Linux 2.6.26

# cat devices.list
 c 1:3 r
 # echo 'c 1:3 w' > sub/devices.allow
 # cat sub/devices.list
 c 1:3 w

As illustrated, the parent group has no write permission to /dev/null, so
it's child should not be allowed to add this write permission.

Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Acked-by: Serge Hallyn <serue@us.ibm.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Cc: Paul Menage <menage@google.com>
Cc: Pavel Emelyanov <xemul@openvz.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

.gitignore

@@ -3,6 +3,10 @@
 # subdirectories here. Add them in the ".gitignore" file
 # in that subdirectory instead.
 #
+# NOTE! Please use 'git-ls-files -i --exclude-standard'
+# command after changing this file, to see if there are
+# any tracked files which get ignored after the change.
+#
 # Normal rules
 #
 .*
@@ -18,19 +22,21 @@
 *.lst
 *.symtypes
 *.order
+*.elf
+*.bin
+*.gz
 
 #
 # Top-level generic files
 #
 tags
 TAGS
-vmlinux*
-!vmlinux.lds.S
-!vmlinux.lds.h
+vmlinux
 System.map
 Module.markers
 Module.symvers
 !.gitignore
+!.mailmap
 
 #
 # Generated include files

CREDITS

@@ -2611,8 +2611,9 @@ S: Perth, Western Australia
 S: Australia
 
 N: Miguel Ojeda Sandonis
-E: maxextreme@gmail.com
-W: http://maxextreme.googlepages.com/
+E: miguel.ojeda.sandonis@gmail.com
+W: http://miguelojeda.es
+W: http://jair.lab.fi.uva.es/~migojed/
 D: Author of the ks0108, cfag12864b and cfag12864bfb auxiliary display drivers.
 D: Maintainer of the auxiliary display drivers tree (drivers/auxdisplay/*)
 S: C/ Mieses 20, 9-B

Documentation/DocBook/kgdb.tmpl

@@ -84,10 +84,9 @@
     runs an instance of gdb against the vmlinux file which contains
     the symbols (not boot image such as bzImage, zImage, uImage...).
     In gdb the developer specifies the connection parameters and
-    connects to kgdb.  Depending on which kgdb I/O modules exist in
-    the kernel for a given architecture, it may be possible to debug
-    the test machine's kernel with the development machine using a
-    rs232 or ethernet connection.
+    connects to kgdb.  The type of connection a developer makes with
+    gdb depends on the availability of kgdb I/O modules compiled as
+    builtin's or kernel modules in the test machine's kernel.
     </para>
   </chapter>
   <chapter id="CompilingAKernel">
@@ -223,7 +222,7 @@
   </para>
   <para>
   IMPORTANT NOTE: Using this option with kgdb over the console
-  (kgdboc) or kgdb over ethernet (kgdboe) is not supported.
+  (kgdboc) is not supported.
   </para>
   </sect1>
   </chapter>
@@ -249,18 +248,11 @@
     (gdb) target remote /dev/ttyS0
     </programlisting>
     <para>
-    Example (kgdb to a terminal server):
+    Example (kgdb to a terminal server on tcp port 2012):
     </para>
     <programlisting>
     % gdb ./vmlinux
-    (gdb) target remote udp:192.168.2.2:6443
-    </programlisting>
-    <para>
-    Example (kgdb over ethernet):
-    </para>
-    <programlisting>
-    % gdb ./vmlinux
-    (gdb) target remote udp:192.168.2.2:6443
+    (gdb) target remote 192.168.2.2:2012
     </programlisting>
     <para>
     Once connected, you can debug a kernel the way you would debug an

Documentation/HOWTO

@@ -377,7 +377,7 @@ Bug Reporting
 bugzilla.kernel.org is where the Linux kernel developers track kernel
 bugs.  Users are encouraged to report all bugs that they find in this
 tool.  For details on how to use the kernel bugzilla, please see:
-	http://test.kernel.org/bugzilla/faq.html
+	http://bugzilla.kernel.org/page.cgi?id=faq.html
 
 The file REPORTING-BUGS in the main kernel source directory has a good
 template for how to report a possible kernel bug, and details what kind

Documentation/accounting/taskstats-struct.txt

@@ -24,6 +24,8 @@ There are three different groups of fields in the struct taskstats:
 
 4) Per-task and per-thread context switch count statistics
 
+5) Time accounting for SMT machines
+
 Future extension should add fields to the end of the taskstats struct, and
 should not change the relative position of each field within the struct.
 
@@ -164,4 +166,8 @@ struct taskstats {
 	__u64	nvcsw;			/* Context voluntary switch counter */
 	__u64	nivcsw;			/* Context involuntary switch counter */
 
+5) Time accounting for SMT machines
+	__u64	ac_utimescaled;		/* utime scaled on frequency etc */
+	__u64	ac_stimescaled;		/* stime scaled on frequency etc */
+	__u64	cpu_scaled_run_real_total; /* scaled cpu_run_real_total */
 }

Documentation/auxdisplay/cfag12864b

@@ -3,7 +3,7 @@
 	===================================
 
 License:		GPLv2
-Author & Maintainer:	Miguel Ojeda Sandonis <maxextreme@gmail.com>
+Author & Maintainer:	Miguel Ojeda Sandonis
 Date:			2006-10-27
 
 
@@ -22,7 +22,7 @@ Date:			2006-10-27
 1. DRIVER INFORMATION
 ---------------------
 
-This driver support one cfag12864b display at time.
+This driver supports a cfag12864b LCD.
 
 
 ---------------------

Documentation/auxdisplay/cfag12864b-example.c

@@ -4,7 +4,7 @@
  * Description: cfag12864b LCD userspace example program
  *     License: GPLv2
  *
- *      Author: Copyright (C) Miguel Ojeda Sandonis <maxextreme@gmail.com>
+ *      Author: Copyright (C) Miguel Ojeda Sandonis
  *        Date: 2006-10-31
  *
  *  This program is free software; you can redistribute it and/or modify

Documentation/auxdisplay/ks0108

@@ -3,7 +3,7 @@
 	==========================================
 
 License:		GPLv2
-Author & Maintainer:	Miguel Ojeda Sandonis <maxextreme@gmail.com>
+Author & Maintainer:	Miguel Ojeda Sandonis
 Date:			2006-10-27
 
 
@@ -21,7 +21,7 @@ Date:			2006-10-27
 1. DRIVER INFORMATION
 ---------------------
 
-This driver support the ks0108 LCD controller.
+This driver supports the ks0108 LCD controller.
 
 
 ---------------------

Documentation/cgroups.txt

@@ -390,6 +390,10 @@ If you have several tasks to attach, you have to do it one after another:
 	...
 # /bin/echo PIDn > tasks
 
+You can attach the current shell task by echoing 0:
+
+# echo 0 > tasks
+
 3. Kernel API
 =============
 

Documentation/controllers/devices.txt

@@ -13,7 +13,7 @@ either an integer or * for all.  Access is a composition of r
 The root device cgroup starts with rwm to 'all'.  A child device
 cgroup gets a copy of the parent.  Administrators can then remove
 devices from the whitelist or add new entries.  A child cgroup can
-never receive a device access which is denied its parent.  However
+never receive a device access which is denied by its parent.  However
 when a device access is removed from a parent it will not also be
 removed from the child(ren).
 
@@ -29,7 +29,11 @@ allows cgroup 1 to read and mknod the device usually known as
 
 	echo a > /cgroups/1/devices.deny
 
-will remove the default 'a *:* mrw' entry.
+will remove the default 'a *:* rwm' entry. Doing
+
+	echo a > /cgroups/1/devices.allow
+
+will add the 'a *:* rwm' entry to the whitelist.
 
 3. Security
 

Documentation/cpusets.txt

@@ -154,13 +154,15 @@ browsing and modifying the cpusets presently known to the kernel.  No
 new system calls are added for cpusets - all support for querying and
 modifying cpusets is via this cpuset file system.
 
-The /proc/<pid>/status file for each task has two added lines,
+The /proc/<pid>/status file for each task has four added lines,
 displaying the tasks cpus_allowed (on which CPUs it may be scheduled)
 and mems_allowed (on which Memory Nodes it may obtain memory),
-in the format seen in the following example:
+in the two formats seen in the following example:
 
   Cpus_allowed:   ffffffff,ffffffff,ffffffff,ffffffff
+  Cpus_allowed_list:      0-127
   Mems_allowed:   ffffffff,ffffffff
+  Mems_allowed_list:      0-63
 
 Each cpuset is represented by a directory in the cgroup file system
 containing (on top of the standard cgroup files) the following
@@ -544,6 +546,9 @@ otherwise initial value -1 that indicates the cpuset has no request.
  ( 4  : search nodes in a chunk of node [on NUMA system] )
  ( 5  : search system wide [on NUMA system] )
 
+The system default is architecture dependent.  The system default
+can be changed using the relax_domain_level= boot parameter.
+
 This file is per-cpuset and affect the sched domain where the cpuset
 belongs to.  Therefore if the flag 'sched_load_balance' of a cpuset
 is disabled, then 'sched_relax_domain_level' have no effect since

Documentation/feature-removal-schedule.txt

@@ -312,3 +312,12 @@ When:	2.6.26
 Why:	Implementation became generic; users should now include
 	linux/semaphore.h instead.
 Who:	Matthew Wilcox <willy@linux.intel.com>
+
+---------------------------
+
+What:	CONFIG_THERMAL_HWMON
+When:	January 2009
+Why:	This option was introduced just to allow older lm-sensors userspace
+	to keep working over the upgrade to 2.6.26. At the scheduled time of
+	removal fixed lm-sensors (2.x or 3.x) should be readily available.
+Who:	Rene Herman <rene.herman@gmail.com>

Documentation/hwmon/sysfs-interface

@@ -2,17 +2,12 @@ Naming and data format standards for sysfs files
 ------------------------------------------------
 
 The libsensors library offers an interface to the raw sensors data
-through the sysfs interface. See libsensors documentation and source for
-further information. As of writing this document, libsensors
-(from lm_sensors 2.8.3) is heavily chip-dependent. Adding or updating
-support for any given chip requires modifying the library's code.
-This is because libsensors was written for the procfs interface
-older kernel modules were using, which wasn't standardized enough.
-Recent versions of libsensors (from lm_sensors 2.8.2 and later) have
-support for the sysfs interface, though.
-
-The new sysfs interface was designed to be as chip-independent as
-possible.
+through the sysfs interface. Since lm-sensors 3.0.0, libsensors is
+completely chip-independent. It assumes that all the kernel drivers
+implement the standard sysfs interface described in this document.
+This makes adding or updating support for any given chip very easy, as
+libsensors, and applications using it, do not need to be modified.
+This is a major improvement compared to lm-sensors 2.
 
 Note that motherboards vary widely in the connections to sensor chips.
 There is no standard that ensures, for example, that the second
@@ -35,19 +30,17 @@ access this data in a simple and consistent way. That said, such programs
 will have to implement conversion, labeling and hiding of inputs. For
 this reason, it is still not recommended to bypass the library.
 
-If you are developing a userspace application please send us feedback on
-this standard.
-
-Note that this standard isn't completely established yet, so it is subject
-to changes. If you are writing a new hardware monitoring driver those
-features can't seem to fit in this interface, please contact us with your
-extension proposal. Keep in mind that backward compatibility must be
-preserved.
-
 Each chip gets its own directory in the sysfs /sys/devices tree.  To
 find all sensor chips, it is easier to follow the device symlinks from
 /sys/class/hwmon/hwmon*.
 
+Up to lm-sensors 3.0.0, libsensors looks for hardware monitoring attributes
+in the "physical" device directory. Since lm-sensors 3.0.1, attributes found
+in the hwmon "class" device directory are also supported. Complex drivers
+(e.g. drivers for multifunction chips) may want to use this possibility to
+avoid namespace pollution. The only drawback will be that older versions of
+libsensors won't support the driver in question.
+
 All sysfs values are fixed point numbers.
 
 There is only one value per file, unlike the older /proc specification.

Documentation/i2c/writing-clients

@@ -25,12 +25,23 @@ routines, and should be zero-initialized except for fields with data you
 provide.  A client structure holds device-specific information like the
 driver model device node, and its I2C address.
 
+/* iff driver uses driver model ("new style") binding model: */
+
+static struct i2c_device_id foo_idtable[] = {
+	{ "foo", my_id_for_foo },
+	{ "bar", my_id_for_bar },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(i2c, foo_idtable);
+
 static struct i2c_driver foo_driver = {
 	.driver = {
 		.name	= "foo",
 	},
 
 	/* iff driver uses driver model ("new style") binding model: */
+	.id_table	= foo_ids,
 	.probe		= foo_probe,
 	.remove		= foo_remove,
 
@@ -173,10 +184,9 @@ handle may be used during foo_probe().  If foo_probe() reports success
 (zero not a negative status code) it may save the handle and use it until
 foo_remove() returns.  That binding model is used by most Linux drivers.
 
-Drivers match devices when i2c_client.driver_name and the driver name are
-the same; this approach is used in several other busses that don't have
-device typing support in the hardware.  The driver and module name should
-match, so hotplug/coldplug mechanisms will modprobe the driver.
+The probe function is called when an entry in the id_table name field
+matches the device's name. It is passed the entry that was matched so
+the driver knows which one in the table matched.
 
 
 Device Creation (Standard driver model)

Documentation/kernel-parameters.txt

@@ -295,7 +295,7 @@ and is between 256 and 4096 characters. It is defined in the file
 			when initialising the APIC and IO-APIC components.
 
 	apm=		[APM] Advanced Power Management
-			See header of arch/i386/kernel/apm.c.
+			See header of arch/x86/kernel/apm_32.c.
 
 	arcrimi=	[HW,NET] ARCnet - "RIM I" (entirely mem-mapped) cards
 			Format: <io>,<irq>,<nodeID>
@@ -638,7 +638,7 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	elanfreq=	[X86-32]
 			See comment before function elanfreq_setup() in
-			arch/i386/kernel/cpu/cpufreq/elanfreq.c.
+			arch/x86/kernel/cpu/cpufreq/elanfreq.c.
 
 	elevator=	[IOSCHED]
 			Format: {"anticipatory" | "cfq" | "deadline" | "noop"}
@@ -1679,6 +1679,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			Format: <reboot_mode>[,<reboot_mode2>[,...]]
 			See arch/*/kernel/reboot.c or arch/*/kernel/process.c			
 
+	relax_domain_level=
+			[KNL, SMP] Set scheduler's default relax_domain_level.
+			See Documentation/cpusets.txt.
+
 	reserve=	[KNL,BUGS] Force the kernel to ignore some iomem area
 
 	reservetop=	[X86-32]

Documentation/networking/ip-sysctl.txt

@@ -81,23 +81,23 @@ inet_peer_minttl - INTEGER
 	Minimum time-to-live of entries.  Should be enough to cover fragment
 	time-to-live on the reassembling side.  This minimum time-to-live  is
 	guaranteed if the pool size is less than inet_peer_threshold.
-	Measured in jiffies(1).
+	Measured in seconds.
 
 inet_peer_maxttl - INTEGER
 	Maximum time-to-live of entries.  Unused entries will expire after
 	this period of time if there is no memory pressure on the pool (i.e.
 	when the number of entries in the pool is very small).
-	Measured in jiffies(1).
+	Measured in seconds.
 
 inet_peer_gc_mintime - INTEGER
 	Minimum interval between garbage collection passes.  This interval is
 	in effect under high memory pressure on the pool.
-	Measured in jiffies(1).
+	Measured in seconds.
 
 inet_peer_gc_maxtime - INTEGER
 	Minimum interval between garbage collection passes.  This interval is
 	in effect under low (or absent) memory pressure on the pool.
-	Measured in jiffies(1).
+	Measured in seconds.
 
