Staging: Merge 2.6.37-rc2 into staging-next

This was necessary in order  to resolve some conflicts that happened
between -rc1 and -rc2 with the following files:
	drivers/staging/bcm/Bcmchar.c
	drivers/staging/intel_sst/intel_sst_app_interface.c

All should be resolved now.

Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>

Documentation/ABI/obsolete/proc-pid-oom_adj

@@ -0,0 +1,22 @@
+What:	/proc/<pid>/oom_adj
+When:	August 2012
+Why:	/proc/<pid>/oom_adj allows userspace to influence the oom killer's
+	badness heuristic used to determine which task to kill when the kernel
+	is out of memory.
+
+	The badness heuristic has since been rewritten since the introduction of
+	this tunable such that its meaning is deprecated.  The value was
+	implemented as a bitshift on a score generated by the badness()
+	function that did not have any precise units of measure.  With the
+	rewrite, the score is given as a proportion of available memory to the
+	task allocating pages, so using a bitshift which grows the score
+	exponentially is, thus, impossible to tune with fine granularity.
+
+	A much more powerful interface, /proc/<pid>/oom_score_adj, was
+	introduced with the oom killer rewrite that allows users to increase or
+	decrease the badness() score linearly.  This interface will replace
+	/proc/<pid>/oom_adj.
+
+	A warning will be emitted to the kernel log if an application uses this
+	deprecated interface.  After it is printed once, future warnings will be
+	suppressed until the kernel is rebooted.

Documentation/arm/OMAP/DSS

@@ -255,9 +255,10 @@ framebuffer parameters.
 Kernel boot arguments
 ---------------------
 
-vram=<size>
-	- Amount of total VRAM to preallocate. For example, "10M". omapfb
-	  allocates memory for framebuffers from VRAM.
+vram=<size>[,<physaddr>]
+	- Amount of total VRAM to preallocate and optionally a physical start
+	  memory address. For example, "10M". omapfb allocates memory for
+	  framebuffers from VRAM.
 
 omapfb.mode=<display>:<mode>[,...]
 	- Default video mode for specified displays. For example,

Documentation/block/switching-sched.txt

@@ -16,7 +16,7 @@ you can do so by typing:
 As of the Linux 2.6.10 kernel, it is now possible to change the
 IO scheduler for a given block device on the fly (thus making it possible,
 for instance, to set the CFQ scheduler for the system default, but
-set a specific device to use the anticipatory or noop schedulers - which
+set a specific device to use the deadline or noop schedulers - which
 can improve that device's throughput).
 
 To set a specific scheduler, simply do this:
@@ -31,7 +31,7 @@ a "cat /sys/block/DEV/queue/scheduler" - the list of valid names
 will be displayed, with the currently selected scheduler in brackets:
 
 # cat /sys/block/hda/queue/scheduler
-noop anticipatory deadline [cfq]
-# echo anticipatory > /sys/block/hda/queue/scheduler
+noop deadline [cfq]
+# echo deadline > /sys/block/hda/queue/scheduler
 # cat /sys/block/hda/queue/scheduler
-noop [anticipatory] deadline cfq
+noop [deadline] cfq

Documentation/feature-removal-schedule.txt

@@ -554,3 +554,13 @@ Why:    This is a legacy interface which have been replaced by a more
 Who:    NeilBrown <neilb@suse.de>
 
 ----------------------------
+
+What:	i2c_adapter.id
+When:	June 2011
+Why:	This field is deprecated. I2C device drivers shouldn't change their
+	behavior based on the underlying I2C adapter. Instead, the I2C
+	adapter driver should instantiate the I2C devices and provide the
+	needed platform-specific information.
+Who:	Jean Delvare <khali@linux-fr.org>
+
+----------------------------

Documentation/filesystems/xfs-delayed-logging-design.txt

@@ -794,17 +794,6 @@ designed.
 
 Roadmap:
 
-2.6.37 Remove experimental tag from mount option
-	=> should be roughly 6 months after initial merge
-	=> enough time to:
-		=> gain confidence and fix problems reported by early
-		   adopters (a.k.a. guinea pigs)
-		=> address worst performance regressions and undesired
-		   behaviours
-		=> start tuning/optimising code for parallelism
-		=> start tuning/optimising algorithms consuming
-		   excessive CPU time
-
 2.6.39 Switch default mount option to use delayed logging
 	=> should be roughly 12 months after initial merge
 	=> enough time to shake out remaining problems before next round of

Documentation/kernel-parameters.txt

@@ -706,7 +706,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			arch/x86/kernel/cpu/cpufreq/elanfreq.c.
 
 	elevator=	[IOSCHED]
-			Format: {"anticipatory" | "cfq" | "deadline" | "noop"}
+			Format: {"cfq" | "deadline" | "noop"}
 			See Documentation/block/as-iosched.txt and
 			Documentation/block/deadline-iosched.txt for details.
 

Documentation/leds-class.txt

@@ -60,15 +60,18 @@ Hardware accelerated blink of LEDs
 
 Some LEDs can be programmed to blink without any CPU interaction. To
 support this feature, a LED driver can optionally implement the
-blink_set() function (see <linux/leds.h>). If implemented, triggers can
-attempt to use it before falling back to software timers. The blink_set()
-function should return 0 if the blink setting is supported, or -EINVAL
-otherwise, which means that LED blinking will be handled by software.
-
-The blink_set() function should choose a user friendly blinking
-value if it is called with *delay_on==0 && *delay_off==0 parameters. In
-this case the driver should give back the chosen value through delay_on
-and delay_off parameters to the leds subsystem.
+blink_set() function (see <linux/leds.h>). To set an LED to blinking,
+however, it is better to use use the API function led_blink_set(),
+as it will check and implement software fallback if necessary.
+
+To turn off blinking again, use the API function led_brightness_set()
+as that will not just set the LED brightness but also stop any software
+timers that may have been required for blinking.
+
+The blink_set() function should choose a user friendly blinking value
+if it is called with *delay_on==0 && *delay_off==0 parameters. In this
+case the driver should give back the chosen value through delay_on and
+delay_off parameters to the leds subsystem.
 
 Setting the brightness to zero with brightness_set() callback function
 should completely turn off the LED and cancel the previously programmed

Documentation/leds/leds-lp5521.txt

@@ -0,0 +1,88 @@
+Kernel driver for lp5521
+========================
+
+* National Semiconductor LP5521 led driver chip
+* Datasheet: http://www.national.com/pf/LP/LP5521.html
+
+Authors: Mathias Nyman, Yuri Zaporozhets, Samu Onkalo
+Contact: Samu Onkalo (samu.p.onkalo-at-nokia.com)
+
+Description
+-----------
+
+LP5521 can drive up to 3 channels. Leds can be controlled directly via
+the led class control interface. Channels have generic names:
+lp5521:channelx, where x is 0 .. 2
+
+All three channels can be also controlled using the engine micro programs.
+More details of the instructions can be found from the public data sheet.
+
+Control interface for the engines:
+x is 1 .. 3
+enginex_mode : disabled, load, run
+enginex_load : store program (visible only in engine load mode)
+
+Example (start to blink the channel 2 led):
+cd   /sys/class/leds/lp5521:channel2/device
+echo "load" > engine3_mode
+echo "037f4d0003ff6000" > engine3_load
+echo "run" > engine3_mode
+
+stop the engine:
+echo "disabled" > engine3_mode
+
+sysfs contains a selftest entry.
+The test communicates with the chip and checks that
+the clock mode is automatically set to the requested one.
+
+Each channel has its own led current settings.
+/sys/class/leds/lp5521:channel0/led_current - RW
+/sys/class/leds/lp5521:channel0/max_current - RO
+Format: 10x mA i.e 10 means 1.0 mA
+
+example platform data:
+
+Note: chan_nr can have values between 0 and 2.
+
+static struct lp5521_led_config lp5521_led_config[] = {
+        {
+                .chan_nr        = 0,
+                .led_current    = 50,
+		.max_current    = 130,
+        }, {
+                .chan_nr        = 1,
+                .led_current    = 0,
+		.max_current    = 130,
+        }, {
+                .chan_nr        = 2,
+                .led_current    = 0,
+		.max_current    = 130,
+        }
+};
+
+static int lp5521_setup(void)
+{
+	/* setup HW resources */
+}
+
+static void lp5521_release(void)
+{
+	/* Release HW resources */
+}
+
+static void lp5521_enable(bool state)
+{
+	/* Control of chip enable signal */
+}
+
+static struct lp5521_platform_data lp5521_platform_data = {
+        .led_config     = lp5521_led_config,
+        .num_channels   = ARRAY_SIZE(lp5521_led_config),
+        .clock_mode     = LP5521_CLOCK_EXT,
+        .setup_resources   = lp5521_setup,
+        .release_resources = lp5521_release,
+        .enable            = lp5521_enable,
+};
+
+If the current is set to 0 in the platform data, that channel is
+disabled and it is not visible in the sysfs.

Documentation/leds/leds-lp5523.txt

@@ -0,0 +1,83 @@
+Kernel driver for lp5523
+========================
+
+* National Semiconductor LP5523 led driver chip
+* Datasheet: http://www.national.com/pf/LP/LP5523.html
+
+Authors: Mathias Nyman, Yuri Zaporozhets, Samu Onkalo
+Contact: Samu Onkalo (samu.p.onkalo-at-nokia.com)
+
+Description
+-----------
+LP5523 can drive up to 9 channels. Leds can be controlled directly via
+the led class control interface. Channels have generic names:
+lp5523:channelx where x is 0...8
+
+The chip provides 3 engines. Each engine can control channels without
+interaction from the main CPU. Details of the micro engine code can be found
+from the public data sheet. Leds can be muxed to different channels.
+
+Control interface for the engines:
+x is 1 .. 3
+enginex_mode : disabled, load, run
+enginex_load : microcode load (visible only in load mode)
+enginex_leds : led mux control (visible only in load mode)
+
+cd /sys/class/leds/lp5523:channel2/device
+echo "load" > engine3_mode
+echo "9d80400004ff05ff437f0000" > engine3_load
+echo "111111111" > engine3_leds
+echo "run" > engine3_mode
+
+sysfs contains a selftest entry. It measures each channel
+voltage level and checks if it looks reasonable. If the level is too high,
+the led is missing; if the level is too low, there is a short circuit.
+
+Selftest uses always the current from the platform data.
+
+Each channel contains led current settings.
+/sys/class/leds/lp5523:channel2/led_current - RW
+/sys/class/leds/lp5523:channel2/max_current - RO
+Format: 10x mA i.e 10 means 1.0 mA
+
+Example platform data:
+
+Note - chan_nr can have values between 0 and 8.
+
+static struct lp5523_led_config lp5523_led_config[] = {
+        {
+                .chan_nr        = 0,
+                .led_current    = 50,
+		.max_current    = 130,
+        },
+...
+        }, {
+                .chan_nr        = 8,
+                .led_current    = 50,
+		.max_current    = 130,
+        }
+};
+
+static int lp5523_setup(void)
+{
+	/* Setup HW resources */
+}
+
+static void lp5523_release(void)
+{
+	/* Release HW resources */
+}
+
+static void lp5523_enable(bool state)
+{
+	/* Control chip enable signal */
+}
+
+static struct lp5523_platform_data lp5523_platform_data = {
+        .led_config     = lp5523_led_config,
+        .num_channels   = ARRAY_SIZE(lp5523_led_config),
+        .clock_mode     = LP5523_CLOCK_EXT,
+        .setup_resources   = lp5523_setup,
+        .release_resources = lp5523_release,
+        .enable            = lp5523_enable,
+};

Documentation/networking/ip-sysctl.txt

@@ -20,6 +20,15 @@ ip_no_pmtu_disc - BOOLEAN
 min_pmtu - INTEGER
 	default 562 - minimum discovered Path MTU
 
+route/max_size - INTEGER
+	Maximum number of routes allowed in the kernel.  Increase
+	this when using large numbers of interfaces and/or routes.
+
+neigh/default/gc_thresh3 - INTEGER
+	Maximum number of neighbor entries allowed.  Increase this
+	when using large numbers of interfaces and when communicating
+	with large numbers of directly-connected peers.
+
 mtu_expires - INTEGER
 	Time, in seconds, that cached PMTU information is kept.
 

Documentation/rbtree.txt

@@ -21,8 +21,8 @@ three rotations, respectively, to balance the tree), with slightly slower
 To quote Linux Weekly News:
 
     There are a number of red-black trees in use in the kernel.
-    The anticipatory, deadline, and CFQ I/O schedulers all employ
-    rbtrees to track requests; the packet CD/DVD driver does the same.
+    The deadline and CFQ I/O schedulers employ rbtrees to
+    track requests; the packet CD/DVD driver does the same.
     The high-resolution timer code uses an rbtree to organize outstanding
     timer requests.  The ext3 filesystem tracks directory entries in a
     red-black tree.  Virtual memory areas (VMAs) are tracked with red-black

Documentation/sysctl/kernel.txt

@@ -28,6 +28,7 @@ show up in /proc/sys/kernel:
 - core_uses_pid
 - ctrl-alt-del
 - dentry-state
+- dmesg_restrict
 - domainname
 - hostname
 - hotplug
@@ -213,6 +214,19 @@ to decide what to do with it.
 
 ==============================================================
 
+dmesg_restrict:
+
+This toggle indicates whether unprivileged users are prevented from using
+dmesg(8) to view messages from the kernel's log buffer.  When
+dmesg_restrict is set to (0) there are no restrictions.  When
+dmesg_restrict is set set to (1), users must have CAP_SYS_ADMIN to use
+dmesg(8).
+
+The kernel config option CONFIG_SECURITY_DMESG_RESTRICT sets the default
+value of dmesg_restrict.
+
+==============================================================
+
 domainname & hostname:
 
 These files can be used to set the NIS/YP domainname and the

MAINTAINERS

@@ -161,7 +161,7 @@ M:	Greg Kroah-Hartman <gregkh@suse.de>
 L:	linux-serial@vger.kernel.org
 W:	http://serial.sourceforge.net
 S:	Maintained
-T:	quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty-2.6.git
 F:	drivers/serial/8250*
 F:	include/linux/serial_8250.h
 
@@ -945,7 +945,7 @@ M:	Magnus Damm <magnus.damm@gmail.com>
 L:	linux-sh@vger.kernel.org
 W:	http://oss.renesas.com
 Q:	http://patchwork.kernel.org/project/linux-sh/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lethal/genesis-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6.git rmobile-latest
 S:	Supported
 F:	arch/arm/mach-shmobile/
 F:	drivers/sh/
@@ -2435,6 +2435,7 @@ F:	drivers/net/wan/sdla.c
 FRAMEBUFFER LAYER
 L:	linux-fbdev@vger.kernel.org
 W:	http://linux-fbdev.sourceforge.net/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lethal/fbdev-2.6.git
 S:	Orphan
 F:	Documentation/fb/
 F:	drivers/video/fb*
@@ -5676,7 +5677,7 @@ S:	Maintained
 
 STAGING SUBSYSTEM
 M:	Greg Kroah-Hartman <gregkh@suse.de>
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging-next-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/staging-2.6.git
 L:	devel@driverdev.osuosl.org
 S:	Maintained
 F:	drivers/staging/
@@ -5705,7 +5706,7 @@ M:	Paul Mundt <lethal@linux-sh.org>
 L:	linux-sh@vger.kernel.org
 W:	http://www.linux-sh.org
 Q:	http://patchwork.kernel.org/project/linux-sh/list/
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6.git
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/lethal/sh-2.6.git sh-latest
 S:	Supported
 F:	Documentation/sh/
 F:	arch/sh/
@@ -5910,7 +5911,7 @@ S:	Maintained
 TTY LAYER
 M:	Greg Kroah-Hartman <gregkh@suse.de>
 S:	Maintained
-T:	quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/tty-2.6.git
 F:	drivers/char/tty_*
 F:	drivers/serial/serial_core.c
 F:	include/linux/serial_core.h
@@ -6233,7 +6234,7 @@ USB SUBSYSTEM
 M:	Greg Kroah-Hartman <gregkh@suse.de>
 L:	linux-usb@vger.kernel.org
 W:	http://www.linux-usb.org
-T:	quilt kernel.org/pub/linux/kernel/people/gregkh/gregkh-2.6/
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/usb-2.6.git
 S:	Supported
 F:	Documentation/usb/
 F:	drivers/net/usb/
@@ -6598,14 +6599,14 @@ F:	drivers/platform/x86
 
 XEN PCI SUBSYSTEM
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
-L:	xen-devel@lists.xensource.com
+L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
 S:	Supported
 F:	arch/x86/pci/*xen*
 F:	drivers/pci/*xen*
 
 XEN SWIOTLB SUBSYSTEM
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
-L:	xen-devel@lists.xensource.com
+L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
 S:	Supported
 F:	arch/x86/xen/*swiotlb*
 F:	drivers/xen/*swiotlb*
@@ -6613,7 +6614,7 @@ F:	drivers/xen/*swiotlb*
 XEN HYPERVISOR INTERFACE
 M:	Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
 M:	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
-L:	xen-devel@lists.xen.org
+L:	xen-devel@lists.xensource.com (moderated for non-subscribers)
 L:	virtualization@lists.osdl.org
 S:	Supported
 F:	arch/x86/xen/

Makefile

@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 37
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc2
 NAME = Flesh-Eating Bats with Fangs
 
 # *DOCUMENTATION*

arch/arm/Kconfig

@@ -6,7 +6,7 @@ config ARM
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
-	select GENERIC_ATOMIC64 if (!CPU_32v6K)
+	select GENERIC_ATOMIC64 if (!CPU_32v6K || !AEABI)
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
 	select HAVE_ARCH_KGDB
 	select HAVE_KPROBES if (!XIP_KERNEL)
@@ -646,7 +646,7 @@ config ARCH_S3C2410
 	select ARCH_HAS_CPUFREQ
 	select HAVE_CLK
 	select ARCH_USES_GETTIMEOFFSET
-	select HAVE_S3C2410_I2C
+	select HAVE_S3C2410_I2C if I2C
 	help
 	  Samsung S3C2410X CPU based systems, such as the Simtec Electronics
 	  BAST (<http://www.simtec.co.uk/products/EB110ITX/>), the IPAQ 1940 or
@@ -676,8 +676,8 @@ config ARCH_S3C64XX
 	select S3C_DEV_NAND
 	select USB_ARCH_HAS_OHCI
 	select SAMSUNG_GPIOLIB_4BIT
-	select HAVE_S3C2410_I2C
-	select HAVE_S3C2410_WATCHDOG
+	select HAVE_S3C2410_I2C if I2C
+	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	help
 	  Samsung S3C64XX series based systems
 
@@ -686,10 +686,10 @@ config ARCH_S5P64X0
 	select CPU_V6
 	select GENERIC_GPIO
 	select HAVE_CLK
-	select HAVE_S3C2410_WATCHDOG
+	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select ARCH_USES_GETTIMEOFFSET
-	select HAVE_S3C2410_I2C
-	select HAVE_S3C_RTC
+	select HAVE_S3C2410_I2C if I2C
+	select HAVE_S3C_RTC if RTC_CLASS
 	help
 	  Samsung S5P64X0 CPU based systems, such as the Samsung SMDK6440,
 	  SMDK6450.
@@ -700,7 +700,7 @@ config ARCH_S5P6442
 	select GENERIC_GPIO
 	select HAVE_CLK
 	select ARCH_USES_GETTIMEOFFSET
-	select HAVE_S3C2410_WATCHDOG
+	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	help
 	  Samsung S5P6442 CPU based systems
 
