The following commit has been merged in the master branch: commit b60b0b3ece4e405498b49d668f67195de3c91760 Merge: afcfd7b1c8ce1b9c9f1e2fad554fbe6943afff2c ad7b134f65385627ebe9b3162a652267c8d991ee Author: Stephen Rothwell sfr@canb.auug.org.au Date: Mon Jul 8 13:06:47 2019 +1000

Merge remote-tracking branch 'net-next/master'

diff --combined MAINTAINERS index 0d589af5a8aa,449e7cdb3303..43426fe42f18 --- a/MAINTAINERS +++ b/MAINTAINERS @@@ -321,7 -321,7 +321,7 @@@ F: drivers/pnp/pnpacpi F: include/linux/acpi.h F: include/linux/fwnode.h F: include/acpi/ -F: Documentation/acpi/ +F: Documentation/firmware-guide/acpi/ F: Documentation/ABI/testing/sysfs-bus-acpi F: Documentation/ABI/testing/configfs-acpi F: drivers/pci/*acpi* @@@ -668,13 -668,6 +668,13 @@@ S: Maintaine F: Documentation/i2c/busses/i2c-ali1563 F: drivers/i2c/busses/i2c-ali1563.c

+ALLEGRO DVT VIDEO IP CORE DRIVER +M: Michael Tretter m.tretter@pengutronix.de +R: Pengutronix Kernel Team kernel@pengutronix.de +L: linux-media@vger.kernel.org +S: Maintained +F: drivers/staging/media/allegro-dvt/ + ALLWINNER SECURITY SYSTEM M: Corentin Labbe clabbe.montjoie@gmail.com L: linux-crypto@vger.kernel.org @@@ -917,7 -910,7 +917,7 @@@ F: drivers/iio/adc/ad7768-1. F: Documentation/devicetree/bindings/iio/adc/adi,ad7768-1.txt

ANALOG DEVICES INC AD9389B DRIVER -M: Hans Verkuil hans.verkuil@cisco.com +M: Hans Verkuil hverkuil-cisco@xs4all.nl L: linux-media@vger.kernel.org S: Maintained F: drivers/media/i2c/ad9389b* @@@ -949,19 -942,19 +949,19 @@@ S: Maintaine F: drivers/media/i2c/adv748x/*

ANALOG DEVICES INC ADV7511 DRIVER -M: Hans Verkuil hans.verkuil@cisco.com +M: Hans Verkuil hverkuil-cisco@xs4all.nl L: linux-media@vger.kernel.org S: Maintained F: drivers/media/i2c/adv7511*

ANALOG DEVICES INC ADV7604 DRIVER -M: Hans Verkuil hans.verkuil@cisco.com +M: Hans Verkuil hverkuil-cisco@xs4all.nl L: linux-media@vger.kernel.org S: Maintained F: drivers/media/i2c/adv7604*

ANALOG DEVICES INC ADV7842 DRIVER -M: Hans Verkuil hans.verkuil@cisco.com +M: Hans Verkuil hverkuil-cisco@xs4all.nl L: linux-media@vger.kernel.org S: Maintained F: drivers/media/i2c/adv7842* @@@ -1147,6 -1140,15 +1147,15 @@@ L: linux-media@vger.kernel.or S: Maintained F: drivers/media/i2c/aptina-pll.*

+ AQUANTIA ETHERNET DRIVER (atlantic) + M: Igor Russkikh igor.russkikh@aquantia.com + L: netdev@vger.kernel.org + S: Supported + W: http://www.aquantia.com + Q: http://patchwork.ozlabs.org/project/netdev/list/ + F: drivers/net/ethernet/aquantia/atlantic/ + F: Documentation/networking/device_drivers/aquantia/atlantic.txt + ARC FRAMEBUFFER DRIVER M: Jaya Kumar jayalk@intworks.biz S: Maintained @@@ -1238,7 -1240,7 +1247,7 @@@ F: include/uapi/drm/panfrost_drm. ARM MFM AND FLOPPY DRIVERS M: Ian Molton spyro@f2s.com S: Maintained -F: arch/arm/lib/floppydma.S +F: arch/arm/mach-rpc/floppydma.S F: arch/arm/include/asm/floppy.h

ARM PMU PROFILING AND DEBUGGING @@@ -1831,7 -1833,6 +1840,7 @@@ F: arch/arm/mach-orion5x F: arch/arm/plat-orion/ F: arch/arm/boot/dts/dove* F: arch/arm/boot/dts/orion5x* +T: git git://git.infradead.org/linux-mvebu.git

ARM/Marvell Kirkwood and Armada 370, 375, 38x, 39x, XP, 3700, 7K/8K SOC support M: Jason Cooper jason@lakedaemon.net @@@ -1852,7 -1853,6 +1861,7 @@@ F: drivers/irqchip/irq-armada-370-xp. F: drivers/irqchip/irq-mvebu-* F: drivers/pinctrl/mvebu/ F: drivers/rtc/rtc-armada38x.c +T: git git://git.infradead.org/linux-mvebu.git

ARM/Mediatek RTC DRIVER M: Eddie Huang eddie.huang@mediatek.com @@@ -2059,6 -2059,7 +2068,6 @@@ S: Maintaine

ARM/QUALCOMM SUPPORT M: Andy Gross agross@kernel.org -M: David Brown david.brown@linaro.org L: linux-arm-msm@vger.kernel.org S: Maintained F: Documentation/devicetree/bindings/soc/qcom/ @@@ -2080,7 -2081,7 +2089,7 @@@ F: drivers/i2c/busses/i2c-qup. F: drivers/i2c/busses/i2c-qcom-geni.c F: drivers/mfd/ssbi.c F: drivers/mmc/host/mmci_qcom* -F: drivers/mmc/host/sdhci_msm.c +F: drivers/mmc/host/sdhci-msm.c F: drivers/pci/controller/dwc/pcie-qcom.c F: drivers/phy/qualcomm/ F: drivers/power/*/msm* @@@ -2352,7 -2353,7 +2361,7 @@@ L: linux-arm-kernel@lists.infradead.or S: Maintained

ARM/TEGRA HDMI CEC SUBSYSTEM SUPPORT -M: Hans Verkuil hans.verkuil@cisco.com +M: Hans Verkuil hverkuil-cisco@xs4all.nl L: linux-tegra@vger.kernel.org L: linux-media@vger.kernel.org S: Maintained @@@ -3687,7 -3688,7 +3696,7 @@@ F: drivers/crypto/ccree W: https://developer.arm.com/products/system-ip/trustzone-cryptocell/cryptocell...

CEC FRAMEWORK -M: Hans Verkuil hans.verkuil@cisco.com +M: Hans Verkuil hverkuil-cisco@xs4all.nl L: linux-media@vger.kernel.org T: git git://linuxtv.org/media_tree.git W: http://linuxtv.org @@@ -3704,7 -3705,7 +3713,7 @@@ F: Documentation/devicetree/bindings/me F: Documentation/ABI/testing/debugfs-cec-error-inj

CEC GPIO DRIVER -M: Hans Verkuil hans.verkuil@cisco.com +M: Hans Verkuil hverkuil-cisco@xs4all.nl L: linux-media@vger.kernel.org T: git git://linuxtv.org/media_tree.git W: http://linuxtv.org @@@ -3896,7 -3897,7 +3905,7 @@@ F: Documentation/devicetree/bindings/hw F: Documentation/devicetree/bindings/pinctrl/cirrus,lochnagar.txt F: Documentation/devicetree/bindings/regulator/cirrus,lochnagar.txt F: Documentation/devicetree/bindings/sound/cirrus,lochnagar.txt -F: Documentation/hwmon/lochnagar +F: Documentation/hwmon/lochnagar.rst

CISCO FCOE HBA DRIVER M: Satish Kharat satishkh@cisco.com @@@ -3950,14 -3951,6 +3959,14 @@@ M: Miguel Ojeda <miguel.ojeda.sandonis@ S: Maintained F: .clang-format

+CLANG/LLVM BUILD SUPPORT +L: clang-built-linux@googlegroups.com +W: https://clangbuiltlinux.github.io/ +B: https://github.com/ClangBuiltLinux/linux/issues +C: irc://chat.freenode.net/clangbuiltlinux +S: Supported +K: \b(?i:clang|llvm)\b + CLEANCACHE API M: Konrad Rzeszutek Wilk konrad.wilk@oracle.com L: linux-kernel@vger.kernel.org @@@ -3988,7 -3981,7 +3997,7 @@@ S: Supporte F: drivers/platform/x86/classmate-laptop.c

COBALT MEDIA DRIVER -M: Hans Verkuil hans.verkuil@cisco.com +M: Hans Verkuil hverkuil-cisco@xs4all.nl L: linux-media@vger.kernel.org T: git git://linuxtv.org/media_tree.git W: https://linuxtv.org @@@ -4807,7 -4800,7 +4816,7 @@@ S: Maintaine W: http://plugable.com/category/projects/udlfb/ F: drivers/video/fbdev/udlfb.c F: include/video/udlfb.h -F: Documentation/fb/udlfb.txt +F: Documentation/fb/udlfb.rst

DISTRIBUTED LOCK MANAGER (DLM) M: Christine Caulfield ccaulfie@redhat.com @@@ -4880,7 -4873,7 +4889,7 @@@ S: Maintaine F: Documentation/ F: scripts/kernel-doc X: Documentation/ABI/ -X: Documentation/acpi/ +X: Documentation/firmware-guide/acpi/ X: Documentation/devicetree/ X: Documentation/i2c/ X: Documentation/media/ @@@ -4940,13 -4933,6 +4949,6 @@@ L: linux-kernel@vger.kernel.or S: Maintained F: drivers/staging/fsl-dpaa2/ethsw

- DPAA2 PTP CLOCK DRIVER - M: Yangbo Lu yangbo.lu@nxp.com - L: netdev@vger.kernel.org - S: Maintained - F: drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp* - F: drivers/net/ethernet/freescale/dpaa2/dprtc* - DPT_I2O SCSI RAID DRIVER M: Adaptec OEM Raid Solutions aacraid@microsemi.com L: linux-scsi@vger.kernel.org @@@ -5618,7 -5604,8 +5620,8 @@@ F: include/linux/dynamic_debug. DYNAMIC INTERRUPT MODERATION M: Tal Gilboa talgi@mellanox.com S: Maintained - F: include/linux/net_dim.h + F: include/linux/dim.h + F: lib/dim/

DZ DECSTATION DZ11 SERIAL DRIVER M: "Maciej W. Rozycki" macro@linux-mips.org @@@ -6050,7 -6037,7 +6053,7 @@@ S: Maintaine F: drivers/extcon/ F: include/linux/extcon/ F: include/linux/extcon.h -F: Documentation/extcon/ +F: Documentation/firmware-guide/acpi/extcon-intel-int3496.rst F: Documentation/devicetree/bindings/extcon/

EXYNOS DP DRIVER @@@ -6268,7 -6255,7 +6271,7 @@@ FPGA DFL DRIVER M: Wu Hao hao.wu@intel.com L: linux-fpga@vger.kernel.org S: Maintained -F: Documentation/fpga/dfl.txt +F: Documentation/fpga/dfl.rst F: include/uapi/linux/fpga-dfl.h F: drivers/fpga/dfl*

@@@ -6345,13 -6332,6 +6348,13 @@@ L: linux-i2c@vger.kernel.or S: Maintained F: drivers/i2c/busses/i2c-cpm.c

+FREESCALE IMX DDR PMU DRIVER +M: Frank Li Frank.li@nxp.com +L: linux-arm-kernel@lists.infradead.org +S: Maintained +F: drivers/perf/fsl_imx8_ddr_perf.c +F: Documentation/devicetree/bindings/perf/fsl-imx-ddr.txt + FREESCALE IMX LPI2C DRIVER M: Dong Aisheng aisheng.dong@nxp.com L: linux-i2c@vger.kernel.org @@@ -6395,6 -6375,8 +6398,8 @@@ FREESCALE QORIQ PTP CLOCK DRIVE M: Yangbo Lu yangbo.lu@nxp.com L: netdev@vger.kernel.org S: Maintained + F: drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp* + F: drivers/net/ethernet/freescale/dpaa2/dprtc* F: drivers/net/ethernet/freescale/enetc/enetc_ptp.c F: drivers/ptp/ptp_qoriq.c F: drivers/ptp/ptp_qoriq_debugfs.c @@@ -6440,7 -6422,6 +6445,7 @@@ M: Li Yang <leoyang.li@nxp.com L: linuxppc-dev@lists.ozlabs.org L: linux-arm-kernel@lists.infradead.org S: Maintained +F: Documentation/devicetree/bindings/misc/fsl,dpaa2-console.txt F: Documentation/devicetree/bindings/soc/fsl/ F: drivers/soc/fsl/ F: include/linux/fsl/ @@@ -6483,7 -6464,7 +6488,7 @@@ M: "Rafael J. Wysocki" <rjw@rjwysocki.n M: Pavel Machek pavel@ucw.cz L: linux-pm@vger.kernel.org S: Supported -F: Documentation/power/freezing-of-tasks.txt +F: Documentation/power/freezing-of-tasks.rst F: include/linux/freezer.h F: kernel/freezer.c

@@@ -6716,9 -6697,7 +6721,7 @@@ M: Paul Bolle <pebolle@tiscali.nl L: gigaset307x-common@lists.sourceforge.net W: http://gigaset307x.sourceforge.net/ S: Odd Fixes - F: Documentation/isdn/README.gigaset - F: drivers/isdn/gigaset/ - F: include/uapi/linux/gigaset_dev.h + F: drivers/staging/isdn/gigaset/

GNSS SUBSYSTEM M: Johan Hovold johan@kernel.org @@@ -6730,7 -6709,7 +6733,7 @@@ F: drivers/gnss F: include/linux/gnss.h

GO7007 MPEG CODEC -M: Hans Verkuil hans.verkuil@cisco.com +M: Hans Verkuil hverkuil-cisco@xs4all.nl L: linux-media@vger.kernel.org S: Maintained F: drivers/media/usb/go7007/ @@@ -6741,6 -6720,15 +6744,15 @@@ L: linux-input@vger.kernel.or S: Maintained F: drivers/input/touchscreen/goodix.c

+ GOOGLE ETHERNET DRIVERS + M: Catherine Sullivan csully@google.com + R: Sagi Shahar sagis@google.com + R: Jon Olson jonolson@google.com + L: netdev@vger.kernel.org + S: Supported + F: Documentation/networking/device_drivers/google/gve.txt + F: drivers/net/ethernet/google + GPD POCKET FAN DRIVER M: Hans de Goede hdegoede@redhat.com L: platform-driver-x86@vger.kernel.org @@@ -7034,7 -7022,7 +7046,7 @@@ F: drivers/media/usb/hdpvr HEWLETT PACKARD ENTERPRISE ILO NMI WATCHDOG DRIVER M: Jerry Hoemann jerry.hoemann@hpe.com S: Supported -F: Documentation/watchdog/hpwdt.txt +F: Documentation/watchdog/hpwdt.rst F: drivers/watchdog/hpwdt.c

HEWLETT-PACKARD SMART ARRAY RAID DRIVER (hpsa) @@@ -7217,7 -7205,7 +7229,7 @@@ F: drivers/net/ethernet/hp/hp100. HPET: High Precision Event Timers driver M: Clemens Ladisch clemens@ladisch.de S: Maintained -F: Documentation/timers/hpet.txt +F: Documentation/timers/hpet.rst F: drivers/char/hpet.c F: include/linux/hpet.h F: include/uapi/linux/hpet.h @@@ -7635,7 -7623,7 +7647,7 @@@ IDE/ATAPI DRIVER M: Borislav Petkov bp@alien8.de L: linux-ide@vger.kernel.org S: Maintained -F: Documentation/cdrom/ide-cd +F: Documentation/cdrom/ide-cd.rst F: drivers/ide/ide-cd*

IDEAPAD LAPTOP EXTRAS DRIVER @@@ -7826,34 -7814,7 +7838,34 @@@ INGENIC JZ4780 NAND DRIVE M: Harvey Hunt harveyhuntnexus@gmail.com L: linux-mtd@lists.infradead.org S: Maintained -F: drivers/mtd/nand/raw/jz4780_* +F: drivers/mtd/nand/raw/ingenic/ + +INGENIC JZ47xx SoCs +M: Paul Cercueil paul@crapouillou.net +S: Maintained +F: arch/mips/boot/dts/ingenic/ +F: arch/mips/include/asm/mach-jz4740/ +F: arch/mips/jz4740/ +F: drivers/clk/ingenic/ +F: drivers/dma/dma-jz4780.c +F: drivers/gpu/drm/ingenic/ +F: drivers/i2c/busses/i2c-jz4780.c +F: drivers/iio/adc/ingenic-adc.c +F: drivers/irqchip/irq-ingenic.c +F: drivers/memory/jz4780-nemc.c +F: drivers/mmc/host/jz4740_mmc.c +F: drivers/mtd/nand/raw/ingenic/ +F: drivers/pinctrl/pinctrl-ingenic.c +F: drivers/power/supply/ingenic-battery.c +F: drivers/pwm/pwm-jz4740.c +F: drivers/rtc/rtc-jz4740.c +F: drivers/tty/serial/8250/8250_ingenic.c +F: drivers/usb/musb/jz4740.c +F: drivers/watchdog/jz4740_wdt.c +F: include/dt-bindings/iio/adc/ingenic,adc.h +F: include/linux/mfd/ingenic-tcu.h +F: sound/soc/jz4740/ +F: sound/soc/codecs/jz47*

INOTIFY M: Jan Kara jack@suse.cz @@@ -7975,7 -7936,7 +7987,7 @@@ INTEL FRAMEBUFFER DRIVER (excluding 81 M: Maik Broemme mbroemme@libmpq.org L: linux-fbdev@vger.kernel.org S: Maintained -F: Documentation/fb/intelfb.txt +F: Documentation/fb/intelfb.rst F: drivers/video/fbdev/intelfb/

INTEL GPIO DRIVERS @@@ -8427,18 -8388,26 +8439,26 @@@ S: Supporte W: http://www.linux-iscsi.org F: drivers/infiniband/ulp/isert

- ISDN SUBSYSTEM + ISDN/mISDN SUBSYSTEM M: Karsten Keil isdn@linux-pingi.de L: isdn4linux@listserv.isdn4linux.de (subscribers-only) L: netdev@vger.kernel.org W: http://www.isdn4linux.de - T: git git://git.kernel.org/pub/scm/linux/kernel/git/kkeil/isdn-2.6.git S: Maintained + F: drivers/isdn/mISDN + F: drivers/isdn/hardware + + ISDN/CAPI SUBSYSTEM + M: Karsten Keil isdn@linux-pingi.de + L: isdn4linux@listserv.isdn4linux.de (subscribers-only) + L: netdev@vger.kernel.org + W: http://www.isdn4linux.de + S: Odd Fixes F: Documentation/isdn/ - F: drivers/isdn/ - F: include/linux/isdn.h + F: drivers/isdn/capi/ + F: drivers/staging/isdn/ + F: net/bluetooth/cmtp/ F: include/linux/isdn/ - F: include/uapi/linux/isdn.h F: include/uapi/linux/isdn/

IT87 HARDWARE MONITORING DRIVER @@@ -9688,17 -9657,6 +9708,17 @@@ L: linux-iio@vger.kernel.or S: Maintained F: drivers/iio/dac/cio-dac.c

+MEDIA CONTROLLER FRAMEWORK +M: Sakari Ailus sakari.ailus@linux.intel.com +M: Laurent Pinchart laurent.pinchart@ideasonboard.com +L: linux-media@vger.kernel.org +W: https://www.linuxtv.org +T: git git://linuxtv.org/media_tree.git +S: Supported +F: drivers/media/mc/ +F: include/media/media-*.h +F: include/uapi/linux/media.h + MEDIA DRIVERS FOR ASCOT2E M: Sergey Kozlov serjk@netup.ru M: Abylay Ospan aospan@netup.ru @@@ -10020,13 -9978,6 +10040,13 @@@ L: linux-wireless@vger.kernel.or S: Maintained F: drivers/net/wireless/mediatek/mt7601u/

+MEDIATEK MT7621/28/88 I2C DRIVER +M: Stefan Roese sr@denx.de +L: linux-i2c@vger.kernel.org +S: Maintained +F: drivers/i2c/busses/i2c-mt7621.c +F: Documentation/devicetree/bindings/i2c/i2c-mt7621.txt + MEDIATEK NAND CONTROLLER DRIVER M: Xiaolei Li xiaolei.li@mediatek.com L: linux-mtd@lists.infradead.org @@@ -10172,6 -10123,7 +10192,7 @@@ Q: http://patchwork.ozlabs.org/project/ S: Supported F: drivers/net/ethernet/mellanox/mlx5/core/ F: include/linux/mlx5/ + F: Documentation/networking/device_drivers/mellanox/

MELLANOX MLX5 IB driver M: Leon Romanovsky leonro@mellanox.com @@@ -10282,7 -10234,7 +10303,7 @@@ F: drivers/watchdog/menz69_wdt.

MESON AO CEC DRIVER FOR AMLOGIC SOCS M: Neil Armstrong narmstrong@baylibre.com -L: linux-media@lists.freedesktop.org +L: linux-media@vger.kernel.org L: linux-amlogic@lists.infradead.org W: http://linux-meson.com/ S: Supported @@@ -10298,14 -10250,6 +10319,14 @@@ S: Maintaine F: drivers/mtd/nand/raw/meson_* F: Documentation/devicetree/bindings/mtd/amlogic,meson-nand.txt

+MESON VIDEO DECODER DRIVER FOR AMLOGIC SOCS +M: Maxime Jourdan mjourdan@baylibre.com +L: linux-media@vger.kernel.org +L: linux-amlogic@lists.infradead.org +S: Supported +F: drivers/staging/media/meson/vdec/ +T: git git://linuxtv.org/media_tree.git + METHODE UDPU SUPPORT M: Vladimir Vid vladimir.vid@sartura.hr S: Maintained @@@ -10359,9 -10303,7 +10380,9 @@@ MICROCHIP ISC DRIVE M: Eugen Hristev eugen.hristev@microchip.com L: linux-media@vger.kernel.org S: Supported -F: drivers/media/platform/atmel/atmel-isc.c +F: drivers/media/platform/atmel/atmel-sama5d2-isc.c +F: drivers/media/platform/atmel/atmel-isc.h +F: drivers/media/platform/atmel/atmel-isc-base.c F: drivers/media/platform/atmel/atmel-isc-regs.h F: Documentation/devicetree/bindings/media/atmel-isc.txt

@@@ -10921,6 -10863,14 +10942,6 @@@ F: driver/net/net_failover. F: include/net/net_failover.h F: Documentation/networking/net_failover.rst

-NETEFFECT IWARP RNIC DRIVER (IW_NES) -M: Faisal Latif faisal.latif@intel.com -L: linux-rdma@vger.kernel.org -W: http://www.intel.com/Products/Server/Adapters/Server-Cluster/Server-Cluster-... -S: Supported -F: drivers/infiniband/hw/nes/ -F: include/uapi/rdma/nes-abi.h - NETEM NETWORK EMULATOR M: Stephen Hemminger stephen@networkplumber.org L: netem@lists.linux-foundation.org (moderated for non-subscribers) @@@ -10937,7 -10887,7 +10958,7 @@@ F: drivers/net/ethernet/neterion

NETFILTER M: Pablo Neira Ayuso pablo@netfilter.org - M: Jozsef Kadlecsik kadlec@blackhole.kfki.hu + M: Jozsef Kadlecsik kadlec@netfilter.org M: Florian Westphal fw@strlen.de L: netfilter-devel@vger.kernel.org L: coreteam@netfilter.org @@@ -11150,6 -11100,15 +11171,15 @@@ L: netdev@vger.kernel.or S: Supported F: drivers/net/ethernet/qlogic/netxen/

+ NEXTHOP + M: David Ahern dsahern@kernel.org + L: netdev@vger.kernel.org + S: Maintained + F: include/net/nexthop.h + F: include/uapi/linux/nexthop.h + F: include/net/netns/nexthop.h + F: net/ipv4/nexthop.c + NFC SUBSYSTEM L: netdev@vger.kernel.org S: Orphan @@@ -11353,7 -11312,7 +11383,7 @@@ NXP FXAS21002C DRIVE M: Rui Miguel Silva rmfrfs@gmail.com L: linux-iio@vger.kernel.org S: Maintained -F: Documentation/devicetree/bindings/iio/gyroscope/fxas21002c.txt +F: Documentation/devicetree/bindings/iio/gyroscope/nxp,fxas21002c.txt F: drivers/iio/gyro/fxas21002c_core.c F: drivers/iio/gyro/fxas21002c.h F: drivers/iio/gyro/fxas21002c_i2c.c @@@ -11755,13 -11714,11 +11785,13 @@@ F: drivers/scsi/st.

OP-TEE DRIVER M: Jens Wiklander jens.wiklander@linaro.org +L: tee-dev@lists.linaro.org S: Maintained F: drivers/tee/optee/

OP-TEE RANDOM NUMBER GENERATOR (RNG) DRIVER M: Sumit Garg sumit.garg@linaro.org +L: tee-dev@lists.linaro.org S: Maintained F: drivers/char/hw_random/optee-rng.c

@@@ -11848,7 -11805,7 +11878,7 @@@ S: Maintaine T: git git://git.kernel.org/pub/scm/linux/kernel/git/vireshk/pm.git F: drivers/opp/ F: include/linux/pm_opp.h -F: Documentation/power/opp.txt +F: Documentation/power/opp.rst F: Documentation/devicetree/bindings/opp/

OPL4 DRIVER @@@ -12227,7 -12184,7 +12257,7 @@@ M: Sam Bobroff <sbobroff@linux.ibm.com M: Oliver O'Halloran oohall@gmail.com L: linuxppc-dev@lists.ozlabs.org S: Supported -F: Documentation/PCI/pci-error-recovery.txt +F: Documentation/PCI/pci-error-recovery.rst F: drivers/pci/pcie/aer.c F: drivers/pci/pcie/dpc.c F: drivers/pci/pcie/err.c @@@ -12240,7 -12197,7 +12270,7 @@@ PCI ERROR RECOVER M: Linas Vepstas linasvepstas@gmail.com L: linux-pci@vger.kernel.org S: Supported -F: Documentation/PCI/pci-error-recovery.txt +F: Documentation/PCI/pci-error-recovery.rst

PCI MSI DRIVER FOR ALTERA MSI IP M: Ley Foon Tan lftan@altera.com @@@ -12733,7 -12690,7 +12763,7 @@@ M: Rodolfo Giometti <giometti@enneenne. W: http://wiki.enneenne.com/index.php/LinuxPPS_support L: linuxpps@ml.enneenne.com (subscribers-only) S: Maintained -F: Documentation/pps/ +F: Documentation/driver-api/pps.rst F: Documentation/devicetree/bindings/pps/pps-gpio.txt F: Documentation/ABI/testing/sysfs-pps F: drivers/pps/ @@@ -12839,7 -12796,7 +12869,7 @@@ L: netdev@vger.kernel.or S: Maintained W: http://linuxptp.sourceforge.net/ F: Documentation/ABI/testing/sysfs-ptp -F: Documentation/ptp/* +F: Documentation/driver-api/ptp.rst F: drivers/net/phy/dp83640* F: drivers/ptp/* F: include/linux/ptp_cl* @@@ -12853,6 -12810,7 +12883,6 @@@ F: include/linux/regset. F: include/linux/tracehook.h F: include/uapi/linux/ptrace.h F: include/uapi/linux/ptrace.h -F: include/asm-generic/ptrace.h F: kernel/ptrace.c F: arch/*/ptrace*.c F: arch/*/*/ptrace*.c @@@ -13126,7 -13084,7 +13156,7 @@@ M: Niklas Cassel <niklas.cassel@linaro. L: netdev@vger.kernel.org S: Maintained F: drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c -F: Documentation/devicetree/bindings/net/qcom,dwmac.txt +F: Documentation/devicetree/bindings/net/qcom,ethqos.txt

QUALCOMM GENERIC INTERFACE I2C DRIVER M: Alok Chauhan alokc@codeaurora.org @@@ -13549,7 -13507,7 +13579,7 @@@ RISC-V ARCHITECTUR M: Palmer Dabbelt palmer@sifive.com M: Albert Ou aou@eecs.berkeley.edu L: linux-riscv@lists.infradead.org -T: git git://git.kernel.org/pub/scm/linux/kernel/git/palmer/riscv-linux.git +T: git git://git.kernel.org/pub/scm/linux/kernel/git/riscv/linux.git S: Supported F: arch/riscv/ K: riscv @@@ -13570,11 -13528,11 +13600,11 @@@ S: Maintaine F: drivers/media/platform/rockchip/rga/ F: Documentation/devicetree/bindings/media/rockchip-rga.txt

-ROCKCHIP VPU CODEC DRIVER +HANTRO VPU CODEC DRIVER M: Ezequiel Garcia ezequiel@collabora.com L: linux-media@vger.kernel.org S: Maintained -F: drivers/staging/media/platform/rockchip/vpu/ +F: drivers/staging/media/platform/hantro/ F: Documentation/devicetree/bindings/media/rockchip-vpu.txt

ROCKER DRIVER @@@ -13775,7 -13733,7 +13805,7 @@@ L: linux-s390@vger.kernel.or L: kvm@vger.kernel.org S: Supported F: drivers/s390/cio/vfio_ccw* -F: Documentation/s390/vfio-ccw.txt +F: Documentation/s390/vfio-ccw.rst F: include/uapi/linux/vfio_ccw.h

S390 ZCRYPT DRIVER @@@ -13795,7 -13753,7 +13825,7 @@@ S: Supporte F: drivers/s390/crypto/vfio_ap_drv.c F: drivers/s390/crypto/vfio_ap_private.h F: drivers/s390/crypto/vfio_ap_ops.c -F: Documentation/s390/vfio-ap.txt +F: Documentation/s390/vfio-ap.rst

S390 ZFCP DRIVER M: Steffen Maier maier@linux.ibm.com @@@ -14405,7 -14363,7 +14435,7 @@@ M: Paul Walmsley <paul.walmsley@sifive. L: linux-riscv@lists.infradead.org T: git git://github.com/sifive/riscv-linux.git S: Supported -K: sifive +K: [^@]sifive N: sifive

SIFIVE FU540 SYSTEM-ON-CHIP @@@ -14432,7 -14390,7 +14462,7 @@@ M: Sudip Mukherjee <sudip.mukherjee@cod L: linux-fbdev@vger.kernel.org S: Maintained F: drivers/video/fbdev/sm712* -F: Documentation/fb/sm712fb.txt +F: Documentation/fb/sm712fb.rst

SIMPLE FIRMWARE INTERFACE (SFI) M: Len Brown lenb@kernel.org @@@ -14502,7 -14460,7 +14532,7 @@@ SIS FRAMEBUFFER DRIVE M: Thomas Winischhofer thomas@winischhofer.net W: http://www.winischhofer.net/linuxsisvga.shtml S: Maintained -F: Documentation/fb/sisfb.txt +F: Documentation/fb/sisfb.rst F: drivers/video/fbdev/sis/ F: include/video/sisfb.h

@@@ -15538,7 -15496,6 +15568,7 @@@ F: include/media/i2c/tw9910.

TEE SUBSYSTEM M: Jens Wiklander jens.wiklander@linaro.org +L: tee-dev@lists.linaro.org S: Maintained F: include/linux/tee_drv.h F: include/uapi/linux/tee.h @@@ -15568,7 -15525,6 +15598,7 @@@ F: drivers/dma/tegra

TEGRA I2C DRIVER M: Laxman Dewangan ldewangan@nvidia.com +R: Dmitry Osipenko digetx@gmail.com S: Supported F: drivers/i2c/busses/i2c-tegra.c

@@@ -15694,7 -15650,7 +15724,7 @@@ M: Viresh Kumar <viresh.kumar@linaro.or M: Javi Merino javi.merino@kernel.org L: linux-pm@vger.kernel.org S: Supported -F: Documentation/thermal/cpu-cooling-api.txt +F: Documentation/thermal/cpu-cooling-api.rst F: drivers/thermal/cpu_cooling.c F: include/linux/cpu_cooling.h

@@@ -16393,7 -16349,7 +16423,7 @@@ M: Benjamin Tissoires <benjamin.tissoir L: linux-usb@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/hid/hid.git S: Maintained -F: Documentation/hid/hiddev.txt +F: Documentation/hid/hiddev.rst F: drivers/hid/usbhid/

USB INTEL XHCI ROLE MUX DRIVER @@@ -16692,7 -16648,7 +16722,7 @@@ M: Michal Januszewski <spock@gentoo.org L: linux-fbdev@vger.kernel.org W: https://github.com/mjanusz/v86d S: Maintained -F: Documentation/fb/uvesafb.txt +F: Documentation/fb/uvesafb.rst F: drivers/video/fbdev/uvesafb.*

VF610 NAND DRIVER @@@ -16767,7 -16723,7 +16797,7 @@@ S: Maintaine F: drivers/net/ethernet/via/via-velocity.*

VICODEC VIRTUAL CODEC DRIVER -M: Hans Verkuil hans.verkuil@cisco.com +M: Hans Verkuil hverkuil-cisco@xs4all.nl L: linux-media@vger.kernel.org T: git git://linuxtv.org/media_tree.git W: https://linuxtv.org @@@ -16790,7 -16746,6 +16820,7 @@@ VIDEOBUF2 FRAMEWOR M: Pawel Osciak pawel@osciak.com M: Marek Szyprowski m.szyprowski@samsung.com M: Kyungmin Park kyungmin.park@samsung.com +R: Tomasz Figa tfiga@chromium.org L: linux-media@vger.kernel.org S: Maintained F: drivers/media/common/videobuf2/* @@@ -17349,7 -17304,6 +17379,7 @@@ N: xd XDP SOCKETS (AF_XDP) M: Björn Töpel bjorn.topel@intel.com M: Magnus Karlsson magnus.karlsson@intel.com +R: Jonathan Lemon jonathan.lemon@gmail.com L: netdev@vger.kernel.org L: bpf@vger.kernel.org S: Maintained @@@ -17443,13 -17397,7 +17473,13 @@@ W: http://xfs.org T: git git://git.kernel.org/pub/scm/fs/xfs/xfs-linux.git S: Supported F: Documentation/filesystems/xfs.txt +F: Documentation/ABI/testing/sysfs-fs-xfs +F: Documentation/filesystems/xfs.txt +F: Documentation/filesystems/xfs-delayed-logging-design.txt +F: Documentation/filesystems/xfs-self-describing-metadata.txt F: fs/xfs/ +F: include/uapi/linux/dqblk_xfs.h +F: include/uapi/linux/fsmap.h

XILINX AXI ETHERNET DRIVER M: Anirudha Sarangi anirudh@xilinx.com diff --combined arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi index e83c080acc8b,22a1c74dddf3..7975519b4f56 --- a/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi +++ b/arch/arm64/boot/dts/freescale/fsl-ls1028a.dtsi @@@ -70,27 -70,6 +70,27 @@@ clock-output-names = "sysclk"; };

+ dpclk: clock-dp { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <27000000>; + clock-output-names= "dpclk"; + }; + + aclk: clock-axi { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <650000000>; + clock-output-names= "aclk"; + }; + + pclk: clock-apb { + compatible = "fixed-clock"; + #clock-cells = <0>; + clock-frequency = <650000000>; + clock-output-names= "pclk"; + }; + reboot { compatible ="syscon-reboot"; regmap = <&dcfg>; @@@ -306,24 -285,13 +306,24 @@@ #interrupt-cells = <2>; };

- wdog0: watchdog@23c0000 { - compatible = "fsl,ls1028a-wdt", "fsl,imx21-wdt"; - reg = <0x0 0x23c0000 0x0 0x10000>; - interrupts = <GIC_SPI 59 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&clockgen 4 1>; - big-endian; - status = "disabled"; + usb0: usb@3100000 { + compatible = "fsl,ls1028a-dwc3", "snps,dwc3"; + reg = <0x0 0x3100000 0x0 0x10000>; + interrupts = <GIC_SPI 80 IRQ_TYPE_LEVEL_HIGH>; + dr_mode = "host"; + snps,dis_rxdet_inp3_quirk; + snps,quirk-frame-length-adjustment = <0x20>; + snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>; + }; + + usb1: usb@3110000 { + compatible = "fsl,ls1028a-dwc3", "snps,dwc3"; + reg = <0x0 0x3110000 0x0 0x10000>; + interrupts = <GIC_SPI 81 IRQ_TYPE_LEVEL_HIGH>; + dr_mode = "host"; + snps,dis_rxdet_inp3_quirk; + snps,quirk-frame-length-adjustment = <0x20>; + snps,incr-burst-type-adjustment = <1>, <4>, <8>, <16>; };

sata: sata@3200000 { @@@ -388,79 -356,6 +388,79 @@@ <GIC_SPI 208 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 209 IRQ_TYPE_LEVEL_HIGH>; };

+ crypto: crypto@8000000 { + compatible = "fsl,sec-v5.0", "fsl,sec-v4.0"; + fsl,sec-era = <10>; + #address-cells = <1>; + #size-cells = <1>; + ranges = <0x0 0x00 0x8000000 0x100000>; + reg = <0x00 0x8000000 0x0 0x100000>; + interrupts = <GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>; + dma-coherent; + + sec_jr0: jr@10000 { + compatible = "fsl,sec-v5.0-job-ring", + "fsl,sec-v4.0-job-ring"; + reg = <0x10000 0x10000>; + interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>; + }; + + sec_jr1: jr@20000 { + compatible = "fsl,sec-v5.0-job-ring", + "fsl,sec-v4.0-job-ring"; + reg = <0x20000 0x10000>; + interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>; + }; + + sec_jr2: jr@30000 { + compatible = "fsl,sec-v5.0-job-ring", + "fsl,sec-v4.0-job-ring"; + reg = <0x30000 0x10000>; + interrupts = <GIC_SPI 142 IRQ_TYPE_LEVEL_HIGH>; + }; + + sec_jr3: jr@40000 { + compatible = "fsl,sec-v5.0-job-ring", + "fsl,sec-v4.0-job-ring"; + reg = <0x40000 0x10000>; + interrupts = <GIC_SPI 143 IRQ_TYPE_LEVEL_HIGH>; + }; + }; + + qdma: dma-controller@8380000 { + compatible = "fsl,ls1028a-qdma", "fsl,ls1021a-qdma"; + reg = <0x0 0x8380000 0x0 0x1000>, /* Controller regs */ + <0x0 0x8390000 0x0 0x10000>, /* Status regs */ + <0x0 0x83a0000 0x0 0x40000>; /* Block regs */ + interrupts = <GIC_SPI 43 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 251 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 252 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 253 IRQ_TYPE_LEVEL_HIGH>, + <GIC_SPI 254 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "qdma-error", "qdma-queue0", + "qdma-queue1", "qdma-queue2", "qdma-queue3"; + dma-channels = <8>; + block-number = <1>; + block-offset = <0x10000>; + fsl,dma-queues = <2>; + status-sizes = <64>; + queue-sizes = <64 64>; + }; + + cluster1_core0_watchdog: watchdog@c000000 { + compatible = "arm,sp805", "arm,primecell"; + reg = <0x0 0xc000000 0x0 0x1000>; + clocks = <&clockgen 4 15>, <&clockgen 4 15>; + clock-names = "apb_pclk", "wdog_clk"; + }; + + cluster1_core1_watchdog: watchdog@c010000 { + compatible = "arm,sp805", "arm,primecell"; + reg = <0x0 0xc010000 0x0 0x1000>; + clocks = <&clockgen 4 15>, <&clockgen 4 15>; + clock-names = "apb_pclk", "wdog_clk"; + }; + sai1: audio-controller@f100000 { #sound-dai-cells = <0>; compatible = "fsl,vf610-sai"; @@@ -536,23 -431,12 +536,29 @@@ compatible = "fsl,enetc"; reg = <0x000100 0 0 0 0>; }; + ethernet@0,4 { + compatible = "fsl,enetc-ptp"; + reg = <0x000400 0 0 0 0>; + clocks = <&clockgen 4 0>; + little-endian; + }; }; }; + + malidp0: display@f080000 { + compatible = "arm,mali-dp500"; + reg = <0x0 0xf080000 0x0 0x10000>; + interrupts = <0 222 IRQ_TYPE_LEVEL_HIGH>, + <0 223 IRQ_TYPE_LEVEL_HIGH>; + interrupt-names = "DE", "SE"; + clocks = <&dpclk>, <&aclk>, <&aclk>, <&pclk>; + clock-names = "pxlclk", "mclk", "aclk", "pclk"; + arm,malidp-output-port-lines = /bits/ 8 <8 8 8>; + + port { + dp0_out: endpoint { + + }; + }; + }; }; diff --combined arch/mips/configs/malta_defconfig index c9c4145c6fc0,0de92ac1ca64..59eedf55419d --- a/arch/mips/configs/malta_defconfig +++ b/arch/mips/configs/malta_defconfig @@@ -210,11 -210,11 +210,10 @@@ CONFIG_NET_ACT_NAT= CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m - CONFIG_NET_CLS_IND=y CONFIG_CFG80211=m CONFIG_MAC80211=m CONFIG_MAC80211_MESH=y CONFIG_RFKILL=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=m CONFIG_MTD=y diff --combined arch/mips/configs/malta_kvm_defconfig index 841f19adaec7,efc3abace048..8ef612552a19 --- a/arch/mips/configs/malta_kvm_defconfig +++ b/arch/mips/configs/malta_kvm_defconfig @@@ -215,11 -215,11 +215,10 @@@ CONFIG_NET_ACT_NAT= CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m - CONFIG_NET_CLS_IND=y CONFIG_CFG80211=m CONFIG_MAC80211=m CONFIG_MAC80211_MESH=y CONFIG_RFKILL=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=m CONFIG_MTD=y diff --combined arch/mips/configs/malta_kvm_guest_defconfig index 764ba62f7a5c,c6ceeca4394d..d2a008c9907c --- a/arch/mips/configs/malta_kvm_guest_defconfig +++ b/arch/mips/configs/malta_kvm_guest_defconfig @@@ -212,11 -212,11 +212,10 @@@ CONFIG_NET_ACT_NAT= CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m - CONFIG_NET_CLS_IND=y CONFIG_CFG80211=m CONFIG_MAC80211=m CONFIG_MAC80211_MESH=y CONFIG_RFKILL=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_CONNECTOR=m CONFIG_MTD=y diff --combined arch/mips/configs/maltaup_xpa_defconfig index de5bb1c9aeb8,56861aef2756..970df6d42728 --- a/arch/mips/configs/maltaup_xpa_defconfig +++ b/arch/mips/configs/maltaup_xpa_defconfig @@@ -212,11 -212,11 +212,10 @@@ CONFIG_NET_ACT_NAT= CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m - CONFIG_NET_CLS_IND=y CONFIG_CFG80211=m CONFIG_MAC80211=m CONFIG_MAC80211_MESH=y CONFIG_RFKILL=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEVTMPFS=y CONFIG_DEVTMPFS_MOUNT=y CONFIG_CONNECTOR=m diff --combined arch/mips/configs/rb532_defconfig index 97d96117e11a,864c70fbe668..5b947183852b --- a/arch/mips/configs/rb532_defconfig +++ b/arch/mips/configs/rb532_defconfig @@@ -103,8 -103,8 +103,7 @@@ CONFIG_GACT_PROB= CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_PEDIT=m - CONFIG_NET_CLS_IND=y CONFIG_HAMRADIO=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_BLOCK=y CONFIG_MTD_BLOCK2MTD=y diff --combined arch/powerpc/configs/ppc6xx_defconfig index 0e09c39afd52,aa51b9b66fa2..9dca4cffa623 --- a/arch/powerpc/configs/ppc6xx_defconfig +++ b/arch/powerpc/configs/ppc6xx_defconfig @@@ -301,7 -301,6 +301,6 @@@ CONFIG_NET_ACT_NAT= CONFIG_NET_ACT_PEDIT=m CONFIG_NET_ACT_SIMP=m CONFIG_NET_ACT_SKBEDIT=m - CONFIG_NET_CLS_IND=y CONFIG_IRDA=m CONFIG_IRLAN=m CONFIG_IRNET=m @@@ -346,6 -345,7 +345,6 @@@ CONFIG_MAC80211_LEDS= CONFIG_MAC80211_DEBUGFS=y CONFIG_NET_9P=m CONFIG_NET_9P_VIRTIO=m -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_DEBUG_DEVRES=y CONFIG_CONNECTOR=y CONFIG_PARPORT=m @@@ -1123,7 -1123,6 +1122,7 @@@ CONFIG_NLS_KOI8_R= CONFIG_NLS_KOI8_U=m CONFIG_DEBUG_INFO=y CONFIG_UNUSED_SYMBOLS=y +CONFIG_HEADERS_INSTALL=y CONFIG_HEADERS_CHECK=y CONFIG_MAGIC_SYSRQ=y CONFIG_DEBUG_KERNEL=y @@@ -1148,6 -1147,7 +1147,6 @@@ CONFIG_FAIL_MAKE_REQUEST= CONFIG_FAIL_IO_TIMEOUT=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y -CONFIG_LATENCYTOP=y CONFIG_SCHED_TRACER=y CONFIG_STACK_TRACER=y CONFIG_BLK_DEV_IO_TRACE=y diff --combined arch/sh/configs/se7712_defconfig index 6ac7d362e106,1e116529735f..9a527f978106 --- a/arch/sh/configs/se7712_defconfig +++ b/arch/sh/configs/se7712_defconfig @@@ -63,7 -63,7 +63,6 @@@ CONFIG_NET_SCH_NETEM= CONFIG_NET_CLS_TCINDEX=y CONFIG_NET_CLS_ROUTE4=y CONFIG_NET_CLS_FW=y - CONFIG_NET_CLS_IND=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y diff --combined arch/sh/configs/se7721_defconfig index ffd15acc2a04,c66e512719ab..3b0e1eb6e874 --- a/arch/sh/configs/se7721_defconfig +++ b/arch/sh/configs/se7721_defconfig @@@ -62,7 -62,7 +62,6 @@@ CONFIG_NET_SCH_NETEM= CONFIG_NET_CLS_TCINDEX=y CONFIG_NET_CLS_ROUTE4=y CONFIG_NET_CLS_FW=y - CONFIG_NET_CLS_IND=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_MTD=y CONFIG_MTD_BLOCK=y CONFIG_MTD_CFI=y diff --combined arch/sh/configs/titan_defconfig index 1c1c78e74fbb,171ab05ce4fc..4ec961ace688 --- a/arch/sh/configs/titan_defconfig +++ b/arch/sh/configs/titan_defconfig @@@ -142,7 -142,7 +142,6 @@@ CONFIG_GACT_PROB= CONFIG_NET_ACT_MIRRED=m CONFIG_NET_ACT_IPT=m CONFIG_NET_ACT_PEDIT=m - CONFIG_NET_CLS_IND=y -CONFIG_UEVENT_HELPER_PATH="/sbin/hotplug" CONFIG_FW_LOADER=m CONFIG_CONNECTOR=m CONFIG_MTD=m diff --combined arch/x86/net/bpf_jit_comp32.c index 1d12d2174085,133433d181ba..393d251798c0 --- a/arch/x86/net/bpf_jit_comp32.c +++ b/arch/x86/net/bpf_jit_comp32.c @@@ -253,13 -253,14 +253,14 @@@ static inline void emit_ia32_mov_r(cons /* dst = src */ static inline void emit_ia32_mov_r64(const bool is64, const u8 dst[], const u8 src[], bool dstk, - bool sstk, u8 **pprog) + bool sstk, u8 **pprog, + const struct bpf_prog_aux *aux) { emit_ia32_mov_r(dst_lo, src_lo, dstk, sstk, pprog); if (is64) /* complete 8 byte move */ emit_ia32_mov_r(dst_hi, src_hi, dstk, sstk, pprog); - else + else if (!aux->verifier_zext) /* zero out high 4 bytes */ emit_ia32_mov_i(dst_hi, 0, dstk, pprog); } @@@ -313,7 -314,8 +314,8 @@@ static inline void emit_ia32_mul_r(cons }

static inline void emit_ia32_to_le_r64(const u8 dst[], s32 val, - bool dstk, u8 **pprog) + bool dstk, u8 **pprog, + const struct bpf_prog_aux *aux) { u8 *prog = *pprog; int cnt = 0; @@@ -334,12 -336,14 +336,14 @@@ */ EMIT2(0x0F, 0xB7); EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo)); - /* xor dreg_hi,dreg_hi */ - EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + if (!aux->verifier_zext) + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); break; case 32: - /* xor dreg_hi,dreg_hi */ - EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + if (!aux->verifier_zext) + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); break; case 64: /* nop */ @@@ -358,7 -362,8 +362,8 @@@ }

static inline void emit_ia32_to_be_r64(const u8 dst[], s32 val, - bool dstk, u8 **pprog) + bool dstk, u8 **pprog, + const struct bpf_prog_aux *aux) { u8 *prog = *pprog; int cnt = 0; @@@ -380,16 -385,18 +385,18 @@@ EMIT2(0x0F, 0xB7); EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo));

- /* xor dreg_hi,dreg_hi */ - EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + if (!aux->verifier_zext) + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); break; case 32: /* Emit 'bswap eax' to swap lower 4 bytes */ EMIT1(0x0F); EMIT1(add_1reg(0xC8, dreg_lo));

- /* xor dreg_hi,dreg_hi */ - EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + if (!aux->verifier_zext) + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); break; case 64: /* Emit 'bswap eax' to swap lower 4 bytes */ @@@ -569,7 -576,7 +576,7 @@@ static inline void emit_ia32_alu_r(cons static inline void emit_ia32_alu_r64(const bool is64, const u8 op, const u8 dst[], const u8 src[], bool dstk, bool sstk, - u8 **pprog) + u8 **pprog, const struct bpf_prog_aux *aux) { u8 *prog = *pprog;

@@@ -577,7 -584,7 +584,7 @@@ if (is64) emit_ia32_alu_r(is64, true, op, dst_hi, src_hi, dstk, sstk, &prog); - else + else if (!aux->verifier_zext) emit_ia32_mov_i(dst_hi, 0, dstk, &prog); *pprog = prog; } @@@ -668,7 -675,8 +675,8 @@@ static inline void emit_ia32_alu_i(cons /* ALU operation (64 bit) */ static inline void emit_ia32_alu_i64(const bool is64, const u8 op, const u8 dst[], const u32 val, - bool dstk, u8 **pprog) + bool dstk, u8 **pprog, + const struct bpf_prog_aux *aux) { u8 *prog = *pprog; u32 hi = 0; @@@ -679,7 -687,7 +687,7 @@@ emit_ia32_alu_i(is64, false, op, dst_lo, val, dstk, &prog); if (is64) emit_ia32_alu_i(is64, true, op, dst_hi, hi, dstk, &prog); - else + else if (!aux->verifier_zext) emit_ia32_mov_i(dst_hi, 0, dstk, &prog);

*pprog = prog; @@@ -724,6 -732,9 +732,6 @@@ static inline void emit_ia32_lsh_r64(co { u8 *prog = *pprog; int cnt = 0; - static int jmp_label1 = -1; - static int jmp_label2 = -1; - static int jmp_label3 = -1; u8 dreg_lo = dstk ? IA32_EAX : dst_lo; u8 dreg_hi = dstk ? IA32_EDX : dst_hi;

@@@ -742,22 -753,78 +750,22 @@@ /* mov ecx,src_lo */ EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));

- /* cmp ecx,32 */ - EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32); - /* Jumps when >= 32 */ - if (is_imm8(jmp_label(jmp_label1, 2))) - EMIT2(IA32_JAE, jmp_label(jmp_label1, 2)); - else - EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6)); - - /* < 32 */ - /* shl dreg_hi,cl */ - EMIT2(0xD3, add_1reg(0xE0, dreg_hi)); - /* mov ebx,dreg_lo */ - EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX)); + /* shld dreg_hi,dreg_lo,cl */ + EMIT3(0x0F, 0xA5, add_2reg(0xC0, dreg_hi, dreg_lo)); /* shl dreg_lo,cl */ EMIT2(0xD3, add_1reg(0xE0, dreg_lo));

- /* IA32_ECX = -IA32_ECX + 32 */ - /* neg ecx */ - EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); - /* add ecx,32 */ - EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); - - /* shr ebx,cl */ - EMIT2(0xD3, add_1reg(0xE8, IA32_EBX)); - /* or dreg_hi,ebx */ - EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX)); - - /* goto out; */ - if (is_imm8(jmp_label(jmp_label3, 2))) - EMIT2(0xEB, jmp_label(jmp_label3, 2)); - else - EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); - - /* >= 32 */ - if (jmp_label1 == -1) - jmp_label1 = cnt; + /* if ecx >= 32, mov dreg_lo into dreg_hi and clear dreg_lo */

- /* cmp ecx,64 */ - EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64); - /* Jumps when >= 64 */ - if (is_imm8(jmp_label(jmp_label2, 2))) - EMIT2(IA32_JAE, jmp_label(jmp_label2, 2)); - else - EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6)); + /* cmp ecx,32 */ + EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32); + /* skip the next two instructions (4 bytes) when < 32 */ + EMIT2(IA32_JB, 4);

- /* >= 32 && < 64 */ - /* sub ecx,32 */ - EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32); - /* shl dreg_lo,cl */ - EMIT2(0xD3, add_1reg(0xE0, dreg_lo)); /* mov dreg_hi,dreg_lo */ EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo)); - - /* xor dreg_lo,dreg_lo */ - EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo)); - - /* goto out; */ - if (is_imm8(jmp_label(jmp_label3, 2))) - EMIT2(0xEB, jmp_label(jmp_label3, 2)); - else - EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); - - /* >= 64 */ - if (jmp_label2 == -1) - jmp_label2 = cnt; /* xor dreg_lo,dreg_lo */ EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo)); - /* xor dreg_hi,dreg_hi */ - EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); - - if (jmp_label3 == -1) - jmp_label3 = cnt;

if (dstk) { /* mov dword ptr [ebp+off],dreg_lo */ @@@ -777,6 -844,9 +785,6 @@@ static inline void emit_ia32_arsh_r64(c { u8 *prog = *pprog; int cnt = 0; - static int jmp_label1 = -1; - static int jmp_label2 = -1; - static int jmp_label3 = -1; u8 dreg_lo = dstk ? IA32_EAX : dst_lo; u8 dreg_hi = dstk ? IA32_EDX : dst_hi;

@@@ -795,22 -865,78 +803,22 @@@ /* mov ecx,src_lo */ EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));

- /* cmp ecx,32 */ - EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32); - /* Jumps when >= 32 */ - if (is_imm8(jmp_label(jmp_label1, 2))) - EMIT2(IA32_JAE, jmp_label(jmp_label1, 2)); - else - EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6)); - - /* < 32 */ - /* lshr dreg_lo,cl */ - EMIT2(0xD3, add_1reg(0xE8, dreg_lo)); - /* mov ebx,dreg_hi */ - EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX)); - /* ashr dreg_hi,cl */ + /* shrd dreg_lo,dreg_hi,cl */ + EMIT3(0x0F, 0xAD, add_2reg(0xC0, dreg_lo, dreg_hi)); + /* sar dreg_hi,cl */ EMIT2(0xD3, add_1reg(0xF8, dreg_hi));

- /* IA32_ECX = -IA32_ECX + 32 */ - /* neg ecx */ - EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); - /* add ecx,32 */ - EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); - - /* shl ebx,cl */ - EMIT2(0xD3, add_1reg(0xE0, IA32_EBX)); - /* or dreg_lo,ebx */ - EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX)); - - /* goto out; */ - if (is_imm8(jmp_label(jmp_label3, 2))) - EMIT2(0xEB, jmp_label(jmp_label3, 2)); - else - EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); - - /* >= 32 */ - if (jmp_label1 == -1) - jmp_label1 = cnt; + /* if ecx >= 32, mov dreg_hi to dreg_lo and set/clear dreg_hi depending on sign */

- /* cmp ecx,64 */ - EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64); - /* Jumps when >= 64 */ - if (is_imm8(jmp_label(jmp_label2, 2))) - EMIT2(IA32_JAE, jmp_label(jmp_label2, 2)); - else - EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6)); + /* cmp ecx,32 */ + EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32); + /* skip the next two instructions (5 bytes) when < 32 */ + EMIT2(IA32_JB, 5);

- /* >= 32 && < 64 */ - /* sub ecx,32 */ - EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32); - /* ashr dreg_hi,cl */ - EMIT2(0xD3, add_1reg(0xF8, dreg_hi)); /* mov dreg_lo,dreg_hi */ EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi)); - - /* ashr dreg_hi,imm8 */ - EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31); - - /* goto out; */ - if (is_imm8(jmp_label(jmp_label3, 2))) - EMIT2(0xEB, jmp_label(jmp_label3, 2)); - else - EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); - - /* >= 64 */ - if (jmp_label2 == -1) - jmp_label2 = cnt; - /* ashr dreg_hi,imm8 */ + /* sar dreg_hi,31 */ EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31); - /* mov dreg_lo,dreg_hi */ - EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi)); - - if (jmp_label3 == -1) - jmp_label3 = cnt;

if (dstk) { /* mov dword ptr [ebp+off],dreg_lo */ @@@ -830,6 -956,9 +838,6 @@@ static inline void emit_ia32_rsh_r64(co { u8 *prog = *pprog; int cnt = 0; - static int jmp_label1 = -1; - static int jmp_label2 = -1; - static int jmp_label3 = -1; u8 dreg_lo = dstk ? IA32_EAX : dst_lo; u8 dreg_hi = dstk ? IA32_EDX : dst_hi;

@@@ -848,23 -977,77 +856,23 @@@ /* mov ecx,src_lo */ EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX));

- /* cmp ecx,32 */ - EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32); - /* Jumps when >= 32 */ - if (is_imm8(jmp_label(jmp_label1, 2))) - EMIT2(IA32_JAE, jmp_label(jmp_label1, 2)); - else - EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6)); - - /* < 32 */ - /* lshr dreg_lo,cl */ - EMIT2(0xD3, add_1reg(0xE8, dreg_lo)); - /* mov ebx,dreg_hi */ - EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX)); + /* shrd dreg_lo,dreg_hi,cl */ + EMIT3(0x0F, 0xAD, add_2reg(0xC0, dreg_lo, dreg_hi)); /* shr dreg_hi,cl */ EMIT2(0xD3, add_1reg(0xE8, dreg_hi));

- /* IA32_ECX = -IA32_ECX + 32 */ - /* neg ecx */ - EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); - /* add ecx,32 */ - EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); - - /* shl ebx,cl */ - EMIT2(0xD3, add_1reg(0xE0, IA32_EBX)); - /* or dreg_lo,ebx */ - EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX)); + /* if ecx >= 32, mov dreg_hi to dreg_lo and clear dreg_hi */

- /* goto out; */ - if (is_imm8(jmp_label(jmp_label3, 2))) - EMIT2(0xEB, jmp_label(jmp_label3, 2)); - else - EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); - - /* >= 32 */ - if (jmp_label1 == -1) - jmp_label1 = cnt; - /* cmp ecx,64 */ - EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64); - /* Jumps when >= 64 */ - if (is_imm8(jmp_label(jmp_label2, 2))) - EMIT2(IA32_JAE, jmp_label(jmp_label2, 2)); - else - EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6)); + /* cmp ecx,32 */ + EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32); + /* skip the next two instructions (4 bytes) when < 32 */ + EMIT2(IA32_JB, 4);

- /* >= 32 && < 64 */ - /* sub ecx,32 */ - EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32); - /* shr dreg_hi,cl */ - EMIT2(0xD3, add_1reg(0xE8, dreg_hi)); /* mov dreg_lo,dreg_hi */ EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi)); /* xor dreg_hi,dreg_hi */ EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi));