 TCP variables: 
 
@@ -148,9 +148,9 @@ tcp_available_congestion_control - STRING
 	but not loaded.
 
 tcp_base_mss - INTEGER
-	The initial value of search_low to be used by Packetization Layer
-	Path MTU Discovery (MTU probing).  If MTU probing is enabled,
-	this is the inital MSS used by the connection.
+	The initial value of search_low to be used by the packetization layer
+	Path MTU discovery (MTU probing).  If MTU probing is enabled,
+	this is the initial MSS used by the connection.
 
 tcp_congestion_control - STRING
 	Set the congestion control algorithm to be used for new
@@ -185,10 +185,9 @@ tcp_frto - INTEGER
 	timeouts.  It is particularly beneficial in wireless environments
 	where packet loss is typically due to random radio interference
 	rather than intermediate router congestion.  F-RTO is sender-side
-	only modification.  Therefore it does not require any support from
-	the peer, but in a typical case, however, where wireless link is
-	the local access link and most of the data flows downlink, the
-	faraway servers should have F-RTO enabled to take advantage of it.
+	only modification. Therefore it does not require any support from
+	the peer.
+
 	If set to 1, basic version is enabled.  2 enables SACK enhanced
 	F-RTO if flow uses SACK.  The basic version can be used also when
 	SACK is in use though scenario(s) with it exists where F-RTO
@@ -276,7 +275,7 @@ tcp_mem - vector of 3 INTEGERs: min, pressure, max
 	memory.
 
 tcp_moderate_rcvbuf - BOOLEAN
-	If set, TCP performs receive buffer autotuning, attempting to
+	If set, TCP performs receive buffer auto-tuning, attempting to
 	automatically size the buffer (no greater than tcp_rmem[2]) to
 	match the size required by the path for full throughput.  Enabled by
 	default.
@@ -336,7 +335,7 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
 	pressure.
 	Default: 8K
 
-	default: default size of receive buffer used by TCP sockets.
+	default: initial size of receive buffer used by TCP sockets.
 	This value overrides net.core.rmem_default used by other protocols.
 	Default: 87380 bytes. This value results in window of 65535 with
 	default setting of tcp_adv_win_scale and tcp_app_win:0 and a bit
@@ -344,8 +343,10 @@ tcp_rmem - vector of 3 INTEGERs: min, default, max
 
 	max: maximal size of receive buffer allowed for automatically
 	selected receiver buffers for TCP socket. This value does not override
-	net.core.rmem_max, "static" selection via SO_RCVBUF does not use this.
-	Default: 87380*2 bytes.
+	net.core.rmem_max.  Calling setsockopt() with SO_RCVBUF disables
+	automatic tuning of that socket's receive buffer size, in which
+	case this value is ignored.
+	Default: between 87380B and 4MB, depending on RAM size.
 
 tcp_sack - BOOLEAN
 	Enable select acknowledgments (SACKS).
@@ -358,7 +359,7 @@ tcp_slow_start_after_idle - BOOLEAN
 	Default: 1
 
 tcp_stdurg - BOOLEAN
-	Use the Host requirements interpretation of the TCP urg pointer field.
+	Use the Host requirements interpretation of the TCP urgent pointer field.
 	Most hosts use the older BSD interpretation, so if you turn this on
 	Linux might not communicate correctly with them.
 	Default: FALSE
@@ -371,12 +372,12 @@ tcp_synack_retries - INTEGER
 tcp_syncookies - BOOLEAN
 	Only valid when the kernel was compiled with CONFIG_SYNCOOKIES
 	Send out syncookies when the syn backlog queue of a socket
-	overflows. This is to prevent against the common 'syn flood attack'
+	overflows. This is to prevent against the common 'SYN flood attack'
 	Default: FALSE
 
 	Note, that syncookies is fallback facility.
 	It MUST NOT be used to help highly loaded servers to stand
-	against legal connection rate. If you see synflood warnings
+	against legal connection rate. If you see SYN flood warnings
 	in your logs, but investigation	shows that they occur
 	because of overload with legal connections, you should tune
 	another parameters until this warning disappear.
@@ -386,7 +387,7 @@ tcp_syncookies - BOOLEAN
 	to use TCP extensions, can result in serious degradation
 	of some services (f.e. SMTP relaying), visible not by you,
 	but your clients and relays, contacting you. While you see
-	synflood warnings in logs not being really flooded, your server
+	SYN flood warnings in logs not being really flooded, your server
 	is seriously misconfigured.
 
 tcp_syn_retries - INTEGER
@@ -419,19 +420,21 @@ tcp_window_scaling - BOOLEAN
 	Enable window scaling as defined in RFC1323.
 
 tcp_wmem - vector of 3 INTEGERs: min, default, max
-	min: Amount of memory reserved for send buffers for TCP socket.
+	min: Amount of memory reserved for send buffers for TCP sockets.
 	Each TCP socket has rights to use it due to fact of its birth.
 	Default: 4K
 
-	default: Amount of memory allowed for send buffers for TCP socket
-	by default. This value overrides net.core.wmem_default used
-	by other protocols, it is usually lower than net.core.wmem_default.
+	default: initial size of send buffer used by TCP sockets.  This
+	value overrides net.core.wmem_default used by other protocols.
+	It is usually lower than net.core.wmem_default.
 	Default: 16K
 
-	max: Maximal amount of memory allowed for automatically selected
-	send buffers for TCP socket. This value does not override
-	net.core.wmem_max, "static" selection via SO_SNDBUF does not use this.
-	Default: 128K
+	max: Maximal amount of memory allowed for automatically tuned
+	send buffers for TCP sockets. This value does not override
+	net.core.wmem_max.  Calling setsockopt() with SO_SNDBUF disables
+	automatic tuning of that socket's send buffer size, in which case
+	this value is ignored.
+	Default: between 64K and 4MB, depending on RAM size.
 
 tcp_workaround_signed_windows - BOOLEAN
 	If set, assume no receipt of a window scaling option means the
@@ -794,10 +797,6 @@ tag - INTEGER
 	Allows you to write a number, which can be used as required.
 	Default value is 0.
 
-(1) Jiffie: internal timeunit for the kernel. On the i386 1/100s, on the
-Alpha 1/1024s. See the HZ define in /usr/include/asm/param.h for the exact
-value on your system. 
-
 Alexey Kuznetsov.
 kuznet@ms2.inr.ac.ru
 
@@ -1064,24 +1063,193 @@ bridge-nf-filter-pppoe-tagged - BOOLEAN
 	Default: 1
 
 
+proc/sys/net/sctp/* Variables:
+
+addip_enable - BOOLEAN
+	Enable or disable extension of  Dynamic Address Reconfiguration
+	(ADD-IP) functionality specified in RFC5061.  This extension provides
+	the ability to dynamically add and remove new addresses for the SCTP
+	associations.
+
+	1: Enable extension.
+
+	0: Disable extension.
+
+	Default: 0
+
+addip_noauth_enable - BOOLEAN
+	Dynamic Address Reconfiguration (ADD-IP) requires the use of
+	authentication to protect the operations of adding or removing new
+	addresses.  This requirement is mandated so that unauthorized hosts
+	would not be able to hijack associations.  However, older
+	implementations may not have implemented this requirement while
+	allowing the ADD-IP extension.  For reasons of interoperability,
+	we provide this variable to control the enforcement of the
+	authentication requirement.
+
+	1: Allow ADD-IP extension to be used without authentication.  This
+	   should only be set in a closed environment for interoperability
+	   with older implementations.
+
+	0: Enforce the authentication requirement
+
+	Default: 0
+
+auth_enable - BOOLEAN
+	Enable or disable Authenticated Chunks extension.  This extension
+	provides the ability to send and receive authenticated chunks and is
+	required for secure operation of Dynamic Address Reconfiguration
+	(ADD-IP) extension.
+
+	1: Enable this extension.
+	0: Disable this extension.
+
+	Default: 0
+
+prsctp_enable - BOOLEAN
+	Enable or disable the Partial Reliability extension (RFC3758) which
+	is used to notify peers that a given DATA should no longer be expected.
+
+	1: Enable extension
+	0: Disable
+
+	Default: 1
+
+max_burst - INTEGER
+	The limit of the number of new packets that can be initially sent.  It
+	controls how bursty the generated traffic can be.
+
+	Default: 4
+
+association_max_retrans - INTEGER
+	Set the maximum number for retransmissions that an association can
+	attempt deciding that the remote end is unreachable.  If this value
+	is exceeded, the association is terminated.
+
+	Default: 10
+
+max_init_retransmits - INTEGER
+	The maximum number of retransmissions of INIT and COOKIE-ECHO chunks
+	that an association will attempt before declaring the destination
+	unreachable and terminating.
+
+	Default: 8
+
+path_max_retrans - INTEGER
+	The maximum number of retransmissions that will be attempted on a given
+	path.  Once this threshold is exceeded, the path is considered
+	unreachable, and new traffic will use a different path when the
+	association is multihomed.
+
+	Default: 5
+
+rto_initial - INTEGER
+	The initial round trip timeout value in milliseconds that will be used
+	in calculating round trip times.  This is the initial time interval
+	for retransmissions.
+
+	Default: 3000
+
+rto_max - INTEGER
+	The maximum value (in milliseconds) of the round trip timeout.  This
+	is the largest time interval that can elapse between retransmissions.
+
+	Default: 60000
+
+rto_min - INTEGER
+	The minimum value (in milliseconds) of the round trip timeout.  This
+	is the smallest time interval the can elapse between retransmissions.
+
+	Default: 1000
+
+hb_interval - INTEGER
+	The interval (in milliseconds) between HEARTBEAT chunks.  These chunks
+	are sent at the specified interval on idle paths to probe the state of
+	a given path between 2 associations.
+
+	Default: 30000
+
+sack_timeout - INTEGER
+	The amount of time (in milliseconds) that the implementation will wait
+	to send a SACK.
+
+	Default: 200
+
+valid_cookie_life - INTEGER
+	The default lifetime of the SCTP cookie (in milliseconds).  The cookie
+	is used during association establishment.
+
+	Default: 60000
+
+cookie_preserve_enable - BOOLEAN
+	Enable or disable the ability to extend the lifetime of the SCTP cookie
+	that is used during the establishment phase of SCTP association
+
+	1: Enable cookie lifetime extension.
+	0: Disable
+
+	Default: 1
+
+rcvbuf_policy - INTEGER
+	Determines if the receive buffer is attributed to the socket or to
+	association.   SCTP supports the capability to create multiple
+	associations on a single socket.  When using this capability, it is
+	possible that a single stalled association that's buffering a lot
+	of data may block other associations from delivering their data by
+	consuming all of the receive buffer space.  To work around this,
+	the rcvbuf_policy could be set to attribute the receiver buffer space
+	to each association instead of the socket.  This prevents the described
+	blocking.
+
+	1: rcvbuf space is per association
+	0: recbuf space is per socket
+
+	Default: 0
+
+sndbuf_policy - INTEGER
+	Similar to rcvbuf_policy above, this applies to send buffer space.
+
+	1: Send buffer is tracked per association
+	0: Send buffer is tracked per socket.
+
+	Default: 0
+
+sctp_mem - vector of 3 INTEGERs: min, pressure, max
+	Number of pages allowed for queueing by all SCTP sockets.
+
+	min: Below this number of pages SCTP is not bothered about its
+	memory appetite. When amount of memory allocated by SCTP exceeds
+	this number, SCTP starts to moderate memory usage.
+
+	pressure: This value was introduced to follow format of tcp_mem.
+
+	max: Number of pages allowed for queueing by all SCTP sockets.
+
+	Default is calculated at boot time from amount of available memory.
+
+sctp_rmem - vector of 3 INTEGERs: min, default, max
+	See tcp_rmem for a description.
+
+sctp_wmem  - vector of 3 INTEGERs: min, default, max
+	See tcp_wmem for a description.
+
 UNDOCUMENTED:
 
-dev_weight FIXME
-discovery_slots FIXME
-discovery_timeout FIXME
-fast_poll_increase FIXME
-ip6_queue_maxlen FIXME
-lap_keepalive_time FIXME
-lo_cong FIXME
-max_baud_rate FIXME
-max_dgram_qlen FIXME
-max_noreply_time FIXME
-max_tx_data_size FIXME
-max_tx_window FIXME
-min_tx_turn_time FIXME
-mod_cong FIXME
-no_cong FIXME
-no_cong_thresh FIXME
-slot_timeout FIXME
-warn_noreply_time FIXME
+/proc/sys/net/core/*
+	dev_weight FIXME
 
+/proc/sys/net/unix/*
+	max_dgram_qlen FIXME
+
+/proc/sys/net/irda/*
+	fast_poll_increase FIXME
+	warn_noreply_time FIXME
+	discovery_slots FIXME
+	slot_timeout FIXME
+	max_baud_rate FIXME
+	discovery_timeout FIXME
+	lap_keepalive_time FIXME
+	max_noreply_time FIXME
+	max_tx_data_size FIXME
+	max_tx_window FIXME
+	min_tx_turn_time FIXME

Documentation/networking/s2io.txt

@@ -83,9 +83,9 @@ Valid range: Limited by memory on system
 Default: 30 
 
 e. intr_type
-Specifies interrupt type. Possible values 1(INTA), 2(MSI), 3(MSI-X)
-Valid range: 1-3
-Default: 1 
+Specifies interrupt type. Possible values 0(INTA), 2(MSI-X)
+Valid values: 0, 2
+Default: 2
 
 5.  Performance suggestions
 General:

Documentation/video4linux/CARDLIST.au0828

@@ -1,4 +1,4 @@
   0 -> Unknown board                            (au0828)
-  1 -> Hauppauge HVR950Q                        (au0828)        [2040:7200]
+  1 -> Hauppauge HVR950Q                        (au0828)        [2040:7200,2040:7210,2040:7217,2040:721b,2040:721f,2040:7280,0fd9:0008]
   2 -> Hauppauge HVR850                         (au0828)        [2040:7240]
   3 -> DViCO FusionHDTV USB                     (au0828)        [0fe9:d620]

Documentation/vm/slabinfo.c

@@ -1,7 +1,7 @@
 /*
  * Slabinfo: Tool to get reports about slabs
  *
- * (C) 2007 sgi, Christoph Lameter <clameter@sgi.com>
+ * (C) 2007 sgi, Christoph Lameter
  *
  * Compile by:
  *
@@ -99,7 +99,7 @@ void fatal(const char *x, ...)
 
 void usage(void)
 {
-	printf("slabinfo 5/7/2007. (c) 2007 sgi. clameter@sgi.com\n\n"
+	printf("slabinfo 5/7/2007. (c) 2007 sgi.\n\n"
 		"slabinfo [-ahnpvtsz] [-d debugopts] [slab-regexp]\n"
 		"-a|--aliases           Show aliases\n"
 		"-A|--activity          Most active slabs first\n"

Documentation/vm/slub.txt

@@ -266,4 +266,4 @@ of other objects.
 
 	slub_debug=FZ,dentry
 
-Christoph Lameter, <clameter@sgi.com>, May 30, 2007
+Christoph Lameter, May 30, 2007

MAINTAINERS

@@ -763,9 +763,10 @@ S:	Maintained
 
 AUXILIARY DISPLAY DRIVERS
 P:	Miguel Ojeda Sandonis
-M:	maxextreme@gmail.com
+M:	miguel.ojeda.sandonis@gmail.com
 L:	linux-kernel@vger.kernel.org
-W:	http://auxdisplay.googlepages.com/
+W:	http://miguelojeda.es/auxdisplay.htm
+W:	http://jair.lab.fi.uva.es/~migojed/auxdisplay.htm
 S:	Maintained
 
 AVR32 ARCHITECTURE
@@ -1055,16 +1056,18 @@ S:	Supported
 
 CFAG12864B LCD DRIVER
 P:	Miguel Ojeda Sandonis
-M:	maxextreme@gmail.com
+M:	miguel.ojeda.sandonis@gmail.com
 L:	linux-kernel@vger.kernel.org
-W:	http://auxdisplay.googlepages.com/
+W:	http://miguelojeda.es/auxdisplay.htm
+W:	http://jair.lab.fi.uva.es/~migojed/auxdisplay.htm
 S:	Maintained
 
 CFAG12864BFB LCD FRAMEBUFFER DRIVER
 P:	Miguel Ojeda Sandonis
-M:	maxextreme@gmail.com
+M:	miguel.ojeda.sandonis@gmail.com
 L:	linux-kernel@vger.kernel.org
-W:	http://auxdisplay.googlepages.com/
+W:	http://miguelojeda.es/auxdisplay.htm
+W:	http://jair.lab.fi.uva.es/~migojed/auxdisplay.htm
 S:	Maintained
 
 CFG80211 and NL80211
@@ -1420,6 +1423,14 @@ M:	kristen.c.accardi@intel.com
 L:	linux-acpi@vger.kernel.org
 S:	Supported
 
+DOCUMENTATION (/Documentation directory)
+P:     Michael Kerrisk
+M:     mtk.manpages@gmail.com
+P:     Randy Dunlap
+M:     rdunlap@xenotime.net
+L:     linux-doc@vger.kernel.org
+S:     Maintained
+
 DOUBLETALK DRIVER
 P:	James R. Van Zandt
 M:	jrv@vanzandt.mv.com
@@ -1626,13 +1637,13 @@ S:	Maintained
 
 EXT3 FILE SYSTEM
 P:	Stephen Tweedie, Andrew Morton
-M:	sct@redhat.com, akpm@linux-foundation.org, adilger@clusterfs.com
+M:	sct@redhat.com, akpm@linux-foundation.org, adilger@sun.com
 L:	linux-ext4@vger.kernel.org
 S:	Maintained
 
 EXT4 FILE SYSTEM
 P:	Stephen Tweedie, Andrew Morton
-M:	sct@redhat.com, akpm@linux-foundation.org, adilger@clusterfs.com
+M:	sct@redhat.com, akpm@linux-foundation.org, adilger@sun.com
 L:	linux-ext4@vger.kernel.org
 S:	Maintained
 
@@ -2428,9 +2439,10 @@ S:	Maintained
 
 KS0108 LCD CONTROLLER DRIVER
 P:	Miguel Ojeda Sandonis
-M:	maxextreme@gmail.com
+M:	miguel.ojeda.sandonis@gmail.com
 L:	linux-kernel@vger.kernel.org
-W:	http://auxdisplay.googlepages.com/
+W:	http://miguelojeda.es/auxdisplay.htm
+W:	http://jair.lab.fi.uva.es/~migojed/auxdisplay.htm
 S:	Maintained
 
 LAPB module
@@ -2474,9 +2486,11 @@ M:	James.Bottomley@HansenPartnership.com
 W:	http://www.hansenpartnership.com/voyager
 S:	Maintained
 
