F: drivers/iommu/amd_iommu*.[ch]
F: include/linux/amd-iommu.h
+AMD KFD
+M: Oded Gabbay <oded.gabbay@amd.com>
+L: dri-devel@lists.freedesktop.org
+T: git git://people.freedesktop.org/~gabbayo/linux.git
+S: Supported
+F: drivers/gpu/drm/amd/amdkfd/
+F: drivers/gpu/drm/radeon/radeon_kfd.c
+F: drivers/gpu/drm/radeon/radeon_kfd.h
+F: include/uapi/linux/kfd_ioctl.h
+
AMD MICROCODE UPDATE SUPPORT
M: Andreas Herrmann <herrmann.der.user@googlemail.com>
L: amd64-microcode@amd64.org
M: Carlo Caione <carlo@caione.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
+F: drivers/media/rc/meson-ir.c
N: meson[x68]
ARM/ATMEL AT91RM9200 AND AT91SAM ARM ARCHITECTURES
W: http://www.linux4sam.org
S: Supported
F: arch/arm/mach-at91/
+F: include/soc/at91/
F: arch/arm/boot/dts/at91*.dts
F: arch/arm/boot/dts/at91*.dtsi
F: arch/arm/boot/dts/sama*.dts
S: Maintained
F: arch/arm/mach-ep93xx/micro9.c
+ARM/CORESIGHT FRAMEWORK AND DRIVERS
+M: Mathieu Poirier <mathieu.poirier@linaro.org>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+F: drivers/coresight/*
+F: Documentation/trace/coresight.txt
+F: Documentation/devicetree/bindings/arm/coresight.txt
+F: Documentation/ABI/testing/sysfs-bus-coresight-devices-*
+
ARM/CORGI MACHINE SUPPORT
M: Richard Purdie <rpurdie@rpsys.net>
S: Maintained
F: drivers/*/*/*rockchip*
F: sound/soc/rockchip/
-ARM/SAMSUNG ARM ARCHITECTURES
-M: Ben Dooks <ben-linux@fluff.org>
-M: Kukjin Kim <kgene.kim@samsung.com>
+ARM/SAMSUNG EXYNOS ARM ARCHITECTURES
+M: Kukjin Kim <kgene@kernel.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
-W: http://www.fluff.org/ben/linux/
S: Maintained
F: arch/arm/boot/dts/s3c*
F: arch/arm/boot/dts/exynos*
F: arch/arm/plat-samsung/
F: arch/arm/mach-s3c24*/
F: arch/arm/mach-s3c64xx/
+F: arch/arm/mach-s5p*/
+F: arch/arm/mach-exynos*/
F: drivers/*/*s3c2410*
F: drivers/*/*/*s3c2410*
F: drivers/spi/spi-s3c*
F: sound/soc/samsung/*
-
-ARM/S5P EXYNOS ARM ARCHITECTURES
-M: Kukjin Kim <kgene.kim@samsung.com>
-L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
-L: linux-samsung-soc@vger.kernel.org (moderated for non-subscribers)
-S: Maintained
-F: arch/arm/mach-s5p*/
-F: arch/arm/mach-exynos*/
N: exynos
ARM/SAMSUNG MOBILE MACHINE SUPPORT
F: arch/arm/configs/ape6evm_defconfig
F: arch/arm/configs/armadillo800eva_defconfig
F: arch/arm/configs/bockw_defconfig
-F: arch/arm/configs/koelsch_defconfig
F: arch/arm/configs/kzm9g_defconfig
F: arch/arm/configs/lager_defconfig
F: arch/arm/configs/mackerel_defconfig
F: arch/arm/configs/marzen_defconfig
F: arch/arm/configs/shmobile_defconfig
+F: arch/arm/include/debug/renesas-scif.S
F: arch/arm/mach-shmobile/
F: drivers/sh/
F: drivers/usb/dwc3/dwc3-st.c
F: drivers/usb/host/ehci-st.c
F: drivers/usb/host/ohci-st.c
+F: drivers/ata/ahci_st.c
ARM/TECHNOLOGIC SYSTEMS TS7250 MACHINE SUPPORT
M: Lennert Buytenhek <kernel@wantstofly.org>
F: drivers/clk/ux500/
F: include/linux/platform_data/clk-ux500.h
+ARM/VERSATILE EXPRESS PLATFORM
+M: Liviu Dudau <liviu.dudau@arm.com>
+M: Sudeep Holla <sudeep.holla@arm.com>
+M: Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+F: arch/arm/boot/dts/vexpress*
+F: arch/arm/mach-vexpress/
+F: */*/vexpress*
+F: */*/*/vexpress*
+F: drivers/clk/versatile/clk-vexpress-osc.c
+F: drivers/clocksource/versatile.c
+
ARM/VFP SUPPORT
M: Russell King <linux@arm.linux.org.uk>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
ARM/ZYNQ ARCHITECTURE
M: Michal Simek <michal.simek@xilinx.com>
+R: Sören Brinkmann <soren.brinkmann@xilinx.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
W: http://wiki.xilinx.com
T: git git://git.xilinx.com/linux-xlnx.git
F: drivers/dma/at_hdmac_regs.h
F: include/linux/platform_data/dma-atmel.h
+ATMEL XDMA DRIVER
+M: Ludovic Desroches <ludovic.desroches@atmel.com>
+L: linux-arm-kernel@lists.infradead.org
+L: dmaengine@vger.kernel.org
+S: Supported
+F: drivers/dma/at_xdmac.c
+
ATMEL I2C DRIVER
M: Ludovic Desroches <ludovic.desroches@atmel.com>
L: linux-i2c@vger.kernel.org
F: drivers/scsi/esas2r
AUDIT SUBSYSTEM
+M: Paul Moore <paul@paul-moore.com>
M: Eric Paris <eparis@redhat.com>
-L: linux-audit@redhat.com (subscribers-only)
+L: linux-audit@redhat.com (moderated for non-subscribers)
W: http://people.redhat.com/sgrubb/audit/
-T: git git://git.infradead.org/users/eparis/audit.git
+T: git git://git.infradead.org/users/pcmoore/audit
S: Maintained
F: include/linux/audit.h
F: include/uapi/linux/audit.h
F: net/ax25/
AZ6007 DVB DRIVER
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-media@vger.kernel.org
W: http://linuxtv.org
T: git git://linuxtv.org/media_tree.git
BACKLIGHT CLASS/SUBSYSTEM
M: Jingoo Han <jg1.han@samsung.com>
-M: Bryan Wu <cooloney@gmail.com>
M: Lee Jones <lee.jones@linaro.org>
S: Maintained
F: drivers/video/backlight/
S: Maintained:
F: drivers/md/bcache/
-BECEEM BCS200/BCS220-3/BCSM250 WIMAX SUPPORT
-M: Kevin McKinney <klmckinney1@gmail.com>
-M: Matthias Beyer <mail@beyermatthias.de>
-L: devel@driverdev.osuosl.org
-S: Maintained
-F: drivers/staging/bcm*
-
BEFS FILE SYSTEM
S: Orphan
F: Documentation/filesystems/befs.txt
BROADCOM BCM2835 ARM ARCHITECTURE
M: Stephen Warren <swarren@wwwdotorg.org>
+M: Lee Jones <lee@kernel.org>
L: linux-rpi-kernel@lists.infradead.org (moderated for non-subscribers)
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/swarren/linux-rpi.git
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/rpi/linux-rpi.git
S: Maintained
N: bcm2835
+BROADCOM BCM33XX MIPS ARCHITECTURE
+M: Kevin Cernekee <cernekee@gmail.com>
+L: linux-mips@linux-mips.org
+S: Maintained
+F: arch/mips/bcm3384/*
+F: arch/mips/include/asm/mach-bcm3384/*
+F: arch/mips/kernel/*bmips*
+
BROADCOM BCM5301X ARM ARCHITECTURE
M: Hauke Mehrtens <hauke@hauke-m.de>
L: linux-arm-kernel@lists.infradead.org
F: arch/arm/mach-bcm/bcm63xx.c
F: arch/arm/include/debug/bcm63xx.S
+BROADCOM BCM63XX/BCM33XX UDC DRIVER
+M: Kevin Cernekee <cernekee@gmail.com>
+L: linux-usb@vger.kernel.org
+S: Maintained
+F: drivers/usb/gadget/udc/bcm63xx_udc.*
+
BROADCOM BCM7XXX ARM ARCHITECTURE
M: Marc Carino <marc.ceeeee@gmail.com>
M: Brian Norris <computersforpeace@gmail.com>
+M: Gregory Fong <gregory.0xf0@gmail.com>
+M: Florian Fainelli <f.fainelli@gmail.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: arch/arm/mach-bcm/*brcmstb*
F: arch/arm/boot/dts/bcm7*.dts*
+F: drivers/bus/brcmstb_gisb.c
+
+BROADCOM BMIPS MIPS ARCHITECTURE
+M: Kevin Cernekee <cernekee@gmail.com>
+M: Florian Fainelli <f.fainelli@gmail.com>
+L: linux-mips@linux-mips.org
+S: Maintained
+F: arch/mips/bmips/*
+F: arch/mips/include/asm/mach-bmips/*
+F: arch/mips/kernel/*bmips*
+F: arch/mips/boot/dts/bcm*.dts*
+F: drivers/irqchip/irq-bcm7*
+F: drivers/irqchip/irq-brcmstb*
BROADCOM TG3 GIGABIT ETHERNET DRIVER
M: Prashant Sreedharan <prashant@broadcom.com>
S: Supported
F: drivers/scsi/bnx2i/
+BROADCOM CYGNUS/IPROC ARM ARCHITECTURE
+M: Ray Jui <rjui@broadcom.com>
+M: Scott Branden <sbranden@broadcom.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+L: bcm-kernel-feedback-list@broadcom.com
+T: git git://git.github.com/brcm/linux.git
+S: Maintained
+N: iproc
+N: cygnus
+N: bcm9113*
+N: bcm9583*
+N: bcm583*
+N: bcm113*
+
BROADCOM KONA GPIO DRIVER
M: Ray Jui <rjui@broadcom.com>
L: bcm-kernel-feedback-list@broadcom.com
F: fs/btrfs/
BTTV VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-media@vger.kernel.org
W: http://linuxtv.org
T: git git://linuxtv.org/media_tree.git
F: security/commoncap.c
F: kernel/capability.c
+CC2520 IEEE-802.15.4 RADIO DRIVER
+M: Varka Bhadram <varkabhadram@gmail.com>
+L: linux-wpan@vger.kernel.org
+S: Maintained
+F: drivers/net/ieee802154/cc2520.c
+F: include/linux/spi/cc2520.h
+F: Documentation/devicetree/bindings/net/ieee802154/cc2520.txt
+
CELL BROADBAND ENGINE ARCHITECTURE
M: Arnd Bergmann <arnd@arndb.de>
L: linuxppc-dev@lists.ozlabs.org
F: include/linux/coda*.h
F: include/uapi/linux/coda*.h
+CODA V4L2 MEM2MEM DRIVER
+M: Philipp Zabel <p.zabel@pengutronix.de>
+L: linux-media@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/media/coda.txt
+F: drivers/media/platform/coda/
+
COMMON CLK FRAMEWORK
M: Mike Turquette <mturquette@linaro.org>
L: linux-kernel@vger.kernel.org
L: linux-cifs@vger.kernel.org
L: samba-technical@lists.samba.org (moderated for non-subscribers)
W: http://linux-cifs.samba.org/
-Q: http://patchwork.ozlabs.org/project/linux-cifs-client/list/
-T: git git://git.kernel.org/pub/scm/linux/kernel/git/sfrench/cifs-2.6.git
+T: git git://git.samba.org/sfrench/cifs-2.6.git
S: Supported
F: Documentation/filesystems/cifs/
F: fs/cifs/
L: linux-mm@kvack.org
S: Maintained
F: mm/memcontrol.c
-F: mm/page_cgroup.c
+F: mm/swap_cgroup.c
CORETEMP HARDWARE MONITORING DRIVER
M: Fenghua Yu <fenghua.yu@intel.com>
S: Maintained
F: drivers/cpuidle/cpuidle-big_little.c
+CPUIDLE DRIVER - ARM EXYNOS
+M: Bartlomiej Zolnierkiewicz <b.zolnierkie@samsung.com>
+M: Daniel Lezcano <daniel.lezcano@linaro.org>
+M: Kukjin Kim <kgene@kernel.org>
+L: linux-pm@vger.kernel.org
+L: linux-samsung-soc@vger.kernel.org
+S: Supported
+F: drivers/cpuidle/cpuidle-exynos.c
+F: arch/arm/mach-exynos/pm.c
+
CPUIDLE DRIVERS
M: Rafael J. Wysocki <rjw@rjwysocki.net>
M: Daniel Lezcano <daniel.lezcano@linaro.org>
CX18 VIDEO4LINUX DRIVER
M: Andy Walls <awalls@md.metrocast.net>
-L: ivtv-devel@ivtvdriver.org (moderated for non-subscribers)
+L: ivtv-devel@ivtvdriver.org (subscribers-only)
L: linux-media@vger.kernel.org
T: git git://linuxtv.org/media_tree.git
W: http://linuxtv.org
F: include/media/cx2341x*
CX88 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-media@vger.kernel.org
W: http://linuxtv.org
T: git git://linuxtv.org/media_tree.git
S: Supported
F: drivers/net/ethernet/chelsio/cxgb3/
+CXGB3 ISCSI DRIVER (CXGB3I)
+M: Karen Xie <kxie@chelsio.com>
+L: linux-scsi@vger.kernel.org
+W: http://www.chelsio.com
+S: Supported
+F: drivers/scsi/cxgbi/cxgb3i
+
CXGB3 IWARP RNIC DRIVER (IW_CXGB3)
M: Steve Wise <swise@chelsio.com>
L: linux-rdma@vger.kernel.org
S: Supported
F: drivers/net/ethernet/chelsio/cxgb4/
+CXGB4 ISCSI DRIVER (CXGB4I)
+M: Karen Xie <kxie@chelsio.com>
+L: linux-scsi@vger.kernel.org
+W: http://www.chelsio.com
+S: Supported
+F: drivers/scsi/cxgbi/cxgb4i
+
CXGB4 IWARP RNIC DRIVER (IW_CXGB4)
M: Steve Wise <swise@chelsio.com>
L: linux-rdma@vger.kernel.org
F: drivers/net/ethernet/dec/tulip/dmfe.c
DC390/AM53C974 SCSI driver
-M: Kurt Garloff <garloff@suse.de>
-W: http://www.garloff.de/kurt/linux/dc390/
-M: Guennadi Liakhovetski <g.liakhovetski@gmx.de>
+M: Hannes Reinecke <hare@suse.de>
+L: linux-scsi@vger.kernel.org
S: Maintained
-F: drivers/scsi/tmscsim.*
+F: drivers/scsi/am53c974.c
DC395x SCSI driver
M: Oliver Neukum <oliver@neukum.org>
S: Maintained
F: drivers/dma/
F: include/linux/dma*
-T: git git://git.infradead.org/users/vkoul/slave-dma.git (slave-dma)
+F: Documentation/dmaengine/
+T: git git://git.infradead.org/users/vkoul/slave-dma.git
DME1737 HARDWARE MONITOR DRIVER
M: Juerg Haefliger <juergh@gmail.com>
F: include/drm/exynos*
F: include/uapi/drm/exynos*
+DRM DRIVERS FOR FREESCALE IMX
+M: Philipp Zabel <p.zabel@pengutronix.de>
+L: dri-devel@lists.freedesktop.org
+S: Maintained
+F: drivers/gpu/drm/imx/
+F: Documentation/devicetree/bindings/drm/imx/
+
DRM DRIVERS FOR NVIDIA TEGRA
M: Thierry Reding <thierry.reding@gmail.com>
M: Terje Bergström <tbergstrom@nvidia.com>
EDAC-CORE
M: Doug Thompson <dougthompson@xmission.com>
M: Borislav Petkov <bp@alien8.de>
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-edac@vger.kernel.org
W: bluesmoke.sourceforge.net
S: Supported
F: drivers/edac/e7xxx_edac.c
EDAC-GHES
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-edac@vger.kernel.org
W: bluesmoke.sourceforge.net
S: Maintained
F: drivers/edac/i5000_edac.c
EDAC-I5400
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-edac@vger.kernel.org
W: bluesmoke.sourceforge.net
S: Maintained
F: drivers/edac/i5400_edac.c
EDAC-I7300
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-edac@vger.kernel.org
W: bluesmoke.sourceforge.net
S: Maintained
F: drivers/edac/i7300_edac.c
EDAC-I7CORE
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-edac@vger.kernel.org
W: bluesmoke.sourceforge.net
S: Maintained
F: drivers/edac/r82600_edac.c
EDAC-SBRIDGE
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-edac@vger.kernel.org
W: bluesmoke.sourceforge.net
S: Maintained
F: drivers/net/ethernet/ibm/ehea/
EM28XX VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-media@vger.kernel.org
W: http://linuxtv.org
T: git git://linuxtv.org/media_tree.git
FREESCALE SOC SOUND DRIVERS
M: Timur Tabi <timur@tabi.org>
M: Nicolin Chen <nicoleotsuka@gmail.com>
-M: Xiubo Li <Li.Xiubo@freescale.com>
+M: Xiubo Li <Xiubo.Lee@gmail.com>
L: alsa-devel@alsa-project.org (moderated for non-subscribers)
L: linuxppc-dev@lists.ozlabs.org
S: Maintained
S: Maintained
F: drivers/media/usb/go7007/