- /* goto out; */ - if (is_imm8(jmp_label(jmp_label3, 2))) - EMIT2(0xEB, jmp_label(jmp_label3, 2)); - else - EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); - - /* >= 64 */ - if (jmp_label2 == -1) - jmp_label2 = cnt; - /* xor dreg_lo,dreg_lo */ - EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo)); - /* xor dreg_hi,dreg_hi */ - EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); - - if (jmp_label3 == -1) - jmp_label3 = cnt; - if (dstk) { /* mov dword ptr [ebp+off],dreg_lo */ EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo), @@@ -894,10 -1077,27 +902,10 @@@ static inline void emit_ia32_lsh_i64(co } /* Do LSH operation */ if (val < 32) { - /* shl dreg_hi,imm8 */ - EMIT3(0xC1, add_1reg(0xE0, dreg_hi), val); - /* mov ebx,dreg_lo */ - EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX)); + /* shld dreg_hi,dreg_lo,imm8 */ + EMIT4(0x0F, 0xA4, add_2reg(0xC0, dreg_hi, dreg_lo), val); /* shl dreg_lo,imm8 */ EMIT3(0xC1, add_1reg(0xE0, dreg_lo), val); - - /* IA32_ECX = 32 - val */ - /* mov ecx,val */ - EMIT2(0xB1, val); - /* movzx ecx,ecx */ - EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX)); - /* neg ecx */ - EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); - /* add ecx,32 */ - EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); - - /* shr ebx,cl */ - EMIT2(0xD3, add_1reg(0xE8, IA32_EBX)); - /* or dreg_hi,ebx */ - EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX)); } else if (val >= 32 && val < 64) { u32 value = val - 32;

@@@ -943,10 -1143,27 +951,10 @@@ static inline void emit_ia32_rsh_i64(co

/* Do RSH operation */ if (val < 32) { - /* shr dreg_lo,imm8 */ - EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val); - /* mov ebx,dreg_hi */ - EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX)); + /* shrd dreg_lo,dreg_hi,imm8 */ + EMIT4(0x0F, 0xAC, add_2reg(0xC0, dreg_lo, dreg_hi), val); /* shr dreg_hi,imm8 */ EMIT3(0xC1, add_1reg(0xE8, dreg_hi), val); - - /* IA32_ECX = 32 - val */ - /* mov ecx,val */ - EMIT2(0xB1, val); - /* movzx ecx,ecx */ - EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX)); - /* neg ecx */ - EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); - /* add ecx,32 */ - EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); - - /* shl ebx,cl */ - EMIT2(0xD3, add_1reg(0xE0, IA32_EBX)); - /* or dreg_lo,ebx */ - EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX)); } else if (val >= 32 && val < 64) { u32 value = val - 32;

@@@ -991,10 -1208,27 +999,10 @@@ static inline void emit_ia32_arsh_i64(c } /* Do RSH operation */ if (val < 32) { - /* shr dreg_lo,imm8 */ - EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val); - /* mov ebx,dreg_hi */ - EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX)); + /* shrd dreg_lo,dreg_hi,imm8 */ + EMIT4(0x0F, 0xAC, add_2reg(0xC0, dreg_lo, dreg_hi), val); /* ashr dreg_hi,imm8 */ EMIT3(0xC1, add_1reg(0xF8, dreg_hi), val); - - /* IA32_ECX = 32 - val */ - /* mov ecx,val */ - EMIT2(0xB1, val); - /* movzx ecx,ecx */ - EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX)); - /* neg ecx */ - EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); - /* add ecx,32 */ - EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); - - /* shl ebx,cl */ - EMIT2(0xD3, add_1reg(0xE0, IA32_EBX)); - /* or dreg_lo,ebx */ - EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX)); } else if (val >= 32 && val < 64) { u32 value = val - 32;

@@@ -1487,8 -1721,13 +1495,13 @@@ static int do_jit(struct bpf_prog *bpf_ case BPF_ALU64 | BPF_MOV | BPF_X: switch (BPF_SRC(code)) { case BPF_X: - emit_ia32_mov_r64(is64, dst, src, dstk, - sstk, &prog); + if (imm32 == 1) { + /* Special mov32 for zext. */ + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + break; + } + emit_ia32_mov_r64(is64, dst, src, dstk, sstk, + &prog, bpf_prog->aux); break; case BPF_K: /* Sign-extend immediate value to dst reg */ @@@ -1528,11 -1767,13 +1541,13 @@@ switch (BPF_SRC(code)) { case BPF_X: emit_ia32_alu_r64(is64, BPF_OP(code), dst, - src, dstk, sstk, &prog); + src, dstk, sstk, &prog, + bpf_prog->aux); break; case BPF_K: emit_ia32_alu_i64(is64, BPF_OP(code), dst, - imm32, dstk, &prog); + imm32, dstk, &prog, + bpf_prog->aux); break; } break; @@@ -1551,7 -1792,8 +1566,8 @@@ false, &prog); break; } - emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + if (!bpf_prog->aux->verifier_zext) + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); break; case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_X: @@@ -1571,7 -1813,8 +1587,8 @@@ &prog); break; } - emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + if (!bpf_prog->aux->verifier_zext) + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); break; /* dst = dst / src(imm) */ /* dst = dst % src(imm) */ @@@ -1593,7 -1836,8 +1610,8 @@@ &prog); break; } - emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + if (!bpf_prog->aux->verifier_zext) + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); break; case BPF_ALU64 | BPF_DIV | BPF_K: case BPF_ALU64 | BPF_DIV | BPF_X: @@@ -1610,7 -1854,8 +1628,8 @@@ EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32); emit_ia32_shift_r(BPF_OP(code), dst_lo, IA32_ECX, dstk, false, &prog); - emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + if (!bpf_prog->aux->verifier_zext) + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); break; /* dst = dst << imm */ case BPF_ALU64 | BPF_LSH | BPF_K: @@@ -1646,7 -1891,8 +1665,8 @@@ case BPF_ALU | BPF_NEG: emit_ia32_alu_i(is64, false, BPF_OP(code), dst_lo, 0, dstk, &prog); - emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + if (!bpf_prog->aux->verifier_zext) + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); break; /* dst = ~dst (64 bit) */ case BPF_ALU64 | BPF_NEG: @@@ -1666,11 -1912,13 +1686,13 @@@ break; /* dst = htole(dst) */ case BPF_ALU | BPF_END | BPF_FROM_LE: - emit_ia32_to_le_r64(dst, imm32, dstk, &prog); + emit_ia32_to_le_r64(dst, imm32, dstk, &prog, + bpf_prog->aux); break; /* dst = htobe(dst) */ case BPF_ALU | BPF_END | BPF_FROM_BE: - emit_ia32_to_be_r64(dst, imm32, dstk, &prog); + emit_ia32_to_be_r64(dst, imm32, dstk, &prog, + bpf_prog->aux); break; /* dst = imm64 */ case BPF_LD | BPF_IMM | BPF_DW: { @@@ -1825,6 -2073,8 +1847,8 @@@ case BPF_B: case BPF_H: case BPF_W: + if (!bpf_prog->aux->verifier_zext) + break; if (dstk) { EMIT3(0xC7, add_1reg(0x40, IA32_EBP), STACK_VAR(dst_hi)); @@@ -2249,6 -2499,11 +2273,11 @@@ notyet return proglen; }

+ bool bpf_jit_needs_zext(void) + { + return true; + } + struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) { struct bpf_binary_header *header = NULL; diff --combined drivers/infiniband/hw/cxgb4/cm.c index 0147c407ac6c,09fcfc9e052d..e87fc0408470 --- a/drivers/infiniband/hw/cxgb4/cm.c +++ b/drivers/infiniband/hw/cxgb4/cm.c @@@ -953,7 -953,7 +953,7 @@@ static int send_mpa_req(struct c4iw_ep mpalen = sizeof(*mpa) + ep->plen; if (mpa_rev_to_use == 2) mpalen += sizeof(struct mpa_v2_conn_params); - wrlen = roundup(mpalen + sizeof *req, 16); + wrlen = roundup(mpalen + sizeof(*req), 16); skb = get_skb(skb, wrlen, GFP_KERNEL); if (!skb) { connect_reply_upcall(ep, -ENOMEM); @@@ -997,9 -997,8 +997,9 @@@ }

if (mpa_rev_to_use == 2) { - mpa->private_data_size = htons(ntohs(mpa->private_data_size) + - sizeof (struct mpa_v2_conn_params)); + mpa->private_data_size = + htons(ntohs(mpa->private_data_size) + + sizeof(struct mpa_v2_conn_params)); pr_debug("initiator ird %u ord %u\n", ep->ird, ep->ord); mpa_v2_params.ird = htons((u16)ep->ird); @@@ -1058,7 -1057,7 +1058,7 @@@ static int send_mpa_reject(struct c4iw_ mpalen = sizeof(*mpa) + plen; if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) mpalen += sizeof(struct mpa_v2_conn_params); - wrlen = roundup(mpalen + sizeof *req, 16); + wrlen = roundup(mpalen + sizeof(*req), 16);

skb = get_skb(NULL, wrlen, GFP_KERNEL); if (!skb) { @@@ -1089,9 -1088,8 +1089,9 @@@

if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) { mpa->flags |= MPA_ENHANCED_RDMA_CONN; - mpa->private_data_size = htons(ntohs(mpa->private_data_size) + - sizeof (struct mpa_v2_conn_params)); + mpa->private_data_size = + htons(ntohs(mpa->private_data_size) + + sizeof(struct mpa_v2_conn_params)); mpa_v2_params.ird = htons(((u16)ep->ird) | (peer2peer ? MPA_V2_PEER2PEER_MODEL : 0)); @@@ -1138,7 -1136,7 +1138,7 @@@ static int send_mpa_reply(struct c4iw_e mpalen = sizeof(*mpa) + plen; if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) mpalen += sizeof(struct mpa_v2_conn_params); - wrlen = roundup(mpalen + sizeof *req, 16); + wrlen = roundup(mpalen + sizeof(*req), 16);

skb = get_skb(NULL, wrlen, GFP_KERNEL); if (!skb) { @@@ -1173,9 -1171,8 +1173,9 @@@

if (ep->mpa_attr.version == 2 && ep->mpa_attr.enhanced_rdma_conn) { mpa->flags |= MPA_ENHANCED_RDMA_CONN; - mpa->private_data_size = htons(ntohs(mpa->private_data_size) + - sizeof (struct mpa_v2_conn_params)); + mpa->private_data_size = + htons(ntohs(mpa->private_data_size) + + sizeof(struct mpa_v2_conn_params)); mpa_v2_params.ird = htons((u16)ep->ird); mpa_v2_params.ord = htons((u16)ep->ord); if (peer2peer && (ep->mpa_attr.p2p_type != @@@ -3233,17 -3230,22 +3233,22 @@@ static int pick_local_ipaddrs(struct c4 int found = 0; struct sockaddr_in *laddr = (struct sockaddr_in *)&cm_id->m_local_addr; struct sockaddr_in *raddr = (struct sockaddr_in *)&cm_id->m_remote_addr; + const struct in_ifaddr *ifa;

ind = in_dev_get(dev->rdev.lldi.ports[0]); if (!ind) return -EADDRNOTAVAIL; - for_primary_ifa(ind) { + rcu_read_lock(); + in_dev_for_each_ifa_rcu(ifa, ind) { + if (ifa->ifa_flags & IFA_F_SECONDARY) + continue; laddr->sin_addr.s_addr = ifa->ifa_address; raddr->sin_addr.s_addr = ifa->ifa_address; found = 1; break; } - endfor_ifa(ind); + rcu_read_unlock(); + in_dev_put(ind); return found ? 0 : -EADDRNOTAVAIL; } diff --combined drivers/infiniband/hw/mlx5/cq.c index 22230fd7d741,4efbbd2fce0c..e29987cdaeff --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@@ -37,7 -37,7 +37,7 @@@ #include "mlx5_ib.h" #include "srq.h"

- static void mlx5_ib_cq_comp(struct mlx5_core_cq *cq) + static void mlx5_ib_cq_comp(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe) { struct ib_cq *ibcq = &to_mibcq(cq)->ibcq;

@@@ -522,9 -522,9 +522,9 @@@ repoll case MLX5_CQE_SIG_ERR: sig_err_cqe = (struct mlx5_sig_err_cqe *)cqe64;

- read_lock(&dev->mdev->priv.mkey_table.lock); - mmkey = __mlx5_mr_lookup(dev->mdev, - mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey))); + xa_lock(&dev->mdev->priv.mkey_table); + mmkey = xa_load(&dev->mdev->priv.mkey_table, + mlx5_base_mkey(be32_to_cpu(sig_err_cqe->mkey))); mr = to_mibmr(mmkey); get_sig_err_item(sig_err_cqe, &mr->sig->err_item); mr->sig->sig_err_exists = true; @@@ -537,7 -537,7 +537,7 @@@ mr->sig->err_item.expected, mr->sig->err_item.actual);

- read_unlock(&dev->mdev->priv.mkey_table.lock); + xa_unlock(&dev->mdev->priv.mkey_table); goto repoll; }

@@@ -884,14 -884,15 +884,15 @@@ static void notify_soft_wc_handler(stru cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context); }

-struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, - const struct ib_cq_init_attr *attr, - struct ib_udata *udata) +int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, + struct ib_udata *udata) { + struct ib_device *ibdev = ibcq->device; int entries = attr->cqe; int vector = attr->comp_vector; struct mlx5_ib_dev *dev = to_mdev(ibdev); + u32 out[MLX5_ST_SZ_DW(create_cq_out)]; - struct mlx5_ib_cq *cq; + struct mlx5_ib_cq *cq = to_mcq(ibcq); int uninitialized_var(index); int uninitialized_var(inlen); u32 *cqb = NULL; @@@ -903,14 -904,18 +904,14 @@@

if (entries < 0 || (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz)))) - return ERR_PTR(-EINVAL); + return -EINVAL;

if (check_cq_create_flags(attr->flags)) - return ERR_PTR(-EOPNOTSUPP); + return -EOPNOTSUPP;

entries = roundup_pow_of_two(entries + 1); if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))) - return ERR_PTR(-EINVAL); - - cq = kzalloc(sizeof(*cq), GFP_KERNEL); - if (!cq) - return ERR_PTR(-ENOMEM); + return -EINVAL;

cq->ibcq.cqe = entries - 1; mutex_init(&cq->resize_mutex); @@@ -925,13 -930,13 +926,13 @@@ err = create_cq_user(dev, udata, cq, entries, &cqb, &cqe_size, &index, &inlen); if (err) - goto err_create; + return err; } else { cqe_size = cache_line_size() == 128 ? 128 : 64; err = create_cq_kernel(dev, cq, entries, cqe_size, &cqb, &index, &inlen); if (err) - goto err_create; + return err;

INIT_WORK(&cq->notify_work, notify_soft_wc_handler); } @@@ -954,7 -959,7 +955,7 @@@ if (cq->create_flags & IB_UVERBS_CQ_FLAGS_IGNORE_OVERRUN) MLX5_SET(cqc, cqc, oi, 1);

- err = mlx5_core_create_cq(dev->mdev, &cq->mcq, cqb, inlen); + err = mlx5_core_create_cq(dev->mdev, &cq->mcq, cqb, inlen, out, sizeof(out)); if (err) goto err_cqb;

@@@ -976,7 -981,7 +977,7 @@@

kvfree(cqb); - return &cq->ibcq; + return 0;

err_cmd: mlx5_core_destroy_cq(dev->mdev, &cq->mcq); @@@ -987,10 -992,14 +988,10 @@@ err_cqb destroy_cq_user(cq, udata); else destroy_cq_kernel(dev, cq); - -err_create: - kfree(cq); - - return ERR_PTR(err); + return err; }

-int mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) +void mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata) { struct mlx5_ib_dev *dev = to_mdev(cq->device); struct mlx5_ib_cq *mcq = to_mcq(cq); @@@ -1000,6 -1009,10 +1001,6 @@@ destroy_cq_user(mcq, udata); else destroy_cq_kernel(dev, mcq); - - kfree(mcq); - - return 0; }

static int is_equal_rsn(struct mlx5_cqe64 *cqe64, u32 rsn) @@@ -1125,6 -1138,11 +1126,6 @@@ static int resize_user(struct mlx5_ib_d return 0; }

-static void un_resize_user(struct mlx5_ib_cq *cq) -{ - ib_umem_release(cq->resize_umem); -} - static int resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, int entries, int cqe_size) { @@@ -1147,6 -1165,12 +1148,6 @@@ ex return err; }

-static void un_resize_kernel(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq) -{ - free_cq_buf(dev, cq->resize_buf); - cq->resize_buf = NULL; -} - static int copy_resize_cqes(struct mlx5_ib_cq *cq) { struct mlx5_ib_dev *dev = to_mdev(cq->ibcq.device); @@@ -1327,11 -1351,10 +1328,11 @@@ ex_alloc kvfree(in);

ex_resize: - if (udata) - un_resize_user(cq); - else - un_resize_kernel(dev, cq); + ib_umem_release(cq->resize_umem); + if (!udata) { + free_cq_buf(dev, cq->resize_buf); + cq->resize_buf = NULL; + } ex: mutex_unlock(&cq->resize_mutex); return err; diff --combined drivers/infiniband/hw/mlx5/main.c index 05d2bfcb3d60,ba312bf59c7a..9db8c06aa01e --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@@ -52,7 -52,6 +52,7 @@@ #include <linux/mlx5/port.h> #include <linux/mlx5/vport.h> #include <linux/mlx5/fs.h> +#include <linux/mlx5/eswitch.h> #include <linux/list.h> #include <rdma/ib_smi.h> #include <rdma/ib_umem.h> @@@ -889,7 -888,7 +889,7 @@@ static int mlx5_ib_query_device(struct } props->device_cap_flags |= IB_DEVICE_MEM_MGT_EXTENSIONS; if (MLX5_CAP_GEN(mdev, sho)) { - props->device_cap_flags |= IB_DEVICE_SIGNATURE_HANDOVER; + props->device_cap_flags |= IB_DEVICE_INTEGRITY_HANDOVER; /* At this stage no support for signature handover */ props->sig_prot_cap = IB_PROT_T10DIF_TYPE_1 | IB_PROT_T10DIF_TYPE_2 | @@@ -1009,8 -1008,6 +1009,8 @@@ props->max_srq_sge = max_rq_sg - 1; props->max_fast_reg_page_list_len = 1 << MLX5_CAP_GEN(mdev, log_max_klm_list_size); + props->max_pi_fast_reg_page_list_len = + props->max_fast_reg_page_list_len / 2; get_atomic_caps_qp(dev, props); props->masked_atomic_cap = IB_ATOMIC_NONE; props->max_mcast_grp = 1 << MLX5_CAP_GEN(mdev, log_max_mcg); @@@ -2669,11 -2666,15 +2669,15 @@@ int parse_flow_flow_action(struct mlx5_ } }

- static int parse_flow_attr(struct mlx5_core_dev *mdev, u32 *match_c, - u32 *match_v, const union ib_flow_spec *ib_spec, + static int parse_flow_attr(struct mlx5_core_dev *mdev, + struct mlx5_flow_spec *spec, + const union ib_flow_spec *ib_spec, const struct ib_flow_attr *flow_attr, struct mlx5_flow_act *action, u32 prev_type) { + struct mlx5_flow_context *flow_context = &spec->flow_context; + u32 *match_c = spec->match_criteria; + u32 *match_v = spec->match_value; void *misc_params_c = MLX5_ADDR_OF(fte_match_param, match_c, misc_parameters); void *misc_params_v = MLX5_ADDR_OF(fte_match_param, match_v, @@@ -2992,8 -2993,8 +2996,8 @@@ if (ib_spec->flow_tag.tag_id >= BIT(24)) return -EINVAL;

- action->flow_tag = ib_spec->flow_tag.tag_id; - action->flags |= FLOW_ACT_HAS_TAG; + flow_context->flow_tag = ib_spec->flow_tag.tag_id; + flow_context->flags |= FLOW_CONTEXT_HAS_TAG; break; case IB_FLOW_SPEC_ACTION_DROP: if (FIELDS_NOT_SUPPORTED(ib_spec->drop, @@@ -3087,7 -3088,8 +3091,8 @@@ is_valid_esp_aes_gcm(struct mlx5_core_d return VALID_SPEC_NA;

return is_crypto && is_ipsec && - (!egress || (!is_drop && !(flow_act->flags & FLOW_ACT_HAS_TAG))) ? + (!egress || (!is_drop && + !(spec->flow_context.flags & FLOW_CONTEXT_HAS_TAG))) ? VALID_SPEC_VALID : VALID_SPEC_INVALID; }

@@@ -3255,14 -3257,11 +3260,14 @@@ static struct mlx5_ib_flow_prio *get_fl int max_table_size; int num_entries; int num_groups; + bool esw_encap; u32 flags = 0; int priority;

max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, log_max_ft_size)); + esw_encap = mlx5_eswitch_get_encap_mode(dev->mdev) != + DEVLINK_ESWITCH_ENCAP_MODE_NONE; if (flow_attr->type == IB_FLOW_ATTR_NORMAL) { enum mlx5_flow_namespace_type fn_type;

@@@ -3275,10 -3274,10 +3280,10 @@@ if (ft_type == MLX5_IB_FT_RX) { fn_type = MLX5_FLOW_NAMESPACE_BYPASS; prio = &dev->flow_db->prios[priority]; - if (!dev->is_rep && + if (!dev->is_rep && !esw_encap && MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, decap)) flags |= MLX5_FLOW_TABLE_TUNNEL_EN_DECAP; - if (!dev->is_rep && + if (!dev->is_rep && !esw_encap && MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, reformat_l3_tunnel_to_l2)) flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; @@@ -3288,7 -3287,7 +3293,7 @@@ log_max_ft_size)); fn_type = MLX5_FLOW_NAMESPACE_EGRESS; prio = &dev->flow_db->egress_prios[priority]; - if (!dev->is_rep && + if (!dev->is_rep && !esw_encap && MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, reformat)) flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; } @@@ -3470,6 -3469,37 +3475,37 @@@ free return ret; }

+ static void mlx5_ib_set_rule_source_port(struct mlx5_ib_dev *dev, + struct mlx5_flow_spec *spec, + struct mlx5_eswitch_rep *rep) + { + struct mlx5_eswitch *esw = dev->mdev->priv.eswitch; + void *misc; + + if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, + misc_parameters_2); + + MLX5_SET(fte_match_set_misc2, misc, metadata_reg_c_0, + mlx5_eswitch_get_vport_metadata_for_match(esw, + rep->vport)); + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + misc_parameters_2); + + MLX5_SET_TO_ONES(fte_match_set_misc2, misc, metadata_reg_c_0); + } else { + misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, + misc_parameters); + + MLX5_SET(fte_match_set_misc, misc, source_port, rep->vport); + + misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, + misc_parameters); + + MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + } + } + static struct mlx5_ib_flow_handler *_create_flow_rule(struct mlx5_ib_dev *dev, struct mlx5_ib_flow_prio *ft_prio, const struct ib_flow_attr *flow_attr, @@@ -3479,7 -3509,7 +3515,7 @@@ { struct mlx5_flow_table *ft = ft_prio->flow_table; struct mlx5_ib_flow_handler *handler; - struct mlx5_flow_act flow_act = {.flow_tag = MLX5_FS_DEFAULT_FLOW_TAG}; + struct mlx5_flow_act flow_act = {}; struct mlx5_flow_spec *spec; struct mlx5_flow_destination dest_arr[2] = {}; struct mlx5_flow_destination *rule_dst = dest_arr; @@@ -3510,8 -3540,7 +3546,7 @@@ }

for (spec_index = 0; spec_index < flow_attr->num_of_specs; spec_index++) { - err = parse_flow_attr(dev->mdev, spec->match_criteria, - spec->match_value, + err = parse_flow_attr(dev->mdev, spec, ib_flow, flow_attr, &flow_act, prev_type); if (err < 0) @@@ -3525,19 -3554,15 +3560,15 @@@ set_underlay_qp(dev, spec, underlay_qpn);

if (dev->is_rep) { - void *misc; + struct mlx5_eswitch_rep *rep;

- if (!dev->port[flow_attr->port - 1].rep) { + rep = dev->port[flow_attr->port - 1].rep; + if (!rep) { err = -EINVAL; goto free; } - misc = MLX5_ADDR_OF(fte_match_param, spec->match_value, - misc_parameters); - MLX5_SET(fte_match_set_misc, misc, source_port, - dev->port[flow_attr->port - 1].rep->vport); - misc = MLX5_ADDR_OF(fte_match_param, spec->match_criteria, - misc_parameters); - MLX5_SET_TO_ONES(fte_match_set_misc, misc, source_port); + + mlx5_ib_set_rule_source_port(dev, spec, rep); }

spec->match_criteria_enable = get_match_criteria_enable(spec->match_criteria); @@@ -3578,11 -3603,11 +3609,11 @@@ MLX5_FLOW_CONTEXT_ACTION_FWD_NEXT_PRIO; }

- if ((flow_act.flags & FLOW_ACT_HAS_TAG) && + if ((spec->flow_context.flags & FLOW_CONTEXT_HAS_TAG) && (flow_attr->type == IB_FLOW_ATTR_ALL_DEFAULT || flow_attr->type == IB_FLOW_ATTR_MC_DEFAULT)) { mlx5_ib_warn(dev, "Flow tag %u and attribute type %x isn't allowed in leftovers\n", - flow_act.flow_tag, flow_attr->type); + spec->flow_context.flow_tag, flow_attr->type); err = -EINVAL; goto free; } @@@ -3898,7 -3923,6 +3929,7 @@@ _get_flow_table(struct mlx5_ib_dev *dev struct mlx5_flow_namespace *ns = NULL; struct mlx5_ib_flow_prio *prio = NULL; int max_table_size = 0; + bool esw_encap; u32 flags = 0; int priority;

@@@ -3907,30 -3931,22 +3938,30 @@@ else priority = ib_prio_to_core_prio(fs_matcher->priority, false);

+ esw_encap = mlx5_eswitch_get_encap_mode(dev->mdev) != + DEVLINK_ESWITCH_ENCAP_MODE_NONE; if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_BYPASS) { max_table_size = BIT(MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, log_max_ft_size)); - if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, decap)) + if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, decap) && !esw_encap) flags |= MLX5_FLOW_TABLE_TUNNEL_EN_DECAP; if (MLX5_CAP_FLOWTABLE_NIC_RX(dev->mdev, - reformat_l3_tunnel_to_l2)) + reformat_l3_tunnel_to_l2) && + !esw_encap) flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; } else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_EGRESS) { max_table_size = BIT( MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, log_max_ft_size)); - if (MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, reformat)) + if (MLX5_CAP_FLOWTABLE_NIC_TX(dev->mdev, reformat) && !esw_encap) flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; } else if (fs_matcher->ns_type == MLX5_FLOW_NAMESPACE_FDB) { max_table_size = BIT( MLX5_CAP_ESW_FLOWTABLE_FDB(dev->mdev, log_max_ft_size)); + if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev->mdev, decap) && esw_encap) + flags |= MLX5_FLOW_TABLE_TUNNEL_EN_DECAP; + if (MLX5_CAP_ESW_FLOWTABLE_FDB(dev->mdev, reformat_l3_tunnel_to_l2) && + esw_encap) + flags |= MLX5_FLOW_TABLE_TUNNEL_EN_REFORMAT; priority = FDB_BYPASS_PATH; }

@@@ -3962,6 -3978,7 +3993,7 @@@ _create_raw_flow_rule(struct mlx5_ib_de struct mlx5_ib_flow_prio *ft_prio, struct mlx5_flow_destination *dst, struct mlx5_ib_flow_matcher *fs_matcher, + struct mlx5_flow_context *flow_context, struct mlx5_flow_act *flow_act, void *cmd_in, int inlen, int dst_num) @@@ -3984,6 -4001,7 +4016,7 @@@ memcpy(spec->match_criteria, fs_matcher->matcher_mask.match_params, fs_matcher->mask_len); spec->match_criteria_enable = fs_matcher->match_criteria_enable; + spec->flow_context = *flow_context;

handler->rule = mlx5_add_flow_rules(ft, spec, flow_act, dst, dst_num); @@@ -4048,6 -4066,7 +4081,7 @@@ static bool raw_fs_is_multicast(struct struct mlx5_ib_flow_handler * mlx5_ib_raw_fs_rule_add(struct mlx5_ib_dev *dev, struct mlx5_ib_flow_matcher *fs_matcher, + struct mlx5_flow_context *flow_context, struct mlx5_flow_act *flow_act, u32 counter_id, void *cmd_in, int inlen, int dest_id, @@@ -4100,7 -4119,8 +4134,8 @@@ dst_num++; }

- handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher, flow_act, + handler = _create_raw_flow_rule(dev, ft_prio, dst, fs_matcher, + flow_context, flow_act, cmd_in, inlen, dst_num);

if (IS_ERR(handler)) { @@@ -4472,7 -4492,7 +4507,7 @@@ static void mlx5_ib_handle_internal_err * lock/unlock above locks Now need to arm all involved CQs. */ list_for_each_entry(mcq, &cq_armed_list, reset_notify) { - mcq->comp(mcq); + mcq->comp(mcq, NULL); } spin_unlock_irqrestore(&ibdev->reset_flow_resource_lock, flags); } @@@ -4906,19 -4926,18 +4941,19 @@@ static int create_dev_resources(struct if (ret) goto error0;

- devr->c0 = mlx5_ib_create_cq(&dev->ib_dev, &cq_attr, NULL); - if (IS_ERR(devr->c0)) { - ret = PTR_ERR(devr->c0); + devr->c0 = rdma_zalloc_drv_obj(ibdev, ib_cq); + if (!devr->c0) { + ret = -ENOMEM; goto error1; } - devr->c0->device = &dev->ib_dev; - devr->c0->uobject = NULL; - devr->c0->comp_handler = NULL; - devr->c0->event_handler = NULL; - devr->c0->cq_context = NULL; + + devr->c0->device = &dev->ib_dev; atomic_set(&devr->c0->usecnt, 0);

+ ret = mlx5_ib_create_cq(devr->c0, &cq_attr, NULL); + if (ret) + goto err_create_cq; + devr->x0 = mlx5_ib_alloc_xrcd(&dev->ib_dev, NULL); if (IS_ERR(devr->x0)) { ret = PTR_ERR(devr->x0); @@@ -5010,8 -5029,6 +5045,8 @@@ error3 mlx5_ib_dealloc_xrcd(devr->x0, NULL); error2: mlx5_ib_destroy_cq(devr->c0, NULL); +err_create_cq: + kfree(devr->c0); error1: mlx5_ib_dealloc_pd(devr->p0, NULL); error0: @@@ -5030,7 -5047,6 +5065,7 @@@ static void destroy_dev_resources(struc mlx5_ib_dealloc_xrcd(devr->x0, NULL); mlx5_ib_dealloc_xrcd(devr->x1, NULL); mlx5_ib_destroy_cq(devr->c0, NULL); + kfree(devr->c0); mlx5_ib_dealloc_pd(devr->p0, NULL); kfree(devr->p0);

@@@ -6063,6 -6079,7 +6098,6 @@@ static int mlx5_ib_stage_init_init(stru if (mlx5_use_mad_ifc(dev)) get_ext_port_caps(dev);

- dev->ib_dev.owner = THIS_MODULE; dev->ib_dev.node_type = RDMA_NODE_IB_CA; dev->ib_dev.local_dma_lkey = 0 /* not supported for now */; dev->ib_dev.phys_port_cnt = dev->num_ports; @@@ -6142,13 -6159,8 +6177,13 @@@ static void mlx5_ib_stage_flow_db_clean }

static const struct ib_device_ops mlx5_ib_dev_ops = { + .owner = THIS_MODULE, + .driver_id = RDMA_DRIVER_MLX5, + .uverbs_abi_ver = MLX5_IB_UVERBS_ABI_VERSION, + .add_gid = mlx5_ib_add_gid, .alloc_mr = mlx5_ib_alloc_mr, + .alloc_mr_integrity = mlx5_ib_alloc_mr_integrity, .alloc_pd = mlx5_ib_alloc_pd, .alloc_ucontext = mlx5_ib_alloc_ucontext, .attach_mcast = mlx5_ib_mcg_attach, @@@ -6178,7 -6190,6 +6213,7 @@@ .get_dma_mr = mlx5_ib_get_dma_mr, .get_link_layer = mlx5_ib_port_link_layer, .map_mr_sg = mlx5_ib_map_mr_sg, + .map_mr_sg_pi = mlx5_ib_map_mr_sg_pi, .mmap = mlx5_ib_mmap, .modify_cq = mlx5_ib_modify_cq, .modify_device = mlx5_ib_modify_device, @@@ -6203,7 -6214,6 +6238,7 @@@ .resize_cq = mlx5_ib_resize_cq,

INIT_RDMA_OBJ_SIZE(ib_ah, mlx5_ib_ah, ibah), + INIT_RDMA_OBJ_SIZE(ib_cq, mlx5_ib_cq, ibcq), INIT_RDMA_OBJ_SIZE(ib_pd, mlx5_ib_pd, ibpd), INIT_RDMA_OBJ_SIZE(ib_srq, mlx5_ib_srq, ibsrq), INIT_RDMA_OBJ_SIZE(ib_ucontext, mlx5_ib_ucontext, ibucontext), @@@ -6246,6 -6256,7 +6281,6 @@@ static int mlx5_ib_stage_caps_init(stru struct mlx5_core_dev *mdev = dev->mdev; int err;

- dev->ib_dev.uverbs_abi_ver = MLX5_IB_UVERBS_ABI_VERSION; dev->ib_dev.uverbs_cmd_mask = (1ull << IB_USER_VERBS_CMD_GET_CONTEXT) | (1ull << IB_USER_VERBS_CMD_QUERY_DEVICE) | @@@ -6314,6 -6325,7 +6349,6 @@@ if (mlx5_accel_ipsec_device_caps(dev->mdev) & MLX5_ACCEL_IPSEC_CAP_DEVICE) ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_flow_ipsec_ops); - dev->ib_dev.driver_id = RDMA_DRIVER_MLX5; ib_set_device_ops(&dev->ib_dev, &mlx5_ib_dev_ops);

if (IS_ENABLED(CONFIG_INFINIBAND_USER_ACCESS)) @@@ -6802,7 -6814,7 +6837,7 @@@ static void *mlx5_ib_add(struct mlx5_co printk_once(KERN_INFO "%s", mlx5_version);

if (MLX5_ESWITCH_MANAGER(mdev) && - mlx5_ib_eswitch_mode(mdev->priv.eswitch) == SRIOV_OFFLOADS) { + mlx5_ib_eswitch_mode(mdev->priv.eswitch) == MLX5_ESWITCH_OFFLOADS) { if (!mlx5_core_mp_enabled(mdev)) mlx5_ib_register_vport_reps(mdev); return mdev; diff --combined drivers/infiniband/hw/mlx5/mlx5_ib.h index bdb83fc85f94,ee73dc122d28..305d26cdf7f3 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@@ -431,6 -431,9 +431,6 @@@ struct mlx5_ib_qp

int create_type;

- /* Store signature errors */ - bool signature_en; - struct list_head qps_list; struct list_head cq_recv_list; struct list_head cq_send_list; @@@ -584,9 -587,6 +584,9 @@@ struct mlx5_ib_mr void *descs; dma_addr_t desc_map; int ndescs; + int data_length; + int meta_ndescs; + int meta_length; int max_descs; int desc_size; int access_mode; @@@ -605,13 -605,6 +605,13 @@@ int access_flags; /* Needed for rereg MR */

struct mlx5_ib_mr *parent; + /* Needed for IB_MR_TYPE_INTEGRITY */ + struct mlx5_ib_mr *pi_mr; + struct mlx5_ib_mr *klm_mr; + struct mlx5_ib_mr *mtt_mr; + u64 data_iova; + u64 pi_iova; + atomic_t num_leaf_free; wait_queue_head_t q_leaf_free; struct mlx5_async_work cb_work; @@@ -985,7 -978,6 +985,6 @@@ struct mlx5_ib_dev u16 devx_whitelist_uid; struct mlx5_srq_table srq_table; struct mlx5_async_ctx async_ctx; - int free_port; };

static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq) @@@ -1123,9 -1115,10 +1122,9 @@@ int mlx5_ib_read_user_wqe_rq(struct mlx int buflen, size_t *bc); int mlx5_ib_read_user_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index, void *buffer, int buflen, size_t *bc); -struct ib_cq *mlx5_ib_create_cq(struct ib_device *ibdev, - const struct ib_cq_init_attr *attr, - struct ib_udata *udata); -int mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); +int mlx5_ib_create_cq(struct ib_cq *ibcq, const struct ib_cq_init_attr *attr, + struct ib_udata *udata); +void mlx5_ib_destroy_cq(struct ib_cq *cq, struct ib_udata *udata); int mlx5_ib_poll_cq(struct ib_cq *ibcq, int num_entries, struct ib_wc *wc); int mlx5_ib_arm_cq(struct ib_cq *ibcq, enum ib_cq_notify_flags flags); int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period); @@@ -1155,15 -1148,8 +1154,15 @@@ int mlx5_ib_rereg_user_mr(struct ib_mr int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata); struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, u32 max_num_sg, struct ib_udata *udata); +struct ib_mr *mlx5_ib_alloc_mr_integrity(struct ib_pd *pd, + u32 max_num_sg, + u32 max_num_meta_sg); int mlx5_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset); +int mlx5_ib_map_mr_sg_pi(struct ib_mr *ibmr, struct scatterlist *data_sg, + int data_sg_nents, unsigned int *data_sg_offset, + struct scatterlist *meta_sg, int meta_sg_nents, + unsigned int *meta_sg_offset); int mlx5_ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num, const struct ib_wc *in_wc, const struct ib_grh *in_grh, const struct ib_mad_hdr *in, size_t in_mad_size, @@@ -1215,7 -1201,7 +1214,7 @@@ int mlx5_ib_check_mr_status(struct ib_m struct ib_wq *mlx5_ib_create_wq(struct ib_pd *pd, struct ib_wq_init_attr *init_attr, struct ib_udata *udata); -int mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata); +void mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata); int mlx5_ib_modify_wq(struct ib_wq *wq, struct ib_wq_attr *wq_attr, u32 wq_attr_mask, struct ib_udata *udata); struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device, @@@ -1330,6 -1316,7 +1329,7 @@@ extern const struct uapi_definition mlx extern const struct uapi_definition mlx5_ib_flow_defs[]; struct mlx5_ib_flow_handler *mlx5_ib_raw_fs_rule_add( struct mlx5_ib_dev *dev, struct mlx5_ib_flow_matcher *fs_matcher, + struct mlx5_flow_context *flow_context, struct mlx5_flow_act *flow_act, u32 counter_id, void *cmd_in, int inlen, int dest_id, int dest_type); bool mlx5_ib_devx_is_flow_dest(void *obj, int *dest_id, int *dest_type); diff --combined drivers/infiniband/hw/mlx5/mr.c index 6ac77e09a34a,83b452d977d4..20ece6e0b2fc --- a/drivers/infiniband/hw/mlx5/mr.c +++ b/drivers/infiniband/hw/mlx5/mr.c @@@ -130,7 -130,7 +130,7 @@@ static void reg_mr_callback(int status struct mlx5_cache_ent *ent = &cache->ent[c]; u8 key; unsigned long flags; - struct mlx5_mkey_table *table = &dev->mdev->priv.mkey_table; + struct xarray *mkeys = &dev->mdev->priv.mkey_table; int err;

spin_lock_irqsave(&ent->lock, flags); @@@ -158,12 -158,12 +158,12 @@@ ent->size++; spin_unlock_irqrestore(&ent->lock, flags);

- write_lock_irqsave(&table->lock, flags); - err = radix_tree_insert(&table->tree, mlx5_base_mkey(mr->mmkey.key), - &mr->mmkey); + xa_lock_irqsave(mkeys, flags); + err = xa_err(__xa_store(mkeys, mlx5_base_mkey(mr->mmkey.key), + &mr->mmkey, GFP_ATOMIC)); + xa_unlock_irqrestore(mkeys, flags); if (err) pr_err("Error inserting to mkey tree. 0x%x\n", -err); - write_unlock_irqrestore(&table->lock, flags);

if (!completion_done(&ent->compl)) complete(&ent->compl); @@@ -1507,9 -1507,10 +1507,9 @@@ int mlx5_ib_rereg_user_mr(struct ib_mr return 0;

err: - if (mr->umem) { - ib_umem_release(mr->umem); - mr->umem = NULL; - } + ib_umem_release(mr->umem); + mr->umem = NULL; + clean_mr(dev, mr); return err; } @@@ -1605,9 -1606,8 +1605,9 @@@ static void dereg_mr(struct mlx5_ib_de synchronize_srcu(&dev->mr_srcu); /* Destroy all page mappings */ if (umem_odp->page_list) - mlx5_ib_invalidate_range(umem_odp, ib_umem_start(umem), - ib_umem_end(umem)); + mlx5_ib_invalidate_range(umem_odp, + ib_umem_start(umem_odp), + ib_umem_end(umem_odp)); else mlx5_ib_free_implicit_mr(mr); /* @@@ -1629,85 -1629,28 +1629,85 @@@ * remove the DMA mapping. */ mlx5_mr_cache_free(dev, mr); - if (umem) { - ib_umem_release(umem); + ib_umem_release(umem); + if (umem) atomic_sub(npages, &dev->mdev->priv.reg_pages); - } + if (!mr->allocated_from_cache) kfree(mr); }

int mlx5_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata) { - dereg_mr(to_mdev(ibmr->device), to_mmr(ibmr)); + struct mlx5_ib_mr *mmr = to_mmr(ibmr); + + if (ibmr->type == IB_MR_TYPE_INTEGRITY) { + dereg_mr(to_mdev(mmr->mtt_mr->ibmr.device), mmr->mtt_mr); + dereg_mr(to_mdev(mmr->klm_mr->ibmr.device), mmr->klm_mr); + } + + dereg_mr(to_mdev(ibmr->device), mmr); + return 0; }

-struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, - u32 max_num_sg, struct ib_udata *udata) +static void mlx5_set_umr_free_mkey(struct ib_pd *pd, u32 *in, int ndescs, + int access_mode, int page_shift) +{ + void *mkc; + + mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + + MLX5_SET(mkc, mkc, free, 1); + MLX5_SET(mkc, mkc, qpn, 0xffffff); + MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn); + MLX5_SET(mkc, mkc, translations_octword_size, ndescs); + MLX5_SET(mkc, mkc, access_mode_1_0, access_mode & 0x3); + MLX5_SET(mkc, mkc, access_mode_4_2, (access_mode >> 2) & 0x7); + MLX5_SET(mkc, mkc, umr_en, 1); + MLX5_SET(mkc, mkc, log_page_size, page_shift); +} + +static int _mlx5_alloc_mkey_descs(struct ib_pd *pd, struct mlx5_ib_mr *mr, + int ndescs, int desc_size, int page_shift, + int access_mode, u32 *in, int inlen) { struct mlx5_ib_dev *dev = to_mdev(pd->device); + int err; + + mr->access_mode = access_mode; + mr->desc_size = desc_size; + mr->max_descs = ndescs; + + err = mlx5_alloc_priv_descs(pd->device, mr, ndescs, desc_size); + if (err) + return err; + + mlx5_set_umr_free_mkey(pd, in, ndescs, access_mode, page_shift); + + err = mlx5_core_create_mkey(dev->mdev, &mr->mmkey, in, inlen); + if (err) + goto err_free_descs; + + mr->mmkey.type = MLX5_MKEY_MR; + mr->ibmr.lkey = mr->mmkey.key; + mr->ibmr.rkey = mr->mmkey.key; + + return 0; + +err_free_descs: + mlx5_free_priv_descs(mr); + return err; +} + +static struct mlx5_ib_mr *mlx5_ib_alloc_pi_mr(struct ib_pd *pd, + u32 max_num_sg, u32 max_num_meta_sg, + int desc_size, int access_mode) +{ int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); - int ndescs = ALIGN(max_num_sg, 4); + int ndescs = ALIGN(max_num_sg + max_num_meta_sg, 4); + int page_shift = 0; struct mlx5_ib_mr *mr; - void *mkc; u32 *in; int err;

@@@ -1715,168 -1658,99 +1715,168 @@@ if (!mr) return ERR_PTR(-ENOMEM);

+ mr->ibmr.pd = pd; + mr->ibmr.device = pd->device; + in = kzalloc(inlen, GFP_KERNEL); if (!in) { err = -ENOMEM; goto err_free; }

+ if (access_mode == MLX5_MKC_ACCESS_MODE_MTT) + page_shift = PAGE_SHIFT; + + err = _mlx5_alloc_mkey_descs(pd, mr, ndescs, desc_size, page_shift, + access_mode, in, inlen); + if (err) + goto err_free_in; + + mr->umem = NULL; + kfree(in); + + return mr; + +err_free_in: + kfree(in); +err_free: + kfree(mr); + return ERR_PTR(err); +} + +static int mlx5_alloc_mem_reg_descs(struct ib_pd *pd, struct mlx5_ib_mr *mr, + int ndescs, u32 *in, int inlen) +{ + return _mlx5_alloc_mkey_descs(pd, mr, ndescs, sizeof(struct mlx5_mtt), + PAGE_SHIFT, MLX5_MKC_ACCESS_MODE_MTT, in, + inlen); +} + +static int mlx5_alloc_sg_gaps_descs(struct ib_pd *pd, struct mlx5_ib_mr *mr, + int ndescs, u32 *in, int inlen) +{ + return _mlx5_alloc_mkey_descs(pd, mr, ndescs, sizeof(struct mlx5_klm), + 0, MLX5_MKC_ACCESS_MODE_KLMS, in, inlen); +} + +static int mlx5_alloc_integrity_descs(struct ib_pd *pd, struct mlx5_ib_mr *mr, + int max_num_sg, int max_num_meta_sg, + u32 *in, int inlen) +{ + struct mlx5_ib_dev *dev = to_mdev(pd->device); + u32 psv_index[2]; + void *mkc; + int err; + + mr->sig = kzalloc(sizeof(*mr->sig), GFP_KERNEL); + if (!mr->sig) + return -ENOMEM; + + /* create mem & wire PSVs */ + err = mlx5_core_create_psv(dev->mdev, to_mpd(pd)->pdn, 2, psv_index); + if (err) + goto err_free_sig; + + mr->sig->psv_memory.psv_idx = psv_index[0]; + mr->sig->psv_wire.psv_idx = psv_index[1]; + + mr->sig->sig_status_checked = true; + mr->sig->sig_err_exists = false; + /* Next UMR, Arm SIGERR */ + ++mr->sig->sigerr_count; + mr->klm_mr = mlx5_ib_alloc_pi_mr(pd, max_num_sg, max_num_meta_sg, + sizeof(struct mlx5_klm), + MLX5_MKC_ACCESS_MODE_KLMS); + if (IS_ERR(mr->klm_mr)) { + err = PTR_ERR(mr->klm_mr); + goto err_destroy_psv; + } + mr->mtt_mr = mlx5_ib_alloc_pi_mr(pd, max_num_sg, max_num_meta_sg, + sizeof(struct mlx5_mtt), + MLX5_MKC_ACCESS_MODE_MTT); + if (IS_ERR(mr->mtt_mr)) { + err = PTR_ERR(mr->mtt_mr); + goto err_free_klm_mr; + } + + /* Set bsf descriptors for mkey */ mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); - MLX5_SET(mkc, mkc, free, 1); - MLX5_SET(mkc, mkc, translations_octword_size, ndescs); - MLX5_SET(mkc, mkc, qpn, 0xffffff); - MLX5_SET(mkc, mkc, pd, to_mpd(pd)->pdn); + MLX5_SET(mkc, mkc, bsf_en, 1); + MLX5_SET(mkc, mkc, bsf_octword_size, MLX5_MKEY_BSF_OCTO_SIZE);

- if (mr_type == IB_MR_TYPE_MEM_REG) { - mr->access_mode = MLX5_MKC_ACCESS_MODE_MTT; - MLX5_SET(mkc, mkc, log_page_size, PAGE_SHIFT); - err = mlx5_alloc_priv_descs(pd->device, mr, - ndescs, sizeof(struct mlx5_mtt)); - if (err) - goto err_free_in; + err = _mlx5_alloc_mkey_descs(pd, mr, 4, sizeof(struct mlx5_klm), 0, + MLX5_MKC_ACCESS_MODE_KLMS, in, inlen); + if (err) + goto err_free_mtt_mr;

- mr->desc_size = sizeof(struct mlx5_mtt); - mr->max_descs = ndescs; - } else if (mr_type == IB_MR_TYPE_SG_GAPS) { - mr->access_mode = MLX5_MKC_ACCESS_MODE_KLMS; + return 0;

- err = mlx5_alloc_priv_descs(pd->device, mr, - ndescs, sizeof(struct mlx5_klm)); - if (err) - goto err_free_in; - mr->desc_size = sizeof(struct mlx5_klm); - mr->max_descs = ndescs; - } else if (mr_type == IB_MR_TYPE_SIGNATURE) { - u32 psv_index[2]; - - MLX5_SET(mkc, mkc, bsf_en, 1); - MLX5_SET(mkc, mkc, bsf_octword_size, MLX5_MKEY_BSF_OCTO_SIZE); - mr->sig = kzalloc(sizeof(*mr->sig), GFP_KERNEL); - if (!mr->sig) { - err = -ENOMEM; - goto err_free_in; - } +err_free_mtt_mr: + dereg_mr(to_mdev(mr->mtt_mr->ibmr.device), mr->mtt_mr); + mr->mtt_mr = NULL; +err_free_klm_mr: + dereg_mr(to_mdev(mr->klm_mr->ibmr.device), mr->klm_mr); + mr->klm_mr = NULL; +err_destroy_psv: + if (mlx5_core_destroy_psv(dev->mdev, mr->sig->psv_memory.psv_idx)) + mlx5_ib_warn(dev, "failed to destroy mem psv %d\n", + mr->sig->psv_memory.psv_idx); + if (mlx5_core_destroy_psv(dev->mdev, mr->sig->psv_wire.psv_idx)) + mlx5_ib_warn(dev, "failed to destroy wire psv %d\n", + mr->sig->psv_wire.psv_idx); +err_free_sig: + kfree(mr->sig);

- /* create mem & wire PSVs */ - err = mlx5_core_create_psv(dev->mdev, to_mpd(pd)->pdn, - 2, psv_index); - if (err) - goto err_free_sig; + return err; +} + +static struct ib_mr *__mlx5_ib_alloc_mr(struct ib_pd *pd, + enum ib_mr_type mr_type, u32 max_num_sg, + u32 max_num_meta_sg) +{ + struct mlx5_ib_dev *dev = to_mdev(pd->device); + int inlen = MLX5_ST_SZ_BYTES(create_mkey_in); + int ndescs = ALIGN(max_num_sg, 4); + struct mlx5_ib_mr *mr; + u32 *in; + int err;

- mr->access_mode = MLX5_MKC_ACCESS_MODE_KLMS; - mr->sig->psv_memory.psv_idx = psv_index[0]; - mr->sig->psv_wire.psv_idx = psv_index[1]; + mr = kzalloc(sizeof(*mr), GFP_KERNEL); + if (!mr) + return ERR_PTR(-ENOMEM);

- mr->sig->sig_status_checked = true; - mr->sig->sig_err_exists = false; - /* Next UMR, Arm SIGERR */ - ++mr->sig->sigerr_count; - } else { + in = kzalloc(inlen, GFP_KERNEL); + if (!in) { + err = -ENOMEM; + goto err_free; + } + + mr->ibmr.device = pd->device; + mr->umem = NULL; + + switch (mr_type) { + case IB_MR_TYPE_MEM_REG: + err = mlx5_alloc_mem_reg_descs(pd, mr, ndescs, in, inlen); + break; + case IB_MR_TYPE_SG_GAPS: + err = mlx5_alloc_sg_gaps_descs(pd, mr, ndescs, in, inlen); + break; + case IB_MR_TYPE_INTEGRITY: + err = mlx5_alloc_integrity_descs(pd, mr, max_num_sg, + max_num_meta_sg, in, inlen); + break; + default: mlx5_ib_warn(dev, "Invalid mr type %d\n", mr_type); err = -EINVAL; - goto err_free_in; }

- MLX5_SET(mkc, mkc, access_mode_1_0, mr->access_mode & 0x3); - MLX5_SET(mkc, mkc, access_mode_4_2, (mr->access_mode >> 2) & 0x7); - MLX5_SET(mkc, mkc, umr_en, 1); - - mr->ibmr.device = pd->device; - err = mlx5_core_create_mkey(dev->mdev, &mr->mmkey, in, inlen); if (err) - goto err_destroy_psv; + goto err_free_in;

- mr->mmkey.type = MLX5_MKEY_MR; - mr->ibmr.lkey = mr->mmkey.key; - mr->ibmr.rkey = mr->mmkey.key; - mr->umem = NULL; kfree(in);

return &mr->ibmr;

-err_destroy_psv: - if (mr->sig) { - if (mlx5_core_destroy_psv(dev->mdev, - mr->sig->psv_memory.psv_idx)) - mlx5_ib_warn(dev, "failed to destroy mem psv %d\n", - mr->sig->psv_memory.psv_idx); - if (mlx5_core_destroy_psv(dev->mdev, - mr->sig->psv_wire.psv_idx)) - mlx5_ib_warn(dev, "failed to destroy wire psv %d\n", - mr->sig->psv_wire.psv_idx); - } - mlx5_free_priv_descs(mr); -err_free_sig: - kfree(mr->sig); err_free_in: kfree(in); err_free: @@@ -1884,19 -1758,6 +1884,19 @@@ return ERR_PTR(err); }

+struct ib_mr *mlx5_ib_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type, + u32 max_num_sg, struct ib_udata *udata) +{ + return __mlx5_ib_alloc_mr(pd, mr_type, max_num_sg, 0); +} + +struct ib_mr *mlx5_ib_alloc_mr_integrity(struct ib_pd *pd, + u32 max_num_sg, u32 max_num_meta_sg) +{ + return __mlx5_ib_alloc_mr(pd, IB_MR_TYPE_INTEGRITY, max_num_sg, + max_num_meta_sg); +} + struct ib_mw *mlx5_ib_alloc_mw(struct ib_pd *pd, enum ib_mw_type type, struct ib_udata *udata) { @@@ -2026,53 -1887,16 +2026,53 @@@ done }

static int +mlx5_ib_map_pa_mr_sg_pi(struct ib_mr *ibmr, struct scatterlist *data_sg, + int data_sg_nents, unsigned int *data_sg_offset, + struct scatterlist *meta_sg, int meta_sg_nents, + unsigned int *meta_sg_offset) +{ + struct mlx5_ib_mr *mr = to_mmr(ibmr); + unsigned int sg_offset = 0; + int n = 0; + + mr->meta_length = 0; + if (data_sg_nents == 1) { + n++; + mr->ndescs = 1; + if (data_sg_offset) + sg_offset = *data_sg_offset; + mr->data_length = sg_dma_len(data_sg) - sg_offset; + mr->data_iova = sg_dma_address(data_sg) + sg_offset; + if (meta_sg_nents == 1) { + n++; + mr->meta_ndescs = 1; + if (meta_sg_offset) + sg_offset = *meta_sg_offset; + else + sg_offset = 0; + mr->meta_length = sg_dma_len(meta_sg) - sg_offset; + mr->pi_iova = sg_dma_address(meta_sg) + sg_offset; + } + ibmr->length = mr->data_length + mr->meta_length; + } + + return n; +} + +static int mlx5_ib_sg_to_klms(struct mlx5_ib_mr *mr, struct scatterlist *sgl, unsigned short sg_nents, - unsigned int *sg_offset_p) + unsigned int *sg_offset_p, + struct scatterlist *meta_sgl, + unsigned short meta_sg_nents, + unsigned int *meta_sg_offset_p) { struct scatterlist *sg = sgl; struct mlx5_klm *klms = mr->descs; unsigned int sg_offset = sg_offset_p ? *sg_offset_p : 0; u32 lkey = mr->ibmr.pd->local_dma_lkey; - int i; + int i, j = 0;

mr->ibmr.iova = sg_dma_address(sg) + sg_offset; mr->ibmr.length = 0; @@@ -2087,36 -1911,12 +2087,36 @@@

sg_offset = 0; } - mr->ndescs = i;

if (sg_offset_p) *sg_offset_p = sg_offset;

- return i; + mr->ndescs = i; + mr->data_length = mr->ibmr.length; + + if (meta_sg_nents) { + sg = meta_sgl; + sg_offset = meta_sg_offset_p ? *meta_sg_offset_p : 0; + for_each_sg(meta_sgl, sg, meta_sg_nents, j) { + if (unlikely(i + j >= mr->max_descs)) + break; + klms[i + j].va = cpu_to_be64(sg_dma_address(sg) + + sg_offset); + klms[i + j].bcount = cpu_to_be32(sg_dma_len(sg) - + sg_offset); + klms[i + j].key = cpu_to_be32(lkey); + mr->ibmr.length += sg_dma_len(sg) - sg_offset; + + sg_offset = 0; + } + if (meta_sg_offset_p) + *meta_sg_offset_p = sg_offset; + + mr->meta_ndescs = j; + mr->meta_length = mr->ibmr.length - mr->data_length; + } + + return i + j; }

static int mlx5_set_page(struct ib_mr *ibmr, u64 addr) @@@ -2133,181 -1933,6 +2133,181 @@@ return 0; }

