction_cachep,
-                                             GFP_NOFS);
-                if (!cur_trans)
-                        return -ENOMEM;
-                root->fs_info->generation++;
-                atomic_set(&cur_trans->num_writers, 1);
-                cur_trans->num_joined = 0;
-                cur_trans->transid = root->fs_info->generation;
-                init_waitqueue_head(&cur_trans->writer_wait);
-                init_waitqueue_head(&cur_trans->commit_wait);
-                cur_trans->in_commit = 0;
-                cur_trans->blocked = 0;
-                atomic_set(&cur_trans->use_count, 1);
-                cur_trans->commit_done = 0;
-                cur_trans->start_time = get_seconds();
-
-                cur_trans->delayed_refs.root = RB_ROOT;
-                cur_trans->delayed_refs.num_entries = 0;
-                cur_trans->delayed_refs.num_heads_ready = 0;
-                cur_trans->delayed_refs.num_heads = 0;
-                cur_trans->delayed_refs.flushing = 0;
-                cur_trans->delayed_refs.run_delayed_start = 0;
-                spin_lock_init(&cur_trans->delayed_refs.lock);
-
-                INIT_LIST_HEAD(&cur_trans->pending_snapshots);
-                list_add_tail(&cur_trans->list, &root->fs_info->trans_list);
-                extent_io_tree_init(&cur_trans->dirty_pages,
-                                     root->fs_info->btree_inode->i_mapping);
-                spin_lock(&root->fs_info->new_trans_lock);
-                root->fs_info->running_transaction = cur_trans;
-                spin_unlock(&root->fs_info->new_trans_lock);
-        } else {
+        if (cur_trans) {
+                atomic_inc(&cur_trans->use_count);
                 atomic_inc(&cur_trans->num_writers);
                 cur_trans->num_joined++;
+                spin_unlock(&root->fs_info->trans_lock);
+                return 0;
         }
+        spin_unlock(&root->fs_info->trans_lock);
+
+        cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS);
+        if (!cur_trans)
+                return -ENOMEM;
+        spin_lock(&root->fs_info->trans_lock);
+        if (root->fs_info->running_transaction) {
+                kmem_cache_free(btrfs_transaction_cachep, cur_trans);
+                cur_trans = root->fs_info->running_transaction;
+                atomic_inc(&cur_trans->use_count);
+                atomic_inc(&cur_trans->num_writers);
+                cur_trans->num_joined++;
+                spin_unlock(&root->fs_info->trans_lock);
+                return 0;
+        }
+        atomic_set(&cur_trans->num_writers, 1);
+        cur_trans->num_joined = 0;
+        init_waitqueue_head(&cur_trans->writer_wait);
+        init_waitqueue_head(&cur_trans->commit_wait);
+        cur_trans->in_commit = 0;
+        cur_trans->blocked = 0;
+        /*
+         * One for this trans handle, one so it will live on until we
+         * commit the transaction.
+         */
+        atomic_set(&cur_trans->use_count, 2);
+        cur_trans->commit_done = 0;
+        cur_trans->start_time = get_seconds();
+
+        cur_trans->delayed_refs.root = RB_ROOT;
+        cur_trans->delayed_refs.num_entries = 0;
+        cur_trans->delayed_refs.num_heads_ready = 0;
+        cur_trans->delayed_refs.num_heads = 0;
+        cur_trans->delayed_refs.flushing = 0;
+        cur_trans->delayed_refs.run_delayed_start = 0;
+        spin_lock_init(&cur_trans->commit_lock);
+        spin_lock_init(&cur_trans->delayed_refs.lock);
+
+        INIT_LIST_HEAD(&cur_trans->pending_snapshots);
+        list_add_tail(&cur_trans->list, &root->fs_info->trans_list);
+        extent_io_tree_init(&cur_trans->dirty_pages,
+                             root->fs_info->btree_inode->i_mapping);
+        root->fs_info->generation++;
+        cur_trans->transid = root->fs_info->generation;
+        root->fs_info->running_transaction = cur_trans;
+        spin_unlock(&root->fs_info->trans_lock);
 
         return 0;
 }
@@ -99,39 +126,28 @@ static noinline int join_transaction(struct btrfs_root *root)
  * to make sure the old root from before we joined the transaction is deleted
  * when the transaction commits
  */
-static noinline int record_root_in_trans(struct btrfs_trans_handle *trans,
-                                         struct btrfs_root *root)
+int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
+                               struct btrfs_root *root)
 {
         if (root->ref_cows && root->last_trans < trans->transid) {
                 WARN_ON(root == root->fs_info->extent_root);
                 WARN_ON(root->commit_root != root->node);
 
+                spin_lock(&root->fs_info->fs_roots_radix_lock);
+                if (root->last_trans == trans->transid) {
+                        spin_unlock(&root->fs_info->fs_roots_radix_lock);
+                        return 0;
+                }
+                root->last_trans = trans->transid;
                 radix_tree_tag_set(&root->fs_info->fs_roots_radix,
                            (unsigned long)root->root_key.objectid,
                            BTRFS_ROOT_TRANS_TAG);
-                root->last_trans = trans->transid;
+                spin_unlock(&root->fs_info->fs_roots_radix_lock);
                 btrfs_init_reloc_root(trans, root);
         }
         return 0;
 }
 
-int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
-                               struct btrfs_root *root)
-{
-        if (!root->ref_cows)
-                return 0;
-
-        mutex_lock(&root->fs_info->trans_mutex);
-        if (root->last_trans == trans->transid) {
-                mutex_unlock(&root->fs_info->trans_mutex);
-                return 0;
-        }
-
-        record_root_in_trans(trans, root);
-        mutex_unlock(&root->fs_info->trans_mutex);
-        return 0;
-}
-
 /* wait for commit against the current transaction to become unblocked
  * when this is done, it is safe to start a new transaction, but the current
  * transaction might not be fully on disk.
@@ -140,21 +156,23 @@ static void wait_current_trans(struct btrfs_root *root)
 {
         struct btrfs_transaction *cur_trans;
 
+        spin_lock(&root->fs_info->trans_lock);
         cur_trans = root->fs_info->running_transaction;
         if (cur_trans && cur_trans->blocked) {
                 DEFINE_WAIT(wait);
                 atomic_inc(&cur_trans->use_count);
+                spin_unlock(&root->fs_info->trans_lock);
                 while (1) {
                         prepare_to_wait(&root->fs_info->transaction_wait, &wait,
                                         TASK_UNINTERRUPTIBLE);
                         if (!cur_trans->blocked)
                                 break;
-                        mutex_unlock(&root->fs_info->trans_mutex);
                         schedule();
-                        mutex_lock(&root->fs_info->trans_mutex);
                 }
                 finish_wait(&root->fs_info->transaction_wait, &wait);
                 put_transaction(cur_trans);
+        } else {
+                spin_unlock(&root->fs_info->trans_lock);
         }
 }
 
@@ -167,10 +185,16 @@ enum btrfs_trans_type {
 
 static int may_wait_transaction(struct btrfs_root *root, int type)
 {
-        if (!root->fs_info->log_root_recovering &&
-            ((type == TRANS_START && !root->fs_info->open_ioctl_trans) ||
-             type == TRANS_USERSPACE))
+        if (root->fs_info->log_root_recovering)
+                return 0;
+
+        if (type == TRANS_USERSPACE)
+                return 1;
+
+        if (type == TRANS_START &&
+            !atomic_read(&root->fs_info->open_ioctl_trans))
                 return 1;
+
         return 0;
 }
 
@@ -184,36 +208,44 @@ static struct btrfs_trans_handle *start_transaction(struct btrfs_root *root,
 
         if (root->fs_info->fs_state & BTRFS_SUPER_FLAG_ERROR)
                 return ERR_PTR(-EROFS);
+
+        if (current->journal_info) {
+                WARN_ON(type != TRANS_JOIN && type != TRANS_JOIN_NOLOCK);
+                h = current->journal_info;
+                h->use_count++;
+                h->orig_rsv = h->block_rsv;
+                h->block_rsv = NULL;
+                goto got_it;
+        }
 again:
         h = kmem_cache_alloc(btrfs_trans_handle_cachep, GFP_NOFS);
         if (!h)
                 return ERR_PTR(-ENOMEM);
 
-        if (type != TRANS_JOIN_NOLOCK)
-                mutex_lock(&root->fs_info->trans_mutex);
         if (may_wait_transaction(root, type))
                 wait_current_trans(root);
 
-        ret = join_transaction(root);
+        do {
+                ret = join_transaction(root, type == TRANS_JOIN_NOLOCK);
+                if (ret == -EBUSY)
+                        wait_current_trans(root);
+        } while (ret == -EBUSY);
+
         if (ret < 0) {
                 kmem_cache_free(btrfs_trans_handle_cachep, h);
-                if (type != TRANS_JOIN_NOLOCK)
-                        mutex_unlock(&root->fs_info->trans_mutex);
                 return ERR_PTR(ret);
         }
 
         cur_trans = root->fs_info->running_transaction;
-        atomic_inc(&cur_trans->use_count);
-        if (type != TRANS_JOIN_NOLOCK)
-                mutex_unlock(&root->fs_info->trans_mutex);
 
         h->transid = cur_trans->transid;
         h->transaction = cur_trans;
         h->blocks_used = 0;
-        h->block_group = 0;
         h->bytes_reserved = 0;
         h->delayed_ref_updates = 0;
+        h->use_count = 1;
         h->block_rsv = NULL;
+        h->orig_rsv = NULL;
 
         smp_mb();
         if (cur_trans->blocked && may_wait_transaction(root, type)) {
@@ -241,11 +273,8 @@ again:
                 }
         }
 
-        if (type != TRANS_JOIN_NOLOCK)
-                mutex_lock(&root->fs_info->trans_mutex);
-        record_root_in_trans(h, root);
-        if (type != TRANS_JOIN_NOLOCK)
-                mutex_unlock(&root->fs_info->trans_mutex);
+got_it:
+        btrfs_record_root_in_trans(h, root);
 
         if (!current->journal_info && type != TRANS_USERSPACE)
                 current->journal_info = h;
@@ -257,22 +286,19 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
 {
         return start_transaction(root, num_items, TRANS_START);
 }
-struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root,
-                                                   int num_blocks)
+struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
 {
         return start_transaction(root, 0, TRANS_JOIN);
 }
 
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root,
-                                                          int num_blocks)
+struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root)
 {
         return start_transaction(root, 0, TRANS_JOIN_NOLOCK);
 }
 
-struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r,
-                                                         int num_blocks)
+struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root)
 {
-        return start_transaction(r, 0, TRANS_USERSPACE);
+        return start_transaction(root, 0, TRANS_USERSPACE);
 }
 
