[linux-next] LinuxNextTracking branch, master, updated. next-20180115 - linux-merge - lists.open-mesh.org

15 Jan 2018

The following commit has been merged in the master branch:
commit ecacef38cbf457d8b80c9c12d832ec2c4fe93c66
Merge: ef883292251b86a627aa3ffc889523738c328cb5 564737f981fb4b4b3266901508bb9b90d9d43de8
Author: Stephen Rothwell sfr@canb.auug.org.au
Date:   Mon Jan 15 10:50:56 2018 +1100
Merge remote-tracking branch 'net-next/master'
diff --combined MAINTAINERS
index 4d875d6bf6ca,e22ca0ae995d..c6ef4753ae36

--- 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/
@@@ -2682,7 -2688,6 +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 -2698,6 +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 -2722,16 +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 -2835,6 +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
@@@ -4936,6 -4942,11 +4939,11 @@@ S:	Maintaine
  F:	lib/dynamic_debug.c
  F:	include/linux/dynamic_debug.h
+ DYNAMIC INTERRUPT MODERATION
+ M:	Tal Gilboa talgi@mellanox.com
+ S:	Maintained
+ F:	include/linux/net_dim.h
+ 
  DZ DECSTATION DZ11 SERIAL DRIVER
  M:	"Maciej W. Rozycki" macro@linux-mips.org
  S:	Maintained
@@@ -7070,14 -7081,6 +7078,14 @@@ 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 -8686,6 +8691,15 @@@ 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 -8729,13 +8743,13 @@@ 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 -9108,6 +9122,7 @@@ 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 -9135,6 +9150,25 @@@ 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 -9612,11 +9646,11 @@@ 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
@@@ -9672,8 -9658,8 +9692,8 @@@ F:	include/uapi/linux/sunrpc
  NILFS2 FILESYSTEM
  M:	Ryusuke Konishi konishi.ryusuke@lab.ntt.co.jp
  L:	linux-nilfs@vger.kernel.org
 -W:	http://nilfs.sourceforge.net/
 -W:	http://nilfs.osdn.jp/
 +W:	https://nilfs.sourceforge.io/
 +W:	https://nilfs.osdn.jp/
  T:	git git://github.com/konis/nilfs2.git
  S:	Supported
  F:	Documentation/filesystems/nilfs2.txt
@@@ -10085,14 -10071,6 +10105,14 @@@ 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
@@@ -10591,12 -10569,8 +10611,12 @@@ 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 -10909,6 +10955,7 @@@ 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 -12356,6 +12403,14 @@@ 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
@@@ -12670,15 -12635,6 +12690,15 @@@ L:	linux-media@vger.kernel.or
  S:	Supported
  F:	drivers/media/pci/solo6x10/
+SOFTWARE DELEGATED EXCEPTION INTERFACE (SDEI)
 +M:	James Morse james.morse@arm.com
 +L:	linux-arm-kernel@lists.infradead.org
 +S:	Maintained
 +F:	Documentation/devicetree/bindings/arm/firmware/sdei.txt
 +F:	drivers/firmware/arm_sdei.c
 +F:	include/linux/sdei.h
 +F:	include/uapi/linux/sdei.h
 +
  SOFTWARE RAID (Multiple Disks) SUPPORT
  M:	Shaohua Li shli@kernel.org
  L:	linux-raid@vger.kernel.org
@@@ -12691,6 -12647,13 +12711,13 @@@ F:	drivers/md/raid
  F:	include/linux/raid/
  F:	include/uapi/linux/raid/
+ SOCIONEXT (SNI) NETSEC NETWORK DRIVER
+ M:	Jassi Brar jaswinder.singh@linaro.org
+ L:	netdev@vger.kernel.org
+ S:	Maintained
+ F:	drivers/net/ethernet/socionext/netsec.c
+ F:	Documentation/devicetree/bindings/net/socionext-netsec.txt
+ 
  SONIC NETWORK DRIVER
  M:	Thomas Bogendoerfer tsbogend@alpha.franken.de
  L:	netdev@vger.kernel.org
@@@ -12930,6 -12893,12 +12957,6 @@@ 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
@@@ -13311,15 -13280,6 +13338,15 @@@ 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
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 bf15dc27ca53,7bb402d3e9d0..499f41a2c6f0
--- a/arch/arm/boot/dts/ls1021a-qds.dts
+++ b/arch/arm/boot/dts/ls1021a-qds.dts
@@@ -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 b186c370ad54,860b898141f0..f0c949d74833
--- a/arch/arm/boot/dts/ls1021a-twr.dts
+++ b/arch/arm/boot/dts/ls1021a-twr.dts
@@@ -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 arch/x86/Kconfig
index 20da391b5f32,45dc6233f2b9..c98fc6715852
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@@ -55,6 -55,7 +55,6 @@@ config X8
    select ARCH_HAS_GCOV_PROFILE_ALL
    select ARCH_HAS_KCOV			if X86_64
    select ARCH_HAS_PMEM_API		if X86_64
 -	# Causing hangs/crashes, see the commit that added this change for details.
    select ARCH_HAS_REFCOUNT
    select ARCH_HAS_UACCESS_FLUSHCACHE	if X86_64
    select ARCH_HAS_SET_MEMORY
@@@ -88,7 -89,6 +88,7 @@@
    select GENERIC_CLOCKEVENTS_MIN_ADJUST
    select GENERIC_CMOS_UPDATE
    select GENERIC_CPU_AUTOPROBE
 +	select GENERIC_CPU_VULNERABILITIES
    select GENERIC_EARLY_IOREMAP
    select GENERIC_FIND_FIRST_BIT
    select GENERIC_IOMAP
@@@ -154,6 -154,7 +154,7 @@@
    select HAVE_KERNEL_XZ
    select HAVE_KPROBES
    select HAVE_KPROBES_ON_FTRACE
+ 	select HAVE_KPROBE_OVERRIDE
    select HAVE_KRETPROBES
    select HAVE_KVM
    select HAVE_LIVEPATCH			if X86_64
@@@ -429,19 -430,6 +430,19 @@@ config GOLDFIS
         def_bool y
         depends on X86_GOLDFISH
+config RETPOLINE
 +	bool "Avoid speculative indirect branches in kernel"
 +	default y
 +	help
 +	  Compile kernel with the retpoline compiler options to guard against
 +	  kernel-to-user data leaks by avoiding speculative indirect
 +	  branches. Requires a compiler with -mindirect-branch=thunk-extern
 +	  support for full protection. The kernel may run slower.
 +
 +	  Without compiler support, at least indirect branches in assembler
 +	  code are eliminated. Since this includes the syscall entry path,
 +	  it is not entirely pointless.
 +
  config INTEL_RDT
    bool "Intel Resource Director Technology support"
    default n
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/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/mellanox/mlx5/core/en.h
index c2d89bfa1a70,d629da213511..7b988595ac5f
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@@ -46,6 -46,8 +46,8 @@@
  #include <linux/mlx5/transobj.h>
  #include <linux/rhashtable.h>
  #include <net/switchdev.h>
+ #include <net/xdp.h>
+ #include <linux/net_dim.h>
  #include "wq.h"
  #include "mlx5_core.h"
  #include "en_stats.h"
@@@ -226,12 -228,6 +228,6 @@@ enum mlx5e_priv_flag 
  #define MLX5E_MAX_BW_ALLOC 100 /* Max percentage of BW allocation */
  #endif
- struct mlx5e_cq_moder {
- 	u16 usec;
- 	u16 pkts;
- 	u8 cq_period_mode;
- };
- 
  struct mlx5e_params {
    u8  log_sq_size;
    u8  rq_wq_type;
@@@ -242,8 -238,8 +238,8 @@@
    u16 num_channels;
    u8  num_tc;
    bool rx_cqe_compress_def;
- 	struct mlx5e_cq_moder rx_cq_moderation;
- 	struct mlx5e_cq_moder tx_cq_moderation;
+ 	struct net_dim_cq_moder rx_cq_moderation;
+ 	struct net_dim_cq_moder tx_cq_moderation;
    bool lro_en;
    u32 lro_wqe_sz;
    u16 tx_max_inline;
@@@ -253,7 -249,7 +249,7 @@@
    u32 indirection_rqt[MLX5E_INDIR_RQT_SIZE];
    bool vlan_strip_disable;
    bool scatter_fcs_en;
- 	bool rx_am_enabled;
+ 	bool rx_dim_enabled;
    u32 lro_timeout;
    u32 pflags;
    struct bpf_prog *xdp_prog;
@@@ -472,32 -468,6 +468,6 @@@ struct mlx5e_mpw_info 
    u16 skbs_frags[MLX5_MPWRQ_PAGES_PER_WQE];
  };
- struct mlx5e_rx_am_stats {
- 	int ppms; /* packets per msec */
- 	int bpms; /* bytes per msec */
- 	int epms; /* events per msec */
- };
- 
- struct mlx5e_rx_am_sample {
- 	ktime_t	time;
- 	u32	pkt_ctr;
- 	u32	byte_ctr;
- 	u16	event_ctr;
- };
- 
- struct mlx5e_rx_am { /* Adaptive Moderation */
- 	u8					state;
- 	struct mlx5e_rx_am_stats		prev_stats;
- 	struct mlx5e_rx_am_sample		start_sample;
- 	struct work_struct			work;
- 	u8					profile_ix;
- 	u8					mode;
- 	u8					tune_state;
- 	u8					steps_right;
- 	u8					steps_left;
- 	u8					tired;
- };
- 
  /* a single cache unit is capable to serve one napi call (for non-striding rq)
   * or a MPWQE (for striding rq).
   */
@@@ -558,7 -528,7 +528,7 @@@ struct mlx5e_rq 
    unsigned long          state;
    int                    ix;
- 	struct mlx5e_rx_am     am; /* Adaptive Moderation */
+ 	struct net_dim         dim; /* Dynamic Interrupt Moderation */
/* XDP */
    struct bpf_prog       *xdp_prog;
@@@ -571,6 -541,9 +541,9 @@@
    u32                    rqn;
    struct mlx5_core_dev  *mdev;
    struct mlx5_core_mkey  umr_mkey;
+ 
+ 	/* XDP read-mostly */
+ 	struct xdp_rxq_info    xdp_rxq;
  } ____cacheline_aligned_in_smp;
struct mlx5e_channel {
@@@ -655,6 -628,7 +628,7 @@@ struct mlx5e_tc_table 
    struct rhashtable               ht;
DECLARE_HASHTABLE(mod_hdr_tbl, 8);
+ 	DECLARE_HASHTABLE(hairpin_tbl, 8);
  };
struct mlx5e_vlan_table {
@@@ -860,10 -834,6 +834,6 @@@ void mlx5e_dealloc_rx_wqe(struct mlx5e_
  void mlx5e_dealloc_rx_mpwqe(struct mlx5e_rq *rq, u16 ix);
  void mlx5e_free_rx_mpwqe(struct mlx5e_rq *rq, struct mlx5e_mpw_info *wi);
- void mlx5e_rx_am(struct mlx5e_rq *rq);
- void mlx5e_rx_am_work(struct work_struct *work);
- struct mlx5e_cq_moder mlx5e_am_get_def_profile(u8 rx_cq_period_mode);
- 
  void mlx5e_update_stats(struct mlx5e_priv *priv, bool full);
int mlx5e_create_flow_steering(struct mlx5e_priv *priv);
@@@ -895,7 -865,7 +865,7 @@@ int mlx5e_vlan_rx_kill_vid(struct net_d
    		   u16 vid);
  void mlx5e_enable_cvlan_filter(struct mlx5e_priv *priv);
  void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv);
 -void mlx5e_timestamp_set(struct mlx5e_priv *priv);
 +void mlx5e_timestamp_init(struct mlx5e_priv *priv);
struct mlx5e_redirect_rqt_param {
    bool is_rss;
@@@ -1110,4 -1080,5 +1080,5 @@@ void mlx5e_build_nic_params(struct mlx5
    		    struct mlx5e_params *params,
    		    u16 max_channels);
  u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev);
+ void mlx5e_rx_dim_work(struct work_struct *work);
  #endif /* __MLX5_EN_H__ */
diff --combined drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index ea5fff2c3143,bd5af7f37198..2d1395015ab5
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@@ -207,7 -207,8 +207,7 @@@ void mlx5e_ethtool_get_ethtool_stats(st
    	return;
mutex_lock(&priv->state_lock);
 -	if (test_bit(MLX5E_STATE_OPENED, &priv->state))
 -		mlx5e_update_stats(priv, true);
 +	mlx5e_update_stats(priv, true);
    mutex_unlock(&priv->state_lock);
for (i = 0; i < mlx5e_num_stats_grps; i++)
@@@ -295,7 -296,6 +295,6 @@@ int mlx5e_ethtool_set_ringparam(struct 
    struct mlx5e_channels new_channels = {};
    u32 rx_pending_wqes;
    u32 min_rq_size;
- 	u32 max_rq_size;
    u8 log_rq_size;
    u8 log_sq_size;
    u32 num_mtts;
@@@ -314,8 -314,6 +313,6 @@@
min_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
    				       1 << mlx5_min_log_rq_size(rq_wq_type));
- 	max_rq_size = mlx5e_rx_wqes_to_packets(priv, rq_wq_type,
- 					       1 << mlx5_max_log_rq_size(rq_wq_type));
    rx_pending_wqes = mlx5e_packets_to_rx_wqes(priv, rq_wq_type,
    					   param->rx_pending);
@@@ -325,12 -323,6 +322,6 @@@
    		    min_rq_size);
    	return -EINVAL;
    }
- 	if (param->rx_pending > max_rq_size) {
- 		netdev_info(priv->netdev, "%s: rx_pending (%d) > max (%d)\n",
- 			    __func__, param->rx_pending,
- 			    max_rq_size);
- 		return -EINVAL;
- 	}
num_mtts = MLX5E_REQUIRED_MTTS(rx_pending_wqes);
    if (priv->channels.params.rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ &&
@@@ -346,12 -338,6 +337,6 @@@
    		    1 << MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE);
    	return -EINVAL;
    }
- 	if (param->tx_pending > (1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE)) {
- 		netdev_info(priv->netdev, "%s: tx_pending (%d) > max (%d)\n",
- 			    __func__, param->tx_pending,
- 			    1 << MLX5E_PARAMS_MAXIMUM_LOG_SQ_SIZE);
- 		return -EINVAL;
- 	}
log_rq_size = order_base_2(rx_pending_wqes);
    log_sq_size = order_base_2(param->tx_pending);
@@@ -479,7 -465,7 +464,7 @@@ int mlx5e_ethtool_get_coalesce(struct m
    coal->rx_max_coalesced_frames = priv->channels.params.rx_cq_moderation.pkts;
    coal->tx_coalesce_usecs       = priv->channels.params.tx_cq_moderation.usec;
    coal->tx_max_coalesced_frames = priv->channels.params.tx_cq_moderation.pkts;
- 	coal->use_adaptive_rx_coalesce = priv->channels.params.rx_am_enabled;
+ 	coal->use_adaptive_rx_coalesce = priv->channels.params.rx_dim_enabled;
return 0;
  }
@@@ -533,7 -519,7 +518,7 @@@ int mlx5e_ethtool_set_coalesce(struct m
    new_channels.params.tx_cq_moderation.pkts = coal->tx_max_coalesced_frames;
    new_channels.params.rx_cq_moderation.usec = coal->rx_coalesce_usecs;
    new_channels.params.rx_cq_moderation.pkts = coal->rx_max_coalesced_frames;
- 	new_channels.params.rx_am_enabled         = !!coal->use_adaptive_rx_coalesce;
+ 	new_channels.params.rx_dim_enabled        = !!coal->use_adaptive_rx_coalesce;
if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) {
    	priv->channels.params = new_channels.params;
@@@ -541,7 -527,7 +526,7 @@@
    }
    /* we are opened */
- 	reset = !!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_am_enabled;
+ 	reset = !!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled;
    if (!reset) {
    	mlx5e_set_priv_channels_coalesce(priv, coal);
    	priv->channels.params = new_channels.params;
diff --combined drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index d8aefeed124d,bbbdb5c0086b..466a4e1244d7
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@@ -582,6 -582,10 +582,10 @@@ static int mlx5e_alloc_rq(struct mlx5e_
    	goto err_rq_wq_destroy;
    }
+ 	err = xdp_rxq_info_reg(&rq->xdp_rxq, rq->netdev, rq->ix);
+ 	if (err < 0)
+ 		goto err_rq_wq_destroy;
+ 
    rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE;
    rq->buff.headroom = params->rq_headroom;
@@@ -674,8 -678,17 +678,17 @@@
    	wqe->data.lkey = rq->mkey_be;
    }
- 	INIT_WORK(&rq->am.work, mlx5e_rx_am_work);
- 	rq->am.mode = params->rx_cq_moderation.cq_period_mode;
+ 	INIT_WORK(&rq->dim.work, mlx5e_rx_dim_work);
+ 
+ 	switch (params->rx_cq_moderation.cq_period_mode) {
+ 	case MLX5_CQ_PERIOD_MODE_START_FROM_CQE:
+ 		rq->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE;
+ 		break;
+ 	case MLX5_CQ_PERIOD_MODE_START_FROM_EQE:
+ 	default:
+ 		rq->dim.mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
+ 	}
+ 
    rq->page_cache.head = 0;
    rq->page_cache.tail = 0;
@@@ -687,6 -700,7 +700,7 @@@ err_destroy_umr_mkey
  err_rq_wq_destroy:
    if (rq->xdp_prog)
    	bpf_prog_put(rq->xdp_prog);
+ 	xdp_rxq_info_unreg(&rq->xdp_rxq);
    mlx5_wq_destroy(&rq->wq_ctrl);
return err;
@@@ -699,6 -713,8 +713,8 @@@ static void mlx5e_free_rq(struct mlx5e_
    if (rq->xdp_prog)
    	bpf_prog_put(rq->xdp_prog);
+ 	xdp_rxq_info_unreg(&rq->xdp_rxq);
+ 
    switch (rq->wq_type) {
    case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ:
    	mlx5e_rq_free_mpwqe_info(rq);
@@@ -919,7 -935,7 +935,7 @@@ static int mlx5e_open_rq(struct mlx5e_c
    if (err)
    	goto err_destroy_rq;
- 	if (params->rx_am_enabled)
+ 	if (params->rx_dim_enabled)
    	c->rq.state |= BIT(MLX5E_RQ_STATE_AM);
return 0;
@@@ -952,7 -968,7 +968,7 @@@ static void mlx5e_deactivate_rq(struct
static void mlx5e_close_rq(struct mlx5e_rq *rq)
  {
- 	cancel_work_sync(&rq->am.work);
+ 	cancel_work_sync(&rq->dim.work);
    mlx5e_destroy_rq(rq);
    mlx5e_free_rx_descs(rq);
    mlx5e_free_rq(rq);
@@@ -1565,7 -1581,7 +1581,7 @@@ static void mlx5e_destroy_cq(struct mlx
  }
static int mlx5e_open_cq(struct mlx5e_channel *c,
- 			 struct mlx5e_cq_moder moder,
+ 			 struct net_dim_cq_moder moder,
    		 struct mlx5e_cq_param *param,
    		 struct mlx5e_cq *cq)
  {
@@@ -1747,7 -1763,7 +1763,7 @@@ static int mlx5e_open_channel(struct ml
    		      struct mlx5e_channel_param *cparam,
    		      struct mlx5e_channel **cp)
  {
- 	struct mlx5e_cq_moder icocq_moder = {0, 0};
+ 	struct net_dim_cq_moder icocq_moder = {0, 0};
    struct net_device *netdev = priv->netdev;
    int cpu = mlx5e_get_cpu(priv, ix);
    struct mlx5e_channel *c;
@@@ -1999,7 -2015,7 +2015,7 @@@ static void mlx5e_build_ico_cq_param(st
mlx5e_build_common_cq_param(priv, param);
- 	param->cq_period_mode = MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
+ 	param->cq_period_mode = NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE;
  }
static void mlx5e_build_icosq_param(struct mlx5e_priv *priv,
@@@ -2669,7 -2685,7 +2685,7 @@@ void mlx5e_switch_priv_channels(struct 
    	netif_carrier_on(netdev);
  }
-void mlx5e_timestamp_set(struct mlx5e_priv *priv)
 +void mlx5e_timestamp_init(struct mlx5e_priv *priv)
  {
    priv->tstamp.tx_type   = HWTSTAMP_TX_OFF;
    priv->tstamp.rx_filter = HWTSTAMP_FILTER_NONE;
@@@ -2690,6 -2706,7 +2706,6 @@@ int mlx5e_open_locked(struct net_devic
    mlx5e_activate_priv_channels(priv);
    if (priv->profile->update_carrier)
    	priv->profile->update_carrier(priv);
 -	mlx5e_timestamp_set(priv);
if (priv->profile->update_stats)
    	queue_delayed_work(priv->wq, &priv->update_stats_work, 0);
@@@ -2765,6 -2782,9 +2781,9 @@@ static int mlx5e_alloc_drop_rq(struct m
    if (err)
    	return err;
+ 	/* Mark as unused given "Drop-RQ" packets never reach XDP */
+ 	xdp_rxq_info_unused(&rq->xdp_rxq);
+ 
    rq->mdev = mdev;
return 0;
@@@ -3218,12 -3238,12 +3237,12 @@@ static int mlx5e_set_mac(struct net_dev
    return 0;
  }
-#define MLX5E_SET_FEATURE(netdev, feature, enable)	\
 +#define MLX5E_SET_FEATURE(features, feature, enable)	\
    do {						\
    	if (enable)				\
 -			netdev->features |= feature;	\
 +			*features |= feature;		\
    	else					\
 -			netdev->features &= ~feature;	\
 +			*features &= ~feature;		\
    } while (0)
typedef int (*mlx5e_feature_handler)(struct net_device *netdev, bool enable);
@@@ -3346,7 -3366,6 +3365,7 @@@ static int set_feature_arfs(struct net_
  #endif
static int mlx5e_handle_feature(struct net_device *netdev,
 +				netdev_features_t *features,
    			netdev_features_t wanted_features,
    			netdev_features_t feature,
    			mlx5e_feature_handler feature_handler)
@@@ -3365,40 -3384,34 +3384,40 @@@
    	return err;
    }
-	MLX5E_SET_FEATURE(netdev, feature, enable);
 +	MLX5E_SET_FEATURE(features, feature, enable);
    return 0;
  }
static int mlx5e_set_features(struct net_device *netdev,
    		      netdev_features_t features)
  {
 +	netdev_features_t oper_features = netdev->features;
    int err;
-	err  = mlx5e_handle_feature(netdev, features, NETIF_F_LRO,
 -				    set_feature_lro);
 -	err |= mlx5e_handle_feature(netdev, features,
 +	err  = mlx5e_handle_feature(netdev, &oper_features, features,
 +				    NETIF_F_LRO, set_feature_lro);
 +	err |= mlx5e_handle_feature(netdev, &oper_features, features,
    			    NETIF_F_HW_VLAN_CTAG_FILTER,
    			    set_feature_cvlan_filter);
 -	err |= mlx5e_handle_feature(netdev, features, NETIF_F_HW_TC,
 -				    set_feature_tc_num_filters);
 -	err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXALL,
 -				    set_feature_rx_all);
 -	err |= mlx5e_handle_feature(netdev, features, NETIF_F_RXFCS,
 -				    set_feature_rx_fcs);
 -	err |= mlx5e_handle_feature(netdev, features, NETIF_F_HW_VLAN_CTAG_RX,
 -				    set_feature_rx_vlan);
 +	err |= mlx5e_handle_feature(netdev, &oper_features, features,
 +				    NETIF_F_HW_TC, set_feature_tc_num_filters);
 +	err |= mlx5e_handle_feature(netdev, &oper_features, features,
 +				    NETIF_F_RXALL, set_feature_rx_all);
 +	err |= mlx5e_handle_feature(netdev, &oper_features, features,
 +				    NETIF_F_RXFCS, set_feature_rx_fcs);
 +	err |= mlx5e_handle_feature(netdev, &oper_features, features,
 +				    NETIF_F_HW_VLAN_CTAG_RX, set_feature_rx_vlan);
  #ifdef CONFIG_RFS_ACCEL
 -	err |= mlx5e_handle_feature(netdev, features, NETIF_F_NTUPLE,
 -				    set_feature_arfs);
 +	err |= mlx5e_handle_feature(netdev, &oper_features, features,
 +				    NETIF_F_NTUPLE, set_feature_arfs);
  #endif
-	return err ? -EINVAL : 0;
 +	if (err) {
 +		netdev->features = oper_features;
 +		return -EINVAL;
 +	}
 +
 +	return 0;
  }
static netdev_features_t mlx5e_fix_features(struct net_device *netdev,
@@@ -4044,9 -4057,18 +4063,18 @@@ void mlx5e_set_rx_cq_mode_params(struc
    	params->rx_cq_moderation.usec =
    		MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE;
- 	if (params->rx_am_enabled)
- 		params->rx_cq_moderation =
- 			mlx5e_am_get_def_profile(cq_period_mode);
+ 	if (params->rx_dim_enabled) {
+ 		switch (cq_period_mode) {
+ 		case MLX5_CQ_PERIOD_MODE_START_FROM_CQE:
+ 			params->rx_cq_moderation =
+ 				net_dim_get_def_profile(NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE);
+ 			break;
+ 		case MLX5_CQ_PERIOD_MODE_START_FROM_EQE:
+ 		default:
+ 			params->rx_cq_moderation =
+ 				net_dim_get_def_profile(NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE);
+ 		}
+ 	}
MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER,
    		params->rx_cq_moderation.cq_period_mode ==
@@@ -4108,7 -4130,7 +4136,7 @@@ void mlx5e_build_nic_params(struct mlx5
    cq_period_mode = MLX5_CAP_GEN(mdev, cq_period_start_from_cqe) ?