+GOODIX TOUCHSCREEN
+M: Bastien Nocera <hadess@hadess.net>
+L: linux-input@vger.kernel.org
+S: Maintained
+F: drivers/input/touchscreen/goodix.c
+
GPIO SUBSYSTEM
M: Linus Walleij <linus.walleij@linaro.org>
M: Alexandre Courbot <gnurou@gmail.com>
Q: https://patchwork.ozlabs.org/project/linux-i2c/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/wsa/linux.git
S: Maintained
+F: Documentation/devicetree/bindings/i2c/
F: Documentation/i2c/
F: drivers/i2c/
F: include/linux/i2c.h
F: net/ieee802154/
F: net/mac802154/
F: drivers/net/ieee802154/
+F: include/linux/nl802154.h
+F: include/linux/ieee802154.h
+F: include/net/nl802154.h
+F: include/net/mac802154.h
+F: include/net/af_ieee802154.h
+F: include/net/cfg802154.h
+F: include/net/ieee802154_netdev.h
F: Documentation/networking/ieee802154.txt
+IGORPLUG-USB IR RECEIVER
+M: Sean Young <sean@mess.org>
+L: linux-media@vger.kernel.org
+S: Maintained
+F: drivers/media/rc/igorplugusb.c
+
IGUANAWORKS USB IR TRANSCEIVER
M: Sean Young <sean@mess.org>
L: linux-media@vger.kernel.org
S: Maintained
F: drivers/iio/
F: drivers/staging/iio/
+F: include/linux/iio/
IKANOS/ADI EAGLE ADSL USB DRIVER
M: Matthieu Castet <castet.matthieu@free.fr>
S: Supported
F: security/integrity/ima/
+IMGTEC IR DECODER DRIVER
+M: James Hogan <james.hogan@imgtec.com>
+S: Maintained
+F: drivers/media/rc/img-ir/
+
IMS TWINTURBO FRAMEBUFFER DRIVER
L: linux-fbdev@vger.kernel.org
S: Orphan
IVTV VIDEO4LINUX DRIVER
M: Andy Walls <awalls@md.metrocast.net>
-L: ivtv-devel@ivtvdriver.org (moderated for non-subscribers)
+L: ivtv-devel@ivtvdriver.org (subscribers-only)
L: linux-media@vger.kernel.org
T: git git://linuxtv.org/media_tree.git
W: http://www.ivtvdriver.org
F: arch/powerpc/include/asm/kvm*
F: arch/powerpc/kvm/
- KERNEL VIRTUAL MACHINE For Itanium (KVM/IA64)
- M: Xiantao Zhang <xiantao.zhang@intel.com>
- L: kvm-ia64@vger.kernel.org
- W: http://kvm.qumranet.com
- S: Supported
- F: Documentation/ia64/kvm.txt
- F: arch/ia64/include/asm/kvm*
- F: arch/ia64/kvm/
-
KERNEL VIRTUAL MACHINE for s390 (KVM/s390)
M: Christian Borntraeger <borntraeger@de.ibm.com>
M: Cornelia Huck <cornelia.huck@de.ibm.com>
S: Maintained
F: drivers/gpu/drm/armada/
+MARVELL 88E6352 DSA support
+M: Guenter Roeck <linux@roeck-us.net>
+S: Maintained
+F: drivers/net/dsa/mv88e6352.c
+
MARVELL GIGABIT ETHERNET DRIVERS (skge/sky2)
M: Mirko Lindner <mlindner@marvell.com>
M: Stephen Hemminger <stephen@networkplumber.org>
F: drivers/media/radio/radio-maxiradio*
MEDIA INPUT INFRASTRUCTURE (V4L/DVB)
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
P: LinuxTV.org Project
L: linux-media@vger.kernel.org
W: http://linuxtv.org
S: Odd Fixes
F: drivers/media/parport/pms*
-MEGARAID SCSI DRIVERS
-M: Neela Syam Kolli <megaraidlinux@lsi.com>
+MEGARAID SCSI/SAS DRIVERS
+M: Kashyap Desai <kashyap.desai@avagotech.com>
+M: Sumit Saxena <sumit.saxena@avagotech.com>
+M: Uday Lingala <uday.lingala@avagotech.com>
+L: megaraidlinux.pdl@avagotech.com
L: linux-scsi@vger.kernel.org
-W: http://megaraid.lsilogic.com
+W: http://www.lsi.com
S: Maintained
F: Documentation/scsi/megaraid.txt
F: drivers/scsi/megaraid.*
F: include/linux/mlx5/
F: drivers/infiniband/hw/mlx5/
+MN88472 MEDIA DRIVER
+M: Antti Palosaari <crope@iki.fi>
+L: linux-media@vger.kernel.org
+W: http://linuxtv.org/
+W: http://palosaari.fi/linux/
+Q: http://patchwork.linuxtv.org/project/linux-media/list/
+T: git git://linuxtv.org/anttip/media_tree.git
+S: Maintained
+F: drivers/staging/media/mn88472/
+F: drivers/media/dvb-frontends/mn88472.h
+
+MN88473 MEDIA DRIVER
+M: Antti Palosaari <crope@iki.fi>
+L: linux-media@vger.kernel.org
+W: http://linuxtv.org/
+W: http://palosaari.fi/linux/
+Q: http://patchwork.linuxtv.org/project/linux-media/list/
+T: git git://linuxtv.org/anttip/media_tree.git
+S: Maintained
+F: drivers/staging/media/mn88473/
+F: drivers/media/dvb-frontends/mn88473.h
+
MODULE SUPPORT
M: Rusty Russell <rusty@rustcorp.com.au>
S: Maintained
F: drivers/scsi/g_NCR5380_mmio.c
F: drivers/scsi/mac_scsi.*
F: drivers/scsi/pas16.*
-F: drivers/scsi/sun3_NCR5380.c
F: drivers/scsi/sun3_scsi.*
F: drivers/scsi/sun3_scsi_vme.c
F: drivers/scsi/t128.*
F: Documentation/scsi/NinjaSCSI.txt
F: drivers/scsi/nsp32*
+NIOS2 ARCHITECTURE
+M: Ley Foon Tan <lftan@altera.com>
+L: nios2-dev@lists.rocketboards.org (moderated for non-subscribers)
+T: git git://git.rocketboards.org/linux-socfpga.git
+S: Maintained
+F: arch/nios2/
+
NTB DRIVER
M: Jon Mason <jdmason@kudzu.us>
M: Dave Jiang <dave.jiang@intel.com>
F: drivers/gpu/drm/i2c/tda998x_drv.c
F: include/drm/i2c/tda998x.h
+NXP TFA9879 DRIVER
+M: Peter Rosin <peda@axentia.se>
+L: alsa-devel@alsa-project.org (moderated for non-subscribers)
+S: Maintained
+F: sound/soc/codecs/tfa9879*
+
OMAP SUPPORT
M: Tony Lindgren <tony@atomide.com>
L: linux-omap@vger.kernel.org
S: Maintained
F: arch/arm/*omap*/
F: drivers/i2c/busses/i2c-omap.c
+F: drivers/irqchip/irq-omap-intc.c
+F: drivers/mfd/*omap*.c
+F: drivers/mfd/menelaus.c
+F: drivers/mfd/palmas.c
+F: drivers/mfd/tps65217.c
+F: drivers/mfd/tps65218.c
+F: drivers/mfd/tps65910.c
+F: drivers/mfd/twl-core.[ch]
+F: drivers/mfd/twl4030*.c
+F: drivers/mfd/twl6030*.c
+F: drivers/mfd/twl6040*.c
+F: drivers/regulator/palmas-regulator*.c
+F: drivers/regulator/pbias-regulator.c
+F: drivers/regulator/tps65217-regulator.c
+F: drivers/regulator/tps65218-regulator.c
+F: drivers/regulator/tps65910-regulator.c
+F: drivers/regulator/twl-regulator.c
F: include/linux/i2c-omap.h
OMAP DEVICE TREE SUPPORT
S: Maintained
F: arch/arm/boot/dts/*omap*
F: arch/arm/boot/dts/*am3*
+F: arch/arm/boot/dts/*am4*
+F: arch/arm/boot/dts/*am5*
+F: arch/arm/boot/dts/*dra7*
OMAP CLOCK FRAMEWORK SUPPORT
M: Paul Walmsley <paul@pwsan.com>
S: Maintained
F: sound/soc/omap/
+OMAP GENERAL PURPOSE MEMORY CONTROLLER SUPPORT
+M: Roger Quadros <rogerq@ti.com>
+M: Tony Lindgren <tony@atomide.com>
+L: linux-omap@vger.kernel.org
+S: Maintained
+F: drivers/memory/omap-gpmc.c
+F: arch/arm/mach-omap2/*gpmc*
+
OMAP FRAMEBUFFER SUPPORT
M: Tomi Valkeinen <tomi.valkeinen@ti.com>
L: linux-fbdev@vger.kernel.org
F: include/scsi/osd_*
F: fs/exofs/
-OVERLAYFS FILESYSTEM
+OVERLAY FILESYSTEM
M: Miklos Szeredi <miklos@szeredi.hu>
-L: linux-fsdevel@vger.kernel.org
+L: linux-unionfs@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/mszeredi/vfs.git
S: Supported
-F: fs/overlayfs/*
+F: fs/overlayfs/
F: Documentation/filesystems/overlayfs.txt
P54 WIRELESS DRIVER
F: Documentation/devicetree/bindings/pci/xgene-pci.txt
F: drivers/pci/host/pci-xgene.c
+PCI DRIVER FOR FREESCALE LAYERSCAPE
+M: Minghuan Lian <minghuan.Lian@freescale.com>
+M: Mingkai Hu <mingkai.hu@freescale.com>
+M: Roy Zang <tie-fei.zang@freescale.com>
+L: linuxppc-dev@lists.ozlabs.org
+L: linux-pci@vger.kernel.org
+L: linux-arm-kernel@lists.infradead.org
+S: Maintained
+F: drivers/pci/host/*layerscape*
+
PCI DRIVER FOR IMX6
M: Richard Zhu <r65037@freescale.com>
M: Lucas Stach <l.stach@pengutronix.de>
PIN CONTROL SUBSYSTEM
M: Linus Walleij <linus.walleij@linaro.org>
+L: linux-gpio@vger.kernel.org
S: Maintained
F: drivers/pinctrl/
F: include/linux/pinctrl/
M: Jean-Christophe Plagniol-Villard <plagnioj@jcrosoft.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
-F: drivers/pinctrl/pinctrl-at91.c
+F: drivers/pinctrl/pinctrl-at91.*
+
+PIN CONTROLLER - INTEL
+M: Mika Westerberg <mika.westerberg@linux.intel.com>
+M: Heikki Krogerus <heikki.krogerus@linux.intel.com>
+S: Maintained
+F: drivers/pinctrl/intel/
PIN CONTROLLER - RENESAS
M: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
F: include/linux/hid-roccat*
F: Documentation/ABI/*/sysfs-driver-hid-roccat*
+ROCKER DRIVER
+M: Jiri Pirko <jiri@resnulli.us>
+M: Scott Feldman <sfeldma@gmail.com>
+L: netdev@vger.kernel.org
+S: Supported
+F: drivers/net/ethernet/rocker/
+
ROCKETPORT DRIVER
P: Comtrol Corp.
W: http://www.comtrol.com
F: Documentation/serial/rocket.txt
F: drivers/tty/rocket*
+ROCKETPORT EXPRESS/INFINITY DRIVER
+M: Kevin Cernekee <cernekee@gmail.com>
+L: linux-serial@vger.kernel.org
+S: Odd Fixes
+F: drivers/tty/serial/rp2.*
+
ROSE NETWORK LAYER
M: Ralf Baechle <ralf@linux-mips.org>
L: linux-hams@vger.kernel.org
F: drivers/media/dvb-frontends/rtl2832_sdr*
RTL8180 WIRELESS DRIVER
-M: "John W. Linville" <linville@tuxdriver.com>
L: linux-wireless@vger.kernel.org
W: http://wireless.kernel.org/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-testing.git
-S: Maintained
+S: Orphan
F: drivers/net/wireless/rtl818x/rtl8180/
RTL8187 WIRELESS DRIVER
F: drivers/media/i2c/saa6588*
SAA7134 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-media@vger.kernel.org
W: http://linuxtv.org
T: git git://linuxtv.org/media_tree.git
F: drivers/media/radio/si4713/radio-usb-si4713.c
SIANO DVB DRIVER
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-media@vger.kernel.org
W: http://linuxtv.org
T: git git://linuxtv.org/media_tree.git
F: drivers/media/usb/siano/
F: drivers/media/mmc/siano/
+SIMPLEFB FB DRIVER
+M: Hans de Goede <hdegoede@redhat.com>
+L: linux-fbdev@vger.kernel.org
+S: Maintained
+F: Documentation/devicetree/bindings/video/simple-framebuffer.txt
+F: drivers/video/fbdev/simplefb.c
+F: include/linux/platform_data/simplefb.h
+
SH_VEU V4L2 MEM2MEM DRIVER
L: linux-media@vger.kernel.org
S: Orphan
TI DAVINCI MACHINE SUPPORT
M: Sekhar Nori <nsekhar@ti.com>
M: Kevin Hilman <khilman@deeprootsystems.com>
-L: davinci-linux-open-source@linux.davincidsp.com (moderated for non-subscribers)
T: git git://gitorious.org/linux-davinci/linux-davinci.git
Q: http://patchwork.kernel.org/project/linux-davinci/list/
S: Supported
TI DAVINCI SERIES MEDIA DRIVER
M: Lad, Prabhakar <prabhakar.csengg@gmail.com>
L: linux-media@vger.kernel.org
-L: davinci-linux-open-source@linux.davincidsp.com (moderated for non-subscribers)
W: http://linuxtv.org/
Q: http://patchwork.linuxtv.org/project/linux-media/list/
T: git git://linuxtv.org/mhadli/v4l-dvb-davinci_devices.git
F: drivers/leds/leds-net48xx.c
SOFTLOGIC 6x10 MPEG CODEC
-M: Ismael Luceno <ismael.luceno@corp.bluecherry.net>
+M: Bluecherry Maintainers <maintainers@bluecherrydvr.com>
+M: Andrey Utkin <andrey.utkin@corp.bluecherry.net>
+M: Andrey Utkin <andrey.krieger.utkin@gmail.com>
L: linux-media@vger.kernel.org
S: Supported
F: drivers/media/pci/solo6x10/
F: arch/*/kernel/pci-swiotlb.c
F: include/linux/swiotlb.h
+SWITCHDEV
+M: Jiri Pirko <jiri@resnulli.us>
+L: netdev@vger.kernel.org
+S: Supported
+F: net/switchdev/
+F: include/net/switchdev.h
+
SYNOPSYS ARC ARCHITECTURE
M: Vineet Gupta <vgupta@synopsys.com>
S: Supported
F: drivers/media/i2c/tda9840*
TEA5761 TUNER DRIVER
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-media@vger.kernel.org
W: http://linuxtv.org
T: git git://linuxtv.org/media_tree.git
F: drivers/media/tuners/tea5761.*
TEA5767 TUNER DRIVER
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-media@vger.kernel.org
W: http://linuxtv.org
T: git git://linuxtv.org/media_tree.git
S: Supported
F: drivers/thermal/
F: include/linux/thermal.h
+F: include/uapi/linux/thermal.h
F: include/linux/cpu_cooling.h
F: Documentation/devicetree/bindings/thermal/
F: net/tipc/
TILE ARCHITECTURE
-M: Chris Metcalf <cmetcalf@tilera.com>
+M: Chris Metcalf <cmetcalf@ezchip.com>
W: http://www.tilera.com/scm/
S: Supported
F: arch/tile/
F: mm/shmem.c
TM6000 VIDEO4LINUX DRIVER
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-media@vger.kernel.org
W: http://linuxtv.org
T: git git://linuxtv.org/media_tree.git
F: Documentation/hid/hiddev.txt
F: drivers/hid/usbhid/
-USB/IP DRIVERS
-L: linux-usb@vger.kernel.org
-S: Orphan
-F: drivers/staging/usbip/
-
USB ISP116X DRIVER
M: Olav Kongas <ok@artecdesign.ee>
L: linux-usb@vger.kernel.org
S: Maintained
F: arch/x86/kernel/cpu/mcheck/*
+X86 VDSO
+M: Andy Lutomirski <luto@amacapital.net>
+L: linux-kernel@vger.kernel.org
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86/vdso
+S: Maintained
+F: arch/x86/vdso/
+
XC2028/3028 TUNER DRIVER
-M: Mauro Carvalho Chehab <m.chehab@samsung.com>
+M: Mauro Carvalho Chehab <mchehab@osg.samsung.com>
L: linux-media@vger.kernel.org
W: http://linuxtv.org
T: git git://linuxtv.org/media_tree.git
pgd = pgdp + pgd_index(addr);
do {
next = kvm_pgd_addr_end(addr, end);
- unmap_puds(kvm, pgd, addr, next);
+ if (!pgd_none(*pgd))
+ unmap_puds(kvm, pgd, addr, next);
} while (pgd++, addr = next, addr != end);
}
unmap_range(kvm, kvm->arch.pgd, start, size);
}
+ static void stage2_unmap_memslot(struct kvm *kvm,
+ struct kvm_memory_slot *memslot)
+ {
+ hva_t hva = memslot->userspace_addr;
+ phys_addr_t addr = memslot->base_gfn << PAGE_SHIFT;
+ phys_addr_t size = PAGE_SIZE * memslot->npages;
+ hva_t reg_end = hva + size;
+
+ /*
+ * A memory region could potentially cover multiple VMAs, and any holes
+ * between them, so iterate over all of them to find out if we should
+ * unmap any of them.
