update ABI file for 5.19.17-2-pve

(generated with debian/scripts/abi-generate) Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
bump version to 5.19.17-2
2023-01-28 16:55:50 +01:00 · 2023-01-28 16:55:47 +01:00 · 2023-01-28 16:38:52 +01:00 · 2023-01-28 16:38:25 +01:00 · 2023-01-28 16:26:32 +01:00 · 2023-01-28 16:23:39 +01:00
62 changed files with 31834 additions and 25726 deletions
@@ -1 +1,2 @@
 ubuntu-zesty
+*.prepared
@@ -1,6 +1,6 @@
-[submodule "submodules/ubuntu-artful"]
-	path = submodules/ubuntu-artful
-	url = ../mirror_ubuntu-artful-kernel
 [submodule "submodules/zfsonlinux"]
 	path = submodules/zfsonlinux
 	url = ../zfsonlinux
+[submodule "submodules/ubuntu-kernel"]
+	path = submodules/ubuntu-kernel
+	url = ../mirror_ubuntu-kernels
@@ -1,12 +1,12 @@
-RELEASE=5.1
+# also bump pve-kernel-meta if either of MAJ.MIN, PATCHLEVEL or KREL change
+KERNEL_MAJ=5
+KERNEL_MIN=19
+KERNEL_PATCHLEVEL=17
+# increment KREL if the ABI changes (abicheck target in debian/rules)
+# rebuild packages with new KREL and run 'make abiupdate'
+KREL=2

-# also update pve-kernel-meta.git if either of these change
-KERNEL_MAJ=4
-KERNEL_MIN=13
-KERNEL_PATCHLEVEL=16
-KREL=4
-
-PKGREL=51
+PKGREL=2

 KERNEL_MAJMIN=$(KERNEL_MAJ).$(KERNEL_MIN)
 KERNEL_VER=$(KERNEL_MAJMIN).$(KERNEL_PATCHLEVEL)
@@ -29,56 +29,32 @@ GITVERSION:=$(shell git rev-parse HEAD)

 SKIPABI=0

-ifeq    ($(CC), cc)
-GCC=gcc
-else
-GCC=$(CC)
-endif
-
 BUILD_DIR=build

-KERNEL_SRC=ubuntu-artful
+KERNEL_SRC=ubuntu-kernel
 KERNEL_SRC_SUBMODULE=submodules/$(KERNEL_SRC)
 KERNEL_CFG_ORG=config-${KERNEL_VER}.org

-E1000EDIR=e1000e-3.3.6
-E1000ESRC=${E1000EDIR}.tar.gz
-
-IGBDIR=igb-5.3.5.10
-IGBSRC=${IGBDIR}.tar.gz
-
-IXGBEDIR=ixgbe-5.3.3
-IXGBESRC=${IXGBEDIR}.tar.gz
-
 ZFSONLINUX_SUBMODULE=submodules/zfsonlinux
-SPLDIR=pkg-spl
-SPLSRC=${ZFSONLINUX_SUBMODULE}/spl-debian
 ZFSDIR=pkg-zfs
-ZFSSRC=${ZFSONLINUX_SUBMODULE}/zfs-debian

 MODULES=modules
-MODULE_DIRS=${E1000EDIR} ${IGBDIR} ${IXGBEDIR} ${SPLDIR} ${ZFSDIR}
+MODULE_DIRS=${ZFSDIR}

 # exported to debian/rules via debian/rules.d/dirs.mk
-DIRS=KERNEL_SRC E1000EDIR IGBDIR IXGBEDIR SPLDIR ZFSDIR MODULES
+DIRS=KERNEL_SRC ZFSDIR MODULES

 DST_DEB=${PACKAGE}_${KERNEL_VER}-${PKGREL}_${ARCH}.deb
 HDR_DEB=${HDRPACKAGE}_${KERNEL_VER}-${PKGREL}_${ARCH}.deb
+USR_HDR_DEB=pve-kernel-libc-dev_${KERNEL_VER}-${PKGREL}_${ARCH}.deb
 LINUX_TOOLS_DEB=linux-tools-$(KERNEL_MAJMIN)_${KERNEL_VER}-${PKGREL}_${ARCH}.deb
+LINUX_TOOLS_DBG_DEB=linux-tools-$(KERNEL_MAJMIN)-dbgsym_${KERNEL_VER}-${PKGREL}_${ARCH}.deb

-DEBS=${DST_DEB} ${HDR_DEB} ${LINUX_TOOLS_DEB}
+DEBS=${DST_DEB} ${HDR_DEB} ${USR_HDR_DEB} ${LINUX_TOOLS_DEB} ${LINUX_TOOLS_DBG_DEB}

-all: check_gcc deb
+all: deb
 deb: ${DEBS}

-check_gcc:
-	$(GCC) --version|grep "6\.3" || false
-	@$(GCC) -Werror -mindirect-branch=thunk-extern -mindirect-branch-register -c -x c /dev/null -o check_gcc.o \
-		|| ( rm -f check_gcc.o; \
-		     echo "Please install gcc-6 packages with indirect thunk / RETPOLINE support"; \
-		     false)
-	@rm -f check_gcc.o
-
 ${LINUX_TOOLS_DEB} ${HDR_DEB}: ${DST_DEB}
 ${DST_DEB}: ${BUILD_DIR}.prepared
 	cd ${BUILD_DIR}; dpkg-buildpackage --jobs=auto -b -uc -us
@@ -112,53 +88,23 @@ ${KERNEL_SRC}.prepared: ${KERNEL_SRC_SUBMODULE} | submodule
 	cp ${KERNEL_CFG_ORG} ${BUILD_DIR}/${KERNEL_SRC}/.config
 	sed -i ${BUILD_DIR}/${KERNEL_SRC}/Makefile -e 's/^EXTRAVERSION.*$$/EXTRAVERSION=${EXTRAVERSION}/'
 	rm -rf ${BUILD_DIR}/${KERNEL_SRC}/debian ${BUILD_DIR}/${KERNEL_SRC}/debian.master
-	cd ${BUILD_DIR}/${KERNEL_SRC}; for patch in ../../patches/kernel/*.patch; do patch -p1 < $${patch}; done
+	set -e; cd ${BUILD_DIR}/${KERNEL_SRC}; for patch in ../../patches/kernel/*.patch; do echo "applying patch '$$patch'" && patch -p1 < $${patch}; done
 	touch $@

 ${MODULES}.prepared: $(addsuffix .prepared,${MODULE_DIRS})
 	touch $@

-${E1000EDIR}.prepared: ${E1000ESRC}
-	rm -rf ${BUILD_DIR}/${MODULES}/${E1000EDIR} $@
-	mkdir -p ${BUILD_DIR}/${MODULES}/${E1000EDIR}
-	tar --strip-components=1 -C ${BUILD_DIR}/${MODULES}/${E1000EDIR} -xf ${E1000ESRC}
-	cd ${BUILD_DIR}/${MODULES}/${E1000EDIR}; patch -p1 < ../../../patches/intel/intel-module-gcc6-compat.patch
-	cd ${BUILD_DIR}/${MODULES}/${E1000EDIR}; patch -p1 < ../../../patches/intel/e1000e/e1000e_4.10_max-mtu.patch
-	touch $@
-
-${IGBDIR}.prepared: ${IGBSRC}
-	rm -rf ${BUILD_DIR}/${MODULES}/${IGBDIR} $@
-	mkdir -p ${BUILD_DIR}/${MODULES}/${IGBDIR}
-	tar --strip-components=1 -C ${BUILD_DIR}/${MODULES}/${IGBDIR} -xf ${IGBSRC}
-	cd ${BUILD_DIR}/${MODULES}/${IGBDIR}; patch -p1 < ../../../patches/intel/igb/igb_4.10_max-mtu.patch
-	cd ${BUILD_DIR}/${MODULES}/${IGBDIR}; patch -p1 < ../../../patches/intel/igb/igb_4.12_compat.patch
-	touch $@
-
-${IXGBEDIR}.prepared: ${IXGBESRC}
-	rm -rf ${BUILD_DIR}/${MODULES}/${IXGBEDIR} $@
-	mkdir -p ${BUILD_DIR}/${MODULES}/${IXGBEDIR}
-	tar --strip-components=1 -C ${BUILD_DIR}/${MODULES}/${IXGBEDIR} -xf ${IXGBESRC}
-	touch $@
-
-$(SPLDIR).prepared: ${SPLSRC}
-	rm -rf ${BUILD_DIR}/${MODULES}/${SPLDIR} $@
-	mkdir -p ${BUILD_DIR}/${MODULES}/${SPLDIR}
-	cp -a ${SPLSRC}/* ${BUILD_DIR}/${MODULES}/${SPLDIR}
-	cd ${BUILD_DIR}/${MODULES}/${SPLDIR}; for patch in ../../../${SPLSRC}/../spl-patches/*.patch; do patch -p1 < $${patch}; done
-	touch $@
-
-$(ZFSDIR).prepared: ${ZFSSRC}
-	rm -rf ${BUILD_DIR}/${MODULES}/${ZFSDIR} $@
-	mkdir -p ${BUILD_DIR}/${MODULES}/${ZFSDIR}
-	cp -a ${ZFSSRC}/* ${BUILD_DIR}/${MODULES}/${ZFSDIR}
-	cd ${BUILD_DIR}/${MODULES}/${ZFSDIR}; for patch in ../../../${ZFSSRC}/../zfs-patches/*.patch; do patch -p1 < $${patch}; done
-	# temporarily since patch does not know about permissions, remove after 0.7.7 was merged properly
-	chmod +x ${BUILD_DIR}/${MODULES}/${ZFSDIR}/scripts/enum-extract.pl
-	touch $@
+${ZFSDIR}.prepared: ${ZFSONLINUX_SUBMODULE}
+	rm -rf ${BUILD_DIR}/${MODULES}/${ZFSDIR} ${BUILD_DIR}/${MODULES}/tmp $@
+	mkdir -p ${BUILD_DIR}/${MODULES}/tmp
+	cp -a ${ZFSONLINUX_SUBMODULE}/* ${BUILD_DIR}/${MODULES}/tmp
+	cd ${BUILD_DIR}/${MODULES}/tmp; make kernel
+	rm -rf ${BUILD_DIR}/${MODULES}/tmp
+	touch ${ZFSDIR}.prepared

 .PHONY: upload
 upload: ${DEBS}
-	tar cf - ${DEBS}|ssh repoman@repo.proxmox.com -- upload --product pve,pmg --dist stretch --arch ${ARCH}
+	tar cf - ${DEBS}|ssh -X repoman@repo.proxmox.com -- upload --product pve,pmg,pbs --dist bullseye --arch ${ARCH}

 .PHONY: distclean
 distclean: clean
@@ -168,15 +114,13 @@ distclean: clean
 .PHONY: update_modules
 update_modules: submodule
 	git submodule foreach 'git pull --ff-only origin master'
-	cd ${ZFSSRC}; git pull --ff-only origin master
-	cd ${SPLSRC}; git pull --ff-only origin master
+	cd ${ZFSONLINUX_SUBMODULE}; git pull --ff-only origin master

 # make sure submodules were initialized
 .PHONY: submodule
 submodule:
 	test -f "${KERNEL_SRC_SUBMODULE}/README" || git submodule update --init ${KERNEL_SRC_SUBMODULE}
-	test -f "${ZFSONLINUX_SUBMODULE}/Makefile" || git submodule update --init ${ZFSONLINUX_SUBMODULE}
-	(test -f "${ZFSSRC}/debian/changelog" && test -f "${SPLZRC}/debian/changelog") || (cd ${ZFSONLINUX_SUBMODULE}; git submodule update --init)
+	test -f "${ZFSONLINUX_SUBMODULE}/Makefile" || git submodule update --init --recursive ${ZFSONLINUX_SUBMODULE}

 # call after ABI bump with header deb in working directory
 .PHONY: abiupdate
@@ -3,22 +3,20 @@ KERNEL SOURCE:

 We currently use the Ubuntu kernel sources, available from:

- http://kernel.ubuntu.com/git/ubuntu/ubuntu-artful.git/
+ http://kernel.ubuntu.com/git/ubuntu/ubuntu-jammy.git/

 Ubuntu will maintain those kernels till:

 https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable
+ or
+ https://pve.proxmox.com/pve-docs/chapter-pve-faq.html#faq-support-table
+
+ whatever happens to be earlier.


 Additional/Updated Modules:
 ---------------------------

- include latest e1000e driver from intel/sourceforge
-
- include latest ixgbe driver from intel/sourceforge
-
- include latest igb driver from intel/sourceforge
-
 - include native OpenZFS filesystem kernel modules for Linux

  * https://github.com/zfsonlinux/
@@ -26,6 +24,32 @@ Additional/Updated Modules:
  For licensing questions, see: http://open-zfs.org/wiki/Talk:FAQ


+SUBMODULE
+=========
+
+We track the current upstream repository as submodule. Besides obvious
+advantages over tracking binary tar archives this also has some implications.
+
+For building the submodule directory gets copied into build/ and a few patches
+get applied with the `patch` tool. From a git point-of-view, the copied
+directory remains clean even with extra patches applied since it does not
+contain a .git directory, but a reference to the (still pristine) submodule:
+
+$ cat build/ubuntu-jammy/.git
+
+If you mistakenly cloned the upstream repo as "normal" clone (not via the
+submodule mechanics) this means that you have a real .git directory with its
+independent objects and tracking info when copying for building, thus git
+operates on the copied directory - and "sees" that it was dirtied by `patch`,
+and thus the kernel buildsystem sees this too and will add a '+' to the version
+as a result. This changes the output directories for modules and other build
+artefacts and let's then the build fail on packaging.
+
+So always ensure that you really checked it out as submodule, not as full
+"normal" clone. You can also explicitly set the LOCALVERSION variable to
+undefined with: `export LOCALVERSION= but that should only be done for test
+builds.
+
 RELATED PACKAGES:
 =================

@@ -40,7 +64,7 @@ pve-kernel-meta
 ---------------

 depends on latest kernel and header package within a certain kernel series,
-e.g., pve-kernel-4.13 / pve-headers-4.13
+e.g., pve-kernel-5.15 / pve-headers-5.15

 git clone git://git.proxmox.com/git/pve-kernel-meta.git

@@ -55,6 +79,21 @@ git clone git://git.proxmox.com/git/pve-firmware.git
 NOTES:
 ======

+ABI versions, package versions and package name:
+------------------------------------------------
+
+We follow debian's versioning w.r.t ABI changes:
+
+https://kernel-team.pages.debian.net/kernel-handbook/ch-versions.html
+https://wiki.debian.org/DebianKernelABIChanges
+
+The debian/rules file has a target comparing the build kernel's ABI against the
+version stored in the repository and indicates when an ABI bump is necessary.
+An ABI bump within one upstream version consists of incrementing the KREL
+variable in the Makefile, rebuilding the packages and running 'make abiupdate'
+(the 'abiupdate' target in 'Makefile' contains the steps for consistently
+updating the repository).
+
 Watchdog blacklist
 ------------------

@@ -63,13 +102,25 @@ which device is actually used for /dev/watchdog.
 We ship this list in /lib/modprobe.d/blacklist_pve-kernel-<VERSION>.conf
 The user typically edit /etc/modules to enable a specific watchdog device.

+Debug kernel and modules
+------------------------
+
+In order to build a -dbgsym package containing an unstripped copy of the kernel
+image and modules, enable the 'pkg.pve-kernel.debug' build profile (e.g. by
+exporting DEB_BUILD_PROFILES='pkg.pve-kernel.debug'). The resulting package can
+be used together with 'crash'/'kdump-tools' to debug kernel crashes.
+
+Note: the -dbgsym package is only valid for the pve-kernel packages produced by
+the same build. A kernel/module from a different build will likely not match,
+even if both builds are of the same kernel and package version.
+
 Additional information
 ----------------------

 We use the default configuration provided by Ubuntu, and apply
 the following modifications:

-see debian/rules (PVE_CONFIG_OPTS)
+NOTE: For the exact and current list see debian/rules (PVE_CONFIG_OPTS)

 - enable INTEL_MEI_WDT=m (to allow disabling via patch)

@@ -80,68 +131,45 @@ see debian/rules (PVE_CONFIG_OPTS)
 - enable CONFIG_CEPH_FS=m (request from user)

 - enable common CONFIG_BLK_DEV_XXX to avoid hardware detection
-  problems (udev, undate-initramfs have serious problems without that)
+  problems (udev, update-initramfs have serious problems without that)

  	 CONFIG_BLK_DEV_SD=y
  	 CONFIG_BLK_DEV_SR=y
  	 CONFIG_BLK_DEV_DM=y

- add workaround for Debian bug #807000 (see
-  https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=807000)
-
-  	 CONFIG_BLK_DEV_NVME=y
-
 - compile NBD and RBD modules
 	 CONFIG_BLK_DEV_NBD=m
 	 CONFIG_BLK_DEV_RBD=m

- set LOOP_MIN_COUNT to 8 (debian defaults)
-	 CONFIG_BLK_DEV_LOOP_MIN_COUNT=8
+- enable IBM JFS file system as module
+  requested by users (bug #64)

- disable module signatures (CONFIG_MODULE_SIG)
-
- enable IBM JFS file system
-
-  This is disabled in RHEL kernel for no real reason, so we enable
-  it as requested by users (bug #64)
-
- enable apple HFS and HFSPLUS
-
-  This is disabled in RHEL kernel for no real reason, so we enable
-  it as requested by users
+- enable apple HFS and HFSPLUS as module
+  requested by users

 - enable CONFIG_BCACHE=m (requested by user)

 - enable CONFIG_BRIDGE=y
-
-  Else we get warnings on boot, that
-  net.bridge.bridge-nf-call-iptables is an unknown key
+  to avoid warnings on boot, e.g. that net.bridge.bridge-nf-call-iptables is an unknown key

 - enable CONFIG_DEFAULT_SECURITY_APPARMOR
-
  We need this for lxc

 - set CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE=y
-
  because if not set, it can give some dynamic memory or cpu frequencies 
  change, and vms can crash (mainly windows guest).
-
  see http://forum.proxmox.com/threads/18238-Windows-7-x64-VMs-crashing-randomly-during-process-termination?p=93273#post93273

 - use 'deadline' as default scheduler
-
-  This is the suggested setting for KVM. We also measure bad fsync
-  performance with ext4 and cfq.
+  This is the suggested setting for KVM. We also measure bad fsync performance with ext4 and cfq.

 - disable CONFIG_INPUT_EVBUG
-
-  Module evbug is not blacklisted on debian, so we simply disable it
-  to avoid key-event logs (which is a big security problem)
+  Module evbug is not blacklisted on debian, so we simply disable it to avoid
+  key-event logs (which is a big security problem)

 - enable CONFIG_MODVERSIONS (needed for ABI tracking)

 - switch default UNWINDER to FRAME_POINTER
-
  the recently introduced ORC_UNWINDER is not 100% stable yet, especially in combination with ZFS

 - enable CONFIG_PAGE_TABLE_ISOLATION (Meltdown mitigation)
@@ -2,18 +2,39 @@ Source: pve-kernel
 Section: devel
 Priority: optional
 Maintainer: Proxmox Support Team <support@proxmox.com>
-Build-Depends: asciidoc,
+Build-Depends: asciidoc-base,
+               automake,
               bc,
               bison,
+               cpio,
+               debhelper (>= 10~),
+               dh-python,
+               dwarves,
+               file,
               flex,
-               gcc-6 (>= 6.3.0-18+deb9u1),
+               gcc (>= 8.3.0-6),
+               git,
+               kmod,
+               libdw-dev,
+               libelf-dev,
               libiberty-dev,
+               libnuma-dev,
+               libpve-common-perl,
+               libslang2-dev,
               libssl-dev,
+               libtool,
               lintian,
+               lz4,
+               perl-modules,
+               python3-minimal,
+               rsync,
               sed,
+               sphinx-common,
               tar,
               xmlto,
-Build-Conflicts: pve-headers-@KVNAME@,
+               zlib1g-dev,
+               zstd,
+Build-Conflicts: pve-headers-@KVNAME@
 Vcs-Git: git://git.proxmox.com/git/pve-kernel
 Vcs-Browser: https://git.proxmox.com/?p=pve-kernel.git

@@ -21,9 +42,7 @@ Package: linux-tools-@KVMAJMIN@
 Architecture: any
 Section: devel
 Priority: optional
-Depends: linux-base,
-         ${misc:Depends},
-         ${shlibs:Depends},
+Depends: linux-base, ${misc:Depends}, ${shlibs:Depends}
 Description: Linux kernel version specific tools for version @KVMAJMIN@
 This package provides the architecture dependent parts for kernel
 version locked tools (such as perf and x86_energy_perf_policy)
@@ -32,21 +51,43 @@ Package: pve-headers-@KVNAME@
 Section: devel
 Priority: optional
 Architecture: any
-Provides: linux-headers,
-          linux-headers-2.6,
-Depends: coreutils | fileutils (>= 4.0),
-Description: The Proxmox PVE Kernel Headers
+Provides: linux-headers-@KVNAME@-amd64
+Depends: coreutils | fileutils (>= 4.0)
+Description: Proxmox Kernel Headers
 This package contains the linux kernel headers

 Package: pve-kernel-@KVNAME@
 Section: admin
 Priority: optional
 Architecture: any
-Provides: linux-image,
-          linux-image-2.6,
-Suggests: pve-firmware,
-Depends: busybox,
-         grub-pc | grub-efi-amd64 | grub-efi-ia32 | grub-efi-arm64,
-         initramfs-tools,
-Description: The Proxmox PVE Kernel Image
+Provides: linux-image-@KVNAME@-amd64
+Suggests: pve-firmware
+Depends: busybox, initramfs-tools
+Recommends: grub-pc | grub-efi-amd64 | grub-efi-ia32 | grub-efi-arm64
+Description: Proxmox Kernel Image
 This package contains the linux kernel and initial ramdisk used for booting
+
+Package: pve-kernel-@KVNAME@-dbgsym
+Architecture: any
+Provides: linux-debug
+Section: devel
+Priority: optional
+Build-Profiles: <pkg.pve-kernel.debug>
+Description: Proxmox Kernel debug image
+ This package provides the kernel debug image for version @KVNAME@. The debug
+ kernel image contained in this package is NOT meant to boot from - it is
+ uncompressed, and unstripped, and suitable for use with crash/kdump-tools/..
+ to analyze kernel crashes. This package also contains the pve-kernel modules
+ in their unstripped version.
+
+Package: pve-kernel-libc-dev
+Section: devel
+Priority: optional
+Architecture: any
+Provides: linux-libc-dev (=${binary:Version})
+Conflicts: linux-libc-dev
+Replaces: linux-libc-dev
+Depends: ${misc:Depends}
+Description: Linux support headers for userspace development
+ This package provides userspaces headers from the Linux kernel.  These headers
+ are used by the installed headers for GNU libc and other system libraries.
@@ -1,11 +1,8 @@
 This is a prepackaged version of the Linux kernel binary image.

-This package was put together by Proxmox Server
-Solutions GmbH <support@proxmox.com>.
-
-We use the RHEL7 kernel sources, available from:
-
-ftp://ftp.redhat.com/redhat/rhel/
+For the packaging and all files in the debian/ folder consider:
+ Copyright (C) 2007-2022 Proxmox Server Solutions GmbH
+ Licensed under the AGPL-3.0-or-later

 Linux is copyrighted by Linus Torvalds and others.

