Merge remote branch 'trond/bugfixes' into for-2.6.37

Without some client-side fixes, server testing is currently difficult.
2010-09-19 23:48:00 -04:00 · 2010-09-19 23:48:00 -04:00 · c88739b373
commit c88739b373
parent 3211af1119 827e345702
443 changed files with 5153 additions and 2559 deletions
--- a/Documentation/DocBook/device-drivers.tmpl
+++ b/Documentation/DocBook/device-drivers.tmpl
@ -46,7 +46,6 @@

     <sect1><title>Atomic and pointer manipulation</title>
 !Iarch/x86/include/asm/atomic.h
-!Iarch/x86/include/asm/unaligned.h
     </sect1>

     <sect1><title>Delaying, scheduling, and timer routines</title>
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@ -57,7 +57,6 @@
     </para>

     <sect1><title>String Conversions</title>
-!Ilib/vsprintf.c
 !Elib/vsprintf.c
     </sect1>
     <sect1><title>String Manipulation</title>
--- a/Documentation/DocBook/kernel-locking.tmpl
+++ b/Documentation/DocBook/kernel-locking.tmpl
@ -1961,6 +1961,12 @@ machines due to caching.
   </sect1>
  </chapter>

+  <chapter id="apiref">
+   <title>Mutex API reference</title>
+!Iinclude/linux/mutex.h
+!Ekernel/mutex.c
+  </chapter>
+
  <chapter id="references">
   <title>Further reading</title>

--- a/Documentation/DocBook/tracepoint.tmpl
+++ b/Documentation/DocBook/tracepoint.tmpl
@ -104,4 +104,9 @@
   <title>Block IO</title>
 !Iinclude/trace/events/block.h
  </chapter>
+
+  <chapter id="workqueue">
+   <title>Workqueue</title>
+!Iinclude/trace/events/workqueue.h
+  </chapter>
 </book>
--- a/Documentation/block/cfq-iosched.txt
+++ b/Documentation/block/cfq-iosched.txt
@ -0,0 +1,45 @@
+CFQ ioscheduler tunables
+========================
+
+slice_idle
+----------
+This specifies how long CFQ should idle for next request on certain cfq queues
+(for sequential workloads) and service trees (for random workloads) before
+queue is expired and CFQ selects next queue to dispatch from.
+
+By default slice_idle is a non-zero value. That means by default we idle on
+queues/service trees. This can be very helpful on highly seeky media like
+single spindle SATA/SAS disks where we can cut down on overall number of
+seeks and see improved throughput.
+
+Setting slice_idle to 0 will remove all the idling on queues/service tree
+level and one should see an overall improved throughput on faster storage
+devices like multiple SATA/SAS disks in hardware RAID configuration. The down
+side is that isolation provided from WRITES also goes down and notion of
+IO priority becomes weaker.
+
+So depending on storage and workload, it might be useful to set slice_idle=0.
+In general I think for SATA/SAS disks and software RAID of SATA/SAS disks
+keeping slice_idle enabled should be useful. For any configurations where
+there are multiple spindles behind single LUN (Host based hardware RAID
+controller or for storage arrays), setting slice_idle=0 might end up in better
+throughput and acceptable latencies.
+
+CFQ IOPS Mode for group scheduling
+===================================
+Basic CFQ design is to provide priority based time slices. Higher priority
+process gets bigger time slice and lower priority process gets smaller time
+slice. Measuring time becomes harder if storage is fast and supports NCQ and
+it would be better to dispatch multiple requests from multiple cfq queues in
+request queue at a time. In such scenario, it is not possible to measure time
+consumed by single queue accurately.
+
+What is possible though is to measure number of requests dispatched from a
+single queue and also allow dispatch from multiple cfq queue at the same time.
+This effectively becomes the fairness in terms of IOPS (IO operations per
+second).
+
+If one sets slice_idle=0 and if storage supports NCQ, CFQ internally switches
+to IOPS mode and starts providing fairness in terms of number of requests
+dispatched. Note that this mode switching takes effect only for group
+scheduling. For non-cgroup users nothing should change.
--- a/Documentation/cgroups/blkio-controller.txt
+++ b/Documentation/cgroups/blkio-controller.txt
@ -217,6 +217,7 @@ Details of cgroup files
 CFQ sysfs tunable
 =================
 /sys/block/<disk>/queue/iosched/group_isolation
+-----------------------------------------------

 If group_isolation=1, it provides stronger isolation between groups at the
 expense of throughput. By default group_isolation is 0. In general that
@ -243,6 +244,33 @@ By default one should run with group_isolation=0. If that is not sufficient
 and one wants stronger isolation between groups, then set group_isolation=1
 but this will come at cost of reduced throughput.

+/sys/block/<disk>/queue/iosched/slice_idle
+------------------------------------------
+On a faster hardware CFQ can be slow, especially with sequential workload.
+This happens because CFQ idles on a single queue and single queue might not
+drive deeper request queue depths to keep the storage busy. In such scenarios
+one can try setting slice_idle=0 and that would switch CFQ to IOPS
+(IO operations per second) mode on NCQ supporting hardware.
+
+That means CFQ will not idle between cfq queues of a cfq group and hence be
+able to driver higher queue depth and achieve better throughput. That also
+means that cfq provides fairness among groups in terms of IOPS and not in
+terms of disk time.
+
+/sys/block/<disk>/queue/iosched/group_idle
+------------------------------------------
+If one disables idling on individual cfq queues and cfq service trees by
+setting slice_idle=0, group_idle kicks in. That means CFQ will still idle
+on the group in an attempt to provide fairness among groups.
+
+By default group_idle is same as slice_idle and does not do anything if
+slice_idle is enabled.
+
+One can experience an overall throughput drop if you have created multiple
+groups and put applications in that group which are not driving enough
+IO to keep disk busy. In that case set group_idle=0, and CFQ will not idle
+on individual groups and throughput should improve.
+
 What works
 ==========
 - Currently only sync IO queues are support. All the buffered writes are
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@ -109,17 +109,19 @@ use numbers 2000-2063 to identify GPIOs in a bank of I2C GPIO expanders.

 If you want to initialize a structure with an invalid GPIO number, use
 some negative number (perhaps "-EINVAL"); that will never be valid.  To
-test if a number could reference a GPIO, you may use this predicate:
+test if such number from such a structure could reference a GPIO, you
+may use this predicate:

 	int gpio_is_valid(int number);

 A number that's not valid will be rejected by calls which may request
 or free GPIOs (see below).  Other numbers may also be rejected; for
-example, a number might be valid but unused on a given board.
-
-Whether a platform supports multiple GPIO controllers is currently a
-platform-specific implementation issue.
+example, a number might be valid but temporarily unused on a given board.

+Whether a platform supports multiple GPIO controllers is a platform-specific
+implementation issue, as are whether that support can leave "holes" in the space
+of GPIO numbers, and whether new controllers can be added at runtime.  Such issues
+can affect things including whether adjacent GPIO numbers are both valid.

 Using GPIOs
 -----------
@ -480,12 +482,16 @@ To support this framework, a platform's Kconfig will "select" either
 ARCH_REQUIRE_GPIOLIB or ARCH_WANT_OPTIONAL_GPIOLIB
 and arrange that its <asm/gpio.h> includes <asm-generic/gpio.h> and defines
 three functions: gpio_get_value(), gpio_set_value(), and gpio_cansleep().
-They may also want to provide a custom value for ARCH_NR_GPIOS.

-ARCH_REQUIRE_GPIOLIB means that the gpio-lib code will always get compiled
+It may also provide a custom value for ARCH_NR_GPIOS, so that it better
+reflects the number of GPIOs in actual use on that platform, without
+wasting static table space.  (It should count both built-in/SoC GPIOs and
+also ones on GPIO expanders.
+
+ARCH_REQUIRE_GPIOLIB means that the gpiolib code will always get compiled
 into the kernel on that architecture.

-ARCH_WANT_OPTIONAL_GPIOLIB means the gpio-lib code defaults to off and the user
+ARCH_WANT_OPTIONAL_GPIOLIB means the gpiolib code defaults to off and the user
 can enable it and build it into the kernel optionally.

 If neither of these options are selected, the platform does not support
--- a/Documentation/kernel-doc-nano-HOWTO.txt
+++ b/Documentation/kernel-doc-nano-HOWTO.txt
@ -345,5 +345,10 @@ documentation, in <filename>, for the functions listed.
 section titled <section title> from <filename>.
 Spaces are allowed in <section title>; do not quote the <section title>.

+!C<filename> is replaced by nothing, but makes the tools check that
+all DOC: sections and documented functions, symbols, etc. are used.
+This makes sense to use when you use !F/!P only and want to verify
+that all documentation is included.
+
 Tim.
 */ <twaugh@redhat.com>
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@ -1974,15 +1974,18 @@ and is between 256 and 4096 characters. It is defined in the file
 		force	Enable ASPM even on devices that claim not to support it.
 			WARNING: Forcing ASPM on may cause system lockups.

+	pcie_ports=	[PCIE] PCIe ports handling:
+		auto	Ask the BIOS whether or not to use native PCIe services
+			associated with PCIe ports (PME, hot-plug, AER).  Use
+			them only if that is allowed by the BIOS.
+		native	Use native PCIe services associated with PCIe ports
+			unconditionally.
+		compat	Treat PCIe ports as PCI-to-PCI bridges, disable the PCIe
+			ports driver.
+
 	pcie_pme=	[PCIE,PM] Native PCIe PME signaling options:
-			Format: {auto|force}[,nomsi]
-		auto	Use native PCIe PME signaling if the BIOS allows the
-			kernel to control PCIe config registers of root ports.
-		force	Use native PCIe PME signaling even if the BIOS refuses
-			to allow the kernel to control the relevant PCIe config
-			registers.
 		nomsi	Do not use MSI for native PCIe PME signaling (this makes
-			all PCIe root ports use INTx for everything).
+			all PCIe root ports use INTx for all services).

 	pcmv=		[HW,PCMCIA] BadgePAD 4

--- a/Documentation/mutex-design.txt
+++ b/Documentation/mutex-design.txt
@ -9,7 +9,7 @@ firstly, there's nothing wrong with semaphores. But if the simpler
 mutex semantics are sufficient for your code, then there are a couple
 of advantages of mutexes:

- - 'struct mutex' is smaller on most architectures: .e.g on x86,
+ - 'struct mutex' is smaller on most architectures: E.g. on x86,
   'struct semaphore' is 20 bytes, 'struct mutex' is 16 bytes.
   A smaller structure size means less RAM footprint, and better
   CPU-cache utilization.
@ -136,3 +136,4 @@ the APIs of 'struct mutex' have been streamlined:
 void mutex_lock_nested(struct mutex *lock, unsigned int subclass);
 int  mutex_lock_interruptible_nested(struct mutex *lock,
                                      unsigned int subclass);
+ int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
--- a/Documentation/sound/alsa/HD-Audio-Models.txt
+++ b/Documentation/sound/alsa/HD-Audio-Models.txt
@ -296,6 +296,7 @@ Conexant 5051
 Conexant 5066
 =============
  laptop	Basic Laptop config (default)
+  hp-laptop	HP laptops, e g G60
  dell-laptop	Dell laptops
  dell-vostro	Dell Vostro
  olpc-xo-1_5	OLPC XO 1.5
--- a/36
+++ b/36
@ -1445,6 +1445,16 @@ S:	Maintained
 F:	Documentation/video4linux/cafe_ccic
 F:	drivers/media/video/cafe_ccic*

+CAIF NETWORK LAYER
+M:	Sjur Braendeland <sjur.brandeland@stericsson.com>
+L:	netdev@vger.kernel.org
+S:	Supported
+F:	Documentation/networking/caif/
+F:	drivers/net/caif/
+F:	include/linux/caif/
+F:	include/net/caif/
+F:	net/caif/
+
 CALGARY x86-64 IOMMU
 M:	Muli Ben-Yehuda <muli@il.ibm.com>
 M:	"Jon D. Mason" <jdmason@kudzu.us>
@ -2201,6 +2211,12 @@ L:	linux-rdma@vger.kernel.org
 S:	Supported
 F:	drivers/infiniband/hw/ehca/

+EHEA (IBM pSeries eHEA 10Gb ethernet adapter) DRIVER
+M:	Breno Leitao <leitao@linux.vnet.ibm.com>
+L:	netdev@vger.kernel.org
+S:	Maintained
+F:	drivers/net/ehea/
+
 EMBEDDED LINUX
 M:	Paul Gortmaker <paul.gortmaker@windriver.com>
 M:	Matt Mackall <mpm@selenic.com>
@ -2781,11 +2797,6 @@ S:	Maintained
 F:	arch/x86/kernel/hpet.c
 F:	arch/x86/include/asm/hpet.h

-HPET:	ACPI
-M:	Bob Picco <bob.picco@hp.com>
-S:	Maintained
-F:	drivers/char/hpet.c
-
 HPFS FILESYSTEM
 M:	Mikulas Patocka <mikulas@artax.karlin.mff.cuni.cz>
 W:	http://artax.karlin.mff.cuni.cz/~mikulas/vyplody/hpfs/index-e.cgi
@ -3398,7 +3409,7 @@ F:	drivers/s390/kvm/

 KEXEC
 M:	Eric Biederman <ebiederm@xmission.com>
-W:	http://ftp.kernel.org/pub/linux/kernel/people/horms/kexec-tools/
+W:	http://kernel.org/pub/linux/utils/kernel/kexec/
 L:	kexec@lists.infradead.org
 S:	Maintained
 F:	include/linux/kexec.h
@ -3923,8 +3934,7 @@ F:	Documentation/sound/oss/MultiSound
 F:	sound/oss/msnd*

 MULTITECH MULTIPORT CARD (ISICOM)
-M:	Jiri Slaby <jirislaby@gmail.com>
-S:	Maintained
+S:	Orphan
 F:	drivers/char/isicom.c
 F:	include/linux/isicom.h

@ -4604,7 +4614,7 @@ F:	include/linux/preempt.h
 PRISM54 WIRELESS DRIVER
 M:	"Luis R. Rodriguez" <mcgrof@gmail.com>
 L:	linux-wireless@vger.kernel.org
-W:	http://prism54.org
+W:	http://wireless.kernel.org/en/users/Drivers/p54
 S:	Obsolete
 F:	drivers/net/wireless/prism54/

@ -4805,6 +4815,7 @@ RCUTORTURE MODULE
 M:	Josh Triplett <josh@freedesktop.org>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 S:	Supported
+T:	git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git
 F:	Documentation/RCU/torture.txt
 F:	kernel/rcutorture.c

@ -4829,6 +4840,7 @@ M:	Dipankar Sarma <dipankar@in.ibm.com>
 M:	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
 W:	http://www.rdrop.com/users/paulmck/rclock/
 S:	Supported
+T:	git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-2.6-rcu.git
 F:	Documentation/RCU/
 F:	include/linux/rcu*
 F:	include/linux/srcu*
@ -4836,12 +4848,10 @@ F:	kernel/rcu*
 F:	kernel/srcu*
 X:	kernel/rcutorture.c

-REAL TIME CLOCK DRIVER
+REAL TIME CLOCK DRIVER (LEGACY)
 M:	Paul Gortmaker <p_gortmaker@yahoo.com>
 S:	Maintained
-F:	Documentation/rtc.txt
-F:	drivers/rtc/
-F:	include/linux/rtc.h
+F:	drivers/char/rtc.c

 REAL TIME CLOCK (RTC) SUBSYSTEM
 M:	Alessandro Zummo <a.zummo@towertech.it>
--- a/2
+++ b/2
@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 36
-EXTRAVERSION = -rc3
+EXTRAVERSION = -rc4
 NAME = Sheep on Meth

 # *DOCUMENTATION*
--- a/arch/alpha/include/asm/cache.h
+++ b/arch/alpha/include/asm/cache.h
@ -17,7 +17,6 @@
 # define L1_CACHE_SHIFT     5
 #endif