    		MLX5_CQ_PERIOD_MODE_START_FROM_CQE :
    		MLX5_CQ_PERIOD_MODE_START_FROM_EQE;
- 	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+ 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
    mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
    mlx5e_set_tx_cq_mode_params(params, cq_period_mode);
@@@ -4145,8 -4167,6 +4173,8 @@@ static void mlx5e_build_nic_netdev_priv
    INIT_WORK(&priv->set_rx_mode_work, mlx5e_set_rx_mode_work);
    INIT_WORK(&priv->tx_timeout_work, mlx5e_tx_timeout_work);
    INIT_DELAYED_WORK(&priv->update_stats_work, mlx5e_update_stats_work);
 +
 +	mlx5e_timestamp_init(priv);
  }
static void mlx5e_set_netdev_dev_addr(struct net_device *netdev)
@@@ -4315,9 -4335,6 +4343,6 @@@ static void mlx5e_nic_cleanup(struct ml
  {
    mlx5e_ipsec_cleanup(priv);
    mlx5e_vxlan_cleanup(priv);
- 
- 	if (priv->channels.params.xdp_prog)
- 		bpf_prog_put(priv->channels.params.xdp_prog);
  }
static int mlx5e_init_nic_rx(struct mlx5e_priv *priv)
diff --combined drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
index 3409d86eb06b,4d1b0ff4b6e4..10fa6a18fcf9
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c
@@@ -190,6 -190,63 +190,63 @@@ int mlx5e_attr_get(struct net_device *d
    return 0;
  }
+ static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw,
+ 				 struct mlx5_eswitch_rep *rep)
+ {
+ 	struct mlx5e_rep_sq *rep_sq, *tmp;
+ 	struct mlx5e_rep_priv *rpriv;
+ 
+ 	if (esw->mode != SRIOV_OFFLOADS)
+ 		return;
+ 
+ 	rpriv = mlx5e_rep_to_rep_priv(rep);
+ 	list_for_each_entry_safe(rep_sq, tmp, &rpriv->vport_sqs_list, list) {
+ 		mlx5_eswitch_del_send_to_vport_rule(rep_sq->send_to_vport_rule);
+ 		list_del(&rep_sq->list);
+ 		kfree(rep_sq);
+ 	}
+ }
+ 
+ static int mlx5e_sqs2vport_start(struct mlx5_eswitch *esw,
+ 				 struct mlx5_eswitch_rep *rep,
+ 				 u16 *sqns_array, int sqns_num)
+ {
+ 	struct mlx5_flow_handle *flow_rule;
+ 	struct mlx5e_rep_priv *rpriv;
+ 	struct mlx5e_rep_sq *rep_sq;
+ 	int err;
+ 	int i;
+ 
+ 	if (esw->mode != SRIOV_OFFLOADS)
+ 		return 0;
+ 
+ 	rpriv = mlx5e_rep_to_rep_priv(rep);
+ 	for (i = 0; i < sqns_num; i++) {
+ 		rep_sq = kzalloc(sizeof(*rep_sq), GFP_KERNEL);
+ 		if (!rep_sq) {
+ 			err = -ENOMEM;
+ 			goto out_err;
+ 		}
+ 
+ 		/* Add re-inject rule to the PF/representor sqs */
+ 		flow_rule = mlx5_eswitch_add_send_to_vport_rule(esw,
+ 								rep->vport,
+ 								sqns_array[i]);
+ 		if (IS_ERR(flow_rule)) {
+ 			err = PTR_ERR(flow_rule);
+ 			kfree(rep_sq);
+ 			goto out_err;
+ 		}
+ 		rep_sq->send_to_vport_rule = flow_rule;
+ 		list_add(&rep_sq->list, &rpriv->vport_sqs_list);
+ 	}
+ 	return 0;
+ 
+ out_err:
+ 	mlx5e_sqs2vport_stop(esw, rep);
+ 	return err;
+ }
+ 
  int mlx5e_add_sqs_fwd_rules(struct mlx5e_priv *priv)
  {
    struct mlx5_eswitch *esw = priv->mdev->priv.eswitch;
@@@ -210,7 -267,7 +267,7 @@@
    		sqs[num_sqs++] = c->sq[tc].sqn;
    }
- 	err = mlx5_eswitch_sqs2vport_start(esw, rep, sqs, num_sqs);
+ 	err = mlx5e_sqs2vport_start(esw, rep, sqs, num_sqs);
    kfree(sqs);
out:
@@@ -225,7 -282,7 +282,7 @@@ void mlx5e_remove_sqs_fwd_rules(struct 
    struct mlx5e_rep_priv *rpriv = priv->ppriv;
    struct mlx5_eswitch_rep *rep = rpriv->rep;
- 	mlx5_eswitch_sqs2vport_stop(esw, rep);
+ 	mlx5e_sqs2vport_stop(esw, rep);
  }
static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv)
@@@ -238,7 -295,7 +295,7 @@@
  #endif
    unsigned long ipv4_interval = NEIGH_VAR(&arp_tbl.parms,
    					DELAY_PROBE_TIME);
- 	struct net_device *netdev = rpriv->rep->netdev;
+ 	struct net_device *netdev = rpriv->netdev;
    struct mlx5e_priv *priv = netdev_priv(netdev);
rpriv->neigh_update.min_interval = min_t(unsigned long, ipv6_interval, ipv4_interval);
@@@ -259,7 -316,7 +316,7 @@@ static void mlx5e_rep_neigh_stats_work(
  {
    struct mlx5e_rep_priv *rpriv = container_of(work, struct mlx5e_rep_priv,
    					    neigh_update.neigh_stats_work.work);
- 	struct net_device *netdev = rpriv->rep->netdev;
+ 	struct net_device *netdev = rpriv->netdev;
    struct mlx5e_priv *priv = netdev_priv(netdev);
    struct mlx5e_neigh_hash_entry *nhe;
@@@ -355,7 -412,7 +412,7 @@@ static int mlx5e_rep_netevent_event(str
    struct mlx5e_rep_priv *rpriv = container_of(nb, struct mlx5e_rep_priv,
    					    neigh_update.netevent_nb);
    struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
- 	struct net_device *netdev = rpriv->rep->netdev;
+ 	struct net_device *netdev = rpriv->netdev;
    struct mlx5e_priv *priv = netdev_priv(netdev);
    struct mlx5e_neigh_hash_entry *nhe = NULL;
    struct mlx5e_neigh m_neigh = {};
@@@ -483,7 -540,7 +540,7 @@@ out_err
  static void mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv)
  {
    struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update;
- 	struct mlx5e_priv *priv = netdev_priv(rpriv->rep->netdev);
+ 	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
unregister_netevent_notifier(&neigh_update->netevent_nb);
@@@ -827,7 -884,7 +884,7 @@@ static void mlx5e_build_rep_params(stru
    params->rq_wq_type  = MLX5_WQ_TYPE_LINKED_LIST;
    params->log_rq_size = MLX5E_PARAMS_MINIMUM_LOG_RQ_SIZE;
- 	params->rx_am_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
+ 	params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation);
    mlx5e_set_rx_cq_mode_params(params, cq_period_mode);
params->tx_max_inline         = mlx5e_get_max_inline_cap(mdev);
@@@ -877,8 -934,6 +934,8 @@@ static void mlx5e_init_rep(struct mlx5_
mlx5e_build_rep_params(mdev, &priv->channels.params);
    mlx5e_build_rep_netdev(netdev);
 +
 +	mlx5e_timestamp_init(priv);
  }
static int mlx5e_init_rep_rx(struct mlx5e_priv *priv)
@@@ -906,7 -961,7 +963,7 @@@
    	err = PTR_ERR(flow_rule);
    	goto err_destroy_direct_tirs;
    }
- 	rep->vport_rx_rule = flow_rule;
+ 	rpriv->vport_rx_rule = flow_rule;
err = mlx5e_tc_init(priv);
    if (err)
@@@ -915,7 -970,7 +972,7 @@@
    return 0;
err_del_flow_rule:
- 	mlx5_del_flow_rules(rep->vport_rx_rule);
+ 	mlx5_del_flow_rules(rpriv->vport_rx_rule);
  err_destroy_direct_tirs:
    mlx5e_destroy_direct_tirs(priv);
  err_destroy_direct_rqts:
@@@ -926,10 -981,9 +983,9 @@@
  static void mlx5e_cleanup_rep_rx(struct mlx5e_priv *priv)
  {
    struct mlx5e_rep_priv *rpriv = priv->ppriv;
- 	struct mlx5_eswitch_rep *rep = rpriv->rep;
mlx5e_tc_cleanup(priv);
- 	mlx5_del_flow_rules(rep->vport_rx_rule);
+ 	mlx5_del_flow_rules(rpriv->vport_rx_rule);
    mlx5e_destroy_direct_tirs(priv);
    mlx5e_destroy_direct_rqts(priv);
  }
@@@ -969,10 -1023,10 +1025,10 @@@ static const struct mlx5e_profile mlx5e
  /* e-Switch vport representors */
static int
- mlx5e_nic_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+ mlx5e_nic_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
  {
- 	struct mlx5e_priv *priv = netdev_priv(rep->netdev);
- 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+ 	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
+ 	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
int err;
@@@ -994,10 -1048,10 +1050,10 @@@ err_remove_sqs
  }
static void
- mlx5e_nic_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+ mlx5e_nic_rep_unload(struct mlx5_eswitch_rep *rep)
  {
- 	struct mlx5e_priv *priv = netdev_priv(rep->netdev);
- 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+ 	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
+ 	struct mlx5e_priv *priv = netdev_priv(rpriv->netdev);
if (test_bit(MLX5E_STATE_OPENED, &priv->state))
    	mlx5e_remove_sqs_fwd_rules(priv);
@@@ -1010,8 -1064,9 +1066,9 @@@
  }
static int
- mlx5e_vport_rep_load(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+ mlx5e_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
  {
+ 	struct mlx5e_rep_priv *uplink_rpriv;
    struct mlx5e_rep_priv *rpriv;
    struct net_device *netdev;
    struct mlx5e_priv *upriv;
@@@ -1021,7 -1076,7 +1078,7 @@@
    if (!rpriv)
    	return -ENOMEM;
- 	netdev = mlx5e_create_netdev(esw->dev, &mlx5e_rep_profile, rpriv);
+ 	netdev = mlx5e_create_netdev(dev, &mlx5e_rep_profile, rpriv);
    if (!netdev) {
    	pr_warn("Failed to create representor netdev for vport %d\n",
    		rep->vport);
@@@ -1029,8 -1084,10 +1086,10 @@@
    	return -EINVAL;
    }
- 	rep->netdev = netdev;
+ 	rpriv->netdev = netdev;
    rpriv->rep = rep;
+ 	rep->rep_if[REP_ETH].priv = rpriv;
+ 	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
err = mlx5e_attach_netdev(netdev_priv(netdev));
    if (err) {
@@@ -1046,7 -1103,8 +1105,8 @@@
    	goto err_detach_netdev;
    }
- 	upriv = netdev_priv(mlx5_eswitch_get_uplink_netdev(esw));
+ 	uplink_rpriv = mlx5_eswitch_get_uplink_priv(dev->priv.eswitch, REP_ETH);
+ 	upriv = netdev_priv(uplink_rpriv->netdev);
    err = tc_setup_cb_egdev_register(netdev, mlx5e_setup_tc_block_cb,
    				 upriv);
    if (err)
@@@ -1078,16 -1136,19 +1138,19 @@@ err_destroy_netdev
  }
static void
- mlx5e_vport_rep_unload(struct mlx5_eswitch *esw, struct mlx5_eswitch_rep *rep)
+ mlx5e_vport_rep_unload(struct mlx5_eswitch_rep *rep)
  {
- 	struct net_device *netdev = rep->netdev;
+ 	struct mlx5e_rep_priv *rpriv = mlx5e_rep_to_rep_priv(rep);
+ 	struct net_device *netdev = rpriv->netdev;
    struct mlx5e_priv *priv = netdev_priv(netdev);
- 	struct mlx5e_rep_priv *rpriv = priv->ppriv;
+ 	struct mlx5e_rep_priv *uplink_rpriv;
    void *ppriv = priv->ppriv;
    struct mlx5e_priv *upriv;
- 	unregister_netdev(rep->netdev);
- 	upriv = netdev_priv(mlx5_eswitch_get_uplink_netdev(esw));
+ 	unregister_netdev(netdev);
+ 	uplink_rpriv = mlx5_eswitch_get_uplink_priv(priv->mdev->priv.eswitch,
+ 						    REP_ETH);
+ 	upriv = netdev_priv(uplink_rpriv->netdev);
    tc_setup_cb_egdev_unregister(netdev, mlx5e_setup_tc_block_cb,
    			     upriv);
    mlx5e_rep_neigh_cleanup(rpriv);
@@@ -1102,18 -1163,13 +1165,13 @@@ static void mlx5e_rep_register_vf_vport
    struct mlx5_eswitch *esw   = mdev->priv.eswitch;
    int total_vfs = MLX5_TOTAL_VPORTS(mdev);
    int vport;
- 	u8 mac[ETH_ALEN];
- 
- 	mlx5_query_nic_vport_mac_address(mdev, 0, mac);
for (vport = 1; vport < total_vfs; vport++) {
- 		struct mlx5_eswitch_rep rep;
+ 		struct mlx5_eswitch_rep_if rep_if = {};
- 		rep.load = mlx5e_vport_rep_load;
- 		rep.unload = mlx5e_vport_rep_unload;
- 		rep.vport = vport;
- 		ether_addr_copy(rep.hw_id, mac);
- 		mlx5_eswitch_register_vport_rep(esw, vport, &rep);
+ 		rep_if.load = mlx5e_vport_rep_load;
+ 		rep_if.unload = mlx5e_vport_rep_unload;
+ 		mlx5_eswitch_register_vport_rep(esw, vport, &rep_if, REP_ETH);
    }
  }
@@@ -1125,21 -1181,24 +1183,24 @@@ static void mlx5e_rep_unregister_vf_vpo
    int vport;
for (vport = 1; vport < total_vfs; vport++)
- 		mlx5_eswitch_unregister_vport_rep(esw, vport);
+ 		mlx5_eswitch_unregister_vport_rep(esw, vport, REP_ETH);
  }
void mlx5e_register_vport_reps(struct mlx5e_priv *priv)
  {
    struct mlx5_core_dev *mdev = priv->mdev;
    struct mlx5_eswitch *esw   = mdev->priv.eswitch;
- 	struct mlx5_eswitch_rep rep;
+ 	struct mlx5_eswitch_rep_if rep_if;
+ 	struct mlx5e_rep_priv *rpriv;
+ 
+ 	rpriv = priv->ppriv;
+ 	rpriv->netdev = priv->netdev;
- 	mlx5_query_nic_vport_mac_address(mdev, 0, rep.hw_id);
- 	rep.load = mlx5e_nic_rep_load;
- 	rep.unload = mlx5e_nic_rep_unload;
- 	rep.vport = FDB_UPLINK_VPORT;
- 	rep.netdev = priv->netdev;
- 	mlx5_eswitch_register_vport_rep(esw, 0, &rep); /* UPLINK PF vport*/
+ 	rep_if.load = mlx5e_nic_rep_load;
+ 	rep_if.unload = mlx5e_nic_rep_unload;
+ 	rep_if.priv = rpriv;
+ 	INIT_LIST_HEAD(&rpriv->vport_sqs_list);
+ 	mlx5_eswitch_register_vport_rep(esw, 0, &rep_if, REP_ETH); /* UPLINK PF vport*/
mlx5e_rep_register_vf_vports(priv); /* VFs vports */
  }
@@@ -1150,7 -1209,7 +1211,7 @@@ void mlx5e_unregister_vport_reps(struc
    struct mlx5_eswitch *esw   = mdev->priv.eswitch;
mlx5e_rep_unregister_vf_vports(priv); /* VFs vports */
- 	mlx5_eswitch_unregister_vport_rep(esw, 0); /* UPLINK PF*/
+ 	mlx5_eswitch_unregister_vport_rep(esw, 0, REP_ETH); /* UPLINK PF*/
  }
void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev)
diff --combined drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
index ee2f378c5030,3b2363e93ba5..ef1e787e6140
--- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c
@@@ -41,7 -41,6 +41,6 @@@
  static int mlx5i_open(struct net_device *netdev);
  static int mlx5i_close(struct net_device *netdev);
  static int mlx5i_change_mtu(struct net_device *netdev, int new_mtu);
- static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd);
static const struct net_device_ops mlx5i_netdev_ops = {
    .ndo_open                = mlx5i_open,
@@@ -86,8 -85,6 +85,8 @@@ void mlx5i_init(struct mlx5_core_dev *m
    mlx5e_build_nic_params(mdev, &priv->channels.params, profile->max_nch(mdev));
    mlx5i_build_nic_params(mdev, &priv->channels.params);
+	mlx5e_timestamp_init(priv);
 +
    /* netdev init */
    netdev->hw_features    |= NETIF_F_SG;
    netdev->hw_features    |= NETIF_F_IP_CSUM;
@@@ -398,7 -395,7 +397,7 @@@ int mlx5i_dev_init(struct net_device *d
    return 0;
  }
- static int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
+ int mlx5i_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
  {
    struct mlx5e_priv *priv = mlx5i_epriv(dev);
@@@ -452,6 -449,7 +451,6 @@@ static int mlx5i_open(struct net_devic
mlx5e_refresh_tirs(epriv, false);
    mlx5e_activate_priv_channels(epriv);
 -	mlx5e_timestamp_set(epriv);
mutex_unlock(&epriv->state_lock);
    return 0;
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,f99f14c35063..cf0e16d1a068
--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
@@@ -2003,22 -2003,60 +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 -2073,7 +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 -2577,7 +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 -3442,8 +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/tap.c
index f39c6f876e67,7c38659b2a76..4f745eb878f3
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@@ -330,7 -330,7 +330,7 @@@ rx_handler_result_t tap_handle_frame(st
    if (!q)
    	return RX_HANDLER_PASS;
- 	if (__skb_array_full(&q->skb_array))
+ 	if (__ptr_ring_full(&q->ring))
    	goto drop;
skb_push(skb, ETH_HLEN);
@@@ -348,7 -348,7 +348,7 @@@
    		goto drop;
if (!segs) {
- 			if (skb_array_produce(&q->skb_array, skb))
+ 			if (ptr_ring_produce(&q->ring, skb))
    			goto drop;
    		goto wake_up;
    	}
@@@ -358,7 -358,7 +358,7 @@@
    		struct sk_buff *nskb = segs->next;
segs->next = NULL;
- 			if (skb_array_produce(&q->skb_array, segs)) {
+ 			if (ptr_ring_produce(&q->ring, segs)) {
    			kfree_skb(segs);
    			kfree_skb_list(nskb);
    			break;
@@@ -375,7 -375,7 +375,7 @@@
    	    !(features & NETIF_F_CSUM_MASK) &&
    	    skb_checksum_help(skb))
    		goto drop;
- 		if (skb_array_produce(&q->skb_array, skb))
+ 		if (ptr_ring_produce(&q->ring, skb))
    		goto drop;
    }
@@@ -497,7 -497,7 +497,7 @@@ static void tap_sock_destruct(struct so
  {
    struct tap_queue *q = container_of(sk, struct tap_queue, sk);
- 	skb_array_cleanup(&q->skb_array);
+ 	ptr_ring_cleanup(&q->ring, __skb_array_destroy_skb);
  }
static int tap_open(struct inode *inode, struct file *file)
@@@ -517,7 -517,7 +517,7 @@@
    				     &tap_proto, 0);
    if (!q)
    	goto err;
- 	if (skb_array_init(&q->skb_array, tap->dev->tx_queue_len, GFP_KERNEL)) {
+ 	if (ptr_ring_init(&q->ring, tap->dev->tx_queue_len, GFP_KERNEL)) {
    	sk_free(&q->sk);
    	goto err;
    }
@@@ -546,7 -546,7 +546,7 @@@
err = tap_set_queue(tap, file, q);
    if (err) {
- 		/* tap_sock_destruct() will take care of freeing skb_array */
+ 		/* tap_sock_destruct() will take care of freeing ptr_ring */
    	goto err_put;
    }
@@@ -572,10 -572,10 +572,10 @@@ static int tap_release(struct inode *in
    return 0;
  }
-static unsigned int tap_poll(struct file *file, poll_table *wait)
 +static __poll_t tap_poll(struct file *file, poll_table *wait)
  {
    struct tap_queue *q = file->private_data;
 -	unsigned int mask = POLLERR;
 +	__poll_t mask = POLLERR;
if (!q)
    	goto out;
@@@ -583,7 -583,7 +583,7 @@@
    mask = 0;
    poll_wait(file, &q->wq.wait, wait);
- 	if (!skb_array_empty(&q->skb_array))
+ 	if (!ptr_ring_empty(&q->ring))
    	mask |= POLLIN | POLLRDNORM;
if (sock_writeable(&q->sk) ||
@@@ -844,7 -844,7 +844,7 @@@ static ssize_t tap_do_read(struct tap_q
    				TASK_INTERRUPTIBLE);
/* Read frames from the queue */
- 		skb = skb_array_consume(&q->skb_array);
+ 		skb = ptr_ring_consume(&q->ring);
    	if (skb)
    		break;
    	if (noblock) {
@@@ -1176,7 -1176,7 +1176,7 @@@ static int tap_peek_len(struct socket *
  {
    struct tap_queue *q = container_of(sock, struct tap_queue,
    				       sock);
- 	return skb_array_peek_len(&q->skb_array);
+ 	return PTR_RING_PEEK_CALL(&q->ring, __skb_array_len_with_tag);
  }
/* Ops structure to mimic raw sockets with tun */
@@@ -1202,7 -1202,7 +1202,7 @@@ struct socket *tap_get_socket(struct fi
  }
  EXPORT_SYMBOL_GPL(tap_get_socket);
- struct skb_array *tap_get_skb_array(struct file *file)
+ struct ptr_ring *tap_get_ptr_ring(struct file *file)
  {
    struct tap_queue *q;
@@@ -1211,29 -1211,30 +1211,30 @@@
    q = file->private_data;
    if (!q)
    	return ERR_PTR(-EBADFD);
- 	return &q->skb_array;
+ 	return &q->ring;
  }
- EXPORT_SYMBOL_GPL(tap_get_skb_array);
+ EXPORT_SYMBOL_GPL(tap_get_ptr_ring);
int tap_queue_resize(struct tap_dev *tap)
  {
    struct net_device *dev = tap->dev;
    struct tap_queue *q;
- 	struct skb_array **arrays;
+ 	struct ptr_ring **rings;
    int n = tap->numqueues;
    int ret, i = 0;
- 	arrays = kmalloc_array(n, sizeof(*arrays), GFP_KERNEL);
- 	if (!arrays)
+ 	rings = kmalloc_array(n, sizeof(*rings), GFP_KERNEL);
+ 	if (!rings)
    	return -ENOMEM;
list_for_each_entry(q, &tap->queue_list, next)
- 		arrays[i++] = &q->skb_array;
+ 		rings[i++] = &q->ring;
- 	ret = skb_array_resize_multiple(arrays, n,
- 					dev->tx_queue_len, GFP_KERNEL);
+ 	ret = ptr_ring_resize_multiple(rings, n,
+ 				       dev->tx_queue_len, GFP_KERNEL,
+ 				       __skb_array_destroy_skb);
- 	kfree(arrays);
+ 	kfree(rings);
    return ret;
  }
  EXPORT_SYMBOL_GPL(tap_queue_resize);
diff --combined drivers/net/tun.c
index 2ffe5dba7e09,2fba3be5719e..55e6fee87375
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@@ -179,7 -179,8 +179,8 @@@ struct tun_file 
    struct mutex napi_mutex;	/* Protects access to the above napi */
    struct list_head next;
    struct tun_struct *detached;
- 	struct skb_array tx_array;
+ 	struct ptr_ring tx_ring;
+ 	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.
@@@ -232,8 -238,27 +238,27 @@@ 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;
  };
+ bool tun_is_xdp_buff(void *ptr)
+ {
+ 	return (unsigned long)ptr & TUN_XDP_FLAG;
+ }
+ EXPORT_SYMBOL(tun_is_xdp_buff);
+ 
+ void *tun_xdp_to_ptr(void *ptr)
+ {
+ 	return (void *)((unsigned long)ptr | TUN_XDP_FLAG);
+ }
+ EXPORT_SYMBOL(tun_xdp_to_ptr);
+ 
+ void *tun_ptr_to_xdp(void *ptr)
+ {
+ 	return (void *)((unsigned long)ptr & ~TUN_XDP_FLAG);
+ }
+ EXPORT_SYMBOL(tun_ptr_to_xdp);
+ 
  static int tun_napi_receive(struct napi_struct *napi, int budget)
  {
    struct tun_file *tfile = container_of(napi, struct tun_file, napi);
@@@ -537,15 -562,12 +562,12 @@@ 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 -585,37 +585,37 @@@
    		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();
@@@ -600,12 -649,25 +649,25 @@@ static struct tun_struct *tun_enable_qu
    return tun;
  }
+ static void tun_ptr_free(void *ptr)
+ {
+ 	if (!ptr)
+ 		return;
+ 	if (tun_is_xdp_buff(ptr)) {
+ 		struct xdp_buff *xdp = tun_ptr_to_xdp(ptr);
+ 
+ 		put_page(virt_to_head_page(xdp->data));
+ 	} else {
+ 		__skb_array_destroy_skb(ptr);
+ 	}
+ }
+ 
  static void tun_queue_purge(struct tun_file *tfile)
  {
- 	struct sk_buff *skb;
+ 	void *ptr;
- 	while ((skb = skb_array_consume(&tfile->tx_array)) != NULL)
- 		kfree_skb(skb);
+ 	while ((ptr = ptr_ring_consume(&tfile->tx_ring)) != NULL)
+ 		tun_ptr_free(ptr);
skb_queue_purge(&tfile->sk.sk_write_queue);
    skb_queue_purge(&tfile->sk.sk_error_queue);
@@@ -657,8 -719,10 +719,10 @@@ static void __tun_detach(struct tun_fil
    		    tun->dev->reg_state == NETREG_REGISTERED)
    			unregister_netdevice(tun->dev);
    	}
- 		if (tun)
- 			skb_array_cleanup(&tfile->tx_array);
+ 		if (tun) {
+ 			ptr_ring_cleanup(&tfile->tx_ring, tun_ptr_free);
+ 			xdp_rxq_info_unreg(&tfile->xdp_rxq);
+ 		}
    	sock_put(&tfile->sk);
    }
  }
@@@ -673,7 -737,6 +737,6 @@@ 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 -762,17 +762,17 @@@
    	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);
  }
@@@ -751,13 -813,29 +813,29 @@@ static int tun_attach(struct tun_struc
    }
if (!tfile->detached &&
- 	    skb_array_init(&tfile->tx_array, dev->tx_queue_len, GFP_KERNEL)) {
+ 	    ptr_ring_init(&tfile->tx_ring, dev->tx_queue_len, GFP_KERNEL)) {
    	err = -ENOMEM;
    	goto out;
    }
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 -1015,10 +1015,10 @@@ 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 -1034,24 +1034,24 @@@
    	}
    }
  #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);
@@@ -996,7 -1079,7 +1079,7 @@@
nf_reset(skb);
- 	if (skb_array_produce(&tfile->tx_array, skb))
+ 	if (ptr_ring_produce(&tfile->tx_ring, skb))
    	goto drop;
/* Notify and wake up reader process */
@@@ -1169,6 -1252,67 +1252,67 @@@ static const struct net_device_ops tun_
    .ndo_get_stats64	= tun_net_get_stats64,
  };
+ static int tun_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp)
+ {
+ 	struct tun_struct *tun = netdev_priv(dev);
+ 	struct xdp_buff *buff = xdp->data_hard_start;
+ 	int headroom = xdp->data - xdp->data_hard_start;
+ 	struct tun_file *tfile;
+ 	u32 numqueues;
+ 	int ret = 0;
+ 
+ 	/* Assure headroom is available and buff is properly aligned */
+ 	if (unlikely(headroom < sizeof(*xdp) || tun_is_xdp_buff(xdp)))
+ 		return -ENOSPC;
+ 
+ 	*buff = *xdp;
+ 
+ 	rcu_read_lock();
+ 
+ 	numqueues = READ_ONCE(tun->numqueues);
+ 	if (!numqueues) {
+ 		ret = -ENOSPC;
+ 		goto out;
+ 	}
+ 
+ 	tfile = rcu_dereference(tun->tfiles[smp_processor_id() %
+ 					    numqueues]);
+ 	/* Encode the XDP flag into lowest bit for consumer to differ
+ 	 * XDP buffer from sk_buff.