@@ -14,8 +14,11 @@ include debian/rules.d/${DEB_BUILD_ARCH}.mk
 CHANGELOG_DATE:=$(shell dpkg-parsechangelog -SDate)

 PVE_KERNEL_PKG=pve-kernel-${KVNAME}
+PVE_DEBUG_KERNEL_PKG=pve-kernel-${KVNAME}-dbgsym
 PVE_HEADER_PKG=pve-headers-${KVNAME}
+PVE_USR_HEADER_PKG=pve-kernel-libc-dev
 LINUX_TOOLS_PKG=linux-tools-${KERNEL_MAJMIN}
+KERNEL_SRC_COPY=${KERNEL_SRC}_tmp

 # TODO: split for archs, move to files?
 PVE_CONFIG_OPTS= \
@@ -26,22 +29,45 @@ PVE_CONFIG_OPTS= \
 -m CONFIG_CEPH_FS \
 -m CONFIG_BLK_DEV_NBD \
 -m CONFIG_BLK_DEV_RBD \
+-d CONFIG_SND_PCSP \
 -m CONFIG_BCACHE \
 -m CONFIG_JFS_FS \
 -m CONFIG_HFS_FS \
 -m CONFIG_HFSPLUS_FS \
+-e CIFS_SMB_DIRECT \
+-e CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU \
 -e CONFIG_BRIDGE \
 -e CONFIG_BRIDGE_NETFILTER \
 -e CONFIG_BLK_DEV_SD \
 -e CONFIG_BLK_DEV_SR \
 -e CONFIG_BLK_DEV_DM \
-e CONFIG_BLK_DEV_NVME \
+-m CONFIG_BLK_DEV_NVME \
+-e CONFIG_NLS_ISO8859_1 \
 -d CONFIG_INPUT_EVBUG \
 -d CONFIG_CPU_FREQ_DEFAULT_GOV_ONDEMAND \
+-d CONFIG_CPU_FREQ_DEFAULT_GOV_SCHEDUTIL \
 -e CONFIG_CPU_FREQ_DEFAULT_GOV_PERFORMANCE \
+-e CONFIG_SYSFB_SIMPLEFB \
+-e CONFIG_DRM_SIMPLEDRM \
 -d CONFIG_MODULE_SIG \
 -d CONFIG_MEMCG_DISABLED \
 -e CONFIG_MEMCG_SWAP_ENABLED \
+-e CONFIG_HYPERV \
+-m CONFIG_VFIO_IOMMU_TYPE1 \
+-m CONFIG_VFIO_VIRQFD \
+-m CONFIG_VFIO \
+-m CONFIG_VFIO_PCI \
+-m CONFIG_USB_XHCI_HCD \
+-m CONFIG_USB_XHCI_PCI \
+-m CONFIG_USB_EHCI_HCD \
+-m CONFIG_USB_EHCI_PCI \
+-m CONFIG_USB_EHCI_HCD_PLATFORM \
+-m CONFIG_USB_OHCI_HCD \
+-m CONFIG_USB_OHCI_HCD_PCI \
+-m CONFIG_USB_OHCI_HCD_PLATFORM \
+-d CONFIG_USB_OHCI_HCD_SSB \
+-m CONFIG_USB_UHCI_HCD \
+-d CONFIG_USB_SL811_HCD_ISO \
 -e CONFIG_MEMCG_KMEM \
 -d CONFIG_DEFAULT_CFQ \
 -e CONFIG_DEFAULT_DEADLINE \
@@ -52,6 +78,11 @@ PVE_CONFIG_OPTS= \
 -d CONFIG_UNWINDER_ORC \
 -d CONFIG_UNWINDER_GUESS \
 -e CONFIG_UNWINDER_FRAME_POINTER \
+--set-str CONFIG_SYSTEM_TRUSTED_KEYS ""\
+--set-str CONFIG_SYSTEM_REVOCATION_KEYS ""\
+-d CONFIG_SECURITY_LOCKDOWN_LSM \
+-d CONFIG_SECURITY_LOCKDOWN_LSM_EARLY \
+--set-str CONFIG_LSM yama,integrity,apparmor \
 -e CONFIG_PAGE_TABLE_ISOLATION

 debian/control: $(wildcard debian/*.in)
@@ -67,7 +98,7 @@ debian/control: $(wildcard debian/*.in)

 build: .compile_mark .tools_compile_mark .modules_compile_mark

-install: .install_mark .tools_install_mark .headers_install_mark
+install: .install_mark .tools_install_mark .headers_install_mark .usr_headers_install_mark
 	dh_installdocs -A debian/copyright debian/SOURCE
 	dh_installchangelogs
 	dh_installman
@@ -77,7 +108,7 @@ install: .install_mark .tools_install_mark .headers_install_mark

 binary: install
 	debian/rules fwcheck abicheck
-	dh_strip -N${PVE_HEADER_PKG}
+	dh_strip -N${PVE_HEADER_PKG} -N${PVE_USR_HEADER_PKG}
 	dh_makeshlibs
 	dh_shlibdeps
 	dh_installdeb
@@ -85,9 +116,15 @@ binary: install
 	dh_md5sums
 	dh_builddeb

-.compile_mark: ${KERNEL_SRC}/.config
+.config_mark:
 	cd ${KERNEL_SRC}; scripts/config ${PVE_CONFIG_OPTS}
 	${MAKE} -C ${KERNEL_SRC} oldconfig
+	# copy to allow building in parallel to kernel/module compilation without interference
+	rm -rf ${KERNEL_SRC_COPY}
+	cp -ar ${KERNEL_SRC} ${KERNEL_SRC_COPY}
+	touch $@
+
+.compile_mark: .config_mark
 	${MAKE} -C ${KERNEL_SRC} KBUILD_BUILD_VERSION_TIMESTAMP="PVE ${DEB_VERSION} (${CHANGELOG_DATE})"
 	touch $@

@@ -99,17 +136,25 @@ binary: install
 	install -m 644 ${KERNEL_SRC}/System.map debian/${PVE_KERNEL_PKG}/boot/System.map-${KVNAME}
 	install -m 644 ${KERNEL_SRC}/${KERNEL_IMAGE_PATH} debian/${PVE_KERNEL_PKG}/boot/${KERNEL_INSTALL_FILE}-${KVNAME}
 	${MAKE} -C ${KERNEL_SRC} INSTALL_MOD_PATH=${BUILD_DIR}/debian/${PVE_KERNEL_PKG}/ modules_install
-	## install latest ibg driver
-	install -m 644 ${MODULES}/igb.ko debian/${PVE_KERNEL_PKG}/lib/modules/${KVNAME}/kernel/drivers/net/ethernet/intel/igb/
-	# install latest ixgbe driver
-	install -m 644 ${MODULES}/ixgbe.ko debian/${PVE_KERNEL_PKG}/lib/modules/${KVNAME}/kernel/drivers/net/ethernet/intel/ixgbe/
-	# install latest e1000e driver
-	install -m 644 ${MODULES}/e1000e.ko debian/${PVE_KERNEL_PKG}/lib/modules/${KVNAME}/kernel/drivers/net/ethernet/intel/e1000e/
 	# install zfs drivers
 	install -d -m 0755 debian/${PVE_KERNEL_PKG}/lib/modules/${KVNAME}/zfs
-	install -m 644 $(addprefix ${MODULES}/,spl.ko splat.ko zfs.ko zavl.ko znvpair.ko zunicode.ko zcommon.ko zpios.ko icp.ko) debian/${PVE_KERNEL_PKG}/lib/modules/${KVNAME}/zfs
+	install -m 644 $(addprefix ${MODULES}/,zfs.ko zavl.ko znvpair.ko zunicode.ko zcommon.ko icp.ko zlua.ko spl.ko zzstd.ko) debian/${PVE_KERNEL_PKG}/lib/modules/${KVNAME}/zfs
 	# remove firmware
 	rm -rf debian/${PVE_KERNEL_PKG}/lib/firmware
+
+ifeq ($(filter pkg.pve-kernel.debug,$(DEB_BUILD_PROFILES)),)
+	echo "'pkg.pve-kernel.debug' build profile disabled, skipping -dbgsym creation"
+else
+	echo "'pkg.pve-kernel.debug' build profile enabled, creating -dbgsym contents"
+	mkdir -p debian/${PVE_DEBUG_KERNEL_PKG}/usr/lib/debug/lib/modules/${KVNAME}
+	mkdir debian/${PVE_DEBUG_KERNEL_PKG}/usr/lib/debug/boot
+	install -m 644 ${KERNEL_SRC}/vmlinux debian/${PVE_DEBUG_KERNEL_PKG}/usr/lib/debug/boot/vmlinux-${KVNAME}
+	cp -r debian/${PVE_KERNEL_PKG}/lib/modules/${KVNAME} debian/${PVE_DEBUG_KERNEL_PKG}/usr/lib/debug/lib/modules/
+	rm -f debian/${PVE_DEBUG_KERNEL_PKG}/usr/lib/debug/lib/modules/${KVNAME}/source
+	rm -f debian/${PVE_DEBUG_KERNEL_PKG}/usr/lib/debug/lib/modules/${KVNAME}/build
+	rm -f debian/${PVE_DEBUG_KERNEL_PKG}/usr/lib/debug/lib/modules/${KVNAME}/modules.*
+endif
+
 	# strip debug info
 	find debian/${PVE_KERNEL_PKG}/lib/modules -name \*.ko -print | while read f ; do strip --strip-debug "$$f"; done
 	# finalize
@@ -124,7 +169,7 @@ binary: install
 	touch $@

 .tools_compile_mark: .compile_mark
-	${MAKE} -C ${KERNEL_SRC}/tools/perf prefix=/usr HAVE_NO_LIBBFD=1 HAVE_CPLUS_DEMANGLE_SUPPORT=1 NO_LIBPYTHON=1 NO_LIBPERL=1 NO_LIBCRYPTO=1 PYTHON=python2.7
+	${MAKE} -C ${KERNEL_SRC}/tools/perf prefix=/usr HAVE_NO_LIBBFD=1 HAVE_CPLUS_DEMANGLE_SUPPORT=1 NO_LIBPYTHON=1 NO_LIBPERL=1 NO_LIBCRYPTO=1 PYTHON=python3
 	echo "checking GPL-2 only perf binary for library linkage with incompatible licenses.."
 	! ldd ${KERNEL_SRC}/tools/perf/perf | grep -q -E '\blibbfd'
 	! ldd ${KERNEL_SRC}/tools/perf/perf | grep -q -E '\blibcrypto'
@@ -142,12 +187,12 @@ binary: install
 	done
 	touch $@

-.headers_install_mark: .compile_mark .modules_compile_mark
+.headers_prepare_mark: .config_mark
 	rm -rf debian/${PVE_HEADER_PKG}
 	mkdir -p debian/${PVE_HEADER_PKG}/usr/src/linux-headers-${KVNAME}
 	install -m 0644 ${KERNEL_SRC}/.config debian/${PVE_HEADER_PKG}/usr/src/linux-headers-${KVNAME}
-	install -m 0644 ${KERNEL_SRC}/Module.symvers debian/${PVE_HEADER_PKG}/usr/src/linux-headers-${KVNAME}
-	cd ${KERNEL_SRC}; find . -path './debian/*' -prune \
+	make -C ${KERNEL_SRC_COPY} mrproper
+	cd ${KERNEL_SRC_COPY}; find . -path './debian/*' -prune \
 	    -o -path './include/*' -prune \
 	    -o -path './Documentation' -prune \
 	    -o -path './scripts' -prune \
@@ -160,50 +205,65 @@ binary: install
 	        -o -name '*.pl' \
 	    \) \
 	    -print | cpio -pd --preserve-modification-time ${BUILD_DIR}/debian/${PVE_HEADER_PKG}/usr/src/linux-headers-${KVNAME}
-	cd ${KERNEL_SRC}; cp -a include scripts ${BUILD_DIR}/debian/${PVE_HEADER_PKG}/usr/src/linux-headers-${KVNAME}
-	cd ${KERNEL_SRC}; \
+	cd ${KERNEL_SRC_COPY}; \
 	    ( \
 	        find arch/${KERNEL_HEADER_ARCH} -name include -type d -print | \
 	        xargs -n1 -i: find : -type f \
 	    ) | \
 	    cpio -pd --preserve-modification-time ${BUILD_DIR}/debian/${PVE_HEADER_PKG}/usr/src/linux-headers-${KVNAME}
+	touch $@
+
+.headers_compile_mark: .headers_prepare_mark
+	# set output to subdir of source to reduce number of hardcoded paths in output files
+	rm -rf ${BUILD_DIR}/${KERNEL_SRC_COPY}/${PVE_HEADER_PKG}
+	mkdir -p ${BUILD_DIR}/${KERNEL_SRC_COPY}/${PVE_HEADER_PKG}
+	cp ${KERNEL_SRC}/.config ${BUILD_DIR}/${KERNEL_SRC_COPY}/${PVE_HEADER_PKG}/.config
+	${MAKE} -C ${KERNEL_SRC_COPY} O=${BUILD_DIR}/${KERNEL_SRC_COPY}/${PVE_HEADER_PKG} -j1 syncconfig modules_prepare prepare scripts
+	cd ${KERNEL_SRC_COPY}; cp -a include scripts ${BUILD_DIR}/debian/${PVE_HEADER_PKG}/usr/src/linux-headers-${KVNAME}
+	find ${BUILD_DIR}/${KERNEL_SRC_COPY}/${PVE_HEADER_PKG} -name \*.o.ur-\* -o -name '*.cmd' | xargs rm -f
+	rsync --ignore-existing -r -v -a $(addprefix ${BUILD_DIR}/${KERNEL_SRC_COPY}/${PVE_HEADER_PKG}/,arch include kernel scripts tools) ${BUILD_DIR}/debian/${PVE_HEADER_PKG}/usr/src/linux-headers-${KVNAME}/
+	rm -rf ${BUILD_DIR}/${KERNEL_SRC_COPY}
+	touch $@
+
+.headers_install_mark: .compile_mark .modules_compile_mark .headers_compile_mark
+	cp ${KERNEL_SRC}/include/generated/compile.h debian/${PVE_HEADER_PKG}/usr/src/linux-headers-${KVNAME}/include/generated/compile.h
+	install -m 0644 ${KERNEL_SRC}/Module.symvers debian/${PVE_HEADER_PKG}/usr/src/linux-headers-${KVNAME}
 	mkdir -p debian/${PVE_HEADER_PKG}/lib/modules/${KVNAME}
 	ln -sf /usr/src/linux-headers-${KVNAME} debian/${PVE_HEADER_PKG}/lib/modules/${KVNAME}/build
 	touch $@

-.modules_compile_mark: $(addprefix ${MODULES}/,igb.ko ixgbe.ko e1000e.ko spl.ko zfs.ko)
+.usr_headers_install_mark: PKG_DIR = debian/${PVE_USR_HEADER_PKG}
+.usr_headers_install_mark: OUT_DIR = ${PKG_DIR}/usr
+.usr_headers_install_mark: .config_mark
+	rm -rf '${PKG_DIR}'
+	mkdir -p  '${PKG_DIR}'
+	$(MAKE) -C ${KERNEL_SRC} headers_install ARCH=$(KERNEL_HEADER_ARCH) INSTALL_HDR_PATH='$(CURDIR)'/$(OUT_DIR)
+	rm -rf $(OUT_DIR)/include/drm $(OUT_DIR)/include/scsi
+	find $(OUT_DIR)/include \( -name .install -o -name ..install.cmd \) -execdir rm {} +
+
+# Move include/asm to arch-specific directory
+	mkdir -p $(OUT_DIR)/include/$(DEB_HOST_MULTIARCH)
+	mv $(OUT_DIR)/include/asm $(OUT_DIR)/include/$(DEB_HOST_MULTIARCH)/
+	test ! -d $(OUT_DIR)/include/arch || \
+		mv $(OUT_DIR)/include/arch $(OUT_DIR)/include/$(DEB_HOST_MULTIARCH)/
 	touch $@

-${MODULES}/spl.ko: .compile_mark
-	cd ${MODULES}/${SPLDIR}; ./autogen.sh
-	cd ${MODULES}/${SPLDIR}; ./configure --with-config=kernel --with-linux=${BUILD_DIR}/${KERNEL_SRC} --with-linux-obj=${BUILD_DIR}/${KERNEL_SRC}
-	${MAKE} -C ${MODULES}/${SPLDIR}
-	cp ${MODULES}/${SPLDIR}/module/splat/splat.ko ${MODULES}/
-	cp ${MODULES}/${SPLDIR}/module/spl/spl.ko ${MODULES}/
+.modules_compile_mark: ${MODULES}/zfs.ko
+	touch $@

-${MODULES}/zfs.ko: .compile_mark ${MODULES}/spl.ko
+${MODULES}/zfs.ko: .compile_mark
 	cd ${MODULES}/${ZFSDIR}; ./autogen.sh
-	cd ${MODULES}/${ZFSDIR}; ./configure --with-spl=${BUILD_DIR}/${MODULES}/${SPLDIR} --with-spl-obj=${BUILD_DIR}/${MODULES}/${SPLDIR} --with-config=kernel --with-linux=${BUILD_DIR}/${KERNEL_SRC} --with-linux-obj=${BUILD_DIR}/${KERNEL_SRC}
+	cd ${MODULES}/${ZFSDIR}; ./configure --with-config=kernel --with-linux=${BUILD_DIR}/${KERNEL_SRC} --with-linux-obj=${BUILD_DIR}/${KERNEL_SRC}
 	${MAKE} -C ${MODULES}/${ZFSDIR}
 	cp ${MODULES}/${ZFSDIR}/module/avl/zavl.ko ${MODULES}/
 	cp ${MODULES}/${ZFSDIR}/module/nvpair/znvpair.ko ${MODULES}/
 	cp ${MODULES}/${ZFSDIR}/module/unicode/zunicode.ko ${MODULES}/
 	cp ${MODULES}/${ZFSDIR}/module/zcommon/zcommon.ko ${MODULES}/
-	cp ${MODULES}/${ZFSDIR}/module/zpios/zpios.ko ${MODULES}/
 	cp ${MODULES}/${ZFSDIR}/module/icp/icp.ko ${MODULES}/
 	cp ${MODULES}/${ZFSDIR}/module/zfs/zfs.ko ${MODULES}/
-
-${MODULES}/igb.ko: .compile_mark
-	${MAKE} -C ${MODULES}/${IGBDIR}/src BUILD_KERNEL=${KVNAME} KSRC=${BUILD_DIR}/${KERNEL_SRC}
-	cp ${MODULES}/${IGBDIR}/src/igb.ko ${MODULES}/
-
-${MODULES}/ixgbe.ko: .compile_mark
-	${MAKE} -C ${MODULES}/${IXGBEDIR}/src CFLAGS_EXTRA="-DIXGBE_NO_LRO" BUILD_KERNEL=${KVNAME} KSRC=${BUILD_DIR}/${KERNEL_SRC}
-	cp ${MODULES}/${IXGBEDIR}/src/ixgbe.ko ${MODULES}/
-
-${MODULES}/e1000e.ko: .compile_mark
-	${MAKE} -C ${MODULES}/${E1000EDIR}/src BUILD_KERNEL=${KVNAME} KSRC=${BUILD_DIR}/${KERNEL_SRC}
-	cp ${MODULES}/${E1000EDIR}/src/e1000e.ko ${MODULES}/
+	cp ${MODULES}/${ZFSDIR}/module/lua/zlua.ko ${MODULES}/
+	cp ${MODULES}/${ZFSDIR}/module/spl/spl.ko ${MODULES}/
+	cp ${MODULES}/${ZFSDIR}/module/zstd/zzstd.ko ${MODULES}/

 fwlist-${KVNAME}: .compile_mark .modules_compile_mark
 	debian/scripts/find-firmware.pl debian/${PVE_KERNEL_PKG}/lib/modules/${KVNAME} >fwlist.tmp
@@ -5,8 +5,7 @@ my $abiold = shift;
 my $skipabi = shift;

 # to catch multiple abi-prev-* files being passed in
-die "invalid value for skipabi parameter\n"
-	if (defined($skipabi) && $skipabi !~ /^[01]$/);
+die "invalid value '$skipabi' for skipabi parameter\n" if defined($skipabi) && $skipabi !~ /^[01]$/;

 $abinew =~ /abi-(.*)/;
 my $abistr = $1;
@@ -6,7 +6,7 @@ top=$(pwd)

 if [ "$#" -ne 3 ]; then
    echo "USAGE: $0 repo patchdir ref"
-    echo "\t exports patches from 'repo' to 'patchdir' based on 'ref'"
+    printf "\t exports patches from 'repo' to 'patchdir' based on 'ref'\n"
    exit 1
 fi

@@ -25,10 +25,10 @@ git format-patch \
    --no-cover-letter \
    --zero-commit \
    --no-signature \
-    --output-dir \
-    "${top}/${kernel_patchdir}" \
+    --diff-algorithm=myers \
+    --output-directory="${top}/${kernel_patchdir}" \
    "${base_ref}.."

-git checkout ${base_ref}
+git checkout "${base_ref}"

 cd "${top}"
@@ -8,7 +8,7 @@ die "no directory to scan" if !$dir;

 die "no such directory" if ! -d $dir;

-die "strange directory name" if $dir !~ m|^(.*/)?(4.13.\d+\-\d+\-pve)(/+)?$|;
+warn "\n\nNOTE: strange directory name: $dir\n\n" if $dir !~ m|^(.*/)?(\d+.\d+.\d+\-\d+\-pve)(/+)?$|;

 my $apiver = $2;

@@ -1,37 +0,0 @@
-diff --git a/src/netdev.c b/src/netdev.c
-index 73b0f9a..aef1bc2 100644
--- a/src/netdev.c
-+++ b/src/netdev.c
-@@ -6724,19 +6724,12 @@ static int e1000_change_mtu(struct net_device *netdev, int new_mtu)
- 	int max_frame = new_mtu + VLAN_ETH_HLEN + ETH_FCS_LEN;
- 
- 	/* Jumbo frame support */
-	if ((max_frame > (VLAN_ETH_FRAME_LEN + ETH_FCS_LEN)) &&
-+	if ((new_mtu > ETH_DATA_LEN) &&
- 	    !(adapter->flags & FLAG_HAS_JUMBO_FRAMES)) {
- 		e_err("Jumbo Frames not supported.\n");
- 		return -EINVAL;
- 	}
- 
-	/* Supported frame sizes */
-	if ((new_mtu < (VLAN_ETH_ZLEN + ETH_FCS_LEN)) ||
-	    (max_frame > adapter->max_hw_frame_size)) {
-		e_err("Unsupported MTU setting\n");
-		return -EINVAL;
-	}
-
- 	/* Jumbo frame workaround on 82579 and newer requires CRC be stripped */
- 	if ((adapter->hw.mac.type >= e1000_pch2lan) &&
- 	    !(adapter->flags2 & FLAG2_CRC_STRIPPING) &&
-@@ -8262,6 +8255,11 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
- #endif /* HAVE_NETDEV_VLAN_FEATURES */
- 	}
- 
-+	/* MTU range: 68 - max_hw_frame_size */
-+	netdev->min_mtu = ETH_MIN_MTU;
-+	netdev->max_mtu = adapter->max_hw_frame_size -
-+	                  (VLAN_ETH_HLEN + ETH_FCS_LEN);
-+
- 	if (e1000e_enable_mng_pass_thru(&adapter->hw))
- 		adapter->flags |= FLAG_MNG_PT_ENABLED;
- 
@@ -1,47 +0,0 @@
-diff --git a/src/e1000_defines.h b/src/e1000_defines.h
-index 6de3988..d58e12f 100644
--- a/src/e1000_defines.h
-+++ b/src/e1000_defines.h
-@@ -423,7 +423,8 @@
- #define ETHERNET_IEEE_VLAN_TYPE		0x8100  /* 802.3ac packet */
- 
- #define ETHERNET_FCS_SIZE		4
-#define MAX_JUMBO_FRAME_SIZE		0x3F00
-+#define MAX_JUMBO_FRAME_SIZE		0x2600
-+#define MAX_STD_JUMBO_FRAME_SIZE	9216
- /* The datasheet maximum supported RX size is 9.5KB (9728 bytes) */
- #define MAX_RX_JUMBO_FRAME_SIZE		0x2600
- #define E1000_TX_PTR_GAP		0x1F
-diff --git a/src/igb_main.c b/src/igb_main.c
-index 2dff0f4..bbfe87e 100644
--- a/src/igb_main.c
-+++ b/src/igb_main.c
-@@ -2852,6 +2852,10 @@ static int igb_probe(struct pci_dev *pdev,
- 	if (pci_using_dac)
- 		netdev->features |= NETIF_F_HIGHDMA;
- 
-+	/* MTU range: 68 - 9216 */
-+	netdev->min_mtu = ETH_MIN_MTU;
-+	netdev->max_mtu = MAX_STD_JUMBO_FRAME_SIZE;
-+
- 	adapter->en_mng_pt = e1000_enable_mng_pass_thru(hw);
- #ifdef DEBUG
- 	if (adapter->dmac != IGB_DMAC_DISABLE)
-@@ -5832,17 +5836,6 @@ static int igb_change_mtu(struct net_device *netdev, int new_mtu)
- 	struct pci_dev *pdev = adapter->pdev;
- 	int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN + VLAN_HLEN;
- 
-	if ((new_mtu < 68) || (max_frame > MAX_JUMBO_FRAME_SIZE)) {
-		dev_err(pci_dev_to_dev(pdev), "Invalid MTU setting\n");
-		return -EINVAL;
-	}
-
-#define MAX_STD_JUMBO_FRAME_SIZE 9238
-	if (max_frame > MAX_STD_JUMBO_FRAME_SIZE) {
-		dev_err(pci_dev_to_dev(pdev), "MTU > 9216 not supported.\n");
-		return -EINVAL;
-	}
-
- 	/* adjust max frame to be at least the size of a standard frame */
- 	if (max_frame < (ETH_FRAME_LEN + ETH_FCS_LEN))
- 		max_frame = ETH_FRAME_LEN + ETH_FCS_LEN;
@@ -1,17 +0,0 @@
-diff --git a/src/igb_main.c.orig b/src/igb_main.c
-index 3ee1ec7..c8adf04 100644
--- a/src/igb_main.c.orig
-+++ b/src/igb_main.c
-@@ -1047,8 +1047,10 @@ static void igb_set_interrupt_capability(struct igb_adapter *adapter, bool msix)
- 			for (i = 0; i < numvecs; i++)
- 				adapter->msix_entries[i].entry = i;
- 
-			err = pci_enable_msix(pdev,
-					      adapter->msix_entries, numvecs);
-+			err = pci_enable_msix_range(pdev,
-+						    adapter->msix_entries,
-+						    numvecs,
-+						    numvecs);
- 			if (err == 0)
- 				break;
- 		}
@@ -1,18 +0,0 @@
-diff --git a/src/Makefile.orig b/src/Makefile
-index 8e962f7..50bcdcc 100644
--- a/src/Makefile.orig
-+++ b/src/Makefile
-@@ -123,6 +123,13 @@ ifeq (,$(CC))
-   $(error Compiler not found)
- endif
- 
-+# workaround for GCC6's default PIE
-+ifeq ($(CC),gcc)
-+  PIE_TEST = [ -z "`$(CC) -fno-PIE -no-pie -x c -c /dev/null -o /dev/null 2>&1`" ]
-+  PIE_FLAGS := $(shell $(PIE_TEST) && echo '-fno-PIE -no-pie')
-+  EXTRA_CFLAGS += $(PIE_FLAGS)
-+endif
-+
- # we need to know what platform the driver is being built on
- # some additional features are only built on Intel platforms
- ARCH := $(shell uname -m | sed 's/i.86/i386/')
@@ -15,15 +15,16 @@ Make mkcompile_h use $KBUILD_BUILD_VERSION_TIMESTAMP in preference to
 $KBUILD_BUILD_TIMESTAMP.

 Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
 scripts/mkcompile_h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

 diff --git a/scripts/mkcompile_h b/scripts/mkcompile_h
-index fd8fdb91581d..1e35ac9fc810 100755
+index ca40a5258c87..6ae930a732f0 100755
 --- a/scripts/mkcompile_h
 +++ b/scripts/mkcompile_h
-@@ -37,10 +37,14 @@ else
+@@ -23,10 +23,14 @@ else
 	VERSION=$KBUILD_BUILD_VERSION
 fi
 
@@ -13,15 +13,16 @@ connected ports (for no real reason). To avoid problems with ARP
 we simply use the MAC of the first connected port.

 Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
 net/bridge/br_stp_if.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

 diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
-index 89110319ef0f..5e73fff65f47 100644
+index 75204d36d7f9..1fb5ff73ec1e 100644
 --- a/net/bridge/br_stp_if.c
 +++ b/net/bridge/br_stp_if.c
-@@ -259,10 +259,7 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br)
+@@ -265,10 +265,7 @@ bool br_stp_recalculate_bridge_id(struct net_bridge *br)
 		return false;
 
 	list_for_each_entry(p, &br->port_list, list) {
@@ -1,7 +1,7 @@
 From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
 From: Mark Weiman <mark.weiman@markzz.com>
-Date: Sat, 29 Jul 2017 09:15:32 -0400
-Subject: [PATCH] pci: Enable overrides for missing ACS capabilities (4.12+)
+Date: Wed, 7 Feb 2018 16:04:03 -0500
+Subject: [PATCH] pci: Enable overrides for missing ACS capabilities (4.15)
 MIME-Version: 1.0
 Content-Type: text/plain; charset=UTF-8
 Content-Transfer-Encoding: 8bit
@@ -48,37 +48,38 @@ capability.  Please contact me to have your devices added and save
 your customers the hassle of this boot option.

 Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
- Documentation/admin-guide/kernel-parameters.txt |   9 +++
- drivers/pci/quirks.c                            | 102 ++++++++++++++++++++++++
+ .../admin-guide/kernel-parameters.txt         |   9 ++
+ drivers/pci/quirks.c                          | 102 ++++++++++++++++++
 2 files changed, 111 insertions(+)

 diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
-index ce24cb1e8f46..0cc1d4200c24 100644
+index 364f1d6f4be4..02df36670b1f 100644
 --- a/Documentation/admin-guide/kernel-parameters.txt
 +++ b/Documentation/admin-guide/kernel-parameters.txt
-@@ -2938,6 +2938,15 @@
- 		nomsi		[MSI] If the PCI_MSI kernel config parameter is
- 				enabled, this kernel boot option can be used to
- 				disable the use of MSI interrupts system-wide.
+@@ -4098,6 +4098,15 @@
+ 				Also, it enforces the PCI Local Bus spec
+ 				rule that those bits should be 0 in system reset
+ 				events (useful for kexec/kdump cases).
 +		pci_acs_override =
-+					[PCIE] Override missing PCIe ACS support for:
+				[PCIE] Override missing PCIe ACS support for:
 +				downstream
 +					All downstream ports - full ACS capabilities
-+				multfunction
-+					All multifunction devices - multifunction ACS subset
+				multifunction
+					Add multifunction devices - multifunction ACS subset
 +				id:nnnn:nnnn
-+					Specfic device - full ACS capabilities
+					Specific device - full ACS capabilities
 +					Specified as vid:did (vendor/device ID) in hex
 		noioapicquirk	[APIC] Disable all boot interrupt quirks.
 				Safety option to keep boot IRQs enabled. This
 				should never be necessary.
 diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
-index 9dcd5ed5a05b..8882b8d38d7d 100644
+index acf45f1f7264..7ab01acebf99 100644
 --- a/drivers/pci/quirks.c
 +++ b/drivers/pci/quirks.c
-@@ -3694,6 +3694,107 @@ static int __init pci_apply_final_quirks(void)
- 
+@@ -194,6 +194,106 @@ static int __init pci_apply_final_quirks(void)
+ }
 fs_initcall_sync(pci_apply_final_quirks);
 
 +static bool acs_on_downstream;
@@ -121,7 +122,6 @@ index 9dcd5ed5a05b..8882b8d38d7d 100644
 +				goto next;
 +			}
 +			acs_on_ids[max_acs_id].vendor = val;
-+
 +			p += strcspn(p, ":");
 +			if (*p != ':') {
 +				pr_warn("PCIe ACS invalid ID\n");
@@ -166,30 +166,31 @@ index 9dcd5ed5a05b..8882b8d38d7d 100644
 +				return 1;
 +
 +	switch (pci_pcie_type(dev)) {
-+	case PCI_EXP_TYPE_DOWNSTREAM:
-+	case PCI_EXP_TYPE_ROOT_PORT:
-+		if (acs_on_downstream)
-+			return 1;
-+		break;
-+	case PCI_EXP_TYPE_ENDPOINT:
-+	case PCI_EXP_TYPE_UPSTREAM:
-+	case PCI_EXP_TYPE_LEG_END:
-+	case PCI_EXP_TYPE_RC_END:
-+		if (acs_on_multifunction && dev->multifunction)
-+			return 1;
+		case PCI_EXP_TYPE_DOWNSTREAM:
+		case PCI_EXP_TYPE_ROOT_PORT:
+			if (acs_on_downstream)
+				return 1;
+			break;
+		case PCI_EXP_TYPE_ENDPOINT:
+		case PCI_EXP_TYPE_UPSTREAM:
+		case PCI_EXP_TYPE_LEG_END:
+		case PCI_EXP_TYPE_RC_END:
+			if (acs_on_multifunction && dev->multifunction)
+				return 1;
 +	}
 +
 +	return -ENOTTY;
 +}
 +
 /*
-  * Following are device-specific reset methods which can be used to
-  * reset a single function if other methods (e.g. FLR, PM D0->D3) are
-@@ -4536,6 +4637,7 @@ static const struct pci_dev_acs_enabled {
- 	{ 0x10df, 0x720, pci_quirk_mf_endpoint_acs }, /* Emulex Skyhawk-R */
- 	/* Cavium ThunderX */
- 	{ PCI_VENDOR_ID_CAVIUM, PCI_ANY_ID, pci_quirk_cavium_acs },
+  * Decoding should be disabled for a PCI device during BAR sizing to avoid
+  * conflict. But doing so may cause problems on host bridge and perhaps other
+@@ -4928,6 +5028,8 @@ static const struct pci_dev_acs_enabled {
+ 	{ PCI_VENDOR_ID_CAVIUM, 0xA060, pci_quirk_mf_endpoint_acs },
+ 	/* APM X-Gene */
+ 	{ PCI_VENDOR_ID_AMCC, 0xE004, pci_quirk_xgene_acs },
+	/* Enable overrides for missing ACS capabilities */
 +	{ PCI_ANY_ID, PCI_ANY_ID, pcie_acs_overrides },
- 	{ 0 }
- };
- 
+ 	/* Ampere Computing */
+ 	{ PCI_VENDOR_ID_AMPERE, 0xE005, pci_quirk_xgene_acs },
+ 	{ PCI_VENDOR_ID_AMPERE, 0xE006, pci_quirk_xgene_acs },
@@ -7,15 +7,16 @@ Content-Type: text/plain; charset=UTF-8
 Content-Transfer-Encoding: 8bit

 Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
 ---
 virt/kvm/kvm_main.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

 diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
-index 3b3e54742263..d0085c9d6297 100644
+index 27712d129f61..b609a08f1f52 100644
 --- a/virt/kvm/kvm_main.c
 +++ b/virt/kvm/kvm_main.c
-@@ -77,7 +77,7 @@ module_param(halt_poll_ns, uint, 0644);
+@@ -79,7 +79,7 @@ module_param(halt_poll_ns, uint, 0644);
 EXPORT_SYMBOL_GPL(halt_poll_ns);
 