-#define L1_CACHE_ALIGN(x)  (((x)+(L1_CACHE_BYTES-1))&~(L1_CACHE_BYTES-1))
 #define SMP_CACHE_BYTES    L1_CACHE_BYTES

 #endif
--- a/arch/alpha/kernel/err_marvel.c
+++ b/arch/alpha/kernel/err_marvel.c
@ -109,7 +109,7 @@ marvel_print_err_cyc(u64 err_cyc)
 #define IO7__ERR_CYC__CYCLE__M	(0x7)

 	printk("%s        Packet In Error: %s\n"
-	       "%s        Error in %s, cycle %ld%s%s\n",
+	       "%s        Error in %s, cycle %lld%s%s\n",
 	       err_print_prefix, 
 	       packet_desc[EXTRACT(err_cyc, IO7__ERR_CYC__PACKET)],
 	       err_print_prefix,
@ -313,7 +313,7 @@ marvel_print_po7_ugbge_sym(u64 ugbge_sym)
 	}

 	printk("%s      Up Hose Garbage Symptom:\n"
-	       "%s        Source Port: %ld - Dest PID: %ld - OpCode: %s\n", 
+	       "%s        Source Port: %lld - Dest PID: %lld - OpCode: %s\n",
 	       err_print_prefix,
 	       err_print_prefix, 
 	       EXTRACT(ugbge_sym, IO7__PO7_UGBGE_SYM__UPH_SRC_PORT),
@ -552,7 +552,7 @@ marvel_print_pox_spl_cmplt(u64 spl_cmplt)
 #define IO7__POX_SPLCMPLT__REM_BYTE_COUNT__M	(0xfff)

 	printk("%s      Split Completion Error:\n"	
-	       "%s         Source (Bus:Dev:Func): %ld:%ld:%ld\n",
+	       "%s         Source (Bus:Dev:Func): %lld:%lld:%lld\n",
 	       err_print_prefix,
 	       err_print_prefix,
 	       EXTRACT(spl_cmplt, IO7__POX_SPLCMPLT__SOURCE_BUS),
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@ -241,20 +241,20 @@ static inline unsigned long alpha_read_pmc(int idx)
 static int alpha_perf_event_set_period(struct perf_event *event,
 				struct hw_perf_event *hwc, int idx)
 {
-	long left = atomic64_read(&hwc->period_left);
+	long left = local64_read(&hwc->period_left);
 	long period = hwc->sample_period;
 	int ret = 0;

 	if (unlikely(left <= -period)) {
 		left = period;
-		atomic64_set(&hwc->period_left, left);
+		local64_set(&hwc->period_left, left);
 		hwc->last_period = period;
 		ret = 1;
 	}

 	if (unlikely(left <= 0)) {
 		left += period;
-		atomic64_set(&hwc->period_left, left);
+		local64_set(&hwc->period_left, left);
 		hwc->last_period = period;
 		ret = 1;
 	}
@ -269,7 +269,7 @@ static int alpha_perf_event_set_period(struct perf_event *event,
 	if (left > (long)alpha_pmu->pmc_max_period[idx])
 		left = alpha_pmu->pmc_max_period[idx];

-	atomic64_set(&hwc->prev_count, (unsigned long)(-left));
+	local64_set(&hwc->prev_count, (unsigned long)(-left));

 	alpha_write_pmc(idx, (unsigned long)(-left));

@ -300,10 +300,10 @@ static unsigned long alpha_perf_event_update(struct perf_event *event,
 	long delta;

 again:
-	prev_raw_count = atomic64_read(&hwc->prev_count);
+	prev_raw_count = local64_read(&hwc->prev_count);
 	new_raw_count = alpha_read_pmc(idx);

-	if (atomic64_cmpxchg(&hwc->prev_count, prev_raw_count,
+	if (local64_cmpxchg(&hwc->prev_count, prev_raw_count,
 			     new_raw_count) != prev_raw_count)
 		goto again;

@ -316,8 +316,8 @@ again:
 		delta += alpha_pmu->pmc_max_period[idx] + 1;
 	}

-	atomic64_add(delta, &event->count);
-	atomic64_sub(delta, &hwc->period_left);
+	local64_add(delta, &event->count);
+	local64_sub(delta, &hwc->period_left);

 	return new_raw_count;
 }
@ -636,7 +636,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 	if (!hwc->sample_period) {
 		hwc->sample_period = alpha_pmu->pmc_max_period[0];
 		hwc->last_period = hwc->sample_period;
-		atomic64_set(&hwc->period_left, hwc->sample_period);
+		local64_set(&hwc->period_left, hwc->sample_period);
 	}

 	return 0;
--- a/arch/alpha/kernel/proto.h
+++ b/arch/alpha/kernel/proto.h
@ -156,9 +156,6 @@ extern void SMC669_Init(int);
 /* es1888.c */
 extern void es1888_init(void);

-/* ns87312.c */
-extern void ns87312_enable_ide(long ide_base);
-
 /* ../lib/fpreg.c */
 extern void alpha_write_fp_reg (unsigned long reg, unsigned long val);
 extern unsigned long alpha_read_fp_reg (unsigned long reg);
--- a/arch/alpha/kernel/sys_cabriolet.c
+++ b/arch/alpha/kernel/sys_cabriolet.c
@ -33,7 +33,7 @@
 #include "irq_impl.h"
 #include "pci_impl.h"
 #include "machvec_impl.h"
-
+#include "pc873xx.h"

 /* Note mask bit is true for DISABLED irqs.  */
 static unsigned long cached_irq_mask = ~0UL;
@ -235,18 +235,31 @@ cabriolet_map_irq(struct pci_dev *dev, u8 slot, u8 pin)
 	return COMMON_TABLE_LOOKUP;
 }

+static inline void __init
+cabriolet_enable_ide(void)
+{
+	if (pc873xx_probe() == -1) {
+		printk(KERN_ERR "Probing for PC873xx Super IO chip failed.\n");
+	 } else {
+		printk(KERN_INFO "Found %s Super IO chip at 0x%x\n",
+			pc873xx_get_model(), pc873xx_get_base());
+
+		pc873xx_enable_ide();
+	}
+}
+
 static inline void __init
 cabriolet_init_pci(void)
 {
 	common_init_pci();
-	ns87312_enable_ide(0x398);
+	cabriolet_enable_ide();
 }

 static inline void __init
 cia_cab_init_pci(void)
 {
 	cia_init_pci();
-	ns87312_enable_ide(0x398);
+	cabriolet_enable_ide();
 }

 /*
--- a/arch/alpha/kernel/sys_takara.c
+++ b/arch/alpha/kernel/sys_takara.c
@ -29,7 +29,7 @@
 #include "irq_impl.h"
 #include "pci_impl.h"
 #include "machvec_impl.h"
-
+#include "pc873xx.h"

 /* Note mask bit is true for DISABLED irqs.  */
 static unsigned long cached_irq_mask[2] = { -1, -1 };
@ -264,7 +264,14 @@ takara_init_pci(void)
 		alpha_mv.pci_map_irq = takara_map_irq_srm;

 	cia_init_pci();
-	ns87312_enable_ide(0x26e);
+
+	if (pc873xx_probe() == -1) {
+		printk(KERN_ERR "Probing for PC873xx Super IO chip failed.\n");
+	} else {
+		printk(KERN_INFO "Found %s Super IO chip at 0x%x\n",
+			pc873xx_get_model(), pc873xx_get_base());
+		pc873xx_enable_ide();
+	}
 }


--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@ -1576,96 +1576,6 @@ config AUTO_ZRELADDR
 	  0xf8000000. This assumes the zImage being placed in the first 128MB
 	  from start of memory.

-config ZRELADDR
-	hex "Physical address of the decompressed kernel image"
-	depends on !AUTO_ZRELADDR
-	default 0x00008000 if ARCH_BCMRING ||\
-		ARCH_CNS3XXX ||\
-		ARCH_DOVE ||\
-		ARCH_EBSA110 ||\
-		ARCH_FOOTBRIDGE ||\
-		ARCH_INTEGRATOR ||\
-		ARCH_IOP13XX ||\
-		ARCH_IOP33X ||\
-		ARCH_IXP2000 ||\
-		ARCH_IXP23XX ||\
-		ARCH_IXP4XX ||\
-		ARCH_KIRKWOOD ||\
-		ARCH_KS8695 ||\
-		ARCH_LOKI ||\
-		ARCH_MMP ||\
-		ARCH_MV78XX0 ||\
-		ARCH_NOMADIK ||\
-		ARCH_NUC93X ||\
-		ARCH_NS9XXX ||\
-		ARCH_ORION5X ||\
-		ARCH_SPEAR3XX ||\
-		ARCH_SPEAR6XX ||\
-		ARCH_U8500 ||\
-		ARCH_VERSATILE ||\
-		ARCH_W90X900
-	default 0x08008000 if ARCH_MX1 ||\
-		ARCH_SHARK
-	default 0x10008000 if ARCH_MSM ||\
-		ARCH_OMAP1 ||\
-		ARCH_RPC
-	default 0x20008000 if ARCH_S5P6440 ||\
-		ARCH_S5P6442 ||\
-		ARCH_S5PC100 ||\
-		ARCH_S5PV210
-	default 0x30008000 if ARCH_S3C2410 ||\
-		ARCH_S3C2400 ||\
-		ARCH_S3C2412 ||\
-		ARCH_S3C2416 ||\
-		ARCH_S3C2440 ||\
-		ARCH_S3C2443
-	default 0x40008000 if ARCH_STMP378X ||\
-		ARCH_STMP37XX ||\
-		ARCH_SH7372 ||\
-		ARCH_SH7377 ||\
-		ARCH_S5PV310
-	default 0x50008000 if ARCH_S3C64XX ||\
-		ARCH_SH7367
-	default 0x60008000 if ARCH_VEXPRESS
-	default 0x80008000 if ARCH_MX25 ||\
-		ARCH_MX3 ||\
-		ARCH_NETX ||\
-		ARCH_OMAP2PLUS ||\
-		ARCH_PNX4008
-	default 0x90008000 if ARCH_MX5 ||\
-		ARCH_MX91231
-	default 0xa0008000 if ARCH_IOP32X ||\
-		ARCH_PXA ||\
-		MACH_MX27
-	default 0xc0008000 if ARCH_LH7A40X ||\
-		MACH_MX21
-	default 0xf0008000 if ARCH_AAEC2000 ||\
-		ARCH_L7200
-	default 0xc0028000 if ARCH_CLPS711X
-	default 0x70008000 if ARCH_AT91 && (ARCH_AT91CAP9 || ARCH_AT91SAM9G45)
-	default 0x20008000 if ARCH_AT91 && !(ARCH_AT91CAP9 || ARCH_AT91SAM9G45)
-	default 0xc0008000 if ARCH_DAVINCI && ARCH_DAVINCI_DA8XX
-	default 0x80008000 if ARCH_DAVINCI && !ARCH_DAVINCI_DA8XX
-	default 0x00008000 if ARCH_EP93XX && EP93XX_SDCE3_SYNC_PHYS_OFFSET
-	default 0xc0008000 if ARCH_EP93XX && EP93XX_SDCE0_PHYS_OFFSET
-	default 0xd0008000 if ARCH_EP93XX && EP93XX_SDCE1_PHYS_OFFSET
-	default 0xe0008000 if ARCH_EP93XX && EP93XX_SDCE2_PHYS_OFFSET
-	default 0xf0008000 if ARCH_EP93XX && EP93XX_SDCE3_ASYNC_PHYS_OFFSET
-	default 0x00008000 if ARCH_GEMINI && GEMINI_MEM_SWAP
-	default 0x10008000 if ARCH_GEMINI && !GEMINI_MEM_SWAP
-	default 0x70008000 if ARCH_REALVIEW && REALVIEW_HIGH_PHYS_OFFSET
-	default 0x00008000 if ARCH_REALVIEW && !REALVIEW_HIGH_PHYS_OFFSET
-	default 0xc0208000 if ARCH_SA1100 && SA1111
-	default 0xc0008000 if ARCH_SA1100 && !SA1111
-	default 0x30108000 if ARCH_S3C2410 && PM_H1940
-	default 0x28E08000 if ARCH_U300 && MACH_U300_SINGLE_RAM
-	default 0x48008000 if ARCH_U300 && !MACH_U300_SINGLE_RAM
-	help
-	  ZRELADDR is the physical address where the decompressed kernel
-	  image will be placed. ZRELADDR has to be specified when the
-	  assumption of AUTO_ZRELADDR is not valid, or when ZBOOT_ROM is
-	  selected.
-
 endmenu

 menu "CPU Power Management"
--- a/arch/arm/boot/Makefile
+++ b/arch/arm/boot/Makefile
@ -14,16 +14,18 @@
 MKIMAGE         := $(srctree)/scripts/mkuboot.sh

 ifneq ($(MACHINE),)
-include $(srctree)/$(MACHINE)/Makefile.boot
+include $(srctree)/$(MACHINE)/Makefile.boot
 endif

 # Note: the following conditions must always be true:
+#   ZRELADDR == virt_to_phys(PAGE_OFFSET + TEXT_OFFSET)
 #   PARAMS_PHYS must be within 4MB of ZRELADDR
 #   INITRD_PHYS must be in RAM
+ZRELADDR    := $(zreladdr-y)
 PARAMS_PHYS := $(params_phys-y)
 INITRD_PHYS := $(initrd_phys-y)

-export INITRD_PHYS PARAMS_PHYS
+export ZRELADDR INITRD_PHYS PARAMS_PHYS

 targets := Image zImage xipImage bootpImage uImage

@ -65,7 +67,7 @@ quiet_cmd_uimage = UIMAGE  $@
 ifeq ($(CONFIG_ZBOOT_ROM),y)
 $(obj)/uImage: LOADADDR=$(CONFIG_ZBOOT_ROM_TEXT)
 else
-$(obj)/uImage: LOADADDR=$(CONFIG_ZRELADDR)
+$(obj)/uImage: LOADADDR=$(ZRELADDR)
 endif

 ifeq ($(CONFIG_THUMB2_KERNEL),y)
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@ -79,6 +79,10 @@ endif
 EXTRA_CFLAGS  := -fpic -fno-builtin
 EXTRA_AFLAGS  := -Wa,-march=all

+# Supply ZRELADDR to the decompressor via a linker symbol.
+ifneq ($(CONFIG_AUTO_ZRELADDR),y)
+LDFLAGS_vmlinux := --defsym zreladdr=$(ZRELADDR)
+endif
 ifeq ($(CONFIG_CPU_ENDIAN_BE8),y)
 LDFLAGS_vmlinux += --be8
 endif
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@ -177,7 +177,7 @@ not_angel:
 		and	r4, pc, #0xf8000000
 		add	r4, r4, #TEXT_OFFSET
 #else
-		ldr	r4, =CONFIG_ZRELADDR
+		ldr	r4, =zreladdr
 #endif
 		subs	r0, r0, r1		@ calculate the delta offset

--- a/arch/arm/common/it8152.c
+++ b/arch/arm/common/it8152.c
@ -263,6 +263,14 @@ static int it8152_pci_platform_notify_remove(struct device *dev)
 	return 0;
 }

+int dma_needs_bounce(struct device *dev, dma_addr_t dma_addr, size_t size)
+{
+	dev_dbg(dev, "%s: dma_addr %08x, size %08x\n",
+		__func__, dma_addr, size);
+	return (dev->bus == &pci_bus_type) &&
+		((dma_addr + size - PHYS_OFFSET) >= SZ_64M);
+}
+
 int __init it8152_pci_setup(int nr, struct pci_sys_data *sys)
 {
 	it8152_io.start = IT8152_IO_BASE + 0x12000;
--- a/arch/arm/include/asm/dma-mapping.h
+++ b/arch/arm/include/asm/dma-mapping.h
@ -288,15 +288,7 @@ extern void dmabounce_unregister_dev(struct device *);
 * DMA access and 1 if the buffer needs to be bounced.
 *
 */
-#ifdef CONFIG_SA1111
 extern int dma_needs_bounce(struct device*, dma_addr_t, size_t);
-#else
-static inline int dma_needs_bounce(struct device *dev, dma_addr_t addr,
-				   size_t size)
-{
-	return 0;
-}
-#endif

 /*
 * The DMA API, implemented by dmabounce.c.  See below for descriptions.
--- a/arch/arm/include/asm/perf_event.h
+++ b/arch/arm/include/asm/perf_event.h
@ -17,7 +17,7 @@
 * counter interrupts are regular interrupts and not an NMI. This
 * means that when we receive the interrupt we can call
 * perf_event_do_pending() that handles all of the work with
- * interrupts enabled.
+ * interrupts disabled.
 */
 static inline void
 set_perf_event_pending(void)
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@ -393,6 +393,9 @@
 #define __NR_perf_event_open		(__NR_SYSCALL_BASE+364)
 #define __NR_recvmmsg			(__NR_SYSCALL_BASE+365)
 #define __NR_accept4			(__NR_SYSCALL_BASE+366)
+#define __NR_fanotify_init		(__NR_SYSCALL_BASE+367)
+#define __NR_fanotify_mark		(__NR_SYSCALL_BASE+368)
+#define __NR_prlimit64			(__NR_SYSCALL_BASE+369)

 /*
 * The following SWIs are ARM private.
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@ -376,6 +376,9 @@
 		CALL(sys_perf_event_open)
 /* 365 */	CALL(sys_recvmmsg)
 		CALL(sys_accept4)
+		CALL(sys_fanotify_init)
+		CALL(sys_fanotify_mark)
+		CALL(sys_prlimit64)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@ -319,8 +319,8 @@ validate_event(struct cpu_hw_events *cpuc,
 {
 	struct hw_perf_event fake_event = event->hw;