 /* wait for a transaction commit to be fully complete */
@@ -280,17 +306,13 @@ static noinline int wait_for_commit(struct btrfs_root *root,
                                     struct btrfs_transaction *commit)
 {
         DEFINE_WAIT(wait);
-        mutex_lock(&root->fs_info->trans_mutex);
         while (!commit->commit_done) {
                 prepare_to_wait(&commit->commit_wait, &wait,
                                 TASK_UNINTERRUPTIBLE);
                 if (commit->commit_done)
                         break;
-                mutex_unlock(&root->fs_info->trans_mutex);
                 schedule();
-                mutex_lock(&root->fs_info->trans_mutex);
         }
-        mutex_unlock(&root->fs_info->trans_mutex);
         finish_wait(&commit->commit_wait, &wait);
         return 0;
 }
@@ -300,59 +322,56 @@ int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid)
         struct btrfs_transaction *cur_trans = NULL, *t;
         int ret;
 
-        mutex_lock(&root->fs_info->trans_mutex);
-
         ret = 0;
         if (transid) {
                 if (transid <= root->fs_info->last_trans_committed)
-                        goto out_unlock;
+                        goto out;
 
                 /* find specified transaction */
+                spin_lock(&root->fs_info->trans_lock);
                 list_for_each_entry(t, &root->fs_info->trans_list, list) {
                         if (t->transid == transid) {
                                 cur_trans = t;
+                                atomic_inc(&cur_trans->use_count);
                                 break;
                         }
                         if (t->transid > transid)
                                 break;
                 }
+                spin_unlock(&root->fs_info->trans_lock);
                 ret = -EINVAL;
                 if (!cur_trans)
-                        goto out_unlock;  /* bad transid */
+                        goto out;  /* bad transid */
         } else {
                 /* find newest transaction that is committing | committed */
+                spin_lock(&root->fs_info->trans_lock);
                 list_for_each_entry_reverse(t, &root->fs_info->trans_list,
                                             list) {
                         if (t->in_commit) {
                                 if (t->commit_done)
-                                        goto out_unlock;
+                                        goto out;
                                 cur_trans = t;
+                                atomic_inc(&cur_trans->use_count);
                                 break;
                         }
                 }
+                spin_unlock(&root->fs_info->trans_lock);
                 if (!cur_trans)
-                        goto out_unlock;  /* nothing committing|committed */
+                        goto out;  /* nothing committing|committed */
         }
 
-        atomic_inc(&cur_trans->use_count);
-        mutex_unlock(&root->fs_info->trans_mutex);
-
         wait_for_commit(root, cur_trans);
 
-        mutex_lock(&root->fs_info->trans_mutex);
         put_transaction(cur_trans);
         ret = 0;
-out_unlock:
-        mutex_unlock(&root->fs_info->trans_mutex);
+out:
         return ret;
 }
 
 void btrfs_throttle(struct btrfs_root *root)
 {
-        mutex_lock(&root->fs_info->trans_mutex);
-        if (!root->fs_info->open_ioctl_trans)
+        if (!atomic_read(&root->fs_info->open_ioctl_trans))
                 wait_current_trans(root);
-        mutex_unlock(&root->fs_info->trans_mutex);
 }
 
 static int should_end_transaction(struct btrfs_trans_handle *trans,
@@ -370,6 +389,7 @@ int btrfs_should_end_transaction(struct btrfs_trans_handle *trans,
         struct btrfs_transaction *cur_trans = trans->transaction;
         int updates;
 
+        smp_mb();
         if (cur_trans->blocked || cur_trans->delayed_refs.flushing)
                 return 1;
 
@@ -388,6 +408,11 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
         struct btrfs_fs_info *info = root->fs_info;
         int count = 0;
 
+        if (--trans->use_count) {
+                trans->block_rsv = trans->orig_rsv;
+                return 0;
+        }
+
         while (count < 4) {
                 unsigned long cur = trans->delayed_ref_updates;
                 trans->delayed_ref_updates = 0;
@@ -410,9 +435,11 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 
         btrfs_trans_release_metadata(trans, root);
 
-        if (lock && !root->fs_info->open_ioctl_trans &&
-            should_end_transaction(trans, root))
+        if (lock && !atomic_read(&root->fs_info->open_ioctl_trans) &&
+            should_end_transaction(trans, root)) {
                 trans->transaction->blocked = 1;
+                smp_wmb();
+        }
 
         if (lock && cur_trans->blocked && !cur_trans->in_commit) {
                 if (throttle)
@@ -703,9 +730,9 @@ static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans,
  */
 int btrfs_add_dead_root(struct btrfs_root *root)
 {
-        mutex_lock(&root->fs_info->trans_mutex);
+        spin_lock(&root->fs_info->trans_lock);
         list_add(&root->root_list, &root->fs_info->dead_roots);
-        mutex_unlock(&root->fs_info->trans_mutex);
+        spin_unlock(&root->fs_info->trans_lock);
         return 0;
 }
 
@@ -721,6 +748,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
         int ret;
         int err = 0;
 
+        spin_lock(&fs_info->fs_roots_radix_lock);
         while (1) {
                 ret = radix_tree_gang_lookup_tag(&fs_info->fs_roots_radix,
                                                  (void **)gang, 0,
@@ -733,6 +761,7 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
                         radix_tree_tag_clear(&fs_info->fs_roots_radix,
                                         (unsigned long)root->root_key.objectid,
                                         BTRFS_ROOT_TRANS_TAG);
+                        spin_unlock(&fs_info->fs_roots_radix_lock);
 
                         btrfs_free_log(trans, root);
                         btrfs_update_reloc_root(trans, root);
@@ -753,10 +782,12 @@ static noinline int commit_fs_roots(struct btrfs_trans_handle *trans,
                         err = btrfs_update_root(trans, fs_info->tree_root,
                                                 &root->root_key,
                                                 &root->root_item);
+                        spin_lock(&fs_info->fs_roots_radix_lock);
                         if (err)
                                 break;
                 }
         }
+        spin_unlock(&fs_info->fs_roots_radix_lock);
         return err;
 }
 
@@ -786,7 +817,7 @@ int btrfs_defrag_root(struct btrfs_root *root, int cacheonly)
                 btrfs_btree_balance_dirty(info->tree_root, nr);
                 cond_resched();
 
-                if (root->fs_info->closing || ret != -EAGAIN)
+                if (btrfs_fs_closing(root->fs_info) || ret != -EAGAIN)
                         break;
         }
         root->defrag_running = 0;
@@ -851,7 +882,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
         parent = dget_parent(dentry);
         parent_inode = parent->d_inode;
         parent_root = BTRFS_I(parent_inode)->root;
-        record_root_in_trans(trans, parent_root);
+        btrfs_record_root_in_trans(trans, parent_root);
 
         /*
          * insert the directory item
@@ -869,7 +900,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
         ret = btrfs_update_inode(trans, parent_root, parent_inode);
         BUG_ON(ret);
 
-        record_root_in_trans(trans, root);
+        btrfs_record_root_in_trans(trans, root);
         btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
         memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
         btrfs_check_and_init_root_item(new_root_item);
@@ -967,20 +998,20 @@ static void update_super_roots(struct btrfs_root *root)
 int btrfs_transaction_in_commit(struct btrfs_fs_info *info)
 {
         int ret = 0;
-        spin_lock(&info->new_trans_lock);
+        spin_lock(&info->trans_lock);
         if (info->running_transaction)
                 ret = info->running_transaction->in_commit;
-        spin_unlock(&info->new_trans_lock);
+        spin_unlock(&info->trans_lock);
         return ret;
 }
 
 int btrfs_transaction_blocked(struct btrfs_fs_info *info)
 {
         int ret = 0;
-        spin_lock(&info->new_trans_lock);
+        spin_lock(&info->trans_lock);
         if (info->running_transaction)
                 ret = info->running_transaction->blocked;
-        spin_unlock(&info->new_trans_lock);
+        spin_unlock(&info->trans_lock);
         return ret;
 }
 
@@ -1004,9 +1035,7 @@ static void wait_current_trans_commit_start(struct btrfs_root *root,
                                     &wait);
                         break;
                 }
-                mutex_unlock(&root->fs_info->trans_mutex);
                 schedule();
-                mutex_lock(&root->fs_info->trans_mutex);
                 finish_wait(&root->fs_info->transaction_blocked_wait, &wait);
         }
 }
@@ -1032,9 +1061,7 @@ static void wait_current_trans_commit_start_and_unblock(struct btrfs_root *root,
                                     &wait);
                         break;
                 }
-                mutex_unlock(&root->fs_info->trans_mutex);
                 schedule();
-                mutex_lock(&root->fs_info->trans_mutex);
                 finish_wait(&root->fs_info->transaction_wait,
                             &wait);
         }
@@ -1072,7 +1099,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 
         INIT_DELAYED_WORK(&ac->work, do_async_commit);
         ac->root = root;
-        ac->newtrans = btrfs_join_transaction(root, 0);
+        ac->newtrans = btrfs_join_transaction(root);
         if (IS_ERR(ac->newtrans)) {
                 int err = PTR_ERR(ac->newtrans);
                 kfree(ac);
@@ -1080,22 +1107,18 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
         }
 
         /* take transaction reference */
-        mutex_lock(&root->fs_info->trans_mutex);
         cur_trans = trans->transaction;
         atomic_inc(&cur_trans->use_count);
-        mutex_unlock(&root->fs_info->trans_mutex);
 
         btrfs_end_transaction(trans, root);
         schedule_delayed_work(&ac->work, 0);
 
         /* wait for transaction to start and unblock */
-        mutex_lock(&root->fs_info->trans_mutex);
         if (wait_for_unblock)
                 wait_current_trans_commit_start_and_unblock(root, cur_trans);
         else
                 wait_current_trans_commit_start(root, cur_trans);
         put_transaction(cur_trans);
-        mutex_unlock(&root->fs_info->trans_mutex);
 
         return 0;
 }
@@ -1139,38 +1162,41 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
         ret = btrfs_run_delayed_refs(trans, root, 0);
         BUG_ON(ret);
 
-        mutex_lock(&root->fs_info->trans_mutex);
+        spin_lock(&cur_trans->commit_lock);
         if (cur_trans->in_commit) {
+                spin_unlock(&cur_trans->commit_lock);
                 atomic_inc(&cur_trans->use_count);
-                mutex_unlock(&root->fs_info->trans_mutex);
                 btrfs_end_transaction(trans, root);
 
                 ret = wait_for_commit(root, cur_trans);
                 BUG_ON(ret);
 
-                mutex_lock(&root->fs_info->trans_mutex);
                 put_transaction(cur_trans);
-                mutex_unlock(&root->fs_info->trans_mutex);
 
                 return 0;
         }
 
         trans->transaction->in_commit = 1;
         trans->transaction->blocked = 1;
+        spin_unlock(&cur_trans->commit_lock);
         wake_up(&root->fs_info->transaction_blocked_wait);
 