 /* Default doubles per-vcpu halt_poll_ns. */
@@ -1,63 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Waiman Long <longman@redhat.com>
-Date: Thu, 17 Aug 2017 15:33:09 -0400
-Subject: [PATCH] cgroup: Add mount flag to enable cpuset to use v2 behavior in
- v1 cgroup
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-A new mount option "cpuset_v2_mode" is added to the v1 cgroupfs
-filesystem to enable cpuset controller to use v2 behavior in a v1
-cgroup. This mount option applies only to cpuset controller and have
-no effect on other controllers.
-
-Signed-off-by: Waiman Long <longman@redhat.com>
-Signed-off-by: Tejun Heo <tj@kernel.org>
-(cherry-picked from e1cba4b85daa71b710384d451ff6238d5e4d1ff6)
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- include/linux/cgroup-defs.h | 5 +++++
- kernel/cgroup/cgroup-v1.c   | 6 ++++++
- 2 files changed, 11 insertions(+)
-
-diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
-index 09f4c7df1478..c344e77707a5 100644
--- a/include/linux/cgroup-defs.h
-+++ b/include/linux/cgroup-defs.h
-@@ -74,6 +74,11 @@ enum {
- 	 * aren't writeable from inside the namespace.
- 	 */
- 	CGRP_ROOT_NS_DELEGATE	= (1 << 3),
-+
-+	/*
-+	 * Enable cpuset controller in v1 cgroup to use v2 behavior.
-+	 */
-+	CGRP_ROOT_CPUSET_V2_MODE = (1 << 4),
- };
- 
- /* cftype->flags */
-diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c
-index 7bf4b1533f34..ce7426b875f5 100644
--- a/kernel/cgroup/cgroup-v1.c
-+++ b/kernel/cgroup/cgroup-v1.c
-@@ -846,6 +846,8 @@ static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_roo
- 		seq_puts(seq, ",noprefix");
- 	if (root->flags & CGRP_ROOT_XATTR)
- 		seq_puts(seq, ",xattr");
-+	if (root->flags & CGRP_ROOT_CPUSET_V2_MODE)
-+		seq_puts(seq, ",cpuset_v2_mode");
- 
- 	spin_lock(&release_agent_path_lock);
- 	if (strlen(root->release_agent_path))
-@@ -900,6 +902,10 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
- 			opts->cpuset_clone_children = true;
- 			continue;
- 		}
-+		if (!strcmp(token, "cpuset_v2_mode")) {
-+			opts->flags |= CGRP_ROOT_CPUSET_V2_MODE;
-+			continue;
-+		}
- 		if (!strcmp(token, "xattr")) {
- 			opts->flags |= CGRP_ROOT_XATTR;
- 			continue;
@@ -0,0 +1,24 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Thomas Lamprecht <t.lamprecht@proxmox.com>
+Date: Wed, 7 Oct 2020 17:18:28 +0200
+Subject: [PATCH] net: core: downgrade unregister_netdevice refcount leak from
+ emergency to error
+
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ net/core/dev.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/net/core/dev.c b/net/core/dev.c
+index 887e44dc2f2e..08578ddbb60e 100644
+--- a/net/core/dev.c
+++ b/net/core/dev.c
+@@ -10272,7 +10272,7 @@ static struct net_device *netdev_wait_allrefs_any(struct list_head *list)
+ 		if (time_after(jiffies, warning_time +
+ 			       READ_ONCE(netdev_unregister_timeout_secs) * HZ)) {
+ 			list_for_each_entry(dev, list, todo_list) {
+-				pr_emerg("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
+				pr_err("unregister_netdevice: waiting for %s to become free. Usage count = %d\n",
+ 					 dev->name, netdev_refcnt_read(dev));
+ 				ref_tracker_dir_print(&dev->refcnt_tracker, 10);
+ 			}
@@ -1,138 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Waiman Long <longman@redhat.com>
-Date: Thu, 17 Aug 2017 15:33:10 -0400
-Subject: [PATCH] cpuset: Allow v2 behavior in v1 cgroup
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Cpuset v2 has some useful behaviors that are not present in v1 because
-of backward compatibility concern. One of that is the restoration of
-the original cpu and memory node mask after a hot removal and addition
-event sequence.
-
-This patch makes the cpuset controller to check the
-CGRP_ROOT_CPUSET_V2_MODE flag and use the v2 behavior if it is set.
-
-Signed-off-by: Waiman Long <longman@redhat.com>
-Signed-off-by: Tejun Heo <tj@kernel.org>
-(cherry-picked from b8d1b8ee93df8ffbabbeadd65d39853cfad6d698)
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- kernel/cgroup/cpuset.c | 33 ++++++++++++++++++++-------------
- 1 file changed, 20 insertions(+), 13 deletions(-)
-
-diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
-index e8cb34193433..f76c4bf3d46a 100644
--- a/kernel/cgroup/cpuset.c
-+++ b/kernel/cgroup/cpuset.c
-@@ -300,6 +300,16 @@ static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn);
- static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq);
- 
- /*
-+ * Cgroup v2 behavior is used when on default hierarchy or the
-+ * cgroup_v2_mode flag is set.
-+ */
-+static inline bool is_in_v2_mode(void)
-+{
-+	return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) ||
-+	      (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE);
-+}
-+
-+/*
-  * This is ugly, but preserves the userspace API for existing cpuset
-  * users. If someone tries to mount the "cpuset" filesystem, we
-  * silently switch it to mount "cgroup" instead
-@@ -489,8 +499,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
- 
- 	/* On legacy hiearchy, we must be a subset of our parent cpuset. */
- 	ret = -EACCES;
-	if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
-	    !is_cpuset_subset(trial, par))
-+	if (!is_in_v2_mode() && !is_cpuset_subset(trial, par))
- 		goto out;
- 
- 	/*
-@@ -896,8 +905,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
- 		 * If it becomes empty, inherit the effective mask of the
- 		 * parent, which is guaranteed to have some CPUs.
- 		 */
-		if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
-		    cpumask_empty(new_cpus))
-+		if (is_in_v2_mode() && cpumask_empty(new_cpus))
- 			cpumask_copy(new_cpus, parent->effective_cpus);
- 
- 		/* Skip the whole subtree if the cpumask remains the same. */
-@@ -914,7 +922,7 @@ static void update_cpumasks_hier(struct cpuset *cs, struct cpumask *new_cpus)
- 		cpumask_copy(cp->effective_cpus, new_cpus);
- 		spin_unlock_irq(&callback_lock);
- 
-		WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
-+		WARN_ON(!is_in_v2_mode() &&
- 			!cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
- 
- 		update_tasks_cpumask(cp);
-@@ -1150,8 +1158,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
- 		 * If it becomes empty, inherit the effective mask of the
- 		 * parent, which is guaranteed to have some MEMs.
- 		 */
-		if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
-		    nodes_empty(*new_mems))
-+		if (is_in_v2_mode() && nodes_empty(*new_mems))
- 			*new_mems = parent->effective_mems;
- 
- 		/* Skip the whole subtree if the nodemask remains the same. */
-@@ -1168,7 +1175,7 @@ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems)
- 		cp->effective_mems = *new_mems;
- 		spin_unlock_irq(&callback_lock);
- 
-		WARN_ON(!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
-+		WARN_ON(!is_in_v2_mode() &&
- 			!nodes_equal(cp->mems_allowed, cp->effective_mems));
- 
- 		update_tasks_nodemask(cp);
-@@ -1460,7 +1467,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
- 
- 	/* allow moving tasks into an empty cpuset if on default hierarchy */
- 	ret = -ENOSPC;
-	if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) &&
-+	if (!is_in_v2_mode() &&
- 	    (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed)))
- 		goto out_unlock;
- 
-@@ -1979,7 +1986,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css)
- 	cpuset_inc();
- 
- 	spin_lock_irq(&callback_lock);
-	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
-+	if (is_in_v2_mode()) {
- 		cpumask_copy(cs->effective_cpus, parent->effective_cpus);
- 		cs->effective_mems = parent->effective_mems;
- 	}
-@@ -2056,7 +2063,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
- 	mutex_lock(&cpuset_mutex);
- 	spin_lock_irq(&callback_lock);
- 
-	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys)) {
-+	if (is_in_v2_mode()) {
- 		cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask);
- 		top_cpuset.mems_allowed = node_possible_map;
- 	} else {
-@@ -2250,7 +2257,7 @@ static void cpuset_hotplug_update_tasks(struct cpuset *cs)
- 	cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus);
- 	mems_updated = !nodes_equal(new_mems, cs->effective_mems);
- 
-	if (cgroup_subsys_on_dfl(cpuset_cgrp_subsys))
-+	if (is_in_v2_mode())
- 		hotplug_update_tasks(cs, &new_cpus, &new_mems,
- 				     cpus_updated, mems_updated);
- 	else
-@@ -2288,7 +2295,7 @@ static void cpuset_hotplug_workfn(struct work_struct *work)
- 	static cpumask_t new_cpus;
- 	static nodemask_t new_mems;
- 	bool cpus_updated, mems_updated;
-	bool on_dfl = cgroup_subsys_on_dfl(cpuset_cgrp_subsys);
-+	bool on_dfl = is_in_v2_mode();
- 
- 	mutex_lock(&cpuset_mutex);
- 
@@ -0,0 +1,28 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: =?UTF-8?q?Fabian=20Gr=C3=BCnbichler?= <f.gruenbichler@proxmox.com>
+Date: Thu, 14 Sep 2017 11:09:58 +0200
+Subject: [PATCH] do not generate split BTF type info per default
+
+This reverts commit a8ed1a0607cfa5478ff6009539f44790c4d0956d.
+
+It breaks ZFS sometimes:
+https://github.com/openzfs/zfs/issues/12301#issuecomment-873303739
+
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ lib/Kconfig.debug | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
+index 8c31c98f0bfc..470b78cd0134 100644
+--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
+@@ -365,7 +365,7 @@ config PAHOLE_HAS_BTF_TAG
+ 	  these attributes, so make the config depend on CC_IS_CLANG.
+ 
+ config DEBUG_INFO_BTF_MODULES
+-	def_bool y
+	def_bool n
+ 	depends on DEBUG_INFO_BTF && MODULES && PAHOLE_HAS_SPLIT_BTF
+ 	help
+ 	  Generate compact split BTF type information for kernel modules.
@@ -1,90 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Parav Pandit <parav@mellanox.com>
-Date: Fri, 5 Jan 2018 23:51:12 +0100
-Subject: [PATCH] IB/core: Avoid crash on pkey enforcement failed in received
- MADs
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-commit 89548bcafec7ecfeea58c553f0834b5d575a66eb upstream.
-
-Below kernel crash is observed when Pkey security enforcement fails on
-received MADs. This issue is reported in [1].
-
-ib_free_recv_mad() accesses the rmpp_list, whose initialization is
-needed before accessing it.
-When security enformcent fails on received MADs, MAD processing avoided
-due to security checks failed.
-
-OpenSM[3770]: SM port is down
-kernel: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008
-kernel: IP: ib_free_recv_mad+0x44/0xa0 [ib_core]
-kernel: PGD 0
-kernel: P4D 0
-kernel:
-kernel: Oops: 0002 [#1] SMP
-kernel: CPU: 0 PID: 2833 Comm: kworker/0:1H Tainted: P          IO    4.13.4-1-pve #1
-kernel: Hardware name: Dell       XS23-TY3        /9CMP63, BIOS 1.71 09/17/2013
-kernel: Workqueue: ib-comp-wq ib_cq_poll_work [ib_core]
-kernel: task: ffffa069c6541600 task.stack: ffffb9a729054000
-kernel: RIP: 0010:ib_free_recv_mad+0x44/0xa0 [ib_core]
-kernel: RSP: 0018:ffffb9a729057d38 EFLAGS: 00010286
-kernel: RAX: ffffa069cb138a48 RBX: ffffa069cb138a10 RCX: 0000000000000000
-kernel: RDX: ffffb9a729057d38 RSI: 0000000000000000 RDI: ffffa069cb138a20
-kernel: RBP: ffffb9a729057d60 R08: ffffa072d2d49800 R09: ffffa069cb138ae0
-kernel: R10: ffffa069cb138ae0 R11: ffffa072b3994e00 R12: ffffb9a729057d38
-kernel: R13: ffffa069d1c90000 R14: 0000000000000000 R15: ffffa069d1c90880
-kernel: FS:  0000000000000000(0000) GS:ffffa069dba00000(0000) knlGS:0000000000000000
-kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
-kernel: CR2: 0000000000000008 CR3: 00000011f51f2000 CR4: 00000000000006f0
-kernel: Call Trace:
-kernel:  ib_mad_recv_done+0x5cc/0xb50 [ib_core]
-kernel:  __ib_process_cq+0x5c/0xb0 [ib_core]
-kernel:  ib_cq_poll_work+0x20/0x60 [ib_core]
-kernel:  process_one_work+0x1e9/0x410
-kernel:  worker_thread+0x4b/0x410
-kernel:  kthread+0x109/0x140
-kernel:  ? process_one_work+0x410/0x410
-kernel:  ? kthread_create_on_node+0x70/0x70
-kernel:  ? SyS_exit_group+0x14/0x20
-kernel:  ret_from_fork+0x25/0x30
-kernel: RIP: ib_free_recv_mad+0x44/0xa0 [ib_core] RSP: ffffb9a729057d38
-kernel: CR2: 0000000000000008
-
-[1] : https://www.spinics.net/lists/linux-rdma/msg56190.html
-
-Fixes: 47a2b338fe63 ("IB/core: Enforce security on management datagrams")
-Signed-off-by: Parav Pandit <parav@mellanox.com>
-Reported-by: Chris Blake <chrisrblake93@gmail.com>
-Reviewed-by: Daniel Jurgens <danielj@mellanox.com>
-Reviewed-by: Hal Rosenstock <hal@mellanox.com>
-Signed-off-by: Doug Ledford <dledford@redhat.com>
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- drivers/infiniband/core/mad.c | 3 ++-
- 1 file changed, 2 insertions(+), 1 deletion(-)
-
-diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
-index f8f53bb90837..cb91245e9163 100644
--- a/drivers/infiniband/core/mad.c
-+++ b/drivers/infiniband/core/mad.c
-@@ -1974,14 +1974,15 @@ static void ib_mad_complete_recv(struct ib_mad_agent_private *mad_agent_priv,
- 	unsigned long flags;
- 	int ret;
- 
-+	INIT_LIST_HEAD(&mad_recv_wc->rmpp_list);
- 	ret = ib_mad_enforce_security(mad_agent_priv,
- 				      mad_recv_wc->wc->pkey_index);
- 	if (ret) {
- 		ib_free_recv_mad(mad_recv_wc);
- 		deref_mad_agent(mad_agent_priv);
-+		return;
- 	}
- 
-	INIT_LIST_HEAD(&mad_recv_wc->rmpp_list);
- 	list_add(&mad_recv_wc->recv_buf.list, &mad_recv_wc->rmpp_list);
- 	if (ib_mad_kernel_rmpp_agent(&mad_agent_priv->agent)) {
- 		mad_recv_wc = ib_process_rmpp_recv_wc(mad_agent_priv,
@@ -0,0 +1,31 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Thomas Lamprecht <t.lamprecht@proxmox.com>
+Date: Sat, 12 Mar 2022 16:19:10 +0100
+Subject: [PATCH] Ubuntu: remove leftover reference to ubuntu/hio driver
+
+A single reference to the hio driver was forgotten when it was removed
+recently. While this reference is not a problem for the build itself, it
+breaks the __clean target from 'scripts/Makefile.clean' here, as make
+cannot enter the "ubuntu/hio" folder for cleaning due to ENOENT.
+
+Fixes: 4ea6dd9afa0a0d ("UBUNTU: Remove ubuntu/hio driver")
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ ubuntu/Makefile | 4 ----
+ 1 file changed, 4 deletions(-)
+
+diff --git a/ubuntu/Makefile b/ubuntu/Makefile
+index 27fa95ba242a..3bfc4494c069 100644
+--- a/ubuntu/Makefile
+++ b/ubuntu/Makefile
+@@ -15,10 +15,6 @@
+ ##
+ ##
+ ##
+-obj-$(CONFIG_HIO)             += hio/
+-##
+-##
+-##
+ obj-$(CONFIG_UBUNTU_HOST)      += ubuntu-host/
+ ##
+ ##
@@ -1,44 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Daniel Jurgens <danielj@mellanox.com>
-Date: Mon, 20 Nov 2017 16:47:45 -0600
-Subject: [PATCH] IB/core: Don't enforce PKey security on SMI MADs
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Per the infiniband spec an SMI MAD can have any PKey. Checking the pkey
-on SMI MADs is not necessary, and it seems that some older adapters
-using the mthca driver don't follow the convention of using the default
-PKey, resulting in false denials, or errors querying the PKey cache.
-
-SMI MAD security is still enforced, only agents allowed to manage the
-subnet are able to receive or send SMI MADs.
-
-Reported-by: Chris Blake <chrisrblake93@gmail.com>
-Fixes: 47a2b338fe63("IB/core: Enforce security on management datagrams")
-Signed-off-by: Daniel Jurgens <danielj@mellanox.com>
-Reviewed-by: Parav Pandit <parav@mellanox.com>
-Signed-off-by: Leon Romanovsky <leon@kernel.org>
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- drivers/infiniband/core/security.c | 7 +++++--
- 1 file changed, 5 insertions(+), 2 deletions(-)
-
-diff --git a/drivers/infiniband/core/security.c b/drivers/infiniband/core/security.c
-index 70ad19c4c73e..8f9fd3b757db 100644
--- a/drivers/infiniband/core/security.c
-+++ b/drivers/infiniband/core/security.c
-@@ -692,8 +692,11 @@ int ib_mad_enforce_security(struct ib_mad_agent_private *map, u16 pkey_index)
- {
- 	int ret;
- 
-	if (map->agent.qp->qp_type == IB_QPT_SMI && !map->agent.smp_allowed)
-		return -EACCES;
-+	if (map->agent.qp->qp_type == IB_QPT_SMI) {
-+		if (!map->agent.smp_allowed)
-+			return -EACCES;
-+		return 0;
-+	}
- 
- 	ret = ib_security_pkey_access(map->agent.device,
- 				      map->agent.port_num,
@@ -0,0 +1,53 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Maxim Levitsky <mlevitsk@redhat.com>
+Date: Wed, 3 Aug 2022 18:49:59 +0300
+Subject: [PATCH] bug: introduce ASSERT_STRUCT_OFFSET
+
+ASSERT_STRUCT_OFFSET allows to assert during the build of
+the kernel that a field in a struct have an expected offset.
+
+KVM used to have such macro, but there is almost nothing KVM specific
+in it so move it to build_bug.h, so that it can be used in other
+places in KVM.
+
+Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/kvm/vmx/vmcs12.h | 5 ++---
+ include/linux/build_bug.h | 9 +++++++++
+ 2 files changed, 11 insertions(+), 3 deletions(-)
+
+diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
+index 746129ddd5ae..01936013428b 100644
+--- a/arch/x86/kvm/vmx/vmcs12.h
+++ b/arch/x86/kvm/vmx/vmcs12.h
+@@ -208,9 +208,8 @@ struct __packed vmcs12 {
+ /*
+  * For save/restore compatibility, the vmcs12 field offsets must not change.
+  */
+-#define CHECK_OFFSET(field, loc)				\
+-	BUILD_BUG_ON_MSG(offsetof(struct vmcs12, field) != (loc),	\
+-		"Offset of " #field " in struct vmcs12 has changed.")
+#define CHECK_OFFSET(field, loc) \
+	ASSERT_STRUCT_OFFSET(struct vmcs12, field, loc)
+ 
+ static inline void vmx_check_vmcs12_offsets(void)
+ {
+diff --git a/include/linux/build_bug.h b/include/linux/build_bug.h
+index e3a0be2c90ad..3aa3640f8c18 100644
+--- a/include/linux/build_bug.h
+++ b/include/linux/build_bug.h
+@@ -77,4 +77,13 @@
+ #define static_assert(expr, ...) __static_assert(expr, ##__VA_ARGS__, #expr)
+ #define __static_assert(expr, msg, ...) _Static_assert(expr, msg)
+ 
+
+/*
+ * Compile time check that field has an expected offset
+ */
+#define ASSERT_STRUCT_OFFSET(type, field, expected_offset)	\
+	BUILD_BUG_ON_MSG(offsetof(type, field) != (expected_offset),	\
+		"Offset of " #field " in " #type " has changed.")
+
+
+ #endif	/* _LINUX_BUILD_BUG_H */
@@ -1,53 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Paolo Bonzini <pbonzini@redhat.com>
-Date: Thu, 26 Oct 2017 09:13:27 +0200
-Subject: [PATCH] KVM: SVM: obey guest PAT
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-For many years some users of assigned devices have reported worse
-performance on AMD processors with NPT than on AMD without NPT,
-Intel or bare metal.
-
-The reason turned out to be that SVM is discarding the guest PAT
-setting and uses the default (PA0=PA4=WB, PA1=PA5=WT, PA2=PA6=UC-,
-PA3=UC).  The guest might be using a different setting, and
-especially might want write combining but isn't getting it
-(instead getting slow UC or UC- accesses).
-
-Thanks a lot to geoff@hostfission.com for noticing the relation
-to the g_pat setting.  The patch has been tested also by a bunch
-of people on VFIO users forums.
-
-Fixes: 709ddebf81cb40e3c36c6109a7892e8b93a09464
-Fixes: https://bugzilla.kernel.org/show_bug.cgi?id=196409
-Cc: stable@vger.kernel.org
-Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
-Reviewed-by: David Hildenbrand <david@redhat.com>
-Tested-by: Nick Sarnie <commendsarnex@gmail.com>
-Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
-(cherry picked from commit 15038e14724799b8c205beb5f20f9e54896013c3)
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- arch/x86/kvm/svm.c | 7 +++++++
- 1 file changed, 7 insertions(+)
-
-diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
-index 068084c8e540..da10db3de636 100644
--- a/arch/x86/kvm/svm.c
-+++ b/arch/x86/kvm/svm.c
-@@ -3666,6 +3666,13 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
- 	u32 ecx = msr->index;
- 	u64 data = msr->data;
- 	switch (ecx) {
-+	case MSR_IA32_CR_PAT:
-+		if (!kvm_mtrr_valid(vcpu, MSR_IA32_CR_PAT, data))
-+			return 1;
-+		vcpu->arch.pat = data;
-+		svm->vmcb->save.g_pat = data;
-+		mark_dirty(svm->vmcb, VMCB_NPT);
-+		break;
- 	case MSR_IA32_TSC:
- 		kvm_write_tsc(vcpu, msr);
- 		break;
@@ -0,0 +1,34 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Maxim Levitsky <mlevitsk@redhat.com>
+Date: Wed, 3 Aug 2022 18:50:02 +0300
+Subject: [PATCH] KVM: x86: emulator: update the emulation mode after rsm
+
+This ensures that RIP will be correctly written back,
+because the RSM instruction can switch the CPU mode from
+32 bit (or less) to 64 bit.
+
+This fixes a guest crash in case the #SMI is received
+while the guest runs a code from an address > 32 bit.
+
+Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/kvm/emulate.c | 5 +++++
+ 1 file changed, 5 insertions(+)
+
+diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
+index 533203fc424f..c19e782ecc54 100644
+--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
+@@ -2654,6 +2654,11 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
+ 	if (ret != X86EMUL_CONTINUE)
+ 		goto emulate_shutdown;
+ 
+
+	ret = emulator_recalc_and_set_mode(ctxt);
+	if (ret != X86EMUL_CONTINUE)
+		goto emulate_shutdown;
+
+ 	/*
+ 	 * Note, the ctxt->ops callbacks are responsible for handling side
+ 	 * effects when writing MSRs and CRs, e.g. MMU context resets, CPUID
@@ -0,0 +1,280 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Maxim Levitsky <mlevitsk@redhat.com>
+Date: Wed, 3 Aug 2022 18:50:05 +0300
+Subject: [PATCH] KVM: x86: emulator/smm: add structs for KVM's smram layout
+
+Those structs will be used to read/write the smram state image.
+
+Also document the differences between KVM's SMRAM layout and SMRAM
+layout that is used by real Intel/AMD cpus.
+
+Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/kvm/emulate.c     |   6 +
+ arch/x86/kvm/kvm_emulate.h | 218 +++++++++++++++++++++++++++++++++++++
+ arch/x86/kvm/x86.c         |   1 +
+ 3 files changed, 225 insertions(+)
+
+diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
+index c19e782ecc54..48173cb63f7a 100644
+--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
+@@ -5856,3 +5856,9 @@ bool emulator_can_use_gpa(struct x86_emulate_ctxt *ctxt)
+ 
+ 	return true;
+ }
+
+void  __init kvm_emulator_init(void)
+{
+	__check_smram32_offsets();
+	__check_smram64_offsets();
+}
+diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
+index 8dff25d267b7..0eb13204bbc2 100644
+--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
+@@ -13,6 +13,7 @@
+ #define _ASM_X86_KVM_X86_EMULATE_H
+ 
+ #include <asm/desc_defs.h>
+#include <linux/build_bug.h>
+ #include "fpu.h"
+ 
+ struct x86_emulate_ctxt;
+@@ -481,6 +482,223 @@ enum x86_intercept {
+ 	nr_x86_intercepts
+ };
+ 
+
+/* 32 bit KVM's emulated SMM layout. Loosely based on Intel's layout */
+
+struct kvm_smm_seg_state_32 {
+	u32 flags;
+	u32 limit;
+	u32 base;
+} __packed;
+
+struct kvm_smram_state_32 {
+	u32 reserved1[62];
+	u32 smbase;
+	u32 smm_revision;
+	u32 reserved2[5];
+	u32 cr4; /* CR4 is not present in Intel/AMD SMRAM image */
+	u32 reserved3[5];
+
+	/*
+	 * Segment state is not present/documented in the Intel/AMD SMRAM image
+	 * Instead this area on Intel/AMD contains IO/HLT restart flags.
+	 */
+	struct kvm_smm_seg_state_32 ds;
+	struct kvm_smm_seg_state_32 fs;
+	struct kvm_smm_seg_state_32 gs;
+	struct kvm_smm_seg_state_32 idtr; /* IDTR has only base and limit */
+	struct kvm_smm_seg_state_32 tr;
+	u32 reserved;
+	struct kvm_smm_seg_state_32 gdtr; /* GDTR has only base and limit */
+	struct kvm_smm_seg_state_32 ldtr;
+	struct kvm_smm_seg_state_32 es;
+	struct kvm_smm_seg_state_32 cs;
+	struct kvm_smm_seg_state_32 ss;
+
+	u32 es_sel;
+	u32 cs_sel;
+	u32 ss_sel;
+	u32 ds_sel;
+	u32 fs_sel;
+	u32 gs_sel;
+	u32 ldtr_sel;
+	u32 tr_sel;
+
+	u32 dr7;
+	u32 dr6;
+	u32 gprs[8]; /* GPRS in the "natural" X86 order (EAX/ECX/EDX.../EDI) */
+	u32 eip;
+	u32 eflags;
+	u32 cr3;
+	u32 cr0;
+} __packed;
+
+
+static inline void __check_smram32_offsets(void)
+{