+ 	 */
+ 	if (ptr_ring_produce(&tfile->tx_ring, tun_xdp_to_ptr(buff))) {
+ 		this_cpu_inc(tun->pcpu_stats->tx_dropped);
+ 		ret = -ENOSPC;
+ 	}
+ 
+ out:
+ 	rcu_read_unlock();
+ 	return ret;
+ }
+ 
+ static void tun_xdp_flush(struct net_device *dev)
+ {
+ 	struct tun_struct *tun = netdev_priv(dev);
+ 	struct tun_file *tfile;
+ 	u32 numqueues;
+ 
+ 	rcu_read_lock();
+ 
+ 	numqueues = READ_ONCE(tun->numqueues);
+ 	if (!numqueues)
+ 		goto out;
+ 
+ 	tfile = rcu_dereference(tun->tfiles[smp_processor_id() %
+ 					    numqueues]);
+ 	/* Notify and wake up reader process */
+ 	if (tfile->flags & TUN_FASYNC)
+ 		kill_fasync(&tfile->fasync, SIGIO, POLL_IN);
+ 	tfile->socket.sk->sk_data_ready(tfile->socket.sk);
+ 
+ out:
+ 	rcu_read_unlock();
+ }
+ 
  static const struct net_device_ops tap_netdev_ops = {
    .ndo_uninit		= tun_net_uninit,
    .ndo_open		= tun_net_open,
@@@ -1186,6 -1330,8 +1330,8 @@@
    .ndo_set_rx_headroom	= tun_set_headroom,
    .ndo_get_stats64	= tun_net_get_stats64,
    .ndo_bpf		= tun_xdp,
+ 	.ndo_xdp_xmit		= tun_xdp_xmit,
+ 	.ndo_xdp_flush		= tun_xdp_flush,
  };
static void tun_flow_init(struct tun_struct *tun)
@@@ -1248,12 -1394,12 +1394,12 @@@ 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;
@@@ -1264,7 -1410,7 +1410,7 @@@
poll_wait(file, sk_sleep(sk), wait);
- 	if (!skb_array_empty(&tfile->tx_array))
+ 	if (!ptr_ring_empty(&tfile->tx_ring))
    	mask |= POLLIN | POLLRDNORM;
if (tun->dev->flags & IFF_UP &&
@@@ -1477,6 -1623,7 +1623,7 @@@ 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 -1698,7 +1698,7 @@@ 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 -1886,10 +1886,10 @@@
    	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 -1933,9 +1933,9 @@@
    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;
  }
@@@ -1804,6 -1956,40 +1956,40 @@@ static ssize_t tun_chr_write_iter(struc
    return result;
  }
+ static ssize_t tun_put_user_xdp(struct tun_struct *tun,
+ 				struct tun_file *tfile,
+ 				struct xdp_buff *xdp,
+ 				struct iov_iter *iter)
+ {
+ 	int vnet_hdr_sz = 0;
+ 	size_t size = xdp->data_end - xdp->data;
+ 	struct tun_pcpu_stats *stats;
+ 	size_t ret;
+ 
+ 	if (tun->flags & IFF_VNET_HDR) {
+ 		struct virtio_net_hdr gso = { 0 };
+ 
+ 		vnet_hdr_sz = READ_ONCE(tun->vnet_hdr_sz);
+ 		if (unlikely(iov_iter_count(iter) < vnet_hdr_sz))
+ 			return -EINVAL;
+ 		if (unlikely(copy_to_iter(&gso, sizeof(gso), iter) !=
+ 			     sizeof(gso)))
+ 			return -EFAULT;
+ 		iov_iter_advance(iter, vnet_hdr_sz - sizeof(gso));
+ 	}
+ 
+ 	ret = copy_to_iter(xdp->data, size, iter) + vnet_hdr_sz;
+ 
+ 	stats = get_cpu_ptr(tun->pcpu_stats);
+ 	u64_stats_update_begin(&stats->syncp);
+ 	stats->tx_packets++;
+ 	stats->tx_bytes += ret;
+ 	u64_stats_update_end(&stats->syncp);
+ 	put_cpu_ptr(tun->pcpu_stats);
+ 
+ 	return ret;
+ }
+ 
  /* Put packet to the user space buffer */
  static ssize_t tun_put_user(struct tun_struct *tun,
    		    struct tun_file *tfile,
@@@ -1901,15 -2087,14 +2087,14 @@@ done
    return total;
  }
- static struct sk_buff *tun_ring_recv(struct tun_file *tfile, int noblock,
- 				     int *err)
+ static void *tun_ring_recv(struct tun_file *tfile, int noblock, int *err)
  {
    DECLARE_WAITQUEUE(wait, current);
- 	struct sk_buff *skb = NULL;
+ 	void *ptr = NULL;
    int error = 0;
- 	skb = skb_array_consume(&tfile->tx_array);
- 	if (skb)
+ 	ptr = ptr_ring_consume(&tfile->tx_ring);
+ 	if (ptr)
    	goto out;
    if (noblock) {
    	error = -EAGAIN;
@@@ -1920,8 -2105,8 +2105,8 @@@
    current->state = TASK_INTERRUPTIBLE;
while (1) {
- 		skb = skb_array_consume(&tfile->tx_array);
- 		if (skb)
+ 		ptr = ptr_ring_consume(&tfile->tx_ring);
+ 		if (ptr)
    		break;
    	if (signal_pending(current)) {
    		error = -ERESTARTSYS;
@@@ -1940,12 -2125,12 +2125,12 @@@
out:
    *err = error;
- 	return skb;
+ 	return ptr;
  }
static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile,
    		   struct iov_iter *to,
- 			   int noblock, struct sk_buff *skb)
+ 			   int noblock, void *ptr)
  {
    ssize_t ret;
    int err;
@@@ -1953,23 -2138,31 +2138,31 @@@
    tun_debug(KERN_INFO, tun, "tun_do_read\n");
if (!iov_iter_count(to)) {
- 		if (skb)
- 			kfree_skb(skb);
+ 		tun_ptr_free(ptr);
    	return 0;
    }
- 	if (!skb) {
+ 	if (!ptr) {
    	/* Read frames from ring */
- 		skb = tun_ring_recv(tfile, noblock, &err);
- 		if (!skb)
+ 		ptr = tun_ring_recv(tfile, noblock, &err);
+ 		if (!ptr)
    		return err;
    }
- 	ret = tun_put_user(tun, tfile, skb, to);
- 	if (unlikely(ret < 0))
- 		kfree_skb(skb);
- 	else
- 		consume_skb(skb);
+ 	if (tun_is_xdp_buff(ptr)) {
+ 		struct xdp_buff *xdp = tun_ptr_to_xdp(ptr);
+ 
+ 		ret = tun_put_user_xdp(tun, tfile, xdp, to);
+ 		put_page(virt_to_head_page(xdp->data));
+ 	} else {
+ 		struct sk_buff *skb = ptr;
+ 
+ 		ret = tun_put_user(tun, tfile, skb, to);
+ 		if (unlikely(ret < 0))
+ 			kfree_skb(skb);
+ 		else
+ 			consume_skb(skb);
+ 	}
return ret;
  }
@@@ -1991,6 -2184,39 +2184,39 @@@ 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 -2225,7 +2225,7 @@@
    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)
@@@ -2072,12 -2299,12 +2299,12 @@@ static int tun_recvmsg(struct socket *s
  {
    struct tun_file *tfile = container_of(sock, struct tun_file, socket);
    struct tun_struct *tun = tun_get(tfile);
- 	struct sk_buff *skb = m->msg_control;
+ 	void *ptr = m->msg_control;
    int ret;
if (!tun) {
    	ret = -EBADFD;
- 		goto out_free_skb;
+ 		goto out_free;
    }
if (flags & ~(MSG_DONTWAIT|MSG_TRUNC|MSG_ERRQUEUE)) {
@@@ -2089,7 -2316,7 +2316,7 @@@
    				 SOL_PACKET, TUN_TX_TIMESTAMP);
    	goto out;
    }
- 	ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, skb);
+ 	ret = tun_do_read(tun, tfile, &m->msg_iter, flags & MSG_DONTWAIT, ptr);
    if (ret > (ssize_t)total_len) {
    	m->msg_flags |= MSG_TRUNC;
    	ret = flags & MSG_TRUNC ? ret : total_len;
@@@ -2100,12 -2327,25 +2327,25 @@@ out
out_put_tun:
    tun_put(tun);
- out_free_skb:
- 	if (skb)
- 		kfree_skb(skb);
+ out_free:
+ 	tun_ptr_free(ptr);
    return ret;
  }
+ static int tun_ptr_peek_len(void *ptr)
+ {
+ 	if (likely(ptr)) {
+ 		if (tun_is_xdp_buff(ptr)) {
+ 			struct xdp_buff *xdp = tun_ptr_to_xdp(ptr);
+ 
+ 			return xdp->data_end - xdp->data;
+ 		}
+ 		return __skb_array_len_with_tag(ptr);
+ 	} else {
+ 		return 0;
+ 	}
+ }
+ 
  static int tun_peek_len(struct socket *sock)
  {
    struct tun_file *tfile = container_of(sock, struct tun_file, socket);
@@@ -2116,7 -2356,7 +2356,7 @@@
    if (!tun)
    	return 0;
- 	ret = skb_array_peek_len(&tfile->tx_array);
+ 	ret = PTR_RING_PEEK_CALL(&tfile->tx_ring, tun_ptr_peek_len);
    tun_put(tun);
return ret;
@@@ -2287,6 -2527,7 +2527,7 @@@ 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 -2720,25 +2720,25 @@@ 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 -3015,10 +3015,10 @@@
    	ret = 0;
    	break;
+ 	case TUNSETSTEERINGEBPF:
+ 		ret = tun_set_steering_ebpf(tun, argp);
+ 		break;
+ 
    default:
    	ret = -EINVAL;
    	break;
@@@ -2998,25 -3262,26 +3262,26 @@@ static int tun_queue_resize(struct tun_
  {
    struct net_device *dev = tun->dev;
    struct tun_file *tfile;
- 	struct skb_array **arrays;
+ 	struct ptr_ring **rings;
    int n = tun->numqueues + tun->numdisabled;
    int ret, i;
- 	arrays = kmalloc_array(n, sizeof(*arrays), GFP_KERNEL);
- 	if (!arrays)
+ 	rings = kmalloc_array(n, sizeof(*rings), GFP_KERNEL);
+ 	if (!rings)
    	return -ENOMEM;
for (i = 0; i < tun->numqueues; i++) {
    	tfile = rtnl_dereference(tun->tfiles[i]);
- 		arrays[i] = &tfile->tx_array;
+ 		rings[i] = &tfile->tx_ring;
    }
    list_for_each_entry(tfile, &tun->disabled, next)
- 		arrays[i++] = &tfile->tx_array;
+ 		rings[i++] = &tfile->tx_ring;
- 	ret = skb_array_resize_multiple(arrays, n,
- 					dev->tx_queue_len, GFP_KERNEL);
+ 	ret = ptr_ring_resize_multiple(rings, n,
+ 				       dev->tx_queue_len, GFP_KERNEL,
+ 				       tun_ptr_free);
- 	kfree(arrays);
+ 	kfree(rings);
    return ret;
  }
@@@ -3102,7 -3367,7 +3367,7 @@@ struct socket *tun_get_socket(struct fi
  }
  EXPORT_SYMBOL_GPL(tun_get_socket);
- struct skb_array *tun_get_skb_array(struct file *file)
+ struct ptr_ring *tun_get_tx_ring(struct file *file)
  {
    struct tun_file *tfile;
@@@ -3111,9 -3376,9 +3376,9 @@@
    tfile = file->private_data;
    if (!tfile)
    	return ERR_PTR(-EBADFD);
- 	return &tfile->tx_array;
+ 	return &tfile->tx_ring;
  }
- EXPORT_SYMBOL_GPL(tun_get_skb_array);
+ EXPORT_SYMBOL_GPL(tun_get_tx_ring);
module_init(tun_init);
  module_exit(tun_cleanup);
diff --combined drivers/vhost/net.c
index 9524ee16878a,7baa90abe097..7cf00872c189
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@@ -89,7 -89,7 +89,7 @@@ struct vhost_net_ubuf_ref
#define VHOST_RX_BATCH 64
  struct vhost_net_buf {
- 	struct sk_buff **queue;
+ 	void **queue;
    int tail;
    int head;
  };
@@@ -108,7 -108,7 +108,7 @@@ struct vhost_net_virtqueue 
    /* Reference counting for outstanding ubufs.
     * Protected by vq mutex. Writers must also take device mutex. */
    struct vhost_net_ubuf_ref *ubufs;
- 	struct skb_array *rx_array;
+ 	struct ptr_ring *rx_ring;
    struct vhost_net_buf rxq;
  };
@@@ -158,7 -158,7 +158,7 @@@ static int vhost_net_buf_produce(struc
    struct vhost_net_buf *rxq = &nvq->rxq;
rxq->head = 0;
- 	rxq->tail = skb_array_consume_batched(nvq->rx_array, rxq->queue,
+ 	rxq->tail = ptr_ring_consume_batched(nvq->rx_ring, rxq->queue,
    				      VHOST_RX_BATCH);
    return rxq->tail;
  }
@@@ -167,13 -167,25 +167,25 @@@ static void vhost_net_buf_unproduce(str
  {
    struct vhost_net_buf *rxq = &nvq->rxq;
- 	if (nvq->rx_array && !vhost_net_buf_is_empty(rxq)) {
- 		skb_array_unconsume(nvq->rx_array, rxq->queue + rxq->head,
- 				    vhost_net_buf_get_size(rxq));
+ 	if (nvq->rx_ring && !vhost_net_buf_is_empty(rxq)) {
+ 		ptr_ring_unconsume(nvq->rx_ring, rxq->queue + rxq->head,
+ 				   vhost_net_buf_get_size(rxq),
+ 				   __skb_array_destroy_skb);
    	rxq->head = rxq->tail = 0;
    }
  }
+ static int vhost_net_buf_peek_len(void *ptr)
+ {
+ 	if (tun_is_xdp_buff(ptr)) {
+ 		struct xdp_buff *xdp = tun_ptr_to_xdp(ptr);
+ 
+ 		return xdp->data_end - xdp->data;
+ 	}
+ 
+ 	return __skb_array_len_with_tag(ptr);
+ }
+ 
  static int vhost_net_buf_peek(struct vhost_net_virtqueue *nvq)
  {
    struct vhost_net_buf *rxq = &nvq->rxq;
@@@ -185,7 -197,7 +197,7 @@@
    	return 0;
out:
- 	return __skb_array_len_with_tag(vhost_net_buf_get_ptr(rxq));
+ 	return vhost_net_buf_peek_len(vhost_net_buf_get_ptr(rxq));
  }
static void vhost_net_buf_init(struct vhost_net_buf *rxq)
@@@ -583,7 -595,7 +595,7 @@@ static int peek_head_len(struct vhost_n
    int len = 0;
    unsigned long flags;
- 	if (rvq->rx_array)
+ 	if (rvq->rx_ring)
    	return vhost_net_buf_peek(rvq);
spin_lock_irqsave(&sk->sk_receive_queue.lock, flags);
@@@ -744,7 -756,7 +756,7 @@@ static void handle_rx(struct vhost_net 
    };
    size_t total_len = 0;
    int err, mergeable;
- 	s16 headcount;
+ 	s16 headcount, nheads = 0;
    size_t vhost_hlen, sock_hlen;
    size_t vhost_len, sock_len;
    struct socket *sock;
@@@ -772,7 -784,7 +784,7 @@@
    while ((sock_len = vhost_net_rx_peek_head_len(net, sock->sk))) {
    	sock_len += sock_hlen;
    	vhost_len = sock_len + vhost_hlen;
- 		headcount = get_rx_bufs(vq, vq->heads, vhost_len,
+ 		headcount = get_rx_bufs(vq, vq->heads + nheads, vhost_len,
    				&in, vq_log, &log,
    				likely(mergeable) ? UIO_MAXIOV : 1);
    	/* On error, stop handling until the next kick. */
@@@ -790,7 -802,7 +802,7 @@@
    		 * they refilled. */
    		goto out;
    	}
- 		if (nvq->rx_array)
+ 		if (nvq->rx_ring)
    		msg.msg_control = vhost_net_buf_consume(&nvq->rxq);
    	/* On overrun, truncate and discard */
    	if (unlikely(headcount > UIO_MAXIOV)) {
@@@ -844,8 -856,12 +856,12 @@@
    		vhost_discard_vq_desc(vq, headcount);
    		goto out;
    	}
- 		vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
- 					    headcount);
+ 		nheads += headcount;
+ 		if (nheads > VHOST_RX_BATCH) {
+ 			vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
+ 						    nheads);
+ 			nheads = 0;
+ 		}
    	if (unlikely(vq_log))
    		vhost_log_write(vq, vq_log, log, vhost_len);
    	total_len += vhost_len;
@@@ -856,6 -872,9 +872,9 @@@
    }
    vhost_net_enable_vq(net, vq);
  out:
+ 	if (nheads)
+ 		vhost_add_used_and_signal_n(&net->dev, vq, vq->heads,
+ 					    nheads);
    mutex_unlock(&vq->mutex);
  }
@@@ -896,7 -915,7 +915,7 @@@ static int vhost_net_open(struct inode 
    struct vhost_net *n;
    struct vhost_dev *dev;
    struct vhost_virtqueue **vqs;
- 	struct sk_buff **queue;
+ 	void **queue;
    int i;
n = kvmalloc(sizeof *n, GFP_KERNEL | __GFP_RETRY_MAYFAIL);
@@@ -908,7 -927,7 +927,7 @@@
    	return -ENOMEM;
    }
- 	queue = kmalloc_array(VHOST_RX_BATCH, sizeof(struct sk_buff *),
+ 	queue = kmalloc_array(VHOST_RX_BATCH, sizeof(void *),
    		      GFP_KERNEL);
    if (!queue) {
    	kfree(vqs);
@@@ -1046,23 -1065,23 +1065,23 @@@ err
    return ERR_PTR(r);
  }
- static struct skb_array *get_tap_skb_array(int fd)
+ static struct ptr_ring *get_tap_ptr_ring(int fd)
  {
- 	struct skb_array *array;
+ 	struct ptr_ring *ring;
    struct file *file = fget(fd);
if (!file)
    	return NULL;
- 	array = tun_get_skb_array(file);
- 	if (!IS_ERR(array))
+ 	ring = tun_get_tx_ring(file);
+ 	if (!IS_ERR(ring))
    	goto out;
- 	array = tap_get_skb_array(file);
- 	if (!IS_ERR(array))
+ 	ring = tap_get_ptr_ring(file);
+ 	if (!IS_ERR(ring))
    	goto out;
- 	array = NULL;
+ 	ring = NULL;
  out:
    fput(file);
- 	return array;
+ 	return ring;
  }
static struct socket *get_tap_socket(int fd)
@@@ -1143,7 -1162,7 +1162,7 @@@ static long vhost_net_set_backend(struc
    	vq->private_data = sock;
    	vhost_net_buf_unproduce(nvq);
    	if (index == VHOST_NET_VQ_RX)
- 			nvq->rx_array = get_tap_skb_array(fd);
+ 			nvq->rx_ring = get_tap_ptr_ring(fd);
    	r = vhost_vq_init_access(vq);
    	if (r)
    		goto err_used;
@@@ -1353,7 -1372,7 +1372,7 @@@ static ssize_t vhost_net_chr_write_iter
    return vhost_chr_write_iter(dev, from);
  }
-static unsigned int vhost_net_chr_poll(struct file *file, poll_table *wait)
 +static __poll_t vhost_net_chr_poll(struct file *file, poll_table *wait)
  {
    struct vhost_net *n = file->private_data;
    struct vhost_dev *dev = &n->dev;
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/mlx5/mlx5_ifc.h
index 1391a82da98e,78e36fc2609e..acd829d8613b
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@@ -794,7 -794,10 +794,10 @@@ enum 
  };
struct mlx5_ifc_cmd_hca_cap_bits {
- 	u8         reserved_at_0[0x80];
+ 	u8         reserved_at_0[0x30];
+ 	u8         vhca_id[0x10];
+ 
+ 	u8         reserved_at_40[0x40];
u8         log_max_srq_sz[0x8];
    u8         log_max_qp_sz[0x8];
@@@ -1023,13 -1026,19 +1026,19 @@@
    u8         reserved_at_3b8[0x3];
    u8         log_min_stride_sz_sq[0x5];
- 	u8         reserved_at_3c0[0x1b];
+ 	u8         hairpin[0x1];
+ 	u8         reserved_at_3c1[0x2];
+ 	u8         log_max_hairpin_queues[0x5];
+ 	u8         reserved_at_3c8[0x3];
+ 	u8         log_max_hairpin_wq_data_sz[0x5];
+ 	u8         reserved_at_3d0[0xb];
    u8         log_max_wq_sz[0x5];
u8         nic_vport_change_event[0x1];
 -	u8         disable_local_lb[0x1];
 -	u8         reserved_at_3e2[0x1];
 +	u8         disable_local_lb_uc[0x1];
 +	u8         disable_local_lb_mc[0x1];
- 	u8         reserved_at_3e3[0x8];
+ 	u8         log_min_hairpin_wq_data_sz[0x5];
+ 	u8         reserved_at_3e8[0x3];
    u8         log_max_vlan_list[0x5];
    u8         reserved_at_3f0[0x3];
    u8         log_max_current_mc_list[0x5];
@@@ -1163,7 -1172,10 +1172,10 @@@ struct mlx5_ifc_wq_bits 
    u8         reserved_at_118[0x3];
    u8         log_wq_sz[0x5];
- 	u8         reserved_at_120[0x15];
+ 	u8         reserved_at_120[0xb];
+ 	u8         log_hairpin_data_sz[0x5];
+ 	u8         reserved_at_130[0x5];
+ 
    u8         log_wqe_num_of_strides[0x3];
    u8         two_byte_shift_en[0x1];
    u8         reserved_at_139[0x4];
@@@ -2483,7 -2495,8 +2495,8 @@@ struct mlx5_ifc_sqc_bits 
    u8         state[0x4];
    u8         reg_umr[0x1];
    u8         allow_swp[0x1];
- 	u8         reserved_at_e[0x12];
+ 	u8         hairpin[0x1];
+ 	u8         reserved_at_f[0x11];
u8         reserved_at_20[0x8];
    u8         user_index[0x18];
@@@ -2491,7 -2504,13 +2504,13 @@@
    u8         reserved_at_40[0x8];
    u8         cqn[0x18];
- 	u8         reserved_at_60[0x90];
+ 	u8         reserved_at_60[0x8];
+ 	u8         hairpin_peer_rq[0x18];
+ 
+ 	u8         reserved_at_80[0x10];
+ 	u8         hairpin_peer_vhca[0x10];
+ 
+ 	u8         reserved_at_a0[0x50];
u8         packet_pacing_rate_limit_index[0x10];
    u8         tis_lst_sz[0x10];
@@@ -2563,7 -2582,8 +2582,8 @@@ struct mlx5_ifc_rqc_bits 
    u8         state[0x4];
    u8         reserved_at_c[0x1];
    u8         flush_in_error_en[0x1];
- 	u8         reserved_at_e[0x12];
+ 	u8         hairpin[0x1];
+ 	u8         reserved_at_f[0x11];
u8         reserved_at_20[0x8];
    u8         user_index[0x18];
@@@ -2577,7 -2597,13 +2597,13 @@@
    u8         reserved_at_80[0x8];
    u8         rmpn[0x18];
- 	u8         reserved_at_a0[0xe0];
+ 	u8         reserved_at_a0[0x8];
+ 	u8         hairpin_peer_sq[0x18];
+ 
+ 	u8         reserved_at_c0[0x10];
+ 	u8         hairpin_peer_vhca[0x10];
+ 
+ 	u8         reserved_at_e0[0xa0];
struct mlx5_ifc_wq_bits wq;
  };
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/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/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 kernel/bpf/core.c
index 7949e8b8f94e,25e723b0dfd4..887e28408f98
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@@ -94,6 -94,7 +94,7 @@@ struct bpf_prog *bpf_prog_alloc(unsigne
    fp->pages = size / PAGE_SIZE;
    fp->aux = aux;
    fp->aux->prog = fp;
+ 	fp->jit_requested = ebpf_jit_enabled();
INIT_LIST_HEAD_RCU(&fp->aux->ksym_lnode);
@@@ -217,30 -218,40 +218,40 @@@ int bpf_prog_calc_tag(struct bpf_prog *
    return 0;
  }
- static bool bpf_is_jmp_and_has_target(const struct bpf_insn *insn)
- {
- 	return BPF_CLASS(insn->code) == BPF_JMP  &&
- 	       /* Call and Exit are both special jumps with no
- 		* target inside the BPF instruction image.
- 		*/
- 	       BPF_OP(insn->code) != BPF_CALL &&
- 	       BPF_OP(insn->code) != BPF_EXIT;
- }
- 
  static void bpf_adj_branches(struct bpf_prog *prog, u32 pos, u32 delta)
  {
    struct bpf_insn *insn = prog->insnsi;
    u32 i, insn_cnt = prog->len;
+ 	bool pseudo_call;
+ 	u8 code;
+ 	int off;
for (i = 0; i < insn_cnt; i++, insn++) {
- 		if (!bpf_is_jmp_and_has_target(insn))
+ 		code = insn->code;
+ 		if (BPF_CLASS(code) != BPF_JMP)
+ 			continue;
+ 		if (BPF_OP(code) == BPF_EXIT)
    		continue;
+ 		if (BPF_OP(code) == BPF_CALL) {
+ 			if (insn->src_reg == BPF_PSEUDO_CALL)
+ 				pseudo_call = true;
+ 			else
+ 				continue;
+ 		} else {
+ 			pseudo_call = false;
+ 		}
+ 		off = pseudo_call ? insn->imm : insn->off;
/* Adjust offset of jmps if we cross boundaries. */
- 		if (i < pos && i + insn->off + 1 > pos)
- 			insn->off += delta;
- 		else if (i > pos + delta && i + insn->off + 1 <= pos + delta)
- 			insn->off -= delta;
+ 		if (i < pos && i + off + 1 > pos)
+ 			off += delta;
+ 		else if (i > pos + delta && i + off + 1 <= pos + delta)
+ 			off -= delta;
+ 
+ 		if (pseudo_call)
+ 			insn->imm = off;
+ 		else
+ 			insn->off = off;
    }
  }
@@@ -711,7 -722,7 +722,7 @@@ struct bpf_prog *bpf_jit_blind_constant
    struct bpf_insn *insn;
    int i, rewritten;
- 	if (!bpf_jit_blinding_enabled())
+ 	if (!bpf_jit_blinding_enabled(prog) || prog->blinded)
    	return prog;
clone = bpf_prog_clone_create(prog, GFP_USER);
@@@ -753,13 -764,16 +764,16 @@@
    	i        += insn_delta;
    }
+ 	clone->blinded = 1;
    return clone;
  }
  #endif /* CONFIG_BPF_JIT */
/* Base function for offset calculation. Needs to go into .text section,
   * therefore keeping it non-static as well; will also be used by JITs
-  * anyway later on, so do not let the compiler omit it.
+  * anyway later on, so do not let the compiler omit it. This also needs
+  * to go into kallsyms for correlation from e.g. bpftool, so naming
+  * must not change.
   */
  noinline u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5)
  {
@@@ -775,8 -789,7 +789,7 @@@ EXPORT_SYMBOL_GPL(__bpf_call_base)
   *
   * Decode and execute eBPF instructions.
   */
- static unsigned int ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn,
- 				    u64 *stack)
+ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack)
  {
    u64 tmp;
    static const void *jumptable[256] = {
@@@ -836,6 -849,7 +849,7 @@@
    	[BPF_ALU64 | BPF_NEG] = &&ALU64_NEG,
    	/* Call instruction */
    	[BPF_JMP | BPF_CALL] = &&JMP_CALL,
+ 		[BPF_JMP | BPF_CALL_ARGS] = &&JMP_CALL_ARGS,
    	[BPF_JMP | BPF_TAIL_CALL] = &&JMP_TAIL_CALL,
    	/* Jumps */
    	[BPF_JMP | BPF_JA] = &&JMP_JA,
@@@ -956,7 -970,7 +970,7 @@@ select_insn
    	DST = tmp;
    	CONT;
    ALU_MOD_X:
 -		if (unlikely(SRC == 0))
 +		if (unlikely((u32)SRC == 0))
    		return 0;
    	tmp = (u32) DST;
    	DST = do_div(tmp, (u32) SRC);
@@@ -975,7 -989,7 +989,7 @@@
    	DST = div64_u64(DST, SRC);
    	CONT;
    ALU_DIV_X:
 -		if (unlikely(SRC == 0))
 +		if (unlikely((u32)SRC == 0))
    		return 0;
    	tmp = (u32) DST;
    	do_div(tmp, (u32) SRC);
@@@ -1026,6 -1040,13 +1040,13 @@@
    					       BPF_R4, BPF_R5);
    	CONT;
+ 	JMP_CALL_ARGS:
+ 		BPF_R0 = (__bpf_call_base_args + insn->imm)(BPF_R1, BPF_R2,
+ 							    BPF_R3, BPF_R4,
+ 							    BPF_R5,
+ 							    insn + insn->off + 1);
+ 		CONT;
+ 
    JMP_TAIL_CALL: {
    	struct bpf_map *map = (struct bpf_map *) (unsigned long) BPF_R2;
    	struct bpf_array *array = container_of(map, struct bpf_array, map);
@@@ -1298,6 -1319,23 +1319,23 @@@ static unsigned int PROG_NAME(stack_siz
    return ___bpf_prog_run(regs, insn, stack); \
  }
+ #define PROG_NAME_ARGS(stack_size) __bpf_prog_run_args##stack_size
+ #define DEFINE_BPF_PROG_RUN_ARGS(stack_size) \
+ static u64 PROG_NAME_ARGS(stack_size)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5, \
+ 				      const struct bpf_insn *insn) \
+ { \
+ 	u64 stack[stack_size / sizeof(u64)]; \
+ 	u64 regs[MAX_BPF_REG]; \
+ \
+ 	FP = (u64) (unsigned long) &stack[ARRAY_SIZE(stack)]; \
+ 	BPF_R1 = r1; \
+ 	BPF_R2 = r2; \
+ 	BPF_R3 = r3; \
+ 	BPF_R4 = r4; \
+ 	BPF_R5 = r5; \
+ 	return ___bpf_prog_run(regs, insn, stack); \
+ }
+ 
  #define EVAL1(FN, X) FN(X)
  #define EVAL2(FN, X, Y...) FN(X) EVAL1(FN, Y)
  #define EVAL3(FN, X, Y...) FN(X) EVAL2(FN, Y)
@@@ -1309,6 -1347,10 +1347,10 @@@ EVAL6(DEFINE_BPF_PROG_RUN, 32, 64, 96, 
  EVAL6(DEFINE_BPF_PROG_RUN, 224, 256, 288, 320, 352, 384);
  EVAL4(DEFINE_BPF_PROG_RUN, 416, 448, 480, 512);
+ EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 32, 64, 96, 128, 160, 192);
+ EVAL6(DEFINE_BPF_PROG_RUN_ARGS, 224, 256, 288, 320, 352, 384);
+ EVAL4(DEFINE_BPF_PROG_RUN_ARGS, 416, 448, 480, 512);
+ 
  #define PROG_NAME_LIST(stack_size) PROG_NAME(stack_size),
static unsigned int (*interpreters[])(const void *ctx,
@@@ -1317,6 -1359,24 +1359,24 @@@ EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 
  EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
  EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
  };
+ #undef PROG_NAME_LIST
+ #define PROG_NAME_LIST(stack_size) PROG_NAME_ARGS(stack_size),
+ static u64 (*interpreters_args[])(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5,
+ 				  const struct bpf_insn *insn) = {
+ EVAL6(PROG_NAME_LIST, 32, 64, 96, 128, 160, 192)
+ EVAL6(PROG_NAME_LIST, 224, 256, 288, 320, 352, 384)
+ EVAL4(PROG_NAME_LIST, 416, 448, 480, 512)
+ };
+ #undef PROG_NAME_LIST
+ 
+ void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth)
+ {
+ 	stack_depth = max_t(u32, stack_depth, 1);
+ 	insn->off = (s16) insn->imm;
+ 	insn->imm = interpreters_args[(round_up(stack_depth, 32) / 32) - 1] -
+ 		__bpf_call_base_args;
+ 	insn->code = BPF_JMP | BPF_CALL_ARGS;
+ }
#else
  static unsigned int __bpf_prog_ret0(const void *ctx,
@@@ -1329,6 -1389,9 +1389,9 @@@
  bool bpf_prog_array_compatible(struct bpf_array *array,
    		       const struct bpf_prog *fp)
  {
+ 	if (fp->kprobe_override)
+ 		return false;
+ 
    if (!array->owner_prog_type) {
    	/* There's no owner yet where we could check for
    	 * compatibility.
@@@ -1481,6 -1544,8 +1544,8 @@@ int bpf_prog_array_copy_to_user(struct 
    rcu_read_lock();
    prog = rcu_dereference(progs)->progs;
    for (; *prog; prog++) {
+ 		if (*prog == &dummy_bpf_prog.prog)
+ 			continue;
    	id = (*prog)->aux->id;
    	if (copy_to_user(prog_ids + i, &id, sizeof(id))) {
    		rcu_read_unlock();
@@@ -1564,14 -1629,41 +1629,41 @@@ int bpf_prog_array_copy(struct bpf_prog
    return 0;
  }
+ int bpf_prog_array_copy_info(struct bpf_prog_array __rcu *array,
+ 			     __u32 __user *prog_ids, u32 request_cnt,
+ 			     __u32 __user *prog_cnt)
+ {
+ 	u32 cnt = 0;
+ 
+ 	if (array)
+ 		cnt = bpf_prog_array_length(array);
+ 
+ 	if (copy_to_user(prog_cnt, &cnt, sizeof(cnt)))
+ 		return -EFAULT;
+ 
+ 	/* return early if user requested only program count or nothing to copy */
+ 	if (!request_cnt || !cnt)
+ 		return 0;
+ 
+ 	return bpf_prog_array_copy_to_user(array, prog_ids, request_cnt);
+ }
+ 
  static void bpf_prog_free_deferred(struct work_struct *work)
  {
    struct bpf_prog_aux *aux;
+ 	int i;
aux = container_of(work, struct bpf_prog_aux, work);
    if (bpf_prog_is_dev_bound(aux))
    	bpf_prog_offload_destroy(aux->prog);
- 	bpf_jit_free(aux->prog);
+ 	for (i = 0; i < aux->func_cnt; i++)
+ 		bpf_jit_free(aux->func[i]);
+ 	if (aux->func_cnt) {
+ 		kfree(aux->func);
+ 		bpf_prog_unlock_free(aux->prog);
+ 	} else {
+ 		bpf_jit_free(aux->prog);
+ 	}
  }
/* Free internal BPF program */
diff --combined kernel/bpf/verifier.c
index 20eb04fd155e,48b61caa94cb..aaaa254402ea
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@@ -20,6 -20,8 +20,8 @@@
  #include <linux/file.h>
  #include <linux/vmalloc.h>
  #include <linux/stringify.h>
+ #include <linux/bsearch.h>
+ #include <linux/sort.h>
#include "disasm.h"
@@@ -167,11 -169,11 +169,11 @@@ struct bpf_call_arg_meta 
  static DEFINE_MUTEX(bpf_verifier_lock);
/* log_level controls verbosity level of eBPF verifier.
