S: Maintained
F: drivers/counter/104-quad-8.c
+ACCES IDIO-16 GPIO LIBRARY
+S: Maintained
+F: drivers/gpio/gpio-idio-16.c
+F: drivers/gpio/gpio-idio-16.h
+
ACCES PCI-IDIO-16 GPIO DRIVER
F: Documentation/devicetree/bindings/media/allwinner,sun4i-a10-csi.yaml
F: drivers/media/platform/sunxi/sun4i-csi/
+ALLWINNER A31 CSI DRIVER
+S: Maintained
+T: git git://linuxtv.org/media_tree.git
+F: Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml
+F: drivers/media/platform/sunxi/sun6i-csi/
+
+ALLWINNER A31 ISP DRIVER
+S: Maintained
+T: git git://linuxtv.org/media_tree.git
+F: Documentation/devicetree/bindings/media/allwinner,sun6i-a31-isp.yaml
+F: drivers/staging/media/sunxi/sun6i-isp/
+F: drivers/staging/media/sunxi/sun6i-isp/uapi/sun6i-isp-config.h
+
ALLWINNER A31 MIPI CSI-2 BRIDGE DRIVER
F: Documentation/hid/amd-sfh*
F: drivers/hid/amd-sfh-hid/
+AMLOGIC DDR PMU DRIVER
+S: Supported
+W: http://www.amlogic.com
+F: Documentation/admin-guide/perf/meson-ddr-pmu.rst
+F: Documentation/devicetree/bindings/perf/amlogic,g12-ddr-pmu.yaml
+F: drivers/perf/amlogic/
+F: include/soc/amlogic/
+
AMPHION VPU CODEC V4L2 DRIVER
S: Maintained
-F: Documentation/devicetree/bindings/memory-controllers/arm,pl353-smc.yaml
+F: Documentation/devicetree/bindings/memory-controllers/arm,pl35x-smc.yaml
F: drivers/memory/pl353-smc.c
ARM PRIMECELL CLCD PL110 DRIVER
F: Documentation/devicetree/bindings/arm/apple.yaml
F: Documentation/devicetree/bindings/arm/apple/*
F: Documentation/devicetree/bindings/clock/apple,nco.yaml
+F: Documentation/devicetree/bindings/cpufreq/apple,cluster-cpufreq.yaml
F: Documentation/devicetree/bindings/dma/apple,admac.yaml
F: Documentation/devicetree/bindings/i2c/apple,i2c.yaml
F: Documentation/devicetree/bindings/interrupt-controller/apple,*
F: Documentation/devicetree/bindings/iommu/apple,dart.yaml
F: Documentation/devicetree/bindings/iommu/apple,sart.yaml
F: Documentation/devicetree/bindings/mailbox/apple,mailbox.yaml
+F: Documentation/devicetree/bindings/net/bluetooth/brcm,bcm4377-bluetooth.yaml
F: Documentation/devicetree/bindings/nvme/apple,nvme-ans.yaml
F: Documentation/devicetree/bindings/nvmem/apple,efuses.yaml
F: Documentation/devicetree/bindings/pci/apple,pcie.yaml
F: Documentation/devicetree/bindings/power/apple*
F: Documentation/devicetree/bindings/watchdog/apple,wdt.yaml
F: arch/arm64/boot/dts/apple/
+F: drivers/bluetooth/hci_bcm4377.c
F: drivers/clk/clk-apple-nco.c
+F: drivers/cpufreq/apple-soc-cpufreq.c
F: drivers/dma/apple-admac.c
F: drivers/i2c/busses/i2c-pasemi-core.c
F: drivers/i2c/busses/i2c-pasemi-platform.c
S: Supported
W: http://www.hisilicon.com
-T: git git://github.com/hisilicon/linux-hisi.git
+T: git https://github.com/hisilicon/linux-hisi.git
F: arch/arm/boot/dts/hi3*
F: arch/arm/boot/dts/hip*
F: arch/arm/boot/dts/hisi*
F: drivers/crypto/ixp4xx_crypto.c
F: drivers/gpio/gpio-ixp4xx.c
F: drivers/irqchip/irq-ixp4xx.c
-F: include/linux/irqchip/irq-ixp4xx.h
-F: include/linux/platform_data/timer-ixp4xx.h
ARM/INTEL KEEMBAY ARCHITECTURE
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gclement/mvebu.git
+F: Documentation/devicetree/bindings/arm/marvell/marvell,dove.txt
+F: Documentation/devicetree/bindings/arm/marvell/marvell,orion5x.txt
F: Documentation/devicetree/bindings/soc/dove/
F: arch/arm/boot/dts/dove*
F: arch/arm/boot/dts/orion5x*
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/gclement/mvebu.git
+F: Documentation/devicetree/bindings/arm/marvell/
F: arch/arm/boot/dts/armada*
F: arch/arm/boot/dts/kirkwood*
F: arch/arm/configs/mvebu_*_defconfig
S: Supported
T: git git://github.com/microchip-ung/linux-upstream.git
F: arch/arm64/boot/dts/microchip/
+F: drivers/net/ethernet/microchip/vcap/
F: drivers/pinctrl/pinctrl-microchip-sgpio.c
N: sparx5
ARM/QUALCOMM SUPPORT
-R: Konrad Dybcio <konrad.dybcio@somainline.org>
+R: Konrad Dybcio <konrad.dybcio@linaro.org>
S: Maintained
T: git git://git.kernel.org/pub/scm/linux/kernel/git/qcom/linux.git
F: arch/arm/mach-realtek/
F: arch/arm64/boot/dts/realtek/
-ARM/RENESAS ARCHITECTURE
+ARM/RISC-V/RENESAS ARCHITECTURE
Q: http://patchwork.kernel.org/project/linux-renesas-soc/list/
C: irc://irc.libera.chat/renesas-soc
T: git git://git.kernel.org/pub/scm/linux/kernel/git/geert/renesas-devel.git next
-F: Documentation/devicetree/bindings/arm/renesas.yaml
F: Documentation/devicetree/bindings/hwinfo/renesas,prr.yaml
F: Documentation/devicetree/bindings/soc/renesas/
F: arch/arm/boot/dts/emev2*
F: arch/arm/include/debug/renesas-scif.S
F: arch/arm/mach-shmobile/
F: arch/arm64/boot/dts/renesas/
+F: arch/riscv/boot/dts/renesas/
F: drivers/soc/renesas/
F: include/linux/soc/renesas/
S: Supported
W: http://ceph.com/
-T: git git://github.com/ceph/ceph-client.git
+T: git https://github.com/ceph/ceph-client.git
F: include/linux/ceph/
F: include/linux/crush/
F: net/ceph/
S: Supported
W: http://ceph.com/
-T: git git://github.com/ceph/ceph-client.git
+T: git https://github.com/ceph/ceph-client.git
F: Documentation/filesystems/ceph.rst
F: fs/ceph/
CHROMEOS EC CODEC DRIVER
-M: Tzung-Bi Shih <tzungbi@google.com>
+M: Tzung-Bi Shih <tzungbi@kernel.org>
S: Maintained
F: drivers/platform/chrome/cros_usbpd_notify.c
F: include/linux/platform_data/cros_usbpd_notify.h
+CHROMEOS HPS DRIVER
+S: Maintained
+F: drivers/platform/chrome/cros_hps_i2c.c
+
CHRONTEL CH7322 CEC DRIVER
S: Maintained
S: Maintained
F: sound/pci/cs5535audio/
-CSI DRIVERS FOR ALLWINNER V3s
-S: Maintained
-T: git git://linuxtv.org/media_tree.git
-F: Documentation/devicetree/bindings/media/allwinner,sun6i-a31-csi.yaml
-F: drivers/media/platform/sunxi/sun6i-csi/
-
CTU CAN FD DRIVER
CXGB4 CRYPTO DRIVER (chcr)
S: Supported
W: http://www.chelsio.com
CXGB4 INLINE CRYPTO DRIVER
S: Supported
W: http://www.chelsio.com
S: Maintained
F: drivers/platform/x86/dell/dell-wmi-descriptor.c
+DELL WMI DDV DRIVER
+S: Maintained
+F: Documentation/ABI/testing/debugfs-dell-wmi-ddv
+F: Documentation/ABI/testing/sysfs-platform-dell-wmi-ddv
+F: drivers/platform/x86/dell/dell-wmi-ddv.c
+
DELL WMI SYSMAN DRIVER
F: include/uapi/linux/devlink.h
F: net/core/devlink.c
-DH ELECTRONICS IMX6 DHCOM BOARD SUPPORT
+DH ELECTRONICS IMX6 DHCOM/DHCOR BOARD SUPPORT
S: Maintained
F: arch/arm/boot/dts/imx6*-dhcom-*
+F: arch/arm/boot/dts/imx6*-dhcor-*
DH ELECTRONICS STM32MP1 DHCOM/DHCOR BOARD SUPPORT
F: drivers/net/ethernet/freescale/dpaa2/Makefile
F: drivers/net/ethernet/freescale/dpaa2/dpaa2-eth*
F: drivers/net/ethernet/freescale/dpaa2/dpaa2-mac*
+F: drivers/net/ethernet/freescale/dpaa2/dpaa2-xsk*
F: drivers/net/ethernet/freescale/dpaa2/dpkg.h
F: drivers/net/ethernet/freescale/dpaa2/dpmac*
F: drivers/net/ethernet/freescale/dpaa2/dpni*
F: drivers/gpu/drm/i810/
F: include/uapi/drm/i810_drm.h
+DRM DRIVER FOR JADARD JD9365DA-H3 MIPI-DSI LCD PANELS
+S: Maintained
+F: Documentation/devicetree/bindings/display/panel/jadard,jd9365da-h3.yaml
+F: drivers/gpu/drm/panel/panel-jadard-jd9365da-h3.c
+
DRM DRIVER FOR LOGICVC DISPLAY CONTROLLER
S: Supported
S: Maintained
T: git git://anongit.freedesktop.org/drm/drm-misc
F: drivers/gpu/drm/drm_aperture.c
+F: drivers/gpu/drm/tiny/ofdrm.c
F: drivers/gpu/drm/tiny/simpledrm.c
F: drivers/video/aperture.c
+F: drivers/video/nomodeset.c
F: include/drm/drm_aperture.h
F: include/linux/aperture.h
+F: include/video/nomodeset.h
DRM DRIVER FOR SIS VIDEO CARDS
S: Orphan / Obsolete
F: include/linux/vga*
F: include/uapi/drm/drm*
+DRM COMPUTE ACCELERATORS DRIVERS AND FRAMEWORK
+S: Maintained
+C: irc://irc.oftc.net/dri-devel
+T: git https://git.kernel.org/pub/scm/linux/kernel/git/ogabbay/accel.git
+F: Documentation/accel/
+F: drivers/accel/
+
DRM DRIVERS FOR ALLWINNER A10
F: include/drm/ttm/
DRM GPU SCHEDULER
-M: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
+M: Luben Tuikov <luben.tuikov@amd.com>
S: Maintained
T: git git://anongit.freedesktop.org/drm/drm-misc
EDAC-CORE
S: Supported
F: drivers/edac/pnd2_edac.[ch]
EDAC-QCOM
S: Maintained
S: Maintained
+F: Documentation/networking/devlink/etas_es58x.rst
F: drivers/net/can/usb/etas_es58x/
ETHERNET BRIDGE
F: arch/*/include/asm/efi.h
F: arch/*/kernel/efi.c
F: arch/arm/boot/compressed/efi-header.S
-F: arch/arm64/kernel/efi-entry.S
F: arch/x86/platform/efi/
F: drivers/firmware/efi/
F: include/linux/efi*.h
S: Maintained
W: https://f2fs.wiki.kernel.org/
+B: https://bugzilla.kernel.org/enter_bug.cgi?product=File%20System&component=f2fs
T: git git://git.kernel.org/pub/scm/linux/kernel/git/jaegeuk/f2fs.git
F: Documentation/ABI/testing/sysfs-fs-f2fs
F: Documentation/filesystems/f2fs.rst
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening
F: include/linux/fortify-string.h
F: lib/fortify_kunit.c
+F: lib/memcpy_kunit.c
+F: lib/strscpy_kunit.c
F: lib/test_fortify/*
F: scripts/test_fortify.sh
K: \b__NO_FORTIFY\b
F: drivers/i2c/busses/i2c-cpm.c
FREESCALE IMX / MXC FEC DRIVER
S: Maintained
F: Documentation/devicetree/bindings/net/fsl,fec.yaml
F: include/uapi/asm-generic/
GENERIC PHY FRAMEWORK
S: Supported
Q: https://patchwork.kernel.org/project/linux-phy/list/
S: Maintained
+F: Documentation/devicetree/bindings/leds/irled/gpio-ir-tx.yaml
F: drivers/media/rc/gpio-ir-tx.c
GPIO MOCKUP DRIVER
F: Documentation/scsi/hptiop.rst
F: drivers/scsi/hptiop.c
+HIMAX HX83112B TOUCHSCREEN SUPPORT
+S: Maintained
+F: Documentation/devicetree/bindings/input/touchscreen/himax,hx83112b.yaml
+F: drivers/input/touchscreen/himax_hx83112b.c
+
HIPPI
S: Maintained
+F: Documentation/devicetree/bindings/gpio/hisilicon,ascend910-gpio.yaml
F: drivers/gpio/gpio-hisi.c
HISILICON HIGH PERFORMANCE RSA ENGINE DRIVER (HPRE)
HISILICON PMU DRIVER
-M: Qi Liu <liuqi115@huawei.com>
+M: Jonathan Cameron <jonathan.cameron@huawei.com>
S: Supported
W: http://www.hisilicon.com
F: Documentation/admin-guide/perf/hisi-pcie-pmu.rst
F: drivers/infiniband/hw/hns/
HISILICON SAS Controller
-M: John Garry <john.garry@huawei.com>
+M: Xiang Chen <chenxiang66@hisilicon.com>
S: Supported
W: http://www.hisilicon.com
F: Documentation/devicetree/bindings/scsi/hisilicon-sas.txt
F: drivers/crypto/hisilicon/trng/trng.c
HISILICON V3XX SPI NOR FLASH Controller Driver
-M: John Garry <john.garry@huawei.com>
+M: Jay Fang <f.fangjian@huawei.com>
S: Maintained
W: http://www.hisilicon.com
F: drivers/spi/spi-hisi-sfc-v3xx.c
HP COMPAQ TC1100 TABLET WMI EXTRAS DRIVER
S: Orphan
-F: drivers/platform/x86/tc1100-wmi.c
+F: drivers/platform/x86/hp/tc1100-wmi.c
HPET: High Precision Event Timers driver
F: drivers/iio/humidity/hts221*
HUAWEI ETHERNET DRIVER
-S: Orphan
+S: Maintained
F: Documentation/networking/device_drivers/ethernet/huawei/hinic.rst
F: drivers/net/ethernet/huawei/hinic/
HUGETLB SUBSYSTEM
S: Maintained
F: Documentation/ABI/testing/sysfs-kernel-mm-hugepages
Hyper-V/Azure CORE AND DRIVERS
F: include/asm-generic/mshyperv.h
F: include/clocksource/hyperv_timer.h
F: include/linux/hyperv.h
+F: include/net/mana
F: include/uapi/linux/hyperv.h
F: net/vmw_vsock/hyperv_transport.c
F: tools/hv/
F: drivers/i3c/master/i3c-master-cdns.c
I3C DRIVER FOR SYNOPSYS DESIGNWARE
-S: Maintained
+S: Orphan
F: Documentation/devicetree/bindings/i3c/snps,dw-i3c-master.yaml
F: drivers/i3c/master/dw*
F: drivers/hwmon/ina2xx.c
F: include/linux/platform_data/ina2xx.h
+INDEX OF FURTHER KERNEL DOCUMENTATION
+S: Maintained
+F: Documentation/process/kernel-docs.rst
+
INDUSTRY PACK SUBSYSTEM (IPACK)
F: include/rdma/
F: include/trace/events/ib_mad.h
F: include/trace/events/ib_umad.h
+F: include/trace/misc/rdma.h
F: include/uapi/linux/if_infiniband.h
F: include/uapi/rdma/
F: samples/bpf/ibumad_kern.c
B: https://gitlab.freedesktop.org/drm/intel/-/wikis/How-to-file-i915-bugs
C: irc://irc.oftc.net/intel-gfx
T: git git://anongit.freedesktop.org/drm-intel
+F: Documentation/ABI/testing/sysfs-driver-intel-i915-hwmon
F: Documentation/gpu/i915.rst
F: drivers/gpu/drm/i915/
F: include/drm/i915*
F: drivers/gpu/drm/i915/gvt/
INTEL HID EVENT DRIVER
-M: Alex Hung <alex.hung@canonical.com>
+M: Alex Hung <alexhung@gmail.com>
S: Maintained
F: drivers/platform/x86/intel/hid.c
F: drivers/iommu/iova.c
F: include/linux/iova.h
+IOMMUFD
+S: Maintained
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd.git
+F: Documentation/userspace-api/iommufd.rst
+F: drivers/iommu/iommufd/
+F: include/linux/iommufd.h
+F: include/uapi/linux/iommufd.h
+F: tools/testing/selftests/iommu/
+
IOMMU SUBSYSTEM
F: drivers/isdn/hardware/
F: drivers/isdn/mISDN/
+ISOFS FILESYSTEM
+S: Maintained
+F: Documentation/filesystems/isofs.rst
+F: fs/isofs/
+
IT87 HARDWARE MONITORING DRIVER
JFS FILESYSTEM
-S: Maintained
+S: Odd Fixes
W: http://jfs.sourceforge.net/
-T: git git://github.com/kleikamp/linux-shaggy.git
+T: git https://github.com/kleikamp/linux-shaggy.git
F: Documentation/admin-guide/jfs.rst
F: fs/jfs/
S: Maintained
+Q: https://patchwork.kernel.org/project/linux-kbuild/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git kconfig
F: Documentation/kbuild/kconfig*
F: scripts/Kconfig.include
KERNEL BUILD + files below scripts/ (unless maintained elsewhere)
S: Maintained
+Q: https://patchwork.kernel.org/project/linux-kbuild/list/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/masahiroy/linux-kbuild.git
F: Documentation/kbuild/
F: Makefile
S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening
+F: Documentation/ABI/testing/sysfs-kernel-oops_count
+F: Documentation/ABI/testing/sysfs-kernel-warn_count
F: include/linux/overflow.h
F: include/linux/randomize_kstack.h
F: mm/usercopy.c
S: Supported
W: http://nfs.sourceforge.net/
T: git git://git.kernel.org/pub/scm/linux/kernel/git/cel/linux.git
+F: fs/exportfs/
F: fs/lockd/
F: fs/nfs_common/
F: fs/nfsd/
F: include/linux/lockd/
F: include/linux/sunrpc/
+F: include/trace/events/rpcgss.h
+F: include/trace/events/rpcrdma.h
+F: include/trace/events/sunrpc.h
+F: include/trace/misc/fs.h
+F: include/trace/misc/nfs.h
+F: include/trace/misc/sunrpc.h
F: include/uapi/linux/nfsd/
F: include/uapi/linux/sunrpc/
F: net/sunrpc/
F: arch/x86/kvm/svm/svm_onhyperv.*
F: arch/x86/kvm/vmx/evmcs.*
+KVM X86 Xen (KVM/Xen)
+S: Supported
+T: git git://git.kernel.org/pub/scm/virt/kvm/kvm.git
+F: arch/x86/kvm/xen.*
+
KERNFS
S: Maintained
F: Documentation/misc-devices/lis3lv02d.rst
F: drivers/misc/lis3lv02d/
-F: drivers/platform/x86/hp_accel.c
+F: drivers/platform/x86/hp/hp_accel.c
LIST KUNIT TEST
F: Documentation/loongarch/
F: Documentation/translations/zh_CN/loongarch/
+LOONGSON-2 SOC SERIES GUTS DRIVER
+S: Maintained
+F: Documentation/devicetree/bindings/hwinfo/loongson,ls2k-chipid.yaml
+F: drivers/soc/loongson/loongson2_guts.c
+
+LOONGSON-2 SOC SERIES PINCTRL DRIVER
+S: Maintained
+F: Documentation/devicetree/bindings/pinctrl/loongson,ls2k-pinctrl.yaml
+F: drivers/pinctrl/pinctrl-loongson2.c
+
LSILOGIC MPT FUSION DRIVERS (FC/SAS/SPI)
S: Maintained
W: http://linux-test-project.github.io/
-T: git git://github.com/linux-test-project/ltp.git
+T: git https://github.com/linux-test-project/ltp.git
LYNX 28G SERDES PHY DRIVER
MARVELL 88E6XXX ETHERNET SWITCH FABRIC DRIVER
S: Maintained
F: Documentation/devicetree/bindings/net/dsa/marvell.txt
S: Maintained
-F: Documentation/devicetree/bindings/net/marvell-pp2.txt
+F: Documentation/devicetree/bindings/net/marvell,pp2.yaml
F: drivers/net/ethernet/marvell/mvpp2/
MARVELL MWIFIEX WIRELESS DRIVER
F: drivers/net/ethernet/marvell/octeontx2/af/
MARVELL PRESTERA ETHERNET SWITCH DRIVER
S: Supported
W: https://github.com/Marvell-switching/switchdev-prestera
F: drivers/net/ethernet/marvell/prestera/
F: Documentation/devicetree/bindings/media/nxp,imx-mipi-csi2.yaml
F: Documentation/devicetree/bindings/media/nxp,imx7-csi.yaml
F: drivers/media/platform/nxp/imx-mipi-csis.c
-F: drivers/staging/media/imx/imx7-media-csi.c
+F: drivers/media/platform/nxp/imx7-media-csi.c
MEDIA DRIVERS FOR HELENE
S: Maintained
F: drivers/net/ethernet/mediatek/
F: include/linux/mm.h
F: include/linux/mmzone.h
F: include/linux/pagewalk.h
-F: include/linux/vmalloc.h
F: mm/
F: tools/testing/selftests/vm/
+VMALLOC
+S: Maintained
+W: http://www.linux-mm.org
+T: git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
+F: include/linux/vmalloc.h
+F: mm/vmalloc.c
+
MEMORY HOT(UN)PLUG
S: Maintained
-F: Documentation/devicetree/bindings/mtd/amlogic,meson-nand.txt
+F: Documentation/devicetree/bindings/mtd/amlogic,meson-nand.yaml
F: drivers/mtd/nand/raw/meson_*
MESON VIDEO DECODER DRIVER FOR AMLOGIC SOCS
S: Supported
F: Documentation/devicetree/bindings/media/microchip,csi2dc.yaml
-F: drivers/media/platform/atmel/microchip-csi2dc.c
+F: drivers/media/platform/microchip/microchip-csi2dc.c
MICROCHIP ECC DRIVER
S: Supported
F: Documentation/devicetree/bindings/media/atmel,isc.yaml
F: Documentation/devicetree/bindings/media/microchip,xisc.yaml
-F: drivers/media/platform/atmel/atmel-isc*
