The following commit has been merged in the master branch: commit 964717e26727513d69e4ffce1c252a86a43dbcdc Merge: a8d0d3eba784fcbf6d7442a2d478423d34361930 0c3b34d804947fef7fb9e74912b7b7563729231e Author: Stephen Rothwell sfr@canb.auug.org.au Date: Tue Jan 9 11:20:44 2018 +1100

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

diff --combined MAINTAINERS index 6809623840de,753799d24cd9..f8b0299bfe08 --- a/MAINTAINERS +++ b/MAINTAINERS @@@ -321,7 -321,7 +321,7 @@@ F: drivers/acpi/apei

ACPI COMPONENT ARCHITECTURE (ACPICA) M: Robert Moore robert.moore@intel.com -M: Lv Zheng lv.zheng@intel.com +M: Erik Schmauss erik.schmauss@intel.com M: "Rafael J. Wysocki" rafael.j.wysocki@intel.com L: linux-acpi@vger.kernel.org L: devel@acpica.org @@@ -1255,12 -1255,6 +1255,12 @@@ L: linux-arm-kernel@lists.infradead.or S: Supported F: drivers/net/ethernet/cavium/thunder/

+ARM/CIRRUS LOGIC BK3 MACHINE SUPPORT +M: Lukasz Majewski lukma@denx.de +L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) +S: Maintained +F: arch/arm/mach-ep93xx/ts72xx.c + ARM/CIRRUS LOGIC CLPS711X ARM ARCHITECTURE M: Alexander Shiyan shc_work@mail.ru L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@@ -1589,7 -1583,6 +1589,7 @@@ F: arch/arm/boot/dts/kirkwood F: arch/arm/configs/mvebu_*_defconfig F: arch/arm/mach-mvebu/ F: arch/arm64/boot/dts/marvell/armada* +F: drivers/cpufreq/armada-37xx-cpufreq.c F: drivers/cpufreq/mvebu-cpufreq.c F: drivers/irqchip/irq-armada-370-xp.c F: drivers/irqchip/irq-mvebu-* @@@ -1642,38 -1635,14 +1642,38 @@@ ARM/NEC MOBILEPRO 900/c MACHINE SUPPOR M: Michael Petchkovsky mkpetch@internode.on.net S: Maintained

-ARM/NOMADIK ARCHITECTURE -M: Alessandro Rubini rubini@unipv.it +ARM/NOMADIK/U300/Ux500 ARCHITECTURES M: Linus Walleij linus.walleij@linaro.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) S: Maintained F: arch/arm/mach-nomadik/ -F: drivers/pinctrl/nomadik/ +F: arch/arm/mach-u300/ +F: arch/arm/mach-ux500/ +F: arch/arm/boot/dts/ste-* +F: drivers/clk/clk-nomadik.c +F: drivers/clk/clk-u300.c +F: drivers/clocksource/clksrc-dbx500-prcmu.c +F: drivers/clocksource/timer-u300.c +F: drivers/dma/coh901318* +F: drivers/dma/ste_dma40* +F: drivers/hwspinlock/u8500_hsem.c F: drivers/i2c/busses/i2c-nomadik.c +F: drivers/i2c/busses/i2c-stu300.c +F: drivers/mfd/ab3100* +F: drivers/mfd/ab8500* +F: drivers/mfd/abx500* +F: drivers/mfd/dbx500* +F: drivers/mfd/db8500* +F: drivers/pinctrl/nomadik/ +F: drivers/pinctrl/pinctrl-coh901* +F: drivers/pinctrl/pinctrl-u300.c +F: drivers/rtc/rtc-ab3100.c +F: drivers/rtc/rtc-ab8500.c +F: drivers/rtc/rtc-coh901331.c +F: drivers/rtc/rtc-pl031.c +F: drivers/watchdog/coh901327_wdt.c +F: Documentation/devicetree/bindings/arm/ste-* +F: Documentation/devicetree/bindings/arm/ux500/ T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-nomadik.git

ARM/NUVOTON W90X900 ARM ARCHITECTURE @@@ -1987,10 -1956,9 +1987,10 @@@ N: stm3 F: drivers/clocksource/armv7m_systick.c

ARM/TANGO ARCHITECTURE -M: Marc Gonzalez marc_gonzalez@sigmadesigns.com +M: Marc Gonzalez marc.w.gonzalez@free.fr +M: Mans Rullgard mans@mansr.com L: linux-arm-kernel@lists.infradead.org -S: Maintained +S: Odd Fixes N: tango

ARM/TECHNOLOGIC SYSTEMS TS7250 MACHINE SUPPORT @@@ -2054,6 -2022,21 +2054,6 @@@ M: Dmitry Eremin-Solenikov <dbaryshkov@ M: Dirk Opfer dirk@opfer-online.de S: Maintained

-ARM/U300 MACHINE SUPPORT -M: Linus Walleij linus.walleij@linaro.org -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Supported -F: arch/arm/mach-u300/ -F: drivers/clocksource/timer-u300.c -F: drivers/i2c/busses/i2c-stu300.c -F: drivers/rtc/rtc-coh901331.c -F: drivers/watchdog/coh901327_wdt.c -F: drivers/dma/coh901318* -F: drivers/mfd/ab3100* -F: drivers/rtc/rtc-ab3100.c -F: drivers/rtc/rtc-coh901331.c -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-stericsson.git - ARM/UNIPHIER ARCHITECTURE M: Masahiro Yamada yamada.masahiro@socionext.com L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@@ -2075,6 -2058,24 +2075,6 @@@ F: drivers/reset/reset-uniphier. F: drivers/tty/serial/8250/8250_uniphier.c N: uniphier

-ARM/Ux500 ARM ARCHITECTURE -M: Linus Walleij linus.walleij@linaro.org -L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) -S: Maintained -F: arch/arm/mach-ux500/ -F: drivers/clocksource/clksrc-dbx500-prcmu.c -F: drivers/dma/ste_dma40* -F: drivers/hwspinlock/u8500_hsem.c -F: drivers/mfd/abx500* -F: drivers/mfd/ab8500* -F: drivers/mfd/dbx500* -F: drivers/mfd/db8500* -F: drivers/pinctrl/nomadik/pinctrl-ab* -F: drivers/pinctrl/nomadik/pinctrl-nomadik* -F: drivers/rtc/rtc-ab8500.c -F: drivers/rtc/rtc-pl031.c -T: git git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-stericsson.git - ARM/Ux500 CLOCK FRAMEWORK SUPPORT M: Ulf Hansson ulf.hansson@linaro.org L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers) @@@ -2201,6 -2202,14 +2201,6 @@@ L: linux-leds@vger.kernel.or S: Maintained F: drivers/leds/leds-as3645a.c

-AS3645A LED FLASH CONTROLLER DRIVER -M: Laurent Pinchart laurent.pinchart@ideasonboard.com -L: linux-media@vger.kernel.org -T: git git://linuxtv.org/media_tree.git -S: Maintained -F: drivers/media/i2c/as3645a.c -F: include/media/i2c/as3645a.h - ASAHI KASEI AK8974 DRIVER M: Linus Walleij linus.walleij@linaro.org L: linux-iio@vger.kernel.org @@@ -2253,9 -2262,7 +2253,9 @@@ F: include/linux/async_tx. AT24 EEPROM DRIVER M: Bartosz Golaszewski brgl@bgdev.pl L: linux-i2c@vger.kernel.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/brgl/linux.git S: Maintained +F: Documentation/devicetree/bindings/eeprom/at24.txt F: drivers/misc/eeprom/at24.c F: include/linux/platform_data/at24.h

@@@ -2494,8 -2501,6 +2494,8 @@@ L: linux-arm-kernel@lists.infradead.or S: Maintained F: Documentation/devicetree/bindings/arm/axentia.txt F: arch/arm/boot/dts/at91-linea.dtsi +F: arch/arm/boot/dts/at91-natte.dtsi +F: arch/arm/boot/dts/at91-nattis-2-natte-2.dts F: arch/arm/boot/dts/at91-tse850-3.dts

AXENTIA ASOC DRIVERS @@@ -2559,6 -2564,7 +2559,7 @@@ S: Maintaine F: Documentation/ABI/testing/sysfs-class-net-batman-adv F: Documentation/ABI/testing/sysfs-class-net-mesh F: Documentation/networking/batman-adv.rst + F: include/uapi/linux/batadv_packet.h F: include/uapi/linux/batman_adv.h F: net/batman-adv/

@@@ -2616,22 -2622,24 +2617,22 @@@ F: fs/bfs F: include/uapi/linux/bfs_fs.h

BLACKFIN ARCHITECTURE -M: Steven Miao realmz6@gmail.com L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) T: git git://git.code.sf.net/p/adi-linux/code W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: arch/blackfin/

BLACKFIN EMAC DRIVER L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: drivers/net/ethernet/adi/

BLACKFIN MEDIA DRIVER -M: Scott Jiang scott.jiang.linux@gmail.com L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org/ -S: Supported +S: Orphan F: drivers/media/platform/blackfin/ F: drivers/media/i2c/adv7183* F: drivers/media/i2c/vs6624* @@@ -2639,25 -2647,25 +2640,25 @@@ BLACKFIN RTC DRIVER L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: drivers/rtc/rtc-bfin.c

BLACKFIN SDH DRIVER L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: drivers/mmc/host/bfin_sdh.c

BLACKFIN SERIAL DRIVER L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: drivers/tty/serial/bfin_uart.c

BLACKFIN WATCHDOG DRIVER L: adi-buildroot-devel@lists.sourceforge.net (moderated for non-subscribers) W: http://blackfin.uclinux.org -S: Supported +S: Orphan F: drivers/watchdog/bfin_wdt.c

BLINKM RGB LED DRIVER @@@ -2682,7 -2690,6 +2683,6 @@@ F: drivers/mtd/devices/block2mtd.

BLUETOOTH DRIVERS M: Marcel Holtmann marcel@holtmann.org - M: Gustavo Padovan gustavo@padovan.org M: Johan Hedberg johan.hedberg@gmail.com L: linux-bluetooth@vger.kernel.org W: http://www.bluez.org/ @@@ -2693,7 -2700,6 +2693,6 @@@ F: drivers/bluetooth

BLUETOOTH SUBSYSTEM M: Marcel Holtmann marcel@holtmann.org - M: Gustavo Padovan gustavo@padovan.org M: Johan Hedberg johan.hedberg@gmail.com L: linux-bluetooth@vger.kernel.org W: http://www.bluez.org/ @@@ -2718,12 -2724,16 +2717,16 @@@ M: Alexei Starovoitov <ast@kernel.org M: Daniel Borkmann daniel@iogearbox.net L: netdev@vger.kernel.org L: linux-kernel@vger.kernel.org + T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git + T: git git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next.git S: Supported F: arch/x86/net/bpf_jit* F: Documentation/networking/filter.txt F: Documentation/bpf/ F: include/linux/bpf* F: include/linux/filter.h + F: include/trace/events/bpf.h + F: include/trace/events/xdp.h F: include/uapi/linux/bpf* F: include/uapi/linux/filter.h F: kernel/bpf/ @@@ -2827,8 -2837,6 +2830,8 @@@ S: Maintaine F: arch/arm/mach-bcm/*brcmstb* F: arch/arm/boot/dts/bcm7*.dts* F: drivers/bus/brcmstb_gisb.c +F: arch/arm/mm/cache-b15-rac.c +F: arch/arm/include/asm/hardware/cache-b15-rac.h N: brcmstb

BROADCOM BMIPS CPUFREQ DRIVER @@@ -5146,15 -5154,15 +5149,15 @@@ F: sound/usb/misc/ua101. EFI TEST DRIVER L: linux-efi@vger.kernel.org M: Ivan Hu ivan.hu@canonical.com -M: Matt Fleming matt@codeblueprint.co.uk +M: Ard Biesheuvel ard.biesheuvel@linaro.org S: Maintained F: drivers/firmware/efi/test/

EFI VARIABLE FILESYSTEM M: Matthew Garrett matthew.garrett@nebula.com M: Jeremy Kerr jk@ozlabs.org -M: Matt Fleming matt@codeblueprint.co.uk -T: git git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi.git +M: Ard Biesheuvel ard.biesheuvel@linaro.org +T: git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git L: linux-efi@vger.kernel.org S: Maintained F: fs/efivarfs/ @@@ -5315,6 -5323,7 +5318,6 @@@ S: Supporte F: security/integrity/evm/

EXTENSIBLE FIRMWARE INTERFACE (EFI) -M: Matt Fleming matt@codeblueprint.co.uk M: Ard Biesheuvel ard.biesheuvel@linaro.org L: linux-efi@vger.kernel.org T: git git://git.kernel.org/pub/scm/linux/kernel/git/efi/efi.git @@@ -7070,14 -7079,6 +7073,14 @@@ R: Dan Williams <dan.j.williams@intel.c S: Odd fixes F: drivers/dma/iop-adma.c

+INTEL IPU3 CSI-2 CIO2 DRIVER +M: Yong Zhi yong.zhi@intel.com +M: Sakari Ailus sakari.ailus@linux.intel.com +L: linux-media@vger.kernel.org +S: Maintained +F: drivers/media/pci/intel/ipu3/ +F: Documentation/media/uapi/v4l/pixfmt-srggb10-ipu3.rst + INTEL IXP4XX QMGR, NPE, ETHERNET and HSS SUPPORT M: Krzysztof Halasa khalasa@piap.pl S: Maintained @@@ -8683,15 -8684,6 +8686,15 @@@ T: git git://linuxtv.org/media_tree.gi S: Maintained F: drivers/media/dvb-frontends/stv6111*

+MEDIA DRIVERS FOR NVIDIA TEGRA - VDE +M: Dmitry Osipenko digetx@gmail.com +L: linux-media@vger.kernel.org +L: linux-tegra@vger.kernel.org +T: git git://linuxtv.org/media_tree.git +S: Maintained +F: Documentation/devicetree/bindings/media/nvidia,tegra-vde.txt +F: drivers/staging/media/tegra-vde/ + MEDIA INPUT INFRASTRUCTURE (V4L/DVB) M: Mauro Carvalho Chehab mchehab@s-opensource.com M: Mauro Carvalho Chehab mchehab@kernel.org @@@ -8735,6 -8727,13 +8738,13 @@@ L: netdev@vger.kernel.or S: Maintained F: drivers/net/ethernet/mediatek/

+ MEDIATEK SWITCH DRIVER + M: Sean Wang sean.wang@mediatek.com + L: netdev@vger.kernel.org + S: Maintained + F: drivers/net/dsa/mt7530.* + F: net/dsa/tag_mtk.c + MEDIATEK JPEG DRIVER M: Rick Chang rick.chang@mediatek.com M: Bin Liu bin.liu@mediatek.com @@@ -9107,7 -9106,6 +9117,7 @@@ S: Supporte F: Documentation/devicetree/bindings/mips/ F: Documentation/mips/ F: arch/mips/ +F: drivers/platform/mips/

MIPS BOSTON DEVELOPMENT BOARD M: Paul Burton paul.burton@mips.com @@@ -9135,25 -9133,6 +9145,25 @@@ F: arch/mips/include/asm/mach-loongson3 F: drivers/*/*loongson1* F: drivers/*/*/*loongson1*

+MIPS/LOONGSON2 ARCHITECTURE +M: Jiaxun Yang jiaxun.yang@flygoat.com +L: linux-mips@linux-mips.org +S: Maintained +F: arch/mips/loongson64/*{2e/2f}* +F: arch/mips/include/asm/mach-loongson64/ +F: drivers/*/*loongson2* +F: drivers/*/*/*loongson2* + +MIPS/LOONGSON3 ARCHITECTURE +M: Huacai Chen chenhc@lemote.com +L: linux-mips@linux-mips.org +S: Maintained +F: arch/mips/loongson64/ +F: arch/mips/include/asm/mach-loongson64/ +F: drivers/platform/mips/cpu_hwmon.c +F: drivers/*/*loongson3* +F: drivers/*/*/*loongson3* + MIPS RINT INSTRUCTION EMULATION M: Aleksandar Markovic aleksandar.markovic@mips.com L: linux-mips@linux-mips.org @@@ -9631,6 -9610,11 +9641,11 @@@ NETWORKING [WIRELESS L: linux-wireless@vger.kernel.org Q: http://patchwork.kernel.org/project/linux-wireless/list/

+ NETDEVSIM + M: Jakub Kicinski jakub.kicinski@netronome.com + S: Maintained + F: drivers/net/netdevsim/* + NETXEN (1/10) GbE SUPPORT M: Manish Chopra manish.chopra@cavium.com M: Rahul Verma rahul.verma@cavium.com @@@ -10085,14 -10069,6 +10100,14 @@@ S: Maintaine F: drivers/media/i2c/ov7670.c F: Documentation/devicetree/bindings/media/i2c/ov7670.txt

+OMNIVISION OV7740 SENSOR DRIVER +M: Wenyou Yang wenyou.yang@microchip.com +L: linux-media@vger.kernel.org +T: git git://linuxtv.org/media_tree.git +S: Maintained +F: drivers/media/i2c/ov7740.c +F: Documentation/devicetree/bindings/media/i2c/ov7740.txt + ONENAND FLASH DRIVER M: Kyungmin Park kyungmin.park@samsung.com L: linux-mtd@lists.infradead.org @@@ -10176,7 -10152,7 +10191,7 @@@ F: drivers/irqchip/irq-ompic. F: drivers/irqchip/irq-or1k-*

OPENVSWITCH -M: Pravin Shelar pshelar@nicira.com +M: Pravin B Shelar pshelar@ovn.org L: netdev@vger.kernel.org L: dev@openvswitch.org W: http://openvswitch.org @@@ -10591,12 -10567,8 +10606,12 @@@ T: git git://git.kernel.org/pub/scm/lin S: Supported F: Documentation/devicetree/bindings/pci/ F: Documentation/PCI/ +F: drivers/acpi/pci* F: drivers/pci/ +F: include/asm-generic/pci* F: include/linux/pci* +F: include/uapi/linux/pci* +F: lib/pci* F: arch/x86/pci/ F: arch/x86/kernel/quirks.c

@@@ -10935,7 -10907,6 +10950,7 @@@ F: include/linux/pm. F: include/linux/pm_* F: include/linux/powercap.h F: drivers/powercap/ +F: kernel/configs/nopm.config

POWER STATE COORDINATION INTERFACE (PSCI) M: Mark Rutland mark.rutland@arm.com @@@ -12383,14 -12354,6 +12398,14 @@@ T: git git://linuxtv.org/anttip/media_t S: Maintained F: drivers/media/tuners/si2157*

+SI2165 MEDIA DRIVER +M: Matthias Schwarzott zzam@gentoo.org +L: linux-media@vger.kernel.org +W: https://linuxtv.org +Q: http://patchwork.linuxtv.org/project/linux-media/list/ +S: Maintained +F: drivers/media/dvb-frontends/si2165* + SI2168 MEDIA DRIVER M: Antti Palosaari crope@iki.fi L: linux-media@vger.kernel.org @@@ -12921,6 -12884,12 +12936,6 @@@ S: Odd Fixe F: Documentation/devicetree/bindings/staging/iio/ F: drivers/staging/iio/

-STAGING - LIRC (LINUX INFRARED REMOTE CONTROL) DRIVERS -M: Jarod Wilson jarod@wilsonet.com -W: http://www.lirc.org/ -S: Odd Fixes -F: drivers/staging/media/lirc/ - STAGING - LUSTRE PARALLEL FILESYSTEM M: Oleg Drokin oleg.drokin@intel.com M: Andreas Dilger andreas.dilger@intel.com @@@ -13302,15 -13271,6 +13317,15 @@@ T: git git://linuxtv.org/anttip/media_t S: Maintained F: drivers/media/tuners/tda18218*

+TDA18250 MEDIA DRIVER +M: Olli Salonen olli.salonen@iki.fi +L: linux-media@vger.kernel.org +W: https://linuxtv.org +Q: http://patchwork.linuxtv.org/project/linux-media/list/ +T: git git://linuxtv.org/media_tree.git +S: Maintained +F: drivers/media/tuners/tda18250* + TDA18271 MEDIA DRIVER M: Michael Krufky mkrufky@linuxtv.org L: linux-media@vger.kernel.org @@@ -13548,7 -13508,6 +13563,7 @@@ M: Mika Westerberg <mika.westerberg@lin M: Yehezkel Bernat yehezkel.bernat@intel.com T: git git://git.kernel.org/pub/scm/linux/kernel/git/westeri/thunderbolt.git S: Maintained +F: Documentation/admin-guide/thunderbolt.rst F: drivers/thunderbolt/ F: include/linux/thunderbolt.h

diff --combined arch/arm/boot/dts/imx25.dtsi index c43cf704b768,fcaff1c66bcb..9445f8e1473c --- a/arch/arm/boot/dts/imx25.dtsi +++ b/arch/arm/boot/dts/imx25.dtsi @@@ -122,7 -122,7 +122,7 @@@ };

can1: can@43f88000 { - compatible = "fsl,imx25-flexcan", "fsl,p1010-flexcan"; + compatible = "fsl,imx25-flexcan"; reg = <0x43f88000 0x4000>; interrupts = <43>; clocks = <&clks 75>, <&clks 75>; @@@ -131,7 -131,7 +131,7 @@@ };

can2: can@43f8c000 { - compatible = "fsl,imx25-flexcan", "fsl,p1010-flexcan"; + compatible = "fsl,imx25-flexcan"; reg = <0x43f8c000 0x4000>; interrupts = <44>; clocks = <&clks 76>, <&clks 76>; @@@ -628,13 -628,11 +628,13 @@@ usbphy0: usb-phy@0 { reg = <0>; compatible = "usb-nop-xceiv"; + #phy-cells = <0>; };

usbphy1: usb-phy@1 { reg = <1>; compatible = "usb-nop-xceiv"; + #phy-cells = <0>; }; }; }; diff --combined arch/arm/boot/dts/imx35.dtsi index f049c692c6b0,1f0e2203b576..e08c0c193767 --- a/arch/arm/boot/dts/imx35.dtsi +++ b/arch/arm/boot/dts/imx35.dtsi @@@ -303,7 -303,7 +303,7 @@@ };

can1: can@53fe4000 { - compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan"; + compatible = "fsl,imx35-flexcan"; reg = <0x53fe4000 0x1000>; clocks = <&clks 33>, <&clks 33>; clock-names = "ipg", "per"; @@@ -312,7 -312,7 +312,7 @@@ };

can2: can@53fe8000 { - compatible = "fsl,imx35-flexcan", "fsl,p1010-flexcan"; + compatible = "fsl,imx35-flexcan"; reg = <0x53fe8000 0x1000>; clocks = <&clks 34>, <&clks 34>; clock-names = "ipg", "per"; @@@ -402,13 -402,11 +402,13 @@@ usbphy0: usb-phy@0 { reg = <0>; compatible = "usb-nop-xceiv"; + #phy-cells = <0>; };

usbphy1: usb-phy@1 { reg = <1>; compatible = "usb-nop-xceiv"; + #phy-cells = <0>; }; }; }; diff --combined arch/arm/boot/dts/imx53.dtsi index 38b31a37339b,85071ff8c639..1040251f2951 --- a/arch/arm/boot/dts/imx53.dtsi +++ b/arch/arm/boot/dts/imx53.dtsi @@@ -116,28 -116,6 +116,28 @@@ }; };

+ pmu { + compatible = "arm,cortex-a8-pmu"; + interrupt-parent = <&tzic>; + interrupts = <77>; + }; + + usbphy0: usbphy-0 { + compatible = "usb-nop-xceiv"; + clocks = <&clks IMX5_CLK_USB_PHY1_GATE>; + clock-names = "main_clk"; + #phy-cells = <0>; + status = "okay"; + }; + + usbphy1: usbphy-1 { + compatible = "usb-nop-xceiv"; + clocks = <&clks IMX5_CLK_USB_PHY2_GATE>; + clock-names = "main_clk"; + #phy-cells = <0>; + status = "okay"; + }; + soc { #address-cells = <1>; #size-cells = <1>; @@@ -321,6 -299,20 +321,6 @@@ reg = <0x53f00000 0x60>; };

- usbphy0: usbphy-0 { - compatible = "usb-nop-xceiv"; - clocks = <&clks IMX5_CLK_USB_PHY1_GATE>; - clock-names = "main_clk"; - status = "okay"; - }; - - usbphy1: usbphy-1 { - compatible = "usb-nop-xceiv"; - clocks = <&clks IMX5_CLK_USB_PHY2_GATE>; - clock-names = "main_clk"; - status = "okay"; - }; - usbotg: usb@53f80000 { compatible = "fsl,imx53-usb", "fsl,imx27-usb"; reg = <0x53f80000 0x0200>; @@@ -441,13 -433,6 +441,13 @@@ clock-names = "ipg", "per"; };

+ srtc: rtc@53fa4000 { + compatible = "fsl,imx53-rtc"; + reg = <0x53fa4000 0x4000>; + interrupts = <24>; + clocks = <&clks IMX5_CLK_SRTC_GATE>; + }; + iomuxc: iomuxc@53fa8000 { compatible = "fsl,imx53-iomuxc"; reg = <0x53fa8000 0x4000>; @@@ -551,7 -536,7 +551,7 @@@ };

can1: can@53fc8000 { - compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan"; + compatible = "fsl,imx53-flexcan"; reg = <0x53fc8000 0x4000>; interrupts = <82>; clocks = <&clks IMX5_CLK_CAN1_IPG_GATE>, @@@ -561,7 -546,7 +561,7 @@@ };

can2: can@53fcc000 { - compatible = "fsl,imx53-flexcan", "fsl,p1010-flexcan"; + compatible = "fsl,imx53-flexcan"; reg = <0x53fcc000 0x4000>; interrupts = <83>; clocks = <&clks IMX5_CLK_CAN2_IPG_GATE>, @@@ -828,5 -813,10 +828,5 @@@ reg = <0xf8000000 0x20000>; clocks = <&clks IMX5_CLK_OCRAM>; }; - - pmu { - compatible = "arm,cortex-a8-pmu"; - interrupts = <77>; - }; }; }; diff --combined arch/arm/boot/dts/ls1021a-qds.dts index bf15dc27ca53,4f211e3c903a..499f41a2c6f0 --- a/arch/arm/boot/dts/ls1021a-qds.dts +++ b/arch/arm/boot/dts/ls1021a-qds.dts @@@ -215,7 -215,7 +215,7 @@@ reg = <0x2a>; VDDA-supply = <&reg_3p3v>; VDDIO-supply = <&reg_3p3v>; - clocks = <&sys_mclk 1>; + clocks = <&sys_mclk>; }; }; }; @@@ -239,11 -239,6 +239,11 @@@ device-width = <1>; };

+ nand@2,0 { + compatible = "fsl,ifc-nand"; + reg = <0x2 0x0 0x10000>; + }; + fpga: board-control@3,0 { #address-cells = <1>; #size-cells = <1>; @@@ -336,3 -331,19 +336,19 @@@ &uart1 { status = "okay"; }; + + &can0 { + status = "okay"; + }; + + &can1 { + status = "okay"; + }; + + &can2 { + status = "disabled"; + }; + + &can3 { + status = "disabled"; + }; diff --combined arch/arm/boot/dts/ls1021a-twr.dts index b186c370ad54,7202d9c504be..f0c949d74833 --- a/arch/arm/boot/dts/ls1021a-twr.dts +++ b/arch/arm/boot/dts/ls1021a-twr.dts @@@ -187,7 -187,7 +187,7 @@@ reg = <0x0a>; VDDA-supply = <&reg_3p3v>; VDDIO-supply = <&reg_3p3v>; - clocks = <&sys_mclk 1>; + clocks = <&sys_mclk>; }; };

@@@ -228,10 -228,6 +228,10 @@@ }; };

+&esdhc { + status = "okay"; +}; + &sai1 { status = "okay"; }; @@@ -247,3 -243,19 +247,19 @@@ &uart1 { status = "okay"; }; + + &can0 { + status = "okay"; + }; + + &can1 { + status = "okay"; + }; + + &can2 { + status = "disabled"; + }; + + &can3 { + status = "disabled"; + }; diff --combined arch/arm/boot/dts/ls1021a.dtsi index c5edfa9a68a6,7789031898b0..c31dad98f989 --- a/arch/arm/boot/dts/ls1021a.dtsi +++ b/arch/arm/boot/dts/ls1021a.dtsi @@@ -106,14 -106,6 +106,14 @@@ compatible = "arm,cortex-a7-pmu"; interrupts = <GIC_SPI 138 IRQ_TYPE_LEVEL_HIGH>, <GIC_SPI 139 IRQ_TYPE_LEVEL_HIGH>; + interrupt-affinity = <&cpu0>, <&cpu1>; + }; + + reboot { + compatible = "syscon-reboot"; + regmap = <&dcfg>; + offset = <0xb0>; + mask = <0x02>; };

soc { @@@ -162,22 -154,8 +162,22 @@@ big-endian; };

+ qspi: quadspi@1550000 { + compatible = "fsl,ls1021a-qspi"; + #address-cells = <1>; + #size-cells = <0>; + reg = <0x0 0x1550000 0x0 0x10000>, + <0x0 0x40000000 0x0 0x40000000>; + reg-names = "QuadSPI", "QuadSPI-memory"; + interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>; + clock-names = "qspi_en", "qspi"; + clocks = <&clockgen 4 1>, <&clockgen 4 1>; + big-endian; + status = "disabled"; + }; + esdhc: esdhc@1560000 { - compatible = "fsl,esdhc"; + compatible = "fsl,ls1021a-esdhc", "fsl,esdhc"; reg = <0x0 0x1560000 0x0 0x10000>; interrupts = <GIC_SPI 94 IRQ_TYPE_LEVEL_HIGH>; clock-frequency = <0>; @@@ -597,7 -575,7 +597,7 @@@ fsl,tclk-period = <5>; fsl,tmr-prsc = <2>; fsl,tmr-add = <0xaaaaaaab>; - fsl,tmr-fiper1 = <999999990>; + fsl,tmr-fiper1 = <999999995>; fsl,tmr-fiper2 = <99990>; fsl,max-adj = <499999999>; }; @@@ -690,7 -668,7 +690,7 @@@ }; };

- usb@8600000 { + usb2: usb@8600000 { compatible = "fsl-usb2-dr-v2.5", "fsl-usb2-dr"; reg = <0x0 0x8600000 0x0 0x1000>; interrupts = <GIC_SPI 171 IRQ_TYPE_LEVEL_HIGH>; @@@ -698,7 -676,7 +698,7 @@@ phy_type = "ulpi"; };

- usb3@3100000 { + usb3: usb3@3100000 { compatible = "snps,dwc3"; reg = <0x0 0x3100000 0x0 0x10000>; interrupts = <GIC_SPI 93 IRQ_TYPE_LEVEL_HIGH>; @@@ -752,5 -730,41 +752,41 @@@ <0000 0 0 3 &gic GIC_SPI 191 IRQ_TYPE_LEVEL_HIGH>, <0000 0 0 4 &gic GIC_SPI 193 IRQ_TYPE_LEVEL_HIGH>; }; + + can0: can@2a70000 { + compatible = "fsl,ls1021ar2-flexcan"; + reg = <0x0 0x2a70000 0x0 0x1000>; + interrupts = <GIC_SPI 126 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 4 1>, <&clockgen 4 1>; + clock-names = "ipg", "per"; + big-endian; + }; + + can1: can@2a80000 { + compatible = "fsl,ls1021ar2-flexcan"; + reg = <0x0 0x2a80000 0x0 0x1000>; + interrupts = <GIC_SPI 127 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 4 1>, <&clockgen 4 1>; + clock-names = "ipg", "per"; + big-endian; + }; + + can2: can@2a90000 { + compatible = "fsl,ls1021ar2-flexcan"; + reg = <0x0 0x2a90000 0x0 0x1000>; + interrupts = <GIC_SPI 128 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 4 1>, <&clockgen 4 1>; + clock-names = "ipg", "per"; + big-endian; + }; + + can3: can@2aa0000 { + compatible = "fsl,ls1021ar2-flexcan"; + reg = <0x0 0x2aa0000 0x0 0x1000>; + interrupts = <GIC_SPI 129 IRQ_TYPE_LEVEL_HIGH>; + clocks = <&clockgen 4 1>, <&clockgen 4 1>; + clock-names = "ipg", "per"; + big-endian; + }; }; }; diff --combined drivers/net/can/flexcan.c index 760d2c07e3a2,3cd371c94e83..634c51e6b8ae --- a/drivers/net/can/flexcan.c +++ b/drivers/net/can/flexcan.c @@@ -190,6 -190,7 +190,7 @@@ * MX53 FlexCAN2 03.00.00.00 yes no no no no * MX6s FlexCAN3 10.00.12.00 yes yes no no yes * VF610 FlexCAN3 ? no yes no yes yes? + * LS1021A FlexCAN2 03.00.04.00 no yes no no yes * * Some SOCs do not have the RX_WARN & TX_WARN interrupt line connected. */ @@@ -279,6 -280,10 +280,10 @@@ struct flexcan_priv struct clk *clk_per; const struct flexcan_devtype_data *devtype_data; struct regulator *reg_xceiver; + + /* Read and Write APIs */ + u32 (*read)(void __iomem *addr); + void (*write)(u32 val, void __iomem *addr); };

static const struct flexcan_devtype_data fsl_p1010_devtype_data = { @@@ -301,6 -306,12 +306,12 @@@ static const struct flexcan_devtype_dat FLEXCAN_QUIRK_BROKEN_PERR_STATE, };

+ static const struct flexcan_devtype_data fsl_ls1021a_r2_devtype_data = { + .quirks = FLEXCAN_QUIRK_DISABLE_RXFG | FLEXCAN_QUIRK_ENABLE_EACEN_RRS | + FLEXCAN_QUIRK_DISABLE_MECR | FLEXCAN_QUIRK_BROKEN_PERR_STATE | + FLEXCAN_QUIRK_USE_OFF_TIMESTAMP, + }; + static const struct can_bittiming_const flexcan_bittiming_const = { .name = DRV_NAME, .tseg1_min = 4, @@@ -313,39 -324,45 +324,45 @@@ .brp_inc = 1, };

- /* Abstract off the read/write for arm versus ppc. This - * assumes that PPC uses big-endian registers and everything - * else uses little-endian registers, independent of CPU - * endianness. + /* FlexCAN module is essentially modelled as a little-endian IP in most + * SoCs, i.e the registers as well as the message buffer areas are + * implemented in a little-endian fashion. + * + * However there are some SoCs (e.g. LS1021A) which implement the FlexCAN + * module in a big-endian fashion (i.e the registers as well as the + * message buffer areas are implemented in a big-endian way). + * + * In addition, the FlexCAN module can be found on SoCs having ARM or + * PPC cores. So, we need to abstract off the register read/write + * functions, ensuring that these cater to all the combinations of module + * endianness and underlying CPU endianness. */ - #if defined(CONFIG_PPC) - static inline u32 flexcan_read(void __iomem *addr) + static inline u32 flexcan_read_be(void __iomem *addr) { - return in_be32(addr); + return ioread32be(addr); }

- static inline void flexcan_write(u32 val, void __iomem *addr) + static inline void flexcan_write_be(u32 val, void __iomem *addr) { - out_be32(addr, val); + iowrite32be(val, addr); } - #else - static inline u32 flexcan_read(void __iomem *addr) + + static inline u32 flexcan_read_le(void __iomem *addr) { - return readl(addr); + return ioread32(addr); }

- static inline void flexcan_write(u32 val, void __iomem *addr) + static inline void flexcan_write_le(u32 val, void __iomem *addr) { - writel(val, addr); + iowrite32(val, addr); } - #endif

static inline void flexcan_error_irq_enable(const struct flexcan_priv *priv) { struct flexcan_regs __iomem *regs = priv->regs; u32 reg_ctrl = (priv->reg_ctrl_default | FLEXCAN_CTRL_ERR_MSK);

- flexcan_write(reg_ctrl, &regs->ctrl); + priv->write(reg_ctrl, &regs->ctrl); }

static inline void flexcan_error_irq_disable(const struct flexcan_priv *priv) @@@ -353,7 -370,7 +370,7 @@@ struct flexcan_regs __iomem *regs = priv->regs; u32 reg_ctrl = (priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_MSK);

- flexcan_write(reg_ctrl, &regs->ctrl); + priv->write(reg_ctrl, &regs->ctrl); }

static inline int flexcan_transceiver_enable(const struct flexcan_priv *priv) @@@ -378,14 -395,14 +395,14 @@@ static int flexcan_chip_enable(struct f unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg;

- reg = flexcan_read(&regs->mcr); + reg = priv->read(&regs->mcr); reg &= ~FLEXCAN_MCR_MDIS; - flexcan_write(reg, &regs->mcr); + priv->write(reg, &regs->mcr);

- while (timeout-- && (flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK)) + while (timeout-- && (priv->read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK)) udelay(10);

- if (flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK) + if (priv->read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK) return -ETIMEDOUT;

return 0; @@@ -397,14 -414,14 +414,14 @@@ static int flexcan_chip_disable(struct unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg;

- reg = flexcan_read(&regs->mcr); + reg = priv->read(&regs->mcr); reg |= FLEXCAN_MCR_MDIS; - flexcan_write(reg, &regs->mcr); + priv->write(reg, &regs->mcr);

- while (timeout-- && !(flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK)) + while (timeout-- && !(priv->read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK)) udelay(10);

- if (!(flexcan_read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK)) + if (!(priv->read(&regs->mcr) & FLEXCAN_MCR_LPM_ACK)) return -ETIMEDOUT;

return 0; @@@ -416,14 -433,14 +433,14 @@@ static int flexcan_chip_freeze(struct f unsigned int timeout = 1000 * 1000 * 10 / priv->can.bittiming.bitrate; u32 reg;

- reg = flexcan_read(&regs->mcr); + reg = priv->read(&regs->mcr); reg |= FLEXCAN_MCR_HALT; - flexcan_write(reg, &regs->mcr); + priv->write(reg, &regs->mcr);

- while (timeout-- && !(flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK)) + while (timeout-- && !(priv->read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK)) udelay(100);

- if (!(flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK)) + if (!(priv->read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK)) return -ETIMEDOUT;

return 0; @@@ -435,14 -452,14 +452,14 @@@ static int flexcan_chip_unfreeze(struc unsigned int timeout = FLEXCAN_TIMEOUT_US / 10; u32 reg;

- reg = flexcan_read(&regs->mcr); + reg = priv->read(&regs->mcr); reg &= ~FLEXCAN_MCR_HALT; - flexcan_write(reg, &regs->mcr); + priv->write(reg, &regs->mcr);

- while (timeout-- && (flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK)) + while (timeout-- && (priv->read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK)) udelay(10);

- if (flexcan_read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK) + if (priv->read(&regs->mcr) & FLEXCAN_MCR_FRZ_ACK) return -ETIMEDOUT;

return 0; @@@ -453,11 -470,11 +470,11 @@@ static int flexcan_chip_softreset(struc struct flexcan_regs __iomem *regs = priv->regs; unsigned int timeout = FLEXCAN_TIMEOUT_US / 10;

- flexcan_write(FLEXCAN_MCR_SOFTRST, &regs->mcr); - while (timeout-- && (flexcan_read(&regs->mcr) & FLEXCAN_MCR_SOFTRST)) + priv->write(FLEXCAN_MCR_SOFTRST, &regs->mcr); + while (timeout-- && (priv->read(&regs->mcr) & FLEXCAN_MCR_SOFTRST)) udelay(10);

- if (flexcan_read(&regs->mcr) & FLEXCAN_MCR_SOFTRST) + if (priv->read(&regs->mcr) & FLEXCAN_MCR_SOFTRST) return -ETIMEDOUT;

return 0; @@@ -468,7 -485,7 +485,7 @@@ static int __flexcan_get_berr_counter(c { const struct flexcan_priv *priv = netdev_priv(dev); struct flexcan_regs __iomem *regs = priv->regs; - u32 reg = flexcan_read(&regs->ecr); + u32 reg = priv->read(&regs->ecr);

bec->txerr = (reg >> 0) & 0xff; bec->rxerr = (reg >> 8) & 0xff; @@@ -524,24 -541,24 +541,24 @@@ static int flexcan_start_xmit(struct sk

if (cf->can_dlc > 0) { data = be32_to_cpup((__be32 *)&cf->data[0]); - flexcan_write(data, &priv->tx_mb->data[0]); + priv->write(data, &priv->tx_mb->data[0]); } - if (cf->can_dlc > 3) { + if (cf->can_dlc > 4) { data = be32_to_cpup((__be32 *)&cf->data[4]); - flexcan_write(data, &priv->tx_mb->data[1]); + priv->write(data, &priv->tx_mb->data[1]); }

can_put_echo_skb(skb, dev, 0);

- flexcan_write(can_id, &priv->tx_mb->can_id); - flexcan_write(ctrl, &priv->tx_mb->can_ctrl); + priv->write(can_id, &priv->tx_mb->can_id); + priv->write(ctrl, &priv->tx_mb->can_ctrl);

/* Errata ERR005829 step8: * Write twice INACTIVE(0x8) code to first MB. */ - flexcan_write(FLEXCAN_MB_CODE_TX_INACTIVE, + priv->write(FLEXCAN_MB_CODE_TX_INACTIVE, &priv->tx_mb_reserved->can_ctrl); - flexcan_write(FLEXCAN_MB_CODE_TX_INACTIVE, + priv->write(FLEXCAN_MB_CODE_TX_INACTIVE, &priv->tx_mb_reserved->can_ctrl);

return NETDEV_TX_OK; @@@ -660,7 -677,7 +677,7 @@@ static unsigned int flexcan_mailbox_rea u32 code;

do { - reg_ctrl = flexcan_read(&mb->can_ctrl); + reg_ctrl = priv->read(&mb->can_ctrl); } while (reg_ctrl & FLEXCAN_MB_CODE_RX_BUSY_BIT);

/* is this MB empty? */ @@@ -675,17 -692,17 +692,17 @@@ offload->dev->stats.rx_errors++; } } else { - reg_iflag1 = flexcan_read(&regs->iflag1); + reg_iflag1 = priv->read(&regs->iflag1); if (!(reg_iflag1 & FLEXCAN_IFLAG_RX_FIFO_AVAILABLE)) return 0;

- reg_ctrl = flexcan_read(&mb->can_ctrl); + reg_ctrl = priv->read(&mb->can_ctrl); }

/* increase timstamp to full 32 bit */ *timestamp = reg_ctrl << 16;

- reg_id = flexcan_read(&mb->can_id); + reg_id = priv->read(&mb->can_id); if (reg_ctrl & FLEXCAN_MB_CNT_IDE) cf->can_id = ((reg_id >> 0) & CAN_EFF_MASK) | CAN_EFF_FLAG; else @@@ -695,19 -712,19 +712,19 @@@ cf->can_id |= CAN_RTR_FLAG; cf->can_dlc = get_can_dlc((reg_ctrl >> 16) & 0xf);

- *(__be32 *)(cf->data + 0) = cpu_to_be32(flexcan_read(&mb->data[0])); - *(__be32 *)(cf->data + 4) = cpu_to_be32(flexcan_read(&mb->data[1])); + *(__be32 *)(cf->data + 0) = cpu_to_be32(priv->read(&mb->data[0])); + *(__be32 *)(cf->data + 4) = cpu_to_be32(priv->read(&mb->data[1]));

/* mark as read */ if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) { /* Clear IRQ */ if (n < 32) - flexcan_write(BIT(n), &regs->iflag1); + priv->write(BIT(n), &regs->iflag1); else - flexcan_write(BIT(n - 32), &regs->iflag2); + priv->write(BIT(n - 32), &regs->iflag2); } else { - flexcan_write(FLEXCAN_IFLAG_RX_FIFO_AVAILABLE, &regs->iflag1); - flexcan_read(&regs->timer); + priv->write(FLEXCAN_IFLAG_RX_FIFO_AVAILABLE, &regs->iflag1); + priv->read(&regs->timer); }

return 1; @@@ -719,8 -736,8 +736,8 @@@ static inline u64 flexcan_read_reg_ifla struct flexcan_regs __iomem *regs = priv->regs; u32 iflag1, iflag2;

- iflag2 = flexcan_read(&regs->iflag2) & priv->reg_imask2_default; - iflag1 = flexcan_read(&regs->iflag1) & priv->reg_imask1_default & + iflag2 = priv->read(&regs->iflag2) & priv->reg_imask2_default; + iflag1 = priv->read(&regs->iflag1) & priv->reg_imask1_default & ~FLEXCAN_IFLAG_MB(priv->tx_mb_idx);

return (u64)iflag2 << 32 | iflag1; @@@ -736,7 -753,7 +753,7 @@@ static irqreturn_t flexcan_irq(int irq u32 reg_iflag1, reg_esr; enum can_state last_state = priv->can.state;

- reg_iflag1 = flexcan_read(&regs->iflag1); + reg_iflag1 = priv->read(&regs->iflag1);

/* reception interrupt */ if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) { @@@ -759,7 -776,8 +776,8 @@@ /* FIFO overflow interrupt */ if (reg_iflag1 & FLEXCAN_IFLAG_RX_FIFO_OVERFLOW) { handled = IRQ_HANDLED; - flexcan_write(FLEXCAN_IFLAG_RX_FIFO_OVERFLOW, &regs->iflag1); + priv->write(FLEXCAN_IFLAG_RX_FIFO_OVERFLOW, + &regs->iflag1); dev->stats.rx_over_errors++; dev->stats.rx_errors++; } @@@ -773,18 -791,18 +791,18 @@@ can_led_event(dev, CAN_LED_EVENT_TX);

/* after sending a RTR frame MB is in RX mode */ - flexcan_write(FLEXCAN_MB_CODE_TX_INACTIVE, - &priv->tx_mb->can_ctrl); - flexcan_write(FLEXCAN_IFLAG_MB(priv->tx_mb_idx), &regs->iflag1); + priv->write(FLEXCAN_MB_CODE_TX_INACTIVE, + &priv->tx_mb->can_ctrl); + priv->write(FLEXCAN_IFLAG_MB(priv->tx_mb_idx), &regs->iflag1); netif_wake_queue(dev); }

- reg_esr = flexcan_read(&regs->esr); + reg_esr = priv->read(&regs->esr);

/* ACK all bus error and state change IRQ sources */ if (reg_esr & FLEXCAN_ESR_ALL_INT) { handled = IRQ_HANDLED; - flexcan_write(reg_esr & FLEXCAN_ESR_ALL_INT, &regs->esr); + priv->write(reg_esr & FLEXCAN_ESR_ALL_INT, &regs->esr); }

/* state change interrupt or broken error state quirk fix is enabled */ @@@ -846,7 -864,7 +864,7 @@@ static void flexcan_set_bittiming(struc struct flexcan_regs __iomem *regs = priv->regs; u32 reg;

- reg = flexcan_read(&regs->ctrl); + reg = priv->read(&regs->ctrl); reg &= ~(FLEXCAN_CTRL_PRESDIV(0xff) | FLEXCAN_CTRL_RJW(0x3) | FLEXCAN_CTRL_PSEG1(0x7) | @@@ -870,11 -888,11 +888,11 @@@ reg |= FLEXCAN_CTRL_SMP;

netdev_dbg(dev, "writing ctrl=0x%08x\n", reg); - flexcan_write(reg, &regs->ctrl); + priv->write(reg, &regs->ctrl);

/* print chip status */ netdev_dbg(dev, "%s: mcr=0x%08x ctrl=0x%08x\n", __func__, - flexcan_read(&regs->mcr), flexcan_read(&regs->ctrl)); + priv->read(&regs->mcr), priv->read(&regs->ctrl)); }

/* flexcan_chip_start @@@ -913,7 -931,7 +931,7 @@@ static int flexcan_chip_start(struct ne * choose format C * set max mailbox number */ - reg_mcr = flexcan_read(&regs->mcr); + reg_mcr = priv->read(&regs->mcr); reg_mcr &= ~FLEXCAN_MCR_MAXMB(0xff); reg_mcr |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT | FLEXCAN_MCR_SUPV | FLEXCAN_MCR_WRN_EN | FLEXCAN_MCR_SRX_DIS | FLEXCAN_MCR_IRMQ | @@@ -927,7 -945,7 +945,7 @@@ FLEXCAN_MCR_MAXMB(priv->tx_mb_idx); } netdev_dbg(dev, "%s: writing mcr=0x%08x", __func__, reg_mcr); - flexcan_write(reg_mcr, &regs->mcr); + priv->write(reg_mcr, &regs->mcr);

/* CTRL * @@@ -940,7 -958,7 +958,7 @@@ * enable bus off interrupt * (== FLEXCAN_CTRL_ERR_STATE) */ - reg_ctrl = flexcan_read(&regs->ctrl); + reg_ctrl = priv->read(&regs->ctrl); reg_ctrl &= ~FLEXCAN_CTRL_TSYN; reg_ctrl |= FLEXCAN_CTRL_BOFF_REC | FLEXCAN_CTRL_LBUF | FLEXCAN_CTRL_ERR_STATE; @@@ -960,45 -978,45 +978,45 @@@ /* leave interrupts disabled for now */ reg_ctrl &= ~FLEXCAN_CTRL_ERR_ALL; netdev_dbg(dev, "%s: writing ctrl=0x%08x", __func__, reg_ctrl); - flexcan_write(reg_ctrl, &regs->ctrl); + priv->write(reg_ctrl, &regs->ctrl);

if ((priv->devtype_data->quirks & FLEXCAN_QUIRK_ENABLE_EACEN_RRS)) { - reg_ctrl2 = flexcan_read(&regs->ctrl2); + reg_ctrl2 = priv->read(&regs->ctrl2); reg_ctrl2 |= FLEXCAN_CTRL2_EACEN | FLEXCAN_CTRL2_RRS; - flexcan_write(reg_ctrl2, &regs->ctrl2); + priv->write(reg_ctrl2, &regs->ctrl2); }