+#define __CHECK_SMRAM32_OFFSET(field, offset) \
+	ASSERT_STRUCT_OFFSET(struct kvm_smram_state_32, field, offset - 0xFE00)
+
+	__CHECK_SMRAM32_OFFSET(reserved1,	0xFE00);
+	__CHECK_SMRAM32_OFFSET(smbase,		0xFEF8);
+	__CHECK_SMRAM32_OFFSET(smm_revision,	0xFEFC);
+	__CHECK_SMRAM32_OFFSET(reserved2,	0xFF00);
+	__CHECK_SMRAM32_OFFSET(cr4,		0xFF14);
+	__CHECK_SMRAM32_OFFSET(reserved3,	0xFF18);
+	__CHECK_SMRAM32_OFFSET(ds,		0xFF2C);
+	__CHECK_SMRAM32_OFFSET(fs,		0xFF38);
+	__CHECK_SMRAM32_OFFSET(gs,		0xFF44);
+	__CHECK_SMRAM32_OFFSET(idtr,		0xFF50);
+	__CHECK_SMRAM32_OFFSET(tr,		0xFF5C);
+	__CHECK_SMRAM32_OFFSET(gdtr,		0xFF6C);
+	__CHECK_SMRAM32_OFFSET(ldtr,		0xFF78);
+	__CHECK_SMRAM32_OFFSET(es,		0xFF84);
+	__CHECK_SMRAM32_OFFSET(cs,		0xFF90);
+	__CHECK_SMRAM32_OFFSET(ss,		0xFF9C);
+	__CHECK_SMRAM32_OFFSET(es_sel,		0xFFA8);
+	__CHECK_SMRAM32_OFFSET(cs_sel,		0xFFAC);
+	__CHECK_SMRAM32_OFFSET(ss_sel,		0xFFB0);
+	__CHECK_SMRAM32_OFFSET(ds_sel,		0xFFB4);
+	__CHECK_SMRAM32_OFFSET(fs_sel,		0xFFB8);
+	__CHECK_SMRAM32_OFFSET(gs_sel,		0xFFBC);
+	__CHECK_SMRAM32_OFFSET(ldtr_sel,	0xFFC0);
+	__CHECK_SMRAM32_OFFSET(tr_sel,		0xFFC4);
+	__CHECK_SMRAM32_OFFSET(dr7,		0xFFC8);
+	__CHECK_SMRAM32_OFFSET(dr6,		0xFFCC);
+	__CHECK_SMRAM32_OFFSET(gprs,		0xFFD0);
+	__CHECK_SMRAM32_OFFSET(eip,		0xFFF0);
+	__CHECK_SMRAM32_OFFSET(eflags,		0xFFF4);
+	__CHECK_SMRAM32_OFFSET(cr3,		0xFFF8);
+	__CHECK_SMRAM32_OFFSET(cr0,		0xFFFC);
+#undef __CHECK_SMRAM32_OFFSET
+}
+
+
+/* 64 bit KVM's emulated SMM layout. Based on AMD64 layout */
+
+struct kvm_smm_seg_state_64 {
+	u16 selector;
+	u16 attributes;
+	u32 limit;
+	u64 base;
+};
+
+struct kvm_smram_state_64 {
+
+	struct kvm_smm_seg_state_64 es;
+	struct kvm_smm_seg_state_64 cs;
+	struct kvm_smm_seg_state_64 ss;
+	struct kvm_smm_seg_state_64 ds;
+	struct kvm_smm_seg_state_64 fs;
+	struct kvm_smm_seg_state_64 gs;
+	struct kvm_smm_seg_state_64 gdtr; /* GDTR has only base and limit*/
+	struct kvm_smm_seg_state_64 ldtr;
+	struct kvm_smm_seg_state_64 idtr; /* IDTR has only base and limit*/
+	struct kvm_smm_seg_state_64 tr;
+
+	/* I/O restart and auto halt restart are not implemented by KVM */
+	u64 io_restart_rip;
+	u64 io_restart_rcx;
+	u64 io_restart_rsi;
+	u64 io_restart_rdi;
+	u32 io_restart_dword;
+	u32 reserved1;
+	u8 io_inst_restart;
+	u8 auto_hlt_restart;
+	u8 reserved2[6];
+
+	u64 efer;
+
+	/*
+	 * Two fields below are implemented on AMD only, to store
+	 * SVM guest vmcb address if the #SMI was received while in the guest mode.
+	 */
+	u64 svm_guest_flag;
+	u64 svm_guest_vmcb_gpa;
+	u64 svm_guest_virtual_int; /* unknown purpose, not implemented */
+
+	u32 reserved3[3];
+	u32 smm_revison;
+	u32 smbase;
+	u32 reserved4[5];
+
+	/* ssp and svm_* fields below are not implemented by KVM */
+	u64 ssp;
+	u64 svm_guest_pat;
+	u64 svm_host_efer;
+	u64 svm_host_cr4;
+	u64 svm_host_cr3;
+	u64 svm_host_cr0;
+
+	u64 cr4;
+	u64 cr3;
+	u64 cr0;
+	u64 dr7;
+	u64 dr6;
+	u64 rflags;
+	u64 rip;
+	u64 gprs[16]; /* GPRS in a reversed "natural" X86 order (R15/R14/../RCX/RAX.) */
+};
+
+
+static inline void __check_smram64_offsets(void)
+{
+#define __CHECK_SMRAM64_OFFSET(field, offset) \
+	ASSERT_STRUCT_OFFSET(struct kvm_smram_state_64, field, offset - 0xFE00)
+
+	__CHECK_SMRAM64_OFFSET(es,			0xFE00);
+	__CHECK_SMRAM64_OFFSET(cs,			0xFE10);
+	__CHECK_SMRAM64_OFFSET(ss,			0xFE20);
+	__CHECK_SMRAM64_OFFSET(ds,			0xFE30);
+	__CHECK_SMRAM64_OFFSET(fs,			0xFE40);
+	__CHECK_SMRAM64_OFFSET(gs,			0xFE50);
+	__CHECK_SMRAM64_OFFSET(gdtr,			0xFE60);
+	__CHECK_SMRAM64_OFFSET(ldtr,			0xFE70);
+	__CHECK_SMRAM64_OFFSET(idtr,			0xFE80);
+	__CHECK_SMRAM64_OFFSET(tr,			0xFE90);
+	__CHECK_SMRAM64_OFFSET(io_restart_rip,		0xFEA0);
+	__CHECK_SMRAM64_OFFSET(io_restart_rcx,		0xFEA8);
+	__CHECK_SMRAM64_OFFSET(io_restart_rsi,		0xFEB0);
+	__CHECK_SMRAM64_OFFSET(io_restart_rdi,		0xFEB8);
+	__CHECK_SMRAM64_OFFSET(io_restart_dword,	0xFEC0);
+	__CHECK_SMRAM64_OFFSET(reserved1,		0xFEC4);
+	__CHECK_SMRAM64_OFFSET(io_inst_restart,		0xFEC8);
+	__CHECK_SMRAM64_OFFSET(auto_hlt_restart,	0xFEC9);
+	__CHECK_SMRAM64_OFFSET(reserved2,		0xFECA);
+	__CHECK_SMRAM64_OFFSET(efer,			0xFED0);
+	__CHECK_SMRAM64_OFFSET(svm_guest_flag,		0xFED8);
+	__CHECK_SMRAM64_OFFSET(svm_guest_vmcb_gpa,	0xFEE0);
+	__CHECK_SMRAM64_OFFSET(svm_guest_virtual_int,	0xFEE8);
+	__CHECK_SMRAM64_OFFSET(reserved3,		0xFEF0);
+	__CHECK_SMRAM64_OFFSET(smm_revison,		0xFEFC);
+	__CHECK_SMRAM64_OFFSET(smbase,			0xFF00);
+	__CHECK_SMRAM64_OFFSET(reserved4,		0xFF04);
+	__CHECK_SMRAM64_OFFSET(ssp,			0xFF18);
+	__CHECK_SMRAM64_OFFSET(svm_guest_pat,		0xFF20);
+	__CHECK_SMRAM64_OFFSET(svm_host_efer,		0xFF28);
+	__CHECK_SMRAM64_OFFSET(svm_host_cr4,		0xFF30);
+	__CHECK_SMRAM64_OFFSET(svm_host_cr3,		0xFF38);
+	__CHECK_SMRAM64_OFFSET(svm_host_cr0,		0xFF40);
+	__CHECK_SMRAM64_OFFSET(cr4,			0xFF48);
+	__CHECK_SMRAM64_OFFSET(cr3,			0xFF50);
+	__CHECK_SMRAM64_OFFSET(cr0,			0xFF58);
+	__CHECK_SMRAM64_OFFSET(dr7,			0xFF60);
+	__CHECK_SMRAM64_OFFSET(dr6,			0xFF68);
+	__CHECK_SMRAM64_OFFSET(rflags,			0xFF70);
+	__CHECK_SMRAM64_OFFSET(rip,			0xFF78);
+	__CHECK_SMRAM64_OFFSET(gprs,			0xFF80);
+#undef __CHECK_SMRAM64_OFFSET
+}
+
+union kvm_smram {
+	struct kvm_smram_state_64 smram64;
+	struct kvm_smram_state_32 smram32;
+	u8 bytes[512];
+};
+
+void  __init kvm_emulator_init(void);
+
+
+ /* Host execution mode. */
+ #if defined(CONFIG_X86_32)
+ #define X86EMUL_MODE_HOST X86EMUL_MODE_PROT32
+diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
+index b3e72a86184e..8e6e85720242 100644
+--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
+@@ -13273,6 +13273,7 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_vmgexit_msr_protocol_exit);
+ static int __init kvm_x86_init(void)
+ {
+ 	kvm_mmu_x86_module_init();
+	kvm_emulator_init();
+ 	return 0;
+ }
+ module_init(kvm_x86_init);
@@ -1,65 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Felix Wilhelm <fwilhelm@google.com>
-Date: Mon, 11 Jun 2018 09:43:44 +0200
-Subject: [PATCH] kvm: nVMX: Enforce cpl=0 for VMX instructions
-
-VMX instructions executed inside a L1 VM will always trigger a VM exit
-even when executed with cpl 3. This means we must perform the
-privilege check in software.
-
-Fixes: 70f3aac964ae("kvm: nVMX: Remove superfluous VMX instruction fault checks")
-Cc: stable@vger.kernel.org
-Signed-off-by: Felix Wilhelm <fwilhelm@google.com>
-Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
---
- arch/x86/kvm/vmx.c | 15 +++++++++++++--
- 1 file changed, 13 insertions(+), 2 deletions(-)
-
-diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
-index 54980817194a..b2d75b59b6e5 100644
--- a/arch/x86/kvm/vmx.c
-+++ b/arch/x86/kvm/vmx.c
-@@ -7180,6 +7180,12 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
- 		return 1;
- 	}
- 
-+	/* CPL=0 must be checked manually. */
-+	if (vmx_get_cpl(vcpu)) {
-+		kvm_queue_exception(vcpu, UD_VECTOR);
-+		return 1;
-+	}
-+
- 	if (vmx->nested.vmxon) {
- 		nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION);
- 		return kvm_skip_emulated_instruction(vcpu);
-@@ -7239,6 +7245,11 @@ static int handle_vmon(struct kvm_vcpu *vcpu)
-  */
- static int nested_vmx_check_permission(struct kvm_vcpu *vcpu)
- {
-+	if (vmx_get_cpl(vcpu)) {
-+		kvm_queue_exception(vcpu, UD_VECTOR);
-+		return 0;
-+	}
-+
- 	if (!to_vmx(vcpu)->nested.vmxon) {
- 		kvm_queue_exception(vcpu, UD_VECTOR);
- 		return 0;
-@@ -7577,7 +7588,7 @@ static int handle_vmread(struct kvm_vcpu *vcpu)
- 		if (get_vmx_mem_address(vcpu, exit_qualification,
- 				vmx_instruction_info, true, &gva))
- 			return 1;
-		/* _system ok, as hardware has verified cpl=0 */
-+		/* _system ok, nested_vmx_check_permission has verified cpl=0 */
- 		kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, gva,
- 			     &field_value, (is_long_mode(vcpu) ? 8 : 4), NULL);
- 	}
-@@ -7720,7 +7731,7 @@ static int handle_vmptrst(struct kvm_vcpu *vcpu)
- 	if (get_vmx_mem_address(vcpu, exit_qualification,
- 			vmx_instruction_info, true, &vmcs_gva))
- 		return 1;
-	/* ok to use *_system, as hardware has verified cpl=0 */
-+	/* *_system ok, nested_vmx_check_permission has verified cpl=0 */
- 	if (kvm_write_guest_virt_system(&vcpu->arch.emulate_ctxt, vmcs_gva,
- 				 (void *)&to_vmx(vcpu)->nested.current_vmptr,
- 				 sizeof(u64), &e)) {
@@ -0,0 +1,214 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Maxim Levitsky <mlevitsk@redhat.com>
+Date: Wed, 3 Aug 2022 18:50:06 +0300
+Subject: [PATCH] KVM: x86: emulator/smm: use smram structs in the common code
+
+Switch from using a raw array to 'union kvm_smram'.
+
+Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/include/asm/kvm_host.h |  5 +++--
+ arch/x86/kvm/emulate.c          | 12 +++++++-----
+ arch/x86/kvm/kvm_emulate.h      |  3 ++-
+ arch/x86/kvm/svm/svm.c          |  8 ++++++--
+ arch/x86/kvm/vmx/vmx.c          |  4 ++--
+ arch/x86/kvm/x86.c              | 16 ++++++++--------
+ 6 files changed, 28 insertions(+), 20 deletions(-)
+
+diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
+index 19c04412f6e1..cff765545738 100644
+--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
+@@ -202,6 +202,7 @@ typedef enum exit_fastpath_completion fastpath_t;
+ 
+ struct x86_emulate_ctxt;
+ struct x86_exception;
+union kvm_smram;
+ enum x86_intercept;
+ enum x86_intercept_stage;
+ 
+@@ -1552,8 +1553,8 @@ struct kvm_x86_ops {
+ 	void (*setup_mce)(struct kvm_vcpu *vcpu);
+ 
+ 	int (*smi_allowed)(struct kvm_vcpu *vcpu, bool for_injection);
+-	int (*enter_smm)(struct kvm_vcpu *vcpu, char *smstate);
+-	int (*leave_smm)(struct kvm_vcpu *vcpu, const char *smstate);
+	int (*enter_smm)(struct kvm_vcpu *vcpu, union kvm_smram *smram);
+	int (*leave_smm)(struct kvm_vcpu *vcpu, const union kvm_smram *smram);
+ 	void (*enable_smi_window)(struct kvm_vcpu *vcpu);
+ 
+ 	int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp);
+diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
+index 48173cb63f7a..66fb9420842c 100644
+--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
+@@ -2582,16 +2582,18 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+ static int em_rsm(struct x86_emulate_ctxt *ctxt)
+ {
+ 	unsigned long cr0, cr4, efer;
+-	char buf[512];
+	const union kvm_smram smram;
+ 	u64 smbase;
+ 	int ret;
+ 
+	BUILD_BUG_ON(sizeof(smram) != 512);
+
+ 	if ((ctxt->ops->get_hflags(ctxt) & X86EMUL_SMM_MASK) == 0)
+ 		return emulate_ud(ctxt);
+ 
+ 	smbase = ctxt->ops->get_smbase(ctxt);
+ 
+-	ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, buf, sizeof(buf));
+	ret = ctxt->ops->read_phys(ctxt, smbase + 0xfe00, (void *)&smram, sizeof(smram));
+ 	if (ret != X86EMUL_CONTINUE)
+ 		return X86EMUL_UNHANDLEABLE;
+ 
+@@ -2641,15 +2643,15 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
+ 	 * state (e.g. enter guest mode) before loading state from the SMM
+ 	 * state-save area.
+ 	 */
+-	if (ctxt->ops->leave_smm(ctxt, buf))
+	if (ctxt->ops->leave_smm(ctxt, &smram))
+ 		goto emulate_shutdown;
+ 
+ #ifdef CONFIG_X86_64
+ 	if (emulator_has_longmode(ctxt))
+-		ret = rsm_load_state_64(ctxt, buf);
+		ret = rsm_load_state_64(ctxt, (const char *)&smram);
+ 	else
+ #endif
+-		ret = rsm_load_state_32(ctxt, buf);
+		ret = rsm_load_state_32(ctxt, (const char *)&smram);
+ 
+ 	if (ret != X86EMUL_CONTINUE)
+ 		goto emulate_shutdown;
+diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
+index 0eb13204bbc2..04ac0cef8b57 100644
+--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
+@@ -19,6 +19,7 @@
+ struct x86_emulate_ctxt;
+ enum x86_intercept;
+ enum x86_intercept_stage;
+union kvm_smram;
+ 
+ struct x86_exception {
+ 	u8 vector;
+@@ -235,7 +236,7 @@ struct x86_emulate_ops {
+ 
+ 	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
+ 	void (*exiting_smm)(struct x86_emulate_ctxt *ctxt);
+-	int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const char *smstate);
+	int (*leave_smm)(struct x86_emulate_ctxt *ctxt, const union kvm_smram *smram);
+ 	void (*triple_fault)(struct x86_emulate_ctxt *ctxt);
+ 	int (*set_xcr)(struct x86_emulate_ctxt *ctxt, u32 index, u64 xcr);
+ };
+diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
+index 92b30b4937fc..f7f58c4cf341 100644
+--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
+@@ -4308,12 +4308,14 @@ static int svm_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
+ 	return 1;
+ }
+ 
+-static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
+ {
+ 	struct vcpu_svm *svm = to_svm(vcpu);
+ 	struct kvm_host_map map_save;
+ 	int ret;
+ 
+	char *smstate = (char *)smram;
+
+ 	if (!is_guest_mode(vcpu))
+ 		return 0;
+ 
+@@ -4355,7 +4357,7 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+ 	return 0;
+ }
+ 
+-static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
+ {
+ 	struct vcpu_svm *svm = to_svm(vcpu);
+ 	struct kvm_host_map map, map_save;
+@@ -4363,6 +4365,8 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+ 	struct vmcb *vmcb12;
+ 	int ret;
+ 
+	const char *smstate = (const char *)smram;
+
+ 	if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ 		return 0;
+ 
+diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
+index eecf8a45446d..017fe8873620 100644
+--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
+@@ -7738,7 +7738,7 @@ static int vmx_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
+ 	return !is_smm(vcpu);
+ }
+ 
+-static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+static int vmx_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
+ {
+ 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+ 
+@@ -7752,7 +7752,7 @@ static int vmx_enter_smm(struct kvm_vcpu *vcpu, char *smstate)
+ 	return 0;
+ }
+ 
+-static int vmx_leave_smm(struct kvm_vcpu *vcpu, const char *smstate)
+static int vmx_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
+ {
+ 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+ 	int ret;
+diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
+index 8e6e85720242..ebd4315080cd 100644
+--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
+@@ -7943,9 +7943,9 @@ static void emulator_exiting_smm(struct x86_emulate_ctxt *ctxt)
+ }
+ 
+ static int emulator_leave_smm(struct x86_emulate_ctxt *ctxt,
+-				  const char *smstate)
+			      const union kvm_smram *smram)
+ {
+-	return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smstate);
+	return static_call(kvm_x86_leave_smm)(emul_to_vcpu(ctxt), smram);
+ }
+ 
+ static void emulator_triple_fault(struct x86_emulate_ctxt *ctxt)
+@@ -9872,25 +9872,25 @@ static void enter_smm(struct kvm_vcpu *vcpu)
+ 	struct kvm_segment cs, ds;
+ 	struct desc_ptr dt;
+ 	unsigned long cr0;
+-	char buf[512];
+	union kvm_smram smram;
+ 
+-	memset(buf, 0, 512);
+	memset(smram.bytes, 0, sizeof(smram.bytes));
+ #ifdef CONFIG_X86_64
+ 	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+-		enter_smm_save_state_64(vcpu, buf);
+		enter_smm_save_state_64(vcpu, (char *)&smram);
+ 	else
+ #endif
+-		enter_smm_save_state_32(vcpu, buf);
+		enter_smm_save_state_32(vcpu, (char *)&smram);
+ 
+ 	/*
+ 	 * Give enter_smm() a chance to make ISA-specific changes to the vCPU
+ 	 * state (e.g. leave guest mode) after we've saved the state into the
+ 	 * SMM state-save area.
+ 	 */
+-	static_call(kvm_x86_enter_smm)(vcpu, buf);
+	static_call(kvm_x86_enter_smm)(vcpu, &smram);
+ 
+ 	kvm_smm_changed(vcpu, true);
+-	kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, buf, sizeof(buf));
+	kvm_vcpu_write_guest(vcpu, vcpu->arch.smbase + 0xfe00, &smram, sizeof(smram));
+ 
+ 	if (static_call(kvm_x86_get_nmi_mask)(vcpu))
+ 		vcpu->arch.hflags |= HF_SMM_INSIDE_NMI_MASK;
@@ -1,30 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Fri, 19 Jan 2018 11:12:37 +0100
-Subject: [PATCH] net: sched: em_nbyte: don't add the data offset twice
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-'ptr' is shifted by the offset and then validated,
-the memcmp should not add it a second time.
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- net/sched/em_nbyte.c | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c
-index df3110d69585..07c10bac06a0 100644
--- a/net/sched/em_nbyte.c
-+++ b/net/sched/em_nbyte.c
-@@ -51,7 +51,7 @@ static int em_nbyte_match(struct sk_buff *skb, struct tcf_ematch *em,
- 	if (!tcf_valid_offset(skb, ptr, nbyte->hdr.len))
- 		return 0;
- 
-	return !memcmp(ptr + nbyte->hdr.off, nbyte->pattern, nbyte->hdr.len);
-+	return !memcmp(ptr, nbyte->pattern, nbyte->hdr.len);
- }
- 
- static struct tcf_ematch_ops em_nbyte_ops = {
@@ -0,0 +1,268 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Maxim Levitsky <mlevitsk@redhat.com>
+Date: Wed, 3 Aug 2022 18:50:07 +0300
+Subject: [PATCH] KVM: x86: emulator/smm: use smram struct for 32 bit smram
+ load/restore
+
+Use kvm_smram_state_32 struct to save/restore 32 bit SMM state
+(used when X86_FEATURE_LM is not present in the guest CPUID).
+
+Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/kvm/emulate.c | 81 +++++++++++++++---------------------------
+ arch/x86/kvm/x86.c     | 75 +++++++++++++++++---------------------
+ 2 files changed, 60 insertions(+), 96 deletions(-)
+
+diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
+index 66fb9420842c..aa60533d9d29 100644
+--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
+@@ -2359,25 +2359,17 @@ static void rsm_set_desc_flags(struct desc_struct *desc, u32 flags)
+ 	desc->type = (flags >>  8) & 15;
+ }
+ 
+-static int rsm_load_seg_32(struct x86_emulate_ctxt *ctxt, const char *smstate,
+static void rsm_load_seg_32(struct x86_emulate_ctxt *ctxt,
+			   const struct kvm_smm_seg_state_32 *state,
+			   u16 selector,
+ 			   int n)
+ {
+ 	struct desc_struct desc;
+-	int offset;
+-	u16 selector;
+-
+-	selector = GET_SMSTATE(u32, smstate, 0x7fa8 + n * 4);
+-
+-	if (n < 3)
+-		offset = 0x7f84 + n * 12;
+-	else
+-		offset = 0x7f2c + (n - 3) * 12;
+ 
+-	set_desc_base(&desc,      GET_SMSTATE(u32, smstate, offset + 8));
+-	set_desc_limit(&desc,     GET_SMSTATE(u32, smstate, offset + 4));
+-	rsm_set_desc_flags(&desc, GET_SMSTATE(u32, smstate, offset));
+	set_desc_base(&desc,      state->base);
+	set_desc_limit(&desc,     state->limit);
+	rsm_set_desc_flags(&desc, state->flags);
+ 	ctxt->ops->set_segment(ctxt, selector, &desc, 0, n);
+-	return X86EMUL_CONTINUE;
+ }
+ 
+ #ifdef CONFIG_X86_64
+@@ -2448,63 +2440,46 @@ static int rsm_enter_protected_mode(struct x86_emulate_ctxt *ctxt,
+ }
+ 
+ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+-			     const char *smstate)
+			     const struct kvm_smram_state_32 *smstate)
+ {
+-	struct desc_struct desc;
+ 	struct desc_ptr dt;
+-	u16 selector;
+-	u32 val, cr0, cr3, cr4;
+ 	int i;
+ 
+-	cr0 =                      GET_SMSTATE(u32, smstate, 0x7ffc);
+-	cr3 =                      GET_SMSTATE(u32, smstate, 0x7ff8);
+-	ctxt->eflags =             GET_SMSTATE(u32, smstate, 0x7ff4) | X86_EFLAGS_FIXED;
+-	ctxt->_eip =               GET_SMSTATE(u32, smstate, 0x7ff0);
+	ctxt->eflags =  smstate->eflags | X86_EFLAGS_FIXED;
+	ctxt->_eip =  smstate->eip;
+ 
+ 	for (i = 0; i < 8; i++)
+-		*reg_write(ctxt, i) = GET_SMSTATE(u32, smstate, 0x7fd0 + i * 4);
+-
+-	val = GET_SMSTATE(u32, smstate, 0x7fcc);
+		*reg_write(ctxt, i) = smstate->gprs[i];
+ 
+-	if (ctxt->ops->set_dr(ctxt, 6, val))
+	if (ctxt->ops->set_dr(ctxt, 6, smstate->dr6))
+ 		return X86EMUL_UNHANDLEABLE;
+-
+-	val = GET_SMSTATE(u32, smstate, 0x7fc8);
+-
+-	if (ctxt->ops->set_dr(ctxt, 7, val))
+	if (ctxt->ops->set_dr(ctxt, 7, smstate->dr7))
+ 		return X86EMUL_UNHANDLEABLE;
+ 
+-	selector =                 GET_SMSTATE(u32, smstate, 0x7fc4);
+-	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f64));
+-	set_desc_limit(&desc,      GET_SMSTATE(u32, smstate, 0x7f60));
+-	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smstate, 0x7f5c));
+-	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_TR);
+	rsm_load_seg_32(ctxt, &smstate->tr, smstate->tr_sel, VCPU_SREG_TR);
+	rsm_load_seg_32(ctxt, &smstate->ldtr, smstate->ldtr_sel, VCPU_SREG_LDTR);
+ 
+-	selector =                 GET_SMSTATE(u32, smstate, 0x7fc0);
+-	set_desc_base(&desc,       GET_SMSTATE(u32, smstate, 0x7f80));
+-	set_desc_limit(&desc,      GET_SMSTATE(u32, smstate, 0x7f7c));
+-	rsm_set_desc_flags(&desc,  GET_SMSTATE(u32, smstate, 0x7f78));
+-	ctxt->ops->set_segment(ctxt, selector, &desc, 0, VCPU_SREG_LDTR);
+ 
+-	dt.address =               GET_SMSTATE(u32, smstate, 0x7f74);
+-	dt.size =                  GET_SMSTATE(u32, smstate, 0x7f70);
+	dt.address =               smstate->gdtr.base;
+	dt.size =                  smstate->gdtr.limit;
+ 	ctxt->ops->set_gdt(ctxt, &dt);
+ 
+-	dt.address =               GET_SMSTATE(u32, smstate, 0x7f58);
+-	dt.size =                  GET_SMSTATE(u32, smstate, 0x7f54);
+	dt.address =               smstate->idtr.base;
+	dt.size =                  smstate->idtr.limit;
+ 	ctxt->ops->set_idt(ctxt, &dt);
+ 
+-	for (i = 0; i < 6; i++) {
+-		int r = rsm_load_seg_32(ctxt, smstate, i);
+-		if (r != X86EMUL_CONTINUE)
+-			return r;
+-	}
+	rsm_load_seg_32(ctxt, &smstate->es, smstate->es_sel, VCPU_SREG_ES);
+	rsm_load_seg_32(ctxt, &smstate->cs, smstate->cs_sel, VCPU_SREG_CS);
+	rsm_load_seg_32(ctxt, &smstate->ss, smstate->ss_sel, VCPU_SREG_SS);
+ 
+-	cr4 = GET_SMSTATE(u32, smstate, 0x7f14);
+	rsm_load_seg_32(ctxt, &smstate->ds, smstate->ds_sel, VCPU_SREG_DS);
+	rsm_load_seg_32(ctxt, &smstate->fs, smstate->fs_sel, VCPU_SREG_FS);
+	rsm_load_seg_32(ctxt, &smstate->gs, smstate->gs_sel, VCPU_SREG_GS);
+ 
+-	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7ef8));
+	ctxt->ops->set_smbase(ctxt, smstate->smbase);
+ 
+-	return rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
+	return rsm_enter_protected_mode(ctxt, smstate->cr0,
+					smstate->cr3, smstate->cr4);
+ }
+ 
+ #ifdef CONFIG_X86_64
+@@ -2651,7 +2626,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
+ 		ret = rsm_load_state_64(ctxt, (const char *)&smram);
+ 	else
+ #endif
+-		ret = rsm_load_state_32(ctxt, (const char *)&smram);
+		ret = rsm_load_state_32(ctxt, &smram.smram32);
+ 
+ 	if (ret != X86EMUL_CONTINUE)
+ 		goto emulate_shutdown;
+diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
+index ebd4315080cd..87c8021e542c 100644
+--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
+@@ -9726,22 +9726,18 @@ static u32 enter_smm_get_segment_flags(struct kvm_segment *seg)
+ 	return flags;
+ }
+ 
+-static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu, char *buf, int n)
+static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu,
+					 struct kvm_smm_seg_state_32 *state,
+					 u32 *selector,
+					 int n)
+ {
+ 	struct kvm_segment seg;
+-	int offset;
+ 
+ 	kvm_get_segment(vcpu, &seg, n);
+-	put_smstate(u32, buf, 0x7fa8 + n * 4, seg.selector);
+-
+-	if (n < 3)
+-		offset = 0x7f84 + n * 12;
+-	else
+-		offset = 0x7f2c + (n - 3) * 12;
+-
+-	put_smstate(u32, buf, offset + 8, seg.base);
+-	put_smstate(u32, buf, offset + 4, seg.limit);
+-	put_smstate(u32, buf, offset, enter_smm_get_segment_flags(&seg));
+	*selector = seg.selector;
+	state->base = seg.base;
+	state->limit = seg.limit;
+	state->flags = enter_smm_get_segment_flags(&seg);
+ }
+ 
+ #ifdef CONFIG_X86_64
+@@ -9762,54 +9758,47 @@ static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
+ }
+ #endif
+ 
+-static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, char *buf)
+static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, struct kvm_smram_state_32 *smram)
+ {
+ 	struct desc_ptr dt;
+-	struct kvm_segment seg;
+ 	unsigned long val;
+ 	int i;
+ 
+-	put_smstate(u32, buf, 0x7ffc, kvm_read_cr0(vcpu));
+-	put_smstate(u32, buf, 0x7ff8, kvm_read_cr3(vcpu));
+-	put_smstate(u32, buf, 0x7ff4, kvm_get_rflags(vcpu));
+-	put_smstate(u32, buf, 0x7ff0, kvm_rip_read(vcpu));
+	smram->cr0     = kvm_read_cr0(vcpu);
+	smram->cr3     = kvm_read_cr3(vcpu);