-F: drivers/media/platform/atmel/atmel-sama*-isc*
+F: drivers/staging/media/deprecated/atmel/atmel-isc*
+F: drivers/staging/media/deprecated/atmel/atmel-sama*-isc*
+F: drivers/media/platform/microchip/microchip-isc*
+F: drivers/media/platform/microchip/microchip-sama*-isc*
F: include/linux/atmel-isc-media.h
MICROCHIP ISI DRIVER
F: drivers/misc/atmel-ssc.c
F: include/linux/atmel-ssc.h
+MICROCHIP SOC DRIVERS
+S: Supported
+T: git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/
+F: drivers/soc/microchip/
+
MICROCHIP USB251XB DRIVER
F: include/linux/cciss*.h
F: include/uapi/linux/cciss*.h
+MICROSOFT MANA RDMA DRIVER
+S: Supported
+F: drivers/infiniband/hw/mana/
+F: include/net/mana
+F: include/uapi/rdma/mana-abi.h
+
MICROSOFT SURFACE AGGREGATOR TABLET-MODE SWITCH
MOTORCOMM PHY DRIVER
S: Maintained
F: drivers/net/phy/motorcomm.c
NETWORKING [DSA]
S: Maintained
T: git git://linuxtv.org/media_tree.git
F: drivers/media/i2c/ov08d10.c
+OMNIVISION OV08X40 SENSOR DRIVER
+S: Maintained
+T: git git://linuxtv.org/media_tree.git
+F: drivers/media/i2c/ov08x40.c
+
OMNIVISION OV13858 SENSOR DRIVER
T: git git://linuxtv.org/media_tree.git
F: drivers/media/i2c/ov2740.c
+OMNIVISION OV4689 SENSOR DRIVER
+S: Maintained
+T: git git://linuxtv.org/media_tree.git
+F: Documentation/devicetree/bindings/media/i2c/ovti,ov4689.yaml
+F: drivers/media/i2c/ov5647.c
+
OMNIVISION OV5640 SENSOR DRIVER
F: drivers/mtd/nand/onenand/
F: include/linux/mtd/onenand*.h
+ONEXPLAYER FAN DRIVER
+S: Maintained
+F: drivers/hwmon/oxp-sensors.c
+
ONION OMEGA2+ BOARD
B: https://bugzilla.kernel.org
C: irc://irc.oftc.net/linux-pci
T: git git://git.kernel.org/pub/scm/linux/kernel/git/lpieralisi/pci.git
+F: Documentation/devicetree/bindings/pci/
F: drivers/pci/controller/
F: drivers/pci/pci-bridge-emul.c
F: drivers/pci/pci-bridge-emul.h
F: drivers/pci/controller/*microchip*
PCIE DRIVER FOR QUALCOMM MSM
S: Maintained
F: include/linux/peci.h
PENSANDO ETHERNET DRIVERS
S: Supported
S: Maintained
F: Documentation/devicetree/bindings/pinctrl/mediatek,mt65xx-pinctrl.yaml
-F: Documentation/devicetree/bindings/pinctrl/mediatek,mt6797-pinctrl.yaml
+F: Documentation/devicetree/bindings/pinctrl/mediatek,mt6779-pinctrl.yaml
F: Documentation/devicetree/bindings/pinctrl/mediatek,mt7622-pinctrl.yaml
F: Documentation/devicetree/bindings/pinctrl/mediatek,mt8183-pinctrl.yaml
F: drivers/pinctrl/mediatek/
F: Documentation/devicetree/bindings/input/pine64,pinephone-keyboard.yaml
F: drivers/input/keyboard/pinephone-keyboard.c
-PKTCDVD DRIVER
-S: Orphan
-F: drivers/block/pktcdvd.c
-F: include/linux/pktcdvd.h
-F: include/uapi/linux/pktcdvd.h
-
PLANTOWER PMS7003 AIR POLLUTION SENSOR DRIVER
S: Maintained
PSTORE FILESYSTEM
-M: Colin Cross <ccross@android.com>
-S: Maintained
+R: Guilherme G. Piccoli <gpiccoli@igalia.com>
+S: Supported
T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/pstore
F: Documentation/admin-guide/ramoops.rst
F: Documentation/admin-guide/pstore-blk.rst
S: Maintained
T: git git://linuxtv.org/media_tree.git
-F: Documentation/admin-guide/media/pulse8-cec.rst
F: drivers/media/cec/usb/pulse8/
PURELIFI PLFXLC DRIVER
S: Maintained
+F: Documentation/devicetree/bindings/leds/irled/pwm-ir-tx.yaml
F: drivers/media/rc/pwm-ir-tx.c
PWM SUBSYSTEM
S: Supported
-F: Documentation/devicetree/bindings/soc/qcom/qcom,apr.yaml
+F: Documentation/devicetree/bindings/soc/qcom/qcom,apr*
F: Documentation/devicetree/bindings/sound/qcom,*
F: drivers/soc/qcom/apr.c
F: include/dt-bindings/sound/qcom,wcd9335.h
F: drivers/thermal/qcom/
QUALCOMM VENUS VIDEO ACCELERATOR DRIVER
S: Maintained
S: Supported
W: http://ceph.com/
-T: git git://github.com/ceph/ceph-client.git
+T: git https://github.com/ceph/ceph-client.git
F: Documentation/ABI/testing/sysfs-bus-rbd
F: drivers/block/rbd.c
F: drivers/block/rbd_types.h
F: drivers/net/wireless/realtek/rtw89/
REDPINE WIRELESS DRIVER
-S: Maintained
+S: Orphan
F: drivers/net/wireless/rsi/
REGISTER MAP ABSTRACTION
N: riscv
K: riscv
-RISC-V/MICROCHIP POLARFIRE SOC SUPPORT
+RISC-V MICROCHIP FPGA SUPPORT
F: arch/riscv/boot/dts/microchip/
F: drivers/char/hw_random/mpfs-rng.c
F: drivers/clk/microchip/clk-mpfs.c
-F: drivers/i2c/busses/i2c-microchip-core.c
+F: drivers/i2c/busses/i2c-microchip-corei2c.c
F: drivers/mailbox/mailbox-mpfs.c
F: drivers/pci/controller/pcie-microchip-host.c
F: drivers/reset/reset-mpfs.c
F: drivers/rtc/rtc-mpfs.c
-F: drivers/soc/microchip/
+F: drivers/soc/microchip/mpfs-sys-controller.c
F: drivers/spi/spi-microchip-core-qspi.c
F: drivers/spi/spi-microchip-core.c
F: drivers/usb/musb/mpfs.c
F: include/soc/microchip/mpfs.h
+RISC-V MISC SOC SUPPORT
+S: Maintained
+Q: https://patchwork.kernel.org/project/linux-riscv/list/
+T: git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/
+F: Documentation/devicetree/bindings/riscv/
+F: arch/riscv/boot/dts/
+
RNBD BLOCK DRIVERS
F: drivers/hid/hid-roccat*
F: include/linux/hid-roccat*
+ROCKCHIP CRYPTO DRIVERS
+S: Maintained
+F: Documentation/devicetree/bindings/crypto/rockchip,rk3288-crypto.yaml
+F: drivers/crypto/rockchip/
+
ROCKCHIP I2S TDM DRIVER
S: Maintained
F: drivers/video/fbdev/savage/
-S390
+S390 ARCHITECTURE
S: Supported
F: drivers/s390/net/
+S390 MM
+S: Supported
+T: git git://git.kernel.org/pub/scm/linux/kernel/git/s390/linux.git
+F: arch/s390/include/asm/pgtable.h
+F: arch/s390/mm
+
S390 PCI SUBSYSTEM
K: \bTIF_SECCOMP\b
SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) Broadcom BRCMSTB DRIVER
S: Supported
+F: Documentation/devicetree/bindings/mmc/sdhci-common.yaml
F: drivers/mmc/host/sdhci*
SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) MICROCHIP DRIVER
S: Supported
-T: git https://github.com/sifive/riscv-linux.git
N: sifive
K: [^@]sifive
F: Documentation/devicetree/bindings/dma/sifive,fu540-c000-pdma.yaml
F: drivers/dma/sf-pdma/
+SIFIVE SOC DRIVERS
+S: Maintained
+T: git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/
+F: drivers/soc/sifive/
+
SILEAD TOUCHSCREEN DRIVER
S: Maintained
F: include/linux/siphash.h
F: lib/siphash.c
-F: lib/test_siphash.c
+F: lib/siphash_kunit.c
SIS 190 ETHERNET DRIVER
F: include/video/sisfb.h
SIS I2C TOUCHSCREEN DRIVER
-M: Mika Penttilä <mika.penttila@nextfour.com>
+M: Mika Penttilä <mpenttil@redhat.com>
S: Maintained
F: Documentation/devicetree/bindings/input/touchscreen/sis_i2c.txt
S: Maintained
-F: Documentation/devicetree/bindings/net/socionext-netsec.txt
+F: Documentation/devicetree/bindings/net/socionext,synquacer-netsec.yaml
F: drivers/net/ethernet/socionext/netsec.c
SOCIONEXT (SNI) Synquacer SPI DRIVER
S: Maintained
-F: Documentation/devicetree/bindings/spi/spi-synquacer.txt
+F: Documentation/devicetree/bindings/spi/socionext,synquacer-spi.yaml
F: drivers/spi/spi-synquacer.c
SOCIONEXT SYNQUACER I2C DRIVER
S: Maintained
T: git git://linuxtv.org/media_tree.git
-F: Documentation/devicetree/bindings/media/i2c/imx290.txt
+F: Documentation/devicetree/bindings/media/i2c/sony,imx290.yaml
F: drivers/media/i2c/imx290.c
SONY IMX319 SENSOR DRIVER
Q: http://patchwork.linuxtv.org/project/linux-media/list/
F: drivers/media/dvb-frontends/sp2*
+SPANISH DOCUMENTATION
+S: Maintained
+F: Documentation/translations/sp_SP/
+
SPARC + UltraSPARC (sparc/sparc64)
S: Maintained
T: git git://linuxtv.org/media_tree.git
-F: Documentation/devicetree/bindings/media/i2c/st,st-mipid02.txt
+F: Documentation/devicetree/bindings/media/i2c/st,st-mipid02.yaml
F: drivers/media/i2c/st-mipid02.c
ST STM32 I2C/SMBUS DRIVER
F: Documentation/hwmon/stpddc60.rst
F: drivers/hwmon/pmbus/stpddc60.c
+ST VGXY61 DRIVER
+S: Maintained
+T: git git://linuxtv.org/media_tree.git
+F: Documentation/devicetree/bindings/media/i2c/st,st-vgxy61.yaml
+F: Documentation/userspace-api/media/drivers/st-vgxy61.rst
+F: drivers/media/i2c/st-vgxy61.c
+
ST VL53L0X ToF RANGER(I2C) IIO DRIVER
F: Documentation/process/stable-kernel-rules.rst
STAGING - ATOMISP DRIVER
S: Odd Fixes
F: drivers/net/ethernet/adaptec/starfire*
+STARFIVE DEVICETREES
+S: Maintained
+F: arch/riscv/boot/dts/starfive/
+
STARFIVE JH7100 CLOCK DRIVERS
S: Maintained
F: Documentation/devicetree/bindings/net/sunplus,sp7021-emac.yaml
F: drivers/net/ethernet/sunplus/
+SUNPLUS MMC DRIVER
+S: Maintained
+F: Documentation/devicetree/bindings/mmc/sunplus,mmc.yaml
+F: drivers/mmc/host/sunplus-mmc.c
+
SUNPLUS OCOTP DRIVER
S: Maintained
F: drivers/cpufreq/sc[mp]i-cpufreq.c
F: drivers/firmware/arm_scmi/
F: drivers/firmware/arm_scpi.c
+F: drivers/powercap/arm_scmi_powercap.c
F: drivers/regulator/scmi-regulator.c
F: drivers/reset/reset-scmi.c
F: include/linux/sc[mp]i_protocol.h
S: Maintained
-T: git git://github.com/czankel/xtensa-linux.git
+T: git https://github.com/jcmvbkbc/linux-xtensa.git
F: arch/xtensa/
F: drivers/irqchip/irq-xtensa-*
W: https://wireless.wiki.kernel.org/en/users/Drivers/wl1251
T: git git://git.kernel.org/pub/scm/linux/kernel/git/luca/wl12xx.git
F: drivers/net/wireless/ti/
-F: include/linux/wl12xx.h
TIMEKEEPING, CLOCKSOURCE CORE, NTP, ALARMTIMER
S: Maintained
- T: git git://github.com/awilliam/linux-vfio.git
+ T: git https://github.com/awilliam/linux-vfio.git
F: Documentation/ABI/testing/sysfs-devices-vfio-dev
F: Documentation/driver-api/vfio.rst
F: drivers/vfio/
F: include/uapi/linux/virtio_*.h
F: tools/virtio/
+VISL VIRTUAL STATELESS DECODER DRIVER
+S: Supported
+F: drivers/media/test-drivers/visl
+
IFCVF VIRTIO DATA PATH ACCELERATOR
F: drivers/vdpa/ifcvf/
return -ESRCH;
}
- kvm_get_kvm(vgpu->vfio_device.kvm);
-
if (__kvmgt_vgpu_exist(vgpu))
return -EEXIST;
vgpu->attached = true;
- kvmgt_protect_table_init(vgpu);
- gvt_cache_init(vgpu);
-
vgpu->track_node.track_write = kvmgt_page_track_write;
vgpu->track_node.track_flush_slot = kvmgt_page_track_flush_slot;
+ kvm_get_kvm(vgpu->vfio_device.kvm);
kvm_page_track_register_notifier(vgpu->vfio_device.kvm,
&vgpu->track_node);
intel_gvt_activate_vgpu(vgpu);
- atomic_set(&vgpu->released, 0);
return 0;
}
if (!vgpu->attached)
return;
- if (atomic_cmpxchg(&vgpu->released, 0, 1))
- return;
-
intel_gvt_release_vgpu(vgpu);
debugfs_remove(debugfs_lookup(KVMGT_DEBUGFS_FILENAME, vgpu->debugfs));
kvm_page_track_unregister_notifier(vgpu->vfio_device.kvm,
&vgpu->track_node);
+ kvm_put_kvm(vgpu->vfio_device.kvm);
+
kvmgt_protect_table_destroy(vgpu);
gvt_cache_destroy(vgpu);
+ WARN_ON(vgpu->nr_cache_entries);
+
+ vgpu->gfn_cache = RB_ROOT;
+ vgpu->dma_addr_cache = RB_ROOT;
+
intel_vgpu_release_msi_eventfd_ctx(vgpu);
vgpu->attached = false;
-
- if (vgpu->vfio_device.kvm)
- kvm_put_kvm(vgpu->vfio_device.kvm);
}
static u64 intel_vgpu_get_bar_addr(struct intel_vgpu *vgpu, int bar)
struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
struct intel_vgpu_type *type =
container_of(mdev->type, struct intel_vgpu_type, type);
+ int ret;
vgpu->gvt = kdev_to_i915(mdev->type->parent->dev)->gvt;
- return intel_gvt_create_vgpu(vgpu, type->conf);
+ ret = intel_gvt_create_vgpu(vgpu, type->conf);
+ if (ret)
+ return ret;
+
+ kvmgt_protect_table_init(vgpu);
+ gvt_cache_init(vgpu);
+
+ return 0;
}
static void intel_vgpu_release_dev(struct vfio_device *vfio_dev)
struct intel_vgpu *vgpu = vfio_dev_to_vgpu(vfio_dev);
intel_gvt_destroy_vgpu(vgpu);
- vfio_free_device(vfio_dev);
}
static const struct vfio_device_ops intel_vgpu_dev_ops = {
.mmap = intel_vgpu_mmap,
.ioctl = intel_vgpu_ioctl,
.dma_unmap = intel_vgpu_dma_unmap,
+ .bind_iommufd = vfio_iommufd_emulated_bind,
+ .unbind_iommufd = vfio_iommufd_emulated_unbind,
+ .attach_ioas = vfio_iommufd_emulated_attach_ioas,
};
static int intel_vgpu_probe(struct mdev_device *mdev)
static int fsm_io_helper(struct vfio_ccw_private *private)
{
- struct subchannel *sch;
+ struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
union orb *orb;
int ccode;
__u8 lpm;
unsigned long flags;
int ret;
- sch = private->sch;
-
spin_lock_irqsave(sch->lock, flags);
- orb = cp_get_orb(&private->cp, (u32)(addr_t)sch, sch->lpm);
+ orb = cp_get_orb(&private->cp, (u32)virt_to_phys(sch), sch->lpm);
if (!orb) {
ret = -EIO;
goto out;
static int fsm_do_halt(struct vfio_ccw_private *private)
{
- struct subchannel *sch;
+ struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
unsigned long flags;
int ccode;
int ret;
- sch = private->sch;
-
spin_lock_irqsave(sch->lock, flags);
VFIO_CCW_TRACE_EVENT(2, "haltIO");
static int fsm_do_clear(struct vfio_ccw_private *private)
{
- struct subchannel *sch;
+ struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
unsigned long flags;
int ccode;
int ret;
- sch = private->sch;
-
spin_lock_irqsave(sch->lock, flags);
VFIO_CCW_TRACE_EVENT(2, "clearIO");
static void fsm_notoper(struct vfio_ccw_private *private,
enum vfio_ccw_event event)
{
- struct subchannel *sch = private->sch;
+ struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: notoper event %x state %x\n",
sch->schid.cssid,
static void fsm_disabled_irq(struct vfio_ccw_private *private,
enum vfio_ccw_event event)
{
- struct subchannel *sch = private->sch;
+ struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
/*
* An interrupt in a disabled state means a previous disable was not
}
inline struct subchannel_id get_schid(struct vfio_ccw_private *p)
{
- return p->sch->schid;
+ struct subchannel *sch = to_subchannel(p->vdev.dev->parent);
+
+ return sch->schid;
}
/*
static void fsm_irq(struct vfio_ccw_private *private,
enum vfio_ccw_event event)
{
+ struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
struct irb *irb = this_cpu_ptr(&cio_irb);
VFIO_CCW_TRACE_EVENT(6, "IRQ");
- VFIO_CCW_TRACE_EVENT(6, dev_name(&private->sch->dev));
+ VFIO_CCW_TRACE_EVENT(6, dev_name(&sch->dev));
memcpy(&private->irb, irb, sizeof(*irb));
static void fsm_open(struct vfio_ccw_private *private,
enum vfio_ccw_event event)
{
- struct subchannel *sch = private->sch;
+ struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
int ret;
spin_lock_irq(sch->lock);
static void fsm_close(struct vfio_ccw_private *private,
enum vfio_ccw_event event)
{
- struct subchannel *sch = private->sch;
+ struct subchannel *sch = to_subchannel(private->vdev.dev->parent);
int ret;
spin_lock_irq(sch->lock);
struct vfio_ccw_private *private =
container_of(vdev, struct vfio_ccw_private, vdev);
- init_completion(&private->release_comp);
+ mutex_init(&private->io_mutex);
+ private->state = VFIO_CCW_STATE_STANDBY;
+ INIT_LIST_HEAD(&private->crw);
+ INIT_WORK(&private->io_work, vfio_ccw_sch_io_todo);
+ INIT_WORK(&private->crw_work, vfio_ccw_crw_todo);
+
+ private->cp.guest_cp = kcalloc(CCWCHAIN_LEN_MAX, sizeof(struct ccw1),
+ GFP_KERNEL);
+ if (!private->cp.guest_cp)
+ goto out_free_private;
+
+ private->io_region = kmem_cache_zalloc(vfio_ccw_io_region,
+ GFP_KERNEL | GFP_DMA);
+ if (!private->io_region)
+ goto out_free_cp;
+
+ private->cmd_region = kmem_cache_zalloc(vfio_ccw_cmd_region,
+ GFP_KERNEL | GFP_DMA);
+ if (!private->cmd_region)
+ goto out_free_io;
+
+ private->schib_region = kmem_cache_zalloc(vfio_ccw_schib_region,
+ GFP_KERNEL | GFP_DMA);
+ if (!private->schib_region)
+ goto out_free_cmd;
+
+ private->crw_region = kmem_cache_zalloc(vfio_ccw_crw_region,
+ GFP_KERNEL | GFP_DMA);
+ if (!private->crw_region)
+ goto out_free_schib;
+
return 0;
+
+ out_free_schib:
+ kmem_cache_free(vfio_ccw_schib_region, private->schib_region);
+ out_free_cmd:
+ kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
+ out_free_io:
+ kmem_cache_free(vfio_ccw_io_region, private->io_region);
+ out_free_cp:
+ kfree(private->cp.guest_cp);
+ out_free_private:
+ mutex_destroy(&private->io_mutex);
+ return -ENOMEM;
}
static int vfio_ccw_mdev_probe(struct mdev_device *mdev)
{
- struct vfio_ccw_private *private = dev_get_drvdata(mdev->dev.parent);
+ struct subchannel *sch = to_subchannel(mdev->dev.parent);
+ struct vfio_ccw_parent *parent = dev_get_drvdata(&sch->dev);
+ struct vfio_ccw_private *private;
int ret;
- if (private->state == VFIO_CCW_STATE_NOT_OPER)
- return -ENODEV;
+ private = vfio_alloc_device(vfio_ccw_private, vdev, &mdev->dev,
+ &vfio_ccw_dev_ops);
+ if (IS_ERR(private))
+ return PTR_ERR(private);
- ret = vfio_init_device(&private->vdev, &mdev->dev, &vfio_ccw_dev_ops);
- if (ret)
- return ret;
+ dev_set_drvdata(&parent->dev, private);
VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: create\n",
- private->sch->schid.cssid,
- private->sch->schid.ssid,
- private->sch->schid.sch_no);
+ sch->schid.cssid,
+ sch->schid.ssid,
+ sch->schid.sch_no);
ret = vfio_register_emulated_iommu_dev(&private->vdev);
if (ret)
return 0;
err_put_vdev:
+ dev_set_drvdata(&parent->dev, NULL);
vfio_put_device(&private->vdev);
return ret;
}
{
struct vfio_ccw_private *private =
container_of(vdev, struct vfio_ccw_private, vdev);
-
- /*
- * We cannot free vfio_ccw_private here because it includes
- * parent info which must be free'ed by css driver.
