Merge branch 'master' into upstream

.mailmap

@@ -0,0 +1,96 @@
+#
+# This list is used by git-shortlog to fix a few botched name translations
+# in the git archive, either because the author's full name was messed up
+# and/or not always written the same way, making contributions from the
+# same person appearing not to be so or badly displayed.
+#
+# repo-abbrev: /pub/scm/linux/kernel/git/
+#
+
+Aaron Durbin <adurbin@google.com>
+Adam Oldham <oldhamca@gmail.com>
+Adam Radford <aradford@gmail.com>
+Adrian Bunk <bunk@stusta.de>
+Alan Cox <alan@lxorguk.ukuu.org.uk>
+Alan Cox <root@hraefn.swansea.linux.org.uk>
+Aleksey Gorelov <aleksey_gorelov@phoenix.com>
+Al Viro <viro@ftp.linux.org.uk>
+Al Viro <viro@zenIV.linux.org.uk>
+Andreas Herrmann <aherrman@de.ibm.com>
+Andrew Morton <akpm@osdl.org>
+Andrew Vasquez <andrew.vasquez@qlogic.com>
+Andy Adamson <andros@citi.umich.edu>
+Arnaud Patard <arnaud.patard@rtp-net.org>
+Arnd Bergmann <arnd@arndb.de>
+Axel Dyks <xl@xlsigned.net>
+Ben Gardner <bgardner@wabtec.com>
+Ben M Cahill <ben.m.cahill@intel.com>
+Björn Steinbrink <B.Steinbrink@gmx.de>
+Brian Avery <b.avery@hp.com>
+Brian King <brking@us.ibm.com>
+Christoph Hellwig <hch@lst.de>
+Corey Minyard <minyard@acm.org>
+David Brownell <david-b@pacbell.net>
+David Woodhouse <dwmw2@shinybook.infradead.org>
+Domen Puncer <domen@coderock.org>
+Douglas Gilbert <dougg@torque.net>
+Ed L. Cashin <ecashin@coraid.com>
+Evgeniy Polyakov <johnpol@2ka.mipt.ru>
+Felipe W Damasio <felipewd@terra.com.br>
+Felix Kuhling <fxkuehl@gmx.de>
+Felix Moeller <felix@derklecks.de>
+Filipe Lautert <filipe@icewall.org>
+Franck Bui-Huu <vagabon.xyz@gmail.com>
+Frank Zago <fzago@systemfabricworks.com>
+Greg Kroah-Hartman <greg@echidna.(none)>
+Greg Kroah-Hartman <gregkh@suse.de>
+Greg Kroah-Hartman <greg@kroah.com>
+Henk Vergonet <Henk.Vergonet@gmail.com>
+Henrik Kretzschmar <henne@nachtwindheim.de>
+Herbert Xu <herbert@gondor.apana.org.au>
+Jacob Shin <Jacob.Shin@amd.com>
+James Bottomley <jejb@mulgrave.(none)>
+James Bottomley <jejb@titanic.il.steeleye.com>
+James E Wilson <wilson@specifix.com>
+James Ketrenos <jketreno@io.(none)>
+Jean Tourrilhes <jt@hpl.hp.com>
+Jeff Garzik <jgarzik@pretzel.yyz.us>
+Jens Axboe <axboe@suse.de>
+Jens Osterkamp <Jens.Osterkamp@de.ibm.com>
+John Stultz <johnstul@us.ibm.com>
+Juha Yrjola <at solidboot.com>
+Juha Yrjola <juha.yrjola@nokia.com>
+Juha Yrjola <juha.yrjola@solidboot.com>
+Kay Sievers <kay.sievers@vrfy.org>
+Kenneth W Chen <kenneth.w.chen@intel.com>
+Koushik <raghavendra.koushik@neterion.com>
+Leonid I Ananiev <leonid.i.ananiev@intel.com>
+Linas Vepstas <linas@austin.ibm.com>
+Matthieu CASTET <castet.matthieu@free.fr>
+Michel Dänzer <michel@tungstengraphics.com>
+Mitesh shah <mshah@teja.com>
+Morten Welinder <terra@gnome.org>
+Morten Welinder <welinder@anemone.rentec.com>
+Morten Welinder <welinder@darter.rentec.com>
+Morten Welinder <welinder@troll.com>
+Nguyen Anh Quynh <aquynh@gmail.com>
+Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
+Patrick Mochel <mochel@digitalimplant.org>
+Peter A Jonsson <pj@ludd.ltu.se>
+Praveen BP <praveenbp@ti.com>
+Rajesh Shah <rajesh.shah@intel.com>
+Ralf Baechle <ralf@linux-mips.org>
+Ralf Wildenhues <Ralf.Wildenhues@gmx.de>
+Rémi Denis-Courmont <rdenis@simphalempin.com>
+Rudolf Marek <R.Marek@sh.cvut.cz>
+Rui Saraiva <rmps@joel.ist.utl.pt>
+Sachin P Sant <ssant@in.ibm.com>
+Sam Ravnborg <sam@mars.ravnborg.org>
+Simon Kelley <simon@thekelleys.org.uk>
+Stéphane Witzmann <stephane.witzmann@ubpmes.univ-bpclermont.fr>
+Stephen Hemminger <shemminger@osdl.org>
+Tejun Heo <htejun@gmail.com>
+Thomas Graf <tgraf@suug.ch>
+Tony Luck <tony.luck@intel.com>
+Tsuneo Yoshioka <Tsuneo.Yoshioka@f-secure.com>
+Valdis Kletnieks <Valdis.Kletnieks@vt.edu>

Documentation/gpio.txt

@@ -78,7 +78,8 @@ Identifying GPIOs
 -----------------
 GPIOs are identified by unsigned integers in the range 0..MAX_INT.  That
 reserves "negative" numbers for other purposes like marking signals as
-"not available on this board", or indicating faults.
+"not available on this board", or indicating faults.  Code that doesn't
+touch the underlying hardware treats these integers as opaque cookies.
 
 Platforms define how they use those integers, and usually #define symbols
 for the GPIO lines so that board-specific setup code directly corresponds
@@ -139,10 +140,10 @@ issues including wire-OR and output latencies.
 The get/set calls have no error returns because "invalid GPIO" should have
 been reported earlier in gpio_set_direction().  However, note that not all
 platforms can read the value of output pins; those that can't should always
-return zero.  Also, these calls will be ignored for GPIOs that can't safely
-be accessed wihtout sleeping (see below).
+return zero.  Also, using these calls for GPIOs that can't safely be accessed
+without sleeping (see below) is an error.
 
-Platform-specific implementations are encouraged to optimise the two
+Platform-specific implementations are encouraged to optimize the two
 calls to access the GPIO value in cases where the GPIO number (and for
 output, value) are constant.  It's normal for them to need only a couple
 of instructions in such cases (reading or writing a hardware register),
@@ -239,7 +240,8 @@ options are part of the IRQ interface, e.g. IRQF_TRIGGER_FALLING, as are
 system wakeup capabilities.
 
 Non-error values returned from irq_to_gpio() would most commonly be used
-with gpio_get_value().
+with gpio_get_value(), for example to initialize or update driver state
+when the IRQ is edge-triggered.
 
 
 
@@ -260,9 +262,10 @@ pullups (or pulldowns) so that the on-chip ones should not be used.
 There are other system-specific mechanisms that are not specified here,
 like the aforementioned options for input de-glitching and wire-OR output.
 Hardware may support reading or writing GPIOs in gangs, but that's usually
-configuration dependednt:  for GPIOs sharing the same bank.  (GPIOs are
+configuration dependent:  for GPIOs sharing the same bank.  (GPIOs are
 commonly grouped in banks of 16 or 32, with a given SOC having several such
-banks.)  Code relying on such mechanisms will necessarily be nonportable.
+banks.)  Some systems can trigger IRQs from output GPIOs.  Code relying on
+such mechanisms will necessarily be nonportable.
 
 Dynamic definition of GPIOs is not currently supported; for example, as
 a side effect of configuring an add-on board with some GPIO expanders.

Documentation/hrtimer/timer_stats.txt

@@ -0,0 +1,68 @@
+timer_stats - timer usage statistics
+------------------------------------
+
+timer_stats is a debugging facility to make the timer (ab)usage in a Linux
+system visible to kernel and userspace developers. It is not intended for
+production usage as it adds significant overhead to the (hr)timer code and the
+(hr)timer data structures.
+
+timer_stats should be used by kernel and userspace developers to verify that
+their code does not make unduly use of timers. This helps to avoid unnecessary
+wakeups, which should be avoided to optimize power consumption.
+
+It can be enabled by CONFIG_TIMER_STATS in the "Kernel hacking" configuration
+section.
+
+timer_stats collects information about the timer events which are fired in a
+Linux system over a sample period:
+
+- the pid of the task(process) which initialized the timer
+- the name of the process which initialized the timer
+- the function where the timer was intialized
+- the callback function which is associated to the timer
+- the number of events (callbacks)
+
+timer_stats adds an entry to /proc: /proc/timer_stats
+
+This entry is used to control the statistics functionality and to read out the
+sampled information.
+
+The timer_stats functionality is inactive on bootup.
+
+To activate a sample period issue:
+# echo 1 >/proc/timer_stats
+
+To stop a sample period issue:
+# echo 0 >/proc/timer_stats
+
+The statistics can be retrieved by:
+# cat /proc/timer_stats
+
+The readout of /proc/timer_stats automatically disables sampling. The sampled
+information is kept until a new sample period is started. This allows multiple
+readouts.
+
+Sample output of /proc/timer_stats:
+
+Timerstats sample period: 3.888770 s
+  12,     0 swapper          hrtimer_stop_sched_tick (hrtimer_sched_tick)
+  15,     1 swapper          hcd_submit_urb (rh_timer_func)
+   4,   959 kedac            schedule_timeout (process_timeout)
+   1,     0 swapper          page_writeback_init (wb_timer_fn)
+  28,     0 swapper          hrtimer_stop_sched_tick (hrtimer_sched_tick)
+  22,  2948 IRQ 4            tty_flip_buffer_push (delayed_work_timer_fn)
+   3,  3100 bash             schedule_timeout (process_timeout)
+   1,     1 swapper          queue_delayed_work_on (delayed_work_timer_fn)
+   1,     1 swapper          queue_delayed_work_on (delayed_work_timer_fn)
+   1,     1 swapper          neigh_table_init_no_netlink (neigh_periodic_timer)
+   1,  2292 ip               __netdev_watchdog_up (dev_watchdog)
+   1,    23 events/1         do_cache_clean (delayed_work_timer_fn)
+90 total events, 30.0 events/sec
+
+The first column is the number of events, the second column the pid, the third
+column is the name of the process. The forth column shows the function which
+initialized the timer and in parantheses the callback function which was
+executed on expiry.
+
+    Thomas, Ingo
+

Documentation/hrtimers/highres.txt

@@ -0,0 +1,249 @@
+High resolution timers and dynamic ticks design notes
+-----------------------------------------------------
+
+Further information can be found in the paper of the OLS 2006 talk "hrtimers
+and beyond". The paper is part of the OLS 2006 Proceedings Volume 1, which can
+be found on the OLS website:
+http://www.linuxsymposium.org/2006/linuxsymposium_procv1.pdf
+
+The slides to this talk are available from:
+http://tglx.de/projects/hrtimers/ols2006-hrtimers.pdf
+
+The slides contain five figures (pages 2, 15, 18, 20, 22), which illustrate the
+changes in the time(r) related Linux subsystems. Figure #1 (p. 2) shows the
+design of the Linux time(r) system before hrtimers and other building blocks
+got merged into mainline.
+
+Note: the paper and the slides are talking about "clock event source", while we
+switched to the name "clock event devices" in meantime.
+
+The design contains the following basic building blocks:
+
+- hrtimer base infrastructure
+- timeofday and clock source management
+- clock event management
+- high resolution timer functionality
+- dynamic ticks
+
+
+hrtimer base infrastructure
+---------------------------
+
+The hrtimer base infrastructure was merged into the 2.6.16 kernel. Details of
+the base implementation are covered in Documentation/hrtimers/hrtimer.txt. See
+also figure #2 (OLS slides p. 15)
+
+The main differences to the timer wheel, which holds the armed timer_list type
+timers are:
+       - time ordered enqueueing into a rb-tree
+       - independent of ticks (the processing is based on nanoseconds)
+
+
+timeofday and clock source management
+-------------------------------------
+
+John Stultz's Generic Time Of Day (GTOD) framework moves a large portion of
+code out of the architecture-specific areas into a generic management
+framework, as illustrated in figure #3 (OLS slides p. 18). The architecture
+specific portion is reduced to the low level hardware details of the clock
+sources, which are registered in the framework and selected on a quality based
+decision. The low level code provides hardware setup and readout routines and
+initializes data structures, which are used by the generic time keeping code to
+convert the clock ticks to nanosecond based time values. All other time keeping
+related functionality is moved into the generic code. The GTOD base patch got
+merged into the 2.6.18 kernel.
+
+Further information about the Generic Time Of Day framework is available in the
+OLS 2005 Proceedings Volume 1:
+http://www.linuxsymposium.org/2005/linuxsymposium_procv1.pdf
+
+The paper "We Are Not Getting Any Younger: A New Approach to Time and
+Timers" was written by J. Stultz, D.V. Hart, & N. Aravamudan.
+
+Figure #3 (OLS slides p.18) illustrates the transformation.
+
+
+clock event management
+----------------------
+
+While clock sources provide read access to the monotonically increasing time
+value, clock event devices are used to schedule the next event
+interrupt(s). The next event is currently defined to be periodic, with its
+period defined at compile time. The setup and selection of the event device
+for various event driven functionalities is hardwired into the architecture
+dependent code. This results in duplicated code across all architectures and
+makes it extremely difficult to change the configuration of the system to use
+event interrupt devices other than those already built into the
+architecture. Another implication of the current design is that it is necessary
+to touch all the architecture-specific implementations in order to provide new
+functionality like high resolution timers or dynamic ticks.
+
+The clock events subsystem tries to address this problem by providing a generic
+solution to manage clock event devices and their usage for the various clock
+event driven kernel functionalities. The goal of the clock event subsystem is
+to minimize the clock event related architecture dependent code to the pure
+hardware related handling and to allow easy addition and utilization of new
+clock event devices. It also minimizes the duplicated code across the
+architectures as it provides generic functionality down to the interrupt
+service handler, which is almost inherently hardware dependent.
+
+Clock event devices are registered either by the architecture dependent boot
+code or at module insertion time. Each clock event device fills a data
+structure with clock-specific property parameters and callback functions. The
+clock event management decides, by using the specified property parameters, the
+set of system functions a clock event device will be used to support. This
+includes the distinction of per-CPU and per-system global event devices.
+
+System-level global event devices are used for the Linux periodic tick. Per-CPU
+event devices are used to provide local CPU functionality such as process
+accounting, profiling, and high resolution timers.
+
+The management layer assignes one or more of the folliwing functions to a clock
+event device:
+      - system global periodic tick (jiffies update)
+      - cpu local update_process_times
+      - cpu local profiling
+      - cpu local next event interrupt (non periodic mode)
+
+The clock event device delegates the selection of those timer interrupt related
+functions completely to the management layer. The clock management layer stores
+a function pointer in the device description structure, which has to be called
+from the hardware level handler. This removes a lot of duplicated code from the
+architecture specific timer interrupt handlers and hands the control over the
+clock event devices and the assignment of timer interrupt related functionality
+to the core code.
+
+The clock event layer API is rather small. Aside from the clock event device
+registration interface it provides functions to schedule the next event
+interrupt, clock event device notification service and support for suspend and
+resume.
+
+The framework adds about 700 lines of code which results in a 2KB increase of
+the kernel binary size. The conversion of i386 removes about 100 lines of
+code. The binary size decrease is in the range of 400 byte. We believe that the
+increase of flexibility and the avoidance of duplicated code across
+architectures justifies the slight increase of the binary size.
+
+The conversion of an architecture has no functional impact, but allows to
+utilize the high resolution and dynamic tick functionalites without any change
+to the clock event device and timer interrupt code. After the conversion the
+enabling of high resolution timers and dynamic ticks is simply provided by
+adding the kernel/time/Kconfig file to the architecture specific Kconfig and
+adding the dynamic tick specific calls to the idle routine (a total of 3 lines
+added to the idle function and the Kconfig file)
+
+Figure #4 (OLS slides p.20) illustrates the transformation.
+
+
+high resolution timer functionality
+-----------------------------------
+
+During system boot it is not possible to use the high resolution timer
+functionality, while making it possible would be difficult and would serve no
+useful function. The initialization of the clock event device framework, the
+clock source framework (GTOD) and hrtimers itself has to be done and
+appropriate clock sources and clock event devices have to be registered before
+the high resolution functionality can work. Up to the point where hrtimers are
+initialized, the system works in the usual low resolution periodic mode. The
+clock source and the clock event device layers provide notification functions
+which inform hrtimers about availability of new hardware. hrtimers validates
+the usability of the registered clock sources and clock event devices before
+switching to high resolution mode. This ensures also that a kernel which is
+configured for high resolution timers can run on a system which lacks the
+necessary hardware support.
+
+The high resolution timer code does not support SMP machines which have only
+global clock event devices. The support of such hardware would involve IPI
+calls when an interrupt happens. The overhead would be much larger than the
+benefit. This is the reason why we currently disable high resolution and
+dynamic ticks on i386 SMP systems which stop the local APIC in C3 power
+state. A workaround is available as an idea, but the problem has not been
+tackled yet.
+
+The time ordered insertion of timers provides all the infrastructure to decide
+whether the event device has to be reprogrammed when a timer is added. The
+decision is made per timer base and synchronized across per-cpu timer bases in
+a support function. The design allows the system to utilize separate per-CPU
+clock event devices for the per-CPU timer bases, but currently only one
+reprogrammable clock event device per-CPU is utilized.
+
+When the timer interrupt happens, the next event interrupt handler is called
+from the clock event distribution code and moves expired timers from the
+red-black tree to a separate double linked list and invokes the softirq
+handler. An additional mode field in the hrtimer structure allows the system to
+execute callback functions directly from the next event interrupt handler. This
+is restricted to code which can safely be executed in the hard interrupt
+context. This applies, for example, to the common case of a wakeup function as
+used by nanosleep. The advantage of executing the handler in the interrupt
+context is the avoidance of up to two context switches - from the interrupted
+context to the softirq and to the task which is woken up by the expired
+timer.
+
+Once a system has switched to high resolution mode, the periodic tick is
+switched off. This disables the per system global periodic clock event device -
+e.g. the PIT on i386 SMP systems.
+
+The periodic tick functionality is provided by an per-cpu hrtimer. The callback
+function is executed in the next event interrupt context and updates jiffies
+and calls update_process_times and profiling. The implementation of the hrtimer
+based periodic tick is designed to be extended with dynamic tick functionality.
+This allows to use a single clock event device to schedule high resolution
+timer and periodic events (jiffies tick, profiling, process accounting) on UP
+systems. This has been proved to work with the PIT on i386 and the Incrementer
+on PPC.
+
+The softirq for running the hrtimer queues and executing the callbacks has been
+separated from the tick bound timer softirq to allow accurate delivery of high
+resolution timer signals which are used by itimer and POSIX interval
+timers. The execution of this softirq can still be delayed by other softirqs,
+but the overall latencies have been significantly improved by this separation.
+
+Figure #5 (OLS slides p.22) illustrates the transformation.
+
+
+dynamic ticks
+-------------
+
+Dynamic ticks are the logical consequence of the hrtimer based periodic tick
+replacement (sched_tick). The functionality of the sched_tick hrtimer is
+extended by three functions:
+
+- hrtimer_stop_sched_tick
+- hrtimer_restart_sched_tick
+- hrtimer_update_jiffies
+
+hrtimer_stop_sched_tick() is called when a CPU goes into idle state. The code
+evaluates the next scheduled timer event (from both hrtimers and the timer
+wheel) and in case that the next event is further away than the next tick it
+reprograms the sched_tick to this future event, to allow longer idle sleeps
+without worthless interruption by the periodic tick. The function is also
+called when an interrupt happens during the idle period, which does not cause a
+reschedule. The call is necessary as the interrupt handler might have armed a
+new timer whose expiry time is before the time which was identified as the
+nearest event in the previous call to hrtimer_stop_sched_tick.
+
+hrtimer_restart_sched_tick() is called when the CPU leaves the idle state before
+it calls schedule(). hrtimer_restart_sched_tick() resumes the periodic tick,
+which is kept active until the next call to hrtimer_stop_sched_tick().
+
+hrtimer_update_jiffies() is called from irq_enter() when an interrupt happens
+in the idle period to make sure that jiffies are up to date and the interrupt
+handler has not to deal with an eventually stale jiffy value.
+
+The dynamic tick feature provides statistical values which are exported to
+userspace via /proc/stats and can be made available for enhanced power
+management control.
+
+The implementation leaves room for further development like full tickless
+systems, where the time slice is controlled by the scheduler, variable
+frequency profiling, and a complete removal of jiffies in the future.
+
+
+Aside the current initial submission of i386 support, the patchset has been
+extended to x86_64 and ARM already. Initial (work in progress) support is also
+available for MIPS and PowerPC.
+
+	  Thomas, Ingo
+
+
+

Documentation/i2c/busses/i2c-i801

@@ -48,14 +48,9 @@ following:
 The SMBus controller is function 3 in device 1f. Class 0c05 is SMBus Serial
 Controller.
 
-If you do NOT see the 24x3 device at function 3, and you can't figure out
-any way in the BIOS to enable it,
-
 The ICH chips are quite similar to Intel's PIIX4 chip, at least in the
 SMBus controller.
 
-See the file i2c-piix4 for some additional information.
-
 
 Process Call Support
 --------------------
@@ -74,6 +69,61 @@ SMBus 2.0 Support
 
 The 82801DB (ICH4) and later chips support several SMBus 2.0 features.
 
+
+Hidden ICH SMBus
+----------------
+
+If your system has an Intel ICH south bridge, but you do NOT see the
+SMBus device at 00:1f.3 in lspci, and you can't figure out any way in the
+BIOS to enable it, it means it has been hidden by the BIOS code. Asus is
+well known for first doing this on their P4B motherboard, and many other
+boards after that. Some vendor machines are affected as well.
+
+The first thing to try is the "i2c_ec" ACPI driver. It could be that the
+SMBus was hidden on purpose because it'll be driven by ACPI. If the
+i2c_ec driver works for you, just forget about the i2c-i801 driver and
+don't try to unhide the ICH SMBus. Even if i2c_ec doesn't work, you
+better make sure that the SMBus isn't used by the ACPI code. Try loading
+the "fan" and "thermal" drivers, and check in /proc/acpi/fan and
+/proc/acpi/thermal_zone. If you find anything there, it's likely that
+the ACPI is accessing the SMBus and it's safer not to unhide it. Only
+once you are certain that ACPI isn't using the SMBus, you can attempt
+to unhide it.
+
+In order to unhide the SMBus, we need to change the value of a PCI
+register before the kernel enumerates the PCI devices. This is done in
+drivers/pci/quirks.c, where all affected boards must be listed (see
+function asus_hides_smbus_hostbridge.) If the SMBus device is missing,
+and you think there's something interesting on the SMBus (e.g. a
+hardware monitoring chip), you need to add your board to the list.
+
+The motherboard is identified using the subvendor and subdevice IDs of the
+host bridge PCI device. Get yours with "lspci -n -v -s 00:00.0":
+
+00:00.0 Class 0600: 8086:2570 (rev 02)
+        Subsystem: 1043:80f2
+        Flags: bus master, fast devsel, latency 0
+        Memory at fc000000 (32-bit, prefetchable) [size=32M]
+        Capabilities: [e4] #09 [2106]
+        Capabilities: [a0] AGP version 3.0
+
+Here the host bridge ID is 2570 (82865G/PE/P), the subvendor ID is 1043
+(Asus) and the subdevice ID is 80f2 (P4P800-X). You can find the symbolic
+names for the bridge ID and the subvendor ID in include/linux/pci_ids.h,
+and then add a case for your subdevice ID at the right place in
+drivers/pci/quirks.c. Then please give it very good testing, to make sure
+that the unhidden SMBus doesn't conflict with e.g. ACPI.
+
+If it works, proves useful (i.e. there are usable chips on the SMBus)
+and seems safe, please submit a patch for inclusion into the kernel.
+
+Note: There's a useful script in lm_sensors 2.10.2 and later, named
+unhide_ICH_SMBus (in prog/hotplug), which uses the fakephp driver to
+temporarily unhide the SMBus without having to patch and recompile your
+kernel. It's very convenient if you just want to check if there's
+anything interesting on your hidden ICH SMBus.
+
+
 **********************
 The lm_sensors project gratefully acknowledges the support of Texas
 Instruments in the initial development of this driver.

Documentation/i2c/busses/i2c-parport

@@ -19,6 +19,7 @@ It currently supports the following devices:
  * (type=4) Analog Devices ADM1032 evaluation board
  * (type=5) Analog Devices evaluation boards: ADM1025, ADM1030, ADM1031
  * (type=6) Barco LPT->DVI (K5800236) adapter
+ * (type=7) One For All JP1 parallel port adapter
 
 These devices use different pinout configurations, so you have to tell
 the driver what you have, using the type module parameter. There is no
@@ -157,3 +158,17 @@ many more, using /dev/velleman.
   http://home.wanadoo.nl/hihihi/libk8005.htm
   http://struyve.mine.nu:8080/index.php?block=k8000
   http://sourceforge.net/projects/libk8005/
+
+
+One For All JP1 parallel port adapter
+-------------------------------------
+
+The JP1 project revolves around a set of remote controls which expose
+the I2C bus their internal configuration EEPROM lives on via a 6 pin
+jumper in the battery compartment. More details can be found at:
+
+http://www.hifi-remote.com/jp1/
+
+Details of the simple parallel port hardware can be found at:
+
+http://www.hifi-remote.com/jp1/hardware.shtml

Documentation/i2c/busses/i2c-piix4

@@ -6,7 +6,7 @@ Supported adapters:
     Datasheet: Publicly available at the Intel website
   * ServerWorks OSB4, CSB5, CSB6 and HT-1000 southbridges
     Datasheet: Only available via NDA from ServerWorks
-  * ATI IXP southbridges IXP200, IXP300, IXP400
+  * ATI IXP200, IXP300, IXP400 and SB600 southbridges
     Datasheet: Not publicly available
   * Standard Microsystems (SMSC) SLC90E66 (Victory66) southbridge
     Datasheet: Publicly available at the SMSC website http://www.smsc.com

Documentation/i2c/busses/i2c-viapro

@@ -13,6 +13,9 @@ Supported adapters:
   * VIA Technologies, Inc. VT8235, VT8237R, VT8237A, VT8251
     Datasheet: available on request and under NDA from VIA
 
+  * VIA Technologies, Inc. CX700
+    Datasheet: available on request and under NDA from VIA
+
 Authors:
 	Kyösti Mälkki <kmalkki@cc.hut.fi>,
 	Mark D. Studebaker <mdsxyz123@yahoo.com>,
@@ -44,6 +47,7 @@ Your lspci -n listing must show one of these :
  device 1106:3227   (VT8237R)
  device 1106:3337   (VT8237A)
  device 1106:3287   (VT8251)
+ device 1106:8324   (CX700)
 
 If none of these show up, you should look in the BIOS for settings like
 enable ACPI / SMBus or even USB.
@@ -51,3 +55,6 @@ enable ACPI / SMBus or even USB.
 Except for the oldest chips (VT82C596A/B, VT82C686A and most probably
 VT8231), this driver supports I2C block transactions. Such transactions
 are mainly useful to read from and write to EEPROMs.
+
+The CX700 additionally appears to support SMBus PEC, although this driver
+doesn't implement it yet.

Documentation/i2c/porting-clients

@@ -129,6 +129,12 @@ Technical changes:
   structure, those name member should be initialized to a driver name
   string. i2c_driver itself has no name member anymore.
 
+* [Driver model] Instead of shutdown or reboot notifiers, provide a
+  shutdown() method in your driver.
+
+* [Power management] Use the driver model suspend() and resume()
+  callbacks instead of the obsolete pm_register() calls.
+
 Coding policy:
 
 * [Copyright] Use (C), not (c), for copyright.

Documentation/i2c/smbus-protocol

@@ -97,7 +97,7 @@ SMBus Write Word Data
 =====================
 
 This is the opposite operation of the Read Word Data command. 16 bits
-of data is read from a device, from a designated register that is 
+of data is written to a device, to the designated register that is
 specified through the Comm byte. 
 
 S Addr Wr [A] Comm [A] DataLow [A] DataHigh [A] P

Documentation/i2c/writing-clients

@@ -21,20 +21,26 @@ The driver structure
 
 Usually, you will implement a single driver structure, and instantiate
 all clients from it. Remember, a driver structure contains general access 
-routines, a client structure specific information like the actual I2C
-address.
+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.
 
 static struct i2c_driver foo_driver = {
 	.driver = {
 		.name	= "foo",
 	},
-	.attach_adapter	= &foo_attach_adapter,
-	.detach_client	= &foo_detach_client,
-	.command	= &foo_command /* may be NULL */
+	.attach_adapter	= foo_attach_adapter,
+	.detach_client	= foo_detach_client,
+	.shutdown	= foo_shutdown,	/* optional */
+	.suspend	= foo_suspend,	/* optional */
+	.resume		= foo_resume,	/* optional */
+	.command	= foo_command,	/* optional */
 }
  
-The name field must match the driver name, including the case. It must not
-contain spaces, and may be up to 31 characters long.
+The name field is the driver name, and must not contain spaces.  It
+should match the module name (if the driver can be compiled as a module),
+although you can use MODULE_ALIAS (passing "foo" in this example) to add
+another name for the module.
 
 All other fields are for call-back functions which will be explained 
 below.
@@ -43,11 +49,18 @@ below.
 Extra client data
 =================
 
-The client structure has a special `data' field that can point to any
-structure at all. You can use this to keep client-specific data. You
+Each client structure has a special `data' field that can point to any
+structure at all.  You should use this to keep device-specific data,
+especially in drivers that handle multiple I2C or SMBUS devices.  You
 do not always need this, but especially for `sensors' drivers, it can
 be very useful.
 
+	/* store the value */
+	void i2c_set_clientdata(struct i2c_client *client, void *data);
+
+	/* retrieve the value */
+	void *i2c_get_clientdata(struct i2c_client *client);
+
 An example structure is below.
 
   struct foo_data {
@@ -493,6 +506,33 @@ by `__init_data'.  Hose functions and structures can be removed after
 kernel booting (or module loading) is completed.
 
 
+Power Management
+================
+
+If your I2C device needs special handling when entering a system low
+power state -- like putting a transceiver into a low power mode, or
+activating a system wakeup mechanism -- do that in the suspend() method.
+The resume() method should reverse what the suspend() method does.
+
+These are standard driver model calls, and they work just like they
+would for any other driver stack.  The calls can sleep, and can use
+I2C messaging to the device being suspended or resumed (since their
+parent I2C adapter is active when these calls are issued, and IRQs
+are still enabled).
+
+
+System Shutdown
+===============
+
+If your I2C device needs special handling when the system shuts down
+or reboots (including kexec) -- like turning something off -- use a
+shutdown() method.
+
+Again, this is a standard driver model call, working just like it
+would for any other driver stack:  the calls can sleep, and can use
+I2C messaging.
+
+
 Command function
 ================
 

Documentation/kernel-parameters.txt

@@ -104,6 +104,9 @@ loader, and have no meaning to the kernel directly.
 Do not modify the syntax of boot loader parameters without extreme
 need or coordination with <Documentation/i386/boot.txt>.
 
+There are also arch-specific kernel-parameters not documented here.
+See for example <Documentation/x86_64/boot-options.txt>.
+
 Note that ALL kernel parameters listed below are CASE SENSITIVE, and that
 a trailing = on the name of any parameter states that that parameter will
 be entered as an environment variable, whereas its absence indicates that
@@ -361,6 +364,11 @@ and is between 256 and 4096 characters. It is defined in the file
 			clocksource is not available, it defaults to PIT.
 			Format: { pit | tsc | cyclone | pmtmr }
 
+	code_bytes	[IA32] How many bytes of object code to print in an
+			oops report.
+			Range: 0 - 8192
+			Default: 64
+
 	disable_8254_timer
 	enable_8254_timer
 			[IA32/X86_64] Disable/Enable interrupt 0 timer routing
@@ -601,6 +609,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			highmem otherwise. This also works to reduce highmem
 			size on bigger boxes.
 
+	highres=	[KNL] Enable/disable high resolution timer mode.
+			Valid parameters: "on", "off"
+			Default: "on"
+
 	hisax=		[HW,ISDN]
 			See Documentation/isdn/README.HiSax.
 
@@ -1070,6 +1082,10 @@ and is between 256 and 4096 characters. It is defined in the file
 			in certain environments such as networked servers or
 			real-time systems.
 
+	nohz=		[KNL] Boottime enable/disable dynamic ticks
+			Valid arguments: on, off
+			Default: on
+
 	noirqbalance	[IA-32,SMP,KNL] Disable kernel irq balancing
 
 	noirqdebug	[IA-32] Disables the code which attempts to detect and

Documentation/powerpc/booting-without-of.txt

@@ -1334,6 +1334,9 @@ platforms are moved over to use the flattened-device-tree model.
       fsl-usb2-mph compatible controllers.  Either this property or
       "port0" (or both) must be defined for "fsl-usb2-mph" compatible 
       controllers.
+    - dr_mode : indicates the working mode for "fsl-usb2-dr" compatible
+      controllers.  Can be "host", "peripheral", or "otg".  Default to
+      "host" if not defined for backward compatibility.
 
    Recommended properties :
     - interrupts : <a b> where a is the interrupt number and b is a
@@ -1367,6 +1370,7 @@ platforms are moved over to use the flattened-device-tree model.
 		#size-cells = <0>;
 		interrupt-parent = <700>;
 		interrupts = <26 1>;
+		dr_mode = "otg";
 		phy = "ulpi";
 	};
 

Documentation/powerpc/mpc52xx-device-tree-bindings.txt

@@ -1,7 +1,7 @@
-MPC52xx Device Tree Bindings
+MPC5200 Device Tree Bindings
 ----------------------------
 
-(c) 2006 Secret Lab Technologies Ltd
+(c) 2006-2007 Secret Lab Technologies Ltd
 Grant Likely <grant.likely at secretlab.ca>
 
 ********** DRAFT ***********
@@ -20,11 +20,11 @@ described in Documentation/powerpc/booting-without-of.txt), or passed
 by Open Firmare (IEEE 1275) compatible firmware using an OF compatible
 client interface API.
 
-This document specifies the requirements on the device-tree for mpc52xx
+This document specifies the requirements on the device-tree for mpc5200
 based boards.  These requirements are above and beyond the details
 specified in either the OpenFirmware spec or booting-without-of.txt
 
-All new mpc52xx-based boards are expected to match this document.  In
+All new mpc5200-based boards are expected to match this document.  In
 cases where this document is not sufficient to support a new board port,
 this document should be updated as part of adding the new board support.
 
@@ -32,26 +32,26 @@ II - Philosophy
 ===============
 The core of this document is naming convention.  The whole point of
 defining this convention is to reduce or eliminate the number of
-special cases required to support a 52xx board.  If all 52xx boards
-follow the same convention, then generic 52xx support code will work
+special cases required to support a 5200 board.  If all 5200 boards
+follow the same convention, then generic 5200 support code will work
 rather than coding special cases for each new board.
 
 This section tries to capture the thought process behind why the naming
 convention is what it is.
 
-1. Node names
--------------
+1.  names
+---------
 There is strong convention/requirements already established for children
 of the root node.  'cpus' describes the processor cores, 'memory'
 describes memory, and 'chosen' provides boot configuration.  Other nodes
 are added to describe devices attached to the processor local bus.
+
 Following convention already established with other system-on-chip
-processors, MPC52xx boards must have an 'soc5200' node as a child of the
-root node.
+processors, 5200 device trees should use the name 'soc5200' for the
+parent node of on chip devices, and the root node should be its parent.
 
-The soc5200 node holds child nodes for all on chip devices.  Child nodes
-are typically named after the configured function.  ie. the FEC node is
-named 'ethernet', and a PSC in uart mode is named 'serial'.
+Child nodes are typically named after the configured function.  ie.
+the FEC node is named 'ethernet', and a PSC in uart mode is named 'serial'.
 
 2. device_type property
 -----------------------
@@ -66,28 +66,47 @@ exactly.
 Since device_type isn't enough to match devices to drivers, there also
 needs to be a naming convention for the compatible property.  Compatible
 is an list of device descriptions sorted from specific to generic.  For
-the mpc52xx, the required format for each compatible value is
-<chip>-<device>[-<mode>].  At the minimum, the list shall contain two
-items; the first specifying the exact chip, and the second specifying
-mpc52xx for the chip.
-
-ie. ethernet on mpc5200b: compatible = "mpc5200b-ethernet\0mpc52xx-ethernet"
-
-The idea here is that most drivers will match to the most generic field
-in the compatible list (mpc52xx-*), but can also test the more specific
-field for enabling bug fixes or extra features.
+the mpc5200, the required format for each compatible value is
+<chip>-<device>[-<mode>].  The OS should be able to match a device driver
+to the device based solely on the compatible value.  If two drivers
+match on the compatible list; the 'most compatible' driver should be
+selected.
+
+The split between the MPC5200 and the MPC5200B leaves a bit of a
+connundrum.  How should the compatible property be set up to provide
+maximum compatability information; but still acurately describe the
+chip?  For the MPC5200; the answer is easy.  Most of the SoC devices
+originally appeared on the MPC5200.  Since they didn't exist anywhere
+else; the 5200 compatible properties will contain only one item;
+"mpc5200-<device>".
+
+The 5200B is almost the same as the 5200, but not quite.  It fixes
+silicon bugs and it adds a small number of enhancements.  Most of the
+devices either provide exactly the same interface as on the 5200.  A few
+devices have extra functions but still have a backwards compatible mode.
+To express this infomation as completely as possible, 5200B device trees
+should have two items in the compatible list;
+"mpc5200b-<device>\0mpc5200-<device>".  It is *strongly* recommended
+that 5200B device trees follow this convention (instead of only listing
+the base mpc5200 item).
+
+If another chip appear on the market with one of the mpc5200 SoC
+devices, then the compatible list should include mpc5200-<device>.
+
+ie. ethernet on mpc5200: compatible = "mpc5200-ethernet"
+    ethernet on mpc5200b: compatible = "mpc5200b-ethernet\0mpc5200-ethernet"
 
 Modal devices, like PSCs, also append the configured function to the
 end of the compatible field.  ie. A PSC in i2s mode would specify
-"mpc52xx-psc-i2s", not "mpc52xx-i2s".  This convention is chosen to
+"mpc5200-psc-i2s", not "mpc5200-i2s".  This convention is chosen to
 avoid naming conflicts with non-psc devices providing the same
-function.  For example, "mpc52xx-spi" and "mpc52xx-psc-spi" describe
+function.  For example, "mpc5200-spi" and "mpc5200-psc-spi" describe
 the mpc5200 simple spi device and a PSC spi mode respectively.
 
 If the soc device is more generic and present on other SOCs, the
 compatible property can specify the more generic device type also.
 
-ie. mscan: compatible = "mpc5200-mscan\0mpc52xx-mscan\0fsl,mscan";
+ie. mscan: compatible = "mpc5200-mscan\0fsl,mscan";
 
 At the time of writing, exact chip may be either 'mpc5200' or
 'mpc5200b'.
@@ -96,7 +115,7 @@ Device drivers should always try to match as generically as possible.
 
 III - Structure
 ===============
-The device tree for an mpc52xx board follows the structure defined in
+The device tree for an mpc5200 board follows the structure defined in
 booting-without-of.txt with the following additional notes:
 
 0) the root node
@@ -115,7 +134,7 @@ Typical memory description node; see booting-without-of.
 
 3) The soc5200 node
 -------------------
-This node describes the on chip SOC peripherals.  Every mpc52xx based
+This node describes the on chip SOC peripherals.  Every mpc5200 based
 board will have this node, and as such there is a common naming
 convention for SOC devices.
 
@@ -125,71 +144,111 @@ name			type		description
 device_type		string		must be "soc"
 ranges			int		should be <0 baseaddr baseaddr+10000>
 reg			int		must be <baseaddr 10000>
+compatible		string		mpc5200: "mpc5200-soc"
+					mpc5200b: "mpc5200b-soc\0mpc5200-soc"
+system-frequency	int		Fsystem frequency; source of all
+					other clocks.
+bus-frequency		int		IPB bus frequency in HZ.  Clock rate
+					used by most of the soc devices.
+#interrupt-cells	int		must be <3>.
 
 Recommended properties:
 name			type		description
 ----			----		-----------
-compatible		string		should be "<chip>-soc\0mpc52xx-soc"
-					ie. "mpc5200b-soc\0mpc52xx-soc"
-#interrupt-cells	int		must be <3>.  If it is not defined
-					here then it must be defined in every
-					soc device node.
-bus-frequency		int		IPB bus frequency in HZ.  Clock rate
-					used by most of the soc devices.
-					Defining it here avoids needing it
-					added to every device node.
+model			string		Exact model of the chip;
+					ie: model="fsl,mpc5200"
+revision		string		Silicon revision of chip
+					ie: revision="M08A"
+
+The 'model' and 'revision' properties are *strongly* recommended.  Having
+them presence acts as a bit of a safety net for working around as yet
+undiscovered bugs on one version of silicon.  For example, device drivers
+can use the model and revision properties to decide if a bug fix should
+be turned on.
 
 4) soc5200 child nodes
 ----------------------
 Any on chip SOC devices available to Linux must appear as soc5200 child nodes.
 
-Note: in the tables below, '*' matches all <chip> values.  ie.
-*-pic would translate to "mpc5200-pic\0mpc52xx-pic"
+Note: The tables below show the value for the mpc5200.  A mpc5200b device
+tree should use the "mpc5200b-<device>\0mpc5200-<device> form.
 
 Required soc5200 child nodes:
 name		device_type		compatible	Description
 ----		-----------		----------	-----------
-cdm@<addr>	cdm			*-cmd		Clock Distribution
-pic@<addr>	interrupt-controller	*-pic		need an interrupt
+cdm@<addr>	cdm			mpc5200-cmd	Clock Distribution
+pic@<addr>	interrupt-controller	mpc5200-pic	need an interrupt
 							controller to boot
-bestcomm@<addr>	dma-controller		*-bestcomm	52xx pic also requires
-							the bestcomm device
+bestcomm@<addr>	dma-controller		mpc5200-bestcomm 5200 pic also requires
+							 the bestcomm device
 
 Recommended soc5200 child nodes; populate as needed for your board
-name		device_type	compatible	Description
-----		-----------	----------	-----------
-gpt@<addr>	gpt		*-gpt		General purpose timers
-rtc@<addr>	rtc		*-rtc		Real time clock
-mscan@<addr>	mscan		*-mscan		CAN bus controller
-pci@<addr>	pci		*-pci		PCI bridge
-serial@<addr>	serial		*-psc-uart	PSC in serial mode
-i2s@<addr>	sound		*-psc-i2s	PSC in i2s mode
-ac97@<addr>	sound		*-psc-ac97	PSC in ac97 mode
-spi@<addr>	spi		*-psc-spi	PSC in spi mode
-irda@<addr>	irda		*-psc-irda	PSC in IrDA mode
-spi@<addr>	spi		*-spi		MPC52xx spi device
-ethernet@<addr>	network		*-fec		MPC52xx ethernet device
-ata@<addr>	ata		*-ata		IDE ATA interface
-i2c@<addr>	i2c		*-i2c		I2C controller
-usb@<addr>	usb-ohci-be	*-ohci,ohci-be	USB controller
-xlb@<addr>	xlb		*-xlb		XLB arbritrator
+name		device_type	compatible	  Description
+----		-----------	----------	  -----------
+gpt@<addr>	gpt		mpc5200-gpt	  General purpose timers
+rtc@<addr>	rtc		mpc5200-rtc	  Real time clock
+mscan@<addr>	mscan		mpc5200-mscan	  CAN bus controller
+pci@<addr>	pci		mpc5200-pci	  PCI bridge
+serial@<addr>	serial		mpc5200-psc-uart  PSC in serial mode
+i2s@<addr>	sound		mpc5200-psc-i2s	  PSC in i2s mode
+ac97@<addr>	sound		mpc5200-psc-ac97  PSC in ac97 mode
+spi@<addr>	spi		mpc5200-psc-spi	  PSC in spi mode
+irda@<addr>	irda		mpc5200-psc-irda  PSC in IrDA mode
+spi@<addr>	spi		mpc5200-spi	  MPC5200 spi device
+ethernet@<addr>	network		mpc5200-fec	  MPC5200 ethernet device
+ata@<addr>	ata		mpc5200-ata	  IDE ATA interface
+i2c@<addr>	i2c		mpc5200-i2c	  I2C controller
+usb@<addr>	usb-ohci-be	mpc5200-ohci,ohci-be	USB controller
+xlb@<addr>	xlb		mpc5200-xlb	  XLB arbritrator
+
+Important child node properties
+name		type		description
+----		----		-----------
+cell-index	int		When multiple devices are present, is the
+				index of the device in the hardware (ie. There
+				are 6 PSC on the 5200 numbered PSC1 to PSC6)
+				    PSC1 has 'cell-index = <0>'
+				    PSC4 has 'cell-index = <3>'
+
+5) General Purpose Timer nodes (child of soc5200 node)
+On the mpc5200 and 5200b, GPT0 has a watchdog timer function.  If the board
+design supports the internal wdt, then the device node for GPT0 should
+include the empty property 'has-wdt'.
+
+6) PSC nodes (child of soc5200 node)
+PSC nodes can define the optional 'port-number' property to force assignment
+order of serial ports.  For example, PSC5 might be physically connected to
+the port labeled 'COM1' and PSC1 wired to 'COM1'.  In this case, PSC5 would
+have a "port-number = <0>" property, and PSC1 would have "port-number = <1>".
+
+PSC in i2s mode:  The mpc5200 and mpc5200b PSCs are not compatible when in
+i2s mode.  An 'mpc5200b-psc-i2s' node cannot include 'mpc5200-psc-i2s' in the
+compatible field.
 