+ *
+ * +--------------------------------------------+
+ * +---------------+----------------+ +----------------+
+ * | : VMA 1 | VMA 2 | | VMA 3 : |
+ * +---------------+----------------+ +----------------+
+ * | memory region |
+ * +--------------------------------------------+
+ */
+ do {
+ struct vm_area_struct *vma = find_vma(current->mm, hva);
+ hva_t vm_start, vm_end;
+
+ if (!vma || vma->vm_start >= reg_end)
+ break;
+
+ /*
+ * Take the intersection of this VMA with the memory region
+ */
+ vm_start = max(hva, vma->vm_start);
+ vm_end = min(reg_end, vma->vm_end);
+
+ if (!(vma->vm_flags & VM_PFNMAP)) {
+ gpa_t gpa = addr + (vm_start - memslot->userspace_addr);
+ unmap_stage2_range(kvm, gpa, vm_end - vm_start);
+ }
+ hva = vm_end;
+ } while (hva < reg_end);
+ }
+
+ /**
+ * stage2_unmap_vm - Unmap Stage-2 RAM mappings
+ * @kvm: The struct kvm pointer
+ *
+ * Go through the memregions and unmap any reguler RAM
+ * backing memory already mapped to the VM.
+ */
+ void stage2_unmap_vm(struct kvm *kvm)
+ {
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+ int idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ spin_lock(&kvm->mmu_lock);
+
+ slots = kvm_memslots(kvm);
+ kvm_for_each_memslot(memslot, slots)
+ stage2_unmap_memslot(kvm, memslot);
+
+ spin_unlock(&kvm->mmu_lock);
+ srcu_read_unlock(&kvm->srcu, idx);
+ }
+
/**
* kvm_free_stage2_pgd - free all stage-2 tables
* @kvm: The KVM struct pointer for the VM.
struct vm_area_struct *vma;
pfn_t pfn;
pgprot_t mem_type = PAGE_S2;
+ bool fault_ipa_uncached;
write_fault = kvm_is_write_fault(vcpu);
if (fault_status == FSC_PERM && !write_fault) {
if (!hugetlb && !force_pte)
hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);
+ fault_ipa_uncached = memslot->flags & KVM_MEMSLOT_INCOHERENT;
+
if (hugetlb) {
pmd_t new_pmd = pfn_pmd(pfn, mem_type);
new_pmd = pmd_mkhuge(new_pmd);
kvm_set_s2pmd_writable(&new_pmd);
kvm_set_pfn_dirty(pfn);
}
- coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE);
+ coherent_cache_guest_page(vcpu, hva & PMD_MASK, PMD_SIZE,
+ fault_ipa_uncached);
ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
} else {
pte_t new_pte = pfn_pte(pfn, mem_type);
kvm_set_s2pte_writable(&new_pte);
kvm_set_pfn_dirty(pfn);
}
- coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
+ coherent_cache_guest_page(vcpu, hva, PAGE_SIZE,
+ fault_ipa_uncached);
ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte,
pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
}
hva = vm_end;
} while (hva < reg_end);
- if (ret) {
- spin_lock(&kvm->mmu_lock);
+ spin_lock(&kvm->mmu_lock);
+ if (ret)
unmap_stage2_range(kvm, mem->guest_phys_addr, mem->memory_size);
- spin_unlock(&kvm->mmu_lock);
- }
+ else
+ stage2_flush_memslot(kvm, memslot);
+ spin_unlock(&kvm->mmu_lock);
return ret;
}
int kvm_arch_create_memslot(struct kvm *kvm, struct kvm_memory_slot *slot,
unsigned long npages)
{
+ /*
+ * Readonly memslots are not incoherent with the caches by definition,
+ * but in practice, they are used mostly to emulate ROMs or NOR flashes
+ * that the guest may consider devices and hence map as uncached.
+ * To prevent incoherency issues in these cases, tag all readonly
+ * regions as incoherent.
+ */
+ if (slot->flags & KVM_MEM_READONLY)
+ slot->flags |= KVM_MEMSLOT_INCOHERENT;
return 0;
}
select PCI if (!IA64_HP_SIM)
select ACPI if (!IA64_HP_SIM)
select ARCH_MIGHT_HAVE_ACPI_PDC if ACPI
- select PM if (!IA64_HP_SIM)
select HAVE_UNSTABLE_SCHED_CLOCK
select HAVE_IDE
select HAVE_OPROFILE
select HAVE_DYNAMIC_FTRACE if (!ITANIUM)
select HAVE_FUNCTION_TRACER
select HAVE_DMA_ATTRS
- select HAVE_KVM
select TTY
select HAVE_ARCH_TRACEHOOK
select HAVE_DMA_API_DEBUG
config IA64_HP_SIM
bool "Ski-simulator"
select SWIOTLB
+ depends on !PM_RUNTIME
endchoice
source "crypto/Kconfig"
- source "arch/ia64/kvm/Kconfig"
-
source "lib/Kconfig"
config IOMMU_HELPER
DEFINE(KVM_HOST_LPID, offsetof(struct kvm, arch.host_lpid));
DEFINE(KVM_HOST_LPCR, offsetof(struct kvm, arch.host_lpcr));
DEFINE(KVM_HOST_SDR1, offsetof(struct kvm, arch.host_sdr1));
- DEFINE(KVM_TLBIE_LOCK, offsetof(struct kvm, arch.tlbie_lock));
DEFINE(KVM_NEED_FLUSH, offsetof(struct kvm, arch.need_tlb_flush.bits));
DEFINE(KVM_ENABLED_HCALLS, offsetof(struct kvm, arch.enabled_hcalls));
DEFINE(KVM_LPCR, offsetof(struct kvm, arch.lpcr));
DEFINE(VCPU_DAR, offsetof(struct kvm_vcpu, arch.shregs.dar));
DEFINE(VCPU_VPA, offsetof(struct kvm_vcpu, arch.vpa.pinned_addr));
DEFINE(VCPU_VPA_DIRTY, offsetof(struct kvm_vcpu, arch.vpa.dirty));
+ DEFINE(VCPU_HEIR, offsetof(struct kvm_vcpu, arch.emul_inst));
#endif
#ifdef CONFIG_PPC_BOOK3S
DEFINE(VCPU_VCPUID, offsetof(struct kvm_vcpu, vcpu_id));
arch.timing_last_enter.tv32.tbl));
#endif
-#ifdef CONFIG_PPC_POWERNV
- DEFINE(OPAL_MC_GPR3, offsetof(struct opal_machine_check_event, gpr3));
- DEFINE(OPAL_MC_SRR0, offsetof(struct opal_machine_check_event, srr0));
- DEFINE(OPAL_MC_SRR1, offsetof(struct opal_machine_check_event, srr1));
- DEFINE(PACA_OPAL_MC_EVT, offsetof(struct paca_struct, opal_mc_evt));
-#endif
-
return 0;
}
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/spinlock.h>
-#include <linux/bootmem.h>
#include <linux/init.h>
#include <linux/memblock.h>
#include <linux/sizes.h>
#include <linux/cma.h>
+ #include <linux/bitops.h>
#include <asm/cputable.h>
#include <asm/kvm_ppc.h>
* By default we reserve 5% of memory for hash pagetable allocation.
*/
static unsigned long kvm_cma_resv_ratio = 5;
- /*
- * We allocate RMAs (real mode areas) for KVM guests from the KVM CMA area.
- * Each RMA has to be physically contiguous and of a size that the
- * hardware supports. PPC970 and POWER7 support 64MB, 128MB and 256MB,
- * and other larger sizes. Since we are unlikely to be allocate that
- * much physically contiguous memory after the system is up and running,
- * we preallocate a set of RMAs in early boot using CMA.
- * should be power of 2.
- */
- unsigned long kvm_rma_pages = (1 << 27) >> PAGE_SHIFT; /* 128MB */
- EXPORT_SYMBOL_GPL(kvm_rma_pages);
static struct cma *kvm_cma;
- /* Work out RMLS (real mode limit selector) field value for a given RMA size.
- Assumes POWER7 or PPC970. */
- static inline int lpcr_rmls(unsigned long rma_size)
- {
- switch (rma_size) {
- case 32ul << 20: /* 32 MB */
- if (cpu_has_feature(CPU_FTR_ARCH_206))
- return 8; /* only supported on POWER7 */
- return -1;
- case 64ul << 20: /* 64 MB */
- return 3;
- case 128ul << 20: /* 128 MB */
- return 7;
- case 256ul << 20: /* 256 MB */
- return 4;
- case 1ul << 30: /* 1 GB */
- return 2;
- case 16ul << 30: /* 16 GB */
- return 1;
- case 256ul << 30: /* 256 GB */
- return 0;
- default:
- return -1;
- }
- }
-
- static int __init early_parse_rma_size(char *p)
- {
- unsigned long kvm_rma_size;
-
- pr_debug("%s(%s)\n", __func__, p);
- if (!p)
- return -EINVAL;
- kvm_rma_size = memparse(p, &p);
- /*
- * Check that the requested size is one supported in hardware
- */
- if (lpcr_rmls(kvm_rma_size) < 0) {
- pr_err("RMA size of 0x%lx not supported\n", kvm_rma_size);
- return -EINVAL;
- }
- kvm_rma_pages = kvm_rma_size >> PAGE_SHIFT;
- return 0;
- }
- early_param("kvm_rma_size", early_parse_rma_size);
-
- struct kvm_rma_info *kvm_alloc_rma()
- {
- struct page *page;
- struct kvm_rma_info *ri;
-
- ri = kmalloc(sizeof(struct kvm_rma_info), GFP_KERNEL);
- if (!ri)
- return NULL;
- page = cma_alloc(kvm_cma, kvm_rma_pages, order_base_2(kvm_rma_pages));
- if (!page)
- goto err_out;
- atomic_set(&ri->use_count, 1);
- ri->base_pfn = page_to_pfn(page);
- return ri;
- err_out:
- kfree(ri);
- return NULL;
- }
- EXPORT_SYMBOL_GPL(kvm_alloc_rma);
-
- void kvm_release_rma(struct kvm_rma_info *ri)
- {
- if (atomic_dec_and_test(&ri->use_count)) {
- cma_release(kvm_cma, pfn_to_page(ri->base_pfn), kvm_rma_pages);
- kfree(ri);
- }
- }
- EXPORT_SYMBOL_GPL(kvm_release_rma);
-
static int __init early_parse_kvm_cma_resv(char *p)
{
pr_debug("%s(%s)\n", __func__, p);
struct page *kvm_alloc_hpt(unsigned long nr_pages)
{
- unsigned long align_pages = HPT_ALIGN_PAGES;
-
VM_BUG_ON(order_base_2(nr_pages) < KVM_CMA_CHUNK_ORDER - PAGE_SHIFT);
- /* Old CPUs require HPT aligned on a multiple of its size */
- if (!cpu_has_feature(CPU_FTR_ARCH_206))
- align_pages = nr_pages;
- return cma_alloc(kvm_cma, nr_pages, order_base_2(align_pages));
+ return cma_alloc(kvm_cma, nr_pages, order_base_2(HPT_ALIGN_PAGES));
}
EXPORT_SYMBOL_GPL(kvm_alloc_hpt);
* kvm_cma_reserve() - reserve area for kvm hash pagetable
*
* This function reserves memory from early allocator. It should be
- * called by arch specific code once the early allocator (memblock or bootmem)
+ * called by arch specific code once the memblock allocator
* has been activated and all other subsystems have already allocated/reserved
* memory.
*/
if (selected_size) {
pr_debug("%s: reserving %ld MiB for global area\n", __func__,
(unsigned long)selected_size / SZ_1M);
- /*
- * Old CPUs require HPT aligned on a multiple of its size. So for them
- * make the alignment as max size we could request.
- */
- if (!cpu_has_feature(CPU_FTR_ARCH_206))
- align_size = __rounddown_pow_of_two(selected_size);
- else
- align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
-
- align_size = max(kvm_rma_pages << PAGE_SHIFT, align_size);
+ align_size = HPT_ALIGN_PAGES << PAGE_SHIFT;
cma_declare_contiguous(0, selected_size, 0, align_size,
KVM_CMA_CHUNK_ORDER - PAGE_SHIFT, false, &kvm_cma);
}
}
+ /*
+ * Real-mode H_CONFER implementation.
+ * We check if we are the only vcpu out of this virtual core
+ * still running in the guest and not ceded. If so, we pop up
+ * to the virtual-mode implementation; if not, just return to
+ * the guest.
+ */
+ long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
+ unsigned int yield_count)
+ {
+ struct kvmppc_vcore *vc = vcpu->arch.vcore;
+ int threads_running;
+ int threads_ceded;
+ int threads_conferring;
+ u64 stop = get_tb() + 10 * tb_ticks_per_usec;
+ int rv = H_SUCCESS; /* => don't yield */
+
+ set_bit(vcpu->arch.ptid, &vc->conferring_threads);
+ while ((get_tb() < stop) && (VCORE_EXIT_COUNT(vc) == 0)) {
+ threads_running = VCORE_ENTRY_COUNT(vc);
+ threads_ceded = hweight32(vc->napping_threads);
+ threads_conferring = hweight32(vc->conferring_threads);
+ if (threads_ceded + threads_conferring >= threads_running) {
+ rv = H_TOO_HARD; /* => do yield */
+ break;
+ }
+ }
+ clear_bit(vcpu->arch.ptid, &vc->conferring_threads);
+ return rv;
+ }
+
/*
* When running HV mode KVM we need to block certain operations while KVM VMs
* exist in the system. We use a counter of VMs to track this.
lwz r6, HSTATE_PMC + 12(r13)
lwz r8, HSTATE_PMC + 16(r13)
lwz r9, HSTATE_PMC + 20(r13)
- BEGIN_FTR_SECTION
- lwz r10, HSTATE_PMC + 24(r13)
- lwz r11, HSTATE_PMC + 28(r13)
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
mtspr SPRN_PMC1, r3
mtspr SPRN_PMC2, r4
mtspr SPRN_PMC3, r5
mtspr SPRN_PMC4, r6
mtspr SPRN_PMC5, r8
mtspr SPRN_PMC6, r9
- BEGIN_FTR_SECTION
- mtspr SPRN_PMC7, r10
- mtspr SPRN_PMC8, r11
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
ld r3, HSTATE_MMCR(r13)
ld r4, HSTATE_MMCR + 8(r13)
ld r5, HSTATE_MMCR + 16(r13)
cmpwi cr1, r12, BOOK3S_INTERRUPT_MACHINE_CHECK
cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL
- BEGIN_FTR_SECTION
beq 11f
cmpwi cr2, r12, BOOK3S_INTERRUPT_HMI
beq cr2, 14f /* HMI check */
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* RFI into the highmem handler, or branch to interrupt handler */
mfmsr r6
mtmsrd r6, 1 /* Clear RI in MSR */
mtsrr0 r8
mtsrr1 r7
- beqa 0x500 /* external interrupt (PPC970) */
beq cr1, 13f /* machine check */
RFI
bge kvm_novcpu_exit /* another thread already exiting */
li r3, NAPPING_NOVCPU
stb r3, HSTATE_NAPPING(r13)
- li r3, 1
- stb r3, HSTATE_HWTHREAD_REQ(r13)
b kvm_do_nap
/* if we have no vcpu to run, go back to sleep */
beq kvm_no_guest
+kvm_secondary_got_guest:
+
/* Set HSTATE_DSCR(r13) to something sensible */
ld r6, PACA_DSCR(r13)
std r6, HSTATE_DSCR(r13)
stwcx. r3, 0, r4
bne 51b
+/*
+ * At this point we have finished executing in the guest.
+ * We need to wait for hwthread_req to become zero, since
+ * we may not turn on the MMU while hwthread_req is non-zero.