-LINUX FOR POWERPC
+LINUX FOR POWERPC (32-BIT AND 64-BIT)
 P:	Paul Mackerras
 M:	paulus@samba.org
+P:	Benjamin Herrenschmidt
+M:	benh@kernel.crashing.org
 W:	http://www.penguinppc.org/
 L:	linuxppc-dev@ozlabs.org
 T:	git kernel.org:/pub/scm/linux/kernel/git/paulus/powerpc.git
@@ -2516,13 +2530,6 @@ W:	http://wiki.secretlab.ca/index.php/Linux_on_Xilinx_Virtex
 L:	linuxppc-dev@ozlabs.org
 S:	Maintained
 
-LINUX FOR POWERPC BOOT CODE
-P:	Tom Rini
-M:	trini@kernel.crashing.org
-W:	http://www.penguinppc.org/
-L:	linuxppc-dev@ozlabs.org
-S:	Maintained
-
 LINUX FOR POWERPC EMBEDDED PPC8XX
 P:	Vitaly Bordug
 M:	vitb@kernel.crashing.org
@@ -2551,17 +2558,6 @@ P:	Arnaldo Carvalho de Melo
 M:	acme@ghostprotocols.net
 S:	Maintained
 
-LINUX FOR 64BIT POWERPC
-P:	Paul Mackerras
-M:	paulus@samba.org
-M:	paulus@au.ibm.com
-P:	Anton Blanchard
-M:	anton@samba.org
-M:	anton@au.ibm.com
-W:	http://www.penguinppc.org/ppc64/
-L:	linuxppc-dev@ozlabs.org
-S:	Supported
-
 LINUX SECURITY MODULE (LSM) FRAMEWORK
 P:	Chris Wright
 M:	chrisw@sous-sol.org
@@ -2680,8 +2676,8 @@ S: 	Supported
 MAN-PAGES: MANUAL PAGES FOR LINUX -- Sections 2, 3, 4, 5, and 7
 P:	Michael Kerrisk
 M:	mtk.manpages@gmail.com
-W:	ftp://ftp.kernel.org/pub/linux/docs/manpages
-S:	Maintained
+W:     http://www.kernel.org/doc/man-pages
+S:     Supported
 
 MARVELL LIBERTAS WIRELESS DRIVER
 P:	Dan Williams
@@ -2814,6 +2810,12 @@ W:	https://tango.0pointer.de/mailman/listinfo/s270-linux
 W:	http://0pointer.de/lennart/tchibo.html
 S:	Maintained
 
+MULTIFUNCTION DEVICES (MFD)
+P:	Samuel Ortiz
+M:	sameo@openedhand.com
+L:	linux-kernel@vger.kernel.org
+S:	Supported
+
 MULTIMEDIA CARD (MMC), SECURE DIGITAL (SD) AND SDIO SUBSYSTEM
 P:	Pierre Ossman
 M:	drzeus-mmc@drzeus.cx
@@ -3080,8 +3082,8 @@ L:	linux-scsi@vger.kernel.org
 S:	Maintained
 
 OPROFILE
-P:	Philippe Elie
-M:	phil.el@wanadoo.fr
+P:	Robert Richter
+M:	robert.richter@amd.com
 L:	oprofile-list@lists.sf.net
 S:	Maintained
 
@@ -3195,8 +3197,8 @@ L:	netdev@vger.kernel.org
 S:	Maintained
 
 PER-TASK DELAY ACCOUNTING
-P:	Shailabh Nagar
-M:	nagar@watson.ibm.com
+P:	Balbir Singh
+M:	balbir@linux.vnet.ibm.com
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 
@@ -3688,7 +3690,7 @@ S:	Maintained
 
 SLAB ALLOCATOR
 P:	Christoph Lameter
-M:	clameter@sgi.com
+M:	cl@linux-foundation.org
 P:	Pekka Enberg
 M:	penberg@cs.helsinki.fi
 P:	Matt Mackall
@@ -3898,8 +3900,8 @@ M:	hch@infradead.org
 S:	Maintained
 
 TASKSTATS STATISTICS INTERFACE
-P:	Shailabh Nagar
-M:	nagar@watson.ibm.com
+P:	Balbir Singh
+M:	balbir@linux.vnet.ibm.com
 L:	linux-kernel@vger.kernel.org
 S:	Maintained
 
@@ -3995,7 +3997,8 @@ W:	http://www.buzzard.org.uk/toshiba/
 S:	Maintained
 
 TPM DEVICE DRIVER
-P:	Kylene Hall
+P:     Debora Velarde
+P:     Rajiv Andrade
 M:	tpmdd-devel@lists.sourceforge.net
 W:	http://tpmdd.sourceforge.net
 P:	Marcel Selhorst
@@ -4314,6 +4317,14 @@ L:	netdev@vger.kernel.org
 W:	http://www.linux-usb.org/usbnet
 S:	Maintained
 
+USB VIDEO CLASS
+P:	Laurent Pinchart
+M:	laurent.pinchart@skynet.be
+L:	linx-uvc-devel@berlios.de
+L:	video4linux-list@redhat.com
+W:	http://linux-uvc.berlios.de
+S:	Maintained
+
 USB W996[87]CF DRIVER
 P:	Luca Risolia
 M:	luca.risolia@studio.unibo.it
@@ -4431,10 +4442,10 @@ M:	johnpol@2ka.mipt.ru
 S:	Maintained
 
 W83791D HARDWARE MONITORING DRIVER
-P:	Charles Spirakis
-M:	bezaur@gmail.com
+P:	Marc Hulsman
+M:	m.hulsman@tudelft.nl
 L:	lm-sensors@lm-sensors.org
-S:	Odd Fixes
+S:	Maintained
 
 W83793 HARDWARE MONITORING DRIVER
 P:	Rudolf Marek

Makefile

@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 26
-EXTRAVERSION = -rc7
+EXTRAVERSION =
 NAME = Rotary Wombat
 
 # *DOCUMENTATION*

arch/alpha/Makefile

@@ -13,6 +13,7 @@ NM := $(NM) -B
 LDFLAGS_vmlinux	:= -static -N #-relax
 CHECKFLAGS	+= -D__alpha__ -m64
 cflags-y	:= -pipe -mno-fp-regs -ffixed-8 -msmall-data
+cflags-y	+= $(call cc-option, -fno-jump-tables)
 
 cpuflags-$(CONFIG_ALPHA_EV4)		:= -mcpu=ev4
 cpuflags-$(CONFIG_ALPHA_EV5)		:= -mcpu=ev5

arch/alpha/kernel/core_t2.c

@@ -74,6 +74,8 @@
 # define DBG(args)
 #endif
 
+DEFINE_SPINLOCK(t2_hae_lock);
+
 static volatile unsigned int t2_mcheck_any_expected;
 static volatile unsigned int t2_mcheck_last_taken;
 

arch/alpha/kernel/pci.c

@@ -71,6 +71,23 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82378, quirk_i
 static void __init
 quirk_cypress(struct pci_dev *dev)
 {
+	/* The Notorious Cy82C693 chip.  */
+
+	/* The generic legacy mode IDE fixup in drivers/pci/probe.c
+	   doesn't work correctly with the Cypress IDE controller as
+	   it has non-standard register layout.  Fix that.  */
+	if (dev->class >> 8 == PCI_CLASS_STORAGE_IDE) {
+		dev->resource[2].start = dev->resource[3].start = 0;
+		dev->resource[2].end = dev->resource[3].end = 0;
+		dev->resource[2].flags = dev->resource[3].flags = 0;
+		if (PCI_FUNC(dev->devfn) == 2) {
+			dev->resource[0].start = 0x170;
+			dev->resource[0].end = 0x177;
+			dev->resource[1].start = 0x376;
+			dev->resource[1].end = 0x376;
+		}
+	}
+
 	/* The Cypress bridge responds on the PCI bus in the address range
 	   0xffff0000-0xffffffff (conventional x86 BIOS ROM).  There is no
 	   way to turn this off.  The bridge also supports several extended

arch/alpha/kernel/traps.c

@@ -447,7 +447,7 @@ struct unaligned_stat {
 
 
 /* Macro for exception fixup code to access integer registers.  */
-#define una_reg(r)  (regs->regs[(r) >= 16 && (r) <= 18 ? (r)+19 : (r)])
+#define una_reg(r)  (_regs[(r) >= 16 && (r) <= 18 ? (r)+19 : (r)])
 
 
 asmlinkage void
@@ -456,6 +456,7 @@ do_entUna(void * va, unsigned long opcode, unsigned long reg,
 {
 	long error, tmp1, tmp2, tmp3, tmp4;
 	unsigned long pc = regs->pc - 4;
+	unsigned long *_regs = regs->regs;
 	const struct exception_table_entry *fixup;
 
 	unaligned[0].count++;

arch/alpha/kernel/vmlinux.lds.S

@@ -25,6 +25,13 @@ SECTIONS
 	} :kernel
 	_etext = .;	/* End of text section */
 
+	NOTES :kernel :note
+	.dummy : {
+		*(.dummy)
+	} :kernel
+
+	RODATA
+
 	/* Exception table */
 	. = ALIGN(16);
 	__ex_table : {
@@ -33,13 +40,6 @@ SECTIONS
 		__stop___ex_table = .;
 	}
 
-	NOTES :kernel :note
-	.dummy : {
-		*(.dummy)
-	} :kernel
-
-	RODATA
-
 	/* Will be freed after init */
 	. = ALIGN(PAGE_SIZE);
 	/* Init code and data */

arch/arm/common/dmabounce.c

@@ -650,7 +650,8 @@ EXPORT_SYMBOL(dma_map_sg);
 EXPORT_SYMBOL(dma_unmap_sg);
 EXPORT_SYMBOL(dma_sync_single_for_cpu);
 EXPORT_SYMBOL(dma_sync_single_for_device);
-EXPORT_SYMBOL(dma_sync_sg);
+EXPORT_SYMBOL(dma_sync_sg_for_cpu);
+EXPORT_SYMBOL(dma_sync_sg_for_device);
 EXPORT_SYMBOL(dmabounce_register_dev);
 EXPORT_SYMBOL(dmabounce_unregister_dev);
 

arch/arm/mach-omap2/gpmc.c

@@ -42,7 +42,7 @@
 #define GPMC_STATUS		0x54
 #define GPMC_PREFETCH_CONFIG1	0x1e0
 #define GPMC_PREFETCH_CONFIG2	0x1e4
-#define GPMC_PREFETCH_CONTROL	0x1e8
+#define GPMC_PREFETCH_CONTROL	0x1ec
 #define GPMC_PREFETCH_STATUS	0x1f0
 #define GPMC_ECC_CONFIG		0x1f4
 #define GPMC_ECC_CONTROL	0x1f8

arch/arm/mach-realview/platsmp.c

@@ -74,6 +74,8 @@ static DEFINE_SPINLOCK(boot_lock);
 
 void __cpuinit platform_secondary_init(unsigned int cpu)
 {
+	trace_hardirqs_off();
+
 	/*
 	 * the primary core may have used a "cross call" soft interrupt
 	 * to get this processor out of WFI in the BootMonitor - make

arch/arm/plat-omap/dma.c

@@ -501,8 +501,6 @@ static inline void omap_enable_channel_irq(int lch)
 
 	/* Enable some nice interrupts. */
 	OMAP_DMA_CICR_REG(lch) = dma_chan[lch].enabled_irqs;
-
-	dma_chan[lch].flags |= OMAP_DMA_ACTIVE;
 }
 
 static void omap_disable_channel_irq(int lch)

arch/blackfin/kernel/cplb-nompu/cplbinit.c

@@ -254,7 +254,8 @@ close_cplbtab(struct cplb_tab *table)
 }
 
 /* helper function */
-static void __fill_code_cplbtab(struct cplb_tab *t, int i, u32 a_start, u32 a_end)
+static void __init
+__fill_code_cplbtab(struct cplb_tab *t, int i, u32 a_start, u32 a_end)
 {
 	if (cplb_data[i].psize) {
 		fill_cplbtab(t,
@@ -291,7 +292,8 @@ static void __fill_code_cplbtab(struct cplb_tab *t, int i, u32 a_start, u32 a_en
 	}
 }
 
-static void __fill_data_cplbtab(struct cplb_tab *t, int i, u32 a_start, u32 a_end)
+static void __init
+__fill_data_cplbtab(struct cplb_tab *t, int i, u32 a_start, u32 a_end)
 {
 	if (cplb_data[i].psize) {
 		fill_cplbtab(t,

arch/blackfin/kernel/irqchip.c

@@ -60,9 +60,14 @@ static struct irq_chip bad_chip = {
 };
 
 static struct irq_desc bad_irq_desc = {
+	.status = IRQ_DISABLED,
 	.chip = &bad_chip,
 	.handle_irq = handle_bad_irq,
 	.depth = 1,
+	.lock = __SPIN_LOCK_UNLOCKED(irq_desc->lock),
+#ifdef CONFIG_SMP
+	.affinity = CPU_MASK_ALL
+#endif
 };
 
 int show_interrupts(struct seq_file *p, void *v)

arch/ia64/kernel/iosapic.c

@@ -558,8 +558,6 @@ static struct iosapic_rte_info * __init_refok iosapic_alloc_rte (void)
 	if (!iosapic_kmalloc_ok && list_empty(&free_rte_list)) {
 		rte = alloc_bootmem(sizeof(struct iosapic_rte_info) *
 				    NR_PREALLOCATE_RTE_ENTRIES);
-		if (!rte)
-			return NULL;
 		for (i = 0; i < NR_PREALLOCATE_RTE_ENTRIES; i++, rte++)
 			list_add(&rte->rte_list, &free_rte_list);
 	}

arch/ia64/kernel/setup.c

@@ -547,7 +547,8 @@ setup_arch (char **cmdline_p)
 # ifdef CONFIG_ACPI_NUMA
 	acpi_numa_init();
 	per_cpu_scan_finalize((cpus_weight(early_cpu_possible_map) == 0 ?
-		32 : cpus_weight(early_cpu_possible_map)), additional_cpus);
+		32 : cpus_weight(early_cpu_possible_map)),
+		additional_cpus > 0 ? additional_cpus : 0);
 # endif
 #else
 # ifdef CONFIG_SMP
@@ -578,8 +579,6 @@ setup_arch (char **cmdline_p)
 	cpu_init();	/* initialize the bootstrap CPU */
 	mmu_context_init();	/* initialize context_id bitmap */
 
-	check_sal_cache_flush();
-
 #ifdef CONFIG_ACPI
 	acpi_boot_init();
 #endif
@@ -607,6 +606,7 @@ setup_arch (char **cmdline_p)
 		ia64_mca_init();
 
 	platform_setup(cmdline_p);
+	check_sal_cache_flush();
 	paging_init();
 }
 

arch/ia64/kernel/time.c

@@ -117,6 +117,7 @@ void account_system_vtime(struct task_struct *tsk)
 
 	local_irq_restore(flags);
 }
+EXPORT_SYMBOL_GPL(account_system_vtime);
 
 /*
  * Called from the timer interrupt handler to charge accumulated user time

arch/ia64/sn/kernel/sn2/sn2_smp.c

@@ -512,6 +512,8 @@ static ssize_t sn2_ptc_proc_write(struct file *file, const char __user *user, si
 	int cpu;
 	char optstr[64];
 
+	if (count == 0 || count > sizeof(optstr))
+		return -EINVAL;
 	if (copy_from_user(optstr, user, count))
 		return -EFAULT;
 	optstr[count - 1] = '\0';

arch/mips/Kconfig

@@ -1006,7 +1006,7 @@ config BOOT_ELF32
 config MIPS_L1_CACHE_SHIFT
 	int
 	default "4" if MACH_DECSTATION
-	default "7" if SGI_IP27 || SGI_IP28 || SNI_RM
+	default "7" if SGI_IP22 || SGI_IP27 || SGI_IP28 || SNI_RM
 	default "4" if PMC_MSP4200_EVAL
 	default "5"
 

arch/mips/kernel/cevt-txx9.c

@@ -161,6 +161,9 @@ void __init txx9_tmr_init(unsigned long baseaddr)
 	struct txx9_tmr_reg __iomem *tmrptr;
 
 	tmrptr = ioremap(baseaddr, sizeof(struct txx9_tmr_reg));
+	/* Start once to make CounterResetEnable effective */
+	__raw_writel(TXx9_TMTCR_CRE | TXx9_TMTCR_TCE, &tmrptr->tcr);
+	/* Stop and reset the counter */
 	__raw_writel(TXx9_TMTCR_CRE, &tmrptr->tcr);
 	__raw_writel(0, &tmrptr->tisr);
 	__raw_writel(0xffffffff, &tmrptr->cpra);

arch/mips/mm/c-r3k.c

@@ -26,7 +26,7 @@
 static unsigned long icache_size, dcache_size;		/* Size in bytes */
 static unsigned long icache_lsize, dcache_lsize;	/* Size in bytes */
 
-unsigned long __init r3k_cache_size(unsigned long ca_flags)
+unsigned long __cpuinit r3k_cache_size(unsigned long ca_flags)
 {
 	unsigned long flags, status, dummy, size;
 	volatile unsigned long *p;
@@ -61,7 +61,7 @@ unsigned long __init r3k_cache_size(unsigned long ca_flags)
 	return size * sizeof(*p);
 }
 