/* clear and invalidate all mailboxes first */ for (i = priv->tx_mb_idx; i < ARRAY_SIZE(regs->mb); i++) { - flexcan_write(FLEXCAN_MB_CODE_RX_INACTIVE, - &regs->mb[i].can_ctrl); + priv->write(FLEXCAN_MB_CODE_RX_INACTIVE, + &regs->mb[i].can_ctrl); }

if (priv->devtype_data->quirks & FLEXCAN_QUIRK_USE_OFF_TIMESTAMP) { for (i = priv->offload.mb_first; i <= priv->offload.mb_last; i++) - flexcan_write(FLEXCAN_MB_CODE_RX_EMPTY, - &regs->mb[i].can_ctrl); + priv->write(FLEXCAN_MB_CODE_RX_EMPTY, + &regs->mb[i].can_ctrl); }

/* Errata ERR005829: mark first TX mailbox as INACTIVE */ - flexcan_write(FLEXCAN_MB_CODE_TX_INACTIVE, - &priv->tx_mb_reserved->can_ctrl); + priv->write(FLEXCAN_MB_CODE_TX_INACTIVE, + &priv->tx_mb_reserved->can_ctrl);

/* mark TX mailbox as INACTIVE */ - flexcan_write(FLEXCAN_MB_CODE_TX_INACTIVE, - &priv->tx_mb->can_ctrl); + priv->write(FLEXCAN_MB_CODE_TX_INACTIVE, + &priv->tx_mb->can_ctrl);

/* acceptance mask/acceptance code (accept everything) */ - flexcan_write(0x0, &regs->rxgmask); - flexcan_write(0x0, &regs->rx14mask); - flexcan_write(0x0, &regs->rx15mask); + priv->write(0x0, &regs->rxgmask); + priv->write(0x0, &regs->rx14mask); + priv->write(0x0, &regs->rx15mask);

if (priv->devtype_data->quirks & FLEXCAN_QUIRK_DISABLE_RXFG) - flexcan_write(0x0, &regs->rxfgmask); + priv->write(0x0, &regs->rxfgmask);

/* clear acceptance filters */ for (i = 0; i < ARRAY_SIZE(regs->mb); i++) - flexcan_write(0, &regs->rximr[i]); + priv->write(0, &regs->rximr[i]);

/* On Vybrid, disable memory error detection interrupts * and freeze mode. @@@ -1011,16 -1029,16 +1029,16 @@@ * and Correction of Memory Errors" to write to * MECR register */ - reg_ctrl2 = flexcan_read(&regs->ctrl2); + reg_ctrl2 = priv->read(&regs->ctrl2); reg_ctrl2 |= FLEXCAN_CTRL2_ECRWRE; - flexcan_write(reg_ctrl2, &regs->ctrl2); + priv->write(reg_ctrl2, &regs->ctrl2);

- reg_mecr = flexcan_read(&regs->mecr); + reg_mecr = priv->read(&regs->mecr); reg_mecr &= ~FLEXCAN_MECR_ECRWRDIS; - flexcan_write(reg_mecr, &regs->mecr); + priv->write(reg_mecr, &regs->mecr); reg_mecr &= ~(FLEXCAN_MECR_NCEFAFRZ | FLEXCAN_MECR_HANCEI_MSK | FLEXCAN_MECR_FANCEI_MSK); - flexcan_write(reg_mecr, &regs->mecr); + priv->write(reg_mecr, &regs->mecr); }

err = flexcan_transceiver_enable(priv); @@@ -1036,14 -1054,14 +1054,14 @@@

/* enable interrupts atomically */ disable_irq(dev->irq); - flexcan_write(priv->reg_ctrl_default, &regs->ctrl); - flexcan_write(priv->reg_imask1_default, &regs->imask1); - flexcan_write(priv->reg_imask2_default, &regs->imask2); + priv->write(priv->reg_ctrl_default, &regs->ctrl); + priv->write(priv->reg_imask1_default, &regs->imask1); + priv->write(priv->reg_imask2_default, &regs->imask2); enable_irq(dev->irq);

/* print chip status */ netdev_dbg(dev, "%s: reading mcr=0x%08x ctrl=0x%08x\n", __func__, - flexcan_read(&regs->mcr), flexcan_read(&regs->ctrl)); + priv->read(&regs->mcr), priv->read(&regs->ctrl));

return 0;

@@@ -1068,10 -1086,10 +1086,10 @@@ static void flexcan_chip_stop(struct ne flexcan_chip_disable(priv);

/* Disable all interrupts */ - flexcan_write(0, &regs->imask2); - flexcan_write(0, &regs->imask1); - flexcan_write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL, - &regs->ctrl); + priv->write(0, &regs->imask2); + priv->write(0, &regs->imask1); + priv->write(priv->reg_ctrl_default & ~FLEXCAN_CTRL_ERR_ALL, + &regs->ctrl);

flexcan_transceiver_disable(priv); priv->can.state = CAN_STATE_STOPPED; @@@ -1186,26 -1204,26 +1204,26 @@@ static int register_flexcandev(struct n err = flexcan_chip_disable(priv); if (err) goto out_disable_per; - reg = flexcan_read(&regs->ctrl); + reg = priv->read(&regs->ctrl); reg |= FLEXCAN_CTRL_CLK_SRC; - flexcan_write(reg, &regs->ctrl); + priv->write(reg, &regs->ctrl);

err = flexcan_chip_enable(priv); if (err) goto out_chip_disable;

/* set freeze, halt and activate FIFO, restrict register access */ - reg = flexcan_read(&regs->mcr); + reg = priv->read(&regs->mcr); reg |= FLEXCAN_MCR_FRZ | FLEXCAN_MCR_HALT | FLEXCAN_MCR_FEN | FLEXCAN_MCR_SUPV; - flexcan_write(reg, &regs->mcr); + priv->write(reg, &regs->mcr);

/* Currently we only support newer versions of this core * featuring a RX hardware FIFO (although this driver doesn't * make use of it on some cores). Older cores, found on some * Coldfire derivates are not tested. */ - reg = flexcan_read(&regs->mcr); + reg = priv->read(&regs->mcr); if (!(reg & FLEXCAN_MCR_FEN)) { netdev_err(dev, "Could not enable RX FIFO, unsupported core\n"); err = -ENODEV; @@@ -1233,8 -1251,12 +1251,12 @@@ static void unregister_flexcandev(struc static const struct of_device_id flexcan_of_match[] = { { .compatible = "fsl,imx6q-flexcan", .data = &fsl_imx6q_devtype_data, }, { .compatible = "fsl,imx28-flexcan", .data = &fsl_imx28_devtype_data, }, + { .compatible = "fsl,imx53-flexcan", .data = &fsl_p1010_devtype_data, }, + { .compatible = "fsl,imx35-flexcan", .data = &fsl_p1010_devtype_data, }, + { .compatible = "fsl,imx25-flexcan", .data = &fsl_p1010_devtype_data, }, { .compatible = "fsl,p1010-flexcan", .data = &fsl_p1010_devtype_data, }, { .compatible = "fsl,vf610-flexcan", .data = &fsl_vf610_devtype_data, }, + { .compatible = "fsl,ls1021ar2-flexcan", .data = &fsl_ls1021a_r2_devtype_data, }, { /* sentinel */ }, }; MODULE_DEVICE_TABLE(of, flexcan_of_match); @@@ -1314,6 -1336,21 +1336,21 @@@ static int flexcan_probe(struct platfor dev->flags |= IFF_ECHO;

priv = netdev_priv(dev); + + if (of_property_read_bool(pdev->dev.of_node, "big-endian")) { + priv->read = flexcan_read_be; + priv->write = flexcan_write_be; + } else { + if (of_device_is_compatible(pdev->dev.of_node, + "fsl,p1010-flexcan")) { + priv->read = flexcan_read_be; + priv->write = flexcan_write_be; + } else { + priv->read = flexcan_read_le; + priv->write = flexcan_write_le; + } + } + priv->can.clock.freq = clock_freq; priv->can.bittiming_const = &flexcan_bittiming_const; priv->can.do_set_mode = flexcan_set_mode; diff --combined drivers/net/can/vxcan.c index b4c4a2c76437,5d1753cfacea..ed6828821fbd --- a/drivers/net/can/vxcan.c +++ b/drivers/net/can/vxcan.c @@@ -194,7 -194,7 +194,7 @@@ static int vxcan_newlink(struct net *ne tbp = peer_tb; }

- if (tbp[IFLA_IFNAME]) { + if (ifmp && tbp[IFLA_IFNAME]) { nla_strlcpy(ifname, tbp[IFLA_IFNAME], IFNAMSIZ); name_assign_type = NET_NAME_USER; } else { @@@ -227,10 -227,8 +227,8 @@@ netif_carrier_off(peer);

err = rtnl_configure_link(peer, ifmp); - if (err < 0) { - unregister_netdevice(peer); - return err; - } + if (err < 0) + goto unregister_network_device;

/* register first device */ if (tb[IFLA_IFNAME]) @@@ -239,10 -237,8 +237,8 @@@ snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d");

err = register_netdevice(dev); - if (err < 0) { - unregister_netdevice(peer); - return err; - } + if (err < 0) + goto unregister_network_device;

netif_carrier_off(dev);

@@@ -254,6 -250,10 +250,10 @@@ rcu_assign_pointer(priv->peer, dev);

return 0; + + unregister_network_device: + unregister_netdevice(peer); + return err; }

static void vxcan_dellink(struct net_device *dev, struct list_head *head) diff --combined drivers/net/dsa/b53/b53_common.c index 4498ab897d94,561b05089cb6..db830a1141d9 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@@ -1029,8 -1029,7 +1029,7 @@@ int b53_vlan_filtering(struct dsa_switc EXPORT_SYMBOL(b53_vlan_filtering);

int b53_vlan_prepare(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_vlan *vlan, - struct switchdev_trans *trans) + const struct switchdev_obj_port_vlan *vlan) { struct b53_device *dev = ds->priv;

@@@ -1047,8 -1046,7 +1046,7 @@@ EXPORT_SYMBOL(b53_vlan_prepare);

void b53_vlan_add(struct dsa_switch *ds, int port, - const struct switchdev_obj_port_vlan *vlan, - struct switchdev_trans *trans) + const struct switchdev_obj_port_vlan *vlan) { struct b53_device *dev = ds->priv; bool untagged = vlan->flags & BRIDGE_VLAN_INFO_UNTAGGED; @@@ -1495,18 -1493,14 +1493,17 @@@ static bool b53_can_enable_brcm_tags(st return false; }

- static enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, - int port) + enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port) { struct b53_device *dev = ds->priv;

- /* Older models support a different tag format that we do not - * support in net/dsa/tag_brcm.c yet. + /* Older models (5325, 5365) support a different tag format that we do + * not support in net/dsa/tag_brcm.c yet. 539x and 531x5 require managed + * mode to be turned on which means we need to specifically manage ARL + * misses on multicast addresses (TBD). */ - if (is5325(dev) || is5365(dev) || !b53_can_enable_brcm_tags(ds, port)) + if (is5325(dev) || is5365(dev) || is539x(dev) || is531x5(dev) || + !b53_can_enable_brcm_tags(ds, port)) return DSA_TAG_PROTO_NONE;

/* Broadcom BCM58xx chips have a flow accelerator on Port 8 @@@ -1517,6 -1511,7 +1514,7 @@@

return DSA_TAG_PROTO_BRCM; } + EXPORT_SYMBOL(b53_get_tag_protocol);

int b53_mirror_add(struct dsa_switch *ds, int port, struct dsa_mall_mirror_tc_entry *mirror, bool ingress) diff --combined drivers/net/ethernet/amazon/ena/ena_netdev.c index fbe21a817bd8,a6f283232cb7..6975150d144e --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@@ -75,9 -75,6 +75,9 @@@ static struct workqueue_struct *ena_wq MODULE_DEVICE_TABLE(pci, ena_pci_tbl);

static int ena_rss_init_default(struct ena_adapter *adapter); +static void check_for_admin_com_state(struct ena_adapter *adapter); +static void ena_destroy_device(struct ena_adapter *adapter); +static int ena_restore_device(struct ena_adapter *adapter);

static void ena_tx_timeout(struct net_device *dev) { @@@ -161,6 -158,8 +161,8 @@@ static void ena_init_io_rings_common(st ring->per_napi_packets = 0; ring->per_napi_bytes = 0; ring->cpu = 0; + ring->first_interrupt = false; + ring->no_interrupt_event_cnt = 0; u64_stats_init(&ring->syncp); }

@@@ -1277,6 -1276,9 +1279,9 @@@ static irqreturn_t ena_intr_msix_io(in { struct ena_napi *ena_napi = data;

+ ena_napi->tx_ring->first_interrupt = true; + ena_napi->rx_ring->first_interrupt = true; + napi_schedule_irqoff(&ena_napi->napi);

return IRQ_HANDLED; @@@ -1568,7 -1570,7 +1573,7 @@@ static int ena_rss_configure(struct ena

static int ena_up_complete(struct ena_adapter *adapter) { - int rc, i; + int rc;

rc = ena_rss_configure(adapter); if (rc) @@@ -1587,6 -1589,17 +1592,6 @@@

ena_napi_enable_all(adapter);

- /* Enable completion queues interrupt */ - for (i = 0; i < adapter->num_queues; i++) - ena_unmask_interrupt(&adapter->tx_ring[i], - &adapter->rx_ring[i]); - - /* schedule napi in case we had pending packets - * from the last time we disable napi - */ - for (i = 0; i < adapter->num_queues; i++) - napi_schedule(&adapter->ena_napi[i].napi); - return 0; }

@@@ -1723,7 -1736,7 +1728,7 @@@ create_err

static int ena_up(struct ena_adapter *adapter) { - int rc; + int rc, i;

netdev_dbg(adapter->netdev, "%s\n", __func__);

@@@ -1766,17 -1779,6 +1771,17 @@@

set_bit(ENA_FLAG_DEV_UP, &adapter->flags);

+ /* Enable completion queues interrupt */ + for (i = 0; i < adapter->num_queues; i++) + ena_unmask_interrupt(&adapter->tx_ring[i], + &adapter->rx_ring[i]); + + /* schedule napi in case we had pending packets + * from the last time we disable napi + */ + for (i = 0; i < adapter->num_queues; i++) + napi_schedule(&adapter->ena_napi[i].napi); + return rc;

err_up: @@@ -1887,17 -1889,6 +1892,17 @@@ static int ena_close(struct net_device if (test_bit(ENA_FLAG_DEV_UP, &adapter->flags)) ena_down(adapter);

+ /* Check for device status and issue reset if needed*/ + check_for_admin_com_state(adapter); + if (unlikely(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags))) { + netif_err(adapter, ifdown, adapter->netdev, + "Destroy failure, restarting device\n"); + ena_dump_stats_to_dmesg(adapter); + /* rtnl lock already obtained in dev_ioctl() layer */ + ena_destroy_device(adapter); + ena_restore_device(adapter); + } + return 0; }

@@@ -2558,12 -2549,11 +2563,12 @@@ static void ena_destroy_device(struct e

ena_com_set_admin_running_state(ena_dev, false);

- ena_close(netdev); + if (test_bit(ENA_FLAG_DEV_UP, &adapter->flags)) + ena_down(adapter);

/* Before releasing the ENA resources, a device reset is required. * (to prevent the device from accessing them). - * In case the reset flag is set and the device is up, ena_close + * In case the reset flag is set and the device is up, ena_down() * already perform the reset, so it can be skipped. */ if (!(test_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags) && dev_up)) @@@ -2663,8 -2653,32 +2668,32 @@@ static void ena_fw_reset_device(struct rtnl_unlock(); }

- static int check_missing_comp_in_queue(struct ena_adapter *adapter, - struct ena_ring *tx_ring) + static int check_for_rx_interrupt_queue(struct ena_adapter *adapter, + struct ena_ring *rx_ring) + { + if (likely(rx_ring->first_interrupt)) + return 0; + + if (ena_com_cq_empty(rx_ring->ena_com_io_cq)) + return 0; + + rx_ring->no_interrupt_event_cnt++; + + if (rx_ring->no_interrupt_event_cnt == ENA_MAX_NO_INTERRUPT_ITERATIONS) { + netif_err(adapter, rx_err, adapter->netdev, + "Potential MSIX issue on Rx side Queue = %d. Reset the device\n", + rx_ring->qid); + adapter->reset_reason = ENA_REGS_RESET_MISS_INTERRUPT; + smp_mb__before_atomic(); + set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + return -EIO; + } + + return 0; + } + + static int check_missing_comp_in_tx_queue(struct ena_adapter *adapter, + struct ena_ring *tx_ring) { struct ena_tx_buffer *tx_buf; unsigned long last_jiffies; @@@ -2674,8 -2688,27 +2703,27 @@@ for (i = 0; i < tx_ring->ring_size; i++) { tx_buf = &tx_ring->tx_buffer_info[i]; last_jiffies = tx_buf->last_jiffies; - if (unlikely(last_jiffies && - time_is_before_jiffies(last_jiffies + adapter->missing_tx_completion_to))) { + + if (last_jiffies == 0) + /* no pending Tx at this location */ + continue; + + if (unlikely(!tx_ring->first_interrupt && time_is_before_jiffies(last_jiffies + + 2 * adapter->missing_tx_completion_to))) { + /* If after graceful period interrupt is still not + * received, we schedule a reset + */ + netif_err(adapter, tx_err, adapter->netdev, + "Potential MSIX issue on Tx side Queue = %d. Reset the device\n", + tx_ring->qid); + adapter->reset_reason = ENA_REGS_RESET_MISS_INTERRUPT; + smp_mb__before_atomic(); + set_bit(ENA_FLAG_TRIGGER_RESET, &adapter->flags); + return -EIO; + } + + if (unlikely(time_is_before_jiffies(last_jiffies + + adapter->missing_tx_completion_to))) { if (!tx_buf->print_once) netif_notice(adapter, tx_err, adapter->netdev, "Found a Tx that wasn't completed on time, qid %d, index %d.\n", @@@ -2704,9 -2737,10 +2752,10 @@@ return rc; }

- static void check_for_missing_tx_completions(struct ena_adapter *adapter) + static void check_for_missing_completions(struct ena_adapter *adapter) { struct ena_ring *tx_ring; + struct ena_ring *rx_ring; int i, budget, rc;

/* Make sure the driver doesn't turn the device in other process */ @@@ -2725,8 -2759,13 +2774,13 @@@

for (i = adapter->last_monitored_tx_qid; i < adapter->num_queues; i++) { tx_ring = &adapter->tx_ring[i]; + rx_ring = &adapter->rx_ring[i]; + + rc = check_missing_comp_in_tx_queue(adapter, tx_ring); + if (unlikely(rc)) + return;

- rc = check_missing_comp_in_queue(adapter, tx_ring); + rc = check_for_rx_interrupt_queue(adapter, rx_ring); if (unlikely(rc)) return;

@@@ -2885,7 -2924,7 +2939,7 @@@ static void ena_timer_service(struct ti

check_for_admin_com_state(adapter);

- check_for_missing_tx_completions(adapter); + check_for_missing_completions(adapter);

check_for_empty_rx_ring(adapter);

diff --combined drivers/net/ethernet/broadcom/bcmsysport.c index 9d7a834c5f62,f15a8fc6dfc9..c2969b260aed --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@@ -1156,7 -1156,7 +1156,7 @@@ static struct sk_buff *bcm_sysport_inse memset(tsb, 0, sizeof(*tsb));

if (skb->ip_summed == CHECKSUM_PARTIAL) { - ip_ver = htons(skb->protocol); + ip_ver = ntohs(skb->protocol); switch (ip_ver) { case ETH_P_IP: ip_proto = ip_hdr(skb)->protocol; @@@ -1216,18 -1216,6 +1216,6 @@@ static netdev_tx_t bcm_sysport_xmit(str goto out; }

- /* The Ethernet switch we are interfaced with needs packets to be at - * least 64 bytes (including FCS) otherwise they will be discarded when - * they enter the switch port logic. When Broadcom tags are enabled, we - * need to make sure that packets are at least 68 bytes - * (including FCS and tag) because the length verification is done after - * the Broadcom tag is stripped off the ingress packet. - */ - if (skb_put_padto(skb, ETH_ZLEN + ENET_BRCM_TAG_LEN)) { - ret = NETDEV_TX_OK; - goto out; - } - /* Insert TSB and checksum infos */ if (priv->tsb_en) { skb = bcm_sysport_insert_tsb(skb, dev); diff --combined drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index d8fee26cd45e,2ae5ed151369..1d9b08c20f95 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@@ -54,12 -54,10 +54,10 @@@ static int bnxt_tc_parse_redir(struct b struct bnxt_tc_actions *actions, const struct tc_action *tc_act) { - int ifindex = tcf_mirred_ifindex(tc_act); - struct net_device *dev; + struct net_device *dev = tcf_mirred_dev(tc_act);

- dev = __dev_get_by_index(dev_net(bp->dev), ifindex); if (!dev) { - netdev_info(bp->dev, "no dev for ifindex=%d", ifindex); + netdev_info(bp->dev, "no dev in mirred action"); return -EINVAL; }

@@@ -148,9 -146,6 +146,6 @@@ static int bnxt_tc_parse_actions(struc } }

- if (rc) - return rc; - if (actions->flags & BNXT_TC_ACTION_FLAG_FWD) { if (actions->flags & BNXT_TC_ACTION_FLAG_TUNNEL_ENCAP) { /* dst_fid is PF's fid */ @@@ -164,7 -159,7 +159,7 @@@ } }

- return rc; + return 0; }

#define GET_KEY(flow_cmd, key_type) \ @@@ -421,7 -416,7 +416,7 @@@ static int bnxt_hwrm_cfa_flow_alloc(str }

/* If all IP and L4 fields are wildcarded then this is an L2 flow */ - if (is_wildcard(&l3_mask, sizeof(l3_mask)) && + if (is_wildcard(l3_mask, sizeof(*l3_mask)) && is_wildcard(&flow->l4_mask, sizeof(flow->l4_mask))) { flow_flags |= CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_L2; } else { @@@ -1417,11 -1412,7 +1412,7 @@@ bnxt_tc_flow_stats_batch_prep(struct bn void *flow_node; int rc, i;

- rc = rhashtable_walk_start(iter); - if (rc && rc != -EAGAIN) { - i = 0; - goto done; - } + rhashtable_walk_start(iter);

rc = 0; for (i = 0; i < BNXT_FLOW_STATS_BATCH_MAX; i++) { diff --combined drivers/net/ethernet/broadcom/tg3.c index 86ff8b49ee57,a77ee2f8fb8d..2bd77d9990f2 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@@ -3227,7 -3227,7 +3227,7 @@@ static int tg3_nvram_read_using_eeprom( return 0; }

- #define NVRAM_CMD_TIMEOUT 5000 + #define NVRAM_CMD_TIMEOUT 10000

static int tg3_nvram_exec_cmd(struct tg3 *tp, u32 nvram_cmd) { @@@ -3744,7 -3744,7 +3744,7 @@@ static int tg3_load_firmware_cpu(struc }

do { - u32 *fw_data = (u32 *)(fw_hdr + 1); + __be32 *fw_data = (__be32 *)(fw_hdr + 1); for (i = 0; i < tg3_fw_data_len(tp, fw_hdr); i++) write_op(tp, cpu_scratch_base + (be32_to_cpu(fw_hdr->base_addr) & 0xffff) + @@@ -14789,7 -14789,7 +14789,7 @@@ static void tg3_get_5717_nvram_info(str

static void tg3_get_5720_nvram_info(struct tg3 *tp) { - u32 nvcfg1, nvmpinstrp; + u32 nvcfg1, nvmpinstrp, nv_status;

nvcfg1 = tr32(NVRAM_CFG1); nvmpinstrp = nvcfg1 & NVRAM_CFG1_5752VENDOR_MASK; @@@ -14801,6 -14801,23 +14801,23 @@@ }

switch (nvmpinstrp) { + case FLASH_5762_MX25L_100: + case FLASH_5762_MX25L_200: + case FLASH_5762_MX25L_400: + case FLASH_5762_MX25L_800: + case FLASH_5762_MX25L_160_320: + tp->nvram_pagesize = 4096; + tp->nvram_jedecnum = JEDEC_MACRONIX; + tg3_flag_set(tp, NVRAM_BUFFERED); + tg3_flag_set(tp, NO_NVRAM_ADDR_TRANS); + tg3_flag_set(tp, FLASH); + nv_status = tr32(NVRAM_AUTOSENSE_STATUS); + tp->nvram_size = + (1 << (nv_status >> AUTOSENSE_DEVID & + AUTOSENSE_DEVID_MASK) + << AUTOSENSE_SIZE_IN_MB); + return; + case FLASH_5762_EEPROM_HD: nvmpinstrp = FLASH_5720_EEPROM_HD; break; diff --combined drivers/net/ethernet/chelsio/cxgb4/cxgb4.h index d8424ed16c33,69d0b64e6986..1ff71825868c --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4.h @@@ -77,7 -77,8 +77,8 @@@ enum MEM_EDC1, MEM_MC, MEM_MC0 = MEM_MC, - MEM_MC1 + MEM_MC1, + MEM_HMA, };

enum { @@@ -344,6 -345,7 +345,6 @@@ struct adapter_params

unsigned int sf_size; /* serial flash size in bytes */ unsigned int sf_nsec; /* # of flash sectors */ - unsigned int sf_fw_start; /* start of FW image in flash */

unsigned int fw_vers; /* firmware version */ unsigned int bs_vers; /* bootstrap version */ @@@ -1422,6 -1424,21 +1423,21 @@@ static inline void init_rspq(struct ada q->size = size; }

+ /** + * t4_is_inserted_mod_type - is a plugged in Firmware Module Type + * @fw_mod_type: the Firmware Mofule Type + * + * Return whether the Firmware Module Type represents a real Transceiver + * Module/Cable Module Type which has been inserted. + */ + static inline bool t4_is_inserted_mod_type(unsigned int fw_mod_type) + { + return (fw_mod_type != FW_PORT_MOD_TYPE_NONE && + fw_mod_type != FW_PORT_MOD_TYPE_NOTSUPPORTED && + fw_mod_type != FW_PORT_MOD_TYPE_UNKNOWN && + fw_mod_type != FW_PORT_MOD_TYPE_ERROR); + } + void t4_write_indirect(struct adapter *adap, unsigned int addr_reg, unsigned int data_reg, const u32 *vals, unsigned int nregs, unsigned int start_idx); @@@ -1511,6 -1528,7 +1527,7 @@@ int t4_init_portinfo(struct port_info * int port, int pf, int vf, u8 mac[]); int t4_port_init(struct adapter *adap, int mbox, int pf, int vf); void t4_fatal_err(struct adapter *adapter); + unsigned int t4_chip_rss_size(struct adapter *adapter); int t4_config_rss_range(struct adapter *adapter, int mbox, unsigned int viid, int start, int n, const u16 *rspq, unsigned int nrspq); int t4_config_glbl_rss(struct adapter *adapter, int mbox, unsigned int mode, @@@ -1652,7 -1670,7 +1669,7 @@@ int t4_ctrl_eq_free(struct adapter *ada unsigned int vf, unsigned int eqid); int t4_ofld_eq_free(struct adapter *adap, unsigned int mbox, unsigned int pf, unsigned int vf, unsigned int eqid); - int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox); + int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type); void t4_handle_get_port_info(struct port_info *pi, const __be64 *rpl); int t4_update_port_info(struct port_info *pi); int t4_get_link_params(struct port_info *pi, unsigned int *link_okp, @@@ -1695,6 -1713,9 +1712,9 @@@ void t4_uld_mem_free(struct adapter *ad int t4_uld_mem_alloc(struct adapter *adap); void t4_uld_clean_up(struct adapter *adap); void t4_register_netevent_notifier(void); + int t4_i2c_rd(struct adapter *adap, unsigned int mbox, int port, + unsigned int devid, unsigned int offset, + unsigned int len, u8 *buf); void free_rspq_fl(struct adapter *adap, struct sge_rspq *rq, struct sge_fl *fl); void free_tx_desc(struct adapter *adap, struct sge_txq *q, unsigned int n, bool unmap); diff --combined drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index 375ef86a84da,f2a60e01d563..0e9f64a46ac5 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@@ -524,11 -524,14 +524,14 @@@ int t4_memory_rw(struct adapter *adap, * MEM_EDC1 = 1 * MEM_MC = 2 -- MEM_MC for chips with only 1 memory controller * MEM_MC1 = 3 -- for chips with 2 memory controllers (e.g. T5) + * MEM_HMA = 4 */ edc_size = EDRAM0_SIZE_G(t4_read_reg(adap, MA_EDRAM0_BAR_A)); - if (mtype != MEM_MC1) + if (mtype == MEM_HMA) { + memoffset = 2 * (edc_size * 1024 * 1024); + } else if (mtype != MEM_MC1) { memoffset = (mtype * (edc_size * 1024 * 1024)); - else { + } else { mc_size = EXT_MEM0_SIZE_G(t4_read_reg(adap, MA_EXT_MEMORY0_BAR_A)); memoffset = (MEM_MC0 * edc_size + mc_size) * 1024 * 1024; @@@ -2844,6 -2847,8 +2847,6 @@@ enum SF_RD_DATA_FAST = 0xb, /* read flash */ SF_RD_ID = 0x9f, /* read ID */ SF_ERASE_SECTOR = 0xd8, /* erase sector */ - - FW_MAX_SIZE = 16 * SF_SEC_SIZE, };

/** @@@ -3556,9 -3561,8 +3559,9 @@@ int t4_load_fw(struct adapter *adap, co const __be32 *p = (const __be32 *)fw_data; const struct fw_hdr *hdr = (const struct fw_hdr *)fw_data; unsigned int sf_sec_size = adap->params.sf_size / adap->params.sf_nsec; - unsigned int fw_img_start = adap->params.sf_fw_start; - unsigned int fw_start_sec = fw_img_start / sf_sec_size; + unsigned int fw_start_sec = FLASH_FW_START_SEC; + unsigned int fw_size = FLASH_FW_MAX_SIZE; + unsigned int fw_start = FLASH_FW_START;

if (!size) { dev_err(adap->pdev_dev, "FW image has no data\n"); @@@ -3574,9 -3578,9 +3577,9 @@@ "FW image size differs from size in FW header\n"); return -EINVAL; } - if (size > FW_MAX_SIZE) { + if (size > fw_size) { dev_err(adap->pdev_dev, "FW image too large, max is %u bytes\n", - FW_MAX_SIZE); + fw_size); return -EFBIG; } if (!t4_fw_matches_chip(adap, hdr)) @@@ -3603,11 -3607,11 +3606,11 @@@ */ memcpy(first_page, fw_data, SF_PAGE_SIZE); ((struct fw_hdr *)first_page)->fw_ver = cpu_to_be32(0xffffffff); - ret = t4_write_flash(adap, fw_img_start, SF_PAGE_SIZE, first_page); + ret = t4_write_flash(adap, fw_start, SF_PAGE_SIZE, first_page); if (ret) goto out;

- addr = fw_img_start; + addr = fw_start; for (size -= SF_PAGE_SIZE; size; size -= SF_PAGE_SIZE) { addr += SF_PAGE_SIZE; fw_data += SF_PAGE_SIZE; @@@ -3617,7 -3621,7 +3620,7 @@@ }

ret = t4_write_flash(adap, - fw_img_start + offsetof(struct fw_hdr, fw_ver), + fw_start + offsetof(struct fw_hdr, fw_ver), sizeof(hdr->fw_ver), (const u8 *)&hdr->fw_ver); out: if (ret) @@@ -4923,6 -4927,14 +4926,14 @@@ void t4_intr_disable(struct adapter *ad t4_set_reg_field(adapter, PL_INT_MAP0_A, 1 << pf, 0); }

+ unsigned int t4_chip_rss_size(struct adapter *adap) + { + if (CHELSIO_CHIP_VERSION(adap->params.chip) <= CHELSIO_T5) + return RSS_NENTRIES; + else + return T6_RSS_NENTRIES; + } + /** * t4_config_rss_range - configure a portion of the RSS mapping table * @adapter: the adapter @@@ -5061,10 -5073,11 +5072,11 @@@ static int rd_rss_row(struct adapter *a */ int t4_read_rss(struct adapter *adapter, u16 *map) { + int i, ret, nentries; u32 val; - int i, ret;

- for (i = 0; i < RSS_NENTRIES / 2; ++i) { + nentries = t4_chip_rss_size(adapter); + for (i = 0; i < nentries / 2; ++i) { ret = rd_rss_row(adapter, i, &val); if (ret) return ret; @@@ -6071,6 -6084,7 +6083,7 @@@ const char *t4_get_port_type_descriptio "CR2_QSFP", "SFP28", "KR_SFP28", + "KR_XLAUI" };

if (port_type < ARRAY_SIZE(port_type_description)) @@@ -6526,18 -6540,21 +6539,21 @@@ void t4_sge_decode_idma_state(struct ad * t4_sge_ctxt_flush - flush the SGE context cache * @adap: the adapter * @mbox: mailbox to use for the FW command + * @ctx_type: Egress or Ingress * * Issues a FW command through the given mailbox to flush the * SGE context cache. */ - int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox) + int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type) { int ret; u32 ldst_addrspace; struct fw_ldst_cmd c;

memset(&c, 0, sizeof(c)); - ldst_addrspace = FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_SGE_EGRC); + ldst_addrspace = FW_LDST_CMD_ADDRSPACE_V(ctxt_type == CTXT_EGRESS ? + FW_LDST_ADDRSPC_SGE_EGRC : + FW_LDST_ADDRSPC_SGE_INGC); c.op_to_addrspace = cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) | FW_CMD_REQUEST_F | FW_CMD_READ_F | ldst_addrspace); @@@ -8491,22 -8508,6 +8507,6 @@@ found return 0; }

- static void set_pcie_completion_timeout(struct adapter *adapter, u8 range) - { - u16 val; - u32 pcie_cap; - - pcie_cap = pci_find_capability(adapter->pdev, PCI_CAP_ID_EXP); - if (pcie_cap) { - pci_read_config_word(adapter->pdev, - pcie_cap + PCI_EXP_DEVCTL2, &val); - val &= ~PCI_EXP_DEVCTL2_COMP_TIMEOUT; - val |= range; - pci_write_config_word(adapter->pdev, - pcie_cap + PCI_EXP_DEVCTL2, val); - } - } - /** * t4_prep_adapter - prepare SW and HW for operation * @adapter: the adapter @@@ -8592,8 -8593,9 +8592,9 @@@ int t4_prep_adapter(struct adapter *ada adapter->params.portvec = 1; adapter->params.vpd.cclk = 50000;

- /* Set pci completion timeout value to 4 seconds. */ - set_pcie_completion_timeout(adapter, 0xd); + /* Set PCIe completion timeout to 4 seconds. */ + pcie_capability_clear_and_set_word(adapter->pdev, PCI_EXP_DEVCTL2, + PCI_EXP_DEVCTL2_COMP_TIMEOUT, 0xd); return 0; }

@@@ -9736,3 -9738,59 +9737,59 @@@ int t4_sched_params(struct adapter *ada return t4_wr_mbox_meat(adapter, adapter->mbox, &cmd, sizeof(cmd), NULL, 1); } + + /** + * t4_i2c_rd - read I2C data from adapter + * @adap: the adapter + * @port: Port number if per-port device; <0 if not + * @devid: per-port device ID or absolute device ID + * @offset: byte offset into device I2C space + * @len: byte length of I2C space data + * @buf: buffer in which to return I2C data + * + * Reads the I2C data from the indicated device and location. + */ + int t4_i2c_rd(struct adapter *adap, unsigned int mbox, int port, + unsigned int devid, unsigned int offset, + unsigned int len, u8 *buf) + { + struct fw_ldst_cmd ldst_cmd, ldst_rpl; + unsigned int i2c_max = sizeof(ldst_cmd.u.i2c.data); + int ret = 0; + + if (len > I2C_PAGE_SIZE) + return -EINVAL; + + /* Dont allow reads that spans multiple pages */ + if (offset < I2C_PAGE_SIZE && offset + len > I2C_PAGE_SIZE) + return -EINVAL; + + memset(&ldst_cmd, 0, sizeof(ldst_cmd)); + ldst_cmd.op_to_addrspace = + cpu_to_be32(FW_CMD_OP_V(FW_LDST_CMD) | + FW_CMD_REQUEST_F | + FW_CMD_READ_F | + FW_LDST_CMD_ADDRSPACE_V(FW_LDST_ADDRSPC_I2C)); + ldst_cmd.cycles_to_len16 = cpu_to_be32(FW_LEN16(ldst_cmd)); + ldst_cmd.u.i2c.pid = (port < 0 ? 0xff : port); + ldst_cmd.u.i2c.did = devid; + + while (len > 0) { + unsigned int i2c_len = (len < i2c_max) ? len : i2c_max; + + ldst_cmd.u.i2c.boffset = offset; + ldst_cmd.u.i2c.blen = i2c_len; + + ret = t4_wr_mbox(adap, mbox, &ldst_cmd, sizeof(ldst_cmd), + &ldst_rpl); + if (ret) + break; + + memcpy(buf, ldst_rpl.u.i2c.data, i2c_len); + offset += i2c_len; + buf += i2c_len; + len -= i2c_len; + } + + return ret; + } diff --combined drivers/net/ethernet/freescale/fec_main.c index a74300a4459c,e17d10b8b041..90aa69a08922 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@@ -1868,6 -1868,8 +1868,8 @@@ static int fec_enet_clk_enable(struct n ret = clk_prepare_enable(fep->clk_ref); if (ret) goto failed_clk_ref; + + phy_reset_after_clk_enable(ndev->phydev); } else { clk_disable_unprepare(fep->clk_ahb); clk_disable_unprepare(fep->clk_enet_out); @@@ -2840,6 -2842,7 +2842,7 @@@ fec_enet_open(struct net_device *ndev { struct fec_enet_private *fep = netdev_priv(ndev); int ret; + bool reset_again;

ret = pm_runtime_get_sync(&fep->pdev->dev); if (ret < 0) @@@ -2850,6 -2853,17 +2853,17 @@@ if (ret) goto clk_enable;

+ /* During the first fec_enet_open call the PHY isn't probed at this + * point. Therefore the phy_reset_after_clk_enable() call within + * fec_enet_clk_enable() fails. As we need this reset in order to be + * sure the PHY is working correctly we check if we need to reset again + * later when the PHY is probed + */ + if (ndev->phydev && ndev->phydev->drv) + reset_again = false; + else + reset_again = true; + /* I should reset the ring buffers here, but I don't yet know * a simple way to do that. */ @@@ -2866,6 -2880,12 +2880,12 @@@ if (ret) goto err_enet_mii_probe;

+ /* Call phy_reset_after_clk_enable() again if it failed during + * phy_reset_after_clk_enable() before because the PHY wasn't probed. + */ + if (reset_again) + phy_reset_after_clk_enable(ndev->phydev); + if (fep->quirks & FEC_QUIRK_ERR006687) imx6q_cpuidle_fec_irqs_used();

@@@ -3469,10 -3489,6 +3489,10 @@@ fec_probe(struct platform_device *pdev goto failed_regulator; } } else { + if (PTR_ERR(fep->reg_phy) == -EPROBE_DEFER) { + ret = -EPROBE_DEFER; + goto failed_regulator; + } fep->reg_phy = NULL; }

@@@ -3556,9 -3572,8 +3576,9 @@@ failed_clk_ipg failed_clk: if (of_phy_is_fixed_link(np)) of_phy_deregister_fixed_link(np); -failed_phy: of_node_put(phy_node); +failed_phy: + dev_id--; failed_ioremap: free_netdev(ndev);

diff --combined drivers/net/ethernet/intel/i40e/i40e_txrx.c index 5bc2748ac468,2a8a85e3ae8f..40edb6e5e6f6 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@@ -27,6 -27,7 +27,7 @@@ #include <linux/prefetch.h> #include <net/busy_poll.h> #include <linux/bpf_trace.h> + #include <net/xdp.h> #include "i40e.h" #include "i40e_trace.h" #include "i40e_prototype.h" @@@ -1236,6 -1237,8 +1237,8 @@@ void i40e_clean_rx_ring(struct i40e_rin void i40e_free_rx_resources(struct i40e_ring *rx_ring) { i40e_clean_rx_ring(rx_ring); + if (rx_ring->vsi->type == I40E_VSI_MAIN) + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); rx_ring->xdp_prog = NULL; kfree(rx_ring->rx_bi); rx_ring->rx_bi = NULL; @@@ -1256,6 -1259,7 +1259,7 @@@ int i40e_setup_rx_descriptors(struct i40e_ring *rx_ring) { struct device *dev = rx_ring->dev; + int err = -ENOMEM; int bi_size;

/* warn if we are about to overwrite the pointer */ @@@ -1283,13 -1287,21 +1287,21 @@@ rx_ring->next_to_clean = 0; rx_ring->next_to_use = 0;

+ /* XDP RX-queue info only needed for RX rings exposed to XDP */ + if (rx_ring->vsi->type == I40E_VSI_MAIN) { + err = xdp_rxq_info_reg(&rx_ring->xdp_rxq, rx_ring->netdev, + rx_ring->queue_index); + if (err < 0) + goto err; + } + rx_ring->xdp_prog = rx_ring->vsi->xdp_prog;

return 0; err: kfree(rx_ring->rx_bi); rx_ring->rx_bi = NULL; - return -ENOMEM; + return err; }

/** @@@ -2068,11 -2080,13 +2080,13 @@@ static int i40e_clean_rx_irq(struct i40 struct sk_buff *skb = rx_ring->skb; u16 cleaned_count = I40E_DESC_UNUSED(rx_ring); bool failure = false, xdp_xmit = false; + struct xdp_buff xdp; + + xdp.rxq = &rx_ring->xdp_rxq;

while (likely(total_rx_packets < (unsigned int)budget)) { struct i40e_rx_buffer *rx_buffer; union i40e_rx_desc *rx_desc; - struct xdp_buff xdp; unsigned int size; u16 vlan_tag; u8 rx_ptype; @@@ -3047,30 -3061,10 +3061,30 @@@ bool __i40e_chk_linearize(struct sk_buf /* Walk through fragments adding latest fragment, testing it, and * then removing stale fragments from the sum. */ - stale = &skb_shinfo(skb)->frags[0]; - for (;;) { + for (stale = &skb_shinfo(skb)->frags[0];; stale++) { + int stale_size = skb_frag_size(stale); + sum += skb_frag_size(frag++);

+ /* The stale fragment may present us with a smaller + * descriptor than the actual fragment size. To account + * for that we need to remove all the data on the front and + * figure out what the remainder would be in the last + * descriptor associated with the fragment. + */ + if (stale_size > I40E_MAX_DATA_PER_TXD) { + int align_pad = -(stale->page_offset) & + (I40E_MAX_READ_REQ_SIZE - 1); + + sum -= align_pad; + stale_size -= align_pad; + + do { + sum -= I40E_MAX_DATA_PER_TXD_ALIGNED; + stale_size -= I40E_MAX_DATA_PER_TXD_ALIGNED; + } while (stale_size > I40E_MAX_DATA_PER_TXD); + } + /* if sum is negative we failed to make sufficient progress */ if (sum < 0) return true; @@@ -3078,7 -3072,7 +3092,7 @@@ if (!nr_frags--) break;

- sum -= skb_frag_size(stale++); + sum -= stale_size; }

return false; diff --combined drivers/net/ethernet/mellanox/mlxsw/spectrum.c index c3837ca7a705,d373df7b11bd..aa96cc6a0fa6 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@@ -1571,14 -1571,11 +1571,11 @@@ mlxsw_sp_port_add_cls_matchall_mirror(s const struct tc_action *a, bool ingress) { - struct net *net = dev_net(mlxsw_sp_port->dev); enum mlxsw_sp_span_type span_type; struct mlxsw_sp_port *to_port; struct net_device *to_dev; - int ifindex;

- ifindex = tcf_mirred_ifindex(a); - to_dev = __dev_get_by_index(net, ifindex); + to_dev = tcf_mirred_dev(a); if (!to_dev) { netdev_err(mlxsw_sp_port->dev, "Could not find requested device\n"); return -EINVAL; @@@ -1838,6 -1835,54 +1835,54 @@@ static int mlxsw_sp_setup_tc(struct net } }

+ + static int mlxsw_sp_feature_hw_tc(struct net_device *dev, bool enable) + { + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + + if (!enable && (mlxsw_sp_port->acl_rule_count || + !list_empty(&mlxsw_sp_port->mall_tc_list))) { + netdev_err(dev, "Active offloaded tc filters, can't turn hw_tc_offload off\n"); + return -EINVAL; + } + return 0; + } + + typedef int (*mlxsw_sp_feature_handler)(struct net_device *dev, bool enable); + + static int mlxsw_sp_handle_feature(struct net_device *dev, + netdev_features_t wanted_features, + netdev_features_t feature, + mlxsw_sp_feature_handler feature_handler) + { + netdev_features_t changes = wanted_features ^ dev->features; + bool enable = !!(wanted_features & feature); + int err; + + if (!(changes & feature)) + return 0; + + err = feature_handler(dev, enable); + if (err) { + netdev_err(dev, "%s feature %pNF failed, err %d\n", + enable ? "Enable" : "Disable", &feature, err); + return err; + } + + if (enable) + dev->features |= feature; + else + dev->features &= ~feature; + + return 0; + } + static int mlxsw_sp_set_features(struct net_device *dev, + netdev_features_t features) + { + return mlxsw_sp_handle_feature(dev, features, NETIF_F_HW_TC, + mlxsw_sp_feature_hw_tc); + } + static const struct net_device_ops mlxsw_sp_port_netdev_ops = { .ndo_open = mlxsw_sp_port_open, .ndo_stop = mlxsw_sp_port_stop, @@@ -1852,6 -1897,7 +1897,7 @@@ .ndo_vlan_rx_add_vid = mlxsw_sp_port_add_vid, .ndo_vlan_rx_kill_vid = mlxsw_sp_port_kill_vid, .ndo_get_phys_port_name = mlxsw_sp_port_get_phys_port_name, + .ndo_set_features = mlxsw_sp_set_features, };

static void mlxsw_sp_port_get_drvinfo(struct net_device *dev, @@@ -4376,10 -4422,7 +4422,10 @@@ static int mlxsw_sp_netdevice_port_uppe } if (!info->linking) break; - if (netdev_has_any_upper_dev(upper_dev)) { + if (netdev_has_any_upper_dev(upper_dev) && + (!netif_is_bridge_master(upper_dev) || + !mlxsw_sp_bridge_device_is_offloaded(mlxsw_sp, + upper_dev))) { NL_SET_ERR_MSG(extack, "spectrum: Enslaving a port to a device that already has an upper device is not supported"); return -EINVAL; @@@ -4507,7 -4550,6 +4553,7 @@@ static int mlxsw_sp_netdevice_port_vlan u16 vid) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; struct netdev_notifier_changeupper_info *info = ptr; struct netlink_ext_ack *extack; struct net_device *upper_dev; @@@ -4524,10 -4566,7 +4570,10 @@@ } if (!info->linking) break; - if (netdev_has_any_upper_dev(upper_dev)) { + if (netdev_has_any_upper_dev(upper_dev) && + (!netif_is_bridge_master(upper_dev) || + !mlxsw_sp_bridge_device_is_offloaded(mlxsw_sp, + upper_dev))) { NL_SET_ERR_MSG(extack, "spectrum: Enslaving a port to a device that already has an upper device is not supported"); return -EINVAL; } diff --combined drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 05ce1befd9b3,a0adcd886589..346b8b688b6f --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@@ -270,6 -270,7 +270,7 @@@ struct mlxsw_sp_port struct mlxsw_sp_port_sample *sample; struct list_head vlans_list; struct mlxsw_sp_qdisc root_qdisc; + unsigned acl_rule_count; };

static inline bool @@@ -365,8 -366,6 +366,8 @@@ int mlxsw_sp_port_bridge_join(struct ml void mlxsw_sp_port_bridge_leave(struct mlxsw_sp_port *mlxsw_sp_port, struct net_device *brport_dev, struct net_device *br_dev); +bool mlxsw_sp_bridge_device_is_offloaded(const struct mlxsw_sp *mlxsw_sp, + const struct net_device *br_dev);

/* spectrum.c */ int mlxsw_sp_port_ets_set(struct mlxsw_sp_port *mlxsw_sp_port, diff --combined drivers/net/ethernet/renesas/sh_eth.c index b9e2846589f8,d47bbbb22e7c..7aa1c12750b3 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@@ -147,7 -147,7 +147,7 @@@ static const u16 sh_eth_offset_gigabit[ [FWNLCR0] = 0x0090, [FWALCR0] = 0x0094, [TXNLCR1] = 0x00a0, - [TXALCR1] = 0x00a0, + [TXALCR1] = 0x00a4, [RXNLCR1] = 0x00a8, [RXALCR1] = 0x00ac, [FWNLCR1] = 0x00b0, @@@ -399,7 -399,7 +399,7 @@@ static const u16 sh_eth_offset_fast_sh3 [FWNLCR0] = 0x0090, [FWALCR0] = 0x0094, [TXNLCR1] = 0x00a0, - [TXALCR1] = 0x00a0, + [TXALCR1] = 0x00a4, [RXNLCR1] = 0x00a8, [RXALCR1] = 0x00ac, [FWNLCR1] = 0x00b0, @@@ -3225,37 -3225,18 +3225,37 @@@ static int sh_eth_drv_probe(struct plat /* ioremap the TSU registers */ if (mdp->cd->tsu) { struct resource *rtsu; + rtsu = platform_get_resource(pdev, IORESOURCE_MEM, 1); - mdp->tsu_addr = devm_ioremap_resource(&pdev->dev, rtsu); - if (IS_ERR(mdp->tsu_addr)) { - ret = PTR_ERR(mdp->tsu_addr); + if (!rtsu) { + dev_err(&pdev->dev, "no TSU resource\n"); + ret = -ENODEV; + goto out_release; + } + /* We can only request the TSU region for the first port + * of the two sharing this TSU for the probe to succeed... + */ + if (devno % 2 == 0 && + !devm_request_mem_region(&pdev->dev, rtsu->start, + resource_size(rtsu), + dev_name(&pdev->dev))) { + dev_err(&pdev->dev, "can't request TSU resource.\n"); + ret = -EBUSY; + goto out_release; + } + mdp->tsu_addr = devm_ioremap(&pdev->dev, rtsu->start, + resource_size(rtsu)); + if (!mdp->tsu_addr) { + dev_err(&pdev->dev, "TSU region ioremap() failed.\n"); + ret = -ENOMEM; goto out_release; } mdp->port = devno % 2; ndev->features = NETIF_F_HW_VLAN_CTAG_FILTER; }