-	if (event->pmu && event->pmu != &pmu)
-		return 0;
+	if (event->pmu != &pmu || event->state <= PERF_EVENT_STATE_OFF)
+		return 1;

 	return armpmu->get_event_idx(cpuc, &fake_event) >= 0;
 }
@ -1041,8 +1041,8 @@ armv6pmu_handle_irq(int irq_num,
 	/*
 	 * Handle the pending perf events.
 	 *
-	 * Note: this call *must* be run with interrupts enabled. For
-	 * platforms that can have the PMU interrupts raised as a PMI, this
+	 * Note: this call *must* be run with interrupts disabled. For
+	 * platforms that can have the PMU interrupts raised as an NMI, this
 	 * will not work.
 	 */
 	perf_event_do_pending();
@ -2017,8 +2017,8 @@ static irqreturn_t armv7pmu_handle_irq(int irq_num, void *dev)
 	/*
 	 * Handle the pending perf events.
 	 *
-	 * Note: this call *must* be run with interrupts enabled. For
-	 * platforms that can have the PMU interrupts raised as a PMI, this
+	 * Note: this call *must* be run with interrupts disabled. For
+	 * platforms that can have the PMU interrupts raised as an NMI, this
 	 * will not work.
 	 */
 	perf_event_do_pending();
--- a/arch/arm/mach-at91/at91sam9g45.c
+++ b/arch/arm/mach-at91/at91sam9g45.c
@ -121,8 +121,8 @@ static struct clk ssc1_clk = {
 	.pmc_mask	= 1 << AT91SAM9G45_ID_SSC1,
 	.type		= CLK_TYPE_PERIPHERAL,
 };
-static struct clk tcb_clk = {
-	.name		= "tcb_clk",
+static struct clk tcb0_clk = {
+	.name		= "tcb0_clk",
 	.pmc_mask	= 1 << AT91SAM9G45_ID_TCB,
 	.type		= CLK_TYPE_PERIPHERAL,
 };
@ -192,6 +192,14 @@ static struct clk ohci_clk = {
 	.parent		= &uhphs_clk,
 };

+/* One additional fake clock for second TC block */
+static struct clk tcb1_clk = {
+	.name		= "tcb1_clk",
+	.pmc_mask	= 0,
+	.type		= CLK_TYPE_PERIPHERAL,
+	.parent		= &tcb0_clk,
+};
+
 static struct clk *periph_clocks[] __initdata = {
 	&pioA_clk,
 	&pioB_clk,
@ -208,7 +216,7 @@ static struct clk *periph_clocks[] __initdata = {
 	&spi1_clk,
 	&ssc0_clk,
 	&ssc1_clk,
-	&tcb_clk,
+	&tcb0_clk,
 	&pwm_clk,
 	&tsc_clk,
 	&dma_clk,
@ -221,6 +229,7 @@ static struct clk *periph_clocks[] __initdata = {
 	&mmc1_clk,
 	// irq0
 	&ohci_clk,
+	&tcb1_clk,
 };

 /*
--- a/arch/arm/mach-at91/at91sam9g45_devices.c
+++ b/arch/arm/mach-at91/at91sam9g45_devices.c
@ -46,7 +46,7 @@ static struct resource hdmac_resources[] = {
 		.end	= AT91_BASE_SYS + AT91_DMA + SZ_512 - 1,
 		.flags	= IORESOURCE_MEM,
 	},
-	[2] = {
+	[1] = {
 		.start	= AT91SAM9G45_ID_DMA,
 		.end	= AT91SAM9G45_ID_DMA,
 		.flags	= IORESOURCE_IRQ,
@ -835,9 +835,9 @@ static struct platform_device at91sam9g45_tcb1_device = {
 static void __init at91_add_device_tc(void)
 {
 	/* this chip has one clock and irq for all six TC channels */
-	at91_clock_associate("tcb_clk", &at91sam9g45_tcb0_device.dev, "t0_clk");
+	at91_clock_associate("tcb0_clk", &at91sam9g45_tcb0_device.dev, "t0_clk");
 	platform_device_register(&at91sam9g45_tcb0_device);
-	at91_clock_associate("tcb_clk", &at91sam9g45_tcb1_device.dev, "t0_clk");
+	at91_clock_associate("tcb1_clk", &at91sam9g45_tcb1_device.dev, "t0_clk");
 	platform_device_register(&at91sam9g45_tcb1_device);
 }
 #else
--- a/arch/arm/mach-at91/board-sam9261ek.c
+++ b/arch/arm/mach-at91/board-sam9261ek.c
@ -93,11 +93,12 @@ static struct resource dm9000_resource[] = {
 		.start	= AT91_PIN_PC11,
 		.end	= AT91_PIN_PC11,
 		.flags	= IORESOURCE_IRQ
+			| IORESOURCE_IRQ_LOWEDGE | IORESOURCE_IRQ_HIGHEDGE,
 	}
 };

 static struct dm9000_plat_data dm9000_platdata = {
-	.flags		= DM9000_PLATF_16BITONLY,
+	.flags		= DM9000_PLATF_16BITONLY | DM9000_PLATF_NO_EEPROM,
 };

 static struct platform_device dm9000_device = {
@ -167,17 +168,6 @@ static struct at91_udc_data __initdata ek_udc_data = {
 };


-/*
- * MCI (SD/MMC)
- */
-static struct at91_mmc_data __initdata ek_mmc_data = {
-	.wire4		= 1,
-//	.det_pin	= ... not connected
-//	.wp_pin		= ... not connected
-//	.vcc_pin	= ... not connected
-};
-
-
 /*
 * NAND flash
 */
@ -246,6 +236,10 @@ static void __init ek_add_device_nand(void)
 	at91_add_device_nand(&ek_nand_data);
 }

+/*
+ * SPI related devices
+ */
+#if defined(CONFIG_SPI_ATMEL) || defined(CONFIG_SPI_ATMEL_MODULE)

 /*
 * ADS7846 Touchscreen
@ -356,6 +350,19 @@ static struct spi_board_info ek_spi_devices[] = {
 #endif
 };

+#else /* CONFIG_SPI_ATMEL_* */
+/* spi0 and mmc/sd share the same PIO pins: cannot be used at the same time */
+
+/*
+ * MCI (SD/MMC)
+ * det_pin, wp_pin and vcc_pin are not connected
+ */
+static struct at91_mmc_data __initdata ek_mmc_data = {
+	.wire4		= 1,
+};
+
+#endif /* CONFIG_SPI_ATMEL_* */
+

 /*
 * LCD Controller
--- a/arch/arm/mach-at91/clock.c
+++ b/arch/arm/mach-at91/clock.c
@ -501,7 +501,8 @@ postcore_initcall(at91_clk_debugfs_init);
 int __init clk_register(struct clk *clk)
 {
 	if (clk_is_peripheral(clk)) {
-		clk->parent = &mck;
+		if (!clk->parent)
+			clk->parent = &mck;
 		clk->mode = pmc_periph_mode;
 		list_add_tail(&clk->node, &clocks);
 	}
--- a/arch/arm/mach-ep93xx/clock.c
+++ b/arch/arm/mach-ep93xx/clock.c
@ -560,4 +560,4 @@ static int __init ep93xx_clock_init(void)
 	clkdev_add_table(clocks, ARRAY_SIZE(clocks));
 	return 0;
 }
-arch_initcall(ep93xx_clock_init);
+postcore_initcall(ep93xx_clock_init);
--- a/arch/arm/mach-mx25/eukrea_mbimxsd-baseboard.c
+++ b/arch/arm/mach-mx25/eukrea_mbimxsd-baseboard.c
@ -215,7 +215,7 @@ struct imx_ssi_platform_data eukrea_mbimxsd_ssi_pdata = {
 * Add platform devices present on this baseboard and init
 * them from CPU side as far as required to use them later on
 */
-void __init eukrea_mbimxsd_baseboard_init(void)
+void __init eukrea_mbimxsd25_baseboard_init(void)
 {
 	if (mxc_iomux_v3_setup_multiple_pads(eukrea_mbimxsd_pads,
 			ARRAY_SIZE(eukrea_mbimxsd_pads)))
--- a/arch/arm/mach-mx25/mach-cpuimx25.c
+++ b/arch/arm/mach-mx25/mach-cpuimx25.c
@ -147,8 +147,8 @@ static void __init eukrea_cpuimx25_init(void)
 	if (!otg_mode_host)
 		mxc_register_device(&otg_udc_device, &otg_device_pdata);

-#ifdef CONFIG_MACH_EUKREA_MBIMXSD_BASEBOARD
-	eukrea_mbimxsd_baseboard_init();
+#ifdef CONFIG_MACH_EUKREA_MBIMXSD25_BASEBOARD
+	eukrea_mbimxsd25_baseboard_init();
 #endif
 }

--- a/arch/arm/mach-mx3/clock-imx35.c
+++ b/arch/arm/mach-mx3/clock-imx35.c
@ -155,7 +155,7 @@ static unsigned long get_rate_arm(void)

 	aad = &clk_consumer[(pdr0 >> 16) & 0xf];
 	if (aad->sel)
-		fref = fref * 2 / 3;
+		fref = fref * 3 / 4;

 	return fref / aad->arm;
 }
@ -164,7 +164,7 @@ static unsigned long get_rate_ahb(struct clk *clk)
 {
 	unsigned long pdr0 = __raw_readl(CCM_BASE + CCM_PDR0);
 	struct arm_ahb_div *aad;
-	unsigned long fref = get_rate_mpll();
+	unsigned long fref = get_rate_arm();

 	aad = &clk_consumer[(pdr0 >> 16) & 0xf];

@ -176,16 +176,11 @@ static unsigned long get_rate_ipg(struct clk *clk)
 	return get_rate_ahb(NULL) >> 1;
 }

-static unsigned long get_3_3_div(unsigned long in)
-{
-	return (((in >> 3) & 0x7) + 1) * ((in & 0x7) + 1);
-}
-
 static unsigned long get_rate_uart(struct clk *clk)
 {
 	unsigned long pdr3 = __raw_readl(CCM_BASE + CCM_PDR3);
 	unsigned long pdr4 = __raw_readl(CCM_BASE + CCM_PDR4);
-	unsigned long div = get_3_3_div(pdr4 >> 10);
+	unsigned long div = ((pdr4 >> 10) & 0x3f) + 1;

 	if (pdr3 & (1 << 14))
 		return get_rate_arm() / div;
@ -216,7 +211,7 @@ static unsigned long get_rate_sdhc(struct clk *clk)
 		break;
 	}

-	return rate / get_3_3_div(div);
+	return rate / (div + 1);
 }

 static unsigned long get_rate_mshc(struct clk *clk)
@ -270,7 +265,7 @@ static unsigned long get_rate_csi(struct clk *clk)
 	else
 		rate = get_rate_ppll();

-	return rate / get_3_3_div((pdr2 >> 16) & 0x3f);
+	return rate / (((pdr2 >> 16) & 0x3f) + 1);
 }

 static unsigned long get_rate_otg(struct clk *clk)
@ -283,25 +278,51 @@ static unsigned long get_rate_otg(struct clk *clk)
 	else
 		rate = get_rate_ppll();

-	return rate / get_3_3_div((pdr4 >> 22) & 0x3f);
+	return rate / (((pdr4 >> 22) & 0x3f) + 1);
 }

 static unsigned long get_rate_ipg_per(struct clk *clk)
 {
 	unsigned long pdr0 = __raw_readl(CCM_BASE + CCM_PDR0);
 	unsigned long pdr4 = __raw_readl(CCM_BASE + CCM_PDR4);
-	unsigned long div1, div2;
+	unsigned long div;

 	if (pdr0 & (1 << 26)) {
-		div1 = (pdr4 >> 19) & 0x7;
-		div2 = (pdr4 >> 16) & 0x7;
-		return get_rate_arm() / ((div1 + 1) * (div2 + 1));
+		div = (pdr4 >> 16) & 0x3f;
+		return get_rate_arm() / (div + 1);
 	} else {
-		div1 = (pdr0 >> 12) & 0x7;
-		return get_rate_ahb(NULL) / div1;
+		div = (pdr0 >> 12) & 0x7;
+		return get_rate_ahb(NULL) / (div + 1);
 	}
 }

+static unsigned long get_rate_hsp(struct clk *clk)
+{
+	unsigned long hsp_podf = (__raw_readl(CCM_BASE + CCM_PDR0) >> 20) & 0x03;
+	unsigned long fref = get_rate_mpll();
+
+	if (fref > 400 * 1000 * 1000) {
+		switch (hsp_podf) {
+		case 0:
+			return fref >> 2;
+		case 1:
+			return fref >> 3;
+		case 2:
+			return fref / 3;
+		}
+	} else {
+		switch (hsp_podf) {
+		case 0:
+		case 2:
+			return fref / 3;
+		case 1:
+			return fref / 6;
+		}
+	}
+
+	return 0;
+}
+
 static int clk_cgr_enable(struct clk *clk)
 {
 	u32 reg;
@ -359,7 +380,7 @@ DEFINE_CLOCK(i2c1_clk,   0, CCM_CGR1, 10, get_rate_ipg_per, NULL);
 DEFINE_CLOCK(i2c2_clk,   1, CCM_CGR1, 12, get_rate_ipg_per, NULL);
 DEFINE_CLOCK(i2c3_clk,   2, CCM_CGR1, 14, get_rate_ipg_per, NULL);
 DEFINE_CLOCK(iomuxc_clk, 0, CCM_CGR1, 16, NULL, NULL);
-DEFINE_CLOCK(ipu_clk,    0, CCM_CGR1, 18, get_rate_ahb, NULL);
+DEFINE_CLOCK(ipu_clk,    0, CCM_CGR1, 18, get_rate_hsp, NULL);
 DEFINE_CLOCK(kpp_clk,    0, CCM_CGR1, 20, get_rate_ipg, NULL);
 DEFINE_CLOCK(mlb_clk,    0, CCM_CGR1, 22, get_rate_ahb, NULL);
 DEFINE_CLOCK(mshc_clk,   0, CCM_CGR1, 24, get_rate_mshc, NULL);
@ -485,10 +506,10 @@ static struct clk_lookup lookups[] = {

 int __init mx35_clocks_init()
 {
-	unsigned int ll = 0;
+	unsigned int cgr2 = 3 << 26, cgr3 = 0;

 #if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_ICEDCC)
-	ll = (3 << 16);
+	cgr2 |= 3 << 16;
 #endif

 	clkdev_add_table(lookups, ARRAY_SIZE(lookups));
@ -499,8 +520,20 @@ int __init mx35_clocks_init()
 	__raw_writel((3 << 18), CCM_BASE + CCM_CGR0);
 	__raw_writel((3 << 2) | (3 << 4) | (3 << 6) | (3 << 8) | (3 << 16),
 			CCM_BASE + CCM_CGR1);
-	__raw_writel((3 << 26) | ll, CCM_BASE + CCM_CGR2);
-	__raw_writel(0, CCM_BASE + CCM_CGR3);
+
+	/*
+	 * Check if we came up in internal boot mode. If yes, we need some
+	 * extra clocks turned on, otherwise the MX35 boot ROM code will
+	 * hang after a watchdog reset.
+	 */
+	if (!(__raw_readl(CCM_BASE + CCM_RCSR) & (3 << 10))) {
+		/* Additionally turn on UART1, SCC, and IIM clocks */
+		cgr2 |= 3 << 16 | 3 << 4;
+		cgr3 |= 3 << 2;
+	}
+
+	__raw_writel(cgr2, CCM_BASE + CCM_CGR2);
+	__raw_writel(cgr3, CCM_BASE + CCM_CGR3);

 	mxc_timer_init(&gpt_clk,
 			MX35_IO_ADDRESS(MX35_GPT1_BASE_ADDR), MX35_INT_GPT);
--- a/arch/arm/mach-mx3/eukrea_mbimxsd-baseboard.c
+++ b/arch/arm/mach-mx3/eukrea_mbimxsd-baseboard.c
@ -216,7 +216,7 @@ struct imx_ssi_platform_data eukrea_mbimxsd_ssi_pdata = {
 * Add platform devices present on this baseboard and init
 * them from CPU side as far as required to use them later on
 */
-void __init eukrea_mbimxsd_baseboard_init(void)
+void __init eukrea_mbimxsd35_baseboard_init(void)
 {
 	if (mxc_iomux_v3_setup_multiple_pads(eukrea_mbimxsd_pads,
 			ARRAY_SIZE(eukrea_mbimxsd_pads)))
--- a/arch/arm/mach-mx3/mach-cpuimx35.c
+++ b/arch/arm/mach-mx3/mach-cpuimx35.c
@ -201,8 +201,8 @@ static void __init mxc_board_init(void)
 	if (!otg_mode_host)
 		mxc_register_device(&mxc_otg_udc_device, &otg_device_pdata);

-#ifdef CONFIG_MACH_EUKREA_MBIMXSD_BASEBOARD
-	eukrea_mbimxsd_baseboard_init();
+#ifdef CONFIG_MACH_EUKREA_MBIMXSD35_BASEBOARD
+	eukrea_mbimxsd35_baseboard_init();
 #endif
 }

--- a/arch/arm/mach-mx5/clock-mx51.c
+++ b/arch/arm/mach-mx5/clock-mx51.c
@ -56,7 +56,7 @@ static void _clk_ccgr_disable(struct clk *clk)
 {
 	u32 reg;
 	reg = __raw_readl(clk->enable_reg);
-	reg &= ~(MXC_CCM_CCGRx_MOD_OFF << clk->enable_shift);
+	reg &= ~(MXC_CCM_CCGRx_CG_MASK << clk->enable_shift);
 	__raw_writel(reg, clk->enable_reg);

 }
--- a/arch/arm/mach-pxa/cpufreq-pxa2xx.c
+++ b/arch/arm/mach-pxa/cpufreq-pxa2xx.c
@ -398,7 +398,7 @@ static int pxa_set_target(struct cpufreq_policy *policy,
 	return 0;
 }

