[Pkg-xen-changes] [xen] 01/36: Import xen_4.4.1.orig.tar.xz
Bastian Blank
waldi at moszumanska.debian.org
Sun Sep 7 09:27:00 UTC 2014
This is an automated email from the git hooks/post-receive script.
waldi pushed a commit to branch develop
in repository xen.
commit 3387be132d526263f246c24d3bbc94767a4eba76
Author: Bastian Blank <waldi at debian.org>
Date: Sun Sep 7 10:59:57 2014 +0200
Import xen_4.4.1.orig.tar.xz
---
Config.mk | 8 +-
MAINTAINERS | 11 +-
config.guess | 258 ++++++++++---------
config.sub | 218 ++++++++++------
docs/misc/xen-command-line.markdown | 8 +
m4/ax_compare_version.m4 | 179 +++++++++++++
stubdom/grub/mini-os.c | 3 +
tools/blktap2/drivers/block-qcow.c | 2 +
tools/configure | 174 +++++++++++++
tools/configure.ac | 7 +
tools/include/Makefile | 9 +-
tools/libxc/xc_dom.h | 8 +
tools/libxc/xc_dom_arm.c | 86 ++++++-
tools/libxc/xc_dom_armzimageloader.c | 42 +--
tools/libxc/xc_dom_core.c | 13 +-
tools/libxc/xc_private.c | 6 +-
tools/libxl/libxl.c | 3 +-
tools/libxl/libxl_arch.h | 11 +-
tools/libxl/libxl_arm.c | 72 +++++-
tools/libxl/libxl_device.c | 3 +-
tools/libxl/libxl_dom.c | 8 +-
tools/libxl/libxl_fork.c | 2 +-
tools/libxl/libxl_json.c | 1 -
tools/libxl/libxl_numa.c | 5 +-
tools/libxl/libxl_save_callout.c | 6 +-
tools/libxl/libxl_utils.c | 5 +-
tools/libxl/libxl_x86.c | 13 +-
tools/pygrub/examples/rhel-7-beta.grub2 | 118 +++++++++
tools/pygrub/src/GrubConf.py | 4 +-
tools/pygrub/src/pygrub | 4 +-
tools/tests/x86_emulator/test_x86_emulator.c | 140 +++++-----
xen/Makefile | 2 +-
xen/arch/arm/Rules.mk | 9 +
xen/arch/arm/arm32/head.S | 13 +-
xen/arch/arm/arm64/head.S | 13 +-
xen/arch/arm/domain.c | 25 +-
xen/arch/arm/domain_build.c | 23 +-
xen/arch/arm/guestcopy.c | 26 +-
xen/arch/arm/kernel.c | 2 +-
xen/arch/arm/p2m.c | 56 ++++
xen/arch/arm/psci.c | 12 +-
xen/arch/arm/time.c | 1 -
xen/arch/arm/traps.c | 366 ++++++++++++++++++++++++---
xen/arch/arm/vgic.c | 11 +-
xen/arch/x86/acpi/boot.c | 2 +
xen/arch/x86/acpi/cpu_idle.c | 6 +
xen/arch/x86/cpu/amd.c | 5 +-
xen/arch/x86/cpu/common.c | 5 +-
xen/arch/x86/cpu/intel.c | 7 +
xen/arch/x86/cpu/mcheck/mce.c | 6 +-
xen/arch/x86/cpu/mcheck/mce_intel.c | 19 +-
xen/arch/x86/cpu/mcheck/mctelem.c | 81 +++---
xen/arch/x86/cpu/mcheck/vmce.c | 4 +
xen/arch/x86/cpu/mwait-idle.c | 4 +-
xen/arch/x86/domain.c | 38 ++-
xen/arch/x86/domctl.c | 82 +++---
xen/arch/x86/efi/runtime.c | 9 +
xen/arch/x86/flushtlb.c | 3 +-
xen/arch/x86/hvm/hvm.c | 60 ++++-
xen/arch/x86/hvm/i8254.c | 3 +-
xen/arch/x86/hvm/io.c | 2 +
xen/arch/x86/hvm/irq.c | 10 +-
xen/arch/x86/hvm/mtrr.c | 85 +++++--
xen/arch/x86/hvm/rtc.c | 77 ++++--
xen/arch/x86/hvm/svm/svm.c | 10 +-
xen/arch/x86/hvm/vmx/vmcs.c | 8 +-
xen/arch/x86/hvm/vmx/vmx.c | 22 +-
xen/arch/x86/hvm/vmx/vpmu_core2.c | 4 +
xen/arch/x86/hvm/vpt.c | 40 ---
xen/arch/x86/i387.c | 17 +-
xen/arch/x86/irq.c | 4 +-
xen/arch/x86/microcode_amd.c | 2 +-
xen/arch/x86/mm.c | 4 +-
xen/arch/x86/mm/hap/hap.c | 9 +-
xen/arch/x86/mm/hap/nested_hap.c | 2 +-
xen/arch/x86/mm/mem_event.c | 32 +++
xen/arch/x86/mm/mem_sharing.c | 17 +-
xen/arch/x86/mm/p2m-pod.c | 6 +-
xen/arch/x86/mm/p2m.c | 47 +++-
xen/arch/x86/mm/shadow/common.c | 8 +-
xen/arch/x86/msi.c | 2 +-
xen/arch/x86/nmi.c | 14 +-
xen/arch/x86/time.c | 16 +-
xen/arch/x86/traps.c | 14 +-
xen/arch/x86/x86_64/compat/traps.c | 14 +-
xen/arch/x86/x86_emulate/x86_emulate.c | 33 ++-
xen/common/compat/multicall.c | 2 +-
xen/common/cpupool.c | 18 +-
xen/common/device_tree.c | 9 +-
xen/common/domain.c | 67 +++--
xen/common/domctl.c | 18 +-
xen/common/event_channel.c | 4 +-
xen/common/kexec.c | 4 +-
xen/common/kimage.c | 1 +
xen/common/lz4/decompress.c | 8 +
xen/common/memory.c | 9 +-
xen/common/multicall.c | 6 +-
xen/common/page_alloc.c | 5 +
xen/common/schedule.c | 3 +-
xen/common/timer.c | 3 +-
xen/common/tmem.c | 2 -
xen/common/trace.c | 2 +-
xen/common/xmalloc_tlsf.c | 5 +-
xen/drivers/acpi/apei/Makefile | 1 +
xen/drivers/acpi/apei/erst.c | 12 +-
xen/drivers/acpi/apei/hest.c | 200 +++++++++++++++
xen/drivers/acpi/tables.c | 6 +
xen/drivers/char/console.c | 4 +-
xen/drivers/passthrough/amd/iommu_map.c | 5 +-
xen/drivers/passthrough/amd/pci_amd_iommu.c | 2 +-
xen/drivers/passthrough/ats.h | 3 +-
xen/drivers/passthrough/iommu.c | 10 +-
xen/drivers/passthrough/pci.c | 228 +++++++++++++++++
xen/drivers/passthrough/vtd/dmar.c | 10 +
xen/drivers/passthrough/vtd/extern.h | 2 +-
xen/drivers/passthrough/vtd/iommu.c | 110 +++++---
xen/drivers/passthrough/vtd/qinval.c | 2 +-
xen/drivers/passthrough/vtd/quirks.c | 124 ++++++++-
xen/drivers/passthrough/vtd/x86/ats.c | 37 ++-
xen/drivers/passthrough/x86/ats.c | 3 +-
xen/drivers/pci/pci.c | 29 ++-
xen/include/acpi/actbl1.h | 8 +
xen/include/acpi/apei.h | 3 +
xen/include/asm-arm/arm32/page.h | 7 +-
xen/include/asm-arm/arm64/page.h | 7 +-
xen/include/asm-arm/arm64/vfp.h | 5 +-
xen/include/asm-arm/bitops.h | 37 +--
xen/include/asm-arm/cpregs.h | 37 ++-
xen/include/asm-arm/domain.h | 3 +
xen/include/asm-arm/mm.h | 7 +-
xen/include/asm-arm/p2m.h | 4 +
xen/include/asm-arm/page.h | 4 +
xen/include/asm-arm/processor.h | 39 ++-
xen/include/asm-arm/sysregs.h | 44 ++++
xen/include/asm-x86/cpufeature.h | 1 +
xen/include/asm-x86/hvm/hvm.h | 31 ++-
xen/include/asm-x86/hvm/vmx/vmcs.h | 2 +
xen/include/asm-x86/hvm/vpt.h | 6 +-
xen/include/asm-x86/i387.h | 1 +
xen/include/asm-x86/mem_event.h | 3 +
xen/include/asm-x86/p2m.h | 4 +-
xen/include/public/arch-arm.h | 3 +-
xen/include/public/xen.h | 10 +-
xen/include/xen/acpi.h | 1 +
xen/include/xen/hvm/iommu.h | 6 -
xen/include/xen/pci.h | 3 +
xen/include/xen/pci_ids.h | 9 +
xen/include/xen/pci_regs.h | 11 +-
xen/include/xen/prefetch.h | 13 +-
xen/include/xen/sched.h | 28 +-
xen/include/xen/trace.h | 2 +-
151 files changed, 3172 insertions(+), 940 deletions(-)
diff --git a/Config.mk b/Config.mk
index eb2c192..c44853f 100644
--- a/Config.mk
+++ b/Config.mk
@@ -234,7 +234,7 @@ QEMU_UPSTREAM_URL ?= git://xenbits.xen.org/qemu-upstream-4.4-testing.git
SEABIOS_UPSTREAM_URL ?= git://xenbits.xen.org/seabios.git
endif
OVMF_UPSTREAM_REVISION ?= 447d264115c476142f884af0be287622cd244423
-QEMU_UPSTREAM_REVISION ?= qemu-xen-4.4.0
+QEMU_UPSTREAM_REVISION ?= qemu-xen-4.4.1
SEABIOS_UPSTREAM_TAG ?= rel-1.7.3.1
# Fri Aug 2 14:12:09 2013 -0400
# Fix bug in CBFS file walking with compressed files.
@@ -246,9 +246,9 @@ ETHERBOOT_NICS ?= rtl8139 8086100e
# CONFIG_QEMU ?= `pwd`/$(XEN_ROOT)/../qemu-xen.git
CONFIG_QEMU ?= $(QEMU_REMOTE)
-QEMU_TAG ?= xen-4.4.0
-# Wed Dec 18 15:25:14 2013 +0000
-# qemu-traditional: Fix build warnings on Wheezy
+QEMU_TAG ?= xen-4.4.1
+# Tue Apr 8 16:50:06 2014 +0000
+# qemu-xen-trad: free all the pirqs for msi/msix when driver unloads
# Short answer -- do not enable this unless you know what you are
# doing and are prepared for some pain.
diff --git a/MAINTAINERS b/MAINTAINERS
index 7757cdd..902c077 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -49,9 +49,14 @@ for inclusion in xen-unstable.
Please see http://wiki.xen.org/wiki/Xen_Maintenance_Releases for more
information.
-Remember to copy the appropriate stable branch maintainer who will be
-listed in this section of the MAINTAINERS file in the appropriate
-branch.
+Remember to copy the stable branch maintainer. The maintainer for this
+branch is:
+
+ Jan Beulich <jbeulich at suse.com>
+
+Tools backport requests should also be copied to:
+
+ Ian Jackson <Ian.Jackson at eu.citrix.com>
Unstable Subsystem Maintainers
==============================
diff --git a/config.guess b/config.guess
index c2246a4..d622a44 100755
--- a/config.guess
+++ b/config.guess
@@ -1,10 +1,10 @@
#! /bin/sh
# Attempt to guess a canonical system name.
# Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999,
-# 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010
-# Free Software Foundation, Inc.
+# 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010,
+# 2011, 2012 Free Software Foundation, Inc.
-timestamp='2009-12-30'
+timestamp='2012-02-10'
# This file is free software; you can redistribute it and/or modify it
# under the terms of the GNU General Public License as published by
@@ -17,9 +17,7 @@ timestamp='2009-12-30'
# General Public License for more details.
#
# You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 51 Franklin Street - Fifth Floor, Boston, MA
-# 02110-1301, USA.
+# along with this program; if not, see <http://www.gnu.org/licenses/>.
#
# As a special exception to the GNU General Public License, if you
# distribute this file as part of a program that contains a
@@ -57,8 +55,8 @@ GNU config.guess ($timestamp)
Originally written by Per Bothner.
Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000,
-2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010 Free
-Software Foundation, Inc.
+2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012
+Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE."
@@ -145,7 +143,7 @@ UNAME_VERSION=`(uname -v) 2>/dev/null` || UNAME_VERSION=unknown
case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
*:NetBSD:*:*)
# NetBSD (nbsd) targets should (where applicable) match one or
- # more of the tupples: *-*-netbsdelf*, *-*-netbsdaout*,
+ # more of the tuples: *-*-netbsdelf*, *-*-netbsdaout*,
# *-*-netbsdecoff* and *-*-netbsd*. For targets that recently
# switched to ELF, *-*-netbsd* would select the old
# object file format. This provides both forward
@@ -181,7 +179,7 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
fi
;;
*)
- os=netbsd
+ os=netbsd
;;
esac
# The OS release
@@ -224,7 +222,7 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
UNAME_RELEASE=`/usr/sbin/sizer -v | awk '{print $3}'`
;;
*5.*)
- UNAME_RELEASE=`/usr/sbin/sizer -v | awk '{print $4}'`
+ UNAME_RELEASE=`/usr/sbin/sizer -v | awk '{print $4}'`
;;
esac
# According to Compaq, /usr/sbin/psrinfo has been available on
@@ -270,7 +268,10 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
# A Xn.n version is an unreleased experimental baselevel.
# 1.2 uses "1.2" for uname -r.
echo ${UNAME_MACHINE}-dec-osf`echo ${UNAME_RELEASE} | sed -e 's/^[PVTX]//' | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'`
- exit ;;
+ # Reset EXIT trap before exiting to avoid spurious non-zero exit code.
+ exitcode=$?
+ trap '' 0
+ exit $exitcode ;;
Alpha\ *:Windows_NT*:*)
# How do we know it's Interix rather than the generic POSIX subsystem?
# Should we change UNAME_MACHINE based on the output of uname instead
@@ -296,7 +297,7 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
echo s390-ibm-zvmoe
exit ;;
*:OS400:*:*)
- echo powerpc-ibm-os400
+ echo powerpc-ibm-os400
exit ;;
arm:RISC*:1.[012]*:*|arm:riscix:1.[012]*:*)
echo arm-acorn-riscix${UNAME_RELEASE}
@@ -395,23 +396,23 @@ case "${UNAME_MACHINE}:${UNAME_SYSTEM}:${UNAME_RELEASE}:${UNAME_VERSION}" in
# MiNT. But MiNT is downward compatible to TOS, so this should
# be no problem.
atarist[e]:*MiNT:*:* | atarist[e]:*mint:*:* | atarist[e]:*TOS:*:*)
- echo m68k-atari-mint${UNAME_RELEASE}
+ echo m68k-atari-mint${UNAME_RELEASE}
exit ;;
atari*:*MiNT:*:* | atari*:*mint:*:* | atarist[e]:*TOS:*:*)
echo m68k-atari-mint${UNAME_RELEASE}
- exit ;;
+ exit ;;
*falcon*:*MiNT:*:* | *falcon*:*mint:*:* | *falcon*:*TOS:*:*)
- echo m68k-atari-mint${UNAME_RELEASE}
+ echo m68k-atari-mint${UNAME_RELEASE}
exit ;;
milan*:*MiNT:*:* | milan*:*mint:*:* | *milan*:*TOS:*:*)
- echo m68k-milan-mint${UNAME_RELEASE}
- exit ;;
+ echo m68k-milan-mint${UNAME_RELEASE}
+ exit ;;
hades*:*MiNT:*:* | hades*:*mint:*:* | *hades*:*TOS:*:*)
- echo m68k-hades-mint${UNAME_RELEASE}
- exit ;;
+ echo m68k-hades-mint${UNAME_RELEASE}
+ exit ;;
*:*MiNT:*:* | *:*mint:*:* | *:*TOS:*:*)
- echo m68k-unknown-mint${UNAME_RELEASE}
- exit ;;
+ echo m68k-unknown-mint${UNAME_RELEASE}
+ exit ;;
m68k:machten:*:*)
echo m68k-apple-machten${UNAME_RELEASE}
exit ;;
@@ -481,8 +482,8 @@ EOF
echo m88k-motorola-sysv3
exit ;;
AViiON:dgux:*:*)
- # DG/UX returns AViiON for all architectures
- UNAME_PROCESSOR=`/usr/bin/uname -p`
+ # DG/UX returns AViiON for all architectures
+ UNAME_PROCESSOR=`/usr/bin/uname -p`
if [ $UNAME_PROCESSOR = mc88100 ] || [ $UNAME_PROCESSOR = mc88110 ]
then
if [ ${TARGET_BINARY_INTERFACE}x = m88kdguxelfx ] || \
@@ -495,7 +496,7 @@ EOF
else
echo i586-dg-dgux${UNAME_RELEASE}
fi
- exit ;;
+ exit ;;
M88*:DolphinOS:*:*) # DolphinOS (SVR3)
echo m88k-dolphin-sysv3
exit ;;
@@ -552,7 +553,7 @@ EOF
echo rs6000-ibm-aix3.2
fi
exit ;;
- *:AIX:*:[456])
+ *:AIX:*:[4567])
IBM_CPU_ID=`/usr/sbin/lsdev -C -c processor -S available | sed 1q | awk '{ print $1 }'`
if /usr/sbin/lsattr -El ${IBM_CPU_ID} | grep ' POWER' >/dev/null 2>&1; then
IBM_ARCH=rs6000
@@ -595,52 +596,52 @@ EOF
9000/[678][0-9][0-9])
if [ -x /usr/bin/getconf ]; then
sc_cpu_version=`/usr/bin/getconf SC_CPU_VERSION 2>/dev/null`
- sc_kernel_bits=`/usr/bin/getconf SC_KERNEL_BITS 2>/dev/null`
- case "${sc_cpu_version}" in
- 523) HP_ARCH="hppa1.0" ;; # CPU_PA_RISC1_0
- 528) HP_ARCH="hppa1.1" ;; # CPU_PA_RISC1_1
- 532) # CPU_PA_RISC2_0
- case "${sc_kernel_bits}" in
- 32) HP_ARCH="hppa2.0n" ;;
- 64) HP_ARCH="hppa2.0w" ;;
+ sc_kernel_bits=`/usr/bin/getconf SC_KERNEL_BITS 2>/dev/null`
+ case "${sc_cpu_version}" in
+ 523) HP_ARCH="hppa1.0" ;; # CPU_PA_RISC1_0
+ 528) HP_ARCH="hppa1.1" ;; # CPU_PA_RISC1_1
+ 532) # CPU_PA_RISC2_0
+ case "${sc_kernel_bits}" in
+ 32) HP_ARCH="hppa2.0n" ;;
+ 64) HP_ARCH="hppa2.0w" ;;
'') HP_ARCH="hppa2.0" ;; # HP-UX 10.20
- esac ;;
- esac
+ esac ;;
+ esac
fi
if [ "${HP_ARCH}" = "" ]; then
eval $set_cc_for_build
- sed 's/^ //' << EOF >$dummy.c
+ sed 's/^ //' << EOF >$dummy.c
- #define _HPUX_SOURCE
- #include <stdlib.h>
- #include <unistd.h>
+ #define _HPUX_SOURCE
+ #include <stdlib.h>
+ #include <unistd.h>
- int main ()
- {
- #if defined(_SC_KERNEL_BITS)
- long bits = sysconf(_SC_KERNEL_BITS);
- #endif
- long cpu = sysconf (_SC_CPU_VERSION);
+ int main ()
+ {
+ #if defined(_SC_KERNEL_BITS)
+ long bits = sysconf(_SC_KERNEL_BITS);
+ #endif
+ long cpu = sysconf (_SC_CPU_VERSION);
- switch (cpu)
- {
- case CPU_PA_RISC1_0: puts ("hppa1.0"); break;
- case CPU_PA_RISC1_1: puts ("hppa1.1"); break;
- case CPU_PA_RISC2_0:
- #if defined(_SC_KERNEL_BITS)
- switch (bits)
- {
- case 64: puts ("hppa2.0w"); break;
- case 32: puts ("hppa2.0n"); break;
- default: puts ("hppa2.0"); break;
- } break;
- #else /* !defined(_SC_KERNEL_BITS) */
- puts ("hppa2.0"); break;
- #endif
- default: puts ("hppa1.0"); break;
- }
- exit (0);
- }
+ switch (cpu)
+ {
+ case CPU_PA_RISC1_0: puts ("hppa1.0"); break;
+ case CPU_PA_RISC1_1: puts ("hppa1.1"); break;
+ case CPU_PA_RISC2_0:
+ #if defined(_SC_KERNEL_BITS)
+ switch (bits)
+ {
+ case 64: puts ("hppa2.0w"); break;
+ case 32: puts ("hppa2.0n"); break;
+ default: puts ("hppa2.0"); break;
+ } break;
+ #else /* !defined(_SC_KERNEL_BITS) */
+ puts ("hppa2.0"); break;
+ #endif
+ default: puts ("hppa1.0"); break;
+ }
+ exit (0);
+ }
EOF
(CCOPTS= $CC_FOR_BUILD -o $dummy $dummy.c 2>/dev/null) && HP_ARCH=`$dummy`
test -z "$HP_ARCH" && HP_ARCH=hppa
@@ -731,22 +732,22 @@ EOF
exit ;;
C1*:ConvexOS:*:* | convex:ConvexOS:C1*:*)
echo c1-convex-bsd
- exit ;;
+ exit ;;
C2*:ConvexOS:*:* | convex:ConvexOS:C2*:*)
if getsysinfo -f scalar_acc
then echo c32-convex-bsd
else echo c2-convex-bsd
fi
- exit ;;
+ exit ;;
C34*:ConvexOS:*:* | convex:ConvexOS:C34*:*)
echo c34-convex-bsd
- exit ;;
+ exit ;;
C38*:ConvexOS:*:* | convex:ConvexOS:C38*:*)
echo c38-convex-bsd
- exit ;;
+ exit ;;
C4*:ConvexOS:*:* | convex:ConvexOS:C4*:*)
echo c4-convex-bsd
- exit ;;
+ exit ;;
CRAY*Y-MP:*:*:*)
echo ymp-cray-unicos${UNAME_RELEASE} | sed -e 's/\.[^.]*$/.X/'
exit ;;
@@ -770,14 +771,14 @@ EOF
exit ;;
F30[01]:UNIX_System_V:*:* | F700:UNIX_System_V:*:*)
FUJITSU_PROC=`uname -m | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz'`
- FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'`
- FUJITSU_REL=`echo ${UNAME_RELEASE} | sed -e 's/ /_/'`
- echo "${FUJITSU_PROC}-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}"
- exit ;;
+ FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'`
+ FUJITSU_REL=`echo ${UNAME_RELEASE} | sed -e 's/ /_/'`
+ echo "${FUJITSU_PROC}-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}"
+ exit ;;
5000:UNIX_System_V:4.*:*)
- FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'`
- FUJITSU_REL=`echo ${UNAME_RELEASE} | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/ /_/'`
- echo "sparc-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}"
+ FUJITSU_SYS=`uname -p | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/\///'`
+ FUJITSU_REL=`echo ${UNAME_RELEASE} | tr 'ABCDEFGHIJKLMNOPQRSTUVWXYZ' 'abcdefghijklmnopqrstuvwxyz' | sed -e 's/ /_/'`
+ echo "sparc-fujitsu-${FUJITSU_SYS}${FUJITSU_REL}"
exit ;;
i*86:BSD/386:*:* | i*86:BSD/OS:*:* | *:Ascend\ Embedded/OS:*:*)
echo ${UNAME_MACHINE}-pc-bsdi${UNAME_RELEASE}
@@ -789,13 +790,12 @@ EOF
echo ${UNAME_MACHINE}-unknown-bsdi${UNAME_RELEASE}
exit ;;
*:FreeBSD:*:*)
- case ${UNAME_MACHINE} in
- pc98)
- echo i386-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` ;;
+ UNAME_PROCESSOR=`/usr/bin/uname -p`
+ case ${UNAME_PROCESSOR} in
amd64)
echo x86_64-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` ;;
*)
- echo ${UNAME_MACHINE}-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` ;;
+ echo ${UNAME_PROCESSOR}-unknown-freebsd`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'` ;;
esac
exit ;;
i*:CYGWIN*:*)
@@ -804,15 +804,18 @@ EOF
*:MINGW*:*)
echo ${UNAME_MACHINE}-pc-mingw32
exit ;;
+ i*:MSYS*:*)
+ echo ${UNAME_MACHINE}-pc-msys
+ exit ;;
i*:windows32*:*)
- # uname -m includes "-pc" on this system.
- echo ${UNAME_MACHINE}-mingw32
+ # uname -m includes "-pc" on this system.
+ echo ${UNAME_MACHINE}-mingw32
exit ;;
i*:PW*:*)
echo ${UNAME_MACHINE}-pc-pw32
exit ;;
*:Interix*:*)
- case ${UNAME_MACHINE} in
+ case ${UNAME_MACHINE} in
x86)
echo i586-pc-interix${UNAME_RELEASE}
exit ;;
@@ -858,6 +861,13 @@ EOF
i*86:Minix:*:*)
echo ${UNAME_MACHINE}-pc-minix
exit ;;
+ aarch64:Linux:*:*)
+ echo ${UNAME_MACHINE}-unknown-linux-gnu
+ exit ;;
+ aarch64_be:Linux:*:*)
+ UNAME_MACHINE=aarch64_be
+ echo ${UNAME_MACHINE}-unknown-linux-gnu
+ exit ;;
alpha:Linux:*:*)
case `sed -n '/^cpu model/s/^.*: \(.*\)/\1/p' < /proc/cpuinfo` in
EV5) UNAME_MACHINE=alphaev5 ;;
@@ -867,7 +877,7 @@ EOF
EV6) UNAME_MACHINE=alphaev6 ;;
EV67) UNAME_MACHINE=alphaev67 ;;
EV68*) UNAME_MACHINE=alphaev68 ;;
- esac
+ esac
objdump --private-headers /bin/sh | grep -q ld.so.1
if test "$?" = 0 ; then LIBC="libc1" ; else LIBC="" ; fi
echo ${UNAME_MACHINE}-unknown-linux-gnu${LIBC}
@@ -879,20 +889,29 @@ EOF
then
echo ${UNAME_MACHINE}-unknown-linux-gnu
else
- echo ${UNAME_MACHINE}-unknown-linux-gnueabi
+ if echo __ARM_PCS_VFP | $CC_FOR_BUILD -E - 2>/dev/null \
+ | grep -q __ARM_PCS_VFP
+ then
+ echo ${UNAME_MACHINE}-unknown-linux-gnueabi
+ else
+ echo ${UNAME_MACHINE}-unknown-linux-gnueabihf
+ fi
fi
exit ;;
avr32*:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-gnu
exit ;;
cris:Linux:*:*)
- echo cris-axis-linux-gnu
+ echo ${UNAME_MACHINE}-axis-linux-gnu
exit ;;
crisv32:Linux:*:*)
- echo crisv32-axis-linux-gnu
+ echo ${UNAME_MACHINE}-axis-linux-gnu
exit ;;
frv:Linux:*:*)
- echo frv-unknown-linux-gnu
+ echo ${UNAME_MACHINE}-unknown-linux-gnu
+ exit ;;
+ hexagon:Linux:*:*)
+ echo ${UNAME_MACHINE}-unknown-linux-gnu
exit ;;
i*86:Linux:*:*)
LIBC=gnu
@@ -934,7 +953,7 @@ EOF
test x"${CPU}" != x && { echo "${CPU}-unknown-linux-gnu"; exit; }
;;
or32:Linux:*:*)
- echo or32-unknown-linux-gnu
+ echo ${UNAME_MACHINE}-unknown-linux-gnu
exit ;;
padre:Linux:*:*)
echo sparc-unknown-linux-gnu
@@ -960,7 +979,7 @@ EOF
echo ${UNAME_MACHINE}-ibm-linux
exit ;;
sh64*:Linux:*:*)
- echo ${UNAME_MACHINE}-unknown-linux-gnu
+ echo ${UNAME_MACHINE}-unknown-linux-gnu
exit ;;
sh*:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-gnu
@@ -968,14 +987,17 @@ EOF
sparc:Linux:*:* | sparc64:Linux:*:*)
echo ${UNAME_MACHINE}-unknown-linux-gnu
exit ;;
+ tile*:Linux:*:*)
+ echo ${UNAME_MACHINE}-unknown-linux-gnu
+ exit ;;
vax:Linux:*:*)
echo ${UNAME_MACHINE}-dec-linux-gnu
exit ;;
x86_64:Linux:*:*)
- echo x86_64-unknown-linux-gnu
+ echo ${UNAME_MACHINE}-unknown-linux-gnu
exit ;;
xtensa*:Linux:*:*)
- echo ${UNAME_MACHINE}-unknown-linux-gnu
+ echo ${UNAME_MACHINE}-unknown-linux-gnu
exit ;;
i*86:DYNIX/ptx:4*:*)
# ptx 4.0 does uname -s correctly, with DYNIX/ptx in there.
@@ -984,11 +1006,11 @@ EOF
echo i386-sequent-sysv4
exit ;;
i*86:UNIX_SV:4.2MP:2.*)
- # Unixware is an offshoot of SVR4, but it has its own version
- # number series starting with 2...
- # I am not positive that other SVR4 systems won't match this,
+ # Unixware is an offshoot of SVR4, but it has its own version
+ # number series starting with 2...
+ # I am not positive that other SVR4 systems won't match this,
# I just have to hope. -- rms.
- # Use sysv4.2uw... so that sysv4* matches it.
+ # Use sysv4.2uw... so that sysv4* matches it.
echo ${UNAME_MACHINE}-pc-sysv4.2uw${UNAME_VERSION}
exit ;;
i*86:OS/2:*:*)
@@ -1020,7 +1042,7 @@ EOF
fi
exit ;;
i*86:*:5:[678]*)
- # UnixWare 7.x, OpenUNIX and OpenServer 6.
+ # UnixWare 7.x, OpenUNIX and OpenServer 6.
case `/bin/uname -X | grep "^Machine"` in
*486*) UNAME_MACHINE=i486 ;;
*Pentium) UNAME_MACHINE=i586 ;;
@@ -1048,13 +1070,13 @@ EOF
exit ;;
pc:*:*:*)
# Left here for compatibility:
- # uname -m prints for DJGPP always 'pc', but it prints nothing about
- # the processor, so we play safe by assuming i586.
+ # uname -m prints for DJGPP always 'pc', but it prints nothing about
+ # the processor, so we play safe by assuming i586.
# Note: whatever this is, it MUST be the same as what config.sub
# prints for the "djgpp" host, or else GDB configury will decide that
# this is a cross-build.
echo i586-pc-msdosdjgpp
- exit ;;
+ exit ;;
Intel:Mach:3*:*)
echo i386-pc-mach3
exit ;;
@@ -1089,8 +1111,8 @@ EOF
/bin/uname -p 2>/dev/null | /bin/grep entium >/dev/null \
&& { echo i586-ncr-sysv4.3${OS_REL}; exit; } ;;
3[34]??:*:4.0:* | 3[34]??,*:*:4.0:*)
- /bin/uname -p 2>/dev/null | grep 86 >/dev/null \
- && { echo i486-ncr-sysv4; exit; } ;;
+ /bin/uname -p 2>/dev/null | grep 86 >/dev/null \
+ && { echo i486-ncr-sysv4; exit; } ;;
NCR*:*:4.2:* | MPRAS*:*:4.2:*)
OS_REL='.3'
test -r /etc/.relid \
@@ -1133,10 +1155,10 @@ EOF
echo ns32k-sni-sysv
fi
exit ;;
- PENTIUM:*:4.0*:*) # Unisys `ClearPath HMP IX 4000' SVR4/MP effort
- # says <Richard.M.Bartel at ccMail.Census.GOV>
- echo i586-unisys-sysv4
- exit ;;
+ PENTIUM:*:4.0*:*) # Unisys `ClearPath HMP IX 4000' SVR4/MP effort
+ # says <Richard.M.Bartel at ccMail.Census.GOV>
+ echo i586-unisys-sysv4
+ exit ;;
*:UNIX_System_V:4*:FTX*)
# From Gerald Hewes <hewes at openmarket.com>.
# How about differentiating between stratus architectures? -djm
@@ -1162,11 +1184,11 @@ EOF
exit ;;
R[34]000:*System_V*:*:* | R4000:UNIX_SYSV:*:* | R*000:UNIX_SV:*:*)
if [ -d /usr/nec ]; then
- echo mips-nec-sysv${UNAME_RELEASE}
+ echo mips-nec-sysv${UNAME_RELEASE}
else
- echo mips-unknown-sysv${UNAME_RELEASE}
+ echo mips-unknown-sysv${UNAME_RELEASE}
fi
- exit ;;
+ exit ;;
BeBox:BeOS:*:*) # BeOS running on hardware made by Be, PPC only.
echo powerpc-be-beos
exit ;;
@@ -1231,6 +1253,9 @@ EOF
*:QNX:*:4*)
echo i386-pc-qnx
exit ;;
+ NEO-?:NONSTOP_KERNEL:*:*)
+ echo neo-tandem-nsk${UNAME_RELEASE}
+ exit ;;
NSE-?:NONSTOP_KERNEL:*:*)
echo nse-tandem-nsk${UNAME_RELEASE}
exit ;;
@@ -1276,13 +1301,13 @@ EOF
echo pdp10-unknown-its
exit ;;
SEI:*:*:SEIUX)
- echo mips-sei-seiux${UNAME_RELEASE}
+ echo mips-sei-seiux${UNAME_RELEASE}
exit ;;
*:DragonFly:*:*)
echo ${UNAME_MACHINE}-unknown-dragonfly`echo ${UNAME_RELEASE}|sed -e 's/[-(].*//'`
exit ;;
*:*VMS:*:*)
- UNAME_MACHINE=`(uname -p) 2>/dev/null`
+ UNAME_MACHINE=`(uname -p) 2>/dev/null`
case "${UNAME_MACHINE}" in
A*) echo alpha-dec-vms ; exit ;;
I*) echo ia64-dec-vms ; exit ;;
@@ -1300,6 +1325,9 @@ EOF
i*86:AROS:*:*)
echo ${UNAME_MACHINE}-pc-aros
exit ;;
+ x86_64:VMkernel:*:*)
+ echo ${UNAME_MACHINE}-unknown-esx
+ exit ;;
esac
#echo '(No uname command or uname output not recognized.)' 1>&2
@@ -1322,11 +1350,11 @@ main ()
#include <sys/param.h>
printf ("m68k-sony-newsos%s\n",
#ifdef NEWSOS4
- "4"
+ "4"
#else
- ""
+ ""
#endif
- ); exit (0);
+ ); exit (0);
#endif
#endif
diff --git a/config.sub b/config.sub
index c2d1257..6205f84 100755
--- a/config.sub
+++ b/config.sub
@@ -1,10 +1,10 @@
#! /bin/sh
# Configuration validation subroutine script.
# Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999,
-# 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010
-# Free Software Foundation, Inc.
+# 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010,
+# 2011, 2012 Free Software Foundation, Inc.
-timestamp='2010-01-22'
+timestamp='2012-04-18'
# This file is (in principle) common to ALL GNU software.
# The presence of a machine in this file suggests that SOME GNU software
@@ -21,9 +21,7 @@ timestamp='2010-01-22'
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
-# along with this program; if not, write to the Free Software
-# Foundation, Inc., 51 Franklin Street - Fifth Floor, Boston, MA
-# 02110-1301, USA.
+# along with this program; if not, see <http://www.gnu.org/licenses/>.
#
# As a special exception to the GNU General Public License, if you
# distribute this file as part of a program that contains a
@@ -76,8 +74,8 @@ version="\
GNU config.sub ($timestamp)
Copyright (C) 1992, 1993, 1994, 1995, 1996, 1997, 1998, 1999, 2000,
-2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010 Free
-Software Foundation, Inc.
+2001, 2002, 2003, 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012
+Free Software Foundation, Inc.
This is free software; see the source for copying conditions. There is NO
warranty; not even for MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE."
@@ -124,13 +122,18 @@ esac
# Here we must recognize all the valid KERNEL-OS combinations.
maybe_os=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\2/'`
case $maybe_os in
- nto-qnx* | linux-gnu* | linux-dietlibc | linux-newlib* | linux-uclibc* | \
- uclinux-uclibc* | uclinux-gnu* | kfreebsd*-gnu* | knetbsd*-gnu* | netbsd*-gnu* | \
+ nto-qnx* | linux-gnu* | linux-android* | linux-dietlibc | linux-newlib* | \
+ linux-uclibc* | uclinux-uclibc* | uclinux-gnu* | kfreebsd*-gnu* | \
+ knetbsd*-gnu* | netbsd*-gnu* | \
kopensolaris*-gnu* | \
storm-chaos* | os2-emx* | rtmk-nova*)
os=-$maybe_os
basic_machine=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\1/'`
;;
+ android-linux)
+ os=-linux-android
+ basic_machine=`echo $1 | sed 's/^\(.*\)-\([^-]*-[^-]*\)$/\1/'`-unknown
+ ;;
*)
basic_machine=`echo $1 | sed 's/-[^-]*$//'`
if [ $basic_machine != $1 ]
@@ -157,8 +160,8 @@ case $os in
os=
basic_machine=$1
;;
- -bluegene*)
- os=-cnk
+ -bluegene*)
+ os=-cnk
;;
-sim | -cisco | -oki | -wec | -winbond)
os=
@@ -174,10 +177,10 @@ case $os in
os=-chorusos
basic_machine=$1
;;
- -chorusrdb)
- os=-chorusrdb
+ -chorusrdb)
+ os=-chorusrdb
basic_machine=$1
- ;;
+ ;;
-hiux*)
os=-hiuxwe2
;;
@@ -222,6 +225,12 @@ case $os in
-isc*)
basic_machine=`echo $1 | sed -e 's/86-.*/86-pc/'`
;;
+ -lynx*178)
+ os=-lynxos178
+ ;;
+ -lynx*5)
+ os=-lynxos5
+ ;;
-lynx*)
os=-lynxos
;;
@@ -246,17 +255,22 @@ case $basic_machine in
# Some are omitted here because they have special meanings below.
1750a | 580 \
| a29k \
+ | aarch64 | aarch64_be \
| alpha | alphaev[4-8] | alphaev56 | alphaev6[78] | alphapca5[67] \
| alpha64 | alpha64ev[4-8] | alpha64ev56 | alpha64ev6[78] | alpha64pca5[67] \
| am33_2.0 \
| arc | arm | arm[bl]e | arme[lb] | armv[2345] | armv[345][lb] | avr | avr32 \
+ | be32 | be64 \
| bfin \
| c4x | clipper \
| d10v | d30v | dlx | dsp16xx \
+ | epiphany \
| fido | fr30 | frv \
| h8300 | h8500 | hppa | hppa1.[01] | hppa2.0 | hppa2.0[nw] | hppa64 \
+ | hexagon \
| i370 | i860 | i960 | ia64 \
| ip2k | iq2000 \
+ | le32 | le64 \
| lm32 \
| m32c | m32r | m32rle | m68000 | m68k | m88k \
| maxq | mb | microblaze | mcore | mep | metag \
@@ -282,29 +296,39 @@ case $basic_machine in
| moxie \
| mt \
| msp430 \
+ | nds32 | nds32le | nds32be \
| nios | nios2 \
| ns16k | ns32k \
+ | open8 \
| or32 \
| pdp10 | pdp11 | pj | pjl \
- | powerpc | powerpc64 | powerpc64le | powerpcle | ppcbe \
+ | powerpc | powerpc64 | powerpc64le | powerpcle \
| pyramid \
- | rx \
+ | rl78 | rx \
| score \
| sh | sh[1234] | sh[24]a | sh[24]aeb | sh[23]e | sh[34]eb | sheb | shbe | shle | sh[1234]le | sh3ele \
| sh64 | sh64le \
| sparc | sparc64 | sparc64b | sparc64v | sparc86x | sparclet | sparclite \
| sparcv8 | sparcv9 | sparcv9b | sparcv9v \
- | spu | strongarm \
- | tahoe | thumb | tic4x | tic80 | tron \
+ | spu \
+ | tahoe | tic4x | tic54x | tic55x | tic6x | tic80 | tron \
| ubicom32 \
- | v850 | v850e \
+ | v850 | v850e | v850e1 | v850e2 | v850es | v850e2v3 \
| we32k \
- | x86 | xc16x | xscale | xscalee[bl] | xstormy16 | xtensa \
+ | x86 | xc16x | xstormy16 | xtensa \
| z8k | z80)
basic_machine=$basic_machine-unknown
;;
- m6811 | m68hc11 | m6812 | m68hc12 | picochip)
- # Motorola 68HC11/12.
