All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Hildenbrand <david@redhat.com>
To: qemu-devel@nongnu.org
Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org,
	Richard Henderson <rth@twiddle.net>,
	Paolo Bonzini <pbonzini@redhat.com>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
	Eduardo Habkost <ehabkost@redhat.com>,
	"Michael S . Tsirkin" <mst@redhat.com>,
	David Hildenbrand <david@redhat.com>
Subject: [PATCH v4 20/21] virtio-mem: Exclude unplugged memory during migration
Date: Wed, 10 Jun 2020 13:54:18 +0200	[thread overview]
Message-ID: <20200610115419.51688-21-david@redhat.com> (raw)
In-Reply-To: <20200610115419.51688-1-david@redhat.com>

The content of unplugged memory is undefined and should not be migrated,
ever. Exclude all unplugged memory during precopy using the precopy notifier
infrastructure introduced for free page hinting in virtio-balloon.

Unplugged memory is marked as "not dirty", meaning it won't be
considered for migration.

Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 hw/virtio/virtio-mem.c         | 54 +++++++++++++++++++++++++++++++++-
 include/hw/virtio/virtio-mem.h |  3 ++
 2 files changed, 56 insertions(+), 1 deletion(-)

diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c
index 468fb4170f..21a23a3252 100644
--- a/hw/virtio/virtio-mem.c
+++ b/hw/virtio/virtio-mem.c
@@ -62,8 +62,14 @@ static bool virtio_mem_is_busy(void)
     /*
      * Postcopy cannot handle concurrent discards and we don't want to migrate
      * pages on-demand with stale content when plugging new blocks.
+     *
+     * For precopy, we don't want unplugged blocks in our migration stream, and
+     * when plugging new blocks, the page content might differ between source
+     * and destination (observable by the guest when not initializing pages
+     * after plugging them) until we're running on the destination (as we didn't
+     * migrate these blocks when they were unplugged).
      */
-    return migration_in_incoming_postcopy();
+    return migration_in_incoming_postcopy() || !migration_is_idle();
 }
 
 static bool virtio_mem_test_bitmap(VirtIOMEM *vmem, uint64_t start_gpa,
@@ -475,6 +481,7 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp)
     host_memory_backend_set_mapped(vmem->memdev, true);
     vmstate_register_ram(&vmem->memdev->mr, DEVICE(vmem));
     qemu_register_reset(virtio_mem_system_reset, vmem);
+    precopy_add_notifier(&vmem->precopy_notifier);
 }
 
 static void virtio_mem_device_unrealize(DeviceState *dev)
@@ -482,6 +489,7 @@ static void virtio_mem_device_unrealize(DeviceState *dev)
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VirtIOMEM *vmem = VIRTIO_MEM(dev);
 
+    precopy_remove_notifier(&vmem->precopy_notifier);
     qemu_unregister_reset(virtio_mem_system_reset, vmem);
     vmstate_unregister_ram(&vmem->memdev->mr, DEVICE(vmem));
     host_memory_backend_set_mapped(vmem->memdev, false);
@@ -756,12 +764,56 @@ static void virtio_mem_set_block_size(Object *obj, Visitor *v, const char *name,
     vmem->block_size = value;
 }
 
+static void virtio_mem_precopy_exclude_unplugged(VirtIOMEM *vmem)
+{
+    void * const host = qemu_ram_get_host_addr(vmem->memdev->mr.ram_block);
+    unsigned long first_zero_bit, last_zero_bit;
+    uint64_t offset, length;
+
+    /*
+     * Find consecutive unplugged blocks and exclude them from migration.
+     *
+     * Note: Blocks cannot get (un)plugged during precopy, no locking needed.
+     */
+    first_zero_bit = find_first_zero_bit(vmem->bitmap, vmem->bitmap_size);
+    while (first_zero_bit < vmem->bitmap_size) {
+        offset = first_zero_bit * vmem->block_size;
+        last_zero_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size,
+                                      first_zero_bit + 1) - 1;
+        length = (last_zero_bit - first_zero_bit + 1) * vmem->block_size;
+
+        qemu_guest_free_page_hint(host + offset, length);
+        first_zero_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size,
+                                            last_zero_bit + 2);
+    }
+}
+
+static int virtio_mem_precopy_notify(NotifierWithReturn *n, void *data)
+{
+    VirtIOMEM *vmem = container_of(n, VirtIOMEM, precopy_notifier);
+    PrecopyNotifyData *pnd = data;
+
+    switch (pnd->reason) {
+    case PRECOPY_NOTIFY_SETUP:
+        precopy_enable_free_page_optimization();
+        break;
+    case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC:
+        virtio_mem_precopy_exclude_unplugged(vmem);
+        break;
+    default:
+        break;
+    }
+
+    return 0;
+}
+
 static void virtio_mem_instance_init(Object *obj)
 {
     VirtIOMEM *vmem = VIRTIO_MEM(obj);
 