 IV - Extra Notes
 ================
 
 1. Interrupt mapping
 --------------------
-The mpc52xx pic driver splits hardware IRQ numbers into two levels.  The
+The mpc5200 pic driver splits hardware IRQ numbers into two levels.  The
 split reflects the layout of the PIC hardware itself, which groups
 interrupts into one of three groups; CRIT, MAIN or PERP.  Also, the
 Bestcomm dma engine has it's own set of interrupt sources which are
 cascaded off of peripheral interrupt 0, which the driver interprets as a
 fourth group, SDMA.
 
-The interrupts property for device nodes using the mpc52xx pic consists
+The interrupts property for device nodes using the mpc5200 pic consists
 of three cells; <L1 L2 level>
 
     L1 := [CRIT=0, MAIN=1, PERP=2, SDMA=3]
     L2 := interrupt number; directly mapped from the value in the
           "ICTL PerStat, MainStat, CritStat Encoded Register"
     level := [LEVEL_HIGH=0, EDGE_RISING=1, EDGE_FALLING=2, LEVEL_LOW=3]
+
+2. Shared registers
+-------------------
+Some SoC devices share registers between them.  ie. the i2c devices use
+a single clock control register, and almost all device are affected by
+the port_config register.  Devices which need to manipulate shared regs
+should look to the parent SoC node.  The soc node is responsible
+for arbitrating all shared register access.

Documentation/x86_64/boot-options.txt

@@ -180,40 +180,81 @@ PCI
   pci=lastbus=NUMBER	       Scan upto NUMBER busses, no matter what the mptable says.
   pci=noacpi		Don't use ACPI to set up PCI interrupt routing.
 
-IOMMU
-
- iommu=[size][,noagp][,off][,force][,noforce][,leak][,memaper[=order]][,merge]
-         [,forcesac][,fullflush][,nomerge][,noaperture][,calgary]
-   size  set size of iommu (in bytes)
-   noagp don't initialize the AGP driver and use full aperture.
-   off   don't use the IOMMU
-   leak  turn on simple iommu leak tracing (only when CONFIG_IOMMU_LEAK is on)
-   memaper[=order] allocate an own aperture over RAM with size 32MB^order.
-   noforce don't force IOMMU usage. Default.
-   force  Force IOMMU.
-   merge  Do SG merging. Implies force (experimental)
-   nomerge Don't do SG merging.
-   forcesac For SAC mode for masks <40bits  (experimental)
-   fullflush Flush IOMMU on each allocation (default)
-   nofullflush Don't use IOMMU fullflush
-   allowed  overwrite iommu off workarounds for specific chipsets.
-   soft	 Use software bounce buffering (default for Intel machines)
-   noaperture Don't touch the aperture for AGP.
-   allowdac Allow DMA >4GB
-	    When off all DMA over >4GB is forced through an IOMMU or bounce
-	    buffering.
-   nodac    Forbid DMA >4GB
-   panic    Always panic when IOMMU overflows
-   calgary  Use the Calgary IOMMU if it is available
-
-  swiotlb=pages[,force]
-
-  pages  Prereserve that many 128K pages for the software IO bounce buffering.
-  force  Force all IO through the software TLB.
-
-  calgary=[64k,128k,256k,512k,1M,2M,4M,8M]
-  calgary=[translate_empty_slots]
-  calgary=[disable=<PCI bus number>]
+IOMMU (input/output memory management unit)
+
+ Currently four x86-64 PCI-DMA mapping implementations exist:
+
+   1. <arch/x86_64/kernel/pci-nommu.c>: use no hardware/software IOMMU at all
+      (e.g. because you have < 3 GB memory).
+      Kernel boot message: "PCI-DMA: Disabling IOMMU"
+
+   2. <arch/x86_64/kernel/pci-gart.c>: AMD GART based hardware IOMMU.
+      Kernel boot message: "PCI-DMA: using GART IOMMU"
+
+   3. <arch/x86_64/kernel/pci-swiotlb.c> : Software IOMMU implementation. Used
+      e.g. if there is no hardware IOMMU in the system and it is need because
+      you have >3GB memory or told the kernel to us it (iommu=soft))
+      Kernel boot message: "PCI-DMA: Using software bounce buffering
+      for IO (SWIOTLB)"
+
+   4. <arch/x86_64/pci-calgary.c> : IBM Calgary hardware IOMMU. Used in IBM
+      pSeries and xSeries servers. This hardware IOMMU supports DMA address
+      mapping with memory protection, etc.
+      Kernel boot message: "PCI-DMA: Using Calgary IOMMU"
+
+ iommu=[<size>][,noagp][,off][,force][,noforce][,leak[=<nr_of_leak_pages>]
+	[,memaper[=<order>]][,merge][,forcesac][,fullflush][,nomerge]
+	[,noaperture][,calgary]
+
+  General iommu options:
+    off                Don't initialize and use any kind of IOMMU.
+    noforce            Don't force hardware IOMMU usage when it is not needed.
+                       (default).
+    force              Force the use of the hardware IOMMU even when it is
+                       not actually needed (e.g. because < 3 GB memory).
+    soft               Use software bounce buffering (SWIOTLB) (default for
+                       Intel machines). This can be used to prevent the usage
+                       of an available hardware IOMMU.
+
+  iommu options only relevant to the AMD GART hardware IOMMU:
+    <size>             Set the size of the remapping area in bytes.
+    allowed            Overwrite iommu off workarounds for specific chipsets.
+    fullflush          Flush IOMMU on each allocation (default).
+    nofullflush        Don't use IOMMU fullflush.
+    leak               Turn on simple iommu leak tracing (only when
+                       CONFIG_IOMMU_LEAK is on). Default number of leak pages
+                       is 20.
+    memaper[=<order>]  Allocate an own aperture over RAM with size 32MB<<order.
+                       (default: order=1, i.e. 64MB)
+    merge              Do scatter-gather (SG) merging. Implies "force"
+                       (experimental).
+    nomerge            Don't do scatter-gather (SG) merging.
+    noaperture         Ask the IOMMU not to touch the aperture for AGP.
+    forcesac           Force single-address cycle (SAC) mode for masks <40bits
+                       (experimental).
+    noagp              Don't initialize the AGP driver and use full aperture.
+    allowdac           Allow double-address cycle (DAC) mode, i.e. DMA >4GB.
+                       DAC is used with 32-bit PCI to push a 64-bit address in
+                       two cycles. When off all DMA over >4GB is forced through
+                       an IOMMU or software bounce buffering.
+    nodac              Forbid DAC mode, i.e. DMA >4GB.
+    panic              Always panic when IOMMU overflows.
+    calgary            Use the Calgary IOMMU if it is available
+
+  iommu options only relevant to the software bounce buffering (SWIOTLB) IOMMU
+  implementation:
+    swiotlb=<pages>[,force]
+    <pages>            Prereserve that many 128K pages for the software IO
+                       bounce buffering.
+    force              Force all IO through the software TLB.
+
+  Settings for the IBM Calgary hardware IOMMU currently found in IBM
+  pSeries and xSeries machines:
+
+    calgary=[64k,128k,256k,512k,1M,2M,4M,8M]
+    calgary=[translate_empty_slots]
+    calgary=[disable=<PCI bus number>]
+    panic              Always panic when IOMMU overflows
 
     64k,...,8M - Set the size of each PCI slot's translation table
     when using the Calgary IOMMU. This is the size of the translation
@@ -234,14 +275,14 @@ IOMMU
 
 Debugging
 
-  oops=panic Always panic on oopses. Default is to just kill the process,
-	     but there is a small probability of deadlocking the machine.
-	     This will also cause panics on machine check exceptions.
-	     Useful together with panic=30 to trigger a reboot.
+  oops=panic	Always panic on oopses. Default is to just kill the process,
+		but there is a small probability of deadlocking the machine.
+		This will also cause panics on machine check exceptions.
+		Useful together with panic=30 to trigger a reboot.
 
-  kstack=N   Print that many words from the kernel stack in oops dumps.
+  kstack=N	Print N words from the kernel stack in oops dumps.
 
-  pagefaulttrace Dump all page faults. Only useful for extreme debugging
+  pagefaulttrace  Dump all page faults. Only useful for extreme debugging
 		and will create a lot of output.
 
   call_trace=[old|both|newfallback|new]
@@ -251,15 +292,8 @@ Debugging
 		newfallback: use new unwinder but fall back to old if it gets
 			stuck (default)
 
-  call_trace=[old|both|newfallback|new]
-		old: use old inexact backtracer
-		new: use new exact dwarf2 unwinder
- 		both: print entries from both
-		newfallback: use new unwinder but fall back to old if it gets
-			stuck (default)
-
-Misc
+Miscellaneous
 
   noreplacement  Don't replace instructions with more appropriate ones
 		 for the CPU. This may be useful on asymmetric MP systems
-		 where some CPU have less capabilities than the others.
+		 where some CPUs have less capabilities than others.

Documentation/x86_64/cpu-hotplug-spec

@@ -2,7 +2,7 @@ Firmware support for CPU hotplug under Linux/x86-64
 ---------------------------------------------------
 
 Linux/x86-64 supports CPU hotplug now. For various reasons Linux wants to
-know in advance boot time the maximum number of CPUs that could be plugged
+know in advance of boot time the maximum number of CPUs that could be plugged
 into the system. ACPI 3.0 currently has no official way to supply
 this information from the firmware to the operating system.
 

Documentation/x86_64/kernel-stacks

@@ -9,9 +9,9 @@ zombie. While the thread is in user space the kernel stack is empty
 except for the thread_info structure at the bottom.
 
 In addition to the per thread stacks, there are specialized stacks
-associated with each cpu.  These stacks are only used while the kernel
-is in control on that cpu, when a cpu returns to user space the
-specialized stacks contain no useful data.  The main cpu stacks is
+associated with each CPU.  These stacks are only used while the kernel
+is in control on that CPU; when a CPU returns to user space the
+specialized stacks contain no useful data.  The main CPU stacks are:
 
 * Interrupt stack.  IRQSTACKSIZE
 
@@ -32,17 +32,17 @@ x86_64 also has a feature which is not available on i386, the ability
 to automatically switch to a new stack for designated events such as
 double fault or NMI, which makes it easier to handle these unusual
 events on x86_64.  This feature is called the Interrupt Stack Table
-(IST).  There can be up to 7 IST entries per cpu. The IST code is an
-index into the Task State Segment (TSS), the IST entries in the TSS
-point to dedicated stacks, each stack can be a different size.
+(IST).  There can be up to 7 IST entries per CPU. The IST code is an
+index into the Task State Segment (TSS). The IST entries in the TSS
+point to dedicated stacks; each stack can be a different size.
 
-An IST is selected by an non-zero value in the IST field of an
+An IST is selected by a non-zero value in the IST field of an
 interrupt-gate descriptor.  When an interrupt occurs and the hardware
 loads such a descriptor, the hardware automatically sets the new stack
 pointer based on the IST value, then invokes the interrupt handler.  If
 software wants to allow nested IST interrupts then the handler must
 adjust the IST values on entry to and exit from the interrupt handler.
-(this is occasionally done, e.g. for debug exceptions)
+(This is occasionally done, e.g. for debug exceptions.)
 
 Events with different IST codes (i.e. with different stacks) can be
 nested.  For example, a debug interrupt can safely be interrupted by an
@@ -58,17 +58,17 @@ The currently assigned IST stacks are :-
 
   Used for interrupt 12 - Stack Fault Exception (#SS).
 
-  This allows to recover from invalid stack segments. Rarely
+  This allows the CPU to recover from invalid stack segments. Rarely
   happens.
 
 * DOUBLEFAULT_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
 
   Used for interrupt 8 - Double Fault Exception (#DF).
 
-  Invoked when handling a exception causes another exception. Happens
-  when the kernel is very confused (e.g. kernel stack pointer corrupt)
-  Using a separate stack allows to recover from it well enough in many
-  cases to still output an oops.
+  Invoked when handling one exception causes another exception. Happens
+  when the kernel is very confused (e.g. kernel stack pointer corrupt).
+  Using a separate stack allows the kernel to recover from it well enough
+  in many cases to still output an oops.
 
 * NMI_STACK.  EXCEPTION_STKSZ (PAGE_SIZE).
 

Documentation/x86_64/machinecheck

@@ -0,0 +1,70 @@
+
+Configurable sysfs parameters for the x86-64 machine check code.
+
+Machine checks report internal hardware error conditions detected
+by the CPU. Uncorrected errors typically cause a machine check
+(often with panic), corrected ones cause a machine check log entry.
+
+Machine checks are organized in banks (normally associated with
+a hardware subsystem) and subevents in a bank. The exact meaning
+of the banks and subevent is CPU specific.
+
+mcelog knows how to decode them.
+
+When you see the "Machine check errors logged" message in the system
+log then mcelog should run to collect and decode machine check entries
+from /dev/mcelog. Normally mcelog should be run regularly from a cronjob.
+
+Each CPU has a directory in /sys/devices/system/machinecheck/machinecheckN
+(N = CPU number)
+
+The directory contains some configurable entries:
+
+Entries:
+
+bankNctl
+(N bank number)
+	64bit Hex bitmask enabling/disabling specific subevents for bank N
+	When a bit in the bitmask is zero then the respective
+	subevent will not be reported.
+	By default all events are enabled.
+	Note that BIOS maintain another mask to disable specific events
+	per bank.  This is not visible here
+
+The following entries appear for each CPU, but they are truly shared
+between all CPUs.
+
+check_interval
+	How often to poll for corrected machine check errors, in seconds
+	(Note output is hexademical). Default 5 minutes.
+
+tolerant
+	Tolerance level. When a machine check exception occurs for a non
+	corrected machine check the kernel can take different actions.
+	Since machine check exceptions can happen any time it is sometimes
+	risky for the kernel to kill a process because it defies
+	normal kernel locking rules. The tolerance level configures
+	how hard the kernel tries to recover even at some risk of deadlock.
+
+	0: always panic,
+	1: panic if deadlock possible,
+	2: try to avoid panic,
+   	3: never panic or exit (for testing only)
+
+	Default: 1
+
+	Note this only makes a difference if the CPU allows recovery
+	from a machine check exception. Current x86 CPUs generally do not.
+
+trigger
+	Program to run when a machine check event is detected.
+	This is an alternative to running mcelog regularly from cron
+	and allows to detect events faster.
+
+TBD document entries for AMD threshold interrupt configuration
+
+For more details about the x86 machine check architecture
+see the Intel and AMD architecture manuals from their developer websites.
+
+For more details about the architecture see
+see http://one.firstfloor.org/~andi/mce.pdf

Documentation/x86_64/mm.txt

@@ -3,26 +3,26 @@
 
 Virtual memory map with 4 level page tables:
 
-0000000000000000 - 00007fffffffffff (=47bits) user space, different per mm
+0000000000000000 - 00007fffffffffff (=47 bits) user space, different per mm
 hole caused by [48:63] sign extension
-ffff800000000000 - ffff80ffffffffff (=40bits) guard hole
-ffff810000000000 - ffffc0ffffffffff (=46bits) direct mapping of all phys. memory
-ffffc10000000000 - ffffc1ffffffffff (=40bits) hole
-ffffc20000000000 - ffffe1ffffffffff (=45bits) vmalloc/ioremap space
+ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
+ffff810000000000 - ffffc0ffffffffff (=46 bits) direct mapping of all phys. memory
+ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
+ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
 ... unused hole ...
-ffffffff80000000 - ffffffff82800000 (=40MB)   kernel text mapping, from phys 0
+ffffffff80000000 - ffffffff82800000 (=40 MB)   kernel text mapping, from phys 0
 ... unused hole ...
-ffffffff88000000 - fffffffffff00000 (=1919MB) module mapping space
+ffffffff88000000 - fffffffffff00000 (=1919 MB) module mapping space
 
-The direct mapping covers all memory in the system upto the highest
+The direct mapping covers all memory in the system up to the highest
 memory address (this means in some cases it can also include PCI memory
-holes)
+holes).
 
 vmalloc space is lazily synchronized into the different PML4 pages of
 the processes using the page fault handler, with init_level4_pgt as
 reference.
 
-Current X86-64 implementations only support 40 bit of address space,
-but we support upto 46bits. This expands into MBZ space in the page tables.
+Current X86-64 implementations only support 40 bits of address space,
+but we support up to 46 bits. This expands into MBZ space in the page tables.
 
 -Andi Kleen, Jul 2004

MAINTAINERS

@@ -620,6 +620,11 @@ P:	Haavard Skinnemoen
 M:	hskinnemoen@atmel.com
 S:	Supported
 
+ATMEL SPI DRIVER
+P:	Haavard Skinnemoen
+M:	hskinnemoen@atmel.com
+S:	Supported
+
 ATMEL WIRELESS DRIVER
 P:	Simon Kelley
 M:	simon@thekelleys.org.uk
@@ -2523,6 +2528,12 @@ M:	olof@lixom.net
 L:	netdev@vger.kernel.org
 S:	Maintained
 
+PA SEMI SMBUS DRIVER
+P:	Olof Johansson
+M:	olof@lixom.net
+L:	i2c@lm-sensors.org
+S:	Maintained
+
 PARALLEL PORT SUPPORT
 P:	Phil Blundell
 M:	philb@gnu.org
@@ -3768,6 +3779,7 @@ P:	Andi Kleen
 M:	ak@suse.de
 L:	discuss@x86-64.org
 W:	http://www.x86-64.org
+T:	quilt ftp://ftp.firstfloor.org/pub/ak/x86_64/quilt-current
 S:	Maintained
 
 YAM DRIVER FOR AX.25

Makefile

@@ -825,9 +825,6 @@ include/config/kernel.release: include/config/auto.conf FORCE
 # Listed in dependency order
 PHONY += prepare archprepare prepare0 prepare1 prepare2 prepare3
 
-# prepare-all is deprecated, use prepare as valid replacement
-PHONY += prepare-all
-
 # prepare3 is used to check if we are building in a separate output directory,
 # and if so do:
 # 1) Check that make has not been executed in the kernel src $(srctree)
@@ -860,7 +857,7 @@ prepare0: archprepare FORCE
 	$(Q)$(MAKE) $(build)=.
 
 # All the preparing..
-prepare prepare-all: prepare0
+prepare: prepare0
 
 # Leave this as default for preprocessing vmlinux.lds.S, which is now
 # done in arch/$(ARCH)/kernel/Makefile
@@ -931,6 +928,12 @@ headers_install: include/linux/version.h scripts_basic FORCE
 	$(Q)$(MAKE) $(build)=scripts scripts/unifdef
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.headersinst obj=include
 
+PHONY += headers_check_all
+headers_check_all: headers_install_all
+	$(Q)for arch in $(HDRARCHES); do \
+	 $(MAKE) ARCH=$$arch -f $(srctree)/scripts/Makefile.headersinst obj=include BIASMDIR=-bi-$$arch HDRCHECK=1 ;\
+	 done
+
 PHONY += headers_check
 headers_check: headers_install
 	$(Q)$(MAKE) -f $(srctree)/scripts/Makefile.headersinst obj=include HDRCHECK=1

arch/arm/kernel/irq.c

@@ -159,8 +159,7 @@ void __init init_IRQ(void)
 	int irq;
 
 	for (irq = 0; irq < NR_IRQS; irq++)
-		irq_desc[irq].status |= IRQ_NOREQUEST | IRQ_DELAYED_DISABLE |
-			IRQ_NOPROBE;
+		irq_desc[irq].status |= IRQ_NOREQUEST | IRQ_NOPROBE;
 
 #ifdef CONFIG_SMP
 	bad_irq_desc.affinity = CPU_MASK_ALL;

arch/arm/kernel/isa.c

@@ -70,5 +70,5 @@ register_isa_ports(unsigned int membase, unsigned int portbase, unsigned int por
 	isa_membase = membase;
 	isa_portbase = portbase;
 	isa_portshift = portshift;
-	isa_sysctl_header = register_sysctl_table(ctl_bus, 0);
+	isa_sysctl_header = register_sysctl_table(ctl_bus);
 }

arch/arm/mach-imx/time.c

@@ -87,7 +87,7 @@ static struct clocksource clocksource_imx = {
 	.read		= imx_get_cycles,
 	.mask		= 0xFFFFFFFF,
 	.shift 		= 20,
-	.is_continuous 	= 1,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static int __init imx_clocksource_init(void)

arch/arm/mach-ixp4xx/common.c

@@ -395,7 +395,7 @@ static struct clocksource clocksource_ixp4xx = {
 	.read		= ixp4xx_get_cycles,
 	.mask		= CLOCKSOURCE_MASK(32),
 	.shift 		= 20,
-	.is_continuous 	= 1,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 unsigned long ixp4xx_timer_freq = FREQ;

arch/arm/mach-netx/time.c

@@ -62,7 +62,7 @@ static struct clocksource clocksource_netx = {
 	.read		= netx_get_cycles,
 	.mask		= CLOCKSOURCE_MASK(32),
 	.shift 		= 20,
-	.is_continuous 	= 1,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 /*

arch/arm/mach-pxa/time.c

@@ -112,7 +112,7 @@ static struct clocksource clocksource_pxa = {
 	.read           = pxa_get_cycles,
 	.mask           = CLOCKSOURCE_MASK(32),
 	.shift          = 20,
-	.is_continuous  = 1,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static void __init pxa_timer_init(void)

arch/avr32/boards/atstk1000/atstk1002.c

@@ -8,7 +8,6 @@
  * published by the Free Software Foundation.
  */
 #include <linux/clk.h>
-#include <linux/device.h>
 #include <linux/etherdevice.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
@@ -36,12 +35,11 @@ static struct eth_addr __initdata hw_addr[2];
 static struct eth_platform_data __initdata eth_data[2];
 extern struct lcdc_platform_data atstk1000_fb0_data;
 
-static struct spi_board_info spi_board_info[] __initdata = {
+static struct spi_board_info spi0_board_info[] __initdata = {
 	{
+		/* QVGA display */
 		.modalias	= "ltv350qv",
-		.controller_data = (void *)GPIO_PIN_PA(4),
 		.max_speed_hz	= 16000000,
-		.bus_num	= 0,
 		.chip_select	= 1,
 	},
 };
@@ -149,8 +147,7 @@ static int __init atstk1002_init(void)
 
 	set_hw_addr(at32_add_device_eth(0, &eth_data[0]));
 
-	spi_register_board_info(spi_board_info, ARRAY_SIZE(spi_board_info));
-	at32_add_device_spi(0);
+	at32_add_device_spi(0, spi0_board_info, ARRAY_SIZE(spi0_board_info));
 	at32_add_device_lcdc(0, &atstk1000_fb0_data);
 
 	return 0;

arch/avr32/kernel/syscall_table.S

@@ -8,14 +8,6 @@
  * published by the Free Software Foundation.
  */
 
-#if !defined(CONFIG_NFSD) && !defined(CONFIG_NFSD_MODULE)
-#define sys_nfsservctl sys_ni_syscall
-#endif
-
-#if !defined(CONFIG_SYSV_IPC)
-# define sys_ipc	sys_ni_syscall
-#endif
-
 	.section .rodata,"a",@progbits
 	.type	sys_call_table,@object
 	.global	sys_call_table
@@ -129,7 +121,7 @@ sys_call_table:
 	.long	sys_getitimer		/* 105 */
 	.long	sys_swapoff
 	.long	sys_sysinfo
-	.long	sys_ipc
+	.long	sys_ni_syscall		/* was sys_ipc briefly */
 	.long	sys_sendfile
 	.long	sys_setdomainname	/* 110 */
 	.long	sys_newuname
@@ -287,4 +279,16 @@ sys_call_table:
 	.long	sys_tee
 	.long	sys_vmsplice
 	.long	__sys_epoll_pwait	/* 265 */
+	.long	sys_msgget
+	.long	sys_msgsnd
+	.long	sys_msgrcv
+	.long	sys_msgctl
+	.long	sys_semget		/* 270 */
+	.long	sys_semop
+	.long	sys_semctl
+	.long	sys_semtimedop
+	.long	sys_shmat
+	.long	sys_shmget		/* 275 */
+	.long	sys_shmdt
+	.long	sys_shmctl
 	.long	sys_ni_syscall		/* r8 is saturated at nr_syscalls */

arch/avr32/kernel/time.c

@@ -37,7 +37,7 @@ static struct clocksource clocksource_avr32 = {
 	.read		= read_cycle_count,
 	.mask		= CLOCKSOURCE_MASK(32),
 	.shift		= 16,
-	.is_continuous	= 1,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 /*

arch/avr32/mach-at32ap/at32ap7000.c

@@ -8,6 +8,7 @@
 #include <linux/clk.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
+#include <linux/spi/spi.h>
 
 #include <asm/io.h>
 
@@ -310,8 +311,6 @@ static void genclk_mode(struct clk *clk, int enabled)
 {
 	u32 control;
 
-	BUG_ON(clk->index > 7);
-
 	control = sm_readl(&system_manager, PM_GCCTRL + 4 * clk->index);
 	if (enabled)
 		control |= SM_BIT(CEN);
@@ -325,11 +324,6 @@ static unsigned long genclk_get_rate(struct clk *clk)
 	u32 control;
 	unsigned long div = 1;
 
-	BUG_ON(clk->index > 7);
-
-	if (!clk->parent)
-		return 0;
-
 	control = sm_readl(&system_manager, PM_GCCTRL + 4 * clk->index);
 	if (control & SM_BIT(DIVEN))
 		div = 2 * (SM_BFEXT(DIV, control) + 1);
@@ -342,11 +336,6 @@ static long genclk_set_rate(struct clk *clk, unsigned long rate, int apply)
 	u32 control;
 	unsigned long parent_rate, actual_rate, div;
 
-	BUG_ON(clk->index > 7);
-
-	if (!clk->parent)
-		return 0;
-
 	parent_rate = clk->parent->get_rate(clk->parent);
 	control = sm_readl(&system_manager, PM_GCCTRL + 4 * clk->index);
 
@@ -373,11 +362,8 @@ int genclk_set_parent(struct clk *clk, struct clk *parent)
 {
 	u32 control;
 
-	BUG_ON(clk->index > 7);
-
 	printk("clk %s: new parent %s (was %s)\n",
-	       clk->name, parent->name,
-	       clk->parent ? clk->parent->name : "(null)");
+	       clk->name, parent->name, clk->parent->name);
 
 	control = sm_readl(&system_manager, PM_GCCTRL + 4 * clk->index);
 
@@ -399,6 +385,22 @@ int genclk_set_parent(struct clk *clk, struct clk *parent)
 	return 0;
 }
 
+static void __init genclk_init_parent(struct clk *clk)
+{
+	u32 control;
+	struct clk *parent;
+
+	BUG_ON(clk->index > 7);
+
+	control = sm_readl(&system_manager, PM_GCCTRL + 4 * clk->index);
+	if (control & SM_BIT(OSCSEL))
+		parent = (control & SM_BIT(PLLSEL)) ? &pll1 : &osc1;
+	else
+		parent = (control & SM_BIT(PLLSEL)) ? &pll0 : &osc0;
+
+	clk->parent = parent;
+}
+
 /* --------------------------------------------------------------------
  *  System peripherals
  * -------------------------------------------------------------------- */
@@ -750,8 +752,41 @@ static struct resource atmel_spi1_resource[] = {
 DEFINE_DEV(atmel_spi, 1);
 DEV_CLK(spi_clk, atmel_spi1, pba, 1);
 
-struct platform_device *__init at32_add_device_spi(unsigned int id)
+static void
+at32_spi_setup_slaves(unsigned int bus_num, struct spi_board_info *b,
+		      unsigned int n, const u8 *pins)
+{
+	unsigned int pin, mode;
+
+	for (; n; n--, b++) {
+		b->bus_num = bus_num;
+		if (b->chip_select >= 4)
+			continue;
+		pin = (unsigned)b->controller_data;
+		if (!pin) {
+			pin = pins[b->chip_select];
+			b->controller_data = (void *)pin;
+		}
+		mode = AT32_GPIOF_OUTPUT;
+		if (!(b->mode & SPI_CS_HIGH))
+			mode |= AT32_GPIOF_HIGH;
+		at32_select_gpio(pin, mode);
+	}
+}
+
+struct platform_device *__init
+at32_add_device_spi(unsigned int id, struct spi_board_info *b, unsigned int n)
 {
+	/*
+	 * Manage the chipselects as GPIOs, normally using the same pins
+	 * the SPI controller expects; but boards can use other pins.
+	 */
+	static u8 __initdata spi0_pins[] =
+		{ GPIO_PIN_PA(3), GPIO_PIN_PA(4),
+		  GPIO_PIN_PA(5), GPIO_PIN_PA(20), };
+	static u8 __initdata spi1_pins[] =
+		{ GPIO_PIN_PB(2), GPIO_PIN_PB(3),
+		  GPIO_PIN_PB(4), GPIO_PIN_PA(27), };
 	struct platform_device *pdev;
 
 	switch (id) {
@@ -760,14 +795,7 @@ struct platform_device *__init at32_add_device_spi(unsigned int id)
 		select_peripheral(PA(0),  PERIPH_A, 0);	/* MISO	 */
 		select_peripheral(PA(1),  PERIPH_A, 0);	/* MOSI	 */
 		select_peripheral(PA(2),  PERIPH_A, 0);	/* SCK	 */
-
-		/* NPCS[2:0] */
-		at32_select_gpio(GPIO_PIN_PA(3),
-				 AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-		at32_select_gpio(GPIO_PIN_PA(4),
-				 AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-		at32_select_gpio(GPIO_PIN_PA(5),
-				 AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
+		at32_spi_setup_slaves(0, b, n, spi0_pins);
 		break;
 
 	case 1:
@@ -775,20 +803,14 @@ struct platform_device *__init at32_add_device_spi(unsigned int id)
 		select_peripheral(PB(0),  PERIPH_B, 0);	/* MISO  */
 		select_peripheral(PB(1),  PERIPH_B, 0);	/* MOSI  */
 		select_peripheral(PB(5),  PERIPH_B, 0);	/* SCK   */
-
-		/* NPCS[2:0] */
-		at32_select_gpio(GPIO_PIN_PB(2),
-				 AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-		at32_select_gpio(GPIO_PIN_PB(3),
-				 AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
-		at32_select_gpio(GPIO_PIN_PB(4),
-				 AT32_GPIOF_OUTPUT | AT32_GPIOF_HIGH);
+		at32_spi_setup_slaves(1, b, n, spi1_pins);
 		break;
 
 	default:
 		return NULL;
 	}
 
+	spi_register_board_info(b, n);
 	platform_device_register(pdev);
 	return pdev;
 }
@@ -872,6 +894,50 @@ at32_add_device_lcdc(unsigned int id, struct lcdc_platform_data *data)
 	return pdev;
 }
 
+/* --------------------------------------------------------------------
+ *  GCLK
+ * -------------------------------------------------------------------- */
+static struct clk gclk0 = {
+	.name		= "gclk0",
+	.mode		= genclk_mode,
+	.get_rate	= genclk_get_rate,
+	.set_rate	= genclk_set_rate,
+	.set_parent	= genclk_set_parent,
+	.index		= 0,
+};
+static struct clk gclk1 = {
+	.name		= "gclk1",
+	.mode		= genclk_mode,
+	.get_rate	= genclk_get_rate,
+	.set_rate	= genclk_set_rate,
+	.set_parent	= genclk_set_parent,
+	.index		= 1,
+};
+static struct clk gclk2 = {
+	.name		= "gclk2",
+	.mode		= genclk_mode,
+	.get_rate	= genclk_get_rate,
+	.set_rate	= genclk_set_rate,
+	.set_parent	= genclk_set_parent,
+	.index		= 2,
+};
+static struct clk gclk3 = {
+	.name		= "gclk3",
+	.mode		= genclk_mode,
+	.get_rate	= genclk_get_rate,
+	.set_rate	= genclk_set_rate,
+	.set_parent	= genclk_set_parent,
+	.index		= 3,
+};
+static struct clk gclk4 = {
+	.name		= "gclk4",
+	.mode		= genclk_mode,
+	.get_rate	= genclk_get_rate,
+	.set_rate	= genclk_set_rate,
+	.set_parent	= genclk_set_parent,
+	.index		= 4,
+};
+
 struct clk *at32_clock_list[] = {
 	&osc32k,
 	&osc0,
@@ -908,6 +974,11 @@ struct clk *at32_clock_list[] = {
 	&atmel_spi1_spi_clk,
 	&lcdc0_hclk,
 	&lcdc0_pixclk,
+	&gclk0,
+	&gclk1,
+	&gclk2,
+	&gclk3,
+	&gclk4,
 };
 unsigned int at32_nr_clocks = ARRAY_SIZE(at32_clock_list);
 
@@ -936,6 +1007,13 @@ void __init at32_clock_init(void)
 	if (sm_readl(sm, PM_PLL1) & SM_BIT(PLLOSC))
 		pll1.parent = &osc1;
 
+	genclk_init_parent(&gclk0);
+	genclk_init_parent(&gclk1);
+	genclk_init_parent(&gclk2);
+	genclk_init_parent(&gclk3);
+	genclk_init_parent(&gclk4);
+	genclk_init_parent(&lcdc0_pixclk);
+
 	/*
 	 * Turn on all clocks that have at least one user already, and
 	 * turn off everything else. We only do this for module

arch/avr32/mach-at32ap/clock.c

@@ -63,7 +63,11 @@ EXPORT_SYMBOL(clk_enable);
 
 static void __clk_disable(struct clk *clk)
 {
-	BUG_ON(clk->users == 0);
+	if (clk->users == 0) {
+		printk(KERN_ERR "%s: mismatched disable\n", clk->name);
+		WARN_ON(1);
+		return;
+	}
 
 	if (--clk->users == 0 && clk->mode)
 		clk->mode(clk, 0);

arch/frv/kernel/pm.c

@@ -125,7 +125,6 @@ unsigned long sleep_phys_sp(void *sp)
  * Use a temporary sysctl number. Horrid, but will be cleaned up in 2.6
  * when all the PM interfaces exist nicely.
  */
-#define CTL_PM 9899
 #define CTL_PM_SUSPEND 1
 #define CTL_PM_CMODE 2
 #define CTL_PM_P0 4
@@ -402,17 +401,53 @@ static int cm_sysctl(ctl_table *table, int __user *name, int nlen,
 
 static struct ctl_table pm_table[] =
 {
-	{CTL_PM_SUSPEND, "suspend", NULL, 0, 0200, NULL, &sysctl_pm_do_suspend},
-	{CTL_PM_CMODE, "cmode", &clock_cmode_current, sizeof(int), 0644, NULL, &cmode_procctl, &cmode_sysctl, NULL},
-	{CTL_PM_P0, "p0", &clock_p0_current, sizeof(int), 0644, NULL, &p0_procctl, &p0_sysctl, NULL},
-	{CTL_PM_CM, "cm", &clock_cm_current, sizeof(int), 0644, NULL, &cm_procctl, &cm_sysctl, NULL},
-	{0}
+	{
+		.ctl_name	= CTL_PM_SUSPEND,
+		.procname	= "suspend",
+		.data		= NULL,
+		.maxlen		= 0,
+		.mode		= 0200,
+		.proc_handler	= &sysctl_pm_do_suspend,
+	},
+	{
+		.ctl_name	= CTL_PM_CMODE,
+		.procname	= "cmode",
+		.data		= &clock_cmode_current,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &cmode_procctl,
+		.strategy	= &cmode_sysctl,
+	},
+	{
+		.ctl_name	= CTL_PM_P0,
+		.procname	= "p0",
+		.data		= &clock_p0_current,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &p0_procctl,
+		.strategy	= &p0_sysctl,
+	},
+	{
+		.ctl_name	= CTL_PM_CM,
+		.procname	= "cm",
+		.data		= &clock_cm_current,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &cm_procctl,
+		.strategy	= &cm_sysctl,
+	},
+	{ .ctl_name = 0}
 };
 
 static struct ctl_table pm_dir_table[] =
 {
-	{CTL_PM, "pm", NULL, 0, 0555, pm_table},
-	{0}
+	{
+		.ctl_name	= CTL_PM,
+		.procname	= "pm",
+		.mode		= 0555,
+		.child		= pm_table,
+	},
+	{ .ctl_name = 0}
 };
 
 /*
@@ -420,7 +455,7 @@ static struct ctl_table pm_dir_table[] =
  */
 static int __init pm_init(void)
 {
-	register_sysctl_table(pm_dir_table, 1);
+	register_sysctl_table(pm_dir_table);
 	return 0;
 }
 

arch/frv/kernel/sysctl.c

@@ -175,22 +175,40 @@ static int procctl_frv_pin_cxnr(ctl_table *table, int write, struct file *filp,
  */
 static struct ctl_table frv_table[] =
 {
-	{ 1, "cache-mode",	NULL, 0, 0644, NULL, &procctl_frv_cachemode },
+	{
+		.ctl_name 	= 1,
+		.procname 	= "cache-mode",
+		.data		= NULL,
+		.maxlen		= 0,
+		.mode		= 0644,
+		.proc_handler	= &procctl_frv_cachemode,
+	},
 #ifdef CONFIG_MMU
-	{ 2, "pin-cxnr",	NULL, 0, 0644, NULL, &procctl_frv_pin_cxnr },
+	{
+		.ctl_name	= 2,
+		.procname	= "pin-cxnr",
+		.data		= NULL,
+		.maxlen		= 0,
+		.mode		= 0644,
+		.proc_handler	= &procctl_frv_pin_cxnr
+	},
 #endif
-	{ 0 }
+	{}
 };
 
 /*
  * Use a temporary sysctl number. Horrid, but will be cleaned up in 2.6
  * when all the PM interfaces exist nicely.
  */
-#define CTL_FRV 9898
 static struct ctl_table frv_dir_table[] =
 {
-	{CTL_FRV, "frv", NULL, 0, 0555, frv_table},
-	{0}
+	{
+		.ctl_name	= CTL_FRV,
+		.procname	= "frv",
+		.mode 		= 0555,
+		.child		= frv_table
+	},
+	{}
 };
 
 /*
@@ -198,7 +216,7 @@ static struct ctl_table frv_dir_table[] =
  */
 static int __init frv_sysctl_init(void)
 {
-	register_sysctl_table(frv_dir_table, 1);
+	register_sysctl_table(frv_dir_table);
 	return 0;
 }
 

arch/i386/Kconfig

@@ -18,6 +18,18 @@ config GENERIC_TIME
 	bool
 	default y
 
+config CLOCKSOURCE_WATCHDOG
+	bool
+	default y
+
+config GENERIC_CLOCKEVENTS
+	bool
+	default y
+
+config GENERIC_CLOCKEVENTS_BROADCAST
+	bool
+	default y
+
 config LOCKDEP_SUPPORT
 	bool
 	default y
@@ -74,6 +86,8 @@ source "init/Kconfig"
 
 menu "Processor type and features"
 
+source "kernel/time/Kconfig"
+
 config SMP
 	bool "Symmetric multi-processing support"
 	---help---
@@ -203,6 +217,15 @@ config PARAVIRT
 	  However, when run without a hypervisor the kernel is
 	  theoretically slower.  If in doubt, say N.
 