+ c54x)
+ basic_machine=tic54x-unknown
+ ;;
+ c55x)
+ basic_machine=tic55x-unknown
+ ;;
+ c6x)
+ basic_machine=tic6x-unknown
+ ;;
+ m6811 | m68hc11 | m6812 | m68hc12 | m68hcs12x | picochip)
basic_machine=$basic_machine-unknown
os=-none
;;
@@ -314,6 +338,21 @@ case $basic_machine in
basic_machine=mt-unknown
;;
+ strongarm | thumb | xscale)
+ basic_machine=arm-unknown
+ ;;
+ xgate)
+ basic_machine=$basic_machine-unknown
+ os=-none
+ ;;
+ xscaleeb)
+ basic_machine=armeb-unknown
+ ;;
+
+ xscaleel)
+ basic_machine=armel-unknown
+ ;;
+
# We use `pc' rather than `unknown'
# because (1) that's what they normally are, and
# (2) the word "unknown" tends to confuse beginning users.
@@ -328,21 +367,25 @@ case $basic_machine in
# Recognize the basic CPU types with company name.
580-* \
| a29k-* \
+ | aarch64-* | aarch64_be-* \
| alpha-* | alphaev[4-8]-* | alphaev56-* | alphaev6[78]-* \
| alpha64-* | alpha64ev[4-8]-* | alpha64ev56-* | alpha64ev6[78]-* \
| alphapca5[67]-* | alpha64pca5[67]-* | arc-* \
| arm-* | armbe-* | armle-* | armeb-* | armv*-* \
| avr-* | avr32-* \
+ | be32-* | be64-* \
| bfin-* | bs2000-* \
- | c[123]* | c30-* | [cjt]90-* | c4x-* | c54x-* | c55x-* | c6x-* \
+ | c[123]* | c30-* | [cjt]90-* | c4x-* \
| clipper-* | craynv-* | cydra-* \
| d10v-* | d30v-* | dlx-* \
| elxsi-* \
| f30[01]-* | f700-* | fido-* | fr30-* | frv-* | fx80-* \
| h8300-* | h8500-* \
| hppa-* | hppa1.[01]-* | hppa2.0-* | hppa2.0[nw]-* | hppa64-* \
+ | hexagon-* \
| i*86-* | i860-* | i960-* | ia64-* \
| ip2k-* | iq2000-* \
+ | le32-* | le64-* \
| lm32-* \
| m32c-* | m32r-* | m32rle-* \
| m68000-* | m680[012346]0-* | m68360-* | m683?2-* | m68k-* \
@@ -368,26 +411,29 @@ case $basic_machine in
| mmix-* \
| mt-* \
| msp430-* \
+ | nds32-* | nds32le-* | nds32be-* \
| nios-* | nios2-* \
| none-* | np1-* | ns16k-* | ns32k-* \
+ | open8-* \
| orion-* \
| pdp10-* | pdp11-* | pj-* | pjl-* | pn-* | power-* \
- | powerpc-* | powerpc64-* | powerpc64le-* | powerpcle-* | ppcbe-* \
+ | powerpc-* | powerpc64-* | powerpc64le-* | powerpcle-* \
| pyramid-* \
- | romp-* | rs6000-* | rx-* \
+ | rl78-* | romp-* | rs6000-* | rx-* \
| sh-* | sh[1234]-* | sh[24]a-* | sh[24]aeb-* | sh[23]e-* | sh[34]eb-* | sheb-* | shbe-* \
| shle-* | sh[1234]le-* | sh3ele-* | sh64-* | sh64le-* \
| sparc-* | sparc64-* | sparc64b-* | sparc64v-* | sparc86x-* | sparclet-* \
| sparclite-* \
- | sparcv8-* | sparcv9-* | sparcv9b-* | sparcv9v-* | strongarm-* | sv1-* | sx?-* \
- | tahoe-* | thumb-* \
+ | sparcv8-* | sparcv9-* | sparcv9b-* | sparcv9v-* | sv1-* | sx?-* \
+ | tahoe-* \
| tic30-* | tic4x-* | tic54x-* | tic55x-* | tic6x-* | tic80-* \
- | tile-* | tilegx-* \
+ | tile*-* \
| tron-* \
| ubicom32-* \
- | v850-* | v850e-* | vax-* \
+ | v850-* | v850e-* | v850e1-* | v850es-* | v850e2-* | v850e2v3-* \
+ | vax-* \
| we32k-* \
- | x86-* | x86_64-* | xc16x-* | xps100-* | xscale-* | xscalee[bl]-* \
+ | x86-* | x86_64-* | xc16x-* | xps100-* \
| xstormy16-* | xtensa*-* \
| ymp-* \
| z8k-* | z80-*)
@@ -412,7 +458,7 @@ case $basic_machine in
basic_machine=a29k-amd
os=-udi
;;
- abacus)
+ abacus)
basic_machine=abacus-unknown
;;
adobe68k)
@@ -482,11 +528,20 @@ case $basic_machine in
basic_machine=powerpc-ibm
os=-cnk
;;
+ c54x-*)
+ basic_machine=tic54x-`echo $basic_machine | sed 's/^[^-]*-//'`
+ ;;
+ c55x-*)
+ basic_machine=tic55x-`echo $basic_machine | sed 's/^[^-]*-//'`
+ ;;
+ c6x-*)
+ basic_machine=tic6x-`echo $basic_machine | sed 's/^[^-]*-//'`
+ ;;
c90)
basic_machine=c90-cray
os=-unicos
;;
- cegcc)
+ cegcc)
basic_machine=arm-unknown
os=-cegcc
;;
@@ -518,7 +573,7 @@ case $basic_machine in
basic_machine=craynv-cray
os=-unicosmp
;;
- cr16)
+ cr16 | cr16-*)
basic_machine=cr16-unknown
os=-elf
;;
@@ -676,7 +731,6 @@ case $basic_machine in
i370-ibm* | ibm*)
basic_machine=i370-ibm
;;
-# I'm not sure what "Sysv32" means. Should this be sysv3.2?
i*86v32)
basic_machine=`echo $1 | sed -e 's/86.*/86-pc/'`
os=-sysv32
@@ -734,7 +788,7 @@ case $basic_machine in
basic_machine=ns32k-utek
os=-sysv
;;
- microblaze)
+ microblaze)
basic_machine=microblaze-xilinx
;;
mingw32)
@@ -773,10 +827,18 @@ case $basic_machine in
ms1-*)
basic_machine=`echo $basic_machine | sed -e 's/ms1-/mt-/'`
;;
+ msys)
+ basic_machine=i386-pc
+ os=-msys
+ ;;
mvs)
basic_machine=i370-ibm
os=-mvs
;;
+ nacl)
+ basic_machine=le32-unknown
+ os=-nacl
+ ;;
ncr3000)
basic_machine=i486-ncr
os=-sysv4
@@ -841,6 +903,12 @@ case $basic_machine in
np1)
basic_machine=np1-gould
;;
+ neo-tandem)
+ basic_machine=neo-tandem
+ ;;
+ nse-tandem)
+ basic_machine=nse-tandem
+ ;;
nsr-tandem)
basic_machine=nsr-tandem
;;
@@ -923,9 +991,10 @@ case $basic_machine in
;;
power) basic_machine=power-ibm
;;
- ppc) basic_machine=powerpc-unknown
+ ppc | ppcbe) basic_machine=powerpc-unknown
;;
- ppc-*) basic_machine=powerpc-`echo $basic_machine | sed 's/^[^-]*-//'`
+ ppc-* | ppcbe-*)
+ basic_machine=powerpc-`echo $basic_machine | sed 's/^[^-]*-//'`
;;
ppcle | powerpclittle | ppc-le | powerpc-little)
basic_machine=powerpcle-unknown
@@ -1019,6 +1088,9 @@ case $basic_machine in
basic_machine=i860-stratus
os=-sysv4
;;
+ strongarm-* | thumb-*)
+ basic_machine=arm-`echo $basic_machine | sed 's/^[^-]*-//'`
+ ;;
sun2)
basic_machine=m68000-sun
;;
@@ -1075,25 +1147,8 @@ case $basic_machine in
basic_machine=t90-cray
os=-unicos
;;
- tic54x | c54x*)
- basic_machine=tic54x-unknown
- os=-coff
- ;;
- tic55x | c55x*)
- basic_machine=tic55x-unknown
- os=-coff
- ;;
- tic6x | c6x*)
- basic_machine=tic6x-unknown
- os=-coff
- ;;
- # This must be matched before tile*.
- tilegx*)
- basic_machine=tilegx-unknown
- os=-linux-gnu
- ;;
tile*)
- basic_machine=tile-unknown
+ basic_machine=$basic_machine-unknown
os=-linux-gnu
;;
tx39)
@@ -1163,6 +1218,9 @@ case $basic_machine in
xps | xps100)
basic_machine=xps100-honeywell
;;
+ xscale-* | xscalee[bl]-*)
+ basic_machine=`echo $basic_machine | sed 's/^xscale/arm/'`
+ ;;
ymp)
basic_machine=ymp-cray
os=-unicos
@@ -1260,11 +1318,11 @@ esac
if [ x"$os" != x"" ]
then
case $os in
- # First match some system type aliases
- # that might get confused with valid system types.
+ # First match some system type aliases
+ # that might get confused with valid system types.
# -solaris* is a basic system type, with this one exception.
- -auroraux)
- os=-auroraux
+ -auroraux)
+ os=-auroraux
;;
-solaris1 | -solaris1.*)
os=`echo $os | sed -e 's|solaris1|sunos4|'`
@@ -1300,8 +1358,9 @@ case $os in
| -ptx* | -coff* | -ecoff* | -winnt* | -domain* | -vsta* \
| -udi* | -eabi* | -lites* | -ieee* | -go32* | -aux* \
| -chorusos* | -chorusrdb* | -cegcc* \
- | -cygwin* | -pe* | -psos* | -moss* | -proelf* | -rtems* \
- | -mingw32* | -linux-gnu* | -linux-newlib* | -linux-uclibc* \
+ | -cygwin* | -msys* | -pe* | -psos* | -moss* | -proelf* | -rtems* \
+ | -mingw32* | -linux-gnu* | -linux-android* \
+ | -linux-newlib* | -linux-uclibc* \
| -uxpv* | -beos* | -mpeix* | -udk* \
| -interix* | -uwin* | -mks* | -rhapsody* | -darwin* | -opened* \
| -openstep* | -oskit* | -conix* | -pw32* | -nonstopux* \
@@ -1348,7 +1407,7 @@ case $os in
-opened*)
os=-openedition
;;
- -os400*)
+ -os400*)
os=-os400
;;
-wince*)
@@ -1397,7 +1456,7 @@ case $os in
-sinix*)
os=-sysv4
;;
- -tpf*)
+ -tpf*)
os=-tpf
;;
-triton*)
@@ -1442,8 +1501,8 @@ case $os in
-dicos*)
os=-dicos
;;
- -nacl*)
- ;;
+ -nacl*)
+ ;;
-none)
;;
*)
@@ -1466,10 +1525,10 @@ else
# system, and we'll never get to this point.
case $basic_machine in
- score-*)
+ score-*)
os=-elf
;;
- spu-*)
+ spu-*)
os=-elf
;;
*-acorn)
@@ -1481,8 +1540,20 @@ case $basic_machine in
arm*-semi)
os=-aout
;;
- c4x-* | tic4x-*)
- os=-coff
+ c4x-* | tic4x-*)
+ os=-coff
+ ;;
+ hexagon-*)
+ os=-elf
+ ;;
+ tic54x-*)
+ os=-coff
+ ;;
+ tic55x-*)
+ os=-coff
+ ;;
+ tic6x-*)
+ os=-coff
;;
# This must come before the *-dec entry.
pdp10-*)
@@ -1502,14 +1573,11 @@ case $basic_machine in
;;
m68000-sun)
os=-sunos3
- # This also exists in the configure program, but was not the
- # default.
- # os=-sunos4
;;
m68*-cisco)
os=-aout
;;
- mep-*)
+ mep-*)
os=-elf
;;
mips*-cisco)
@@ -1536,7 +1604,7 @@ case $basic_machine in
*-ibm)
os=-aix
;;
- *-knuth)
+ *-knuth)
os=-mmixware
;;
*-wec)
diff --git a/docs/misc/xen-command-line.markdown b/docs/misc/xen-command-line.markdown
index 15aa404..293d5ac 100644
--- a/docs/misc/xen-command-line.markdown
+++ b/docs/misc/xen-command-line.markdown
@@ -754,6 +754,14 @@ Defaults to booting secondary processors.
Default: `on`
+### pci
+> `= {no-}serr | {no-}perr`
+
+Disable signaling of SERR (system errors) and/or PERR (parity errors)
+on all PCI devices.
+
+Default: Signaling left as set by firmware.
+
### pci-phantom
> `=[<seg>:]<bus>:<device>,<stride>`
diff --git a/m4/ax_compare_version.m4 b/m4/ax_compare_version.m4
new file mode 100644
index 0000000..26f4dec
--- /dev/null
+++ b/m4/ax_compare_version.m4
@@ -0,0 +1,179 @@
+# Fetched from http://git.savannah.gnu.org/gitweb/?p=autoconf-archive.git;a=blob_plain;f=m4/ax_compare_version.m4
+# Commit ID: 27948f49ca30e4222bb7cdd55182bd7341ac50c5
+# ===========================================================================
+# http://www.gnu.org/software/autoconf-archive/ax_compare_version.html
+# ===========================================================================
+#
+# SYNOPSIS
+#
+# AX_COMPARE_VERSION(VERSION_A, OP, VERSION_B, [ACTION-IF-TRUE], [ACTION-IF-FALSE])
+#
+# DESCRIPTION
+#
+# This macro compares two version strings. Due to the various number of
+# minor-version numbers that can exist, and the fact that string
+# comparisons are not compatible with numeric comparisons, this is not
+# necessarily trivial to do in a autoconf script. This macro makes doing
+# these comparisons easy.
+#
+# The six basic comparisons are available, as well as checking equality
+# limited to a certain number of minor-version levels.
+#
+# The operator OP determines what type of comparison to do, and can be one
+# of:
+#
+# eq - equal (test A == B)
+# ne - not equal (test A != B)
+# le - less than or equal (test A <= B)
+# ge - greater than or equal (test A >= B)
+# lt - less than (test A < B)
+# gt - greater than (test A > B)
+#
+# Additionally, the eq and ne operator can have a number after it to limit
+# the test to that number of minor versions.
+#
+# eq0 - equal up to the length of the shorter version
+# ne0 - not equal up to the length of the shorter version
+# eqN - equal up to N sub-version levels
+# neN - not equal up to N sub-version levels
+#
+# When the condition is true, shell commands ACTION-IF-TRUE are run,
+# otherwise shell commands ACTION-IF-FALSE are run. The environment
+# variable 'ax_compare_version' is always set to either 'true' or 'false'
+# as well.
+#
+# Examples:
+#
+# AX_COMPARE_VERSION([3.15.7],[lt],[3.15.8])
+# AX_COMPARE_VERSION([3.15],[lt],[3.15.8])
+#
+# would both be true.
+#
+# AX_COMPARE_VERSION([3.15.7],[eq],[3.15.8])
+# AX_COMPARE_VERSION([3.15],[gt],[3.15.8])
+#
+# would both be false.
+#
+# AX_COMPARE_VERSION([3.15.7],[eq2],[3.15.8])
+#
+# would be true because it is only comparing two minor versions.
+#
+# AX_COMPARE_VERSION([3.15.7],[eq0],[3.15])
+#
+# would be true because it is only comparing the lesser number of minor
+# versions of the two values.
+#
+# Note: The characters that separate the version numbers do not matter. An
+# empty string is the same as version 0. OP is evaluated by autoconf, not
+# configure, so must be a string, not a variable.
+#
+# The author would like to acknowledge Guido Draheim whose advice about
+# the m4_case and m4_ifvaln functions make this macro only include the
+# portions necessary to perform the specific comparison specified by the
+# OP argument in the final configure script.
+#
+# LICENSE
+#
+# Copyright (c) 2008 Tim Toolan <toolan at ele.uri.edu>
+#
+# Copying and distribution of this file, with or without modification, are
+# permitted in any medium without royalty provided the copyright notice
+# and this notice are preserved. This file is offered as-is, without any
+# warranty.
+
+#serial 11
+
+dnl #########################################################################
+AC_DEFUN([AX_COMPARE_VERSION], [
+ AC_REQUIRE([AC_PROG_AWK])
+
+ # Used to indicate true or false condition
+ ax_compare_version=false
+
+ # Convert the two version strings to be compared into a format that
+ # allows a simple string comparison. The end result is that a version
+ # string of the form 1.12.5-r617 will be converted to the form
+ # 0001001200050617. In other words, each number is zero padded to four
+ # digits, and non digits are removed.
+ AS_VAR_PUSHDEF([A],[ax_compare_version_A])
+ A=`echo "$1" | sed -e 's/\([[0-9]]*\)/Z\1Z/g' \
+ -e 's/Z\([[0-9]]\)Z/Z0\1Z/g' \
+ -e 's/Z\([[0-9]][[0-9]]\)Z/Z0\1Z/g' \
+ -e 's/Z\([[0-9]][[0-9]][[0-9]]\)Z/Z0\1Z/g' \
+ -e 's/[[^0-9]]//g'`
+
+ AS_VAR_PUSHDEF([B],[ax_compare_version_B])
+ B=`echo "$3" | sed -e 's/\([[0-9]]*\)/Z\1Z/g' \
+ -e 's/Z\([[0-9]]\)Z/Z0\1Z/g' \
+ -e 's/Z\([[0-9]][[0-9]]\)Z/Z0\1Z/g' \
+ -e 's/Z\([[0-9]][[0-9]][[0-9]]\)Z/Z0\1Z/g' \
+ -e 's/[[^0-9]]//g'`
+
+ dnl # In the case of le, ge, lt, and gt, the strings are sorted as necessary
+ dnl # then the first line is used to determine if the condition is true.
+ dnl # The sed right after the echo is to remove any indented white space.
+ m4_case(m4_tolower($2),
+ [lt],[
+ ax_compare_version=`echo "x$A
+x$B" | sed 's/^ *//' | sort -r | sed "s/x${A}/false/;s/x${B}/true/;1q"`
+ ],
+ [gt],[
+ ax_compare_version=`echo "x$A
+x$B" | sed 's/^ *//' | sort | sed "s/x${A}/false/;s/x${B}/true/;1q"`
+ ],
+ [le],[
+ ax_compare_version=`echo "x$A
+x$B" | sed 's/^ *//' | sort | sed "s/x${A}/true/;s/x${B}/false/;1q"`
+ ],
+ [ge],[
+ ax_compare_version=`echo "x$A
+x$B" | sed 's/^ *//' | sort -r | sed "s/x${A}/true/;s/x${B}/false/;1q"`
+ ],[
+ dnl Split the operator from the subversion count if present.
+ m4_bmatch(m4_substr($2,2),
+ [0],[
+ # A count of zero means use the length of the shorter version.
+ # Determine the number of characters in A and B.
+ ax_compare_version_len_A=`echo "$A" | $AWK '{print(length)}'`
+ ax_compare_version_len_B=`echo "$B" | $AWK '{print(length)}'`
+
+ # Set A to no more than B's length and B to no more than A's length.
+ A=`echo "$A" | sed "s/\(.\{$ax_compare_version_len_B\}\).*/\1/"`
+ B=`echo "$B" | sed "s/\(.\{$ax_compare_version_len_A\}\).*/\1/"`
+ ],
+ [[0-9]+],[
+ # A count greater than zero means use only that many subversions
+ A=`echo "$A" | sed "s/\(\([[0-9]]\{4\}\)\{m4_substr($2,2)\}\).*/\1/"`
+ B=`echo "$B" | sed "s/\(\([[0-9]]\{4\}\)\{m4_substr($2,2)\}\).*/\1/"`
+ ],
+ [.+],[
+ AC_WARNING(
+ [illegal OP numeric parameter: $2])
+ ],[])
+
+ # Pad zeros at end of numbers to make same length.
+ ax_compare_version_tmp_A="$A`echo $B | sed 's/./0/g'`"
+ B="$B`echo $A | sed 's/./0/g'`"
+ A="$ax_compare_version_tmp_A"
+
+ # Check for equality or inequality as necessary.
+ m4_case(m4_tolower(m4_substr($2,0,2)),
+ [eq],[
+ test "x$A" = "x$B" && ax_compare_version=true
+ ],
+ [ne],[
+ test "x$A" != "x$B" && ax_compare_version=true
+ ],[
+ AC_WARNING([illegal OP parameter: $2])
+ ])
+ ])
+
+ AS_VAR_POPDEF([A])dnl
+ AS_VAR_POPDEF([B])dnl
+
+ dnl # Execute ACTION-IF-TRUE / ACTION-IF-FALSE.
+ if test "$ax_compare_version" = "true" ; then
+ m4_ifvaln([$4],[$4],[:])dnl
+ m4_ifvaln([$5],[else $5])dnl
+ fi
+]) dnl AX_COMPARE_VERSION
diff --git a/stubdom/grub/mini-os.c b/stubdom/grub/mini-os.c
index 8cecf90..64ab962 100644
--- a/stubdom/grub/mini-os.c
+++ b/stubdom/grub/mini-os.c
@@ -126,6 +126,9 @@ biosdisk (int read, int drive, struct geometry *geometry,
if (i >= blk_nb)
return -1;
+ if (sector + nsec > geometry->total_sectors)
+ return -1;
+
aiocb.aio_dev = blk_dev[i];
aiocb.aio_buf = addr;
aiocb.aio_nbytes = (size_t)nsec * blk_info[i].sector_size;
diff --git a/tools/blktap2/drivers/block-qcow.c b/tools/blktap2/drivers/block-qcow.c
index d5053d4..b45bcaa 100644
--- a/tools/blktap2/drivers/block-qcow.c
+++ b/tools/blktap2/drivers/block-qcow.c
@@ -427,6 +427,7 @@ static uint64_t get_cluster_offset(struct tdqcow_state *s,
if (posix_memalign((void **)&tmp_ptr, 4096, 4096) != 0) {
DPRINTF("ERROR allocating memory for L1 table\n");
+ return 0;
}
memcpy(tmp_ptr, l1_ptr, 4096);
@@ -600,6 +601,7 @@ found:
if (posix_memalign((void **)&tmp_ptr2, 4096, 4096) != 0) {
DPRINTF("ERROR allocating memory for L1 table\n");
+ return 0;
}
memcpy(tmp_ptr2, l2_ptr, 4096);
lseek(s->fd, l2_offset + (l2_sector << 12), SEEK_SET);
diff --git a/tools/configure b/tools/configure
index 3f2eecf..b06fcf9 100755
--- a/tools/configure
+++ b/tools/configure
@@ -648,6 +648,7 @@ CPP
pyconfig
PYTHONPATH
CHECKPOLICY
+AWK
OCAMLFIND
OCAMLBUILD
OCAMLDOC
@@ -3450,6 +3451,92 @@ esac
+# Fetched from http://git.savannah.gnu.org/gitweb/?p=autoconf-archive.git;a=blob_plain;f=m4/ax_compare_version.m4
+# Commit ID: 27948f49ca30e4222bb7cdd55182bd7341ac50c5
+# ===========================================================================
+# http://www.gnu.org/software/autoconf-archive/ax_compare_version.html
+# ===========================================================================
+#
+# SYNOPSIS
+#
+# AX_COMPARE_VERSION(VERSION_A, OP, VERSION_B, [ACTION-IF-TRUE], [ACTION-IF-FALSE])
+#
+# DESCRIPTION
+#
+# This macro compares two version strings. Due to the various number of
+# minor-version numbers that can exist, and the fact that string
+# comparisons are not compatible with numeric comparisons, this is not
+# necessarily trivial to do in a autoconf script. This macro makes doing
+# these comparisons easy.
+#
+# The six basic comparisons are available, as well as checking equality
+# limited to a certain number of minor-version levels.
+#
+# The operator OP determines what type of comparison to do, and can be one
+# of:
+#
+# eq - equal (test A == B)
+# ne - not equal (test A != B)
+# le - less than or equal (test A <= B)
+# ge - greater than or equal (test A >= B)
+# lt - less than (test A < B)
+# gt - greater than (test A > B)
+#
+# Additionally, the eq and ne operator can have a number after it to limit
+# the test to that number of minor versions.
+#
+# eq0 - equal up to the length of the shorter version
+# ne0 - not equal up to the length of the shorter version
+# eqN - equal up to N sub-version levels
+# neN - not equal up to N sub-version levels
+#
+# When the condition is true, shell commands ACTION-IF-TRUE are run,
+# otherwise shell commands ACTION-IF-FALSE are run. The environment
+# variable 'ax_compare_version' is always set to either 'true' or 'false'
+# as well.
+#
+# Examples:
+#
+# AX_COMPARE_VERSION([3.15.7],[lt],[3.15.8])
+# AX_COMPARE_VERSION([3.15],[lt],[3.15.8])
+#
+# would both be true.
+#
+# AX_COMPARE_VERSION([3.15.7],[eq],[3.15.8])
+# AX_COMPARE_VERSION([3.15],[gt],[3.15.8])
+#
+# would both be false.
+#
+# AX_COMPARE_VERSION([3.15.7],[eq2],[3.15.8])
+#
+# would be true because it is only comparing two minor versions.
+#
+# AX_COMPARE_VERSION([3.15.7],[eq0],[3.15])
+#
+# would be true because it is only comparing the lesser number of minor
+# versions of the two values.
+#
+# Note: The characters that separate the version numbers do not matter. An
+# empty string is the same as version 0. OP is evaluated by autoconf, not
+# configure, so must be a string, not a variable.
+#
+# The author would like to acknowledge Guido Draheim whose advice about
+# the m4_case and m4_ifvaln functions make this macro only include the
+# portions necessary to perform the specific comparison specified by the
+# OP argument in the final configure script.
+#
+# LICENSE
+#
+# Copyright (c) 2008 Tim Toolan <toolan at ele.uri.edu>
+#
+# Copying and distribution of this file, with or without modification, are
+# permitted in any medium without royalty provided the copyright notice
+# and this notice are preserved. This file is offered as-is, without any
+# warranty.
+
+#serial 11
+
+
# Enable/disable options
@@ -4709,6 +4796,48 @@ then
fi
fi
+for ac_prog in gawk mawk nawk awk
+do
+ # Extract the first word of "$ac_prog", so it can be a program name with args.
+set dummy $ac_prog; ac_word=$2
+{ $as_echo "$as_me:${as_lineno-$LINENO}: checking for $ac_word" >&5
+$as_echo_n "checking for $ac_word... " >&6; }
+if ${ac_cv_prog_AWK+:} false; then :
+ $as_echo_n "(cached) " >&6
+else
+ if test -n "$AWK"; then
+ ac_cv_prog_AWK="$AWK" # Let the user override the test.
+else
+as_save_IFS=$IFS; IFS=$PATH_SEPARATOR
+for as_dir in $PATH
+do
+ IFS=$as_save_IFS
+ test -z "$as_dir" && as_dir=.
+ for ac_exec_ext in '' $ac_executable_extensions; do
+ if as_fn_executable_p "$as_dir/$ac_word$ac_exec_ext"; then
+ ac_cv_prog_AWK="$ac_prog"
+ $as_echo "$as_me:${as_lineno-$LINENO}: found $as_dir/$ac_word$ac_exec_ext" >&5
+ break 2
+ fi
+done
+ done
+IFS=$as_save_IFS
+
+fi
+fi
+AWK=$ac_cv_prog_AWK
+if test -n "$AWK"; then
+ { $as_echo "$as_me:${as_lineno-$LINENO}: result: $AWK" >&5
+$as_echo "$AWK" >&6; }
+else
+ { $as_echo "$as_me:${as_lineno-$LINENO}: result: no" >&5
+$as_echo "no" >&6; }
+fi
+
+
+ test -n "$AWK" && break
+done
+
if test "x$ocamltools" = "xy"; then :
# checking for ocamlc
@@ -5813,6 +5942,50 @@ fi
fi
ocamltools="n"
+else
+
+
+
+
+ # Used to indicate true or false condition
+ ax_compare_version=false
+
+ # Convert the two version strings to be compared into a format that
+ # allows a simple string comparison. The end result is that a version
+ # string of the form 1.12.5-r617 will be converted to the form
+ # 0001001200050617. In other words, each number is zero padded to four
+ # digits, and non digits are removed.
+
+ ax_compare_version_A=`echo "$OCAMLVERSION" | sed -e 's/\([0-9]*\)/Z\1Z/g' \
+ -e 's/Z\([0-9]\)Z/Z0\1Z/g' \
+ -e 's/Z\([0-9][0-9]\)Z/Z0\1Z/g' \
+ -e 's/Z\([0-9][0-9][0-9]\)Z/Z0\1Z/g' \
+ -e 's/[^0-9]//g'`
+
+
+ ax_compare_version_B=`echo "3.09.3" | sed -e 's/\([0-9]*\)/Z\1Z/g' \
+ -e 's/Z\([0-9]\)Z/Z0\1Z/g' \
+ -e 's/Z\([0-9][0-9]\)Z/Z0\1Z/g' \
+ -e 's/Z\([0-9][0-9][0-9]\)Z/Z0\1Z/g' \
+ -e 's/[^0-9]//g'`
+
+
+ ax_compare_version=`echo "x$ax_compare_version_A
+x$ax_compare_version_B" | sed 's/^ *//' | sort -r | sed "s/x${ax_compare_version_A}/false/;s/x${ax_compare_version_B}/true/;1q"`
+
+
+
+ if test "$ax_compare_version" = "true" ; then
+
+ if test "x$enable_ocamltools" = "xyes"; then :
+
+ as_fn_error $? "Your version of OCaml: $OCAMLVERSION is not supported" "$LINENO" 5
+fi
+ ocamltools="n"
+
+ fi
+
+
fi
fi
@@ -8606,6 +8779,7 @@ gives unlimited permission to copy, distribute and modify it."
ac_pwd='$ac_pwd'
srcdir='$srcdir'
INSTALL='$INSTALL'
+AWK='$AWK'
test -n "\$AWK" || AWK=awk
_ACEOF
diff --git a/tools/configure.ac b/tools/configure.ac
index 5083c7b..884d63d 100644
--- a/tools/configure.ac
+++ b/tools/configure.ac
@@ -46,6 +46,7 @@ m4_include([../m4/pthread.m4])
m4_include([../m4/ptyfuncs.m4])
m4_include([../m4/extfs.m4])
m4_include([../m4/fetcher.m4])
+m4_include([../m4/ax_compare_version.m4])
# Enable/disable options
AX_ARG_DEFAULT_DISABLE([githttp], [Download GIT repositories via HTTP])
@@ -161,6 +162,12 @@ AS_IF([test "x$ocamltools" = "xy"], [
AS_IF([test "x$enable_ocamltools" = "xyes"], [
AC_MSG_ERROR([Ocaml tools enabled, but unable to find Ocaml])])
ocamltools="n"
+ ], [
+ AX_COMPARE_VERSION([$OCAMLVERSION], [lt], [3.09.3], [
+ AS_IF([test "x$enable_ocamltools" = "xyes"], [
+ AC_MSG_ERROR([Your version of OCaml: $OCAMLVERSION is not supported])])
+ ocamltools="n"
+ ])
])
])
AS_IF([test "x$xsmpolicy" = "xy"], [
diff --git a/tools/include/Makefile b/tools/include/Makefile
index 9ed41f1..f7a6256 100644
--- a/tools/include/Makefile
+++ b/tools/include/Makefile
@@ -13,7 +13,7 @@ xen/.dir:
mkdir -p xen/libelf
ln -sf $(XEN_ROOT)/xen/include/public/COPYING xen
ln -sf $(wildcard $(XEN_ROOT)/xen/include/public/*.h) xen
- ln -sf $(addprefix $(XEN_ROOT)/xen/include/public/,arch-x86 hvm io xsm) xen
+ ln -sf $(addprefix $(XEN_ROOT)/xen/include/public/,arch-x86 arch-arm hvm io xsm) xen
ln -sf ../xen-sys/$(XEN_OS) xen/sys
ln -sf $(addprefix $(XEN_ROOT)/xen/include/xen/,libelf.h elfstructs.h) xen/libelf/
ln -s ../xen-foreign xen/foreign
@@ -23,6 +23,8 @@ xen/.dir:
install: all
$(INSTALL_DIR) $(DESTDIR)$(INCLUDEDIR)/xen/arch-x86
$(INSTALL_DIR) $(DESTDIR)$(INCLUDEDIR)/xen/arch-x86/hvm
+ $(INSTALL_DIR) $(DESTDIR)$(INCLUDEDIR)/xen/arch-arm
+ $(INSTALL_DIR) $(DESTDIR)$(INCLUDEDIR)/xen/arch-arm/hvm
$(INSTALL_DIR) $(DESTDIR)$(INCLUDEDIR)/xen/foreign
$(INSTALL_DIR) $(DESTDIR)$(INCLUDEDIR)/xen/hvm
$(INSTALL_DIR) $(DESTDIR)$(INCLUDEDIR)/xen/io
@@ -32,6 +34,11 @@ install: all
$(INSTALL_DATA) xen/*.h $(DESTDIR)$(INCLUDEDIR)/xen
$(INSTALL_DATA) xen/arch-x86/*.h $(DESTDIR)$(INCLUDEDIR)/xen/arch-x86
$(INSTALL_DATA) xen/arch-x86/hvm/*.h $(DESTDIR)$(INCLUDEDIR)/xen/arch-x86/hvm
+
+# xen/arch-arm doesn't contains headers for now. Uncommented the line
+# as soon as a new header is added
+# $(INSTALL_DATA) xen/arch-arm/*.h $(DESTDIR)$(INCLUDEDIR)/xen/arch-arm
+ $(INSTALL_DATA) xen/arch-arm/hvm/*.h $(DESTDIR)$(INCLUDEDIR)/xen/arch-arm/hvm
$(INSTALL_DATA) xen/foreign/*.h $(DESTDIR)$(INCLUDEDIR)/xen/foreign
$(INSTALL_DATA) xen/hvm/*.h $(DESTDIR)$(INCLUDEDIR)/xen/hvm
$(INSTALL_DATA) xen/io/*.h $(DESTDIR)$(INCLUDEDIR)/xen/io
diff --git a/tools/libxc/xc_dom.h b/tools/libxc/xc_dom.h
index 7099cee..c9af0ce 100644
--- a/tools/libxc/xc_dom.h
+++ b/tools/libxc/xc_dom.h
@@ -68,6 +68,14 @@ struct xc_dom_image {
/* memory layout */
struct xc_dom_seg kernel_seg;
+ /* If ramdisk_seg.vstart is non zero then the ramdisk will be
+ * loaded at that address, otherwise it will automatically placed.
+ *
+ * If automatic placement is used and the ramdisk is gzip
+ * compressed then it will be decompressed as it is loaded. If the
+ * ramdisk has been explicitly placed then it is loaded as is
+ * otherwise decompressing risks undoing the manual placement.
+ */
struct xc_dom_seg ramdisk_seg;
struct xc_dom_seg p2m_seg;
struct xc_dom_seg pgtables_seg;
diff --git a/tools/libxc/xc_dom_arm.c b/tools/libxc/xc_dom_arm.c
index a40e04d..d5831a2 100644
--- a/tools/libxc/xc_dom_arm.c
+++ b/tools/libxc/xc_dom_arm.c
@@ -249,6 +249,37 @@ int arch_setup_meminit(struct xc_dom_image *dom)
{
int rc;
xen_pfn_t pfn, allocsz, i;
+ uint64_t modbase;
+
+ /* Convenient */
+ const uint64_t rambase = dom->rambase_pfn << XC_PAGE_SHIFT;
+ const uint64_t ramsize = dom->total_pages << XC_PAGE_SHIFT;
+ const uint64_t ramend = rambase + ramsize;
+ const uint64_t kernbase = dom->kernel_seg.vstart;
+ const uint64_t kernend = ROUNDUP(dom->kernel_seg.vend, 21/*2MB*/);
+ const uint64_t kernsize = kernend - kernbase;
+ const uint64_t dtb_size = dom->devicetree_blob ?
+ ROUNDUP(dom->devicetree_size, XC_PAGE_SHIFT) : 0;
+ const uint64_t ramdisk_size = dom->ramdisk_blob ?
+ ROUNDUP(dom->ramdisk_size, XC_PAGE_SHIFT) : 0;
+ const uint64_t modsize = dtb_size + ramdisk_size;
+ const uint64_t ram128mb = rambase + (128<<20);
+
+ if ( modsize + kernsize > ramsize )
+ {
+ DOMPRINTF("%s: Not enough memory for the kernel+dtb+initrd",
+ __FUNCTION__);
+ return -1;
+ }
+
+ if ( ramsize > GUEST_RAM_SIZE - NR_MAGIC_PAGES*XC_PAGE_SIZE )
+ {
+ DOMPRINTF("%s: ram size is too large for guest address space: "
+ "%"PRIx64" > %llx",
+ __FUNCTION__, ramsize,
+ GUEST_RAM_SIZE - NR_MAGIC_PAGES*XC_PAGE_SIZE);
+ return -1;
+ }
rc = set_mode(dom->xch, dom->guest_domid, dom->guest_type);
if ( rc )
@@ -278,23 +309,52 @@ int arch_setup_meminit(struct xc_dom_image *dom)
0, 0, &dom->p2m_host[i]);
}
- if ( dom->devicetree_blob )
+ /*
+ * We try to place dtb+initrd at 128MB or if we have less RAM
+ * as high as possible. If there is no space then fallback to
+ * just before the kernel.
+ *
+ * If changing this then consider
+ * xen/arch/arm/kernel.c:place_modules as well.
+ */
+ if ( ramend >= ram128mb + modsize && kernend < ram128mb )
+ modbase = ram128mb;
+ else if ( ramend - modsize > kernend )
+ modbase = ramend - modsize;
+ else if (kernbase - rambase > modsize )
+ modbase = kernbase - modsize;
+ else
+ return -1;
+
+ DOMPRINTF("%s: placing boot modules at 0x%" PRIx64, __FUNCTION__, modbase);
+
+ /*
+ * Must map DTB *after* initrd, to satisfy order of calls to
+ * xc_dom_alloc_segment in xc_dom_build_image, which must map
+ * things at monotonolically increasing addresses.
+ */
+ if ( ramdisk_size )
{
- const uint64_t rambase = dom->rambase_pfn << XC_PAGE_SHIFT;
- const uint64_t ramend = rambase + ( dom->total_pages << XC_PAGE_SHIFT );
- const uint64_t dtbsize = ROUNDUP(dom->devicetree_size, XC_PAGE_SHIFT);
-
- /* Place at 128MB if there is sufficient RAM */
- if ( ramend >= rambase + 128*1024*1024 + dtbsize )
- dom->devicetree_seg.vstart = rambase + 128*1024*1024;
- else /* otherwise at top of RAM */
- dom->devicetree_seg.vstart = ramend - dtbsize;
-
- dom->devicetree_seg.vend =
- dom->devicetree_seg.vstart + dom->devicetree_size;
+ dom->ramdisk_seg.vstart = modbase;
+ dom->ramdisk_seg.vend = modbase + ramdisk_size;
+
+ DOMPRINTF("%s: ramdisk: 0x%" PRIx64 " -> 0x%" PRIx64 "",
+ __FUNCTION__,
+ dom->ramdisk_seg.vstart, dom->ramdisk_seg.vend);
+
+ modbase += ramdisk_size;
+ }
+
+ if ( dtb_size )
+ {
+ dom->devicetree_seg.vstart = modbase;
+ dom->devicetree_seg.vend = modbase + dtb_size;
+
DOMPRINTF("%s: devicetree: 0x%" PRIx64 " -> 0x%" PRIx64 "",
__FUNCTION__,
dom->devicetree_seg.vstart, dom->devicetree_seg.vend);
+
+ modbase += dtb_size;
}
return 0;
diff --git a/tools/libxc/xc_dom_armzimageloader.c b/tools/libxc/xc_dom_armzimageloader.c
index e6516a1..2b28781 100644
--- a/tools/libxc/xc_dom_armzimageloader.c
+++ b/tools/libxc/xc_dom_armzimageloader.c
@@ -51,7 +51,6 @@ struct minimal_dtb_header {
static int xc_dom_probe_zimage32_kernel(struct xc_dom_image *dom)
{
uint32_t *zimage;
- uint32_t end;
if ( dom->kernel_blob == NULL )
{
@@ -73,22 +72,6 @@ static int xc_dom_probe_zimage32_kernel(struct xc_dom_image *dom)
return -EINVAL;
}
- end = zimage[ZIMAGE32_END_OFFSET/4];
-
- /*
- * Check for an appended DTB.
- */
- if ( end + sizeof(struct minimal_dtb_header) < dom->kernel_size ) {
- struct minimal_dtb_header *dtb_hdr;
- dtb_hdr = (struct minimal_dtb_header *)(dom->kernel_blob + end);
- if (ntohl/*be32_to_cpu*/(dtb_hdr->magic) == DTB_MAGIC) {
- xc_dom_printf(dom->xch, "%s: found an appended DTB", __FUNCTION__);
- end += ntohl/*be32_to_cpu*/(dtb_hdr->total_size);
- }
- }
-
- dom->kernel_size = end;
-
return 0;
}
@@ -105,8 +88,20 @@ static int xc_dom_parse_zimage32_kernel(struct xc_dom_image *dom)
/* Do not load kernel at the very first RAM address */
v_start = rambase + 0x8000;
+
+ if ( dom->kernel_size > UINT64_MAX - v_start )
+ {
+ DOMPRINTF("%s: kernel is too large\n", __FUNCTION__);
+ return -EINVAL;
+ }
+
v_end = v_start + dom->kernel_size;
+ /*
+ * If start is invalid then the guest will start at some invalid
+ * address and crash, but this happens in guest context so doesn't
+ * concern us here.
+ */
start = zimage[ZIMAGE32_START_OFFSET/4];
if (start == 0)
@@ -187,7 +182,20 @@ static int xc_dom_parse_zimage64_kernel(struct xc_dom_image *dom)
zimage = dom->kernel_blob;
+ if ( zimage->text_offset > UINT64_MAX - rambase )
+ {
+ DOMPRINTF("%s: kernel text offset is too large\n", __FUNCTION__);
+ return -EINVAL;
+ }
+
v_start = rambase + zimage->text_offset;
+
+ if ( dom->kernel_size > UINT64_MAX - v_start )
+ {
+ DOMPRINTF("%s: kernel is too large\n", __FUNCTION__);
+ return -EINVAL;
+ }
+
v_end = v_start + dom->kernel_size;
dom->kernel_seg.vstart = v_start;
diff --git a/tools/libxc/xc_dom_core.c b/tools/libxc/xc_dom_core.c
index b9d1015..baa62a1 100644
--- a/tools/libxc/xc_dom_core.c
+++ b/tools/libxc/xc_dom_core.c
@@ -955,13 +955,20 @@ int xc_dom_build_image(struct xc_dom_image *dom)
size_t unziplen, ramdisklen;
void *ramdiskmap;
- unziplen = xc_dom_check_gzip(dom->xch, dom->ramdisk_blob, dom->ramdisk_size);
- if ( xc_dom_ramdisk_check_size(dom, unziplen) != 0 )
+ if ( !dom->ramdisk_seg.vstart )
+ {
+ unziplen = xc_dom_check_gzip(dom->xch,
+ dom->ramdisk_blob, dom->ramdisk_size);
+ if ( xc_dom_ramdisk_check_size(dom, unziplen) != 0 )
+ unziplen = 0;
+ }
+ else
unziplen = 0;
ramdisklen = unziplen ? unziplen : dom->ramdisk_size;
- if ( xc_dom_alloc_segment(dom, &dom->ramdisk_seg, "ramdisk", 0,
+ if ( xc_dom_alloc_segment(dom, &dom->ramdisk_seg, "ramdisk",
+ dom->ramdisk_seg.vstart,
ramdisklen) != 0 )
goto err;
ramdiskmap = xc_dom_seg_to_ptr(dom, &dom->ramdisk_seg);
diff --git a/tools/libxc/xc_private.c b/tools/libxc/xc_private.c
index 33ed15b..0478f52 100644
--- a/tools/libxc/xc_private.c
+++ b/tools/libxc/xc_private.c
@@ -201,14 +201,14 @@ static int xc_interface_close_common(xc_interface *xch)
if (!xch)
return 0;
+ rc = xch->ops->close(xch, xch->ops_handle);
+ if (rc) PERROR("Could not close hypervisor interface");
+
xc__hypercall_buffer_cache_release(xch);
xtl_logger_destroy(xch->dombuild_logger_tofree);
xtl_logger_destroy(xch->error_handler_tofree);
- rc = xch->ops->close(xch, xch->ops_handle);
- if (rc) PERROR("Could not close hypervisor interface");
-
free(xch);
return rc;
}
diff --git a/tools/libxl/libxl.c b/tools/libxl/libxl.c
index 730f6e1..2d29ad2 100644
--- a/tools/libxl/libxl.c
+++ b/tools/libxl/libxl.c
@@ -3881,7 +3881,8 @@ int libxl_device_events_handler(libxl_ctx *ctx,
out:
GC_FREE;
- return rc ? : AO_INPROGRESS;
+ if (rc) return AO_ABORT(rc);
+ return AO_INPROGRESS;
}
/******************************************************************************/
diff --git a/tools/libxl/libxl_arch.h b/tools/libxl/libxl_arch.h
index aee0a91..d3bc136 100644
--- a/tools/libxl/libxl_arch.h
+++ b/tools/libxl/libxl_arch.h
@@ -19,7 +19,12 @@
int libxl__arch_domain_create(libxl__gc *gc, libxl_domain_config *d_config,
uint32_t domid);
-int libxl__arch_domain_configure(libxl__gc *gc,
- libxl_domain_build_info *info,
- struct xc_dom_image *dom);
+/* setup arch specific hardware description, i.e. DTB on ARM */
+int libxl__arch_domain_init_hw_description(libxl__gc *gc,
+ libxl_domain_build_info *info,
+ struct xc_dom_image *dom);
+/* finalize arch specific hardware description. */
+int libxl__arch_domain_finalise_hw_description(libxl__gc *gc,
+ libxl_domain_build_info *info,
+ struct xc_dom_image *dom);
#endif
diff --git a/tools/libxl/libxl_arm.c b/tools/libxl/libxl_arm.c
index 0a1c8c5..4f0f0e2 100644
--- a/tools/libxl/libxl_arm.c
+++ b/tools/libxl/libxl_arm.c
@@ -2,6 +2,7 @@
#include "libxl_arch.h"
#include <xc_dom.h>
+#include <stdbool.h>
#include <libfdt.h>
#include <assert.h>
@@ -31,6 +32,9 @@ typedef be32 gic_interrupt[3];
#define ROOT_ADDRESS_CELLS 2
#define ROOT_SIZE_CELLS 2
+#define PROP_INITRD_START "linux,initrd-start"
+#define PROP_INITRD_END "linux,initrd-end"
+
static void set_cell(be32 **cellp, int size, uint64_t val)
{
int cells = size;
@@ -155,7 +159,7 @@ static int make_root_properties(libxl__gc *gc,
return 0;
}
-static int make_chosen_node(libxl__gc *gc, void *fdt,
+static int make_chosen_node(libxl__gc *gc, void *fdt, bool ramdisk,
const libxl_domain_build_info *info)
{
int res;
@@ -164,8 +168,19 @@ static int make_chosen_node(libxl__gc *gc, void *fdt,
res = fdt_begin_node(fdt, "chosen");
if (res) return res;
- res = fdt_property_string(fdt, "bootargs", info->u.pv.cmdline);
- if (res) return res;
+ if (info->u.pv.cmdline) {
+ res = fdt_property_string(fdt, "bootargs", info->u.pv.cmdline);
+ if (res) return res;
+ }
+
+ if (ramdisk) {
+ uint64_t dummy = 0;
+ LOG(DEBUG, "/chosen adding placeholder linux,initrd properties");
+ res = fdt_property(fdt, PROP_INITRD_START, &dummy, sizeof(dummy));
+ if (res) return res;
+ res = fdt_property(fdt, PROP_INITRD_END, &dummy, sizeof(dummy));
+ if (res) return res;
+ }
res = fdt_end_node(fdt);
if (res) return res;
@@ -410,9 +425,9 @@ out:
#define FDT_MAX_SIZE (1<<20)
-int libxl__arch_domain_configure(libxl__gc *gc,
- libxl_domain_build_info *info,
- struct xc_dom_image *dom)
+int libxl__arch_domain_init_hw_description(libxl__gc *gc,
+ libxl_domain_build_info *info,
+ struct xc_dom_image *dom)
{
void *fdt = NULL;
int rc, res;
@@ -473,7 +488,7 @@ next_resize:
FDT( fdt_begin_node(fdt, "") );
FDT( make_root_properties(gc, vers, fdt) );
- FDT( make_chosen_node(gc, fdt, info) );
+ FDT( make_chosen_node(gc, fdt, !!dom->ramdisk_blob, info) );
FDT( make_cpus_node(gc, fdt, info->max_vcpus, ainfo) );
FDT( make_psci_node(gc, fdt) );
@@ -503,10 +518,49 @@ next_resize:
goto out;
}
- debug_dump_fdt(gc, fdt);
-
rc = 0;
out:
return rc;
}
+
+int libxl__arch_domain_finalise_hw_description(libxl__gc *gc,
+ libxl_domain_build_info *info,
+ struct xc_dom_image *dom)
+{
+ void *fdt = dom->devicetree_blob;
+
+ const struct xc_dom_seg *ramdisk = dom->ramdisk_blob ?
