update ABI file for 6.2.16-20-bpo11-pve

(generated with debian/scripts/abi-generate)

Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>

Makefile

@@ -1,12 +1,14 @@
+include /usr/share/dpkg/pkg-info.mk
+
 # also bump pve-kernel-meta if either of MAJ.MIN, PATCHLEVEL or KREL change
 KERNEL_MAJ=6
 KERNEL_MIN=2
-KERNEL_PATCHLEVEL=11
+KERNEL_PATCHLEVEL=16
 # increment KREL if the ABI changes (abicheck target in debian/rules)
 # rebuild packages with new KREL and run 'make abiupdate'
-KREL=2
+KREL=20-bpo11
 
-PKGREL=2
+PKGREL=20~bpo11+1
 
 KERNEL_MAJMIN=$(KERNEL_MAJ).$(KERNEL_MIN)
 KERNEL_VER=$(KERNEL_MAJMIN).$(KERNEL_PATCHLEVEL)
@@ -63,10 +65,15 @@ $(DST_DEB): $(BUILD_DIR).prepared
 	#lintian $(HDR_DEB)
 	lintian $(LINUX_TOOLS_DEB)
 
-dsc: $(DSC)
+dsc:
+	$(MAKE) $(DSC)
+	lintian $(DSC)
+
 $(DSC): $(BUILD_DIR).prepared
 	cd $(BUILD_DIR); dpkg-buildpackage -S -uc -us -d
-	lintian $(DSC)
+
+sbuild: $(DSC)
+	sbuild $(DSC)
 
 $(BUILD_DIR).prepared: $(addsuffix .prepared,$(KERNEL_SRC) $(MODULES) debian)
 	cp -a fwlist-previous $(BUILD_DIR)/
@@ -113,8 +120,9 @@ $(ZFSDIR).prepared: $(ZFSONLINUX_SUBMODULE)
 	touch $(ZFSDIR).prepared
 
 .PHONY: upload
+upload: UPLOAD_DIST ?= $(DEB_DISTRIBUTION)
 upload: $(DEBS)
-	tar cf - $(DEBS)|ssh -X repoman@repo.proxmox.com -- upload --product pve,pmg,pbs --dist bullseye --arch $(ARCH)
+	tar cf - $(DEBS)|ssh -X repoman@repo.proxmox.com -- upload --product pve,pmg,pbs --dist $(UPLOAD_DIST) --arch $(ARCH)
 
 .PHONY: distclean
 distclean: clean

debian/changelog

@@ -1,3 +1,147 @@
+pve-kernel (6.2.16-20~bpo11+1) bullseye-backports; urgency=medium
+
+  * backport to Debian Bullseye based Proxmox projects.
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 01 Dec 2023 15:42:23 +0100
+
+proxmox-kernel-6.2 (6.2.16-20) bookworm; urgency=medium
+
+  * update sources to Ubuntu-6.2.0-39.40
+
+  * update ZFS to 2.1.14
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 01 Dec 2023 14:17:27 +0100
+
+proxmox-kernel-6.2 (6.2.16-19) bookworm; urgency=medium
+
+  * backport exposing FLUSHBYASID when running nested VMs on AMD CPUs to fix
+    nesting of some hyper-visors like VMware Workstation.
+
+  * backport constraining guest-supported xfeatures only at KVM_GET_XSAVE{2}
+    to further improve compatibility for guests w.r.t. live-migration, or live
+    snapshot rollback, to hosts with less (FPU) xfeatures supported.
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 24 Oct 2023 14:07:51 +0200
+
+proxmox-kernel-6.2 (6.2.16-18) bookworm; urgency=medium
+
+  * backport fix for AMD erratum #1485 on Zen4-based CPUs to avoid triggering
+    undefined instruction exceptions when disabling all, or certain security
+    mitigations, like using the "mitigations=off" kernel command line
+    parameter
+
+  * backport ZFS fix to avoid crashes and hangs if used on modern Intel HW
+    like the Xeon Scalable 4th Gen "Sapphire Rapids" CPUs due to a HW bug as
+    per Intel SPR erratum SPR4
+
+ -- Proxmox Support Team <support@proxmox.com>  Wed, 11 Oct 2023 17:05:18 +0200
+
+proxmox-kernel-6.2 (6.2.16-16) bookworm; urgency=medium
+
+  * update sources to Ubuntu-6.2.0-36.36
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 03 Oct 2023 07:42:21 +0200
+
+proxmox-kernel-6.2 (6.2.16-15) bookworm; urgency=medium
+
+  * fix thunderbolt ring-interrupt not being masked on suspend
+
+  * cherry-pick fix to avoid potentially offlining one CPU thread on some EPYC
+    CPUs with a new amd64-microcode package (still in unstable).
+
+  * update ZFS to 2.1.13
+
+ -- Proxmox Support Team <support@proxmox.com>  Thu, 28 Sep 2023 15:53:58 +0200
+
+proxmox-kernel-6.2 (6.2.16-14) bookworm; urgency=medium
+
+  * cherry-pick fix for setting X86_FEATURE_OSXSAVE feature improving
+    performance of some code that tries to live-detect available CPU features,
+    like, e.g., ZFS.
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 19 Sep 2023 10:17:16 +0200
+
+proxmox-kernel-6.2 (6.2.16-13) bookworm; urgency=medium
+
+  * fix #4707: add override parameter for RMRR relaxation
+
+  * backport thunderbolt-net fixes for IPv6 and connection re-establishment
+    after a node got rebooted
+
+  * update sources to Ubuntu-6.2.0-34.34
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 18 Sep 2023 15:31:57 +0200
+
+
+pve-kernel (6.2.16-11~bpo11+2) bullseye; urgency=medium
+
+  * cherry-pick fix for KVM vCPU page-fault loop.
+    Due to to small and signed type used for an memory related sequence
+    counter there was a chance that for long-lived VMs KVM would effectively
+    hang vCPUs due to always thinking page faults are stale, which results in
+    KVM refusing to "fix" faults.
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 04 Sep 2023 16:49:15 +0200
+
+proxmox-kernel-6.2 (6.2.16-12) bookworm; urgency=medium
+
+  * cherry-pick fix for KVM vCPU page-fault loop.
+    Due to too small and signed type used for an memory related sequence
+    counter there was a chance that for long-lived VMs KVM would effectively
+    hang vCPUs due to always thinking page faults are stale, which results in
+    KVM refusing to "fix" faults.
+
+ -- Proxmox Support Team <support@proxmox.com>  Mon, 04 Sep 2023 15:21:22 +0200
+
+pve-kernel (6.2.16-11~bpo11+1) bullseye; urgency=medium
+
+  * Rebuild 6.2.6-11 for Bullseye
+
+  * bump ABI to 6.2.16-11~bpo11
+
+ -- Proxmox Support Team <support@proxmox.com>  Thu, 31 Aug 2023 12:18:44 +0200
+
+pve-kernel (6.2.16-4~bpo11+1) bullseye; urgency=medium
+
+  * Rebuild for bullseye but keep ZFS at 2.1.11 for now.
+
+  * bump ABI to 6.2.16-4~bpo11
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 07 Jul 2023 17:05:59 +0200
+
+pve-kernel (6.2.16-4) bookworm; urgency=medium
+
+  * backport fixes for StackRot (CVE-2023-3269)
+
+ -- Proxmox Support Team <support@proxmox.com>  Fri, 07 Jul 2023 06:22:28 +0200
+
+pve-kernel (6.2.16-3) bookworm; urgency=medium
+
+  * update to Ubuntu-6.2.0-25.25
+
+ -- Proxmox Support Team <support@proxmox.com>  Sat, 17 Jun 2023 07:58:57 +0200
+
+pve-kernel (6.2.16-2) bookworm; urgency=medium
+
+  * update ZFS to 2.1.12
+
+  * bump ABI to 6.2.16-2
+
+  * backport "net/sched: flower: fix possible OOB write in fl_set_geneve_opt()"
+
+  * backport re-adding mdev_set_iommu_device() kABI for support of SRIOV based
+    Nvidia vGPU
+
+ -- Proxmox Support Team <support@proxmox.com>  Tue, 13 Jun 2023 15:30:53 +0200
+
+pve-kernel (6.2.16-1) bookworm; urgency=medium
+
+  * update to Ubuntu-6.2.0-23.23 and pull in stable fixes up to v6.2.16
+
+  * build for Debian 12 Bookworm based releases
+
+ -- Proxmox Support Team <support@proxmox.com>  Sat, 20 May 2023 19:23:34 +0200
+
 pve-kernel (6.2.11-2) bullseye; urgency=medium
 
   * backport "netfilter: nf_tables: deactivate anonymous set from preparation

debian/compat

@@ -1 +0,0 @@
-10

debian/control.in

@@ -7,7 +7,7 @@ Build-Depends: asciidoc-base,
                bc,
                bison,
                cpio,
-               debhelper (>= 10~),
+               debhelper-compat (= 12),
                dh-python,
                dwarves,
                file,
@@ -50,7 +50,7 @@ Section: devel
 Priority: optional
 Architecture: any
 Provides: linux-headers-@KVNAME@-amd64,
-Depends: coreutils | fileutils (>= 4.0), ${misc:Depends},
+Depends: ${misc:Depends},
 Description: Proxmox Kernel Headers
  This package contains the linux kernel headers
 

debian/pve-kernel.postinst.in

@@ -1,6 +1,7 @@
-#!/usr/bin/perl -w
+#!/usr/bin/perl
 
 use strict;
+use warnings;
 