+config VMI
+	bool "VMI Paravirt-ops support"
+	depends on PARAVIRT && !NO_HZ
+	default y
+	help
+	  VMI provides a paravirtualized interface to multiple hypervisors
+	  include VMware ESX server and Xen by connecting to a ROM module
+	  provided by the hypervisor.
+
 config ACPI_SRAT
 	bool
 	default y
@@ -1263,3 +1286,12 @@ config X86_TRAMPOLINE
 config KTIME_SCALAR
 	bool
 	default y
+
+config NO_IDLE_HZ
+	bool
+	depends on PARAVIRT
+	default y
+	help
+	  Switches the regular HZ timer off when the system is going idle.
+	  This helps a hypervisor detect that the Linux system is idle,
+	  reducing the overhead of idle systems.

arch/i386/Kconfig.cpu

@@ -226,11 +226,6 @@ config X86_CMPXCHG
 	depends on !M386
 	default y
 
-config X86_XADD
-	bool
-	depends on !M386
-	default y
-
 config X86_L1_CACHE_SHIFT
 	int
 	default "7" if MPENTIUM4 || X86_GENERIC

arch/i386/Kconfig.debug

@@ -87,7 +87,7 @@ config DOUBLEFAULT
 
 config DEBUG_PARAVIRT
 	bool "Enable some paravirtualization debugging"
-	default y
+	default n
 	depends on PARAVIRT && DEBUG_KERNEL
 	help
 	  Currently deliberately clobbers regs which are allowed to be

arch/i386/defconfig

@@ -1,7 +1,7 @@
 #
 # Automatically generated make config: don't edit
-# Linux kernel version: 2.6.20-rc3
-# Fri Jan  5 11:54:46 2007
+# Linux kernel version: 2.6.20-git8
+# Tue Feb 13 11:25:18 2007
 #
 CONFIG_X86_32=y
 CONFIG_GENERIC_TIME=y
@@ -10,6 +10,7 @@ CONFIG_STACKTRACE_SUPPORT=y
 CONFIG_SEMAPHORE_SLEEPERS=y
 CONFIG_X86=y
 CONFIG_MMU=y
+CONFIG_ZONE_DMA=y
 CONFIG_GENERIC_ISA_DMA=y
 CONFIG_GENERIC_IOMAP=y
 CONFIG_GENERIC_BUG=y
@@ -139,7 +140,6 @@ CONFIG_MPENTIUMIII=y
 # CONFIG_MVIAC3_2 is not set
 CONFIG_X86_GENERIC=y
 CONFIG_X86_CMPXCHG=y
-CONFIG_X86_XADD=y
 CONFIG_X86_L1_CACHE_SHIFT=7
 CONFIG_RWSEM_XCHGADD_ALGORITHM=y
 # CONFIG_ARCH_HAS_ILOG2_U32 is not set
@@ -198,6 +198,7 @@ CONFIG_FLAT_NODE_MEM_MAP=y
 # CONFIG_SPARSEMEM_STATIC is not set
 CONFIG_SPLIT_PTLOCK_CPUS=4
 CONFIG_RESOURCES_64BIT=y
+CONFIG_ZONE_DMA_FLAG=1
 # CONFIG_HIGHPTE is not set
 # CONFIG_MATH_EMULATION is not set
 CONFIG_MTRR=y
@@ -211,6 +212,7 @@ CONFIG_HZ_250=y
 CONFIG_HZ=250
 # CONFIG_KEXEC is not set
 # CONFIG_CRASH_DUMP is not set
+CONFIG_PHYSICAL_START=0x100000
 # CONFIG_RELOCATABLE is not set
 CONFIG_PHYSICAL_ALIGN=0x100000
 # CONFIG_HOTPLUG_CPU is not set
@@ -229,13 +231,14 @@ CONFIG_PM_SYSFS_DEPRECATED=y
 # ACPI (Advanced Configuration and Power Interface) Support
 #
 CONFIG_ACPI=y
+CONFIG_ACPI_PROCFS=y
 CONFIG_ACPI_AC=y
 CONFIG_ACPI_BATTERY=y
 CONFIG_ACPI_BUTTON=y
-# CONFIG_ACPI_VIDEO is not set
 # CONFIG_ACPI_HOTKEY is not set
 CONFIG_ACPI_FAN=y
 # CONFIG_ACPI_DOCK is not set
+# CONFIG_ACPI_BAY is not set
 CONFIG_ACPI_PROCESSOR=y
 CONFIG_ACPI_THERMAL=y
 # CONFIG_ACPI_ASUS is not set
@@ -306,7 +309,6 @@ CONFIG_PCI_DIRECT=y
 CONFIG_PCI_MMCONFIG=y
 # CONFIG_PCIEPORTBUS is not set
 CONFIG_PCI_MSI=y
-# CONFIG_PCI_MULTITHREAD_PROBE is not set
 # CONFIG_PCI_DEBUG is not set
 # CONFIG_HT_IRQ is not set
 CONFIG_ISA_DMA_API=y
@@ -347,6 +349,7 @@ CONFIG_UNIX=y
 CONFIG_XFRM=y
 # CONFIG_XFRM_USER is not set
 # CONFIG_XFRM_SUB_POLICY is not set
+# CONFIG_XFRM_MIGRATE is not set
 # CONFIG_NET_KEY is not set
 CONFIG_INET=y
 CONFIG_IP_MULTICAST=y
@@ -446,6 +449,7 @@ CONFIG_STANDALONE=y
 CONFIG_PREVENT_FIRMWARE_BUILD=y
 CONFIG_FW_LOADER=y
 # CONFIG_DEBUG_DRIVER is not set
+# CONFIG_DEBUG_DEVRES is not set
 # CONFIG_SYS_HYPERVISOR is not set
 
 #
@@ -466,8 +470,7 @@ CONFIG_FW_LOADER=y
 #
 # Plug and Play support
 #
-CONFIG_PNP=y
-CONFIG_PNPACPI=y
+# CONFIG_PNP is not set
 
 #
 # Block devices
@@ -515,6 +518,7 @@ CONFIG_BLK_DEV_IDECD=y
 # CONFIG_BLK_DEV_IDETAPE is not set
 # CONFIG_BLK_DEV_IDEFLOPPY is not set
 # CONFIG_BLK_DEV_IDESCSI is not set
+CONFIG_BLK_DEV_IDEACPI=y
 # CONFIG_IDE_TASK_IOCTL is not set
 
 #
@@ -547,6 +551,7 @@ CONFIG_BLK_DEV_AMD74XX=y
 # CONFIG_BLK_DEV_JMICRON is not set
 # CONFIG_BLK_DEV_SC1200 is not set
 CONFIG_BLK_DEV_PIIX=y
+# CONFIG_BLK_DEV_IT8213 is not set
 # CONFIG_BLK_DEV_IT821X is not set
 # CONFIG_BLK_DEV_NS87415 is not set
 # CONFIG_BLK_DEV_PDC202XX_OLD is not set
@@ -557,6 +562,7 @@ CONFIG_BLK_DEV_PIIX=y
 # CONFIG_BLK_DEV_SLC90E66 is not set
 # CONFIG_BLK_DEV_TRM290 is not set
 # CONFIG_BLK_DEV_VIA82CXXX is not set
+# CONFIG_BLK_DEV_TC86C001 is not set
 # CONFIG_IDE_ARM is not set
 CONFIG_BLK_DEV_IDEDMA=y
 # CONFIG_IDEDMA_IVB is not set
@@ -655,6 +661,7 @@ CONFIG_AIC79XX_DEBUG_MASK=0
 # Serial ATA (prod) and Parallel ATA (experimental) drivers
 #
 CONFIG_ATA=y
+# CONFIG_ATA_NONSTANDARD is not set
 CONFIG_SATA_AHCI=y
 CONFIG_SATA_SVW=y
 CONFIG_ATA_PIIX=y
@@ -670,6 +677,7 @@ CONFIG_SATA_SIL=y
 # CONFIG_SATA_ULI is not set
 CONFIG_SATA_VIA=y
 # CONFIG_SATA_VITESSE is not set
+# CONFIG_SATA_INIC162X is not set
 CONFIG_SATA_INTEL_COMBINED=y
 # CONFIG_PATA_ALI is not set
 # CONFIG_PATA_AMD is not set
@@ -687,6 +695,7 @@ CONFIG_SATA_INTEL_COMBINED=y
 # CONFIG_PATA_HPT3X2N is not set
 # CONFIG_PATA_HPT3X3 is not set
 # CONFIG_PATA_IT821X is not set
+# CONFIG_PATA_IT8213 is not set
 # CONFIG_PATA_JMICRON is not set
 # CONFIG_PATA_TRIFLEX is not set
 # CONFIG_PATA_MARVELL is not set
@@ -739,9 +748,7 @@ CONFIG_IEEE1394=y
 # Subsystem Options
 #
 # CONFIG_IEEE1394_VERBOSEDEBUG is not set
-# CONFIG_IEEE1394_OUI_DB is not set
 # CONFIG_IEEE1394_EXTRA_CONFIG_ROMS is not set
-# CONFIG_IEEE1394_EXPORT_FULL_API is not set
 
 #
 # Device Drivers
@@ -766,6 +773,11 @@ CONFIG_IEEE1394_RAWIO=y
 #
 # CONFIG_I2O is not set
 
+#
+# Macintosh device drivers
+#
+# CONFIG_MAC_EMUMOUSEBTN is not set
+
 #
 # Network device support
 #
@@ -833,6 +845,7 @@ CONFIG_8139TOO=y
 # CONFIG_SUNDANCE is not set
 # CONFIG_TLAN is not set
 # CONFIG_VIA_RHINE is not set
+# CONFIG_SC92031 is not set
 
 #
 # Ethernet (1000 Mbit)
@@ -855,11 +868,13 @@ CONFIG_SKY2=y
 CONFIG_TIGON3=y
 CONFIG_BNX2=y
 # CONFIG_QLA3XXX is not set
+# CONFIG_ATL1 is not set
 
 #
 # Ethernet (10000 Mbit)
 #
 # CONFIG_CHELSIO_T1 is not set
+# CONFIG_CHELSIO_T3 is not set
 # CONFIG_IXGB is not set
 # CONFIG_S2IO is not set
 # CONFIG_MYRI10GE is not set
@@ -1090,6 +1105,7 @@ CONFIG_SOUND=y
 # Open Sound System
 #
 CONFIG_SOUND_PRIME=y
+CONFIG_OBSOLETE_OSS=y
 # CONFIG_SOUND_BT878 is not set
 # CONFIG_SOUND_ES1371 is not set
 CONFIG_SOUND_ICH=y
@@ -1103,6 +1119,7 @@ CONFIG_SOUND_ICH=y
 # HID Devices
 #
 CONFIG_HID=y
+# CONFIG_HID_DEBUG is not set
 
 #
 # USB support
@@ -1117,10 +1134,8 @@ CONFIG_USB=y
 # Miscellaneous USB options
 #
 CONFIG_USB_DEVICEFS=y
-# CONFIG_USB_BANDWIDTH is not set
 # CONFIG_USB_DYNAMIC_MINORS is not set
 # CONFIG_USB_SUSPEND is not set
-# CONFIG_USB_MULTITHREAD_PROBE is not set
 # CONFIG_USB_OTG is not set
 
 #
@@ -1130,9 +1145,11 @@ CONFIG_USB_EHCI_HCD=y
 # CONFIG_USB_EHCI_SPLIT_ISO is not set
 # CONFIG_USB_EHCI_ROOT_HUB_TT is not set
 # CONFIG_USB_EHCI_TT_NEWSCHED is not set
+# CONFIG_USB_EHCI_BIG_ENDIAN_MMIO is not set
 # CONFIG_USB_ISP116X_HCD is not set
 CONFIG_USB_OHCI_HCD=y
-# CONFIG_USB_OHCI_BIG_ENDIAN is not set
+# CONFIG_USB_OHCI_BIG_ENDIAN_DESC is not set
+# CONFIG_USB_OHCI_BIG_ENDIAN_MMIO is not set
 CONFIG_USB_OHCI_LITTLE_ENDIAN=y
 CONFIG_USB_UHCI_HCD=y
 # CONFIG_USB_SL811_HCD is not set
@@ -1183,6 +1200,7 @@ CONFIG_USB_HID=y
 # CONFIG_USB_ATI_REMOTE2 is not set
 # CONFIG_USB_KEYSPAN_REMOTE is not set
 # CONFIG_USB_APPLETOUCH is not set
+# CONFIG_USB_GTCO is not set
 
 #
 # USB Imaging devices
@@ -1287,6 +1305,10 @@ CONFIG_USB_MON=y
 # DMA Devices
 #
 
+#
+# Auxiliary Display support
+#
+
 #
 # Virtualization
 #
@@ -1480,6 +1502,7 @@ CONFIG_UNUSED_SYMBOLS=y
 # CONFIG_DEBUG_FS is not set
 # CONFIG_HEADERS_CHECK is not set
 CONFIG_DEBUG_KERNEL=y
+# CONFIG_DEBUG_SHIRQ is not set
 CONFIG_LOG_BUF_SHIFT=18
 CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_SCHEDSTATS is not set
@@ -1488,7 +1511,6 @@ CONFIG_DETECT_SOFTLOCKUP=y
 # CONFIG_RT_MUTEX_TESTER is not set
 # CONFIG_DEBUG_SPINLOCK is not set
 # CONFIG_DEBUG_MUTEXES is not set
-# CONFIG_DEBUG_RWSEMS is not set
 # CONFIG_DEBUG_LOCK_ALLOC is not set
 # CONFIG_PROVE_LOCKING is not set
 # CONFIG_DEBUG_SPINLOCK_SLEEP is not set
@@ -1533,7 +1555,8 @@ CONFIG_CRC32=y
 # CONFIG_LIBCRC32C is not set
 CONFIG_ZLIB_INFLATE=y
 CONFIG_PLIST=y
-CONFIG_IOMAP_COPY=y
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_IOPORT=y
 CONFIG_GENERIC_HARDIRQS=y
 CONFIG_GENERIC_IRQ_PROBE=y
 CONFIG_GENERIC_PENDING_IRQ=y

arch/i386/kernel/Makefile

@@ -18,7 +18,7 @@ obj-$(CONFIG_X86_MSR)		+= msr.o
 obj-$(CONFIG_X86_CPUID)		+= cpuid.o
 obj-$(CONFIG_MICROCODE)		+= microcode.o
 obj-$(CONFIG_APM)		+= apm.o
-obj-$(CONFIG_X86_SMP)		+= smp.o smpboot.o
+obj-$(CONFIG_X86_SMP)		+= smp.o smpboot.o tsc_sync.o
 obj-$(CONFIG_X86_TRAMPOLINE)	+= trampoline.o
 obj-$(CONFIG_X86_MPPARSE)	+= mpparse.o
 obj-$(CONFIG_X86_LOCAL_APIC)	+= apic.o nmi.o
@@ -32,7 +32,6 @@ obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_MODULES)		+= module.o
 obj-y				+= sysenter.o vsyscall.o
 obj-$(CONFIG_ACPI_SRAT) 	+= srat.o
-obj-$(CONFIG_HPET_TIMER) 	+= time_hpet.o
 obj-$(CONFIG_EFI) 		+= efi.o efi_stub.o
 obj-$(CONFIG_DOUBLEFAULT) 	+= doublefault.o
 obj-$(CONFIG_VM86)		+= vm86.o
@@ -40,8 +39,9 @@ obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_HPET_TIMER) 	+= hpet.o
 obj-$(CONFIG_K8_NB)		+= k8.o
 
-# Make sure this is linked after any other paravirt_ops structs: see head.S
+obj-$(CONFIG_VMI)		+= vmi.o vmitime.o
 obj-$(CONFIG_PARAVIRT)		+= paravirt.o
+obj-y				+= pcspeaker.o
 
 EXTRA_AFLAGS   := -traditional
 

arch/i386/kernel/acpi/boot.c

@@ -25,6 +25,7 @@
 
 #include <linux/init.h>
 #include <linux/acpi.h>
+#include <linux/acpi_pmtmr.h>
 #include <linux/efi.h>
 #include <linux/cpumask.h>
 #include <linux/module.h>
@@ -615,6 +616,7 @@ static int __init acpi_parse_sbf(struct acpi_table_header *table)
 }
 
 #ifdef CONFIG_HPET_TIMER
+#include <asm/hpet.h>
 
 static int __init acpi_parse_hpet(struct acpi_table_header *table)
 {
@@ -645,24 +647,11 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table)
 		hpet_res->end = (1 * 1024) - 1;
 	}
 
-#ifdef CONFIG_X86_64
-	vxtime.hpet_address = hpet_tbl->address.address;
-
+	hpet_address = hpet_tbl->address.address;
 	printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n",
-		hpet_tbl->id, vxtime.hpet_address);
-
-	res_start = vxtime.hpet_address;
-#else                          /* X86 */
-	{
-		extern unsigned long hpet_address;
-
-		hpet_address = hpet_tbl->address.address;
-		printk(KERN_INFO PREFIX "HPET id: %#x base: %#lx\n",
-			hpet_tbl->id, hpet_address);
+	       hpet_tbl->id, hpet_address);
 
-		res_start = hpet_address;
-	}
-#endif                         /* X86 */
+	res_start = hpet_address;
 
 	if (hpet_res) {
 		hpet_res->start = res_start;
@@ -676,10 +665,6 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table)
 #define	acpi_parse_hpet	NULL
 #endif
 
-#ifdef CONFIG_X86_PM_TIMER
-extern u32 pmtmr_ioport;
-#endif
-
 static int __init acpi_parse_fadt(struct acpi_table_header *table)
 {
 

arch/i386/kernel/apm.c

@@ -211,6 +211,7 @@
 #include <linux/slab.h>
 #include <linux/stat.h>
 #include <linux/proc_fs.h>
+#include <linux/seq_file.h>
 #include <linux/miscdevice.h>
 #include <linux/apm_bios.h>
 #include <linux/init.h>
@@ -235,7 +236,6 @@
 
 #include "io_ports.h"
 
-extern unsigned long get_cmos_time(void);
 extern void machine_real_restart(unsigned char *, int);
 
 #if defined(CONFIG_APM_DISPLAY_BLANK) && defined(CONFIG_VT)
@@ -1175,28 +1175,6 @@ out:
 	spin_unlock(&user_list_lock);
 }
 
-static void set_time(void)
-{
-	struct timespec ts;
-	if (got_clock_diff) {	/* Must know time zone in order to set clock */
-		ts.tv_sec = get_cmos_time() + clock_cmos_diff;
-		ts.tv_nsec = 0;
-		do_settimeofday(&ts);
-	} 
-}
-
-static void get_time_diff(void)
-{
-#ifndef CONFIG_APM_RTC_IS_GMT
-	/*
-	 * Estimate time zone so that set_time can update the clock
-	 */
-	clock_cmos_diff = -get_cmos_time();
-	clock_cmos_diff += get_seconds();
-	got_clock_diff = 1;
-#endif
-}
-
 static void reinit_timer(void)
 {
 #ifdef INIT_TIMER_AFTER_SUSPEND
@@ -1236,19 +1214,6 @@ static int suspend(int vetoable)
 	local_irq_disable();
 	device_power_down(PMSG_SUSPEND);
 
-	/* serialize with the timer interrupt */
-	write_seqlock(&xtime_lock);
-
-	/* protect against access to timer chip registers */
-	spin_lock(&i8253_lock);
-
-	get_time_diff();
-	/*
-	 * Irq spinlock must be dropped around set_system_power_state.
-	 * We'll undo any timer changes due to interrupts below.
-	 */
-	spin_unlock(&i8253_lock);
-	write_sequnlock(&xtime_lock);
 	local_irq_enable();
 
 	save_processor_state();
@@ -1257,7 +1222,6 @@ static int suspend(int vetoable)
 	restore_processor_state();
 
 	local_irq_disable();
-	set_time();
 	reinit_timer();
 
 	if (err == APM_NO_ERROR)
@@ -1287,11 +1251,6 @@ static void standby(void)
 
 	local_irq_disable();
 	device_power_down(PMSG_SUSPEND);
-	/* serialize with the timer interrupt */
-	write_seqlock(&xtime_lock);
-	/* If needed, notify drivers here */
-	get_time_diff();
-	write_sequnlock(&xtime_lock);
 	local_irq_enable();
 
 	err = set_system_power_state(APM_STATE_STANDBY);
@@ -1385,7 +1344,6 @@ static void check_events(void)
 			ignore_bounce = 1;
 			if ((event != APM_NORMAL_RESUME)
 			    || (ignore_normal_resume == 0)) {
-				set_time();
 				device_resume();
 				pm_send_all(PM_RESUME, (void *)0);
 				queue_event(event, NULL);
@@ -1401,7 +1359,6 @@ static void check_events(void)
 			break;
 
 		case APM_UPDATE_TIME:
-			set_time();
 			break;
 
 		case APM_CRITICAL_SUSPEND:
@@ -1636,9 +1593,8 @@ static int do_open(struct inode * inode, struct file * filp)
 	return 0;
 }
 
-static int apm_get_info(char *buf, char **start, off_t fpos, int length)
+static int proc_apm_show(struct seq_file *m, void *v)
 {
-	char *		p;
 	unsigned short	bx;
 	unsigned short	cx;
 	unsigned short	dx;
@@ -1650,8 +1606,6 @@ static int apm_get_info(char *buf, char **start, off_t fpos, int length)
 	int             time_units     = -1;
 	char            *units         = "?";
 
-	p = buf;
-
 	if ((num_online_cpus() == 1) &&
 	    !(error = apm_get_power_status(&bx, &cx, &dx))) {
 		ac_line_status = (bx >> 8) & 0xff;
@@ -1705,7 +1659,7 @@ static int apm_get_info(char *buf, char **start, off_t fpos, int length)
 	      -1: Unknown
 	   8) min = minutes; sec = seconds */
 
-	p += sprintf(p, "%s %d.%d 0x%02x 0x%02x 0x%02x 0x%02x %d%% %d %s\n",
+	seq_printf(m, "%s %d.%d 0x%02x 0x%02x 0x%02x 0x%02x %d%% %d %s\n",
 		     driver_version,
 		     (apm_info.bios.version >> 8) & 0xff,
 		     apm_info.bios.version & 0xff,
@@ -1716,10 +1670,22 @@ static int apm_get_info(char *buf, char **start, off_t fpos, int length)
 		     percentage,
 		     time_units,
 		     units);
+	return 0;
+}
 
-	return p - buf;
+static int proc_apm_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, proc_apm_show, NULL);
 }
 
+static const struct file_operations apm_file_ops = {
+	.owner		= THIS_MODULE,
+	.open		= proc_apm_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
 static int apm(void *unused)
 {
 	unsigned short	bx;
@@ -2341,9 +2307,9 @@ static int __init apm_init(void)
 	set_base(gdt[APM_DS >> 3],
 		 __va((unsigned long)apm_info.bios.dseg << 4));
 
-	apm_proc = create_proc_info_entry("apm", 0, NULL, apm_get_info);
+	apm_proc = create_proc_entry("apm", 0, NULL);
 	if (apm_proc)
-		apm_proc->owner = THIS_MODULE;
+		apm_proc->proc_fops = &apm_file_ops;
 
 	kapmd_task = kthread_create(apm, NULL, "kapmd");
 	if (IS_ERR(kapmd_task)) {

arch/i386/kernel/asm-offsets.c

@@ -72,7 +72,7 @@ void foo(void)
 	OFFSET(PT_EAX, pt_regs, eax);
 	OFFSET(PT_DS,  pt_regs, xds);
 	OFFSET(PT_ES,  pt_regs, xes);
-	OFFSET(PT_GS,  pt_regs, xgs);
+	OFFSET(PT_FS,  pt_regs, xfs);
 	OFFSET(PT_ORIG_EAX, pt_regs, orig_eax);
 	OFFSET(PT_EIP, pt_regs, eip);
 	OFFSET(PT_CS,  pt_regs, xcs);

arch/i386/kernel/cpu/common.c

@@ -605,7 +605,7 @@ void __init early_cpu_init(void)
 struct pt_regs * __devinit idle_regs(struct pt_regs *regs)
 {
 	memset(regs, 0, sizeof(struct pt_regs));
-	regs->xgs = __KERNEL_PDA;
+	regs->xfs = __KERNEL_PDA;
 	return regs;
 }
 
@@ -662,12 +662,12 @@ struct i386_pda boot_pda = {
 	.pcurrent = &init_task,
 };
 
-static inline void set_kernel_gs(void)
+static inline void set_kernel_fs(void)
 {
-	/* Set %gs for this CPU's PDA.  Memory clobber is to create a
+	/* Set %fs for this CPU's PDA.  Memory clobber is to create a
 	   barrier with respect to any PDA operations, so the compiler
 	   doesn't move any before here. */
-	asm volatile ("mov %0, %%gs" : : "r" (__KERNEL_PDA) : "memory");
+	asm volatile ("mov %0, %%fs" : : "r" (__KERNEL_PDA) : "memory");
 }
 
 /* Initialize the CPU's GDT and PDA.  The boot CPU does this for
@@ -718,7 +718,7 @@ void __cpuinit cpu_set_gdt(int cpu)
 	   the boot CPU, this will transition from the boot gdt+pda to
 	   the real ones). */
 	load_gdt(cpu_gdt_descr);
-	set_kernel_gs();
+	set_kernel_fs();
 }
 
 /* Common CPU init for both boot and secondary CPUs */
@@ -764,8 +764,8 @@ static void __cpuinit _cpu_init(int cpu, struct task_struct *curr)
 	__set_tss_desc(cpu, GDT_ENTRY_DOUBLEFAULT_TSS, &doublefault_tss);
 #endif
 
-	/* Clear %fs. */
-	asm volatile ("mov %0, %%fs" : : "r" (0));
+	/* Clear %gs. */
+	asm volatile ("mov %0, %%gs" : : "r" (0));
 
 	/* Clear all 6 debug registers: */
 	set_debugreg(0, 0);

arch/i386/kernel/cpu/cpufreq/Kconfig

@@ -217,6 +217,15 @@ config X86_LONGHAUL
 
 	  If in doubt, say N.
 
+config X86_E_POWERSAVER
+	tristate "VIA C7 Enhanced PowerSaver (EXPERIMENTAL)"
+	select CPU_FREQ_TABLE
+	depends on EXPERIMENTAL
+	help
+	  This adds the CPUFreq driver for VIA C7 processors.
+
+	  If in doubt, say N.
+
 comment "shared options"
 
 config X86_ACPI_CPUFREQ_PROC_INTF

arch/i386/kernel/cpu/cpufreq/Makefile

@@ -2,6 +2,7 @@ obj-$(CONFIG_X86_POWERNOW_K6)		+= powernow-k6.o
 obj-$(CONFIG_X86_POWERNOW_K7)		+= powernow-k7.o
 obj-$(CONFIG_X86_POWERNOW_K8)		+= powernow-k8.o
 obj-$(CONFIG_X86_LONGHAUL)		+= longhaul.o
+obj-$(CONFIG_X86_E_POWERSAVER)		+= e_powersaver.o
 obj-$(CONFIG_ELAN_CPUFREQ)		+= elanfreq.o
 obj-$(CONFIG_SC520_CPUFREQ)		+= sc520_freq.o
 obj-$(CONFIG_X86_LONGRUN)		+= longrun.o  

arch/i386/kernel/cpu/cpufreq/e_powersaver.c

@@ -0,0 +1,334 @@
+/*
+ *  Based on documentation provided by Dave Jones. Thanks!
+ *
+ *  Licensed under the terms of the GNU GPL License version 2.
+ *
+ *  BIG FAT DISCLAIMER: Work in progress code. Possibly *dangerous*
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/cpufreq.h>
+#include <linux/ioport.h>
+#include <linux/slab.h>
+
+#include <asm/msr.h>
+#include <asm/tsc.h>
+#include <asm/timex.h>
+#include <asm/io.h>
+#include <asm/delay.h>
+
+#define EPS_BRAND_C7M	0
+#define EPS_BRAND_C7	1
+#define EPS_BRAND_EDEN	2
+#define EPS_BRAND_C3	3
+
+struct eps_cpu_data {
+	u32 fsb;
+	struct cpufreq_frequency_table freq_table[];
+};
+
+static struct eps_cpu_data *eps_cpu[NR_CPUS];
+
+
+static unsigned int eps_get(unsigned int cpu)
+{
+	struct eps_cpu_data *centaur;
+	u32 lo, hi;
+
+	if (cpu)
+		return 0;
+	centaur = eps_cpu[cpu];
+	if (centaur == NULL)
+		return 0;
+
+	/* Return current frequency */
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	return centaur->fsb * ((lo >> 8) & 0xff);
+}
+
+static int eps_set_state(struct eps_cpu_data *centaur,
+			 unsigned int cpu,
+			 u32 dest_state)
+{
+	struct cpufreq_freqs freqs;
+	u32 lo, hi;
+	int err = 0;
+	int i;
+
+	freqs.old = eps_get(cpu);
+	freqs.new = centaur->fsb * ((dest_state >> 8) & 0xff);
+	freqs.cpu = cpu;
+	cpufreq_notify_transition(&freqs, CPUFREQ_PRECHANGE);
+
+	/* Wait while CPU is busy */
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	i = 0;
+	while (lo & ((1 << 16) | (1 << 17))) {
+		udelay(16);
+		rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+		i++;
+		if (unlikely(i > 64)) {
+			err = -ENODEV;
+			goto postchange;
+		}
+	}
+	/* Set new multiplier and voltage */
+	wrmsr(MSR_IA32_PERF_CTL, dest_state & 0xffff, 0);
+	/* Wait until transition end */
+	i = 0;
+	do {
+		udelay(16);
+		rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+		i++;
+		if (unlikely(i > 64)) {
+			err = -ENODEV;
+			goto postchange;
+		}
+	} while (lo & ((1 << 16) | (1 << 17)));
+
+	/* Return current frequency */
+postchange:
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	freqs.new = centaur->fsb * ((lo >> 8) & 0xff);
+
+	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
+	return err;
+}
+
+static int eps_target(struct cpufreq_policy *policy,
+			       unsigned int target_freq,
+			       unsigned int relation)
+{
+	struct eps_cpu_data *centaur;
+	unsigned int newstate = 0;
+	unsigned int cpu = policy->cpu;
+	unsigned int dest_state;
+	int ret;
+
+	if (unlikely(eps_cpu[cpu] == NULL))
+		return -ENODEV;
+	centaur = eps_cpu[cpu];
+
+	if (unlikely(cpufreq_frequency_table_target(policy,
+			&eps_cpu[cpu]->freq_table[0],
+			target_freq,
+			relation,
+			&newstate))) {
+		return -EINVAL;
+	}
+
+	/* Make frequency transition */
+	dest_state = centaur->freq_table[newstate].index & 0xffff;
+	ret = eps_set_state(centaur, cpu, dest_state);
+	if (ret)
+		printk(KERN_ERR "eps: Timeout!\n");
+	return ret;
+}
+
+static int eps_verify(struct cpufreq_policy *policy)
+{
+	return cpufreq_frequency_table_verify(policy,
+			&eps_cpu[policy->cpu]->freq_table[0]);
+}
+
+static int eps_cpu_init(struct cpufreq_policy *policy)
+{
+	unsigned int i;
+	u32 lo, hi;
+	u64 val;
+	u8 current_multiplier, current_voltage;
+	u8 max_multiplier, max_voltage;
+	u8 min_multiplier, min_voltage;
+	u8 brand;
+	u32 fsb;
+	struct eps_cpu_data *centaur;
+	struct cpufreq_frequency_table *f_table;
+	int k, step, voltage;
+	int ret;
+	int states;
+
+	if (policy->cpu != 0)
+		return -ENODEV;
+
+	/* Check brand */
+	printk("eps: Detected VIA ");
+	rdmsr(0x1153, lo, hi);
+	brand = (((lo >> 2) ^ lo) >> 18) & 3;
+	switch(brand) {
+	case EPS_BRAND_C7M:
+		printk("C7-M\n");
+		break;
+	case EPS_BRAND_C7:
+		printk("C7\n");
+		break;
+	case EPS_BRAND_EDEN:
+		printk("Eden\n");
+		break;
+	case EPS_BRAND_C3:
+		printk("C3\n");
+		return -ENODEV;
+		break;
+	}
+	/* Enable Enhanced PowerSaver */
+	rdmsrl(MSR_IA32_MISC_ENABLE, val);
+	if (!(val & 1 << 16)) {
+		val |= 1 << 16;
+		wrmsrl(MSR_IA32_MISC_ENABLE, val);
+		/* Can be locked at 0 */
+		rdmsrl(MSR_IA32_MISC_ENABLE, val);
+		if (!(val & 1 << 16)) {
+			printk("eps: Can't enable Enhanced PowerSaver\n");
+			return -ENODEV;
+		}
+	}
+
+	/* Print voltage and multiplier */
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	current_voltage = lo & 0xff;
+	printk("eps: Current voltage = %dmV\n", current_voltage * 16 + 700);
+	current_multiplier = (lo >> 8) & 0xff;
+	printk("eps: Current multiplier = %d\n", current_multiplier);
+
+	/* Print limits */
+	max_voltage = hi & 0xff;
+	printk("eps: Highest voltage = %dmV\n", max_voltage * 16 + 700);
+	max_multiplier = (hi >> 8) & 0xff;
+	printk("eps: Highest multiplier = %d\n", max_multiplier);
+	min_voltage = (hi >> 16) & 0xff;
+	printk("eps: Lowest voltage = %dmV\n", min_voltage * 16 + 700);
+	min_multiplier = (hi >> 24) & 0xff;
+	printk("eps: Lowest multiplier = %d\n", min_multiplier);
+
+	/* Sanity checks */
+	if (current_multiplier == 0 || max_multiplier == 0
+	    || min_multiplier == 0)
+		return -EINVAL;
+	if (current_multiplier > max_multiplier
+	    || max_multiplier <= min_multiplier)
+		return -EINVAL;
+	if (current_voltage > 0x1c || max_voltage > 0x1c)
+		return -EINVAL;
+	if (max_voltage < min_voltage)
+		return -EINVAL;
+
+	/* Calc FSB speed */
+	fsb = cpu_khz / current_multiplier;
+	/* Calc number of p-states supported */
+	if (brand == EPS_BRAND_C7M)
+		states = max_multiplier - min_multiplier + 1;
+	else
+		states = 2;
+
+	/* Allocate private data and frequency table for current cpu */
+	centaur = kzalloc(sizeof(struct eps_cpu_data)
+		    + (states + 1) * sizeof(struct cpufreq_frequency_table),
+		    GFP_KERNEL);
+	if (!centaur)
+		return -ENOMEM;
+	eps_cpu[0] = centaur;
+
+	/* Copy basic values */
+	centaur->fsb = fsb;
+
+	/* Fill frequency and MSR value table */
+	f_table = &centaur->freq_table[0];
+	if (brand != EPS_BRAND_C7M) {
+		f_table[0].frequency = fsb * min_multiplier;
+		f_table[0].index = (min_multiplier << 8) | min_voltage;
+		f_table[1].frequency = fsb * max_multiplier;
+		f_table[1].index = (max_multiplier << 8) | max_voltage;
+		f_table[2].frequency = CPUFREQ_TABLE_END;
+	} else {
+		k = 0;
+		step = ((max_voltage - min_voltage) * 256)
+			/ (max_multiplier - min_multiplier);
+		for (i = min_multiplier; i <= max_multiplier; i++) {
+			voltage = (k * step) / 256 + min_voltage;
+			f_table[k].frequency = fsb * i;
+			f_table[k].index = (i << 8) | voltage;
+			k++;
+		}
+		f_table[k].frequency = CPUFREQ_TABLE_END;
+	}
+
+	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
+	policy->cpuinfo.transition_latency = 140000; /* 844mV -> 700mV in ns */
+	policy->cur = fsb * current_multiplier;
+
+	ret = cpufreq_frequency_table_cpuinfo(policy, &centaur->freq_table[0]);
+	if (ret) {
+		kfree(centaur);
+		return ret;
+	}
+
+	cpufreq_frequency_table_get_attr(&centaur->freq_table[0], policy->cpu);
+	return 0;
+}
+
+static int eps_cpu_exit(struct cpufreq_policy *policy)
+{
+	unsigned int cpu = policy->cpu;
+	struct eps_cpu_data *centaur;
+	u32 lo, hi;
+
+	if (eps_cpu[cpu] == NULL)
+		return -ENODEV;
+	centaur = eps_cpu[cpu];
+
+	/* Get max frequency */
+	rdmsr(MSR_IA32_PERF_STATUS, lo, hi);
+	/* Set max frequency */
+	eps_set_state(centaur, cpu, hi & 0xffff);
+	/* Bye */
+	cpufreq_frequency_table_put_attr(policy->cpu);
+	kfree(eps_cpu[cpu]);
+	eps_cpu[cpu] = NULL;
+	return 0;
+}
+
+static struct freq_attr* eps_attr[] = {
+	&cpufreq_freq_attr_scaling_available_freqs,
+	NULL,
+};
+
+static struct cpufreq_driver eps_driver = {
+	.verify		= eps_verify,
+	.target		= eps_target,
+	.init		= eps_cpu_init,
+	.exit		= eps_cpu_exit,
+	.get		= eps_get,
+	.name		= "e_powersaver",
+	.owner		= THIS_MODULE,
+	.attr		= eps_attr,
+};
+
+static int __init eps_init(void)
+{
+	struct cpuinfo_x86 *c = cpu_data;
+
+	/* This driver will work only on Centaur C7 processors with
+	 * Enhanced SpeedStep/PowerSaver registers */
+	if (c->x86_vendor != X86_VENDOR_CENTAUR
+	    || c->x86 != 6 || c->x86_model != 10)
+		return -ENODEV;
+	if (!cpu_has(c, X86_FEATURE_EST))
+		return -ENODEV;
+
+	if (cpufreq_register_driver(&eps_driver))
+		return -EINVAL;
+	return 0;
+}
+
+static void __exit eps_exit(void)
+{
+	cpufreq_unregister_driver(&eps_driver);
+}
+
+MODULE_AUTHOR("Rafa³ Bilski <rafalbilski@interia.pl>");
+MODULE_DESCRIPTION("Enhanced PowerSaver driver for VIA C7 CPU's.");
+MODULE_LICENSE("GPL");
+
+module_init(eps_init);
+module_exit(eps_exit);

arch/i386/kernel/cpu/cpufreq/longhaul.c

@@ -8,12 +8,11 @@
  *  VIA have currently 3 different versions of Longhaul.
  *  Version 1 (Longhaul) uses the BCR2 MSR at 0x1147.
  *   It is present only in Samuel 1 (C5A), Samuel 2 (C5B) stepping 0.
- *  Version 2 of longhaul is the same as v1, but adds voltage scaling.
- *   Present in Samuel 2 (steppings 1-7 only) (C5B), and Ezra (C5C)
- *   voltage scaling support has currently been disabled in this driver
- *   until we have code that gets it right.
+ *  Version 2 of longhaul is backward compatible with v1, but adds
+ *   LONGHAUL MSR for purpose of both frequency and voltage scaling.
+ *   Present in Samuel 2 (steppings 1-7 only) (C5B), and Ezra (C5C).
  *  Version 3 of longhaul got renamed to Powersaver and redesigned
- *   to use the POWERSAVER MSR at 0x110a.
+ *   to use only the POWERSAVER MSR at 0x110a.
  *   It is present in Ezra-T (C5M), Nehemiah (C5X) and above.
  *   It's pretty much the same feature wise to longhaul v2, though
  *   there is provision for scaling FSB too, but this doesn't work
@@ -51,10 +50,12 @@
 #define	CPU_EZRA	3
 #define	CPU_EZRA_T	4
 #define	CPU_NEHEMIAH	5
+#define	CPU_NEHEMIAH_C	6
 
 /* Flags */
 #define USE_ACPI_C3		(1 << 1)
 #define USE_NORTHBRIDGE		(1 << 2)
+#define USE_VT8235		(1 << 3)
 
 static int cpu_model;
 static unsigned int numscales=16;
@@ -63,7 +64,8 @@ static unsigned int fsb;
 static struct mV_pos *vrm_mV_table;
 static unsigned char *mV_vrm_table;
 struct f_msr {
-	unsigned char vrm;
+	u8 vrm;
+	u8 pos;
 };
 static struct f_msr f_msr_table[32];
 
@@ -73,10 +75,10 @@ static int can_scale_voltage;
 static struct acpi_processor *pr = NULL;
 static struct acpi_processor_cx *cx = NULL;
 static u8 longhaul_flags;
+static u8 longhaul_pos;
 
 /* Module parameters */
 static int scale_voltage;
-static int ignore_latency;
 
 #define dprintk(msg...) cpufreq_debug_printk(CPUFREQ_DEBUG_DRIVER, "longhaul", msg)
 
@@ -164,26 +166,47 @@ static void do_longhaul1(unsigned int clock_ratio_index)
 static void do_powersaver(int cx_address, unsigned int clock_ratio_index)
 {
 	union msr_longhaul longhaul;
+	u8 dest_pos;
 	u32 t;
 
+	dest_pos = f_msr_table[clock_ratio_index].pos;
+
 	rdmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+	/* Setup new frequency */
 	longhaul.bits.RevisionKey = longhaul.bits.RevisionID;
 	longhaul.bits.SoftBusRatio = clock_ratio_index & 0xf;
 	longhaul.bits.SoftBusRatio4 = (clock_ratio_index & 0x10) >> 4;
-	longhaul.bits.EnableSoftBusRatio = 1;
-
-	if (can_scale_voltage) {
+	/* Setup new voltage */
+	if (can_scale_voltage)
 		longhaul.bits.SoftVID = f_msr_table[clock_ratio_index].vrm;
+	/* Sync to timer tick */
+	safe_halt();
+	/* Raise voltage if necessary */
+	if (can_scale_voltage && longhaul_pos < dest_pos) {
 		longhaul.bits.EnableSoftVID = 1;
+		wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+		/* Change voltage */
+		if (!cx_address) {
+			ACPI_FLUSH_CPU_CACHE();
+			halt();
+		} else {
+			ACPI_FLUSH_CPU_CACHE();
+			/* Invoke C3 */
+			inb(cx_address);
+			/* Dummy op - must do something useless after P_LVL3
+			 * read */
+			t = inl(acpi_gbl_FADT.xpm_timer_block.address);
+		}
+		longhaul.bits.EnableSoftVID = 0;
+		wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+		longhaul_pos = dest_pos;
 	}
 
-	/* Sync to timer tick */
-	safe_halt();
 	/* Change frequency on next halt or sleep */
+	longhaul.bits.EnableSoftBusRatio = 1;
 	wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
 	if (!cx_address) {
 		ACPI_FLUSH_CPU_CACHE();
-		/* Invoke C1 */
 		halt();
 	} else {
 		ACPI_FLUSH_CPU_CACHE();
@@ -193,12 +216,29 @@ static void do_powersaver(int cx_address, unsigned int clock_ratio_index)
 		t = inl(acpi_gbl_FADT.xpm_timer_block.address);
 	}
 	/* Disable bus ratio bit */
-	local_irq_disable();
-	longhaul.bits.RevisionKey = longhaul.bits.RevisionID;
 	longhaul.bits.EnableSoftBusRatio = 0;
-	longhaul.bits.EnableSoftBSEL = 0;
-	longhaul.bits.EnableSoftVID = 0;
 	wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+
+	/* Reduce voltage if necessary */
+	if (can_scale_voltage && longhaul_pos > dest_pos) {
+		longhaul.bits.EnableSoftVID = 1;
+		wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+		/* Change voltage */
+		if (!cx_address) {
+			ACPI_FLUSH_CPU_CACHE();
+			halt();
+		} else {
+			ACPI_FLUSH_CPU_CACHE();
+			/* Invoke C3 */
+			inb(cx_address);
+			/* Dummy op - must do something useless after P_LVL3
+			 * read */
+			t = inl(acpi_gbl_FADT.xpm_timer_block.address);
+		}
+		longhaul.bits.EnableSoftVID = 0;
+		wrmsrl(MSR_VIA_LONGHAUL, longhaul.val);
+		longhaul_pos = dest_pos;
+	}
 }
 
 /**
@@ -257,26 +297,19 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 	/*
 	 * Longhaul v1. (Samuel[C5A] and Samuel2 stepping 0[C5B])
 	 * Software controlled multipliers only.
-	 *
-	 * *NB* Until we get voltage scaling working v1 & v2 are the same code.
-	 * Longhaul v2 appears in Samuel2 Steppings 1->7 [C5b] and Ezra [C5C]
 	 */
 	case TYPE_LONGHAUL_V1:
-	case TYPE_LONGHAUL_V2:
 		do_longhaul1(clock_ratio_index);
 		break;
 
 	/*
+	 * Longhaul v2 appears in Samuel2 Steppings 1->7 [C5B] and Ezra [C5C]
+	 *
 	 * Longhaul v3 (aka Powersaver). (Ezra-T [C5M] & Nehemiah [C5N])
-	 * We can scale voltage with this too, but that's currently
-	 * disabled until we come up with a decent 'match freq to voltage'
-	 * algorithm.
-	 * When we add voltage scaling, we will also need to do the
-	 * voltage/freq setting in order depending on the direction
-	 * of scaling (like we do in powernow-k7.c)
 	 * Nehemiah can do FSB scaling too, but this has never been proven
 	 * to work in practice.
 	 */
+	case TYPE_LONGHAUL_V2:
 	case TYPE_POWERSAVER:
 		if (longhaul_flags & USE_ACPI_C3) {
 			/* Don't allow wakeup */
@@ -301,6 +334,7 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 	local_irq_restore(flags);
 	preempt_enable();
 
+	freqs.new = calc_speed(longhaul_get_cpu_mult());
 	cpufreq_notify_transition(&freqs, CPUFREQ_POSTCHANGE);
 }
 
@@ -315,31 +349,19 @@ static void longhaul_setstate(unsigned int clock_ratio_index)
 
 #define ROUNDING	0xf
 
-static int _guess(int guess, int mult)
-{
-	int target;
-
-	target = ((mult/10)*guess);
-	if (mult%10 != 0)
-		target += (guess/2);
-	target += ROUNDING/2;
-	target &= ~ROUNDING;
-	return target;
-}
-
-
 static int guess_fsb(int mult)
 {
-	int speed = (cpu_khz/1000);
+	int speed = cpu_khz / 1000;
 	int i;
-	int speeds[] = { 66, 100, 133, 200 };
-
-	speed += ROUNDING/2;
-	speed &= ~ROUNDING;
-
-	for (i=0; i<4; i++) {
-		if (_guess(speeds[i], mult) == speed)
-			return speeds[i];
+	int speeds[] = { 666, 1000, 1333, 2000 };
+	int f_max, f_min;
+
+	for (i = 0; i < 4; i++) {
+		f_max = ((speeds[i] * mult) + 50) / 100;
+		f_max += (ROUNDING / 2);
+		f_min = f_max - ROUNDING;
+		if ((speed <= f_max) && (speed >= f_min))
+			return speeds[i] / 10;
 	}
 	return 0;
 }
@@ -347,67 +369,40 @@ static int guess_fsb(int mult)
 
 static int __init longhaul_get_ranges(void)
 {
-	unsigned long invalue;
-	unsigned int ezra_t_multipliers[32]= {
-			90,  30,  40, 100,  55,  35,  45,  95,
-			50,  70,  80,  60, 120,  75,  85,  65,
-			-1, 110, 120,  -1, 135, 115, 125, 105,
-			130, 150, 160, 140,  -1, 155,  -1, 145 };
 	unsigned int j, k = 0;
-	union msr_longhaul longhaul;
-	int mult = 0;
+	int mult;
 
-	switch (longhaul_version) {
-	case TYPE_LONGHAUL_V1:
-	case TYPE_LONGHAUL_V2:
-		/* Ugh, Longhaul v1 didn't have the min/max MSRs.
-		   Assume min=3.0x & max = whatever we booted at. */
+	/* Get current frequency */
+	mult = longhaul_get_cpu_mult();
+	if (mult == -1) {
+		printk(KERN_INFO PFX "Invalid (reserved) multiplier!\n");
+		return -EINVAL;
+	}
+	fsb = guess_fsb(mult);
+	if (fsb == 0) {
+		printk(KERN_INFO PFX "Invalid (reserved) FSB!\n");
+		return -EINVAL;
+	}
+	/* Get max multiplier - as we always did.
+	 * Longhaul MSR is usefull only when voltage scaling is enabled.
+	 * C3 is booting at max anyway. */
+	maxmult = mult;
+	/* Get min multiplier */
+	switch (cpu_model) {
+	case CPU_NEHEMIAH:
+		minmult = 50;
+		break;
+	case CPU_NEHEMIAH_C:
+		minmult = 40;
+		break;
+	default:
 		minmult = 30;
-		maxmult = mult = longhaul_get_cpu_mult();
 		break;
-
-	case TYPE_POWERSAVER:
-		/* Ezra-T */
-		if (cpu_model==CPU_EZRA_T) {
-			minmult = 30;
-			rdmsrl (MSR_VIA_LONGHAUL, longhaul.val);
-			invalue = longhaul.bits.MaxMHzBR;
-			if (longhaul.bits.MaxMHzBR4)
-				invalue += 16;
-			maxmult = mult = ezra_t_multipliers[invalue];
-			break;
-		}
-
-		/* Nehemiah */
-		if (cpu_model==CPU_NEHEMIAH) {
-			rdmsrl (MSR_VIA_LONGHAUL, longhaul.val);
-
-			/*
-			 * TODO: This code works, but raises a lot of questions.
-			 * - Some Nehemiah's seem to have broken Min/MaxMHzBR's.
-			 *   We get around this by using a hardcoded multiplier of 4.0x
-			 *   for the minimimum speed, and the speed we booted up at for the max.
-			 *   This is done in longhaul_get_cpu_mult() by reading the EBLCR register.
-			 * - According to some VIA documentation EBLCR is only
-			 *   in pre-Nehemiah C3s. How this still works is a mystery.
-			 *   We're possibly using something undocumented and unsupported,
-			 *   But it works, so we don't grumble.
-			 */
-			minmult=40;
-			maxmult = mult = longhaul_get_cpu_mult();
-			break;
-		}
 	}
-	fsb = guess_fsb(mult);
 
 	dprintk ("MinMult:%d.%dx MaxMult:%d.%dx\n",
 		 minmult/10, minmult%10, maxmult/10, maxmult%10);
 