+ &dom->ramdisk_seg : NULL;
+
+ if (ramdisk) {
+ int chosen, res;
+ uint64_t val;
+
+ /* Neither the fdt_path_offset() nor either of the
+ * fdt_setprop_inplace() calls can fail. If they do then
+ * make_chosen_node() (see above) has got something very
+ * wrong.
+ */
+ chosen = fdt_path_offset(fdt, "/chosen");
+ assert(chosen > 0);
+
+ LOG(DEBUG, "/chosen updating initrd properties to cover "
+ "%"PRIx64"-%"PRIx64,
+ ramdisk->vstart, ramdisk->vend);
+
+ val = cpu_to_fdt64(ramdisk->vstart);
+ res = fdt_setprop_inplace(fdt, chosen, PROP_INITRD_START,
+ &val, sizeof(val));
+ assert(!res);
+
+ val = cpu_to_fdt64(ramdisk->vend);
+ res = fdt_setprop_inplace(fdt, chosen,PROP_INITRD_END,
+ &val, sizeof(val));
+ assert(!res);
+ }
+
+ debug_dump_fdt(gc, fdt);
+
+ return 0;
+}
diff --git a/tools/libxl/libxl_device.c b/tools/libxl/libxl_device.c
index ba7d100..29ed547 100644
--- a/tools/libxl/libxl_device.c
+++ b/tools/libxl/libxl_device.c
@@ -775,6 +775,8 @@ void libxl__initiate_device_remove(libxl__egc *egc,
uint32_t my_domid, domid = aodev->dev->domid;
int rc = 0;
+ libxl_dominfo_init(&info);
+
rc = libxl__get_domid(gc, &my_domid);
if (rc) {
LOG(ERROR, "unable to get my domid");
@@ -782,7 +784,6 @@ void libxl__initiate_device_remove(libxl__egc *egc,
}
if (my_domid == LIBXL_TOOLSTACK_DOMID) {
- libxl_dominfo_init(&info);
rc = libxl_domain_info(CTX, &info, domid);
if (rc) {
LOG(ERROR, "unable to get info for domain %d", domid);
diff --git a/tools/libxl/libxl_dom.c b/tools/libxl/libxl_dom.c
index 55f74b2..69e6088 100644
--- a/tools/libxl/libxl_dom.c
+++ b/tools/libxl/libxl_dom.c
@@ -407,8 +407,8 @@ int libxl__build_pv(libxl__gc *gc, uint32_t domid,
LOGE(ERROR, "xc_dom_parse_image failed");
goto out;
}
- if ( (ret = libxl__arch_domain_configure(gc, info, dom)) != 0 ) {
- LOGE(ERROR, "libxl__arch_domain_configure failed");
+ if ( (ret = libxl__arch_domain_init_hw_description(gc, info, dom)) != 0 ) {
+ LOGE(ERROR, "libxl__arch_domain_init_hw_description failed");
goto out;
}
if ( (ret = xc_dom_mem_init(dom, info->target_memkb / 1024)) != 0 ) {
@@ -419,6 +419,10 @@ int libxl__build_pv(libxl__gc *gc, uint32_t domid,
LOGE(ERROR, "xc_dom_boot_mem_init failed");
goto out;
}
+ if ( (ret = libxl__arch_domain_finalise_hw_description(gc, info, dom)) != 0 ) {
+ LOGE(ERROR, "libxl__arch_domain_finalise_hw_description failed");
+ goto out;
+ }
if ( (ret = xc_dom_build_image(dom)) != 0 ) {
LOGE(ERROR, "xc_dom_build_image failed");
goto out;
diff --git a/tools/libxl/libxl_fork.c b/tools/libxl/libxl_fork.c
index 8421296..fa15095 100644
--- a/tools/libxl/libxl_fork.c
+++ b/tools/libxl/libxl_fork.c
@@ -184,9 +184,9 @@ void libxl_postfork_child_noexec(libxl_ctx *ctx)
int libxl__carefd_close(libxl__carefd *cf)
{
if (!cf) return 0;
+ atfork_lock();
int r = cf->fd < 0 ? 0 : close(cf->fd);
int esave = errno;
- atfork_lock();
LIBXL_LIST_REMOVE(cf, entry);
atfork_unlock();
free(cf);
diff --git a/tools/libxl/libxl_json.c b/tools/libxl/libxl_json.c
index d2f7de8..989ac3f 100644
--- a/tools/libxl/libxl_json.c
+++ b/tools/libxl/libxl_json.c
@@ -285,7 +285,6 @@ void libxl__json_object_free(libxl__gc *gc, libxl__json_object *obj)
}
case JSON_ARRAY: {
libxl__json_object *node = NULL;
- break;
for (idx = 0; idx < obj->u.array->count; idx++) {
if (flexarray_get(obj->u.array, idx, (void**)&node) != 0)
diff --git a/tools/libxl/libxl_numa.c b/tools/libxl/libxl_numa.c
index 20c99ac..4fac664 100644
--- a/tools/libxl/libxl_numa.c
+++ b/tools/libxl/libxl_numa.c
@@ -180,6 +180,7 @@ static int nodemap_to_nr_vcpus(libxl__gc *gc, int vcpus_on_node[],
/* Number of vcpus able to run on the cpus of the various nodes
* (reported by filling the array vcpus_on_node[]). */
static int nr_vcpus_on_nodes(libxl__gc *gc, libxl_cputopology *tinfo,
+ size_t tinfo_elements,
const libxl_bitmap *suitable_cpumap,
int vcpus_on_node[])
{
@@ -222,6 +223,8 @@ static int nr_vcpus_on_nodes(libxl__gc *gc, libxl_cputopology *tinfo,
*/
libxl_bitmap_set_none(&nodes_counted);
libxl_for_each_set_bit(k, vinfo[j].cpumap) {
+ if (k >= tinfo_elements)
+ break;
int node = tinfo[k].node;
if (libxl_bitmap_test(suitable_cpumap, k) &&
@@ -364,7 +367,7 @@ int libxl__get_numa_candidate(libxl__gc *gc,
* all we have to do later is summing up the right elements of the
* vcpus_on_node array.
*/
- rc = nr_vcpus_on_nodes(gc, tinfo, suitable_cpumap, vcpus_on_node);
+ rc = nr_vcpus_on_nodes(gc, tinfo, nr_cpus, suitable_cpumap, vcpus_on_node);
if (rc)
goto out;
diff --git a/tools/libxl/libxl_save_callout.c b/tools/libxl/libxl_save_callout.c
index 6e45b2f..e3bda8f 100644
--- a/tools/libxl/libxl_save_callout.c
+++ b/tools/libxl/libxl_save_callout.c
@@ -185,7 +185,11 @@ static void run_helper(libxl__egc *egc, libxl__save_helper_state *shs,
for (childfd=0; childfd<2; childfd++) {
/* Setting up the pipe for the child's fd childfd */
int fds[2];
- if (libxl_pipe(CTX,fds)) { rc = ERROR_FAIL; goto out; }
+ if (libxl_pipe(CTX,fds)) {
+ rc = ERROR_FAIL;
+ libxl__carefd_unlock();
+ goto out;
+ }
int childs_end = childfd==0 ? 0 /*read*/ : 1 /*write*/;
int our_end = childfd==0 ? 1 /*write*/ : 0 /*read*/;
childs_pipes[childfd] = libxl__carefd_record(CTX, fds[childs_end]);
diff --git a/tools/libxl/libxl_utils.c b/tools/libxl/libxl_utils.c
index c9cef66..1f334f2 100644
--- a/tools/libxl/libxl_utils.c
+++ b/tools/libxl/libxl_utils.c
@@ -762,8 +762,11 @@ int libxl_cpumap_to_nodemap(libxl_ctx *ctx,
}
libxl_bitmap_set_none(nodemap);
- libxl_for_each_set_bit(i, *cpumap)
+ libxl_for_each_set_bit(i, *cpumap) {
+ if (i >= nr_cpus)
+ break;
libxl_bitmap_set(nodemap, tinfo[i].node);
+ }
out:
libxl_cputopology_list_free(tinfo, nr_cpus);
return rc;
diff --git a/tools/libxl/libxl_x86.c b/tools/libxl/libxl_x86.c
index b11d036..7589060 100644
--- a/tools/libxl/libxl_x86.c
+++ b/tools/libxl/libxl_x86.c
@@ -311,9 +311,16 @@ int libxl__arch_domain_create(libxl__gc *gc, libxl_domain_config *d_config,
return ret;
}
-int libxl__arch_domain_configure(libxl__gc *gc,
- libxl_domain_build_info *info,
- struct xc_dom_image *dom)
+int libxl__arch_domain_init_hw_description(libxl__gc *gc,
+ libxl_domain_build_info *info,
+ struct xc_dom_image *dom)
+{
+ return 0;
+}
+
+int libxl__arch_domain_finalise_hw_description(libxl__gc *gc,
+ libxl_domain_build_info *info,
+ struct xc_dom_image *dom)
{
return 0;
}
diff --git a/tools/pygrub/examples/rhel-7-beta.grub2 b/tools/pygrub/examples/rhel-7-beta.grub2
new file mode 100644
index 0000000..88f0f99
--- /dev/null
+++ b/tools/pygrub/examples/rhel-7-beta.grub2
@@ -0,0 +1,118 @@
+#
+# DO NOT EDIT THIS FILE
+#
+# It is automatically generated by grub2-mkconfig using templates
+# from /etc/grub.d and settings from /etc/default/grub
+#
+
+### BEGIN /etc/grub.d/00_header ###
+set pager=1
+
+if [ -s $prefix/grubenv ]; then
+ load_env
+fi
+if [ "${next_entry}" ] ; then
+ set default="${next_entry}"
+ set next_entry=
+ save_env next_entry
+ set boot_once=true
+else
+ set default="${saved_entry}"
+fi
+
+if [ x"${feature_menuentry_id}" = xy ]; then
+ menuentry_id_option="--id"
+else
+ menuentry_id_option=""
+fi
+
+export menuentry_id_option
+
+if [ "${prev_saved_entry}" ]; then
+ set saved_entry="${prev_saved_entry}"
+ save_env saved_entry
+ set prev_saved_entry=
+ save_env prev_saved_entry
+ set boot_once=true
+fi
+
+function savedefault {
+ if [ -z "${boot_once}" ]; then
+ saved_entry="${chosen}"
+ save_env saved_entry
+ fi
+}
+
+function load_video {
+ if [ x$feature_all_video_module = xy ]; then
+ insmod all_video
+ else
+ insmod efi_gop
+ insmod efi_uga
+ insmod ieee1275_fb
+ insmod vbe
+ insmod vga
+ insmod video_bochs
+ insmod video_cirrus
+ fi
+}
+
+terminal_output console
+set timeout=5
+### END /etc/grub.d/00_header ###
+
+### BEGIN /etc/grub.d/10_linux ###
+menuentry 'Red Hat Enterprise Linux Everything, with Linux 3.10.0-54.0.1.el7.x86_64' --class red --class gnu-linux --class gnu --class os $menuentry_id_option 'gnulinux-3.10.0-54.0.1.el7.x86_64-advanced-d23b8b49-4cfe-4900-8ef1-ec80bc633163' {
+ load_video
+ set gfxpayload=keep
+ insmod gzio
+ insmod part_msdos
+ insmod xfs
+ set root='hd0,msdos1'
+ if [ x$feature_platform_search_hint = xy ]; then
+ search --no-floppy --fs-uuid --set=root --hint='hd0,msdos1' 89ffef78-82b3-457c-bc57-42cccc373851
+ else
+ search --no-floppy --fs-uuid --set=root 89ffef78-82b3-457c-bc57-42cccc373851
+ fi
+ linux16 /vmlinuz-3.10.0-54.0.1.el7.x86_64 root=/dev/mapper/rhel-root ro rd.lvm.lv=rhel/swap vconsole.keymap=uk crashkernel=auto rd.lvm.lv=rhel/root vconsole.font=latarcyrheb-sun16 LANG=en_GB.UTF-8
+ initrd16 /initramfs-3.10.0-54.0.1.el7.x86_64.img
+}
+menuentry 'Red Hat Enterprise Linux Everything, with Linux 0-rescue-af34f0b8cf364cdbbe6d093f8228a37f' --class red --class gnu-linux --class gnu --class os $menuentry_id_option 'gnulinux-0-rescue-af34f0b8cf364cdbbe6d093f8228a37f-advanced-d23b8b49-4cfe-4900-8ef1-ec80bc633163' {
+ load_video
+ insmod gzio
+ insmod part_msdos
+ insmod xfs
+ set root='hd0,msdos1'
+ if [ x$feature_platform_search_hint = xy ]; then
+ search --no-floppy --fs-uuid --set=root --hint='hd0,msdos1' 89ffef78-82b3-457c-bc57-42cccc373851
+ else
+ search --no-floppy --fs-uuid --set=root 89ffef78-82b3-457c-bc57-42cccc373851
+ fi
+ linux16 /vmlinuz-0-rescue-af34f0b8cf364cdbbe6d093f8228a37f root=/dev/mapper/rhel-root ro rd.lvm.lv=rhel/swap vconsole.keymap=uk crashkernel=auto rd.lvm.lv=rhel/root vconsole.font=latarcyrheb-sun16
+ initrd16 /initramfs-0-rescue-af34f0b8cf364cdbbe6d093f8228a37f.img
+}
+
+### END /etc/grub.d/10_linux ###
+
+### BEGIN /etc/grub.d/20_linux_xen ###
+### END /etc/grub.d/20_linux_xen ###
+
+### BEGIN /etc/grub.d/20_ppc_terminfo ###
+### END /etc/grub.d/20_ppc_terminfo ###
+
+### BEGIN /etc/grub.d/30_os-prober ###
+### END /etc/grub.d/30_os-prober ###
+
+### BEGIN /etc/grub.d/40_custom ###
+# This file provides an easy way to add custom menu entries. Simply type the
+# menu entries you want to add after this comment. Be careful not to change
+# the 'exec tail' line above.
+### END /etc/grub.d/40_custom ###
+
+### BEGIN /etc/grub.d/41_custom ###
+if [ -f ${config_directory}/custom.cfg ]; then
+ source ${config_directory}/custom.cfg
+elif [ -z "${config_directory}" -a -f $prefix/custom.cfg ]; then
+ source $prefix/custom.cfg;
+fi
+### END /etc/grub.d/41_custom ###
diff --git a/tools/pygrub/src/GrubConf.py b/tools/pygrub/src/GrubConf.py
index cb853c9..974cded 100644
--- a/tools/pygrub/src/GrubConf.py
+++ b/tools/pygrub/src/GrubConf.py
@@ -348,7 +348,9 @@ class Grub2Image(_GrubImage):
commands = {'set:root': 'root',
'linux': 'kernel',
+ 'linux16': 'kernel',
'initrd': 'initrd',
+ 'initrd16': 'initrd',
'echo': None,
'insmod': None,
'search': None}
@@ -394,7 +396,7 @@ class Grub2ConfigFile(_GrubConfigFile):
continue
# new image
- title_match = re.match('^menuentry ["\'](.*)["\'] (.*){', l)
+ title_match = re.match('^menuentry ["\'](.*?)["\'] (.*){', l)
if title_match:
if img is not None:
raise RuntimeError, "syntax error: cannot nest menuentry (%d %s)" % (len(img),img)
diff --git a/tools/pygrub/src/pygrub b/tools/pygrub/src/pygrub
index ee4e741..45a7290 100644
--- a/tools/pygrub/src/pygrub
+++ b/tools/pygrub/src/pygrub
@@ -760,7 +760,7 @@ if __name__ == "__main__":
usage()
sys.exit(1)
file = args[0]
-
+ fs = None
output = None
entry = None
interactive = True
@@ -882,7 +882,7 @@ if __name__ == "__main__":
sys.exit(0)
# Did looping through partitions find us a kernel?
- if not fs:
+ if fs is None:
raise RuntimeError, "Unable to find partition containing kernel"
bootcfg["kernel"] = copy_from_image(fs, chosencfg["kernel"], "kernel",
diff --git a/tools/tests/x86_emulator/test_x86_emulator.c b/tools/tests/x86_emulator/test_x86_emulator.c
index 7404ee3..3166674 100644
--- a/tools/tests/x86_emulator/test_x86_emulator.c
+++ b/tools/tests/x86_emulator/test_x86_emulator.c
@@ -597,23 +597,32 @@ int main(int argc, char **argv)
printf("skipped\n");
#endif
+#define decl_insn(which) extern const unsigned char which[], which##_len[]
+#define put_insn(which, insn) ".pushsection .test, \"ax\", @progbits\n" \
+ #which ": " insn "\n" \
+ ".equ " #which "_len, .-" #which "\n" \
+ ".popsection"
+#define set_insn(which) (regs.eip = (unsigned long)memcpy(instr, which, \
+ (unsigned long)which##_len))
+#define check_eip(which) (regs.eip == (unsigned long)instr + \
+ (unsigned long)which##_len)
+
printf("%-40s", "Testing movq %mm3,(%ecx)...");
if ( stack_exec && cpu_has_mmx )
{
- extern const unsigned char movq_to_mem[];
+ decl_insn(movq_to_mem);
asm volatile ( "pcmpeqb %%mm3, %%mm3\n"
- ".pushsection .test, \"a\", @progbits\n"
- "movq_to_mem: movq %%mm3, (%0)\n"
- ".popsection" :: "c" (NULL) );
+ put_insn(movq_to_mem, "movq %%mm3, (%0)")
+ :: "c" (NULL) );
- memcpy(instr, movq_to_mem, 15);
+ set_insn(movq_to_mem);
memset(res, 0x33, 64);
memset(res + 8, 0xff, 8);
- regs.eip = (unsigned long)&instr[0];
regs.ecx = (unsigned long)res;
rc = x86_emulate(&ctxt, &emulops);
- if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) )
+ if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) ||
+ !check_eip(movq_to_mem) )
goto fail;
printf("okay\n");
}
@@ -623,19 +632,17 @@ int main(int argc, char **argv)
printf("%-40s", "Testing movq (%edx),%mm5...");
if ( stack_exec && cpu_has_mmx )
{
- extern const unsigned char movq_from_mem[];
+ decl_insn(movq_from_mem);
asm volatile ( "pcmpgtb %%mm5, %%mm5\n"
- ".pushsection .test, \"a\", @progbits\n"
- "movq_from_mem: movq (%0), %%mm5\n"
- ".popsection" :: "d" (NULL) );
+ put_insn(movq_from_mem, "movq (%0), %%mm5")
+ :: "d" (NULL) );
- memcpy(instr, movq_from_mem, 15);
- regs.eip = (unsigned long)&instr[0];
+ set_insn(movq_from_mem);
regs.ecx = 0;
regs.edx = (unsigned long)res;
rc = x86_emulate(&ctxt, &emulops);
- if ( rc != X86EMUL_OKAY )
+ if ( rc != X86EMUL_OKAY || !check_eip(movq_from_mem) )
goto fail;
asm ( "pcmpeqb %%mm3, %%mm3\n\t"
"pcmpeqb %%mm5, %%mm3\n\t"
@@ -650,20 +657,19 @@ int main(int argc, char **argv)
printf("%-40s", "Testing movdqu %xmm2,(%ecx)...");
if ( stack_exec && cpu_has_sse2 )
{
- extern const unsigned char movdqu_to_mem[];
+ decl_insn(movdqu_to_mem);
asm volatile ( "pcmpeqb %%xmm2, %%xmm2\n"
- ".pushsection .test, \"a\", @progbits\n"
- "movdqu_to_mem: movdqu %%xmm2, (%0)\n"
- ".popsection" :: "c" (NULL) );
+ put_insn(movdqu_to_mem, "movdqu %%xmm2, (%0)")
+ :: "c" (NULL) );
- memcpy(instr, movdqu_to_mem, 15);
+ set_insn(movdqu_to_mem);
memset(res, 0x55, 64);
memset(res + 8, 0xff, 16);
- regs.eip = (unsigned long)&instr[0];
regs.ecx = (unsigned long)res;
rc = x86_emulate(&ctxt, &emulops);
- if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) )
+ if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) ||
+ !check_eip(movdqu_to_mem) )
goto fail;
printf("okay\n");
}
@@ -673,19 +679,17 @@ int main(int argc, char **argv)
printf("%-40s", "Testing movdqu (%edx),%xmm4...");
if ( stack_exec && cpu_has_sse2 )
{
- extern const unsigned char movdqu_from_mem[];
+ decl_insn(movdqu_from_mem);
asm volatile ( "pcmpgtb %%xmm4, %%xmm4\n"
- ".pushsection .test, \"a\", @progbits\n"
- "movdqu_from_mem: movdqu (%0), %%xmm4\n"
- ".popsection" :: "d" (NULL) );
+ put_insn(movdqu_from_mem, "movdqu (%0), %%xmm4")
+ :: "d" (NULL) );
- memcpy(instr, movdqu_from_mem, 15);
- regs.eip = (unsigned long)&instr[0];
+ set_insn(movdqu_from_mem);
regs.ecx = 0;
regs.edx = (unsigned long)res;
rc = x86_emulate(&ctxt, &emulops);
- if ( rc != X86EMUL_OKAY )
+ if ( rc != X86EMUL_OKAY || !check_eip(movdqu_from_mem) )
goto fail;
asm ( "pcmpeqb %%xmm2, %%xmm2\n\t"
"pcmpeqb %%xmm4, %%xmm2\n\t"
@@ -700,21 +704,20 @@ int main(int argc, char **argv)
printf("%-40s", "Testing vmovdqu %ymm2,(%ecx)...");
if ( stack_exec && cpu_has_avx )
{
- extern const unsigned char vmovdqu_to_mem[];
+ decl_insn(vmovdqu_to_mem);
asm volatile ( "vpcmpeqb %%xmm2, %%xmm2, %%xmm2\n"
- ".pushsection .test, \"a\", @progbits\n"
- "vmovdqu_to_mem: vmovdqu %%ymm2, (%0)\n"
- ".popsection" :: "c" (NULL) );
+ put_insn(vmovdqu_to_mem, "vmovdqu %%ymm2, (%0)")
+ :: "c" (NULL) );
- memcpy(instr, vmovdqu_to_mem, 15);
+ set_insn(vmovdqu_to_mem);
memset(res, 0x55, 128);
memset(res + 16, 0xff, 16);
memset(res + 20, 0x00, 16);
- regs.eip = (unsigned long)&instr[0];
regs.ecx = (unsigned long)res;
rc = x86_emulate(&ctxt, &emulops);
- if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 16, 64) )
+ if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 16, 64) ||
+ !check_eip(vmovdqu_to_mem) )
goto fail;
printf("okay\n");
}
@@ -724,7 +727,7 @@ int main(int argc, char **argv)
printf("%-40s", "Testing vmovdqu (%edx),%ymm4...");
if ( stack_exec && cpu_has_avx )
{
- extern const unsigned char vmovdqu_from_mem[];
+ decl_insn(vmovdqu_from_mem);
#if 0 /* Don't use AVX2 instructions for now */
asm volatile ( "vpcmpgtb %%ymm4, %%ymm4, %%ymm4\n"
@@ -732,17 +735,15 @@ int main(int argc, char **argv)
asm volatile ( "vpcmpgtb %%xmm4, %%xmm4, %%xmm4\n\t"
"vinsertf128 $1, %%xmm4, %%ymm4, %%ymm4\n"
#endif
- ".pushsection .test, \"a\", @progbits\n"
- "vmovdqu_from_mem: vmovdqu (%0), %%ymm4\n"
- ".popsection" :: "d" (NULL) );
+ put_insn(vmovdqu_from_mem, "vmovdqu (%0), %%ymm4")
+ :: "d" (NULL) );
- memcpy(instr, vmovdqu_from_mem, 15);
+ set_insn(vmovdqu_from_mem);
memset(res + 4, 0xff, 16);
- regs.eip = (unsigned long)&instr[0];
regs.ecx = 0;
regs.edx = (unsigned long)res;
rc = x86_emulate(&ctxt, &emulops);
- if ( rc != X86EMUL_OKAY )
+ if ( rc != X86EMUL_OKAY || !check_eip(vmovdqu_from_mem) )
goto fail;
#if 0 /* Don't use AVX2 instructions for now */
asm ( "vpcmpeqb %%ymm2, %%ymm2, %%ymm2\n\t"
@@ -769,20 +770,19 @@ int main(int argc, char **argv)
memset(res + 10, 0x66, 8);
if ( stack_exec && cpu_has_sse2 )
{
- extern const unsigned char movsd_to_mem[];
+ decl_insn(movsd_to_mem);
asm volatile ( "movlpd %0, %%xmm5\n\t"
"movhpd %0, %%xmm5\n"
- ".pushsection .test, \"a\", @progbits\n"
- "movsd_to_mem: movsd %%xmm5, (%1)\n"
- ".popsection" :: "m" (res[10]), "c" (NULL) );
+ put_insn(movsd_to_mem, "movsd %%xmm5, (%1)")
+ :: "m" (res[10]), "c" (NULL) );
- memcpy(instr, movsd_to_mem, 15);
- regs.eip = (unsigned long)&instr[0];
+ set_insn(movsd_to_mem);
regs.ecx = (unsigned long)(res + 2);
regs.edx = 0;
rc = x86_emulate(&ctxt, &emulops);
- if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) )
+ if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) ||
+ !check_eip(movsd_to_mem) )
goto fail;
printf("okay\n");
}
@@ -795,19 +795,17 @@ int main(int argc, char **argv)
printf("%-40s", "Testing movaps (%edx),%xmm7...");
if ( stack_exec && cpu_has_sse )
{
- extern const unsigned char movaps_from_mem[];
+ decl_insn(movaps_from_mem);
asm volatile ( "xorps %%xmm7, %%xmm7\n"
- ".pushsection .test, \"a\", @progbits\n"
- "movaps_from_mem: movaps (%0), %%xmm7\n"
- ".popsection" :: "d" (NULL) );
+ put_insn(movaps_from_mem, "movaps (%0), %%xmm7")
+ :: "d" (NULL) );
- memcpy(instr, movaps_from_mem, 15);
- regs.eip = (unsigned long)&instr[0];
+ set_insn(movaps_from_mem);
regs.ecx = 0;
regs.edx = (unsigned long)res;
rc = x86_emulate(&ctxt, &emulops);
- if ( rc != X86EMUL_OKAY )
+ if ( rc != X86EMUL_OKAY || !check_eip(movaps_from_mem) )
goto fail;
asm ( "cmpeqps %1, %%xmm7\n\t"
"movmskps %%xmm7, %0" : "=r" (rc) : "m" (res[8]) );
@@ -823,19 +821,18 @@ int main(int argc, char **argv)
memset(res + 10, 0x77, 8);
if ( stack_exec && cpu_has_avx )
{
- extern const unsigned char vmovsd_to_mem[];
+ decl_insn(vmovsd_to_mem);
asm volatile ( "vbroadcastsd %0, %%ymm5\n"
- ".pushsection .test, \"a\", @progbits\n"
- "vmovsd_to_mem: vmovsd %%xmm5, (%1)\n"
- ".popsection" :: "m" (res[10]), "c" (NULL) );
+ put_insn(vmovsd_to_mem, "vmovsd %%xmm5, (%1)")
+ :: "m" (res[10]), "c" (NULL) );
- memcpy(instr, vmovsd_to_mem, 15);
- regs.eip = (unsigned long)&instr[0];
+ set_insn(vmovsd_to_mem);
regs.ecx = (unsigned long)(res + 2);
regs.edx = 0;
rc = x86_emulate(&ctxt, &emulops);
- if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) )
+ if ( (rc != X86EMUL_OKAY) || memcmp(res, res + 8, 32) ||
+ !check_eip(vmovsd_to_mem) )
goto fail;
printf("okay\n");
}
@@ -848,19 +845,17 @@ int main(int argc, char **argv)
printf("%-40s", "Testing vmovaps (%edx),%ymm7...");
if ( stack_exec && cpu_has_avx )
{
- extern const unsigned char vmovaps_from_mem[];
+ decl_insn(vmovaps_from_mem);
asm volatile ( "vxorps %%ymm7, %%ymm7, %%ymm7\n"
- ".pushsection .test, \"a\", @progbits\n"
- "vmovaps_from_mem: vmovaps (%0), %%ymm7\n"
- ".popsection" :: "d" (NULL) );
+ put_insn(vmovaps_from_mem, "vmovaps (%0), %%ymm7")
+ :: "d" (NULL) );
- memcpy(instr, vmovaps_from_mem, 15);
- regs.eip = (unsigned long)&instr[0];
+ set_insn(vmovaps_from_mem);
regs.ecx = 0;
regs.edx = (unsigned long)res;
rc = x86_emulate(&ctxt, &emulops);
- if ( rc != X86EMUL_OKAY )
+ if ( rc != X86EMUL_OKAY || !check_eip(vmovaps_from_mem) )
goto fail;
asm ( "vcmpeqps %1, %%ymm7, %%ymm0\n\t"
"vmovmskps %%ymm0, %0" : "=r" (rc) : "m" (res[8]) );
@@ -871,6 +866,11 @@ int main(int argc, char **argv)
else
printf("skipped\n");
+#undef decl_insn
+#undef put_insn
+#undef set_insn
+#undef check_eip
+
for ( j = 1; j <= 2; j++ )
{
#if defined(__i386__)
diff --git a/xen/Makefile b/xen/Makefile
index 39839a3..134a8bd 100644
--- a/xen/Makefile
+++ b/xen/Makefile
@@ -2,7 +2,7 @@
# All other places this is stored (eg. compile.h) should be autogenerated.
export XEN_VERSION = 4
export XEN_SUBVERSION = 4
-export XEN_EXTRAVERSION ?= .0$(XEN_VENDORVERSION)
+export XEN_EXTRAVERSION ?= .1$(XEN_VENDORVERSION)
export XEN_FULLVERSION = $(XEN_VERSION).$(XEN_SUBVERSION)$(XEN_EXTRAVERSION)
-include xen-version
diff --git a/xen/arch/arm/Rules.mk b/xen/arch/arm/Rules.mk
index aaa203e..2db39ad 100644
--- a/xen/arch/arm/Rules.mk
+++ b/xen/arch/arm/Rules.mk
@@ -27,6 +27,7 @@ endif
ifeq ($(TARGET_SUBARCH),arm64)
CFLAGS += -mcpu=generic
+CFLAGS += -mgeneral-regs-only # No fp registers etc
arm32 := n
arm64 := y
endif
@@ -99,4 +100,12 @@ CFLAGS-$(EARLY_PRINTK) += -DEARLY_PRINTK_INC=\"debug-$(EARLY_PRINTK_INC).inc\"
CFLAGS-$(EARLY_PRINTK) += -DEARLY_PRINTK_BAUD=$(EARLY_PRINTK_BAUD)
CFLAGS-$(EARLY_PRINTK) += -DEARLY_UART_BASE_ADDRESS=$(EARLY_UART_BASE_ADDRESS)
CFLAGS-$(EARLY_PRINTK) += -DEARLY_UART_REG_SHIFT=$(EARLY_UART_REG_SHIFT)
+
+else # !debug
+
+ifneq ($(CONFIG_EARLY_PRINTK),)
+# Early printk is dependant on a debug build.
+$(error CONFIG_EARLY_PRINTK enabled for non-debug build)
+endif
+
endif
diff --git a/xen/arch/arm/arm32/head.S b/xen/arch/arm/arm32/head.S
index 96230ac..5bc23cc 100644
--- a/xen/arch/arm/arm32/head.S
+++ b/xen/arch/arm/arm32/head.S
@@ -372,9 +372,20 @@ paging:
ldr r4, =BOOT_FDT_VIRT_START
mov r4, r4, lsr #18 /* Slot for BOOT_FDT_VIRT_START */
strd r2, r3, [r1, r4] /* Map it in the early fdt slot */
- dsb
1:
+ /*
+ * Flush the TLB in case the 1:1 mapping happens to clash with
+ * the virtual addresses used by the fixmap or DTB.
+ */
+ dsb /* Ensure any page table updates made above
+ * have occurred. */
+
+ isb
+ mcr CP32(r0, TLBIALLH) /* Flush hypervisor TLB */
+ dsb /* Ensure completion of TLB flush */
+ isb
+
PRINT("- Ready -\r\n")
/* The boot CPU should go straight into C now */
diff --git a/xen/arch/arm/arm64/head.S b/xen/arch/arm/arm64/head.S
index 31afdd0..be44f67 100644
--- a/xen/arch/arm/arm64/head.S
+++ b/xen/arch/arm/arm64/head.S
@@ -382,9 +382,20 @@ paging:
ldr x1, =BOOT_FDT_VIRT_START
lsr x1, x1, #18 /* x4 := Slot for BOOT_FDT_VIRT_START */
str x2, [x4, x1] /* Map it in the early fdt slot */
- dsb sy
1:
+ /*
+ * Flush the TLB in case the 1:1 mapping happens to clash with
+ * the virtual addresses used by the fixmap or DTB.
+ */
+ dsb sy /* Ensure any page table updates made above
+ * have occurred. */
+
+ isb
+ tlbi alle2
+ dsb sy /* Ensure completion of TLB flush */
+ isb
+
PRINT("- Ready -\r\n")
/* The boot CPU should go straight into C now */
diff --git a/xen/arch/arm/domain.c b/xen/arch/arm/domain.c
index 8f20fdf..67de12a 100644
--- a/xen/arch/arm/domain.c
+++ b/xen/arch/arm/domain.c
@@ -59,11 +59,12 @@ void idle_loop(void)
static void ctxt_switch_from(struct vcpu *p)
{
+ p2m_save_state(p);
+
/* CP 15 */
p->arch.csselr = READ_SYSREG(CSSELR_EL1);
/* Control Registers */
- p->arch.sctlr = READ_SYSREG(SCTLR_EL1);
p->arch.cpacr = READ_SYSREG(CPACR_EL1);
p->arch.contextidr = READ_SYSREG(CONTEXTIDR_EL1);
@@ -72,6 +73,7 @@ static void ctxt_switch_from(struct vcpu *p)
p->arch.tpidr_el1 = READ_SYSREG(TPIDR_EL1);
/* Arch timer */
+ p->arch.cntkctl = READ_SYSREG32(CNTKCTL_EL1);
virt_timer_save(p);
if ( is_pv32_domain(p->domain) && cpu_has_thumbee )
@@ -134,14 +136,7 @@ static void ctxt_switch_from(struct vcpu *p)
static void ctxt_switch_to(struct vcpu *n)
{
- register_t hcr;
-
- hcr = READ_SYSREG(HCR_EL2);
- WRITE_SYSREG(hcr & ~HCR_VM, HCR_EL2);
- isb();
-
- p2m_load_VTTBR(n->domain);
- isb();
+ p2m_restore_state(n);
WRITE_SYSREG32(n->domain->arch.vpidr, VPIDR_EL2);
WRITE_SYSREG(n->arch.vmpidr, VMPIDR_EL2);
@@ -189,7 +184,6 @@ static void ctxt_switch_to(struct vcpu *n)
isb();
/* Control Registers */
- WRITE_SYSREG(n->arch.sctlr, SCTLR_EL1);
WRITE_SYSREG(n->arch.cpacr, CPACR_EL1);
WRITE_SYSREG(n->arch.contextidr, CONTEXTIDR_EL1);
@@ -214,16 +208,9 @@ static void ctxt_switch_to(struct vcpu *n)
isb();
- if ( is_pv32_domain(n->domain) )
- hcr &= ~HCR_RW;
- else
- hcr |= HCR_RW;
-
- WRITE_SYSREG(hcr, HCR_EL2);
- isb();
-
/* This is could trigger an hardware interrupt from the virtual
* timer. The interrupt needs to be injected into the guest. */
+ WRITE_SYSREG32(n->arch.cntkctl, CNTKCTL_EL1);
virt_timer_restore(n);
}
@@ -407,7 +394,7 @@ struct domain *alloc_domain_struct(void)
return NULL;
clear_page(d);
- d->arch.grant_table_gpfn = xmalloc_array(xen_pfn_t, max_nr_grant_frames);
+ d->arch.grant_table_gpfn = xzalloc_array(xen_pfn_t, max_nr_grant_frames);
return d;
}
diff --git a/xen/arch/arm/domain_build.c b/xen/arch/arm/domain_build.c
index 5ca2f15..8cbd776 100644
--- a/xen/arch/arm/domain_build.c
+++ b/xen/arch/arm/domain_build.c
@@ -967,7 +967,7 @@ static void initrd_load(struct kernel_info *kinfo)
s = offs & ~PAGE_MASK;
l = min(PAGE_SIZE - s, len);
- rc = gvirt_to_maddr(load_addr + offs, &ma);
+ rc = gvirt_to_maddr(load_addr + offs, &ma, GV2M_WRITE);
if ( rc )
{
panic("Unable to translate guest address");
@@ -986,6 +986,7 @@ static void initrd_load(struct kernel_info *kinfo)
int construct_dom0(struct domain *d)
{
struct kernel_info kinfo = {};
+ struct vcpu *saved_current;
int rc, i, cpu;
struct vcpu *v = d->vcpu[0];
@@ -1020,15 +1021,13 @@ int construct_dom0(struct domain *d)
if ( rc < 0 )
return rc;
- /* The following loads use the domain's p2m */
- p2m_load_VTTBR(d);
-#ifdef CONFIG_ARM_64
- d->arch.type = kinfo.type;
- if ( is_pv32_domain(d) )
- WRITE_SYSREG(READ_SYSREG(HCR_EL2) & ~HCR_RW, HCR_EL2);
- else
- WRITE_SYSREG(READ_SYSREG(HCR_EL2) | HCR_RW, HCR_EL2);
-#endif
+ /*
+ * The following loads use the domain's p2m and require current to
+ * be a vcpu of the domain, temporarily switch
+ */
+ saved_current = current;
+ p2m_restore_state(v);
+ set_current(v);
/*
* kernel_load will determine the placement of the initrd & fdt in
@@ -1039,6 +1038,10 @@ int construct_dom0(struct domain *d)
initrd_load(&kinfo);
dtb_load(&kinfo);
+ /* Now that we are done restore the original p2m and current. */
+ set_current(saved_current);
+ p2m_restore_state(saved_current);
+
discard_initial_modules();
v->is_initialised = 1;
diff --git a/xen/arch/arm/guestcopy.c b/xen/arch/arm/guestcopy.c
index cea5f97..0173597 100644
--- a/xen/arch/arm/guestcopy.c
+++ b/xen/arch/arm/guestcopy.c
@@ -1,6 +1,8 @@
#include <xen/config.h>
#include <xen/lib.h>
#include <xen/domain_page.h>
+#include <xen/sched.h>
+#include <asm/current.h>
#include <asm/mm.h>
#include <asm/guest_access.h>
@@ -13,20 +15,22 @@ static unsigned long raw_copy_to_guest_helper(void *to, const void *from,
while ( len )
{
- paddr_t g;
void *p;
unsigned size = min(len, (unsigned)PAGE_SIZE - offset);
+ struct page_info *page;
- if ( gvirt_to_maddr((vaddr_t) to, &g) )
+ page = get_page_from_gva(current->domain, (vaddr_t) to, GV2M_WRITE);
+ if ( page == NULL )
return len;
- p = map_domain_page(g>>PAGE_SHIFT);
+ p = __map_domain_page(page);
p += offset;
memcpy(p, from, size);
if ( flush_dcache )
clean_xen_dcache_va_range(p, size);
unmap_domain_page(p - offset);
+ put_page(page);
len -= size;
from += size;
to += size;
@@ -58,18 +62,20 @@ unsigned long raw_clear_guest(void *to, unsigned len)
while ( len )
{
- paddr_t g;
void *p;
unsigned size = min(len, (unsigned)PAGE_SIZE - offset);
+ struct page_info *page;
- if ( gvirt_to_maddr((vaddr_t) to, &g) )
+ page = get_page_from_gva(current->domain, (vaddr_t) to, GV2M_WRITE);
+ if ( page == NULL )
return len;
- p = map_domain_page(g>>PAGE_SHIFT);
+ p = __map_domain_page(page);
p += offset;
memset(p, 0x00, size);
unmap_domain_page(p - offset);
+ put_page(page);
len -= size;
to += size;
/*
@@ -88,19 +94,21 @@ unsigned long raw_copy_from_guest(void *to, const void __user *from, unsigned le
while ( len )
{
- paddr_t g;
void *p;
unsigned size = min(len, (unsigned)(PAGE_SIZE - offset));
+ struct page_info *page;
- if ( gvirt_to_maddr((vaddr_t) from & PAGE_MASK, &g) )
+ page = get_page_from_gva(current->domain, (vaddr_t) from, GV2M_READ);
+ if ( page == NULL )
return len;
- p = map_domain_page(g>>PAGE_SHIFT);
+ p = __map_domain_page(page);
p += ((vaddr_t)from & (~PAGE_MASK));
memcpy(to, p, size);
unmap_domain_page(p);
+ put_page(page);
len -= size;
from += size;
to += size;
diff --git a/xen/arch/arm/kernel.c b/xen/arch/arm/kernel.c
index 1e3107d..69c7d43 100644
--- a/xen/arch/arm/kernel.c
+++ b/xen/arch/arm/kernel.c
@@ -141,7 +141,7 @@ static void kernel_zimage_load(struct kernel_info *info)
s = offs & ~PAGE_MASK;
l = min(PAGE_SIZE - s, len);
- rc = gvirt_to_maddr(load_addr + offs, &ma);
+ rc = gvirt_to_maddr(load_addr + offs, &ma, GV2M_WRITE);
if ( rc )
{
panic("Unable to map translate guest address");
diff --git a/xen/arch/arm/p2m.c b/xen/arch/arm/p2m.c
index d00c882..bc81b67 100644
--- a/xen/arch/arm/p2m.c
+++ b/xen/arch/arm/p2m.c
@@ -44,6 +44,34 @@ void p2m_load_VTTBR(struct domain *d)
isb(); /* Ensure update is visible */
}
+void p2m_save_state(struct vcpu *p)
+{
+ p->arch.sctlr = READ_SYSREG(SCTLR_EL1);
+}
+
+void p2m_restore_state(struct vcpu *n)
+{
+ register_t hcr;
+
+ hcr = READ_SYSREG(HCR_EL2);
+ WRITE_SYSREG(hcr & ~HCR_VM, HCR_EL2);
+ isb();
+
+ p2m_load_VTTBR(n->domain);
+ isb();
+
+ if ( is_pv32_domain(n->domain) )
+ hcr &= ~HCR_RW;
+ else
+ hcr |= HCR_RW;
+
+ WRITE_SYSREG(n->arch.sctlr, SCTLR_EL1);
+ isb();
+
+ WRITE_SYSREG(hcr, HCR_EL2);
+ isb();
+}
+
static int p2m_first_level_index(paddr_t addr)
{
/*
@@ -655,6 +683,34 @@ unsigned long gmfn_to_mfn(struct domain *d, unsigned long gpfn)
return p >> PAGE_SHIFT;
}
+struct page_info *get_page_from_gva(struct domain *d, vaddr_t va,
+ unsigned long flags)
+{
+ struct p2m_domain *p2m = &d->arch.p2m;
+ struct page_info *page = NULL;
+ paddr_t maddr;
+
+ ASSERT(d == current->domain);
+
+ spin_lock(&p2m->lock);
+
+ if ( gvirt_to_maddr(va, &maddr, flags) )
+ goto err;
+
+ if ( !mfn_valid(maddr >> PAGE_SHIFT) )
+ goto err;
+
+ page = mfn_to_page(maddr >> PAGE_SHIFT);
+ ASSERT(page);
+
+ if ( unlikely(!get_page(page, d)) )
+ page = NULL;
+
+err:
+ spin_unlock(&p2m->lock);
+ return page;
+}
+
/*
* Local variables:
* mode: C
diff --git a/xen/arch/arm/psci.c b/xen/arch/arm/psci.c
index 25a8697..b6360d5 100644
--- a/xen/arch/arm/psci.c
+++ b/xen/arch/arm/psci.c
@@ -54,7 +54,8 @@ static uint32_t psci_cpu_on_nr;
int call_psci_cpu_on(int cpu)
{
- return __invoke_psci_fn_smc(psci_cpu_on_nr, cpu, __pa(init_secondary), 0);
+ return __invoke_psci_fn_smc(psci_cpu_on_nr,
+ cpu_logical_map(cpu), __pa(init_secondary), 0);
}
int __init psci_init(void)
@@ -96,3 +97,12 @@ int __init psci_init(void)
return 0;
}
+
+/*
+ * Local variables:
+ * mode: C
+ * c-file-style: "BSD"
+ * c-basic-offset: 4
+ * indent-tabs-mode: nil
+ * End:
+ */
diff --git a/xen/arch/arm/time.c b/xen/arch/arm/time.c
index 81e3e28..5374bf7 100644
--- a/xen/arch/arm/time.c
+++ b/xen/arch/arm/time.c
@@ -234,7 +234,6 @@ void __cpuinit init_timer_interrupt(void)
{
/* Sensible defaults */
WRITE_SYSREG64(0, CNTVOFF_EL2); /* No VM-specific offset */
- WRITE_SYSREG32(0, CNTKCTL_EL1); /* No user-mode access */
#if USE_HYP_TIMER
/* Do not let the VMs program the physical timer, only read the physical counter */
WRITE_SYSREG32(CNTHCTL_PA, CNTHCTL_EL2);
diff --git a/xen/arch/arm/traps.c b/xen/arch/arm/traps.c
index 21c7b26..4c910c8 100644
--- a/xen/arch/arm/traps.c
+++ b/xen/arch/arm/traps.c
@@ -17,6 +17,7 @@
*/
#include <xen/config.h>
+#include <xen/stdbool.h>
#include <xen/init.h>
#include <xen/string.h>
#include <xen/version.h>
@@ -74,9 +75,22 @@ void __cpuinit init_traps(void)
/* Setup Hyp vector base */
WRITE_SYSREG((vaddr_t)hyp_traps_vector, VBAR_EL2);
+ /* Trap Debug and Performance Monitor accesses */
+ WRITE_SYSREG(HDCR_TDRA|HDCR_TDOSA|HDCR_TDA|HDCR_TPM|HDCR_TPMCR,
+ MDCR_EL2);
+
+ /* Trap CP15 c15 used for implementation defined registers */
+ WRITE_SYSREG(HSTR_T(15), HSTR_EL2);
+
+ /* Trap all coprocessor registers (0-13) except cp10 and cp11 for VFP
+ * /!\ All processors except cp10 and cp11 cannot be used in Xen
+ */
+ WRITE_SYSREG((HCPTR_CP_MASK & ~(HCPTR_CP(10) | HCPTR_CP(11))) | HCPTR_TTA,
+ CPTR_EL2);
+
/* Setup hypervisor traps */
- WRITE_SYSREG(HCR_PTW|HCR_BSU_OUTER|HCR_AMO|HCR_IMO|HCR_VM|HCR_TWI|HCR_TSC|
- HCR_TAC, HCR_EL2);
+ WRITE_SYSREG(HCR_PTW|HCR_BSU_OUTER|HCR_AMO|HCR_IMO|HCR_FMO|HCR_VM|
+ HCR_TWI|HCR_TSC|HCR_TAC|HCR_SWIO|HCR_TIDCP, HCR_EL2);
isb();
}
@@ -272,7 +286,7 @@ static void cpsr_switch_mode(struct cpu_user_regs *regs, int mode)
regs->cpsr |= PSR_BIG_ENDIAN;
}
-static vaddr_t exception_handler(vaddr_t offset)
+static vaddr_t exception_handler32(vaddr_t offset)
{
uint32_t sctlr = READ_SYSREG32(SCTLR_EL1);
@@ -304,7 +318,7 @@ static void inject_undef32_exception(struct cpu_user_regs *regs)
regs->lr_und = regs->pc32 + return_offset;
/* Branch to exception vector */
- regs->pc32 = exception_handler(VECTOR32_UND);
+ regs->pc32 = exception_handler32(VECTOR32_UND);
}
/* Injects an Abort exception into the current vcpu, PC is the exact
@@ -330,7 +344,7 @@ static void inject_abt32_exception(struct cpu_user_regs *regs,
regs->spsr_abt = spsr;
regs->lr_abt = regs->pc32 + return_offset;
- regs->pc32 = exception_handler(prefetch ? VECTOR32_PABT : VECTOR32_DABT);
+ regs->pc32 = exception_handler32(prefetch ? VECTOR32_PABT : VECTOR32_DABT);
/* Inject a debug fault, best we can do right now */
if ( READ_SYSREG(TCR_EL1) & TTBCR_EAE )
@@ -383,9 +397,28 @@ static void inject_pabt32_exception(struct cpu_user_regs *regs,
}
#ifdef CONFIG_ARM_64
+/*
+ * Take care to call this while regs contains the original faulting
+ * state and not the (partially constructed) exception state.