- /* initialize first or needed device */ - if (!devno || pd->needs_init) { + /* Need to init only the first port of the two sharing a TSU */ + if (devno % 2 == 0) { if (mdp->cd->chip_reset) mdp->cd->chip_reset(ndev);

@@@ -3301,8 -3282,7 +3301,7 @@@ out_napi_del

out_release: /* net_dev free */ - if (ndev) - free_netdev(ndev); + free_netdev(ndev);

pm_runtime_put(&pdev->dev); pm_runtime_disable(&pdev->dev); diff --combined drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 5bbcaf8298f6,2fd8456999f6..b419229d7457 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@@ -241,13 -241,12 +241,13 @@@ static int dwmac4_rx_check_timestamp(vo u32 own, ctxt; int ret = 1;

- own = p->des3 & RDES3_OWN; - ctxt = ((p->des3 & RDES3_CONTEXT_DESCRIPTOR) + own = le32_to_cpu(p->des3) & RDES3_OWN; + ctxt = ((le32_to_cpu(p->des3) & RDES3_CONTEXT_DESCRIPTOR) >> RDES3_CONTEXT_DESCRIPTOR_SHIFT);

if (likely(!own && ctxt)) { - if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff)) + if ((p->des0 == cpu_to_le32(0xffffffff)) && + (p->des1 == cpu_to_le32(0xffffffff))) /* Corrupted value */ ret = -EINVAL; else @@@ -266,7 -265,7 +266,7 @@@ static int dwmac4_wrback_get_rx_timesta int ret = -EINVAL;

/* Get the status from normal w/b descriptor */ - if (likely(p->des3 & TDES3_RS1V)) { + if (likely(p->des3 & cpu_to_le32(TDES3_RS1V))) { if (likely(le32_to_cpu(p->des1) & RDES1_TIMESTAMP_AVAILABLE)) { int i = 0;

@@@ -407,7 -406,7 +407,7 @@@ static void dwmac4_display_ring(void *h pr_info("%s descriptor ring:\n", rx ? "RX" : "TX");

for (i = 0; i < size; i++) { - pr_info("%d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n", + pr_info("%03d [0x%x]: 0x%x 0x%x 0x%x 0x%x\n", i, (unsigned int)virt_to_phys(p), le32_to_cpu(p->des0), le32_to_cpu(p->des1), le32_to_cpu(p->des2), le32_to_cpu(p->des3)); diff --combined drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 323464576fc0,d9c98fd810bb..cf0e16d1a068 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@@ -364,15 -364,9 +364,15 @@@ static void stmmac_eee_ctrl_timer(struc bool stmmac_eee_init(struct stmmac_priv *priv) { struct net_device *ndev = priv->dev; + int interface = priv->plat->interface; unsigned long flags; bool ret = false;

+ if ((interface != PHY_INTERFACE_MODE_MII) && + (interface != PHY_INTERFACE_MODE_GMII) && + !phy_interface_mode_is_rgmii(interface)) + goto out; + /* Using PCS we cannot dial with the phy registers at this stage * so we do not support extra feature like EEE. */ @@@ -2003,22 -1997,60 +2003,60 @@@ static void stmmac_set_dma_operation_mo static void stmmac_dma_interrupt(struct stmmac_priv *priv) { u32 tx_channel_count = priv->plat->tx_queues_to_use; - int status; + u32 rx_channel_count = priv->plat->rx_queues_to_use; + u32 channels_to_check = tx_channel_count > rx_channel_count ? + tx_channel_count : rx_channel_count; u32 chan; + bool poll_scheduled = false; + int status[channels_to_check]; + + /* Each DMA channel can be used for rx and tx simultaneously, yet + * napi_struct is embedded in struct stmmac_rx_queue rather than in a + * stmmac_channel struct. + * Because of this, stmmac_poll currently checks (and possibly wakes) + * all tx queues rather than just a single tx queue. + */ + for (chan = 0; chan < channels_to_check; chan++) + status[chan] = priv->hw->dma->dma_interrupt(priv->ioaddr, + &priv->xstats, + chan);

- for (chan = 0; chan < tx_channel_count; chan++) { - struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan]; + for (chan = 0; chan < rx_channel_count; chan++) { + if (likely(status[chan] & handle_rx)) { + struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan];

- status = priv->hw->dma->dma_interrupt(priv->ioaddr, - &priv->xstats, chan); - if (likely((status & handle_rx)) || (status & handle_tx)) { if (likely(napi_schedule_prep(&rx_q->napi))) { stmmac_disable_dma_irq(priv, chan); __napi_schedule(&rx_q->napi); + poll_scheduled = true; } } + }

- if (unlikely(status & tx_hard_error_bump_tc)) { + /* If we scheduled poll, we already know that tx queues will be checked. + * If we didn't schedule poll, see if any DMA channel (used by tx) has a + * completed transmission, if so, call stmmac_poll (once). + */ + if (!poll_scheduled) { + for (chan = 0; chan < tx_channel_count; chan++) { + if (status[chan] & handle_tx) { + /* It doesn't matter what rx queue we choose + * here. We use 0 since it always exists. + */ + struct stmmac_rx_queue *rx_q = + &priv->rx_queue[0]; + + if (likely(napi_schedule_prep(&rx_q->napi))) { + stmmac_disable_dma_irq(priv, chan); + __napi_schedule(&rx_q->napi); + } + break; + } + } + } + + for (chan = 0; chan < tx_channel_count; chan++) { + if (unlikely(status[chan] & tx_hard_error_bump_tc)) { /* Try to bump up the dma threshold on this failure */ if (unlikely(priv->xstats.threshold != SF_DMA_MODE) && (tc <= 256)) { @@@ -2035,7 -2067,7 +2073,7 @@@ chan); priv->xstats.threshold = tc; } - } else if (unlikely(status == tx_hard_error)) { + } else if (unlikely(status[chan] == tx_hard_error)) { stmmac_tx_err(priv, chan); } } @@@ -2539,7 -2571,7 +2577,7 @@@ static int stmmac_hw_setup(struct net_d }

if (priv->hw->pcs && priv->hw->mac->pcs_ctrl_ane) - priv->hw->mac->pcs_ctrl_ane(priv->hw, 1, priv->hw->ps, 0); + priv->hw->mac->pcs_ctrl_ane(priv->ioaddr, 1, priv->hw->ps, 0);

/* set TX and RX rings length */ stmmac_set_rings_length(priv); @@@ -3404,9 -3436,8 +3442,8 @@@ static int stmmac_rx(struct stmmac_pri if (netif_msg_rx_status(priv)) { netdev_dbg(priv->dev, "\tdesc: %p [entry %d] buff=0x%x\n", p, entry, des); - if (frame_len > ETH_FRAME_LEN) - netdev_dbg(priv->dev, "frame size %d, COE: %d\n", - frame_len, status); + netdev_dbg(priv->dev, "frame size %d, COE: %d\n", + frame_len, status); }

/* The zero-copy is always used for all the sizes diff --combined drivers/net/geneve.c index 0a48b3073d3d,667c44f68dbc..195e0d0add8d --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@@ -825,13 -825,6 +825,13 @@@ static int geneve_xmit_skb(struct sk_bu if (IS_ERR(rt)) return PTR_ERR(rt);

+ if (skb_dst(skb)) { + int mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr) - + GENEVE_BASE_HLEN - info->options_len - 14; + + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); + } + sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); if (geneve->collect_md) { tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); @@@ -871,13 -864,6 +871,13 @@@ static int geneve6_xmit_skb(struct sk_b if (IS_ERR(dst)) return PTR_ERR(dst);

+ if (skb_dst(skb)) { + int mtu = dst_mtu(dst) - sizeof(struct ipv6hdr) - + GENEVE_BASE_HLEN - info->options_len - 14; + + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu); + } + sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true); if (geneve->collect_md) { prio = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb); @@@ -1652,19 -1638,16 +1652,16 @@@ static __net_init int geneve_init_net(s return 0; }

- static void __net_exit geneve_exit_net(struct net *net) + static void geneve_destroy_tunnels(struct net *net, struct list_head *head) { struct geneve_net *gn = net_generic(net, geneve_net_id); struct geneve_dev *geneve, *next; struct net_device *dev, *aux; - LIST_HEAD(list); - - rtnl_lock();

/* gather any geneve devices that were moved into this ns */ for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &geneve_link_ops) - unregister_netdevice_queue(dev, &list); + unregister_netdevice_queue(dev, head);

/* now gather any other geneve devices that were created in this ns */ list_for_each_entry_safe(geneve, next, &gn->geneve_list, next) { @@@ -1672,18 -1655,29 +1669,29 @@@ * to the list by the previous loop. */ if (!net_eq(dev_net(geneve->dev), net)) - unregister_netdevice_queue(geneve->dev, &list); + unregister_netdevice_queue(geneve->dev, head); }

+ WARN_ON_ONCE(!list_empty(&gn->sock_list)); + } + + static void __net_exit geneve_exit_batch_net(struct list_head *net_list) + { + struct net *net; + LIST_HEAD(list); + + rtnl_lock(); + list_for_each_entry(net, net_list, exit_list) + geneve_destroy_tunnels(net, &list); + /* unregister the devices gathered above */ unregister_netdevice_many(&list); rtnl_unlock(); - WARN_ON_ONCE(!list_empty(&gn->sock_list)); }

static struct pernet_operations geneve_net_ops = { .init = geneve_init_net, - .exit = geneve_exit_net, + .exit_batch = geneve_exit_batch_net, .id = &geneve_net_id, .size = sizeof(struct geneve_net), }; diff --combined drivers/net/phy/phylink.c index 249ce5cbea22,d1f9466f2fbf..6ac8b29b2dc3 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@@ -36,7 -36,11 +36,11 @@@ enum PHYLINK_DISABLE_LINK, };

+ /** + * struct phylink - internal data type for phylink + */ struct phylink { + /* private: */ struct net_device *netdev; const struct phylink_mac_ops *ops;

@@@ -50,6 -54,8 +54,8 @@@ /* The link configuration settings */ struct phylink_link_state link_config; struct gpio_desc *link_gpio; + void (*get_fixed_state)(struct net_device *dev, + struct phylink_link_state *s);

struct mutex state_mutex; struct phylink_link_state phy_state; @@@ -87,6 -93,13 +93,13 @@@ static inline bool linkmode_empty(cons return bitmap_empty(src, __ETHTOOL_LINK_MODE_MASK_NBITS); }

+ /** + * phylink_set_port_modes() - set the port type modes in the ethtool mask + * @mask: ethtool link mode mask + * + * Sets all the port type modes in the ethtool mask. MAC drivers should + * use this in their 'validate' callback. + */ void phylink_set_port_modes(unsigned long *mask) { phylink_set(mask, TP); @@@ -117,8 -130,7 +130,7 @@@ static const char *phylink_an_mode_str( static const char *modestr[] = { [MLO_AN_PHY] = "phy", [MLO_AN_FIXED] = "fixed", - [MLO_AN_SGMII] = "SGMII", - [MLO_AN_8023Z] = "802.3z", + [MLO_AN_INBAND] = "inband", };

return mode < ARRAY_SIZE(modestr) ? modestr[mode] : "unknown"; @@@ -132,59 -144,64 +144,64 @@@ static int phylink_validate(struct phyl return phylink_is_empty_linkmode(supported) ? -EINVAL : 0; }

- static int phylink_parse_fixedlink(struct phylink *pl, struct device_node *np) + static int phylink_parse_fixedlink(struct phylink *pl, + struct fwnode_handle *fwnode) { - struct device_node *fixed_node; + struct fwnode_handle *fixed_node; const struct phy_setting *s; struct gpio_desc *desc; - const __be32 *fixed_prop; u32 speed; - int ret, len; + int ret;

- fixed_node = of_get_child_by_name(np, "fixed-link"); + fixed_node = fwnode_get_named_child_node(fwnode, "fixed-link"); if (fixed_node) { - ret = of_property_read_u32(fixed_node, "speed", &speed); + ret = fwnode_property_read_u32(fixed_node, "speed", &speed);

pl->link_config.speed = speed; pl->link_config.duplex = DUPLEX_HALF;

- if (of_property_read_bool(fixed_node, "full-duplex")) + if (fwnode_property_read_bool(fixed_node, "full-duplex")) pl->link_config.duplex = DUPLEX_FULL;

/* We treat the "pause" and "asym-pause" terminology as * defining the link partner's ability. */ - if (of_property_read_bool(fixed_node, "pause")) + if (fwnode_property_read_bool(fixed_node, "pause")) pl->link_config.pause |= MLO_PAUSE_SYM; - if (of_property_read_bool(fixed_node, "asym-pause")) + if (fwnode_property_read_bool(fixed_node, "asym-pause")) pl->link_config.pause |= MLO_PAUSE_ASYM;

if (ret == 0) { - desc = fwnode_get_named_gpiod(&fixed_node->fwnode, - "link-gpios", 0, - GPIOD_IN, "?"); + desc = fwnode_get_named_gpiod(fixed_node, "link-gpios", + 0, GPIOD_IN, "?");

if (!IS_ERR(desc)) pl->link_gpio = desc; else if (desc == ERR_PTR(-EPROBE_DEFER)) ret = -EPROBE_DEFER; } - of_node_put(fixed_node); + fwnode_handle_put(fixed_node);

if (ret) return ret; } else { - fixed_prop = of_get_property(np, "fixed-link", &len); - if (!fixed_prop) { + u32 prop[5]; + + ret = fwnode_property_read_u32_array(fwnode, "fixed-link", + NULL, 0); + if (ret != ARRAY_SIZE(prop)) { netdev_err(pl->netdev, "broken fixed-link?\n"); return -EINVAL; } - if (len == 5 * sizeof(*fixed_prop)) { - pl->link_config.duplex = be32_to_cpu(fixed_prop[1]) ? + + ret = fwnode_property_read_u32_array(fwnode, "fixed-link", + prop, ARRAY_SIZE(prop)); + if (!ret) { + pl->link_config.duplex = prop[1] ? DUPLEX_FULL : DUPLEX_HALF; - pl->link_config.speed = be32_to_cpu(fixed_prop[2]); - if (be32_to_cpu(fixed_prop[3])) + pl->link_config.speed = prop[2]; + if (prop[3]) pl->link_config.pause |= MLO_PAUSE_SYM; - if (be32_to_cpu(fixed_prop[4])) + if (prop[4]) pl->link_config.pause |= MLO_PAUSE_ASYM; } } @@@ -220,17 -237,17 +237,17 @@@ return 0; }

- static int phylink_parse_mode(struct phylink *pl, struct device_node *np) + static int phylink_parse_mode(struct phylink *pl, struct fwnode_handle *fwnode) { - struct device_node *dn; + struct fwnode_handle *dn; const char *managed;

- dn = of_get_child_by_name(np, "fixed-link"); - if (dn || of_find_property(np, "fixed-link", NULL)) + dn = fwnode_get_named_child_node(fwnode, "fixed-link"); + if (dn || fwnode_property_present(fwnode, "fixed-link")) pl->link_an_mode = MLO_AN_FIXED; - of_node_put(dn); + fwnode_handle_put(dn);

- if (of_property_read_string(np, "managed", &managed) == 0 && + if (fwnode_property_read_string(fwnode, "managed", &managed) == 0 && strcmp(managed, "in-band-status") == 0) { if (pl->link_an_mode == MLO_AN_FIXED) { netdev_err(pl->netdev, @@@ -244,6 -261,7 +261,7 @@@ phylink_set(pl->supported, Asym_Pause); phylink_set(pl->supported, Pause); pl->link_config.an_enabled = true; + pl->link_an_mode = MLO_AN_INBAND;

switch (pl->link_config.interface) { case PHY_INTERFACE_MODE_SGMII: @@@ -253,17 -271,14 +271,14 @@@ phylink_set(pl->supported, 100baseT_Full); phylink_set(pl->supported, 1000baseT_Half); phylink_set(pl->supported, 1000baseT_Full); - pl->link_an_mode = MLO_AN_SGMII; break;

case PHY_INTERFACE_MODE_1000BASEX: phylink_set(pl->supported, 1000baseX_Full); - pl->link_an_mode = MLO_AN_8023Z; break;

case PHY_INTERFACE_MODE_2500BASEX: phylink_set(pl->supported, 2500baseX_Full); - pl->link_an_mode = MLO_AN_8023Z; break;

case PHY_INTERFACE_MODE_10GKR: @@@ -280,7 -295,6 +295,6 @@@ phylink_set(pl->supported, 10000baseLR_Full); phylink_set(pl->supported, 10000baseLRM_Full); phylink_set(pl->supported, 10000baseER_Full); - pl->link_an_mode = MLO_AN_SGMII; break;

default: @@@ -320,8 -334,7 +334,7 @@@ static void phylink_mac_config(struct p static void phylink_mac_an_restart(struct phylink *pl) { if (pl->link_config.an_enabled && - (pl->link_config.interface == PHY_INTERFACE_MODE_1000BASEX || - pl->link_config.interface == PHY_INTERFACE_MODE_2500BASEX)) + phy_interface_mode_is_8023z(pl->link_config.interface)) pl->ops->mac_an_restart(pl->netdev); }

@@@ -339,12 -352,14 +352,14 @@@ static int phylink_get_mac_state(struc }

/* The fixed state is... fixed except for the link state, - * which may be determined by a GPIO. + * which may be determined by a GPIO or a callback. */ static void phylink_get_fixed_state(struct phylink *pl, struct phylink_link_state *state) { *state = pl->link_config; - if (pl->link_gpio) + if (pl->get_fixed_state) + pl->get_fixed_state(pl->netdev, state); + else if (pl->link_gpio) state->link = !!gpiod_get_value(pl->link_gpio); }

@@@ -423,7 -438,7 +438,7 @@@ static void phylink_resolve(struct work phylink_mac_config(pl, &link_state); break;

- case MLO_AN_SGMII: + case MLO_AN_INBAND: phylink_get_mac_state(pl, &link_state); if (pl->phydev) { bool changed = false; @@@ -449,10 -464,6 +464,6 @@@ } } break; - - case MLO_AN_8023Z: - phylink_get_mac_state(pl, &link_state); - break; } }

@@@ -489,15 -500,27 +500,27 @@@ static void phylink_run_resolve(struct

static const struct sfp_upstream_ops sfp_phylink_ops;

- static int phylink_register_sfp(struct phylink *pl, struct device_node *np) + static int phylink_register_sfp(struct phylink *pl, + struct fwnode_handle *fwnode) { - struct device_node *sfp_np; + struct fwnode_reference_args ref; + int ret;

- sfp_np = of_parse_phandle(np, "sfp", 0); - if (!sfp_np) + if (!fwnode) return 0;

- pl->sfp_bus = sfp_register_upstream(sfp_np, pl->netdev, pl, + ret = fwnode_property_get_reference_args(fwnode, "sfp", NULL, + 0, 0, &ref); + if (ret < 0) { + if (ret == -ENOENT) + return 0; + + netdev_err(pl->netdev, "unable to parse "sfp" node: %d\n", + ret); + return ret; + } + + pl->sfp_bus = sfp_register_upstream(ref.fwnode, pl->netdev, pl, &sfp_phylink_ops); if (!pl->sfp_bus) return -ENOMEM; @@@ -505,7 -528,22 +528,22 @@@ return 0; }

- struct phylink *phylink_create(struct net_device *ndev, struct device_node *np, + /** + * phylink_create() - create a phylink instance + * @ndev: a pointer to the &struct net_device + * @fwnode: a pointer to a &struct fwnode_handle describing the network + * interface + * @iface: the desired link mode defined by &typedef phy_interface_t + * @ops: a pointer to a &struct phylink_mac_ops for the MAC. + * + * Create a new phylink instance, and parse the link parameters found in @np. + * This will parse in-band modes, fixed-link or SFP configuration. + * + * Returns a pointer to a &struct phylink, or an error-pointer value. Users + * must use IS_ERR() to check for errors from this function. + */ + struct phylink *phylink_create(struct net_device *ndev, + struct fwnode_handle *fwnode, phy_interface_t iface, const struct phylink_mac_ops *ops) { @@@ -521,7 -559,10 +559,10 @@@ pl->netdev = ndev; pl->phy_state.interface = iface; pl->link_interface = iface; - pl->link_port = PORT_MII; + if (iface == PHY_INTERFACE_MODE_MOCA) + pl->link_port = PORT_BNC; + else + pl->link_port = PORT_MII; pl->link_config.interface = iface; pl->link_config.pause = MLO_PAUSE_AN; pl->link_config.speed = SPEED_UNKNOWN; @@@ -534,21 -575,21 +575,21 @@@ linkmode_copy(pl->link_config.advertising, pl->supported); phylink_validate(pl, pl->supported, &pl->link_config);

- ret = phylink_parse_mode(pl, np); + ret = phylink_parse_mode(pl, fwnode); if (ret < 0) { kfree(pl); return ERR_PTR(ret); }

if (pl->link_an_mode == MLO_AN_FIXED) { - ret = phylink_parse_fixedlink(pl, np); + ret = phylink_parse_fixedlink(pl, fwnode); if (ret < 0) { kfree(pl); return ERR_PTR(ret); } }

- ret = phylink_register_sfp(pl, np); + ret = phylink_register_sfp(pl, fwnode); if (ret < 0) { kfree(pl); return ERR_PTR(ret); @@@ -558,6 -599,13 +599,13 @@@ } EXPORT_SYMBOL_GPL(phylink_create);

+ /** + * phylink_destroy() - cleanup and destroy the phylink instance + * @pl: a pointer to a &struct phylink returned from phylink_create() + * + * Destroy a phylink instance. Any PHY that has been attached must have been + * cleaned up via phylink_disconnect_phy() prior to calling this function. + */ void phylink_destroy(struct phylink *pl) { if (pl->sfp_bus) @@@ -654,10 -702,39 +702,39 @@@ static int phylink_bringup_phy(struct p return 0; }

+ /** + * phylink_connect_phy() - connect a PHY to the phylink instance + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @phy: a pointer to a &struct phy_device. + * + * Connect @phy to the phylink instance specified by @pl by calling + * phy_attach_direct(). Configure the @phy according to the MAC driver's + * capabilities, start the PHYLIB state machine and enable any interrupts + * that the PHY supports. + * + * This updates the phylink's ethtool supported and advertising link mode + * masks. + * + * Returns 0 on success or a negative errno. + */ int phylink_connect_phy(struct phylink *pl, struct phy_device *phy) { int ret;

+ if (WARN_ON(pl->link_an_mode == MLO_AN_FIXED || + (pl->link_an_mode == MLO_AN_INBAND && + phy_interface_mode_is_8023z(pl->link_interface)))) + return -EINVAL; + + if (pl->phydev) + return -EBUSY; + + /* Use PHY device/driver interface */ + if (pl->link_interface == PHY_INTERFACE_MODE_NA) { + pl->link_interface = phy->interface; + pl->link_config.interface = pl->link_interface; + } + ret = phy_attach_direct(pl->netdev, phy, 0, pl->link_interface); if (ret) return ret; @@@ -670,14 -747,29 +747,29 @@@ } EXPORT_SYMBOL_GPL(phylink_connect_phy);

- int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn) + /** + * phylink_of_phy_connect() - connect the PHY specified in the DT mode. + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @dn: a pointer to a &struct device_node. + * @flags: PHY-specific flags to communicate to the PHY device driver + * + * Connect the phy specified in the device node @dn to the phylink instance + * specified by @pl. Actions specified in phylink_connect_phy() will be + * performed. + * + * Returns 0 on success or a negative errno. + */ + int phylink_of_phy_connect(struct phylink *pl, struct device_node *dn, + u32 flags) { struct device_node *phy_node; struct phy_device *phy_dev; int ret;

- /* Fixed links are handled without needing a PHY */ - if (pl->link_an_mode == MLO_AN_FIXED) + /* Fixed links and 802.3z are handled without needing a PHY */ + if (pl->link_an_mode == MLO_AN_FIXED || + (pl->link_an_mode == MLO_AN_INBAND && + phy_interface_mode_is_8023z(pl->link_interface))) return 0;

phy_node = of_parse_phandle(dn, "phy-handle", 0); @@@ -687,14 -779,13 +779,13 @@@ phy_node = of_parse_phandle(dn, "phy-device", 0);

if (!phy_node) { - if (pl->link_an_mode == MLO_AN_PHY) { - netdev_err(pl->netdev, "unable to find PHY node\n"); + if (pl->link_an_mode == MLO_AN_PHY) return -ENODEV; - } return 0; }

- phy_dev = of_phy_attach(pl->netdev, phy_node, 0, pl->link_interface); + phy_dev = of_phy_attach(pl->netdev, phy_node, flags, + pl->link_interface); /* We're done with the phy_node handle */ of_node_put(phy_node);

@@@ -709,11 -800,18 +800,18 @@@ } EXPORT_SYMBOL_GPL(phylink_of_phy_connect);

+ /** + * phylink_disconnect_phy() - disconnect any PHY attached to the phylink + * instance. + * @pl: a pointer to a &struct phylink returned from phylink_create() + * + * Disconnect any current PHY from the phylink instance described by @pl. + */ void phylink_disconnect_phy(struct phylink *pl) { struct phy_device *phy;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

phy = pl->phydev; if (phy) { @@@ -730,6 -828,40 +828,40 @@@ } EXPORT_SYMBOL_GPL(phylink_disconnect_phy);

+ /** + * phylink_fixed_state_cb() - allow setting a fixed link callback + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @cb: callback to execute to determine the fixed link state. + * + * The MAC driver should call this driver when the state of its link + * can be determined through e.g: an out of band MMIO register. + */ + int phylink_fixed_state_cb(struct phylink *pl, + void (*cb)(struct net_device *dev, + struct phylink_link_state *state)) + { + /* It does not make sense to let the link be overriden unless we use + * MLO_AN_FIXED + */ + if (pl->link_an_mode != MLO_AN_FIXED) + return -EINVAL; + + mutex_lock(&pl->state_mutex); + pl->get_fixed_state = cb; + mutex_unlock(&pl->state_mutex); + + return 0; + } + EXPORT_SYMBOL_GPL(phylink_fixed_state_cb); + + /** + * phylink_mac_change() - notify phylink of a change in MAC state + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @up: indicates whether the link is currently up. + * + * The MAC driver should call this driver when the state of its link + * changes (eg, link failure, new negotiation results, etc.) + */ void phylink_mac_change(struct phylink *pl, bool up) { if (!up) @@@ -739,9 -871,17 +871,17 @@@ } EXPORT_SYMBOL_GPL(phylink_mac_change);

+ /** + * phylink_start() - start a phylink instance + * @pl: a pointer to a &struct phylink returned from phylink_create() + * + * Start the phylink instance specified by @pl, configuring the MAC for the + * desired link mode(s) and negotiation style. This should be called from the + * network device driver's &struct net_device_ops ndo_open() method. + */ void phylink_start(struct phylink *pl) { - WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

netdev_info(pl->netdev, "configuring for %s/%s link mode\n", phylink_an_mode_str(pl->link_an_mode), @@@ -754,6 -894,12 +894,12 @@@ phylink_resolve_flow(pl, &pl->link_config); phylink_mac_config(pl, &pl->link_config);

+ /* Restart autonegotiation if using 802.3z to ensure that the link + * parameters are properly negotiated. This is necessary for DSA + * switches using 802.3z negotiation to ensure they see our modes. + */ + phylink_mac_an_restart(pl); + clear_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state); phylink_run_resolve(pl);

@@@ -764,9 -910,18 +910,18 @@@ } EXPORT_SYMBOL_GPL(phylink_start);

+ /** + * phylink_stop() - stop a phylink instance + * @pl: a pointer to a &struct phylink returned from phylink_create() + * + * Stop the phylink instance specified by @pl. This should be called from the + * network device driver's &struct net_device_ops ndo_stop() method. The + * network device's carrier state should not be changed prior to calling this + * function. + */ void phylink_stop(struct phylink *pl) { - WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

if (pl->phydev) phy_stop(pl->phydev); @@@ -779,9 -934,18 +934,18 @@@ } EXPORT_SYMBOL_GPL(phylink_stop);

+ /** + * phylink_ethtool_get_wol() - get the wake on lan parameters for the PHY + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @wol: a pointer to &struct ethtool_wolinfo to hold the read parameters + * + * Read the wake on lan parameters from the PHY attached to the phylink + * instance specified by @pl. If no PHY is currently attached, report no + * support for wake on lan. + */ void phylink_ethtool_get_wol(struct phylink *pl, struct ethtool_wolinfo *wol) { - WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

wol->supported = 0; wol->wolopts = 0; @@@ -791,11 -955,22 +955,22 @@@ } EXPORT_SYMBOL_GPL(phylink_ethtool_get_wol);

+ /** + * phylink_ethtool_set_wol() - set wake on lan parameters + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @wol: a pointer to &struct ethtool_wolinfo for the desired parameters + * + * Set the wake on lan parameters for the PHY attached to the phylink + * instance specified by @pl. If no PHY is attached, returns %EOPNOTSUPP + * error. + * + * Returns zero on success or negative errno code. + */ int phylink_ethtool_set_wol(struct phylink *pl, struct ethtool_wolinfo *wol) { int ret = -EOPNOTSUPP;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

if (pl->phydev) ret = phy_ethtool_set_wol(pl->phydev, wol); @@@ -826,12 -1001,21 +1001,21 @@@ static void phylink_get_ksettings(cons AUTONEG_DISABLE; }

+ /** + * phylink_ethtool_ksettings_get() - get the current link settings + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @kset: a pointer to a &struct ethtool_link_ksettings to hold link settings + * + * Read the current link settings for the phylink instance specified by @pl. + * This will be the link settings read from the MAC, PHY or fixed link + * settings depending on the current negotiation mode. + */ int phylink_ethtool_ksettings_get(struct phylink *pl, struct ethtool_link_ksettings *kset) { struct phylink_link_state link_state;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

if (pl->phydev) { phy_ethtool_ksettings_get(pl->phydev, kset); @@@ -851,14 -1035,13 +1035,13 @@@ phylink_get_ksettings(&link_state, kset); break;

- case MLO_AN_SGMII: + case MLO_AN_INBAND: /* If there is a phy attached, then use the reported * settings from the phy with no modification. */ if (pl->phydev) break;

- case MLO_AN_8023Z: phylink_get_mac_state(pl, &link_state);

/* The MAC is reporting the link results from its own PCS @@@ -873,6 -1056,11 +1056,11 @@@ } EXPORT_SYMBOL_GPL(phylink_ethtool_ksettings_get);

+ /** + * phylink_ethtool_ksettings_set() - set the link settings + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @kset: a pointer to a &struct ethtool_link_ksettings for the desired modes + */ int phylink_ethtool_ksettings_set(struct phylink *pl, const struct ethtool_link_ksettings *kset) { @@@ -880,7 -1068,7 +1068,7 @@@ struct phylink_link_state config; int ret;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

if (kset->base.autoneg != AUTONEG_DISABLE && kset->base.autoneg != AUTONEG_ENABLE) @@@ -967,11 -1155,22 +1155,22 @@@ } EXPORT_SYMBOL_GPL(phylink_ethtool_ksettings_set);

+ /** + * phylink_ethtool_nway_reset() - restart negotiation + * @pl: a pointer to a &struct phylink returned from phylink_create() + * + * Restart negotiation for the phylink instance specified by @pl. This will + * cause any attached phy to restart negotiation with the link partner, and + * if the MAC is in a BaseX mode, the MAC will also be requested to restart + * negotiation. + * + * Returns zero on success, or negative error code. + */ int phylink_ethtool_nway_reset(struct phylink *pl) { int ret = 0;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

if (pl->phydev) ret = phy_restart_aneg(pl->phydev); @@@ -981,10 -1180,15 +1180,15 @@@ } EXPORT_SYMBOL_GPL(phylink_ethtool_nway_reset);

+ /** + * phylink_ethtool_get_pauseparam() - get the current pause parameters + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @pause: a pointer to a &struct ethtool_pauseparam + */ void phylink_ethtool_get_pauseparam(struct phylink *pl, struct ethtool_pauseparam *pause) { - WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

pause->autoneg = !!(pl->link_config.pause & MLO_PAUSE_AN); pause->rx_pause = !!(pl->link_config.pause & MLO_PAUSE_RX); @@@ -992,12 -1196,17 +1196,17 @@@ } EXPORT_SYMBOL_GPL(phylink_ethtool_get_pauseparam);

+ /** + * phylink_ethtool_set_pauseparam() - set the current pause parameters + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @pause: a pointer to a &struct ethtool_pauseparam + */ int phylink_ethtool_set_pauseparam(struct phylink *pl, struct ethtool_pauseparam *pause) { struct phylink_link_state *config = &pl->link_config;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

if (!phylink_test(pl->supported, Pause) && !phylink_test(pl->supported, Asym_Pause)) @@@ -1030,8 -1239,7 +1239,7 @@@ phylink_mac_config(pl, config); break;

- case MLO_AN_SGMII: - case MLO_AN_8023Z: + case MLO_AN_INBAND: phylink_mac_config(pl, config); phylink_mac_an_restart(pl); break; @@@ -1070,24 -1278,21 +1278,21 @@@ int phylink_ethtool_get_module_eeprom(s } EXPORT_SYMBOL_GPL(phylink_ethtool_get_module_eeprom);

- int phylink_init_eee(struct phylink *pl, bool clk_stop_enable) - { - int ret = -EPROTONOSUPPORT; - - WARN_ON(!lockdep_rtnl_is_held()); - - if (pl->phydev) - ret = phy_init_eee(pl->phydev, clk_stop_enable); - - return ret; - } - EXPORT_SYMBOL_GPL(phylink_init_eee); - + /** + * phylink_ethtool_get_eee_err() - read the energy efficient ethernet error + * counter + * @pl: a pointer to a &struct phylink returned from phylink_create(). + * + * Read the Energy Efficient Ethernet error counter from the PHY associated + * with the phylink instance specified by @pl. + * + * Returns positive error counter value, or negative error code. + */ int phylink_get_eee_err(struct phylink *pl) { int ret = 0;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

if (pl->phydev) ret = phy_get_eee_err(pl->phydev); @@@ -1096,11 -1301,16 +1301,16 @@@ } EXPORT_SYMBOL_GPL(phylink_get_eee_err);

+ /** + * phylink_ethtool_get_eee() - read the energy efficient ethernet parameters + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @eee: a pointer to a &struct ethtool_eee for the read parameters + */ int phylink_ethtool_get_eee(struct phylink *pl, struct ethtool_eee *eee) { int ret = -EOPNOTSUPP;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

if (pl->phydev) ret = phy_ethtool_get_eee(pl->phydev, eee); @@@ -1109,11 -1319,16 +1319,16 @@@ } EXPORT_SYMBOL_GPL(phylink_ethtool_get_eee);

+ /** + * phylink_ethtool_set_eee() - set the energy efficient ethernet parameters + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @eee: a pointer to a &struct ethtool_eee for the desired parameters + */ int phylink_ethtool_set_eee(struct phylink *pl, struct ethtool_eee *eee) { int ret = -EOPNOTSUPP;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

if (pl->phydev) ret = phy_ethtool_set_eee(pl->phydev, eee); @@@ -1248,9 -1463,7 +1463,7 @@@ static int phylink_mii_read(struct phyl case MLO_AN_PHY: return -EOPNOTSUPP;

- case MLO_AN_SGMII: - /* No phy, fall through to 8023z method */ - case MLO_AN_8023Z: + case MLO_AN_INBAND: if (phy_id == 0) { val = phylink_get_mac_state(pl, &state); if (val < 0) @@@ -1275,28 -1488,43 +1488,44 @@@ static int phylink_mii_write(struct phy case MLO_AN_PHY: return -EOPNOTSUPP;

- case MLO_AN_SGMII: - /* No phy, fall through to 8023z method */ - case MLO_AN_8023Z: + case MLO_AN_INBAND: break; }

return 0; }

+ /** + * phylink_mii_ioctl() - generic mii ioctl interface + * @pl: a pointer to a &struct phylink returned from phylink_create() + * @ifr: a pointer to a &struct ifreq for socket ioctls + * @cmd: ioctl cmd to execute + * + * Perform the specified MII ioctl on the PHY attached to the phylink instance + * specified by @pl. If no PHY is attached, emulate the presence of the PHY. + * + * Returns: zero on success or negative error code. + * + * %SIOCGMIIPHY: + * read register from the current PHY. + * %SIOCGMIIREG: + * read register from the specified PHY. + * %SIOCSMIIREG: + * set a register on the specified PHY. + */ int phylink_mii_ioctl(struct phylink *pl, struct ifreq *ifr, int cmd) { struct mii_ioctl_data *mii = if_mii(ifr); int ret;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

if (pl->phydev) { - /* PHYs only exist for MLO_AN_PHY and MLO_AN_SGMII */ + /* PHYs only exist for MLO_AN_PHY and SGMII */ switch (cmd) { case SIOCGMIIPHY: mii->phy_id = pl->phydev->mdio.addr; + /* fall through */

case SIOCGMIIREG: ret = phylink_phy_read(pl, mii->phy_id, mii->reg_num); @@@ -1319,7 -1547,6 +1548,7 @@@ switch (cmd) { case SIOCGMIIPHY: mii->phy_id = 0; + /* fall through */

case SIOCGMIIREG: ret = phylink_mii_read(pl, mii->phy_id, mii->reg_num); @@@ -1351,7 -1578,7 +1580,7 @@@ static int phylink_sfp_module_insert(vo __ETHTOOL_DECLARE_LINK_MODE_MASK(support) = { 0, }; struct phylink_link_state config; phy_interface_t iface; - int mode, ret = 0; + int ret = 0; bool changed; u8 port;

@@@ -1359,14 -1586,13 +1588,13 @@@ port = sfp_parse_port(pl->sfp_bus, id, support); iface = sfp_parse_interface(pl->sfp_bus, id);

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

switch (iface) { case PHY_INTERFACE_MODE_SGMII: - mode = MLO_AN_SGMII; - break; case PHY_INTERFACE_MODE_1000BASEX: - mode = MLO_AN_8023Z; + case PHY_INTERFACE_MODE_2500BASEX: + case PHY_INTERFACE_MODE_10GKR: break; default: return -EINVAL; @@@ -1384,16 -1610,18 +1612,18 @@@ ret = phylink_validate(pl, support, &config); if (ret) { netdev_err(pl->netdev, "validation of %s/%s with support %*pb failed: %d\n", - phylink_an_mode_str(mode), phy_modes(config.interface), + phylink_an_mode_str(MLO_AN_INBAND), + phy_modes(config.interface), __ETHTOOL_LINK_MODE_MASK_NBITS, support, ret); return ret; }

netdev_dbg(pl->netdev, "requesting link mode %s/%s with support %*pb\n", - phylink_an_mode_str(mode), phy_modes(config.interface), + phylink_an_mode_str(MLO_AN_INBAND), + phy_modes(config.interface), __ETHTOOL_LINK_MODE_MASK_NBITS, support);

- if (mode == MLO_AN_8023Z && pl->phydev) + if (phy_interface_mode_is_8023z(iface) && pl->phydev) return -EINVAL;

changed = !bitmap_equal(pl->supported, support, @@@ -1403,15 -1631,15 +1633,15 @@@ linkmode_copy(pl->link_config.advertising, config.advertising); }

- if (pl->link_an_mode != mode || + if (pl->link_an_mode != MLO_AN_INBAND || pl->link_config.interface != config.interface) { pl->link_config.interface = config.interface; - pl->link_an_mode = mode; + pl->link_an_mode = MLO_AN_INBAND;

changed = true;

netdev_info(pl->netdev, "switched to %s/%s link mode\n", - phylink_an_mode_str(mode), + phylink_an_mode_str(MLO_AN_INBAND), phy_modes(config.interface)); }

@@@ -1428,18 -1656,19 +1658,18 @@@ static void phylink_sfp_link_down(void { struct phylink *pl = upstream;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

set_bit(PHYLINK_DISABLE_LINK, &pl->phylink_disable_state); + queue_work(system_power_efficient_wq, &pl->resolve); flush_work(&pl->resolve); - - netif_carrier_off(pl->netdev); }

static void phylink_sfp_link_up(void *upstream) { struct phylink *pl = upstream;

- WARN_ON(!lockdep_rtnl_is_held()); + ASSERT_RTNL();

clear_bit(PHYLINK_DISABLE_LINK, &pl->phylink_disable_state); phylink_run_resolve(pl); diff --combined drivers/net/phy/sfp-bus.c index ab64a142b832,3ecc378e0716..bdc4bb3c8288 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@@ -8,10 -8,14 +8,14 @@@

#include "sfp.h"

+ /** + * struct sfp_bus - internal representation of a sfp bus + */ struct sfp_bus { + /* private: */ struct kref kref; struct list_head node; - struct device_node *device_node; + struct fwnode_handle *fwnode;

const struct sfp_socket_ops *socket_ops; struct device *sfp_dev; @@@ -26,6 -30,20 +30,20 @@@ bool started; };

+ /** + * sfp_parse_port() - Parse the EEPROM base ID, setting the port type + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * @id: a pointer to the module's &struct sfp_eeprom_id + * @support: optional pointer to an array of unsigned long for the + * ethtool support mask + * + * Parse the EEPROM identification given in @id, and return one of + * %PORT_TP, %PORT_FIBRE or %PORT_OTHER. If @support is non-%NULL, + * also set the ethtool %ETHTOOL_LINK_MODE_xxx_BIT corresponding with + * the connector type. + * + * If the port type is not known, returns %PORT_OTHER. + */ int sfp_parse_port(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support) { @@@ -39,21 -57,19 +57,19 @@@ case SFP_CONNECTOR_MT_RJ: case SFP_CONNECTOR_MU: case SFP_CONNECTOR_OPTICAL_PIGTAIL: - if (support) - phylink_set(support, FIBRE); port = PORT_FIBRE; break;

case SFP_CONNECTOR_RJ45: - if (support) - phylink_set(support, TP); port = PORT_TP; break;

+ case SFP_CONNECTOR_COPPER_PIGTAIL: + port = PORT_DA; + break; + case SFP_CONNECTOR_UNSPEC: if (id->base.e1000_base_t) { - if (support) - phylink_set(support, TP); port = PORT_TP; break; } @@@ -62,7 -78,6 +78,6 @@@ case SFP_CONNECTOR_MPO_1X12: case SFP_CONNECTOR_MPO_2X16: case SFP_CONNECTOR_HSSDC_II: - case SFP_CONNECTOR_COPPER_PIGTAIL: case SFP_CONNECTOR_NOSEPARATE: case SFP_CONNECTOR_MXC_2X16: port = PORT_OTHER; @@@ -74,10 -89,40 +89,40 @@@ break; }

+ if (support) { + switch (port) { + case PORT_FIBRE: + phylink_set(support, FIBRE); + break; + + case PORT_TP: + phylink_set(support, TP); + break; + } + } + return port; } EXPORT_SYMBOL_GPL(sfp_parse_port);

+ /** + * sfp_parse_interface() - Parse the phy_interface_t + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * @id: a pointer to the module's &struct sfp_eeprom_id + * + * Derive the phy_interface_t mode for the information found in the + * module's identifying EEPROM. There is no standard or defined way + * to derive this information, so we use some heuristics. + * + * If the encoding is 64b66b, then the module must be >= 10G, so + * return %PHY_INTERFACE_MODE_10GKR. + * + * If it's 8b10b, then it's 1G or slower. If it's definitely a fibre + * module, return %PHY_INTERFACE_MODE_1000BASEX mode, otherwise return + * %PHY_INTERFACE_MODE_SGMII mode. + * + * If the encoding is not known, return %PHY_INTERFACE_MODE_NA. + */ phy_interface_t sfp_parse_interface(struct sfp_bus *bus, const struct sfp_eeprom_id *id) { @@@ -107,6 -152,11 +152,11 @@@ break;

default: + if (id->base.e1000_base_cx) { + iface = PHY_INTERFACE_MODE_1000BASEX; + break; + } + iface = PHY_INTERFACE_MODE_NA; dev_err(bus->sfp_dev, "SFP module encoding does not support 8b10b nor 64b66b\n"); @@@ -117,13 -167,38 +167,38 @@@ } EXPORT_SYMBOL_GPL(sfp_parse_interface);

+ /** + * sfp_parse_support() - Parse the eeprom id for supported link modes + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * @id: a pointer to the module's &struct sfp_eeprom_id + * @support: pointer to an array of unsigned long for the ethtool support mask + * + * Parse the EEPROM identification information and derive the supported + * ethtool link modes for the module. + */ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, unsigned long *support) { + unsigned int br_min, br_nom, br_max; + phylink_set(support, Autoneg); phylink_set(support, Pause); phylink_set(support, Asym_Pause);

+ /* Decode the bitrate information to MBd */ + br_min = br_nom = br_max = 0; + if (id->base.br_nominal) { + if (id->base.br_nominal != 255) { + br_nom = id->base.br_nominal * 100; + br_min = br_nom + id->base.br_nominal * id->ext.br_min; + br_max = br_nom + id->base.br_nominal * id->ext.br_max; + } else if (id->ext.br_max) { + br_nom = 250 * id->ext.br_max; + br_max = br_nom + br_nom * id->ext.br_min / 100; + br_min = br_nom - br_nom * id->ext.br_min / 100; + } + } + /* Set ethtool support from the compliance fields. */ if (id->base.e10g_base_sr) phylink_set(support, 10000baseSR_Full); @@@ -142,6 -217,34 +217,34 @@@ phylink_set(support, 1000baseT_Full); }

+ /* 1000Base-PX or 1000Base-BX10 */ + if ((id->base.e_base_px || id->base.e_base_bx10) && + br_min <= 1300 && br_max >= 1200) + phylink_set(support, 1000baseX_Full); + + /* For active or passive cables, select the link modes + * based on the bit rates and the cable compliance bytes. + */ + if ((id->base.sfp_ct_passive || id->base.sfp_ct_active) && br_nom) { + /* This may look odd, but some manufacturers use 12000MBd */ + if (br_min <= 12000 && br_max >= 10300) + phylink_set(support, 10000baseCR_Full); + if (br_min <= 3200 && br_max >= 3100) + phylink_set(support, 2500baseX_Full); + if (br_min <= 1300 && br_max >= 1200) + phylink_set(support, 1000baseX_Full); + } + if (id->base.sfp_ct_passive) { + if (id->base.passive.sff8431_app_e) + phylink_set(support, 10000baseCR_Full); + } + if (id->base.sfp_ct_active) { + if (id->base.active.sff8431_app_e || + id->base.active.sff8431_lim) { + phylink_set(support, 10000baseCR_Full); + } + } + switch (id->base.extended_cc) { case 0x00: /* Unspecified */ break; @@@ -175,35 -278,6 +278,6 @@@ if (id->base.br_nominal >= 12) phylink_set(support, 1000baseX_Full); } - - switch (id->base.connector) { - case SFP_CONNECTOR_SC: - case SFP_CONNECTOR_FIBERJACK: - case SFP_CONNECTOR_LC: - case SFP_CONNECTOR_MT_RJ: - case SFP_CONNECTOR_MU: - case SFP_CONNECTOR_OPTICAL_PIGTAIL: - break; - - case SFP_CONNECTOR_UNSPEC: - if (id->base.e1000_base_t) - break; - - case SFP_CONNECTOR_SG: /* guess */ - case SFP_CONNECTOR_MPO_1X12: - case SFP_CONNECTOR_MPO_2X16: - case SFP_CONNECTOR_HSSDC_II: - case SFP_CONNECTOR_COPPER_PIGTAIL: - case SFP_CONNECTOR_NOSEPARATE: - case SFP_CONNECTOR_MXC_2X16: - default: - /* a guess at the supported link modes */ - dev_warn(bus->sfp_dev, - "Guessing link modes, please report...\n"); - phylink_set(support, 1000baseT_Half); - phylink_set(support, 1000baseT_Full); - break; - } } EXPORT_SYMBOL_GPL(sfp_parse_support);

@@@ -215,7 -289,7 +289,7 @@@ static const struct sfp_upstream_ops *s return bus->registered ? bus->upstream_ops : NULL; }

- static struct sfp_bus *sfp_bus_get(struct device_node *np) + static struct sfp_bus *sfp_bus_get(struct fwnode_handle *fwnode) { struct sfp_bus *sfp, *new, *found = NULL;

@@@ -224,7 -298,7 +298,7 @@@ mutex_lock(&sfp_mutex);

list_for_each_entry(sfp, &sfp_buses, node) { - if (sfp->device_node == np) { + if (sfp->fwnode == fwnode) { kref_get(&sfp->kref); found = sfp; break; @@@ -233,7 -307,7 +307,7 @@@

if (!found && new) { kref_init(&new->kref); - new->device_node = np; + new->fwnode = fwnode; list_add(&new->node, &sfp_buses); found = new; new = NULL; @@@ -246,7 -320,7 +320,7 @@@ return found; }

- static void sfp_bus_release(struct kref *kref) __releases(sfp_mutex) + static void sfp_bus_release(struct kref *kref) { struct sfp_bus *bus = container_of(kref, struct sfp_bus, kref);

@@@ -293,6 -367,16 +367,16 @@@ static void sfp_unregister_bus(struct s bus->registered = false; }

