Merge branches 'x86/acpi', 'x86/apic', 'x86/asm', 'x86/cleanups', 'x86/mm', 'x86/signal' and 'x86/urgent'; commit 'v2.6.29-rc6' into x86/core
diff --git a/Documentation/DocBook/Makefile b/Documentation/DocBook/Makefile
index dc3154e..1462ed8 100644
--- a/Documentation/DocBook/Makefile
+++ b/Documentation/DocBook/Makefile
@@ -6,7 +6,7 @@
# To add a new book the only step required is to add the book to the
# list of DOCBOOKS.
-DOCBOOKS := z8530book.xml mcabook.xml \
+DOCBOOKS := z8530book.xml mcabook.xml device-drivers.xml \
kernel-hacking.xml kernel-locking.xml deviceiobook.xml \
procfs-guide.xml writing_usb_driver.xml networking.xml \
kernel-api.xml filesystems.xml lsm.xml usb.xml kgdb.xml \
diff --git a/Documentation/DocBook/device-drivers.tmpl b/Documentation/DocBook/device-drivers.tmpl
new file mode 100644
index 0000000..94a20fe
--- /dev/null
+++ b/Documentation/DocBook/device-drivers.tmpl
@@ -0,0 +1,418 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<!DOCTYPE book PUBLIC "-//OASIS//DTD DocBook XML V4.1.2//EN"
+ "http://www.oasis-open.org/docbook/xml/4.1.2/docbookx.dtd" []>
+
+<book id="LinuxDriversAPI">
+ <bookinfo>
+ <title>Linux Device Drivers</title>
+
+ <legalnotice>
+ <para>
+ This documentation 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.
+ </para>
+
+ <para>
+ This program is distributed in the hope that it will be
+ useful, but WITHOUT ANY WARRANTY; without even the implied
+ warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ See the GNU General Public License for more details.
+ </para>
+
+ <para>
+ 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., 59 Temple Place, Suite 330, Boston,
+ MA 02111-1307 USA
+ </para>
+
+ <para>
+ For more details see the file COPYING in the source
+ distribution of Linux.
+ </para>
+ </legalnotice>
+ </bookinfo>
+
+<toc></toc>
+
+ <chapter id="Basics">
+ <title>Driver Basics</title>
+ <sect1><title>Driver Entry and Exit points</title>
+!Iinclude/linux/init.h
+ </sect1>
+
+ <sect1><title>Atomic and pointer manipulation</title>
+!Iarch/x86/include/asm/atomic_32.h
+!Iarch/x86/include/asm/unaligned.h
+ </sect1>
+
+ <sect1><title>Delaying, scheduling, and timer routines</title>
+!Iinclude/linux/sched.h
+!Ekernel/sched.c
+!Ekernel/timer.c
+ </sect1>
+ <sect1><title>High-resolution timers</title>
+!Iinclude/linux/ktime.h
+!Iinclude/linux/hrtimer.h
+!Ekernel/hrtimer.c
+ </sect1>
+ <sect1><title>Workqueues and Kevents</title>
+!Ekernel/workqueue.c
+ </sect1>
+ <sect1><title>Internal Functions</title>
+!Ikernel/exit.c
+!Ikernel/signal.c
+!Iinclude/linux/kthread.h
+!Ekernel/kthread.c
+ </sect1>
+
+ <sect1><title>Kernel objects manipulation</title>
+<!--
+X!Iinclude/linux/kobject.h
+-->
+!Elib/kobject.c
+ </sect1>
+
+ <sect1><title>Kernel utility functions</title>
+!Iinclude/linux/kernel.h
+!Ekernel/printk.c
+!Ekernel/panic.c
+!Ekernel/sys.c
+!Ekernel/rcupdate.c
+ </sect1>
+
+ <sect1><title>Device Resource Management</title>
+!Edrivers/base/devres.c
+ </sect1>
+
+ </chapter>
+
+ <chapter id="devdrivers">
+ <title>Device drivers infrastructure</title>
+ <sect1><title>Device Drivers Base</title>
+<!--
+X!Iinclude/linux/device.h
+-->
+!Edrivers/base/driver.c
+!Edrivers/base/core.c
+!Edrivers/base/class.c
+!Edrivers/base/firmware_class.c
+!Edrivers/base/transport_class.c
+<!-- Cannot be included, because
+ attribute_container_add_class_device_adapter
+ and attribute_container_classdev_to_container
+ exceed allowed 44 characters maximum
+X!Edrivers/base/attribute_container.c
+-->
+!Edrivers/base/sys.c
+<!--
+X!Edrivers/base/interface.c
+-->
+!Edrivers/base/platform.c
+!Edrivers/base/bus.c
+ </sect1>
+ <sect1><title>Device Drivers Power Management</title>
+!Edrivers/base/power/main.c
+ </sect1>
+ <sect1><title>Device Drivers ACPI Support</title>
+<!-- Internal functions only
+X!Edrivers/acpi/sleep/main.c
+X!Edrivers/acpi/sleep/wakeup.c
+X!Edrivers/acpi/motherboard.c
+X!Edrivers/acpi/bus.c
+-->
+!Edrivers/acpi/scan.c
+!Idrivers/acpi/scan.c
+<!-- No correct structured comments
+X!Edrivers/acpi/pci_bind.c
+-->
+ </sect1>
+ <sect1><title>Device drivers PnP support</title>
+!Idrivers/pnp/core.c
+<!-- No correct structured comments
+X!Edrivers/pnp/system.c
+ -->
+!Edrivers/pnp/card.c
+!Idrivers/pnp/driver.c
+!Edrivers/pnp/manager.c
+!Edrivers/pnp/support.c
+ </sect1>
+ <sect1><title>Userspace IO devices</title>
+!Edrivers/uio/uio.c
+!Iinclude/linux/uio_driver.h
+ </sect1>
+ </chapter>
+
+ <chapter id="parportdev">
+ <title>Parallel Port Devices</title>
+!Iinclude/linux/parport.h
+!Edrivers/parport/ieee1284.c
+!Edrivers/parport/share.c
+!Idrivers/parport/daisy.c
+ </chapter>
+
+ <chapter id="message_devices">
+ <title>Message-based devices</title>
+ <sect1><title>Fusion message devices</title>
+!Edrivers/message/fusion/mptbase.c
+!Idrivers/message/fusion/mptbase.c
+!Edrivers/message/fusion/mptscsih.c
+!Idrivers/message/fusion/mptscsih.c
+!Idrivers/message/fusion/mptctl.c
+!Idrivers/message/fusion/mptspi.c
+!Idrivers/message/fusion/mptfc.c
+!Idrivers/message/fusion/mptlan.c
+ </sect1>
+ <sect1><title>I2O message devices</title>
+!Iinclude/linux/i2o.h
+!Idrivers/message/i2o/core.h
+!Edrivers/message/i2o/iop.c
+!Idrivers/message/i2o/iop.c
+!Idrivers/message/i2o/config-osm.c
+!Edrivers/message/i2o/exec-osm.c
+!Idrivers/message/i2o/exec-osm.c
+!Idrivers/message/i2o/bus-osm.c
+!Edrivers/message/i2o/device.c
+!Idrivers/message/i2o/device.c
+!Idrivers/message/i2o/driver.c
+!Idrivers/message/i2o/pci.c
+!Idrivers/message/i2o/i2o_block.c
+!Idrivers/message/i2o/i2o_scsi.c
+!Idrivers/message/i2o/i2o_proc.c
+ </sect1>
+ </chapter>
+
+ <chapter id="snddev">
+ <title>Sound Devices</title>
+!Iinclude/sound/core.h
+!Esound/sound_core.c
+!Iinclude/sound/pcm.h
+!Esound/core/pcm.c
+!Esound/core/device.c
+!Esound/core/info.c
+!Esound/core/rawmidi.c
+!Esound/core/sound.c
+!Esound/core/memory.c
+!Esound/core/pcm_memory.c
+!Esound/core/init.c
+!Esound/core/isadma.c
+!Esound/core/control.c
+!Esound/core/pcm_lib.c
+!Esound/core/hwdep.c
+!Esound/core/pcm_native.c
+!Esound/core/memalloc.c
+<!-- FIXME: Removed for now since no structured comments in source
+X!Isound/sound_firmware.c
+-->
+ </chapter>
+
+ <chapter id="uart16x50">
+ <title>16x50 UART Driver</title>
+!Iinclude/linux/serial_core.h
+!Edrivers/serial/serial_core.c
+!Edrivers/serial/8250.c
+ </chapter>
+
+ <chapter id="fbdev">
+ <title>Frame Buffer Library</title>
+
+ <para>
+ The frame buffer drivers depend heavily on four data structures.
+ These structures are declared in include/linux/fb.h. They are
+ fb_info, fb_var_screeninfo, fb_fix_screeninfo and fb_monospecs.
+ The last three can be made available to and from userland.
+ </para>
+
+ <para>
+ fb_info defines the current state of a particular video card.
+ Inside fb_info, there exists a fb_ops structure which is a
+ collection of needed functions to make fbdev and fbcon work.
+ fb_info is only visible to the kernel.
+ </para>
+
+ <para>
+ fb_var_screeninfo is used to describe the features of a video card
+ that are user defined. With fb_var_screeninfo, things such as
+ depth and the resolution may be defined.
+ </para>
+
+ <para>
+ The next structure is fb_fix_screeninfo. This defines the
+ properties of a card that are created when a mode is set and can't
+ be changed otherwise. A good example of this is the start of the
+ frame buffer memory. This "locks" the address of the frame buffer
+ memory, so that it cannot be changed or moved.
+ </para>
+
+ <para>
+ The last structure is fb_monospecs. In the old API, there was
+ little importance for fb_monospecs. This allowed for forbidden things
+ such as setting a mode of 800x600 on a fix frequency monitor. With
+ the new API, fb_monospecs prevents such things, and if used
+ correctly, can prevent a monitor from being cooked. fb_monospecs
+ will not be useful until kernels 2.5.x.
+ </para>
+
+ <sect1><title>Frame Buffer Memory</title>
+!Edrivers/video/fbmem.c
+ </sect1>
+<!--
+ <sect1><title>Frame Buffer Console</title>
+X!Edrivers/video/console/fbcon.c
+ </sect1>
+-->
+ <sect1><title>Frame Buffer Colormap</title>
+!Edrivers/video/fbcmap.c
+ </sect1>
+<!-- FIXME:
+ drivers/video/fbgen.c has no docs, which stuffs up the sgml. Comment
+ out until somebody adds docs. KAO
+ <sect1><title>Frame Buffer Generic Functions</title>
+X!Idrivers/video/fbgen.c
+ </sect1>
+KAO -->
+ <sect1><title>Frame Buffer Video Mode Database</title>
+!Idrivers/video/modedb.c
+!Edrivers/video/modedb.c
+ </sect1>
+ <sect1><title>Frame Buffer Macintosh Video Mode Database</title>
+!Edrivers/video/macmodes.c
+ </sect1>
+ <sect1><title>Frame Buffer Fonts</title>
+ <para>
+ Refer to the file drivers/video/console/fonts.c for more information.
+ </para>
+<!-- FIXME: Removed for now since no structured comments in source
+X!Idrivers/video/console/fonts.c
+-->
+ </sect1>
+ </chapter>
+
+ <chapter id="input_subsystem">
+ <title>Input Subsystem</title>
+!Iinclude/linux/input.h
+!Edrivers/input/input.c
+!Edrivers/input/ff-core.c
+!Edrivers/input/ff-memless.c
+ </chapter>
+
+ <chapter id="spi">
+ <title>Serial Peripheral Interface (SPI)</title>
+ <para>
+ SPI is the "Serial Peripheral Interface", widely used with
+ embedded systems because it is a simple and efficient
+ interface: basically a multiplexed shift register.
+ Its three signal wires hold a clock (SCK, often in the range
+ of 1-20 MHz), a "Master Out, Slave In" (MOSI) data line, and
+ a "Master In, Slave Out" (MISO) data line.
+ SPI is a full duplex protocol; for each bit shifted out the
+ MOSI line (one per clock) another is shifted in on the MISO line.
+ Those bits are assembled into words of various sizes on the
+ way to and from system memory.
+ An additional chipselect line is usually active-low (nCS);
+ four signals are normally used for each peripheral, plus
+ sometimes an interrupt.
+ </para>
+ <para>
+ The SPI bus facilities listed here provide a generalized
+ interface to declare SPI busses and devices, manage them
+ according to the standard Linux driver model, and perform
+ input/output operations.
+ At this time, only "master" side interfaces are supported,
+ where Linux talks to SPI peripherals and does not implement
+ such a peripheral itself.
+ (Interfaces to support implementing SPI slaves would
+ necessarily look different.)
+ </para>
+ <para>
+ The programming interface is structured around two kinds of driver,
+ and two kinds of device.
+ A "Controller Driver" abstracts the controller hardware, which may
+ be as simple as a set of GPIO pins or as complex as a pair of FIFOs
+ connected to dual DMA engines on the other side of the SPI shift
+ register (maximizing throughput). Such drivers bridge between
+ whatever bus they sit on (often the platform bus) and SPI, and
+ expose the SPI side of their device as a
+ <structname>struct spi_master</structname>.
+ SPI devices are children of that master, represented as a
+ <structname>struct spi_device</structname> and manufactured from
+ <structname>struct spi_board_info</structname> descriptors which
+ are usually provided by board-specific initialization code.
+ A <structname>struct spi_driver</structname> is called a
+ "Protocol Driver", and is bound to a spi_device using normal
+ driver model calls.
+ </para>
+ <para>
+ The I/O model is a set of queued messages. Protocol drivers
+ submit one or more <structname>struct spi_message</structname>
+ objects, which are processed and completed asynchronously.
+ (There are synchronous wrappers, however.) Messages are
+ built from one or more <structname>struct spi_transfer</structname>
+ objects, each of which wraps a full duplex SPI transfer.
+ A variety of protocol tweaking options are needed, because
+ different chips adopt very different policies for how they
+ use the bits transferred with SPI.
+ </para>
+!Iinclude/linux/spi/spi.h
+!Fdrivers/spi/spi.c spi_register_board_info
+!Edrivers/spi/spi.c
+ </chapter>
+
+ <chapter id="i2c">
+ <title>I<superscript>2</superscript>C and SMBus Subsystem</title>
+
+ <para>
+ I<superscript>2</superscript>C (or without fancy typography, "I2C")
+ is an acronym for the "Inter-IC" bus, a simple bus protocol which is
+ widely used where low data rate communications suffice.
+ Since it's also a licensed trademark, some vendors use another
+ name (such as "Two-Wire Interface", TWI) for the same bus.
+ I2C only needs two signals (SCL for clock, SDA for data), conserving
+ board real estate and minimizing signal quality issues.
+ Most I2C devices use seven bit addresses, and bus speeds of up
+ to 400 kHz; there's a high speed extension (3.4 MHz) that's not yet
+ found wide use.
+ I2C is a multi-master bus; open drain signaling is used to
+ arbitrate between masters, as well as to handshake and to
+ synchronize clocks from slower clients.
+ </para>
+
+ <para>
+ The Linux I2C programming interfaces support only the master
+ side of bus interactions, not the slave side.
+ The programming interface is structured around two kinds of driver,
+ and two kinds of device.
+ An I2C "Adapter Driver" abstracts the controller hardware; it binds
+ to a physical device (perhaps a PCI device or platform_device) and
+ exposes a <structname>struct i2c_adapter</structname> representing
+ each I2C bus segment it manages.
+ On each I2C bus segment will be I2C devices represented by a
+ <structname>struct i2c_client</structname>. Those devices will
+ be bound to a <structname>struct i2c_driver</structname>,
+ which should follow the standard Linux driver model.
+ (At this writing, a legacy model is more widely used.)
+ There are functions to perform various I2C protocol operations; at
+ this writing all such functions are usable only from task context.
+ </para>
+
+ <para>
+ The System Management Bus (SMBus) is a sibling protocol. Most SMBus
+ systems are also I2C conformant. The electrical constraints are
+ tighter for SMBus, and it standardizes particular protocol messages
+ and idioms. Controllers that support I2C can also support most
+ SMBus operations, but SMBus controllers don't support all the protocol
+ options that an I2C controller will.
+ There are functions to perform various SMBus protocol operations,
+ either using I2C primitives or by issuing SMBus commands to
+ i2c_adapter devices which don't support those I2C operations.