+ */
+static vaddr_t exception_handler64(struct cpu_user_regs *regs, vaddr_t offset)
+{
+ vaddr_t base = READ_SYSREG(VBAR_EL1);
+
+ if ( usr_mode(regs) )
+ base += VECTOR64_LOWER32_BASE;
+ else if ( psr_mode(regs->cpsr,PSR_MODE_EL0t) )
+ base += VECTOR64_LOWER64_BASE;
+ else /* Otherwise must be from kernel mode */
+ base += VECTOR64_CURRENT_SPx_BASE;
+
+ return base + offset;
+}
+
/* Inject an undefined exception into a 64 bit guest */
static void inject_undef64_exception(struct cpu_user_regs *regs, int instr_len)
{
+ vaddr_t handler;
union hsr esr = {
.iss = 0,
.len = instr_len,
@@ -394,12 +427,14 @@ static void inject_undef64_exception(struct cpu_user_regs *regs, int instr_len)
BUG_ON( is_pv32_domain(current->domain) );
+ handler = exception_handler64(regs, VECTOR64_SYNC_OFFSET);
+
regs->spsr_el1 = regs->cpsr;
regs->elr_el1 = regs->pc;
regs->cpsr = PSR_MODE_EL1h | PSR_ABT_MASK | PSR_FIQ_MASK | \
PSR_IRQ_MASK | PSR_DBG_MASK;
- regs->pc = READ_SYSREG(VBAR_EL1) + VECTOR64_CURRENT_SPx_SYNC;
+ regs->pc = handler;
WRITE_SYSREG32(esr.bits, ESR_EL1);
}
@@ -410,6 +445,7 @@ static void inject_abt64_exception(struct cpu_user_regs *regs,
register_t addr,
int instr_len)
{
+ vaddr_t handler;
union hsr esr = {
.iss = 0,
.len = instr_len,
@@ -431,12 +467,14 @@ static void inject_abt64_exception(struct cpu_user_regs *regs,
BUG_ON( is_pv32_domain(current->domain) );
+ handler = exception_handler64(regs, VECTOR64_SYNC_OFFSET);
+
regs->spsr_el1 = regs->cpsr;
regs->elr_el1 = regs->pc;
regs->cpsr = PSR_MODE_EL1h | PSR_ABT_MASK | PSR_FIQ_MASK | \
PSR_IRQ_MASK | PSR_DBG_MASK;
- regs->pc = READ_SYSREG(VBAR_EL1) + VECTOR64_CURRENT_SPx_SYNC;
+ regs->pc = handler;
WRITE_SYSREG(addr, FAR_EL1);
WRITE_SYSREG32(esr.bits, ESR_EL1);
@@ -458,6 +496,17 @@ static void inject_iabt64_exception(struct cpu_user_regs *regs,
#endif
+static void inject_undef_exception(struct cpu_user_regs *regs,
+ int instr_len)
+{
+ if ( is_pv32_domain(current->domain) )
+ inject_undef32_exception(regs);
+#ifdef CONFIG_ARM_64
+ else
+ inject_undef64_exception(regs, instr_len);
+#endif
+}
+
static void inject_iabt_exception(struct cpu_user_regs *regs,
register_t addr,
int instr_len)
@@ -683,7 +732,17 @@ static void _show_registers(struct cpu_user_regs *regs,
show_registers_32(regs, ctxt, guest_mode, v);
#ifdef CONFIG_ARM_64
else if ( is_pv64_domain(v->domain) )
- show_registers_64(regs, ctxt, guest_mode, v);
+ {
+ if ( psr_mode_is_32bit(regs->cpsr) )
+ {
+ BUG_ON(!usr_mode(regs));
+ show_registers_32(regs, ctxt, guest_mode, v);
+ }
+ else
+ {
+ show_registers_64(regs, ctxt, guest_mode, v);
+ }
+ }
#endif
}
else
@@ -763,7 +822,7 @@ static void show_guest_stack(struct vcpu *v, struct cpu_user_regs *regs)
{
int i;
vaddr_t sp;
- paddr_t stack_phys;
+ struct page_info *page;
void *mapped;
unsigned long *stack, addr;
@@ -823,13 +882,20 @@ static void show_guest_stack(struct vcpu *v, struct cpu_user_regs *regs)
printk("Guest stack trace from sp=%"PRIvaddr":\n ", sp);
- if ( gvirt_to_maddr(sp, &stack_phys) )
+ if ( sp & ( sizeof(long) - 1 ) )
+ {
+ printk("Stack is misaligned\n");
+ return;
+ }
+
+ page = get_page_from_gva(current->domain, sp, GV2M_READ);
+ if ( page == NULL )
{
printk("Failed to convert stack to physical address\n");
return;
}
- mapped = map_domain_page(stack_phys >> PAGE_SHIFT);
+ mapped = __map_domain_page(page);
stack = mapped + (sp & ~PAGE_MASK);
@@ -847,7 +913,7 @@ static void show_guest_stack(struct vcpu *v, struct cpu_user_regs *regs)
printk("Stack empty.");
printk("\n");
unmap_domain_page(mapped);
-
+ put_page(page);
}
#define STACK_BEFORE_EXCEPTION(regs) ((register_t*)(regs)->sp)
@@ -978,7 +1044,7 @@ void do_unexpected_trap(const char *msg, struct cpu_user_regs *regs)
{
printk("CPU%d: Unexpected Trap: %s\n", smp_processor_id(), msg);
show_execution_state(regs);
- while(1);
+ panic("CPU%d: Unexpected Trap: %s\n", smp_processor_id(), msg);
}
typedef register_t (*arm_hypercall_fn_t)(
@@ -1011,6 +1077,7 @@ static arm_hypercall_t arm_hypercall_table[] = {
HYPERCALL(sysctl, 2),
HYPERCALL(hvm_op, 2),
HYPERCALL(grant_table_op, 3),
+ HYPERCALL(multicall, 2),
HYPERCALL_ARM(vcpu_op, 3),
};
@@ -1158,6 +1225,24 @@ static void do_trap_hypercall(struct cpu_user_regs *regs, register_t *nr,
#endif
}
+static bool_t check_multicall_32bit_clean(struct multicall_entry *multi)
+{
+ int i;
+
+ for ( i = 0; i < arm_hypercall_table[multi->op].nr_args; i++ )
+ {
+ if ( unlikely(multi->args[i] & 0xffffffff00000000ULL) )
+ {
+ printk("%pv: multicall argument %d is not 32-bit clean %"PRIx64"\n",
+ current, i, multi->args[i]);
+ domain_crash(current->domain);
+ return false;
+ }
+ }
+
+ return true;
+}
+
void do_multicall_call(struct multicall_entry *multi)
{
arm_hypercall_fn_t call = NULL;
@@ -1175,9 +1260,13 @@ void do_multicall_call(struct multicall_entry *multi)
return;
}
+ if ( is_pv32_domain(current->domain) &&
+ !check_multicall_32bit_clean(multi) )
+ return;
+
multi->result = call(multi->args[0], multi->args[1],
- multi->args[2], multi->args[3],
- multi->args[4]);
+ multi->args[2], multi->args[3],
+ multi->args[4]);
}
/*
@@ -1349,11 +1438,45 @@ static void do_cp15_32(struct cpu_user_regs *regs,
if ( cp32.read )
*r = v->arch.actlr;
break;
+
+ /* We could trap ID_DFR0 and tell the guest we don't support
+ * performance monitoring, but Linux doesn't check the ID_DFR0.
+ * Therefore it will read PMCR.
+ *
+ * We tell the guest we have 0 counters. Unfortunately we must
+ * always support PMCCNTR (the cyle counter): we just RAZ/WI for all
+ * PM register, which doesn't crash the kernel at least
+ */
+ case HSR_CPREG32(PMCR):
+ case HSR_CPREG32(PMCNTENSET):
+ case HSR_CPREG32(PMCNTENCLR):
+ case HSR_CPREG32(PMOVSR):
+ case HSR_CPREG32(PMSWINC):
+ case HSR_CPREG32(PMSELR):
+ case HSR_CPREG32(PMCEID0):
+ case HSR_CPREG32(PMCEID1):
+ case HSR_CPREG32(PMCCNTR):
+ case HSR_CPREG32(PMXEVCNTR):
+ case HSR_CPREG32(PMXEVCNR):
+ case HSR_CPREG32(PMUSERENR):
+ case HSR_CPREG32(PMINTENSET):
+ case HSR_CPREG32(PMINTENCLR):
+ case HSR_CPREG32(PMOVSSET):
+ if ( cp32.read )
+ *r = 0;
+ break;
+
default:
- printk("%s p15, %d, r%d, cr%d, cr%d, %d @ 0x%"PRIregister"\n",
- cp32.read ? "mrc" : "mcr",
- cp32.op1, cp32.reg, cp32.crn, cp32.crm, cp32.op2, regs->pc);
- panic("unhandled 32-bit CP15 access %#x", hsr.bits & HSR_CP32_REGS_MASK);
+#ifndef NDEBUG
+ gdprintk(XENLOG_ERR,
+ "%s p15, %d, r%d, cr%d, cr%d, %d @ 0x%"PRIregister"\n",
+ cp32.read ? "mrc" : "mcr",
+ cp32.op1, cp32.reg, cp32.crn, cp32.crm, cp32.op2, regs->pc);
+ gdprintk(XENLOG_ERR, "unhandled 32-bit CP15 access %#x\n",
+ hsr.bits & HSR_CP32_REGS_MASK);
+#endif
+ inject_undef_exception(regs, hsr.len);
+ return;
}
advance_pc(regs, hsr);
}
@@ -1361,8 +1484,6 @@ static void do_cp15_32(struct cpu_user_regs *regs,
static void do_cp15_64(struct cpu_user_regs *regs,
union hsr hsr)
{
- struct hsr_cp64 cp64 = hsr.cp64;
-
if ( !check_conditional_instr(regs, hsr) )
{
advance_pc(regs, hsr);
@@ -1380,22 +1501,161 @@ static void do_cp15_64(struct cpu_user_regs *regs,
}
break;
default:
- printk("%s p15, %d, r%d, r%d, cr%d @ 0x%"PRIregister"\n",
- cp64.read ? "mrrc" : "mcrr",
- cp64.op1, cp64.reg1, cp64.reg2, cp64.crm, regs->pc);
- panic("unhandled 64-bit CP15 access %#x", hsr.bits & HSR_CP64_REGS_MASK);
+ {
+#ifndef NDEBUG
+ struct hsr_cp64 cp64 = hsr.cp64;
+
+ gdprintk(XENLOG_ERR,
+ "%s p15, %d, r%d, r%d, cr%d @ 0x%"PRIregister"\n",
+ cp64.read ? "mrrc" : "mcrr",
+ cp64.op1, cp64.reg1, cp64.reg2, cp64.crm, regs->pc);
+ gdprintk(XENLOG_ERR, "unhandled 64-bit CP15 access %#x\n",
+ hsr.bits & HSR_CP64_REGS_MASK);
+#endif
+ inject_undef_exception(regs, hsr.len);
+ return;
+ }
+ }
+ advance_pc(regs, hsr);
+}
+
+static void do_cp14_32(struct cpu_user_regs *regs, union hsr hsr)
+{
+ struct hsr_cp32 cp32 = hsr.cp32;
+ uint32_t *r = (uint32_t *)select_user_reg(regs, cp32.reg);
+ struct domain *d = current->domain;
+
+ if ( !check_conditional_instr(regs, hsr) )
+ {
+ advance_pc(regs, hsr);
+ return;
+ }
+
+ switch ( hsr.bits & HSR_CP32_REGS_MASK )
+ {
+ case HSR_CPREG32(DBGDIDR):
+
+ /* Read-only register */
+ if ( !cp32.read )
+ goto bad_cp;
+
+ /* Implement the minimum requirements:
+ * - Number of watchpoints: 1
+ * - Number of breakpoints: 2
+ * - Version: ARMv7 v7.1
+ * - Variant and Revision bits match MDIR
+ */
+ *r = (1 << 24) | (5 << 16);
+ *r |= ((d->arch.vpidr >> 20) & 0xf) | (d->arch.vpidr & 0xf);
+ break;
+
+ case HSR_CPREG32(DBGDSCRINT):
+ case HSR_CPREG32(DBGDSCREXT):
+ /* Implement debug status and control register as RAZ/WI.
+ * The OS won't use Hardware debug if MDBGen not set
+ */
+ if ( cp32.read )
+ *r = 0;
+ break;
+ case HSR_CPREG32(DBGVCR):
+ case HSR_CPREG32(DBGOSLAR):
+ case HSR_CPREG32(DBGBVR0):
+ case HSR_CPREG32(DBGBCR0):
+ case HSR_CPREG32(DBGWVR0):
+ case HSR_CPREG32(DBGWCR0):
+ case HSR_CPREG32(DBGBVR1):
+ case HSR_CPREG32(DBGBCR1):
+ case HSR_CPREG32(DBGOSDLR):
+ /* RAZ/WI */
+ if ( cp32.read )
+ *r = 0;
+ break;
+
+ default:
+bad_cp:
+#ifndef NDEBUG
+ gdprintk(XENLOG_ERR,
+ "%s p14, %d, r%d, cr%d, cr%d, %d @ 0x%"PRIregister"\n",
+ cp32.read ? "mrc" : "mcr",
+ cp32.op1, cp32.reg, cp32.crn, cp32.crm, cp32.op2, regs->pc);
+ gdprintk(XENLOG_ERR, "unhandled 32-bit cp14 access %#x\n",
+ hsr.bits & HSR_CP32_REGS_MASK);
+#endif
+ inject_undef_exception(regs, hsr.len);
+ return;
}
+
advance_pc(regs, hsr);
}
+static void do_cp14_dbg(struct cpu_user_regs *regs, union hsr hsr)
+{
+ if ( !check_conditional_instr(regs, hsr) )
+ {
+ advance_pc(regs, hsr);
+ return;
+ }
+
+ inject_undef_exception(regs, hsr.len);
+}
+
+static void do_cp(struct cpu_user_regs *regs, union hsr hsr)
+{
+ if ( !check_conditional_instr(regs, hsr) )
+ {
+ advance_pc(regs, hsr);
+ return;
+ }
+
+ inject_undef_exception(regs, hsr.len);
+}
+
#ifdef CONFIG_ARM_64
static void do_sysreg(struct cpu_user_regs *regs,
union hsr hsr)
{
- struct hsr_sysreg sysreg = hsr.sysreg;
+ register_t *x = select_user_reg(regs, hsr.sysreg.reg);
switch ( hsr.bits & HSR_SYSREG_REGS_MASK )
{
+ /* RAZ/WI registers: */
+ /* - Debug */
+ case HSR_SYSREG_MDSCR_EL1:
+ /* - Perf monitors */
+ case HSR_SYSREG_PMINTENSET_EL1:
+ case HSR_SYSREG_PMINTENCLR_EL1:
+ case HSR_SYSREG_PMCR_EL0:
+ case HSR_SYSREG_PMCNTENSET_EL0:
+ case HSR_SYSREG_PMCNTENCLR_EL0:
+ case HSR_SYSREG_PMOVSCLR_EL0:
+ case HSR_SYSREG_PMSWINC_EL0:
+ case HSR_SYSREG_PMSELR_EL0:
+ case HSR_SYSREG_PMCEID0_EL0:
+ case HSR_SYSREG_PMCEID1_EL0:
+ case HSR_SYSREG_PMCCNTR_EL0:
+ case HSR_SYSREG_PMXEVTYPER_EL0:
+ case HSR_SYSREG_PMXEVCNTR_EL0:
+ case HSR_SYSREG_PMUSERENR_EL0:
+ case HSR_SYSREG_PMOVSSET_EL0:
+ /* - Breakpoints */
+ HSR_SYSREG_DBG_CASES(DBGBVR):
+ HSR_SYSREG_DBG_CASES(DBGBCR):
+ /* - Watchpoints */
+ HSR_SYSREG_DBG_CASES(DBGWVR):
+ HSR_SYSREG_DBG_CASES(DBGWCR):
+ /* - Double Lock Register */
+ case HSR_SYSREG_OSDLR_EL1:
+ if ( hsr.sysreg.read )
+ *x = 0;
+ /* else: write ignored */
+ break;
+
+ /* Write only, Write ignore registers: */
+ case HSR_SYSREG_OSLAR_EL1:
+ if ( hsr.sysreg.read )
+ goto bad_sysreg;
+ /* else: write ignored */
+ break;
case HSR_SYSREG_CNTP_CTL_EL0:
case HSR_SYSREG_CNTP_TVAL_EL0:
if ( !vtimer_emulate(regs, hsr) )
@@ -1406,15 +1666,25 @@ static void do_sysreg(struct cpu_user_regs *regs,
}
break;
default:
- printk("%s %d, %d, c%d, c%d, %d %s x%d @ 0x%"PRIregister"\n",
- sysreg.read ? "mrs" : "msr",
- sysreg.op0, sysreg.op1,
- sysreg.crn, sysreg.crm,
- sysreg.op2,
- sysreg.read ? "=>" : "<=",
- sysreg.reg, regs->pc);
- panic("unhandled 64-bit sysreg access %#x",
- hsr.bits & HSR_SYSREG_REGS_MASK);
+ bad_sysreg:
+ {
+ struct hsr_sysreg sysreg = hsr.sysreg;
+#ifndef NDEBUG
+
+ gdprintk(XENLOG_ERR,
+ "%s %d, %d, c%d, c%d, %d %s x%d @ 0x%"PRIregister"\n",
+ sysreg.read ? "mrs" : "msr",
+ sysreg.op0, sysreg.op1,
+ sysreg.crn, sysreg.crm,
+ sysreg.op2,
+ sysreg.read ? "=>" : "<=",
+ sysreg.reg, regs->pc);
+ gdprintk(XENLOG_ERR, "unhandled 64-bit sysreg access %#x\n",
+ hsr.bits & HSR_SYSREG_REGS_MASK);
+#endif
+ inject_undef_exception(regs, sysreg.len);
+ return;
+ }
}
regs->pc += 4;
@@ -1543,6 +1813,17 @@ asmlinkage void do_trap_hypervisor(struct cpu_user_regs *regs)
{
union hsr hsr = { .bits = READ_SYSREG32(ESR_EL2) };
+ /*
+ * We currently do not handle 32-bit userspace on 64-bit kernels
+ * correctly (See XSA-102). Until that is resolved we treat any
+ * trap from 32-bit userspace on 64-bit kernel as undefined.
+ */
+ if ( is_pv64_domain(current->domain) && psr_mode_is_32bit(regs->cpsr) )
+ {
+ inject_undef_exception(regs, hsr.len);
+ return;
+ }
+
switch (hsr.ec) {
case HSR_EC_WFI_WFE:
if ( !check_conditional_instr(regs, hsr) )
@@ -1572,6 +1853,21 @@ asmlinkage void do_trap_hypervisor(struct cpu_user_regs *regs)
goto bad_trap;
do_cp15_64(regs, hsr);
break;
+ case HSR_EC_CP14_32:
+ if ( !is_pv32_domain(current->domain) )
+ goto bad_trap;
+ do_cp14_32(regs, hsr);
+ break;
+ case HSR_EC_CP14_DBG:
+ if ( !is_pv32_domain(current->domain) )
+ goto bad_trap;
+ do_cp14_dbg(regs, hsr);
+ break;
+ case HSR_EC_CP:
+ if ( !is_pv32_domain(current->domain) )
+ goto bad_trap;
+ do_cp(regs, hsr);
+ break;
case HSR_EC_SMC32:
inject_undef32_exception(regs);
break;
diff --git a/xen/arch/arm/vgic.c b/xen/arch/arm/vgic.c
index 553411d..850006c 100644
--- a/xen/arch/arm/vgic.c
+++ b/xen/arch/arm/vgic.c
@@ -89,8 +89,17 @@ int domain_vgic_init(struct domain *d)
d->arch.vgic.shared_irqs =
xzalloc_array(struct vgic_irq_rank, DOMAIN_NR_RANKS(d));
+ if ( d->arch.vgic.shared_irqs == NULL )
+ return -ENOMEM;
+
d->arch.vgic.pending_irqs =
xzalloc_array(struct pending_irq, d->arch.vgic.nr_lines);
+ if ( d->arch.vgic.pending_irqs == NULL )
+ {
+ xfree(d->arch.vgic.shared_irqs);
+ return -ENOMEM;
+ }
+
for (i=0; i<d->arch.vgic.nr_lines; i++)
{
INIT_LIST_HEAD(&d->arch.vgic.pending_irqs[i].inflight);
@@ -583,8 +592,8 @@ static int vgic_distr_mmio_write(struct vcpu *v, mmio_info_t *info)
case GICD_ICFGR + 2 ... GICD_ICFGRN: /* SPIs */
if ( dabt.size != 2 ) goto bad_width;
rank = vgic_irq_rank(v, 2, gicd_reg - GICD_ICFGR);
- vgic_lock_rank(v, rank);
if ( rank == NULL) goto write_ignore;
+ vgic_lock_rank(v, rank);
rank->icfg[REG_RANK_INDEX(2, gicd_reg - GICD_ICFGR)] = *r;
vgic_unlock_rank(v, rank);
return 1;
diff --git a/xen/arch/x86/acpi/boot.c b/xen/arch/x86/acpi/boot.c
index 6d7984f..05de536 100644
--- a/xen/arch/x86/acpi/boot.c
+++ b/xen/arch/x86/acpi/boot.c
@@ -748,6 +748,8 @@ int __init acpi_boot_init(void)
erst_init();
+ acpi_hest_init();
+
acpi_table_parse(ACPI_SIG_BGRT, acpi_invalidate_bgrt);
return 0;
diff --git a/xen/arch/x86/acpi/cpu_idle.c b/xen/arch/x86/acpi/cpu_idle.c
index 597befa..6aaa7ab 100644
--- a/xen/arch/x86/acpi/cpu_idle.c
+++ b/xen/arch/x86/acpi/cpu_idle.c
@@ -139,6 +139,9 @@ static void do_get_hw_residencies(void *arg)
case 0x3F:
case 0x45:
case 0x46:
+ /* future */
+ case 0x3D:
+ case 0x4E:
GET_PC2_RES(hw_res->pc2);
GET_CC7_RES(hw_res->cc7);
/* fall through */
@@ -296,6 +299,9 @@ void mwait_idle_with_hints(unsigned int eax, unsigned int ecx)
unsigned int cpu = smp_processor_id();
s_time_t expires = per_cpu(timer_deadline, cpu);
+ if ( boot_cpu_has(X86_FEATURE_CLFLUSH_MONITOR) )
+ clflush((void *)&mwait_wakeup(cpu));
+
__monitor((void *)&mwait_wakeup(cpu), 0, 0);
smp_mb();
diff --git a/xen/arch/x86/cpu/amd.c b/xen/arch/x86/cpu/amd.c
index 44087fa..46c1e48 100644
--- a/xen/arch/x86/cpu/amd.c
+++ b/xen/arch/x86/cpu/amd.c
@@ -107,6 +107,10 @@ static void __devinit set_cpuidmask(const struct cpuinfo_x86 *c)
ASSERT((status == not_parsed) && (smp_processor_id() == 0));
status = no_mask;
+ /* Fam11 doesn't support masking at all. */
+ if (c->x86 == 0x11)
+ return;
+
if (~(opt_cpuid_mask_ecx & opt_cpuid_mask_edx &
opt_cpuid_mask_ext_ecx & opt_cpuid_mask_ext_edx)) {
feat_ecx = opt_cpuid_mask_ecx;
@@ -176,7 +180,6 @@ static void __devinit set_cpuidmask(const struct cpuinfo_x86 *c)
extfeat_ecx, extfeat_edx);
setmask:
- /* FIXME check if processor supports CPUID masking */
/* AMD processors prior to family 10h required a 32-bit password */
if (c->x86 >= 0x10) {
wrmsr(MSR_K8_FEATURE_MASK, feat_edx, feat_ecx);
diff --git a/xen/arch/x86/cpu/common.c b/xen/arch/x86/cpu/common.c
index 32ca458..4221826 100644
--- a/xen/arch/x86/cpu/common.c
+++ b/xen/arch/x86/cpu/common.c
@@ -234,6 +234,9 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
paddr_bits = cpuid_eax(0x80000008) & 0xff;
}
+ /* Might lift BIOS max_leaf=3 limit. */
+ early_intel_workaround(c);
+
/* Intel-defined flags: level 0x00000007 */
if ( c->cpuid_level >= 0x00000007 ) {
u32 dummy;
@@ -241,8 +244,6 @@ static void __cpuinit generic_identify(struct cpuinfo_x86 *c)
c->x86_capability[X86_FEATURE_FSGSBASE / 32] = ebx;
}
- early_intel_workaround(c);
-
#ifdef CONFIG_X86_HT
c->phys_proc_id = (cpuid_ebx(1) >> 24) & 0xff;
#endif
diff --git a/xen/arch/x86/cpu/intel.c b/xen/arch/x86/cpu/intel.c
index 27fe762..992650f 100644
--- a/xen/arch/x86/cpu/intel.c
+++ b/xen/arch/x86/cpu/intel.c
@@ -147,6 +147,9 @@ void __devinit early_intel_workaround(struct cpuinfo_x86 *c)
/*
* P4 Xeon errata 037 workaround.
* Hardware prefetcher may cause stale data to be loaded into the cache.
+ *
+ * Xeon 7400 erratum AAI65 (and further newer Xeons)
+ * MONITOR/MWAIT may have excessive false wakeups
*/
static void __devinit Intel_errata_workarounds(struct cpuinfo_x86 *c)
{
@@ -161,6 +164,10 @@ static void __devinit Intel_errata_workarounds(struct cpuinfo_x86 *c)
wrmsr (MSR_IA32_MISC_ENABLE, lo, hi);
}
}
+
+ if (c->x86 == 6 && cpu_has_clflush &&
+ (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47))
+ set_bit(X86_FEATURE_CLFLUSH_MONITOR, c->x86_capability);
}
diff --git a/xen/arch/x86/cpu/mcheck/mce.c b/xen/arch/x86/cpu/mcheck/mce.c
index b375ef7..af6f0be 100644
--- a/xen/arch/x86/cpu/mcheck/mce.c
+++ b/xen/arch/x86/cpu/mcheck/mce.c
@@ -729,8 +729,10 @@ void mcheck_init(struct cpuinfo_x86 *c, bool_t bsp)
{
enum mcheck_type inited = mcheck_none;
- if (mce_disabled == 1) {
- dprintk(XENLOG_INFO, "MCE support disabled by bootparam\n");
+ if ( mce_disabled )
+ {
+ if ( bsp )
+ printk(XENLOG_INFO "MCE support disabled by bootparam\n");
return;
}
diff --git a/xen/arch/x86/cpu/mcheck/mce_intel.c b/xen/arch/x86/cpu/mcheck/mce_intel.c
index b32fdb2..5b93870 100644
--- a/xen/arch/x86/cpu/mcheck/mce_intel.c
+++ b/xen/arch/x86/cpu/mcheck/mce_intel.c
@@ -49,11 +49,15 @@ static int __read_mostly nr_intel_ext_msrs;
#define INTEL_SRAR_INSTR_FETCH 0x150
#ifdef CONFIG_X86_MCE_THERMAL
+#define MCE_RING 0x1
+static DEFINE_PER_CPU(int, last_state);
+
static void intel_thermal_interrupt(struct cpu_user_regs *regs)
{
uint64_t msr_content;
unsigned int cpu = smp_processor_id();
static DEFINE_PER_CPU(s_time_t, next);
+ int *this_last_state;
ack_APIC_irq();
@@ -62,13 +66,17 @@ static void intel_thermal_interrupt(struct cpu_user_regs *regs)
per_cpu(next, cpu) = NOW() + MILLISECS(5000);
rdmsrl(MSR_IA32_THERM_STATUS, msr_content);
- if (msr_content & 0x1) {
- printk(KERN_EMERG "CPU%d: Temperature above threshold\n", cpu);
- printk(KERN_EMERG "CPU%d: Running in modulated clock mode\n",
- cpu);
+ this_last_state = &per_cpu(last_state, cpu);
+ if ( *this_last_state == (msr_content & MCE_RING) )
+ return;
+ *this_last_state = msr_content & MCE_RING;
+ if ( msr_content & MCE_RING )
+ {
+ printk(KERN_EMERG "CPU%u: Temperature above threshold\n", cpu);
+ printk(KERN_EMERG "CPU%u: Running in modulated clock mode\n", cpu);
add_taint(TAINT_MACHINE_CHECK);
} else {
- printk(KERN_INFO "CPU%d: Temperature/speed normal\n", cpu);
+ printk(KERN_INFO "CPU%u: Temperature/speed normal\n", cpu);
}
}
@@ -802,6 +810,7 @@ static int cpu_mcabank_alloc(unsigned int cpu)
per_cpu(no_cmci_banks, cpu) = cmci;
per_cpu(mce_banks_owned, cpu) = owned;
+ per_cpu(last_state, cpu) = -1;
return 0;
out:
diff --git a/xen/arch/x86/cpu/mcheck/mctelem.c b/xen/arch/x86/cpu/mcheck/mctelem.c
index 895ce1a..ed8e8d2 100644
--- a/xen/arch/x86/cpu/mcheck/mctelem.c
+++ b/xen/arch/x86/cpu/mcheck/mctelem.c
@@ -37,24 +37,19 @@ struct mctelem_ent {
void *mcte_data; /* corresponding data payload */
};
-#define MCTE_F_HOME_URGENT 0x0001U /* free to urgent freelist */
-#define MCTE_F_HOME_NONURGENT 0x0002U /* free to nonurgent freelist */
-#define MCTE_F_CLASS_URGENT 0x0004U /* in use - urgent errors */
-#define MCTE_F_CLASS_NONURGENT 0x0008U /* in use - nonurgent errors */
+#define MCTE_F_CLASS_URGENT 0x0001U /* in use - urgent errors */
+#define MCTE_F_CLASS_NONURGENT 0x0002U /* in use - nonurgent errors */
#define MCTE_F_STATE_FREE 0x0010U /* on a freelist */
#define MCTE_F_STATE_UNCOMMITTED 0x0020U /* reserved; on no list */
#define MCTE_F_STATE_COMMITTED 0x0040U /* on a committed list */
#define MCTE_F_STATE_PROCESSING 0x0080U /* on a processing list */
-#define MCTE_F_MASK_HOME (MCTE_F_HOME_URGENT | MCTE_F_HOME_NONURGENT)
#define MCTE_F_MASK_CLASS (MCTE_F_CLASS_URGENT | MCTE_F_CLASS_NONURGENT)
#define MCTE_F_MASK_STATE (MCTE_F_STATE_FREE | \
MCTE_F_STATE_UNCOMMITTED | \
MCTE_F_STATE_COMMITTED | \
MCTE_F_STATE_PROCESSING)
-#define MCTE_HOME(tep) ((tep)->mcte_flags & MCTE_F_MASK_HOME)
-
#define MCTE_CLASS(tep) ((tep)->mcte_flags & MCTE_F_MASK_CLASS)
#define MCTE_SET_CLASS(tep, new) do { \
(tep)->mcte_flags &= ~MCTE_F_MASK_CLASS; \
@@ -69,6 +64,8 @@ struct mctelem_ent {
#define MC_URGENT_NENT 10
#define MC_NONURGENT_NENT 20
+#define MC_NENT (MC_URGENT_NENT + MC_NONURGENT_NENT)
+
#define MC_NCLASSES (MC_NONURGENT + 1)
#define COOKIE2MCTE(c) ((struct mctelem_ent *)(c))
@@ -77,11 +74,9 @@ struct mctelem_ent {
static struct mc_telem_ctl {
/* Linked lists that thread the array members together.
*
- * The free lists are singly-linked via mcte_next, and we allocate
- * from them by atomically unlinking an element from the head.
- * Consumed entries are returned to the head of the free list.
- * When an entry is reserved off the free list it is not linked
- * on any list until it is committed or dismissed.
+ * The free lists is a bit array where bit 1 means free.
+ * This as element number is quite small and is easy to
+ * atomically allocate that way.
*
* The committed list grows at the head and we do not maintain a
* tail pointer; insertions are performed atomically. The head
@@ -101,7 +96,7 @@ static struct mc_telem_ctl {
* we can lock it for updates. The head of the processing list
* always has the oldest telemetry, and we append (as above)
* at the tail of the processing list. */
- struct mctelem_ent *mctc_free[MC_NCLASSES];
+ DECLARE_BITMAP(mctc_free, MC_NENT);
struct mctelem_ent *mctc_committed[MC_NCLASSES];
struct mctelem_ent *mctc_processing_head[MC_NCLASSES];
struct mctelem_ent *mctc_processing_tail[MC_NCLASSES];
@@ -207,14 +202,14 @@ int mctelem_has_deferred(unsigned int cpu)
*/
static void mctelem_free(struct mctelem_ent *tep)
{
- mctelem_class_t target = MCTE_HOME(tep) == MCTE_F_HOME_URGENT ?
- MC_URGENT : MC_NONURGENT;
-
BUG_ON(tep->mcte_refcnt != 0);
BUG_ON(MCTE_STATE(tep) != MCTE_F_STATE_FREE);
tep->mcte_prev = NULL;
- mctelem_xchg_head(&mctctl.mctc_free[target], &tep->mcte_next, tep);
+ tep->mcte_next = NULL;
+
+ /* set free in array */
+ set_bit(tep - mctctl.mctc_elems, mctctl.mctc_free);
}
/* Increment the reference count of an entry that is not linked on to
@@ -274,34 +269,25 @@ void mctelem_init(int reqdatasz)
}
if ((mctctl.mctc_elems = xmalloc_array(struct mctelem_ent,
- MC_URGENT_NENT + MC_NONURGENT_NENT)) == NULL ||
- (datarr = xmalloc_bytes((MC_URGENT_NENT + MC_NONURGENT_NENT) *
- datasz)) == NULL) {
+ MC_NENT)) == NULL ||
+ (datarr = xmalloc_bytes(MC_NENT * datasz)) == NULL) {
if (mctctl.mctc_elems)
xfree(mctctl.mctc_elems);
printk("Allocations for MCA telemetry failed\n");
return;
}
- for (i = 0; i < MC_URGENT_NENT + MC_NONURGENT_NENT; i++) {
- struct mctelem_ent *tep, **tepp;
+ for (i = 0; i < MC_NENT; i++) {
+ struct mctelem_ent *tep;
tep = mctctl.mctc_elems + i;
tep->mcte_flags = MCTE_F_STATE_FREE;
tep->mcte_refcnt = 0;
tep->mcte_data = datarr + i * datasz;
- if (i < MC_URGENT_NENT) {
- tepp = &mctctl.mctc_free[MC_URGENT];
- tep->mcte_flags |= MCTE_F_HOME_URGENT;
- } else {
- tepp = &mctctl.mctc_free[MC_NONURGENT];
- tep->mcte_flags |= MCTE_F_HOME_NONURGENT;
- }
-
- tep->mcte_next = *tepp;
+ __set_bit(i, mctctl.mctc_free);
+ tep->mcte_next = NULL;
tep->mcte_prev = NULL;
- *tepp = tep;
}
}
@@ -310,32 +296,25 @@ static int mctelem_drop_count;
/* Reserve a telemetry entry, or return NULL if none available.
* If we return an entry then the caller must subsequently call exactly one of
- * mctelem_unreserve or mctelem_commit for that entry.
+ * mctelem_dismiss or mctelem_commit for that entry.
*/
mctelem_cookie_t mctelem_reserve(mctelem_class_t which)
{
- struct mctelem_ent **freelp;
- struct mctelem_ent *oldhead, *newhead;
- mctelem_class_t target = (which == MC_URGENT) ?
- MC_URGENT : MC_NONURGENT;
+ unsigned bit;
+ unsigned start_bit = (which == MC_URGENT) ? 0 : MC_URGENT_NENT;
- freelp = &mctctl.mctc_free[target];
for (;;) {
- if ((oldhead = *freelp) == NULL) {
- if (which == MC_URGENT && target == MC_URGENT) {
- /* raid the non-urgent freelist */
- target = MC_NONURGENT;
- freelp = &mctctl.mctc_free[target];
- continue;
- } else {
- mctelem_drop_count++;
- return (NULL);
- }
+ bit = find_next_bit(mctctl.mctc_free, MC_NENT, start_bit);
+
+ if (bit >= MC_NENT) {
+ mctelem_drop_count++;
+ return (NULL);
}
- newhead = oldhead->mcte_next;
- if (cmpxchgptr(freelp, oldhead, newhead) == oldhead) {
- struct mctelem_ent *tep = oldhead;
+ /* try to allocate, atomically clear free bit */
+ if (test_and_clear_bit(bit, mctctl.mctc_free)) {
+ /* return element we got */
+ struct mctelem_ent *tep = mctctl.mctc_elems + bit;
mctelem_hold(tep);
MCTE_TRANSITION_STATE(tep, FREE, UNCOMMITTED);
diff --git a/xen/arch/x86/cpu/mcheck/vmce.c b/xen/arch/x86/cpu/mcheck/vmce.c
index f6c35db..dcfe97e 100644
--- a/xen/arch/x86/cpu/mcheck/vmce.c
+++ b/xen/arch/x86/cpu/mcheck/vmce.c
@@ -357,6 +357,10 @@ int inject_vmce(struct domain *d, int vcpu)
if ( vcpu != VMCE_INJECT_BROADCAST && vcpu != v->vcpu_id )
continue;
+ /* Don't inject to uninitialized VCPU. */
+ if ( !v->is_initialised )
+ continue;
+
if ( (has_hvm_container_domain(d) ||
guest_has_trap_callback(d, v->vcpu_id, TRAP_machine_check)) &&
!test_and_set_bool(v->mce_pending) )
diff --git a/xen/arch/x86/cpu/mwait-idle.c b/xen/arch/x86/cpu/mwait-idle.c
index 85179f2..65ea7b3 100644
--- a/xen/arch/x86/cpu/mwait-idle.c
+++ b/xen/arch/x86/cpu/mwait-idle.c
@@ -360,7 +360,7 @@ static void mwait_idle(void)
lapic_timer_off();
before = cpuidle_get_tick();
- TRACE_4D(TRC_PM_IDLE_ENTRY, cx->idx, before, exp, pred);
+ TRACE_4D(TRC_PM_IDLE_ENTRY, cx->type, before, exp, pred);
if (cpu_is_haltable(cpu))
mwait_idle_with_hints(eax, MWAIT_ECX_INTERRUPT_BREAK);
@@ -369,7 +369,7 @@ static void mwait_idle(void)
cstate_restore_tsc();
trace_exit_reason(irq_traced);
- TRACE_6D(TRC_PM_IDLE_EXIT, cx->idx, after,
+ TRACE_6D(TRC_PM_IDLE_EXIT, cx->type, after,
irq_traced[0], irq_traced[1], irq_traced[2], irq_traced[3]);
update_idle_stats(power, cx, before, after);
diff --git a/xen/arch/x86/domain.c b/xen/arch/x86/domain.c
index 6618ae6..195b07f 100644
--- a/xen/arch/x86/domain.c
+++ b/xen/arch/x86/domain.c
@@ -180,6 +180,28 @@ void dump_pageframe_info(struct domain *d)
spin_unlock(&d->page_alloc_lock);
}
+/*
+ * The hole may be at or above the 44-bit boundary, so we need to determine
+ * the total bit count until reaching 32 significant (not squashed out) bits
+ * in PFN representations.
+ * Note that the way "bits" gets initialized/updated/bounds-checked guarantees
+ * that the function will never return zero, and hence will never be called
+ * more than once (which is important due to it being deliberately placed in
+ * .init.text).
+ */
+static unsigned int __init noinline _domain_struct_bits(void)
+{
+ unsigned int bits = 32 + PAGE_SHIFT;
+ unsigned int sig = hweight32(~pfn_hole_mask);
+ unsigned int mask = pfn_hole_mask >> 32;
+
+ for ( ; bits < BITS_PER_LONG && sig < 32; ++bits, mask >>= 1 )
+ if ( !(mask & 1) )
+ ++sig;
+
+ return bits;
+}
+
struct domain *alloc_domain_struct(void)
{
struct domain *d;
@@ -187,7 +209,10 @@ struct domain *alloc_domain_struct(void)
* We pack the PDX of the domain structure into a 32-bit field within
* the page_info structure. Hence the MEMF_bits() restriction.