+ * While waiting we also need to check if we get given a vcpu to run.
+ */
kvm_no_guest:
- li r0, KVM_HWTHREAD_IN_NAP
+ lbz r3, HSTATE_HWTHREAD_REQ(r13)
+ cmpwi r3, 0
+ bne 53f
+ HMT_MEDIUM
+ li r0, KVM_HWTHREAD_IN_KERNEL
stb r0, HSTATE_HWTHREAD_STATE(r13)
-kvm_do_nap:
- /* Clear the runlatch bit before napping */
- mfspr r2, SPRN_CTRLF
- clrrdi r2, r2, 1
- mtspr SPRN_CTRLT, r2
-
+ /* need to recheck hwthread_req after a barrier, to avoid race */
+ sync
+ lbz r3, HSTATE_HWTHREAD_REQ(r13)
+ cmpwi r3, 0
+ bne 54f
+/*
+ * We jump to power7_wakeup_loss, which will return to the caller
+ * of power7_nap in the powernv cpu offline loop. The value we
+ * put in r3 becomes the return value for power7_nap.
+ */
li r3, LPCR_PECE0
mfspr r4, SPRN_LPCR
rlwimi r4, r3, 0, LPCR_PECE0 | LPCR_PECE1
mtspr SPRN_LPCR, r4
- isync
- std r0, HSTATE_SCRATCH0(r13)
- ptesync
- ld r0, HSTATE_SCRATCH0(r13)
-1: cmpd r0, r0
- bne 1b
- nap
- b .
+ li r3, 0
+ b power7_wakeup_loss
+
+53: HMT_LOW
+ ld r4, HSTATE_KVM_VCPU(r13)
+ cmpdi r4, 0
+ beq kvm_no_guest
+ HMT_MEDIUM
+ b kvm_secondary_got_guest
+
+54: li r0, KVM_HWTHREAD_IN_KVM
+ stb r0, HSTATE_HWTHREAD_STATE(r13)
+ b kvm_no_guest
/******************************************************************************
* *
slbia
ptesync
- BEGIN_FTR_SECTION
- b 30f
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
/*
- * POWER7 host -> guest partition switch code.
+ * POWER7/POWER8 host -> guest partition switch code.
* We don't have to lock against concurrent tlbies,
* but we do have to coordinate across hardware threads.
*/
cmpwi r3,512 /* 1 microsecond */
li r12,BOOK3S_INTERRUPT_HV_DECREMENTER
blt hdec_soon
- b 31f
-
- /*
- * PPC970 host -> guest partition switch code.
- * We have to lock against concurrent tlbies,
- * using native_tlbie_lock to lock against host tlbies
- * and kvm->arch.tlbie_lock to lock against guest tlbies.
- * We also have to invalidate the TLB since its
- * entries aren't tagged with the LPID.
- */
- 30: ld r5,HSTATE_KVM_VCORE(r13)
- ld r9,VCORE_KVM(r5) /* pointer to struct kvm */
-
- /* first take native_tlbie_lock */
- .section ".toc","aw"
- toc_tlbie_lock:
- .tc native_tlbie_lock[TC],native_tlbie_lock
- .previous
- ld r3,toc_tlbie_lock@toc(r2)
- #ifdef __BIG_ENDIAN__
- lwz r8,PACA_LOCK_TOKEN(r13)
- #else
- lwz r8,PACAPACAINDEX(r13)
- #endif
- 24: lwarx r0,0,r3
- cmpwi r0,0
- bne 24b
- stwcx. r8,0,r3
- bne 24b
- isync
-
- ld r5,HSTATE_KVM_VCORE(r13)
- ld r7,VCORE_LPCR(r5) /* use vcore->lpcr to store HID4 */
- li r0,0x18f
- rotldi r0,r0,HID4_LPID5_SH /* all lpid bits in HID4 = 1 */
- or r0,r7,r0
- ptesync
- sync
- mtspr SPRN_HID4,r0 /* switch to reserved LPID */
- isync
- li r0,0
- stw r0,0(r3) /* drop native_tlbie_lock */
-
- /* invalidate the whole TLB */
- li r0,256
- mtctr r0
- li r6,0
- 25: tlbiel r6
- addi r6,r6,0x1000
- bdnz 25b
- ptesync
- /* Take the guest's tlbie_lock */
- addi r3,r9,KVM_TLBIE_LOCK
- 24: lwarx r0,0,r3
- cmpwi r0,0
- bne 24b
- stwcx. r8,0,r3
- bne 24b
- isync
- ld r6,KVM_SDR1(r9)
- mtspr SPRN_SDR1,r6 /* switch to partition page table */
-
- /* Set up HID4 with the guest's LPID etc. */
- sync
- mtspr SPRN_HID4,r7
- isync
-
- /* drop the guest's tlbie_lock */
- li r0,0
- stw r0,0(r3)
-
- /* Check if HDEC expires soon */
- mfspr r3,SPRN_HDEC
- cmpwi r3,10
- li r12,BOOK3S_INTERRUPT_HV_DECREMENTER
- blt hdec_soon
-
- /* Enable HDEC interrupts */
- mfspr r0,SPRN_HID0
- li r3,1
- rldimi r0,r3, HID0_HDICE_SH, 64-HID0_HDICE_SH-1
- sync
- mtspr SPRN_HID0,r0
- mfspr r0,SPRN_HID0
- mfspr r0,SPRN_HID0
- mfspr r0,SPRN_HID0
- mfspr r0,SPRN_HID0
- mfspr r0,SPRN_HID0
- mfspr r0,SPRN_HID0
- 31:
/* Do we have a guest vcpu to run? */
cmpdi r4, 0
beq kvmppc_primary_no_guest
stb r6, VCPU_VPA_DIRTY(r4)
25:
- BEGIN_FTR_SECTION
/* Save purr/spurr */
mfspr r5,SPRN_PURR
mfspr r6,SPRN_SPURR
ld r8,VCPU_SPURR(r4)
mtspr SPRN_PURR,r7
mtspr SPRN_SPURR,r8
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
BEGIN_FTR_SECTION
/* Set partition DABR */
ld r6,VCPU_DABR(r4)
mtspr SPRN_DABRX,r5
mtspr SPRN_DABR,r6
- BEGIN_FTR_SECTION_NESTED(89)
isync
- END_FTR_SECTION_NESTED(CPU_FTR_ARCH_206, CPU_FTR_ARCH_206, 89)
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
lwz r7, VCPU_PMC + 12(r4)
lwz r8, VCPU_PMC + 16(r4)
lwz r9, VCPU_PMC + 20(r4)
- BEGIN_FTR_SECTION
- lwz r10, VCPU_PMC + 24(r4)
- lwz r11, VCPU_PMC + 28(r4)
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
mtspr SPRN_PMC1, r3
mtspr SPRN_PMC2, r5
mtspr SPRN_PMC3, r6
mtspr SPRN_PMC4, r7
mtspr SPRN_PMC5, r8
mtspr SPRN_PMC6, r9
- BEGIN_FTR_SECTION
- mtspr SPRN_PMC7, r10
- mtspr SPRN_PMC8, r11
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
ld r3, VCPU_MMCR(r4)
ld r5, VCPU_MMCR + 8(r4)
ld r6, VCPU_MMCR + 16(r4)
ld r30, VCPU_GPR(R30)(r4)
ld r31, VCPU_GPR(R31)(r4)
- BEGIN_FTR_SECTION
/* Switch DSCR to guest value */
ld r5, VCPU_DSCR(r4)
mtspr SPRN_DSCR, r5
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
BEGIN_FTR_SECTION
- /* Skip next section on POWER7 or PPC970 */
+ /* Skip next section on POWER7 */
b 8f
END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
/* Turn on TM so we can access TFHAR/TFIAR/TEXASR */
mtspr SPRN_DAR, r5
mtspr SPRN_DSISR, r6
- BEGIN_FTR_SECTION
/* Restore AMR and UAMOR, set AMOR to all 1s */
ld r5,VCPU_AMR(r4)
ld r6,VCPU_UAMOR(r4)
mtspr SPRN_AMR,r5
mtspr SPRN_UAMOR,r6
mtspr SPRN_AMOR,r7
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* Restore state of CTRL run bit; assume 1 on entry */
lwz r5,VCPU_CTRL(r4)
rldicl r0, r0, 64 - BOOK3S_IRQPRIO_EXTERNAL_LEVEL, 63
cmpdi cr1, r0, 0
andi. r8, r11, MSR_EE
- BEGIN_FTR_SECTION
mfspr r8, SPRN_LPCR
/* Insert EXTERNAL_LEVEL bit into LPCR at the MER bit position */
rldimi r8, r0, LPCR_MER_SH, 63 - LPCR_MER_SH
mtspr SPRN_LPCR, r8
isync
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
beq 5f
li r0, BOOK3S_INTERRUPT_EXTERNAL
bne cr1, 12f
stw r12,VCPU_TRAP(r9)
- /* Save HEIR (HV emulation assist reg) in last_inst
+ /* Save HEIR (HV emulation assist reg) in emul_inst
if this is an HEI (HV emulation interrupt, e40) */
li r3,KVM_INST_FETCH_FAILED
- BEGIN_FTR_SECTION
cmpwi r12,BOOK3S_INTERRUPT_H_EMUL_ASSIST
bne 11f
mfspr r3,SPRN_HEIR
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
- 11: stw r3,VCPU_LAST_INST(r9)
+ 11: stw r3,VCPU_HEIR(r9)
/* these are volatile across C function calls */
mfctr r3
std r3, VCPU_CTR(r9)
stw r4, VCPU_XER(r9)
- BEGIN_FTR_SECTION
/* If this is a page table miss then see if it's theirs or ours */
cmpwi r12, BOOK3S_INTERRUPT_H_DATA_STORAGE
beq kvmppc_hdsi
cmpwi r12, BOOK3S_INTERRUPT_H_INST_STORAGE
beq kvmppc_hisi
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* See if this is a leftover HDEC interrupt */
cmpwi r12,BOOK3S_INTERRUPT_HV_DECREMENTER
cmpwi r12,BOOK3S_INTERRUPT_SYSCALL
beq hcall_try_real_mode
- /* Only handle external interrupts here on arch 206 and later */
- BEGIN_FTR_SECTION
- b ext_interrupt_to_host
- END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
-
/* External interrupt ? */
cmpwi r12, BOOK3S_INTERRUPT_EXTERNAL
bne+ ext_interrupt_to_host
mfdsisr r7
std r6, VCPU_DAR(r9)
stw r7, VCPU_DSISR(r9)
- BEGIN_FTR_SECTION
/* don't overwrite fault_dar/fault_dsisr if HDSI */
cmpwi r12,BOOK3S_INTERRUPT_H_DATA_STORAGE
beq 6f
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
std r6, VCPU_FAULT_DAR(r9)
stw r7, VCPU_FAULT_DSISR(r9)
/*
* Save the guest PURR/SPURR
*/
- BEGIN_FTR_SECTION
mfspr r5,SPRN_PURR
mfspr r6,SPRN_SPURR
ld r7,VCPU_PURR(r9)
add r4,r4,r6
mtspr SPRN_PURR,r3
mtspr SPRN_SPURR,r4
- END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_201)
/* Save DEC */
mfspr r5,SPRN_DEC
8:
/* Save and reset AMR and UAMOR before turning on the MMU */
- BEGIN_FTR_SECTION
mfspr r5,SPRN_AMR
mfspr r6,SPRN_UAMOR
std r5,VCPU_AMR(r9)
std r6,VCPU_UAMOR(r9)
li r6,0
mtspr SPRN_AMR,r6
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* Switch DSCR back to host value */
- BEGIN_FTR_SECTION
mfspr r8, SPRN_DSCR
ld r7, HSTATE_DSCR(r13)
std r8, VCPU_DSCR(r9)
mtspr SPRN_DSCR, r7
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
/* Save non-volatile GPRs */
std r14, VCPU_GPR(R14)(r9)
mfspr r4, SPRN_MMCR0 /* save MMCR0 */
mtspr SPRN_MMCR0, r3 /* freeze all counters, disable ints */
mfspr r6, SPRN_MMCRA
- BEGIN_FTR_SECTION
- /* On P7, clear MMCRA in order to disable SDAR updates */
+ /* Clear MMCRA in order to disable SDAR updates */
li r7, 0
mtspr SPRN_MMCRA, r7
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_206)
isync
beq 21f /* if no VPA, save PMU stuff anyway */
lbz r7, LPPACA_PMCINUSE(r8)
mfspr r6, SPRN_PMC4
mfspr r7, SPRN_PMC5
mfspr r8, SPRN_PMC6
- BEGIN_FTR_SECTION
- mfspr r10, SPRN_PMC7
- mfspr r11, SPRN_PMC8
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
stw r3, VCPU_PMC(r9)
stw r4, VCPU_PMC + 4(r9)
stw r5, VCPU_PMC + 8(r9)
stw r6, VCPU_PMC + 12(r9)
stw r7, VCPU_PMC + 16(r9)
stw r8, VCPU_PMC + 20(r9)
- BEGIN_FTR_SECTION
- stw r10, VCPU_PMC + 24(r9)
- stw r11, VCPU_PMC + 28(r9)
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
BEGIN_FTR_SECTION
mfspr r5, SPRN_SIER
mfspr r6, SPRN_SPMC1
ptesync
hdec_soon: /* r12 = trap, r13 = paca */
- BEGIN_FTR_SECTION
- b 32f
- END_FTR_SECTION_IFSET(CPU_FTR_ARCH_201)
/*
- * POWER7 guest -> host partition switch code.
+ * POWER7/POWER8 guest -> host partition switch code.
* We don't have to lock against tlbies but we do
* have to coordinate the hardware threads.
*/
16: ld r8,KVM_HOST_LPCR(r4)
mtspr SPRN_LPCR,r8
isync
- b 33f
-
- /*
- * PPC970 guest -> host partition switch code.
- * We have to lock against concurrent tlbies, and
- * we have to flush the whole TLB.
- */
- 32: ld r5,HSTATE_KVM_VCORE(r13)
- ld r4,VCORE_KVM(r5) /* pointer to struct kvm */
-
- /* Take the guest's tlbie_lock */
- #ifdef __BIG_ENDIAN__
- lwz r8,PACA_LOCK_TOKEN(r13)
- #else
- lwz r8,PACAPACAINDEX(r13)
- #endif
- addi r3,r4,KVM_TLBIE_LOCK
- 24: lwarx r0,0,r3
- cmpwi r0,0
- bne 24b
- stwcx. r8,0,r3
- bne 24b
- isync
-
- ld r7,KVM_HOST_LPCR(r4) /* use kvm->arch.host_lpcr for HID4 */
- li r0,0x18f
- rotldi r0,r0,HID4_LPID5_SH /* all lpid bits in HID4 = 1 */
- or r0,r7,r0
- ptesync
- sync
- mtspr SPRN_HID4,r0 /* switch to reserved LPID */
- isync
- li r0,0
- stw r0,0(r3) /* drop guest tlbie_lock */
-
- /* invalidate the whole TLB */
- li r0,256
- mtctr r0
- li r6,0
- 25: tlbiel r6
- addi r6,r6,0x1000
- bdnz 25b
- ptesync
-
- /* take native_tlbie_lock */
- ld r3,toc_tlbie_lock@toc(2)
- 24: lwarx r0,0,r3
- cmpwi r0,0
- bne 24b
- stwcx. r8,0,r3
- bne 24b
- isync
-
- ld r6,KVM_HOST_SDR1(r4)
- mtspr SPRN_SDR1,r6 /* switch to host page table */
-
- /* Set up host HID4 value */
- sync
- mtspr SPRN_HID4,r7
- isync
- li r0,0
- stw r0,0(r3) /* drop native_tlbie_lock */
-
- lis r8,0x7fff /* MAX_INT@h */
- mtspr SPRN_HDEC,r8
-
- /* Disable HDEC interrupts */
- mfspr r0,SPRN_HID0
- li r3,0
- rldimi r0,r3, HID0_HDICE_SH, 64-HID0_HDICE_SH-1
- sync
- mtspr SPRN_HID0,r0
- mfspr r0,SPRN_HID0
- mfspr r0,SPRN_HID0
- mfspr r0,SPRN_HID0
- mfspr r0,SPRN_HID0
- mfspr r0,SPRN_HID0
- mfspr r0,SPRN_HID0
/* load host SLB entries */
- 33: ld r8,PACA_SLBSHADOWPTR(r13)
+ ld r8,PACA_SLBSHADOWPTR(r13)
.rept SLB_NUM_BOLTED
li r3, SLBSHADOW_SAVEAREA
.long 0 /* 0xd8 */
.long 0 /* 0xdc */
.long DOTSYM(kvmppc_h_cede) - hcall_real_table
- .long 0 /* 0xe4 */
+ .long DOTSYM(kvmppc_rm_h_confer) - hcall_real_table
.long 0 /* 0xe8 */
.long 0 /* 0xec */
.long 0 /* 0xf0 */
stw r0,VCPU_TRAP(r3)
li r0,H_SUCCESS
std r0,VCPU_GPR(R3)(r3)
- BEGIN_FTR_SECTION
- b kvm_cede_exit /* just send it up to host on 970 */
- END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_206)
/*
* Set our bit in the bitmask of napping threads unless all the
* occurs, with PECE1, PECE0 and PECEDP set in LPCR. Also clear the
* runlatch bit before napping.