+	smram->eflags  = kvm_get_rflags(vcpu);
+	smram->eip     = kvm_rip_read(vcpu);
+ 
+ 	for (i = 0; i < 8; i++)
+-		put_smstate(u32, buf, 0x7fd0 + i * 4, kvm_register_read_raw(vcpu, i));
+		smram->gprs[i] = kvm_register_read_raw(vcpu, i);
+ 
+ 	kvm_get_dr(vcpu, 6, &val);
+-	put_smstate(u32, buf, 0x7fcc, (u32)val);
+	smram->dr6     = (u32)val;
+ 	kvm_get_dr(vcpu, 7, &val);
+-	put_smstate(u32, buf, 0x7fc8, (u32)val);
+	smram->dr7     = (u32)val;
+ 
+-	kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
+-	put_smstate(u32, buf, 0x7fc4, seg.selector);
+-	put_smstate(u32, buf, 0x7f64, seg.base);
+-	put_smstate(u32, buf, 0x7f60, seg.limit);
+-	put_smstate(u32, buf, 0x7f5c, enter_smm_get_segment_flags(&seg));
+-
+-	kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
+-	put_smstate(u32, buf, 0x7fc0, seg.selector);
+-	put_smstate(u32, buf, 0x7f80, seg.base);
+-	put_smstate(u32, buf, 0x7f7c, seg.limit);
+-	put_smstate(u32, buf, 0x7f78, enter_smm_get_segment_flags(&seg));
+	enter_smm_save_seg_32(vcpu, &smram->tr, &smram->tr_sel, VCPU_SREG_TR);
+	enter_smm_save_seg_32(vcpu, &smram->ldtr, &smram->ldtr_sel, VCPU_SREG_LDTR);
+ 
+ 	static_call(kvm_x86_get_gdt)(vcpu, &dt);
+-	put_smstate(u32, buf, 0x7f74, dt.address);
+-	put_smstate(u32, buf, 0x7f70, dt.size);
+	smram->gdtr.base = dt.address;
+	smram->gdtr.limit = dt.size;
+ 
+ 	static_call(kvm_x86_get_idt)(vcpu, &dt);
+-	put_smstate(u32, buf, 0x7f58, dt.address);
+-	put_smstate(u32, buf, 0x7f54, dt.size);
+	smram->idtr.base = dt.address;
+	smram->idtr.limit = dt.size;
+ 
+-	for (i = 0; i < 6; i++)
+-		enter_smm_save_seg_32(vcpu, buf, i);
+	enter_smm_save_seg_32(vcpu, &smram->es, &smram->es_sel, VCPU_SREG_ES);
+	enter_smm_save_seg_32(vcpu, &smram->cs, &smram->cs_sel, VCPU_SREG_CS);
+	enter_smm_save_seg_32(vcpu, &smram->ss, &smram->ss_sel, VCPU_SREG_SS);
+ 
+-	put_smstate(u32, buf, 0x7f14, kvm_read_cr4(vcpu));
+	enter_smm_save_seg_32(vcpu, &smram->ds, &smram->ds_sel, VCPU_SREG_DS);
+	enter_smm_save_seg_32(vcpu, &smram->fs, &smram->fs_sel, VCPU_SREG_FS);
+	enter_smm_save_seg_32(vcpu, &smram->gs, &smram->gs_sel, VCPU_SREG_GS);
+ 
+-	/* revision id */
+-	put_smstate(u32, buf, 0x7efc, 0x00020000);
+-	put_smstate(u32, buf, 0x7ef8, vcpu->arch.smbase);
+	smram->cr4 = kvm_read_cr4(vcpu);
+	smram->smm_revision = 0x00020000;
+	smram->smbase = vcpu->arch.smbase;
+ }
+ 
+ #ifdef CONFIG_X86_64
+@@ -9880,7 +9869,7 @@ static void enter_smm(struct kvm_vcpu *vcpu)
+ 		enter_smm_save_state_64(vcpu, (char *)&smram);
+ 	else
+ #endif
+-		enter_smm_save_state_32(vcpu, (char *)&smram);
+		enter_smm_save_state_32(vcpu, &smram.smram32);
+ 
+ 	/*
+ 	 * Give enter_smm() a chance to make ISA-specific changes to the vCPU
@@ -1,31 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Fri, 19 Jan 2018 11:12:38 +0100
-Subject: [PATCH] net: sched: fix TCF_LAYER_LINK case in tcf_get_base_ptr
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-TCF_LAYER_LINK and TCF_LAYER_NETWORK returned the same pointer as
-skb->data points to the network header.
-Use skb_mac_header instead.
-
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- include/net/pkt_cls.h | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h
-index 537d0a0ad4c4..4450961b1554 100644
--- a/include/net/pkt_cls.h
-+++ b/include/net/pkt_cls.h
-@@ -395,7 +395,7 @@ static inline unsigned char * tcf_get_base_ptr(struct sk_buff *skb, int layer)
- {
- 	switch (layer) {
- 		case TCF_LAYER_LINK:
-			return skb->data;
-+			return skb_mac_header(skb);
- 		case TCF_LAYER_NETWORK:
- 			return skb_network_header(skb);
- 		case TCF_LAYER_TRANSPORT:
@@ -1,46 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Andrew Honig <ahonig@google.com>
-Date: Wed, 10 Jan 2018 10:12:03 -0800
-Subject: [PATCH] KVM: x86: Add memory barrier on vmcs field lookup
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-commit 75f139aaf896d6fdeec2e468ddfa4b2fe469bf40 upstream.
-
-This adds a memory barrier when performing a lookup into
-the vmcs_field_to_offset_table.  This is related to
-CVE-2017-5753.
-
-Signed-off-by: Andrew Honig <ahonig@google.com>
-Reviewed-by: Jim Mattson <jmattson@google.com>
-Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
-Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- arch/x86/kvm/vmx.c | 12 ++++++++++--
- 1 file changed, 10 insertions(+), 2 deletions(-)
-
-diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
-index b2d75b59b6e5..a393186d14b1 100644
--- a/arch/x86/kvm/vmx.c
-+++ b/arch/x86/kvm/vmx.c
-@@ -883,8 +883,16 @@ static inline short vmcs_field_to_offset(unsigned long field)
- {
- 	BUILD_BUG_ON(ARRAY_SIZE(vmcs_field_to_offset_table) > SHRT_MAX);
- 
-	if (field >= ARRAY_SIZE(vmcs_field_to_offset_table) ||
-	    vmcs_field_to_offset_table[field] == 0)
-+	if (field >= ARRAY_SIZE(vmcs_field_to_offset_table))
-+		return -ENOENT;
-+
-+	/*
-+	 * FIXME: Mitigation for CVE-2017-5753.  To be replaced with a
-+	 * generic mechanism.
-+	 */
-+	asm("lfence");
-+
-+	if (vmcs_field_to_offset_table[field] == 0)
- 		return -ENOENT;
- 
- 	return vmcs_field_to_offset_table[field];
@@ -0,0 +1,279 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Maxim Levitsky <mlevitsk@redhat.com>
+Date: Wed, 3 Aug 2022 18:50:08 +0300
+Subject: [PATCH] KVM: x86: emulator/smm: use smram struct for 64 bit smram
+ load/restore
+
+Use kvm_smram_state_64 struct to save/restore the 64 bit SMM state
+(used when X86_FEATURE_LM is present in the guest CPUID,
+regardless of 32-bitness of the guest).
+
+Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/kvm/emulate.c | 88 ++++++++++++++----------------------------
+ arch/x86/kvm/x86.c     | 75 ++++++++++++++++-------------------
+ 2 files changed, 62 insertions(+), 101 deletions(-)
+
+diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
+index aa60533d9d29..5480b23112e3 100644
+--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
+@@ -2373,24 +2373,16 @@ static void rsm_load_seg_32(struct x86_emulate_ctxt *ctxt,
+ }
+ 
+ #ifdef CONFIG_X86_64
+-static int rsm_load_seg_64(struct x86_emulate_ctxt *ctxt, const char *smstate,
+-			   int n)
+static void rsm_load_seg_64(struct x86_emulate_ctxt *ctxt,
+			    const struct kvm_smm_seg_state_64 *state,
+			    int n)
+ {
+ 	struct desc_struct desc;
+-	int offset;
+-	u16 selector;
+-	u32 base3;
+-
+-	offset = 0x7e00 + n * 16;
+-
+-	selector =                GET_SMSTATE(u16, smstate, offset);
+-	rsm_set_desc_flags(&desc, GET_SMSTATE(u16, smstate, offset + 2) << 8);
+-	set_desc_limit(&desc,     GET_SMSTATE(u32, smstate, offset + 4));
+-	set_desc_base(&desc,      GET_SMSTATE(u32, smstate, offset + 8));
+-	base3 =                   GET_SMSTATE(u32, smstate, offset + 12);
+ 
+-	ctxt->ops->set_segment(ctxt, selector, &desc, base3, n);
+-	return X86EMUL_CONTINUE;
+	rsm_set_desc_flags(&desc, state->attributes << 8);
+	set_desc_limit(&desc,     state->limit);
+	set_desc_base(&desc,      (u32)state->base);
+	ctxt->ops->set_segment(ctxt, state->selector, &desc, state->base >> 32, n);
+ }
+ #endif
+ 
+@@ -2484,71 +2476,49 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+ 
+ #ifdef CONFIG_X86_64
+ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+-			     const char *smstate)
+			     const struct kvm_smram_state_64 *smstate)
+ {
+-	struct desc_struct desc;
+ 	struct desc_ptr dt;
+-	u64 val, cr0, cr3, cr4;
+-	u32 base3;
+-	u16 selector;
+ 	int i, r;
+ 
+ 	for (i = 0; i < 16; i++)
+-		*reg_write(ctxt, i) = GET_SMSTATE(u64, smstate, 0x7ff8 - i * 8);
+		*reg_write(ctxt, i) = smstate->gprs[15 - i];
+ 
+-	ctxt->_eip   = GET_SMSTATE(u64, smstate, 0x7f78);
+-	ctxt->eflags = GET_SMSTATE(u32, smstate, 0x7f70) | X86_EFLAGS_FIXED;
+	ctxt->_eip   = smstate->rip;
+	ctxt->eflags = smstate->rflags | X86_EFLAGS_FIXED;
+ 
+-	val = GET_SMSTATE(u64, smstate, 0x7f68);
+-
+-	if (ctxt->ops->set_dr(ctxt, 6, val))
+	if (ctxt->ops->set_dr(ctxt, 6, smstate->dr6))
+ 		return X86EMUL_UNHANDLEABLE;
+-
+-	val = GET_SMSTATE(u64, smstate, 0x7f60);
+-
+-	if (ctxt->ops->set_dr(ctxt, 7, val))
+	if (ctxt->ops->set_dr(ctxt, 7, smstate->dr7))
+ 		return X86EMUL_UNHANDLEABLE;
+ 
+-	cr0 =                       GET_SMSTATE(u64, smstate, 0x7f58);
+-	cr3 =                       GET_SMSTATE(u64, smstate, 0x7f50);
+-	cr4 =                       GET_SMSTATE(u64, smstate, 0x7f48);
+-	ctxt->ops->set_smbase(ctxt, GET_SMSTATE(u32, smstate, 0x7f00));
+-	val =                       GET_SMSTATE(u64, smstate, 0x7ed0);
+	ctxt->ops->set_smbase(ctxt, smstate->smbase);
+ 
+-	if (ctxt->ops->set_msr(ctxt, MSR_EFER, val & ~EFER_LMA))
+	if (ctxt->ops->set_msr(ctxt, MSR_EFER, smstate->efer & ~EFER_LMA))
+ 		return X86EMUL_UNHANDLEABLE;
+ 
+-	selector =                  GET_SMSTATE(u32, smstate, 0x7e90);
+-	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e92) << 8);
+-	set_desc_limit(&desc,       GET_SMSTATE(u32, smstate, 0x7e94));
+-	set_desc_base(&desc,        GET_SMSTATE(u32, smstate, 0x7e98));
+-	base3 =                     GET_SMSTATE(u32, smstate, 0x7e9c);
+-	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_TR);
+	rsm_load_seg_64(ctxt, &smstate->tr, VCPU_SREG_TR);
+ 
+-	dt.size =                   GET_SMSTATE(u32, smstate, 0x7e84);
+-	dt.address =                GET_SMSTATE(u64, smstate, 0x7e88);
+	dt.size =                   smstate->idtr.limit;
+	dt.address =                smstate->idtr.base;
+ 	ctxt->ops->set_idt(ctxt, &dt);
+ 
+-	selector =                  GET_SMSTATE(u32, smstate, 0x7e70);
+-	rsm_set_desc_flags(&desc,   GET_SMSTATE(u32, smstate, 0x7e72) << 8);
+-	set_desc_limit(&desc,       GET_SMSTATE(u32, smstate, 0x7e74));
+-	set_desc_base(&desc,        GET_SMSTATE(u32, smstate, 0x7e78));
+-	base3 =                     GET_SMSTATE(u32, smstate, 0x7e7c);
+-	ctxt->ops->set_segment(ctxt, selector, &desc, base3, VCPU_SREG_LDTR);
+	rsm_load_seg_64(ctxt, &smstate->ldtr, VCPU_SREG_LDTR);
+ 
+-	dt.size =                   GET_SMSTATE(u32, smstate, 0x7e64);
+-	dt.address =                GET_SMSTATE(u64, smstate, 0x7e68);
+	dt.size =                   smstate->gdtr.limit;
+	dt.address =                smstate->gdtr.base;
+ 	ctxt->ops->set_gdt(ctxt, &dt);
+ 
+-	r = rsm_enter_protected_mode(ctxt, cr0, cr3, cr4);
+	r = rsm_enter_protected_mode(ctxt, smstate->cr0, smstate->cr3, smstate->cr4);
+ 	if (r != X86EMUL_CONTINUE)
+ 		return r;
+ 
+-	for (i = 0; i < 6; i++) {
+-		r = rsm_load_seg_64(ctxt, smstate, i);
+-		if (r != X86EMUL_CONTINUE)
+-			return r;
+-	}
+	rsm_load_seg_64(ctxt, &smstate->es, VCPU_SREG_ES);
+	rsm_load_seg_64(ctxt, &smstate->cs, VCPU_SREG_CS);
+	rsm_load_seg_64(ctxt, &smstate->ss, VCPU_SREG_SS);
+	rsm_load_seg_64(ctxt, &smstate->ds, VCPU_SREG_DS);
+	rsm_load_seg_64(ctxt, &smstate->fs, VCPU_SREG_FS);
+	rsm_load_seg_64(ctxt, &smstate->gs, VCPU_SREG_GS);
+ 
+ 	return X86EMUL_CONTINUE;
+ }
+@@ -2623,7 +2593,7 @@ static int em_rsm(struct x86_emulate_ctxt *ctxt)
+ 
+ #ifdef CONFIG_X86_64
+ 	if (emulator_has_longmode(ctxt))
+-		ret = rsm_load_state_64(ctxt, (const char *)&smram);
+		ret = rsm_load_state_64(ctxt, &smram.smram64);
+ 	else
+ #endif
+ 		ret = rsm_load_state_32(ctxt, &smram.smram32);
+diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
+index 87c8021e542c..ada063ab8ae9 100644
+--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
+@@ -9741,20 +9741,17 @@ static void enter_smm_save_seg_32(struct kvm_vcpu *vcpu,
+ }
+ 
+ #ifdef CONFIG_X86_64
+-static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu, char *buf, int n)
+static void enter_smm_save_seg_64(struct kvm_vcpu *vcpu,
+				  struct kvm_smm_seg_state_64 *state,
+				  int n)
+ {
+ 	struct kvm_segment seg;
+-	int offset;
+-	u16 flags;
+ 
+ 	kvm_get_segment(vcpu, &seg, n);
+-	offset = 0x7e00 + n * 16;
+-
+-	flags = enter_smm_get_segment_flags(&seg) >> 8;
+-	put_smstate(u16, buf, offset, seg.selector);
+-	put_smstate(u16, buf, offset + 2, flags);
+-	put_smstate(u32, buf, offset + 4, seg.limit);
+-	put_smstate(u64, buf, offset + 8, seg.base);
+	state->selector = seg.selector;
+	state->attributes = enter_smm_get_segment_flags(&seg) >> 8;
+	state->limit = seg.limit;
+	state->base = seg.base;
+ }
+ #endif
+ 
+@@ -9802,57 +9799,51 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, struct kvm_smram_stat
+ }
+ 
+ #ifdef CONFIG_X86_64
+-static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, char *buf)
+static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, struct kvm_smram_state_64 *smram)
+ {
+ 	struct desc_ptr dt;
+-	struct kvm_segment seg;
+ 	unsigned long val;
+ 	int i;
+ 
+ 	for (i = 0; i < 16; i++)
+-		put_smstate(u64, buf, 0x7ff8 - i * 8, kvm_register_read_raw(vcpu, i));
+		smram->gprs[15 - i] = kvm_register_read_raw(vcpu, i);
+
+	smram->rip    = kvm_rip_read(vcpu);
+	smram->rflags = kvm_get_rflags(vcpu);
+ 
+-	put_smstate(u64, buf, 0x7f78, kvm_rip_read(vcpu));
+-	put_smstate(u32, buf, 0x7f70, kvm_get_rflags(vcpu));
+ 
+ 	kvm_get_dr(vcpu, 6, &val);
+-	put_smstate(u64, buf, 0x7f68, val);
+	smram->dr6 = val;
+ 	kvm_get_dr(vcpu, 7, &val);
+-	put_smstate(u64, buf, 0x7f60, val);
+-
+-	put_smstate(u64, buf, 0x7f58, kvm_read_cr0(vcpu));
+-	put_smstate(u64, buf, 0x7f50, kvm_read_cr3(vcpu));
+-	put_smstate(u64, buf, 0x7f48, kvm_read_cr4(vcpu));
+	smram->dr7 = val;
+ 
+-	put_smstate(u32, buf, 0x7f00, vcpu->arch.smbase);
+	smram->cr0 = kvm_read_cr0(vcpu);
+	smram->cr3 = kvm_read_cr3(vcpu);
+	smram->cr4 = kvm_read_cr4(vcpu);
+ 
+-	/* revision id */
+-	put_smstate(u32, buf, 0x7efc, 0x00020064);
+	smram->smbase = vcpu->arch.smbase;
+	smram->smm_revison = 0x00020064;
+ 
+-	put_smstate(u64, buf, 0x7ed0, vcpu->arch.efer);
+	smram->efer = vcpu->arch.efer;
+ 
+-	kvm_get_segment(vcpu, &seg, VCPU_SREG_TR);
+-	put_smstate(u16, buf, 0x7e90, seg.selector);
+-	put_smstate(u16, buf, 0x7e92, enter_smm_get_segment_flags(&seg) >> 8);
+-	put_smstate(u32, buf, 0x7e94, seg.limit);
+-	put_smstate(u64, buf, 0x7e98, seg.base);
+	enter_smm_save_seg_64(vcpu, &smram->tr, VCPU_SREG_TR);
+ 
+ 	static_call(kvm_x86_get_idt)(vcpu, &dt);
+-	put_smstate(u32, buf, 0x7e84, dt.size);
+-	put_smstate(u64, buf, 0x7e88, dt.address);
+	smram->idtr.limit = dt.size;
+	smram->idtr.base = dt.address;
+ 
+-	kvm_get_segment(vcpu, &seg, VCPU_SREG_LDTR);
+-	put_smstate(u16, buf, 0x7e70, seg.selector);
+-	put_smstate(u16, buf, 0x7e72, enter_smm_get_segment_flags(&seg) >> 8);
+-	put_smstate(u32, buf, 0x7e74, seg.limit);
+-	put_smstate(u64, buf, 0x7e78, seg.base);
+	enter_smm_save_seg_64(vcpu, &smram->ldtr, VCPU_SREG_LDTR);
+ 
+ 	static_call(kvm_x86_get_gdt)(vcpu, &dt);
+-	put_smstate(u32, buf, 0x7e64, dt.size);
+-	put_smstate(u64, buf, 0x7e68, dt.address);
+	smram->gdtr.limit = dt.size;
+	smram->gdtr.base = dt.address;
+ 
+-	for (i = 0; i < 6; i++)
+-		enter_smm_save_seg_64(vcpu, buf, i);
+	enter_smm_save_seg_64(vcpu, &smram->es, VCPU_SREG_ES);
+	enter_smm_save_seg_64(vcpu, &smram->cs, VCPU_SREG_CS);
+	enter_smm_save_seg_64(vcpu, &smram->ss, VCPU_SREG_SS);
+	enter_smm_save_seg_64(vcpu, &smram->ds, VCPU_SREG_DS);
+	enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS);
+	enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS);
+ }
+ #endif
+ 
+@@ -9866,7 +9857,7 @@ static void enter_smm(struct kvm_vcpu *vcpu)
+ 	memset(smram.bytes, 0, sizeof(smram.bytes));
+ #ifdef CONFIG_X86_64
+ 	if (guest_cpuid_has(vcpu, X86_FEATURE_LM))
+-		enter_smm_save_state_64(vcpu, (char *)&smram);
+		enter_smm_save_state_64(vcpu, &smram.smram64);
+ 	else
+ #endif
+ 		enter_smm_save_state_32(vcpu, &smram.smram32);
@@ -1,34 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Gustavo A. R. Silva" <garsilva@embeddedor.com>
-Date: Mon, 16 Oct 2017 12:40:29 -0500
-Subject: [PATCH] EDAC, sb_edac: Fix missing break in switch
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Add missing break statement in order to prevent the code from falling
-through.
-
-Signed-off-by: Gustavo A. R. Silva <garsilva@embeddedor.com>
-Cc: Qiuxu Zhuo <qiuxu.zhuo@intel.com>
-Cc: linux-edac <linux-edac@vger.kernel.org>
-Link: http://lkml.kernel.org/r/20171016174029.GA19757@embeddedor.com
-Signed-off-by: Borislav Petkov <bp@suse.de>
-(cherry picked from commit a8e9b186f153a44690ad0363a56716e7077ad28c)
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- drivers/edac/sb_edac.c | 1 +
- 1 file changed, 1 insertion(+)
-
-diff --git a/drivers/edac/sb_edac.c b/drivers/edac/sb_edac.c
-index 5c3e707ff3fc..59af590b660c 100644
--- a/drivers/edac/sb_edac.c
-+++ b/drivers/edac/sb_edac.c
-@@ -2454,6 +2454,7 @@ static int ibridge_mci_bind_devs(struct mem_ctl_info *mci,
- 		case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_TA:
- 		case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_TA:
- 			pvt->pci_ta = pdev;
-+			break;
- 		case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA0_RAS:
- 		case PCI_DEVICE_ID_INTEL_IBRIDGE_IMC_HA1_RAS:
- 			pvt->pci_ras = pdev;
@@ -0,0 +1,98 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Maxim Levitsky <mlevitsk@redhat.com>
+Date: Wed, 3 Aug 2022 18:50:09 +0300
+Subject: [PATCH] KVM: x86: SVM: use smram structs
+
+This removes the last user of put_smstate/GET_SMSTATE so
+remove these functions as well.
+
+Also add a sanity check that we don't attempt to enter the SMM
+on non long mode capable guest CPU with a running nested guest.
+
+Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/include/asm/kvm_host.h |  6 ------
+ arch/x86/kvm/svm/svm.c          | 21 ++++++---------------
+ 2 files changed, 6 insertions(+), 21 deletions(-)
+
+diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
+index cff765545738..143cd0b5d593 100644
+--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
+@@ -2044,12 +2044,6 @@ static inline int kvm_cpu_get_apicid(int mps_cpu)
+ #endif
+ }
+ 
+-#define put_smstate(type, buf, offset, val)                      \
+-	*(type *)((buf) + (offset) - 0x7e00) = val
+-
+-#define GET_SMSTATE(type, buf, offset)		\
+-	(*(type *)((buf) + (offset) - 0x7e00))
+-
+ int kvm_cpu_dirty_log_size(void);
+ 
+ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
+diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
+index f7f58c4cf341..20f90c596d6a 100644
+--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
+@@ -4314,15 +4314,11 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
+ 	struct kvm_host_map map_save;
+ 	int ret;
+ 
+-	char *smstate = (char *)smram;
+-
+ 	if (!is_guest_mode(vcpu))
+ 		return 0;
+ 
+-	/* FED8h - SVM Guest */
+-	put_smstate(u64, smstate, 0x7ed8, 1);
+-	/* FEE0h - SVM Guest VMCB Physical Address */
+-	put_smstate(u64, smstate, 0x7ee0, svm->nested.vmcb12_gpa);
+	smram->smram64.svm_guest_flag = 1;
+	smram->smram64.svm_guest_vmcb_gpa = svm->nested.vmcb12_gpa;
+ 
+ 	svm->vmcb->save.rax = vcpu->arch.regs[VCPU_REGS_RAX];
+ 	svm->vmcb->save.rsp = vcpu->arch.regs[VCPU_REGS_RSP];
+@@ -4361,28 +4357,23 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
+ {
+ 	struct vcpu_svm *svm = to_svm(vcpu);
+ 	struct kvm_host_map map, map_save;
+-	u64 saved_efer, vmcb12_gpa;
+ 	struct vmcb *vmcb12;
+ 	int ret;
+ 
+-	const char *smstate = (const char *)smram;
+-
+ 	if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+ 		return 0;
+ 
+ 	/* Non-zero if SMI arrived while vCPU was in guest mode. */
+-	if (!GET_SMSTATE(u64, smstate, 0x7ed8))
+	if (!smram->smram64.svm_guest_flag)
+ 		return 0;
+ 
+ 	if (!guest_cpuid_has(vcpu, X86_FEATURE_SVM))
+ 		return 1;
+ 
+-	saved_efer = GET_SMSTATE(u64, smstate, 0x7ed0);
+-	if (!(saved_efer & EFER_SVME))
+	if (!(smram->smram64.efer & EFER_SVME))
+ 		return 1;
+ 
+-	vmcb12_gpa = GET_SMSTATE(u64, smstate, 0x7ee0);
+-	if (kvm_vcpu_map(vcpu, gpa_to_gfn(vmcb12_gpa), &map) == -EINVAL)
+	if (kvm_vcpu_map(vcpu, gpa_to_gfn(smram->smram64.svm_guest_vmcb_gpa), &map) == -EINVAL)
+ 		return 1;
+ 
+ 	ret = 1;
+@@ -4408,7 +4399,7 @@ static int svm_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
+ 	vmcb12 = map.hva;
+ 	nested_copy_vmcb_control_to_cache(svm, &vmcb12->control);
+ 	nested_copy_vmcb_save_to_cache(svm, &vmcb12->save);
+-	ret = enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, false);
+	ret = enter_svm_guest_mode(vcpu, smram->smram64.svm_guest_vmcb_gpa, vmcb12, false);
+ 
+ 	if (ret)
+ 		goto unmap_save;
@@ -0,0 +1,40 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Maxim Levitsky <mlevitsk@redhat.com>
+Date: Wed, 3 Aug 2022 18:50:10 +0300
+Subject: [PATCH] KVM: x86: SVM: don't save SVM state to SMRAM when VM is not
+ long mode capable
+
+When the guest CPUID doesn't have support for long mode, 32 bit SMRAM
+layout is used and it has no support for preserving EFER and/or SVM
+state.
+
+Note that this isn't relevant to running 32 bit guests on VM which is
+long mode capable - such VM can still run 32 bit guests in compatibility
+mode.
+
+Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/kvm/svm/svm.c | 9 +++++++++
+ 1 file changed, 9 insertions(+)
+
+diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
+index 20f90c596d6a..c816783737b0 100644
+--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
+@@ -4317,6 +4317,15 @@ static int svm_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
+ 	if (!is_guest_mode(vcpu))
+ 		return 0;
+ 
+	/*
+	 * 32 bit SMRAM format doesn't preserve EFER and SVM state.
+	 * SVM should not be enabled by the userspace without marking
+	 * the CPU as at least long mode capable.
+	 */
+
+	if (!guest_cpuid_has(vcpu, X86_FEATURE_LM))
+		return 1;
+
+ 	smram->smram64.svm_guest_flag = 1;
+ 	smram->smram64.svm_guest_vmcb_gpa = svm->nested.vmcb12_gpa;
+ 
@@ -1,49 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Omar Sandoval <osandov@fb.com>
-Date: Tue, 5 Dec 2017 23:15:31 -0800
-Subject: [PATCH] sched/wait: Fix add_wait_queue() behavioral change
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-The following cleanup commit:
-
-  50816c48997a ("sched/wait: Standardize internal naming of wait-queue entries")
-
-... unintentionally changed the behavior of add_wait_queue() from
-inserting the wait entry at the head of the wait queue to the tail
-of the wait queue.
-
-Beyond a negative performance impact this change in behavior
-theoretically also breaks wait queues which mix exclusive and
-non-exclusive waiters, as non-exclusive waiters will not be
-woken up if they are queued behind enough exclusive waiters.
-
-Signed-off-by: Omar Sandoval <osandov@fb.com>
-Reviewed-by: Jens Axboe <axboe@kernel.dk>
-Acked-by: Peter Zijlstra <peterz@infradead.org>
-Cc: Linus Torvalds <torvalds@linux-foundation.org>
-Cc: Thomas Gleixner <tglx@linutronix.de>
-Cc: kernel-team@fb.com
-Fixes: ("sched/wait: Standardize internal naming of wait-queue entries")
-Link: http://lkml.kernel.org/r/a16c8ccffd39bd08fdaa45a5192294c784b803a7.1512544324.git.osandov@fb.com
-Signed-off-by: Ingo Molnar <mingo@kernel.org>
-(cherry picked from commit c6b9d9a33029014446bd9ed84c1688f6d3d4eab9)
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- kernel/sched/wait.c | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
-index d6afed6d0752..c09ebe92a40a 100644
--- a/kernel/sched/wait.c
-+++ b/kernel/sched/wait.c
-@@ -27,7 +27,7 @@ void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq
- 
- 	wq_entry->flags &= ~WQ_FLAG_EXCLUSIVE;
- 	spin_lock_irqsave(&wq_head->lock, flags);
-	__add_wait_queue_entry_tail(wq_head, wq_entry);
-+	__add_wait_queue(wq_head, wq_entry);
- 	spin_unlock_irqrestore(&wq_head->lock, flags);
- }
- EXPORT_SYMBOL(add_wait_queue);
@@ -0,0 +1,180 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Maxim Levitsky <mlevitsk@redhat.com>
+Date: Wed, 3 Aug 2022 18:50:11 +0300
+Subject: [PATCH] KVM: x86: emulator/smm: preserve interrupt shadow in SMRAM
+
+When #SMI is asserted, the CPU can be in interrupt shadow
+due to sti or mov ss.
+
+It is not mandatory in  Intel/AMD prm to have the #SMI