+ /** + * sfp_get_module_info() - Get the ethtool_modinfo for a SFP module + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * @modinfo: a &struct ethtool_modinfo + * + * Fill in the type and eeprom_len parameters in @modinfo for a module on + * the sfp bus specified by @bus. + * + * Returns 0 on success or a negative errno number. + */ int sfp_get_module_info(struct sfp_bus *bus, struct ethtool_modinfo *modinfo) { if (!bus->registered) @@@ -301,6 -385,17 +385,17 @@@ } EXPORT_SYMBOL_GPL(sfp_get_module_info);

+ /** + * sfp_get_module_eeprom() - Read the SFP module EEPROM + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * @ee: a &struct ethtool_eeprom + * @data: buffer to contain the EEPROM data (must be at least @ee->len bytes) + * + * Read the EEPROM as specified by the supplied @ee. See the documentation + * for &struct ethtool_eeprom for the region to be read. + * + * Returns 0 on success or a negative errno number. + */ int sfp_get_module_eeprom(struct sfp_bus *bus, struct ethtool_eeprom *ee, u8 *data) { @@@ -310,6 -405,15 +405,15 @@@ } EXPORT_SYMBOL_GPL(sfp_get_module_eeprom);

+ /** + * sfp_upstream_start() - Inform the SFP that the network device is up + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * + * Inform the SFP socket that the network device is now up, so that the + * module can be enabled by allowing TX_DISABLE to be deasserted. This + * should be called from the network device driver's &struct net_device_ops + * ndo_open() method. + */ void sfp_upstream_start(struct sfp_bus *bus) { if (bus->registered) @@@ -318,6 -422,15 +422,15 @@@ } EXPORT_SYMBOL_GPL(sfp_upstream_start);

+ /** + * sfp_upstream_stop() - Inform the SFP that the network device is down + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * + * Inform the SFP socket that the network device is now up, so that the + * module can be disabled by asserting TX_DISABLE, disabling the laser + * in optical modules. This should be called from the network device + * driver's &struct net_device_ops ndo_stop() method. + */ void sfp_upstream_stop(struct sfp_bus *bus) { if (bus->registered) @@@ -326,11 -439,24 +439,24 @@@ } EXPORT_SYMBOL_GPL(sfp_upstream_stop);

- struct sfp_bus *sfp_register_upstream(struct device_node *np, + /** + * sfp_register_upstream() - Register the neighbouring device + * @np: device node for the SFP bus + * @ndev: network device associated with the interface + * @upstream: the upstream private data + * @ops: the upstream's &struct sfp_upstream_ops + * + * Register the upstream device (eg, PHY) with the SFP bus. MAC drivers + * should use phylink, which will call this function for them. Returns + * a pointer to the allocated &struct sfp_bus. + * + * On error, returns %NULL. + */ + struct sfp_bus *sfp_register_upstream(struct fwnode_handle *fwnode, struct net_device *ndev, void *upstream, const struct sfp_upstream_ops *ops) { - struct sfp_bus *bus = sfp_bus_get(np); + struct sfp_bus *bus = sfp_bus_get(fwnode); int ret = 0;

if (bus) { @@@ -353,11 -479,17 +479,18 @@@ } EXPORT_SYMBOL_GPL(sfp_register_upstream);

+ /** + * sfp_unregister_upstream() - Unregister sfp bus + * @bus: a pointer to the &struct sfp_bus structure for the sfp module + * + * Unregister a previously registered upstream connection for the SFP + * module. @bus is returned from sfp_register_upstream(). + */ void sfp_unregister_upstream(struct sfp_bus *bus) { rtnl_lock(); - sfp_unregister_bus(bus); + if (bus->sfp) + sfp_unregister_bus(bus); bus->upstream = NULL; bus->netdev = NULL; rtnl_unlock(); @@@ -434,7 -566,7 +567,7 @@@ EXPORT_SYMBOL_GPL(sfp_module_remove) struct sfp_bus *sfp_register_socket(struct device *dev, struct sfp *sfp, const struct sfp_socket_ops *ops) { - struct sfp_bus *bus = sfp_bus_get(dev->of_node); + struct sfp_bus *bus = sfp_bus_get(dev->fwnode); int ret = 0;

if (bus) { @@@ -460,8 -592,7 +593,8 @@@ EXPORT_SYMBOL_GPL(sfp_register_socket) void sfp_unregister_socket(struct sfp_bus *bus) { rtnl_lock(); - sfp_unregister_bus(bus); + if (bus->netdev) + sfp_unregister_bus(bus); bus->sfp_dev = NULL; bus->sfp = NULL; bus->socket_ops = NULL; diff --combined drivers/net/tun.c index 2ffe5dba7e09,e7c5f4b2a9a6..cb56dfe84f26 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@@ -180,6 -180,7 +180,7 @@@ struct tun_file struct list_head next; struct tun_struct *detached; struct skb_array tx_array; + struct xdp_rxq_info xdp_rxq; };

struct tun_flow_entry { @@@ -195,6 -196,11 +196,11 @@@

#define TUN_NUM_FLOW_ENTRIES 1024

+ struct tun_steering_prog { + struct rcu_head rcu; + struct bpf_prog *prog; + }; + /* Since the socket were moved to tun_file, to preserve the behavior of persist * device, socket filter, sndbuf and vnet header size were restore when the * file were attached to a persist device. @@@ -232,6 -238,7 +238,7 @@@ struct tun_struct u32 rx_batched; struct tun_pcpu_stats __percpu *pcpu_stats; struct bpf_prog __rcu *xdp_prog; + struct tun_steering_prog __rcu *steering_prog; };

static int tun_napi_receive(struct napi_struct *napi, int budget) @@@ -537,15 -544,12 +544,12 @@@ static inline void tun_flow_save_rps_rx * different rxq no. here. If we could not get rxhash, then we would * hope the rxq no. may help here. */ - static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, - void *accel_priv, select_queue_fallback_t fallback) + static u16 tun_automq_select_queue(struct tun_struct *tun, struct sk_buff *skb) { - struct tun_struct *tun = netdev_priv(dev); struct tun_flow_entry *e; u32 txq = 0; u32 numqueues = 0;

- rcu_read_lock(); numqueues = READ_ONCE(tun->numqueues);

txq = __skb_get_hash_symmetric(skb); @@@ -563,10 -567,37 +567,37 @@@ txq -= numqueues; }

- rcu_read_unlock(); return txq; }

+ static u16 tun_ebpf_select_queue(struct tun_struct *tun, struct sk_buff *skb) + { + struct tun_steering_prog *prog; + u16 ret = 0; + + prog = rcu_dereference(tun->steering_prog); + if (prog) + ret = bpf_prog_run_clear_cb(prog->prog, skb); + + return ret % tun->numqueues; + } + + static u16 tun_select_queue(struct net_device *dev, struct sk_buff *skb, + void *accel_priv, select_queue_fallback_t fallback) + { + struct tun_struct *tun = netdev_priv(dev); + u16 ret; + + rcu_read_lock(); + if (rcu_dereference(tun->steering_prog)) + ret = tun_ebpf_select_queue(tun, skb); + else + ret = tun_automq_select_queue(tun, skb); + rcu_read_unlock(); + + return ret; + } + static inline bool tun_not_capable(struct tun_struct *tun) { const struct cred *cred = current_cred(); @@@ -657,8 -688,10 +688,10 @@@ static void __tun_detach(struct tun_fil tun->dev->reg_state == NETREG_REGISTERED) unregister_netdevice(tun->dev); } - if (tun) + if (tun) { skb_array_cleanup(&tfile->tx_array); + xdp_rxq_info_unreg(&tfile->xdp_rxq); + } sock_put(&tfile->sk); } } @@@ -673,7 -706,6 +706,6 @@@ static void tun_detach(struct tun_file static void tun_detach_all(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); - struct bpf_prog *xdp_prog = rtnl_dereference(tun->xdp_prog); struct tun_file *tfile, *tmp; int i, n = tun->numqueues;

@@@ -699,18 -731,17 +731,17 @@@ tun_napi_del(tun, tfile); /* Drop read queue */ tun_queue_purge(tfile); + xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } list_for_each_entry_safe(tfile, tmp, &tun->disabled, next) { tun_enable_queue(tfile); tun_queue_purge(tfile); + xdp_rxq_info_unreg(&tfile->xdp_rxq); sock_put(&tfile->sk); } BUG_ON(tun->numdisabled != 0);

- if (xdp_prog) - bpf_prog_put(xdp_prog); - if (tun->flags & IFF_PERSIST) module_put(THIS_MODULE); } @@@ -758,6 -789,22 +789,22 @@@ static int tun_attach(struct tun_struc

tfile->queue_index = tun->numqueues; tfile->socket.sk->sk_shutdown &= ~RCV_SHUTDOWN; + + if (tfile->detached) { + /* Re-attach detached tfile, updating XDP queue_index */ + WARN_ON(!xdp_rxq_info_is_reg(&tfile->xdp_rxq)); + + if (tfile->xdp_rxq.queue_index != tfile->queue_index) + tfile->xdp_rxq.queue_index = tfile->queue_index; + } else { + /* Setup XDP RX-queue info, for new tfile getting attached */ + err = xdp_rxq_info_reg(&tfile->xdp_rxq, + tun->dev, tfile->queue_index); + if (err < 0) + goto out; + err = 0; + } + rcu_assign_pointer(tfile->tun, tun); rcu_assign_pointer(tun->tfiles[tun->numqueues], tfile); tun->numqueues++; @@@ -937,23 -984,10 +984,10 @@@ static int tun_net_close(struct net_dev }

/* Net device start xmit */ - static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) + static void tun_automq_xmit(struct tun_struct *tun, struct sk_buff *skb) { - struct tun_struct *tun = netdev_priv(dev); - int txq = skb->queue_mapping; - struct tun_file *tfile; - u32 numqueues = 0; - - rcu_read_lock(); - tfile = rcu_dereference(tun->tfiles[txq]); - numqueues = READ_ONCE(tun->numqueues); - - /* Drop packet if interface is not attached */ - if (txq >= numqueues) - goto drop; - #ifdef CONFIG_RPS - if (numqueues == 1 && static_key_false(&rps_needed)) { + if (tun->numqueues == 1 && static_key_false(&rps_needed)) { /* Select queue was not called for the skbuff, so we extract the * RPS hash and save it into the flow_table here. */ @@@ -969,6 -1003,24 +1003,24 @@@ } } #endif + } + + /* Net device start xmit */ + static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev) + { + struct tun_struct *tun = netdev_priv(dev); + int txq = skb->queue_mapping; + struct tun_file *tfile; + + rcu_read_lock(); + tfile = rcu_dereference(tun->tfiles[txq]); + + /* Drop packet if interface is not attached */ + if (txq >= tun->numqueues) + goto drop; + + if (!rcu_dereference(tun->steering_prog)) + tun_automq_xmit(tun, skb);

tun_debug(KERN_INFO, tun, "tun_net_xmit %d\n", skb->len);

@@@ -1248,12 -1300,12 +1300,12 @@@ static void tun_net_init(struct net_dev /* Character device part */

/* Poll */ -static unsigned int tun_chr_poll(struct file *file, poll_table *wait) +static __poll_t tun_chr_poll(struct file *file, poll_table *wait) { struct tun_file *tfile = file->private_data; struct tun_struct *tun = tun_get(tfile); struct sock *sk; - unsigned int mask = 0; + __poll_t mask = 0;

if (!tun) return POLLERR; @@@ -1477,6 -1529,7 +1529,7 @@@ static struct sk_buff *tun_build_skb(st xdp.data = buf + pad; xdp_set_data_meta_invalid(&xdp); xdp.data_end = xdp.data + len; + xdp.rxq = &tfile->xdp_rxq; orig_data = xdp.data; act = bpf_prog_run_xdp(xdp_prog, &xdp);

@@@ -1551,7 -1604,7 +1604,7 @@@ static ssize_t tun_get_user(struct tun_ int copylen; bool zerocopy = false; int err; - u32 rxhash; + u32 rxhash = 0; int skb_xdp = 1; bool frags = tun_napi_frags_enabled(tun);

@@@ -1739,7 -1792,10 +1792,10 @@@ rcu_read_unlock(); }

- rxhash = __skb_get_hash_symmetric(skb); + rcu_read_lock(); + if (!rcu_dereference(tun->steering_prog)) + rxhash = __skb_get_hash_symmetric(skb); + rcu_read_unlock();

if (frags) { /* Exercise flow dissector code path. */ @@@ -1783,7 -1839,9 +1839,9 @@@ u64_stats_update_end(&stats->syncp); put_cpu_ptr(stats);

- tun_flow_update(tun, rxhash, tfile); + if (rxhash) + tun_flow_update(tun, rxhash, tfile); + return total_len; }

@@@ -1991,6 -2049,39 +2049,39 @@@ static ssize_t tun_chr_read_iter(struc return ret; }

+ static void tun_steering_prog_free(struct rcu_head *rcu) + { + struct tun_steering_prog *prog = container_of(rcu, + struct tun_steering_prog, rcu); + + bpf_prog_destroy(prog->prog); + kfree(prog); + } + + static int __tun_set_steering_ebpf(struct tun_struct *tun, + struct bpf_prog *prog) + { + struct tun_steering_prog *old, *new = NULL; + + if (prog) { + new = kmalloc(sizeof(*new), GFP_KERNEL); + if (!new) + return -ENOMEM; + new->prog = prog; + } + + spin_lock_bh(&tun->lock); + old = rcu_dereference_protected(tun->steering_prog, + lockdep_is_held(&tun->lock)); + rcu_assign_pointer(tun->steering_prog, new); + spin_unlock_bh(&tun->lock); + + if (old) + call_rcu(&old->rcu, tun_steering_prog_free); + + return 0; + } + static void tun_free_netdev(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); @@@ -1999,6 -2090,7 +2090,7 @@@ free_percpu(tun->pcpu_stats); tun_flow_uninit(tun); security_tun_dev_free_security(tun->security); + __tun_set_steering_ebpf(tun, NULL); }

static void tun_setup(struct net_device *dev) @@@ -2287,6 -2379,7 +2379,7 @@@ static int tun_set_iff(struct net *net tun->filter_attached = false; tun->sndbuf = tfile->socket.sk->sk_sndbuf; tun->rx_batched = 0; + RCU_INIT_POINTER(tun->steering_prog, NULL);

tun->pcpu_stats = netdev_alloc_pcpu_stats(struct tun_pcpu_stats); if (!tun->pcpu_stats) { @@@ -2479,6 -2572,25 +2572,25 @@@ unlock return ret; }

+ static int tun_set_steering_ebpf(struct tun_struct *tun, void __user *data) + { + struct bpf_prog *prog; + int fd; + + if (copy_from_user(&fd, data, sizeof(fd))) + return -EFAULT; + + if (fd == -1) { + prog = NULL; + } else { + prog = bpf_prog_get_type(fd, BPF_PROG_TYPE_SOCKET_FILTER); + if (IS_ERR(prog)) + return PTR_ERR(prog); + } + + return __tun_set_steering_ebpf(tun, prog); + } + static long __tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg, int ifreq_len) { @@@ -2755,6 -2867,10 +2867,10 @@@ ret = 0; break;

+ case TUNSETSTEERINGEBPF: + ret = tun_set_steering_ebpf(tun, argp); + break; + default: ret = -EINVAL; break; diff --combined drivers/net/usb/qmi_wwan.c index 728819feab44,cfaa07f230e5..ae0580b577b8 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@@ -826,7 -826,7 +826,7 @@@ err

static const struct driver_info qmi_wwan_info = { .description = "WWAN/QMI device", - .flags = FLAG_WWAN, + .flags = FLAG_WWAN | FLAG_SEND_ZLP, .bind = qmi_wwan_bind, .unbind = qmi_wwan_unbind, .manage_power = qmi_wwan_manage_power, @@@ -835,7 -835,7 +835,7 @@@

static const struct driver_info qmi_wwan_info_quirk_dtr = { .description = "WWAN/QMI device", - .flags = FLAG_WWAN, + .flags = FLAG_WWAN | FLAG_SEND_ZLP, .bind = qmi_wwan_bind, .unbind = qmi_wwan_unbind, .manage_power = qmi_wwan_manage_power, @@@ -1100,7 -1100,6 +1100,7 @@@ static const struct usb_device_id produ {QMI_FIXED_INTF(0x05c6, 0x9084, 4)}, {QMI_FIXED_INTF(0x05c6, 0x920d, 0)}, {QMI_FIXED_INTF(0x05c6, 0x920d, 5)}, + {QMI_QUIRK_SET_DTR(0x05c6, 0x9625, 4)}, /* YUGA CLM920-NC5 */ {QMI_FIXED_INTF(0x0846, 0x68a2, 8)}, {QMI_FIXED_INTF(0x12d1, 0x140c, 1)}, /* Huawei E173 */ {QMI_FIXED_INTF(0x12d1, 0x14ac, 1)}, /* Huawei E1820 */ diff --combined drivers/net/wireless/ath/wcn36xx/main.c index 987f1252a3cf,5bed323f1100..ab5be6d2c691 --- a/drivers/net/wireless/ath/wcn36xx/main.c +++ b/drivers/net/wireless/ath/wcn36xx/main.c @@@ -384,18 -384,6 +384,18 @@@ static int wcn36xx_config(struct ieee80 } }

+ if (changed & IEEE80211_CONF_CHANGE_PS) { + list_for_each_entry(tmp, &wcn->vif_list, list) { + vif = wcn36xx_priv_to_vif(tmp); + if (hw->conf.flags & IEEE80211_CONF_PS) { + if (vif->bss_conf.ps) /* ps allowed ? */ + wcn36xx_pmc_enter_bmps_state(wcn, vif); + } else { + wcn36xx_pmc_exit_bmps_state(wcn, vif); + } + } + } + mutex_unlock(&wcn->conf_mutex);

return 0; @@@ -641,7 -629,6 +641,6 @@@ static int wcn36xx_hw_scan(struct ieee8 struct ieee80211_scan_request *hw_req) { struct wcn36xx *wcn = hw->priv; - mutex_lock(&wcn->scan_lock); if (wcn->scan_req) { mutex_unlock(&wcn->scan_lock); @@@ -650,11 -637,16 +649,16 @@@

wcn->scan_aborted = false; wcn->scan_req = &hw_req->req; + mutex_unlock(&wcn->scan_lock);

- schedule_work(&wcn->scan_work); + if (!get_feat_caps(wcn->fw_feat_caps, SCAN_OFFLOAD)) { + /* legacy manual/sw scan */ + schedule_work(&wcn->scan_work); + return 0; + }

- return 0; + return wcn36xx_smd_start_hw_scan(wcn, vif, &hw_req->req); }

static void wcn36xx_cancel_hw_scan(struct ieee80211_hw *hw, @@@ -662,6 -654,12 +666,12 @@@ { struct wcn36xx *wcn = hw->priv;

+ if (!wcn36xx_smd_stop_hw_scan(wcn)) { + struct cfg80211_scan_info scan_info = { .aborted = true }; + + ieee80211_scan_completed(wcn->hw, &scan_info); + } + mutex_lock(&wcn->scan_lock); wcn->scan_aborted = true; mutex_unlock(&wcn->scan_lock); @@@ -759,6 -757,17 +769,6 @@@ static void wcn36xx_bss_info_changed(st vif_priv->dtim_period = bss_conf->dtim_period; }

- if (changed & BSS_CHANGED_PS) { - wcn36xx_dbg(WCN36XX_DBG_MAC, - "mac bss PS set %d\n", - bss_conf->ps); - if (bss_conf->ps) { - wcn36xx_pmc_enter_bmps_state(wcn, vif); - } else { - wcn36xx_pmc_exit_bmps_state(wcn, vif); - } - } - if (changed & BSS_CHANGED_BSSID) { wcn36xx_dbg(WCN36XX_DBG_MAC, "mac bss changed_bssid %pM\n", bss_conf->bssid); diff --combined fs/btrfs/disk-io.c index e5a4faf9e304,5da18ebc9222..bf31663de6b7 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@@ -30,6 -30,7 +30,7 @@@ #include <linux/ratelimit.h> #include <linux/uuid.h> #include <linux/semaphore.h> + #include <linux/bpf.h> #include <asm/unaligned.h> #include "ctree.h" #include "disk-io.h" @@@ -220,7 -221,7 +221,7 @@@ void btrfs_set_buffer_lockdep_class(u6 * extents on the btree inode are pretty simple, there's one extent * that covers the entire device */ -static struct extent_map *btree_get_extent(struct btrfs_inode *inode, +struct extent_map *btree_get_extent(struct btrfs_inode *inode, struct page *page, size_t pg_offset, u64 start, u64 len, int create) { @@@ -285,7 -286,7 +286,7 @@@ static int csum_tree_block(struct btrfs int verify) { u16 csum_size = btrfs_super_csum_size(fs_info->super_copy); - char *result = NULL; + char result[BTRFS_CSUM_SIZE]; unsigned long len; unsigned long cur_len; unsigned long offset = BTRFS_CSUM_SIZE; @@@ -294,6 -295,7 +295,6 @@@ unsigned long map_len; int err; u32 crc = ~(u32)0; - unsigned long inline_result;

len = buf->len - offset; while (len > 0) { @@@ -307,7 -309,13 +308,7 @@@ len -= cur_len; offset += cur_len; } - if (csum_size > sizeof(inline_result)) { - result = kzalloc(csum_size, GFP_NOFS); - if (!result) - return -ENOMEM; - } else { - result = (char *)&inline_result; - } + memset(result, 0, BTRFS_CSUM_SIZE);

btrfs_csum_final(crc, result);

@@@ -322,12 -330,15 +323,12 @@@ "%s checksum verify failed on %llu wanted %X found %X level %d", fs_info->sb->s_id, buf->start, val, found, btrfs_header_level(buf)); - if (result != (char *)&inline_result) - kfree(result); return -EUCLEAN; } } else { write_extent_buffer(buf, result, 0, csum_size); } - if (result != (char *)&inline_result) - kfree(result); + return 0; }

@@@ -381,7 -392,7 +382,7 @@@ static int verify_parent_transid(struc clear_extent_buffer_uptodate(eb); out: unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1, - &cached_state, GFP_NOFS); + &cached_state); if (need_lock) btrfs_tree_read_unlock_blocking(eb); return ret; @@@ -445,7 -456,7 +446,7 @@@ static int btree_read_extent_buffer_pag io_tree = &BTRFS_I(fs_info->btree_inode)->io_tree; while (1) { ret = read_extent_buffer_pages(io_tree, eb, WAIT_COMPLETE, - btree_get_extent, mirror_num); + mirror_num); if (!ret) { if (!verify_parent_transid(io_tree, eb, parent_transid, 0)) @@@ -855,8 -866,6 +856,8 @@@ static blk_status_t btree_submit_bio_ho int async = check_async_write(BTRFS_I(inode)); blk_status_t ret;

+ bio_associate_blkcg(bio, blkcg_root_css); + if (bio_op(bio) != REQ_OP_WRITE) { /* * called for a read, do the setup so that checksum validation @@@ -1004,7 -1013,7 +1005,7 @@@ void readahead_tree_block(struct btrfs_ if (IS_ERR(buf)) return; read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree, - buf, WAIT_NONE, btree_get_extent, 0); + buf, WAIT_NONE, 0); free_extent_buffer(buf); }

@@@ -1023,7 -1032,7 +1024,7 @@@ int reada_tree_block_flagged(struct btr set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);

ret = read_extent_buffer_pages(io_tree, buf, WAIT_PAGE_LOCK, - btree_get_extent, mirror_num); + mirror_num); if (ret) { free_extent_buffer(buf); return ret; @@@ -1160,7 -1169,6 +1161,7 @@@ static void __setup_root(struct btrfs_r spin_lock_init(&root->accounting_lock); spin_lock_init(&root->log_extents_lock[0]); spin_lock_init(&root->log_extents_lock[1]); + spin_lock_init(&root->qgroup_meta_rsv_lock); mutex_init(&root->objectid_mutex); mutex_init(&root->log_mutex); mutex_init(&root->ordered_extent_mutex); @@@ -1177,6 -1185,7 +1178,6 @@@ atomic_set(&root->orphan_inodes, 0); refcount_set(&root->refs, 1); atomic_set(&root->will_be_snapshotted, 0); - atomic64_set(&root->qgroup_meta_rsv, 0); root->log_transid = 0; root->log_transid_committed = -1; root->last_log_commit = 0; @@@ -1235,7 -1244,7 +1236,7 @@@ struct btrfs_root *btrfs_create_tree(st struct btrfs_root *root; struct btrfs_key key; int ret = 0; - uuid_le uuid; + uuid_le uuid = NULL_UUID_LE;

root = btrfs_alloc_root(fs_info, GFP_KERNEL); if (!root) @@@ -1276,8 -1285,7 +1277,8 @@@ btrfs_set_root_used(&root->root_item, leaf->len); btrfs_set_root_last_snapshot(&root->root_item, 0); btrfs_set_root_dirid(&root->root_item, 0); - uuid_le_gen(&uuid); + if (is_fstree(objectid)) + uuid_le_gen(&uuid); memcpy(root->root_item.uuid, uuid.b, BTRFS_UUID_SIZE); root->root_item.drop_level = 0;

@@@ -2868,7 -2876,7 +2869,7 @@@ retry_root_backup goto fail_sysfs; }

- if (!sb_rdonly(sb) && !btrfs_check_rw_degradable(fs_info)) { + if (!sb_rdonly(sb) && !btrfs_check_rw_degradable(fs_info, NULL)) { btrfs_warn(fs_info, "writeable mount is not allowed due to too many missing devices"); goto fail_sysfs; @@@ -3116,6 -3124,7 +3117,7 @@@ recovery_tree_root goto fail_block_groups; goto retry_root_backup; } + BPF_ALLOW_ERROR_INJECTION(open_ctree);

static void btrfs_end_buffer_write_sync(struct buffer_head *bh, int uptodate) { @@@ -3343,8 -3352,6 +3345,8 @@@ static void write_dev_flush(struct btrf return;

bio_reset(bio); + bio_associate_blkcg(bio, blkcg_root_css); + bio->bi_end_io = btrfs_end_empty_barrier; bio_set_dev(bio, device->bdev); bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH; @@@ -3352,7 -3359,7 +3354,7 @@@ bio->bi_private = &device->flush_wait;

btrfsic_submit_bio(bio); - device->flush_bio_sent = 1; + set_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state); }

/* @@@ -3362,10 -3369,10 +3364,10 @@@ static blk_status_t wait_dev_flush(stru { struct bio *bio = device->flush_bio;

- if (!device->flush_bio_sent) + if (!test_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state)) return BLK_STS_OK;

- device->flush_bio_sent = 0; + clear_bit(BTRFS_DEV_STATE_FLUSH_SENT, &device->dev_state); wait_for_completion_io(&device->flush_wait);

return bio->bi_status; @@@ -3373,7 -3380,7 +3375,7 @@@

static int check_barrier_error(struct btrfs_fs_info *fs_info) { - if (!btrfs_check_rw_degradable(fs_info)) + if (!btrfs_check_rw_degradable(fs_info, NULL)) return -EIO; return 0; } @@@ -3389,16 -3396,14 +3391,16 @@@ static int barrier_all_devices(struct b int errors_wait = 0; blk_status_t ret;

+ lockdep_assert_held(&info->fs_devices->device_list_mutex); /* send down all the barriers */ head = &info->fs_devices->devices; - list_for_each_entry_rcu(dev, head, dev_list) { - if (dev->missing) + list_for_each_entry(dev, head, dev_list) { + if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) continue; if (!dev->bdev) continue; - if (!dev->in_fs_metadata || !dev->writeable) + if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || + !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue;

write_dev_flush(dev); @@@ -3406,15 -3411,14 +3408,15 @@@ }

/* wait for all the barriers */ - list_for_each_entry_rcu(dev, head, dev_list) { - if (dev->missing) + list_for_each_entry(dev, head, dev_list) { + if (test_bit(BTRFS_DEV_STATE_MISSING, &dev->dev_state)) continue; if (!dev->bdev) { errors_wait++; continue; } - if (!dev->in_fs_metadata || !dev->writeable) + if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || + !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue;

ret = wait_dev_flush(dev); @@@ -3506,13 -3510,12 +3508,13 @@@ int write_all_supers(struct btrfs_fs_in } }

- list_for_each_entry_rcu(dev, head, dev_list) { + list_for_each_entry(dev, head, dev_list) { if (!dev->bdev) { total_errors++; continue; } - if (!dev->in_fs_metadata || !dev->writeable) + if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || + !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue;

btrfs_set_stack_device_generation(dev_item, 0); @@@ -3548,11 -3551,10 +3550,11 @@@ }

total_errors = 0; - list_for_each_entry_rcu(dev, head, dev_list) { + list_for_each_entry(dev, head, dev_list) { if (!dev->bdev) continue; - if (!dev->in_fs_metadata || !dev->writeable) + if (!test_bit(BTRFS_DEV_STATE_IN_FS_METADATA, &dev->dev_state) || + !test_bit(BTRFS_DEV_STATE_WRITEABLE, &dev->dev_state)) continue;

ret = wait_dev_supers(dev, max_mirrors); diff --combined fs/btrfs/free-space-cache.c index 9e8c1f046e02,fb1382893bfc..9088b0b0d10f --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@@ -22,6 -22,7 +22,7 @@@ #include <linux/slab.h> #include <linux/math64.h> #include <linux/ratelimit.h> + #include <linux/bpf.h> #include "ctree.h" #include "free-space-cache.h" #include "transaction.h" @@@ -332,6 -333,7 +333,7 @@@ static int io_ctl_init(struct btrfs_io_

return 0; } + BPF_ALLOW_ERROR_INJECTION(io_ctl_init);

static void io_ctl_free(struct btrfs_io_ctl *io_ctl) { @@@ -993,7 -995,8 +995,7 @@@ update_cache_item(struct btrfs_trans_ha ret = btrfs_search_slot(trans, root, &key, path, 0, 1); if (ret < 0) { clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1, - EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL, - GFP_NOFS); + EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL); goto fail; } leaf = path->nodes[0]; @@@ -1007,7 -1010,7 +1009,7 @@@ clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1, EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, - NULL, GFP_NOFS); + NULL); btrfs_release_path(path); goto fail; } @@@ -1104,7 -1107,8 +1106,7 @@@ static int flush_dirty_cache(struct ino ret = btrfs_wait_ordered_range(inode, 0, (u64)-1); if (ret) clear_extent_bit(&BTRFS_I(inode)->io_tree, 0, inode->i_size - 1, - EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL, - GFP_NOFS); + EXTENT_DIRTY | EXTENT_DELALLOC, 0, 0, NULL);

return ret; } @@@ -1125,7 -1129,8 +1127,7 @@@ cleanup_write_cache_enospc(struct inod { io_ctl_drop_pages(io_ctl); unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, - i_size_read(inode) - 1, cached_state, - GFP_NOFS); + i_size_read(inode) - 1, cached_state); }

static int __btrfs_wait_cache_io(struct btrfs_root *root, @@@ -1319,7 -1324,7 +1321,7 @@@ static int __btrfs_write_out_cache(stru io_ctl_drop_pages(io_ctl);

unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0, - i_size_read(inode) - 1, &cached_state, GFP_NOFS); + i_size_read(inode) - 1, &cached_state);

/* * at this point the pages are under IO and we're happy, @@@ -3545,7 -3550,7 +3547,7 @@@ int btrfs_write_out_ino_cache(struct bt if (ret) { if (release_metadata) btrfs_delalloc_release_metadata(BTRFS_I(inode), - inode->i_size); + inode->i_size, true); #ifdef DEBUG btrfs_err(fs_info, "failed to write free ino cache for root %llu", diff --combined include/linux/bpf.h index b63a592ad29d,9e03046d1df2..6be837c063c3 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@@ -17,6 -17,7 +17,7 @@@ #include <linux/numa.h> #include <linux/wait.h>

+ struct bpf_verifier_env; struct perf_event; struct bpf_prog; struct bpf_map; @@@ -184,14 -185,18 +185,18 @@@ struct bpf_verifier_ops struct bpf_prog *prog, u32 *target_size); };

+ struct bpf_prog_offload_ops { + int (*insn_hook)(struct bpf_verifier_env *env, + int insn_idx, int prev_insn_idx); + }; + struct bpf_dev_offload { struct bpf_prog *prog; struct net_device *netdev; void *dev_priv; struct list_head offloads; bool dev_state; - bool verifier_running; - wait_queue_head_t verifier_done; + const struct bpf_prog_offload_ops *dev_ops; };

struct bpf_prog_aux { @@@ -200,6 -205,10 +205,10 @@@ u32 max_ctx_offset; u32 stack_depth; u32 id; + u32 func_cnt; + bool offload_requested; + struct bpf_prog **func; + void *jit_data; /* JIT specific data. arch dependent */ struct latch_tree_node ksym_tnode; struct list_head ksym_lnode; const struct bpf_prog_ops *ops; @@@ -285,6 -294,9 +294,9 @@@ int bpf_prog_array_copy_to_user(struct

void bpf_prog_array_delete_safe(struct bpf_prog_array __rcu *progs, struct bpf_prog *old_prog); + int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array, + __u32 __user *prog_ids, u32 request_cnt, + __u32 __user *prog_cnt); int bpf_prog_array_copy(struct bpf_prog_array __rcu *old_array, struct bpf_prog *exclude_prog, struct bpf_prog *include_prog, @@@ -345,6 -357,8 +357,8 @@@ void bpf_prog_put(struct bpf_prog *prog int __bpf_prog_charge(struct user_struct *user, u32 pages); void __bpf_prog_uncharge(struct user_struct *user, u32 pages);

+ void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock); + struct bpf_map *bpf_map_get_with_uref(u32 ufd); struct bpf_map *__bpf_map_get(struct fd f); struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref); @@@ -399,6 -413,7 +413,7 @@@ static inline void bpf_long_memcpy(voi

/* verify correctness of eBPF program */ int bpf_check(struct bpf_prog **fp, union bpf_attr *attr); + void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);

/* Map specifics */ struct net_device *__dev_map_lookup_elem(struct bpf_map *map, u32 key); @@@ -419,8 -434,6 +434,8 @@@ static inline int bpf_map_attr_numa_nod attr->numa_node : NUMA_NO_NODE; }

+struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type); + #else /* !CONFIG_BPF_SYSCALL */ static inline struct bpf_prog *bpf_prog_get(u32 ufd) { @@@ -508,12 -521,6 +523,12 @@@ static inline int cpu_map_enqueue(struc { return 0; } + +static inline struct bpf_prog *bpf_prog_get_type_path(const char *name, + enum bpf_prog_type type) +{ + return ERR_PTR(-EOPNOTSUPP); +} #endif /* CONFIG_BPF_SYSCALL */

static inline struct bpf_prog *bpf_prog_get_type(u32 ufd, @@@ -522,17 -529,17 +537,19 @@@ return bpf_prog_get_type_dev(ufd, type, false); }

+bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool); + int bpf_prog_offload_compile(struct bpf_prog *prog); void bpf_prog_offload_destroy(struct bpf_prog *prog); + int bpf_prog_offload_info_fill(struct bpf_prog_info *info, + struct bpf_prog *prog);

#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);

static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux) { - return aux->offload; + return aux->offload_requested; } #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, @@@ -547,7 -554,7 +564,7 @@@ static inline bool bpf_prog_is_dev_boun } #endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */

- #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) + #if defined(CONFIG_STREAM_PARSER) && defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_INET) struct sock *__sock_map_lookup_elem(struct bpf_map *map, u32 key); int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type); #else @@@ -586,4 -593,15 +603,15 @@@ extern const struct bpf_func_proto bpf_ void bpf_user_rnd_init_once(void); u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);

+ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) + #ifdef CONFIG_BPF_KPROBE_OVERRIDE + #define BPF_ALLOW_ERROR_INJECTION(fname) \ + static unsigned long __used \ + __attribute__((__section__("_kprobe_error_inject_list"))) \ + _eil_addr_##fname = (unsigned long)fname; + #else + #define BPF_ALLOW_ERROR_INJECTION(fname) + #endif + #endif + #endif /* _LINUX_BPF_H */ diff --combined include/linux/module.h index e6249795f9e2,548fa09fa806..0fd65481c045 --- a/include/linux/module.h +++ b/include/linux/module.h @@@ -475,6 -475,11 +475,11 @@@ struct module ctor_fn_t *ctors; unsigned int num_ctors; #endif + + #ifdef CONFIG_BPF_KPROBE_OVERRIDE + unsigned int num_kprobe_ei_funcs; + unsigned long *kprobe_ei_funcs; + #endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} @@@ -606,9 -611,6 +611,9 @@@ int ref_module(struct module *a, struc __mod ? __mod->name : "kernel"; \ })

+/* Dereference module function descriptor */ +void *dereference_module_function_descriptor(struct module *mod, void *ptr); + /* For kallsyms to ask for address resolution. namebuf should be at * least KSYM_NAME_LEN long: a pointer to namebuf is returned if * found, otherwise NULL. */ @@@ -763,13 -765,6 +768,13 @@@ static inline bool is_module_sig_enforc return false; }

+/* Dereference module function descriptor */ +static inline +void *dereference_module_function_descriptor(struct module *mod, void *ptr) +{ + return ptr; +} + #endif /* CONFIG_MODULES */

#ifdef CONFIG_SYSFS diff --combined include/linux/pci.h index 95807535d175,0314e0716c30..66cca1c6f742 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@@ -48,17 -48,17 +48,17 @@@ * In the interest of not exposing interfaces to user-space unnecessarily, * the following kernel-only defines are being added here. */ -#define PCI_DEVID(bus, devfn) ((((u16)(bus)) << 8) | (devfn)) +#define PCI_DEVID(bus, devfn) ((((u16)(bus)) << 8) | (devfn)) /* return bus from PCI devid = ((u16)bus_number) << 8) | devfn */ #define PCI_BUS_NUM(x) (((x) >> 8) & 0xff)

/* pci_slot represents a physical slot */ struct pci_slot { - struct pci_bus *bus; /* The bus this slot is on */ - struct list_head list; /* node in list of slots on this bus */ - struct hotplug_slot *hotplug; /* Hotplug info (migrate over time) */ - unsigned char number; /* PCI_SLOT(pci_dev->devfn) */ - struct kobject kobj; + struct pci_bus *bus; /* Bus this slot is on */ + struct list_head list; /* Node in list of slots */ + struct hotplug_slot *hotplug; /* Hotplug info (move here) */ + unsigned char number; /* PCI_SLOT(pci_dev->devfn) */ + struct kobject kobj; };

static inline const char *pci_slot_name(const struct pci_slot *slot) @@@ -72,7 -72,9 +72,7 @@@ enum pci_mmap_state pci_mmap_mem };

-/* - * For PCI devices, the region numbers are assigned this way: - */ +/* For PCI devices, the region numbers are assigned this way: */ enum { /* #0-5: standard PCI resources */ PCI_STD_RESOURCES, @@@ -81,23 -83,23 +81,23 @@@ /* #6: expansion ROM resource */ PCI_ROM_RESOURCE,

- /* device specific resources */ + /* Device-specific resources */ #ifdef CONFIG_PCI_IOV PCI_IOV_RESOURCES, PCI_IOV_RESOURCE_END = PCI_IOV_RESOURCES + PCI_SRIOV_NUM_BARS - 1, #endif

- /* resources assigned to buses behind the bridge */ + /* Resources assigned to buses behind the bridge */ #define PCI_BRIDGE_RESOURCE_NUM 4

PCI_BRIDGE_RESOURCES, PCI_BRIDGE_RESOURCE_END = PCI_BRIDGE_RESOURCES + PCI_BRIDGE_RESOURCE_NUM - 1,

- /* total resources associated with a PCI device */ + /* Total resources associated with a PCI device */ PCI_NUM_RESOURCES,

- /* preserve this for compatibility */ + /* Preserve this for compatibility */ DEVICE_COUNT_RESOURCE = PCI_NUM_RESOURCES, };

@@@ -150,10 -152,9 +150,10 @@@ static inline const char *pci_power_nam #define PCI_PM_D3COLD_WAIT 100 #define PCI_PM_BUS_WAIT 50

-/** The pci_channel state describes connectivity between the CPU and - * the pci device. If some PCI bus between here and the pci device - * has crashed or locked up, this info is reflected here. +/** + * The pci_channel state describes connectivity between the CPU and + * the PCI device. If some PCI bus between here and the PCI device + * has crashed or locked up, this info is reflected here. */ typedef unsigned int __bitwise pci_channel_state_t;

@@@ -183,7 -184,9 +183,7 @@@ enum pcie_reset_state

typedef unsigned short __bitwise pci_dev_flags_t; enum pci_dev_flags { - /* INTX_DISABLE in PCI_COMMAND register disables MSI - * generation too. - */ + /* INTX_DISABLE in PCI_COMMAND register disables MSI too */ PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG = (__force pci_dev_flags_t) (1 << 0), /* Device configuration is irrevocably lost if disabled into D3 */ PCI_DEV_FLAGS_NO_D3 = (__force pci_dev_flags_t) (1 << 1), @@@ -199,7 -202,7 +199,7 @@@ PCI_DEV_FLAGS_NO_PM_RESET = (__force pci_dev_flags_t) (1 << 7), /* Get VPD from function 0 VPD */ PCI_DEV_FLAGS_VPD_REF_F0 = (__force pci_dev_flags_t) (1 << 8), - /* a non-root bridge where translation occurs, stop alias search here */ + /* A non-root bridge where translation occurs, stop alias search here */ PCI_DEV_FLAGS_BRIDGE_XLATE_ROOT = (__force pci_dev_flags_t) (1 << 9), /* Do not use FLR even if device advertises PCI_AF_CAP */ PCI_DEV_FLAGS_NO_FLR_RESET = (__force pci_dev_flags_t) (1 << 10), @@@ -219,17 -222,17 +219,17 @@@ enum pci_bus_flags PCI_BUS_FLAGS_NO_AERSID = (__force pci_bus_flags_t) 4, };

-/* These values come from the PCI Express Spec */ +/* Values from Link Status register, PCIe r3.1, sec 7.8.8 */ enum pcie_link_width { PCIE_LNK_WIDTH_RESRV = 0x00, PCIE_LNK_X1 = 0x01, PCIE_LNK_X2 = 0x02, PCIE_LNK_X4 = 0x04, PCIE_LNK_X8 = 0x08, - PCIE_LNK_X12 = 0x0C, + PCIE_LNK_X12 = 0x0c, PCIE_LNK_X16 = 0x10, PCIE_LNK_X32 = 0x20, - PCIE_LNK_WIDTH_UNKNOWN = 0xFF, + PCIE_LNK_WIDTH_UNKNOWN = 0xff, };

/* Based on the PCI Hotplug Spec, but some values are made up by us */ @@@ -260,15 -263,15 +260,15 @@@ enum pci_bus_speed };

struct pci_cap_saved_data { - u16 cap_nr; - bool cap_extended; - unsigned int size; - u32 data[0]; + u16 cap_nr; + bool cap_extended; + unsigned int size; + u32 data[0]; };

struct pci_cap_saved_state { - struct hlist_node next; - struct pci_cap_saved_data cap; + struct hlist_node next; + struct pci_cap_saved_data cap; };

struct irq_affinity; @@@ -277,17 -280,19 +277,17 @@@ struct pci_vpd struct pci_sriov; struct pci_ats;

-/* - * The pci_dev structure is used to describe PCI devices. - */ +/* The pci_dev structure describes PCI devices */ struct pci_dev { - struct list_head bus_list; /* node in per-bus list */ - struct pci_bus *bus; /* bus this device is on */ - struct pci_bus *subordinate; /* bus this device bridges to */ + struct list_head bus_list; /* Node in per-bus list */ + struct pci_bus *bus; /* Bus this device is on */ + struct pci_bus *subordinate; /* Bus this device bridges to */

- void *sysdata; /* hook for sys-specific extension */ - struct proc_dir_entry *procent; /* device entry in /proc/bus/pci */ + void *sysdata; /* Hook for sys-specific extension */ + struct proc_dir_entry *procent; /* Device entry in /proc/bus/pci */ struct pci_slot *slot; /* Physical slot this device is in */

- unsigned int devfn; /* encoded device & function index */ + unsigned int devfn; /* Encoded device & function index */ unsigned short vendor; unsigned short device; unsigned short subsystem_vendor; @@@ -302,12 -307,12 +302,12 @@@ u8 msi_cap; /* MSI capability offset */ u8 msix_cap; /* MSI-X capability offset */ u8 pcie_mpss:3; /* PCIe Max Payload Size Supported */ - u8 rom_base_reg; /* which config register controls the ROM */ - u8 pin; /* which interrupt pin this device uses */ - u16 pcie_flags_reg; /* cached PCIe Capabilities Register */ - unsigned long *dma_alias_mask;/* mask of enabled devfn aliases */ + u8 rom_base_reg; /* Config register controlling ROM */ + u8 pin; /* Interrupt pin this device uses */ + u16 pcie_flags_reg; /* Cached PCIe Capabilities Register */ + unsigned long *dma_alias_mask;/* Mask of enabled devfn aliases */

- struct pci_driver *driver; /* which driver has allocated this device */ + struct pci_driver *driver; /* Driver bound to this device */ u64 dma_mask; /* Mask of the bits of bus address this device implements. Normally this is 0xffffffff. You only need to change @@@ -316,9 -321,9 +316,9 @@@

struct device_dma_parameters dma_parms;

- pci_power_t current_state; /* Current operating state. In ACPI-speak, - this is D0-D3, D0 being fully functional, - and D3 being off. */ + pci_power_t current_state; /* Current operating state. In ACPI, + this is D0-D3, D0 being fully + functional, and D3 being off. */ u8 pm_cap; /* PM capability offset */ unsigned int pme_support:5; /* Bitmask of states from which PME# can be generated */ @@@ -329,10 -334,10 +329,10 @@@ unsigned int no_d3cold:1; /* D3cold is forbidden */ unsigned int bridge_d3:1; /* Allow D3 for bridge */ unsigned int d3cold_allowed:1; /* D3cold is allowed by user */ - unsigned int mmio_always_on:1; /* disallow turning off io/mem - decoding during bar sizing */ + unsigned int mmio_always_on:1; /* Disallow turning off io/mem + decoding during BAR sizing */ unsigned int wakeup_prepared:1; - unsigned int runtime_d3cold:1; /* whether go through runtime + unsigned int runtime_d3cold:1; /* Whether go through runtime D3cold, not set for devices powered on/off by the corresponding bridge */ @@@ -345,14 -350,12 +345,14 @@@

#ifdef CONFIG_PCIEASPM struct pcie_link_state *link_state; /* ASPM link state */ + unsigned int ltr_path:1; /* Latency Tolerance Reporting + supported from root to here */ #endif

- pci_channel_state_t error_state; /* current connectivity state */ - struct device dev; /* Generic device interface */ + pci_channel_state_t error_state; /* Current connectivity state */ + struct device dev; /* Generic device interface */

- int cfg_size; /* Size of configuration space */ + int cfg_size; /* Size of config space */

/* * Instead of touching interrupt line and base address registers @@@ -361,47 -364,47 +361,47 @@@ unsigned int irq; struct resource resource[DEVICE_COUNT_RESOURCE]; /* I/O and memory regions + expansion ROMs */

- bool match_driver; /* Skip attaching driver */ - /* These fields are used by common fixups */ - unsigned int transparent:1; /* Subtractive decode PCI bridge */ - unsigned int multifunction:1;/* Part of multi-function device */ - /* keep track of device state */ + bool match_driver; /* Skip attaching driver */ + + unsigned int transparent:1; /* Subtractive decode bridge */ + unsigned int multifunction:1; /* Multi-function device */ + unsigned int is_added:1; - unsigned int is_busmaster:1; /* device is busmaster */ - unsigned int no_msi:1; /* device may not use msi */ - unsigned int no_64bit_msi:1; /* device may only use 32-bit MSIs */ - unsigned int block_cfg_access:1; /* config space access is blocked */ - unsigned int broken_parity_status:1; /* Device generates false positive parity */ - unsigned int irq_reroute_variant:2; /* device needs IRQ rerouting variant */ + unsigned int is_busmaster:1; /* Is busmaster */ + unsigned int no_msi:1; /* May not use MSI */ + unsigned int no_64bit_msi:1; /* May only use 32-bit MSIs */ + unsigned int block_cfg_access:1; /* Config space access blocked */ + unsigned int broken_parity_status:1; /* Generates false positive parity */ + unsigned int irq_reroute_variant:2; /* Needs IRQ rerouting variant */ unsigned int msi_enabled:1; unsigned int msix_enabled:1; - unsigned int ari_enabled:1; /* ARI forwarding */ - unsigned int ats_enabled:1; /* Address Translation Service */ + unsigned int ari_enabled:1; /* ARI forwarding */ + unsigned int ats_enabled:1; /* Address Translation Svc */ unsigned int pasid_enabled:1; /* Process Address Space ID */ unsigned int pri_enabled:1; /* Page Request Interface */ unsigned int is_managed:1; - unsigned int needs_freset:1; /* Dev requires fundamental reset */ + unsigned int needs_freset:1; /* Requires fundamental reset */ unsigned int state_saved:1; unsigned int is_physfn:1; unsigned int is_virtfn:1; unsigned int reset_fn:1; - unsigned int is_hotplug_bridge:1; - unsigned int is_thunderbolt:1; /* Thunderbolt controller */ - unsigned int __aer_firmware_first_valid:1; + unsigned int is_hotplug_bridge:1; + unsigned int is_thunderbolt:1; /* Thunderbolt controller */ + unsigned int __aer_firmware_first_valid:1; unsigned int __aer_firmware_first:1; - unsigned int broken_intx_masking:1; /* INTx masking can't be used */ - unsigned int io_window_1k:1; /* Intel P2P bridge 1K I/O windows */ + unsigned int broken_intx_masking:1; /* INTx masking can't be used */ + unsigned int io_window_1k:1; /* Intel bridge 1K I/O windows */ unsigned int irq_managed:1; unsigned int has_secondary_link:1; - unsigned int non_compliant_bars:1; /* broken BARs; ignore them */ - unsigned int is_probed:1; /* device probing in progress */ + unsigned int non_compliant_bars:1; /* Broken BARs; ignore them */ + unsigned int is_probed:1; /* Device probing in progress */ pci_dev_flags_t dev_flags; atomic_t enable_cnt; /* pci_enable_device has been called */