*/
+kvm_do_nap:
mfspr r2, SPRN_CTRLF
clrrdi r2, r2, 1
mtspr SPRN_CTRLT, r2
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
mtmsrd r8
- isync
addi r3,r3,VCPU_FPRS
bl store_fp_state
#ifdef CONFIG_ALTIVEC
END_FTR_SECTION_IFSET(CPU_FTR_VSX)
#endif
mtmsrd r8
- isync
addi r3,r4,VCPU_FPRS
bl load_fp_state
#ifdef CONFIG_ALTIVEC
unsigned long sid;
int ret = -1;
- sid = ++(__get_cpu_var(pcpu_last_used_sid));
+ sid = __this_cpu_inc_return(pcpu_last_used_sid);
if (sid < NUM_TIDS) {
- __get_cpu_var(pcpu_sids).entry[sid] = entry;
+ __this_cpu_write(pcpu_sids.entry[sid], entry);
entry->val = sid;
- entry->pentry = &__get_cpu_var(pcpu_sids).entry[sid];
+ entry->pentry = this_cpu_ptr(&pcpu_sids.entry[sid]);
ret = sid;
}
static inline int local_sid_lookup(struct id *entry)
{
if (entry && entry->val != 0 &&
- __get_cpu_var(pcpu_sids).entry[entry->val] == entry &&
- entry->pentry == &__get_cpu_var(pcpu_sids).entry[entry->val])
+ __this_cpu_read(pcpu_sids.entry[entry->val]) == entry &&
+ entry->pentry == this_cpu_ptr(&pcpu_sids.entry[entry->val]))
return entry->val;
return -1;
}
/* Invalidate all id mappings on local core -- call with preempt disabled */
static inline void local_sid_destroy_all(void)
{
- __get_cpu_var(pcpu_last_used_sid) = 0;
- memset(&__get_cpu_var(pcpu_sids), 0, sizeof(__get_cpu_var(pcpu_sids)));
+ __this_cpu_write(pcpu_last_used_sid, 0);
+ memset(this_cpu_ptr(&pcpu_sids), 0, sizeof(pcpu_sids));
}
static void *kvmppc_e500_id_table_alloc(struct kvmppc_vcpu_e500 *vcpu_e500)
kvmppc_e500_recalc_shadow_pid(to_e500(vcpu));
}
- void kvmppc_core_load_host_debugstate(struct kvm_vcpu *vcpu)
- {
- }
-
- void kvmppc_core_load_guest_debugstate(struct kvm_vcpu *vcpu)
- {
- }
-
static void kvmppc_core_vcpu_load_e500(struct kvm_vcpu *vcpu, int cpu)
{
kvmppc_booke_vcpu_load(vcpu, cpu);
void page_table_free(struct mm_struct *, unsigned long *);
void page_table_free_rcu(struct mmu_gather *, unsigned long *, unsigned long);
-void page_table_reset_pgste(struct mm_struct *, unsigned long, unsigned long,
- bool init_skey);
int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
unsigned long key, bool nq);
+ unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr);
static inline void clear_table(unsigned long *s, unsigned long val, size_t n)
{
{ "instruction_sigp_sense_running", VCPU_STAT(instruction_sigp_sense_running) },
{ "instruction_sigp_external_call", VCPU_STAT(instruction_sigp_external_call) },
{ "instruction_sigp_emergency", VCPU_STAT(instruction_sigp_emergency) },
+ { "instruction_sigp_cond_emergency", VCPU_STAT(instruction_sigp_cond_emergency) },
+ { "instruction_sigp_start", VCPU_STAT(instruction_sigp_start) },
{ "instruction_sigp_stop", VCPU_STAT(instruction_sigp_stop) },
+ { "instruction_sigp_stop_store_status", VCPU_STAT(instruction_sigp_stop_store_status) },
+ { "instruction_sigp_store_status", VCPU_STAT(instruction_sigp_store_status) },
{ "instruction_sigp_set_arch", VCPU_STAT(instruction_sigp_arch) },
{ "instruction_sigp_set_prefix", VCPU_STAT(instruction_sigp_prefix) },
{ "instruction_sigp_restart", VCPU_STAT(instruction_sigp_restart) },
+ { "instruction_sigp_cpu_reset", VCPU_STAT(instruction_sigp_cpu_reset) },
+ { "instruction_sigp_init_cpu_reset", VCPU_STAT(instruction_sigp_init_cpu_reset) },
+ { "instruction_sigp_unknown", VCPU_STAT(instruction_sigp_unknown) },
{ "diagnose_10", VCPU_STAT(diagnose_10) },
{ "diagnose_44", VCPU_STAT(diagnose_44) },
{ "diagnose_9c", VCPU_STAT(diagnose_9c) },
case KVM_S390_VM_MEM_CLR_CMMA:
mutex_lock(&kvm->lock);
idx = srcu_read_lock(&kvm->srcu);
- page_table_reset_pgste(kvm->arch.gmap->mm, 0, TASK_SIZE, false);
+ s390_reset_cmma(kvm->arch.gmap->mm);
srcu_read_unlock(&kvm->srcu, idx);
mutex_unlock(&kvm->lock);
ret = 0;
spin_lock_init(&kvm->arch.float_int.lock);
INIT_LIST_HEAD(&kvm->arch.float_int.list);
init_waitqueue_head(&kvm->arch.ipte_wq);
+ mutex_init(&kvm->arch.ipte_mutex);
debug_register_view(kvm->arch.dbf, &debug_sprintf_view);
VM_EVENT(kvm, 3, "%s", "vm created");
}
spin_lock_init(&vcpu->arch.local_int.lock);
- INIT_LIST_HEAD(&vcpu->arch.local_int.list);
vcpu->arch.local_int.float_int = &kvm->arch.float_int;
vcpu->arch.local_int.wq = &vcpu->wq;
vcpu->arch.local_int.cpuflags = &vcpu->arch.sie_block->cpuflags;
unsigned long token)
{
struct kvm_s390_interrupt inti;
- inti.parm64 = token;
+ struct kvm_s390_irq irq;
if (start_token) {
- inti.type = KVM_S390_INT_PFAULT_INIT;
- WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &inti));
+ irq.u.ext.ext_params2 = token;
+ irq.type = KVM_S390_INT_PFAULT_INIT;
+ WARN_ON_ONCE(kvm_s390_inject_vcpu(vcpu, &irq));
} else {
inti.type = KVM_S390_INT_PFAULT_DONE;
+ inti.parm64 = token;
WARN_ON_ONCE(kvm_s390_inject_vm(vcpu->kvm, &inti));
}
}
switch (ioctl) {
case KVM_S390_INTERRUPT: {
struct kvm_s390_interrupt s390int;
+ struct kvm_s390_irq s390irq;
r = -EFAULT;
if (copy_from_user(&s390int, argp, sizeof(s390int)))
break;
- r = kvm_s390_inject_vcpu(vcpu, &s390int);
+ if (s390int_to_s390irq(&s390int, &s390irq))
+ return -EINVAL;
+ r = kvm_s390_inject_vcpu(vcpu, &s390irq);
break;
}
case KVM_S390_STORE_STATUS:
return 0;
}
-static void __skey_check_enable(struct kvm_vcpu *vcpu)
+static int __skey_check_enable(struct kvm_vcpu *vcpu)
{
+ int rc = 0;
if (!(vcpu->arch.sie_block->ictl & (ICTL_ISKE | ICTL_SSKE | ICTL_RRBE)))
- return;
+ return rc;
- s390_enable_skey();
+ rc = s390_enable_skey();
trace_kvm_s390_skey_related_inst(vcpu);
vcpu->arch.sie_block->ictl &= ~(ICTL_ISKE | ICTL_SSKE | ICTL_RRBE);
+ return rc;
}
static int handle_skey(struct kvm_vcpu *vcpu)
{
- __skey_check_enable(vcpu);
+ int rc = __skey_check_enable(vcpu);
+ if (rc)
+ return rc;
vcpu->stat.instruction_storage_key++;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
- vcpu->arch.sie_block->gpsw.addr =
- __rewind_psw(vcpu->arch.sie_block->gpsw, 4);
+ kvm_s390_rewind_psw(vcpu, 4);
VCPU_EVENT(vcpu, 4, "%s", "retrying storage key operation");
return 0;
}
static int handle_ipte_interlock(struct kvm_vcpu *vcpu)
{
- psw_t *psw = &vcpu->arch.sie_block->gpsw;
-
vcpu->stat.instruction_ipte_interlock++;
- if (psw_bits(*psw).p)
+ if (psw_bits(vcpu->arch.sie_block->gpsw).p)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
wait_event(vcpu->kvm->arch.ipte_wq, !ipte_lock_held(vcpu));
- psw->addr = __rewind_psw(*psw, 4);
+ kvm_s390_rewind_psw(vcpu, 4);
VCPU_EVENT(vcpu, 4, "%s", "retrying ipte interlock operation");
return 0;
}
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
start = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
- if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
- if (kvm_s390_check_low_addr_protection(vcpu, start))
- return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
- }
+ start = kvm_s390_logical_to_effective(vcpu, start);
switch (vcpu->run->s.regs.gprs[reg1] & PFMF_FSC) {
case 0x00000000:
default:
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
}
+
+ if (vcpu->run->s.regs.gprs[reg1] & PFMF_CF) {
+ if (kvm_s390_check_low_addr_protection(vcpu, start))
+ return kvm_s390_inject_prog_irq(vcpu, &vcpu->arch.pgm);
+ }
+
while (start < end) {
unsigned long useraddr, abs_addr;
}
if (vcpu->run->s.regs.gprs[reg1] & PFMF_SK) {
- __skey_check_enable(vcpu);
+ int rc = __skey_check_enable(vcpu);
+
+ if (rc)
+ return rc;
if (set_guest_storage_key(current->mm, useraddr,
vcpu->run->s.regs.gprs[reg1] & PFMF_KEY,
vcpu->run->s.regs.gprs[reg1] & PFMF_NQ))
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
/* Rewind PSW to repeat the ESSA instruction */
- vcpu->arch.sie_block->gpsw.addr =
- __rewind_psw(vcpu->arch.sie_block->gpsw, 4);
+ kvm_s390_rewind_psw(vcpu, 4);
vcpu->arch.sie_block->cbrlo &= PAGE_MASK; /* reset nceo */
cbrlo = phys_to_virt(vcpu->arch.sie_block->cbrlo);
down_read(&gmap->mm->mmap_sem);
{
int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
- u32 val = 0;
- int reg, rc;
+ int reg, rc, nr_regs;
+ u32 ctl_array[16];
u64 ga;
vcpu->stat.instruction_lctl++;
VCPU_EVENT(vcpu, 5, "lctl r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
trace_kvm_s390_handle_lctl(vcpu, 0, reg1, reg3, ga);
+ nr_regs = ((reg3 - reg1) & 0xf) + 1;
+ rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32));
+ if (rc)
+ return kvm_s390_inject_prog_cond(vcpu, rc);
reg = reg1;
+ nr_regs = 0;
do {
- rc = read_guest(vcpu, ga, &val, sizeof(val));
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
vcpu->arch.sie_block->gcr[reg] &= 0xffffffff00000000ul;
- vcpu->arch.sie_block->gcr[reg] |= val;
- ga += 4;
+ vcpu->arch.sie_block->gcr[reg] |= ctl_array[nr_regs++];
if (reg == reg3)
break;
reg = (reg + 1) % 16;
} while (1);
-
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
return 0;
}
{
int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
+ int reg, rc, nr_regs;
+ u32 ctl_array[16];
u64 ga;
- u32 val;
- int reg, rc;
vcpu->stat.instruction_stctl++;
trace_kvm_s390_handle_stctl(vcpu, 0, reg1, reg3, ga);
reg = reg1;
+ nr_regs = 0;
do {
- val = vcpu->arch.sie_block->gcr[reg] & 0x00000000fffffffful;
- rc = write_guest(vcpu, ga, &val, sizeof(val));
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
- ga += 4;
+ ctl_array[nr_regs++] = vcpu->arch.sie_block->gcr[reg];
if (reg == reg3)
break;
reg = (reg + 1) % 16;
} while (1);
-
- return 0;
+ rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u32));
+ return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0;
}
static int handle_lctlg(struct kvm_vcpu *vcpu)
{
int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
- u64 ga, val;
- int reg, rc;
+ int reg, rc, nr_regs;
+ u64 ctl_array[16];
+ u64 ga;
vcpu->stat.instruction_lctlg++;
if (ga & 7)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- reg = reg1;
-
VCPU_EVENT(vcpu, 5, "lctlg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
trace_kvm_s390_handle_lctl(vcpu, 1, reg1, reg3, ga);
+ nr_regs = ((reg3 - reg1) & 0xf) + 1;
+ rc = read_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64));
+ if (rc)
+ return kvm_s390_inject_prog_cond(vcpu, rc);
+ reg = reg1;
+ nr_regs = 0;
do {
- rc = read_guest(vcpu, ga, &val, sizeof(val));
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
- vcpu->arch.sie_block->gcr[reg] = val;
- ga += 8;
+ vcpu->arch.sie_block->gcr[reg] = ctl_array[nr_regs++];
if (reg == reg3)
break;
reg = (reg + 1) % 16;
} while (1);
-
+ kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
return 0;
}
{
int reg1 = (vcpu->arch.sie_block->ipa & 0x00f0) >> 4;
int reg3 = vcpu->arch.sie_block->ipa & 0x000f;
- u64 ga, val;
- int reg, rc;
+ int reg, rc, nr_regs;
+ u64 ctl_array[16];
+ u64 ga;
vcpu->stat.instruction_stctg++;
if (ga & 7)
return kvm_s390_inject_program_int(vcpu, PGM_SPECIFICATION);
- reg = reg1;
-
VCPU_EVENT(vcpu, 5, "stctg r1:%x, r3:%x, addr:%llx", reg1, reg3, ga);
trace_kvm_s390_handle_stctl(vcpu, 1, reg1, reg3, ga);
+ reg = reg1;
+ nr_regs = 0;
do {
- val = vcpu->arch.sie_block->gcr[reg];
- rc = write_guest(vcpu, ga, &val, sizeof(val));
- if (rc)
- return kvm_s390_inject_prog_cond(vcpu, rc);
- ga += 8;
+ ctl_array[nr_regs++] = vcpu->arch.sie_block->gcr[reg];
if (reg == reg3)
break;
reg = (reg + 1) % 16;
} while (1);
-
- return 0;
+ rc = write_guest(vcpu, ga, ctl_array, nr_regs * sizeof(u64));
+ return rc ? kvm_s390_inject_prog_cond(vcpu, rc) : 0;
}
static const intercept_handler_t eb_handlers[256] = {
#include <linux/rcupdate.h>
#include <linux/slab.h>
#include <linux/swapops.h>
+#include <linux/ksm.h>
+#include <linux/mman.h>
#include <asm/pgtable.h>
#include <asm/pgalloc.h>
break;
/* Walk the process page table, lock and get pte pointer */
ptep = get_locked_pte(gmap->mm, addr, &ptl);
- if (unlikely(!ptep))
- continue;
+ VM_BUG_ON(!ptep);
/* Set notification bit in the pgste of the pte */
entry = *ptep;
if ((pte_val(entry) & (_PAGE_INVALID | _PAGE_PROTECT)) == 0) {
gaddr += PAGE_SIZE;
len -= PAGE_SIZE;
}
- spin_unlock(ptl);
+ pte_unmap_unlock(ptep, ptl);
}
up_read(&gmap->mm->mmap_sem);
return rc;
__free_page(page);
}
-static inline unsigned long page_table_reset_pte(struct mm_struct *mm, pmd_t *pmd,
- unsigned long addr, unsigned long end, bool init_skey)
-{
- pte_t *start_pte, *pte;
- spinlock_t *ptl;
- pgste_t pgste;
-
- start_pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
- pte = start_pte;
- do {
- pgste = pgste_get_lock(pte);
- pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
- if (init_skey) {
- unsigned long address;
-
- pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
- PGSTE_GR_BIT | PGSTE_GC_BIT);
-
- /* skip invalid and not writable pages */
- if (pte_val(*pte) & _PAGE_INVALID ||
- !(pte_val(*pte) & _PAGE_WRITE)) {
- pgste_set_unlock(pte, pgste);
- continue;
- }
-
- address = pte_val(*pte) & PAGE_MASK;
- page_set_storage_key(address, PAGE_DEFAULT_KEY, 1);
- }
- pgste_set_unlock(pte, pgste);
- } while (pte++, addr += PAGE_SIZE, addr != end);
- pte_unmap_unlock(start_pte, ptl);
-
- return addr;
-}
-
-static inline unsigned long page_table_reset_pmd(struct mm_struct *mm, pud_t *pud,
- unsigned long addr, unsigned long end, bool init_skey)
-{
- unsigned long next;
- pmd_t *pmd;
-
- pmd = pmd_offset(pud, addr);
- do {
- next = pmd_addr_end(addr, end);
- if (pmd_none_or_clear_bad(pmd))
- continue;
- next = page_table_reset_pte(mm, pmd, addr, next, init_skey);
- } while (pmd++, addr = next, addr != end);
-
- return addr;
-}
-
-static inline unsigned long page_table_reset_pud(struct mm_struct *mm, pgd_t *pgd,
- unsigned long addr, unsigned long end, bool init_skey)
-{
- unsigned long next;
- pud_t *pud;
-
- pud = pud_offset(pgd, addr);
- do {
- next = pud_addr_end(addr, end);
- if (pud_none_or_clear_bad(pud))
- continue;
- next = page_table_reset_pmd(mm, pud, addr, next, init_skey);
- } while (pud++, addr = next, addr != end);
-
- return addr;
-}
-
-void page_table_reset_pgste(struct mm_struct *mm, unsigned long start,
- unsigned long end, bool init_skey)
-{
- unsigned long addr, next;
- pgd_t *pgd;
-
- down_write(&mm->mmap_sem);
- if (init_skey && mm_use_skey(mm))
- goto out_up;
- addr = start;
- pgd = pgd_offset(mm, addr);
- do {
- next = pgd_addr_end(addr, end);
- if (pgd_none_or_clear_bad(pgd))
- continue;
- next = page_table_reset_pud(mm, pgd, addr, next, init_skey);
- } while (pgd++, addr = next, addr != end);
- if (init_skey)
- current->mm->context.use_skey = 1;
-out_up:
- up_write(&mm->mmap_sem);
-}
-EXPORT_SYMBOL(page_table_reset_pgste);
-
int set_guest_storage_key(struct mm_struct *mm, unsigned long addr,
unsigned long key, bool nq)
{
down_read(&mm->mmap_sem);
retry:
- ptep = get_locked_pte(current->mm, addr, &ptl);
+ ptep = get_locked_pte(mm, addr, &ptl);
if (unlikely(!ptep)) {
up_read(&mm->mmap_sem);
return -EFAULT;
}
EXPORT_SYMBOL(set_guest_storage_key);
+ unsigned long get_guest_storage_key(struct mm_struct *mm, unsigned long addr)
+ {
+ spinlock_t *ptl;
+ pgste_t pgste;
+ pte_t *ptep;
+ uint64_t physaddr;
+ unsigned long key = 0;
+
+ down_read(&mm->mmap_sem);
+ ptep = get_locked_pte(mm, addr, &ptl);
+ if (unlikely(!ptep)) {
+ up_read(&mm->mmap_sem);
+ return -EFAULT;
+ }
+ pgste = pgste_get_lock(ptep);
+
+ if (pte_val(*ptep) & _PAGE_INVALID) {
+ key |= (pgste_val(pgste) & PGSTE_ACC_BITS) >> 56;
+ key |= (pgste_val(pgste) & PGSTE_FP_BIT) >> 56;
+ key |= (pgste_val(pgste) & PGSTE_GR_BIT) >> 48;
+ key |= (pgste_val(pgste) & PGSTE_GC_BIT) >> 48;
+ } else {
+ physaddr = pte_val(*ptep) & PAGE_MASK;
+ key = page_get_storage_key(physaddr);
+
+ /* Reflect guest's logical view, not physical */
+ if (pgste_val(pgste) & PGSTE_GR_BIT)
+ key |= _PAGE_REFERENCED;
+ if (pgste_val(pgste) & PGSTE_GC_BIT)
+ key |= _PAGE_CHANGED;
+ }
+
+ pgste_set_unlock(ptep, pgste);
+ pte_unmap_unlock(ptep, ptl);
+ up_read(&mm->mmap_sem);
+ return key;
+ }
+ EXPORT_SYMBOL(get_guest_storage_key);
+
#else /* CONFIG_PGSTE */
static inline int page_table_with_pgste(struct page *page)
return NULL;
}
-void page_table_reset_pgste(struct mm_struct *mm, unsigned long start,
- unsigned long end, bool init_skey)
-{
-}
-
static inline void page_table_free_pgste(unsigned long *table)
{
}
* Enable storage key handling from now on and initialize the storage
* keys with the default key.