+blocked during the shadow, and on top of
+that, since neither SVM nor VMX has true support for SMI
+window, waiting for one instruction would mean single stepping
+the guest.
+
+Instead, allow #SMI in this case, but both reset the interrupt
+window and stash its value in SMRAM to restore it on exit
+from SMM.
+
+This fixes rare failures seen mostly on windows guests on VMX,
+when #SMI falls on the sti instruction which mainfest in
+VM entry failure due to EFLAGS.IF not being set, but STI interrupt
+window still being set in the VMCS.
+
+Signed-off-by: Maxim Levitsky <mlevitsk@redhat.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/kvm/emulate.c     | 17 ++++++++++++++---
+ arch/x86/kvm/kvm_emulate.h | 10 ++++++----
+ arch/x86/kvm/x86.c         | 12 ++++++++++++
+ 3 files changed, 32 insertions(+), 7 deletions(-)
+
+diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
+index 5480b23112e3..4c9c9844d38f 100644
+--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
+@@ -2435,7 +2435,7 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+ 			     const struct kvm_smram_state_32 *smstate)
+ {
+ 	struct desc_ptr dt;
+-	int i;
+	int i, r;
+ 
+ 	ctxt->eflags =  smstate->eflags | X86_EFLAGS_FIXED;
+ 	ctxt->_eip =  smstate->eip;
+@@ -2470,8 +2470,16 @@ static int rsm_load_state_32(struct x86_emulate_ctxt *ctxt,
+ 
+ 	ctxt->ops->set_smbase(ctxt, smstate->smbase);
+ 
+-	return rsm_enter_protected_mode(ctxt, smstate->cr0,
+-					smstate->cr3, smstate->cr4);
+	r = rsm_enter_protected_mode(ctxt, smstate->cr0,
+				     smstate->cr3, smstate->cr4);
+
+	if (r != X86EMUL_CONTINUE)
+		return r;
+
+	ctxt->ops->set_int_shadow(ctxt, 0);
+	ctxt->interruptibility = (u8)smstate->int_shadow;
+
+	return X86EMUL_CONTINUE;
+ }
+ 
+ #ifdef CONFIG_X86_64
+@@ -2520,6 +2528,9 @@ static int rsm_load_state_64(struct x86_emulate_ctxt *ctxt,
+ 	rsm_load_seg_64(ctxt, &smstate->fs, VCPU_SREG_FS);
+ 	rsm_load_seg_64(ctxt, &smstate->gs, VCPU_SREG_GS);
+ 
+	ctxt->ops->set_int_shadow(ctxt, 0);
+	ctxt->interruptibility = (u8)smstate->int_shadow;
+
+ 	return X86EMUL_CONTINUE;
+ }
+ #endif
+diff --git a/arch/x86/kvm/kvm_emulate.h b/arch/x86/kvm/kvm_emulate.h
+index 04ac0cef8b57..d5707b3f254c 100644
+--- a/arch/x86/kvm/kvm_emulate.h
+++ b/arch/x86/kvm/kvm_emulate.h
+@@ -233,6 +233,7 @@ struct x86_emulate_ops {
+ 	bool (*guest_has_rdpid)(struct x86_emulate_ctxt *ctxt);
+ 
+ 	void (*set_nmi_mask)(struct x86_emulate_ctxt *ctxt, bool masked);
+	void (*set_int_shadow)(struct x86_emulate_ctxt *ctxt, u8 shadow);
+ 
+ 	unsigned (*get_hflags)(struct x86_emulate_ctxt *ctxt);
+ 	void (*exiting_smm)(struct x86_emulate_ctxt *ctxt);
+@@ -496,7 +497,8 @@ struct kvm_smram_state_32 {
+ 	u32 reserved1[62];
+ 	u32 smbase;
+ 	u32 smm_revision;
+-	u32 reserved2[5];
+	u32 reserved2[4];
+	u32 int_shadow; /* KVM extension */
+ 	u32 cr4; /* CR4 is not present in Intel/AMD SMRAM image */
+ 	u32 reserved3[5];
+ 
+@@ -544,6 +546,7 @@ static inline void __check_smram32_offsets(void)
+ 	__CHECK_SMRAM32_OFFSET(smbase,		0xFEF8);
+ 	__CHECK_SMRAM32_OFFSET(smm_revision,	0xFEFC);
+ 	__CHECK_SMRAM32_OFFSET(reserved2,	0xFF00);
+	__CHECK_SMRAM32_OFFSET(int_shadow,	0xFF10);
+ 	__CHECK_SMRAM32_OFFSET(cr4,		0xFF14);
+ 	__CHECK_SMRAM32_OFFSET(reserved3,	0xFF18);
+ 	__CHECK_SMRAM32_OFFSET(ds,		0xFF2C);
+@@ -603,7 +606,7 @@ struct kvm_smram_state_64 {
+ 	u64 io_restart_rsi;
+ 	u64 io_restart_rdi;
+ 	u32 io_restart_dword;
+-	u32 reserved1;
+	u32 int_shadow;
+ 	u8 io_inst_restart;
+ 	u8 auto_hlt_restart;
+ 	u8 reserved2[6];
+@@ -641,7 +644,6 @@ struct kvm_smram_state_64 {
+ 	u64 gprs[16]; /* GPRS in a reversed "natural" X86 order (R15/R14/../RCX/RAX.) */
+ };
+ 
+-
+ static inline void __check_smram64_offsets(void)
+ {
+ #define __CHECK_SMRAM64_OFFSET(field, offset) \
+@@ -662,7 +664,7 @@ static inline void __check_smram64_offsets(void)
+ 	__CHECK_SMRAM64_OFFSET(io_restart_rsi,		0xFEB0);
+ 	__CHECK_SMRAM64_OFFSET(io_restart_rdi,		0xFEB8);
+ 	__CHECK_SMRAM64_OFFSET(io_restart_dword,	0xFEC0);
+-	__CHECK_SMRAM64_OFFSET(reserved1,		0xFEC4);
+	__CHECK_SMRAM64_OFFSET(int_shadow,		0xFEC4);
+ 	__CHECK_SMRAM64_OFFSET(io_inst_restart,		0xFEC8);
+ 	__CHECK_SMRAM64_OFFSET(auto_hlt_restart,	0xFEC9);
+ 	__CHECK_SMRAM64_OFFSET(reserved2,		0xFECA);
+diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
+index ada063ab8ae9..4050b34806ac 100644
+--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
+@@ -7930,6 +7930,11 @@ static void emulator_set_nmi_mask(struct x86_emulate_ctxt *ctxt, bool masked)
+ 	static_call(kvm_x86_set_nmi_mask)(emul_to_vcpu(ctxt), masked);
+ }
+ 
+static void emulator_set_int_shadow(struct x86_emulate_ctxt *ctxt, u8 shadow)
+{
+	 static_call(kvm_x86_set_interrupt_shadow)(emul_to_vcpu(ctxt), shadow);
+}
+
+ static unsigned emulator_get_hflags(struct x86_emulate_ctxt *ctxt)
+ {
+ 	return emul_to_vcpu(ctxt)->arch.hflags;
+@@ -8001,6 +8006,7 @@ static const struct x86_emulate_ops emulate_ops = {
+ 	.guest_has_fxsr      = emulator_guest_has_fxsr,
+ 	.guest_has_rdpid     = emulator_guest_has_rdpid,
+ 	.set_nmi_mask        = emulator_set_nmi_mask,
+	.set_int_shadow      = emulator_set_int_shadow,
+ 	.get_hflags          = emulator_get_hflags,
+ 	.exiting_smm         = emulator_exiting_smm,
+ 	.leave_smm           = emulator_leave_smm,
+@@ -9796,6 +9802,8 @@ static void enter_smm_save_state_32(struct kvm_vcpu *vcpu, struct kvm_smram_stat
+ 	smram->cr4 = kvm_read_cr4(vcpu);
+ 	smram->smm_revision = 0x00020000;
+ 	smram->smbase = vcpu->arch.smbase;
+
+	smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
+ }
+ 
+ #ifdef CONFIG_X86_64
+@@ -9844,6 +9852,8 @@ static void enter_smm_save_state_64(struct kvm_vcpu *vcpu, struct kvm_smram_stat
+ 	enter_smm_save_seg_64(vcpu, &smram->ds, VCPU_SREG_DS);
+ 	enter_smm_save_seg_64(vcpu, &smram->fs, VCPU_SREG_FS);
+ 	enter_smm_save_seg_64(vcpu, &smram->gs, VCPU_SREG_GS);
+
+	smram->int_shadow = static_call(kvm_x86_get_interrupt_shadow)(vcpu);
+ }
+ #endif
+ 
+@@ -9880,6 +9890,8 @@ static void enter_smm(struct kvm_vcpu *vcpu)
+ 	kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
+ 	kvm_rip_write(vcpu, 0x8000);
+ 
+	static_call(kvm_x86_set_interrupt_shadow)(vcpu, 0);
+
+ 	cr0 = vcpu->arch.cr0 & ~(X86_CR0_PE | X86_CR0_EM | X86_CR0_TS | X86_CR0_PG);
+ 	static_call(kvm_x86_set_cr0)(vcpu, cr0);
+ 	vcpu->arch.cr0 = cr0;
@@ -1,161 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Andi Kleen <ak@linux.intel.com>
-Date: Thu, 25 Jan 2018 15:50:28 -0800
-Subject: [PATCH] module/retpoline: Warn about missing retpoline in module
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-There's a risk that a kernel which has full retpoline mitigations becomes
-vulnerable when a module gets loaded that hasn't been compiled with the
-right compiler or the right option.
-
-To enable detection of that mismatch at module load time, add a module info
-string "retpoline" at build time when the module was compiled with
-retpoline support. This only covers compiled C source, but assembler source
-or prebuilt object files are not checked.
-
-If a retpoline enabled kernel detects a non retpoline protected module at
-load time, print a warning and report it in the sysfs vulnerability file.
-
-[ tglx: Massaged changelog ]
-
-Signed-off-by: Andi Kleen <ak@linux.intel.com>
-Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
-Cc: David Woodhouse <dwmw2@infradead.org>
-Cc: gregkh@linuxfoundation.org
-Cc: torvalds@linux-foundation.org
-Cc: jeyu@kernel.org
-Cc: arjan@linux.intel.com
-Link: https://lkml.kernel.org/r/20180125235028.31211-1-andi@firstfloor.org
-(backported from commit caf7501a1b4ec964190f31f9c3f163de252273b8)
-Conflicts:
-	arch/x86/kernel/cpu/bugs.c
-context changes
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- arch/x86/kernel/cpu/bugs.c | 18 +++++++++++++++++-
- include/linux/module.h     |  9 +++++++++
- kernel/module.c            | 11 +++++++++++
- scripts/mod/modpost.c      |  9 +++++++++
- 4 files changed, 46 insertions(+), 1 deletion(-)
-
-diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
-index 7e5db5aa37f3..b5bcdf7e94d7 100644
--- a/arch/x86/kernel/cpu/bugs.c
-+++ b/arch/x86/kernel/cpu/bugs.c
-@@ -11,6 +11,7 @@
- #include <linux/utsname.h>
- #include <linux/cpu.h>
- #include <linux/smp.h>
-+#include <linux/module.h>
- #include <linux/nospec.h>
- #include <linux/prctl.h>
- 
-@@ -131,6 +132,19 @@ static const char *spectre_v2_strings[] = {
- 
- static enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init =
- 	SPECTRE_V2_NONE;
-+static bool spectre_v2_bad_module;
-+
-+#ifdef RETPOLINE
-+bool retpoline_module_ok(bool has_retpoline)
-+{
-+	if (spectre_v2_enabled == SPECTRE_V2_NONE || has_retpoline)
-+		return true;
-+
-+	pr_err("System may be vunerable to spectre v2\n");
-+	spectre_v2_bad_module = true;
-+	return false;
-+}
-+#endif
- 
- void
- x86_virt_spec_ctrl(u64 guest_spec_ctrl, u64 guest_virt_spec_ctrl, bool setguest)
-@@ -627,7 +641,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
- 			return sprintf(buf, "Mitigation: OSB (observable speculation barrier, Intel v6)\n");
- 
- 	case X86_BUG_SPECTRE_V2:
-		return sprintf(buf, "%s%s\n", spectre_v2_strings[spectre_v2_enabled], ibpb_inuse ? ", IBPB (Intel v4)" : "");
-+		return sprintf(buf, "%s%s%s\n", spectre_v2_strings[spectre_v2_enabled],
-+		               ibpb_inuse ? ",IBPB (Intel v4)" : "",
-+		               spectre_v2_bad_module ? " - vulnerable module loaded" : "");
- 
- 	case X86_BUG_SPEC_STORE_BYPASS:
- 		return sprintf(buf, "%s\n", ssb_strings[ssb_mode]);
-diff --git a/include/linux/module.h b/include/linux/module.h
-index e7bdd549e527..c4fdf7661f82 100644
--- a/include/linux/module.h
-+++ b/include/linux/module.h
-@@ -794,6 +794,15 @@ static inline void module_bug_finalize(const Elf_Ehdr *hdr,
- static inline void module_bug_cleanup(struct module *mod) {}
- #endif	/* CONFIG_GENERIC_BUG */
- 
-+#ifdef RETPOLINE
-+extern bool retpoline_module_ok(bool has_retpoline);
-+#else
-+static inline bool retpoline_module_ok(bool has_retpoline)
-+{
-+	return true;
-+}
-+#endif
-+
- #ifdef CONFIG_MODULE_SIG
- static inline bool module_sig_ok(struct module *module)
- {
-diff --git a/kernel/module.c b/kernel/module.c
-index 41b97a191a72..1c3fd6f767b4 100644
--- a/kernel/module.c
-+++ b/kernel/module.c
-@@ -2855,6 +2855,15 @@ static int check_modinfo_livepatch(struct module *mod, struct load_info *info)
- }
- #endif /* CONFIG_LIVEPATCH */
- 
-+static void check_modinfo_retpoline(struct module *mod, struct load_info *info)
-+{
-+	if (retpoline_module_ok(get_modinfo(info, "retpoline")))
-+		return;
-+
-+	pr_warn("%s: loading module not compiled with retpoline compiler.\n",
-+		mod->name);
-+}
-+
- /* Sets info->hdr and info->len. */
- static int copy_module_from_user(const void __user *umod, unsigned long len,
- 				  struct load_info *info)
-@@ -3021,6 +3030,8 @@ static int check_modinfo(struct module *mod, struct load_info *info, int flags)
- 		add_taint_module(mod, TAINT_OOT_MODULE, LOCKDEP_STILL_OK);
- 	}
- 
-+	check_modinfo_retpoline(mod, info);
-+
- 	if (get_modinfo(info, "staging")) {
- 		add_taint_module(mod, TAINT_CRAP, LOCKDEP_STILL_OK);
- 		pr_warn("%s: module is from the staging directory, the quality "
-diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
-index 48397feb08fb..cc91f81ac33e 100644
--- a/scripts/mod/modpost.c
-+++ b/scripts/mod/modpost.c
-@@ -2147,6 +2147,14 @@ static void add_intree_flag(struct buffer *b, int is_intree)
- 		buf_printf(b, "\nMODULE_INFO(intree, \"Y\");\n");
- }
- 
-+/* Cannot check for assembler */
-+static void add_retpoline(struct buffer *b)
-+{
-+	buf_printf(b, "\n#ifdef RETPOLINE\n");
-+	buf_printf(b, "MODULE_INFO(retpoline, \"Y\");\n");
-+	buf_printf(b, "#endif\n");
-+}
-+
- static void add_staging_flag(struct buffer *b, const char *name)
- {
- 	static const char *staging_dir = "drivers/staging";
-@@ -2492,6 +2500,7 @@ int main(int argc, char **argv)
- 
- 		add_header(&buf, mod);
- 		add_intree_flag(&buf, !external_module);
-+		add_retpoline(&buf);
- 		add_staging_flag(&buf, mod->name);
- 		err |= add_versions(&buf, mod);
- 		add_depends(&buf, mod, modules);
@@ -1,124 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Dan Streetman <ddstreet@ieee.org>
-Date: Thu, 18 Jan 2018 16:14:26 -0500
-Subject: [PATCH] net: tcp: close sock if net namespace is exiting
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-When a tcp socket is closed, if it detects that its net namespace is
-exiting, close immediately and do not wait for FIN sequence.
-
-For normal sockets, a reference is taken to their net namespace, so it will
-never exit while the socket is open.  However, kernel sockets do not take a
-reference to their net namespace, so it may begin exiting while the kernel
-socket is still open.  In this case if the kernel socket is a tcp socket,
-it will stay open trying to complete its close sequence.  The sock's dst(s)
-hold a reference to their interface, which are all transferred to the
-namespace's loopback interface when the real interfaces are taken down.
-When the namespace tries to take down its loopback interface, it hangs
-waiting for all references to the loopback interface to release, which
-results in messages like:
-
-unregister_netdevice: waiting for lo to become free. Usage count = 1
-
-These messages continue until the socket finally times out and closes.
-Since the net namespace cleanup holds the net_mutex while calling its
-registered pernet callbacks, any new net namespace initialization is
-blocked until the current net namespace finishes exiting.
-
-After this change, the tcp socket notices the exiting net namespace, and
-closes immediately, releasing its dst(s) and their reference to the
-loopback interface, which lets the net namespace continue exiting.
-
-Link: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1711407
-Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=97811
-Signed-off-by: Dan Streetman <ddstreet@canonical.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- include/net/net_namespace.h | 10 ++++++++++
- net/ipv4/tcp.c              |  3 +++
- net/ipv4/tcp_timer.c        | 15 +++++++++++++++
- 3 files changed, 28 insertions(+)
-
-diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h
-index 1c401bd4c2e0..a5d023fa78db 100644
--- a/include/net/net_namespace.h
-+++ b/include/net/net_namespace.h
-@@ -221,6 +221,11 @@ int net_eq(const struct net *net1, const struct net *net2)
- 	return net1 == net2;
- }
- 
-+static inline int check_net(const struct net *net)
-+{
-+	return atomic_read(&net->count) != 0;
-+}
-+
- void net_drop_ns(void *);
- 
- #else
-@@ -245,6 +250,11 @@ int net_eq(const struct net *net1, const struct net *net2)
- 	return 1;
- }
- 
-+static inline int check_net(const struct net *net)
-+{
-+	return 1;
-+}
-+
- #define net_drop_ns NULL
- #endif
- 
-diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
-index a3e91b552edc..fd2a086da910 100644
--- a/net/ipv4/tcp.c
-+++ b/net/ipv4/tcp.c
-@@ -2258,6 +2258,9 @@ void tcp_close(struct sock *sk, long timeout)
- 			tcp_send_active_reset(sk, GFP_ATOMIC);
- 			__NET_INC_STATS(sock_net(sk),
- 					LINUX_MIB_TCPABORTONMEMORY);
-+		} else if (!check_net(sock_net(sk))) {
-+			/* Not possible to send reset; just close */
-+			tcp_set_state(sk, TCP_CLOSE);
- 		}
- 	}
- 
-diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
-index e906014890b6..ec1e5de41653 100644
--- a/net/ipv4/tcp_timer.c
-+++ b/net/ipv4/tcp_timer.c
-@@ -50,11 +50,19 @@ static void tcp_write_err(struct sock *sk)
-  *  to prevent DoS attacks. It is called when a retransmission timeout
-  *  or zero probe timeout occurs on orphaned socket.
-  *
-+ *  Also close if our net namespace is exiting; in that case there is no
-+ *  hope of ever communicating again since all netns interfaces are already
-+ *  down (or about to be down), and we need to release our dst references,
-+ *  which have been moved to the netns loopback interface, so the namespace
-+ *  can finish exiting.  This condition is only possible if we are a kernel
-+ *  socket, as those do not hold references to the namespace.
-+ *
-  *  Criteria is still not confirmed experimentally and may change.
-  *  We kill the socket, if:
-  *  1. If number of orphaned sockets exceeds an administratively configured
-  *     limit.
-  *  2. If we have strong memory pressure.
-+ *  3. If our net namespace is exiting.
-  */
- static int tcp_out_of_resources(struct sock *sk, bool do_reset)
- {
-@@ -83,6 +91,13 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
- 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
- 		return 1;
- 	}
-+
-+	if (!check_net(sock_net(sk))) {
-+		/* Not possible to send reset; just close */
-+		tcp_done(sk);
-+		return 1;
-+	}
-+
- 	return 0;
- }
- 
@@ -1,86 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Tommi Rantala <tommi.t.rantala@nokia.com>
-Date: Mon, 5 Feb 2018 21:48:14 +0200
-Subject: [PATCH] sctp: fix dst refcnt leak in sctp_v4_get_dst
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Fix dst reference count leak in sctp_v4_get_dst() introduced in commit
-410f03831 ("sctp: add routing output fallback"):
-
-When walking the address_list, successive ip_route_output_key() calls
-may return the same rt->dst with the reference incremented on each call.
-
-The code would not decrement the dst refcount when the dst pointer was
-identical from the previous iteration, causing the dst refcnt leak.
-
-Testcase:
-  ip netns add TEST
-  ip netns exec TEST ip link set lo up
-  ip link add dummy0 type dummy
-  ip link add dummy1 type dummy
-  ip link add dummy2 type dummy
-  ip link set dev dummy0 netns TEST
-  ip link set dev dummy1 netns TEST
-  ip link set dev dummy2 netns TEST
-  ip netns exec TEST ip addr add 192.168.1.1/24 dev dummy0
-  ip netns exec TEST ip link set dummy0 up
-  ip netns exec TEST ip addr add 192.168.1.2/24 dev dummy1
-  ip netns exec TEST ip link set dummy1 up
-  ip netns exec TEST ip addr add 192.168.1.3/24 dev dummy2
-  ip netns exec TEST ip link set dummy2 up
-  ip netns exec TEST sctp_test -H 192.168.1.2 -P 20002 -h 192.168.1.1 -p 20000 -s -B 192.168.1.3
-  ip netns del TEST
-
-In 4.4 and 4.9 kernels this results to:
-  [  354.179591] unregister_netdevice: waiting for lo to become free. Usage count = 1
-  [  364.419674] unregister_netdevice: waiting for lo to become free. Usage count = 1
-  [  374.663664] unregister_netdevice: waiting for lo to become free. Usage count = 1
-  [  384.903717] unregister_netdevice: waiting for lo to become free. Usage count = 1
-  [  395.143724] unregister_netdevice: waiting for lo to become free. Usage count = 1
-  [  405.383645] unregister_netdevice: waiting for lo to become free. Usage count = 1
-  ...
-
-Fixes: 410f03831 ("sctp: add routing output fallback")
-Fixes: 0ca50d12f ("sctp: fix src address selection if using secondary addresses")
-Signed-off-by: Tommi Rantala <tommi.t.rantala@nokia.com>
-Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
-Acked-by: Neil Horman <nhorman@tuxdriver.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- net/sctp/protocol.c | 10 ++++------
- 1 file changed, 4 insertions(+), 6 deletions(-)
-
-diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
-index 989a900383b5..e1a3ae4f3cab 100644
--- a/net/sctp/protocol.c
-+++ b/net/sctp/protocol.c
-@@ -514,22 +514,20 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
- 		if (IS_ERR(rt))
- 			continue;
- 
-		if (!dst)
-			dst = &rt->dst;
-
- 		/* Ensure the src address belongs to the output
- 		 * interface.
- 		 */
- 		odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr,
- 				     false);
- 		if (!odev || odev->ifindex != fl4->flowi4_oif) {
-			if (&rt->dst != dst)
-+			if (!dst)
-+				dst = &rt->dst;
-+			else
- 				dst_release(&rt->dst);
- 			continue;
- 		}
- 
-		if (dst != &rt->dst)
-			dst_release(dst);
-+		dst_release(dst);
- 		dst = &rt->dst;
- 		break;
- 	}
@@ -1,57 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Alexey Kodanev <alexey.kodanev@oracle.com>
-Date: Mon, 5 Feb 2018 15:10:35 +0300
-Subject: [PATCH] sctp: fix dst refcnt leak in sctp_v6_get_dst()
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-When going through the bind address list in sctp_v6_get_dst() and
-the previously found address is better ('matchlen > bmatchlen'),
-the code continues to the next iteration without releasing currently
-held destination.
-
-Fix it by releasing 'bdst' before continue to the next iteration, and
-instead of introducing one more '!IS_ERR(bdst)' check for dst_release(),
-move the already existed one right after ip6_dst_lookup_flow(), i.e. we
-shouldn't proceed further if we get an error for the route lookup.
-
-Fixes: dbc2b5e9a09e ("sctp: fix src address selection if using secondary addresses for ipv6")
-Signed-off-by: Alexey Kodanev <alexey.kodanev@oracle.com>
-Acked-by: Neil Horman <nhorman@tuxdriver.com>
-Acked-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
-Signed-off-by: David S. Miller <davem@davemloft.net>
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- net/sctp/ipv6.c | 10 +++++++---
- 1 file changed, 7 insertions(+), 3 deletions(-)
-
-diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c
-index edb462b0b73b..e626d72868fe 100644
--- a/net/sctp/ipv6.c
-+++ b/net/sctp/ipv6.c
-@@ -326,8 +326,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
- 		final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final);
- 		bdst = ip6_dst_lookup_flow(sk, fl6, final_p);
- 
-		if (!IS_ERR(bdst) &&
-		    ipv6_chk_addr(dev_net(bdst->dev),
-+		if (IS_ERR(bdst))
-+			continue;
-+
-+		if (ipv6_chk_addr(dev_net(bdst->dev),
- 				  &laddr->a.v6.sin6_addr, bdst->dev, 1)) {
- 			if (!IS_ERR_OR_NULL(dst))
- 				dst_release(dst);
-@@ -336,8 +338,10 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr,
- 		}
- 
- 		bmatchlen = sctp_v6_addr_match_len(daddr, &laddr->a);
-		if (matchlen > bmatchlen)
-+		if (matchlen > bmatchlen) {
-+			dst_release(bdst);
- 			continue;
-+		}
- 
- 		if (!IS_ERR_OR_NULL(dst))
- 			dst_release(dst);
@@ -1,43 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Vasily Averin <vvs@virtuozzo.com>
-Date: Thu, 2 Nov 2017 13:03:42 +0300
-Subject: [PATCH] lockd: lost rollback of set_grace_period() in
- lockd_down_net()
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Commit efda760fe95ea ("lockd: fix lockd shutdown race") is incorrect,
-it removes lockd_manager and disarm grace_period_end for init_net only.
-
-If nfsd was started from another net namespace lockd_up_net() calls
-set_grace_period() that adds lockd_manager into per-netns list
-and queues grace_period_end delayed work.
-
-These action should be reverted in lockd_down_net().
-Otherwise it can lead to double list_add on after restart nfsd in netns,
-and to use-after-free if non-disarmed delayed work will be executed after netns destroy.
-
-Fixes: efda760fe95e ("lockd: fix lockd shutdown race")
-Cc: stable@vger.kernel.org
-Signed-off-by: Vasily Averin <vvs@virtuozzo.com>
-Signed-off-by: J. Bruce Fields <bfields@redhat.com>
-(cherry picked from commit 3a2b19d1ee5633f76ae8a88da7bc039a5d1732aa)
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- fs/lockd/svc.c | 2 ++
- 1 file changed, 2 insertions(+)
-
-diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
-index 726b6cecf430..fa8f6effcf00 100644
--- a/fs/lockd/svc.c
-+++ b/fs/lockd/svc.c
-@@ -274,6 +274,8 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net)
- 	if (ln->nlmsvc_users) {
- 		if (--ln->nlmsvc_users == 0) {
- 			nlm_shutdown_hosts_net(net);
-+			cancel_delayed_work_sync(&ln->grace_period_end);
-+			locks_end_grace(&ln->lockd_manager);
- 			svc_shutdown_net(serv, net);