-unsigned long __init r3k_cache_lsize(unsigned long ca_flags)
+unsigned long __cpuinit r3k_cache_lsize(unsigned long ca_flags)
 {
 	unsigned long flags, status, lsize, i;
 	volatile unsigned long *p;
@@ -90,7 +90,7 @@ unsigned long __init r3k_cache_lsize(unsigned long ca_flags)
 	return lsize * sizeof(*p);
 }
 
-static void __init r3k_probe_cache(void)
+static void __cpuinit r3k_probe_cache(void)
 {
 	dcache_size = r3k_cache_size(ST0_ISC);
 	if (dcache_size)

arch/mips/mm/page.c

@@ -235,13 +235,12 @@ static void __cpuinit set_prefetch_parameters(void)
 	}
 	/*
 	 * Too much unrolling will overflow the available space in
-	 * clear_space_array / copy_page_array. 8 words sounds generous,
-	 * but a R4000 with 128 byte L2 line length can exceed even that.
+	 * clear_space_array / copy_page_array.
 	 */
-	half_clear_loop_size = min(8 * clear_word_size,
+	half_clear_loop_size = min(16 * clear_word_size,
 				   max(cache_line_size >> 1,
 				       4 * clear_word_size));
-	half_copy_loop_size = min(8 * copy_word_size,
+	half_copy_loop_size = min(16 * copy_word_size,
 				  max(cache_line_size >> 1,
 				      4 * copy_word_size));
 }
@@ -263,21 +262,23 @@ static inline void __cpuinit build_clear_pref(u32 **buf, int off)
 	if (pref_bias_clear_store) {
 		uasm_i_pref(buf, pref_dst_mode, pref_bias_clear_store + off,
 			    A0);
-	} else if (cpu_has_cache_cdex_s) {
-		uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0);
-	} else if (cpu_has_cache_cdex_p) {
-		if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) {
-			uasm_i_nop(buf);
-			uasm_i_nop(buf);
-			uasm_i_nop(buf);
-			uasm_i_nop(buf);
+	} else if (cache_line_size == (half_clear_loop_size << 1)) {
+		if (cpu_has_cache_cdex_s) {
+			uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0);
+		} else if (cpu_has_cache_cdex_p) {
+			if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) {
+				uasm_i_nop(buf);
+				uasm_i_nop(buf);
+				uasm_i_nop(buf);
+				uasm_i_nop(buf);
+			}
+
+			if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
+				uasm_i_lw(buf, ZERO, ZERO, AT);
+
+			uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0);
+		}
 		}
-
-		if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
-			uasm_i_lw(buf, ZERO, ZERO, AT);
-
-		uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0);
-	}
 }
 
 void __cpuinit build_clear_page(void)
@@ -403,20 +404,22 @@ static inline void build_copy_store_pref(u32 **buf, int off)
 	if (pref_bias_copy_store) {
 		uasm_i_pref(buf, pref_dst_mode, pref_bias_copy_store + off,
 			    A0);
-	} else if (cpu_has_cache_cdex_s) {
-		uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0);
-	} else if (cpu_has_cache_cdex_p) {
-		if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) {
-			uasm_i_nop(buf);
-			uasm_i_nop(buf);
-			uasm_i_nop(buf);
-			uasm_i_nop(buf);
+	} else if (cache_line_size == (half_copy_loop_size << 1)) {
+		if (cpu_has_cache_cdex_s) {
+			uasm_i_cache(buf, Create_Dirty_Excl_SD, off, A0);
+		} else if (cpu_has_cache_cdex_p) {
+			if (R4600_V1_HIT_CACHEOP_WAR && cpu_is_r4600_v1_x()) {
+				uasm_i_nop(buf);
+				uasm_i_nop(buf);
+				uasm_i_nop(buf);
+				uasm_i_nop(buf);
+			}
+
+			if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
+				uasm_i_lw(buf, ZERO, ZERO, AT);
+
+			uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0);
 		}
-
-		if (R4600_V2_HIT_CACHEOP_WAR && cpu_is_r4600_v2_x())
-			uasm_i_lw(buf, ZERO, ZERO, AT);
-
-		uasm_i_cache(buf, Create_Dirty_Excl_D, off, A0);
 	}
 }
 

arch/mips/mm/sc-rm7k.c

@@ -86,7 +86,7 @@ static void rm7k_sc_inv(unsigned long addr, unsigned long size)
 /*
  * This function is executed in uncached address space.
  */
-static __init void __rm7k_sc_enable(void)
+static __cpuinit void __rm7k_sc_enable(void)
 {
 	int i;
 
@@ -107,7 +107,7 @@ static __init void __rm7k_sc_enable(void)
 	}
 }
 
-static __init void rm7k_sc_enable(void)
+static __cpuinit void rm7k_sc_enable(void)
 {
 	if (read_c0_config() & RM7K_CONF_SE)
 		return;

arch/mips/sgi-ip32/ip32-irq.c

@@ -425,6 +425,11 @@ static void ip32_irq0(void)
 	BUILD_BUG_ON(MACEISA_SERIAL2_RDMAOR_IRQ - MACEISA_AUDIO_SW_IRQ != 31);
 
 	crime_int = crime->istat & crime_mask;
+
+	/* crime sometime delivers spurious interrupts, ignore them */
+	if (unlikely(crime_int == 0))
+		return;
+
 	irq = MACE_VID_IN1_IRQ + __ffs(crime_int);
 
 	if (crime_int & CRIME_MACEISA_INT_MASK) {

arch/mn10300/kernel/mn10300_ksyms.c

@@ -10,8 +10,11 @@
  */
 #include <linux/module.h>
 #include <asm/uaccess.h>
+#include <asm/pgtable.h>
 
 
+EXPORT_SYMBOL(empty_zero_page);
+
 EXPORT_SYMBOL(change_bit);
 EXPORT_SYMBOL(test_and_change_bit);
 
@@ -31,7 +34,9 @@ extern u64 __ashrdi3(u64, unsigned);
 extern u64 __ashldi3(u64, unsigned);
 extern u64 __lshrdi3(u64, unsigned);
 extern s64 __negdi2(s64);
+extern int __ucmpdi2(u64, u64);
 EXPORT_SYMBOL(__ashrdi3);
 EXPORT_SYMBOL(__ashldi3);
 EXPORT_SYMBOL(__lshrdi3);
 EXPORT_SYMBOL(__negdi2);
+EXPORT_SYMBOL(__ucmpdi2);

arch/mn10300/kernel/process.c

@@ -153,6 +153,7 @@ int kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 	return do_fork(flags | CLONE_VM | CLONE_UNTRACED, 0, &regs, 0,
 		       NULL, NULL);
 }
+EXPORT_SYMBOL(kernel_thread);
 
 /*
  * free current thread data structures etc..

arch/mn10300/lib/Makefile

@@ -4,4 +4,4 @@
 
 lib-y = delay.o usercopy.o checksum.o bitops.o memcpy.o memmove.o memset.o
 lib-y += do_csum.o
-lib-y += __ashldi3.o __ashrdi3.o __lshrdi3.o negdi2.o
+lib-y += __ashldi3.o __ashrdi3.o __lshrdi3.o negdi2.o __ucmpdi2.o

arch/mn10300/lib/__ucmpdi2.S

@@ -0,0 +1,43 @@
+/* __ucmpdi2.S: 64-bit unsigned compare
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+
+        .text
+        .p2align	4
+
+###############################################################################
+#
+# int __ucmpdi2(unsigned long long a [D0:D1],
+#		unsigned long long b [(SP,12),(SP,16)])
+#
+# - returns 0, 1, or 2 as a <, =, > b respectively.
+#
+###############################################################################
+        .globl		__ucmpdi2
+        .type		__ucmpdi2,@function
+__ucmpdi2:
+	mov		(12,sp),a0		# b.lsw
+	mov		(16,sp),a1		# b.msw
+
+	sub		a0,d0
+	subc		a1,d1			# may clear Z, never sets it
+	bne		__ucmpdi2_differ	# a.msw != b.msw
+	mov		+1,d0
+	rets
+
+__ucmpdi2_differ:
+	# C flag is set if LE, clear if GE
+	subc		d0,d0			# -1 if LE, 0 if GE
+	add		+1,d0			#  0 if LE, 1 if GE
+	add		d0,d0			#  0 if LE, 2 if GE
+	rets
+
+	.size		__ucmpdi2, .-__ucmpdi2

arch/powerpc/boot/Makefile

@@ -273,7 +273,8 @@ endif
 initrd-  := $(patsubst zImage%, zImage.initrd%, $(image-n) $(image-))
 initrd-y := $(patsubst zImage%, zImage.initrd%, \
 		$(patsubst dtbImage%, dtbImage.initrd%, \
-		$(patsubst treeImage%, treeImage.initrd%, $(image-y))))
+		$(patsubst simpleImage%, simpleImage.initrd%, \
+		$(patsubst treeImage%, treeImage.initrd%, $(image-y)))))
 initrd-y := $(filter-out $(image-y), $(initrd-y))
 targets	+= $(image-y) $(initrd-y)
 

arch/powerpc/kernel/legacy_serial.c

@@ -33,13 +33,14 @@ static struct legacy_serial_info {
 	phys_addr_t			taddr;
 } legacy_serial_infos[MAX_LEGACY_SERIAL_PORTS];
 
-static struct __initdata of_device_id parents[] = {
+static struct __initdata of_device_id legacy_serial_parents[] = {
 	{.type = "soc",},
 	{.type = "tsi-bridge",},
 	{.type = "opb", },
 	{.compatible = "ibm,opb",},
 	{.compatible = "simple-bus",},
 	{.compatible = "wrs,epld-localbus",},
+	{},
 };
 
 static unsigned int legacy_serial_count;
@@ -136,6 +137,11 @@ static int __init add_legacy_soc_port(struct device_node *np,
 	if (of_get_property(np, "clock-frequency", NULL) == NULL)
 		return -1;
 
+	/* if reg-shift or offset, don't try to use it */
+	if ((of_get_property(np, "reg-shift", NULL) != NULL) ||
+		(of_get_property(np, "reg-offset", NULL) != NULL))
+		return -1;
+
 	/* if rtas uses this device, don't try to use it as well */
 	if (of_get_property(np, "used-by-rtas", NULL) != NULL)
 		return -1;
@@ -322,7 +328,7 @@ void __init find_legacy_serial_ports(void)
 		struct device_node *parent = of_get_parent(np);
 		if (!parent)
 			continue;
-		if (of_match_node(parents, parent) != NULL) {
+		if (of_match_node(legacy_serial_parents, parent) != NULL) {
 			index = add_legacy_soc_port(np, np);
 			if (index >= 0 && np == stdout)
 				legacy_serial_console = index;

arch/powerpc/kernel/of_platform.c

@@ -76,6 +76,8 @@ struct of_device* of_platform_device_create(struct device_node *np,
 		return NULL;
 
 	dev->dma_mask = 0xffffffffUL;
+	dev->dev.coherent_dma_mask = DMA_32BIT_MASK;
+
 	dev->dev.bus = &of_platform_bus_type;
 
 	/* We do not fill the DMA ops for platform devices by default.

arch/powerpc/platforms/52xx/lite5200_pm.c

@@ -14,6 +14,7 @@ static struct mpc52xx_sdma __iomem *bes;
 static struct mpc52xx_xlb __iomem *xlb;
 static struct mpc52xx_gpio __iomem *gps;
 static struct mpc52xx_gpio_wkup __iomem *gpw;
+static void __iomem *pci;
 static void __iomem *sram;
 static const int sram_size = 0x4000;	/* 16 kBytes */
 static void __iomem *mbar;
@@ -50,6 +51,8 @@ static int lite5200_pm_prepare(void)
 		{ .type = "builtin", .compatible = "mpc5200", }, /* efika */
 		{}
 	};
+	u64 regaddr64 = 0;
+	const u32 *regaddr_p;
 
 	/* deep sleep? let mpc52xx code handle that */
 	if (lite5200_pm_target_state == PM_SUSPEND_STANDBY)
@@ -60,8 +63,12 @@ static int lite5200_pm_prepare(void)
 
 	/* map registers */
 	np = of_find_matching_node(NULL, immr_ids);
-	mbar = of_iomap(np, 0);
+	regaddr_p = of_get_address(np, 0, NULL, NULL);
+	if (regaddr_p)
+		regaddr64 = of_translate_address(np, regaddr_p);
 	of_node_put(np);
+
+	mbar = ioremap((u32) regaddr64, 0xC000);
 	if (!mbar) {
 		printk(KERN_ERR "%s:%i Error mapping registers\n", __func__, __LINE__);
 		return -ENOSYS;
@@ -71,6 +78,7 @@ static int lite5200_pm_prepare(void)
 	pic = mbar + 0x500;
 	gps = mbar + 0xb00;
 	gpw = mbar + 0xc00;
+	pci = mbar + 0xd00;
 	bes = mbar + 0x1200;
 	xlb = mbar + 0x1f00;
 	sram = mbar + 0x8000;
@@ -85,6 +93,7 @@ static struct mpc52xx_sdma sbes;
 static struct mpc52xx_xlb sxlb;
 static struct mpc52xx_gpio sgps;
 static struct mpc52xx_gpio_wkup sgpw;
+static char spci[0x200];
 
 static void lite5200_save_regs(void)
 {
@@ -94,6 +103,7 @@ static void lite5200_save_regs(void)
 	_memcpy_fromio(&sxlb, xlb, sizeof(*xlb));
 	_memcpy_fromio(&sgps, gps, sizeof(*gps));
 	_memcpy_fromio(&sgpw, gpw, sizeof(*gpw));
+	_memcpy_fromio(spci, pci, 0x200);
 
 	_memcpy_fromio(saved_sram, sram, sram_size);
 }
@@ -103,6 +113,8 @@ static void lite5200_restore_regs(void)
 	int i;
 	_memcpy_toio(sram, saved_sram, sram_size);
 
+	/* PCI Configuration */
+	_memcpy_toio(pci, spci, 0x200);
 
 	/*
 	 * GPIOs. Interrupt Master Enable has higher address then other

arch/um/Makefile

@@ -77,7 +77,6 @@ include $(srctree)/$(ARCH_DIR)/Makefile-os-$(OS)
 KERNEL_DEFINES = $(strip -Derrno=kernel_errno -Dsigprocmask=kernel_sigprocmask \
 			 -Dmktime=kernel_mktime $(ARCH_KERNEL_DEFINES))
 KBUILD_CFLAGS += $(KERNEL_DEFINES)
-KBUILD_CFLAGS += $(call cc-option,-fno-unit-at-a-time,)
 
 PHONY += linux
 

arch/um/Makefile-i386

@@ -32,4 +32,11 @@ cflags-y += $(call cc-option,-mpreferred-stack-boundary=2)
 # an unresolved reference.
 cflags-y += -ffreestanding
 
+# Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
+# a lot more stack due to the lack of sharing of stacklots.  Also, gcc
+# 4.3.0 needs -funit-at-a-time for extern inline functions.
+KBUILD_CFLAGS += $(shell if [ $(call cc-version) -lt 0400 ] ; then \
+			echo $(call cc-option,-fno-unit-at-a-time); \
+			else echo $(call cc-option,-funit-at-a-time); fi ;)
+
 KBUILD_CFLAGS += $(cflags-y)

arch/um/Makefile-x86_64

@@ -21,3 +21,6 @@ HEADER_ARCH := x86
 
 LINK-$(CONFIG_LD_SCRIPT_DYN) += -Wl,-rpath,/lib64
 LINK-y += -m64
+
+# Do unit-at-a-time unconditionally on x86_64, following the host
+KBUILD_CFLAGS += $(call cc-option,-funit-at-a-time)

arch/x86/Kconfig

@@ -383,6 +383,7 @@ config VMI
 config KVM_CLOCK
 	bool "KVM paravirtualized clock"
 	select PARAVIRT
+	select PARAVIRT_CLOCK
 	depends on !(X86_VISWS || X86_VOYAGER)
 	help
 	  Turning on this option will allow you to run a paravirtualized clock
@@ -410,6 +411,10 @@ config PARAVIRT
 	  over full virtualization.  However, when run without a hypervisor
 	  the kernel is theoretically slower and slightly larger.
 