*/
-void s390_enable_skey(void)
+static int __s390_enable_skey(pte_t *pte, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
{
- page_table_reset_pgste(current->mm, 0, TASK_SIZE, true);
+ unsigned long ptev;
+ pgste_t pgste;
+
+ pgste = pgste_get_lock(pte);
+ /*
+ * Remove all zero page mappings,
+ * after establishing a policy to forbid zero page mappings
+ * following faults for that page will get fresh anonymous pages
+ */
+ if (is_zero_pfn(pte_pfn(*pte))) {
+ ptep_flush_direct(walk->mm, addr, pte);
+ pte_val(*pte) = _PAGE_INVALID;
+ }
+ /* Clear storage key */
+ pgste_val(pgste) &= ~(PGSTE_ACC_BITS | PGSTE_FP_BIT |
+ PGSTE_GR_BIT | PGSTE_GC_BIT);
+ ptev = pte_val(*pte);
+ if (!(ptev & _PAGE_INVALID) && (ptev & _PAGE_WRITE))
+ page_set_storage_key(ptev & PAGE_MASK, PAGE_DEFAULT_KEY, 1);
+ pgste_set_unlock(pte, pgste);
+ return 0;
+}
+
+int s390_enable_skey(void)
+{
+ struct mm_walk walk = { .pte_entry = __s390_enable_skey };
+ struct mm_struct *mm = current->mm;
+ struct vm_area_struct *vma;
+ int rc = 0;
+
+ down_write(&mm->mmap_sem);
+ if (mm_use_skey(mm))
+ goto out_up;
+
+ mm->context.use_skey = 1;
+ for (vma = mm->mmap; vma; vma = vma->vm_next) {
+ if (ksm_madvise(vma, vma->vm_start, vma->vm_end,
+ MADV_UNMERGEABLE, &vma->vm_flags)) {
+ mm->context.use_skey = 0;
+ rc = -ENOMEM;
+ goto out_up;
+ }
+ }
+ mm->def_flags &= ~VM_MERGEABLE;
+
+ walk.mm = mm;
+ walk_page_range(0, TASK_SIZE, &walk);
+
+out_up:
+ up_write(&mm->mmap_sem);
+ return rc;
}
EXPORT_SYMBOL_GPL(s390_enable_skey);
+/*
+ * Reset CMMA state, make all pages stable again.
+ */
+static int __s390_reset_cmma(pte_t *pte, unsigned long addr,
+ unsigned long next, struct mm_walk *walk)
+{
+ pgste_t pgste;
+
+ pgste = pgste_get_lock(pte);
+ pgste_val(pgste) &= ~_PGSTE_GPS_USAGE_MASK;
+ pgste_set_unlock(pte, pgste);
+ return 0;
+}
+
+void s390_reset_cmma(struct mm_struct *mm)
+{
+ struct mm_walk walk = { .pte_entry = __s390_reset_cmma };
+
+ down_write(&mm->mmap_sem);
+ walk.mm = mm;
+ walk_page_range(0, TASK_SIZE, &walk);
+ up_write(&mm->mmap_sem);
+}
+EXPORT_SYMBOL_GPL(s390_reset_cmma);
+
/*
* Test and reset if a guest page is dirty
*/
#define Prefix (3<<15) /* Instruction varies with 66/f2/f3 prefix */
#define RMExt (4<<15) /* Opcode extension in ModRM r/m if mod == 3 */
#define Escape (5<<15) /* Escape to coprocessor instruction */
+ #define InstrDual (6<<15) /* Alternate instruction decoding of mod == 3 */
#define Sse (1<<18) /* SSE Vector instruction */
/* Generic ModRM decode. */
#define ModRM (1<<19)
#define CheckPerm ((u64)1 << 49) /* Has valid check_perm field */
#define NoBigReal ((u64)1 << 50) /* No big real mode */
#define PrivUD ((u64)1 << 51) /* #UD instead of #GP on CPL > 0 */
+ #define NearBranch ((u64)1 << 52) /* Near branches */
+ #define No16 ((u64)1 << 53) /* No 16 bit operand */
#define DstXacc (DstAccLo | SrcAccHi | SrcWrite)
const struct group_dual *gdual;
const struct gprefix *gprefix;
const struct escape *esc;
+ const struct instr_dual *idual;
void (*fastop)(struct fastop *fake);
} u;
int (*check_perm)(struct x86_emulate_ctxt *ctxt);
struct opcode high[64];
};
+ struct instr_dual {
+ struct opcode mod012;
+ struct opcode mod3;
+ };
+
/* EFLAGS bit definitions. */
#define EFLG_ID (1<<21)
#define EFLG_VIP (1<<20)
ON64(FOP2E(op##q, rax, cl)) \
FOP_END
+ /* 2 operand, src and dest are reversed */
+ #define FASTOP2R(op, name) \
+ FOP_START(name) \
+ FOP2E(op##b, dl, al) \
+ FOP2E(op##w, dx, ax) \
+ FOP2E(op##l, edx, eax) \
+ ON64(FOP2E(op##q, rdx, rax)) \
+ FOP_END
+
#define FOP3E(op, dst, src, src2) \
FOP_ALIGN #op " %" #src2 ", %" #src ", %" #dst " \n\t" FOP_RET
}
static inline unsigned long
- register_address(struct x86_emulate_ctxt *ctxt, unsigned long reg)
+ register_address(struct x86_emulate_ctxt *ctxt, int reg)
{
- return address_mask(ctxt, reg);
+ return address_mask(ctxt, reg_read(ctxt, reg));
}
static void masked_increment(ulong *reg, ulong mask, int inc)
}
static inline void
- register_address_increment(struct x86_emulate_ctxt *ctxt, unsigned long *reg, int inc)
+ register_address_increment(struct x86_emulate_ctxt *ctxt, int reg, int inc)
{
ulong mask;
mask = ~0UL;
else
mask = ad_mask(ctxt);
- masked_increment(reg, mask, inc);
+ masked_increment(reg_rmw(ctxt, reg), mask, inc);
}
static void rsp_increment(struct x86_emulate_ctxt *ctxt, int inc)
return emulate_exception(ctxt, NM_VECTOR, 0, false);
}
- static inline int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
- int cs_l)
- {
- switch (ctxt->op_bytes) {
- case 2:
- ctxt->_eip = (u16)dst;
- break;
- case 4:
- ctxt->_eip = (u32)dst;
- break;
- #ifdef CONFIG_X86_64
- case 8:
- if ((cs_l && is_noncanonical_address(dst)) ||
- (!cs_l && (dst >> 32) != 0))
- return emulate_gp(ctxt, 0);
- ctxt->_eip = dst;
- break;
- #endif
- default:
- WARN(1, "unsupported eip assignment size\n");
- }
- return X86EMUL_CONTINUE;
- }
-
- static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
- {
- return assign_eip_far(ctxt, dst, ctxt->mode == X86EMUL_MODE_PROT64);
- }
-
- static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
- {
- return assign_eip_near(ctxt, ctxt->_eip + rel);
- }
-
static u16 get_segment_selector(struct x86_emulate_ctxt *ctxt, unsigned seg)
{
u16 selector;
return true;
}
- static int __linearize(struct x86_emulate_ctxt *ctxt,
- struct segmented_address addr,
- unsigned *max_size, unsigned size,
- bool write, bool fetch,
- ulong *linear)
+ static __always_inline int __linearize(struct x86_emulate_ctxt *ctxt,
+ struct segmented_address addr,
+ unsigned *max_size, unsigned size,
+ bool write, bool fetch,
+ enum x86emul_mode mode, ulong *linear)
{
struct desc_struct desc;
bool usable;
ulong la;
u32 lim;
u16 sel;
- unsigned cpl;
la = seg_base(ctxt, addr.seg) + addr.ea;
*max_size = 0;
- switch (ctxt->mode) {
+ switch (mode) {
case X86EMUL_MODE_PROT64:
- if (((signed long)la << 16) >> 16 != la)
- return emulate_gp(ctxt, 0);
+ if (is_noncanonical_address(la))
+ goto bad;
*max_size = min_t(u64, ~0u, (1ull << 48) - la);
if (size > *max_size)
if (!fetch && (desc.type & 8) && !(desc.type & 2))
goto bad;
lim = desc_limit_scaled(&desc);
- if ((ctxt->mode == X86EMUL_MODE_REAL) && !fetch &&
- (ctxt->d & NoBigReal)) {
- /* la is between zero and 0xffff */
- if (la > 0xffff)
- goto bad;
- *max_size = 0x10000 - la;
- } else if ((desc.type & 8) || !(desc.type & 4)) {
- /* expand-up segment */
- if (addr.ea > lim)
- goto bad;
- *max_size = min_t(u64, ~0u, (u64)lim + 1 - addr.ea);
- } else {
+ if (!(desc.type & 8) && (desc.type & 4)) {
/* expand-down segment */
if (addr.ea <= lim)
goto bad;
lim = desc.d ? 0xffffffff : 0xffff;
- if (addr.ea > lim)
- goto bad;
- *max_size = min_t(u64, ~0u, (u64)lim + 1 - addr.ea);
}
+ if (addr.ea > lim)
+ goto bad;
+ *max_size = min_t(u64, ~0u, (u64)lim + 1 - addr.ea);
if (size > *max_size)
goto bad;
- cpl = ctxt->ops->cpl(ctxt);
- if (!(desc.type & 8)) {
- /* data segment */
- if (cpl > desc.dpl)
- goto bad;
- } else if ((desc.type & 8) && !(desc.type & 4)) {
- /* nonconforming code segment */
- if (cpl != desc.dpl)
- goto bad;
- } else if ((desc.type & 8) && (desc.type & 4)) {
- /* conforming code segment */
- if (cpl < desc.dpl)
- goto bad;
- }
+ la &= (u32)-1;
break;
}
- if (fetch ? ctxt->mode != X86EMUL_MODE_PROT64 : ctxt->ad_bytes != 8)
- la &= (u32)-1;
if (insn_aligned(ctxt, size) && ((la & (size - 1)) != 0))
return emulate_gp(ctxt, 0);
*linear = la;
ulong *linear)
{
unsigned max_size;
- return __linearize(ctxt, addr, &max_size, size, write, false, linear);
+ return __linearize(ctxt, addr, &max_size, size, write, false,
+ ctxt->mode, linear);
+ }
+
+ static inline int assign_eip(struct x86_emulate_ctxt *ctxt, ulong dst,
+ enum x86emul_mode mode)
+ {
+ ulong linear;
+ int rc;
+ unsigned max_size;
+ struct segmented_address addr = { .seg = VCPU_SREG_CS,
+ .ea = dst };
+
+ if (ctxt->op_bytes != sizeof(unsigned long))
+ addr.ea = dst & ((1UL << (ctxt->op_bytes << 3)) - 1);
+ rc = __linearize(ctxt, addr, &max_size, 1, false, true, mode, &linear);
+ if (rc == X86EMUL_CONTINUE)
+ ctxt->_eip = addr.ea;
+ return rc;
+ }
+
+ static inline int assign_eip_near(struct x86_emulate_ctxt *ctxt, ulong dst)
+ {
+ return assign_eip(ctxt, dst, ctxt->mode);
}
+ static int assign_eip_far(struct x86_emulate_ctxt *ctxt, ulong dst,
+ const struct desc_struct *cs_desc)
+ {
+ enum x86emul_mode mode = ctxt->mode;
+
+ #ifdef CONFIG_X86_64
+ if (ctxt->mode >= X86EMUL_MODE_PROT32 && cs_desc->l) {
+ u64 efer = 0;
+
+ ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
+ if (efer & EFER_LMA)
+ mode = X86EMUL_MODE_PROT64;
+ }
+ #endif
+ if (mode == X86EMUL_MODE_PROT16 || mode == X86EMUL_MODE_PROT32)
+ mode = cs_desc->d ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16;
+ return assign_eip(ctxt, dst, mode);
+ }
+
+ static inline int jmp_rel(struct x86_emulate_ctxt *ctxt, int rel)
+ {
+ return assign_eip_near(ctxt, ctxt->_eip + rel);
+ }
static int segmented_read_std(struct x86_emulate_ctxt *ctxt,
struct segmented_address addr,
* boundary check itself. Instead, we use max_size to check
* against op_size.
