[Qemu-devel] [PATCH v5 45/45] Inhibit ballooning during postcopy

[Dr. David Alan Gilbert (git)]

From: "Dr. David Alan Gilbert" <address@hidden>

The userfault mechanism used for postcopy generates faults
for us on pages that are 'not present', inflating a balloon in
the guest causes host pages to be marked as 'not present'; doing
this during a postcopy, as potentially the same pages were being
received from the source, would confuse the state of the received
page -> disable ballooning during postcopy.

When disabled we drop balloon requests from the guest.  Since ballooning
is generally initiated by the host, the management system should avoid
initiating any balloon instructions to the guest during migration,
although it's not possible to know how long it would take a guest to
process a request made prior to the start of migration.

Signed-off-by: Dr. David Alan Gilbert <address@hidden>
---
 balloon.c                  | 11 +++++++++++
 hw/virtio/virtio-balloon.c |  4 +++-
 include/sysemu/balloon.h   |  2 ++
 migration/postcopy-ram.c   |  9 +++++++++
 4 files changed, 25 insertions(+), 1 deletion(-)

diff --git a/balloon.c b/balloon.c
index dea19a4..faedb60 100644
--- a/balloon.c
+++ b/balloon.c
@@ -35,6 +35,17 @@
 static QEMUBalloonEvent *balloon_event_fn;
 static QEMUBalloonStatus *balloon_stat_fn;
 static void *balloon_opaque;
+static bool balloon_inhibited;
+
+bool qemu_balloon_is_inhibited(void)
+{
+    return balloon_inhibited;
+}
+
+void qemu_balloon_inhibit(bool state)
+{
+    balloon_inhibited = state;
+}
 
 static bool have_ballon(Error **errp)
 {
diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c
index 7bfbb75..b0e94ee 100644
--- a/hw/virtio/virtio-balloon.c
+++ b/hw/virtio/virtio-balloon.c
@@ -36,9 +36,11 @@
 static void balloon_page(void *addr, int deflate)
 {
 #if defined(__linux__)
-    if (!kvm_enabled() || kvm_has_sync_mmu())
+    if (!qemu_balloon_is_inhibited() && (!kvm_enabled() ||
+                                         kvm_has_sync_mmu())) {
         qemu_madvise(addr, TARGET_PAGE_SIZE,
                 deflate ? QEMU_MADV_WILLNEED : QEMU_MADV_DONTNEED);
+    }
 #endif
 }
 
diff --git a/include/sysemu/balloon.h b/include/sysemu/balloon.h
index 0345e01..6851d99 100644
--- a/include/sysemu/balloon.h
+++ b/include/sysemu/balloon.h
@@ -23,5 +23,7 @@ typedef void (QEMUBalloonStatus)(void *opaque, BalloonInfo 
*info);
 int qemu_add_balloon_handler(QEMUBalloonEvent *event_func,
                             QEMUBalloonStatus *stat_func, void *opaque);
 void qemu_remove_balloon_handler(void *opaque);
+bool qemu_balloon_is_inhibited(void);
+void qemu_balloon_inhibit(bool state);
 
 #endif
diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c
index d8f5ccd..b9f5848 100644
--- a/migration/postcopy-ram.c
+++ b/migration/postcopy-ram.c
@@ -24,6 +24,7 @@
 #include "migration/migration.h"
 #include "migration/postcopy-ram.h"
 #include "sysemu/sysemu.h"
+#include "sysemu/balloon.h"
 #include "qemu/bitmap.h"
 #include "qemu/error-report.h"
 #include "trace.h"
@@ -531,6 +532,8 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState 
*mis)
         mis->have_fault_thread = false;
     }
 
+    qemu_balloon_inhibit(false);
+
     if (enable_mlock) {
         if (os_mlock() < 0) {
             error_report("mlock: %s", strerror(errno));
@@ -780,6 +783,12 @@ int postcopy_ram_enable_notify(MigrationIncomingState *mis)
         return -1;
     }
 
+    /*
+     * Ballooning can mark pages as absent while we're postcopying
+     * that would cause false userfaults.
+     */
+    qemu_balloon_inhibit(true);
+
     trace_postcopy_ram_enable_notify();
 
     return 0;
-- 
2.1.0