+        spin_lock(&root->fs_info->trans_lock);
         if (cur_trans->list.prev != &root->fs_info->trans_list) {
                 prev_trans = list_entry(cur_trans->list.prev,
                                         struct btrfs_transaction, list);
                 if (!prev_trans->commit_done) {
                         atomic_inc(&prev_trans->use_count);
-                        mutex_unlock(&root->fs_info->trans_mutex);
+                        spin_unlock(&root->fs_info->trans_lock);
 
                         wait_for_commit(root, prev_trans);
 
-                        mutex_lock(&root->fs_info->trans_mutex);
                         put_transaction(prev_trans);
+                } else {
+                        spin_unlock(&root->fs_info->trans_lock);
                 }
+        } else {
+                spin_unlock(&root->fs_info->trans_lock);
         }
 
         if (now < cur_trans->start_time || now - cur_trans->start_time < 1)
@@ -1178,12 +1204,12 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
         do {
                 int snap_pending = 0;
+
                 joined = cur_trans->num_joined;
                 if (!list_empty(&trans->transaction->pending_snapshots))
                         snap_pending = 1;
 
                 WARN_ON(cur_trans != trans->transaction);
-                mutex_unlock(&root->fs_info->trans_mutex);
 
                 if (flush_on_commit || snap_pending) {
                         btrfs_start_delalloc_inodes(root, 1);
@@ -1206,14 +1232,15 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
                 prepare_to_wait(&cur_trans->writer_wait, &wait,
                                 TASK_UNINTERRUPTIBLE);
 
-                smp_mb();
                 if (atomic_read(&cur_trans->num_writers) > 1)
                         schedule_timeout(MAX_SCHEDULE_TIMEOUT);
                 else if (should_grow)
                         schedule_timeout(1);
 
-                mutex_lock(&root->fs_info->trans_mutex);
                 finish_wait(&cur_trans->writer_wait, &wait);
+                spin_lock(&root->fs_info->trans_lock);
+                root->fs_info->trans_no_join = 1;
+                spin_unlock(&root->fs_info->trans_lock);
         } while (atomic_read(&cur_trans->num_writers) > 1 ||
                  (should_grow && cur_trans->num_joined != joined));
 
@@ -1258,9 +1285,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
         btrfs_prepare_extent_commit(trans, root);
 
         cur_trans = root->fs_info->running_transaction;
-        spin_lock(&root->fs_info->new_trans_lock);
-        root->fs_info->running_transaction = NULL;
-        spin_unlock(&root->fs_info->new_trans_lock);
 
         btrfs_set_root_node(&root->fs_info->tree_root->root_item,
                             root->fs_info->tree_root->node);
@@ -1281,10 +1305,13 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
                sizeof(root->fs_info->super_copy));
 
         trans->transaction->blocked = 0;
+        spin_lock(&root->fs_info->trans_lock);
+        root->fs_info->running_transaction = NULL;
+        root->fs_info->trans_no_join = 0;
+        spin_unlock(&root->fs_info->trans_lock);
 
         wake_up(&root->fs_info->transaction_wait);
 
-        mutex_unlock(&root->fs_info->trans_mutex);
         ret = btrfs_write_and_wait_transaction(trans, root);
         BUG_ON(ret);
         write_ctree_super(trans, root, 0);
@@ -1297,22 +1324,21 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
         btrfs_finish_extent_commit(trans, root);
 
-        mutex_lock(&root->fs_info->trans_mutex);
-
         cur_trans->commit_done = 1;
 
         root->fs_info->last_trans_committed = cur_trans->transid;
 
         wake_up(&cur_trans->commit_wait);
 
+        spin_lock(&root->fs_info->trans_lock);
         list_del_init(&cur_trans->list);
+        spin_unlock(&root->fs_info->trans_lock);
+
         put_transaction(cur_trans);
         put_transaction(cur_trans);
 
         trace_btrfs_transaction_commit(root);
 
-        mutex_unlock(&root->fs_info->trans_mutex);
-
         btrfs_scrub_continue(root);
 
         if (current->journal_info == trans)
@@ -1334,9 +1360,9 @@ int btrfs_clean_old_snapshots(struct btrfs_root *root)
         LIST_HEAD(list);
         struct btrfs_fs_info *fs_info = root->fs_info;
 
-        mutex_lock(&fs_info->trans_mutex);
+        spin_lock(&fs_info->trans_lock);
         list_splice_init(&fs_info->dead_roots, &list);
-        mutex_unlock(&fs_info->trans_mutex);
+        spin_unlock(&fs_info->trans_lock);
 
         while (!list_empty(&list)) {
                 root = list_entry(list.next, struct btrfs_root, root_list);
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 804c88639e5d..02564e6230ac 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -28,10 +28,12 @@ struct btrfs_transaction {
          * transaction can end
          */
         atomic_t num_writers;
+        atomic_t use_count;
 
         unsigned long num_joined;
+
+        spinlock_t commit_lock;
         int in_commit;
-        atomic_t use_count;
         int commit_done;
         int blocked;
         struct list_head list;
@@ -45,13 +47,14 @@ struct btrfs_transaction {
 
 struct btrfs_trans_handle {
         u64 transid;
-        u64 block_group;
         u64 bytes_reserved;
+        unsigned long use_count;
         unsigned long blocks_reserved;
         unsigned long blocks_used;
         unsigned long delayed_ref_updates;
         struct btrfs_transaction *transaction;
         struct btrfs_block_rsv *block_rsv;
+        struct btrfs_block_rsv *orig_rsv;
 };
 
 struct btrfs_pending_snapshot {
@@ -66,19 +69,6 @@ struct btrfs_pending_snapshot {
         struct list_head list;
 };
 
-static inline void btrfs_set_trans_block_group(struct btrfs_trans_handle *trans,
-                                               struct inode *inode)
-{
-        trans->block_group = BTRFS_I(inode)->block_group;
-}
-
-static inline void btrfs_update_inode_block_group(
-                                          struct btrfs_trans_handle *trans,
-                                          struct inode *inode)
-{
-        BTRFS_I(inode)->block_group = trans->block_group;
-}
-
 static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans,
                                               struct inode *inode)
 {
@@ -92,12 +82,9 @@ int btrfs_end_transaction_nolock(struct btrfs_trans_handle *trans,
                                  struct btrfs_root *root);
 struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
                                                    int num_items);
-struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root,
-                                                  int num_blocks);
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root,
-                                                          int num_blocks);
-struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *r,
-                                                         int num_blocks);
+struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root);
 int btrfs_wait_for_commit(struct btrfs_root *root, u64 transid);
 int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans,
                                      struct btrfs_root *root);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index c48214ef5c09..da541dfca2e3 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -504,7 +504,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
                 BUG_ON(!new_device);
                 memcpy(new_device, device, sizeof(*new_device));
                 new_device->name = kstrdup(device->name, GFP_NOFS);
-                BUG_ON(!new_device->name);
+                BUG_ON(device->name && !new_device->name);
                 new_device->bdev = NULL;
                 new_device->writeable = 0;
                 new_device->in_fs_metadata = 0;
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index f3107e4b4d56..5366fe452ab0 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -158,8 +158,6 @@ int __btrfs_setxattr(struct btrfs_trans_handle *trans,
         if (IS_ERR(trans))
                 return PTR_ERR(trans);
 
-        btrfs_set_trans_block_group(trans, inode);
-
         ret = do_setxattr(trans, inode, name, value, size, flags);
         if (ret)
                 goto out;
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/partitions/check.c b/fs/partitions/check.c
index f82e762eeca2..d545e97d99c3 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -255,13 +255,7 @@ ssize_t part_discard_alignment_show(struct device *dev,
                                    struct device_attribute *attr, char *buf)
 {
         struct hd_struct *p = dev_to_part(dev);
-        struct gendisk *disk = dev_to_disk(dev);
-        unsigned int alignment = 0;
-
-        if (disk->queue)
-                alignment = queue_limit_discard_alignment(&disk->queue->limits,
-                                                                p->start_sect);
-        return sprintf(buf, "%u\n", alignment);
+        return sprintf(buf, "%u\n", p->discard_alignment);
 }
 
 ssize_t part_stat_show(struct device *dev,
@@ -455,6 +449,8 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
         p->start_sect = start;
         p->alignment_offset =
                 queue_limit_alignment_offset(&disk->queue->limits, start);
+        p->discard_alignment =
+                queue_limit_discard_alignment(&disk->queue->limits, start);
         p->nr_sects = len;
         p->partno = partno;
         p->policy = get_disk_ro(disk);
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/fs/ubifs/io.c b/fs/ubifs/io.c
index 166951e0dcd3..3be645e012c9 100644
--- a/fs/ubifs/io.c
+++ b/fs/ubifs/io.c
@@ -581,6 +581,7 @@ int ubifs_wbuf_write_nolock(struct ubifs_wbuf *wbuf, void *buf, int len)
         ubifs_assert(wbuf->size % c->min_io_size == 0);
         ubifs_assert(mutex_is_locked(&wbuf->io_mutex));
         ubifs_assert(!c->ro_media && !c->ro_mount);
+        ubifs_assert(!c->space_fixup);
         if (c->leb_size - wbuf->offs >= c->max_write_size)
                 ubifs_assert(!((wbuf->offs + wbuf->size) % c->max_write_size));
 
@@ -759,6 +760,7 @@ int ubifs_write_node(struct ubifs_info *c, void *buf, int len, int lnum,
         ubifs_assert(lnum >= 0 && lnum < c->leb_cnt && offs >= 0);
         ubifs_assert(offs % c->min_io_size == 0 && offs < c->leb_size);
         ubifs_assert(!c->ro_media && !c->ro_mount);
+        ubifs_assert(!c->space_fixup);
 
         if (c->ro_error)
                 return -EROFS;
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 34b1679e6e3a..cef0460f4c54 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -669,6 +669,7 @@ out_free:
 
 out_release:
         release_head(c, BASEHD);
+        kfree(dent);
 out_ro:
         ubifs_ro_mode(c, err);
         if (last_reference)
diff --git a/fs/ubifs/orphan.c b/fs/ubifs/orphan.c
index bd644bf587a8..a5422fffbd69 100644
--- a/fs/ubifs/orphan.c
+++ b/fs/ubifs/orphan.c
@@ -674,7 +674,7 @@ static int kill_orphans(struct ubifs_info *c)
                 if (IS_ERR(sleb)) {
                         if (PTR_ERR(sleb) == -EUCLEAN)
                                 sleb = ubifs_recover_leb(c, lnum, 0,
-                                                         c->sbuf, 0);
+                                                         c->sbuf, -1);
                         if (IS_ERR(sleb)) {
                                 err = PTR_ERR(sleb);
                                 break;
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index 731d9e2e7b50..783d8e0beb76 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -564,19 +564,15 @@ static int fix_unclean_leb(struct ubifs_info *c, struct ubifs_scan_leb *sleb,
 }
 