- *
- * Use a workaround by memset'ing the core device part and
- * then notifying the remove path that all active references
- * to this device have been released.
- */
- memset(vdev, 0, sizeof(*vdev));
- complete(&private->release_comp);
+ struct vfio_ccw_crw *crw, *temp;
+
+ list_for_each_entry_safe(crw, temp, &private->crw, next) {
+ list_del(&crw->next);
+ kfree(crw);
+ }
+
+ kmem_cache_free(vfio_ccw_crw_region, private->crw_region);
+ kmem_cache_free(vfio_ccw_schib_region, private->schib_region);
+ kmem_cache_free(vfio_ccw_cmd_region, private->cmd_region);
+ kmem_cache_free(vfio_ccw_io_region, private->io_region);
+ kfree(private->cp.guest_cp);
+ mutex_destroy(&private->io_mutex);
}
static void vfio_ccw_mdev_remove(struct mdev_device *mdev)
{
- struct vfio_ccw_private *private = dev_get_drvdata(mdev->dev.parent);
+ struct subchannel *sch = to_subchannel(mdev->dev.parent);
+ struct vfio_ccw_parent *parent = dev_get_drvdata(&sch->dev);
+ struct vfio_ccw_private *private = dev_get_drvdata(&parent->dev);
VFIO_CCW_MSG_EVENT(2, "sch %x.%x.%04x: remove\n",
- private->sch->schid.cssid,
- private->sch->schid.ssid,
- private->sch->schid.sch_no);
+ sch->schid.cssid,
+ sch->schid.ssid,
+ sch->schid.sch_no);
vfio_unregister_group_dev(&private->vdev);
+ dev_set_drvdata(&parent->dev, NULL);
vfio_put_device(&private->vdev);
- /*
- * Wait for all active references on mdev are released so it
- * is safe to defer kfree() to a later point.
- *
- * TODO: the clean fix is to split parent/mdev info from ccw
- * private structure so each can be managed in its own life
- * cycle.
- */
- wait_for_completion(&private->release_comp);
}
static int vfio_ccw_mdev_open_device(struct vfio_device *vdev)
.ioctl = vfio_ccw_mdev_ioctl,
.request = vfio_ccw_mdev_request,
.dma_unmap = vfio_ccw_dma_unmap,
+ .bind_iommufd = vfio_iommufd_emulated_bind,
+ .unbind_iommufd = vfio_iommufd_emulated_unbind,
+ .attach_ioas = vfio_iommufd_emulated_attach_ioas,
};
struct mdev_driver vfio_ccw_mdev_driver = {
aqic_gisa.isc = nisc;
aqic_gisa.ir = 1;
- aqic_gisa.gisa = (uint64_t)gisa >> 4;
+ aqic_gisa.gisa = virt_to_phys(gisa) >> 4;
status = ap_aqic(q->apqn, aqic_gisa, h_nib);
switch (status.response_code) {
}
}
- static void vfio_ap_mdev_release_dev(struct vfio_device *vdev)
- {
- vfio_free_device(vdev);
- }
-
static void vfio_ap_mdev_remove(struct mdev_device *mdev)
{
struct ap_matrix_mdev *matrix_mdev = dev_get_drvdata(&mdev->dev);
return 0;
}
+static void unmap_iova(struct ap_matrix_mdev *matrix_mdev, u64 iova, u64 length)
+{
+ struct ap_queue_table *qtable = &matrix_mdev->qtable;
+ struct vfio_ap_queue *q;
+ int loop_cursor;
+
+ hash_for_each(qtable->queues, loop_cursor, q, mdev_qnode) {
+ if (q->saved_iova >= iova && q->saved_iova < iova + length)
+ vfio_ap_irq_disable(q);
+ }
+}
+
static void vfio_ap_mdev_dma_unmap(struct vfio_device *vdev, u64 iova,
u64 length)
{
struct ap_matrix_mdev *matrix_mdev =
container_of(vdev, struct ap_matrix_mdev, vdev);
- vfio_unpin_pages(&matrix_mdev->vdev, iova, 1);
+ mutex_lock(&matrix_dev->mdevs_lock);
+
+ unmap_iova(matrix_mdev, iova, length);
+
+ mutex_unlock(&matrix_dev->mdevs_lock);
}
/**
static const struct vfio_device_ops vfio_ap_matrix_dev_ops = {
.init = vfio_ap_mdev_init_dev,
- .release = vfio_ap_mdev_release_dev,
.open_device = vfio_ap_mdev_open_device,
.close_device = vfio_ap_mdev_close_device,
.ioctl = vfio_ap_mdev_ioctl,
.dma_unmap = vfio_ap_mdev_dma_unmap,
+ .bind_iommufd = vfio_iommufd_emulated_bind,
+ .unbind_iommufd = vfio_iommufd_emulated_unbind,
+ .attach_ioas = vfio_iommufd_emulated_attach_ioas,
};
static struct mdev_driver vfio_ap_matrix_driver = {
menuconfig VFIO
tristate "VFIO Non-Privileged userspace driver framework"
select IOMMU_API
- select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
+ depends on IOMMUFD || !IOMMUFD
select INTERVAL_TREE
+ select VFIO_CONTAINER if IOMMUFD=n
help
VFIO provides a framework for secure userspace device drivers.
See Documentation/driver-api/vfio.rst for more details.
If you don't know what to do here, say N.
if VFIO
+config VFIO_CONTAINER
+ bool "Support for the VFIO container /dev/vfio/vfio"
+ select VFIO_IOMMU_TYPE1 if MMU && (X86 || S390 || ARM || ARM64)
+ default y
+ help
+ The VFIO container is the classic interface to VFIO for establishing
+ IOMMU mappings. If N is selected here then IOMMUFD must be used to
+ manage the mappings.
+
+ Unless testing IOMMUFD say Y here.
+
+if VFIO_CONTAINER
config VFIO_IOMMU_TYPE1
tristate
default n
depends on SPAPR_TCE_IOMMU
default VFIO
-config VFIO_VIRQFD
- bool
- select EVENTFD
- default n
-
config VFIO_NOIOMMU
bool "VFIO No-IOMMU support"
help
this mode since there is no IOMMU to provide DMA translation.
If you don't know what to do here, say N.
- config VFIO_SPAPR_EEH
- tristate
- depends on EEH && VFIO_IOMMU_SPAPR_TCE
- default VFIO
-
+endif
+
- tristate
+config VFIO_VIRQFD
++ bool
+ select EVENTFD
+ default n
source "drivers/vfio/pci/Kconfig"
source "drivers/vfio/platform/Kconfig"
# SPDX-License-Identifier: GPL-2.0
- vfio_virqfd-y := virqfd.o
-
obj-$(CONFIG_VFIO) += vfio.o
vfio-y += vfio_main.o \
- iova_bitmap.o \
- container.o
+ group.o \
+ iova_bitmap.o
+vfio-$(CONFIG_IOMMUFD) += iommufd.o
+vfio-$(CONFIG_VFIO_CONTAINER) += container.o
+ vfio-$(CONFIG_VFIO_VIRQFD) += virqfd.o
- obj-$(CONFIG_VFIO_VIRQFD) += vfio_virqfd.o
obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
- obj-$(CONFIG_VFIO_SPAPR_EEH) += vfio_spapr_eeh.o
obj-$(CONFIG_VFIO_PCI) += pci/
obj-$(CONFIG_VFIO_PLATFORM) += platform/
obj-$(CONFIG_VFIO_MDEV) += mdev/
vfio_fsl_uninit_device(vdev);
mutex_destroy(&vdev->igate);
- vfio_free_device(core_vdev);
}
static int vfio_fsl_mc_remove(struct fsl_mc_device *mc_dev)
.read = vfio_fsl_mc_read,
.write = vfio_fsl_mc_write,
.mmap = vfio_fsl_mc_mmap,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static struct fsl_mc_driver vfio_fsl_mc_driver = {
u32 que_iso_state;
int ret;
- if (migf->total_length < QM_MATCH_SIZE)
- return -EINVAL;
+ if (migf->total_length < QM_MATCH_SIZE || hisi_acc_vdev->match_done)
+ return 0;
if (vf_data->acc_magic != ACC_DEV_MAGIC) {
dev_err(dev, "failed to match ACC_DEV_MAGIC\n");
}
hisi_acc_vdev->vf_qm_state = vf_data->vf_qm_state;
+ hisi_acc_vdev->match_done = true;
return 0;
}
struct device *dev = &vf_qm->pdev->dev;
int ret;
- ret = vf_qm_get_match_data(hisi_acc_vdev, vf_data);
- if (ret)
- return ret;
-
if (unlikely(qm_wait_dev_not_ready(vf_qm))) {
/* Update state and return with match data */
vf_data->vf_qm_state = QM_NOT_READY;
struct hisi_acc_vf_migration_file *migf = hisi_acc_vdev->resuming_migf;
int ret;
- /* Check dev compatibility */
- ret = vf_qm_check_match(hisi_acc_vdev, migf);
- if (ret) {
- dev_err(dev, "failed to match the VF!\n");
- return ret;
- }
/* Recover data to VF */
ret = vf_qm_load_data(hisi_acc_vdev, migf);
if (ret) {
*pos += len;
done = len;
migf->total_length += len;
+
+ ret = vf_qm_check_match(migf->hisi_acc_vdev, migf);
+ if (ret)
+ done = -EFAULT;
out_unlock:
mutex_unlock(&migf->lock);
return done;
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
+ migf->hisi_acc_vdev = hisi_acc_vdev;
return migf;
}
+ static long hisi_acc_vf_precopy_ioctl(struct file *filp,
+ unsigned int cmd, unsigned long arg)
+ {
+ struct hisi_acc_vf_migration_file *migf = filp->private_data;
+ struct hisi_acc_vf_core_device *hisi_acc_vdev = migf->hisi_acc_vdev;
+ loff_t *pos = &filp->f_pos;
+ struct vfio_precopy_info info;
+ unsigned long minsz;
+ int ret;
+
+ if (cmd != VFIO_MIG_GET_PRECOPY_INFO)
+ return -ENOTTY;
+
+ minsz = offsetofend(struct vfio_precopy_info, dirty_bytes);
+
+ if (copy_from_user(&info, (void __user *)arg, minsz))
+ return -EFAULT;
+ if (info.argsz < minsz)
+ return -EINVAL;
+
+ mutex_lock(&hisi_acc_vdev->state_mutex);
+ if (hisi_acc_vdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY) {
+ mutex_unlock(&hisi_acc_vdev->state_mutex);
+ return -EINVAL;
+ }
+
+ mutex_lock(&migf->lock);
+
+ if (migf->disabled) {
+ ret = -ENODEV;
+ goto out;
+ }
+
+ if (*pos > migf->total_length) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ info.dirty_bytes = 0;
+ info.initial_bytes = migf->total_length - *pos;
+
+ ret = copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
+ out:
+ mutex_unlock(&migf->lock);
+ mutex_unlock(&hisi_acc_vdev->state_mutex);
+ return ret;
+ }
+
static ssize_t hisi_acc_vf_save_read(struct file *filp, char __user *buf, size_t len,
loff_t *pos)
{
static const struct file_operations hisi_acc_vf_save_fops = {
.owner = THIS_MODULE,
.read = hisi_acc_vf_save_read,
+ .unlocked_ioctl = hisi_acc_vf_precopy_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.release = hisi_acc_vf_release_file,
.llseek = no_llseek,
};
static struct hisi_acc_vf_migration_file *
- hisi_acc_vf_stop_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev)
+ hisi_acc_open_saving_migf(struct hisi_acc_vf_core_device *hisi_acc_vdev)
{
struct hisi_acc_vf_migration_file *migf;
int ret;
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
+ migf->hisi_acc_vdev = hisi_acc_vdev;
- ret = vf_qm_state_save(hisi_acc_vdev, migf);
+ ret = vf_qm_get_match_data(hisi_acc_vdev, &migf->vf_data);
if (ret) {
fput(migf->filp);
return ERR_PTR(ret);
return migf;
}
+ static struct hisi_acc_vf_migration_file *
+ hisi_acc_vf_pre_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev)
+ {
+ struct hisi_acc_vf_migration_file *migf;
+
+ migf = hisi_acc_open_saving_migf(hisi_acc_vdev);
+ if (IS_ERR(migf))
+ return migf;
+
+ migf->total_length = QM_MATCH_SIZE;
+ return migf;
+ }
+
+ static struct hisi_acc_vf_migration_file *
+ hisi_acc_vf_stop_copy(struct hisi_acc_vf_core_device *hisi_acc_vdev, bool open)
+ {
+ int ret;
+ struct hisi_acc_vf_migration_file *migf = NULL;
+
+ if (open) {
+ /*
+ * Userspace didn't use PRECOPY support. Hence saving_migf
+ * is not opened yet.