+config PARAVIRT_CLOCK
+	bool
+	default n
+
 endif
 
 config MEMTEST_BOOTPARAM
@@ -961,8 +966,8 @@ config NUMA_EMU
 	  number of nodes. This is only useful for debugging.
 
 config NODES_SHIFT
-	int "Max num nodes shift(1-15)"
-	range 1 15  if X86_64
+	int "Max num nodes shift(1-9)"
+	range 1 9  if X86_64
 	default "6" if X86_64
 	default "4" if X86_NUMAQ
 	default "3"

arch/x86/kernel/.gitignore

@@ -1,2 +1,3 @@
 vsyscall.lds
 vsyscall_32.lds
+vmlinux.lds

arch/x86/kernel/Makefile

@@ -82,6 +82,7 @@ obj-$(CONFIG_VMI)		+= vmi_32.o vmiclock_32.o
 obj-$(CONFIG_KVM_GUEST)		+= kvm.o
 obj-$(CONFIG_KVM_CLOCK)		+= kvmclock.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirt_patch_$(BITS).o
+obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
 
 obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
 

arch/x86/kernel/acpi/realmode/wakeup.S

@@ -5,6 +5,7 @@
 #include <asm/msr-index.h>
 #include <asm/page.h>
 #include <asm/pgtable.h>
+#include <asm/processor-flags.h>
 
 	.code16
 	.section ".header", "a"
@@ -24,6 +25,11 @@ pmode_gdt:	.quad	0
 realmode_flags:	.long	0
 real_magic:	.long	0
 trampoline_segment:	.word 0
+_pad1:		.byte	0
+wakeup_jmp:	.byte	0xea	/* ljmpw */
+wakeup_jmp_off:	.word	3f
+wakeup_jmp_seg:	.word	0
+wakeup_gdt:	.quad	0, 0, 0
 signature:	.long	0x51ee1111
 
 	.text
@@ -34,11 +40,34 @@ _start:
 	cli
 	cld
 
+	/* Apparently some dimwit BIOS programmers don't know how to
+	   program a PM to RM transition, and we might end up here with
+	   junk in the data segment descriptor registers.  The only way
+	   to repair that is to go into PM and fix it ourselves... */
+	movw	$16, %cx
+	lgdtl	%cs:wakeup_gdt
+	movl	%cr0, %eax
+	orb	$X86_CR0_PE, %al
+	movl	%eax, %cr0
+	jmp	1f
+1:	ljmpw	$8, $2f
+2:
+	movw	%cx, %ds
+	movw	%cx, %es
+	movw	%cx, %ss
+	movw	%cx, %fs
+	movw	%cx, %gs
+
+	andb	$~X86_CR0_PE, %al
+	movl	%eax, %cr0
+	jmp	wakeup_jmp
+3:
 	/* Set up segments */
 	movw	%cs, %ax
 	movw	%ax, %ds
 	movw	%ax, %es
 	movw	%ax, %ss
+	lidtl	wakeup_idt
 
 	movl	$wakeup_stack_end, %esp
 
@@ -98,7 +127,14 @@ bogus_real_magic:
 	jmp	1b
 
 	.data
-	.balign	4
+	.balign	8
+
+	/* This is the standard real-mode IDT */
+wakeup_idt:
+	.word	0xffff		/* limit */
+	.long	0		/* address */
+	.word	0
+
 	.globl	HEAP, heap_end
 HEAP:
 	.long	wakeup_heap

arch/x86/kernel/acpi/realmode/wakeup.h

@@ -24,6 +24,11 @@ struct wakeup_header {
 	u32 realmode_flags;
 	u32 real_magic;
 	u16 trampoline_segment;	/* segment with trampoline code, 64-bit only */
+	u8  _pad1;
+	u8  wakeup_jmp;
+	u16 wakeup_jmp_off;
+	u16 wakeup_jmp_seg;
+	u64 wakeup_gdt[3];
 	u32 signature;		/* To check we have correct structure */
 } __attribute__((__packed__));
 

arch/x86/kernel/acpi/sleep.c

@@ -50,6 +50,20 @@ int acpi_save_state_mem(void)
 
 	header->video_mode = saved_video_mode;
 
+	header->wakeup_jmp_seg = acpi_wakeup_address >> 4;
+	/* GDT[0]: GDT self-pointer */
+	header->wakeup_gdt[0] =
+		(u64)(sizeof(header->wakeup_gdt) - 1) +
+		((u64)(acpi_wakeup_address +
+			((char *)&header->wakeup_gdt - (char *)acpi_realmode))
+				<< 16);
+	/* GDT[1]: real-mode-like code segment */
+	header->wakeup_gdt[1] = (0x009bULL << 40) +
+		((u64)acpi_wakeup_address << 16) + 0xffff;
+	/* GDT[2]: real-mode-like data segment */
+	header->wakeup_gdt[2] = (0x0093ULL << 40) +
+		((u64)acpi_wakeup_address << 16) + 0xffff;
+
 #ifndef CONFIG_64BIT
 	store_gdt((struct desc_ptr *)&header->pmode_gdt);
 
@@ -111,7 +125,7 @@ void __init acpi_reserve_bootmem(void)
 		return;
 	}
 
-	acpi_wakeup_address = acpi_realmode;
+	acpi_wakeup_address = virt_to_phys((void *)acpi_realmode);
 }
 
 

arch/x86/kernel/efi_32.c

@@ -49,13 +49,13 @@ void efi_call_phys_prelog(void)
 	local_irq_save(efi_rt_eflags);
 
 	/*
-	 * If I don't have PSE, I should just duplicate two entries in page
-	 * directory. If I have PSE, I just need to duplicate one entry in
+	 * If I don't have PAE, I should just duplicate two entries in page
+	 * directory. If I have PAE, I just need to duplicate one entry in
 	 * page directory.
 	 */
 	cr4 = read_cr4();
 
-	if (cr4 & X86_CR4_PSE) {
+	if (cr4 & X86_CR4_PAE) {
 		efi_bak_pg_dir_pointer[0].pgd =
 		    swapper_pg_dir[pgd_index(0)].pgd;
 		swapper_pg_dir[0].pgd =
@@ -93,7 +93,7 @@ void efi_call_phys_epilog(void)
 
 	cr4 = read_cr4();
 
-	if (cr4 & X86_CR4_PSE) {
+	if (cr4 & X86_CR4_PAE) {
 		swapper_pg_dir[pgd_index(0)].pgd =
 		    efi_bak_pg_dir_pointer[0].pgd;
 	} else {

arch/x86/kernel/head_64.S

@@ -128,7 +128,7 @@ ident_complete:
 	/* Fixup phys_base */
 	addq	%rbp, phys_base(%rip)
 
-#ifdef CONFIG_SMP
+#ifdef CONFIG_X86_TRAMPOLINE
 	addq	%rbp, trampoline_level4_pgt + 0(%rip)
 	addq	%rbp, trampoline_level4_pgt + (511*8)(%rip)
 #endif

arch/x86/kernel/i387.c

@@ -162,7 +162,7 @@ int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
 	int ret;
 
 	if (!cpu_has_fxsr)
-		return -ENODEV;
+		return -EIO;
 
 	ret = init_fpu(target);
 	if (ret)
@@ -179,7 +179,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
 	int ret;
 
 	if (!cpu_has_fxsr)
-		return -ENODEV;
+		return -EIO;
 
 	ret = init_fpu(target);
 	if (ret)

arch/x86/kernel/kvmclock.c

@@ -18,6 +18,7 @@
 
 #include <linux/clocksource.h>
 #include <linux/kvm_para.h>
+#include <asm/pvclock.h>
 #include <asm/arch_hooks.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
@@ -36,18 +37,9 @@ static int parse_no_kvmclock(char *arg)
 early_param("no-kvmclock", parse_no_kvmclock);
 
 /* The hypervisor will put information about time periodically here */
-static DEFINE_PER_CPU_SHARED_ALIGNED(struct kvm_vcpu_time_info, hv_clock);
-#define get_clock(cpu, field) per_cpu(hv_clock, cpu).field
+static DEFINE_PER_CPU_SHARED_ALIGNED(struct pvclock_vcpu_time_info, hv_clock);
+static struct pvclock_wall_clock wall_clock;
 
-static inline u64 kvm_get_delta(u64 last_tsc)
-{
-	int cpu = smp_processor_id();
-	u64 delta = native_read_tsc() - last_tsc;
-	return (delta * get_clock(cpu, tsc_to_system_mul)) >> KVM_SCALE;
-}
-
-static struct kvm_wall_clock wall_clock;
-static cycle_t kvm_clock_read(void);
 /*
  * The wallclock is the time of day when we booted. Since then, some time may
  * have elapsed since the hypervisor wrote the data. So we try to account for
@@ -55,64 +47,37 @@ static cycle_t kvm_clock_read(void);
  */
 static unsigned long kvm_get_wallclock(void)
 {
-	u32 wc_sec, wc_nsec;
-	u64 delta;
+	struct pvclock_vcpu_time_info *vcpu_time;
 	struct timespec ts;
-	int version, nsec;
 	int low, high;
 
 	low = (int)__pa(&wall_clock);
 	high = ((u64)__pa(&wall_clock) >> 32);
-
-	delta = kvm_clock_read();
-
 	native_write_msr(MSR_KVM_WALL_CLOCK, low, high);
-	do {
-		version = wall_clock.wc_version;
-		rmb();
-		wc_sec = wall_clock.wc_sec;
-		wc_nsec = wall_clock.wc_nsec;
-		rmb();
-	} while ((wall_clock.wc_version != version) || (version & 1));
 
-	delta = kvm_clock_read() - delta;
-	delta += wc_nsec;
-	nsec = do_div(delta, NSEC_PER_SEC);
-	set_normalized_timespec(&ts, wc_sec + delta, nsec);
-	/*
-	 * Of all mechanisms of time adjustment I've tested, this one
-	 * was the champion!
-	 */
-	return ts.tv_sec + 1;
+	vcpu_time = &get_cpu_var(hv_clock);
+	pvclock_read_wallclock(&wall_clock, vcpu_time, &ts);
+	put_cpu_var(hv_clock);
+
+	return ts.tv_sec;
 }
 
 static int kvm_set_wallclock(unsigned long now)
 {
-	return 0;
+	return -1;
 }
 
-/*
- * This is our read_clock function. The host puts an tsc timestamp each time
- * it updates a new time. Without the tsc adjustment, we can have a situation
- * in which a vcpu starts to run earlier (smaller system_time), but probes
- * time later (compared to another vcpu), leading to backwards time
- */
 static cycle_t kvm_clock_read(void)
 {
-	u64 last_tsc, now;
-	int cpu;
+	struct pvclock_vcpu_time_info *src;
+	cycle_t ret;
 
-	preempt_disable();
-	cpu = smp_processor_id();
-
-	last_tsc = get_clock(cpu, tsc_timestamp);
-	now = get_clock(cpu, system_time);
-
-	now += kvm_get_delta(last_tsc);
-	preempt_enable();
-
-	return now;
+	src = &get_cpu_var(hv_clock);
+	ret = pvclock_clocksource_read(src);
+	put_cpu_var(hv_clock);
+	return ret;
 }
+
 static struct clocksource kvm_clock = {
 	.name = "kvm-clock",
 	.read = kvm_clock_read,
@@ -123,13 +88,14 @@ static struct clocksource kvm_clock = {
 	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
-static int kvm_register_clock(void)
+static int kvm_register_clock(char *txt)
 {
 	int cpu = smp_processor_id();
 	int low, high;
 	low = (int)__pa(&per_cpu(hv_clock, cpu)) | 1;
 	high = ((u64)__pa(&per_cpu(hv_clock, cpu)) >> 32);
-
+	printk(KERN_INFO "kvm-clock: cpu %d, msr %x:%x, %s\n",
+	       cpu, high, low, txt);
 	return native_write_msr_safe(MSR_KVM_SYSTEM_TIME, low, high);
 }
 
@@ -140,12 +106,20 @@ static void kvm_setup_secondary_clock(void)
 	 * Now that the first cpu already had this clocksource initialized,
 	 * we shouldn't fail.
 	 */
-	WARN_ON(kvm_register_clock());
+	WARN_ON(kvm_register_clock("secondary cpu clock"));
 	/* ok, done with our trickery, call native */
 	setup_secondary_APIC_clock();
 }
 #endif
 
+#ifdef CONFIG_SMP
+void __init kvm_smp_prepare_boot_cpu(void)
+{
+	WARN_ON(kvm_register_clock("primary cpu clock"));
+	native_smp_prepare_boot_cpu();
+}
+#endif
+
 /*
  * After the clock is registered, the host will keep writing to the
  * registered memory location. If the guest happens to shutdown, this memory
@@ -174,13 +148,16 @@ void __init kvmclock_init(void)
 		return;
 
 	if (kvmclock && kvm_para_has_feature(KVM_FEATURE_CLOCKSOURCE)) {
-		if (kvm_register_clock())
+		if (kvm_register_clock("boot clock"))
 			return;
 		pv_time_ops.get_wallclock = kvm_get_wallclock;
 		pv_time_ops.set_wallclock = kvm_set_wallclock;
 		pv_time_ops.sched_clock = kvm_clock_read;
 #ifdef CONFIG_X86_LOCAL_APIC
 		pv_apic_ops.setup_secondary_clock = kvm_setup_secondary_clock;
+#endif
+#ifdef CONFIG_SMP
+		smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
 #endif
 		machine_ops.shutdown  = kvm_shutdown;
 #ifdef CONFIG_KEXEC

arch/x86/kernel/pvclock.c

@@ -0,0 +1,141 @@
+/*  paravirtual clock -- common code used by kvm/xen
+
+    This program is free software; you can redistribute it and/or modify
+    it under the terms of the GNU General Public License as published by
+    the Free Software Foundation; either version 2 of the License, or
+    (at your option) any later version.
+
+    This program is distributed in the hope that it will be useful,
+    but WITHOUT ANY WARRANTY; without even the implied warranty of
+    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+    GNU General Public License for more details.
+
+    You should have received a copy of the GNU General Public License
+    along with this program; if not, write to the Free Software
+    Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+*/
+
+#include <linux/kernel.h>
+#include <linux/percpu.h>
+#include <asm/pvclock.h>
+
+/*
+ * These are perodically updated
+ *    xen: magic shared_info page
+ *    kvm: gpa registered via msr
+ * and then copied here.
+ */
+struct pvclock_shadow_time {
+	u64 tsc_timestamp;     /* TSC at last update of time vals.  */
+	u64 system_timestamp;  /* Time, in nanosecs, since boot.    */
+	u32 tsc_to_nsec_mul;
+	int tsc_shift;
+	u32 version;
+};
+
+/*
+ * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
+ * yielding a 64-bit result.
+ */
+static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
+{
+	u64 product;
+#ifdef __i386__
+	u32 tmp1, tmp2;
+#endif
+
+	if (shift < 0)
+		delta >>= -shift;
+	else
+		delta <<= shift;
+
+#ifdef __i386__
+	__asm__ (
+		"mul  %5       ; "
+		"mov  %4,%%eax ; "
+		"mov  %%edx,%4 ; "
+		"mul  %5       ; "
+		"xor  %5,%5    ; "
+		"add  %4,%%eax ; "
+		"adc  %5,%%edx ; "
+		: "=A" (product), "=r" (tmp1), "=r" (tmp2)
+		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
+#elif __x86_64__
+	__asm__ (
+		"mul %%rdx ; shrd $32,%%rdx,%%rax"
+		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
+#else
+#error implement me!
+#endif
+
+	return product;
+}
+
+static u64 pvclock_get_nsec_offset(struct pvclock_shadow_time *shadow)
+{
+	u64 delta = native_read_tsc() - shadow->tsc_timestamp;
+	return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift);
+}
+
+/*
+ * Reads a consistent set of time-base values from hypervisor,
+ * into a shadow data area.
+ */
+static unsigned pvclock_get_time_values(struct pvclock_shadow_time *dst,
+					struct pvclock_vcpu_time_info *src)
+{
+	do {
+		dst->version = src->version;
+		rmb();		/* fetch version before data */
+		dst->tsc_timestamp     = src->tsc_timestamp;
+		dst->system_timestamp  = src->system_time;
+		dst->tsc_to_nsec_mul   = src->tsc_to_system_mul;
+		dst->tsc_shift         = src->tsc_shift;
+		rmb();		/* test version after fetching data */
+	} while ((src->version & 1) || (dst->version != src->version));
+
+	return dst->version;
+}
+
+cycle_t pvclock_clocksource_read(struct pvclock_vcpu_time_info *src)
+{
+	struct pvclock_shadow_time shadow;
+	unsigned version;
+	cycle_t ret, offset;
+
+	do {
+		version = pvclock_get_time_values(&shadow, src);
+		barrier();
+		offset = pvclock_get_nsec_offset(&shadow);
+		ret = shadow.system_timestamp + offset;
+		barrier();
+	} while (version != src->version);
+
+	return ret;
+}
+
+void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock,
+			    struct pvclock_vcpu_time_info *vcpu_time,
+			    struct timespec *ts)
+{
+	u32 version;
+	u64 delta;
+	struct timespec now;
+
+	/* get wallclock at system boot */
+	do {
+		version = wall_clock->version;
+		rmb();		/* fetch version before time */
+		now.tv_sec  = wall_clock->sec;
+		now.tv_nsec = wall_clock->nsec;
+		rmb();		/* fetch time before checking version */
+	} while ((wall_clock->version & 1) || (version != wall_clock->version));
+
+	delta = pvclock_clocksource_read(vcpu_time);	/* time since system boot */
+	delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
+
+	now.tv_nsec = do_div(delta, NSEC_PER_SEC);
+	now.tv_sec = delta;
+
+	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
+}

arch/x86/kernel/smpboot.c

@@ -996,7 +996,6 @@ do_rest:
 #endif
 		cpu_clear(cpu, cpu_callout_map); /* was set by do_boot_cpu() */
 		cpu_clear(cpu, cpu_initialized); /* was set by cpu_init() */
-		cpu_clear(cpu, cpu_possible_map);
 		cpu_clear(cpu, cpu_present_map);
 		per_cpu(x86_cpu_to_apicid, cpu) = BAD_APICID;
 	}

arch/x86/kvm/i8254.c

@@ -200,9 +200,12 @@ int __pit_timer_fn(struct kvm_kpit_state *ps)
 
 	atomic_inc(&pt->pending);
 	smp_mb__after_atomic_inc();
-	if (vcpu0 && waitqueue_active(&vcpu0->wq)) {
-		vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
-		wake_up_interruptible(&vcpu0->wq);
+	if (vcpu0) {
+		set_bit(KVM_REQ_PENDING_TIMER, &vcpu0->requests);
+		if (waitqueue_active(&vcpu0->wq)) {
+			vcpu0->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+			wake_up_interruptible(&vcpu0->wq);
+		}
 	}
 
 	pt->timer.expires = ktime_add_ns(pt->timer.expires, pt->period);

arch/x86/kvm/lapic.c

@@ -940,6 +940,7 @@ static int __apic_timer_fn(struct kvm_lapic *apic)
 	wait_queue_head_t *q = &apic->vcpu->wq;
 
 	atomic_inc(&apic->timer.pending);
+	set_bit(KVM_REQ_PENDING_TIMER, &apic->vcpu->requests);
 	if (waitqueue_active(q)) {
 		apic->vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
 		wake_up_interruptible(q);

arch/x86/kvm/mmu.c

@@ -640,6 +640,7 @@ static void rmap_write_protect(struct kvm *kvm, u64 gfn)
 			rmap_remove(kvm, spte);
 			--kvm->stat.lpages;
 			set_shadow_pte(spte, shadow_trap_nonpresent_pte);
+			spte = NULL;
 			write_protected = 1;
 		}
 		spte = rmap_next(kvm, rmapp, spte);
@@ -1082,10 +1083,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		struct kvm_mmu_page *shadow;
 
 		spte |= PT_WRITABLE_MASK;
-		if (user_fault) {
-			mmu_unshadow(vcpu->kvm, gfn);
-			goto unshadowed;
-		}
 
 		shadow = kvm_mmu_lookup_page(vcpu->kvm, gfn);
 		if (shadow ||
@@ -1102,8 +1099,6 @@ static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *shadow_pte,
 		}
 	}
 