 /**
- * drop_last_node - drop the last node or group of nodes.
+ * drop_last_group - drop the last group of nodes.
  * @sleb: scanned LEB information
  * @offs: offset of dropped nodes is returned here
- * @grouped: non-zero if whole group of nodes have to be dropped
  *
  * This is a helper function for 'ubifs_recover_leb()' which drops the last
- * node of the scanned LEB or the last group of nodes if @grouped is not zero.
- * This function returns %1 if a node was dropped and %0 otherwise.
+ * group of nodes of the scanned LEB.
  */
-static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
+static void drop_last_group(struct ubifs_scan_leb *sleb, int *offs)
 {
-        int dropped = 0;
-
         while (!list_empty(&sleb->nodes)) {
                 struct ubifs_scan_node *snod;
                 struct ubifs_ch *ch;
@@ -585,17 +581,40 @@ static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
                                   list);
                 ch = snod->node;
                 if (ch->group_type != UBIFS_IN_NODE_GROUP)
-                        return dropped;
-                dbg_rcvry("dropping node at %d:%d", sleb->lnum, snod->offs);
+                        break;
+
+                dbg_rcvry("dropping grouped node at %d:%d",
+                          sleb->lnum, snod->offs);
+                *offs = snod->offs;
+                list_del(&snod->list);
+                kfree(snod);
+                sleb->nodes_cnt -= 1;
+        }
+}
+
+/**
+ * drop_last_node - drop the last node.
+ * @sleb: scanned LEB information
+ * @offs: offset of dropped nodes is returned here
+ * @grouped: non-zero if whole group of nodes have to be dropped
+ *
+ * This is a helper function for 'ubifs_recover_leb()' which drops the last
+ * node of the scanned LEB.
+ */
+static void drop_last_node(struct ubifs_scan_leb *sleb, int *offs)
+{
+        struct ubifs_scan_node *snod;
+
+        if (!list_empty(&sleb->nodes)) {
+                snod = list_entry(sleb->nodes.prev, struct ubifs_scan_node,
+                                  list);
+
+                dbg_rcvry("dropping last node at %d:%d", sleb->lnum, snod->offs);
                 *offs = snod->offs;
                 list_del(&snod->list);
                 kfree(snod);
                 sleb->nodes_cnt -= 1;
-                dropped = 1;
-                if (!grouped)
-                        break;
         }
-        return dropped;
 }
 
 /**
@@ -604,7 +623,8 @@ static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
  * @lnum: LEB number
  * @offs: offset
  * @sbuf: LEB-sized buffer to use
- * @grouped: nodes may be grouped for recovery
+ * @jhead: journal head number this LEB belongs to (%-1 if the LEB does not
+ *         belong to any journal head)
  *
  * This function does a scan of a LEB, but caters for errors that might have
  * been caused by the unclean unmount from which we are attempting to recover.
@@ -612,13 +632,14 @@ static int drop_last_node(struct ubifs_scan_leb *sleb, int *offs, int grouped)
  * found, and a negative error code in case of failure.
  */
 struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
-                                         int offs, void *sbuf, int grouped)
+                                         int offs, void *sbuf, int jhead)
 {
         int ret = 0, err, len = c->leb_size - offs, start = offs, min_io_unit;
+        int grouped = jhead == -1 ? 0 : c->jheads[jhead].grouped;
         struct ubifs_scan_leb *sleb;
         void *buf = sbuf + offs;
 
-        dbg_rcvry("%d:%d", lnum, offs);
+        dbg_rcvry("%d:%d, jhead %d, grouped %d", lnum, offs, jhead, grouped);
 
         sleb = ubifs_start_scan(c, lnum, offs, sbuf);
         if (IS_ERR(sleb))
@@ -635,7 +656,7 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
                  * Scan quietly until there is an error from which we cannot
                  * recover
                  */
-                ret = ubifs_scan_a_node(c, buf, len, lnum, offs, 0);
+                ret = ubifs_scan_a_node(c, buf, len, lnum, offs, 1);
                 if (ret == SCANNED_A_NODE) {
                         /* A valid node, and not a padding node */
                         struct ubifs_ch *ch = buf;
@@ -695,59 +716,62 @@ struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
                  * If nodes are grouped, always drop the incomplete group at
                  * the end.
                  */
-                drop_last_node(sleb, &offs, 1);
+                drop_last_group(sleb, &offs);
 
-        /*
-         * While we are in the middle of the same min. I/O unit keep dropping
-         * nodes. So basically, what we want is to make sure that the last min.
-         * I/O unit where we saw the corruption is dropped completely with all
-         * the uncorrupted node which may possibly sit there.
-         *
-         * In other words, let's name the min. I/O unit where the corruption
-         * starts B, and the previous min. I/O unit A. The below code tries to
-         * deal with a situation when half of B contains valid nodes or the end
-         * of a valid node, and the second half of B contains corrupted data or
-         * garbage. This means that UBIFS had been writing to B just before the
-         * power cut happened. I do not know how realistic is this scenario
-         * that half of the min. I/O unit had been written successfully and the
-         * other half not, but this is possible in our 'failure mode emulation'
-         * infrastructure at least.
-         *
-         * So what is the problem, why we need to drop those nodes? Whey can't
-         * we just clean-up the second half of B by putting a padding node
-         * there? We can, and this works fine with one exception which was
-         * reproduced with power cut emulation testing and happens extremely
-         * rarely. The description follows, but it is worth noting that that is
-         * only about the GC head, so we could do this trick only if the bud
-         * belongs to the GC head, but it does not seem to be worth an
-         * additional "if" statement.
-         *
-         * So, imagine the file-system is full, we run GC which is moving valid
-         * nodes from LEB X to LEB Y (obviously, LEB Y is the current GC head
-         * LEB). The @c->gc_lnum is -1, which means that GC will retain LEB X
-         * and will try to continue. Imagine that LEB X is currently the
-         * dirtiest LEB, and the amount of used space in LEB Y is exactly the
-         * same as amount of free space in LEB X.
-         *
-         * And a power cut happens when nodes are moved from LEB X to LEB Y. We
-         * are here trying to recover LEB Y which is the GC head LEB. We find
-         * the min. I/O unit B as described above. Then we clean-up LEB Y by
-         * padding min. I/O unit. And later 'ubifs_rcvry_gc_commit()' function
-         * fails, because it cannot find a dirty LEB which could be GC'd into
-         * LEB Y! Even LEB X does not match because the amount of valid nodes
-         * there does not fit the free space in LEB Y any more! And this is
-         * because of the padding node which we added to LEB Y. The
-         * user-visible effect of this which I once observed and analysed is
-         * that we cannot mount the file-system with -ENOSPC error.
-         *
-         * So obviously, to make sure that situation does not happen we should
-         * free min. I/O unit B in LEB Y completely and the last used min. I/O
-         * unit in LEB Y should be A. This is basically what the below code
-         * tries to do.
-         */
-        while (min_io_unit == round_down(offs, c->min_io_size) &&
-               min_io_unit != offs &&
-               drop_last_node(sleb, &offs, grouped));
+        if (jhead == GCHD) {
+                /*
+                 * If this LEB belongs to the GC head then while we are in the
+                 * middle of the same min. I/O unit keep dropping nodes. So
+                 * basically, what we want is to make sure that the last min.
+                 * I/O unit where we saw the corruption is dropped completely
+                 * with all the uncorrupted nodes which may possibly sit there.
+                 *
+                 * In other words, let's name the min. I/O unit where the
+                 * corruption starts B, and the previous min. I/O unit A. The
+                 * below code tries to deal with a situation when half of B
+                 * contains valid nodes or the end of a valid node, and the
+                 * second half of B contains corrupted data or garbage. This
+                 * means that UBIFS had been writing to B just before the power
+                 * cut happened. I do not know how realistic is this scenario
+                 * that half of the min. I/O unit had been written successfully
+                 * and the other half not, but this is possible in our 'failure
+                 * mode emulation' infrastructure at least.
+                 *
+                 * So what is the problem, why we need to drop those nodes? Why
+                 * can't we just clean-up the second half of B by putting a
+                 * padding node there? We can, and this works fine with one
+                 * exception which was reproduced with power cut emulation
+                 * testing and happens extremely rarely.
+                 *
+                 * Imagine the file-system is full, we run GC which starts
+                 * moving valid nodes from LEB X to LEB Y (obviously, LEB Y is
+                 * the current GC head LEB). The @c->gc_lnum is -1, which means
+                 * that GC will retain LEB X and will try to continue. Imagine
+                 * that LEB X is currently the dirtiest LEB, and the amount of
+                 * used space in LEB Y is exactly the same as amount of free
+                 * space in LEB X.
+                 *
+                 * And a power cut happens when nodes are moved from LEB X to
+                 * LEB Y. We are here trying to recover LEB Y which is the GC
+                 * head LEB. We find the min. I/O unit B as described above.
+                 * Then we clean-up LEB Y by padding min. I/O unit. And later
+                 * 'ubifs_rcvry_gc_commit()' function fails, because it cannot
+                 * find a dirty LEB which could be GC'd into LEB Y! Even LEB X
+                 * does not match because the amount of valid nodes there does
+                 * not fit the free space in LEB Y any more! And this is
+                 * because of the padding node which we added to LEB Y. The
+                 * user-visible effect of this which I once observed and
+                 * analysed is that we cannot mount the file-system with
+                 * -ENOSPC error.
+                 *
+                 * So obviously, to make sure that situation does not happen we
+                 * should free min. I/O unit B in LEB Y completely and the last
+                 * used min. I/O unit in LEB Y should be A. This is basically
+                 * what the below code tries to do.
+                 */
+                while (offs > min_io_unit)
+                        drop_last_node(sleb, &offs);
+        }
 
         buf = sbuf + offs;
         len = c->leb_size - offs;
@@ -881,7 +905,7 @@ struct ubifs_scan_leb *ubifs_recover_log_leb(struct ubifs_info *c, int lnum,
                 }
                 ubifs_scan_destroy(sleb);
         }
-        return ubifs_recover_leb(c, lnum, offs, sbuf, 0);
+        return ubifs_recover_leb(c, lnum, offs, sbuf, -1);
 }
 