+ */
+ migf = hisi_acc_open_saving_migf(hisi_acc_vdev);
+ if (IS_ERR(migf))
+ return migf;
+ } else {
+ migf = hisi_acc_vdev->saving_migf;
+ }
+
+ ret = vf_qm_state_save(hisi_acc_vdev, migf);
+ if (ret)
+ return ERR_PTR(ret);
+
+ return open ? migf : NULL;
+ }
+
static int hisi_acc_vf_stop_device(struct hisi_acc_vf_core_device *hisi_acc_vdev)
{
struct device *dev = &hisi_acc_vdev->vf_dev->dev;
u32 cur = hisi_acc_vdev->mig_state;
int ret;
+ if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_PRE_COPY) {
+ struct hisi_acc_vf_migration_file *migf;
+
+ migf = hisi_acc_vf_pre_copy(hisi_acc_vdev);
+ if (IS_ERR(migf))
+ return ERR_CAST(migf);
+ get_file(migf->filp);
+ hisi_acc_vdev->saving_migf = migf;
+ return migf->filp;
+ }
+
+ if (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_STOP_COPY) {
+ struct hisi_acc_vf_migration_file *migf;
+
+ ret = hisi_acc_vf_stop_device(hisi_acc_vdev);
+ if (ret)
+ return ERR_PTR(ret);
+
+ migf = hisi_acc_vf_stop_copy(hisi_acc_vdev, false);
+ if (IS_ERR(migf))
+ return ERR_CAST(migf);
+
+ return NULL;
+ }
+
if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_STOP) {
ret = hisi_acc_vf_stop_device(hisi_acc_vdev);
if (ret)
if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_STOP_COPY) {
struct hisi_acc_vf_migration_file *migf;
- migf = hisi_acc_vf_stop_copy(hisi_acc_vdev);
+ migf = hisi_acc_vf_stop_copy(hisi_acc_vdev, true);
if (IS_ERR(migf))
return ERR_CAST(migf);
get_file(migf->filp);
return NULL;
}
+ if (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_RUNNING) {
+ hisi_acc_vf_disable_fds(hisi_acc_vdev);
+ return NULL;
+ }
+
if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RUNNING) {
hisi_acc_vf_start_device(hisi_acc_vdev);
return NULL;
return res;
}
+ static int
+ hisi_acc_vfio_pci_get_data_size(struct vfio_device *vdev,
+ unsigned long *stop_copy_length)
+ {
+ *stop_copy_length = sizeof(struct acc_vf_data);
+ return 0;
+ }
+
static int
hisi_acc_vfio_pci_get_device_state(struct vfio_device *vdev,
enum vfio_device_mig_state *curr_state)
static const struct vfio_migration_ops hisi_acc_vfio_pci_migrn_state_ops = {
.migration_set_state = hisi_acc_vfio_pci_set_device_state,
.migration_get_state = hisi_acc_vfio_pci_get_device_state,
+ .migration_get_data_size = hisi_acc_vfio_pci_get_data_size,
};
static int hisi_acc_vfio_pci_migrn_init_dev(struct vfio_device *core_vdev)
hisi_acc_vdev->vf_dev = pdev;
mutex_init(&hisi_acc_vdev->state_mutex);
- core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY;
+ core_vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY;
core_vdev->mig_ops = &hisi_acc_vfio_pci_migrn_state_ops;
return vfio_pci_core_init_dev(core_vdev);
.mmap = hisi_acc_vfio_pci_mmap,
.request = vfio_pci_core_request,
.match = vfio_pci_core_match,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
.mmap = vfio_pci_core_mmap,
.request = vfio_pci_core_request,
.match = vfio_pci_core_match,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
core_device);
}
- static struct page *
- mlx5vf_get_migration_page(struct mlx5_vf_migration_file *migf,
+ struct page *
+ mlx5vf_get_migration_page(struct mlx5_vhca_data_buffer *buf,
unsigned long offset)
{
unsigned long cur_offset = 0;
unsigned int i;
/* All accesses are sequential */
- if (offset < migf->last_offset || !migf->last_offset_sg) {
- migf->last_offset = 0;
- migf->last_offset_sg = migf->table.sgt.sgl;
- migf->sg_last_entry = 0;
+ if (offset < buf->last_offset || !buf->last_offset_sg) {
+ buf->last_offset = 0;
+ buf->last_offset_sg = buf->table.sgt.sgl;
+ buf->sg_last_entry = 0;
}
- cur_offset = migf->last_offset;
+ cur_offset = buf->last_offset;
- for_each_sg(migf->last_offset_sg, sg,
- migf->table.sgt.orig_nents - migf->sg_last_entry, i) {
+ for_each_sg(buf->last_offset_sg, sg,
+ buf->table.sgt.orig_nents - buf->sg_last_entry, i) {
if (offset < sg->length + cur_offset) {
- migf->last_offset_sg = sg;
- migf->sg_last_entry += i;
- migf->last_offset = cur_offset;
+ buf->last_offset_sg = sg;
+ buf->sg_last_entry += i;
+ buf->last_offset = cur_offset;
return nth_page(sg_page(sg),
(offset - cur_offset) / PAGE_SIZE);
}
return NULL;
}
- static int mlx5vf_add_migration_pages(struct mlx5_vf_migration_file *migf,
- unsigned int npages)
+ int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
+ unsigned int npages)
{
unsigned int to_alloc = npages;
struct page **page_list;
}
to_alloc -= filled;
ret = sg_alloc_append_table_from_pages(
- &migf->table, page_list, filled, 0,
+ &buf->table, page_list, filled, 0,
filled << PAGE_SHIFT, UINT_MAX, SG_MAX_SINGLE_ALLOC,
GFP_KERNEL);
if (ret)
goto err;
- migf->allocated_length += filled * PAGE_SIZE;
+ buf->allocated_length += filled * PAGE_SIZE;
/* clean input for another bulk allocation */
memset(page_list, 0, filled * sizeof(*page_list));
to_fill = min_t(unsigned int, to_alloc,
static void mlx5vf_disable_fd(struct mlx5_vf_migration_file *migf)
{
- struct sg_page_iter sg_iter;
-
mutex_lock(&migf->lock);
- /* Undo alloc_pages_bulk_array() */
- for_each_sgtable_page(&migf->table.sgt, &sg_iter, 0)
- __free_page(sg_page_iter_page(&sg_iter));
- sg_free_append_table(&migf->table);
- migf->disabled = true;
- migf->total_length = 0;
- migf->allocated_length = 0;
+ migf->state = MLX5_MIGF_STATE_ERROR;
migf->filp->f_pos = 0;
mutex_unlock(&migf->lock);
}
return 0;
}
+ static struct mlx5_vhca_data_buffer *
+ mlx5vf_get_data_buff_from_pos(struct mlx5_vf_migration_file *migf, loff_t pos,
+ bool *end_of_data)
+ {
+ struct mlx5_vhca_data_buffer *buf;
+ bool found = false;
+
+ *end_of_data = false;
+ spin_lock_irq(&migf->list_lock);
+ if (list_empty(&migf->buf_list)) {
+ *end_of_data = true;
+ goto end;
+ }
+
+ buf = list_first_entry(&migf->buf_list, struct mlx5_vhca_data_buffer,
+ buf_elm);
+ if (pos >= buf->start_pos &&
+ pos < buf->start_pos + buf->length) {
+ found = true;
+ goto end;
+ }
+
+ /*
+ * As we use a stream based FD we may expect having the data always
+ * on first chunk
+ */
+ migf->state = MLX5_MIGF_STATE_ERROR;
+
+ end:
+ spin_unlock_irq(&migf->list_lock);
+ return found ? buf : NULL;
+ }
+
+ static ssize_t mlx5vf_buf_read(struct mlx5_vhca_data_buffer *vhca_buf,
+ char __user **buf, size_t *len, loff_t *pos)
+ {
+ unsigned long offset;
+ ssize_t done = 0;
+ size_t copy_len;
+
+ copy_len = min_t(size_t,
+ vhca_buf->start_pos + vhca_buf->length - *pos, *len);
+ while (copy_len) {
+ size_t page_offset;
+ struct page *page;
+ size_t page_len;
+ u8 *from_buff;
+ int ret;
+
+ offset = *pos - vhca_buf->start_pos;
+ page_offset = offset % PAGE_SIZE;
+ offset -= page_offset;
+ page = mlx5vf_get_migration_page(vhca_buf, offset);
+ if (!page)
+ return -EINVAL;
+ page_len = min_t(size_t, copy_len, PAGE_SIZE - page_offset);
+ from_buff = kmap_local_page(page);
+ ret = copy_to_user(*buf, from_buff + page_offset, page_len);
+ kunmap_local(from_buff);
+ if (ret)
+ return -EFAULT;
+ *pos += page_len;
+ *len -= page_len;
+ *buf += page_len;
+ done += page_len;
+ copy_len -= page_len;
+ }
+
+ if (*pos >= vhca_buf->start_pos + vhca_buf->length) {
+ spin_lock_irq(&vhca_buf->migf->list_lock);
+ list_del_init(&vhca_buf->buf_elm);
+ list_add_tail(&vhca_buf->buf_elm, &vhca_buf->migf->avail_list);
+ spin_unlock_irq(&vhca_buf->migf->list_lock);
+ }
+
+ return done;
+ }
+
static ssize_t mlx5vf_save_read(struct file *filp, char __user *buf, size_t len,
loff_t *pos)
{
struct mlx5_vf_migration_file *migf = filp->private_data;
+ struct mlx5_vhca_data_buffer *vhca_buf;
+ bool first_loop_call = true;
+ bool end_of_data;
ssize_t done = 0;
if (pos)
if (!(filp->f_flags & O_NONBLOCK)) {
if (wait_event_interruptible(migf->poll_wait,
- READ_ONCE(migf->total_length) || migf->is_err))
+ !list_empty(&migf->buf_list) ||
+ migf->state == MLX5_MIGF_STATE_ERROR ||
+ migf->state == MLX5_MIGF_STATE_PRE_COPY_ERROR ||
+ migf->state == MLX5_MIGF_STATE_PRE_COPY ||
+ migf->state == MLX5_MIGF_STATE_COMPLETE))
return -ERESTARTSYS;
}
mutex_lock(&migf->lock);
- if ((filp->f_flags & O_NONBLOCK) && !READ_ONCE(migf->total_length)) {
- done = -EAGAIN;
- goto out_unlock;
- }
- if (*pos > migf->total_length) {
- done = -EINVAL;
- goto out_unlock;
- }
- if (migf->disabled || migf->is_err) {
+ if (migf->state == MLX5_MIGF_STATE_ERROR) {
done = -ENODEV;
goto out_unlock;
}
- len = min_t(size_t, migf->total_length - *pos, len);
while (len) {
- size_t page_offset;
- struct page *page;
- size_t page_len;
- u8 *from_buff;
- int ret;
+ ssize_t count;
+
+ vhca_buf = mlx5vf_get_data_buff_from_pos(migf, *pos,
+ &end_of_data);
+ if (first_loop_call) {
+ first_loop_call = false;
+ /* Temporary end of file as part of PRE_COPY */
+ if (end_of_data && (migf->state == MLX5_MIGF_STATE_PRE_COPY ||
+ migf->state == MLX5_MIGF_STATE_PRE_COPY_ERROR)) {
+ done = -ENOMSG;
+ goto out_unlock;
+ }
+
+ if (end_of_data && migf->state != MLX5_MIGF_STATE_COMPLETE) {
+ if (filp->f_flags & O_NONBLOCK) {
+ done = -EAGAIN;
+ goto out_unlock;
+ }
+ }
+ }
+
+ if (end_of_data)
+ goto out_unlock;
- page_offset = (*pos) % PAGE_SIZE;
- page = mlx5vf_get_migration_page(migf, *pos - page_offset);
- if (!page) {
- if (done == 0)
- done = -EINVAL;
+ if (!vhca_buf) {
+ done = -EINVAL;
goto out_unlock;
}
- page_len = min_t(size_t, len, PAGE_SIZE - page_offset);
- from_buff = kmap_local_page(page);
- ret = copy_to_user(buf, from_buff + page_offset, page_len);
- kunmap_local(from_buff);
- if (ret) {
- done = -EFAULT;
+ count = mlx5vf_buf_read(vhca_buf, &buf, &len, pos);
+ if (count < 0) {
+ done = count;
goto out_unlock;
}
- *pos += page_len;
- len -= page_len;
- done += page_len;
- buf += page_len;
+ done += count;
}
out_unlock:
poll_wait(filp, &migf->poll_wait, wait);
mutex_lock(&migf->lock);
- if (migf->disabled || migf->is_err)
+ if (migf->state == MLX5_MIGF_STATE_ERROR)
pollflags = EPOLLIN | EPOLLRDNORM | EPOLLRDHUP;
- else if (READ_ONCE(migf->total_length))
+ else if (!list_empty(&migf->buf_list) ||
+ migf->state == MLX5_MIGF_STATE_COMPLETE)
pollflags = EPOLLIN | EPOLLRDNORM;
mutex_unlock(&migf->lock);
return pollflags;
}
+ /*
+ * FD is exposed and user can use it after receiving an error.
+ * Mark migf in error, and wake the user.
+ */
+ static void mlx5vf_mark_err(struct mlx5_vf_migration_file *migf)
+ {
+ migf->state = MLX5_MIGF_STATE_ERROR;
+ wake_up_interruptible(&migf->poll_wait);
+ }
+
+ static long mlx5vf_precopy_ioctl(struct file *filp, unsigned int cmd,
+ unsigned long arg)
+ {
+ struct mlx5_vf_migration_file *migf = filp->private_data;
+ struct mlx5vf_pci_core_device *mvdev = migf->mvdev;
+ struct mlx5_vhca_data_buffer *buf;
+ struct vfio_precopy_info info = {};
+ loff_t *pos = &filp->f_pos;
+ unsigned long minsz;
+ size_t inc_length = 0;
+ bool end_of_data;
+ int ret;
+
+ if (cmd != VFIO_MIG_GET_PRECOPY_INFO)
+ return -ENOTTY;
+
+ minsz = offsetofend(struct vfio_precopy_info, dirty_bytes);
+
+ if (copy_from_user(&info, (void __user *)arg, minsz))
+ return -EFAULT;
+
+ if (info.argsz < minsz)
+ return -EINVAL;
+
+ mutex_lock(&mvdev->state_mutex);
+ if (mvdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY &&
+ mvdev->mig_state != VFIO_DEVICE_STATE_PRE_COPY_P2P) {
+ ret = -EINVAL;
+ goto err_state_unlock;
+ }
+
+ /*
+ * We can't issue a SAVE command when the device is suspended, so as
+ * part of VFIO_DEVICE_STATE_PRE_COPY_P2P no reason to query for extra
+ * bytes that can't be read.
+ */
+ if (mvdev->mig_state == VFIO_DEVICE_STATE_PRE_COPY) {
+ /*
+ * Once the query returns it's guaranteed that there is no
+ * active SAVE command.
+ * As so, the other code below is safe with the proper locks.
+ */
+ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &inc_length,
+ MLX5VF_QUERY_INC);
+ if (ret)
+ goto err_state_unlock;
+ }
+
+ mutex_lock(&migf->lock);
+ if (migf->state == MLX5_MIGF_STATE_ERROR) {
+ ret = -ENODEV;
+ goto err_migf_unlock;
+ }
+
+ buf = mlx5vf_get_data_buff_from_pos(migf, *pos, &end_of_data);
+ if (buf) {
+ if (buf->start_pos == 0) {
+ info.initial_bytes = buf->header_image_size - *pos;
+ } else if (buf->start_pos ==
+ sizeof(struct mlx5_vf_migration_header)) {
+ /* First data buffer following the header */
+ info.initial_bytes = buf->start_pos +
+ buf->length - *pos;
+ } else {
+ info.dirty_bytes = buf->start_pos + buf->length - *pos;
+ }
+ } else {
+ if (!end_of_data) {
+ ret = -EINVAL;
+ goto err_migf_unlock;
+ }
+
+ info.dirty_bytes = inc_length;
+ }
+
+ if (!end_of_data || !inc_length) {
+ mutex_unlock(&migf->lock);
+ goto done;
+ }
+
+ mutex_unlock(&migf->lock);
+ /*
+ * We finished transferring the current state and the device has a
+ * dirty state, save a new state to be ready for.
+ */
+ buf = mlx5vf_get_data_buffer(migf, inc_length, DMA_FROM_DEVICE);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ mlx5vf_mark_err(migf);
+ goto err_state_unlock;
+ }
+
+ ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf, true, true);
+ if (ret) {
+ mlx5vf_mark_err(migf);
+ mlx5vf_put_data_buffer(buf);
+ goto err_state_unlock;
+ }
+
+ done:
+ mlx5vf_state_mutex_unlock(mvdev);
+ if (copy_to_user((void __user *)arg, &info, minsz))
+ return -EFAULT;
+ return 0;
+
+ err_migf_unlock:
+ mutex_unlock(&migf->lock);
+ err_state_unlock:
+ mlx5vf_state_mutex_unlock(mvdev);
+ return ret;
+ }
+
static const struct file_operations mlx5vf_save_fops = {
.owner = THIS_MODULE,
.read = mlx5vf_save_read,
.poll = mlx5vf_save_poll,
+ .unlocked_ioctl = mlx5vf_precopy_ioctl,
+ .compat_ioctl = compat_ptr_ioctl,
.release = mlx5vf_release_file,
.llseek = no_llseek,
};
+ static int mlx5vf_pci_save_device_inc_data(struct mlx5vf_pci_core_device *mvdev)
+ {
+ struct mlx5_vf_migration_file *migf = mvdev->saving_migf;
+ struct mlx5_vhca_data_buffer *buf;
+ size_t length;
+ int ret;
+
+ if (migf->state == MLX5_MIGF_STATE_ERROR)
+ return -ENODEV;
+
+ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length,
+ MLX5VF_QUERY_INC | MLX5VF_QUERY_FINAL);
+ if (ret)
+ goto err;
+
+ buf = mlx5vf_get_data_buffer(migf, length, DMA_FROM_DEVICE);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ goto err;
+ }
+
+ ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf, true, false);
+ if (ret)
+ goto err_save;
+
+ return 0;
+
+ err_save:
+ mlx5vf_put_data_buffer(buf);
+ err:
+ mlx5vf_mark_err(migf);
+ return ret;
+ }
+
static struct mlx5_vf_migration_file *
- mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev)
+ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev, bool track)
{
struct mlx5_vf_migration_file *migf;
+ struct mlx5_vhca_data_buffer *buf;
+ size_t length;
int ret;
migf = kzalloc(sizeof(*migf), GFP_KERNEL);
migf->filp = anon_inode_getfile("mlx5vf_mig", &mlx5vf_save_fops, migf,
O_RDONLY);
if (IS_ERR(migf->filp)) {
- int err = PTR_ERR(migf->filp);
-
- kfree(migf);
- return ERR_PTR(err);
+ ret = PTR_ERR(migf->filp);
+ goto end;
}
+ migf->mvdev = mvdev;
+ ret = mlx5vf_cmd_alloc_pd(migf);
+ if (ret)
+ goto out_free;
+
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
init_waitqueue_head(&migf->poll_wait);
+ init_completion(&migf->save_comp);
+ /*
+ * save_comp is being used as a binary semaphore built from
+ * a completion. A normal mutex cannot be used because the lock is
+ * passed between kernel threads and lockdep can't model this.