@@ -711,9 +711,9 @@ config ARCH_S5PC100
 	select CPU_V7
 	select ARM_L1_CACHE_SHIFT_6
 	select ARCH_USES_GETTIMEOFFSET
-	select HAVE_S3C2410_I2C
-	select HAVE_S3C_RTC
-	select HAVE_S3C2410_WATCHDOG
+	select HAVE_S3C2410_I2C if I2C
+	select HAVE_S3C_RTC if RTC_CLASS
+	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	help
 	  Samsung S5PC100 series based systems
 
@@ -726,9 +726,9 @@ config ARCH_S5PV210
 	select ARM_L1_CACHE_SHIFT_6
 	select ARCH_HAS_CPUFREQ
 	select ARCH_USES_GETTIMEOFFSET
-	select HAVE_S3C2410_I2C
-	select HAVE_S3C_RTC
-	select HAVE_S3C2410_WATCHDOG
+	select HAVE_S3C2410_I2C if I2C
+	select HAVE_S3C_RTC if RTC_CLASS
+	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	help
 	  Samsung S5PV210/S5PC110 series based systems
 
@@ -739,9 +739,9 @@ config ARCH_S5PV310
 	select GENERIC_GPIO
 	select HAVE_CLK
 	select GENERIC_CLOCKEVENTS
-	select HAVE_S3C_RTC
-	select HAVE_S3C2410_I2C
-	select HAVE_S3C2410_WATCHDOG
+	select HAVE_S3C_RTC if RTC_CLASS
+	select HAVE_S3C2410_I2C if I2C
+	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	help
 	  Samsung S5PV310 series based systems
 

arch/arm/common/gic.c

@@ -251,15 +251,16 @@ void __init gic_dist_init(unsigned int gic_nr, void __iomem *base,
 		writel(cpumask, base + GIC_DIST_TARGET + i * 4 / 4);
 
 	/*
-	 * Set priority on all interrupts.
+	 * Set priority on all global interrupts.
 	 */
-	for (i = 0; i < max_irq; i += 4)
+	for (i = 32; i < max_irq; i += 4)
 		writel(0xa0a0a0a0, base + GIC_DIST_PRI + i * 4 / 4);
 
 	/*
-	 * Disable all interrupts.
+	 * Disable all interrupts.  Leave the PPI and SGIs alone
+	 * as these enables are banked registers.
 	 */
-	for (i = 0; i < max_irq; i += 32)
+	for (i = 32; i < max_irq; i += 32)
 		writel(0xffffffff, base + GIC_DIST_ENABLE_CLEAR + i * 4 / 32);
 
 	/*
@@ -277,11 +278,30 @@ void __init gic_dist_init(unsigned int gic_nr, void __iomem *base,
 
 void __cpuinit gic_cpu_init(unsigned int gic_nr, void __iomem *base)
 {
+	void __iomem *dist_base;
+	int i;
+
 	if (gic_nr >= MAX_GIC_NR)
 		BUG();
 
+	dist_base = gic_data[gic_nr].dist_base;
+	BUG_ON(!dist_base);
+
 	gic_data[gic_nr].cpu_base = base;
 
+	/*
+	 * Deal with the banked PPI and SGI interrupts - disable all
+	 * PPI interrupts, ensure all SGI interrupts are enabled.
+	 */
+	writel(0xffff0000, dist_base + GIC_DIST_ENABLE_CLEAR);
+	writel(0x0000ffff, dist_base + GIC_DIST_ENABLE_SET);
+
+	/*
+	 * Set priority on PPI and SGI interrupts
+	 */
+	for (i = 0; i < 32; i += 4)
+		writel(0xa0a0a0a0, dist_base + GIC_DIST_PRI + i * 4 / 4);
+
 	writel(0xf0, base + GIC_CPU_PRIMASK);
 	writel(1, base + GIC_CPU_CTRL);
 }

arch/arm/include/asm/hardware/it8152.h

@@ -75,7 +75,7 @@ extern unsigned long it8152_base_address;
   IT8152_PD_IRQ(1)  USB (USBR)
   IT8152_PD_IRQ(0)  Audio controller (ACR)
  */
-#define IT8152_IRQ(x)   (IRQ_BOARD_END + (x))
+#define IT8152_IRQ(x)   (IRQ_BOARD_START + (x))
 
 /* IRQ-sources in 3 groups - local devices, LPC (serial), and external PCI */
 #define IT8152_LD_IRQ_COUNT     9

arch/arm/kernel/hw_breakpoint.c

@@ -748,8 +748,7 @@ static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr,
 		breakpoint_handler(addr, regs);
 		break;
 	case ARM_ENTRY_ASYNC_WATCHPOINT:
-		WARN_ON("Asynchronous watchpoint exception taken. "
-			"Debugging results may be unreliable");
+		WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n");
 	case ARM_ENTRY_SYNC_WATCHPOINT:
 		watchpoint_handler(addr, regs);
 		break;

arch/arm/kernel/perf_event.c

@@ -1749,7 +1749,7 @@ static inline int armv7_pmnc_has_overflowed(unsigned long pmnc)
 static inline int armv7_pmnc_counter_has_overflowed(unsigned long pmnc,
 					enum armv7_counters counter)
 {
-	int ret;
+	int ret = 0;
 
 	if (counter == ARMV7_CYCLE_COUNTER)
 		ret = pmnc & ARMV7_FLAG_C;

arch/arm/kernel/stacktrace.c

@@ -28,7 +28,7 @@ int notrace unwind_frame(struct stackframe *frame)
 
 	/* only go to a higher address on the stack */
 	low = frame->sp;
-	high = ALIGN(low, THREAD_SIZE) + THREAD_SIZE;
+	high = ALIGN(low, THREAD_SIZE);
 
 	/* check current frame pointer is within bounds */
 	if (fp < (low + 12) || fp + 4 >= high)

arch/arm/kernel/traps.c

@@ -53,10 +53,7 @@ static void dump_mem(const char *, const char *, unsigned long, unsigned long);
 void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame)
 {
 #ifdef CONFIG_KALLSYMS
-	char sym1[KSYM_SYMBOL_LEN], sym2[KSYM_SYMBOL_LEN];
-	sprint_symbol(sym1, where);
-	sprint_symbol(sym2, from);
-	printk("[<%08lx>] (%s) from [<%08lx>] (%s)\n", where, sym1, from, sym2);
+	printk("[<%08lx>] (%pS) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from);
 #else
 	printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from);
 #endif

arch/arm/kernel/unwind.c

@@ -279,7 +279,7 @@ int unwind_frame(struct stackframe *frame)
 
 	/* only go to a higher address on the stack */
 	low = frame->sp;
-	high = ALIGN(low, THREAD_SIZE) + THREAD_SIZE;
+	high = ALIGN(low, THREAD_SIZE);
 
 	pr_debug("%s(pc = %08lx lr = %08lx sp = %08lx)\n", __func__,
 		 frame->pc, frame->lr, frame->sp);

arch/arm/mach-ep93xx/include/mach/dma.h

@@ -1,5 +1,13 @@
-/*
- * arch/arm/mach-ep93xx/include/mach/dma.h
+/**
+ * DOC: EP93xx DMA M2P memory to peripheral and peripheral to memory engine
+ *
+ * The EP93xx DMA M2P subsystem handles DMA transfers between memory and
+ * peripherals. DMA M2P channels are available for audio, UARTs and IrDA.
+ * See chapter 10 of the EP93xx users guide for full details on the DMA M2P
+ * engine.
+ *
+ * See sound/soc/ep93xx/ep93xx-pcm.c for an example use of the DMA M2P code.
+ *
  */
 
 #ifndef __ASM_ARCH_DMA_H
@@ -8,12 +16,34 @@
 #include <linux/list.h>
 #include <linux/types.h>
 
+/**
+ * struct ep93xx_dma_buffer - Information about a buffer to be transferred
+ * using the DMA M2P engine
+ *
+ * @list: Entry in DMA buffer list
+ * @bus_addr: Physical address of the buffer
+ * @size: Size of the buffer in bytes
+ */
 struct ep93xx_dma_buffer {
 	struct list_head	list;
 	u32			bus_addr;
 	u16			size;
 };
 
+/**
+ * struct ep93xx_dma_m2p_client - Information about a DMA M2P client
+ *
+ * @name: Unique name for this client
+ * @flags: Client flags
+ * @cookie: User data to pass to callback functions
+ * @buffer_started: Non NULL function to call when a transfer is started.
+ * 			The arguments are the user data cookie and the DMA
+ *			buffer which is starting.
+ * @buffer_finished: Non NULL function to call when a transfer is completed.
+ *			The arguments are the user data cookie, the DMA buffer
+ *			which has completed, and a boolean flag indicating if
+ *			the transfer had an error.
+ */
 struct ep93xx_dma_m2p_client {
 	char			*name;
 	u8			flags;
@@ -24,10 +54,11 @@ struct ep93xx_dma_m2p_client {
 					struct ep93xx_dma_buffer *buf,
 					int bytes, int error);
 
-	/* Internal to the DMA code.  */
+	/* private: Internal use only */
 	void			*channel;
 };
 
+/* DMA M2P ports */
 #define EP93XX_DMA_M2P_PORT_I2S1	0x00
 #define EP93XX_DMA_M2P_PORT_I2S2	0x01
 #define EP93XX_DMA_M2P_PORT_AAC1	0x02
@@ -39,18 +70,80 @@ struct ep93xx_dma_m2p_client {
 #define EP93XX_DMA_M2P_PORT_UART3	0x08
 #define EP93XX_DMA_M2P_PORT_IRDA	0x09
 #define EP93XX_DMA_M2P_PORT_MASK	0x0f
-#define EP93XX_DMA_M2P_TX		0x00
-#define EP93XX_DMA_M2P_RX		0x10
-#define EP93XX_DMA_M2P_ABORT_ON_ERROR	0x20
-#define EP93XX_DMA_M2P_IGNORE_ERROR	0x40
-#define EP93XX_DMA_M2P_ERROR_MASK	0x60
 
-int  ep93xx_dma_m2p_client_register(struct ep93xx_dma_m2p_client *m2p);
+/* DMA M2P client flags */
+#define EP93XX_DMA_M2P_TX		0x00	/* Memory to peripheral */
+#define EP93XX_DMA_M2P_RX		0x10	/* Peripheral to memory */
+
+/*
+ * DMA M2P client error handling flags. See the EP93xx users guide
+ * documentation on the DMA M2P CONTROL register for more details
+ */
+#define EP93XX_DMA_M2P_ABORT_ON_ERROR	0x20	/* Abort on peripheral error */
+#define EP93XX_DMA_M2P_IGNORE_ERROR	0x40	/* Ignore peripheral errors */
+#define EP93XX_DMA_M2P_ERROR_MASK	0x60	/* Mask of error bits */
+
+/**
+ * ep93xx_dma_m2p_client_register - Register a client with the DMA M2P
+ * subsystem
+ *
+ * @m2p: Client information to register
+ * returns 0 on success
+ *
+ * The DMA M2P subsystem allocates a channel and an interrupt line for the DMA
+ * client
+ */
+int ep93xx_dma_m2p_client_register(struct ep93xx_dma_m2p_client *m2p);
+
+/**
+ * ep93xx_dma_m2p_client_unregister - Unregister a client from the DMA M2P
+ * subsystem
+ *
+ * @m2p: Client to unregister
+ *
+ * Any transfers currently in progress will be completed in hardware, but
+ * ignored in software.
+ */
 void ep93xx_dma_m2p_client_unregister(struct ep93xx_dma_m2p_client *m2p);
+
+/**
+ * ep93xx_dma_m2p_submit - Submit a DMA M2P transfer
+ *
+ * @m2p: DMA Client to submit the transfer on
+ * @buf: DMA Buffer to submit
+ *
+ * If the current or next transfer positions are free on the M2P client then
+ * the transfer is started immediately. If not, the transfer is added to the
+ * list of pending transfers. This function must not be called from the
+ * buffer_finished callback for an M2P channel.
+ *
+ */
 void ep93xx_dma_m2p_submit(struct ep93xx_dma_m2p_client *m2p,
 			   struct ep93xx_dma_buffer *buf);
+
+/**
+ * ep93xx_dma_m2p_submit_recursive - Put a DMA transfer on the pending list
+ * for an M2P channel
+ *
+ * @m2p: DMA Client to submit the transfer on
+ * @buf: DMA Buffer to submit
+ *
+ * This function must only be called from the buffer_finished callback for an
+ * M2P channel. It is commonly used to add the next transfer in a chained list
+ * of DMA transfers.
+ */
 void ep93xx_dma_m2p_submit_recursive(struct ep93xx_dma_m2p_client *m2p,
 				     struct ep93xx_dma_buffer *buf);
+
+/**
+ * ep93xx_dma_m2p_flush - Flush all pending transfers on a DMA M2P client
+ *
+ * @m2p: DMA client to flush transfers on
+ *
+ * Any transfers currently in progress will be completed in hardware, but
+ * ignored in software.
+ *
+ */
 void ep93xx_dma_m2p_flush(struct ep93xx_dma_m2p_client *m2p);
 
 #endif /* __ASM_ARCH_DMA_H */

arch/arm/mach-kirkwood/common.c

@@ -854,10 +854,9 @@ int __init kirkwood_find_tclk(void)
 
 	kirkwood_pcie_id(&dev, &rev);
 
-	if ((dev == MV88F6281_DEV_ID && (rev == MV88F6281_REV_A0 ||
-					rev == MV88F6281_REV_A1)) ||
-	    (dev == MV88F6282_DEV_ID))
-		return 200000000;
+	if (dev == MV88F6281_DEV_ID || dev == MV88F6282_DEV_ID)
+		if (((readl(SAMPLE_AT_RESET) >> 21) & 1) == 0)
+			return 200000000;
 
 	return 166666667;
 }

arch/arm/mach-kirkwood/d2net_v2-setup.c

@@ -225,5 +225,5 @@ MACHINE_START(D2NET_V2, "LaCie d2 Network v2")
 	.init_machine	= d2net_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_irq	= kirkwood_init_irq,
-	.timer		= &lacie_v2_timer,
+	.timer		= &kirkwood_timer,
 MACHINE_END

arch/arm/mach-kirkwood/lacie_v2-common.c

@@ -111,17 +111,3 @@ void __init lacie_v2_hdd_power_init(int hdd_num)
 			pr_err("Failed to power up HDD%d\n", i + 1);
 	}
 }
-
-/*****************************************************************************
- * Timer
- ****************************************************************************/
-
-static void lacie_v2_timer_init(void)
-{
-	kirkwood_tclk = 166666667;
-	orion_time_init(IRQ_KIRKWOOD_BRIDGE, kirkwood_tclk);
-}
-
-struct sys_timer lacie_v2_timer = {
-	.init = lacie_v2_timer_init,
-};

arch/arm/mach-kirkwood/lacie_v2-common.h

@@ -13,6 +13,4 @@ void lacie_v2_register_flash(void);
 void lacie_v2_register_i2c_devices(void);
 void lacie_v2_hdd_power_init(int hdd_num);
 
-extern struct sys_timer lacie_v2_timer;
-
 #endif

arch/arm/mach-kirkwood/mpp.c

@@ -59,7 +59,7 @@ void __init kirkwood_mpp_conf(unsigned int *mpp_list)
 	}
 	printk("\n");
 
-	while (*mpp_list) {
+	for ( ; *mpp_list; mpp_list++) {
 		unsigned int num = MPP_NUM(*mpp_list);
 		unsigned int sel = MPP_SEL(*mpp_list);
 		int shift, gpio_mode;
@@ -88,8 +88,6 @@ void __init kirkwood_mpp_conf(unsigned int *mpp_list)
 		if (sel != 0)
 			gpio_mode = 0;
 		orion_gpio_set_valid(num, gpio_mode);
-
-		mpp_list++;
 	}
 
 	printk(KERN_DEBUG "  final MPP regs:");

arch/arm/mach-kirkwood/netspace_v2-setup.c

@@ -262,7 +262,7 @@ MACHINE_START(NETSPACE_V2, "LaCie Network Space v2")
 	.init_machine	= netspace_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_irq	= kirkwood_init_irq,
-	.timer		= &lacie_v2_timer,
+	.timer		= &kirkwood_timer,
 MACHINE_END
 #endif
 
@@ -272,7 +272,7 @@ MACHINE_START(INETSPACE_V2, "LaCie Internet Space v2")
 	.init_machine	= netspace_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_irq	= kirkwood_init_irq,
-	.timer		= &lacie_v2_timer,
+	.timer		= &kirkwood_timer,
 MACHINE_END
 #endif
 
@@ -282,6 +282,6 @@ MACHINE_START(NETSPACE_MAX_V2, "LaCie Network Space Max v2")
 	.init_machine	= netspace_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_irq	= kirkwood_init_irq,
-	.timer		= &lacie_v2_timer,
+	.timer		= &kirkwood_timer,
 MACHINE_END
 #endif

arch/arm/mach-kirkwood/netxbig_v2-setup.c

@@ -403,7 +403,7 @@ MACHINE_START(NET2BIG_V2, "LaCie 2Big Network v2")
 	.init_machine	= netxbig_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_irq	= kirkwood_init_irq,
-	.timer		= &lacie_v2_timer,
+	.timer		= &kirkwood_timer,
 MACHINE_END
 #endif
 
@@ -413,6 +413,6 @@ MACHINE_START(NET5BIG_V2, "LaCie 5Big Network v2")
 	.init_machine	= netxbig_v2_init,
 	.map_io		= kirkwood_map_io,
 	.init_irq	= kirkwood_init_irq,
-	.timer		= &lacie_v2_timer,
+	.timer		= &kirkwood_timer,
 MACHINE_END
 #endif

arch/arm/mach-kirkwood/ts41x-setup.c

@@ -27,6 +27,10 @@
 #include "mpp.h"
 #include "tsx1x-common.h"
 
+/* for the PCIe reset workaround */
+#include <plat/pcie.h>
+
+
 #define QNAP_TS41X_JUMPER_JP1	45
 
 static struct i2c_board_info __initdata qnap_ts41x_i2c_rtc = {
@@ -140,8 +144,16 @@ static void __init qnap_ts41x_init(void)
 
 static int __init ts41x_pci_init(void)
 {
-	if (machine_is_ts41x())
+	if (machine_is_ts41x()) {
+		/*
+		 * Without this explicit reset, the PCIe SATA controller
+		 * (Marvell 88sx7042/sata_mv) is known to stop working
+		 * after a few minutes.
+		 */
+		orion_pcie_reset((void __iomem *)PCIE_VIRT_BASE);
+
 		kirkwood_pcie_init(KW_PCIE0);
+	}
 
    return 0;
 }

arch/arm/mach-mmp/include/mach/cputype.h

@@ -46,7 +46,8 @@ static inline int cpu_is_pxa910(void)
 #ifdef CONFIG_CPU_MMP2
 static inline int cpu_is_mmp2(void)
 {
-	return (((cpu_readid_id() >> 8) & 0xff) == 0x58);
+	return (((read_cpuid_id() >> 8) & 0xff) == 0x58);
+}
 #else
 #define cpu_is_mmp2()	(0)
 #endif

arch/arm/mach-mv78xx0/mpp.c

@@ -54,7 +54,7 @@ void __init mv78xx0_mpp_conf(unsigned int *mpp_list)
 	}
 	printk("\n");
 