*/
- rc = __linearize(ctxt, addr, &max_size, 0, false, true, &linear);
+ rc = __linearize(ctxt, addr, &max_size, 0, false, true, ctxt->mode,
+ &linear);
if (unlikely(rc != X86EMUL_CONTINUE))
return rc;
FASTOP2(xadd);
+ FASTOP2R(cmp, cmp_r);
+
static u8 test_cc(unsigned int condition, unsigned long flags)
{
u8 rc;
if (index_reg != 4)
modrm_ea += reg_read(ctxt, index_reg) << scale;
} else if ((ctxt->modrm_rm & 7) == 5 && ctxt->modrm_mod == 0) {
+ modrm_ea += insn_fetch(s32, ctxt);
if (ctxt->mode == X86EMUL_MODE_PROT64)
ctxt->rip_relative = 1;
} else {
adjust_modrm_seg(ctxt, base_reg);
}
switch (ctxt->modrm_mod) {
- case 0:
- if (ctxt->modrm_rm == 5)
- modrm_ea += insn_fetch(s32, ctxt);
- break;
case 1:
modrm_ea += insn_fetch(s8, ctxt);
break;
else
sv = (s64)ctxt->src.val & (s64)mask;
- ctxt->dst.addr.mem.ea += (sv >> 3);
+ ctxt->dst.addr.mem.ea = address_mask(ctxt,
+ ctxt->dst.addr.mem.ea + (sv >> 3));
}
/* only subword offset */
sizeof(base3), &ctxt->exception);
if (ret != X86EMUL_CONTINUE)
return ret;
+ if (is_noncanonical_address(get_desc_base(&seg_desc) |
+ ((u64)base3 << 32)))
+ return emulate_gp(ctxt, 0);
}
load:
ctxt->ops->set_segment(ctxt, selector, &seg_desc, base3, seg);
int seg = ctxt->src2.val;
ctxt->src.val = get_segment_selector(ctxt, seg);
+ if (ctxt->op_bytes == 4) {
+ rsp_increment(ctxt, -2);
+ ctxt->op_bytes = 2;
+ }
return em_push(ctxt);
}
static int em_pushf(struct x86_emulate_ctxt *ctxt)
{
- ctxt->src.val = (unsigned long)ctxt->eflags;
+ ctxt->src.val = (unsigned long)ctxt->eflags & ~EFLG_VM;
return em_push(ctxt);
}
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = assign_eip_far(ctxt, ctxt->src.val, new_desc.l);
+ rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
if (rc != X86EMUL_CONTINUE) {
WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
/* assigning eip failed; restore the old cs */
return rc;
}
- static int em_grp45(struct x86_emulate_ctxt *ctxt)
+ static int em_jmp_abs(struct x86_emulate_ctxt *ctxt)
{
- int rc = X86EMUL_CONTINUE;
+ return assign_eip_near(ctxt, ctxt->src.val);
+ }
- switch (ctxt->modrm_reg) {
- case 2: /* call near abs */ {
- long int old_eip;
- old_eip = ctxt->_eip;
- rc = assign_eip_near(ctxt, ctxt->src.val);
- if (rc != X86EMUL_CONTINUE)
- break;
- ctxt->src.val = old_eip;
- rc = em_push(ctxt);
- break;
- }
- case 4: /* jmp abs */
- rc = assign_eip_near(ctxt, ctxt->src.val);
- break;
- case 5: /* jmp far */
- rc = em_jmp_far(ctxt);
- break;
- case 6: /* push */
- rc = em_push(ctxt);
- break;
- }
+ static int em_call_near_abs(struct x86_emulate_ctxt *ctxt)
+ {
+ int rc;
+ long int old_eip;
+
+ old_eip = ctxt->_eip;
+ rc = assign_eip_near(ctxt, ctxt->src.val);
+ if (rc != X86EMUL_CONTINUE)
+ return rc;
+ ctxt->src.val = old_eip;
+ rc = em_push(ctxt);
return rc;
}
/* Outer-privilege level return is not implemented */
if (ctxt->mode >= X86EMUL_MODE_PROT16 && (cs & 3) > cpl)
return X86EMUL_UNHANDLEABLE;
- rc = __load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS, 0, false,
+ rc = __load_segment_descriptor(ctxt, (u16)cs, VCPU_SREG_CS, cpl, false,
&new_desc);
if (rc != X86EMUL_CONTINUE)
return rc;
- rc = assign_eip_far(ctxt, eip, new_desc.l);
+ rc = assign_eip_far(ctxt, eip, &new_desc);
if (rc != X86EMUL_CONTINUE) {
WARN_ON(ctxt->mode != X86EMUL_MODE_PROT64);
ops->set_segment(ctxt, old_cs, &old_desc, 0, VCPU_SREG_CS);
ops->get_msr(ctxt, MSR_SYSCALL_MASK, &msr_data);
ctxt->eflags &= ~msr_data;
+ ctxt->eflags |= EFLG_RESERVED_ONE_MASK;
#endif
} else {
/* legacy mode */
&& !vendor_intel(ctxt))
return emulate_ud(ctxt);
- /* XXX sysenter/sysexit have not been tested in 64bit mode.
- * Therefore, we inject an #UD.
- */
+ /* sysenter/sysexit have not been tested in 64bit mode. */
if (ctxt->mode == X86EMUL_MODE_PROT64)
- return emulate_ud(ctxt);
+ return X86EMUL_UNHANDLEABLE;
setup_syscalls_segments(ctxt, &cs, &ss);
if ((msr_data & 0xfffc) == 0x0)
return emulate_gp(ctxt, 0);
ss_sel = (u16)(msr_data + 24);
+ rcx = (u32)rcx;
+ rdx = (u32)rdx;
break;
case X86EMUL_MODE_PROT64:
cs_sel = (u16)(msr_data + 32);
ret = ops->read_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
&ctxt->exception);
if (ret != X86EMUL_CONTINUE)
- /* FIXME: need to provide precise fault address */
return ret;
save_state_to_tss16(ctxt, &tss_seg);
ret = ops->write_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg,
&ctxt->exception);
if (ret != X86EMUL_CONTINUE)
- /* FIXME: need to provide precise fault address */
return ret;
ret = ops->read_std(ctxt, new_tss_base, &tss_seg, sizeof tss_seg,
&ctxt->exception);
if (ret != X86EMUL_CONTINUE)
- /* FIXME: need to provide precise fault address */
return ret;
if (old_tss_sel != 0xffff) {
sizeof tss_seg.prev_task_link,
&ctxt->exception);
if (ret != X86EMUL_CONTINUE)
- /* FIXME: need to provide precise fault address */
return ret;
}
*
* 1. jmp/call/int to task gate: Check against DPL of the task gate
* 2. Exception/IRQ/iret: No check is performed
- * 3. jmp/call to TSS: Check against DPL of the TSS
+ * 3. jmp/call to TSS/task-gate: No check is performed since the
+ * hardware checks it before exiting.
*/
if (reason == TASK_SWITCH_GATE) {
if (idt_index != -1) {
if ((tss_selector & 3) > dpl || ops->cpl(ctxt) > dpl)
return emulate_gp(ctxt, (idt_index << 3) | 0x2);
}
- } else if (reason != TASK_SWITCH_IRET) {
- int dpl = next_tss_desc.dpl;
- if ((tss_selector & 3) > dpl || ops->cpl(ctxt) > dpl)
- return emulate_gp(ctxt, tss_selector);
}
-
desc_limit = desc_limit_scaled(&next_tss_desc);
if (!next_tss_desc.p ||
((desc_limit < 0x67 && (next_tss_desc.type & 8)) ||
{
int df = (ctxt->eflags & EFLG_DF) ? -op->count : op->count;
- register_address_increment(ctxt, reg_rmw(ctxt, reg), df * op->bytes);
- op->addr.mem.ea = register_address(ctxt, reg_read(ctxt, reg));
+ register_address_increment(ctxt, reg, df * op->bytes);
+ op->addr.mem.ea = register_address(ctxt, reg);
}
static int em_das(struct x86_emulate_ctxt *ctxt)
if (rc != X86EMUL_CONTINUE)
return X86EMUL_CONTINUE;
- rc = assign_eip_far(ctxt, ctxt->src.val, new_desc.l);
+ rc = assign_eip_far(ctxt, ctxt->src.val, &new_desc);
if (rc != X86EMUL_CONTINUE)
goto fail;
return emulate_ud(ctxt);
ctxt->dst.val = get_segment_selector(ctxt, ctxt->modrm_reg);
+ if (ctxt->dst.bytes == 4 && ctxt->dst.type == OP_MEM)
+ ctxt->dst.bytes = 2;
return X86EMUL_CONTINUE;
}
return emulate_store_desc_ptr(ctxt, ctxt->ops->get_idt);
}
- static int em_lgdt(struct x86_emulate_ctxt *ctxt)
+ static int em_lgdt_lidt(struct x86_emulate_ctxt *ctxt, bool lgdt)
{
struct desc_ptr desc_ptr;
int rc;
ctxt->op_bytes);
if (rc != X86EMUL_CONTINUE)
return rc;
- ctxt->ops->set_gdt(ctxt, &desc_ptr);
+ if (ctxt->mode == X86EMUL_MODE_PROT64 &&
+ is_noncanonical_address(desc_ptr.address))
+ return emulate_gp(ctxt, 0);
+ if (lgdt)
+ ctxt->ops->set_gdt(ctxt, &desc_ptr);
+ else
+ ctxt->ops->set_idt(ctxt, &desc_ptr);
/* Disable writeback. */
ctxt->dst.type = OP_NONE;
return X86EMUL_CONTINUE;
}
+ static int em_lgdt(struct x86_emulate_ctxt *ctxt)
+ {
+ return em_lgdt_lidt(ctxt, true);
+ }
+
static int em_vmmcall(struct x86_emulate_ctxt *ctxt)
{
int rc;
static int em_lidt(struct x86_emulate_ctxt *ctxt)
{
- struct desc_ptr desc_ptr;
- int rc;
-
- if (ctxt->mode == X86EMUL_MODE_PROT64)
- ctxt->op_bytes = 8;
- rc = read_descriptor(ctxt, ctxt->src.addr.mem,
- &desc_ptr.size, &desc_ptr.address,
- ctxt->op_bytes);
- if (rc != X86EMUL_CONTINUE)
- return rc;
- ctxt->ops->set_idt(ctxt, &desc_ptr);
- /* Disable writeback. */
- ctxt->dst.type = OP_NONE;
- return X86EMUL_CONTINUE;
+ return em_lgdt_lidt(ctxt, false);
}
static int em_smsw(struct x86_emulate_ctxt *ctxt)
{
int rc = X86EMUL_CONTINUE;
- register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX), -1);
+ register_address_increment(ctxt, VCPU_REGS_RCX, -1);
if ((address_mask(ctxt, reg_read(ctxt, VCPU_REGS_RCX)) != 0) &&
(ctxt->b == 0xe2 || test_cc(ctxt->b ^ 0x5, ctxt->eflags)))
rc = jmp_rel(ctxt, ctxt->src.val);
ctxt->ops->get_msr(ctxt, MSR_EFER, &efer);
if (efer & EFER_LMA)
- rsvd = CR3_L_MODE_RESERVED_BITS;
+ rsvd = CR3_L_MODE_RESERVED_BITS & ~CR3_PCID_INVD;
if (new_val & rsvd)
return emulate_gp(ctxt, 0);
if ((cr4 & X86_CR4_DE) && (dr == 4 || dr == 5))
return emulate_ud(ctxt);
- if (check_dr7_gd(ctxt))
+ if (check_dr7_gd(ctxt)) {
+ ulong dr6;
+
+ ctxt->ops->get_dr(ctxt, 6, &dr6);
+ dr6 &= ~15;
+ dr6 |= DR6_BD | DR6_RTM;
+ ctxt->ops->set_dr(ctxt, 6, dr6);
return emulate_db(ctxt);
+ }
return X86EMUL_CONTINUE;
}
#define EXT(_f, _e) { .flags = ((_f) | RMExt), .u.group = (_e) }
#define G(_f, _g) { .flags = ((_f) | Group | ModRM), .u.group = (_g) }
#define GD(_f, _g) { .flags = ((_f) | GroupDual | ModRM), .u.gdual = (_g) }
+ #define ID(_f, _i) { .flags = ((_f) | InstrDual | ModRM), .u.idual = (_i) }
#define E(_f, _e) { .flags = ((_f) | Escape | ModRM), .u.esc = (_e) }
#define I(_f, _e) { .flags = (_f), .u.execute = (_e) }
#define F(_f, _e) { .flags = (_f) | Fastop, .u.fastop = (_e) }
static const struct opcode group5[] = {
F(DstMem | SrcNone | Lock, em_inc),
F(DstMem | SrcNone | Lock, em_dec),
- I(SrcMem | Stack, em_grp45),
+ I(SrcMem | NearBranch, em_call_near_abs),
I(SrcMemFAddr | ImplicitOps | Stack, em_call_far),
- I(SrcMem | Stack, em_grp45),
- I(SrcMemFAddr | ImplicitOps, em_grp45),
- I(SrcMem | Stack, em_grp45), D(Undefined),
+ I(SrcMem | NearBranch, em_jmp_abs),
+ I(SrcMemFAddr | ImplicitOps, em_jmp_far),
+ I(SrcMem | Stack, em_push), D(Undefined),
};
static const struct opcode group6[] = {
I(Mmx, em_mov), I(Sse | Aligned, em_mov), N, I(Sse | Unaligned, em_mov),
};
+ static const struct instr_dual instr_dual_0f_2b = {
+ I(0, em_mov), N
+ };
+
static const struct gprefix pfx_0f_2b = {
- I(0, em_mov), I(0, em_mov), N, N,
+ ID(0, &instr_dual_0f_2b), ID(0, &instr_dual_0f_2b), N, N,
};
static const struct gprefix pfx_0f_28_0f_29 = {
N, N, N, N, N, N, N, N,
} };
+ static const struct instr_dual instr_dual_0f_c3 = {
+ I(DstMem | SrcReg | ModRM | No16 | Mov, em_mov), N
+ };
+
static const struct opcode opcode_table[256] = {
/* 0x00 - 0x07 */
F6ALU(Lock, em_add),
I2bvIP(DstDI | SrcDX | Mov | String | Unaligned, em_in, ins, check_perm_in), /* insb, insw/insd */
I2bvIP(SrcSI | DstDX | String, em_out, outs, check_perm_out), /* outsb, outsw/outsd */
/* 0x70 - 0x7F */
- X16(D(SrcImmByte)),
+ X16(D(SrcImmByte | NearBranch)),
/* 0x80 - 0x87 */
G(ByteOp | DstMem | SrcImm, group1),
G(DstMem | SrcImm, group1),
I2bv(DstAcc | SrcMem | Mov | MemAbs, em_mov),
I2bv(DstMem | SrcAcc | Mov | MemAbs | PageTable, em_mov),
I2bv(SrcSI | DstDI | Mov | String, em_mov),
- F2bv(SrcSI | DstDI | String | NoWrite, em_cmp),
+ F2bv(SrcSI | DstDI | String | NoWrite, em_cmp_r),
/* 0xA8 - 0xAF */
F2bv(DstAcc | SrcImm | NoWrite, em_test),
I2bv(SrcAcc | DstDI | Mov | String, em_mov),
I2bv(SrcSI | DstAcc | Mov | String, em_mov),
- F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp),
+ F2bv(SrcAcc | DstDI | String | NoWrite, em_cmp_r),
/* 0xB0 - 0xB7 */
X8(I(ByteOp | DstReg | SrcImm | Mov, em_mov)),
/* 0xB8 - 0xBF */
X8(I(DstReg | SrcImm64 | Mov, em_mov)),
/* 0xC0 - 0xC7 */
G(ByteOp | Src2ImmByte, group2), G(Src2ImmByte, group2),
- I(ImplicitOps | Stack | SrcImmU16, em_ret_near_imm),
- I(ImplicitOps | Stack, em_ret),
+ I(ImplicitOps | NearBranch | SrcImmU16, em_ret_near_imm),
+ I(ImplicitOps | NearBranch, em_ret),
I(DstReg | SrcMemFAddr | ModRM | No64 | Src2ES, em_lseg),
I(DstReg | SrcMemFAddr | ModRM | No64 | Src2DS, em_lseg),
G(ByteOp, group11), G(0, group11),
/* 0xD8 - 0xDF */
N, E(0, &escape_d9), N, E(0, &escape_db), N, E(0, &escape_dd), N, N,
/* 0xE0 - 0xE7 */
- X3(I(SrcImmByte, em_loop)),
- I(SrcImmByte, em_jcxz),
+ X3(I(SrcImmByte | NearBranch, em_loop)),
+ I(SrcImmByte | NearBranch, em_jcxz),
I2bvIP(SrcImmUByte | DstAcc, em_in, in, check_perm_in),
I2bvIP(SrcAcc | DstImmUByte, em_out, out, check_perm_out),
/* 0xE8 - 0xEF */
- I(SrcImm | Stack, em_call), D(SrcImm | ImplicitOps),
- I(SrcImmFAddr | No64, em_jmp_far), D(SrcImmByte | ImplicitOps),
+ I(SrcImm | NearBranch, em_call), D(SrcImm | ImplicitOps | NearBranch),
+ I(SrcImmFAddr | No64, em_jmp_far),
+ D(SrcImmByte | ImplicitOps | NearBranch),