-static __init int pxa_cpufreq_init(struct cpufreq_policy *policy)
+static int pxa_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int i;
 	unsigned int freq;
--- a/arch/arm/mach-pxa/cpufreq-pxa3xx.c
+++ b/arch/arm/mach-pxa/cpufreq-pxa3xx.c
@ -204,7 +204,7 @@ static int pxa3xx_cpufreq_set(struct cpufreq_policy *policy,
 	return 0;
 }

-static __init int pxa3xx_cpufreq_init(struct cpufreq_policy *policy)
+static int pxa3xx_cpufreq_init(struct cpufreq_policy *policy)
 {
 	int ret = -EINVAL;

--- a/arch/arm/mach-pxa/include/mach/mfp-pxa300.h
+++ b/arch/arm/mach-pxa/include/mach/mfp-pxa300.h
@ -71,10 +71,10 @@
 #define GPIO46_CI_DD_7		MFP_CFG_DRV(GPIO46, AF0, DS04X)
 #define GPIO47_CI_DD_8		MFP_CFG_DRV(GPIO47, AF1, DS04X)
 #define GPIO48_CI_DD_9		MFP_CFG_DRV(GPIO48, AF1, DS04X)
-#define GPIO52_CI_HSYNC		MFP_CFG_DRV(GPIO52, AF0, DS04X)
-#define GPIO51_CI_VSYNC		MFP_CFG_DRV(GPIO51, AF0, DS04X)
 #define GPIO49_CI_MCLK		MFP_CFG_DRV(GPIO49, AF0, DS04X)
 #define GPIO50_CI_PCLK		MFP_CFG_DRV(GPIO50, AF0, DS04X)
+#define GPIO51_CI_HSYNC		MFP_CFG_DRV(GPIO51, AF0, DS04X)
+#define GPIO52_CI_VSYNC		MFP_CFG_DRV(GPIO52, AF0, DS04X)

 /* KEYPAD */
 #define GPIO3_KP_DKIN_6		MFP_CFG_LPM(GPIO3,   AF2, FLOAT)
--- a/arch/arm/mach-shmobile/Makefile
+++ b/arch/arm/mach-shmobile/Makefile
@ -3,7 +3,7 @@
 #

 # Common objects
-obj-y				:= timer.o console.o clock.o
+obj-y				:= timer.o console.o clock.o pm_runtime.o

 # CPU objects
 obj-$(CONFIG_ARCH_SH7367)	+= setup-sh7367.o clock-sh7367.o intc-sh7367.o
--- a/arch/arm/mach-shmobile/board-ap4evb.c
+++ b/arch/arm/mach-shmobile/board-ap4evb.c
@ -25,6 +25,7 @@
 #include <linux/platform_device.h>
 #include <linux/delay.h>
 #include <linux/mfd/sh_mobile_sdhi.h>
+#include <linux/mfd/tmio.h>
 #include <linux/mmc/host.h>
 #include <linux/mtd/mtd.h>
 #include <linux/mtd/partitions.h>
@ -39,6 +40,7 @@
 #include <linux/sh_clk.h>
 #include <linux/gpio.h>
 #include <linux/input.h>
+#include <linux/leds.h>
 #include <linux/input/sh_keysc.h>
 #include <linux/usb/r8a66597.h>

@ -307,6 +309,7 @@ static struct sh_mobile_sdhi_info sdhi1_info = {
 	.dma_slave_tx	= SHDMA_SLAVE_SDHI1_TX,
 	.dma_slave_rx	= SHDMA_SLAVE_SDHI1_RX,
 	.tmio_ocr_mask	= MMC_VDD_165_195,
+	.tmio_flags	= TMIO_MMC_WRPROTECT_DISABLE,
 };

 static struct resource sdhi1_resources[] = {
@ -558,7 +561,7 @@ static struct resource fsi_resources[] = {

 static struct platform_device fsi_device = {
 	.name		= "sh_fsi2",
-	.id		= 0,
+	.id		= -1,
 	.num_resources	= ARRAY_SIZE(fsi_resources),
 	.resource	= fsi_resources,
 	.dev	= {
@ -650,7 +653,44 @@ static struct platform_device hdmi_device = {
 	},
 };

+static struct gpio_led ap4evb_leds[] = {
+	{
+		.name			= "led4",
+		.gpio			= GPIO_PORT185,
+		.default_state	= LEDS_GPIO_DEFSTATE_ON,
+	},
+	{
+		.name			= "led2",
+		.gpio			= GPIO_PORT186,
+		.default_state	= LEDS_GPIO_DEFSTATE_ON,
+	},
+	{
+		.name			= "led3",
+		.gpio			= GPIO_PORT187,
+		.default_state	= LEDS_GPIO_DEFSTATE_ON,
+	},
+	{
+		.name			= "led1",
+		.gpio			= GPIO_PORT188,
+		.default_state	= LEDS_GPIO_DEFSTATE_ON,
+	}
+};
+
+static struct gpio_led_platform_data ap4evb_leds_pdata = {
+	.num_leds = ARRAY_SIZE(ap4evb_leds),
+	.leds = ap4evb_leds,
+};
+
+static struct platform_device leds_device = {
+	.name = "leds-gpio",
+	.id = 0,
+	.dev = {
+		.platform_data  = &ap4evb_leds_pdata,
+	},
+};
+
 static struct platform_device *ap4evb_devices[] __initdata = {
+	&leds_device,
 	&nor_flash_device,
 	&smc911x_device,
 	&sdhi0_device,
@ -840,20 +880,6 @@ static void __init ap4evb_init(void)
 	gpio_request(GPIO_FN_CS5A,	NULL);
 	gpio_request(GPIO_FN_IRQ6_39,	NULL);

-	/* enable LED 1 - 4 */
-	gpio_request(GPIO_PORT185, NULL);
-	gpio_request(GPIO_PORT186, NULL);
-	gpio_request(GPIO_PORT187, NULL);
-	gpio_request(GPIO_PORT188, NULL);
-	gpio_direction_output(GPIO_PORT185, 1);
-	gpio_direction_output(GPIO_PORT186, 1);
-	gpio_direction_output(GPIO_PORT187, 1);
-	gpio_direction_output(GPIO_PORT188, 1);
-	gpio_export(GPIO_PORT185, 0);
-	gpio_export(GPIO_PORT186, 0);
-	gpio_export(GPIO_PORT187, 0);
-	gpio_export(GPIO_PORT188, 0);
-
 	/* enable Debug switch (S6) */
 	gpio_request(GPIO_PORT32, NULL);
 	gpio_request(GPIO_PORT33, NULL);
--- a/arch/arm/mach-shmobile/clock-sh7372.c
+++ b/arch/arm/mach-shmobile/clock-sh7372.c
@ -286,7 +286,6 @@ static struct clk_ops pllc2_clk_ops = {

 struct clk pllc2_clk = {
 	.ops		= &pllc2_clk_ops,
-	.flags		= CLK_ENABLE_ON_INIT,
 	.parent		= &extal1_div2_clk,
 	.freq_table	= pllc2_freq_table,
 	.parent_table	= pllc2_parent,
@ -395,7 +394,7 @@ static struct clk div6_reparent_clks[DIV6_REPARENT_NR] = {

 enum { MSTP001,
       MSTP131, MSTP130,
-       MSTP129, MSTP128,
+       MSTP129, MSTP128, MSTP127, MSTP126,
       MSTP118, MSTP117, MSTP116,
       MSTP106, MSTP101, MSTP100,
       MSTP223,
@ -413,6 +412,8 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP130] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 30, 0), /* VEU2 */
 	[MSTP129] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 29, 0), /* VEU1 */
 	[MSTP128] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 28, 0), /* VEU0 */
+	[MSTP127] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 27, 0), /* CEU */
+	[MSTP126] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 26, 0), /* CSI2 */
 	[MSTP118] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 18, 0), /* DSITX */
 	[MSTP117] = MSTP(&div4_clks[DIV4_B], SMSTPCR1, 17, 0), /* LCDC1 */
 	[MSTP116] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR1, 16, 0), /* IIC0 */
@ -428,7 +429,7 @@ static struct clk mstp_clks[MSTP_NR] = {
 	[MSTP201] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 1, 0), /* SCIFA3 */
 	[MSTP200] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR2, 0, 0), /* SCIFA4 */
 	[MSTP329] = MSTP(&r_clk, SMSTPCR3, 29, 0), /* CMT10 */
-	[MSTP328] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR3, 28, CLK_ENABLE_ON_INIT), /* FSIA */
+	[MSTP328] = MSTP(&div6_clks[DIV6_SPU], SMSTPCR3, 28, 0), /* FSIA */
 	[MSTP323] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 23, 0), /* IIC1 */
 	[MSTP322] = MSTP(&div6_clks[DIV6_SUB], SMSTPCR3, 22, 0), /* USB0 */
 	[MSTP314] = MSTP(&div4_clks[DIV4_HP], SMSTPCR3, 14, 0), /* SDHI0 */
@ -498,6 +499,8 @@ static struct clk_lookup lookups[] = {
 	CLKDEV_DEV_ID("uio_pdrv_genirq.3", &mstp_clks[MSTP130]), /* VEU2 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.2", &mstp_clks[MSTP129]), /* VEU1 */
 	CLKDEV_DEV_ID("uio_pdrv_genirq.1", &mstp_clks[MSTP128]), /* VEU0 */
+	CLKDEV_DEV_ID("sh_mobile_ceu.0", &mstp_clks[MSTP127]), /* CEU */
+	CLKDEV_DEV_ID("sh-mobile-csi2.0", &mstp_clks[MSTP126]), /* CSI2 */
 	CLKDEV_DEV_ID("sh-mipi-dsi.0", &mstp_clks[MSTP118]), /* DSITX */
 	CLKDEV_DEV_ID("sh_mobile_lcdc_fb.1", &mstp_clks[MSTP117]), /* LCDC1 */
 	CLKDEV_DEV_ID("i2c-sh_mobile.0", &mstp_clks[MSTP116]), /* IIC0 */
--- a/arch/arm/mach-shmobile/clock.c
+++ b/arch/arm/mach-shmobile/clock.c
@ -1,8 +1,10 @@
 /*
- * SH-Mobile Timer
+ * SH-Mobile Clock Framework
 *
 * Copyright (C) 2010  Magnus Damm
 *
+ * Used together with arch/arm/common/clkdev.c and drivers/sh/clk.c.
+ *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; version 2 of the License.
--- a/arch/arm/mach-shmobile/pm_runtime.c
+++ b/arch/arm/mach-shmobile/pm_runtime.c
@ -0,0 +1,169 @@
+/*
+ * arch/arm/mach-shmobile/pm_runtime.c
+ *
+ * Runtime PM support code for SuperH Mobile ARM
+ *
+ *  Copyright (C) 2009-2010 Magnus Damm
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/io.h>
+#include <linux/pm_runtime.h>
+#include <linux/platform_device.h>
+#include <linux/clk.h>
+#include <linux/sh_clk.h>
+#include <linux/bitmap.h>
+
+#ifdef CONFIG_PM_RUNTIME
+#define BIT_ONCE 0
+#define BIT_ACTIVE 1
+#define BIT_CLK_ENABLED 2
+
+struct pm_runtime_data {
+	unsigned long flags;
+	struct clk *clk;
+};
+
+static void __devres_release(struct device *dev, void *res)
+{
+	struct pm_runtime_data *prd = res;
+
+	dev_dbg(dev, "__devres_release()\n");
+
+	if (test_bit(BIT_CLK_ENABLED, &prd->flags))
+		clk_disable(prd->clk);
+
+	if (test_bit(BIT_ACTIVE, &prd->flags))
+		clk_put(prd->clk);
+}
+
+static struct pm_runtime_data *__to_prd(struct device *dev)
+{
+	return devres_find(dev, __devres_release, NULL, NULL);
+}
+
+static void platform_pm_runtime_init(struct device *dev,
+				     struct pm_runtime_data *prd)
+{
+	if (prd && !test_and_set_bit(BIT_ONCE, &prd->flags)) {
+		prd->clk = clk_get(dev, NULL);
+		if (!IS_ERR(prd->clk)) {
+			set_bit(BIT_ACTIVE, &prd->flags);
+			dev_info(dev, "clocks managed by runtime pm\n");
+		}
+	}
+}
+
+static void platform_pm_runtime_bug(struct device *dev,
+				    struct pm_runtime_data *prd)
+{
+	if (prd && !test_and_set_bit(BIT_ONCE, &prd->flags))
+		dev_err(dev, "runtime pm suspend before resume\n");
+}
+
+int platform_pm_runtime_suspend(struct device *dev)
+{
+	struct pm_runtime_data *prd = __to_prd(dev);
+
+	dev_dbg(dev, "platform_pm_runtime_suspend()\n");
+
+	platform_pm_runtime_bug(dev, prd);
+
+	if (prd && test_bit(BIT_ACTIVE, &prd->flags)) {
+		clk_disable(prd->clk);
+		clear_bit(BIT_CLK_ENABLED, &prd->flags);
+	}
+
+	return 0;
+}
+
+int platform_pm_runtime_resume(struct device *dev)
+{
+	struct pm_runtime_data *prd = __to_prd(dev);
+
+	dev_dbg(dev, "platform_pm_runtime_resume()\n");
+
+	platform_pm_runtime_init(dev, prd);
+
+	if (prd && test_bit(BIT_ACTIVE, &prd->flags)) {
+		clk_enable(prd->clk);
+		set_bit(BIT_CLK_ENABLED, &prd->flags);
+	}
+
+	return 0;
+}
+
+int platform_pm_runtime_idle(struct device *dev)
+{
+	/* suspend synchronously to disable clocks immediately */
+	return pm_runtime_suspend(dev);
+}
+
+static int platform_bus_notify(struct notifier_block *nb,
+			       unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct pm_runtime_data *prd;
+
+	dev_dbg(dev, "platform_bus_notify() %ld !\n", action);
+
+	if (action == BUS_NOTIFY_BIND_DRIVER) {
+		prd = devres_alloc(__devres_release, sizeof(*prd), GFP_KERNEL);
+		if (prd)
+			devres_add(dev, prd);
+		else
+			dev_err(dev, "unable to alloc memory for runtime pm\n");
+	}
+
+	return 0;
+}
+
+#else /* CONFIG_PM_RUNTIME */
+
+static int platform_bus_notify(struct notifier_block *nb,
+			       unsigned long action, void *data)
+{
+	struct device *dev = data;
+	struct clk *clk;
+
+	dev_dbg(dev, "platform_bus_notify() %ld !\n", action);
+
+	switch (action) {
+	case BUS_NOTIFY_BIND_DRIVER:
+		clk = clk_get(dev, NULL);
+		if (!IS_ERR(clk)) {
+			clk_enable(clk);
+			clk_put(clk);
+			dev_info(dev, "runtime pm disabled, clock forced on\n");
+		}
+		break;
+	case BUS_NOTIFY_UNBOUND_DRIVER:
+		clk = clk_get(dev, NULL);
+		if (!IS_ERR(clk)) {
+			clk_disable(clk);
+			clk_put(clk);
+			dev_info(dev, "runtime pm disabled, clock forced off\n");
+		}
+		break;
+	}
+
+	return 0;
+}
+
+#endif /* CONFIG_PM_RUNTIME */
+
+static struct notifier_block platform_bus_notifier = {
+	.notifier_call = platform_bus_notify
+};
+
+static int __init sh_pm_runtime_init(void)
+{
+	bus_register_notifier(&platform_bus_type, &platform_bus_notifier);
+	return 0;
+}
+core_initcall(sh_pm_runtime_init);
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@ -398,7 +398,7 @@ config CPU_V6
 # ARMv6k
 config CPU_32v6K
 	bool "Support ARM V6K processor extensions" if !SMP
-	depends on CPU_V6
+	depends on CPU_V6 || CPU_V7
 	default y if SMP && !(ARCH_MX3 || ARCH_OMAP2)
 	help
 	  Say Y here if your ARMv6 processor supports the 'K' extension.
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@ -229,6 +229,8 @@ __dma_alloc_remap(struct page *page, size_t size, gfp_t gfp, pgprot_t prot)
 			}
 		} while (size -= PAGE_SIZE);

+		dsb();
+
 		return (void *)c->vm_start;
 	}
 	return NULL;
--- a/arch/arm/plat-mxc/Kconfig
+++ b/arch/arm/plat-mxc/Kconfig
@ -43,6 +43,7 @@ config ARCH_MXC91231
 config ARCH_MX5
 	bool "MX5-based"
 	select CPU_V7
+	select ARM_L1_CACHE_SHIFT_6
 	help
 	  This enables support for systems based on the Freescale i.MX51 family

--- a/arch/arm/plat-mxc/include/mach/eukrea-baseboards.h
+++ b/arch/arm/plat-mxc/include/mach/eukrea-baseboards.h
@ -37,9 +37,9 @@
 * mach-mx5/eukrea_mbimx51-baseboard.c for cpuimx51
 */

-extern void eukrea_mbimx25_baseboard_init(void);
+extern void eukrea_mbimxsd25_baseboard_init(void);
 extern void eukrea_mbimx27_baseboard_init(void);
-extern void eukrea_mbimx35_baseboard_init(void);
+extern void eukrea_mbimxsd35_baseboard_init(void);
 extern void eukrea_mbimx51_baseboard_init(void);