-	while (*mpp_list) {
+	for ( ; *mpp_list; mpp_list++) {
 		unsigned int num = MPP_NUM(*mpp_list);
 		unsigned int sel = MPP_SEL(*mpp_list);
 		int shift, gpio_mode;
@@ -83,8 +83,6 @@ void __init mv78xx0_mpp_conf(unsigned int *mpp_list)
 		if (sel != 0)
 			gpio_mode = 0;
 		orion_gpio_set_valid(num, gpio_mode);
-
-		mpp_list++;
 	}
 
 	printk(KERN_DEBUG "  final MPP regs:");

arch/arm/mach-omap1/devices.c

@@ -321,10 +321,9 @@ static struct platform_device omap_wdt_device = {
 static int __init omap_init_wdt(void)
 {
 	if (!cpu_is_omap16xx())
-		return;
+		return -ENODEV;
 
-	platform_device_register(&omap_wdt_device);
-	return 0;
+	return platform_device_register(&omap_wdt_device);
 }
 subsys_initcall(omap_init_wdt);
 #endif

arch/arm/mach-omap1/include/mach/camera.h

@@ -1,6 +1,8 @@
 #ifndef __ASM_ARCH_CAMERA_H_
 #define __ASM_ARCH_CAMERA_H_
 
+#include <media/omap1_camera.h>
+
 void omap1_camera_init(void *);
 
 static inline void omap1_set_camera_info(struct omap1_cam_platform_data *info)

arch/arm/mach-omap2/board-devkit8000.c

@@ -242,9 +242,6 @@ static int devkit8000_twl_gpio_setup(struct device *dev,
 	mmc[0].gpio_cd = gpio + 0;
 	omap2_hsmmc_init(mmc);
 
-	/* link regulators to MMC adapters */
-	devkit8000_vmmc1_supply.dev = mmc[0].dev;
-
 	/* TWL4030_GPIO_MAX + 1 == ledB, PMU_STAT (out, active low LED) */
 	gpio_leds[2].gpio = gpio + TWL4030_GPIO_MAX + 1;
 

arch/arm/mach-orion5x/mpp.c

@@ -127,7 +127,7 @@ void __init orion5x_mpp_conf(struct orion5x_mpp_mode *mode)
 	/* Initialize gpiolib. */
 	orion_gpio_init();
 
-	while (mode->mpp >= 0) {
+	for ( ; mode->mpp >= 0; mode++) {
 		u32 *reg;
 		int num_type;
 		int shift;
@@ -160,8 +160,6 @@ void __init orion5x_mpp_conf(struct orion5x_mpp_mode *mode)
 			orion_gpio_set_unused(mode->mpp);
 
 		orion_gpio_set_valid(mode->mpp, !!(mode->type == MPP_GPIO));
-
-		mode++;
 	}
 
 	writel(mpp_0_7_ctrl, MPP_0_7_CTRL);

arch/arm/mach-orion5x/ts78xx-setup.c

@@ -239,7 +239,7 @@ static struct platform_nand_data ts78xx_ts_nand_data = {
 static struct resource ts78xx_ts_nand_resources = {
 	.start		= TS_NAND_DATA,
 	.end		= TS_NAND_DATA + 4,
-	.flags		= IORESOURCE_IO,
+	.flags		= IORESOURCE_MEM,
 };
 
 static struct platform_device ts78xx_ts_nand_device = {

arch/arm/mach-pxa/cm-x2xx.c

@@ -476,8 +476,6 @@ static void __init cmx2xx_init(void)
 
 static void __init cmx2xx_init_irq(void)
 {
-	pxa27x_init_irq();
-
 	if (cpu_is_pxa25x()) {
 		pxa25x_init_irq();
 		cmx2xx_pci_init_irq(CMX255_GPIO_IT8152_IRQ);

arch/arm/mach-pxa/saar.c

@@ -116,7 +116,7 @@ static struct platform_device smc91x_device = {
 	},
 };
 
-#if defined(CONFIG_FB_PXA) || (CONFIG_FB_PXA_MODULE)
+#if defined(CONFIG_FB_PXA) || defined(CONFIG_FB_PXA_MODULE)
 static uint16_t lcd_power_on[] = {
 	/* single frame */
 	SMART_CMD_NOOP,

arch/arm/mach-s3c64xx/Kconfig

@@ -143,7 +143,7 @@ config MACH_SMDK6410
 	select S3C_DEV_USB_HSOTG
 	select S3C_DEV_WDT
 	select SAMSUNG_DEV_KEYPAD
-	select HAVE_S3C2410_WATCHDOG
+	select HAVE_S3C2410_WATCHDOG if WATCHDOG
 	select S3C64XX_SETUP_SDHCI
 	select S3C64XX_SETUP_I2C1
 	select S3C64XX_SETUP_IDE

arch/arm/mach-shmobile/board-ap4evb.c

@@ -163,11 +163,13 @@ static struct mtd_partition nor_flash_partitions[] = {
 		.name		= "loader",
 		.offset		= 0x00000000,
 		.size		= 512 * 1024,
+		.mask_flags	= MTD_WRITEABLE,
 	},
 	{
 		.name		= "bootenv",
 		.offset		= MTDPART_OFS_APPEND,
 		.size		= 512 * 1024,
+		.mask_flags	= MTD_WRITEABLE,
 	},
 	{
 		.name		= "kernel_ro",
@@ -581,6 +583,10 @@ static int fsi_set_rate(int is_porta, int rate)
 		return -EINVAL;
 
 	switch (rate) {
+	case 44100:
+		clk_set_rate(fsib_clk, clk_round_rate(fsib_clk, 11283000));
+		ret = SH_FSI_ACKMD_256 | SH_FSI_BPFMD_64;
+		break;
 	case 48000:
 		clk_set_rate(fsib_clk, clk_round_rate(fsib_clk, 85428000));
 		clk_set_rate(fdiv_clk, clk_round_rate(fdiv_clk, 12204000));

arch/arm/mach-shmobile/intc-sh7372.c

@@ -98,7 +98,7 @@ static struct intc_vect intca_vectors[] __initdata = {
 	INTC_VECT(IRQ14A, 0x03c0), INTC_VECT(IRQ15A, 0x03e0),
 	INTC_VECT(IRQ16A, 0x3200), INTC_VECT(IRQ17A, 0x3220),
 	INTC_VECT(IRQ18A, 0x3240), INTC_VECT(IRQ19A, 0x3260),
-	INTC_VECT(IRQ20A, 0x3280), INTC_VECT(IRQ31A, 0x32a0),
+	INTC_VECT(IRQ20A, 0x3280), INTC_VECT(IRQ21A, 0x32a0),
 	INTC_VECT(IRQ22A, 0x32c0), INTC_VECT(IRQ23A, 0x32e0),
 	INTC_VECT(IRQ24A, 0x3300), INTC_VECT(IRQ25A, 0x3320),
 	INTC_VECT(IRQ26A, 0x3340), INTC_VECT(IRQ27A, 0x3360),

arch/arm/mach-vexpress/ct-ca9x4.c

@@ -54,7 +54,9 @@ static struct map_desc ct_ca9x4_io_desc[] __initdata = {
 
 static void __init ct_ca9x4_map_io(void)
 {
+#ifdef CONFIG_LOCAL_TIMERS
 	twd_base = MMIO_P2V(A9_MPCORE_TWD);
+#endif
 	v2m_map_io(ct_ca9x4_io_desc, ARRAY_SIZE(ct_ca9x4_io_desc));
 }
 

arch/arm/mm/dma-mapping.c

@@ -198,7 +198,7 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
 	 * fragmentation of the DMA space, and also prevents allocations
 	 * smaller than a section from crossing a section boundary.
 	 */
-	bit = fls(size - 1) + 1;
+	bit = fls(size - 1);
 	if (bit > SECTION_SHIFT)
 		bit = SECTION_SHIFT;
 	align = 1 << bit;

arch/arm/plat-omap/devices.c

@@ -284,12 +284,14 @@ void __init omap_dsp_reserve_sdram_memblock(void)
 	if (!size)
 		return;
 
-	paddr = __memblock_alloc_base(size, SZ_1M, MEMBLOCK_REAL_LIMIT);
+	paddr = memblock_alloc(size, SZ_1M);
 	if (!paddr) {
 		pr_err("%s: failed to reserve %x bytes\n",
 				__func__, size);
 		return;
 	}
+	memblock_free(paddr, size);
+	memblock_remove(paddr, size);
 
 	omap_dsp_phys_mempool_base = paddr;
 }

arch/arm/plat-omap/dma.c

@@ -1983,6 +1983,8 @@ static int omap2_dma_handle_ch(int ch)
 
 	dma_write(OMAP2_DMA_CSR_CLEAR_MASK, CSR(ch));
 	dma_write(1 << ch, IRQSTATUS_L0);
+	/* read back the register to flush the write */
+	dma_read(IRQSTATUS_L0);
 
 	/* If the ch is not chained then chain_id will be -1 */
 	if (dma_chan[ch].chain_id != -1) {

arch/arm/plat-orion/include/plat/pcie.h

@@ -11,12 +11,15 @@
 #ifndef __PLAT_PCIE_H
 #define __PLAT_PCIE_H
 
+struct pci_bus;
+
 u32 orion_pcie_dev_id(void __iomem *base);
 u32 orion_pcie_rev(void __iomem *base);
 int orion_pcie_link_up(void __iomem *base);
 int orion_pcie_x4_mode(void __iomem *base);
 int orion_pcie_get_local_bus_nr(void __iomem *base);
 void orion_pcie_set_local_bus_nr(void __iomem *base, int nr);
+void orion_pcie_reset(void __iomem *base);
 void orion_pcie_setup(void __iomem *base,
 		      struct mbus_dram_target_info *dram);
 int orion_pcie_rd_conf(void __iomem *base, struct pci_bus *bus,

arch/arm/plat-orion/pcie.c

@@ -181,11 +181,6 @@ void __init orion_pcie_setup(void __iomem *base,
 	u16 cmd;
 	u32 mask;
 
-	/*
-	 * soft reset PCIe unit
-	 */
-	orion_pcie_reset(base);
-
 	/*
 	 * Point PCIe unit MBUS decode windows to DRAM space.
 	 */

arch/um/include/asm/ptrace-generic.h

@@ -38,8 +38,8 @@ struct pt_regs {
 
 struct task_struct;
 
-extern long subarch_ptrace(struct task_struct *child, long request, long addr,
-			   long data);
+extern long subarch_ptrace(struct task_struct *child, long request,
+	unsigned long addr, unsigned long data);
 extern unsigned long getreg(struct task_struct *child, int regno);
 extern int putreg(struct task_struct *child, int regno, unsigned long value);
 extern int get_fpregs(struct user_i387_struct __user *buf,

arch/um/kernel/ptrace.c

@@ -122,7 +122,7 @@ long arch_ptrace(struct task_struct *child, long request,
 		break;
 
 	case PTRACE_SET_THREAD_AREA:
-		ret = ptrace_set_thread_area(child, addr, datavp);
+		ret = ptrace_set_thread_area(child, addr, vp);
 		break;
 
 	case PTRACE_FAULTINFO: {

arch/x86/include/asm/apic.h

@@ -141,13 +141,13 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
 
 static inline u32 native_apic_msr_read(u32 reg)
 {
-	u32 low, high;
+	u64 msr;
 
 	if (reg == APIC_DFR)
 		return -1;
 
-	rdmsr(APIC_BASE_MSR + (reg >> 4), low, high);
-	return low;
+	rdmsrl(APIC_BASE_MSR + (reg >> 4), msr);
+	return (u32)msr;
 }
 
 static inline void native_x2apic_wait_icr_idle(void)
@@ -181,12 +181,12 @@ extern void enable_x2apic(void);
 extern void x2apic_icr_write(u32 low, u32 id);
 static inline int x2apic_enabled(void)
 {
-	int msr, msr2;
+	u64 msr;
 
 	if (!cpu_has_x2apic)
 		return 0;
 
-	rdmsr(MSR_IA32_APICBASE, msr, msr2);
+	rdmsrl(MSR_IA32_APICBASE, msr);
 	if (msr & X2APIC_ENABLE)
 		return 1;
 	return 0;

arch/x86/include/asm/uv/uv_mmrs.h

@@ -805,6 +805,78 @@ union uvh_node_present_table_u {
     } s;
 };
 
+/* ========================================================================= */
+/*                 UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR 0x16000c8UL
+
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_SHFT 48
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_alias210_overlay_config_0_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_alias210_overlay_config_0_mmr_s {
+	unsigned long	rsvd_0_23: 24;  /*    */
+	unsigned long	base    :  8;  /* RW */
+	unsigned long	rsvd_32_47: 16;  /*    */
+	unsigned long	m_alias :  5;  /* RW */
+	unsigned long	rsvd_53_62: 10;  /*    */
+	unsigned long	enable  :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                 UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR 0x16000d8UL
+
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_SHFT 48
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_alias210_overlay_config_1_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_alias210_overlay_config_1_mmr_s {
+	unsigned long	rsvd_0_23: 24;  /*    */
+	unsigned long	base    :  8;  /* RW */
+	unsigned long	rsvd_32_47: 16;  /*    */
+	unsigned long	m_alias :  5;  /* RW */
+	unsigned long	rsvd_53_62: 10;  /*    */
+	unsigned long	enable  :  1;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                 UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR                  */
+/* ========================================================================= */
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR 0x16000e8UL
+
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_SHFT 24
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_BASE_MASK 0x00000000ff000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_SHFT 48
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_M_ALIAS_MASK 0x001f000000000000UL
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_SHFT 63
+#define UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR_ENABLE_MASK 0x8000000000000000UL
+
+union uvh_rh_gam_alias210_overlay_config_2_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_alias210_overlay_config_2_mmr_s {
+	unsigned long	rsvd_0_23: 24;  /*    */
+	unsigned long	base    :  8;  /* RW */
+	unsigned long	rsvd_32_47: 16;  /*    */
+	unsigned long	m_alias :  5;  /* RW */
+	unsigned long	rsvd_53_62: 10;  /*    */
+	unsigned long	enable  :  1;  /* RW */
+    } s;
+};
+
 /* ========================================================================= */
 /*                UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR                  */
 /* ========================================================================= */
@@ -856,6 +928,29 @@ union uvh_rh_gam_alias210_redirect_config_2_mmr_u {
     } s;
 };
 
+/* ========================================================================= */
+/*                          UVH_RH_GAM_CONFIG_MMR                            */
+/* ========================================================================= */
+#define UVH_RH_GAM_CONFIG_MMR 0x1600000UL
+
+#define UVH_RH_GAM_CONFIG_MMR_M_SKT_SHFT 0
+#define UVH_RH_GAM_CONFIG_MMR_M_SKT_MASK 0x000000000000003fUL
+#define UVH_RH_GAM_CONFIG_MMR_N_SKT_SHFT 6
+#define UVH_RH_GAM_CONFIG_MMR_N_SKT_MASK 0x00000000000003c0UL
+#define UVH_RH_GAM_CONFIG_MMR_MMIOL_CFG_SHFT 12
+#define UVH_RH_GAM_CONFIG_MMR_MMIOL_CFG_MASK 0x0000000000001000UL
+
+union uvh_rh_gam_config_mmr_u {
+    unsigned long	v;
+    struct uvh_rh_gam_config_mmr_s {
+	unsigned long	m_skt     :  6;  /* RW */
+	unsigned long	n_skt     :  4;  /* RW */
+	unsigned long	rsvd_10_11:  2;  /*    */
+	unsigned long	mmiol_cfg :  1;  /* RW */
+	unsigned long	rsvd_13_63: 51;  /*    */
+    } s;
+};
+
 /* ========================================================================= */
 /*                    UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR                      */
 /* ========================================================================= */
@@ -987,97 +1082,5 @@ union uvh_rtc1_int_config_u {
     } s;
 };
 
-/* ========================================================================= */
-/*                          UVH_SI_ADDR_MAP_CONFIG                           */
-/* ========================================================================= */
-#define UVH_SI_ADDR_MAP_CONFIG 0xc80000UL
-
-#define UVH_SI_ADDR_MAP_CONFIG_M_SKT_SHFT 0
-#define UVH_SI_ADDR_MAP_CONFIG_M_SKT_MASK 0x000000000000003fUL
-#define UVH_SI_ADDR_MAP_CONFIG_N_SKT_SHFT 8
-#define UVH_SI_ADDR_MAP_CONFIG_N_SKT_MASK 0x0000000000000f00UL
-
-union uvh_si_addr_map_config_u {
-    unsigned long	v;
-    struct uvh_si_addr_map_config_s {
-	unsigned long	m_skt :  6;  /* RW */
-	unsigned long	rsvd_6_7:  2;  /*    */
-	unsigned long	n_skt :  4;  /* RW */
-	unsigned long	rsvd_12_63: 52;  /*    */
-    } s;
-};
-
-/* ========================================================================= */
-/*                       UVH_SI_ALIAS0_OVERLAY_CONFIG                        */
-/* ========================================================================= */
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG 0xc80008UL
-
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS0_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_si_alias0_overlay_config_u {
-    unsigned long	v;
-    struct uvh_si_alias0_overlay_config_s {
-	unsigned long	rsvd_0_23: 24;  /*    */
-	unsigned long	base    :  8;  /* RW */
-	unsigned long	rsvd_32_47: 16;  /*    */
-	unsigned long	m_alias :  5;  /* RW */
-	unsigned long	rsvd_53_62: 10;  /*    */
-	unsigned long	enable  :  1;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                       UVH_SI_ALIAS1_OVERLAY_CONFIG                        */
-/* ========================================================================= */
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG 0xc80010UL
-
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS1_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_si_alias1_overlay_config_u {
-    unsigned long	v;
-    struct uvh_si_alias1_overlay_config_s {
-	unsigned long	rsvd_0_23: 24;  /*    */
-	unsigned long	base    :  8;  /* RW */
-	unsigned long	rsvd_32_47: 16;  /*    */
-	unsigned long	m_alias :  5;  /* RW */
-	unsigned long	rsvd_53_62: 10;  /*    */
-	unsigned long	enable  :  1;  /* RW */
-    } s;
-};
-
-/* ========================================================================= */
-/*                       UVH_SI_ALIAS2_OVERLAY_CONFIG                        */
-/* ========================================================================= */
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG 0xc80018UL
-
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_SHFT 24
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_BASE_MASK 0x00000000ff000000UL
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_SHFT 48
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_M_ALIAS_MASK 0x001f000000000000UL
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_SHFT 63
-#define UVH_SI_ALIAS2_OVERLAY_CONFIG_ENABLE_MASK 0x8000000000000000UL
-
-union uvh_si_alias2_overlay_config_u {
-    unsigned long	v;
-    struct uvh_si_alias2_overlay_config_s {
-	unsigned long	rsvd_0_23: 24;  /*    */
-	unsigned long	base    :  8;  /* RW */
-	unsigned long	rsvd_32_47: 16;  /*    */
-	unsigned long	m_alias :  5;  /* RW */
-	unsigned long	rsvd_53_62: 10;  /*    */
-	unsigned long	enable  :  1;  /* RW */
-    } s;
-};
-
 