+ </para>
+
+!Iinclude/linux/i2c.h
+!Fdrivers/i2c/i2c-boardinfo.c i2c_register_board_info
+!Edrivers/i2c/i2c-core.c
+ </chapter>
+
+</book>
diff --git a/Documentation/DocBook/kernel-api.tmpl b/Documentation/DocBook/kernel-api.tmpl
index 5818ff7..bc962cd 100644
--- a/Documentation/DocBook/kernel-api.tmpl
+++ b/Documentation/DocBook/kernel-api.tmpl
@@ -38,58 +38,6 @@
<toc></toc>
- <chapter id="Basics">
- <title>Driver Basics</title>
- <sect1><title>Driver Entry and Exit points</title>
-!Iinclude/linux/init.h
- </sect1>
-
- <sect1><title>Atomic and pointer manipulation</title>
-!Iarch/x86/include/asm/atomic_32.h
-!Iarch/x86/include/asm/unaligned.h
- </sect1>
-
- <sect1><title>Delaying, scheduling, and timer routines</title>
-!Iinclude/linux/sched.h
-!Ekernel/sched.c
-!Ekernel/timer.c
- </sect1>
- <sect1><title>High-resolution timers</title>
-!Iinclude/linux/ktime.h
-!Iinclude/linux/hrtimer.h
-!Ekernel/hrtimer.c
- </sect1>
- <sect1><title>Workqueues and Kevents</title>
-!Ekernel/workqueue.c
- </sect1>
- <sect1><title>Internal Functions</title>
-!Ikernel/exit.c
-!Ikernel/signal.c
-!Iinclude/linux/kthread.h
-!Ekernel/kthread.c
- </sect1>
-
- <sect1><title>Kernel objects manipulation</title>
-<!--
-X!Iinclude/linux/kobject.h
--->
-!Elib/kobject.c
- </sect1>
-
- <sect1><title>Kernel utility functions</title>
-!Iinclude/linux/kernel.h
-!Ekernel/printk.c
-!Ekernel/panic.c
-!Ekernel/sys.c
-!Ekernel/rcupdate.c
- </sect1>
-
- <sect1><title>Device Resource Management</title>
-!Edrivers/base/devres.c
- </sect1>
-
- </chapter>
-
<chapter id="adt">
<title>Data Types</title>
<sect1><title>Doubly Linked Lists</title>
@@ -298,62 +246,6 @@
!Ikernel/acct.c
</chapter>
- <chapter id="devdrivers">
- <title>Device drivers infrastructure</title>
- <sect1><title>Device Drivers Base</title>
-<!--
-X!Iinclude/linux/device.h
--->
-!Edrivers/base/driver.c
-!Edrivers/base/core.c
-!Edrivers/base/class.c
-!Edrivers/base/firmware_class.c
-!Edrivers/base/transport_class.c
-<!-- Cannot be included, because
- attribute_container_add_class_device_adapter
- and attribute_container_classdev_to_container
- exceed allowed 44 characters maximum
-X!Edrivers/base/attribute_container.c
--->
-!Edrivers/base/sys.c
-<!--
-X!Edrivers/base/interface.c
--->
-!Edrivers/base/platform.c
-!Edrivers/base/bus.c
- </sect1>
- <sect1><title>Device Drivers Power Management</title>
-!Edrivers/base/power/main.c
- </sect1>
- <sect1><title>Device Drivers ACPI Support</title>
-<!-- Internal functions only
-X!Edrivers/acpi/sleep/main.c
-X!Edrivers/acpi/sleep/wakeup.c
-X!Edrivers/acpi/motherboard.c
-X!Edrivers/acpi/bus.c
--->
-!Edrivers/acpi/scan.c
-!Idrivers/acpi/scan.c
-<!-- No correct structured comments
-X!Edrivers/acpi/pci_bind.c
--->
- </sect1>
- <sect1><title>Device drivers PnP support</title>
-!Idrivers/pnp/core.c
-<!-- No correct structured comments
-X!Edrivers/pnp/system.c
- -->
-!Edrivers/pnp/card.c
-!Idrivers/pnp/driver.c
-!Edrivers/pnp/manager.c
-!Edrivers/pnp/support.c
- </sect1>
- <sect1><title>Userspace IO devices</title>
-!Edrivers/uio/uio.c
-!Iinclude/linux/uio_driver.h
- </sect1>
- </chapter>
-
<chapter id="blkdev">
<title>Block Devices</title>
!Eblock/blk-core.c
@@ -381,275 +273,6 @@
!Edrivers/char/misc.c
</chapter>
- <chapter id="parportdev">
- <title>Parallel Port Devices</title>
-!Iinclude/linux/parport.h
-!Edrivers/parport/ieee1284.c
-!Edrivers/parport/share.c
-!Idrivers/parport/daisy.c
- </chapter>
-
- <chapter id="message_devices">
- <title>Message-based devices</title>
- <sect1><title>Fusion message devices</title>
-!Edrivers/message/fusion/mptbase.c
-!Idrivers/message/fusion/mptbase.c
-!Edrivers/message/fusion/mptscsih.c
-!Idrivers/message/fusion/mptscsih.c
-!Idrivers/message/fusion/mptctl.c
-!Idrivers/message/fusion/mptspi.c
-!Idrivers/message/fusion/mptfc.c
-!Idrivers/message/fusion/mptlan.c
- </sect1>
- <sect1><title>I2O message devices</title>
-!Iinclude/linux/i2o.h
-!Idrivers/message/i2o/core.h
-!Edrivers/message/i2o/iop.c
-!Idrivers/message/i2o/iop.c
-!Idrivers/message/i2o/config-osm.c
-!Edrivers/message/i2o/exec-osm.c
-!Idrivers/message/i2o/exec-osm.c
-!Idrivers/message/i2o/bus-osm.c
-!Edrivers/message/i2o/device.c
-!Idrivers/message/i2o/device.c
-!Idrivers/message/i2o/driver.c
-!Idrivers/message/i2o/pci.c
-!Idrivers/message/i2o/i2o_block.c
-!Idrivers/message/i2o/i2o_scsi.c
-!Idrivers/message/i2o/i2o_proc.c
- </sect1>
- </chapter>
-
- <chapter id="snddev">
- <title>Sound Devices</title>
-!Iinclude/sound/core.h
-!Esound/sound_core.c
-!Iinclude/sound/pcm.h
-!Esound/core/pcm.c
-!Esound/core/device.c
-!Esound/core/info.c
-!Esound/core/rawmidi.c
-!Esound/core/sound.c
-!Esound/core/memory.c
-!Esound/core/pcm_memory.c
-!Esound/core/init.c
-!Esound/core/isadma.c
-!Esound/core/control.c
-!Esound/core/pcm_lib.c
-!Esound/core/hwdep.c
-!Esound/core/pcm_native.c
-!Esound/core/memalloc.c
-<!-- FIXME: Removed for now since no structured comments in source
-X!Isound/sound_firmware.c
--->
- </chapter>
-
- <chapter id="uart16x50">
- <title>16x50 UART Driver</title>
-!Iinclude/linux/serial_core.h
-!Edrivers/serial/serial_core.c
-!Edrivers/serial/8250.c
- </chapter>
-
- <chapter id="fbdev">
- <title>Frame Buffer Library</title>
-
- <para>
- The frame buffer drivers depend heavily on four data structures.
- These structures are declared in include/linux/fb.h. They are
- fb_info, fb_var_screeninfo, fb_fix_screeninfo and fb_monospecs.
- The last three can be made available to and from userland.
- </para>
-
- <para>
- fb_info defines the current state of a particular video card.
- Inside fb_info, there exists a fb_ops structure which is a
- collection of needed functions to make fbdev and fbcon work.
- fb_info is only visible to the kernel.
- </para>
-
- <para>
- fb_var_screeninfo is used to describe the features of a video card
- that are user defined. With fb_var_screeninfo, things such as
- depth and the resolution may be defined.
- </para>
-
- <para>
- The next structure is fb_fix_screeninfo. This defines the
- properties of a card that are created when a mode is set and can't
- be changed otherwise. A good example of this is the start of the
- frame buffer memory. This "locks" the address of the frame buffer
- memory, so that it cannot be changed or moved.
- </para>
-
- <para>
- The last structure is fb_monospecs. In the old API, there was
- little importance for fb_monospecs. This allowed for forbidden things
- such as setting a mode of 800x600 on a fix frequency monitor. With
- the new API, fb_monospecs prevents such things, and if used
- correctly, can prevent a monitor from being cooked. fb_monospecs
- will not be useful until kernels 2.5.x.
- </para>
-
- <sect1><title>Frame Buffer Memory</title>
-!Edrivers/video/fbmem.c
- </sect1>
-<!--
- <sect1><title>Frame Buffer Console</title>
-X!Edrivers/video/console/fbcon.c
- </sect1>
--->
- <sect1><title>Frame Buffer Colormap</title>
-!Edrivers/video/fbcmap.c
- </sect1>
-<!-- FIXME:
- drivers/video/fbgen.c has no docs, which stuffs up the sgml. Comment
- out until somebody adds docs. KAO
- <sect1><title>Frame Buffer Generic Functions</title>
-X!Idrivers/video/fbgen.c
- </sect1>
-KAO -->
- <sect1><title>Frame Buffer Video Mode Database</title>
-!Idrivers/video/modedb.c
-!Edrivers/video/modedb.c
- </sect1>
- <sect1><title>Frame Buffer Macintosh Video Mode Database</title>
-!Edrivers/video/macmodes.c
- </sect1>
- <sect1><title>Frame Buffer Fonts</title>
- <para>
- Refer to the file drivers/video/console/fonts.c for more information.
- </para>
-<!-- FIXME: Removed for now since no structured comments in source
-X!Idrivers/video/console/fonts.c
--->
- </sect1>
- </chapter>
-
- <chapter id="input_subsystem">
- <title>Input Subsystem</title>
-!Iinclude/linux/input.h
-!Edrivers/input/input.c
-!Edrivers/input/ff-core.c
-!Edrivers/input/ff-memless.c
- </chapter>
-
- <chapter id="spi">
- <title>Serial Peripheral Interface (SPI)</title>
- <para>
- SPI is the "Serial Peripheral Interface", widely used with
- embedded systems because it is a simple and efficient
- interface: basically a multiplexed shift register.
- Its three signal wires hold a clock (SCK, often in the range
- of 1-20 MHz), a "Master Out, Slave In" (MOSI) data line, and
- a "Master In, Slave Out" (MISO) data line.
- SPI is a full duplex protocol; for each bit shifted out the
- MOSI line (one per clock) another is shifted in on the MISO line.
- Those bits are assembled into words of various sizes on the
- way to and from system memory.
- An additional chipselect line is usually active-low (nCS);
- four signals are normally used for each peripheral, plus
- sometimes an interrupt.
- </para>
- <para>
- The SPI bus facilities listed here provide a generalized
- interface to declare SPI busses and devices, manage them
- according to the standard Linux driver model, and perform
- input/output operations.
- At this time, only "master" side interfaces are supported,
- where Linux talks to SPI peripherals and does not implement
- such a peripheral itself.
- (Interfaces to support implementing SPI slaves would
- necessarily look different.)
- </para>
- <para>
- The programming interface is structured around two kinds of driver,
- and two kinds of device.
- A "Controller Driver" abstracts the controller hardware, which may
- be as simple as a set of GPIO pins or as complex as a pair of FIFOs
- connected to dual DMA engines on the other side of the SPI shift
- register (maximizing throughput). Such drivers bridge between
- whatever bus they sit on (often the platform bus) and SPI, and
- expose the SPI side of their device as a
- <structname>struct spi_master</structname>.
- SPI devices are children of that master, represented as a
- <structname>struct spi_device</structname> and manufactured from
- <structname>struct spi_board_info</structname> descriptors which
- are usually provided by board-specific initialization code.
- A <structname>struct spi_driver</structname> is called a
- "Protocol Driver", and is bound to a spi_device using normal
- driver model calls.
- </para>
- <para>
- The I/O model is a set of queued messages. Protocol drivers
- submit one or more <structname>struct spi_message</structname>
- objects, which are processed and completed asynchronously.
- (There are synchronous wrappers, however.) Messages are
- built from one or more <structname>struct spi_transfer</structname>
- objects, each of which wraps a full duplex SPI transfer.
- A variety of protocol tweaking options are needed, because
- different chips adopt very different policies for how they
- use the bits transferred with SPI.
- </para>
-!Iinclude/linux/spi/spi.h
-!Fdrivers/spi/spi.c spi_register_board_info
-!Edrivers/spi/spi.c
- </chapter>
-
- <chapter id="i2c">
- <title>I<superscript>2</superscript>C and SMBus Subsystem</title>
-
- <para>
- I<superscript>2</superscript>C (or without fancy typography, "I2C")
- is an acronym for the "Inter-IC" bus, a simple bus protocol which is
- widely used where low data rate communications suffice.
- Since it's also a licensed trademark, some vendors use another
- name (such as "Two-Wire Interface", TWI) for the same bus.
- I2C only needs two signals (SCL for clock, SDA for data), conserving
- board real estate and minimizing signal quality issues.
- Most I2C devices use seven bit addresses, and bus speeds of up
- to 400 kHz; there's a high speed extension (3.4 MHz) that's not yet
- found wide use.
- I2C is a multi-master bus; open drain signaling is used to
- arbitrate between masters, as well as to handshake and to
- synchronize clocks from slower clients.
- </para>
-
- <para>
- The Linux I2C programming interfaces support only the master
- side of bus interactions, not the slave side.
- The programming interface is structured around two kinds of driver,
- and two kinds of device.
- An I2C "Adapter Driver" abstracts the controller hardware; it binds
- to a physical device (perhaps a PCI device or platform_device) and
- exposes a <structname>struct i2c_adapter</structname> representing
- each I2C bus segment it manages.
- On each I2C bus segment will be I2C devices represented by a
- <structname>struct i2c_client</structname>. Those devices will
- be bound to a <structname>struct i2c_driver</structname>,
- which should follow the standard Linux driver model.
- (At this writing, a legacy model is more widely used.)
- There are functions to perform various I2C protocol operations; at
- this writing all such functions are usable only from task context.
- </para>
-
- <para>
- The System Management Bus (SMBus) is a sibling protocol. Most SMBus
- systems are also I2C conformant. The electrical constraints are
- tighter for SMBus, and it standardizes particular protocol messages
- and idioms. Controllers that support I2C can also support most
- SMBus operations, but SMBus controllers don't support all the protocol
- options that an I2C controller will.
- There are functions to perform various SMBus protocol operations,
- either using I2C primitives or by issuing SMBus commands to
- i2c_adapter devices which don't support those I2C operations.
- </para>
-
-!Iinclude/linux/i2c.h
-!Fdrivers/i2c/i2c-boardinfo.c i2c_register_board_info
-!Edrivers/i2c/i2c-core.c
- </chapter>
-
<chapter id="clk">
<title>Clock Framework</title>
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index b182626..f6d5d5b 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -114,7 +114,7 @@
Parameters denoted with BOOT are actually interpreted by the boot
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/x86/i386/boot.txt>.
+need or coordination with <Documentation/x86/boot.txt>.
There are also arch-specific kernel-parameters not documented here.
See for example <Documentation/x86/x86_64/boot-options.txt>.
@@ -134,7 +134,7 @@
acpi= [HW,ACPI,X86-64,i386]
Advanced Configuration and Power Interface
- Format: { force | off | ht | strict | noirq }
+ Format: { force | off | ht | strict | noirq | rsdt }
force -- enable ACPI if default was off
off -- disable ACPI if default was on
noirq -- do not use ACPI for IRQ routing
@@ -2449,7 +2449,7 @@
See Documentation/fb/modedb.txt.
vga= [BOOT,X86-32] Select a particular video mode
- See Documentation/x86/i386/boot.txt and
+ See Documentation/x86/boot.txt and
Documentation/svga.txt.
Use vga=ask for menu.
This is actually a boot loader parameter; the value is
diff --git a/Makefile b/Makefile
index 96628d0..27fb890 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
VERSION = 2
PATCHLEVEL = 6
SUBLEVEL = 29
-EXTRAVERSION = -rc5
+EXTRAVERSION = -rc6
NAME = Erotic Pickled Herring
# *DOCUMENTATION*
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index 29c5fbf..3a8a866 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -25,14 +25,12 @@
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/boot.h>
#include <asm/asm-offsets.h>
.section ".text.head","ax",@progbits
- .globl startup_32
-
-startup_32:
+ENTRY(startup_32)
cld
/* test KEEP_SEGMENTS flag to see if the bootloader is asking
* us to not reload segments */
@@ -113,6 +111,8 @@
*/
leal relocated(%ebx), %eax
jmp *%eax
+ENDPROC(startup_32)
+
.section ".text"
relocated:
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 1d5dff4..ed4a829 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -26,8 +26,8 @@
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
+#include <asm/pgtable_types.h>
+#include <asm/page_types.h>
#include <asm/boot.h>
#include <asm/msr.h>
#include <asm/processor-flags.h>
@@ -35,9 +35,7 @@
.section ".text.head"
.code32
- .globl startup_32
-
-startup_32:
+ENTRY(startup_32)
cld
/* test KEEP_SEGMENTS flag to see if the bootloader is asking
* us to not reload segments */
@@ -176,6 +174,7 @@
/* Jump from 32bit compatibility mode into 64bit mode. */
lret
+ENDPROC(startup_32)
no_longmode:
/* This isn't an x86-64 CPU so hang */
@@ -295,7 +294,6 @@
call decompress_kernel
popq %rsi
-
/*
* Jump to the decompressed kernel.