 # Ignore all invocations except when called on to configure.
 exit 0 unless $ARGV[0] =~ /configure/;
@@ -16,10 +17,9 @@ system("depmod $version");
 
 if (-d "/etc/kernel/postinst.d") {
   print STDERR "Examining /etc/kernel/postinst.d.\n";
-  system ("run-parts --verbose --exit-on-error --arg=$version " .
-          "--arg=$imagedir/vmlinuz-$version " .
-          "/etc/kernel/postinst.d") &&
-            die "Failed to process /etc/kernel/postinst.d";
+  system(
+      "run-parts --verbose --exit-on-error --arg=$version --arg=$imagedir/vmlinuz-$version /etc/kernel/postinst.d"
+  ) && die "Failed to process /etc/kernel/postinst.d";
 }
 
 exit 0

debian/pve-kernel.postrm.in

@@ -1,6 +1,7 @@
-#!/usr/bin/perl -w
+#!/usr/bin/perl
 
 use strict;
+use warnings;
 
 # Ignore all 'upgrade' invocations .
 exit 0 if $ARGV[0] =~ /upgrade/;
@@ -11,10 +12,9 @@ my $version = "@@KVNAME@@";
 
 if (-d "/etc/kernel/postrm.d") {
   print STDERR "Examining /etc/kernel/postrm.d.\n";
-  system ("run-parts --verbose --exit-on-error --arg=$version " .
-          "--arg=$imagedir/vmlinuz-$version " .
-          "/etc/kernel/postrm.d") &&
-            die "Failed to process /etc/kernel/postrm.d";
+  system (
+      "run-parts --verbose --exit-on-error --arg=$version --arg=$imagedir/vmlinuz-$version /etc/kernel/postrm.d"
+  ) && die "Failed to process /etc/kernel/postrm.d";
 }
 
 unlink "$imagedir/initrd.img-$version";
@@ -25,15 +25,15 @@ unlink "/var/lib/initramfs-tools/$version";
 exit 0 unless $ARGV[0] =~ /purge/;
 
 my @files_to_remove = qw{
-                         modules.dep modules.isapnpmap modules.pcimap
-                         modules.usbmap modules.parportmap
-                         modules.generic_string modules.ieee1394map
-                         modules.ieee1394map modules.pnpbiosmap
-                         modules.alias modules.ccwmap modules.inputmap
-                         modules.symbols modules.ofmap
-                         modules.seriomap modules.*.bin
-			 modules.softdep modules.devname
-                       };
+    modules.dep modules.isapnpmap modules.pcimap
+    modules.usbmap modules.parportmap
+    modules.generic_string modules.ieee1394map
+    modules.ieee1394map modules.pnpbiosmap
+    modules.alias modules.ccwmap modules.inputmap
+    modules.symbols modules.ofmap
+    modules.seriomap modules.*.bin
+    modules.softdep modules.devname
+};
 
 foreach my $extra_file (@files_to_remove) {
     for (glob("/lib/modules/$version/$extra_file")) {

debian/pve-kernel.prerm.in

@@ -1,6 +1,7 @@
-#!/usr/bin/perl -w
+#!/usr/bin/perl
 
 use strict;
+use warnings;
 
 # Ignore all invocations uxcept when called on to remove
 exit 0 unless ($ARGV[0] && $ARGV[0] =~ /remove/) ;
@@ -14,10 +15,9 @@ my $version = "@@KVNAME@@";
 
 if (-d "/etc/kernel/prerm.d") {
   print STDERR "Examining /etc/kernel/prerm.d.\n";
-  system ("run-parts --verbose --exit-on-error --arg=$version " . 
-          "--arg=$imagedir/vmlinuz-$version " .
-          "/etc/kernel/prerm.d") &&
-	  die "Failed to process /etc/kernel/prerm.d";
+  system(
+      "run-parts --verbose --exit-on-error --arg=$version --arg=$imagedir/vmlinuz-$version /etc/kernel/prerm.d"
+  ) && die "Failed to process /etc/kernel/prerm.d";
 }
 
 exit 0

debian/scripts/abi-check

@@ -1,4 +1,7 @@
-#!/usr/bin/perl -w
+#!/usr/bin/perl
+
+use strict;
+use warnings;
 
 my $abinew = shift;
 my $abiold = shift;
@@ -22,30 +25,30 @@ my $count;
 print "II: Checking ABI...\n";
 
 if ($skipabi) {
-	print "WW: Explicitly asked to ignore ABI, running in no-fail mode\n";
-	$fail_exit = 0;
-	$abiskip = 1;
-	$EE = "WW:";
+    print "WW: Explicitly asked to ignore ABI, running in no-fail mode\n";
+    $fail_exit = 0;
+    $abiskip = 1;
+    $EE = "WW:";
 }
 
 if ($prev_abistr ne $abistr) {
-	print "II: Different ABI's, running in no-fail mode\n";
-	$fail_exit = 0;
-	$EE = "WW:";
+    print "II: Different ABI's, running in no-fail mode\n";
+    $fail_exit = 0;
+    $EE = "WW:";
 }
 
 if (not -f "$abinew" or not -f "$abiold") {
-	print "EE: Previous or current ABI file missing!\n";
-	print "    $abinew\n" if not -f "$abinew";
-	print "    $abiold\n" if not -f "$abiold";
+    print "EE: Previous or current ABI file missing!\n";
+    print "    $abinew\n" if not -f "$abinew";
+    print "    $abiold\n" if not -f "$abiold";
 
-	# Exit if the ABI files are missing, but return status based on whether
-	# skip ABI was indicated.
-	if ("$abiskip" eq "1") {
-		exit(0);
-	} else {
-		exit(1);
-	}
+    # Exit if the ABI files are missing, but return status based on whether
+    # skip ABI was indicated.
+    if ("$abiskip" eq "1") {
+	exit(0);
+    } else {
+	exit(1);
+    }
 }
 
 my %symbols;
@@ -57,101 +60,97 @@ my %module_syms;
 my $ignore = 0;
 print "    Reading symbols/modules to ignore...";
 
-for $file ("abi-blacklist") {
-	if (-f $file) {
-		open(IGNORE, "< $file") or
-			die "Could not open $file";
-		while (<IGNORE>) {
-			chomp;
-			if ($_ =~ m/M: (.*)/) {
-				$modules_ignore{$1} = 1;
-			} else {
-				$symbols_ignore{$_} = 1;
-			}
-			$ignore++;
-		}
-		close(IGNORE);
+for my $file ("abi-blacklist") {
+    next if !-f $file;
+    open(my $IGNORE_FH, '<', $file) or die "Could not open $file - $!";
+
+    while (<$IGNORE_FH>) {
+	chomp;
+	if ($_ =~ m/M: (.*)/) {
+	    $modules_ignore{$1} = 1;
+	} else {
+	    $symbols_ignore{$_} = 1;
 	}
+	$ignore++;
+    }
+    close($IGNORE_FH);
 }
 print "read $ignore symbols/modules.\n";
 
 sub is_ignored($$) {
-	my ($mod, $sym) = @_;
+    my ($mod, $sym) = @_;
 
-	die "Missing module name in is_ignored()" if not defined($mod);
-	die "Missing symbol name in is_ignored()" if not defined($sym);
+    die "Missing module name in is_ignored()" if not defined($mod);
+    die "Missing symbol name in is_ignored()" if not defined($sym);
 
-	if (defined($symbols_ignore{$sym}) or defined($modules_ignore{$mod})) {
-		return 1;
-	}
-	return 0;
+    if (defined($symbols_ignore{$sym}) or defined($modules_ignore{$mod})) {
+	return 1;
+    }
+    return 0;
 }
 
 # Read new syms first
 print "    Reading new symbols ($abistr)...";
 $count = 0;
-open(NEW, "< $abinew") or
-	die "Could not open $abinew";
-while (<NEW>) {
-	chomp;
-	m/^(\S+)\s(.+)\s(0x[0-9a-f]+)\s(.+)$/;
-	$symbols{$4}{'type'} = $1;
-	$symbols{$4}{'loc'} = $2;
-	$symbols{$4}{'hash'} = $3;
-	$module_syms{$2} = 0;
-	$count++;
+open(my $NEW_FH, '<', $abinew) or die "Could not open $abinew - $!";
+while (<$NEW_FH>) {
+    chomp;
+    m/^(\S+)\s(.+)\s(0x[0-9a-f]+)\s(.+)$/;
+    $symbols{$4}{'type'} = $1;
+    $symbols{$4}{'loc'} = $2;
+    $symbols{$4}{'hash'} = $3;
+    $module_syms{$2} = 0;
+    $count++;
 }
-close(NEW);
+close($NEW_FH);
 print "read $count symbols.\n";
 