 #endif
--- a/arch/arm/plat-mxc/tzic.c
+++ b/arch/arm/plat-mxc/tzic.c
@ -164,8 +164,9 @@ int tzic_enable_wake(int is_idle)
 		return -EAGAIN;

 	for (i = 0; i < 4; i++) {
-		v = is_idle ? __raw_readl(TZIC_ENSET0(i)) : wakeup_intr[i];
-		__raw_writel(v, TZIC_WAKEUP0(i));
+		v = is_idle ? __raw_readl(tzic_base + TZIC_ENSET0(i)) :
+			wakeup_intr[i];
+		__raw_writel(v, tzic_base + TZIC_WAKEUP0(i));
 	}

 	return 0;
--- a/arch/arm/plat-pxa/pwm.c
+++ b/arch/arm/plat-pxa/pwm.c
@ -176,7 +176,7 @@ static inline void __add_pwm(struct pwm_device *pwm)

 static int __devinit pwm_probe(struct platform_device *pdev)
 {
-	struct platform_device_id *id = platform_get_device_id(pdev);
+	const struct platform_device_id *id = platform_get_device_id(pdev);
 	struct pwm_device *pwm, *secondary = NULL;
 	struct resource *r;
 	int ret = 0;
--- a/arch/arm/tools/mach-types
+++ b/arch/arm/tools/mach-types
@ -12,7 +12,7 @@
 #
 #   http://www.arm.linux.org.uk/developer/machines/?action=new
 #
-# Last update: Mon Jul 12 21:10:14 2010
+# Last update: Thu Sep 9 22:43:01 2010
 #
 # machine_is_xxx	CONFIG_xxxx		MACH_TYPE_xxx		number
 #
@ -2622,7 +2622,7 @@ kraken			MACH_KRAKEN		KRAKEN			2634
 gw2388			MACH_GW2388		GW2388			2635
 jadecpu			MACH_JADECPU		JADECPU			2636
 carlisle		MACH_CARLISLE		CARLISLE		2637
-lux_sf9			MACH_LUX_SFT9		LUX_SFT9		2638
+lux_sf9			MACH_LUX_SF9		LUX_SF9			2638
 nemid_tb		MACH_NEMID_TB		NEMID_TB		2639
 terrier			MACH_TERRIER		TERRIER			2640
 turbot			MACH_TURBOT		TURBOT			2641
@ -2950,3 +2950,97 @@ davinci_dm365_dvr	MACH_DAVINCI_DM365_DVR	DAVINCI_DM365_DVR	2963
 netviz			MACH_NETVIZ		NETVIZ			2964
 flexibity		MACH_FLEXIBITY		FLEXIBITY		2965
 wlan_computer		MACH_WLAN_COMPUTER	WLAN_COMPUTER		2966
+lpc24xx			MACH_LPC24XX		LPC24XX			2967
+spica			MACH_SPICA		SPICA			2968
+gpsdisplay		MACH_GPSDISPLAY		GPSDISPLAY		2969
+bipnet			MACH_BIPNET		BIPNET			2970
+overo_ctu_inertial	MACH_OVERO_CTU_INERTIAL	OVERO_CTU_INERTIAL	2971
+davinci_dm355_mmm	MACH_DAVINCI_DM355_MMM	DAVINCI_DM355_MMM	2972
+pc9260_v2		MACH_PC9260_V2		PC9260_V2		2973
+ptx7545			MACH_PTX7545		PTX7545			2974
+tm_efdc			MACH_TM_EFDC		TM_EFDC			2975
+omap3_waldo1		MACH_OMAP3_WALDO1	OMAP3_WALDO1		2977
+flyer			MACH_FLYER		FLYER			2978
+tornado3240		MACH_TORNADO3240	TORNADO3240		2979
+soli_01			MACH_SOLI_01		SOLI_01			2980
+omapl138_europalc	MACH_OMAPL138_EUROPALC	OMAPL138_EUROPALC	2981
+helios_v1		MACH_HELIOS_V1		HELIOS_V1		2982
+netspace_lite_v2	MACH_NETSPACE_LITE_V2	NETSPACE_LITE_V2	2983
+ssc			MACH_SSC		SSC			2984
+premierwave_en		MACH_PREMIERWAVE_EN	PREMIERWAVE_EN		2985
+wasabi			MACH_WASABI		WASABI			2986
+vivow			MACH_VIVOW		VIVOW			2987
+mx50_rdp		MACH_MX50_RDP		MX50_RDP		2988
+universal		MACH_UNIVERSAL		UNIVERSAL		2989
+real6410		MACH_REAL6410		REAL6410		2990
+spx_sakura		MACH_SPX_SAKURA		SPX_SAKURA		2991
+ij3k_2440		MACH_IJ3K_2440		IJ3K_2440		2992
+omap3_bc10		MACH_OMAP3_BC10		OMAP3_BC10		2993
+thebe			MACH_THEBE		THEBE			2994
+rv082			MACH_RV082		RV082			2995
+armlguest		MACH_ARMLGUEST		ARMLGUEST		2996
+tjinc1000		MACH_TJINC1000		TJINC1000		2997
+dockstar		MACH_DOCKSTAR		DOCKSTAR		2998
+ax8008			MACH_AX8008		AX8008			2999
+gnet_sgce		MACH_GNET_SGCE		GNET_SGCE		3000
+pxwnas_500_1000		MACH_PXWNAS_500_1000	PXWNAS_500_1000		3001
+ea20			MACH_EA20		EA20			3002
+awm2			MACH_AWM2		AWM2			3003
+ti8148evm		MACH_TI8148EVM		TI8148EVM		3004
+tegra_seaboard		MACH_TEGRA_SEABOARD	TEGRA_SEABOARD		3005
+linkstation_chlv2	MACH_LINKSTATION_CHLV2	LINKSTATION_CHLV2	3006
+tera_pro2_rack		MACH_TERA_PRO2_RACK	TERA_PRO2_RACK		3007
+rubys			MACH_RUBYS		RUBYS			3008
+aquarius		MACH_AQUARIUS		AQUARIUS		3009
+mx53_ard		MACH_MX53_ARD		MX53_ARD		3010
+mx53_smd		MACH_MX53_SMD		MX53_SMD		3011
+lswxl			MACH_LSWXL		LSWXL			3012
+dove_avng_v3		MACH_DOVE_AVNG_V3	DOVE_AVNG_V3		3013
+sdi_ess_9263		MACH_SDI_ESS_9263	SDI_ESS_9263		3014
+jocpu550		MACH_JOCPU550		JOCPU550		3015
+msm8x60_rumi3		MACH_MSM8X60_RUMI3	MSM8X60_RUMI3		3016
+msm8x60_ffa		MACH_MSM8X60_FFA	MSM8X60_FFA		3017
+yanomami		MACH_YANOMAMI		YANOMAMI		3018
+gta04			MACH_GTA04		GTA04			3019
+cm_a510			MACH_CM_A510		CM_A510			3020
+omap3_rfs200		MACH_OMAP3_RFS200	OMAP3_RFS200		3021
+kx33xx			MACH_KX33XX		KX33XX			3022
+ptx7510			MACH_PTX7510		PTX7510			3023
+top9000			MACH_TOP9000		TOP9000			3024
+teenote			MACH_TEENOTE		TEENOTE			3025
+ts3			MACH_TS3		TS3			3026
+a0			MACH_A0			A0			3027
+fsm9xxx_surf		MACH_FSM9XXX_SURF	FSM9XXX_SURF		3028
+fsm9xxx_ffa		MACH_FSM9XXX_FFA	FSM9XXX_FFA		3029
+frrhwcdma60w		MACH_FRRHWCDMA60W	FRRHWCDMA60W		3030
+remus			MACH_REMUS		REMUS			3031
+at91cap7xdk		MACH_AT91CAP7XDK	AT91CAP7XDK		3032
+at91cap7stk		MACH_AT91CAP7STK	AT91CAP7STK		3033
+kt_sbc_sam9_1		MACH_KT_SBC_SAM9_1	KT_SBC_SAM9_1		3034
+oratisrouter		MACH_ORATISROUTER	ORATISROUTER		3035
+armada_xp_db		MACH_ARMADA_XP_DB	ARMADA_XP_DB		3036
+spdm			MACH_SPDM		SPDM			3037
+gtib			MACH_GTIB		GTIB			3038
+dgm3240			MACH_DGM3240		DGM3240			3039
+atlas_i_lpe		MACH_ATLAS_I_LPE	ATLAS_I_LPE		3040
+htcmega			MACH_HTCMEGA		HTCMEGA			3041
+tricorder		MACH_TRICORDER		TRICORDER		3042
+tx28			MACH_TX28		TX28			3043
+bstbrd			MACH_BSTBRD		BSTBRD			3044
+pwb3090			MACH_PWB3090		PWB3090			3045
+idea6410		MACH_IDEA6410		IDEA6410		3046
+qbc9263			MACH_QBC9263		QBC9263			3047
+borabora		MACH_BORABORA		BORABORA		3048
+valdez			MACH_VALDEZ		VALDEZ			3049
+ls9g20			MACH_LS9G20		LS9G20			3050
+mios_v1			MACH_MIOS_V1		MIOS_V1			3051
+s5pc110_crespo		MACH_S5PC110_CRESPO	S5PC110_CRESPO		3052
+controltek9g20		MACH_CONTROLTEK9G20	CONTROLTEK9G20		3053
+tin307			MACH_TIN307		TIN307			3054
+tin510			MACH_TIN510		TIN510			3055
+bluecheese		MACH_BLUECHEESE		BLUECHEESE		3057
+tem3x30			MACH_TEM3X30		TEM3X30			3058
+harvest_desoto		MACH_HARVEST_DESOTO	HARVEST_DESOTO		3059
+msm8x60_qrdc		MACH_MSM8X60_QRDC	MSM8X60_QRDC		3060
+spear900		MACH_SPEAR900		SPEAR900		3061
+pcontrol_g20		MACH_PCONTROL_G20	PCONTROL_G20		3062
--- a/arch/h8300/include/asm/atomic.h
+++ b/arch/h8300/include/asm/atomic.h
@ -18,7 +18,8 @@

 static __inline__ int atomic_add_return(int i, atomic_t *v)
 {
-	int ret,flags;
+	unsigned long flags;
+	int ret;
 	local_irq_save(flags);
 	ret = v->counter += i;
 	local_irq_restore(flags);
@ -30,7 +31,8 @@ static __inline__ int atomic_add_return(int i, atomic_t *v)

 static __inline__ int atomic_sub_return(int i, atomic_t *v)
 {
-	int ret,flags;
+	unsigned long flags;
+	int ret;
 	local_irq_save(flags);
 	ret = v->counter -= i;
 	local_irq_restore(flags);
@ -42,7 +44,8 @@ static __inline__ int atomic_sub_return(int i, atomic_t *v)

 static __inline__ int atomic_inc_return(atomic_t *v)
 {
-	int ret,flags;
+	unsigned long flags;
+	int ret;
 	local_irq_save(flags);
 	v->counter++;
 	ret = v->counter;
@ -64,7 +67,8 @@ static __inline__ int atomic_inc_return(atomic_t *v)

 static __inline__ int atomic_dec_return(atomic_t *v)
 {
-	int ret,flags;
+	unsigned long flags;
+	int ret;
 	local_irq_save(flags);
 	--v->counter;
 	ret = v->counter;
@ -76,7 +80,8 @@ static __inline__ int atomic_dec_return(atomic_t *v)

 static __inline__ int atomic_dec_and_test(atomic_t *v)
 {
-	int ret,flags;
+	unsigned long flags;
+	int ret;
 	local_irq_save(flags);
 	--v->counter;
 	ret = v->counter;
--- a/arch/h8300/include/asm/system.h
+++ b/arch/h8300/include/asm/system.h
@ -3,6 +3,8 @@

 #include <linux/linkage.h>

+struct pt_regs;
+
 /*
 * switch_to(n) should switch tasks to task ptr, first checking that
 * ptr isn't the current task, in which case it does nothing.  This
@ -155,6 +157,6 @@ static inline unsigned long __xchg(unsigned long x, volatile void * ptr, int siz

 #define arch_align_stack(x) (x)

-void die(char *str, struct pt_regs *fp, unsigned long err);
+extern void die(const char *str, struct pt_regs *fp, unsigned long err);

 #endif /* _H8300_SYSTEM_H */
--- a/arch/h8300/kernel/sys_h8300.c
+++ b/arch/h8300/kernel/sys_h8300.c
@ -56,8 +56,8 @@ int kernel_execve(const char *filename,
 		  const char *const envp[])
 {
 	register long res __asm__("er0");
-	register char *const *_c __asm__("er3") = envp;
-	register char *const *_b __asm__("er2") = argv;
+	register const char *const *_c __asm__("er3") = envp;
+	register const char *const *_b __asm__("er2") = argv;
 	register const char * _a __asm__("er1") = filename;
 	__asm__ __volatile__ ("mov.l %1,er0\n\t"
 			"trapa	#0\n\t"
--- a/arch/h8300/kernel/traps.c
+++ b/arch/h8300/kernel/traps.c
@ -96,7 +96,7 @@ static void dump(struct pt_regs *fp)
 	printk("\n\n");
 }

-void die(char *str, struct pt_regs *fp, unsigned long err)
+void die(const char *str, struct pt_regs *fp, unsigned long err)
 {
 	static int diecount;

--- a/arch/m68knommu/kernel/vmlinux.lds.S
+++ b/arch/m68knommu/kernel/vmlinux.lds.S
@ -150,6 +150,8 @@ SECTIONS {
 		_sdata = . ;
 		DATA_DATA
 		CACHELINE_ALIGNED_DATA(32)
+		PAGE_ALIGNED_DATA(PAGE_SIZE)
+		*(.data..shared_aligned)
 		INIT_TASK_DATA(THREAD_SIZE)
 		_edata = . ;
 	} > DATA
--- a/arch/powerpc/include/asm/fsldma.h
+++ b/arch/powerpc/include/asm/fsldma.h
@ -11,6 +11,7 @@
 #ifndef __ARCH_POWERPC_ASM_FSLDMA_H__
 #define __ARCH_POWERPC_ASM_FSLDMA_H__

+#include <linux/slab.h>
 #include <linux/dmaengine.h>

 /*
--- a/arch/powerpc/kernel/head_64.S
+++ b/arch/powerpc/kernel/head_64.S
@ -575,13 +575,19 @@ __secondary_start:
 	/* Initialize the kernel stack.  Just a repeat for iSeries.	 */
 	LOAD_REG_ADDR(r3, current_set)
 	sldi	r28,r24,3		/* get current_set[cpu#]	 */
-	ldx	r1,r3,r28
-	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD
-	std	r1,PACAKSAVE(r13)
+	ldx	r14,r3,r28
+	addi	r14,r14,THREAD_SIZE-STACK_FRAME_OVERHEAD
+	std	r14,PACAKSAVE(r13)

 	/* Do early setup for that CPU (stab, slb, hash table pointer) */
 	bl	.early_setup_secondary

+	/*
+	 * setup the new stack pointer, but *don't* use this until
+	 * translation is on.
+	 */
+	mr	r1, r14
+
 	/* Clear backchain so we get nice backtraces */
 	li	r7,0
 	mtlr	r7
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@ -810,6 +810,9 @@ relocate_new_kernel:
 	isync
 	sync

+	mfspr	r3, SPRN_PIR /* current core we are running on */
+	mr	r4, r5 /* load physical address of chunk called */
+
 	/* jump to the entry point, usually the setup routine */
 	mtlr	r5
 	blrl
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@ -577,20 +577,11 @@ void timer_interrupt(struct pt_regs * regs)
 	 * some CPUs will continuue to take decrementer exceptions */
 	set_dec(DECREMENTER_MAX);

-#ifdef CONFIG_PPC32
+#if defined(CONFIG_PPC32) && defined(CONFIG_PMAC)
 	if (atomic_read(&ppc_n_lost_interrupts) != 0)
 		do_IRQ(regs);
 #endif

-	now = get_tb_or_rtc();
-	if (now < decrementer->next_tb) {
-		/* not time for this event yet */
-		now = decrementer->next_tb - now;
-		if (now <= DECREMENTER_MAX)
-			set_dec((int)now);
-		trace_timer_interrupt_exit(regs);
-		return;
-	}
 	old_regs = set_irq_regs(regs);
 	irq_enter();

@ -606,8 +597,16 @@ void timer_interrupt(struct pt_regs * regs)
 		get_lppaca()->int_dword.fields.decr_int = 0;
 #endif

-	if (evt->event_handler)
-		evt->event_handler(evt);
+	now = get_tb_or_rtc();
+	if (now >= decrementer->next_tb) {
+		decrementer->next_tb = ~(u64)0;
+		if (evt->event_handler)
+			evt->event_handler(evt);
+	} else {
+		now = decrementer->next_tb - now;
+		if (now <= DECREMENTER_MAX)
+			set_dec((int)now);
+	}