- u32 saved_config_space[16]; /* config space saved at suspend time */ + u32 saved_config_space[16]; /* Config space saved at suspend time */ struct hlist_head saved_cap_space; - struct bin_attribute *rom_attr; /* attribute descriptor for sysfs ROM entry */ - int rom_attr_enabled; /* has display of the rom attribute been enabled? */ + struct bin_attribute *rom_attr; /* Attribute descriptor for sysfs ROM entry */ + int rom_attr_enabled; /* Display of ROM attribute enabled? */ struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for resources */ struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file for WC mapping of resources */

@@@ -416,12 -419,12 +416,12 @@@ struct pci_vpd *vpd; #ifdef CONFIG_PCI_ATS union { - struct pci_sriov *sriov; /* SR-IOV capability related */ - struct pci_dev *physfn; /* the PF this VF is associated with */ + struct pci_sriov *sriov; /* PF: SR-IOV info */ + struct pci_dev *physfn; /* VF: related PF */ }; u16 ats_cap; /* ATS Capability offset */ u8 ats_stu; /* ATS Smallest Translation Unit */ - atomic_t ats_ref_cnt; /* number of VFs with ATS enabled */ + atomic_t ats_ref_cnt; /* Number of VFs with ATS enabled */ #endif #ifdef CONFIG_PCI_PRI u32 pri_reqs_alloc; /* Number of PRI requests allocated */ @@@ -429,11 -432,11 +429,11 @@@ #ifdef CONFIG_PCI_PASID u16 pasid_features; #endif - phys_addr_t rom; /* Physical address of ROM if it's not from the BAR */ - size_t romlen; /* Length of ROM if it's not from the BAR */ - char *driver_override; /* Driver name to force a match */ + phys_addr_t rom; /* Physical address if not from BAR */ + size_t romlen; /* Length if not from BAR */ + char *driver_override; /* Driver name to force a match */

- unsigned long priv_flags; /* Private flags for the pci driver */ + unsigned long priv_flags; /* Private flags for the PCI driver */ };

static inline struct pci_dev *pci_physfn(struct pci_dev *dev) @@@ -456,26 -459,26 +456,26 @@@ static inline int pci_channel_offline(s }

struct pci_host_bridge { - struct device dev; - struct pci_bus *bus; /* root bus */ - struct pci_ops *ops; - void *sysdata; - int busnr; + struct device dev; + struct pci_bus *bus; /* Root bus */ + struct pci_ops *ops; + void *sysdata; + int busnr; struct list_head windows; /* resource_entry */ - u8 (*swizzle_irq)(struct pci_dev *, u8 *); /* platform IRQ swizzler */ + u8 (*swizzle_irq)(struct pci_dev *, u8 *); /* Platform IRQ swizzler */ int (*map_irq)(const struct pci_dev *, u8, u8); void (*release_fn)(struct pci_host_bridge *); - void *release_data; + void *release_data; struct msi_controller *msi; - unsigned int ignore_reset_delay:1; /* for entire hierarchy */ - unsigned int no_ext_tags:1; /* no Extended Tags */ + unsigned int ignore_reset_delay:1; /* For entire hierarchy */ + unsigned int no_ext_tags:1; /* No Extended Tags */ /* Resource alignment requirements */ resource_size_t (*align_resource)(struct pci_dev *dev, const struct resource *res, resource_size_t start, resource_size_t size, resource_size_t align); - unsigned long private[0] ____cacheline_aligned; + unsigned long private[0] ____cacheline_aligned; };

#define to_pci_host_bridge(n) container_of(n, struct pci_host_bridge, dev) @@@ -497,8 -500,8 +497,8 @@@ void pci_free_host_bridge(struct pci_ho struct pci_host_bridge *pci_find_host_bridge(struct pci_bus *bus);

void pci_set_host_bridge_release(struct pci_host_bridge *bridge, - void (*release_fn)(struct pci_host_bridge *), - void *release_data); + void (*release_fn)(struct pci_host_bridge *), + void *release_data);

int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge);

@@@ -518,32 -521,32 +518,32 @@@ #define PCI_SUBTRACTIVE_DECODE 0x1

struct pci_bus_resource { - struct list_head list; - struct resource *res; - unsigned int flags; + struct list_head list; + struct resource *res; + unsigned int flags; };

#define PCI_REGION_FLAG_MASK 0x0fU /* These bits of resource flags tell us the PCI region flags */

struct pci_bus { - struct list_head node; /* node in list of buses */ - struct pci_bus *parent; /* parent bus this bridge is on */ - struct list_head children; /* list of child buses */ - struct list_head devices; /* list of devices on this bus */ - struct pci_dev *self; /* bridge device as seen by parent */ - struct list_head slots; /* list of slots on this bus; + struct list_head node; /* Node in list of buses */ + struct pci_bus *parent; /* Parent bus this bridge is on */ + struct list_head children; /* List of child buses */ + struct list_head devices; /* List of devices on this bus */ + struct pci_dev *self; /* Bridge device as seen by parent */ + struct list_head slots; /* List of slots on this bus; protected by pci_slot_mutex */ struct resource *resource[PCI_BRIDGE_RESOURCE_NUM]; - struct list_head resources; /* address space routed to this bus */ - struct resource busn_res; /* bus numbers routed to this bus */ + struct list_head resources; /* Address space routed to this bus */ + struct resource busn_res; /* Bus numbers routed to this bus */

- struct pci_ops *ops; /* configuration access functions */ + struct pci_ops *ops; /* Configuration access functions */ struct msi_controller *msi; /* MSI controller */ - void *sysdata; /* hook for sys-specific extension */ - struct proc_dir_entry *procdir; /* directory entry in /proc/bus/pci */ + void *sysdata; /* Hook for sys-specific extension */ + struct proc_dir_entry *procdir; /* Directory entry in /proc/bus/pci */

- unsigned char number; /* bus number */ - unsigned char primary; /* number of primary bridge */ + unsigned char number; /* Bus number */ + unsigned char primary; /* Number of primary bridge */ unsigned char max_bus_speed; /* enum pci_bus_speed */ unsigned char cur_bus_speed; /* enum pci_bus_speed */ #ifdef CONFIG_PCI_DOMAINS_GENERIC @@@ -552,12 -555,12 +552,12 @@@

char name[48];

- unsigned short bridge_ctl; /* manage NO_ISA/FBB/et al behaviors */ - pci_bus_flags_t bus_flags; /* inherited by child buses */ + unsigned short bridge_ctl; /* Manage NO_ISA/FBB/et al behaviors */ + pci_bus_flags_t bus_flags; /* Inherited by child buses */ struct device *bridge; struct device dev; - struct bin_attribute *legacy_io; /* legacy I/O for this bus */ - struct bin_attribute *legacy_mem; /* legacy mem */ + struct bin_attribute *legacy_io; /* Legacy I/O for this bus */ + struct bin_attribute *legacy_mem; /* Legacy mem */ unsigned int is_added:1; };

@@@ -614,7 -617,9 +614,7 @@@ static inline bool pci_dev_msi_enabled( static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { return false; } #endif

-/* - * Error values that may be returned by PCI functions. - */ +/* Error values that may be returned by PCI functions */ #define PCIBIOS_SUCCESSFUL 0x00 #define PCIBIOS_FUNC_NOT_SUPPORTED 0x81 #define PCIBIOS_BAD_VENDOR_ID 0x83 @@@ -623,7 -628,9 +623,7 @@@ #define PCIBIOS_SET_FAILED 0x88 #define PCIBIOS_BUFFER_TOO_SMALL 0x89

-/* - * Translate above to generic errno for passing back through non-PCI code. - */ +/* Translate above to generic errno for passing back through non-PCI code */ static inline int pcibios_err_to_errno(int err) { if (err <= PCIBIOS_SUCCESSFUL) @@@ -673,13 -680,13 +673,13 @@@ typedef u32 pci_bus_addr_t #endif

struct pci_bus_region { - pci_bus_addr_t start; - pci_bus_addr_t end; + pci_bus_addr_t start; + pci_bus_addr_t end; };

struct pci_dynids { - spinlock_t lock; /* protects list, index */ - struct list_head list; /* for IDs added at runtime */ + spinlock_t lock; /* Protects list, index */ + struct list_head list; /* For IDs added at runtime */ };

@@@ -693,13 -700,13 +693,13 @@@ typedef unsigned int __bitwise pci_ers_result_t;

enum pci_ers_result { - /* no result/none/not supported in device driver */ + /* No result/none/not supported in device driver */ PCI_ERS_RESULT_NONE = (__force pci_ers_result_t) 1,

/* Device driver can recover without slot reset */ PCI_ERS_RESULT_CAN_RECOVER = (__force pci_ers_result_t) 2,

- /* Device driver wants slot to be reset. */ + /* Device driver wants slot to be reset */ PCI_ERS_RESULT_NEED_RESET = (__force pci_ers_result_t) 3,

/* Device has completely failed, is unrecoverable */ @@@ -735,27 -742,27 +735,27 @@@ struct pci_error_handlers

struct module; struct pci_driver { - struct list_head node; - const char *name; - const struct pci_device_id *id_table; /* must be non-NULL for probe to be called */ - int (*probe) (struct pci_dev *dev, const struct pci_device_id *id); /* New device inserted */ - void (*remove) (struct pci_dev *dev); /* Device removed (NULL if not a hot-plug capable driver) */ - int (*suspend) (struct pci_dev *dev, pm_message_t state); /* Device suspended */ - int (*suspend_late) (struct pci_dev *dev, pm_message_t state); - int (*resume_early) (struct pci_dev *dev); - int (*resume) (struct pci_dev *dev); /* Device woken up */ + struct list_head node; + const char *name; + const struct pci_device_id *id_table; /* Must be non-NULL for probe to be called */ + int (*probe)(struct pci_dev *dev, const struct pci_device_id *id); /* New device inserted */ + void (*remove)(struct pci_dev *dev); /* Device removed (NULL if not a hot-plug capable driver) */ + int (*suspend)(struct pci_dev *dev, pm_message_t state); /* Device suspended */ + int (*suspend_late)(struct pci_dev *dev, pm_message_t state); + int (*resume_early)(struct pci_dev *dev); + int (*resume) (struct pci_dev *dev); /* Device woken up */ void (*shutdown) (struct pci_dev *dev); - int (*sriov_configure) (struct pci_dev *dev, int num_vfs); /* PF pdev */ + int (*sriov_configure) (struct pci_dev *dev, int num_vfs); /* On PF */ const struct pci_error_handlers *err_handler; const struct attribute_group **groups; struct device_driver driver; - struct pci_dynids dynids; + struct pci_dynids dynids; };

#define to_pci_driver(drv) container_of(drv, struct pci_driver, driver)

/** - * PCI_DEVICE - macro used to describe a specific pci device + * PCI_DEVICE - macro used to describe a specific PCI device * @vend: the 16 bit PCI Vendor ID * @dev: the 16 bit PCI Device ID * @@@ -768,7 -775,7 +768,7 @@@ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID

/** - * PCI_DEVICE_SUB - macro used to describe a specific pci device with subsystem + * PCI_DEVICE_SUB - macro used to describe a specific PCI device with subsystem * @vend: the 16 bit PCI Vendor ID * @dev: the 16 bit PCI Device ID * @subvend: the 16 bit PCI Subvendor ID @@@ -782,7 -789,7 +782,7 @@@ .subvendor = (subvend), .subdevice = (subdev)

/** - * PCI_DEVICE_CLASS - macro used to describe a specific pci device class + * PCI_DEVICE_CLASS - macro used to describe a specific PCI device class * @dev_class: the class, subclass, prog-if triple for this device * @dev_class_mask: the class mask for this device * @@@ -796,7 -803,7 +796,7 @@@ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID

/** - * PCI_VDEVICE - macro used to describe a specific pci device in short form + * PCI_VDEVICE - macro used to describe a specific PCI device in short form * @vend: the vendor name * @dev: the 16 bit PCI Device ID * @@@ -805,21 -812,22 +805,21 @@@ * to PCI_ANY_ID. The macro allows the next field to follow as the device * private data. */ - #define PCI_VDEVICE(vend, dev) \ .vendor = PCI_VENDOR_ID_##vend, .device = (dev), \ .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0

enum { - PCI_REASSIGN_ALL_RSRC = 0x00000001, /* ignore firmware setup */ - PCI_REASSIGN_ALL_BUS = 0x00000002, /* reassign all bus numbers */ - PCI_PROBE_ONLY = 0x00000004, /* use existing setup */ - PCI_CAN_SKIP_ISA_ALIGN = 0x00000008, /* don't do ISA alignment */ - PCI_ENABLE_PROC_DOMAINS = 0x00000010, /* enable domains in /proc */ + PCI_REASSIGN_ALL_RSRC = 0x00000001, /* Ignore firmware setup */ + PCI_REASSIGN_ALL_BUS = 0x00000002, /* Reassign all bus numbers */ + PCI_PROBE_ONLY = 0x00000004, /* Use existing setup */ + PCI_CAN_SKIP_ISA_ALIGN = 0x00000008, /* Don't do ISA alignment */ + PCI_ENABLE_PROC_DOMAINS = 0x00000010, /* Enable domains in /proc */ PCI_COMPAT_DOMAIN_0 = 0x00000020, /* ... except domain 0 */ - PCI_SCAN_ALL_PCIE_DEVS = 0x00000040, /* scan all, not just dev 0 */ + PCI_SCAN_ALL_PCIE_DEVS = 0x00000040, /* Scan all, not just dev 0 */ };

-/* these external functions are only available when PCI support is enabled */ +/* These external functions are only available when PCI support is enabled */ #ifdef CONFIG_PCI

extern unsigned int pci_flags; @@@ -832,11 -840,11 +832,11 @@@ static inline int pci_has_flag(int flag void pcie_bus_configure_settings(struct pci_bus *bus);

enum pcie_bus_config_types { - PCIE_BUS_TUNE_OFF, /* don't touch MPS at all */ - PCIE_BUS_DEFAULT, /* ensure MPS matches upstream bridge */ - PCIE_BUS_SAFE, /* use largest MPS boot-time devices support */ - PCIE_BUS_PERFORMANCE, /* use MPS and MRRS for best performance */ - PCIE_BUS_PEER2PEER, /* set MPS = 128 for all devices */ + PCIE_BUS_TUNE_OFF, /* Don't touch MPS at all */ + PCIE_BUS_DEFAULT, /* Ensure MPS matches upstream bridge */ + PCIE_BUS_SAFE, /* Use largest MPS boot-time devices support */ + PCIE_BUS_PERFORMANCE, /* Use MPS and MRRS for best performance */ + PCIE_BUS_PEER2PEER, /* Set MPS = 128 for all devices */ };

extern enum pcie_bus_config_types pcie_bus_config; @@@ -845,7 -853,7 +845,7 @@@ extern struct bus_type pci_bus_type

/* Do NOT directly access these two variables, unless you are arch-specific PCI * code, or PCI core code. */ -extern struct list_head pci_root_buses; /* list of all known PCI buses */ +extern struct list_head pci_root_buses; /* List of all known PCI buses */ /* Some device drivers need know if PCI is initiated */ int no_pci_devices(void);

@@@ -883,8 -891,8 +883,8 @@@ int pci_bus_insert_busn_res(struct pci_ int pci_bus_update_busn_res_end(struct pci_bus *b, int busmax); void pci_bus_release_busn_res(struct pci_bus *b); struct pci_bus *pci_scan_root_bus(struct device *parent, int bus, - struct pci_ops *ops, void *sysdata, - struct list_head *resources); + struct pci_ops *ops, void *sysdata, + struct list_head *resources); int pci_scan_root_bus_bridge(struct pci_host_bridge *bridge); struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev, int busnr); @@@ -941,10 -949,10 +941,10 @@@ int pci_find_next_ht_capability(struct struct pci_bus *pci_find_next_bus(const struct pci_bus *from);

struct pci_dev *pci_get_device(unsigned int vendor, unsigned int device, - struct pci_dev *from); + struct pci_dev *from); struct pci_dev *pci_get_subsys(unsigned int vendor, unsigned int device, - unsigned int ss_vendor, unsigned int ss_device, - struct pci_dev *from); + unsigned int ss_vendor, unsigned int ss_device, + struct pci_dev *from); struct pci_dev *pci_get_slot(struct pci_bus *bus, unsigned int devfn); struct pci_dev *pci_get_domain_bus_and_slot(int domain, unsigned int bus, unsigned int devfn); @@@ -1020,7 -1028,7 +1020,7 @@@ static inline int pcie_capability_clear return pcie_capability_clear_and_set_dword(dev, pos, clear, 0); }

-/* user-space driven config access */ +/* User-space driven config access */ int pci_user_read_config_byte(struct pci_dev *dev, int where, u8 *val); int pci_user_read_config_word(struct pci_dev *dev, int where, u16 *val); int pci_user_read_config_dword(struct pci_dev *dev, int where, u32 *val); @@@ -1064,6 -1072,7 +1064,7 @@@ int pci_set_pcie_reset_state(struct pci int pci_set_cacheline_size(struct pci_dev *dev); #define HAVE_PCI_SET_MWI int __must_check pci_set_mwi(struct pci_dev *dev); + int __must_check pcim_set_mwi(struct pci_dev *dev); int pci_try_set_mwi(struct pci_dev *dev); void pci_clear_mwi(struct pci_dev *dev); void pci_intx(struct pci_dev *dev, int enable); @@@ -1162,7 -1171,7 +1163,7 @@@ unsigned int pci_rescan_bus(struct pci_ void pci_lock_rescan_remove(void); void pci_unlock_rescan_remove(void);

-/* Vital product data routines */ +/* Vital Product Data routines */ ssize_t pci_read_vpd(struct pci_dev *dev, loff_t pos, size_t count, void *buf); ssize_t pci_write_vpd(struct pci_dev *dev, loff_t pos, size_t count, const void *buf); int pci_set_vpd_size(struct pci_dev *dev, size_t len); @@@ -1247,7 -1256,9 +1248,7 @@@ static inline pci_bus_addr_t pci_bus_ad int __must_check __pci_register_driver(struct pci_driver *, struct module *, const char *mod_name);

-/* - * pci_register_driver must be a macro so that KBUILD_MODNAME can be expanded - */ +/* pci_register_driver() must be a macro so KBUILD_MODNAME can be expanded */ #define pci_register_driver(driver) \ __pci_register_driver(driver, THIS_MODULE, KBUILD_MODNAME)

@@@ -1262,7 -1273,8 +1263,7 @@@ void pci_unregister_driver(struct pci_d * use this macro once, and calling it replaces module_init() and module_exit() */ #define module_pci_driver(__pci_driver) \ - module_driver(__pci_driver, pci_register_driver, \ - pci_unregister_driver) + module_driver(__pci_driver, pci_register_driver, pci_unregister_driver)

/** * builtin_pci_driver() - Helper macro for registering a PCI driver @@@ -1301,10 -1313,10 +1302,10 @@@ resource_size_t pcibios_iov_resource_al int pci_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags);

-#define PCI_IRQ_LEGACY (1 << 0) /* allow legacy interrupts */ -#define PCI_IRQ_MSI (1 << 1) /* allow MSI interrupts */ -#define PCI_IRQ_MSIX (1 << 2) /* allow MSI-X interrupts */ -#define PCI_IRQ_AFFINITY (1 << 3) /* auto-assign affinity */ +#define PCI_IRQ_LEGACY (1 << 0) /* Allow legacy interrupts */ +#define PCI_IRQ_MSI (1 << 1) /* Allow MSI interrupts */ +#define PCI_IRQ_MSIX (1 << 2) /* Allow MSI-X interrupts */ +#define PCI_IRQ_AFFINITY (1 << 3) /* Auto-assign affinity */ #define PCI_IRQ_ALL_TYPES \ (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX)

@@@ -1323,8 -1335,8 +1324,8 @@@ #define pci_pool_free(pool, vaddr, addr) dma_pool_free(pool, vaddr, addr)

struct msix_entry { - u32 vector; /* kernel uses to write allocated vector */ - u16 entry; /* driver uses to specify entry, OS writes */ + u32 vector; /* Kernel uses to write allocated vector */ + u16 entry; /* Driver uses to specify entry, OS writes */ };

#ifdef CONFIG_PCI_MSI @@@ -1364,10 -1376,10 +1365,10 @@@ static inline int pci_msi_enabled(void static inline int pci_enable_msi(struct pci_dev *dev) { return -ENOSYS; } static inline int pci_enable_msix_range(struct pci_dev *dev, - struct msix_entry *entries, int minvec, int maxvec) + struct msix_entry *entries, int minvec, int maxvec) { return -ENOSYS; } static inline int pci_enable_msix_exact(struct pci_dev *dev, - struct msix_entry *entries, int nvec) + struct msix_entry *entries, int nvec) { return -ENOSYS; }

static inline int @@@ -1532,9 -1544,9 +1533,9 @@@ static inline int acpi_pci_bus_find_dom int pci_bus_find_domain_nr(struct pci_bus *bus, struct device *parent); #endif

-/* some architectures require additional setup to direct VGA traffic */ +/* Some architectures require additional setup to direct VGA traffic */ typedef int (*arch_set_vga_state_t)(struct pci_dev *pdev, bool decode, - unsigned int command_bits, u32 flags); + unsigned int command_bits, u32 flags); void pci_register_set_vga_state(arch_set_vga_state_t func);

static inline int @@@ -1573,9 -1585,10 +1574,9 @@@ static inline void pci_clear_flags(int static inline int pci_has_flag(int flag) { return 0; }

/* - * If the system does not have PCI, clearly these return errors. Define - * these as simple inline functions to avoid hair in drivers. + * If the system does not have PCI, clearly these return errors. Define + * these as simple inline functions to avoid hair in drivers. */ - #define _PCI_NOP(o, s, t) \ static inline int pci_##o##_config_##s(struct pci_dev *dev, \ int where, t val) \ @@@ -1714,10 -1727,8 +1715,10 @@@ int pci_iobar_pfn(struct pci_dev *pdev #define pci_root_bus_fwnode(bus) NULL #endif

-/* these helpers provide future and backwards compatibility - * for accessing popular PCI BAR info */ +/* + * These helpers provide future and backwards compatibility + * for accessing popular PCI BAR info + */ #define pci_resource_start(dev, bar) ((dev)->resource[(bar)].start) #define pci_resource_end(dev, bar) ((dev)->resource[(bar)].end) #define pci_resource_flags(dev, bar) ((dev)->resource[(bar)].flags) @@@ -1729,8 -1740,7 +1730,8 @@@ (pci_resource_end((dev), (bar)) - \ pci_resource_start((dev), (bar)) + 1))

-/* Similar to the helpers above, these manipulate per-pci_dev +/* + * Similar to the helpers above, these manipulate per-pci_dev * driver-specific data. They are really just a wrapper around * the generic device structure functions of these calls. */ @@@ -1744,14 -1754,16 +1745,14 @@@ static inline void pci_set_drvdata(stru dev_set_drvdata(&pdev->dev, data); }

-/* If you want to know what to call your pci_dev, ask this function. - * Again, it's a wrapper around the generic device. - */ static inline const char *pci_name(const struct pci_dev *pdev) { return dev_name(&pdev->dev); }

-/* Some archs don't want to expose struct resource to userland as-is +/* + * Some archs don't want to expose struct resource to userland as-is * in sysfs and /proc */ #ifdef HAVE_ARCH_PCI_RESOURCE_TO_USER @@@ -1770,16 -1782,16 +1771,16 @@@ static inline void pci_resource_to_user

/* - * The world is not perfect and supplies us with broken PCI devices. - * For at least a part of these bugs we need a work-around, so both - * generic (drivers/pci/quirks.c) and per-architecture code can define - * fixup hooks to be called for particular buggy devices. + * The world is not perfect and supplies us with broken PCI devices. + * For at least a part of these bugs we need a work-around, so both + * generic (drivers/pci/quirks.c) and per-architecture code can define + * fixup hooks to be called for particular buggy devices. */

struct pci_fixup { - u16 vendor; /* You can use PCI_ANY_ID here of course */ - u16 device; /* You can use PCI_ANY_ID here of course */ - u32 class; /* You can use PCI_ANY_ID here too */ + u16 vendor; /* Or PCI_ANY_ID */ + u16 device; /* Or PCI_ANY_ID */ + u32 class; /* Or PCI_ANY_ID */ unsigned int class_shift; /* should be 0, 8, 16 */ void (*hook)(struct pci_dev *dev); }; @@@ -1821,19 -1833,23 +1822,19 @@@ enum pci_fixup_pass #define DECLARE_PCI_FIXUP_CLASS_RESUME(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume, \ - resume##hook, vendor, device, class, \ - class_shift, hook) + resume##hook, vendor, device, class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_RESUME_EARLY(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume_early, \ - resume_early##hook, vendor, device, \ - class, class_shift, hook) + resume_early##hook, vendor, device, class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_SUSPEND(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_suspend, \ - suspend##hook, vendor, device, class, \ - class_shift, hook) + suspend##hook, vendor, device, class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_SUSPEND_LATE(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_suspend_late, \ - suspend_late##hook, vendor, device, \ - class, class_shift, hook) + suspend_late##hook, vendor, device, class, class_shift, hook)

#define DECLARE_PCI_FIXUP_EARLY(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_early, \ @@@ -1849,16 -1865,20 +1850,16 @@@ hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_RESUME(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume, \ - resume##hook, vendor, device, \ - PCI_ANY_ID, 0, hook) + resume##hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_RESUME_EARLY(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume_early, \ - resume_early##hook, vendor, device, \ - PCI_ANY_ID, 0, hook) + resume_early##hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_SUSPEND(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_suspend, \ - suspend##hook, vendor, device, \ - PCI_ANY_ID, 0, hook) + suspend##hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_SUSPEND_LATE(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_suspend_late, \ - suspend_late##hook, vendor, device, \ - PCI_ANY_ID, 0, hook) + suspend_late##hook, vendor, device, PCI_ANY_ID, 0, hook)

#ifdef CONFIG_PCI_QUIRKS void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev); @@@ -1945,7 -1965,6 +1946,7 @@@ int pci_vfs_assigned(struct pci_dev *de int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs); int pci_sriov_get_totalvfs(struct pci_dev *dev); resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno); +void pci_vf_drivers_autoprobe(struct pci_dev *dev, bool probe); #else static inline int pci_iov_virtfn_bus(struct pci_dev *dev, int id) { @@@ -1973,7 -1992,6 +1974,7 @@@ static inline int pci_sriov_get_totalvf { return 0; } static inline resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno) { return 0; } +static inline void pci_vf_drivers_autoprobe(struct pci_dev *dev, bool probe) { } #endif

#if defined(CONFIG_HOTPLUG_PCI) || defined(CONFIG_HOTPLUG_PCI_MODULE) @@@ -2095,7 -2113,7 +2096,7 @@@ static inline u16 pci_vpd_lrdt_size(con */ static inline u16 pci_vpd_lrdt_tag(const u8 *lrdt) { - return (u16)(lrdt[0] & PCI_VPD_LRDT_TIN_MASK); + return (u16)(lrdt[0] & PCI_VPD_LRDT_TIN_MASK); }

/** @@@ -2180,7 -2198,7 +2181,7 @@@ static inline struct device_node *pci_b return bus ? bus->dev.of_node : NULL; }

-#else /* CONFIG_OF */ +#else /* CONFIG_OF */ static inline void pci_set_of_node(struct pci_dev *dev) { } static inline void pci_release_of_node(struct pci_dev *dev) { } static inline void pci_set_bus_of_node(struct pci_bus *bus) { } @@@ -2189,7 -2207,7 +2190,7 @@@ static inline struct device_node pci_device_to_OF_node(const struct pci_dev *pdev) { return NULL; } static inline struct irq_domain * pci_host_bridge_of_msi_domain(struct pci_bus *bus) { return NULL; } -#endif /* CONFIG_OF */ +#endif /* CONFIG_OF */

#ifdef CONFIG_ACPI struct irq_domain *pci_host_bridge_acpi_msi_domain(struct pci_bus *bus); @@@ -2214,7 -2232,7 +2215,7 @@@ int pci_for_each_dma_alias(struct pci_d int (*fn)(struct pci_dev *pdev, u16 alias, void *data), void *data);

-/* helper functions for operation of device flag */ +/* Helper functions for operation of device flag */ static inline void pci_set_dev_assigned(struct pci_dev *pdev) { pdev->dev_flags |= PCI_DEV_FLAGS_ASSIGNED; @@@ -2261,7 -2279,7 +2262,7 @@@ static inline bool pci_is_thunderbolt_a return false; }

-/* provide the legacy pci_dma_* API */ +/* Provide the legacy pci_dma_* API */ #include <linux/pci-dma-compat.h>

#endif /* LINUX_PCI_H */ diff --combined include/linux/sh_eth.h index 94081e9a5010,dd5d69323701..6dfda97a6c1a --- a/include/linux/sh_eth.h +++ b/include/linux/sh_eth.h @@@ -5,18 -5,16 +5,15 @@@ #include <linux/phy.h> #include <linux/if_ether.h>

- enum {EDMAC_LITTLE_ENDIAN}; - struct sh_eth_plat_data { int phy; int phy_irq; - int edmac_endian; phy_interface_t phy_interface; void (*set_mdio_gate)(void *addr);

unsigned char mac_addr[ETH_ALEN]; unsigned no_ether_link:1; unsigned ether_link_active_low:1; - unsigned needs_init:1; };

#endif diff --combined include/linux/skbuff.h index a87e43d16f44,b8e0da6c27d6..ac89a93b7c83 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@@ -1211,6 -1211,11 +1211,11 @@@ static inline bool skb_flow_dissect_flo data, proto, nhoff, hlen, flags); }

+ void + skb_flow_dissect_tunnel_info(const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + void *target_container); + static inline __u32 skb_get_hash(struct sk_buff *skb) { if (!skb->l4_hash && !skb->sw_hash) @@@ -3241,7 -3246,7 +3246,7 @@@ struct sk_buff *__skb_recv_datagram(str int *peeked, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, int noblock, int *err); -unsigned int datagram_poll(struct file *file, struct socket *sock, +__poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, struct iov_iter *to, int size); diff --combined include/net/inet_connection_sock.h index ec72cdb5bc39,8e1bf9ae4a5e..6692d67e9245 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@@ -77,6 -77,7 +77,7 @@@ struct inet_connection_sock_af_ops * @icsk_af_ops Operations which are AF_INET{4,6} specific * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data + * @icsk_listen_portaddr_node hash to the portaddr listener hashtable * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts * @icsk_pending: Scheduled timer event @@@ -101,6 -102,7 +102,7 @@@ struct inet_connection_sock const struct inet_connection_sock_af_ops *icsk_af_ops; const struct tcp_ulp_ops *icsk_ulp_ops; void *icsk_ulp_data; + struct hlist_node icsk_listen_portaddr_node; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:6, icsk_ca_setsockopt:1, @@@ -305,7 -307,7 +307,7 @@@ void inet_csk_prepare_forced_close(stru /* * LISTEN is a special case for poll.. */ -static inline unsigned int inet_csk_listen_poll(const struct sock *sk) +static inline __poll_t inet_csk_listen_poll(const struct sock *sk) { return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ? (POLLIN | POLLRDNORM) : 0; diff --combined include/net/sctp/sctp.h index 608d123ef25f,20c0c1be2ca7..f7ae6b0a21d0 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@@ -107,7 -107,7 +107,7 @@@ int sctp_backlog_rcv(struct sock *sk, s int sctp_inet_listen(struct socket *sock, int backlog); void sctp_write_space(struct sock *sk); void sctp_data_ready(struct sock *sk); -unsigned int sctp_poll(struct file *file, struct socket *sock, +__poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait); void sctp_sock_rfree(struct sk_buff *skb); void sctp_copy_sock(struct sock *newsk, struct sock *sk, @@@ -116,7 -116,7 +116,7 @@@ extern struct percpu_counter sctp_socke int sctp_asconf_mgmt(struct sctp_sock *, struct sctp_sockaddr_entry *); struct sk_buff *sctp_skb_recv_datagram(struct sock *, int, int, int *);

- int sctp_transport_walk_start(struct rhashtable_iter *iter); + void sctp_transport_walk_start(struct rhashtable_iter *iter); void sctp_transport_walk_stop(struct rhashtable_iter *iter); struct sctp_transport *sctp_transport_get_next(struct net *net, struct rhashtable_iter *iter); @@@ -444,13 -444,13 +444,13 @@@ static inline int sctp_frag_point(cons int frag = pmtu;

frag -= sp->pf->af->net_header_len; - frag -= sizeof(struct sctphdr) + sizeof(struct sctp_data_chunk); + frag -= sizeof(struct sctphdr) + sctp_datachk_len(&asoc->stream);

if (asoc->user_frag) frag = min_t(int, frag, asoc->user_frag);

frag = SCTP_TRUNC4(min_t(int, frag, SCTP_MAX_CHUNK_LEN - - sizeof(struct sctp_data_chunk))); + sctp_datachk_len(&asoc->stream)));

return frag; } diff --combined include/net/sctp/structs.h index 9a5ccf03a59b,8ac4d5cdbfed..02369e379d35 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@@ -89,6 -89,7 +89,7 @@@ struct sctp_stream #include <net/sctp/tsnmap.h> #include <net/sctp/ulpevent.h> #include <net/sctp/ulpqueue.h> + #include <net/sctp/stream_interleave.h>

/* Structures useful for managing bind/connect. */

@@@ -217,6 -218,7 +218,7 @@@ struct sctp_sock disable_fragments:1, v4mapped:1, frag_interleave:1, + strm_interleave:1, recvrcvinfo:1, recvnxtinfo:1, data_ready_signalled:1; @@@ -397,6 -399,28 +399,28 @@@ void sctp_stream_update(struct sctp_str #define sctp_ssn_skip(stream, type, sid, ssn) \ ((stream)->type[sid].ssn = ssn + 1)

+ /* What is the current MID number for this stream? */ + #define sctp_mid_peek(stream, type, sid) \ + ((stream)->type[sid].mid) + + /* Return the next MID number for this stream. */ + #define sctp_mid_next(stream, type, sid) \ + ((stream)->type[sid].mid++) + + /* Skip over this mid and all below. */ + #define sctp_mid_skip(stream, type, sid, mid) \ + ((stream)->type[sid].mid = mid + 1) + + #define sctp_stream_in(asoc, sid) (&(asoc)->stream.in[sid]) + + /* What is the current MID_uo number for this stream? */ + #define sctp_mid_uo_peek(stream, type, sid) \ + ((stream)->type[sid].mid_uo) + + /* Return the next MID_uo number for this stream. */ + #define sctp_mid_uo_next(stream, type, sid) \ + ((stream)->type[sid].mid_uo++) + /* * Pointers to address related SCTP functions. * (i.e. things that depend on the address family.) @@@ -574,6 -598,8 +598,8 @@@ struct sctp_chunk struct sctp_addiphdr *addip_hdr; struct sctp_fwdtsn_hdr *fwdtsn_hdr; struct sctp_authhdr *auth_hdr; + struct sctp_idatahdr *idata_hdr; + struct sctp_ifwdtsn_hdr *ifwdtsn_hdr; } subh;

__u8 *chunk_end; @@@ -620,6 -646,7 +646,7 @@@ __u16 rtt_in_progress:1, /* This chunk used for RTT calc? */ has_tsn:1, /* Does this chunk have a TSN yet? */ has_ssn:1, /* Does this chunk have a SSN yet? */ + #define has_mid has_ssn singleton:1, /* Only chunk in the packet? */ end_of_packet:1, /* Last chunk in the packet? */ ecn_ce_done:1, /* Have we processed the ECN CE bit? */ @@@ -966,7 -993,7 +993,7 @@@ void sctp_transport_burst_limited(struc void sctp_transport_burst_reset(struct sctp_transport *); unsigned long sctp_transport_timeout(struct sctp_transport *); void sctp_transport_reset(struct sctp_transport *t); -void sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); +bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu); void sctp_transport_immediate_rtx(struct sctp_transport *); void sctp_transport_dst_release(struct sctp_transport *t); void sctp_transport_dst_confirm(struct sctp_transport *t); @@@ -1073,6 -1100,7 +1100,7 @@@ void sctp_retransmit_mark(struct sctp_o void sctp_outq_uncork(struct sctp_outq *, gfp_t gfp); void sctp_prsctp_prune(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo, int msg_len); + void sctp_generate_fwdtsn(struct sctp_outq *q, __u32 sack_ctsn); /* Uncork and flush an outqueue. */ static inline void sctp_outq_cork(struct sctp_outq *q) { @@@ -1357,13 -1385,25 +1385,25 @@@ struct sctp_stream_out_ext };

struct sctp_stream_out { - __u16 ssn; - __u8 state; + union { + __u32 mid; + __u16 ssn; + }; + __u32 mid_uo; struct sctp_stream_out_ext *ext; + __u8 state; };

struct sctp_stream_in { - __u16 ssn; + union { + __u32 mid; + __u16 ssn; + }; + __u32 mid_uo; + __u32 fsn; + __u32 fsn_uo; + char pd_mode; + char pd_mode_uo; };

struct sctp_stream { @@@ -1387,11 -1427,32 +1427,32 @@@ struct sctp_stream_out_ext *rr_next; }; }; + struct sctp_stream_interleave *si; };

#define SCTP_STREAM_CLOSED 0x00 #define SCTP_STREAM_OPEN 0x01

+ static inline __u16 sctp_datachk_len(const struct sctp_stream *stream) + { + return stream->si->data_chunk_len; + } + + static inline __u16 sctp_datahdr_len(const struct sctp_stream *stream) + { + return stream->si->data_chunk_len - sizeof(struct sctp_chunkhdr); + } + + static inline __u16 sctp_ftsnchk_len(const struct sctp_stream *stream) + { + return stream->si->ftsn_chunk_len; + } + + static inline __u16 sctp_ftsnhdr_len(const struct sctp_stream *stream) + { + return stream->si->ftsn_chunk_len - sizeof(struct sctp_chunkhdr); + } + /* SCTP_GET_ASSOC_STATS counters */ struct sctp_priv_assoc_stats { /* Maximum observed rto in the association during subsequent @@@ -1940,6 -2001,7 +2001,7 @@@ struct sctp_association __u8 need_ecne:1, /* Need to send an ECNE Chunk? */ temp:1, /* Is it a temporary association? */ force_delay:1, + intl_enable:1, prsctp_enable:1, reconf_enable:1;

diff --combined include/net/sock.h index 4fd74e0d1bbb,73b7830b0bb8..0752f034f1bf --- a/include/net/sock.h +++ b/include/net/sock.h @@@ -72,6 -72,7 +72,7 @@@ #include <net/tcp_states.h> #include <linux/net_tstamp.h> #include <net/smc.h> + #include <net/l3mdev.h>

/* * This structure really needs to be cleaned up. @@@ -1262,6 -1263,7 +1263,7 @@@ proto_memory_pressure(struct proto *pro /* Called with local bh disabled */ void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc); int sock_prot_inuse_get(struct net *net, struct proto *proto); + int sock_inuse_get(struct net *net); #else static inline void sock_prot_inuse_add(struct net *net, struct proto *prot, int inc) @@@ -1583,7 -1585,7 +1585,7 @@@ int sock_no_connect(struct socket *, st int sock_no_socketpair(struct socket *, struct socket *); int sock_no_accept(struct socket *, struct socket *, int, bool); int sock_no_getname(struct socket *, struct sockaddr *, int *, int); -unsigned int sock_no_poll(struct file *, struct socket *, +__poll_t sock_no_poll(struct file *, struct socket *, struct poll_table_struct *); int sock_no_ioctl(struct socket *, unsigned int, unsigned long); int sock_no_listen(struct socket *, int); @@@ -2337,31 -2339,6 +2339,6 @@@ static inline bool sk_listener(const st return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); }

- /** - * sk_state_load - read sk->sk_state for lockless contexts - * @sk: socket pointer - * - * Paired with sk_state_store(). Used in places we do not hold socket lock : - * tcp_diag_get_info(), tcp_get_info(), tcp_poll(), get_tcp4_sock() ... - */ - static inline int sk_state_load(const struct sock *sk) - { - return smp_load_acquire(&sk->sk_state); - } - - /** - * sk_state_store - update sk->sk_state - * @sk: socket pointer - * @newstate: new state - * - * Paired with sk_state_load(). Should be used in contexts where - * state change might impact lockless readers. - */ - static inline void sk_state_store(struct sock *sk, int newstate) - { - smp_store_release(&sk->sk_state, newstate); - } - void sock_enable_timestamp(struct sock *sk, int flag); int sock_get_timestamp(struct sock *, struct timeval __user *); int sock_get_timestampns(struct sock *, struct timespec __user *); @@@ -2412,4 -2389,34 +2389,34 @@@ static inline int sk_get_rmem0(const st return *proto->sysctl_rmem; }

+ /* Default TCP Small queue budget is ~1 ms of data (1sec >> 10) + * Some wifi drivers need to tweak it to get more chunks. + * They can use this helper from their ndo_start_xmit() + */ + static inline void sk_pacing_shift_update(struct sock *sk, int val) + { + if (!sk || !sk_fullsock(sk) || sk->sk_pacing_shift == val) + return; + sk->sk_pacing_shift = val; + } + + /* if a socket is bound to a device, check that the given device + * index is either the same or that the socket is bound to an L3 + * master device and the given device index is also enslaved to + * that L3 master + */ + static inline bool sk_dev_equal_l3scope(struct sock *sk, int dif) + { + int mdif; + + if (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dif) + return true; + + mdif = l3mdev_master_ifindex_by_index(sock_net(sk), dif); + if (mdif && mdif == sk->sk_bound_dev_if) + return true; + + return false; + } + #endif /* _SOCK_H */ diff --combined include/net/tcp.h index 50b21a49d870,6939e69d3c37..26c2793846a1 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@@ -387,7 -387,7 +387,7 @@@ bool tcp_peer_is_proven(struct request_ void tcp_close(struct sock *sk, long timeout); void tcp_init_sock(struct sock *sk); void tcp_init_transfer(struct sock *sk, int bpf_op); -unsigned int tcp_poll(struct file *file, struct socket *sock, +__poll_t tcp_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int tcp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); @@@ -1507,8 -1507,7 +1507,7 @@@ int tcp_md5_hash_key(struct tcp_md5sig_

/* From tcp_fastopen.c */ void tcp_fastopen_cache_get(struct sock *sk, u16 *mss, - struct tcp_fastopen_cookie *cookie, int *syn_loss, - unsigned long *last_syn_loss); + struct tcp_fastopen_cookie *cookie); void tcp_fastopen_cache_set(struct sock *sk, u16 mss, struct tcp_fastopen_cookie *cookie, bool syn_lost, u16 try_exp); @@@ -1546,7 -1545,7 +1545,7 @@@ extern unsigned int sysctl_tcp_fastopen void tcp_fastopen_active_disable(struct sock *sk); bool tcp_fastopen_active_should_disable(struct sock *sk); void tcp_fastopen_active_disable_ofo_check(struct sock *sk); - void tcp_fastopen_active_timeout_reset(void); + void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired);

/* Latencies incurred by various limits for a sender. They are * chronograph-like stats that are mutually exclusive. @@@ -2011,10 -2010,12 +2010,12 @@@ static inline int tcp_call_bpf(struct s struct bpf_sock_ops_kern sock_ops; int ret;

- if (sk_fullsock(sk)) + memset(&sock_ops, 0, sizeof(sock_ops)); + if (sk_fullsock(sk)) { + sock_ops.is_fullsock = 1; sock_owned_by_me(sk); + }

- memset(&sock_ops, 0, sizeof(sock_ops)); sock_ops.sk = sk; sock_ops.op = op;

diff --combined include/uapi/linux/if_ether.h index 144de4d2f385,87b7529fcdfe..f8cb5760ea4f --- a/include/uapi/linux/if_ether.h +++ b/include/uapi/linux/if_ether.h @@@ -23,7 -23,6 +23,7 @@@ #define _UAPI_LINUX_IF_ETHER_H

#include <linux/types.h> +#include <linux/libc-compat.h>

/* * IEEE 802.3 Ethernet magic constants. The frame sizes omit the preamble @@@ -48,6 -47,7 +48,7 @@@ #define ETH_P_PUP 0x0200 /* Xerox PUP packet */ #define ETH_P_PUPAT 0x0201 /* Xerox PUP Addr Trans packet */ #define ETH_P_TSN 0x22F0 /* TSN (IEEE 1722) packet */ + #define ETH_P_ERSPAN2 0x22EB /* ERSPAN version 2 (type III) */ #define ETH_P_IP 0x0800 /* Internet Protocol packet */ #define ETH_P_X25 0x0805 /* CCITT X.25 */ #define ETH_P_ARP 0x0806 /* Address Resolution packet */ @@@ -150,13 -150,11 +151,13 @@@ * This is an Ethernet frame header. */

+#if __UAPI_DEF_ETHHDR struct ethhdr { unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ unsigned char h_source[ETH_ALEN]; /* source ether addr */ __be16 h_proto; /* packet type ID field */ } __attribute__((packed)); +#endif

#endif /* _UAPI_LINUX_IF_ETHER_H */ diff --combined kernel/bpf/sockmap.c index 1712d319c2d8,3f662ee23a34..079968680bc3 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@@ -96,14 -96,6 +96,6 @@@ static inline struct smap_psock *smap_p return rcu_dereference_sk_user_data(sk); }

- /* compute the linear packet data range [data, data_end) for skb when - * sk_skb type programs are in use. - */ - static inline void bpf_compute_data_end_sk_skb(struct sk_buff *skb) - { - TCP_SKB_CB(skb)->bpf.data_end = skb->data + skb_headlen(skb); - } - enum __sk_action { __SK_DROP = 0, __SK_PASS, @@@ -591,15 -583,8 +583,15 @@@ static void sock_map_free(struct bpf_ma

write_lock_bh(&sock->sk_callback_lock); psock = smap_psock_sk(sock); - smap_list_remove(psock, &stab->sock_map[i]); - smap_release_sock(psock, sock); + /* This check handles a racing sock event that can get the + * sk_callback_lock before this case but after xchg happens + * causing the refcnt to hit zero and sock user data (psock) + * to be null and queued for garbage collection. + */ + if (likely(psock)) { + smap_list_remove(psock, &stab->sock_map[i]); + smap_release_sock(psock, sock); + } write_unlock_bh(&sock->sk_callback_lock); } rcu_read_unlock(); diff --combined kernel/bpf/syscall.c index 5cb783fc8224,ebf0fb23e237..2bac0dc8baba --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@@ -905,9 -905,13 +905,13 @@@ static int bpf_prog_alloc_id(struct bpf return id > 0 ? 0 : id; }

- static void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) + void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock) { - /* cBPF to eBPF migrations are currently not in the idr store. */ + /* cBPF to eBPF migrations are currently not in the idr store. + * Offloaded programs are removed from the store when their device + * disappears - even if someone grabs an fd to them they are unusable, + * simply waiting for refcnt to drop to be freed. + */ if (!prog->aux->id) return;

@@@ -917,6 -921,7 +921,7 @@@ __acquire(&prog_idr_lock);

idr_remove(&prog_idr, prog->aux->id); + prog->aux->id = 0;

if (do_idr_lock) spin_unlock_bh(&prog_idr_lock); @@@ -937,10 -942,16 +942,16 @@@ static void __bpf_prog_put_rcu(struct r static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) { if (atomic_dec_and_test(&prog->aux->refcnt)) { + int i; + trace_bpf_prog_put_rcu(prog); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); + + for (i = 0; i < prog->aux->func_cnt; i++) + bpf_prog_kallsyms_del(prog->aux->func[i]); bpf_prog_kallsyms_del(prog); + call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu); } } @@@ -1057,7 -1068,7 +1068,7 @@@ struct bpf_prog *bpf_prog_inc_not_zero( } EXPORT_SYMBOL_GPL(bpf_prog_inc_not_zero);

-static bool bpf_prog_get_ok(struct bpf_prog *prog, +bool bpf_prog_get_ok(struct bpf_prog *prog, enum bpf_prog_type *attach_type, bool attach_drv) { /* not an attachment, just a refcount inc, always allow */ @@@ -1151,6 -1162,8 +1162,8 @@@ static int bpf_prog_load(union bpf_att if (!prog) return -ENOMEM;

+ prog->aux->offload_requested = !!attr->prog_ifindex; + err = security_bpf_prog_alloc(prog->aux); if (err) goto free_prog_nouncharge; @@@ -1172,7 -1185,7 +1185,7 @@@ atomic_set(&prog->aux->refcnt, 1); prog->gpl_compatible = is_gpl ? 1 : 0;

- if (attr->prog_ifindex) { + if (bpf_prog_is_dev_bound(prog->aux)) { err = bpf_prog_offload_init(prog, attr); if (err) goto free_prog; @@@ -1194,7 -1207,8 +1207,8 @@@ goto free_used_maps;

/* eBPF program is ready to be JITed */ - prog = bpf_prog_select_runtime(prog, &err); + if (!prog->bpf_func) + prog = bpf_prog_select_runtime(prog, &err); if (err < 0) goto free_used_maps;

@@@ -1551,6 -1565,67 +1565,67 @@@ static int bpf_map_get_fd_by_id(const u return fd; }