*/
- unsigned int bits = 32 + PAGE_SHIFT + pfn_pdx_hole_shift;
+ static unsigned int __read_mostly bits;
+
+ if ( unlikely(!bits) )
+ bits = _domain_struct_bits();
BUILD_BUG_ON(sizeof(*d) > PAGE_SIZE);
d = alloc_xenheap_pages(0, MEMF_bits(bits));
@@ -422,10 +447,6 @@ int vcpu_initialise(struct vcpu *v)
/* PV guests by default have a 100Hz ticker. */
v->periodic_period = MILLISECS(10);
-
- /* PV guests get an emulated PIT too for video BIOSes to use. */
- if ( v->vcpu_id == 0 )
- pit_init(v, cpu_khz);
}
v->arch.schedule_tail = continue_nonidle_domain;
@@ -528,7 +549,7 @@ int arch_domain_create(struct domain *d, unsigned int domcr_flags)
if ( !is_idle_domain(d) )
{
- d->arch.cpuids = xzalloc_array(cpuid_input_t, MAX_CPUID_INPUT);
+ d->arch.cpuids = xmalloc_array(cpuid_input_t, MAX_CPUID_INPUT);
rc = -ENOMEM;
if ( d->arch.cpuids == NULL )
goto fail;
@@ -579,6 +600,9 @@ int arch_domain_create(struct domain *d, unsigned int domcr_flags)
tsc_set_info(d, TSC_MODE_DEFAULT, 0UL, 0, 0);
spin_lock_init(&d->arch.vtsc_lock);
+ /* PV/PVH guests get an emulated PIT too for video BIOSes to use. */
+ pit_init(d, cpu_khz);
+
return 0;
fail:
@@ -1980,6 +2004,8 @@ int domain_relinquish_resources(struct domain *d)
BUG();
}
+ pit_deinit(d);
+
if ( has_hvm_container_domain(d) )
hvm_domain_relinquish_resources(d);
diff --git a/xen/arch/x86/domctl.c b/xen/arch/x86/domctl.c
index 26635ff..a967b65 100644
--- a/xen/arch/x86/domctl.c
+++ b/xen/arch/x86/domctl.c
@@ -920,7 +920,7 @@ long arch_do_domctl(
case XEN_DOMCTL_set_cpuid:
{
xen_domctl_cpuid_t *ctl = &domctl->u.cpuid;
- cpuid_input_t *cpuid = NULL;
+ cpuid_input_t *cpuid, *unused = NULL;
int i;
for ( i = 0; i < MAX_CPUID_INPUT; i++ )
@@ -928,7 +928,11 @@ long arch_do_domctl(
cpuid = &d->arch.cpuids[i];
if ( cpuid->input[0] == XEN_CPUID_INPUT_UNUSED )
- break;
+ {
+ if ( !unused )
+ unused = cpuid;
+ continue;
+ }
if ( (cpuid->input[0] == ctl->input[0]) &&
((cpuid->input[1] == XEN_CPUID_INPUT_UNUSED) ||
@@ -936,15 +940,12 @@ long arch_do_domctl(
break;
}
- if ( i == MAX_CPUID_INPUT )
- {
- ret = -ENOENT;
- }
+ if ( i < MAX_CPUID_INPUT )
+ *cpuid = *ctl;
+ else if ( unused )
+ *unused = *ctl;
else
- {
- memcpy(cpuid, ctl, sizeof(cpuid_input_t));
- ret = 0;
- }
+ ret = -ENOENT;
}
break;
@@ -1018,7 +1019,7 @@ long arch_do_domctl(
struct vcpu *v;
ret = -EBUSY;
- if ( !d->is_paused_by_controller )
+ if ( !d->controller_pause_count )
break;
ret = -EINVAL;
if ( domctl->u.gdbsx_pauseunp_vcpu.vcpu >= MAX_VIRT_CPUS ||
@@ -1034,7 +1035,7 @@ long arch_do_domctl(
struct vcpu *v;
ret = -EBUSY;
- if ( !d->is_paused_by_controller )
+ if ( !d->controller_pause_count )
break;
ret = -EINVAL;
if ( domctl->u.gdbsx_pauseunp_vcpu.vcpu >= MAX_VIRT_CPUS ||
@@ -1052,7 +1053,7 @@ long arch_do_domctl(
struct vcpu *v;
domctl->u.gdbsx_domstatus.vcpu_id = -1;
- domctl->u.gdbsx_domstatus.paused = d->is_paused_by_controller;
+ domctl->u.gdbsx_domstatus.paused = d->controller_pause_count > 0;
if ( domctl->u.gdbsx_domstatus.paused )
{
for_each_vcpu ( d, v )
@@ -1088,45 +1089,48 @@ long arch_do_domctl(
((v = d->vcpu[evc->vcpu]) == NULL) )
goto vcpuextstate_out;
+ ret = -EINVAL;
+ if ( v == current ) /* no vcpu_pause() */
+ goto vcpuextstate_out;
+
if ( domctl->cmd == XEN_DOMCTL_getvcpuextstate )
{
- unsigned int size = PV_XSAVE_SIZE(v->arch.xcr0_accum);
+ unsigned int size;
- if ( !evc->size && !evc->xfeature_mask )
+ ret = 0;
+ vcpu_pause(v);
+
+ size = PV_XSAVE_SIZE(v->arch.xcr0_accum);
+ if ( (!evc->size && !evc->xfeature_mask) ||
+ guest_handle_is_null(evc->buffer) )
{
evc->xfeature_mask = xfeature_mask;
evc->size = size;
- ret = 0;
+ vcpu_unpause(v);
goto vcpuextstate_out;
}
+
if ( evc->size != size || evc->xfeature_mask != xfeature_mask )
- {
ret = -EINVAL;
- goto vcpuextstate_out;
- }
- if ( copy_to_guest_offset(domctl->u.vcpuextstate.buffer,
- offset, (void *)&v->arch.xcr0,
- sizeof(v->arch.xcr0)) )
- {
+
+ if ( !ret && copy_to_guest_offset(evc->buffer, offset,
+ (void *)&v->arch.xcr0,
+ sizeof(v->arch.xcr0)) )
ret = -EFAULT;
- goto vcpuextstate_out;
- }
+
offset += sizeof(v->arch.xcr0);
- if ( copy_to_guest_offset(domctl->u.vcpuextstate.buffer,
- offset, (void *)&v->arch.xcr0_accum,
- sizeof(v->arch.xcr0_accum)) )
- {
+ if ( !ret && copy_to_guest_offset(evc->buffer, offset,
+ (void *)&v->arch.xcr0_accum,
+ sizeof(v->arch.xcr0_accum)) )
ret = -EFAULT;
- goto vcpuextstate_out;
- }
+
offset += sizeof(v->arch.xcr0_accum);
- if ( copy_to_guest_offset(domctl->u.vcpuextstate.buffer,
- offset, (void *)v->arch.xsave_area,
- size - 2 * sizeof(uint64_t)) )
- {
+ if ( !ret && copy_to_guest_offset(evc->buffer, offset,
+ (void *)v->arch.xsave_area,
+ size - 2 * sizeof(uint64_t)) )
ret = -EFAULT;
- goto vcpuextstate_out;
- }
+
+ vcpu_unpause(v);
}
else
{
@@ -1175,12 +1179,14 @@ long arch_do_domctl(
if ( evc->size <= PV_XSAVE_SIZE(_xcr0_accum) )
{
+ vcpu_pause(v);
v->arch.xcr0 = _xcr0;
v->arch.xcr0_accum = _xcr0_accum;
if ( _xcr0_accum & XSTATE_NONLAZY )
v->arch.nonlazy_xstate_used = 1;
memcpy(v->arch.xsave_area, _xsave_area,
evc->size - 2 * sizeof(uint64_t));
+ vcpu_unpause(v);
}
else
ret = -EINVAL;
@@ -1188,8 +1194,6 @@ long arch_do_domctl(
xfree(receive_buf);
}
- ret = 0;
-
vcpuextstate_out:
if ( domctl->cmd == XEN_DOMCTL_getvcpuextstate )
copyback = 1;
diff --git a/xen/arch/x86/efi/runtime.c b/xen/arch/x86/efi/runtime.c
index d7c884b..166852d 100644
--- a/xen/arch/x86/efi/runtime.c
+++ b/xen/arch/x86/efi/runtime.c
@@ -10,6 +10,8 @@ DEFINE_XEN_GUEST_HANDLE(CHAR16);
#ifndef COMPAT
+# include <asm/i387.h>
+# include <asm/xstate.h>
# include <public/platform.h>
const bool_t efi_enabled = 1;
@@ -45,8 +47,14 @@ const struct efi_pci_rom *__read_mostly efi_pci_roms;
unsigned long efi_rs_enter(void)
{
+ static const u16 fcw = FCW_DEFAULT;
+ static const u32 mxcsr = MXCSR_DEFAULT;
unsigned long cr3 = read_cr3();
+ save_fpu_enable();
+ asm volatile ( "fldcw %0" :: "m" (fcw) );
+ asm volatile ( "ldmxcsr %0" :: "m" (mxcsr) );
+
spin_lock(&efi_rs_lock);
/* prevent fixup_page_fault() from doing anything */
@@ -82,6 +90,7 @@ void efi_rs_leave(unsigned long cr3)
}
irq_exit();
spin_unlock(&efi_rs_lock);
+ stts();
}
unsigned long efi_get_time(void)
diff --git a/xen/arch/x86/flushtlb.c b/xen/arch/x86/flushtlb.c
index e0388e7..1b75652 100644
--- a/xen/arch/x86/flushtlb.c
+++ b/xen/arch/x86/flushtlb.c
@@ -152,7 +152,8 @@ void flush_area_local(const void *va, unsigned int flags)
if ( order < (BITS_PER_LONG - PAGE_SHIFT) )
sz = 1UL << (order + PAGE_SHIFT);
- if ( c->x86_clflush_size && c->x86_cache_size && sz &&
+ if ( !(flags & (FLUSH_TLB|FLUSH_TLB_GLOBAL)) &&
+ c->x86_clflush_size && c->x86_cache_size && sz &&
((sz >> 10) < c->x86_cache_size) )
{
va = (const void *)((unsigned long)va & ~(sz - 1));
diff --git a/xen/arch/x86/hvm/hvm.c b/xen/arch/x86/hvm/hvm.c
index 69f7e74..be1a2d3 100644
--- a/xen/arch/x86/hvm/hvm.c
+++ b/xen/arch/x86/hvm/hvm.c
@@ -478,7 +478,7 @@ static int hvm_set_ioreq_page(
if ( (iorp->va != NULL) || d->is_dying )
{
- destroy_ring_for_helper(&iorp->va, iorp->page);
+ destroy_ring_for_helper(&va, page);
spin_unlock(&iorp->lock);
return -EINVAL;
}
@@ -643,7 +643,6 @@ void hvm_domain_relinquish_resources(struct domain *d)
rtc_deinit(d);
if ( d->vcpu != NULL && d->vcpu[0] != NULL )
{
- pit_deinit(d);
pmtimer_deinit(d);
hpet_deinit(d);
}
@@ -858,7 +857,7 @@ static int hvm_load_cpu_ctxt(struct domain *d, hvm_domain_context_t *h)
return -EINVAL;
}
- if ( ctxt.cr4 & HVM_CR4_GUEST_RESERVED_BITS(v) )
+ if ( ctxt.cr4 & HVM_CR4_GUEST_RESERVED_BITS(v, 1) )
{
printk(XENLOG_G_ERR "HVM%d restore: bad CR4 %#" PRIx64 "\n",
d->domain_id, ctxt.cr4);
@@ -1217,7 +1216,6 @@ int hvm_vcpu_initialise(struct vcpu *v)
if ( v->vcpu_id == 0 )
{
/* NB. All these really belong in hvm_domain_initialise(). */
- pit_init(v, cpu_khz);
pmtimer_init(v);
hpet_init(v);
@@ -1529,6 +1527,11 @@ int hvm_hap_nested_page_fault(paddr_t gpa,
(access_w && (p2mt == p2m_ram_ro)) )
{
put_gfn(p2m->domain, gfn);
+
+ rc = 0;
+ if ( unlikely(is_pvh_vcpu(v)) )
+ goto out;
+
if ( !handle_mmio() )
hvm_inject_hw_exception(TRAP_gp_fault, 0);
rc = 1;
@@ -1923,6 +1926,7 @@ int hvm_set_cr0(unsigned long value)
hvm_funcs.handle_cd(v, value);
hvm_update_cr(v, 0, value);
+ hvm_memory_event_cr0(value, old_value);
if ( (value ^ old_value) & X86_CR0_PG ) {
if ( !nestedhvm_vmswitch_in_progress(v) && nestedhvm_vcpu_in_guestmode(v) )
@@ -1977,7 +1981,7 @@ int hvm_set_cr4(unsigned long value)
struct vcpu *v = current;
unsigned long old_cr;
- if ( value & HVM_CR4_GUEST_RESERVED_BITS(v) )
+ if ( value & HVM_CR4_GUEST_RESERVED_BITS(v, 0) )
{
HVM_DBG_LOG(DBG_LEVEL_1,
"Guest attempts to set reserved bit in CR4: %lx",
@@ -2885,6 +2889,8 @@ void hvm_cpuid(unsigned int input, unsigned int *eax, unsigned int *ebx,
switch ( input )
{
+ unsigned int sub_leaf, _eax, _ebx, _ecx, _edx;
+
case 0x1:
/* Fix up VLAPIC details. */
*ebx &= 0x00FFFFFFu;
@@ -2918,8 +2924,6 @@ void hvm_cpuid(unsigned int input, unsigned int *eax, unsigned int *ebx,
*edx = v->vcpu_id * 2;
break;
case 0xd:
- {
- unsigned int sub_leaf, _eax, _ebx, _ecx, _edx;
/* EBX value of main leaf 0 depends on enabled xsave features */
if ( count == 0 && v->arch.xcr0 )
{
@@ -2936,7 +2940,7 @@ void hvm_cpuid(unsigned int input, unsigned int *eax, unsigned int *ebx,
}
}
break;
- }
+
case 0x80000001:
/* We expose RDTSCP feature to guest only when
tsc_mode == TSC_MODE_DEFAULT and host_tsc_is_safe() returns 1 */
@@ -2950,6 +2954,23 @@ void hvm_cpuid(unsigned int input, unsigned int *eax, unsigned int *ebx,
if ( !(hvm_pae_enabled(v) || hvm_long_mode_enabled(v)) )
*edx &= ~cpufeat_mask(X86_FEATURE_PSE36);
break;
+
+ case 0x80000008:
+ count = cpuid_eax(0x80000008);
+ count = (count >> 16) & 0xff ?: count & 0xff;
+ if ( (*eax & 0xff) > count )
+ *eax = (*eax & ~0xff) | count;
+
+ hvm_cpuid(1, NULL, NULL, NULL, &_edx);
+ count = _edx & (cpufeat_mask(X86_FEATURE_PAE) |
+ cpufeat_mask(X86_FEATURE_PSE36)) ? 36 : 32;
+ if ( (*eax & 0xff) < count )
+ *eax = (*eax & ~0xff) | count;
+
+ hvm_cpuid(0x80000001, NULL, NULL, NULL, &_edx);
+ *eax = (*eax & ~0xffff00) | (_edx & cpufeat_mask(X86_FEATURE_LM)
+ ? 0x3000 : 0x2000);
+ break;
}
}
@@ -3294,6 +3315,12 @@ static long hvm_physdev_op(int cmd, XEN_GUEST_HANDLE_PARAM(void) arg)
case PHYSDEVOP_irq_status_query:
case PHYSDEVOP_get_free_pirq:
return do_physdev_op(cmd, arg);
+
+ /* pvh fixme: coming soon */
+ case PHYSDEVOP_pirq_eoi_gmfn_v1:
+ case PHYSDEVOP_pirq_eoi_gmfn_v2:
+ return -ENOSYS;
+
}
}
@@ -4393,12 +4420,10 @@ long do_hvm_op(unsigned long op, XEN_GUEST_HANDLE_PARAM(void) arg)
rc = -EINVAL;
goto param_fail4;
}
- if ( p2m_is_grant(t) )
+ if ( !p2m_is_ram(t) &&
+ (!p2m_is_hole(t) || a.hvmmem_type != HVMMEM_mmio_dm) )
{
put_gfn(d, pfn);
- gdprintk(XENLOG_WARNING,
- "type for pfn %#lx changed to grant while "
- "we were working?\n", pfn);
goto param_fail4;
}
else
@@ -4465,6 +4490,15 @@ long do_hvm_op(unsigned long op, XEN_GUEST_HANDLE_PARAM(void) arg)
goto param_fail5;
rc = p2m_set_mem_access(d, a.first_pfn, a.nr, a.hvmmem_access);
+ if ( rc > 0 )
+ {
+ a.first_pfn += a.nr - rc;
+ a.nr = rc;
+ if ( __copy_to_guest(arg, &a, 1) )
+ rc = -EFAULT;
+ else
+ rc = -EAGAIN;
+ }
param_fail5:
rcu_unlock_domain(d);
@@ -4671,7 +4705,7 @@ static int hvm_memory_event_traps(long p, uint32_t reason,
if ( (p & HVMPME_MODE_MASK) == HVMPME_mode_sync )
{
req.flags |= MEM_EVENT_FLAG_VCPU_PAUSED;
- vcpu_pause_nosync(v);
+ mem_event_vcpu_pause(v);
}
req.gfn = value;
diff --git a/xen/arch/x86/hvm/i8254.c b/xen/arch/x86/hvm/i8254.c
index c0d6bc2..f7493b8 100644
--- a/xen/arch/x86/hvm/i8254.c
+++ b/xen/arch/x86/hvm/i8254.c
@@ -447,9 +447,8 @@ void pit_reset(struct domain *d)
spin_unlock(&pit->lock);
}
-void pit_init(struct vcpu *v, unsigned long cpu_khz)
+void pit_init(struct domain *d, unsigned long cpu_khz)
{
- struct domain *d = v->domain;
PITState *pit = domain_vpit(d);
spin_lock_init(&pit->lock);
diff --git a/xen/arch/x86/hvm/io.c b/xen/arch/x86/hvm/io.c
index bf6309d..247fb7e 100644
--- a/xen/arch/x86/hvm/io.c
+++ b/xen/arch/x86/hvm/io.c
@@ -178,6 +178,8 @@ int handle_mmio(void)
struct hvm_vcpu_io *vio = &curr->arch.hvm_vcpu.hvm_io;
int rc;
+ ASSERT(!is_pvh_vcpu(curr));
+
hvm_emulate_prepare(&ctxt, guest_cpu_user_regs());
rc = hvm_emulate_one(&ctxt);
diff --git a/xen/arch/x86/hvm/irq.c b/xen/arch/x86/hvm/irq.c
index 677fbcd..5048c29 100644
--- a/xen/arch/x86/hvm/irq.c
+++ b/xen/arch/x86/hvm/irq.c
@@ -289,20 +289,18 @@ void hvm_inject_msi(struct domain *d, uint64_t addr, uint32_t data)
struct pirq *info = pirq_info(d, pirq);
/* if it is the first time, allocate the pirq */
- if (info->arch.hvm.emuirq == IRQ_UNBOUND)
+ if ( !info || info->arch.hvm.emuirq == IRQ_UNBOUND )
{
spin_lock(&d->event_lock);
map_domain_emuirq_pirq(d, pirq, IRQ_MSI_EMU);
spin_unlock(&d->event_lock);
+ info = pirq_info(d, pirq);
+ if ( !info )
+ return;
} else if (info->arch.hvm.emuirq != IRQ_MSI_EMU)
- {
- printk("%s: pirq %d does not correspond to an emulated MSI\n", __func__, pirq);
return;
- }
send_guest_pirq(d, info);
return;
- } else {
- printk("%s: error getting pirq from MSI: pirq = %d\n", __func__, pirq);
}
}
diff --git a/xen/arch/x86/hvm/mtrr.c b/xen/arch/x86/hvm/mtrr.c
index 9937f5a..e13647c 100644
--- a/xen/arch/x86/hvm/mtrr.c
+++ b/xen/arch/x86/hvm/mtrr.c
@@ -145,7 +145,7 @@ bool_t is_var_mtrr_overlapped(struct mtrr_state *m)
static int hvm_mtrr_pat_init(void)
{
- unsigned int i, j, phys_addr;
+ unsigned int i, j;
memset(&mtrr_epat_tbl, INVALID_MEM_TYPE, sizeof(mtrr_epat_tbl));
for ( i = 0; i < MTRR_NUM_TYPES; i++ )
@@ -172,11 +172,7 @@ static int hvm_mtrr_pat_init(void)
}
}
- phys_addr = 36;
- if ( cpuid_eax(0x80000000) >= 0x80000008 )
- phys_addr = (uint8_t)cpuid_eax(0x80000008);
-
- size_or_mask = ~((1 << (phys_addr - PAGE_SHIFT)) - 1);
+ size_or_mask = ~((1 << (paddr_bits - PAGE_SHIFT)) - 1);
return 0;
}
@@ -455,7 +451,7 @@ bool_t mtrr_fix_range_msr_set(struct mtrr_state *m, uint32_t row,
bool_t mtrr_var_range_msr_set(
struct domain *d, struct mtrr_state *m, uint32_t msr, uint64_t msr_content)
{
- uint32_t index, type, phys_addr, eax, ebx, ecx, edx;
+ uint32_t index, type, phys_addr, eax;
uint64_t msr_mask;
uint64_t *var_range_base = (uint64_t*)m->var_ranges;
@@ -468,16 +464,21 @@ bool_t mtrr_var_range_msr_set(
type == 4 || type == 5 || type == 6)) )
return 0;
- phys_addr = 36;
- domain_cpuid(d, 0x80000000, 0, &eax, &ebx, &ecx, &edx);
- if ( eax >= 0x80000008 )
+ if ( d == current->domain )
{
- domain_cpuid(d, 0x80000008, 0, &eax, &ebx, &ecx, &edx);
- phys_addr = (uint8_t)eax;
+ phys_addr = 36;
+ hvm_cpuid(0x80000000, &eax, NULL, NULL, NULL);
+ if ( eax >= 0x80000008 )
+ {
+ hvm_cpuid(0x80000008, &eax, NULL, NULL, NULL);
+ phys_addr = (uint8_t)eax;
+ }
}
+ else
+ phys_addr = paddr_bits;
msr_mask = ~((((uint64_t)1) << phys_addr) - 1);
msr_mask |= (index & 1) ? 0x7ffUL : 0xf00UL;
- if ( unlikely(msr_content && (msr_content & msr_mask)) )
+ if ( unlikely(msr_content & msr_mask) )
{
HVM_DBG_LOG(DBG_LEVEL_MSR, "invalid msr content:%"PRIx64"\n",
msr_content);
@@ -689,13 +690,8 @@ uint8_t epte_get_entry_emt(struct domain *d, unsigned long gfn, mfn_t mfn,
*ipat = 0;
- if ( (current->domain != d) &&
- ((d->vcpu == NULL) || ((v = d->vcpu[0]) == NULL)) )
- return MTRR_TYPE_WRBACK;
-
- if ( !is_pvh_vcpu(v) &&
- !v->domain->arch.hvm_domain.params[HVM_PARAM_IDENT_PT] )
- return MTRR_TYPE_WRBACK;
+ if ( v->domain != d )
+ v = d->vcpu ? d->vcpu[0] : NULL;
if ( !mfn_valid(mfn_x(mfn)) )
return MTRR_TYPE_UNCACHABLE;
@@ -703,14 +699,24 @@ uint8_t epte_get_entry_emt(struct domain *d, unsigned long gfn, mfn_t mfn,
if ( hvm_get_mem_pinned_cacheattr(d, gfn, &type) )
return type;
- if ( !iommu_enabled )
+ if ( !iommu_enabled ||
+ (rangeset_is_empty(d->iomem_caps) &&
+ rangeset_is_empty(d->arch.ioport_caps) &&
+ !has_arch_pdevs(d)) )
{
+ ASSERT(!direct_mmio ||
+ mfn_x(mfn) == d->arch.hvm_domain.vmx.apic_access_mfn);
*ipat = 1;
return MTRR_TYPE_WRBACK;
}
if ( direct_mmio )
- return MTRR_TYPE_UNCACHABLE;
+ {
+ if ( mfn_x(mfn) != d->arch.hvm_domain.vmx.apic_access_mfn )
+ return MTRR_TYPE_UNCACHABLE;
+ *ipat = 1;
+ return MTRR_TYPE_WRBACK;
+ }
if ( iommu_snoop )
{
@@ -718,10 +724,41 @@ uint8_t epte_get_entry_emt(struct domain *d, unsigned long gfn, mfn_t mfn,
return MTRR_TYPE_WRBACK;
}
- gmtrr_mtype = is_hvm_vcpu(v) ?
+ gmtrr_mtype = is_hvm_domain(d) && v &&
+ d->arch.hvm_domain.params[HVM_PARAM_IDENT_PT] ?
get_mtrr_type(&v->arch.hvm_vcpu.mtrr, (gfn << PAGE_SHIFT)) :
MTRR_TYPE_WRBACK;
hmtrr_mtype = get_mtrr_type(&mtrr_state, (mfn_x(mfn) << PAGE_SHIFT));
- return ((gmtrr_mtype <= hmtrr_mtype) ? gmtrr_mtype : hmtrr_mtype);
+
+ /* If both types match we're fine. */
+ if ( likely(gmtrr_mtype == hmtrr_mtype) )
+ return hmtrr_mtype;
+
+ /* If either type is UC, we have to go with that one. */
+ if ( gmtrr_mtype == MTRR_TYPE_UNCACHABLE ||
+ hmtrr_mtype == MTRR_TYPE_UNCACHABLE )
+ return MTRR_TYPE_UNCACHABLE;
+
+ /* If either type is WB, we have to go with the other one. */
+ if ( gmtrr_mtype == MTRR_TYPE_WRBACK )
+ return hmtrr_mtype;
+ if ( hmtrr_mtype == MTRR_TYPE_WRBACK )
+ return gmtrr_mtype;
+
+ /*
+ * At this point we have disagreeing WC, WT, or WP types. The only
+ * combination that can be cleanly resolved is WT:WP. The ones involving
+ * WC need to be converted to UC, both due to the memory ordering
+ * differences and because WC disallows reads to be cached (WT and WP
+ * permit this), while WT and WP require writes to go straight to memory
+ * (WC can buffer them).
+ */
+ if ( (gmtrr_mtype == MTRR_TYPE_WRTHROUGH &&
+ hmtrr_mtype == MTRR_TYPE_WRPROT) ||
+ (gmtrr_mtype == MTRR_TYPE_WRPROT &&
+ hmtrr_mtype == MTRR_TYPE_WRTHROUGH) )
+ return MTRR_TYPE_WRPROT;
+
+ return MTRR_TYPE_UNCACHABLE;
}
diff --git a/xen/arch/x86/hvm/rtc.c b/xen/arch/x86/hvm/rtc.c
index cdedefe..639b4c5 100644
--- a/xen/arch/x86/hvm/rtc.c
+++ b/xen/arch/x86/hvm/rtc.c
@@ -78,29 +78,44 @@ static void rtc_update_irq(RTCState *s)
hvm_isa_irq_assert(vrtc_domain(s), RTC_IRQ);
}
-bool_t rtc_periodic_interrupt(void *opaque)
+/* Called by the VPT code after it's injected a PF interrupt for us.
+ * Fix up the register state to reflect what happened. */
+static void rtc_pf_callback(struct vcpu *v, void *opaque)
{
RTCState *s = opaque;
- bool_t ret;
spin_lock(&s->lock);
- ret = rtc_mode_is(s, no_ack) || !(s->hw.cmos_data[RTC_REG_C] & RTC_IRQF);
- if ( rtc_mode_is(s, no_ack) || !(s->hw.cmos_data[RTC_REG_C] & RTC_PF) )
- {
- s->hw.cmos_data[RTC_REG_C] |= RTC_PF;
- rtc_update_irq(s);
- }
- else if ( ++(s->pt_dead_ticks) >= 10 )
+
+ if ( !rtc_mode_is(s, no_ack)
+ && (s->hw.cmos_data[RTC_REG_C] & RTC_IRQF)
+ && ++(s->pt_dead_ticks) >= 10 )
{
/* VM is ignoring its RTC; no point in running the timer */
destroy_periodic_time(&s->pt);
- s->pt_code = 0;
+ s->period = 0;
}
- if ( !(s->hw.cmos_data[RTC_REG_C] & RTC_IRQF) )
- ret = 0;
+
+ s->hw.cmos_data[RTC_REG_C] |= RTC_PF|RTC_IRQF;
+
spin_unlock(&s->lock);
+}
- return ret;
+/* Check whether the REG_C.PF bit should have been set by a tick since
+ * the last time we looked. This is used to track ticks when REG_B.PIE
+ * is clear; when PIE is set, PF ticks are handled by the VPT callbacks. */
+static void check_for_pf_ticks(RTCState *s)
+{
+ s_time_t now;
+
+ if ( s->period == 0 || (s->hw.cmos_data[RTC_REG_B] & RTC_PIE) )
+ return;
+
+ now = NOW();
+ if ( (now - s->start_time) / s->period
+ != (s->check_ticks_since - s->start_time) / s->period )
+ s->hw.cmos_data[RTC_REG_C] |= RTC_PF;
+
+ s->check_ticks_since = now;
}
/* Enable/configure/disable the periodic timer based on the RTC_PIE and
@@ -125,24 +140,29 @@ static void rtc_timer_update(RTCState *s)
case RTC_REF_CLCK_4MHZ:
if ( period_code != 0 )
{
- if ( period_code != s->pt_code )
+ period = 1 << (period_code - 1); /* period in 32 Khz cycles */
+ period = DIV_ROUND(period * 1000000000ULL, 32768); /* in ns */
+ if ( period != s->period )
{
- s->pt_code = period_code;
- period = 1 << (period_code - 1); /* period in 32 Khz cycles */
- period = DIV_ROUND(period * 1000000000ULL, 32768); /* in ns */
+ s_time_t now = NOW();
+
+ s->period = period;
if ( v->domain->arch.hvm_domain.params[HVM_PARAM_VPT_ALIGN] )
delta = 0;
else
- delta = period - ((NOW() - s->start_time) % period);
- create_periodic_time(v, &s->pt, delta, period,
- RTC_IRQ, NULL, s);
+ delta = period - ((now - s->start_time) % period);
+ if ( s->hw.cmos_data[RTC_REG_B] & RTC_PIE )
+ create_periodic_time(v, &s->pt, delta, period,
+ RTC_IRQ, rtc_pf_callback, s);
+ else
+ s->check_ticks_since = now;
}
break;
}
/* fall through */
default:
destroy_periodic_time(&s->pt);
- s->pt_code = 0;
+ s->period = 0;
break;
}
}
@@ -484,14 +504,19 @@ static int rtc_ioport_write(void *opaque, uint32_t addr, uint32_t data)
if ( orig & RTC_SET )
rtc_set_time(s);
}
+ check_for_pf_ticks(s);
s->hw.cmos_data[RTC_REG_B] = data;
/*
* If the interrupt is already set when the interrupt becomes
* enabled, raise an interrupt immediately.
*/
rtc_update_irq(s);
- if ( (data & RTC_PIE) && !(orig & RTC_PIE) )
+ if ( (data ^ orig) & RTC_PIE )
+ {
+ destroy_periodic_time(&s->pt);
+ s->period = 0;
rtc_timer_update(s);
+ }
if ( (data ^ orig) & RTC_SET )
check_update_timer(s);
if ( (data ^ orig) & (RTC_24H | RTC_DM_BINARY | RTC_SET) )
@@ -645,14 +670,14 @@ static uint32_t rtc_ioport_read(RTCState *s, uint32_t addr)
ret |= RTC_UIP;
break;
case RTC_REG_C:
+ check_for_pf_ticks(s);
ret = s->hw.cmos_data[s->hw.cmos_index];
s->hw.cmos_data[RTC_REG_C] = 0x00;
- if ( (ret & RTC_IRQF) && !rtc_mode_is(s, no_ack) )
+ if ( ret & RTC_IRQF )
hvm_isa_irq_deassert(d, RTC_IRQ);
- rtc_update_irq(s);
check_update_timer(s);
alarm_timer_update(s);
- rtc_timer_update(s);
+ s->pt_dead_ticks = 0;
break;
default:
ret = s->hw.cmos_data[s->hw.cmos_index];
@@ -748,7 +773,7 @@ void rtc_reset(struct domain *d)
RTCState *s = domain_vrtc(d);
destroy_periodic_time(&s->pt);
- s->pt_code = 0;
+ s->period = 0;
s->pt.source = PTSRC_isa;
}
diff --git a/xen/arch/x86/hvm/svm/svm.c b/xen/arch/x86/hvm/svm/svm.c
index 406d394..3f274f0 100644
--- a/xen/arch/x86/hvm/svm/svm.c
+++ b/xen/arch/x86/hvm/svm/svm.c
@@ -728,7 +728,7 @@ static void svm_set_rdtsc_exiting(struct vcpu *v, bool_t enable)
general1_intercepts &= ~GENERAL1_INTERCEPT_RDTSC;
general2_intercepts &= ~GENERAL2_INTERCEPT_RDTSCP;
- if ( enable && !cpu_has_tsc_ratio )
+ if ( enable )
{
general1_intercepts |= GENERAL1_INTERCEPT_RDTSC;
general2_intercepts |= GENERAL2_INTERCEPT_RDTSCP;
@@ -861,6 +861,14 @@ static void svm_ctxt_switch_from(struct vcpu *v)
{
int cpu = smp_processor_id();
+ /*
+ * Return early if trying to do a context switch without SVM enabled,
+ * this can happen when the hypervisor shuts down with HVM guests
+ * still running.
+ */
+ if ( unlikely((read_efer() & EFER_SVME) == 0) )
+ return;
+
svm_fpu_leave(v);
svm_save_dr(v);
diff --git a/xen/arch/x86/hvm/vmx/vmcs.c b/xen/arch/x86/hvm/vmx/vmcs.c
index 44f33cb..ee1f4d5 100644
--- a/xen/arch/x86/hvm/vmx/vmcs.c
+++ b/xen/arch/x86/hvm/vmx/vmcs.c
@@ -74,7 +74,7 @@ u64 vmx_ept_vpid_cap __read_mostly;
static DEFINE_PER_CPU_READ_MOSTLY(struct vmcs_struct *, vmxon_region);
static DEFINE_PER_CPU(struct vmcs_struct *, current_vmcs);
static DEFINE_PER_CPU(struct list_head, active_vmcs_list);
-static DEFINE_PER_CPU(bool_t, vmxon);
+DEFINE_PER_CPU(bool_t, vmxon);
static u32 vmcs_revision_id __read_mostly;
u64 __read_mostly vmx_basic_msr;
@@ -828,8 +828,12 @@ void virtual_vmcs_enter(void *vvmcs)
void virtual_vmcs_exit(void *vvmcs)
{
+ struct vmcs_struct *cur = this_cpu(current_vmcs);
+
__vmpclear(pfn_to_paddr(domain_page_map_to_mfn(vvmcs)));
- __vmptrld(virt_to_maddr(this_cpu(current_vmcs)));
+ if ( cur )
+ __vmptrld(virt_to_maddr(cur));
+
}
u64 virtual_vmcs_vmread(void *vvmcs, u32 vmcs_encoding)
diff --git a/xen/arch/x86/hvm/vmx/vmx.c b/xen/arch/x86/hvm/vmx/vmx.c
index f6409d6..2cd4c59 100644
--- a/xen/arch/x86/hvm/vmx/vmx.c
+++ b/xen/arch/x86/hvm/vmx/vmx.c
@@ -617,6 +617,14 @@ static void vmx_fpu_leave(struct vcpu *v)
static void vmx_ctxt_switch_from(struct vcpu *v)
{
+ /*
+ * Return early if trying to do a context switch without VMX enabled,
+ * this can happen when the hypervisor shuts down with HVM guests
+ * still running.
+ */
+ if ( unlikely(!this_cpu(vmxon)) )
+ return;
+
vmx_fpu_leave(v);
vmx_save_guest_msrs(v);
vmx_restore_host_msrs();
@@ -984,6 +992,8 @@ static void vmx_handle_cd(struct vcpu *v, unsigned long value)
vmx_get_guest_pat(v, pat);
vmx_set_guest_pat(v, uc_pat);
+ vmx_enable_intercept_for_msr(v, MSR_IA32_CR_PAT,
+ MSR_TYPE_R | MSR_TYPE_W);
wbinvd(); /* flush possibly polluted cache */
hvm_asid_flush_vcpu(v); /* invalidate memory type cached in TLB */
@@ -993,6 +1003,9 @@ static void vmx_handle_cd(struct vcpu *v, unsigned long value)
{
v->arch.hvm_vcpu.cache_mode = NORMAL_CACHE_MODE;
vmx_set_guest_pat(v, *pat);
+ if ( !iommu_enabled || iommu_snoop )
+ vmx_disable_intercept_for_msr(v, MSR_IA32_CR_PAT,
+ MSR_TYPE_R | MSR_TYPE_W);
hvm_asid_flush_vcpu(v); /* no need to flush cache */
}
}
@@ -1914,10 +1927,14 @@ static const struct lbr_info *last_branch_msr_get(void)
case 58: case 62:
/* Haswell */
case 60: case 63: case 69: case 70:
+ /* future */
+ case 61: case 78:
return nh_lbr;
break;
/* Atom */
- case 28:
+ case 28: case 38: case 39: case 53: case 54:
+ /* Silvermont */
+ case 55: case 74: case 77: case 90: case 93:
return at_lbr;
break;
}
@@ -2038,9 +2055,9 @@ static int vmx_alloc_vlapic_mapping(struct domain *d)
if ( apic_va == NULL )
return -ENOMEM;
share_xen_page_with_guest(virt_to_page(apic_va), d, XENSHARE_writable);
+ d->arch.hvm_domain.vmx.apic_access_mfn = virt_to_mfn(apic_va);
set_mmio_p2m_entry(d, paddr_to_pfn(APIC_DEFAULT_PHYS_BASE),
_mfn(virt_to_mfn(apic_va)));
- d->arch.hvm_domain.vmx.apic_access_mfn = virt_to_mfn(apic_va);
return 0;
}
@@ -2541,6 +2558,7 @@ void vmx_vmexit_handler(struct cpu_user_regs *regs)
vcpu_nestedhvm(v).nv_vmswitch_in_progress = 0;
if ( nestedhvm_vcpu_in_guestmode(v) )
{
+ paging_update_nestedmode(v);
if ( nvmx_n2_vmexit_handler(regs, exit_reason) )
goto out;
}
diff --git a/xen/arch/x86/hvm/vmx/vpmu_core2.c b/xen/arch/x86/hvm/vmx/vpmu_core2.c
index ee26362..f6e8ec0 100644
--- a/xen/arch/x86/hvm/vmx/vpmu_core2.c
+++ b/xen/arch/x86/hvm/vmx/vpmu_core2.c
@@ -916,6 +916,10 @@ int vmx_vpmu_initialise(struct vcpu *v, unsigned int vpmu_flags)
case 0x3f:
case 0x45:
case 0x46:
+
+ /* future: */
+ case 0x3d:
+ case 0x4e:
ret = core2_vpmu_initialise(v, vpmu_flags);
if ( !ret )
vpmu->arch_vpmu_ops = &core2_vpmu_ops;
diff --git a/xen/arch/x86/hvm/vpt.c b/xen/arch/x86/hvm/vpt.c
index 1961bda..f7af688 100644
--- a/xen/arch/x86/hvm/vpt.c
+++ b/xen/arch/x86/hvm/vpt.c
@@ -231,12 +231,9 @@ int pt_update_irq(struct vcpu *v)
struct periodic_time *pt, *temp, *earliest_pt;
uint64_t max_lag;
int irq, is_lapic;
- void *pt_priv;
- rescan:
spin_lock(&v->arch.hvm_vcpu.tm_lock);
- rescan_locked:
earliest_pt = NULL;
max_lag = -1ULL;
list_for_each_entry_safe ( pt, temp, head, list )
@@ -270,48 +267,11 @@ int pt_update_irq(struct vcpu *v)
earliest_pt->irq_issued = 1;
irq = earliest_pt->irq;
is_lapic = (earliest_pt->source == PTSRC_lapic);
- pt_priv = earliest_pt->priv;
spin_unlock(&v->arch.hvm_vcpu.tm_lock);
if ( is_lapic )
vlapic_set_irq(vcpu_vlapic(v), irq, 0);
- else if ( irq == RTC_IRQ && pt_priv )
- {
- if ( !rtc_periodic_interrupt(pt_priv) )
- irq = -1;
-
- pt_lock(earliest_pt);
-
- if ( irq < 0 && earliest_pt->pending_intr_nr )
- {
- /*
- * RTC periodic timer runs without the corresponding interrupt
- * being enabled - need to mimic enough of pt_intr_post() to keep
- * things going.
- */
- earliest_pt->pending_intr_nr = 0;
- earliest_pt->irq_issued = 0;
- set_timer(&earliest_pt->timer, earliest_pt->scheduled);
- }
- else if ( irq >= 0 && pt_irq_masked(earliest_pt) )
- {
- if ( earliest_pt->on_list )
- {
- /* suspend timer emulation */
- list_del(&earliest_pt->list);
- earliest_pt->on_list = 0;
- }
- irq = -1;
- }
-
- /* Avoid dropping the lock if we can. */
- if ( irq < 0 && v == earliest_pt->vcpu )
- goto rescan_locked;
- pt_unlock(earliest_pt);
- if ( irq < 0 )
- goto rescan;
- }
else
{
hvm_isa_irq_deassert(v->domain, irq);
diff --git a/xen/arch/x86/i387.c b/xen/arch/x86/i387.c
index bd72138..a372e0b 100644
--- a/xen/arch/x86/i387.c
+++ b/xen/arch/x86/i387.c
@@ -266,10 +266,10 @@ void vcpu_restore_fpu_lazy(struct vcpu *v)
* On each context switch, save the necessary FPU info of VCPU being switch
* out. It dispatches saving operation based on CPU's capability.