 # Now the old symbols, checking for missing ones
 print "    Reading old symbols...";
 $count = 0;
-open(OLD, "< $abiold") or
-	die "Could not open $abiold";
-while (<OLD>) {
-	chomp;
-	m/^(\S+)\s(.+)\s(0x[0-9a-f]+)\s(.+)$/;
-	$symbols{$4}{'old_type'} = $1;
-	$symbols{$4}{'old_loc'} = $2;
-	$symbols{$4}{'old_hash'} = $3;
-	$count++;
+open(my $OLD_FH, '<', $abiold) or die "Could not open $abiold - $!";
+while (<$OLD_FH>) {
+    chomp;
+    m/^(\S+)\s(.+)\s(0x[0-9a-f]+)\s(.+)$/;
+    $symbols{$4}{'old_type'} = $1;
+    $symbols{$4}{'old_loc'} = $2;
+    $symbols{$4}{'old_hash'} = $3;
+    $count++;
 }
-close(OLD);
+close($OLD_FH);
 
 print "read $count symbols.\n";
 
 print "II: Checking for missing symbols in new ABI...";
 $count = 0;
-foreach $sym (keys(%symbols)) {
-	if (!defined($symbols{$sym}{'type'})) {
-		print "\n" if not $count;
-		printf("    MISS : %s%s\n", $sym,
-			is_ignored($symbols{$sym}{'old_loc'}, $sym) ? " (ignored)" : "");
-		$count++ if !is_ignored($symbols{$sym}{'old_loc'}, $sym);
-	}
+for my $sym (keys(%symbols)) {
+    if (!defined($symbols{$sym}{'type'})) {
+	print "\n" if not $count;
+	printf("    MISS : %s%s\n", $sym, is_ignored($symbols{$sym}{'old_loc'}, $sym) ? " (ignored)" : "");
+	$count++ if !is_ignored($symbols{$sym}{'old_loc'}, $sym);
+    }
 }
 print "    " if $count;
 print "found $count missing symbols\n";
 if ($count) {
-	print "$EE Symbols gone missing (what did you do!?!)\n";
-	$errors++;
+    print "$EE Symbols gone missing (what did you do!?!)\n";
+    $errors++;
 }
 
 
 print "II: Checking for new symbols in new ABI...";
 $count = 0;
-foreach $sym (keys(%symbols)) {
-	if (!defined($symbols{$sym}{'old_type'})) {
-		print "\n" if not $count;
-		print "    NEW : $sym\n";
-		$count++;
-	}
+for my $sym (keys(%symbols)) {
+    if (!defined($symbols{$sym}{'old_type'})) {
+	print "\n" if not $count;
+	print "    NEW : $sym\n";
+	$count++;
+    }
 }
 print "    " if $count;
 print "found $count new symbols\n";
 if ($count) {
-	print "WW: Found new symbols. Not recommended unless ABI was bumped\n";
+    print "WW: Found new symbols. Not recommended unless ABI was bumped\n";
 }
 
 print "II: Checking for changes to ABI...\n";
@@ -159,37 +158,34 @@ $count = 0;
 my $moved = 0;
 my $changed_type = 0;
 my $changed_hash = 0;
-foreach $sym (keys(%symbols)) {
-	if (!defined($symbols{$sym}{'old_type'}) or
-	    !defined($symbols{$sym}{'type'})) {
-		next;
-	}
+for my $sym (keys(%symbols)) {
+    if (!defined($symbols{$sym}{'old_type'}) or !defined($symbols{$sym}{'type'})) {
+	next;
+    }
 
-	# Changes in location don't hurt us, but log it anyway
-	if ($symbols{$sym}{'loc'} ne $symbols{$sym}{'old_loc'}) {
-		printf("    MOVE : %-40s : %s => %s\n", $sym, $symbols{$sym}{'old_loc'},
-			$symbols{$sym}{'loc'});
-		$moved++;
-	}
+    # Changes in location don't hurt us, but log it anyway
+    if ($symbols{$sym}{'loc'} ne $symbols{$sym}{'old_loc'}) {
+	printf("    MOVE : %-40s : %s => %s\n", $sym, $symbols{$sym}{'old_loc'}, $symbols{$sym}{'loc'});
+	$moved++;
+    }
 
-	# Changes to export type are only bad if new type isn't
-	# EXPORT_SYMBOL. Changing things to GPL are bad.
-	if ($symbols{$sym}{'type'} ne $symbols{$sym}{'old_type'}) {
-		printf("    TYPE : %-40s : %s => %s%s\n", $sym, $symbols{$sym}{'old_type'}.
-			$symbols{$sym}{'type'}, is_ignored($symbols{$sym}{'loc'}, $sym)
-			? " (ignored)" : "");
-		$changed_type++ if $symbols{$sym}{'type'} ne "EXPORT_SYMBOL"
-			and !is_ignored($symbols{$sym}{'loc'}, $sym);
-	}
+    # Changes to export type are only bad if new type isn't
+    # EXPORT_SYMBOL. Changing things to GPL are bad.
+    if ($symbols{$sym}{'type'} ne $symbols{$sym}{'old_type'}) {
+	printf("    TYPE : %-40s : %s => %s%s\n", $sym, $symbols{$sym}{'old_type'}.
+	    $symbols{$sym}{'type'}, is_ignored($symbols{$sym}{'loc'}, $sym)
+	    ? " (ignored)" : "");
+	$changed_type++ if $symbols{$sym}{'type'} ne "EXPORT_SYMBOL" and !is_ignored($symbols{$sym}{'loc'}, $sym);
+    }
 
-	# Changes to the hash are always bad
-	if ($symbols{$sym}{'hash'} ne $symbols{$sym}{'old_hash'}) {
-		printf("    HASH : %-40s : %s => %s%s\n", $sym, $symbols{$sym}{'old_hash'},
-			$symbols{$sym}{'hash'}, is_ignored($symbols{$sym}{'loc'}, $sym)
-			? " (ignored)" : "");
-		$changed_hash++ if !is_ignored($symbols{$sym}{'loc'}, $sym);
-		$module_syms{$symbols{$sym}{'loc'}}++;
-	}
+    # Changes to the hash are always bad
+    if ($symbols{$sym}{'hash'} ne $symbols{$sym}{'old_hash'}) {
+	printf("    HASH : %-40s : %s => %s%s\n", $sym, $symbols{$sym}{'old_hash'},
+	    $symbols{$sym}{'hash'}, is_ignored($symbols{$sym}{'loc'}, $sym)
+	    ? " (ignored)" : "");
+	$changed_hash++ if !is_ignored($symbols{$sym}{'loc'}, $sym);
+	$module_syms{$symbols{$sym}{'loc'}}++;
+    }
 }
 
 print "WW: $moved symbols changed location\n" if $moved;
@@ -198,17 +194,17 @@ print "$EE $changed_hash symbols changed hash and weren't ignored\n" if $changed
 
 $errors++ if $changed_hash or $changed_type;
 if ($changed_hash) {
-	print "II: Module hash change summary...\n";
-	foreach $mod (sort { $module_syms{$b} <=> $module_syms{$a} } keys %module_syms) {
-		next if ! $module_syms{$mod};
-		printf("    %-40s: %d\n", $mod, $module_syms{$mod});
-	}
+    print "II: Module hash change summary...\n";
+    for my $mod (sort { $module_syms{$b} <=> $module_syms{$a} } keys %module_syms) {
+	next if ! $module_syms{$mod};
+	printf("    %-40s: %d\n", $mod, $module_syms{$mod});
+    }
 }
 
 print "II: Done\n";
 
 if ($errors) {
-	exit($fail_exit);
+    exit($fail_exit);
 } else {
-	exit(0);
+    exit(0);
 }

debian/scripts/abi-generate

@@ -1,8 +1,11 @@
-#!/usr/bin/perl -w
+#!/usr/bin/perl
 
-use PVE::Tools;
+use strict;
+use warnings;
 
-use IO::File;
+use PVE::Tools ();
+
+use IO::File ();
 
 sub usage {
     die "USAGE: $0 INFILE OUTFILE [ABI INFILE-IS-DEB]\n";

debian/scripts/find-firmware.pl

@@ -1,6 +1,7 @@
-#!/usr/bin/perl -w
+#!/usr/bin/perl
 
 use strict;
+use warnings;
 
 my $dir = shift;
 
@@ -12,21 +13,21 @@ warn "\n\nNOTE: strange directory name: $dir\n\n" if $dir !~ m|^(.*/)?(\d+.\d+.\
 
 my $apiver = $2;
 
-open(TMP, "find '$dir' -name '*.ko'|");
-while (defined(my $fn = <TMP>)) {
+open(my $FIND_KO_FH, "find '$dir' -name '*.ko'|");
+while (defined(my $fn = <$FIND_KO_FH>)) {
     chomp $fn;
     my $relfn = $fn;
     $relfn =~ s|^$dir/*||;
 
     my $cmd = "/sbin/modinfo -F firmware '$fn'";
-    open(MOD, "$cmd|");
-    while (defined(my $fw = <MOD>)) {
+    open(my $MOD_FH, "$cmd|");
+    while (defined(my $fw = <$MOD_FH>)) {
 	chomp $fw;
 	print "$fw $relfn\n";
     }
-    close(MOD);
+    close($MOD_FH);
 