-#endif /* _ASM_X86_UV_UV_MMRS_H */
+#endif /* __ASM_UV_MMRS_X86_H__ */

arch/x86/kernel/apic/apic.c

@@ -52,7 +52,6 @@
 #include <asm/mce.h>
 #include <asm/kvm_para.h>
 #include <asm/tsc.h>
-#include <asm/atomic.h>
 
 unsigned int num_processors;
 

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -379,14 +379,14 @@ struct redir_addr {
 #define DEST_SHIFT UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR_DEST_BASE_SHFT
 
 static __initdata struct redir_addr redir_addrs[] = {
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR, UVH_SI_ALIAS0_OVERLAY_CONFIG},
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR, UVH_SI_ALIAS1_OVERLAY_CONFIG},
-	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_SI_ALIAS2_OVERLAY_CONFIG},
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_0_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_0_MMR},
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_1_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_1_MMR},
+	{UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR},
 };
 
 static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size)
 {
-	union uvh_si_alias0_overlay_config_u alias;
+	union uvh_rh_gam_alias210_overlay_config_2_mmr_u alias;
 	union uvh_rh_gam_alias210_redirect_config_2_mmr_u redirect;
 	int i;
 
@@ -660,7 +660,7 @@ void uv_nmi_init(void)
 
 void __init uv_system_init(void)
 {
-	union uvh_si_addr_map_config_u m_n_config;
+	union uvh_rh_gam_config_mmr_u  m_n_config;
 	union uvh_node_id_u node_id;
 	unsigned long gnode_upper, lowmem_redir_base, lowmem_redir_size;
 	int bytes, nid, cpu, lcpu, pnode, blade, i, j, m_val, n_val;
@@ -670,7 +670,7 @@ void __init uv_system_init(void)
 
 	map_low_mmrs();
 
-	m_n_config.v = uv_read_local_mmr(UVH_SI_ADDR_MAP_CONFIG);
+	m_n_config.v = uv_read_local_mmr(UVH_RH_GAM_CONFIG_MMR );
 	m_val = m_n_config.s.m_skt;
 	n_val = m_n_config.s.n_skt;
 	mmr_base =

arch/x86/kernel/cpu/perf_event_amd.c

@@ -280,11 +280,11 @@ static struct amd_nb *amd_alloc_nb(int cpu, int nb_id)
 	struct amd_nb *nb;
 	int i;
 
-	nb = kmalloc(sizeof(struct amd_nb), GFP_KERNEL);
+	nb = kmalloc_node(sizeof(struct amd_nb), GFP_KERNEL | __GFP_ZERO,
+			  cpu_to_node(cpu));
 	if (!nb)
 		return NULL;
 
-	memset(nb, 0, sizeof(*nb));
 	nb->nb_id = nb_id;
 
 	/*

arch/x86/kernel/microcode_amd.c

@@ -212,7 +212,7 @@ static int install_equiv_cpu_table(const u8 *buf)
 		return 0;
 	}
 
-	equiv_cpu_table = (struct equiv_cpu_entry *) vmalloc(size);
+	equiv_cpu_table = vmalloc(size);
 	if (!equiv_cpu_table) {
 		pr_err("failed to allocate equivalent CPU table\n");
 		return 0;

arch/x86/kernel/mmconf-fam10h_64.c

@@ -217,13 +217,13 @@ void __cpuinit fam10h_check_enable_mmcfg(void)
 	wrmsrl(address, val);
 }
 
-static int __devinit set_check_enable_amd_mmconf(const struct dmi_system_id *d)
+static int __init set_check_enable_amd_mmconf(const struct dmi_system_id *d)
 {
         pci_probe |= PCI_CHECK_ENABLE_AMD_MMCONF;
         return 0;
 }
 
-static const struct dmi_system_id __cpuinitconst mmconf_dmi_table[] = {
+static const struct dmi_system_id __initconst mmconf_dmi_table[] = {
         {
                 .callback = set_check_enable_amd_mmconf,
                 .ident = "Sun Microsystems Machine",
@@ -234,7 +234,8 @@ static const struct dmi_system_id __cpuinitconst mmconf_dmi_table[] = {
 	{}
 };
 
-void __cpuinit check_enable_amd_mmconf_dmi(void)
+/* Called from a __cpuinit function, but only on the BSP. */
+void __ref check_enable_amd_mmconf_dmi(void)
 {
 	dmi_check_system(mmconf_dmi_table);
 }

arch/x86/kernel/pvclock.c

@@ -41,44 +41,6 @@ void pvclock_set_flags(u8 flags)
 	valid_flags = flags;
 }
 
-/*
- * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
- * yielding a 64-bit result.
- */
-static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
-{
-	u64 product;
-#ifdef __i386__
-	u32 tmp1, tmp2;
-#endif
-
-	if (shift < 0)
-		delta >>= -shift;
-	else
-		delta <<= shift;
-
-#ifdef __i386__
-	__asm__ (
-		"mul  %5       ; "
-		"mov  %4,%%eax ; "
-		"mov  %%edx,%4 ; "
-		"mul  %5       ; "
-		"xor  %5,%5    ; "
-		"add  %4,%%eax ; "
-		"adc  %5,%%edx ; "
-		: "=A" (product), "=r" (tmp1), "=r" (tmp2)
-		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
-#elif defined(__x86_64__)
-	__asm__ (
-		"mul %%rdx ; shrd $32,%%rdx,%%rax"
-		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
-#else
-#error implement me!
-#endif
-
-	return product;
-}
-
 static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow)
 {
 	u64 delta = native_read_tsc() - shadow->tsc_timestamp;

arch/x86/mm/tlb.c

@@ -251,7 +251,7 @@ static void __cpuinit calculate_tlb_offset(void)
 	}
 }
 
-static int tlb_cpuhp_notify(struct notifier_block *n,
+static int __cpuinit tlb_cpuhp_notify(struct notifier_block *n,
 		unsigned long action, void *hcpu)
 {
 	switch (action & 0xf) {

arch/x86/pci/acpi.c

@@ -138,7 +138,6 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 	struct acpi_resource_address64 addr;
 	acpi_status status;
 	unsigned long flags;
-	struct resource *root, *conflict;
 	u64 start, end;
 
 	status = resource_to_addr(acpi_res, &addr);
@@ -146,12 +145,10 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 		return AE_OK;
 
 	if (addr.resource_type == ACPI_MEMORY_RANGE) {
-		root = &iomem_resource;
 		flags = IORESOURCE_MEM;
 		if (addr.info.mem.caching == ACPI_PREFETCHABLE_MEMORY)
 			flags |= IORESOURCE_PREFETCH;
 	} else if (addr.resource_type == ACPI_IO_RANGE) {
-		root = &ioport_resource;
 		flags = IORESOURCE_IO;
 	} else
 		return AE_OK;
@@ -172,25 +169,90 @@ setup_resource(struct acpi_resource *acpi_res, void *data)
 		return AE_OK;
 	}
 
-	conflict = insert_resource_conflict(root, res);
-	if (conflict) {
-		dev_err(&info->bridge->dev,
-			"address space collision: host bridge window %pR "
-			"conflicts with %s %pR\n",
-			res, conflict->name, conflict);
-	} else {
-		pci_bus_add_resource(info->bus, res, 0);
-		info->res_num++;
-		if (addr.translation_offset)
-			dev_info(&info->bridge->dev, "host bridge window %pR "
-				 "(PCI address [%#llx-%#llx])\n",
-				 res, res->start - addr.translation_offset,
-				 res->end - addr.translation_offset);
+	info->res_num++;
+	if (addr.translation_offset)
+		dev_info(&info->bridge->dev, "host bridge window %pR "
+			 "(PCI address [%#llx-%#llx])\n",
+			 res, res->start - addr.translation_offset,
+			 res->end - addr.translation_offset);
+	else
+		dev_info(&info->bridge->dev, "host bridge window %pR\n", res);
+
+	return AE_OK;
+}
+
+static bool resource_contains(struct resource *res, resource_size_t point)
+{
+	if (res->start <= point && point <= res->end)
+		return true;
+	return false;
+}
+
+static void coalesce_windows(struct pci_root_info *info, int type)
+{
+	int i, j;
+	struct resource *res1, *res2;
+
+	for (i = 0; i < info->res_num; i++) {
+		res1 = &info->res[i];
+		if (!(res1->flags & type))
+			continue;
+
+		for (j = i + 1; j < info->res_num; j++) {
+			res2 = &info->res[j];
+			if (!(res2->flags & type))
+				continue;
+
+			/*
+			 * I don't like throwing away windows because then
+			 * our resources no longer match the ACPI _CRS, but
+			 * the kernel resource tree doesn't allow overlaps.
+			 */
+			if (resource_contains(res1, res2->start) ||
+			    resource_contains(res1, res2->end) ||
+			    resource_contains(res2, res1->start) ||
+			    resource_contains(res2, res1->end)) {
+				res1->start = min(res1->start, res2->start);
+				res1->end = max(res1->end, res2->end);
+				dev_info(&info->bridge->dev,
+					 "host bridge window expanded to %pR; %pR ignored\n",
+					 res1, res2);
+				res2->flags = 0;
+			}
+		}
+	}
+}
+
+static void add_resources(struct pci_root_info *info)
+{
+	int i;
+	struct resource *res, *root, *conflict;
+
+	if (!pci_use_crs)
+		return;
+
+	coalesce_windows(info, IORESOURCE_MEM);
+	coalesce_windows(info, IORESOURCE_IO);
+
+	for (i = 0; i < info->res_num; i++) {
+		res = &info->res[i];
+
+		if (res->flags & IORESOURCE_MEM)
+			root = &iomem_resource;
+		else if (res->flags & IORESOURCE_IO)
+			root = &ioport_resource;
 		else
-			dev_info(&info->bridge->dev,
-				 "host bridge window %pR\n", res);
+			continue;
+
+		conflict = insert_resource_conflict(root, res);
+		if (conflict)
+			dev_err(&info->bridge->dev,
+				"address space collision: host bridge window %pR "
+				"conflicts with %s %pR\n",
+				res, conflict->name, conflict);
+		else
+			pci_bus_add_resource(info->bus, res, 0);
 	}
-	return AE_OK;
 }
 
 static void
@@ -224,6 +286,7 @@ get_current_resources(struct acpi_device *device, int busnum,
 	acpi_walk_resources(device->handle, METHOD_NAME__CRS, setup_resource,
 				&info);
 
+	add_resources(&info);
 	return;
 
 name_alloc_fail:

arch/x86/pci/xen.c

@@ -147,8 +147,10 @@ static int xen_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 		irq = xen_allocate_pirq(v[i], 0, /* not sharable */
 			(type == PCI_CAP_ID_MSIX) ?
 			"pcifront-msi-x" : "pcifront-msi");
-		if (irq < 0)
-			return -1;
+		if (irq < 0) {
+			ret = -1;
+			goto free;
+		}
 
 		ret = set_irq_msi(irq, msidesc);
 		if (ret)
@@ -164,7 +166,7 @@ error:
 	if (ret == -ENODEV)
 		dev_err(&dev->dev, "Xen PCI frontend has not registered" \
 			" MSI/MSI-X support!\n");
-
+free:
 	kfree(v);
 	return ret;
 }

arch/x86/platform/uv/tlb_uv.c

@@ -1343,8 +1343,8 @@ uv_activation_descriptor_init(int node, int pnode)
 	 * each bau_desc is 64 bytes; there are 8 (UV_ITEMS_PER_DESCRIPTOR)
 	 * per cpu; and up to 32 (UV_ADP_SIZE) cpu's per uvhub
 	 */
-	bau_desc = (struct bau_desc *)kmalloc_node(sizeof(struct bau_desc)*
-		UV_ADP_SIZE*UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node);
+	bau_desc = kmalloc_node(sizeof(struct bau_desc) * UV_ADP_SIZE
+				* UV_ITEMS_PER_DESCRIPTOR, GFP_KERNEL, node);
 	BUG_ON(!bau_desc);
 
 	pa = uv_gpa(bau_desc); /* need the real nasid*/
@@ -1402,9 +1402,9 @@ uv_payload_queue_init(int node, int pnode)
 	struct bau_payload_queue_entry *pqp_malloc;
 	struct bau_control *bcp;
 
-	pqp = (struct bau_payload_queue_entry *) kmalloc_node(
-		(DEST_Q_SIZE + 1) * sizeof(struct bau_payload_queue_entry),
-		GFP_KERNEL, node);
+	pqp = kmalloc_node((DEST_Q_SIZE + 1)
+			   * sizeof(struct bau_payload_queue_entry),
+			   GFP_KERNEL, node);
 	BUG_ON(!pqp);
 	pqp_malloc = pqp;
 
@@ -1520,8 +1520,7 @@ static void __init uv_init_per_cpu(int nuvhubs)
 
 	timeout_us = calculate_destination_timeout();
 
-	uvhub_descs = (struct uvhub_desc *)
-		kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL);
+	uvhub_descs = kmalloc(nuvhubs * sizeof(struct uvhub_desc), GFP_KERNEL);
 	memset(uvhub_descs, 0, nuvhubs * sizeof(struct uvhub_desc));
 	uvhub_mask = kzalloc((nuvhubs+7)/8, GFP_KERNEL);
 	for_each_present_cpu(cpu) {

arch/x86/xen/mmu.c

@@ -2126,7 +2126,7 @@ __init pgd_t *xen_setup_kernel_pagetable(pgd_t *pgd,
 {
 	pmd_t *kernel_pmd;
 
-	level2_kernel_pgt = extend_brk(sizeof(pmd_t *) * PTRS_PER_PMD, PAGE_SIZE);
+	level2_kernel_pgt = extend_brk(sizeof(pmd_t) * PTRS_PER_PMD, PAGE_SIZE);
 
 	max_pfn_mapped = PFN_DOWN(__pa(xen_start_info->pt_base) +
 				  xen_start_info->nr_pt_frames * PAGE_SIZE +

arch/x86/xen/setup.c

@@ -118,16 +118,18 @@ static unsigned long __init xen_return_unused_memory(unsigned long max_pfn,
 						     const struct e820map *e820)
 {
 	phys_addr_t max_addr = PFN_PHYS(max_pfn);
-	phys_addr_t last_end = 0;
+	phys_addr_t last_end = ISA_END_ADDRESS;
 	unsigned long released = 0;
 	int i;
 
+	/* Free any unused memory above the low 1Mbyte. */
 	for (i = 0; i < e820->nr_map && last_end < max_addr; i++) {
 		phys_addr_t end = e820->map[i].addr;
 		end = min(max_addr, end);
 
-		released += xen_release_chunk(last_end, end);
-		last_end = e820->map[i].addr + e820->map[i].size;
+		if (last_end < end)
+			released += xen_release_chunk(last_end, end);
+		last_end = max(last_end, e820->map[i].addr + e820->map[i].size);
 	}
 
 	if (last_end < max_addr)
@@ -164,6 +166,7 @@ char * __init xen_memory_setup(void)
 		XENMEM_memory_map;
 	rc = HYPERVISOR_memory_op(op, &memmap);
 	if (rc == -ENOSYS) {
+		BUG_ON(xen_initial_domain());
 		memmap.nr_entries = 1;
 		map[0].addr = 0ULL;
 		map[0].size = mem_end;
@@ -201,12 +204,13 @@ char * __init xen_memory_setup(void)
 	}
 
 	/*
-	 * Even though this is normal, usable memory under Xen, reserve
-	 * ISA memory anyway because too many things think they can poke
+	 * In domU, the ISA region is normal, usable memory, but we
+	 * reserve ISA memory anyway because too many things poke
 	 * about in there.
 	 *
-	 * In a dom0 kernel, this region is identity mapped with the
-	 * hardware ISA area, so it really is out of bounds.
+	 * In Dom0, the host E820 information can leave gaps in the
+	 * ISA range, which would cause us to release those pages.  To
+	 * avoid this, we unconditionally reserve them here.
 	 */
 	e820_add_region(ISA_START_ADDRESS, ISA_END_ADDRESS - ISA_START_ADDRESS,
 			E820_RESERVED);

block/blk-core.c

@@ -1194,13 +1194,6 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	int where = ELEVATOR_INSERT_SORT;
 	int rw_flags;
 
-	/* REQ_HARDBARRIER is no more */
-	if (WARN_ONCE(bio->bi_rw & REQ_HARDBARRIER,
-		"block: HARDBARRIER is deprecated, use FLUSH/FUA instead\n")) {
-		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
-	}
-
 	/*
 	 * low level driver can indicate that it wants pages above a
 	 * certain limit bounced to low memory (ie for highmem, or even
@@ -1351,7 +1344,7 @@ static void handle_bad_sector(struct bio *bio)
 			bdevname(bio->bi_bdev, b),
 			bio->bi_rw,
 			(unsigned long long)bio->bi_sector + bio_sectors(bio),
-			(long long)(bio->bi_bdev->bd_inode->i_size >> 9));
+			(long long)(i_size_read(bio->bi_bdev->bd_inode) >> 9));
 
 	set_bit(BIO_EOF, &bio->bi_flags);
 }
@@ -1404,7 +1397,7 @@ static inline int bio_check_eod(struct bio *bio, unsigned int nr_sectors)
 		return 0;
 
 	/* Test device or partition size, when known. */
-	maxsector = bio->bi_bdev->bd_inode->i_size >> 9;
+	maxsector = i_size_read(bio->bi_bdev->bd_inode) >> 9;
 	if (maxsector) {
 		sector_t sector = bio->bi_sector;
 

block/blk-ioc.c

@@ -153,20 +153,6 @@ struct io_context *get_io_context(gfp_t gfp_flags, int node)
 }
 EXPORT_SYMBOL(get_io_context);
 
-void copy_io_context(struct io_context **pdst, struct io_context **psrc)
-{
-	struct io_context *src = *psrc;
-	struct io_context *dst = *pdst;
-
-	if (src) {
-		BUG_ON(atomic_long_read(&src->refcount) == 0);
-		atomic_long_inc(&src->refcount);
-		put_io_context(dst);
-		*pdst = src;
-	}
-}
-EXPORT_SYMBOL(copy_io_context);
-
 static int __init blk_ioc_init(void)
 {
 	iocontext_cachep = kmem_cache_create("blkdev_ioc",

block/blk-map.c

@@ -205,6 +205,8 @@ int blk_rq_map_user_iov(struct request_queue *q, struct request *rq,
 			unaligned = 1;
 			break;
 		}
+		if (!iov[i].iov_len)
+			return -EINVAL;
 	}
 
 	if (unaligned || (q->dma_pad_mask & len) || map_data)

block/compat_ioctl.c

@@ -744,13 +744,13 @@ long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg)
 		bdi->ra_pages = (arg * 512) / PAGE_CACHE_SIZE;
 		return 0;
 	case BLKGETSIZE:
-		size = bdev->bd_inode->i_size;
+		size = i_size_read(bdev->bd_inode);
 		if ((size >> 9) > ~0UL)
 			return -EFBIG;
 		return compat_put_ulong(arg, size >> 9);
 
 	case BLKGETSIZE64_32:
-		return compat_put_u64(arg, bdev->bd_inode->i_size);
+		return compat_put_u64(arg, i_size_read(bdev->bd_inode));
 
 	case BLKTRACESETUP32:
 	case BLKTRACESTART: /* compatible */

block/elevator.c

@@ -429,7 +429,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq)
 	q->nr_sorted--;
 
 	boundary = q->end_sector;
-	stop_flags = REQ_SOFTBARRIER | REQ_HARDBARRIER | REQ_STARTED;
+	stop_flags = REQ_SOFTBARRIER | REQ_STARTED;
 	list_for_each_prev(entry, &q->queue_head) {
 		struct request *pos = list_entry_rq(entry);
 