*/
-void vcpu_save_fpu(struct vcpu *v)
+static bool_t _vcpu_save_fpu(struct vcpu *v)
{
if ( !v->fpu_dirtied && !v->arch.nonlazy_xstate_used )
- return;
+ return 0;
ASSERT(!is_idle_vcpu(v));
@@ -284,9 +284,22 @@ void vcpu_save_fpu(struct vcpu *v)
fpu_fsave(v);
v->fpu_dirtied = 0;
+
+ return 1;
+}
+
+void vcpu_save_fpu(struct vcpu *v)
+{
+ _vcpu_save_fpu(v);
stts();
}
+void save_fpu_enable(void)
+{
+ if ( !_vcpu_save_fpu(current) )
+ clts();
+}
+
/* Initialize FPU's context save area */
int vcpu_init_fpu(struct vcpu *v)
{
diff --git a/xen/arch/x86/irq.c b/xen/arch/x86/irq.c
index db70077..88444be 100644
--- a/xen/arch/x86/irq.c
+++ b/xen/arch/x86/irq.c
@@ -1068,13 +1068,13 @@ bool_t cpu_has_pending_apic_eoi(void)
static inline void set_pirq_eoi(struct domain *d, unsigned int irq)
{
- if ( !is_hvm_domain(d) && d->arch.pv_domain.pirq_eoi_map )
+ if ( is_pv_domain(d) && d->arch.pv_domain.pirq_eoi_map )
set_bit(irq, d->arch.pv_domain.pirq_eoi_map);
}
static inline void clear_pirq_eoi(struct domain *d, unsigned int irq)
{
- if ( !is_hvm_domain(d) && d->arch.pv_domain.pirq_eoi_map )
+ if ( is_pv_domain(d) && d->arch.pv_domain.pirq_eoi_map )
clear_bit(irq, d->arch.pv_domain.pirq_eoi_map);
}
diff --git a/xen/arch/x86/microcode_amd.c b/xen/arch/x86/microcode_amd.c
index 3014245..32d7fa1 100644
--- a/xen/arch/x86/microcode_amd.c
+++ b/xen/arch/x86/microcode_amd.c
@@ -164,7 +164,7 @@ static int apply_microcode(int cpu)
if ( rev != hdr->patch_id )
{
printk(KERN_ERR "microcode: CPU%d update from revision "
- "%#x to %#x failed\n", cpu, hdr->patch_id, rev);
+ "%#x to %#x failed\n", cpu, rev, hdr->patch_id);
return -EIO;
}
diff --git a/xen/arch/x86/mm.c b/xen/arch/x86/mm.c
index 172c68c..fdc5ed3 100644
--- a/xen/arch/x86/mm.c
+++ b/xen/arch/x86/mm.c
@@ -2934,7 +2934,7 @@ long do_mmuext_op(
for ( i = 0; i < count; i++ )
{
- if ( curr->arch.old_guest_table || hypercall_preempt_check() )
+ if ( curr->arch.old_guest_table || (i && hypercall_preempt_check()) )
{
rc = -EAGAIN;
break;
@@ -3481,7 +3481,7 @@ long do_mmu_update(
for ( i = 0; i < count; i++ )
{
- if ( curr->arch.old_guest_table || hypercall_preempt_check() )
+ if ( curr->arch.old_guest_table || (i && hypercall_preempt_check()) )
{
rc = -EAGAIN;
break;
diff --git a/xen/arch/x86/mm/hap/hap.c b/xen/arch/x86/mm/hap/hap.c
index 5f75636..71227ef 100644
--- a/xen/arch/x86/mm/hap/hap.c
+++ b/xen/arch/x86/mm/hap/hap.c
@@ -326,7 +326,7 @@ hap_set_allocation(struct domain *d, unsigned int pages, int *preempted)
else
pages -= d->arch.paging.hap.p2m_pages;
- while ( d->arch.paging.hap.total_pages != pages )
+ for ( ; ; )
{
if ( d->arch.paging.hap.total_pages < pages )
{
@@ -355,6 +355,8 @@ hap_set_allocation(struct domain *d, unsigned int pages, int *preempted)
d->arch.paging.hap.total_pages--;
free_domheap_page(pg);
}
+ else
+ break;
/* Check to see if we need to yield and try again */
if ( preempted && hypercall_preempt_check() )
@@ -709,9 +711,8 @@ hap_write_p2m_entry(struct vcpu *v, unsigned long gfn, l1_pgentry_t *p,
}
safe_write_pte(p, new);
- if ( (old_flags & _PAGE_PRESENT)
- && (level == 1 || (level == 2 && (old_flags & _PAGE_PSE))) )
- flush_tlb_mask(d->domain_dirty_cpumask);
+ if ( old_flags & _PAGE_PRESENT )
+ flush_tlb_mask(d->domain_dirty_cpumask);
paging_unlock(d);
diff --git a/xen/arch/x86/mm/hap/nested_hap.c b/xen/arch/x86/mm/hap/nested_hap.c
index 38e2327..f4c3f34 100644
--- a/xen/arch/x86/mm/hap/nested_hap.c
+++ b/xen/arch/x86/mm/hap/nested_hap.c
@@ -133,7 +133,7 @@ nestedhap_fix_p2m(struct vcpu *v, struct p2m_domain *p2m,
gdprintk(XENLOG_ERR,
"failed to set entry for %#"PRIx64" -> %#"PRIx64"\n",
L2_gpa, L0_gpa);
- BUG();
+ domain_crash(p2m->domain);
}
}
diff --git a/xen/arch/x86/mm/mem_event.c b/xen/arch/x86/mm/mem_event.c
index d00e404..909d7a4 100644
--- a/xen/arch/x86/mm/mem_event.c
+++ b/xen/arch/x86/mm/mem_event.c
@@ -655,6 +655,38 @@ int mem_event_domctl(struct domain *d, xen_domctl_mem_event_op_t *mec,
return rc;
}
+void mem_event_vcpu_pause(struct vcpu *v)
+{
+ ASSERT(v == current);
+
+ atomic_inc(&v->mem_event_pause_count);
+ vcpu_pause_nosync(v);
+}
+
+void mem_event_vcpu_unpause(struct vcpu *v)
+{
+ int old, new, prev = v->mem_event_pause_count.counter;
+
+ /* All unpause requests as a result of toolstack responses. Prevent
+ * underflow of the vcpu pause count. */
+ do
+ {
+ old = prev;
+ new = old - 1;
+
+ if ( new < 0 )
+ {
+ printk(XENLOG_G_WARNING
+ "d%d:v%d mem_event: Too many unpause attempts\n",
+ v->domain->domain_id, v->vcpu_id);
+ return;
+ }
+
+ prev = cmpxchg(&v->mem_event_pause_count.counter, old, new);
+ } while ( prev != old );
+
+ vcpu_unpause(v);
+}
/*
* Local variables:
diff --git a/xen/arch/x86/mm/mem_sharing.c b/xen/arch/x86/mm/mem_sharing.c
index 4a5d9e8..11df871 100644
--- a/xen/arch/x86/mm/mem_sharing.c
+++ b/xen/arch/x86/mm/mem_sharing.c
@@ -568,7 +568,7 @@ int mem_sharing_notify_enomem(struct domain *d, unsigned long gfn,
if ( v->domain == d )
{
req.flags = MEM_EVENT_FLAG_VCPU_PAUSED;
- vcpu_pause_nosync(v);
+ mem_event_vcpu_pause(v);
}
req.p2mt = p2m_ram_shared;
@@ -596,11 +596,20 @@ int mem_sharing_sharing_resume(struct domain *d)
/* Get all requests off the ring */
while ( mem_event_get_response(d, &d->mem_event->share, &rsp) )
{
+ struct vcpu *v;
+
if ( rsp.flags & MEM_EVENT_FLAG_DUMMY )
continue;
+
+ /* Validate the vcpu_id in the response. */
+ if ( (rsp.vcpu_id >= d->max_vcpus) || !d->vcpu[rsp.vcpu_id] )
+ continue;
+
+ v = d->vcpu[rsp.vcpu_id];
+
/* Unpause domain/vcpu */
if ( rsp.flags & MEM_EVENT_FLAG_VCPU_PAUSED )
- vcpu_unpause(d->vcpu[rsp.vcpu_id]);
+ mem_event_vcpu_unpause(v);
}
return 0;
@@ -1268,8 +1277,8 @@ int relinquish_shared_pages(struct domain *d)
return 0;
p2m_lock(p2m);
- for (gfn = p2m->next_shared_gfn_to_relinquish;
- gfn < p2m->max_mapped_pfn; gfn++ )
+ for ( gfn = p2m->next_shared_gfn_to_relinquish;
+ gfn <= p2m->max_mapped_pfn; gfn++ )
{
p2m_access_t a;
p2m_type_t t;
diff --git a/xen/arch/x86/mm/p2m-pod.c b/xen/arch/x86/mm/p2m-pod.c
index 81645c4..d14565d 100644
--- a/xen/arch/x86/mm/p2m-pod.c
+++ b/xen/arch/x86/mm/p2m-pod.c
@@ -242,7 +242,8 @@ p2m_pod_set_cache_target(struct p2m_domain *p2m, unsigned long pod_target, int p
p2m_pod_cache_add(p2m, page, order);
- if ( hypercall_preempt_check() && preemptible )
+ if ( preemptible && pod_target != p2m->pod.count &&
+ hypercall_preempt_check() )
{
ret = -EAGAIN;
goto out;
@@ -286,7 +287,8 @@ p2m_pod_set_cache_target(struct p2m_domain *p2m, unsigned long pod_target, int p
put_page(page+i);
- if ( hypercall_preempt_check() && preemptible )
+ if ( preemptible && pod_target != p2m->pod.count &&
+ hypercall_preempt_check() )
{
ret = -EAGAIN;
goto out;
diff --git a/xen/arch/x86/mm/p2m.c b/xen/arch/x86/mm/p2m.c
index 8f380ed..246ddd7 100644
--- a/xen/arch/x86/mm/p2m.c
+++ b/xen/arch/x86/mm/p2m.c
@@ -1094,7 +1094,7 @@ void p2m_mem_paging_populate(struct domain *d, unsigned long gfn)
/* Pause domain if request came from guest and gfn has paging type */
if ( p2m_is_paging(p2mt) && v->domain == d )
{
- vcpu_pause_nosync(v);
+ mem_event_vcpu_pause(v);
req.flags |= MEM_EVENT_FLAG_VCPU_PAUSED;
}
/* No need to inform pager if the gfn is not in the page-out path */
@@ -1228,8 +1228,17 @@ void p2m_mem_paging_resume(struct domain *d)
/* Pull all responses off the ring */
while( mem_event_get_response(d, &d->mem_event->paging, &rsp) )
{
+ struct vcpu *v;
+
if ( rsp.flags & MEM_EVENT_FLAG_DUMMY )
continue;
+
+ /* Validate the vcpu_id in the response. */
+ if ( (rsp.vcpu_id >= d->max_vcpus) || !d->vcpu[rsp.vcpu_id] )
+ continue;
+
+ v = d->vcpu[rsp.vcpu_id];
+
/* Fix p2m entry if the page was not dropped */
if ( !(rsp.flags & MEM_EVENT_FLAG_DROP_PAGE) )
{
@@ -1248,7 +1257,7 @@ void p2m_mem_paging_resume(struct domain *d)
}
/* Unpause domain */
if ( rsp.flags & MEM_EVENT_FLAG_VCPU_PAUSED )
- vcpu_unpause(d->vcpu[rsp.vcpu_id]);
+ mem_event_vcpu_unpause(v);
}
}
@@ -1343,7 +1352,7 @@ bool_t p2m_mem_access_check(paddr_t gpa, bool_t gla_valid, unsigned long gla,
/* Pause the current VCPU */
if ( p2ma != p2m_access_n2rwx )
- vcpu_pause_nosync(v);
+ mem_event_vcpu_pause(v);
/* VCPU may be paused, return whether we promoted automatically */
return (p2ma == p2m_access_n2rwx);
@@ -1356,25 +1365,33 @@ void p2m_mem_access_resume(struct domain *d)
/* Pull all responses off the ring */
while( mem_event_get_response(d, &d->mem_event->access, &rsp) )
{
+ struct vcpu *v;
+
if ( rsp.flags & MEM_EVENT_FLAG_DUMMY )
continue;
+
+ /* Validate the vcpu_id in the response. */
+ if ( (rsp.vcpu_id >= d->max_vcpus) || !d->vcpu[rsp.vcpu_id] )
+ continue;
+
+ v = d->vcpu[rsp.vcpu_id];
+
/* Unpause domain */
if ( rsp.flags & MEM_EVENT_FLAG_VCPU_PAUSED )
- vcpu_unpause(d->vcpu[rsp.vcpu_id]);
+ mem_event_vcpu_unpause(v);
}
}
/* Set access type for a region of pfns.
* If start_pfn == -1ul, sets the default access type */
-int p2m_set_mem_access(struct domain *d, unsigned long start_pfn,
- uint32_t nr, hvmmem_access_t access)
+long p2m_set_mem_access(struct domain *d, unsigned long pfn, uint32_t nr,
+ hvmmem_access_t access)
{
struct p2m_domain *p2m = p2m_get_hostp2m(d);
- unsigned long pfn;
p2m_access_t a, _a;
p2m_type_t t;
mfn_t mfn;
- int rc = 0;
+ long rc;
/* N.B. _not_ static: initializer depends on p2m->default_access */
p2m_access_t memaccess[] = {
@@ -1397,14 +1414,17 @@ int p2m_set_mem_access(struct domain *d, unsigned long start_pfn,
a = memaccess[access];
/* If request to set default access */
- if ( start_pfn == ~0ull )
+ if ( pfn == ~0ul )
{
p2m->default_access = a;
return 0;
}
+ if ( !nr )
+ return 0;
+
p2m_lock(p2m);
- for ( pfn = start_pfn; pfn < start_pfn + nr; pfn++ )
+ for ( ; ; ++pfn )
{
mfn = p2m->get_entry(p2m, pfn, &t, &_a, 0, NULL);
if ( p2m->set_entry(p2m, pfn, mfn, PAGE_ORDER_4K, t, a) == 0 )
@@ -1412,6 +1432,13 @@ int p2m_set_mem_access(struct domain *d, unsigned long start_pfn,
rc = -ENOMEM;
break;
}
+
+ /* Check for continuation if it's not the last interation. */
+ if ( !--nr || hypercall_preempt_check() )
+ {
+ rc = nr;
+ break;
+ }
}
p2m_unlock(p2m);
return rc;
diff --git a/xen/arch/x86/mm/shadow/common.c b/xen/arch/x86/mm/shadow/common.c
index 11c6b62..be095f6 100644
--- a/xen/arch/x86/mm/shadow/common.c
+++ b/xen/arch/x86/mm/shadow/common.c
@@ -1674,7 +1674,7 @@ static unsigned int sh_set_allocation(struct domain *d,
SHADOW_PRINTK("current %i target %i\n",
d->arch.paging.shadow.total_pages, pages);
- while ( d->arch.paging.shadow.total_pages != pages )
+ for ( ; ; )
{
if ( d->arch.paging.shadow.total_pages < pages )
{
@@ -1709,6 +1709,8 @@ static unsigned int sh_set_allocation(struct domain *d,
d->arch.paging.shadow.total_pages--;
free_domheap_page(sp);
}
+ else
+ break;
/* Check to see if we need to yield and try again */
if ( preempted && hypercall_preempt_check() )
@@ -3487,9 +3489,7 @@ int shadow_track_dirty_vram(struct domain *d,
struct sh_dirty_vram *dirty_vram = d->arch.hvm_domain.dirty_vram;
struct p2m_domain *p2m = p2m_get_hostp2m(d);
- if (end_pfn < begin_pfn
- || begin_pfn > p2m->max_mapped_pfn
- || end_pfn >= p2m->max_mapped_pfn)
+ if ( end_pfn < begin_pfn || end_pfn > p2m->max_mapped_pfn + 1 )
return -EINVAL;
/* We perform p2m lookups, so lock the p2m upfront to avoid deadlock */
diff --git a/xen/arch/x86/msi.c b/xen/arch/x86/msi.c
index 1aaceeb..61d6dd0 100644
--- a/xen/arch/x86/msi.c
+++ b/xen/arch/x86/msi.c
@@ -636,7 +636,7 @@ static u64 read_pci_mem_bar(u16 seg, u8 bus, u8 slot, u8 func, u8 bir, int vf)
return 0;
base = pos + PCI_SRIOV_BAR;
vf -= PCI_BDF(bus, slot, func) + offset;
- if ( vf < 0 || (vf && vf % stride) )
+ if ( vf < 0 )
return 0;
if ( stride )
{
diff --git a/xen/arch/x86/nmi.c b/xen/arch/x86/nmi.c
index c67a9c3..7aaab8a 100644
--- a/xen/arch/x86/nmi.c
+++ b/xen/arch/x86/nmi.c
@@ -118,11 +118,12 @@ int __init check_nmi_watchdog (void)
{
static unsigned int __initdata prev_nmi_count[NR_CPUS];
int cpu;
-
+ bool_t ok = 1;
+
if ( !nmi_watchdog )
return 0;
- printk("Testing NMI watchdog --- ");
+ printk("Testing NMI watchdog on all CPUs:");
for_each_online_cpu ( cpu )
prev_nmi_count[cpu] = nmi_count(cpu);
@@ -137,12 +138,13 @@ int __init check_nmi_watchdog (void)
for_each_online_cpu ( cpu )
{
if ( nmi_count(cpu) - prev_nmi_count[cpu] <= 5 )
- printk("CPU#%d stuck. ", cpu);
- else
- printk("CPU#%d okay. ", cpu);
+ {
+ printk(" %d", cpu);
+ ok = 0;
+ }
}
- printk("\n");
+ printk(" %s\n", ok ? "ok" : "stuck");
/*
* Now that we know it works we can reduce NMI frequency to
diff --git a/xen/arch/x86/time.c b/xen/arch/x86/time.c
index 6e31e1f..f80d661 100644
--- a/xen/arch/x86/time.c
+++ b/xen/arch/x86/time.c
@@ -37,6 +37,7 @@
#include <asm/hpet.h>
#include <io_ports.h>
#include <asm/setup.h> /* for early_time_init */
+#include <asm/hvm/svm/svm.h> /* for cpu_has_tsc_ratio */
#include <public/arch-x86/cpuid.h>
/* opt_clocksource: Force clocksource to one of: pit, hpet, acpi. */
@@ -1632,6 +1633,7 @@ int dom0_pit_access(struct ioreq *ioreq)
outb(ioreq->data, PIT_MODE);
return 1;
}
+ break;
case 0x61:
if ( ioreq->dir == IOREQ_READ )
@@ -1883,10 +1885,16 @@ void tsc_set_info(struct domain *d,
d->arch.vtsc_offset = get_s_time() - elapsed_nsec;
d->arch.tsc_khz = gtsc_khz ? gtsc_khz : cpu_khz;
set_time_scale(&d->arch.vtsc_to_ns, d->arch.tsc_khz * 1000 );
- /* use native TSC if initial host has safe TSC, has not migrated
- * yet and tsc_khz == cpu_khz */
- if ( host_tsc_is_safe() && incarnation == 0 &&
- d->arch.tsc_khz == cpu_khz )
+ /*
+ * Use native TSC if the host has safe TSC and:
+ * HVM/PVH: host and guest frequencies are the same (either
+ * "naturally" or via TSC scaling)
+ * PV: guest has not migrated yet (and thus arch.tsc_khz == cpu_khz)
+ */
+ if ( host_tsc_is_safe() &&
+ ((has_hvm_container_domain(d) &&
+ (d->arch.tsc_khz == cpu_khz || cpu_has_tsc_ratio)) ||
+ incarnation == 0) )
d->arch.vtsc = 0;
else
d->arch.ns_to_vtsc = scale_reciprocal(d->arch.vtsc_to_ns);
diff --git a/xen/arch/x86/traps.c b/xen/arch/x86/traps.c
index 0bd43b9..4d27e12 100644
--- a/xen/arch/x86/traps.c
+++ b/xen/arch/x86/traps.c
@@ -3595,13 +3595,6 @@ long do_set_trap_table(XEN_GUEST_HANDLE_PARAM(const_trap_info_t) traps)
for ( ; ; )
{
- if ( hypercall_preempt_check() )
- {
- rc = hypercall_create_continuation(
- __HYPERVISOR_set_trap_table, "h", traps);
- break;
- }
-
if ( copy_from_guest(&cur, traps, 1) )
{
rc = -EFAULT;
@@ -3622,6 +3615,13 @@ long do_set_trap_table(XEN_GUEST_HANDLE_PARAM(const_trap_info_t) traps)
init_int80_direct_trap(curr);
guest_handle_add_offset(traps, 1);
+
+ if ( hypercall_preempt_check() )
+ {
+ rc = hypercall_create_continuation(
+ __HYPERVISOR_set_trap_table, "h", traps);
+ break;
+ }
}
return rc;
diff --git a/xen/arch/x86/x86_64/compat/traps.c b/xen/arch/x86/x86_64/compat/traps.c
index 21a82b9..5f0ea0a 100644
--- a/xen/arch/x86/x86_64/compat/traps.c
+++ b/xen/arch/x86/x86_64/compat/traps.c
@@ -329,13 +329,6 @@ int compat_set_trap_table(XEN_GUEST_HANDLE(trap_info_compat_t) traps)
for ( ; ; )
{
- if ( hypercall_preempt_check() )
- {
- rc = hypercall_create_continuation(
- __HYPERVISOR_set_trap_table, "h", traps);
- break;
- }
-
if ( copy_from_guest(&cur, traps, 1) )
{
rc = -EFAULT;
@@ -353,6 +346,13 @@ int compat_set_trap_table(XEN_GUEST_HANDLE(trap_info_compat_t) traps)
init_int80_direct_trap(current);
guest_handle_add_offset(traps, 1);
+
+ if ( hypercall_preempt_check() )
+ {
+ rc = hypercall_create_continuation(
+ __HYPERVISOR_set_trap_table, "h", traps);
+ break;
+ }
}
return rc;
diff --git a/xen/arch/x86/x86_emulate/x86_emulate.c b/xen/arch/x86/x86_emulate/x86_emulate.c
index e833cdf..50d8965 100644
--- a/xen/arch/x86/x86_emulate/x86_emulate.c
+++ b/xen/arch/x86/x86_emulate/x86_emulate.c
@@ -720,29 +720,26 @@ do{ uint8_t stub[] = { _bytes, 0xc3 }; \
put_fpu(&fic); \
} while (0)
-static unsigned long __get_rep_prefix(
- struct cpu_user_regs *int_regs,
- struct cpu_user_regs *ext_regs,
+static unsigned long _get_rep_prefix(
+ const struct cpu_user_regs *int_regs,
int ad_bytes)
{
- unsigned long ecx = ((ad_bytes == 2) ? (uint16_t)int_regs->ecx :
- (ad_bytes == 4) ? (uint32_t)int_regs->ecx :
- int_regs->ecx);
-
- /* Skip the instruction if no repetitions are required. */
- if ( ecx == 0 )
- ext_regs->eip = int_regs->eip;
-
- return ecx;
+ return (ad_bytes == 2) ? (uint16_t)int_regs->ecx :
+ (ad_bytes == 4) ? (uint32_t)int_regs->ecx :
+ int_regs->ecx;
}
#define get_rep_prefix() ({ \
unsigned long max_reps = 1; \
if ( rep_prefix() ) \
- max_reps = __get_rep_prefix(&_regs, ctxt->regs, ad_bytes); \
+ max_reps = _get_rep_prefix(&_regs, ad_bytes); \
if ( max_reps == 0 ) \
- goto done; \
- max_reps; \
+ { \
+ /* Skip the instruction if no repetitions are required. */ \
+ dst.type = OP_NONE; \
+ goto writeback; \
+ } \
+ max_reps; \
})
static void __put_rep_prefix(
@@ -3921,7 +3918,8 @@ x86_emulate(
if ( !rc && (b & 1) && (ea.type == OP_MEM) )
rc = ops->write(ea.mem.seg, ea.mem.off, mmvalp,
ea.bytes, ctxt);
- goto done;
+ dst.type = OP_NONE;
+ break;
}
case 0x20: /* mov cr,reg */
@@ -4188,7 +4186,8 @@ x86_emulate(
if ( !rc && (b != 0x6f) && (ea.type == OP_MEM) )
rc = ops->write(ea.mem.seg, ea.mem.off, mmvalp,
ea.bytes, ctxt);
- goto done;
+ dst.type = OP_NONE;
+ break;
}
case 0x80 ... 0x8f: /* jcc (near) */ {
diff --git a/xen/common/compat/multicall.c b/xen/common/compat/multicall.c
index 95c047a..2af8aef 100644
--- a/xen/common/compat/multicall.c
+++ b/xen/common/compat/multicall.c
@@ -29,7 +29,7 @@ DEFINE_XEN_GUEST_HANDLE(multicall_entry_compat_t);
static void __trace_multicall_call(multicall_entry_t *call)
{
- unsigned long args[6];
+ xen_ulong_t args[6];
int i;
for ( i = 0; i < ARRAY_SIZE(args); i++ )
diff --git a/xen/common/cpupool.c b/xen/common/cpupool.c
index 933de78..e46e930 100644
--- a/xen/common/cpupool.c
+++ b/xen/common/cpupool.c
@@ -471,12 +471,24 @@ static void cpupool_cpu_add(unsigned int cpu)
*/
static int cpupool_cpu_remove(unsigned int cpu)
{
- int ret = 0;
+ int ret = -EBUSY;
+ struct cpupool **c;
spin_lock(&cpupool_lock);
- if ( !cpumask_test_cpu(cpu, cpupool0->cpu_valid))
- ret = -EBUSY;
+ if ( cpumask_test_cpu(cpu, cpupool0->cpu_valid) )
+ ret = 0;
else
+ {
+ for_each_cpupool(c)
+ {
+ if ( cpumask_test_cpu(cpu, (*c)->cpu_suspended ) )
+ {
+ ret = 0;
+ break;
+ }
+ }
+ }
+ if ( !ret )
cpumask_set_cpu(cpu, &cpupool_locked_cpus);
spin_unlock(&cpupool_lock);
diff --git a/xen/common/device_tree.c b/xen/common/device_tree.c
index 55716a8..2ebacb2 100644
--- a/xen/common/device_tree.c
+++ b/xen/common/device_tree.c
@@ -350,9 +350,11 @@ static void __init process_multiboot_node(const void *fdt, int node,
struct dt_mb_module *mod;
int len;
- if ( fdt_node_check_compatible(fdt, node, "xen,linux-zimage") == 0 )
+ if ( fdt_node_check_compatible(fdt, node, "xen,linux-zimage") == 0 ||
+ fdt_node_check_compatible(fdt, node, "multiboot,kernel") == 0 )
nr = MOD_KERNEL;
- else if ( fdt_node_check_compatible(fdt, node, "xen,linux-initrd") == 0)
+ else if ( fdt_node_check_compatible(fdt, node, "xen,linux-initrd") == 0 ||
+ fdt_node_check_compatible(fdt, node, "multiboot,ramdisk") == 0 )
nr = MOD_INITRD;
else
early_panic("%s not a known xen multiboot type\n", name);
@@ -443,7 +445,8 @@ static int __init early_scan_node(const void *fdt,
{
if ( device_tree_node_matches(fdt, node, "memory") )
process_memory_node(fdt, node, name, address_cells, size_cells);
- else if ( device_tree_node_compatible(fdt, node, "xen,multiboot-module" ) )
+ else if ( device_tree_node_compatible(fdt, node, "xen,multiboot-module" ) ||
+ device_tree_node_compatible(fdt, node, "multiboot,module" ))
process_multiboot_node(fdt, node, name, address_cells, size_cells);
else if ( depth == 1 && device_tree_node_matches(fdt, node, "chosen") )
process_chosen_node(fdt, node, name, address_cells, size_cells);
diff --git a/xen/common/domain.c b/xen/common/domain.c
index 2636fc9..1308193 100644
--- a/xen/common/domain.c
+++ b/xen/common/domain.c
@@ -264,7 +264,7 @@ struct domain *domain_create(
if ( (err = xsm_domain_create(XSM_HOOK, d, ssidref)) != 0 )
goto fail;
- d->is_paused_by_controller = 1;
+ d->controller_pause_count = 1;
atomic_inc(&d->pause_count);
if ( domid )
@@ -539,6 +539,8 @@ int domain_kill(struct domain *d)
BUG_ON(rc != -EAGAIN);
break;
}
+ if ( sched_move_domain(d, cpupool0) )
+ return -EAGAIN;
for_each_vcpu ( d, v )
unmap_vcpu_info(v);
d->is_dying = DOMDYING_dead;
@@ -678,18 +680,13 @@ void vcpu_end_shutdown_deferral(struct vcpu *v)
#ifdef HAS_GDBSX
void domain_pause_for_debugger(void)
{
- struct domain *d = current->domain;
- struct vcpu *v;
+ struct vcpu *curr = current;
+ struct domain *d = curr->domain;
- atomic_inc(&d->pause_count);
- if ( test_and_set_bool(d->is_paused_by_controller) )
- domain_unpause(d); /* race-free atomic_dec(&d->pause_count) */
-
- for_each_vcpu ( d, v )
- vcpu_sleep_nosync(v);
+ domain_pause_by_systemcontroller_nosync(d);
/* if gdbsx active, we just need to pause the domain */
- if (current->arch.gdbsx_vcpu_event == 0)
+ if ( curr->arch.gdbsx_vcpu_event == 0 )
send_global_virq(VIRQ_DEBUGGER);
}
#endif
@@ -721,8 +718,6 @@ static void complete_domain_destroy(struct rcu_head *head)
sched_destroy_domain(d);
- cpupool_rm_domain(d);
-
/* Free page used by xen oprofile buffer. */
#ifdef CONFIG_XENOPROF
free_xenoprof_pages(d);
@@ -770,6 +765,8 @@ void domain_destroy(struct domain *d)
if ( _atomic_read(old) != 0 )
return;
+ cpupool_rm_domain(d);
+
/* Delete from task list and task hashtable. */
TRACE_1D(TRC_SCHED_DOM_REM, d->domain_id);
spin_lock(&domlist_update_lock);
@@ -837,17 +834,49 @@ void domain_unpause(struct domain *d)
vcpu_wake(v);
}
-void domain_pause_by_systemcontroller(struct domain *d)
+int __domain_pause_by_systemcontroller(struct domain *d,
+ void (*pause_fn)(struct domain *d))
{
- domain_pause(d);
- if ( test_and_set_bool(d->is_paused_by_controller) )
- domain_unpause(d);
+ int old, new, prev = d->controller_pause_count;
+
+ do
+ {
+ old = prev;
+ new = old + 1;
+
+ /*
+ * Limit the toolstack pause count to an arbitrary 255 to prevent the
+ * toolstack overflowing d->pause_count with many repeated hypercalls.
+ */
+ if ( new > 255 )
+ return -EUSERS;
+
+ prev = cmpxchg(&d->controller_pause_count, old, new);
+ } while ( prev != old );
+
+ pause_fn(d);
+
+ return 0;
}
-void domain_unpause_by_systemcontroller(struct domain *d)
+int domain_unpause_by_systemcontroller(struct domain *d)
{
- if ( test_and_clear_bool(d->is_paused_by_controller) )
- domain_unpause(d);
+ int old, new, prev = d->controller_pause_count;
+
+ do
+ {
+ old = prev;
+ new = old - 1;
+
+ if ( new < 0 )
+ return -EINVAL;
+
+ prev = cmpxchg(&d->controller_pause_count, old, new);
+ } while ( prev != old );
+
+ domain_unpause(d);
+
+ return 0;
}
int vcpu_reset(struct vcpu *v)
diff --git a/xen/common/domctl.c b/xen/common/domctl.c
index 7cf610a..060af1b 100644
--- a/xen/common/domctl.c
+++ b/xen/common/domctl.c
@@ -181,7 +181,7 @@ void getdomaininfo(struct domain *d, struct xen_domctl_getdomaininfo *info)
info->flags = (info->nr_online_vcpus ? flags : 0) |
((d->is_dying == DOMDYING_dead) ? XEN_DOMINF_dying : 0) |
(d->is_shut_down ? XEN_DOMINF_shutdown : 0) |
- (d->is_paused_by_controller ? XEN_DOMINF_paused : 0) |
+ (d->controller_pause_count > 0 ? XEN_DOMINF_paused : 0) |
(d->debugger_attached ? XEN_DOMINF_debugged : 0) |
d->shutdown_code << XEN_DOMINF_shutdownshift;
@@ -384,22 +384,14 @@ long do_domctl(XEN_GUEST_HANDLE_PARAM(xen_domctl_t) u_domctl)
break;
case XEN_DOMCTL_pausedomain:
- {
ret = -EINVAL;
if ( d != current->domain )
- {
- domain_pause_by_systemcontroller(d);
- ret = 0;
- }
- }
- break;
+ ret = domain_pause_by_systemcontroller(d);
+ break;
case XEN_DOMCTL_unpausedomain:
- {
- domain_unpause_by_systemcontroller(d);
- ret = 0;
- }
- break;
+ ret = domain_unpause_by_systemcontroller(d);
+ break;
case XEN_DOMCTL_resumedomain:
{
diff --git a/xen/common/event_channel.c b/xen/common/event_channel.c
index db952af..6fd4a2c 100644
--- a/xen/common/event_channel.c
+++ b/xen/common/event_channel.c
@@ -275,12 +275,12 @@ static long evtchn_bind_interdomain(evtchn_bind_interdomain_t *bind)
goto out;
lchn->u.interdomain.remote_dom = rd;
- lchn->u.interdomain.remote_port = (u16)rport;
+ lchn->u.interdomain.remote_port = rport;
lchn->state = ECS_INTERDOMAIN;
evtchn_port_init(ld, lchn);
rchn->u.interdomain.remote_dom = ld;
- rchn->u.interdomain.remote_port = (u16)lport;
+ rchn->u.interdomain.remote_port = lport;
rchn->state = ECS_INTERDOMAIN;
/*
diff --git a/xen/common/kexec.c b/xen/common/kexec.c
index 481b0c2..23d964e 100644
--- a/xen/common/kexec.c
+++ b/xen/common/kexec.c
@@ -265,6 +265,8 @@ static int noinline one_cpu_only(void)
}
set_bit(KEXEC_FLAG_IN_PROGRESS, &kexec_flags);
+ printk("Executing kexec image on cpu%u\n", cpu);
+
return 0;
}
@@ -340,8 +342,6 @@ void kexec_crash(void)
if ( !test_bit(KEXEC_IMAGE_CRASH_BASE + pos, &kexec_flags) )
return;
- printk("Executing crash image\n");
-
kexecing = TRUE;
if ( kexec_common_shutdown() != 0 )
diff --git a/xen/common/kimage.c b/xen/common/kimage.c
index 91943f1..9b79a5e 100644
--- a/xen/common/kimage.c
+++ b/xen/common/kimage.c
@@ -182,6 +182,7 @@ static int do_kimage_alloc(struct kexec_image **rimage, paddr_t entry,
goto out;
/* Add an empty indirection page. */
+ result = -ENOMEM;
image->entry_page = kimage_alloc_control_page(image, 0);
if ( !image->entry_page )
goto out;
diff --git a/xen/common/lz4/decompress.c b/xen/common/lz4/decompress.c
index 40b3381..5cf8f37 100644
--- a/xen/common/lz4/decompress.c
+++ b/xen/common/lz4/decompress.c
@@ -84,6 +84,8 @@ static int INIT lz4_uncompress(const unsigned char *source, unsigned char *dest,
ip += length;
break; /* EOF */
}
+ if (unlikely((unsigned long)cpy < (unsigned long)op))
+ goto _output_error;
LZ4_WILDCOPY(ip, op, cpy);
ip -= (op - cpy);
op = cpy;
@@ -142,6 +144,8 @@ static int INIT lz4_uncompress(const unsigned char *source, unsigned char *dest,
goto _output_error;
continue;
}
+ if (unlikely((unsigned long)cpy < (unsigned long)op))
+ goto _output_error;
LZ4_SECURECOPY(ref, op, cpy);
op = cpy; /* correction */
}
@@ -207,6 +211,8 @@ static int lz4_uncompress_unknownoutputsize(const unsigned char *source,
op += length;
break;/* Necessarily EOF, due to parsing restrictions */
}
+ if (unlikely((unsigned long)cpy < (unsigned long)op))
+ goto _output_error;
LZ4_WILDCOPY(ip, op, cpy);
ip -= (op - cpy);
op = cpy;
@@ -270,6 +276,8 @@ static int lz4_uncompress_unknownoutputsize(const unsigned char *source,
goto _output_error;
continue;
}
+ if (unlikely((unsigned long)cpy < (unsigned long)op))
+ goto _output_error;
LZ4_SECURECOPY(ref, op, cpy);
op = cpy; /* correction */
}
diff --git a/xen/common/memory.c b/xen/common/memory.c
index 5a0efd5..4d6ffee 100644
--- a/xen/common/memory.c
+++ b/xen/common/memory.c
@@ -63,7 +63,7 @@ static void increase_reservation(struct memop_args *a)
for ( i = a->nr_done; i < a->nr_extents; i++ )
{
- if ( hypercall_preempt_check() )
+ if ( i != a->nr_done && hypercall_preempt_check() )
{
a->preempted = 1;
goto out;
@@ -109,7 +109,7 @@ static void populate_physmap(struct memop_args *a)
for ( i = a->nr_done; i < a->nr_extents; i++ )
{
- if ( hypercall_preempt_check() )
+ if ( i != a->nr_done && hypercall_preempt_check() )
{
a->preempted = 1;
goto out;
@@ -268,7 +268,7 @@ static void decrease_reservation(struct memop_args *a)
for ( i = a->nr_done; i < a->nr_extents; i++ )
{
- if ( hypercall_preempt_check() )
+ if ( i != a->nr_done && hypercall_preempt_check() )
{
a->preempted = 1;
goto out;
@@ -398,7 +398,8 @@ static long memory_exchange(XEN_GUEST_HANDLE_PARAM(xen_memory_exchange_t) arg)
i < (exch.in.nr_extents >> in_chunk_order);
i++ )
{
- if ( hypercall_preempt_check() )
+ if ( i != (exch.nr_exchanged >> in_chunk_order) &&
+ hypercall_preempt_check() )
{
exch.nr_exchanged = i << in_chunk_order;
rcu_unlock_domain(d);
diff --git a/xen/common/multicall.c b/xen/common/multicall.c
index 2afba98..fa9d910 100644
--- a/xen/common/multicall.c
+++ b/xen/common/multicall.c
@@ -35,10 +35,10 @@ static void trace_multicall_call(multicall_entry_t *call)
ret_t
do_multicall(
- XEN_GUEST_HANDLE_PARAM(multicall_entry_t) call_list, unsigned int nr_calls)
+ XEN_GUEST_HANDLE_PARAM(multicall_entry_t) call_list, uint32_t nr_calls)
{
struct mc_state *mcs = ¤t->mc_state;
- unsigned int i;
+ uint32_t i;
int rc = 0;
if ( unlikely(__test_and_set_bit(_MCSF_in_multicall, &mcs->flags)) )
@@ -52,7 +52,7 @@ do_multicall(
for ( i = 0; !rc && i < nr_calls; i++ )
{
- if ( hypercall_preempt_check() )
+ if ( i && hypercall_preempt_check() )
goto preempted;
if ( unlikely(__copy_from_guest(&mcs->call, call_list, 1)) )
diff --git a/xen/common/page_alloc.c b/xen/common/page_alloc.c
index 601319c..5cbdeb7 100644
--- a/xen/common/page_alloc.c
+++ b/xen/common/page_alloc.c
@@ -1409,7 +1409,10 @@ void free_xenheap_pages(void *v, unsigned int order)
pg = virt_to_page(v);
for ( i = 0; i < (1u << order); i++ )
+ {
+ scrub_one_page(&pg[i]);
pg[i].count_info &= ~PGC_xen_heap;
+ }
free_heap_pages(pg, order);
}
@@ -1579,6 +1582,8 @@ void free_domheap_pages(struct page_info *pg, unsigned int order)
else
{
/* Freeing anonymous domain-heap pages. */
+ for ( i = 0; i < (1 << order); i++ )
+ scrub_one_page(&pg[i]);
free_heap_pages(pg, order);
drop_dom_ref = 0;
}
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 1192fe2..2f28487 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -297,7 +297,8 @@ int sched_move_domain(struct domain *d, struct cpupool *c)
spin_unlock_irq(lock);
v->sched_priv = vcpu_priv[v->vcpu_id];
- evtchn_move_pirqs(v);
+ if ( !d->is_dying )
+ evtchn_move_pirqs(v);
new_p = cpumask_cycle(new_p, c->cpu_valid);
diff --git a/xen/common/timer.c b/xen/common/timer.c
index 1895a78..f36aebc 100644
--- a/xen/common/timer.c
+++ b/xen/common/timer.c
@@ -492,8 +492,9 @@ static void timer_softirq_action(void)
deadline = heap[1]->expires;
if ( (ts->list != NULL) && (ts->list->expires < deadline) )
deadline = ts->list->expires;
+ now = NOW();
this_cpu(timer_deadline) =
- (deadline == STIME_MAX) ? 0 : deadline + timer_slop;
+ (deadline == STIME_MAX) ? 0 : MAX(deadline, now + timer_slop);
if ( !reprogram_timer(this_cpu(timer_deadline)) )
raise_softirq(TIMER_SOFTIRQ);
diff --git a/xen/common/tmem.c b/xen/common/tmem.c
index d9e912b..ea4d9cc 100644
--- a/xen/common/tmem.c
+++ b/xen/common/tmem.c
@@ -1845,8 +1845,6 @@ static int do_tmem_destroy_pool(uint32_t pool_id)
struct client *client = current->domain->tmem_client;
struct tmem_pool *pool;
- if ( client->pools == NULL )
- return 0;
if ( pool_id >= MAX_POOLS_PER_DOMAIN )
return 0;
if ( (pool = client->pools[pool_id]) == NULL )
diff --git a/xen/common/trace.c b/xen/common/trace.c
index 41ddc33..0bc8ca2 100644
--- a/xen/common/trace.c
+++ b/xen/common/trace.c
@@ -817,7 +817,7 @@ unlock:
}
void __trace_hypercall(uint32_t event, unsigned long op,
- const unsigned long *args)
+ const xen_ulong_t *args)
{
struct {
uint32_t op;
diff --git a/xen/common/xmalloc_tlsf.c b/xen/common/xmalloc_tlsf.c
index d3bdfa7..a5769c9 100644
--- a/xen/common/xmalloc_tlsf.c
+++ b/xen/common/xmalloc_tlsf.c
@@ -527,11 +527,10 @@ static void xmalloc_pool_put(void *p)
static void *xmalloc_whole_pages(unsigned long size, unsigned long align)
{
- unsigned int i, order = get_order_from_bytes(size);
+ unsigned int i, order;
void *res, *p;
- if ( align > size )
- get_order_from_bytes(align);
+ order = get_order_from_bytes(max(align, size));
res = alloc_xenheap_pages(order, 0);
if ( res == NULL )
diff --git a/xen/drivers/acpi/apei/Makefile b/xen/drivers/acpi/apei/Makefile
index af6ecb0..6ad7c64 100644
--- a/xen/drivers/acpi/apei/Makefile
+++ b/xen/drivers/acpi/apei/Makefile
@@ -1,3 +1,4 @@
obj-y += erst.o
+obj-y += hest.o
obj-y += apei-base.o
obj-y += apei-io.o
diff --git a/xen/drivers/acpi/apei/erst.c b/xen/drivers/acpi/apei/erst.c
index 98f73d9..2583afa 100644
--- a/xen/drivers/acpi/apei/erst.c
+++ b/xen/drivers/acpi/apei/erst.c
@@ -760,21 +760,27 @@ int __init erst_init(void)
{
int rc = 0;
acpi_status status;
+ acpi_physical_address erst_addr;
+ acpi_native_uint erst_len;
struct apei_exec_context ctx;
if (acpi_disabled)
return -ENODEV;
- status = acpi_get_table(ACPI_SIG_ERST, 0,
- (struct acpi_table_header **)&erst_tab);
+ status = acpi_get_table_phys(ACPI_SIG_ERST, 0, &erst_addr, &erst_len);
if (status == AE_NOT_FOUND) {
printk(KERN_INFO "ERST table was not found\n");
return -ENODEV;
- } else if (ACPI_FAILURE(status)) {
+ }
+ if (ACPI_FAILURE(status)) {
const char *msg = acpi_format_exception(status);
printk(KERN_WARNING "Failed to get ERST table: %s\n", msg);
return -EINVAL;
}
+ map_pages_to_xen((unsigned long)__va(erst_addr), PFN_DOWN(erst_addr),
+ PFN_UP(erst_addr + erst_len) - PFN_DOWN(erst_addr),
+ PAGE_HYPERVISOR);
+ erst_tab = __va(erst_addr);
rc = erst_check_table(erst_tab);
if (rc) {
diff --git a/xen/drivers/acpi/apei/hest.c b/xen/drivers/acpi/apei/hest.c
new file mode 100644
index 0000000..b8790a6
--- /dev/null
+++ b/xen/drivers/acpi/apei/hest.c
@@ -0,0 +1,200 @@
+/*
+ * APEI Hardware Error Souce Table support
+ *
+ * HEST describes error sources in detail; communicates operational
+ * parameters (i.e. severity levels, masking bits, and threshold
+ * values) to Linux as necessary. It also allows the BIOS to report
+ * non-standard error sources to Linux (for example, chipset-specific
+ * error registers).
+ *
+ * For more information about HEST, please refer to ACPI Specification
+ * version 4.0, section 17.3.2.
+ *
+ * Copyright 2009 Intel Corp.
