From e9148733cef44bebb0d74a731a70b3304e720634 Mon Sep 17 00:00:00 2001

From: Alex Williamson <alex.williamson@redhat.com>

Date: Thu, 13 Dec 2018 21:55:26 +0100

Subject: [PATCH 5/5] vfio: Inhibit ballooning based on group attachment to a

 container

RH-Author: Alex Williamson <alex.williamson@redhat.com>

Message-id: <154473812659.22725.6814768117383324849.stgit@gimli.home>

Patchwork-id: 83497

O-Subject: [RHEL-7.7 qemu-kvm PATCH 5/5] vfio: Inhibit ballooning based on group attachment to a container

Bugzilla: 1659229

RH-Acked-by: Peter Xu <peterx@redhat.com>

RH-Acked-by: Cornelia Huck <cohuck@redhat.com>

RH-Acked-by: Auger Eric <eric.auger@redhat.com>

Bugzilla: 1659229

Notes: Error path has more exit paths versus upstream

We use a VFIOContainer to associate an AddressSpace to one or more

VFIOGroups.  The VFIOContainer represents the DMA context for that

AdressSpace for those VFIOGroups and is synchronized to changes in

that AddressSpace via a MemoryListener.  For IOMMU backed devices,

maintaining the DMA context for a VFIOGroup generally involves

pinning a host virtual address in order to create a stable host

physical address and then mapping a translation from the associated

guest physical address to that host physical address into the IOMMU.

While the above maintains the VFIOContainer synchronized to the QEMU

memory API of the VM, memory ballooning occurs outside of that API.

Inflating the memory balloon (ie. cooperatively capturing pages from

the guest for use by the host) simply uses MADV_DONTNEED to "zap"

pages from QEMU's host virtual address space.  The page pinning and

IOMMU mapping above remains in place, negating the host's ability to

reuse the page, but the host virtual to host physical mapping of the

page is invalidated outside of QEMU's memory API.

When the balloon is later deflated, attempting to cooperatively

return pages to the guest, the page is simply freed by the guest

balloon driver, allowing it to be used in the guest and incurring a

page fault when that occurs.  The page fault maps a new host physical

page backing the existing host virtual address, meanwhile the

VFIOContainer still maintains the translation to the original host

physical address.  At this point the guest vCPU and any assigned

devices will map different host physical addresses to the same guest

physical address.  Badness.

The IOMMU typically does not have page level granularity with which

it can track this mapping without also incurring inefficiencies in

using page size mappings throughout.  MMU notifiers in the host

kernel also provide indicators for invalidating the mapping on

balloon inflation, not for updating the mapping when the balloon is

deflated.  For these reasons we assume a default behavior that the

mapping of each VFIOGroup into the VFIOContainer is incompatible

with memory ballooning and increment the balloon inhibitor to match

the attached VFIOGroups.

Reviewed-by: Peter Xu <peterx@redhat.com>

Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

(cherry picked from commit c65ee433153b5925e183a00ebf568e160077c694)

Signed-off-by: Miroslav Rezanina <mrezanin@redhat.com>

---

 hw/misc/vfio.c | 35 +++++++++++++++++++++++++++++++++++

 1 file changed, 35 insertions(+)

diff --git a/hw/misc/vfio.c b/hw/misc/vfio.c

index f91eecb..f7360bf 100644

--- a/hw/misc/vfio.c

+++ b/hw/misc/vfio.c

@@ -37,6 +37,7 @@

 #include "qemu/event_notifier.h"

 #include "qemu/queue.h"

 #include "qemu/range.h"

+#include "sysemu/balloon.h"

 #include "sysemu/kvm.h"

 #include "sysemu/sysemu.h"

 #include "trace.h"

@@ -3667,6 +3668,33 @@ static int vfio_connect_container(VFIOGroup *group)

         return 0;

     }

+    /*

+     * VFIO is currently incompatible with memory ballooning insofar as the

+     * madvise to purge (zap) the page from QEMU's address space does not

+     * interact with the memory API and therefore leaves stale virtual to

+     * physical mappings in the IOMMU if the page was previously pinned.  We

+     * therefore add a balloon inhibit for each group added to a container,

+     * whether the container is used individually or shared.  This provides

+     * us with options to allow devices within a group to opt-in and allow

+     * ballooning, so long as it is done consistently for a group (for instance

+     * if the device is an mdev device where it is known that the host vendor

+     * driver will never pin pages outside of the working set of the guest

+     * driver, which would thus not be ballooning candidates).

+     *

+     * The first opportunity to induce pinning occurs here where we attempt to

+     * attach the group to existing containers within the AddressSpace.  If any

+     * pages are already zapped from the virtual address space, such as from a

+     * previous ballooning opt-in, new pinning will cause valid mappings to be

+     * re-established.  Likewise, when the overall MemoryListener for a new

+     * container is registered, a replay of mappings within the AddressSpace

+     * will occur, re-establishing any previously zapped pages as well.

+     *

+     * NB. Balloon inhibiting does not currently block operation of the

+     * balloon driver or revoke previously pinned pages, it only prevents

+     * calling madvise to modify the virtual mapping of ballooned pages.

+     */

+    qemu_balloon_inhibit(true);

+

     QLIST_FOREACH(container, &container_list, next) {

         if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) {

             group->container = container;

@@ -3678,6 +3706,7 @@ static int vfio_connect_container(VFIOGroup *group)

     fd = qemu_open("/dev/vfio/vfio", O_RDWR);

     if (fd < 0) {

         error_report("vfio: failed to open /dev/vfio/vfio: %m");

+        qemu_balloon_inhibit(false);

         return -errno;

     }

@@ -3686,6 +3715,7 @@ static int vfio_connect_container(VFIOGroup *group)

         error_report("vfio: supported vfio version: %d, "

                      "reported version: %d", VFIO_API_VERSION, ret);

         close(fd);

+        qemu_balloon_inhibit(false);

         return -EINVAL;

     }

@@ -3701,6 +3731,7 @@ static int vfio_connect_container(VFIOGroup *group)

             error_report("vfio: failed to set group container: %m");

             g_free(container);

             close(fd);

+            qemu_balloon_inhibit(false);

             return -errno;

         }

@@ -3710,6 +3741,7 @@ static int vfio_connect_container(VFIOGroup *group)

             error_report("vfio: failed to set iommu for container: %m");

             g_free(container);

             close(fd);

+            qemu_balloon_inhibit(false);

             return -errno;

         }

@@ -3724,6 +3756,7 @@ static int vfio_connect_container(VFIOGroup *group)

             vfio_listener_release(container);

             g_free(container);

             close(fd);

+            qemu_balloon_inhibit(false);

             error_report("vfio: memory listener initialization failed for container\n");

             return ret;

         }

@@ -3734,6 +3767,7 @@ static int vfio_connect_container(VFIOGroup *group)

         error_report("vfio: No available IOMMU models");

         g_free(container);

         close(fd);

+        qemu_balloon_inhibit(false);

         return -EINVAL;

     }

@@ -3834,6 +3868,7 @@ static void vfio_put_group(VFIOGroup *group)

         return;

     }

+    qemu_balloon_inhibit(false);

     vfio_kvm_device_del_group(group);

     vfio_disconnect_container(group);

     QLIST_REMOVE(group, next);

-- 

1.8.3.1