+static int mlx5_set_page_pi(struct ib_mr *ibmr, u64 addr) +{ + struct mlx5_ib_mr *mr = to_mmr(ibmr); + __be64 *descs; + + if (unlikely(mr->ndescs + mr->meta_ndescs == mr->max_descs)) + return -ENOMEM; + + descs = mr->descs; + descs[mr->ndescs + mr->meta_ndescs++] = + cpu_to_be64(addr | MLX5_EN_RD | MLX5_EN_WR); + + return 0; +} + +static int +mlx5_ib_map_mtt_mr_sg_pi(struct ib_mr *ibmr, struct scatterlist *data_sg, + int data_sg_nents, unsigned int *data_sg_offset, + struct scatterlist *meta_sg, int meta_sg_nents, + unsigned int *meta_sg_offset) +{ + struct mlx5_ib_mr *mr = to_mmr(ibmr); + struct mlx5_ib_mr *pi_mr = mr->mtt_mr; + int n; + + pi_mr->ndescs = 0; + pi_mr->meta_ndescs = 0; + pi_mr->meta_length = 0; + + ib_dma_sync_single_for_cpu(ibmr->device, pi_mr->desc_map, + pi_mr->desc_size * pi_mr->max_descs, + DMA_TO_DEVICE); + + pi_mr->ibmr.page_size = ibmr->page_size; + n = ib_sg_to_pages(&pi_mr->ibmr, data_sg, data_sg_nents, data_sg_offset, + mlx5_set_page); + if (n != data_sg_nents) + return n; + + pi_mr->data_iova = pi_mr->ibmr.iova; + pi_mr->data_length = pi_mr->ibmr.length; + pi_mr->ibmr.length = pi_mr->data_length; + ibmr->length = pi_mr->data_length; + + if (meta_sg_nents) { + u64 page_mask = ~((u64)ibmr->page_size - 1); + u64 iova = pi_mr->data_iova; + + n += ib_sg_to_pages(&pi_mr->ibmr, meta_sg, meta_sg_nents, + meta_sg_offset, mlx5_set_page_pi); + + pi_mr->meta_length = pi_mr->ibmr.length; + /* + * PI address for the HW is the offset of the metadata address + * relative to the first data page address. + * It equals to first data page address + size of data pages + + * metadata offset at the first metadata page + */ + pi_mr->pi_iova = (iova & page_mask) + + pi_mr->ndescs * ibmr->page_size + + (pi_mr->ibmr.iova & ~page_mask); + /* + * In order to use one MTT MR for data and metadata, we register + * also the gaps between the end of the data and the start of + * the metadata (the sig MR will verify that the HW will access + * to right addresses). This mapping is safe because we use + * internal mkey for the registration. + */ + pi_mr->ibmr.length = pi_mr->pi_iova + pi_mr->meta_length - iova; + pi_mr->ibmr.iova = iova; + ibmr->length += pi_mr->meta_length; + } + + ib_dma_sync_single_for_device(ibmr->device, pi_mr->desc_map, + pi_mr->desc_size * pi_mr->max_descs, + DMA_TO_DEVICE); + + return n; +} + +static int +mlx5_ib_map_klm_mr_sg_pi(struct ib_mr *ibmr, struct scatterlist *data_sg, + int data_sg_nents, unsigned int *data_sg_offset, + struct scatterlist *meta_sg, int meta_sg_nents, + unsigned int *meta_sg_offset) +{ + struct mlx5_ib_mr *mr = to_mmr(ibmr); + struct mlx5_ib_mr *pi_mr = mr->klm_mr; + int n; + + pi_mr->ndescs = 0; + pi_mr->meta_ndescs = 0; + pi_mr->meta_length = 0; + + ib_dma_sync_single_for_cpu(ibmr->device, pi_mr->desc_map, + pi_mr->desc_size * pi_mr->max_descs, + DMA_TO_DEVICE); + + n = mlx5_ib_sg_to_klms(pi_mr, data_sg, data_sg_nents, data_sg_offset, + meta_sg, meta_sg_nents, meta_sg_offset); + + ib_dma_sync_single_for_device(ibmr->device, pi_mr->desc_map, + pi_mr->desc_size * pi_mr->max_descs, + DMA_TO_DEVICE); + + /* This is zero-based memory region */ + pi_mr->data_iova = 0; + pi_mr->ibmr.iova = 0; + pi_mr->pi_iova = pi_mr->data_length; + ibmr->length = pi_mr->ibmr.length; + + return n; +} + +int mlx5_ib_map_mr_sg_pi(struct ib_mr *ibmr, struct scatterlist *data_sg, + int data_sg_nents, unsigned int *data_sg_offset, + struct scatterlist *meta_sg, int meta_sg_nents, + unsigned int *meta_sg_offset) +{ + struct mlx5_ib_mr *mr = to_mmr(ibmr); + struct mlx5_ib_mr *pi_mr = NULL; + int n; + + WARN_ON(ibmr->type != IB_MR_TYPE_INTEGRITY); + + mr->ndescs = 0; + mr->data_length = 0; + mr->data_iova = 0; + mr->meta_ndescs = 0; + mr->pi_iova = 0; + /* + * As a performance optimization, if possible, there is no need to + * perform UMR operation to register the data/metadata buffers. + * First try to map the sg lists to PA descriptors with local_dma_lkey. + * Fallback to UMR only in case of a failure. + */ + n = mlx5_ib_map_pa_mr_sg_pi(ibmr, data_sg, data_sg_nents, + data_sg_offset, meta_sg, meta_sg_nents, + meta_sg_offset); + if (n == data_sg_nents + meta_sg_nents) + goto out; + /* + * As a performance optimization, if possible, there is no need to map + * the sg lists to KLM descriptors. First try to map the sg lists to MTT + * descriptors and fallback to KLM only in case of a failure. + * It's more efficient for the HW to work with MTT descriptors + * (especially in high load). + * Use KLM (indirect access) only if it's mandatory. + */ + pi_mr = mr->mtt_mr; + n = mlx5_ib_map_mtt_mr_sg_pi(ibmr, data_sg, data_sg_nents, + data_sg_offset, meta_sg, meta_sg_nents, + meta_sg_offset); + if (n == data_sg_nents + meta_sg_nents) + goto out; + + pi_mr = mr->klm_mr; + n = mlx5_ib_map_klm_mr_sg_pi(ibmr, data_sg, data_sg_nents, + data_sg_offset, meta_sg, meta_sg_nents, + meta_sg_offset); + if (unlikely(n != data_sg_nents + meta_sg_nents)) + return -ENOMEM; + +out: + /* This is zero-based memory region */ + ibmr->iova = 0; + mr->pi_mr = pi_mr; + if (pi_mr) + ibmr->sig_attrs->meta_length = pi_mr->meta_length; + else + ibmr->sig_attrs->meta_length = mr->meta_length; + + return 0; +} + int mlx5_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents, unsigned int *sg_offset) { @@@ -2321,8 -1946,7 +2321,8 @@@ DMA_TO_DEVICE);

if (mr->access_mode == MLX5_MKC_ACCESS_MODE_KLMS) - n = mlx5_ib_sg_to_klms(mr, sg, sg_nents, sg_offset); + n = mlx5_ib_sg_to_klms(mr, sg, sg_nents, sg_offset, NULL, 0, + NULL); else n = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, mlx5_set_page); diff --combined drivers/infiniband/hw/mlx5/odp.c index 3d18b6ea9efa,831c450b271a..5b642d81e617 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@@ -150,7 -150,7 +150,7 @@@ static struct ib_umem_odp *odp_lookup(u if (!rb) goto not_found; odp = rb_entry(rb, struct ib_umem_odp, interval_tree.rb); - if (ib_umem_start(&odp->umem) > start + length) + if (ib_umem_start(odp) > start + length) goto not_found; } not_found: @@@ -200,7 -200,7 +200,7 @@@ void mlx5_odp_populate_klm(struct mlx5_ static void mr_leaf_free_action(struct work_struct *work) { struct ib_umem_odp *odp = container_of(work, struct ib_umem_odp, work); - int idx = ib_umem_start(&odp->umem) >> MLX5_IMR_MTT_SHIFT; + int idx = ib_umem_start(odp) >> MLX5_IMR_MTT_SHIFT; struct mlx5_ib_mr *mr = odp->private, *imr = mr->parent;

mr->parent = NULL; @@@ -224,6 -224,7 +224,6 @@@ void mlx5_ib_invalidate_range(struct ib const u64 umr_block_mask = (MLX5_UMR_MTT_ALIGNMENT / sizeof(struct mlx5_mtt)) - 1; u64 idx = 0, blk_start_idx = 0; - struct ib_umem *umem; int in_block = 0; u64 addr;

@@@ -231,14 -232,15 +231,14 @@@ pr_err("invalidation called on NULL umem or non-ODP umem\n"); return; } - umem = &umem_odp->umem;

mr = umem_odp->private;

if (!mr || !mr->ibmr.pd) return;

- start = max_t(u64, ib_umem_start(umem), start); - end = min_t(u64, ib_umem_end(umem), end); + start = max_t(u64, ib_umem_start(umem_odp), start); + end = min_t(u64, ib_umem_end(umem_odp), end);

/* * Iteration one - zap the HW's MTTs. The notifiers_count ensures that @@@ -247,8 -249,8 +247,8 @@@ * but they will write 0s as well, so no difference in the end result. */

- for (addr = start; addr < end; addr += BIT(umem->page_shift)) { - idx = (addr - ib_umem_start(umem)) >> umem->page_shift; + for (addr = start; addr < end; addr += BIT(umem_odp->page_shift)) { + idx = (addr - ib_umem_start(umem_odp)) >> umem_odp->page_shift; /* * Strive to write the MTTs in chunks, but avoid overwriting * non-existing MTTs. The huristic here can be improved to @@@ -542,12 -544,13 +542,12 @@@ static int mr_leaf_free(struct ib_umem_ void *cookie) { struct mlx5_ib_mr *mr = umem_odp->private, *imr = cookie; - struct ib_umem *umem = &umem_odp->umem;

if (mr->parent != imr) return 0;

- ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem), - ib_umem_end(umem)); + ib_umem_odp_unmap_dma_pages(umem_odp, ib_umem_start(umem_odp), + ib_umem_end(umem_odp));

if (umem_odp->dying) return 0; @@@ -599,9 -602,9 +599,9 @@@ static int pagefault_mr(struct mlx5_ib_ }

next_mr: - size = min_t(size_t, bcnt, ib_umem_end(&odp->umem) - io_virt); + size = min_t(size_t, bcnt, ib_umem_end(odp) - io_virt);

- page_shift = mr->umem->page_shift; + page_shift = odp->page_shift; page_mask = ~(BIT(page_shift) - 1); start_idx = (io_virt - (mr->mmkey.iova & page_mask)) >> page_shift; access_mask = ODP_READ_ALLOWED_BIT; @@@ -765,7 -768,7 +765,7 @@@ static int pagefault_single_data_segmen bcnt -= *bytes_committed;

next_mr: - mmkey = __mlx5_mr_lookup(dev->mdev, mlx5_base_mkey(key)); + mmkey = xa_load(&dev->mdev->priv.mkey_table, mlx5_base_mkey(key)); if (!mkey_is_eq(mmkey, key)) { mlx5_ib_dbg(dev, "failed to find mkey %x\n", key); ret = -EFAULT; @@@ -1555,9 -1558,9 +1555,9 @@@ mlx5_ib_create_pf_eq(struct mlx5_ib_de eq->irq_nb.notifier_call = mlx5_ib_eq_pf_int; param = (struct mlx5_eq_param) { .irq_index = 0, - .mask = 1 << MLX5_EVENT_TYPE_PAGE_FAULT, .nent = MLX5_IB_NUM_PF_EQE, }; + param.mask[0] = 1ull << MLX5_EVENT_TYPE_PAGE_FAULT; eq->core = mlx5_eq_create_generic(dev->mdev, &param); if (IS_ERR(eq->core)) { err = PTR_ERR(eq->core); @@@ -1683,8 -1686,8 +1683,8 @@@ static void num_pending_prefetch_dec(st struct mlx5_core_mkey *mmkey; struct mlx5_ib_mr *mr;

- mmkey = __mlx5_mr_lookup(dev->mdev, - mlx5_base_mkey(sg_list[i].lkey)); + mmkey = xa_load(&dev->mdev->priv.mkey_table, + mlx5_base_mkey(sg_list[i].lkey)); mr = container_of(mmkey, struct mlx5_ib_mr, mmkey); atomic_dec(&mr->num_pending_prefetch); } @@@ -1703,8 -1706,8 +1703,8 @@@ static bool num_pending_prefetch_inc(st struct mlx5_core_mkey *mmkey; struct mlx5_ib_mr *mr;

- mmkey = __mlx5_mr_lookup(dev->mdev, - mlx5_base_mkey(sg_list[i].lkey)); + mmkey = xa_load(&dev->mdev->priv.mkey_table, + mlx5_base_mkey(sg_list[i].lkey)); if (!mmkey || mmkey->key != sg_list[i].lkey) { ret = false; break; diff --combined drivers/infiniband/hw/mlx5/qp.c index 4fbf60fed374,768c7e81f688..8b7a60ada92c --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@@ -442,9 -442,9 +442,9 @@@ static int calc_send_wqe(struct ib_qp_i }

size += attr->cap.max_send_sge * sizeof(struct mlx5_wqe_data_seg); - if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN && + if (attr->create_flags & IB_QP_CREATE_INTEGRITY_EN && ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB) < MLX5_SIG_WQE_SIZE) - return MLX5_SIG_WQE_SIZE; + return MLX5_SIG_WQE_SIZE; else return ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB); } @@@ -496,6 -496,9 +496,6 @@@ static int calc_sq_size(struct mlx5_ib_ sizeof(struct mlx5_wqe_inline_seg); attr->cap.max_inline_data = qp->max_inline_data;

- if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN) - qp->signature_en = true; - wq_size = roundup_pow_of_two(attr->cap.max_send_wr * wqe_size); qp->sq.wqe_cnt = wq_size / MLX5_SEND_WQE_BB; if (qp->sq.wqe_cnt > (1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz))) { @@@ -787,7 -790,8 +787,7 @@@ static void destroy_user_rq(struct mlx5 atomic_dec(&dev->delay_drop.rqs_cnt);

mlx5_ib_db_unmap_user(context, &rwq->db); - if (rwq->umem) - ib_umem_release(rwq->umem); + ib_umem_release(rwq->umem); }

static int create_user_rq(struct mlx5_ib_dev *dev, struct ib_pd *pd, @@@ -973,7 -977,8 +973,7 @@@ err_free kvfree(*in);

err_umem: - if (ubuffer->umem) - ib_umem_release(ubuffer->umem); + ib_umem_release(ubuffer->umem);

err_bfreg: if (bfregn != MLX5_IB_INVALID_BFREG) @@@ -992,7 -997,8 +992,7 @@@ static void destroy_qp_user(struct mlx5 ibucontext);

mlx5_ib_db_unmap_user(context, &qp->db); - if (base->ubuffer.umem) - ib_umem_release(base->ubuffer.umem); + ib_umem_release(base->ubuffer.umem);

/* * Free only the BFREGs which are handled by the kernel. @@@ -1036,7 -1042,7 +1036,7 @@@ static int create_kernel_qp(struct mlx5 void *qpc; int err;

- if (init_attr->create_flags & ~(IB_QP_CREATE_SIGNATURE_EN | + if (init_attr->create_flags & ~(IB_QP_CREATE_INTEGRITY_EN | IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK | IB_QP_CREATE_IPOIB_UD_LSO | IB_QP_CREATE_NETIF_QP | @@@ -4164,13 -4170,15 +4164,13 @@@ static __be64 sig_mkey_mask(void }

static void set_reg_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr, - struct mlx5_ib_mr *mr, bool umr_inline) + struct mlx5_ib_mr *mr, u8 flags) { - int size = mr->ndescs * mr->desc_size; + int size = (mr->ndescs + mr->meta_ndescs) * mr->desc_size;

memset(umr, 0, sizeof(*umr));

- umr->flags = MLX5_UMR_CHECK_NOT_FREE; - if (umr_inline) - umr->flags |= MLX5_UMR_INLINE; + umr->flags = flags; umr->xlt_octowords = cpu_to_be16(get_xlt_octo(size)); umr->mkey_mask = frwr_mkey_mask(); } @@@ -4297,7 -4305,7 +4297,7 @@@ static void set_reg_mkey_seg(struct mlx struct mlx5_ib_mr *mr, u32 key, int access) { - int ndescs = ALIGN(mr->ndescs, 8) >> 1; + int ndescs = ALIGN(mr->ndescs + mr->meta_ndescs, 8) >> 1;

memset(seg, 0, sizeof(*seg));

@@@ -4348,7 -4356,7 +4348,7 @@@ static void set_reg_data_seg(struct mlx struct mlx5_ib_mr *mr, struct mlx5_ib_pd *pd) { - int bcount = mr->desc_size * mr->ndescs; + int bcount = mr->desc_size * (mr->ndescs + mr->meta_ndescs);

dseg->addr = cpu_to_be64(mr->desc_map); dseg->byte_count = cpu_to_be32(ALIGN(bcount, 64)); @@@ -4541,37 -4549,23 +4541,37 @@@ static int mlx5_set_bsf(struct ib_mr *s return 0; }

-static int set_sig_data_segment(const struct ib_sig_handover_wr *wr, - struct mlx5_ib_qp *qp, void **seg, - int *size, void **cur_edge) +static int set_sig_data_segment(const struct ib_send_wr *send_wr, + struct ib_mr *sig_mr, + struct ib_sig_attrs *sig_attrs, + struct mlx5_ib_qp *qp, void **seg, int *size, + void **cur_edge) { - struct ib_sig_attrs *sig_attrs = wr->sig_attrs; - struct ib_mr *sig_mr = wr->sig_mr; struct mlx5_bsf *bsf; - u32 data_len = wr->wr.sg_list->length; - u32 data_key = wr->wr.sg_list->lkey; - u64 data_va = wr->wr.sg_list->addr; + u32 data_len; + u32 data_key; + u64 data_va; + u32 prot_len = 0; + u32 prot_key = 0; + u64 prot_va = 0; + bool prot = false; int ret; int wqe_size; + struct mlx5_ib_mr *mr = to_mmr(sig_mr); + struct mlx5_ib_mr *pi_mr = mr->pi_mr; + + data_len = pi_mr->data_length; + data_key = pi_mr->ibmr.lkey; + data_va = pi_mr->data_iova; + if (pi_mr->meta_ndescs) { + prot_len = pi_mr->meta_length; + prot_key = pi_mr->ibmr.lkey; + prot_va = pi_mr->pi_iova; + prot = true; + }

- if (!wr->prot || - (data_key == wr->prot->lkey && - data_va == wr->prot->addr && - data_len == wr->prot->length)) { + if (!prot || (data_key == prot_key && data_va == prot_va && + data_len == prot_len)) { /** * Source domain doesn't contain signature information * or data and protection are interleaved in memory. @@@ -4605,6 -4599,8 +4605,6 @@@ struct mlx5_stride_block_ctrl_seg *sblock_ctrl; struct mlx5_stride_block_entry *data_sentry; struct mlx5_stride_block_entry *prot_sentry; - u32 prot_key = wr->prot->lkey; - u64 prot_va = wr->prot->addr; u16 block_size = sig_attrs->mem.sig.dif.pi_interval; int prot_size;

@@@ -4654,15 -4650,17 +4654,15 @@@ }

static void set_sig_mkey_segment(struct mlx5_mkey_seg *seg, - const struct ib_sig_handover_wr *wr, u32 size, - u32 length, u32 pdn) + struct ib_mr *sig_mr, int access_flags, + u32 size, u32 length, u32 pdn) { - struct ib_mr *sig_mr = wr->sig_mr; u32 sig_key = sig_mr->rkey; u8 sigerr = to_mmr(sig_mr)->sig->sigerr_count & 1;

memset(seg, 0, sizeof(*seg));

- seg->flags = get_umr_flags(wr->access_flags) | - MLX5_MKC_ACCESS_MODE_KLMS; + seg->flags = get_umr_flags(access_flags) | MLX5_MKC_ACCESS_MODE_KLMS; seg->qpn_mkey7_0 = cpu_to_be32((sig_key & 0xff) | 0xffffff00); seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL | sigerr << 26 | MLX5_MKEY_BSF_EN | pdn); @@@ -4682,50 -4680,49 +4682,50 @@@ static void set_sig_umr_segment(struct umr->mkey_mask = sig_mkey_mask(); }

- -static int set_sig_umr_wr(const struct ib_send_wr *send_wr, - struct mlx5_ib_qp *qp, void **seg, int *size, - void **cur_edge) +static int set_pi_umr_wr(const struct ib_send_wr *send_wr, + struct mlx5_ib_qp *qp, void **seg, int *size, + void **cur_edge) { - const struct ib_sig_handover_wr *wr = sig_handover_wr(send_wr); - struct mlx5_ib_mr *sig_mr = to_mmr(wr->sig_mr); + const struct ib_reg_wr *wr = reg_wr(send_wr); + struct mlx5_ib_mr *sig_mr = to_mmr(wr->mr); + struct mlx5_ib_mr *pi_mr = sig_mr->pi_mr; + struct ib_sig_attrs *sig_attrs = sig_mr->ibmr.sig_attrs; u32 pdn = get_pd(qp)->pdn; u32 xlt_size; int region_len, ret;

- if (unlikely(wr->wr.num_sge != 1) || - unlikely(wr->access_flags & IB_ACCESS_REMOTE_ATOMIC) || - unlikely(!sig_mr->sig) || unlikely(!qp->signature_en) || + if (unlikely(send_wr->num_sge != 0) || + unlikely(wr->access & IB_ACCESS_REMOTE_ATOMIC) || + unlikely(!sig_mr->sig) || unlikely(!qp->ibqp.integrity_en) || unlikely(!sig_mr->sig->sig_status_checked)) return -EINVAL;

/* length of the protected region, data + protection */ - region_len = wr->wr.sg_list->length; - if (wr->prot && - (wr->prot->lkey != wr->wr.sg_list->lkey || - wr->prot->addr != wr->wr.sg_list->addr || - wr->prot->length != wr->wr.sg_list->length)) - region_len += wr->prot->length; + region_len = pi_mr->ibmr.length;

/** * KLM octoword size - if protection was provided * then we use strided block format (3 octowords), * else we use single KLM (1 octoword) **/ - xlt_size = wr->prot ? 0x30 : sizeof(struct mlx5_klm); + if (sig_attrs->mem.sig_type != IB_SIG_TYPE_NONE) + xlt_size = 0x30; + else + xlt_size = sizeof(struct mlx5_klm);

set_sig_umr_segment(*seg, xlt_size); *seg += sizeof(struct mlx5_wqe_umr_ctrl_seg); *size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16; handle_post_send_edge(&qp->sq, seg, *size, cur_edge);

- set_sig_mkey_segment(*seg, wr, xlt_size, region_len, pdn); + set_sig_mkey_segment(*seg, wr->mr, wr->access, xlt_size, region_len, + pdn); *seg += sizeof(struct mlx5_mkey_seg); *size += sizeof(struct mlx5_mkey_seg) / 16; handle_post_send_edge(&qp->sq, seg, *size, cur_edge);

- ret = set_sig_data_segment(wr, qp, seg, size, cur_edge); + ret = set_sig_data_segment(send_wr, wr->mr, sig_attrs, qp, seg, size, + cur_edge); if (ret) return ret;

@@@ -4762,14 -4759,12 +4762,14 @@@ static int set_psv_wr(struct ib_sig_dom

static int set_reg_wr(struct mlx5_ib_qp *qp, const struct ib_reg_wr *wr, - void **seg, int *size, void **cur_edge) + void **seg, int *size, void **cur_edge, + bool check_not_free) { struct mlx5_ib_mr *mr = to_mmr(wr->mr); struct mlx5_ib_pd *pd = to_mpd(qp->ibqp.pd); - size_t mr_list_size = mr->ndescs * mr->desc_size; + int mr_list_size = (mr->ndescs + mr->meta_ndescs) * mr->desc_size; bool umr_inline = mr_list_size <= MLX5_IB_SQ_UMR_INLINE_THRESHOLD; + u8 flags = 0;

if (unlikely(wr->wr.send_flags & IB_SEND_INLINE)) { mlx5_ib_warn(to_mdev(qp->ibqp.device), @@@ -4777,12 -4772,7 +4777,12 @@@ return -EINVAL; }

- set_reg_umr_seg(*seg, mr, umr_inline); + if (check_not_free) + flags |= MLX5_UMR_CHECK_NOT_FREE; + if (umr_inline) + flags |= MLX5_UMR_INLINE; + + set_reg_umr_seg(*seg, mr, flags); *seg += sizeof(struct mlx5_wqe_umr_ctrl_seg); *size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16; handle_post_send_edge(&qp->sq, seg, *size, cur_edge); @@@ -4908,12 -4898,8 +4908,12 @@@ static int _mlx5_ib_post_send(struct ib struct mlx5_wqe_ctrl_seg *ctrl = NULL; /* compiler warning */ struct mlx5_ib_dev *dev = to_mdev(ibqp->device); struct mlx5_core_dev *mdev = dev->mdev; + struct ib_reg_wr reg_pi_wr; struct mlx5_ib_qp *qp; struct mlx5_ib_mr *mr; + struct mlx5_ib_mr *pi_mr; + struct mlx5_ib_mr pa_pi_mr; + struct ib_sig_attrs *sig_attrs; struct mlx5_wqe_xrc_seg *xrc; struct mlx5_bf *bf; void *cur_edge; @@@ -4967,8 -4953,7 +4967,8 @@@ goto out; }

- if (wr->opcode == IB_WR_REG_MR) { + if (wr->opcode == IB_WR_REG_MR || + wr->opcode == IB_WR_REG_MR_INTEGRITY) { fence = dev->umr_fence; next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL; } else { @@@ -5018,7 -5003,7 +5018,7 @@@ qp->sq.wr_data[idx] = IB_WR_REG_MR; ctrl->imm = cpu_to_be32(reg_wr(wr)->key); err = set_reg_wr(qp, reg_wr(wr), &seg, &size, - &cur_edge); + &cur_edge, true); if (err) { *bad_wr = wr; goto out; @@@ -5026,82 -5011,26 +5026,82 @@@ num_sge = 0; break;

- case IB_WR_REG_SIG_MR: - qp->sq.wr_data[idx] = IB_WR_REG_SIG_MR; - mr = to_mmr(sig_handover_wr(wr)->sig_mr); - + case IB_WR_REG_MR_INTEGRITY: + qp->sq.wr_data[idx] = IB_WR_REG_MR_INTEGRITY; + + mr = to_mmr(reg_wr(wr)->mr); + pi_mr = mr->pi_mr; + + if (pi_mr) { + memset(&reg_pi_wr, 0, + sizeof(struct ib_reg_wr)); + + reg_pi_wr.mr = &pi_mr->ibmr; + reg_pi_wr.access = reg_wr(wr)->access; + reg_pi_wr.key = pi_mr->ibmr.rkey; + + ctrl->imm = cpu_to_be32(reg_pi_wr.key); + /* UMR for data + prot registration */ + err = set_reg_wr(qp, &reg_pi_wr, &seg, + &size, &cur_edge, + false); + if (err) { + *bad_wr = wr; + goto out; + } + finish_wqe(qp, ctrl, seg, size, + cur_edge, idx, wr->wr_id, + nreq, fence, + MLX5_OPCODE_UMR); + + err = begin_wqe(qp, &seg, &ctrl, wr, + &idx, &size, &cur_edge, + nreq); + if (err) { + mlx5_ib_warn(dev, "\n"); + err = -ENOMEM; + *bad_wr = wr; + goto out; + } + } else { + memset(&pa_pi_mr, 0, + sizeof(struct mlx5_ib_mr)); + /* No UMR, use local_dma_lkey */ + pa_pi_mr.ibmr.lkey = + mr->ibmr.pd->local_dma_lkey; + + pa_pi_mr.ndescs = mr->ndescs; + pa_pi_mr.data_length = mr->data_length; + pa_pi_mr.data_iova = mr->data_iova; + if (mr->meta_ndescs) { + pa_pi_mr.meta_ndescs = + mr->meta_ndescs; + pa_pi_mr.meta_length = + mr->meta_length; + pa_pi_mr.pi_iova = mr->pi_iova; + } + + pa_pi_mr.ibmr.length = mr->ibmr.length; + mr->pi_mr = &pa_pi_mr; + } ctrl->imm = cpu_to_be32(mr->ibmr.rkey); - err = set_sig_umr_wr(wr, qp, &seg, &size, - &cur_edge); + /* UMR for sig MR */ + err = set_pi_umr_wr(wr, qp, &seg, &size, + &cur_edge); if (err) { mlx5_ib_warn(dev, "\n"); *bad_wr = wr; goto out; } - finish_wqe(qp, ctrl, seg, size, cur_edge, idx, wr->wr_id, nreq, fence, MLX5_OPCODE_UMR); + /* * SET_PSV WQEs are not signaled and solicited * on error */ + sig_attrs = mr->ibmr.sig_attrs; err = __begin_wqe(qp, &seg, &ctrl, wr, &idx, &size, &cur_edge, nreq, false, true); @@@ -5111,18 -5040,19 +5111,18 @@@ *bad_wr = wr; goto out; } - - err = set_psv_wr(&sig_handover_wr(wr)->sig_attrs->mem, - mr->sig->psv_memory.psv_idx, &seg, - &size); + err = set_psv_wr(&sig_attrs->mem, + mr->sig->psv_memory.psv_idx, + &seg, &size); if (err) { mlx5_ib_warn(dev, "\n"); *bad_wr = wr; goto out; } - finish_wqe(qp, ctrl, seg, size, cur_edge, idx, - wr->wr_id, nreq, fence, + wr->wr_id, nreq, next_fence, MLX5_OPCODE_SET_PSV); + err = __begin_wqe(qp, &seg, &ctrl, wr, &idx, &size, &cur_edge, nreq, false, true); @@@ -5132,20 -5062,20 +5132,20 @@@ *bad_wr = wr; goto out; } - - err = set_psv_wr(&sig_handover_wr(wr)->sig_attrs->wire, - mr->sig->psv_wire.psv_idx, &seg, - &size); + err = set_psv_wr(&sig_attrs->wire, + mr->sig->psv_wire.psv_idx, + &seg, &size); if (err) { mlx5_ib_warn(dev, "\n"); *bad_wr = wr; goto out; } - finish_wqe(qp, ctrl, seg, size, cur_edge, idx, - wr->wr_id, nreq, fence, + wr->wr_id, nreq, next_fence, MLX5_OPCODE_SET_PSV); - qp->next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL; + + qp->next_fence = + MLX5_FENCE_MODE_INITIATOR_SMALL; num_sge = 0; goto skip_psv;

@@@ -6117,7 -6047,7 +6117,7 @@@ err return ERR_PTR(err); }

-int mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata) +void mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata) { struct mlx5_ib_dev *dev = to_mdev(wq->device); struct mlx5_ib_rwq *rwq = to_mrwq(wq); @@@ -6125,6 -6055,8 +6125,6 @@@ mlx5_core_destroy_rq_tracked(dev->mdev, &rwq->core_qp); destroy_user_rq(dev, wq->pd, rwq, udata); kfree(rwq); - - return 0; }

struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device, @@@ -6365,7 -6297,7 +6365,7 @@@ static void handle_drain_completion(str /* Run the CQ handler - this makes sure that the drain WR will * be processed if wasn't processed yet. */ - mcq->mcq.comp(&mcq->mcq); + mcq->mcq.comp(&mcq->mcq, NULL); }

wait_for_completion(&sdrain->done); diff --combined drivers/infiniband/hw/qedr/main.c index a0a7ba0a5af4,5ebf3c53b3fb..533157a2a3be --- a/drivers/infiniband/hw/qedr/main.c +++ b/drivers/infiniband/hw/qedr/main.c @@@ -183,10 -183,6 +183,10 @@@ static void qedr_roce_register_device(s }

static const struct ib_device_ops qedr_dev_ops = { + .owner = THIS_MODULE, + .driver_id = RDMA_DRIVER_QEDR, + .uverbs_abi_ver = QEDR_ABI_VERSION, + .alloc_mr = qedr_alloc_mr, .alloc_pd = qedr_alloc_pd, .alloc_ucontext = qedr_alloc_ucontext, @@@ -224,7 -220,6 +224,7 @@@ .resize_cq = qedr_resize_cq,

INIT_RDMA_OBJ_SIZE(ib_ah, qedr_ah, ibah), + INIT_RDMA_OBJ_SIZE(ib_cq, qedr_cq, ibcq), INIT_RDMA_OBJ_SIZE(ib_pd, qedr_pd, ibpd), INIT_RDMA_OBJ_SIZE(ib_srq, qedr_srq, ibsrq), INIT_RDMA_OBJ_SIZE(ib_ucontext, qedr_ucontext, ibucontext), @@@ -236,6 -231,8 +236,6 @@@ static int qedr_register_device(struct

dev->ibdev.node_guid = dev->attr.node_guid; memcpy(dev->ibdev.node_desc, QEDR_NODE_DESC, sizeof(QEDR_NODE_DESC)); - dev->ibdev.owner = THIS_MODULE; - dev->ibdev.uverbs_abi_ver = QEDR_ABI_VERSION;

dev->ibdev.uverbs_cmd_mask = QEDR_UVERBS(GET_CONTEXT) | QEDR_UVERBS(QUERY_DEVICE) | @@@ -277,6 -274,7 +277,6 @@@ rdma_set_device_sysfs_group(&dev->ibdev, &qedr_attr_group); ib_set_device_ops(&dev->ibdev, &qedr_dev_ops);

- dev->ibdev.driver_id = RDMA_DRIVER_QEDR; rc = ib_device_set_netdev(&dev->ibdev, dev->ndev, 1); if (rc) return rc; @@@ -314,7 -312,8 +314,8 @@@ static void qedr_free_mem_sb(struct qed struct qed_sb_info *sb_info, int sb_id) { if (sb_info->sb_virt) { - dev->ops->common->sb_release(dev->cdev, sb_info, sb_id); + dev->ops->common->sb_release(dev->cdev, sb_info, sb_id, + QED_SB_TYPE_CNQ); dma_free_coherent(&dev->pdev->dev, sizeof(*sb_info->sb_virt), (void *)sb_info->sb_virt, sb_info->sb_phys); } @@@ -506,11 -505,13 +507,13 @@@ static irqreturn_t qedr_irq_handler(in static void qedr_sync_free_irqs(struct qedr_dev *dev) { u32 vector; + u16 idx; int i;

for (i = 0; i < dev->int_info.used_cnt; i++) { if (dev->int_info.msix_cnt) { - vector = dev->int_info.msix[i * dev->num_hwfns].vector; + idx = i * dev->num_hwfns + dev->affin_hwfn_idx; + vector = dev->int_info.msix[idx].vector; synchronize_irq(vector); free_irq(vector, &dev->cnq_array[i]); } @@@ -522,6 -523,7 +525,7 @@@ static int qedr_req_msix_irqs(struct qedr_dev *dev) { int i, rc = 0; + u16 idx;

if (dev->num_cnq > dev->int_info.msix_cnt) { DP_ERR(dev, @@@ -531,7 -533,8 +535,8 @@@ }

for (i = 0; i < dev->num_cnq; i++) { - rc = request_irq(dev->int_info.msix[i * dev->num_hwfns].vector, + idx = i * dev->num_hwfns + dev->affin_hwfn_idx; + rc = request_irq(dev->int_info.msix[idx].vector, qedr_irq_handler, 0, dev->cnq_array[i].name, &dev->cnq_array[i]); if (rc) { @@@ -868,6 -871,16 +873,16 @@@ static struct qedr_dev *qedr_add(struc dev->user_dpm_enabled = dev_info.user_dpm_enabled; dev->rdma_type = dev_info.rdma_type; dev->num_hwfns = dev_info.common.num_hwfns; + + if (IS_IWARP(dev) && QEDR_IS_CMT(dev)) { + rc = dev->ops->iwarp_set_engine_affin(cdev, false); + if (rc) { + DP_ERR(dev, "iWARP is disabled over a 100g device Enabling it may impact L2 performance. To enable it run devlink dev param set <dev> name iwarp_cmt value true cmode runtime\n"); + goto init_err; + } + } + dev->affin_hwfn_idx = dev->ops->common->get_affin_hwfn_idx(cdev); + dev->rdma_ctx = dev->ops->rdma_get_rdma_ctx(cdev);

dev->num_cnq = dev->ops->rdma_get_min_cnq_msix(cdev); @@@ -928,6 -941,10 +943,10 @@@ static void qedr_remove(struct qedr_de qedr_stop_hw(dev); qedr_sync_free_irqs(dev); qedr_free_resources(dev); + + if (IS_IWARP(dev) && QEDR_IS_CMT(dev)) + dev->ops->iwarp_set_engine_affin(dev->cdev, true); + ib_dealloc_device(&dev->ibdev); }

diff --combined drivers/infiniband/hw/usnic/usnic_ib_main.c index 6ae5ce007fed,34c1f9d6c915..03f54eb9404b --- a/drivers/infiniband/hw/usnic/usnic_ib_main.c +++ b/drivers/infiniband/hw/usnic/usnic_ib_main.c @@@ -329,10 -329,6 +329,10 @@@ static void usnic_get_dev_fw_str(struc }

static const struct ib_device_ops usnic_dev_ops = { + .owner = THIS_MODULE, + .driver_id = RDMA_DRIVER_USNIC, + .uverbs_abi_ver = USNIC_UVERBS_ABI_VERSION, + .alloc_pd = usnic_ib_alloc_pd, .alloc_ucontext = usnic_ib_alloc_ucontext, .create_cq = usnic_ib_create_cq, @@@ -354,7 -350,6 +354,7 @@@ .query_qp = usnic_ib_query_qp, .reg_user_mr = usnic_ib_reg_mr, INIT_RDMA_OBJ_SIZE(ib_pd, usnic_ib_pd, ibpd), + INIT_RDMA_OBJ_SIZE(ib_cq, usnic_ib_cq, ibcq), INIT_RDMA_OBJ_SIZE(ib_ucontext, usnic_ib_ucontext, ibucontext), };

@@@ -389,10 -384,12 +389,10 @@@ static void *usnic_ib_device_add(struc

us_ibdev->pdev = dev; us_ibdev->netdev = pci_get_drvdata(dev); - us_ibdev->ib_dev.owner = THIS_MODULE; us_ibdev->ib_dev.node_type = RDMA_NODE_USNIC_UDP; us_ibdev->ib_dev.phys_port_cnt = USNIC_IB_PORT_CNT; us_ibdev->ib_dev.num_comp_vectors = USNIC_IB_NUM_COMP_VECTORS; us_ibdev->ib_dev.dev.parent = &dev->dev; - us_ibdev->ib_dev.uverbs_abi_ver = USNIC_UVERBS_ABI_VERSION;

us_ibdev->ib_dev.uverbs_cmd_mask = (1ull << IB_USER_VERBS_CMD_GET_CONTEXT) | @@@ -415,6 -412,7 +415,6 @@@

ib_set_device_ops(&us_ibdev->ib_dev, &usnic_dev_ops);

- us_ibdev->ib_dev.driver_id = RDMA_DRIVER_USNIC; rdma_set_device_sysfs_group(&us_ibdev->ib_dev, &usnic_attr_group);

ret = ib_device_set_netdev(&us_ibdev->ib_dev, us_ibdev->netdev, 1); @@@ -429,11 -427,16 +429,16 @@@ if (netif_carrier_ok(us_ibdev->netdev)) usnic_fwd_carrier_up(us_ibdev->ufdev);

- ind = in_dev_get(netdev); - if (ind->ifa_list) - usnic_fwd_add_ipaddr(us_ibdev->ufdev, - ind->ifa_list->ifa_address); - in_dev_put(ind); + rcu_read_lock(); + ind = __in_dev_get_rcu(netdev); + if (ind) { + const struct in_ifaddr *ifa; + + ifa = rcu_dereference(ind->ifa_list); + if (ifa) + usnic_fwd_add_ipaddr(us_ibdev->ufdev, ifa->ifa_address); + } + rcu_read_unlock();

usnic_mac_ip_to_gid(us_ibdev->netdev->perm_addr, us_ibdev->ufdev->inaddr, &gid.raw[0]); diff --combined drivers/net/bonding/bond_main.c index b0aab3a0a1bf,302499ae05e6..9b7016abca2f --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@@ -613,8 -613,8 +613,8 @@@ static int bond_set_dev_addr(struct net { int err;

- netdev_dbg(bond_dev, "bond_dev=%p slave_dev=%p slave_dev->name=%s slave_dev->addr_len=%d\n", - bond_dev, slave_dev, slave_dev->name, slave_dev->addr_len); + slave_dbg(bond_dev, slave_dev, "bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n", + bond_dev, slave_dev, slave_dev->addr_len); err = dev_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL); if (err) return err; @@@ -661,8 -661,8 +661,8 @@@ static void bond_do_fail_over_mac(struc if (new_active) { rv = bond_set_dev_addr(bond->dev, new_active->dev); if (rv) - netdev_err(bond->dev, "Error %d setting MAC of slave %s\n", - -rv, bond->dev->name); + slave_err(bond->dev, new_active->dev, "Error %d setting bond MAC from slave\n", + -rv); } break; case BOND_FOM_FOLLOW: @@@ -692,8 -692,8 +692,8 @@@ rv = dev_set_mac_address(new_active->dev, (struct sockaddr *)&ss, NULL); if (rv) { - netdev_err(bond->dev, "Error %d setting MAC of slave %s\n", - -rv, new_active->dev->name); + slave_err(bond->dev, new_active->dev, "Error %d setting MAC of new active slave\n", + -rv); goto out; }

@@@ -707,8 -707,8 +707,8 @@@ rv = dev_set_mac_address(old_active->dev, (struct sockaddr *)&ss, NULL); if (rv) - netdev_err(bond->dev, "Error %d setting MAC of slave %s\n", - -rv, new_active->dev->name); + slave_err(bond->dev, old_active->dev, "Error %d setting MAC of old active slave\n", + -rv); out: break; default: @@@ -796,6 -796,8 +796,8 @@@ static bool bond_should_notify_peers(st slave ? slave->dev->name : "NULL");

if (!slave || !bond->send_peer_notif || + bond->send_peer_notif % + max(1, bond->params.peer_notif_delay) != 0 || !netif_carrier_ok(bond->dev) || test_bit(__LINK_STATE_LINKWATCH_PENDING, &slave->dev->state)) return false; @@@ -834,9 -836,8 +836,8 @@@ void bond_change_active_slave(struct bo

if (new_active->link == BOND_LINK_BACK) { if (bond_uses_primary(bond)) { - netdev_info(bond->dev, "making interface %s the new active one %d ms earlier\n", - new_active->dev->name, - (bond->params.updelay - new_active->delay) * bond->params.miimon); + slave_info(bond->dev, new_active->dev, "making interface the new active one %d ms earlier\n", + (bond->params.updelay - new_active->delay) * bond->params.miimon); }

new_active->delay = 0; @@@ -850,8 -851,7 +851,7 @@@ bond_alb_handle_link_change(bond, new_active, BOND_LINK_UP); } else { if (bond_uses_primary(bond)) { - netdev_info(bond->dev, "making interface %s the new active one\n", - new_active->dev->name); + slave_info(bond->dev, new_active->dev, "making interface the new active one\n"); } } } @@@ -888,15 -888,18 +888,18 @@@

if (netif_running(bond->dev)) { bond->send_peer_notif = - bond->params.num_peer_notif; + bond->params.num_peer_notif * + max(1, bond->params.peer_notif_delay); should_notify_peers = bond_should_notify_peers(bond); }

call_netdevice_notifiers(NETDEV_BONDING_FAILOVER, bond->dev); - if (should_notify_peers) + if (should_notify_peers) { + bond->send_peer_notif--; call_netdevice_notifiers(NETDEV_NOTIFY_PEERS, bond->dev); + } } }

@@@ -939,7 -942,7 +942,7 @@@ void bond_select_active_slave(struct bo return;

if (netif_carrier_ok(bond->dev)) - netdev_info(bond->dev, "first active interface up!\n"); + netdev_info(bond->dev, "active interface up!\n"); else netdev_info(bond->dev, "now running without any active interface!\n"); } @@@ -1077,12 -1080,16 +1080,16 @@@ static netdev_features_t bond_fix_featu #define BOND_ENC_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ NETIF_F_RXCSUM | NETIF_F_ALL_TSO)

+ #define BOND_MPLS_FEATURES (NETIF_F_HW_CSUM | NETIF_F_SG | \ + NETIF_F_ALL_TSO) + static void bond_compute_features(struct bonding *bond) { unsigned int dst_release_flag = IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM; netdev_features_t vlan_features = BOND_VLAN_FEATURES; netdev_features_t enc_features = BOND_ENC_FEATURES; + netdev_features_t mpls_features = BOND_MPLS_FEATURES; struct net_device *bond_dev = bond->dev; struct list_head *iter; struct slave *slave; @@@ -1093,6 -1100,7 +1100,7 @@@ if (!bond_has_slaves(bond)) goto done; vlan_features &= NETIF_F_ALL_FOR_ALL; + mpls_features &= NETIF_F_ALL_FOR_ALL;

bond_for_each_slave(bond, slave, iter) { vlan_features = netdev_increment_features(vlan_features, @@@ -1101,6 -1109,11 +1109,11 @@@ enc_features = netdev_increment_features(enc_features, slave->dev->hw_enc_features, BOND_ENC_FEATURES); + + mpls_features = netdev_increment_features(mpls_features, + slave->dev->mpls_features, + BOND_MPLS_FEATURES); + dst_release_flag &= slave->dev->priv_flags; if (slave->dev->hard_header_len > max_hard_header_len) max_hard_header_len = slave->dev->hard_header_len; @@@ -1114,6 -1127,7 +1127,7 @@@ done bond_dev->vlan_features = vlan_features; bond_dev->hw_enc_features = enc_features | NETIF_F_GSO_ENCAP_ALL | NETIF_F_GSO_UDP_L4; + bond_dev->mpls_features = mpls_features; bond_dev->gso_max_segs = gso_max_segs; netif_set_gso_max_size(bond_dev, gso_max_size);

@@@ -1369,15 -1383,14 +1383,14 @@@ int bond_enslave(struct net_device *bon if (!bond->params.use_carrier && slave_dev->ethtool_ops->get_link == NULL && slave_ops->ndo_do_ioctl == NULL) { - netdev_warn(bond_dev, "no link monitoring support for %s\n", - slave_dev->name); + slave_warn(bond_dev, slave_dev, "no link monitoring support\n"); }

/* already in-use? */ if (netdev_is_rx_handler_busy(slave_dev)) { NL_SET_ERR_MSG(extack, "Device is in use and cannot be enslaved"); - netdev_err(bond_dev, - "Error: Device is in use and cannot be enslaved\n"); + slave_err(bond_dev, slave_dev, + "Error: Device is in use and cannot be enslaved\n"); return -EBUSY; }

@@@ -1390,21 -1403,16 +1403,16 @@@ /* vlan challenged mutual exclusion */ /* no need to lock since we're protected by rtnl_lock */ if (slave_dev->features & NETIF_F_VLAN_CHALLENGED) { - netdev_dbg(bond_dev, "%s is NETIF_F_VLAN_CHALLENGED\n", - slave_dev->name); + slave_dbg(bond_dev, slave_dev, "is NETIF_F_VLAN_CHALLENGED\n"); if (vlan_uses_dev(bond_dev)) { NL_SET_ERR_MSG(extack, "Can not enslave VLAN challenged device to VLAN enabled bond"); - netdev_err(bond_dev, "Error: cannot enslave VLAN challenged slave %s on VLAN enabled bond %s\n", - slave_dev->name, bond_dev->name); + slave_err(bond_dev, slave_dev, "Error: cannot enslave VLAN challenged slave on VLAN enabled bond\n"); return -EPERM; } else { - netdev_warn(bond_dev, "enslaved VLAN challenged slave %s. Adding VLANs will be blocked as long as %s is part of bond %s\n", - slave_dev->name, slave_dev->name, - bond_dev->name); + slave_warn(bond_dev, slave_dev, "enslaved VLAN challenged slave. Adding VLANs will be blocked as long as it is part of bond.\n"); } } else { - netdev_dbg(bond_dev, "%s is !NETIF_F_VLAN_CHALLENGED\n", - slave_dev->name); + slave_dbg(bond_dev, slave_dev, "is !NETIF_F_VLAN_CHALLENGED\n"); }

/* Old ifenslave binaries are no longer supported. These can @@@ -1414,8 -1422,7 +1422,7 @@@ */ if (slave_dev->flags & IFF_UP) { NL_SET_ERR_MSG(extack, "Device can not be enslaved while up"); - netdev_err(bond_dev, "%s is up - this may be due to an out of date ifenslave\n", - slave_dev->name); + slave_err(bond_dev, slave_dev, "slave is up - this may be due to an out of date ifenslave\n"); return -EPERM; }

@@@ -1428,14 -1435,14 +1435,14 @@@ */ if (!bond_has_slaves(bond)) { if (bond_dev->type != slave_dev->type) { - netdev_dbg(bond_dev, "change device type from %d to %d\n", - bond_dev->type, slave_dev->type); + slave_dbg(bond_dev, slave_dev, "change device type from %d to %d\n", + bond_dev->type, slave_dev->type);

res = call_netdevice_notifiers(NETDEV_PRE_TYPE_CHANGE, bond_dev); res = notifier_to_errno(res); if (res) { - netdev_err(bond_dev, "refused to change device type\n"); + slave_err(bond_dev, slave_dev, "refused to change device type\n"); return -EBUSY; }

@@@ -1455,31 -1462,31 +1462,31 @@@ } } else if (bond_dev->type != slave_dev->type) { NL_SET_ERR_MSG(extack, "Device type is different from other slaves"); - netdev_err(bond_dev, "%s ether type (%d) is different from other slaves (%d), can not enslave it\n", - slave_dev->name, slave_dev->type, bond_dev->type); + slave_err(bond_dev, slave_dev, "ether type (%d) is different from other slaves (%d), can not enslave it\n", + slave_dev->type, bond_dev->type); return -EINVAL; }

if (slave_dev->type == ARPHRD_INFINIBAND && BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) { NL_SET_ERR_MSG(extack, "Only active-backup mode is supported for infiniband slaves"); - netdev_warn(bond_dev, "Type (%d) supports only active-backup mode\n", - slave_dev->type); + slave_warn(bond_dev, slave_dev, "Type (%d) supports only active-backup mode\n", + slave_dev->type); res = -EOPNOTSUPP; goto err_undo_flags; }

if (!slave_ops->ndo_set_mac_address || slave_dev->type == ARPHRD_INFINIBAND) { - netdev_warn(bond_dev, "The slave device specified does not support setting the MAC address\n"); + slave_warn(bond_dev, slave_dev, "The slave device specified does not support setting the MAC address\n"); if (BOND_MODE(bond) == BOND_MODE_ACTIVEBACKUP && bond->params.fail_over_mac != BOND_FOM_ACTIVE) { if (!bond_has_slaves(bond)) { bond->params.fail_over_mac = BOND_FOM_ACTIVE; - netdev_warn(bond_dev, "Setting fail_over_mac to active for active-backup mode\n"); + slave_warn(bond_dev, slave_dev, "Setting fail_over_mac to active for active-backup mode\n"); } else { NL_SET_ERR_MSG(extack, "Slave device does not support setting the MAC address, but fail_over_mac is not set to active"); - netdev_err(bond_dev, "The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active\n"); + slave_err(bond_dev, slave_dev, "The slave device specified does not support setting the MAC address, but fail_over_mac is not set to active\n"); res = -EOPNOTSUPP; goto err_undo_flags; } @@@ -1515,7 -1522,7 +1522,7 @@@ new_slave->original_mtu = slave_dev->mtu; res = dev_set_mtu(slave_dev, bond->dev->mtu); if (res) { - netdev_dbg(bond_dev, "Error %d calling dev_set_mtu\n", res); + slave_err(bond_dev, slave_dev, "Error %d calling dev_set_mtu\n", res); goto err_free; }

@@@ -1536,7 -1543,7 +1543,7 @@@ res = dev_set_mac_address(slave_dev, (struct sockaddr *)&ss, extack); if (res) { - netdev_dbg(bond_dev, "Error %d calling set_mac_address\n", res); + slave_err(bond_dev, slave_dev, "Error %d calling set_mac_address\n", res); goto err_restore_mtu; } } @@@ -1547,7 -1554,7 +1554,7 @@@ /* open the slave since the application closed it */ res = dev_open(slave_dev, extack); if (res) { - netdev_dbg(bond_dev, "Opening slave %s failed\n", slave_dev->name); + slave_err(bond_dev, slave_dev, "Opening slave failed\n"); goto err_restore_mac; }

@@@ -1566,8 -1573,7 +1573,7 @@@

res = vlan_vids_add_by_dev(slave_dev, bond_dev); if (res) { - netdev_err(bond_dev, "Couldn't add bond vlan ids to %s\n", - slave_dev->name); + slave_err(bond_dev, slave_dev, "Couldn't add bond vlan ids\n"); goto err_close; }

@@@ -1597,12 -1603,10 +1603,10 @@@ * supported); thus, we don't need to change * the messages for netif_carrier. */ - netdev_warn(bond_dev, "MII and ETHTOOL support not available for interface %s, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details\n", - slave_dev->name); + slave_warn(bond_dev, slave_dev, "MII and ETHTOOL support not available for slave, and arp_interval/arp_ip_target module parameters not specified, thus bonding will not detect link failures! see bonding.txt for details\n"); } else if (link_reporting == -1) { /* unable get link status using mii/ethtool */ - netdev_warn(bond_dev, "can't get link status from interface %s; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface\n", - slave_dev->name); + slave_warn(bond_dev, slave_dev, "can't get link status from slave; the network driver associated with this interface does not support MII or ETHTOOL link status reporting, thus miimon has no effect on this interface\n"); } }

@@@ -1636,9 -1640,9 +1640,9 @@@

if (new_slave->link != BOND_LINK_DOWN) new_slave->last_link_up = jiffies; - netdev_dbg(bond_dev, "Initial state of slave_dev is BOND_LINK_%s\n", - new_slave->link == BOND_LINK_DOWN ? "DOWN" : - (new_slave->link == BOND_LINK_UP ? "UP" : "BACK")); + slave_dbg(bond_dev, slave_dev, "Initial state of slave is BOND_LINK_%s\n", + new_slave->link == BOND_LINK_DOWN ? "DOWN" : + (new_slave->link == BOND_LINK_UP ? "UP" : "BACK"));

if (bond_uses_primary(bond) && bond->params.primary[0]) { /* if there is a primary slave, remember it */ @@@ -1679,7 -1683,7 +1683,7 @@@ bond_set_slave_inactive_flags(new_slave, BOND_SLAVE_NOTIFY_NOW); break; default: - netdev_dbg(bond_dev, "This slave is always active in trunk mode\n"); + slave_dbg(bond_dev, slave_dev, "This slave is always active in trunk mode\n");

/* always active in trunk mode */ bond_set_active_slave(new_slave); @@@ -1698,7 -1702,7 +1702,7 @@@ #ifdef CONFIG_NET_POLL_CONTROLLER if (bond->dev->npinfo) { if (slave_enable_netpoll(new_slave)) { - netdev_info(bond_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n"); + slave_info(bond_dev, slave_dev, "master_dev is using netpoll, but new slave device does not support netpoll\n"); res = -EBUSY; goto err_detach; } @@@ -1711,19 -1715,19 +1715,19 @@@ res = netdev_rx_handler_register(slave_dev, bond_handle_frame, new_slave); if (res) { - netdev_dbg(bond_dev, "Error %d calling netdev_rx_handler_register\n", res); + slave_dbg(bond_dev, slave_dev, "Error %d calling netdev_rx_handler_register\n", res); goto err_detach; }

res = bond_master_upper_dev_link(bond, new_slave, extack); if (res) { - netdev_dbg(bond_dev, "Error %d calling bond_master_upper_dev_link\n", res); + slave_dbg(bond_dev, slave_dev, "Error %d calling bond_master_upper_dev_link\n", res); goto err_unregister; }

res = bond_sysfs_slave_add(new_slave); if (res) { - netdev_dbg(bond_dev, "Error %d calling bond_sysfs_slave_add\n", res); + slave_dbg(bond_dev, slave_dev, "Error %d calling bond_sysfs_slave_add\n", res); goto err_upper_unlink; }

@@@ -1777,10 -1781,9 +1781,9 @@@ bond_update_slave_arr(bond, NULL);

- netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n", - slave_dev->name, - bond_is_active_slave(new_slave) ? "an active" : "a backup", - new_slave->link != BOND_LINK_DOWN ? "an up" : "a down"); + slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n", + bond_is_active_slave(new_slave) ? "an active" : "a backup", + new_slave->link != BOND_LINK_DOWN ? "an up" : "a down");

/* enslave is successful */ bond_queue_slave_event(new_slave); @@@ -1875,8 -1878,7 +1878,7 @@@ static int __bond_release_one(struct ne /* slave is not a slave or master is not master of this slave */ if (!(slave_dev->flags & IFF_SLAVE) || !netdev_has_upper_dev(slave_dev, bond_dev)) { - netdev_dbg(bond_dev, "cannot release %s\n", - slave_dev->name); + slave_dbg(bond_dev, slave_dev, "cannot release slave\n"); return -EINVAL; }

@@@ -1885,8 -1887,7 +1887,7 @@@ slave = bond_get_slave_by_dev(bond, slave_dev); if (!slave) { /* not a slave of this bond */ - netdev_info(bond_dev, "%s not enslaved\n", - slave_dev->name); + slave_info(bond_dev, slave_dev, "interface not enslaved\n"); unblock_netpoll_tx(); return -EINVAL; } @@@ -1910,9 -1911,8 +1911,8 @@@ if (bond_mode_can_use_xmit_hash(bond)) bond_update_slave_arr(bond, slave);

- netdev_info(bond_dev, "Releasing %s interface %s\n", - bond_is_active_slave(slave) ? "active" : "backup", - slave_dev->name); + slave_info(bond_dev, slave_dev, "Releasing %s interface\n", + bond_is_active_slave(slave) ? "active" : "backup");

oldcurrent = rcu_access_pointer(bond->curr_active_slave);

@@@ -1922,9 -1922,8 +1922,8 @@@ BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)) { if (ether_addr_equal_64bits(bond_dev->dev_addr, slave->perm_hwaddr) && bond_has_slaves(bond)) - netdev_warn(bond_dev, "the permanent HWaddr of %s - %pM - is still in use by %s - set the HWaddr of %s to a different address to avoid conflicts\n", - slave_dev->name, slave->perm_hwaddr, - bond_dev->name, slave_dev->name); + slave_warn(bond_dev, slave_dev, "the permanent HWaddr of slave - %pM - is still in use by bond - set the HWaddr of slave to a different address to avoid conflicts\n", + slave->perm_hwaddr); }

if (rtnl_dereference(bond->primary_slave) == slave) @@@ -1972,8 -1971,7 +1971,7 @@@ bond_compute_features(bond); if (!(bond_dev->features & NETIF_F_VLAN_CHALLENGED) && (old_features & NETIF_F_VLAN_CHALLENGED)) - netdev_info(bond_dev, "last VLAN challenged slave %s left bond %s - VLAN blocking is removed\n", - slave_dev->name, bond_dev->name); + slave_info(bond_dev, slave_dev, "last VLAN challenged slave left bond - VLAN blocking is removed\n");

vlan_vids_del_by_dev(slave_dev, bond_dev);

@@@ -2033,8 -2031,8 +2031,8 @@@ int bond_release(struct net_device *bon /* First release a slave and then destroy the bond if no more slaves are left. * Must be under rtnl_lock when this function is called. */ - static int bond_release_and_destroy(struct net_device *bond_dev, - struct net_device *slave_dev) + static int bond_release_and_destroy(struct net_device *bond_dev, + struct net_device *slave_dev) { struct bonding *bond = netdev_priv(bond_dev); int ret; @@@ -2042,8 -2040,7 +2040,7 @@@ ret = __bond_release_one(bond_dev, slave_dev, false, true); if (ret == 0 && !bond_has_slaves(bond)) { bond_dev->priv_flags |= IFF_DISABLE_NETPOLL; - netdev_info(bond_dev, "Destroying bond %s\n", - bond_dev->name); + netdev_info(bond_dev, "Destroying bond\n"); bond_remove_proc_entry(bond); unregister_netdevice(bond_dev); } @@@ -2101,13 -2098,12 +2098,12 @@@ static int bond_miimon_inspect(struct b commit++; slave->delay = bond->params.downdelay; if (slave->delay) { - netdev_info(bond->dev, "link status down for %sinterface %s, disabling it in %d ms\n", - (BOND_MODE(bond) == - BOND_MODE_ACTIVEBACKUP) ? - (bond_is_active_slave(slave) ? - "active " : "backup ") : "", - slave->dev->name, - bond->params.downdelay * bond->params.miimon); + slave_info(bond->dev, slave->dev, "link status down for %sinterface, disabling it in %d ms\n", + (BOND_MODE(bond) == + BOND_MODE_ACTIVEBACKUP) ? + (bond_is_active_slave(slave) ? + "active " : "backup ") : "", + bond->params.downdelay * bond->params.miimon); } /*FALLTHRU*/ case BOND_LINK_FAIL: @@@ -2115,10 -2111,9 +2111,9 @@@ /* recovered before downdelay expired */ bond_propose_link_state(slave, BOND_LINK_UP); slave->last_link_up = jiffies; - netdev_info(bond->dev, "link status up again after %d ms for interface %s\n", - (bond->params.downdelay - slave->delay) * - bond->params.miimon, - slave->dev->name); + slave_info(bond->dev, slave->dev, "link status up again after %d ms\n", + (bond->params.downdelay - slave->delay) * + bond->params.miimon); commit++; continue; } @@@ -2141,20 -2136,18 +2136,18 @@@ slave->delay = bond->params.updelay;

if (slave->delay) { - netdev_info(bond->dev, "link status up for interface %s, enabling it in %d ms\n", - slave->dev->name, - ignore_updelay ? 0 : - bond->params.updelay * - bond->params.miimon); + slave_info(bond->dev, slave->dev, "link status up, enabling it in %d ms\n", + ignore_updelay ? 0 : + bond->params.updelay * + bond->params.miimon); } /*FALLTHRU*/ case BOND_LINK_BACK: if (!link_state) { bond_propose_link_state(slave, BOND_LINK_DOWN); - netdev_info(bond->dev, "link status down again after %d ms for interface %s\n", - (bond->params.updelay - slave->delay) * - bond->params.miimon, - slave->dev->name); + slave_info(bond->dev, slave->dev, "link status down again after %d ms\n", + (bond->params.updelay - slave->delay) * + bond->params.miimon); commit++; continue; } @@@ -2210,9 -2203,8 +2203,8 @@@ static void bond_miimon_commit(struct b bond_needs_speed_duplex(bond)) { slave->link = BOND_LINK_DOWN; if (net_ratelimit()) - netdev_warn(bond->dev, - "failed to get link speed/duplex for %s\n", - slave->dev->name); + slave_warn(bond->dev, slave->dev, + "failed to get link speed/duplex\n"); continue; } bond_set_slave_link_state(slave, BOND_LINK_UP, @@@ -2231,10 -2223,9 +2223,9 @@@ bond_set_backup_slave(slave); }