+ * Author: Huang Ying <ying.huang at intel.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License version
+ * 2 as published by the Free Software Foundation;
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <xen/errno.h>
+#include <xen/init.h>
+#include <xen/kernel.h>
+#include <xen/mm.h>
+#include <xen/pfn.h>
+#include <acpi/acpi.h>
+#include <acpi/apei.h>
+
+#include "apei-internal.h"
+
+#define HEST_PFX "HEST: "
+
+static bool_t hest_disable;
+boolean_param("hest_disable", hest_disable);
+
+/* HEST table parsing */
+
+static struct acpi_table_hest *__read_mostly hest_tab;
+
+static const int hest_esrc_len_tab[ACPI_HEST_TYPE_RESERVED] = {
+ [ACPI_HEST_TYPE_IA32_CHECK] = -1, /* need further calculation */
+ [ACPI_HEST_TYPE_IA32_CORRECTED_CHECK] = -1,
+ [ACPI_HEST_TYPE_IA32_NMI] = sizeof(struct acpi_hest_ia_nmi),
+ [ACPI_HEST_TYPE_AER_ROOT_PORT] = sizeof(struct acpi_hest_aer_root),
+ [ACPI_HEST_TYPE_AER_ENDPOINT] = sizeof(struct acpi_hest_aer),
+ [ACPI_HEST_TYPE_AER_BRIDGE] = sizeof(struct acpi_hest_aer_bridge),
+ [ACPI_HEST_TYPE_GENERIC_ERROR] = sizeof(struct acpi_hest_generic),
+};
+
+static int hest_esrc_len(const struct acpi_hest_header *hest_hdr)
+{
+ u16 hest_type = hest_hdr->type;
+ int len;
+
+ if (hest_type >= ACPI_HEST_TYPE_RESERVED)
+ return 0;
+
+ len = hest_esrc_len_tab[hest_type];
+
+ if (hest_type == ACPI_HEST_TYPE_IA32_CORRECTED_CHECK) {
+ const struct acpi_hest_ia_corrected *cmc =
+ container_of(hest_hdr,
+ const struct acpi_hest_ia_corrected,
+ header);
+
+ len = sizeof(*cmc) + cmc->num_hardware_banks *
+ sizeof(struct acpi_hest_ia_error_bank);
+ } else if (hest_type == ACPI_HEST_TYPE_IA32_CHECK) {
+ const struct acpi_hest_ia_machine_check *mc =
+ container_of(hest_hdr,
+ const struct acpi_hest_ia_machine_check,
+ header);
+
+ len = sizeof(*mc) + mc->num_hardware_banks *
+ sizeof(struct acpi_hest_ia_error_bank);
+ }
+ BUG_ON(len == -1);
+
+ return len;
+};
+
+int apei_hest_parse(apei_hest_func_t func, void *data)
+{
+ struct acpi_hest_header *hest_hdr;
+ int i, rc, len;
+
+ if (hest_disable || !hest_tab)
+ return -EINVAL;
+
+ hest_hdr = (struct acpi_hest_header *)(hest_tab + 1);
+ for (i = 0; i < hest_tab->error_source_count; i++) {
+ len = hest_esrc_len(hest_hdr);
+ if (!len) {
+ printk(XENLOG_WARNING HEST_PFX
+ "Unknown or unused hardware error source "
+ "type: %d for hardware error source: %d\n",
+ hest_hdr->type, hest_hdr->source_id);
+ return -EINVAL;
+ }
+ if ((void *)hest_hdr + len >
+ (void *)hest_tab + hest_tab->header.length) {
+ printk(XENLOG_WARNING HEST_PFX
+ "Table contents overflow for hardware error source: %d\n",
+ hest_hdr->source_id);
+ return -EINVAL;
+ }
+
+ rc = func(hest_hdr, data);
+ if (rc)
+ return rc;
+
+ hest_hdr = (void *)hest_hdr + len;
+ }
+
+ return 0;
+}
+
+/*
+ * Check if firmware advertises firmware first mode. We need FF bit to be set
+ * along with a set of MC banks which work in FF mode.
+ */
+static int __init hest_parse_cmc(const struct acpi_hest_header *hest_hdr,
+ void *data)
+{
+#ifdef CONFIG_X86_MCE
+ unsigned int i;
+ const struct acpi_hest_ia_corrected *cmc;
+ const struct acpi_hest_ia_error_bank *mc_bank;
+
+ if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK)
+ return 0;
+
+ cmc = container_of(hest_hdr, const struct acpi_hest_ia_corrected, header);
+ if (!cmc->enabled)
+ return 0;
+
+ /*
+ * We expect HEST to provide a list of MC banks that report errors
+ * in firmware first mode. Otherwise, return non-zero value to
+ * indicate that we are done parsing HEST.
+ */
+ if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) || !cmc->num_hardware_banks)
+ return 1;
+
+ printk(XENLOG_INFO HEST_PFX "Enabling Firmware First mode for corrected errors.\n");
+
+ mc_bank = (const struct acpi_hest_ia_error_bank *)(cmc + 1);
+ for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++)
+ mce_disable_bank(mc_bank->bank_number);
+#else
+# define acpi_disable_cmcff 1
+#endif
+
+ return 1;
+}
+
+void __init acpi_hest_init(void)
+{
+ acpi_status status;
+ acpi_physical_address hest_addr;
+ acpi_native_uint hest_len;
+
+ if (acpi_disabled)
+ return;
+
+ if (hest_disable) {
+ printk(XENLOG_INFO HEST_PFX "Table parsing disabled.\n");
+ return;
+ }
+
+ status = acpi_get_table_phys(ACPI_SIG_HEST, 0, &hest_addr, &hest_len);
+ if (status == AE_NOT_FOUND)
+ goto err;
+ if (ACPI_FAILURE(status)) {
+ printk(XENLOG_ERR HEST_PFX "Failed to get table, %s\n",
+ acpi_format_exception(status));
+ goto err;
+ }
+ map_pages_to_xen((unsigned long)__va(hest_addr), PFN_DOWN(hest_addr),
+ PFN_UP(hest_addr + hest_len) - PFN_DOWN(hest_addr),
+ PAGE_HYPERVISOR);
+ hest_tab = __va(hest_addr);
+
+ if (!acpi_disable_cmcff)
+ apei_hest_parse(hest_parse_cmc, NULL);
+
+ printk(XENLOG_INFO HEST_PFX "Table parsing has been initialized\n");
+ return;
+err:
+ hest_disable = 1;
+}
diff --git a/xen/drivers/acpi/tables.c b/xen/drivers/acpi/tables.c
index 08e8f3b..1beca79 100644
--- a/xen/drivers/acpi/tables.c
+++ b/xen/drivers/acpi/tables.c
@@ -233,6 +233,12 @@ acpi_table_parse_entries(char *id,
while (((unsigned long)entry) + sizeof(struct acpi_subtable_header) <
table_end) {
+ if (entry->length < sizeof(*entry)) {
+ printk(KERN_ERR PREFIX "[%4.4s:%#x] Invalid length\n",
+ id, entry_id);
+ return -ENODATA;
+ }
+
if (entry->type == entry_id
&& (!max_entries || count++ < max_entries))
if (handler(entry, table_end))
diff --git a/xen/drivers/char/console.c b/xen/drivers/char/console.c
index 532c426..89ffe64 100644
--- a/xen/drivers/char/console.c
+++ b/xen/drivers/char/console.c
@@ -375,12 +375,12 @@ static DECLARE_SOFTIRQ_TASKLET(notify_dom0_con_ring_tasklet,
static long guest_console_write(XEN_GUEST_HANDLE_PARAM(char) buffer, int count)
{
char kbuf[128];
- int kcount;
+ int kcount = 0;
struct domain *cd = current->domain;
while ( count > 0 )
{
- if ( hypercall_preempt_check() )
+ if ( kcount && hypercall_preempt_check() )
return hypercall_create_continuation(
__HYPERVISOR_console_io, "iih",
CONSOLEIO_write, count, buffer);
diff --git a/xen/drivers/passthrough/amd/iommu_map.c b/xen/drivers/passthrough/amd/iommu_map.c
index 1294561..5e02ac8 100644
--- a/xen/drivers/passthrough/amd/iommu_map.c
+++ b/xen/drivers/passthrough/amd/iommu_map.c
@@ -691,8 +691,6 @@ int amd_iommu_map_page(struct domain *d, unsigned long gfn, unsigned long mfn,
if ( !iommu_update_pde_count(d, pt_mfn[merge_level],
gfn, mfn, merge_level) )
break;
- /* Deallocate lower level page table */
- free_amd_iommu_pgtable(mfn_to_page(pt_mfn[merge_level - 1]));
if ( iommu_merge_pages(d, pt_mfn[merge_level], gfn,
flags, merge_level) )
@@ -703,6 +701,9 @@ int amd_iommu_map_page(struct domain *d, unsigned long gfn, unsigned long mfn,
domain_crash(d);
return -EFAULT;
}
+
+ /* Deallocate lower level page table */
+ free_amd_iommu_pgtable(mfn_to_page(pt_mfn[merge_level - 1]));
}
out:
diff --git a/xen/drivers/passthrough/amd/pci_amd_iommu.c b/xen/drivers/passthrough/amd/pci_amd_iommu.c
index c26aabc..f97fcf2 100644
--- a/xen/drivers/passthrough/amd/pci_amd_iommu.c
+++ b/xen/drivers/passthrough/amd/pci_amd_iommu.c
@@ -163,7 +163,7 @@ static void amd_iommu_setup_domain_device(
!pci_ats_enabled(iommu->seg, bus, pdev->devfn) )
{
if ( devfn == pdev->devfn )
- enable_ats_device(iommu->seg, bus, devfn);
+ enable_ats_device(iommu->seg, bus, devfn, iommu);
amd_iommu_flush_iotlb(devfn, pdev, INV_IOMMU_ALL_PAGES_ADDRESS, 0);
}
diff --git a/xen/drivers/passthrough/ats.h b/xen/drivers/passthrough/ats.h
index cf649d4..000e76d 100644
--- a/xen/drivers/passthrough/ats.h
+++ b/xen/drivers/passthrough/ats.h
@@ -24,6 +24,7 @@ struct pci_ats_dev {
u8 bus;
u8 devfn;
u16 ats_queue_depth; /* ATS device invalidation queue depth */
+ const void *iommu; /* No common IOMMU struct so use void pointer */
};
#define ATS_REG_CAP 4
@@ -34,7 +35,7 @@ struct pci_ats_dev {
extern struct list_head ats_devices;
extern bool_t ats_enabled;
-int enable_ats_device(int seg, int bus, int devfn);
+int enable_ats_device(int seg, int bus, int devfn, const void *iommu);
void disable_ats_device(int seg, int bus, int devfn);
struct pci_ats_dev *get_ats_device(int seg, int bus, int devfn);
diff --git a/xen/drivers/passthrough/iommu.c b/xen/drivers/passthrough/iommu.c
index 19b0e23..c687c53 100644
--- a/xen/drivers/passthrough/iommu.c
+++ b/xen/drivers/passthrough/iommu.c
@@ -412,9 +412,8 @@ static int iommu_populate_page_table(struct domain *d)
void iommu_domain_destroy(struct domain *d)
{
struct hvm_iommu *hd = domain_hvm_iommu(d);
- struct list_head *ioport_list, *rmrr_list, *tmp;
+ struct list_head *ioport_list, *tmp;
struct g2m_ioport *ioport;
- struct mapped_rmrr *mrmrr;
if ( !iommu_enabled || !hd->platform_ops )
return;
@@ -428,13 +427,6 @@ void iommu_domain_destroy(struct domain *d)
list_del(&ioport->list);
xfree(ioport);
}
-
- list_for_each_safe ( rmrr_list, tmp, &hd->mapped_rmrrs )
- {
- mrmrr = list_entry(rmrr_list, struct mapped_rmrr, list);
- list_del(&mrmrr->list);
- xfree(mrmrr);
- }
}
int iommu_map_page(struct domain *d, unsigned long gfn, unsigned long mfn,
diff --git a/xen/drivers/passthrough/pci.c b/xen/drivers/passthrough/pci.c
index c5c8344..e5d332d 100644
--- a/xen/drivers/passthrough/pci.c
+++ b/xen/drivers/passthrough/pci.c
@@ -27,6 +27,7 @@
#include <xen/delay.h>
#include <xen/keyhandler.h>
#include <xen/radix-tree.h>
+#include <xen/softirq.h>
#include <xen/tasklet.h>
#include <xsm/xsm.h>
#include <asm/msi.h>
@@ -153,6 +154,115 @@ static void __init parse_phantom_dev(char *str) {
}
custom_param("pci-phantom", parse_phantom_dev);
+static u16 __read_mostly command_mask;
+static u16 __read_mostly bridge_ctl_mask;
+
+/*
+ * The 'pci' parameter controls certain PCI device aspects.
+ * Optional comma separated value may contain:
+ *
+ * serr don't suppress system errors (default)
+ * no-serr suppress system errors
+ * perr don't suppress parity errors (default)
+ * no-perr suppress parity errors
+ */
+static void __init parse_pci_param(char *s)
+{
+ char *ss;
+
+ do {
+ bool_t on = !!strncmp(s, "no-", 3);
+ u16 cmd_mask = 0, brctl_mask = 0;
+
+ if ( !on )
+ s += 3;
+
+ ss = strchr(s, ',');
+ if ( ss )
+ *ss = '\0';
+
+ if ( !strcmp(s, "serr") )
+ {
+ cmd_mask = PCI_COMMAND_SERR;
+ brctl_mask = PCI_BRIDGE_CTL_SERR | PCI_BRIDGE_CTL_DTMR_SERR;
+ }
+ else if ( !strcmp(s, "perr") )
+ {
+ cmd_mask = PCI_COMMAND_PARITY;
+ brctl_mask = PCI_BRIDGE_CTL_PARITY;
+ }
+
+ if ( on )
+ {
+ command_mask &= ~cmd_mask;
+ bridge_ctl_mask &= ~brctl_mask;
+ }
+ else
+ {
+ command_mask |= cmd_mask;
+ bridge_ctl_mask |= brctl_mask;
+ }
+
+ s = ss + 1;
+ } while ( ss );
+}
+custom_param("pci", parse_pci_param);
+
+static void check_pdev(const struct pci_dev *pdev)
+{
+#define PCI_STATUS_CHECK \
+ (PCI_STATUS_PARITY | PCI_STATUS_SIG_TARGET_ABORT | \
+ PCI_STATUS_REC_TARGET_ABORT | PCI_STATUS_REC_MASTER_ABORT | \
+ PCI_STATUS_SIG_SYSTEM_ERROR | PCI_STATUS_DETECTED_PARITY)
+ u16 seg = pdev->seg;
+ u8 bus = pdev->bus;
+ u8 dev = PCI_SLOT(pdev->devfn);
+ u8 func = PCI_FUNC(pdev->devfn);
+ u16 val;
+
+ if ( command_mask )
+ {
+ val = pci_conf_read16(seg, bus, dev, func, PCI_COMMAND);
+ if ( val & command_mask )
+ pci_conf_write16(seg, bus, dev, func, PCI_COMMAND,
+ val & ~command_mask);
+ val = pci_conf_read16(seg, bus, dev, func, PCI_STATUS);
+ if ( val & PCI_STATUS_CHECK )
+ {
+ printk(XENLOG_INFO "%04x:%02x:%02x.%u status %04x -> %04x\n",
+ seg, bus, dev, func, val, val & ~PCI_STATUS_CHECK);
+ pci_conf_write16(seg, bus, dev, func, PCI_STATUS,
+ val & PCI_STATUS_CHECK);
+ }
+ }
+
+ switch ( pci_conf_read8(seg, bus, dev, func, PCI_HEADER_TYPE) & 0x7f )
+ {
+ case PCI_HEADER_TYPE_BRIDGE:
+ if ( !bridge_ctl_mask )
+ break;
+ val = pci_conf_read16(seg, bus, dev, func, PCI_BRIDGE_CONTROL);
+ if ( val & bridge_ctl_mask )
+ pci_conf_write16(seg, bus, dev, func, PCI_BRIDGE_CONTROL,
+ val & ~bridge_ctl_mask);
+ val = pci_conf_read16(seg, bus, dev, func, PCI_SEC_STATUS);
+ if ( val & PCI_STATUS_CHECK )
+ {
+ printk(XENLOG_INFO
+ "%04x:%02x:%02x.%u secondary status %04x -> %04x\n",
+ seg, bus, dev, func, val, val & ~PCI_STATUS_CHECK);
+ pci_conf_write16(seg, bus, dev, func, PCI_SEC_STATUS,
+ val & PCI_STATUS_CHECK);
+ }
+ break;
+
+ case PCI_HEADER_TYPE_CARDBUS:
+ /* TODO */
+ break;
+ }
+#undef PCI_STATUS_CHECK
+}
+
static struct pci_dev *alloc_pdev(struct pci_seg *pseg, u8 bus, u8 devfn)
{
struct pci_dev *pdev;
@@ -251,6 +361,8 @@ static struct pci_dev *alloc_pdev(struct pci_seg *pseg, u8 bus, u8 devfn)
break;
}
+ check_pdev(pdev);
+
return pdev;
}
@@ -565,6 +677,8 @@ int pci_add_device(u16 seg, u8 bus, u8 devfn, const struct pci_dev_info *info)
seg, bus, slot, func, ctrl);
}
+ check_pdev(pdev);
+
ret = 0;
if ( !pdev->domain )
{
@@ -922,6 +1036,20 @@ static int __init _setup_dom0_pci_devices(struct pci_seg *pseg, void *arg)
printk(XENLOG_WARNING "Dom%d owning %04x:%02x:%02x.%u?\n",
pdev->domain->domain_id, pseg->nr, bus,
PCI_SLOT(devfn), PCI_FUNC(devfn));
+
+ if ( iommu_verbose )
+ {
+ spin_unlock(&pcidevs_lock);
+ process_pending_softirqs();
+ spin_lock(&pcidevs_lock);
+ }
+ }
+
+ if ( !iommu_verbose )
+ {
+ spin_unlock(&pcidevs_lock);
+ process_pending_softirqs();
+ spin_lock(&pcidevs_lock);
}
}
@@ -938,6 +1066,106 @@ void __init setup_dom0_pci_devices(
spin_unlock(&pcidevs_lock);
}
+#ifdef CONFIG_ACPI
+#include <acpi/acpi.h>
+#include <acpi/apei.h>
+
+static int hest_match_pci(const struct acpi_hest_aer_common *p,
+ const struct pci_dev *pdev)
+{
+ return ACPI_HEST_SEGMENT(p->bus) == pdev->seg &&
+ ACPI_HEST_BUS(p->bus) == pdev->bus &&
+ p->device == PCI_SLOT(pdev->devfn) &&
+ p->function == PCI_FUNC(pdev->devfn);
+}
+
+static bool_t hest_match_type(const struct acpi_hest_header *hest_hdr,
+ const struct pci_dev *pdev)
+{
+ unsigned int pos = pci_find_cap_offset(pdev->seg, pdev->bus,
+ PCI_SLOT(pdev->devfn),
+ PCI_FUNC(pdev->devfn),
+ PCI_CAP_ID_EXP);
+ u8 pcie = MASK_EXTR(pci_conf_read16(pdev->seg, pdev->bus,
+ PCI_SLOT(pdev->devfn),
+ PCI_FUNC(pdev->devfn),
+ pos + PCI_EXP_FLAGS),
+ PCI_EXP_FLAGS_TYPE);
+
+ switch ( hest_hdr->type )
+ {
+ case ACPI_HEST_TYPE_AER_ROOT_PORT:
+ return pcie == PCI_EXP_TYPE_ROOT_PORT;
+ case ACPI_HEST_TYPE_AER_ENDPOINT:
+ return pcie == PCI_EXP_TYPE_ENDPOINT;
+ case ACPI_HEST_TYPE_AER_BRIDGE:
+ return pci_conf_read16(pdev->seg, pdev->bus, PCI_SLOT(pdev->devfn),
+ PCI_FUNC(pdev->devfn), PCI_CLASS_DEVICE) ==
+ PCI_CLASS_BRIDGE_PCI;
+ }
+
+ return 0;
+}
+
+struct aer_hest_parse_info {
+ const struct pci_dev *pdev;
+ bool_t firmware_first;
+};
+
+static bool_t hest_source_is_pcie_aer(const struct acpi_hest_header *hest_hdr)
+{
+ if ( hest_hdr->type == ACPI_HEST_TYPE_AER_ROOT_PORT ||
+ hest_hdr->type == ACPI_HEST_TYPE_AER_ENDPOINT ||
+ hest_hdr->type == ACPI_HEST_TYPE_AER_BRIDGE )
+ return 1;
+ return 0;
+}
+
+static int aer_hest_parse(const struct acpi_hest_header *hest_hdr, void *data)
+{
+ struct aer_hest_parse_info *info = data;
+ const struct acpi_hest_aer_common *p;
+ bool_t ff;
+
+ if ( !hest_source_is_pcie_aer(hest_hdr) )
+ return 0;
+
+ p = (const struct acpi_hest_aer_common *)(hest_hdr + 1);
+ ff = !!(p->flags & ACPI_HEST_FIRMWARE_FIRST);
+
+ /*
+ * If no specific device is supplied, determine whether
+ * FIRMWARE_FIRST is set for *any* PCIe device.
+ */
+ if ( !info->pdev )
+ {
+ info->firmware_first |= ff;
+ return 0;
+ }
+
+ /* Otherwise, check the specific device */
+ if ( p->flags & ACPI_HEST_GLOBAL ?
+ hest_match_type(hest_hdr, info->pdev) :
+ hest_match_pci(p, info->pdev) )
+ {
+ info->firmware_first = ff;
+ return 1;
+ }
+
+ return 0;
+}
+
+bool_t pcie_aer_get_firmware_first(const struct pci_dev *pdev)
+{
+ struct aer_hest_parse_info info = { .pdev = pdev };
+
+ return pci_find_cap_offset(pdev->seg, pdev->bus, PCI_SLOT(pdev->devfn),
+ PCI_FUNC(pdev->devfn), PCI_CAP_ID_EXP) &&
+ apei_hest_parse(aer_hest_parse, &info) >= 0 &&
+ info.firmware_first;
+}
+#endif
+
static int _dump_pci_devices(struct pci_seg *pseg, void *arg)
{
struct pci_dev *pdev;
diff --git a/xen/drivers/passthrough/vtd/dmar.c b/xen/drivers/passthrough/vtd/dmar.c
index cb998e2..1152c3a 100644
--- a/xen/drivers/passthrough/vtd/dmar.c
+++ b/xen/drivers/passthrough/vtd/dmar.c
@@ -580,6 +580,16 @@ acpi_parse_one_rmrr(struct acpi_dmar_header *header)
if ( (ret = acpi_dmar_check_length(header, sizeof(*rmrr))) != 0 )
return ret;
+ list_for_each_entry(rmrru, &acpi_rmrr_units, list)
+ if ( base_addr <= rmrru->end_address && rmrru->base_address <= end_addr )
+ {
+ printk(XENLOG_ERR VTDPREFIX
+ "Overlapping RMRRs [%"PRIx64",%"PRIx64"] and [%"PRIx64",%"PRIx64"]\n",
+ rmrru->base_address, rmrru->end_address,
+ base_addr, end_addr);
+ return -EEXIST;
+ }
+
/* This check is here simply to detect when RMRR values are
* not properly represented in the system memory map and
* inform the user
diff --git a/xen/drivers/passthrough/vtd/extern.h b/xen/drivers/passthrough/vtd/extern.h
index 14cd90e..afe7faf 100644
--- a/xen/drivers/passthrough/vtd/extern.h
+++ b/xen/drivers/passthrough/vtd/extern.h
@@ -99,7 +99,7 @@ void platform_quirks_init(void);
void vtd_ops_preamble_quirk(struct iommu* iommu);
void vtd_ops_postamble_quirk(struct iommu* iommu);
void me_wifi_quirk(struct domain *domain, u8 bus, u8 devfn, int map);
-void pci_vtd_quirk(struct pci_dev *pdev);
+void pci_vtd_quirk(const struct pci_dev *);
int platform_supports_intremap(void);
int platform_supports_x2apic(void);
diff --git a/xen/drivers/passthrough/vtd/iommu.c b/xen/drivers/passthrough/vtd/iommu.c
index 5f10034..e543c08 100644
--- a/xen/drivers/passthrough/vtd/iommu.c
+++ b/xen/drivers/passthrough/vtd/iommu.c
@@ -31,7 +31,6 @@
#include <xen/pci.h>
#include <xen/pci_regs.h>
#include <xen/keyhandler.h>
-#include <xen/softirq.h>
#include <asm/msi.h>
#include <asm/irq.h>
#include <asm/hvm/vmx/vmx.h>
@@ -43,6 +42,12 @@
#include "vtd.h"
#include "../ats.h"
+struct mapped_rmrr {
+ struct list_head list;
+ u64 base, end;
+ unsigned int count;
+};
+
/* Possible unfiltered LAPIC/MSI messages from untrusted sources? */
bool_t __read_mostly untrusted_msi;
@@ -620,7 +625,6 @@ static void dma_pte_clear_one(struct domain *domain, u64 addr)
struct hvm_iommu *hd = domain_hvm_iommu(domain);
struct dma_pte *page = NULL, *pte = NULL;
u64 pg_maddr;
- struct mapped_rmrr *mrmrr;
spin_lock(&hd->mapping_lock);
/* get last level pte */
@@ -649,21 +653,6 @@ static void dma_pte_clear_one(struct domain *domain, u64 addr)
__intel_iommu_iotlb_flush(domain, addr >> PAGE_SHIFT_4K, 1, 1);
unmap_vtd_domain_page(page);
-
- /* if the cleared address is between mapped RMRR region,
- * remove the mapped RMRR
- */
- spin_lock(&hd->mapping_lock);
- list_for_each_entry ( mrmrr, &hd->mapped_rmrrs, list )
- {
- if ( addr >= mrmrr->base && addr <= mrmrr->end )
- {
- list_del(&mrmrr->list);
- xfree(mrmrr);
- break;
- }
- }
- spin_unlock(&hd->mapping_lock);
}
static void iommu_free_pagetable(u64 pt_maddr, int level)
@@ -1453,7 +1442,7 @@ static int domain_context_mapping(
ret = domain_context_mapping_one(domain, drhd->iommu, bus, devfn,
pdev);
if ( !ret && devfn == pdev->devfn && ats_device(pdev, drhd) > 0 )
- enable_ats_device(seg, bus, devfn);
+ enable_ats_device(seg, bus, devfn, drhd->iommu);
break;
@@ -1494,8 +1483,8 @@ static int domain_context_mapping(
break;
}
- if ( iommu_verbose )
- process_pending_softirqs();
+ if ( !ret && devfn == pdev->devfn )
+ pci_vtd_quirk(pdev);
return ret;
}
@@ -1704,10 +1693,17 @@ static int reassign_device_ownership(
void iommu_domain_teardown(struct domain *d)
{
struct hvm_iommu *hd = domain_hvm_iommu(d);
+ struct mapped_rmrr *mrmrr, *tmp;
if ( list_empty(&acpi_drhd_units) )
return;
+ list_for_each_entry_safe ( mrmrr, tmp, &hd->mapped_rmrrs, list )
+ {
+ list_del(&mrmrr->list);
+ xfree(mrmrr);
+ }
+
if ( iommu_use_hap_pt(d) )
return;
@@ -1852,14 +1848,17 @@ static int rmrr_identity_mapping(struct domain *d,
ASSERT(rmrr->base_address < rmrr->end_address);
/*
- * No need to acquire hd->mapping_lock, as the only theoretical race is
- * with the insertion below (impossible due to holding pcidevs_lock).
+ * No need to acquire hd->mapping_lock: Both insertion and removal
+ * get done while holding pcidevs_lock.
*/
list_for_each_entry( mrmrr, &hd->mapped_rmrrs, list )
{
if ( mrmrr->base == rmrr->base_address &&
mrmrr->end == rmrr->end_address )
+ {
+ ++mrmrr->count;
return 0;
+ }
}
base = rmrr->base_address & PAGE_MASK_4K;
@@ -1880,9 +1879,8 @@ static int rmrr_identity_mapping(struct domain *d,
return -ENOMEM;
mrmrr->base = rmrr->base_address;
mrmrr->end = rmrr->end_address;
- spin_lock(&hd->mapping_lock);
+ mrmrr->count = 1;
list_add_tail(&mrmrr->list, &hd->mapped_rmrrs);
- spin_unlock(&hd->mapping_lock);
return 0;
}
@@ -1927,10 +1925,12 @@ static int intel_iommu_enable_device(struct pci_dev *pdev)
struct acpi_drhd_unit *drhd = acpi_find_matched_drhd_unit(pdev);
int ret = drhd ? ats_device(pdev, drhd) : -ENODEV;
+ pci_vtd_quirk(pdev);
+
if ( ret <= 0 )
return ret;
- ret = enable_ats_device(pdev->seg, pdev->bus, pdev->devfn);
+ ret = enable_ats_device(pdev->seg, pdev->bus, pdev->devfn, drhd->iommu);
return ret >= 0 ? 0 : ret;
}
@@ -1944,17 +1944,52 @@ static int intel_iommu_remove_device(u8 devfn, struct pci_dev *pdev)
if ( !pdev->domain )
return -EINVAL;
- /* If the device belongs to dom0, and it has RMRR, don't remove it
- * from dom0, because BIOS may use RMRR at booting time.
- */
- if ( pdev->domain->domain_id == 0 )
+ for_each_rmrr_device ( rmrr, bdf, i )
{
- for_each_rmrr_device ( rmrr, bdf, i )
+ struct hvm_iommu *hd;
+ struct mapped_rmrr *mrmrr, *tmp;
+
+ if ( rmrr->segment != pdev->seg ||
+ PCI_BUS(bdf) != pdev->bus ||
+ PCI_DEVFN2(bdf) != devfn )
+ continue;
+
+ /*
+ * If the device belongs to dom0, and it has RMRR, don't remove
+ * it from dom0, because BIOS may use RMRR at booting time.
+ */
+ if ( is_hardware_domain(pdev->domain) )
+ return 0;
+
+ hd = domain_hvm_iommu(pdev->domain);
+
+ /*
+ * No need to acquire hd->mapping_lock: Both insertion and removal
+ * get done while holding pcidevs_lock.
+ */
+ ASSERT(spin_is_locked(&pcidevs_lock));
+ list_for_each_entry_safe ( mrmrr, tmp, &hd->mapped_rmrrs, list )
{
- if ( rmrr->segment == pdev->seg &&
- PCI_BUS(bdf) == pdev->bus &&
- PCI_DEVFN2(bdf) == devfn )
- return 0;
+ unsigned long base_pfn, end_pfn;
+
+ if ( rmrr->base_address != mrmrr->base ||
+ rmrr->end_address != mrmrr->end )
+ continue;
+
+ if ( --mrmrr->count )
+ break;
+
+ base_pfn = (mrmrr->base & PAGE_MASK_4K) >> PAGE_SHIFT_4K;
+ end_pfn = PAGE_ALIGN_4K(mrmrr->end) >> PAGE_SHIFT_4K;
+ while ( base_pfn < end_pfn )
+ {
+ if ( intel_iommu_unmap_page(pdev->domain, base_pfn) )
+ return -ENXIO;
+ base_pfn++;
+ }
+
+ list_del(&mrmrr->list);
+ xfree(mrmrr);
}
}
@@ -1963,12 +1998,7 @@ static int intel_iommu_remove_device(u8 devfn, struct pci_dev *pdev)
static int __init setup_dom0_device(u8 devfn, struct pci_dev *pdev)
{
- int err;
-
- err = domain_context_mapping(pdev->domain, devfn, pdev);
- if ( !err && devfn == pdev->devfn )
- pci_vtd_quirk(pdev);
- return err;
+ return domain_context_mapping(pdev->domain, devfn, pdev);
}
void clear_fault_bits(struct iommu *iommu)
diff --git a/xen/drivers/passthrough/vtd/qinval.c b/xen/drivers/passthrough/vtd/qinval.c
index ef5de99..fe29e82 100644
--- a/xen/drivers/passthrough/vtd/qinval.c
+++ b/xen/drivers/passthrough/vtd/qinval.c
@@ -196,7 +196,7 @@ static int queue_invalidate_wait(struct iommu *iommu,
u8 iflag, u8 sw, u8 fn)
{
s_time_t start_time;
- u32 poll_slot = QINVAL_STAT_INIT;
+ volatile u32 poll_slot = QINVAL_STAT_INIT;
int index = -1;
int ret = -1;
unsigned long flags;
diff --git a/xen/drivers/passthrough/vtd/quirks.c b/xen/drivers/passthrough/vtd/quirks.c
index 7f6c3a7..647723d 100644
--- a/xen/drivers/passthrough/vtd/quirks.c
+++ b/xen/drivers/passthrough/vtd/quirks.c
@@ -27,6 +27,7 @@
#include <xen/softirq.h>
#include <xen/time.h>
#include <xen/pci.h>
+#include <xen/pci_ids.h>
#include <xen/pci_regs.h>
#include <xen/keyhandler.h>
#include <asm/msi.h>
@@ -378,24 +379,127 @@ void me_wifi_quirk(struct domain *domain, u8 bus, u8 devfn, int map)
}
}
-/*
- * Mask reporting Intel VT-d faults to IOH core logic:
- * - Some platform escalates VT-d faults to platform errors
- * - This can cause system failure upon non-fatal VT-d faults
- * - Potential security issue if malicious guest trigger VT-d faults
- */
-void __init pci_vtd_quirk(struct pci_dev *pdev)
+void pci_vtd_quirk(const struct pci_dev *pdev)
{
int seg = pdev->seg;
int bus = pdev->bus;
int dev = PCI_SLOT(pdev->devfn);
int func = PCI_FUNC(pdev->devfn);
- int id, val;
+ int pos;
+ bool_t ff;
+ u32 val, val2;
+ u64 bar;
+ paddr_t pa;
+ const char *action;
+
+ if ( pci_conf_read16(seg, bus, dev, func, PCI_VENDOR_ID) !=
+ PCI_VENDOR_ID_INTEL )
+ return;
- id = pci_conf_read32(seg, bus, dev, func, 0);
- if ( id == 0x342e8086 || id == 0x3c288086 )
+ switch ( pci_conf_read16(seg, bus, dev, func, PCI_DEVICE_ID) )
{
+ /*
+ * Mask reporting Intel VT-d faults to IOH core logic:
+ * - Some platform escalates VT-d faults to platform errors.
+ * - This can cause system failure upon non-fatal VT-d faults.
+ * - Potential security issue if malicious guest trigger VT-d faults.
+ */
+ case 0x0e28: /* Xeon-E5v2 (IvyBridge) */
+ case 0x342e: /* Tylersburg chipset (Nehalem / Westmere systems) */
+ case 0x3728: /* Xeon C5500/C3500 (JasperForest) */
+ case 0x3c28: /* Sandybridge */
val = pci_conf_read32(seg, bus, dev, func, 0x1AC);
pci_conf_write32(seg, bus, dev, func, 0x1AC, val | (1 << 31));
+ printk(XENLOG_INFO "Masked VT-d error signaling on %04x:%02x:%02x.%u\n",
+ seg, bus, dev, func);
+ break;
+
+ /* Tylersburg (EP)/Boxboro (MP) chipsets (NHM-EP/EX, WSM-EP/EX) */
+ case 0x3400 ... 0x3407: /* host bridges */
+ case 0x3408 ... 0x3411: case 0x3420 ... 0x3421: /* root ports */
+ /* JasperForest (Intel Xeon Processor C5500/C3500 */
+ case 0x3700 ... 0x370f: /* host bridges */
+ case 0x3720 ... 0x3724: /* root ports */
+ /* Sandybridge-EP (Romley) */
+ case 0x3c00: /* host bridge */
+ case 0x3c01 ... 0x3c0b: /* root ports */
+ pos = pci_find_ext_capability(seg, bus, pdev->devfn,
+ PCI_EXT_CAP_ID_ERR);
+ if ( !pos )
+ {
+ pos = pci_find_ext_capability(seg, bus, pdev->devfn,
+ PCI_EXT_CAP_ID_VNDR);
+ while ( pos )
+ {
+ val = pci_conf_read32(seg, bus, dev, func, pos + PCI_VNDR_HEADER);
+ if ( PCI_VNDR_HEADER_ID(val) == 4 && PCI_VNDR_HEADER_REV(val) == 1 )
+ {
+ pos += PCI_VNDR_HEADER;
+ break;
+ }
+ pos = pci_find_next_ext_capability(seg, bus, pdev->devfn, pos,
+ PCI_EXT_CAP_ID_VNDR);
+ }
+ ff = 0;
+ }
+ else
+ ff = pcie_aer_get_firmware_first(pdev);
+ if ( !pos )
+ {
+ printk(XENLOG_WARNING "%04x:%02x:%02x.%u without AER capability?\n",
+ seg, bus, dev, func);
+ break;
+ }
+
+ val = pci_conf_read32(seg, bus, dev, func, pos + PCI_ERR_UNCOR_MASK);
+ val2 = pci_conf_read32(seg, bus, dev, func, pos + PCI_ERR_COR_MASK);
+ if ( (val & PCI_ERR_UNC_UNSUP) && (val2 & PCI_ERR_COR_ADV_NFAT) )
+ action = "Found masked";
+ else if ( !ff )
+ {
+ pci_conf_write32(seg, bus, dev, func, pos + PCI_ERR_UNCOR_MASK,
+ val | PCI_ERR_UNC_UNSUP);
+ pci_conf_write32(seg, bus, dev, func, pos + PCI_ERR_COR_MASK,
+ val2 | PCI_ERR_COR_ADV_NFAT);
+ action = "Masked";
+ }
+ else
+ action = "Must not mask";
+
+ /* XPUNCERRMSK Send Completion with Unsupported Request */
+ val = pci_conf_read32(seg, bus, dev, func, 0x20c);
+ pci_conf_write32(seg, bus, dev, func, 0x20c, val | (1 << 4));
+
+ printk(XENLOG_INFO "%s UR signaling on %04x:%02x:%02x.%u\n",
+ action, seg, bus, dev, func);
+ break;
+
+ case 0x100: case 0x104: case 0x108: /* Sandybridge */
+ case 0x150: case 0x154: case 0x158: /* Ivybridge */
+ case 0xa04: /* Haswell ULT */
+ case 0xc00: case 0xc04: case 0xc08: /* Haswell */
+ bar = pci_conf_read32(seg, bus, dev, func, 0x6c);
+ bar = (bar << 32) | pci_conf_read32(seg, bus, dev, func, 0x68);
+ pa = bar & 0x7ffffff000UL; /* bits 12...38 */
+ if ( (bar & 1) && pa &&
+ page_is_ram_type(paddr_to_pfn(pa), RAM_TYPE_RESERVED) )
+ {
+ u32 __iomem *va = ioremap(pa, PAGE_SIZE);
+
+ if ( va )
+ {
+ __set_bit(0x1c8 * 8 + 20, va);
+ iounmap(va);
+ printk(XENLOG_INFO "Masked UR signaling on %04x:%02x:%02x.%u\n",
+ seg, bus, dev, func);
+ }
+ else
+ printk(XENLOG_ERR "Could not map %"PRIpaddr" for %04x:%02x:%02x.%u\n",
+ pa, seg, bus, dev, func);
+ }
+ else
+ printk(XENLOG_WARNING "Bogus DMIBAR %#"PRIx64" on %04x:%02x:%02x.%u\n",
+ bar, seg, bus, dev, func);
+ break;
}
}
diff --git a/xen/drivers/passthrough/vtd/x86/ats.c b/xen/drivers/passthrough/vtd/x86/ats.c
index f3b8c2d..6b0632b 100644
--- a/xen/drivers/passthrough/vtd/x86/ats.c
+++ b/xen/drivers/passthrough/vtd/x86/ats.c
@@ -110,17 +110,23 @@ int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
u64 addr, unsigned int size_order, u64 type)
{
struct pci_ats_dev *pdev;
- int sbit, ret = 0;
- u16 sid;
+ int ret = 0;
if ( !ecap_dev_iotlb(iommu->ecap) )
return ret;
list_for_each_entry( pdev, &ats_devices, list )
{
- sid = (pdev->bus << 8) | pdev->devfn;
+ u16 sid = PCI_BDF2(pdev->bus, pdev->devfn);
+ bool_t sbit;
+ int rc = 0;
- switch ( type ) {
+ /* Only invalidate devices that belong to this IOMMU */
+ if ( pdev->iommu != iommu )
+ continue;
+
+ switch ( type )
+ {
case DMA_TLB_DSI_FLUSH:
if ( !device_in_domain(iommu, pdev, did) )
break;
@@ -129,32 +135,37 @@ int dev_invalidate_iotlb(struct iommu *iommu, u16 did,
/* invalidate all translations: sbit=1,bit_63=0,bit[62:12]=1 */
sbit = 1;
addr = (~0 << PAGE_SHIFT_4K) & 0x7FFFFFFFFFFFFFFF;
- ret |= qinval_device_iotlb(iommu, pdev->ats_queue_depth,
- sid, sbit, addr);
+ rc = qinval_device_iotlb(iommu, pdev->ats_queue_depth,
+ sid, sbit, addr);
break;
case DMA_TLB_PSI_FLUSH:
if ( !device_in_domain(iommu, pdev, did) )
break;
- addr &= ~0 << (PAGE_SHIFT + size_order);
-
/* if size <= 4K, set sbit = 0, else set sbit = 1 */
sbit = size_order ? 1 : 0;
/* clear lower bits */
- addr &= (~0 << (PAGE_SHIFT + size_order));
+ addr &= ~0 << PAGE_SHIFT_4K;
/* if sbit == 1, zero out size_order bit and set lower bits to 1 */
if ( sbit )
- addr &= (~0 & ~(1 << (PAGE_SHIFT + size_order)));
+ {
+ addr &= ~((u64)PAGE_SIZE_4K << (size_order - 1));
+ addr |= (((u64)1 << (size_order - 1)) - 1) << PAGE_SHIFT_4K;
+ }
- ret |= qinval_device_iotlb(iommu, pdev->ats_queue_depth,
- sid, sbit, addr);
+ rc = qinval_device_iotlb(iommu, pdev->ats_queue_depth,
+ sid, sbit, addr);
break;
default:
dprintk(XENLOG_WARNING VTDPREFIX, "invalid vt-d flush type\n");
- break;
+ return -EOPNOTSUPP;
}
+
+ if ( !ret )
+ ret = rc;
}
+
return ret;
}
diff --git a/xen/drivers/passthrough/x86/ats.c b/xen/drivers/passthrough/x86/ats.c
index bb7ee9a..1e3e03a 100644
--- a/xen/drivers/passthrough/x86/ats.c
+++ b/xen/drivers/passthrough/x86/ats.c
@@ -23,7 +23,7 @@ LIST_HEAD(ats_devices);
bool_t __read_mostly ats_enabled = 1;
boolean_param("ats", ats_enabled);
-int enable_ats_device(int seg, int bus, int devfn)
+int enable_ats_device(int seg, int bus, int devfn, const void *iommu)
{
struct pci_ats_dev *pdev = NULL;
u32 value;
@@ -66,6 +66,7 @@ int enable_ats_device(int seg, int bus, int devfn)
pdev->seg = seg;
pdev->bus = bus;
pdev->devfn = devfn;
+ pdev->iommu = iommu;
value = pci_conf_read16(seg, bus, PCI_SLOT(devfn),
PCI_FUNC(devfn), pos + ATS_REG_CAP);
pdev->ats_queue_depth = value & ATS_QUEUE_DEPTH_MASK ?:
diff --git a/xen/drivers/pci/pci.c b/xen/drivers/pci/pci.c
index 25dc5f1..ca07ed0 100644
--- a/xen/drivers/pci/pci.c
+++ b/xen/drivers/pci/pci.c
@@ -66,23 +66,33 @@ int pci_find_next_cap(u16 seg, u8 bus, unsigned int devfn, u8 pos, int cap)
/**
* pci_find_ext_capability - Find an extended capability
- * @dev: PCI device to query
+ * @seg/@bus/@devfn: PCI device to query
* @cap: capability code
*
* Returns the address of the requested extended capability structure
* within the device's PCI configuration space or 0 if the device does
- * not support it. Possible values for @cap:
- *
- * %PCI_EXT_CAP_ID_ERR Advanced Error Reporting
- * %PCI_EXT_CAP_ID_VC Virtual Channel
- * %PCI_EXT_CAP_ID_DSN Device Serial Number
- * %PCI_EXT_CAP_ID_PWR Power Budgeting
+ * not support it.
*/
int pci_find_ext_capability(int seg, int bus, int devfn, int cap)
{
+ return pci_find_next_ext_capability(seg, bus, devfn, 0, cap);
+}
+
+/**
+ * pci_find_next_ext_capability - Find another extended capability
+ * @seg/@bus/@devfn: PCI device to query
+ * @pos: starting position
+ * @cap: capability code
+ *
+ * Returns the address of the requested extended capability structure
+ * within the device's PCI configuration space or 0 if the device does
+ * not support it.