-  * verbose() is used to dump the verification trace to the log, so the user
-  * can figure out what's wrong with the program
+  * bpf_verifier_log_write() is used to dump the verification trace to the log,
+  * so the user can figure out what's wrong with the program
   */
- static __printf(2, 3) void verbose(struct bpf_verifier_env *env,
- 				   const char *fmt, ...)
+ __printf(2, 3) void bpf_verifier_log_write(struct bpf_verifier_env *env,
+ 					   const char *fmt, ...)
  {
    struct bpf_verifer_log *log = &env->log;
    unsigned int n;
@@@ -195,6 -197,14 +197,14 @@@
    else
    	log->ubuf = NULL;
  }
+ EXPORT_SYMBOL_GPL(bpf_verifier_log_write);
+ /* Historically bpf_verifier_log_write was called verbose, but the name was too
+  * generic for symbol export. The function was renamed, but not the calls in
+  * the verifier to avoid complicating backports. Hence the alias below.
+  */
+ static __printf(2, 3) void verbose(struct bpf_verifier_env *env,
+ 				   const char *fmt, ...)
+ 	__attribute__((alias("bpf_verifier_log_write")));
static bool type_is_pkt_pointer(enum bpf_reg_type type)
  {
@@@ -216,23 -226,48 +226,48 @@@ static const char * const reg_type_str[
    [PTR_TO_PACKET_END]	= "pkt_end",
  };
+ static void print_liveness(struct bpf_verifier_env *env,
+ 			   enum bpf_reg_liveness live)
+ {
+ 	if (live & (REG_LIVE_READ | REG_LIVE_WRITTEN))
+ 	    verbose(env, "_");
+ 	if (live & REG_LIVE_READ)
+ 		verbose(env, "r");
+ 	if (live & REG_LIVE_WRITTEN)
+ 		verbose(env, "w");
+ }
+ 
+ static struct bpf_func_state *func(struct bpf_verifier_env *env,
+ 				   const struct bpf_reg_state *reg)
+ {
+ 	struct bpf_verifier_state *cur = env->cur_state;
+ 
+ 	return cur->frame[reg->frameno];
+ }
+ 
  static void print_verifier_state(struct bpf_verifier_env *env,
- 				 struct bpf_verifier_state *state)
+ 				 const struct bpf_func_state *state)
  {
- 	struct bpf_reg_state *reg;
+ 	const struct bpf_reg_state *reg;
    enum bpf_reg_type t;
    int i;
+ 	if (state->frameno)
+ 		verbose(env, " frame%d:", state->frameno);
    for (i = 0; i < MAX_BPF_REG; i++) {
    	reg = &state->regs[i];
    	t = reg->type;
    	if (t == NOT_INIT)
    		continue;
- 		verbose(env, " R%d=%s", i, reg_type_str[t]);
+ 		verbose(env, " R%d", i);
+ 		print_liveness(env, reg->live);
+ 		verbose(env, "=%s", reg_type_str[t]);
    	if ((t == SCALAR_VALUE || t == PTR_TO_STACK) &&
    	    tnum_is_const(reg->var_off)) {
    		/* reg->off should be 0 for SCALAR_VALUE */
    		verbose(env, "%lld", reg->var_off.value + reg->off);
+ 			if (t == PTR_TO_STACK)
+ 				verbose(env, ",call_%d", func(env, reg)->callsite);
    	} else {
    		verbose(env, "(id=%d", reg->id);
    		if (t != SCALAR_VALUE)
@@@ -277,16 -312,21 +312,21 @@@
    	}
    }
    for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
- 		if (state->stack[i].slot_type[0] == STACK_SPILL)
- 			verbose(env, " fp%d=%s",
- 				-MAX_BPF_STACK + i * BPF_REG_SIZE,
+ 		if (state->stack[i].slot_type[0] == STACK_SPILL) {
+ 			verbose(env, " fp%d",
+ 				(-i - 1) * BPF_REG_SIZE);
+ 			print_liveness(env, state->stack[i].spilled_ptr.live);
+ 			verbose(env, "=%s",
    			reg_type_str[state->stack[i].spilled_ptr.type]);
+ 		}
+ 		if (state->stack[i].slot_type[0] == STACK_ZERO)
+ 			verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE);
    }
    verbose(env, "\n");
  }
- static int copy_stack_state(struct bpf_verifier_state *dst,
- 			    const struct bpf_verifier_state *src)
+ static int copy_stack_state(struct bpf_func_state *dst,
+ 			    const struct bpf_func_state *src)
  {
    if (!src->stack)
    	return 0;
@@@ -302,13 -342,13 +342,13 @@@
/* do_check() starts with zero-sized stack in struct bpf_verifier_state to
   * make it consume minimal amount of memory. check_stack_write() access from
-  * the program calls into realloc_verifier_state() to grow the stack size.
+  * the program calls into realloc_func_state() to grow the stack size.
   * Note there is a non-zero 'parent' pointer inside bpf_verifier_state
   * which this function copies over. It points to previous bpf_verifier_state
   * which is never reallocated
   */
- static int realloc_verifier_state(struct bpf_verifier_state *state, int size,
- 				  bool copy_old)
+ static int realloc_func_state(struct bpf_func_state *state, int size,
+ 			      bool copy_old)
  {
    u32 old_size = state->allocated_stack;
    struct bpf_stack_state *new_stack;
@@@ -341,10 -381,23 +381,23 @@@
    return 0;
  }
+ static void free_func_state(struct bpf_func_state *state)
+ {
+ 	if (!state)
+ 		return;
+ 	kfree(state->stack);
+ 	kfree(state);
+ }
+ 
  static void free_verifier_state(struct bpf_verifier_state *state,
    			bool free_self)
  {
- 	kfree(state->stack);
+ 	int i;
+ 
+ 	for (i = 0; i <= state->curframe; i++) {
+ 		free_func_state(state->frame[i]);
+ 		state->frame[i] = NULL;
+ 	}
    if (free_self)
    	kfree(state);
  }
@@@ -352,18 -405,46 +405,46 @@@
  /* copy verifier state from src to dst growing dst stack space
   * when necessary to accommodate larger src stack
   */
- static int copy_verifier_state(struct bpf_verifier_state *dst,
- 			       const struct bpf_verifier_state *src)
+ static int copy_func_state(struct bpf_func_state *dst,
+ 			   const struct bpf_func_state *src)
  {
    int err;
- 	err = realloc_verifier_state(dst, src->allocated_stack, false);
+ 	err = realloc_func_state(dst, src->allocated_stack, false);
    if (err)
    	return err;
- 	memcpy(dst, src, offsetof(struct bpf_verifier_state, allocated_stack));
+ 	memcpy(dst, src, offsetof(struct bpf_func_state, allocated_stack));
    return copy_stack_state(dst, src);
  }
+ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
+ 			       const struct bpf_verifier_state *src)
+ {
+ 	struct bpf_func_state *dst;
+ 	int i, err;
+ 
+ 	/* if dst has more stack frames then src frame, free them */
+ 	for (i = src->curframe + 1; i <= dst_state->curframe; i++) {
+ 		free_func_state(dst_state->frame[i]);
+ 		dst_state->frame[i] = NULL;
+ 	}
+ 	dst_state->curframe = src->curframe;
+ 	dst_state->parent = src->parent;
+ 	for (i = 0; i <= src->curframe; i++) {
+ 		dst = dst_state->frame[i];
+ 		if (!dst) {
+ 			dst = kzalloc(sizeof(*dst), GFP_KERNEL);
+ 			if (!dst)
+ 				return -ENOMEM;
+ 			dst_state->frame[i] = dst;
+ 		}
+ 		err = copy_func_state(dst, src->frame[i]);
+ 		if (err)
+ 			return err;
+ 	}
+ 	return 0;
+ }
+ 
  static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
    	     int *insn_idx)
  {
@@@ -416,6 -497,8 +497,8 @@@ static struct bpf_verifier_state *push_
    }
    return &elem->st;
  err:
+ 	free_verifier_state(env->cur_state, true);
+ 	env->cur_state = NULL;
    /* pop all elements and return */
    while (!pop_stack(env, NULL, NULL));
    return NULL;
@@@ -425,6 -508,10 +508,10 @@@
  static const int caller_saved[CALLER_SAVED_REGS] = {
    BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
  };
+ #define CALLEE_SAVED_REGS 5
+ static const int callee_saved[CALLEE_SAVED_REGS] = {
+ 	BPF_REG_6, BPF_REG_7, BPF_REG_8, BPF_REG_9
+ };
static void __mark_reg_not_init(struct bpf_reg_state *reg);
@@@ -449,6 -536,13 +536,13 @@@ static void __mark_reg_known_zero(struc
    __mark_reg_known(reg, 0);
  }
+ static void __mark_reg_const_zero(struct bpf_reg_state *reg)
+ {
+ 	__mark_reg_known(reg, 0);
+ 	reg->off = 0;
+ 	reg->type = SCALAR_VALUE;
+ }
+ 
  static void mark_reg_known_zero(struct bpf_verifier_env *env,
    			struct bpf_reg_state *regs, u32 regno)
  {
@@@ -560,6 -654,7 +654,7 @@@ static void __mark_reg_unknown(struct b
    reg->id = 0;
    reg->off = 0;
    reg->var_off = tnum_unknown;
+ 	reg->frameno = 0;
    __mark_reg_unbounded(reg);
  }
@@@ -568,8 -663,8 +663,8 @@@ static void mark_reg_unknown(struct bpf
  {
    if (WARN_ON(regno >= MAX_BPF_REG)) {
    	verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
- 		/* Something bad happened, let's kill all regs */
- 		for (regno = 0; regno < MAX_BPF_REG; regno++)
+ 		/* Something bad happened, let's kill all regs except FP */
+ 		for (regno = 0; regno < BPF_REG_FP; regno++)
    		__mark_reg_not_init(regs + regno);
    	return;
    }
@@@ -587,8 -682,8 +682,8 @@@ static void mark_reg_not_init(struct bp
  {
    if (WARN_ON(regno >= MAX_BPF_REG)) {
    	verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
- 		/* Something bad happened, let's kill all regs */
- 		for (regno = 0; regno < MAX_BPF_REG; regno++)
+ 		/* Something bad happened, let's kill all regs except FP */
+ 		for (regno = 0; regno < BPF_REG_FP; regno++)
    		__mark_reg_not_init(regs + regno);
    	return;
    }
@@@ -596,8 -691,9 +691,9 @@@
  }
static void init_reg_state(struct bpf_verifier_env *env,
- 			   struct bpf_reg_state *regs)
+ 			   struct bpf_func_state *state)
  {
+ 	struct bpf_reg_state *regs = state->regs;
    int i;
for (i = 0; i < MAX_BPF_REG; i++) {
@@@ -608,41 -704,218 +704,218 @@@
    /* frame pointer */
    regs[BPF_REG_FP].type = PTR_TO_STACK;
    mark_reg_known_zero(env, regs, BPF_REG_FP);
+ 	regs[BPF_REG_FP].frameno = state->frameno;
/* 1st arg to a function */
    regs[BPF_REG_1].type = PTR_TO_CTX;
    mark_reg_known_zero(env, regs, BPF_REG_1);
  }
+ #define BPF_MAIN_FUNC (-1)
+ static void init_func_state(struct bpf_verifier_env *env,
+ 			    struct bpf_func_state *state,
+ 			    int callsite, int frameno, int subprogno)
+ {
+ 	state->callsite = callsite;
+ 	state->frameno = frameno;
+ 	state->subprogno = subprogno;
+ 	init_reg_state(env, state);
+ }
+ 
  enum reg_arg_type {
    SRC_OP,		/* register is used as source operand */
    DST_OP,		/* register is used as destination operand */
    DST_OP_NO_MARK	/* same as above, check only, don't mark */
  };
- static void mark_reg_read(const struct bpf_verifier_state *state, u32 regno)
+ static int cmp_subprogs(const void *a, const void *b)
  {
- 	struct bpf_verifier_state *parent = state->parent;
+ 	return *(int *)a - *(int *)b;
+ }
+ 
+ static int find_subprog(struct bpf_verifier_env *env, int off)
+ {
+ 	u32 *p;
+ 
+ 	p = bsearch(&off, env->subprog_starts, env->subprog_cnt,
+ 		    sizeof(env->subprog_starts[0]), cmp_subprogs);
+ 	if (!p)
+ 		return -ENOENT;
+ 	return p - env->subprog_starts;
+ 
+ }
+ 
+ static int add_subprog(struct bpf_verifier_env *env, int off)
+ {
+ 	int insn_cnt = env->prog->len;
+ 	int ret;
+ 
+ 	if (off >= insn_cnt || off < 0) {
+ 		verbose(env, "call to invalid destination\n");
+ 		return -EINVAL;
+ 	}
+ 	ret = find_subprog(env, off);
+ 	if (ret >= 0)
+ 		return 0;
+ 	if (env->subprog_cnt >= BPF_MAX_SUBPROGS) {
+ 		verbose(env, "too many subprograms\n");
+ 		return -E2BIG;
+ 	}
+ 	env->subprog_starts[env->subprog_cnt++] = off;
+ 	sort(env->subprog_starts, env->subprog_cnt,
+ 	     sizeof(env->subprog_starts[0]), cmp_subprogs, NULL);
+ 	return 0;
+ }
+ 
+ static int check_subprogs(struct bpf_verifier_env *env)
+ {
+ 	int i, ret, subprog_start, subprog_end, off, cur_subprog = 0;
+ 	struct bpf_insn *insn = env->prog->insnsi;
+ 	int insn_cnt = env->prog->len;
+ 
+ 	/* determine subprog starts. The end is one before the next starts */
+ 	for (i = 0; i < insn_cnt; i++) {
+ 		if (insn[i].code != (BPF_JMP | BPF_CALL))
+ 			continue;
+ 		if (insn[i].src_reg != BPF_PSEUDO_CALL)
+ 			continue;
+ 		if (!env->allow_ptr_leaks) {
+ 			verbose(env, "function calls to other bpf functions are allowed for root only\n");
+ 			return -EPERM;
+ 		}
+ 		if (bpf_prog_is_dev_bound(env->prog->aux)) {
+ 			verbose(env, "function calls in offloaded programs are not supported yet\n");
+ 			return -EINVAL;
+ 		}
+ 		ret = add_subprog(env, i + insn[i].imm + 1);
+ 		if (ret < 0)
+ 			return ret;
+ 	}
+ 
+ 	if (env->log.level > 1)
+ 		for (i = 0; i < env->subprog_cnt; i++)
+ 			verbose(env, "func#%d @%d\n", i, env->subprog_starts[i]);
+ 
+ 	/* now check that all jumps are within the same subprog */
+ 	subprog_start = 0;
+ 	if (env->subprog_cnt == cur_subprog)
+ 		subprog_end = insn_cnt;
+ 	else
+ 		subprog_end = env->subprog_starts[cur_subprog++];
+ 	for (i = 0; i < insn_cnt; i++) {
+ 		u8 code = insn[i].code;
+ 
+ 		if (BPF_CLASS(code) != BPF_JMP)
+ 			goto next;
+ 		if (BPF_OP(code) == BPF_EXIT || BPF_OP(code) == BPF_CALL)
+ 			goto next;
+ 		off = i + insn[i].off + 1;
+ 		if (off < subprog_start || off >= subprog_end) {
+ 			verbose(env, "jump out of range from insn %d to %d\n", i, off);
+ 			return -EINVAL;
+ 		}
+ next:
+ 		if (i == subprog_end - 1) {
+ 			/* to avoid fall-through from one subprog into another
+ 			 * the last insn of the subprog should be either exit
+ 			 * or unconditional jump back
+ 			 */
+ 			if (code != (BPF_JMP | BPF_EXIT) &&
+ 			    code != (BPF_JMP | BPF_JA)) {
+ 				verbose(env, "last insn is not an exit or jmp\n");
+ 				return -EINVAL;
+ 			}
+ 			subprog_start = subprog_end;
+ 			if (env->subprog_cnt == cur_subprog)
+ 				subprog_end = insn_cnt;
+ 			else
+ 				subprog_end = env->subprog_starts[cur_subprog++];
+ 		}
+ 	}
+ 	return 0;
+ }
+ 
+ static
+ struct bpf_verifier_state *skip_callee(struct bpf_verifier_env *env,
+ 				       const struct bpf_verifier_state *state,
+ 				       struct bpf_verifier_state *parent,
+ 				       u32 regno)
+ {
+ 	struct bpf_verifier_state *tmp = NULL;
+ 
+ 	/* 'parent' could be a state of caller and
+ 	 * 'state' could be a state of callee. In such case
+ 	 * parent->curframe < state->curframe
+ 	 * and it's ok for r1 - r5 registers
+ 	 *
+ 	 * 'parent' could be a callee's state after it bpf_exit-ed.
+ 	 * In such case parent->curframe > state->curframe
+ 	 * and it's ok for r0 only
+ 	 */
+ 	if (parent->curframe == state->curframe ||
+ 	    (parent->curframe < state->curframe &&
+ 	     regno >= BPF_REG_1 && regno <= BPF_REG_5) ||
+ 	    (parent->curframe > state->curframe &&
+ 	       regno == BPF_REG_0))
+ 		return parent;
+ 
+ 	if (parent->curframe > state->curframe &&
+ 	    regno >= BPF_REG_6) {
+ 		/* for callee saved regs we have to skip the whole chain
+ 		 * of states that belong to callee and mark as LIVE_READ
+ 		 * the registers before the call
+ 		 */
+ 		tmp = parent;
+ 		while (tmp && tmp->curframe != state->curframe) {
+ 			tmp = tmp->parent;
+ 		}
+ 		if (!tmp)
+ 			goto bug;
+ 		parent = tmp;
+ 	} else {
+ 		goto bug;
+ 	}
+ 	return parent;
+ bug:
+ 	verbose(env, "verifier bug regno %d tmp %p\n", regno, tmp);
+ 	verbose(env, "regno %d parent frame %d current frame %d\n",
+ 		regno, parent->curframe, state->curframe);
+ 	return NULL;
+ }
+ 
+ static int mark_reg_read(struct bpf_verifier_env *env,
+ 			 const struct bpf_verifier_state *state,
+ 			 struct bpf_verifier_state *parent,
+ 			 u32 regno)
+ {
+ 	bool writes = parent == state->parent; /* Observe write marks */
if (regno == BPF_REG_FP)
    	/* We don't need to worry about FP liveness because it's read-only */
- 		return;
+ 		return 0;
while (parent) {
    	/* if read wasn't screened by an earlier write ... */
- 		if (state->regs[regno].live & REG_LIVE_WRITTEN)
+ 		if (writes && state->frame[state->curframe]->regs[regno].live & REG_LIVE_WRITTEN)
    		break;
+ 		parent = skip_callee(env, state, parent, regno);
+ 		if (!parent)
+ 			return -EFAULT;
    	/* ... then we depend on parent's value */
- 		parent->regs[regno].live |= REG_LIVE_READ;
+ 		parent->frame[parent->curframe]->regs[regno].live |= REG_LIVE_READ;
    	state = parent;
    	parent = state->parent;
+ 		writes = true;
    }
+ 	return 0;
  }
static int check_reg_arg(struct bpf_verifier_env *env, u32 regno,
    		 enum reg_arg_type t)
  {
- 	struct bpf_reg_state *regs = env->cur_state->regs;
+ 	struct bpf_verifier_state *vstate = env->cur_state;
+ 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ 	struct bpf_reg_state *regs = state->regs;
if (regno >= MAX_BPF_REG) {
    	verbose(env, "R%d is invalid\n", regno);
@@@ -655,7 -928,7 +928,7 @@@
    		verbose(env, "R%d !read_ok\n", regno);
    		return -EACCES;
    	}
- 		mark_reg_read(env->cur_state, regno);
+ 		return mark_reg_read(env, vstate, vstate->parent, regno);
    } else {
    	/* check whether register used as dest operand can be written to */
    	if (regno == BPF_REG_FP) {
@@@ -686,17 -959,25 +959,25 @@@ static bool is_spillable_regtype(enum b
    }
  }
+ /* Does this register contain a constant zero? */
+ static bool register_is_null(struct bpf_reg_state *reg)
+ {
+ 	return reg->type == SCALAR_VALUE && tnum_equals_const(reg->var_off, 0);
+ }
+ 
  /* check_stack_read/write functions track spill/fill of registers,
   * stack boundary and alignment are checked in check_mem_access()
   */
  static int check_stack_write(struct bpf_verifier_env *env,
- 			     struct bpf_verifier_state *state, int off,
- 			     int size, int value_regno)
+ 			     struct bpf_func_state *state, /* func where register points to */
+ 			     int off, int size, int value_regno)
  {
+ 	struct bpf_func_state *cur; /* state of the current function */
    int i, slot = -off - 1, spi = slot / BPF_REG_SIZE, err;
+ 	enum bpf_reg_type type;
- 	err = realloc_verifier_state(state, round_up(slot + 1, BPF_REG_SIZE),
- 				     true);
+ 	err = realloc_func_state(state, round_up(slot + 1, BPF_REG_SIZE),
+ 				 true);
    if (err)
    	return err;
    /* caller checked that off % size == 0 and -MAX_BPF_STACK <= off < 0,
@@@ -709,8 -990,9 +990,9 @@@
    	return -EACCES;
    }
+ 	cur = env->cur_state->frame[env->cur_state->curframe];
    if (value_regno >= 0 &&
- 	    is_spillable_regtype(state->regs[value_regno].type)) {
+ 	    is_spillable_regtype((type = cur->regs[value_regno].type))) {
/* register containing pointer is being spilled into stack */
    	if (size != BPF_REG_SIZE) {
@@@ -718,51 -1000,116 +1000,116 @@@
    		return -EACCES;
    	}
+ 		if (state != cur && type == PTR_TO_STACK) {
+ 			verbose(env, "cannot spill pointers to stack into stack frame of the caller\n");
+ 			return -EINVAL;
+ 		}
+ 
    	/* save register state */
- 		state->stack[spi].spilled_ptr = state->regs[value_regno];
+ 		state->stack[spi].spilled_ptr = cur->regs[value_regno];
    	state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
for (i = 0; i < BPF_REG_SIZE; i++)
    		state->stack[spi].slot_type[i] = STACK_SPILL;
    } else {
+ 		u8 type = STACK_MISC;
+ 
    	/* regular write of data into stack */
    	state->stack[spi].spilled_ptr = (struct bpf_reg_state) {};
+ 		/* only mark the slot as written if all 8 bytes were written
+ 		 * otherwise read propagation may incorrectly stop too soon
+ 		 * when stack slots are partially written.
+ 		 * This heuristic means that read propagation will be
+ 		 * conservative, since it will add reg_live_read marks
+ 		 * to stack slots all the way to first state when programs
+ 		 * writes+reads less than 8 bytes
+ 		 */
+ 		if (size == BPF_REG_SIZE)
+ 			state->stack[spi].spilled_ptr.live |= REG_LIVE_WRITTEN;
+ 
+ 		/* when we zero initialize stack slots mark them as such */
+ 		if (value_regno >= 0 &&
+ 		    register_is_null(&cur->regs[value_regno]))
+ 			type = STACK_ZERO;
+ 
    	for (i = 0; i < size; i++)
    		state->stack[spi].slot_type[(slot - i) % BPF_REG_SIZE] =
- 				STACK_MISC;
+ 				type;
    }
    return 0;
  }
- static void mark_stack_slot_read(const struct bpf_verifier_state *state, int slot)
+ /* registers of every function are unique and mark_reg_read() propagates
+  * the liveness in the following cases:
+  * - from callee into caller for R1 - R5 that were used as arguments
+  * - from caller into callee for R0 that used as result of the call
+  * - from caller to the same caller skipping states of the callee for R6 - R9,
+  *   since R6 - R9 are callee saved by implicit function prologue and
+  *   caller's R6 != callee's R6, so when we propagate liveness up to
+  *   parent states we need to skip callee states for R6 - R9.
+  *
+  * stack slot marking is different, since stacks of caller and callee are
+  * accessible in both (since caller can pass a pointer to caller's stack to
+  * callee which can pass it to another function), hence mark_stack_slot_read()
+  * has to propagate the stack liveness to all parent states at given frame number.
+  * Consider code:
+  * f1() {
+  *   ptr = fp - 8;
+  *   *ptr = ctx;
+  *   call f2 {
+  *      .. = *ptr;
+  *   }
+  *   .. = *ptr;
+  * }
+  * First *ptr is reading from f1's stack and mark_stack_slot_read() has
+  * to mark liveness at the f1's frame and not f2's frame.
+  * Second *ptr is also reading from f1's stack and mark_stack_slot_read() has
+  * to propagate liveness to f2 states at f1's frame level and further into
+  * f1 states at f1's frame level until write into that stack slot
+  */
+ static void mark_stack_slot_read(struct bpf_verifier_env *env,
+ 				 const struct bpf_verifier_state *state,
+ 				 struct bpf_verifier_state *parent,
+ 				 int slot, int frameno)
  {
- 	struct bpf_verifier_state *parent = state->parent;
+ 	bool writes = parent == state->parent; /* Observe write marks */
while (parent) {
+ 		if (parent->frame[frameno]->allocated_stack <= slot * BPF_REG_SIZE)
+ 			/* since LIVE_WRITTEN mark is only done for full 8-byte
+ 			 * write the read marks are conservative and parent
+ 			 * state may not even have the stack allocated. In such case
+ 			 * end the propagation, since the loop reached beginning
+ 			 * of the function
+ 			 */
+ 			break;
    	/* if read wasn't screened by an earlier write ... */
- 		if (state->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN)
+ 		if (writes && state->frame[frameno]->stack[slot].spilled_ptr.live & REG_LIVE_WRITTEN)
    		break;
    	/* ... then we depend on parent's value */
- 		parent->stack[slot].spilled_ptr.live |= REG_LIVE_READ;
+ 		parent->frame[frameno]->stack[slot].spilled_ptr.live |= REG_LIVE_READ;
    	state = parent;
    	parent = state->parent;
+ 		writes = true;
    }
  }
static int check_stack_read(struct bpf_verifier_env *env,
- 			    struct bpf_verifier_state *state, int off, int size,
- 			    int value_regno)
+ 			    struct bpf_func_state *reg_state /* func where register points to */,
+ 			    int off, int size, int value_regno)
  {
+ 	struct bpf_verifier_state *vstate = env->cur_state;
+ 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
    int i, slot = -off - 1, spi = slot / BPF_REG_SIZE;
    u8 *stype;
- 	if (state->allocated_stack <= slot) {
+ 	if (reg_state->allocated_stack <= slot) {
    	verbose(env, "invalid read from stack off %d+0 size %d\n",
    		off, size);
    	return -EACCES;
    }
- 	stype = state->stack[spi].slot_type;
+ 	stype = reg_state->stack[spi].slot_type;
if (stype[0] == STACK_SPILL) {
    	if (size != BPF_REG_SIZE) {
@@@ -778,21 -1125,44 +1125,44 @@@
if (value_regno >= 0) {
    		/* restore register state from stack */
- 			state->regs[value_regno] = state->stack[spi].spilled_ptr;
- 			mark_stack_slot_read(state, spi);
+ 			state->regs[value_regno] = reg_state->stack[spi].spilled_ptr;
+ 			/* mark reg as written since spilled pointer state likely
+ 			 * has its liveness marks cleared by is_state_visited()
+ 			 * which resets stack/reg liveness for state transitions
+ 			 */
+ 			state->regs[value_regno].live |= REG_LIVE_WRITTEN;
    	}
+ 		mark_stack_slot_read(env, vstate, vstate->parent, spi,
+ 				     reg_state->frameno);
    	return 0;
    } else {
+ 		int zeros = 0;
+ 
    	for (i = 0; i < size; i++) {
- 			if (stype[(slot - i) % BPF_REG_SIZE] != STACK_MISC) {
- 				verbose(env, "invalid read from stack off %d+%d size %d\n",
- 					off, i, size);
- 				return -EACCES;
+ 			if (stype[(slot - i) % BPF_REG_SIZE] == STACK_MISC)
+ 				continue;
+ 			if (stype[(slot - i) % BPF_REG_SIZE] == STACK_ZERO) {
+ 				zeros++;
+ 				continue;
+ 			}
+ 			verbose(env, "invalid read from stack off %d+%d size %d\n",
+ 				off, i, size);
+ 			return -EACCES;
+ 		}
+ 		mark_stack_slot_read(env, vstate, vstate->parent, spi,
+ 				     reg_state->frameno);
+ 		if (value_regno >= 0) {
+ 			if (zeros == size) {
+ 				/* any size read into register is zero extended,
+ 				 * so the whole register == const_zero
+ 				 */
+ 				__mark_reg_const_zero(&state->regs[value_regno]);
+ 			} else {
+ 				/* have read misc data from the stack */
+ 				mark_reg_unknown(env, state->regs, value_regno);
    		}
+ 			state->regs[value_regno].live |= REG_LIVE_WRITTEN;
    	}
- 		if (value_regno >= 0)
- 			/* have read misc data from the stack */
- 			mark_reg_unknown(env, state->regs, value_regno);
    	return 0;
    }
  }
@@@ -817,7 -1187,8 +1187,8 @@@ static int __check_map_access(struct bp
  static int check_map_access(struct bpf_verifier_env *env, u32 regno,
    		    int off, int size, bool zero_size_allowed)
  {
- 	struct bpf_verifier_state *state = env->cur_state;
+ 	struct bpf_verifier_state *vstate = env->cur_state;
+ 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
    struct bpf_reg_state *reg = &state->regs[regno];
    int err;
@@@ -1072,6 -1443,103 +1443,103 @@@ static int check_ptr_alignment(struct b
    				   strict);
  }
+ static int update_stack_depth(struct bpf_verifier_env *env,
+ 			      const struct bpf_func_state *func,
+ 			      int off)
+ {
+ 	u16 stack = env->subprog_stack_depth[func->subprogno];
+ 
+ 	if (stack >= -off)
+ 		return 0;
+ 
+ 	/* update known max for given subprogram */
+ 	env->subprog_stack_depth[func->subprogno] = -off;
+ 	return 0;
+ }
+ 
+ /* starting from main bpf function walk all instructions of the function
+  * and recursively walk all callees that given function can call.