-unshadowed:
-
 	if (pte_access & ACC_WRITE_MASK)
 		mark_page_dirty(vcpu->kvm, gfn);
 
@@ -1580,11 +1575,13 @@ static void mmu_pte_write_new_pte(struct kvm_vcpu *vcpu,
 				  u64 *spte,
 				  const void *new)
 {
-	if ((sp->role.level != PT_PAGE_TABLE_LEVEL)
-	    && !vcpu->arch.update_pte.largepage) {
-		++vcpu->kvm->stat.mmu_pde_zapped;
-		return;
-	}
+	if (sp->role.level != PT_PAGE_TABLE_LEVEL) {
+		if (!vcpu->arch.update_pte.largepage ||
+		    sp->role.glevels == PT32_ROOT_LEVEL) {
+			++vcpu->kvm->stat.mmu_pde_zapped;
+			return;
+		}
+        }
 
 	++vcpu->kvm->stat.mmu_pte_updated;
 	if (sp->role.glevels == PT32_ROOT_LEVEL)

arch/x86/kvm/vmx.c

@@ -566,7 +566,7 @@ static void vmx_save_host_state(struct kvm_vcpu *vcpu)
 	load_transition_efer(vmx);
 }
 
-static void vmx_load_host_state(struct vcpu_vmx *vmx)
+static void __vmx_load_host_state(struct vcpu_vmx *vmx)
 {
 	unsigned long flags;
 
@@ -596,6 +596,13 @@ static void vmx_load_host_state(struct vcpu_vmx *vmx)
 	reload_host_efer(vmx);
 }
 
+static void vmx_load_host_state(struct vcpu_vmx *vmx)
+{
+	preempt_disable();
+	__vmx_load_host_state(vmx);
+	preempt_enable();
+}
+
 /*
  * Switches to specified vcpu, until a matching vcpu_put(), but assumes
  * vcpu mutex is already taken.
@@ -654,7 +661,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 static void vmx_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	vmx_load_host_state(to_vmx(vcpu));
+	__vmx_load_host_state(to_vmx(vcpu));
 }
 
 static void vmx_fpu_activate(struct kvm_vcpu *vcpu)
@@ -884,11 +891,8 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 	switch (msr_index) {
 #ifdef CONFIG_X86_64
 	case MSR_EFER:
+		vmx_load_host_state(vmx);
 		ret = kvm_set_msr_common(vcpu, msr_index, data);
-		if (vmx->host_state.loaded) {
-			reload_host_efer(vmx);
-			load_transition_efer(vmx);
-		}
 		break;
 	case MSR_FS_BASE:
 		vmcs_writel(GUEST_FS_BASE, data);
@@ -910,11 +914,10 @@ static int vmx_set_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 		guest_write_tsc(data);
 		break;
 	default:
+		vmx_load_host_state(vmx);
 		msr = find_msr_entry(vmx, msr_index);
 		if (msr) {
 			msr->data = data;
-			if (vmx->host_state.loaded)
-				load_msrs(vmx->guest_msrs, vmx->save_nmsrs);
 			break;
 		}
 		ret = kvm_set_msr_common(vcpu, msr_index, data);

arch/x86/kvm/x86.c

@@ -492,8 +492,8 @@ static int do_set_msr(struct kvm_vcpu *vcpu, unsigned index, u64 *data)
 static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 {
 	static int version;
-	struct kvm_wall_clock wc;
-	struct timespec wc_ts;
+	struct pvclock_wall_clock wc;
+	struct timespec now, sys, boot;
 
 	if (!wall_clock)
 		return;
@@ -502,10 +502,19 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 
 	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
 
-	wc_ts = current_kernel_time();
-	wc.wc_sec = wc_ts.tv_sec;
-	wc.wc_nsec = wc_ts.tv_nsec;
-	wc.wc_version = version;
+	/*
+	 * The guest calculates current wall clock time by adding
+	 * system time (updated by kvm_write_guest_time below) to the
+	 * wall clock specified here.  guest system time equals host
+	 * system time for us, thus we must fill in host boot time here.
+	 */
+	now = current_kernel_time();
+	ktime_get_ts(&sys);
+	boot = ns_to_timespec(timespec_to_ns(&now) - timespec_to_ns(&sys));
+
+	wc.sec = boot.tv_sec;
+	wc.nsec = boot.tv_nsec;
+	wc.version = version;
 
 	kvm_write_guest(kvm, wall_clock, &wc, sizeof(wc));
 
@@ -513,6 +522,45 @@ static void kvm_write_wall_clock(struct kvm *kvm, gpa_t wall_clock)
 	kvm_write_guest(kvm, wall_clock, &version, sizeof(version));
 }
 
+static uint32_t div_frac(uint32_t dividend, uint32_t divisor)
+{
+	uint32_t quotient, remainder;
+
+	/* Don't try to replace with do_div(), this one calculates
+	 * "(dividend << 32) / divisor" */
+	__asm__ ( "divl %4"
+		  : "=a" (quotient), "=d" (remainder)
+		  : "0" (0), "1" (dividend), "r" (divisor) );
+	return quotient;
+}
+
+static void kvm_set_time_scale(uint32_t tsc_khz, struct pvclock_vcpu_time_info *hv_clock)
+{
+	uint64_t nsecs = 1000000000LL;
+	int32_t  shift = 0;
+	uint64_t tps64;
+	uint32_t tps32;
+
+	tps64 = tsc_khz * 1000LL;
+	while (tps64 > nsecs*2) {
+		tps64 >>= 1;
+		shift--;
+	}
+
+	tps32 = (uint32_t)tps64;
+	while (tps32 <= (uint32_t)nsecs) {
+		tps32 <<= 1;
+		shift++;
+	}
+
+	hv_clock->tsc_shift = shift;
+	hv_clock->tsc_to_system_mul = div_frac(nsecs, tps32);
+
+	pr_debug("%s: tsc_khz %u, tsc_shift %d, tsc_mul %u\n",
+		 __FUNCTION__, tsc_khz, hv_clock->tsc_shift,
+		 hv_clock->tsc_to_system_mul);
+}
+
 static void kvm_write_guest_time(struct kvm_vcpu *v)
 {
 	struct timespec ts;
@@ -523,6 +571,11 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	if ((!vcpu->time_page))
 		return;
 
+	if (unlikely(vcpu->hv_clock_tsc_khz != tsc_khz)) {
+		kvm_set_time_scale(tsc_khz, &vcpu->hv_clock);
+		vcpu->hv_clock_tsc_khz = tsc_khz;
+	}
+
 	/* Keep irq disabled to prevent changes to the clock */
 	local_irq_save(flags);
 	kvm_get_msr(v, MSR_IA32_TIME_STAMP_COUNTER,
@@ -537,14 +590,14 @@ static void kvm_write_guest_time(struct kvm_vcpu *v)
 	/*
 	 * The interface expects us to write an even number signaling that the
 	 * update is finished. Since the guest won't see the intermediate
-	 * state, we just write "2" at the end
+	 * state, we just increase by 2 at the end.
 	 */
-	vcpu->hv_clock.version = 2;
+	vcpu->hv_clock.version += 2;
 
 	shared_kaddr = kmap_atomic(vcpu->time_page, KM_USER0);
 
 	memcpy(shared_kaddr + vcpu->time_offset, &vcpu->hv_clock,
-		sizeof(vcpu->hv_clock));
+	       sizeof(vcpu->hv_clock));
 
 	kunmap_atomic(shared_kaddr, KM_USER0);
 
@@ -599,10 +652,6 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 		/* ...but clean it before doing the actual write */
 		vcpu->arch.time_offset = data & ~(PAGE_MASK | 1);
 
-		vcpu->arch.hv_clock.tsc_to_system_mul =
-					clocksource_khz2mult(tsc_khz, 22);
-		vcpu->arch.hv_clock.tsc_shift = 22;
-
 		down_read(&current->mm->mmap_sem);
 		vcpu->arch.time_page =
 				gfn_to_page(vcpu->kvm, data >> PAGE_SHIFT);
@@ -2759,6 +2808,8 @@ again:
 	if (vcpu->requests) {
 		if (test_and_clear_bit(KVM_REQ_MIGRATE_TIMER, &vcpu->requests))
 			__kvm_migrate_timers(vcpu);
+		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
+			kvm_x86_ops->tlb_flush(vcpu);
 		if (test_and_clear_bit(KVM_REQ_REPORT_TPR_ACCESS,
 				       &vcpu->requests)) {
 			kvm_run->exit_reason = KVM_EXIT_TPR_ACCESS;
@@ -2772,6 +2823,7 @@ again:
 		}
 	}
 
+	clear_bit(KVM_REQ_PENDING_TIMER, &vcpu->requests);
 	kvm_inject_pending_timer_irqs(vcpu);
 
 	preempt_disable();
@@ -2781,21 +2833,13 @@ again:
 
 	local_irq_disable();
 
-	if (need_resched()) {
+	if (vcpu->requests || need_resched()) {
 		local_irq_enable();
 		preempt_enable();
 		r = 1;
 		goto out;
 	}
 
-	if (vcpu->requests)
-		if (test_bit(KVM_REQ_MMU_RELOAD, &vcpu->requests)) {
-			local_irq_enable();
-			preempt_enable();
-			r = 1;
-			goto out;
-		}
-
 	if (signal_pending(current)) {
 		local_irq_enable();
 		preempt_enable();
@@ -2825,9 +2869,6 @@ again:
 
 	kvm_guest_enter();
 
-	if (vcpu->requests)
-		if (test_and_clear_bit(KVM_REQ_TLB_FLUSH, &vcpu->requests))
-			kvm_x86_ops->tlb_flush(vcpu);
 
 	KVMTRACE_0D(VMENTRY, vcpu, entryexit);
 	kvm_x86_ops->run(vcpu, kvm_run);

arch/x86/mm/init_64.c

@@ -135,7 +135,7 @@ static __init void *spp_getpage(void)
 	return ptr;
 }
 
-static void
+static __init void
 set_pte_phys(unsigned long vaddr, unsigned long phys, pgprot_t prot)
 {
 	pgd_t *pgd;
@@ -214,7 +214,7 @@ void __init cleanup_highmap(void)
 }
 
 /* NOTE: this is meant to be run only at boot */
-void __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
+void __init __set_fixmap(enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
 {
 	unsigned long address = __fix_to_virt(idx);
 
@@ -526,7 +526,8 @@ static void __init early_memtest(unsigned long start, unsigned long end)
 				t_size = end - t_start;
 
 			printk(KERN_CONT "\n  %016llx - %016llx pattern %d",
-				t_start, t_start + t_size, pattern);
+				(unsigned long long)t_start,
+				(unsigned long long)t_start + t_size, pattern);
 
 			memtest(t_start, t_size, pattern);
 

arch/x86/mm/ioremap.c

@@ -300,6 +300,29 @@ void __iomem *ioremap_cache(resource_size_t phys_addr, unsigned long size)
 }
 EXPORT_SYMBOL(ioremap_cache);
 
+static void __iomem *ioremap_default(resource_size_t phys_addr,
+					unsigned long size)
+{
+	unsigned long flags;
+	void *ret;
+	int err;
+
+	/*
+	 * - WB for WB-able memory and no other conflicting mappings
+	 * - UC_MINUS for non-WB-able memory with no other conflicting mappings
+	 * - Inherit from confliting mappings otherwise
+	 */
+	err = reserve_memtype(phys_addr, phys_addr + size, -1, &flags);
+	if (err < 0)
+		return NULL;
+
+	ret = (void *) __ioremap_caller(phys_addr, size, flags,
+					__builtin_return_address(0));
+
+	free_memtype(phys_addr, phys_addr + size);
+	return (void __iomem *)ret;
+}
+
 /**
  * iounmap - Free a IO remapping
  * @addr: virtual address from ioremap_*
@@ -365,7 +388,7 @@ void *xlate_dev_mem_ptr(unsigned long phys)
 	if (page_is_ram(start >> PAGE_SHIFT))
 		return __va(phys);
 
-	addr = (void *)ioremap(start, PAGE_SIZE);
+	addr = (void *)ioremap_default(start, PAGE_SIZE);
 	if (addr)
 		addr = (void *)((unsigned long)addr | (phys & ~PAGE_MASK));
 

arch/x86/pci/common.c

@@ -328,18 +328,18 @@ static struct dmi_system_id __devinitdata pciprobe_dmi_table[] = {
 #endif
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL360",
+		.ident = "HP ProLiant DL385 G2",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL360"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL385 G2"),
 		},
 	},
 	{
 		.callback = set_bf_sort,
-		.ident = "HP ProLiant DL380",
+		.ident = "HP ProLiant DL585 G2",
 		.matches = {
 			DMI_MATCH(DMI_SYS_VENDOR, "HP"),
-			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL380"),
+			DMI_MATCH(DMI_PRODUCT_NAME, "ProLiant DL585 G2"),
 		},
 	},
 	{}

arch/x86/xen/Kconfig

@@ -5,8 +5,9 @@
 config XEN
 	bool "Xen guest support"
 	select PARAVIRT
+	select PARAVIRT_CLOCK
 	depends on X86_32
-	depends on X86_CMPXCHG && X86_TSC && !(X86_VISWS || X86_VOYAGER)
+	depends on X86_CMPXCHG && X86_TSC && X86_PAE && !(X86_VISWS || X86_VOYAGER)
 	help
 	  This is the Linux Xen port.  Enabling this will allow the
 	  kernel to boot in a paravirtualized environment under the

arch/x86/xen/enlighten.c

@@ -785,38 +785,35 @@ static __init void xen_set_pte_init(pte_t *ptep, pte_t pte)
 static __init void xen_pagetable_setup_start(pgd_t *base)
 {
 	pgd_t *xen_pgd = (pgd_t *)xen_start_info->pt_base;
+	int i;
 
 	/* special set_pte for pagetable initialization */
 	pv_mmu_ops.set_pte = xen_set_pte_init;
 
 	init_mm.pgd = base;
 	/*
-	 * copy top-level of Xen-supplied pagetable into place.	 For
-	 * !PAE we can use this as-is, but for PAE it is a stand-in
-	 * while we copy the pmd pages.
+	 * copy top-level of Xen-supplied pagetable into place.  This
+	 * is a stand-in while we copy the pmd pages.
 	 */
 	memcpy(base, xen_pgd, PTRS_PER_PGD * sizeof(pgd_t));
 
-	if (PTRS_PER_PMD > 1) {
-		int i;
-		/*
-		 * For PAE, need to allocate new pmds, rather than
-		 * share Xen's, since Xen doesn't like pmd's being
-		 * shared between address spaces.
-		 */
-		for (i = 0; i < PTRS_PER_PGD; i++) {
-			if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) {
-				pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
+	/*
+	 * For PAE, need to allocate new pmds, rather than
+	 * share Xen's, since Xen doesn't like pmd's being
+	 * shared between address spaces.
+	 */
+	for (i = 0; i < PTRS_PER_PGD; i++) {
+		if (pgd_val_ma(xen_pgd[i]) & _PAGE_PRESENT) {
+			pmd_t *pmd = (pmd_t *)alloc_bootmem_low_pages(PAGE_SIZE);
 