- netdev_info(bond->dev, "link status definitely up for interface %s, %u Mbps %s duplex\n", - slave->dev->name, - slave->speed == SPEED_UNKNOWN ? 0 : slave->speed, - slave->duplex ? "full" : "half"); + slave_info(bond->dev, slave->dev, "link status definitely up, %u Mbps %s duplex\n", + slave->speed == SPEED_UNKNOWN ? 0 : slave->speed, + slave->duplex ? "full" : "half");

bond_miimon_link_change(bond, slave, BOND_LINK_UP);

@@@ -2255,8 -2246,7 +2246,7 @@@ bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW);

- netdev_info(bond->dev, "link status definitely down for interface %s, disabling it\n", - slave->dev->name); + slave_info(bond->dev, slave->dev, "link status definitely down, disabling slave\n");

bond_miimon_link_change(bond, slave, BOND_LINK_DOWN);

@@@ -2266,8 -2256,8 +2256,8 @@@ continue;

default: - netdev_err(bond->dev, "invalid new link %d on slave %s\n", - slave->new_link, slave->dev->name); + slave_err(bond->dev, slave->dev, "invalid new link %d on slave\n", + slave->new_link); slave->new_link = BOND_LINK_NOCHANGE;

continue; @@@ -2294,6 -2284,7 +2284,7 @@@ static void bond_mii_monitor(struct wor struct bonding *bond = container_of(work, struct bonding, mii_work.work); bool should_notify_peers = false; + bool commit; unsigned long delay; struct slave *slave; struct list_head *iter; @@@ -2304,12 -2295,19 +2295,19 @@@ goto re_arm;

rcu_read_lock(); - should_notify_peers = bond_should_notify_peers(bond); - - if (bond_miimon_inspect(bond)) { + commit = !!bond_miimon_inspect(bond); + if (bond->send_peer_notif) { rcu_read_unlock(); + if (rtnl_trylock()) { + bond->send_peer_notif--; + rtnl_unlock(); + } + } else { + rcu_read_unlock(); + }

+ if (commit) { /* Race avoidance with bond_close cancel of workqueue */ if (!rtnl_trylock()) { delay = 1; @@@ -2323,8 -2321,7 +2321,7 @@@ bond_miimon_commit(bond);

rtnl_unlock(); /* might sleep, hold no other locks */ - } else - rcu_read_unlock(); + }

re_arm: if (bond->params.miimon) @@@ -2364,15 -2361,16 +2361,16 @@@ static bool bond_has_this_ip(struct bon * switches in VLAN mode (especially if ports are configured as * "native" to a VLAN) might not pass non-tagged frames. */ - static void bond_arp_send(struct net_device *slave_dev, int arp_op, - __be32 dest_ip, __be32 src_ip, - struct bond_vlan_tag *tags) + static void bond_arp_send(struct slave *slave, int arp_op, __be32 dest_ip, + __be32 src_ip, struct bond_vlan_tag *tags) { struct sk_buff *skb; struct bond_vlan_tag *outer_tag = tags; + struct net_device *slave_dev = slave->dev; + struct net_device *bond_dev = slave->bond->dev;

- netdev_dbg(slave_dev, "arp %d on slave %s: dst %pI4 src %pI4\n", - arp_op, slave_dev->name, &dest_ip, &src_ip); + slave_dbg(bond_dev, slave_dev, "arp %d on slave: dst %pI4 src %pI4\n", + arp_op, &dest_ip, &src_ip);

skb = arp_create(arp_op, ETH_P_ARP, dest_ip, slave_dev, src_ip, NULL, slave_dev->dev_addr, NULL); @@@ -2394,8 -2392,8 +2392,8 @@@ continue; }

- netdev_dbg(slave_dev, "inner tag: proto %X vid %X\n", - ntohs(outer_tag->vlan_proto), tags->vlan_id); + slave_dbg(bond_dev, slave_dev, "inner tag: proto %X vid %X\n", + ntohs(outer_tag->vlan_proto), tags->vlan_id); skb = vlan_insert_tag_set_proto(skb, tags->vlan_proto, tags->vlan_id); if (!skb) { @@@ -2407,8 -2405,8 +2405,8 @@@ } /* Set the outer tag */ if (outer_tag->vlan_id) { - netdev_dbg(slave_dev, "outer tag: proto %X vid %X\n", - ntohs(outer_tag->vlan_proto), outer_tag->vlan_id); + slave_dbg(bond_dev, slave_dev, "outer tag: proto %X vid %X\n", + ntohs(outer_tag->vlan_proto), outer_tag->vlan_id); __vlan_hwaccel_put_tag(skb, outer_tag->vlan_proto, outer_tag->vlan_id); } @@@ -2465,7 -2463,8 +2463,8 @@@ static void bond_arp_send_all(struct bo int i;

for (i = 0; i < BOND_MAX_ARP_TARGETS && targets[i]; i++) { - netdev_dbg(bond->dev, "basa: target %pI4\n", &targets[i]); + slave_dbg(bond->dev, slave->dev, "%s: target %pI4\n", + __func__, &targets[i]); tags = NULL;

/* Find out through which dev should the packet go */ @@@ -2479,7 -2478,7 +2478,7 @@@ net_warn_ratelimited("%s: no route to arp_ip_target %pI4 and arp_validate is set\n", bond->dev->name, &targets[i]); - bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], + bond_arp_send(slave, ARPOP_REQUEST, targets[i], 0, tags); continue; } @@@ -2496,7 -2495,7 +2495,7 @@@ goto found;

/* Not our device - skip */ - netdev_dbg(bond->dev, "no path to arp_ip_target %pI4 via rt.dev %s\n", + slave_dbg(bond->dev, slave->dev, "no path to arp_ip_target %pI4 via rt.dev %s\n", &targets[i], rt->dst.dev ? rt->dst.dev->name : "NULL");

ip_rt_put(rt); @@@ -2505,8 -2504,7 +2504,7 @@@ found: addr = bond_confirm_addr(rt->dst.dev, targets[i], 0); ip_rt_put(rt); - bond_arp_send(slave->dev, ARPOP_REQUEST, targets[i], - addr, tags); + bond_arp_send(slave, ARPOP_REQUEST, targets[i], addr, tags); kfree(tags); } } @@@ -2516,15 -2514,15 +2514,15 @@@ static void bond_validate_arp(struct bo int i;

if (!sip || !bond_has_this_ip(bond, tip)) { - netdev_dbg(bond->dev, "bva: sip %pI4 tip %pI4 not found\n", - &sip, &tip); + slave_dbg(bond->dev, slave->dev, "%s: sip %pI4 tip %pI4 not found\n", + __func__, &sip, &tip); return; }

i = bond_get_targets_ip(bond->params.arp_targets, sip); if (i == -1) { - netdev_dbg(bond->dev, "bva: sip %pI4 not found in targets\n", - &sip); + slave_dbg(bond->dev, slave->dev, "%s: sip %pI4 not found in targets\n", + __func__, &sip); return; } slave->last_rx = jiffies; @@@ -2552,8 -2550,8 +2550,8 @@@ int bond_arp_rcv(const struct sk_buff *

alen = arp_hdr_len(bond->dev);

- netdev_dbg(bond->dev, "bond_arp_rcv: skb->dev %s\n", - skb->dev->name); + slave_dbg(bond->dev, slave->dev, "%s: skb->dev %s\n", + __func__, skb->dev->name);

if (alen > skb_headlen(skb)) { arp = kmalloc(alen, GFP_ATOMIC); @@@ -2577,10 -2575,10 +2575,10 @@@ arp_ptr += 4 + bond->dev->addr_len; memcpy(&tip, arp_ptr, 4);

- netdev_dbg(bond->dev, "bond_arp_rcv: %s/%d av %d sv %d sip %pI4 tip %pI4\n", - slave->dev->name, bond_slave_state(slave), - bond->params.arp_validate, slave_do_arp_validate(bond, slave), - &sip, &tip); + slave_dbg(bond->dev, slave->dev, "%s: %s/%d av %d sv %d sip %pI4 tip %pI4\n", + __func__, slave->dev->name, bond_slave_state(slave), + bond->params.arp_validate, slave_do_arp_validate(bond, slave), + &sip, &tip);

curr_active_slave = rcu_dereference(bond->curr_active_slave); curr_arp_slave = rcu_dereference(bond->current_arp_slave); @@@ -2683,12 -2681,10 +2681,10 @@@ static void bond_loadbalance_arp_mon(st * is closed. */ if (!oldcurrent) { - netdev_info(bond->dev, "link status definitely up for interface %s\n", - slave->dev->name); + slave_info(bond->dev, slave->dev, "link status definitely up\n"); do_failover = 1; } else { - netdev_info(bond->dev, "interface %s is now up\n", - slave->dev->name); + slave_info(bond->dev, slave->dev, "interface is now up\n"); } } } else { @@@ -2707,8 -2703,7 +2703,7 @@@ if (slave->link_failure_count < UINT_MAX) slave->link_failure_count++;

- netdev_info(bond->dev, "interface %s is now down\n", - slave->dev->name); + slave_info(bond->dev, slave->dev, "interface is now down\n");

if (slave == oldcurrent) do_failover = 1; @@@ -2858,8 -2853,7 +2853,7 @@@ static void bond_ab_arp_commit(struct b RCU_INIT_POINTER(bond->current_arp_slave, NULL); }

- netdev_info(bond->dev, "link status definitely up for interface %s\n", - slave->dev->name); + slave_info(bond->dev, slave->dev, "link status definitely up\n");

if (!rtnl_dereference(bond->curr_active_slave) || slave == rtnl_dereference(bond->primary_slave)) @@@ -2878,8 -2872,7 +2872,7 @@@ bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_NOW);

- netdev_info(bond->dev, "link status definitely down for interface %s, disabling it\n", - slave->dev->name); + slave_info(bond->dev, slave->dev, "link status definitely down, disabling slave\n");

if (slave == rtnl_dereference(bond->curr_active_slave)) { RCU_INIT_POINTER(bond->current_arp_slave, NULL); @@@ -2889,8 -2882,8 +2882,8 @@@ continue;

default: - netdev_err(bond->dev, "impossible: new_link %d on slave %s\n", - slave->new_link, slave->dev->name); + slave_err(bond->dev, slave->dev, "impossible: new_link %d on slave\n", + slave->new_link); continue; }

@@@ -2961,8 -2954,7 +2954,7 @@@ static bool bond_ab_arp_probe(struct bo bond_set_slave_inactive_flags(slave, BOND_SLAVE_NOTIFY_LATER);

- netdev_info(bond->dev, "backup interface %s is now down\n", - slave->dev->name); + slave_info(bond->dev, slave->dev, "backup interface is now down\n"); } if (slave == curr_arp_slave) found = true; @@@ -3074,6 -3066,8 +3066,8 @@@ static int bond_master_netdev_event(uns { struct bonding *event_bond = netdev_priv(bond_dev);

+ netdev_dbg(bond_dev, "%s called\n", __func__); + switch (event) { case NETDEV_CHANGENAME: return bond_event_changename(event_bond); @@@ -3083,10 -3077,6 +3077,6 @@@ case NETDEV_REGISTER: bond_create_proc_entry(event_bond); break; - case NETDEV_NOTIFY_PEERS: - if (event_bond->send_peer_notif) - event_bond->send_peer_notif--; - break; default: break; } @@@ -3105,12 -3095,17 +3095,17 @@@ static int bond_slave_netdev_event(unsi * before netdev_rx_handler_register is called in which case * slave will be NULL */ - if (!slave) + if (!slave) { + netdev_dbg(slave_dev, "%s called on NULL slave\n", __func__); return NOTIFY_DONE; + } + bond_dev = slave->bond->dev; bond = slave->bond; primary = rtnl_dereference(bond->primary_slave);

+ slave_dbg(bond_dev, slave_dev, "%s called\n", __func__); + switch (event) { case NETDEV_UNREGISTER: if (bond_dev->type != ARPHRD_ETHER) @@@ -3212,7 -3207,8 +3207,8 @@@ static int bond_netdev_event(struct not { struct net_device *event_dev = netdev_notifier_info_to_dev(ptr);

- netdev_dbg(event_dev, "event: %lx\n", event); + netdev_dbg(event_dev, "%s received %s\n", + __func__, netdev_cmd_to_name(event));

if (!(event_dev->priv_flags & IFF_BONDING)) return NOTIFY_DONE; @@@ -3220,16 -3216,13 +3216,13 @@@ if (event_dev->flags & IFF_MASTER) { int ret;

- netdev_dbg(event_dev, "IFF_MASTER\n"); ret = bond_master_netdev_event(event, event_dev); if (ret != NOTIFY_DONE) return ret; }

- if (event_dev->flags & IFF_SLAVE) { - netdev_dbg(event_dev, "IFF_SLAVE\n"); + if (event_dev->flags & IFF_SLAVE) return bond_slave_netdev_event(event, event_dev); - }

return NOTIFY_DONE; } @@@ -3546,12 -3539,11 +3539,11 @@@ static int bond_do_ioctl(struct net_dev

slave_dev = __dev_get_by_name(net, ifr->ifr_slave);

- netdev_dbg(bond_dev, "slave_dev=%p:\n", slave_dev); + slave_dbg(bond_dev, slave_dev, "slave_dev=%p:\n", slave_dev);

if (!slave_dev) return -ENODEV;

- netdev_dbg(bond_dev, "slave_dev->name=%s:\n", slave_dev->name); switch (cmd) { case BOND_ENSLAVE_OLD: case SIOCBONDENSLAVE: @@@ -3676,7 -3668,7 +3668,7 @@@ static int bond_change_mtu(struct net_d netdev_dbg(bond_dev, "bond=%p, new_mtu=%d\n", bond, new_mtu);

bond_for_each_slave(bond, slave, iter) { - netdev_dbg(bond_dev, "s %p c_m %p\n", + slave_dbg(bond_dev, slave->dev, "s %p c_m %p\n", slave, slave->dev->netdev_ops->ndo_change_mtu);

res = dev_set_mtu(slave->dev, new_mtu); @@@ -3690,8 -3682,8 +3682,8 @@@ * means changing their mtu from timer context, which * is probably not a good idea. */ - netdev_dbg(bond_dev, "err %d %s\n", res, - slave->dev->name); + slave_dbg(bond_dev, slave->dev, "err %d setting mtu to %d\n", + res, new_mtu); goto unwind; } } @@@ -3709,10 -3701,9 +3701,9 @@@ unwind break;

tmp_res = dev_set_mtu(rollback_slave->dev, bond_dev->mtu); - if (tmp_res) { - netdev_dbg(bond_dev, "unwind err %d dev %s\n", - tmp_res, rollback_slave->dev->name); - } + if (tmp_res) + slave_dbg(bond_dev, rollback_slave->dev, "unwind err %d\n", + tmp_res); }

return res; @@@ -3736,7 -3727,7 +3727,7 @@@ static int bond_set_mac_address(struct return bond_alb_set_mac_address(bond_dev, addr);

- netdev_dbg(bond_dev, "bond=%p\n", bond); + netdev_dbg(bond_dev, "%s: bond=%p\n", __func__, bond);

/* If fail_over_mac is enabled, do nothing and return success. * Returning an error causes ifenslave to fail. @@@ -3749,7 -3740,8 +3740,8 @@@ return -EADDRNOTAVAIL;

bond_for_each_slave(bond, slave, iter) { - netdev_dbg(bond_dev, "slave %p %s\n", slave, slave->dev->name); + slave_dbg(bond_dev, slave->dev, "%s: slave=%p\n", + __func__, slave); res = dev_set_mac_address(slave->dev, addr, NULL); if (res) { /* TODO: consider downing the slave @@@ -3758,7 -3750,8 +3750,8 @@@ * breakage anyway until ARP finish * updating, so... */ - netdev_dbg(bond_dev, "err %d %s\n", res, slave->dev->name); + slave_dbg(bond_dev, slave->dev, "%s: err %d\n", + __func__, res); goto unwind; } } @@@ -3781,8 -3774,8 +3774,8 @@@ unwind tmp_res = dev_set_mac_address(rollback_slave->dev, (struct sockaddr *)&tmp_ss, NULL); if (tmp_res) { - netdev_dbg(bond_dev, "unwind err %d dev %s\n", - tmp_res, rollback_slave->dev->name); + slave_dbg(bond_dev, rollback_slave->dev, "%s: unwind err %d\n", + __func__, tmp_res); } }

@@@ -3866,8 -3859,8 +3859,8 @@@ static netdev_tx_t bond_xmit_roundrobin struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); - struct iphdr *iph = ip_hdr(skb); struct slave *slave; + int slave_cnt; u32 slave_id;

/* Start with the curr_active_slave that joined the bond as the @@@ -3876,32 -3869,23 +3869,32 @@@ * send the join/membership reports. The curr_active_slave found * will send all of this type of traffic. */ - if (iph->protocol == IPPROTO_IGMP && skb->protocol == htons(ETH_P_IP)) { - slave = rcu_dereference(bond->curr_active_slave); - if (slave) - bond_dev_queue_xmit(bond, skb, slave->dev); - else - bond_xmit_slave_id(bond, skb, 0); - } else { - int slave_cnt = READ_ONCE(bond->slave_cnt); + if (skb->protocol == htons(ETH_P_IP)) { + int noff = skb_network_offset(skb); + struct iphdr *iph;

- if (likely(slave_cnt)) { - slave_id = bond_rr_gen_slave_id(bond); - bond_xmit_slave_id(bond, skb, slave_id % slave_cnt); - } else { - bond_tx_drop(bond_dev, skb); + if (unlikely(!pskb_may_pull(skb, noff + sizeof(*iph)))) + goto non_igmp; + + iph = ip_hdr(skb); + if (iph->protocol == IPPROTO_IGMP) { + slave = rcu_dereference(bond->curr_active_slave); + if (slave) + bond_dev_queue_xmit(bond, skb, slave->dev); + else + bond_xmit_slave_id(bond, skb, 0); + return NETDEV_TX_OK; } }

+non_igmp: + slave_cnt = READ_ONCE(bond->slave_cnt); + if (likely(slave_cnt)) { + slave_id = bond_rr_gen_slave_id(bond); + bond_xmit_slave_id(bond, skb, slave_id % slave_cnt); + } else { + bond_tx_drop(bond_dev, skb); + } return NETDEV_TX_OK; }

@@@ -4012,9 -3996,8 +4005,8 @@@ int bond_update_slave_arr(struct bondin if (skipslave == slave) continue;

- netdev_dbg(bond->dev, - "Adding slave dev %s to tx hash array[%d]\n", - slave->dev->name, new_arr->count); + slave_dbg(bond->dev, slave->dev, "Adding slave to tx hash array[%d]\n", + new_arr->count);

new_arr->arr[new_arr->count++] = slave; } @@@ -4716,6 -4699,7 +4708,7 @@@ static int bond_check_params(struct bon params->arp_all_targets = arp_all_targets_value; params->updelay = updelay; params->downdelay = downdelay; + params->peer_notif_delay = 0; params->use_carrier = use_carrier; params->lacp_fast = lacp_fast; params->primary[0] = 0; diff --combined drivers/net/dsa/mv88e6xxx/chip.c index 2e8b1ab2c6f7,40b1fb22d8df..6b17cd961d06 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@@ -118,9 -118,9 +118,9 @@@ static irqreturn_t mv88e6xxx_g1_irq_thr u16 ctl1; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &reg); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

if (err) goto out; @@@ -135,13 -135,13 +135,13 @@@ } }

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL1, &ctl1); if (err) goto unlock; err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_STS, &reg); unlock: - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); if (err) goto out; ctl1 &= GENMASK(chip->g1_irq.nirqs, 0); @@@ -162,7 -162,7 +162,7 @@@ static void mv88e6xxx_g1_irq_bus_lock(s { struct mv88e6xxx_chip *chip = irq_data_get_irq_chip_data(d);

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); }

static void mv88e6xxx_g1_irq_bus_sync_unlock(struct irq_data *d) @@@ -184,7 -184,7 +184,7 @@@ goto out;

out: - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); }

static const struct irq_chip mv88e6xxx_g1_irq_chip = { @@@ -239,9 -239,9 +239,9 @@@ static void mv88e6xxx_g1_irq_free(struc */ free_irq(chip->irq, chip);

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); mv88e6xxx_g1_irq_free_common(chip); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); }

static int mv88e6xxx_g1_irq_setup_common(struct mv88e6xxx_chip *chip) @@@ -310,12 -310,12 +310,12 @@@ static int mv88e6xxx_g1_irq_setup(struc */ irq_set_lockdep_class(chip->irq, &lock_key, &request_key);

- mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); err = request_threaded_irq(chip->irq, NULL, mv88e6xxx_g1_irq_thread_fn, IRQF_ONESHOT | IRQF_SHARED, dev_name(chip->dev), chip); - mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); if (err) mv88e6xxx_g1_irq_free_common(chip);

@@@ -359,9 -359,9 +359,9 @@@ static void mv88e6xxx_irq_poll_free(str kthread_cancel_delayed_work_sync(&chip->irq_poll_work); kthread_destroy_worker(chip->kworker);

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); mv88e6xxx_g1_irq_free_common(chip); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); }

int mv88e6xxx_wait(struct mv88e6xxx_chip *chip, int addr, int reg, u16 mask) @@@ -496,11 -496,11 +496,11 @@@ static void mv88e6xxx_adjust_link(struc mv88e6xxx_phy_is_internal(ds, port)) return;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_port_setup_mac(chip, port, phydev->link, phydev->speed, phydev->duplex, phydev->pause, phydev->interface); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

if (err && err != -EOPNOTSUPP) dev_err(ds->dev, "p%d: failed to configure MAC\n", port); @@@ -616,12 -616,12 +616,12 @@@ static int mv88e6xxx_link_state(struct struct mv88e6xxx_chip *chip = ds->priv; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); if (chip->info->ops->port_link_state) err = chip->info->ops->port_link_state(chip, port, state); else err = -EOPNOTSUPP; - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -651,10 -651,10 +651,10 @@@ static void mv88e6xxx_mac_config(struc } pause = !!phylink_test(state->advertising, Pause);

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_port_setup_mac(chip, port, link, speed, duplex, pause, state->interface); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

if (err && err != -EOPNOTSUPP) dev_err(ds->dev, "p%d: failed to configure MAC\n", port); @@@ -665,9 -665,9 +665,9 @@@ static void mv88e6xxx_mac_link_force(st struct mv88e6xxx_chip *chip = ds->priv; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = chip->info->ops->port_set_link(chip, port, link); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

if (err) dev_err(chip->dev, "p%d: failed to force MAC link\n", port); @@@ -825,6 -825,12 +825,12 @@@ static int mv88e6095_stats_get_strings( STATS_TYPE_BANK0 | STATS_TYPE_PORT); }

+ static int mv88e6250_stats_get_strings(struct mv88e6xxx_chip *chip, + uint8_t *data) + { + return mv88e6xxx_stats_get_strings(chip, data, STATS_TYPE_BANK0); + } + static int mv88e6320_stats_get_strings(struct mv88e6xxx_chip *chip, uint8_t *data) { @@@ -859,7 -865,7 +865,7 @@@ static void mv88e6xxx_get_strings(struc if (stringset != ETH_SS_STATS) return;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip);

if (chip->info->ops->stats_get_strings) count = chip->info->ops->stats_get_strings(chip, data); @@@ -872,7 -878,7 +878,7 @@@ data += count * ETH_GSTRING_LEN; mv88e6xxx_atu_vtu_get_strings(data);

- mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); }

static int mv88e6xxx_stats_get_sset_count(struct mv88e6xxx_chip *chip, @@@ -895,6 -901,11 +901,11 @@@ static int mv88e6095_stats_get_sset_cou STATS_TYPE_PORT); }

+ static int mv88e6250_stats_get_sset_count(struct mv88e6xxx_chip *chip) + { + return mv88e6xxx_stats_get_sset_count(chip, STATS_TYPE_BANK0); + } + static int mv88e6320_stats_get_sset_count(struct mv88e6xxx_chip *chip) { return mv88e6xxx_stats_get_sset_count(chip, STATS_TYPE_BANK0 | @@@ -910,7 -921,7 +921,7 @@@ static int mv88e6xxx_get_sset_count(str if (sset != ETH_SS_STATS) return 0;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); if (chip->info->ops->stats_get_sset_count) count = chip->info->ops->stats_get_sset_count(chip); if (count < 0) @@@ -927,7 -938,7 +938,7 @@@ count += ARRAY_SIZE(mv88e6xxx_atu_vtu_stats_strings);

out: - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return count; } @@@ -942,11 -953,11 +953,11 @@@ static int mv88e6xxx_stats_get_stats(st for (i = 0, j = 0; i < ARRAY_SIZE(mv88e6xxx_hw_stats); i++) { stat = &mv88e6xxx_hw_stats[i]; if (stat->type & types) { - mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); data[j] = _mv88e6xxx_get_ethtool_stat(chip, stat, port, bank1_select, histogram); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

j++; } @@@ -962,6 -973,13 +973,13 @@@ static int mv88e6095_stats_get_stats(st 0, MV88E6XXX_G1_STATS_OP_HIST_RX_TX); }

+ static int mv88e6250_stats_get_stats(struct mv88e6xxx_chip *chip, int port, + uint64_t *data) + { + return mv88e6xxx_stats_get_stats(chip, port, data, STATS_TYPE_BANK0, + 0, MV88E6XXX_G1_STATS_OP_HIST_RX_TX); + } + static int mv88e6320_stats_get_stats(struct mv88e6xxx_chip *chip, int port, uint64_t *data) { @@@ -998,14 -1016,14 +1016,14 @@@ static void mv88e6xxx_get_stats(struct if (chip->info->ops->stats_get_stats) count = chip->info->ops->stats_get_stats(chip, port, data);

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); if (chip->info->ops->serdes_get_stats) { data += count; count = chip->info->ops->serdes_get_stats(chip, port, data); } data += count; mv88e6xxx_atu_vtu_get_stats(chip, port, data); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); }

static void mv88e6xxx_get_ethtool_stats(struct dsa_switch *ds, int port, @@@ -1014,10 -1032,10 +1032,10 @@@ struct mv88e6xxx_chip *chip = ds->priv; int ret;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip);

ret = mv88e6xxx_stats_snapshot(chip, port); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

if (ret < 0) return; @@@ -1044,7 -1062,7 +1062,7 @@@ static void mv88e6xxx_get_regs(struct d

memset(p, 0xff, 32 * sizeof(u16));

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip);

for (i = 0; i < 32; i++) {

@@@ -1053,7 -1071,7 +1071,7 @@@ p[i] = reg; }

- mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); }

static int mv88e6xxx_get_mac_eee(struct dsa_switch *ds, int port, @@@ -1119,9 -1137,9 +1137,9 @@@ static void mv88e6xxx_port_stp_state_se struct mv88e6xxx_chip *chip = ds->priv; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_port_set_state(chip, port, state); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

if (err) dev_err(ds->dev, "p%d: failed to update state\n", port); @@@ -1306,9 -1324,9 +1324,9 @@@ static void mv88e6xxx_port_fast_age(str struct mv88e6xxx_chip *chip = ds->priv; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_g1_atu_remove(chip, 0, port, false); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

if (err) dev_err(ds->dev, "p%d: failed to flush ATU\n", port); @@@ -1436,7 -1454,7 +1454,7 @@@ static int mv88e6xxx_port_check_hw_vlan if (!vid_begin) return -EOPNOTSUPP;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip);

do { err = mv88e6xxx_vtu_getnext(chip, &vlan); @@@ -1476,7 -1494,7 +1494,7 @@@ } while (vlan.vid < vid_end);

unlock: - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -1492,9 -1510,9 +1510,9 @@@ static int mv88e6xxx_port_vlan_filterin if (!chip->info->max_vid) return -EOPNOTSUPP;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_port_set_8021q_mode(chip, port, mode); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -1628,7 -1646,7 +1646,7 @@@ static void mv88e6xxx_port_vlan_add(str else member = MV88E6XXX_G1_VTU_DATA_MEMBER_TAG_TAGGED;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip);

for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) if (_mv88e6xxx_port_vlan_add(chip, port, vid, member)) @@@ -1639,7 -1657,7 +1657,7 @@@ dev_err(ds->dev, "p%d: failed to set PVID %d\n", port, vlan->vid_end);

- mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); }

static int _mv88e6xxx_port_vlan_del(struct mv88e6xxx_chip *chip, @@@ -1685,7 -1703,7 +1703,7 @@@ static int mv88e6xxx_port_vlan_del(stru if (!chip->info->max_vid) return -EOPNOTSUPP;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip);

err = mv88e6xxx_port_get_pvid(chip, port, &pvid); if (err) @@@ -1704,7 -1722,7 +1722,7 @@@ }

unlock: - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -1715,10 -1733,10 +1733,10 @@@ static int mv88e6xxx_port_fdb_add(struc struct mv88e6xxx_chip *chip = ds->priv; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_port_db_load_purge(chip, port, addr, vid, MV88E6XXX_G1_ATU_DATA_STATE_UC_STATIC); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -1729,10 -1747,10 +1747,10 @@@ static int mv88e6xxx_port_fdb_del(struc struct mv88e6xxx_chip *chip = ds->priv; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_port_db_load_purge(chip, port, addr, vid, MV88E6XXX_G1_ATU_DATA_STATE_UNUSED); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -1749,9 -1767,7 +1767,7 @@@ static int mv88e6xxx_port_db_dump_fid(s eth_broadcast_addr(addr.mac);

do { - mutex_lock(&chip->reg_lock); err = mv88e6xxx_g1_atu_getnext(chip, fid, &addr); - mutex_unlock(&chip->reg_lock); if (err) return err;

@@@ -1784,10 -1800,7 +1800,7 @@@ static int mv88e6xxx_port_db_dump(struc int err;

/* Dump port's default Filtering Information Database (VLAN ID 0) */ - mutex_lock(&chip->reg_lock); err = mv88e6xxx_port_get_fid(chip, port, &fid); - mutex_unlock(&chip->reg_lock); - if (err) return err;

@@@ -1797,9 -1810,7 +1810,7 @@@

/* Dump VLANs' Filtering Information Databases */ do { - mutex_lock(&chip->reg_lock); err = mv88e6xxx_vtu_getnext(chip, &vlan); - mutex_unlock(&chip->reg_lock); if (err) return err;

@@@ -1819,8 -1830,13 +1830,13 @@@ static int mv88e6xxx_port_fdb_dump(stru dsa_fdb_dump_cb_t *cb, void *data) { struct mv88e6xxx_chip *chip = ds->priv; + int err;

- return mv88e6xxx_port_db_dump(chip, port, cb, data); + mv88e6xxx_reg_lock(chip); + err = mv88e6xxx_port_db_dump(chip, port, cb, data); + mv88e6xxx_reg_unlock(chip); + + return err; }

static int mv88e6xxx_bridge_map(struct mv88e6xxx_chip *chip, @@@ -1867,9 -1883,9 +1883,9 @@@ static int mv88e6xxx_port_bridge_join(s struct mv88e6xxx_chip *chip = ds->priv; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_bridge_map(chip, br); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -1879,11 -1895,11 +1895,11 @@@ static void mv88e6xxx_port_bridge_leave { struct mv88e6xxx_chip *chip = ds->priv;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); if (mv88e6xxx_bridge_map(chip, br) || mv88e6xxx_port_vlan_map(chip, port)) dev_err(ds->dev, "failed to remap in-chip Port VLAN\n"); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); }

static int mv88e6xxx_crosschip_bridge_join(struct dsa_switch *ds, int dev, @@@ -1895,9 -1911,9 +1911,9 @@@ if (!mv88e6xxx_has_pvt(chip)) return 0;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_pvt_map(chip, dev, port); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -1910,10 -1926,10 +1926,10 @@@ static void mv88e6xxx_crosschip_bridge_ if (!mv88e6xxx_has_pvt(chip)) return;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); if (mv88e6xxx_pvt_map(chip, dev, port)) dev_err(ds->dev, "failed to remap cross-chip Port VLAN\n"); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); }

static int mv88e6xxx_software_reset(struct mv88e6xxx_chip *chip) @@@ -2264,14 -2280,14 +2280,14 @@@ static int mv88e6xxx_port_enable(struc struct mv88e6xxx_chip *chip = ds->priv; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip);

err = mv88e6xxx_serdes_power(chip, port, true);

if (!err && chip->info->ops->serdes_irq_setup) err = chip->info->ops->serdes_irq_setup(chip, port);

- mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -2280,7 -2296,7 +2296,7 @@@ static void mv88e6xxx_port_disable(stru { struct mv88e6xxx_chip *chip = ds->priv;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip);

if (mv88e6xxx_port_set_state(chip, port, BR_STATE_DISABLED)) dev_err(chip->dev, "failed to disable port\n"); @@@ -2291,7 -2307,7 +2307,7 @@@ if (mv88e6xxx_serdes_power(chip, port, false)) dev_err(chip->dev, "failed to power off SERDES\n");

- mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); }

static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds, @@@ -2300,9 -2316,9 +2316,9 @@@ struct mv88e6xxx_chip *chip = ds->priv; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_g1_atu_set_age_time(chip, ageing_time); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -2432,7 -2448,7 +2448,7 @@@ static int mv88e6xxx_setup(struct dsa_s chip->ds = ds; ds->slave_mii_bus = mv88e6xxx_default_mdio_bus(chip);

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip);

if (chip->info->ops->setup_errata) { err = chip->info->ops->setup_errata(chip); @@@ -2539,7 -2555,7 +2555,7 @@@ goto unlock;

unlock: - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -2554,9 -2570,9 +2570,9 @@@ static int mv88e6xxx_mdio_read(struct m if (!chip->info->ops->phy_read) return -EOPNOTSUPP;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = chip->info->ops->phy_read(chip, bus, phy, reg, &val); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

if (reg == MII_PHYSID2) { /* Some internal PHYs don't have a model number. */ @@@ -2589,9 -2605,9 +2605,9 @@@ static int mv88e6xxx_mdio_write(struct if (!chip->info->ops->phy_write) return -EOPNOTSUPP;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = chip->info->ops->phy_write(chip, bus, phy, reg, val); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -2606,9 -2622,9 +2622,9 @@@ static int mv88e6xxx_mdio_register(stru int err;

if (external) { - mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_g2_scratch_gpio_set_smi(chip, true); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

if (err) return err; @@@ -2729,9 -2745,9 +2745,9 @@@ static int mv88e6xxx_get_eeprom(struct if (!chip->info->ops->get_eeprom) return -EOPNOTSUPP;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = chip->info->ops->get_eeprom(chip, eeprom, data); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

if (err) return err; @@@ -2753,9 -2769,9 +2769,9 @@@ static int mv88e6xxx_set_eeprom(struct if (eeprom->magic != 0xc3ec4951) return -EINVAL;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = chip->info->ops->set_eeprom(chip, eeprom, data); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -3444,6 -3460,44 +3460,44 @@@ static const struct mv88e6xxx_ops mv88e .phylink_validate = mv88e6352_phylink_validate, };

+ static const struct mv88e6xxx_ops mv88e6250_ops = { + /* MV88E6XXX_FAMILY_6250 */ + .ieee_pri_map = mv88e6250_g1_ieee_pri_map, + .ip_pri_map = mv88e6085_g1_ip_pri_map, + .irl_init_all = mv88e6352_g2_irl_init_all, + .get_eeprom = mv88e6xxx_g2_get_eeprom16, + .set_eeprom = mv88e6xxx_g2_set_eeprom16, + .set_switch_mac = mv88e6xxx_g2_set_switch_mac, + .phy_read = mv88e6xxx_g2_smi_phy_read, + .phy_write = mv88e6xxx_g2_smi_phy_write, + .port_set_link = mv88e6xxx_port_set_link, + .port_set_duplex = mv88e6xxx_port_set_duplex, + .port_set_rgmii_delay = mv88e6352_port_set_rgmii_delay, + .port_set_speed = mv88e6250_port_set_speed, + .port_tag_remap = mv88e6095_port_tag_remap, + .port_set_frame_mode = mv88e6351_port_set_frame_mode, + .port_set_egress_floods = mv88e6352_port_set_egress_floods, + .port_set_ether_type = mv88e6351_port_set_ether_type, + .port_egress_rate_limiting = mv88e6097_port_egress_rate_limiting, + .port_pause_limit = mv88e6097_port_pause_limit, + .port_disable_pri_override = mv88e6xxx_port_disable_pri_override, + .port_link_state = mv88e6250_port_link_state, + .stats_snapshot = mv88e6320_g1_stats_snapshot, + .stats_set_histogram = mv88e6095_g1_stats_set_histogram, + .stats_get_sset_count = mv88e6250_stats_get_sset_count, + .stats_get_strings = mv88e6250_stats_get_strings, + .stats_get_stats = mv88e6250_stats_get_stats, + .set_cpu_port = mv88e6095_g1_set_cpu_port, + .set_egress_port = mv88e6095_g1_set_egress_port, + .watchdog_ops = &mv88e6250_watchdog_ops, + .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, + .pot_clear = mv88e6xxx_g2_pot_clear, + .reset = mv88e6250_g1_reset, + .vtu_getnext = mv88e6250_g1_vtu_getnext, + .vtu_loadpurge = mv88e6250_g1_vtu_loadpurge, + .phylink_validate = mv88e6065_phylink_validate, + }; + static const struct mv88e6xxx_ops mv88e6290_ops = { /* MV88E6XXX_FAMILY_6390 */ .setup_errata = mv88e6390_setup_errata, @@@ -4229,6 -4283,27 +4283,27 @@@ static const struct mv88e6xxx_info mv88 .ops = &mv88e6240_ops, },

+ [MV88E6250] = { + .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6250, + .family = MV88E6XXX_FAMILY_6250, + .name = "Marvell 88E6250", + .num_databases = 64, + .num_ports = 7, + .num_internal_phys = 5, + .max_vid = 4095, + .port_base_addr = 0x08, + .phy_base_addr = 0x00, + .global1_addr = 0x0f, + .global2_addr = 0x07, + .age_time_coeff = 15000, + .g1_irqs = 9, + .g2_irqs = 10, + .atu_move_port_mask = 0xf, + .dual_chip = true, + .tag_protocol = DSA_TAG_PROTO_DSA, + .ops = &mv88e6250_ops, + }, + [MV88E6290] = { .prod_num = MV88E6XXX_PORT_SWITCH_ID_PROD_6290, .family = MV88E6XXX_FAMILY_6390, @@@ -4457,9 -4532,9 +4532,9 @@@ static int mv88e6xxx_detect(struct mv88 u16 id; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_port_read(chip, 0, MV88E6XXX_PORT_SWITCH_ID, &id); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); if (err) return err;

@@@ -4522,12 -4597,12 +4597,12 @@@ static void mv88e6xxx_port_mdb_add(stru { struct mv88e6xxx_chip *chip = ds->priv;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); if (mv88e6xxx_port_db_load_purge(chip, port, mdb->addr, mdb->vid, MV88E6XXX_G1_ATU_DATA_STATE_MC_STATIC)) dev_err(ds->dev, "p%d: failed to load multicast MAC address\n", port); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); }

static int mv88e6xxx_port_mdb_del(struct dsa_switch *ds, int port, @@@ -4536,10 -4611,10 +4611,10 @@@ struct mv88e6xxx_chip *chip = ds->priv; int err;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_port_db_load_purge(chip, port, mdb->addr, mdb->vid, MV88E6XXX_G1_ATU_DATA_STATE_UNUSED); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -4550,12 -4625,12 +4625,12 @@@ static int mv88e6xxx_port_egress_floods struct mv88e6xxx_chip *chip = ds->priv; int err = -EOPNOTSUPP;

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); if (chip->info->ops->port_set_egress_floods) err = chip->info->ops->port_set_egress_floods(chip, port, unicast, multicast); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

return err; } @@@ -4711,8 -4786,6 +4786,8 @@@ static int mv88e6xxx_probe(struct mdio_ err = PTR_ERR(chip->reset); goto out; } + if (chip->reset) + usleep_range(1000, 2000);

err = mv88e6xxx_detect(chip); if (err) @@@ -4728,9 -4801,9 +4803,9 @@@ chip->eeprom_len = pdata->eeprom_len; }

- mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); err = mv88e6xxx_switch_reset(chip); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip); if (err) goto out;

@@@ -4749,12 -4822,12 +4824,12 @@@ * the PHYs will link their interrupts to these interrupt * controllers */ - mutex_lock(&chip->reg_lock); + mv88e6xxx_reg_lock(chip); if (chip->irq > 0) err = mv88e6xxx_g1_irq_setup(chip); else err = mv88e6xxx_irq_poll_setup(chip); - mutex_unlock(&chip->reg_lock); + mv88e6xxx_reg_unlock(chip);

if (err) goto out; @@@ -4839,6 -4912,10 +4914,10 @@@ static const struct of_device_id mv88e6 .compatible = "marvell,mv88e6190", .data = &mv88e6xxx_table[MV88E6190], }, + { + .compatible = "marvell,mv88e6250", + .data = &mv88e6xxx_table[MV88E6250], + }, { /* sentinel */ }, };

diff --combined drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index c12c1bab0fe4,c4986b519191..656ed80647f0 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@@ -684,7 -684,7 +684,7 @@@ static void *bnx2x_frag_alloc(const str if (unlikely(gfpflags_allow_blocking(gfp_mask))) return (void *)__get_free_page(gfp_mask);

- return netdev_alloc_frag(fp->rx_frag_size); + return napi_alloc_frag(fp->rx_frag_size); }

return kmalloc(fp->rx_buf_size + NET_SKB_PAD, gfp_mask); @@@ -3857,12 -3857,9 +3857,12 @@@ netdev_tx_t bnx2x_start_xmit(struct sk_

if (unlikely(skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP)) { if (!(bp->flags & TX_TIMESTAMPING_EN)) { + bp->eth_stats.ptp_skip_tx_ts++; BNX2X_ERR("Tx timestamping was not enabled, this packet will not be timestamped\n"); } else if (bp->ptp_tx_skb) { - BNX2X_ERR("The device supports only a single outstanding packet to timestamp, this packet will not be timestamped\n"); + bp->eth_stats.ptp_skip_tx_ts++; + netdev_err_once(bp->dev, + "Device supports only a single outstanding packet to timestamp, this packet won't be timestamped\n"); } else { skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; /* schedule check for Tx timestamp */ diff --combined drivers/net/ethernet/broadcom/bnxt/bnxt.c index 9090c79387c1,b7b62273c955..dd15d35ab745 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@@ -2130,12 -2130,12 +2130,12 @@@ static int bnxt_poll(struct napi_struc } } if (bp->flags & BNXT_FLAG_DIM) { - struct net_dim_sample dim_sample; + struct dim_sample dim_sample;

- net_dim_sample(cpr->event_ctr, - cpr->rx_packets, - cpr->rx_bytes, - &dim_sample); + dim_update_sample(cpr->event_ctr, + cpr->rx_packets, + cpr->rx_bytes, + &dim_sample); net_dim(&cpr->dim, dim_sample); } return work_done; @@@ -5508,16 -5508,7 +5508,16 @@@ static int bnxt_cp_rings_in_use(struct

static int bnxt_get_func_stat_ctxs(struct bnxt *bp) { - return bp->cp_nr_rings + bnxt_get_ulp_stat_ctxs(bp); + int ulp_stat = bnxt_get_ulp_stat_ctxs(bp); + int cp = bp->cp_nr_rings; + + if (!ulp_stat) + return cp; + + if (bnxt_nq_rings_in_use(bp) > cp + bnxt_get_ulp_msix_num(bp)) + return bnxt_get_ulp_msix_base(bp) + ulp_stat; + + return cp + ulp_stat; }

static bool bnxt_need_reserve_rings(struct bnxt *bp) @@@ -7486,7 -7477,11 +7486,7 @@@ unsigned int bnxt_get_avail_cp_rings_fo

unsigned int bnxt_get_avail_stat_ctxs_for_en(struct bnxt *bp) { - unsigned int stat; - - stat = bnxt_get_max_func_stat_ctxs(bp) - bnxt_get_ulp_stat_ctxs(bp); - stat -= bp->cp_nr_rings; - return stat; + return bnxt_get_max_func_stat_ctxs(bp) - bnxt_get_func_stat_ctxs(bp); }

int bnxt_get_avail_msix(struct bnxt *bp, int num) @@@ -7818,7 -7813,7 +7818,7 @@@ static void bnxt_enable_napi(struct bnx

if (bp->bnapi[i]->rx_ring) { INIT_WORK(&cpr->dim.work, bnxt_dim_work); - cpr->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE; + cpr->dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; } napi_enable(&bp->bnapi[i]->napi); } @@@ -10267,10 -10262,10 +10267,10 @@@ static void bnxt_remove_one(struct pci_ bnxt_dcb_free(bp); kfree(bp->edev); bp->edev = NULL; + bnxt_cleanup_pci(bp); bnxt_free_ctx_mem(bp); kfree(bp->ctx); bp->ctx = NULL; - bnxt_cleanup_pci(bp); bnxt_free_port_stats(bp); free_netdev(dev); } @@@ -10864,7 -10859,6 +10864,7 @@@ static void bnxt_shutdown(struct pci_de

if (system_state == SYSTEM_POWER_OFF) { bnxt_clear_int_mode(bp); + pci_disable_device(pdev); pci_wake_from_d3(pdev, bp->wol); pci_set_power_state(pdev, PCI_D3hot); } diff --combined drivers/net/ethernet/cadence/macb.h index 98735584570d,515bfd2c9e3f..03983bd46eef --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@@ -496,11 -496,7 +496,11 @@@

/* Bitfields in TISUBN */ #define GEM_SUBNSINCR_OFFSET 0 -#define GEM_SUBNSINCR_SIZE 16 +#define GEM_SUBNSINCRL_OFFSET 24 +#define GEM_SUBNSINCRL_SIZE 8 +#define GEM_SUBNSINCRH_OFFSET 0 +#define GEM_SUBNSINCRH_SIZE 16 +#define GEM_SUBNSINCR_SIZE 24

/* Bitfields in TI */ #define GEM_NSINCR_OFFSET 0 @@@ -838,9 -834,6 +838,9 @@@ struct gem_tx_ts /* limit RX checksum offload to TCP and UDP packets */ #define GEM_RX_CSUM_CHECKED_MASK 2

+/* Scaled PPM fraction */ +#define PPM_FRACTION 16 + /* struct macb_tx_skb - data about an skb which is being transmitted * @skb: skb currently being transmitted, only set for the last buffer * of the frame @@@ -1067,7 -1060,8 +1067,8 @@@ struct macb_or_gem_ops int (*mog_alloc_rx_buffers)(struct macb *bp); void (*mog_free_rx_buffers)(struct macb *bp); void (*mog_init_rings)(struct macb *bp); - int (*mog_rx)(struct macb_queue *queue, int budget); + int (*mog_rx)(struct macb_queue *queue, struct napi_struct *napi, + int budget); };

/* MACB-PTP interface: adapt to platform needs. */ diff --combined drivers/net/ethernet/ti/cpsw.c index 4e3026f9abed,32b7b3b74a6b..1e70ae7bbd61 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@@ -457,16 -457,13 +457,13 @@@ static void cpsw_rx_handler(void *token }

requeue: - if (netif_dormant(ndev)) { - dev_kfree_skb_any(new_skb); - return; - } - ch = cpsw->rxv[skb_get_queue_mapping(new_skb)].ch; ret = cpdma_chan_submit(ch, new_skb, new_skb->data, skb_tailroom(new_skb), 0); - if (WARN_ON(ret < 0)) + if (ret < 0) { + WARN_ON(ret == -ENOMEM); dev_kfree_skb_any(new_skb); + } }

void cpsw_split_res(struct cpsw_common *cpsw) @@@ -1051,9 -1048,9 +1048,9 @@@ int cpsw_fill_rx_channels(struct cpsw_p }

skb_set_queue_mapping(skb, ch); - ret = cpdma_chan_submit(cpsw->rxv[ch].ch, skb, - skb->data, skb_tailroom(skb), - 0); + ret = cpdma_chan_idle_submit(cpsw->rxv[ch].ch, skb, + skb->data, + skb_tailroom(skb), 0); if (ret < 0) { cpsw_err(priv, ifup, "cannot submit skb to channel %d rx, error %d\n", @@@ -1423,8 -1420,11 +1420,11 @@@ static int cpsw_ndo_open(struct net_dev return 0;

err_cleanup: - cpdma_ctlr_stop(cpsw->dma); - for_each_slave(priv, cpsw_slave_stop, cpsw); + if (!cpsw->usage_count) { + cpdma_ctlr_stop(cpsw->dma); + for_each_slave(priv, cpsw_slave_stop, cpsw); + } + pm_runtime_put_sync(cpsw->dev); netif_carrier_off(priv->ndev); return ret; @@@ -2179,7 -2179,6 +2179,7 @@@ static int cpsw_probe_dt(struct cpsw_pl return ret; }

+ slave_data->slave_node = slave_node; slave_data->phy_node = of_parse_phandle(slave_node, "phy-handle", 0); parp = of_get_property(slave_node, "phy_id", &lenp); @@@ -2263,8 -2262,7 +2263,7 @@@ no_phy_slave

static void cpsw_remove_dt(struct platform_device *pdev) { - struct net_device *ndev = platform_get_drvdata(pdev); - struct cpsw_common *cpsw = ndev_to_cpsw(ndev); + struct cpsw_common *cpsw = platform_get_drvdata(pdev); struct cpsw_platform_data *data = &cpsw->data; struct device_node *node = pdev->dev.of_node; struct device_node *slave_node; @@@ -2331,7 -2329,6 +2330,7 @@@ static int cpsw_probe_dual_emac(struct

/* register the network device */ SET_NETDEV_DEV(ndev, cpsw->dev); + ndev->dev.of_node = cpsw->slaves[1].data->slave_node; ret = register_netdev(ndev); if (ret) dev_err(cpsw->dev, "cpsw: error registering net device\n"); @@@ -2476,7 -2473,7 +2475,7 @@@ static int cpsw_probe(struct platform_d goto clean_cpts; }

- platform_set_drvdata(pdev, ndev); + platform_set_drvdata(pdev, cpsw); priv = netdev_priv(ndev); priv->cpsw = cpsw; priv->ndev = ndev; @@@ -2509,7 -2506,6 +2508,7 @@@

/* register the network device */ SET_NETDEV_DEV(ndev, dev); + ndev->dev.of_node = cpsw->slaves[0].data->slave_node; ret = register_netdev(ndev); if (ret) { dev_err(dev, "error registering net device\n"); @@@ -2570,9 -2566,8 +2569,8 @@@ clean_runtime_disable_ret

static int cpsw_remove(struct platform_device *pdev) { - struct net_device *ndev = platform_get_drvdata(pdev); - struct cpsw_common *cpsw = ndev_to_cpsw(ndev); - int ret; + struct cpsw_common *cpsw = platform_get_drvdata(pdev); + int i, ret;

ret = pm_runtime_get_sync(&pdev->dev); if (ret < 0) { @@@ -2580,9 -2575,9 +2578,9 @@@ return ret; }

- if (cpsw->data.dual_emac) - unregister_netdev(cpsw->slaves[1].ndev); - unregister_netdev(ndev); + for (i = 0; i < cpsw->data.slaves; i++) + if (cpsw->slaves[i].ndev) + unregister_netdev(cpsw->slaves[i].ndev);

cpts_release(cpsw->cpts); cpdma_ctlr_destroy(cpsw->dma); @@@ -2595,20 -2590,13 +2593,13 @@@ #ifdef CONFIG_PM_SLEEP static int cpsw_suspend(struct device *dev) { - struct net_device *ndev = dev_get_drvdata(dev); - struct cpsw_common *cpsw = ndev_to_cpsw(ndev); - - if (cpsw->data.dual_emac) { - int i; + struct cpsw_common *cpsw = dev_get_drvdata(dev); + int i;

- for (i = 0; i < cpsw->data.slaves; i++) { + for (i = 0; i < cpsw->data.slaves; i++) + if (cpsw->slaves[i].ndev) if (netif_running(cpsw->slaves[i].ndev)) cpsw_ndo_stop(cpsw->slaves[i].ndev); - } - } else { - if (netif_running(ndev)) - cpsw_ndo_stop(ndev); - }

/* Select sleep pin state */ pinctrl_pm_select_sleep_state(dev); @@@ -2618,25 -2606,20 +2609,20 @@@

static int cpsw_resume(struct device *dev) { - struct net_device *ndev = dev_get_drvdata(dev); - struct cpsw_common *cpsw = ndev_to_cpsw(ndev); + struct cpsw_common *cpsw = dev_get_drvdata(dev); + int i;

/* Select default pin state */ pinctrl_pm_select_default_state(dev);

/* shut up ASSERT_RTNL() warning in netif_set_real_num_tx/rx_queues */ rtnl_lock(); - if (cpsw->data.dual_emac) { - int i;

- for (i = 0; i < cpsw->data.slaves; i++) { + for (i = 0; i < cpsw->data.slaves; i++) + if (cpsw->slaves[i].ndev) if (netif_running(cpsw->slaves[i].ndev)) cpsw_ndo_open(cpsw->slaves[i].ndev); - } - } else { - if (netif_running(ndev)) - cpsw_ndo_open(ndev); - } + rtnl_unlock();

return 0; diff --combined drivers/net/vxlan.c index b4283f52a09d,5e2323592e08..3d9bcc957f7d --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@@ -468,14 -468,19 +468,19 @@@ static u32 eth_vni_hash(const unsigned return jhash_2words(key, vni, vxlan_salt) & (FDB_HASH_SIZE - 1); }

+ static u32 fdb_head_index(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) + { + if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) + return eth_vni_hash(mac, vni); + else + return eth_hash(mac); + } + /* Hash chain to use given mac address */ static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan, const u8 *mac, __be32 vni) { - if (vxlan->cfg.flags & VXLAN_F_COLLECT_METADATA) - return &vxlan->fdb_head[eth_vni_hash(mac, vni)]; - else - return &vxlan->fdb_head[eth_hash(mac)]; + return &vxlan->fdb_head[fdb_head_index(vxlan, mac, vni)]; }

/* Look up Ethernet address in forwarding table */ @@@ -590,8 -595,8 +595,8 @@@ int vxlan_fdb_replay(const struct net_d return -EINVAL; vxlan = netdev_priv(dev);

- spin_lock_bh(&vxlan->hash_lock); for (h = 0; h < FDB_HASH_SIZE; ++h) { + spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) { if (f->vni == vni) { list_for_each_entry(rdst, &f->remotes, list) { @@@ -599,14 -604,16 +604,16 @@@ f, rdst, extack); if (rc) - goto out; + goto unlock; } } } + spin_unlock_bh(&vxlan->hash_lock[h]); } + return 0;

- out: - spin_unlock_bh(&vxlan->hash_lock); + unlock: + spin_unlock_bh(&vxlan->hash_lock[h]); return rc; } EXPORT_SYMBOL_GPL(vxlan_fdb_replay); @@@ -622,14 -629,15 +629,15 @@@ void vxlan_fdb_clear_offload(const stru return; vxlan = netdev_priv(dev);

- spin_lock_bh(&vxlan->hash_lock); for (h = 0; h < FDB_HASH_SIZE; ++h) { + spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_entry(f, &vxlan->fdb_head[h], hlist) if (f->vni == vni) list_for_each_entry(rdst, &f->remotes, list) rdst->offloaded = false; + spin_unlock_bh(&vxlan->hash_lock[h]); } - spin_unlock_bh(&vxlan->hash_lock); + } EXPORT_SYMBOL_GPL(vxlan_fdb_clear_offload);

@@@ -804,14 -812,6 +812,14 @@@ static struct vxlan_fdb *vxlan_fdb_allo return f; }

+static void vxlan_fdb_insert(struct vxlan_dev *vxlan, const u8 *mac, + __be32 src_vni, struct vxlan_fdb *f) +{ + ++vxlan->addrcnt; + hlist_add_head_rcu(&f->hlist, + vxlan_fdb_head(vxlan, mac, src_vni)); +} + static int vxlan_fdb_create(struct vxlan_dev *vxlan, const u8 *mac, union vxlan_addr *ip, __u16 state, __be16 port, __be32 src_vni, @@@ -837,13 -837,18 +845,13 @@@ return rc; }

- ++vxlan->addrcnt; - hlist_add_head_rcu(&f->hlist, - vxlan_fdb_head(vxlan, mac, src_vni)); - *fdb = f;

return 0; }

-static void vxlan_fdb_free(struct rcu_head *head) +static void __vxlan_fdb_free(struct vxlan_fdb *f) { - struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu); struct vxlan_rdst *rd, *nd;

list_for_each_entry_safe(rd, nd, &f->remotes, list) { @@@ -853,13 -858,6 +861,13 @@@ kfree(f); }

+static void vxlan_fdb_free(struct rcu_head *head) +{ + struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu); + + __vxlan_fdb_free(f); +} + static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f, bool do_notify, bool swdev_notify) { @@@ -987,7 -985,6 +995,7 @@@ static int vxlan_fdb_update_create(stru if (rc < 0) return rc;

+ vxlan_fdb_insert(vxlan, mac, src_vni, f); rc = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, swdev_notify, extack); if (rc) @@@ -1116,6 -1113,7 +1124,7 @@@ static int vxlan_fdb_add(struct ndmsg * __be16 port; __be32 src_vni, vni; u32 ifindex; + u32 hash_index; int err;

if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) { @@@ -1134,12 -1132,13 +1143,13 @@@ if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family) return -EAFNOSUPPORT;

- spin_lock_bh(&vxlan->hash_lock); + hash_index = fdb_head_index(vxlan, addr, src_vni); + spin_lock_bh(&vxlan->hash_lock[hash_index]); err = vxlan_fdb_update(vxlan, addr, &ip, ndm->ndm_state, flags, port, src_vni, vni, ifindex, ndm->ndm_flags | NTF_VXLAN_ADDED_BY_USER, true, extack); - spin_unlock_bh(&vxlan->hash_lock); + spin_unlock_bh(&vxlan->hash_lock[hash_index]);

return err; } @@@ -1187,16 -1186,18 +1197,18 @@@ static int vxlan_fdb_delete(struct ndms __be32 src_vni, vni; __be16 port; u32 ifindex; + u32 hash_index; int err;

err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &src_vni, &vni, &ifindex); if (err) return err;