+ */
+ complete(&migf->save_comp);
mlx5_cmd_init_async_ctx(mvdev->mdev, &migf->async_ctx);
INIT_WORK(&migf->async_data.work, mlx5vf_mig_file_cleanup_cb);
- ret = mlx5vf_cmd_query_vhca_migration_state(mvdev,
- &migf->total_length);
+ INIT_LIST_HEAD(&migf->buf_list);
+ INIT_LIST_HEAD(&migf->avail_list);
+ spin_lock_init(&migf->list_lock);
+ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length, 0);
if (ret)
- goto out_free;
+ goto out_pd;
- ret = mlx5vf_add_migration_pages(
- migf, DIV_ROUND_UP_ULL(migf->total_length, PAGE_SIZE));
- if (ret)
- goto out_free;
+ buf = mlx5vf_alloc_data_buffer(migf, length, DMA_FROM_DEVICE);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ goto out_pd;
+ }
- migf->mvdev = mvdev;
- ret = mlx5vf_cmd_save_vhca_state(mvdev, migf);
+ ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf, false, track);
if (ret)
- goto out_free;
+ goto out_save;
return migf;
+ out_save:
+ mlx5vf_free_data_buffer(buf);
+ out_pd:
+ mlx5vf_cmd_dealloc_pd(migf);
out_free:
fput(migf->filp);
+ end:
+ kfree(migf);
return ERR_PTR(ret);
}
+ static int
+ mlx5vf_append_page_to_mig_buf(struct mlx5_vhca_data_buffer *vhca_buf,
+ const char __user **buf, size_t *len,
+ loff_t *pos, ssize_t *done)
+ {
+ unsigned long offset;
+ size_t page_offset;
+ struct page *page;
+ size_t page_len;
+ u8 *to_buff;
+ int ret;
+
+ offset = *pos - vhca_buf->start_pos;
+ page_offset = offset % PAGE_SIZE;
+
+ page = mlx5vf_get_migration_page(vhca_buf, offset - page_offset);
+ if (!page)
+ return -EINVAL;
+ page_len = min_t(size_t, *len, PAGE_SIZE - page_offset);
+ to_buff = kmap_local_page(page);
+ ret = copy_from_user(to_buff + page_offset, *buf, page_len);
+ kunmap_local(to_buff);
+ if (ret)
+ return -EFAULT;
+
+ *pos += page_len;
+ *done += page_len;
+ *buf += page_len;
+ *len -= page_len;
+ vhca_buf->length += page_len;
+ return 0;
+ }
+
+ static int
+ mlx5vf_resume_read_image_no_header(struct mlx5_vhca_data_buffer *vhca_buf,
+ loff_t requested_length,
+ const char __user **buf, size_t *len,
+ loff_t *pos, ssize_t *done)
+ {
+ int ret;
+
+ if (requested_length > MAX_MIGRATION_SIZE)
+ return -ENOMEM;
+
+ if (vhca_buf->allocated_length < requested_length) {
+ ret = mlx5vf_add_migration_pages(
+ vhca_buf,
+ DIV_ROUND_UP(requested_length - vhca_buf->allocated_length,
+ PAGE_SIZE));
+ if (ret)
+ return ret;
+ }
+
+ while (*len) {
+ ret = mlx5vf_append_page_to_mig_buf(vhca_buf, buf, len, pos,
+ done);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
+ }
+
+ static ssize_t
+ mlx5vf_resume_read_image(struct mlx5_vf_migration_file *migf,
+ struct mlx5_vhca_data_buffer *vhca_buf,
+ size_t image_size, const char __user **buf,
+ size_t *len, loff_t *pos, ssize_t *done,
+ bool *has_work)
+ {
+ size_t copy_len, to_copy;
+ int ret;
+
+ to_copy = min_t(size_t, *len, image_size - vhca_buf->length);
+ copy_len = to_copy;
+ while (to_copy) {
+ ret = mlx5vf_append_page_to_mig_buf(vhca_buf, buf, &to_copy, pos,
+ done);
+ if (ret)
+ return ret;
+ }
+
+ *len -= copy_len;
+ if (vhca_buf->length == image_size) {
+ migf->load_state = MLX5_VF_LOAD_STATE_LOAD_IMAGE;
+ migf->max_pos += image_size;
+ *has_work = true;
+ }
+
+ return 0;
+ }
+
+ static int
+ mlx5vf_resume_read_header(struct mlx5_vf_migration_file *migf,
+ struct mlx5_vhca_data_buffer *vhca_buf,
+ const char __user **buf,
+ size_t *len, loff_t *pos,
+ ssize_t *done, bool *has_work)
+ {
+ struct page *page;
+ size_t copy_len;
+ u8 *to_buff;
+ int ret;
+
+ copy_len = min_t(size_t, *len,
+ sizeof(struct mlx5_vf_migration_header) - vhca_buf->length);
+ page = mlx5vf_get_migration_page(vhca_buf, 0);
+ if (!page)
+ return -EINVAL;
+ to_buff = kmap_local_page(page);
+ ret = copy_from_user(to_buff + vhca_buf->length, *buf, copy_len);
+ if (ret) {
+ ret = -EFAULT;
+ goto end;
+ }
+
+ *buf += copy_len;
+ *pos += copy_len;
+ *done += copy_len;
+ *len -= copy_len;
+ vhca_buf->length += copy_len;
+ if (vhca_buf->length == sizeof(struct mlx5_vf_migration_header)) {
+ u64 flags;
+
+ vhca_buf->header_image_size = le64_to_cpup((__le64 *)to_buff);
+ if (vhca_buf->header_image_size > MAX_MIGRATION_SIZE) {
+ ret = -ENOMEM;
+ goto end;
+ }
+
+ flags = le64_to_cpup((__le64 *)(to_buff +
+ offsetof(struct mlx5_vf_migration_header, flags)));
+ if (flags) {
+ ret = -EOPNOTSUPP;
+ goto end;
+ }
+
+ migf->load_state = MLX5_VF_LOAD_STATE_PREP_IMAGE;
+ migf->max_pos += vhca_buf->length;
+ *has_work = true;
+ }
+ end:
+ kunmap_local(to_buff);
+ return ret;
+ }
+
static ssize_t mlx5vf_resume_write(struct file *filp, const char __user *buf,
size_t len, loff_t *pos)
{
struct mlx5_vf_migration_file *migf = filp->private_data;
+ struct mlx5_vhca_data_buffer *vhca_buf = migf->buf;
+ struct mlx5_vhca_data_buffer *vhca_buf_header = migf->buf_header;
loff_t requested_length;
+ bool has_work = false;
ssize_t done = 0;
+ int ret = 0;
if (pos)
return -ESPIPE;
check_add_overflow((loff_t)len, *pos, &requested_length))
return -EINVAL;
- if (requested_length > MAX_MIGRATION_SIZE)
- return -ENOMEM;
-
+ mutex_lock(&migf->mvdev->state_mutex);
mutex_lock(&migf->lock);
- if (migf->disabled) {
- done = -ENODEV;
+ if (migf->state == MLX5_MIGF_STATE_ERROR) {
+ ret = -ENODEV;
goto out_unlock;
}
- if (migf->allocated_length < requested_length) {
- done = mlx5vf_add_migration_pages(
- migf,
- DIV_ROUND_UP(requested_length - migf->allocated_length,
- PAGE_SIZE));
- if (done)
- goto out_unlock;
- }
-
- while (len) {
- size_t page_offset;
- struct page *page;
- size_t page_len;
- u8 *to_buff;
- int ret;
-
- page_offset = (*pos) % PAGE_SIZE;
- page = mlx5vf_get_migration_page(migf, *pos - page_offset);
- if (!page) {
- if (done == 0)
- done = -EINVAL;
- goto out_unlock;
+ while (len || has_work) {
+ has_work = false;
+ switch (migf->load_state) {
+ case MLX5_VF_LOAD_STATE_READ_HEADER:
+ ret = mlx5vf_resume_read_header(migf, vhca_buf_header,
+ &buf, &len, pos,
+ &done, &has_work);
+ if (ret)
+ goto out_unlock;
+ break;
+ case MLX5_VF_LOAD_STATE_PREP_IMAGE:
+ {
+ u64 size = vhca_buf_header->header_image_size;
+
+ if (vhca_buf->allocated_length < size) {
+ mlx5vf_free_data_buffer(vhca_buf);
+
+ migf->buf = mlx5vf_alloc_data_buffer(migf,
+ size, DMA_TO_DEVICE);
+ if (IS_ERR(migf->buf)) {
+ ret = PTR_ERR(migf->buf);
+ migf->buf = NULL;
+ goto out_unlock;
+ }
+
+ vhca_buf = migf->buf;
+ }
+
+ vhca_buf->start_pos = migf->max_pos;
+ migf->load_state = MLX5_VF_LOAD_STATE_READ_IMAGE;
+ break;
}
+ case MLX5_VF_LOAD_STATE_READ_IMAGE_NO_HEADER:
+ ret = mlx5vf_resume_read_image_no_header(vhca_buf,
+ requested_length,
+ &buf, &len, pos, &done);
+ if (ret)
+ goto out_unlock;
+ break;
+ case MLX5_VF_LOAD_STATE_READ_IMAGE:
+ ret = mlx5vf_resume_read_image(migf, vhca_buf,
+ vhca_buf_header->header_image_size,
+ &buf, &len, pos, &done, &has_work);
+ if (ret)
+ goto out_unlock;
+ break;
+ case MLX5_VF_LOAD_STATE_LOAD_IMAGE:
+ ret = mlx5vf_cmd_load_vhca_state(migf->mvdev, migf, vhca_buf);
+ if (ret)
+ goto out_unlock;
+ migf->load_state = MLX5_VF_LOAD_STATE_READ_HEADER;
+
+ /* prep header buf for next image */
+ vhca_buf_header->length = 0;
+ vhca_buf_header->header_image_size = 0;
+ /* prep data buf for next image */
+ vhca_buf->length = 0;
- page_len = min_t(size_t, len, PAGE_SIZE - page_offset);
- to_buff = kmap_local_page(page);
- ret = copy_from_user(to_buff + page_offset, buf, page_len);
- kunmap_local(to_buff);
- if (ret) {
- done = -EFAULT;
- goto out_unlock;
+ break;
+ default:
+ break;
}
- *pos += page_len;
- len -= page_len;
- done += page_len;
- buf += page_len;
- migf->total_length += page_len;
}
+
out_unlock:
+ if (ret)
+ migf->state = MLX5_MIGF_STATE_ERROR;
mutex_unlock(&migf->lock);
- return done;
+ mlx5vf_state_mutex_unlock(migf->mvdev);
+ return ret ? ret : done;
}
static const struct file_operations mlx5vf_resume_fops = {
mlx5vf_pci_resume_device_data(struct mlx5vf_pci_core_device *mvdev)
{
struct mlx5_vf_migration_file *migf;
+ struct mlx5_vhca_data_buffer *buf;
+ int ret;
migf = kzalloc(sizeof(*migf), GFP_KERNEL);
if (!migf)
migf->filp = anon_inode_getfile("mlx5vf_mig", &mlx5vf_resume_fops, migf,
O_WRONLY);
if (IS_ERR(migf->filp)) {
- int err = PTR_ERR(migf->filp);
+ ret = PTR_ERR(migf->filp);
+ goto end;
+ }
- kfree(migf);
- return ERR_PTR(err);
+ migf->mvdev = mvdev;
+ ret = mlx5vf_cmd_alloc_pd(migf);
+ if (ret)
+ goto out_free;
+
+ buf = mlx5vf_alloc_data_buffer(migf, 0, DMA_TO_DEVICE);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ goto out_pd;
+ }
+
+ migf->buf = buf;
+ if (MLX5VF_PRE_COPY_SUPP(mvdev)) {
+ buf = mlx5vf_alloc_data_buffer(migf,
+ sizeof(struct mlx5_vf_migration_header), DMA_NONE);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ goto out_buf;
+ }
+
+ migf->buf_header = buf;
+ migf->load_state = MLX5_VF_LOAD_STATE_READ_HEADER;
+ } else {
+ /* Initial state will be to read the image */
+ migf->load_state = MLX5_VF_LOAD_STATE_READ_IMAGE_NO_HEADER;
}
+
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
+ INIT_LIST_HEAD(&migf->buf_list);
+ INIT_LIST_HEAD(&migf->avail_list);
+ spin_lock_init(&migf->list_lock);
return migf;
+ out_buf:
+ mlx5vf_free_data_buffer(migf->buf);
+ out_pd:
+ mlx5vf_cmd_dealloc_pd(migf);
+ out_free:
+ fput(migf->filp);
+ end:
+ kfree(migf);
+ return ERR_PTR(ret);
}
void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev)
{
if (mvdev->resuming_migf) {
mlx5vf_disable_fd(mvdev->resuming_migf);
+ mlx5fv_cmd_clean_migf_resources(mvdev->resuming_migf);
fput(mvdev->resuming_migf->filp);
mvdev->resuming_migf = NULL;
}
mlx5_cmd_cleanup_async_ctx(&mvdev->saving_migf->async_ctx);
cancel_work_sync(&mvdev->saving_migf->async_data.work);
mlx5vf_disable_fd(mvdev->saving_migf);
+ mlx5fv_cmd_clean_migf_resources(mvdev->saving_migf);
fput(mvdev->saving_migf->filp);
mvdev->saving_migf = NULL;
}
return NULL;
}
- if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) {
+ if ((cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_PRE_COPY_P2P)) {
ret = mlx5vf_cmd_suspend_vhca(mvdev,
MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_INITIATOR);
if (ret)
return NULL;
}
- if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) {
+ if ((cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_PRE_COPY)) {
ret = mlx5vf_cmd_resume_vhca(mvdev,
MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_INITIATOR);
if (ret)
if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_STOP_COPY) {
struct mlx5_vf_migration_file *migf;
- migf = mlx5vf_pci_save_device_data(mvdev);
+ migf = mlx5vf_pci_save_device_data(mvdev, false);
if (IS_ERR(migf))
return ERR_CAST(migf);
get_file(migf->filp);
return migf->filp;
}
- if ((cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP)) {
+ if ((cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_RUNNING) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P &&
+ new == VFIO_DEVICE_STATE_RUNNING_P2P)) {
mlx5vf_disable_fds(mvdev);
return NULL;
}
}
if (cur == VFIO_DEVICE_STATE_RESUMING && new == VFIO_DEVICE_STATE_STOP) {
- ret = mlx5vf_cmd_load_vhca_state(mvdev,
- mvdev->resuming_migf);
- if (ret)
- return ERR_PTR(ret);
+ if (!MLX5VF_PRE_COPY_SUPP(mvdev)) {
+ ret = mlx5vf_cmd_load_vhca_state(mvdev,
+ mvdev->resuming_migf,
+ mvdev->resuming_migf->buf);
+ if (ret)
+ return ERR_PTR(ret);
+ }
mlx5vf_disable_fds(mvdev);
return NULL;
}
+ if ((cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_PRE_COPY) ||
+ (cur == VFIO_DEVICE_STATE_RUNNING_P2P &&
+ new == VFIO_DEVICE_STATE_PRE_COPY_P2P)) {
+ struct mlx5_vf_migration_file *migf;
+
+ migf = mlx5vf_pci_save_device_data(mvdev, true);
+ if (IS_ERR(migf))
+ return ERR_CAST(migf);
+ get_file(migf->filp);
+ mvdev->saving_migf = migf;
+ return migf->filp;
+ }
+
+ if (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_STOP_COPY) {
+ ret = mlx5vf_cmd_suspend_vhca(mvdev,
+ MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_RESPONDER);
+ if (ret)
+ return ERR_PTR(ret);
+ ret = mlx5vf_pci_save_device_inc_data(mvdev);
+ return ret ? ERR_PTR(ret) : NULL;
+ }
+
/*
* vfio_mig_get_next_state() does not use arcs other than the above
*/
return res;
}
+ static int mlx5vf_pci_get_data_size(struct vfio_device *vdev,
+ unsigned long *stop_copy_length)
+ {
+ struct mlx5vf_pci_core_device *mvdev = container_of(
+ vdev, struct mlx5vf_pci_core_device, core_device.vdev);
+ size_t state_size;
+ int ret;
+
+ mutex_lock(&mvdev->state_mutex);
+ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev,
+ &state_size, 0);
+ if (!ret)
+ *stop_copy_length = state_size;
+ mlx5vf_state_mutex_unlock(mvdev);
+ return ret;
+ }
+
static int mlx5vf_pci_get_device_state(struct vfio_device *vdev,
enum vfio_device_mig_state *curr_state)
{
static const struct vfio_migration_ops mlx5vf_pci_mig_ops = {
.migration_set_state = mlx5vf_pci_set_device_state,
.migration_get_state = mlx5vf_pci_get_device_state,
+ .migration_get_data_size = mlx5vf_pci_get_data_size,
};
static const struct vfio_log_ops mlx5vf_pci_log_ops = {
.mmap = vfio_pci_core_mmap,
.request = vfio_pci_core_request,
.match = vfio_pci_core_match,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static int mlx5vf_pci_probe(struct pci_dev *pdev,
.driver_managed_dma = true,
};
- static void __exit mlx5vf_pci_cleanup(void)
- {
- pci_unregister_driver(&mlx5vf_pci_driver);
- }
-
- static int __init mlx5vf_pci_init(void)
- {
- return pci_register_driver(&mlx5vf_pci_driver);
- }
-
- module_init(mlx5vf_pci_init);
- module_exit(mlx5vf_pci_cleanup);
+ module_pci_driver(mlx5vf_pci_driver);
MODULE_LICENSE("GPL");
#include <linux/vgaarb.h>
#include <linux/nospec.h>
#include <linux/sched/mm.h>
+ #if IS_ENABLED(CONFIG_EEH)
+ #include <asm/eeh.h>
+ #endif
#include "vfio_pci_priv.h"
vdev->sriov_pf_core_dev->vf_token->users--;
mutex_unlock(&vdev->sriov_pf_core_dev->vf_token->lock);
}
- vfio_spapr_pci_eeh_release(vdev->pdev);
+ #if IS_ENABLED(CONFIG_EEH)
+ eeh_dev_release(vdev->pdev);
+ #endif
vfio_pci_core_disable(vdev);
mutex_lock(&vdev->igate);
void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev)
{
vfio_pci_probe_mmaps(vdev);
- vfio_spapr_pci_eeh_open(vdev->pdev);
+ #if IS_ENABLED(CONFIG_EEH)
+ eeh_dev_open(vdev->pdev);
+ #endif
if (vdev->sriov_pf_core_dev) {
mutex_lock(&vdev->sriov_pf_core_dev->vf_token->lock);
mutex_destroy(&vdev->vma_lock);
kfree(vdev->region);
kfree(vdev->pm_save);
- vfio_free_device(core_vdev);
}
EXPORT_SYMBOL_GPL(vfio_pci_core_release_dev);
if (vdev->vdev.mig_ops) {
if (!(vdev->vdev.mig_ops->migration_get_state &&
- vdev->vdev.mig_ops->migration_set_state) ||
+ vdev->vdev.mig_ops->migration_set_state &&
+ vdev->vdev.mig_ops->migration_get_data_size) ||
!(vdev->vdev.migration_flags & VFIO_MIGRATION_STOP_COPY))
return -EINVAL;
}
struct vfio_pci_core_device *cur;
bool needs_reset = false;
- list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list) {
- /* No VFIO device in the set can have an open device FD */
- if (cur->vdev.open_count)
- return false;
+ /* No other VFIO device in the set can be open. */
+ if (vfio_device_set_open_count(dev_set) > 1)
+ return false;
+
+ list_for_each_entry(cur, &dev_set->device_list, vdev.dev_set_list)
needs_reset |= cur->needs_reset;
- }
return needs_reset;
}
vfio_platform_release_common(vdev);
kfree(vdev->name);
- vfio_free_device(core_vdev);
}
static void vfio_amba_remove(struct amba_device *adev)
.read = vfio_platform_read,
.write = vfio_platform_write,
.mmap = vfio_platform_mmap,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static const struct amba_id pl330_ids[] = {
container_of(core_vdev, struct vfio_platform_device, vdev);
vfio_platform_release_common(vdev);
- vfio_free_device(core_vdev);
}
static int vfio_platform_remove(struct platform_device *pdev)
.read = vfio_platform_read,
.write = vfio_platform_write,
.mmap = vfio_platform_mmap,
+ .bind_iommufd = vfio_iommufd_physical_bind,
+ .unbind_iommufd = vfio_iommufd_physical_unbind,
+ .attach_ioas = vfio_iommufd_physical_attach_ioas,
};
static struct platform_driver vfio_platform_driver = {
#ifndef __VFIO_VFIO_H__
#define __VFIO_VFIO_H__
+#include <linux/file.h>
#include <linux/device.h>
#include <linux/cdev.h>
#include <linux/module.h>
+struct iommufd_ctx;
struct iommu_group;
struct vfio_device;
struct vfio_container;
+void vfio_device_put_registration(struct vfio_device *device);
+bool vfio_device_try_get_registration(struct vfio_device *device);
+int vfio_device_open(struct vfio_device *device,
+ struct iommufd_ctx *iommufd, struct kvm *kvm);
+void vfio_device_close(struct vfio_device *device,
+ struct iommufd_ctx *iommufd);
+
+extern const struct file_operations vfio_device_fops;
+
enum vfio_group_type {
/*
* Physical device with IOMMU backing.