*/
diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S
index ef50c84..11f272c 100644
--- a/arch/x86/boot/copy.S
+++ b/arch/x86/boot/copy.S
@@ -8,6 +8,8 @@
*
* ----------------------------------------------------------------------- */
+#include <linux/linkage.h>
+
/*
* Memory copy routines
*/
@@ -15,9 +17,7 @@
.code16gcc
.text
- .globl memcpy
- .type memcpy, @function
-memcpy:
+GLOBAL(memcpy)
pushw %si
pushw %di
movw %ax, %di
@@ -31,11 +31,9 @@
popw %di
popw %si
ret
- .size memcpy, .-memcpy
+ENDPROC(memcpy)
- .globl memset
- .type memset, @function
-memset:
+GLOBAL(memset)
pushw %di
movw %ax, %di
movzbl %dl, %eax
@@ -48,52 +46,42 @@
rep; stosb
popw %di
ret
- .size memset, .-memset
+ENDPROC(memset)
- .globl copy_from_fs
- .type copy_from_fs, @function
-copy_from_fs:
+GLOBAL(copy_from_fs)
pushw %ds
pushw %fs
popw %ds
call memcpy
popw %ds
ret
- .size copy_from_fs, .-copy_from_fs
+ENDPROC(copy_from_fs)
- .globl copy_to_fs
- .type copy_to_fs, @function
-copy_to_fs:
+GLOBAL(copy_to_fs)
pushw %es
pushw %fs
popw %es
call memcpy
popw %es
ret
- .size copy_to_fs, .-copy_to_fs
+ENDPROC(copy_to_fs)
#if 0 /* Not currently used, but can be enabled as needed */
-
- .globl copy_from_gs
- .type copy_from_gs, @function
-copy_from_gs:
+GLOBAL(copy_from_gs)
pushw %ds
pushw %gs
popw %ds
call memcpy
popw %ds
ret
- .size copy_from_gs, .-copy_from_gs
- .globl copy_to_gs
+ENDPROC(copy_from_gs)
- .type copy_to_gs, @function
-copy_to_gs:
+GLOBAL(copy_to_gs)
pushw %es
pushw %gs
popw %es
call memcpy
popw %es
ret
- .size copy_to_gs, .-copy_to_gs
-
+ENDPROC(copy_to_gs)
#endif
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b993062..7ccff48 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -19,7 +19,7 @@
#include <linux/utsrelease.h>
#include <asm/boot.h>
#include <asm/e820.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/setup.h>
#include "boot.h"
#include "offsets.h"
diff --git a/arch/x86/boot/pmjump.S b/arch/x86/boot/pmjump.S
index 141b6e2..019c17a 100644
--- a/arch/x86/boot/pmjump.S
+++ b/arch/x86/boot/pmjump.S
@@ -15,18 +15,15 @@
#include <asm/boot.h>
#include <asm/processor-flags.h>
#include <asm/segment.h>
+#include <linux/linkage.h>
.text
-
- .globl protected_mode_jump
- .type protected_mode_jump, @function
-
.code16
/*
* void protected_mode_jump(u32 entrypoint, u32 bootparams);
*/
-protected_mode_jump:
+GLOBAL(protected_mode_jump)
movl %edx, %esi # Pointer to boot_params table
xorl %ebx, %ebx
@@ -47,12 +44,10 @@
.byte 0x66, 0xea # ljmpl opcode
2: .long in_pm32 # offset
.word __BOOT_CS # segment
-
- .size protected_mode_jump, .-protected_mode_jump
+ENDPROC(protected_mode_jump)
.code32
- .type in_pm32, @function
-in_pm32:
+GLOBAL(in_pm32)
# Set up data segments for flat 32-bit mode
movl %ecx, %ds
movl %ecx, %es
@@ -78,5 +73,4 @@
lldt %cx
jmpl *%eax # Jump to the 32-bit entrypoint
-
- .size in_pm32, .-in_pm32
+ENDPROC(in_pm32)
diff --git a/arch/x86/ia32/ia32_signal.c b/arch/x86/ia32/ia32_signal.c
index dd77ac0..588a7aa 100644
--- a/arch/x86/ia32/ia32_signal.c
+++ b/arch/x86/ia32/ia32_signal.c
@@ -33,8 +33,6 @@
#include <asm/sigframe.h>
#include <asm/sys_ia32.h>
-#define DEBUG_SIG 0
-
#define _BLOCKABLE (~(sigmask(SIGKILL) | sigmask(SIGSTOP)))
#define FIX_EFLAGS (X86_EFLAGS_AC | X86_EFLAGS_OF | \
@@ -190,42 +188,47 @@
/*
* Do a signal return; undo the signal stack.
*/
+#define loadsegment_gs(v) load_gs_index(v)
+#define loadsegment_fs(v) loadsegment(fs, v)
+#define loadsegment_ds(v) loadsegment(ds, v)
+#define loadsegment_es(v) loadsegment(es, v)
+
+#define get_user_seg(seg) ({ unsigned int v; savesegment(seg, v); v; })
+#define set_user_seg(seg, v) loadsegment_##seg(v)
+
#define COPY(x) { \
get_user_ex(regs->x, &sc->x); \
}
-#define COPY_SEG_CPL3(seg) { \
- unsigned short tmp; \
- get_user_ex(tmp, &sc->seg); \
- regs->seg = tmp | 3; \
-}
+#define GET_SEG(seg) ({ \
+ unsigned short tmp; \
+ get_user_ex(tmp, &sc->seg); \
+ tmp; \
+})
+
+#define COPY_SEG_CPL3(seg) do { \
+ regs->seg = GET_SEG(seg) | 3; \
+} while (0)
#define RELOAD_SEG(seg) { \
- unsigned int cur, pre; \
- get_user_ex(pre, &sc->seg); \
- savesegment(seg, cur); \
+ unsigned int pre = GET_SEG(seg); \
+ unsigned int cur = get_user_seg(seg); \
pre |= 3; \
if (pre != cur) \
- loadsegment(seg, pre); \
+ set_user_seg(seg, pre); \
}
static int ia32_restore_sigcontext(struct pt_regs *regs,
struct sigcontext_ia32 __user *sc,
unsigned int *pax)
{
- unsigned int tmpflags, gs, oldgs, err = 0;
+ unsigned int tmpflags, err = 0;
void __user *buf;
u32 tmp;
/* Always make any pending restarted system calls return -EINTR */
current_thread_info()->restart_block.fn = do_no_restart_syscall;
-#if DEBUG_SIG
- printk(KERN_DEBUG "SIG restore_sigcontext: "
- "sc=%p err(%x) eip(%x) cs(%x) flg(%x)\n",
- sc, sc->err, sc->ip, sc->cs, sc->flags);
-#endif
-
get_user_try {
/*
* Reload fs and gs if they have changed in the signal
@@ -233,12 +236,7 @@
* the handler, but does not clobber them at least in the
* normal case.
*/
- get_user_ex(gs, &sc->gs);
- gs |= 3;
- savesegment(gs, oldgs);
- if (gs != oldgs)
- load_gs_index(gs);
-
+ RELOAD_SEG(gs);
RELOAD_SEG(fs);
RELOAD_SEG(ds);
RELOAD_SEG(es);
@@ -337,17 +335,13 @@
void __user *fpstate,
struct pt_regs *regs, unsigned int mask)
{
- int tmp, err = 0;
+ int err = 0;
put_user_try {
- savesegment(gs, tmp);
- put_user_ex(tmp, (unsigned int __user *)&sc->gs);
- savesegment(fs, tmp);
- put_user_ex(tmp, (unsigned int __user *)&sc->fs);
- savesegment(ds, tmp);
- put_user_ex(tmp, (unsigned int __user *)&sc->ds);
- savesegment(es, tmp);
- put_user_ex(tmp, (unsigned int __user *)&sc->es);
+ put_user_ex(get_user_seg(gs), (unsigned int __user *)&sc->gs);
+ put_user_ex(get_user_seg(fs), (unsigned int __user *)&sc->fs);
+ put_user_ex(get_user_seg(ds), (unsigned int __user *)&sc->ds);
+ put_user_ex(get_user_seg(es), (unsigned int __user *)&sc->es);
put_user_ex(regs->di, &sc->di);
put_user_ex(regs->si, &sc->si);
@@ -488,11 +482,6 @@
regs->cs = __USER32_CS;
regs->ss = __USER32_DS;
-#if DEBUG_SIG
- printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
- current->comm, current->pid, frame, regs->ip, frame->pretcode);
-#endif
-
return 0;
}
@@ -574,10 +563,5 @@
regs->cs = __USER32_CS;
regs->ss = __USER32_DS;
-#if DEBUG_SIG
- printk(KERN_DEBUG "SIG deliver (%s:%d): sp=%p pc=%lx ra=%u\n",
- current->comm, current->pid, frame, regs->ip, frame->pretcode);
-#endif
-
return 0;
}
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index 4f8e820..683d0b4 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -124,10 +124,15 @@
/*
* ISA I/O bus memory addresses are 1:1 with the physical address.
+ * However, we truncate the address to unsigned int to avoid undesirable
+ * promitions in legacy drivers.
*/
-#define isa_virt_to_bus (unsigned long)virt_to_phys
-#define isa_page_to_bus page_to_phys
-#define isa_bus_to_virt phys_to_virt
+static inline unsigned int isa_virt_to_bus(volatile void *address)
+{
+ return (unsigned int)virt_to_phys(address);
+}
+#define isa_page_to_bus(page) ((unsigned int)page_to_phys(page))
+#define isa_bus_to_virt phys_to_virt
/*
* However PCI ones are not necessarily 1:1 and therefore these interfaces
diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h
index b07278c..8a285f3 100644
--- a/arch/x86/include/asm/irq_vectors.h
+++ b/arch/x86/include/asm/irq_vectors.h
@@ -128,7 +128,7 @@
#ifndef __ASSEMBLY__
static inline int invalid_vm86_irq(int irq)
{
- return irq < 3 || irq > 15;
+ return irq < FIRST_VM86_IRQ || irq > LAST_VM86_IRQ;
}
#endif
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index 5d98d0b..9320e2a 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -52,70 +52,14 @@
#endif
+#define GLOBAL(name) \
+ .globl name; \
+ name:
+
#ifdef CONFIG_X86_ALIGNMENT_16
#define __ALIGN .align 16,0x90
#define __ALIGN_STR ".align 16,0x90"
#endif
-/*
- * to check ENTRY_X86/END_X86 and
- * KPROBE_ENTRY_X86/KPROBE_END_X86
- * unbalanced-missed-mixed appearance
- */
-#define __set_entry_x86 .set ENTRY_X86_IN, 0
-#define __unset_entry_x86 .set ENTRY_X86_IN, 1
-#define __set_kprobe_x86 .set KPROBE_X86_IN, 0
-#define __unset_kprobe_x86 .set KPROBE_X86_IN, 1
-
-#define __macro_err_x86 .error "ENTRY_X86/KPROBE_X86 unbalanced,missed,mixed"
-
-#define __check_entry_x86 \
- .ifdef ENTRY_X86_IN; \
- .ifeq ENTRY_X86_IN; \
- __macro_err_x86; \
- .abort; \
- .endif; \
- .endif
-
-#define __check_kprobe_x86 \
- .ifdef KPROBE_X86_IN; \
- .ifeq KPROBE_X86_IN; \
- __macro_err_x86; \
- .abort; \
- .endif; \
- .endif
-
-#define __check_entry_kprobe_x86 \
- __check_entry_x86; \
- __check_kprobe_x86
-
-#define ENTRY_KPROBE_FINAL_X86 __check_entry_kprobe_x86
-
-#define ENTRY_X86(name) \
- __check_entry_kprobe_x86; \
- __set_entry_x86; \
- .globl name; \
- __ALIGN; \
- name:
-
-#define END_X86(name) \
- __unset_entry_x86; \
- __check_entry_kprobe_x86; \
- .size name, .-name
-
-#define KPROBE_ENTRY_X86(name) \
- __check_entry_kprobe_x86; \
- __set_kprobe_x86; \
- .pushsection .kprobes.text, "ax"; \
- .globl name; \
- __ALIGN; \
- name:
-
-#define KPROBE_END_X86(name) \
- __unset_kprobe_x86; \
- __check_entry_kprobe_x86; \
- .size name, .-name; \
- .popsection
-
#endif /* _ASM_X86_LINKAGE_H */
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index b5486aa..f1e4a79 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -33,12 +33,10 @@
/* 44=32+12, the limit we can fit into an unsigned long pfn */
#define __PHYSICAL_MASK_SHIFT 44
#define __VIRTUAL_MASK_SHIFT 32
-#define PAGETABLE_LEVELS 3
#else /* !CONFIG_X86_PAE */
#define __PHYSICAL_MASK_SHIFT 32
#define __VIRTUAL_MASK_SHIFT 32
-#define PAGETABLE_LEVELS 2
#endif /* CONFIG_X86_PAE */
#ifndef __ASSEMBLY__
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index bc73af3..d38c91b 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -1,8 +1,6 @@
#ifndef _ASM_X86_PAGE_64_DEFS_H
#define _ASM_X86_PAGE_64_DEFS_H
-#define PAGETABLE_LEVELS 4
-
#define THREAD_ORDER 1
#define THREAD_SIZE (PAGE_SIZE << THREAD_ORDER)
#define CURRENT_MASK (~(THREAD_SIZE - 1))
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 2c52ff7..2d625da 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -16,12 +16,6 @@
(ie, 32-bit PAE). */
#define PHYSICAL_PAGE_MASK (((signed long)PAGE_MASK) & __PHYSICAL_MASK)
-/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
-#define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK)
-
-/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */
-#define PTE_FLAGS_MASK (~PTE_PFN_MASK)
-
#define PMD_PAGE_SIZE (_AC(1, UL) << PMD_SHIFT)
#define PMD_PAGE_MASK (~(PMD_PAGE_SIZE-1))
diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index 09ae67e..daacc23 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -17,6 +17,7 @@
#endif /* !__ASSEMBLY__ */
#define SHARED_KERNEL_PMD 0
+#define PAGETABLE_LEVELS 2
/*
* traditional i386 two-level paging structure:
@@ -25,6 +26,7 @@
#define PGDIR_SHIFT 22
#define PTRS_PER_PGD 1024
+
/*
* the i386 is two-level, so we don't really have any
* PMD directory physically.
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index bcc8962..1bd5876 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -24,6 +24,8 @@
#define SHARED_KERNEL_PMD 1
#endif
+#define PAGETABLE_LEVELS 3
+
/*
* PGDIR_SHIFT determines what a top-level page table entry can map
*/
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 2f59135..fbf42b8 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -18,6 +18,7 @@
#endif /* !__ASSEMBLY__ */
#define SHARED_KERNEL_PMD 0
+#define PAGETABLE_LEVELS 4
/*
* PGDIR_SHIFT determines what a top-level page table entry can map
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 9dafe87..4d258ad 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -173,6 +173,12 @@
#include <linux/types.h>
+/* PTE_PFN_MASK extracts the PFN from a (pte|pmd|pud|pgd)val_t */
+#define PTE_PFN_MASK ((pteval_t)PHYSICAL_PAGE_MASK)
+
+/* PTE_FLAGS_MASK extracts the flags from a (pte|pmd|pud|pgd)val_t */
+#define PTE_FLAGS_MASK (~PTE_PFN_MASK)
+
typedef struct pgprot { pgprotval_t pgprot; } pgprot_t;
typedef struct { pgdval_t pgd; } pgd_t;
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index dabab1a..c7a98f7 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -403,7 +403,6 @@
#endif
#endif /* X86_64 */
-extern void print_cpu_info(struct cpuinfo_x86 *);
extern unsigned int xstate_size;
extern void free_thread_xstate(struct task_struct *);
extern struct kmem_cache *task_xstate_cachep;
@@ -862,6 +861,7 @@
* User space process size: 3GB (default).