@@ -691,7 +691,7 @@ void elv_insert(struct request_queue *q, struct request *rq, int where)
 void __elv_add_request(struct request_queue *q, struct request *rq, int where,
 		       int plug)
 {
-	if (rq->cmd_flags & (REQ_SOFTBARRIER | REQ_HARDBARRIER)) {
+	if (rq->cmd_flags & REQ_SOFTBARRIER) {
 		/* barriers are scheduling boundary, update end_sector */
 		if (rq->cmd_type == REQ_TYPE_FS ||
 		    (rq->cmd_flags & REQ_DISCARD)) {

block/ioctl.c

@@ -125,7 +125,7 @@ static int blk_ioctl_discard(struct block_device *bdev, uint64_t start,
 	start >>= 9;
 	len >>= 9;
 
-	if (start + len > (bdev->bd_inode->i_size >> 9))
+	if (start + len > (i_size_read(bdev->bd_inode) >> 9))
 		return -EINVAL;
 	if (secure)
 		flags |= BLKDEV_DISCARD_SECURE;
@@ -242,6 +242,7 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		 * We need to set the startsect first, the driver may
 		 * want to override it.
 		 */
+		memset(&geo, 0, sizeof(geo));
 		geo.start = get_start_sect(bdev);
 		ret = disk->fops->getgeo(bdev, &geo);
 		if (ret)
@@ -307,12 +308,12 @@ int blkdev_ioctl(struct block_device *bdev, fmode_t mode, unsigned cmd,
 		ret = blkdev_reread_part(bdev);
 		break;
 	case BLKGETSIZE:
-		size = bdev->bd_inode->i_size;
+		size = i_size_read(bdev->bd_inode);
 		if ((size >> 9) > ~0UL)
 			return -EFBIG;
 		return put_ulong(arg, size >> 9);
 	case BLKGETSIZE64:
-		return put_u64(arg, bdev->bd_inode->i_size);
+		return put_u64(arg, i_size_read(bdev->bd_inode));
 	case BLKTRACESTART:
 	case BLKTRACESTOP:
 	case BLKTRACESETUP:

block/scsi_ioctl.c

@@ -321,33 +321,47 @@ static int sg_io(struct request_queue *q, struct gendisk *bd_disk,
 	if (hdr->iovec_count) {
 		const int size = sizeof(struct sg_iovec) * hdr->iovec_count;
 		size_t iov_data_len;
-		struct sg_iovec *iov;
+		struct sg_iovec *sg_iov;
+		struct iovec *iov;
+		int i;
 
-		iov = kmalloc(size, GFP_KERNEL);
-		if (!iov) {
+		sg_iov = kmalloc(size, GFP_KERNEL);
+		if (!sg_iov) {
 			ret = -ENOMEM;
 			goto out;
 		}
 
-		if (copy_from_user(iov, hdr->dxferp, size)) {
-			kfree(iov);
+		if (copy_from_user(sg_iov, hdr->dxferp, size)) {
+			kfree(sg_iov);
 			ret = -EFAULT;
 			goto out;
 		}
 
+		/*
+		 * Sum up the vecs, making sure they don't overflow
+		 */
+		iov = (struct iovec *) sg_iov;
+		iov_data_len = 0;
+		for (i = 0; i < hdr->iovec_count; i++) {
+			if (iov_data_len + iov[i].iov_len < iov_data_len) {
+				kfree(sg_iov);
+				ret = -EINVAL;
+				goto out;
+			}
+			iov_data_len += iov[i].iov_len;
+		}
+
 		/* SG_IO howto says that the shorter of the two wins */
-		iov_data_len = iov_length((struct iovec *)iov,
-					  hdr->iovec_count);
 		if (hdr->dxfer_len < iov_data_len) {
-			hdr->iovec_count = iov_shorten((struct iovec *)iov,
+			hdr->iovec_count = iov_shorten(iov,
 						       hdr->iovec_count,
 						       hdr->dxfer_len);
 			iov_data_len = hdr->dxfer_len;
 		}
 
-		ret = blk_rq_map_user_iov(q, rq, NULL, iov, hdr->iovec_count,
+		ret = blk_rq_map_user_iov(q, rq, NULL, sg_iov, hdr->iovec_count,
 					  iov_data_len, GFP_KERNEL);
-		kfree(iov);
+		kfree(sg_iov);
 	} else if (hdr->dxfer_len)
 		ret = blk_rq_map_user(q, rq, NULL, hdr->dxferp, hdr->dxfer_len,
 				      GFP_KERNEL);

crypto/pcrypt.c

@@ -504,7 +504,6 @@ err:
 
 static void pcrypt_fini_padata(struct padata_pcrypt *pcrypt)
 {
-	kobject_put(&pcrypt->pinst->kobj);
 	free_cpumask_var(pcrypt->cb_cpumask->mask);
 	kfree(pcrypt->cb_cpumask);
 

drivers/acpi/debugfs.c

@@ -80,7 +80,7 @@ int __init acpi_debugfs_init(void)
 	if (!acpi_dir)
 		goto err;
 
-	cm_dentry = debugfs_create_file("custom_method", S_IWUGO,
+	cm_dentry = debugfs_create_file("custom_method", S_IWUSR,
 					acpi_dir, NULL, &cm_fops);
 	if (!cm_dentry)
 		goto err;

drivers/ata/libata-scsi.c

@@ -2552,8 +2552,11 @@ static void atapi_qc_complete(struct ata_queued_cmd *qc)
 		 *
 		 * If door lock fails, always clear sdev->locked to
 		 * avoid this infinite loop.
+		 *
+		 * This may happen before SCSI scan is complete.  Make
+		 * sure qc->dev->sdev isn't NULL before dereferencing.
 		 */
-		if (qc->cdb[0] == ALLOW_MEDIUM_REMOVAL)
+		if (qc->cdb[0] == ALLOW_MEDIUM_REMOVAL && qc->dev->sdev)
 			qc->dev->sdev->locked = 0;
 
 		qc->scsicmd->result = SAM_STAT_CHECK_CONDITION;

drivers/ata/pata_legacy.c

@@ -142,7 +142,7 @@ static int autospeed;		/* Chip present which snoops speed changes */
 static int pio_mask = ATA_PIO4;	/* PIO range for autospeed devices */
 static int iordy_mask = 0xFFFFFFFF;	/* Use iordy if available */
 
-#ifdef PATA_WINBOND_VLB_MODULE
+#ifdef CONFIG_PATA_WINBOND_VLB_MODULE
 static int winbond = 1;		/* Set to probe Winbond controllers,
 					give I/O port if non standard */
 #else

drivers/ata/pata_octeon_cf.c

@@ -652,8 +652,6 @@ static irqreturn_t octeon_cf_interrupt(int irq, void *dev_instance)
 		struct octeon_cf_data *ocd;
 
 		ap = host->ports[i];
-		ocd = ap->dev->platform_data;
-
 		ocd = ap->dev->platform_data;
 		cf_port = ap->private_data;
 		dma_int.u64 =

drivers/atm/solos-attrlist.c

@@ -1,6 +1,7 @@
 SOLOS_ATTR_RO(DriverVersion)
 SOLOS_ATTR_RO(APIVersion)
 SOLOS_ATTR_RO(FirmwareVersion)
+SOLOS_ATTR_RO(Version)
 // SOLOS_ATTR_RO(DspVersion)
 // SOLOS_ATTR_RO(CommonHandshake)
 SOLOS_ATTR_RO(Connected)

drivers/atm/solos-pci.c

@@ -1161,6 +1161,14 @@ static int fpga_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	dev_info(&dev->dev, "Solos FPGA Version %d.%02d svn-%d\n",
 		 major_ver, minor_ver, fpga_ver);
 
+	if (fpga_ver < 37 && (fpga_upgrade || firmware_upgrade ||
+			      db_fpga_upgrade || db_firmware_upgrade)) {
+		dev_warn(&dev->dev,
+			 "FPGA too old; cannot upgrade flash. Use JTAG.\n");
+		fpga_upgrade = firmware_upgrade = 0;
+		db_fpga_upgrade = db_firmware_upgrade = 0;
+	}
+
 	if (card->fpga_version >= DMA_SUPPORTED){
 		card->using_dma = 1;
 	} else {

drivers/block/aoe/aoeblk.c

@@ -180,9 +180,6 @@ aoeblk_make_request(struct request_queue *q, struct bio *bio)
 		BUG();
 		bio_endio(bio, -ENXIO);
 		return 0;
-	} else if (bio->bi_rw & REQ_HARDBARRIER) {
-		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
 	} else if (bio->bi_io_vec == NULL) {
 		printk(KERN_ERR "aoe: bi_io_vec is NULL\n");
 		BUG();

drivers/block/cciss.c

@@ -113,6 +113,8 @@ static struct board_type products[] = {
 	{0x409D0E11, "Smart Array 6400 EM", &SA5_access},
 	{0x40910E11, "Smart Array 6i", &SA5_access},
 	{0x3225103C, "Smart Array P600", &SA5_access},
+	{0x3223103C, "Smart Array P800", &SA5_access},
+	{0x3234103C, "Smart Array P400", &SA5_access},
 	{0x3235103C, "Smart Array P400i", &SA5_access},
 	{0x3211103C, "Smart Array E200i", &SA5_access},
 	{0x3212103C, "Smart Array E200", &SA5_access},
@@ -3753,7 +3755,7 @@ static void __devinit cciss_wait_for_mode_change_ack(ctlr_info_t *h)
 	for (i = 0; i < MAX_CONFIG_WAIT; i++) {
 		if (!(readl(h->vaddr + SA5_DOORBELL) & CFGTBL_ChangeReq))
 			break;
-		msleep(10);
+		usleep_range(10000, 20000);
 	}
 }
 
@@ -3937,10 +3939,9 @@ static int __devinit cciss_lookup_board_id(struct pci_dev *pdev, u32 *board_id)
 	*board_id = ((subsystem_device_id << 16) & 0xffff0000) |
 			subsystem_vendor_id;
 
-	for (i = 0; i < ARRAY_SIZE(products); i++) {
+	for (i = 0; i < ARRAY_SIZE(products); i++)
 		if (*board_id == products[i].board_id)
 			return i;
-	}
 	dev_warn(&pdev->dev, "unrecognized board ID: 0x%08x, ignoring.\n",
 		*board_id);
 	return -ENODEV;
@@ -3971,18 +3972,31 @@ static int __devinit cciss_pci_find_memory_BAR(struct pci_dev *pdev,
 	return -ENODEV;
 }
 
-static int __devinit cciss_wait_for_board_ready(ctlr_info_t *h)
+static int __devinit cciss_wait_for_board_state(struct pci_dev *pdev,
+	void __iomem *vaddr, int wait_for_ready)
+#define BOARD_READY 1
+#define BOARD_NOT_READY 0
 {
-	int i;
+	int i, iterations;
 	u32 scratchpad;
 
-	for (i = 0; i < CCISS_BOARD_READY_ITERATIONS; i++) {
-		scratchpad = readl(h->vaddr + SA5_SCRATCHPAD_OFFSET);
-		if (scratchpad == CCISS_FIRMWARE_READY)
-			return 0;
+	if (wait_for_ready)
+		iterations = CCISS_BOARD_READY_ITERATIONS;
+	else
+		iterations = CCISS_BOARD_NOT_READY_ITERATIONS;
+
+	for (i = 0; i < iterations; i++) {
+		scratchpad = readl(vaddr + SA5_SCRATCHPAD_OFFSET);
+		if (wait_for_ready) {
+			if (scratchpad == CCISS_FIRMWARE_READY)
+				return 0;
+		} else {
+			if (scratchpad != CCISS_FIRMWARE_READY)
+				return 0;
+		}
 		msleep(CCISS_BOARD_READY_POLL_INTERVAL_MSECS);
 	}
-	dev_warn(&h->pdev->dev, "board not ready, timed out.\n");
+	dev_warn(&pdev->dev, "board not ready, timed out.\n");
 	return -ENODEV;
 }
 
@@ -4031,6 +4045,11 @@ static int __devinit cciss_find_cfgtables(ctlr_info_t *h)
 static void __devinit cciss_get_max_perf_mode_cmds(struct ctlr_info *h)
 {
 	h->max_commands = readl(&(h->cfgtable->MaxPerformantModeCommands));
+
+	/* Limit commands in memory limited kdump scenario. */
+	if (reset_devices && h->max_commands > 32)
+		h->max_commands = 32;
+
 	if (h->max_commands < 16) {
 		dev_warn(&h->pdev->dev, "Controller reports "
 			"max supported commands of %d, an obvious lie. "
@@ -4148,7 +4167,7 @@ static int __devinit cciss_pci_init(ctlr_info_t *h)
 		err = -ENOMEM;
 		goto err_out_free_res;
 	}
-	err = cciss_wait_for_board_ready(h);
+	err = cciss_wait_for_board_state(h->pdev, h->vaddr, BOARD_READY);
 	if (err)
 		goto err_out_free_res;
 	err = cciss_find_cfgtables(h);
@@ -4313,36 +4332,6 @@ static __devinit int cciss_message(struct pci_dev *pdev, unsigned char opcode, u
 #define cciss_soft_reset_controller(p) cciss_message(p, 1, 0)
 #define cciss_noop(p) cciss_message(p, 3, 0)
 
-static __devinit int cciss_reset_msi(struct pci_dev *pdev)
-{
-/* the #defines are stolen from drivers/pci/msi.h. */
-#define msi_control_reg(base)		(base + PCI_MSI_FLAGS)
-#define PCI_MSIX_FLAGS_ENABLE		(1 << 15)
-
-	int pos;
-	u16 control = 0;
-
-	pos = pci_find_capability(pdev, PCI_CAP_ID_MSI);
-	if (pos) {
-		pci_read_config_word(pdev, msi_control_reg(pos), &control);
-		if (control & PCI_MSI_FLAGS_ENABLE) {
-			dev_info(&pdev->dev, "resetting MSI\n");
-			pci_write_config_word(pdev, msi_control_reg(pos), control & ~PCI_MSI_FLAGS_ENABLE);
-		}
-	}
-
-	pos = pci_find_capability(pdev, PCI_CAP_ID_MSIX);
-	if (pos) {
-		pci_read_config_word(pdev, msi_control_reg(pos), &control);
-		if (control & PCI_MSIX_FLAGS_ENABLE) {
-			dev_info(&pdev->dev, "resetting MSI-X\n");
-			pci_write_config_word(pdev, msi_control_reg(pos), control & ~PCI_MSIX_FLAGS_ENABLE);
-		}
-	}
-
-	return 0;
-}
-
 static int cciss_controller_hard_reset(struct pci_dev *pdev,
 	void * __iomem vaddr, bool use_doorbell)
 {
@@ -4397,17 +4386,17 @@ static int cciss_controller_hard_reset(struct pci_dev *pdev,
  * states or using the doorbell register. */
 static __devinit int cciss_kdump_hard_reset_controller(struct pci_dev *pdev)
 {
-	u16 saved_config_space[32];
 	u64 cfg_offset;
 	u32 cfg_base_addr;
 	u64 cfg_base_addr_index;
 	void __iomem *vaddr;
 	unsigned long paddr;
 	u32 misc_fw_support, active_transport;
-	int rc, i;
+	int rc;
 	CfgTable_struct __iomem *cfgtable;
 	bool use_doorbell;
 	u32 board_id;
+	u16 command_register;
 
 	/* For controllers as old a the p600, this is very nearly
 	 * the same thing as
@@ -4417,14 +4406,6 @@ static __devinit int cciss_kdump_hard_reset_controller(struct pci_dev *pdev)
 	 * pci_set_power_state(pci_dev, PCI_D0);
 	 * pci_restore_state(pci_dev);
 	 *
-	 * but we can't use these nice canned kernel routines on
-	 * kexec, because they also check the MSI/MSI-X state in PCI
-	 * configuration space and do the wrong thing when it is
-	 * set/cleared.  Also, the pci_save/restore_state functions
-	 * violate the ordering requirements for restoring the
-	 * configuration space from the CCISS document (see the
-	 * comment below).  So we roll our own ....
-	 *
 	 * For controllers newer than the P600, the pci power state
 	 * method of resetting doesn't work so we have another way
 	 * using the doorbell register.
@@ -4443,8 +4424,13 @@ static __devinit int cciss_kdump_hard_reset_controller(struct pci_dev *pdev)
 		return -ENODEV;
 	}
 
-	for (i = 0; i < 32; i++)
-		pci_read_config_word(pdev, 2*i, &saved_config_space[i]);
+	/* Save the PCI command register */
+	pci_read_config_word(pdev, 4, &command_register);
+	/* Turn the board off.  This is so that later pci_restore_state()
+	 * won't turn the board on before the rest of config space is ready.
+	 */
+	pci_disable_device(pdev);
+	pci_save_state(pdev);
 
 	/* find the first memory BAR, so we can find the cfg table */
 	rc = cciss_pci_find_memory_BAR(pdev, &paddr);
@@ -4479,26 +4465,32 @@ static __devinit int cciss_kdump_hard_reset_controller(struct pci_dev *pdev)
 	rc = cciss_controller_hard_reset(pdev, vaddr, use_doorbell);
 	if (rc)
 		goto unmap_cfgtable;
-
-	/* Restore the PCI configuration space.  The Open CISS
-	 * Specification says, "Restore the PCI Configuration
-	 * Registers, offsets 00h through 60h. It is important to
-	 * restore the command register, 16-bits at offset 04h,
-	 * last. Do not restore the configuration status register,
-	 * 16-bits at offset 06h."  Note that the offset is 2*i.
-	 */
-	for (i = 0; i < 32; i++) {
-		if (i == 2 || i == 3)
-			continue;
-		pci_write_config_word(pdev, 2*i, saved_config_space[i]);
+	pci_restore_state(pdev);
+	rc = pci_enable_device(pdev);
+	if (rc) {
+		dev_warn(&pdev->dev, "failed to enable device.\n");
+		goto unmap_cfgtable;
 	}
-	wmb();
-	pci_write_config_word(pdev, 4, saved_config_space[2]);
+	pci_write_config_word(pdev, 4, command_register);
 
 	/* Some devices (notably the HP Smart Array 5i Controller)
 	   need a little pause here */
 	msleep(CCISS_POST_RESET_PAUSE_MSECS);
 