-	if (fsb == 0) {
-		printk (KERN_INFO PFX "Invalid (reserved) FSB!\n");
-		return -EINVAL;
-	}
-
 	highest_speed = calc_speed(maxmult);
 	lowest_speed = calc_speed(minmult);
 	dprintk ("FSB:%dMHz  Lowest speed: %s   Highest speed:%s\n", fsb,
@@ -455,6 +450,7 @@ static void __init longhaul_setup_voltagescaling(void)
 	union msr_longhaul longhaul;
 	struct mV_pos minvid, maxvid;
 	unsigned int j, speed, pos, kHz_step, numvscales;
+	int min_vid_speed;
 
 	rdmsrl(MSR_VIA_LONGHAUL, longhaul.val);
 	if (!(longhaul.bits.RevisionID & 1)) {
@@ -468,14 +464,14 @@ static void __init longhaul_setup_voltagescaling(void)
 		mV_vrm_table = &mV_vrm85[0];
 	} else {
 		printk (KERN_INFO PFX "Mobile VRM\n");
+		if (cpu_model < CPU_NEHEMIAH)
+			return;
 		vrm_mV_table = &mobilevrm_mV[0];
 		mV_vrm_table = &mV_mobilevrm[0];
 	}
 
 	minvid = vrm_mV_table[longhaul.bits.MinimumVID];
 	maxvid = vrm_mV_table[longhaul.bits.MaximumVID];
-	numvscales = maxvid.pos - minvid.pos + 1;
-	kHz_step = (highest_speed - lowest_speed) / numvscales;
 
 	if (minvid.mV == 0 || maxvid.mV == 0 || minvid.mV > maxvid.mV) {
 		printk (KERN_INFO PFX "Bogus values Min:%d.%03d Max:%d.%03d. "
@@ -491,20 +487,59 @@ static void __init longhaul_setup_voltagescaling(void)
 		return;
 	}
 
-	printk(KERN_INFO PFX "Max VID=%d.%03d  Min VID=%d.%03d, %d possible voltage scales\n",
+	/* How many voltage steps */
+	numvscales = maxvid.pos - minvid.pos + 1;
+	printk(KERN_INFO PFX
+		"Max VID=%d.%03d  "
+		"Min VID=%d.%03d, "
+		"%d possible voltage scales\n",
 		maxvid.mV/1000, maxvid.mV%1000,
 		minvid.mV/1000, minvid.mV%1000,
 		numvscales);
 
+	/* Calculate max frequency at min voltage */
+	j = longhaul.bits.MinMHzBR;
+	if (longhaul.bits.MinMHzBR4)
+		j += 16;
+	min_vid_speed = eblcr_table[j];
+	if (min_vid_speed == -1)
+		return;
+	switch (longhaul.bits.MinMHzFSB) {
+	case 0:
+		min_vid_speed *= 13333;
+		break;
+	case 1:
+		min_vid_speed *= 10000;
+		break;
+	case 3:
+		min_vid_speed *= 6666;
+		break;
+	default:
+		return;
+		break;
+	}
+	if (min_vid_speed >= highest_speed)
+		return;
+	/* Calculate kHz for one voltage step */
+	kHz_step = (highest_speed - min_vid_speed) / numvscales;
+
+
 	j = 0;
 	while (longhaul_table[j].frequency != CPUFREQ_TABLE_END) {
 		speed = longhaul_table[j].frequency;
-		pos = (speed - lowest_speed) / kHz_step + minvid.pos;
+		if (speed > min_vid_speed)
+			pos = (speed - min_vid_speed) / kHz_step + minvid.pos;
+		else
+			pos = minvid.pos;
 		f_msr_table[longhaul_table[j].index].vrm = mV_vrm_table[pos];
+		f_msr_table[longhaul_table[j].index].pos = pos;
 		j++;
 	}
 
+	longhaul_pos = maxvid.pos;
 	can_scale_voltage = 1;
+	printk(KERN_INFO PFX "Voltage scaling enabled. "
+		"Use of \"conservative\" governor is highly recommended.\n");
 }
 
 
@@ -573,20 +608,51 @@ static int enable_arbiter_disable(void)
 	if (dev != NULL) {
 		/* Enable access to port 0x22 */
 		pci_read_config_byte(dev, reg, &pci_cmd);
-		if ( !(pci_cmd & 1<<7) ) {
+		if (!(pci_cmd & 1<<7)) {
 			pci_cmd |= 1<<7;
 			pci_write_config_byte(dev, reg, pci_cmd);
+			pci_read_config_byte(dev, reg, &pci_cmd);
+			if (!(pci_cmd & 1<<7)) {
+				printk(KERN_ERR PFX
+					"Can't enable access to port 0x22.\n");
+				return 0;
+			}
 		}
 		return 1;
 	}
 	return 0;
 }
 
+static int longhaul_setup_vt8235(void)
+{
+	struct pci_dev *dev;
+	u8 pci_cmd;
+
+	/* Find VT8235 southbridge */
+	dev = pci_find_device(PCI_VENDOR_ID_VIA, PCI_DEVICE_ID_VIA_8235, NULL);
+	if (dev != NULL) {
+		/* Set transition time to max */
+		pci_read_config_byte(dev, 0xec, &pci_cmd);
+		pci_cmd &= ~(1 << 2);
+		pci_write_config_byte(dev, 0xec, pci_cmd);
+		pci_read_config_byte(dev, 0xe4, &pci_cmd);
+		pci_cmd &= ~(1 << 7);
+		pci_write_config_byte(dev, 0xe4, pci_cmd);
+		pci_read_config_byte(dev, 0xe5, &pci_cmd);
+		pci_cmd |= 1 << 7;
+		pci_write_config_byte(dev, 0xe5, pci_cmd);
+		return 1;
+	}
+	return 0;
+}
+
 static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 {
 	struct cpuinfo_x86 *c = cpu_data;
 	char *cpuname=NULL;
 	int ret;
+	u32 lo, hi;
+	int vt8235_present;
 
 	/* Check what we have on this motherboard */
 	switch (c->x86_model) {
@@ -599,16 +665,20 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 		break;
 
 	case 7:
-		longhaul_version = TYPE_LONGHAUL_V1;
 		switch (c->x86_mask) {
 		case 0:
+			longhaul_version = TYPE_LONGHAUL_V1;
 			cpu_model = CPU_SAMUEL2;
 			cpuname = "C3 'Samuel 2' [C5B]";
-			/* Note, this is not a typo, early Samuel2's had Samuel1 ratios. */
-			memcpy (clock_ratio, samuel1_clock_ratio, sizeof(samuel1_clock_ratio));
-			memcpy (eblcr_table, samuel2_eblcr, sizeof(samuel2_eblcr));
+			/* Note, this is not a typo, early Samuel2's had
+			 * Samuel1 ratios. */
+			memcpy(clock_ratio, samuel1_clock_ratio,
+				sizeof(samuel1_clock_ratio));
+			memcpy(eblcr_table, samuel2_eblcr,
+				sizeof(samuel2_eblcr));
 			break;
 		case 1 ... 15:
+			longhaul_version = TYPE_LONGHAUL_V2;
 			if (c->x86_mask < 8) {
 				cpu_model = CPU_SAMUEL2;
 				cpuname = "C3 'Samuel 2' [C5B]";
@@ -616,8 +686,10 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 				cpu_model = CPU_EZRA;
 				cpuname = "C3 'Ezra' [C5C]";
 			}
-			memcpy (clock_ratio, ezra_clock_ratio, sizeof(ezra_clock_ratio));
-			memcpy (eblcr_table, ezra_eblcr, sizeof(ezra_eblcr));
+			memcpy(clock_ratio, ezra_clock_ratio,
+				sizeof(ezra_clock_ratio));
+			memcpy(eblcr_table, ezra_eblcr,
+				sizeof(ezra_eblcr));
 			break;
 		}
 		break;
@@ -632,24 +704,24 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 		break;
 
 	case 9:
-		cpu_model = CPU_NEHEMIAH;
 		longhaul_version = TYPE_POWERSAVER;
-		numscales=32;
+		numscales = 32;
+		memcpy(clock_ratio,
+		       nehemiah_clock_ratio,
+		       sizeof(nehemiah_clock_ratio));
+		memcpy(eblcr_table, nehemiah_eblcr, sizeof(nehemiah_eblcr));
 		switch (c->x86_mask) {
 		case 0 ... 1:
-			cpuname = "C3 'Nehemiah A' [C5N]";
-			memcpy (clock_ratio, nehemiah_a_clock_ratio, sizeof(nehemiah_a_clock_ratio));
-			memcpy (eblcr_table, nehemiah_a_eblcr, sizeof(nehemiah_a_eblcr));
+			cpu_model = CPU_NEHEMIAH;
+			cpuname = "C3 'Nehemiah A' [C5XLOE]";
 			break;
 		case 2 ... 4:
-			cpuname = "C3 'Nehemiah B' [C5N]";
-			memcpy (clock_ratio, nehemiah_b_clock_ratio, sizeof(nehemiah_b_clock_ratio));
-			memcpy (eblcr_table, nehemiah_b_eblcr, sizeof(nehemiah_b_eblcr));
+			cpu_model = CPU_NEHEMIAH;
+			cpuname = "C3 'Nehemiah B' [C5XLOH]";
 			break;
 		case 5 ... 15:
-			cpuname = "C3 'Nehemiah C' [C5N]";
-			memcpy (clock_ratio, nehemiah_c_clock_ratio, sizeof(nehemiah_c_clock_ratio));
-			memcpy (eblcr_table, nehemiah_c_eblcr, sizeof(nehemiah_c_eblcr));
+			cpu_model = CPU_NEHEMIAH_C;
+			cpuname = "C3 'Nehemiah C' [C5P]";
 			break;
 		}
 		break;
@@ -658,6 +730,13 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 		cpuname = "Unknown";
 		break;
 	}
+	/* Check Longhaul ver. 2 */
+	if (longhaul_version == TYPE_LONGHAUL_V2) {
+		rdmsr(MSR_VIA_LONGHAUL, lo, hi);
+		if (lo == 0 && hi == 0)
+			/* Looks like MSR isn't present */
+			longhaul_version = TYPE_LONGHAUL_V1;
+	}
 
 	printk (KERN_INFO PFX "VIA %s CPU detected.  ", cpuname);
 	switch (longhaul_version) {
@@ -670,15 +749,18 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 		break;
 	};
 
+	/* Doesn't hurt */
+	vt8235_present = longhaul_setup_vt8235();
+
 	/* Find ACPI data for processor */
-	acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT, ACPI_UINT32_MAX,
-			    &longhaul_walk_callback, NULL, (void *)&pr);
+	acpi_walk_namespace(ACPI_TYPE_PROCESSOR, ACPI_ROOT_OBJECT,
+				ACPI_UINT32_MAX, &longhaul_walk_callback,
+				NULL, (void *)&pr);
 
 	/* Check ACPI support for C3 state */
-	if ((pr != NULL) && (longhaul_version == TYPE_POWERSAVER)) {
+	if (pr != NULL && longhaul_version != TYPE_LONGHAUL_V1) {
 		cx = &pr->power.states[ACPI_STATE_C3];
-		if (cx->address > 0 &&
-		   (cx->latency <= 1000 || ignore_latency != 0) ) {
+		if (cx->address > 0 && cx->latency <= 1000) {
 			longhaul_flags |= USE_ACPI_C3;
 			goto print_support_type;
 		}
@@ -688,8 +770,11 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 		longhaul_flags |= USE_NORTHBRIDGE;
 		goto print_support_type;
 	}
-
-	/* No ACPI C3 or we can't use it */
+	/* Use VT8235 southbridge if present */
+	if (longhaul_version == TYPE_POWERSAVER && vt8235_present) {
+		longhaul_flags |= USE_VT8235;
+		goto print_support_type;
+	}
 	/* Check ACPI support for bus master arbiter disable */
 	if ((pr == NULL) || !(pr->flags.bm_control)) {
 		printk(KERN_ERR PFX
@@ -698,18 +783,18 @@ static int __init longhaul_cpu_init(struct cpufreq_policy *policy)
 	}
 
 print_support_type:
-	if (!(longhaul_flags & USE_NORTHBRIDGE)) {
-		printk (KERN_INFO PFX "Using ACPI support.\n");
-	} else {
+	if (longhaul_flags & USE_NORTHBRIDGE)
 		printk (KERN_INFO PFX "Using northbridge support.\n");
-	}
+	else if (longhaul_flags & USE_VT8235)
+		printk (KERN_INFO PFX "Using VT8235 support.\n");
+	else
+		printk (KERN_INFO PFX "Using ACPI support.\n");
 
 	ret = longhaul_get_ranges();
 	if (ret != 0)
 		return ret;
 
-	if ((longhaul_version==TYPE_LONGHAUL_V2 || longhaul_version==TYPE_POWERSAVER) &&
-		 (scale_voltage != 0))
+	if ((longhaul_version != TYPE_LONGHAUL_V1) && (scale_voltage != 0))
 		longhaul_setup_voltagescaling();
 
 	policy->governor = CPUFREQ_DEFAULT_GOVERNOR;
@@ -797,8 +882,6 @@ static void __exit longhaul_exit(void)
 
 module_param (scale_voltage, int, 0644);
 MODULE_PARM_DESC(scale_voltage, "Scale voltage of processor");
-module_param(ignore_latency, int, 0644);
-MODULE_PARM_DESC(ignore_latency, "Skip ACPI C3 latency test");
 
 MODULE_AUTHOR ("Dave Jones <davej@codemonkey.org.uk>");
 MODULE_DESCRIPTION ("Longhaul driver for VIA Cyrix processors.");

arch/i386/kernel/cpu/cpufreq/longhaul.h

@@ -235,84 +235,14 @@ static int __initdata ezrat_eblcr[32] = {
 /*
  * VIA C3 Nehemiah */
 
-static int __initdata nehemiah_a_clock_ratio[32] = {
+static int __initdata  nehemiah_clock_ratio[32] = {
 	100, /* 0000 -> 10.0x */
 	160, /* 0001 -> 16.0x */
-	-1,  /* 0010 ->  RESERVED */
-	90,  /* 0011 ->  9.0x */
-	95,  /* 0100 ->  9.5x */
-	-1,  /* 0101 ->  RESERVED */
-	-1,  /* 0110 ->  RESERVED */
-	55,  /* 0111 ->  5.5x */
-	60,  /* 1000 ->  6.0x */
-	70,  /* 1001 ->  7.0x */
-	80,  /* 1010 ->  8.0x */
-	50,  /* 1011 ->  5.0x */
-	65,  /* 1100 ->  6.5x */
-	75,  /* 1101 ->  7.5x */
-	85,  /* 1110 ->  8.5x */
-	120, /* 1111 -> 12.0x */
-	100, /* 0000 -> 10.0x */
-	-1,  /* 0001 -> RESERVED */
-	120, /* 0010 -> 12.0x */
-	90,  /* 0011 ->  9.0x */
-	105, /* 0100 -> 10.5x */
-	115, /* 0101 -> 11.5x */
-	125, /* 0110 -> 12.5x */
-	135, /* 0111 -> 13.5x */
-	140, /* 1000 -> 14.0x */
-	150, /* 1001 -> 15.0x */
-	160, /* 1010 -> 16.0x */
-	130, /* 1011 -> 13.0x */
-	145, /* 1100 -> 14.5x */
-	155, /* 1101 -> 15.5x */
-	-1,  /* 1110 -> RESERVED (13.0x) */
-	120, /* 1111 -> 12.0x */
-};
-
-static int __initdata  nehemiah_b_clock_ratio[32] = {
-	100, /* 0000 -> 10.0x */
-	160, /* 0001 -> 16.0x */
-	-1,  /* 0010 ->  RESERVED */
-	90,  /* 0011 ->  9.0x */
-	95,  /* 0100 ->  9.5x */
-	-1,  /* 0101 ->  RESERVED */
-	-1,  /* 0110 ->  RESERVED */
-	55,  /* 0111 ->  5.5x */
-	60,  /* 1000 ->  6.0x */
-	70,  /* 1001 ->  7.0x */
-	80,  /* 1010 ->  8.0x */
-	50,  /* 1011 ->  5.0x */
-	65,  /* 1100 ->  6.5x */
-	75,  /* 1101 ->  7.5x */
-	85,  /* 1110 ->  8.5x */
-	120, /* 1111 -> 12.0x */
-	100, /* 0000 -> 10.0x */
-	110, /* 0001 -> 11.0x */
-	120, /* 0010 -> 12.0x */
-	90,  /* 0011 ->  9.0x */
-	105, /* 0100 -> 10.5x */
-	115, /* 0101 -> 11.5x */
-	125, /* 0110 -> 12.5x */
-	135, /* 0111 -> 13.5x */
-	140, /* 1000 -> 14.0x */
-	150, /* 1001 -> 15.0x */
-	160, /* 1010 -> 16.0x */
-	130, /* 1011 -> 13.0x */
-	145, /* 1100 -> 14.5x */
-	155, /* 1101 -> 15.5x */
-	-1,  /* 1110 -> RESERVED (13.0x) */
-	120, /* 1111 -> 12.0x */
-};
-
-static int __initdata  nehemiah_c_clock_ratio[32] = {
-	100, /* 0000 -> 10.0x */
-	160, /* 0001 -> 16.0x */
-	40,  /* 0010 ->  RESERVED */
+	40,  /* 0010 ->  4.0x */
 	90,  /* 0011 ->  9.0x */
 	95,  /* 0100 ->  9.5x */
 	-1,  /* 0101 ->  RESERVED */
-	45,  /* 0110 ->  RESERVED */
+	45,  /* 0110 ->  4.5x */
 	55,  /* 0111 ->  5.5x */
 	60,  /* 1000 ->  6.0x */
 	70,  /* 1001 ->  7.0x */
@@ -340,84 +270,14 @@ static int __initdata  nehemiah_c_clock_ratio[32] = {
 	120, /* 1111 -> 12.0x */
 };
 
-static int __initdata nehemiah_a_eblcr[32] = {
-	50,  /* 0000 ->  5.0x */
-	160, /* 0001 -> 16.0x */
-	-1,  /* 0010 ->  RESERVED */
-	100, /* 0011 -> 10.0x */
-	55,  /* 0100 ->  5.5x */
-	-1,  /* 0101 ->  RESERVED */
-	-1,  /* 0110 ->  RESERVED */
-	95,  /* 0111 ->  9.5x */
-	90,  /* 1000 ->  9.0x */
-	70,  /* 1001 ->  7.0x */
-	80,  /* 1010 ->  8.0x */
-	60,  /* 1011 ->  6.0x */
-	120, /* 1100 -> 12.0x */
-	75,  /* 1101 ->  7.5x */
-	85,  /* 1110 ->  8.5x */
-	65,  /* 1111 ->  6.5x */
-	90,  /* 0000 ->  9.0x */
-	-1,  /* 0001 -> RESERVED */
-	120, /* 0010 -> 12.0x */
-	100, /* 0011 -> 10.0x */
-	135, /* 0100 -> 13.5x */
-	115, /* 0101 -> 11.5x */
-	125, /* 0110 -> 12.5x */
-	105, /* 0111 -> 10.5x */
-	130, /* 1000 -> 13.0x */
-	150, /* 1001 -> 15.0x */
-	160, /* 1010 -> 16.0x */
-	140, /* 1011 -> 14.0x */
-	120, /* 1100 -> 12.0x */
-	155, /* 1101 -> 15.5x */
-	-1,  /* 1110 -> RESERVED (13.0x) */
-	145 /* 1111 -> 14.5x */
-   /* end of table  */
-};
-static int __initdata nehemiah_b_eblcr[32] = {
-	50,  /* 0000 ->  5.0x */
-	160, /* 0001 -> 16.0x */
-	-1,  /* 0010 ->  RESERVED */
-	100, /* 0011 -> 10.0x */
-	55,  /* 0100 ->  5.5x */
-	-1,  /* 0101 ->  RESERVED */
-	-1,  /* 0110 ->  RESERVED */
-	95,  /* 0111 ->  9.5x */
-	90,  /* 1000 ->  9.0x */
-	70,  /* 1001 ->  7.0x */
-	80,  /* 1010 ->  8.0x */
-	60,  /* 1011 ->  6.0x */
-	120, /* 1100 -> 12.0x */
-	75,  /* 1101 ->  7.5x */
-	85,  /* 1110 ->  8.5x */
-	65,  /* 1111 ->  6.5x */
-	90,  /* 0000 ->  9.0x */
-	110, /* 0001 -> 11.0x */
-	120, /* 0010 -> 12.0x */
-	100, /* 0011 -> 10.0x */
-	135, /* 0100 -> 13.5x */
-	115, /* 0101 -> 11.5x */
-	125, /* 0110 -> 12.5x */
-	105, /* 0111 -> 10.5x */
-	130, /* 1000 -> 13.0x */
-	150, /* 1001 -> 15.0x */
-	160, /* 1010 -> 16.0x */
-	140, /* 1011 -> 14.0x */
-	120, /* 1100 -> 12.0x */
-	155, /* 1101 -> 15.5x */
-	-1,  /* 1110 -> RESERVED (13.0x) */
-	145 /* 1111 -> 14.5x */
-	   /* end of table  */
-};
-static int __initdata nehemiah_c_eblcr[32] = {
+static int __initdata nehemiah_eblcr[32] = {
 	50,  /* 0000 ->  5.0x */
 	160, /* 0001 -> 16.0x */
-	40,  /* 0010 ->  RESERVED */
+	40,  /* 0010 ->  4.0x */
 	100, /* 0011 -> 10.0x */
 	55,  /* 0100 ->  5.5x */
 	-1,  /* 0101 ->  RESERVED */
-	45,  /* 0110 ->  RESERVED */
+	45,  /* 0110 ->  4.5x */
 	95,  /* 0111 ->  9.5x */
 	90,  /* 1000 ->  9.0x */
 	70,  /* 1001 ->  7.0x */
@@ -443,7 +303,6 @@ static int __initdata nehemiah_c_eblcr[32] = {
 	155, /* 1101 -> 15.5x */
 	-1,  /* 1110 -> RESERVED (13.0x) */
 	145 /* 1111 -> 14.5x */
-	  /* end of table  */
 };
 
 /*

arch/i386/kernel/cpu/cpufreq/powernow-k8.c

@@ -1289,7 +1289,11 @@ static unsigned int powernowk8_get (unsigned int cpu)
 	if (query_current_values_with_pending_wait(data))
 		goto out;
 
-	khz = find_khz_freq_from_fid(data->currfid);
+	if (cpu_family == CPU_HW_PSTATE)
+		khz = find_khz_freq_from_fiddid(data->currfid, data->currdid);
+	else
+		khz = find_khz_freq_from_fid(data->currfid);
+
 
 out:
 	set_cpus_allowed(current, oldmask);

arch/i386/kernel/cpu/cyrix.c

@@ -6,6 +6,7 @@
 #include <asm/io.h>
 #include <asm/processor.h>
 #include <asm/timer.h>
+#include <asm/pci-direct.h>
 
 #include "cpu.h"
 
@@ -161,19 +162,19 @@ static void __cpuinit set_cx86_inc(void)
 static void __cpuinit geode_configure(void)
 {
 	unsigned long flags;
-	u8 ccr3, ccr4;
+	u8 ccr3;
 	local_irq_save(flags);
 
 	/* Suspend on halt power saving and enable #SUSP pin */
 	setCx86(CX86_CCR2, getCx86(CX86_CCR2) | 0x88);
 
 	ccr3 = getCx86(CX86_CCR3);
-	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);	/* Enable */
-	
-	ccr4 = getCx86(CX86_CCR4);
-	ccr4 |= 0x38;		/* FPU fast, DTE cache, Mem bypass */
+	setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);	/* enable MAPEN */
 	
-	setCx86(CX86_CCR3, ccr3);
+
+	/* FPU fast, DTE cache, Mem bypass */
+	setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x38);
+	setCx86(CX86_CCR3, ccr3);			/* disable MAPEN */
 	
 	set_cx86_memwb();
 	set_cx86_reorder();	
@@ -183,14 +184,6 @@ static void __cpuinit geode_configure(void)
 }
 
 
-#ifdef CONFIG_PCI
-static struct pci_device_id __cpuinitdata cyrix_55x0[] = {
-	{ PCI_DEVICE(PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5510) },
-	{ PCI_DEVICE(PCI_VENDOR_ID_CYRIX, PCI_DEVICE_ID_CYRIX_5520) },
-	{ },
-};
-#endif
-
 static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
 {
 	unsigned char dir0, dir0_msn, dir0_lsn, dir1 = 0;
@@ -258,6 +251,8 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
 
 	case 4: /* MediaGX/GXm or Geode GXM/GXLV/GX1 */
 #ifdef CONFIG_PCI
+	{
+		u32 vendor, device;
 		/* It isn't really a PCI quirk directly, but the cure is the
 		   same. The MediaGX has deep magic SMM stuff that handles the
 		   SB emulation. It thows away the fifo on disable_dma() which
@@ -273,22 +268,34 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c)
 		printk(KERN_INFO "Working around Cyrix MediaGX virtual DMA bugs.\n");
 		isa_dma_bridge_buggy = 2;
 
+		/* We do this before the PCI layer is running. However we
+		   are safe here as we know the bridge must be a Cyrix
+		   companion and must be present */
+		vendor = read_pci_config_16(0, 0, 0x12, PCI_VENDOR_ID);
+		device = read_pci_config_16(0, 0, 0x12, PCI_DEVICE_ID);
 
 		/*
 		 *  The 5510/5520 companion chips have a funky PIT.
 		 */  
-		if (pci_dev_present(cyrix_55x0))
+		if (vendor == PCI_VENDOR_ID_CYRIX &&
+	 (device == PCI_DEVICE_ID_CYRIX_5510 || device == PCI_DEVICE_ID_CYRIX_5520))
 			pit_latch_buggy = 1;
+	}
 #endif
 		c->x86_cache_size=16;	/* Yep 16K integrated cache thats it */
 
 		/* GXm supports extended cpuid levels 'ala' AMD */
 		if (c->cpuid_level == 2) {
 			/* Enable cxMMX extensions (GX1 Datasheet 54) */
-			setCx86(CX86_CCR7, getCx86(CX86_CCR7)|1);
+			setCx86(CX86_CCR7, getCx86(CX86_CCR7) | 1);
 			
-			/* GXlv/GXm/GX1 */
-			if((dir1 >= 0x50 && dir1 <= 0x54) || dir1 >= 0x63)
+			/*
+			 * GXm : 0x30 ... 0x5f GXm  datasheet 51
+			 * GXlv: 0x6x          GXlv datasheet 54
+			 *  ?  : 0x7x
+			 * GX1 : 0x8x          GX1  datasheet 56
+			 */
+			if((0x30 <= dir1 && dir1 <= 0x6f) || (0x80 <=dir1 && dir1 <= 0x8f))
 				geode_configure();
 			get_model_name(c);  /* get CPU marketing name */
 			return;
@@ -415,15 +422,14 @@ static void __cpuinit cyrix_identify(struct cpuinfo_x86 * c)
 		
    	        if (dir0 == 5 || dir0 == 3)
    	        {
-			unsigned char ccr3, ccr4;
+			unsigned char ccr3;
 			unsigned long flags;
 			printk(KERN_INFO "Enabling CPUID on Cyrix processor.\n");
 			local_irq_save(flags);
 			ccr3 = getCx86(CX86_CCR3);
-			setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10); /* enable MAPEN  */
-			ccr4 = getCx86(CX86_CCR4);
-			setCx86(CX86_CCR4, ccr4 | 0x80);          /* enable cpuid  */
-			setCx86(CX86_CCR3, ccr3);                 /* disable MAPEN */
+			setCx86(CX86_CCR3, (ccr3 & 0x0f) | 0x10);       /* enable MAPEN  */
+			setCx86(CX86_CCR4, getCx86(CX86_CCR4) | 0x80);  /* enable cpuid  */
+			setCx86(CX86_CCR3, ccr3);                       /* disable MAPEN */
 			local_irq_restore(flags);
 		}
 	}

arch/i386/kernel/cpu/mcheck/mce.c

@@ -12,6 +12,7 @@
 
 #include <asm/processor.h> 
 #include <asm/system.h>
+#include <asm/mce.h>
 
 #include "mce.h"
 

arch/i386/kernel/cpu/mcheck/mce.h

@@ -1,4 +1,5 @@
 #include <linux/init.h>
+#include <asm/mce.h>
 
 void amd_mcheck_init(struct cpuinfo_x86 *c);
 void intel_p4_mcheck_init(struct cpuinfo_x86 *c);
@@ -9,6 +10,5 @@ void winchip_mcheck_init(struct cpuinfo_x86 *c);
 /* Call the installed machine check handler for this CPU setup. */
 extern fastcall void (*machine_check_vector)(struct pt_regs *, long error_code);
 
-extern int mce_disabled;
 extern int nr_mce_banks;
 

arch/i386/kernel/cpu/mcheck/p4.c

@@ -12,6 +12,7 @@
 #include <asm/system.h>
 #include <asm/msr.h>
 #include <asm/apic.h>
+#include <asm/idle.h>
 
 #include <asm/therm_throt.h>
 
@@ -59,6 +60,7 @@ static void (*vendor_thermal_interrupt)(struct pt_regs *regs) = unexpected_therm
 
 fastcall void smp_thermal_interrupt(struct pt_regs *regs)
 {
+	exit_idle();
 	irq_enter();
 	vendor_thermal_interrupt(regs);
 	irq_exit();

arch/i386/kernel/cpu/mtrr/if.c

@@ -211,6 +211,9 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 	default:
 		return -ENOTTY;
 	case MTRRIOC_ADD_ENTRY:
+#ifdef CONFIG_COMPAT
+	case MTRRIOC32_ADD_ENTRY:
+#endif
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		err =
@@ -218,21 +221,33 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 				  file, 0);
 		break;
 	case MTRRIOC_SET_ENTRY:
+#ifdef CONFIG_COMPAT
+	case MTRRIOC32_SET_ENTRY:
+#endif
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		err = mtrr_add(sentry.base, sentry.size, sentry.type, 0);
 		break;
 	case MTRRIOC_DEL_ENTRY:
+#ifdef CONFIG_COMPAT
+	case MTRRIOC32_DEL_ENTRY:
+#endif
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		err = mtrr_file_del(sentry.base, sentry.size, file, 0);
 		break;
 	case MTRRIOC_KILL_ENTRY:
+#ifdef CONFIG_COMPAT
+	case MTRRIOC32_KILL_ENTRY:
+#endif
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		err = mtrr_del(-1, sentry.base, sentry.size);
 		break;
 	case MTRRIOC_GET_ENTRY:
+#ifdef CONFIG_COMPAT
+	case MTRRIOC32_GET_ENTRY:
+#endif
 		if (gentry.regnum >= num_var_ranges)
 			return -EINVAL;
 		mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);
@@ -249,6 +264,9 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 
 		break;
 	case MTRRIOC_ADD_PAGE_ENTRY:
+#ifdef CONFIG_COMPAT
+	case MTRRIOC32_ADD_PAGE_ENTRY:
+#endif
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		err =
@@ -256,21 +274,33 @@ mtrr_ioctl(struct file *file, unsigned int cmd, unsigned long __arg)
 				  file, 1);
 		break;
 	case MTRRIOC_SET_PAGE_ENTRY:
+#ifdef CONFIG_COMPAT
+	case MTRRIOC32_SET_PAGE_ENTRY:
+#endif
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		err = mtrr_add_page(sentry.base, sentry.size, sentry.type, 0);
 		break;
 	case MTRRIOC_DEL_PAGE_ENTRY:
+#ifdef CONFIG_COMPAT
+	case MTRRIOC32_DEL_PAGE_ENTRY:
+#endif
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		err = mtrr_file_del(sentry.base, sentry.size, file, 1);
 		break;
 	case MTRRIOC_KILL_PAGE_ENTRY:
+#ifdef CONFIG_COMPAT
+	case MTRRIOC32_KILL_PAGE_ENTRY:
+#endif
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 		err = mtrr_del_page(-1, sentry.base, sentry.size);
 		break;
 	case MTRRIOC_GET_PAGE_ENTRY:
+#ifdef CONFIG_COMPAT
+	case MTRRIOC32_GET_PAGE_ENTRY:
+#endif
 		if (gentry.regnum >= num_var_ranges)
 			return -EINVAL;
 		mtrr_if->get(gentry.regnum, &gentry.base, &size, &type);

arch/i386/kernel/cpu/mtrr/main.c

@@ -50,7 +50,7 @@ u32 num_var_ranges = 0;
 unsigned int *usage_table;
 static DEFINE_MUTEX(mtrr_mutex);
 
-u32 size_or_mask, size_and_mask;
+u64 size_or_mask, size_and_mask;
 
 static struct mtrr_ops * mtrr_ops[X86_VENDOR_NUM] = {};
 
@@ -662,8 +662,8 @@ void __init mtrr_bp_init(void)
 			     boot_cpu_data.x86_mask == 0x4))
 				phys_addr = 36;
 
-			size_or_mask = ~((1 << (phys_addr - PAGE_SHIFT)) - 1);
-			size_and_mask = ~size_or_mask & 0xfff00000;
+			size_or_mask = ~((1ULL << (phys_addr - PAGE_SHIFT)) - 1);
+			size_and_mask = ~size_or_mask & 0xfffff00000ULL;
 		} else if (boot_cpu_data.x86_vendor == X86_VENDOR_CENTAUR &&
 			   boot_cpu_data.x86 == 6) {
 			/* VIA C* family have Intel style MTRRs, but

arch/i386/kernel/cpu/mtrr/mtrr.h

@@ -84,7 +84,7 @@ void get_mtrr_state(void);
 
 extern void set_mtrr_ops(struct mtrr_ops * ops);
 
-extern u32 size_or_mask, size_and_mask;
+extern u64 size_or_mask, size_and_mask;
 extern struct mtrr_ops * mtrr_if;
 
 #define is_cpu(vnd)	(mtrr_if && mtrr_if->vendor == X86_VENDOR_##vnd)

arch/i386/kernel/cpu/proc.c

@@ -29,7 +29,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 		NULL, NULL, NULL, "syscall", NULL, NULL, NULL, NULL,
 		NULL, NULL, NULL, "mp", "nx", NULL, "mmxext", NULL,
-		NULL, "fxsr_opt", "rdtscp", NULL, NULL, "lm", "3dnowext", "3dnow",
+		NULL, "fxsr_opt", "pdpe1gb", "rdtscp", NULL, "lm", "3dnowext", "3dnow",
 
 		/* Transmeta-defined */
 		"recovery", "longrun", NULL, "lrti", NULL, NULL, NULL, NULL,
@@ -47,7 +47,7 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		/* Intel-defined (#2) */
 		"pni", NULL, NULL, "monitor", "ds_cpl", "vmx", "smx", "est",
 		"tm2", "ssse3", "cid", NULL, NULL, "cx16", "xtpr", NULL,
-		NULL, NULL, "dca", NULL, NULL, NULL, NULL, NULL,
+		NULL, NULL, "dca", NULL, NULL, NULL, NULL, "popcnt",
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 
 		/* VIA/Cyrix/Centaur-defined */
@@ -57,8 +57,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 
 		/* AMD-defined (#2) */
-		"lahf_lm", "cmp_legacy", "svm", NULL, "cr8legacy", NULL, NULL, NULL,
-		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
+		"lahf_lm", "cmp_legacy", "svm", "extapic", "cr8legacy", "abm",
+		"sse4a", "misalignsse",
+		"3dnowprefetch", "osvw", "ibs", NULL, NULL, NULL, NULL, NULL,
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 		NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL,
 	};
@@ -69,8 +70,11 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 		"ttp",  /* thermal trip */
 		"tm",
 		"stc",
+		"100mhzsteps",
+		"hwpstate",
 		NULL,
-		/* nothing */	/* constant_tsc - moved to flags */
+		NULL,	/* constant_tsc - moved to flags */
+		/* nothing */
 	};
 	struct cpuinfo_x86 *c = v;
 	int i, n = c - cpu_data;

arch/i386/kernel/cpu/transmeta.c

@@ -9,7 +9,7 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c)
 {
 	unsigned int cap_mask, uk, max, dummy;
 	unsigned int cms_rev1, cms_rev2;
-	unsigned int cpu_rev, cpu_freq, cpu_flags, new_cpu_rev;
+	unsigned int cpu_rev, cpu_freq = 0, cpu_flags, new_cpu_rev;
 	char cpu_info[65];
 
 	get_model_name(c);	/* Same as AMD/Cyrix */
@@ -72,6 +72,9 @@ static void __cpuinit init_transmeta(struct cpuinfo_x86 *c)
 	wrmsr(0x80860004, ~0, uk);
 	c->x86_capability[0] = cpuid_edx(0x00000001);
 	wrmsr(0x80860004, cap_mask, uk);
+
+	/* All Transmeta CPUs have a constant TSC */
+	set_bit(X86_FEATURE_CONSTANT_TSC, c->x86_capability);
 	
 	/* If we can run i686 user-space code, call us an i686 */
 #define USER686 (X86_FEATURE_TSC|X86_FEATURE_CX8|X86_FEATURE_CMOV)

arch/i386/kernel/cpuid.c

@@ -48,7 +48,6 @@ static struct class *cpuid_class;
 #ifdef CONFIG_SMP
 
 struct cpuid_command {
-	int cpu;
 	u32 reg;
 	u32 *data;
 };
@@ -57,8 +56,7 @@ static void cpuid_smp_cpuid(void *cmd_block)
 {
 	struct cpuid_command *cmd = (struct cpuid_command *)cmd_block;
 
-	if (cmd->cpu == smp_processor_id())
-		cpuid(cmd->reg, &cmd->data[0], &cmd->data[1], &cmd->data[2],
+	cpuid(cmd->reg, &cmd->data[0], &cmd->data[1], &cmd->data[2],
 		      &cmd->data[3]);
 }
 
@@ -70,11 +68,10 @@ static inline void do_cpuid(int cpu, u32 reg, u32 * data)
 	if (cpu == smp_processor_id()) {
 		cpuid(reg, &data[0], &data[1], &data[2], &data[3]);
 	} else {
-		cmd.cpu = cpu;
 		cmd.reg = reg;
 		cmd.data = data;
 
-		smp_call_function(cpuid_smp_cpuid, &cmd, 1, 1);
+		smp_call_function_single(cpu, cpuid_smp_cpuid, &cmd, 1, 1);
 	}
 	preempt_enable();
 }

arch/i386/kernel/e820.c

@@ -14,6 +14,7 @@
 #include <asm/pgtable.h>
 #include <asm/page.h>
 #include <asm/e820.h>
+#include <asm/setup.h>
 
 #ifdef CONFIG_EFI
 int efi_enabled = 0;
@@ -156,21 +157,22 @@ static struct resource standard_io_resources[] = { {
 	.flags	= IORESOURCE_BUSY | IORESOURCE_IO
 } };
 
-static int romsignature(const unsigned char *x)
+#define ROMSIGNATURE 0xaa55
+
+static int __init romsignature(const unsigned char *rom)
 {
 	unsigned short sig;
-	int ret = 0;
-	if (probe_kernel_address((const unsigned short *)x, sig) == 0)
-		ret = (sig == 0xaa55);
-	return ret;
+
+	return probe_kernel_address((const unsigned short *)rom, sig) == 0 &&
+	       sig == ROMSIGNATURE;
 }
 
 static int __init romchecksum(unsigned char *rom, unsigned long length)
 {
-	unsigned char *p, sum = 0;
+	unsigned char sum;
 
-	for (p = rom; p < rom + length; p++)
-		sum += *p;
+	for (sum = 0; length; length--)
+		sum += *rom++;
 	return sum == 0;
 }
 

arch/i386/kernel/entry.S

@@ -30,7 +30,7 @@
  *	18(%esp) - %eax
  *	1C(%esp) - %ds
  *	20(%esp) - %es
- *	24(%esp) - %gs
+ *	24(%esp) - %fs
  *	28(%esp) - orig_eax
  *	2C(%esp) - %eip
  *	30(%esp) - %cs
@@ -99,9 +99,9 @@ VM_MASK		= 0x00020000
 
 #define SAVE_ALL \
 	cld; \
-	pushl %gs; \
+	pushl %fs; \
 	CFI_ADJUST_CFA_OFFSET 4;\
-	/*CFI_REL_OFFSET gs, 0;*/\
+	/*CFI_REL_OFFSET fs, 0;*/\
 	pushl %es; \
 	CFI_ADJUST_CFA_OFFSET 4;\
 	/*CFI_REL_OFFSET es, 0;*/\
@@ -133,7 +133,7 @@ VM_MASK		= 0x00020000
 	movl %edx, %ds; \
 	movl %edx, %es; \
 	movl $(__KERNEL_PDA), %edx; \
-	movl %edx, %gs
+	movl %edx, %fs
 
 #define RESTORE_INT_REGS \
 	popl %ebx;	\
@@ -166,9 +166,9 @@ VM_MASK		= 0x00020000
 2:	popl %es;	\
 	CFI_ADJUST_CFA_OFFSET -4;\
 	/*CFI_RESTORE es;*/\
-3:	popl %gs;	\
+3:	popl %fs;	\
 	CFI_ADJUST_CFA_OFFSET -4;\
-	/*CFI_RESTORE gs;*/\
+	/*CFI_RESTORE fs;*/\
 .pushsection .fixup,"ax";	\
 4:	movl $0,(%esp);	\
 	jmp 1b;		\
@@ -227,6 +227,7 @@ ENTRY(ret_from_fork)
 	CFI_ADJUST_CFA_OFFSET -4
 	jmp syscall_exit
 	CFI_ENDPROC
+END(ret_from_fork)
 
 /*
  * Return to user mode is not as complex as all this looks,
@@ -258,6 +259,7 @@ ENTRY(resume_userspace)
 					# int/exception return?
 	jne work_pending
 	jmp restore_all
+END(ret_from_exception)
 
 #ifdef CONFIG_PREEMPT
 ENTRY(resume_kernel)
@@ -272,6 +274,7 @@ need_resched:
 	jz restore_all
 	call preempt_schedule_irq
 	jmp need_resched
+END(resume_kernel)
 #endif
 	CFI_ENDPROC
 
@@ -349,16 +352,17 @@ sysenter_past_esp:
 	movl PT_OLDESP(%esp), %ecx
 	xorl %ebp,%ebp
 	TRACE_IRQS_ON
-1:	mov  PT_GS(%esp), %gs
+1:	mov  PT_FS(%esp), %fs
 	ENABLE_INTERRUPTS_SYSEXIT
 	CFI_ENDPROC
 .pushsection .fixup,"ax"
-2:	movl $0,PT_GS(%esp)
+2:	movl $0,PT_FS(%esp)
 	jmp 1b
 .section __ex_table,"a"
 	.align 4
 	.long 1b,2b
 .popsection
+ENDPROC(sysenter_entry)
 
 	# system call handler stub
 ENTRY(system_call)
@@ -459,6 +463,7 @@ ldt_ss:
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp restore_nocheck
 	CFI_ENDPROC
+ENDPROC(system_call)
 
 	# perform work that needs to be done immediately before resumption
 	ALIGN
@@ -504,6 +509,7 @@ work_notifysig_v86:
 	xorl %edx, %edx
 	call do_notify_resume
 	jmp resume_userspace_sig
+END(work_pending)
 
 	# perform syscall exit tracing
 	ALIGN
@@ -519,6 +525,7 @@ syscall_trace_entry:
 	cmpl $(nr_syscalls), %eax
 	jnae syscall_call
 	jmp syscall_exit
+END(syscall_trace_entry)
 
 	# perform syscall exit tracing
 	ALIGN
@@ -532,6 +539,7 @@ syscall_exit_work:
 	movl $1, %edx
 	call do_syscall_trace
 	jmp resume_userspace
+END(syscall_exit_work)
 	CFI_ENDPROC
 
 	RING0_INT_FRAME			# can't unwind into user space anyway
@@ -542,15 +550,17 @@ syscall_fault:
 	GET_THREAD_INFO(%ebp)
 	movl $-EFAULT,PT_EAX(%esp)
 	jmp resume_userspace
+END(syscall_fault)
 
 syscall_badsys:
 	movl $-ENOSYS,PT_EAX(%esp)
 	jmp resume_userspace
+END(syscall_badsys)
 	CFI_ENDPROC
 
 #define FIXUP_ESPFIX_STACK \
 	/* since we are on a wrong stack, we cant make it a C code :( */ \
-	movl %gs:PDA_cpu, %ebx; \
+	movl %fs:PDA_cpu, %ebx; \
 	PER_CPU(cpu_gdt_descr, %ebx); \
 	movl GDS_address(%ebx), %ebx; \
 	GET_DESC_BASE(GDT_ENTRY_ESPFIX_SS, %ebx, %eax, %ax, %al, %ah); \
@@ -581,9 +591,9 @@ syscall_badsys:
 ENTRY(interrupt)
 .text
 
-vector=0
 ENTRY(irq_entries_start)
 	RING0_INT_FRAME
+vector=0
 .rept NR_IRQS
 	ALIGN
  .if vector
@@ -592,11 +602,16 @@ ENTRY(irq_entries_start)
 1:	pushl $~(vector)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp common_interrupt
-.data
+ .previous
 	.long 1b
-.text
+ .text
 vector=vector+1
 .endr
+END(irq_entries_start)
+
+.previous
+END(interrupt)
+.previous
 
 /*
  * the CPU automatically disables interrupts when executing an IRQ vector,
@@ -609,6 +624,7 @@ common_interrupt:
 	movl %esp,%eax
 	call do_IRQ
 	jmp ret_from_intr
+ENDPROC(common_interrupt)
 	CFI_ENDPROC
 
 #define BUILD_INTERRUPT(name, nr)	\
@@ -621,18 +637,24 @@ ENTRY(name)				\
 	movl %esp,%eax;			\
 	call smp_/**/name;		\
 	jmp ret_from_intr;		\
-	CFI_ENDPROC
+	CFI_ENDPROC;			\
+ENDPROC(name)
 
 /* The include is where all of the SMP etc. interrupts come from */
 #include "entry_arch.h"
 