+  * Ignore jump and exit insns.
+  * Since recursion is prevented by check_cfg() this algorithm
+  * only needs a local stack of MAX_CALL_FRAMES to remember callsites
+  */
+ static int check_max_stack_depth(struct bpf_verifier_env *env)
+ {
+ 	int depth = 0, frame = 0, subprog = 0, i = 0, subprog_end;
+ 	struct bpf_insn *insn = env->prog->insnsi;
+ 	int insn_cnt = env->prog->len;
+ 	int ret_insn[MAX_CALL_FRAMES];
+ 	int ret_prog[MAX_CALL_FRAMES];
+ 
+ process_func:
+ 	/* round up to 32-bytes, since this is granularity
+ 	 * of interpreter stack size
+ 	 */
+ 	depth += round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
+ 	if (depth > MAX_BPF_STACK) {
+ 		verbose(env, "combined stack size of %d calls is %d. Too large\n",
+ 			frame + 1, depth);
+ 		return -EACCES;
+ 	}
+ continue_func:
+ 	if (env->subprog_cnt == subprog)
+ 		subprog_end = insn_cnt;
+ 	else
+ 		subprog_end = env->subprog_starts[subprog];
+ 	for (; i < subprog_end; i++) {
+ 		if (insn[i].code != (BPF_JMP | BPF_CALL))
+ 			continue;
+ 		if (insn[i].src_reg != BPF_PSEUDO_CALL)
+ 			continue;
+ 		/* remember insn and function to return to */
+ 		ret_insn[frame] = i + 1;
+ 		ret_prog[frame] = subprog;
+ 
+ 		/* find the callee */
+ 		i = i + insn[i].imm + 1;
+ 		subprog = find_subprog(env, i);
+ 		if (subprog < 0) {
+ 			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
+ 				  i);
+ 			return -EFAULT;
+ 		}
+ 		subprog++;
+ 		frame++;
+ 		if (frame >= MAX_CALL_FRAMES) {
+ 			WARN_ONCE(1, "verifier bug. Call stack is too deep\n");
+ 			return -EFAULT;
+ 		}
+ 		goto process_func;
+ 	}
+ 	/* end of for() loop means the last insn of the 'subprog'
+ 	 * was reached. Doesn't matter whether it was JA or EXIT
+ 	 */
+ 	if (frame == 0)
+ 		return 0;
+ 	depth -= round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32);
+ 	frame--;
+ 	i = ret_insn[frame];
+ 	subprog = ret_prog[frame];
+ 	goto continue_func;
+ }
+ 
+ #ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ static int get_callee_stack_depth(struct bpf_verifier_env *env,
+ 				  const struct bpf_insn *insn, int idx)
+ {
+ 	int start = idx + insn->imm + 1, subprog;
+ 
+ 	subprog = find_subprog(env, start);
+ 	if (subprog < 0) {
+ 		WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
+ 			  start);
+ 		return -EFAULT;
+ 	}
+ 	subprog++;
+ 	return env->subprog_stack_depth[subprog];
+ }
+ #endif
+ 
  /* truncate register to smaller size (in bytes)
   * must be called with size < BPF_REG_SIZE
   */
@@@ -1105,9 -1573,9 +1573,9 @@@ static int check_mem_access(struct bpf_
    		    int bpf_size, enum bpf_access_type t,
    		    int value_regno)
  {
- 	struct bpf_verifier_state *state = env->cur_state;
    struct bpf_reg_state *regs = cur_regs(env);
    struct bpf_reg_state *reg = regs + regno;
+ 	struct bpf_func_state *state;
    int size, err = 0;
size = bpf_size_to_bytes(bpf_size);
@@@ -1196,8 -1664,10 +1664,10 @@@
    		return -EACCES;
    	}
- 		if (env->prog->aux->stack_depth < -off)
- 			env->prog->aux->stack_depth = -off;
+ 		state = func(env, reg);
+ 		err = update_stack_depth(env, state, off);
+ 		if (err)
+ 			return err;
if (t == BPF_WRITE)
    		err = check_stack_write(env, state, off, size,
@@@ -1269,12 -1739,6 +1739,6 @@@ static int check_xadd(struct bpf_verifi
    			BPF_SIZE(insn->code), BPF_WRITE, -1);
  }
- /* Does this register contain a constant zero? */
- static bool register_is_null(struct bpf_reg_state reg)
- {
- 	return reg.type == SCALAR_VALUE && tnum_equals_const(reg.var_off, 0);
- }
- 
  /* when register 'regno' is passed into function that will read 'access_size'
   * bytes from that pointer, make sure that it's within stack boundary
   * and all elements of stack are initialized.
@@@ -1285,32 -1749,32 +1749,32 @@@ static int check_stack_boundary(struct 
    			int access_size, bool zero_size_allowed,
    			struct bpf_call_arg_meta *meta)
  {
- 	struct bpf_verifier_state *state = env->cur_state;
- 	struct bpf_reg_state *regs = state->regs;
+ 	struct bpf_reg_state *reg = cur_regs(env) + regno;
+ 	struct bpf_func_state *state = func(env, reg);
    int off, i, slot, spi;
- 	if (regs[regno].type != PTR_TO_STACK) {
+ 	if (reg->type != PTR_TO_STACK) {
    	/* Allow zero-byte read from NULL, regardless of pointer type */
    	if (zero_size_allowed && access_size == 0 &&
- 		    register_is_null(regs[regno]))
+ 		    register_is_null(reg))
    		return 0;
verbose(env, "R%d type=%s expected=%s\n", regno,
- 			reg_type_str[regs[regno].type],
+ 			reg_type_str[reg->type],
    		reg_type_str[PTR_TO_STACK]);
    	return -EACCES;
    }
/* Only allow fixed-offset stack reads */
- 	if (!tnum_is_const(regs[regno].var_off)) {
+ 	if (!tnum_is_const(reg->var_off)) {
    	char tn_buf[48];
- 		tnum_strn(tn_buf, sizeof(tn_buf), regs[regno].var_off);
+ 		tnum_strn(tn_buf, sizeof(tn_buf), reg->var_off);
    	verbose(env, "invalid variable stack read R%d var_off=%s\n",
    		regno, tn_buf);
    	return -EACCES;
    }
- 	off = regs[regno].off + regs[regno].var_off.value;
+ 	off = reg->off + reg->var_off.value;
    if (off >= 0 || off < -MAX_BPF_STACK || off + access_size > 0 ||
        access_size < 0 || (access_size == 0 && !zero_size_allowed)) {
    	verbose(env, "invalid stack type R%d off=%d access_size=%d\n",
@@@ -1318,9 -1782,6 +1782,6 @@@
    	return -EACCES;
    }
- 	if (env->prog->aux->stack_depth < -off)
- 		env->prog->aux->stack_depth = -off;
- 
    if (meta && meta->raw_mode) {
    	meta->access_size = access_size;
    	meta->regno = regno;
@@@ -1328,17 -1789,32 +1789,32 @@@
    }
for (i = 0; i < access_size; i++) {
+ 		u8 *stype;
+ 
    	slot = -(off + i) - 1;
    	spi = slot / BPF_REG_SIZE;
- 		if (state->allocated_stack <= slot ||
- 		    state->stack[spi].slot_type[slot % BPF_REG_SIZE] !=
- 			STACK_MISC) {
- 			verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
- 				off, i, access_size);
- 			return -EACCES;
+ 		if (state->allocated_stack <= slot)
+ 			goto err;
+ 		stype = &state->stack[spi].slot_type[slot % BPF_REG_SIZE];
+ 		if (*stype == STACK_MISC)
+ 			goto mark;
+ 		if (*stype == STACK_ZERO) {
+ 			/* helper can write anything into the stack */
+ 			*stype = STACK_MISC;
+ 			goto mark;
    	}
+ err:
+ 		verbose(env, "invalid indirect read from stack off %d+%d size %d\n",
+ 			off, i, access_size);
+ 		return -EACCES;
+ mark:
+ 		/* reading any byte out of 8-byte 'spill_slot' will cause
+ 		 * the whole slot to be marked as 'read'
+ 		 */
+ 		mark_stack_slot_read(env, env->cur_state, env->cur_state->parent,
+ 				     spi, state->frameno);
    }
- 	return 0;
+ 	return update_stack_depth(env, state, off);
  }
static int check_helper_mem_access(struct bpf_verifier_env *env, int regno,
@@@ -1418,7 -1894,7 +1894,7 @@@ static int check_func_arg(struct bpf_ve
    	 * passed in as argument, it's a SCALAR_VALUE type. Final test
    	 * happens during stack boundary checking.
    	 */
- 		if (register_is_null(*reg) &&
+ 		if (register_is_null(reg) &&
    	    arg_type == ARG_PTR_TO_MEM_OR_NULL)
    		/* final test in check_stack_boundary() */;
    	else if (!type_is_pkt_pointer(type) &&
@@@ -1591,6 -2067,10 +2067,10 @@@ static int check_map_func_compatibility
    case BPF_FUNC_tail_call:
    	if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY)
    		goto error;
+ 		if (env->subprog_cnt) {
+ 			verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n");
+ 			return -EINVAL;
+ 		}
    	break;
    case BPF_FUNC_perf_event_read:
    case BPF_FUNC_perf_event_output:
@@@ -1652,9 -2132,9 +2132,9 @@@ static int check_raw_mode(const struct 
  /* Packet data might have moved, any old PTR_TO_PACKET[_META,_END]
   * are now invalid, so turn them into unknown SCALAR_VALUE.
   */
- static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
+ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env,
+ 				     struct bpf_func_state *state)
  {
- 	struct bpf_verifier_state *state = env->cur_state;
    struct bpf_reg_state *regs = state->regs, *reg;
    int i;
@@@ -1671,7 -2151,121 +2151,121 @@@
    }
  }
- static int check_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
+ static void clear_all_pkt_pointers(struct bpf_verifier_env *env)
+ {
+ 	struct bpf_verifier_state *vstate = env->cur_state;
+ 	int i;
+ 
+ 	for (i = 0; i <= vstate->curframe; i++)
+ 		__clear_all_pkt_pointers(env, vstate->frame[i]);
+ }
+ 
+ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
+ 			   int *insn_idx)
+ {
+ 	struct bpf_verifier_state *state = env->cur_state;
+ 	struct bpf_func_state *caller, *callee;
+ 	int i, subprog, target_insn;
+ 
+ 	if (state->curframe + 1 >= MAX_CALL_FRAMES) {
+ 		verbose(env, "the call stack of %d frames is too deep\n",
+ 			state->curframe + 2);
+ 		return -E2BIG;
+ 	}
+ 
+ 	target_insn = *insn_idx + insn->imm;
+ 	subprog = find_subprog(env, target_insn + 1);
+ 	if (subprog < 0) {
+ 		verbose(env, "verifier bug. No program starts at insn %d\n",
+ 			target_insn + 1);
+ 		return -EFAULT;
+ 	}
+ 
+ 	caller = state->frame[state->curframe];
+ 	if (state->frame[state->curframe + 1]) {
+ 		verbose(env, "verifier bug. Frame %d already allocated\n",
+ 			state->curframe + 1);
+ 		return -EFAULT;
+ 	}
+ 
+ 	callee = kzalloc(sizeof(*callee), GFP_KERNEL);
+ 	if (!callee)
+ 		return -ENOMEM;
+ 	state->frame[state->curframe + 1] = callee;
+ 
+ 	/* callee cannot access r0, r6 - r9 for reading and has to write
+ 	 * into its own stack before reading from it.
+ 	 * callee can read/write into caller's stack
+ 	 */
+ 	init_func_state(env, callee,
+ 			/* remember the callsite, it will be used by bpf_exit */
+ 			*insn_idx /* callsite */,
+ 			state->curframe + 1 /* frameno within this callchain */,
+ 			subprog + 1 /* subprog number within this prog */);
+ 
+ 	/* copy r1 - r5 args that callee can access */
+ 	for (i = BPF_REG_1; i <= BPF_REG_5; i++)
+ 		callee->regs[i] = caller->regs[i];
+ 
+ 	/* after the call regsiters r0 - r5 were scratched */
+ 	for (i = 0; i < CALLER_SAVED_REGS; i++) {
+ 		mark_reg_not_init(env, caller->regs, caller_saved[i]);
+ 		check_reg_arg(env, caller_saved[i], DST_OP_NO_MARK);
+ 	}
+ 
+ 	/* only increment it after check_reg_arg() finished */
+ 	state->curframe++;
+ 
+ 	/* and go analyze first insn of the callee */
+ 	*insn_idx = target_insn;
+ 
+ 	if (env->log.level) {
+ 		verbose(env, "caller:\n");
+ 		print_verifier_state(env, caller);
+ 		verbose(env, "callee:\n");
+ 		print_verifier_state(env, callee);
+ 	}
+ 	return 0;
+ }
+ 
+ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
+ {
+ 	struct bpf_verifier_state *state = env->cur_state;
+ 	struct bpf_func_state *caller, *callee;
+ 	struct bpf_reg_state *r0;
+ 
+ 	callee = state->frame[state->curframe];
+ 	r0 = &callee->regs[BPF_REG_0];
+ 	if (r0->type == PTR_TO_STACK) {
+ 		/* technically it's ok to return caller's stack pointer
+ 		 * (or caller's caller's pointer) back to the caller,
+ 		 * since these pointers are valid. Only current stack
+ 		 * pointer will be invalid as soon as function exits,
+ 		 * but let's be conservative
+ 		 */
+ 		verbose(env, "cannot return stack pointer to the caller\n");
+ 		return -EINVAL;
+ 	}
+ 
+ 	state->curframe--;
+ 	caller = state->frame[state->curframe];
+ 	/* return to the caller whatever r0 had in the callee */
+ 	caller->regs[BPF_REG_0] = *r0;
+ 
+ 	*insn_idx = callee->callsite + 1;
+ 	if (env->log.level) {
+ 		verbose(env, "returning from callee:\n");
+ 		print_verifier_state(env, callee);
+ 		verbose(env, "to caller at %d:\n", *insn_idx);
+ 		print_verifier_state(env, caller);
+ 	}
+ 	/* clear everything in the callee */
+ 	free_func_state(callee);
+ 	state->frame[state->curframe + 1] = NULL;
+ 	return 0;
+ }
+ 
+ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx)
  {
    const struct bpf_func_proto *fn = NULL;
    struct bpf_reg_state *regs;
@@@ -1871,7 -2465,9 +2465,9 @@@ static int adjust_ptr_min_max_vals(stru
    			   const struct bpf_reg_state *ptr_reg,
    			   const struct bpf_reg_state *off_reg)
  {
- 	struct bpf_reg_state *regs = cur_regs(env), *dst_reg;
+ 	struct bpf_verifier_state *vstate = env->cur_state;
+ 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ 	struct bpf_reg_state *regs = state->regs, *dst_reg;
    bool known = tnum_is_const(off_reg->var_off);
    s64 smin_val = off_reg->smin_value, smax_val = off_reg->smax_value,
        smin_ptr = ptr_reg->smin_value, smax_ptr = ptr_reg->smax_value;
@@@ -1883,13 -2479,13 +2479,13 @@@
    dst_reg = &regs[dst];
if (WARN_ON_ONCE(known && (smin_val != smax_val))) {
- 		print_verifier_state(env, env->cur_state);
+ 		print_verifier_state(env, state);
    	verbose(env,
    		"verifier internal error: known but bad sbounds\n");
    	return -EINVAL;
    }
    if (WARN_ON_ONCE(known && (umin_val != umax_val))) {
- 		print_verifier_state(env, env->cur_state);
+ 		print_verifier_state(env, state);
    	verbose(env,
    		"verifier internal error: known but bad ubounds\n");
    	return -EINVAL;
@@@ -2301,7 -2897,9 +2897,9 @@@ static int adjust_scalar_min_max_vals(s
  static int adjust_reg_min_max_vals(struct bpf_verifier_env *env,
    			   struct bpf_insn *insn)
  {
- 	struct bpf_reg_state *regs = cur_regs(env), *dst_reg, *src_reg;
+ 	struct bpf_verifier_state *vstate = env->cur_state;
+ 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
+ 	struct bpf_reg_state *regs = state->regs, *dst_reg, *src_reg;
    struct bpf_reg_state *ptr_reg = NULL, off_reg = {0};
    u8 opcode = BPF_OP(insn->code);
@@@ -2352,12 -2950,12 +2950,12 @@@
/* Got here implies adding two SCALAR_VALUEs */
    if (WARN_ON_ONCE(ptr_reg)) {
- 		print_verifier_state(env, env->cur_state);
+ 		print_verifier_state(env, state);
    	verbose(env, "verifier internal error: unexpected ptr_reg\n");
    	return -EINVAL;
    }
    if (WARN_ON(!src_reg)) {
- 		print_verifier_state(env, env->cur_state);
+ 		print_verifier_state(env, state);
    	verbose(env, "verifier internal error: no src_reg\n");
    	return -EINVAL;
    }
@@@ -2493,11 -3091,6 +3091,11 @@@ static int check_alu_op(struct bpf_veri
    		return -EINVAL;
    	}
+		if (opcode == BPF_ARSH && BPF_CLASS(insn->code) != BPF_ALU64) {
 +			verbose(env, "BPF_ARSH not supported for 32 bit ALU\n");
 +			return -EINVAL;
 +		}
 +
    	if ((opcode == BPF_LSH || opcode == BPF_RSH ||
    	     opcode == BPF_ARSH) && BPF_SRC(insn->code) == BPF_K) {
    		int size = BPF_CLASS(insn->code) == BPF_ALU64 ? 64 : 32;
@@@ -2519,14 -3112,15 +3117,15 @@@
    return 0;
  }
- static void find_good_pkt_pointers(struct bpf_verifier_state *state,
+ static void find_good_pkt_pointers(struct bpf_verifier_state *vstate,
    			   struct bpf_reg_state *dst_reg,
    			   enum bpf_reg_type type,
    			   bool range_right_open)
  {
+ 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
    struct bpf_reg_state *regs = state->regs, *reg;
    u16 new_range;
- 	int i;
+ 	int i, j;
if (dst_reg->off < 0 ||
        (dst_reg->off == 0 && range_right_open))
@@@ -2596,12 -3190,15 +3195,15 @@@
    		/* keep the maximum range already checked */
    		regs[i].range = max(regs[i].range, new_range);
- 	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
- 		if (state->stack[i].slot_type[0] != STACK_SPILL)
- 			continue;
- 		reg = &state->stack[i].spilled_ptr;
- 		if (reg->type == type && reg->id == dst_reg->id)
- 			reg->range = max(reg->range, new_range);
+ 	for (j = 0; j <= vstate->curframe; j++) {
+ 		state = vstate->frame[j];
+ 		for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ 			if (state->stack[i].slot_type[0] != STACK_SPILL)
+ 				continue;
+ 			reg = &state->stack[i].spilled_ptr;
+ 			if (reg->type == type && reg->id == dst_reg->id)
+ 				reg->range = max(reg->range, new_range);
+ 		}
    }
  }
@@@ -2839,20 -3436,24 +3441,24 @@@ static void mark_map_reg(struct bpf_reg
  /* The logic is similar to find_good_pkt_pointers(), both could eventually
   * be folded together at some point.
   */
- static void mark_map_regs(struct bpf_verifier_state *state, u32 regno,
+ static void mark_map_regs(struct bpf_verifier_state *vstate, u32 regno,
    		  bool is_null)
  {
+ 	struct bpf_func_state *state = vstate->frame[vstate->curframe];
    struct bpf_reg_state *regs = state->regs;
    u32 id = regs[regno].id;
- 	int i;
+ 	int i, j;
for (i = 0; i < MAX_BPF_REG; i++)
    	mark_map_reg(regs, i, id, is_null);
- 	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
- 		if (state->stack[i].slot_type[0] != STACK_SPILL)
- 			continue;
- 		mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null);
+ 	for (j = 0; j <= vstate->curframe; j++) {
+ 		state = vstate->frame[j];
+ 		for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
+ 			if (state->stack[i].slot_type[0] != STACK_SPILL)
+ 				continue;
+ 			mark_map_reg(&state->stack[i].spilled_ptr, 0, id, is_null);
+ 		}
    }
  }
@@@ -2952,8 -3553,10 +3558,10 @@@ static bool try_match_pkt_pointers(cons
  static int check_cond_jmp_op(struct bpf_verifier_env *env,
    		     struct bpf_insn *insn, int *insn_idx)
  {
- 	struct bpf_verifier_state *other_branch, *this_branch = env->cur_state;
- 	struct bpf_reg_state *regs = this_branch->regs, *dst_reg;
+ 	struct bpf_verifier_state *this_branch = env->cur_state;
+ 	struct bpf_verifier_state *other_branch;
+ 	struct bpf_reg_state *regs = this_branch->frame[this_branch->curframe]->regs;
+ 	struct bpf_reg_state *dst_reg, *other_branch_regs;
    u8 opcode = BPF_OP(insn->code);
    int err;
@@@ -2996,8 -3599,9 +3604,9 @@@
    if (BPF_SRC(insn->code) == BPF_K &&
        (opcode == BPF_JEQ || opcode == BPF_JNE) &&
        dst_reg->type == SCALAR_VALUE &&
- 	    tnum_equals_const(dst_reg->var_off, insn->imm)) {
- 		if (opcode == BPF_JEQ) {
+ 	    tnum_is_const(dst_reg->var_off)) {
+ 		if ((opcode == BPF_JEQ && dst_reg->var_off.value == insn->imm) ||
+ 		    (opcode == BPF_JNE && dst_reg->var_off.value != insn->imm)) {
    		/* if (imm == imm) goto pc+off;
    		 * only follow the goto, ignore fall-through
    		 */
@@@ -3015,6 -3619,7 +3624,7 @@@
    other_branch = push_stack(env, *insn_idx + insn->off + 1, *insn_idx);
    if (!other_branch)
    	return -EFAULT;
+ 	other_branch_regs = other_branch->frame[other_branch->curframe]->regs;
/* detect if we are comparing against a constant value so we can adjust
     * our min/max values for our dst register.
@@@ -3027,22 -3632,22 +3637,22 @@@
    	if (dst_reg->type == SCALAR_VALUE &&
    	    regs[insn->src_reg].type == SCALAR_VALUE) {
    		if (tnum_is_const(regs[insn->src_reg].var_off))
- 				reg_set_min_max(&other_branch->regs[insn->dst_reg],
+ 				reg_set_min_max(&other_branch_regs[insn->dst_reg],
    					dst_reg, regs[insn->src_reg].var_off.value,
    					opcode);
    		else if (tnum_is_const(dst_reg->var_off))
- 				reg_set_min_max_inv(&other_branch->regs[insn->src_reg],
+ 				reg_set_min_max_inv(&other_branch_regs[insn->src_reg],
    					    &regs[insn->src_reg],
    					    dst_reg->var_off.value, opcode);
    		else if (opcode == BPF_JEQ || opcode == BPF_JNE)
    			/* Comparing for equality, we can combine knowledge */
- 				reg_combine_min_max(&other_branch->regs[insn->src_reg],
- 						    &other_branch->regs[insn->dst_reg],
+ 				reg_combine_min_max(&other_branch_regs[insn->src_reg],
+ 						    &other_branch_regs[insn->dst_reg],
    					    &regs[insn->src_reg],
    					    &regs[insn->dst_reg], opcode);
    	}
    } else if (dst_reg->type == SCALAR_VALUE) {
- 		reg_set_min_max(&other_branch->regs[insn->dst_reg],
+ 		reg_set_min_max(&other_branch_regs[insn->dst_reg],
    				dst_reg, insn->imm, opcode);
    }
@@@ -3063,7 -3668,7 +3673,7 @@@
    	return -EACCES;
    }
    if (env->log.level)
- 		print_verifier_state(env, this_branch);
+ 		print_verifier_state(env, this_branch->frame[this_branch->curframe]);
    return 0;
  }
@@@ -3148,6 -3753,18 +3758,18 @@@ static int check_ld_abs(struct bpf_veri
    	return -EINVAL;
    }
+ 	if (env->subprog_cnt) {
+ 		/* when program has LD_ABS insn JITs and interpreter assume
+ 		 * that r1 == ctx == skb which is not the case for callees
+ 		 * that can have arbitrary arguments. It's problematic
+ 		 * for main prog as well since JITs would need to analyze
+ 		 * all functions in order to make proper register save/restore
+ 		 * decisions in the main prog. Hence disallow LD_ABS with calls
+ 		 */
+ 		verbose(env, "BPF_LD_[ABS|IND] instructions cannot be mixed with bpf-to-bpf calls\n");
+ 		return -EINVAL;
+ 	}
+ 
    if (insn->dst_reg != BPF_REG_0 || insn->off != 0 ||
        BPF_SIZE(insn->code) == BPF_DW ||
        (mode == BPF_ABS && insn->src_reg != BPF_REG_0)) {
@@@ -3324,6 -3941,10 +3946,10 @@@ static int check_cfg(struct bpf_verifie
    int ret = 0;
    int i, t;
+ 	ret = check_subprogs(env);
+ 	if (ret < 0)
+ 		return ret;
+ 
    insn_state = kcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
    if (!insn_state)
    	return -ENOMEM;
@@@ -3356,6 -3977,14 +3982,14 @@@ peek_stack
    			goto err_free;
    		if (t + 1 < insn_cnt)
    			env->explored_states[t + 1] = STATE_LIST_MARK;
+ 			if (insns[t].src_reg == BPF_PSEUDO_CALL) {
+ 				env->explored_states[t] = STATE_LIST_MARK;
+ 				ret = push_insn(t, t + insns[t].imm + 1, BRANCH, env);
+ 				if (ret == 1)
+ 					goto peek_stack;
+ 				else if (ret < 0)
+ 					goto err_free;
+ 			}
    	} else if (opcode == BPF_JA) {
    		if (BPF_SRC(insns[t].code) != BPF_K) {
    			ret = -EINVAL;
@@@ -3474,11 -4103,21 +4108,21 @@@ static bool check_ids(u32 old_id, u32 c
  static bool regsafe(struct bpf_reg_state *rold, struct bpf_reg_state *rcur,
    	    struct idpair *idmap)
  {
+ 	bool equal;
+ 
    if (!(rold->live & REG_LIVE_READ))
    	/* explored state didn't use this */
    	return true;
- 	if (memcmp(rold, rcur, offsetof(struct bpf_reg_state, live)) == 0)
+ 	equal = memcmp(rold, rcur, offsetof(struct bpf_reg_state, frameno)) == 0;
+ 
+ 	if (rold->type == PTR_TO_STACK)
+ 		/* two stack pointers are equal only if they're pointing to
+ 		 * the same stack frame, since fp-8 in foo != fp-8 in bar
+ 		 */
+ 		return equal && rold->frameno == rcur->frameno;
+ 
+ 	if (equal)
    	return true;
if (rold->type == NOT_INIT)
@@@ -3550,7 -4189,6 +4194,6 @@@
    	       tnum_in(rold->var_off, rcur->var_off);
    case PTR_TO_CTX:
    case CONST_PTR_TO_MAP:
- 	case PTR_TO_STACK:
    case PTR_TO_PACKET_END:
    	/* Only valid matches are exact, which memcmp() above
    	 * would have accepted
@@@ -3565,8 -4203,8 +4208,8 @@@
    return false;
  }
- static bool stacksafe(struct bpf_verifier_state *old,
- 		      struct bpf_verifier_state *cur,
+ static bool stacksafe(struct bpf_func_state *old,
+ 		      struct bpf_func_state *cur,
    	      struct idpair *idmap)
  {
    int i, spi;
@@@ -3584,8 -4222,19 +4227,19 @@@
    for (i = 0; i < old->allocated_stack; i++) {
    	spi = i / BPF_REG_SIZE;
+ 		if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ))
+ 			/* explored state didn't use this */
+ 			continue;
+ 
    	if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_INVALID)
    		continue;
+ 		/* if old state was safe with misc data in the stack
+ 		 * it will be safe with zero-initialized stack.