- spin_lock_bh(&vxlan->hash_lock); + hash_index = fdb_head_index(vxlan, addr, src_vni); + spin_lock_bh(&vxlan->hash_lock[hash_index]); err = __vxlan_fdb_delete(vxlan, addr, ip, port, src_vni, vni, ifindex, true); - spin_unlock_bh(&vxlan->hash_lock); + spin_unlock_bh(&vxlan->hash_lock[hash_index]);

return err; } @@@ -1308,8 -1309,10 +1320,10 @@@ static bool vxlan_snoop(struct net_devi f->updated = jiffies; vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH, true, NULL); } else { + u32 hash_index = fdb_head_index(vxlan, src_mac, vni); + /* learned new entry */ - spin_lock(&vxlan->hash_lock); + spin_lock(&vxlan->hash_lock[hash_index]);

/* close off race between vxlan_flush and incoming packets */ if (netif_running(dev)) @@@ -1320,7 -1323,7 +1334,7 @@@ vni, vxlan->default_dst.remote_vni, ifindex, NTF_SELF, true, NULL); - spin_unlock(&vxlan->hash_lock); + spin_unlock(&vxlan->hash_lock[hash_index]); }

return false; @@@ -2230,7 -2233,7 +2244,7 @@@ static struct rtable *vxlan_get_route(s fl4.fl4_sport = sport;

rt = ip_route_output_key(vxlan->net, &fl4); - if (likely(!IS_ERR(rt))) { + if (!IS_ERR(rt)) { if (rt->dst.dev == dev) { netdev_dbg(dev, "circular route to %pI4\n", &daddr); ip_rt_put(rt); @@@ -2710,7 -2713,7 +2724,7 @@@ static void vxlan_cleanup(struct timer_ for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n;

- spin_lock(&vxlan->hash_lock); + spin_lock(&vxlan->hash_lock[h]); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); @@@ -2732,7 -2735,7 +2746,7 @@@ } else if (time_before(timeout, next_timer)) next_timer = timeout; } - spin_unlock(&vxlan->hash_lock); + spin_unlock(&vxlan->hash_lock[h]); }

mod_timer(&vxlan->age_timer, next_timer); @@@ -2775,12 -2778,13 +2789,13 @@@ static int vxlan_init(struct net_devic static void vxlan_fdb_delete_default(struct vxlan_dev *vxlan, __be32 vni) { struct vxlan_fdb *f; + u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, vni);

- spin_lock_bh(&vxlan->hash_lock); + spin_lock_bh(&vxlan->hash_lock[hash_index]); f = __vxlan_find_mac(vxlan, all_zeros_mac, vni); if (f) vxlan_fdb_destroy(vxlan, f, true, true); - spin_unlock_bh(&vxlan->hash_lock); + spin_unlock_bh(&vxlan->hash_lock[hash_index]); }

static void vxlan_uninit(struct net_device *dev) @@@ -2825,9 -2829,10 +2840,10 @@@ static void vxlan_flush(struct vxlan_de { unsigned int h;

- spin_lock_bh(&vxlan->hash_lock); for (h = 0; h < FDB_HASH_SIZE; ++h) { struct hlist_node *p, *n; + + spin_lock_bh(&vxlan->hash_lock[h]); hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) { struct vxlan_fdb *f = container_of(p, struct vxlan_fdb, hlist); @@@ -2837,8 -2842,8 +2853,8 @@@ if (!is_zero_ether_addr(f->eth_addr)) vxlan_fdb_destroy(vxlan, f, true, true); } + spin_unlock_bh(&vxlan->hash_lock[h]); } - spin_unlock_bh(&vxlan->hash_lock); }

/* Cleanup timer and forwarding table on shutdown */ @@@ -3022,7 -3027,6 +3038,6 @@@ static void vxlan_setup(struct net_devi dev->max_mtu = ETH_MAX_MTU;

INIT_LIST_HEAD(&vxlan->next); - spin_lock_init(&vxlan->hash_lock);

timer_setup(&vxlan->age_timer, vxlan_cleanup, TIMER_DEFERRABLE);

@@@ -3030,8 -3034,10 +3045,10 @@@

gro_cells_init(&vxlan->gro_cells, dev);

- for (h = 0; h < FDB_HASH_SIZE; ++h) + for (h = 0; h < FDB_HASH_SIZE; ++h) { + spin_lock_init(&vxlan->hash_lock[h]); INIT_HLIST_HEAD(&vxlan->fdb_head[h]); + } }

static void vxlan_ether_setup(struct net_device *dev) @@@ -3582,17 -3588,12 +3599,17 @@@ static int __vxlan_dev_create(struct ne if (err) goto errout;

- /* notify default fdb entry */ if (f) { + vxlan_fdb_insert(vxlan, all_zeros_mac, + vxlan->default_dst.remote_vni, f); + + /* notify default fdb entry */ err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, true, extack); - if (err) - goto errout; + if (err) { + vxlan_fdb_destroy(vxlan, f, false, false); + goto unregister; + } }

list_add(&vxlan->next, &vn->vxlan_list); @@@ -3604,8 -3605,7 +3621,8 @@@ errout * destroy the entry by hand here. */ if (f) - vxlan_fdb_destroy(vxlan, f, false, false); + __vxlan_fdb_free(f); +unregister: if (unregister) unregister_netdevice(dev); return err; @@@ -3931,7 -3931,9 +3948,9 @@@ static int vxlan_changelink(struct net_

/* handle default dst entry */ if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) { - spin_lock_bh(&vxlan->hash_lock); + u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni); + + spin_lock_bh(&vxlan->hash_lock[hash_index]); if (!vxlan_addr_any(&conf.remote_ip)) { err = vxlan_fdb_update(vxlan, all_zeros_mac, &conf.remote_ip, @@@ -3942,7 -3944,7 +3961,7 @@@ conf.remote_ifindex, NTF_SELF, true, extack); if (err) { - spin_unlock_bh(&vxlan->hash_lock); + spin_unlock_bh(&vxlan->hash_lock[hash_index]); return err; } } @@@ -3954,7 -3956,7 +3973,7 @@@ dst->remote_vni, dst->remote_ifindex, true); - spin_unlock_bh(&vxlan->hash_lock); + spin_unlock_bh(&vxlan->hash_lock[hash_index]); }

if (conf.age_interval != vxlan->cfg.age_interval) @@@ -4209,8 -4211,11 +4228,11 @@@ vxlan_fdb_offloaded_set(struct net_devi struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_rdst *rdst; struct vxlan_fdb *f; + u32 hash_index; + + hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni);

- spin_lock_bh(&vxlan->hash_lock); + spin_lock_bh(&vxlan->hash_lock[hash_index]);

f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) @@@ -4226,7 -4231,7 +4248,7 @@@ rdst->offloaded = fdb_info->offloaded;

out: - spin_unlock_bh(&vxlan->hash_lock); + spin_unlock_bh(&vxlan->hash_lock[hash_index]); }

static int @@@ -4235,11 -4240,13 +4257,13 @@@ vxlan_fdb_external_learn_add(struct net { struct vxlan_dev *vxlan = netdev_priv(dev); struct netlink_ext_ack *extack; + u32 hash_index; int err;

+ hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); extack = switchdev_notifier_info_to_extack(&fdb_info->info);

- spin_lock_bh(&vxlan->hash_lock); + spin_lock_bh(&vxlan->hash_lock[hash_index]); err = vxlan_fdb_update(vxlan, fdb_info->eth_addr, &fdb_info->remote_ip, NUD_REACHABLE, NLM_F_CREATE | NLM_F_REPLACE, @@@ -4249,7 -4256,7 +4273,7 @@@ fdb_info->remote_ifindex, NTF_USE | NTF_SELF | NTF_EXT_LEARNED, false, extack); - spin_unlock_bh(&vxlan->hash_lock); + spin_unlock_bh(&vxlan->hash_lock[hash_index]);

return err; } @@@ -4260,9 -4267,11 +4284,11 @@@ vxlan_fdb_external_learn_del(struct net { struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f; + u32 hash_index; int err = 0;

- spin_lock_bh(&vxlan->hash_lock); + hash_index = fdb_head_index(vxlan, fdb_info->eth_addr, fdb_info->vni); + spin_lock_bh(&vxlan->hash_lock[hash_index]);

f = vxlan_find_mac(vxlan, fdb_info->eth_addr, fdb_info->vni); if (!f) @@@ -4276,7 -4285,7 +4302,7 @@@ fdb_info->remote_ifindex, false);

- spin_unlock_bh(&vxlan->hash_lock); + spin_unlock_bh(&vxlan->hash_lock[hash_index]);

return err; } diff --combined drivers/net/wireless/intel/iwlwifi/pcie/trans.c index 38ab24d96244,602c31b3992a..f5df5b370d78 --- a/drivers/net/wireless/intel/iwlwifi/pcie/trans.c +++ b/drivers/net/wireless/intel/iwlwifi/pcie/trans.c @@@ -90,8 -90,10 +90,10 @@@

void iwl_trans_pcie_dump_regs(struct iwl_trans *trans) { - #define PCI_DUMP_SIZE 64 - #define PREFIX_LEN 32 + #define PCI_DUMP_SIZE 352 + #define PCI_MEM_DUMP_SIZE 64 + #define PCI_PARENT_DUMP_SIZE 524 + #define PREFIX_LEN 32 struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); struct pci_dev *pdev = trans_pcie->pci_dev; u32 i, pos, alloc_size, *ptr, *buf; @@@ -102,11 -104,15 +104,15 @@@

/* Should be a multiple of 4 */ BUILD_BUG_ON(PCI_DUMP_SIZE > 4096 || PCI_DUMP_SIZE & 0x3); + BUILD_BUG_ON(PCI_MEM_DUMP_SIZE > 4096 || PCI_MEM_DUMP_SIZE & 0x3); + BUILD_BUG_ON(PCI_PARENT_DUMP_SIZE > 4096 || PCI_PARENT_DUMP_SIZE & 0x3); + /* Alloc a max size buffer */ - if (PCI_ERR_ROOT_ERR_SRC + 4 > PCI_DUMP_SIZE) - alloc_size = PCI_ERR_ROOT_ERR_SRC + 4 + PREFIX_LEN; - else - alloc_size = PCI_DUMP_SIZE + PREFIX_LEN; + alloc_size = PCI_ERR_ROOT_ERR_SRC + 4 + PREFIX_LEN; + alloc_size = max_t(u32, alloc_size, PCI_DUMP_SIZE + PREFIX_LEN); + alloc_size = max_t(u32, alloc_size, PCI_MEM_DUMP_SIZE + PREFIX_LEN); + alloc_size = max_t(u32, alloc_size, PCI_PARENT_DUMP_SIZE + PREFIX_LEN); + buf = kmalloc(alloc_size, GFP_ATOMIC); if (!buf) return; @@@ -123,7 -129,7 +129,7 @@@ print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, 4, buf, i, 0);

IWL_ERR(trans, "iwlwifi device memory mapped registers:\n"); - for (i = 0, ptr = buf; i < PCI_DUMP_SIZE; i += 4, ptr++) + for (i = 0, ptr = buf; i < PCI_MEM_DUMP_SIZE; i += 4, ptr++) *ptr = iwl_read32(trans, i); print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, 4, buf, i, 0);

@@@ -146,7 -152,7 +152,7 @@@

IWL_ERR(trans, "iwlwifi parent port (%s) config registers:\n", pci_name(pdev)); - for (i = 0, ptr = buf; i < PCI_DUMP_SIZE; i += 4, ptr++) + for (i = 0, ptr = buf; i < PCI_PARENT_DUMP_SIZE; i += 4, ptr++) if (pci_read_config_dword(pdev, i, ptr)) goto err_read; print_hex_dump(KERN_ERR, prefix, DUMP_PREFIX_OFFSET, 32, 4, buf, i, 0); @@@ -188,14 -194,14 +194,14 @@@ static void iwl_pcie_free_fw_monitor(st { int i;

- for (i = 0; i < trans->num_blocks; i++) { - dma_free_coherent(trans->dev, trans->fw_mon[i].size, - trans->fw_mon[i].block, - trans->fw_mon[i].physical); - trans->fw_mon[i].block = NULL; - trans->fw_mon[i].physical = 0; - trans->fw_mon[i].size = 0; - trans->num_blocks--; + for (i = 0; i < trans->dbg.num_blocks; i++) { + dma_free_coherent(trans->dev, trans->dbg.fw_mon[i].size, + trans->dbg.fw_mon[i].block, + trans->dbg.fw_mon[i].physical); + trans->dbg.fw_mon[i].block = NULL; + trans->dbg.fw_mon[i].physical = 0; + trans->dbg.fw_mon[i].size = 0; + trans->dbg.num_blocks--; } }

@@@ -230,10 -236,10 +236,10 @@@ static void iwl_pcie_alloc_fw_monitor_b (unsigned long)BIT(power - 10), (unsigned long)BIT(max_power - 10));

- trans->fw_mon[trans->num_blocks].block = cpu_addr; - trans->fw_mon[trans->num_blocks].physical = phys; - trans->fw_mon[trans->num_blocks].size = size; - trans->num_blocks++; + trans->dbg.fw_mon[trans->dbg.num_blocks].block = cpu_addr; + trans->dbg.fw_mon[trans->dbg.num_blocks].physical = phys; + trans->dbg.fw_mon[trans->dbg.num_blocks].size = size; + trans->dbg.num_blocks++; }

void iwl_pcie_alloc_fw_monitor(struct iwl_trans *trans, u8 max_power) @@@ -254,7 -260,7 +260,7 @@@ * This function allocats the default fw monitor. * The optional additional ones will be allocated in runtime */ - if (trans->num_blocks) + if (trans->dbg.num_blocks) return;

iwl_pcie_alloc_fw_monitor_block(trans, max_power, 11); @@@ -889,21 -895,21 +895,21 @@@ static int iwl_pcie_load_cpu_sections(s

void iwl_pcie_apply_destination(struct iwl_trans *trans) { - const struct iwl_fw_dbg_dest_tlv_v1 *dest = trans->dbg_dest_tlv; + const struct iwl_fw_dbg_dest_tlv_v1 *dest = trans->dbg.dest_tlv; int i;

- if (trans->ini_valid) { - if (!trans->num_blocks) + if (trans->dbg.ini_valid) { + if (!trans->dbg.num_blocks) return;

IWL_DEBUG_FW(trans, "WRT: applying DRAM buffer[0] destination\n"); iwl_write_umac_prph(trans, MON_BUFF_BASE_ADDR_VER2, - trans->fw_mon[0].physical >> + trans->dbg.fw_mon[0].physical >> MON_BUFF_SHIFT_VER2); iwl_write_umac_prph(trans, MON_BUFF_END_ADDR_VER2, - (trans->fw_mon[0].physical + - trans->fw_mon[0].size - 256) >> + (trans->dbg.fw_mon[0].physical + + trans->dbg.fw_mon[0].size - 256) >> MON_BUFF_SHIFT_VER2); return; } @@@ -916,7 -922,7 +922,7 @@@ else IWL_WARN(trans, "PCI should have external buffer debug\n");

- for (i = 0; i < trans->dbg_n_dest_reg; i++) { + for (i = 0; i < trans->dbg.n_dest_reg; i++) { u32 addr = le32_to_cpu(dest->reg_ops[i].addr); u32 val = le32_to_cpu(dest->reg_ops[i].val);

@@@ -955,18 -961,19 +961,19 @@@ }

monitor: - if (dest->monitor_mode == EXTERNAL_MODE && trans->fw_mon[0].size) { + if (dest->monitor_mode == EXTERNAL_MODE && trans->dbg.fw_mon[0].size) { iwl_write_prph(trans, le32_to_cpu(dest->base_reg), - trans->fw_mon[0].physical >> dest->base_shift); + trans->dbg.fw_mon[0].physical >> + dest->base_shift); if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_8000) iwl_write_prph(trans, le32_to_cpu(dest->end_reg), - (trans->fw_mon[0].physical + - trans->fw_mon[0].size - 256) >> + (trans->dbg.fw_mon[0].physical + + trans->dbg.fw_mon[0].size - 256) >> dest->end_shift); else iwl_write_prph(trans, le32_to_cpu(dest->end_reg), - (trans->fw_mon[0].physical + - trans->fw_mon[0].size) >> + (trans->dbg.fw_mon[0].physical + + trans->dbg.fw_mon[0].size) >> dest->end_shift); } } @@@ -1003,12 -1010,12 +1010,12 @@@ static int iwl_pcie_load_given_ucode(st trans->cfg->device_family == IWL_DEVICE_FAMILY_7000) { iwl_pcie_alloc_fw_monitor(trans, 0);

- if (trans->fw_mon[0].size) { + if (trans->dbg.fw_mon[0].size) { iwl_write_prph(trans, MON_BUFF_BASE_ADDR, - trans->fw_mon[0].physical >> 4); + trans->dbg.fw_mon[0].physical >> 4); iwl_write_prph(trans, MON_BUFF_END_ADDR, - (trans->fw_mon[0].physical + - trans->fw_mon[0].size) >> 4); + (trans->dbg.fw_mon[0].physical + + trans->dbg.fw_mon[0].size) >> 4); } } else if (iwl_pcie_dbg_on(trans)) { iwl_pcie_apply_destination(trans); @@@ -1236,7 -1243,7 +1243,7 @@@ static void _iwl_trans_pcie_stop_device trans_pcie->is_down = true;

/* Stop dbgc before stopping device */ - _iwl_fw_dbg_stop_recording(trans, NULL); + iwl_fw_dbg_stop_recording(trans, NULL);

/* tell the device to stop sending interrupts */ iwl_disable_interrupts(trans); @@@ -2729,8 -2736,8 +2736,8 @@@ static int iwl_dbgfs_monitor_data_open( struct iwl_trans *trans = inode->i_private; struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans);

- if (!trans->dbg_dest_tlv || - trans->dbg_dest_tlv->monitor_mode != EXTERNAL_MODE) { + if (!trans->dbg.dest_tlv || + trans->dbg.dest_tlv->monitor_mode != EXTERNAL_MODE) { IWL_ERR(trans, "Debug destination is not set to DRAM\n"); return -ENOENT; } @@@ -2777,22 -2784,22 +2784,22 @@@ static ssize_t iwl_dbgfs_monitor_data_r { struct iwl_trans *trans = file->private_data; struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); - void *cpu_addr = (void *)trans->fw_mon[0].block, *curr_buf; + void *cpu_addr = (void *)trans->dbg.fw_mon[0].block, *curr_buf; struct cont_rec *data = &trans_pcie->fw_mon_data; u32 write_ptr_addr, wrap_cnt_addr, write_ptr, wrap_cnt; ssize_t size, bytes_copied = 0; bool b_full;

- if (trans->dbg_dest_tlv) { + if (trans->dbg.dest_tlv) { write_ptr_addr = - le32_to_cpu(trans->dbg_dest_tlv->write_ptr_reg); - wrap_cnt_addr = le32_to_cpu(trans->dbg_dest_tlv->wrap_count); + le32_to_cpu(trans->dbg.dest_tlv->write_ptr_reg); + wrap_cnt_addr = le32_to_cpu(trans->dbg.dest_tlv->wrap_count); } else { write_ptr_addr = MON_BUFF_WRPTR; wrap_cnt_addr = MON_BUFF_CYCLE_CNT; }

- if (unlikely(!trans->dbg_rec_on)) + if (unlikely(!trans->dbg.rec_on)) return 0;

mutex_lock(&data->mutex); @@@ -2816,7 -2823,7 +2823,7 @@@

} else if (data->prev_wrap_cnt == wrap_cnt - 1 && write_ptr < data->prev_wr_ptr) { - size = trans->fw_mon[0].size - data->prev_wr_ptr; + size = trans->dbg.fw_mon[0].size - data->prev_wr_ptr; curr_buf = cpu_addr + data->prev_wr_ptr; b_full = iwl_write_to_user_buf(user_buf, count, curr_buf, &size, @@@ -3035,14 -3042,10 +3042,10 @@@ iwl_trans_pcie_dump_pointers(struct iwl base_high = DBGC_CUR_DBGBUF_BASE_ADDR_MSB; write_ptr = DBGC_CUR_DBGBUF_STATUS; wrap_cnt = DBGC_DBGBUF_WRAP_AROUND; - } else if (trans->ini_valid) { - base = iwl_umac_prph(trans, MON_BUFF_BASE_ADDR_VER2); - write_ptr = iwl_umac_prph(trans, MON_BUFF_WRPTR_VER2); - wrap_cnt = iwl_umac_prph(trans, MON_BUFF_CYCLE_CNT_VER2); - } else if (trans->dbg_dest_tlv) { - write_ptr = le32_to_cpu(trans->dbg_dest_tlv->write_ptr_reg); - wrap_cnt = le32_to_cpu(trans->dbg_dest_tlv->wrap_count); - base = le32_to_cpu(trans->dbg_dest_tlv->base_reg); + } else if (trans->dbg.dest_tlv) { + write_ptr = le32_to_cpu(trans->dbg.dest_tlv->write_ptr_reg); + wrap_cnt = le32_to_cpu(trans->dbg.dest_tlv->wrap_count); + base = le32_to_cpu(trans->dbg.dest_tlv->base_reg); } else { base = MON_BUFF_BASE_ADDR; write_ptr = MON_BUFF_WRPTR; @@@ -3069,11 -3072,10 +3072,10 @@@ iwl_trans_pcie_dump_monitor(struct iwl_ { u32 len = 0;

- if ((trans->num_blocks && + if (trans->dbg.dest_tlv || + (trans->dbg.num_blocks && (trans->cfg->device_family == IWL_DEVICE_FAMILY_7000 || - trans->cfg->device_family >= IWL_DEVICE_FAMILY_AX210 || - trans->ini_valid)) || - (trans->dbg_dest_tlv && !trans->ini_valid)) { + trans->cfg->device_family >= IWL_DEVICE_FAMILY_AX210))) { struct iwl_fw_error_dump_fw_mon *fw_mon_data;

(*data)->type = cpu_to_le32(IWL_FW_ERROR_DUMP_FW_MONITOR); @@@ -3082,32 -3084,32 +3084,32 @@@ iwl_trans_pcie_dump_pointers(trans, fw_mon_data);

len += sizeof(**data) + sizeof(*fw_mon_data); - if (trans->num_blocks) { + if (trans->dbg.num_blocks) { memcpy(fw_mon_data->data, - trans->fw_mon[0].block, - trans->fw_mon[0].size); + trans->dbg.fw_mon[0].block, + trans->dbg.fw_mon[0].size);

- monitor_len = trans->fw_mon[0].size; - } else if (trans->dbg_dest_tlv->monitor_mode == SMEM_MODE) { + monitor_len = trans->dbg.fw_mon[0].size; + } else if (trans->dbg.dest_tlv->monitor_mode == SMEM_MODE) { u32 base = le32_to_cpu(fw_mon_data->fw_mon_base_ptr); /* * Update pointers to reflect actual values after * shifting */ - if (trans->dbg_dest_tlv->version) { + if (trans->dbg.dest_tlv->version) { base = (iwl_read_prph(trans, base) & IWL_LDBG_M2S_BUF_BA_MSK) << - trans->dbg_dest_tlv->base_shift; + trans->dbg.dest_tlv->base_shift; base *= IWL_M2S_UNIT_SIZE; base += trans->cfg->smem_offset; } else { base = iwl_read_prph(trans, base) << - trans->dbg_dest_tlv->base_shift; + trans->dbg.dest_tlv->base_shift; }

iwl_trans_read_mem(trans, base, fw_mon_data->data, monitor_len / sizeof(u32)); - } else if (trans->dbg_dest_tlv->monitor_mode == MARBH_MODE) { + } else if (trans->dbg.dest_tlv->monitor_mode == MARBH_MODE) { monitor_len = iwl_trans_pci_dump_marbh_monitor(trans, fw_mon_data, @@@ -3126,40 -3128,40 +3128,40 @@@

static int iwl_trans_get_fw_monitor_len(struct iwl_trans *trans, u32 *len) { - if (trans->num_blocks) { + if (trans->dbg.num_blocks) { *len += sizeof(struct iwl_fw_error_dump_data) + sizeof(struct iwl_fw_error_dump_fw_mon) + - trans->fw_mon[0].size; - return trans->fw_mon[0].size; - } else if (trans->dbg_dest_tlv) { + trans->dbg.fw_mon[0].size; + return trans->dbg.fw_mon[0].size; + } else if (trans->dbg.dest_tlv) { u32 base, end, cfg_reg, monitor_len;

- if (trans->dbg_dest_tlv->version == 1) { - cfg_reg = le32_to_cpu(trans->dbg_dest_tlv->base_reg); + if (trans->dbg.dest_tlv->version == 1) { + cfg_reg = le32_to_cpu(trans->dbg.dest_tlv->base_reg); cfg_reg = iwl_read_prph(trans, cfg_reg); base = (cfg_reg & IWL_LDBG_M2S_BUF_BA_MSK) << - trans->dbg_dest_tlv->base_shift; + trans->dbg.dest_tlv->base_shift; base *= IWL_M2S_UNIT_SIZE; base += trans->cfg->smem_offset;

monitor_len = (cfg_reg & IWL_LDBG_M2S_BUF_SIZE_MSK) >> - trans->dbg_dest_tlv->end_shift; + trans->dbg.dest_tlv->end_shift; monitor_len *= IWL_M2S_UNIT_SIZE; } else { - base = le32_to_cpu(trans->dbg_dest_tlv->base_reg); - end = le32_to_cpu(trans->dbg_dest_tlv->end_reg); + base = le32_to_cpu(trans->dbg.dest_tlv->base_reg); + end = le32_to_cpu(trans->dbg.dest_tlv->end_reg);

base = iwl_read_prph(trans, base) << - trans->dbg_dest_tlv->base_shift; + trans->dbg.dest_tlv->base_shift; end = iwl_read_prph(trans, end) << - trans->dbg_dest_tlv->end_shift; + trans->dbg.dest_tlv->end_shift;

/* Make "end" point to the actual end */ if (trans->cfg->device_family >= IWL_DEVICE_FAMILY_8000 || - trans->dbg_dest_tlv->monitor_mode == MARBH_MODE) - end += (1 << trans->dbg_dest_tlv->end_shift); + trans->dbg.dest_tlv->monitor_mode == MARBH_MODE) + end += (1 << trans->dbg.dest_tlv->end_shift); monitor_len = end - base; } *len += sizeof(struct iwl_fw_error_dump_data) + @@@ -3192,7 -3194,7 +3194,7 @@@ static struct iwl_trans_dump_dat len = sizeof(*dump_data);

/* host commands */ - if (dump_mask & BIT(IWL_FW_ERROR_DUMP_TXCMD)) + if (dump_mask & BIT(IWL_FW_ERROR_DUMP_TXCMD) && cmdq) len += sizeof(*data) + cmdq->n_window * (sizeof(*txcmd) + TFD_MAX_PAYLOAD_SIZE); @@@ -3244,7 -3246,7 +3246,7 @@@ len = 0; data = (void *)dump_data->data;

- if (dump_mask & BIT(IWL_FW_ERROR_DUMP_TXCMD)) { + if (dump_mask & BIT(IWL_FW_ERROR_DUMP_TXCMD) && cmdq) { u16 tfd_size = trans_pcie->tfd_size;

data->type = cpu_to_le32(IWL_FW_ERROR_DUMP_TXCMD); @@@ -3569,17 -3571,15 +3571,17 @@@ struct iwl_trans *iwl_trans_pcie_alloc( trans->cfg = &iwlax210_2ax_cfg_so_jf_a0; } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_GF)) { - trans->cfg = &iwlax210_2ax_cfg_so_gf_a0; + trans->cfg = &iwlax211_2ax_cfg_so_gf_a0; } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_GF4)) { - trans->cfg = &iwlax210_2ax_cfg_so_gf4_a0; + trans->cfg = &iwlax411_2ax_cfg_so_gf4_a0; } } else if (cfg == &iwl_ax101_cfg_qu_hr) { - if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == - CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) && - trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0) { + if ((CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == + CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) && + trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0) || + (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == + CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR1))) { trans->cfg = &iwl22000_2ax_cfg_qnj_hr_b0; } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR)) { @@@ -3601,9 -3601,8 +3603,9 @@@ } else if (CSR_HW_RF_ID_TYPE_CHIP_ID(trans->hw_rf_id) == CSR_HW_RF_ID_TYPE_CHIP_ID(CSR_HW_RF_ID_TYPE_HR) && ((trans->cfg != &iwl_ax200_cfg_cc && - trans->cfg != &killer1650x_2ax_cfg && - trans->cfg != &killer1650w_2ax_cfg) || + trans->cfg != &killer1650x_2ax_cfg && + trans->cfg != &killer1650w_2ax_cfg && + trans->cfg != &iwl_ax201_cfg_quz_hr) || trans->hw_rev == CSR_HW_REV_TYPE_QNJ_B0)) { u32 hw_status;

@@@ -3684,6 -3683,7 +3686,7 @@@ void iwl_trans_pcie_sync_nmi(struct iwl { struct iwl_trans_pcie *trans_pcie = IWL_TRANS_GET_PCIE_TRANS(trans); unsigned long timeout = jiffies + IWL_TRANS_NMI_TIMEOUT; + bool interrupts_enabled = test_bit(STATUS_INT_ENABLED, &trans->status); u32 inta_addr, sw_err_bit;

if (trans_pcie->msix_enabled) { @@@ -3694,7 -3694,12 +3697,12 @@@ sw_err_bit = CSR_INT_BIT_SW_ERR; }

- iwl_disable_interrupts(trans); + /* if the interrupts were already disabled, there is no point in + * calling iwl_disable_interrupts + */ + if (interrupts_enabled) + iwl_disable_interrupts(trans); + iwl_force_nmi(trans); while (time_after(timeout, jiffies)) { u32 inta_hw = iwl_read32(trans, inta_addr); @@@ -3708,6 -3713,13 +3716,13 @@@

mdelay(1); } - iwl_enable_interrupts(trans); + + /* enable interrupts only if there were already enabled before this + * function to avoid a case were the driver enable interrupts before + * proper configurations were made + */ + if (interrupts_enabled) + iwl_enable_interrupts(trans); + iwl_trans_fw_error(trans); } diff --combined drivers/net/wireless/marvell/mwifiex/scan.c index e2786ab612ca,d870d4b2e03d..0d6d41727037 --- a/drivers/net/wireless/marvell/mwifiex/scan.c +++ b/drivers/net/wireless/marvell/mwifiex/scan.c @@@ -1361,25 -1361,21 +1361,25 @@@ int mwifiex_update_bss_desc_with_ie(str break;

case WLAN_EID_VENDOR_SPECIFIC: - if (element_len + 2 < sizeof(vendor_ie->vend_hdr)) - return -EINVAL; - vendor_ie = (struct ieee_types_vendor_specific *) current_ptr;

- if (!memcmp - (vendor_ie->vend_hdr.oui, wpa_oui, - sizeof(wpa_oui))) { + /* 802.11 requires at least 3-byte OUI. */ + if (element_len < sizeof(vendor_ie->vend_hdr.oui.oui)) + return -EINVAL; + + /* Not long enough for a match? Skip it. */ + if (element_len < sizeof(wpa_oui)) + break; + + if (!memcmp(&vendor_ie->vend_hdr.oui, wpa_oui, + sizeof(wpa_oui))) { bss_entry->bcn_wpa_ie = (struct ieee_types_vendor_specific *) current_ptr; bss_entry->wpa_offset = (u16) (current_ptr - bss_entry->beacon_buf); - } else if (!memcmp(vendor_ie->vend_hdr.oui, wmm_oui, + } else if (!memcmp(&vendor_ie->vend_hdr.oui, wmm_oui, sizeof(wmm_oui))) { if (total_ie_len == sizeof(struct ieee_types_wmm_parameter) || @@@ -1504,7 -1500,6 +1504,6 @@@ int mwifiex_scan_networks(struct mwifie u8 filtered_scan; u8 scan_current_chan_only; u8 max_chan_per_scan; - unsigned long flags;

if (adapter->scan_processing) { mwifiex_dbg(adapter, WARN, @@@ -1525,9 -1520,9 +1524,9 @@@ return -EFAULT; }

- spin_lock_irqsave(&adapter->mwifiex_cmd_lock, flags); + spin_lock_bh(&adapter->mwifiex_cmd_lock); adapter->scan_processing = true; - spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, flags); + spin_unlock_bh(&adapter->mwifiex_cmd_lock);

scan_cfg_out = kzalloc(sizeof(union mwifiex_scan_cmd_config_tlv), GFP_KERNEL); @@@ -1555,13 -1550,12 +1554,12 @@@

/* Get scan command from scan_pending_q and put to cmd_pending_q */ if (!ret) { - spin_lock_irqsave(&adapter->scan_pending_q_lock, flags); + spin_lock_bh(&adapter->scan_pending_q_lock); if (!list_empty(&adapter->scan_pending_q)) { cmd_node = list_first_entry(&adapter->scan_pending_q, struct cmd_ctrl_node, list); list_del(&cmd_node->list); - spin_unlock_irqrestore(&adapter->scan_pending_q_lock, - flags); + spin_unlock_bh(&adapter->scan_pending_q_lock); mwifiex_insert_cmd_to_pending_q(adapter, cmd_node); queue_work(adapter->workqueue, &adapter->main_work);

@@@ -1572,8 -1566,7 +1570,7 @@@ mwifiex_wait_queue_complete(adapter, cmd_node); } } else { - spin_unlock_irqrestore(&adapter->scan_pending_q_lock, - flags); + spin_unlock_bh(&adapter->scan_pending_q_lock); } }

@@@ -1581,9 -1574,9 +1578,9 @@@ kfree(scan_chan_list); done: if (ret) { - spin_lock_irqsave(&adapter->mwifiex_cmd_lock, flags); + spin_lock_bh(&adapter->mwifiex_cmd_lock); adapter->scan_processing = false; - spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, flags); + spin_unlock_bh(&adapter->mwifiex_cmd_lock); } return ret; } @@@ -1719,7 -1712,6 +1716,6 @@@ static int mwifiex_update_curr_bss_para { struct mwifiex_bssdescriptor *bss_desc; int ret; - unsigned long flags;

/* Allocate and fill new bss descriptor */ bss_desc = kzalloc(sizeof(struct mwifiex_bssdescriptor), GFP_KERNEL); @@@ -1734,7 -1726,7 +1730,7 @@@ if (ret) goto done;

- spin_lock_irqsave(&priv->curr_bcn_buf_lock, flags); + spin_lock_bh(&priv->curr_bcn_buf_lock); /* Make a copy of current BSSID descriptor */ memcpy(&priv->curr_bss_params.bss_descriptor, bss_desc, sizeof(priv->curr_bss_params.bss_descriptor)); @@@ -1743,7 -1735,7 +1739,7 @@@ * in mwifiex_save_curr_bcn() */ mwifiex_save_curr_bcn(priv); - spin_unlock_irqrestore(&priv->curr_bcn_buf_lock, flags); + spin_unlock_bh(&priv->curr_bcn_buf_lock);

done: /* beacon_ie buffer was allocated in function @@@ -1997,15 -1989,14 +1993,14 @@@ static void mwifiex_check_next_scan_com { struct mwifiex_adapter *adapter = priv->adapter; struct cmd_ctrl_node *cmd_node; - unsigned long flags;

- spin_lock_irqsave(&adapter->scan_pending_q_lock, flags); + spin_lock_bh(&adapter->scan_pending_q_lock); if (list_empty(&adapter->scan_pending_q)) { - spin_unlock_irqrestore(&adapter->scan_pending_q_lock, flags); + spin_unlock_bh(&adapter->scan_pending_q_lock);

- spin_lock_irqsave(&adapter->mwifiex_cmd_lock, flags); + spin_lock_bh(&adapter->mwifiex_cmd_lock); adapter->scan_processing = false; - spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, flags); + spin_unlock_bh(&adapter->mwifiex_cmd_lock);

mwifiex_active_scan_req_for_passive_chan(priv);

@@@ -2029,13 -2020,13 +2024,13 @@@ } } else if ((priv->scan_aborting && !priv->scan_request) || priv->scan_block) { - spin_unlock_irqrestore(&adapter->scan_pending_q_lock, flags); + spin_unlock_bh(&adapter->scan_pending_q_lock);

mwifiex_cancel_pending_scan_cmd(adapter);

- spin_lock_irqsave(&adapter->mwifiex_cmd_lock, flags); + spin_lock_bh(&adapter->mwifiex_cmd_lock); adapter->scan_processing = false; - spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, flags); + spin_unlock_bh(&adapter->mwifiex_cmd_lock);

if (!adapter->active_scan_triggered) { if (priv->scan_request) { @@@ -2061,7 -2052,7 +2056,7 @@@ cmd_node = list_first_entry(&adapter->scan_pending_q, struct cmd_ctrl_node, list); list_del(&cmd_node->list); - spin_unlock_irqrestore(&adapter->scan_pending_q_lock, flags); + spin_unlock_bh(&adapter->scan_pending_q_lock); mwifiex_insert_cmd_to_pending_q(adapter, cmd_node); }

@@@ -2071,15 -2062,14 +2066,14 @@@ void mwifiex_cancel_scan(struct mwifiex_adapter *adapter) { struct mwifiex_private *priv; - unsigned long cmd_flags; int i;

mwifiex_cancel_pending_scan_cmd(adapter);

if (adapter->scan_processing) { - spin_lock_irqsave(&adapter->mwifiex_cmd_lock, cmd_flags); + spin_lock_bh(&adapter->mwifiex_cmd_lock); adapter->scan_processing = false; - spin_unlock_irqrestore(&adapter->mwifiex_cmd_lock, cmd_flags); + spin_unlock_bh(&adapter->mwifiex_cmd_lock); for (i = 0; i < adapter->priv_num; i++) { priv = adapter->priv[i]; if (!priv) @@@ -2561,7 -2551,6 +2555,6 @@@ int mwifiex_ret_802_11_scan_ext(struct

struct host_cmd_ds_command *cmd_ptr; struct cmd_ctrl_node *cmd_node; - unsigned long cmd_flags, scan_flags; bool complete_scan = false;

mwifiex_dbg(adapter, INFO, "info: EXT scan returns successfully\n"); @@@ -2596,8 -2585,8 +2589,8 @@@ sizeof(struct mwifiex_ie_types_header)); }

- spin_lock_irqsave(&adapter->cmd_pending_q_lock, cmd_flags); - spin_lock_irqsave(&adapter->scan_pending_q_lock, scan_flags); + spin_lock_bh(&adapter->cmd_pending_q_lock); + spin_lock_bh(&adapter->scan_pending_q_lock); if (list_empty(&adapter->scan_pending_q)) { complete_scan = true; list_for_each_entry(cmd_node, &adapter->cmd_pending_q, list) { @@@ -2611,8 -2600,8 +2604,8 @@@ } } } - spin_unlock_irqrestore(&adapter->scan_pending_q_lock, scan_flags); - spin_unlock_irqrestore(&adapter->cmd_pending_q_lock, cmd_flags); + spin_unlock_bh(&adapter->scan_pending_q_lock); + spin_unlock_bh(&adapter->cmd_pending_q_lock);

if (complete_scan) mwifiex_complete_scan(priv); @@@ -2784,13 -2773,12 +2777,12 @@@ mwifiex_queue_scan_cmd(struct mwifiex_p struct cmd_ctrl_node *cmd_node) { struct mwifiex_adapter *adapter = priv->adapter; - unsigned long flags;

cmd_node->wait_q_enabled = true; cmd_node->condition = &adapter->scan_wait_q_woken; - spin_lock_irqsave(&adapter->scan_pending_q_lock, flags); + spin_lock_bh(&adapter->scan_pending_q_lock); list_add_tail(&cmd_node->list, &adapter->scan_pending_q); - spin_unlock_irqrestore(&adapter->scan_pending_q_lock, flags); + spin_unlock_bh(&adapter->scan_pending_q_lock); }

/* diff --combined drivers/net/wireless/marvell/mwifiex/wmm.c index 64916ba15df5,0301bc33f554..41f0231376c0 --- a/drivers/net/wireless/marvell/mwifiex/wmm.c +++ b/drivers/net/wireless/marvell/mwifiex/wmm.c @@@ -138,7 -138,6 +138,6 @@@ void mwifiex_ralist_add(struct mwifiex_ struct mwifiex_ra_list_tbl *ra_list; struct mwifiex_adapter *adapter = priv->adapter; struct mwifiex_sta_node *node; - unsigned long flags;

for (i = 0; i < MAX_NUM_TID; ++i) { @@@ -163,7 -162,7 +162,7 @@@ ra_list->is_11n_enabled = IS_11N_ENABLED(priv); } } else { - spin_lock_irqsave(&priv->sta_list_spinlock, flags); + spin_lock_bh(&priv->sta_list_spinlock); node = mwifiex_get_sta_entry(priv, ra); if (node) ra_list->tx_paused = node->tx_pause; @@@ -171,7 -170,7 +170,7 @@@ mwifiex_is_sta_11n_enabled(priv, node); if (ra_list->is_11n_enabled) ra_list->max_amsdu = node->max_amsdu; - spin_unlock_irqrestore(&priv->sta_list_spinlock, flags); + spin_unlock_bh(&priv->sta_list_spinlock); }

mwifiex_dbg(adapter, DATA, "data: ralist %p: is_11n_enabled=%d\n", @@@ -240,7 -239,7 +239,7 @@@ mwifiex_wmm_setup_queue_priorities(stru mwifiex_dbg(priv->adapter, INFO, "info: WMM Parameter IE: version=%d,\t" "qos_info Parameter Set Count=%d, Reserved=%#x\n", - wmm_ie->vend_hdr.version, wmm_ie->qos_info_bitmap & + wmm_ie->version, wmm_ie->qos_info_bitmap & IEEE80211_WMM_IE_AP_QOSINFO_PARAM_SET_CNT_MASK, wmm_ie->reserved);

@@@ -583,11 -582,10 +582,10 @@@ static int mwifiex_free_ack_frame(int i void mwifiex_clean_txrx(struct mwifiex_private *priv) { - unsigned long flags; struct sk_buff *skb, *tmp;

mwifiex_11n_cleanup_reorder_tbl(priv); - spin_lock_irqsave(&priv->wmm.ra_list_spinlock, flags); + spin_lock_bh(&priv->wmm.ra_list_spinlock);

mwifiex_wmm_cleanup_queues(priv); mwifiex_11n_delete_all_tx_ba_stream_tbl(priv); @@@ -601,7 -599,7 +599,7 @@@ if (priv->adapter->if_ops.clean_pcie_ring && !test_bit(MWIFIEX_SURPRISE_REMOVED, &priv->adapter->work_flags)) priv->adapter->if_ops.clean_pcie_ring(priv->adapter); - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock);

skb_queue_walk_safe(&priv->tdls_txq, skb, tmp) { skb_unlink(skb, &priv->tdls_txq); @@@ -642,10 -640,9 +640,9 @@@ void mwifiex_update_ralist_tx_pause(str { struct mwifiex_ra_list_tbl *ra_list; u32 pkt_cnt = 0, tx_pkts_queued; - unsigned long flags; int i;

- spin_lock_irqsave(&priv->wmm.ra_list_spinlock, flags); + spin_lock_bh(&priv->wmm.ra_list_spinlock);

for (i = 0; i < MAX_NUM_TID; ++i) { ra_list = mwifiex_wmm_get_ralist_node(priv, i, mac); @@@ -671,7 -668,7 +668,7 @@@ atomic_set(&priv->wmm.tx_pkts_queued, tx_pkts_queued); atomic_set(&priv->wmm.highest_queued_prio, HIGH_PRIO_TID); } - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); }

/* This function updates non-tdls peer ralist tx_pause while @@@ -682,10 -679,9 +679,9 @@@ void mwifiex_update_ralist_tx_pause_in_ { struct mwifiex_ra_list_tbl *ra_list; u32 pkt_cnt = 0, tx_pkts_queued; - unsigned long flags; int i;

- spin_lock_irqsave(&priv->wmm.ra_list_spinlock, flags); + spin_lock_bh(&priv->wmm.ra_list_spinlock);

for (i = 0; i < MAX_NUM_TID; ++i) { list_for_each_entry(ra_list, &priv->wmm.tid_tbl_ptr[i].ra_list, @@@ -716,7 -712,7 +712,7 @@@ atomic_set(&priv->wmm.tx_pkts_queued, tx_pkts_queued); atomic_set(&priv->wmm.highest_queued_prio, HIGH_PRIO_TID); } - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); }

/* @@@ -748,10 -744,9 +744,9 @@@ voi mwifiex_wmm_del_peer_ra_list(struct mwifiex_private *priv, const u8 *ra_addr) { struct mwifiex_ra_list_tbl *ra_list; - unsigned long flags; int i;

- spin_lock_irqsave(&priv->wmm.ra_list_spinlock, flags); + spin_lock_bh(&priv->wmm.ra_list_spinlock);

for (i = 0; i < MAX_NUM_TID; ++i) { ra_list = mwifiex_wmm_get_ralist_node(priv, i, ra_addr); @@@ -767,7 -762,7 +762,7 @@@ list_del(&ra_list->list); kfree(ra_list); } - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); }

/* @@@ -818,7 -813,6 +813,6 @@@ mwifiex_wmm_add_buf_txqueue(struct mwif u32 tid; struct mwifiex_ra_list_tbl *ra_list; u8 ra[ETH_ALEN], tid_down; - unsigned long flags; struct list_head list_head; int tdls_status = TDLS_NOT_SETUP; struct ethhdr *eth_hdr = (struct ethhdr *)skb->data; @@@ -844,7 -838,7 +838,7 @@@

tid = skb->priority;

- spin_lock_irqsave(&priv->wmm.ra_list_spinlock, flags); + spin_lock_bh(&priv->wmm.ra_list_spinlock);

tid_down = mwifiex_wmm_downgrade_tid(priv, tid);

@@@ -864,8 -858,7 +858,7 @@@ break; case TDLS_SETUP_INPROGRESS: skb_queue_tail(&priv->tdls_txq, skb); - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, - flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); return; default: list_head = priv->wmm.tid_tbl_ptr[tid_down].ra_list; @@@ -881,7 -874,7 +874,7 @@@ }

if (!ra_list) { - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); mwifiex_write_data_complete(adapter, skb, 0, -1); return; } @@@ -901,7 -894,7 +894,7 @@@ else atomic_inc(&priv->wmm.tx_pkts_queued);

- spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); }

/* @@@ -1092,7 -1085,6 +1085,6 @@@ mwifiex_wmm_get_highest_priolist_ptr(st struct mwifiex_ra_list_tbl *ptr; struct mwifiex_tid_tbl *tid_ptr; atomic_t *hqp; - unsigned long flags_ra; int i, j;

/* check the BSS with highest priority first */ @@@ -1118,8 -1110,7 +1110,7 @@@ try_again hqp = &priv_tmp->wmm.highest_queued_prio; for (i = atomic_read(hqp); i >= LOW_PRIO_TID; --i) {

- spin_lock_irqsave(&priv_tmp->wmm. - ra_list_spinlock, flags_ra); + spin_lock_bh(&priv_tmp->wmm.ra_list_spinlock);

tid_ptr = &(priv_tmp)->wmm. tid_tbl_ptr[tos_to_tid[i]]; @@@ -1134,9 -1125,7 +1125,7 @@@ goto found; }

- spin_unlock_irqrestore(&priv_tmp->wmm. - ra_list_spinlock, - flags_ra); + spin_unlock_bh(&priv_tmp->wmm.ra_list_spinlock); }

if (atomic_read(&priv_tmp->wmm.tx_pkts_queued) != 0) { @@@ -1158,7 -1147,7 +1147,7 @@@ found /* holds ra_list_spinlock */ if (atomic_read(hqp) > i) atomic_set(hqp, i); - spin_unlock_irqrestore(&priv_tmp->wmm.ra_list_spinlock, flags_ra); + spin_unlock_bh(&priv_tmp->wmm.ra_list_spinlock);

*priv = priv_tmp; *tid = tos_to_tid[i]; @@@ -1182,24 -1171,23 +1171,23 @@@ void mwifiex_rotate_priolists(struct mw struct mwifiex_adapter *adapter = priv->adapter; struct mwifiex_bss_prio_tbl *tbl = adapter->bss_prio_tbl; struct mwifiex_tid_tbl *tid_ptr = &priv->wmm.tid_tbl_ptr[tid]; - unsigned long flags;

- spin_lock_irqsave(&tbl[priv->bss_priority].bss_prio_lock, flags); + spin_lock_bh(&tbl[priv->bss_priority].bss_prio_lock); /* * dirty trick: we remove 'head' temporarily and reinsert it after * curr bss node. imagine list to stay fixed while head is moved */ list_move(&tbl[priv->bss_priority].bss_prio_head, &tbl[priv->bss_priority].bss_prio_cur->list); - spin_unlock_irqrestore(&tbl[priv->bss_priority].bss_prio_lock, flags); + spin_unlock_bh(&tbl[priv->bss_priority].bss_prio_lock);

- spin_lock_irqsave(&priv->wmm.ra_list_spinlock, flags); + spin_lock_bh(&priv->wmm.ra_list_spinlock); if (mwifiex_is_ralist_valid(priv, ra, tid)) { priv->wmm.packets_out[tid]++; /* same as above */ list_move(&tid_ptr->ra_list, &ra->list); } - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); }

/* @@@ -1236,8 -1224,7 +1224,7 @@@ mwifiex_is_11n_aggragation_possible(str */ static void mwifiex_send_single_packet(struct mwifiex_private *priv, - struct mwifiex_ra_list_tbl *ptr, int ptr_index, - unsigned long ra_list_flags) + struct mwifiex_ra_list_tbl *ptr, int ptr_index) __releases(&priv->wmm.ra_list_spinlock) { struct sk_buff *skb, *skb_next; @@@ -1246,8 -1233,7 +1233,7 @@@ struct mwifiex_txinfo *tx_info;

if (skb_queue_empty(&ptr->skb_head)) { - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, - ra_list_flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); mwifiex_dbg(adapter, DATA, "data: nothing to send\n"); return; } @@@ -1265,18 -1251,17 +1251,17 @@@ else skb_next = NULL;

- spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, ra_list_flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock);

tx_param.next_pkt_len = ((skb_next) ? skb_next->len + sizeof(struct txpd) : 0);

if (mwifiex_process_tx(priv, skb, &tx_param) == -EBUSY) { /* Queue the packet back at the head */ - spin_lock_irqsave(&priv->wmm.ra_list_spinlock, ra_list_flags); + spin_lock_bh(&priv->wmm.ra_list_spinlock);

if (!mwifiex_is_ralist_valid(priv, ptr, ptr_index)) { - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, - ra_list_flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); mwifiex_write_data_complete(adapter, skb, 0, -1); return; } @@@ -1286,8 -1271,7 +1271,7 @@@ ptr->total_pkt_count++; ptr->ba_pkt_count++; tx_info->flags |= MWIFIEX_BUF_FLAG_REQUEUED_PKT; - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, - ra_list_flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); } else { mwifiex_rotate_priolists(priv, ptr, ptr_index); atomic_dec(&priv->wmm.tx_pkts_queued); @@@ -1323,8 -1307,7 +1307,7 @@@ mwifiex_is_ptr_processed(struct mwifiex */ static void mwifiex_send_processed_packet(struct mwifiex_private *priv, - struct mwifiex_ra_list_tbl *ptr, int ptr_index, - unsigned long ra_list_flags) + struct mwifiex_ra_list_tbl *ptr, int ptr_index) __releases(&priv->wmm.ra_list_spinlock) { struct mwifiex_tx_param tx_param; @@@ -1334,8 -1317,7 +1317,7 @@@ struct mwifiex_txinfo *tx_info;

if (skb_queue_empty(&ptr->skb_head)) { - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, - ra_list_flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); return; }

@@@ -1343,8 -1325,7 +1325,7 @@@

if (adapter->data_sent || adapter->tx_lock_flag) { ptr->total_pkt_count--; - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, - ra_list_flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); skb_queue_tail(&adapter->tx_data_q, skb); atomic_dec(&priv->wmm.tx_pkts_queued); atomic_inc(&adapter->tx_queued); @@@ -1358,7 -1339,7 +1339,7 @@@

tx_info = MWIFIEX_SKB_TXCB(skb);

- spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, ra_list_flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock);

tx_param.next_pkt_len = ((skb_next) ? skb_next->len + @@@ -1374,11 -1355,10 +1355,10 @@@ switch (ret) { case -EBUSY: mwifiex_dbg(adapter, ERROR, "data: -EBUSY is returned\n"); - spin_lock_irqsave(&priv->wmm.ra_list_spinlock, ra_list_flags); + spin_lock_bh(&priv->wmm.ra_list_spinlock);

if (!mwifiex_is_ralist_valid(priv, ptr, ptr_index)) { - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, - ra_list_flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); mwifiex_write_data_complete(adapter, skb, 0, -1); return; } @@@ -1386,8 -1366,7 +1366,7 @@@ skb_queue_tail(&ptr->skb_head, skb);

tx_info->flags |= MWIFIEX_BUF_FLAG_REQUEUED_PKT; - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, - ra_list_flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); break; case -1: mwifiex_dbg(adapter, ERROR, "host_to_card failed: %#x\n", ret); @@@ -1404,10 -1383,9 +1383,9 @@@ if (ret != -EBUSY) { mwifiex_rotate_priolists(priv, ptr, ptr_index); atomic_dec(&priv->wmm.tx_pkts_queued); - spin_lock_irqsave(&priv->wmm.ra_list_spinlock, ra_list_flags); + spin_lock_bh(&priv->wmm.ra_list_spinlock); ptr->total_pkt_count--; - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, - ra_list_flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); } }

@@@ -1423,7 -1401,6 +1401,6 @@@ mwifiex_dequeue_tx_packet(struct mwifie int ptr_index = 0; u8 ra[ETH_ALEN]; int tid_del = 0, tid = 0; - unsigned long flags;

ptr = mwifiex_wmm_get_highest_priolist_ptr(adapter, &priv, &ptr_index); if (!ptr) @@@ -1433,14 -1410,14 +1410,14 @@@

mwifiex_dbg(adapter, DATA, "data: tid=%d\n", tid);

- spin_lock_irqsave(&priv->wmm.ra_list_spinlock, flags); + spin_lock_bh(&priv->wmm.ra_list_spinlock); if (!mwifiex_is_ralist_valid(priv, ptr, ptr_index)) { - spin_unlock_irqrestore(&priv->wmm.ra_list_spinlock, flags); + spin_unlock_bh(&priv->wmm.ra_list_spinlock); return -1; }

if (mwifiex_is_ptr_processed(priv, ptr)) { - mwifiex_send_processed_packet(priv, ptr, ptr_index, flags); + mwifiex_send_processed_packet(priv, ptr, ptr_index); /* ra_list_spinlock has been freed in mwifiex_send_processed_packet() */ return 0; @@@ -1455,12 -1432,12 +1432,12 @@@ mwifiex_is_amsdu_allowed(priv, tid) && mwifiex_is_11n_aggragation_possible(priv, ptr, adapter->tx_buf_size)) - mwifiex_11n_aggregate_pkt(priv, ptr, ptr_index, flags); + mwifiex_11n_aggregate_pkt(priv, ptr, ptr_index); /* ra_list_spinlock has been freed in * mwifiex_11n_aggregate_pkt() */ else - mwifiex_send_single_packet(priv, ptr, ptr_index, flags); + mwifiex_send_single_packet(priv, ptr, ptr_index); /* ra_list_spinlock has been freed in * mwifiex_send_single_packet() */ @@@ -1481,11 -1458,11 +1458,11 @@@ if (mwifiex_is_amsdu_allowed(priv, tid) && mwifiex_is_11n_aggragation_possible(priv, ptr, adapter->tx_buf_size)) - mwifiex_11n_aggregate_pkt(priv, ptr, ptr_index, flags); + mwifiex_11n_aggregate_pkt(priv, ptr, ptr_index); /* ra_list_spinlock has been freed in mwifiex_11n_aggregate_pkt() */ else - mwifiex_send_single_packet(priv, ptr, ptr_index, flags); + mwifiex_send_single_packet(priv, ptr, ptr_index); /* ra_list_spinlock has been freed in mwifiex_send_single_packet() */ } diff --combined drivers/net/wireless/mediatek/mt76/mt76.h index 889b76deb703,56bf93a8988e..989386ecb5e4 --- a/drivers/net/wireless/mediatek/mt76/mt76.h +++ b/drivers/net/wireless/mediatek/mt76/mt76.h @@@ -30,7 -30,6 +30,7 @@@ #define MT_TX_RING_SIZE 256 #define MT_MCU_RING_SIZE 32 #define MT_RX_BUF_SIZE 2048 +#define MT_SKB_HEAD_LEN 128

struct mt76_dev; struct mt76_wcid; @@@ -259,10 -258,11 +259,11 @@@ struct mt76_rx_tid #define MT_TX_CB_TXS_DONE BIT(1) #define MT_TX_CB_TXS_FAILED BIT(2)

- #define MT_PACKET_ID_MASK GENMASK(7, 0) + #define MT_PACKET_ID_MASK GENMASK(6, 0) #define MT_PACKET_ID_NO_ACK 0 #define MT_PACKET_ID_NO_SKB 1 #define MT_PACKET_ID_FIRST 2 + #define MT_PACKET_ID_HAS_RATE BIT(7)

#define MT_TX_STATUS_SKB_TIMEOUT HZ

@@@ -382,7 -382,8 +383,8 @@@ enum mt76u_out_ep __MT_EP_OUT_MAX, };

- #define MT_SG_MAX_SIZE 8 + #define MT_TX_SG_MAX_SIZE 8 + #define MT_RX_SG_MAX_SIZE 1 #define MT_NUM_TX_ENTRIES 256 #define MT_NUM_RX_ENTRIES 128 #define MCU_RESP_URB_SIZE 1024 @@@ -394,9 -395,7 +396,7 @@@ struct mt76_usb struct delayed_work stat_work;

u8 out_ep[__MT_EP_OUT_MAX]; - u16 out_max_packet; u8 in_ep[__MT_EP_IN_MAX]; - u16 in_max_packet; bool sg_en;

struct mt76u_mcu { @@@ -453,6 -452,7 +453,7 @@@ struct mt76_dev int tx_dma_idx[4];

struct tasklet_struct tx_tasklet; + struct napi_struct tx_napi; struct delayed_work mac_work;

wait_queue_head_t tx_wait; @@@ -484,6 -484,8 +485,8 @@@ int txpower_conf; int txpower_cur;

+ enum nl80211_dfs_regions region; + u32 debugfs_reg;

struct led_classdev led_cdev; @@@ -689,6 -691,14 +692,14 @@@ static inline void mt76_insert_hdr_pad( skb->data[len + 1] = 0; }

+ static inline bool mt76_is_skb_pktid(u8 pktid) + { + if (pktid & MT_PACKET_ID_HAS_RATE) + return false; + + return pktid >= MT_PACKET_ID_FIRST; + } + void mt76_rx(struct mt76_dev *dev, enum mt76_rxq_id q, struct sk_buff *skb); void mt76_tx(struct mt76_dev *dev, struct ieee80211_sta *sta, struct mt76_wcid *wcid, struct sk_buff *skb); @@@ -750,6 -760,10 +761,10 @@@ void mt76_csa_check(struct mt76_dev *de void mt76_csa_finish(struct mt76_dev *dev);

int mt76_set_tim(struct ieee80211_hw *hw, struct ieee80211_sta *sta, bool set); + void mt76_insert_ccmp_hdr(struct sk_buff *skb, u8 key_id); + int mt76_get_rate(struct mt76_dev *dev, + struct ieee80211_supported_band *sband, + int idx, bool cck);