+/* This alternate entry is needed because we hijack the apic LVTT */
+#if defined(CONFIG_VMI) && defined(CONFIG_X86_LOCAL_APIC)
+BUILD_INTERRUPT(apic_vmi_timer_interrupt,LOCAL_TIMER_VECTOR)
+#endif
+
 KPROBE_ENTRY(page_fault)
 	RING0_EC_FRAME
 	pushl $do_page_fault
 	CFI_ADJUST_CFA_OFFSET 4
 	ALIGN
 error_code:
-	/* the function address is in %gs's slot on the stack */
+	/* the function address is in %fs's slot on the stack */
 	pushl %es
 	CFI_ADJUST_CFA_OFFSET 4
 	/*CFI_REL_OFFSET es, 0*/
@@ -661,20 +683,20 @@ error_code:
 	CFI_ADJUST_CFA_OFFSET 4
 	CFI_REL_OFFSET ebx, 0
 	cld
-	pushl %gs
+	pushl %fs
 	CFI_ADJUST_CFA_OFFSET 4
-	/*CFI_REL_OFFSET gs, 0*/
+	/*CFI_REL_OFFSET fs, 0*/
 	movl $(__KERNEL_PDA), %ecx
-	movl %ecx, %gs
+	movl %ecx, %fs
 	UNWIND_ESPFIX_STACK
 	popl %ecx
 	CFI_ADJUST_CFA_OFFSET -4
 	/*CFI_REGISTER es, ecx*/
-	movl PT_GS(%esp), %edi		# get the function address
+	movl PT_FS(%esp), %edi		# get the function address
 	movl PT_ORIG_EAX(%esp), %edx	# get the error code
 	movl $-1, PT_ORIG_EAX(%esp)	# no syscall to restart
-	mov  %ecx, PT_GS(%esp)
-	/*CFI_REL_OFFSET gs, ES*/
+	mov  %ecx, PT_FS(%esp)
+	/*CFI_REL_OFFSET fs, ES*/
 	movl $(__USER_DS), %ecx
 	movl %ecx, %ds
 	movl %ecx, %es
@@ -692,6 +714,7 @@ ENTRY(coprocessor_error)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(coprocessor_error)
 
 ENTRY(simd_coprocessor_error)
 	RING0_INT_FRAME
@@ -701,6 +724,7 @@ ENTRY(simd_coprocessor_error)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(simd_coprocessor_error)
 
 ENTRY(device_not_available)
 	RING0_INT_FRAME
@@ -721,6 +745,7 @@ device_not_available_emulate:
 	CFI_ADJUST_CFA_OFFSET -4
 	jmp ret_from_exception
 	CFI_ENDPROC
+END(device_not_available)
 
 /*
  * Debug traps and NMI can happen at the one SYSENTER instruction
@@ -864,10 +889,12 @@ ENTRY(native_iret)
 	.align 4
 	.long 1b,iret_exc
 .previous
+END(native_iret)
 
 ENTRY(native_irq_enable_sysexit)
 	sti
 	sysexit
+END(native_irq_enable_sysexit)
 #endif
 
 KPROBE_ENTRY(int3)
@@ -890,6 +917,7 @@ ENTRY(overflow)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(overflow)
 
 ENTRY(bounds)
 	RING0_INT_FRAME
@@ -899,6 +927,7 @@ ENTRY(bounds)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(bounds)
 
 ENTRY(invalid_op)
 	RING0_INT_FRAME
@@ -908,6 +937,7 @@ ENTRY(invalid_op)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(invalid_op)
 
 ENTRY(coprocessor_segment_overrun)
 	RING0_INT_FRAME
@@ -917,6 +947,7 @@ ENTRY(coprocessor_segment_overrun)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(coprocessor_segment_overrun)
 
 ENTRY(invalid_TSS)
 	RING0_EC_FRAME
@@ -924,6 +955,7 @@ ENTRY(invalid_TSS)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(invalid_TSS)
 
 ENTRY(segment_not_present)
 	RING0_EC_FRAME
@@ -931,6 +963,7 @@ ENTRY(segment_not_present)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(segment_not_present)
 
 ENTRY(stack_segment)
 	RING0_EC_FRAME
@@ -938,6 +971,7 @@ ENTRY(stack_segment)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(stack_segment)
 
 KPROBE_ENTRY(general_protection)
 	RING0_EC_FRAME
@@ -953,6 +987,7 @@ ENTRY(alignment_check)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(alignment_check)
 
 ENTRY(divide_error)
 	RING0_INT_FRAME
@@ -962,6 +997,7 @@ ENTRY(divide_error)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(divide_error)
 
 #ifdef CONFIG_X86_MCE
 ENTRY(machine_check)
@@ -972,6 +1008,7 @@ ENTRY(machine_check)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(machine_check)
 #endif
 
 ENTRY(spurious_interrupt_bug)
@@ -982,6 +1019,7 @@ ENTRY(spurious_interrupt_bug)
 	CFI_ADJUST_CFA_OFFSET 4
 	jmp error_code
 	CFI_ENDPROC
+END(spurious_interrupt_bug)
 
 ENTRY(kernel_thread_helper)
 	pushl $0		# fake return address for unwinder

arch/i386/kernel/head.S

@@ -53,6 +53,7 @@
  * any particular GDT layout, because we load our own as soon as we
  * can.
  */
+.section .text.head,"ax",@progbits
 ENTRY(startup_32)
 
 #ifdef CONFIG_PARAVIRT
@@ -141,16 +142,25 @@ page_pde_offset = (__PAGE_OFFSET >> 20);
 	jb 10b
 	movl %edi,(init_pg_tables_end - __PAGE_OFFSET)
 
-#ifdef CONFIG_SMP
 	xorl %ebx,%ebx				/* This is the boot CPU (BSP) */
 	jmp 3f
-
 /*
  * Non-boot CPU entry point; entered from trampoline.S
  * We can't lgdt here, because lgdt itself uses a data segment, but
  * we know the trampoline has already loaded the boot_gdt_table GDT
  * for us.
+ *
+ * If cpu hotplug is not supported then this code can go in init section
+ * which will be freed later
  */
+
+#ifdef CONFIG_HOTPLUG_CPU
+.section .text,"ax",@progbits
+#else
+.section .init.text,"ax",@progbits
+#endif
+
+#ifdef CONFIG_SMP
 ENTRY(startup_32_smp)
 	cld
 	movl $(__BOOT_DS),%eax
@@ -208,8 +218,8 @@ ENTRY(startup_32_smp)
 	xorl %ebx,%ebx
 	incl %ebx
 
-3:
 #endif /* CONFIG_SMP */
+3:
 
 /*
  * Enable paging
@@ -309,7 +319,7 @@ is386:	movl $2,%ecx		# set MP
 
 	call check_x87
 	call setup_pda
-	lgdt cpu_gdt_descr
+	lgdt early_gdt_descr
 	lidt idt_descr
 	ljmp $(__KERNEL_CS),$1f
 1:	movl $(__KERNEL_DS),%eax	# reload all the segment registers
@@ -319,12 +329,12 @@ is386:	movl $2,%ecx		# set MP
 	movl %eax,%ds
 	movl %eax,%es
 
-	xorl %eax,%eax			# Clear FS and LDT
-	movl %eax,%fs
+	xorl %eax,%eax			# Clear GS and LDT
+	movl %eax,%gs
 	lldt %ax
 
 	movl $(__KERNEL_PDA),%eax
-	mov  %eax,%gs
+	mov  %eax,%fs
 
 	cld			# gcc2 wants the direction flag cleared at all times
 	pushl $0		# fake return address for unwinder
@@ -360,12 +370,12 @@ check_x87:
  * cpu_gdt_table and boot_pda; for secondary CPUs, these will be
  * that CPU's GDT and PDA.
  */
-setup_pda:
+ENTRY(setup_pda)
 	/* get the PDA pointer */
 	movl start_pda, %eax
 
 	/* slot the PDA address into the GDT */
-	mov cpu_gdt_descr+2, %ecx
+	mov early_gdt_descr+2, %ecx
 	mov %ax, (__KERNEL_PDA+0+2)(%ecx)		/* base & 0x0000ffff */
 	shr $16, %eax
 	mov %al, (__KERNEL_PDA+4+0)(%ecx)		/* base & 0x00ff0000 */
@@ -492,6 +502,7 @@ ignore_int:
 #endif
 	iret
 
+.section .text
 #ifdef CONFIG_PARAVIRT
 startup_paravirt:
 	cld
@@ -502,10 +513,11 @@ startup_paravirt:
 	pushl	%ecx
 	pushl	%eax
 
-	/* paravirt.o is last in link, and that probe fn never returns */
 	pushl	$__start_paravirtprobe
 1:
 	movl	0(%esp), %eax
+	cmpl	$__stop_paravirtprobe, %eax
+	je	unhandled_paravirt
 	pushl	(%eax)
 	movl	8(%esp), %eax
 	call	*(%esp)
@@ -517,6 +529,10 @@ startup_paravirt:
 
 	addl	$4, (%esp)
 	jmp	1b
+
+unhandled_paravirt:
+	/* Nothing wanted us: we're screwed. */
+	ud2
 #endif
 
 /*
@@ -581,7 +597,7 @@ idt_descr:
 
 # boot GDT descriptor (later on used by CPU#0):
 	.word 0				# 32 bit align gdt_desc.address
-ENTRY(cpu_gdt_descr)
+ENTRY(early_gdt_descr)
 	.word GDT_ENTRIES*8-1
 	.long cpu_gdt_table
 

arch/i386/kernel/hpet.c

@@ -1,4 +1,5 @@
 #include <linux/clocksource.h>
+#include <linux/clockchips.h>
 #include <linux/errno.h>
 #include <linux/hpet.h>
 #include <linux/init.h>
@@ -6,17 +7,278 @@
 #include <asm/hpet.h>
 #include <asm/io.h>
 
+extern struct clock_event_device *global_clock_event;
+
 #define HPET_MASK	CLOCKSOURCE_MASK(32)
 #define HPET_SHIFT	22
 
 /* FSEC = 10^-15 NSEC = 10^-9 */
 #define FSEC_PER_NSEC	1000000
 
-static void __iomem *hpet_ptr;
+/*
+ * HPET address is set in acpi/boot.c, when an ACPI entry exists
+ */
+unsigned long hpet_address;
+static void __iomem * hpet_virt_address;
+
+static inline unsigned long hpet_readl(unsigned long a)
+{
+	return readl(hpet_virt_address + a);
+}
+
+static inline void hpet_writel(unsigned long d, unsigned long a)
+{
+	writel(d, hpet_virt_address + a);
+}
+
+/*
+ * HPET command line enable / disable
+ */
+static int boot_hpet_disable;
+
+static int __init hpet_setup(char* str)
+{
+	if (str) {
+		if (!strncmp("disable", str, 7))
+			boot_hpet_disable = 1;
+	}
+	return 1;
+}
+__setup("hpet=", hpet_setup);
+
+static inline int is_hpet_capable(void)
+{
+	return (!boot_hpet_disable && hpet_address);
+}
+
+/*
+ * HPET timer interrupt enable / disable
+ */
+static int hpet_legacy_int_enabled;
+
+/**
+ * is_hpet_enabled - check whether the hpet timer interrupt is enabled
+ */
+int is_hpet_enabled(void)
+{
+	return is_hpet_capable() && hpet_legacy_int_enabled;
+}
+
+/*
+ * When the hpet driver (/dev/hpet) is enabled, we need to reserve
+ * timer 0 and timer 1 in case of RTC emulation.
+ */
+#ifdef CONFIG_HPET
+static void hpet_reserve_platform_timers(unsigned long id)
+{
+	struct hpet __iomem *hpet = hpet_virt_address;
+	struct hpet_timer __iomem *timer = &hpet->hpet_timers[2];
+	unsigned int nrtimers, i;
+	struct hpet_data hd;
+
+	nrtimers = ((id & HPET_ID_NUMBER) >> HPET_ID_NUMBER_SHIFT) + 1;
+
+	memset(&hd, 0, sizeof (hd));
+	hd.hd_phys_address = hpet_address;
+	hd.hd_address = hpet_virt_address;
+	hd.hd_nirqs = nrtimers;
+	hd.hd_flags = HPET_DATA_PLATFORM;
+	hpet_reserve_timer(&hd, 0);
+
+#ifdef CONFIG_HPET_EMULATE_RTC
+	hpet_reserve_timer(&hd, 1);
+#endif
+
+	hd.hd_irq[0] = HPET_LEGACY_8254;
+	hd.hd_irq[1] = HPET_LEGACY_RTC;
+
+	for (i = 2; i < nrtimers; timer++, i++)
+		hd.hd_irq[i] = (timer->hpet_config & Tn_INT_ROUTE_CNF_MASK) >>
+			Tn_INT_ROUTE_CNF_SHIFT;
+
+	hpet_alloc(&hd);
+
+}
+#else
+static void hpet_reserve_platform_timers(unsigned long id) { }
+#endif
+
+/*
+ * Common hpet info
+ */
+static unsigned long hpet_period;
+
+static void hpet_set_mode(enum clock_event_mode mode,
+			  struct clock_event_device *evt);
+static int hpet_next_event(unsigned long delta,
+			   struct clock_event_device *evt);
+
+/*
+ * The hpet clock event device
+ */
+static struct clock_event_device hpet_clockevent = {
+	.name		= "hpet",
+	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.set_mode	= hpet_set_mode,
+	.set_next_event = hpet_next_event,
+	.shift		= 32,
+	.irq		= 0,
+};
+
+static void hpet_start_counter(void)
+{
+	unsigned long cfg = hpet_readl(HPET_CFG);
+
+	cfg &= ~HPET_CFG_ENABLE;
+	hpet_writel(cfg, HPET_CFG);
+	hpet_writel(0, HPET_COUNTER);
+	hpet_writel(0, HPET_COUNTER + 4);
+	cfg |= HPET_CFG_ENABLE;
+	hpet_writel(cfg, HPET_CFG);
+}
+
+static void hpet_enable_int(void)
+{
+	unsigned long cfg = hpet_readl(HPET_CFG);
+
+	cfg |= HPET_CFG_LEGACY;
+	hpet_writel(cfg, HPET_CFG);
+	hpet_legacy_int_enabled = 1;
+}
+
+static void hpet_set_mode(enum clock_event_mode mode,
+			  struct clock_event_device *evt)
+{
+	unsigned long cfg, cmp, now;
+	uint64_t delta;
+
+	switch(mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		delta = ((uint64_t)(NSEC_PER_SEC/HZ)) * hpet_clockevent.mult;
+		delta >>= hpet_clockevent.shift;
+		now = hpet_readl(HPET_COUNTER);
+		cmp = now + (unsigned long) delta;
+		cfg = hpet_readl(HPET_T0_CFG);
+		cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
+		       HPET_TN_SETVAL | HPET_TN_32BIT;
+		hpet_writel(cfg, HPET_T0_CFG);
+		/*
+		 * The first write after writing TN_SETVAL to the
+		 * config register sets the counter value, the second
+		 * write sets the period.
+		 */
+		hpet_writel(cmp, HPET_T0_CMP);
+		udelay(1);
+		hpet_writel((unsigned long) delta, HPET_T0_CMP);
+		break;
+
+	case CLOCK_EVT_MODE_ONESHOT:
+		cfg = hpet_readl(HPET_T0_CFG);
+		cfg &= ~HPET_TN_PERIODIC;
+		cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
+		hpet_writel(cfg, HPET_T0_CFG);
+		break;
+
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		cfg = hpet_readl(HPET_T0_CFG);
+		cfg &= ~HPET_TN_ENABLE;
+		hpet_writel(cfg, HPET_T0_CFG);
+		break;
+	}
+}
+
+static int hpet_next_event(unsigned long delta,
+			   struct clock_event_device *evt)
+{
+	unsigned long cnt;
+
+	cnt = hpet_readl(HPET_COUNTER);
+	cnt += delta;
+	hpet_writel(cnt, HPET_T0_CMP);
+
+	return ((long)(hpet_readl(HPET_COUNTER) - cnt ) > 0);
+}
+
+/*
+ * Try to setup the HPET timer
+ */
+int __init hpet_enable(void)
+{
+	unsigned long id;
+	uint64_t hpet_freq;
+
+	if (!is_hpet_capable())
+		return 0;
+
+	hpet_virt_address = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
+
+	/*
+	 * Read the period and check for a sane value:
+	 */
+	hpet_period = hpet_readl(HPET_PERIOD);
+	if (hpet_period < HPET_MIN_PERIOD || hpet_period > HPET_MAX_PERIOD)
+		goto out_nohpet;
+
+	/*
+	 * The period is a femto seconds value. We need to calculate the
+	 * scaled math multiplication factor for nanosecond to hpet tick
+	 * conversion.
+	 */
+	hpet_freq = 1000000000000000ULL;
+	do_div(hpet_freq, hpet_period);
+	hpet_clockevent.mult = div_sc((unsigned long) hpet_freq,
+				      NSEC_PER_SEC, 32);
+	/* Calculate the min / max delta */
+	hpet_clockevent.max_delta_ns = clockevent_delta2ns(0x7FFFFFFF,
+							   &hpet_clockevent);
+	hpet_clockevent.min_delta_ns = clockevent_delta2ns(0x30,
+							   &hpet_clockevent);
+
+	/*
+	 * Read the HPET ID register to retrieve the IRQ routing
+	 * information and the number of channels
+	 */
+	id = hpet_readl(HPET_ID);
+
+#ifdef CONFIG_HPET_EMULATE_RTC
+	/*
+	 * The legacy routing mode needs at least two channels, tick timer
+	 * and the rtc emulation channel.
+	 */
+	if (!(id & HPET_ID_NUMBER))
+		goto out_nohpet;
+#endif
+
+	/* Start the counter */
+	hpet_start_counter();
+
+	if (id & HPET_ID_LEGSUP) {
+		hpet_enable_int();
+		hpet_reserve_platform_timers(id);
+		/*
+		 * Start hpet with the boot cpu mask and make it
+		 * global after the IO_APIC has been initialized.
+		 */
+		hpet_clockevent.cpumask =cpumask_of_cpu(0);
+		clockevents_register_device(&hpet_clockevent);
+		global_clock_event = &hpet_clockevent;
+		return 1;
+	}
+	return 0;
 
+out_nohpet:
+	iounmap(hpet_virt_address);
+	hpet_virt_address = NULL;
+	return 0;
+}
+
+/*
+ * Clock source related code
+ */
 static cycle_t read_hpet(void)
 {
-	return (cycle_t)readl(hpet_ptr);
+	return (cycle_t)hpet_readl(HPET_COUNTER);
 }
 
 static struct clocksource clocksource_hpet = {
@@ -24,28 +286,17 @@ static struct clocksource clocksource_hpet = {
 	.rating		= 250,
 	.read		= read_hpet,
 	.mask		= HPET_MASK,
-	.mult		= 0, /* set below */
 	.shift		= HPET_SHIFT,
-	.is_continuous	= 1,
+	.flags		= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
 static int __init init_hpet_clocksource(void)
 {
-	unsigned long hpet_period;
-	void __iomem* hpet_base;
 	u64 tmp;
-	int err;
 
-	if (!is_hpet_enabled())
+	if (!hpet_virt_address)
 		return -ENODEV;
 
-	/* calculate the hpet address: */
-	hpet_base = ioremap_nocache(hpet_address, HPET_MMAP_SIZE);
-	hpet_ptr = hpet_base + HPET_COUNTER;
-
-	/* calculate the frequency: */
-	hpet_period = readl(hpet_base + HPET_PERIOD);
-
 	/*
 	 * hpet period is in femto seconds per cycle
 	 * so we need to convert this to ns/cyc units
@@ -61,11 +312,218 @@ static int __init init_hpet_clocksource(void)
 	do_div(tmp, FSEC_PER_NSEC);
 	clocksource_hpet.mult = (u32)tmp;
 
-	err = clocksource_register(&clocksource_hpet);
-	if (err)
-		iounmap(hpet_base);
-
-	return err;
+	return clocksource_register(&clocksource_hpet);
 }
 
 module_init(init_hpet_clocksource);
+
+#ifdef CONFIG_HPET_EMULATE_RTC
+
+/* HPET in LegacyReplacement Mode eats up RTC interrupt line. When, HPET
+ * is enabled, we support RTC interrupt functionality in software.
+ * RTC has 3 kinds of interrupts:
+ * 1) Update Interrupt - generate an interrupt, every sec, when RTC clock
+ *    is updated
+ * 2) Alarm Interrupt - generate an interrupt at a specific time of day
+ * 3) Periodic Interrupt - generate periodic interrupt, with frequencies
+ *    2Hz-8192Hz (2Hz-64Hz for non-root user) (all freqs in powers of 2)
+ * (1) and (2) above are implemented using polling at a frequency of
+ * 64 Hz. The exact frequency is a tradeoff between accuracy and interrupt
+ * overhead. (DEFAULT_RTC_INT_FREQ)
+ * For (3), we use interrupts at 64Hz or user specified periodic
+ * frequency, whichever is higher.
+ */
+#include <linux/mc146818rtc.h>
+#include <linux/rtc.h>
+
+#define DEFAULT_RTC_INT_FREQ	64
+#define DEFAULT_RTC_SHIFT	6
+#define RTC_NUM_INTS		1
+
+static unsigned long hpet_rtc_flags;
+static unsigned long hpet_prev_update_sec;
+static struct rtc_time hpet_alarm_time;
+static unsigned long hpet_pie_count;
+static unsigned long hpet_t1_cmp;
+static unsigned long hpet_default_delta;
+static unsigned long hpet_pie_delta;
+static unsigned long hpet_pie_limit;
+
+/*
+ * Timer 1 for RTC emulation. We use one shot mode, as periodic mode
+ * is not supported by all HPET implementations for timer 1.
+ *
+ * hpet_rtc_timer_init() is called when the rtc is initialized.
+ */
+int hpet_rtc_timer_init(void)
+{
+	unsigned long cfg, cnt, delta, flags;
+
+	if (!is_hpet_enabled())
+		return 0;
+
+	if (!hpet_default_delta) {
+		uint64_t clc;
+
+		clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC;
+		clc >>= hpet_clockevent.shift + DEFAULT_RTC_SHIFT;
+		hpet_default_delta = (unsigned long) clc;
+	}
+
+	if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit)
+		delta = hpet_default_delta;
+	else
+		delta = hpet_pie_delta;
+
+	local_irq_save(flags);
+
+	cnt = delta + hpet_readl(HPET_COUNTER);
+	hpet_writel(cnt, HPET_T1_CMP);
+	hpet_t1_cmp = cnt;
+
+	cfg = hpet_readl(HPET_T1_CFG);
+	cfg &= ~HPET_TN_PERIODIC;
+	cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
+	hpet_writel(cfg, HPET_T1_CFG);
+
+	local_irq_restore(flags);
+
+	return 1;
+}
+
+/*
+ * The functions below are called from rtc driver.
+ * Return 0 if HPET is not being used.
+ * Otherwise do the necessary changes and return 1.
+ */
+int hpet_mask_rtc_irq_bit(unsigned long bit_mask)
+{
+	if (!is_hpet_enabled())
+		return 0;
+
+	hpet_rtc_flags &= ~bit_mask;
+	return 1;
+}
+
+int hpet_set_rtc_irq_bit(unsigned long bit_mask)
+{
+	unsigned long oldbits = hpet_rtc_flags;
+
+	if (!is_hpet_enabled())
+		return 0;
+
+	hpet_rtc_flags |= bit_mask;
+
+	if (!oldbits)
+		hpet_rtc_timer_init();
+
+	return 1;
+}
+
+int hpet_set_alarm_time(unsigned char hrs, unsigned char min,
+			unsigned char sec)
+{
+	if (!is_hpet_enabled())
+		return 0;
+
+	hpet_alarm_time.tm_hour = hrs;
+	hpet_alarm_time.tm_min = min;
+	hpet_alarm_time.tm_sec = sec;
+
+	return 1;
+}
+
+int hpet_set_periodic_freq(unsigned long freq)
+{
+	uint64_t clc;
+
+	if (!is_hpet_enabled())
+		return 0;
+
+	if (freq <= DEFAULT_RTC_INT_FREQ)
+		hpet_pie_limit = DEFAULT_RTC_INT_FREQ / freq;
+	else {
+		clc = (uint64_t) hpet_clockevent.mult * NSEC_PER_SEC;
+		do_div(clc, freq);
+		clc >>= hpet_clockevent.shift;
+		hpet_pie_delta = (unsigned long) clc;
+	}
+	return 1;
+}
+
+int hpet_rtc_dropped_irq(void)
+{
+	return is_hpet_enabled();
+}
+
+static void hpet_rtc_timer_reinit(void)
+{
+	unsigned long cfg, delta;
+	int lost_ints = -1;
+
+	if (unlikely(!hpet_rtc_flags)) {
+		cfg = hpet_readl(HPET_T1_CFG);
+		cfg &= ~HPET_TN_ENABLE;
+		hpet_writel(cfg, HPET_T1_CFG);
+		return;
+	}
+
+	if (!(hpet_rtc_flags & RTC_PIE) || hpet_pie_limit)
+		delta = hpet_default_delta;
+	else
+		delta = hpet_pie_delta;
+
+	/*
+	 * Increment the comparator value until we are ahead of the
+	 * current count.
+	 */
+	do {
+		hpet_t1_cmp += delta;
+		hpet_writel(hpet_t1_cmp, HPET_T1_CMP);
+		lost_ints++;
+	} while ((long)(hpet_readl(HPET_COUNTER) - hpet_t1_cmp) > 0);
+
+	if (lost_ints) {
+		if (hpet_rtc_flags & RTC_PIE)
+			hpet_pie_count += lost_ints;
+		if (printk_ratelimit())
+			printk(KERN_WARNING "rtc: lost %d interrupts\n",
+				lost_ints);
+	}
+}
+
+irqreturn_t hpet_rtc_interrupt(int irq, void *dev_id)
+{
+	struct rtc_time curr_time;
+	unsigned long rtc_int_flag = 0;
+
+	hpet_rtc_timer_reinit();
+
+	if (hpet_rtc_flags & (RTC_UIE | RTC_AIE))
+		rtc_get_rtc_time(&curr_time);
+
+	if (hpet_rtc_flags & RTC_UIE &&
+	    curr_time.tm_sec != hpet_prev_update_sec) {
+		rtc_int_flag = RTC_UF;
+		hpet_prev_update_sec = curr_time.tm_sec;
+	}
+
+	if (hpet_rtc_flags & RTC_PIE &&
+	    ++hpet_pie_count >= hpet_pie_limit) {
+		rtc_int_flag |= RTC_PF;
+		hpet_pie_count = 0;
+	}
+
+	if (hpet_rtc_flags & RTC_PIE &&
+	    (curr_time.tm_sec == hpet_alarm_time.tm_sec) &&
+	    (curr_time.tm_min == hpet_alarm_time.tm_min) &&
+	    (curr_time.tm_hour == hpet_alarm_time.tm_hour))
+			rtc_int_flag |= RTC_AF;
+
+	if (rtc_int_flag) {
+		rtc_int_flag |= (RTC_IRQF | (RTC_NUM_INTS << 8));
+		rtc_interrupt(rtc_int_flag, dev_id);
+	}
+	return IRQ_HANDLED;
+}
+#endif

arch/i386/kernel/i8253.c

@@ -2,7 +2,7 @@
  * i8253.c  8253/PIT functions
  *
  */
-#include <linux/clocksource.h>
+#include <linux/clockchips.h>
 #include <linux/spinlock.h>
 #include <linux/jiffies.h>
 #include <linux/sysdev.h>
@@ -19,17 +19,97 @@
 DEFINE_SPINLOCK(i8253_lock);
 EXPORT_SYMBOL(i8253_lock);
 
-void setup_pit_timer(void)
+/*
+ * HPET replaces the PIT, when enabled. So we need to know, which of
+ * the two timers is used
+ */
+struct clock_event_device *global_clock_event;
+
+/*
+ * Initialize the PIT timer.
+ *
+ * This is also called after resume to bring the PIT into operation again.
+ */
+static void init_pit_timer(enum clock_event_mode mode,
+			   struct clock_event_device *evt)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&i8253_lock, flags);
+
+	switch(mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		/* binary, mode 2, LSB/MSB, ch 0 */
+		outb_p(0x34, PIT_MODE);
+		udelay(10);
+		outb_p(LATCH & 0xff , PIT_CH0);	/* LSB */
+		udelay(10);
+		outb(LATCH >> 8 , PIT_CH0);	/* MSB */
+		break;
+
+	case CLOCK_EVT_MODE_ONESHOT:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	case CLOCK_EVT_MODE_UNUSED:
+		/* One shot setup */
+		outb_p(0x38, PIT_MODE);
+		udelay(10);
+		break;
+	}
+	spin_unlock_irqrestore(&i8253_lock, flags);
+}
+
+/*
+ * Program the next event in oneshot mode
+ *
+ * Delta is given in PIT ticks
+ */
+static int pit_next_event(unsigned long delta, struct clock_event_device *evt)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&i8253_lock, flags);
-	outb_p(0x34,PIT_MODE);		/* binary, mode 2, LSB/MSB, ch 0 */
-	udelay(10);
-	outb_p(LATCH & 0xff , PIT_CH0);	/* LSB */
-	udelay(10);
-	outb(LATCH >> 8 , PIT_CH0);	/* MSB */
+	outb_p(delta & 0xff , PIT_CH0);	/* LSB */
+	outb(delta >> 8 , PIT_CH0);	/* MSB */
 	spin_unlock_irqrestore(&i8253_lock, flags);
+
+	return 0;
+}
+
+/*
+ * On UP the PIT can serve all of the possible timer functions. On SMP systems
+ * it can be solely used for the global tick.
+ *
+ * The profiling and update capabilites are switched off once the local apic is
+ * registered. This mechanism replaces the previous #ifdef LOCAL_APIC -
+ * !using_apic_timer decisions in do_timer_interrupt_hook()
+ */
+struct clock_event_device pit_clockevent = {
+	.name		= "pit",
+	.features	= CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT,
+	.set_mode	= init_pit_timer,
+	.set_next_event = pit_next_event,
+	.shift		= 32,
+	.irq		= 0,
+};
+
+/*
+ * Initialize the conversion factor and the min/max deltas of the clock event
+ * structure and register the clock event source with the framework.
+ */
+void __init setup_pit_timer(void)
+{
+	/*
+	 * Start pit with the boot cpu mask and make it global after the
+	 * IO_APIC has been initialized.
+	 */
+	pit_clockevent.cpumask = cpumask_of_cpu(0);
+	pit_clockevent.mult = div_sc(CLOCK_TICK_RATE, NSEC_PER_SEC, 32);
+	pit_clockevent.max_delta_ns =
+		clockevent_delta2ns(0x7FFF, &pit_clockevent);
+	pit_clockevent.min_delta_ns =
+		clockevent_delta2ns(0xF, &pit_clockevent);
+	clockevents_register_device(&pit_clockevent);
+	global_clock_event = &pit_clockevent;
 }
 
 /*
@@ -46,7 +126,7 @@ static cycle_t pit_read(void)
 	static u32 old_jifs;
 
 	spin_lock_irqsave(&i8253_lock, flags);
-        /*
+	/*
 	 * Although our caller may have the read side of xtime_lock,
 	 * this is now a seqlock, and we are cheating in this routine
 	 * by having side effects on state that we cannot undo if

arch/i386/kernel/i8259.c

@@ -41,6 +41,7 @@ static void mask_and_ack_8259A(unsigned int);
 static struct irq_chip i8259A_chip = {
 	.name		= "XT-PIC",
 	.mask		= disable_8259A_irq,
+	.disable	= disable_8259A_irq,
 	.unmask		= enable_8259A_irq,
 	.mask_ack	= mask_and_ack_8259A,
 };
@@ -409,12 +410,6 @@ void __init native_init_IRQ(void)
 	 */
 	intr_init_hook();
 
-	/*
-	 * Set the clock to HZ Hz, we already have a valid
-	 * vector now:
-	 */
-	setup_pit_timer();
-
 	/*
 	 * External FPU? Set up irq13 if so, for
 	 * original braindamaged IBM FERR coupling.

arch/i386/kernel/io_apic.c

@@ -482,8 +482,8 @@ static void do_irq_balance(void)
 		package_index = CPU_TO_PACKAGEINDEX(i);
 		for (j = 0; j < NR_IRQS; j++) {
 			unsigned long value_now, delta;
-			/* Is this an active IRQ? */
-			if (!irq_desc[j].action)
+			/* Is this an active IRQ or balancing disabled ? */
+			if (!irq_desc[j].action || irq_balancing_disabled(j))
 				continue;
 			if ( package_index == i )
 				IRQ_DELTA(package_index,j) = 0;
@@ -1281,11 +1281,9 @@ static void ioapic_register_intr(int irq, int vector, unsigned long trigger)
 			trigger == IOAPIC_LEVEL)
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
 					 handle_fasteoi_irq, "fasteoi");
-	else {
-		irq_desc[irq].status |= IRQ_DELAYED_DISABLE;
+	else
 		set_irq_chip_and_handler_name(irq, &ioapic_chip,
 					 handle_edge_irq, "edge");
-	}
 	set_intr_gate(vector, interrupt[irq]);
 }
 
@@ -1588,7 +1586,7 @@ void /*__init*/ print_local_APIC(void * dummy)
 	v = apic_read(APIC_LVR);
 	printk(KERN_INFO "... APIC VERSION: %08x\n", v);
 	ver = GET_APIC_VERSION(v);
-	maxlvt = get_maxlvt();
+	maxlvt = lapic_get_maxlvt();
 
 	v = apic_read(APIC_TASKPRI);
 	printk(KERN_DEBUG "... APIC TASKPRI: %08x (%02x)\n", v, v & APIC_TPRI_MASK);
@@ -1920,7 +1918,7 @@ static void __init setup_ioapic_ids_from_mpc(void)
 static void __init setup_ioapic_ids_from_mpc(void) { }
 #endif
 
-static int no_timer_check __initdata;
+int no_timer_check __initdata;
 
 static int __init notimercheck(char *s)
 {
@@ -2310,7 +2308,7 @@ static inline void __init check_timer(void)
 
 	disable_8259A_irq(0);
 	set_irq_chip_and_handler_name(0, &lapic_chip, handle_fasteoi_irq,
-				      "fasteio");
+				      "fasteoi");
 	apic_write_around(APIC_LVT0, APIC_DM_FIXED | vector);	/* Fixed mode */
 	enable_8259A_irq(0);
 

arch/i386/kernel/irq.c

@@ -10,7 +10,6 @@
  * io_apic.c.)
  */
 
-#include <asm/uaccess.h>
 #include <linux/module.h>
 #include <linux/seq_file.h>
 #include <linux/interrupt.h>
@@ -19,19 +18,36 @@
 #include <linux/cpu.h>
 #include <linux/delay.h>
 
+#include <asm/idle.h>
+
+#include <asm/apic.h>
+#include <asm/uaccess.h>
+
 DEFINE_PER_CPU(irq_cpustat_t, irq_stat) ____cacheline_internodealigned_in_smp;
 EXPORT_PER_CPU_SYMBOL(irq_stat);
 
-#ifndef CONFIG_X86_LOCAL_APIC
 /*
  * 'what should we do if we get a hw irq event on an illegal vector'.
  * each architecture has to answer this themselves.
  */
 void ack_bad_irq(unsigned int irq)
 {
-	printk("unexpected IRQ trap at vector %02x\n", irq);
-}
+	printk(KERN_ERR "unexpected IRQ trap at vector %02x\n", irq);
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	/*
+	 * Currently unexpected vectors happen only on SMP and APIC.
+	 * We _must_ ack these because every local APIC has only N
+	 * irq slots per priority level, and a 'hanging, unacked' IRQ
+	 * holds up an irq slot - in excessive cases (when multiple
+	 * unexpected vectors occur) that might lock up the APIC
+	 * completely.
+	 * But only ack when the APIC is enabled -AK
+	 */
+	if (cpu_has_apic)
+		ack_APIC_irq();
 #endif
+}
 
 #ifdef CONFIG_4KSTACKS
 /*
@@ -61,6 +77,7 @@ fastcall unsigned int do_IRQ(struct pt_regs *regs)
 	union irq_ctx *curctx, *irqctx;
 	u32 *isp;
 #endif
+	exit_idle();
 
 	if (unlikely((unsigned)irq >= NR_IRQS)) {
 		printk(KERN_EMERG "%s: cannot handle IRQ %d\n",

arch/i386/kernel/kprobes.c

@@ -363,7 +363,7 @@ no_kprobe:
 			"	pushf\n"
 			/* skip cs, eip, orig_eax */
 			"	subl $12, %esp\n"
-			"	pushl %gs\n"
+			"	pushl %fs\n"
 			"	pushl %ds\n"
 			"	pushl %es\n"
 			"	pushl %eax\n"
@@ -387,7 +387,7 @@ no_kprobe:
 			"	popl %edi\n"
 			"	popl %ebp\n"
 			"	popl %eax\n"
-			/* skip eip, orig_eax, es, ds, gs */
+			/* skip eip, orig_eax, es, ds, fs */
 			"	addl $20, %esp\n"
 			"	popf\n"
 			"	ret\n");
@@ -408,7 +408,7 @@ fastcall void *__kprobes trampoline_handler(struct pt_regs *regs)
 	spin_lock_irqsave(&kretprobe_lock, flags);
 	head = kretprobe_inst_table_head(current);
 	/* fixup registers */
-	regs->xcs = __KERNEL_CS;
+	regs->xcs = __KERNEL_CS | get_kernel_rpl();
 	regs->eip = trampoline_address;
 	regs->orig_eax = 0xffffffff;
 

arch/i386/kernel/microcode.c

@@ -384,7 +384,7 @@ static int do_microcode_update (void)
 {
 	long cursor = 0;
 	int error = 0;
-	void *new_mc;
+	void *new_mc = NULL;
 	int cpu;
 	cpumask_t old;
 

arch/i386/kernel/msr.c

@@ -68,7 +68,6 @@ static inline int rdmsr_eio(u32 reg, u32 *eax, u32 *edx)
 #ifdef CONFIG_SMP
 
 struct msr_command {
-	int cpu;
 	int err;
 	u32 reg;
 	u32 data[2];
@@ -78,16 +77,14 @@ static void msr_smp_wrmsr(void *cmd_block)
 {
 	struct msr_command *cmd = (struct msr_command *)cmd_block;
 
-	if (cmd->cpu == smp_processor_id())
-		cmd->err = wrmsr_eio(cmd->reg, cmd->data[0], cmd->data[1]);
+	cmd->err = wrmsr_eio(cmd->reg, cmd->data[0], cmd->data[1]);
 }
 
 static void msr_smp_rdmsr(void *cmd_block)
 {
 	struct msr_command *cmd = (struct msr_command *)cmd_block;
 
-	if (cmd->cpu == smp_processor_id())
-		cmd->err = rdmsr_eio(cmd->reg, &cmd->data[0], &cmd->data[1]);
+	cmd->err = rdmsr_eio(cmd->reg, &cmd->data[0], &cmd->data[1]);
 }
 
 static inline int do_wrmsr(int cpu, u32 reg, u32 eax, u32 edx)
@@ -99,12 +96,11 @@ static inline int do_wrmsr(int cpu, u32 reg, u32 eax, u32 edx)
 	if (cpu == smp_processor_id()) {
 		ret = wrmsr_eio(reg, eax, edx);
 	} else {
-		cmd.cpu = cpu;
 		cmd.reg = reg;
 		cmd.data[0] = eax;
 		cmd.data[1] = edx;
 
-		smp_call_function(msr_smp_wrmsr, &cmd, 1, 1);
+		smp_call_function_single(cpu, msr_smp_wrmsr, &cmd, 1, 1);
 		ret = cmd.err;
 	}
 	preempt_enable();
@@ -120,10 +116,9 @@ static inline int do_rdmsr(int cpu, u32 reg, u32 * eax, u32 * edx)
 	if (cpu == smp_processor_id()) {
 		ret = rdmsr_eio(reg, eax, edx);
 	} else {
-		cmd.cpu = cpu;
 		cmd.reg = reg;
 
-		smp_call_function(msr_smp_rdmsr, &cmd, 1, 1);
+		smp_call_function_single(cpu, msr_smp_rdmsr, &cmd, 1, 1);
 
 		*eax = cmd.data[0];
 		*edx = cmd.data[1];

arch/i386/kernel/nmi.c

@@ -23,6 +23,7 @@
 #include <linux/dmi.h>
 #include <linux/kprobes.h>
 #include <linux/cpumask.h>
+#include <linux/kernel_stat.h>
 
 #include <asm/smp.h>
 #include <asm/nmi.h>
@@ -185,7 +186,8 @@ static __cpuinit inline int nmi_known_cpu(void)
 {
 	switch (boot_cpu_data.x86_vendor) {
 	case X86_VENDOR_AMD:
-		return ((boot_cpu_data.x86 == 15) || (boot_cpu_data.x86 == 6));
+		return ((boot_cpu_data.x86 == 15) || (boot_cpu_data.x86 == 6)
+			|| (boot_cpu_data.x86 == 16));
 	case X86_VENDOR_INTEL:
 		if (cpu_has(&boot_cpu_data, X86_FEATURE_ARCH_PERFMON))
 			return 1;
@@ -216,6 +218,28 @@ static __init void nmi_cpu_busy(void *data)
 }
 #endif
 
+static unsigned int adjust_for_32bit_ctr(unsigned int hz)
+{
+	u64 counter_val;
+	unsigned int retval = hz;
+
+	/*
+	 * On Intel CPUs with P6/ARCH_PERFMON only 32 bits in the counter
+	 * are writable, with higher bits sign extending from bit 31.
+	 * So, we can only program the counter with 31 bit values and
+	 * 32nd bit should be 1, for 33.. to be 1.
+	 * Find the appropriate nmi_hz
+	 */
+	counter_val = (u64)cpu_khz * 1000;
+	do_div(counter_val, retval);
+ 	if (counter_val > 0x7fffffffULL) {
+		u64 count = (u64)cpu_khz * 1000;
+		do_div(count, 0x7fffffffUL);
+		retval = count + 1;
+	}
+	return retval;
+}
+
 static int __init check_nmi_watchdog(void)
 {
 	unsigned int *prev_nmi_count;
@@ -281,18 +305,10 @@ static int __init check_nmi_watchdog(void)
 		struct nmi_watchdog_ctlblk *wd = &__get_cpu_var(nmi_watchdog_ctlblk);
 
 		nmi_hz = 1;
-		/*
-		 * On Intel CPUs with ARCH_PERFMON only 32 bits in the counter
-		 * are writable, with higher bits sign extending from bit 31.
-		 * So, we can only program the counter with 31 bit values and
-		 * 32nd bit should be 1, for 33.. to be 1.
-		 * Find the appropriate nmi_hz
-		 */
-	 	if (wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0 &&
-			((u64)cpu_khz * 1000) > 0x7fffffffULL) {
-			u64 count = (u64)cpu_khz * 1000;
-			do_div(count, 0x7fffffffUL);
-			nmi_hz = count + 1;
+
+		if (wd->perfctr_msr == MSR_P6_PERFCTR0 ||
+		    wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
+			nmi_hz = adjust_for_32bit_ctr(nmi_hz);
 		}
 	}
 
@@ -369,6 +385,34 @@ void enable_timer_nmi_watchdog(void)
 	}
 }
 
+static void __acpi_nmi_disable(void *__unused)
+{
+	apic_write_around(APIC_LVT0, APIC_DM_NMI | APIC_LVT_MASKED);
+}
+
+/*
+ * Disable timer based NMIs on all CPUs:
+ */
+void acpi_nmi_disable(void)
+{
+	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
+		on_each_cpu(__acpi_nmi_disable, NULL, 0, 1);
+}
+
+static void __acpi_nmi_enable(void *__unused)
+{
+	apic_write_around(APIC_LVT0, APIC_DM_NMI);
+}
+
+/*
+ * Enable timer based NMIs on all CPUs:
+ */
+void acpi_nmi_enable(void)
+{
+	if (atomic_read(&nmi_active) && nmi_watchdog == NMI_IO_APIC)
+		on_each_cpu(__acpi_nmi_enable, NULL, 0, 1);
+}
+
 #ifdef CONFIG_PM
 
 static int nmi_pm_active; /* nmi_active before suspend */
@@ -442,6 +486,17 @@ static void write_watchdog_counter(unsigned int perfctr_msr, const char *descr)
 	wrmsrl(perfctr_msr, 0 - count);
 }
 
+static void write_watchdog_counter32(unsigned int perfctr_msr,
+		const char *descr)
+{
+	u64 count = (u64)cpu_khz * 1000;
+
+	do_div(count, nmi_hz);
+	if(descr)
+		Dprintk("setting %s to -0x%08Lx\n", descr, count);
+	wrmsr(perfctr_msr, (u32)(-count), 0);
+}
+
 /* Note that these events don't tick when the CPU idles. This means
    the frequency varies with CPU load. */
 
@@ -531,7 +586,8 @@ static int setup_p6_watchdog(void)
 
 	/* setup the timer */
 	wrmsr(evntsel_msr, evntsel, 0);
-	write_watchdog_counter(perfctr_msr, "P6_PERFCTR0");
+	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
+	write_watchdog_counter32(perfctr_msr, "P6_PERFCTR0");
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 	evntsel |= P6_EVNTSEL0_ENABLE;
 	wrmsr(evntsel_msr, evntsel, 0);
@@ -704,7 +760,8 @@ static int setup_intel_arch_watchdog(void)
 