struct list_head device_list;
struct mutex device_lock;
struct list_head vfio_next;
+#if IS_ENABLED(CONFIG_VFIO_CONTAINER)
struct list_head container_next;
+#endif
enum vfio_group_type type;
struct mutex group_lock;
struct kvm *kvm;
struct file *opened_file;
struct blocking_notifier_head notifier;
+ struct iommufd_ctx *iommufd;
};
+int vfio_device_set_group(struct vfio_device *device,
+ enum vfio_group_type type);
+void vfio_device_remove_group(struct vfio_device *device);
+void vfio_device_group_register(struct vfio_device *device);
+void vfio_device_group_unregister(struct vfio_device *device);
+int vfio_device_group_use_iommu(struct vfio_device *device);
+void vfio_device_group_unuse_iommu(struct vfio_device *device);
+void vfio_device_group_close(struct vfio_device *device);
+bool vfio_device_has_container(struct vfio_device *device);
+int __init vfio_group_init(void);
+void vfio_group_cleanup(void);
+
+#if IS_ENABLED(CONFIG_VFIO_CONTAINER)
/* events for the backend driver notify callback */
enum vfio_iommu_notify_type {
VFIO_IOMMU_CONTAINER_CLOSE = 0,
int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops);
void vfio_unregister_iommu_driver(const struct vfio_iommu_driver_ops *ops);
-bool vfio_assert_device_open(struct vfio_device *device);
-
struct vfio_container *vfio_container_from_file(struct file *filep);
-int vfio_device_assign_container(struct vfio_device *device);
-void vfio_device_unassign_container(struct vfio_device *device);
+int vfio_group_use_container(struct vfio_group *group);
+void vfio_group_unuse_container(struct vfio_group *group);
int vfio_container_attach_group(struct vfio_container *container,
struct vfio_group *group);
void vfio_group_detach_container(struct vfio_group *group);
void vfio_device_container_register(struct vfio_device *device);
void vfio_device_container_unregister(struct vfio_device *device);
-long vfio_container_ioctl_check_extension(struct vfio_container *container,
- unsigned long arg);
+int vfio_device_container_pin_pages(struct vfio_device *device,
+ dma_addr_t iova, int npage,
+ int prot, struct page **pages);
+void vfio_device_container_unpin_pages(struct vfio_device *device,
+ dma_addr_t iova, int npage);
+int vfio_device_container_dma_rw(struct vfio_device *device,
+ dma_addr_t iova, void *data,
+ size_t len, bool write);
+
int __init vfio_container_init(void);
void vfio_container_cleanup(void);
+#else
+static inline struct vfio_container *
+vfio_container_from_file(struct file *filep)
+{
+ return NULL;
+}
+
+static inline int vfio_group_use_container(struct vfio_group *group)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void vfio_group_unuse_container(struct vfio_group *group)
+{
+}
+
+static inline int vfio_container_attach_group(struct vfio_container *container,
+ struct vfio_group *group)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void vfio_group_detach_container(struct vfio_group *group)
+{
+}
+
+static inline void vfio_device_container_register(struct vfio_device *device)
+{
+}
+
+static inline void vfio_device_container_unregister(struct vfio_device *device)
+{
+}
+
+static inline int vfio_device_container_pin_pages(struct vfio_device *device,
+ dma_addr_t iova, int npage,
+ int prot, struct page **pages)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void vfio_device_container_unpin_pages(struct vfio_device *device,
+ dma_addr_t iova, int npage)
+{
+}
+
+static inline int vfio_device_container_dma_rw(struct vfio_device *device,
+ dma_addr_t iova, void *data,
+ size_t len, bool write)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline int vfio_container_init(void)
+{
+ return 0;
+}
+static inline void vfio_container_cleanup(void)
+{
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IOMMUFD)
+int vfio_iommufd_bind(struct vfio_device *device, struct iommufd_ctx *ictx);
+void vfio_iommufd_unbind(struct vfio_device *device);
+#else
+static inline int vfio_iommufd_bind(struct vfio_device *device,
+ struct iommufd_ctx *ictx)
+{
+ return -EOPNOTSUPP;
+}
+
+static inline void vfio_iommufd_unbind(struct vfio_device *device)
+{
+}
+#endif
+ #if IS_ENABLED(CONFIG_VFIO_VIRQFD)
+ int __init vfio_virqfd_init(void);
+ void vfio_virqfd_exit(void);
+ #else
+ static inline int __init vfio_virqfd_init(void)
+ {
+ return 0;
+ }
+ static inline void vfio_virqfd_exit(void)
+ {
+ }
+ #endif
+
#ifdef CONFIG_VFIO_NOIOMMU
extern bool vfio_noiommu __read_mostly;
#else
#include <linux/cdev.h>
#include <linux/compat.h>
#include <linux/device.h>
-#include <linux/file.h>
-#include <linux/anon_inodes.h>
#include <linux/fs.h>
#include <linux/idr.h>
#include <linux/iommu.h>
#include <linux/pm_runtime.h>
#include <linux/interval_tree.h>
#include <linux/iova_bitmap.h>
+#include <linux/iommufd.h>
#include "vfio.h"
#define DRIVER_VERSION "0.3"
#define DRIVER_DESC "VFIO - User Level meta-driver"
static struct vfio {
- struct class *class;
- struct list_head group_list;
- struct mutex group_lock; /* locks group_list */
- struct ida group_ida;
- dev_t group_devt;
struct class *device_class;
struct ida device_ida;
} vfio;
static DEFINE_XARRAY(vfio_device_set_xa);
-static const struct file_operations vfio_group_fops;
int vfio_assign_device_set(struct vfio_device *device, void *set_id)
{
xa_unlock(&vfio_device_set_xa);
}
-/*
- * Group objects - create, release, get, put, search
- */
-static struct vfio_group *
-__vfio_group_get_from_iommu(struct iommu_group *iommu_group)
-{
- struct vfio_group *group;
-
- /*
- * group->iommu_group from the vfio.group_list cannot be NULL
- * under the vfio.group_lock.
- */
- list_for_each_entry(group, &vfio.group_list, vfio_next) {
- if (group->iommu_group == iommu_group) {
- refcount_inc(&group->drivers);
- return group;
- }
- }
- return NULL;
-}
-
-static struct vfio_group *
-vfio_group_get_from_iommu(struct iommu_group *iommu_group)
-{
- struct vfio_group *group;
-
- mutex_lock(&vfio.group_lock);
- group = __vfio_group_get_from_iommu(iommu_group);
- mutex_unlock(&vfio.group_lock);
- return group;
-}
-
-static void vfio_group_release(struct device *dev)
-{
- struct vfio_group *group = container_of(dev, struct vfio_group, dev);
-
- mutex_destroy(&group->device_lock);
- mutex_destroy(&group->group_lock);
- WARN_ON(group->iommu_group);
- ida_free(&vfio.group_ida, MINOR(group->dev.devt));
- kfree(group);
-}
-
-static struct vfio_group *vfio_group_alloc(struct iommu_group *iommu_group,
- enum vfio_group_type type)
-{
- struct vfio_group *group;
- int minor;
-
- group = kzalloc(sizeof(*group), GFP_KERNEL);
- if (!group)
- return ERR_PTR(-ENOMEM);
-
- minor = ida_alloc_max(&vfio.group_ida, MINORMASK, GFP_KERNEL);
- if (minor < 0) {
- kfree(group);
- return ERR_PTR(minor);
- }
-
- device_initialize(&group->dev);
- group->dev.devt = MKDEV(MAJOR(vfio.group_devt), minor);
- group->dev.class = vfio.class;
- group->dev.release = vfio_group_release;
- cdev_init(&group->cdev, &vfio_group_fops);
- group->cdev.owner = THIS_MODULE;
-
- refcount_set(&group->drivers, 1);
- mutex_init(&group->group_lock);
- INIT_LIST_HEAD(&group->device_list);
- mutex_init(&group->device_lock);
- group->iommu_group = iommu_group;
- /* put in vfio_group_release() */
- iommu_group_ref_get(iommu_group);
- group->type = type;
- BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier);
-
- return group;
-}
-
-static struct vfio_group *vfio_create_group(struct iommu_group *iommu_group,
- enum vfio_group_type type)
+unsigned int vfio_device_set_open_count(struct vfio_device_set *dev_set)
{
- struct vfio_group *group;
- struct vfio_group *ret;
- int err;
-
- group = vfio_group_alloc(iommu_group, type);
- if (IS_ERR(group))
- return group;
-
- err = dev_set_name(&group->dev, "%s%d",
- group->type == VFIO_NO_IOMMU ? "noiommu-" : "",
- iommu_group_id(iommu_group));
- if (err) {
- ret = ERR_PTR(err);
- goto err_put;
- }
-
- mutex_lock(&vfio.group_lock);
-
- /* Did we race creating this group? */
- ret = __vfio_group_get_from_iommu(iommu_group);
- if (ret)
- goto err_unlock;
-
- err = cdev_device_add(&group->cdev, &group->dev);
- if (err) {
- ret = ERR_PTR(err);
- goto err_unlock;
- }
+ struct vfio_device *cur;
+ unsigned int open_count = 0;
- list_add(&group->vfio_next, &vfio.group_list);
+ lockdep_assert_held(&dev_set->lock);
- mutex_unlock(&vfio.group_lock);
- return group;
-
-err_unlock:
- mutex_unlock(&vfio.group_lock);
-err_put:
- put_device(&group->dev);
- return ret;
-}
-
-static void vfio_device_remove_group(struct vfio_device *device)
-{
- struct vfio_group *group = device->group;
- struct iommu_group *iommu_group;
-
- if (group->type == VFIO_NO_IOMMU || group->type == VFIO_EMULATED_IOMMU)
- iommu_group_remove_device(device->dev);
-
- /* Pairs with vfio_create_group() / vfio_group_get_from_iommu() */
- if (!refcount_dec_and_mutex_lock(&group->drivers, &vfio.group_lock))
- return;
- list_del(&group->vfio_next);
-
- /*
- * We could concurrently probe another driver in the group that might
- * race vfio_device_remove_group() with vfio_get_group(), so we have to
- * ensure that the sysfs is all cleaned up under lock otherwise the
- * cdev_device_add() will fail due to the name aready existing.
- */
- cdev_device_del(&group->cdev, &group->dev);
-
- mutex_lock(&group->group_lock);
- /*
- * These data structures all have paired operations that can only be
- * undone when the caller holds a live reference on the device. Since
- * all pairs must be undone these WARN_ON's indicate some caller did not
- * properly hold the group reference.
- */
- WARN_ON(!list_empty(&group->device_list));
- WARN_ON(group->notifier.head);
-
- /*
- * Revoke all users of group->iommu_group. At this point we know there
- * are no devices active because we are unplugging the last one. Setting
- * iommu_group to NULL blocks all new users.
- */
- if (group->container)
- vfio_group_detach_container(group);
- iommu_group = group->iommu_group;
- group->iommu_group = NULL;
- mutex_unlock(&group->group_lock);
- mutex_unlock(&vfio.group_lock);
-
- iommu_group_put(iommu_group);
- put_device(&group->dev);
+ list_for_each_entry(cur, &dev_set->device_list, dev_set_list)
+ open_count += cur->open_count;
+ return open_count;
}
+EXPORT_SYMBOL_GPL(vfio_device_set_open_count);
/*
* Device objects - create, release, get, put, search
*/
/* Device reference always implies a group reference */
-static void vfio_device_put_registration(struct vfio_device *device)
+void vfio_device_put_registration(struct vfio_device *device)
{
if (refcount_dec_and_test(&device->refcount))
complete(&device->comp);
}
-static bool vfio_device_try_get_registration(struct vfio_device *device)
+bool vfio_device_try_get_registration(struct vfio_device *device)
{
return refcount_inc_not_zero(&device->refcount);
}
-static struct vfio_device *vfio_group_get_device(struct vfio_group *group,
- struct device *dev)
-{
- struct vfio_device *device;
-
- mutex_lock(&group->device_lock);
- list_for_each_entry(device, &group->device_list, group_next) {
- if (device->dev == dev &&
- vfio_device_try_get_registration(device)) {
- mutex_unlock(&group->device_lock);
- return device;
- }
- }
- mutex_unlock(&group->device_lock);
- return NULL;
-}
-
/*
* VFIO driver API
*/
vfio_release_device_set(device);
ida_free(&vfio.device_ida, device->index);
- /*
- * kvfree() cannot be done here due to a life cycle mess in
- * vfio-ccw. Before the ccw part is fixed all drivers are
- * required to support @release and call vfio_free_device()
- * from there.
- */
- device->ops->release(device);
+ if (device->ops->release)
+ device->ops->release(device);
+
+ kvfree(device);
}
+ static int vfio_init_device(struct vfio_device *device, struct device *dev,
+ const struct vfio_device_ops *ops);
+
/*
* Allocate and initialize vfio_device so it can be registered to vfio
* core.
/*
* Initialize a vfio_device so it can be registered to vfio core.
- *
- * Only vfio-ccw driver should call this interface.
*/
- int vfio_init_device(struct vfio_device *device, struct device *dev,
- const struct vfio_device_ops *ops)
+ static int vfio_init_device(struct vfio_device *device, struct device *dev,
+ const struct vfio_device_ops *ops)
{
int ret;
ida_free(&vfio.device_ida, device->index);
return ret;
}
- EXPORT_SYMBOL_GPL(vfio_init_device);
-
- /*
- * The helper called by driver @release callback to free the device
- * structure. Drivers which don't have private data to clean can
- * simply use this helper as its @release.
- */
- void vfio_free_device(struct vfio_device *device)
- {
- kvfree(device);
- }
- EXPORT_SYMBOL_GPL(vfio_free_device);
-static struct vfio_group *vfio_noiommu_group_alloc(struct device *dev,
- enum vfio_group_type type)
-{
- struct iommu_group *iommu_group;
- struct vfio_group *group;
- int ret;
-
- iommu_group = iommu_group_alloc();
- if (IS_ERR(iommu_group))
- return ERR_CAST(iommu_group);
-
- ret = iommu_group_set_name(iommu_group, "vfio-noiommu");
- if (ret)
- goto out_put_group;
- ret = iommu_group_add_device(iommu_group, dev);
- if (ret)
- goto out_put_group;
-
- group = vfio_create_group(iommu_group, type);
- if (IS_ERR(group)) {
- ret = PTR_ERR(group);
- goto out_remove_device;
- }
- iommu_group_put(iommu_group);
- return group;
-
-out_remove_device:
- iommu_group_remove_device(dev);
-out_put_group:
- iommu_group_put(iommu_group);
- return ERR_PTR(ret);
-}
-
-static struct vfio_group *vfio_group_find_or_alloc(struct device *dev)
-{
- struct iommu_group *iommu_group;
- struct vfio_group *group;
-
- iommu_group = iommu_group_get(dev);
- if (!iommu_group && vfio_noiommu) {
- /*
- * With noiommu enabled, create an IOMMU group for devices that
- * don't already have one, implying no IOMMU hardware/driver
- * exists. Taint the kernel because we're about to give a DMA
- * capable device to a user without IOMMU protection.
- */
- group = vfio_noiommu_group_alloc(dev, VFIO_NO_IOMMU);
- if (!IS_ERR(group)) {
- add_taint(TAINT_USER, LOCKDEP_STILL_OK);
- dev_warn(dev, "Adding kernel taint for vfio-noiommu group on device\n");
- }
- return group;
- }
-
- if (!iommu_group)
- return ERR_PTR(-EINVAL);
-
- /*
- * VFIO always sets IOMMU_CACHE because we offer no way for userspace to
- * restore cache coherency. It has to be checked here because it is only
- * valid for cases where we are using iommu groups.
- */
- if (!device_iommu_capable(dev, IOMMU_CAP_CACHE_COHERENCY)) {
- iommu_group_put(iommu_group);
- return ERR_PTR(-EINVAL);
- }
-
- group = vfio_group_get_from_iommu(iommu_group);
- if (!group)
- group = vfio_create_group(iommu_group, VFIO_IOMMU);
-
- /* The vfio_group holds a reference to the iommu_group */
- iommu_group_put(iommu_group);
- return group;
-}
-
static int __vfio_register_dev(struct vfio_device *device,
- struct vfio_group *group)
+ enum vfio_group_type type)
{
- struct vfio_device *existing_device;
int ret;
- /*
- * In all cases group is the output of one of the group allocation
- * functions and we have group->drivers incremented for us.
- */
- if (IS_ERR(group))
- return PTR_ERR(group);
+ if (WARN_ON(device->ops->bind_iommufd &&
+ (!device->ops->unbind_iommufd ||
+ !device->ops->attach_ioas)))
+ return -EINVAL;
/*
* If the driver doesn't specify a set then the device is added to a
if (!device->dev_set)
vfio_assign_device_set(device, device);
- existing_device = vfio_group_get_device(group, device->dev);
- if (existing_device) {
- /*
- * group->iommu_group is non-NULL because we hold the drivers
- * refcount.
- */
- dev_WARN(device->dev, "Device already exists on group %d\n",
- iommu_group_id(group->iommu_group));
- vfio_device_put_registration(existing_device);
- ret = -EBUSY;
- goto err_out;
- }
-
- /* Our reference on group is moved to the device */
- device->group = group;
-
ret = dev_set_name(&device->device, "vfio%d", device->index);
if (ret)
- goto err_out;
+ return ret;
+
+ ret = vfio_device_set_group(device, type);
+ if (ret)
+ return ret;
ret = device_add(&device->device);
if (ret)
/* Refcounting can't start until the driver calls register */
refcount_set(&device->refcount, 1);
- mutex_lock(&group->device_lock);
- list_add(&device->group_next, &group->device_list);
- mutex_unlock(&group->device_lock);
+ vfio_device_group_register(device);
return 0;
err_out:
int vfio_register_group_dev(struct vfio_device *device)
{
- return __vfio_register_dev(device,
- vfio_group_find_or_alloc(device->dev));
+ return __vfio_register_dev(device, VFIO_IOMMU);
}
EXPORT_SYMBOL_GPL(vfio_register_group_dev);
*/
int vfio_register_emulated_iommu_dev(struct vfio_device *device)
{
- return __vfio_register_dev(device,
- vfio_noiommu_group_alloc(device->dev, VFIO_EMULATED_IOMMU));
+ return __vfio_register_dev(device, VFIO_EMULATED_IOMMU);
}
EXPORT_SYMBOL_GPL(vfio_register_emulated_iommu_dev);
-static struct vfio_device *vfio_device_get_from_name(struct vfio_group *group,
- char *buf)
-{
- struct vfio_device *it, *device = ERR_PTR(-ENODEV);
-
- mutex_lock(&group->device_lock);
- list_for_each_entry(it, &group->device_list, group_next) {
- int ret;
-
- if (it->ops->match) {
- ret = it->ops->match(it, buf);
- if (ret < 0) {
- device = ERR_PTR(ret);
- break;
- }
- } else {
- ret = !strcmp(dev_name(it->dev), buf);
- }
-
- if (ret && vfio_device_try_get_registration(it)) {
- device = it;
- break;
- }
- }
- mutex_unlock(&group->device_lock);
-
- return device;
-}
-
/*
* Decrement the device reference count and wait for the device to be
* removed. Open file descriptors for the device... */
void vfio_unregister_group_dev(struct vfio_device *device)
{
- struct vfio_group *group = device->group;
unsigned int i = 0;
bool interrupted = false;
long rc;
}
}
- mutex_lock(&group->device_lock);
- list_del(&device->group_next);
- mutex_unlock(&group->device_lock);
+ vfio_device_group_unregister(device);
/* Balances device_add in register path */
device_del(&device->device);
+ /* Balances vfio_device_set_group in register path */
vfio_device_remove_group(device);
}
EXPORT_SYMBOL_GPL(vfio_unregister_group_dev);
-/*
- * VFIO Group fd, /dev/vfio/$GROUP
- */
-/*
- * VFIO_GROUP_UNSET_CONTAINER should fail if there are other users or
- * if there was no container to unset. Since the ioctl is called on
- * the group, we know that still exists, therefore the only valid
- * transition here is 1->0.
- */
-static int vfio_group_ioctl_unset_container(struct vfio_group *group)
-{
- int ret = 0;
-
- mutex_lock(&group->group_lock);
- if (!group->container) {
- ret = -EINVAL;
- goto out_unlock;
- }
- if (group->container_users != 1) {
- ret = -EBUSY;
- goto out_unlock;
- }
- vfio_group_detach_container(group);
-
-out_unlock:
- mutex_unlock(&group->group_lock);
- return ret;
-}
-
-static int vfio_group_ioctl_set_container(struct vfio_group *group,
- int __user *arg)
-{
- struct vfio_container *container;
- struct fd f;
- int ret;
- int fd;
-
- if (get_user(fd, arg))
- return -EFAULT;
-
- f = fdget(fd);
- if (!f.file)
- return -EBADF;
-
- mutex_lock(&group->group_lock);
- if (group->container || WARN_ON(group->container_users)) {
- ret = -EINVAL;
- goto out_unlock;
- }
- if (!group->iommu_group) {
- ret = -ENODEV;
- goto out_unlock;
- }
-
- container = vfio_container_from_file(f.file);
- ret = -EINVAL;
- if (container) {
- ret = vfio_container_attach_group(container, group);
- goto out_unlock;
- }
-
-out_unlock:
- mutex_unlock(&group->group_lock);
- fdput(f);
- return ret;
-}
-
-static const struct file_operations vfio_device_fops;
-
/* true if the vfio_device has open_device() called but not close_device() */
-bool vfio_assert_device_open(struct vfio_device *device)
+static bool vfio_assert_device_open(struct vfio_device *device)
{
return !WARN_ON_ONCE(!READ_ONCE(device->open_count));
}
-static struct file *vfio_device_open(struct vfio_device *device)
+static int vfio_device_first_open(struct vfio_device *device,
+ struct iommufd_ctx *iommufd, struct kvm *kvm)
{
- struct file *filep;
int ret;
- mutex_lock(&device->group->group_lock);
- ret = vfio_device_assign_container(device);
- mutex_unlock(&device->group->group_lock);
- if (ret)
- return ERR_PTR(ret);
+ lockdep_assert_held(&device->dev_set->lock);
- if (!try_module_get(device->dev->driver->owner)) {
- ret = -ENODEV;
- goto err_unassign_container;
- }
-
- mutex_lock(&device->dev_set->lock);
- device->open_count++;
- if (device->open_count == 1) {
- /*
- * Here we pass the KVM pointer with the group under the read
- * lock. If the device driver will use it, it must obtain a
- * reference and release it during close_device.