 /**
diff --git a/fs/ubifs/replay.c b/fs/ubifs/replay.c
index 6617280d1679..5e97161ce4d3 100644
--- a/fs/ubifs/replay.c
+++ b/fs/ubifs/replay.c
@@ -557,8 +557,7 @@ static int replay_bud(struct ubifs_info *c, struct bud_entry *b)
                  * these LEBs could possibly be written to at the power cut
                  * time.
                  */
-                sleb = ubifs_recover_leb(c, lnum, offs, c->sbuf,
-                                         b->bud->jhead != GCHD);
+                sleb = ubifs_recover_leb(c, lnum, offs, c->sbuf, b->bud->jhead);
         else
                 sleb = ubifs_scan(c, lnum, offs, c->sbuf, 0);
         if (IS_ERR(sleb))
diff --git a/fs/ubifs/shrinker.c b/fs/ubifs/shrinker.c
index ca953a945029..9e1d05666fed 100644
--- a/fs/ubifs/shrinker.c
+++ b/fs/ubifs/shrinker.c
@@ -284,7 +284,11 @@ int ubifs_shrinker(struct shrinker *shrink, struct shrink_control *sc)
         long clean_zn_cnt = atomic_long_read(&ubifs_clean_zn_cnt);
 
         if (nr == 0)
-                return clean_zn_cnt;
+                /*
+                 * Due to the way UBIFS updates the clean znode counter it may
+                 * temporarily be negative.
+                 */
+                return clean_zn_cnt >= 0 ? clean_zn_cnt : 1;
 
         if (!clean_zn_cnt) {
                 /*
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index 1ab0d22e4c94..b5aeb5a8ebed 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -811,15 +811,18 @@ static int alloc_wbufs(struct ubifs_info *c)
 
                 c->jheads[i].wbuf.sync_callback = &bud_wbuf_callback;
                 c->jheads[i].wbuf.jhead = i;
+                c->jheads[i].grouped = 1;
         }
 
         c->jheads[BASEHD].wbuf.dtype = UBI_SHORTTERM;
         /*
          * Garbage Collector head likely contains long-term data and
-         * does not need to be synchronized by timer.
+         * does not need to be synchronized by timer. Also GC head nodes are
+         * not grouped.
          */
         c->jheads[GCHD].wbuf.dtype = UBI_LONGTERM;
         c->jheads[GCHD].wbuf.no_timer = 1;
+        c->jheads[GCHD].grouped = 0;
 
         return 0;
 }
@@ -1284,12 +1287,25 @@ static int mount_ubifs(struct ubifs_info *c)
         if ((c->mst_node->flags & cpu_to_le32(UBIFS_MST_DIRTY)) != 0) {
                 ubifs_msg("recovery needed");
                 c->need_recovery = 1;
-                if (!c->ro_mount) {
-                        err = ubifs_recover_inl_heads(c, c->sbuf);
-                        if (err)
-                                goto out_master;
-                }
-        } else if (!c->ro_mount) {
+        }
+
+        if (c->need_recovery && !c->ro_mount) {
+                err = ubifs_recover_inl_heads(c, c->sbuf);
+                if (err)
+                        goto out_master;
+        }
+
+        err = ubifs_lpt_init(c, 1, !c->ro_mount);
+        if (err)
+                goto out_master;
+
+        if (!c->ro_mount && c->space_fixup) {
+                err = ubifs_fixup_free_space(c);
+                if (err)
+                        goto out_master;
+        }
+
+        if (!c->ro_mount) {
                 /*
                  * Set the "dirty" flag so that if we reboot uncleanly we
                  * will notice this immediately on the next mount.
@@ -1297,13 +1313,9 @@ static int mount_ubifs(struct ubifs_info *c)
                 c->mst_node->flags |= cpu_to_le32(UBIFS_MST_DIRTY);
                 err = ubifs_write_master(c);
                 if (err)
-                        goto out_master;
+                        goto out_lpt;
         }
 
-        err = ubifs_lpt_init(c, 1, !c->ro_mount);
-        if (err)
-                goto out_lpt;
-
         err = dbg_check_idx_size(c, c->bi.old_idx_sz);
         if (err)
                 goto out_lpt;
@@ -1396,12 +1408,6 @@ static int mount_ubifs(struct ubifs_info *c)
         } else
                 ubifs_assert(c->lst.taken_empty_lebs > 0);
 
-        if (!c->ro_mount && c->space_fixup) {
-                err = ubifs_fixup_free_space(c);
-                if (err)
-                        goto out_infos;
-        }
-
         err = dbg_check_filesystem(c);
         if (err)
                 goto out_infos;
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 8119b1fd8d94..91b4213dde84 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -2876,12 +2876,13 @@ static void tnc_destroy_cnext(struct ubifs_info *c)
  */
 void ubifs_tnc_close(struct ubifs_info *c)
 {
-        long clean_freed;
-
         tnc_destroy_cnext(c);
         if (c->zroot.znode) {
-                clean_freed = ubifs_destroy_tnc_subtree(c->zroot.znode);
-                atomic_long_sub(clean_freed, &ubifs_clean_zn_cnt);
+                long n;
+
+                ubifs_destroy_tnc_subtree(c->zroot.znode);
+                n = atomic_long_read(&c->clean_zn_cnt);
+                atomic_long_sub(n, &ubifs_clean_zn_cnt);
         }
         kfree(c->gap_lebs);
         kfree(c->ilebs);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index a70d7b4ffb25..f79983d6f860 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -722,12 +722,14 @@ struct ubifs_bud {
  * struct ubifs_jhead - journal head.
  * @wbuf: head's write-buffer
  * @buds_list: list of bud LEBs belonging to this journal head
+ * @grouped: non-zero if UBIFS groups nodes when writing to this journal head
  *
  * Note, the @buds list is protected by the @c->buds_lock.
  */
 struct ubifs_jhead {
         struct ubifs_wbuf wbuf;
         struct list_head buds_list;
+        unsigned int grouped:1;
 };
 
 /**
@@ -1742,7 +1744,7 @@ struct inode *ubifs_iget(struct super_block *sb, unsigned long inum);
 int ubifs_recover_master_node(struct ubifs_info *c);
 int ubifs_write_rcvrd_mst_node(struct ubifs_info *c);
 struct ubifs_scan_leb *ubifs_recover_leb(struct ubifs_info *c, int lnum,
-                                         int offs, void *sbuf, int grouped);
+                                         int offs, void *sbuf, int jhead);
 struct ubifs_scan_leb *ubifs_recover_log_leb(struct ubifs_info *c, int lnum,
                                              int offs, void *sbuf);
 int ubifs_recover_inl_heads(const struct ubifs_info *c, void *sbuf);
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index ae90e0f63995..4f76959397fa 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -683,9 +683,11 @@ __SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
 __SYSCALL(__NR_syncfs, sys_syncfs)
 #define __NR_setns 268
 __SYSCALL(__NR_setns, sys_setns)
+#define __NR_sendmmsg 269
+__SC_COMP(__NR_sendmmsg, sys_sendmmsg, compat_sys_sendmmsg)
 
 #undef __NR_syscalls
-#define __NR_syscalls 269
+#define __NR_syscalls 270
 
 /*
  * All syscalls below here should go away really,
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/blkdev.h b/include/linux/blkdev.h
index ae9091a68480..1a23722e8878 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1282,8 +1282,8 @@ queue_max_integrity_segments(struct request_queue *q)
 #define blk_get_integrity(a)                    (0)
 #define blk_integrity_compare(a, b)             (0)
 #define blk_integrity_register(a, b)            (0)
-#define blk_integrity_unregister(a)             do { } while (0);
-#define blk_queue_max_integrity_segments(a, b)  do { } while (0);
+#define blk_integrity_unregister(a)             do { } while (0)
+#define blk_queue_max_integrity_segments(a, b)  do { } while (0)
 #define queue_max_integrity_segments(a)         (0)
 #define blk_integrity_merge_rq(a, b, c)         (0)
 #define blk_integrity_merge_bio(a, b, c)        (0)
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/genhd.h b/include/linux/genhd.h
index b78956b3c2e7..300d7582006e 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -100,6 +100,7 @@ struct hd_struct {
         sector_t start_sect;
         sector_t nr_sects;
         sector_t alignment_offset;
+        unsigned int discard_alignment;
         struct device __dev;
         struct kobject *holder_dir;
         int policy, partno;
diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index b2eee5879883..bf56b6f78270 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1003,8 +1003,12 @@ struct ieee80211_ht_info {
 #define WLAN_CAPABILITY_ESS             (1<<0)
 #define WLAN_CAPABILITY_IBSS            (1<<1)
 
-/* A mesh STA sets the ESS and IBSS capability bits to zero */
-#define WLAN_CAPABILITY_IS_MBSS(cap)    \
+/*
+ * A mesh STA sets the ESS and IBSS capability bits to zero.
+ * however, this holds true for p2p probe responses (in the p2p_find
+ * phase) as well.
+ */
+#define WLAN_CAPABILITY_IS_STA_BSS(cap) \
         (!((cap) & (WLAN_CAPABILITY_ESS | WLAN_CAPABILITY_IBSS)))
 
 #define WLAN_CAPABILITY_CF_POLLABLE     (1<<2)
diff --git a/include/linux/if_packet.h b/include/linux/if_packet.h
index 72bfa5a034dd..6d66ce1791a9 100644
--- a/include/linux/if_packet.h
+++ b/include/linux/if_packet.h
@@ -70,6 +70,7 @@ struct tpacket_auxdata {
 #define TP_STATUS_COPY          0x2
 #define TP_STATUS_LOSING        0x4
 #define TP_STATUS_CSUMNOTREADY  0x8
+#define TP_STATUS_VLAN_VALID   0x10 /* auxdata has valid tp_vlan_tci */
 
 /* Tx ring - header status */
 #define TP_STATUS_AVAILABLE     0x0
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/linux/tty_ldisc.h b/include/linux/tty_ldisc.h
index 5b07792ccb46..ff7dc08696a8 100644
--- a/include/linux/tty_ldisc.h
+++ b/include/linux/tty_ldisc.h
@@ -76,7 +76,7 @@
  *      tty device.  It is solely the responsibility of the line
  *      discipline to handle poll requests.
  *
- * unsigned int (*receive_buf)(struct tty_struct *, const unsigned char *cp,
+ * void (*receive_buf)(struct tty_struct *, const unsigned char *cp,
  *                     char *fp, int count);
  *
  *      This function is called by the low-level tty driver to send
@@ -84,8 +84,7 @@
  *      processing.  <cp> is a pointer to the buffer of input
  *      character received by the device.  <fp> is a pointer to a
  *      pointer of flag bytes which indicate whether a character was
- *      received with a parity error, etc. Returns the amount of bytes
- *      received.
+ *      received with a parity error, etc.
  * 
  * void (*write_wakeup)(struct tty_struct *);
  *
@@ -141,8 +140,8 @@ struct tty_ldisc_ops {
         /*
          * The following routines are called from below.
          */
-        unsigned int (*receive_buf)(struct tty_struct *,
-                        const unsigned char *cp, char *fp, int count);
+        void    (*receive_buf)(struct tty_struct *, const unsigned char *cp,
+                               char *fp, int count);
         void    (*write_wakeup)(struct tty_struct *);
         void    (*dcd_change)(struct tty_struct *, unsigned int,
                                 struct pps_event_time *);
diff --git a/include/net/sctp/command.h b/include/net/sctp/command.h
index 2b447646ce4b..dd6847e5d6e4 100644
--- a/include/net/sctp/command.h
+++ b/include/net/sctp/command.h
@@ -107,6 +107,7 @@ typedef enum {
         SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */
         SCTP_CMD_SEND_MSG,       /* Send the whole use message */
         SCTP_CMD_SEND_NEXT_ASCONF, /* Send the next ASCONF after ACK */
+        SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/
         SCTP_CMD_LAST
 } sctp_verb_t;
 
diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h
index 795f4886e111..7df327a6d564 100644
--- a/include/net/sctp/structs.h
+++ b/include/net/sctp/structs.h
@@ -1993,7 +1993,7 @@ void sctp_assoc_clean_asconf_ack_cache(const struct sctp_association *asoc);
 struct sctp_chunk *sctp_assoc_lookup_asconf_ack(
                                         const struct sctp_association *asoc,
                                         __be32 serial);
-
+void sctp_asconf_queue_teardown(struct sctp_association *asoc);
 
 int sctp_cmp_addr_exact(const union sctp_addr *ss1,
                         const union sctp_addr *ss2);
diff --git a/include/trace/events/net.h b/include/trace/events/net.h
index 5f247f5ffc56..f99645d05a8f 100644
--- a/include/trace/events/net.h
+++ b/include/trace/events/net.h
@@ -12,22 +12,24 @@
 TRACE_EVENT(net_dev_xmit,
 