 #ifdef CONFIG_PPC_ISERIES
 	if (firmware_has_feature(FW_FEATURE_ISERIES) && hvlpevent_is_pending())
--- a/arch/powerpc/platforms/83xx/mpc837x_mds.c
+++ b/arch/powerpc/platforms/83xx/mpc837x_mds.c
@ -48,8 +48,10 @@ static int mpc837xmds_usb_cfg(void)
 		return -1;

 	np = of_find_node_by_name(NULL, "usb");
-	if (!np)
-		return -ENODEV;
+	if (!np) {
+		ret = -ENODEV;
+		goto out;
+	}
 	phy_type = of_get_property(np, "phy_type", NULL);
 	if (phy_type && !strcmp(phy_type, "ulpi")) {
 		clrbits8(bcsr_regs + 12, BCSR12_USB_SER_PIN);
@ -65,8 +67,9 @@ static int mpc837xmds_usb_cfg(void)
 	}

 	of_node_put(np);
+out:
 	iounmap(bcsr_regs);
-	return 0;
+	return ret;
 }

 /* ************************************************************************
--- a/arch/powerpc/platforms/85xx/mpc85xx_mds.c
+++ b/arch/powerpc/platforms/85xx/mpc85xx_mds.c
@ -357,6 +357,7 @@ static void __init mpc85xx_mds_setup_arch(void)
 {
 #ifdef CONFIG_PCI
 	struct pci_controller *hose;
+	struct device_node *np;
 #endif
 	dma_addr_t max = 0xffffffff;

--- a/arch/powerpc/platforms/85xx/p1022_ds.c
+++ b/arch/powerpc/platforms/85xx/p1022_ds.c
@ -19,7 +19,7 @@

 #include <linux/pci.h>
 #include <linux/of_platform.h>
-#include <linux/lmb.h>
+#include <linux/memblock.h>

 #include <asm/mpic.h>
 #include <asm/swiotlb.h>
@ -97,7 +97,7 @@ static void __init p1022_ds_setup_arch(void)
 #endif

 #ifdef CONFIG_SWIOTLB
-	if (lmb_end_of_DRAM() > max) {
+	if (memblock_end_of_DRAM() > max) {
 		ppc_swiotlb_enable = 1;
 		set_pci_dma_ops(&swiotlb_dma_ops);
 		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@ -129,20 +129,35 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 	struct property *property;
 	struct property *last_property = NULL;
 	struct cc_workarea *ccwa;
+	char *data_buf;
 	int cc_token;
-	int rc;
+	int rc = -1;

 	cc_token = rtas_token("ibm,configure-connector");
 	if (cc_token == RTAS_UNKNOWN_SERVICE)
 		return NULL;

-	spin_lock(&rtas_data_buf_lock);
-	ccwa = (struct cc_workarea *)&rtas_data_buf[0];
+	data_buf = kzalloc(RTAS_DATA_BUF_SIZE, GFP_KERNEL);
+	if (!data_buf)
+		return NULL;
+
+	ccwa = (struct cc_workarea *)&data_buf[0];
 	ccwa->drc_index = drc_index;
 	ccwa->zero = 0;

-	rc = rtas_call(cc_token, 2, 1, NULL, rtas_data_buf, NULL);
-	while (rc) {
+	do {
+		/* Since we release the rtas_data_buf lock between configure
+		 * connector calls we want to re-populate the rtas_data_buffer
+		 * with the contents of the previous call.
+		 */
+		spin_lock(&rtas_data_buf_lock);
+
+		memcpy(rtas_data_buf, data_buf, RTAS_DATA_BUF_SIZE);
+		rc = rtas_call(cc_token, 2, 1, NULL, rtas_data_buf, NULL);
+		memcpy(data_buf, rtas_data_buf, RTAS_DATA_BUF_SIZE);
+
+		spin_unlock(&rtas_data_buf_lock);
+
 		switch (rc) {
 		case NEXT_SIBLING:
 			dn = dlpar_parse_cc_node(ccwa);
@ -197,18 +212,19 @@ struct device_node *dlpar_configure_connector(u32 drc_index)
 			       "returned from configure-connector\n", rc);
 			goto cc_error;
 		}
-
-		rc = rtas_call(cc_token, 2, 1, NULL, rtas_data_buf, NULL);
-	}
-
-	spin_unlock(&rtas_data_buf_lock);
-	return first_dn;
+	} while (rc);

 cc_error:
-	if (first_dn)
-		dlpar_free_cc_nodes(first_dn);
-	spin_unlock(&rtas_data_buf_lock);
-	return NULL;
+	kfree(data_buf);
+
+	if (rc) {
+		if (first_dn)
+			dlpar_free_cc_nodes(first_dn);
+
+		return NULL;
+	}
+
+	return first_dn;
 }

 static struct device_node *derive_parent(const char *path)
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@ -399,6 +399,8 @@ DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1013E, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1013, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1020E, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1020, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1021E, quirk_fsl_pcie_header);
+DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1021, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1022E, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P1022, quirk_fsl_pcie_header);
 DECLARE_PCI_FIXUP_HEADER(0x1957, PCI_DEVICE_ID_P2010E, quirk_fsl_pcie_header);
--- a/arch/powerpc/sysdev/fsl_rio.c
+++ b/arch/powerpc/sysdev/fsl_rio.c
@ -240,12 +240,13 @@ struct rio_priv {

 static void __iomem *rio_regs_win;

+#ifdef CONFIG_E500
 static int (*saved_mcheck_exception)(struct pt_regs *regs);

 static int fsl_rio_mcheck_exception(struct pt_regs *regs)
 {
 	const struct exception_table_entry *entry = NULL;
-	unsigned long reason = (mfspr(SPRN_MCSR) & MCSR_MASK);
+	unsigned long reason = mfspr(SPRN_MCSR);

 	if (reason & MCSR_BUS_RBERR) {
 		reason = in_be32((u32 *)(rio_regs_win + RIO_LTLEDCSR));
@ -269,6 +270,7 @@ static int fsl_rio_mcheck_exception(struct pt_regs *regs)
 	else
 		return cur_cpu_spec->machine_check(regs);
 }
+#endif

 /**
 * fsl_rio_doorbell_send - Send a MPC85xx doorbell message
@ -1517,8 +1519,10 @@ int fsl_rio_setup(struct platform_device *dev)
 	fsl_rio_doorbell_init(port);
 	fsl_rio_port_write_init(port);

+#ifdef CONFIG_E500
 	saved_mcheck_exception = ppc_md.machine_check_exception;
 	ppc_md.machine_check_exception = fsl_rio_mcheck_exception;
+#endif
 	/* Ensure that RFXE is set */
 	mtspr(SPRN_HID1, (mfspr(SPRN_HID1) | 0x20000));

--- a/arch/powerpc/sysdev/qe_lib/qe.c
+++ b/arch/powerpc/sysdev/qe_lib/qe.c
@ -640,6 +640,7 @@ unsigned int qe_get_num_of_snums(void)
 		if ((num_of_snums < 28) || (num_of_snums > QE_NUM_OF_SNUM)) {
 			/* No QE ever has fewer than 28 SNUMs */
 			pr_err("QE: number of snum is invalid\n");
+			of_node_put(qe);
 			return -EINVAL;
 		}
 	}
--- a/arch/sparc/kernel/sys_sparc_32.c
+++ b/arch/sparc/kernel/sys_sparc_32.c
@ -166,7 +166,6 @@ sparc_breakpoint (struct pt_regs *regs)
 {
 	siginfo_t info;

-	lock_kernel();
 #ifdef DEBUG_SPARC_BREAKPOINT
        printk ("TRAP: Entering kernel PC=%x, nPC=%x\n", regs->pc, regs->npc);
 #endif
@ -180,7 +179,6 @@ sparc_breakpoint (struct pt_regs *regs)
 #ifdef DEBUG_SPARC_BREAKPOINT
 	printk ("TRAP: Returning to space: PC=%x nPC=%x\n", regs->pc, regs->npc);
 #endif
-	unlock_kernel();
 }

 asmlinkage int
--- a/arch/sparc/kernel/unaligned_32.c
+++ b/arch/sparc/kernel/unaligned_32.c
@ -323,7 +323,6 @@ asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 {
 	enum direction dir;

-	lock_kernel();
 	if(!(current->thread.flags & SPARC_FLAG_UNALIGNED) ||
 	   (((insn >> 30) & 3) != 3))
 		goto kill_user;
@ -377,5 +376,5 @@ asmlinkage void user_unaligned_trap(struct pt_regs *regs, unsigned int insn)
 kill_user:
 	user_mna_trap_fault(regs, insn);
 out:
-	unlock_kernel();
+	;
 }
--- a/arch/sparc/kernel/windows.c
+++ b/arch/sparc/kernel/windows.c
@ -112,7 +112,6 @@ void try_to_clear_window_buffer(struct pt_regs *regs, int who)
 	struct thread_info *tp = current_thread_info();
 	int window;

-	lock_kernel();
 	flush_user_windows();
 	for(window = 0; window < tp->w_saved; window++) {
 		unsigned long sp = tp->rwbuf_stkptrs[window];
@ -123,5 +122,4 @@ void try_to_clear_window_buffer(struct pt_regs *regs, int who)
 			do_exit(SIGILL);
 	}
 	tp->w_saved = 0;
-	unlock_kernel();
 }
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@ -26,11 +26,11 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>

-void *
+void __iomem *
 iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);

 void
-iounmap_atomic(void *kvaddr, enum km_type type);
+iounmap_atomic(void __iomem *kvaddr, enum km_type type);

 int
 iomap_create_wc(resource_size_t base, unsigned long size, pgprot_t *prot);
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@ -152,9 +152,14 @@ struct x86_emulate_ops {
 struct operand {
 	enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type;
 	unsigned int bytes;
-	unsigned long orig_val, *ptr;
+	union {
+		unsigned long orig_val;
+		u64 orig_val64;
+	};
+	unsigned long *ptr;
 	union {
 		unsigned long val;
+		u64 val64;
 		char valptr[sizeof(unsigned long) + 2];
 	};
 };
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@ -27,6 +27,9 @@ extern struct pci_bus *pci_scan_bus_on_node(int busno, struct pci_ops *ops,
 					    int node);
 extern struct pci_bus *pci_scan_bus_with_sysdata(int busno);

+#ifdef CONFIG_PCI
+
+#ifdef CONFIG_PCI_DOMAINS
 static inline int pci_domain_nr(struct pci_bus *bus)
 {
 	struct pci_sysdata *sd = bus->sysdata;
@ -37,13 +40,12 @@ static inline int pci_proc_domain(struct pci_bus *bus)
 {
 	return pci_domain_nr(bus);
 }
-
+#endif

 /* Can be used to override the logic in pci_scan_bus for skipping
   already-configured bus numbers - to be used for buggy BIOSes
   or architectures with incomplete PCI setup by the loader */

-#ifdef CONFIG_PCI
 extern unsigned int pcibios_assign_all_busses(void);
 extern int pci_legacy_init(void);
 # ifdef CONFIG_ACPI
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@ -530,7 +530,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		err = -ENOMEM;
 		goto out;
 	}
-	if (!alloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
+	if (!zalloc_cpumask_var(&b->cpus, GFP_KERNEL)) {
 		kfree(b);
 		err = -ENOMEM;
 		goto out;
@ -543,7 +543,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
 	cpumask_setall(b->cpus);
 #else
-	cpumask_copy(b->cpus, c->llc_shared_map);
+	cpumask_set_cpu(cpu, b->cpus);
 #endif

 	per_cpu(threshold_banks, cpu)[bank] = b;
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@ -202,10 +202,11 @@ static int therm_throt_process(bool new_event, int event, int level)

 #ifdef CONFIG_SYSFS
 /* Add/Remove thermal_throttle interface for CPU device: */
-static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev)
+static __cpuinit int thermal_throttle_add_dev(struct sys_device *sys_dev,
+				unsigned int cpu)
 {
 	int err;
-	struct cpuinfo_x86 *c = &cpu_data(smp_processor_id());
+	struct cpuinfo_x86 *c = &cpu_data(cpu);

 	err = sysfs_create_group(&sys_dev->kobj, &thermal_attr_group);
 	if (err)
@ -251,7 +252,7 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb,
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
 		mutex_lock(&therm_cpu_lock);
-		err = thermal_throttle_add_dev(sys_dev);
+		err = thermal_throttle_add_dev(sys_dev, cpu);
 		mutex_unlock(&therm_cpu_lock);
 		WARN_ON(err);
 		break;
@ -287,7 +288,7 @@ static __init int thermal_throttle_init_device(void)
 #endif
 	/* connect live CPUs to sysfs */
 	for_each_online_cpu(cpu) {
-		err = thermal_throttle_add_dev(get_cpu_sysdev(cpu));
+		err = thermal_throttle_add_dev(get_cpu_sysdev(cpu), cpu);
 		WARN_ON(err);
 	}
 #ifdef CONFIG_HOTPLUG_CPU
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@ -1154,7 +1154,7 @@ static int x86_pmu_handle_irq(struct pt_regs *regs)
 		/*
 		 * event overflow
 		 */
-		handled		= 1;
+		handled++;
 		data.period	= event->hw.last_period;

 		if (!x86_perf_event_set_period(event))
@ -1200,12 +1200,20 @@ void perf_events_lapic_init(void)
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 }

+struct pmu_nmi_state {
+	unsigned int	marked;
+	int		handled;
+};
+
+static DEFINE_PER_CPU(struct pmu_nmi_state, pmu_nmi);
+
 static int __kprobes
 perf_event_nmi_handler(struct notifier_block *self,
 			 unsigned long cmd, void *__args)
 {
 	struct die_args *args = __args;
-	struct pt_regs *regs;
+	unsigned int this_nmi;
+	int handled;

 	if (!atomic_read(&active_events))
 		return NOTIFY_DONE;
@ -1214,22 +1222,47 @@ perf_event_nmi_handler(struct notifier_block *self,
 	case DIE_NMI:
 	case DIE_NMI_IPI:
 		break;
-
+	case DIE_NMIUNKNOWN:
+		this_nmi = percpu_read(irq_stat.__nmi_count);
+		if (this_nmi != __get_cpu_var(pmu_nmi).marked)
+			/* let the kernel handle the unknown nmi */
+			return NOTIFY_DONE;
+		/*
+		 * This one is a PMU back-to-back nmi. Two events
+		 * trigger 'simultaneously' raising two back-to-back
+		 * NMIs. If the first NMI handles both, the latter
+		 * will be empty and daze the CPU. So, we drop it to
+		 * avoid false-positive 'unknown nmi' messages.
+		 */
+		return NOTIFY_STOP;
 	default:
 		return NOTIFY_DONE;
 	}

-	regs = args->regs;
-
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
-	/*
-	 * Can't rely on the handled return value to say it was our NMI, two
-	 * events could trigger 'simultaneously' raising two back-to-back NMIs.
-	 *
-	 * If the first NMI handles both, the latter will be empty and daze
-	 * the CPU.
-	 */
-	x86_pmu.handle_irq(regs);
+
+	handled = x86_pmu.handle_irq(args->regs);
+	if (!handled)
+		return NOTIFY_DONE;
+
+	this_nmi = percpu_read(irq_stat.__nmi_count);
+	if ((handled > 1) ||
+		/* the next nmi could be a back-to-back nmi */
+	    ((__get_cpu_var(pmu_nmi).marked == this_nmi) &&
+	     (__get_cpu_var(pmu_nmi).handled > 1))) {
+		/*
+		 * We could have two subsequent back-to-back nmis: The
+		 * first handles more than one counter, the 2nd
+		 * handles only one counter and the 3rd handles no
+		 * counter.
+		 *
+		 * This is the 2nd nmi because the previous was
+		 * handling more than one counter. We will mark the
+		 * next (3rd) and then drop it if unhandled.
+		 */
+		__get_cpu_var(pmu_nmi).marked	= this_nmi + 1;
+		__get_cpu_var(pmu_nmi).handled	= handled;
+	}

 	return NOTIFY_STOP;
 }
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@ -712,7 +712,8 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)
 	struct perf_sample_data data;
 	struct cpu_hw_events *cpuc;
 	int bit, loops;
-	u64 ack, status;
+	u64 status;
+	int handled = 0;

 	perf_sample_data_init(&data, 0);

@ -728,6 +729,7 @@ static int intel_pmu_handle_irq(struct pt_regs *regs)

 	loops = 0;
 again:
+	intel_pmu_ack_status(status);
 	if (++loops > 100) {
 		WARN_ONCE(1, "perfevents: irq loop stuck!\n");
 		perf_event_print_debug();
@ -736,19 +738,22 @@ again:
 	}

 	inc_irq_stat(apic_perf_irqs);
-	ack = status;

 	intel_pmu_lbr_read();

 	/*
 	 * PEBS overflow sets bit 62 in the global status register
 	 */
-	if (__test_and_clear_bit(62, (unsigned long *)&status))
+	if (__test_and_clear_bit(62, (unsigned long *)&status)) {
+		handled++;
 		x86_pmu.drain_pebs(regs);
+	}

 	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
 		struct perf_event *event = cpuc->events[bit];

+		handled++;
+
 		if (!test_bit(bit, cpuc->active_mask))
 			continue;