 }
-close TMP;
+close($FIND_KO_FH);
 
 exit 0;

patches/kernel/0001-Make-mkcompile_h-accept-an-alternate-timestamp-strin.patch

@@ -21,7 +21,7 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 1 insertion(+), 1 deletion(-)
 
 diff --git a/init/Makefile b/init/Makefile
-index 26de459006c4..3157d9c79901 100644
+index ec557ada3c12..72095034f338 100644
 --- a/init/Makefile
 +++ b/init/Makefile
 @@ -29,7 +29,7 @@ preempt-flag-$(CONFIG_PREEMPT_DYNAMIC)	:= PREEMPT_DYNAMIC

patches/kernel/0004-pci-Enable-overrides-for-missing-ACS-capabilities-4..patch

@@ -55,10 +55,10 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  2 files changed, 111 insertions(+)
 
 diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
-index 2e77ecc12692..eae6fdc4c683 100644
+index 5d47f23514d0..f06df077504b 100644
 --- a/Documentation/admin-guide/kernel-parameters.txt
 +++ b/Documentation/admin-guide/kernel-parameters.txt
-@@ -4188,6 +4188,15 @@
+@@ -4210,6 +4210,15 @@
  				Also, it enforces the PCI Local Bus spec
  				rule that those bits should be 0 in system reset
  				events (useful for kexec/kdump cases).
@@ -75,7 +75,7 @@ index 2e77ecc12692..eae6fdc4c683 100644
  				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 267e6002e29f..fac76ca1d16a 100644
+index 592e1c4ae697..aebf6f412203 100644
 --- a/drivers/pci/quirks.c
 +++ b/drivers/pci/quirks.c
 @@ -194,6 +194,106 @@ static int __init pci_apply_final_quirks(void)
@@ -185,7 +185,7 @@ index 267e6002e29f..fac76ca1d16a 100644
  /*
   * 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
-@@ -4959,6 +5059,8 @@ static const struct pci_dev_acs_enabled {
+@@ -4974,6 +5074,8 @@ 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 },

patches/kernel/0005-kvm-disable-default-dynamic-halt-polling-growth.patch

@@ -13,7 +13,7 @@ Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
  1 file changed, 1 insertion(+), 1 deletion(-)
 
 diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
-index 07aae60288f9..949b7204cf52 100644
+index 73fad57408f7..99ae3e468ce6 100644
 --- a/virt/kvm/kvm_main.c
 +++ b/virt/kvm/kvm_main.c
 @@ -79,7 +79,7 @@ module_param(halt_poll_ns, uint, 0644);

patches/kernel/0006-net-core-downgrade-unregister_netdevice-refcount-lea.patch

@@ -14,10 +14,10 @@ Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
  1 file changed, 1 insertion(+), 1 deletion(-)
 
 diff --git a/net/core/dev.c b/net/core/dev.c
-index fce980d531bd..5079a3851798 100644
+index 555bbe774734..de2e0d0185fc 100644
 --- a/net/core/dev.c
 +++ b/net/core/dev.c
-@@ -10257,7 +10257,7 @@ static struct net_device *netdev_wait_allrefs_any(struct list_head *list)
+@@ -10262,7 +10262,7 @@ 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) {

patches/kernel/0008-kvm-xsave-set-mask-out-PKRU-bit-in-xfeatures-if-vCPU.patch

@@ -0,0 +1,133 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Thomas Lamprecht <t.lamprecht@proxmox.com>
+Date: Fri, 14 Jul 2023 18:10:32 +0200
+Subject: [PATCH] kvm: xsave set: mask-out PKRU bit in xfeatures if vCPU has no
+ support
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Fixes live-migrations & snapshot-rollback of VMs with a restricted
+CPU type (e.g., qemu64) from our 5.15 based kernel (default Proxmox
+VE 7.4) to the 6.2 (and future newer) of Proxmox VE 8.0.
+
+Previous to ad856280ddea ("x86/kvm/fpu: Limit guest user_xfeatures to
+supported bits of XCR0") the PKRU bit of the host could leak into the
+state from the guest, which caused trouble when migrating between
+hosts with different CPUs, i.e., where the source supported it but
+the target did not, causing a general protection fault when the guest
+tried to use a pkru related instruction after the migration.
+
+But the fix, while welcome, caused a temporary out-of-sync state when
+migrating such a VM from a kernel without the fix to a kernel with
+the fix, as it threw of KVM when the CPUID of the guest and most of
+the state doesn't report XSAVE and thus any xfeatures, but PKRU and
+the related state is set as enabled, causing the vCPU to spin at 100%
+without any progress forever.
+
+The fix could be at two sites, either in QEMU or in the kernel, I
+choose the kernel as we have all the info there for a targeted
+heuristic so that we don't have to adapt QEMU and qemu-server, the
+latter even on both sides.
+
+Still, a short summary of the possible fixes and short drawbacks:
+* on QEMU-side either
+  - clear the PKRU state in the migration saved state would be rather
+    complicated to implement as the vCPU is initialised way before we
+    have the saved xfeature state available to check what we'd need
+    to do, plus the user-space only gets a memory blob from ioctl
+    KVM_GET_XSAVE2 that it passes to KVM_SET_XSAVE ioctl, there are
+    no ABI guarantees, and while the struct seem stable for 5.15 to
+    6.5-rc1, that doesn't has to be for future kernels, so off the
+    table.
+  - enforce that the CPUID reports PKU support even if it normally
+    wouldn't. While this works (tested by hard-coding it as POC) it
+    is a) not really nice and b) needs some interaction from
+    qemu-server to enable this flag as otherwise we have no good info
+    to decide when it's OK to do this, which means we need to adapt
+    both PVE 7 and 8's qemu-server and also pve-qemu, workable but
+    not optimal
+
+* on Kernel/KVM-side we can hook into the set XSAVE ioctl specific to
+  the KVM subsystem, which already reduces chance of regression for
+  all other places. There we have access to the union/struct
+  definitions of the saved state and thus can savely cast to that.
+  We also got access to the vCPU's CPUID capabilities, meaning we can
+  check if the XCR0 (first XSAVE Control Register) reports
+  that it support the PKRU feature, and if it does *NOT* but the
+  saved xfeatures register from XSAVE *DOES* report it, we can safely
+  assume that this combination is due to an migration from an older,
+  leaky kernel – and clear the bit in the xfeature register before
+  restoring it to the guest vCPU KVM state, avoiding the confusing
+  situation that made the vCPU spin at 100%.
+  This should be safe to do, as the guest vCPU CPUID never reported
+  support for the PKRU feature, and it's also a relatively niche and
+  newish feature.
+
+If it gains us something we can drop this patch a bit in the future
+Proxmox VE 9 major release, but we should ensure that VMs that where
+started before PVE 8 cannot be directly live-migrated to the release
+that includes that change; so we should rather only drop it if the
+maintenance burden is high.
+
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/kvm/cpuid.c |  6 ++++++
+ arch/x86/kvm/cpuid.h |  2 ++
+ arch/x86/kvm/x86.c   | 13 +++++++++++++
+ 3 files changed, 21 insertions(+)
+
+diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
+index 7ccdf991d18e..61aefeb3fdbc 100644
+--- a/arch/x86/kvm/cpuid.c
++++ b/arch/x86/kvm/cpuid.c
+@@ -251,6 +251,12 @@ static u64 cpuid_get_supported_xcr0(struct kvm_cpuid_entry2 *entries, int nent)
+ 	return (best->eax | ((u64)best->edx << 32)) & kvm_caps.supported_xcr0;
+ }
+ 
++bool vcpu_supports_xsave_pkru(struct kvm_vcpu *vcpu) {
++	u64 guest_supported_xcr0 = cpuid_get_supported_xcr0(
++	    vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
++	return (guest_supported_xcr0 & XFEATURE_MASK_PKRU) != 0;
++}
++
+ static void __kvm_update_cpuid_runtime(struct kvm_vcpu *vcpu, struct kvm_cpuid_entry2 *entries,
+ 				       int nent)
+ {
+diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
+index b1658c0de847..12a02851ff57 100644
+--- a/arch/x86/kvm/cpuid.h
++++ b/arch/x86/kvm/cpuid.h
+@@ -32,6 +32,8 @@ int kvm_vcpu_ioctl_get_cpuid2(struct kvm_vcpu *vcpu,
+ bool kvm_cpuid(struct kvm_vcpu *vcpu, u32 *eax, u32 *ebx,
+ 	       u32 *ecx, u32 *edx, bool exact_only);
+ 
++bool vcpu_supports_xsave_pkru(struct kvm_vcpu *vcpu);
++
+ u32 xstate_required_size(u64 xstate_bv, bool compacted);
+ 
+ int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu);
+diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
+index ee603f4edce1..ff92ff41d5ce 100644
+--- a/arch/x86/kvm/x86.c
++++ b/arch/x86/kvm/x86.c
+@@ -5342,6 +5342,19 @@ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,
+ 	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
+ 		return 0;
+ 
++	if (!vcpu_supports_xsave_pkru(vcpu)) {
++		void *buf = guest_xsave->region;
++		union fpregs_state *ustate = buf;
++		if (ustate->xsave.header.xfeatures & XFEATURE_MASK_PKRU) {
++			printk(
++				KERN_NOTICE "clearing PKRU xfeature bit as vCPU from PID %d"
++				" reports no PKRU support - migration from fpu-leaky kernel?",
++				current->pid
++			);
++			ustate->xsave.header.xfeatures &= ~XFEATURE_MASK_PKRU;
++		}
++	}
++
+ 	return fpu_copy_uabi_to_guest_fpstate(&vcpu->arch.guest_fpu,
+ 					      guest_xsave->region,
+ 					      kvm_caps.supported_xcr0,