         TP_PROTO(struct sk_buff *skb,
-                 int rc),
+                 int rc,
+                 struct net_device *dev,
+                 unsigned int skb_len),
 
-        TP_ARGS(skb, rc),
+        TP_ARGS(skb, rc, dev, skb_len),
 
         TP_STRUCT__entry(
                 __field(        void *,         skbaddr         )
                 __field(        unsigned int,   len             )
                 __field(        int,            rc              )
-                __string(       name,           skb->dev->name  )
+                __string(       name,           dev->name       )
         ),
 
         TP_fast_assign(
                 __entry->skbaddr = skb;
-                __entry->len = skb->len;
+                __entry->len = skb_len;
                 __entry->rc = rc;
-                __assign_str(name, skb->dev->name);
+                __assign_str(name, dev->name);
         ),
 
         TP_printk("dev=%s skbaddr=%p len=%u rc=%d",
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/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;
+
+                if (delta < 256)
+                        return expires;
 
-                /* No slack, if already expired else auto slack 0.4% */
-                if (time_after(expires, now))
-                        expires_limit = expires + (expires - now)/256;
+                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/lib/Kconfig.debug b/lib/Kconfig.debug
index 28afa4c5333c..dd373c8ee943 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -697,7 +697,7 @@ config DEBUG_BUGVERBOSE
         bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EXPERT
         depends on BUG
         depends on ARM || AVR32 || M32R || M68K || SPARC32 || SPARC64 || \
-                   FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300
+                   FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300 || TILE
         default y
         help
           Say Y here to make BUG() panics output the file name and line number
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/mm/hugetlb.c b/mm/hugetlb.c
index f33bb319b73f..6402458fee38 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1033,10 +1033,10 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma,
          */
         chg = vma_needs_reservation(h, vma, addr);
         if (chg < 0)
-                return ERR_PTR(chg);
+                return ERR_PTR(-VM_FAULT_OOM);
         if (chg)
                 if (hugetlb_get_quota(inode->i_mapping, chg))
-                        return ERR_PTR(-ENOSPC);
+                        return ERR_PTR(-VM_FAULT_SIGBUS);
 
         spin_lock(&hugetlb_lock);
         page = dequeue_huge_page_vma(h, vma, addr, avoid_reserve);
diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c
index f247f5bff88d..7ea5cf9ea08a 100644
--- a/net/8021q/vlan_dev.c
+++ b/net/8021q/vlan_dev.c
@@ -165,7 +165,7 @@ static netdev_tx_t vlan_dev_hard_start_xmit(struct sk_buff *skb,
                 u64_stats_update_begin(&stats->syncp);
                 stats->tx_packets++;
                 stats->tx_bytes += len;
-                u64_stats_update_begin(&stats->syncp);
+                u64_stats_update_end(&stats->syncp);
         } else {
                 this_cpu_inc(vlan_dev_info(dev)->vlan_pcpu_stats->tx_dropped);
         }
diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
index a86f9ba4f05c..e64a1c2df238 100644
--- a/net/bluetooth/l2cap_core.c
+++ b/net/bluetooth/l2cap_core.c
@@ -906,7 +906,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, bdaddr
                 if (c->psm == psm) {
                         /* Exact match. */
                         if (!bacmp(&bt_sk(sk)->src, src)) {
-                                read_unlock_bh(&chan_list_lock);
+                                read_unlock(&chan_list_lock);
                                 return c;
                         }
 
diff --git a/net/caif/chnl_net.c b/net/caif/chnl_net.c
index 649ebacaf6bc..adbb424403d4 100644
--- a/net/caif/chnl_net.c
+++ b/net/caif/chnl_net.c
@@ -139,17 +139,14 @@ static void close_work(struct work_struct *work)
         struct chnl_net *dev = NULL;
         struct list_head *list_node;
         struct list_head *_tmp;
-        /* May be called with or without RTNL lock held */
-        int islocked = rtnl_is_locked();
-        if (!islocked)
-                rtnl_lock();
+
+        rtnl_lock();
         list_for_each_safe(list_node, _tmp, &chnl_net_list) {
                 dev = list_entry(list_node, struct chnl_net, list_field);
                 if (dev->state == CAIF_SHUTDOWN)
                         dev_close(dev->netdev);
         }
-        if (!islocked)
-                rtnl_unlock();
+        rtnl_unlock();
 }
 static DECLARE_WORK(close_worker, close_work);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index c7e305d13b71..939307891e71 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2096,6 +2096,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
 {
         const struct net_device_ops *ops = dev->netdev_ops;
         int rc = NETDEV_TX_OK;
+        unsigned int skb_len;
 
         if (likely(!skb->next)) {
                 u32 features;
@@ -2146,8 +2147,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev,
                         }
                 }
 
+                skb_len = skb->len;
                 rc = ops->ndo_start_xmit(skb, dev);
-                trace_net_dev_xmit(skb, rc);
+                trace_net_dev_xmit(skb, rc, dev, skb_len);
                 if (rc == NETDEV_TX_OK)
                         txq_trans_update(txq);
                 return rc;
@@ -2167,8 +2169,9 @@ gso:
                 if (dev->priv_flags & IFF_XMIT_DST_RELEASE)
                         skb_dst_drop(nskb);
 
+                skb_len = nskb->len;
                 rc = ops->ndo_start_xmit(nskb, dev);
-                trace_net_dev_xmit(nskb, rc);
+                trace_net_dev_xmit(nskb, rc, dev, skb_len);
                 if (unlikely(rc != NETDEV_TX_OK)) {
                         if (rc & ~NETDEV_TX_MASK)
                                 goto out_kfree_gso_skb;
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index cc1463156cd0..9c1926027a26 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -465,6 +465,9 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
         if (addr_len < sizeof(struct sockaddr_in))
                 goto out;
 
+        if (addr->sin_family != AF_INET)
+                goto out;
+
         chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
 
         /* Not specified by any standard per-se, however it breaks too
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index c3118e1cd3bb..ec93335901dd 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -14,6 +14,7 @@
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <asm/uaccess.h>
+#include <asm/unaligned.h>
 #include <linux/skbuff.h>
 #include <linux/ip.h>
 #include <linux/icmp.h>
@@ -350,7 +351,7 @@ int ip_options_compile(struct net *net,
                                 goto error;
                         }
                         if (optptr[2] <= optlen) {
-                                __be32 *timeptr = NULL;
+                                unsigned char *timeptr = NULL;
                                 if (optptr[2]+3 > optptr[1]) {
                                         pp_ptr = optptr + 2;
                                         goto error;
@@ -359,7 +360,7 @@ int ip_options_compile(struct net *net,
                                       case IPOPT_TS_TSONLY:
                                         opt->ts = optptr - iph;
                                         if (skb)
-                                                timeptr = (__be32*)&optptr[optptr[2]-1];
+                                                timeptr = &optptr[optptr[2]-1];
                                         opt->ts_needtime = 1;
                                         optptr[2] += 4;
                                         break;
@@ -371,7 +372,7 @@ int ip_options_compile(struct net *net,
                                         opt->ts = optptr - iph;
                                         if (rt)  {
                                                 memcpy(&optptr[optptr[2]-1], &rt->rt_spec_dst, 4);
-                                                timeptr = (__be32*)&optptr[optptr[2]+3];
+                                                timeptr = &optptr[optptr[2]+3];
                                         }
                                         opt->ts_needaddr = 1;
                                         opt->ts_needtime = 1;
@@ -389,7 +390,7 @@ int ip_options_compile(struct net *net,
                                                 if (inet_addr_type(net, addr) == RTN_UNICAST)
                                                         break;
                                                 if (skb)
-                                                        timeptr = (__be32*)&optptr[optptr[2]+3];
+                                                        timeptr = &optptr[optptr[2]+3];
                                         }
                                         opt->ts_needtime = 1;
                                         optptr[2] += 8;
@@ -403,10 +404,10 @@ int ip_options_compile(struct net *net,
                                 }
                                 if (timeptr) {
                                         struct timespec tv;
-                                        __be32  midtime;
+                                        u32  midtime;
                                         getnstimeofday(&tv);
-                                        midtime = htonl((tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC);
-                                        memcpy(timeptr, &midtime, sizeof(__be32));
+                                        midtime = (tv.tv_sec % 86400) * MSEC_PER_SEC + tv.tv_nsec / NSEC_PER_MSEC;
+                                        put_unaligned_be32(midtime, timeptr);
                                         opt->is_changed = 1;
                                 }
                         } else {
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 4f6b2675e41d..456cccf26b51 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -232,6 +232,9 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata,
                 WARN_ON(!ieee80211_set_channel_type(local, sdata, channel_type));
         }
 
+        ieee80211_stop_queues_by_reason(&sdata->local->hw,
+                                        IEEE80211_QUEUE_STOP_REASON_CSA);
+
         /* channel_type change automatically detected */
         ieee80211_hw_config(local, 0);
 
@@ -245,6 +248,9 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata,
                 rcu_read_unlock();
         }
 
+        ieee80211_wake_queues_by_reason(&sdata->local->hw,
+                                        IEEE80211_QUEUE_STOP_REASON_CSA);
+
         ht_opmode = le16_to_cpu(hti->operation_mode);
 