-				memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]),
-				       PAGE_SIZE);
+			memcpy(pmd, (void *)pgd_page_vaddr(xen_pgd[i]),
+			       PAGE_SIZE);
 
-				make_lowmem_page_readonly(pmd);
+			make_lowmem_page_readonly(pmd);
 
-				set_pgd(&base[i], __pgd(1 + __pa(pmd)));
-			} else
-				pgd_clear(&base[i]);
-		}
+			set_pgd(&base[i], __pgd(1 + __pa(pmd)));
+		} else
+			pgd_clear(&base[i]);
 	}
 
 	/* make sure zero_page is mapped RO so we can use it in pagetables */
@@ -873,17 +870,7 @@ static __init void xen_pagetable_setup_done(pgd_t *base)
 
 	/* Actually pin the pagetable down, but we can't set PG_pinned
 	   yet because the page structures don't exist yet. */
-	{
-		unsigned level;
-
-#ifdef CONFIG_X86_PAE
-		level = MMUEXT_PIN_L3_TABLE;
-#else
-		level = MMUEXT_PIN_L2_TABLE;
-#endif
-
-		pin_pagetable_pfn(level, PFN_DOWN(__pa(base)));
-	}
+	pin_pagetable_pfn(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(base)));
 }
 
 /* This is called once we have the cpu_possible_map */
@@ -1093,7 +1080,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 	.make_pte = xen_make_pte,
 	.make_pgd = xen_make_pgd,
 
-#ifdef CONFIG_X86_PAE
 	.set_pte_atomic = xen_set_pte_atomic,
 	.set_pte_present = xen_set_pte_at,
 	.set_pud = xen_set_pud,
@@ -1102,7 +1088,6 @@ static const struct pv_mmu_ops xen_mmu_ops __initdata = {
 
 	.make_pmd = xen_make_pmd,
 	.pmd_val = xen_pmd_val,
-#endif	/* PAE */
 
 	.activate_mm = xen_activate_mm,
 	.dup_mmap = xen_dup_mmap,
@@ -1228,6 +1213,11 @@ asmlinkage void __init xen_start_kernel(void)
 	if (xen_feature(XENFEAT_supervisor_mode_kernel))
 		pv_info.kernel_rpl = 0;
 
+	/* Prevent unwanted bits from being set in PTEs. */
+	__supported_pte_mask &= ~_PAGE_GLOBAL;
+	if (!is_initial_xendomain())
+		__supported_pte_mask &= ~(_PAGE_PWT | _PAGE_PCD);
+
 	/* set the limit of our address space */
 	xen_reserve_top();
 

arch/x86/xen/mmu.c

@@ -179,50 +179,56 @@ out:
 		preempt_enable();
 }
 
+/* Assume pteval_t is equivalent to all the other *val_t types. */
+static pteval_t pte_mfn_to_pfn(pteval_t val)
+{
+	if (val & _PAGE_PRESENT) {
+		unsigned long mfn = (val & PTE_MASK) >> PAGE_SHIFT;
+		pteval_t flags = val & ~PTE_MASK;
+		val = ((pteval_t)mfn_to_pfn(mfn) << PAGE_SHIFT) | flags;
+	}
+
+	return val;
+}
+
+static pteval_t pte_pfn_to_mfn(pteval_t val)
+{
+	if (val & _PAGE_PRESENT) {
+		unsigned long pfn = (val & PTE_MASK) >> PAGE_SHIFT;
+		pteval_t flags = val & ~PTE_MASK;
+		val = ((pteval_t)pfn_to_mfn(pfn) << PAGE_SHIFT) | flags;
+	}
+
+	return val;
+}
+
 pteval_t xen_pte_val(pte_t pte)
 {
-	pteval_t ret = pte.pte;
-
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
-
-	return ret;
+	return pte_mfn_to_pfn(pte.pte);
 }
 
 pgdval_t xen_pgd_val(pgd_t pgd)
 {
-	pgdval_t ret = pgd.pgd;
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
-	return ret;
+	return pte_mfn_to_pfn(pgd.pgd);
 }
 
 pte_t xen_make_pte(pteval_t pte)
 {
-	if (pte & _PAGE_PRESENT) {
-		pte = phys_to_machine(XPADDR(pte)).maddr;
-		pte &= ~(_PAGE_PCD | _PAGE_PWT);
-	}
-
-	return (pte_t){ .pte = pte };
+	pte = pte_pfn_to_mfn(pte);
+	return native_make_pte(pte);
 }
 
 pgd_t xen_make_pgd(pgdval_t pgd)
 {
-	if (pgd & _PAGE_PRESENT)
-		pgd = phys_to_machine(XPADDR(pgd)).maddr;
-
-	return (pgd_t){ pgd };
+	pgd = pte_pfn_to_mfn(pgd);
+	return native_make_pgd(pgd);
 }
 
 pmdval_t xen_pmd_val(pmd_t pmd)
 {
-	pmdval_t ret = native_pmd_val(pmd);
-	if (ret & _PAGE_PRESENT)
-		ret = machine_to_phys(XMADDR(ret)).paddr | _PAGE_PRESENT;
-	return ret;
+	return pte_mfn_to_pfn(pmd.pmd);
 }
-#ifdef CONFIG_X86_PAE
+
 void xen_set_pud(pud_t *ptr, pud_t val)
 {
 	struct multicall_space mcs;
@@ -267,17 +273,9 @@ void xen_pmd_clear(pmd_t *pmdp)
 
 pmd_t xen_make_pmd(pmdval_t pmd)
 {
-	if (pmd & _PAGE_PRESENT)
-		pmd = phys_to_machine(XPADDR(pmd)).maddr;
-
+	pmd = pte_pfn_to_mfn(pmd);
 	return native_make_pmd(pmd);
 }
-#else  /* !PAE */
-void xen_set_pte(pte_t *ptep, pte_t pte)
-{
-	*ptep = pte;
-}
-#endif	/* CONFIG_X86_PAE */
 
 /*
   (Yet another) pagetable walker.  This one is intended for pinning a
@@ -430,8 +428,6 @@ static int pin_page(struct page *page, enum pt_level level)
    read-only, and can be pinned. */
 void xen_pgd_pin(pgd_t *pgd)
 {
-	unsigned level;
-
 	xen_mc_batch();
 
 	if (pgd_walk(pgd, pin_page, TASK_SIZE)) {
@@ -441,14 +437,7 @@ void xen_pgd_pin(pgd_t *pgd)
 		xen_mc_batch();
 	}
 
-#ifdef CONFIG_X86_PAE
-	level = MMUEXT_PIN_L3_TABLE;
-#else
-	level = MMUEXT_PIN_L2_TABLE;
-#endif
-
-	xen_do_pin(level, PFN_DOWN(__pa(pgd)));
-
+	xen_do_pin(MMUEXT_PIN_L3_TABLE, PFN_DOWN(__pa(pgd)));
 	xen_mc_issue(0);
 }
 

arch/x86/xen/mmu.h

@@ -37,14 +37,13 @@ void xen_exit_mmap(struct mm_struct *mm);
 void xen_pgd_pin(pgd_t *pgd);
 //void xen_pgd_unpin(pgd_t *pgd);
 
-#ifdef CONFIG_X86_PAE
-unsigned long long xen_pte_val(pte_t);
-unsigned long long xen_pmd_val(pmd_t);
-unsigned long long xen_pgd_val(pgd_t);
+pteval_t xen_pte_val(pte_t);
+pmdval_t xen_pmd_val(pmd_t);
+pgdval_t xen_pgd_val(pgd_t);
 
-pte_t xen_make_pte(unsigned long long);
-pmd_t xen_make_pmd(unsigned long long);
-pgd_t xen_make_pgd(unsigned long long);
+pte_t xen_make_pte(pteval_t);
+pmd_t xen_make_pmd(pmdval_t);
+pgd_t xen_make_pgd(pgdval_t);
 
 void xen_set_pte_at(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, pte_t pteval);
@@ -53,15 +52,4 @@ void xen_set_pud(pud_t *ptr, pud_t val);
 void xen_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep);
 void xen_pmd_clear(pmd_t *pmdp);
 
-
-#else
-unsigned long xen_pte_val(pte_t);
-unsigned long xen_pmd_val(pmd_t);
-unsigned long xen_pgd_val(pgd_t);
-
-pte_t xen_make_pte(unsigned long);
-pmd_t xen_make_pmd(unsigned long);
-pgd_t xen_make_pgd(unsigned long);
-#endif
-
 #endif	/* _XEN_MMU_H */

arch/x86/xen/time.c

@@ -14,6 +14,7 @@
 #include <linux/kernel_stat.h>
 #include <linux/math64.h>
 
+#include <asm/pvclock.h>
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/hypercall.h>
 
@@ -31,17 +32,6 @@
 
 static cycle_t xen_clocksource_read(void);
 
-/* These are perodically updated in shared_info, and then copied here. */
-struct shadow_time_info {
-	u64 tsc_timestamp;     /* TSC at last update of time vals.  */
-	u64 system_timestamp;  /* Time, in nanosecs, since boot.    */
-	u32 tsc_to_nsec_mul;
-	int tsc_shift;
-	u32 version;
-};
-
-static DEFINE_PER_CPU(struct shadow_time_info, shadow_time);
-
 /* runstate info updated by Xen */
 static DEFINE_PER_CPU(struct vcpu_runstate_info, runstate);
 
@@ -211,7 +201,7 @@ unsigned long long xen_sched_clock(void)
 unsigned long xen_cpu_khz(void)
 {
 	u64 xen_khz = 1000000ULL << 32;
-	const struct vcpu_time_info *info =
+	const struct pvclock_vcpu_time_info *info =
 		&HYPERVISOR_shared_info->vcpu_info[0].time;
 
 	do_div(xen_khz, info->tsc_to_system_mul);
@@ -223,121 +213,26 @@ unsigned long xen_cpu_khz(void)
 	return xen_khz;
 }
 
-/*
- * Reads a consistent set of time-base values from Xen, into a shadow data
- * area.
- */
-static unsigned get_time_values_from_xen(void)
-{
-	struct vcpu_time_info   *src;
-	struct shadow_time_info *dst;
-
-	/* src is shared memory with the hypervisor, so we need to
-	   make sure we get a consistent snapshot, even in the face of
-	   being preempted. */
-	src = &__get_cpu_var(xen_vcpu)->time;
-	dst = &__get_cpu_var(shadow_time);
-
-	do {
-		dst->version = src->version;
-		rmb();		/* fetch version before data */
-		dst->tsc_timestamp     = src->tsc_timestamp;
-		dst->system_timestamp  = src->system_time;
-		dst->tsc_to_nsec_mul   = src->tsc_to_system_mul;
-		dst->tsc_shift         = src->tsc_shift;
-		rmb();		/* test version after fetching data */
-	} while ((src->version & 1) | (dst->version ^ src->version));
-
-	return dst->version;
-}
-
-/*
- * Scale a 64-bit delta by scaling and multiplying by a 32-bit fraction,
- * yielding a 64-bit result.
- */
-static inline u64 scale_delta(u64 delta, u32 mul_frac, int shift)
-{
-	u64 product;
-#ifdef __i386__
-	u32 tmp1, tmp2;
-#endif
-
-	if (shift < 0)
-		delta >>= -shift;
-	else
-		delta <<= shift;
-
-#ifdef __i386__
-	__asm__ (
-		"mul  %5       ; "
-		"mov  %4,%%eax ; "
-		"mov  %%edx,%4 ; "
-		"mul  %5       ; "
-		"xor  %5,%5    ; "
-		"add  %4,%%eax ; "
-		"adc  %5,%%edx ; "
-		: "=A" (product), "=r" (tmp1), "=r" (tmp2)
-		: "a" ((u32)delta), "1" ((u32)(delta >> 32)), "2" (mul_frac) );
-#elif __x86_64__
-	__asm__ (
-		"mul %%rdx ; shrd $32,%%rdx,%%rax"
-		: "=a" (product) : "0" (delta), "d" ((u64)mul_frac) );
-#else
-#error implement me!
-#endif
-
-	return product;
-}
-
-static u64 get_nsec_offset(struct shadow_time_info *shadow)
-{
-	u64 now, delta;
-	now = native_read_tsc();
-	delta = now - shadow->tsc_timestamp;
-	return scale_delta(delta, shadow->tsc_to_nsec_mul, shadow->tsc_shift);
-}
-
 static cycle_t xen_clocksource_read(void)
 {
-	struct shadow_time_info *shadow = &get_cpu_var(shadow_time);
+        struct pvclock_vcpu_time_info *src;
 	cycle_t ret;
-	unsigned version;
-
-	do {
-		version = get_time_values_from_xen();
-		barrier();
-		ret = shadow->system_timestamp + get_nsec_offset(shadow);
-		barrier();
-	} while (version != __get_cpu_var(xen_vcpu)->time.version);
-
-	put_cpu_var(shadow_time);
 
+	src = &get_cpu_var(xen_vcpu)->time;
+	ret = pvclock_clocksource_read(src);
+	put_cpu_var(xen_vcpu);
 	return ret;
 }
 
 static void xen_read_wallclock(struct timespec *ts)
 {
-	const struct shared_info *s = HYPERVISOR_shared_info;
-	u32 version;
-	u64 delta;
-	struct timespec now;
+	struct shared_info *s = HYPERVISOR_shared_info;
+	struct pvclock_wall_clock *wall_clock = &(s->wc);
+        struct pvclock_vcpu_time_info *vcpu_time;
 
-	/* get wallclock at system boot */
-	do {
-		version = s->wc_version;
-		rmb();		/* fetch version before time */
-		now.tv_sec  = s->wc_sec;
-		now.tv_nsec = s->wc_nsec;
-		rmb();		/* fetch time before checking version */
-	} while ((s->wc_version & 1) | (version ^ s->wc_version));
-
-	delta = xen_clocksource_read();	/* time since system boot */
-	delta += now.tv_sec * (u64)NSEC_PER_SEC + now.tv_nsec;
-
-	now.tv_nsec = do_div(delta, NSEC_PER_SEC);
-	now.tv_sec = delta;
-
-	set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
+	vcpu_time = &get_cpu_var(xen_vcpu)->time;
+	pvclock_read_wallclock(wall_clock, vcpu_time, ts);
+	put_cpu_var(xen_vcpu);
 }
 
 unsigned long xen_get_wallclock(void)
@@ -345,7 +240,6 @@ unsigned long xen_get_wallclock(void)
 	struct timespec ts;
 
 	xen_read_wallclock(&ts);
-
 	return ts.tv_sec;
 }
 
@@ -569,8 +463,6 @@ __init void xen_time_init(void)
 {
 	int cpu = smp_processor_id();
 
-	get_time_values_from_xen();
-
 	clocksource_register(&xen_clocksource);
 
 	if (HYPERVISOR_vcpu_op(VCPUOP_stop_periodic_timer, cpu, NULL) == 0) {

arch/x86/xen/xen-head.S

@@ -17,7 +17,7 @@ ENTRY(startup_xen)
 
 	__FINIT
 
-.pushsection .bss.page_aligned
+.pushsection .text
 	.align PAGE_SIZE_asm
 ENTRY(hypercall_page)
 	.skip 0x1000
@@ -30,11 +30,7 @@ ENTRY(hypercall_page)
 	ELFNOTE(Xen, XEN_ELFNOTE_ENTRY,          .long  startup_xen)
 	ELFNOTE(Xen, XEN_ELFNOTE_HYPERCALL_PAGE, .long  hypercall_page)
 	ELFNOTE(Xen, XEN_ELFNOTE_FEATURES,       .asciz "!writable_page_tables|pae_pgdir_above_4gb")
-#ifdef CONFIG_X86_PAE
 	ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "yes")
-#else
-	ELFNOTE(Xen, XEN_ELFNOTE_PAE_MODE,       .asciz "no")
-#endif
 	ELFNOTE(Xen, XEN_ELFNOTE_LOADER,         .asciz "generic")
 
 #endif /*CONFIG_XEN */

block/as-iosched.c

@@ -831,6 +831,8 @@ static void as_completed_request(struct request_queue *q, struct request *rq)
 	}
 
 	if (ad->changed_batch && ad->nr_dispatched == 1) {
+		ad->current_batch_expires = jiffies +
+					ad->batch_expire[ad->batch_data_dir];
 		kblockd_schedule_work(&ad->antic_work);
 		ad->changed_batch = 0;
 

block/bsg.c

@@ -709,11 +709,12 @@ static void bsg_kref_release_function(struct kref *kref)
 {
 	struct bsg_class_device *bcd =
 		container_of(kref, struct bsg_class_device, ref);
+	struct device *parent = bcd->parent;
 
 	if (bcd->release)
 		bcd->release(bcd->parent);
 