- */
- mutex_lock(&device->group->group_lock);
- device->kvm = device->group->kvm;
+ if (!try_module_get(device->dev->driver->owner))
+ return -ENODEV;
- if (device->ops->open_device) {
- ret = device->ops->open_device(device);
- if (ret)
- goto err_undo_count;
- }
- vfio_device_container_register(device);
- mutex_unlock(&device->group->group_lock);
- }
- mutex_unlock(&device->dev_set->lock);
+ if (iommufd)
+ ret = vfio_iommufd_bind(device, iommufd);
+ else
+ ret = vfio_device_group_use_iommu(device);
+ if (ret)
+ goto err_module_put;
- /*
- * We can't use anon_inode_getfd() because we need to modify
- * the f_mode flags directly to allow more than just ioctls
- */
- filep = anon_inode_getfile("[vfio-device]", &vfio_device_fops,
- device, O_RDWR);
- if (IS_ERR(filep)) {
- ret = PTR_ERR(filep);
- goto err_close_device;
+ device->kvm = kvm;
+ if (device->ops->open_device) {
+ ret = device->ops->open_device(device);
+ if (ret)
+ goto err_unuse_iommu;
}
+ return 0;
- /*
- * TODO: add an anon_inode interface to do this.
- * Appears to be missing by lack of need rather than
- * explicitly prevented. Now there's need.
- */
- filep->f_mode |= (FMODE_PREAD | FMODE_PWRITE);
-
- if (device->group->type == VFIO_NO_IOMMU)
- dev_warn(device->dev, "vfio-noiommu device opened by user "
- "(%s:%d)\n", current->comm, task_pid_nr(current));
- /*
- * On success the ref of device is moved to the file and
- * put in vfio_device_fops_release()
- */
- return filep;
-
-err_close_device:
- mutex_lock(&device->dev_set->lock);
- mutex_lock(&device->group->group_lock);
- if (device->open_count == 1 && device->ops->close_device) {
- device->ops->close_device(device);
-
- vfio_device_container_unregister(device);
- }
-err_undo_count:
- mutex_unlock(&device->group->group_lock);
- device->open_count--;
- if (device->open_count == 0 && device->kvm)
- device->kvm = NULL;
- mutex_unlock(&device->dev_set->lock);
+err_unuse_iommu:
+ device->kvm = NULL;
+ if (iommufd)
+ vfio_iommufd_unbind(device);
+ else
+ vfio_device_group_unuse_iommu(device);
+err_module_put:
module_put(device->dev->driver->owner);
-err_unassign_container:
- vfio_device_unassign_container(device);
- return ERR_PTR(ret);
-}
-
-static int vfio_group_ioctl_get_device_fd(struct vfio_group *group,
- char __user *arg)
-{
- struct vfio_device *device;
- struct file *filep;
- char *buf;
- int fdno;
- int ret;
-
- buf = strndup_user(arg, PAGE_SIZE);
- if (IS_ERR(buf))
- return PTR_ERR(buf);
-
- device = vfio_device_get_from_name(group, buf);
- kfree(buf);
- if (IS_ERR(device))
- return PTR_ERR(device);
-
- fdno = get_unused_fd_flags(O_CLOEXEC);
- if (fdno < 0) {
- ret = fdno;
- goto err_put_device;
- }
-
- filep = vfio_device_open(device);
- if (IS_ERR(filep)) {
- ret = PTR_ERR(filep);
- goto err_put_fdno;
- }
-
- fd_install(fdno, filep);
- return fdno;
-
-err_put_fdno:
- put_unused_fd(fdno);
-err_put_device:
- vfio_device_put_registration(device);
return ret;
}
-static int vfio_group_ioctl_get_status(struct vfio_group *group,
- struct vfio_group_status __user *arg)
-{
- unsigned long minsz = offsetofend(struct vfio_group_status, flags);
- struct vfio_group_status status;
-
- if (copy_from_user(&status, arg, minsz))
- return -EFAULT;
-
- if (status.argsz < minsz)
- return -EINVAL;
-
- status.flags = 0;
-
- mutex_lock(&group->group_lock);
- if (!group->iommu_group) {
- mutex_unlock(&group->group_lock);
- return -ENODEV;
- }
-
- if (group->container)
- status.flags |= VFIO_GROUP_FLAGS_CONTAINER_SET |
- VFIO_GROUP_FLAGS_VIABLE;
- else if (!iommu_group_dma_owner_claimed(group->iommu_group))
- status.flags |= VFIO_GROUP_FLAGS_VIABLE;
- mutex_unlock(&group->group_lock);
-
- if (copy_to_user(arg, &status, minsz))
- return -EFAULT;
- return 0;
-}
-
-static long vfio_group_fops_unl_ioctl(struct file *filep,
- unsigned int cmd, unsigned long arg)
+static void vfio_device_last_close(struct vfio_device *device,
+ struct iommufd_ctx *iommufd)
{
- struct vfio_group *group = filep->private_data;
- void __user *uarg = (void __user *)arg;
+ lockdep_assert_held(&device->dev_set->lock);
- switch (cmd) {
- case VFIO_GROUP_GET_DEVICE_FD:
- return vfio_group_ioctl_get_device_fd(group, uarg);
- case VFIO_GROUP_GET_STATUS:
- return vfio_group_ioctl_get_status(group, uarg);
- case VFIO_GROUP_SET_CONTAINER:
- return vfio_group_ioctl_set_container(group, uarg);
- case VFIO_GROUP_UNSET_CONTAINER:
- return vfio_group_ioctl_unset_container(group);
- default:
- return -ENOTTY;
- }
+ if (device->ops->close_device)
+ device->ops->close_device(device);
+ device->kvm = NULL;
+ if (iommufd)
+ vfio_iommufd_unbind(device);
+ else
+ vfio_device_group_unuse_iommu(device);
+ module_put(device->dev->driver->owner);
}
-static int vfio_group_fops_open(struct inode *inode, struct file *filep)
+int vfio_device_open(struct vfio_device *device,
+ struct iommufd_ctx *iommufd, struct kvm *kvm)
{
- struct vfio_group *group =
- container_of(inode->i_cdev, struct vfio_group, cdev);
- int ret;
-
- mutex_lock(&group->group_lock);
-
- /*
- * drivers can be zero if this races with vfio_device_remove_group(), it
- * will be stable at 0 under the group rwsem
- */
- if (refcount_read(&group->drivers) == 0) {
- ret = -ENODEV;
- goto out_unlock;
- }
+ int ret = 0;
- if (group->type == VFIO_NO_IOMMU && !capable(CAP_SYS_RAWIO)) {
- ret = -EPERM;
- goto out_unlock;
+ mutex_lock(&device->dev_set->lock);
+ device->open_count++;
+ if (device->open_count == 1) {
+ ret = vfio_device_first_open(device, iommufd, kvm);
+ if (ret)
+ device->open_count--;
}
+ mutex_unlock(&device->dev_set->lock);
- /*
- * Do we need multiple instances of the group open? Seems not.
- */
- if (group->opened_file) {
- ret = -EBUSY;
- goto out_unlock;
- }
- group->opened_file = filep;
- filep->private_data = group;
- ret = 0;
-out_unlock:
- mutex_unlock(&group->group_lock);
return ret;
}
-static int vfio_group_fops_release(struct inode *inode, struct file *filep)
+void vfio_device_close(struct vfio_device *device,
+ struct iommufd_ctx *iommufd)
{
- struct vfio_group *group = filep->private_data;
-
- filep->private_data = NULL;
-
- mutex_lock(&group->group_lock);
- /*
- * Device FDs hold a group file reference, therefore the group release
- * is only called when there are no open devices.
- */
- WARN_ON(group->notifier.head);
- if (group->container)
- vfio_group_detach_container(group);
- group->opened_file = NULL;
- mutex_unlock(&group->group_lock);
- return 0;
+ mutex_lock(&device->dev_set->lock);
+ vfio_assert_device_open(device);
+ if (device->open_count == 1)
+ vfio_device_last_close(device, iommufd);
+ device->open_count--;
+ mutex_unlock(&device->dev_set->lock);
}
-static const struct file_operations vfio_group_fops = {
- .owner = THIS_MODULE,
- .unlocked_ioctl = vfio_group_fops_unl_ioctl,
- .compat_ioctl = compat_ptr_ioctl,
- .open = vfio_group_fops_open,
- .release = vfio_group_fops_release,
-};
-
/*
* Wrapper around pm_runtime_resume_and_get().
* Return error code on failure or 0 on success.
{
struct vfio_device *device = filep->private_data;
- mutex_lock(&device->dev_set->lock);
- vfio_assert_device_open(device);
- mutex_lock(&device->group->group_lock);
- if (device->open_count == 1 && device->ops->close_device)
- device->ops->close_device(device);
-
- vfio_device_container_unregister(device);
- mutex_unlock(&device->group->group_lock);
- device->open_count--;
- if (device->open_count == 0)
- device->kvm = NULL;
- mutex_unlock(&device->dev_set->lock);
-
- module_put(device->dev->driver->owner);
-
- vfio_device_unassign_container(device);
+ vfio_device_group_close(device);
vfio_device_put_registration(device);
enum vfio_device_mig_state new_fsm,
enum vfio_device_mig_state *next_fsm)
{
- enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_RUNNING_P2P + 1 };
+ enum { VFIO_DEVICE_NUM_STATES = VFIO_DEVICE_STATE_PRE_COPY_P2P + 1 };
/*
* The coding in this table requires the driver to implement the
* following FSM arcs:
* RUNNING_P2P -> RUNNING
* RUNNING_P2P -> STOP
* STOP -> RUNNING_P2P
- * Without P2P the driver must implement:
+ *
+ * If precopy is supported then the driver must support these additional
+ * FSM arcs:
+ * RUNNING -> PRE_COPY
+ * PRE_COPY -> RUNNING
+ * PRE_COPY -> STOP_COPY
+ * However, if precopy and P2P are supported together then the driver
+ * must support these additional arcs beyond the P2P arcs above:
+ * PRE_COPY -> RUNNING
+ * PRE_COPY -> PRE_COPY_P2P
+ * PRE_COPY_P2P -> PRE_COPY
+ * PRE_COPY_P2P -> RUNNING_P2P
+ * PRE_COPY_P2P -> STOP_COPY
+ * RUNNING -> PRE_COPY
+ * RUNNING_P2P -> PRE_COPY_P2P
+ *
+ * Without P2P and precopy the driver must implement:
* RUNNING -> STOP
* STOP -> RUNNING
*
* The coding will step through multiple states for some combination
* transitions; if all optional features are supported, this means the
* following ones:
+ * PRE_COPY -> PRE_COPY_P2P -> STOP_COPY
+ * PRE_COPY -> RUNNING -> RUNNING_P2P
+ * PRE_COPY -> RUNNING -> RUNNING_P2P -> STOP
+ * PRE_COPY -> RUNNING -> RUNNING_P2P -> STOP -> RESUMING
+ * PRE_COPY_P2P -> RUNNING_P2P -> RUNNING
+ * PRE_COPY_P2P -> RUNNING_P2P -> STOP
+ * PRE_COPY_P2P -> RUNNING_P2P -> STOP -> RESUMING
* RESUMING -> STOP -> RUNNING_P2P
+ * RESUMING -> STOP -> RUNNING_P2P -> PRE_COPY_P2P
* RESUMING -> STOP -> RUNNING_P2P -> RUNNING
+ * RESUMING -> STOP -> RUNNING_P2P -> RUNNING -> PRE_COPY
* RESUMING -> STOP -> STOP_COPY
+ * RUNNING -> RUNNING_P2P -> PRE_COPY_P2P
* RUNNING -> RUNNING_P2P -> STOP
* RUNNING -> RUNNING_P2P -> STOP -> RESUMING
* RUNNING -> RUNNING_P2P -> STOP -> STOP_COPY
+ * RUNNING_P2P -> RUNNING -> PRE_COPY
* RUNNING_P2P -> STOP -> RESUMING
* RUNNING_P2P -> STOP -> STOP_COPY
+ * STOP -> RUNNING_P2P -> PRE_COPY_P2P
* STOP -> RUNNING_P2P -> RUNNING
+ * STOP -> RUNNING_P2P -> RUNNING -> PRE_COPY
* STOP_COPY -> STOP -> RESUMING
* STOP_COPY -> STOP -> RUNNING_P2P
* STOP_COPY -> STOP -> RUNNING_P2P -> RUNNING
+ *
+ * The following transitions are blocked:
+ * STOP_COPY -> PRE_COPY
+ * STOP_COPY -> PRE_COPY_P2P
*/
static const u8 vfio_from_fsm_table[VFIO_DEVICE_NUM_STATES][VFIO_DEVICE_NUM_STATES] = {
[VFIO_DEVICE_STATE_STOP] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_RUNNING] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
},
+ [VFIO_DEVICE_STATE_PRE_COPY] = {
+ [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P,
+ [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_PRE_COPY_P2P,
+ [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
+ },
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = {
+ [VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_PRE_COPY,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P,
+ [VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY,
+ [VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
+ [VFIO_DEVICE_STATE_ERROR] = VFIO_DEVICE_STATE_ERROR,
+ },
[VFIO_DEVICE_STATE_STOP_COPY] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_ERROR,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_ERROR,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP_COPY,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RESUMING] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_STOP,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_STOP,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_RESUMING,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING_P2P] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_RUNNING,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_PRE_COPY_P2P,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_STOP,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_RUNNING_P2P,
[VFIO_DEVICE_STATE_ERROR] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_DEVICE_STATE_ERROR,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_DEVICE_STATE_ERROR,
+ [VFIO_DEVICE_STATE_PRE_COPY] = VFIO_DEVICE_STATE_ERROR,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_DEVICE_STATE_ERROR,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_DEVICE_STATE_ERROR,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_DEVICE_STATE_ERROR,
[VFIO_DEVICE_STATE_RUNNING_P2P] = VFIO_DEVICE_STATE_ERROR,
static const unsigned int state_flags_table[VFIO_DEVICE_NUM_STATES] = {
[VFIO_DEVICE_STATE_STOP] = VFIO_MIGRATION_STOP_COPY,
[VFIO_DEVICE_STATE_RUNNING] = VFIO_MIGRATION_STOP_COPY,
+ [VFIO_DEVICE_STATE_PRE_COPY] =
+ VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_PRE_COPY,
+ [VFIO_DEVICE_STATE_PRE_COPY_P2P] = VFIO_MIGRATION_STOP_COPY |
+ VFIO_MIGRATION_P2P |
+ VFIO_MIGRATION_PRE_COPY,
[VFIO_DEVICE_STATE_STOP_COPY] = VFIO_MIGRATION_STOP_COPY,
[VFIO_DEVICE_STATE_RESUMING] = VFIO_MIGRATION_STOP_COPY,
[VFIO_DEVICE_STATE_RUNNING_P2P] =
return 0;
}
+ static int
+ vfio_ioctl_device_feature_migration_data_size(struct vfio_device *device,
+ u32 flags, void __user *arg,
+ size_t argsz)
+ {
+ struct vfio_device_feature_mig_data_size data_size = {};
+ unsigned long stop_copy_length;
+ int ret;
+
+ if (!device->mig_ops)
+ return -ENOTTY;
+
+ ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET,
+ sizeof(data_size));
+ if (ret != 1)
+ return ret;
+
+ ret = device->mig_ops->migration_get_data_size(device, &stop_copy_length);
+ if (ret)
+ return ret;
+
+ data_size.stop_copy_length = stop_copy_length;
+ if (copy_to_user(arg, &data_size, sizeof(data_size)))
+ return -EFAULT;
+
+ return 0;
+ }
+
static int vfio_ioctl_device_feature_migration(struct vfio_device *device,
u32 flags, void __user *arg,
size_t argsz)
return vfio_ioctl_device_feature_logging_report(
device, feature.flags, arg->data,
feature.argsz - minsz);
+ case VFIO_DEVICE_FEATURE_MIG_DATA_SIZE:
+ return vfio_ioctl_device_feature_migration_data_size(
+ device, feature.flags, arg->data,
+ feature.argsz - minsz);
default:
if (unlikely(!device->ops->device_feature))
return -EINVAL;
return device->ops->mmap(device, vma);
}
-static const struct file_operations vfio_device_fops = {
+const struct file_operations vfio_device_fops = {
.owner = THIS_MODULE,
.release = vfio_device_fops_release,
.read = vfio_device_fops_read,
.mmap = vfio_device_fops_mmap,
};
-/**
- * vfio_file_iommu_group - Return the struct iommu_group for the vfio group file
- * @file: VFIO group file
- *
- * The returned iommu_group is valid as long as a ref is held on the file. This
- * returns a reference on the group. This function is deprecated, only the SPAPR
- * path in kvm should call it.
- */
-struct iommu_group *vfio_file_iommu_group(struct file *file)
-{
- struct vfio_group *group = file->private_data;
- struct iommu_group *iommu_group = NULL;
-
- if (!IS_ENABLED(CONFIG_SPAPR_TCE_IOMMU))
- return NULL;
-
- if (!vfio_file_is_group(file))
- return NULL;
-
- mutex_lock(&group->group_lock);
- if (group->iommu_group) {
- iommu_group = group->iommu_group;
- iommu_group_ref_get(iommu_group);
- }
- mutex_unlock(&group->group_lock);
- return iommu_group;
-}
-EXPORT_SYMBOL_GPL(vfio_file_iommu_group);
-
-/**
- * vfio_file_is_group - True if the file is usable with VFIO aPIS
- * @file: VFIO group file
- */
-bool vfio_file_is_group(struct file *file)
-{
- return file->f_op == &vfio_group_fops;
-}
-EXPORT_SYMBOL_GPL(vfio_file_is_group);
-
-/**
- * vfio_file_enforced_coherent - True if the DMA associated with the VFIO file
- * is always CPU cache coherent
- * @file: VFIO group file
- *
- * Enforced coherency means that the IOMMU ignores things like the PCIe no-snoop
- * bit in DMA transactions. A return of false indicates that the user has
- * rights to access additional instructions such as wbinvd on x86.
- */
-bool vfio_file_enforced_coherent(struct file *file)
-{
- struct vfio_group *group = file->private_data;
- bool ret;
-
- if (!vfio_file_is_group(file))
- return true;
-
- mutex_lock(&group->group_lock);
- if (group->container) {
- ret = vfio_container_ioctl_check_extension(group->container,
- VFIO_DMA_CC_IOMMU);
- } else {
- /*
- * Since the coherency state is determined only once a container
- * is attached the user must do so before they can prove they
- * have permission.
- */
- ret = true;
- }
- mutex_unlock(&group->group_lock);
- return ret;
-}
-EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent);
-
-/**
- * vfio_file_set_kvm - Link a kvm with VFIO drivers
- * @file: VFIO group file
- * @kvm: KVM to link
- *
- * When a VFIO device is first opened the KVM will be available in
- * device->kvm if one was associated with the group.
- */
-void vfio_file_set_kvm(struct file *file, struct kvm *kvm)
-{
- struct vfio_group *group = file->private_data;
-
- if (!vfio_file_is_group(file))
- return;
-
- mutex_lock(&group->group_lock);
- group->kvm = kvm;
- mutex_unlock(&group->group_lock);
-}
-EXPORT_SYMBOL_GPL(vfio_file_set_kvm);
-
-/**
- * vfio_file_has_dev - True if the VFIO file is a handle for device
- * @file: VFIO file to check
- * @device: Device that must be part of the file
- *
- * Returns true if given file has permission to manipulate the given device.