patches/kernel/0008-netfilter-nf_tables-deactivate-anonymous-set-from-pr.patch

@@ -1,120 +0,0 @@
-From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
-From: Pablo Neira Ayuso <pablo@netfilter.org>
-Date: Tue, 2 May 2023 10:25:24 +0200
-Subject: [PATCH] netfilter: nf_tables: deactivate anonymous set from
- preparation phase
-
-Toggle deleted anonymous sets as inactive in the next generation, so
-users cannot perform any update on it. Clear the generation bitmask
-in case the transaction is aborted.
-
-The following KASAN splat shows a set element deletion for a bound
-anonymous set that has been already removed in the same transaction.
-
-[   64.921510] ==================================================================
-[   64.923123] BUG: KASAN: wild-memory-access in nf_tables_commit+0xa24/0x1490 [nf_tables]
-[   64.924745] Write of size 8 at addr dead000000000122 by task test/890
-[   64.927903] CPU: 3 PID: 890 Comm: test Not tainted 6.3.0+ #253
-[   64.931120] Call Trace:
-[   64.932699]  <TASK>
-[   64.934292]  dump_stack_lvl+0x33/0x50
-[   64.935908]  ? nf_tables_commit+0xa24/0x1490 [nf_tables]
-[   64.937551]  kasan_report+0xda/0x120
-[   64.939186]  ? nf_tables_commit+0xa24/0x1490 [nf_tables]
-[   64.940814]  nf_tables_commit+0xa24/0x1490 [nf_tables]
-[   64.942452]  ? __kasan_slab_alloc+0x2d/0x60
-[   64.944070]  ? nf_tables_setelem_notify+0x190/0x190 [nf_tables]
-[   64.945710]  ? kasan_set_track+0x21/0x30
-[   64.947323]  nfnetlink_rcv_batch+0x709/0xd90 [nfnetlink]
-[   64.948898]  ? nfnetlink_rcv_msg+0x480/0x480 [nfnetlink]
-
-Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
-Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
----
- include/net/netfilter/nf_tables.h |  1 +
- net/netfilter/nf_tables_api.c     | 12 ++++++++++++
- net/netfilter/nft_dynset.c        |  2 +-
- net/netfilter/nft_lookup.c        |  2 +-
- net/netfilter/nft_objref.c        |  2 +-
- 5 files changed, 16 insertions(+), 3 deletions(-)
-
-diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h
-index 9430128aae99..06815130e861 100644
---- a/include/net/netfilter/nf_tables.h
-+++ b/include/net/netfilter/nf_tables.h
-@@ -619,6 +619,7 @@ struct nft_set_binding {
- };
- 
- enum nft_trans_phase;
-+void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set);
- void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
- 			      struct nft_set_binding *binding,
- 			      enum nft_trans_phase phase);
-diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
-index 6023c9f72cdc..26255c2a6692 100644
---- a/net/netfilter/nf_tables_api.c
-+++ b/net/netfilter/nf_tables_api.c
-@@ -4932,12 +4932,24 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
- 	}
- }
- 
-+void nf_tables_activate_set(const struct nft_ctx *ctx, struct nft_set *set)
-+{
-+	if (nft_set_is_anonymous(set))
-+		nft_clear(ctx->net, set);
-+
-+	set->use++;
-+}
-+EXPORT_SYMBOL_GPL(nf_tables_activate_set);
-+
- void nf_tables_deactivate_set(const struct nft_ctx *ctx, struct nft_set *set,
- 			      struct nft_set_binding *binding,
- 			      enum nft_trans_phase phase)
- {
- 	switch (phase) {
- 	case NFT_TRANS_PREPARE:
-+		if (nft_set_is_anonymous(set))
-+			nft_deactivate_next(ctx->net, set);
-+
- 		set->use--;
- 		return;
- 	case NFT_TRANS_ABORT:
-diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
-index 274579b1696e..bd19c7aec92e 100644
---- a/net/netfilter/nft_dynset.c
-+++ b/net/netfilter/nft_dynset.c
-@@ -342,7 +342,7 @@ static void nft_dynset_activate(const struct nft_ctx *ctx,
- {
- 	struct nft_dynset *priv = nft_expr_priv(expr);
- 
--	priv->set->use++;
-+	nf_tables_activate_set(ctx, priv->set);
- }
- 
- static void nft_dynset_destroy(const struct nft_ctx *ctx,
-diff --git a/net/netfilter/nft_lookup.c b/net/netfilter/nft_lookup.c
-index cae5a6724163..925392bab58a 100644
---- a/net/netfilter/nft_lookup.c
-+++ b/net/netfilter/nft_lookup.c
-@@ -167,7 +167,7 @@ static void nft_lookup_activate(const struct nft_ctx *ctx,
- {
- 	struct nft_lookup *priv = nft_expr_priv(expr);
- 
--	priv->set->use++;
-+	nf_tables_activate_set(ctx, priv->set);
- }
- 
- static void nft_lookup_destroy(const struct nft_ctx *ctx,
-diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c
-index 7b01aa2ef653..d985d361ed8a 100644
---- a/net/netfilter/nft_objref.c
-+++ b/net/netfilter/nft_objref.c
-@@ -185,7 +185,7 @@ static void nft_objref_map_activate(const struct nft_ctx *ctx,
- {
- 	struct nft_objref_map *priv = nft_expr_priv(expr);
- 
--	priv->set->use++;
-+	nf_tables_activate_set(ctx, priv->set);
- }
- 
- static void nft_objref_map_destroy(const struct nft_ctx *ctx,

patches/kernel/0009-allow-opt-in-to-allow-pass-through-on-broken-hardwar.patch

@@ -0,0 +1,41 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: kiler129 <grzegorz@noflash.pl>
+Date: Mon, 18 Sep 2023 15:19:26 +0200
+Subject: [PATCH] allow opt-in to allow pass-through on broken hardware..
+
+adapted from https://github.com/kiler129/relax-intel-rmrr , licensed under MIT or GPL 2.0+
+---
+ drivers/iommu/intel/iommu.c | 6 +++++-
+ 1 file changed, 5 insertions(+), 1 deletion(-)
+
+diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
+index 1c5ba4dbfe78..887667218e3b 100644
+--- a/drivers/iommu/intel/iommu.c
++++ b/drivers/iommu/intel/iommu.c
+@@ -297,6 +297,7 @@ static int dmar_map_gfx = 1;
+ static int dmar_map_ipu = 1;
+ static int intel_iommu_superpage = 1;
+ static int iommu_identity_mapping;
++static int intel_relaxable_rmrr = 0;
+ static int iommu_skip_te_disable;
+ 
+ #define IDENTMAP_GFX		2
+@@ -358,6 +359,9 @@ static int __init intel_iommu_setup(char *str)
+ 		} else if (!strncmp(str, "tboot_noforce", 13)) {
+ 			pr_info("Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
+ 			intel_iommu_tboot_noforce = 1;
++		} else if (!strncmp(str, "relax_rmrr", 10)) {
++			pr_info("Intel-IOMMU: assuming all RMRRs are relaxable. This can lead to instability or data loss\n");
++			intel_relaxable_rmrr = 1;
+ 		} else {
+ 			pr_notice("Unknown option - '%s'\n", str);
+ 		}
+@@ -2538,7 +2542,7 @@ static bool device_rmrr_is_relaxable(struct device *dev)
+ 		return false;
+ 
+ 	pdev = to_pci_dev(dev);
+-	if (IS_USB_DEVICE(pdev) || IS_GFX_DEVICE(pdev))
++	if (intel_relaxable_rmrr || IS_USB_DEVICE(pdev) || IS_GFX_DEVICE(pdev))
+ 		return true;
+ 	else
+ 		return false;

patches/kernel/0010-net-thunderbolt-Fix-TCPv6-GSO-checksum-calculation.patch

@@ -0,0 +1,42 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Mika Westerberg <mika.westerberg@linux.intel.com>
+Date: Wed, 13 Sep 2023 08:26:47 +0300
+Subject: [PATCH] net: thunderbolt: Fix TCPv6 GSO checksum calculation
+
+Alex reported that running ssh over IPv6 does not work with
+Thunderbolt/USB4 networking driver. The reason for that is that driver
+should call skb_is_gso() before calling skb_is_gso_v6(), and it should
+not return false after calculates the checksum successfully. This probably
+was a copy paste error from the original driver where it was done properly.
+
+Reported-by: Alex Balcanquall <alex@alexbal.com>
+Fixes: e69b6c02b4c3 ("net: Add support for networking over Thunderbolt cable")
+Cc: stable@vger.kernel.org
+Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
+Reviewed-by: Eric Dumazet <edumazet@google.com>
+Reviewed-by: Jiri Pirko <jiri@nvidia.com>
+Reviewed-by: Jiri Pirko <jiri@nvidia.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ drivers/net/thunderbolt.c | 3 +--
+ 1 file changed, 1 insertion(+), 2 deletions(-)
+
+diff --git a/drivers/net/thunderbolt.c b/drivers/net/thunderbolt.c
+index 990484776f2d..0c554a7a5ce4 100644
+--- a/drivers/net/thunderbolt.c
++++ b/drivers/net/thunderbolt.c
+@@ -1005,12 +1005,11 @@ static bool tbnet_xmit_csum_and_map(struct tbnet *net, struct sk_buff *skb,
+ 		*tucso = ~csum_tcpudp_magic(ip_hdr(skb)->saddr,
+ 					    ip_hdr(skb)->daddr, 0,
+ 					    ip_hdr(skb)->protocol, 0);
+-	} else if (skb_is_gso_v6(skb)) {
++	} else if (skb_is_gso(skb) && skb_is_gso_v6(skb)) {
+ 		tucso = dest + ((void *)&(tcp_hdr(skb)->check) - data);
+ 		*tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,
+ 					  &ipv6_hdr(skb)->daddr, 0,
+ 					  IPPROTO_TCP, 0);
+-		return false;
+ 	} else if (protocol == htons(ETH_P_IPV6)) {
+ 		tucso = dest + skb_checksum_start_offset(skb) + skb->csum_offset;
+ 		*tucso = ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr,