 	/* setup the timer */
 	wrmsr(evntsel_msr, evntsel, 0);
-	write_watchdog_counter(perfctr_msr, "INTEL_ARCH_PERFCTR0");
+	nmi_hz = adjust_for_32bit_ctr(nmi_hz);
+	write_watchdog_counter32(perfctr_msr, "INTEL_ARCH_PERFCTR0");
 	apic_write(APIC_LVTPC, APIC_DM_NMI);
 	evntsel |= ARCH_PERFMON_EVENTSEL0_ENABLE;
 	wrmsr(evntsel_msr, evntsel, 0);
@@ -762,7 +819,8 @@ void setup_apic_nmi_watchdog (void *unused)
 	if (nmi_watchdog == NMI_LOCAL_APIC) {
 		switch (boot_cpu_data.x86_vendor) {
 		case X86_VENDOR_AMD:
-			if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15)
+			if (boot_cpu_data.x86 != 6 && boot_cpu_data.x86 != 15 &&
+				boot_cpu_data.x86 != 16)
 				return;
 			if (!setup_k7_watchdog())
 				return;
@@ -916,9 +974,13 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 		cpu_clear(cpu, backtrace_mask);
 	}
 
-	sum = per_cpu(irq_stat, cpu).apic_timer_irqs;
+	/*
+	 * Take the local apic timer and PIT/HPET into account. We don't
+	 * know which one is active, when we have highres/dyntick on
+	 */
+	sum = per_cpu(irq_stat, cpu).apic_timer_irqs + kstat_irqs(0);
 
-	/* if the apic timer isn't firing, this cpu isn't doing much */
+	/* if the none of the timers isn't firing, this cpu isn't doing much */
 	if (!touched && last_irq_sums[cpu] == sum) {
 		/*
 		 * Ayiee, looks like this CPU is stuck ...
@@ -956,6 +1018,8 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 				dummy &= ~P4_CCCR_OVF;
 	 			wrmsrl(wd->cccr_msr, dummy);
 	 			apic_write(APIC_LVTPC, APIC_DM_NMI);
+				/* start the cycle over again */
+				write_watchdog_counter(wd->perfctr_msr, NULL);
 	 		}
 			else if (wd->perfctr_msr == MSR_P6_PERFCTR0 ||
 				 wd->perfctr_msr == MSR_ARCH_PERFMON_PERFCTR0) {
@@ -964,9 +1028,12 @@ __kprobes int nmi_watchdog_tick(struct pt_regs * regs, unsigned reason)
 				 * other P6 variant.
 				 * ArchPerfom/Core Duo also needs this */
 				apic_write(APIC_LVTPC, APIC_DM_NMI);
+				/* P6/ARCH_PERFMON has 32 bit counter write */
+				write_watchdog_counter32(wd->perfctr_msr, NULL);
+			} else {
+				/* start the cycle over again */
+				write_watchdog_counter(wd->perfctr_msr, NULL);
 			}
-			/* start the cycle over again */
-			write_watchdog_counter(wd->perfctr_msr, NULL);
 			rc = 1;
 		} else if (nmi_watchdog == NMI_IO_APIC) {
 			/* don't know how to accurately check for this.

arch/i386/kernel/paravirt.c

@@ -92,7 +92,7 @@ static unsigned native_patch(u8 type, u16 clobbers, void *insns, unsigned len)
 	return insn_len;
 }
 
-static fastcall unsigned long native_get_debugreg(int regno)
+static unsigned long native_get_debugreg(int regno)
 {
 	unsigned long val = 0; 	/* Damn you, gcc! */
 
@@ -115,7 +115,7 @@ static fastcall unsigned long native_get_debugreg(int regno)
 	return val;
 }
 
-static fastcall void native_set_debugreg(int regno, unsigned long value)
+static void native_set_debugreg(int regno, unsigned long value)
 {
 	switch (regno) {
 	case 0:
@@ -146,55 +146,55 @@ void init_IRQ(void)
 	paravirt_ops.init_IRQ();
 }
 
-static fastcall void native_clts(void)
+static void native_clts(void)
 {
 	asm volatile ("clts");
 }
 
-static fastcall unsigned long native_read_cr0(void)
+static unsigned long native_read_cr0(void)
 {
 	unsigned long val;
 	asm volatile("movl %%cr0,%0\n\t" :"=r" (val));
 	return val;
 }
 
-static fastcall void native_write_cr0(unsigned long val)
+static void native_write_cr0(unsigned long val)
 {
 	asm volatile("movl %0,%%cr0": :"r" (val));
 }
 
-static fastcall unsigned long native_read_cr2(void)
+static unsigned long native_read_cr2(void)
 {
 	unsigned long val;
 	asm volatile("movl %%cr2,%0\n\t" :"=r" (val));
 	return val;
 }
 
-static fastcall void native_write_cr2(unsigned long val)
+static void native_write_cr2(unsigned long val)
 {
 	asm volatile("movl %0,%%cr2": :"r" (val));
 }
 
-static fastcall unsigned long native_read_cr3(void)
+static unsigned long native_read_cr3(void)
 {
 	unsigned long val;
 	asm volatile("movl %%cr3,%0\n\t" :"=r" (val));
 	return val;
 }
 
-static fastcall void native_write_cr3(unsigned long val)
+static void native_write_cr3(unsigned long val)
 {
 	asm volatile("movl %0,%%cr3": :"r" (val));
 }
 
-static fastcall unsigned long native_read_cr4(void)
+static unsigned long native_read_cr4(void)
 {
 	unsigned long val;
 	asm volatile("movl %%cr4,%0\n\t" :"=r" (val));
 	return val;
 }
 
-static fastcall unsigned long native_read_cr4_safe(void)
+static unsigned long native_read_cr4_safe(void)
 {
 	unsigned long val;
 	/* This could fault if %cr4 does not exist */
@@ -207,51 +207,51 @@ static fastcall unsigned long native_read_cr4_safe(void)
 	return val;
 }
 
-static fastcall void native_write_cr4(unsigned long val)
+static void native_write_cr4(unsigned long val)
 {
 	asm volatile("movl %0,%%cr4": :"r" (val));
 }
 
-static fastcall unsigned long native_save_fl(void)
+static unsigned long native_save_fl(void)
 {
 	unsigned long f;
 	asm volatile("pushfl ; popl %0":"=g" (f): /* no input */);
 	return f;
 }
 
-static fastcall void native_restore_fl(unsigned long f)
+static void native_restore_fl(unsigned long f)
 {
 	asm volatile("pushl %0 ; popfl": /* no output */
 			     :"g" (f)
 			     :"memory", "cc");
 }
 
-static fastcall void native_irq_disable(void)
+static void native_irq_disable(void)
 {
 	asm volatile("cli": : :"memory");
 }
 
-static fastcall void native_irq_enable(void)
+static void native_irq_enable(void)
 {
 	asm volatile("sti": : :"memory");
 }
 
-static fastcall void native_safe_halt(void)
+static void native_safe_halt(void)
 {
 	asm volatile("sti; hlt": : :"memory");
 }
 
-static fastcall void native_halt(void)
+static void native_halt(void)
 {
 	asm volatile("hlt": : :"memory");
 }
 
-static fastcall void native_wbinvd(void)
+static void native_wbinvd(void)
 {
 	asm volatile("wbinvd": : :"memory");
 }
 
-static fastcall unsigned long long native_read_msr(unsigned int msr, int *err)
+static unsigned long long native_read_msr(unsigned int msr, int *err)
 {
 	unsigned long long val;
 
@@ -270,7 +270,7 @@ static fastcall unsigned long long native_read_msr(unsigned int msr, int *err)
 	return val;
 }
 
-static fastcall int native_write_msr(unsigned int msr, unsigned long long val)
+static int native_write_msr(unsigned int msr, unsigned long long val)
 {
 	int err;
 	asm volatile("2: wrmsr ; xorl %0,%0\n"
@@ -288,53 +288,53 @@ static fastcall int native_write_msr(unsigned int msr, unsigned long long val)
 	return err;
 }
 
-static fastcall unsigned long long native_read_tsc(void)
+static unsigned long long native_read_tsc(void)
 {
 	unsigned long long val;
 	asm volatile("rdtsc" : "=A" (val));
 	return val;
 }
 
-static fastcall unsigned long long native_read_pmc(void)
+static unsigned long long native_read_pmc(void)
 {
 	unsigned long long val;
 	asm volatile("rdpmc" : "=A" (val));
 	return val;
 }
 
-static fastcall void native_load_tr_desc(void)
+static void native_load_tr_desc(void)
 {
 	asm volatile("ltr %w0"::"q" (GDT_ENTRY_TSS*8));
 }
 
-static fastcall void native_load_gdt(const struct Xgt_desc_struct *dtr)
+static void native_load_gdt(const struct Xgt_desc_struct *dtr)
 {
 	asm volatile("lgdt %0"::"m" (*dtr));
 }
 
-static fastcall void native_load_idt(const struct Xgt_desc_struct *dtr)
+static void native_load_idt(const struct Xgt_desc_struct *dtr)
 {
 	asm volatile("lidt %0"::"m" (*dtr));
 }
 
-static fastcall void native_store_gdt(struct Xgt_desc_struct *dtr)
+static void native_store_gdt(struct Xgt_desc_struct *dtr)
 {
 	asm ("sgdt %0":"=m" (*dtr));
 }
 
-static fastcall void native_store_idt(struct Xgt_desc_struct *dtr)
+static void native_store_idt(struct Xgt_desc_struct *dtr)
 {
 	asm ("sidt %0":"=m" (*dtr));
 }
 
-static fastcall unsigned long native_store_tr(void)
+static unsigned long native_store_tr(void)
 {
 	unsigned long tr;
 	asm ("str %0":"=r" (tr));
 	return tr;
 }
 
-static fastcall void native_load_tls(struct thread_struct *t, unsigned int cpu)
+static void native_load_tls(struct thread_struct *t, unsigned int cpu)
 {
 #define C(i) get_cpu_gdt_table(cpu)[GDT_ENTRY_TLS_MIN + i] = t->tls_array[i]
 	C(0); C(1); C(2);
@@ -348,22 +348,22 @@ static inline void native_write_dt_entry(void *dt, int entry, u32 entry_low, u32
 	lp[1] = entry_high;
 }
 
-static fastcall void native_write_ldt_entry(void *dt, int entrynum, u32 low, u32 high)
+static void native_write_ldt_entry(void *dt, int entrynum, u32 low, u32 high)
 {
 	native_write_dt_entry(dt, entrynum, low, high);
 }
 
-static fastcall void native_write_gdt_entry(void *dt, int entrynum, u32 low, u32 high)
+static void native_write_gdt_entry(void *dt, int entrynum, u32 low, u32 high)
 {
 	native_write_dt_entry(dt, entrynum, low, high);
 }
 
-static fastcall void native_write_idt_entry(void *dt, int entrynum, u32 low, u32 high)
+static void native_write_idt_entry(void *dt, int entrynum, u32 low, u32 high)
 {
 	native_write_dt_entry(dt, entrynum, low, high);
 }
 
-static fastcall void native_load_esp0(struct tss_struct *tss,
+static void native_load_esp0(struct tss_struct *tss,
 				      struct thread_struct *thread)
 {
 	tss->esp0 = thread->esp0;
@@ -375,12 +375,12 @@ static fastcall void native_load_esp0(struct tss_struct *tss,
 	}
 }
 
-static fastcall void native_io_delay(void)
+static void native_io_delay(void)
 {
 	asm volatile("outb %al,$0x80");
 }
 
-static fastcall void native_flush_tlb(void)
+static void native_flush_tlb(void)
 {
 	__native_flush_tlb();
 }
@@ -389,49 +389,49 @@ static fastcall void native_flush_tlb(void)
  * Global pages have to be flushed a bit differently. Not a real
  * performance problem because this does not happen often.
  */
-static fastcall void native_flush_tlb_global(void)
+static void native_flush_tlb_global(void)
 {
 	__native_flush_tlb_global();
 }
 
-static fastcall void native_flush_tlb_single(u32 addr)
+static void native_flush_tlb_single(u32 addr)
 {
 	__native_flush_tlb_single(addr);
 }
 
 #ifndef CONFIG_X86_PAE
-static fastcall void native_set_pte(pte_t *ptep, pte_t pteval)
+static void native_set_pte(pte_t *ptep, pte_t pteval)
 {
 	*ptep = pteval;
 }
 
-static fastcall void native_set_pte_at(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pteval)
+static void native_set_pte_at(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pteval)
 {
 	*ptep = pteval;
 }
 
-static fastcall void native_set_pmd(pmd_t *pmdp, pmd_t pmdval)
+static void native_set_pmd(pmd_t *pmdp, pmd_t pmdval)
 {
 	*pmdp = pmdval;
 }
 
 #else /* CONFIG_X86_PAE */
 
-static fastcall void native_set_pte(pte_t *ptep, pte_t pte)
+static void native_set_pte(pte_t *ptep, pte_t pte)
 {
 	ptep->pte_high = pte.pte_high;
 	smp_wmb();
 	ptep->pte_low = pte.pte_low;
 }
 
-static fastcall void native_set_pte_at(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pte)
+static void native_set_pte_at(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pte)
 {
 	ptep->pte_high = pte.pte_high;
 	smp_wmb();
 	ptep->pte_low = pte.pte_low;
 }
 
-static fastcall void native_set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+static void native_set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
 {
 	ptep->pte_low = 0;
 	smp_wmb();
@@ -440,29 +440,29 @@ static fastcall void native_set_pte_present(struct mm_struct *mm, unsigned long
 	ptep->pte_low = pte.pte_low;
 }
 
-static fastcall void native_set_pte_atomic(pte_t *ptep, pte_t pteval)
+static void native_set_pte_atomic(pte_t *ptep, pte_t pteval)
 {
 	set_64bit((unsigned long long *)ptep,pte_val(pteval));
 }
 
-static fastcall void native_set_pmd(pmd_t *pmdp, pmd_t pmdval)
+static void native_set_pmd(pmd_t *pmdp, pmd_t pmdval)
 {
 	set_64bit((unsigned long long *)pmdp,pmd_val(pmdval));
 }
 
-static fastcall void native_set_pud(pud_t *pudp, pud_t pudval)
+static void native_set_pud(pud_t *pudp, pud_t pudval)
 {
 	*pudp = pudval;
 }
 
-static fastcall void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+static void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 {
 	ptep->pte_low = 0;
 	smp_wmb();
 	ptep->pte_high = 0;
 }
 
-static fastcall void native_pmd_clear(pmd_t *pmd)
+static void native_pmd_clear(pmd_t *pmd)
 {
 	u32 *tmp = (u32 *)pmd;
 	*tmp = 0;
@@ -472,8 +472,8 @@ static fastcall void native_pmd_clear(pmd_t *pmd)
 #endif /* CONFIG_X86_PAE */
 
 /* These are in entry.S */
-extern fastcall void native_iret(void);
-extern fastcall void native_irq_enable_sysexit(void);
+extern void native_iret(void);
+extern void native_irq_enable_sysexit(void);
 
 static int __init print_banner(void)
 {
@@ -482,9 +482,6 @@ static int __init print_banner(void)
 }
 core_initcall(print_banner);
 
-/* We simply declare start_kernel to be the paravirt probe of last resort. */
-paravirt_probe(start_kernel);
-
 struct paravirt_ops paravirt_ops = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
@@ -544,12 +541,21 @@ struct paravirt_ops paravirt_ops = {
 	.apic_write = native_apic_write,
 	.apic_write_atomic = native_apic_write_atomic,
 	.apic_read = native_apic_read,
+	.setup_boot_clock = setup_boot_APIC_clock,
+	.setup_secondary_clock = setup_secondary_APIC_clock,
 #endif
+	.set_lazy_mode = (void *)native_nop,
 
 	.flush_tlb_user = native_flush_tlb,
 	.flush_tlb_kernel = native_flush_tlb_global,
 	.flush_tlb_single = native_flush_tlb_single,
 
+	.alloc_pt = (void *)native_nop,
+	.alloc_pd = (void *)native_nop,
+	.alloc_pd_clone = (void *)native_nop,
+	.release_pt = (void *)native_nop,
+	.release_pd = (void *)native_nop,
+
 	.set_pte = native_set_pte,
 	.set_pte_at = native_set_pte_at,
 	.set_pmd = native_set_pmd,
@@ -565,6 +571,8 @@ struct paravirt_ops paravirt_ops = {
 
 	.irq_enable_sysexit = native_irq_enable_sysexit,
 	.iret = native_iret,
+
+	.startup_ipi_hook = (void *)native_nop,
 };
 
 /*

arch/i386/kernel/pcspeaker.c

@@ -0,0 +1,20 @@
+#include <linux/platform_device.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+
+static __init int add_pcspkr(void)
+{
+	struct platform_device *pd;
+	int ret;
+
+	pd = platform_device_alloc("pcspkr", -1);
+	if (!pd)
+		return -ENOMEM;
+
+	ret = platform_device_add(pd);
+	if (ret)
+		platform_device_put(pd);
+
+	return ret;
+}
+device_initcall(add_pcspkr);

arch/i386/kernel/process.c

@@ -38,6 +38,7 @@
 #include <linux/ptrace.h>
 #include <linux/random.h>
 #include <linux/personality.h>
+#include <linux/tick.h>
 
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
@@ -48,6 +49,7 @@
 #include <asm/i387.h>
 #include <asm/desc.h>
 #include <asm/vm86.h>
+#include <asm/idle.h>
 #ifdef CONFIG_MATH_EMULATION
 #include <asm/math_emu.h>
 #endif
@@ -80,6 +82,42 @@ void (*pm_idle)(void);
 EXPORT_SYMBOL(pm_idle);
 static DEFINE_PER_CPU(unsigned int, cpu_idle_state);
 
+static ATOMIC_NOTIFIER_HEAD(idle_notifier);
+
+void idle_notifier_register(struct notifier_block *n)
+{
+	atomic_notifier_chain_register(&idle_notifier, n);
+}
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+	atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+
+static DEFINE_PER_CPU(volatile unsigned long, idle_state);
+
+void enter_idle(void)
+{
+	/* needs to be atomic w.r.t. interrupts, not against other CPUs */
+	__set_bit(0, &__get_cpu_var(idle_state));
+	atomic_notifier_call_chain(&idle_notifier, IDLE_START, NULL);
+}
+
+static void __exit_idle(void)
+{
+	/* needs to be atomic w.r.t. interrupts, not against other CPUs */
+	if (__test_and_clear_bit(0, &__get_cpu_var(idle_state)) == 0)
+		return;
+	atomic_notifier_call_chain(&idle_notifier, IDLE_END, NULL);
+}
+
+void exit_idle(void)
+{
+	if (current->pid)
+		return;
+	__exit_idle();
+}
+
 void disable_hlt(void)
 {
 	hlt_counter++;
@@ -130,6 +168,7 @@ EXPORT_SYMBOL(default_idle);
  */
 static void poll_idle (void)
 {
+	local_irq_enable();
 	cpu_relax();
 }
 
@@ -173,6 +212,7 @@ void cpu_idle(void)
 
 	/* endless idle loop with no priority at all */
 	while (1) {
+		tick_nohz_stop_sched_tick();
 		while (!need_resched()) {
 			void (*idle)(void);
 
@@ -189,8 +229,18 @@ void cpu_idle(void)
 				play_dead();
 
 			__get_cpu_var(irq_stat).idle_timestamp = jiffies;
+
+			/*
+			 * Idle routines should keep interrupts disabled
+			 * from here on, until they go to idle.
+			 * Otherwise, idle callbacks can misfire.
+			 */
+			local_irq_disable();
+			enter_idle();
 			idle();
+			__exit_idle();
 		}
+		tick_nohz_restart_sched_tick();
 		preempt_enable_no_resched();
 		schedule();
 		preempt_disable();
@@ -243,7 +293,11 @@ void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
 		smp_mb();
 		if (!need_resched())
-			__mwait(eax, ecx);
+			__sti_mwait(eax, ecx);
+		else
+			local_irq_enable();
+	} else {
+		local_irq_enable();
 	}
 }
 
@@ -308,8 +362,8 @@ void show_regs(struct pt_regs * regs)
 		regs->eax,regs->ebx,regs->ecx,regs->edx);
 	printk("ESI: %08lx EDI: %08lx EBP: %08lx",
 		regs->esi, regs->edi, regs->ebp);
-	printk(" DS: %04x ES: %04x GS: %04x\n",
-	       0xffff & regs->xds,0xffff & regs->xes, 0xffff & regs->xgs);
+	printk(" DS: %04x ES: %04x FS: %04x\n",
+	       0xffff & regs->xds,0xffff & regs->xes, 0xffff & regs->xfs);
 
 	cr0 = read_cr0();
 	cr2 = read_cr2();
@@ -340,7 +394,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
 
 	regs.xds = __USER_DS;
 	regs.xes = __USER_DS;
-	regs.xgs = __KERNEL_PDA;
+	regs.xfs = __KERNEL_PDA;
 	regs.orig_eax = -1;
 	regs.eip = (unsigned long) kernel_thread_helper;
 	regs.xcs = __KERNEL_CS | get_kernel_rpl();
@@ -425,7 +479,7 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
 
 	p->thread.eip = (unsigned long) ret_from_fork;
 
-	savesegment(fs,p->thread.fs);
+	savesegment(gs,p->thread.gs);
 
 	tsk = current;
 	if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
@@ -501,8 +555,8 @@ void dump_thread(struct pt_regs * regs, struct user * dump)
 	dump->regs.eax = regs->eax;
 	dump->regs.ds = regs->xds;
 	dump->regs.es = regs->xes;
-	savesegment(fs,dump->regs.fs);
-	dump->regs.gs = regs->xgs;
+	dump->regs.fs = regs->xfs;
+	savesegment(gs,dump->regs.gs);
 	dump->regs.orig_eax = regs->orig_eax;
 	dump->regs.eip = regs->eip;
 	dump->regs.cs = regs->xcs;
@@ -653,7 +707,7 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
 	load_esp0(tss, next);
 
 	/*
-	 * Save away %fs. No need to save %gs, as it was saved on the
+	 * Save away %gs. No need to save %fs, as it was saved on the
 	 * stack on entry.  No need to save %es and %ds, as those are
 	 * always kernel segments while inside the kernel.  Doing this
 	 * before setting the new TLS descriptors avoids the situation
@@ -662,7 +716,7 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
 	 * used %fs or %gs (it does not today), or if the kernel is
 	 * running inside of a hypervisor layer.
 	 */
-	savesegment(fs, prev->fs);
+	savesegment(gs, prev->gs);
 
 	/*
 	 * Load the per-thread Thread-Local Storage descriptor.
@@ -670,14 +724,13 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
 	load_TLS(next, cpu);
 
 	/*
-	 * Restore %fs if needed.
-	 *
-	 * Glibc normally makes %fs be zero.
+	 * Restore IOPL if needed.  In normal use, the flags restore
+	 * in the switch assembly will handle this.  But if the kernel
+	 * is running virtualized at a non-zero CPL, the popf will
+	 * not restore flags, so it must be done in a separate step.
 	 */
-	if (unlikely(prev->fs | next->fs))
-		loadsegment(fs, next->fs);
-
-	write_pda(pcurrent, next_p);
+	if (get_kernel_rpl() && unlikely(prev->iopl != next->iopl))
+		set_iopl_mask(next->iopl);
 
 	/*
 	 * Now maybe handle debug registers and/or IO bitmaps
@@ -688,6 +741,15 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
 
 	disable_tsc(prev_p, next_p);
 
+	/*
+	 * Leave lazy mode, flushing any hypercalls made here.
+	 * This must be done before restoring TLS segments so
+	 * the GDT and LDT are properly updated, and must be
+	 * done before math_state_restore, so the TS bit is up
+	 * to date.
+	 */
+	arch_leave_lazy_cpu_mode();
+
 	/* If the task has used fpu the last 5 timeslices, just do a full
 	 * restore of the math state immediately to avoid the trap; the
 	 * chances of needing FPU soon are obviously high now
@@ -695,6 +757,14 @@ struct task_struct fastcall * __switch_to(struct task_struct *prev_p, struct tas
 	if (next_p->fpu_counter > 5)
 		math_state_restore();
 
+	/*
+	 * Restore %gs if needed (which is common)
+	 */
+	if (prev->gs | next->gs)
+		loadsegment(gs, next->gs);
+
+	write_pda(pcurrent, next_p);
+
 	return prev_p;
 }
 

arch/i386/kernel/ptrace.c

@@ -89,14 +89,14 @@ static int putreg(struct task_struct *child,
 	unsigned long regno, unsigned long value)
 {
 	switch (regno >> 2) {
-		case FS:
+		case GS:
 			if (value && (value & 3) != 3)
 				return -EIO;
-			child->thread.fs = value;
+			child->thread.gs = value;
 			return 0;
 		case DS:
 		case ES:
-		case GS:
+		case FS:
 			if (value && (value & 3) != 3)
 				return -EIO;
 			value &= 0xffff;
@@ -112,7 +112,7 @@ static int putreg(struct task_struct *child,
 			value |= get_stack_long(child, EFL_OFFSET) & ~FLAG_MASK;
 			break;
 	}
-	if (regno > ES*4)
+	if (regno > FS*4)
 		regno -= 1*4;
 	put_stack_long(child, regno, value);
 	return 0;
@@ -124,18 +124,18 @@ static unsigned long getreg(struct task_struct *child,
 	unsigned long retval = ~0UL;
 
 	switch (regno >> 2) {
-		case FS:
-			retval = child->thread.fs;
+		case GS:
+			retval = child->thread.gs;
 			break;
 		case DS:
 		case ES:
-		case GS:
+		case FS:
 		case SS:
 		case CS:
 			retval = 0xffff;
 			/* fall through */
 		default:
-			if (regno > ES*4)
+			if (regno > FS*4)
 				regno -= 1*4;
 			retval &= get_stack_long(child, regno);
 	}

arch/i386/kernel/setup.c

@@ -33,7 +33,6 @@
 #include <linux/initrd.h>
 #include <linux/bootmem.h>
 #include <linux/seq_file.h>
-#include <linux/platform_device.h>
 #include <linux/console.h>
 #include <linux/mca.h>
 #include <linux/root_dev.h>
@@ -60,6 +59,7 @@
 #include <asm/io_apic.h>
 #include <asm/ist.h>
 #include <asm/io.h>
+#include <asm/vmi.h>
 #include <setup_arch.h>
 #include <bios_ebda.h>
 
@@ -581,6 +581,14 @@ void __init setup_arch(char **cmdline_p)
 
 	max_low_pfn = setup_memory();
 
+#ifdef CONFIG_VMI
+	/*
+	 * Must be after max_low_pfn is determined, and before kernel
+	 * pagetables are setup.
+	 */
+	vmi_init();
+#endif
+
 	/*
 	 * NOTE: before this point _nobody_ is allowed to allocate
 	 * any memory using the bootmem allocator.  Although the
@@ -651,28 +659,3 @@ void __init setup_arch(char **cmdline_p)
 #endif
 	tsc_init();
 }
-
-static __init int add_pcspkr(void)
-{
-	struct platform_device *pd;
-	int ret;
-
-	pd = platform_device_alloc("pcspkr", -1);
-	if (!pd)
-		return -ENOMEM;
-
-	ret = platform_device_add(pd);
-	if (ret)
-		platform_device_put(pd);
-
-	return ret;
-}
-device_initcall(add_pcspkr);
-
-/*
- * Local Variables:
- * mode:c
- * c-file-style:"k&r"
- * c-basic-offset:8
- * End:
- */

arch/i386/kernel/signal.c

@@ -21,6 +21,7 @@
 #include <linux/suspend.h>
 #include <linux/ptrace.h>
 #include <linux/elf.h>
+#include <linux/binfmts.h>
 #include <asm/processor.h>
 #include <asm/ucontext.h>
 #include <asm/uaccess.h>
@@ -128,8 +129,8 @@ restore_sigcontext(struct pt_regs *regs, struct sigcontext __user *sc, int *peax
 			 X86_EFLAGS_TF | X86_EFLAGS_SF | X86_EFLAGS_ZF | \
 			 X86_EFLAGS_AF | X86_EFLAGS_PF | X86_EFLAGS_CF)
 
-	COPY_SEG(gs);
-	GET_SEG(fs);
+	GET_SEG(gs);
+	COPY_SEG(fs);
 	COPY_SEG(es);
 	COPY_SEG(ds);
 	COPY(edi);
@@ -244,9 +245,9 @@ setup_sigcontext(struct sigcontext __user *sc, struct _fpstate __user *fpstate,
 {
 	int tmp, err = 0;
 
-	err |= __put_user(regs->xgs, (unsigned int __user *)&sc->gs);
-	savesegment(fs, tmp);
-	err |= __put_user(tmp, (unsigned int __user *)&sc->fs);
+	err |= __put_user(regs->xfs, (unsigned int __user *)&sc->fs);
+	savesegment(gs, tmp);
+	err |= __put_user(tmp, (unsigned int __user *)&sc->gs);
 
 	err |= __put_user(regs->xes, (unsigned int __user *)&sc->es);
 	err |= __put_user(regs->xds, (unsigned int __user *)&sc->ds);
@@ -349,7 +350,10 @@ static int setup_frame(int sig, struct k_sigaction *ka,
 			goto give_sigsegv;
 	}
 
-	restorer = (void *)VDSO_SYM(&__kernel_sigreturn);
+	if (current->binfmt->hasvdso)
+		restorer = (void *)VDSO_SYM(&__kernel_sigreturn);
+	else
+		restorer = (void *)&frame->retcode;
 	if (ka->sa.sa_flags & SA_RESTORER)
 		restorer = ka->sa.sa_restorer;
 

arch/i386/kernel/smp.c

@@ -23,6 +23,7 @@
 
 #include <asm/mtrr.h>
 #include <asm/tlbflush.h>
+#include <asm/idle.h>
 #include <mach_apic.h>
 
 /*
@@ -374,8 +375,7 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 	/*
 	 * i'm not happy about this global shared spinlock in the
 	 * MM hot path, but we'll see how contended it is.
-	 * Temporarily this turns IRQs off, so that lockups are
-	 * detected by the NMI watchdog.
+	 * AK: x86-64 has a faster method that could be ported.
 	 */
 	spin_lock(&tlbstate_lock);
 	
@@ -400,7 +400,7 @@ static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
 
 	while (!cpus_empty(flush_cpumask))
 		/* nothing. lockup detection does not belong here */
-		mb();
+		cpu_relax();
 
 	flush_mm = NULL;
 	flush_va = 0;
@@ -624,6 +624,7 @@ fastcall void smp_call_function_interrupt(struct pt_regs *regs)
 	/*
 	 * At this point the info structure may be out of scope unless wait==1
 	 */
+	exit_idle();
 	irq_enter();
 	(*func)(info);
 	irq_exit();

arch/i386/kernel/smpboot.c

@@ -63,6 +63,7 @@
 #include <mach_apic.h>
 #include <mach_wakecpu.h>
 #include <smpboot_hooks.h>
+#include <asm/vmi.h>
 
 /* Set if we find a B stepping CPU */
 static int __devinitdata smp_b_stepping;
@@ -93,12 +94,6 @@ cpumask_t cpu_possible_map;
 EXPORT_SYMBOL(cpu_possible_map);
 static cpumask_t smp_commenced_mask;
 
-/* TSC's upper 32 bits can't be written in eariler CPU (before prescott), there
- * is no way to resync one AP against BP. TBD: for prescott and above, we
- * should use IA64's algorithm
- */
-static int __devinitdata tsc_sync_disabled;
-
 /* Per CPU bogomips and other parameters */
 struct cpuinfo_x86 cpu_data[NR_CPUS] __cacheline_aligned;
 EXPORT_SYMBOL(cpu_data);
@@ -215,151 +210,6 @@ valid_k7:
 	;
 }
 
-/*
- * TSC synchronization.
- *
- * We first check whether all CPUs have their TSC's synchronized,
- * then we print a warning if not, and always resync.
- */
-
-static struct {
-	atomic_t start_flag;
-	atomic_t count_start;
-	atomic_t count_stop;
-	unsigned long long values[NR_CPUS];
-} tsc __cpuinitdata = {
-	.start_flag = ATOMIC_INIT(0),
-	.count_start = ATOMIC_INIT(0),
-	.count_stop = ATOMIC_INIT(0),
-};
-
-#define NR_LOOPS 5
-
-static void __init synchronize_tsc_bp(void)
-{
-	int i;
-	unsigned long long t0;
-	unsigned long long sum, avg;
-	long long delta;
-	unsigned int one_usec;
-	int buggy = 0;
-
-	printk(KERN_INFO "checking TSC synchronization across %u CPUs: ", num_booting_cpus());
-
-	/* convert from kcyc/sec to cyc/usec */
-	one_usec = cpu_khz / 1000;
-
-	atomic_set(&tsc.start_flag, 1);
-	wmb();
-
-	/*
-	 * We loop a few times to get a primed instruction cache,
-	 * then the last pass is more or less synchronized and
-	 * the BP and APs set their cycle counters to zero all at
-	 * once. This reduces the chance of having random offsets
-	 * between the processors, and guarantees that the maximum
-	 * delay between the cycle counters is never bigger than
-	 * the latency of information-passing (cachelines) between
-	 * two CPUs.
-	 */
-	for (i = 0; i < NR_LOOPS; i++) {
-		/*
-		 * all APs synchronize but they loop on '== num_cpus'
-		 */
-		while (atomic_read(&tsc.count_start) != num_booting_cpus()-1)
-			cpu_relax();
-		atomic_set(&tsc.count_stop, 0);
-		wmb();
-		/*
-		 * this lets the APs save their current TSC:
-		 */
-		atomic_inc(&tsc.count_start);
-
-		rdtscll(tsc.values[smp_processor_id()]);
-		/*
-		 * We clear the TSC in the last loop:
-		 */
-		if (i == NR_LOOPS-1)
-			write_tsc(0, 0);
-
-		/*
-		 * Wait for all APs to leave the synchronization point:
-		 */
-		while (atomic_read(&tsc.count_stop) != num_booting_cpus()-1)
-			cpu_relax();
-		atomic_set(&tsc.count_start, 0);
-		wmb();
-		atomic_inc(&tsc.count_stop);
-	}
-
-	sum = 0;
-	for (i = 0; i < NR_CPUS; i++) {
-		if (cpu_isset(i, cpu_callout_map)) {
-			t0 = tsc.values[i];
-			sum += t0;
-		}
-	}
-	avg = sum;
-	do_div(avg, num_booting_cpus());
-
-	for (i = 0; i < NR_CPUS; i++) {
-		if (!cpu_isset(i, cpu_callout_map))
-			continue;
-		delta = tsc.values[i] - avg;
-		if (delta < 0)
-			delta = -delta;
-		/*
-		 * We report bigger than 2 microseconds clock differences.
-		 */
-		if (delta > 2*one_usec) {
-			long long realdelta;
-
-			if (!buggy) {
-				buggy = 1;
-				printk("\n");
-			}
-			realdelta = delta;
-			do_div(realdelta, one_usec);
-			if (tsc.values[i] < avg)
-				realdelta = -realdelta;
-
-			if (realdelta)
-				printk(KERN_INFO "CPU#%d had %Ld usecs TSC "
-					"skew, fixed it up.\n", i, realdelta);
-		}
-	}
-	if (!buggy)
-		printk("passed.\n");
-}
-
-static void __cpuinit synchronize_tsc_ap(void)
-{
-	int i;
-
-	/*
-	 * Not every cpu is online at the time
-	 * this gets called, so we first wait for the BP to
-	 * finish SMP initialization:
-	 */
-	while (!atomic_read(&tsc.start_flag))
-		cpu_relax();
-
-	for (i = 0; i < NR_LOOPS; i++) {
-		atomic_inc(&tsc.count_start);
-		while (atomic_read(&tsc.count_start) != num_booting_cpus())
-			cpu_relax();
-
-		rdtscll(tsc.values[smp_processor_id()]);
-		if (i == NR_LOOPS-1)
-			write_tsc(0, 0);
-
-		atomic_inc(&tsc.count_stop);
-		while (atomic_read(&tsc.count_stop) != num_booting_cpus())
-			cpu_relax();
-	}
-}
-#undef NR_LOOPS
-
 extern void calibrate_delay(void);
 
 static atomic_t init_deasserted;
@@ -437,20 +287,12 @@ static void __cpuinit smp_callin(void)
 	/*
 	 * Save our processor parameters
 	 */
- 	smp_store_cpu_info(cpuid);
-
-	disable_APIC_timer();
+	smp_store_cpu_info(cpuid);
 
 	/*
 	 * Allow the master to continue.
 	 */
 	cpu_set(cpuid, cpu_callin_map);
-
-	/*
-	 *      Synchronize the TSC with the BP
-	 */
-	if (cpu_has_tsc && cpu_khz && !tsc_sync_disabled)
-		synchronize_tsc_ap();
 }
 
 static int cpucount;
@@ -545,18 +387,25 @@ static void __cpuinit start_secondary(void *unused)
 	 * booting is too fragile that we want to limit the
 	 * things done here to the most necessary things.
 	 */
+#ifdef CONFIG_VMI
+	vmi_bringup();
+#endif
 	secondary_cpu_init();
 	preempt_disable();
 	smp_callin();
 	while (!cpu_isset(smp_processor_id(), smp_commenced_mask))
 		rep_nop();
-	setup_secondary_APIC_clock();
+	/*
+	 * Check TSC synchronization with the BP:
+	 */
+	check_tsc_sync_target();
+
+	setup_secondary_clock();
 	if (nmi_watchdog == NMI_IO_APIC) {
 		disable_8259A_irq(0);
 		enable_NMI_through_LVT0(NULL);
 		enable_8259A_irq(0);
 	}
-	enable_APIC_timer();
 	/*
 	 * low-memory mappings have been cleared, flush them from
 	 * the local TLBs too.
@@ -619,7 +468,6 @@ extern struct {
 	unsigned short ss;
 } stack_start;
 extern struct i386_pda *start_pda;
-extern struct Xgt_desc_struct cpu_gdt_descr;
 
 #ifdef CONFIG_NUMA
 
@@ -749,7 +597,7 @@ wakeup_secondary_cpu(int logical_apicid, unsigned long start_eip)
 	/*
 	 * Due to the Pentium erratum 3AP.
 	 */
-	maxlvt = get_maxlvt();
+	maxlvt = lapic_get_maxlvt();
 	if (maxlvt > 3) {
 		apic_read_around(APIC_SPIV);
 		apic_write(APIC_ESR, 0);
@@ -834,12 +682,19 @@ wakeup_secondary_cpu(int phys_apicid, unsigned long start_eip)
 	else
 		num_starts = 0;
 
+	/*
+	 * Paravirt / VMI wants a startup IPI hook here to set up the
+	 * target processor state.
+	 */
+	startup_ipi_hook(phys_apicid, (unsigned long) start_secondary,
+		         (unsigned long) stack_start.esp);
+
 	/*
 	 * Run STARTUP IPI loop.
 	 */
 	Dprintk("#startup loops: %d.\n", num_starts);
 
-	maxlvt = get_maxlvt();
+	maxlvt = lapic_get_maxlvt();
 
 	for (j = 1; j <= num_starts; j++) {
 		Dprintk("Sending STARTUP #%d.\n",j);
@@ -1115,8 +970,6 @@ static int __cpuinit __smp_prepare_cpu(int cpu)
 	info.cpu = cpu;
 	INIT_WORK(&info.task, do_warm_boot_cpu);
 
-	tsc_sync_disabled = 1;
-
 	/* init low mem mapping */
 	clone_pgd_range(swapper_pg_dir, swapper_pg_dir + USER_PGD_PTRS,
 			min_t(unsigned long, KERNEL_PGD_PTRS, USER_PGD_PTRS));
@@ -1124,7 +977,6 @@ static int __cpuinit __smp_prepare_cpu(int cpu)
 	schedule_work(&info.task);
 	wait_for_completion(&done);
 
-	tsc_sync_disabled = 0;
 	zap_low_mappings();
 	ret = 0;
 exit:
@@ -1320,13 +1172,7 @@ static void __init smp_boot_cpus(unsigned int max_cpus)
 
 	smpboot_setup_io_apic();
 
-	setup_boot_APIC_clock();
-
-	/*
-	 * Synchronize the TSC with the AP
-	 */
-	if (cpu_has_tsc && cpucount && cpu_khz)
-		synchronize_tsc_bp();
+	setup_boot_clock();
 }
 
 /* These are wrappers to interface to the new boot process.  Someone
@@ -1461,9 +1307,16 @@ int __cpuinit __cpu_up(unsigned int cpu)
 	}
 
 	local_irq_enable();
+
 	per_cpu(cpu_state, cpu) = CPU_UP_PREPARE;
 	/* Unleash the CPU! */
 	cpu_set(cpu, smp_commenced_mask);
+
+	/*
+	 * Check TSC synchronization with the AP:
+	 */
+	check_tsc_sync_source(cpu);
+
 	while (!cpu_isset(cpu, cpu_online_map))
 		cpu_relax();
 

arch/i386/kernel/sysenter.c

@@ -78,7 +78,7 @@ int __init sysenter_setup(void)
 	syscall_pages[0] = virt_to_page(syscall_page);
 
 #ifdef CONFIG_COMPAT_VDSO
-	__set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_READONLY);
+	__set_fixmap(FIX_VDSO, __pa(syscall_page), PAGE_READONLY_EXEC);
 	printk("Compat vDSO mapped to %08lx.\n", __fix_to_virt(FIX_VDSO));
 #endif
 

arch/i386/kernel/time.c

@@ -131,15 +131,13 @@ unsigned long profile_pc(struct pt_regs *regs)
 	unsigned long pc = instruction_pointer(regs);
 
 #ifdef CONFIG_SMP
-	if (!user_mode_vm(regs) && in_lock_functions(pc)) {
+	if (!v8086_mode(regs) && SEGMENT_IS_KERNEL_CODE(regs->xcs) &&
+	    in_lock_functions(pc)) {
 #ifdef CONFIG_FRAME_POINTER
 		return *(unsigned long *)(regs->ebp + 4);
 #else
-		unsigned long *sp;
-		if ((regs->xcs & 3) == 0)
-			sp = (unsigned long *)&regs->esp;
-		else
-			sp = (unsigned long *)regs->esp;
+		unsigned long *sp = (unsigned long *)&regs->esp;
+
 		/* Return address is either directly at stack pointer
 		   or above a saved eflags. Eflags has bits 22-31 zero,
 		   kernel addresses don't. */
@@ -161,15 +159,6 @@ EXPORT_SYMBOL(profile_pc);
  */
 irqreturn_t timer_interrupt(int irq, void *dev_id)
 {
-	/*
-	 * Here we are in the timer irq handler. We just have irqs locally
-	 * disabled but we don't know if the timer_bh is running on the other
-	 * CPU. We need to avoid to SMP race with it. NOTE: we don' t need
-	 * the irq version of write_lock because as just said we have irq
-	 * locally disabled. -arca
-	 */
-	write_seqlock(&xtime_lock);
-
 #ifdef CONFIG_X86_IO_APIC
 	if (timer_ack) {
 		/*
@@ -188,7 +177,6 @@ irqreturn_t timer_interrupt(int irq, void *dev_id)
 
 	do_timer_interrupt_hook();
 
-
 	if (MCA_bus) {
 		/* The PS/2 uses level-triggered interrupts.  You can't
 		turn them off, nor would you want to (any attempt to
@@ -203,18 +191,11 @@ irqreturn_t timer_interrupt(int irq, void *dev_id)
 		outb_p( irq_v|0x80, 0x61 );	/* reset the IRQ */
 	}
 
-	write_sequnlock(&xtime_lock);
-
-#ifdef CONFIG_X86_LOCAL_APIC
-	if (using_apic_timer)
-		smp_send_timer_broadcast_ipi();
-#endif
-
 	return IRQ_HANDLED;
 }
 
 /* not static: needed by APM */
-unsigned long get_cmos_time(void)
+unsigned long read_persistent_clock(void)
 {
 	unsigned long retval;
 	unsigned long flags;
@@ -227,11 +208,11 @@ unsigned long get_cmos_time(void)
 
 	return retval;
 }
-EXPORT_SYMBOL(get_cmos_time);
 
 static void sync_cmos_clock(unsigned long dummy);
 
 static DEFINE_TIMER(sync_cmos_timer, sync_cmos_clock, 0, 0);
+int no_sync_cmos_clock;
 
 static void sync_cmos_clock(unsigned long dummy)
 {
@@ -275,117 +256,20 @@ static void sync_cmos_clock(unsigned long dummy)
 
 void notify_arch_cmos_timer(void)
 {
-	mod_timer(&sync_cmos_timer, jiffies + 1);
-}
-
-static long clock_cmos_diff;
-static unsigned long sleep_start;
-
-static int timer_suspend(struct sys_device *dev, pm_message_t state)
-{
-	/*
-	 * Estimate time zone so that set_time can update the clock
-	 */
-	unsigned long ctime =  get_cmos_time();
-
-	clock_cmos_diff = -ctime;
-	clock_cmos_diff += get_seconds();
-	sleep_start = ctime;
-	return 0;
-}
-
-static int timer_resume(struct sys_device *dev)
-{
-	unsigned long flags;
-	unsigned long sec;
-	unsigned long ctime = get_cmos_time();
-	long sleep_length = (ctime - sleep_start) * HZ;
-	struct timespec ts;
-
-	if (sleep_length < 0) {
-		printk(KERN_WARNING "CMOS clock skew detected in timer resume!\n");
-		/* The time after the resume must not be earlier than the time
-		 * before the suspend or some nasty things will happen
-		 */
-		sleep_length = 0;
-		ctime = sleep_start;
-	}
-#ifdef CONFIG_HPET_TIMER
-	if (is_hpet_enabled())
-		hpet_reenable();
-#endif
-	setup_pit_timer();
-
-	sec = ctime + clock_cmos_diff;
-	ts.tv_sec = sec;
-	ts.tv_nsec = 0;
-	do_settimeofday(&ts);
-	write_seqlock_irqsave(&xtime_lock, flags);
-	jiffies_64 += sleep_length;
-	write_sequnlock_irqrestore(&xtime_lock, flags);
-	touch_softlockup_watchdog();
-	return 0;
-}
-
-static struct sysdev_class timer_sysclass = {
-	.resume = timer_resume,
-	.suspend = timer_suspend,
-	set_kset_name("timer"),
-};
-
-
-/* XXX this driverfs stuff should probably go elsewhere later -john */
-static struct sys_device device_timer = {
-	.id	= 0,
-	.cls	= &timer_sysclass,
-};
-
-static int time_init_device(void)
-{
-	int error = sysdev_class_register(&timer_sysclass);
-	if (!error)
-		error = sysdev_register(&device_timer);
-	return error;
+	if (!no_sync_cmos_clock)
+		mod_timer(&sync_cmos_timer, jiffies + 1);
 }
 