         /* if bss configuration changed store the new one */
@@ -1089,6 +1095,7 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
                 local->hw.conf.flags &= ~IEEE80211_CONF_PS;
                 config_changed |= IEEE80211_CONF_CHANGE_PS;
         }
+        local->ps_sdata = NULL;
 
         ieee80211_hw_config(local, config_changed);
 
diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
index 27af6723cb5e..58ffa7d069c7 100644
--- a/net/mac80211/scan.c
+++ b/net/mac80211/scan.c
@@ -15,7 +15,6 @@
 #include <linux/if_arp.h>
 #include <linux/rtnetlink.h>
 #include <linux/pm_qos_params.h>
-#include <linux/slab.h>
 #include <net/sch_generic.h>
 #include <linux/slab.h>
 #include <net/mac80211.h>
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 925f715686a5..ba248d93399a 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -798,7 +798,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
                         getnstimeofday(&ts);
                 h.h2->tp_sec = ts.tv_sec;
                 h.h2->tp_nsec = ts.tv_nsec;
-                h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
+                if (vlan_tx_tag_present(skb)) {
+                        h.h2->tp_vlan_tci = vlan_tx_tag_get(skb);
+                        status |= TP_STATUS_VLAN_VALID;
+                } else {
+                        h.h2->tp_vlan_tci = 0;
+                }
                 hdrlen = sizeof(*h.h2);
                 break;
         default:
@@ -1725,8 +1730,12 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
                 aux.tp_snaplen = skb->len;
                 aux.tp_mac = 0;
                 aux.tp_net = skb_network_offset(skb);
-                aux.tp_vlan_tci = vlan_tx_tag_get(skb);
-
+                if (vlan_tx_tag_present(skb)) {
+                        aux.tp_vlan_tci = vlan_tx_tag_get(skb);
+                        aux.tp_status |= TP_STATUS_VLAN_VALID;
+                } else {
+                        aux.tp_vlan_tci = 0;
+                }
                 put_cmsg(msg, SOL_PACKET, PACKET_AUXDATA, sizeof(aux), &aux);
         }
 
diff --git a/net/sctp/associola.c b/net/sctp/associola.c
index 525f97c467e9..4a62888f2e43 100644
--- a/net/sctp/associola.c
+++ b/net/sctp/associola.c
@@ -444,15 +444,7 @@ void sctp_association_free(struct sctp_association *asoc)
 
         asoc->peer.transport_count = 0;
 
-        /* Free any cached ASCONF_ACK chunk. */
-        sctp_assoc_free_asconf_acks(asoc);
-
-        /* Free the ASCONF queue. */
-        sctp_assoc_free_asconf_queue(asoc);
-
-        /* Free any cached ASCONF chunk. */
-        if (asoc->addip_last_asconf)
-                sctp_chunk_free(asoc->addip_last_asconf);
+        sctp_asconf_queue_teardown(asoc);
 
         /* AUTH - Free the endpoint shared keys */
         sctp_auth_destroy_keys(&asoc->endpoint_shared_keys);
@@ -1646,3 +1638,16 @@ struct sctp_chunk *sctp_assoc_lookup_asconf_ack(
 
         return NULL;
 }
+
+void sctp_asconf_queue_teardown(struct sctp_association *asoc)
+{
+        /* Free any cached ASCONF_ACK chunk. */
+        sctp_assoc_free_asconf_acks(asoc);
+
+        /* Free the ASCONF queue. */
+        sctp_assoc_free_asconf_queue(asoc);
+
+        /* Free any cached ASCONF chunk. */
+        if (asoc->addip_last_asconf)
+                sctp_chunk_free(asoc->addip_last_asconf);
+}
diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c
index d612ca1ca6c0..534c2e5feb05 100644
--- a/net/sctp/sm_sideeffect.c
+++ b/net/sctp/sm_sideeffect.c
@@ -1670,6 +1670,9 @@ static int sctp_cmd_interpreter(sctp_event_t event_type,
                 case SCTP_CMD_SEND_NEXT_ASCONF:
                         sctp_cmd_send_asconf(asoc);
                         break;
+                case SCTP_CMD_PURGE_ASCONF_QUEUE:
+                        sctp_asconf_queue_teardown(asoc);
+                        break;
                 default:
                         pr_warn("Impossible command: %u, %p\n",
                                 cmd->verb, cmd->obj.ptr);
diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
index 7f4a4f8368ee..a297283154d5 100644
--- a/net/sctp/sm_statefuns.c
+++ b/net/sctp/sm_statefuns.c
@@ -1718,11 +1718,21 @@ static sctp_disposition_t sctp_sf_do_dupcook_a(const struct sctp_endpoint *ep,
                 return SCTP_DISPOSITION_CONSUME;
         }
 
-        /* For now, fail any unsent/unacked data.  Consider the optional
-         * choice of resending of this data.
+        /* For now, stop pending T3-rtx and SACK timers, fail any unsent/unacked
+         * data. Consider the optional choice of resending of this data.
          */
+        sctp_add_cmd_sf(commands, SCTP_CMD_T3_RTX_TIMERS_STOP, SCTP_NULL());
+        sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
+                        SCTP_TO(SCTP_EVENT_TIMEOUT_SACK));
         sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_OUTQUEUE, SCTP_NULL());
 
+        /* Stop pending T4-rto timer, teardown ASCONF queue, ASCONF-ACK queue
+         * and ASCONF-ACK cache.
+         */
+        sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP,
+                        SCTP_TO(SCTP_EVENT_TIMEOUT_T4_RTO));
+        sctp_add_cmd_sf(commands, SCTP_CMD_PURGE_ASCONF_QUEUE, SCTP_NULL());
+
         repl = sctp_make_cookie_ack(new_asoc, chunk);
         if (!repl)
                 goto nomem;
diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index ec83f413a7ed..88a565f130a5 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3406,12 +3406,12 @@ static int nl80211_trigger_scan(struct sk_buff *skb, struct genl_info *info)
         i = 0;
         if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) {
                 nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS], tmp) {
+                        request->ssids[i].ssid_len = nla_len(attr);
                         if (request->ssids[i].ssid_len > IEEE80211_MAX_SSID_LEN) {
                                 err = -EINVAL;
                                 goto out_free;
                         }
                         memcpy(request->ssids[i].ssid, nla_data(attr), nla_len(attr));
-                        request->ssids[i].ssid_len = nla_len(attr);
                         i++;
                 }
         }
@@ -3572,6 +3572,7 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
         if (info->attrs[NL80211_ATTR_SCAN_SSIDS]) {
                 nla_for_each_nested(attr, info->attrs[NL80211_ATTR_SCAN_SSIDS],
                                     tmp) {
+                        request->ssids[i].ssid_len = nla_len(attr);
                         if (request->ssids[i].ssid_len >
                             IEEE80211_MAX_SSID_LEN) {
                                 err = -EINVAL;
@@ -3579,7 +3580,6 @@ static int nl80211_start_sched_scan(struct sk_buff *skb,
                         }
                         memcpy(request->ssids[i].ssid, nla_data(attr),
                                nla_len(attr));
-                        request->ssids[i].ssid_len = nla_len(attr);
                         i++;
                 }
         }
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index 73a441d237b5..7a6c67667d70 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -267,13 +267,35 @@ static bool is_bss(struct cfg80211_bss *a,
         return memcmp(ssidie + 2, ssid, ssid_len) == 0;
 }
 
+static bool is_mesh_bss(struct cfg80211_bss *a)
+{
+        const u8 *ie;
+
+        if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability))
+                return false;
+
+        ie = cfg80211_find_ie(WLAN_EID_MESH_ID,
+                              a->information_elements,
+                              a->len_information_elements);
+        if (!ie)
+                return false;
+
+        ie = cfg80211_find_ie(WLAN_EID_MESH_CONFIG,
+                              a->information_elements,
+                              a->len_information_elements);
+        if (!ie)
+                return false;
+
+        return true;
+}
+
 static bool is_mesh(struct cfg80211_bss *a,
                     const u8 *meshid, size_t meshidlen,
                     const u8 *meshcfg)
 {
         const u8 *ie;
 
-        if (!WLAN_CAPABILITY_IS_MBSS(a->capability))
+        if (!WLAN_CAPABILITY_IS_STA_BSS(a->capability))
                 return false;
 
         ie = cfg80211_find_ie(WLAN_EID_MESH_ID,
@@ -311,7 +333,7 @@ static int cmp_bss(struct cfg80211_bss *a,
         if (a->channel != b->channel)
                 return b->channel->center_freq - a->channel->center_freq;
 
-        if (WLAN_CAPABILITY_IS_MBSS(a->capability | b->capability)) {
+        if (is_mesh_bss(a) && is_mesh_bss(b)) {
                 r = cmp_ies(WLAN_EID_MESH_ID,
                             a->information_elements,
                             a->len_information_elements,
@@ -457,7 +479,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
                     struct cfg80211_internal_bss *res)
 {
         struct cfg80211_internal_bss *found = NULL;
-        const u8 *meshid, *meshcfg;
 
         /*
          * The reference to "res" is donated to this function.
@@ -470,22 +491,6 @@ cfg80211_bss_update(struct cfg80211_registered_device *dev,
 
         res->ts = jiffies;
 
-        if (WLAN_CAPABILITY_IS_MBSS(res->pub.capability)) {
-                /* must be mesh, verify */
-                meshid = cfg80211_find_ie(WLAN_EID_MESH_ID,
-                                          res->pub.information_elements,
-                                          res->pub.len_information_elements);
-                meshcfg = cfg80211_find_ie(WLAN_EID_MESH_CONFIG,
-                                           res->pub.information_elements,
-                                           res->pub.len_information_elements);
-                if (!meshid || !meshcfg ||
-                    meshcfg[1] != sizeof(struct ieee80211_meshconf_ie)) {
-                        /* bogus mesh */
-                        kref_put(&res->ref, bss_release);
-                        return NULL;
-                }
-        }
-
         spin_lock_bh(&dev->bss_lock);
 
         found = rb_find_bss(dev, res);
diff --git a/sound/pci/asihpi/hpidspcd.c b/sound/pci/asihpi/hpidspcd.c
index fb311d8c05bf..5c6ea113d219 100644
--- a/sound/pci/asihpi/hpidspcd.c
+++ b/sound/pci/asihpi/hpidspcd.c
@@ -60,7 +60,7 @@ struct code_header {
             HPI_VER_MINOR(HPI_VER) * 100 + HPI_VER_RELEASE(HPI_VER)))
 