+ static const struct bpf_map *bpf_map_from_imm(const struct bpf_prog *prog, + unsigned long addr) + { + int i; + + for (i = 0; i < prog->aux->used_map_cnt; i++) + if (prog->aux->used_maps[i] == (void *)addr) + return prog->aux->used_maps[i]; + return NULL; + } + + static struct bpf_insn *bpf_insn_prepare_dump(const struct bpf_prog *prog) + { + const struct bpf_map *map; + struct bpf_insn *insns; + u64 imm; + int i; + + insns = kmemdup(prog->insnsi, bpf_prog_insn_size(prog), + GFP_USER); + if (!insns) + return insns; + + for (i = 0; i < prog->len; i++) { + if (insns[i].code == (BPF_JMP | BPF_TAIL_CALL)) { + insns[i].code = BPF_JMP | BPF_CALL; + insns[i].imm = BPF_FUNC_tail_call; + /* fall-through */ + } + if (insns[i].code == (BPF_JMP | BPF_CALL) || + insns[i].code == (BPF_JMP | BPF_CALL_ARGS)) { + if (insns[i].code == (BPF_JMP | BPF_CALL_ARGS)) + insns[i].code = BPF_JMP | BPF_CALL; + if (!bpf_dump_raw_ok()) + insns[i].imm = 0; + continue; + } + + if (insns[i].code != (BPF_LD | BPF_IMM | BPF_DW)) + continue; + + imm = ((u64)insns[i + 1].imm << 32) | (u32)insns[i].imm; + map = bpf_map_from_imm(prog, imm); + if (map) { + insns[i].src_reg = BPF_PSEUDO_MAP_FD; + insns[i].imm = map->id; + insns[i + 1].imm = 0; + continue; + } + + if (!bpf_dump_raw_ok() && + imm == (unsigned long)prog->aux) { + insns[i].imm = 0; + insns[i + 1].imm = 0; + continue; + } + } + + return insns; + } + static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, const union bpf_attr *attr, union bpf_attr __user *uattr) @@@ -1601,21 -1676,43 +1676,43 @@@ ulen = info.jited_prog_len; info.jited_prog_len = prog->jited_len; if (info.jited_prog_len && ulen) { - uinsns = u64_to_user_ptr(info.jited_prog_insns); - ulen = min_t(u32, info.jited_prog_len, ulen); - if (copy_to_user(uinsns, prog->bpf_func, ulen)) - return -EFAULT; + if (bpf_dump_raw_ok()) { + uinsns = u64_to_user_ptr(info.jited_prog_insns); + ulen = min_t(u32, info.jited_prog_len, ulen); + if (copy_to_user(uinsns, prog->bpf_func, ulen)) + return -EFAULT; + } else { + info.jited_prog_insns = 0; + } }

ulen = info.xlated_prog_len; info.xlated_prog_len = bpf_prog_insn_size(prog); if (info.xlated_prog_len && ulen) { + struct bpf_insn *insns_sanitized; + bool fault; + + if (prog->blinded && !bpf_dump_raw_ok()) { + info.xlated_prog_insns = 0; + goto done; + } + insns_sanitized = bpf_insn_prepare_dump(prog); + if (!insns_sanitized) + return -ENOMEM; uinsns = u64_to_user_ptr(info.xlated_prog_insns); ulen = min_t(u32, info.xlated_prog_len, ulen); - if (copy_to_user(uinsns, prog->insnsi, ulen)) + fault = copy_to_user(uinsns, insns_sanitized, ulen); + kfree(insns_sanitized); + if (fault) return -EFAULT; }

+ if (bpf_prog_is_dev_bound(prog->aux)) { + err = bpf_prog_offload_info_fill(&info, prog); + if (err) + return err; + } + done: if (copy_to_user(uinfo, &info, info_len) || put_user(info_len, &uattr->info.info_len)) diff --combined kernel/events/core.c index 56d2b99de409,878d86c513d6..0f2fe78c2fa2 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@@ -4511,11 -4511,11 +4511,11 @@@ perf_read(struct file *file, char __use return ret; }

-static unsigned int perf_poll(struct file *file, poll_table *wait) +static __poll_t perf_poll(struct file *file, poll_table *wait) { struct perf_event *event = file->private_data; struct ring_buffer *rb; - unsigned int events = POLLHUP; + __poll_t events = POLLHUP;

poll_wait(file, &event->waitq, wait);

@@@ -4723,6 -4723,9 +4723,9 @@@ static long _perf_ioctl(struct perf_eve rcu_read_unlock(); return 0; } + + case PERF_EVENT_IOC_QUERY_BPF: + return perf_event_query_prog_array(event, (void __user *)arg); default: return -ENOTTY; } @@@ -4904,7 -4907,6 +4907,7 @@@ void perf_event_update_userpage(struct unlock: rcu_read_unlock(); } +EXPORT_SYMBOL_GPL(perf_event_update_userpage);

static int perf_mmap_fault(struct vm_fault *vmf) { @@@ -8081,6 -8083,13 +8084,13 @@@ static int perf_event_set_bpf_prog(stru return -EINVAL; }

+ /* Kprobe override only works for kprobes, not uprobes. */ + if (prog->kprobe_override && + !(event->tp_event->flags & TRACE_EVENT_FL_KPROBE)) { + bpf_prog_put(prog); + return -EINVAL; + } + if (is_tracepoint || is_syscall_tp) { int off = trace_event_get_offsets(event->tp_event);

diff --combined kernel/module.c index 8042b8fcbf14,bd695bfdc5c4..83075a104710 --- a/kernel/module.c +++ b/kernel/module.c @@@ -3118,7 -3118,11 +3118,11 @@@ static int find_module_sections(struct sizeof(*mod->ftrace_callsites), &mod->num_ftrace_callsites); #endif - + #ifdef CONFIG_BPF_KPROBE_OVERRIDE + mod->kprobe_ei_funcs = section_objs(info, "_kprobe_error_inject_list", + sizeof(*mod->kprobe_ei_funcs), + &mod->num_kprobe_ei_funcs); + #endif mod->extable = section_objs(info, "__ex_table", sizeof(*mod->extable), &mod->num_exentries);

@@@ -3938,12 -3942,6 +3942,12 @@@ static const char *get_ksymbol(struct m return symname(kallsyms, best); }

+void * __weak dereference_module_function_descriptor(struct module *mod, + void *ptr) +{ + return ptr; +} + /* For kallsyms to ask for address resolution. NULL means not found. Careful * not to lock to avoid deadlock on oopses, simply disable preemption. */ const char *module_address_lookup(unsigned long addr, diff --combined net/atm/common.c index 8f12f1c6fa14,5763fd241dc3..6523f38c4957 --- a/net/atm/common.c +++ b/net/atm/common.c @@@ -14,7 -14,7 +14,7 @@@ #include <linux/capability.h> #include <linux/mm.h> #include <linux/sched/signal.h> - #include <linux/time.h> /* struct timeval */ + #include <linux/time64.h> /* 64-bit time for seconds */ #include <linux/skbuff.h> #include <linux/bitops.h> #include <linux/init.h> @@@ -648,11 -648,11 +648,11 @@@ out return error; }

-unsigned int vcc_poll(struct file *file, struct socket *sock, poll_table *wait) +__poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct atm_vcc *vcc; - unsigned int mask; + __poll_t mask;

sock_poll_wait(file, sk_sleep(sk), wait); mask = 0; diff --combined net/batman-adv/icmp_socket.c index a98e0a986cef,8041cf106c37..581375d0eed2 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@@ -1,3 -1,4 +1,4 @@@ + // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2007-2017 B.A.T.M.A.N. contributors: * * Marek Lindner @@@ -26,6 -27,7 +27,7 @@@ #include <linux/export.h> #include <linux/fcntl.h> #include <linux/fs.h> + #include <linux/gfp.h> #include <linux/if_ether.h> #include <linux/kernel.h> #include <linux/list.h> @@@ -42,11 -44,11 +44,11 @@@ #include <linux/string.h> #include <linux/uaccess.h> #include <linux/wait.h> + #include <uapi/linux/batadv_packet.h>

#include "hard-interface.h" #include "log.h" #include "originator.h" - #include "packet.h" #include "send.h"

static struct batadv_socket_client *batadv_socket_client_hash[256]; @@@ -55,6 -57,9 +57,9 @@@ static void batadv_socket_add_packet(st struct batadv_icmp_header *icmph, size_t icmp_len);

+ /** + * batadv_socket_init() - Initialize soft interface independent socket data + */ void batadv_socket_init(void) { memset(batadv_socket_client_hash, 0, sizeof(batadv_socket_client_hash)); @@@ -292,7 -297,7 +297,7 @@@ out return len; }

-static unsigned int batadv_socket_poll(struct file *file, poll_table *wait) +static __poll_t batadv_socket_poll(struct file *file, poll_table *wait) { struct batadv_socket_client *socket_client = file->private_data;

@@@ -314,6 -319,12 +319,12 @@@ static const struct file_operations bat .llseek = no_llseek, };

+ /** + * batadv_socket_setup() - Create debugfs "socket" file + * @bat_priv: the bat priv with all the soft interface information + * + * Return: 0 on success or negative error number in case of failure + */ int batadv_socket_setup(struct batadv_priv *bat_priv) { struct dentry *d; @@@ -333,7 -344,7 +344,7 @@@ err }

/** - * batadv_socket_add_packet - schedule an icmp packet to be sent to + * batadv_socket_add_packet() - schedule an icmp packet to be sent to * userspace on an icmp socket. * @socket_client: the socket this packet belongs to * @icmph: pointer to the header of the icmp packet @@@ -390,7 -401,7 +401,7 @@@ static void batadv_socket_add_packet(st }

/** - * batadv_socket_receive_packet - schedule an icmp packet to be received + * batadv_socket_receive_packet() - schedule an icmp packet to be received * locally and sent to userspace. * @icmph: pointer to the header of the icmp packet * @icmp_len: total length of the icmp packet diff --combined net/batman-adv/log.c index 76451460c98d,da004980ab8b..9be74a44e99d --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@@ -1,3 -1,4 +1,4 @@@ + // SPDX-License-Identifier: GPL-2.0 /* Copyright (C) 2010-2017 B.A.T.M.A.N. contributors: * * Marek Lindner @@@ -24,6 -25,7 +25,7 @@@ #include <linux/export.h> #include <linux/fcntl.h> #include <linux/fs.h> + #include <linux/gfp.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/module.h> @@@ -86,6 -88,13 +88,13 @@@ static int batadv_fdebug_log(struct bat return 0; }

+ /** + * batadv_debug_log() - Add debug log entry + * @bat_priv: the bat priv with all the soft interface information + * @fmt: format string + * + * Return: 0 on success or negative error number in case of failure + */ int batadv_debug_log(struct batadv_priv *bat_priv, const char *fmt, ...) { va_list args; @@@ -176,7 -185,7 +185,7 @@@ static ssize_t batadv_log_read(struct f return error; }

-static unsigned int batadv_log_poll(struct file *file, poll_table *wait) +static __poll_t batadv_log_poll(struct file *file, poll_table *wait) { struct batadv_priv *bat_priv = file->private_data; struct batadv_priv_debug_log *debug_log = bat_priv->debug_log; @@@ -197,6 -206,12 +206,12 @@@ static const struct file_operations bat .llseek = no_llseek, };

+ /** + * batadv_debug_log_setup() - Initialize debug log + * @bat_priv: the bat priv with all the soft interface information + * + * Return: 0 on success or negative error number in case of failure + */ int batadv_debug_log_setup(struct batadv_priv *bat_priv) { struct dentry *d; @@@ -222,6 -237,10 +237,10 @@@ err return -ENOMEM; }

+ /** + * batadv_debug_log_cleanup() - Destroy debug log + * @bat_priv: the bat priv with all the soft interface information + */ void batadv_debug_log_cleanup(struct batadv_priv *bat_priv) { kfree(bat_priv->debug_log); diff --combined net/bluetooth/af_bluetooth.c index 671b907ba678,f044202346c6..f897681780db --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@@ -421,7 -421,7 +421,7 @@@ out } EXPORT_SYMBOL(bt_sock_stream_recvmsg);

-static inline unsigned int bt_accept_poll(struct sock *parent) +static inline __poll_t bt_accept_poll(struct sock *parent) { struct bt_sock *s, *n; struct sock *sk; @@@ -437,11 -437,11 +437,11 @@@ return 0; }

-unsigned int bt_sock_poll(struct file *file, struct socket *sock, +__poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; - unsigned int mask = 0; + __poll_t mask = 0;

BT_DBG("sock %p, sk %p", sock, sk);

@@@ -766,43 -766,39 +766,39 @@@ static int __init bt_init(void return err;

err = sock_register(&bt_sock_family_ops); - if (err < 0) { - bt_sysfs_cleanup(); - return err; - } + if (err) + goto cleanup_sysfs;

BT_INFO("HCI device and connection manager initialized");

err = hci_sock_init(); - if (err < 0) - goto error; + if (err) + goto unregister_socket;

err = l2cap_init(); - if (err < 0) - goto sock_err; + if (err) + goto cleanup_socket;

err = sco_init(); - if (err < 0) { - l2cap_exit(); - goto sock_err; - } + if (err) + goto cleanup_cap;

err = mgmt_init(); - if (err < 0) { - sco_exit(); - l2cap_exit(); - goto sock_err; - } + if (err) + goto cleanup_sco;

return 0;

- sock_err: + cleanup_sco: + sco_exit(); + cleanup_cap: + l2cap_exit(); + cleanup_socket: hci_sock_cleanup(); - - error: + unregister_socket: sock_unregister(PF_BLUETOOTH); + cleanup_sysfs: bt_sysfs_cleanup(); - return err; }

diff --combined net/core/dev.c index 0e0ba36eeac9,d7925ef8743d..5cb782f074d7 --- a/net/core/dev.c +++ b/net/core/dev.c @@@ -1146,19 -1146,7 +1146,19 @@@ EXPORT_SYMBOL(dev_alloc_name) int dev_get_valid_name(struct net *net, struct net_device *dev, const char *name) { - return dev_alloc_name_ns(net, dev, name); + BUG_ON(!net); + + if (!dev_valid_name(name)) + return -EINVAL; + + if (strchr(name, '%')) + return dev_alloc_name_ns(net, dev, name); + else if (__dev_get_by_name(net, name)) + return -EEXIST; + else if (dev->name != name) + strlcpy(dev->name, name, IFNAMSIZ); + + return 0; } EXPORT_SYMBOL(dev_get_valid_name);

@@@ -1554,6 -1542,23 +1554,23 @@@ void dev_disable_lro(struct net_device } EXPORT_SYMBOL(dev_disable_lro);

+ /** + * dev_disable_gro_hw - disable HW Generic Receive Offload on a device + * @dev: device + * + * Disable HW Generic Receive Offload (GRO_HW) on a net device. Must be + * called under RTNL. This is needed if Generic XDP is installed on + * the device. + */ + static void dev_disable_gro_hw(struct net_device *dev) + { + dev->wanted_features &= ~NETIF_F_GRO_HW; + netdev_update_features(dev); + + if (unlikely(dev->features & NETIF_F_GRO_HW)) + netdev_WARN(dev, "failed to disable GRO_HW!\n"); + } + static int call_netdevice_notifier(struct notifier_block *nb, unsigned long val, struct net_device *dev) { @@@ -2815,7 -2820,7 +2832,7 @@@ struct sk_buff *__skb_gso_segment(struc

segs = skb_mac_gso_segment(skb, features);

- if (unlikely(skb_needs_check(skb, tx_path))) + if (unlikely(skb_needs_check(skb, tx_path) && !IS_ERR(segs))) skb_warn_bad_offload(skb);

return segs; @@@ -3054,7 -3059,7 +3071,7 @@@ int skb_csum_hwoffload_help(struct sk_b } EXPORT_SYMBOL(skb_csum_hwoffload_help);

- static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev) + static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device *dev, bool *again) { netdev_features_t features;

@@@ -3078,9 -3083,6 +3095,6 @@@ __skb_linearize(skb)) goto out_kfree_skb;

- if (validate_xmit_xfrm(skb, features)) - goto out_kfree_skb; - /* If packet is not checksummed and device does not * support checksumming for this protocol, complete * checksumming here. @@@ -3097,6 -3099,8 +3111,8 @@@ } }

+ skb = validate_xmit_xfrm(skb, features, again); + return skb;

out_kfree_skb: @@@ -3106,7 -3110,7 +3122,7 @@@ out_null return NULL; }

- struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev) + struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again) { struct sk_buff *next, *head = NULL, *tail;

@@@ -3117,7 -3121,7 +3133,7 @@@ /* in case skb wont be segmented, point to itself */ skb->prev = skb;

- skb = validate_xmit_skb(skb, dev); + skb = validate_xmit_skb(skb, dev, again); if (!skb) continue;

@@@ -3174,6 -3178,21 +3190,21 @@@ static inline int __dev_xmit_skb(struc int rc;

qdisc_calculate_pkt_len(skb, q); + + if (q->flags & TCQ_F_NOLOCK) { + if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { + __qdisc_drop(skb, &to_free); + rc = NET_XMIT_DROP; + } else { + rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + __qdisc_run(q); + } + + if (unlikely(to_free)) + kfree_skb_list(to_free); + return rc; + } + /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. @@@ -3204,9 -3223,9 +3235,9 @@@ contended = false; } __qdisc_run(q); - } else - qdisc_run_end(q); + }

+ qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; @@@ -3216,6 -3235,7 +3247,7 @@@ contended = false; } __qdisc_run(q); + qdisc_run_end(q); } } spin_unlock(root_lock); @@@ -3428,6 -3448,7 +3460,7 @@@ static int __dev_queue_xmit(struct sk_b struct netdev_queue *txq; struct Qdisc *q; int rc = -ENOMEM; + bool again = false;

skb_reset_mac_header(skb);

@@@ -3489,7 -3510,7 +3522,7 @@@ XMIT_RECURSION_LIMIT)) goto recursion_alert;

- skb = validate_xmit_skb(skb, dev); + skb = validate_xmit_skb(skb, dev, &again); if (!skb) goto out;

@@@ -3885,9 -3906,33 +3918,33 @@@ drop return NET_RX_DROP; }

+ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) + { + struct net_device *dev = skb->dev; + struct netdev_rx_queue *rxqueue; + + rxqueue = dev->_rx; + + if (skb_rx_queue_recorded(skb)) { + u16 index = skb_get_rx_queue(skb); + + if (unlikely(index >= dev->real_num_rx_queues)) { + WARN_ONCE(dev->real_num_rx_queues > 1, + "%s received packet on queue %u, but number " + "of RX queues is %u\n", + dev->name, index, dev->real_num_rx_queues); + + return rxqueue; /* Return first rxqueue */ + } + rxqueue += index; + } + return rxqueue; + } + static u32 netif_receive_generic_xdp(struct sk_buff *skb, struct bpf_prog *xdp_prog) { + struct netdev_rx_queue *rxqueue; u32 metalen, act = XDP_DROP; struct xdp_buff xdp; void *orig_data; @@@ -3931,6 -3976,9 +3988,9 @@@ xdp.data_hard_start = skb->data - skb_headroom(skb); orig_data = xdp.data;

+ rxqueue = netif_get_rxqueue(skb); + xdp.rxq = &rxqueue->xdp_rxq; + act = bpf_prog_run_xdp(xdp_prog, &xdp);

off = xdp.data - orig_data; @@@ -4155,21 -4203,26 +4215,26 @@@ static __latent_entropy void net_tx_act

while (head) { struct Qdisc *q = head; - spinlock_t *root_lock; + spinlock_t *root_lock = NULL;

head = head->next_sched;

- root_lock = qdisc_lock(q); - spin_lock(root_lock); + if (!(q->flags & TCQ_F_NOLOCK)) { + root_lock = qdisc_lock(q); + spin_lock(root_lock); + } /* We need to make sure head->next_sched is read * before clearing __QDISC_STATE_SCHED */ smp_mb__before_atomic(); clear_bit(__QDISC_STATE_SCHED, &q->state); qdisc_run(q); - spin_unlock(root_lock); + if (root_lock) + spin_unlock(root_lock); } } + + xfrm_dev_backlog(sd); }

#if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_ATM_LANE) @@@ -4557,6 -4610,7 +4622,7 @@@ static int generic_xdp_install(struct n } else if (new && !old) { static_key_slow_inc(&generic_xdp_needed); dev_disable_lro(dev); + dev_disable_gro_hw(dev); } break;

@@@ -7085,17 -7139,21 +7151,21 @@@ int dev_change_proto_down(struct net_de } EXPORT_SYMBOL(dev_change_proto_down);

- u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op, u32 *prog_id) + void __dev_xdp_query(struct net_device *dev, bpf_op_t bpf_op, + struct netdev_bpf *xdp) { - struct netdev_bpf xdp; - - memset(&xdp, 0, sizeof(xdp)); - xdp.command = XDP_QUERY_PROG; + memset(xdp, 0, sizeof(*xdp)); + xdp->command = XDP_QUERY_PROG;

/* Query must always succeed. */ - WARN_ON(bpf_op(dev, &xdp) < 0); - if (prog_id) - *prog_id = xdp.prog_id; + WARN_ON(bpf_op(dev, xdp) < 0); + } + + static u8 __dev_xdp_attached(struct net_device *dev, bpf_op_t bpf_op) + { + struct netdev_bpf xdp; + + __dev_xdp_query(dev, bpf_op, &xdp);

return xdp.prog_attached; } @@@ -7118,6 -7176,27 +7188,27 @@@ static int dev_xdp_install(struct net_d return bpf_op(dev, &xdp); }

+ static void dev_xdp_uninstall(struct net_device *dev) + { + struct netdev_bpf xdp; + bpf_op_t ndo_bpf; + + /* Remove generic XDP */ + WARN_ON(dev_xdp_install(dev, generic_xdp_install, NULL, 0, NULL)); + + /* Remove from the driver */ + ndo_bpf = dev->netdev_ops->ndo_bpf; + if (!ndo_bpf) + return; + + __dev_xdp_query(dev, ndo_bpf, &xdp); + if (xdp.prog_attached == XDP_ATTACHED_NONE) + return; + + /* Program removal should always succeed */ + WARN_ON(dev_xdp_install(dev, ndo_bpf, NULL, xdp.prog_flags, NULL)); + } + /** * dev_change_xdp_fd - set or clear a bpf program for a device rx path * @dev: device @@@ -7146,10 -7225,10 +7237,10 @@@ int dev_change_xdp_fd(struct net_devic bpf_chk = generic_xdp_install;

if (fd >= 0) { - if (bpf_chk && __dev_xdp_attached(dev, bpf_chk, NULL)) + if (bpf_chk && __dev_xdp_attached(dev, bpf_chk)) return -EEXIST; if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && - __dev_xdp_attached(dev, bpf_op, NULL)) + __dev_xdp_attached(dev, bpf_op)) return -EBUSY;

prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, @@@ -7248,6 -7327,7 +7339,7 @@@ static void rollback_registered_many(st /* Shutdown queueing discipline. */ dev_shutdown(dev);

+ dev_xdp_uninstall(dev);

/* Notify protocols, that we are about to destroy * this device. They should clean all the things. @@@ -7391,6 -7471,18 +7483,18 @@@ static netdev_features_t netdev_fix_fea features &= ~dev->gso_partial_features; }

+ if (!(features & NETIF_F_RXCSUM)) { + /* NETIF_F_GRO_HW implies doing RXCSUM since every packet + * successfully merged by hardware must also have the + * checksum verified by hardware. If the user does not + * want to enable RXCSUM, logically, we should disable GRO_HW. + */ + if (features & NETIF_F_GRO_HW) { + netdev_dbg(dev, "Dropping NETIF_F_GRO_HW since no RXCSUM feature.\n"); + features &= ~NETIF_F_GRO_HW; + } + } + return features; }

@@@ -7524,12 -7616,12 +7628,12 @@@ void netif_stacked_transfer_operstate(c } EXPORT_SYMBOL(netif_stacked_transfer_operstate);

- #ifdef CONFIG_SYSFS static int netif_alloc_rx_queues(struct net_device *dev) { unsigned int i, count = dev->num_rx_queues; struct netdev_rx_queue *rx; size_t sz = count * sizeof(*rx); + int err = 0;

BUG_ON(count < 1);

@@@ -7539,11 -7631,39 +7643,39 @@@

dev->_rx = rx;

- for (i = 0; i < count; i++) + for (i = 0; i < count; i++) { rx[i].dev = dev; + + /* XDP RX-queue setup */ + err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i); + if (err < 0) + goto err_rxq_info; + } return 0; + + err_rxq_info: + /* Rollback successful reg's and free other resources */ + while (i--) + xdp_rxq_info_unreg(&rx[i].xdp_rxq); + kfree(dev->_rx); + dev->_rx = NULL; + return err; + } + + static void netif_free_rx_queues(struct net_device *dev) + { + unsigned int i, count = dev->num_rx_queues; + struct netdev_rx_queue *rx; + + /* netif_alloc_rx_queues alloc failed, resources have been unreg'ed */ + if (!dev->_rx) + return; + + rx = dev->_rx; + + for (i = 0; i < count; i++) + xdp_rxq_info_unreg(&rx[i].xdp_rxq); } - #endif

static void netdev_init_one_queue(struct net_device *dev, struct netdev_queue *queue, void *_unused) @@@ -8104,12 -8224,10 +8236,10 @@@ struct net_device *alloc_netdev_mqs(in return NULL; }

- #ifdef CONFIG_SYSFS if (rxqs < 1) { pr_err("alloc_netdev: Unable to allocate device with zero RX queues\n"); return NULL; } - #endif

alloc_size = sizeof(struct net_device); if (sizeof_priv) { @@@ -8166,12 -8284,10 +8296,10 @@@ if (netif_alloc_netdev_queues(dev)) goto free_all;

- #ifdef CONFIG_SYSFS dev->num_rx_queues = rxqs; dev->real_num_rx_queues = rxqs; if (netif_alloc_rx_queues(dev)) goto free_all; - #endif

strcpy(dev->name, name); dev->name_assign_type = name_assign_type; @@@ -8207,13 -8323,10 +8335,10 @@@ EXPORT_SYMBOL(alloc_netdev_mqs) void free_netdev(struct net_device *dev) { struct napi_struct *p, *n; - struct bpf_prog *prog;

might_sleep(); netif_free_tx_queues(dev); - #ifdef CONFIG_SYSFS - kvfree(dev->_rx); - #endif + netif_free_rx_queues(dev);

kfree(rcu_dereference_protected(dev->ingress_queue, 1));

@@@ -8226,12 -8339,6 +8351,6 @@@ free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL;

- prog = rcu_dereference_protected(dev->xdp_prog, 1); - if (prog) { - bpf_prog_put(prog); - static_key_slow_dec(&generic_xdp_needed); - } - /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { netdev_freemem(dev); @@@ -8819,6 -8926,9 +8938,9 @@@ static int __init net_dev_init(void

skb_queue_head_init(&sd->input_pkt_queue); skb_queue_head_init(&sd->process_queue); + #ifdef CONFIG_XFRM_OFFLOAD + skb_queue_head_init(&sd->xfrm_backlog); + #endif INIT_LIST_HEAD(&sd->poll_list); sd->output_queue_tailp = &sd->output_queue; #ifdef CONFIG_RPS diff --combined net/core/ethtool.c index 8225416911ae,50a79203043b..fff6314f4c5e --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@@ -73,6 -73,7 +73,7 @@@ static const char netdev_features_strin [NETIF_F_LLTX_BIT] = "tx-lockless", [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", [NETIF_F_GRO_BIT] = "rx-gro", + [NETIF_F_GRO_HW_BIT] = "rx-gro-hw", [NETIF_F_LRO_BIT] = "rx-lro",

[NETIF_F_TSO_BIT] = "tx-tcp-segmentation", @@@ -770,6 -771,15 +771,6 @@@ static int ethtool_set_link_ksettings(s return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); }

-static void -warn_incomplete_ethtool_legacy_settings_conversion(const char *details) -{ - char name[sizeof(current->comm)]; - - pr_info_once("warning: `%s' uses legacy ethtool link settings API, %s\n", - get_task_comm(name, current), details); -} - /* Query device for its ethtool_cmd settings. * * Backward compatibility note: for compatibility with legacy ethtool, @@@ -796,8 -806,10 +797,8 @@@ static int ethtool_get_settings(struct &link_ksettings); if (err < 0) return err; - if (!convert_link_ksettings_to_legacy_settings(&cmd, - &link_ksettings)) - warn_incomplete_ethtool_legacy_settings_conversion( - "link modes are only partially reported"); + convert_link_ksettings_to_legacy_settings(&cmd, + &link_ksettings);

/* send a sensible cmd tag back to user */ cmd.cmd = ETHTOOL_GSET; diff --combined net/core/rtnetlink.c index 778d7f03404a,c688dc564b11..a0500eeda344 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@@ -62,7 -62,9 +62,9 @@@ struct rtnl_link { rtnl_doit_func doit; rtnl_dumpit_func dumpit; + struct module *owner; unsigned int flags; + struct rcu_head rcu; };

static DEFINE_MUTEX(rtnl_mutex); @@@ -127,8 -129,7 +129,7 @@@ bool lockdep_rtnl_is_held(void EXPORT_SYMBOL(lockdep_rtnl_is_held); #endif /* #ifdef CONFIG_PROVE_LOCKING */

- static struct rtnl_link __rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1]; - static refcount_t rtnl_msg_handlers_ref[RTNL_FAMILY_MAX + 1]; + static struct rtnl_link *__rcu *rtnl_msg_handlers[RTNL_FAMILY_MAX + 1];

static inline int rtm_msgindex(int msgtype) { @@@ -144,72 -145,127 +145,127 @@@ return msgindex; }

- /** - * __rtnl_register - Register a rtnetlink message type - * @protocol: Protocol family or PF_UNSPEC - * @msgtype: rtnetlink message type - * @doit: Function pointer called for each request message - * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message - * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions - * - * Registers the specified function pointers (at least one of them has - * to be non-NULL) to be called whenever a request message for the - * specified protocol family and message type is received. - * - * The special protocol family PF_UNSPEC may be used to define fallback - * function pointers for the case when no entry for the specific protocol - * family exists. - * - * Returns 0 on success or a negative error code. - */ - int __rtnl_register(int protocol, int msgtype, - rtnl_doit_func doit, rtnl_dumpit_func dumpit, - unsigned int flags) + static struct rtnl_link *rtnl_get_link(int protocol, int msgtype) + { + struct rtnl_link **tab; + + if (protocol >= ARRAY_SIZE(rtnl_msg_handlers)) + protocol = PF_UNSPEC; + + tab = rcu_dereference_rtnl(rtnl_msg_handlers[protocol]); + if (!tab) + tab = rcu_dereference_rtnl(rtnl_msg_handlers[PF_UNSPEC]); + + return tab[msgtype]; + } + + static int rtnl_register_internal(struct module *owner, + int protocol, int msgtype, + rtnl_doit_func doit, rtnl_dumpit_func dumpit, + unsigned int flags) { - struct rtnl_link *tab; + struct rtnl_link *link, *old; + struct rtnl_link __rcu **tab; int msgindex; + int ret = -ENOBUFS;

BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); msgindex = rtm_msgindex(msgtype);

- tab = rcu_dereference_raw(rtnl_msg_handlers[protocol]); + rtnl_lock(); + tab = rtnl_msg_handlers[protocol]; if (tab == NULL) { - tab = kcalloc(RTM_NR_MSGTYPES, sizeof(*tab), GFP_KERNEL); - if (tab == NULL) - return -ENOBUFS; + tab = kcalloc(RTM_NR_MSGTYPES, sizeof(void *), GFP_KERNEL); + if (!tab) + goto unlock;

+ /* ensures we see the 0 stores */ rcu_assign_pointer(rtnl_msg_handlers[protocol], tab); }

+ old = rtnl_dereference(tab[msgindex]); + if (old) { + link = kmemdup(old, sizeof(*old), GFP_KERNEL); + if (!link) + goto unlock; + } else { + link = kzalloc(sizeof(*link), GFP_KERNEL); + if (!link) + goto unlock; + } + + WARN_ON(link->owner && link->owner != owner); + link->owner = owner; + + WARN_ON(doit && link->doit && link->doit != doit); if (doit) - tab[msgindex].doit = doit; + link->doit = doit; + WARN_ON(dumpit && link->dumpit && link->dumpit != dumpit); if (dumpit) - tab[msgindex].dumpit = dumpit; - tab[msgindex].flags |= flags; + link->dumpit = dumpit;

- return 0; + link->flags |= flags; + + /* publish protocol:msgtype */ + rcu_assign_pointer(tab[msgindex], link); + ret = 0; + if (old) + kfree_rcu(old, rcu); + unlock: + rtnl_unlock(); + return ret; + } + + /** + * rtnl_register_module - Register a rtnetlink message type + * + * @owner: module registering the hook (THIS_MODULE) + * @protocol: Protocol family or PF_UNSPEC + * @msgtype: rtnetlink message type + * @doit: Function pointer called for each request message + * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message + * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions + * + * Like rtnl_register, but for use by removable modules. + */ + int rtnl_register_module(struct module *owner, + int protocol, int msgtype, + rtnl_doit_func doit, rtnl_dumpit_func dumpit, + unsigned int flags) + { + return rtnl_register_internal(owner, protocol, msgtype, + doit, dumpit, flags); } - EXPORT_SYMBOL_GPL(__rtnl_register); + EXPORT_SYMBOL_GPL(rtnl_register_module);

/** * rtnl_register - Register a rtnetlink message type + * @protocol: Protocol family or PF_UNSPEC + * @msgtype: rtnetlink message type + * @doit: Function pointer called for each request message + * @dumpit: Function pointer called for each dump request (NLM_F_DUMP) message + * @flags: rtnl_link_flags to modifiy behaviour of doit/dumpit functions * - * Identical to __rtnl_register() but panics on failure. This is useful - * as failure of this function is very unlikely, it can only happen due - * to lack of memory when allocating the chain to store all message - * handlers for a protocol. Meant for use in init functions where lack - * of memory implies no sense in continuing. + * Registers the specified function pointers (at least one of them has + * to be non-NULL) to be called whenever a request message for the + * specified protocol family and message type is received. + * + * The special protocol family PF_UNSPEC may be used to define fallback + * function pointers for the case when no entry for the specific protocol + * family exists. */ void rtnl_register(int protocol, int msgtype, rtnl_doit_func doit, rtnl_dumpit_func dumpit, unsigned int flags) { - if (__rtnl_register(protocol, msgtype, doit, dumpit, flags) < 0) - panic("Unable to register rtnetlink message handler, " - "protocol = %d, message type = %d\n", - protocol, msgtype); + int err; + + err = rtnl_register_internal(NULL, protocol, msgtype, doit, dumpit, + flags); + if (err) + pr_err("Unable to register rtnetlink message handler, " + "protocol = %d, message type = %d\n", protocol, msgtype); } - EXPORT_SYMBOL_GPL(rtnl_register);

/** * rtnl_unregister - Unregister a rtnetlink message type @@@ -220,24 -276,25 +276,25 @@@ */ int rtnl_unregister(int protocol, int msgtype) { - struct rtnl_link *handlers; + struct rtnl_link **tab, *link; int msgindex;

BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX); msgindex = rtm_msgindex(msgtype);

rtnl_lock(); - handlers = rtnl_dereference(rtnl_msg_handlers[protocol]); - if (!handlers) { + tab = rtnl_dereference(rtnl_msg_handlers[protocol]); + if (!tab) { rtnl_unlock(); return -ENOENT; }

- handlers[msgindex].doit = NULL; - handlers[msgindex].dumpit = NULL; - handlers[msgindex].flags = 0; + link = tab[msgindex]; + rcu_assign_pointer(tab[msgindex], NULL); rtnl_unlock();

+ kfree_rcu(link, rcu); + return 0; } EXPORT_SYMBOL_GPL(rtnl_unregister); @@@ -251,20 -308,27 +308,27 @@@ */ void rtnl_unregister_all(int protocol) { - struct rtnl_link *handlers; + struct rtnl_link **tab, *link; + int msgindex;

BUG_ON(protocol < 0 || protocol > RTNL_FAMILY_MAX);

rtnl_lock(); - handlers = rtnl_dereference(rtnl_msg_handlers[protocol]); + tab = rtnl_msg_handlers[protocol]; RCU_INIT_POINTER(rtnl_msg_handlers[protocol], NULL); + for (msgindex = 0; msgindex < RTM_NR_MSGTYPES; msgindex++) { + link = tab[msgindex]; + if (!link) + continue; + + rcu_assign_pointer(tab[msgindex], NULL); + kfree_rcu(link, rcu); + } rtnl_unlock();

synchronize_net();

- while (refcount_read(&rtnl_msg_handlers_ref[protocol]) > 1) - schedule(); - kfree(handlers); + kfree(tab); } EXPORT_SYMBOL_GPL(rtnl_unregister_all);

@@@ -1261,6 -1325,7 +1325,7 @@@ static u8 rtnl_xdp_attached_mode(struc { const struct net_device_ops *ops = dev->netdev_ops; const struct bpf_prog *generic_xdp_prog; + struct netdev_bpf xdp;

ASSERT_RTNL();

@@@ -1273,7 -1338,10 +1338,10 @@@ if (!ops->ndo_bpf) return XDP_ATTACHED_NONE;

- return __dev_xdp_attached(dev, ops->ndo_bpf, prog_id); + __dev_xdp_query(dev, ops->ndo_bpf, &xdp); + *prog_id = xdp.prog_id; + + return xdp.prog_attached; }

static int rtnl_xdp_fill(struct sk_buff *skb, struct net_device *dev) @@@ -1569,6 -1637,8 +1637,8 @@@ static const struct nla_policy ifla_pol [IFLA_PROMISCUITY] = { .type = NLA_U32 }, [IFLA_NUM_TX_QUEUES] = { .type = NLA_U32 }, [IFLA_NUM_RX_QUEUES] = { .type = NLA_U32 }, + [IFLA_GSO_MAX_SEGS] = { .type = NLA_U32 }, + [IFLA_GSO_MAX_SIZE] = { .type = NLA_U32 }, [IFLA_PHYS_PORT_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN }, [IFLA_CARRIER_CHANGES] = { .type = NLA_U32 }, /* ignored */ [IFLA_PHYS_SWITCH_ID] = { .type = NLA_BINARY, .len = MAX_PHYS_ITEM_ID_LEN }, @@@ -1681,18 -1751,18 +1751,18 @@@ static bool link_dump_filtered(struct n return false; }

-static struct net *get_target_net(struct sk_buff *skb, int netnsid) +static struct net *get_target_net(struct sock *sk, int netnsid) { struct net *net;

- net = get_net_ns_by_id(sock_net(skb->sk), netnsid); + net = get_net_ns_by_id(sock_net(sk), netnsid); if (!net) return ERR_PTR(-EINVAL);

/* For now, the caller is required to have CAP_NET_ADMIN in * the user namespace owning the target net ns. */ - if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + if (!sk_ns_capable(sk, net->user_ns, CAP_NET_ADMIN)) { put_net(net); return ERR_PTR(-EACCES); } @@@ -1733,7 -1803,7 +1803,7 @@@ static int rtnl_dump_ifinfo(struct sk_b ifla_policy, NULL) >= 0) { if (tb[IFLA_IF_NETNSID]) { netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); - tgt_net = get_target_net(skb, netnsid); + tgt_net = get_target_net(skb->sk, netnsid); if (IS_ERR(tgt_net)) { tgt_net = net; netnsid = -1; @@@ -2219,6 -2289,34 +2289,34 @@@ static int do_setlink(const struct sk_b } }

+ if (tb[IFLA_GSO_MAX_SIZE]) { + u32 max_size = nla_get_u32(tb[IFLA_GSO_MAX_SIZE]); + + if (max_size > GSO_MAX_SIZE) { + err = -EINVAL; + goto errout; + } + + if (dev->gso_max_size ^ max_size) { + netif_set_gso_max_size(dev, max_size); + status |= DO_SETLINK_MODIFIED; + } + } + + if (tb[IFLA_GSO_MAX_SEGS]) { + u32 max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]); + + if (max_segs > GSO_MAX_SEGS) { + err = -EINVAL; + goto errout; + } + + if (dev->gso_max_segs ^ max_segs) { + dev->gso_max_segs = max_segs; + status |= DO_SETLINK_MODIFIED; + } + } + if (tb[IFLA_OPERSTATE]) set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));

@@@ -2583,6 -2681,10 +2681,10 @@@ struct net_device *rtnl_create_link(str dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]); if (tb[IFLA_GROUP]) dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); + if (tb[IFLA_GSO_MAX_SIZE]) + netif_set_gso_max_size(dev, nla_get_u32(tb[IFLA_GSO_MAX_SIZE])); + if (tb[IFLA_GSO_MAX_SEGS]) + dev->gso_max_segs = nla_get_u32(tb[IFLA_GSO_MAX_SEGS]);

return dev; } @@@ -2883,7 -2985,7 +2985,7 @@@ static int rtnl_getlink(struct sk_buff

if (tb[IFLA_IF_NETNSID]) { netnsid = nla_get_s32(tb[IFLA_IF_NETNSID]); - tgt_net = get_target_net(skb, netnsid); + tgt_net = get_target_net(NETLINK_CB(skb).sk, netnsid); if (IS_ERR(tgt_net)) return PTR_ERR(tgt_net); } @@@ -2973,18 -3075,26 +3075,26 @@@ static int rtnl_dump_all(struct sk_buf s_idx = 1;

for (idx = 1; idx <= RTNL_FAMILY_MAX; idx++) { + struct rtnl_link **tab; int type = cb->nlh->nlmsg_type-RTM_BASE; - struct rtnl_link *handlers; + struct rtnl_link *link; rtnl_dumpit_func dumpit;

if (idx < s_idx || idx == PF_PACKET) continue;

- handlers = rtnl_dereference(rtnl_msg_handlers[idx]); - if (!handlers) + if (type < 0 || type >= RTM_NR_MSGTYPES) continue;

- dumpit = READ_ONCE(handlers[type].dumpit); + tab = rcu_dereference_rtnl(rtnl_msg_handlers[idx]); + if (!tab) + continue; + + link = tab[type]; + if (!link) + continue; + + dumpit = link->dumpit; if (!dumpit) continue;

@@@ -4314,7 -4424,8 +4424,8 @@@ static int rtnetlink_rcv_msg(struct sk_ struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); - struct rtnl_link *handlers; + struct rtnl_link *link; + struct module *owner; int err = -EOPNOTSUPP; rtnl_doit_func doit; unsigned int flags; @@@ -4338,79 -4449,85 +4449,85 @@@ if (kind != 2 && !netlink_net_capable(skb, CAP_NET_ADMIN)) return -EPERM;

- if (family >= ARRAY_SIZE(rtnl_msg_handlers)) - family = PF_UNSPEC; - rcu_read_lock(); - handlers = rcu_dereference(rtnl_msg_handlers[family]); - if (!handlers) { - family = PF_UNSPEC; - handlers = rcu_dereference(rtnl_msg_handlers[family]); - } - if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) { struct sock *rtnl; rtnl_dumpit_func dumpit; u16 min_dump_alloc = 0;

- dumpit = READ_ONCE(handlers[type].dumpit); - if (!dumpit) { + link = rtnl_get_link(family, type); + if (!link || !link->dumpit) { family = PF_UNSPEC; - handlers = rcu_dereference(rtnl_msg_handlers[PF_UNSPEC]); - if (!handlers) - goto err_unlock; - - dumpit = READ_ONCE(handlers[type].dumpit); - if (!dumpit) + link = rtnl_get_link(family, type); + if (!link || !link->dumpit) goto err_unlock; } - - refcount_inc(&rtnl_msg_handlers_ref[family]); + owner = link->owner; + dumpit = link->dumpit;

if (type == RTM_GETLINK - RTM_BASE) min_dump_alloc = rtnl_calcit(skb, nlh);

+ err = 0; + /* need to do this before rcu_read_unlock() */ + if (!try_module_get(owner)) + err = -EPROTONOSUPPORT; + rcu_read_unlock();

rtnl = net->rtnl; - { + if (err == 0) { struct netlink_dump_control c = { .dump = dumpit, .min_dump_alloc = min_dump_alloc, + .module = owner, }; err = netlink_dump_start(rtnl, skb, nlh, &c); + /* netlink_dump_start() will keep a reference on + * module if dump is still in progress. + */ + module_put(owner); } - refcount_dec(&rtnl_msg_handlers_ref[family]); return err; }

- doit = READ_ONCE(handlers[type].doit); - if (!doit) { + link = rtnl_get_link(family, type); + if (!link || !link->doit) { family = PF_UNSPEC; - handlers = rcu_dereference(rtnl_msg_handlers[family]); + link = rtnl_get_link(PF_UNSPEC, type); + if (!link || !link->doit) + goto out_unlock; }

- flags = READ_ONCE(handlers[type].flags); + owner = link->owner; + if (!try_module_get(owner)) { + err = -EPROTONOSUPPORT; + goto out_unlock; + } + + flags = link->flags; if (flags & RTNL_FLAG_DOIT_UNLOCKED) { - refcount_inc(&rtnl_msg_handlers_ref[family]); - doit = READ_ONCE(handlers[type].doit); + doit = link->doit; rcu_read_unlock(); if (doit) err = doit(skb, nlh, extack); - refcount_dec(&rtnl_msg_handlers_ref[family]); + module_put(owner); return err; } - rcu_read_unlock();

rtnl_lock(); - handlers = rtnl_dereference(rtnl_msg_handlers[family]); - if (handlers) { - doit = READ_ONCE(handlers[type].doit); - if (doit) - err = doit(skb, nlh, extack); - } + link = rtnl_get_link(family, type); + if (link && link->doit) + err = link->doit(skb, nlh, extack); rtnl_unlock(); + + module_put(owner); + + return err; + + out_unlock: + rcu_read_unlock(); return err;

err_unlock: @@@ -4498,11 -4615,6 +4615,6 @@@ static struct pernet_operations rtnetli

void __init rtnetlink_init(void) { - int i; - - for (i = 0; i < ARRAY_SIZE(rtnl_msg_handlers_ref); i++) - refcount_set(&rtnl_msg_handlers_ref[i], 1); - if (register_pernet_subsys(&rtnetlink_net_ops)) panic("rtnetlink_init: cannot initialize rtnetlink\n");

diff --combined net/core/sock.c index 1211159718ad,72d14b221784..420c380bc61d --- a/net/core/sock.c +++ b/net/core/sock.c @@@ -145,6 -145,8 +145,8 @@@ static DEFINE_MUTEX(proto_list_mutex); static LIST_HEAD(proto_list);

+ static void sock_inuse_add(struct net *net, int val); + /** * sk_ns_capable - General socket capability test * @sk: Socket to use a capability on or through @@@ -1531,8 -1533,11 +1533,11 @@@ struct sock *sk_alloc(struct net *net, sk->sk_kern_sock = kern; sock_lock_init(sk); sk->sk_net_refcnt = kern ? 0 : 1; - if (likely(sk->sk_net_refcnt)) + if (likely(sk->sk_net_refcnt)) { get_net(net); + sock_inuse_add(net, 1); + } + sock_net_set(sk, net); refcount_set(&sk->sk_wmem_alloc, 1);

@@@ -1595,6 -1600,9 +1600,9 @@@ void sk_destruct(struct sock *sk

static void __sk_free(struct sock *sk) { + if (likely(sk->sk_net_refcnt)) + sock_inuse_add(sock_net(sk), -1); + if (unlikely(sock_diag_has_destroy_listeners(sk) && sk->sk_net_refcnt)) sock_diag_broadcast_destroy(sk); else @@@ -1716,6 -1724,8 +1724,8 @@@ struct sock *sk_clone_lock(const struc newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); atomic64_set(&newsk->sk_cookie, 0); + if (likely(newsk->sk_net_refcnt)) + sock_inuse_add(sock_net(newsk), 1);

/* * Before updating sk_refcnt, we must commit prior changes to memory @@@ -2496,7 -2506,7 +2506,7 @@@ int sock_no_getname(struct socket *sock } EXPORT_SYMBOL(sock_no_getname);

-unsigned int sock_no_poll(struct file *file, struct socket *sock, poll_table *pt) +__poll_t sock_no_poll(struct file *file, struct socket *sock, poll_table *pt) { return 0; } @@@ -3045,7 -3055,7 +3055,7 @@@ static DECLARE_BITMAP(proto_inuse_idx,

void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) { - __this_cpu_add(net->core.inuse->val[prot->inuse_idx], val); + __this_cpu_add(net->core.prot_inuse->val[prot->inuse_idx], val); } EXPORT_SYMBOL_GPL(sock_prot_inuse_add);

@@@ -3055,21 -3065,50 +3065,50 @@@ int sock_prot_inuse_get(struct net *net int res = 0;

for_each_possible_cpu(cpu) - res += per_cpu_ptr(net->core.inuse, cpu)->val[idx]; + res += per_cpu_ptr(net->core.prot_inuse, cpu)->val[idx];

return res >= 0 ? res : 0; } EXPORT_SYMBOL_GPL(sock_prot_inuse_get);

+ static void sock_inuse_add(struct net *net, int val) + { + this_cpu_add(*net->core.sock_inuse, val); + } + + int sock_inuse_get(struct net *net) + { + int cpu, res = 0; + + for_each_possible_cpu(cpu) + res += *per_cpu_ptr(net->core.sock_inuse, cpu); + + return res; + } + + EXPORT_SYMBOL_GPL(sock_inuse_get); + static int __net_init sock_inuse_init_net(struct net *net) { - net->core.inuse = alloc_percpu(struct prot_inuse); - return net->core.inuse ? 0 : -ENOMEM; + net->core.prot_inuse = alloc_percpu(struct prot_inuse); + if (net->core.prot_inuse == NULL) + return -ENOMEM; + + net->core.sock_inuse = alloc_percpu(int); + if (net->core.sock_inuse == NULL) + goto out; + + return 0; + + out: + free_percpu(net->core.prot_inuse); + return -ENOMEM; }

static void __net_exit sock_inuse_exit_net(struct net *net) { - free_percpu(net->core.inuse); + free_percpu(net->core.prot_inuse); + free_percpu(net->core.sock_inuse); }

static struct pernet_operations net_inuse_ops = { @@@ -3112,6 -3151,10 +3151,10 @@@ static inline void assign_proto_idx(str static inline void release_proto_idx(struct proto *prot) { } + + static void sock_inuse_add(struct net *net, int val) + { + } #endif

static void req_prot_cleanup(struct request_sock_ops *rsk_prot) diff --combined net/dccp/proto.c index 8b8db3d481bd,fa7e92e08920..74685fecfdb9 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@@ -38,6 -38,9 +38,9 @@@ #include "dccp.h" #include "feat.h"