@ -761,8 +766,6 @@ again:
 			x86_pmu_stop(event);
 	}

-	intel_pmu_ack_status(ack);
-
 	/*
 	 * Repeat if there is more work to be done:
 	 */
@ -772,7 +775,7 @@ again:

 done:
 	intel_pmu_enable_all(0);
-	return 1;
+	return handled;
 }

 static struct event_constraint *
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@ -692,7 +692,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
 		inc_irq_stat(apic_perf_irqs);
 	}

-	return handled > 0;
+	return handled;
 }

 /*
--- a/arch/x86/kernel/trampoline.c
+++ b/arch/x86/kernel/trampoline.c
@ -45,8 +45,7 @@ void __init setup_trampoline_page_table(void)
 	/* Copy kernel address range */
 	clone_pgd_range(trampoline_pg_dir + KERNEL_PGD_BOUNDARY,
 			swapper_pg_dir + KERNEL_PGD_BOUNDARY,
-			min_t(unsigned long, KERNEL_PGD_PTRS,
-			      KERNEL_PGD_BOUNDARY));
+			KERNEL_PGD_PTRS);

 	/* Initialize low mappings */
 	clone_pgd_range(trampoline_pg_dir,
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@ -655,7 +655,7 @@ void restore_sched_clock_state(void)

 	local_irq_save(flags);

-	get_cpu_var(cyc2ns_offset) = 0;
+	__get_cpu_var(cyc2ns_offset) = 0;
 	offset = cyc2ns_suspend - sched_clock();

 	for_each_possible_cpu(cpu)
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@ -1870,17 +1870,16 @@ static inline int emulate_grp9(struct x86_emulate_ctxt *ctxt,
 			       struct x86_emulate_ops *ops)
 {
 	struct decode_cache *c = &ctxt->decode;
-	u64 old = c->dst.orig_val;
+	u64 old = c->dst.orig_val64;

 	if (((u32) (old >> 0) != (u32) c->regs[VCPU_REGS_RAX]) ||
 	    ((u32) (old >> 32) != (u32) c->regs[VCPU_REGS_RDX])) {
-
 		c->regs[VCPU_REGS_RAX] = (u32) (old >> 0);
 		c->regs[VCPU_REGS_RDX] = (u32) (old >> 32);
 		ctxt->eflags &= ~EFLG_ZF;
 	} else {
-		c->dst.val = ((u64)c->regs[VCPU_REGS_RCX] << 32) |
-		       (u32) c->regs[VCPU_REGS_RBX];
+		c->dst.val64 = ((u64)c->regs[VCPU_REGS_RCX] << 32) |
+			(u32) c->regs[VCPU_REGS_RBX];

 		ctxt->eflags |= EFLG_ZF;
 	}
@ -2616,7 +2615,7 @@ x86_emulate_insn(struct x86_emulate_ctxt *ctxt, struct x86_emulate_ops *ops)
 					c->src.valptr, c->src.bytes);
 		if (rc != X86EMUL_CONTINUE)
 			goto done;
-		c->src.orig_val = c->src.val;
+		c->src.orig_val64 = c->src.val64;
 	}

 	if (c->src2.type == OP_MEM) {
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@ -64,6 +64,9 @@ static void pic_unlock(struct kvm_pic *s)
 		if (!found)
 			found = s->kvm->bsp_vcpu;

+		if (!found)
+			return;
+
 		kvm_vcpu_kick(found);
 	}
 }
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@ -43,7 +43,6 @@ struct kvm_kpic_state {
 	u8 irr;		/* interrupt request register */
 	u8 imr;		/* interrupt mask register */
 	u8 isr;		/* interrupt service register */
-	u8 isr_ack;	/* interrupt ack detection */
 	u8 priority_add;	/* highest irq priority */
 	u8 irq_base;
 	u8 read_reg_select;
@ -56,6 +55,7 @@ struct kvm_kpic_state {
 	u8 init4;		/* true if 4 byte init */
 	u8 elcr;		/* PIIX edge/trigger selection */
 	u8 elcr_mask;
+	u8 isr_ack;	/* interrupt ack detection */
 	struct kvm_pic *pics_state;
 };

--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@ -74,7 +74,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 /*
 * Map 'pfn' using fixed map 'type' and protections 'prot'
 */
-void *
+void __iomem *
 iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 {
 	/*
@ -86,12 +86,12 @@ iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 	if (!pat_enabled && pgprot_val(prot) == pgprot_val(PAGE_KERNEL_WC))
 		prot = PAGE_KERNEL_UC_MINUS;

-	return kmap_atomic_prot_pfn(pfn, type, prot);
+	return (void __force __iomem *) kmap_atomic_prot_pfn(pfn, type, prot);
 }
 EXPORT_SYMBOL_GPL(iomap_atomic_prot_pfn);

 void
-iounmap_atomic(void *kvaddr, enum km_type type)
+iounmap_atomic(void __iomem *kvaddr, enum km_type type)
 {
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
 	enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
--- a/arch/x86/oprofile/nmi_int.c
+++ b/arch/x86/oprofile/nmi_int.c
@ -568,8 +568,13 @@ static int __init init_sysfs(void)
 	int error;

 	error = sysdev_class_register(&oprofile_sysclass);
-	if (!error)
-		error = sysdev_register(&device_oprofile);
+	if (error)
+		return error;
+
+	error = sysdev_register(&device_oprofile);
+	if (error)
+		sysdev_class_unregister(&oprofile_sysclass);
+
 	return error;
 }

@ -580,8 +585,10 @@ static void exit_sysfs(void)
 }

 #else
-#define init_sysfs() do { } while (0)
-#define exit_sysfs() do { } while (0)
+
+static inline int  init_sysfs(void) { return 0; }
+static inline void exit_sysfs(void) { }
+
 #endif /* CONFIG_PM */

 static int __init p4_init(char **cpu_type)
@ -695,6 +702,8 @@ int __init op_nmi_init(struct oprofile_operations *ops)
 	char *cpu_type = NULL;
 	int ret = 0;

+	using_nmi = 0;
+
 	if (!cpu_has_apic)
 		return -ENODEV;

@ -774,7 +783,10 @@ int __init op_nmi_init(struct oprofile_operations *ops)

 	mux_init(ops);

-	init_sysfs();
+	ret = init_sysfs();
+	if (ret)
+		return ret;
+
 	using_nmi = 1;
 	printk(KERN_INFO "oprofile: using NMI interrupt.\n");
 	return 0;
--- a/block/blk-cgroup.c
+++ b/block/blk-cgroup.c
@ -966,7 +966,7 @@ blkiocg_create(struct cgroup_subsys *subsys, struct cgroup *cgroup)

 	/* Currently we do not support hierarchy deeper than two level (0,1) */
 	if (parent != cgroup->top_cgroup)
-		return ERR_PTR(-EINVAL);
+		return ERR_PTR(-EPERM);

 	blkcg = kzalloc(sizeof(*blkcg), GFP_KERNEL);
 	if (!blkcg)
--- a/block/blk-core.c
+++ b/block/blk-core.c
@ -1198,9 +1198,9 @@ static int __make_request(struct request_queue *q, struct bio *bio)
 	int el_ret;
 	unsigned int bytes = bio->bi_size;
 	const unsigned short prio = bio_prio(bio);
-	const bool sync = (bio->bi_rw & REQ_SYNC);
-	const bool unplug = (bio->bi_rw & REQ_UNPLUG);
-	const unsigned int ff = bio->bi_rw & REQ_FAILFAST_MASK;
+	const bool sync = !!(bio->bi_rw & REQ_SYNC);
+	const bool unplug = !!(bio->bi_rw & REQ_UNPLUG);
+	const unsigned long ff = bio->bi_rw & REQ_FAILFAST_MASK;
 	int rw_flags;

 	if ((bio->bi_rw & REQ_HARDBARRIER) &&
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@ -511,6 +511,7 @@ int blk_register_queue(struct gendisk *disk)
 		kobject_uevent(&q->kobj, KOBJ_REMOVE);
 		kobject_del(&q->kobj);
 		blk_trace_remove_sysfs(disk_to_dev(disk));
+		kobject_put(&dev->kobj);
 		return ret;
 	}

--- a/block/blk.h
+++ b/block/blk.h
@ -142,14 +142,18 @@ static inline int queue_congestion_off_threshold(struct request_queue *q)

 static inline int blk_cpu_to_group(int cpu)
 {
+	int group = NR_CPUS;
 #ifdef CONFIG_SCHED_MC
 	const struct cpumask *mask = cpu_coregroup_mask(cpu);
-	return cpumask_first(mask);
+	group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-	return cpumask_first(topology_thread_cpumask(cpu));
+	group = cpumask_first(topology_thread_cpumask(cpu));
 #else
 	return cpu;
 #endif
+	if (likely(group < NR_CPUS))
+		return group;
+	return cpu;
 }

 /*
--- a/block/cfq-iosched.c
+++ b/block/cfq-iosched.c
@ -30,6 +30,7 @@ static const int cfq_slice_sync = HZ / 10;
 static int cfq_slice_async = HZ / 25;
 static const int cfq_slice_async_rq = 2;
 static int cfq_slice_idle = HZ / 125;
+static int cfq_group_idle = HZ / 125;
 static const int cfq_target_latency = HZ * 3/10; /* 300 ms */
 static const int cfq_hist_divisor = 4;

@ -147,6 +148,8 @@ struct cfq_queue {
 	struct cfq_queue *new_cfqq;
 	struct cfq_group *cfqg;
 	struct cfq_group *orig_cfqg;
+	/* Number of sectors dispatched from queue in single dispatch round */
+	unsigned long nr_sectors;
 };

 /*
@ -198,6 +201,8 @@ struct cfq_group {
 	struct hlist_node cfqd_node;
 	atomic_t ref;
 #endif
+	/* number of requests that are on the dispatch list or inside driver */
+	int dispatched;
 };

 /*
@ -271,6 +276,7 @@ struct cfq_data {
 	unsigned int cfq_slice[2];
 	unsigned int cfq_slice_async_rq;
 	unsigned int cfq_slice_idle;
+	unsigned int cfq_group_idle;
 	unsigned int cfq_latency;
 	unsigned int cfq_group_isolation;

@ -378,6 +384,21 @@ CFQ_CFQQ_FNS(wait_busy);
 			&cfqg->service_trees[i][j]: NULL) \


+static inline bool iops_mode(struct cfq_data *cfqd)
+{
+	/*
+	 * If we are not idling on queues and it is a NCQ drive, parallel
+	 * execution of requests is on and measuring time is not possible
+	 * in most of the cases until and unless we drive shallower queue
+	 * depths and that becomes a performance bottleneck. In such cases
+	 * switch to start providing fairness in terms of number of IOs.
+	 */
+	if (!cfqd->cfq_slice_idle && cfqd->hw_tag)
+		return true;
+	else
+		return false;
+}
+
 static inline enum wl_prio_t cfqq_prio(struct cfq_queue *cfqq)
 {
 	if (cfq_class_idle(cfqq))
@ -906,7 +927,6 @@ static inline unsigned int cfq_cfqq_slice_usage(struct cfq_queue *cfqq)
 			slice_used = cfqq->allocated_slice;
 	}

-	cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u", slice_used);
 	return slice_used;
 }

@ -914,19 +934,21 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,
 				struct cfq_queue *cfqq)
 {
 	struct cfq_rb_root *st = &cfqd->grp_service_tree;
-	unsigned int used_sl, charge_sl;
+	unsigned int used_sl, charge;
 	int nr_sync = cfqg->nr_cfqq - cfqg_busy_async_queues(cfqd, cfqg)
 			- cfqg->service_tree_idle.count;

 	BUG_ON(nr_sync < 0);
-	used_sl = charge_sl = cfq_cfqq_slice_usage(cfqq);
+	used_sl = charge = cfq_cfqq_slice_usage(cfqq);

-	if (!cfq_cfqq_sync(cfqq) && !nr_sync)
-		charge_sl = cfqq->allocated_slice;
+	if (iops_mode(cfqd))
+		charge = cfqq->slice_dispatch;
+	else if (!cfq_cfqq_sync(cfqq) && !nr_sync)
+		charge = cfqq->allocated_slice;

 	/* Can't update vdisktime while group is on service tree */
 	cfq_rb_erase(&cfqg->rb_node, st);
-	cfqg->vdisktime += cfq_scale_slice(charge_sl, cfqg);
+	cfqg->vdisktime += cfq_scale_slice(charge, cfqg);
 	__cfq_group_service_tree_add(st, cfqg);

 	/* This group is being expired. Save the context */
@ -940,6 +962,9 @@ static void cfq_group_served(struct cfq_data *cfqd, struct cfq_group *cfqg,

 	cfq_log_cfqg(cfqd, cfqg, "served: vt=%llu min_vt=%llu", cfqg->vdisktime,
 					st->min_vdisktime);
+	cfq_log_cfqq(cfqq->cfqd, cfqq, "sl_used=%u disp=%u charge=%u iops=%u"
+			" sect=%u", used_sl, cfqq->slice_dispatch, charge,
+			iops_mode(cfqd), cfqq->nr_sectors);
 	cfq_blkiocg_update_timeslice_used(&cfqg->blkg, used_sl);
 	cfq_blkiocg_set_start_empty_time(&cfqg->blkg);
 }
@ -1587,6 +1612,7 @@ static void __cfq_set_active_queue(struct cfq_data *cfqd,
 		cfqq->allocated_slice = 0;
 		cfqq->slice_end = 0;
 		cfqq->slice_dispatch = 0;
+		cfqq->nr_sectors = 0;

 		cfq_clear_cfqq_wait_request(cfqq);
 		cfq_clear_cfqq_must_dispatch(cfqq);
@ -1839,6 +1865,9 @@ static bool cfq_should_idle(struct cfq_data *cfqd, struct cfq_queue *cfqq)
 	BUG_ON(!service_tree);
 	BUG_ON(!service_tree->count);

+	if (!cfqd->cfq_slice_idle)
+		return false;
+
 	/* We never do for idle class queues. */
 	if (prio == IDLE_WORKLOAD)
 		return false;
@ -1863,7 +1892,7 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 {
 	struct cfq_queue *cfqq = cfqd->active_queue;
 	struct cfq_io_context *cic;
-	unsigned long sl;
+	unsigned long sl, group_idle = 0;

 	/*
 	 * SSD device without seek penalty, disable idling. But only do so
@ -1879,8 +1908,13 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 	/*
 	 * idle is disabled, either manually or by past process history
 	 */
-	if (!cfqd->cfq_slice_idle || !cfq_should_idle(cfqd, cfqq))
-		return;
+	if (!cfq_should_idle(cfqd, cfqq)) {
+		/* no queue idling. Check for group idling */
+		if (cfqd->cfq_group_idle)
+			group_idle = cfqd->cfq_group_idle;
+		else
+			return;
+	}

 	/*
 	 * still active requests from this queue, don't idle
@ -1907,13 +1941,21 @@ static void cfq_arm_slice_timer(struct cfq_data *cfqd)
 		return;
 	}

+	/* There are other queues in the group, don't do group idle */
+	if (group_idle && cfqq->cfqg->nr_cfqq > 1)
+		return;
+
 	cfq_mark_cfqq_wait_request(cfqq);

-	sl = cfqd->cfq_slice_idle;
+	if (group_idle)
+		sl = cfqd->cfq_group_idle;
+	else
+		sl = cfqd->cfq_slice_idle;

 	mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
 	cfq_blkiocg_update_set_idle_time_stats(&cfqq->cfqg->blkg);
-	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu", sl);
+	cfq_log_cfqq(cfqd, cfqq, "arm_idle: %lu group_idle: %d", sl,
+			group_idle ? 1 : 0);
 }

 /*
@ -1929,9 +1971,11 @@ static void cfq_dispatch_insert(struct request_queue *q, struct request *rq)
 	cfqq->next_rq = cfq_find_next_rq(cfqd, cfqq, rq);
 	cfq_remove_request(rq);
 	cfqq->dispatched++;
+	(RQ_CFQG(rq))->dispatched++;
 	elv_dispatch_sort(q, rq);

 	cfqd->rq_in_flight[cfq_cfqq_sync(cfqq)]++;
+	cfqq->nr_sectors += blk_rq_sectors(rq);
 	cfq_blkiocg_update_dispatch_stats(&cfqq->cfqg->blkg, blk_rq_bytes(rq),
 					rq_data_dir(rq), rq_is_sync(rq));
 }
@ -2198,7 +2242,7 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 			cfqq = NULL;
 			goto keep_queue;
 		} else
-			goto expire;
+			goto check_group_idle;
 	}