-device_initcall(time_init_device);
-
-#ifdef CONFIG_HPET_TIMER
 extern void (*late_time_init)(void);
 /* Duplicate of time_init() below, with hpet_enable part added */
 static void __init hpet_time_init(void)
 {
-	struct timespec ts;
-	ts.tv_sec = get_cmos_time();
-	ts.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ);
-
-	do_settimeofday(&ts);
-
-	if ((hpet_enable() >= 0) && hpet_use_timer) {
-		printk("Using HPET for base-timer\n");
-	}
-
+	if (!hpet_enable())
+		setup_pit_timer();
 	do_time_init();
 }
-#endif
 
 void __init time_init(void)
 {
-	struct timespec ts;
-#ifdef CONFIG_HPET_TIMER
-	if (is_hpet_capable()) {
-		/*
-		 * HPET initialization needs to do memory-mapped io. So, let
-		 * us do a late initialization after mem_init().
-		 */
-		late_time_init = hpet_time_init;
-		return;
-	}
-#endif
-	ts.tv_sec = get_cmos_time();
-	ts.tv_nsec = (INITIAL_JIFFIES % HZ) * (NSEC_PER_SEC / HZ);
-
-	do_settimeofday(&ts);
-
-	do_time_init();
+	late_time_init = hpet_time_init;
 }

arch/i386/kernel/traps.c

@@ -94,6 +94,7 @@ asmlinkage void spurious_interrupt_bug(void);
 asmlinkage void machine_check(void);
 
 int kstack_depth_to_print = 24;
+static unsigned int code_bytes = 64;
 ATOMIC_NOTIFIER_HEAD(i386die_chain);
 
 int register_die_notifier(struct notifier_block *nb)
@@ -291,10 +292,11 @@ void show_registers(struct pt_regs *regs)
 	int i;
 	int in_kernel = 1;
 	unsigned long esp;
-	unsigned short ss;
+	unsigned short ss, gs;
 
 	esp = (unsigned long) (&regs->esp);
 	savesegment(ss, ss);
+	savesegment(gs, gs);
 	if (user_mode_vm(regs)) {
 		in_kernel = 0;
 		esp = regs->esp;
@@ -313,8 +315,8 @@ void show_registers(struct pt_regs *regs)
 		regs->eax, regs->ebx, regs->ecx, regs->edx);
 	printk(KERN_EMERG "esi: %08lx   edi: %08lx   ebp: %08lx   esp: %08lx\n",
 		regs->esi, regs->edi, regs->ebp, esp);
-	printk(KERN_EMERG "ds: %04x   es: %04x   ss: %04x\n",
-		regs->xds & 0xffff, regs->xes & 0xffff, ss);
+	printk(KERN_EMERG "ds: %04x   es: %04x   fs: %04x  gs: %04x  ss: %04x\n",
+	       regs->xds & 0xffff, regs->xes & 0xffff, regs->xfs & 0xffff, gs, ss);
 	printk(KERN_EMERG "Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)",
 		TASK_COMM_LEN, current->comm, current->pid,
 		current_thread_info(), current, current->thread_info);
@@ -324,7 +326,8 @@ void show_registers(struct pt_regs *regs)
 	 */
 	if (in_kernel) {
 		u8 *eip;
-		int code_bytes = 64;
+		unsigned int code_prologue = code_bytes * 43 / 64;
+		unsigned int code_len = code_bytes;
 		unsigned char c;
 
 		printk("\n" KERN_EMERG "Stack: ");
@@ -332,14 +335,14 @@ void show_registers(struct pt_regs *regs)
 
 		printk(KERN_EMERG "Code: ");
 
-		eip = (u8 *)regs->eip - 43;
+		eip = (u8 *)regs->eip - code_prologue;
 		if (eip < (u8 *)PAGE_OFFSET ||
 			probe_kernel_address(eip, c)) {
 			/* try starting at EIP */
 			eip = (u8 *)regs->eip;
-			code_bytes = 32;
+			code_len = code_len - code_prologue + 1;
 		}
-		for (i = 0; i < code_bytes; i++, eip++) {
+		for (i = 0; i < code_len; i++, eip++) {
 			if (eip < (u8 *)PAGE_OFFSET ||
 				probe_kernel_address(eip, c)) {
 				printk(" Bad EIP value.");
@@ -1191,3 +1194,13 @@ static int __init kstack_setup(char *s)
 	return 1;
 }
 __setup("kstack=", kstack_setup);
+
+static int __init code_bytes_setup(char *s)
+{
+	code_bytes = simple_strtoul(s, NULL, 0);
+	if (code_bytes > 8192)
+		code_bytes = 8192;
+
+	return 1;
+}
+__setup("code_bytes=", code_bytes_setup);

arch/i386/kernel/tsc.c

@@ -23,6 +23,7 @@
  * an extra value to store the TSC freq
  */
 unsigned int tsc_khz;
+unsigned long long (*custom_sched_clock)(void);
 
 int tsc_disable;
 
@@ -59,12 +60,6 @@ static inline int check_tsc_unstable(void)
 	return tsc_unstable;
 }
 
-void mark_tsc_unstable(void)
-{
-	tsc_unstable = 1;
-}
-EXPORT_SYMBOL_GPL(mark_tsc_unstable);
-
 /* Accellerators for sched_clock()
  * convert from cycles(64bits) => nanoseconds (64bits)
  *  basic equation:
@@ -107,14 +102,14 @@ unsigned long long sched_clock(void)
 {
 	unsigned long long this_offset;
 
+	if (unlikely(custom_sched_clock))
+		return (*custom_sched_clock)();
+
 	/*
-	 * in the NUMA case we dont use the TSC as they are not
-	 * synchronized across all CPUs.
+	 * Fall back to jiffies if there's no TSC available:
 	 */
-#ifndef CONFIG_NUMA
-	if (!cpu_khz || check_tsc_unstable())
-#endif
-		/* no locking but a rare wrong value is not a big deal */
+	if (unlikely(tsc_disable))
+		/* No locking but a rare wrong value is not a big deal: */
 		return (jiffies_64 - INITIAL_JIFFIES) * (1000000000 / HZ);
 
 	/* read the Time Stamp Counter: */
@@ -194,13 +189,13 @@ EXPORT_SYMBOL(recalibrate_cpu_khz);
 void __init tsc_init(void)
 {
 	if (!cpu_has_tsc || tsc_disable)
-		return;
+		goto out_no_tsc;
 
 	cpu_khz = calculate_cpu_khz();
 	tsc_khz = cpu_khz;
 
 	if (!cpu_khz)
-		return;
+		goto out_no_tsc;
 
 	printk("Detected %lu.%03lu MHz processor.\n",
 				(unsigned long)cpu_khz / 1000,
@@ -208,37 +203,18 @@ void __init tsc_init(void)
 
 	set_cyc2ns_scale(cpu_khz);
 	use_tsc_delay();
-}
+	return;
 
-#ifdef CONFIG_CPU_FREQ
-
-static unsigned int cpufreq_delayed_issched = 0;
-static unsigned int cpufreq_init = 0;
-static struct work_struct cpufreq_delayed_get_work;
-
-static void handle_cpufreq_delayed_get(struct work_struct *work)
-{
-	unsigned int cpu;
-
-	for_each_online_cpu(cpu)
-		cpufreq_get(cpu);
-
-	cpufreq_delayed_issched = 0;
+out_no_tsc:
+	/*
+	 * Set the tsc_disable flag if there's no TSC support, this
+	 * makes it a fast flag for the kernel to see whether it
+	 * should be using the TSC.
+	 */
+	tsc_disable = 1;
 }
 
-/*
- * if we notice cpufreq oddness, schedule a call to cpufreq_get() as it tries
- * to verify the CPU frequency the timing core thinks the CPU is running
- * at is still correct.
- */
-static inline void cpufreq_delayed_get(void)
-{
-	if (cpufreq_init && !cpufreq_delayed_issched) {
-		cpufreq_delayed_issched = 1;
-		printk(KERN_DEBUG "Checking if CPU frequency changed.\n");
-		schedule_work(&cpufreq_delayed_get_work);
-	}
-}
+#ifdef CONFIG_CPU_FREQ
 
 /*
  * if the CPU frequency is scaled, TSC-based delays will need a different
@@ -303,17 +279,9 @@ static struct notifier_block time_cpufreq_notifier_block = {
 
 static int __init cpufreq_tsc(void)
 {
-	int ret;
-
-	INIT_WORK(&cpufreq_delayed_get_work, handle_cpufreq_delayed_get);
-	ret = cpufreq_register_notifier(&time_cpufreq_notifier_block,
-					CPUFREQ_TRANSITION_NOTIFIER);
-	if (!ret)
-		cpufreq_init = 1;
-
-	return ret;
+	return cpufreq_register_notifier(&time_cpufreq_notifier_block,
+					 CPUFREQ_TRANSITION_NOTIFIER);
 }
-
 core_initcall(cpufreq_tsc);
 
 #endif
@@ -321,7 +289,6 @@ core_initcall(cpufreq_tsc);
 /* clock source code */
 
 static unsigned long current_tsc_khz = 0;
-static int tsc_update_callback(void);
 
 static cycle_t read_tsc(void)
 {
@@ -339,37 +306,28 @@ static struct clocksource clocksource_tsc = {
 	.mask			= CLOCKSOURCE_MASK(64),
 	.mult			= 0, /* to be set */
 	.shift			= 22,
-	.update_callback	= tsc_update_callback,
-	.is_continuous		= 1,
+	.flags			= CLOCK_SOURCE_IS_CONTINUOUS |
+				  CLOCK_SOURCE_MUST_VERIFY,
 };
 
-static int tsc_update_callback(void)
+void mark_tsc_unstable(void)
 {
-	int change = 0;
-
-	/* check to see if we should switch to the safe clocksource: */
-	if (clocksource_tsc.rating != 0 && check_tsc_unstable()) {
-		clocksource_tsc.rating = 0;
-		clocksource_reselect();
-		change = 1;
-	}
-
-	/* only update if tsc_khz has changed: */
-	if (current_tsc_khz != tsc_khz) {
-		current_tsc_khz = tsc_khz;
-		clocksource_tsc.mult = clocksource_khz2mult(current_tsc_khz,
-							clocksource_tsc.shift);
-		change = 1;
+	if (!tsc_unstable) {
+		tsc_unstable = 1;
+		/* Can be called before registration */
+		if (clocksource_tsc.mult)
+			clocksource_change_rating(&clocksource_tsc, 0);
+		else
+			clocksource_tsc.rating = 0;
 	}
-
-	return change;
 }
+EXPORT_SYMBOL_GPL(mark_tsc_unstable);
 
 static int __init dmi_mark_tsc_unstable(struct dmi_system_id *d)
 {
 	printk(KERN_NOTICE "%s detected: marking TSC unstable.\n",
 		       d->ident);
-	mark_tsc_unstable();
+	tsc_unstable = 1;
 	return 0;
 }
 
@@ -386,65 +344,44 @@ static struct dmi_system_id __initdata bad_tsc_dmi_table[] = {
 	 {}
 };
 
-#define TSC_FREQ_CHECK_INTERVAL (10*MSEC_PER_SEC) /* 10sec in MS */
-static struct timer_list verify_tsc_freq_timer;
-
-/* XXX - Probably should add locking */
-static void verify_tsc_freq(unsigned long unused)
-{
-	static u64 last_tsc;
-	static unsigned long last_jiffies;
-
-	u64 now_tsc, interval_tsc;
-	unsigned long now_jiffies, interval_jiffies;
-
-
-	if (check_tsc_unstable())
-		return;
-
-	rdtscll(now_tsc);
-	now_jiffies = jiffies;
-
-	if (!last_jiffies) {
-		goto out;
-	}
-
-	interval_jiffies = now_jiffies - last_jiffies;
-	interval_tsc = now_tsc - last_tsc;
-	interval_tsc *= HZ;
-	do_div(interval_tsc, cpu_khz*1000);
-
-	if (interval_tsc < (interval_jiffies * 3 / 4)) {
-		printk("TSC appears to be running slowly. "
-			"Marking it as unstable\n");
-		mark_tsc_unstable();
-		return;
-	}
-
-out:
-	last_tsc = now_tsc;
-	last_jiffies = now_jiffies;
-	/* set us up to go off on the next interval: */
-	mod_timer(&verify_tsc_freq_timer,
-		jiffies + msecs_to_jiffies(TSC_FREQ_CHECK_INTERVAL));
-}
-
 /*
  * Make an educated guess if the TSC is trustworthy and synchronized
  * over all CPUs.
  */
-static __init int unsynchronized_tsc(void)
+__cpuinit int unsynchronized_tsc(void)
 {
+	if (!cpu_has_tsc || tsc_unstable)
+		return 1;
 	/*
 	 * Intel systems are normally all synchronized.
 	 * Exceptions must mark TSC as unstable:
 	 */
-	if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
- 		return 0;
+	if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
+		/* assume multi socket systems are not synchronized: */
+		if (num_possible_cpus() > 1)
+			tsc_unstable = 1;
+	}
+	return tsc_unstable;
+}
+
+/*
+ * Geode_LX - the OLPC CPU has a possibly a very reliable TSC
+ */
+#ifdef CONFIG_MGEODE_LX
+/* RTSC counts during suspend */
+#define RTSC_SUSP 0x100
+
+static void __init check_geode_tsc_reliable(void)
+{
+	unsigned long val;
 
-	/* assume multi socket systems are not synchronized: */
- 	return num_possible_cpus() > 1;
+	rdmsrl(MSR_GEODE_BUSCONT_CONF0, val);
+	if ((val & RTSC_SUSP))
+		clocksource_tsc.flags &= ~CLOCK_SOURCE_MUST_VERIFY;
 }
+#else
+static inline void check_geode_tsc_reliable(void) { }
+#endif
 
 static int __init init_tsc_clocksource(void)
 {
@@ -453,20 +390,16 @@ static int __init init_tsc_clocksource(void)
 		/* check blacklist */
 		dmi_check_system(bad_tsc_dmi_table);
 
-		if (unsynchronized_tsc()) /* mark unstable if unsynced */
-			mark_tsc_unstable();
+		unsynchronized_tsc();
+		check_geode_tsc_reliable();
 		current_tsc_khz = tsc_khz;
 		clocksource_tsc.mult = clocksource_khz2mult(current_tsc_khz,
 							clocksource_tsc.shift);
 		/* lower the rating if we already know its unstable: */
-		if (check_tsc_unstable())
+		if (check_tsc_unstable()) {
 			clocksource_tsc.rating = 0;
-
-		init_timer(&verify_tsc_freq_timer);
-		verify_tsc_freq_timer.function = verify_tsc_freq;
-		verify_tsc_freq_timer.expires =
-			jiffies + msecs_to_jiffies(TSC_FREQ_CHECK_INTERVAL);
-		add_timer(&verify_tsc_freq_timer);
+			clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS;
+		}
 
 		return clocksource_register(&clocksource_tsc);
 	}

arch/i386/kernel/tsc_sync.c

@@ -0,0 +1 @@
+#include "../../x86_64/kernel/tsc_sync.c"

arch/i386/kernel/vm86.c

@@ -96,12 +96,12 @@ static int copy_vm86_regs_to_user(struct vm86_regs __user *user,
 {
 	int ret = 0;
 
-	/* kernel_vm86_regs is missing xfs, so copy everything up to
-	   (but not including) xgs, and then rest after xgs. */
-	ret += copy_to_user(user, regs, offsetof(struct kernel_vm86_regs, pt.xgs));
-	ret += copy_to_user(&user->__null_gs, &regs->pt.xgs,
+	/* kernel_vm86_regs is missing xgs, so copy everything up to
+	   (but not including) orig_eax, and then rest including orig_eax. */
+	ret += copy_to_user(user, regs, offsetof(struct kernel_vm86_regs, pt.orig_eax));
+	ret += copy_to_user(&user->orig_eax, &regs->pt.orig_eax,
 			    sizeof(struct kernel_vm86_regs) -
-			    offsetof(struct kernel_vm86_regs, pt.xgs));
+			    offsetof(struct kernel_vm86_regs, pt.orig_eax));
 
 	return ret;
 }
@@ -113,12 +113,13 @@ static int copy_vm86_regs_from_user(struct kernel_vm86_regs *regs,
 {
 	int ret = 0;
 
-	ret += copy_from_user(regs, user, offsetof(struct kernel_vm86_regs, pt.xgs));
-	ret += copy_from_user(&regs->pt.xgs, &user->__null_gs,
+	/* copy eax-xfs inclusive */
+	ret += copy_from_user(regs, user, offsetof(struct kernel_vm86_regs, pt.orig_eax));
+	/* copy orig_eax-__gsh+extra */
+	ret += copy_from_user(&regs->pt.orig_eax, &user->orig_eax,
 			      sizeof(struct kernel_vm86_regs) -
-			      offsetof(struct kernel_vm86_regs, pt.xgs) +
+			      offsetof(struct kernel_vm86_regs, pt.orig_eax) +
 			      extra);
-
 	return ret;
 }
 
@@ -157,8 +158,8 @@ struct pt_regs * fastcall save_v86_state(struct kernel_vm86_regs * regs)
 
 	ret = KVM86->regs32;
 
-	loadsegment(fs, current->thread.saved_fs);
-	ret->xgs = current->thread.saved_gs;
+	ret->xfs = current->thread.saved_fs;
+	loadsegment(gs, current->thread.saved_gs);
 
 	return ret;
 }
@@ -285,9 +286,9 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
  */
 	info->regs.pt.xds = 0;
 	info->regs.pt.xes = 0;
-	info->regs.pt.xgs = 0;
+	info->regs.pt.xfs = 0;
 
-/* we are clearing fs later just before "jmp resume_userspace",
+/* we are clearing gs later just before "jmp resume_userspace",
  * because it is not saved/restored.
  */
 
@@ -321,8 +322,8 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
  */
 	info->regs32->eax = 0;
 	tsk->thread.saved_esp0 = tsk->thread.esp0;
-	savesegment(fs, tsk->thread.saved_fs);
-	tsk->thread.saved_gs = info->regs32->xgs;
+	tsk->thread.saved_fs = info->regs32->xfs;
+	savesegment(gs, tsk->thread.saved_gs);
 
 	tss = &per_cpu(init_tss, get_cpu());
 	tsk->thread.esp0 = (unsigned long) &info->VM86_TSS_ESP0;
@@ -342,7 +343,7 @@ static void do_sys_vm86(struct kernel_vm86_struct *info, struct task_struct *tsk
 	__asm__ __volatile__(
 		"movl %0,%%esp\n\t"
 		"movl %1,%%ebp\n\t"
-		"mov  %2, %%fs\n\t"
+		"mov  %2, %%gs\n\t"
 		"jmp resume_userspace"
 		: /* no outputs */
 		:"r" (&info->regs), "r" (task_thread_info(tsk)), "r" (0));

arch/i386/kernel/vmi.c

@@ -0,0 +1,949 @@
+/*
+ * VMI specific paravirt-ops implementation
+ *
+ * Copyright (C) 2005, VMware, Inc.
+ *
+ * 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, GOOD TITLE or
+ * NON INFRINGEMENT.  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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to zach@vmware.com
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/license.h>
+#include <linux/cpu.h>
+#include <linux/bootmem.h>
+#include <linux/mm.h>
+#include <asm/vmi.h>
+#include <asm/io.h>
+#include <asm/fixmap.h>
+#include <asm/apicdef.h>
+#include <asm/apic.h>
+#include <asm/processor.h>
+#include <asm/timer.h>
+#include <asm/vmi_time.h>
+
+/* Convenient for calling VMI functions indirectly in the ROM */
+typedef u32 __attribute__((regparm(1))) (VROMFUNC)(void);
+typedef u64 __attribute__((regparm(2))) (VROMLONGFUNC)(int);
+
+#define call_vrom_func(rom,func) \
+   (((VROMFUNC *)(rom->func))())
+
+#define call_vrom_long_func(rom,func,arg) \
+   (((VROMLONGFUNC *)(rom->func)) (arg))
+
+static struct vrom_header *vmi_rom;
+static int license_gplok;
+static int disable_nodelay;
+static int disable_pge;
+static int disable_pse;
+static int disable_sep;
+static int disable_tsc;
+static int disable_mtrr;
+
+/* Cached VMI operations */
+struct {
+	void (*cpuid)(void /* non-c */);
+	void (*_set_ldt)(u32 selector);
+	void (*set_tr)(u32 selector);
+	void (*set_kernel_stack)(u32 selector, u32 esp0);
+	void (*allocate_page)(u32, u32, u32, u32, u32);
+	void (*release_page)(u32, u32);
+	void (*set_pte)(pte_t, pte_t *, unsigned);
+	void (*update_pte)(pte_t *, unsigned);
+	void (*set_linear_mapping)(int, u32, u32, u32);
+	void (*flush_tlb)(int);
+	void (*set_initial_ap_state)(int, int);
+	void (*halt)(void);
+} vmi_ops;
+
+/* XXX move this to alternative.h */
+extern struct paravirt_patch __start_parainstructions[],
+	__stop_parainstructions[];
+
+/*
+ * VMI patching routines.
+ */
+#define MNEM_CALL 0xe8
+#define MNEM_JMP  0xe9
+#define MNEM_RET  0xc3
+
+static char irq_save_disable_callout[] = {
+	MNEM_CALL, 0, 0, 0, 0,
+	MNEM_CALL, 0, 0, 0, 0,
+	MNEM_RET
+};
+#define IRQ_PATCH_INT_MASK 0
+#define IRQ_PATCH_DISABLE  5
+
+static inline void patch_offset(unsigned char *eip, unsigned char *dest)
+{
+        *(unsigned long *)(eip+1) = dest-eip-5;
+}
+
+static unsigned patch_internal(int call, unsigned len, void *insns)
+{
+	u64 reloc;
+	struct vmi_relocation_info *const rel = (struct vmi_relocation_info *)&reloc;
+	reloc = call_vrom_long_func(vmi_rom, get_reloc,	call);
+	switch(rel->type) {
+		case VMI_RELOCATION_CALL_REL:
+			BUG_ON(len < 5);
+			*(char *)insns = MNEM_CALL;
+			patch_offset(insns, rel->eip);
+			return 5;
+
+		case VMI_RELOCATION_JUMP_REL:
+			BUG_ON(len < 5);
+			*(char *)insns = MNEM_JMP;
+			patch_offset(insns, rel->eip);
+			return 5;
+
+		case VMI_RELOCATION_NOP:
+			/* obliterate the whole thing */
+			return 0;
+
+		case VMI_RELOCATION_NONE:
+			/* leave native code in place */
+			break;
+
+		default:
+			BUG();
+	}
+	return len;
+}
+
+/*
+ * Apply patch if appropriate, return length of new instruction
+ * sequence.  The callee does nop padding for us.
+ */
+static unsigned vmi_patch(u8 type, u16 clobbers, void *insns, unsigned len)
+{
+	switch (type) {
+		case PARAVIRT_IRQ_DISABLE:
+			return patch_internal(VMI_CALL_DisableInterrupts, len, insns);
+		case PARAVIRT_IRQ_ENABLE:
+			return patch_internal(VMI_CALL_EnableInterrupts, len, insns);
+		case PARAVIRT_RESTORE_FLAGS:
+			return patch_internal(VMI_CALL_SetInterruptMask, len, insns);
+		case PARAVIRT_SAVE_FLAGS:
+			return patch_internal(VMI_CALL_GetInterruptMask, len, insns);
+        	case PARAVIRT_SAVE_FLAGS_IRQ_DISABLE:
+			if (len >= 10) {
+				patch_internal(VMI_CALL_GetInterruptMask, len, insns);
+				patch_internal(VMI_CALL_DisableInterrupts, len-5, insns+5);
+				return 10;
+			} else {
+				/*
+				 * You bastards didn't leave enough room to
+				 * patch save_flags_irq_disable inline.  Patch
+				 * to a helper
+				 */
+				BUG_ON(len < 5);
+				*(char *)insns = MNEM_CALL;
+				patch_offset(insns, irq_save_disable_callout);
+				return 5;
+			}
+		case PARAVIRT_INTERRUPT_RETURN:
+			return patch_internal(VMI_CALL_IRET, len, insns);
+		case PARAVIRT_STI_SYSEXIT:
+			return patch_internal(VMI_CALL_SYSEXIT, len, insns);
+		default:
+			break;
+	}
+	return len;
+}
+
+/* CPUID has non-C semantics, and paravirt-ops API doesn't match hardware ISA */
+static void vmi_cpuid(unsigned int *eax, unsigned int *ebx,
+                               unsigned int *ecx, unsigned int *edx)
+{
+	int override = 0;
+	if (*eax == 1)
+		override = 1;
+        asm volatile ("call *%6"
+                      : "=a" (*eax),
+                        "=b" (*ebx),
+                        "=c" (*ecx),
+                        "=d" (*edx)
+                      : "0" (*eax), "2" (*ecx), "r" (vmi_ops.cpuid));
+	if (override) {
+		if (disable_pse)
+			*edx &= ~X86_FEATURE_PSE;
+		if (disable_pge)
+			*edx &= ~X86_FEATURE_PGE;
+		if (disable_sep)
+			*edx &= ~X86_FEATURE_SEP;
+		if (disable_tsc)
+			*edx &= ~X86_FEATURE_TSC;
+		if (disable_mtrr)
+			*edx &= ~X86_FEATURE_MTRR;
+	}
+}
+
+static inline void vmi_maybe_load_tls(struct desc_struct *gdt, int nr, struct desc_struct *new)
+{
+	if (gdt[nr].a != new->a || gdt[nr].b != new->b)
+		write_gdt_entry(gdt, nr, new->a, new->b);
+}
+
+static void vmi_load_tls(struct thread_struct *t, unsigned int cpu)
+{
+	struct desc_struct *gdt = get_cpu_gdt_table(cpu);
+	vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 0, &t->tls_array[0]);
+	vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 1, &t->tls_array[1]);
+	vmi_maybe_load_tls(gdt, GDT_ENTRY_TLS_MIN + 2, &t->tls_array[2]);
+}
+
+static void vmi_set_ldt(const void *addr, unsigned entries)
+{
+	unsigned cpu = smp_processor_id();
+	u32 low, high;
+
+	pack_descriptor(&low, &high, (unsigned long)addr,
+			entries * sizeof(struct desc_struct) - 1,
+			DESCTYPE_LDT, 0);
+	write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_LDT, low, high);
+	vmi_ops._set_ldt(entries ? GDT_ENTRY_LDT*sizeof(struct desc_struct) : 0);
+}
+
+static void vmi_set_tr(void)
+{
+	vmi_ops.set_tr(GDT_ENTRY_TSS*sizeof(struct desc_struct));
+}
+
+static void vmi_load_esp0(struct tss_struct *tss,
+				   struct thread_struct *thread)
+{
+	tss->esp0 = thread->esp0;
+
+	/* This can only happen when SEP is enabled, no need to test "SEP"arately */
+	if (unlikely(tss->ss1 != thread->sysenter_cs)) {
+		tss->ss1 = thread->sysenter_cs;
+		wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
+	}
+	vmi_ops.set_kernel_stack(__KERNEL_DS, tss->esp0);
+}
+
+static void vmi_flush_tlb_user(void)
+{
+	vmi_ops.flush_tlb(VMI_FLUSH_TLB);
+}
+
+static void vmi_flush_tlb_kernel(void)
+{
+	vmi_ops.flush_tlb(VMI_FLUSH_TLB | VMI_FLUSH_GLOBAL);
+}
+
+/* Stub to do nothing at all; used for delays and unimplemented calls */
+static void vmi_nop(void)
+{
+}
+
+/* For NO_IDLE_HZ, we stop the clock when halting the kernel */
+#ifdef CONFIG_NO_IDLE_HZ
+static fastcall void vmi_safe_halt(void)
+{
+	int idle = vmi_stop_hz_timer();
+	vmi_ops.halt();
+	if (idle) {
+		local_irq_disable();
+		vmi_account_time_restart_hz_timer();
+		local_irq_enable();
+	}
+}
+#endif
+
+#ifdef CONFIG_DEBUG_PAGE_TYPE
+
+#ifdef CONFIG_X86_PAE
+#define MAX_BOOT_PTS (2048+4+1)
+#else
+#define MAX_BOOT_PTS (1024+1)
+#endif
+
+/*
+ * During boot, mem_map is not yet available in paging_init, so stash
+ * all the boot page allocations here.
+ */
+static struct {
+	u32 pfn;
+	int type;
+} boot_page_allocations[MAX_BOOT_PTS];
+static int num_boot_page_allocations;
+static int boot_allocations_applied;
+
+void vmi_apply_boot_page_allocations(void)
+{
+	int i;
+	BUG_ON(!mem_map);
+	for (i = 0; i < num_boot_page_allocations; i++) {
+		struct page *page = pfn_to_page(boot_page_allocations[i].pfn);
+		page->type = boot_page_allocations[i].type;
+		page->type = boot_page_allocations[i].type &
+				~(VMI_PAGE_ZEROED | VMI_PAGE_CLONE);
+	}
+	boot_allocations_applied = 1;
+}
+
+static void record_page_type(u32 pfn, int type)
+{
+	BUG_ON(num_boot_page_allocations >= MAX_BOOT_PTS);
+	boot_page_allocations[num_boot_page_allocations].pfn = pfn;
+	boot_page_allocations[num_boot_page_allocations].type = type;
+	num_boot_page_allocations++;
+}
+
+static void check_zeroed_page(u32 pfn, int type, struct page *page)
+{
+	u32 *ptr;
+	int i;
+	int limit = PAGE_SIZE / sizeof(int);
+
+	if (page_address(page))
+		ptr = (u32 *)page_address(page);
+	else
+		ptr = (u32 *)__va(pfn << PAGE_SHIFT);
+	/*
+	 * When cloning the root in non-PAE mode, only the userspace
+	 * pdes need to be zeroed.
+	 */
+	if (type & VMI_PAGE_CLONE)
+		limit = USER_PTRS_PER_PGD;
+	for (i = 0; i < limit; i++)
+		BUG_ON(ptr[i]);
+}
+
+/*
+ * We stash the page type into struct page so we can verify the page
+ * types are used properly.
+ */
+static void vmi_set_page_type(u32 pfn, int type)
+{
+	/* PAE can have multiple roots per page - don't track */
+	if (PTRS_PER_PMD > 1 && (type & VMI_PAGE_PDP))
+		return;
+
+	if (boot_allocations_applied) {
+		struct page *page = pfn_to_page(pfn);
+		if (type != VMI_PAGE_NORMAL)
+			BUG_ON(page->type);
+		else
+			BUG_ON(page->type == VMI_PAGE_NORMAL);
+		page->type = type & ~(VMI_PAGE_ZEROED | VMI_PAGE_CLONE);
+		if (type & VMI_PAGE_ZEROED)
+			check_zeroed_page(pfn, type, page);
+	} else {
+		record_page_type(pfn, type);
+	}
+}
+
+static void vmi_check_page_type(u32 pfn, int type)
+{
+	/* PAE can have multiple roots per page - skip checks */
+	if (PTRS_PER_PMD > 1 && (type & VMI_PAGE_PDP))
+		return;
+
+	type &= ~(VMI_PAGE_ZEROED | VMI_PAGE_CLONE);
+	if (boot_allocations_applied) {
+		struct page *page = pfn_to_page(pfn);
+		BUG_ON((page->type ^ type) & VMI_PAGE_PAE);
+		BUG_ON(type == VMI_PAGE_NORMAL && page->type);
+		BUG_ON((type & page->type) == 0);
+	}
+}
+#else
+#define vmi_set_page_type(p,t) do { } while (0)
+#define vmi_check_page_type(p,t) do { } while (0)
+#endif
+
+static void vmi_allocate_pt(u32 pfn)
+{
+	vmi_set_page_type(pfn, VMI_PAGE_L1);
+	vmi_ops.allocate_page(pfn, VMI_PAGE_L1, 0, 0, 0);
+}
+
+static void vmi_allocate_pd(u32 pfn)
+{
+ 	/*
+	 * This call comes in very early, before mem_map is setup.
+	 * It is called only for swapper_pg_dir, which already has
+	 * data on it.
+	 */
+ 	vmi_set_page_type(pfn, VMI_PAGE_L2);
+	vmi_ops.allocate_page(pfn, VMI_PAGE_L2, 0, 0, 0);
+}
+
+static void vmi_allocate_pd_clone(u32 pfn, u32 clonepfn, u32 start, u32 count)
+{
+ 	vmi_set_page_type(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE);
+	vmi_check_page_type(clonepfn, VMI_PAGE_L2);
+	vmi_ops.allocate_page(pfn, VMI_PAGE_L2 | VMI_PAGE_CLONE, clonepfn, start, count);
+}
+
+static void vmi_release_pt(u32 pfn)
+{
+	vmi_ops.release_page(pfn, VMI_PAGE_L1);
+	vmi_set_page_type(pfn, VMI_PAGE_NORMAL);
+}
+
+static void vmi_release_pd(u32 pfn)
+{
+	vmi_ops.release_page(pfn, VMI_PAGE_L2);
+	vmi_set_page_type(pfn, VMI_PAGE_NORMAL);
+}
+
+/*
+ * Helper macros for MMU update flags.  We can defer updates until a flush
+ * or page invalidation only if the update is to the current address space
+ * (otherwise, there is no flush).  We must check against init_mm, since
+ * this could be a kernel update, which usually passes init_mm, although
+ * sometimes this check can be skipped if we know the particular function
+ * is only called on user mode PTEs.  We could change the kernel to pass
+ * current->active_mm here, but in particular, I was unsure if changing
+ * mm/highmem.c to do this would still be correct on other architectures.
+ */
+#define is_current_as(mm, mustbeuser) ((mm) == current->active_mm ||    \
+                                       (!mustbeuser && (mm) == &init_mm))
+#define vmi_flags_addr(mm, addr, level, user)                           \
+        ((level) | (is_current_as(mm, user) ?                           \
+                (VMI_PAGE_CURRENT_AS | ((addr) & VMI_PAGE_VA_MASK)) : 0))
+#define vmi_flags_addr_defer(mm, addr, level, user)                     \
+        ((level) | (is_current_as(mm, user) ?                           \
+                (VMI_PAGE_DEFER | VMI_PAGE_CURRENT_AS | ((addr) & VMI_PAGE_VA_MASK)) : 0))
+
+static void vmi_update_pte(struct mm_struct *mm, u32 addr, pte_t *ptep)
+{
+	vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
+	vmi_ops.update_pte(ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
+}
+
+static void vmi_update_pte_defer(struct mm_struct *mm, u32 addr, pte_t *ptep)
+{
+	vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
+	vmi_ops.update_pte(ptep, vmi_flags_addr_defer(mm, addr, VMI_PAGE_PT, 0));
+}
+
+static void vmi_set_pte(pte_t *ptep, pte_t pte)
+{
+	/* XXX because of set_pmd_pte, this can be called on PT or PD layers */
+	vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE | VMI_PAGE_PD);
+	vmi_ops.set_pte(pte, ptep, VMI_PAGE_PT);
+}
+
+static void vmi_set_pte_at(struct mm_struct *mm, u32 addr, pte_t *ptep, pte_t pte)
+{
+	vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
+	vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
+}
+
+static void vmi_set_pmd(pmd_t *pmdp, pmd_t pmdval)
+{
+#ifdef CONFIG_X86_PAE
+	const pte_t pte = { pmdval.pmd, pmdval.pmd >> 32 };
+	vmi_check_page_type(__pa(pmdp) >> PAGE_SHIFT, VMI_PAGE_PMD);
+#else
+	const pte_t pte = { pmdval.pud.pgd.pgd };
+	vmi_check_page_type(__pa(pmdp) >> PAGE_SHIFT, VMI_PAGE_PGD);
+#endif
+	vmi_ops.set_pte(pte, (pte_t *)pmdp, VMI_PAGE_PD);
+}
+
+#ifdef CONFIG_X86_PAE
+
+static void vmi_set_pte_atomic(pte_t *ptep, pte_t pteval)
+{
+	/*
+	 * XXX This is called from set_pmd_pte, but at both PT
+	 * and PD layers so the VMI_PAGE_PT flag is wrong.  But
+	 * it is only called for large page mapping changes,
+	 * the Xen backend, doesn't support large pages, and the
+	 * ESX backend doesn't depend on the flag.
+	 */
+	set_64bit((unsigned long long *)ptep,pte_val(pteval));
+	vmi_ops.update_pte(ptep, VMI_PAGE_PT);
+}
+
+static void vmi_set_pte_present(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte)
+{
+	vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
+	vmi_ops.set_pte(pte, ptep, vmi_flags_addr_defer(mm, addr, VMI_PAGE_PT, 1));
+}
+
+static void vmi_set_pud(pud_t *pudp, pud_t pudval)
+{
+	/* Um, eww */
+	const pte_t pte = { pudval.pgd.pgd, pudval.pgd.pgd >> 32 };
+	vmi_check_page_type(__pa(pudp) >> PAGE_SHIFT, VMI_PAGE_PGD);
+	vmi_ops.set_pte(pte, (pte_t *)pudp, VMI_PAGE_PDP);
+}
+
+static void vmi_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+{
+	const pte_t pte = { 0 };
+	vmi_check_page_type(__pa(ptep) >> PAGE_SHIFT, VMI_PAGE_PTE);
+	vmi_ops.set_pte(pte, ptep, vmi_flags_addr(mm, addr, VMI_PAGE_PT, 0));
+}
+
+void vmi_pmd_clear(pmd_t *pmd)
+{
+	const pte_t pte = { 0 };
+	vmi_check_page_type(__pa(pmd) >> PAGE_SHIFT, VMI_PAGE_PMD);
+	vmi_ops.set_pte(pte, (pte_t *)pmd, VMI_PAGE_PD);
+}
+#endif
+
+#ifdef CONFIG_SMP
+struct vmi_ap_state ap;
+extern void setup_pda(void);
+
+static void __init /* XXX cpu hotplug */
+vmi_startup_ipi_hook(int phys_apicid, unsigned long start_eip,
+		     unsigned long start_esp)
+{
+	/* Default everything to zero.  This is fine for most GPRs. */
+	memset(&ap, 0, sizeof(struct vmi_ap_state));
+
+	ap.gdtr_limit = GDT_SIZE - 1;
+	ap.gdtr_base = (unsigned long) get_cpu_gdt_table(phys_apicid);
+
+	ap.idtr_limit = IDT_ENTRIES * 8 - 1;
+	ap.idtr_base = (unsigned long) idt_table;
+
+	ap.ldtr = 0;
+
+	ap.cs = __KERNEL_CS;
+	ap.eip = (unsigned long) start_eip;
+	ap.ss = __KERNEL_DS;
+	ap.esp = (unsigned long) start_esp;
+
+	ap.ds = __USER_DS;
+	ap.es = __USER_DS;
+	ap.fs = __KERNEL_PDA;
+	ap.gs = 0;
+
+	ap.eflags = 0;
+
+	setup_pda();
+
+#ifdef CONFIG_X86_PAE
+	/* efer should match BSP efer. */
+	if (cpu_has_nx) {
+		unsigned l, h;
+		rdmsr(MSR_EFER, l, h);
+		ap.efer = (unsigned long long) h << 32 | l;
+	}
+#endif
+
+	ap.cr3 = __pa(swapper_pg_dir);
+	/* Protected mode, paging, AM, WP, NE, MP. */
+	ap.cr0 = 0x80050023;
+	ap.cr4 = mmu_cr4_features;
+	vmi_ops.set_initial_ap_state(__pa(&ap), phys_apicid);
+}
+#endif
+
+static inline int __init check_vmi_rom(struct vrom_header *rom)
+{
+	struct pci_header *pci;
+	struct pnp_header *pnp;
+	const char *manufacturer = "UNKNOWN";
+	const char *product = "UNKNOWN";
+	const char *license = "unspecified";
+
+	if (rom->rom_signature != 0xaa55)
+		return 0;
+	if (rom->vrom_signature != VMI_SIGNATURE)
+		return 0;
+	if (rom->api_version_maj != VMI_API_REV_MAJOR ||
+	    rom->api_version_min+1 < VMI_API_REV_MINOR+1) {
+		printk(KERN_WARNING "VMI: Found mismatched rom version %d.%d\n",
+				rom->api_version_maj,
+				rom->api_version_min);
+		return 0;
+	}
+
+	/*
+	 * Relying on the VMI_SIGNATURE field is not 100% safe, so check
+	 * the PCI header and device type to make sure this is really a
+	 * VMI device.
+	 */
+	if (!rom->pci_header_offs) {
+		printk(KERN_WARNING "VMI: ROM does not contain PCI header.\n");
+		return 0;
+	}
+
+	pci = (struct pci_header *)((char *)rom+rom->pci_header_offs);
+	if (pci->vendorID != PCI_VENDOR_ID_VMWARE ||
+	    pci->deviceID != PCI_DEVICE_ID_VMWARE_VMI) {
+		/* Allow it to run... anyways, but warn */
+		printk(KERN_WARNING "VMI: ROM from unknown manufacturer\n");
+	}
+
+	if (rom->pnp_header_offs) {
+		pnp = (struct pnp_header *)((char *)rom+rom->pnp_header_offs);
+		if (pnp->manufacturer_offset)
+			manufacturer = (const char *)rom+pnp->manufacturer_offset;
+		if (pnp->product_offset)
+			product = (const char *)rom+pnp->product_offset;
+	}
+
+	if (rom->license_offs)
+		license = (char *)rom+rom->license_offs;
+
+	printk(KERN_INFO "VMI: Found %s %s, API version %d.%d, ROM version %d.%d\n",
+		manufacturer, product,
+		rom->api_version_maj, rom->api_version_min,
+		pci->rom_version_maj, pci->rom_version_min);
+
+        license_gplok = license_is_gpl_compatible(license);
+        if (!license_gplok) {
+                printk(KERN_WARNING "VMI: ROM license '%s' taints kernel... "
+		       "inlining disabled\n",
+                       license);
+                add_taint(TAINT_PROPRIETARY_MODULE);
+        }
+	return 1;
+}
+
+/*
+ * Probe for the VMI option ROM
+ */
+static inline int __init probe_vmi_rom(void)
+{
+	unsigned long base;
+
+	/* VMI ROM is in option ROM area, check signature */
+	for (base = 0xC0000; base < 0xE0000; base += 2048) {
+		struct vrom_header *romstart;
+		romstart = (struct vrom_header *)isa_bus_to_virt(base);
+		if (check_vmi_rom(romstart)) {
+			vmi_rom = romstart;
+			return 1;
+		}
+	}
+	return 0;
+}
+
+/*
+ * VMI setup common to all processors
+ */
+void vmi_bringup(void)
+{
+ 	/* We must establish the lowmem mapping for MMU ops to work */
+	if (vmi_rom)
+		vmi_ops.set_linear_mapping(0, __PAGE_OFFSET, max_low_pfn, 0);
+}
+
+/*
+ * Return a pointer to the VMI function or a NOP stub
+ */
+static void *vmi_get_function(int vmicall)
+{
+	u64 reloc;
+	const struct vmi_relocation_info *rel = (struct vmi_relocation_info *)&reloc;
+	reloc = call_vrom_long_func(vmi_rom, get_reloc,	vmicall);
+	BUG_ON(rel->type == VMI_RELOCATION_JUMP_REL);
+	if (rel->type == VMI_RELOCATION_CALL_REL)
+		return (void *)rel->eip;
+	else
+		return (void *)vmi_nop;
+}
+
+/*
+ * Helper macro for making the VMI paravirt-ops fill code readable.
+ * For unimplemented operations, fall back to default.
+ */
+#define para_fill(opname, vmicall)				\
+do {								\
+	reloc = call_vrom_long_func(vmi_rom, get_reloc,		\
+				    VMI_CALL_##vmicall);	\
+	if (rel->type != VMI_RELOCATION_NONE) {			\
+		BUG_ON(rel->type != VMI_RELOCATION_CALL_REL);	\
+		paravirt_ops.opname = (void *)rel->eip;		\
+	}							\
+} while (0)
+
+/*
+ * Activate the VMI interface and switch into paravirtualized mode
+ */
+static inline int __init activate_vmi(void)
+{
+	short kernel_cs;
+	u64 reloc;
+	const struct vmi_relocation_info *rel = (struct vmi_relocation_info *)&reloc;
+
+	if (call_vrom_func(vmi_rom, vmi_init) != 0) {
+		printk(KERN_ERR "VMI ROM failed to initialize!");
+		return 0;
+	}
+	savesegment(cs, kernel_cs);
+
+	paravirt_ops.paravirt_enabled = 1;
+	paravirt_ops.kernel_rpl = kernel_cs & SEGMENT_RPL_MASK;
+
+	paravirt_ops.patch = vmi_patch;
+	paravirt_ops.name = "vmi";
+
+	/*
+	 * Many of these operations are ABI compatible with VMI.
+	 * This means we can fill in the paravirt-ops with direct
+	 * pointers into the VMI ROM.  If the calling convention for
+	 * these operations changes, this code needs to be updated.
+	 *
+	 * Exceptions
+	 *  CPUID paravirt-op uses pointers, not the native ISA
+	 *  halt has no VMI equivalent; all VMI halts are "safe"
+	 *  no MSR support yet - just trap and emulate.  VMI uses the
+	 *    same ABI as the native ISA, but Linux wants exceptions
+	 *    from bogus MSR read / write handled
+	 *  rdpmc is not yet used in Linux
+	 */
+
+	/* CPUID is special, so very special */
+	reloc = call_vrom_long_func(vmi_rom, get_reloc,	VMI_CALL_CPUID);
+	if (rel->type != VMI_RELOCATION_NONE) {
+		BUG_ON(rel->type != VMI_RELOCATION_CALL_REL);
+		vmi_ops.cpuid = (void *)rel->eip;
+		paravirt_ops.cpuid = vmi_cpuid;
+	}
+
+	para_fill(clts, CLTS);
+	para_fill(get_debugreg, GetDR);
+	para_fill(set_debugreg, SetDR);
+	para_fill(read_cr0, GetCR0);
+	para_fill(read_cr2, GetCR2);
+	para_fill(read_cr3, GetCR3);
+	para_fill(read_cr4, GetCR4);
+	para_fill(write_cr0, SetCR0);
+	para_fill(write_cr2, SetCR2);
+	para_fill(write_cr3, SetCR3);
+	para_fill(write_cr4, SetCR4);
+	para_fill(save_fl, GetInterruptMask);
+	para_fill(restore_fl, SetInterruptMask);
+	para_fill(irq_disable, DisableInterrupts);
+	para_fill(irq_enable, EnableInterrupts);
+	/* irq_save_disable !!! sheer pain */
+	patch_offset(&irq_save_disable_callout[IRQ_PATCH_INT_MASK],
+		     (char *)paravirt_ops.save_fl);
+	patch_offset(&irq_save_disable_callout[IRQ_PATCH_DISABLE],
+		     (char *)paravirt_ops.irq_disable);
+#ifndef CONFIG_NO_IDLE_HZ
+	para_fill(safe_halt, Halt);
+#else
+	vmi_ops.halt = vmi_get_function(VMI_CALL_Halt);
+	paravirt_ops.safe_halt = vmi_safe_halt;
+#endif
+	para_fill(wbinvd, WBINVD);
+	/* paravirt_ops.read_msr = vmi_rdmsr */
+	/* paravirt_ops.write_msr = vmi_wrmsr */
+	para_fill(read_tsc, RDTSC);
+	/* paravirt_ops.rdpmc = vmi_rdpmc */
+
+	/* TR interface doesn't pass TR value */
+	reloc = call_vrom_long_func(vmi_rom, get_reloc,	VMI_CALL_SetTR);
+	if (rel->type != VMI_RELOCATION_NONE) {
+		BUG_ON(rel->type != VMI_RELOCATION_CALL_REL);
+		vmi_ops.set_tr = (void *)rel->eip;
+		paravirt_ops.load_tr_desc = vmi_set_tr;
+	}
+
+	/* LDT is special, too */
+	reloc = call_vrom_long_func(vmi_rom, get_reloc,	VMI_CALL_SetLDT);
+	if (rel->type != VMI_RELOCATION_NONE) {
+		BUG_ON(rel->type != VMI_RELOCATION_CALL_REL);
+		vmi_ops._set_ldt = (void *)rel->eip;
+		paravirt_ops.set_ldt = vmi_set_ldt;
+	}
+
+	para_fill(load_gdt, SetGDT);
+	para_fill(load_idt, SetIDT);
+	para_fill(store_gdt, GetGDT);
+	para_fill(store_idt, GetIDT);
+	para_fill(store_tr, GetTR);
+	paravirt_ops.load_tls = vmi_load_tls;
+	para_fill(write_ldt_entry, WriteLDTEntry);
+	para_fill(write_gdt_entry, WriteGDTEntry);
+	para_fill(write_idt_entry, WriteIDTEntry);
+	reloc = call_vrom_long_func(vmi_rom, get_reloc,
+				    VMI_CALL_UpdateKernelStack);
+	if (rel->type != VMI_RELOCATION_NONE) {
+		BUG_ON(rel->type != VMI_RELOCATION_CALL_REL);
+		vmi_ops.set_kernel_stack = (void *)rel->eip;
+		paravirt_ops.load_esp0 = vmi_load_esp0;
+	}
+
+	para_fill(set_iopl_mask, SetIOPLMask);
+	paravirt_ops.io_delay = (void *)vmi_nop;
+	if (!disable_nodelay) {
+		paravirt_ops.const_udelay = (void *)vmi_nop;
+	}
+
+	para_fill(set_lazy_mode, SetLazyMode);
+
+	reloc = call_vrom_long_func(vmi_rom, get_reloc, VMI_CALL_FlushTLB);
+	if (rel->type != VMI_RELOCATION_NONE) {
+		vmi_ops.flush_tlb = (void *)rel->eip;
+		paravirt_ops.flush_tlb_user = vmi_flush_tlb_user;
+		paravirt_ops.flush_tlb_kernel = vmi_flush_tlb_kernel;
+	}
+	para_fill(flush_tlb_single, InvalPage);
+
+	/*
+	 * Until a standard flag format can be agreed on, we need to
+	 * implement these as wrappers in Linux.  Get the VMI ROM
+	 * function pointers for the two backend calls.
+	 */
+#ifdef CONFIG_X86_PAE
+	vmi_ops.set_pte = vmi_get_function(VMI_CALL_SetPxELong);
+	vmi_ops.update_pte = vmi_get_function(VMI_CALL_UpdatePxELong);
+#else
+	vmi_ops.set_pte = vmi_get_function(VMI_CALL_SetPxE);
+	vmi_ops.update_pte = vmi_get_function(VMI_CALL_UpdatePxE);
+#endif
+	vmi_ops.set_linear_mapping = vmi_get_function(VMI_CALL_SetLinearMapping);
+	vmi_ops.allocate_page = vmi_get_function(VMI_CALL_AllocatePage);
+	vmi_ops.release_page = vmi_get_function(VMI_CALL_ReleasePage);
+
+	paravirt_ops.alloc_pt = vmi_allocate_pt;
+	paravirt_ops.alloc_pd = vmi_allocate_pd;
+	paravirt_ops.alloc_pd_clone = vmi_allocate_pd_clone;
+	paravirt_ops.release_pt = vmi_release_pt;
+	paravirt_ops.release_pd = vmi_release_pd;
+	paravirt_ops.set_pte = vmi_set_pte;
+	paravirt_ops.set_pte_at = vmi_set_pte_at;
+	paravirt_ops.set_pmd = vmi_set_pmd;
+	paravirt_ops.pte_update = vmi_update_pte;
+	paravirt_ops.pte_update_defer = vmi_update_pte_defer;
+#ifdef CONFIG_X86_PAE
+	paravirt_ops.set_pte_atomic = vmi_set_pte_atomic;
+	paravirt_ops.set_pte_present = vmi_set_pte_present;
+	paravirt_ops.set_pud = vmi_set_pud;
+	paravirt_ops.pte_clear = vmi_pte_clear;
+	paravirt_ops.pmd_clear = vmi_pmd_clear;
+#endif
+	/*
+	 * These MUST always be patched.  Don't support indirect jumps
+	 * through these operations, as the VMI interface may use either
+	 * a jump or a call to get to these operations, depending on
+	 * the backend.  They are performance critical anyway, so requiring
+	 * a patch is not a big problem.
+	 */
+	paravirt_ops.irq_enable_sysexit = (void *)0xfeedbab0;
+	paravirt_ops.iret = (void *)0xbadbab0;
+
+#ifdef CONFIG_SMP
+	paravirt_ops.startup_ipi_hook = vmi_startup_ipi_hook;
+	vmi_ops.set_initial_ap_state = vmi_get_function(VMI_CALL_SetInitialAPState);
+#endif
+
+#ifdef CONFIG_X86_LOCAL_APIC
+	paravirt_ops.apic_read = vmi_get_function(VMI_CALL_APICRead);
+	paravirt_ops.apic_write = vmi_get_function(VMI_CALL_APICWrite);
+	paravirt_ops.apic_write_atomic = vmi_get_function(VMI_CALL_APICWrite);
+#endif
+
+	/*
+	 * Check for VMI timer functionality by probing for a cycle frequency method
+	 */
+	reloc = call_vrom_long_func(vmi_rom, get_reloc, VMI_CALL_GetCycleFrequency);
+	if (rel->type != VMI_RELOCATION_NONE) {
+		vmi_timer_ops.get_cycle_frequency = (void *)rel->eip;
+		vmi_timer_ops.get_cycle_counter =
+			vmi_get_function(VMI_CALL_GetCycleCounter);
+		vmi_timer_ops.get_wallclock =
+			vmi_get_function(VMI_CALL_GetWallclockTime);
+		vmi_timer_ops.wallclock_updated =
+			vmi_get_function(VMI_CALL_WallclockUpdated);
+		vmi_timer_ops.set_alarm = vmi_get_function(VMI_CALL_SetAlarm);
+		vmi_timer_ops.cancel_alarm =
+			 vmi_get_function(VMI_CALL_CancelAlarm);
+		paravirt_ops.time_init = vmi_time_init;
+		paravirt_ops.get_wallclock = vmi_get_wallclock;
+		paravirt_ops.set_wallclock = vmi_set_wallclock;
+#ifdef CONFIG_X86_LOCAL_APIC
+		paravirt_ops.setup_boot_clock = vmi_timer_setup_boot_alarm;
+		paravirt_ops.setup_secondary_clock = vmi_timer_setup_secondary_alarm;
+#endif
+		custom_sched_clock = vmi_sched_clock;
+	}
+
+	/*
+	 * Alternative instruction rewriting doesn't happen soon enough
+	 * to convert VMI_IRET to a call instead of a jump; so we have
+	 * to do this before IRQs get reenabled.  Fortunately, it is
+	 * idempotent.
+	 */
+	apply_paravirt(__start_parainstructions, __stop_parainstructions);
+
+	vmi_bringup();
+
+	return 1;
+}
+
+#undef para_fill
+
+void __init vmi_init(void)
+{
+	unsigned long flags;
+
+	if (!vmi_rom)
+		probe_vmi_rom();
+	else
+		check_vmi_rom(vmi_rom);
+
+	/* In case probing for or validating the ROM failed, basil */
+	if (!vmi_rom)
+		return;
+
+	reserve_top_address(-vmi_rom->virtual_top);
+
+	local_irq_save(flags);
+	activate_vmi();
+#ifdef CONFIG_SMP
+	no_timer_check = 1;
+#endif
+	local_irq_restore(flags & X86_EFLAGS_IF);
+}
+
+static int __init parse_vmi(char *arg)
+{
+	if (!arg)
+		return -EINVAL;
+
+	if (!strcmp(arg, "disable_nodelay"))
+		disable_nodelay = 1;
+	else if (!strcmp(arg, "disable_pge")) {
+		clear_bit(X86_FEATURE_PGE, boot_cpu_data.x86_capability);
+		disable_pge = 1;
+	} else if (!strcmp(arg, "disable_pse")) {
+		clear_bit(X86_FEATURE_PSE, boot_cpu_data.x86_capability);
+		disable_pse = 1;
+	} else if (!strcmp(arg, "disable_sep")) {
+		clear_bit(X86_FEATURE_SEP, boot_cpu_data.x86_capability);
+		disable_sep = 1;
+	} else if (!strcmp(arg, "disable_tsc")) {
+		clear_bit(X86_FEATURE_TSC, boot_cpu_data.x86_capability);
+		disable_tsc = 1;
+	} else if (!strcmp(arg, "disable_mtrr")) {
+		clear_bit(X86_FEATURE_MTRR, boot_cpu_data.x86_capability);
+		disable_mtrr = 1;
+	}
+	return 0;
+}
+
+early_param("vmi", parse_vmi);