/* internal */ void mt76_tx_free(struct mt76_dev *dev); diff --combined drivers/net/wireless/mediatek/mt76/usb.c index dd90427b2d67,61b27f3ec6e4..fb87ce7fbdf6 --- a/drivers/net/wireless/mediatek/mt76/usb.c +++ b/drivers/net/wireless/mediatek/mt76/usb.c @@@ -267,12 -267,10 +267,10 @@@ mt76u_set_endpoints(struct usb_interfac if (usb_endpoint_is_bulk_in(ep_desc) && in_ep < __MT_EP_IN_MAX) { usb->in_ep[in_ep] = usb_endpoint_num(ep_desc); - usb->in_max_packet = usb_endpoint_maxp(ep_desc); in_ep++; } else if (usb_endpoint_is_bulk_out(ep_desc) && out_ep < __MT_EP_OUT_MAX) { usb->out_ep[out_ep] = usb_endpoint_num(ep_desc); - usb->out_max_packet = usb_endpoint_maxp(ep_desc); out_ep++; } } @@@ -333,12 -331,13 +331,13 @@@ mt76u_refill_rx(struct mt76_dev *dev, s }

static int - mt76u_urb_alloc(struct mt76_dev *dev, struct mt76_queue_entry *e) + mt76u_urb_alloc(struct mt76_dev *dev, struct mt76_queue_entry *e, + int sg_max_size) { unsigned int size = sizeof(struct urb);

if (dev->usb.sg_en) - size += MT_SG_MAX_SIZE * sizeof(struct scatterlist); + size += sg_max_size * sizeof(struct scatterlist);

e->urb = kzalloc(size, GFP_KERNEL); if (!e->urb) @@@ -357,11 -356,12 +356,12 @@@ mt76u_rx_urb_alloc(struct mt76_dev *dev { int err;

- err = mt76u_urb_alloc(dev, e); + err = mt76u_urb_alloc(dev, e, MT_RX_SG_MAX_SIZE); if (err) return err;

- return mt76u_refill_rx(dev, e->urb, MT_SG_MAX_SIZE, GFP_KERNEL); + return mt76u_refill_rx(dev, e->urb, MT_RX_SG_MAX_SIZE, + GFP_KERNEL); }

static void mt76u_urb_free(struct urb *urb) @@@ -429,42 -429,6 +429,42 @@@ static int mt76u_get_rx_entry_len(u8 *d return dma_len; }

+static struct sk_buff * +mt76u_build_rx_skb(void *data, int len, int buf_size) +{ + struct sk_buff *skb; + + if (SKB_WITH_OVERHEAD(buf_size) < MT_DMA_HDR_LEN + len) { + struct page *page; + + /* slow path, not enough space for data and + * skb_shared_info + */ + skb = alloc_skb(MT_SKB_HEAD_LEN, GFP_ATOMIC); + if (!skb) + return NULL; + + skb_put_data(skb, data + MT_DMA_HDR_LEN, MT_SKB_HEAD_LEN); + data += (MT_DMA_HDR_LEN + MT_SKB_HEAD_LEN); + page = virt_to_head_page(data); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + page, data - page_address(page), + len - MT_SKB_HEAD_LEN, buf_size); + + return skb; + } + + /* fast path */ + skb = build_skb(data, buf_size); + if (!skb) + return NULL; + + skb_reserve(skb, MT_DMA_HDR_LEN); + __skb_put(skb, len); + + return skb; +} + static int mt76u_process_rx_entry(struct mt76_dev *dev, struct urb *urb) { @@@ -482,11 -446,19 +482,11 @@@ return 0;

data_len = min_t(int, len, data_len - MT_DMA_HDR_LEN); - if (MT_DMA_HDR_LEN + data_len > SKB_WITH_OVERHEAD(q->buf_size)) { - dev_err_ratelimited(dev->dev, "rx data too big %d\n", data_len); - return 0; - } - - skb = build_skb(data, q->buf_size); + skb = mt76u_build_rx_skb(data, data_len, q->buf_size); if (!skb) return 0;

- skb_reserve(skb, MT_DMA_HDR_LEN); - __skb_put(skb, data_len); len -= data_len; - while (len > 0 && nsgs < urb->num_sgs) { data_len = min_t(int, len, urb->sg[nsgs].length); skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, @@@ -605,8 -577,9 +605,9 @@@ static int mt76u_alloc_rx(struct mt76_d if (!q->entry) return -ENOMEM;

- q->buf_size = dev->usb.sg_en ? MT_RX_BUF_SIZE : PAGE_SIZE; q->ndesc = MT_NUM_RX_ENTRIES; + q->buf_size = PAGE_SIZE; + for (i = 0; i < q->ndesc; i++) { err = mt76u_rx_urb_alloc(dev, &q->entry[i]); if (err < 0) @@@ -763,7 -736,7 +764,7 @@@ mt76u_tx_setup_buffers(struct mt76_dev urb->transfer_buffer = skb->data; return 0; } else { - sg_init_table(urb->sg, MT_SG_MAX_SIZE); + sg_init_table(urb->sg, MT_TX_SG_MAX_SIZE); urb->num_sgs = skb_to_sgvec(skb, urb->sg, 0, skb->len); if (urb->num_sgs == 0) return -ENOMEM; @@@ -857,7 -830,8 +858,8 @@@ static int mt76u_alloc_tx(struct mt76_d

q->ndesc = MT_NUM_TX_ENTRIES; for (j = 0; j < q->ndesc; j++) { - err = mt76u_urb_alloc(dev, &q->entry[j]); + err = mt76u_urb_alloc(dev, &q->entry[j], + MT_TX_SG_MAX_SIZE); if (err < 0) return err; } diff --combined fs/afs/cmservice.c index 2168b36c7a2a,1ea39971eb91..b86195e4dc6c --- a/fs/afs/cmservice.c +++ b/fs/afs/cmservice.c @@@ -256,11 -256,8 +256,11 @@@ static void SRXAFSCB_CallBack(struct wo * server holds up change visibility till it receives our reply so as * to maintain cache coherency. */ - if (call->server) + if (call->server) { + trace_afs_server(call->server, atomic_read(&call->server->usage), + afs_server_trace_callback); afs_break_callbacks(call->server, call->count, call->request); + }

afs_send_empty_reply(call); afs_put_call(call); @@@ -505,14 -502,18 +505,14 @@@ static void SRXAFSCB_ProbeUuid(struct w struct afs_call *call = container_of(work, struct afs_call, work); struct afs_uuid *r = call->request;

- struct { - __be32 match; - } reply; - _enter("");

if (memcmp(r, &call->net->uuid, sizeof(call->net->uuid)) == 0) - reply.match = htonl(0); + afs_send_empty_reply(call); else - reply.match = htonl(1); + rxrpc_kernel_abort_call(call->net->socket, call->rxcall, + 1, 1, "K-1");

- afs_send_simple_reply(call, &reply, sizeof(reply)); afs_put_call(call); _leave(""); } @@@ -579,9 -580,8 +579,8 @@@ static int afs_deliver_cb_probe_uuid(st */ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work) { - struct afs_interface *ifs; struct afs_call *call = container_of(work, struct afs_call, work); - int loop, nifs; + int loop;

struct { struct /* InterfaceAddr */ { @@@ -599,19 -599,7 +598,7 @@@

_enter("");

- nifs = 0; - ifs = kcalloc(32, sizeof(*ifs), GFP_KERNEL); - if (ifs) { - nifs = afs_get_ipv4_interfaces(call->net, ifs, 32, false); - if (nifs < 0) { - kfree(ifs); - ifs = NULL; - nifs = 0; - } - } - memset(&reply, 0, sizeof(reply)); - reply.ia.nifs = htonl(nifs);

reply.ia.uuid[0] = call->net->uuid.time_low; reply.ia.uuid[1] = htonl(ntohs(call->net->uuid.time_mid)); @@@ -621,15 -609,6 +608,6 @@@ for (loop = 0; loop < 6; loop++) reply.ia.uuid[loop + 5] = htonl((s8) call->net->uuid.node[loop]);

- if (ifs) { - for (loop = 0; loop < nifs; loop++) { - reply.ia.ifaddr[loop] = ifs[loop].address.s_addr; - reply.ia.netmask[loop] = ifs[loop].netmask.s_addr; - reply.ia.mtu[loop] = htonl(ifs[loop].mtu); - } - kfree(ifs); - } - reply.cap.capcount = htonl(1); reply.cap.caps[0] = htonl(AFS_CAP_ERROR_TRANSLATION); afs_send_simple_reply(call, &reply, sizeof(reply)); diff --combined fs/afs/internal.h index be37fafbaeb5,0f84d0da5417..f66a3be12fd6 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@@ -514,7 -514,6 +514,7 @@@ struct afs_server atomic_t usage; u32 addr_version; /* Address list version */ u32 cm_epoch; /* Server RxRPC epoch */ + unsigned int debug_id; /* Debugging ID for traces */

/* file service access */ rwlock_t fs_lock; /* access lock */ @@@ -720,15 -719,6 +720,6 @@@ struct afs_permits };

/* - * record of one of a system's set of network interfaces - */ - struct afs_interface { - struct in_addr address; /* IPv4 address bound to interface */ - struct in_addr netmask; /* netmask applied to address */ - unsigned mtu; /* MTU of interface */ - }; - - /* * Error prioritisation and accumulation. */ struct afs_error { @@@ -845,9 -835,9 +836,9 @@@ extern struct fscache_cookie_def afs_vn * callback.c */ extern void afs_init_callback_state(struct afs_server *); -extern void __afs_break_callback(struct afs_vnode *); -extern void afs_break_callback(struct afs_vnode *); -extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break*); +extern void __afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); +extern void afs_break_callback(struct afs_vnode *, enum afs_cb_break_reason); +extern void afs_break_callbacks(struct afs_server *, size_t, struct afs_callback_break *);

extern int afs_register_server_cb_interest(struct afs_vnode *, struct afs_server_list *, unsigned int); @@@ -1091,12 -1081,6 +1082,6 @@@ extern struct vfsmount *afs_d_automount extern void afs_mntpt_kill_timer(void);

/* - * netdevices.c - */ - extern int afs_get_ipv4_interfaces(struct afs_net *, struct afs_interface *, - size_t, bool); - - /* * proc.c */ #ifdef CONFIG_PROC_FS @@@ -1241,12 -1225,17 +1226,12 @@@ extern void __exit afs_clean_up_permit_ */ extern spinlock_t afs_server_peer_lock;

-static inline struct afs_server *afs_get_server(struct afs_server *server) -{ - atomic_inc(&server->usage); - return server; -} - extern struct afs_server *afs_find_server(struct afs_net *, const struct sockaddr_rxrpc *); extern struct afs_server *afs_find_server_by_uuid(struct afs_net *, const uuid_t *); extern struct afs_server *afs_lookup_server(struct afs_cell *, struct key *, const uuid_t *); -extern void afs_put_server(struct afs_net *, struct afs_server *); +extern struct afs_server *afs_get_server(struct afs_server *, enum afs_server_trace); +extern void afs_put_server(struct afs_net *, struct afs_server *, enum afs_server_trace); extern void afs_manage_servers(struct work_struct *); extern void afs_servers_timer(struct timer_list *); extern void __net_exit afs_purge_servers(struct afs_net *); @@@ -1430,7 -1419,7 +1415,7 @@@ static inline void afs_check_for_remote { if (fc->ac.error == -ENOENT) { set_bit(AFS_VNODE_DELETED, &vnode->flags); - afs_break_callback(vnode); + afs_break_callback(vnode, afs_cb_break_for_deleted); } }

diff --combined include/linux/mlx5/qp.h index 08e43cd9e742,127d224443e3..937041101504 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@@ -37,8 -37,7 +37,8 @@@ #include <linux/mlx5/driver.h>

#define MLX5_INVALID_LKEY 0x100 -#define MLX5_SIG_WQE_SIZE (MLX5_SEND_WQE_BB * 5) +/* UMR (3 WQE_BB's) + SIG (3 WQE_BB's) + PSV (mem) + PSV (wire) */ +#define MLX5_SIG_WQE_SIZE (MLX5_SEND_WQE_BB * 8) #define MLX5_DIF_SIZE 8 #define MLX5_STRIDE_BLOCK_OP 0x400 #define MLX5_CPY_GRD_MASK 0xc0 @@@ -203,7 -202,12 +203,12 @@@ struct mlx5_wqe_ctrl_seg u8 signature; u8 rsvd[2]; u8 fm_ce_se; - __be32 imm; + union { + __be32 general_id; + __be32 imm; + __be32 umr_mkey; + __be32 tisn; + }; };

#define MLX5_WQE_CTRL_DS_MASK 0x3f @@@ -552,11 -556,6 +557,6 @@@ static inline struct mlx5_core_qp *__ml return radix_tree_lookup(&dev->priv.qp_table.tree, qpn); }

- static inline struct mlx5_core_mkey *__mlx5_mr_lookup(struct mlx5_core_dev *dev, u32 key) - { - return radix_tree_lookup(&dev->priv.mkey_table.tree, key); - } - int mlx5_core_create_dct(struct mlx5_core_dev *dev, struct mlx5_core_dct *qp, u32 *in, int inlen, diff --combined include/linux/phylink.h index 5b130140fb8f,0fe57a261c9c..300ecdb6790a --- a/include/linux/phylink.h +++ b/include/linux/phylink.h @@@ -54,6 -54,21 +54,21 @@@ struct phylink_link_state unsigned int an_complete:1; };

+ enum phylink_op_type { + PHYLINK_NETDEV = 0, + PHYLINK_DEV, + }; + + /** + * struct phylink_config - PHYLINK configuration structure + * @dev: a pointer to a struct device associated with the MAC + * @type: operation type of PHYLINK instance + */ + struct phylink_config { + struct device *dev; + enum phylink_op_type type; + }; + /** * struct phylink_mac_ops - MAC operations structure. * @validate: Validate and update the link configuration. @@@ -66,16 -81,17 +81,17 @@@ * The individual methods are described more fully below. */ struct phylink_mac_ops { - void (*validate)(struct net_device *ndev, unsigned long *supported, + void (*validate)(struct phylink_config *config, + unsigned long *supported, struct phylink_link_state *state); - int (*mac_link_state)(struct net_device *ndev, + int (*mac_link_state)(struct phylink_config *config, struct phylink_link_state *state); - void (*mac_config)(struct net_device *ndev, unsigned int mode, + void (*mac_config)(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state); - void (*mac_an_restart)(struct net_device *ndev); - void (*mac_link_down)(struct net_device *ndev, unsigned int mode, + void (*mac_an_restart)(struct phylink_config *config); + void (*mac_link_down)(struct phylink_config *config, unsigned int mode, phy_interface_t interface); - void (*mac_link_up)(struct net_device *ndev, unsigned int mode, + void (*mac_link_up)(struct phylink_config *config, unsigned int mode, phy_interface_t interface, struct phy_device *phy); }; @@@ -83,7 -99,7 +99,7 @@@ #if 0 /* For kernel-doc purposes only. */ /** * validate - Validate and update the link configuration - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @supported: ethtool bitmask for supported link modes. * @state: a pointer to a &struct phylink_link_state. * @@@ -93,26 -109,19 +109,26 @@@ * Note that the PHY may be able to transform from one connection * technology to another, so, eg, don't clear 1000BaseX just * because the MAC is unable to BaseX mode. This is more about - * clearing unsupported speeds and duplex settings. + * clearing unsupported speeds and duplex settings. The port modes + * should not be cleared; phylink_set_port_modes() will help with this. * * If the @state->interface mode is %PHY_INTERFACE_MODE_1000BASEX * or %PHY_INTERFACE_MODE_2500BASEX, select the appropriate mode * based on @state->advertising and/or @state->speed and update - * @state->interface accordingly. + * @state->interface accordingly. See phylink_helper_basex_speed(). + * + * When @state->interface is %PHY_INTERFACE_MODE_NA, phylink expects the + * MAC driver to return all supported link modes. + * + * If the @state->interface mode is not supported, then the @supported + * mask must be cleared. */ - void validate(struct net_device *ndev, unsigned long *supported, + void validate(struct phylink_config *config, unsigned long *supported, struct phylink_link_state *state);

/** * mac_link_state() - Read the current link state from the hardware - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @state: a pointer to a &struct phylink_link_state. * * Read the current link state from the MAC, reporting the current @@@ -121,12 -130,12 +137,12 @@@ * negotiation completion state in @state->an_complete, and link * up state in @state->link. */ - int mac_link_state(struct net_device *ndev, + int mac_link_state(struct phylink_config *config, struct phylink_link_state *state);

/** * mac_config() - configure the MAC for the selected mode and state - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @mode: one of %MLO_AN_FIXED, %MLO_AN_PHY, %MLO_AN_INBAND. * @state: a pointer to a &struct phylink_link_state. * @@@ -175,18 -184,18 +191,18 @@@ * down. This "update" behaviour is critical to avoid bouncing the * link up status. */ - void mac_config(struct net_device *ndev, unsigned int mode, + void mac_config(struct phylink_config *config, unsigned int mode, const struct phylink_link_state *state);

/** * mac_an_restart() - restart 802.3z BaseX autonegotiation - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. */ - void mac_an_restart(struct net_device *ndev); + void mac_an_restart(struct phylink_config *config);

/** * mac_link_down() - take the link down - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @mode: link autonegotiation mode * @interface: link &typedef phy_interface_t mode * @@@ -195,12 -204,12 +211,12 @@@ * Energy Efficient Ethernet MAC configuration. Interface type * selection must be done in mac_config(). */ - void mac_link_down(struct net_device *ndev, unsigned int mode, + void mac_link_down(struct phylink_config *config, unsigned int mode, phy_interface_t interface);

/** * mac_link_up() - allow the link to come up - * @ndev: a pointer to a &struct net_device for the MAC. + * @config: a pointer to a &struct phylink_config. * @mode: link autonegotiation mode * @interface: link &typedef phy_interface_t mode * @phy: any attached phy @@@ -211,13 -220,14 +227,14 @@@ * phy_init_eee() and perform appropriate MAC configuration for EEE. * Interface type selection must be done in mac_config(). */ - void mac_link_up(struct net_device *ndev, unsigned int mode, + void mac_link_up(struct phylink_config *config, unsigned int mode, phy_interface_t interface, struct phy_device *phy); #endif

- struct phylink *phylink_create(struct net_device *, struct fwnode_handle *, - phy_interface_t iface, const struct phylink_mac_ops *ops); + struct phylink *phylink_create(struct phylink_config *, struct fwnode_handle *, + phy_interface_t iface, + const struct phylink_mac_ops *ops); void phylink_destroy(struct phylink *);

int phylink_connect_phy(struct phylink *, struct phy_device *); diff --combined include/net/ip_vs.h index b36a1df93e7c,cb1ad0cc5c7b..3759167f91f5 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@@ -603,6 -603,7 +603,7 @@@ struct ip_vs_dest_user_kern

u16 tun_type; /* tunnel type */ __be16 tun_port; /* tunnel port */ + u16 tun_flags; /* tunnel flags */ };

@@@ -665,6 -666,7 +666,7 @@@ struct ip_vs_dest atomic_t last_weight; /* server latest weight */ __u16 tun_type; /* tunnel type */ __be16 tun_port; /* tunnel port */ + __u16 tun_flags; /* tunnel flags */

refcount_t refcnt; /* reference counter */ struct ip_vs_stats stats; /* statistics */ @@@ -808,12 -810,11 +810,12 @@@ struct ipvs_master_sync_state struct ip_vs_sync_buff *sync_buff; unsigned long sync_queue_len; unsigned int sync_queue_delay; - struct task_struct *master_thread; struct delayed_work master_wakeup_work; struct netns_ipvs *ipvs; };

+struct ip_vs_sync_thread_data; + /* How much time to keep dests in trash */ #define IP_VS_DEST_TRASH_PERIOD (120 * HZ)

@@@ -944,8 -945,7 +946,8 @@@ struct netns_ipvs spinlock_t sync_lock; struct ipvs_master_sync_state *ms; spinlock_t sync_buff_lock; - struct task_struct **backup_threads; + struct ip_vs_sync_thread_data *master_tinfo; + struct ip_vs_sync_thread_data *backup_tinfo; int threads_mask; volatile int sync_state; struct mutex sync_mutex; @@@ -1406,6 -1406,9 +1408,9 @@@ bool ip_vs_has_real_service(struct netn struct ip_vs_dest * ip_vs_find_real_service(struct netns_ipvs *ipvs, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); + struct ip_vs_dest *ip_vs_find_tunnel(struct netns_ipvs *ipvs, int af, + const union nf_inet_addr *daddr, + __be16 tun_port);

int ip_vs_use_count_inc(void); void ip_vs_use_count_dec(void); @@@ -1499,6 -1502,9 +1504,9 @@@ static inline int ip_vs_todrop(struct n static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { return 0; } #endif

+ #define IP_VS_DFWD_METHOD(dest) (atomic_read(&(dest)->conn_flags) & \ + IP_VS_CONN_F_FWD_MASK) + /* ip_vs_fwd_tag returns the forwarding tag of the connection */ #define IP_VS_FWD_METHOD(cp) (cp->flags & IP_VS_CONN_F_FWD_MASK)

diff --combined include/net/tls.h index 889df0312cd1,0279938386ab..176d0b039f32 --- a/include/net/tls.h +++ b/include/net/tls.h @@@ -40,6 -40,7 +40,7 @@@ #include <linux/socket.h> #include <linux/tcp.h> #include <linux/skmsg.h> + #include <linux/netdevice.h>

#include <net/tcp.h> #include <net/strparser.h> @@@ -61,6 -62,7 +62,7 @@@ #define TLS_DEVICE_NAME_MAX 32

#define MAX_IV_SIZE 16 + #define TLS_MAX_REC_SEQ_SIZE 8

/* For AES-CCM, the full 16-bytes of IV is made of '4' fields of given sizes. * @@@ -197,20 -199,24 +199,24 @@@ struct tls_offload_context_tx

struct scatterlist sg_tx_data[MAX_SKB_FRAGS]; void (*sk_destruct)(struct sock *sk); - u8 driver_state[]; + u8 driver_state[] __aligned(8); /* The TLS layer reserves room for driver specific state * Currently the belief is that there is not enough * driver specific state to justify another layer of indirection */ - #define TLS_DRIVER_STATE_SIZE (max_t(size_t, 8, sizeof(void *))) + #define TLS_DRIVER_STATE_SIZE_TX 16 };

#define TLS_OFFLOAD_CONTEXT_SIZE_TX \ - (ALIGN(sizeof(struct tls_offload_context_tx), sizeof(void *)) + \ - TLS_DRIVER_STATE_SIZE) + (sizeof(struct tls_offload_context_tx) + TLS_DRIVER_STATE_SIZE_TX)

enum tls_context_flags { TLS_RX_SYNC_RUNNING = 0, + /* Unlike RX where resync is driven entirely by the core in TX only + * the driver knows when things went out of sync, so we need the flag + * to be atomic. + */ + TLS_TX_SYNC_SCHED = 1, };

struct cipher_context { @@@ -240,34 -246,32 +246,32 @@@ struct tls_prot_info };

struct tls_context { + /* read-only cache line */ struct tls_prot_info prot_info;

- union tls_crypto_context crypto_send; - union tls_crypto_context crypto_recv; + u8 tx_conf:3; + u8 rx_conf:3;

- struct list_head list; - struct net_device *netdev; - refcount_t refcount; + int (*push_pending_record)(struct sock *sk, int flags); + void (*sk_write_space)(struct sock *sk);

void *priv_ctx_tx; void *priv_ctx_rx;

- u8 tx_conf:3; - u8 rx_conf:3; + struct net_device *netdev;

+ /* rw cache line */ struct cipher_context tx; struct cipher_context rx;

struct scatterlist *partially_sent_record; u16 partially_sent_offset;

- unsigned long flags; bool in_tcp_sendpages; bool pending_open_record_frags; + unsigned long flags;

- int (*push_pending_record)(struct sock *sk, int flags); - - void (*sk_write_space)(struct sock *sk); + /* cache cold stuff */ void (*sk_destruct)(struct sock *sk); void (*sk_proto_close)(struct sock *sk, long timeout);

@@@ -279,6 -283,12 +283,12 @@@ int __user *optlen); int (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); + + union tls_crypto_context crypto_send; + union tls_crypto_context crypto_recv; + + struct list_head list; + refcount_t refcount; };

enum tls_offload_ctx_dir { @@@ -294,26 -304,49 +304,50 @@@ struct tlsdev_ops void (*tls_dev_del)(struct net_device *netdev, struct tls_context *ctx, enum tls_offload_ctx_dir direction); - void (*tls_dev_resync_rx)(struct net_device *netdev, - struct sock *sk, u32 seq, u64 rcd_sn); + void (*tls_dev_resync)(struct net_device *netdev, + struct sock *sk, u32 seq, u8 *rcd_sn, + enum tls_offload_ctx_dir direction); };

+ enum tls_offload_sync_type { + TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ = 0, + TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT = 1, + }; + + #define TLS_DEVICE_RESYNC_NH_START_IVAL 2 + #define TLS_DEVICE_RESYNC_NH_MAX_IVAL 128 + struct tls_offload_context_rx { /* sw must be the first member of tls_offload_context_rx */ struct tls_sw_context_rx sw; - atomic64_t resync_req; - u8 driver_state[]; + enum tls_offload_sync_type resync_type; + /* this member is set regardless of resync_type, to avoid branches */ + u8 resync_nh_reset:1; + /* CORE_NEXT_HINT-only member, but use the hole here */ + u8 resync_nh_do_now:1; + union { + /* TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ */ + struct { + atomic64_t resync_req; + }; + /* TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT */ + struct { + u32 decrypted_failed; + u32 decrypted_tgt; + } resync_nh; + }; + u8 driver_state[] __aligned(8); /* The TLS layer reserves room for driver specific state * Currently the belief is that there is not enough * driver specific state to justify another layer of indirection */ + #define TLS_DRIVER_STATE_SIZE_RX 8 };

#define TLS_OFFLOAD_CONTEXT_SIZE_RX \ - (ALIGN(sizeof(struct tls_offload_context_rx), sizeof(void *)) + \ - TLS_DRIVER_STATE_SIZE) + (sizeof(struct tls_offload_context_rx) + TLS_DRIVER_STATE_SIZE_RX)

+void tls_ctx_free(struct tls_context *ctx); int wait_on_pending_writer(struct sock *sk, long *timeo); int tls_sk_query(struct sock *sk, int optname, char __user *optval, int __user *optlen); @@@ -432,19 -465,15 +466,15 @@@ static inline struct tls_context *tls_g }

static inline void tls_advance_record_sn(struct sock *sk, - struct cipher_context *ctx, - int version) + struct tls_prot_info *prot, + struct cipher_context *ctx) { - struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_prot_info *prot = &tls_ctx->prot_info; - if (tls_bigint_increment(ctx->rec_seq, prot->rec_seq_size)) tls_err_abort(sk, EBADMSG);

- if (version != TLS_1_3_VERSION) { + if (prot->version != TLS_1_3_VERSION) tls_bigint_increment(ctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, prot->iv_size); - } }

static inline void tls_fill_prepend(struct tls_context *ctx, @@@ -546,6 -575,23 +576,23 @@@ tls_offload_ctx_rx(const struct tls_con return (struct tls_offload_context_rx *)tls_ctx->priv_ctx_rx; }

+ #if IS_ENABLED(CONFIG_TLS_DEVICE) + static inline void *__tls_driver_ctx(struct tls_context *tls_ctx, + enum tls_offload_ctx_dir direction) + { + if (direction == TLS_OFFLOAD_CTX_DIR_TX) + return tls_offload_ctx_tx(tls_ctx)->driver_state; + else + return tls_offload_ctx_rx(tls_ctx)->driver_state; + } + + static inline void * + tls_driver_ctx(const struct sock *sk, enum tls_offload_ctx_dir direction) + { + return __tls_driver_ctx(tls_get_ctx(sk), direction); + } + #endif + /* The TLS context is valid until sk_destruct is called */ static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq) { @@@ -555,6 -601,31 +602,31 @@@ atomic64_set(&rx_ctx->resync_req, ((u64)ntohl(seq) << 32) | 1); }

+ static inline void + tls_offload_rx_resync_set_type(struct sock *sk, enum tls_offload_sync_type type) + { + struct tls_context *tls_ctx = tls_get_ctx(sk); + + tls_offload_ctx_rx(tls_ctx)->resync_type = type; + } + + static inline void tls_offload_tx_resync_request(struct sock *sk) + { + struct tls_context *tls_ctx = tls_get_ctx(sk); + + WARN_ON(test_and_set_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags)); + } + + /* Driver's seq tracking has to be disabled until resync succeeded */ + static inline bool tls_offload_tx_resync_pending(struct sock *sk) + { + struct tls_context *tls_ctx = tls_get_ctx(sk); + bool ret; + + ret = test_bit(TLS_TX_SYNC_SCHED, &tls_ctx->flags); + smp_mb__after_atomic(); + return ret; + }

int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, unsigned char *record_type); @@@ -563,6 -634,7 +635,7 @@@ void tls_unregister_device(struct tls_d int tls_device_decrypted(struct sock *sk, struct sk_buff *skb); int decrypt_skb(struct sock *sk, struct sk_buff *skb, struct scatterlist *sgout); + struct sk_buff *tls_encrypt_skb(struct sk_buff *skb);

struct sk_buff *tls_validate_xmit_skb(struct sock *sk, struct net_device *dev, @@@ -575,6 -647,6 +648,6 @@@ int tls_sw_fallback_init(struct sock *s int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx);

void tls_device_offload_cleanup_rx(struct sock *sk); - void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn); + void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq);

#endif /* _TLS_OFFLOAD_H */ diff --combined include/net/xdp_sock.h index 7da155164947,057b159ff8b9..dc0aa9b2c12d --- a/include/net/xdp_sock.h +++ b/include/net/xdp_sock.h @@@ -58,16 -58,11 +58,16 @@@ struct xdp_sock struct xdp_umem *umem; struct list_head flush_node; u16 queue_id; - struct xsk_queue *tx ____cacheline_aligned_in_smp; - struct list_head list; bool zc; + enum { + XSK_READY = 0, + XSK_BOUND, + XSK_UNBOUND, + } state; /* Protects multiple processes in the control path */ struct mutex mutex; + struct xsk_queue *tx ____cacheline_aligned_in_smp; + struct list_head list; /* Mutual exclusion of NAPI TX thread and sendmsg error paths * in the SKB destructor callback. */ @@@ -82,10 -77,11 +82,11 @@@ int xsk_rcv(struct xdp_sock *xs, struc void xsk_flush(struct xdp_sock *xs); bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs); /* Used from netdev driver */ + bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt); u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr); void xsk_umem_discard_addr(struct xdp_umem *umem); void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries); - bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len); + bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc); void xsk_umem_consume_tx_done(struct xdp_umem *umem); struct xdp_umem_fq_reuse *xsk_reuseq_prepare(u32 nentries); struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem, @@@ -104,6 -100,16 +105,16 @@@ static inline dma_addr_t xdp_umem_get_d }

/* Reuse-queue aware version of FILL queue helpers */ + static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt) + { + struct xdp_umem_fq_reuse *rq = umem->fq_reuse; + + if (rq->length >= cnt) + return true; + + return xsk_umem_has_addrs(umem, cnt - rq->length); + } + static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) { struct xdp_umem_fq_reuse *rq = umem->fq_reuse; @@@ -151,6 -157,11 +162,11 @@@ static inline bool xsk_is_setup_for_bpf return false; }

+ static inline bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt) + { + return false; + } + static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) { return NULL; @@@ -164,8 -175,8 +180,8 @@@ static inline void xsk_umem_complete_tx { }

- static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, - u32 *len) + static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, + struct xdp_desc *desc) { return false; } @@@ -205,6 -216,11 +221,11 @@@ static inline dma_addr_t xdp_umem_get_d return 0; }

+ static inline bool xsk_umem_has_addrs_rq(struct xdp_umem *umem, u32 cnt) + { + return false; + } + static inline u64 *xsk_umem_peek_addr_rq(struct xdp_umem *umem, u64 *addr) { return NULL; diff --combined include/uapi/linux/bpf.h index 29a5bc3d5c66,ead27aebf491..a82657a64dd4 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@@ -170,6 -170,7 +170,7 @@@ enum bpf_prog_type BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + BPF_PROG_TYPE_CGROUP_SOCKOPT, };

enum bpf_attach_type { @@@ -194,6 -195,8 +195,8 @@@ BPF_CGROUP_SYSCTL, BPF_CGROUP_UDP4_RECVMSG, BPF_CGROUP_UDP6_RECVMSG, + BPF_CGROUP_GETSOCKOPT, + BPF_CGROUP_SETSOCKOPT, __MAX_BPF_ATTACH_TYPE };

@@@ -262,6 -265,24 +265,24 @@@ */ #define BPF_F_ANY_ALIGNMENT (1U << 1)

+ /* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose. + * Verifier does sub-register def/use analysis and identifies instructions whose + * def only matters for low 32-bit, high 32-bit is never referenced later + * through implicit zero extension. Therefore verifier notifies JIT back-ends + * that it is safe to ignore clearing high 32-bit for these instructions. This + * saves some back-ends a lot of code-gen. However such optimization is not + * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends + * hence hasn't used verifier's analysis result. But, we really want to have a + * way to be able to verify the correctness of the described optimization on + * x86_64 on which testsuites are frequently exercised. + * + * So, this flag is introduced. Once it is set, verifier will randomize high + * 32-bit for those instructions who has been identified as safe to ignore them. + * Then, if verifier is not doing correct analysis, such randomization will + * regress tests to expose bugs. + */ + #define BPF_F_TEST_RND_HI32 (1U << 2) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * two extensions: * @@@ -1550,8 -1571,11 +1571,11 @@@ union bpf_attr * but this is only implemented for native XDP (with driver * support) as of this writing). * - * All values for *flags* are reserved for future usage, and must - * be left at zero. + * The lower two bits of *flags* are used as the return code if + * the map lookup fails. This is so that the return value can be + * one of the XDP program return codes up to XDP_TX, as chosen by + * the caller. Any higher bits in the *flags* argument must be + * unset. * * When used to redirect packets to net devices, this helper * provides a high performance increase over **bpf_redirect**\ (). @@@ -1746,6 -1770,7 +1770,7 @@@ * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT) * * Therefore, this function can be used to clear a callback flag by * setting the appropriate bit to zero. e.g. to disable the RTO @@@ -2674,6 -2699,20 +2699,20 @@@ * 0 on success. * * **-ENOENT** if the bpf-local-storage cannot be found. + * + * int bpf_send_signal(u32 sig) + * Description + * Send signal *sig* to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@@ -2784,7 -2823,8 +2823,8 @@@ FN(strtol), \ FN(strtoul), \ FN(sk_storage_get), \ - FN(sk_storage_delete), + FN(sk_storage_delete), \ + FN(send_signal),

/* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@@ -3033,6 -3073,12 +3073,12 @@@ struct bpf_tcp_sock * sum(delta(snd_una)), or how many bytes * were acked. */ + __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups + * total number of DSACK blocks received + */ + __u32 delivered; /* Total data packets delivered incl. rexmits */ + __u32 delivered_ce; /* Like the above but only ECE marked packets */ + __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */ };

struct bpf_sock_tuple { @@@ -3052,6 -3098,10 +3098,10 @@@ }; };

+ struct bpf_xdp_sock { + __u32 queue_id; + }; + #define XDP_PACKET_HEADROOM 256

/* User return codes for XDP prog type. @@@ -3143,7 -3193,6 +3193,7 @@@ struct bpf_prog_info char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; __u32 gpl_compatible:1; + __u32 :31; /* alignment pad */ __u64 netns_dev; __u64 netns_ino; __u32 nr_jited_ksyms; @@@ -3213,6 -3262,7 +3263,7 @@@ struct bpf_sock_addr __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. * Stored in network byte order. */ + __bpf_md_ptr(struct bpf_sock *, sk); };

/* User bpf_sock_ops struct to access socket values and specify request ops @@@ -3264,13 -3314,15 +3315,15 @@@ struct bpf_sock_ops __u32 sk_txhash; __u64 bytes_received; __u64 bytes_acked; + __bpf_md_ptr(struct bpf_sock *, sk); };

/* Definitions for bpf_sock_ops_cb_flags */ #define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) #define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) #define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) - #define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently + #define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3) + #define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently * supported cb flags */

@@@ -3325,6 -3377,8 +3378,8 @@@ enum BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after * socket transition to LISTEN state. */ + BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + */ };

/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@@ -3503,4 -3557,15 +3558,15 @@@ struct bpf_sysctl */ };

+ struct bpf_sockopt { + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(void *, optval); + __bpf_md_ptr(void *, optval_end); + + __s32 level; + __s32 optname; + __s32 optlen; + __s32 retval; + }; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --combined include/uapi/linux/nl80211.h index fa7ebbc6ff27,8fc3a43cac75..75758ec26c8b --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@@ -235,6 -235,15 +235,15 @@@ */

/** + * DOC: SAE authentication offload + * + * By setting @NL80211_EXT_FEATURE_SAE_OFFLOAD flag drivers can indicate they + * support offloading SAE authentication for WPA3-Personal networks. In + * %NL80211_CMD_CONNECT the password for SAE should be specified using + * %NL80211_ATTR_SAE_PASSWORD. + */ + + /** * enum nl80211_commands - supported nl80211 commands * * @NL80211_CMD_UNSPEC: unspecified command to catch errors @@@ -2341,6 -2350,12 +2350,12 @@@ enum nl80211_commands * should be picking up the lowest tx power, either tx power per-interface * or per-station. * + * @NL80211_ATTR_SAE_PASSWORD: attribute for passing SAE password material. It + * is used with %NL80211_CMD_CONNECT to provide password for offloading + * SAE authentication for WPA3-Personal networks. + * + * @NL80211_ATTR_TWT_RESPONDER: Enable target wait time responder support. + * * @NUM_NL80211_ATTR: total number of nl80211_attrs available * @NL80211_ATTR_MAX: highest attribute number currently defined * @__NL80211_ATTR_AFTER_LAST: internal use @@@ -2794,6 -2809,10 +2809,10 @@@ enum nl80211_attrs NL80211_ATTR_STA_TX_POWER_SETTING, NL80211_ATTR_STA_TX_POWER,

+ NL80211_ATTR_SAE_PASSWORD, + + NL80211_ATTR_TWT_RESPONDER, + /* add attributes here, update the policy in nl80211.c */

__NL80211_ATTR_AFTER_LAST, @@@ -4406,6 -4425,7 +4425,7 @@@ enum nl80211_mfp enum nl80211_wpa_versions { NL80211_WPA_VERSION_1 = 1 << 0, NL80211_WPA_VERSION_2 = 1 << 1, + NL80211_WPA_VERSION_3 = 1 << 2, };

/** @@@ -5314,7 -5334,7 +5334,7 @@@ enum nl80211_feature_flags NL80211_FEATURE_TDLS_CHANNEL_SWITCH = 1 << 28, NL80211_FEATURE_SCAN_RANDOM_MAC_ADDR = 1 << 29, NL80211_FEATURE_SCHED_SCAN_RANDOM_MAC_ADDR = 1 << 30, - NL80211_FEATURE_ND_RANDOM_MAC_ADDR = 1 << 31, + NL80211_FEATURE_ND_RANDOM_MAC_ADDR = 1U << 31, };

/** @@@ -5422,6 -5442,9 +5442,9 @@@ * @NL80211_EXT_FEATURE_STA_TX_PWR: This driver supports controlling tx power * to a station. * + * @NL80211_EXT_FEATURE_SAE_OFFLOAD: Device wants to do SAE authentication in + * station mode (SAE password is passed as part of the connect command). + * * @NUM_NL80211_EXT_FEATURES: number of extended features. * @MAX_NL80211_EXT_FEATURES: highest extended feature index. */ @@@ -5466,6 -5489,7 +5489,7 @@@ enum nl80211_ext_feature_index NL80211_EXT_FEATURE_SCHED_SCAN_BAND_SPECIFIC_RSSI_THOLD, NL80211_EXT_FEATURE_EXT_KEY_ID, NL80211_EXT_FEATURE_STA_TX_PWR, + NL80211_EXT_FEATURE_SAE_OFFLOAD,

/* add new features before the definition below */ NUM_NL80211_EXT_FEATURES, diff --combined kernel/bpf/core.c index f2148db91439,e2c1b43728da..16079550db6d --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@@ -1364,10 -1364,10 +1364,10 @@@ select_insn insn++; CONT; ALU_ARSH_X: - DST = (u64) (u32) ((*(s32 *) &DST) >> SRC); + DST = (u64) (u32) (((s32) DST) >> SRC); CONT; ALU_ARSH_K: - DST = (u64) (u32) ((*(s32 *) &DST) >> IMM); + DST = (u64) (u32) (((s32) DST) >> IMM); CONT; ALU64_ARSH_X: (*(s64 *) &DST) >>= SRC; @@@ -1791,38 -1791,42 +1791,42 @@@ struct bpf_prog_array *bpf_prog_array_a return &empty_prog_array.hdr; }

- void bpf_prog_array_free(struct bpf_prog_array __rcu *progs) + void bpf_prog_array_free(struct bpf_prog_array *progs) { - if (!progs || - progs == (struct bpf_prog_array __rcu *)&empty_prog_array.hdr) + if (!progs || progs == &empty_prog_array.hdr) return; kfree_rcu(progs, rcu); }

- int bpf_prog_array_length(struct bpf_prog_array __rcu *array) + int bpf_prog_array_length(struct bpf_prog_array *array) { struct bpf_prog_array_item *item; u32 cnt = 0;

- rcu_read_lock(); - item = rcu_dereference(array)->items; - for (; item->prog; item++) + for (item = array->items; item->prog; item++) if (item->prog != &dummy_bpf_prog.prog) cnt++; - rcu_read_unlock(); return cnt; }

+ bool bpf_prog_array_is_empty(struct bpf_prog_array *array) + { + struct bpf_prog_array_item *item; + + for (item = array->items; item->prog; item++) + if (item->prog != &dummy_bpf_prog.prog) + return false; + return true; + }

- static bool bpf_prog_array_copy_core(struct bpf_prog_array __rcu *array, + static bool bpf_prog_array_copy_core(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt) { struct bpf_prog_array_item *item; int i = 0;

- item = rcu_dereference_check(array, 1)->items; - for (; item->prog; item++) { + for (item = array->items; item->prog; item++) { if (item->prog == &dummy_bpf_prog.prog) continue; prog_ids[i] = item->prog->aux->id; @@@ -1835,7 -1839,7 +1839,7 @@@ return !!(item->prog); }

- int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *array, + int bpf_prog_array_copy_to_user(struct bpf_prog_array *array, __u32 __user *prog_ids, u32 cnt) { unsigned long err = 0; @@@ -1846,18 -1850,12 +1850,12 @@@ * cnt = bpf_prog_array_length(); * if (cnt > 0) * bpf_prog_array_copy_to_user(..., cnt); - * so below kcalloc doesn't need extra cnt > 0 check, but - * bpf_prog_array_length() releases rcu lock and - * prog array could have been swapped with empty or larger array, - * so always copy 'cnt' prog_ids to the user. - * In a rare race the user will see zero prog_ids + * so below kcalloc doesn't need extra cnt > 0 check. */ ids = kcalloc(cnt, sizeof(u32), GFP_USER | __GFP_NOWARN); if (!ids) return -ENOMEM; - rcu_read_lock(); nospc = bpf_prog_array_copy_core(array, ids, cnt); - rcu_read_unlock(); err = copy_to_user(prog_ids, ids, cnt * sizeof(u32)); kfree(ids); if (err) @@@ -1867,19 -1865,19 +1865,19 @@@ return 0; }

- void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *array, + void bpf_prog_array_delete_safe(struct bpf_prog_array *array, struct bpf_prog *old_prog) { - struct bpf_prog_array_item *item = array->items; + struct bpf_prog_array_item *item;

- for (; item->prog; item++) + for (item = array->items; item->prog; item++) if (item->prog == old_prog) { WRITE_ONCE(item->prog, &dummy_bpf_prog.prog); break; } }

- int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, + int bpf_prog_array_copy(struct bpf_prog_array *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, struct bpf_prog_array **new_array) @@@ -1943,7 -1941,7 +1941,7 @@@ return 0; }

- int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, + int bpf_prog_array_copy_info(struct bpf_prog_array *array, u32 *prog_ids, u32 request_cnt, u32 *prog_cnt) { @@@ -2086,6 -2084,15 +2084,15 @@@ bool __weak bpf_helper_changes_pkt_data return false; }

+ /* Return TRUE if the JIT backend wants verifier to enable sub-register usage + * analysis code and wants explicit zero extension inserted by verifier. + * Otherwise, return FALSE. + */ + bool __weak bpf_jit_needs_zext(void) + { + return false; + } + /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ @@@ -2103,3 -2110,4 +2110,4 @@@ EXPORT_SYMBOL(bpf_stats_enabled_key) #include <linux/bpf_trace.h>

EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); + EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx); diff --combined kernel/cgroup/cgroup.c index 2a42a52ea75f,daa567728251..b8042569a119 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@@ -2201,7 -2201,8 +2201,7 @@@ static int cgroup_init_fs_context(struc fc->ops = &cgroup_fs_context_ops; else fc->ops = &cgroup1_fs_context_ops; - if (fc->user_ns) - put_user_ns(fc->user_ns); + put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(ctx->ns->user_ns); fc->global = true; return 0; @@@ -2242,50 -2243,6 +2242,50 @@@ static struct file_system_type cgroup2_ .fs_flags = FS_USERNS_MOUNT, };

+#ifdef CONFIG_CPUSETS +static const struct fs_context_operations cpuset_fs_context_ops = { + .get_tree = cgroup1_get_tree, + .free = cgroup_fs_context_free, +}; + +/* + * This is ugly, but preserves the userspace API for existing cpuset + * users. If someone tries to mount the "cpuset" filesystem, we + * silently switch it to mount "cgroup" instead + */ +static int cpuset_init_fs_context(struct fs_context *fc) +{ + char *agent = kstrdup("/sbin/cpuset_release_agent", GFP_USER); + struct cgroup_fs_context *ctx; + int err; + + err = cgroup_init_fs_context(fc); + if (err) { + kfree(agent); + return err; + } + + fc->ops = &cpuset_fs_context_ops; + + ctx = cgroup_fc2context(fc); + ctx->subsys_mask = 1 << cpuset_cgrp_id; + ctx->flags |= CGRP_ROOT_NOPREFIX; + ctx->release_agent = agent; + + get_filesystem(&cgroup_fs_type); + put_filesystem(fc->fs_type); + fc->fs_type = &cgroup_fs_type; + + return 0; +} + +static struct file_system_type cpuset_fs_type = { + .name = "cpuset", + .init_fs_context = cpuset_init_fs_context, + .fs_flags = FS_USERNS_MOUNT, +}; +#endif + int cgroup_path_ns_locked(struct cgroup *cgrp, char *buf, size_t buflen, struct cgroup_namespace *ns) { @@@ -5048,8 -5005,6 +5048,6 @@@ static void css_release_work_fn(struct if (cgrp->kn) RCU_INIT_POINTER(*(void __rcu __force **)&cgrp->kn->priv, NULL); - - cgroup_bpf_put(cgrp); }

mutex_unlock(&cgroup_mutex); @@@ -5575,6 -5530,8 +5573,8 @@@ static int cgroup_destroy_locked(struc

cgroup1_check_for_release(parent);

+ cgroup_bpf_offline(cgrp); + /* put the base reference */ percpu_ref_kill(&cgrp->self.refcnt);

@@@ -5804,9 -5761,6 +5804,9 @@@ int __init cgroup_init(void WARN_ON(register_filesystem(&cgroup_fs_type)); WARN_ON(register_filesystem(&cgroup2_fs_type)); WARN_ON(!proc_create_single("cgroups", 0, NULL, proc_cgroupstats_show)); +#ifdef CONFIG_CPUSETS + WARN_ON(register_filesystem(&cpuset_fs_type)); +#endif

return 0; } @@@ -6325,6 -6279,7 +6325,7 @@@ void cgroup_sk_alloc(struct sock_cgroup * Don't use cgroup_get_live(). */ cgroup_get(sock_cgroup_ptr(skcd)); + cgroup_bpf_get(sock_cgroup_ptr(skcd)); return; }

@@@ -6336,6 -6291,7 +6337,7 @@@ cset = task_css_set(current); if (likely(cgroup_tryget(cset->dfl_cgrp))) { skcd->val = (unsigned long)cset->dfl_cgrp; + cgroup_bpf_get(cset->dfl_cgrp); break; } cpu_relax(); @@@ -6346,7 -6302,10 +6348,10 @@@

void cgroup_sk_free(struct sock_cgroup_data *skcd) { - cgroup_put(sock_cgroup_ptr(skcd)); + struct cgroup *cgrp = sock_cgroup_ptr(skcd); + + cgroup_bpf_put(cgrp); + cgroup_put(cgrp); }

#endif /* CONFIG_SOCK_CGROUP_DATA */ diff --combined lib/Kconfig index e09b3e081a53,78ddb9526b62..f8d4088551d7 --- a/lib/Kconfig +++ b/lib/Kconfig @@@ -531,6 -531,14 +531,6 @@@ config LRU_CACH config CLZ_TAB bool

-config DDR - bool "JEDEC DDR data" - help - Data from JEDEC specs for DDR SDRAM memories, - particularly the AC timing parameters and addressing - information. This data is useful for drivers handling - DDR SDRAM controllers. - config IRQ_POLL bool "IRQ polling library" help @@@ -554,6 -562,14 +554,14 @@@ config SIGNATUR Digital signature verification. Currently only RSA is supported. Implementation is done using GnuPG MPI library

+ config DIMLIB + bool "DIM library" + default y + help + Dynamic Interrupt Moderation library. + Implements an algorithm for dynamically change CQ modertion values + according to run time performance. + # # libfdt files, only selected if needed. # diff --combined lib/Kconfig.debug index be9787484fb4,99272b5dd980..4542bac32a88 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@@ -305,26 -305,19 +305,26 @@@ config DEBUG_F

If unsure, say N.

-config HEADERS_CHECK - bool "Run 'make headers_check' when building vmlinux" +config HEADERS_INSTALL + bool "Install uapi headers to usr/include" depends on !UML help - This option will extract the user-visible kernel headers whenever - building the kernel, and will run basic sanity checks on them to - ensure that exported files do not attempt to include files which - were not exported, etc. + This option will install uapi headers (headers exported to user-space) + into the usr/include directory for use during the kernel build. + This is unneeded for building the kernel itself, but needed for some + user-space program samples. It is also needed by some features such + as uapi header sanity checks. + +config HEADERS_CHECK + bool "Run sanity checks on uapi headers when building 'all'" + depends on HEADERS_INSTALL + help + This option will run basic sanity checks on uapi headers when + building the 'all' target, for example, ensure that they do not + attempt to include files which were not exported, etc.

If you're making modifications to header files which are - relevant for userspace, say 'Y', and check the headers - exported to $(INSTALL_HDR_PATH) (usually 'usr/include' in - your build tree), to make sure they're suitable. + relevant for userspace, say 'Y'.

config OPTIMIZE_INLINING bool "Allow compiler to uninline functions marked 'inline'" @@@ -1708,7 -1701,7 +1708,7 @@@ config LKDT called lkdtm.

Documentation on how to use the module can be found in - Documentation/fault-injection/provoke-crashes.txt + Documentation/fault-injection/provoke-crashes.rst

config TEST_LIST_SORT tristate "Linked list sorting test" @@@ -1916,6 -1909,15 +1916,15 @@@ config TEST_BP

If unsure, say N.

+ config TEST_BLACKHOLE_DEV + tristate "Test blackhole netdev functionality" + depends on m && NET + help + This builds the "test_blackhole_dev" module that validates the + data path through this blackhole netdev. + + If unsure, say N. + config FIND_BIT_BENCHMARK tristate "Test find_bit functions" help diff --combined lib/Makefile index cb66bc9c5b2f,6ac44fe2a37f..86c39ec0d874 --- a/lib/Makefile +++ b/lib/Makefile @@@ -91,6 -91,7 +91,7 @@@ obj-$(CONFIG_TEST_DEBUG_VIRTUAL) += tes obj-$(CONFIG_TEST_MEMCAT_P) += test_memcat_p.o obj-$(CONFIG_TEST_OBJAGG) += test_objagg.o obj-$(CONFIG_TEST_STACKINIT) += test_stackinit.o + obj-$(CONFIG_TEST_BLACKHOLE_DEV) += test_blackhole_dev.o

obj-$(CONFIG_TEST_LIVEPATCH) += livepatch/

@@@ -202,10 -203,13 +203,11 @@@ obj-$(CONFIG_GLOB) += glob. obj-$(CONFIG_GLOB_SELFTEST) += globtest.o

obj-$(CONFIG_MPILIB) += mpi/ + obj-$(CONFIG_DIMLIB) += dim/ obj-$(CONFIG_SIGNATURE) += digsig.o

lib-$(CONFIG_CLZ_TAB) += clz_tab.o

-obj-$(CONFIG_DDR) += jedec_ddr_data.o - obj-$(CONFIG_GENERIC_STRNCPY_FROM_USER) += strncpy_from_user.o obj-$(CONFIG_GENERIC_STRNLEN_USER) += strnlen_user.o

diff --combined net/batman-adv/hard-interface.c index 3719cfd026f0,b5465e6e380d..c90e47342bb0 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@@ -16,6 -16,7 +16,7 @@@ #include <linux/if_ether.h> #include <linux/kernel.h> #include <linux/kref.h> + #include <linux/limits.h> #include <linux/list.h> #include <linux/netdevice.h> #include <linux/printk.h> @@@ -795,9 -796,6 +796,9 @@@ int batadv_hardif_enable_interface(stru

batadv_hardif_recalc_extra_skbroom(soft_iface);

+ if (bat_priv->algo_ops->iface.enabled) + bat_priv->algo_ops->iface.enabled(hard_iface); + out: return 0;

@@@ -923,9 -921,7 +924,7 @@@ batadv_hardif_add_interface(struct net_ hard_iface->soft_iface = NULL; hard_iface->if_status = BATADV_IF_NOT_IN_USE;

- ret = batadv_debugfs_add_hardif(hard_iface); - if (ret) - goto free_sysfs; + batadv_debugfs_add_hardif(hard_iface);

INIT_LIST_HEAD(&hard_iface->list); INIT_HLIST_HEAD(&hard_iface->neigh_list); @@@ -947,8 -943,6 +946,6 @@@

return hard_iface;

- free_sysfs: - batadv_sysfs_del_hardif(&hard_iface->hardif_obj); free_if: kfree(hard_iface); release_dev: diff --combined net/batman-adv/types.h index e0b25104cbfa,c2996296b953..6ae139d74e0f --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@@ -14,20 -14,22 +14,22 @@@ #include <linux/average.h> #include <linux/bitops.h> #include <linux/compiler.h> + #include <linux/if.h> #include <linux/if_ether.h> #include <linux/kref.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/sched.h> /* for linux/wait.h */ + #include <linux/seq_file.h> + #include <linux/skbuff.h> #include <linux/spinlock.h> + #include <linux/timer.h> #include <linux/types.h> #include <linux/wait.h> #include <linux/workqueue.h> #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h>

- struct seq_file; - #ifdef CONFIG_BATMAN_ADV_DAT

/** @@@ -402,6 -404,17 +404,17 @@@ struct batadv_orig_node * list */ struct hlist_node mcast_want_all_ipv6_node; + + /** + * @mcast_want_all_rtr4_node: a list node for the mcast.want_all_rtr4 + * list + */ + struct hlist_node mcast_want_all_rtr4_node; + /** + * @mcast_want_all_rtr6_node: a list node for the mcast.want_all_rtr6 + * list + */ + struct hlist_node mcast_want_all_rtr6_node; #endif

/** @capabilities: announced capabilities of this originator */ @@@ -1169,6 -1182,26 +1182,26 @@@ struct batadv_mcast_querier_state };

/** + * struct batadv_mcast_mla_flags - flags for the querier, bridge and tvlv state + */ + struct batadv_mcast_mla_flags { + /** @querier_ipv4: the current state of an IGMP querier in the mesh */ + struct batadv_mcast_querier_state querier_ipv4; + + /** @querier_ipv6: the current state of an MLD querier in the mesh */ + struct batadv_mcast_querier_state querier_ipv6; + + /** @enabled: whether the multicast tvlv is currently enabled */ + unsigned char enabled:1; + + /** @bridged: whether the soft interface has a bridge on top */ + unsigned char bridged:1; + + /** @tvlv_flags: the flags we have last sent in our mcast tvlv */ + u8 tvlv_flags; + }; + + /** * struct batadv_priv_mcast - per mesh interface mcast data */ struct batadv_priv_mcast { @@@ -1196,20 -1229,22 +1229,22 @@@ */ struct hlist_head want_all_ipv6_list;

- /** @querier_ipv4: the current state of an IGMP querier in the mesh */ - struct batadv_mcast_querier_state querier_ipv4; - - /** @querier_ipv6: the current state of an MLD querier in the mesh */ - struct batadv_mcast_querier_state querier_ipv6; - - /** @flags: the flags we have last sent in our mcast tvlv */ - u8 flags; + /** + * @want_all_rtr4_list: a list of orig_nodes wanting all routable IPv4 + * multicast traffic + */ + struct hlist_head want_all_rtr4_list;

- /** @enabled: whether the multicast tvlv is currently enabled */ - unsigned char enabled:1; + /** + * @want_all_rtr6_list: a list of orig_nodes wanting all routable IPv6 + * multicast traffic + */ + struct hlist_head want_all_rtr6_list;

- /** @bridged: whether the soft interface has a bridge on top */ - unsigned char bridged:1; + /** + * @mla_flags: flags for the querier, bridge and tvlv state + */ + struct batadv_mcast_mla_flags mla_flags;

/** * @mla_lock: a lock protecting mla_list and mla_flags @@@ -1228,6 -1263,12 +1263,12 @@@ /** @num_want_all_ipv6: counter for items in want_all_ipv6_list */ atomic_t num_want_all_ipv6;

+ /** @num_want_all_rtr4: counter for items in want_all_rtr4_list */ + atomic_t num_want_all_rtr4; + + /** @num_want_all_rtr6: counter for items in want_all_rtr6_list */ + atomic_t num_want_all_rtr6; + /** * @want_lists_lock: lock for protecting modifications to mcasts * want_all_{unsnoopables,ipv4,ipv6}_list (traversals are rcu-locked) @@@ -2129,9 -2170,6 +2170,9 @@@ struct batadv_algo_iface_ops /** @enable: init routing info when hard-interface is enabled */ int (*enable)(struct batadv_hard_iface *hard_iface);

+ /** @enabled: notification when hard-interface was enabled (optional) */ + void (*enabled)(struct batadv_hard_iface *hard_iface); + /** @disable: de-init routing info when hard-interface is disabled */ void (*disable)(struct batadv_hard_iface *hard_iface);

diff --combined net/bluetooth/l2cap_core.c index 5406d7cd46ad,007317b072b4..cc506fe99b4d --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@@ -168,11 -168,18 +168,18 @@@ static struct l2cap_chan *l2cap_get_cha return c; }

- static struct l2cap_chan *__l2cap_global_chan_by_addr(__le16 psm, bdaddr_t *src) + static struct l2cap_chan *__l2cap_global_chan_by_addr(__le16 psm, bdaddr_t *src, + u8 src_type) { struct l2cap_chan *c;

list_for_each_entry(c, &chan_list, global_l) { + if (src_type == BDADDR_BREDR && c->src_type != BDADDR_BREDR) + continue; + + if (src_type != BDADDR_BREDR && c->src_type == BDADDR_BREDR) + continue; + if (c->sport == psm && !bacmp(&c->src, src)) return c; } @@@ -185,7 -192,7 +192,7 @@@ int l2cap_add_psm(struct l2cap_chan *ch

write_lock(&chan_list_lock);

- if (psm && __l2cap_global_chan_by_addr(psm, src)) { + if (psm && __l2cap_global_chan_by_addr(psm, src, chan->src_type)) { err = -EADDRINUSE; goto done; } @@@ -209,7 -216,8 +216,8 @@@

err = -EINVAL; for (p = start; p <= end; p += incr) - if (!__l2cap_global_chan_by_addr(cpu_to_le16(p), src)) { + if (!__l2cap_global_chan_by_addr(cpu_to_le16(p), src, + chan->src_type)) { chan->psm = cpu_to_le16(p); chan->sport = cpu_to_le16(p); err = 0; @@@ -1353,7 -1361,7 +1361,7 @@@ static bool l2cap_check_enc_key_size(st * actually encrypted before enforcing a key size. */ return (!test_bit(HCI_CONN_ENCRYPT, &hcon->flags) || - hcon->enc_key_size > HCI_MIN_ENC_KEY_SIZE); + hcon->enc_key_size >= HCI_MIN_ENC_KEY_SIZE); }

static void l2cap_do_start(struct l2cap_chan *chan) @@@ -4394,6 -4402,12 +4402,12 @@@ static inline int l2cap_disconnect_rsp(

l2cap_chan_lock(chan);

+ if (chan->state != BT_DISCONN) { + l2cap_chan_unlock(chan); + mutex_unlock(&conn->chan_lock); + return 0; + } + l2cap_chan_hold(chan); l2cap_chan_del(chan, 0);

@@@ -5291,7 -5305,14 +5305,14 @@@ static inline int l2cap_conn_param_upda

memset(&rsp, 0, sizeof(rsp));

- err = hci_check_conn_params(min, max, latency, to_multiplier); + if (min < hcon->le_conn_min_interval || + max > hcon->le_conn_max_interval) { + BT_DBG("requested connection interval exceeds current bounds."); + err = -EINVAL; + } else { + err = hci_check_conn_params(min, max, latency, to_multiplier); + } + if (err) rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); else diff --combined net/bridge/netfilter/Kconfig index 36a98d36d339,f4fb0b9b927d..d978f6d820f3 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@@ -19,6 -19,20 +19,20 @@@ config NF_LOG_BRIDG tristate "Bridge packet logging" select NF_LOG_COMMON

+ config NF_CONNTRACK_BRIDGE + tristate "IPv4/IPV6 bridge connection tracking support" + depends on NF_CONNTRACK + default n + help + Connection tracking keeps a record of what packets have passed + through your machine, in order to figure out how they are related + into connections. This is used to enhance packet filtering via + stateful policies. Enable this if you want native tracking from + the bridge. This provides a replacement for the `br_netfilter' + infrastructure. + + To compile it as a module, choose M here. If unsure, say N. + endif # NF_TABLES_BRIDGE

menuconfig BRIDGE_NF_EBTABLES @@@ -114,7 -128,7 +128,7 @@@ config BRIDGE_EBT_LIMI equivalent of the iptables limit match.