+ #define CREATE_TRACE_POINTS + #include "trace.h" + DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly;

EXPORT_SYMBOL_GPL(dccp_statistics); @@@ -110,7 -113,7 +113,7 @@@ void dccp_set_state(struct sock *sk, co /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ - sk->sk_state = state; + inet_sk_set_state(sk, state); }

EXPORT_SYMBOL_GPL(dccp_set_state); @@@ -318,10 -321,10 +321,10 @@@ EXPORT_SYMBOL_GPL(dccp_disconnect) * take care of normal races (between the test and the event) and we don't * go look at any of the socket buffers directly. */ -unsigned int dccp_poll(struct file *file, struct socket *sock, +__poll_t dccp_poll(struct file *file, struct socket *sock, poll_table *wait) { - unsigned int mask; + __poll_t mask; struct sock *sk = sock->sk;

sock_poll_wait(file, sk_sleep(sk), wait); @@@ -761,6 -764,8 +764,8 @@@ int dccp_sendmsg(struct sock *sk, struc int rc, size; long timeo;

+ trace_dccp_probe(sk, len); + if (len > dp->dccps_mss_cache) return -EMSGSIZE;

diff --combined net/ipv4/tcp.c index c4a7ee7f6721,f68cb33d50d1..d58285b54813 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@@ -283,8 -283,6 +283,6 @@@ #include <asm/ioctls.h> #include <net/busy_poll.h>

- #include <trace/events/tcp.h> - struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count);

@@@ -493,18 -491,16 +491,16 @@@ static void tcp_tx_timestamp(struct soc * take care of normal races (between the test and the event) and we don't * go look at any of the socket buffers directly. */ -unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) +__poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) { - unsigned int mask; + __poll_t mask; struct sock *sk = sock->sk; const struct tcp_sock *tp = tcp_sk(sk); int state;

- sock_rps_record_flow(sk); - sock_poll_wait(file, sk_sleep(sk), wait);

- state = sk_state_load(sk); + state = inet_sk_state_load(sk); if (state == TCP_LISTEN) return inet_csk_listen_poll(sk);

@@@ -1106,12 -1102,15 +1102,15 @@@ static int linear_payload_sz(bool first return 0; }

- static int select_size(const struct sock *sk, bool sg, bool first_skb) + static int select_size(const struct sock *sk, bool sg, bool first_skb, bool zc) { const struct tcp_sock *tp = tcp_sk(sk); int tmp = tp->mss_cache;

if (sg) { + if (zc) + return 0; + if (sk_can_gso(sk)) { tmp = linear_payload_sz(first_skb); } else { @@@ -1188,7 -1187,7 +1187,7 @@@ int tcp_sendmsg_locked(struct sock *sk int flags, err, copied = 0; int mss_now = 0, size_goal, copied_syn = 0; bool process_backlog = false; - bool sg; + bool sg, zc = false; long timeo;

flags = msg->msg_flags; @@@ -1206,7 -1205,8 +1205,8 @@@ goto out_err; }

- if (!(sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG)) + zc = sk_check_csum_caps(sk) && sk->sk_route_caps & NETIF_F_SG; + if (!zc) uarg->zerocopy = 0; }

@@@ -1283,6 -1283,7 +1283,7 @@@ restart

if (copy <= 0 || !tcp_skb_can_collapse_to(skb)) { bool first_skb; + int linear;

new_segment: /* Allocate new segment. If the interface is SG, @@@ -1296,9 -1297,8 +1297,8 @@@ goto restart; } first_skb = tcp_rtx_and_write_queues_empty(sk); - skb = sk_stream_alloc_skb(sk, - select_size(sk, sg, first_skb), - sk->sk_allocation, + linear = select_size(sk, sg, first_skb, zc); + skb = sk_stream_alloc_skb(sk, linear, sk->sk_allocation, first_skb); if (!skb) goto wait_for_memory; @@@ -1327,13 -1327,13 +1327,13 @@@ copy = msg_data_left(msg);

/* Where to copy to? */ - if (skb_availroom(skb) > 0) { + if (skb_availroom(skb) > 0 && !zc) { /* We have some space in skb head. Superb! */ copy = min_t(int, copy, skb_availroom(skb)); err = skb_add_data_nocache(sk, skb, &msg->msg_iter, copy); if (err) goto do_fault; - } else if (!uarg || !uarg->zerocopy) { + } else if (!zc) { bool merge = true; int i = skb_shinfo(skb)->nr_frags; struct page_frag *pfrag = sk_page_frag(sk); @@@ -1373,8 -1373,10 +1373,10 @@@ pfrag->offset += copy; } else { err = skb_zerocopy_iter_stream(sk, skb, msg, copy, uarg); - if (err == -EMSGSIZE || err == -EEXIST) + if (err == -EMSGSIZE || err == -EEXIST) { + tcp_mark_push(tp, skb); goto new_segment; + } if (err < 0) goto do_error; copy = err; @@@ -2040,8 -2042,6 +2042,6 @@@ void tcp_set_state(struct sock *sk, in { int oldstate = sk->sk_state;

- trace_tcp_set_state(sk, oldstate, state); - switch (state) { case TCP_ESTABLISHED: if (oldstate != TCP_ESTABLISHED) @@@ -2065,7 -2065,7 +2065,7 @@@ /* Change state AFTER socket is unhashed to avoid closed * socket sitting in hash tables. */ - sk_state_store(sk, state); + inet_sk_state_store(sk, state);

#ifdef STATE_TRACE SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]); @@@ -2920,7 -2920,7 +2920,7 @@@ void tcp_get_info(struct sock *sk, stru if (sk->sk_type != SOCK_STREAM) return;

- info->tcpi_state = sk_state_load(sk); + info->tcpi_state = inet_sk_state_load(sk);

/* Report meaningful fields for all TCP states, including listeners */ rate = READ_ONCE(sk->sk_pacing_rate); @@@ -3578,6 -3578,9 +3578,9 @@@ void __init tcp_init(void percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); inet_hashinfo_init(&tcp_hashinfo); + inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash", + thash_entries, 21, /* one slot per 2 MB*/ + 0, 64 * 1024); tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, diff --combined net/ipv4/udp.c index ef45adfc0edb,db72619e07e4..6eddd0602813 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@@ -357,18 -357,12 +357,12 @@@ fail } EXPORT_SYMBOL(udp_lib_get_port);

- static u32 udp4_portaddr_hash(const struct net *net, __be32 saddr, - unsigned int port) - { - return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port; - } - int udp_v4_get_port(struct sock *sk, unsigned short snum) { unsigned int hash2_nulladdr = - udp4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum); + ipv4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum); unsigned int hash2_partial = - udp4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0); + ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0);

/* precompute partial secondary hash */ udp_sk(sk)->udp_portaddr_hash = hash2_partial; @@@ -445,7 -439,7 +439,7 @@@ static struct sock *udp4_lib_lookup2(st struct sk_buff *skb) { struct sock *sk, *result; - int score, badness, matches = 0, reuseport = 0; + int score, badness; u32 hash = 0;

result = NULL; @@@ -454,23 -448,16 +448,16 @@@ score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif, exact_dif); if (score > badness) { - reuseport = sk->sk_reuseport; - if (reuseport) { + if (sk->sk_reuseport) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); if (result) return result; - matches = 1; } badness = score; result = sk; - } else if (score == badness && reuseport) { - matches++; - if (reciprocal_scale(hash, matches) == 0) - result = sk; - hash = next_pseudo_random32(hash); } } return result; @@@ -488,11 -475,11 +475,11 @@@ struct sock *__udp4_lib_lookup(struct n unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; bool exact_dif = udp_lib_exact_dif_match(net, skb); - int score, badness, matches = 0, reuseport = 0; + int score, badness; u32 hash = 0;

if (hslot->count > 10) { - hash2 = udp4_portaddr_hash(net, daddr, hnum); + hash2 = ipv4_portaddr_hash(net, daddr, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; if (hslot->count < hslot2->count) @@@ -503,7 -490,7 +490,7 @@@ exact_dif, hslot2, skb); if (!result) { unsigned int old_slot2 = slot2; - hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum); + hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum); slot2 = hash2 & udptable->mask; /* avoid searching the same slot again. */ if (unlikely(slot2 == old_slot2)) @@@ -526,23 -513,16 +513,16 @@@ begin score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif, exact_dif); if (score > badness) { - reuseport = sk->sk_reuseport; - if (reuseport) { + if (sk->sk_reuseport) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); result = reuseport_select_sock(sk, hash, skb, sizeof(struct udphdr)); if (result) return result; - matches = 1; } result = sk; badness = score; - } else if (score == badness && reuseport) { - matches++; - if (reciprocal_scale(hash, matches) == 0) - result = sk; - hash = next_pseudo_random32(hash); } } return result; @@@ -1775,7 -1755,7 +1755,7 @@@ EXPORT_SYMBOL(udp_lib_rehash)

static void udp_v4_rehash(struct sock *sk) { - u16 new_hash = udp4_portaddr_hash(sock_net(sk), + u16 new_hash = ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, inet_sk(sk)->inet_num); udp_lib_rehash(sk, new_hash); @@@ -1966,9 -1946,9 +1946,9 @@@ static int __udp4_lib_mcast_deliver(str struct sk_buff *nskb;

if (use_hash2) { - hash2_any = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & + hash2_any = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & udptable->mask; - hash2 = udp4_portaddr_hash(net, daddr, hnum) & udptable->mask; + hash2 = ipv4_portaddr_hash(net, daddr, hnum) & udptable->mask; start_lookup: hslot = &udptable->hash2[hash2]; offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); @@@ -2200,7 -2180,7 +2180,7 @@@ static struct sock *__udp4_lib_demux_lo int dif, int sdif) { unsigned short hnum = ntohs(loc_port); - unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum); + unsigned int hash2 = ipv4_portaddr_hash(net, loc_addr, hnum); unsigned int slot2 = hash2 & udp_table.mask; struct udp_hslot *hslot2 = &udp_table.hash2[slot2]; INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr); @@@ -2502,16 -2482,14 +2482,14 @@@ int compat_udp_getsockopt(struct sock * * but then block when reading it. Add special case code * to work around these arguably broken applications. */ -unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) +__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) { - unsigned int mask = datagram_poll(file, sock, wait); + __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk;

if (!skb_queue_empty(&udp_sk(sk)->reader_queue)) mask |= POLLIN | POLLRDNORM;

- sock_rps_record_flow(sk); - /* Check for false positives due to checksum errors */ if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) && !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) diff --combined net/ipv6/ip6_fib.c index d11a5578e4f8,edda5ad3b405..b5f19703fca6 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@@ -107,16 -107,13 +107,13 @@@ enum

void fib6_update_sernum(struct rt6_info *rt) { - struct fib6_table *table = rt->rt6i_table; struct net *net = dev_net(rt->dst.dev); struct fib6_node *fn;

- spin_lock_bh(&table->tb6_lock); fn = rcu_dereference_protected(rt->rt6i_node, - lockdep_is_held(&table->tb6_lock)); + lockdep_is_held(&rt->rt6i_table->tb6_lock)); if (fn) fn->fn_sernum = fib6_new_sernum(net); - spin_unlock_bh(&table->tb6_lock); }

/* @@@ -893,7 -890,7 +890,7 @@@ static int fib6_add_rt2node(struct fib6 ins = &fn->leaf;

for (iter = leaf; iter; - iter = rcu_dereference_protected(iter->dst.rt6_next, + iter = rcu_dereference_protected(iter->rt6_next, lockdep_is_held(&rt->rt6i_table->tb6_lock))) { /* * Search for duplicates @@@ -950,7 -947,7 +947,7 @@@ break;

next_iter: - ins = &iter->dst.rt6_next; + ins = &iter->rt6_next; }

if (fallback_ins && !found) { @@@ -979,7 -976,7 +976,7 @@@ &sibling->rt6i_siblings); break; } - sibling = rcu_dereference_protected(sibling->dst.rt6_next, + sibling = rcu_dereference_protected(sibling->rt6_next, lockdep_is_held(&rt->rt6i_table->tb6_lock)); } /* For each sibling in the list, increment the counter of @@@ -1009,7 -1006,7 +1006,7 @@@ add if (err) return err;

- rcu_assign_pointer(rt->dst.rt6_next, iter); + rcu_assign_pointer(rt->rt6_next, iter); atomic_inc(&rt->rt6i_ref); rcu_assign_pointer(rt->rt6i_node, fn); rcu_assign_pointer(*ins, rt); @@@ -1040,7 -1037,7 +1037,7 @@@

atomic_inc(&rt->rt6i_ref); rcu_assign_pointer(rt->rt6i_node, fn); - rt->dst.rt6_next = iter->dst.rt6_next; + rt->rt6_next = iter->rt6_next; rcu_assign_pointer(*ins, rt); call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt, extack); @@@ -1059,14 -1056,14 +1056,14 @@@

if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ - ins = &rt->dst.rt6_next; + ins = &rt->rt6_next; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->rt6i_table->tb6_lock)); while (iter) { if (iter->rt6i_metric > rt->rt6i_metric) break; if (rt6_qualify_for_ecmp(iter)) { - *ins = iter->dst.rt6_next; + *ins = iter->rt6_next; iter->rt6i_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); if (rcu_access_pointer(fn->rr_ptr) == iter) @@@ -1075,7 -1072,7 +1072,7 @@@ nsiblings--; info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } else { - ins = &iter->dst.rt6_next; + ins = &iter->rt6_next; } iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->rt6i_table->tb6_lock)); @@@ -1102,8 -1099,8 +1099,8 @@@ void fib6_force_start_gc(struct net *ne jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); }

- static void fib6_update_sernum_upto_root(struct rt6_info *rt, - int sernum) + static void __fib6_update_sernum_upto_root(struct rt6_info *rt, + int sernum) { struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, lockdep_is_held(&rt->rt6i_table->tb6_lock)); @@@ -1117,6 -1114,11 +1114,11 @@@ } }

+ void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt) + { + __fib6_update_sernum_upto_root(rt, fib6_new_sernum(net)); + } + /* * Add routing information to the routing tree. * <destination addr>/<source addr> @@@ -1230,7 -1232,7 +1232,7 @@@ int fib6_add(struct fib6_node *root, st

err = fib6_add_rt2node(fn, rt, info, mxc, extack); if (!err) { - fib6_update_sernum_upto_root(rt, sernum); + __fib6_update_sernum_upto_root(rt, sernum); fib6_start_gc(info->nl_net, rt); }

@@@ -1241,28 -1243,23 +1243,28 @@@ out * If fib6_add_1 has cleared the old leaf pointer in the * super-tree leaf node we have to find a new one for it. */ - struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf, - lockdep_is_held(&table->tb6_lock)); - if (pn != fn && pn_leaf == rt) { - pn_leaf = NULL; - RCU_INIT_POINTER(pn->leaf, NULL); - atomic_dec(&rt->rt6i_ref); - } - if (pn != fn && !pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { - pn_leaf = fib6_find_prefix(info->nl_net, table, pn); -#if RT6_DEBUG >= 2 - if (!pn_leaf) { - WARN_ON(!pn_leaf); - pn_leaf = info->nl_net->ipv6.ip6_null_entry; + if (pn != fn) { + struct rt6_info *pn_leaf = + rcu_dereference_protected(pn->leaf, + lockdep_is_held(&table->tb6_lock)); + if (pn_leaf == rt) { + pn_leaf = NULL; + RCU_INIT_POINTER(pn->leaf, NULL); + atomic_dec(&rt->rt6i_ref); } + if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { + pn_leaf = fib6_find_prefix(info->nl_net, table, + pn); +#if RT6_DEBUG >= 2 + if (!pn_leaf) { + WARN_ON(!pn_leaf); + pn_leaf = + info->nl_net->ipv6.ip6_null_entry; + } #endif - atomic_inc(&pn_leaf->rt6i_ref); - rcu_assign_pointer(pn->leaf, pn_leaf); + atomic_inc(&pn_leaf->rt6i_ref); + rcu_assign_pointer(pn->leaf, pn_leaf); + } } #endif goto failure; @@@ -1649,7 -1646,7 +1651,7 @@@ static void fib6_del_route(struct fib6_ WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE);

/* Unlink it */ - *rtp = rt->dst.rt6_next; + *rtp = rt->rt6_next; rt->rt6i_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; @@@ -1677,7 -1674,7 +1679,7 @@@ FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); - w->leaf = rcu_dereference_protected(rt->dst.rt6_next, + w->leaf = rcu_dereference_protected(rt->rt6_next, lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; @@@ -1736,7 -1733,7 +1738,7 @@@ int fib6_del(struct rt6_info *rt, struc fib6_del_route(table, fn, rtp, info); return 0; } - rtp_next = &cur->dst.rt6_next; + rtp_next = &cur->rt6_next; } return -ENOENT; } @@@ -1892,7 -1889,7 +1894,7 @@@ static int fib6_clean_node(struct fib6_

for_each_fib6_walker_rt(w) { res = c->func(rt, c->arg); - if (res < 0) { + if (res == -1) { w->leaf = rt; res = fib6_del(rt, &info); if (res) { @@@ -1905,6 -1902,12 +1907,12 @@@ continue; } return 0; + } else if (res == -2) { + if (WARN_ON(!rt->rt6i_nsiblings)) + continue; + rt = list_last_entry(&rt->rt6i_siblings, + struct rt6_info, rt6i_siblings); + continue; } WARN_ON(res != 0); } @@@ -1916,7 -1919,8 +1924,8 @@@ * Convenient frontend to tree walker. * * func is called on each route. - * It may return -1 -> delete this route. + * It may return -2 -> skip multipath route. + * -1 -> delete this route. * 0 -> continue walking */

@@@ -2108,7 -2112,6 +2117,6 @@@ static void fib6_net_exit(struct net *n { unsigned int i;

- rt6_ifdown(net, NULL); del_timer_sync(&net->ipv6.ip6_fib_timer);

for (i = 0; i < FIB6_TABLE_HASHSZ; i++) { @@@ -2147,8 -2150,8 +2155,8 @@@ int __init fib6_init(void if (ret) goto out_kmem_cache_create;

- ret = __rtnl_register(PF_INET6, RTM_GETROUTE, NULL, inet6_dump_fib, - 0); + ret = rtnl_register_module(THIS_MODULE, PF_INET6, RTM_GETROUTE, NULL, + inet6_dump_fib, 0); if (ret) goto out_unregister_subsys;

@@@ -2213,7 -2216,7 +2221,7 @@@ static int ipv6_route_yield(struct fib6

do { iter->w.leaf = rcu_dereference_protected( - iter->w.leaf->dst.rt6_next, + iter->w.leaf->rt6_next, lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) @@@ -2279,7 -2282,7 +2287,7 @@@ static void *ipv6_route_seq_next(struc if (!v) goto iter_table;

- n = rcu_dereference_bh(((struct rt6_info *)v)->dst.rt6_next); + n = rcu_dereference_bh(((struct rt6_info *)v)->rt6_next); if (n) { ++*pos; return n; diff --combined net/ipv6/ip6_tunnel.c index 9a7cf355bc8c,8a4610e84e58..8071f42cd8a0 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@@ -861,7 -861,7 +861,7 @@@ int ip6_tnl_rcv(struct ip6_tnl *t, stru struct metadata_dst *tun_dst, bool log_ecn_err) { - return __ip6_tnl_rcv(t, skb, tpi, NULL, ip6ip6_dscp_ecn_decapsulate, + return __ip6_tnl_rcv(t, skb, tpi, tun_dst, ip6ip6_dscp_ecn_decapsulate, log_ecn_err); } EXPORT_SYMBOL(ip6_tnl_rcv); @@@ -979,6 -979,9 +979,9 @@@ int ip6_tnl_xmit_ctl(struct ip6_tnl *t int ret = 0; struct net *net = t->net;

+ if (t->parms.collect_md) + return 1; + if ((p->flags & IP6_TNL_F_CAP_XMIT) || ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_XMIT))) { @@@ -1074,11 -1077,10 +1077,11 @@@ int ip6_tnl_xmit(struct sk_buff *skb, s memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); } - } else if (!(t->parms.flags & - (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { - /* enable the cache only only if the routing decision does - * not depend on the current inner header value + } else if (t->parms.proto != 0 && !(t->parms.flags & + (IP6_TNL_F_USE_ORIG_TCLASS | + IP6_TNL_F_USE_ORIG_FWMARK))) { + /* enable the cache only if neither the outer protocol nor the + * routing decision depends on the current inner header value */ use_cache = true; } @@@ -1677,11 -1679,11 +1680,11 @@@ int ip6_tnl_change_mtu(struct net_devic { struct ip6_tnl *tnl = netdev_priv(dev);

- if (tnl->parms.proto == IPPROTO_IPIP) { - if (new_mtu < ETH_MIN_MTU) + if (tnl->parms.proto == IPPROTO_IPV6) { + if (new_mtu < IPV6_MIN_MTU) return -EINVAL; } else { - if (new_mtu < IPV6_MIN_MTU) + if (new_mtu < ETH_MIN_MTU) return -EINVAL; } if (new_mtu > 0xFFF8 - dev->hard_header_len) diff --combined net/mac80211/rx.c index 4daafb07602f,b3cff69bfd66..fd580614085b --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@@ -1607,23 -1607,16 +1607,16 @@@ ieee80211_rx_h_sta_process(struct ieee8

/* * Change STA power saving mode only at the end of a frame - * exchange sequence. + * exchange sequence, and only for a data or management + * frame as specified in IEEE 802.11-2016 11.2.3.2 */ if (!ieee80211_hw_check(&sta->local->hw, AP_LINK_PS) && !ieee80211_has_morefrags(hdr->frame_control) && - !ieee80211_is_back_req(hdr->frame_control) && + (ieee80211_is_mgmt(hdr->frame_control) || + ieee80211_is_data(hdr->frame_control)) && !(status->rx_flags & IEEE80211_RX_DEFERRED_RELEASE) && (rx->sdata->vif.type == NL80211_IFTYPE_AP || - rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN) && - /* - * PM bit is only checked in frames where it isn't reserved, - * in AP mode it's reserved in non-bufferable management frames - * (cf. IEEE 802.11-2012 8.2.4.1.7 Power Management field) - * BAR frames should be ignored as specified in - * IEEE 802.11-2012 10.2.1.2. - */ - (!ieee80211_is_mgmt(hdr->frame_control) || - ieee80211_is_bufferable_mmpdu(hdr->frame_control))) { + rx->sdata->vif.type == NL80211_IFTYPE_AP_VLAN)) { if (test_sta_flag(sta, WLAN_STA_PS_STA)) { if (!ieee80211_has_pm(hdr->frame_control)) sta_ps_end(sta); @@@ -3632,8 -3625,6 +3625,8 @@@ static bool ieee80211_accept_frame(stru } return true; case NL80211_IFTYPE_MESH_POINT: + if (ether_addr_equal(sdata->vif.addr, hdr->addr2)) + return false; if (multicast) return true; return ether_addr_equal(sdata->vif.addr, hdr->addr1); diff --combined net/packet/af_packet.c index 3b4d6a3cf190,ee7aa0ba3a67..2a80f19f0913 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@@ -247,12 -247,13 +247,13 @@@ static int packet_direct_xmit(struct sk struct sk_buff *orig_skb = skb; struct netdev_queue *txq; int ret = NETDEV_TX_BUSY; + bool again = false;

if (unlikely(!netif_running(dev) || !netif_carrier_ok(dev))) goto drop;

- skb = validate_xmit_skb_list(skb, dev); + skb = validate_xmit_skb_list(skb, dev, &again); if (skb != orig_skb) goto drop;

@@@ -4073,12 -4074,12 +4074,12 @@@ static int packet_ioctl(struct socket * return 0; }

-static unsigned int packet_poll(struct file *file, struct socket *sock, +static __poll_t packet_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct packet_sock *po = pkt_sk(sk); - unsigned int mask = datagram_poll(file, sock, wait); + __poll_t mask = datagram_poll(file, sock, wait);

spin_lock_bh(&sk->sk_receive_queue.lock); if (po->rx_ring.pg_vec) { diff --combined net/sched/act_gact.c index a0ac42b3ed06,9d632e92cad0..b56986d41c87 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@@ -159,7 -159,7 +159,7 @@@ static void tcf_gact_stats_update(struc if (action == TC_ACT_SHOT) this_cpu_ptr(gact->common.cpu_qstats)->drops += packets;

- tm->lastuse = lastuse; + tm->lastuse = max_t(u64, tm->lastuse, lastuse); }

static int tcf_gact_dump(struct sk_buff *skb, struct tc_action *a, @@@ -235,16 -235,14 +235,14 @@@ static __net_init int gact_init_net(str return tc_action_net_init(tn, &act_gact_ops); }

- static void __net_exit gact_exit_net(struct net *net) + static void __net_exit gact_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, gact_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, gact_net_id); }

static struct pernet_operations gact_net_ops = { .init = gact_init_net, - .exit = gact_exit_net, + .exit_batch = gact_exit_net, .id = &gact_net_id, .size = sizeof(struct tc_action_net), }; diff --combined net/sched/act_mirred.c index 08b61849c2a2,37e5e4decbd6..e6ff88f72900 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@@ -29,7 -29,6 +29,6 @@@ #include <net/tc_act/tc_mirred.h>

static LIST_HEAD(mirred_list); - static DEFINE_SPINLOCK(mirred_list_lock);

static bool tcf_mirred_is_act_redirect(int action) { @@@ -50,18 -49,15 +49,15 @@@ static bool tcf_mirred_act_wants_ingres } }

- static void tcf_mirred_release(struct tc_action *a, int bind) + static void tcf_mirred_release(struct tc_action *a) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev;

- /* We could be called either in a RCU callback or with RTNL lock held. */ - spin_lock_bh(&mirred_list_lock); list_del(&m->tcfm_list); - dev = rcu_dereference_protected(m->tcfm_dev, 1); + dev = rtnl_dereference(m->tcfm_dev); if (dev) dev_put(dev); - spin_unlock_bh(&mirred_list_lock); }

static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { @@@ -139,8 -135,6 +135,6 @@@ static int tcf_mirred_init(struct net * m->tcf_action = parm->action; m->tcfm_eaction = parm->eaction; if (dev != NULL) { - m->tcfm_ifindex = parm->ifindex; - m->net = net; if (ret != ACT_P_CREATED) dev_put(rcu_dereference_protected(m->tcfm_dev, 1)); dev_hold(dev); @@@ -149,9 -143,7 +143,7 @@@ }

if (ret == ACT_P_CREATED) { - spin_lock_bh(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); - spin_unlock_bh(&mirred_list_lock); tcf_idr_insert(tn, *a); }

@@@ -239,7 -231,7 +231,7 @@@ static void tcf_stats_update(struct tc_ struct tcf_t *tm = &m->tcf_tm;

_bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); - tm->lastuse = lastuse; + tm->lastuse = max_t(u64, tm->lastuse, lastuse); }

static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, @@@ -247,13 -239,14 +239,14 @@@ { unsigned char *b = skb_tail_pointer(skb); struct tcf_mirred *m = to_mirred(a); + struct net_device *dev = rtnl_dereference(m->tcfm_dev); struct tc_mirred opt = { .index = m->tcf_index, .action = m->tcf_action, .refcnt = m->tcf_refcnt - ref, .bindcnt = m->tcf_bindcnt - bind, .eaction = m->tcfm_eaction, - .ifindex = m->tcfm_ifindex, + .ifindex = dev ? dev->ifindex : 0, }; struct tcf_t t;

@@@ -294,7 -287,6 +287,6 @@@ static int mirred_device_event(struct n

ASSERT_RTNL(); if (event == NETDEV_UNREGISTER) { - spin_lock_bh(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { if (rcu_access_pointer(m->tcfm_dev) == dev) { dev_put(dev); @@@ -304,7 -296,6 +296,6 @@@ RCU_INIT_POINTER(m->tcfm_dev, NULL); } } - spin_unlock_bh(&mirred_list_lock); }

return NOTIFY_DONE; @@@ -318,7 -309,7 +309,7 @@@ static struct net_device *tcf_mirred_ge { struct tcf_mirred *m = to_mirred(a);

- return __dev_get_by_index(m->net, m->tcfm_ifindex); + return rtnl_dereference(m->tcfm_dev); }

static struct tc_action_ops act_mirred_ops = { @@@ -343,16 -334,14 +334,14 @@@ static __net_init int mirred_init_net(s return tc_action_net_init(tn, &act_mirred_ops); }

- static void __net_exit mirred_exit_net(struct net *net) + static void __net_exit mirred_exit_net(struct list_head *net_list) { - struct tc_action_net *tn = net_generic(net, mirred_net_id); - - tc_action_net_exit(tn); + tc_action_net_exit(net_list, mirred_net_id); }

static struct pernet_operations mirred_net_ops = { .init = mirred_init_net, - .exit = mirred_exit_net, + .exit_batch = mirred_exit_net, .id = &mirred_net_id, .size = sizeof(struct tc_action_net), }; diff --combined net/sctp/socket.c index 8f7536de5f41,a5e2150ab013..eb68ae261054 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@@ -201,6 -201,22 +201,22 @@@ static void sctp_for_each_tx_datachunk( cb(chunk); }

+ static void sctp_for_each_rx_skb(struct sctp_association *asoc, struct sock *sk, + void (*cb)(struct sk_buff *, struct sock *)) + + { + struct sk_buff *skb, *tmp; + + sctp_skb_for_each(skb, &asoc->ulpq.lobby, tmp) + cb(skb, sk); + + sctp_skb_for_each(skb, &asoc->ulpq.reasm, tmp) + cb(skb, sk); + + sctp_skb_for_each(skb, &asoc->ulpq.reasm_uo, tmp) + cb(skb, sk); + } + /* Verify that this is a valid address. */ static inline int sctp_verify_addr(struct sock *sk, union sctp_addr *addr, int len) @@@ -1528,7 -1544,7 +1544,7 @@@ static void sctp_close(struct sock *sk

lock_sock_nested(sk, SINGLE_DEPTH_NESTING); sk->sk_shutdown = SHUTDOWN_MASK; - sk->sk_state = SCTP_SS_CLOSING; + inet_sk_set_state(sk, SCTP_SS_CLOSING);

ep = sctp_sk(sk)->ep;

@@@ -1554,6 -1570,7 +1570,7 @@@

if (data_was_unread || !skb_queue_empty(&asoc->ulpq.lobby) || !skb_queue_empty(&asoc->ulpq.reasm) || + !skb_queue_empty(&asoc->ulpq.reasm_uo) || (sock_flag(sk, SOCK_LINGER) && !sk->sk_lingertime)) { struct sctp_chunk *chunk;

@@@ -2002,7 -2019,20 +2019,20 @@@ static int sctp_sendmsg(struct sock *sk if (err < 0) goto out_free;

- wait_connect = true; + /* If stream interleave is enabled, wait_connect has to be + * done earlier than data enqueue, as it needs to make data + * or idata according to asoc->intl_enable which is set + * after connection is done. + */ + if (sctp_sk(asoc->base.sk)->strm_interleave) { + timeo = sock_sndtimeo(sk, 0); + err = sctp_wait_for_connect(asoc, &timeo); + if (err) + goto out_unlock; + } else { + wait_connect = true; + } + pr_debug("%s: we associated primitively\n", __func__); }

@@@ -2281,7 -2311,7 +2311,7 @@@ static int sctp_setsockopt_events(struc if (!event) return -ENOMEM;

- sctp_ulpq_tail_event(&asoc->ulpq, event); + asoc->stream.si->enqueue_event(&asoc->ulpq, event); } }

@@@ -3180,7 -3210,7 +3210,7 @@@ static int sctp_setsockopt_maxseg(struc if (val == 0) { val = asoc->pathmtu - sp->pf->af->net_header_len; val -= sizeof(struct sctphdr) + - sizeof(struct sctp_data_chunk); + sctp_datachk_len(&asoc->stream); } asoc->user_frag = val; asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu); @@@ -3350,7 -3380,10 +3380,10 @@@ static int sctp_setsockopt_fragment_int if (get_user(val, (int __user *)optval)) return -EFAULT;

- sctp_sk(sk)->frag_interleave = (val == 0) ? 0 : 1; + sctp_sk(sk)->frag_interleave = !!val; + + if (!sctp_sk(sk)->frag_interleave) + sctp_sk(sk)->strm_interleave = 0;

return 0; } @@@ -4023,6 -4056,40 +4056,40 @@@ out return retval; }

+ static int sctp_setsockopt_interleaving_supported(struct sock *sk, + char __user *optval, + unsigned int optlen) + { + struct sctp_sock *sp = sctp_sk(sk); + struct net *net = sock_net(sk); + struct sctp_assoc_value params; + int retval = -EINVAL; + + if (optlen < sizeof(params)) + goto out; + + optlen = sizeof(params); + if (copy_from_user(&params, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + if (params.assoc_id) + goto out; + + if (!net->sctp.intl_enable || !sp->frag_interleave) { + retval = -EPERM; + goto out; + } + + sp->strm_interleave = !!params.assoc_value; + + retval = 0; + + out: + return retval; + } + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@@ -4210,6 -4277,10 +4277,10 @@@ static int sctp_setsockopt(struct sock case SCTP_STREAM_SCHEDULER_VALUE: retval = sctp_setsockopt_scheduler_value(sk, optval, optlen); break; + case SCTP_INTERLEAVING_SUPPORTED: + retval = sctp_setsockopt_interleaving_supported(sk, optval, + optlen); + break; default: retval = -ENOPROTOOPT; break; @@@ -4586,7 -4657,7 +4657,7 @@@ static void sctp_shutdown(struct sock * if (how & SEND_SHUTDOWN && !list_empty(&ep->asocs)) { struct sctp_association *asoc;

- sk->sk_state = SCTP_SS_CLOSING; + inet_sk_set_state(sk, SCTP_SS_CLOSING); asoc = list_entry(ep->asocs.next, struct sctp_association, asocs); sctp_primitive_SHUTDOWN(net, asoc, NULL); @@@ -4680,20 -4751,11 +4751,11 @@@ int sctp_get_sctp_info(struct sock *sk EXPORT_SYMBOL_GPL(sctp_get_sctp_info);

/* use callback to avoid exporting the core structure */ - int sctp_transport_walk_start(struct rhashtable_iter *iter) + void sctp_transport_walk_start(struct rhashtable_iter *iter) { - int err; - rhltable_walk_enter(&sctp_transport_hashtable, iter);

- err = rhashtable_walk_start(iter); - if (err && err != -EAGAIN) { - rhashtable_walk_stop(iter); - rhashtable_walk_exit(iter); - return err; - } - - return 0; + rhashtable_walk_start(iter); }

void sctp_transport_walk_stop(struct rhashtable_iter *iter) @@@ -4784,12 -4846,10 +4846,10 @@@ int sctp_for_each_transport(int (*cb)(s struct net *net, int *pos, void *p) { struct rhashtable_iter hti; struct sctp_transport *tsp; - int ret; + int ret = 0;

again: - ret = sctp_transport_walk_start(&hti); - if (ret) - return ret; + sctp_transport_walk_start(&hti);

tsp = sctp_transport_get_idx(net, &hti, *pos + 1); for (; !IS_ERR_OR_NULL(tsp); tsp = sctp_transport_get_next(net, &hti)) { @@@ -6984,6 -7044,47 +7044,47 @@@ out return retval; }

+ static int sctp_getsockopt_interleaving_supported(struct sock *sk, int len, + char __user *optval, + int __user *optlen) + { + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(&params, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (asoc) { + params.assoc_value = asoc->intl_enable; + } else if (!params.assoc_id) { + struct sctp_sock *sp = sctp_sk(sk); + + params.assoc_value = sp->strm_interleave; + } else { + retval = -EINVAL; + goto out; + } + + if (put_user(len, optlen)) + goto out; + + if (copy_to_user(optval, &params, len)) + goto out; + + retval = 0; + + out: + return retval; + } + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@@ -7174,6 -7275,10 +7275,10 @@@ retval = sctp_getsockopt_scheduler_value(sk, len, optval, optlen); break; + case SCTP_INTERLEAVING_SUPPORTED: + retval = sctp_getsockopt_interleaving_supported(sk, len, optval, + optlen); + break; default: retval = -ENOPROTOOPT; break; @@@ -7408,13 -7513,13 +7513,13 @@@ static int sctp_listen_start(struct soc * sockets. * */ - sk->sk_state = SCTP_SS_LISTENING; + inet_sk_set_state(sk, SCTP_SS_LISTENING); if (!ep->base.bind_addr.port) { if (sctp_autobind(sk)) return -EAGAIN; } else { if (sctp_get_port(sk, inet_sk(sk)->inet_num)) { - sk->sk_state = SCTP_SS_CLOSED; + inet_sk_set_state(sk, SCTP_SS_CLOSED); return -EADDRINUSE; } } @@@ -7500,11 -7605,11 +7605,11 @@@ out * here, again, by modeling the current TCP/UDP code. We don't have * a good way to test with it yet. */ -unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait) +__poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct sctp_sock *sp = sctp_sk(sk); - unsigned int mask; + __poll_t mask;

poll_wait(file, sk_sleep(sk), wait);

@@@ -8411,11 -8516,7 +8516,7 @@@ static void sctp_sock_migrate(struct so

}

- sctp_skb_for_each(skb, &assoc->ulpq.reasm, tmp) - sctp_skb_set_owner_r_frag(skb, newsk); - - sctp_skb_for_each(skb, &assoc->ulpq.lobby, tmp) - sctp_skb_set_owner_r_frag(skb, newsk); + sctp_for_each_rx_skb(assoc, newsk, sctp_skb_set_owner_r_frag);

/* Set the type of socket to indicate that it is peeled off from the * original UDP-style socket or created with the accept() call on a @@@ -8441,10 -8542,10 +8542,10 @@@ * is called, set RCV_SHUTDOWN flag. */ if (sctp_state(assoc, CLOSED) && sctp_style(newsk, TCP)) { - newsk->sk_state = SCTP_SS_CLOSED; + inet_sk_set_state(newsk, SCTP_SS_CLOSED); newsk->sk_shutdown |= RCV_SHUTDOWN; } else { - newsk->sk_state = SCTP_SS_ESTABLISHED; + inet_sk_set_state(newsk, SCTP_SS_ESTABLISHED); }

release_sock(newsk); diff --combined net/sctp/stream.c index 524dfeb94c41,06b644dd858c..cedf672487f9 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@@ -156,9 -156,9 +156,9 @@@ int sctp_stream_init(struct sctp_strea sctp_stream_outq_migrate(stream, NULL, outcnt); sched->sched_all(stream);

- i = sctp_stream_alloc_out(stream, outcnt, gfp); - if (i) - return i; + ret = sctp_stream_alloc_out(stream, outcnt, gfp); + if (ret) + goto out;

stream->outcnt = outcnt; for (i = 0; i < stream->outcnt; i++) @@@ -167,20 -167,23 +167,21 @@@ sched->init(stream);

in: + sctp_stream_interleave_init(stream); if (!incnt) goto out;

- i = sctp_stream_alloc_in(stream, incnt, gfp); - if (i) { - ret = -ENOMEM; - goto free; + ret = sctp_stream_alloc_in(stream, incnt, gfp); + if (ret) { + sched->free(stream); + kfree(stream->out); + stream->out = NULL; + stream->outcnt = 0; + goto out; }

stream->incnt = incnt; - goto out;

-free: - sched->free(stream); - kfree(stream->out); - stream->out = NULL; out: return ret; } @@@ -213,11 -216,13 +214,13 @@@ void sctp_stream_clear(struct sctp_stre { int i;

- for (i = 0; i < stream->outcnt; i++) - stream->out[i].ssn = 0; + for (i = 0; i < stream->outcnt; i++) { + stream->out[i].mid = 0; + stream->out[i].mid_uo = 0; + }

for (i = 0; i < stream->incnt; i++) - stream->in[i].ssn = 0; + stream->in[i].mid = 0; }

void sctp_stream_update(struct sctp_stream *stream, struct sctp_stream *new) @@@ -604,10 -609,10 +607,10 @@@ struct sctp_chunk *sctp_process_strrese }

for (i = 0; i < nums; i++) - stream->in[ntohs(str_p[i])].ssn = 0; + stream->in[ntohs(str_p[i])].mid = 0; } else { for (i = 0; i < stream->incnt; i++) - stream->in[i].ssn = 0; + stream->in[i].mid = 0; }

result = SCTP_STRRESET_PERFORMED; @@@ -751,8 -756,7 +754,7 @@@ struct sctp_chunk *sctp_process_strrese * performed. */ max_tsn_seen = sctp_tsnmap_get_max_tsn_seen(&asoc->peer.tsn_map); - sctp_ulpq_reasm_flushtsn(&asoc->ulpq, max_tsn_seen); - sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC); + asoc->stream.si->report_ftsn(&asoc->ulpq, max_tsn_seen);

/* G1: Compute an appropriate value for the Receiver's Next TSN -- the * TSN that the peer should use to send the next DATA chunk. The @@@ -781,10 -785,12 +783,12 @@@ /* G5: The next expected and outgoing SSNs MUST be reset to 0 for all * incoming and outgoing streams. */ - for (i = 0; i < stream->outcnt; i++) - stream->out[i].ssn = 0; + for (i = 0; i < stream->outcnt; i++) { + stream->out[i].mid = 0; + stream->out[i].mid_uo = 0; + } for (i = 0; i < stream->incnt; i++) - stream->in[i].ssn = 0; + stream->in[i].mid = 0;

result = SCTP_STRRESET_PERFORMED;

@@@ -974,11 -980,15 +978,15 @@@ struct sctp_chunk *sctp_process_strrese

if (result == SCTP_STRRESET_PERFORMED) { if (nums) { - for (i = 0; i < nums; i++) - stream->out[ntohs(str_p[i])].ssn = 0; + for (i = 0; i < nums; i++) { + stream->out[ntohs(str_p[i])].mid = 0; + stream->out[ntohs(str_p[i])].mid_uo = 0; + } } else { - for (i = 0; i < stream->outcnt; i++) - stream->out[i].ssn = 0; + for (i = 0; i < stream->outcnt; i++) { + stream->out[i].mid = 0; + stream->out[i].mid_uo = 0; + } }

flags = SCTP_STREAM_RESET_OUTGOING_SSN; @@@ -1021,8 -1031,7 +1029,7 @@@ &asoc->peer.tsn_map); LIST_HEAD(temp);

- sctp_ulpq_reasm_flushtsn(&asoc->ulpq, mtsn); - sctp_ulpq_abort_pd(&asoc->ulpq, GFP_ATOMIC); + asoc->stream.si->report_ftsn(&asoc->ulpq, mtsn);

sctp_tsnmap_init(&asoc->peer.tsn_map, SCTP_TSN_MAP_INITIAL, @@@ -1040,10 -1049,12 +1047,12 @@@ asoc->ctsn_ack_point = asoc->next_tsn - 1; asoc->adv_peer_ack_point = asoc->ctsn_ack_point;

- for (i = 0; i < stream->outcnt; i++) - stream->out[i].ssn = 0; + for (i = 0; i < stream->outcnt; i++) { + stream->out[i].mid = 0; + stream->out[i].mid_uo = 0; + } for (i = 0; i < stream->incnt; i++) - stream->in[i].ssn = 0; + stream->in[i].mid = 0; }

for (i = 0; i < stream->outcnt; i++) diff --combined net/smc/af_smc.c index 449f62e1e270,daf8075f5a4c..b6e4e2e4fe12 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@@ -520,7 -520,7 +520,7 @@@ decline_rdma smc->use_fallback = true; if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) { rc = smc_clc_send_decline(smc, reason_code); - if (rc < sizeof(struct smc_clc_msg_decline)) + if (rc < 0) goto out_err; } goto out_connected; @@@ -751,14 -751,16 +751,16 @@@ static void smc_listen_work(struct work { struct smc_sock *new_smc = container_of(work, struct smc_sock, smc_listen_work); + struct smc_clc_msg_proposal_prefix *pclc_prfx; struct socket *newclcsock = new_smc->clcsock; struct smc_sock *lsmc = new_smc->listen_smc; struct smc_clc_msg_accept_confirm cclc; int local_contact = SMC_REUSE_CONTACT; struct sock *newsmcsk = &new_smc->sk; - struct smc_clc_msg_proposal pclc; + struct smc_clc_msg_proposal *pclc; struct smc_ib_device *smcibdev; struct sockaddr_in peeraddr; + u8 buf[SMC_CLC_MAX_LEN]; struct smc_link *link; int reason_code = 0; int rc = 0, len; @@@ -775,7 -777,7 +777,7 @@@ /* do inband token exchange - *wait for and receive SMC Proposal CLC message */ - reason_code = smc_clc_wait_msg(new_smc, &pclc, sizeof(pclc), + reason_code = smc_clc_wait_msg(new_smc, &buf, sizeof(buf), SMC_CLC_PROPOSAL); if (reason_code < 0) goto out_err; @@@ -804,8 -806,11 +806,11 @@@ reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */ goto decline_rdma; } - if ((pclc.outgoing_subnet != subnet) || - (pclc.prefix_len != prefix_len)) { + + pclc = (struct smc_clc_msg_proposal *)&buf; + pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (pclc_prfx->outgoing_subnet != subnet || + pclc_prfx->prefix_len != prefix_len) { reason_code = SMC_CLC_DECL_CNFERR; /* configuration error */ goto decline_rdma; } @@@ -816,7 -821,7 +821,7 @@@ /* allocate connection / link group */ mutex_lock(&smc_create_lgr_pending); local_contact = smc_conn_create(new_smc, peeraddr.sin_addr.s_addr, - smcibdev, ibport, &pclc.lcl, 0); + smcibdev, ibport, &pclc->lcl, 0); if (local_contact < 0) { rc = local_contact; if (rc == -ENOMEM) @@@ -879,11 -884,9 +884,9 @@@ } /* QP confirmation over RoCE fabric */ reason_code = smc_serv_conf_first_link(new_smc); - if (reason_code < 0) { + if (reason_code < 0) /* peer is not aware of a problem */ - rc = reason_code; goto out_err_unlock; - } if (reason_code > 0) goto decline_rdma_unlock; } @@@ -916,8 -919,7 +919,7 @@@ decline_rdma smc_conn_free(&new_smc->conn); new_smc->use_fallback = true; if (reason_code && (reason_code != SMC_CLC_DECL_REPLY)) { - rc = smc_clc_send_decline(new_smc, reason_code); - if (rc < sizeof(struct smc_clc_msg_decline)) + if (smc_clc_send_decline(new_smc, reason_code) < 0) goto out_err; } goto out_connected; @@@ -1107,7 -1109,7 +1109,7 @@@ out return rc; }

-static unsigned int smc_accept_poll(struct sock *parent) +static __poll_t smc_accept_poll(struct sock *parent) { struct smc_sock *isk; struct sock *sk; @@@ -1126,11 -1128,11 +1128,11 @@@ return 0; }

-static unsigned int smc_poll(struct file *file, struct socket *sock, +static __poll_t smc_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; - unsigned int mask = 0; + __poll_t mask = 0; struct smc_sock *smc; int rc;

diff --combined net/smc/smc_clc.c index 511548085d16,abf7ceb6690b..8ac51583a063 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@@ -22,6 -22,54 +22,54 @@@ #include "smc_clc.h" #include "smc_ib.h"

+ /* check if received message has a correct header length and contains valid + * heading and trailing eyecatchers + */ + static bool smc_clc_msg_hdr_valid(struct smc_clc_msg_hdr *clcm) + { + struct smc_clc_msg_proposal_prefix *pclc_prfx; + struct smc_clc_msg_accept_confirm *clc; + struct smc_clc_msg_proposal *pclc; + struct smc_clc_msg_decline *dclc; + struct smc_clc_msg_trail *trl; + + if (memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER))) + return false; + switch (clcm->type) { + case SMC_CLC_PROPOSAL: + pclc = (struct smc_clc_msg_proposal *)clcm; + pclc_prfx = smc_clc_proposal_get_prefix(pclc); + if (ntohs(pclc->hdr.length) != + sizeof(*pclc) + ntohs(pclc->iparea_offset) + + sizeof(*pclc_prfx) + + pclc_prfx->ipv6_prefixes_cnt * + sizeof(struct smc_clc_ipv6_prefix) + + sizeof(*trl)) + return false; + trl = (struct smc_clc_msg_trail *) + ((u8 *)pclc + ntohs(pclc->hdr.length) - sizeof(*trl)); + break; + case SMC_CLC_ACCEPT: + case SMC_CLC_CONFIRM: + clc = (struct smc_clc_msg_accept_confirm *)clcm; + if (ntohs(clc->hdr.length) != sizeof(*clc)) + return false; + trl = &clc->trl; + break; + case SMC_CLC_DECLINE: + dclc = (struct smc_clc_msg_decline *)clcm; + if (ntohs(dclc->hdr.length) != sizeof(*dclc)) + return false; + trl = &dclc->trl; + break; + default: + return false; + } + if (memcmp(trl->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER))) + return false; + return true; + } + /* Wait for data on the tcp-socket, analyze received data * Returns: * 0 if success and it was not a decline that we received. @@@ -35,7 -83,7 +83,7 @@@ int smc_clc_wait_msg(struct smc_sock *s struct smc_clc_msg_hdr *clcm = buf; struct msghdr msg = {NULL, 0}; int reason_code = 0; - struct kvec vec; + struct kvec vec = {buf, buflen}; int len, datlen; int krflags;