- */
-bool vfio_file_has_dev(struct file *file, struct vfio_device *device)
-{
- struct vfio_group *group = file->private_data;
-
- if (!vfio_file_is_group(file))
- return false;
-
- return group == device->group;
-}
-EXPORT_SYMBOL_GPL(vfio_file_has_dev);
-
/*
* Sub-module support
*/
EXPORT_SYMBOL(vfio_set_irqs_validate_and_prepare);
/*
- * Module/class support
+ * Pin contiguous user pages and return their associated host pages for local
+ * domain only.
+ * @device [in] : device
+ * @iova [in] : starting IOVA of user pages to be pinned.
+ * @npage [in] : count of pages to be pinned. This count should not
+ * be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
+ * @prot [in] : protection flags
+ * @pages[out] : array of host pages
+ * Return error or number of pages pinned.
+ *
+ * A driver may only call this function if the vfio_device was created
+ * by vfio_register_emulated_iommu_dev() due to vfio_device_container_pin_pages().
*/
-static char *vfio_devnode(struct device *dev, umode_t *mode)
+int vfio_pin_pages(struct vfio_device *device, dma_addr_t iova,
+ int npage, int prot, struct page **pages)
{
- return kasprintf(GFP_KERNEL, "vfio/%s", dev_name(dev));
+ /* group->container cannot change while a vfio device is open */
+ if (!pages || !npage || WARN_ON(!vfio_assert_device_open(device)))
+ return -EINVAL;
+ if (vfio_device_has_container(device))
+ return vfio_device_container_pin_pages(device, iova,
+ npage, prot, pages);
+ if (device->iommufd_access) {
+ int ret;
+
+ if (iova > ULONG_MAX)
+ return -EINVAL;
+ /*
+ * VFIO ignores the sub page offset, npages is from the start of
+ * a PAGE_SIZE chunk of IOVA. The caller is expected to recover
+ * the sub page offset by doing:
+ * pages[0] + (iova % PAGE_SIZE)
+ */
+ ret = iommufd_access_pin_pages(
+ device->iommufd_access, ALIGN_DOWN(iova, PAGE_SIZE),
+ npage * PAGE_SIZE, pages,
+ (prot & IOMMU_WRITE) ? IOMMUFD_ACCESS_RW_WRITE : 0);
+ if (ret)
+ return ret;
+ return npage;
+ }
+ return -EINVAL;
}
+EXPORT_SYMBOL(vfio_pin_pages);
+/*
+ * Unpin contiguous host pages for local domain only.
+ * @device [in] : device
+ * @iova [in] : starting address of user pages to be unpinned.
+ * @npage [in] : count of pages to be unpinned. This count should not
+ * be greater than VFIO_PIN_PAGES_MAX_ENTRIES.
+ */
+void vfio_unpin_pages(struct vfio_device *device, dma_addr_t iova, int npage)
+{
+ if (WARN_ON(!vfio_assert_device_open(device)))
+ return;
+
+ if (vfio_device_has_container(device)) {
+ vfio_device_container_unpin_pages(device, iova, npage);
+ return;
+ }
+ if (device->iommufd_access) {
+ if (WARN_ON(iova > ULONG_MAX))
+ return;
+ iommufd_access_unpin_pages(device->iommufd_access,
+ ALIGN_DOWN(iova, PAGE_SIZE),
+ npage * PAGE_SIZE);
+ return;
+ }
+}
+EXPORT_SYMBOL(vfio_unpin_pages);
+
+/*
+ * This interface allows the CPUs to perform some sort of virtual DMA on
+ * behalf of the device.
+ *
+ * CPUs read/write from/into a range of IOVAs pointing to user space memory
+ * into/from a kernel buffer.
+ *
+ * As the read/write of user space memory is conducted via the CPUs and is
+ * not a real device DMA, it is not necessary to pin the user space memory.
+ *
+ * @device [in] : VFIO device
+ * @iova [in] : base IOVA of a user space buffer
+ * @data [in] : pointer to kernel buffer
+ * @len [in] : kernel buffer length
+ * @write : indicate read or write
+ * Return error code on failure or 0 on success.
+ */
+int vfio_dma_rw(struct vfio_device *device, dma_addr_t iova, void *data,
+ size_t len, bool write)
+{
+ if (!data || len <= 0 || !vfio_assert_device_open(device))
+ return -EINVAL;
+
+ if (vfio_device_has_container(device))
+ return vfio_device_container_dma_rw(device, iova,
+ data, len, write);
+
+ if (device->iommufd_access) {
+ unsigned int flags = 0;
+
+ if (iova > ULONG_MAX)
+ return -EINVAL;
+
+ /* VFIO historically tries to auto-detect a kthread */
+ if (!current->mm)
+ flags |= IOMMUFD_ACCESS_RW_KTHREAD;
+ if (write)
+ flags |= IOMMUFD_ACCESS_RW_WRITE;
+ return iommufd_access_rw(device->iommufd_access, iova, data,
+ len, flags);
+ }
+ return -EINVAL;
+}
+EXPORT_SYMBOL(vfio_dma_rw);
+
+/*
+ * Module/class support
+ */
static int __init vfio_init(void)
{
int ret;
- ida_init(&vfio.group_ida);
ida_init(&vfio.device_ida);
- mutex_init(&vfio.group_lock);
- INIT_LIST_HEAD(&vfio.group_list);
- ret = vfio_container_init();
+ ret = vfio_group_init();
if (ret)
return ret;
- /* /dev/vfio/$GROUP */
- vfio.class = class_create(THIS_MODULE, "vfio");
- if (IS_ERR(vfio.class)) {
- ret = PTR_ERR(vfio.class);
- goto err_group_class;
- }
-
- vfio.class->devnode = vfio_devnode;
-
+ ret = vfio_virqfd_init();
+ if (ret)
+ goto err_virqfd;
+
/* /sys/class/vfio-dev/vfioX */
vfio.device_class = class_create(THIS_MODULE, "vfio-dev");
if (IS_ERR(vfio.device_class)) {
goto err_dev_class;
}
- ret = alloc_chrdev_region(&vfio.group_devt, 0, MINORMASK + 1, "vfio");
- if (ret)
- goto err_alloc_chrdev;
-
pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n");
return 0;
-err_alloc_chrdev:
- class_destroy(vfio.device_class);
- vfio.device_class = NULL;
err_dev_class:
- class_destroy(vfio.class);
- vfio.class = NULL;
-err_group_class:
+ vfio_virqfd_exit();
+ err_virqfd:
- vfio_container_cleanup();
+ vfio_group_cleanup();
return ret;
}
static void __exit vfio_cleanup(void)
{
- WARN_ON(!list_empty(&vfio.group_list));
-
ida_destroy(&vfio.device_ida);
- ida_destroy(&vfio.group_ida);
- unregister_chrdev_region(vfio.group_devt, MINORMASK + 1);
class_destroy(vfio.device_class);
vfio.device_class = NULL;
- class_destroy(vfio.class);
+ vfio_virqfd_exit();
- vfio_container_cleanup();
- vfio.class = NULL;
+ vfio_group_cleanup();
xa_destroy(&vfio_device_set_xa);
}
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR(DRIVER_AUTHOR);
MODULE_DESCRIPTION(DRIVER_DESC);
-MODULE_ALIAS_MISCDEV(VFIO_MINOR);
-MODULE_ALIAS("devname:vfio/vfio");
MODULE_SOFTDEP("post: vfio_iommu_type1 vfio_iommu_spapr_tce");
MLX5_SET_HCA_CAP_OP_MOD_ODP = 0x2,
MLX5_SET_HCA_CAP_OP_MOD_ATOMIC = 0x3,
MLX5_SET_HCA_CAP_OP_MOD_ROCE = 0x4,
+ MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE2 = 0x20,
MLX5_SET_HCA_CAP_OP_MODE_PORT_SELECTION = 0x25,
};
u8 max_modify_header_actions[0x8];
u8 max_ft_level[0x8];
- u8 reserved_at_40[0x6];
+ u8 reformat_add_esp_trasport[0x1];
+ u8 reserved_at_41[0x2];
+ u8 reformat_del_esp_trasport[0x1];
+ u8 reserved_at_44[0x2];
u8 execute_aso[0x1];
u8 reserved_at_47[0x19];
u8 reserved_at_1a0[0x8];
u8 macsec_syndrome[0x8];
+ u8 ipsec_syndrome[0x8];
+ u8 reserved_at_1b8[0x8];
- u8 reserved_at_1b0[0x50];
+ u8 reserved_at_1c0[0x40];
};
struct mlx5_ifc_fte_match_set_misc3_bits {
};
struct mlx5_ifc_cmd_hca_cap_2_bits {
- u8 reserved_at_0[0xa0];
+ u8 reserved_at_0[0x80];
+
+ u8 migratable[0x1];
+ u8 reserved_at_81[0x1f];
u8 max_reformat_insert_size[0x8];
u8 max_reformat_insert_offset[0x8];
u8 max_reformat_remove_size[0x8];
u8 max_reformat_remove_offset[0x8];
- u8 reserved_at_c0[0xe0];
+ u8 reserved_at_c0[0x8];
+ u8 migration_multi_load[0x1];
+ u8 migration_tracking_state[0x1];
+ u8 reserved_at_ca[0x16];
+
+ u8 reserved_at_e0[0xc0];
u8 reserved_at_1a0[0xb];
u8 log_min_mkey_entity_size[0x5];
u8 inner_dmac_15_0[0x10];
};
+enum {
+ MLX5_IFC_DEFINER_FORMAT_ID_SELECT = 61,
+};
+
+#define MLX5_IFC_DEFINER_FORMAT_OFFSET_UNUSED 0x0
+#define MLX5_IFC_DEFINER_FORMAT_OFFSET_OUTER_ETH_PKT_LEN 0x48
+#define MLX5_IFC_DEFINER_DW_SELECTORS_NUM 9
+#define MLX5_IFC_DEFINER_BYTE_SELECTORS_NUM 8
+
+struct mlx5_ifc_match_definer_match_mask_bits {
+ u8 reserved_at_1c0[5][0x20];
+ u8 match_dw_8[0x20];
+ u8 match_dw_7[0x20];
+ u8 match_dw_6[0x20];
+ u8 match_dw_5[0x20];
+ u8 match_dw_4[0x20];
+ u8 match_dw_3[0x20];
+ u8 match_dw_2[0x20];
+ u8 match_dw_1[0x20];
+ u8 match_dw_0[0x20];
+
+ u8 match_byte_7[0x8];
+ u8 match_byte_6[0x8];
+ u8 match_byte_5[0x8];
+ u8 match_byte_4[0x8];
+
+ u8 match_byte_3[0x8];
+ u8 match_byte_2[0x8];
+ u8 match_byte_1[0x8];
+ u8 match_byte_0[0x8];
+};
+
struct mlx5_ifc_match_definer_bits {
u8 modify_field_select[0x40];
u8 reserved_at_80[0x10];
u8 format_id[0x10];
- u8 reserved_at_a0[0x160];
+ u8 reserved_at_a0[0x60];
+
+ u8 format_select_dw3[0x8];
+ u8 format_select_dw2[0x8];
+ u8 format_select_dw1[0x8];
+ u8 format_select_dw0[0x8];
+
+ u8 format_select_dw7[0x8];
+ u8 format_select_dw6[0x8];
+ u8 format_select_dw5[0x8];
+ u8 format_select_dw4[0x8];
+
+ u8 reserved_at_100[0x18];
+ u8 format_select_dw8[0x8];
+
+ u8 reserved_at_120[0x20];
+
+ u8 format_select_byte3[0x8];
+ u8 format_select_byte2[0x8];
+ u8 format_select_byte1[0x8];
+ u8 format_select_byte0[0x8];
+
+ u8 format_select_byte7[0x8];
+ u8 format_select_byte6[0x8];
+ u8 format_select_byte5[0x8];
+ u8 format_select_byte4[0x8];
+
+ u8 reserved_at_180[0x40];
- u8 match_mask[16][0x20];
+ union {
+ struct {
+ u8 match_mask[16][0x20];
+ };
+ struct mlx5_ifc_match_definer_match_mask_bits match_mask_format;
+ };
};
struct mlx5_ifc_general_obj_in_cmd_hdr_bits {
MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL = 0x2,
MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2 = 0x3,
MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL = 0x4,
+ MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV4 = 0x5,
+ MLX5_REFORMAT_TYPE_DEL_ESP_TRANSPORT = 0x8,
+ MLX5_REFORMAT_TYPE_ADD_ESP_TRANSPORT_OVER_IPV6 = 0xb,
MLX5_REFORMAT_TYPE_INSERT_HDR = 0xf,
MLX5_REFORMAT_TYPE_REMOVE_HDR = 0x10,
MLX5_REFORMAT_TYPE_ADD_MACSEC = 0x11,
MLX5_IPSEC_OBJECT_ICV_LEN_16B,
};
+enum {
+ MLX5_IPSEC_ASO_REG_C_0_1 = 0x0,
+ MLX5_IPSEC_ASO_REG_C_2_3 = 0x1,
+ MLX5_IPSEC_ASO_REG_C_4_5 = 0x2,
+ MLX5_IPSEC_ASO_REG_C_6_7 = 0x3,
+};
+
+enum {
+ MLX5_IPSEC_ASO_MODE = 0x0,
+ MLX5_IPSEC_ASO_REPLAY_PROTECTION = 0x1,
+ MLX5_IPSEC_ASO_INC_SN = 0x2,
+};
+
+struct mlx5_ifc_ipsec_aso_bits {
+ u8 valid[0x1];
+ u8 reserved_at_201[0x1];
+ u8 mode[0x2];
+ u8 window_sz[0x2];
+ u8 soft_lft_arm[0x1];
+ u8 hard_lft_arm[0x1];
+ u8 remove_flow_enable[0x1];
+ u8 esn_event_arm[0x1];
+ u8 reserved_at_20a[0x16];
+
+ u8 remove_flow_pkt_cnt[0x20];
+
+ u8 remove_flow_soft_lft[0x20];
+
+ u8 reserved_at_260[0x80];
+
+ u8 mode_parameter[0x20];
+
+ u8 replay_protection_window[0x100];
+};
+
struct mlx5_ifc_ipsec_obj_bits {
u8 modify_field_select[0x40];
u8 full_offload[0x1];
u8 implicit_iv[0x40];
- u8 reserved_at_100[0x700];
+ u8 reserved_at_100[0x8];
+ u8 ipsec_aso_access_pd[0x18];
+ u8 reserved_at_120[0xe0];
+
+ struct mlx5_ifc_ipsec_aso_bits ipsec_aso;
};
struct mlx5_ifc_create_ipsec_obj_in_bits {
u8 reserved_at_20[0x10];
u8 op_mod[0x10];
- u8 reserved_at_40[0x10];
+ u8 incremental[0x1];
+ u8 reserved_at_41[0xf];
u8 vhca_id[0x10];
u8 reserved_at_60[0x20];
u8 reserved_at_20[0x10];
u8 op_mod[0x10];
- u8 reserved_at_40[0x10];
+ u8 incremental[0x1];
+ u8 set_track[0x1];
+ u8 reserved_at_42[0xe];
u8 vhca_id[0x10];
u8 reserved_at_60[0x20];
#include <linux/iova_bitmap.h>
struct kvm;
+struct iommufd_ctx;
+struct iommufd_device;
+struct iommufd_access;
/*
* VFIO devices can be placed in a set, this allows all devices to share this
struct completion comp;
struct list_head group_next;
struct list_head iommu_entry;
+ struct iommufd_access *iommufd_access;
+#if IS_ENABLED(CONFIG_IOMMUFD)
+ struct iommufd_device *iommufd_device;
+ struct iommufd_ctx *iommufd_ictx;
+ bool iommufd_attached;
+#endif
};
/**
char *name;
int (*init)(struct vfio_device *vdev);
void (*release)(struct vfio_device *vdev);
+ int (*bind_iommufd)(struct vfio_device *vdev,
+ struct iommufd_ctx *ictx, u32 *out_device_id);
+ void (*unbind_iommufd)(struct vfio_device *vdev);
+ int (*attach_ioas)(struct vfio_device *vdev, u32 *pt_id);
int (*open_device)(struct vfio_device *vdev);
void (*close_device)(struct vfio_device *vdev);
ssize_t (*read)(struct vfio_device *vdev, char __user *buf,
void __user *arg, size_t argsz);
};
+#if IS_ENABLED(CONFIG_IOMMUFD)
+int vfio_iommufd_physical_bind(struct vfio_device *vdev,
+ struct iommufd_ctx *ictx, u32 *out_device_id);
+void vfio_iommufd_physical_unbind(struct vfio_device *vdev);
+int vfio_iommufd_physical_attach_ioas(struct vfio_device *vdev, u32 *pt_id);
+int vfio_iommufd_emulated_bind(struct vfio_device *vdev,
+ struct iommufd_ctx *ictx, u32 *out_device_id);
+void vfio_iommufd_emulated_unbind(struct vfio_device *vdev);
+int vfio_iommufd_emulated_attach_ioas(struct vfio_device *vdev, u32 *pt_id);
+#else
+#define vfio_iommufd_physical_bind \
+ ((int (*)(struct vfio_device *vdev, struct iommufd_ctx *ictx, \
+ u32 *out_device_id)) NULL)
+#define vfio_iommufd_physical_unbind \
+ ((void (*)(struct vfio_device *vdev)) NULL)
+#define vfio_iommufd_physical_attach_ioas \
+ ((int (*)(struct vfio_device *vdev, u32 *pt_id)) NULL)
+#define vfio_iommufd_emulated_bind \
+ ((int (*)(struct vfio_device *vdev, struct iommufd_ctx *ictx, \
+ u32 *out_device_id)) NULL)
+#define vfio_iommufd_emulated_unbind \
+ ((void (*)(struct vfio_device *vdev)) NULL)
+#define vfio_iommufd_emulated_attach_ioas \
+ ((int (*)(struct vfio_device *vdev, u32 *pt_id)) NULL)
+#endif
+
/**
* @migration_set_state: Optional callback to change the migration state for
* devices that support migration. It's mandatory for
* @migration_get_state: Optional callback to get the migration state for
* devices that support migration. It's mandatory for
* VFIO_DEVICE_FEATURE_MIGRATION migration support.
+ * @migration_get_data_size: Optional callback to get the estimated data
+ * length that will be required to complete stop copy. It's mandatory for
+ * VFIO_DEVICE_FEATURE_MIGRATION migration support.
*/
struct vfio_migration_ops {
struct file *(*migration_set_state)(
enum vfio_device_mig_state new_state);
int (*migration_get_state)(struct vfio_device *device,
enum vfio_device_mig_state *curr_state);
+ int (*migration_get_data_size)(struct vfio_device *device,
+ unsigned long *stop_copy_length);
};
/**
dev, ops), \
struct dev_struct, member)
- int vfio_init_device(struct vfio_device *device, struct device *dev,
- const struct vfio_device_ops *ops);
- void vfio_free_device(struct vfio_device *device);
static inline void vfio_put_device(struct vfio_device *device)
{
put_device(&device->device);
void vfio_unregister_group_dev(struct vfio_device *device);
int vfio_assign_device_set(struct vfio_device *device, void *set_id);
+unsigned int vfio_device_set_open_count(struct vfio_device_set *dev_set);
int vfio_mig_get_next_state(struct vfio_device *device,
enum vfio_device_mig_state cur_fsm,
int num_irqs, int max_irq_type,
size_t *data_size);
- struct pci_dev;
- #if IS_ENABLED(CONFIG_VFIO_SPAPR_EEH)
- void vfio_spapr_pci_eeh_open(struct pci_dev *pdev);
- void vfio_spapr_pci_eeh_release(struct pci_dev *pdev);
- long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group, unsigned int cmd,
- unsigned long arg);
- #else
- static inline void vfio_spapr_pci_eeh_open(struct pci_dev *pdev)
- {
- }
-
- static inline void vfio_spapr_pci_eeh_release(struct pci_dev *pdev)
- {
- }
-
- static inline long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
- unsigned int cmd,
- unsigned long arg)
- {
- return -ENOTTY;
- }
- #endif /* CONFIG_VFIO_SPAPR_EEH */
-
/*
* IRQfd - generic
*/
projects / J-linux.git / commitdiff