*/
#define TASK_SIZE PAGE_OFFSET
+#define TASK_SIZE_MAX TASK_SIZE
#define STACK_TOP TASK_SIZE
#define STACK_TOP_MAX STACK_TOP
@@ -921,7 +921,7 @@
/*
* User space process size. 47bits minus one guard page.
*/
-#define TASK_SIZE64 ((1UL << 47) - PAGE_SIZE)
+#define TASK_SIZE_MAX ((1UL << 47) - PAGE_SIZE)
/* This decides where the kernel will search for a free chunk of vm
* space during mmap's.
@@ -930,12 +930,12 @@
0xc0000000 : 0xFFFFe000)
#define TASK_SIZE (test_thread_flag(TIF_IA32) ? \
- IA32_PAGE_OFFSET : TASK_SIZE64)
+ IA32_PAGE_OFFSET : TASK_SIZE_MAX)
#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_IA32)) ? \
- IA32_PAGE_OFFSET : TASK_SIZE64)
+ IA32_PAGE_OFFSET : TASK_SIZE_MAX)
#define STACK_TOP TASK_SIZE
-#define STACK_TOP_MAX TASK_SIZE64
+#define STACK_TOP_MAX TASK_SIZE_MAX
#define INIT_THREAD { \
.sp0 = (unsigned long)&init_stack + sizeof(init_stack) \
diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h
index 258ef73..7043408 100644
--- a/arch/x86/include/asm/syscalls.h
+++ b/arch/x86/include/asm/syscalls.h
@@ -82,7 +82,7 @@
/* kernel/signal_64.c */
asmlinkage long sys_sigaltstack(const stack_t __user *, stack_t __user *,
struct pt_regs *);
-asmlinkage long sys_rt_sigreturn(struct pt_regs *);
+long sys_rt_sigreturn(struct pt_regs *);
/* kernel/sys_x86_64.c */
asmlinkage long sys_mmap(unsigned long, unsigned long, unsigned long,
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index 84210c4..987a2c1 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -192,14 +192,26 @@
unsigned size)
{
might_sleep();
- return __copy_user_nocache(dst, src, size, 1);
+ /*
+ * In practice this limit means that large file write()s
+ * which get chunked to 4K copies get handled via
+ * non-temporal stores here. Smaller writes get handled
+ * via regular __copy_from_user():
+ */
+ if (likely(size >= PAGE_SIZE))
+ return __copy_user_nocache(dst, src, size, 1);
+ else
+ return __copy_from_user(dst, src, size);
}
static inline int __copy_from_user_inatomic_nocache(void *dst,
const void __user *src,
unsigned size)
{
- return __copy_user_nocache(dst, src, size, 0);
+ if (likely(size >= PAGE_SIZE))
+ return __copy_user_nocache(dst, src, size, 0);
+ else
+ return __copy_from_user_inatomic(dst, src, size);
}
unsigned long
diff --git a/arch/x86/kernel/acpi/realmode/wakeup.S b/arch/x86/kernel/acpi/realmode/wakeup.S
index 3355973..580b4e2 100644
--- a/arch/x86/kernel/acpi/realmode/wakeup.S
+++ b/arch/x86/kernel/acpi/realmode/wakeup.S
@@ -3,8 +3,8 @@
*/
#include <asm/segment.h>
#include <asm/msr-index.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
+#include <asm/page_types.h>
+#include <asm/pgtable_types.h>
#include <asm/processor-flags.h>
.code16
diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S
index a12e6a9..8ded418 100644
--- a/arch/x86/kernel/acpi/wakeup_32.S
+++ b/arch/x86/kernel/acpi/wakeup_32.S
@@ -1,7 +1,7 @@
.section .text.page_aligned
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
# Copyright 2003, 2008 Pavel Machek <pavel@suse.cz>, distribute under GPLv2
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index 96258d9..8ea5164 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -1,8 +1,8 @@
.text
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
+#include <asm/pgtable_types.h>
+#include <asm/page_types.h>
#include <asm/msr.h>
#include <asm/asm-offsets.h>
diff --git a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
index c2f930d..41ab3f0 100644
--- a/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
+++ b/arch/x86/kernel/cpu/cpufreq/e_powersaver.c
@@ -204,12 +204,12 @@
}
/* Enable Enhanced PowerSaver */
rdmsrl(MSR_IA32_MISC_ENABLE, val);
- if (!(val & 1 << 16)) {
- val |= 1 << 16;
+ if (!(val & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
+ val |= MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP;
wrmsrl(MSR_IA32_MISC_ENABLE, val);
/* Can be locked at 0 */
rdmsrl(MSR_IA32_MISC_ENABLE, val);
- if (!(val & 1 << 16)) {
+ if (!(val & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
printk(KERN_INFO "eps: Can't enable Enhanced PowerSaver\n");
return -ENODEV;
}
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
index f089982..c9f1fdc 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-centrino.c
@@ -390,14 +390,14 @@
enable it if not. */
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
- if (!(l & (1<<16))) {
- l |= (1<<16);
+ if (!(l & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
+ l |= MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP;
dprintk("trying to enable Enhanced SpeedStep (%x)\n", l);
wrmsr(MSR_IA32_MISC_ENABLE, l, h);
/* check to see if it stuck */
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
- if (!(l & (1<<16))) {
+ if (!(l & MSR_IA32_MISC_ENABLE_ENHANCED_SPEEDSTEP)) {
printk(KERN_INFO PFX
"couldn't enable Enhanced SpeedStep\n");
return -ENODEV;
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 7aeef1d..25c559b 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -146,10 +146,10 @@
*/
if ((c->x86 == 15) && (c->x86_model == 1) && (c->x86_mask == 1)) {
rdmsr(MSR_IA32_MISC_ENABLE, lo, hi);
- if ((lo & (1<<9)) == 0) {
+ if ((lo & MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE) == 0) {
printk (KERN_INFO "CPU: C0 stepping P4 Xeon detected.\n");
printk (KERN_INFO "CPU: Disabling hardware prefetching (Errata 037)\n");
- lo |= (1<<9); /* Disable hw prefetching */
+ lo |= MSR_IA32_MISC_ENABLE_PREFETCH_DISABLE;
wrmsr (MSR_IA32_MISC_ENABLE, lo, hi);
}
}
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index 4b7d78c..aa5e287 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -49,13 +49,13 @@
*/
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
h = apic_read(APIC_LVTTHMR);
- if ((l & (1 << 3)) && (h & APIC_DM_SMI)) {
+ if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
printk(KERN_DEBUG
"CPU%d: Thermal monitoring handled by SMI\n", cpu);
return;
}
- if (cpu_has(c, X86_FEATURE_TM2) && (l & (1 << 13)))
+ if (cpu_has(c, X86_FEATURE_TM2) && (l & MSR_IA32_MISC_ENABLE_TM2))
tm2 = 1;
if (h & APIC_VECTOR_MASK) {
@@ -73,7 +73,7 @@
wrmsr(MSR_IA32_THERM_INTERRUPT, l | 0x03, h);
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
- wrmsr(MSR_IA32_MISC_ENABLE, l | (1 << 3), h);
+ wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h);
l = apic_read(APIC_LVTTHMR);
apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
diff --git a/arch/x86/kernel/cpu/mcheck/p4.c b/arch/x86/kernel/cpu/mcheck/p4.c
index 9b60fce..f53bdcb 100644
--- a/arch/x86/kernel/cpu/mcheck/p4.c
+++ b/arch/x86/kernel/cpu/mcheck/p4.c
@@ -85,7 +85,7 @@
*/
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
h = apic_read(APIC_LVTTHMR);
- if ((l & (1<<3)) && (h & APIC_DM_SMI)) {
+ if ((l & MSR_IA32_MISC_ENABLE_TM1) && (h & APIC_DM_SMI)) {
printk(KERN_DEBUG "CPU%d: Thermal monitoring handled by SMI\n",
cpu);
return; /* -EBUSY */
@@ -111,7 +111,7 @@
vendor_thermal_interrupt = intel_thermal_interrupt;
rdmsr(MSR_IA32_MISC_ENABLE, l, h);
- wrmsr(MSR_IA32_MISC_ENABLE, l | (1<<3), h);
+ wrmsr(MSR_IA32_MISC_ENABLE, l | MSR_IA32_MISC_ENABLE_TM1, h);
l = apic_read(APIC_LVTTHMR);
apic_write(APIC_LVTTHMR, l & ~APIC_LVT_MASKED);
diff --git a/arch/x86/kernel/efi_stub_32.S b/arch/x86/kernel/efi_stub_32.S
index ef00bb7..fbe66e6 100644
--- a/arch/x86/kernel/efi_stub_32.S
+++ b/arch/x86/kernel/efi_stub_32.S
@@ -6,7 +6,7 @@
*/
#include <linux/linkage.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
/*
* efi_call_phys(void *, ...) is a function with variable parameters.
@@ -113,6 +113,7 @@
movl (%edx), %ecx
pushl %ecx
ret
+ENDPROC(efi_call_phys)
.previous
.data
diff --git a/arch/x86/kernel/efi_stub_64.S b/arch/x86/kernel/efi_stub_64.S
index 99b47d4..4c07cca 100644
--- a/arch/x86/kernel/efi_stub_64.S
+++ b/arch/x86/kernel/efi_stub_64.S
@@ -41,6 +41,7 @@
addq $32, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call0)
ENTRY(efi_call1)
SAVE_XMM
@@ -50,6 +51,7 @@
addq $32, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call1)
ENTRY(efi_call2)
SAVE_XMM
@@ -59,6 +61,7 @@
addq $32, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call2)
ENTRY(efi_call3)
SAVE_XMM
@@ -69,6 +72,7 @@
addq $32, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call3)
ENTRY(efi_call4)
SAVE_XMM
@@ -80,6 +84,7 @@
addq $32, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call4)
ENTRY(efi_call5)
SAVE_XMM
@@ -92,6 +97,7 @@
addq $48, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call5)
ENTRY(efi_call6)
SAVE_XMM
@@ -107,3 +113,4 @@
addq $48, %rsp
RESTORE_XMM
ret
+ENDPROC(efi_call6)
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index e992068..899e893 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -47,7 +47,7 @@
#include <asm/errno.h>
#include <asm/segment.h>
#include <asm/smp.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/desc.h>
#include <asm/percpu.h>
#include <asm/dwarf2.h>
@@ -1359,7 +1359,7 @@
CFI_ADJUST_CFA_OFFSET 4
pushl %esp
CFI_ADJUST_CFA_OFFSET 4
- addw $4, (%esp)
+ addl $4, (%esp)
/* copy the iret frame of 12 bytes */
.rept 3
pushl 16(%esp)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index fbcf96b..83d1836 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -48,7 +48,7 @@
#include <asm/unistd.h>
#include <asm/thread_info.h>
#include <asm/hw_irq.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/irqflags.h>
#include <asm/paravirt.h>
#include <asm/ftrace.h>
@@ -77,20 +77,17 @@
movq 8(%rbp), %rsi
subq $MCOUNT_INSN_SIZE, %rdi
-.globl ftrace_call
-ftrace_call:
+GLOBAL(ftrace_call)
call ftrace_stub
MCOUNT_RESTORE_FRAME
#ifdef CONFIG_FUNCTION_GRAPH_TRACER
-.globl ftrace_graph_call
-ftrace_graph_call:
+GLOBAL(ftrace_graph_call)
jmp ftrace_stub
#endif
-.globl ftrace_stub
-ftrace_stub:
+GLOBAL(ftrace_stub)
retq
END(ftrace_caller)
@@ -110,8 +107,7 @@
jnz ftrace_graph_caller
#endif
-.globl ftrace_stub
-ftrace_stub:
+GLOBAL(ftrace_stub)
retq
trace:
@@ -148,9 +144,7 @@
retq
END(ftrace_graph_caller)
-
-.globl return_to_handler
-return_to_handler:
+GLOBAL(return_to_handler)
subq $80, %rsp
movq %rax, (%rsp)
@@ -188,6 +182,7 @@
ENTRY(native_usergs_sysret64)
swapgs
sysretq
+ENDPROC(native_usergs_sysret64)
#endif /* CONFIG_PARAVIRT */
@@ -633,16 +628,14 @@
* Syscall return path ending with IRET.
* Has correct top of stack, but partial stack frame.
*/
- .globl int_ret_from_sys_call
- .globl int_with_check
-int_ret_from_sys_call:
+GLOBAL(int_ret_from_sys_call)
DISABLE_INTERRUPTS(CLBR_NONE)
TRACE_IRQS_OFF
testl $3,CS-ARGOFFSET(%rsp)
je retint_restore_args
movl $_TIF_ALLWORK_MASK,%edi
/* edi: mask to check */
-int_with_check:
+GLOBAL(int_with_check)
LOCKDEP_SYS_EXIT_IRQ
GET_THREAD_INFO(%rcx)
movl TI_flags(%rcx),%edx
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 2a0aad7..c32ca19 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -11,8 +11,8 @@
#include <linux/init.h>
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
-#include <asm/pgtable.h>
+#include <asm/page_types.h>
+#include <asm/pgtable_types.h>
#include <asm/desc.h>
#include <asm/cache.h>
#include <asm/thread_info.h>
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 2e648e3..54b29bb 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -329,8 +329,6 @@
#endif /* CONFIG_EARLY_PRINTK */
.previous
-.balign PAGE_SIZE
-
#define NEXT_PAGE(name) \
.balign PAGE_SIZE; \
ENTRY(name)
@@ -419,7 +417,7 @@
.section .bss, "aw", @nobits
.align L1_CACHE_BYTES
ENTRY(idt_table)
- .skip 256 * 16
+ .skip IDT_ENTRIES * 16
.section .bss.page_aligned, "aw", @nobits
.align PAGE_SIZE
diff --git a/arch/x86/kernel/machine_kexec_32.c b/arch/x86/kernel/machine_kexec_32.c
index 37f4200..f5fc8c7 100644
--- a/arch/x86/kernel/machine_kexec_32.c
+++ b/arch/x86/kernel/machine_kexec_32.c
@@ -121,7 +121,7 @@
static void machine_kexec_prepare_page_tables(struct kimage *image)
{
void *control_page;
- pmd_t *pmd = 0;
+ pmd_t *pmd = NULL;
control_page = page_address(image->control_code_page);
#ifdef CONFIG_X86_PAE
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index d2f7cd5..fb2159a 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -268,7 +268,7 @@
if (test_tsk_thread_flag(task, TIF_IA32))
return IA32_PAGE_OFFSET - 3;
#endif
- return TASK_SIZE64 - 7;
+ return TASK_SIZE_MAX - 7;
}
#endif /* CONFIG_X86_32 */
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index a160f31..2064d0a 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -7,7 +7,7 @@
*/
#include <linux/linkage.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/kexec.h>
#include <asm/processor-flags.h>
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index b0bbdd4..d32cfb2 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -7,10 +7,10 @@
*/
#include <linux/linkage.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/kexec.h>
#include <asm/processor-flags.h>
-#include <asm/pgtable.h>
+#include <asm/pgtable_types.h>
/*
* Must be relocatable PIC code callable as a C function
diff --git a/arch/x86/kernel/trampoline_32.S b/arch/x86/kernel/trampoline_32.S
index d8ccc3c..66d874e 100644
--- a/arch/x86/kernel/trampoline_32.S
+++ b/arch/x86/kernel/trampoline_32.S
@@ -29,7 +29,7 @@
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
/* We can free up trampoline after bootup if cpu hotplug is not supported. */
#ifndef CONFIG_HOTPLUG_CPU
diff --git a/arch/x86/kernel/trampoline_64.S b/arch/x86/kernel/trampoline_64.S
index 95a012a..cddfb8d 100644
--- a/arch/x86/kernel/trampoline_64.S
+++ b/arch/x86/kernel/trampoline_64.S
@@ -25,8 +25,8 @@
*/
#include <linux/linkage.h>
-#include <asm/pgtable.h>
-#include <asm/page.h>
+#include <asm/pgtable_types.h>
+#include <asm/page_types.h>
#include <asm/msr.h>
#include <asm/segment.h>
#include <asm/processor-flags.h>
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index c8c0a7e..c05430a 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -942,7 +942,7 @@
info.si_signo = SIGILL;
info.si_errno = 0;
info.si_code = ILL_BADSTK;
- info.si_addr = 0;
+ info.si_addr = NULL;
if (notify_die(DIE_TRAP, "iret exception",
regs, error_code, 32, SIGILL) == NOTIFY_STOP)
return;
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index 49b4cd6..33a788d 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -287,8 +287,7 @@
static cycle_t read_real_cycles(void)
{
cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
- return ret >= clocksource_vmi.cycle_last ?