@@@ -43,15 -91,12 +91,15 @@@ * so we don't consume any subsequent CLC message or payload data * in the TCP byte stream */ - vec.iov_base = buf; - vec.iov_len = buflen; + /* + * Caller must make sure that buflen is no less than + * sizeof(struct smc_clc_msg_hdr) + */ krflags = MSG_PEEK | MSG_WAITALL; smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME; - len = kernel_recvmsg(smc->clcsock, &msg, &vec, 1, - sizeof(struct smc_clc_msg_hdr), krflags); + iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, + sizeof(struct smc_clc_msg_hdr)); + len = sock_recvmsg(smc->clcsock, &msg, krflags); if (signal_pending(current)) { reason_code = -EINTR; clc_sk->sk_err = EINTR; @@@ -75,9 -120,7 +123,7 @@@ } datlen = ntohs(clcm->length); if ((len < sizeof(struct smc_clc_msg_hdr)) || - (datlen < sizeof(struct smc_clc_msg_decline)) || - (datlen > sizeof(struct smc_clc_msg_accept_confirm)) || - memcmp(clcm->eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)) || + (datlen > buflen) || ((clcm->type != SMC_CLC_DECLINE) && (clcm->type != expected_type))) { smc->sk.sk_err = EPROTO; @@@ -86,12 -129,13 +132,12 @@@ }

/* receive the complete CLC message */ - vec.iov_base = buf; - vec.iov_len = buflen; memset(&msg, 0, sizeof(struct msghdr)); + iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, buflen); krflags = MSG_WAITALL; smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME; - len = kernel_recvmsg(smc->clcsock, &msg, &vec, 1, datlen, krflags); + len = sock_recvmsg(smc->clcsock, &msg, krflags); - if (len < datlen) { + if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) { smc->sk.sk_err = EPROTO; reason_code = -EPROTO; goto out; @@@ -135,7 -179,7 +181,7 @@@ int smc_clc_send_decline(struct smc_soc smc->sk.sk_err = EPROTO; if (len < 0) smc->sk.sk_err = -len; - return len; + return sock_error(&smc->sk); }

/* send CLC PROPOSAL message across internal TCP socket */ @@@ -143,33 -187,43 +189,43 @@@ int smc_clc_send_proposal(struct smc_so struct smc_ib_device *smcibdev, u8 ibport) { + struct smc_clc_msg_proposal_prefix pclc_prfx; struct smc_clc_msg_proposal pclc; + struct smc_clc_msg_trail trl; int reason_code = 0; + struct kvec vec[3]; struct msghdr msg; - struct kvec vec; - int len, rc; + int len, plen, rc;

/* send SMC Proposal CLC message */ + plen = sizeof(pclc) + sizeof(pclc_prfx) + sizeof(trl); memset(&pclc, 0, sizeof(pclc)); memcpy(pclc.hdr.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); pclc.hdr.type = SMC_CLC_PROPOSAL; - pclc.hdr.length = htons(sizeof(pclc)); + pclc.hdr.length = htons(plen); pclc.hdr.version = SMC_CLC_V1; /* SMC version */ memcpy(pclc.lcl.id_for_peer, local_systemid, sizeof(local_systemid)); memcpy(&pclc.lcl.gid, &smcibdev->gid[ibport - 1], SMC_GID_SIZE); memcpy(&pclc.lcl.mac, &smcibdev->mac[ibport - 1], ETH_ALEN); + pclc.iparea_offset = htons(0);

+ memset(&pclc_prfx, 0, sizeof(pclc_prfx)); /* determine subnet and mask from internal TCP socket */ - rc = smc_netinfo_by_tcpsk(smc->clcsock, &pclc.outgoing_subnet, - &pclc.prefix_len); + rc = smc_netinfo_by_tcpsk(smc->clcsock, &pclc_prfx.outgoing_subnet, + &pclc_prfx.prefix_len); if (rc) return SMC_CLC_DECL_CNFERR; /* configuration error */ - memcpy(pclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); + pclc_prfx.ipv6_prefixes_cnt = 0; + memcpy(trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); memset(&msg, 0, sizeof(msg)); - vec.iov_base = &pclc; - vec.iov_len = sizeof(pclc); + vec[0].iov_base = &pclc; + vec[0].iov_len = sizeof(pclc); + vec[1].iov_base = &pclc_prfx; + vec[1].iov_len = sizeof(pclc_prfx); + vec[2].iov_base = &trl; + vec[2].iov_len = sizeof(trl); /* due to the few bytes needed for clc-handshake this cannot block */ - len = kernel_sendmsg(smc->clcsock, &msg, &vec, 1, sizeof(pclc)); + len = kernel_sendmsg(smc->clcsock, &msg, vec, 3, plen); if (len < sizeof(pclc)) { if (len >= 0) { reason_code = -ENETUNREACH; diff --combined net/socket.c index 092baa464afc,bbd2e9ceb692..60d05479b2c1 --- a/net/socket.c +++ b/net/socket.c @@@ -118,7 -118,7 +118,7 @@@ static ssize_t sock_write_iter(struct k static int sock_mmap(struct file *file, struct vm_area_struct *vma);

static int sock_close(struct inode *inode, struct file *file); -static unsigned int sock_poll(struct file *file, +static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait); static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT @@@ -163,12 -163,6 +163,6 @@@ static DEFINE_SPINLOCK(net_family_lock) static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly;

/* - * Statistics counters of the socket lists - */ - - static DEFINE_PER_CPU(int, sockets_in_use); - - /* * Support routines. * Move socket addresses back and forth across the kernel/user * divide and look after the messy bits. @@@ -578,7 -572,6 +572,6 @@@ struct socket *sock_alloc(void inode->i_gid = current_fsgid(); inode->i_op = &sockfs_inode_ops;

- this_cpu_add(sockets_in_use, 1); return sock; } EXPORT_SYMBOL(sock_alloc); @@@ -605,7 -598,6 +598,6 @@@ void sock_release(struct socket *sock if (rcu_dereference_protected(sock->wq, 1)->fasync_list) pr_err("%s: fasync list not empty!\n", __func__);

- this_cpu_sub(sockets_in_use, 1); if (!sock->file) { iput(SOCK_INODE(sock)); return; @@@ -1095,9 -1087,9 +1087,9 @@@ out_release EXPORT_SYMBOL(sock_create_lite);

/* No kernel lock held - perfect */ -static unsigned int sock_poll(struct file *file, poll_table *wait) +static __poll_t sock_poll(struct file *file, poll_table *wait) { - unsigned int busy_flag = 0; + __poll_t busy_flag = 0; struct socket *sock;

/* @@@ -2622,17 -2614,8 +2614,8 @@@ core_initcall(sock_init); /* early init #ifdef CONFIG_PROC_FS void socket_seq_show(struct seq_file *seq) { - int cpu; - int counter = 0; - - for_each_possible_cpu(cpu) - counter += per_cpu(sockets_in_use, cpu); - - /* It can be negative, by the way. 8) */ - if (counter < 0) - counter = 0; - - seq_printf(seq, "sockets: used %d\n", counter); + seq_printf(seq, "sockets: used %d\n", + sock_inuse_get(seq->private)); } #endif /* CONFIG_PROC_FS */

diff --combined net/tipc/group.c index 5f4ffae807ee,fb7fe971e51b..3e8268d966fa --- a/net/tipc/group.c +++ b/net/tipc/group.c @@@ -64,7 -64,7 +64,7 @@@ enum mbr_state struct tipc_member { struct rb_node tree_node; struct list_head list; - struct list_head congested; + struct list_head small_win; struct sk_buff *event_msg; struct sk_buff_head deferredq; struct tipc_group *group; @@@ -82,7 -82,7 +82,7 @@@

struct tipc_group { struct rb_root members; - struct list_head congested; + struct list_head small_win; struct list_head pending; struct list_head active; struct list_head reclaiming; @@@ -109,8 -109,7 +109,8 @@@ static void tipc_group_proto_xmit(struc static void tipc_group_decr_active(struct tipc_group *grp, struct tipc_member *m) { - if (m->state == MBR_ACTIVE || m->state == MBR_RECLAIMING) + if (m->state == MBR_ACTIVE || m->state == MBR_RECLAIMING || + m->state == MBR_REMITTED) grp->active_cnt--; }

@@@ -137,12 -136,12 +137,12 @@@ u16 tipc_group_bc_snd_nxt(struct tipc_g return grp->bc_snd_nxt; }

- static bool tipc_group_is_enabled(struct tipc_member *m) + static bool tipc_group_is_receiver(struct tipc_member *m) { return m->state != MBR_QUARANTINED && m->state != MBR_LEAVING; }

- static bool tipc_group_is_receiver(struct tipc_member *m) + static bool tipc_group_is_sender(struct tipc_member *m) { return m && m->state >= MBR_JOINED; } @@@ -169,7 -168,7 +169,7 @@@ struct tipc_group *tipc_group_create(st if (!grp) return NULL; tipc_nlist_init(&grp->dests, tipc_own_addr(net)); - INIT_LIST_HEAD(&grp->congested); + INIT_LIST_HEAD(&grp->small_win); INIT_LIST_HEAD(&grp->active); INIT_LIST_HEAD(&grp->pending); INIT_LIST_HEAD(&grp->reclaiming); @@@ -233,7 -232,7 +233,7 @@@ static struct tipc_member *tipc_group_f struct tipc_member *m;

m = tipc_group_find_member(grp, node, port); - if (m && tipc_group_is_enabled(m)) + if (m && tipc_group_is_receiver(m)) return m; return NULL; } @@@ -286,7 -285,7 +286,7 @@@ static struct tipc_member *tipc_group_c if (!m) return NULL; INIT_LIST_HEAD(&m->list); - INIT_LIST_HEAD(&m->congested); + INIT_LIST_HEAD(&m->small_win); __skb_queue_head_init(&m->deferredq); m->group = grp; m->node = node; @@@ -315,7 -314,7 +315,7 @@@ static void tipc_group_delete_member(st grp->bc_ackers--;

list_del_init(&m->list); - list_del_init(&m->congested); + list_del_init(&m->small_win); tipc_group_decr_active(grp, m);

/* If last member on a node, remove node from dest list */ @@@ -344,7 -343,7 +344,7 @@@ void tipc_group_update_member(struct ti struct tipc_group *grp = m->group; struct tipc_member *_m, *tmp;

- if (!tipc_group_is_enabled(m)) + if (!tipc_group_is_receiver(m)) return;

m->window -= len; @@@ -352,16 -351,14 +352,14 @@@ if (m->window >= ADV_IDLE) return;

- list_del_init(&m->congested); + list_del_init(&m->small_win);

- /* Sort member into congested members' list */ - list_for_each_entry_safe(_m, tmp, &grp->congested, congested) { - if (m->window > _m->window) - continue; - list_add_tail(&m->congested, &_m->congested); - return; + /* Sort member into small_window members' list */ + list_for_each_entry_safe(_m, tmp, &grp->small_win, small_win) { + if (_m->window > m->window) + break; } - list_add_tail(&m->congested, &grp->congested); + list_add_tail(&m->small_win, &_m->small_win); }

void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack) @@@ -373,7 -370,7 +371,7 @@@

for (n = rb_first(&grp->members); n; n = rb_next(n)) { m = container_of(n, struct tipc_member, tree_node); - if (tipc_group_is_enabled(m)) { + if (tipc_group_is_receiver(m)) { tipc_group_update_member(m, len); m->bc_acked = prev; ackers++; @@@ -428,10 -425,10 +426,10 @@@ bool tipc_group_bc_cong(struct tipc_gro if (grp->bc_ackers) return true;

- if (list_empty(&grp->congested)) + if (list_empty(&grp->small_win)) return false;

- m = list_first_entry(&grp->congested, struct tipc_member, congested); + m = list_first_entry(&grp->small_win, struct tipc_member, small_win); if (m->window >= len) return false;

@@@ -486,7 -483,7 +484,7 @@@ void tipc_group_filter_msg(struct tipc_ goto drop;

m = tipc_group_find_member(grp, node, port); - if (!tipc_group_is_receiver(m)) + if (!tipc_group_is_sender(m)) goto drop;

if (less(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) @@@ -563,7 -560,7 +561,7 @@@ void tipc_group_update_rcv_win(struct t int max_active = grp->max_active; int reclaim_limit = max_active * 3 / 4; int active_cnt = grp->active_cnt; - struct tipc_member *m, *rm; + struct tipc_member *m, *rm, *pm;

m = tipc_group_find_member(grp, node, port); if (!m) @@@ -606,17 -603,6 +604,17 @@@ pr_warn_ratelimited("Rcv unexpected msg after REMIT\n"); tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); } + grp->active_cnt--; + list_del_init(&m->list); + if (list_empty(&grp->pending)) + return; + + /* Set oldest pending member to active and advertise */ + pm = list_first_entry(&grp->pending, struct tipc_member, list); + pm->state = MBR_ACTIVE; + list_move_tail(&pm->list, &grp->active); + grp->active_cnt++; + tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq); break; case MBR_RECLAIMING: case MBR_DISCOVERED: @@@ -703,7 -689,7 +701,7 @@@ void tipc_group_proto_rcv(struct tipc_g msg_set_grp_bc_seqno(ehdr, m->bc_syncpt); __skb_queue_tail(inputq, m->event_msg); } - list_del_init(&m->congested); + list_del_init(&m->small_win); tipc_group_update_member(m, 0); return; case GRP_LEAVE_MSG: @@@ -711,7 -697,7 +709,7 @@@ return; m->bc_syncpt = msg_grp_bc_syncpt(hdr); list_del_init(&m->list); - list_del_init(&m->congested); + list_del_init(&m->small_win); *usr_wakeup = true;

/* Wait until WITHDRAW event is received */ @@@ -731,7 -717,7 +729,7 @@@ m->window += msg_adv_win(hdr); *usr_wakeup = m->usr_pending; m->usr_pending = false; - list_del_init(&m->congested); + list_del_init(&m->small_win); return; case GRP_ACK_MSG: if (!m) @@@ -754,14 -740,14 +752,14 @@@ if (!m || m->state != MBR_RECLAIMING) return;

- list_del_init(&m->list); - grp->active_cnt--; remitted = msg_grp_remitted(hdr);

/* Messages preceding the REMIT still in receive queue */ if (m->advertised > remitted) { m->state = MBR_REMITTED; in_flight = m->advertised - remitted; + m->advertised = ADV_IDLE + in_flight; + return; } /* All messages preceding the REMIT have been read */ if (m->advertised <= remitted) { @@@ -773,8 -759,6 +771,8 @@@ tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq);

m->advertised = ADV_IDLE + in_flight; + grp->active_cnt--; + list_del_init(&m->list);

/* Set oldest pending member to active and advertise */ if (list_empty(&grp->pending)) @@@ -851,10 -835,7 +849,7 @@@ void tipc_group_member_evt(struct tipc_ m->instance = instance; TIPC_SKB_CB(skb)->orig_member = m->instance; tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); - if (m->window < ADV_IDLE) - tipc_group_update_member(m, 0); - else - list_del_init(&m->congested); + tipc_group_update_member(m, 0); } else if (event == TIPC_WITHDRAWN) { if (!m) goto drop; @@@ -887,7 -868,7 +882,7 @@@ __skb_queue_tail(inputq, skb); } list_del_init(&m->list); - list_del_init(&m->congested); + list_del_init(&m->small_win); } *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); return; diff --combined net/tipc/socket.c index 2aa46e8cd8fe,b51d5cba5094..cf9644ea13ba --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@@ -710,13 -710,13 +710,13 @@@ static int tipc_getname(struct socket * * imply that the operation will succeed, merely that it should be performed * and will not block. */ -static unsigned int tipc_poll(struct file *file, struct socket *sock, +static __poll_t tipc_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); struct tipc_group *grp = tsk->group; - u32 revents = 0; + __poll_t revents = 0;

sock_poll_wait(file, sk_sleep(sk), wait);

@@@ -2640,9 -2640,7 +2640,7 @@@ void tipc_sk_reinit(struct net *net rhashtable_walk_enter(&tn->sk_rht, &iter);

do { - tsk = ERR_PTR(rhashtable_walk_start(&iter)); - if (IS_ERR(tsk)) - goto walk_stop; + rhashtable_walk_start(&iter);

while ((tsk = rhashtable_walk_next(&iter)) && !IS_ERR(tsk)) { spin_lock_bh(&tsk->sk.sk_lock.slock); @@@ -2651,7 -2649,7 +2649,7 @@@ msg_set_orignode(msg, tn->own_addr); spin_unlock_bh(&tsk->sk.sk_lock.slock); } - walk_stop: + rhashtable_walk_stop(&iter); } while (tsk == ERR_PTR(-EAGAIN)); } diff --combined net/wireless/nl80211.c index 2b3dbcd40e46,79a9ff682b7e..c084dd2205ac --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@@ -734,11 -734,12 +734,12 @@@ struct key_parse bool def_uni, def_multi; };

- static int nl80211_parse_key_new(struct nlattr *key, struct key_parse *k) + static int nl80211_parse_key_new(struct genl_info *info, struct nlattr *key, + struct key_parse *k) { struct nlattr *tb[NL80211_KEY_MAX + 1]; int err = nla_parse_nested(tb, NL80211_KEY_MAX, key, - nl80211_key_policy, NULL); + nl80211_key_policy, info->extack); if (err) return err;

@@@ -771,7 -772,8 +772,8 @@@ if (tb[NL80211_KEY_TYPE]) { k->type = nla_get_u32(tb[NL80211_KEY_TYPE]); if (k->type < 0 || k->type >= NUM_NL80211_KEYTYPES) - return -EINVAL; + return genl_err_attr(info, -EINVAL, + tb[NL80211_KEY_TYPE]); }

if (tb[NL80211_KEY_DEFAULT_TYPES]) { @@@ -779,7 -781,8 +781,8 @@@

err = nla_parse_nested(kdt, NUM_NL80211_KEY_DEFAULT_TYPES - 1, tb[NL80211_KEY_DEFAULT_TYPES], - nl80211_key_default_policy, NULL); + nl80211_key_default_policy, + info->extack); if (err) return err;

@@@ -820,8 -823,10 +823,10 @@@ static int nl80211_parse_key_old(struc

if (info->attrs[NL80211_ATTR_KEY_TYPE]) { k->type = nla_get_u32(info->attrs[NL80211_ATTR_KEY_TYPE]); - if (k->type < 0 || k->type >= NUM_NL80211_KEYTYPES) + if (k->type < 0 || k->type >= NUM_NL80211_KEYTYPES) { + GENL_SET_ERR_MSG(info, "key type out of range"); return -EINVAL; + } }

if (info->attrs[NL80211_ATTR_KEY_DEFAULT_TYPES]) { @@@ -850,31 -855,42 +855,42 @@@ static int nl80211_parse_key(struct gen k->type = -1;

if (info->attrs[NL80211_ATTR_KEY]) - err = nl80211_parse_key_new(info->attrs[NL80211_ATTR_KEY], k); + err = nl80211_parse_key_new(info, info->attrs[NL80211_ATTR_KEY], k); else err = nl80211_parse_key_old(info, k);

if (err) return err;

- if (k->def && k->defmgmt) + if (k->def && k->defmgmt) { + GENL_SET_ERR_MSG(info, "key with def && defmgmt is invalid"); return -EINVAL; + }

if (k->defmgmt) { - if (k->def_uni || !k->def_multi) + if (k->def_uni || !k->def_multi) { + GENL_SET_ERR_MSG(info, "defmgmt key must be mcast"); return -EINVAL; + } }

if (k->idx != -1) { if (k->defmgmt) { - if (k->idx < 4 || k->idx > 5) + if (k->idx < 4 || k->idx > 5) { + GENL_SET_ERR_MSG(info, + "defmgmt key idx not 4 or 5"); return -EINVAL; + } } else if (k->def) { - if (k->idx < 0 || k->idx > 3) + if (k->idx < 0 || k->idx > 3) { + GENL_SET_ERR_MSG(info, "def key idx not 0-3"); return -EINVAL; + } } else { - if (k->idx < 0 || k->idx > 5) + if (k->idx < 0 || k->idx > 5) { + GENL_SET_ERR_MSG(info, "key idx not 0-5"); return -EINVAL; + } } }

@@@ -883,8 -899,9 +899,9 @@@

static struct cfg80211_cached_keys * nl80211_parse_connkeys(struct cfg80211_registered_device *rdev, - struct nlattr *keys, bool *no_ht) + struct genl_info *info, bool *no_ht) { + struct nlattr *keys = info->attrs[NL80211_ATTR_KEYS]; struct key_parse parse; struct nlattr *key; struct cfg80211_cached_keys *result; @@@ -909,17 -926,22 +926,22 @@@ memset(&parse, 0, sizeof(parse)); parse.idx = -1;

- err = nl80211_parse_key_new(key, &parse); + err = nl80211_parse_key_new(info, key, &parse); if (err) goto error; err = -EINVAL; if (!parse.p.key) goto error; - if (parse.idx < 0 || parse.idx > 3) + if (parse.idx < 0 || parse.idx > 3) { + GENL_SET_ERR_MSG(info, "key index out of range [0-3]"); goto error; + } if (parse.def) { - if (def) + if (def) { + GENL_SET_ERR_MSG(info, + "only one key can be default"); goto error; + } def = 1; result->def = parse.idx; if (!parse.def_uni || !parse.def_multi) @@@ -932,6 -954,7 +954,7 @@@ goto error; if (parse.p.cipher != WLAN_CIPHER_SUITE_WEP40 && parse.p.cipher != WLAN_CIPHER_SUITE_WEP104) { + GENL_SET_ERR_MSG(info, "connect key must be WEP"); err = -EINVAL; goto error; } @@@ -947,6 -970,7 +970,7 @@@

if (result->def < 0) { err = -EINVAL; + GENL_SET_ERR_MSG(info, "need a default/TX key"); goto error; }

@@@ -7817,6 -7841,11 +7841,11 @@@ static int nl80211_send_bss(struct sk_b intbss->ts_boottime, NL80211_BSS_PAD)) goto nla_put_failure;

+ if (!nl80211_put_signal(msg, intbss->pub.chains, + intbss->pub.chain_signal, + NL80211_BSS_CHAIN_SIGNAL)) + goto nla_put_failure; + switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: if (nla_put_u32(msg, NL80211_BSS_SIGNAL_MBM, res->signal)) @@@ -8613,9 -8642,7 +8642,7 @@@ static int nl80211_join_ibss(struct sk_ if (ibss.privacy && info->attrs[NL80211_ATTR_KEYS]) { bool no_ht = false;

- connkeys = nl80211_parse_connkeys(rdev, - info->attrs[NL80211_ATTR_KEYS], - &no_ht); + connkeys = nl80211_parse_connkeys(rdev, info, &no_ht); if (IS_ERR(connkeys)) return PTR_ERR(connkeys);

@@@ -9019,8 -9046,7 +9046,7 @@@ static int nl80211_connect(struct sk_bu }

if (connect.privacy && info->attrs[NL80211_ATTR_KEYS]) { - connkeys = nl80211_parse_connkeys(rdev, - info->attrs[NL80211_ATTR_KEYS], NULL); + connkeys = nl80211_parse_connkeys(rdev, info, NULL); if (IS_ERR(connkeys)) return PTR_ERR(connkeys); } @@@ -11361,8 -11387,7 +11387,8 @@@ static int nl80211_nan_add_func(struct break; case NL80211_NAN_FUNC_FOLLOW_UP: if (!tb[NL80211_NAN_FUNC_FOLLOW_UP_ID] || - !tb[NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID]) { + !tb[NL80211_NAN_FUNC_FOLLOW_UP_REQ_ID] || + !tb[NL80211_NAN_FUNC_FOLLOW_UP_DEST]) { err = -EINVAL; goto out; } @@@ -13945,7 -13970,7 +13971,7 @@@ void nl80211_send_disconnected(struct c

if (nla_put_u32(msg, NL80211_ATTR_WIPHY, rdev->wiphy_idx) || nla_put_u32(msg, NL80211_ATTR_IFINDEX, netdev->ifindex) || - (from_ap && reason && + (reason && nla_put_u16(msg, NL80211_ATTR_REASON_CODE, reason)) || (from_ap && nla_put_flag(msg, NL80211_ATTR_DISCONNECTED_BY_AP)) || diff --combined net/xfrm/xfrm_input.c index 5b2409746ae0,26b10eb7a206..1472c0857975 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@@ -257,7 -257,6 +257,6 @@@ int xfrm_input(struct sk_buff *skb, in

if (xo && (xo->flags & CRYPTO_DONE)) { crypto_done = true; - x = xfrm_input_state(skb); family = XFRM_SPI_SKB_CB(skb)->family;

if (!(xo->status & CRYPTO_SUCCESS)) { @@@ -518,7 -517,7 +517,7 @@@ int xfrm_trans_queue(struct sk_buff *sk return -ENOBUFS;

XFRM_TRANS_SKB_CB(skb)->finish = finish; - skb_queue_tail(&trans->queue, skb); + __skb_queue_tail(&trans->queue, skb); tasklet_schedule(&trans->tasklet); return 0; } diff --combined net/xfrm/xfrm_policy.c index 2ef6db98e9ba,d8a8129b9232..26f56e64654a --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@@ -54,7 -54,7 +54,7 @@@ static struct xfrm_policy_afinfo const static struct kmem_cache *xfrm_dst_cache __read_mostly; static __read_mostly seqcount_t xfrm_policy_hash_generation;

- static void xfrm_init_pmtu(struct dst_entry *dst); + static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr); static int stale_bundle(struct dst_entry *dst); static int xfrm_bundle_ok(struct xfrm_dst *xdst); static void xfrm_policy_queue_process(struct timer_list *t); @@@ -609,8 -609,7 +609,8 @@@ static void xfrm_hash_rebuild(struct wo

/* re-insert all policies by order of creation */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { - if (xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) { + if (policy->walk.dead || + xfrm_policy_id2dir(policy->index) >= XFRM_POLICY_MAX) { /* skip socket policies */ continue; } @@@ -1258,7 -1257,7 +1258,7 @@@ EXPORT_SYMBOL(xfrm_policy_delete)

int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) { - struct net *net = xp_net(pol); + struct net *net = sock_net(sk); struct xfrm_policy *old_pol;

#ifdef CONFIG_XFRM_SUB_POLICY @@@ -1545,7 -1544,9 +1545,9 @@@ static inline int xfrm_fill_dst(struct */

static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, - struct xfrm_state **xfrm, int nx, + struct xfrm_state **xfrm, + struct xfrm_dst **bundle, + int nx, const struct flowi *fl, struct dst_entry *dst) { @@@ -1553,8 -1554,8 +1555,8 @@@ unsigned long now = jiffies; struct net_device *dev; struct xfrm_mode *inner_mode; - struct dst_entry *dst_prev = NULL; - struct dst_entry *dst0 = NULL; + struct xfrm_dst *xdst_prev = NULL; + struct xfrm_dst *xdst0 = NULL; int i = 0; int err; int header_len = 0; @@@ -1580,13 -1581,14 +1582,14 @@@ goto put_states; }

- if (!dst_prev) - dst0 = dst1; + bundle[i] = xdst; + if (!xdst_prev) + xdst0 = xdst; else /* Ref count is taken during xfrm_alloc_dst() * No need to do dst_clone() on dst1 */ - dst_prev->child = dst1; + xfrm_dst_set_child(xdst_prev, &xdst->u.dst);

if (xfrm[i]->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(xfrm[i], @@@ -1623,8 -1625,7 +1626,7 @@@ dst1->input = dst_discard; dst1->output = inner_mode->afinfo->output;

- dst1->next = dst_prev; - dst_prev = dst1; + xdst_prev = xdst;

header_len += xfrm[i]->props.header_len; if (xfrm[i]->type->flags & XFRM_TYPE_NON_FRAGMENT) @@@ -1632,40 -1633,39 +1634,39 @@@ trailer_len += xfrm[i]->props.trailer_len; }

- dst_prev->child = dst; - dst0->path = dst; + xfrm_dst_set_child(xdst_prev, dst); + xdst0->path = dst;

err = -ENODEV; dev = dst->dev; if (!dev) goto free_dst;

- xfrm_init_path((struct xfrm_dst *)dst0, dst, nfheader_len); - xfrm_init_pmtu(dst_prev); - - for (dst_prev = dst0; dst_prev != dst; dst_prev = dst_prev->child) { - struct xfrm_dst *xdst = (struct xfrm_dst *)dst_prev; + xfrm_init_path(xdst0, dst, nfheader_len); + xfrm_init_pmtu(bundle, nx);

- err = xfrm_fill_dst(xdst, dev, fl); + for (xdst_prev = xdst0; xdst_prev != (struct xfrm_dst *)dst; + xdst_prev = (struct xfrm_dst *) xfrm_dst_child(&xdst_prev->u.dst)) { + err = xfrm_fill_dst(xdst_prev, dev, fl); if (err) goto free_dst;

- dst_prev->header_len = header_len; - dst_prev->trailer_len = trailer_len; - header_len -= xdst->u.dst.xfrm->props.header_len; - trailer_len -= xdst->u.dst.xfrm->props.trailer_len; + xdst_prev->u.dst.header_len = header_len; + xdst_prev->u.dst.trailer_len = trailer_len; + header_len -= xdst_prev->u.dst.xfrm->props.header_len; + trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len; }

out: - return dst0; + return &xdst0->u.dst;

put_states: for (; i < nx; i++) xfrm_state_put(xfrm[i]); free_dst: - if (dst0) - dst_release_immediate(dst0); - dst0 = ERR_PTR(err); + if (xdst0) + dst_release_immediate(&xdst0->u.dst); + xdst0 = ERR_PTR(err); goto out; }

@@@ -1807,7 -1807,7 +1808,7 @@@ static bool xfrm_xdst_can_reuse(struct for (i = 0; i < num; i++) { if (!dst || dst->xfrm != xfrm[i]) return false; - dst = dst->child; + dst = xfrm_dst_child(dst); }

return xfrm_bundle_ok(xdst); @@@ -1820,6 -1820,7 +1821,7 @@@ xfrm_resolve_and_create_bundle(struct x { struct net *net = xp_net(pols[0]); struct xfrm_state *xfrm[XFRM_MAX_DEPTH]; + struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; struct xfrm_dst *xdst, *old; struct dst_entry *dst; int err; @@@ -1848,7 -1849,7 +1850,7 @@@

old = xdst;

- dst = xfrm_bundle_create(pols[0], xfrm, err, fl, dst_orig); + dst = xfrm_bundle_create(pols[0], xfrm, bundle, err, fl, dst_orig); if (IS_ERR(dst)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR); return ERR_CAST(dst); @@@ -1888,8 -1889,8 +1890,8 @@@ static void xfrm_policy_queue_process(s xfrm_decode_session(skb, &fl, dst->ops->family); spin_unlock(&pq->hold_queue.lock);

- dst_hold(dst->path); - dst = xfrm_lookup(net, dst->path, &fl, sk, 0); + dst_hold(xfrm_dst_path(dst)); + dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, 0); if (IS_ERR(dst)) goto purge_queue;

@@@ -1918,8 -1919,8 +1920,8 @@@ skb = __skb_dequeue(&list);

xfrm_decode_session(skb, &fl, skb_dst(skb)->ops->family); - dst_hold(skb_dst(skb)->path); - dst = xfrm_lookup(net, skb_dst(skb)->path, &fl, skb->sk, 0); + dst_hold(xfrm_dst_path(skb_dst(skb))); + dst = xfrm_lookup(net, xfrm_dst_path(skb_dst(skb)), &fl, skb->sk, 0); if (IS_ERR(dst)) { kfree_skb(skb); continue; @@@ -2020,8 -2021,8 +2022,8 @@@ static struct xfrm_dst *xfrm_create_dum dst1->output = xdst_queue_output;

dst_hold(dst); - dst1->child = dst; - dst1->path = dst; + xfrm_dst_set_child(xdst, dst); + xdst->path = dst;

xfrm_init_path((struct xfrm_dst *)dst1, dst, 0);

@@@ -2584,7 -2585,7 +2586,7 @@@ static int stale_bundle(struct dst_entr

void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { - while ((dst = dst->child) && dst->xfrm && dst->dev == dev) { + while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) { dst->dev = dev_net(dev)->loopback_dev; dev_hold(dst->dev); dev_put(dev); @@@ -2608,13 -2609,15 +2610,15 @@@ static struct dst_entry *xfrm_negative_ return dst; }

- static void xfrm_init_pmtu(struct dst_entry *dst) + static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr) { - do { - struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + while (nr--) { + struct xfrm_dst *xdst = bundle[nr]; u32 pmtu, route_mtu_cached; + struct dst_entry *dst;

- pmtu = dst_mtu(dst->child); + dst = &xdst->u.dst; + pmtu = dst_mtu(xfrm_dst_child(dst)); xdst->child_mtu_cached = pmtu;

pmtu = xfrm_state_mtu(dst->xfrm, pmtu); @@@ -2626,7 -2629,7 +2630,7 @@@ pmtu = route_mtu_cached;

dst_metric_set(dst, RTAX_MTU, pmtu); - } while ((dst = dst->next)); + } }

/* Check that the bundle accepts the flow and its components are @@@ -2635,19 -2638,20 +2639,20 @@@

static int xfrm_bundle_ok(struct xfrm_dst *first) { + struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; struct dst_entry *dst = &first->u.dst; - struct xfrm_dst *last; + struct xfrm_dst *xdst; + int start_from, nr; u32 mtu;

- if (!dst_check(dst->path, ((struct xfrm_dst *)dst)->path_cookie) || + if (!dst_check(xfrm_dst_path(dst), ((struct xfrm_dst *)dst)->path_cookie) || (dst->dev && !netif_running(dst->dev))) return 0;

if (dst->flags & DST_XFRM_QUEUE) return 1;

- last = NULL; - + start_from = nr = 0; do { struct xfrm_dst *xdst = (struct xfrm_dst *)dst;

@@@ -2659,9 -2663,11 +2664,11 @@@ xdst->policy_genid != atomic_read(&xdst->pols[0]->genid)) return 0;

- mtu = dst_mtu(dst->child); + bundle[nr++] = xdst; + + mtu = dst_mtu(xfrm_dst_child(dst)); if (xdst->child_mtu_cached != mtu) { - last = xdst; + start_from = nr; xdst->child_mtu_cached = mtu; }

@@@ -2669,30 -2675,30 +2676,30 @@@ return 0; mtu = dst_mtu(xdst->route); if (xdst->route_mtu_cached != mtu) { - last = xdst; + start_from = nr; xdst->route_mtu_cached = mtu; }

- dst = dst->child; + dst = xfrm_dst_child(dst); } while (dst->xfrm);

- if (likely(!last)) + if (likely(!start_from)) return 1;

- mtu = last->child_mtu_cached; - for (;;) { - dst = &last->u.dst; + xdst = bundle[start_from - 1]; + mtu = xdst->child_mtu_cached; + while (start_from--) { + dst = &xdst->u.dst;

mtu = xfrm_state_mtu(dst->xfrm, mtu); - if (mtu > last->route_mtu_cached) - mtu = last->route_mtu_cached; + if (mtu > xdst->route_mtu_cached) + mtu = xdst->route_mtu_cached; dst_metric_set(dst, RTAX_MTU, mtu); - - if (last == first) + if (!start_from) break;

- last = (struct xfrm_dst *)last->u.dst.next; - last->child_mtu_cached = mtu; + xdst = bundle[start_from - 1]; + xdst->child_mtu_cached = mtu; }

return 1; @@@ -2700,22 -2706,20 +2707,20 @@@

static unsigned int xfrm_default_advmss(const struct dst_entry *dst) { - return dst_metric_advmss(dst->path); + return dst_metric_advmss(xfrm_dst_path(dst)); }

static unsigned int xfrm_mtu(const struct dst_entry *dst) { unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);

- return mtu ? : dst_mtu(dst->path); + return mtu ? : dst_mtu(xfrm_dst_path(dst)); }

static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst, const void *daddr) { - const struct dst_entry *path = dst->path; - - for (; dst != path; dst = dst->child) { + while (dst->xfrm) { const struct xfrm_state *xfrm = dst->xfrm;

if (xfrm->props.mode == XFRM_MODE_TRANSPORT) @@@ -2724,6 -2728,8 +2729,8 @@@ daddr = xfrm->coaddr; else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR)) daddr = &xfrm->id.daddr; + + dst = xfrm_dst_child(dst); } return daddr; } @@@ -2732,7 -2738,7 +2739,7 @@@ static struct neighbour *xfrm_neigh_loo struct sk_buff *skb, const void *daddr) { - const struct dst_entry *path = dst->path; + const struct dst_entry *path = xfrm_dst_path(dst);

if (!skb) daddr = xfrm_get_dst_nexthop(dst, daddr); @@@ -2741,7 -2747,7 +2748,7 @@@

static void xfrm_confirm_neigh(const struct dst_entry *dst, const void *daddr) { - const struct dst_entry *path = dst->path; + const struct dst_entry *path = xfrm_dst_path(dst);

daddr = xfrm_get_dst_nexthop(dst, daddr); path->ops->confirm_neigh(path, daddr); diff --combined net/xfrm/xfrm_state.c index 429957412633,cc4c519cad76..20b1e414dbee --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@@ -313,14 -313,13 +313,14 @@@ retry if ((type && !try_module_get(type->owner))) type = NULL;

+ rcu_read_unlock(); + if (!type && try_load) { request_module("xfrm-offload-%d-%d", family, proto); try_load = 0; goto retry; }

- rcu_read_unlock(); return type; }

@@@ -1535,12 -1534,8 +1535,12 @@@ out err = -EINVAL; spin_lock_bh(&x1->lock); if (likely(x1->km.state == XFRM_STATE_VALID)) { - if (x->encap && x1->encap) + if (x->encap && x1->encap && + x->encap->encap_type == x1->encap->encap_type) memcpy(x1->encap, x->encap, sizeof(*x1->encap)); + else if (x->encap || x1->encap) + goto fail; + if (x->coaddr && x1->coaddr) { memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr)); } @@@ -1557,8 -1552,6 +1557,8 @@@ x->km.state = XFRM_STATE_DEAD; __xfrm_state_put(x); } + +fail: spin_unlock_bh(&x1->lock);

xfrm_state_put(x1); @@@ -2056,6 -2049,13 +2056,13 @@@ int xfrm_user_policy(struct sock *sk, i struct xfrm_mgr *km; struct xfrm_policy *pol = NULL;

+ if (!optval && !optlen) { + xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); + xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); + __sk_dst_reset(sk); + return 0; + } + if (optlen <= 0 || optlen > PAGE_SIZE) return -EMSGSIZE;

diff --combined tools/testing/selftests/bpf/test_align.c index 471bbbdb94db,fe916d29e166..e19b410125eb --- a/tools/testing/selftests/bpf/test_align.c +++ b/tools/testing/selftests/bpf/test_align.c @@@ -64,11 -64,11 +64,11 @@@ static struct bpf_align_test tests[] = .matches = { {1, "R1=ctx(id=0,off=0,imm=0)"}, {1, "R10=fp0"}, - {1, "R3=inv2"}, - {2, "R3=inv4"}, - {3, "R3=inv8"}, - {4, "R3=inv16"}, - {5, "R3=inv32"}, + {1, "R3_w=inv2"}, + {2, "R3_w=inv4"}, + {3, "R3_w=inv8"}, + {4, "R3_w=inv16"}, + {5, "R3_w=inv32"}, }, }, { @@@ -92,17 -92,17 +92,17 @@@ .matches = { {1, "R1=ctx(id=0,off=0,imm=0)"}, {1, "R10=fp0"}, - {1, "R3=inv1"}, - {2, "R3=inv2"}, - {3, "R3=inv4"}, - {4, "R3=inv8"}, - {5, "R3=inv16"}, - {6, "R3=inv1"}, - {7, "R4=inv32"}, - {8, "R4=inv16"}, - {9, "R4=inv8"}, - {10, "R4=inv4"}, - {11, "R4=inv2"}, + {1, "R3_w=inv1"}, + {2, "R3_w=inv2"}, + {3, "R3_w=inv4"}, + {4, "R3_w=inv8"}, + {5, "R3_w=inv16"}, + {6, "R3_w=inv1"}, + {7, "R4_w=inv32"}, + {8, "R4_w=inv16"}, + {9, "R4_w=inv8"}, + {10, "R4_w=inv4"}, + {11, "R4_w=inv2"}, }, }, { @@@ -121,12 -121,12 +121,12 @@@ .matches = { {1, "R1=ctx(id=0,off=0,imm=0)"}, {1, "R10=fp0"}, - {1, "R3=inv4"}, - {2, "R3=inv8"}, - {3, "R3=inv10"}, - {4, "R4=inv8"}, - {5, "R4=inv12"}, - {6, "R4=inv14"}, + {1, "R3_w=inv4"}, + {2, "R3_w=inv8"}, + {3, "R3_w=inv10"}, + {4, "R4_w=inv8"}, + {5, "R4_w=inv12"}, + {6, "R4_w=inv14"}, }, }, { @@@ -143,10 -143,10 +143,10 @@@ .matches = { {1, "R1=ctx(id=0,off=0,imm=0)"}, {1, "R10=fp0"}, - {1, "R3=inv7"}, - {2, "R3=inv7"}, - {3, "R3=inv14"}, - {4, "R3=inv56"}, + {1, "R3_w=inv7"}, + {2, "R3_w=inv7"}, + {3, "R3_w=inv14"}, + {4, "R3_w=inv56"}, }, },

@@@ -185,18 -185,18 +185,18 @@@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { {7, "R0=pkt(id=0,off=8,r=8,imm=0)"}, - {7, "R3=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {8, "R3=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, - {9, "R3=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {10, "R3=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {11, "R3=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {8, "R3_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {9, "R3_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {10, "R3_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {11, "R3_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, {18, "R3=pkt_end(id=0,off=0,imm=0)"}, - {18, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {19, "R4=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"}, - {20, "R4=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, - {21, "R4=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {22, "R4=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {23, "R4=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {18, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {19, "R4_w=inv(id=0,umax_value=8160,var_off=(0x0; 0x1fe0))"}, + {20, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {21, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {22, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {23, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, }, }, { @@@ -217,16 -217,16 +217,16 @@@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {7, "R3=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {8, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {9, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {10, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {11, "R4=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, - {12, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {13, "R4=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, - {14, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {15, "R4=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, - {16, "R4=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, + {7, "R3_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {8, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {9, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {11, "R4_w=inv(id=0,umax_value=510,var_off=(0x0; 0x1fe))"}, + {12, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {13, "R4_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {14, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {15, "R4_w=inv(id=0,umax_value=2040,var_off=(0x0; 0x7f8))"}, + {16, "R4_w=inv(id=0,umax_value=4080,var_off=(0x0; 0xff0))"}, }, }, { @@@ -257,14 -257,14 +257,14 @@@ }, .prog_type = BPF_PROG_TYPE_SCHED_CLS, .matches = { - {4, "R5=pkt(id=0,off=0,r=0,imm=0)"}, - {5, "R5=pkt(id=0,off=14,r=0,imm=0)"}, - {6, "R4=pkt(id=0,off=14,r=0,imm=0)"}, + {4, "R5_w=pkt(id=0,off=0,r=0,imm=0)"}, + {5, "R5_w=pkt(id=0,off=14,r=0,imm=0)"}, + {6, "R4_w=pkt(id=0,off=14,r=0,imm=0)"}, {10, "R2=pkt(id=0,off=0,r=18,imm=0)"}, {10, "R5=pkt(id=0,off=14,r=18,imm=0)"}, - {10, "R4=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, - {14, "R4=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, - {15, "R4=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, + {10, "R4_w=inv(id=0,umax_value=255,var_off=(0x0; 0xff))"}, + {14, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, + {15, "R4_w=inv(id=0,umax_value=65535,var_off=(0x0; 0xffff))"}, }, }, { @@@ -320,11 -320,11 +320,11 @@@ * alignment of 4. */ {8, "R2=pkt(id=0,off=0,r=8,imm=0)"}, - {8, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Offset is added to packet pointer R5, resulting in * known fixed offset, and variable offset from R6. */ - {11, "R5=pkt(id=1,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {11, "R5_w=pkt(id=1,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, * it's total offset is NET_IP_ALIGN + reg->off (0) + * reg->aux_off (14) which is 16. Then the variable @@@ -336,11 -336,11 +336,11 @@@ /* Variable offset is added to R5 packet pointer, * resulting in auxiliary alignment of 4. */ - {18, "R5=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {18, "R5_w=pkt(id=2,off=0,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Constant offset is added to R5, resulting in * reg->off of 14. */ - {19, "R5=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {19, "R5_w=pkt(id=2,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off * (14) which is 16. Then the variable offset is 4-byte @@@ -352,18 -352,18 +352,18 @@@ /* Constant offset is added to R5 packet pointer, * resulting in reg->off value of 14. */ - {26, "R5=pkt(id=0,off=14,r=8"}, + {26, "R5_w=pkt(id=0,off=14,r=8"}, /* Variable offset is added to R5, resulting in a * variable offset of (4n). */ - {27, "R5=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {27, "R5_w=pkt(id=3,off=14,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Constant is added to R5 again, setting reg->off to 18. */ - {28, "R5=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {28, "R5_w=pkt(id=3,off=18,r=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* And once more we add a variable; resulting var_off * is still (4n), fixed offset is not changed. * Also, we create a new reg->id. */ - {29, "R5=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"}, + {29, "R5_w=pkt(id=4,off=18,r=0,umax_value=2040,var_off=(0x0; 0x7fc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (18) * which is 20. Then the variable offset is (4n), so @@@ -410,11 -410,11 +410,11 @@@ * alignment of 4. */ {8, "R2=pkt(id=0,off=0,r=8,imm=0)"}, - {8, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {8, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ - {9, "R6=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {9, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* Packet pointer has (4n+2) offset */ - {11, "R5=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {11, "R5_w=pkt(id=1,off=0,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, {13, "R4=pkt(id=1,off=4,r=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) @@@ -426,11 -426,11 +426,11 @@@ /* Newly read value in R6 was shifted left by 2, so has * known alignment of 4. */ - {18, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {18, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Added (4n) to packet pointer's (4n+2) var_off, giving * another (4n+2). */ - {19, "R5=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, + {19, "R5_w=pkt(id=2,off=0,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, {21, "R4=pkt(id=2,off=4,r=0,umin_value=14,umax_value=2054,var_off=(0x2; 0xffc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) @@@ -473,8 -473,28 +473,8 @@@ .prog_type = BPF_PROG_TYPE_SCHED_CLS, .result = REJECT, .matches = { - {4, "R5=pkt(id=0,off=0,r=0,imm=0)"}, + {4, "R5_w=pkt(id=0,off=0,r=0,imm=0)"}, - /* ptr & 0x40 == either 0 or 0x40 */ - {5, "R5_w=inv(id=0,umax_value=64,var_off=(0x0; 0x40))"}, - /* ptr << 2 == unknown, (4n) */ - {7, "R5_w=inv(id=0,smax_value=9223372036854775804,umax_value=18446744073709551612,var_off=(0x0; 0xfffffffffffffffc))"}, - /* (4n) + 14 == (4n+2). We blow our bounds, because - * the add could overflow. - */ - {8, "R5=inv(id=0,var_off=(0x2; 0xfffffffffffffffc))"}, - /* Checked s>=0 */ - {10, "R5=inv(id=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, - /* packet pointer + nonnegative (4n+2) */ - {12, "R6_w=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, - {14, "R4=pkt(id=1,off=4,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, - /* NET_IP_ALIGN + (4n+2) == (4n), alignment is fine. - * We checked the bounds, but it might have been able - * to overflow if the packet pointer started in the - * upper half of the address space. - * So we did not get a 'range' on R6, and the access - * attempt will fail. - */ - {16, "R6=pkt(id=1,off=0,r=0,umin_value=2,umax_value=9223372036854775806,var_off=(0x2; 0x7ffffffffffffffc))"}, + /* R5 bitwise operator &= on pointer prohibited */ } }, { @@@ -510,11 -530,11 +510,11 @@@ * alignment of 4. */ {7, "R2=pkt(id=0,off=0,r=8,imm=0)"}, - {9, "R6=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {9, "R6_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Adding 14 makes R6 be (4n+2) */ - {10, "R6=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, + {10, "R6_w=inv(id=0,umin_value=14,umax_value=1034,var_off=(0x2; 0x7fc))"}, /* New unknown value in R7 is (4n) */ - {11, "R7=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, + {11, "R7_w=inv(id=0,umax_value=1020,var_off=(0x0; 0x3fc))"}, /* Subtracting it from R6 blows our unsigned bounds */ {12, "R6=inv(id=0,smin_value=-1006,smax_value=1034,var_off=(0x2; 0xfffffffffffffffc))"}, /* Checked s>= 0 */ @@@ -563,15 -583,15 +563,15 @@@ * alignment of 4. */ {7, "R2=pkt(id=0,off=0,r=8,imm=0)"}, - {10, "R6=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"}, + {10, "R6_w=inv(id=0,umax_value=60,var_off=(0x0; 0x3c))"}, /* Adding 14 makes R6 be (4n+2) */ - {11, "R6=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, + {11, "R6_w=inv(id=0,umin_value=14,umax_value=74,var_off=(0x2; 0x7c))"}, /* Subtracting from packet pointer overflows ubounds */ - {13, "R5=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"}, + {13, "R5_w=pkt(id=1,off=0,r=8,umin_value=18446744073709551542,umax_value=18446744073709551602,var_off=(0xffffffffffffff82; 0x7c))"}, /* New unknown value in R7 is (4n), >= 76 */ - {15, "R7=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, + {15, "R7_w=inv(id=0,umin_value=76,umax_value=1096,var_off=(0x0; 0x7fc))"}, /* Adding it to packet pointer gives nice bounds again */ - {16, "R5=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"}, + {16, "R5_w=pkt(id=2,off=0,r=0,umin_value=2,umax_value=1082,var_off=(0x2; 0x7fc))"}, /* At the time the word size load is performed from R5, * its total fixed offset is NET_IP_ALIGN + reg->off (0) * which is 2. Then the variable offset is (4n+2), so