+ 		 * The opposite is not true
+ 		 */
+ 		if (old->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_MISC &&
+ 		    cur->stack[spi].slot_type[i % BPF_REG_SIZE] == STACK_ZERO)
+ 			continue;
    	if (old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
    	    cur->stack[spi].slot_type[i % BPF_REG_SIZE])
    		/* Ex: old explored (safe) state has STACK_SPILL in
@@@ -3642,9 -4291,8 +4296,8 @@@
   * whereas register type in current state is meaningful, it means that
   * the current state will reach 'bpf_exit' instruction safely
   */
- static bool states_equal(struct bpf_verifier_env *env,
- 			 struct bpf_verifier_state *old,
- 			 struct bpf_verifier_state *cur)
+ static bool func_states_equal(struct bpf_func_state *old,
+ 			      struct bpf_func_state *cur)
  {
    struct idpair *idmap;
    bool ret = false;
@@@ -3668,71 -4316,72 +4321,72 @@@ out_free
    return ret;
  }
+ static bool states_equal(struct bpf_verifier_env *env,
+ 			 struct bpf_verifier_state *old,
+ 			 struct bpf_verifier_state *cur)
+ {
+ 	int i;
+ 
+ 	if (old->curframe != cur->curframe)
+ 		return false;
+ 
+ 	/* for states to be equal callsites have to be the same
+ 	 * and all frame states need to be equivalent
+ 	 */
+ 	for (i = 0; i <= old->curframe; i++) {
+ 		if (old->frame[i]->callsite != cur->frame[i]->callsite)
+ 			return false;
+ 		if (!func_states_equal(old->frame[i], cur->frame[i]))
+ 			return false;
+ 	}
+ 	return true;
+ }
+ 
  /* A write screens off any subsequent reads; but write marks come from the
-  * straight-line code between a state and its parent.  When we arrive at a
-  * jump target (in the first iteration of the propagate_liveness() loop),
-  * we didn't arrive by the straight-line code, so read marks in state must
-  * propagate to parent regardless of state's write marks.
+  * straight-line code between a state and its parent.  When we arrive at an
+  * equivalent state (jump target or such) we didn't arrive by the straight-line
+  * code, so read marks in the state must propagate to the parent regardless
+  * of the state's write marks. That's what 'parent == state->parent' comparison
+  * in mark_reg_read() and mark_stack_slot_read() is for.
   */
- static bool do_propagate_liveness(const struct bpf_verifier_state *state,
- 				  struct bpf_verifier_state *parent)
+ static int propagate_liveness(struct bpf_verifier_env *env,
+ 			      const struct bpf_verifier_state *vstate,
+ 			      struct bpf_verifier_state *vparent)
  {
- 	bool writes = parent == state->parent; /* Observe write marks */
- 	bool touched = false; /* any changes made? */
- 	int i;
+ 	int i, frame, err = 0;
+ 	struct bpf_func_state *state, *parent;
- 	if (!parent)
- 		return touched;
+ 	if (vparent->curframe != vstate->curframe) {
+ 		WARN(1, "propagate_live: parent frame %d current frame %d\n",
+ 		     vparent->curframe, vstate->curframe);
+ 		return -EFAULT;
+ 	}
    /* Propagate read liveness of registers... */
    BUILD_BUG_ON(BPF_REG_FP + 1 != MAX_BPF_REG);
    /* We don't need to worry about FP liveness because it's read-only */
    for (i = 0; i < BPF_REG_FP; i++) {
- 		if (parent->regs[i].live & REG_LIVE_READ)
+ 		if (vparent->frame[vparent->curframe]->regs[i].live & REG_LIVE_READ)
    		continue;
- 		if (writes && (state->regs[i].live & REG_LIVE_WRITTEN))
- 			continue;
- 		if (state->regs[i].live & REG_LIVE_READ) {
- 			parent->regs[i].live |= REG_LIVE_READ;
- 			touched = true;
+ 		if (vstate->frame[vstate->curframe]->regs[i].live & REG_LIVE_READ) {
+ 			err = mark_reg_read(env, vstate, vparent, i);
+ 			if (err)
+ 				return err;
    	}
    }
+ 
    /* ... and stack slots */
- 	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE &&
- 		    i < parent->allocated_stack / BPF_REG_SIZE; i++) {
- 		if (parent->stack[i].slot_type[0] != STACK_SPILL)
- 			continue;
- 		if (state->stack[i].slot_type[0] != STACK_SPILL)
- 			continue;
- 		if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ)
- 			continue;
- 		if (writes &&
- 		    (state->stack[i].spilled_ptr.live & REG_LIVE_WRITTEN))
- 			continue;
- 		if (state->stack[i].spilled_ptr.live & REG_LIVE_READ) {
- 			parent->stack[i].spilled_ptr.live |= REG_LIVE_READ;
- 			touched = true;
+ 	for (frame = 0; frame <= vstate->curframe; frame++) {
+ 		state = vstate->frame[frame];
+ 		parent = vparent->frame[frame];
+ 		for (i = 0; i < state->allocated_stack / BPF_REG_SIZE &&
+ 			    i < parent->allocated_stack / BPF_REG_SIZE; i++) {
+ 			if (parent->stack[i].spilled_ptr.live & REG_LIVE_READ)
+ 				continue;
+ 			if (state->stack[i].spilled_ptr.live & REG_LIVE_READ)
+ 				mark_stack_slot_read(env, vstate, vparent, i, frame);
    	}
    }
- 	return touched;
- }
- 
- /* "parent" is "a state from which we reach the current state", but initially
-  * it is not the state->parent (i.e. "the state whose straight-line code leads
-  * to the current state"), instead it is the state that happened to arrive at
-  * a (prunable) equivalent of the current state.  See comment above
-  * do_propagate_liveness() for consequences of this.
-  * This function is just a more efficient way of calling mark_reg_read() or
-  * mark_stack_slot_read() on each reg in "parent" that is read in "state",
-  * though it requires that parent != state->parent in the call arguments.
-  */
- static void propagate_liveness(const struct bpf_verifier_state *state,
- 			       struct bpf_verifier_state *parent)
- {
- 	while (do_propagate_liveness(state, parent)) {
- 		/* Something changed, so we need to feed those changes onward */
- 		state = parent;
- 		parent = state->parent;
- 	}
+ 	return err;
  }
static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
@@@ -3740,7 -4389,7 +4394,7 @@@
    struct bpf_verifier_state_list *new_sl;
    struct bpf_verifier_state_list *sl;
    struct bpf_verifier_state *cur = env->cur_state;
- 	int i, err;
+ 	int i, j, err;
sl = env->explored_states[insn_idx];
    if (!sl)
@@@ -3761,7 -4410,9 +4415,9 @@@
    		 * they'll be immediately forgotten as we're pruning
    		 * this state and will pop a new one.
    		 */
- 			propagate_liveness(&sl->state, cur);
+ 			err = propagate_liveness(env, &sl->state, cur);
+ 			if (err)
+ 				return err;
    		return 1;
    	}
    	sl = sl->next;
@@@ -3769,9 -4420,10 +4425,10 @@@
/* there were no equivalent states, remember current one.
     * technically the current state is not proven to be safe yet,
- 	 * but it will either reach bpf_exit (which means it's safe) or
- 	 * it will be rejected. Since there are no loops, we won't be
- 	 * seeing this 'insn_idx' instruction again on the way to bpf_exit
+ 	 * but it will either reach outer most bpf_exit (which means it's safe)
+ 	 * or it will be rejected. Since there are no loops, we won't be
+ 	 * seeing this tuple (frame[0].callsite, frame[1].callsite, .. insn_idx)
+ 	 * again on the way to bpf_exit
     */
    new_sl = kzalloc(sizeof(struct bpf_verifier_state_list), GFP_KERNEL);
    if (!new_sl)
@@@ -3795,19 -4447,15 +4452,15 @@@
     * explored_states can get read marks.)
     */
    for (i = 0; i < BPF_REG_FP; i++)
- 		cur->regs[i].live = REG_LIVE_NONE;
- 	for (i = 0; i < cur->allocated_stack / BPF_REG_SIZE; i++)
- 		if (cur->stack[i].slot_type[0] == STACK_SPILL)
- 			cur->stack[i].spilled_ptr.live = REG_LIVE_NONE;
- 	return 0;
- }
+ 		cur->frame[cur->curframe]->regs[i].live = REG_LIVE_NONE;
- static int ext_analyzer_insn_hook(struct bpf_verifier_env *env,
- 				  int insn_idx, int prev_insn_idx)
- {
- 	if (env->dev_ops && env->dev_ops->insn_hook)
- 		return env->dev_ops->insn_hook(env, insn_idx, prev_insn_idx);
+ 	/* all stack frames are accessible from callee, clear them all */
+ 	for (j = 0; j <= cur->curframe; j++) {
+ 		struct bpf_func_state *frame = cur->frame[j];
+ 		for (i = 0; i < frame->allocated_stack / BPF_REG_SIZE; i++)
+ 			frame->stack[i].spilled_ptr.live = REG_LIVE_NONE;
+ 	}
    return 0;
  }
@@@ -3816,7 -4464,7 +4469,7 @@@ static int do_check(struct bpf_verifier
    struct bpf_verifier_state *state;
    struct bpf_insn *insns = env->prog->insnsi;
    struct bpf_reg_state *regs;
- 	int insn_cnt = env->prog->len;
+ 	int insn_cnt = env->prog->len, i;
    int insn_idx, prev_insn_idx = 0;
    int insn_processed = 0;
    bool do_print_state = false;
@@@ -3824,9 -4472,18 +4477,18 @@@
    state = kzalloc(sizeof(struct bpf_verifier_state), GFP_KERNEL);
    if (!state)
    	return -ENOMEM;
- 	env->cur_state = state;
- 	init_reg_state(env, state->regs);
+ 	state->curframe = 0;
    state->parent = NULL;
+ 	state->frame[0] = kzalloc(sizeof(struct bpf_func_state), GFP_KERNEL);
+ 	if (!state->frame[0]) {
+ 		kfree(state);
+ 		return -ENOMEM;
+ 	}
+ 	env->cur_state = state;
+ 	init_func_state(env, state->frame[0],
+ 			BPF_MAIN_FUNC /* callsite */,
+ 			0 /* frameno */,
+ 			0 /* subprogno, zero == main subprog */);
    insn_idx = 0;
    for (;;) {
    	struct bpf_insn *insn;
@@@ -3873,19 -4530,25 +4535,25 @@@
    		else
    			verbose(env, "\nfrom %d to %d:",
    				prev_insn_idx, insn_idx);
- 			print_verifier_state(env, state);
+ 			print_verifier_state(env, state->frame[state->curframe]);
    		do_print_state = false;
    	}
if (env->log.level) {
+ 			const struct bpf_insn_cbs cbs = {
+ 				.cb_print	= verbose,
+ 			};
+ 
    		verbose(env, "%d: ", insn_idx);
- 			print_bpf_insn(verbose, env, insn,
- 				       env->allow_ptr_leaks);
+ 			print_bpf_insn(&cbs, env, insn, env->allow_ptr_leaks);
    	}
- 		err = ext_analyzer_insn_hook(env, insn_idx, prev_insn_idx);
- 		if (err)
- 			return err;
+ 		if (bpf_prog_is_dev_bound(env->prog->aux)) {
+ 			err = bpf_prog_offload_verify_insn(env, insn_idx,
+ 							   prev_insn_idx);
+ 			if (err)
+ 				return err;
+ 		}
regs = cur_regs(env);
    	env->insn_aux_data[insn_idx].seen = true;
@@@ -4006,13 -4669,17 +4674,17 @@@
    		if (opcode == BPF_CALL) {
    			if (BPF_SRC(insn->code) != BPF_K ||
    			    insn->off != 0 ||
- 				    insn->src_reg != BPF_REG_0 ||
+ 				    (insn->src_reg != BPF_REG_0 &&
+ 				     insn->src_reg != BPF_PSEUDO_CALL) ||
    			    insn->dst_reg != BPF_REG_0) {
    				verbose(env, "BPF_CALL uses reserved fields\n");
    				return -EINVAL;
    			}
- 				err = check_call(env, insn->imm, insn_idx);
+ 				if (insn->src_reg == BPF_PSEUDO_CALL)
+ 					err = check_func_call(env, insn, &insn_idx);
+ 				else
+ 					err = check_helper_call(env, insn->imm, insn_idx);
    			if (err)
    				return err;
@@@ -4037,6 -4704,16 +4709,16 @@@
    				return -EINVAL;
    			}
+ 				if (state->curframe) {
+ 					/* exit from nested function */
+ 					prev_insn_idx = insn_idx;
+ 					err = prepare_func_exit(env, &insn_idx);
+ 					if (err)
+ 						return err;
+ 					do_print_state = true;
+ 					continue;
+ 				}
+ 
    			/* eBPF calling convetion is such that R0 is used
    			 * to return the value from eBPF program.
    			 * Make sure that it's readable at this time
@@@ -4097,8 -4774,16 +4779,16 @@@ process_bpf_exit
    	insn_idx++;
    }
- 	verbose(env, "processed %d insns, stack depth %d\n", insn_processed,
- 		env->prog->aux->stack_depth);
+ 	verbose(env, "processed %d insns, stack depth ", insn_processed);
+ 	for (i = 0; i < env->subprog_cnt + 1; i++) {
+ 		u32 depth = env->subprog_stack_depth[i];
+ 
+ 		verbose(env, "%d", depth);
+ 		if (i + 1 < env->subprog_cnt + 1)
+ 			verbose(env, "+");
+ 	}
+ 	verbose(env, "\n");
+ 	env->prog->aux->stack_depth = env->subprog_stack_depth[0];
    return 0;
  }
@@@ -4284,6 -4969,19 +4974,19 @@@ static int adjust_insn_aux_data(struct 
    return 0;
  }
+ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len)
+ {
+ 	int i;
+ 
+ 	if (len == 1)
+ 		return;
+ 	for (i = 0; i < env->subprog_cnt; i++) {
+ 		if (env->subprog_starts[i] < off)
+ 			continue;
+ 		env->subprog_starts[i] += len - 1;
+ 	}
+ }
+ 
  static struct bpf_prog *bpf_patch_insn_data(struct bpf_verifier_env *env, u32 off,
    				    const struct bpf_insn *patch, u32 len)
  {
@@@ -4294,6 -4992,7 +4997,7 @@@
    	return NULL;
    if (adjust_insn_aux_data(env, new_prog->len, off, len))
    	return NULL;
+ 	adjust_subprog_starts(env, off, len);
    return new_prog;
  }
@@@ -4428,6 -5127,180 +5132,180 @@@ static int convert_ctx_accesses(struct 
    return 0;
  }
+ static int jit_subprogs(struct bpf_verifier_env *env)
+ {
+ 	struct bpf_prog *prog = env->prog, **func, *tmp;
+ 	int i, j, subprog_start, subprog_end = 0, len, subprog;
+ 	struct bpf_insn *insn;
+ 	void *old_bpf_func;
+ 	int err = -ENOMEM;
+ 
+ 	if (env->subprog_cnt == 0)
+ 		return 0;
+ 
+ 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
+ 		if (insn->code != (BPF_JMP | BPF_CALL) ||
+ 		    insn->src_reg != BPF_PSEUDO_CALL)
+ 			continue;
+ 		subprog = find_subprog(env, i + insn->imm + 1);
+ 		if (subprog < 0) {
+ 			WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
+ 				  i + insn->imm + 1);
+ 			return -EFAULT;
+ 		}
+ 		/* temporarily remember subprog id inside insn instead of
+ 		 * aux_data, since next loop will split up all insns into funcs
+ 		 */
+ 		insn->off = subprog + 1;
+ 		/* remember original imm in case JIT fails and fallback
+ 		 * to interpreter will be needed
+ 		 */
+ 		env->insn_aux_data[i].call_imm = insn->imm;
+ 		/* point imm to __bpf_call_base+1 from JITs point of view */
+ 		insn->imm = 1;
+ 	}
+ 
+ 	func = kzalloc(sizeof(prog) * (env->subprog_cnt + 1), GFP_KERNEL);
+ 	if (!func)
+ 		return -ENOMEM;
+ 
+ 	for (i = 0; i <= env->subprog_cnt; i++) {
+ 		subprog_start = subprog_end;
+ 		if (env->subprog_cnt == i)
+ 			subprog_end = prog->len;
+ 		else
+ 			subprog_end = env->subprog_starts[i];
+ 
+ 		len = subprog_end - subprog_start;
+ 		func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER);
+ 		if (!func[i])
+ 			goto out_free;
+ 		memcpy(func[i]->insnsi, &prog->insnsi[subprog_start],
+ 		       len * sizeof(struct bpf_insn));
+ 		func[i]->type = prog->type;
+ 		func[i]->len = len;
+ 		if (bpf_prog_calc_tag(func[i]))
+ 			goto out_free;
+ 		func[i]->is_func = 1;
+ 		/* Use bpf_prog_F_tag to indicate functions in stack traces.
+ 		 * Long term would need debug info to populate names
+ 		 */
+ 		func[i]->aux->name[0] = 'F';
+ 		func[i]->aux->stack_depth = env->subprog_stack_depth[i];
+ 		func[i]->jit_requested = 1;
+ 		func[i] = bpf_int_jit_compile(func[i]);
+ 		if (!func[i]->jited) {
+ 			err = -ENOTSUPP;
+ 			goto out_free;
+ 		}
+ 		cond_resched();
+ 	}
+ 	/* at this point all bpf functions were successfully JITed
+ 	 * now populate all bpf_calls with correct addresses and
+ 	 * run last pass of JIT
+ 	 */
+ 	for (i = 0; i <= env->subprog_cnt; i++) {
+ 		insn = func[i]->insnsi;
+ 		for (j = 0; j < func[i]->len; j++, insn++) {
+ 			if (insn->code != (BPF_JMP | BPF_CALL) ||
+ 			    insn->src_reg != BPF_PSEUDO_CALL)
+ 				continue;
+ 			subprog = insn->off;
+ 			insn->off = 0;
+ 			insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
+ 				func[subprog]->bpf_func -
+ 				__bpf_call_base;
+ 		}
+ 	}
+ 	for (i = 0; i <= env->subprog_cnt; i++) {
+ 		old_bpf_func = func[i]->bpf_func;
+ 		tmp = bpf_int_jit_compile(func[i]);
+ 		if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
+ 			verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
+ 			err = -EFAULT;
+ 			goto out_free;
+ 		}
+ 		cond_resched();
+ 	}
+ 
+ 	/* finally lock prog and jit images for all functions and
+ 	 * populate kallsysm
+ 	 */
+ 	for (i = 0; i <= env->subprog_cnt; i++) {
+ 		bpf_prog_lock_ro(func[i]);
+ 		bpf_prog_kallsyms_add(func[i]);
+ 	}
+ 
+ 	/* Last step: make now unused interpreter insns from main
+ 	 * prog consistent for later dump requests, so they can
+ 	 * later look the same as if they were interpreted only.
+ 	 */
+ 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
+ 		unsigned long addr;
+ 
+ 		if (insn->code != (BPF_JMP | BPF_CALL) ||
+ 		    insn->src_reg != BPF_PSEUDO_CALL)
+ 			continue;
+ 		insn->off = env->insn_aux_data[i].call_imm;
+ 		subprog = find_subprog(env, i + insn->off + 1);
+ 		addr  = (unsigned long)func[subprog + 1]->bpf_func;
+ 		addr &= PAGE_MASK;
+ 		insn->imm = (u64 (*)(u64, u64, u64, u64, u64))
+ 			    addr - __bpf_call_base;
+ 	}
+ 
+ 	prog->jited = 1;
+ 	prog->bpf_func = func[0]->bpf_func;
+ 	prog->aux->func = func;
+ 	prog->aux->func_cnt = env->subprog_cnt + 1;
+ 	return 0;
+ out_free:
+ 	for (i = 0; i <= env->subprog_cnt; i++)
+ 		if (func[i])
+ 			bpf_jit_free(func[i]);
+ 	kfree(func);
+ 	/* cleanup main prog to be interpreted */
+ 	prog->jit_requested = 0;
+ 	for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
+ 		if (insn->code != (BPF_JMP | BPF_CALL) ||
+ 		    insn->src_reg != BPF_PSEUDO_CALL)
+ 			continue;
+ 		insn->off = 0;
+ 		insn->imm = env->insn_aux_data[i].call_imm;
+ 	}
+ 	return err;
+ }
+ 
+ static int fixup_call_args(struct bpf_verifier_env *env)
+ {
+ #ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ 	struct bpf_prog *prog = env->prog;
+ 	struct bpf_insn *insn = prog->insnsi;
+ 	int i, depth;
+ #endif
+ 	int err;
+ 
+ 	err = 0;
+ 	if (env->prog->jit_requested) {
+ 		err = jit_subprogs(env);
+ 		if (err == 0)
+ 			return 0;
+ 	}
+ #ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ 	for (i = 0; i < prog->len; i++, insn++) {
+ 		if (insn->code != (BPF_JMP | BPF_CALL) ||
+ 		    insn->src_reg != BPF_PSEUDO_CALL)
+ 			continue;
+ 		depth = get_callee_stack_depth(env, insn, i);
+ 		if (depth < 0)
+ 			return depth;
+ 		bpf_patch_call_args(insn, depth);
+ 	}
+ 	err = 0;
+ #endif
+ 	return err;
+ }
+ 
  /* fixup insn->imm field of bpf_call instructions
   * and inline eligible helpers as explicit sequence of BPF instructions
   *
@@@ -4447,11 -5320,15 +5325,15 @@@ static int fixup_bpf_calls(struct bpf_v
    for (i = 0; i < insn_cnt; i++, insn++) {
    	if (insn->code != (BPF_JMP | BPF_CALL))
    		continue;
+ 		if (insn->src_reg == BPF_PSEUDO_CALL)
+ 			continue;
if (insn->imm == BPF_FUNC_get_route_realm)
    		prog->dst_needed = 1;
    	if (insn->imm == BPF_FUNC_get_prandom_u32)
    		bpf_user_rnd_init_once();
+ 		if (insn->imm == BPF_FUNC_override_return)
+ 			prog->kprobe_override = 1;
    	if (insn->imm == BPF_FUNC_tail_call) {
    		/* If we tail call into other programs, we
    		 * cannot make any assumptions since they can
@@@ -4477,7 -5354,7 +5359,7 @@@
    		 */
    		map_ptr = env->insn_aux_data[i + delta].map_ptr;
    		if (map_ptr == BPF_MAP_PTR_POISON) {
 -				verbose(env, "tail_call obusing map_ptr\n");
 +				verbose(env, "tail_call abusing map_ptr\n");
    			return -EINVAL;
    		}
    		if (!map_ptr->unpriv_array)
@@@ -4503,7 -5380,7 +5385,7 @@@
    	/* BPF_EMIT_CALL() assumptions in some of the map_gen_lookup
    	 * handlers are currently limited to 64 bit only.