- ret : clocksource_vmi.cycle_last;
+ return max(ret, clocksource_vmi.cycle_last);
}
static struct clocksource clocksource_vmi = {
diff --git a/arch/x86/kernel/vmlinux_32.lds.S b/arch/x86/kernel/vmlinux_32.lds.S
index 3eba7f7..0d86096 100644
--- a/arch/x86/kernel/vmlinux_32.lds.S
+++ b/arch/x86/kernel/vmlinux_32.lds.S
@@ -12,7 +12,7 @@
#include <asm-generic/vmlinux.lds.h>
#include <asm/thread_info.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/cache.h>
#include <asm/boot.h>
diff --git a/arch/x86/kernel/vmlinux_64.lds.S b/arch/x86/kernel/vmlinux_64.lds.S
index 087a7f2..fbfced6 100644
--- a/arch/x86/kernel/vmlinux_64.lds.S
+++ b/arch/x86/kernel/vmlinux_64.lds.S
@@ -6,7 +6,7 @@
#include <asm-generic/vmlinux.lds.h>
#include <asm/asm-offsets.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#undef i386 /* in case the preprocessor is a 32bit one */
diff --git a/arch/x86/lib/getuser.S b/arch/x86/lib/getuser.S
index ad37400..51f1504 100644
--- a/arch/x86/lib/getuser.S
+++ b/arch/x86/lib/getuser.S
@@ -28,7 +28,7 @@
#include <linux/linkage.h>
#include <asm/dwarf2.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/errno.h>
#include <asm/asm-offsets.h>
#include <asm/thread_info.h>
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 2964417..a03b727 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1,74 +1,79 @@
/*
* Copyright (C) 1995 Linus Torvalds
- * Copyright (C) 2001,2002 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
+ * Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
*/
-
-#include <linux/signal.h>
-#include <linux/sched.h>
-#include <linux/kernel.h>
-#include <linux/errno.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <linux/ptrace.h>
-#include <linux/mmiotrace.h>
-#include <linux/mman.h>
-#include <linux/mm.h>
-#include <linux/smp.h>
#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/tty.h>
-#include <linux/vt_kern.h> /* For unblank_screen() */
+#include <linux/mmiotrace.h>
+#include <linux/bootmem.h>
#include <linux/compiler.h>
#include <linux/highmem.h>
-#include <linux/bootmem.h> /* for max_low_pfn */
-#include <linux/vmalloc.h>
-#include <linux/module.h>
#include <linux/kprobes.h>
#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/vt_kern.h>
+#include <linux/signal.h>
+#include <linux/kernel.h>
+#include <linux/ptrace.h>
+#include <linux/string.h>
+#include <linux/module.h>
#include <linux/kdebug.h>
+#include <linux/errno.h>
#include <linux/magic.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/mman.h>
+#include <linux/tty.h>
+#include <linux/smp.h>
+#include <linux/mm.h>
-#include <asm/system.h>
-#include <asm/desc.h>
-#include <asm/segment.h>
-#include <asm/pgalloc.h>
-#include <asm/smp.h>
-#include <asm/tlbflush.h>
-#include <asm/proto.h>
#include <asm-generic/sections.h>
+
+#include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+#include <asm/segment.h>
+#include <asm/system.h>
+#include <asm/proto.h>
#include <asm/traps.h>
+#include <asm/desc.h>
/*
- * Page fault error code bits
- * bit 0 == 0 means no page found, 1 means protection fault
- * bit 1 == 0 means read, 1 means write
- * bit 2 == 0 means kernel, 1 means user-mode
- * bit 3 == 1 means use of reserved bit detected
- * bit 4 == 1 means fault was an instruction fetch
+ * Page fault error code bits:
+ *
+ * bit 0 == 0: no page found 1: protection fault
+ * bit 1 == 0: read access 1: write access
+ * bit 2 == 0: kernel-mode access 1: user-mode access
+ * bit 3 == 1: use of reserved bit detected
+ * bit 4 == 1: fault was an instruction fetch
*/
-#define PF_PROT (1<<0)
-#define PF_WRITE (1<<1)
-#define PF_USER (1<<2)
-#define PF_RSVD (1<<3)
-#define PF_INSTR (1<<4)
+enum x86_pf_error_code {
+ PF_PROT = 1 << 0,
+ PF_WRITE = 1 << 1,
+ PF_USER = 1 << 2,
+ PF_RSVD = 1 << 3,
+ PF_INSTR = 1 << 4,
+};
+
+/*
+ * Returns 0 if mmiotrace is disabled, or if the fault is not
+ * handled by mmiotrace:
+ */
static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr)
{
-#ifdef CONFIG_MMIOTRACE
if (unlikely(is_kmmio_active()))
if (kmmio_handler(regs, addr) == 1)
return -1;
-#endif
return 0;
}
static inline int notify_page_fault(struct pt_regs *regs)
{
-#ifdef CONFIG_KPROBES
int ret = 0;
/* kprobe_running() needs smp_processor_id() */
- if (!user_mode_vm(regs)) {
+ if (kprobes_built_in() && !user_mode_vm(regs)) {
preempt_disable();
if (kprobe_running() && kprobe_fault_handler(regs, 14))
ret = 1;
@@ -76,29 +81,76 @@
}
return ret;
-#else
- return 0;
-#endif
}
/*
- * X86_32
- * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
- * Check that here and ignore it.
+ * Prefetch quirks:
*
- * X86_64
- * Sometimes the CPU reports invalid exceptions on prefetch.
- * Check that here and ignore it.
+ * 32-bit mode:
*
- * Opcode checker based on code by Richard Brunner
+ * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
+ * Check that here and ignore it.
+ *
+ * 64-bit mode:
+ *
+ * Sometimes the CPU reports invalid exceptions on prefetch.
+ * Check that here and ignore it.
+ *
+ * Opcode checker based on code by Richard Brunner.
*/
-static int is_prefetch(struct pt_regs *regs, unsigned long error_code,
- unsigned long addr)
+static inline int
+check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
+ unsigned char opcode, int *prefetch)
{
- unsigned char *instr;
- int scan_more = 1;
- int prefetch = 0;
+ unsigned char instr_hi = opcode & 0xf0;
+ unsigned char instr_lo = opcode & 0x0f;
+
+ switch (instr_hi) {
+ case 0x20:
+ case 0x30:
+ /*
+ * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes.
+ * In X86_64 long mode, the CPU will signal invalid
+ * opcode if some of these prefixes are present so
+ * X86_64 will never get here anyway
+ */
+ return ((instr_lo & 7) == 0x6);
+#ifdef CONFIG_X86_64
+ case 0x40:
+ /*
+ * In AMD64 long mode 0x40..0x4F are valid REX prefixes
+ * Need to figure out under what instruction mode the
+ * instruction was issued. Could check the LDT for lm,
+ * but for now it's good enough to assume that long
+ * mode only uses well known segments or kernel.
+ */
+ return (!user_mode(regs)) || (regs->cs == __USER_CS);
+#endif
+ case 0x60:
+ /* 0x64 thru 0x67 are valid prefixes in all modes. */
+ return (instr_lo & 0xC) == 0x4;
+ case 0xF0:
+ /* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */
+ return !instr_lo || (instr_lo>>1) == 1;
+ case 0x00:
+ /* Prefetch instruction is 0x0F0D or 0x0F18 */
+ if (probe_kernel_address(instr, opcode))
+ return 0;
+
+ *prefetch = (instr_lo == 0xF) &&
+ (opcode == 0x0D || opcode == 0x18);
+ return 0;
+ default:
+ return 0;
+ }
+}
+
+static int
+is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
+{
unsigned char *max_instr;
+ unsigned char *instr;
+ int prefetch = 0;
/*
* If it was a exec (instruction fetch) fault on NX page, then
@@ -107,164 +159,42 @@
if (error_code & PF_INSTR)
return 0;
- instr = (unsigned char *)convert_ip_to_linear(current, regs);
+ instr = (void *)convert_ip_to_linear(current, regs);
max_instr = instr + 15;
if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE)
return 0;
- while (scan_more && instr < max_instr) {
+ while (instr < max_instr) {
unsigned char opcode;
- unsigned char instr_hi;
- unsigned char instr_lo;
if (probe_kernel_address(instr, opcode))
break;
- instr_hi = opcode & 0xf0;
- instr_lo = opcode & 0x0f;
instr++;
- switch (instr_hi) {
- case 0x20:
- case 0x30:
- /*
- * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes.
- * In X86_64 long mode, the CPU will signal invalid
- * opcode if some of these prefixes are present so
- * X86_64 will never get here anyway
- */
- scan_more = ((instr_lo & 7) == 0x6);
+ if (!check_prefetch_opcode(regs, instr, opcode, &prefetch))
break;
-#ifdef CONFIG_X86_64
- case 0x40:
- /*
- * In AMD64 long mode 0x40..0x4F are valid REX prefixes
- * Need to figure out under what instruction mode the
- * instruction was issued. Could check the LDT for lm,
- * but for now it's good enough to assume that long
- * mode only uses well known segments or kernel.
- */
- scan_more = (!user_mode(regs)) || (regs->cs == __USER_CS);
- break;
-#endif
- case 0x60:
- /* 0x64 thru 0x67 are valid prefixes in all modes. */
- scan_more = (instr_lo & 0xC) == 0x4;
- break;
- case 0xF0:
- /* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */
- scan_more = !instr_lo || (instr_lo>>1) == 1;
- break;
- case 0x00:
- /* Prefetch instruction is 0x0F0D or 0x0F18 */
- scan_more = 0;
-
- if (probe_kernel_address(instr, opcode))
- break;
- prefetch = (instr_lo == 0xF) &&
- (opcode == 0x0D || opcode == 0x18);
- break;
- default:
- scan_more = 0;
- break;
- }
}
return prefetch;
}
-static void force_sig_info_fault(int si_signo, int si_code,
- unsigned long address, struct task_struct *tsk)
+static void
+force_sig_info_fault(int si_signo, int si_code, unsigned long address,
+ struct task_struct *tsk)
{
siginfo_t info;
- info.si_signo = si_signo;
- info.si_errno = 0;
- info.si_code = si_code;
- info.si_addr = (void __user *)address;
+ info.si_signo = si_signo;
+ info.si_errno = 0;
+ info.si_code = si_code;
+ info.si_addr = (void __user *)address;
+
force_sig_info(si_signo, &info, tsk);
}
-#ifdef CONFIG_X86_64
-static int bad_address(void *p)
-{
- unsigned long dummy;
- return probe_kernel_address((unsigned long *)p, dummy);
-}
-#endif
-
-static void dump_pagetable(unsigned long address)
-{
-#ifdef CONFIG_X86_32
- __typeof__(pte_val(__pte(0))) page;
-
- page = read_cr3();
- page = ((__typeof__(page) *) __va(page))[address >> PGDIR_SHIFT];
-#ifdef CONFIG_X86_PAE
- printk("*pdpt = %016Lx ", page);
- if ((page >> PAGE_SHIFT) < max_low_pfn
- && page & _PAGE_PRESENT) {
- page &= PAGE_MASK;
- page = ((__typeof__(page) *) __va(page))[(address >> PMD_SHIFT)
- & (PTRS_PER_PMD - 1)];
- printk(KERN_CONT "*pde = %016Lx ", page);
- page &= ~_PAGE_NX;
- }
-#else
- printk("*pde = %08lx ", page);
-#endif
-
- /*
- * We must not directly access the pte in the highpte
- * case if the page table is located in highmem.
- * And let's rather not kmap-atomic the pte, just in case
- * it's allocated already.
- */
- if ((page >> PAGE_SHIFT) < max_low_pfn
- && (page & _PAGE_PRESENT)
- && !(page & _PAGE_PSE)) {
- page &= PAGE_MASK;
- page = ((__typeof__(page) *) __va(page))[(address >> PAGE_SHIFT)
- & (PTRS_PER_PTE - 1)];
- printk("*pte = %0*Lx ", sizeof(page)*2, (u64)page);
- }
-
- printk("\n");
-#else /* CONFIG_X86_64 */
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *pte;
-
- pgd = (pgd_t *)read_cr3();
-
- pgd = __va((unsigned long)pgd & PHYSICAL_PAGE_MASK);
- pgd += pgd_index(address);
- if (bad_address(pgd)) goto bad;
- printk("PGD %lx ", pgd_val(*pgd));
- if (!pgd_present(*pgd)) goto ret;
-
- pud = pud_offset(pgd, address);
- if (bad_address(pud)) goto bad;
- printk("PUD %lx ", pud_val(*pud));
- if (!pud_present(*pud) || pud_large(*pud))
- goto ret;
-
- pmd = pmd_offset(pud, address);
- if (bad_address(pmd)) goto bad;
- printk("PMD %lx ", pmd_val(*pmd));
- if (!pmd_present(*pmd) || pmd_large(*pmd)) goto ret;
-
- pte = pte_offset_kernel(pmd, address);
- if (bad_address(pte)) goto bad;
- printk("PTE %lx", pte_val(*pte));
-ret:
- printk("\n");
- return;
-bad:
- printk("BAD\n");
-#endif
-}
+DEFINE_SPINLOCK(pgd_lock);
+LIST_HEAD(pgd_list);
#ifdef CONFIG_X86_32
static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
@@ -285,7 +215,6 @@
* and redundant with the set_pmd() on non-PAE. As would
* set_pud.
*/
-
pud = pud_offset(pgd, address);
pud_k = pud_offset(pgd_k, address);
if (!pud_present(*pud_k))
@@ -295,46 +224,334 @@
pmd_k = pmd_offset(pud_k, address);
if (!pmd_present(*pmd_k))
return NULL;
+
if (!pmd_present(*pmd)) {
set_pmd(pmd, *pmd_k);
arch_flush_lazy_mmu_mode();
- } else
+ } else {
BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
+ }
+
return pmd_k;
}
+
+void vmalloc_sync_all(void)
+{
+ unsigned long address;
+
+ if (SHARED_KERNEL_PMD)
+ return;
+
+ for (address = VMALLOC_START & PMD_MASK;
+ address >= TASK_SIZE && address < FIXADDR_TOP;
+ address += PMD_SIZE) {
+
+ unsigned long flags;
+ struct page *page;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+ list_for_each_entry(page, &pgd_list, lru) {
+ if (!vmalloc_sync_one(page_address(page), address))
+ break;
+ }
+ spin_unlock_irqrestore(&pgd_lock, flags);
+ }
+}
+
+/*
+ * 32-bit:
+ *
+ * Handle a fault on the vmalloc or module mapping area
+ */
+static noinline int vmalloc_fault(unsigned long address)
+{
+ unsigned long pgd_paddr;
+ pmd_t *pmd_k;
+ pte_t *pte_k;
+
+ /* Make sure we are in vmalloc area: */
+ if (!(address >= VMALLOC_START && address < VMALLOC_END))
+ return -1;
+
+ /*
+ * Synchronize this task's top level page-table
+ * with the 'reference' page table.
+ *
+ * Do _not_ use "current" here. We might be inside
+ * an interrupt in the middle of a task switch..
+ */
+ pgd_paddr = read_cr3();
+ pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
+ if (!pmd_k)
+ return -1;
+
+ pte_k = pte_offset_kernel(pmd_k, address);
+ if (!pte_present(*pte_k))
+ return -1;
+
+ return 0;
+}
+
+/*
+ * Did it hit the DOS screen memory VA from vm86 mode?
+ */
+static inline void
+check_v8086_mode(struct pt_regs *regs, unsigned long address,
+ struct task_struct *tsk)
+{
+ unsigned long bit;
+
+ if (!v8086_mode(regs))
+ return;
+
+ bit = (address - 0xA0000) >> PAGE_SHIFT;
+ if (bit < 32)
+ tsk->thread.screen_bitmap |= 1 << bit;
+}
+
+static void dump_pagetable(unsigned long address)
+{
+ __typeof__(pte_val(__pte(0))) page;
+
+ page = read_cr3();
+ page = ((__typeof__(page) *) __va(page))[address >> PGDIR_SHIFT];
+
+#ifdef CONFIG_X86_PAE
+ printk("*pdpt = %016Lx ", page);
+ if ((page >> PAGE_SHIFT) < max_low_pfn
+ && page & _PAGE_PRESENT) {
+ page &= PAGE_MASK;
+ page = ((__typeof__(page) *) __va(page))[(address >> PMD_SHIFT)
+ & (PTRS_PER_PMD - 1)];
+ printk(KERN_CONT "*pde = %016Lx ", page);
+ page &= ~_PAGE_NX;
+ }
+#else
+ printk("*pde = %08lx ", page);
#endif
-#ifdef CONFIG_X86_64
+ /*
+ * We must not directly access the pte in the highpte
+ * case if the page table is located in highmem.