arch/i386/kernel/vmitime.c

@@ -0,0 +1,499 @@
+/*
+ * VMI paravirtual timer support routines.
+ *
+ * Copyright (C) 2005, VMware, Inc.
+ *
+ * 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, GOOD TITLE or
+ * NON INFRINGEMENT.  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., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send feedback to dhecht@vmware.com
+ *
+ */
+
+/*
+ * Portions of this code from arch/i386/kernel/timers/timer_tsc.c.
+ * Portions of the CONFIG_NO_IDLE_HZ code from arch/s390/kernel/time.c.
+ * See comments there for proper credits.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/jiffies.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/rcupdate.h>
+#include <linux/clocksource.h>
+
+#include <asm/timer.h>
+#include <asm/io.h>
+#include <asm/apic.h>
+#include <asm/div64.h>
+#include <asm/timer.h>
+#include <asm/desc.h>
+
+#include <asm/vmi.h>
+#include <asm/vmi_time.h>
+
+#include <mach_timer.h>
+#include <io_ports.h>
+
+#ifdef CONFIG_X86_LOCAL_APIC
+#define VMI_ALARM_WIRING VMI_ALARM_WIRED_LVTT
+#else
+#define VMI_ALARM_WIRING VMI_ALARM_WIRED_IRQ0
+#endif
+
+/* Cached VMI operations */
+struct vmi_timer_ops vmi_timer_ops;
+
+#ifdef CONFIG_NO_IDLE_HZ
+
+/* /proc/sys/kernel/hz_timer state. */
+int sysctl_hz_timer;
+
+/* Some stats */
+static DEFINE_PER_CPU(unsigned long, vmi_idle_no_hz_irqs);
+static DEFINE_PER_CPU(unsigned long, vmi_idle_no_hz_jiffies);
+static DEFINE_PER_CPU(unsigned long, idle_start_jiffies);
+
+#endif /* CONFIG_NO_IDLE_HZ */
+
+/* Number of alarms per second. By default this is CONFIG_VMI_ALARM_HZ. */
+static int alarm_hz = CONFIG_VMI_ALARM_HZ;
+
+/* Cache of the value get_cycle_frequency / HZ. */
+static signed long long cycles_per_jiffy;
+
+/* Cache of the value get_cycle_frequency / alarm_hz. */
+static signed long long cycles_per_alarm;
+
+/* The number of cycles accounted for by the 'jiffies'/'xtime' count.
+ * Protected by xtime_lock. */
+static unsigned long long real_cycles_accounted_system;
+
+/* The number of cycles accounted for by update_process_times(), per cpu. */
+static DEFINE_PER_CPU(unsigned long long, process_times_cycles_accounted_cpu);
+
+/* The number of stolen cycles accounted, per cpu. */
+static DEFINE_PER_CPU(unsigned long long, stolen_cycles_accounted_cpu);
+
+/* Clock source. */
+static cycle_t read_real_cycles(void)
+{
+	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+}
+
+static cycle_t read_available_cycles(void)
+{
+	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_AVAILABLE);
+}
+
+#if 0
+static cycle_t read_stolen_cycles(void)
+{
+	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_STOLEN);
+}
+#endif  /*  0  */
+
+static struct clocksource clocksource_vmi = {
+	.name			= "vmi-timer",
+	.rating			= 450,
+	.read			= read_real_cycles,
+	.mask			= CLOCKSOURCE_MASK(64),
+	.mult			= 0, /* to be set */
+	.shift			= 22,
+	.flags			= CLOCK_SOURCE_IS_CONTINUOUS,
+};
+
+
+/* Timer interrupt handler. */
+static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id);
+
+static struct irqaction vmi_timer_irq  = {
+	vmi_timer_interrupt,
+	SA_INTERRUPT,
+	CPU_MASK_NONE,
+	"VMI-alarm",
+	NULL,
+	NULL
+};
+
+/* Alarm rate */
+static int __init vmi_timer_alarm_rate_setup(char* str)
+{
+	int alarm_rate;
+	if (get_option(&str, &alarm_rate) == 1 && alarm_rate > 0) {
+		alarm_hz = alarm_rate;
+		printk(KERN_WARNING "VMI timer alarm HZ set to %d\n", alarm_hz);
+	}
+	return 1;
+}
+__setup("vmi_timer_alarm_hz=", vmi_timer_alarm_rate_setup);
+
+
+/* Initialization */
+static void vmi_get_wallclock_ts(struct timespec *ts)
+{
+	unsigned long long wallclock;
+	wallclock = vmi_timer_ops.get_wallclock(); // nsec units
+	ts->tv_nsec = do_div(wallclock, 1000000000);
+	ts->tv_sec = wallclock;
+}
+
+static void update_xtime_from_wallclock(void)
+{
+	struct timespec ts;
+	vmi_get_wallclock_ts(&ts);
+	do_settimeofday(&ts);
+}
+
+unsigned long vmi_get_wallclock(void)
+{
+	struct timespec ts;
+	vmi_get_wallclock_ts(&ts);
+	return ts.tv_sec;
+}
+
+int vmi_set_wallclock(unsigned long now)
+{
+	return -1;
+}
+
+unsigned long long vmi_sched_clock(void)
+{
+	return read_available_cycles();
+}
+
+void __init vmi_time_init(void)
+{
+	unsigned long long cycles_per_sec, cycles_per_msec;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	setup_irq(0, &vmi_timer_irq);
+#ifdef CONFIG_X86_LOCAL_APIC
+	set_intr_gate(LOCAL_TIMER_VECTOR, apic_vmi_timer_interrupt);
+#endif
+
+	no_sync_cmos_clock = 1;
+
+	vmi_get_wallclock_ts(&xtime);
+	set_normalized_timespec(&wall_to_monotonic,
+		-xtime.tv_sec, -xtime.tv_nsec);
+
+	real_cycles_accounted_system = read_real_cycles();
+	update_xtime_from_wallclock();
+	per_cpu(process_times_cycles_accounted_cpu, 0) = read_available_cycles();
+
+	cycles_per_sec = vmi_timer_ops.get_cycle_frequency();
+
+	cycles_per_jiffy = cycles_per_sec;
+	(void)do_div(cycles_per_jiffy, HZ);
+	cycles_per_alarm = cycles_per_sec;
+	(void)do_div(cycles_per_alarm, alarm_hz);
+	cycles_per_msec = cycles_per_sec;
+	(void)do_div(cycles_per_msec, 1000);
+	cpu_khz = cycles_per_msec;
+
+	printk(KERN_WARNING "VMI timer cycles/sec = %llu ; cycles/jiffy = %llu ;"
+	       "cycles/alarm = %llu\n", cycles_per_sec, cycles_per_jiffy,
+	       cycles_per_alarm);
+
+	clocksource_vmi.mult = clocksource_khz2mult(cycles_per_msec,
+						    clocksource_vmi.shift);
+	if (clocksource_register(&clocksource_vmi))
+		printk(KERN_WARNING "Error registering VMITIME clocksource.");
+
+	/* Disable PIT. */
+	outb_p(0x3a, PIT_MODE); /* binary, mode 5, LSB/MSB, ch 0 */
+
+	/* schedule the alarm. do this in phase with process_times_cycles_accounted_cpu
+	 * reduce the latency calling update_process_times. */
+	vmi_timer_ops.set_alarm(
+		      VMI_ALARM_WIRED_IRQ0 | VMI_ALARM_IS_PERIODIC | VMI_CYCLES_AVAILABLE,
+		      per_cpu(process_times_cycles_accounted_cpu, 0) + cycles_per_alarm,
+		      cycles_per_alarm);
+
+	local_irq_restore(flags);
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+void __init vmi_timer_setup_boot_alarm(void)
+{
+	local_irq_disable();
+
+	/* Route the interrupt to the correct vector. */
+	apic_write_around(APIC_LVTT, LOCAL_TIMER_VECTOR);
+
+	/* Cancel the IRQ0 wired alarm, and setup the LVTT alarm. */
+	vmi_timer_ops.cancel_alarm(VMI_CYCLES_AVAILABLE);
+	vmi_timer_ops.set_alarm(
+		      VMI_ALARM_WIRED_LVTT | VMI_ALARM_IS_PERIODIC | VMI_CYCLES_AVAILABLE,
+		      per_cpu(process_times_cycles_accounted_cpu, 0) + cycles_per_alarm,
+		      cycles_per_alarm);
+	local_irq_enable();
+}
+
+/* Initialize the time accounting variables for an AP on an SMP system.
+ * Also, set the local alarm for the AP. */
+void __init vmi_timer_setup_secondary_alarm(void)
+{
+	int cpu = smp_processor_id();
+
+	/* Route the interrupt to the correct vector. */
+	apic_write_around(APIC_LVTT, LOCAL_TIMER_VECTOR);
+
+	per_cpu(process_times_cycles_accounted_cpu, cpu) = read_available_cycles();
+
+	vmi_timer_ops.set_alarm(
+		      VMI_ALARM_WIRED_LVTT | VMI_ALARM_IS_PERIODIC | VMI_CYCLES_AVAILABLE,
+		      per_cpu(process_times_cycles_accounted_cpu, cpu) + cycles_per_alarm,
+		      cycles_per_alarm);
+}
+
+#endif
+
+/* Update system wide (real) time accounting (e.g. jiffies, xtime). */
+static void vmi_account_real_cycles(unsigned long long cur_real_cycles)
+{
+	long long cycles_not_accounted;
+
+	write_seqlock(&xtime_lock);
+
+	cycles_not_accounted = cur_real_cycles - real_cycles_accounted_system;
+	while (cycles_not_accounted >= cycles_per_jiffy) {
+		/* systems wide jiffies and wallclock. */
+		do_timer(1);
+
+		cycles_not_accounted -= cycles_per_jiffy;
+		real_cycles_accounted_system += cycles_per_jiffy;
+	}
+
+	if (vmi_timer_ops.wallclock_updated())
+		update_xtime_from_wallclock();
+
+	write_sequnlock(&xtime_lock);
+}
+
+/* Update per-cpu process times. */
+static void vmi_account_process_times_cycles(struct pt_regs *regs, int cpu,
+					     unsigned long long cur_process_times_cycles)
+{
+	long long cycles_not_accounted;
+	cycles_not_accounted = cur_process_times_cycles -
+		per_cpu(process_times_cycles_accounted_cpu, cpu);
+
+	while (cycles_not_accounted >= cycles_per_jiffy) {
+		/* Account time to the current process.  This includes
+		 * calling into the scheduler to decrement the timeslice
+		 * and possibly reschedule.*/
+		update_process_times(user_mode(regs));
+		/* XXX handle /proc/profile multiplier.  */
+		profile_tick(CPU_PROFILING);
+
+		cycles_not_accounted -= cycles_per_jiffy;
+		per_cpu(process_times_cycles_accounted_cpu, cpu) += cycles_per_jiffy;
+	}
+}
+
+#ifdef CONFIG_NO_IDLE_HZ
+/* Update per-cpu idle times.  Used when a no-hz halt is ended. */
+static void vmi_account_no_hz_idle_cycles(int cpu,
+					  unsigned long long cur_process_times_cycles)
+{
+	long long cycles_not_accounted;
+	unsigned long no_idle_hz_jiffies = 0;
+
+	cycles_not_accounted = cur_process_times_cycles -
+		per_cpu(process_times_cycles_accounted_cpu, cpu);
+
+	while (cycles_not_accounted >= cycles_per_jiffy) {
+		no_idle_hz_jiffies++;
+		cycles_not_accounted -= cycles_per_jiffy;
+		per_cpu(process_times_cycles_accounted_cpu, cpu) += cycles_per_jiffy;
+	}
+	/* Account time to the idle process. */
+	account_steal_time(idle_task(cpu), jiffies_to_cputime(no_idle_hz_jiffies));
+}
+#endif
+
+/* Update per-cpu stolen time. */
+static void vmi_account_stolen_cycles(int cpu,
+				      unsigned long long cur_real_cycles,
+				      unsigned long long cur_avail_cycles)
+{
+	long long stolen_cycles_not_accounted;
+	unsigned long stolen_jiffies = 0;
+
+	if (cur_real_cycles < cur_avail_cycles)
+		return;
+
+	stolen_cycles_not_accounted = cur_real_cycles - cur_avail_cycles -
+		per_cpu(stolen_cycles_accounted_cpu, cpu);
+
+	while (stolen_cycles_not_accounted >= cycles_per_jiffy) {
+		stolen_jiffies++;
+		stolen_cycles_not_accounted -= cycles_per_jiffy;
+		per_cpu(stolen_cycles_accounted_cpu, cpu) += cycles_per_jiffy;
+	}
+	/* HACK: pass NULL to force time onto cpustat->steal. */
+	account_steal_time(NULL, jiffies_to_cputime(stolen_jiffies));
+}
+
+/* Body of either IRQ0 interrupt handler (UP no local-APIC) or
+ * local-APIC LVTT interrupt handler (UP & local-APIC or SMP). */
+static void vmi_local_timer_interrupt(int cpu)
+{
+	unsigned long long cur_real_cycles, cur_process_times_cycles;
+
+	cur_real_cycles = read_real_cycles();
+	cur_process_times_cycles = read_available_cycles();
+	/* Update system wide (real) time state (xtime, jiffies). */
+	vmi_account_real_cycles(cur_real_cycles);
+	/* Update per-cpu process times. */
+	vmi_account_process_times_cycles(get_irq_regs(), cpu, cur_process_times_cycles);
+        /* Update time stolen from this cpu by the hypervisor. */
+	vmi_account_stolen_cycles(cpu, cur_real_cycles, cur_process_times_cycles);
+}
+
+#ifdef CONFIG_NO_IDLE_HZ
+
+/* Must be called only from idle loop, with interrupts disabled. */
+int vmi_stop_hz_timer(void)
+{
+	/* Note that cpu_set, cpu_clear are (SMP safe) atomic on x86. */
+
+	unsigned long seq, next;
+	unsigned long long real_cycles_expiry;
+	int cpu = smp_processor_id();
+	int idle;
+
+	BUG_ON(!irqs_disabled());
+	if (sysctl_hz_timer != 0)
+		return 0;
+
+	cpu_set(cpu, nohz_cpu_mask);
+	smp_mb();
+	if (rcu_needs_cpu(cpu) || local_softirq_pending() ||
+	    (next = next_timer_interrupt(), time_before_eq(next, jiffies))) {
+		cpu_clear(cpu, nohz_cpu_mask);
+		next = jiffies;
+		idle = 0;
+	} else
+		idle = 1;
+
+	/* Convert jiffies to the real cycle counter. */
+	do {
+		seq = read_seqbegin(&xtime_lock);
+		real_cycles_expiry = real_cycles_accounted_system +
+			(long)(next - jiffies) * cycles_per_jiffy;
+	} while (read_seqretry(&xtime_lock, seq));
+
+	/* This cpu is going idle. Disable the periodic alarm. */
+	if (idle) {
+		vmi_timer_ops.cancel_alarm(VMI_CYCLES_AVAILABLE);
+		per_cpu(idle_start_jiffies, cpu) = jiffies;
+	}
+
+	/* Set the real time alarm to expire at the next event. */
+	vmi_timer_ops.set_alarm(
+		      VMI_ALARM_WIRING | VMI_ALARM_IS_ONESHOT | VMI_CYCLES_REAL,
+		      real_cycles_expiry, 0);
+
+	return idle;
+}
+
+static void vmi_reenable_hz_timer(int cpu)
+{
+	/* For /proc/vmi/info idle_hz stat. */
+	per_cpu(vmi_idle_no_hz_jiffies, cpu) += jiffies - per_cpu(idle_start_jiffies, cpu);
+	per_cpu(vmi_idle_no_hz_irqs, cpu)++;
+
+	/* Don't bother explicitly cancelling the one-shot alarm -- at
+	 * worse we will receive a spurious timer interrupt. */
+	vmi_timer_ops.set_alarm(
+		      VMI_ALARM_WIRING | VMI_ALARM_IS_PERIODIC | VMI_CYCLES_AVAILABLE,
+		      per_cpu(process_times_cycles_accounted_cpu, cpu) + cycles_per_alarm,
+		      cycles_per_alarm);
+	/* Indicate this cpu is no longer nohz idle. */
+	cpu_clear(cpu, nohz_cpu_mask);
+}
+
+/* Called from interrupt handlers when (local) HZ timer is disabled. */
+void vmi_account_time_restart_hz_timer(void)
+{
+	unsigned long long cur_real_cycles, cur_process_times_cycles;
+	int cpu = smp_processor_id();
+
+	BUG_ON(!irqs_disabled());
+	/* Account the time during which the HZ timer was disabled. */
+	cur_real_cycles = read_real_cycles();
+	cur_process_times_cycles = read_available_cycles();
+	/* Update system wide (real) time state (xtime, jiffies). */
+	vmi_account_real_cycles(cur_real_cycles);
+	/* Update per-cpu idle times. */
+	vmi_account_no_hz_idle_cycles(cpu, cur_process_times_cycles);
+        /* Update time stolen from this cpu by the hypervisor. */
+	vmi_account_stolen_cycles(cpu, cur_real_cycles, cur_process_times_cycles);
+	/* Reenable the hz timer. */
+	vmi_reenable_hz_timer(cpu);
+}
+
+#endif /* CONFIG_NO_IDLE_HZ */
+
+/* UP (and no local-APIC) VMI-timer alarm interrupt handler.
+ * Handler for IRQ0. Not used when SMP or X86_LOCAL_APIC after
+ * APIC setup and setup_boot_vmi_alarm() is called.  */
+static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id)
+{
+	vmi_local_timer_interrupt(smp_processor_id());
+	return IRQ_HANDLED;
+}
+
+#ifdef CONFIG_X86_LOCAL_APIC
+
+/* SMP VMI-timer alarm interrupt handler. Handler for LVTT vector.
+ * Also used in UP when CONFIG_X86_LOCAL_APIC.
+ * The wrapper code is from arch/i386/kernel/apic.c#smp_apic_timer_interrupt. */
+void smp_apic_vmi_timer_interrupt(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+	int cpu = smp_processor_id();
+
+	/*
+	 * the NMI deadlock-detector uses this.
+	 */
+        per_cpu(irq_stat,cpu).apic_timer_irqs++;
+
+	/*
+	 * NOTE! We'd better ACK the irq immediately,
+	 * because timer handling can be slow.
+	 */
+	ack_APIC_irq();
+
+	/*
+	 * update_process_times() expects us to have done irq_enter().
+	 * Besides, if we don't timer interrupts ignore the global
+	 * interrupt lock, which is the WrongThing (tm) to do.
+	 */
+	irq_enter();
+	vmi_local_timer_interrupt(cpu);
+	irq_exit();
+	set_irq_regs(old_regs);
+}
+
+#endif  /* CONFIG_X86_LOCAL_APIC */

arch/i386/kernel/vmlinux.lds.S

@@ -37,9 +37,14 @@ SECTIONS
 {
   . = LOAD_OFFSET + LOAD_PHYSICAL_ADDR;
   phys_startup_32 = startup_32 - LOAD_OFFSET;
+
+  .text.head : AT(ADDR(.text.head) - LOAD_OFFSET) {
+  	_text = .;			/* Text and read-only data */
+	*(.text.head)
+  } :text = 0x9090
+
   /* read-only */
   .text : AT(ADDR(.text) - LOAD_OFFSET) {
-  	_text = .;			/* Text and read-only data */
 	*(.text)
 	SCHED_TEXT
 	LOCK_TEXT

arch/i386/mach-default/setup.c

@@ -79,7 +79,12 @@ void __init trap_init_hook(void)
 {
 }
 
-static struct irqaction irq0  = { timer_interrupt, IRQF_DISABLED, CPU_MASK_NONE, "timer", NULL, NULL};
+static struct irqaction irq0  = {
+	.handler = timer_interrupt,
+	.flags = IRQF_DISABLED | IRQF_NOBALANCING,
+	.mask = CPU_MASK_NONE,
+	.name = "timer"
+};
 
 /**
  * time_init_hook - do any specific initialisations for the system timer.
@@ -90,6 +95,7 @@ static struct irqaction irq0  = { timer_interrupt, IRQF_DISABLED, CPU_MASK_NONE,
  **/
 void __init time_init_hook(void)
 {
+	irq0.mask = cpumask_of_cpu(0);
 	setup_irq(0, &irq0);
 }
 

arch/i386/math-emu/get_address.c

@@ -56,15 +56,14 @@ static int reg_offset_vm86[] = {
 #define VM86_REG_(x) (*(unsigned short *) \
 		      (reg_offset_vm86[((unsigned)x)]+(u_char *) FPU_info))
 
-/* These are dummy, fs and gs are not saved on the stack. */
-#define ___FS ___ds
+/* This dummy, gs is not saved on the stack. */
 #define ___GS ___ds
 
 static int reg_offset_pm[] = {
 	offsetof(struct info,___cs),
 	offsetof(struct info,___ds),
 	offsetof(struct info,___es),
-	offsetof(struct info,___FS),
+	offsetof(struct info,___fs),
 	offsetof(struct info,___GS),
 	offsetof(struct info,___ss),
 	offsetof(struct info,___ds)
@@ -169,13 +168,10 @@ static long pm_address(u_char FPU_modrm, u_char segment,
 
   switch ( segment )
     {
-      /* fs and gs aren't used by the kernel, so they still have their
-	 user-space values. */
-    case PREFIX_FS_-1:
-      /* N.B. - movl %seg, mem is a 2 byte write regardless of prefix */
-      savesegment(fs, addr->selector);
-      break;
+      /* gs isn't used by the kernel, so it still has its
+	 user-space value. */
     case PREFIX_GS_-1:
+      /* N.B. - movl %seg, mem is a 2 byte write regardless of prefix */
       savesegment(gs, addr->selector);
       break;
     default:

arch/i386/math-emu/status_w.h

@@ -48,9 +48,11 @@
 
 #define status_word() \
   ((partial_status & ~SW_Top & 0xffff) | ((top << SW_Top_Shift) & SW_Top))
-#define setcc(cc) ({ \
-  partial_status &= ~(SW_C0|SW_C1|SW_C2|SW_C3); \
-  partial_status |= (cc) & (SW_C0|SW_C1|SW_C2|SW_C3); })
+static inline void setcc(int cc)
+{
+	partial_status &= ~(SW_C0|SW_C1|SW_C2|SW_C3);
+	partial_status |= (cc) & (SW_C0|SW_C1|SW_C2|SW_C3);
+}
 
 #ifdef PECULIAR_486
    /* Default, this conveys no information, but an 80486 does it. */

arch/i386/mm/discontig.c

@@ -101,7 +101,6 @@ extern void find_max_pfn(void);
 extern void add_one_highpage_init(struct page *, int, int);
 
 extern struct e820map e820;
-extern unsigned long init_pg_tables_end;
 extern unsigned long highend_pfn, highstart_pfn;
 extern unsigned long max_low_pfn;
 extern unsigned long totalram_pages;

arch/i386/mm/fault.c

@@ -46,17 +46,17 @@ int unregister_page_fault_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL_GPL(unregister_page_fault_notifier);
 
-static inline int notify_page_fault(enum die_val val, const char *str,
-			struct pt_regs *regs, long err, int trap, int sig)
+static inline int notify_page_fault(struct pt_regs *regs, long err)
 {
 	struct die_args args = {
 		.regs = regs,
-		.str = str,
+		.str = "page fault",
 		.err = err,
-		.trapnr = trap,
-		.signr = sig
+		.trapnr = 14,
+		.signr = SIGSEGV
 	};
-	return atomic_notifier_call_chain(&notify_page_fault_chain, val, &args);
+	return atomic_notifier_call_chain(&notify_page_fault_chain,
+	                                  DIE_PAGE_FAULT, &args);
 }
 
 /*
@@ -327,8 +327,7 @@ fastcall void __kprobes do_page_fault(struct pt_regs *regs,
 	if (unlikely(address >= TASK_SIZE)) {
 		if (!(error_code & 0x0000000d) && vmalloc_fault(address) >= 0)
 			return;
-		if (notify_page_fault(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
-						SIGSEGV) == NOTIFY_STOP)
+		if (notify_page_fault(regs, error_code) == NOTIFY_STOP)
 			return;
 		/*
 		 * Don't take the mm semaphore here. If we fixup a prefetch
@@ -337,8 +336,7 @@ fastcall void __kprobes do_page_fault(struct pt_regs *regs,
 		goto bad_area_nosemaphore;
 	}
 
-	if (notify_page_fault(DIE_PAGE_FAULT, "page fault", regs, error_code, 14,
-					SIGSEGV) == NOTIFY_STOP)
+	if (notify_page_fault(regs, error_code) == NOTIFY_STOP)
 		return;
 
 	/* It's safe to allow irq's after cr2 has been saved and the vmalloc

arch/i386/mm/init.c

@@ -62,6 +62,7 @@ static pmd_t * __init one_md_table_init(pgd_t *pgd)
 		
 #ifdef CONFIG_X86_PAE
 	pmd_table = (pmd_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+	paravirt_alloc_pd(__pa(pmd_table) >> PAGE_SHIFT);
 	set_pgd(pgd, __pgd(__pa(pmd_table) | _PAGE_PRESENT));
 	pud = pud_offset(pgd, 0);
 	if (pmd_table != pmd_offset(pud, 0)) 
@@ -82,6 +83,7 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 {
 	if (pmd_none(*pmd)) {
 		pte_t *page_table = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE);
+		paravirt_alloc_pt(__pa(page_table) >> PAGE_SHIFT);
 		set_pmd(pmd, __pmd(__pa(page_table) | _PAGE_TABLE));
 		if (page_table != pte_offset_kernel(pmd, 0))
 			BUG();	
@@ -345,6 +347,8 @@ static void __init pagetable_init (void)
 	/* Init entries of the first-level page table to the zero page */
 	for (i = 0; i < PTRS_PER_PGD; i++)
 		set_pgd(pgd_base + i, __pgd(__pa(empty_zero_page) | _PAGE_PRESENT));
+#else
+	paravirt_alloc_pd(__pa(swapper_pg_dir) >> PAGE_SHIFT);
 #endif
 
 	/* Enable PSE if available */

arch/i386/mm/pageattr.c

@@ -60,6 +60,7 @@ static struct page *split_large_page(unsigned long address, pgprot_t prot,
 	address = __pa(address);
 	addr = address & LARGE_PAGE_MASK; 
 	pbase = (pte_t *)page_address(base);
+	paravirt_alloc_pt(page_to_pfn(base));
 	for (i = 0; i < PTRS_PER_PTE; i++, addr += PAGE_SIZE) {
                set_pte(&pbase[i], pfn_pte(addr >> PAGE_SHIFT,
                                           addr == address ? prot : ref_prot));
@@ -172,6 +173,7 @@ __change_page_attr(struct page *page, pgprot_t prot)
 	if (!PageReserved(kpte_page)) {
 		if (cpu_has_pse && (page_private(kpte_page) == 0)) {
 			ClearPagePrivate(kpte_page);
+			paravirt_release_pt(page_to_pfn(kpte_page));
 			list_add(&kpte_page->lru, &df_list);
 			revert_page(kpte_page, address);
 		}

arch/i386/mm/pgtable.c

@@ -171,6 +171,8 @@ void __set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t flags)
 void reserve_top_address(unsigned long reserve)
 {
 	BUG_ON(fixmaps > 0);
+	printk(KERN_INFO "Reserving virtual address space above 0x%08x\n",
+	       (int)-reserve);
 #ifdef CONFIG_COMPAT_VDSO
 	BUG_ON(reserve != 0);
 #else
@@ -248,9 +250,15 @@ void pgd_ctor(void *pgd, struct kmem_cache *cache, unsigned long unused)
 	clone_pgd_range((pgd_t *)pgd + USER_PTRS_PER_PGD,
 			swapper_pg_dir + USER_PTRS_PER_PGD,
 			KERNEL_PGD_PTRS);
+
 	if (PTRS_PER_PMD > 1)
 		return;
 
+	/* must happen under lock */
+	paravirt_alloc_pd_clone(__pa(pgd) >> PAGE_SHIFT,
+			__pa(swapper_pg_dir) >> PAGE_SHIFT,
+			USER_PTRS_PER_PGD, PTRS_PER_PGD - USER_PTRS_PER_PGD);
+
 	pgd_list_add(pgd);
 	spin_unlock_irqrestore(&pgd_lock, flags);
 }
@@ -260,6 +268,7 @@ void pgd_dtor(void *pgd, struct kmem_cache *cache, unsigned long unused)
 {
 	unsigned long flags; /* can be called from interrupt context */
 
+	paravirt_release_pd(__pa(pgd) >> PAGE_SHIFT);
 	spin_lock_irqsave(&pgd_lock, flags);
 	pgd_list_del(pgd);
 	spin_unlock_irqrestore(&pgd_lock, flags);
@@ -277,13 +286,18 @@ pgd_t *pgd_alloc(struct mm_struct *mm)
 		pmd_t *pmd = kmem_cache_alloc(pmd_cache, GFP_KERNEL);
 		if (!pmd)
 			goto out_oom;
+		paravirt_alloc_pd(__pa(pmd) >> PAGE_SHIFT);
 		set_pgd(&pgd[i], __pgd(1 + __pa(pmd)));
 	}
 	return pgd;
 
 out_oom:
-	for (i--; i >= 0; i--)
-		kmem_cache_free(pmd_cache, (void *)__va(pgd_val(pgd[i])-1));
+	for (i--; i >= 0; i--) {
+		pgd_t pgdent = pgd[i];
+		void* pmd = (void *)__va(pgd_val(pgdent)-1);
+		paravirt_release_pd(__pa(pmd) >> PAGE_SHIFT);
+		kmem_cache_free(pmd_cache, pmd);
+	}
 	kmem_cache_free(pgd_cache, pgd);
 	return NULL;
 }
@@ -294,8 +308,12 @@ void pgd_free(pgd_t *pgd)
 
 	/* in the PAE case user pgd entries are overwritten before usage */
 	if (PTRS_PER_PMD > 1)
-		for (i = 0; i < USER_PTRS_PER_PGD; ++i)
-			kmem_cache_free(pmd_cache, (void *)__va(pgd_val(pgd[i])-1));
+		for (i = 0; i < USER_PTRS_PER_PGD; ++i) {
+			pgd_t pgdent = pgd[i];
+			void* pmd = (void *)__va(pgd_val(pgdent)-1);
+			paravirt_release_pd(__pa(pmd) >> PAGE_SHIFT);
+			kmem_cache_free(pmd_cache, pmd);
+		}
 	/* in the non-PAE case, free_pgtables() clears user pgd entries */
 	kmem_cache_free(pgd_cache, pgd);
 }

arch/i386/oprofile/op_model_ppro.c

@@ -24,7 +24,8 @@
 
 #define CTR_IS_RESERVED(msrs,c) (msrs->counters[(c)].addr ? 1 : 0)
 #define CTR_READ(l,h,msrs,c) do {rdmsr(msrs->counters[(c)].addr, (l), (h));} while (0)
-#define CTR_WRITE(l,msrs,c) do {wrmsr(msrs->counters[(c)].addr, -(u32)(l), -1);} while (0)
+#define CTR_32BIT_WRITE(l,msrs,c)	\
+	do {wrmsr(msrs->counters[(c)].addr, -(u32)(l), 0);} while (0)
 #define CTR_OVERFLOWED(n) (!((n) & (1U<<31)))
 
 #define CTRL_IS_RESERVED(msrs,c) (msrs->controls[(c)].addr ? 1 : 0)
@@ -79,7 +80,7 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
 	for (i = 0; i < NUM_COUNTERS; ++i) {
 		if (unlikely(!CTR_IS_RESERVED(msrs,i)))
 			continue;
-		CTR_WRITE(1, msrs, i);
+		CTR_32BIT_WRITE(1, msrs, i);
 	}
 
 	/* enable active counters */
@@ -87,7 +88,7 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
 		if ((counter_config[i].enabled) && (CTR_IS_RESERVED(msrs,i))) {
 			reset_value[i] = counter_config[i].count;
 
-			CTR_WRITE(counter_config[i].count, msrs, i);
+			CTR_32BIT_WRITE(counter_config[i].count, msrs, i);
 
 			CTRL_READ(low, high, msrs, i);
 			CTRL_CLEAR(low);
@@ -116,7 +117,7 @@ static int ppro_check_ctrs(struct pt_regs * const regs,
 		CTR_READ(low, high, msrs, i);
 		if (CTR_OVERFLOWED(low)) {
 			oprofile_add_sample(regs, i);
-			CTR_WRITE(reset_value[i], msrs, i);
+			CTR_32BIT_WRITE(reset_value[i], msrs, i);
 		}
 	}
 

arch/i386/pci/Makefile

@@ -1,7 +1,7 @@
 obj-y				:= i386.o init.o
 
 obj-$(CONFIG_PCI_BIOS)		+= pcbios.o
-obj-$(CONFIG_PCI_MMCONFIG)	+= mmconfig.o direct.o
+obj-$(CONFIG_PCI_MMCONFIG)	+= mmconfig.o direct.o mmconfig-shared.o
 obj-$(CONFIG_PCI_DIRECT)	+= direct.o
 
 pci-y				:= fixup.o