If you want to compile it as a module, say M here and read - file:Documentation/kbuild/modules.txt. If unsure, say `N'. + file:Documentation/kbuild/modules.rst. If unsure, say `N'.

config BRIDGE_EBT_MARK tristate "ebt: mark filter support" diff --combined net/core/filter.c index 3fdf1b21be36,089aaea0ccc6..b106f677fd55 --- a/net/core/filter.c +++ b/net/core/filter.c @@@ -62,6 -62,7 +62,7 @@@ #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/ip_fib.h> + #include <net/nexthop.h> #include <net/flow.h> #include <net/arp.h> #include <net/ipv6.h> @@@ -2157,8 -2158,8 +2158,8 @@@ BPF_CALL_2(bpf_redirect, u32, ifindex, if (unlikely(flags & ~(BPF_F_INGRESS))) return TC_ACT_SHOT;

- ri->ifindex = ifindex; ri->flags = flags; + ri->tgt_index = ifindex;

return TC_ACT_REDIRECT; } @@@ -2168,8 -2169,8 +2169,8 @@@ int skb_do_redirect(struct sk_buff *skb struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct net_device *dev;

- dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->ifindex); - ri->ifindex = 0; + dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index); + ri->tgt_index = 0; if (unlikely(!dev)) { kfree_skb(skb); return -EINVAL; @@@ -3487,11 -3488,11 +3488,11 @@@ xdp_do_redirect_slow(struct net_device struct bpf_prog *xdp_prog, struct bpf_redirect_info *ri) { struct net_device *fwd; - u32 index = ri->ifindex; + u32 index = ri->tgt_index; int err;

fwd = dev_get_by_index_rcu(dev_net(dev), index); - ri->ifindex = 0; + ri->tgt_index = 0; if (unlikely(!fwd)) { err = -EINVAL; goto err; @@@ -3522,7 -3523,6 +3523,6 @@@ static int __bpf_tx_xdp_map(struct net_ err = dev_map_enqueue(dst, xdp, dev_rx); if (unlikely(err)) return err; - __dev_map_insert_ctx(map, index); break; } case BPF_MAP_TYPE_CPUMAP: { @@@ -3531,7 -3531,6 +3531,6 @@@ err = cpu_map_enqueue(rcpu, xdp, dev_rx); if (unlikely(err)) return err; - __cpu_map_insert_ctx(map, index); break; } case BPF_MAP_TYPE_XSKMAP: { @@@ -3605,18 -3604,14 +3604,14 @@@ static int xdp_do_redirect_map(struct n struct bpf_prog *xdp_prog, struct bpf_map *map, struct bpf_redirect_info *ri) { - u32 index = ri->ifindex; - void *fwd = NULL; + u32 index = ri->tgt_index; + void *fwd = ri->tgt_value; int err;

- ri->ifindex = 0; + ri->tgt_index = 0; + ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL);

- fwd = __xdp_map_lookup_elem(map, index); - if (unlikely(!fwd)) { - err = -EINVAL; - goto err; - } if (ri->map_to_flush && unlikely(ri->map_to_flush != map)) xdp_do_flush_map();

@@@ -3652,19 -3647,14 +3647,14 @@@ static int xdp_do_generic_redirect_map( struct bpf_map *map) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - u32 index = ri->ifindex; - void *fwd = NULL; + u32 index = ri->tgt_index; + void *fwd = ri->tgt_value; int err = 0;

- ri->ifindex = 0; + ri->tgt_index = 0; + ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL);

- fwd = __xdp_map_lookup_elem(map, index); - if (unlikely(!fwd)) { - err = -EINVAL; - goto err; - } - if (map->map_type == BPF_MAP_TYPE_DEVMAP) { struct bpf_dtab_netdev *dst = fwd;

@@@ -3696,14 -3686,14 +3686,14 @@@ int xdp_do_generic_redirect(struct net_ { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); struct bpf_map *map = READ_ONCE(ri->map); - u32 index = ri->ifindex; + u32 index = ri->tgt_index; struct net_device *fwd; int err = 0;

if (map) return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog, map); - ri->ifindex = 0; + ri->tgt_index = 0; fwd = dev_get_by_index_rcu(dev_net(dev), index); if (unlikely(!fwd)) { err = -EINVAL; @@@ -3731,8 -3721,9 +3721,9 @@@ BPF_CALL_2(bpf_xdp_redirect, u32, ifind if (unlikely(flags)) return XDP_ABORTED;

- ri->ifindex = ifindex; ri->flags = flags; + ri->tgt_index = ifindex; + ri->tgt_value = NULL; WRITE_ONCE(ri->map, NULL);

return XDP_REDIRECT; @@@ -3751,11 -3742,23 +3742,23 @@@ BPF_CALL_3(bpf_xdp_redirect_map, struc { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);

- if (unlikely(flags)) + /* Lower bits of the flags are used as return code on lookup failure */ + if (unlikely(flags > XDP_TX)) return XDP_ABORTED;

- ri->ifindex = ifindex; + ri->tgt_value = __xdp_map_lookup_elem(map, ifindex); + if (unlikely(!ri->tgt_value)) { + /* If the lookup fails we want to clear out the state in the + * redirect_info struct completely, so that if an eBPF program + * performs multiple lookups, the last one always takes + * precedence. + */ + WRITE_ONCE(ri->map, NULL); + return flags; + } + ri->flags = flags; + ri->tgt_index = ifindex; WRITE_ONCE(ri->map, map);

return XDP_REDIRECT; @@@ -4670,7 -4673,7 +4673,7 @@@ static int bpf_ipv4_fib_lookup(struct n if (res.type != RTN_UNICAST) return BPF_FIB_LKUP_RET_NOT_FWDED;

- if (res.fi->fib_nhs > 1) + if (fib_info_num_path(res.fi) > 1) fib_select_path(net, &res, &fl4, NULL);

if (check_mtu) { @@@ -4737,7 -4740,7 +4740,7 @@@ static int bpf_ipv6_fib_lookup(struct n return -ENODEV;

idev = __in6_dev_get_safely(dev); - if (unlikely(!idev || !net->ipv6.devconf_all->forwarding)) + if (unlikely(!idev || !idev->cnf.forwarding)) return BPF_FIB_LKUP_RET_FWD_DISABLED;

if (flags & BPF_FIB_LOOKUP_OUTPUT) { @@@ -5191,54 -5194,6 +5194,6 @@@ static const struct bpf_func_proto bpf_ }; #endif /* CONFIG_IPV6_SEG6_BPF */

- #define CONVERT_COMMON_TCP_SOCK_FIELDS(md_type, CONVERT) \ - do { \ - switch (si->off) { \ - case offsetof(md_type, snd_cwnd): \ - CONVERT(snd_cwnd); break; \ - case offsetof(md_type, srtt_us): \ - CONVERT(srtt_us); break; \ - case offsetof(md_type, snd_ssthresh): \ - CONVERT(snd_ssthresh); break; \ - case offsetof(md_type, rcv_nxt): \ - CONVERT(rcv_nxt); break; \ - case offsetof(md_type, snd_nxt): \ - CONVERT(snd_nxt); break; \ - case offsetof(md_type, snd_una): \ - CONVERT(snd_una); break; \ - case offsetof(md_type, mss_cache): \ - CONVERT(mss_cache); break; \ - case offsetof(md_type, ecn_flags): \ - CONVERT(ecn_flags); break; \ - case offsetof(md_type, rate_delivered): \ - CONVERT(rate_delivered); break; \ - case offsetof(md_type, rate_interval_us): \ - CONVERT(rate_interval_us); break; \ - case offsetof(md_type, packets_out): \ - CONVERT(packets_out); break; \ - case offsetof(md_type, retrans_out): \ - CONVERT(retrans_out); break; \ - case offsetof(md_type, total_retrans): \ - CONVERT(total_retrans); break; \ - case offsetof(md_type, segs_in): \ - CONVERT(segs_in); break; \ - case offsetof(md_type, data_segs_in): \ - CONVERT(data_segs_in); break; \ - case offsetof(md_type, segs_out): \ - CONVERT(segs_out); break; \ - case offsetof(md_type, data_segs_out): \ - CONVERT(data_segs_out); break; \ - case offsetof(md_type, lost_out): \ - CONVERT(lost_out); break; \ - case offsetof(md_type, sacked_out): \ - CONVERT(sacked_out); break; \ - case offsetof(md_type, bytes_received): \ - CONVERT(bytes_received); break; \ - case offsetof(md_type, bytes_acked): \ - CONVERT(bytes_acked); break; \ - } \ - } while (0) - #ifdef CONFIG_INET static struct sock *sk_lookup(struct net *net, struct bpf_sock_tuple *tuple, int dif, int sdif, u8 family, u8 proto) @@@ -5589,7 -5544,8 +5544,8 @@@ static const struct bpf_func_proto bpf_ bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type, struct bpf_insn_access_aux *info) { - if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, bytes_acked)) + if (off < 0 || off >= offsetofend(struct bpf_tcp_sock, + icsk_retransmits)) return false;

if (off % size != 0) @@@ -5620,8 -5576,19 +5576,19 @@@ u32 bpf_tcp_sock_convert_ctx_access(enu offsetof(struct tcp_sock, FIELD)); \ } while (0)

- CONVERT_COMMON_TCP_SOCK_FIELDS(struct bpf_tcp_sock, - BPF_TCP_SOCK_GET_COMMON); + #define BPF_INET_SOCK_GET_COMMON(FIELD) \ + do { \ + BUILD_BUG_ON(FIELD_SIZEOF(struct inet_connection_sock, \ + FIELD) > \ + FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ + struct inet_connection_sock, \ + FIELD), \ + si->dst_reg, si->src_reg, \ + offsetof( \ + struct inet_connection_sock, \ + FIELD)); \ + } while (0)

if (insn > insn_buf) return insn - insn_buf; @@@ -5637,6 -5604,81 +5604,81 @@@ offsetof(struct tcp_sock, rtt_min) + offsetof(struct minmax_sample, v)); break; + case offsetof(struct bpf_tcp_sock, snd_cwnd): + BPF_TCP_SOCK_GET_COMMON(snd_cwnd); + break; + case offsetof(struct bpf_tcp_sock, srtt_us): + BPF_TCP_SOCK_GET_COMMON(srtt_us); + break; + case offsetof(struct bpf_tcp_sock, snd_ssthresh): + BPF_TCP_SOCK_GET_COMMON(snd_ssthresh); + break; + case offsetof(struct bpf_tcp_sock, rcv_nxt): + BPF_TCP_SOCK_GET_COMMON(rcv_nxt); + break; + case offsetof(struct bpf_tcp_sock, snd_nxt): + BPF_TCP_SOCK_GET_COMMON(snd_nxt); + break; + case offsetof(struct bpf_tcp_sock, snd_una): + BPF_TCP_SOCK_GET_COMMON(snd_una); + break; + case offsetof(struct bpf_tcp_sock, mss_cache): + BPF_TCP_SOCK_GET_COMMON(mss_cache); + break; + case offsetof(struct bpf_tcp_sock, ecn_flags): + BPF_TCP_SOCK_GET_COMMON(ecn_flags); + break; + case offsetof(struct bpf_tcp_sock, rate_delivered): + BPF_TCP_SOCK_GET_COMMON(rate_delivered); + break; + case offsetof(struct bpf_tcp_sock, rate_interval_us): + BPF_TCP_SOCK_GET_COMMON(rate_interval_us); + break; + case offsetof(struct bpf_tcp_sock, packets_out): + BPF_TCP_SOCK_GET_COMMON(packets_out); + break; + case offsetof(struct bpf_tcp_sock, retrans_out): + BPF_TCP_SOCK_GET_COMMON(retrans_out); + break; + case offsetof(struct bpf_tcp_sock, total_retrans): + BPF_TCP_SOCK_GET_COMMON(total_retrans); + break; + case offsetof(struct bpf_tcp_sock, segs_in): + BPF_TCP_SOCK_GET_COMMON(segs_in); + break; + case offsetof(struct bpf_tcp_sock, data_segs_in): + BPF_TCP_SOCK_GET_COMMON(data_segs_in); + break; + case offsetof(struct bpf_tcp_sock, segs_out): + BPF_TCP_SOCK_GET_COMMON(segs_out); + break; + case offsetof(struct bpf_tcp_sock, data_segs_out): + BPF_TCP_SOCK_GET_COMMON(data_segs_out); + break; + case offsetof(struct bpf_tcp_sock, lost_out): + BPF_TCP_SOCK_GET_COMMON(lost_out); + break; + case offsetof(struct bpf_tcp_sock, sacked_out): + BPF_TCP_SOCK_GET_COMMON(sacked_out); + break; + case offsetof(struct bpf_tcp_sock, bytes_received): + BPF_TCP_SOCK_GET_COMMON(bytes_received); + break; + case offsetof(struct bpf_tcp_sock, bytes_acked): + BPF_TCP_SOCK_GET_COMMON(bytes_acked); + break; + case offsetof(struct bpf_tcp_sock, dsack_dups): + BPF_TCP_SOCK_GET_COMMON(dsack_dups); + break; + case offsetof(struct bpf_tcp_sock, delivered): + BPF_TCP_SOCK_GET_COMMON(delivered); + break; + case offsetof(struct bpf_tcp_sock, delivered_ce): + BPF_TCP_SOCK_GET_COMMON(delivered_ce); + break; + case offsetof(struct bpf_tcp_sock, icsk_retransmits): + BPF_INET_SOCK_GET_COMMON(icsk_retransmits); + break; }

return insn - insn_buf; @@@ -5650,7 -5692,7 +5692,7 @@@ BPF_CALL_1(bpf_tcp_sock, struct sock * return (unsigned long)NULL; }

- static const struct bpf_func_proto bpf_tcp_sock_proto = { + const struct bpf_func_proto bpf_tcp_sock_proto = { .func = bpf_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_TCP_SOCK_OR_NULL, @@@ -5694,6 -5736,46 +5736,46 @@@ BPF_CALL_1(bpf_skb_ecn_set_ce, struct s return INET_ECN_set_ce(skb); }

+ bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type, + struct bpf_insn_access_aux *info) + { + if (off < 0 || off >= offsetofend(struct bpf_xdp_sock, queue_id)) + return false; + + if (off % size != 0) + return false; + + switch (off) { + default: + return size == sizeof(__u32); + } + } + + u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type, + const struct bpf_insn *si, + struct bpf_insn *insn_buf, + struct bpf_prog *prog, u32 *target_size) + { + struct bpf_insn *insn = insn_buf; + + #define BPF_XDP_SOCK_GET(FIELD) \ + do { \ + BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_sock, FIELD) > \ + FIELD_SIZEOF(struct bpf_xdp_sock, FIELD)); \ + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ + si->dst_reg, si->src_reg, \ + offsetof(struct xdp_sock, FIELD)); \ + } while (0) + + switch (si->off) { + case offsetof(struct bpf_xdp_sock, queue_id): + BPF_XDP_SOCK_GET(queue_id); + break; + } + + return insn - insn_buf; + } + static const struct bpf_func_proto bpf_skb_ecn_set_ce_proto = { .func = bpf_skb_ecn_set_ce, .gpl_only = false, @@@ -5896,6 -5978,10 +5978,10 @@@ sock_addr_func_proto(enum bpf_func_id f case BPF_FUNC_skc_lookup_tcp: return &bpf_sock_addr_skc_lookup_tcp_proto; #endif /* CONFIG_INET */ + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_proto; default: return bpf_base_func_proto(func_id); } @@@ -5933,6 -6019,10 +6019,10 @@@ cg_skb_func_proto(enum bpf_func_id func return &bpf_sk_storage_get_proto; case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; + #ifdef CONFIG_SOCK_CGROUP_DATA + case BPF_FUNC_skb_cgroup_id: + return &bpf_skb_cgroup_id_proto; + #endif #ifdef CONFIG_INET case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; @@@ -6113,6 -6203,14 +6203,14 @@@ sock_ops_func_proto(enum bpf_func_id fu return &bpf_get_local_storage_proto; case BPF_FUNC_perf_event_output: return &bpf_sockopt_event_output_proto; + case BPF_FUNC_sk_storage_get: + return &bpf_sk_storage_get_proto; + case BPF_FUNC_sk_storage_delete: + return &bpf_sk_storage_delete_proto; + #ifdef CONFIG_INET + case BPF_FUNC_tcp_sock: + return &bpf_tcp_sock_proto; + #endif /* CONFIG_INET */ default: return bpf_base_func_proto(func_id); } @@@ -6800,6 -6898,13 +6898,13 @@@ static bool sock_addr_is_valid_access(i if (size != size_default) return false; break; + case offsetof(struct bpf_sock_addr, sk): + if (type != BPF_READ) + return false; + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_SOCKET; + break; default: if (type == BPF_READ) { if (size != size_default) @@@ -6843,6 -6948,11 +6948,11 @@@ static bool sock_ops_is_valid_access(in if (size != sizeof(__u64)) return false; break; + case offsetof(struct bpf_sock_ops, sk): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_SOCKET_OR_NULL; + break; default: if (size != size_default) return false; @@@ -7750,6 -7860,11 +7860,11 @@@ static u32 sock_addr_convert_ctx_access struct bpf_sock_addr_kern, struct in6_addr, t_ctx, s6_addr32[0], BPF_SIZE(si->code), off, tmp_reg); break; + case offsetof(struct bpf_sock_addr, sk): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_addr_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_addr_kern, sk)); + break; }

return insn - insn_buf; @@@ -7837,9 -7952,6 +7952,6 @@@ static u32 sock_ops_convert_ctx_access( SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ); \ } while (0)

- CONVERT_COMMON_TCP_SOCK_FIELDS(struct bpf_sock_ops, - SOCK_OPS_GET_TCP_SOCK_FIELD); - if (insn > insn_buf) return insn - insn_buf;

@@@ -8009,6 -8121,82 +8121,82 @@@ SOCK_OPS_GET_OR_SET_FIELD(sk_txhash, sk_txhash, struct sock, type); break; + case offsetof(struct bpf_sock_ops, snd_cwnd): + SOCK_OPS_GET_TCP_SOCK_FIELD(snd_cwnd); + break; + case offsetof(struct bpf_sock_ops, srtt_us): + SOCK_OPS_GET_TCP_SOCK_FIELD(srtt_us); + break; + case offsetof(struct bpf_sock_ops, snd_ssthresh): + SOCK_OPS_GET_TCP_SOCK_FIELD(snd_ssthresh); + break; + case offsetof(struct bpf_sock_ops, rcv_nxt): + SOCK_OPS_GET_TCP_SOCK_FIELD(rcv_nxt); + break; + case offsetof(struct bpf_sock_ops, snd_nxt): + SOCK_OPS_GET_TCP_SOCK_FIELD(snd_nxt); + break; + case offsetof(struct bpf_sock_ops, snd_una): + SOCK_OPS_GET_TCP_SOCK_FIELD(snd_una); + break; + case offsetof(struct bpf_sock_ops, mss_cache): + SOCK_OPS_GET_TCP_SOCK_FIELD(mss_cache); + break; + case offsetof(struct bpf_sock_ops, ecn_flags): + SOCK_OPS_GET_TCP_SOCK_FIELD(ecn_flags); + break; + case offsetof(struct bpf_sock_ops, rate_delivered): + SOCK_OPS_GET_TCP_SOCK_FIELD(rate_delivered); + break; + case offsetof(struct bpf_sock_ops, rate_interval_us): + SOCK_OPS_GET_TCP_SOCK_FIELD(rate_interval_us); + break; + case offsetof(struct bpf_sock_ops, packets_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(packets_out); + break; + case offsetof(struct bpf_sock_ops, retrans_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(retrans_out); + break; + case offsetof(struct bpf_sock_ops, total_retrans): + SOCK_OPS_GET_TCP_SOCK_FIELD(total_retrans); + break; + case offsetof(struct bpf_sock_ops, segs_in): + SOCK_OPS_GET_TCP_SOCK_FIELD(segs_in); + break; + case offsetof(struct bpf_sock_ops, data_segs_in): + SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_in); + break; + case offsetof(struct bpf_sock_ops, segs_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(segs_out); + break; + case offsetof(struct bpf_sock_ops, data_segs_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(data_segs_out); + break; + case offsetof(struct bpf_sock_ops, lost_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(lost_out); + break; + case offsetof(struct bpf_sock_ops, sacked_out): + SOCK_OPS_GET_TCP_SOCK_FIELD(sacked_out); + break; + case offsetof(struct bpf_sock_ops, bytes_received): + SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_received); + break; + case offsetof(struct bpf_sock_ops, bytes_acked): + SOCK_OPS_GET_TCP_SOCK_FIELD(bytes_acked); + break; + case offsetof(struct bpf_sock_ops, sk): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, + is_fullsock), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + is_fullsock)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( + struct bpf_sock_ops_kern, sk), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, sk)); + break; } return insn - insn_buf; } diff --combined net/ipv4/devinet.c index c5ebfa199794,137d1892395d..a4b5bd4d2c89 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@@ -62,11 -62,6 +62,11 @@@ #include <net/net_namespace.h> #include <net/addrconf.h>

+#define IPV6ONLY_FLAGS \ + (IFA_F_NODAD | IFA_F_OPTIMISTIC | IFA_F_DADFAILED | \ + IFA_F_HOMEADDRESS | IFA_F_TENTATIVE | \ + IFA_F_MANAGETEMPADDR | IFA_F_STABLE_PRIVACY) + static struct ipv4_devconf ipv4_devconf = { .data = { [IPV4_DEVCONF_ACCEPT_REDIRECTS - 1] = 1, @@@ -195,7 -190,8 +195,8 @@@ static void rtmsg_ifa(int event, struc

static BLOCKING_NOTIFIER_HEAD(inetaddr_chain); static BLOCKING_NOTIFIER_HEAD(inetaddr_validator_chain); - static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, + static void inet_del_ifa(struct in_device *in_dev, + struct in_ifaddr __rcu **ifap, int destroy); #ifdef CONFIG_SYSCTL static int devinet_sysctl_register(struct in_device *idev); @@@ -301,8 -297,8 +302,8 @@@ static void in_dev_rcu_put(struct rcu_h

static void inetdev_destroy(struct in_device *in_dev) { - struct in_ifaddr *ifa; struct net_device *dev; + struct in_ifaddr *ifa;

ASSERT_RTNL();

@@@ -312,7 -308,7 +313,7 @@@

ip_mc_destroy_dev(in_dev);

- while ((ifa = in_dev->ifa_list) != NULL) { + while ((ifa = rtnl_dereference(in_dev->ifa_list)) != NULL) { inet_del_ifa(in_dev, &in_dev->ifa_list, 0); inet_free_ifa(ifa); } @@@ -328,30 -324,35 +329,35 @@@

int inet_addr_onlink(struct in_device *in_dev, __be32 a, __be32 b) { + const struct in_ifaddr *ifa; + rcu_read_lock(); - for_primary_ifa(in_dev) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { if (inet_ifa_match(a, ifa)) { if (!b || inet_ifa_match(b, ifa)) { rcu_read_unlock(); return 1; } } - } endfor_ifa(in_dev); + } rcu_read_unlock(); return 0; }

- static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, - int destroy, struct nlmsghdr *nlh, u32 portid) + static void __inet_del_ifa(struct in_device *in_dev, + struct in_ifaddr __rcu **ifap, + int destroy, struct nlmsghdr *nlh, u32 portid) { struct in_ifaddr *promote = NULL; - struct in_ifaddr *ifa, *ifa1 = *ifap; - struct in_ifaddr *last_prim = in_dev->ifa_list; + struct in_ifaddr *ifa, *ifa1; + struct in_ifaddr *last_prim; struct in_ifaddr *prev_prom = NULL; int do_promote = IN_DEV_PROMOTE_SECONDARIES(in_dev);

ASSERT_RTNL();

+ ifa1 = rtnl_dereference(*ifap); + last_prim = rtnl_dereference(in_dev->ifa_list); if (in_dev->dead) goto no_promotions;

@@@ -360,9 -361,9 +366,9 @@@ **/

if (!(ifa1->ifa_flags & IFA_F_SECONDARY)) { - struct in_ifaddr **ifap1 = &ifa1->ifa_next; + struct in_ifaddr __rcu **ifap1 = &ifa1->ifa_next;

- while ((ifa = *ifap1) != NULL) { + while ((ifa = rtnl_dereference(*ifap1)) != NULL) { if (!(ifa->ifa_flags & IFA_F_SECONDARY) && ifa1->ifa_scope <= ifa->ifa_scope) last_prim = ifa; @@@ -395,7 -396,7 +401,7 @@@ * and later to add them back with new prefsrc. Do this * while all addresses are on the device list. */ - for (ifa = promote; ifa; ifa = ifa->ifa_next) { + for (ifa = promote; ifa; ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa)) fib_del_ifaddr(ifa, ifa1); @@@ -421,19 -422,25 +427,25 @@@ no_promotions blocking_notifier_call_chain(&inetaddr_chain, NETDEV_DOWN, ifa1);

if (promote) { - struct in_ifaddr *next_sec = promote->ifa_next; + struct in_ifaddr *next_sec;

+ next_sec = rtnl_dereference(promote->ifa_next); if (prev_prom) { - prev_prom->ifa_next = promote->ifa_next; - promote->ifa_next = last_prim->ifa_next; - last_prim->ifa_next = promote; + struct in_ifaddr *last_sec; + + rcu_assign_pointer(prev_prom->ifa_next, next_sec); + + last_sec = rtnl_dereference(last_prim->ifa_next); + rcu_assign_pointer(promote->ifa_next, last_sec); + rcu_assign_pointer(last_prim->ifa_next, promote); }

promote->ifa_flags &= ~IFA_F_SECONDARY; rtmsg_ifa(RTM_NEWADDR, promote, nlh, portid); blocking_notifier_call_chain(&inetaddr_chain, NETDEV_UP, promote); - for (ifa = next_sec; ifa; ifa = ifa->ifa_next) { + for (ifa = next_sec; ifa; + ifa = rtnl_dereference(ifa->ifa_next)) { if (ifa1->ifa_mask != ifa->ifa_mask || !inet_ifa_match(ifa1->ifa_address, ifa)) continue; @@@ -445,7 -452,8 +457,8 @@@ inet_free_ifa(ifa1); }

- static void inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap, + static void inet_del_ifa(struct in_device *in_dev, + struct in_ifaddr __rcu **ifap, int destroy) { __inet_del_ifa(in_dev, ifap, destroy, NULL, 0); @@@ -458,9 -466,10 +471,10 @@@ static DECLARE_DELAYED_WORK(check_lifet static int __inet_insert_ifa(struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 portid, struct netlink_ext_ack *extack) { + struct in_ifaddr __rcu **last_primary, **ifap; struct in_device *in_dev = ifa->ifa_dev; - struct in_ifaddr *ifa1, **ifap, **last_primary; struct in_validator_info ivi; + struct in_ifaddr *ifa1; int ret;

ASSERT_RTNL(); @@@ -473,11 -482,10 +487,13 @@@ ifa->ifa_flags &= ~IFA_F_SECONDARY; last_primary = &in_dev->ifa_list;

+ /* Don't set IPv6 only flags to IPv4 addresses */ + ifa->ifa_flags &= ~IPV6ONLY_FLAGS; + - for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; - ifap = &ifa1->ifa_next) { + ifap = &in_dev->ifa_list; + ifa1 = rtnl_dereference(*ifap); + + while (ifa1) { if (!(ifa1->ifa_flags & IFA_F_SECONDARY) && ifa->ifa_scope <= ifa1->ifa_scope) last_primary = &ifa1->ifa_next; @@@ -493,6 -501,9 +509,9 @@@ } ifa->ifa_flags |= IFA_F_SECONDARY; } + + ifap = &ifa1->ifa_next; + ifa1 = rtnl_dereference(*ifap); }

/* Allow any devices that wish to register ifaddr validtors to weigh @@@ -518,8 -529,8 +537,8 @@@ ifap = last_primary; }

- ifa->ifa_next = *ifap; - *ifap = ifa; + rcu_assign_pointer(ifa->ifa_next, *ifap); + rcu_assign_pointer(*ifap, ifa);

inet_hash_insert(dev_net(in_dev->dev), ifa);

@@@ -584,12 -595,14 +603,14 @@@ EXPORT_SYMBOL(inetdev_by_index) struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, __be32 mask) { + struct in_ifaddr *ifa; + ASSERT_RTNL();

- for_primary_ifa(in_dev) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { if (ifa->ifa_mask == mask && inet_ifa_match(prefix, ifa)) return ifa; - } endfor_ifa(in_dev); + } return NULL; }

@@@ -617,10 -630,12 +638,12 @@@ static int inet_rtm_deladdr(struct sk_b struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); + struct in_ifaddr __rcu **ifap; struct nlattr *tb[IFA_MAX+1]; struct in_device *in_dev; struct ifaddrmsg *ifm; - struct in_ifaddr *ifa, **ifap; + struct in_ifaddr *ifa; + int err = -EINVAL;

ASSERT_RTNL(); @@@ -637,7 -652,7 +660,7 @@@ goto errout; }

- for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; + for (ifap = &in_dev->ifa_list; (ifa = rtnl_dereference(*ifap)) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && ifa->ifa_local != nla_get_in_addr(tb[IFA_LOCAL])) @@@ -725,15 -740,19 +748,19 @@@ static void check_lifetime(struct work_

if (ifa->ifa_valid_lft != INFINITY_LIFE_TIME && age >= ifa->ifa_valid_lft) { - struct in_ifaddr **ifap; + struct in_ifaddr __rcu **ifap; + struct in_ifaddr *tmp;

- for (ifap = &ifa->ifa_dev->ifa_list; - *ifap != NULL; ifap = &(*ifap)->ifa_next) { - if (*ifap == ifa) { + ifap = &ifa->ifa_dev->ifa_list; + tmp = rtnl_dereference(*ifap); + while (tmp) { + if (tmp == ifa) { inet_del_ifa(ifa->ifa_dev, ifap, 1); break; } + ifap = &tmp->ifa_next; + tmp = rtnl_dereference(*ifap); } } else if (ifa->ifa_preferred_lft != INFINITY_LIFE_TIME && @@@ -877,13 -896,12 +904,12 @@@ errout static struct in_ifaddr *find_matching_ifa(struct in_ifaddr *ifa) { struct in_device *in_dev = ifa->ifa_dev; - struct in_ifaddr *ifa1, **ifap; + struct in_ifaddr *ifa1;

if (!ifa->ifa_local) return NULL;

- for (ifap = &in_dev->ifa_list; (ifa1 = *ifap) != NULL; - ifap = &ifa1->ifa_next) { + in_dev_for_each_ifa_rtnl(ifa1, in_dev) { if (ifa1->ifa_mask == ifa->ifa_mask && inet_ifa_match(ifa1->ifa_address, ifa) && ifa1->ifa_local == ifa->ifa_local) @@@ -978,8 -996,8 +1004,8 @@@ int devinet_ioctl(struct net *net, unsi { struct sockaddr_in sin_orig; struct sockaddr_in *sin = (struct sockaddr_in *)&ifr->ifr_addr; + struct in_ifaddr __rcu **ifap = NULL; struct in_device *in_dev; - struct in_ifaddr **ifap = NULL; struct in_ifaddr *ifa = NULL; struct net_device *dev; char *colon; @@@ -1050,7 -1068,9 +1076,9 @@@ /* note: we only do this for a limited set of ioctls and only if the original address family was AF_INET. This is checked above. */ - for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; + + for (ifap = &in_dev->ifa_list; + (ifa = rtnl_dereference(*ifap)) != NULL; ifap = &ifa->ifa_next) { if (!strcmp(ifr->ifr_name, ifa->ifa_label) && sin_orig.sin_addr.s_addr == @@@ -1063,7 -1083,8 +1091,8 @@@ 4.3BSD-style and passed in junk so we fall back to comparing just the label */ if (!ifa) { - for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; + for (ifap = &in_dev->ifa_list; + (ifa = rtnl_dereference(*ifap)) != NULL; ifap = &ifa->ifa_next) if (!strcmp(ifr->ifr_name, ifa->ifa_label)) break; @@@ -1212,7 -1233,7 +1241,7 @@@ out static int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size) { struct in_device *in_dev = __in_dev_get_rtnl(dev); - struct in_ifaddr *ifa; + const struct in_ifaddr *ifa; struct ifreq ifr; int done = 0;

@@@ -1222,7 -1243,7 +1251,7 @@@ if (!in_dev) goto out;

- for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { if (!buf) { done += size; continue; @@@ -1250,18 -1271,24 +1279,24 @@@ out static __be32 in_dev_select_addr(const struct in_device *in_dev, int scope) { - for_primary_ifa(in_dev) { + const struct in_ifaddr *ifa; + + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (ifa->ifa_flags & IFA_F_SECONDARY) + continue; if (ifa->ifa_scope != RT_SCOPE_LINK && ifa->ifa_scope <= scope) return ifa->ifa_local; - } endfor_ifa(in_dev); + }

return 0; }

__be32 inet_select_addr(const struct net_device *dev, __be32 dst, int scope) { + const struct in_ifaddr *ifa; __be32 addr = 0; + unsigned char localnet_scope = RT_SCOPE_HOST; struct in_device *in_dev; struct net *net = dev_net(dev); int master_idx; @@@ -1271,8 -1298,13 +1306,13 @@@ if (!in_dev) goto no_in_dev;

- for_primary_ifa(in_dev) { - if (ifa->ifa_scope > scope) + if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) + localnet_scope = RT_SCOPE_LINK; + + in_dev_for_each_ifa_rcu(ifa, in_dev) { + if (ifa->ifa_flags & IFA_F_SECONDARY) + continue; + if (min(ifa->ifa_scope, localnet_scope) > scope) continue; if (!dst || inet_ifa_match(dst, ifa)) { addr = ifa->ifa_local; @@@ -1280,7 -1312,7 +1320,7 @@@ } if (!addr) addr = ifa->ifa_local; - } endfor_ifa(in_dev); + }

if (addr) goto out_unlock; @@@ -1325,13 -1357,20 +1365,20 @@@ EXPORT_SYMBOL(inet_select_addr) static __be32 confirm_addr_indev(struct in_device *in_dev, __be32 dst, __be32 local, int scope) { - int same = 0; + unsigned char localnet_scope = RT_SCOPE_HOST; + const struct in_ifaddr *ifa; __be32 addr = 0; + int same = 0; + + if (unlikely(IN_DEV_ROUTE_LOCALNET(in_dev))) + localnet_scope = RT_SCOPE_LINK; + + in_dev_for_each_ifa_rcu(ifa, in_dev) { + unsigned char min_scope = min(ifa->ifa_scope, localnet_scope);

- for_ifa(in_dev) { if (!addr && (local == ifa->ifa_local || !local) && - ifa->ifa_scope <= scope) { + min_scope <= scope) { addr = ifa->ifa_local; if (same) break; @@@ -1346,7 -1385,7 +1393,7 @@@ if (inet_ifa_match(addr, ifa)) break; /* No, then can we use new local src? */ - if (ifa->ifa_scope <= scope) { + if (min_scope <= scope) { addr = ifa->ifa_local; break; } @@@ -1354,7 -1393,7 +1401,7 @@@ same = 0; } } - } endfor_ifa(in_dev); + }

return same ? addr : 0; } @@@ -1428,7 -1467,7 +1475,7 @@@ static void inetdev_changename(struct n struct in_ifaddr *ifa; int named = 0;

- for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { char old[IFNAMSIZ], *dot;

memcpy(old, ifa->ifa_label, IFNAMSIZ); @@@ -1458,10 -1497,9 +1505,9 @@@ static void inetdev_send_gratuitous_arp struct in_device *in_dev)

{ - struct in_ifaddr *ifa; + const struct in_ifaddr *ifa;

- for (ifa = in_dev->ifa_list; ifa; - ifa = ifa->ifa_next) { + in_dev_for_each_ifa_rtnl(ifa, in_dev) { arp_send(ARPOP_REQUEST, ETH_P_ARP, ifa->ifa_local, dev, ifa->ifa_local, NULL, @@@ -1731,15 -1769,17 +1777,17 @@@ static int in_dev_dump_addr(struct in_d int ip_idx = 0; int err;

- for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next, ip_idx++) { - if (ip_idx < s_ip_idx) + in_dev_for_each_ifa_rtnl(ifa, in_dev) { + if (ip_idx < s_ip_idx) { + ip_idx++; continue; - + } err = inet_fill_ifaddr(skb, ifa, fillargs); if (err < 0) goto done;

nl_dump_check_consistent(cb, nlmsg_hdr(skb)); + ip_idx++; } err = 0;

diff --combined net/ipv4/igmp.c index 85107bf812f2,9a206931a342..180f6896b98b --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@@ -332,14 -332,15 +332,15 @@@ static __be32 igmpv3_get_srcaddr(struc const struct flowi4 *fl4) { struct in_device *in_dev = __in_dev_get_rcu(dev); + const struct in_ifaddr *ifa;

if (!in_dev) return htonl(INADDR_ANY);

- for_ifa(in_dev) { + in_dev_for_each_ifa_rcu(ifa, in_dev) { if (fl4->saddr == ifa->ifa_local) return fl4->saddr; - } endfor_ifa(in_dev); + }

return htonl(INADDR_ANY); } @@@ -1228,8 -1229,12 +1229,8 @@@ static void igmpv3_del_delrec(struct in if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { - im->tomb = pmc->tomb; - pmc->tomb = NULL; - - im->sources = pmc->sources; - pmc->sources = NULL; - + swap(im->tomb, pmc->tomb); + swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; } else { diff --combined net/ipv4/route.c index b2b35b38724d,dc1f510a7c81..69a289f8de4f --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@@ -95,6 -95,7 +95,7 @@@ #include <net/inetpeer.h> #include <net/sock.h> #include <net/ip_fib.h> + #include <net/nexthop.h> #include <net/arp.h> #include <net/tcp.h> #include <net/icmp.h> @@@ -447,7 -448,7 +448,7 @@@ static struct neighbour *ipv4_neigh_loo n = ip_neigh_gw4(dev, pkey); }

- if (n && !refcount_inc_not_zero(&n->refcnt)) + if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt)) n = NULL;

rcu_read_unlock_bh(); @@@ -1531,7 -1532,6 +1532,6 @@@ static void ipv4_dst_destroy(struct dst

void rt_flush_dev(struct net_device *dev) { - struct net *net = dev_net(dev); struct rtable *rt; int cpu;

@@@ -1542,7 -1542,7 +1542,7 @@@ list_for_each_entry(rt, &ul->head, rt_uncached) { if (rt->dst.dev != dev) continue; - rt->dst.dev = net->loopback_dev; + rt->dst.dev = blackhole_netdev; dev_hold(rt->dst.dev); dev_put(dev); } @@@ -1580,7 -1580,7 +1580,7 @@@ static void rt_set_nexthop(struct rtabl ip_dst_init_metrics(&rt->dst, fi->fib_metrics);

#ifdef CONFIG_IP_ROUTE_CLASSID - { + if (nhc->nhc_family == AF_INET) { struct fib_nh *nh;

nh = container_of(nhc, struct fib_nh, nh_common); @@@ -1962,6 -1962,23 +1962,23 @@@ int fib_multipath_hash(const struct ne hash_keys.basic.ip_proto = fl4->flowi4_proto; } break; + case 2: + memset(&hash_keys, 0, sizeof(hash_keys)); + hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; + /* skb is currently provided only when forwarding */ + if (skb) { + struct flow_keys keys; + + skb_flow_dissect_flow_keys(skb, &keys, 0); + + hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; + hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; + } else { + /* Same as case 0 */ + hash_keys.addrs.v4addrs.src = fl4->saddr; + hash_keys.addrs.v4addrs.dst = fl4->daddr; + } + break; } mhash = flow_hash_from_keys(&hash_keys);

@@@ -1979,7 -1996,7 +1996,7 @@@ static int ip_mkroute_input(struct sk_b struct flow_keys *hkeys) { #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (res->fi && res->fi->fib_nhs > 1) { + if (res->fi && fib_info_num_path(res->fi) > 1) { int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys);

fib_select_multipath(res, h); @@@ -2714,7 -2731,7 +2731,7 @@@ static int rt_fill_info(struct net *net r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; - r->rtm_tos = fl4->flowi4_tos; + r->rtm_tos = fl4 ? fl4->flowi4_tos : 0; r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; @@@ -2742,7 -2759,7 +2759,7 @@@ nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid)) goto nla_put_failure; #endif - if (!rt_is_input_route(rt) && + if (fl4 && !rt_is_input_route(rt) && fl4->saddr != src) { if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; @@@ -2782,36 -2799,40 +2799,40 @@@ if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure;

- if (fl4->flowi4_mark && - nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark)) - goto nla_put_failure; - - if (!uid_eq(fl4->flowi4_uid, INVALID_UID) && - nla_put_u32(skb, RTA_UID, - from_kuid_munged(current_user_ns(), fl4->flowi4_uid))) - goto nla_put_failure; + if (fl4) { + if (fl4->flowi4_mark && + nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark)) + goto nla_put_failure;

- error = rt->dst.error; + if (!uid_eq(fl4->flowi4_uid, INVALID_UID) && + nla_put_u32(skb, RTA_UID, + from_kuid_munged(current_user_ns(), + fl4->flowi4_uid))) + goto nla_put_failure;

- if (rt_is_input_route(rt)) { + if (rt_is_input_route(rt)) { #ifdef CONFIG_IP_MROUTE - if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && - IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { - int err = ipmr_get_route(net, skb, - fl4->saddr, fl4->daddr, - r, portid); - - if (err <= 0) { - if (err == 0) - return 0; - goto nla_put_failure; - } - } else + if (ipv4_is_multicast(dst) && + !ipv4_is_local_multicast(dst) && + IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { + int err = ipmr_get_route(net, skb, + fl4->saddr, fl4->daddr, + r, portid); + + if (err <= 0) { + if (err == 0) + return 0; + goto nla_put_failure; + } + } else #endif - if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif)) - goto nla_put_failure; + if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif)) + goto nla_put_failure; + } }

+ error = rt->dst.error; + if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) goto nla_put_failure;

@@@ -2823,6 -2844,80 +2844,80 @@@ nla_put_failure return -EMSGSIZE; }

+ static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, + struct netlink_callback *cb, u32 table_id, + struct fnhe_hash_bucket *bucket, int genid, + int *fa_index, int fa_start) + { + int i; + + for (i = 0; i < FNHE_HASH_SIZE; i++) { + struct fib_nh_exception *fnhe; + + for (fnhe = rcu_dereference(bucket[i].chain); fnhe; + fnhe = rcu_dereference(fnhe->fnhe_next)) { + struct rtable *rt; + int err; + + if (*fa_index < fa_start) + goto next; + + if (fnhe->fnhe_genid != genid) + goto next; + + if (fnhe->fnhe_expires && + time_after(jiffies, fnhe->fnhe_expires)) + goto next; + + rt = rcu_dereference(fnhe->fnhe_rth_input); + if (!rt) + rt = rcu_dereference(fnhe->fnhe_rth_output); + if (!rt) + goto next; + + err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, + table_id, NULL, skb, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq); + if (err) + return err; + next: + (*fa_index)++; + } + } + + return 0; + } + + int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, + u32 table_id, struct fib_info *fi, + int *fa_index, int fa_start) + { + struct net *net = sock_net(cb->skb->sk); + int nhsel, genid = fnhe_genid(net); + + for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { + struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel); + struct fnhe_hash_bucket *bucket; + int err; + + if (nhc->nhc_flags & RTNH_F_DEAD) + continue; + + rcu_read_lock(); + bucket = rcu_dereference(nhc->nhc_exceptions); + err = 0; + if (bucket) + err = fnhe_dump_bucket(net, skb, cb, table_id, bucket, + genid, fa_index, fa_start); + rcu_read_unlock(); + if (err) + return err; + } + + return 0; + } + static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst, u8 ip_proto, __be16 sport, __be16 dport) @@@ -3230,9 -3325,11 +3325,11 @@@ static struct ctl_table ipv4_route_tabl { } };

+ static const char ipv4_route_flush_procname[] = "flush"; + static struct ctl_table ipv4_route_flush_table[] = { { - .procname = "flush", + .procname = ipv4_route_flush_procname, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv4_sysctl_rtcache_flush, @@@ -3250,9 -3347,11 +3347,11 @@@ static __net_init int sysctl_route_net_ if (!tbl) goto err_dup;

- /* Don't export sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) - tbl[0].procname = NULL; + /* Don't export non-whitelisted sysctls to unprivileged users */ + if (net->user_ns != &init_user_ns) { + if (tbl[0].procname != ipv4_route_flush_procname) + tbl[0].procname = NULL; + } } tbl[0].extra1 = net;

diff --combined net/key/af_key.c index fe5fc4bab7ee,39b3d95094eb..b67ed3a8486c --- a/net/key/af_key.c +++ b/net/key/af_key.c @@@ -928,8 -928,7 +928,7 @@@ static struct sk_buff *__pfkey_xfrm_sta pfkey_sockaddr_fill(&x->props.saddr, 0, (struct sockaddr *) (addr + 1), x->props.family); - if (!addr->sadb_address_prefixlen) - BUG(); + BUG_ON(!addr->sadb_address_prefixlen);

/* dst address */ addr = skb_put(skb, sizeof(struct sadb_address) + sockaddr_size); @@@ -944,8 -943,7 +943,7 @@@ pfkey_sockaddr_fill(&x->id.daddr, 0, (struct sockaddr *) (addr + 1), x->props.family); - if (!addr->sadb_address_prefixlen) - BUG(); + BUG_ON(!addr->sadb_address_prefixlen);

if (!xfrm_addr_equal(&x->sel.saddr, &x->props.saddr, x->props.family)) { @@@ -2438,10 -2436,8 +2436,10 @@@ static int key_pol_get_resp(struct soc goto out; } err = pfkey_xfrm_policy2msg(out_skb, xp, dir); - if (err < 0) + if (err < 0) { + kfree_skb(out_skb); goto out; + }

out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = hdr->sadb_msg_version; @@@ -2692,10 -2688,8 +2690,10 @@@ static int dump_sp(struct xfrm_policy * return PTR_ERR(out_skb);

err = pfkey_xfrm_policy2msg(out_skb, xp, dir); - if (err < 0) + if (err < 0) { + kfree_skb(out_skb); return err; + }

out_hdr = (struct sadb_msg *) out_skb->data; out_hdr->sadb_msg_version = pfk->dump.msg_version; diff --combined net/netfilter/ipvs/ip_vs_core.c index d5103a9eb302,e8651fd621ef..f662f198b458 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@@ -34,6 -34,7 +34,7 @@@ #include <net/tcp.h> #include <net/udp.h> #include <net/icmp.h> /* for icmp_send */ + #include <net/gue.h> #include <net/route.h> #include <net/ip6_checksum.h> #include <net/netns/generic.h> /* net_generic() */ @@@ -892,7 -893,7 +893,7 @@@ static int handle_response_icmp(int af if (IPPROTO_TCP == protocol || IPPROTO_UDP == protocol || IPPROTO_SCTP == protocol) offset += 2 * sizeof(__u16); - if (!skb_make_writable(skb, offset)) + if (skb_ensure_writable(skb, offset)) goto out;

#ifdef CONFIG_IP_VS_IPV6 @@@ -1282,7 -1283,7 +1283,7 @@@ handle_response(int af, struct sk_buff

IP_VS_DBG_PKT(11, af, pp, skb, iph->off, "Outgoing packet");

- if (!skb_make_writable(skb, iph->len)) + if (skb_ensure_writable(skb, iph->len)) goto drop;

/* mangle the packet */ @@@ -1574,6 -1575,41 +1575,41 @@@ ip_vs_try_to_schedule(struct netns_ipv return 1; }

+ /* Check the UDP tunnel and return its header length */ + static int ipvs_udp_decap(struct netns_ipvs *ipvs, struct sk_buff *skb, + unsigned int offset, __u16 af, + const union nf_inet_addr *daddr, __u8 *proto) + { + struct udphdr _udph, *udph; + struct ip_vs_dest *dest; + + udph = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); + if (!udph) + goto unk; + offset += sizeof(struct udphdr); + dest = ip_vs_find_tunnel(ipvs, af, daddr, udph->dest); + if (!dest) + goto unk; + if (dest->tun_type == IP_VS_CONN_F_TUNNEL_TYPE_GUE) { + struct guehdr _gueh, *gueh; + + gueh = skb_header_pointer(skb, offset, sizeof(_gueh), &_gueh); + if (!gueh) + goto unk; + if (gueh->control != 0 || gueh->version != 0) + goto unk; + /* Later we can support also IPPROTO_IPV6 */ + if (gueh->proto_ctype != IPPROTO_IPIP) + goto unk; + *proto = gueh->proto_ctype; + return sizeof(struct udphdr) + sizeof(struct guehdr) + + (gueh->hlen << 2); + } + + unk: + return 0; + } + /* * Handle ICMP messages in the outside-to-inside direction (incoming). * Find any that might be relevant, check against existing connections, @@@ -1593,6 -1629,7 +1629,7 @@@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd; unsigned int offset, offset2, ihl, verdict; bool ipip, new_cp = false; + union nf_inet_addr *raddr;

*related = 1;

@@@ -1631,20 -1668,51 +1668,51 @@@ cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ + raddr = (union nf_inet_addr *)&cih->daddr;

/* Special case for errors for IPIP packets */ ipip = false; if (cih->protocol == IPPROTO_IPIP) { + struct ip_vs_dest *dest; + if (unlikely(cih->frag_off & htons(IP_OFFSET))) return NF_ACCEPT; /* Error for our IPIP must arrive at LOCAL_IN */ if (!(skb_rtable(skb)->rt_flags & RTCF_LOCAL)) return NF_ACCEPT; + dest = ip_vs_find_tunnel(ipvs, AF_INET, raddr, 0); + /* Only for known tunnel */ + if (!dest || dest->tun_type != IP_VS_CONN_F_TUNNEL_TYPE_IPIP) + return NF_ACCEPT; offset += cih->ihl * 4; cih = skb_header_pointer(skb, offset, sizeof(_ciph), &_ciph); if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ ipip = true; + } else if (cih->protocol == IPPROTO_UDP && /* Can be UDP encap */ + /* Error for our tunnel must arrive at LOCAL_IN */ + (skb_rtable(skb)->rt_flags & RTCF_LOCAL)) { + __u8 iproto; + int ulen; + + /* Non-first fragment has no UDP header */ + if (unlikely(cih->frag_off & htons(IP_OFFSET))) + return NF_ACCEPT; + offset2 = offset + cih->ihl * 4; + ulen = ipvs_udp_decap(ipvs, skb, offset2, AF_INET, raddr, + &iproto); + if (ulen > 0) { + /* Skip IP and UDP tunnel headers */ + offset = offset2 + ulen; + /* Now we should be at the original IP header */ + cih = skb_header_pointer(skb, offset, sizeof(_ciph), + &_ciph); + if (cih && cih->version == 4 && cih->ihl >= 5 && + iproto == IPPROTO_IPIP) + ipip = true; + else + return NF_ACCEPT; + } }

pd = ip_vs_proto_data_get(ipvs, cih->protocol); @@@ -2245,6 -2313,7 +2313,6 @@@ static const struct nf_hook_ops ip_vs_o static int __net_init __ip_vs_init(struct net *net) { struct netns_ipvs *ipvs; - int ret;

ipvs = net_generic(net, ip_vs_net_id); if (ipvs == NULL) @@@ -2276,11 -2345,17 +2344,11 @@@ if (ip_vs_sync_net_init(ipvs) < 0) goto sync_fail;

- ret = nf_register_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); - if (ret < 0) - goto hook_fail; - return 0; /* * Error handling */

-hook_fail: - ip_vs_sync_net_cleanup(ipvs); sync_fail: ip_vs_conn_net_cleanup(ipvs); conn_fail: @@@ -2310,19 -2385,6 +2378,19 @@@ static void __net_exit __ip_vs_cleanup( net->ipvs = NULL; }

+static int __net_init __ip_vs_dev_init(struct net *net) +{ + int ret; + + ret = nf_register_net_hooks(net, ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); + if (ret < 0) + goto hook_fail; + return 0; + +hook_fail: + return ret; +} + static void __net_exit __ip_vs_dev_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@@ -2342,7 -2404,6 +2410,7 @@@ static struct pernet_operations ipvs_co };

static struct pernet_operations ipvs_core_dev_ops = { + .init = __ip_vs_dev_init, .exit = __ip_vs_dev_cleanup, };

diff --combined net/netfilter/ipvs/ip_vs_ctl.c index 741d91aa4a8d,84384d896e29..a8abba7e3d2d --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@@ -510,15 -510,36 +510,36 @@@ static inline unsigned int ip_vs_rs_has static void ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest) { unsigned int hash; + __be16 port;

if (dest->in_rs_table) return;

+ switch (IP_VS_DFWD_METHOD(dest)) { + case IP_VS_CONN_F_MASQ: + port = dest->port; + break; + case IP_VS_CONN_F_TUNNEL: + switch (dest->tun_type) { + case IP_VS_CONN_F_TUNNEL_TYPE_GUE: + port = dest->tun_port; + break; + case IP_VS_CONN_F_TUNNEL_TYPE_IPIP: + port = 0; + break; + default: + return; + } + break; + default: + return; + } + /* * Hash by proto,addr,port, * which are the parameters of the real service. */ - hash = ip_vs_rs_hashkey(dest->af, &dest->addr, dest->port); + hash = ip_vs_rs_hashkey(dest->af, &dest->addr, port);

hlist_add_head_rcu(&dest->d_list, &ipvs->rs_table[hash]); dest->in_rs_table = 1; @@@ -550,7 -571,8 +571,8 @@@ bool ip_vs_has_real_service(struct netn if (dest->port == dport && dest->af == af && ip_vs_addr_equal(af, &dest->addr, daddr) && - (dest->protocol == protocol || dest->vfwmark)) { + (dest->protocol == protocol || dest->vfwmark) && + IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_MASQ) { /* HIT */ return true; } @@@ -580,7 -602,37 +602,37 @@@ struct ip_vs_dest *ip_vs_find_real_serv if (dest->port == dport && dest->af == af && ip_vs_addr_equal(af, &dest->addr, daddr) && - (dest->protocol == protocol || dest->vfwmark)) { + (dest->protocol == protocol || dest->vfwmark) && + IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_MASQ) { + /* HIT */ + return dest; + } + } + + return NULL; + } + + /* Find real service record by <af,addr,tun_port>. + * In case of multiple records with the same <af,addr,tun_port>, only + * the first found record is returned. + * + * To be called under RCU lock. + */ + struct ip_vs_dest *ip_vs_find_tunnel(struct netns_ipvs *ipvs, int af, + const union nf_inet_addr *daddr, + __be16 tun_port) + { + struct ip_vs_dest *dest; + unsigned int hash; + + /* Check for "full" addressed entries */ + hash = ip_vs_rs_hashkey(af, daddr, tun_port); + + hlist_for_each_entry_rcu(dest, &ipvs->rs_table[hash], d_list) { + if (dest->tun_port == tun_port && + dest->af == af && + ip_vs_addr_equal(af, &dest->addr, daddr) && + IP_VS_DFWD_METHOD(dest) == IP_VS_CONN_F_TUNNEL) { /* HIT */ return dest; } @@@ -826,24 -878,29 +878,29 @@@ __ip_vs_update_dest(struct ip_vs_servic conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK; conn_flags |= IP_VS_CONN_F_INACTIVE;

+ /* Need to rehash? */ + if ((udest->conn_flags & IP_VS_CONN_F_FWD_MASK) != + IP_VS_DFWD_METHOD(dest) || + udest->tun_type != dest->tun_type || + udest->tun_port != dest->tun_port) + ip_vs_rs_unhash(dest); + /* set the tunnel info */ dest->tun_type = udest->tun_type; dest->tun_port = udest->tun_port; + dest->tun_flags = udest->tun_flags;

/* set the IP_VS_CONN_F_NOOUTPUT flag if not masquerading/NAT */ if ((conn_flags & IP_VS_CONN_F_FWD_MASK) != IP_VS_CONN_F_MASQ) { conn_flags |= IP_VS_CONN_F_NOOUTPUT; } else { - /* - * Put the real service in rs_table if not present. - * For now only for NAT! - */ - ip_vs_rs_hash(ipvs, dest); /* FTP-NAT requires conntrack for mangling */ if (svc->port == FTPPORT) ip_vs_register_conntrack(svc); } atomic_set(&dest->conn_flags, conn_flags); + /* Put the real service in rs_table if not present. */ + ip_vs_rs_hash(ipvs, dest);