patches/kernel/0011-thunderbolt-Restart-XDomain-discovery-handshake-afte.patch

@@ -0,0 +1,134 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Mika Westerberg <mika.westerberg@linux.intel.com>
+Date: Thu, 7 Sep 2023 16:02:30 +0300
+Subject: [PATCH] thunderbolt: Restart XDomain discovery handshake after
+ failure
+
+Alex reported that after rebooting the other host the peer-to-peer link
+does not come up anymore. The reason for this is that the host that was
+not rebooted tries to send the UUID request only 10 times according to
+the USB4 Inter-Domain spec and gives up if it does not get reply. Then
+when the other side is actually ready it cannot get the link established
+anymore. The USB4 Inter-Domain spec requires that the discovery protocol
+is restarted in that case so implement this now.
+
+Reported-by: Alex Balcanquall <alex@alexbal.com>
+Fixes: 8e1de7042596 ("thunderbolt: Add support for XDomain lane bonding")
+Cc: stable@vger.kernel.org
+Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ drivers/thunderbolt/xdomain.c | 58 +++++++++++++++++++++++++----------
+ 1 file changed, 41 insertions(+), 17 deletions(-)
+
+diff --git a/drivers/thunderbolt/xdomain.c b/drivers/thunderbolt/xdomain.c
+index 3c51e47dd86b..0b17a4d4e9b9 100644
+--- a/drivers/thunderbolt/xdomain.c
++++ b/drivers/thunderbolt/xdomain.c
+@@ -704,6 +704,27 @@ static void update_property_block(struct tb_xdomain *xd)
+ 	mutex_unlock(&xdomain_lock);
+ }
+ 
++static void start_handshake(struct tb_xdomain *xd)
++{
++	xd->state = XDOMAIN_STATE_INIT;
++	queue_delayed_work(xd->tb->wq, &xd->state_work,
++			   msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT));
++}
++
++/* Can be called from state_work */
++static void __stop_handshake(struct tb_xdomain *xd)
++{
++	cancel_delayed_work_sync(&xd->properties_changed_work);
++	xd->properties_changed_retries = 0;
++	xd->state_retries = 0;
++}
++
++static void stop_handshake(struct tb_xdomain *xd)
++{
++	cancel_delayed_work_sync(&xd->state_work);
++	__stop_handshake(xd);
++}
++
+ static void tb_xdp_handle_request(struct work_struct *work)
+ {
+ 	struct xdomain_request_work *xw = container_of(work, typeof(*xw), work);
+@@ -766,6 +787,15 @@ static void tb_xdp_handle_request(struct work_struct *work)
+ 	case UUID_REQUEST:
+ 		tb_dbg(tb, "%llx: received XDomain UUID request\n", route);
+ 		ret = tb_xdp_uuid_response(ctl, route, sequence, uuid);
++		/*
++		 * If we've stopped the discovery with an error such as
++		 * timing out, we will restart the handshake now that we
++		 * received UUID request from the remote host.
++		 */
++		if (!ret && xd && xd->state == XDOMAIN_STATE_ERROR) {
++			dev_dbg(&xd->dev, "restarting handshake\n");
++			start_handshake(xd);
++		}
+ 		break;
+ 
+ 	case LINK_STATE_STATUS_REQUEST:
+@@ -1522,6 +1552,13 @@ static void tb_xdomain_queue_properties_changed(struct tb_xdomain *xd)
+ 			   msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT));
+ }
+ 
++static void tb_xdomain_failed(struct tb_xdomain *xd)
++{
++	xd->state = XDOMAIN_STATE_ERROR;
++	queue_delayed_work(xd->tb->wq, &xd->state_work,
++			   msecs_to_jiffies(XDOMAIN_DEFAULT_TIMEOUT));
++}
++
+ static void tb_xdomain_state_work(struct work_struct *work)
+ {
+ 	struct tb_xdomain *xd = container_of(work, typeof(*xd), state_work.work);
+@@ -1548,7 +1585,7 @@ static void tb_xdomain_state_work(struct work_struct *work)
+ 		if (ret) {
+ 			if (ret == -EAGAIN)
+ 				goto retry_state;
+-			xd->state = XDOMAIN_STATE_ERROR;
++			tb_xdomain_failed(xd);
+ 		} else {
+ 			tb_xdomain_queue_properties_changed(xd);
+ 			if (xd->bonding_possible)
+@@ -1613,7 +1650,7 @@ static void tb_xdomain_state_work(struct work_struct *work)
+ 		if (ret) {
+ 			if (ret == -EAGAIN)
+ 				goto retry_state;
+-			xd->state = XDOMAIN_STATE_ERROR;
++			tb_xdomain_failed(xd);
+ 		} else {
+ 			xd->state = XDOMAIN_STATE_ENUMERATED;
+ 		}
+@@ -1624,6 +1661,8 @@ static void tb_xdomain_state_work(struct work_struct *work)
+ 		break;
+ 
+ 	case XDOMAIN_STATE_ERROR:
++		dev_dbg(&xd->dev, "discovery failed, stopping handshake\n");
++		__stop_handshake(xd);
+ 		break;
+ 
+ 	default:
+@@ -1793,21 +1832,6 @@ static void tb_xdomain_release(struct device *dev)
+ 	kfree(xd);
+ }
+ 
+-static void start_handshake(struct tb_xdomain *xd)
+-{
+-	xd->state = XDOMAIN_STATE_INIT;
+-	queue_delayed_work(xd->tb->wq, &xd->state_work,
+-			   msecs_to_jiffies(XDOMAIN_SHORT_TIMEOUT));
+-}
+-
+-static void stop_handshake(struct tb_xdomain *xd)
+-{
+-	cancel_delayed_work_sync(&xd->properties_changed_work);
+-	cancel_delayed_work_sync(&xd->state_work);
+-	xd->properties_changed_retries = 0;
+-	xd->state_retries = 0;
+-}
+-
+ static int __maybe_unused tb_xdomain_suspend(struct device *dev)
+ {
+ 	stop_handshake(tb_to_xdomain(dev));

patches/kernel/0012-x86-cpu-Fix-AMD-erratum-1485-on-Zen4-based-CPUs.patch

@@ -0,0 +1,72 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: "Borislav Petkov (AMD)" <bp@alien8.de>
+Date: Sat, 7 Oct 2023 12:57:02 +0200
+Subject: [PATCH] x86/cpu: Fix AMD erratum #1485 on Zen4-based CPUs
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+Fix erratum #1485 on Zen4 parts where running with STIBP disabled can
+cause an #UD exception. The performance impact of the fix is negligible.
+
+Reported-by: René Rebe <rene@exactcode.de>
+Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
+Tested-by: René Rebe <rene@exactcode.de>
+Cc: <stable@kernel.org>
+Link: https://lore.kernel.org/r/D99589F4-BC5D-430B-87B2-72C20370CF57@exactcode.com
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/include/asm/msr-index.h | 9 +++++++--
+ arch/x86/kernel/cpu/amd.c        | 8 ++++++++
+ 2 files changed, 15 insertions(+), 2 deletions(-)
+
+diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
+index ebbf80d8b8bd..a79b10e57757 100644
+--- a/arch/x86/include/asm/msr-index.h
++++ b/arch/x86/include/asm/msr-index.h
+@@ -630,12 +630,17 @@
+ /* AMD Last Branch Record MSRs */
+ #define MSR_AMD64_LBR_SELECT			0xc000010e
+ 
+-/* Fam 17h MSRs */
+-#define MSR_F17H_IRPERF			0xc00000e9
++/* Zen4 */
++#define MSR_ZEN4_BP_CFG			0xc001102e
++#define MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT 5
+ 
++/* Zen 2 */
+ #define MSR_ZEN2_SPECTRAL_CHICKEN	0xc00110e3
+ #define MSR_ZEN2_SPECTRAL_CHICKEN_BIT	BIT_ULL(1)
+ 
++/* Fam 17h MSRs */
++#define MSR_F17H_IRPERF			0xc00000e9
++
+ /* Fam 16h MSRs */
+ #define MSR_F16H_L2I_PERF_CTL		0xc0010230
+ #define MSR_F16H_L2I_PERF_CTR		0xc0010231
+diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
+index a608a2b78073..154e9c0c16bd 100644
+--- a/arch/x86/kernel/cpu/amd.c
++++ b/arch/x86/kernel/cpu/amd.c
+@@ -80,6 +80,10 @@ static const int amd_div0[] =
+ 	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x17, 0x00, 0x0, 0x2f, 0xf),
+ 			   AMD_MODEL_RANGE(0x17, 0x50, 0x0, 0x5f, 0xf));
+ 
++static const int amd_erratum_1485[] =
++	AMD_LEGACY_ERRATUM(AMD_MODEL_RANGE(0x19, 0x10, 0x0, 0x1f, 0xf),
++			   AMD_MODEL_RANGE(0x19, 0x60, 0x0, 0xaf, 0xf));
++
+ static bool cpu_has_amd_erratum(struct cpuinfo_x86 *cpu, const int *erratum)
+ {
+ 	int osvw_id = *erratum++;
+@@ -1125,6 +1129,10 @@ static void init_amd(struct cpuinfo_x86 *c)
+ 		pr_notice_once("AMD Zen1 DIV0 bug detected. Disable SMT for full protection.\n");
+ 		setup_force_cpu_bug(X86_BUG_DIV0);
+ 	}
++
++	if (!cpu_has(c, X86_FEATURE_HYPERVISOR) &&
++	     cpu_has_amd_erratum(c, amd_erratum_1485))
++		msr_set_bit(MSR_ZEN4_BP_CFG, MSR_ZEN4_BP_CFG_SHARED_BTB_FIX_BIT);
+ }
+ 
+ #ifdef CONFIG_X86_32