-	put_device(bcd->parent);
+	put_device(parent);
 }
 
 static int bsg_put_device(struct bsg_device *bd)

crypto/chainiv.c

@@ -117,6 +117,7 @@ static int chainiv_init(struct crypto_tfm *tfm)
 static int async_chainiv_schedule_work(struct async_chainiv_ctx *ctx)
 {
 	int queued;
+	int err = ctx->err;
 
 	if (!ctx->queue.qlen) {
 		smp_mb__before_clear_bit();
@@ -131,7 +132,7 @@ static int async_chainiv_schedule_work(struct async_chainiv_ctx *ctx)
 	BUG_ON(!queued);
 
 out:
-	return ctx->err;
+	return err;
 }
 
 static int async_chainiv_postpone_request(struct skcipher_givcrypt_request *req)
@@ -227,6 +228,7 @@ static void async_chainiv_do_postponed(struct work_struct *work)
 						     postponed);
 	struct skcipher_givcrypt_request *req;
 	struct ablkcipher_request *subreq;
+	int err;
 
 	/* Only handle one request at a time to avoid hogging keventd. */
 	spin_lock_bh(&ctx->lock);
@@ -241,7 +243,11 @@ static void async_chainiv_do_postponed(struct work_struct *work)
 	subreq = skcipher_givcrypt_reqctx(req);
 	subreq->base.flags |= CRYPTO_TFM_REQ_MAY_SLEEP;
 
-	async_chainiv_givencrypt_tail(req);
+	err = async_chainiv_givencrypt_tail(req);
+
+	local_bh_disable();
+	skcipher_givcrypt_complete(req, err);
+	local_bh_enable();
 }
 
 static int async_chainiv_init(struct crypto_tfm *tfm)

crypto/tcrypt.c

@@ -586,12 +586,6 @@ static void test_cipher(char *algo, int enc,
 	j = 0;
 	for (i = 0; i < tcount; i++) {
 
-		data = kzalloc(template[i].ilen, GFP_KERNEL);
-		if (!data)
-			continue;
-
-		memcpy(data, template[i].input, template[i].ilen);
-
 		if (template[i].iv)
 			memcpy(iv, template[i].iv, MAX_IVLEN);
 		else
@@ -613,10 +607,8 @@ static void test_cipher(char *algo, int enc,
 				printk("setkey() failed flags=%x\n",
 						crypto_ablkcipher_get_flags(tfm));
 
-				if (!template[i].fail) {
-					kfree(data);
+				if (!template[i].fail)
 					goto out;
-				}
 			}
 
 			temp = 0;

drivers/acpi/bay.c

@@ -377,6 +377,9 @@ static int __init bay_init(void)
 
 	INIT_LIST_HEAD(&drive_bays);
 
+	if (acpi_disabled)
+		return -ENODEV;
+
 	/* look for dockable drive bays */
 	acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
 		ACPI_UINT32_MAX, find_bay, &bays, NULL);

drivers/acpi/dock.c

@@ -917,6 +917,9 @@ static int __init dock_init(void)
 
 	dock_station = NULL;
 
+	if (acpi_disabled)
+		return 0;
+
 	/* look for a dock station */
 	acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
 			    ACPI_UINT32_MAX, find_dock, &num, NULL);

drivers/acpi/glue.c

@@ -333,6 +333,9 @@ static int __init acpi_rtc_init(void)
 {
 	struct device *dev = get_rtc_dev();
 
+	if (acpi_disabled)
+		return 0;
+
 	if (dev) {
 		rtc_wake_setup();
 		rtc_info.wake_on = rtc_wake_on;

drivers/acpi/sleep/main.c

@@ -36,9 +36,8 @@ static int acpi_sleep_prepare(u32 acpi_state)
 		if (!acpi_wakeup_address) {
 			return -EFAULT;
 		}
-		acpi_set_firmware_waking_vector((acpi_physical_address)
-						virt_to_phys((void *)
-							     acpi_wakeup_address));
+		acpi_set_firmware_waking_vector(
+				(acpi_physical_address)acpi_wakeup_address);
 
 	}
 	ACPI_FLUSH_CPU_CACHE();

drivers/acpi/sleep/proc.c

@@ -315,8 +315,11 @@ acpi_system_write_alarm(struct file *file,
 		cmos_bcd_write(day, acpi_gbl_FADT.day_alarm, rtc_control);
 	if (acpi_gbl_FADT.month_alarm)
 		cmos_bcd_write(mo, acpi_gbl_FADT.month_alarm, rtc_control);
-	if (acpi_gbl_FADT.century)
+	if (acpi_gbl_FADT.century) {
+		if (adjust)
+			yr += cmos_bcd_read(acpi_gbl_FADT.century, rtc_control) * 100;
 		cmos_bcd_write(yr / 100, acpi_gbl_FADT.century, rtc_control);
+	}
 	/* enable the rtc alarm interrupt */
 	rtc_control |= RTC_AIE;
 	CMOS_WRITE(rtc_control, RTC_CONTROL);

drivers/ata/ahci.c

@@ -1777,7 +1777,7 @@ static irqreturn_t ahci_interrupt(int irq, void *dev_instance)
 	struct ahci_host_priv *hpriv;
 	unsigned int i, handled = 0;
 	void __iomem *mmio;
-	u32 irq_stat, irq_ack = 0;
+	u32 irq_stat, irq_masked;
 
 	VPRINTK("ENTER\n");
 
@@ -1786,16 +1786,17 @@ static irqreturn_t ahci_interrupt(int irq, void *dev_instance)
 
 	/* sigh.  0xffffffff is a valid return from h/w */
 	irq_stat = readl(mmio + HOST_IRQ_STAT);
-	irq_stat &= hpriv->port_map;
 	if (!irq_stat)
 		return IRQ_NONE;
 
+	irq_masked = irq_stat & hpriv->port_map;
+
 	spin_lock(&host->lock);
 
 	for (i = 0; i < host->n_ports; i++) {
 		struct ata_port *ap;
 
-		if (!(irq_stat & (1 << i)))
+		if (!(irq_masked & (1 << i)))
 			continue;
 
 		ap = host->ports[i];
@@ -1809,14 +1810,20 @@ static irqreturn_t ahci_interrupt(int irq, void *dev_instance)
 					"interrupt on disabled port %u\n", i);
 		}
 
-		irq_ack |= (1 << i);
-	}
-
-	if (irq_ack) {
-		writel(irq_ack, mmio + HOST_IRQ_STAT);
 		handled = 1;
 	}
 
+	/* HOST_IRQ_STAT behaves as level triggered latch meaning that
+	 * it should be cleared after all the port events are cleared;
+	 * otherwise, it will raise a spurious interrupt after each
+	 * valid one.  Please read section 10.6.2 of ahci 1.1 for more
+	 * information.
+	 *
+	 * Also, use the unmasked value to clear interrupt as spurious
+	 * pending event on a dummy port might cause screaming IRQ.
+	 */
+	writel(irq_stat, mmio + HOST_IRQ_STAT);
+
 	spin_unlock(&host->lock);
 
 	VPRINTK("EXIT\n");

drivers/ata/libata-acpi.c

@@ -29,14 +29,16 @@
 enum {
 	ATA_ACPI_FILTER_SETXFER	= 1 << 0,
 	ATA_ACPI_FILTER_LOCK	= 1 << 1,
+	ATA_ACPI_FILTER_DIPM	= 1 << 2,
 
 	ATA_ACPI_FILTER_DEFAULT	= ATA_ACPI_FILTER_SETXFER |
-				  ATA_ACPI_FILTER_LOCK,
+				  ATA_ACPI_FILTER_LOCK |
+				  ATA_ACPI_FILTER_DIPM,
 };
 
 static unsigned int ata_acpi_gtf_filter = ATA_ACPI_FILTER_DEFAULT;
 module_param_named(acpi_gtf_filter, ata_acpi_gtf_filter, int, 0644);
-MODULE_PARM_DESC(acpi_gtf_filter, "filter mask for ACPI _GTF commands, set to filter out (0x1=set xfermode, 0x2=lock/freeze lock)");
+MODULE_PARM_DESC(acpi_gtf_filter, "filter mask for ACPI _GTF commands, set to filter out (0x1=set xfermode, 0x2=lock/freeze lock, 0x4=DIPM)");
 
 #define NO_PORT_MULT		0xffff
 #define SATA_ADR(root, pmp)	(((root) << 16) | (pmp))
@@ -195,6 +197,10 @@ static void ata_acpi_handle_hotplug(struct ata_port *ap, struct ata_device *dev,
 		/* This device does not support hotplug */
 		return;
 
+	if (event == ACPI_NOTIFY_BUS_CHECK ||
+	    event == ACPI_NOTIFY_DEVICE_CHECK)
+		status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
+
 	spin_lock_irqsave(ap->lock, flags);
 
 	switch (event) {
@@ -202,7 +208,6 @@ static void ata_acpi_handle_hotplug(struct ata_port *ap, struct ata_device *dev,
 	case ACPI_NOTIFY_DEVICE_CHECK:
 		ata_ehi_push_desc(ehi, "ACPI event");
 
-		status = acpi_evaluate_integer(handle, "_STA", NULL, &sta);
 		if (ACPI_FAILURE(status)) {
 			ata_port_printk(ap, KERN_ERR,
 				"acpi: failed to determine bay status (0x%x)\n",
@@ -690,6 +695,14 @@ static int ata_acpi_filter_tf(const struct ata_taskfile *tf,
 			return 1;
 	}
 
+	if (ata_acpi_gtf_filter & ATA_ACPI_FILTER_DIPM) {
+		/* inhibit enabling DIPM */
+		if (tf->command == ATA_CMD_SET_FEATURES &&
+		    tf->feature == SETFEATURES_SATA_ENABLE &&
+		    tf->nsect == SATA_DIPM)
+			return 1;
+	}
+
 	return 0;
 }
 

drivers/ata/libata-sff.c

@@ -1094,6 +1094,7 @@ static void ata_hsm_qc_complete(struct ata_queued_cmd *qc, int in_wq)
 int ata_sff_hsm_move(struct ata_port *ap, struct ata_queued_cmd *qc,
 		     u8 status, int in_wq)
 {
+	struct ata_eh_info *ehi = &ap->link.eh_info;
 	unsigned long flags = 0;
 	int poll_next;
 
@@ -1125,9 +1126,12 @@ fsm_start:
 			if (likely(status & (ATA_ERR | ATA_DF)))
 				/* device stops HSM for abort/error */
 				qc->err_mask |= AC_ERR_DEV;
-			else
+			else {
 				/* HSM violation. Let EH handle this */
+				ata_ehi_push_desc(ehi,
+					"ST_FIRST: !(DRQ|ERR|DF)");
 				qc->err_mask |= AC_ERR_HSM;
+			}
 
 			ap->hsm_task_state = HSM_ST_ERR;
 			goto fsm_start;
@@ -1146,9 +1150,9 @@ fsm_start:
 			 * the CDB.
 			 */
 			if (!(qc->dev->horkage & ATA_HORKAGE_STUCK_ERR)) {
-				ata_port_printk(ap, KERN_WARNING,
-						"DRQ=1 with device error, "
-						"dev_stat 0x%X\n", status);
+				ata_ehi_push_desc(ehi, "ST_FIRST: "
+					"DRQ=1 with device error, "
+					"dev_stat 0x%X", status);
 				qc->err_mask |= AC_ERR_HSM;
 				ap->hsm_task_state = HSM_ST_ERR;
 				goto fsm_start;
@@ -1205,9 +1209,9 @@ fsm_start:
 			 * let the EH abort the command or reset the device.
 			 */
 			if (unlikely(status & (ATA_ERR | ATA_DF))) {
-				ata_port_printk(ap, KERN_WARNING, "DRQ=1 with "
-						"device error, dev_stat 0x%X\n",
-						status);
+				ata_ehi_push_desc(ehi, "ST-ATAPI: "
+					"DRQ=1 with device error, "
+					"dev_stat 0x%X", status);
 				qc->err_mask |= AC_ERR_HSM;
 				ap->hsm_task_state = HSM_ST_ERR;
 				goto fsm_start;
@@ -1226,13 +1230,17 @@ fsm_start:
 				if (likely(status & (ATA_ERR | ATA_DF)))
 					/* device stops HSM for abort/error */
 					qc->err_mask |= AC_ERR_DEV;
-				else
+				else {
 					/* HSM violation. Let EH handle this.
 					 * Phantom devices also trigger this
 					 * condition.  Mark hint.
 					 */
+					ata_ehi_push_desc(ehi, "ST-ATA: "
+						"DRQ=1 with device error, "
+						"dev_stat 0x%X", status);
 					qc->err_mask |= AC_ERR_HSM |
 							AC_ERR_NODEV_HINT;
+				}
 
 				ap->hsm_task_state = HSM_ST_ERR;
 				goto fsm_start;
@@ -1257,8 +1265,12 @@ fsm_start:
 					status = ata_wait_idle(ap);
 				}
 
-				if (status & (ATA_BUSY | ATA_DRQ))
+				if (status & (ATA_BUSY | ATA_DRQ)) {
+					ata_ehi_push_desc(ehi, "ST-ATA: "
+						"BUSY|DRQ persists on ERR|DF, "
+						"dev_stat 0x%X", status);
 					qc->err_mask |= AC_ERR_HSM;
+				}
 
 				/* ata_pio_sectors() might change the
 				 * state to HSM_ST_LAST. so, the state

drivers/ata/pata_sis.c

@@ -56,6 +56,7 @@ static const struct sis_laptop sis_laptop[] = {
 	{ 0x5513, 0x1043, 0x1107 },	/* ASUS A6K */
 	{ 0x5513, 0x1734, 0x105F },	/* FSC Amilo A1630 */
 	{ 0x5513, 0x1071, 0x8640 },     /* EasyNote K5305 */
+	{ 0x5513, 0x1039, 0x5513 },	/* Targa Visionary 1000 */
 	/* end marker */
 	{ 0, }
 };

drivers/ata/sata_mv.c

@@ -1607,7 +1607,7 @@ static unsigned int mv_qc_issue(struct ata_queued_cmd *qc)
 		 * Much of the time, this could just work regardless.
 		 * So for now, just log the incident, and allow the attempt.
 		 */
-		if (limit_warnings && (qc->nbytes / qc->sect_size) > 1) {
+		if (limit_warnings > 0 && (qc->nbytes / qc->sect_size) > 1) {
 			--limit_warnings;
 			ata_link_printk(qc->dev->link, KERN_WARNING, DRV_NAME
 					": attempting PIO w/multiple DRQ: "

drivers/ata/sata_sil24.c

@@ -370,6 +370,7 @@ static const struct pci_device_id sil24_pci_tbl[] = {
 	{ PCI_VDEVICE(INTEL, 0x3124), BID_SIL3124 },
 	{ PCI_VDEVICE(CMD, 0x3132), BID_SIL3132 },
 	{ PCI_VDEVICE(CMD, 0x0242), BID_SIL3132 },
+	{ PCI_VDEVICE(CMD, 0x0244), BID_SIL3132 },
 	{ PCI_VDEVICE(CMD, 0x3131), BID_SIL3131 },
 	{ PCI_VDEVICE(CMD, 0x3531), BID_SIL3131 },
 

drivers/ata/sata_uli.c

@@ -83,6 +83,7 @@ static struct ata_port_operations uli_ops = {
 	.inherits		= &ata_bmdma_port_ops,
 	.scr_read		= uli_scr_read,
 	.scr_write		= uli_scr_write,
+	.hardreset		= ATA_OP_NULL,
 };
 
 static const struct ata_port_info uli_port_info = {

drivers/auxdisplay/Kconfig

@@ -64,7 +64,7 @@ config KS0108_DELAY
 	  Amount of time the ks0108 should wait between each control write
 	  to the parallel port.
 
-	  If your driver seems to miss random writings, increment this.
+	  If your LCD seems to miss random writings, increment this.
 
 	  If you don't know what I'm talking about, ignore it.
 

drivers/auxdisplay/cfag12864b.c

@@ -5,7 +5,7 @@
  *     License: GPLv2
  *     Depends: ks0108
  *
- *      Author: Copyright (C) Miguel Ojeda Sandonis <maxextreme@gmail.com>
+ *      Author: Copyright (C) Miguel Ojeda Sandonis
  *        Date: 2006-10-31
  *
  *  This program is free software; you can redistribute it and/or modify
@@ -398,5 +398,5 @@ module_init(cfag12864b_init);
 module_exit(cfag12864b_exit);
 
 MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Miguel Ojeda Sandonis <maxextreme@gmail.com>");
+MODULE_AUTHOR("Miguel Ojeda Sandonis <miguel.ojeda.sandonis@gmail.com>");
 MODULE_DESCRIPTION("cfag12864b LCD driver");

drivers/auxdisplay/cfag12864bfb.c

@@ -5,7 +5,7 @@
  *     License: GPLv2
  *     Depends: cfag12864b
  *
- *      Author: Copyright (C) Miguel Ojeda Sandonis <maxextreme@gmail.com>
+ *      Author: Copyright (C) Miguel Ojeda Sandonis
  *        Date: 2006-10-31
  *
  *  This program is free software; you can redistribute it and/or modify
@@ -186,5 +186,5 @@ module_init(cfag12864bfb_init);
 module_exit(cfag12864bfb_exit);
 
 MODULE_LICENSE("GPL v2");
-MODULE_AUTHOR("Miguel Ojeda Sandonis <maxextreme@gmail.com>");
+MODULE_AUTHOR("Miguel Ojeda Sandonis <miguel.ojeda.sandonis@gmail.com>");
 MODULE_DESCRIPTION("cfag12864b LCD framebuffer driver");