- 			dprintk("lockd_down_net: per-net data destroyed; net=%p\n", net);
- 		}
@@ -1,58 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Changwei Ge <ge.changwei@h3c.com>
-Date: Wed, 31 Jan 2018 16:15:02 -0800
-Subject: [PATCH] ocfs2: make metadata estimation accurate and clear
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-Current code assume that ::w_unwritten_list always has only one item on.
-This is not right and hard to get understood.  So improve how to count
-unwritten item.
-
-Link: http://lkml.kernel.org/r/1515479070-32653-1-git-send-email-ge.changwei@h3c.com
-Signed-off-by: Changwei Ge <ge.changwei@h3c.com>
-Reported-by: John Lightsey <john@nixnuts.net>
-Tested-by: John Lightsey <john@nixnuts.net>
-Cc: Mark Fasheh <mfasheh@versity.com>
-Cc: Joseph Qi <jiangqi903@gmail.com>
-Cc: Junxiao Bi <junxiao.bi@oracle.com>
-Cc: Joel Becker <jlbec@evilplan.org>
-Cc: Changwei Ge <ge.changwei@h3c.com>
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-(cherry picked from commit 63de8bd9328bf2a778fc277503da163ae3defa3c)
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- fs/ocfs2/aops.c | 4 +++-
- 1 file changed, 3 insertions(+), 1 deletion(-)
-
-diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
-index 88a31e9340a0..77ec9b495027 100644
--- a/fs/ocfs2/aops.c
-+++ b/fs/ocfs2/aops.c
-@@ -784,6 +784,7 @@ struct ocfs2_write_ctxt {
- 	struct ocfs2_cached_dealloc_ctxt w_dealloc;
- 
- 	struct list_head		w_unwritten_list;
-+	unsigned int			w_unwritten_count;
- };
- 
- void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
-@@ -1373,6 +1374,7 @@ static int ocfs2_unwritten_check(struct inode *inode,
- 	desc->c_clear_unwritten = 0;
- 	list_add_tail(&new->ue_ip_node, &oi->ip_unwritten_list);
- 	list_add_tail(&new->ue_node, &wc->w_unwritten_list);
-+	wc->w_unwritten_count++;
- 	new = NULL;
- unlock:
- 	spin_unlock(&oi->ip_lock);
-@@ -2246,7 +2248,7 @@ static int ocfs2_dio_get_block(struct inode *inode, sector_t iblock,
- 		ue->ue_phys = desc->c_phys;
- 
- 		list_splice_tail_init(&wc->w_unwritten_list, &dwc->dw_zero_list);
-		dwc->dw_zero_count++;
-+		dwc->dw_zero_count += wc->w_unwritten_count;
- 	}
- 
- 	ret = ocfs2_write_end_nolock(inode->i_mapping, pos, len, len, wc);
@@ -1,367 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Changwei Ge <ge.changwei@h3c.com>
-Date: Wed, 31 Jan 2018 16:15:06 -0800
-Subject: [PATCH] ocfs2: try to reuse extent block in dealloc without
- meta_alloc
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-A crash issue was reported by John Lightsey with a call trace as follows:
-
-  ocfs2_split_extent+0x1ad3/0x1b40 [ocfs2]
-  ocfs2_change_extent_flag+0x33a/0x470 [ocfs2]
-  ocfs2_mark_extent_written+0x172/0x220 [ocfs2]
-  ocfs2_dio_end_io+0x62d/0x910 [ocfs2]
-  dio_complete+0x19a/0x1a0
-  do_blockdev_direct_IO+0x19dd/0x1eb0
-  __blockdev_direct_IO+0x43/0x50
-  ocfs2_direct_IO+0x8f/0xa0 [ocfs2]
-  generic_file_direct_write+0xb2/0x170
-  __generic_file_write_iter+0xc3/0x1b0
-  ocfs2_file_write_iter+0x4bb/0xca0 [ocfs2]
-  __vfs_write+0xae/0xf0
-  vfs_write+0xb8/0x1b0
-  SyS_write+0x4f/0xb0
-  system_call_fastpath+0x16/0x75
-
-The BUG code told that extent tree wants to grow but no metadata was
-reserved ahead of time.  From my investigation into this issue, the root
-cause it that although enough metadata is not reserved, there should be
-enough for following use.  Rightmost extent is merged into its left one
-due to a certain times of marking extent written.  Because during
-marking extent written, we got many physically continuous extents.  At
-last, an empty extent showed up and the rightmost path is removed from
-extent tree.
-
-Add a new mechanism to reuse extent block cached in dealloc which were
-just unlinked from extent tree to solve this crash issue.
-
-Criteria is that during marking extents *written*, if extent rotation
-and merging results in unlinking extent with growing extent tree later
-without any metadata reserved ahead of time, try to reuse those extents
-in dealloc in which deleted extents are cached.
-
-Also, this patch addresses the issue John reported that ::dw_zero_count
-is not calculated properly.
-
-After applying this patch, the issue John reported was gone.  Thanks for
-the reproducer provided by John.  And this patch has passed
-ocfs2-test(29 cases) suite running by New H3C Group.
-
-[ge.changwei@h3c.com: fix static checker warnning]
-  Link: http://lkml.kernel.org/r/63ADC13FD55D6546B7DECE290D39E373F29196AE@H3CMLB12-EX.srv.huawei-3com.com
-[akpm@linux-foundation.org: brelse(NULL) is legal]
-Link: http://lkml.kernel.org/r/1515479070-32653-2-git-send-email-ge.changwei@h3c.com
-Signed-off-by: Changwei Ge <ge.changwei@h3c.com>
-Reported-by: John Lightsey <john@nixnuts.net>
-Tested-by: John Lightsey <john@nixnuts.net>
-Cc: Joel Becker <jlbec@evilplan.org>
-Cc: Joseph Qi <jiangqi903@gmail.com>
-Cc: Junxiao Bi <junxiao.bi@oracle.com>
-Cc: Dan Carpenter <dan.carpenter@oracle.com>
-Cc: Mark Fasheh <mfasheh@versity.com>
-Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-(cherry picked from commit 71a36944042b7d9dd71f6a5d1c5ea1c2353b5d42)
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- fs/ocfs2/alloc.c | 206 ++++++++++++++++++++++++++++++++++++++++++++++++++++---
- fs/ocfs2/alloc.h |   1 +
- fs/ocfs2/aops.c  |   6 ++
- 3 files changed, 203 insertions(+), 10 deletions(-)
-
-diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
-index 386aecce881d..9b5e7d8ba710 100644
--- a/fs/ocfs2/alloc.c
-+++ b/fs/ocfs2/alloc.c
-@@ -165,6 +165,13 @@ static int ocfs2_dinode_insert_check(struct ocfs2_extent_tree *et,
- 				     struct ocfs2_extent_rec *rec);
- static int ocfs2_dinode_sanity_check(struct ocfs2_extent_tree *et);
- static void ocfs2_dinode_fill_root_el(struct ocfs2_extent_tree *et);
-+
-+static int ocfs2_reuse_blk_from_dealloc(handle_t *handle,
-+					struct ocfs2_extent_tree *et,
-+					struct buffer_head **new_eb_bh,
-+					int blk_wanted, int *blk_given);
-+static int ocfs2_is_dealloc_empty(struct ocfs2_extent_tree *et);
-+
- static const struct ocfs2_extent_tree_operations ocfs2_dinode_et_ops = {
- 	.eo_set_last_eb_blk	= ocfs2_dinode_set_last_eb_blk,
- 	.eo_get_last_eb_blk	= ocfs2_dinode_get_last_eb_blk,
-@@ -448,6 +455,7 @@ static void __ocfs2_init_extent_tree(struct ocfs2_extent_tree *et,
- 	if (!obj)
- 		obj = (void *)bh->b_data;
- 	et->et_object = obj;
-+	et->et_dealloc = NULL;
- 
- 	et->et_ops->eo_fill_root_el(et);
- 	if (!et->et_ops->eo_fill_max_leaf_clusters)
-@@ -1159,7 +1167,7 @@ static int ocfs2_add_branch(handle_t *handle,
- 			    struct buffer_head **last_eb_bh,
- 			    struct ocfs2_alloc_context *meta_ac)
- {
-	int status, new_blocks, i;
-+	int status, new_blocks, i, block_given = 0;
- 	u64 next_blkno, new_last_eb_blk;
- 	struct buffer_head *bh;
- 	struct buffer_head **new_eb_bhs = NULL;
-@@ -1214,11 +1222,31 @@ static int ocfs2_add_branch(handle_t *handle,
- 		goto bail;
- 	}
- 
-	status = ocfs2_create_new_meta_bhs(handle, et, new_blocks,
-					   meta_ac, new_eb_bhs);
-	if (status < 0) {
-		mlog_errno(status);
-		goto bail;
-+	/* Firstyly, try to reuse dealloc since we have already estimated how
-+	 * many extent blocks we may use.
-+	 */
-+	if (!ocfs2_is_dealloc_empty(et)) {
-+		status = ocfs2_reuse_blk_from_dealloc(handle, et,
-+						      new_eb_bhs, new_blocks,
-+						      &block_given);
-+		if (status < 0) {
-+			mlog_errno(status);
-+			goto bail;
-+		}
-+	}
-+
-+	BUG_ON(block_given > new_blocks);
-+
-+	if (block_given < new_blocks) {
-+		BUG_ON(!meta_ac);
-+		status = ocfs2_create_new_meta_bhs(handle, et,
-+						   new_blocks - block_given,
-+						   meta_ac,
-+						   &new_eb_bhs[block_given]);
-+		if (status < 0) {
-+			mlog_errno(status);
-+			goto bail;
-+		}
- 	}
- 
- 	/* Note: new_eb_bhs[new_blocks - 1] is the guy which will be
-@@ -1341,15 +1369,25 @@ static int ocfs2_shift_tree_depth(handle_t *handle,
- 				  struct ocfs2_alloc_context *meta_ac,
- 				  struct buffer_head **ret_new_eb_bh)
- {
-	int status, i;
-+	int status, i, block_given = 0;
- 	u32 new_clusters;
- 	struct buffer_head *new_eb_bh = NULL;
- 	struct ocfs2_extent_block *eb;
- 	struct ocfs2_extent_list  *root_el;
- 	struct ocfs2_extent_list  *eb_el;
- 
-	status = ocfs2_create_new_meta_bhs(handle, et, 1, meta_ac,
-					   &new_eb_bh);
-+	if (!ocfs2_is_dealloc_empty(et)) {
-+		status = ocfs2_reuse_blk_from_dealloc(handle, et,
-+						      &new_eb_bh, 1,
-+						      &block_given);
-+	} else if (meta_ac) {
-+		status = ocfs2_create_new_meta_bhs(handle, et, 1, meta_ac,
-+						   &new_eb_bh);
-+
-+	} else {
-+		BUG();
-+	}
-+
- 	if (status < 0) {
- 		mlog_errno(status);
- 		goto bail;
-@@ -1512,7 +1550,7 @@ static int ocfs2_grow_tree(handle_t *handle, struct ocfs2_extent_tree *et,
- 	int depth = le16_to_cpu(el->l_tree_depth);
- 	struct buffer_head *bh = NULL;
- 
-	BUG_ON(meta_ac == NULL);
-+	BUG_ON(meta_ac == NULL && ocfs2_is_dealloc_empty(et));
- 
- 	shift = ocfs2_find_branch_target(et, &bh);
- 	if (shift < 0) {
-@@ -6593,6 +6631,154 @@ ocfs2_find_per_slot_free_list(int type,
- 	return fl;
- }
- 
-+static struct ocfs2_per_slot_free_list *
-+ocfs2_find_preferred_free_list(int type,
-+			       int preferred_slot,
-+			       int *real_slot,
-+			       struct ocfs2_cached_dealloc_ctxt *ctxt)
-+{
-+	struct ocfs2_per_slot_free_list *fl = ctxt->c_first_suballocator;
-+
-+	while (fl) {
-+		if (fl->f_inode_type == type && fl->f_slot == preferred_slot) {
-+			*real_slot = fl->f_slot;
-+			return fl;
-+		}
-+
-+		fl = fl->f_next_suballocator;
-+	}
-+
-+	/* If we can't find any free list matching preferred slot, just use
-+	 * the first one.
-+	 */
-+	fl = ctxt->c_first_suballocator;
-+	*real_slot = fl->f_slot;
-+
-+	return fl;
-+}
-+
-+/* Return Value 1 indicates empty */
-+static int ocfs2_is_dealloc_empty(struct ocfs2_extent_tree *et)
-+{
-+	struct ocfs2_per_slot_free_list *fl = NULL;
-+
-+	if (!et->et_dealloc)
-+		return 1;
-+
-+	fl = et->et_dealloc->c_first_suballocator;
-+	if (!fl)
-+		return 1;
-+
-+	if (!fl->f_first)
-+		return 1;
-+
-+	return 0;
-+}
-+
-+/* If extent was deleted from tree due to extent rotation and merging, and
-+ * no metadata is reserved ahead of time. Try to reuse some extents
-+ * just deleted. This is only used to reuse extent blocks.
-+ * It is supposed to find enough extent blocks in dealloc if our estimation
-+ * on metadata is accurate.
-+ */
-+static int ocfs2_reuse_blk_from_dealloc(handle_t *handle,
-+					struct ocfs2_extent_tree *et,
-+					struct buffer_head **new_eb_bh,
-+					int blk_wanted, int *blk_given)
-+{
-+	int i, status = 0, real_slot;
-+	struct ocfs2_cached_dealloc_ctxt *dealloc;
-+	struct ocfs2_per_slot_free_list *fl;
-+	struct ocfs2_cached_block_free *bf;
-+	struct ocfs2_extent_block *eb;
-+	struct ocfs2_super *osb =
-+		OCFS2_SB(ocfs2_metadata_cache_get_super(et->et_ci));
-+
-+	*blk_given = 0;
-+
-+	/* If extent tree doesn't have a dealloc, this is not faulty. Just
-+	 * tell upper caller dealloc can't provide any block and it should
-+	 * ask for alloc to claim more space.
-+	 */
-+	dealloc = et->et_dealloc;
-+	if (!dealloc)
-+		goto bail;
-+
-+	for (i = 0; i < blk_wanted; i++) {
-+		/* Prefer to use local slot */
-+		fl = ocfs2_find_preferred_free_list(EXTENT_ALLOC_SYSTEM_INODE,
-+						    osb->slot_num, &real_slot,
-+						    dealloc);
-+		/* If no more block can be reused, we should claim more
-+		 * from alloc. Just return here normally.
-+		 */
-+		if (!fl) {
-+			status = 0;
-+			break;
-+		}
-+
-+		bf = fl->f_first;
-+		fl->f_first = bf->free_next;
-+
-+		new_eb_bh[i] = sb_getblk(osb->sb, bf->free_blk);
-+		if (new_eb_bh[i] == NULL) {
-+			status = -ENOMEM;
-+			mlog_errno(status);
-+			goto bail;
-+		}
-+
-+		mlog(0, "Reusing block(%llu) from "
-+		     "dealloc(local slot:%d, real slot:%d)\n",
-+		     bf->free_blk, osb->slot_num, real_slot);
-+
-+		ocfs2_set_new_buffer_uptodate(et->et_ci, new_eb_bh[i]);
-+
-+		status = ocfs2_journal_access_eb(handle, et->et_ci,
-+						 new_eb_bh[i],
-+						 OCFS2_JOURNAL_ACCESS_CREATE);
-+		if (status < 0) {
-+			mlog_errno(status);
-+			goto bail;
-+		}
-+
-+		memset(new_eb_bh[i]->b_data, 0, osb->sb->s_blocksize);
-+		eb = (struct ocfs2_extent_block *) new_eb_bh[i]->b_data;
-+
-+		/* We can't guarantee that buffer head is still cached, so
-+		 * polutlate the extent block again.
-+		 */
-+		strcpy(eb->h_signature, OCFS2_EXTENT_BLOCK_SIGNATURE);
-+		eb->h_blkno = cpu_to_le64(bf->free_blk);
-+		eb->h_fs_generation = cpu_to_le32(osb->fs_generation);
-+		eb->h_suballoc_slot = cpu_to_le16(real_slot);
-+		eb->h_suballoc_loc = cpu_to_le64(bf->free_bg);
-+		eb->h_suballoc_bit = cpu_to_le16(bf->free_bit);
-+		eb->h_list.l_count =
-+			cpu_to_le16(ocfs2_extent_recs_per_eb(osb->sb));
-+
-+		/* We'll also be dirtied by the caller, so
-+		 * this isn't absolutely necessary.
-+		 */
-+		ocfs2_journal_dirty(handle, new_eb_bh[i]);
-+
-+		if (!fl->f_first) {
-+			dealloc->c_first_suballocator = fl->f_next_suballocator;
-+			kfree(fl);
-+		}
-+		kfree(bf);
-+	}
-+
-+	*blk_given = i;
-+
-+bail:
-+	if (unlikely(status < 0)) {
-+		for (i = 0; i < blk_wanted; i++)
-+			brelse(new_eb_bh[i]);
-+	}
-+
-+	return status;
-+}
-+
- int ocfs2_cache_block_dealloc(struct ocfs2_cached_dealloc_ctxt *ctxt,
- 			      int type, int slot, u64 suballoc,
- 			      u64 blkno, unsigned int bit)
-diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
-index 4a5152ec88a3..571692171dd1 100644
--- a/fs/ocfs2/alloc.h
-+++ b/fs/ocfs2/alloc.h
-@@ -61,6 +61,7 @@ struct ocfs2_extent_tree {
- 	ocfs2_journal_access_func		et_root_journal_access;
- 	void					*et_object;
- 	unsigned int				et_max_leaf_clusters;
-+	struct ocfs2_cached_dealloc_ctxt	*et_dealloc;
- };
- 
- /*
-diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
-index 77ec9b495027..2ff02dda97d8 100644
--- a/fs/ocfs2/aops.c
-+++ b/fs/ocfs2/aops.c
-@@ -2322,6 +2322,12 @@ static int ocfs2_dio_end_io_write(struct inode *inode,
- 
- 	ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), di_bh);
- 
-+	/* Attach dealloc with extent tree in case that we may reuse extents
-+	 * which are already unlinked from current extent tree due to extent
-+	 * rotation and merging.
-+	 */
-+	et.et_dealloc = &dealloc;
-+
- 	ret = ocfs2_lock_allocators(inode, &et, 0, dwc->dw_zero_count*2,
- 				    &data_ac, &meta_ac);
- 	if (ret) {
@@ -1,100 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
-Date: Fri, 23 Mar 2018 09:19:21 +0100
-Subject: [PATCH] mm/shmem: do not wait for lock_page() in
- shmem_unused_huge_shrink()
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-shmem_unused_huge_shrink() gets called from reclaim path.  Waiting for
-page lock may lead to deadlock there.
-
-There was a bug report that may be attributed to this:
-
-http://lkml.kernel.org/r/alpine.LRH.2.11.1801242349220.30642@mail.ewheeler.net
-
-Replace lock_page() with trylock_page() and skip the page if we failed to
-lock it.  We will get to the page on the next scan.
-
-We can test for the PageTransHuge() outside the page lock as we only need
-protection against splitting the page under us.  Holding pin oni the page
-is enough for this.
-
-Link: http://lkml.kernel.org/r/20180316210830.43738-1-kirill.shutemov@linux.intel.com
-Fixes: 779750d20b93 ("shmem: split huge pages beyond i_size under memory pressure")
-Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
-Reported-by: Eric Wheeler <linux-mm@lists.ewheeler.net>
-Acked-by: Michal Hocko <mhocko@suse.com>
-Reviewed-by: Andrew Morton <akpm@linux-foundation.org>
-Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
-Cc: Hugh Dickins <hughd@google.com>
-Cc: <stable@vger.kernel.org>	[4.8+]
-Signed-off-by: Andrew Morton <>
-(cherry-picked from https://git.kernel.org/pub/scm/linux/kernel/git/mhocko/mm.git/commit/?h=since-4.15&id=73eccc61c701ee7b4223aea2079542a712feeea7)
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- mm/shmem.c | 31 ++++++++++++++++++++-----------
- 1 file changed, 20 insertions(+), 11 deletions(-)
-
-diff --git a/mm/shmem.c b/mm/shmem.c
-index 859e4c224b80..2aae929eb90b 100644
--- a/mm/shmem.c
-+++ b/mm/shmem.c
-@@ -483,36 +483,45 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
- 		info = list_entry(pos, struct shmem_inode_info, shrinklist);
- 		inode = &info->vfs_inode;
- 
-		if (nr_to_split && split >= nr_to_split) {
-			iput(inode);
-			continue;
-		}
-+		if (nr_to_split && split >= nr_to_split)
-+			goto leave;
- 
-		page = find_lock_page(inode->i_mapping,
-+		page = find_get_page(inode->i_mapping,
- 				(inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT);
- 		if (!page)
- 			goto drop;
- 
-+		/* No huge page at the end of the file: nothing to split */
- 		if (!PageTransHuge(page)) {
-			unlock_page(page);
- 			put_page(page);
- 			goto drop;
- 		}
- 
-+		/*
-+		 * Leave the inode on the list if we failed to lock
-+		 * the page at this time.
-+		 *
-+		 * Waiting for the lock may lead to deadlock in the
-+		 * reclaim path.
-+		 */
-+		if (!trylock_page(page)) {
-+			put_page(page);
-+			goto leave;
-+		}
-+
- 		ret = split_huge_page(page);
- 		unlock_page(page);
- 		put_page(page);
- 
-		if (ret) {
-			/* split failed: leave it on the list */
-			iput(inode);
-			continue;
-		}
-+		/* If split failed leave the inode on the list */
-+		if (ret)
-+			goto leave;
- 
- 		split++;
- drop:
- 		list_del_init(&info->shrinklist);
- 		removed++;
-+leave:
- 		iput(inode);
- 	}
- 
@@ -1,43 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
-Date: Thu, 15 Mar 2018 18:07:47 +0300
-Subject: [PATCH] mm/thp: Do not wait for lock_page() in deferred_split_scan()
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-deferred_split_scan() gets called from reclaim path. Waiting for page
-lock may lead to deadlock there.
-
-Replace lock_page() with trylock_page() and skip the page if we failed
-to lock it. We will get to the page on the next scan.
-
-Fixes: 9a982250f773 ("thp: introduce deferred_split_huge_page()")
-
-Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
-Acked-by: Michal Hocko <mhocko@suse.com>
-(cherry-picked from https://patchwork.kernel.org/patch/10284703/)
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- mm/huge_memory.c | 4 +++-
- 1 file changed, 3 insertions(+), 1 deletion(-)
-
-diff --git a/mm/huge_memory.c b/mm/huge_memory.c
-index 8b887db33383..5c4093e0be8d 100644
--- a/mm/huge_memory.c
-+++ b/mm/huge_memory.c
-@@ -2621,11 +2621,13 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
- 
- 	list_for_each_safe(pos, next, &list) {
- 		page = list_entry((void *)pos, struct page, mapping);
-		lock_page(page);
-+		if (!trylock_page(page))
-+			goto next;
- 		/* split_huge_page() removes page from list on success */
- 		if (!split_huge_page(page))
- 			split++;
- 		unlock_page(page);
-+next:
- 		put_page(page);
- 	}
- 
@@ -1,46 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: =?UTF-8?q?Fabian=20Gr=C3=BCnbichler?= <f.gruenbichler@proxmox.com>
-Date: Mon, 9 Apr 2018 09:33:25 +0200
-Subject: [PATCH] Revert Ubuntu RETPOLINE checks in kernel Makefile
-MIME-Version: 1.0
-Content-Type: text/plain; charset=UTF-8
-Content-Transfer-Encoding: 8bit
-
-these break builds outside of Ubuntu's packaging.
-
-Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
- scripts/Makefile.build | 8 --------
- 1 file changed, 8 deletions(-)
-
-diff --git a/scripts/Makefile.build b/scripts/Makefile.build
-index d74c3f9f1fa8..436005392047 100644
--- a/scripts/Makefile.build
-+++ b/scripts/Makefile.build
-@@ -282,18 +282,11 @@ objtool_dep = $(objtool_obj)					\
- 	      $(wildcard include/config/orc/unwinder.h		\
- 			 include/config/stack/validation.h)
- 
-ifdef CONFIG_RETPOLINE
-cmd_ubuntu_retpoline = $(CONFIG_SHELL) $(srctree)/scripts/ubuntu-retpoline-extract-one $(@) $(<) "$(filter -m16 %code16gcc.h,$(a_flags))";
-else
-cmd_ubuntu_retpoline =
-endif
-
- define rule_cc_o_c
- 	$(call echo-cmd,checksrc) $(cmd_checksrc)			  \
- 	$(call cmd_and_fixdep,cc_o_c)					  \
- 	$(cmd_modversions_c)						  \
- 	$(call echo-cmd,objtool) $(cmd_objtool)				  \
-	$(call echo-cmd,ubuntu-retpoline) $(cmd_ubuntu_retpoline)	  \
- 	$(call echo-cmd,record_mcount) $(cmd_record_mcount)
- endef
- 
-@@ -301,7 +294,6 @@ define rule_as_o_S
- 	$(call cmd_and_fixdep,as_o_S)					  \
- 	$(cmd_modversions_S)						  \
- 	$(call echo-cmd,objtool) $(cmd_objtool)
-	$(call echo-cmd,ubuntu-retpoline) $(cmd_ubuntu_retpoline)
- endef
- 
- # List module undefined symbols (or empty line if not enabled)
@@ -1,92 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Wolfgang Bumiller <w.bumiller@proxmox.com>
-Date: Mon, 9 Apr 2018 14:56:29 +0200
-Subject: [PATCH] net: fix deadlock while clearing neighbor proxy table
-
-When coming from ndisc_netdev_event() in net/ipv6/ndisc.c,
-neigh_ifdown() is called with &nd_tbl, locking this while
-clearing the proxy neighbor entries when eg. deleting an
-interface. Calling the table's pndisc_destructor() with the
-lock still held, however, can cause a deadlock: When a
-multicast listener is available an IGMP packet of type
-ICMPV6_MGM_REDUCTION may be sent out. When reaching
-ip6_finish_output2(), if no neighbor entry for the target
-address is found, __neigh_create() is called with &nd_tbl,
-which it'll want to lock.
-
-Move the elements into their own list, then unlock the table
-and perform the destruction.
-
-Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=199289
-Fixes: 6fd6ce2056de ("ipv6: Do not depend on rt->n in ip6_finish_output2().")
-Signed-off-by: Wolfgang Bumiller <w.bumiller@proxmox.com>
---
- net/core/neighbour.c | 28 ++++++++++++++++++----------
- 1 file changed, 18 insertions(+), 10 deletions(-)
-
-diff --git a/net/core/neighbour.c b/net/core/neighbour.c
-index d0713627deb6..3b495739bf65 100644
--- a/net/core/neighbour.c
-+++ b/net/core/neighbour.c
-@@ -55,7 +55,8 @@ static void neigh_timer_handler(unsigned long arg);
- static void __neigh_notify(struct neighbour *n, int type, int flags,
- 			   u32 pid);
- static void neigh_update_notify(struct neighbour *neigh, u32 nlmsg_pid);
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev);
-+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
-+				    struct net_device *dev);
- 
- #ifdef CONFIG_PROC_FS
- static const struct file_operations neigh_stat_seq_fops;
-@@ -291,8 +292,7 @@ int neigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
- {
- 	write_lock_bh(&tbl->lock);
- 	neigh_flush_dev(tbl, dev);
-	pneigh_ifdown(tbl, dev);
-	write_unlock_bh(&tbl->lock);
-+	pneigh_ifdown_and_unlock(tbl, dev);
- 
- 	del_timer_sync(&tbl->proxy_timer);
- 	pneigh_queue_purge(&tbl->proxy_queue);
-@@ -681,9 +681,10 @@ int pneigh_delete(struct neigh_table *tbl, struct net *net, const void *pkey,
- 	return -ENOENT;
- }
- 
-static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
-+static int pneigh_ifdown_and_unlock(struct neigh_table *tbl,
-+				    struct net_device *dev)
- {
-	struct pneigh_entry *n, **np;
-+	struct pneigh_entry *n, **np, *freelist = NULL;
- 	u32 h;
- 
- 	for (h = 0; h <= PNEIGH_HASHMASK; h++) {
-@@ -691,16 +692,23 @@ static int pneigh_ifdown(struct neigh_table *tbl, struct net_device *dev)
- 		while ((n = *np) != NULL) {
- 			if (!dev || n->dev == dev) {
- 				*np = n->next;
-				if (tbl->pdestructor)
-					tbl->pdestructor(n);
-				if (n->dev)
-					dev_put(n->dev);
-				kfree(n);
-+				n->next = freelist;
-+				freelist = n;
- 				continue;
- 			}
- 			np = &n->next;
- 		}
- 	}
-+	write_unlock_bh(&tbl->lock);
-+	while ((n = freelist)) {
-+		freelist = n->next;
-+		n->next = NULL;
-+		if (tbl->pdestructor)
-+			tbl->pdestructor(n);
-+		if (n->dev)
-+			dev_put(n->dev);
-+		kfree(n);
-+	}
- 	return -ENOENT;
- }
-