+ * And let's rather not kmap-atomic the pte, just in case
+ * it's allocated already:
+ */
+ if ((page >> PAGE_SHIFT) < max_low_pfn
+ && (page & _PAGE_PRESENT)
+ && !(page & _PAGE_PSE)) {
+
+ page &= PAGE_MASK;
+ page = ((__typeof__(page) *) __va(page))[(address >> PAGE_SHIFT)
+ & (PTRS_PER_PTE - 1)];
+ printk("*pte = %0*Lx ", sizeof(page)*2, (u64)page);
+ }
+
+ printk("\n");
+}
+
+#else /* CONFIG_X86_64: */
+
+void vmalloc_sync_all(void)
+{
+ unsigned long address;
+
+ for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
+ address += PGDIR_SIZE) {
+
+ const pgd_t *pgd_ref = pgd_offset_k(address);
+ unsigned long flags;
+ struct page *page;
+
+ if (pgd_none(*pgd_ref))
+ continue;
+
+ spin_lock_irqsave(&pgd_lock, flags);
+ list_for_each_entry(page, &pgd_list, lru) {
+ pgd_t *pgd;
+ pgd = (pgd_t *)page_address(page) + pgd_index(address);
+ if (pgd_none(*pgd))
+ set_pgd(pgd, *pgd_ref);
+ else
+ BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+ }
+ spin_unlock_irqrestore(&pgd_lock, flags);
+ }
+}
+
+/*
+ * 64-bit:
+ *
+ * Handle a fault on the vmalloc area
+ *
+ * This assumes no large pages in there.
+ */
+static noinline int vmalloc_fault(unsigned long address)
+{
+ pgd_t *pgd, *pgd_ref;
+ pud_t *pud, *pud_ref;
+ pmd_t *pmd, *pmd_ref;
+ pte_t *pte, *pte_ref;
+
+ /* Make sure we are in vmalloc area: */
+ if (!(address >= VMALLOC_START && address < VMALLOC_END))
+ return -1;
+
+ /*
+ * Copy kernel mappings over when needed. This can also
+ * happen within a race in page table update. In the later
+ * case just flush:
+ */
+ pgd = pgd_offset(current->active_mm, address);
+ pgd_ref = pgd_offset_k(address);
+ if (pgd_none(*pgd_ref))
+ return -1;
+
+ if (pgd_none(*pgd))
+ set_pgd(pgd, *pgd_ref);
+ else
+ BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+
+ /*
+ * Below here mismatches are bugs because these lower tables
+ * are shared:
+ */
+
+ pud = pud_offset(pgd, address);
+ pud_ref = pud_offset(pgd_ref, address);
+ if (pud_none(*pud_ref))
+ return -1;
+
+ if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
+ BUG();
+
+ pmd = pmd_offset(pud, address);
+ pmd_ref = pmd_offset(pud_ref, address);
+ if (pmd_none(*pmd_ref))
+ return -1;
+
+ if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
+ BUG();
+
+ pte_ref = pte_offset_kernel(pmd_ref, address);
+ if (!pte_present(*pte_ref))
+ return -1;
+
+ pte = pte_offset_kernel(pmd, address);
+
+ /*
+ * Don't use pte_page here, because the mappings can point
+ * outside mem_map, and the NUMA hash lookup cannot handle
+ * that:
+ */
+ if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref))
+ BUG();
+
+ return 0;
+}
+
static const char errata93_warning[] =
KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n"
KERN_ERR "******* Working around it, but it may cause SEGVs or burn power.\n"
KERN_ERR "******* Please consider a BIOS update.\n"
KERN_ERR "******* Disabling USB legacy in the BIOS may also help.\n";
-#endif
-/* Workaround for K8 erratum #93 & buggy BIOS.
- BIOS SMM functions are required to use a specific workaround
- to avoid corruption of the 64bit RIP register on C stepping K8.
- A lot of BIOS that didn't get tested properly miss this.
- The OS sees this as a page fault with the upper 32bits of RIP cleared.
- Try to work around it here.
- Note we only handle faults in kernel here.
- Does nothing for X86_32
+/*
+ * No vm86 mode in 64-bit mode:
+ */
+static inline void
+check_v8086_mode(struct pt_regs *regs, unsigned long address,
+ struct task_struct *tsk)
+{
+}
+
+static int bad_address(void *p)
+{
+ unsigned long dummy;
+
+ return probe_kernel_address((unsigned long *)p, dummy);
+}
+
+static void dump_pagetable(unsigned long address)
+{
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+ pte_t *pte;
+
+ pgd = (pgd_t *)read_cr3();
+
+ pgd = __va((unsigned long)pgd & PHYSICAL_PAGE_MASK);
+
+ pgd += pgd_index(address);
+ if (bad_address(pgd))
+ goto bad;
+
+ printk("PGD %lx ", pgd_val(*pgd));
+
+ if (!pgd_present(*pgd))
+ goto out;
+
+ pud = pud_offset(pgd, address);
+ if (bad_address(pud))
+ goto bad;
+
+ printk("PUD %lx ", pud_val(*pud));
+ if (!pud_present(*pud) || pud_large(*pud))
+ goto out;
+
+ pmd = pmd_offset(pud, address);
+ if (bad_address(pmd))
+ goto bad;
+
+ printk("PMD %lx ", pmd_val(*pmd));
+ if (!pmd_present(*pmd) || pmd_large(*pmd))
+ goto out;
+
+ pte = pte_offset_kernel(pmd, address);
+ if (bad_address(pte))
+ goto bad;
+
+ printk("PTE %lx", pte_val(*pte));
+out:
+ printk("\n");
+ return;
+bad:
+ printk("BAD\n");
+}
+
+#endif /* CONFIG_X86_64 */
+
+/*
+ * Workaround for K8 erratum #93 & buggy BIOS.
+ *
+ * BIOS SMM functions are required to use a specific workaround
+ * to avoid corruption of the 64bit RIP register on C stepping K8.
+ *
+ * A lot of BIOS that didn't get tested properly miss this.
+ *
+ * The OS sees this as a page fault with the upper 32bits of RIP cleared.
+ * Try to work around it here.
+ *
+ * Note we only handle faults in kernel here.
+ * Does nothing on 32-bit.
*/
static int is_errata93(struct pt_regs *regs, unsigned long address)
{
#ifdef CONFIG_X86_64
- static int warned;
+ static int once;
+
if (address != regs->ip)
return 0;
+
if ((address >> 32) != 0)
return 0;
+
address |= 0xffffffffUL << 32;
if ((address >= (u64)_stext && address <= (u64)_etext) ||
(address >= MODULES_VADDR && address <= MODULES_END)) {
- if (!warned) {
+ if (!once) {
printk(errata93_warning);
- warned = 1;
+ once = 1;
}
regs->ip = address;
return 1;
@@ -344,16 +561,17 @@
}
/*
- * Work around K8 erratum #100 K8 in compat mode occasionally jumps to illegal
- * addresses >4GB. We catch this in the page fault handler because these
- * addresses are not reachable. Just detect this case and return. Any code
+ * Work around K8 erratum #100 K8 in compat mode occasionally jumps
+ * to illegal addresses >4GB.
+ *
+ * We catch this in the page fault handler because these addresses
+ * are not reachable. Just detect this case and return. Any code
* segment in LDT is compatibility mode.
*/
static int is_errata100(struct pt_regs *regs, unsigned long address)
{
#ifdef CONFIG_X86_64
- if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) &&
- (address >> 32))
+ if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && (address >> 32))
return 1;
#endif
return 0;
@@ -363,8 +581,9 @@
{
#ifdef CONFIG_X86_F00F_BUG
unsigned long nr;
+
/*
- * Pentium F0 0F C7 C8 bug workaround.
+ * Pentium F0 0F C7 C8 bug workaround:
*/
if (boot_cpu_data.f00f_bug) {
nr = (address - idt_descr.address) >> 3;
@@ -378,80 +597,87 @@
return 0;
}
-static void show_fault_oops(struct pt_regs *regs, unsigned long error_code,
- unsigned long address)
+static const char nx_warning[] = KERN_CRIT
+"kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n";
+
+static void
+show_fault_oops(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
-#ifdef CONFIG_X86_32
if (!oops_may_print())
return;
-#endif
-#ifdef CONFIG_X86_PAE
if (error_code & PF_INSTR) {
unsigned int level;
+
pte_t *pte = lookup_address(address, &level);
if (pte && pte_present(*pte) && !pte_exec(*pte))
- printk(KERN_CRIT "kernel tried to execute "
- "NX-protected page - exploit attempt? "
- "(uid: %d)\n", current_uid());
+ printk(nx_warning, current_uid());
}
-#endif
printk(KERN_ALERT "BUG: unable to handle kernel ");
if (address < PAGE_SIZE)
printk(KERN_CONT "NULL pointer dereference");
else
printk(KERN_CONT "paging request");
+
printk(KERN_CONT " at %p\n", (void *) address);
printk(KERN_ALERT "IP:");
printk_address(regs->ip, 1);
+
dump_pagetable(address);
}
-#ifdef CONFIG_X86_64
-static noinline void pgtable_bad(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static noinline void
+pgtable_bad(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
- unsigned long flags = oops_begin();
- int sig = SIGKILL;
- struct task_struct *tsk = current;
+ struct task_struct *tsk;
+ unsigned long flags;
+ int sig;
+
+ flags = oops_begin();
+ tsk = current;
+ sig = SIGKILL;
printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
tsk->comm, address);
dump_pagetable(address);
- tsk->thread.cr2 = address;
- tsk->thread.trap_no = 14;
- tsk->thread.error_code = error_code;
+
+ tsk->thread.cr2 = address;
+ tsk->thread.trap_no = 14;
+ tsk->thread.error_code = error_code;
+
if (__die("Bad pagetable", regs, error_code))
sig = 0;
+
oops_end(flags, regs, sig);
}
-#endif
-static noinline void no_context(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static noinline void
+no_context(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
struct task_struct *tsk = current;
unsigned long *stackend;
-
-#ifdef CONFIG_X86_64
unsigned long flags;
int sig;
-#endif
- /* Are we prepared to handle this kernel fault? */
+ /* Are we prepared to handle this kernel fault? */
if (fixup_exception(regs))
return;
/*
- * X86_32
- * Valid to do another page fault here, because if this fault
- * had been triggered by is_prefetch fixup_exception would have
- * handled it.
+ * 32-bit:
*
- * X86_64
- * Hall of shame of CPU/BIOS bugs.
+ * Valid to do another page fault here, because if this fault
+ * had been triggered by is_prefetch fixup_exception would have
+ * handled it.
+ *
+ * 64-bit:
+ *
+ * Hall of shame of CPU/BIOS bugs.
*/
if (is_prefetch(regs, error_code, address))
return;
@@ -461,54 +687,70 @@
/*
* Oops. The kernel tried to access some bad page. We'll have to
- * terminate things with extreme prejudice.
+ * terminate things with extreme prejudice:
*/
-#ifdef CONFIG_X86_32
- bust_spinlocks(1);
-#else
flags = oops_begin();
-#endif
show_fault_oops(regs, error_code, address);
- stackend = end_of_stack(tsk);
+ stackend = end_of_stack(tsk);
if (*stackend != STACK_END_MAGIC)
printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
- tsk->thread.cr2 = address;
- tsk->thread.trap_no = 14;
- tsk->thread.error_code = error_code;
+ tsk->thread.cr2 = address;
+ tsk->thread.trap_no = 14;
+ tsk->thread.error_code = error_code;
-#ifdef CONFIG_X86_32
- die("Oops", regs, error_code);
- bust_spinlocks(0);
- do_exit(SIGKILL);
-#else
sig = SIGKILL;
if (__die("Oops", regs, error_code))
sig = 0;
+
/* Executive summary in case the body of the oops scrolled away */
printk(KERN_EMERG "CR2: %016lx\n", address);
+
oops_end(flags, regs, sig);
-#endif
}
-static void __bad_area_nosemaphore(struct pt_regs *regs,
- unsigned long error_code, unsigned long address,
- int si_code)
+/*
+ * Print out info about fatal segfaults, if the show_unhandled_signals
+ * sysctl is set:
+ */
+static inline void
+show_signal_msg(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address, struct task_struct *tsk)
+{
+ if (!unhandled_signal(tsk, SIGSEGV))
+ return;
+
+ if (!printk_ratelimit())
+ return;
+
+ printk(KERN_CONT "%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
+ task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
+ tsk->comm, task_pid_nr(tsk), address,
+ (void *)regs->ip, (void *)regs->sp, error_code);
+
+ print_vma_addr(KERN_CONT " in ", regs->ip);
+
+ printk(KERN_CONT "\n");
+}
+
+static void
+__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address, int si_code)
{
struct task_struct *tsk = current;
/* User mode accesses just cause a SIGSEGV */
if (error_code & PF_USER) {
/*
- * It's possible to have interrupts off here.
+ * It's possible to have interrupts off here:
*/
local_irq_enable();
/*
* Valid to do another page fault here because this one came
- * from user space.
+ * from user space:
*/
if (is_prefetch(regs, error_code, address))
return;
@@ -516,22 +758,16 @@
if (is_errata100(regs, address))
return;
- if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
- printk_ratelimit()) {
- printk(
- "%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
- task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
- tsk->comm, task_pid_nr(tsk), address,
- (void *) regs->ip, (void *) regs->sp, error_code);
- print_vma_addr(" in ", regs->ip);
- printk("\n");
- }
+ if (unlikely(show_unhandled_signals))
+ show_signal_msg(regs, error_code, address, tsk);
- tsk->thread.cr2 = address;
- /* Kernel addresses are always protection faults */
- tsk->thread.error_code = error_code | (address >= TASK_SIZE);
- tsk->thread.trap_no = 14;
+ /* Kernel addresses are always protection faults: */
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code | (address >= TASK_SIZE);
+ tsk->thread.trap_no = 14;
+
force_sig_info_fault(SIGSEGV, si_code, address, tsk);
+
return;
}
@@ -541,15 +777,16 @@
no_context(regs, error_code, address);
}
-static noinline void bad_area_nosemaphore(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static noinline void
+bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
__bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR);
}
-static void __bad_area(struct pt_regs *regs,
- unsigned long error_code, unsigned long address,
- int si_code)
+static void
+__bad_area(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address, int si_code)
{
struct mm_struct *mm = current->mm;
@@ -562,67 +799,75 @@
__bad_area_nosemaphore(regs, error_code, address, si_code);
}
-static noinline void bad_area(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static noinline void
+bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address)
{
__bad_area(regs, error_code, address, SEGV_MAPERR);
}
-static noinline void bad_area_access_error(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static noinline void
+bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
__bad_area(regs, error_code, address, SEGV_ACCERR);
}
/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */
-static void out_of_memory(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static void
+out_of_memory(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address)
{
/*
* We ran out of memory, call the OOM killer, and return the userspace
- * (which will retry the fault, or kill us if we got oom-killed).
+ * (which will retry the fault, or kill us if we got oom-killed):
*/
up_read(¤t->mm->mmap_sem);
+
pagefault_out_of_memory();
}
-static void do_sigbus(struct pt_regs *regs,
- unsigned long error_code, unsigned long address)
+static void
+do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
up_read(&mm->mmap_sem);
- /* Kernel mode? Handle exceptions or die */
+ /* Kernel mode? Handle exceptions or die: */
if (!(error_code & PF_USER))
no_context(regs, error_code, address);
-#ifdef CONFIG_X86_32
- /* User space => ok to do another page fault */
+
+ /* User-space => ok to do another page fault: */
if (is_prefetch(regs, error_code, address))
return;
-#endif
- tsk->thread.cr2 = address;
- tsk->thread.error_code = error_code;
- tsk->thread.trap_no = 14;
+
+ tsk->thread.cr2 = address;
+ tsk->thread.error_code = error_code;
+ tsk->thread.trap_no = 14;
+
force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
}
-static noinline void mm_fault_error(struct pt_regs *regs,
- unsigned long error_code, unsigned long address, unsigned int fault)
+static noinline void
+mm_fault_error(struct pt_regs *regs, unsigned long error_code,
+ unsigned long address, unsigned int fault)
{
- if (fault & VM_FAULT_OOM)
+ if (fault & VM_FAULT_OOM) {
out_of_memory(regs, error_code, address);
- else if (fault & VM_FAULT_SIGBUS)
- do_sigbus(regs, error_code, address);
- else
- BUG();
+ } else {
+ if (fault & VM_FAULT_SIGBUS)
+ do_sigbus(regs, error_code, address);
+ else
+ BUG();
+ }
}
static int spurious_fault_check(unsigned long error_code, pte_t *pte)
{
if ((error_code & PF_WRITE) && !pte_write(*pte))
return 0;
+
if ((error_code & PF_INSTR) && !pte_exec(*pte))
return 0;
@@ -630,21 +875,25 @@
}
/*
- * Handle a spurious fault caused by a stale TLB entry. This allows
- * us to lazily refresh the TLB when increasing the permissions of a
- * kernel page (RO -> RW or NX -> X). Doing it eagerly is very
- * expensive since that implies doing a full cross-processor TLB
- * flush, even if no stale TLB entries exist on other processors.
