configure | 13 +++++++++++++ 1 file changed, 13 insertions(+)
KVM guests on s390 need a different page table layout than normal
processes (2kb page table + 2kb page status extensions vs 2kb page table
only). As of today this has to be enabled via the vm.allocate_pgste
sysctl.
Newer kernels (>= 4.12) on s390 check for an S390_PGSTE program header
and enable the pgste page table extensions in that case. This makes the
vm.allocate_pgste sysctl unnecessary. We enable this program header for
the s390 system emulation (qemu-system-s390x) if
- the linker supports --s390-pgste (binutils >= 2.29)
- KVM is enabled
This will allow distributions to disable the global vm.allocate_pgste
sysctl, which will improve the page table allocation for non KVM
processes as only 2kb chunks are necessary.
Cc: Christian Ehrhardt <christian.ehrhardt@canonical.com>
Cc: Alexander Graf <agraf@suse.de>
Cc: Dan Horak <dhorak@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Acked-by: Janosch Frank <frankja@linux.vnet.ibm.com>
---
configure | 13 +++++++++++++
1 file changed, 13 insertions(+)
diff --git a/configure b/configure
index dd73cce..4c9084b 100755
--- a/configure
+++ b/configure
@@ -6522,6 +6522,19 @@ if test "$target_linux_user" = "yes" -o "$target_bsd_user" = "yes" ; then
ldflags="$ldflags $textseg_ldflags"
fi
+# Newer kernels on s390 check for an S390_PGSTE program header and
+# enable the pgste page table extensions in that case. This makes
+# the vm.allocate_pgste sysctl unnecessary. We enable this program
+# header if
+# - the linker support --s390-pgste
+# - we build the system emulation (qemu-system-s390x)
+# - KVM is enabled
+if $ld --help 2>/dev/null | grep ".--s390-pgste" >/dev/null 2>/dev/null ; then
+ if test "$target_softmmu" = "yes" -a "$ARCH" = "s390x" -a "$kvm" = "yes" ; then
+ ldflags="-Wl,--s390-pgste $ldflags"
+ fi
+fi
+
echo "LDFLAGS+=$ldflags" >> $config_target_mak
echo "QEMU_CFLAGS+=$cflags" >> $config_target_mak
--
2.7.4
On 22.08.2017 16:47, Christian Borntraeger wrote: > KVM guests on s390 need a different page table layout than normal > processes (2kb page table + 2kb page status extensions vs 2kb page table > only). As of today this has to be enabled via the vm.allocate_pgste > sysctl. > > Newer kernels (>= 4.12) on s390 check for an S390_PGSTE program header > and enable the pgste page table extensions in that case. This makes the > vm.allocate_pgste sysctl unnecessary. We enable this program header for > the s390 system emulation (qemu-system-s390x) if > - the linker supports --s390-pgste (binutils >= 2.29) > - KVM is enabled > > This will allow distributions to disable the global vm.allocate_pgste > sysctl, which will improve the page table allocation for non KVM > processes as only 2kb chunks are necessary. > > Cc: Christian Ehrhardt <christian.ehrhardt@canonical.com> > Cc: Alexander Graf <agraf@suse.de> > Cc: Dan Horak <dhorak@redhat.com> > Cc: David Hildenbrand <david@redhat.com> > Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com> > Acked-by: Janosch Frank <frankja@linux.vnet.ibm.com> > --- > configure | 13 +++++++++++++ > 1 file changed, 13 insertions(+) > > diff --git a/configure b/configure > index dd73cce..4c9084b 100755 > --- a/configure > +++ b/configure > @@ -6522,6 +6522,19 @@ if test "$target_linux_user" = "yes" -o "$target_bsd_user" = "yes" ; then > ldflags="$ldflags $textseg_ldflags" > fi > > +# Newer kernels on s390 check for an S390_PGSTE program header and > +# enable the pgste page table extensions in that case. This makes > +# the vm.allocate_pgste sysctl unnecessary. We enable this program > +# header if > +# - the linker support --s390-pgste > +# - we build the system emulation (qemu-system-s390x) > +# - KVM is enabled > +if $ld --help 2>/dev/null | grep ".--s390-pgste" >/dev/null 2>/dev/null ; then >/dev/null 2>&1 (from has(){} definiton) maybe even introduce ld_has() { $ld --help 2>/dev/null | grep ".$1" >/dev/null 2>&1 } I guess it also makes sense to test for s390x first, before checking for ld support. > + if test "$target_softmmu" = "yes" -a "$ARCH" = "s390x" -a "$kvm" = "yes" ; then > + ldflags="-Wl,--s390-pgste $ldflags" > + fi > +fi > + > echo "LDFLAGS+=$ldflags" >> $config_target_mak > echo "QEMU_CFLAGS+=$cflags" >> $config_target_mak > > Happy to see this change :) -- Thanks, David
© 2016 - 2024 Red Hat, Inc.