+ */
+int pci_find_next_ext_capability(int seg, int bus, int devfn, int start, int cap)
+{
u32 header;
int ttl = 480; /* 3840 bytes, minimum 8 bytes per capability */
- int pos = 0x100;
+ int pos = max(start, 0x100);
header = pci_conf_read32(seg, bus, PCI_SLOT(devfn), PCI_FUNC(devfn), pos);
@@ -92,9 +102,10 @@ int pci_find_ext_capability(int seg, int bus, int devfn, int cap)
*/
if ( (header == 0) || (header == -1) )
return 0;
+ ASSERT(start != pos || PCI_EXT_CAP_ID(header) == cap);
while ( ttl-- > 0 ) {
- if ( PCI_EXT_CAP_ID(header) == cap )
+ if ( PCI_EXT_CAP_ID(header) == cap && pos != start )
return pos;
pos = PCI_EXT_CAP_NEXT(header);
if ( pos < 0x100 )
diff --git a/xen/include/acpi/actbl1.h b/xen/include/acpi/actbl1.h
index 492be4e..9311e3a 100644
--- a/xen/include/acpi/actbl1.h
+++ b/xen/include/acpi/actbl1.h
@@ -445,6 +445,14 @@ struct acpi_hest_aer_common {
#define ACPI_HEST_FIRMWARE_FIRST (1)
#define ACPI_HEST_GLOBAL (1<<1)
+/*
+ * Macros to access the bus/segment numbers in Bus field above:
+ * Bus number is encoded in bits 7:0
+ * Segment number is encoded in bits 23:8
+ */
+#define ACPI_HEST_BUS(bus) ((bus) & 0xFF)
+#define ACPI_HEST_SEGMENT(bus) (((bus) >> 8) & 0xFFFF)
+
/* Hardware Error Notification */
struct acpi_hest_notify {
diff --git a/xen/include/acpi/apei.h b/xen/include/acpi/apei.h
index 162f616..087bbef 100644
--- a/xen/include/acpi/apei.h
+++ b/xen/include/acpi/apei.h
@@ -12,6 +12,9 @@
#define FIX_APEI_RANGE_MAX 64
+typedef int (*apei_hest_func_t)(const struct acpi_hest_header *, void *);
+int apei_hest_parse(apei_hest_func_t, void *);
+
int erst_write(const struct cper_record_header *record);
size_t erst_get_record_count(void);
int erst_get_next_record_id(u64 *record_id);
diff --git a/xen/include/asm-arm/arm32/page.h b/xen/include/asm-arm/arm32/page.h
index b8221ca..80d5c36 100644
--- a/xen/include/asm-arm/arm32/page.h
+++ b/xen/include/asm-arm/arm32/page.h
@@ -90,11 +90,14 @@ static inline uint64_t __va_to_par(vaddr_t va)
}
/* Ask the MMU to translate a Guest VA for us */
-static inline uint64_t gva_to_ma_par(vaddr_t va)
+static inline uint64_t gva_to_ma_par(vaddr_t va, unsigned int flags)
{
uint64_t par, tmp;
tmp = READ_CP64(PAR);
- WRITE_CP32(va, ATS12NSOPR);
+ if ( (flags & GV2M_WRITE) == GV2M_WRITE )
+ WRITE_CP32(va, ATS12NSOPW);
+ else
+ WRITE_CP32(va, ATS12NSOPR);
isb(); /* Ensure result is available. */
par = READ_CP64(PAR);
WRITE_CP64(tmp, PAR);
diff --git a/xen/include/asm-arm/arm64/page.h b/xen/include/asm-arm/arm64/page.h
index 3352821..3922d87 100644
--- a/xen/include/asm-arm/arm64/page.h
+++ b/xen/include/asm-arm/arm64/page.h
@@ -83,11 +83,14 @@ static inline uint64_t __va_to_par(vaddr_t va)
}
/* Ask the MMU to translate a Guest VA for us */
-static inline uint64_t gva_to_ma_par(vaddr_t va)
+static inline uint64_t gva_to_ma_par(vaddr_t va, unsigned int flags)
{
uint64_t par, tmp = READ_SYSREG64(PAR_EL1);
- asm volatile ("at s12e1r, %0;" : : "r" (va));
+ if ( (flags & GV2M_WRITE) == GV2M_WRITE )
+ asm volatile ("at s12e1r, %0;" : : "r" (va));
+ else
+ asm volatile ("at s12e1w, %0;" : : "r" (va));
isb();
par = READ_SYSREG64(PAR_EL1);
WRITE_SYSREG64(tmp, PAR_EL1);
diff --git a/xen/include/asm-arm/arm64/vfp.h b/xen/include/asm-arm/arm64/vfp.h
index 373f156..6ab5d36 100644
--- a/xen/include/asm-arm/arm64/vfp.h
+++ b/xen/include/asm-arm/arm64/vfp.h
@@ -1,9 +1,12 @@
#ifndef _ARM_ARM64_VFP_H
#define _ARM_ARM64_VFP_H
+/* ARM64 VFP instruction requires fpregs address to be 128-byte aligned */
+#define __vfp_aligned __attribute__((aligned(16)))
+
struct vfp_state
{
- uint64_t fpregs[64];
+ uint64_t fpregs[64] __vfp_aligned;
uint32_t fpcr;
uint32_t fpexc32_el2;
uint32_t fpsr;
diff --git a/xen/include/asm-arm/bitops.h b/xen/include/asm-arm/bitops.h
index 0a7caee..25f96c8 100644
--- a/xen/include/asm-arm/bitops.h
+++ b/xen/include/asm-arm/bitops.h
@@ -18,13 +18,14 @@
#define __set_bit(n,p) set_bit(n,p)
#define __clear_bit(n,p) clear_bit(n,p)
+#define BITS_PER_WORD 32
#define BIT(nr) (1UL << (nr))
-#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_LONG))
-#define BIT_WORD(nr) ((nr) / BITS_PER_LONG)
+#define BIT_MASK(nr) (1UL << ((nr) % BITS_PER_WORD))
+#define BIT_WORD(nr) ((nr) / BITS_PER_WORD)
#define BITS_PER_BYTE 8
-#define ADDR (*(volatile long *) addr)
-#define CONST_ADDR (*(const volatile long *) addr)
+#define ADDR (*(volatile int *) addr)
+#define CONST_ADDR (*(const volatile int *) addr)
#if defined(CONFIG_ARM_32)
# include <asm/arm32/bitops.h>
@@ -45,10 +46,10 @@
*/
static inline int __test_and_set_bit(int nr, volatile void *addr)
{
- unsigned long mask = BIT_MASK(nr);
- volatile unsigned long *p =
- ((volatile unsigned long *)addr) + BIT_WORD(nr);
- unsigned long old = *p;
+ unsigned int mask = BIT_MASK(nr);
+ volatile unsigned int *p =
+ ((volatile unsigned int *)addr) + BIT_WORD(nr);
+ unsigned int old = *p;
*p = old | mask;
return (old & mask) != 0;
@@ -65,10 +66,10 @@ static inline int __test_and_set_bit(int nr, volatile void *addr)
*/
static inline int __test_and_clear_bit(int nr, volatile void *addr)
{
- unsigned long mask = BIT_MASK(nr);
- volatile unsigned long *p =
- ((volatile unsigned long *)addr) + BIT_WORD(nr);
- unsigned long old = *p;
+ unsigned int mask = BIT_MASK(nr);
+ volatile unsigned int *p =
+ ((volatile unsigned int *)addr) + BIT_WORD(nr);
+ unsigned int old = *p;
*p = old & ~mask;
return (old & mask) != 0;
@@ -78,10 +79,10 @@ static inline int __test_and_clear_bit(int nr, volatile void *addr)
static inline int __test_and_change_bit(int nr,
volatile void *addr)
{
- unsigned long mask = BIT_MASK(nr);
- volatile unsigned long *p =
- ((volatile unsigned long *)addr) + BIT_WORD(nr);
- unsigned long old = *p;
+ unsigned int mask = BIT_MASK(nr);
+ volatile unsigned int *p =
+ ((volatile unsigned int *)addr) + BIT_WORD(nr);
+ unsigned int old = *p;
*p = old ^ mask;
return (old & mask) != 0;
@@ -94,8 +95,8 @@ static inline int __test_and_change_bit(int nr,
*/
static inline int test_bit(int nr, const volatile void *addr)
{
- const volatile unsigned long *p = (const volatile unsigned long *)addr;
- return 1UL & (p[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
+ const volatile unsigned int *p = (const volatile unsigned int *)addr;
+ return 1UL & (p[BIT_WORD(nr)] >> (nr & (BITS_PER_WORD-1)));
}
static inline int constant_fls(int x)
diff --git a/xen/include/asm-arm/cpregs.h b/xen/include/asm-arm/cpregs.h
index 508467a..f1100c8 100644
--- a/xen/include/asm-arm/cpregs.h
+++ b/xen/include/asm-arm/cpregs.h
@@ -71,6 +71,20 @@
/* Coprocessor 14 */
+/* CP14 0: Debug Register interface */
+#define DBGDIDR p14,0,c0,c0,0 /* Debug ID Register */
+#define DBGDSCRINT p14,0,c0,c1,0 /* Debug Status and Control Internal */
+#define DBGDSCREXT p14,0,c0,c2,2 /* Debug Status and Control External */
+#define DBGVCR p14,0,c0,c7,0 /* Vector Catch */
+#define DBGBVR0 p14,0,c0,c0,4 /* Breakpoint Value 0 */
+#define DBGBCR0 p14,0,c0,c0,5 /* Breakpoint Control 0 */
+#define DBGWVR0 p14,0,c0,c0,6 /* Watchpoint Value 0 */
+#define DBGWCR0 p14,0,c0,c0,7 /* Watchpoint Control 0 */
+#define DBGBVR1 p14,0,c0,c1,4 /* Breakpoint Value 1 */
+#define DBGBCR1 p14,0,c0,c1,5 /* Breakpoint Control 1 */
+#define DBGOSLAR p14,0,c1,c0,4 /* OS Lock Access */
+#define DBGOSDLR p14,0,c1,c3,4 /* OS Double Lock */
+
/* CP14 CR0: */
#define TEECR p14,6,c0,c0,0 /* ThumbEE Configuration Register */
@@ -115,6 +129,9 @@
#define NSACR p15,0,c1,c1,2 /* Non-Secure Access Control Register */
#define HSCTLR p15,4,c1,c0,0 /* Hyp. System Control Register */
#define HCR p15,4,c1,c1,0 /* Hyp. Configuration Register */
+#define HDCR p15,4,c1,c1,1 /* Hyp. Debug Configuration Register */
+#define HCPTR p15,4,c1,c1,2 /* Hyp. Coprocessor Trap Register */
+#define HSTR p15,4,c1,c1,3 /* Hyp. System Trap Register */
/* CP15 CR2: Translation Table Base and Control Registers */
#define TTBCR p15,0,c2,c0,2 /* Translatation Table Base Control Register */
@@ -195,7 +212,22 @@
#define TLBIMVAH p15,4,c8,c7,1 /* Invalidate Unified Hyp. TLB by MVA */
#define TLBIALLNSNH p15,4,c8,c7,4 /* Invalidate Entire Non-Secure Non-Hyp. Unified TLB */
-/* CP15 CR9: */
+/* CP15 CR9: Performance monitors */
+#define PMCR p15,0,c9,c12,0 /* Perf. Mon. Control Register */
+#define PMCNTENSET p15,0,c9,c12,1 /* Perf. Mon. Count Enable Set register */
+#define PMCNTENCLR p15,0,c9,c12,2 /* Perf. Mon. Count Enable Clear register */
+#define PMOVSR p15,0,c9,c12,3 /* Perf. Mon. Overflow Flag Status Register */
+#define PMSWINC p15,0,c9,c12,4 /* Perf. Mon. Software Increment register */
+#define PMSELR p15,0,c9,c12,5 /* Perf. Mon. Event Counter Selection Register */
+#define PMCEID0 p15,0,c9,c12,6 /* Perf. Mon. Common Event Identification register 0 */
+#define PMCEID1 p15,0,c9,c12,7 /* Perf. Mon. Common Event Identification register 1 */
+#define PMCCNTR p15,0,c9,c13,0 /* Perf. Mon. Cycle Count Register */
+#define PMXEVCNTR p15,0,c9,c13,1 /* Perf. Mon. Event Type Select Register */
+#define PMXEVCNR p15,0,c9,c13,2 /* Perf. Mon. Event Count Register */
+#define PMUSERENR p15,0,c9,c14,0 /* Perf. Mon. User Enable Register */
+#define PMINTENSET p15,0,c9,c14,1 /* Perf. Mon. Interrupt Enable Set Register */
+#define PMINTENCLR p15,0,c9,c14,2 /* Perf. Mon. Interrupt Enable Clear Register */
+#define PMOVSSET p15,0,c9,c14,3 /* Perf. Mon. Overflow Flag Status Set register */
/* CP15 CR10: */
#define MAIR0 p15,0,c10,c2,0 /* Memory Attribute Indirection Register 0 AKA PRRR */
@@ -260,6 +292,7 @@
#define CNTV_CVAL_EL0 CNTV_CVAL
#define CONTEXTIDR_EL1 CONTEXTIDR
#define CPACR_EL1 CPACR
+#define CPTR_EL2 HCPTR
#define CSSELR_EL1 CSSELR
#define DACR32_EL2 DACR
#define ESR_EL1 DFSR
@@ -268,6 +301,7 @@
#define FAR_EL2 HIFAR
#define HCR_EL2 HCR
#define HPFAR_EL2 HPFAR
+#define HSTR_EL2 HSTR
#define ID_AFR0_EL1 ID_AFR0
#define ID_DFR0_EL1 ID_DFR0
#define ID_ISAR0_EL1 ID_ISAR0
@@ -283,6 +317,7 @@
#define ID_PFR0_EL1 ID_PFR0
#define ID_PFR1_EL1 ID_PFR1
#define IFSR32_EL2 IFSR
+#define MDCR_EL2 HDCR
#define MIDR_EL1 MIDR
#define MPIDR_EL1 MPIDR
#define PAR_EL1 PAR
diff --git a/xen/include/asm-arm/domain.h b/xen/include/asm-arm/domain.h
index bc20a15..49f64b8 100644
--- a/xen/include/asm-arm/domain.h
+++ b/xen/include/asm-arm/domain.h
@@ -283,6 +283,9 @@ struct arch_vcpu
spinlock_t lock;
} vgic;
+ /* Timer registers */
+ uint32_t cntkctl;
+
struct vtimer phys_timer;
struct vtimer virt_timer;
} __cacheline_aligned;
diff --git a/xen/include/asm-arm/mm.h b/xen/include/asm-arm/mm.h
index b8d4e7d..8bf179d 100644
--- a/xen/include/asm-arm/mm.h
+++ b/xen/include/asm-arm/mm.h
@@ -233,9 +233,9 @@ static inline void *maddr_to_virt(paddr_t ma)
}
#endif
-static inline int gvirt_to_maddr(vaddr_t va, paddr_t *pa)
+static inline int gvirt_to_maddr(vaddr_t va, paddr_t *pa, unsigned int flags)
{
- uint64_t par = gva_to_ma_par(va);
+ uint64_t par = gva_to_ma_par(va, flags);
if ( par & PAR_F )
return -EFAULT;
*pa = (par & PADDR_MASK & PAGE_MASK) | ((unsigned long) va & ~PAGE_MASK);
@@ -273,6 +273,9 @@ struct domain *page_get_owner_and_reference(struct page_info *page);
void put_page(struct page_info *page);
int get_page(struct page_info *page, struct domain *domain);
+struct page_info *get_page_from_gva(struct domain *d, vaddr_t va,
+ unsigned long flags);
+
/*
* The MPT (machine->physical mapping table) is an array of word-sized
* values, indexed on machine frame number. It is expected that guest OSes
diff --git a/xen/include/asm-arm/p2m.h b/xen/include/asm-arm/p2m.h
index 3b39c45..e1013c8 100644
--- a/xen/include/asm-arm/p2m.h
+++ b/xen/include/asm-arm/p2m.h
@@ -75,6 +75,10 @@ int p2m_alloc_table(struct domain *d);
/* */
void p2m_load_VTTBR(struct domain *d);
+/* Context switch */
+void p2m_save_state(struct vcpu *p);
+void p2m_restore_state(struct vcpu *n);
+
/* Look up the MFN corresponding to a domain's PFN. */
paddr_t p2m_lookup(struct domain *d, paddr_t gpfn, p2m_type_t *t);
diff --git a/xen/include/asm-arm/page.h b/xen/include/asm-arm/page.h
index e00be9e..c118309 100644
--- a/xen/include/asm-arm/page.h
+++ b/xen/include/asm-arm/page.h
@@ -73,6 +73,10 @@
#define MATTR_DEV 0x1
#define MATTR_MEM 0xf
+/* Flags for get_page_from_gva, gvirt_to_maddr etc */
+#define GV2M_READ (0u<<0)
+#define GV2M_WRITE (1u<<0)
+
#ifndef __ASSEMBLY__
#include <xen/types.h>
diff --git a/xen/include/asm-arm/processor.h b/xen/include/asm-arm/processor.h
index 06e638f..1f158ce 100644
--- a/xen/include/asm-arm/processor.h
+++ b/xen/include/asm-arm/processor.h
@@ -84,13 +84,28 @@
#define HCR_SWIO (_AC(1,UL)<<1) /* Set/Way Invalidation Override */
#define HCR_VM (_AC(1,UL)<<0) /* Virtual MMU Enable */
+/* HCPTR Hyp. Coprocessor Trap Register */
+#define HCPTR_TTA ((_AC(1,U)<<20)) /* Trap trace registers */
+#define HCPTR_CP(x) ((_AC(1,U)<<(x))) /* Trap Coprocessor x */
+#define HCPTR_CP_MASK ((_AC(1,U)<<14)-1)
+
+/* HSTR Hyp. System Trap Register */
+#define HSTR_T(x) ((_AC(1,U)<<(x))) /* Trap Cp15 c<x> */
+
+/* HDCR Hyp. Debug Configuration Register */
+#define HDCR_TDRA (_AC(1,U)<<11) /* Trap Debug ROM access */
+#define HDCR_TDOSA (_AC(1,U)<<10) /* Trap Debug-OS-related register access */
+#define HDCR_TDA (_AC(1,U)<<9) /* Trap Debug Access */
+#define HDCR_TPM (_AC(1,U)<<6) /* Trap Performance Monitors accesses */
+#define HDCR_TPMCR (_AC(1,U)<<5) /* Trap PMCR accesses */
+
#define HSR_EC_UNKNOWN 0x00
#define HSR_EC_WFI_WFE 0x01
#define HSR_EC_CP15_32 0x03
#define HSR_EC_CP15_64 0x04
-#define HSR_EC_CP14_32 0x05
-#define HSR_EC_CP14_DBG 0x06
-#define HSR_EC_CP 0x07
+#define HSR_EC_CP14_32 0x05 /* Trapped MCR or MRC access to CP14 */
+#define HSR_EC_CP14_DBG 0x06 /* Trapped LDC/STC access to CP14 (only for debug registers) */
+#define HSR_EC_CP 0x07 /* HCPTR-trapped access to CP0-CP13 */
#define HSR_EC_CP10 0x08
#define HSR_EC_JAZELLE 0x09
#define HSR_EC_BXJ 0x0a
@@ -417,14 +432,16 @@ union hsr {
#define VECTOR32_PABT 12
#define VECTOR32_DABT 16
/* ... ARM64 */
-#define VECTOR64_CURRENT_SP0_SYNC 0x000
-#define VECTOR64_CURRENT_SP0_IRQ 0x080
-#define VECTOR64_CURRENT_SP0_FIQ 0x100
-#define VECTOR64_CURRENT_SP0_ERROR 0x180
-#define VECTOR64_CURRENT_SPx_SYNC 0x200
-#define VECTOR64_CURRENT_SPx_IRQ 0x280
-#define VECTOR64_CURRENT_SPx_FIQ 0x300
-#define VECTOR64_CURRENT_SPx_ERROR 0x380
+#define VECTOR64_CURRENT_SP0_BASE 0x000
+#define VECTOR64_CURRENT_SPx_BASE 0x200
+#define VECTOR64_LOWER64_BASE 0x400
+#define VECTOR64_LOWER32_BASE 0x600
+
+#define VECTOR64_SYNC_OFFSET 0x000
+#define VECTOR64_IRQ_OFFSET 0x080
+#define VECTOR64_FIQ_OFFSET 0x100
+#define VECTOR64_ERROR_OFFSET 0x180
+
#if defined(CONFIG_ARM_32)
# include <asm/arm32/processor.h>
diff --git a/xen/include/asm-arm/sysregs.h b/xen/include/asm-arm/sysregs.h
index 0cee0e9..b00871c 100644
--- a/xen/include/asm-arm/sysregs.h
+++ b/xen/include/asm-arm/sysregs.h
@@ -40,6 +40,32 @@
((__HSR_SYSREG_##crm) << HSR_SYSREG_CRM_SHIFT) | \
((__HSR_SYSREG_##op2) << HSR_SYSREG_OP2_SHIFT)
+#define HSR_SYSREG_MDSCR_EL1 HSR_SYSREG(2,0,c0,c2,2)
+#define HSR_SYSREG_OSLAR_EL1 HSR_SYSREG(2,0,c1,c0,4)
+#define HSR_SYSREG_OSDLR_EL1 HSR_SYSREG(2,0,c1,c3,4)
+
+#define HSR_SYSREG_DBGBVRn_EL1(n) HSR_SYSREG(2,0,c0,c##n,4)
+#define HSR_SYSREG_DBGBCRn_EL1(n) HSR_SYSREG(2,0,c0,c##n,5)
+#define HSR_SYSREG_DBGWVRn_EL1(n) HSR_SYSREG(2,0,c0,c##n,6)
+#define HSR_SYSREG_DBGWCRn_EL1(n) HSR_SYSREG(2,0,c0,c##n,7)
+
+#define HSR_SYSREG_DBG_CASES(REG) case HSR_SYSREG_##REG##n_EL1(0): \
+ case HSR_SYSREG_##REG##n_EL1(1): \
+ case HSR_SYSREG_##REG##n_EL1(2): \
+ case HSR_SYSREG_##REG##n_EL1(3): \
+ case HSR_SYSREG_##REG##n_EL1(4): \
+ case HSR_SYSREG_##REG##n_EL1(5): \
+ case HSR_SYSREG_##REG##n_EL1(6): \
+ case HSR_SYSREG_##REG##n_EL1(7): \
+ case HSR_SYSREG_##REG##n_EL1(8): \
+ case HSR_SYSREG_##REG##n_EL1(9): \
+ case HSR_SYSREG_##REG##n_EL1(10): \
+ case HSR_SYSREG_##REG##n_EL1(11): \
+ case HSR_SYSREG_##REG##n_EL1(12): \
+ case HSR_SYSREG_##REG##n_EL1(13): \
+ case HSR_SYSREG_##REG##n_EL1(14): \
+ case HSR_SYSREG_##REG##n_EL1(15)
+
#define HSR_SYSREG_SCTLR_EL1 HSR_SYSREG(3,0,c1, c0,0)
#define HSR_SYSREG_TTBR0_EL1 HSR_SYSREG(3,0,c2, c0,0)
#define HSR_SYSREG_TTBR1_EL1 HSR_SYSREG(3,0,c2, c0,1)
@@ -48,10 +74,28 @@
#define HSR_SYSREG_AFSR1_EL1 HSR_SYSREG(3,0,c5, c1,1)
#define HSR_SYSREG_ESR_EL1 HSR_SYSREG(3,0,c5, c2,0)
#define HSR_SYSREG_FAR_EL1 HSR_SYSREG(3,0,c6, c0,0)
+#define HSR_SYSREG_PMINTENSET_EL1 HSR_SYSREG(3,0,c9,c14,1)
+#define HSR_SYSREG_PMINTENCLR_EL1 HSR_SYSREG(3,0,c9,c14,2)
#define HSR_SYSREG_MAIR_EL1 HSR_SYSREG(3,0,c10,c2,0)
#define HSR_SYSREG_AMAIR_EL1 HSR_SYSREG(3,0,c10,c3,0)
#define HSR_SYSREG_CONTEXTIDR_EL1 HSR_SYSREG(3,0,c13,c0,1)
+#define HSR_SYSREG_PMCR_EL0 HSR_SYSREG(3,3,c9,c12,0)
+#define HSR_SYSREG_PMCNTENSET_EL0 HSR_SYSREG(3,3,c9,c12,1)
+#define HSR_SYSREG_PMCNTENCLR_EL0 HSR_SYSREG(3,3,c9,c12,2)
+#define HSR_SYSREG_PMOVSCLR_EL0 HSR_SYSREG(3,3,c9,c12,3)
+#define HSR_SYSREG_PMSWINC_EL0 HSR_SYSREG(3,3,c9,c12,4)
+#define HSR_SYSREG_PMSELR_EL0 HSR_SYSREG(3,3,c9,c12,5)
+#define HSR_SYSREG_PMCEID0_EL0 HSR_SYSREG(3,3,c9,c12,6)
+#define HSR_SYSREG_PMCEID1_EL0 HSR_SYSREG(3,3,c9,c12,7)
+
+#define HSR_SYSREG_PMCCNTR_EL0 HSR_SYSREG(3,3,c9,c13,0)
+#define HSR_SYSREG_PMXEVTYPER_EL0 HSR_SYSREG(3,3,c9,c13,1)
+#define HSR_SYSREG_PMXEVCNTR_EL0 HSR_SYSREG(3,3,c9,c13,2)
+
+#define HSR_SYSREG_PMUSERENR_EL0 HSR_SYSREG(3,3,c9,c14,0)
+#define HSR_SYSREG_PMOVSSET_EL0 HSR_SYSREG(3,3,c9,c14,3)
+
#define HSR_SYSREG_CNTPCT_EL0 HSR_SYSREG(3,3,c14,c0,0)
#define HSR_SYSREG_CNTP_CTL_EL0 HSR_SYSREG(3,3,c14,c2,1)
#define HSR_SYSREG_CNTP_TVAL_EL0 HSR_SYSREG(3,3,c14,c2,0)
diff --git a/xen/include/asm-x86/cpufeature.h b/xen/include/asm-x86/cpufeature.h
index 1cfaf94..526821f 100644
--- a/xen/include/asm-x86/cpufeature.h
+++ b/xen/include/asm-x86/cpufeature.h
@@ -71,6 +71,7 @@
#define X86_FEATURE_TSC_RELIABLE (3*32+12) /* TSC is known to be reliable */
#define X86_FEATURE_XTOPOLOGY (3*32+13) /* cpu topology enum extensions */
#define X86_FEATURE_CPUID_FAULTING (3*32+14) /* cpuid faulting */
+#define X86_FEATURE_CLFLUSH_MONITOR (3*32+15) /* clflush reqd with monitor */
/* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
#define X86_FEATURE_XMM3 (4*32+ 0) /* Streaming SIMD Extensions-3 */
diff --git a/xen/include/asm-x86/hvm/hvm.h b/xen/include/asm-x86/hvm/hvm.h
index ccca5df..974bcc0 100644
--- a/xen/include/asm-x86/hvm/hvm.h
+++ b/xen/include/asm-x86/hvm/hvm.h
@@ -347,6 +347,19 @@ static inline int hvm_event_pending(struct vcpu *v)
return hvm_funcs.event_pending(v);
}
+static inline bool_t hvm_vcpu_has_smep(void)
+{
+ unsigned int eax, ebx;
+
+ hvm_cpuid(0, &eax, NULL, NULL, NULL);
+
+ if ( eax < 7 )
+ return 0;
+
+ hvm_cpuid(7, NULL, &ebx, NULL, NULL);
+ return !!(ebx & cpufeat_mask(X86_FEATURE_SMEP));
+}
+
/* These reserved bits in lower 32 remain 0 after any load of CR0 */
#define HVM_CR0_GUEST_RESERVED_BITS \
(~((unsigned long) \
@@ -360,18 +373,24 @@ static inline int hvm_event_pending(struct vcpu *v)
(X86_CR4_VMXE | X86_CR4_PAE | X86_CR4_MCE))
/* These bits in CR4 cannot be set by the guest. */
-#define HVM_CR4_GUEST_RESERVED_BITS(_v) \
+#define HVM_CR4_GUEST_RESERVED_BITS(v, restore) ({ \
+ const struct vcpu *_v = (v); \
+ bool_t _restore = !!(restore); \
+ ASSERT((_restore) || _v == current); \
(~((unsigned long) \
(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | \
X86_CR4_DE | X86_CR4_PSE | X86_CR4_PAE | \
X86_CR4_MCE | X86_CR4_PGE | X86_CR4_PCE | \
X86_CR4_OSFXSR | X86_CR4_OSXMMEXCPT | \
- (cpu_has_smep ? X86_CR4_SMEP : 0) | \
+ (((_restore) ? cpu_has_smep : \
+ hvm_vcpu_has_smep()) ? \
+ X86_CR4_SMEP : 0) | \
(cpu_has_fsgsbase ? X86_CR4_FSGSBASE : 0) | \
- ((nestedhvm_enabled((_v)->domain) && cpu_has_vmx)\
- ? X86_CR4_VMXE : 0) | \
- (cpu_has_pcid ? X86_CR4_PCIDE : 0) | \
- (cpu_has_xsave ? X86_CR4_OSXSAVE : 0))))
+ ((nestedhvm_enabled(_v->domain) && cpu_has_vmx) \
+ ? X86_CR4_VMXE : 0) | \
+ (cpu_has_pcid ? X86_CR4_PCIDE : 0) | \
+ (cpu_has_xsave ? X86_CR4_OSXSAVE : 0)))); \
+})
/* These exceptions must always be intercepted. */
#define HVM_TRAP_MASK ((1U << TRAP_machine_check) | (1U << TRAP_invalid_op))
diff --git a/xen/include/asm-x86/hvm/vmx/vmcs.h b/xen/include/asm-x86/hvm/vmx/vmcs.h
index ebaba5c..f0c5fa5 100644
--- a/xen/include/asm-x86/hvm/vmx/vmcs.h
+++ b/xen/include/asm-x86/hvm/vmx/vmcs.h
@@ -483,6 +483,8 @@ void virtual_vmcs_exit(void *vvmcs);
u64 virtual_vmcs_vmread(void *vvmcs, u32 vmcs_encoding);
void virtual_vmcs_vmwrite(void *vvmcs, u32 vmcs_encoding, u64 val);
+DECLARE_PER_CPU(bool_t, vmxon);
+
#endif /* ASM_X86_HVM_VMX_VMCS_H__ */
/*
diff --git a/xen/include/asm-x86/hvm/vpt.h b/xen/include/asm-x86/hvm/vpt.h
index 87c3a66..41159d8 100644
--- a/xen/include/asm-x86/hvm/vpt.h
+++ b/xen/include/asm-x86/hvm/vpt.h
@@ -113,7 +113,8 @@ typedef struct RTCState {
/* periodic timer */
struct periodic_time pt;
s_time_t start_time;
- int pt_code;
+ s_time_t check_ticks_since;
+ int period;
uint8_t pt_dead_ticks;
uint32_t use_timer;
spinlock_t lock;
@@ -175,7 +176,7 @@ void destroy_periodic_time(struct periodic_time *pt);
int pv_pit_handler(int port, int data, int write);
void pit_reset(struct domain *d);
-void pit_init(struct vcpu *v, unsigned long cpu_khz);
+void pit_init(struct domain *d, unsigned long cpu_khz);
void pit_stop_channel0_irq(PITState * pit);
void pit_deinit(struct domain *d);
void rtc_init(struct domain *d);
@@ -183,7 +184,6 @@ void rtc_migrate_timers(struct vcpu *v);
void rtc_deinit(struct domain *d);
void rtc_reset(struct domain *d);
void rtc_update_clock(struct domain *d);
-bool_t rtc_periodic_interrupt(void *);
void pmtimer_init(struct vcpu *v);
void pmtimer_deinit(struct domain *d);
diff --git a/xen/include/asm-x86/i387.h b/xen/include/asm-x86/i387.h
index 1f5fe50..fd268a9 100644
--- a/xen/include/asm-x86/i387.h
+++ b/xen/include/asm-x86/i387.h
@@ -38,6 +38,7 @@ struct ix87_state {
void vcpu_restore_fpu_eager(struct vcpu *v);
void vcpu_restore_fpu_lazy(struct vcpu *v);
void vcpu_save_fpu(struct vcpu *v);
+void save_fpu_enable(void);
int vcpu_init_fpu(struct vcpu *v);
void vcpu_destroy_fpu(struct vcpu *v);
diff --git a/xen/include/asm-x86/mem_event.h b/xen/include/asm-x86/mem_event.h
index 045ef9b..ed4481a 100644
--- a/xen/include/asm-x86/mem_event.h
+++ b/xen/include/asm-x86/mem_event.h
@@ -66,6 +66,9 @@ int do_mem_event_op(int op, uint32_t domain, void *arg);
int mem_event_domctl(struct domain *d, xen_domctl_mem_event_op_t *mec,
XEN_GUEST_HANDLE_PARAM(void) u_domctl);
+void mem_event_vcpu_pause(struct vcpu *v);
+void mem_event_vcpu_unpause(struct vcpu *v);
+
#endif /* __MEM_EVENT_H__ */
diff --git a/xen/include/asm-x86/p2m.h b/xen/include/asm-x86/p2m.h
index f4e7253..a2cb1b7 100644
--- a/xen/include/asm-x86/p2m.h
+++ b/xen/include/asm-x86/p2m.h
@@ -576,8 +576,8 @@ void p2m_mem_access_resume(struct domain *d);
/* Set access type for a region of pfns.
* If start_pfn == -1ul, sets the default access type */
-int p2m_set_mem_access(struct domain *d, unsigned long start_pfn,
- uint32_t nr, hvmmem_access_t access);
+long p2m_set_mem_access(struct domain *d, unsigned long start_pfn,
+ uint32_t nr, hvmmem_access_t access);
/* Get access type for a pfn
* If pfn == -1ul, gets the default access type */
diff --git a/xen/include/public/arch-arm.h b/xen/include/public/arch-arm.h
index 7496556..dd53c94 100644
--- a/xen/include/public/arch-arm.h
+++ b/xen/include/public/arch-arm.h
@@ -369,7 +369,8 @@ typedef uint64_t xen_callback_t;
#define GUEST_GICC_BASE 0x2c002000ULL
#define GUEST_GICC_SIZE 0x100ULL
-#define GUEST_RAM_BASE 0x80000000ULL
+#define GUEST_RAM_BASE 0x80000000ULL /* 768M @ 2GB */
+#define GUEST_RAM_SIZE 0x30000000ULL
#define GUEST_GNTTAB_BASE 0xb0000000ULL
#define GUEST_GNTTAB_SIZE 0x00020000ULL
diff --git a/xen/include/public/xen.h b/xen/include/public/xen.h
index 8c5697e..a6a2092 100644
--- a/xen/include/public/xen.h
+++ b/xen/include/public/xen.h
@@ -541,13 +541,15 @@ DEFINE_XEN_GUEST_HANDLE(mmu_update_t);
/*
* ` enum neg_errnoval
* ` HYPERVISOR_multicall(multicall_entry_t call_list[],
- * ` unsigned int nr_calls);
+ * ` uint32_t nr_calls);
*
- * NB. The fields are natural register size for this architecture.
+ * NB. The fields are logically the natural register size for this
+ * architecture. In cases where xen_ulong_t is larger than this then
+ * any unused bits in the upper portion must be zero.
*/
struct multicall_entry {
- unsigned long op, result;
- unsigned long args[6];
+ xen_ulong_t op, result;
+ xen_ulong_t args[6];
};
typedef struct multicall_entry multicall_entry_t;
DEFINE_XEN_GUEST_HANDLE(multicall_entry_t);
diff --git a/xen/include/xen/acpi.h b/xen/include/xen/acpi.h
index aedec65..3aeba4a 100644
--- a/xen/include/xen/acpi.h
+++ b/xen/include/xen/acpi.h
@@ -61,6 +61,7 @@ int acpi_boot_init (void);
int acpi_boot_table_init (void);
int acpi_numa_init (void);
int erst_init(void);
+void acpi_hest_init(void);
int acpi_table_init (void);
int acpi_table_parse(char *id, acpi_table_handler handler);
diff --git a/xen/include/xen/hvm/iommu.h b/xen/include/xen/hvm/iommu.h
index 26539e0..8c98274 100644
--- a/xen/include/xen/hvm/iommu.h
+++ b/xen/include/xen/hvm/iommu.h
@@ -29,12 +29,6 @@ struct g2m_ioport {
unsigned int np;
};
-struct mapped_rmrr {
- struct list_head list;
- u64 base;
- u64 end;
-};
-
struct hvm_iommu {
u64 pgd_maddr; /* io page directory machine address */
spinlock_t mapping_lock; /* io page table lock */
diff --git a/xen/include/xen/pci.h b/xen/include/xen/pci.h
index cadb525..f3f080f 100644
--- a/xen/include/xen/pci.h
+++ b/xen/include/xen/pci.h
@@ -140,9 +140,12 @@ int pci_mmcfg_write(unsigned int seg, unsigned int bus,
int pci_find_cap_offset(u16 seg, u8 bus, u8 dev, u8 func, u8 cap);
int pci_find_next_cap(u16 seg, u8 bus, unsigned int devfn, u8 pos, int cap);
int pci_find_ext_capability(int seg, int bus, int devfn, int cap);
+int pci_find_next_ext_capability(int seg, int bus, int devfn, int pos, int cap);
const char *parse_pci(const char *, unsigned int *seg, unsigned int *bus,
unsigned int *dev, unsigned int *func);
+bool_t pcie_aer_get_firmware_first(const struct pci_dev *);
+
struct pirq;
int msixtbl_pt_register(struct domain *, struct pirq *, uint64_t gtable);
void msixtbl_pt_unregister(struct domain *, struct pirq *);
diff --git a/xen/include/xen/pci_ids.h b/xen/include/xen/pci_ids.h
new file mode 100644
index 0000000..f5b1d94
--- /dev/null
+++ b/xen/include/xen/pci_ids.h
@@ -0,0 +1,9 @@
+#define PCI_VENDOR_ID_AMD 0x1022
+
+#define PCI_VENDOR_ID_NVIDIA 0x10de
+
+#define PCI_VENDOR_ID_OXSEMI 0x1415
+
+#define PCI_VENDOR_ID_BROADCOM 0x14e4
+
+#define PCI_VENDOR_ID_INTEL 0x8086
diff --git a/xen/include/xen/pci_regs.h b/xen/include/xen/pci_regs.h
index ad47054..ecd6124 100644
--- a/xen/include/xen/pci_regs.h
+++ b/xen/include/xen/pci_regs.h
@@ -125,7 +125,7 @@
#define PCI_IO_RANGE_TYPE_16 0x00
#define PCI_IO_RANGE_TYPE_32 0x01
#define PCI_IO_RANGE_MASK (~0x0fUL)
-#define PCI_SEC_STATUS 0x1e /* Secondary status register, only bit 14 used */
+#define PCI_SEC_STATUS 0x1e /* Secondary status register */
#define PCI_MEMORY_BASE 0x20 /* Memory range behind */
#define PCI_MEMORY_LIMIT 0x22
#define PCI_MEMORY_RANGE_TYPE_MASK 0x0fUL
@@ -152,6 +152,7 @@
#define PCI_BRIDGE_CTL_MASTER_ABORT 0x20 /* Report master aborts */
#define PCI_BRIDGE_CTL_BUS_RESET 0x40 /* Secondary bus reset */
#define PCI_BRIDGE_CTL_FAST_BACK 0x80 /* Fast Back2Back enabled on secondary interface */
+#define PCI_BRIDGE_CTL_DTMR_SERR 0x800 /* SERR upon discard timer expiry */
/* Header type 2 (CardBus bridges) */
#define PCI_CB_CAPABILITY_LIST 0x14
@@ -431,6 +432,7 @@
#define PCI_EXT_CAP_ID_VC 2
#define PCI_EXT_CAP_ID_DSN 3
#define PCI_EXT_CAP_ID_PWR 4
+#define PCI_EXT_CAP_ID_VNDR 11
#define PCI_EXT_CAP_ID_ACS 13
#define PCI_EXT_CAP_ID_ARI 14
#define PCI_EXT_CAP_ID_ATS 15
@@ -459,6 +461,7 @@
#define PCI_ERR_COR_BAD_DLLP 0x00000080 /* Bad DLLP Status */
#define PCI_ERR_COR_REP_ROLL 0x00000100 /* REPLAY_NUM Rollover */
#define PCI_ERR_COR_REP_TIMER 0x00001000 /* Replay Timer Timeout */
+#define PCI_ERR_COR_ADV_NFAT 0x00002000 /* Advisory Non-Fatal */
#define PCI_ERR_COR_MASK 20 /* Correctable Error Mask */
/* Same bits as above */
#define PCI_ERR_CAP 24 /* Advanced Error Capabilities */
@@ -510,6 +513,12 @@
#define PCI_PWR_CAP 12 /* Capability */
#define PCI_PWR_CAP_BUDGET(x) ((x) & 1) /* Included in system budget */
+/* Vendor-Specific (VSEC, PCI_EXT_CAP_ID_VNDR) */
+#define PCI_VNDR_HEADER 4 /* Vendor-Specific Header */
+#define PCI_VNDR_HEADER_ID(x) ((x) & 0xffff)
+#define PCI_VNDR_HEADER_REV(x) (((x) >> 16) & 0xf)
+#define PCI_VNDR_HEADER_LEN(x) (((x) >> 20) & 0xfff)
+
/*
* Hypertransport sub capability types
*
diff --git a/xen/include/xen/prefetch.h b/xen/include/xen/prefetch.h
index 8d7d3ff..ba73998 100644
--- a/xen/include/xen/prefetch.h
+++ b/xen/include/xen/prefetch.h
@@ -28,24 +28,17 @@
prefetchw(x) - prefetches the cacheline at "x" for write
spin_lock_prefetch(x) - prefectches the spinlock *x for taking
- there is also PREFETCH_STRIDE which is the architecure-prefered
+ there is also PREFETCH_STRIDE which is the architecture-preferred
"lookahead" size for prefetching streamed operations.
*/
-/*
- * These cannot be do{}while(0) macros. See the mental gymnastics in
- * the loop macro.
- */
-
#ifndef ARCH_HAS_PREFETCH
-#define ARCH_HAS_PREFETCH
-static inline void prefetch(const void *x) {;}
+#define prefetch(x) __builtin_prefetch(x)
#endif
#ifndef ARCH_HAS_PREFETCHW
-#define ARCH_HAS_PREFETCHW
-static inline void prefetchw(const void *x) {;}
+#define prefetchw(x) __builtin_prefetch(x,1)
#endif
#ifndef ARCH_HAS_SPINLOCK_PREFETCH
diff --git a/xen/include/xen/sched.h b/xen/include/xen/sched.h
index fb8bd36..4418883 100644
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -86,13 +86,13 @@ struct evtchn
domid_t remote_domid;
} unbound; /* state == ECS_UNBOUND */
struct {
- u16 remote_port;
+ evtchn_port_t remote_port;
struct domain *remote_dom;
} interdomain; /* state == ECS_INTERDOMAIN */
struct {
- u16 irq;
- u16 next_port;
- u16 prev_port;
+ u32 irq;
+ evtchn_port_t next_port;
+ evtchn_port_t prev_port;
} pirq; /* state == ECS_PIRQ */
u16 virq; /* state == ECS_VIRQ */
} u;
@@ -189,8 +189,11 @@ struct vcpu
unsigned long pause_flags;
atomic_t pause_count;
+ /* VCPU paused for mem_event replies. */
+ atomic_t mem_event_pause_count;
+
/* IRQ-safe virq_lock protects against delivering VIRQ to stale evtchn. */
- u16 virq_to_evtchn[NR_VIRQS];
+ evtchn_port_t virq_to_evtchn[NR_VIRQS];
spinlock_t virq_lock;
/* Bitmask of CPUs on which this VCPU may run. */
@@ -338,7 +341,7 @@ struct domain
/* Is this guest dying (i.e., a zombie)? */
enum { DOMDYING_alive, DOMDYING_dying, DOMDYING_dead } is_dying;
/* Domain is paused by controller software? */
- bool_t is_paused_by_controller;
+ int controller_pause_count;
/* Domain's VCPUs are pinned 1:1 to physical CPUs? */
bool_t is_pinned;
@@ -742,8 +745,17 @@ void domain_pause(struct domain *d);
void domain_pause_nosync(struct domain *d);
void vcpu_unpause(struct vcpu *v);
void domain_unpause(struct domain *d);
-void domain_pause_by_systemcontroller(struct domain *d);
-void domain_unpause_by_systemcontroller(struct domain *d);
+int domain_unpause_by_systemcontroller(struct domain *d);
+int __domain_pause_by_systemcontroller(struct domain *d,
+ void (*pause_fn)(struct domain *d));
+static inline int domain_pause_by_systemcontroller(struct domain *d)
+{
+ return __domain_pause_by_systemcontroller(d, domain_pause);
+}
+static inline int domain_pause_by_systemcontroller_nosync(struct domain *d)
+{
+ return __domain_pause_by_systemcontroller(d, domain_pause_nosync);
+}
void cpu_init(void);
struct scheduler;
diff --git a/xen/include/xen/trace.h b/xen/include/xen/trace.h
index 3b8a7b3..12966ea 100644
--- a/xen/include/xen/trace.h
+++ b/xen/include/xen/trace.h
@@ -45,7 +45,7 @@ static inline void trace_var(u32 event, int cycles, int extra,
}
void __trace_hypercall(uint32_t event, unsigned long op,
- const unsigned long *args);
+ const xen_ulong_t *args);
/* Convenience macros for calling the trace function. */
#define TRACE_0D(_e) \
--
Alioth's /usr/local/bin/git-commit-notice on /srv/git.debian.org/git/pkg-xen/xen.git
More information about the Pkg-xen-changes
mailing list