+ * Handle a spurious fault caused by a stale TLB entry.
+ *
+ * This allows us to lazily refresh the TLB when increasing the
+ * permissions of a kernel page (RO -> RW or NX -> X). Doing it
+ * eagerly is very expensive since that implies doing a full
+ * cross-processor TLB flush, even if no stale TLB entries exist
+ * on other processors.
+ *
* There are no security implications to leaving a stale TLB when
* increasing the permissions on a page.
*/
-static noinline int spurious_fault(unsigned long error_code,
- unsigned long address)
+static noinline int
+spurious_fault(unsigned long error_code, unsigned long address)
{
pgd_t *pgd;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
+ int ret;
/* Reserved-bit violation or user access to kernel space? */
if (error_code & (PF_USER | PF_RSVD))
@@ -672,123 +921,46 @@
if (!pte_present(*pte))
return 0;
- return spurious_fault_check(error_code, pte);
-}
-
-/*
- * X86_32
- * Handle a fault on the vmalloc or module mapping area
- *
- * X86_64
- * Handle a fault on the vmalloc area
- *
- * This assumes no large pages in there.
- */
-static noinline int vmalloc_fault(unsigned long address)
-{
-#ifdef CONFIG_X86_32
- unsigned long pgd_paddr;
- pmd_t *pmd_k;
- pte_t *pte_k;
-
- /* Make sure we are in vmalloc area */
- if (!(address >= VMALLOC_START && address < VMALLOC_END))
- return -1;
+ ret = spurious_fault_check(error_code, pte);
+ if (!ret)
+ return 0;
/*
- * Synchronize this task's top level page-table
- * with the 'reference' page table.
- *
- * Do _not_ use "current" here. We might be inside
- * an interrupt in the middle of a task switch..
+ * Make sure we have permissions in PMD.
+ * If not, then there's a bug in the page tables:
*/
- pgd_paddr = read_cr3();
- pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
- if (!pmd_k)
- return -1;
- pte_k = pte_offset_kernel(pmd_k, address);
- if (!pte_present(*pte_k))
- return -1;
- return 0;
-#else
- pgd_t *pgd, *pgd_ref;
- pud_t *pud, *pud_ref;
- pmd_t *pmd, *pmd_ref;
- pte_t *pte, *pte_ref;
+ ret = spurious_fault_check(error_code, (pte_t *) pmd);
+ WARN_ONCE(!ret, "PMD has incorrect permission bits\n");
- /* Make sure we are in vmalloc area */
- if (!(address >= VMALLOC_START && address < VMALLOC_END))
- return -1;
-
- /* Copy kernel mappings over when needed. This can also
- happen within a race in page table update. In the later
- case just flush. */
-
- pgd = pgd_offset(current->active_mm, address);
- pgd_ref = pgd_offset_k(address);
- if (pgd_none(*pgd_ref))
- return -1;
- if (pgd_none(*pgd))
- set_pgd(pgd, *pgd_ref);
- else
- BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
-
- /* Below here mismatches are bugs because these lower tables
- are shared */
-
- pud = pud_offset(pgd, address);
- pud_ref = pud_offset(pgd_ref, address);
- if (pud_none(*pud_ref))
- return -1;
- if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
- BUG();
- pmd = pmd_offset(pud, address);
- pmd_ref = pmd_offset(pud_ref, address);
- if (pmd_none(*pmd_ref))
- return -1;
- if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
- BUG();
- pte_ref = pte_offset_kernel(pmd_ref, address);
- if (!pte_present(*pte_ref))
- return -1;
- pte = pte_offset_kernel(pmd, address);
- /* Don't use pte_page here, because the mappings can point
- outside mem_map, and the NUMA hash lookup cannot handle
- that. */
- if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref))
- BUG();
- return 0;
-#endif
+ return ret;
}
int show_unhandled_signals = 1;
-static inline int access_error(unsigned long error_code, int write,
- struct vm_area_struct *vma)
+static inline int
+access_error(unsigned long error_code, int write, struct vm_area_struct *vma)
{
if (write) {
- /* write, present and write, not present */
+ /* write, present and write, not present: */
if (unlikely(!(vma->vm_flags & VM_WRITE)))
return 1;
- } else if (unlikely(error_code & PF_PROT)) {
- /* read, present */
- return 1;
- } else {
- /* read, not present */
- if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
- return 1;
+ return 0;
}
+ /* read, present: */
+ if (unlikely(error_code & PF_PROT))
+ return 1;
+
+ /* read, not present: */
+ if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
+ return 1;
+
return 0;
}
static int fault_in_kernel_space(unsigned long address)
{
-#ifdef CONFIG_X86_32
- return address >= TASK_SIZE;
-#else /* !CONFIG_X86_32 */
- return address >= TASK_SIZE64;
-#endif /* CONFIG_X86_32 */
+ return address >= TASK_SIZE_MAX;
}
/*
@@ -796,23 +968,22 @@
* and the problem, and then passes it off to one of the appropriate
* routines.
*/
-#ifdef CONFIG_X86_64
-asmlinkage
-#endif
-void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
+dotraplinkage void __kprobes
+do_page_fault(struct pt_regs *regs, unsigned long error_code)
{
- unsigned long address;
- struct task_struct *tsk;
- struct mm_struct *mm;
struct vm_area_struct *vma;
+ struct task_struct *tsk;
+ unsigned long address;
+ struct mm_struct *mm;
int write;
int fault;
tsk = current;
mm = tsk->mm;
+
prefetchw(&mm->mmap_sem);
- /* get the address */
+ /* Get the faulting address: */
address = read_cr2();
if (unlikely(kmmio_fault(regs, address)))
@@ -836,22 +1007,23 @@
vmalloc_fault(address) >= 0)
return;
- /* Can handle a stale RO->RW TLB */
+ /* Can handle a stale RO->RW TLB: */
if (spurious_fault(error_code, address))
return;
- /* kprobes don't want to hook the spurious faults. */
+ /* kprobes don't want to hook the spurious faults: */
if (notify_page_fault(regs))
return;
/*
* Don't take the mm semaphore here. If we fixup a prefetch
- * fault we could otherwise deadlock.
+ * fault we could otherwise deadlock:
*/
bad_area_nosemaphore(regs, error_code, address);
+
return;
}
- /* kprobes don't want to hook the spurious faults. */
+ /* kprobes don't want to hook the spurious faults: */
if (unlikely(notify_page_fault(regs)))
return;
/*
@@ -859,22 +1031,22 @@
* vmalloc fault has been handled.
*
* User-mode registers count as a user access even for any
- * potential system fault or CPU buglet.
+ * potential system fault or CPU buglet:
*/
if (user_mode_vm(regs)) {
local_irq_enable();
error_code |= PF_USER;
- } else if (regs->flags & X86_EFLAGS_IF)
- local_irq_enable();
+ } else {
+ if (regs->flags & X86_EFLAGS_IF)
+ local_irq_enable();
+ }
-#ifdef CONFIG_X86_64
if (unlikely(error_code & PF_RSVD))
pgtable_bad(regs, error_code, address);
-#endif
/*
- * If we're in an interrupt, have no user context or are running in an
- * atomic region then we must not take the fault.
+ * If we're in an interrupt, have no user context or are running
+ * in an atomic region then we must not take the fault:
*/
if (unlikely(in_atomic() || !mm)) {
bad_area_nosemaphore(regs, error_code, address);
@@ -883,19 +1055,19 @@
/*
* When running in the kernel we expect faults to occur only to
- * addresses in user space. All other faults represent errors in the
- * kernel and should generate an OOPS. Unfortunately, in the case of an
- * erroneous fault occurring in a code path which already holds mmap_sem
- * we will deadlock attempting to validate the fault against the
- * address space. Luckily the kernel only validly references user
- * space from well defined areas of code, which are listed in the
- * exceptions table.
+ * addresses in user space. All other faults represent errors in
+ * the kernel and should generate an OOPS. Unfortunately, in the
+ * case of an erroneous fault occurring in a code path which already
+ * holds mmap_sem we will deadlock attempting to validate the fault
+ * against the address space. Luckily the kernel only validly
+ * references user space from well defined areas of code, which are
+ * listed in the exceptions table.
*
* As the vast majority of faults will be valid we will only perform
- * the source reference check when there is a possibility of a deadlock.
- * Attempt to lock the address space, if we cannot we then validate the
- * source. If this is invalid we can skip the address space check,
- * thus avoiding the deadlock.
+ * the source reference check when there is a possibility of a
+ * deadlock. Attempt to lock the address space, if we cannot we then
+ * validate the source. If this is invalid we can skip the address
+ * space check, thus avoiding the deadlock:
*/
if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
if ((error_code & PF_USER) == 0 &&
@@ -906,8 +1078,9 @@
down_read(&mm->mmap_sem);
} else {
/*
- * The above down_read_trylock() might have succeeded in which
- * case we'll have missed the might_sleep() from down_read().
+ * The above down_read_trylock() might have succeeded in
+ * which case we'll have missed the might_sleep() from
+ * down_read():
*/
might_sleep();
}
@@ -927,7 +1100,7 @@
/*
* Accessing the stack below %sp is always a bug.
* The large cushion allows instructions like enter
- * and pusha to work. ("enter $65535,$31" pushes
+ * and pusha to work. ("enter $65535, $31" pushes
* 32 pointers and then decrements %sp by 65535.)
*/
if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) {
@@ -946,6 +1119,7 @@
*/
good_area:
write = error_code & PF_WRITE;
+
if (unlikely(access_error(error_code, write, vma))) {
bad_area_access_error(regs, error_code, address);
return;
@@ -954,75 +1128,21 @@
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
- * the fault.
+ * the fault:
*/
fault = handle_mm_fault(mm, vma, address, write);
+
if (unlikely(fault & VM_FAULT_ERROR)) {
mm_fault_error(regs, error_code, address, fault);
return;
}
+
if (fault & VM_FAULT_MAJOR)
tsk->maj_flt++;
else
tsk->min_flt++;
-#ifdef CONFIG_X86_32
- /*
- * Did it hit the DOS screen memory VA from vm86 mode?
- */
- if (v8086_mode(regs)) {
- unsigned long bit = (address - 0xA0000) >> PAGE_SHIFT;
- if (bit < 32)
- tsk->thread.screen_bitmap |= 1 << bit;
- }
-#endif
+ check_v8086_mode(regs, address, tsk);
+
up_read(&mm->mmap_sem);
}
-
-DEFINE_SPINLOCK(pgd_lock);
-LIST_HEAD(pgd_list);
-
-void vmalloc_sync_all(void)
-{
- unsigned long address;
-
-#ifdef CONFIG_X86_32
- if (SHARED_KERNEL_PMD)
- return;
-
- for (address = VMALLOC_START & PMD_MASK;
- address >= TASK_SIZE && address < FIXADDR_TOP;
- address += PMD_SIZE) {
- unsigned long flags;
- struct page *page;
-
- spin_lock_irqsave(&pgd_lock, flags);
- list_for_each_entry(page, &pgd_list, lru) {
- if (!vmalloc_sync_one(page_address(page),
- address))
- break;
- }
- spin_unlock_irqrestore(&pgd_lock, flags);
- }
-#else /* CONFIG_X86_64 */
- for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
- address += PGDIR_SIZE) {
- const pgd_t *pgd_ref = pgd_offset_k(address);
- unsigned long flags;
- struct page *page;
-
- if (pgd_none(*pgd_ref))
- continue;
- spin_lock_irqsave(&pgd_lock, flags);
- list_for_each_entry(page, &pgd_list, lru) {
- pgd_t *pgd;
- pgd = (pgd_t *)page_address(page) + pgd_index(address);
- if (pgd_none(*pgd))
- set_pgd(pgd, *pgd_ref);
- else
- BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
- }
- spin_unlock_irqrestore(&pgd_lock, flags);
- }
-#endif
-}
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index d1f7439..3957cd6 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -194,7 +194,7 @@
size = ALIGN(size, L1_CACHE_BYTES);
if (!allocation || (allocation + size) >= node_remap_end_vaddr[nid])
- return 0;
+ return NULL;
node_remap_alloc_vaddr[nid] += size;
memset(allocation, 0, size);
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 7be47d1..8253bc9 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -482,6 +482,13 @@
pbase = (pte_t *)page_address(base);
paravirt_alloc_pte(&init_mm, page_to_pfn(base));
ref_prot = pte_pgprot(pte_clrhuge(*kpte));
+ /*
+ * If we ever want to utilize the PAT bit, we need to
+ * update this function to make sure it's converted from
+ * bit 12 to bit 7 when we cross from the 2MB level to
+ * the 4K level:
+ */
+ WARN_ON_ONCE(pgprot_val(ref_prot) & _PAGE_PAT_LARGE);
#ifdef CONFIG_X86_64
if (level == PG_LEVEL_1G) {
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index d1e9b53..b641388 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -8,7 +8,7 @@
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/asm-offsets.h>
#include <asm/processor-flags.h>
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 0004159..9356547 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -18,7 +18,7 @@
.text
#include <linux/linkage.h>
#include <asm/segment.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <asm/asm-offsets.h>
#include <asm/processor-flags.h>
diff --git a/arch/x86/vdso/vma.c b/arch/x86/vdso/vma.c
index 9c98cc6..7133cdf 100644
--- a/arch/x86/vdso/vma.c
+++ b/arch/x86/vdso/vma.c
@@ -85,8 +85,8 @@
unsigned long addr, end;
unsigned offset;
end = (start + PMD_SIZE - 1) & PMD_MASK;
- if (end >= TASK_SIZE64)
- end = TASK_SIZE64;
+ if (end >= TASK_SIZE_MAX)
+ end = TASK_SIZE_MAX;
end -= len;
/* This loses some more bits than a modulo, but is cheaper */
offset = get_random_int() & (PTRS_PER_PTE - 1);
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 63d49a5..1a5ff24 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -8,7 +8,7 @@
#include <asm/boot.h>
#include <asm/asm.h>
-#include <asm/page.h>
+#include <asm/page_types.h>
#include <xen/interface/elfnote.h>
#include <asm/xen/interface.h>
diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index d1dd516..2b6c590 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -272,7 +272,7 @@
}
EXPORT_SYMBOL_GPL(acpi_os_map_memory);
-void acpi_os_unmap_memory(void __iomem * virt, acpi_size size)
+void __ref acpi_os_unmap_memory(void __iomem *virt, acpi_size size)
{
if (acpi_gbl_permanent_mmap)
iounmap(virt);
@@ -281,7 +281,7 @@
}
EXPORT_SYMBOL_GPL(acpi_os_unmap_memory);
-void early_acpi_os_unmap_memory(void __iomem * virt, acpi_size size)
+void __init early_acpi_os_unmap_memory(void __iomem *virt, acpi_size size)
{
if (!acpi_gbl_permanent_mmap)
__acpi_unmap_table(virt, size);
diff --git a/drivers/base/sys.c b/drivers/base/sys.c
index c98c31e..b428c8c 100644
--- a/drivers/base/sys.c
+++ b/drivers/base/sys.c
@@ -303,7 +303,6 @@
* is guaranteed by virtue of the fact that child devices are registered
* after their parents.
*/
-
void sysdev_shutdown(void)
{
struct sysdev_class * cls;
@@ -363,7 +362,6 @@
* This is only called by the device PM core, so we let them handle
* all synchronization.
*/
-
int sysdev_suspend(pm_message_t state)
{
struct sysdev_class * cls;
@@ -432,7 +430,7 @@
}
return ret;
}
-
+EXPORT_SYMBOL_GPL(sysdev_suspend);
/**
* sysdev_resume - Bring system devices back to life.
@@ -442,7 +440,6 @@
*
* Note: Interrupts are disabled when called.