I2bvIP(SrcDX | DstAcc, em_in, in, check_perm_in),
I2bvIP(SrcAcc | DstDX, em_out, out, check_perm_out),
/* 0xF0 - 0xF7 */
N, N, N, N,
N, N, N, GP(SrcReg | DstMem | ModRM | Mov, &pfx_0f_6f_0f_7f),
/* 0x80 - 0x8F */
- X16(D(SrcImm)),
+ X16(D(SrcImm | NearBranch)),
/* 0x90 - 0x9F */
X16(D(ByteOp | DstMem | SrcNone | ModRM| Mov)),
/* 0xA0 - 0xA7 */
D(DstReg | SrcMem8 | ModRM | Mov), D(DstReg | SrcMem16 | ModRM | Mov),
/* 0xC0 - 0xC7 */
F2bv(DstMem | SrcReg | ModRM | SrcWrite | Lock, em_xadd),
- N, D(DstMem | SrcReg | ModRM | Mov),
+ N, ID(0, &instr_dual_0f_c3),
N, N, N, GD(0, &group9),
/* 0xC8 - 0xCF */
X8(I(DstReg, em_bswap)),
N, N, N, N, N, N, N, N, N, N, N, N, N, N, N, N
};
+ static const struct instr_dual instr_dual_0f_38_f0 = {
+ I(DstReg | SrcMem | Mov, em_movbe), N
+ };
+
+ static const struct instr_dual instr_dual_0f_38_f1 = {
+ I(DstMem | SrcReg | Mov, em_movbe), N
+ };
+
static const struct gprefix three_byte_0f_38_f0 = {
- I(DstReg | SrcMem | Mov, em_movbe), N, N, N
+ ID(0, &instr_dual_0f_38_f0), N, N, N
};
static const struct gprefix three_byte_0f_38_f1 = {
- I(DstMem | SrcReg | Mov, em_movbe), N, N, N
+ ID(0, &instr_dual_0f_38_f1), N, N, N
};
/*
/* 0x80 - 0xef */
X16(N), X16(N), X16(N), X16(N), X16(N), X16(N), X16(N),
/* 0xf0 - 0xf1 */
- GP(EmulateOnUD | ModRM | Prefix, &three_byte_0f_38_f0),
- GP(EmulateOnUD | ModRM | Prefix, &three_byte_0f_38_f1),
+ GP(EmulateOnUD | ModRM, &three_byte_0f_38_f0),
+ GP(EmulateOnUD | ModRM, &three_byte_0f_38_f1),
/* 0xf2 - 0xff */
N, N, X4(N), X8(N)
};
op->type = OP_MEM;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
op->addr.mem.ea =
- register_address(ctxt, reg_read(ctxt, VCPU_REGS_RDI));
+ register_address(ctxt, VCPU_REGS_RDI);
op->addr.mem.seg = VCPU_SREG_ES;
op->val = 0;
op->count = 1;
fetch_register_operand(op);
break;
case OpCL:
+ op->type = OP_IMM;
op->bytes = 1;
op->val = reg_read(ctxt, VCPU_REGS_RCX) & 0xff;
break;
rc = decode_imm(ctxt, op, 1, true);
break;
case OpOne:
+ op->type = OP_IMM;
op->bytes = 1;
op->val = 1;
break;
op->type = OP_MEM;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
op->addr.mem.ea =
- register_address(ctxt, reg_read(ctxt, VCPU_REGS_RSI));
+ register_address(ctxt, VCPU_REGS_RSI);
op->addr.mem.seg = ctxt->seg_override;
op->val = 0;
op->count = 1;
op->type = OP_MEM;
op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes;
op->addr.mem.ea =
- register_address(ctxt,
+ address_mask(ctxt,
reg_read(ctxt, VCPU_REGS_RBX) +
(reg_read(ctxt, VCPU_REGS_RAX) & 0xff));
op->addr.mem.seg = ctxt->seg_override;
ctxt->memop.bytes = ctxt->op_bytes + 2;
goto mem_common;
case OpES:
+ op->type = OP_IMM;
op->val = VCPU_SREG_ES;
break;
case OpCS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_CS;
break;
case OpSS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_SS;
break;
case OpDS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_DS;
break;
case OpFS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_FS;
break;
case OpGS:
+ op->type = OP_IMM;
op->val = VCPU_SREG_GS;
break;
case OpImplicit:
/* vex-prefix instructions are not implemented */
if (ctxt->opcode_len == 1 && (ctxt->b == 0xc5 || ctxt->b == 0xc4) &&
- (mode == X86EMUL_MODE_PROT64 ||
- (mode >= X86EMUL_MODE_PROT16 && (ctxt->modrm & 0x80)))) {
+ (mode == X86EMUL_MODE_PROT64 || (ctxt->modrm & 0xc0) == 0xc0)) {
ctxt->d = NotImpl;
}
else
opcode = opcode.u.esc->op[(ctxt->modrm >> 3) & 7];
break;
+ case InstrDual:
+ if ((ctxt->modrm >> 6) == 3)
+ opcode = opcode.u.idual->mod3;
+ else
+ opcode = opcode.u.idual->mod012;
+ break;
default:
return EMULATION_FAILED;
}
return EMULATION_FAILED;
if (unlikely(ctxt->d &
- (NotImpl|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm))) {
+ (NotImpl|Stack|Op3264|Sse|Mmx|Intercept|CheckPerm|NearBranch|
+ No16))) {
/*
* These are copied unconditionally here, and checked unconditionally
* in x86_emulate_insn.
if (ctxt->d & NotImpl)
return EMULATION_FAILED;
- if (mode == X86EMUL_MODE_PROT64 && (ctxt->d & Stack))
- ctxt->op_bytes = 8;
+ if (mode == X86EMUL_MODE_PROT64) {
+ if (ctxt->op_bytes == 4 && (ctxt->d & Stack))
+ ctxt->op_bytes = 8;
+ else if (ctxt->d & NearBranch)
+ ctxt->op_bytes = 8;
+ }
if (ctxt->d & Op3264) {
if (mode == X86EMUL_MODE_PROT64)
ctxt->op_bytes = 4;
}
+ if ((ctxt->d & No16) && ctxt->op_bytes == 2)
+ ctxt->op_bytes = 4;
+
if (ctxt->d & Sse)
ctxt->op_bytes = 16;
else if (ctxt->d & Mmx)
rc = decode_operand(ctxt, &ctxt->dst, (ctxt->d >> DstShift) & OpMask);
if (ctxt->rip_relative)
- ctxt->memopp->addr.mem.ea += ctxt->_eip;
+ ctxt->memopp->addr.mem.ea = address_mask(ctxt,
+ ctxt->memopp->addr.mem.ea + ctxt->_eip);
done:
return (rc != X86EMUL_CONTINUE) ? EMULATION_FAILED : EMULATION_OK;
goto done;
}
+ /* Instruction can only be executed in protected mode */
+ if ((ctxt->d & Prot) && ctxt->mode < X86EMUL_MODE_PROT16) {
+ rc = emulate_ud(ctxt);
+ goto done;
+ }
+
/* Privileged instruction can be executed only in CPL=0 */
if ((ctxt->d & Priv) && ops->cpl(ctxt)) {
if (ctxt->d & PrivUD)
goto done;
}
- /* Instruction can only be executed in protected mode */
- if ((ctxt->d & Prot) && ctxt->mode < X86EMUL_MODE_PROT16) {
- rc = emulate_ud(ctxt);
- goto done;
- }
-
/* Do instruction specific permission checks */
if (ctxt->d & CheckPerm) {
rc = ctxt->check_perm(ctxt);
count = ctxt->src.count;
else
count = ctxt->dst.count;
- register_address_increment(ctxt, reg_rmw(ctxt, VCPU_REGS_RCX),
- -count);
+ register_address_increment(ctxt, VCPU_REGS_RCX, -count);
if (!string_insn_completed(ctxt)) {
/*
ctxt->dst.val = (ctxt->src.bytes == 1) ? (s8) ctxt->src.val :
(s16) ctxt->src.val;
break;
- case 0xc3: /* movnti */
- ctxt->dst.bytes = ctxt->op_bytes;
- ctxt->dst.val = (ctxt->op_bytes == 8) ? (u64) ctxt->src.val :
- (u32) ctxt->src.val;
- break;
default:
goto cannot_emulate;
}
#define ACCESS_WRITE_VALUE (3 << 1)
#define ACCESS_WRITE_MASK(x) ((x) & (3 << 1))
+ static int vgic_init(struct kvm *kvm);
static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu);
static void vgic_retire_lr(int lr_nr, int irq, struct kvm_vcpu *vcpu);
static void vgic_update_state(struct kvm *kvm);
}
}
- static bool vgic_update_irq_pending(struct kvm *kvm, int cpuid,
+ static int vgic_update_irq_pending(struct kvm *kvm, int cpuid,
unsigned int irq_num, bool level)
{
struct vgic_dist *dist = &kvm->arch.vgic;
vgic_dist_irq_clear_level(vcpu, irq_num);
if (!vgic_dist_irq_soft_pend(vcpu, irq_num))
vgic_dist_irq_clear_pending(vcpu, irq_num);
- } else {
- vgic_dist_irq_clear_pending(vcpu, irq_num);
}
+
+ ret = false;
+ goto out;
}
enabled = vgic_irq_is_enabled(vcpu, irq_num);
out:
spin_unlock(&dist->lock);
- return ret;
+ return ret ? cpuid : -EINVAL;
}
/**
int kvm_vgic_inject_irq(struct kvm *kvm, int cpuid, unsigned int irq_num,
bool level)
{
- if (likely(vgic_initialized(kvm)) &&
- vgic_update_irq_pending(kvm, cpuid, irq_num, level))
- vgic_kick_vcpus(kvm);
+ int ret = 0;
+ int vcpu_id;
- return 0;
+ if (unlikely(!vgic_initialized(kvm))) {
+ mutex_lock(&kvm->lock);
+ ret = vgic_init(kvm);
+ mutex_unlock(&kvm->lock);
+
+ if (ret)
+ goto out;
+ }
+
+ vcpu_id = vgic_update_irq_pending(kvm, cpuid, irq_num, level);
+ if (vcpu_id >= 0) {
+ /* kick the specified vcpu */
+ kvm_vcpu_kick(kvm_get_vcpu(kvm, vcpu_id));
+ }
+
+ out:
+ return ret;
}
static irqreturn_t vgic_maintenance_handler(int irq, void *data)
int sz = (nr_irqs - VGIC_NR_PRIVATE_IRQS) / 8;
vgic_cpu->pending_shared = kzalloc(sz, GFP_KERNEL);
- vgic_cpu->vgic_irq_lr_map = kzalloc(nr_irqs, GFP_KERNEL);
+ vgic_cpu->vgic_irq_lr_map = kmalloc(nr_irqs, GFP_KERNEL);
if (!vgic_cpu->pending_shared || !vgic_cpu->vgic_irq_lr_map) {
kvm_vgic_vcpu_destroy(vcpu);
return -ENOMEM;
}
- return 0;
- }
-
- /**
- * kvm_vgic_vcpu_init - Initialize per-vcpu VGIC state
- * @vcpu: pointer to the vcpu struct
- *
- * Initialize the vgic_cpu struct and vgic_dist struct fields pertaining to
- * this vcpu and enable the VGIC for this VCPU
- */
- static void kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu)
- {
- struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu;
- struct vgic_dist *dist = &vcpu->kvm->arch.vgic;
- int i;
-
- for (i = 0; i < dist->nr_irqs; i++) {
- if (i < VGIC_NR_PPIS)
- vgic_bitmap_set_irq_val(&dist->irq_enabled,
- vcpu->vcpu_id, i, 1);
- if (i < VGIC_NR_PRIVATE_IRQS)
- vgic_bitmap_set_irq_val(&dist->irq_cfg,
- vcpu->vcpu_id, i, VGIC_CFG_EDGE);
-
- vgic_cpu->vgic_irq_lr_map[i] = LR_EMPTY;
- }
+ memset(vgic_cpu->vgic_irq_lr_map, LR_EMPTY, nr_irqs);
/*
* Store the number of LRs per vcpu, so we don't have to go
*/
vgic_cpu->nr_lr = vgic->nr_lr;
- vgic_enable(vcpu);
+ return 0;
}
void kvm_vgic_destroy(struct kvm *kvm)
dist->irq_spi_cpu = NULL;
dist->irq_spi_target = NULL;
dist->irq_pending_on_cpu = NULL;
+ dist->nr_cpus = 0;
}
/*
* Allocate and initialize the various data structures. Must be called
* with kvm->lock held!
*/
- static int vgic_init_maps(struct kvm *kvm)
+ static int vgic_init(struct kvm *kvm)
{
struct vgic_dist *dist = &kvm->arch.vgic;
struct kvm_vcpu *vcpu;
int nr_cpus, nr_irqs;
- int ret, i;
+ int ret, i, vcpu_id;
- if (dist->nr_cpus) /* Already allocated */
+ if (vgic_initialized(kvm))
return 0;
nr_cpus = dist->nr_cpus = atomic_read(&kvm->online_vcpus);
if (ret)
goto out;
- kvm_for_each_vcpu(i, vcpu, kvm) {
+ for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i += 4)
+ vgic_set_target_reg(kvm, 0, i);
+
+ kvm_for_each_vcpu(vcpu_id, vcpu, kvm) {
ret = vgic_vcpu_init_maps(vcpu, nr_irqs);
if (ret) {
kvm_err("VGIC: Failed to allocate vcpu memory\n");
break;
}
- }
- for (i = VGIC_NR_PRIVATE_IRQS; i < dist->nr_irqs; i += 4)
- vgic_set_target_reg(kvm, 0, i);
+ for (i = 0; i < dist->nr_irqs; i++) {
+ if (i < VGIC_NR_PPIS)
+ vgic_bitmap_set_irq_val(&dist->irq_enabled,
+ vcpu->vcpu_id, i, 1);
+ if (i < VGIC_NR_PRIVATE_IRQS)
+ vgic_bitmap_set_irq_val(&dist->irq_cfg,
+ vcpu->vcpu_id, i,
+ VGIC_CFG_EDGE);
+ }
+
+ vgic_enable(vcpu);
+ }
out:
if (ret)
}
/**
- * kvm_vgic_init - Initialize global VGIC state before running any VCPUs
+ * kvm_vgic_map_resources - Configure global VGIC state before running any VCPUs
* @kvm: pointer to the kvm struct
*
* Map the virtual CPU interface into the VM before running any VCPUs. We
* can't do this at creation time, because user space must first set the
- * virtual CPU interface address in the guest physical address space. Also
- * initialize the ITARGETSRn regs to 0 on the emulated distributor.
+ * virtual CPU interface address in the guest physical address space.
*/
- int kvm_vgic_init(struct kvm *kvm)
+ int kvm_vgic_map_resources(struct kvm *kvm)
{
- struct kvm_vcpu *vcpu;
- int ret = 0, i;
+ int ret = 0;
if (!irqchip_in_kernel(kvm))
return 0;
mutex_lock(&kvm->lock);
- if (vgic_initialized(kvm))
+ if (vgic_ready(kvm))
goto out;
if (IS_VGIC_ADDR_UNDEF(kvm->arch.vgic.vgic_dist_base) ||
goto out;
}
- ret = vgic_init_maps(kvm);
+ /*
+ * Initialize the vgic if this hasn't already been done on demand by
+ * accessing the vgic state from userspace.
+ */
+ ret = vgic_init(kvm);
if (ret) {
kvm_err("Unable to allocate maps\n");
goto out;
goto out;
}
- kvm_for_each_vcpu(i, vcpu, kvm)
- kvm_vgic_vcpu_init(vcpu);
-
kvm->arch.vgic.ready = true;
out:
if (ret)
int kvm_vgic_create(struct kvm *kvm)
{
- int i, vcpu_lock_idx = -1, ret = 0;
+ int i, vcpu_lock_idx = -1, ret;
struct kvm_vcpu *vcpu;
mutex_lock(&kvm->lock);
* vcpu->mutex. By grabbing the vcpu->mutex of all VCPUs we ensure
* that no other VCPUs are run while we create the vgic.
*/
+ ret = -EBUSY;
kvm_for_each_vcpu(i, vcpu, kvm) {
if (!mutex_trylock(&vcpu->mutex))
goto out_unlock;
}
kvm_for_each_vcpu(i, vcpu, kvm) {
- if (vcpu->arch.has_run_once) {
- ret = -EBUSY;
+ if (vcpu->arch.has_run_once)
goto out_unlock;
- }
}
+ ret = 0;
spin_lock_init(&kvm->arch.vgic.lock);
kvm->arch.vgic.in_kernel = true;
mutex_lock(&dev->kvm->lock);
- ret = vgic_init_maps(dev->kvm);
+ ret = vgic_init(dev->kvm);
if (ret)
goto out;
mutex_lock(&dev->kvm->lock);
- if (vgic_initialized(dev->kvm) || dev->kvm->arch.vgic.nr_irqs)
+ if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_irqs)
ret = -EBUSY;
else
dev->kvm->arch.vgic.nr_irqs = val;