patches/kernel/0013-Revert-nSVM-Check-for-reserved-encodings-of-TLB_CONT.patch

@@ -0,0 +1,46 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Stefan Sterz <s.sterz@proxmox.com>
+Date: Wed, 18 Oct 2023 10:45:45 +0200
+Subject: [PATCH] Revert "nSVM: Check for reserved encodings of TLB_CONTROL in
+ nested VMCB"
+
+This reverts commit 174a921b6975ef959dd82ee9e8844067a62e3ec1.
+
+Signed-off-by: Stefan Sterz <s.sterz@proxmox.com>
+---
+ arch/x86/kvm/svm/nested.c | 15 ---------------
+ 1 file changed, 15 deletions(-)
+
+diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
+index add65dd59756..61a6c0235519 100644
+--- a/arch/x86/kvm/svm/nested.c
++++ b/arch/x86/kvm/svm/nested.c
+@@ -242,18 +242,6 @@ static bool nested_svm_check_bitmap_pa(struct kvm_vcpu *vcpu, u64 pa, u32 size)
+ 	    kvm_vcpu_is_legal_gpa(vcpu, addr + size - 1);
+ }
+ 
+-static bool nested_svm_check_tlb_ctl(struct kvm_vcpu *vcpu, u8 tlb_ctl)
+-{
+-	/* Nested FLUSHBYASID is not supported yet.  */
+-	switch(tlb_ctl) {
+-		case TLB_CONTROL_DO_NOTHING:
+-		case TLB_CONTROL_FLUSH_ALL_ASID:
+-			return true;
+-		default:
+-			return false;
+-	}
+-}
+-
+ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
+ 					 struct vmcb_ctrl_area_cached *control)
+ {
+@@ -273,9 +261,6 @@ static bool __nested_vmcb_check_controls(struct kvm_vcpu *vcpu,
+ 					   IOPM_SIZE)))
+ 		return false;
+ 
+-	if (CC(!nested_svm_check_tlb_ctl(vcpu, control->tlb_ctl)))
+-		return false;
+-
+ 	return true;
+ }
+ 

patches/kernel/0014-KVM-nSVM-Advertise-support-for-flush-by-ASID.patch

@@ -0,0 +1,36 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Sean Christopherson <seanjc@google.com>
+Date: Wed, 18 Oct 2023 12:41:04 -0700
+Subject: [PATCH] KVM: nSVM: Advertise support for flush-by-ASID
+
+Advertise support for FLUSHBYASID when nested SVM is enabled, as KVM can
+always emulate flushing TLB entries for a vmcb12 ASID, e.g. by running L2
+with a new, fresh ASID in vmcb02.  Some modern hypervisors, e.g. VMWare
+Workstation 17, require FLUSHBYASID support and will refuse to run if it's
+not present.
+
+Punt on proper support, as "Honor L1's request to flush an ASID on nested
+VMRUN" is one of the TODO items in the (incomplete) list of issues that
+need to be addressed in order for KVM to NOT do a full TLB flush on every
+nested SVM transition (see nested_svm_transition_tlb_flush()).
+
+Reported-by: Stefan Sterz <s.sterz@proxmox.com>
+Closes: https://lkml.kernel.org/r/b9915c9c-4cf6-051a-2d91-44cc6380f455%40proxmox.com
+Signed-off-by: Sean Christopherson <seanjc@google.com>
+Signed-off-by: Stefan Sterz <s.sterz@proxmox.com>
+---
+ arch/x86/kvm/svm/svm.c | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
+index cf31babfbbb9..99a7e93b2edf 100644
+--- a/arch/x86/kvm/svm/svm.c
++++ b/arch/x86/kvm/svm/svm.c
+@@ -4920,6 +4920,7 @@ static __init void svm_set_cpu_caps(void)
+ 	if (nested) {
+ 		kvm_cpu_cap_set(X86_FEATURE_SVM);
+ 		kvm_cpu_cap_set(X86_FEATURE_VMCBCLEAN);
++		kvm_cpu_cap_set(X86_FEATURE_FLUSHBYASID);
+ 
+ 		if (nrips)
+ 			kvm_cpu_cap_set(X86_FEATURE_NRIPS);

patches/kernel/0015-x86-fpu-Allow-caller-to-constrain-xfeatures-when-cop.patch

@@ -0,0 +1,164 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Sean Christopherson <seanjc@google.com>
+Date: Wed, 27 Sep 2023 17:19:52 -0700
+Subject: [PATCH] x86/fpu: Allow caller to constrain xfeatures when copying to
+ uabi buffer
+
+Plumb an xfeatures mask into __copy_xstate_to_uabi_buf() so that KVM can
+constrain which xfeatures are saved into the userspace buffer without
+having to modify the user_xfeatures field in KVM's guest_fpu state.
+
+KVM's ABI for KVM_GET_XSAVE{2} is that features that are not exposed to
+guest must not show up in the effective xstate_bv field of the buffer.
+Saving only the guest-supported xfeatures allows userspace to load the
+saved state on a different host with a fewer xfeatures, so long as the
+target host supports the xfeatures that are exposed to the guest.
+
+KVM currently sets user_xfeatures directly to restrict KVM_GET_XSAVE{2} to
+the set of guest-supported xfeatures, but doing so broke KVM's historical
+ABI for KVM_SET_XSAVE, which allows userspace to load any xfeatures that
+are supported by the *host*.
+
+Cc: stable@vger.kernel.org
+Signed-off-by: Sean Christopherson <seanjc@google.com>
+Message-Id: <20230928001956.924301-2-seanjc@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+(cherry picked from commit 18164f66e6c59fda15c198b371fa008431efdb22)
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/include/asm/fpu/api.h |  3 ++-
+ arch/x86/kernel/fpu/core.c     |  5 +++--
+ arch/x86/kernel/fpu/xstate.c   |  7 +++++--
+ arch/x86/kernel/fpu/xstate.h   |  3 ++-
+ arch/x86/kvm/x86.c             | 21 +++++++++------------
+ 5 files changed, 21 insertions(+), 18 deletions(-)
+
+diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
+index b475d9a582b8..e829fa4c6788 100644
+--- a/arch/x86/include/asm/fpu/api.h
++++ b/arch/x86/include/asm/fpu/api.h
+@@ -148,7 +148,8 @@ static inline void fpu_update_guest_xfd(struct fpu_guest *guest_fpu, u64 xfd) {
+ static inline void fpu_sync_guest_vmexit_xfd_state(void) { }
+ #endif
+ 
+-extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf, unsigned int size, u32 pkru);
++extern void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
++					   unsigned int size, u64 xfeatures, u32 pkru);
+ extern int fpu_copy_uabi_to_guest_fpstate(struct fpu_guest *gfpu, const void *buf, u64 xcr0, u32 *vpkru);
+ 
+ static inline void fpstate_set_confidential(struct fpu_guest *gfpu)
+diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
+index a083f9ac9e4f..1d190761d00f 100644
+--- a/arch/x86/kernel/fpu/core.c
++++ b/arch/x86/kernel/fpu/core.c
+@@ -369,14 +369,15 @@ int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
+ EXPORT_SYMBOL_GPL(fpu_swap_kvm_fpstate);
+ 
+ void fpu_copy_guest_fpstate_to_uabi(struct fpu_guest *gfpu, void *buf,
+-				    unsigned int size, u32 pkru)
++				    unsigned int size, u64 xfeatures, u32 pkru)
+ {
+ 	struct fpstate *kstate = gfpu->fpstate;
+ 	union fpregs_state *ustate = buf;
+ 	struct membuf mb = { .p = buf, .left = size };
+ 
+ 	if (cpu_feature_enabled(X86_FEATURE_XSAVE)) {
+-		__copy_xstate_to_uabi_buf(mb, kstate, pkru, XSTATE_COPY_XSAVE);
++		__copy_xstate_to_uabi_buf(mb, kstate, xfeatures, pkru,
++					  XSTATE_COPY_XSAVE);
+ 	} else {
+ 		memcpy(&ustate->fxsave, &kstate->regs.fxsave,
+ 		       sizeof(ustate->fxsave));
+diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
+index 1afbc4866b10..463ec0cd0dab 100644
+--- a/arch/x86/kernel/fpu/xstate.c
++++ b/arch/x86/kernel/fpu/xstate.c
+@@ -1053,6 +1053,7 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
+  * __copy_xstate_to_uabi_buf - Copy kernel saved xstate to a UABI buffer
+  * @to:		membuf descriptor
+  * @fpstate:	The fpstate buffer from which to copy
++ * @xfeatures:	The mask of xfeatures to save (XSAVE mode only)
+  * @pkru_val:	The PKRU value to store in the PKRU component
+  * @copy_mode:	The requested copy mode
+  *
+@@ -1063,7 +1064,8 @@ static void copy_feature(bool from_xstate, struct membuf *to, void *xstate,
+  * It supports partial copy but @to.pos always starts from zero.
+  */
+ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
+-			       u32 pkru_val, enum xstate_copy_mode copy_mode)
++			       u64 xfeatures, u32 pkru_val,
++			       enum xstate_copy_mode copy_mode)
+ {
+ 	const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
+ 	struct xregs_state *xinit = &init_fpstate.regs.xsave;
+@@ -1087,7 +1089,7 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
+ 		break;
+ 
+ 	case XSTATE_COPY_XSAVE:
+-		header.xfeatures &= fpstate->user_xfeatures;
++		header.xfeatures &= fpstate->user_xfeatures & xfeatures;
+ 		break;
+ 	}
+ 
+@@ -1189,6 +1191,7 @@ void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
+ 			     enum xstate_copy_mode copy_mode)
+ {
+ 	__copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
++				  tsk->thread.fpu.fpstate->user_xfeatures,
+ 				  tsk->thread.pkru, copy_mode);
+ }
+ 
+diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
+index a4ecb04d8d64..3518fb26d06b 100644
+--- a/arch/x86/kernel/fpu/xstate.h
++++ b/arch/x86/kernel/fpu/xstate.h
+@@ -43,7 +43,8 @@ enum xstate_copy_mode {
+ 
+ struct membuf;
+ extern void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
+-				      u32 pkru_val, enum xstate_copy_mode copy_mode);
++				      u64 xfeatures, u32 pkru_val,
++				      enum xstate_copy_mode copy_mode);
+ extern void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
+ 				    enum xstate_copy_mode mode);
+ extern int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u32 *pkru);
+diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
+index ff92ff41d5ce..a43a950d04cb 100644
+--- a/arch/x86/kvm/x86.c
++++ b/arch/x86/kvm/x86.c
+@@ -5314,26 +5314,23 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
+ 	return 0;
+ }
+ 
+-static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
+-					 struct kvm_xsave *guest_xsave)
++
++static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
++					  u8 *state, unsigned int size)
+ {
+ 	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
+ 		return;
+ 
+-	fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
+-				       guest_xsave->region,
+-				       sizeof(guest_xsave->region),
++	fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size,
++				       vcpu->arch.guest_fpu.fpstate->user_xfeatures,
+ 				       vcpu->arch.pkru);
+ }
+ 
+-static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
+-					  u8 *state, unsigned int size)
++static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,
++					 struct kvm_xsave *guest_xsave)
+ {
+-	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
+-		return;
+-
+-	fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu,
+-				       state, size, vcpu->arch.pkru);
++	return kvm_vcpu_ioctl_x86_get_xsave2(vcpu, (void *)guest_xsave->region,
++					     sizeof(guest_xsave->region));
+ }
+ 
+ static int kvm_vcpu_ioctl_x86_set_xsave(struct kvm_vcpu *vcpu,