    	 */
- 		if (ebpf_jit_enabled() && BITS_PER_LONG == 64 &&
+ 		if (prog->jit_requested && BITS_PER_LONG == 64 &&
    	    insn->imm == BPF_FUNC_map_lookup_elem) {
    		map_ptr = env->insn_aux_data[i + delta].map_ptr;
    		if (map_ptr == BPF_MAP_PTR_POISON ||
@@@ -4638,7 -5515,7 +5520,7 @@@ int bpf_check(struct bpf_prog **prog, u
    if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS))
    	env->strict_alignment = true;
- 	if (env->prog->aux->offload) {
+ 	if (bpf_prog_is_dev_bound(env->prog->aux)) {
    	ret = bpf_prog_offload_verifier_prep(env);
    	if (ret)
    		goto err_unlock;
@@@ -4655,12 -5532,12 +5537,12 @@@
    if (!env->explored_states)
    	goto skip_full_check;
+ 	env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
+ 
    ret = check_cfg(env);
    if (ret < 0)
    	goto skip_full_check;
- 	env->allow_ptr_leaks = capable(CAP_SYS_ADMIN);
- 
    ret = do_check(env);
    if (env->cur_state) {
    	free_verifier_state(env->cur_state, true);
@@@ -4675,12 -5552,18 +5557,18 @@@ skip_full_check
    	sanitize_dead_code(env);
if (ret == 0)
+ 		ret = check_max_stack_depth(env);
+ 
+ 	if (ret == 0)
    	/* program is valid, convert *(u32*)(ctx + off) accesses */
    	ret = convert_ctx_accesses(env);
if (ret == 0)
    	ret = fixup_bpf_calls(env);
+ 	if (ret == 0)
+ 		ret = fixup_call_args(env);
+ 
    if (log->level && bpf_verifier_log_full(log))
    	ret = -ENOSPC;
    if (log->level && !log->ubuf) {
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/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/esp4.c
index 61fe6e4d23fc,6f00e43120a8..296d0b956bfe
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@@ -121,14 -121,32 +121,32 @@@ static void esp_ssg_unref(struct xfrm_s
  static void esp_output_done(struct crypto_async_request *base, int err)
  {
    struct sk_buff *skb = base->data;
+ 	struct xfrm_offload *xo = xfrm_offload(skb);
    void *tmp;
- 	struct dst_entry *dst = skb_dst(skb);
- 	struct xfrm_state *x = dst->xfrm;
+ 	struct xfrm_state *x;
+ 
+ 	if (xo && (xo->flags & XFRM_DEV_RESUME))
+ 		x = skb->sp->xvec[skb->sp->len - 1];
+ 	else
+ 		x = skb_dst(skb)->xfrm;
tmp = ESP_SKB_CB(skb)->tmp;
    esp_ssg_unref(x, tmp);
    kfree(tmp);
- 	xfrm_output_resume(skb, err);
+ 
+ 	if (xo && (xo->flags & XFRM_DEV_RESUME)) {
+ 		if (err) {
+ 			XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR);
+ 			kfree_skb(skb);
+ 			return;
+ 		}
+ 
+ 		skb_push(skb, skb->data - skb_mac_header(skb));
+ 		secpath_reset(skb);
+ 		xfrm_dev_resume(skb);
+ 	} else {
+ 		xfrm_output_resume(skb, err);
+ 	}
  }
/* Move ESP header back into place. */
@@@ -825,17 -843,13 +843,13 @@@ static int esp_init_aead(struct xfrm_st
    char aead_name[CRYPTO_MAX_ALG_NAME];
    struct crypto_aead *aead;
    int err;
- 	u32 mask = 0;
err = -ENAMETOOLONG;
    if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
    	     x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME)
    	goto error;
- 	if (x->xso.offload_handle)
- 		mask |= CRYPTO_ALG_ASYNC;
- 
- 	aead = crypto_alloc_aead(aead_name, 0, mask);
+ 	aead = crypto_alloc_aead(aead_name, 0, 0);
    err = PTR_ERR(aead);
    if (IS_ERR(aead))
    	goto error;
@@@ -865,7 -879,6 +879,6 @@@ static int esp_init_authenc(struct xfrm
    char authenc_name[CRYPTO_MAX_ALG_NAME];
    unsigned int keylen;
    int err;
- 	u32 mask = 0;
err = -EINVAL;
    if (!x->ealg)
@@@ -891,10 -904,7 +904,7 @@@
    		goto error;
    }
- 	if (x->xso.offload_handle)
- 		mask |= CRYPTO_ALG_ASYNC;
- 
- 	aead = crypto_alloc_aead(authenc_name, 0, mask);
+ 	aead = crypto_alloc_aead(authenc_name, 0, 0);
    err = PTR_ERR(aead);
    if (IS_ERR(aead))
    	goto error;
@@@ -981,7 -991,6 +991,7 @@@ static int esp_init_state(struct xfrm_s
switch (encap->encap_type) {
    	default:
 +			err = -EINVAL;
    		goto error;
    	case UDP_ENCAP_ESPINUDP:
    		x->props.header_len += sizeof(struct udphdr);
diff --combined net/ipv4/esp4_offload.c
index b1338e576d00,c359f3cfeec3..32fbd9ba3609
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@@ -38,8 -38,7 +38,8 @@@ static struct sk_buff **esp4_gro_receiv
    __be32 spi;
    int err;
-	skb_pull(skb, offset);
 +	if (!pskb_pull(skb, offset))
 +		return NULL;
if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0)
    	goto out;
@@@ -109,75 -108,36 +109,36 @@@ static void esp4_gso_encap(struct xfrm_
  static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
    			        netdev_features_t features)
  {
- 	__u32 seq;
- 	int err = 0;
- 	struct sk_buff *skb2;
    struct xfrm_state *x;
    struct ip_esp_hdr *esph;
    struct crypto_aead *aead;
- 	struct sk_buff *segs = ERR_PTR(-EINVAL);
    netdev_features_t esp_features = features;
    struct xfrm_offload *xo = xfrm_offload(skb);
if (!xo)
- 		goto out;
- 
- 	seq = xo->seq.low;
+ 		return ERR_PTR(-EINVAL);
x = skb->sp->xvec[skb->sp->len - 1];
    aead = x->data;
    esph = ip_esp_hdr(skb);
if (esph->spi != x->id.spi)
- 		goto out;
+ 		return ERR_PTR(-EINVAL);
if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)))
- 		goto out;
+ 		return ERR_PTR(-EINVAL);
__skb_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead));
skb->encap_hdr_csum = 1;
- 	if (!(features & NETIF_F_HW_ESP))
+ 	if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle ||
+ 	    (x->xso.dev != skb->dev))
    	esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
- 	segs = x->outer_mode->gso_segment(x, skb, esp_features);
- 	if (IS_ERR_OR_NULL(segs))
- 		goto out;
- 
- 	__skb_pull(skb, skb->data - skb_mac_header(skb));
- 
- 	skb2 = segs;
- 	do {
- 		struct sk_buff *nskb = skb2->next;
- 
- 		xo = xfrm_offload(skb2);
- 		xo->flags |= XFRM_GSO_SEGMENT;
- 		xo->seq.low = seq;
- 		xo->seq.hi = xfrm_replay_seqhi(x, seq);
+ 	xo->flags |= XFRM_GSO_SEGMENT;
- 		if(!(features & NETIF_F_HW_ESP))
- 			xo->flags |= CRYPTO_FALLBACK;
- 
- 		x->outer_mode->xmit(x, skb2);
- 
- 		err = x->type_offload->xmit(x, skb2, esp_features);
- 		if (err) {
- 			kfree_skb_list(segs);
- 			return ERR_PTR(err);
- 		}
- 
- 		if (!skb_is_gso(skb2))
- 			seq++;
- 		else
- 			seq += skb_shinfo(skb2)->gso_segs;
- 
- 		skb_push(skb2, skb2->mac_len);
- 		skb2 = nskb;
- 	} while (skb2);
- 
- out:
- 	return segs;
+ 	return x->outer_mode->gso_segment(x, skb, esp_features);
  }
static int esp_input_tail(struct xfrm_state *x, struct sk_buff *skb)
@@@ -204,6 -164,7 +165,7 @@@ static int esp_xmit(struct xfrm_state *
    struct crypto_aead *aead;
    struct esp_info esp;
    bool hw_offload = true;
+ 	__u32 seq;
esp.inplace = true;
@@@ -242,23 -203,30 +204,30 @@@
    		return esp.nfrags;
    }
+ 	seq = xo->seq.low;
+ 
    esph = esp.esph;
    esph->spi = x->id.spi;
skb_push(skb, -skb_network_offset(skb));
if (xo->flags & XFRM_GSO_SEGMENT) {
- 		esph->seq_no = htonl(xo->seq.low);
- 	} else {
- 		ip_hdr(skb)->tot_len = htons(skb->len);
- 		ip_send_check(ip_hdr(skb));
+ 		esph->seq_no = htonl(seq);
+ 
+ 		if (!skb_is_gso(skb))
+ 			xo->seq.low++;
+ 		else
+ 			xo->seq.low += skb_shinfo(skb)->gso_segs;
    }
+ 	esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32));
+ 
+ 	ip_hdr(skb)->tot_len = htons(skb->len);
+ 	ip_send_check(ip_hdr(skb));
+ 
    if (hw_offload)
    	return 0;
- 	esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));
- 
    err = esp_output_tail(x, skb, &esp);
    if (err)
    	return err;
diff --combined net/ipv4/tcp.c
index c4a7ee7f6721,d7cf861bf699..c1a295d93b4a
--- 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;
@@@ -1731,8 -1733,8 +1733,8 @@@ static void tcp_update_recv_tstamps(str
  }
/* Similar to __sock_recv_timestamp, but does not require an skb */
- void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
- 			struct scm_timestamping *tss)
+ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk,
+ 			       struct scm_timestamping *tss)
  {
    struct timeval tv;
    bool has_timestamping = false;
@@@ -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/esp6.c
index 1a7f00cd4803,7c888c6e53a9..97513f35bcc5
--- a/net/ipv6/esp6.c
+++ b/net/ipv6/esp6.c
@@@ -141,14 -141,32 +141,32 @@@ static void esp_ssg_unref(struct xfrm_s
  static void esp_output_done(struct crypto_async_request *base, int err)
  {
    struct sk_buff *skb = base->data;
+ 	struct xfrm_offload *xo = xfrm_offload(skb);
    void *tmp;
- 	struct dst_entry *dst = skb_dst(skb);
- 	struct xfrm_state *x = dst->xfrm;
+ 	struct xfrm_state *x;
+ 
+ 	if (xo && (xo->flags & XFRM_DEV_RESUME))
+ 		x = skb->sp->xvec[skb->sp->len - 1];
+ 	else
+ 		x = skb_dst(skb)->xfrm;
tmp = ESP_SKB_CB(skb)->tmp;
    esp_ssg_unref(x, tmp);
    kfree(tmp);
- 	xfrm_output_resume(skb, err);
+ 
+ 	if (xo && (xo->flags & XFRM_DEV_RESUME)) {
+ 		if (err) {
+ 			XFRM_INC_STATS(xs_net(x), LINUX_MIB_XFRMOUTSTATEPROTOERROR);
+ 			kfree_skb(skb);
+ 			return;
+ 		}
+ 
+ 		skb_push(skb, skb->data - skb_mac_header(skb));
+ 		secpath_reset(skb);
+ 		xfrm_dev_resume(skb);
+ 	} else {
+ 		xfrm_output_resume(skb, err);
+ 	}
  }
/* Move ESP header back into place. */
@@@ -734,17 -752,13 +752,13 @@@ static int esp_init_aead(struct xfrm_st
    char aead_name[CRYPTO_MAX_ALG_NAME];
    struct crypto_aead *aead;
    int err;
- 	u32 mask = 0;
err = -ENAMETOOLONG;
    if (snprintf(aead_name, CRYPTO_MAX_ALG_NAME, "%s(%s)",
    	     x->geniv, x->aead->alg_name) >= CRYPTO_MAX_ALG_NAME)
    	goto error;
- 	if (x->xso.offload_handle)
- 		mask |= CRYPTO_ALG_ASYNC;
- 
- 	aead = crypto_alloc_aead(aead_name, 0, mask);
+ 	aead = crypto_alloc_aead(aead_name, 0, 0);
    err = PTR_ERR(aead);
    if (IS_ERR(aead))
    	goto error;
@@@ -774,7 -788,6 +788,6 @@@ static int esp_init_authenc(struct xfrm
    char authenc_name[CRYPTO_MAX_ALG_NAME];
    unsigned int keylen;
    int err;
- 	u32 mask = 0;
err = -EINVAL;
    if (!x->ealg)
@@@ -800,10 -813,7 +813,7 @@@
    		goto error;
    }
- 	if (x->xso.offload_handle)
- 		mask |= CRYPTO_ALG_ASYNC;
- 
- 	aead = crypto_alloc_aead(authenc_name, 0, mask);
+ 	aead = crypto_alloc_aead(authenc_name, 0, 0);
    err = PTR_ERR(aead);
    if (IS_ERR(aead))
    	goto error;
@@@ -890,12 -900,13 +900,12 @@@ static int esp6_init_state(struct xfrm_
    		x->props.header_len += IPV4_BEET_PHMAXLEN +
    				       (sizeof(struct ipv6hdr) - sizeof(struct iphdr));
    	break;
 +	default:
    case XFRM_MODE_TRANSPORT:
    	break;
    case XFRM_MODE_TUNNEL:
    	x->props.header_len += sizeof(struct ipv6hdr);
    	break;
 -	default:
 -		goto error;
    }
align = ALIGN(crypto_aead_blocksize(aead), 4);
diff --combined net/ipv6/esp6_offload.c
index dd9627490c7c,0bb7d54cf2cb..44d109c435bc
--- a/net/ipv6/esp6_offload.c
+++ b/net/ipv6/esp6_offload.c
@@@ -60,8 -60,7 +60,8 @@@ static struct sk_buff **esp6_gro_receiv
    int nhoff;
    int err;
-	skb_pull(skb, offset);
 +	if (!pskb_pull(skb, offset))
 +		return NULL;
if ((err = xfrm_parse_spi(skb, IPPROTO_ESP, &spi, &seq)) != 0)
    	goto out;
@@@ -136,75 -135,36 +136,36 @@@ static void esp6_gso_encap(struct xfrm_
  static struct sk_buff *esp6_gso_segment(struct sk_buff *skb,
    			        netdev_features_t features)
  {
- 	__u32 seq;
- 	int err = 0;
- 	struct sk_buff *skb2;
    struct xfrm_state *x;
    struct ip_esp_hdr *esph;
    struct crypto_aead *aead;
- 	struct sk_buff *segs = ERR_PTR(-EINVAL);
    netdev_features_t esp_features = features;
    struct xfrm_offload *xo = xfrm_offload(skb);
if (!xo)
- 		goto out;
- 
- 	seq = xo->seq.low;
+ 		return ERR_PTR(-EINVAL);
x = skb->sp->xvec[skb->sp->len - 1];
    aead = x->data;
    esph = ip_esp_hdr(skb);
if (esph->spi != x->id.spi)
- 		goto out;
+ 		return ERR_PTR(-EINVAL);
if (!pskb_may_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead)))
- 		goto out;
+ 		return ERR_PTR(-EINVAL);
__skb_pull(skb, sizeof(*esph) + crypto_aead_ivsize(aead));
skb->encap_hdr_csum = 1;
- 	if (!(features & NETIF_F_HW_ESP))
+ 	if (!(features & NETIF_F_HW_ESP) || !x->xso.offload_handle ||
+ 	    (x->xso.dev != skb->dev))
    	esp_features = features & ~(NETIF_F_SG | NETIF_F_CSUM_MASK);
- 	segs = x->outer_mode->gso_segment(x, skb, esp_features);
- 	if (IS_ERR_OR_NULL(segs))
- 		goto out;
- 
- 	__skb_pull(skb, skb->data - skb_mac_header(skb));
- 
- 	skb2 = segs;
- 	do {
- 		struct sk_buff *nskb = skb2->next;
- 
- 		xo = xfrm_offload(skb2);
- 		xo->flags |= XFRM_GSO_SEGMENT;
- 		xo->seq.low = seq;
- 		xo->seq.hi = xfrm_replay_seqhi(x, seq);
- 
- 		if(!(features & NETIF_F_HW_ESP))
- 			xo->flags |= CRYPTO_FALLBACK;
- 
- 		x->outer_mode->xmit(x, skb2);
- 
- 		err = x->type_offload->xmit(x, skb2, esp_features);
- 		if (err) {
- 			kfree_skb_list(segs);
- 			return ERR_PTR(err);
- 		}
- 
- 		if (!skb_is_gso(skb2))
- 			seq++;
- 		else
- 			seq += skb_shinfo(skb2)->gso_segs;
- 
- 		skb_push(skb2, skb2->mac_len);
- 		skb2 = nskb;
- 	} while (skb2);
+ 	xo->flags |= XFRM_GSO_SEGMENT;
- out:
- 	return segs;
+ 	return x->outer_mode->gso_segment(x, skb, esp_features);
  }
static int esp6_input_tail(struct xfrm_state *x, struct sk_buff *skb)
@@@ -223,6 -183,7 +184,7 @@@
static int esp6_xmit(struct xfrm_state *x, struct sk_buff *skb,  netdev_features_t features)
  {
+ 	int len;
    int err;
    int alen;
    int blksize;
@@@ -231,6 -192,7 +193,7 @@@
    struct crypto_aead *aead;
    struct esp_info esp;
    bool hw_offload = true;
+ 	__u32 seq;
esp.inplace = true;
@@@ -266,28 -228,33 +229,33 @@@
    		return esp.nfrags;
    }
+ 	seq = xo->seq.low;
+ 
    esph = ip_esp_hdr(skb);
    esph->spi = x->id.spi;
skb_push(skb, -skb_network_offset(skb));
if (xo->flags & XFRM_GSO_SEGMENT) {
- 		esph->seq_no = htonl(xo->seq.low);
- 	} else {
- 		int len;
- 
- 		len = skb->len - sizeof(struct ipv6hdr);
- 		if (len > IPV6_MAXPLEN)
- 			len = 0;
+ 		esph->seq_no = htonl(seq);
- 		ipv6_hdr(skb)->payload_len = htons(len);
+ 		if (!skb_is_gso(skb))
+ 			xo->seq.low++;
+ 		else
+ 			xo->seq.low += skb_shinfo(skb)->gso_segs;
    }
+ 	esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));
+ 
+ 	len = skb->len - sizeof(struct ipv6hdr);
+ 	if (len > IPV6_MAXPLEN)
+ 		len = 0;
+ 
+ 	ipv6_hdr(skb)->payload_len = htons(len);
+ 
    if (hw_offload)
    	return 0;
- 	esp.seqno = cpu_to_be64(xo->seq.low + ((u64)xo->seq.hi << 32));
- 
    err = esp6_output_tail(x, skb, &esp);
    if (err)
    	return err;
diff --combined net/netfilter/x_tables.c
index e02a21549c99,10c19a3f4cbd..ecbdea0431d4
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@@ -39,6 -39,7 +39,6 @@@ MODULE_LICENSE("GPL")
  MODULE_AUTHOR("Harald Welte laforge@netfilter.org");
  MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module");
-#define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1))
  #define XT_PCPU_BLOCK_SIZE 4096
struct compat_delta {
@@@ -999,7 -1000,7 +999,7 @@@ struct xt_table_info *xt_alloc_table_in
    	return NULL;
/* Pedantry: prevent them from hitting BUG() in vmalloc.c --RR */
 -	if ((SMP_ALIGN(size) >> PAGE_SHIFT) + 2 > totalram_pages)
 +	if ((size >> PAGE_SHIFT) + 2 > totalram_pages)
    	return NULL;
info = kvmalloc(sz, GFP_KERNEL);
@@@ -1026,7 -1027,7 +1026,7 @@@ void xt_free_table_info(struct xt_table
  }
  EXPORT_SYMBOL(xt_free_table_info);
- /* Find table by name, grabs mutex & ref.  Returns NULL on error. */
+ /* Find table by name, grabs mutex & ref.  Returns ERR_PTR on error. */
  struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af,
    			    const char *name)
  {
@@@ -1042,17 -1043,17 +1042,17 @@@
/* Table doesn't exist in this netns, re-try init */
    list_for_each_entry(t, &init_net.xt.tables[af], list) {
+ 		int err;
+ 
    	if (strcmp(t->name, name))
    		continue;
- 		if (!try_module_get(t->me)) {
- 			mutex_unlock(&xt[af].mutex);
- 			return NULL;
- 		}
- 
+ 		if (!try_module_get(t->me))
+ 			goto out;
    	mutex_unlock(&xt[af].mutex);
- 		if (t->table_init(net) != 0) {
+ 		err = t->table_init(net);
+ 		if (err < 0) {
    		module_put(t->me);
- 			return NULL;
+ 			return ERR_PTR(err);
    	}
found = t;
@@@ -1072,10 -1073,28 +1072,28 @@@
    module_put(found->me);
   out:
    mutex_unlock(&xt[af].mutex);
- 	return NULL;
+ 	return ERR_PTR(-ENOENT);
  }
  EXPORT_SYMBOL_GPL(xt_find_table_lock);
+ struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af,
+ 					    const char *name)
+ {
+ 	struct xt_table *t = xt_find_table_lock(net, af, name);
+ 
+ #ifdef CONFIG_MODULE
+ 	if (IS_ERR(t)) {
+ 		int err = request_module("%stable_%s", xt_prefix[af], name);
+ 		if (err)
+ 			return ERR_PTR(err);
+ 		t = xt_find_table_lock(net, af, name);
+ 	}
+ #endif
+ 
+ 	return t;
+ }
+ EXPORT_SYMBOL_GPL(xt_request_find_table_lock);
+ 
  void xt_table_unlock(struct xt_table *table)
  {
    mutex_unlock(&xt[table->af].mutex);
@@@ -1396,7 -1415,7 +1414,7 @@@ static void *xt_mttg_seq_next(struct se
    	trav->curr = trav->curr->next;
    	if (trav->curr != trav->head)
    		break;
- 		/* fallthru, _stop will unlock */
+ 		/* fall through */
    default:
    	return NULL;
    }
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/sctp/socket.c
index 2a16db8c4a1f,6a54ff06c9da..112cda6426a3
--- 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;
  }
@@@ -4033,6 -4066,40 +4066,40 @@@ 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
@@@ -4220,6 -4287,10 +4287,10 @@@ 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;
@@@ -4596,7 -4667,7 +4667,7 @@@ 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);
@@@ -4690,20 -4761,11 +4761,11 @@@ 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)
@@@ -4794,12 -4856,10 +4856,10 @@@ 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)) {
@@@ -6998,6 -7058,47 +7058,47 @@@ 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)
  {
@@@ -7188,6 -7289,10 +7289,10 @@@
    	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;
@@@ -7422,13 -7527,13 +7527,13 @@@ 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;
    	}
    }
@@@ -7514,11 -7619,11 +7619,11 @@@ 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);
@@@ -8425,11 -8530,7 +8530,7 @@@ 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
@@@ -8455,10 -8556,10 +8556,10 @@@
     * 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/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 2f378449bc1b,fbfae1ed3ff5..fd0f0ae976e6
--- 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.
@@@ -580,7 -574,6 +574,6 @@@ 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);
@@@ -607,7 -600,6 +600,6 @@@ 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;
@@@ -1097,9 -1089,9 +1089,9 @@@ 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;
/*
@@@ -2633,17 -2625,8 +2625,8 @@@ pure_initcall(jit_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/server.c
index 78a292a84afc,8ee5e86b7870..125da165e523
--- a/net/tipc/server.c
+++ b/net/tipc/server.c
@@@ -264,8 -264,8 +264,8 @@@ static int tipc_receive_from_sock(struc
    iov.iov_base = buf;
    iov.iov_len = s->max_rcvbuf_size;
    msg.msg_name = &addr;
 -	ret = kernel_recvmsg(con->sock, &msg, &iov, 1, iov.iov_len,
 -			     MSG_DONTWAIT);
 +	iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len);
 +	ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT);
    if (ret <= 0) {
    	kmem_cache_free(s->rcvbuf_cache, buf);
    	goto out_close;
@@@ -489,8 -489,8 +489,8 @@@ void tipc_conn_terminate(struct tipc_se
    }
  }
- bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type,
- 			     u32 lower, u32 upper, int *conid)
+ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower,
+ 			     u32 upper, u32 filter, int *conid)
  {
    struct tipc_subscriber *scbr;
    struct tipc_subscr sub;
@@@ -501,7 -501,7 +501,7 @@@
    sub.seq.lower = lower;
    sub.seq.upper = upper;
    sub.timeout = TIPC_WAIT_FOREVER;
- 	sub.filter = TIPC_SUB_PORTS;
+ 	sub.filter = filter;
    *(u32 *)&sub.usr_handle = port;
con = tipc_alloc_conn(tipc_topsrv(net));
diff --combined net/tipc/socket.c
index 2aa46e8cd8fe,1f236271766c..cbabc44cd19a
--- 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;
+ 	struct tipc_group *grp;
 -	u32 revents = 0;
 +	__poll_t revents = 0;
sock_poll_wait(file, sk_sleep(sk), wait);
@@@ -736,9 -736,9 +736,9 @@@
    		revents |= POLLIN | POLLRDNORM;
    	break;
    case TIPC_OPEN:
- 		if (!grp || tipc_group_size(grp))
- 			if (!tsk->cong_link_cnt)
- 				revents |= POLLOUT;
+ 		grp = tsk->group;
+ 		if ((!grp || tipc_group_is_open(grp)) && !tsk->cong_link_cnt)
+ 			revents |= POLLOUT;
    	if (!tipc_sk_type_connectionless(sk))
    		break;
    	if (skb_queue_empty(&sk->sk_receive_queue))
@@@ -928,21 -928,22 +928,22 @@@ static int tipc_send_group_anycast(stru
    struct list_head *cong_links = &tsk->cong_links;
    int blks = tsk_blocks(GROUP_H_SIZE + dlen);
    struct tipc_group *grp = tsk->group;
+ 	struct tipc_msg *hdr = &tsk->phdr;
    struct tipc_member *first = NULL;
    struct tipc_member *mbr = NULL;
    struct net *net = sock_net(sk);
    u32 node, port, exclude;
- 	u32 type, inst, domain;
    struct list_head dsts;
+ 	u32 type, inst, scope;
    int lookups = 0;
    int dstcnt, rc;
    bool cong;
INIT_LIST_HEAD(&dsts);
- 	type = dest->addr.name.name.type;
+ 	type = msg_nametype(hdr);
    inst = dest->addr.name.name.instance;
- 	domain = addr_domain(net, dest->scope);
+ 	scope = msg_lookup_scope(hdr);
    exclude = tipc_group_exclude(grp);
while (++lookups < 4) {
@@@ -950,7 -951,7 +951,7 @@@
/* Look for a non-congested destination member, if any */
    	while (1) {
- 			if (!tipc_nametbl_lookup(net, type, inst, domain, &dsts,
+ 			if (!tipc_nametbl_lookup(net, type, inst, scope, &dsts,
    					 &dstcnt, exclude, false))
    			return -EHOSTUNREACH;
    		tipc_dest_pop(&dsts, &node, &port);
@@@ -1079,22 -1080,23 +1080,23 @@@ static int tipc_send_group_mcast(struc
  {
    struct sock *sk = sock->sk;
    DECLARE_SOCKADDR(struct sockaddr_tipc *, dest, m->msg_name);
- 	struct tipc_name_seq *seq = &dest->addr.nameseq;
    struct tipc_sock *tsk = tipc_sk(sk);
    struct tipc_group *grp = tsk->group;
+ 	struct tipc_msg *hdr = &tsk->phdr;
    struct net *net = sock_net(sk);
- 	u32 domain, exclude, dstcnt;
+ 	u32 type, inst, scope, exclude;
    struct list_head dsts;
+ 	u32 dstcnt;
INIT_LIST_HEAD(&dsts);
- 	if (seq->lower != seq->upper)
- 		return -ENOTSUPP;
- 
- 	domain = addr_domain(net, dest->scope);
+ 	type = msg_nametype(hdr);
+ 	inst = dest->addr.name.name.instance;
+ 	scope = msg_lookup_scope(hdr);
    exclude = tipc_group_exclude(grp);
- 	if (!tipc_nametbl_lookup(net, seq->type, seq->lower, domain,
- 				 &dsts, &dstcnt, exclude, true))
+ 
+ 	if (!tipc_nametbl_lookup(net, type, inst, scope, &dsts,
+ 				 &dstcnt, exclude, true))
    	return -EHOSTUNREACH;
if (dstcnt == 1) {
@@@ -1116,24 -1118,29 +1118,29 @@@
  void tipc_sk_mcast_rcv(struct net *net, struct sk_buff_head *arrvq,
    	       struct sk_buff_head *inputq)
  {
- 	u32 scope = TIPC_CLUSTER_SCOPE;
    u32 self = tipc_own_addr(net);
+ 	u32 type, lower, upper, scope;
    struct sk_buff *skb, *_skb;
- 	u32 lower = 0, upper = ~0;
- 	struct sk_buff_head tmpq;
    u32 portid, oport, onode;
+ 	struct sk_buff_head tmpq;
    struct list_head dports;
- 	struct tipc_msg *msg;
- 	int user, mtyp, hsz;
+ 	struct tipc_msg *hdr;
+ 	int user, mtyp, hlen;
+ 	bool exact;
__skb_queue_head_init(&tmpq);
    INIT_LIST_HEAD(&dports);
skb = tipc_skb_peek(arrvq, &inputq->lock);
    for (; skb; skb = tipc_skb_peek(arrvq, &inputq->lock)) {
- 		msg = buf_msg(skb);
- 		user = msg_user(msg);
- 		mtyp = msg_type(msg);
+ 		hdr = buf_msg(skb);
+ 		user = msg_user(hdr);
+ 		mtyp = msg_type(hdr);
+ 		hlen = skb_headroom(skb) + msg_hdr_sz(hdr);
+ 		oport = msg_origport(hdr);
+ 		onode = msg_orignode(hdr);
+ 		type = msg_nametype(hdr);
+ 
    	if (mtyp == TIPC_GRP_UCAST_MSG || user == GROUP_PROTOCOL) {
    		spin_lock_bh(&inputq->lock);
    		if (skb_peek(arrvq) == skb) {
@@@ -1144,21 -1151,31 +1151,31 @@@
    		spin_unlock_bh(&inputq->lock);
    		continue;
    	}
- 		hsz = skb_headroom(skb) + msg_hdr_sz(msg);
- 		oport = msg_origport(msg);
- 		onode = msg_orignode(msg);
- 		if (onode == self)
- 			scope = TIPC_NODE_SCOPE;
- 
- 		/* Create destination port list and message clones: */
- 		if (!msg_in_group(msg)) {
- 			lower = msg_namelower(msg);
- 			upper = msg_nameupper(msg);
+ 
+ 		/* Group messages require exact scope match */
+ 		if (msg_in_group(hdr)) {
+ 			lower = 0;
+ 			upper = ~0;
+ 			scope = msg_lookup_scope(hdr);
+ 			exact = true;
+ 		} else {
+ 			/* TIPC_NODE_SCOPE means "any scope" in this context */
+ 			if (onode == self)
+ 				scope = TIPC_NODE_SCOPE;
+ 			else
+ 				scope = TIPC_CLUSTER_SCOPE;
+ 			exact = false;
+ 			lower = msg_namelower(hdr);
+ 			upper = msg_nameupper(hdr);
    	}
- 		tipc_nametbl_mc_translate(net, msg_nametype(msg), lower, upper,
- 					  scope, &dports);
+ 
+ 		/* Create destination port list: */
+ 		tipc_nametbl_mc_lookup(net, type, lower, upper,
+ 				       scope, exact, &dports);
+ 
+ 		/* Clone message per destination */
    	while (tipc_dest_pop(&dports, NULL, &portid)) {
- 			_skb = __pskb_copy(skb, hsz, GFP_ATOMIC);
+ 			_skb = __pskb_copy(skb, hlen, GFP_ATOMIC);
    		if (_skb) {
    			msg_set_destport(buf_msg(_skb), portid);
    			__skb_queue_tail(&tmpq, _skb);
@@@ -1933,8 -1950,7 +1950,7 @@@ static void tipc_sk_proto_rcv(struct so
    	break;
    case TOP_SRV:
    	tipc_group_member_evt(tsk->group, &wakeup, &sk->sk_rcvbuf,
- 				      skb, inputq, xmitq);
- 		skb = NULL;
+ 				      hdr, inputq, xmitq);
    	break;
    default:
    	break;
@@@ -2640,9 -2656,7 +2656,7 @@@ 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 -2665,7 +2665,7 @@@
    		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));
  }
@@@ -2734,7 -2748,6 +2748,6 @@@ void tipc_sk_rht_destroy(struct net *ne
  static int tipc_sk_join(struct tipc_sock *tsk, struct tipc_group_req *mreq)
  {
    struct net *net = sock_net(&tsk->sk);
- 	u32 domain = addr_domain(net, mreq->scope);
    struct tipc_group *grp = tsk->group;
    struct tipc_msg *hdr = &tsk->phdr;
    struct tipc_name_seq seq;
@@@ -2742,6 -2755,8 +2755,8 @@@
if (mreq->type < TIPC_RESERVED_TYPES)
    	return -EACCES;
+ 	if (mreq->scope > TIPC_NODE_SCOPE)
+ 		return -EINVAL;
    if (grp)
    	return -EACCES;
    grp = tipc_group_create(net, tsk->portid, mreq);
@@@ -2754,16 -2769,16 +2769,16 @@@
    seq.type = mreq->type;
    seq.lower = mreq->instance;
    seq.upper = seq.lower;
- 	tipc_nametbl_build_group(net, grp, mreq->type, domain);
+ 	tipc_nametbl_build_group(net, grp, mreq->type, mreq->scope);
    rc = tipc_sk_publish(tsk, mreq->scope, &seq);
    if (rc) {
    	tipc_group_delete(net, grp);
    	tsk->group = NULL;
    }
- 
- 	/* Eliminate any risk that a broadcast overtakes the sent JOIN */
+ 	/* Eliminate any risk that a broadcast overtakes sent JOINs */
    tsk->mc_method.rcast = true;
    tsk->mc_method.mandatory = true;
+ 	tipc_group_join(net, grp, &tsk->sk.sk_rcvbuf);
    return rc;
  }
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 bd6b0e7a0ee4,d8a8129b9232..7a23078132cf
--- 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;
    	}
@@@ -975,6 -974,8 +975,6 @@@ int xfrm_policy_flush(struct net *net, 
    }
    if (!cnt)
    	err = -ESRCH;
 -	else
 -		xfrm_policy_cache_flush();
  out:
    spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
    return err;
@@@ -1256,7 -1257,7 +1256,7 @@@ 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
@@@ -1543,7 -1544,9 +1543,9 @@@ 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)
  {
@@@ -1551,8 -1554,8 +1553,8 @@@
    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;
@@@ -1578,13 -1581,14 +1580,14 @@@
    		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],
@@@ -1621,8 -1625,7 +1624,7 @@@
    	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)
@@@ -1630,40 -1633,39 +1632,39 @@@
    	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;
  }
@@@ -1742,8 -1744,6 +1743,8 @@@ void xfrm_policy_cache_flush(void
    bool found = 0;
    int cpu;
+	might_sleep();
 +
    local_bh_disable();
    rcu_read_lock();
    for_each_possible_cpu(cpu) {
@@@ -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);
@@@ -2063,11 -2064,8 +2065,11 @@@ xfrm_bundle_lookup(struct net *net, con
    if (num_xfrms <= 0)
    	goto make_dummy_bundle;
+	local_bh_disable();
    xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family,
 -						  xflo->dst_orig);
 +					      xflo->dst_orig);
 +	local_bh_enable();
 +
    if (IS_ERR(xdst)) {
    	err = PTR_ERR(xdst);
    	if (err != -EAGAIN)
@@@ -2154,12 -2152,9 +2156,12 @@@ struct dst_entry *xfrm_lookup(struct ne
    			goto no_transform;
    		}
+			local_bh_disable();
    		xdst = xfrm_resolve_and_create_bundle(
    				pols, num_pols, fl,
    				family, dst_orig);
 +			local_bh_enable();
 +
    		if (IS_ERR(xdst)) {
    			xfrm_pols_put(pols, num_pols);
    			err = PTR_ERR(xdst);
@@@ -2590,7 -2585,7 +2592,7 @@@ 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);
@@@ -2614,13 -2609,15 +2616,15 @@@ 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);
@@@ -2632,7 -2629,7 +2636,7 @@@
    		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
@@@ -2641,19 -2638,20 +2645,20 @@@
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;
@@@ -2665,9 -2663,11 +2670,11 @@@
    	    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;
    	}
@@@ -2675,30 -2675,30 +2682,30 @@@
    		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;
@@@ -2706,22 -2706,20 +2713,20 @@@
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)
@@@ -2730,6 -2728,8 +2735,8 @@@
    		daddr = xfrm->coaddr;
    	else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR))
    		daddr = &xfrm->id.daddr;
+ 
+ 		dst = xfrm_dst_child(dst);
    }
    return daddr;
  }
@@@ -2738,7 -2738,7 +2745,7 @@@ 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);
@@@ -2747,7 -2747,7 +2754,7 @@@
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_verifier.c
index 6bafa5456568,543847957fdd..960179882a1c
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@@ -2,6 -2,7 +2,7 @@@
   * Testsuite for eBPF verifier
   *
   * Copyright (c) 2014 PLUMgrid, http://plumgrid.com
+  * Copyright (c) 2017 Facebook
   *
   * This program is free software; you can redistribute it and/or
   * modify it under the terms of version 2 of the GNU General Public
@@@ -273,51 -274,11 +274,51 @@@ static struct bpf_test tests[] = 
    	.result = REJECT,
    },
    {
 +		"arsh32 on imm",
 +		.insns = {
 +			BPF_MOV64_IMM(BPF_REG_0, 1),
 +			BPF_ALU32_IMM(BPF_ARSH, BPF_REG_0, 5),
 +			BPF_EXIT_INSN(),
 +		},
 +		.result = REJECT,
 +		.errstr = "BPF_ARSH not supported for 32 bit ALU",
 +	},
 +	{
 +		"arsh32 on reg",
 +		.insns = {
 +			BPF_MOV64_IMM(BPF_REG_0, 1),
 +			BPF_MOV64_IMM(BPF_REG_1, 5),
 +			BPF_ALU32_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1),
 +			BPF_EXIT_INSN(),
 +		},
 +		.result = REJECT,
 +		.errstr = "BPF_ARSH not supported for 32 bit ALU",
 +	},
 +	{
 +		"arsh64 on imm",
 +		.insns = {
 +			BPF_MOV64_IMM(BPF_REG_0, 1),
 +			BPF_ALU64_IMM(BPF_ARSH, BPF_REG_0, 5),
 +			BPF_EXIT_INSN(),
 +		},
 +		.result = ACCEPT,
 +	},
 +	{
 +		"arsh64 on reg",
 +		.insns = {
 +			BPF_MOV64_IMM(BPF_REG_0, 1),
 +			BPF_MOV64_IMM(BPF_REG_1, 5),
 +			BPF_ALU64_REG(BPF_ARSH, BPF_REG_0, BPF_REG_1),
 +			BPF_EXIT_INSN(),
 +		},
 +		.result = ACCEPT,
 +	},
 +	{
    	"no bpf_exit",
    	.insns = {
    		BPF_ALU64_REG(BPF_MOV, BPF_REG_0, BPF_REG_2),
    	},
- 		.errstr = "jump out of range",
+ 		.errstr = "not an exit",
    	.result = REJECT,
    },
    {
@@@ -5675,7 -5636,7 +5676,7 @@@
    	"helper access to variable memory: size > 0 not allowed on NULL (ARG_PTR_TO_MEM_OR_NULL)",
    	.insns = {
    		BPF_MOV64_IMM(BPF_REG_1, 0),
- 			BPF_MOV64_IMM(BPF_REG_2, 0),
+ 			BPF_MOV64_IMM(BPF_REG_2, 1),
    		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
    		BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
    		BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 64),
@@@ -5910,7 -5871,7 +5911,7 @@@
    		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -24),
    		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -16),
    		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
- 			BPF_MOV64_IMM(BPF_REG_2, 0),
+ 			BPF_MOV64_IMM(BPF_REG_2, 1),
    		BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_2, -128),
    		BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_10, -128),
    		BPF_ALU64_IMM(BPF_AND, BPF_REG_2, 63),
@@@ -8680,6 -8641,1864 +8681,1864 @@@
    	.result = REJECT,
    	.prog_type = BPF_PROG_TYPE_CGROUP_SOCK,
    },
+ 	{
+ 		"calls: basic sanity",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 2),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: not on unpriviledged",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 2),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.errstr_unpriv = "function calls to other bpf functions are allowed for root only",
+ 		.result_unpriv = REJECT,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: overlapping caller/callee",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "last insn is not an exit or jmp",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: wrong recursive calls",
+ 		.insns = {
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 4),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 4),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -2),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -2),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "jump out of range",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: wrong src reg",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 2, 0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "BPF_CALL uses reserved fields",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: wrong off value",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, -1, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 2),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "BPF_CALL uses reserved fields",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: jump back loop",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -1),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "back-edge from insn 0 to 0",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: conditional call",
+ 		.insns = {
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, mark)),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 2),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "jump out of range",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: conditional call 2",
+ 		.insns = {
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, mark)),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 2),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 3),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: conditional call 3",
+ 		.insns = {
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, mark)),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 4),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, -6),
+ 			BPF_MOV64_IMM(BPF_REG_0, 3),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, -6),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "back-edge from insn",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: conditional call 4",
+ 		.insns = {
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, mark)),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, -5),
+ 			BPF_MOV64_IMM(BPF_REG_0, 3),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: conditional call 5",
+ 		.insns = {
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, mark)),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 3),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, -6),
+ 			BPF_MOV64_IMM(BPF_REG_0, 3),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "back-edge from insn",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: conditional call 6",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -2),
+ 			BPF_EXIT_INSN(),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, mark)),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "back-edge from insn",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: using r0 returned by callee",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 2),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: using uninit r0 from callee",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "!read_ok",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: callee is using r1",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, len)),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_ACT,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: callee using args1",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.errstr_unpriv = "allowed for root only",