+	/* Wait for board to become not ready, then ready. */
+	dev_info(&pdev->dev, "Waiting for board to become ready.\n");
+	rc = cciss_wait_for_board_state(pdev, vaddr, BOARD_NOT_READY);
+	if (rc) /* Don't bail, might be E500, etc. which can't be reset */
+		dev_warn(&pdev->dev,
+			"failed waiting for board to become not ready\n");
+	rc = cciss_wait_for_board_state(pdev, vaddr, BOARD_READY);
+	if (rc) {
+		dev_warn(&pdev->dev,
+			"failed waiting for board to become ready\n");
+		goto unmap_cfgtable;
+	}
+	dev_info(&pdev->dev, "board ready.\n");
+
 	/* Controller should be in simple mode at this point.  If it's not,
 	 * It means we're on one of those controllers which doesn't support
 	 * the doorbell reset method and on which the PCI power management reset
@@ -4539,8 +4531,6 @@ static __devinit int cciss_init_reset_devices(struct pci_dev *pdev)
 		return 0; /* just try to do the kdump anyhow. */
 	if (rc)
 		return -ENODEV;
-	if (cciss_reset_msi(pdev))
-		return -ENODEV;
 
 	/* Now try to get the controller to respond to a no-op */
 	for (i = 0; i < CCISS_POST_RESET_NOOP_RETRIES; i++) {
@@ -4936,7 +4926,8 @@ static void __exit cciss_cleanup(void)
 		}
 	}
 	kthread_stop(cciss_scan_thread);
-	remove_proc_entry("driver/cciss", NULL);
+	if (proc_cciss)
+		remove_proc_entry("driver/cciss", NULL);
 	bus_unregister(&cciss_bus_type);
 }
 

drivers/block/cciss.h

@@ -200,10 +200,14 @@ struct ctlr_info
  * the above.
  */
 #define CCISS_BOARD_READY_WAIT_SECS (120)
+#define CCISS_BOARD_NOT_READY_WAIT_SECS (10)
 #define CCISS_BOARD_READY_POLL_INTERVAL_MSECS (100)
 #define CCISS_BOARD_READY_ITERATIONS \
 	((CCISS_BOARD_READY_WAIT_SECS * 1000) / \
 		CCISS_BOARD_READY_POLL_INTERVAL_MSECS)
+#define CCISS_BOARD_NOT_READY_ITERATIONS \
+	((CCISS_BOARD_NOT_READY_WAIT_SECS * 1000) / \
+		CCISS_BOARD_READY_POLL_INTERVAL_MSECS)
 #define CCISS_POST_RESET_PAUSE_MSECS (3000)
 #define CCISS_POST_RESET_NOOP_INTERVAL_MSECS (1000)
 #define CCISS_POST_RESET_NOOP_RETRIES (12)

drivers/block/drbd/drbd_actlog.c

@@ -78,11 +78,10 @@ static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
 	init_completion(&md_io.event);
 	md_io.error = 0;
 
-	if ((rw & WRITE) && !test_bit(MD_NO_BARRIER, &mdev->flags))
-		rw |= REQ_HARDBARRIER;
+	if ((rw & WRITE) && !test_bit(MD_NO_FUA, &mdev->flags))
+		rw |= REQ_FUA;
 	rw |= REQ_UNPLUG | REQ_SYNC;
 
- retry:
 	bio = bio_alloc(GFP_NOIO, 1);
 	bio->bi_bdev = bdev->md_bdev;
 	bio->bi_sector = sector;
@@ -100,17 +99,6 @@ static int _drbd_md_sync_page_io(struct drbd_conf *mdev,
 	wait_for_completion(&md_io.event);
 	ok = bio_flagged(bio, BIO_UPTODATE) && md_io.error == 0;
 
-	/* check for unsupported barrier op.
-	 * would rather check on EOPNOTSUPP, but that is not reliable.
-	 * don't try again for ANY return value != 0 */
-	if (unlikely((bio->bi_rw & REQ_HARDBARRIER) && !ok)) {
-		/* Try again with no barrier */
-		dev_warn(DEV, "Barriers not supported on meta data device - disabling\n");
-		set_bit(MD_NO_BARRIER, &mdev->flags);
-		rw &= ~REQ_HARDBARRIER;
-		bio_put(bio);
-		goto retry;
-	}
  out:
 	bio_put(bio);
 	return ok;
@@ -284,18 +272,32 @@ w_al_write_transaction(struct drbd_conf *mdev, struct drbd_work *w, int unused)
 	u32 xor_sum = 0;
 
 	if (!get_ldev(mdev)) {
-		dev_err(DEV, "get_ldev() failed in w_al_write_transaction\n");
+		dev_err(DEV,
+			"disk is %s, cannot start al transaction (-%d +%d)\n",
+			drbd_disk_str(mdev->state.disk), evicted, new_enr);
 		complete(&((struct update_al_work *)w)->event);
 		return 1;
 	}
 	/* do we have to do a bitmap write, first?
 	 * TODO reduce maximum latency:
 	 * submit both bios, then wait for both,
-	 * instead of doing two synchronous sector writes. */
+	 * instead of doing two synchronous sector writes.
+	 * For now, we must not write the transaction,
+	 * if we cannot write out the bitmap of the evicted extent. */
 	if (mdev->state.conn < C_CONNECTED && evicted != LC_FREE)
 		drbd_bm_write_sect(mdev, evicted/AL_EXT_PER_BM_SECT);
 
-	mutex_lock(&mdev->md_io_mutex); /* protects md_io_page, al_tr_cycle, ... */
+	/* The bitmap write may have failed, causing a state change. */
+	if (mdev->state.disk < D_INCONSISTENT) {
+		dev_err(DEV,
+			"disk is %s, cannot write al transaction (-%d +%d)\n",
+			drbd_disk_str(mdev->state.disk), evicted, new_enr);
+		complete(&((struct update_al_work *)w)->event);
+		put_ldev(mdev);
+		return 1;
+	}
+
+	mutex_lock(&mdev->md_io_mutex); /* protects md_io_buffer, al_tr_cycle, ... */
 	buffer = (struct al_transaction *)page_address(mdev->md_io_page);
 
 	buffer->magic = __constant_cpu_to_be32(DRBD_MAGIC);
@@ -739,7 +741,7 @@ void drbd_al_apply_to_bm(struct drbd_conf *mdev)
 	unsigned int enr;
 	unsigned long add = 0;
 	char ppb[10];
-	int i;
+	int i, tmp;
 
 	wait_event(mdev->al_wait, lc_try_lock(mdev->act_log));
 
@@ -747,7 +749,9 @@ void drbd_al_apply_to_bm(struct drbd_conf *mdev)
 		enr = lc_element_by_index(mdev->act_log, i)->lc_number;
 		if (enr == LC_FREE)
 			continue;
-		add += drbd_bm_ALe_set_all(mdev, enr);
+		tmp = drbd_bm_ALe_set_all(mdev, enr);
+		dynamic_dev_dbg(DEV, "AL: set %d bits in extent %u\n", tmp, enr);
+		add += tmp;
 	}
 
 	lc_unlock(mdev->act_log);

drivers/block/drbd/drbd_int.h

@@ -114,11 +114,11 @@ struct drbd_conf;
 #define D_ASSERT(exp)	if (!(exp)) \
 	 dev_err(DEV, "ASSERT( " #exp " ) in %s:%d\n", __FILE__, __LINE__)
 
-#define ERR_IF(exp) if (({				\
-	int _b = (exp) != 0;				\
-	if (_b) dev_err(DEV, "%s: (%s) in %s:%d\n",	\
-		__func__, #exp, __FILE__, __LINE__);	\
-	 _b;						\
+#define ERR_IF(exp) if (({						\
+	int _b = (exp) != 0;						\
+	if (_b) dev_err(DEV, "ASSERT FAILED: %s: (%s) in %s:%d\n",	\
+			__func__, #exp, __FILE__, __LINE__);		\
+	_b;								\
 	}))
 
 /* Defines to control fault insertion */
@@ -749,17 +749,12 @@ struct drbd_epoch {
 
 /* drbd_epoch flag bits */
 enum {
-	DE_BARRIER_IN_NEXT_EPOCH_ISSUED,
-	DE_BARRIER_IN_NEXT_EPOCH_DONE,
-	DE_CONTAINS_A_BARRIER,
 	DE_HAVE_BARRIER_NUMBER,
-	DE_IS_FINISHING,
 };
 
 enum epoch_event {
 	EV_PUT,
 	EV_GOT_BARRIER_NR,
-	EV_BARRIER_DONE,
 	EV_BECAME_LAST,
 	EV_CLEANUP = 32, /* used as flag */
 };
@@ -801,11 +796,6 @@ enum {
 	__EE_CALL_AL_COMPLETE_IO,
 	__EE_MAY_SET_IN_SYNC,
 
-	/* This epoch entry closes an epoch using a barrier.
-	 * On sucessful completion, the epoch is released,
-	 * and the P_BARRIER_ACK send. */
-	__EE_IS_BARRIER,
-
 	/* In case a barrier failed,
 	 * we need to resubmit without the barrier flag. */
 	__EE_RESUBMITTED,
@@ -820,7 +810,6 @@ enum {
 };
 #define EE_CALL_AL_COMPLETE_IO (1<<__EE_CALL_AL_COMPLETE_IO)
 #define EE_MAY_SET_IN_SYNC     (1<<__EE_MAY_SET_IN_SYNC)
-#define EE_IS_BARRIER          (1<<__EE_IS_BARRIER)
 #define	EE_RESUBMITTED         (1<<__EE_RESUBMITTED)
 #define EE_WAS_ERROR           (1<<__EE_WAS_ERROR)
 #define EE_HAS_DIGEST          (1<<__EE_HAS_DIGEST)
@@ -843,16 +832,15 @@ enum {
 				 * Gets cleared when the state.conn
 				 * goes into C_CONNECTED state. */
 	WRITE_BM_AFTER_RESYNC,	/* A kmalloc() during resync failed */
-	NO_BARRIER_SUPP,	/* underlying block device doesn't implement barriers */
 	CONSIDER_RESYNC,
 
-	MD_NO_BARRIER,		/* meta data device does not support barriers,
-				   so don't even try */
+	MD_NO_FUA,		/* Users wants us to not use FUA/FLUSH on meta data dev */
 	SUSPEND_IO,		/* suspend application io */
 	BITMAP_IO,		/* suspend application io;
 				   once no more io in flight, start bitmap io */
 	BITMAP_IO_QUEUED,       /* Started bitmap IO */
-	GO_DISKLESS,		/* Disk failed, local_cnt reached zero, we are going diskless */
+	GO_DISKLESS,		/* Disk is being detached, on io-error or admin request. */
+	WAS_IO_ERROR,		/* Local disk failed returned IO error */
 	RESYNC_AFTER_NEG,       /* Resync after online grow after the attach&negotiate finished. */
 	NET_CONGESTED,		/* The data socket is congested */
 
@@ -947,7 +935,6 @@ enum write_ordering_e {
 	WO_none,
 	WO_drain_io,
 	WO_bdev_flush,
-	WO_bio_barrier
 };
 
 struct fifo_buffer {
@@ -1281,6 +1268,7 @@ extern int drbd_bmio_set_n_write(struct drbd_conf *mdev);
 extern int drbd_bmio_clear_n_write(struct drbd_conf *mdev);
 extern int drbd_bitmap_io(struct drbd_conf *mdev, int (*io_fn)(struct drbd_conf *), char *why);
 extern void drbd_go_diskless(struct drbd_conf *mdev);
+extern void drbd_ldev_destroy(struct drbd_conf *mdev);
 
 
 /* Meta data layout
@@ -1798,17 +1786,17 @@ static inline void __drbd_chk_io_error_(struct drbd_conf *mdev, int forcedetach,
 	case EP_PASS_ON:
 		if (!forcedetach) {
 			if (__ratelimit(&drbd_ratelimit_state))
-				dev_err(DEV, "Local IO failed in %s."
-					     "Passing error on...\n", where);
+				dev_err(DEV, "Local IO failed in %s.\n", where);
 			break;
 		}
 		/* NOTE fall through to detach case if forcedetach set */
 	case EP_DETACH:
 	case EP_CALL_HELPER:
+		set_bit(WAS_IO_ERROR, &mdev->flags);
 		if (mdev->state.disk > D_FAILED) {
 			_drbd_set_state(_NS(mdev, disk, D_FAILED), CS_HARD, NULL);
-			dev_err(DEV, "Local IO failed in %s."
-				     "Detaching...\n", where);
+			dev_err(DEV,
+				"Local IO failed in %s. Detaching...\n", where);
 		}
 		break;
 	}
@@ -1874,7 +1862,7 @@ static inline sector_t drbd_md_last_sector(struct drbd_backing_dev *bdev)
 static inline sector_t drbd_get_capacity(struct block_device *bdev)
 {
 	/* return bdev ? get_capacity(bdev->bd_disk) : 0; */
-	return bdev ? bdev->bd_inode->i_size >> 9 : 0;
+	return bdev ? i_size_read(bdev->bd_inode) >> 9 : 0;
 }
 
 /**
@@ -2127,7 +2115,11 @@ static inline void put_ldev(struct drbd_conf *mdev)
 	__release(local);
 	D_ASSERT(i >= 0);
 	if (i == 0) {
+		if (mdev->state.disk == D_DISKLESS)
+			/* even internal references gone, safe to destroy */
+			drbd_ldev_destroy(mdev);
 		if (mdev->state.disk == D_FAILED)
+			/* all application IO references gone. */
 			drbd_go_diskless(mdev);
 		wake_up(&mdev->misc_wait);
 	}
@@ -2138,6 +2130,10 @@ static inline int _get_ldev_if_state(struct drbd_conf *mdev, enum drbd_disk_stat
 {
 	int io_allowed;
 
+	/* never get a reference while D_DISKLESS */
+	if (mdev->state.disk == D_DISKLESS)
+		return 0;
+
 	atomic_inc(&mdev->local_cnt);
 	io_allowed = (mdev->state.disk >= mins);
 	if (!io_allowed)
@@ -2406,12 +2402,12 @@ static inline void drbd_md_flush(struct drbd_conf *mdev)
 {
 	int r;
 
-	if (test_bit(MD_NO_BARRIER, &mdev->flags))
+	if (test_bit(MD_NO_FUA, &mdev->flags))
 		return;
 
 	r = blkdev_issue_flush(mdev->ldev->md_bdev, GFP_KERNEL, NULL);
 	if (r) {
-		set_bit(MD_NO_BARRIER, &mdev->flags);
+		set_bit(MD_NO_FUA, &mdev->flags);
 		dev_err(DEV, "meta data flush failed with status %d, disabling md-flushes\n", r);
 	}
 }

drivers/block/drbd/drbd_main.c

@@ -835,6 +835,15 @@ static union drbd_state sanitize_state(struct drbd_conf *mdev, union drbd_state
 	    ns.conn != C_UNCONNECTED && ns.conn != C_DISCONNECTING && ns.conn <= C_TEAR_DOWN)
 		ns.conn = os.conn;
 
+	/* we cannot fail (again) if we already detached */
+	if (ns.disk == D_FAILED && os.disk == D_DISKLESS)
+		ns.disk = D_DISKLESS;
+
+	/* if we are only D_ATTACHING yet,
+	 * we can (and should) go directly to D_DISKLESS. */
+	if (ns.disk == D_FAILED && os.disk == D_ATTACHING)
+		ns.disk = D_DISKLESS;
+
 	/* After C_DISCONNECTING only C_STANDALONE may follow */
 	if (os.conn == C_DISCONNECTING && ns.conn != C_STANDALONE)
 		ns.conn = os.conn;
@@ -1056,7 +1065,15 @@ int __drbd_set_state(struct drbd_conf *mdev,
 	    !test_and_set_bit(CONFIG_PENDING, &mdev->flags))
 		set_bit(DEVICE_DYING, &mdev->flags);
 
-	mdev->state.i = ns.i;
+	/* if we are going -> D_FAILED or D_DISKLESS, grab one extra reference
+	 * on the ldev here, to be sure the transition -> D_DISKLESS resp.
+	 * drbd_ldev_destroy() won't happen before our corresponding
+	 * after_state_ch works run, where we put_ldev again. */
+	if ((os.disk != D_FAILED && ns.disk == D_FAILED) ||
+	    (os.disk != D_DISKLESS && ns.disk == D_DISKLESS))
+		atomic_inc(&mdev->local_cnt);
+
+	mdev->state = ns;
 	wake_up(&mdev->misc_wait);
 	wake_up(&mdev->state_wait);
 
@@ -1268,7 +1285,6 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
 			if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
 				drbd_uuid_new_current(mdev);
 				clear_bit(NEW_CUR_UUID, &mdev->flags);
-				drbd_md_sync(mdev);
 			}
 			spin_lock_irq(&mdev->req_lock);
 			_drbd_set_state(_NS(mdev, susp_fen, 0), CS_VERBOSE, NULL);
@@ -1365,63 +1381,64 @@ static void after_state_ch(struct drbd_conf *mdev, union drbd_state os,
 	    os.disk > D_INCONSISTENT && ns.disk == D_INCONSISTENT)
 		drbd_queue_bitmap_io(mdev, &drbd_bmio_set_n_write, NULL, "set_n_write from invalidate");
 
-	/* first half of local IO error */
-	if (os.disk > D_FAILED && ns.disk == D_FAILED) {
-		enum drbd_io_error_p eh = EP_PASS_ON;
+	/* first half of local IO error, failure to attach,
+	 * or administrative detach */
+	if (os.disk != D_FAILED && ns.disk == D_FAILED) {
+		enum drbd_io_error_p eh;
+		int was_io_error;
+		/* corresponding get_ldev was in __drbd_set_state, to serialize
+		 * our cleanup here with the transition to D_DISKLESS,
+		 * so it is safe to dreference ldev here. */
+		eh = mdev->ldev->dc.on_io_error;
+		was_io_error = test_and_clear_bit(WAS_IO_ERROR, &mdev->flags);
+
+		/* current state still has to be D_FAILED,
+		 * there is only one way out: to D_DISKLESS,
+		 * and that may only happen after our put_ldev below. */
+		if (mdev->state.disk != D_FAILED)
+			dev_err(DEV,
+				"ASSERT FAILED: disk is %s during detach\n",
+				drbd_disk_str(mdev->state.disk));
 
 		if (drbd_send_state(mdev))
-			dev_warn(DEV, "Notified peer that my disk is broken.\n");
+			dev_warn(DEV, "Notified peer that I am detaching my disk\n");
 		else
-			dev_err(DEV, "Sending state for drbd_io_error() failed\n");
+			dev_err(DEV, "Sending state for detaching disk failed\n");
 
 		drbd_rs_cancel_all(mdev);
 
-		if (get_ldev_if_state(mdev, D_FAILED)) {
-			eh = mdev->ldev->dc.on_io_error;
-			put_ldev(mdev);
-		}
-		if (eh == EP_CALL_HELPER)
+		/* In case we want to get something to stable storage still,
+		 * this may be the last chance.
+		 * Following put_ldev may transition to D_DISKLESS. */
+		drbd_md_sync(mdev);
+		put_ldev(mdev);
+
+		if (was_io_error && eh == EP_CALL_HELPER)
 			drbd_khelper(mdev, "local-io-error");
 	}
 
+        /* second half of local IO error, failure to attach,
+         * or administrative detach,
+         * after local_cnt references have reached zero again */
+        if (os.disk != D_DISKLESS && ns.disk == D_DISKLESS) {
+                /* We must still be diskless,
+                 * re-attach has to be serialized with this! */
+                if (mdev->state.disk != D_DISKLESS)
+                        dev_err(DEV,
+                                "ASSERT FAILED: disk is %s while going diskless\n",
+                                drbd_disk_str(mdev->state.disk));
 