/* bind the service */ old_svc = rcu_dereference_protected(dest->svc, 1); @@@ -2396,7 -2453,9 +2453,7 @@@ do_ip_vs_set_ctl(struct sock *sk, int c cfg.syncid = dm->syncid; ret = start_sync_thread(ipvs, &cfg, dm->state); } else { - mutex_lock(&ipvs->sync_mutex); ret = stop_sync_thread(ipvs, dm->state); - mutex_unlock(&ipvs->sync_mutex); } goto out_dec; } @@@ -2904,6 -2963,7 +2961,7 @@@ static const struct nla_policy ip_vs_de [IPVS_DEST_ATTR_ADDR_FAMILY] = { .type = NLA_U16 }, [IPVS_DEST_ATTR_TUN_TYPE] = { .type = NLA_U8 }, [IPVS_DEST_ATTR_TUN_PORT] = { .type = NLA_U16 }, + [IPVS_DEST_ATTR_TUN_FLAGS] = { .type = NLA_U16 }, };

static int ip_vs_genl_fill_stats(struct sk_buff *skb, int container_type, @@@ -3210,6 -3270,8 +3268,8 @@@ static int ip_vs_genl_fill_dest(struct dest->tun_type) || nla_put_be16(skb, IPVS_DEST_ATTR_TUN_PORT, dest->tun_port) || + nla_put_u16(skb, IPVS_DEST_ATTR_TUN_FLAGS, + dest->tun_flags) || nla_put_u32(skb, IPVS_DEST_ATTR_U_THRESH, dest->u_threshold) || nla_put_u32(skb, IPVS_DEST_ATTR_L_THRESH, dest->l_threshold) || nla_put_u32(skb, IPVS_DEST_ATTR_ACTIVE_CONNS, @@@ -3330,7 -3392,8 +3390,8 @@@ static int ip_vs_genl_parse_dest(struc /* If a full entry was requested, check for the additional fields */ if (full_entry) { struct nlattr *nla_fwd, *nla_weight, *nla_u_thresh, - *nla_l_thresh, *nla_tun_type, *nla_tun_port; + *nla_l_thresh, *nla_tun_type, *nla_tun_port, + *nla_tun_flags;

nla_fwd = attrs[IPVS_DEST_ATTR_FWD_METHOD]; nla_weight = attrs[IPVS_DEST_ATTR_WEIGHT]; @@@ -3338,6 -3401,7 +3399,7 @@@ nla_l_thresh = attrs[IPVS_DEST_ATTR_L_THRESH]; nla_tun_type = attrs[IPVS_DEST_ATTR_TUN_TYPE]; nla_tun_port = attrs[IPVS_DEST_ATTR_TUN_PORT]; + nla_tun_flags = attrs[IPVS_DEST_ATTR_TUN_FLAGS];

if (!(nla_fwd && nla_weight && nla_u_thresh && nla_l_thresh)) return -EINVAL; @@@ -3353,6 -3417,9 +3415,9 @@@

if (nla_tun_port) udest->tun_port = nla_get_be16(nla_tun_port); + + if (nla_tun_flags) + udest->tun_flags = nla_get_u16(nla_tun_flags); }

return 0; @@@ -3513,8 -3580,10 +3578,8 @@@ static int ip_vs_genl_del_daemon(struc if (!attrs[IPVS_DAEMON_ATTR_STATE]) return -EINVAL;

- mutex_lock(&ipvs->sync_mutex); ret = stop_sync_thread(ipvs, nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); - mutex_unlock(&ipvs->sync_mutex); return ret; }

diff --combined net/netfilter/nf_nat_proto.c index 83a24cc5753b,888292e8fbb2..7ac733ebd060 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@@ -70,7 -70,7 +70,7 @@@ static bool udp_manip_pkt(struct sk_buf struct udphdr *hdr; bool do_csum;

- if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false;

hdr = (struct udphdr *)(skb->data + hdroff); @@@ -88,7 -88,7 +88,7 @@@ static bool udplite_manip_pkt(struct sk #ifdef CONFIG_NF_CT_PROTO_UDPLITE struct udphdr *hdr;

- if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false;

hdr = (struct udphdr *)(skb->data + hdroff); @@@ -114,7 -114,7 +114,7 @@@ sctp_manip_pkt(struct sk_buff *skb if (skb->len >= hdroff + sizeof(*hdr)) hdrsize = sizeof(*hdr);

- if (!skb_make_writable(skb, hdroff + hdrsize)) + if (skb_ensure_writable(skb, hdroff + hdrsize)) return false;

hdr = (struct sctphdr *)(skb->data + hdroff); @@@ -155,7 -155,7 +155,7 @@@ tcp_manip_pkt(struct sk_buff *skb if (skb->len >= hdroff + sizeof(struct tcphdr)) hdrsize = sizeof(struct tcphdr);

- if (!skb_make_writable(skb, hdroff + hdrsize)) + if (skb_ensure_writable(skb, hdroff + hdrsize)) return false;

hdr = (struct tcphdr *)(skb->data + hdroff); @@@ -195,7 -195,7 +195,7 @@@ dccp_manip_pkt(struct sk_buff *skb if (skb->len >= hdroff + sizeof(struct dccp_hdr)) hdrsize = sizeof(struct dccp_hdr);

- if (!skb_make_writable(skb, hdroff + hdrsize)) + if (skb_ensure_writable(skb, hdroff + hdrsize)) return false;

hdr = (struct dccp_hdr *)(skb->data + hdroff); @@@ -229,7 -229,7 +229,7 @@@ icmp_manip_pkt(struct sk_buff *skb { struct icmphdr *hdr;

- if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false;

hdr = (struct icmphdr *)(skb->data + hdroff); @@@ -247,7 -247,7 +247,7 @@@ icmpv6_manip_pkt(struct sk_buff *skb { struct icmp6hdr *hdr;

- if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) + if (skb_ensure_writable(skb, hdroff + sizeof(*hdr))) return false;

hdr = (struct icmp6hdr *)(skb->data + hdroff); @@@ -275,7 -275,7 +275,7 @@@ gre_manip_pkt(struct sk_buff *skb

/* pgreh includes two optional 32bit fields which are not required * to be there. That's where the magic '8' comes from */ - if (!skb_make_writable(skb, hdroff + sizeof(*pgreh) - 8)) + if (skb_ensure_writable(skb, hdroff + sizeof(*pgreh) - 8)) return false;

greh = (void *)skb->data + hdroff; @@@ -347,7 -347,7 +347,7 @@@ static bool nf_nat_ipv4_manip_pkt(struc struct iphdr *iph; unsigned int hdroff;

- if (!skb_make_writable(skb, iphdroff + sizeof(*iph))) + if (skb_ensure_writable(skb, iphdroff + sizeof(*iph))) return false;

iph = (void *)skb->data + iphdroff; @@@ -378,7 -378,7 +378,7 @@@ static bool nf_nat_ipv6_manip_pkt(struc int hdroff; u8 nexthdr;

- if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h))) + if (skb_ensure_writable(skb, iphdroff + sizeof(*ipv6h))) return false;

ipv6h = (void *)skb->data + iphdroff; @@@ -562,9 -562,9 +562,9 @@@ int nf_nat_icmp_reply_translation(struc

WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY);

- if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) + if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; - if (nf_ip_checksum(skb, hooknum, hdrlen, 0)) + if (nf_ip_checksum(skb, hooknum, hdrlen, IPPROTO_ICMP)) return 0;

inside = (void *)skb->data + hdrlen; @@@ -784,7 -784,7 +784,7 @@@ int nf_nat_icmpv6_reply_translation(str

WARN_ON(ctinfo != IP_CT_RELATED && ctinfo != IP_CT_RELATED_REPLY);

- if (!skb_make_writable(skb, hdrlen + sizeof(*inside))) + if (skb_ensure_writable(skb, hdrlen + sizeof(*inside))) return 0; if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6)) return 0; diff --combined net/sched/cls_flower.c index fdeede3af72e,ce2e9b1c9850..5d4935b51e6f --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@@ -27,7 -27,7 +27,7 @@@ #include <net/dst_metadata.h>

struct fl_flow_key { - int indev_ifindex; + struct flow_dissector_key_meta meta; struct flow_dissector_key_control control; struct flow_dissector_key_control enc_control; struct flow_dissector_key_basic basic; @@@ -284,7 -284,7 +284,7 @@@ static int fl_classify(struct sk_buff * list_for_each_entry_rcu(mask, &head->masks, list) { fl_clear_masked_range(&skb_key, mask);

- skb_key.indev_ifindex = skb->skb_iif; + skb_flow_dissect_meta(skb, &mask->dissector, &skb_key); /* skb_flow_dissect() does not set n_proto in case an unknown * protocol, so do it rather here. */ @@@ -524,6 -524,24 +524,6 @@@ static struct cls_fl_filter *__fl_get(s return f; }

-static struct cls_fl_filter *fl_get_next_filter(struct tcf_proto *tp, - unsigned long *handle) -{ - struct cls_fl_head *head = fl_head_dereference(tp); - struct cls_fl_filter *f; - - rcu_read_lock(); - while ((f = idr_get_next_ul(&head->handle_idr, handle))) { - /* don't return filters that are being deleted */ - if (refcount_inc_not_zero(&f->refcnt)) - break; - ++(*handle); - } - rcu_read_unlock(); - - return f; -} - static int __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, bool *last, bool rtnl_held, struct netlink_ext_ack *extack) @@@ -1003,15 -1021,14 +1003,14 @@@ static int fl_set_key(struct net *net, { __be16 ethertype; int ret = 0; - #ifdef CONFIG_NET_CLS_IND + if (tb[TCA_FLOWER_INDEV]) { int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV], extack); if (err < 0) return err; - key->indev_ifindex = err; - mask->indev_ifindex = 0xffffffff; + key->meta.ingress_ifindex = err; + mask->meta.ingress_ifindex = 0xffffffff; } - #endif

fl_set_key_val(tb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST, mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK, @@@ -1264,6 -1281,8 +1263,8 @@@ static void fl_init_dissector(struct fl struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX]; size_t cnt = 0;

+ FL_KEY_SET_IF_MASKED(mask, keys, cnt, + FLOW_DISSECTOR_KEY_META, meta); FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control); FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic); FL_KEY_SET_IF_MASKED(mask, keys, cnt, @@@ -1673,25 -1692,20 +1674,25 @@@ static int fl_delete(struct tcf_proto * static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg, bool rtnl_held) { + struct cls_fl_head *head = fl_head_dereference(tp); + unsigned long id = arg->cookie, tmp; struct cls_fl_filter *f;

arg->count = arg->skip;

- while ((f = fl_get_next_filter(tp, &arg->cookie)) != NULL) { + idr_for_each_entry_continue_ul(&head->handle_idr, f, tmp, id) { + /* don't return filters that are being deleted */ + if (!refcount_inc_not_zero(&f->refcnt)) + continue; if (arg->fn(tp, f, arg) < 0) { __fl_put(f); arg->stop = 1; break; } __fl_put(f); - arg->cookie++; arg->count++; } + arg->cookie = id; }

static struct cls_fl_filter * @@@ -2110,10 -2124,10 +2111,10 @@@ static int fl_dump_key_enc_opt(struct s static int fl_dump_key(struct sk_buff *skb, struct net *net, struct fl_flow_key *key, struct fl_flow_key *mask) { - if (mask->indev_ifindex) { + if (mask->meta.ingress_ifindex) { struct net_device *dev;

- dev = __dev_get_by_index(net, key->indev_ifindex); + dev = __dev_get_by_index(net, key->meta.ingress_ifindex); if (dev && nla_put_string(skb, TCA_FLOWER_INDEV, dev->name)) goto nla_put_failure; } diff --combined net/socket.c index 92739450956b,d97b74f762e8..77b8f3d3448f --- a/net/socket.c +++ b/net/socket.c @@@ -73,7 -73,6 +73,7 @@@ #include <linux/module.h> #include <linux/highmem.h> #include <linux/mount.h> +#include <linux/pseudo_fs.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/compat.h> @@@ -104,13 -103,6 +104,6 @@@ #include <net/busy_poll.h> #include <linux/errqueue.h>

- /* proto_ops for ipv4 and ipv6 use the same {recv,send}msg function */ - #if IS_ENABLED(CONFIG_INET) - #define INDIRECT_CALL_INET4(f, f1, ...) INDIRECT_CALL_1(f, f1, __VA_ARGS__) - #else - #define INDIRECT_CALL_INET4(f, f1, ...) f(__VA_ARGS__) - #endif - #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; @@@ -354,22 -346,19 +347,22 @@@ static const struct xattr_handler *sock NULL };

-static struct dentry *sockfs_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *data) +static int sockfs_init_fs_context(struct fs_context *fc) { - return mount_pseudo_xattr(fs_type, "socket:", &sockfs_ops, - sockfs_xattr_handlers, - &sockfs_dentry_operations, SOCKFS_MAGIC); + struct pseudo_fs_context *ctx = init_pseudo(fc, SOCKFS_MAGIC); + if (!ctx) + return -ENOMEM; + ctx->ops = &sockfs_ops; + ctx->dops = &sockfs_dentry_operations; + ctx->xattr = sockfs_xattr_handlers; + return 0; }

static struct vfsmount *sock_mnt __read_mostly;

static struct file_system_type sock_fs_type = { .name = "sockfs", - .mount = sockfs_mount, + .init_fs_context = sockfs_init_fs_context, .kill_sb = kill_anon_super, };

@@@ -433,7 -422,7 +426,7 @@@ static int sock_map_fd(struct socket *s }

newfile = sock_alloc_file(sock, flags, NULL); - if (likely(!IS_ERR(newfile))) { + if (!IS_ERR(newfile)) { fd_install(fd, newfile); return fd; } @@@ -645,10 -634,13 +638,13 @@@ EXPORT_SYMBOL(__sock_tx_timestamp)

INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *, size_t)); + INDIRECT_CALLABLE_DECLARE(int inet6_sendmsg(struct socket *, struct msghdr *, + size_t)); static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) { - int ret = INDIRECT_CALL_INET4(sock->ops->sendmsg, inet_sendmsg, sock, - msg, msg_data_left(msg)); + int ret = INDIRECT_CALL_INET(sock->ops->sendmsg, inet6_sendmsg, + inet_sendmsg, sock, msg, + msg_data_left(msg)); BUG_ON(ret == -EIOCBQUEUED); return ret; } @@@ -874,12 -866,15 +870,15 @@@ void __sock_recv_ts_and_drops(struct ms EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);

INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *, - size_t , int )); + size_t, int)); + INDIRECT_CALLABLE_DECLARE(int inet6_recvmsg(struct socket *, struct msghdr *, + size_t, int)); static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, int flags) { - return INDIRECT_CALL_INET4(sock->ops->recvmsg, inet_recvmsg, sock, msg, - msg_data_left(msg), flags); + return INDIRECT_CALL_INET(sock->ops->recvmsg, inet6_recvmsg, + inet_recvmsg, sock, msg, msg_data_left(msg), + flags); }

/** @@@ -2055,6 -2050,8 +2054,8 @@@ SYSCALL_DEFINE4(recv, int, fd, void __u static int __sys_setsockopt(int fd, int level, int optname, char __user *optval, int optlen) { + mm_segment_t oldfs = get_fs(); + char *kernel_optval = NULL; int err, fput_needed; struct socket *sock;

@@@ -2067,6 -2064,22 +2068,22 @@@ if (err) goto out_put;

+ err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, + &optname, optval, &optlen, + &kernel_optval); + + if (err < 0) { + goto out_put; + } else if (err > 0) { + err = 0; + goto out_put; + } + + if (kernel_optval) { + set_fs(KERNEL_DS); + optval = (char __user __force *)kernel_optval; + } + if (level == SOL_SOCKET) err = sock_setsockopt(sock, level, optname, optval, @@@ -2075,6 -2088,11 +2092,11 @@@ err = sock->ops->setsockopt(sock, level, optname, optval, optlen); + + if (kernel_optval) { + set_fs(oldfs); + kfree(kernel_optval); + } out_put: fput_light(sock->file, fput_needed); } @@@ -2097,6 -2115,7 +2119,7 @@@ static int __sys_getsockopt(int fd, in { int err, fput_needed; struct socket *sock; + int max_optlen;

sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { @@@ -2104,6 -2123,8 +2127,8 @@@ if (err) goto out_put;

+ max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); + if (level == SOL_SOCKET) err = sock_getsockopt(sock, level, optname, optval, @@@ -2112,6 -2133,10 +2137,10 @@@ err = sock->ops->getsockopt(sock, level, optname, optval, optlen); + + err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, + optval, optlen, + max_optlen, err); out_put: fput_light(sock->file, fput_needed); } diff --combined net/tls/tls_device.c index eb8f24f420f0,40076f423dcb..92fd1352c037 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@@ -61,7 -61,7 +61,7 @@@ static void tls_device_free_ctx(struct if (ctx->rx_conf == TLS_HW) kfree(tls_offload_ctx_rx(ctx));

- kfree(ctx); + tls_ctx_free(ctx); }

static void tls_device_gc_task(struct work_struct *work) @@@ -209,6 -209,29 +209,29 @@@ void tls_device_free_resources_tx(struc tls_free_partial_record(sk, tls_ctx); }

+ static void tls_device_resync_tx(struct sock *sk, struct tls_context *tls_ctx, + u32 seq) + { + struct net_device *netdev; + struct sk_buff *skb; + u8 *rcd_sn; + + skb = tcp_write_queue_tail(sk); + if (skb) + TCP_SKB_CB(skb)->eor = 1; + + rcd_sn = tls_ctx->tx.rec_seq; + + down_read(&device_offload_lock); + netdev = tls_ctx->netdev; + if (netdev) + netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn, + TLS_OFFLOAD_CTX_DIR_TX); + up_read(&device_offload_lock); + + clear_bit_unlock(TLS_TX_SYNC_SCHED, &tls_ctx->flags); + } + static void tls_append_frag(struct tls_record_info *record, struct page_frag *pfrag, int size) @@@ -252,7 -275,7 +275,7 @@@ static int tls_push_record(struct sock skb_frag_address(frag), record->len - prot->prepend_size, record_type, - ctx->crypto_send.info.version); + prot->version);

/* HW doesn't care about the data in the tag, because it fills it. */ dummy_tag_frag.page = skb_frag_page(frag); @@@ -264,7 -287,11 +287,11 @@@ list_add_tail(&record->list, &offload_ctx->records_list); spin_unlock_irq(&offload_ctx->lock); offload_ctx->open_record = NULL; - tls_advance_record_sn(sk, &ctx->tx, ctx->crypto_send.info.version); + + if (test_bit(TLS_TX_SYNC_SCHED, &ctx->flags)) + tls_device_resync_tx(sk, ctx, tp->write_seq); + + tls_advance_record_sn(sk, prot, &ctx->tx);

for (i = 0; i < record->num_frags; i++) { frag = &record->frags[i]; @@@ -551,7 -578,7 +578,7 @@@ void tls_device_write_space(struct soc }

static void tls_device_resync_rx(struct tls_context *tls_ctx, - struct sock *sk, u32 seq, u64 rcd_sn) + struct sock *sk, u32 seq, u8 *rcd_sn) { struct net_device *netdev;

@@@ -559,14 -586,17 +586,17 @@@ return; netdev = READ_ONCE(tls_ctx->netdev); if (netdev) - netdev->tlsdev_ops->tls_dev_resync_rx(netdev, sk, seq, rcd_sn); + netdev->tlsdev_ops->tls_dev_resync(netdev, sk, seq, rcd_sn, + TLS_OFFLOAD_CTX_DIR_RX); clear_bit_unlock(TLS_RX_SYNC_RUNNING, &tls_ctx->flags); }

- void handle_device_resync(struct sock *sk, u32 seq, u64 rcd_sn) + void tls_device_rx_resync_new_rec(struct sock *sk, u32 rcd_len, u32 seq) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_offload_context_rx *rx_ctx; + u8 rcd_sn[TLS_MAX_REC_SEQ_SIZE]; + struct tls_prot_info *prot; u32 is_req_pending; s64 resync_req; u32 req_seq; @@@ -574,15 -604,83 +604,83 @@@ if (tls_ctx->rx_conf != TLS_HW) return;

+ prot = &tls_ctx->prot_info; rx_ctx = tls_offload_ctx_rx(tls_ctx); - resync_req = atomic64_read(&rx_ctx->resync_req); - req_seq = (resync_req >> 32) - ((u32)TLS_HEADER_SIZE - 1); - is_req_pending = resync_req; + memcpy(rcd_sn, tls_ctx->rx.rec_seq, prot->rec_seq_size);

- if (unlikely(is_req_pending) && req_seq == seq && - atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0)) { + switch (rx_ctx->resync_type) { + case TLS_OFFLOAD_SYNC_TYPE_DRIVER_REQ: + resync_req = atomic64_read(&rx_ctx->resync_req); + req_seq = resync_req >> 32; seq += TLS_HEADER_SIZE - 1; - tls_device_resync_rx(tls_ctx, sk, seq, rcd_sn); + is_req_pending = resync_req; + + if (likely(!is_req_pending) || req_seq != seq || + !atomic64_try_cmpxchg(&rx_ctx->resync_req, &resync_req, 0)) + return; + break; + case TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT: + if (likely(!rx_ctx->resync_nh_do_now)) + return; + + /* head of next rec is already in, note that the sock_inq will + * include the currently parsed message when called from parser + */ + if (tcp_inq(sk) > rcd_len) + return; + + rx_ctx->resync_nh_do_now = 0; + seq += rcd_len; + tls_bigint_increment(rcd_sn, prot->rec_seq_size); + break; + } + + tls_device_resync_rx(tls_ctx, sk, seq, rcd_sn); + } + + static void tls_device_core_ctrl_rx_resync(struct tls_context *tls_ctx, + struct tls_offload_context_rx *ctx, + struct sock *sk, struct sk_buff *skb) + { + struct strp_msg *rxm; + + /* device will request resyncs by itself based on stream scan */ + if (ctx->resync_type != TLS_OFFLOAD_SYNC_TYPE_CORE_NEXT_HINT) + return; + /* already scheduled */ + if (ctx->resync_nh_do_now) + return; + /* seen decrypted fragments since last fully-failed record */ + if (ctx->resync_nh_reset) { + ctx->resync_nh_reset = 0; + ctx->resync_nh.decrypted_failed = 1; + ctx->resync_nh.decrypted_tgt = TLS_DEVICE_RESYNC_NH_START_IVAL; + return; + } + + if (++ctx->resync_nh.decrypted_failed <= ctx->resync_nh.decrypted_tgt) + return; + + /* doing resync, bump the next target in case it fails */ + if (ctx->resync_nh.decrypted_tgt < TLS_DEVICE_RESYNC_NH_MAX_IVAL) + ctx->resync_nh.decrypted_tgt *= 2; + else + ctx->resync_nh.decrypted_tgt += TLS_DEVICE_RESYNC_NH_MAX_IVAL; + + rxm = strp_msg(skb); + + /* head of next rec is already in, parser will sync for us */ + if (tcp_inq(sk) > rxm->full_len) { + ctx->resync_nh_do_now = 1; + } else { + struct tls_prot_info *prot = &tls_ctx->prot_info; + u8 rcd_sn[TLS_MAX_REC_SEQ_SIZE]; + + memcpy(rcd_sn, tls_ctx->rx.rec_seq, prot->rec_seq_size); + tls_bigint_increment(rcd_sn, prot->rec_seq_size); + + tls_device_resync_rx(tls_ctx, sk, tcp_sk(sk)->copied_seq, + rcd_sn); } }

@@@ -610,8 -708,10 +708,10 @@@ static int tls_device_reencrypt(struct sg_set_buf(&sg[0], buf, rxm->full_len + TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE); - skb_copy_bits(skb, offset, buf, - TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE); + err = skb_copy_bits(skb, offset, buf, + TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE); + if (err) + goto free_buf;

/* We are interested only in the decrypted data not the auth */ err = decrypt_skb(sk, skb, sg); @@@ -625,8 -725,11 +725,11 @@@ if (skb_pagelen(skb) > offset) { copy = min_t(int, skb_pagelen(skb) - offset, data_len);

- if (skb->decrypted) - skb_store_bits(skb, offset, buf, copy); + if (skb->decrypted) { + err = skb_store_bits(skb, offset, buf, copy); + if (err) + goto free_buf; + }

offset += copy; buf += copy; @@@ -649,8 -752,11 +752,11 @@@ copy = min_t(int, skb_iter->len - frag_pos, data_len + rxm->offset - offset);

- if (skb_iter->decrypted) - skb_store_bits(skb_iter, frag_pos, buf, copy); + if (skb_iter->decrypted) { + err = skb_store_bits(skb_iter, frag_pos, buf, copy); + if (err) + goto free_buf; + }

offset += copy; buf += copy; @@@ -671,10 -777,6 +777,6 @@@ int tls_device_decrypted(struct sock *s int is_encrypted = !is_decrypted; struct sk_buff *skb_iter;

- /* Skip if it is already decrypted */ - if (ctx->sw.decrypted) - return 0; - /* Check if all the data is decrypted already */ skb_walk_frags(skb, skb_iter) { is_decrypted &= skb_iter->decrypted; @@@ -683,12 -785,21 +785,21 @@@

ctx->sw.decrypted |= is_decrypted;

- /* Return immedeatly if the record is either entirely plaintext or + /* Return immediately if the record is either entirely plaintext or * entirely ciphertext. Otherwise handle reencrypt partially decrypted * record. */ - return (is_encrypted || is_decrypted) ? 0 : - tls_device_reencrypt(sk, skb); + if (is_decrypted) { + ctx->resync_nh_reset = 1; + return 0; + } + if (is_encrypted) { + tls_device_core_ctrl_rx_resync(tls_ctx, ctx, sk, skb); + return 0; + } + + ctx->resync_nh_reset = 1; + return tls_device_reencrypt(sk, skb); }

static void tls_device_attach(struct tls_context *ctx, struct sock *sk, @@@ -742,11 -853,6 +853,11 @@@ int tls_set_device_offload(struct sock }

crypto_info = &ctx->crypto_send.info; + if (crypto_info->version != TLS_1_2_VERSION) { + rc = -EOPNOTSUPP; + goto free_offload_ctx; + } + switch (crypto_info->cipher_type) { case TLS_CIPHER_AES_GCM_128: nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; @@@ -762,6 -868,12 +873,12 @@@ goto free_offload_ctx; }

+ /* Sanity-check the rec_seq_size for stack allocations */ + if (rec_seq_size > TLS_MAX_REC_SEQ_SIZE) { + rc = -EINVAL; + goto free_offload_ctx; + } + prot->prepend_size = TLS_HEADER_SIZE + nonce_size; prot->tag_size = tag_size; prot->overhead_size = prot->prepend_size + prot->tag_size; @@@ -881,9 -993,6 +998,9 @@@ int tls_set_device_offload_rx(struct so struct net_device *netdev; int rc = 0;

+ if (ctx->crypto_recv.info.version != TLS_1_2_VERSION) + return -EOPNOTSUPP; + /* We support starting offload on multiple sockets * concurrently, so we only need a read lock here. * This lock must precede get_netdev_for_sock to prevent races between @@@ -916,6 -1025,7 +1033,7 @@@ rc = -ENOMEM; goto release_netdev; } + context->resync_nh_reset = 1;

ctx->priv_ctx_rx = context; rc = tls_set_sw_offload(sk, ctx, 0); @@@ -1023,7 -1133,7 +1141,7 @@@ static int tls_dev_event(struct notifie case NETDEV_REGISTER: case NETDEV_FEAT_CHANGE: if ((dev->features & NETIF_F_HW_TLS_RX) && - !dev->tlsdev_ops->tls_dev_resync_rx) + !dev->tlsdev_ops->tls_dev_resync) return NOTIFY_BAD;

if (dev->tlsdev_ops && diff --combined net/tls/tls_sw.c index e2385183526e,db585964b52b..53b4ad94e74a --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@@ -534,7 -534,7 +534,7 @@@ static int tls_do_encryption(struct soc

/* Unhook the record from context if encryption is not failure */ ctx->open_rec = NULL; - tls_advance_record_sn(sk, &tls_ctx->tx, prot->version); + tls_advance_record_sn(sk, prot, &tls_ctx->tx); return rc; }

@@@ -1485,15 -1485,16 +1485,16 @@@ static int decrypt_skb_update(struct so struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct tls_prot_info *prot = &tls_ctx->prot_info; - int version = prot->version; struct strp_msg *rxm = strp_msg(skb); int pad, err = 0;

if (!ctx->decrypted) { #ifdef CONFIG_TLS_DEVICE - err = tls_device_decrypted(sk, skb); - if (err < 0) - return err; + if (tls_ctx->rx_conf == TLS_HW) { + err = tls_device_decrypted(sk, skb); + if (err < 0) + return err; + } #endif /* Still not decrypted after tls_device */ if (!ctx->decrypted) { @@@ -1501,8 -1502,8 +1502,8 @@@ async); if (err < 0) { if (err == -EINPROGRESS) - tls_advance_record_sn(sk, &tls_ctx->rx, - version); + tls_advance_record_sn(sk, prot, + &tls_ctx->rx);

return err; } @@@ -1517,7 -1518,7 +1518,7 @@@ rxm->full_len -= pad; rxm->offset += prot->prepend_size; rxm->full_len -= prot->overhead_size; - tls_advance_record_sn(sk, &tls_ctx->rx, version); + tls_advance_record_sn(sk, prot, &tls_ctx->rx); ctx->decrypted = true; ctx->saved_data_ready(sk); } else { @@@ -1958,8 -1959,7 +1959,8 @@@ bool tls_sw_stream_read(const struct so ingress_empty = list_empty(&psock->ingress_msg); rcu_read_unlock();

- return !ingress_empty || ctx->recv_pkt; + return !ingress_empty || ctx->recv_pkt || + !skb_queue_empty(&ctx->rx_list); }

static int tls_read_size(struct strparser *strp, struct sk_buff *skb) @@@ -2014,8 -2014,8 +2015,8 @@@ goto read_failure; } #ifdef CONFIG_TLS_DEVICE - handle_device_resync(strp->sk, TCP_SKB_CB(skb)->seq + rxm->offset, - *(u64*)tls_ctx->rx.rec_seq); + tls_device_rx_resync_new_rec(strp->sk, data_len + TLS_HEADER_SIZE, + TCP_SKB_CB(skb)->seq + rxm->offset); #endif return data_len + TLS_HEADER_SIZE;

@@@ -2282,8 -2282,9 +2283,9 @@@ int tls_set_sw_offload(struct sock *sk goto free_priv; }

- /* Sanity-check the IV size for stack allocations. */ - if (iv_size > MAX_IV_SIZE || nonce_size > MAX_IV_SIZE) { + /* Sanity-check the sizes for stack allocations. */ + if (iv_size > MAX_IV_SIZE || nonce_size > MAX_IV_SIZE || + rec_seq_size > TLS_MAX_REC_SEQ_SIZE) { rc = -EINVAL; goto free_priv; } diff --combined net/xdp/xsk.c index f53a6ef7c155,74417a851ed5..ada385a89cc3 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@@ -37,6 -37,12 +37,12 @@@ bool xsk_is_setup_for_bpf_map(struct xd READ_ONCE(xs->umem->fq); }

+ bool xsk_umem_has_addrs(struct xdp_umem *umem, u32 cnt) + { + return xskq_has_addrs(umem->fq, cnt); + } + EXPORT_SYMBOL(xsk_umem_has_addrs); + u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr) { return xskq_peek_addr(umem->fq, addr); @@@ -166,22 -172,18 +172,18 @@@ void xsk_umem_consume_tx_done(struct xd } EXPORT_SYMBOL(xsk_umem_consume_tx_done);

- bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len) + bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc) { - struct xdp_desc desc; struct xdp_sock *xs;

rcu_read_lock(); list_for_each_entry_rcu(xs, &umem->xsk_list, list) { - if (!xskq_peek_desc(xs->tx, &desc)) + if (!xskq_peek_desc(xs->tx, desc)) continue;

- if (xskq_produce_addr_lazy(umem->cq, desc.addr)) + if (xskq_produce_addr_lazy(umem->cq, desc->addr)) goto out;

- *dma = xdp_umem_get_dma(umem, desc.addr); - *len = desc.len; - xskq_discard_desc(xs->tx); rcu_read_unlock(); return true; @@@ -335,22 -337,6 +337,22 @@@ static int xsk_init_queue(u32 entries, return 0; }

+static void xsk_unbind_dev(struct xdp_sock *xs) +{ + struct net_device *dev = xs->dev; + + if (!dev || xs->state != XSK_BOUND) + return; + + xs->state = XSK_UNBOUND; + + /* Wait for driver to stop using the xdp socket. */ + xdp_del_sk_umem(xs->umem, xs); + xs->dev = NULL; + synchronize_net(); + dev_put(dev); +} + static int xsk_release(struct socket *sock) { struct sock *sk = sock->sk; @@@ -370,7 -356,15 +372,7 @@@ sock_prot_inuse_add(net, sk->sk_prot, -1); local_bh_enable();

- if (xs->dev) { - struct net_device *dev = xs->dev; - - /* Wait for driver to stop using the xdp socket. */ - xdp_del_sk_umem(xs->umem, xs); - xs->dev = NULL; - synchronize_net(); - dev_put(dev); - } + xsk_unbind_dev(xs);

xskq_destroy(xs->rx); xskq_destroy(xs->tx); @@@ -420,7 -414,7 +422,7 @@@ static int xsk_bind(struct socket *sock return -EINVAL;

mutex_lock(&xs->mutex); - if (xs->dev) { + if (xs->state != XSK_READY) { err = -EBUSY; goto out_release; } @@@ -500,8 -494,6 +502,8 @@@ out_unlock: if (err) dev_put(dev); + else + xs->state = XSK_BOUND; out_release: mutex_unlock(&xs->mutex); return err; @@@ -530,10 -522,6 +532,10 @@@ static int xsk_setsockopt(struct socke return -EFAULT;

mutex_lock(&xs->mutex); + if (xs->state != XSK_READY) { + mutex_unlock(&xs->mutex); + return -EBUSY; + } q = (optname == XDP_TX_RING) ? &xs->tx : &xs->rx; err = xsk_init_queue(entries, q, false); mutex_unlock(&xs->mutex); @@@ -548,7 -536,7 +550,7 @@@ return -EFAULT;

mutex_lock(&xs->mutex); - if (xs->umem) { + if (xs->state != XSK_READY || xs->umem) { mutex_unlock(&xs->mutex); return -EBUSY; } @@@ -575,10 -563,6 +577,10 @@@ return -EFAULT;

mutex_lock(&xs->mutex); + if (xs->state != XSK_READY) { + mutex_unlock(&xs->mutex); + return -EBUSY; + } if (!xs->umem) { mutex_unlock(&xs->mutex); return -EINVAL; @@@ -662,6 -646,26 +664,26 @@@ static int xsk_getsockopt(struct socke

return 0; } + case XDP_OPTIONS: + { + struct xdp_options opts = {}; + + if (len < sizeof(opts)) + return -EINVAL; + + mutex_lock(&xs->mutex); + if (xs->zc) + opts.flags |= XDP_OPTIONS_ZEROCOPY; + mutex_unlock(&xs->mutex); + + len = sizeof(opts); + if (copy_to_user(optval, &opts, len)) + return -EFAULT; + if (put_user(len, optlen)) + return -EFAULT; + + return 0; + } default: break; } @@@ -680,9 -684,6 +702,9 @@@ static int xsk_mmap(struct file *file, unsigned long pfn; struct page *qpg;

+ if (xs->state != XSK_READY) + return -EBUSY; + if (offset == XDP_PGOFF_RX_RING) { q = READ_ONCE(xs->rx); } else if (offset == XDP_PGOFF_TX_RING) { @@@ -714,38 -715,6 +736,38 @@@ size, vma->vm_page_prot); }

+static int xsk_notifier(struct notifier_block *this, + unsigned long msg, void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct net *net = dev_net(dev); + struct sock *sk; + + switch (msg) { + case NETDEV_UNREGISTER: + mutex_lock(&net->xdp.lock); + sk_for_each(sk, &net->xdp.list) { + struct xdp_sock *xs = xdp_sk(sk); + + mutex_lock(&xs->mutex); + if (xs->dev == dev) { + sk->sk_err = ENETDOWN; + if (!sock_flag(sk, SOCK_DEAD)) + sk->sk_error_report(sk); + + xsk_unbind_dev(xs); + + /* Clear device references in umem. */ + xdp_umem_clear_dev(xs->umem); + } + mutex_unlock(&xs->mutex); + } + mutex_unlock(&net->xdp.lock); + break; + } + return NOTIFY_DONE; +} + static struct proto xsk_proto = { .name = "XDP", .owner = THIS_MODULE, @@@ -817,7 -786,6 +839,7 @@@ static int xsk_create(struct net *net, sock_set_flag(sk, SOCK_RCU_FREE);

xs = xdp_sk(sk); + xs->state = XSK_READY; mutex_init(&xs->mutex); spin_lock_init(&xs->tx_completion_lock);

@@@ -838,10 -806,6 +860,10 @@@ static const struct net_proto_family xs .owner = THIS_MODULE, };

+static struct notifier_block xsk_netdev_notifier = { + .notifier_call = xsk_notifier, +}; + static int __net_init xsk_net_init(struct net *net) { mutex_init(&net->xdp.lock); @@@ -874,15 -838,8 +896,15 @@@ static int __init xsk_init(void err = register_pernet_subsys(&xsk_net_ops); if (err) goto out_sk; + + err = register_netdevice_notifier(&xsk_netdev_notifier); + if (err) + goto out_pernet; + return 0;

+out_pernet: + unregister_pernet_subsys(&xsk_net_ops); out_sk: sock_unregister(PF_XDP); out_proto: diff --combined net/xdp/xsk_queue.h index cba4a640d5e8,12b49784a6d5..909c5168ed0f --- a/net/xdp/xsk_queue.h +++ b/net/xdp/xsk_queue.h @@@ -117,6 -117,20 +117,20 @@@ static inline u32 xskq_nb_free(struct x return q->nentries - (producer - q->cons_tail); }

+ static inline bool xskq_has_addrs(struct xsk_queue *q, u32 cnt) + { + u32 entries = q->prod_tail - q->cons_tail; + + if (entries >= cnt) + return true; + + /* Refresh the local pointer. */ + q->prod_tail = READ_ONCE(q->ring->producer); + entries = q->prod_tail - q->cons_tail; + + return entries >= cnt; + } + /* UMEM queue */

static inline bool xskq_is_valid_addr(struct xsk_queue *q, u64 addr) @@@ -288,7 -302,7 +302,7 @@@ static inline void xskq_produce_flush_d /* Order producer and data */ smp_wmb(); /* B, matches C */

- q->prod_tail = q->prod_head, + q->prod_tail = q->prod_head; WRITE_ONCE(q->ring->producer, q->prod_tail); }

diff --combined net/xfrm/xfrm_interface.c index 7dbe0c608df5,f8eb9e342173..74868f9d81fb --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@@ -133,7 -133,7 +133,7 @@@ static void xfrmi_dev_free(struct net_d free_percpu(dev->tstats); }

-static int xfrmi_create2(struct net_device *dev) +static int xfrmi_create(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net *net = dev_net(dev); @@@ -156,7 -156,54 +156,7 @@@ out return err; }

-static struct xfrm_if *xfrmi_create(struct net *net, struct xfrm_if_parms *p) -{ - struct net_device *dev; - struct xfrm_if *xi; - char name[IFNAMSIZ]; - int err; - - if (p->name[0]) { - strlcpy(name, p->name, IFNAMSIZ); - } else { - err = -EINVAL; - goto failed; - } - - dev = alloc_netdev(sizeof(*xi), name, NET_NAME_UNKNOWN, xfrmi_dev_setup); - if (!dev) { - err = -EAGAIN; - goto failed; - } - - dev_net_set(dev, net); - - xi = netdev_priv(dev); - xi->p = *p; - xi->net = net; - xi->dev = dev; - xi->phydev = dev_get_by_index(net, p->link); - if (!xi->phydev) { - err = -ENODEV; - goto failed_free; - } - - err = xfrmi_create2(dev); - if (err < 0) - goto failed_dev_put; - - return xi; - -failed_dev_put: - dev_put(xi->phydev); -failed_free: - free_netdev(dev); -failed: - return ERR_PTR(err); -} - -static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p, - int create) +static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p) { struct xfrm_if __rcu **xip; struct xfrm_if *xi; @@@ -164,11 -211,17 +164,11 @@@

for (xip = &xfrmn->xfrmi[0]; (xi = rtnl_dereference(*xip)) != NULL; - xip = &xi->next) { - if (xi->p.if_id == p->if_id) { - if (create) - return ERR_PTR(-EEXIST); - + xip = &xi->next) + if (xi->p.if_id == p->if_id) return xi; - } - } - if (!create) - return ERR_PTR(-ENODEV); - return xfrmi_create(net, p); + + return NULL; }

static void xfrmi_dev_uninit(struct net_device *dev) @@@ -633,33 -686,21 +633,33 @@@ static int xfrmi_newlink(struct net *sr struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); - struct xfrm_if_parms *p; + struct xfrm_if_parms p; struct xfrm_if *xi; + int err;

- xi = netdev_priv(dev); - p = &xi->p; - - xfrmi_netlink_parms(data, p); + xfrmi_netlink_parms(data, &p);

if (!tb[IFLA_IFNAME]) return -EINVAL;

- nla_strlcpy(p->name, tb[IFLA_IFNAME], IFNAMSIZ); + nla_strlcpy(p.name, tb[IFLA_IFNAME], IFNAMSIZ);

- xi = xfrmi_locate(net, p, 1); - return PTR_ERR_OR_ZERO(xi); + xi = xfrmi_locate(net, &p); + if (xi) + return -EEXIST; + + xi = netdev_priv(dev); + xi->p = p; + xi->net = net; + xi->dev = dev; + xi->phydev = dev_get_by_index(net, p.link); + if (!xi->phydev) + return -ENODEV; + + err = xfrmi_create(dev); + if (err < 0) + dev_put(xi->phydev); + return err; }

static void xfrmi_dellink(struct net_device *dev, struct list_head *head) @@@ -676,8 -717,9 +676,8 @@@ static int xfrmi_changelink(struct net_

xfrmi_netlink_parms(data, &xi->p);

- xi = xfrmi_locate(net, &xi->p, 0); - - if (IS_ERR_OR_NULL(xi)) { + xi = xfrmi_locate(net, &xi->p); + if (!xi) { xi = netdev_priv(dev); } else { if (xi->dev != dev) @@@ -751,11 -793,6 +751,6 @@@ static void __net_exit xfrmi_destroy_in unregister_netdevice_many(&list); }

- static int __net_init xfrmi_init_net(struct net *net) - { - return 0; - } - static void __net_exit xfrmi_exit_net(struct net *net) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); @@@ -766,7 -803,6 +761,6 @@@ }

static struct pernet_operations xfrmi_net_ops = { - .init = xfrmi_init_net, .exit = xfrmi_exit_net, .id = &xfrmi_net_id, .size = sizeof(struct xfrmi_net), diff --combined net/xfrm/xfrm_policy.c index 4fb58dfecc7a,1070dfece76b..8ca637a72697 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@@ -585,6 -585,9 +585,6 @@@ static void xfrm_bydst_resize(struct ne odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock));

- odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, - lockdep_is_held(&net->xfrm.xfrm_policy_lock)); - for (i = hmask; i >= 0; i--) xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir);

@@@ -1277,17 -1280,13 +1277,17 @@@ static void xfrm_hash_rebuild(struct wo

hlist_for_each_entry_safe(policy, n, &net->xfrm.policy_inexact[dir], - bydst_inexact_list) + bydst_inexact_list) { + hlist_del_rcu(&policy->bydst); hlist_del_init(&policy->bydst_inexact_list); + }

hmask = net->xfrm.policy_bydst[dir].hmask; odst = net->xfrm.policy_bydst[dir].table; - for (i = hmask; i >= 0; i--) - INIT_HLIST_HEAD(odst + i); + for (i = hmask; i >= 0; i--) { + hlist_for_each_entry_safe(policy, n, odst + i, bydst) + hlist_del_rcu(&policy->bydst); + } if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { /* dir out => dst = remote, src = local */ net->xfrm.policy_bydst[dir].dbits4 = rbits4; @@@ -1316,6 -1315,8 +1316,6 @@@ chain = policy_hash_bysel(net, &policy->selector, policy->family, dir);

- hlist_del_rcu(&policy->bydst); - if (!chain) { void *p = xfrm_policy_inexact_insert(policy, dir, 0);

@@@ -3627,7 -3628,7 +3627,7 @@@ int __xfrm_policy_check(struct sock *sk } xfrm_nr = ti; if (npols > 1) { - xfrm_tmpl_sort(stp, tpp, xfrm_nr, family, net); + xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); tpp = stp; }

diff --combined samples/bpf/xdp_redirect_user.c index 003c0c6e38c5,39de06f3ec25..5440cd620607 --- a/samples/bpf/xdp_redirect_user.c +++ b/samples/bpf/xdp_redirect_user.c @@@ -10,13 -10,14 +10,14 @@@ #include <stdlib.h> #include <stdbool.h> #include <string.h> + #include <net/if.h> #include <unistd.h> #include <libgen.h> #include <sys/resource.h>

#include "bpf_util.h" #include <bpf/bpf.h> - #include "bpf/libbpf.h" + #include "libbpf.h"

static int ifindex_in; static int ifindex_out; @@@ -85,7 -86,7 +86,7 @@@ static void poll_stats(int interval, in static void usage(const char *prog) { fprintf(stderr, - "usage: %s [OPTS] IFINDEX_IN IFINDEX_OUT\n\n" + "usage: %s [OPTS] <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n\n" "OPTS:\n" " -S use skb-mode\n" " -N enforce native mode\n" @@@ -128,7 -129,7 +129,7 @@@ int main(int argc, char **argv }

if (optind == argc) { - printf("usage: %s IFINDEX_IN IFINDEX_OUT\n", argv[0]); + printf("usage: %s <IFNAME|IFINDEX>_IN <IFNAME|IFINDEX>_OUT\n", argv[0]); return 1; }

@@@ -137,8 -138,14 +138,14 @@@ return 1; }

- ifindex_in = strtoul(argv[optind], NULL, 0); - ifindex_out = strtoul(argv[optind + 1], NULL, 0); + ifindex_in = if_nametoindex(argv[optind]); + if (!ifindex_in) + ifindex_in = strtoul(argv[optind], NULL, 0); + + ifindex_out = if_nametoindex(argv[optind + 1]); + if (!ifindex_out) + ifindex_out = strtoul(argv[optind + 1], NULL, 0); + printf("input: %d output: %d\n", ifindex_in, ifindex_out);

snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); @@@ -189,7 -196,7 +196,7 @@@ }

memset(&info, 0, sizeof(info)); - ret = bpf_obj_get_info_by_fd(prog_fd, &info, &info_len); + ret = bpf_obj_get_info_by_fd(dummy_prog_fd, &info, &info_len); if (ret) { printf("can't get prog info - %s\n", strerror(errno)); return ret; diff --combined tools/bpf/bpftool/cgroup.c index a13fb7265d1a,390b89a224f1..f3c05b08c68c --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@@ -26,7 -26,8 +26,8 @@@ " sock_ops | device | bind4 | bind6 |\n" \ " post_bind4 | post_bind6 | connect4 |\n" \ " connect6 | sendmsg4 | sendmsg6 |\n" \ - " recvmsg4 | recvmsg6 | sysctl }" + " recvmsg4 | recvmsg6 | sysctl |\n" \ + " getsockopt | setsockopt }"

static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", @@@ -45,6 -46,8 +46,8 @@@ [BPF_CGROUP_SYSCTL] = "sysctl", [BPF_CGROUP_UDP4_RECVMSG] = "recvmsg4", [BPF_CGROUP_UDP6_RECVMSG] = "recvmsg6", + [BPF_CGROUP_GETSOCKOPT] = "getsockopt", + [BPF_CGROUP_SETSOCKOPT] = "setsockopt", [__MAX_BPF_ATTACH_TYPE] = NULL, };

@@@ -168,7 -171,7 +171,7 @@@ static int do_show(int argc, char **arg

cgroup_fd = open(argv[0], O_RDONLY); if (cgroup_fd < 0) { - p_err("can't open cgroup %s", argv[1]); + p_err("can't open cgroup %s", argv[0]); goto exit; }

@@@ -356,7 -359,7 +359,7 @@@ static int do_attach(int argc, char **a

cgroup_fd = open(argv[0], O_RDONLY); if (cgroup_fd < 0) { - p_err("can't open cgroup %s", argv[1]); + p_err("can't open cgroup %s", argv[0]); goto exit; }

@@@ -414,7 -417,7 +417,7 @@@ static int do_detach(int argc, char **a

cgroup_fd = open(argv[0], O_RDONLY); if (cgroup_fd < 0) { - p_err("can't open cgroup %s", argv[1]); + p_err("can't open cgroup %s", argv[0]); goto exit; }

diff --combined tools/include/uapi/linux/bpf.h index 29a5bc3d5c66,cecf42c871d4..387d28252af6 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@@ -170,6 -170,7 +170,7 @@@ enum bpf_prog_type BPF_PROG_TYPE_FLOW_DISSECTOR, BPF_PROG_TYPE_CGROUP_SYSCTL, BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, + BPF_PROG_TYPE_CGROUP_SOCKOPT, };

enum bpf_attach_type { @@@ -194,6 -195,8 +195,8 @@@ BPF_CGROUP_SYSCTL, BPF_CGROUP_UDP4_RECVMSG, BPF_CGROUP_UDP6_RECVMSG, + BPF_CGROUP_GETSOCKOPT, + BPF_CGROUP_SETSOCKOPT, __MAX_BPF_ATTACH_TYPE };

@@@ -262,6 -265,24 +265,24 @@@ */ #define BPF_F_ANY_ALIGNMENT (1U << 1)

+ /* BPF_F_TEST_RND_HI32 is used in BPF_PROG_LOAD command for testing purpose. + * Verifier does sub-register def/use analysis and identifies instructions whose + * def only matters for low 32-bit, high 32-bit is never referenced later + * through implicit zero extension. Therefore verifier notifies JIT back-ends + * that it is safe to ignore clearing high 32-bit for these instructions. This + * saves some back-ends a lot of code-gen. However such optimization is not + * necessary on some arches, for example x86_64, arm64 etc, whose JIT back-ends + * hence hasn't used verifier's analysis result. But, we really want to have a + * way to be able to verify the correctness of the described optimization on + * x86_64 on which testsuites are frequently exercised. + * + * So, this flag is introduced. Once it is set, verifier will randomize high + * 32-bit for those instructions who has been identified as safe to ignore them. + * Then, if verifier is not doing correct analysis, such randomization will + * regress tests to expose bugs. + */ + #define BPF_F_TEST_RND_HI32 (1U << 2) + /* When BPF ldimm64's insn[0].src_reg != 0 then this can have * two extensions: * @@@ -1746,6 -1767,7 +1767,7 @@@ union bpf_attr * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * * **BPF_SOCK_OPS_RTT_CB_FLAG** (every RTT) * * Therefore, this function can be used to clear a callback flag by * setting the appropriate bit to zero. e.g. to disable the RTO @@@ -2674,6 -2696,20 +2696,20 @@@ * 0 on success. * * **-ENOENT** if the bpf-local-storage cannot be found. + * + * int bpf_send_signal(u32 sig) + * Description + * Send signal *sig* to the current task. + * Return + * 0 on success or successfully queued. + * + * **-EBUSY** if work queue under nmi is full. + * + * **-EINVAL** if *sig* is invalid. + * + * **-EPERM** if no permission to send the *sig*. + * + * **-EAGAIN** if bpf program can try again. */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@@ -2784,7 -2820,8 +2820,8 @@@ FN(strtol), \ FN(strtoul), \ FN(sk_storage_get), \ - FN(sk_storage_delete), + FN(sk_storage_delete), \ + FN(send_signal),

/* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@@ -3033,6 -3070,12 +3070,12 @@@ struct bpf_tcp_sock * sum(delta(snd_una)), or how many bytes * were acked. */ + __u32 dsack_dups; /* RFC4898 tcpEStatsStackDSACKDups + * total number of DSACK blocks received + */ + __u32 delivered; /* Total data packets delivered incl. rexmits */ + __u32 delivered_ce; /* Like the above but only ECE marked packets */ + __u32 icsk_retransmits; /* Number of unrecovered [RTO] timeouts */ };

struct bpf_sock_tuple { @@@ -3052,6 -3095,10 +3095,10 @@@ }; };

+ struct bpf_xdp_sock { + __u32 queue_id; + }; + #define XDP_PACKET_HEADROOM 256

/* User return codes for XDP prog type. @@@ -3143,7 -3190,6 +3190,7 @@@ struct bpf_prog_info char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; __u32 gpl_compatible:1; + __u32 :31; /* alignment pad */ __u64 netns_dev; __u64 netns_ino; __u32 nr_jited_ksyms; @@@ -3213,6 -3259,7 +3260,7 @@@ struct bpf_sock_addr __u32 msg_src_ip6[4]; /* Allows 1,2,4-byte read an 4-byte write. * Stored in network byte order. */ + __bpf_md_ptr(struct bpf_sock *, sk); };

/* User bpf_sock_ops struct to access socket values and specify request ops @@@ -3264,13 -3311,15 +3312,15 @@@ struct bpf_sock_ops __u32 sk_txhash; __u64 bytes_received; __u64 bytes_acked; + __bpf_md_ptr(struct bpf_sock *, sk); };

/* Definitions for bpf_sock_ops_cb_flags */ #define BPF_SOCK_OPS_RTO_CB_FLAG (1<<0) #define BPF_SOCK_OPS_RETRANS_CB_FLAG (1<<1) #define BPF_SOCK_OPS_STATE_CB_FLAG (1<<2) - #define BPF_SOCK_OPS_ALL_CB_FLAGS 0x7 /* Mask of all currently + #define BPF_SOCK_OPS_RTT_CB_FLAG (1<<3) + #define BPF_SOCK_OPS_ALL_CB_FLAGS 0xF /* Mask of all currently * supported cb flags */

@@@ -3325,6 -3374,8 +3375,8 @@@ enum BPF_SOCK_OPS_TCP_LISTEN_CB, /* Called on listen(2), right after * socket transition to LISTEN state. */ + BPF_SOCK_OPS_RTT_CB, /* Called on every RTT. + */ };

/* List of TCP states. There is a build check in net/ipv4/tcp.c to detect @@@ -3503,4 -3554,15 +3555,15 @@@ struct bpf_sysctl */ };

+ struct bpf_sockopt { + __bpf_md_ptr(struct bpf_sock *, sk); + __bpf_md_ptr(void *, optval); + __bpf_md_ptr(void *, optval_end); + + __s32 level; + __s32 optname; + __s32 optlen; + __s32 retval; + }; + #endif /* _UAPI__LINUX_BPF_H__ */ diff --combined tools/testing/selftests/bpf/progs/test_lwt_seg6local.c index e2f6ed0a583d,7c7cb3177463..a334a0e882e4 --- a/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c +++ b/tools/testing/selftests/bpf/progs/test_lwt_seg6local.c @@@ -6,13 -6,6 +6,6 @@@ #include "bpf_helpers.h" #include "bpf_endian.h"

- #define bpf_printk(fmt, ...) \ - ({ \ - char ____fmt[] = fmt; \ - bpf_trace_printk(____fmt, sizeof(____fmt), \ - ##__VA_ARGS__); \ - }) - /* Packet parsing state machine helpers. */ #define cursor_advance(_cursor, _len) \ ({ void *_tmp = _cursor; _cursor += _len; _tmp; }) @@@ -61,7 -54,7 +54,7 @@@ struct sr6_tlv_t unsigned char value[0]; } BPF_PACKET_HEADER;

-__attribute__((always_inline)) struct ip6_srh_t *get_srh(struct __sk_buff *skb) +static __always_inline struct ip6_srh_t *get_srh(struct __sk_buff *skb) { void *cursor, *data_end; struct ip6_srh_t *srh; @@@ -95,7 -88,7 +88,7 @@@ return srh; }

-__attribute__((always_inline)) +static __always_inline int update_tlv_pad(struct __sk_buff *skb, uint32_t new_pad, uint32_t old_pad, uint32_t pad_off) { @@@ -125,7 -118,7 +118,7 @@@ return 0; }

-__attribute__((always_inline)) +static __always_inline int is_valid_tlv_boundary(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t *tlv_off, uint32_t *pad_size, uint32_t *pad_off) @@@ -184,7 -177,7 +177,7 @@@ return 0; }

-__attribute__((always_inline)) +static __always_inline int add_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off, struct sr6_tlv_t *itlv, uint8_t tlv_size) { @@@ -228,7 -221,7 +221,7 @@@ return update_tlv_pad(skb, new_pad, pad_size, pad_off); }

-__attribute__((always_inline)) +static __always_inline int delete_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh, uint32_t tlv_off) { @@@ -266,7 -259,7 +259,7 @@@ return update_tlv_pad(skb, new_pad, pad_size, pad_off); }

-__attribute__((always_inline)) +static __always_inline int has_egr_tlv(struct __sk_buff *skb, struct ip6_srh_t *srh) { int tlv_offset = sizeof(struct ip6_t) + sizeof(struct ip6_srh_t) + diff --combined tools/testing/selftests/net/config index 3dea2cba2325,e4b878d95ba0..d98a17fc0837 --- a/tools/testing/selftests/net/config +++ b/tools/testing/selftests/net/config @@@ -25,4 -25,6 +25,7 @@@ CONFIG_NF_TABLES_IPV6= CONFIG_NF_TABLES_IPV4=y CONFIG_NFT_CHAIN_NAT_IPV6=m CONFIG_NFT_CHAIN_NAT_IPV4=m +CONFIG_KALLSYMS=y + CONFIG_NET_SCH_FQ=m + CONFIG_NET_SCH_ETF=m + CONFIG_TEST_BLACKHOLE_DEV=m diff --combined tools/testing/selftests/tc-testing/tc-tests/filters/tests.json index 16559c436f21,8135778040c2..0f89cd50a94b --- a/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json +++ b/tools/testing/selftests/tc-testing/tc-tests/filters/tests.json @@@ -6,6 -6,9 +6,9 @@@ "filter", "u32" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 ingress" ], @@@ -25,6 -28,9 +28,9 @@@ "filter", "matchall" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV1 clsact", "$TC filter add dev $DEV1 protocol all pref 1 ingress handle 0x1234 matchall action ok" @@@ -39,31 -45,15 +45,34 @@@ ] }, { + "id": "2ff3", + "name": "Add flower with max handle and then dump it", + "category": [ + "filter", + "flower" + ], + "setup": [ + "$TC qdisc add dev $DEV2 ingress" + ], + "cmdUnderTest": "$TC filter add dev $DEV2 protocol ip pref 1 parent ffff: handle 0xffffffff flower action ok", + "expExitCode": "0", + "verifyCmd": "$TC filter show dev $DEV2 ingress", + "matchPattern": "filter protocol ip pref 1 flower.*handle 0xffffffff", + "matchCount": "1", + "teardown": [ + "$TC qdisc del dev $DEV2 ingress" + ] + }, + { "id": "d052", "name": "Add 1M filters with the same action", "category": [ "filter", "flower" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV2 ingress", "./tdc_batch.py $DEV2 $BATCH_FILE --share_action -n 1000000" @@@ -85,6 -75,9 +94,9 @@@ "filter", "flower" ], + "plugins": { + "requires": "nsPlugin" + }, "setup": [ "$TC qdisc add dev $DEV2 ingress", "$TC filter add dev $DEV2 protocol ip prio 1 parent ffff: flower dst_mac e4:11:22:11:4a:51 src_mac e4:11:22:11:4a:50 ip_proto tcp src_ip 1.1.1.1 dst_ip 2.2.2.2 action drop"