+ 		.result_unpriv = REJECT,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: callee using wrong args2",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "R2 !read_ok",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: callee using two args",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_1, BPF_REG_6,
+ 				    offsetof(struct __sk_buff, len)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_6,
+ 				    offsetof(struct __sk_buff, len)),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_1),
+ 			BPF_ALU64_REG(BPF_ADD, BPF_REG_0, BPF_REG_2),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.errstr_unpriv = "allowed for root only",
+ 		.result_unpriv = REJECT,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: callee changing pkt pointers",
+ 		.insns = {
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_6, BPF_REG_1,
+ 				    offsetof(struct xdp_md, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_1,
+ 				    offsetof(struct xdp_md, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_8, BPF_REG_6),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_8, 8),
+ 			BPF_JMP_REG(BPF_JGT, BPF_REG_8, BPF_REG_7, 2),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			/* clear_all_pkt_pointers() has to walk all frames
+ 			 * to make sure that pkt pointers in the caller
+ 			 * are cleared when callee is calling a helper that
+ 			 * adjusts packet size
+ 			 */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
+ 			BPF_MOV32_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_2, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_xdp_adjust_head),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.result = REJECT,
+ 		.errstr = "R6 invalid mem access 'inv'",
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 	},
+ 	{
+ 		"calls: two calls with args",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+ 			BPF_EXIT_INSN(),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, len)),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: calls with stack arith",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -64),
+ 			BPF_MOV64_IMM(BPF_REG_0, 42),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: calls with misaligned stack access",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -63),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -61),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -63),
+ 			BPF_MOV64_IMM(BPF_REG_0, 42),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_2, BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.flags = F_LOAD_WITH_STRICT_ALIGNMENT,
+ 		.errstr = "misaligned stack access",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: calls control flow, jump test",
+ 		.insns = {
+ 			BPF_MOV64_IMM(BPF_REG_0, 42),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 43),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, -3),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: calls control flow, jump test 2",
+ 		.insns = {
+ 			BPF_MOV64_IMM(BPF_REG_0, 42),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 43),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -3),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.errstr = "jump out of range from insn 1 to 4",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: two calls with bad jump",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+ 			BPF_EXIT_INSN(),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, len)),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, -3),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "jump out of range from insn 11 to 9",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: recursive call. test1",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -1),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "back-edge",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: recursive call. test2",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -3),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "back-edge",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: unreachable code",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "unreachable insn 6",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: invalid call",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, -4),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "invalid destination",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: invalid call 2",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 0x7fffffff),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "invalid destination",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: jumping across function bodies. test1",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -3),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "jump out of range",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: jumping across function bodies. test2",
+ 		.insns = {
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 3),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "jump out of range",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: call without exit",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, -2),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "not an exit",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: call into middle of ld_imm64",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 			BPF_LD_IMM64(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "last insn",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: call into middle of other call",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "last insn",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: ld_abs with changing ctx data in callee",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_LD_ABS(BPF_B, 0),
+ 			BPF_LD_ABS(BPF_H, 0),
+ 			BPF_LD_ABS(BPF_W, 0),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_6),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_7),
+ 			BPF_LD_ABS(BPF_B, 0),
+ 			BPF_LD_ABS(BPF_H, 0),
+ 			BPF_LD_ABS(BPF_W, 0),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_IMM(BPF_REG_2, 1),
+ 			BPF_MOV64_IMM(BPF_REG_3, 2),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_skb_vlan_push),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.errstr = "BPF_LD_[ABS|IND] instructions cannot be mixed",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: two calls with bad fallthrough",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_0),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, len)),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 		.errstr = "not an exit",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: two calls with stack read",
+ 		.insns = {
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 6),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_ALU64_REG(BPF_ADD, BPF_REG_7, BPF_REG_0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_7),
+ 			BPF_EXIT_INSN(),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: two calls with stack write",
+ 		.insns = {
+ 			/* main prog */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 7),
+ 			BPF_MOV64_REG(BPF_REG_8, BPF_REG_0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+ 			BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_8),
+ 			/* write into stack frame of main prog */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 2 */
+ 			/* read from stack frame of main prog */
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_1, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: stack overflow using two frames (pre-call access)",
+ 		.insns = {
+ 			/* prog 1 */
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* prog 2 */
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.errstr = "combined stack size",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: stack overflow using two frames (post-call access)",
+ 		.insns = {
+ 			/* prog 1 */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 2),
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* prog 2 */
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.errstr = "combined stack size",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: stack depth check using three frames. test1",
+ 		.insns = {
+ 			/* main */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 4), /* call A */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 5), /* call B */
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -32, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 			/* A */
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -256, 0),
+ 			BPF_EXIT_INSN(),
+ 			/* B */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, -3), /* call A */
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -64, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		/* stack_main=32, stack_A=256, stack_B=64
+ 		 * and max(main+A, main+A+B) < 512
+ 		 */
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: stack depth check using three frames. test2",
+ 		.insns = {
+ 			/* main */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 4), /* call A */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 5), /* call B */
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -32, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 			/* A */
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -64, 0),
+ 			BPF_EXIT_INSN(),
+ 			/* B */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, -3), /* call A */
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -256, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		/* stack_main=32, stack_A=64, stack_B=256
+ 		 * and max(main+A, main+A+B) < 512
+ 		 */
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: stack depth check using three frames. test3",
+ 		.insns = {
+ 			/* main */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 6), /* call A */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 8), /* call B */
+ 			BPF_JMP_IMM(BPF_JGE, BPF_REG_6, 0, 1),
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -64, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 			/* A */
+ 			BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 10, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -224, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, -3),
+ 			/* B */
+ 			BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 2, 1),
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, -6), /* call A */
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -256, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		/* stack_main=64, stack_A=224, stack_B=256
+ 		 * and max(main+A, main+A+B) > 512
+ 		 */
+ 		.errstr = "combined stack",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: stack depth check using three frames. test4",
+ 		/* void main(void) {
+ 		 *   func1(0);
+ 		 *   func1(1);
+ 		 *   func2(1);
+ 		 * }
+ 		 * void func1(int alloc_or_recurse) {
+ 		 *   if (alloc_or_recurse) {
+ 		 *     frame_pointer[-300] = 1;
+ 		 *   } else {
+ 		 *     func2(alloc_or_recurse);
+ 		 *   }
+ 		 * }
+ 		 * void func2(int alloc_or_recurse) {
+ 		 *   if (alloc_or_recurse) {
+ 		 *     frame_pointer[-300] = 1;
+ 		 *   }
+ 		 * }
+ 		 */
+ 		.insns = {
+ 			/* main */
+ 			BPF_MOV64_IMM(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 6), /* call A */
+ 			BPF_MOV64_IMM(BPF_REG_1, 1),
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 4), /* call A */
+ 			BPF_MOV64_IMM(BPF_REG_1, 1),
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 7), /* call B */
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 			/* A */
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 2),
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+ 			BPF_EXIT_INSN(),
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call B */
+ 			BPF_EXIT_INSN(),
+ 			/* B */
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+ 			BPF_ST_MEM(BPF_B, BPF_REG_10, -300, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.result = REJECT,
+ 		.errstr = "combined stack",
+ 	},
+ 	{
+ 		"calls: stack depth check using three frames. test5",
+ 		.insns = {
+ 			/* main */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call A */
+ 			BPF_EXIT_INSN(),
+ 			/* A */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call B */
+ 			BPF_EXIT_INSN(),
+ 			/* B */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call C */
+ 			BPF_EXIT_INSN(),
+ 			/* C */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call D */
+ 			BPF_EXIT_INSN(),
+ 			/* D */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call E */
+ 			BPF_EXIT_INSN(),
+ 			/* E */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call F */
+ 			BPF_EXIT_INSN(),
+ 			/* F */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call G */
+ 			BPF_EXIT_INSN(),
+ 			/* G */
+ 			BPF_RAW_INSN(BPF_JMP|BPF_CALL, 0, 1, 0, 1), /* call H */
+ 			BPF_EXIT_INSN(),
+ 			/* H */
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.errstr = "call stack",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: spill into caller stack frame",
+ 		.insns = {
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_1, BPF_REG_1, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.errstr = "cannot spill",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: write into caller stack frame",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
+ 			BPF_EXIT_INSN(),
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 42),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: write into callee stack frame",
+ 		.insns = {
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 42),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, -8),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.errstr = "cannot return stack pointer",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: two calls with stack write and void return",
+ 		.insns = {
+ 			/* main prog */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 2 */
+ 			/* write into stack frame of main prog */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_1, 0, 0),
+ 			BPF_EXIT_INSN(), /* void return */
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: ambiguous return value",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 5),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_0),
+ 			BPF_EXIT_INSN(),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 1),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.errstr_unpriv = "allowed for root only",
+ 		.result_unpriv = REJECT,
+ 		.errstr = "R0 !read_ok",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: two calls that return map_value",
+ 		.insns = {
+ 			/* main prog */
+ 			/* pass fp-16, fp-8 into a function */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 8),
+ 
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 			/* fetch secound map_value_ptr from the stack */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -16),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			/* call 3rd function twice */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+ 			/* first time with fp-8 */
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ 			/* second time with fp-16 */
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 2 */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			/* lookup from map */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			/* write map_value_ptr into stack frame of main prog */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(), /* return 0 */
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.fixup_map1 = { 23 },
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: two calls that return map_value with bool condition",
+ 		.insns = {
+ 			/* main prog */
+ 			/* pass fp-16, fp-8 into a function */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			/* call 3rd function twice */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+ 			/* first time with fp-8 */
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 9),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ 			/* second time with fp-16 */
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ 			/* fetch secound map_value_ptr from the stack */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 2 */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			/* lookup from map */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(), /* return 0 */
+ 			/* write map_value_ptr into stack frame of main prog */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(), /* return 1 */
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.fixup_map1 = { 23 },
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: two calls that return map_value with incorrect bool check",
+ 		.insns = {
+ 			/* main prog */
+ 			/* pass fp-16, fp-8 into a function */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			/* call 3rd function twice */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+ 			/* first time with fp-8 */
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 9),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 1, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_6, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_7),
+ 			/* second time with fp-16 */
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			/* fetch secound map_value_ptr from the stack */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_7, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 2 */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			/* lookup from map */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(), /* return 0 */
+ 			/* write map_value_ptr into stack frame of main prog */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_0, 1),
+ 			BPF_EXIT_INSN(), /* return 1 */
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 		.fixup_map1 = { 23 },
+ 		.result = REJECT,
+ 		.errstr = "invalid read from stack off -16+0 size 8",
+ 	},
+ 	{
+ 		"calls: two calls that receive map_value via arg=ptr_stack_of_caller. test1",
+ 		.insns = {
+ 			/* main prog */
+ 			/* pass fp-16, fp-8 into a function */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+ 			/* 1st lookup from map */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_8, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ 			/* write map_value_ptr into stack frame of main prog at fp-8 */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_8, 1),
+ 
+ 			/* 2nd lookup from map */
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), /* 20 */
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, /* 24 */
+ 				     BPF_FUNC_map_lookup_elem),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_9, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ 			/* write map_value_ptr into stack frame of main prog at fp-16 */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_9, 1),
+ 
+ 			/* call 3rd func with fp-8, 0|1, fp-16, 0|1 */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), /* 30 */
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_8),
+ 			BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_9),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),  /* 34 */
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 2 */
+ 			/* if arg2 == 1 do *arg1 = 0 */
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 
+ 			/* if arg4 == 1 do *arg3 = 0 */
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.fixup_map1 = { 12, 22 },
+ 		.result = REJECT,
+ 		.errstr = "invalid access to map value, value_size=8 off=2 size=8",
+ 	},
+ 	{
+ 		"calls: two calls that receive map_value via arg=ptr_stack_of_caller. test2",
+ 		.insns = {
+ 			/* main prog */
+ 			/* pass fp-16, fp-8 into a function */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+ 			/* 1st lookup from map */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_8, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ 			/* write map_value_ptr into stack frame of main prog at fp-8 */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_8, 1),
+ 
+ 			/* 2nd lookup from map */
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), /* 20 */
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, /* 24 */
+ 				     BPF_FUNC_map_lookup_elem),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_9, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ 			/* write map_value_ptr into stack frame of main prog at fp-16 */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_9, 1),
+ 
+ 			/* call 3rd func with fp-8, 0|1, fp-16, 0|1 */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), /* 30 */
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_8),
+ 			BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_9),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),  /* 34 */
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 2 */
+ 			/* if arg2 == 1 do *arg1 = 0 */
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 
+ 			/* if arg4 == 1 do *arg3 = 0 */
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.fixup_map1 = { 12, 22 },
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: two jumps that receive map_value via arg=ptr_stack_of_jumper. test3",
+ 		.insns = {
+ 			/* main prog */
+ 			/* pass fp-16, fp-8 into a function */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+ 			/* 1st lookup from map */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -24, 0),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -24),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_8, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ 			/* write map_value_ptr into stack frame of main prog at fp-8 */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_8, 1),
+ 
+ 			/* 2nd lookup from map */
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -24),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_9, 0),  // 26
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+ 			/* write map_value_ptr into stack frame of main prog at fp-16 */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_9, 1),
+ 
+ 			/* call 3rd func with fp-8, 0|1, fp-16, 0|1 */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), // 30
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_8),
+ 			BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_9),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_1, 0, 1), // 34
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, -30),
+ 
+ 			/* subprog 2 */
+ 			/* if arg2 == 1 do *arg1 = 0 */
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 
+ 			/* if arg4 == 1 do *arg3 = 0 */
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 2, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, -8),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.fixup_map1 = { 12, 22 },
+ 		.result = REJECT,
+ 		.errstr = "invalid access to map value, value_size=8 off=2 size=8",
+ 	},
+ 	{
+ 		"calls: two calls that receive map_value_ptr_or_null via arg. test1",
+ 		.insns = {
+ 			/* main prog */
+ 			/* pass fp-16, fp-8 into a function */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+ 			/* 1st lookup from map */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			/* write map_value_ptr_or_null into stack frame of main prog at fp-8 */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_8, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ 			BPF_MOV64_IMM(BPF_REG_8, 1),
+ 
+ 			/* 2nd lookup from map */
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			/* write map_value_ptr_or_null into stack frame of main prog at fp-16 */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_9, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ 			BPF_MOV64_IMM(BPF_REG_9, 1),
+ 
+ 			/* call 3rd func with fp-8, 0|1, fp-16, 0|1 */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_8),
+ 			BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_9),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 2 */
+ 			/* if arg2 == 1 do *arg1 = 0 */
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 
+ 			/* if arg4 == 1 do *arg3 = 0 */
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 1, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.fixup_map1 = { 12, 22 },
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: two calls that receive map_value_ptr_or_null via arg. test2",
+ 		.insns = {
+ 			/* main prog */
+ 			/* pass fp-16, fp-8 into a function */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, -8),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -16),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_1),
+ 			BPF_MOV64_REG(BPF_REG_7, BPF_REG_2),
+ 			/* 1st lookup from map */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			/* write map_value_ptr_or_null into stack frame of main prog at fp-8 */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_8, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ 			BPF_MOV64_IMM(BPF_REG_8, 1),
+ 
+ 			/* 2nd lookup from map */
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			/* write map_value_ptr_or_null into stack frame of main prog at fp-16 */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_7, BPF_REG_0, 0),
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_9, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 1),
+ 			BPF_MOV64_IMM(BPF_REG_9, 1),
+ 
+ 			/* call 3rd func with fp-8, 0|1, fp-16, 0|1 */
+ 			BPF_MOV64_REG(BPF_REG_1, BPF_REG_6),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_8),
+ 			BPF_MOV64_REG(BPF_REG_3, BPF_REG_7),
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_9),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 2 */
+ 			/* if arg2 == 1 do *arg1 = 0 */
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_2, 1, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 
+ 			/* if arg4 == 0 do *arg3 = 0 */
+ 			BPF_JMP_IMM(BPF_JNE, BPF_REG_4, 0, 2),
+ 			/* fetch map_value_ptr from the stack of this function */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_3, 0),
+ 			/* write into map value */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_0, 0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.fixup_map1 = { 12, 22 },
+ 		.result = REJECT,
+ 		.errstr = "R0 invalid mem access 'inv'",
+ 	},
+ 	{
+ 		"calls: pkt_ptr spill into caller stack",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 1),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ 			/* spill unchecked pkt_ptr into stack of caller */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2),
+ 			/* now the pkt range is verified, read pkt_ptr from stack */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
+ 			/* write 4 bytes into packet */
+ 			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.result = ACCEPT,
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 	},
+ 	{
+ 		"calls: pkt_ptr spill into caller stack 2",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			/* Marking is still kept, but not in all cases safe. */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+ 			BPF_ST_MEM(BPF_W, BPF_REG_4, 0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ 			/* spill unchecked pkt_ptr into stack of caller */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2),
+ 			/* now the pkt range is verified, read pkt_ptr from stack */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
+ 			/* write 4 bytes into packet */
+ 			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.errstr = "invalid access to packet",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: pkt_ptr spill into caller stack 3",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ 			/* Marking is still kept and safe here. */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+ 			BPF_ST_MEM(BPF_W, BPF_REG_4, 0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ 			/* spill unchecked pkt_ptr into stack of caller */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_MOV64_IMM(BPF_REG_5, 0),
+ 			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3),
+ 			BPF_MOV64_IMM(BPF_REG_5, 1),
+ 			/* now the pkt range is verified, read pkt_ptr from stack */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_2, BPF_REG_4, 0),
+ 			/* write 4 bytes into packet */
+ 			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: pkt_ptr spill into caller stack 4",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 2),
+ 			/* Check marking propagated. */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+ 			BPF_ST_MEM(BPF_W, BPF_REG_4, 0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ 			/* spill unchecked pkt_ptr into stack of caller */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_MOV64_IMM(BPF_REG_5, 0),
+ 			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2),
+ 			BPF_MOV64_IMM(BPF_REG_5, 1),
+ 			/* don't read back pkt_ptr from stack here */
+ 			/* write 4 bytes into packet */
+ 			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: pkt_ptr spill into caller stack 5",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ 			BPF_MOV64_IMM(BPF_REG_5, 0),
+ 			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3),
+ 			/* spill checked pkt_ptr into stack of caller */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_MOV64_IMM(BPF_REG_5, 1),
+ 			/* don't read back pkt_ptr from stack here */
+ 			/* write 4 bytes into packet */
+ 			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.errstr = "same insn cannot be used with different",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: pkt_ptr spill into caller stack 6",
+ 		.insns = {
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ 			BPF_MOV64_IMM(BPF_REG_5, 0),
+ 			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3),
+ 			/* spill checked pkt_ptr into stack of caller */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_MOV64_IMM(BPF_REG_5, 1),
+ 			/* don't read back pkt_ptr from stack here */
+ 			/* write 4 bytes into packet */
+ 			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.errstr = "R4 invalid mem access",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: pkt_ptr spill into caller stack 7",
+ 		.insns = {
+ 			BPF_MOV64_IMM(BPF_REG_2, 0),
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ 			BPF_MOV64_IMM(BPF_REG_5, 0),
+ 			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3),
+ 			/* spill checked pkt_ptr into stack of caller */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_MOV64_IMM(BPF_REG_5, 1),
+ 			/* don't read back pkt_ptr from stack here */
+ 			/* write 4 bytes into packet */
+ 			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.errstr = "R4 invalid mem access",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: pkt_ptr spill into caller stack 8",
+ 		.insns = {
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ 			BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ 			BPF_MOV64_IMM(BPF_REG_5, 0),
+ 			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 3),
+ 			/* spill checked pkt_ptr into stack of caller */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_MOV64_IMM(BPF_REG_5, 1),
+ 			/* don't read back pkt_ptr from stack here */
+ 			/* write 4 bytes into packet */
+ 			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.result = ACCEPT,
+ 	},
+ 	{
+ 		"calls: pkt_ptr spill into caller stack 9",
+ 		.insns = {
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ 			BPF_JMP_REG(BPF_JLE, BPF_REG_0, BPF_REG_3, 1),
+ 			BPF_EXIT_INSN(),
+ 			BPF_MOV64_REG(BPF_REG_4, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_4, -8),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 3),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_4, BPF_REG_10, -8),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_4, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data)),
+ 			BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+ 				    offsetof(struct __sk_buff, data_end)),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_2),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_0, 8),
+ 			BPF_MOV64_IMM(BPF_REG_5, 0),
+ 			/* spill unchecked pkt_ptr into stack of caller */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_4, BPF_REG_2, 0),
+ 			BPF_JMP_REG(BPF_JGT, BPF_REG_0, BPF_REG_3, 2),
+ 			BPF_MOV64_IMM(BPF_REG_5, 1),
+ 			/* don't read back pkt_ptr from stack here */
+ 			/* write 4 bytes into packet */
+ 			BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+ 			BPF_MOV64_REG(BPF_REG_0, BPF_REG_5),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.prog_type = BPF_PROG_TYPE_SCHED_CLS,
+ 		.errstr = "invalid access to packet",
+ 		.result = REJECT,
+ 	},
+ 	{
+ 		"calls: caller stack init to zero or map_value_or_null",
+ 		.insns = {
+ 			BPF_MOV64_IMM(BPF_REG_0, 0),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 1, 0, 4),
+ 			/* fetch map_value_or_null or const_zero from stack */
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 1),
+ 			/* store into map_value */
+ 			BPF_ST_MEM(BPF_W, BPF_REG_0, 0, 0),
+ 			BPF_EXIT_INSN(),
+ 
+ 			/* subprog 1 */
+ 			/* if (ctx == 0) return; */
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_1, 0, 8),
+ 			/* else bpf_map_lookup() and *(fp - 8) = r0 */
+ 			BPF_MOV64_REG(BPF_REG_6, BPF_REG_2),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			/* write map_value_ptr_or_null into stack frame of main prog at fp-8 */
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_6, BPF_REG_0, 0),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.fixup_map1 = { 13 },
+ 		.result = ACCEPT,
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 	},
+ 	{
+ 		"calls: stack init to zero and pruning",
+ 		.insns = {
+ 			/* first make allocated_stack 16 byte */
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -16, 0),
+ 			/* now fork the execution such that the false branch
+ 			 * of JGT insn will be verified second and it skisp zero
+ 			 * init of fp-8 stack slot. If stack liveness marking
+ 			 * is missing live_read marks from call map_lookup
+ 			 * processing then pruning will incorrectly assume
+ 			 * that fp-8 stack slot was unused in the fall-through
+ 			 * branch and will accept the program incorrectly
+ 			 */
+ 			BPF_JMP_IMM(BPF_JGT, BPF_REG_1, 2, 2),
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+ 			BPF_JMP_IMM(BPF_JA, 0, 0, 0),
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+ 				     BPF_FUNC_map_lookup_elem),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.fixup_map2 = { 6 },
+ 		.errstr = "invalid indirect read from stack off -8+0 size 8",
+ 		.result = REJECT,
+ 		.prog_type = BPF_PROG_TYPE_XDP,
+ 	},
+ 	{
+ 		"search pruning: all branches should be verified (nop operation)",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 11),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0xbeef, 2),
+ 			BPF_MOV64_IMM(BPF_REG_4, 0),
+ 			BPF_JMP_A(1),
+ 			BPF_MOV64_IMM(BPF_REG_4, 1),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -16),
+ 			BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -16),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_5, 0, 2),
+ 			BPF_MOV64_IMM(BPF_REG_6, 0),
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_6, 0, 0xdead),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.fixup_map1 = { 3 },
+ 		.errstr = "R6 invalid mem access 'inv'",
+ 		.result = REJECT,
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 	},
+ 	{
+ 		"search pruning: all branches should be verified (invalid stack access)",
+ 		.insns = {
+ 			BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+ 			BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+ 			BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0),
+ 			BPF_LD_MAP_FD(BPF_REG_1, 0),
+ 			BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 8),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_3, BPF_REG_0, 0),
+ 			BPF_MOV64_IMM(BPF_REG_4, 0),
+ 			BPF_JMP_IMM(BPF_JEQ, BPF_REG_3, 0xbeef, 2),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -16),
+ 			BPF_JMP_A(1),
+ 			BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_4, -24),
+ 			BPF_EMIT_CALL(BPF_FUNC_ktime_get_ns),
+ 			BPF_LDX_MEM(BPF_DW, BPF_REG_5, BPF_REG_10, -16),
+ 			BPF_EXIT_INSN(),
+ 		},
+ 		.fixup_map1 = { 3 },
+ 		.errstr = "invalid read from stack off -16+0 size 8",
+ 		.result = REJECT,
+ 		.prog_type = BPF_PROG_TYPE_TRACEPOINT,
+ 	},
  };
static int probe_filter_length(const struct bpf_insn *fp)
-- 
LinuxNextTracking

    