 /***********************************************************************/
-#include "linux/pci.h"
+#include <linux/pci.h>
 /*-------------------------------------------------------------------*/
 short hpi_dsp_code_open(u32 adapter, struct dsp_code *ps_dsp_code,
         u32 *pos_error_code)
diff --git a/sound/pci/fm801.c b/sound/pci/fm801.c
index eacd4901a308..a7ec7030cf87 100644
--- a/sound/pci/fm801.c
+++ b/sound/pci/fm801.c
@@ -1234,9 +1234,12 @@ static int __devinit snd_fm801_create(struct snd_card *card,
         sprintf(chip->tea.bus_info, "PCI:%s", pci_name(pci));
         if ((tea575x_tuner & TUNER_TYPE_MASK) > 0 &&
             (tea575x_tuner & TUNER_TYPE_MASK) < 4) {
-                if (snd_tea575x_init(&chip->tea))
+                if (snd_tea575x_init(&chip->tea)) {
                         snd_printk(KERN_ERR "TEA575x radio not found\n");
-        } else if ((tea575x_tuner & TUNER_TYPE_MASK) == 0)
+                        snd_fm801_free(chip);
+                        return -ENODEV;
+                }
+        } else if ((tea575x_tuner & TUNER_TYPE_MASK) == 0) {
                 /* autodetect tuner connection */
                 for (tea575x_tuner = 1; tea575x_tuner <= 3; tea575x_tuner++) {
                         chip->tea575x_tuner = tea575x_tuner;
@@ -1246,6 +1249,12 @@ static int __devinit snd_fm801_create(struct snd_card *card,
                                 break;
                         }
                 }
+                if (tea575x_tuner == 4) {
+                        snd_printk(KERN_ERR "TEA575x radio not found\n");
+                        snd_fm801_free(chip);
+                        return -ENODEV;
+                }
+        }
         strlcpy(chip->tea.card, snd_fm801_tea575x_gpios[(tea575x_tuner & TUNER_TYPE_MASK) - 1].name, sizeof(chip->tea.card));
 #endif
 
diff --git a/sound/pci/hda/patch_analog.c b/sound/pci/hda/patch_analog.c
index 696ac2590307..d694e9d4921d 100644
--- a/sound/pci/hda/patch_analog.c
+++ b/sound/pci/hda/patch_analog.c
@@ -506,9 +506,11 @@ static void ad198x_power_eapd_write(struct hda_codec *codec, hda_nid_t front,
                                 hda_nid_t hp)
 {
         struct ad198x_spec *spec = codec->spec;
-        snd_hda_codec_write(codec, front, 0, AC_VERB_SET_EAPD_BTLENABLE,
+        if (snd_hda_query_pin_caps(codec, front) & AC_PINCAP_EAPD)
+                snd_hda_codec_write(codec, front, 0, AC_VERB_SET_EAPD_BTLENABLE,
                             !spec->inv_eapd ? 0x00 : 0x02);
-        snd_hda_codec_write(codec, hp, 0, AC_VERB_SET_EAPD_BTLENABLE,
+        if (snd_hda_query_pin_caps(codec, hp) & AC_PINCAP_EAPD)
+                snd_hda_codec_write(codec, hp, 0, AC_VERB_SET_EAPD_BTLENABLE,
                             !spec->inv_eapd ? 0x00 : 0x02);
 }
 
@@ -524,6 +526,10 @@ static void ad198x_power_eapd(struct hda_codec *codec)
         case 0x11d4184a:
         case 0x11d4194a:
         case 0x11d4194b:
+        case 0x11d41988:
+        case 0x11d4198b:
+        case 0x11d4989a:
+        case 0x11d4989b:
                 ad198x_power_eapd_write(codec, 0x12, 0x11);
                 break;
         case 0x11d41981:
@@ -533,12 +539,6 @@ static void ad198x_power_eapd(struct hda_codec *codec)
         case 0x11d41986:
                 ad198x_power_eapd_write(codec, 0x1b, 0x1a);
                 break;
-        case 0x11d41988:
-        case 0x11d4198b:
-        case 0x11d4989a:
-        case 0x11d4989b:
-                ad198x_power_eapd_write(codec, 0x29, 0x22);
-                break;
         }
 }
 
diff --git a/sound/soc/codecs/cx20442.c b/sound/soc/codecs/cx20442.c
index f8c663dcff02..d68ea532cc7f 100644
--- a/sound/soc/codecs/cx20442.c
+++ b/sound/soc/codecs/cx20442.c
@@ -262,14 +262,14 @@ static int v253_hangup(struct tty_struct *tty)
 }
 
 /* Line discipline .receive_buf() */
-static unsigned int v253_receive(struct tty_struct *tty,
-                                 const unsigned char *cp, char *fp, int count)
+static void v253_receive(struct tty_struct *tty,
+                                const unsigned char *cp, char *fp, int count)
 {
         struct snd_soc_codec *codec = tty->disc_data;
         struct cx20442_priv *cx20442;
 
         if (!codec)
-                return count;
+                return;
 
         cx20442 = snd_soc_codec_get_drvdata(codec);
 
@@ -281,8 +281,6 @@ static unsigned int v253_receive(struct tty_struct *tty,
                 codec->hw_write = (hw_write_t)tty->ops->write;
                 codec->card->pop_time = 1;
         }
-
-        return count;
 }
 
 /* Line discipline .write_wakeup() */
diff --git a/sound/soc/codecs/wm_hubs.c b/sound/soc/codecs/wm_hubs.c
index e55b298c14a0..9e370d14ad88 100644
--- a/sound/soc/codecs/wm_hubs.c
+++ b/sound/soc/codecs/wm_hubs.c
@@ -215,23 +215,23 @@ static const struct snd_kcontrol_new analogue_snd_controls[] = {
 SOC_SINGLE_TLV("IN1L Volume", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 0, 31, 0,
                inpga_tlv),
 SOC_SINGLE("IN1L Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN1L ZC Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN1L ZC Switch", WM8993_LEFT_LINE_INPUT_1_2_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("IN1R Volume", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 0, 31, 0,
                inpga_tlv),
 SOC_SINGLE("IN1R Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN1R ZC Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN1R ZC Switch", WM8993_RIGHT_LINE_INPUT_1_2_VOLUME, 6, 1, 0),
 
 
 SOC_SINGLE_TLV("IN2L Volume", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 0, 31, 0,
                inpga_tlv),
 SOC_SINGLE("IN2L Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN2L ZC Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN2L ZC Switch", WM8993_LEFT_LINE_INPUT_3_4_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("IN2R Volume", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 0, 31, 0,
                inpga_tlv),
 SOC_SINGLE("IN2R Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 7, 1, 1),
-SOC_SINGLE("IN2R ZC Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 7, 1, 0),
+SOC_SINGLE("IN2R ZC Switch", WM8993_RIGHT_LINE_INPUT_3_4_VOLUME, 6, 1, 0),
 
 SOC_SINGLE_TLV("MIXINL IN2L Volume", WM8993_INPUT_MIXER3, 7, 1, 0,
                inmix_sw_tlv),
diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
index 999bb08cdfb1..776e6f418306 100644
--- a/sound/soc/soc-dapm.c
+++ b/sound/soc/soc-dapm.c
@@ -325,6 +325,7 @@ static int dapm_connect_mixer(struct snd_soc_dapm_context *dapm,
 }
 
 static int dapm_is_shared_kcontrol(struct snd_soc_dapm_context *dapm,
+        struct snd_soc_dapm_widget *kcontrolw,
         const struct snd_kcontrol_new *kcontrol_new,
         struct snd_kcontrol **kcontrol)
 {
@@ -334,6 +335,8 @@ static int dapm_is_shared_kcontrol(struct snd_soc_dapm_context *dapm,
         *kcontrol = NULL;
 
         list_for_each_entry(w, &dapm->card->widgets, list) {
+                if (w == kcontrolw || w->dapm != kcontrolw->dapm)
+                        continue;
                 for (i = 0; i < w->num_kcontrols; i++) {
                         if (&w->kcontrol_news[i] == kcontrol_new) {
                                 if (w->kcontrols)
@@ -468,7 +471,7 @@ static int dapm_new_mux(struct snd_soc_dapm_context *dapm,
                 return -EINVAL;
         }
 
-        shared = dapm_is_shared_kcontrol(dapm, &w->kcontrol_news[0],
+        shared = dapm_is_shared_kcontrol(dapm, w, &w->kcontrol_news[0],
                                          &kcontrol);
         if (kcontrol) {
                 wlist = kcontrol->private_data;
diff --git a/sound/usb/6fire/firmware.c b/sound/usb/6fire/firmware.c
index d47beffedb0f..a91719d5918b 100644
--- a/sound/usb/6fire/firmware.c
+++ b/sound/usb/6fire/firmware.c
@@ -227,6 +227,7 @@ static int usb6fire_fw_ezusb_upload(
         ret = usb6fire_fw_ihex_init(fw, rec);
         if (ret < 0) {
                 kfree(rec);
+                release_firmware(fw);
                 snd_printk(KERN_ERR PREFIX "error validating ezusb "
                                 "firmware %s.\n", fwname);
                 return ret;
diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
index 2e969cbb393b..090e1930dfdc 100644
--- a/sound/usb/quirks.c
+++ b/sound/usb/quirks.c
@@ -403,7 +403,7 @@ static int snd_usb_cm106_boot_quirk(struct usb_device *dev)
 static int snd_usb_cm6206_boot_quirk(struct usb_device *dev)
 {
         int err, reg;
-        int val[] = {0x200c, 0x3000, 0xf800, 0x143f, 0x0000, 0x3000};
+        int val[] = {0x2004, 0x3000, 0xf800, 0x143f, 0x0000, 0x3000};
 
         for (reg = 0; reg < ARRAY_SIZE(val); reg++) {
                 err = snd_usb_cm106_write_int_reg(dev, reg, val[reg]);
diff --git a/tools/testing/ktest/ktest.pl b/tools/testing/ktest/ktest.pl
index 1fd29b2daa92..cef28e6632b9 100755
--- a/tools/testing/ktest/ktest.pl
+++ b/tools/testing/ktest/ktest.pl
@@ -788,7 +788,7 @@ sub wait_for_input
 
 sub reboot_to {
     if ($reboot_type eq "grub") {
-        run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch; reboot)'";
+        run_ssh "'(echo \"savedefault --default=$grub_number --once\" | grub --batch && reboot)'";
         return;
     }
 
@@ -1480,7 +1480,7 @@ sub process_config_ignore {
         or dodie "Failed to read $config";
 
     while (<IN>) {
-        if (/^(.*?(CONFIG\S*)(=.*| is not set))/) {
+        if (/^((CONFIG\S*)=.*)/) {
             $config_ignore{$2} = $1;
         }
     }
@@ -1638,7 +1638,7 @@ sub run_config_bisect {
         if (!$found) {
             # try the other half
             doprint "Top half produced no set configs, trying bottom half\n";
-            @tophalf = @start_list[$half .. $#start_list];
+            @tophalf = @start_list[$half + 1 .. $#start_list];
             create_config @tophalf;
             read_current_config \%current_config;
             foreach my $config (@tophalf) {
@@ -1690,7 +1690,7 @@ sub run_config_bisect {
         # remove half the configs we are looking at and see if
         # they are good.
         $half = int($#start_list / 2);
-    } while ($half > 0);
+    } while ($#start_list > 0);
 
     # we found a single config, try it again unless we are running manually
 
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;
 
+        spin_lock_init(&kvm->mmu_lock);
         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;