-	/* second half of local IO error handling,
-	 * after local_cnt references have reached zero: */
-	if (os.disk == D_FAILED && ns.disk == D_DISKLESS) {
-		mdev->rs_total = 0;
-		mdev->rs_failed = 0;
-		atomic_set(&mdev->rs_pending_cnt, 0);
-	}
-
-	if (os.disk > D_DISKLESS && ns.disk == D_DISKLESS) {
-		/* We must still be diskless,
-		 * re-attach has to be serialized with this! */
-		if (mdev->state.disk != D_DISKLESS)
-			dev_err(DEV,
-				"ASSERT FAILED: disk is %s while going diskless\n",
-				drbd_disk_str(mdev->state.disk));
+                mdev->rs_total = 0;
+                mdev->rs_failed = 0;
+                atomic_set(&mdev->rs_pending_cnt, 0);
 
-		/* we cannot assert local_cnt == 0 here, as get_ldev_if_state
-		 * will inc/dec it frequently. Since we became D_DISKLESS, no
-		 * one has touched the protected members anymore, though, so we
-		 * are safe to free them here. */
 		if (drbd_send_state(mdev))
-			dev_warn(DEV, "Notified peer that I detached my disk.\n");
+			dev_warn(DEV, "Notified peer that I'm now diskless.\n");
 		else
-			dev_err(DEV, "Sending state for detach failed\n");
-
-		lc_destroy(mdev->resync);
-		mdev->resync = NULL;
-		lc_destroy(mdev->act_log);
-		mdev->act_log = NULL;
-		__no_warn(local,
-			drbd_free_bc(mdev->ldev);
-			mdev->ldev = NULL;);
-
-		if (mdev->md_io_tmpp) {
-			__free_page(mdev->md_io_tmpp);
-			mdev->md_io_tmpp = NULL;
-		}
+			dev_err(DEV, "Sending state for being diskless failed\n");
+		/* corresponding get_ldev in __drbd_set_state
+		 * this may finaly trigger drbd_ldev_destroy. */
+		put_ldev(mdev);
 	}
 
 	/* Disks got bigger while they were detached */
@@ -2772,11 +2789,6 @@ void drbd_init_set_defaults(struct drbd_conf *mdev)
 
 	drbd_set_defaults(mdev);
 
-	/* for now, we do NOT yet support it,
-	 * even though we start some framework
-	 * to eventually support barriers */
-	set_bit(NO_BARRIER_SUPP, &mdev->flags);
-
 	atomic_set(&mdev->ap_bio_cnt, 0);
 	atomic_set(&mdev->ap_pending_cnt, 0);
 	atomic_set(&mdev->rs_pending_cnt, 0);
@@ -2842,7 +2854,7 @@ void drbd_init_set_defaults(struct drbd_conf *mdev)
 	drbd_thread_init(mdev, &mdev->asender, drbd_asender);
 
 	mdev->agreed_pro_version = PRO_VERSION_MAX;
-	mdev->write_ordering = WO_bio_barrier;
+	mdev->write_ordering = WO_bdev_flush;
 	mdev->resync_wenr = LC_FREE;
 }
 
@@ -2899,7 +2911,6 @@ void drbd_mdev_cleanup(struct drbd_conf *mdev)
 	D_ASSERT(list_empty(&mdev->resync_work.list));
 	D_ASSERT(list_empty(&mdev->unplug_work.list));
 	D_ASSERT(list_empty(&mdev->go_diskless.list));
-
 }
 
 
@@ -3660,6 +3671,8 @@ void drbd_uuid_new_current(struct drbd_conf *mdev) __must_hold(local)
 
 	get_random_bytes(&val, sizeof(u64));
 	_drbd_uuid_set(mdev, UI_CURRENT, val);
+	/* get it to stable storage _now_ */
+	drbd_md_sync(mdev);
 }
 
 void drbd_uuid_set_bm(struct drbd_conf *mdev, u64 val) __must_hold(local)
@@ -3756,19 +3769,31 @@ static int w_bitmap_io(struct drbd_conf *mdev, struct drbd_work *w, int unused)
 	return 1;
 }
 
+void drbd_ldev_destroy(struct drbd_conf *mdev)
+{
+	lc_destroy(mdev->resync);
+	mdev->resync = NULL;
+	lc_destroy(mdev->act_log);
+	mdev->act_log = NULL;
+	__no_warn(local,
+		drbd_free_bc(mdev->ldev);
+		mdev->ldev = NULL;);
+
+	if (mdev->md_io_tmpp) {
+		__free_page(mdev->md_io_tmpp);
+		mdev->md_io_tmpp = NULL;
+	}
+	clear_bit(GO_DISKLESS, &mdev->flags);
+}
+
 static int w_go_diskless(struct drbd_conf *mdev, struct drbd_work *w, int unused)
 {
 	D_ASSERT(mdev->state.disk == D_FAILED);
 	/* we cannot assert local_cnt == 0 here, as get_ldev_if_state will
 	 * inc/dec it frequently. Once we are D_DISKLESS, no one will touch
-	 * the protected members anymore, though, so in the after_state_ch work
-	 * it will be safe to free them. */
+	 * the protected members anymore, though, so once put_ldev reaches zero
+	 * again, it will be safe to free them. */
 	drbd_force_state(mdev, NS(disk, D_DISKLESS));
-	/* We need to wait for return of references checked out while we still
-	 * have been D_FAILED, though (drbd_md_sync, bitmap io). */
-	wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
-
-	clear_bit(GO_DISKLESS, &mdev->flags);
 	return 1;
 }
 
@@ -3777,9 +3802,6 @@ void drbd_go_diskless(struct drbd_conf *mdev)
 	D_ASSERT(mdev->state.disk == D_FAILED);
 	if (!test_and_set_bit(GO_DISKLESS, &mdev->flags))
 		drbd_queue_work(&mdev->data.work, &mdev->go_diskless);
-		/* don't drbd_queue_work_front,
-		 * we need to serialize with the after_state_ch work
-		 * of the -> D_FAILED transition. */
 }
 
 /**

drivers/block/drbd/drbd_nl.c

@@ -870,6 +870,11 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 		retcode = ERR_DISK_CONFIGURED;
 		goto fail;
 	}
+	/* It may just now have detached because of IO error.  Make sure
+	 * drbd_ldev_destroy is done already, we may end up here very fast,
+	 * e.g. if someone calls attach from the on-io-error handler,
+	 * to realize a "hot spare" feature (not that I'd recommend that) */
+	wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
 
 	/* allocation not in the IO path, cqueue thread context */
 	nbc = kzalloc(sizeof(struct drbd_backing_dev), GFP_KERNEL);
@@ -1098,9 +1103,9 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	/* Reset the "barriers don't work" bits here, then force meta data to
 	 * be written, to ensure we determine if barriers are supported. */
 	if (nbc->dc.no_md_flush)
-		set_bit(MD_NO_BARRIER, &mdev->flags);
+		set_bit(MD_NO_FUA, &mdev->flags);
 	else
-		clear_bit(MD_NO_BARRIER, &mdev->flags);
+		clear_bit(MD_NO_FUA, &mdev->flags);
 
 	/* Point of no return reached.
 	 * Devices and memory are no longer released by error cleanup below.
@@ -1112,8 +1117,8 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	nbc = NULL;
 	resync_lru = NULL;
 
-	mdev->write_ordering = WO_bio_barrier;
-	drbd_bump_write_ordering(mdev, WO_bio_barrier);
+	mdev->write_ordering = WO_bdev_flush;
+	drbd_bump_write_ordering(mdev, WO_bdev_flush);
 
 	if (drbd_md_test_flag(mdev->ldev, MDF_CRASHED_PRIMARY))
 		set_bit(CRASHED_PRIMARY, &mdev->flags);
@@ -1262,7 +1267,7 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
  force_diskless_dec:
 	put_ldev(mdev);
  force_diskless:
-	drbd_force_state(mdev, NS(disk, D_DISKLESS));
+	drbd_force_state(mdev, NS(disk, D_FAILED));
 	drbd_md_sync(mdev);
  release_bdev2_fail:
 	if (nbc)
@@ -1285,10 +1290,19 @@ static int drbd_nl_disk_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	return 0;
 }
 
+/* Detaching the disk is a process in multiple stages.  First we need to lock
+ * out application IO, in-flight IO, IO stuck in drbd_al_begin_io.
+ * Then we transition to D_DISKLESS, and wait for put_ldev() to return all
+ * internal references as well.
+ * Only then we have finally detached. */
 static int drbd_nl_detach(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp,
 			  struct drbd_nl_cfg_reply *reply)
 {
+	drbd_suspend_io(mdev); /* so no-one is stuck in drbd_al_begin_io */
 	reply->ret_code = drbd_request_state(mdev, NS(disk, D_DISKLESS));
+	if (mdev->state.disk == D_DISKLESS)
+		wait_event(mdev->misc_wait, !atomic_read(&mdev->local_cnt));
+	drbd_resume_io(mdev);
 	return 0;
 }
 
@@ -1953,7 +1967,6 @@ static int drbd_nl_resume_io(struct drbd_conf *mdev, struct drbd_nl_cfg_req *nlp
 	if (test_bit(NEW_CUR_UUID, &mdev->flags)) {
 		drbd_uuid_new_current(mdev);
 		clear_bit(NEW_CUR_UUID, &mdev->flags);
-		drbd_md_sync(mdev);
 	}
 	drbd_suspend_io(mdev);
 	reply->ret_code = drbd_request_state(mdev, NS3(susp, 0, susp_nod, 0, susp_fen, 0));

drivers/block/drbd/drbd_proc.c

@@ -158,7 +158,6 @@ static int drbd_seq_show(struct seq_file *seq, void *v)
 		[WO_none] = 'n',
 		[WO_drain_io] = 'd',
 		[WO_bdev_flush] = 'f',
-		[WO_bio_barrier] = 'b',
 	};
 
 	seq_printf(seq, "version: " REL_VERSION " (api:%d/proto:%d-%d)\n%s\n",

drivers/block/drbd/drbd_receiver.c

@@ -49,11 +49,6 @@
 
 #include "drbd_vli.h"
 
-struct flush_work {
-	struct drbd_work w;
-	struct drbd_epoch *epoch;
-};
-
 enum finish_epoch {
 	FE_STILL_LIVE,
 	FE_DESTROYED,
@@ -66,16 +61,6 @@ static int drbd_do_auth(struct drbd_conf *mdev);
 static enum finish_epoch drbd_may_finish_epoch(struct drbd_conf *, struct drbd_epoch *, enum epoch_event);
 static int e_end_block(struct drbd_conf *, struct drbd_work *, int);
 
-static struct drbd_epoch *previous_epoch(struct drbd_conf *mdev, struct drbd_epoch *epoch)
-{
-	struct drbd_epoch *prev;
-	spin_lock(&mdev->epoch_lock);
-	prev = list_entry(epoch->list.prev, struct drbd_epoch, list);
-	if (prev == epoch || prev == mdev->current_epoch)
-		prev = NULL;
-	spin_unlock(&mdev->epoch_lock);
-	return prev;
-}
 
 #define GFP_TRY	(__GFP_HIGHMEM | __GFP_NOWARN)
 
@@ -981,7 +966,7 @@ static int drbd_recv_header(struct drbd_conf *mdev, enum drbd_packets *cmd, unsi
 	return TRUE;
 }
 
-static enum finish_epoch drbd_flush_after_epoch(struct drbd_conf *mdev, struct drbd_epoch *epoch)
+static void drbd_flush(struct drbd_conf *mdev)
 {
 	int rv;
 
@@ -997,24 +982,6 @@ static enum finish_epoch drbd_flush_after_epoch(struct drbd_conf *mdev, struct d
 		}
 		put_ldev(mdev);
 	}
-
-	return drbd_may_finish_epoch(mdev, epoch, EV_BARRIER_DONE);
-}
-
-static int w_flush(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
-{
-	struct flush_work *fw = (struct flush_work *)w;
-	struct drbd_epoch *epoch = fw->epoch;
-
-	kfree(w);
-
-	if (!test_and_set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags))
-		drbd_flush_after_epoch(mdev, epoch);
-
-	drbd_may_finish_epoch(mdev, epoch, EV_PUT |
-			      (mdev->state.conn < C_CONNECTED ? EV_CLEANUP : 0));
-
-	return 1;
 }
 
 /**
@@ -1027,15 +994,13 @@ static enum finish_epoch drbd_may_finish_epoch(struct drbd_conf *mdev,
 					       struct drbd_epoch *epoch,
 					       enum epoch_event ev)
 {
-	int finish, epoch_size;
+	int epoch_size;
 	struct drbd_epoch *next_epoch;
-	int schedule_flush = 0;
 	enum finish_epoch rv = FE_STILL_LIVE;
 
 	spin_lock(&mdev->epoch_lock);
 	do {
 		next_epoch = NULL;
-		finish = 0;
 
 		epoch_size = atomic_read(&epoch->epoch_size);
 
@@ -1045,16 +1010,6 @@ static enum finish_epoch drbd_may_finish_epoch(struct drbd_conf *mdev,
 			break;
 		case EV_GOT_BARRIER_NR:
 			set_bit(DE_HAVE_BARRIER_NUMBER, &epoch->flags);
-
-			/* Special case: If we just switched from WO_bio_barrier to
-			   WO_bdev_flush we should not finish the current epoch */
-			if (test_bit(DE_CONTAINS_A_BARRIER, &epoch->flags) && epoch_size == 1 &&
-			    mdev->write_ordering != WO_bio_barrier &&
-			    epoch == mdev->current_epoch)
-				clear_bit(DE_CONTAINS_A_BARRIER, &epoch->flags);
-			break;
-		case EV_BARRIER_DONE:
-			set_bit(DE_BARRIER_IN_NEXT_EPOCH_DONE, &epoch->flags);
 			break;
 		case EV_BECAME_LAST:
 			/* nothing to do*/
@@ -1063,23 +1018,7 @@ static enum finish_epoch drbd_may_finish_epoch(struct drbd_conf *mdev,
 
 		if (epoch_size != 0 &&
 		    atomic_read(&epoch->active) == 0 &&
-		    test_bit(DE_HAVE_BARRIER_NUMBER, &epoch->flags) &&
-		    epoch->list.prev == &mdev->current_epoch->list &&
-		    !test_bit(DE_IS_FINISHING, &epoch->flags)) {
-			/* Nearly all conditions are met to finish that epoch... */
-			if (test_bit(DE_BARRIER_IN_NEXT_EPOCH_DONE, &epoch->flags) ||
-			    mdev->write_ordering == WO_none ||
-			    (epoch_size == 1 && test_bit(DE_CONTAINS_A_BARRIER, &epoch->flags)) ||
-			    ev & EV_CLEANUP) {
-				finish = 1;
-				set_bit(DE_IS_FINISHING, &epoch->flags);
-			} else if (!test_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags) &&
-				 mdev->write_ordering == WO_bio_barrier) {
-				atomic_inc(&epoch->active);
-				schedule_flush = 1;
-			}
-		}
-		if (finish) {
+		    test_bit(DE_HAVE_BARRIER_NUMBER, &epoch->flags)) {
 			if (!(ev & EV_CLEANUP)) {
 				spin_unlock(&mdev->epoch_lock);
 				drbd_send_b_ack(mdev, epoch->barrier_nr, epoch_size);
@@ -1102,6 +1041,7 @@ static enum finish_epoch drbd_may_finish_epoch(struct drbd_conf *mdev,
 				/* atomic_set(&epoch->active, 0); is already zero */
 				if (rv == FE_STILL_LIVE)
 					rv = FE_RECYCLED;
+				wake_up(&mdev->ee_wait);
 			}
 		}
 
@@ -1113,22 +1053,6 @@ static enum finish_epoch drbd_may_finish_epoch(struct drbd_conf *mdev,
 
 	spin_unlock(&mdev->epoch_lock);
 
-	if (schedule_flush) {
-		struct flush_work *fw;
-		fw = kmalloc(sizeof(*fw), GFP_ATOMIC);
-		if (fw) {
-			fw->w.cb = w_flush;
-			fw->epoch = epoch;
-			drbd_queue_work(&mdev->data.work, &fw->w);
-		} else {
-			dev_warn(DEV, "Could not kmalloc a flush_work obj\n");
-			set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags);
-			/* That is not a recursion, only one level */
-			drbd_may_finish_epoch(mdev, epoch, EV_BARRIER_DONE);
-			drbd_may_finish_epoch(mdev, epoch, EV_PUT);
-		}
-	}
-
 	return rv;
 }
 
@@ -1144,19 +1068,16 @@ void drbd_bump_write_ordering(struct drbd_conf *mdev, enum write_ordering_e wo)
 		[WO_none] = "none",
 		[WO_drain_io] = "drain",
 		[WO_bdev_flush] = "flush",
-		[WO_bio_barrier] = "barrier",
 	};
 
 	pwo = mdev->write_ordering;
 	wo = min(pwo, wo);
-	if (wo == WO_bio_barrier && mdev->ldev->dc.no_disk_barrier)
-		wo = WO_bdev_flush;
 	if (wo == WO_bdev_flush && mdev->ldev->dc.no_disk_flush)
 		wo = WO_drain_io;
 	if (wo == WO_drain_io && mdev->ldev->dc.no_disk_drain)
 		wo = WO_none;
 	mdev->write_ordering = wo;
-	if (pwo != mdev->write_ordering || wo == WO_bio_barrier)
+	if (pwo != mdev->write_ordering || wo == WO_bdev_flush)
 		dev_info(DEV, "Method to ensure write ordering: %s\n", write_ordering_str[mdev->write_ordering]);
 }
 
@@ -1192,7 +1113,7 @@ next_bio:
 	bio->bi_sector = sector;
 	bio->bi_bdev = mdev->ldev->backing_bdev;
 	/* we special case some flags in the multi-bio case, see below
-	 * (REQ_UNPLUG, REQ_HARDBARRIER) */
+	 * (REQ_UNPLUG) */
 	bio->bi_rw = rw;
 	bio->bi_private = e;
 	bio->bi_end_io = drbd_endio_sec;
@@ -1226,11 +1147,6 @@ next_bio:
 			bio->bi_rw &= ~REQ_UNPLUG;
 
 		drbd_generic_make_request(mdev, fault_type, bio);
-
-		/* strip off REQ_HARDBARRIER,
-		 * unless it is the first or last bio */
-		if (bios && bios->bi_next)
-			bios->bi_rw &= ~REQ_HARDBARRIER;
 	} while (bios);
 	maybe_kick_lo(mdev);
 	return 0;
@@ -1244,45 +1160,9 @@ fail:
 	return -ENOMEM;
 }
 