patches/kernel/0016-KVM-x86-Constrain-guest-supported-xfeatures-only-at-.patch

@@ -0,0 +1,119 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Sean Christopherson <seanjc@google.com>
+Date: Wed, 27 Sep 2023 17:19:53 -0700
+Subject: [PATCH] KVM: x86: Constrain guest-supported xfeatures only at
+ KVM_GET_XSAVE{2}
+
+Mask off xfeatures that aren't exposed to the guest only when saving guest
+state via KVM_GET_XSAVE{2} instead of modifying user_xfeatures directly.
+Preserving the maximal set of xfeatures in user_xfeatures restores KVM's
+ABI for KVM_SET_XSAVE, which prior to commit ad856280ddea ("x86/kvm/fpu:
+Limit guest user_xfeatures to supported bits of XCR0") allowed userspace
+to load xfeatures that are supported by the host, irrespective of what
+xfeatures are exposed to the guest.
+
+There is no known use case where userspace *intentionally* loads xfeatures
+that aren't exposed to the guest, but the bug fixed by commit ad856280ddea
+was specifically that KVM_GET_SAVE{2} would save xfeatures that weren't
+exposed to the guest, e.g. would lead to userspace unintentionally loading
+guest-unsupported xfeatures when live migrating a VM.
+
+Restricting KVM_SET_XSAVE to guest-supported xfeatures is especially
+problematic for QEMU-based setups, as QEMU has a bug where instead of
+terminating the VM if KVM_SET_XSAVE fails, QEMU instead simply stops
+loading guest state, i.e. resumes the guest after live migration with
+incomplete guest state, and ultimately results in guest data corruption.
+
+Note, letting userspace restore all host-supported xfeatures does not fix
+setups where a VM is migrated from a host *without* commit ad856280ddea,
+to a target with a subset of host-supported xfeatures.  However there is
+no way to safely address that scenario, e.g. KVM could silently drop the
+unsupported features, but that would be a clear violation of KVM's ABI and
+so would require userspace to opt-in, at which point userspace could
+simply be updated to sanitize the to-be-loaded XSAVE state.
+
+Reported-by: Tyler Stachecki <stachecki.tyler@gmail.com>
+Closes: https://lore.kernel.org/all/20230914010003.358162-1-tstachecki@bloomberg.net
+Fixes: ad856280ddea ("x86/kvm/fpu: Limit guest user_xfeatures to supported bits of XCR0")
+Cc: stable@vger.kernel.org
+Cc: Leonardo Bras <leobras@redhat.com>
+Signed-off-by: Sean Christopherson <seanjc@google.com>
+Acked-by: Dave Hansen <dave.hansen@linux.intel.com>
+Message-Id: <20230928001956.924301-3-seanjc@google.com>
+Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+(cherry picked from commit 8647c52e9504c99752a39f1d44f6268f82c40a5c)
+Signed-off-by: Thomas Lamprecht <t.lamprecht@proxmox.com>
+---
+ arch/x86/kernel/fpu/xstate.c |  5 +----
+ arch/x86/kvm/cpuid.c         |  8 --------
+ arch/x86/kvm/x86.c           | 18 ++++++++++++++++--
+ 3 files changed, 17 insertions(+), 14 deletions(-)
+
+diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
+index 463ec0cd0dab..ebe698f8af73 100644
+--- a/arch/x86/kernel/fpu/xstate.c
++++ b/arch/x86/kernel/fpu/xstate.c
+@@ -1543,10 +1543,7 @@ static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
+ 		fpregs_restore_userregs();
+ 
+ 	newfps->xfeatures = curfps->xfeatures | xfeatures;
+-
+-	if (!guest_fpu)
+-		newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
+-
++	newfps->user_xfeatures = curfps->user_xfeatures | xfeatures;
+ 	newfps->xfd = curfps->xfd & ~xfeatures;
+ 
+ 	/* Do the final updates within the locked region */
+diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
+index 61aefeb3fdbc..e5393ee652ba 100644
+--- a/arch/x86/kvm/cpuid.c
++++ b/arch/x86/kvm/cpuid.c
+@@ -350,14 +350,6 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
+ 	vcpu->arch.guest_supported_xcr0 =
+ 		cpuid_get_supported_xcr0(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent);
+ 
+-	/*
+-	 * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if
+-	 * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't
+-	 * supported by the host.
+-	 */
+-	vcpu->arch.guest_fpu.fpstate->user_xfeatures = vcpu->arch.guest_supported_xcr0 |
+-						       XFEATURE_MASK_FPSSE;
+-
+ 	kvm_update_pv_runtime(vcpu);
+ 
+ 	vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu);
+diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
+index a43a950d04cb..a4a44adf7c72 100644
+--- a/arch/x86/kvm/x86.c
++++ b/arch/x86/kvm/x86.c
+@@ -5318,12 +5318,26 @@ static int kvm_vcpu_ioctl_x86_set_debugregs(struct kvm_vcpu *vcpu,
+ static void kvm_vcpu_ioctl_x86_get_xsave2(struct kvm_vcpu *vcpu,
+ 					  u8 *state, unsigned int size)
+ {
++	/*
++	 * Only copy state for features that are enabled for the guest.  The
++	 * state itself isn't problematic, but setting bits in the header for
++	 * features that are supported in *this* host but not exposed to the
++	 * guest can result in KVM_SET_XSAVE failing when live migrating to a
++	 * compatible host without the features that are NOT exposed to the
++	 * guest.
++	 *
++	 * FP+SSE can always be saved/restored via KVM_{G,S}ET_XSAVE, even if
++	 * XSAVE/XCRO are not exposed to the guest, and even if XSAVE isn't
++	 * supported by the host.
++	 */
++	u64 supported_xcr0 = vcpu->arch.guest_supported_xcr0 |
++			     XFEATURE_MASK_FPSSE;
++
+ 	if (fpstate_is_confidential(&vcpu->arch.guest_fpu))
+ 		return;
+ 
+ 	fpu_copy_guest_fpstate_to_uabi(&vcpu->arch.guest_fpu, state, size,
+-				       vcpu->arch.guest_fpu.fpstate->user_xfeatures,
+-				       vcpu->arch.pkru);
++				       supported_xcr0, vcpu->arch.pkru);
+ }
+ 
+ static void kvm_vcpu_ioctl_x86_get_xsave(struct kvm_vcpu *vcpu,

submodules/ubuntu-kernel

@@ -1 +1 @@
-Subproject commit d3bf8f1da09634a8b4e661d022702ead6c0dadfb
+Subproject commit 7afee6a065ac401acfe0624f7e60e9fcd08f903c

submodules/zfsonlinux

@@ -1 +1 @@
-Subproject commit b0c4d8ac0b3c0d7de51130b2fd1f3a63efda832c
+Subproject commit d5320c35ef466d28f470fd92fb8c4ce169a3defe