*/
-
int sysdev_resume(void)
{
struct sysdev_class * cls;
@@ -463,7 +460,7 @@
}
return 0;
}
-
+EXPORT_SYMBOL_GPL(sysdev_resume);
int __init system_bus_init(void)
{
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 81f1cff..2d797ff 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -202,7 +202,7 @@
dev_priv->ring.map.flags = 0;
dev_priv->ring.map.mtrr = 0;
- drm_core_ioremap(&dev_priv->ring.map, dev);
+ drm_core_ioremap_wc(&dev_priv->ring.map, dev);
if (dev_priv->ring.map.handle == NULL) {
i915_dma_cleanup(dev);
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index a31cbdb..0692622 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -27,6 +27,7 @@
*
*/
+#include <linux/device.h>
#include "drmP.h"
#include "drm.h"
#include "i915_drm.h"
@@ -66,6 +67,12 @@
i915_save_state(dev);
+ /* If KMS is active, we do the leavevt stuff here */
+ if (drm_core_check_feature(dev, DRIVER_MODESET) && i915_gem_idle(dev)) {
+ dev_err(&dev->pdev->dev, "GEM idle failed, aborting suspend\n");
+ return -EBUSY;
+ }
+
intel_opregion_free(dev);
if (state.event == PM_EVENT_SUSPEND) {
@@ -79,6 +86,9 @@
static int i915_resume(struct drm_device *dev)
{
+ struct drm_i915_private *dev_priv = dev->dev_private;
+ int ret = 0;
+
pci_set_power_state(dev->pdev, PCI_D0);
pci_restore_state(dev->pdev);
if (pci_enable_device(dev->pdev))
@@ -89,7 +99,18 @@
intel_opregion_init(dev);
- return 0;
+ /* KMS EnterVT equivalent */
+ if (drm_core_check_feature(dev, DRIVER_MODESET)) {
+ mutex_lock(&dev->struct_mutex);
+ dev_priv->mm.suspended = 0;
+
+ ret = i915_gem_init_ringbuffer(dev);
+ if (ret != 0)
+ ret = -1;
+ mutex_unlock(&dev->struct_mutex);
+ }
+
+ return ret;
}
static struct vm_operations_struct i915_gem_vm_ops = {
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 135a08f..17fa408 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -618,6 +618,7 @@
void i915_gem_cleanup_ringbuffer(struct drm_device *dev);
int i915_gem_do_init(struct drm_device *dev, unsigned long start,
unsigned long end);
+int i915_gem_idle(struct drm_device *dev);
int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
int i915_gem_object_set_to_gtt_domain(struct drm_gem_object *obj,
int write);
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index ac534c9..25b3374 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -34,10 +34,6 @@
#define I915_GEM_GPU_DOMAINS (~(I915_GEM_DOMAIN_CPU | I915_GEM_DOMAIN_GTT))
-static void
-i915_gem_object_set_to_gpu_domain(struct drm_gem_object *obj,
- uint32_t read_domains,
- uint32_t write_domain);
static void i915_gem_object_flush_gpu_write_domain(struct drm_gem_object *obj);
static void i915_gem_object_flush_gtt_write_domain(struct drm_gem_object *obj);
static void i915_gem_object_flush_cpu_write_domain(struct drm_gem_object *obj);
@@ -2021,30 +2017,28 @@
* drm_agp_chipset_flush
*/
static void
-i915_gem_object_set_to_gpu_domain(struct drm_gem_object *obj,
- uint32_t read_domains,
- uint32_t write_domain)
+i915_gem_object_set_to_gpu_domain(struct drm_gem_object *obj)
{
struct drm_device *dev = obj->dev;
struct drm_i915_gem_object *obj_priv = obj->driver_private;
uint32_t invalidate_domains = 0;
uint32_t flush_domains = 0;
- BUG_ON(read_domains & I915_GEM_DOMAIN_CPU);
- BUG_ON(write_domain == I915_GEM_DOMAIN_CPU);
+ BUG_ON(obj->pending_read_domains & I915_GEM_DOMAIN_CPU);
+ BUG_ON(obj->pending_write_domain == I915_GEM_DOMAIN_CPU);
#if WATCH_BUF
DRM_INFO("%s: object %p read %08x -> %08x write %08x -> %08x\n",
__func__, obj,
- obj->read_domains, read_domains,
- obj->write_domain, write_domain);
+ obj->read_domains, obj->pending_read_domains,
+ obj->write_domain, obj->pending_write_domain);
#endif
/*
* If the object isn't moving to a new write domain,
* let the object stay in multiple read domains
*/
- if (write_domain == 0)
- read_domains |= obj->read_domains;
+ if (obj->pending_write_domain == 0)
+ obj->pending_read_domains |= obj->read_domains;
else
obj_priv->dirty = 1;
@@ -2054,15 +2048,17 @@
* any read domains which differ from the old
* write domain
*/
- if (obj->write_domain && obj->write_domain != read_domains) {
+ if (obj->write_domain &&
+ obj->write_domain != obj->pending_read_domains) {
flush_domains |= obj->write_domain;
- invalidate_domains |= read_domains & ~obj->write_domain;
+ invalidate_domains |=
+ obj->pending_read_domains & ~obj->write_domain;
}
/*
* Invalidate any read caches which may have
* stale data. That is, any new read domains.
*/
- invalidate_domains |= read_domains & ~obj->read_domains;
+ invalidate_domains |= obj->pending_read_domains & ~obj->read_domains;
if ((flush_domains | invalidate_domains) & I915_GEM_DOMAIN_CPU) {
#if WATCH_BUF
DRM_INFO("%s: CPU domain flush %08x invalidate %08x\n",
@@ -2071,9 +2067,15 @@
i915_gem_clflush_object(obj);
}
- if ((write_domain | flush_domains) != 0)
- obj->write_domain = write_domain;
- obj->read_domains = read_domains;
+ /* The actual obj->write_domain will be updated with
+ * pending_write_domain after we emit the accumulated flush for all
+ * of our domain changes in execbuffers (which clears objects'
+ * write_domains). So if we have a current write domain that we
+ * aren't changing, set pending_write_domain to that.
+ */
+ if (flush_domains == 0 && obj->pending_write_domain == 0)
+ obj->pending_write_domain = obj->write_domain;
+ obj->read_domains = obj->pending_read_domains;
dev->invalidate_domains |= invalidate_domains;
dev->flush_domains |= flush_domains;
@@ -2583,9 +2585,7 @@
struct drm_gem_object *obj = object_list[i];
/* Compute new gpu domains and update invalidate/flush */
- i915_gem_object_set_to_gpu_domain(obj,
- obj->pending_read_domains,
- obj->pending_write_domain);
+ i915_gem_object_set_to_gpu_domain(obj);
}
i915_verify_inactive(dev, __FILE__, __LINE__);
@@ -2604,6 +2604,12 @@
(void)i915_add_request(dev, dev->flush_domains);
}
+ for (i = 0; i < args->buffer_count; i++) {
+ struct drm_gem_object *obj = object_list[i];
+
+ obj->write_domain = obj->pending_write_domain;
+ }
+
i915_verify_inactive(dev, __FILE__, __LINE__);
#if WATCH_COHERENCY
@@ -2866,6 +2872,13 @@
return -EBADF;
}
+ /* Update the active list for the hardware's current position.
+ * Otherwise this only updates on a delayed timer or when irqs are
+ * actually unmasked, and our working set ends up being larger than
+ * required.
+ */
+ i915_gem_retire_requests(dev);
+
obj_priv = obj->driver_private;
/* Don't count being on the flushing list against the object being
* done. Otherwise, a buffer left on the flushing list but not getting
@@ -2967,7 +2980,7 @@
return 0;
}
-static int
+int
i915_gem_idle(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = dev->dev_private;
@@ -3130,16 +3143,20 @@
i915_gem_cleanup_hws(struct drm_device *dev)
{
drm_i915_private_t *dev_priv = dev->dev_private;
- struct drm_gem_object *obj = dev_priv->hws_obj;
- struct drm_i915_gem_object *obj_priv = obj->driver_private;
+ struct drm_gem_object *obj;
+ struct drm_i915_gem_object *obj_priv;
if (dev_priv->hws_obj == NULL)
return;
+ obj = dev_priv->hws_obj;
+ obj_priv = obj->driver_private;
+
kunmap(obj_priv->page_list[0]);
i915_gem_object_unpin(obj);
drm_gem_object_unreference(obj);
dev_priv->hws_obj = NULL;
+
memset(&dev_priv->hws_map, 0, sizeof(dev_priv->hws_map));
dev_priv->hw_status_page = NULL;
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index 4d2baf7..65b635c 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -1008,6 +1008,7 @@
temp = CURSOR_MODE_DISABLE;
addr = 0;
bo = NULL;
+ mutex_lock(&dev->struct_mutex);
goto finish;
}
diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h
index 32851ee..2ec6cc1 100644
--- a/include/linux/kprobes.h
+++ b/include/linux/kprobes.h
@@ -182,6 +182,14 @@
DECLARE_PER_CPU(struct kprobe *, current_kprobe);
DECLARE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
+/*
+ * For #ifdef avoidance:
+ */
+static inline int kprobes_built_in(void)
+{
+ return 1;
+}
+
#ifdef CONFIG_KRETPROBES
extern void arch_prepare_kretprobe(struct kretprobe_instance *ri,
struct pt_regs *regs);
@@ -271,8 +279,16 @@
void kprobe_flush_task(struct task_struct *tk);
void recycle_rp_inst(struct kretprobe_instance *ri, struct hlist_head *head);
-#else /* CONFIG_KPROBES */
+#else /* !CONFIG_KPROBES: */
+static inline int kprobes_built_in(void)
+{
+ return 0;
+}
+static inline int kprobe_fault_handler(struct pt_regs *regs, int trapnr)
+{
+ return 0;
+}
static inline struct kprobe *get_kprobe(void *addr)
{
return NULL;
@@ -329,5 +345,5 @@
static inline void kprobe_flush_task(struct task_struct *tk)
{
}
-#endif /* CONFIG_KPROBES */
-#endif /* _LINUX_KPROBES_H */
+#endif /* CONFIG_KPROBES */
+#endif /* _LINUX_KPROBES_H */
diff --git a/include/linux/mmiotrace.h b/include/linux/mmiotrace.h
index 139d7c8..3d1b7bd 100644
--- a/include/linux/mmiotrace.h
+++ b/include/linux/mmiotrace.h
@@ -1,5 +1,5 @@
-#ifndef MMIOTRACE_H
-#define MMIOTRACE_H
+#ifndef _LINUX_MMIOTRACE_H
+#define _LINUX_MMIOTRACE_H
#include <linux/types.h>
#include <linux/list.h>
@@ -13,28 +13,34 @@
unsigned long condition, struct pt_regs *);
struct kmmio_probe {
- struct list_head list; /* kmmio internal list */
- unsigned long addr; /* start location of the probe point */
- unsigned long len; /* length of the probe region */
- kmmio_pre_handler_t pre_handler; /* Called before addr is executed. */
- kmmio_post_handler_t post_handler; /* Called after addr is executed */
- void *private;
+ /* kmmio internal list: */
+ struct list_head list;
+ /* start location of the probe point: */
+ unsigned long addr;
+ /* length of the probe region: */
+ unsigned long len;
+ /* Called before addr is executed: */
+ kmmio_pre_handler_t pre_handler;
+ /* Called after addr is executed: */
+ kmmio_post_handler_t post_handler;
+ void *private;
};
-/* kmmio is active by some kmmio_probes? */
-static inline int is_kmmio_active(void)
-{
- extern unsigned int kmmio_count;
- return kmmio_count;
-}
+extern unsigned int kmmio_count;
extern int register_kmmio_probe(struct kmmio_probe *p);
extern void unregister_kmmio_probe(struct kmmio_probe *p);
+#ifdef CONFIG_MMIOTRACE
+/* kmmio is active by some kmmio_probes? */
+static inline int is_kmmio_active(void)
+{
+ return kmmio_count;
+}
+
/* Called from page fault handler. */
extern int kmmio_handler(struct pt_regs *regs, unsigned long addr);
-#ifdef CONFIG_MMIOTRACE
/* Called from ioremap.c */
extern void mmiotrace_ioremap(resource_size_t offset, unsigned long size,
void __iomem *addr);
@@ -43,7 +49,17 @@
/* For anyone to insert markers. Remember trailing newline. */
extern int mmiotrace_printk(const char *fmt, ...)
__attribute__ ((format (printf, 1, 2)));
-#else
+#else /* !CONFIG_MMIOTRACE: */
+static inline int is_kmmio_active(void)
+{
+ return 0;
+}
+
+static inline int kmmio_handler(struct pt_regs *regs, unsigned long addr)
+{
+ return 0;
+}
+
static inline void mmiotrace_ioremap(resource_size_t offset,
unsigned long size, void __iomem *addr)
{
@@ -63,28 +79,28 @@
#endif /* CONFIG_MMIOTRACE */
enum mm_io_opcode {
- MMIO_READ = 0x1, /* struct mmiotrace_rw */
- MMIO_WRITE = 0x2, /* struct mmiotrace_rw */
- MMIO_PROBE = 0x3, /* struct mmiotrace_map */
- MMIO_UNPROBE = 0x4, /* struct mmiotrace_map */
- MMIO_UNKNOWN_OP = 0x5, /* struct mmiotrace_rw */
+ MMIO_READ = 0x1, /* struct mmiotrace_rw */
+ MMIO_WRITE = 0x2, /* struct mmiotrace_rw */
+ MMIO_PROBE = 0x3, /* struct mmiotrace_map */
+ MMIO_UNPROBE = 0x4, /* struct mmiotrace_map */
+ MMIO_UNKNOWN_OP = 0x5, /* struct mmiotrace_rw */
};
struct mmiotrace_rw {
- resource_size_t phys; /* PCI address of register */
- unsigned long value;
- unsigned long pc; /* optional program counter */
- int map_id;
- unsigned char opcode; /* one of MMIO_{READ,WRITE,UNKNOWN_OP} */
- unsigned char width; /* size of register access in bytes */
+ resource_size_t phys; /* PCI address of register */
+ unsigned long value;
+ unsigned long pc; /* optional program counter */
+ int map_id;
+ unsigned char opcode; /* one of MMIO_{READ,WRITE,UNKNOWN_OP} */
+ unsigned char width; /* size of register access in bytes */
};
struct mmiotrace_map {
- resource_size_t phys; /* base address in PCI space */
- unsigned long virt; /* base virtual address */
- unsigned long len; /* mapping size */
- int map_id;
- unsigned char opcode; /* MMIO_PROBE or MMIO_UNPROBE */
+ resource_size_t phys; /* base address in PCI space */
+ unsigned long virt; /* base virtual address */
+ unsigned long len; /* mapping size */
+ int map_id;
+ unsigned char opcode; /* MMIO_PROBE or MMIO_UNPROBE */
};
/* in kernel/trace/trace_mmiotrace.c */
@@ -94,4 +110,4 @@
extern void mmio_trace_mapping(struct mmiotrace_map *map);
extern int mmio_trace_printk(const char *fmt, va_list args);
-#endif /* MMIOTRACE_H */
+#endif /* _LINUX_MMIOTRACE_H */
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 6bb2635..7bc9929 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -3,11 +3,16 @@
*
* This is an implementation of the CIPSO 2.2 protocol as specified in
* draft-ietf-cipso-ipsecurity-01.txt with additional tag types as found in
- * FIPS-188, copies of both documents can be found in the Documentation
- * directory. While CIPSO never became a full IETF RFC standard many vendors
+ * FIPS-188. While CIPSO never became a full IETF RFC standard many vendors
* have chosen to adopt the protocol and over the years it has become a
* de-facto standard for labeled networking.
*
+ * The CIPSO draft specification can be found in the kernel's Documentation
+ * directory as well as the following URL:
+ * http://netlabel.sourceforge.net/files/draft-ietf-cipso-ipsecurity-01.txt
+ * The FIPS-188 specification can be found at the following URL:
+ * http://www.itl.nist.gov/fipspubs/fip188.htm
+ *
* Author: Paul Moore <paul.moore@hp.com>
*
*/
diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c
index f58701a..3f4b266 100644
--- a/security/selinux/netlabel.c
+++ b/security/selinux/netlabel.c
@@ -490,8 +490,10 @@
lock_sock(sk);
rc = netlbl_sock_getattr(sk, &secattr);
release_sock(sk);
- if (rc == 0 && secattr.flags != NETLBL_SECATTR_NONE)
+ if (rc == 0)
rc = -EACCES;
+ else if (rc == -ENOMSG)
+ rc = 0;
netlbl_secattr_destroy(&secattr);
}