-/**
- * w_e_reissue() - Worker callback; Resubmit a bio, without REQ_HARDBARRIER set
- * @mdev:	DRBD device.
- * @w:		work object.
- * @cancel:	The connection will be closed anyways (unused in this callback)
- */
-int w_e_reissue(struct drbd_conf *mdev, struct drbd_work *w, int cancel) __releases(local)
-{
-	struct drbd_epoch_entry *e = (struct drbd_epoch_entry *)w;
-	/* We leave DE_CONTAINS_A_BARRIER and EE_IS_BARRIER in place,
-	   (and DE_BARRIER_IN_NEXT_EPOCH_ISSUED in the previous Epoch)
-	   so that we can finish that epoch in drbd_may_finish_epoch().
-	   That is necessary if we already have a long chain of Epochs, before
-	   we realize that REQ_HARDBARRIER is actually not supported */
-
-	/* As long as the -ENOTSUPP on the barrier is reported immediately
-	   that will never trigger. If it is reported late, we will just
-	   print that warning and continue correctly for all future requests
-	   with WO_bdev_flush */
-	if (previous_epoch(mdev, e->epoch))
-		dev_warn(DEV, "Write ordering was not enforced (one time event)\n");
-
-	/* we still have a local reference,
-	 * get_ldev was done in receive_Data. */
-
-	e->w.cb = e_end_block;
-	if (drbd_submit_ee(mdev, e, WRITE, DRBD_FAULT_DT_WR) != 0) {
-		/* drbd_submit_ee fails for one reason only:
-		 * if was not able to allocate sufficient bios.
-		 * requeue, try again later. */
-		e->w.cb = w_e_reissue;
-		drbd_queue_work(&mdev->data.work, &e->w);
-	}
-	return 1;
-}
-
 static int receive_Barrier(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned int data_size)
 {
-	int rv, issue_flush;
+	int rv;
 	struct p_barrier *p = &mdev->data.rbuf.barrier;
 	struct drbd_epoch *epoch;
 
@@ -1300,44 +1180,40 @@ static int receive_Barrier(struct drbd_conf *mdev, enum drbd_packets cmd, unsign
 	 * Therefore we must send the barrier_ack after the barrier request was
 	 * completed. */
 	switch (mdev->write_ordering) {
-	case WO_bio_barrier:
 	case WO_none:
 		if (rv == FE_RECYCLED)
 			return TRUE;
-		break;
+
+		/* receiver context, in the writeout path of the other node.
+		 * avoid potential distributed deadlock */
+		epoch = kmalloc(sizeof(struct drbd_epoch), GFP_NOIO);
+		if (epoch)
+			break;
+		else
+			dev_warn(DEV, "Allocation of an epoch failed, slowing down\n");
+			/* Fall through */
 
 	case WO_bdev_flush:
 	case WO_drain_io:
-		if (rv == FE_STILL_LIVE) {
-			set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &mdev->current_epoch->flags);
-			drbd_wait_ee_list_empty(mdev, &mdev->active_ee);
-			rv = drbd_flush_after_epoch(mdev, mdev->current_epoch);
-		}
-		if (rv == FE_RECYCLED)
-			return TRUE;
-
-		/* The asender will send all the ACKs and barrier ACKs out, since
-		   all EEs moved from the active_ee to the done_ee. We need to
-		   provide a new epoch object for the EEs that come in soon */
-		break;
-	}
-
-	/* receiver context, in the writeout path of the other node.
-	 * avoid potential distributed deadlock */
-	epoch = kmalloc(sizeof(struct drbd_epoch), GFP_NOIO);
-	if (!epoch) {
-		dev_warn(DEV, "Allocation of an epoch failed, slowing down\n");
-		issue_flush = !test_and_set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &mdev->current_epoch->flags);
 		drbd_wait_ee_list_empty(mdev, &mdev->active_ee);
-		if (issue_flush) {
-			rv = drbd_flush_after_epoch(mdev, mdev->current_epoch);
-			if (rv == FE_RECYCLED)
-				return TRUE;
+		drbd_flush(mdev);
+
+		if (atomic_read(&mdev->current_epoch->epoch_size)) {
+			epoch = kmalloc(sizeof(struct drbd_epoch), GFP_NOIO);
+			if (epoch)
+				break;
 		}
 
-		drbd_wait_ee_list_empty(mdev, &mdev->done_ee);
+		epoch = mdev->current_epoch;
+		wait_event(mdev->ee_wait, atomic_read(&epoch->epoch_size) == 0);
+
+		D_ASSERT(atomic_read(&epoch->active) == 0);
+		D_ASSERT(epoch->flags == 0);
 
 		return TRUE;
+	default:
+		dev_err(DEV, "Strangeness in mdev->write_ordering %d\n", mdev->write_ordering);
+		return FALSE;
 	}
 
 	epoch->flags = 0;
@@ -1652,15 +1528,8 @@ static int e_end_block(struct drbd_conf *mdev, struct drbd_work *w, int cancel)
 {
 	struct drbd_epoch_entry *e = (struct drbd_epoch_entry *)w;
 	sector_t sector = e->sector;
-	struct drbd_epoch *epoch;
 	int ok = 1, pcmd;
 
-	if (e->flags & EE_IS_BARRIER) {
-		epoch = previous_epoch(mdev, e->epoch);
-		if (epoch)
-			drbd_may_finish_epoch(mdev, epoch, EV_BARRIER_DONE + (cancel ? EV_CLEANUP : 0));
-	}
-
 	if (mdev->net_conf->wire_protocol == DRBD_PROT_C) {
 		if (likely((e->flags & EE_WAS_ERROR) == 0)) {
 			pcmd = (mdev->state.conn >= C_SYNC_SOURCE &&
@@ -1817,27 +1686,6 @@ static int receive_Data(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
 	e->epoch = mdev->current_epoch;
 	atomic_inc(&e->epoch->epoch_size);
 	atomic_inc(&e->epoch->active);
-
-	if (mdev->write_ordering == WO_bio_barrier && atomic_read(&e->epoch->epoch_size) == 1) {
-		struct drbd_epoch *epoch;
-		/* Issue a barrier if we start a new epoch, and the previous epoch
-		   was not a epoch containing a single request which already was
-		   a Barrier. */
-		epoch = list_entry(e->epoch->list.prev, struct drbd_epoch, list);
-		if (epoch == e->epoch) {
-			set_bit(DE_CONTAINS_A_BARRIER, &e->epoch->flags);
-			rw |= REQ_HARDBARRIER;
-			e->flags |= EE_IS_BARRIER;
-		} else {
-			if (atomic_read(&epoch->epoch_size) > 1 ||
-			    !test_bit(DE_CONTAINS_A_BARRIER, &epoch->flags)) {
-				set_bit(DE_BARRIER_IN_NEXT_EPOCH_ISSUED, &epoch->flags);
-				set_bit(DE_CONTAINS_A_BARRIER, &e->epoch->flags);
-				rw |= REQ_HARDBARRIER;
-				e->flags |= EE_IS_BARRIER;
-			}
-		}
-	}
 	spin_unlock(&mdev->epoch_lock);
 
 	dp_flags = be32_to_cpu(p->dp_flags);
@@ -1995,10 +1843,11 @@ static int receive_Data(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
 		break;
 	}
 
-	if (mdev->state.pdsk == D_DISKLESS) {
+	if (mdev->state.pdsk < D_INCONSISTENT) {
 		/* In case we have the only disk of the cluster, */
 		drbd_set_out_of_sync(mdev, e->sector, e->size);
 		e->flags |= EE_CALL_AL_COMPLETE_IO;
+		e->flags &= ~EE_MAY_SET_IN_SYNC;
 		drbd_al_begin_io(mdev, e->sector);
 	}
 
@@ -3362,7 +3211,7 @@ static int receive_state(struct drbd_conf *mdev, enum drbd_packets cmd, unsigned
 		if (ns.conn == C_MASK) {
 			ns.conn = C_CONNECTED;
 			if (mdev->state.disk == D_NEGOTIATING) {
-				drbd_force_state(mdev, NS(disk, D_DISKLESS));
+				drbd_force_state(mdev, NS(disk, D_FAILED));
 			} else if (peer_state.disk == D_NEGOTIATING) {
 				dev_err(DEV, "Disk attach process on the peer node was aborted.\n");
 				peer_state.disk = D_DISKLESS;

drivers/block/drbd/drbd_req.c

@@ -258,7 +258,7 @@ void _req_may_be_done(struct drbd_request *req, struct bio_and_error *m)
 		if (!hlist_unhashed(&req->colision))
 			hlist_del(&req->colision);
 		else
-			D_ASSERT((s & RQ_NET_MASK) == 0);
+			D_ASSERT((s & (RQ_NET_MASK & ~RQ_NET_DONE)) == 0);
 
 		/* for writes we need to do some extra housekeeping */
 		if (rw == WRITE)
@@ -813,7 +813,8 @@ static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio)
 			     mdev->state.conn >= C_CONNECTED));
 
 	if (!(local || remote) && !is_susp(mdev->state)) {
-		dev_err(DEV, "IO ERROR: neither local nor remote disk\n");
+		if (__ratelimit(&drbd_ratelimit_state))
+			dev_err(DEV, "IO ERROR: neither local nor remote disk\n");
 		goto fail_free_complete;
 	}
 
@@ -942,12 +943,21 @@ allocate_barrier:
 	if (local) {
 		req->private_bio->bi_bdev = mdev->ldev->backing_bdev;
 
-		if (FAULT_ACTIVE(mdev, rw == WRITE ? DRBD_FAULT_DT_WR
-				     : rw == READ  ? DRBD_FAULT_DT_RD
-				     :               DRBD_FAULT_DT_RA))
+		/* State may have changed since we grabbed our reference on the
+		 * mdev->ldev member. Double check, and short-circuit to endio.
+		 * In case the last activity log transaction failed to get on
+		 * stable storage, and this is a WRITE, we may not even submit
+		 * this bio. */
+		if (get_ldev(mdev)) {
+			if (FAULT_ACTIVE(mdev, rw == WRITE ? DRBD_FAULT_DT_WR
+					     : rw == READ  ? DRBD_FAULT_DT_RD
+					     :               DRBD_FAULT_DT_RA))
+				bio_endio(req->private_bio, -EIO);
+			else
+				generic_make_request(req->private_bio);
+			put_ldev(mdev);
+		} else
 			bio_endio(req->private_bio, -EIO);
-		else
-			generic_make_request(req->private_bio);
 	}
 
 	/* we need to plug ALWAYS since we possibly need to kick lo_dev.
@@ -1022,20 +1032,6 @@ int drbd_make_request_26(struct request_queue *q, struct bio *bio)
 		return 0;
 	}
 
-	/* Reject barrier requests if we know the underlying device does
-	 * not support them.
-	 * XXX: Need to get this info from peer as well some how so we
-	 * XXX: reject if EITHER side/data/metadata area does not support them.
-	 *
-	 * because of those XXX, this is not yet enabled,
-	 * i.e. in drbd_init_set_defaults we set the NO_BARRIER_SUPP bit.
-	 */
-	if (unlikely(bio->bi_rw & REQ_HARDBARRIER) && test_bit(NO_BARRIER_SUPP, &mdev->flags)) {
-		/* dev_warn(DEV, "Rejecting barrier request as underlying device does not support\n"); */
-		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
-	}
-
 	/*
 	 * what we "blindly" assume:
 	 */

drivers/block/drbd/drbd_worker.c

@@ -102,12 +102,6 @@ void drbd_endio_read_sec_final(struct drbd_epoch_entry *e) __releases(local)
 	put_ldev(mdev);
 }
 
-static int is_failed_barrier(int ee_flags)
-{
-	return (ee_flags & (EE_IS_BARRIER|EE_WAS_ERROR|EE_RESUBMITTED))
-			== (EE_IS_BARRIER|EE_WAS_ERROR);
-}
-
 /* writes on behalf of the partner, or resync writes,
  * "submitted" by the receiver, final stage.  */
 static void drbd_endio_write_sec_final(struct drbd_epoch_entry *e) __releases(local)
@@ -119,21 +113,6 @@ static void drbd_endio_write_sec_final(struct drbd_epoch_entry *e) __releases(lo
 	int is_syncer_req;
 	int do_al_complete_io;
 
-	/* if this is a failed barrier request, disable use of barriers,
-	 * and schedule for resubmission */
-	if (is_failed_barrier(e->flags)) {
-		drbd_bump_write_ordering(mdev, WO_bdev_flush);
-		spin_lock_irqsave(&mdev->req_lock, flags);
-		list_del(&e->w.list);
-		e->flags = (e->flags & ~EE_WAS_ERROR) | EE_RESUBMITTED;
-		e->w.cb = w_e_reissue;
-		/* put_ldev actually happens below, once we come here again. */
-		__release(local);
-		spin_unlock_irqrestore(&mdev->req_lock, flags);
-		drbd_queue_work(&mdev->data.work, &e->w);
-		return;
-	}
-
 	D_ASSERT(e->block_id != ID_VACANT);
 
 	/* after we moved e to done_ee,
@@ -925,7 +904,7 @@ out:
 	drbd_md_sync(mdev);
 
 	if (test_and_clear_bit(WRITE_BM_AFTER_RESYNC, &mdev->flags)) {
-		dev_warn(DEV, "Writing the whole bitmap, due to failed kmalloc\n");
+		dev_info(DEV, "Writing the whole bitmap\n");
 		drbd_queue_bitmap_io(mdev, &drbd_bm_write, NULL, "write from resync_finished");
 	}
 

drivers/block/loop.c

@@ -481,12 +481,6 @@ static int do_bio_filebacked(struct loop_device *lo, struct bio *bio)
 	if (bio_rw(bio) == WRITE) {
 		struct file *file = lo->lo_backing_file;
 
-		/* REQ_HARDBARRIER is deprecated */
-		if (bio->bi_rw & REQ_HARDBARRIER) {
-			ret = -EOPNOTSUPP;
-			goto out;
-		}
-
 		if (bio->bi_rw & REQ_FLUSH) {
 			ret = vfs_fsync(file, 0);
 			if (unlikely(ret && ret != -EINVAL)) {

drivers/block/xen-blkfront.c

@@ -289,8 +289,6 @@ static int blkif_queue_request(struct request *req)
 
 	ring_req->operation = rq_data_dir(req) ?
 		BLKIF_OP_WRITE : BLKIF_OP_READ;
-	if (req->cmd_flags & REQ_HARDBARRIER)
-		ring_req->operation = BLKIF_OP_WRITE_BARRIER;
 
 	ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg);
 	BUG_ON(ring_req->nr_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);

drivers/bluetooth/btusb.c

@@ -68,6 +68,9 @@ static struct usb_device_id btusb_table[] = {
 	/* Apple MacBookPro6,2 */
 	{ USB_DEVICE(0x05ac, 0x8218) },
 
+	/* Apple MacBookAir3,1, MacBookAir3,2 */
+	{ USB_DEVICE(0x05ac, 0x821b) },
+
 	/* AVM BlueFRITZ! USB v2.0 */
 	{ USB_DEVICE(0x057c, 0x3800) },
 
@@ -1029,6 +1032,8 @@ static int btusb_probe(struct usb_interface *intf,
 
 	usb_set_intfdata(intf, data);
 
+	usb_enable_autosuspend(interface_to_usbdev(intf));
+
 	return 0;
 }
 

drivers/char/agp/intel-gtt.c

@@ -1210,14 +1210,14 @@ static void gen6_write_entry(dma_addr_t addr, unsigned int entry,
 	unsigned int gfdt = flags & AGP_USER_CACHED_MEMORY_GFDT;
 	u32 pte_flags;
 
-	if (type_mask == AGP_USER_UNCACHED_MEMORY)
+	if (type_mask == AGP_USER_MEMORY)
 		pte_flags = GEN6_PTE_UNCACHED | I810_PTE_VALID;
 	else if (type_mask == AGP_USER_CACHED_MEMORY_LLC_MLC) {
-		pte_flags = GEN6_PTE_LLC | I810_PTE_VALID;
+		pte_flags = GEN6_PTE_LLC_MLC | I810_PTE_VALID;
 		if (gfdt)
 			pte_flags |= GEN6_PTE_GFDT;
 	} else { /* set 'normal'/'cached' to LLC by default */
-		pte_flags = GEN6_PTE_LLC_MLC | I810_PTE_VALID;
+		pte_flags = GEN6_PTE_LLC | I810_PTE_VALID;
 		if (gfdt)
 			pte_flags |= GEN6_PTE_GFDT;
 	}

drivers/char/amiserial.c

@@ -1299,7 +1299,6 @@ static int rs_ioctl(struct tty_struct *tty, struct file * file,
 {
 	struct async_struct * info = tty->driver_data;
 	struct async_icount cprev, cnow;	/* kernel counter temps */
-	struct serial_icounter_struct icount;
 	void __user *argp = (void __user *)arg;
 	unsigned long flags;
 

drivers/char/i8k.c

@@ -120,7 +120,7 @@ static int i8k_smm(struct smm_regs *regs)
 	int eax = regs->eax;
 
 #if defined(CONFIG_X86_64)
-	asm("pushq %%rax\n\t"
+	asm volatile("pushq %%rax\n\t"
 		"movl 0(%%rax),%%edx\n\t"
 		"pushq %%rdx\n\t"
 		"movl 4(%%rax),%%ebx\n\t"
@@ -146,7 +146,7 @@ static int i8k_smm(struct smm_regs *regs)
 		:    "a"(regs)
 		:    "%ebx", "%ecx", "%edx", "%esi", "%edi", "memory");
 #else
-	asm("pushl %%eax\n\t"
+	asm volatile("pushl %%eax\n\t"
 	    "movl 0(%%eax),%%edx\n\t"
 	    "push %%edx\n\t"
 	    "movl 4(%%eax),%%ebx\n\t"
@@ -167,7 +167,8 @@ static int i8k_smm(struct smm_regs *regs)
 	    "movl %%edx,0(%%eax)\n\t"
 	    "lahf\n\t"
 	    "shrl $8,%%eax\n\t"
-	    "andl $1,%%eax\n":"=a"(rc)
+	    "andl $1,%%eax\n"
+	    :"=a"(rc)
 	    :    "a"(regs)
 	    :    "%ebx", "%ecx", "%edx", "%esi", "%edi", "memory");
 #endif

drivers/char/nozomi.c

@@ -1828,7 +1828,6 @@ static int ntty_ioctl(struct tty_struct *tty, struct file *file,
 		      unsigned int cmd, unsigned long arg)
 {
 	struct port *port = tty->driver_data;
-	void __user *argp = (void __user *)arg;
 	int rval = -ENOIOCTLCMD;
 
 	DBG1("******** IOCTL, cmd: %d", cmd);

drivers/char/pcmcia/cm4000_cs.c

@@ -979,8 +979,9 @@ static ssize_t cmm_read(struct file *filp, __user char *buf, size_t count,
 		if (dev->flags0 & 1) {
 			set_bit(IS_CMM_ABSENT, &dev->flags);
 			rc = -ENODEV;
+		} else {
+			rc = -EIO;
 		}
-		rc = -EIO;
 		goto release_io;
 	}
 

drivers/char/pcmcia/synclink_cs.c

@@ -2796,6 +2796,7 @@ static const struct tty_operations mgslpc_ops = {
 	.hangup = mgslpc_hangup,
 	.tiocmget = tiocmget,
 	.tiocmset = tiocmset,
+	.get_icount = mgslpc_get_icount,
 	.proc_fops = &mgslpc_proc_fops,
 };
 

drivers/crypto/n2_core.c

@@ -1832,7 +1832,7 @@ static int __devinit get_irq_props(struct mdesc_handle *mdesc, u64 node,
 		return -ENODEV;
 
 	ino = mdesc_get_property(mdesc, node, "ino", &ino_len);
-	if (!intr)
+	if (!ino)
 		return -ENODEV;
 
 	if (intr_len != ino_len)