 	/*
@ -2226,8 +2270,23 @@ static struct cfq_queue *cfq_select_queue(struct cfq_data *cfqd)
 	 * flight or is idling for a new request, allow either of these
 	 * conditions to happen (or time out) before selecting a new queue.
 	 */
-	if (timer_pending(&cfqd->idle_slice_timer) ||
-	    (cfqq->dispatched && cfq_should_idle(cfqd, cfqq))) {
+	if (timer_pending(&cfqd->idle_slice_timer)) {
+		cfqq = NULL;
+		goto keep_queue;
+	}
+
+	if (cfqq->dispatched && cfq_should_idle(cfqd, cfqq)) {
+		cfqq = NULL;
+		goto keep_queue;
+	}
+
+	/*
+	 * If group idle is enabled and there are requests dispatched from
+	 * this group, wait for requests to complete.
+	 */
+check_group_idle:
+	if (cfqd->cfq_group_idle && cfqq->cfqg->nr_cfqq == 1
+	    && cfqq->cfqg->dispatched) {
 		cfqq = NULL;
 		goto keep_queue;
 	}
@ -3375,6 +3434,7 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 	WARN_ON(!cfqq->dispatched);
 	cfqd->rq_in_driver--;
 	cfqq->dispatched--;
+	(RQ_CFQG(rq))->dispatched--;
 	cfq_blkiocg_update_completion_stats(&cfqq->cfqg->blkg,
 			rq_start_time_ns(rq), rq_io_start_time_ns(rq),
 			rq_data_dir(rq), rq_is_sync(rq));
@ -3404,7 +3464,10 @@ static void cfq_completed_request(struct request_queue *q, struct request *rq)
 		 * the queue.
 		 */
 		if (cfq_should_wait_busy(cfqd, cfqq)) {
-			cfqq->slice_end = jiffies + cfqd->cfq_slice_idle;
+			unsigned long extend_sl = cfqd->cfq_slice_idle;
+			if (!cfqd->cfq_slice_idle)
+				extend_sl = cfqd->cfq_group_idle;
+			cfqq->slice_end = jiffies + extend_sl;
 			cfq_mark_cfqq_wait_busy(cfqq);
 			cfq_log_cfqq(cfqd, cfqq, "will busy wait");
 		}
@ -3850,6 +3913,7 @@ static void *cfq_init_queue(struct request_queue *q)
 	cfqd->cfq_slice[1] = cfq_slice_sync;
 	cfqd->cfq_slice_async_rq = cfq_slice_async_rq;
 	cfqd->cfq_slice_idle = cfq_slice_idle;
+	cfqd->cfq_group_idle = cfq_group_idle;
 	cfqd->cfq_latency = 1;
 	cfqd->cfq_group_isolation = 0;
 	cfqd->hw_tag = -1;
@ -3922,6 +3986,7 @@ SHOW_FUNCTION(cfq_fifo_expire_async_show, cfqd->cfq_fifo_expire[0], 1);
 SHOW_FUNCTION(cfq_back_seek_max_show, cfqd->cfq_back_max, 0);
 SHOW_FUNCTION(cfq_back_seek_penalty_show, cfqd->cfq_back_penalty, 0);
 SHOW_FUNCTION(cfq_slice_idle_show, cfqd->cfq_slice_idle, 1);
+SHOW_FUNCTION(cfq_group_idle_show, cfqd->cfq_group_idle, 1);
 SHOW_FUNCTION(cfq_slice_sync_show, cfqd->cfq_slice[1], 1);
 SHOW_FUNCTION(cfq_slice_async_show, cfqd->cfq_slice[0], 1);
 SHOW_FUNCTION(cfq_slice_async_rq_show, cfqd->cfq_slice_async_rq, 0);
@ -3954,6 +4019,7 @@ STORE_FUNCTION(cfq_back_seek_max_store, &cfqd->cfq_back_max, 0, UINT_MAX, 0);
 STORE_FUNCTION(cfq_back_seek_penalty_store, &cfqd->cfq_back_penalty, 1,
 		UINT_MAX, 0);
 STORE_FUNCTION(cfq_slice_idle_store, &cfqd->cfq_slice_idle, 0, UINT_MAX, 1);
+STORE_FUNCTION(cfq_group_idle_store, &cfqd->cfq_group_idle, 0, UINT_MAX, 1);
 STORE_FUNCTION(cfq_slice_sync_store, &cfqd->cfq_slice[1], 1, UINT_MAX, 1);
 STORE_FUNCTION(cfq_slice_async_store, &cfqd->cfq_slice[0], 1, UINT_MAX, 1);
 STORE_FUNCTION(cfq_slice_async_rq_store, &cfqd->cfq_slice_async_rq, 1,
@ -3975,6 +4041,7 @@ static struct elv_fs_entry cfq_attrs[] = {
 	CFQ_ATTR(slice_async),
 	CFQ_ATTR(slice_async_rq),
 	CFQ_ATTR(slice_idle),
+	CFQ_ATTR(group_idle),
 	CFQ_ATTR(low_latency),
 	CFQ_ATTR(group_isolation),
 	__ATTR_NULL
@ -4028,6 +4095,12 @@ static int __init cfq_init(void)
 	if (!cfq_slice_idle)
 		cfq_slice_idle = 1;

+#ifdef CONFIG_CFQ_GROUP_IOSCHED
+	if (!cfq_group_idle)
+		cfq_group_idle = 1;
+#else
+		cfq_group_idle = 0;
+#endif
 	if (cfq_slab_setup())
 		return -ENOMEM;

--- a/block/elevator.c
+++ b/block/elevator.c
@ -1009,18 +1009,19 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)
 {
 	struct elevator_queue *old_elevator, *e;
 	void *data;
+	int err;

 	/*
 	 * Allocate new elevator
 	 */
 	e = elevator_alloc(q, new_e);
 	if (!e)
-		return 0;
+		return -ENOMEM;

 	data = elevator_init_queue(q, e);
 	if (!data) {
 		kobject_put(&e->kobj);
-		return 0;
+		return -ENOMEM;
 	}

 	/*
@ -1043,7 +1044,8 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)

 	__elv_unregister_queue(old_elevator);

-	if (elv_register_queue(q))
+	err = elv_register_queue(q);
+	if (err)
 		goto fail_register;

 	/*
@ -1056,7 +1058,7 @@ static int elevator_switch(struct request_queue *q, struct elevator_type *new_e)

 	blk_add_trace_msg(q, "elv switch: %s", e->elevator_type->elevator_name);

-	return 1;
+	return 0;

 fail_register:
 	/*
@ -1071,17 +1073,19 @@ fail_register:
 	queue_flag_clear(QUEUE_FLAG_ELVSWITCH, q);
 	spin_unlock_irq(q->queue_lock);

-	return 0;
+	return err;
 }

-ssize_t elv_iosched_store(struct request_queue *q, const char *name,
-			  size_t count)
+/*
+ * Switch this queue to the given IO scheduler.
+ */
+int elevator_change(struct request_queue *q, const char *name)
 {
 	char elevator_name[ELV_NAME_MAX];
 	struct elevator_type *e;

 	if (!q->elevator)
-		return count;
+		return -ENXIO;

 	strlcpy(elevator_name, name, sizeof(elevator_name));
 	e = elevator_get(strstrip(elevator_name));
@ -1092,13 +1096,27 @@ ssize_t elv_iosched_store(struct request_queue *q, const char *name,

 	if (!strcmp(elevator_name, q->elevator->elevator_type->elevator_name)) {
 		elevator_put(e);
-		return count;
+		return 0;
 	}

-	if (!elevator_switch(q, e))
-		printk(KERN_ERR "elevator: switch to %s failed\n",
-							elevator_name);
-	return count;
+	return elevator_switch(q, e);
+}
+EXPORT_SYMBOL(elevator_change);
+
+ssize_t elv_iosched_store(struct request_queue *q, const char *name,
+			  size_t count)
+{
+	int ret;
+
+	if (!q->elevator)
+		return count;
+
+	ret = elevator_change(q, name);
+	if (!ret)
+		return count;
+
+	printk(KERN_ERR "elevator: switch to %s failed\n", name);
+	return ret;
 }

 ssize_t elv_iosched_show(struct request_queue *q, char *name)
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@ -101,13 +101,13 @@ config CRYPTO_MANAGER2
 	select CRYPTO_BLKCIPHER2
 	select CRYPTO_PCOMP2

-config CRYPTO_MANAGER_TESTS
-	bool "Run algolithms' self-tests"
+config CRYPTO_MANAGER_DISABLE_TESTS
+	bool "Disable run-time self tests"
 	default y
 	depends on CRYPTO_MANAGER2
 	help
-	  Run cryptomanager's tests for the new crypto algorithms being
-	  registered.
+	  Disable run-time self tests that normally take place at
+	  algorithm registration.

 config CRYPTO_GF128MUL
 	tristate "GF(2^128) multiplication functions (EXPERIMENTAL)"
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@ -47,8 +47,11 @@ static int hash_walk_next(struct crypto_hash_walk *walk)
 	walk->data = crypto_kmap(walk->pg, 0);
 	walk->data += offset;

-	if (offset & alignmask)
-		nbytes = alignmask + 1 - (offset & alignmask);
+	if (offset & alignmask) {
+		unsigned int unaligned = alignmask + 1 - (offset & alignmask);
+		if (nbytes > unaligned)
+			nbytes = unaligned;
+	}

 	walk->entrylen -= nbytes;
 	return nbytes;
--- a/crypto/algboss.c
+++ b/crypto/algboss.c
@ -206,13 +206,16 @@ err:
 	return NOTIFY_OK;
 }

-#ifdef CONFIG_CRYPTO_MANAGER_TESTS
 static int cryptomgr_test(void *data)
 {
 	struct crypto_test_param *param = data;
 	u32 type = param->type;
 	int err = 0;

+#ifdef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS
+	goto skiptest;
+#endif
+
 	if (type & CRYPTO_ALG_TESTED)
 		goto skiptest;

@ -267,7 +270,6 @@ err_put_module:
 err:
 	return NOTIFY_OK;
 }
-#endif /* CONFIG_CRYPTO_MANAGER_TESTS */

 static int cryptomgr_notify(struct notifier_block *this, unsigned long msg,
 			    void *data)
@ -275,10 +277,8 @@ static int cryptomgr_notify(struct notifier_block *this, unsigned long msg,
 	switch (msg) {
 	case CRYPTO_MSG_ALG_REQUEST:
 		return cryptomgr_schedule_probe(data);
-#ifdef CONFIG_CRYPTO_MANAGER_TESTS
 	case CRYPTO_MSG_ALG_REGISTER:
 		return cryptomgr_schedule_test(data);
-#endif
 	}

 	return NOTIFY_DONE;
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@ -23,7 +23,7 @@

 #include "internal.h"

-#ifndef CONFIG_CRYPTO_MANAGER_TESTS
+#ifdef CONFIG_CRYPTO_MANAGER_DISABLE_TESTS

 /* a perfect nop */
 int alg_test(const char *driver, const char *alg, u32 type, u32 mask)
@ -2542,6 +2542,6 @@ non_fips_alg:
 	return -EINVAL;
 }

-#endif /* CONFIG_CRYPTO_MANAGER_TESTS */
+#endif /* CONFIG_CRYPTO_MANAGER_DISABLE_TESTS */

 EXPORT_SYMBOL_GPL(alg_test);
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@ -33,7 +33,6 @@
 #include <linux/pm_runtime.h>
 #include <linux/pci.h>
 #include <linux/pci-acpi.h>
-#include <linux/pci-aspm.h>
 #include <linux/acpi.h>
 #include <linux/slab.h>
 #include <acpi/acpi_bus.h>
@ -226,22 +225,31 @@ static acpi_status acpi_pci_run_osc(acpi_handle handle,
 	return status;
 }

-static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root, u32 flags)
+static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root,
+					u32 support,
+					u32 *control)
 {
 	acpi_status status;
-	u32 support_set, result, capbuf[3];
+	u32 result, capbuf[3];
+
+	support &= OSC_PCI_SUPPORT_MASKS;
+	support |= root->osc_support_set;

-	/* do _OSC query for all possible controls */
-	support_set = root->osc_support_set | (flags & OSC_PCI_SUPPORT_MASKS);
 	capbuf[OSC_QUERY_TYPE] = OSC_QUERY_ENABLE;
-	capbuf[OSC_SUPPORT_TYPE] = support_set;
-	capbuf[OSC_CONTROL_TYPE] = OSC_PCI_CONTROL_MASKS;
+	capbuf[OSC_SUPPORT_TYPE] = support;
+	if (control) {
+		*control &= OSC_PCI_CONTROL_MASKS;
+		capbuf[OSC_CONTROL_TYPE] = *control | root->osc_control_set;
+	} else {
+		/* Run _OSC query for all possible controls. */
+		capbuf[OSC_CONTROL_TYPE] = OSC_PCI_CONTROL_MASKS;
+	}

 	status = acpi_pci_run_osc(root->device->handle, capbuf, &result);
 	if (ACPI_SUCCESS(status)) {
-		root->osc_support_set = support_set;
-		root->osc_control_qry = result;
-		root->osc_queried = 1;
+		root->osc_support_set = support;
+		if (control)
+			*control = result;
 	}
 	return status;
 }
@ -255,7 +263,7 @@ static acpi_status acpi_pci_osc_support(struct acpi_pci_root *root, u32 flags)
 	if (ACPI_FAILURE(status))
 		return status;
 	mutex_lock(&osc_lock);
-	status = acpi_pci_query_osc(root, flags);
+	status = acpi_pci_query_osc(root, flags, NULL);
 	mutex_unlock(&osc_lock);
 	return status;
 }
@ -365,55 +373,70 @@ out:
 EXPORT_SYMBOL_GPL(acpi_get_pci_dev);

 /**
- * acpi_pci_osc_control_set - commit requested control to Firmware
- * @handle: acpi_handle for the target ACPI object
- * @flags: driver's requested control bits
+ * acpi_pci_osc_control_set - Request control of PCI root _OSC features.
+ * @handle: ACPI handle of a PCI root bridge (or PCIe Root Complex).
+ * @mask: Mask of _OSC bits to request control of, place to store control mask.
+ * @req: Mask of _OSC bits the control of is essential to the caller.
 *
- * Attempt to take control from Firmware on requested control bits.
+ * Run _OSC query for @mask and if that is successful, compare the returned
+ * mask of control bits with @req.  If all of the @req bits are set in the
+ * returned mask, run _OSC request for it.
+ *
+ * The variable at the @mask address may be modified regardless of whether or
+ * not the function returns success.  On success it will contain the mask of
+ * _OSC bits the BIOS has granted control of, but its contents are meaningless
+ * on failure.
 **/
-acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 flags)
+acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 req)
 {
-	acpi_status status;
-	u32 control_req, result, capbuf[3];
-	acpi_handle tmp;
 	struct acpi_pci_root *root;
+	acpi_status status;
+	u32 ctrl, capbuf[3];
+	acpi_handle tmp;

-	status = acpi_get_handle(handle, "_OSC", &tmp);
-	if (ACPI_FAILURE(status))
-		return status;
+	if (!mask)
+		return AE_BAD_PARAMETER;

-	control_req = (flags & OSC_PCI_CONTROL_MASKS);
-	if (!control_req)
+	ctrl = *mask & OSC_PCI_CONTROL_MASKS;
+	if ((ctrl & req) != req)
 		return AE_TYPE;

 	root = acpi_pci_find_root(handle);
 	if (!root)
 		return AE_NOT_EXIST;

+	status = acpi_get_handle(handle, "_OSC", &tmp);
+	if (ACPI_FAILURE(status))
+		return status;
+
 	mutex_lock(&osc_lock);
+
+	*mask = ctrl | root->osc_control_set;
 	/* No need to evaluate _OSC if the control was already granted. */
-	if ((root->osc_control_set & control_req) == control_req)
+	if ((root->osc_control_set & ctrl) == ctrl)
 		goto out;

-	/* Need to query controls first before requesting them */
-	if (!root->osc_queried) {
-		status = acpi_pci_query_osc(root, root->osc_support_set);
+	/* Need to check the available controls bits before requesting them. */
+	while (*mask) {
+		status = acpi_pci_query_osc(root, root->osc_support_set, mask);
 		if (ACPI_FAILURE(status))
 			goto out;
+		if (ctrl == *mask)
+			break;
+		ctrl = *mask;
 	}
-	if ((root->osc_control_qry & control_req) != control_req) {
-		printk(KERN_DEBUG
-		       "Firmware did not grant requested _OSC control\n");
+
+	if ((ctrl & req) != req) {
 		status = AE_SUPPORT;
 		goto out;
 	}

 	capbuf[OSC_QUERY_TYPE] = 0;
 	capbuf[OSC_SUPPORT_TYPE] = root->osc_support_set;
-	capbuf[OSC_CONTROL_TYPE] = root->osc_control_set | control_req;
-	status = acpi_pci_run_osc(handle, capbuf, &result);
+	capbuf[OSC_CONTROL_TYPE] = ctrl;
+	status = acpi_pci_run_osc(handle, capbuf, mask);
 	if (ACPI_SUCCESS(status))
-		root->osc_control_set = result;
+		root->osc_control_set = *mask;
 out:
 	mutex_unlock(&osc_lock);
 	return status;
@ -544,14 +567,6 @@ static int __devinit acpi_pci_root_add(struct acpi_device *device)
 	if (flags != base_flags)
 		acpi_pci_osc_support(root, flags);

-	status = acpi_pci_osc_control_set(root->device->handle,
-					  OSC_PCI_EXPRESS_CAP_STRUCTURE_CONTROL);
-
-	if (ACPI_FAILURE(status)) {
-		printk(KERN_INFO "Unable to assume PCIe control: Disabling ASPM\n");
-		pcie_no_aspm();
-	}
-
 	pci_acpi_add_bus_pm_notifier(device, root->bus);
 	if (device->wakeup.flags.run_wake)
 		device_set_run_wake(root->bus->bridge, true);
--- a/Show More
+++ b/Show More