     vmem->block_size = VIRTIO_MEM_MIN_BLOCK_SIZE;
     notifier_list_init(&vmem->size_change_notifiers);
+    vmem->precopy_notifier.notify = virtio_mem_precopy_notify;
 
     object_property_add(obj, VIRTIO_MEM_SIZE_PROP, "size", virtio_mem_get_size,
                         NULL, NULL, NULL);
diff --git a/include/hw/virtio/virtio-mem.h b/include/hw/virtio/virtio-mem.h
index b74c77cd42..0778224964 100644
--- a/include/hw/virtio/virtio-mem.h
+++ b/include/hw/virtio/virtio-mem.h
@@ -67,6 +67,9 @@ typedef struct VirtIOMEM {
 
     /* notifiers to notify when "size" changes */
     NotifierList size_change_notifiers;
+
+    /* don't migrate unplugged memory */
+    NotifierWithReturn precopy_notifier;
 } VirtIOMEM;
 
 typedef struct VirtIOMEMClass {
-- 
2.26.2


WARNING: multiple messages have this Message-ID (diff)
From: David Hildenbrand <david@redhat.com>
To: qemu-devel@nongnu.org
Cc: Eduardo Habkost <ehabkost@redhat.com>,
	kvm@vger.kernel.org, "Michael S . Tsirkin" <mst@redhat.com>,
	David Hildenbrand <david@redhat.com>,
	"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
	qemu-s390x@nongnu.org, Paolo Bonzini <pbonzini@redhat.com>,
	Richard Henderson <rth@twiddle.net>
Subject: [PATCH v4 20/21] virtio-mem: Exclude unplugged memory during migration
Date: Wed, 10 Jun 2020 13:54:18 +0200	[thread overview]
Message-ID: <20200610115419.51688-21-david@redhat.com> (raw)
In-Reply-To: <20200610115419.51688-1-david@redhat.com>

The content of unplugged memory is undefined and should not be migrated,
ever. Exclude all unplugged memory during precopy using the precopy notifier
infrastructure introduced for free page hinting in virtio-balloon.

Unplugged memory is marked as "not dirty", meaning it won't be
considered for migration.

Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: "Dr. David Alan Gilbert" <dgilbert@redhat.com>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 hw/virtio/virtio-mem.c         | 54 +++++++++++++++++++++++++++++++++-
 include/hw/virtio/virtio-mem.h |  3 ++
 2 files changed, 56 insertions(+), 1 deletion(-)

diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c
index 468fb4170f..21a23a3252 100644
--- a/hw/virtio/virtio-mem.c
+++ b/hw/virtio/virtio-mem.c
@@ -62,8 +62,14 @@ static bool virtio_mem_is_busy(void)
     /*
      * Postcopy cannot handle concurrent discards and we don't want to migrate
      * pages on-demand with stale content when plugging new blocks.
+     *
+     * For precopy, we don't want unplugged blocks in our migration stream, and
+     * when plugging new blocks, the page content might differ between source
+     * and destination (observable by the guest when not initializing pages
+     * after plugging them) until we're running on the destination (as we didn't
+     * migrate these blocks when they were unplugged).
      */
-    return migration_in_incoming_postcopy();
+    return migration_in_incoming_postcopy() || !migration_is_idle();
 }
 
 static bool virtio_mem_test_bitmap(VirtIOMEM *vmem, uint64_t start_gpa,
@@ -475,6 +481,7 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp)
     host_memory_backend_set_mapped(vmem->memdev, true);
     vmstate_register_ram(&vmem->memdev->mr, DEVICE(vmem));
     qemu_register_reset(virtio_mem_system_reset, vmem);
+    precopy_add_notifier(&vmem->precopy_notifier);
 }
 
 static void virtio_mem_device_unrealize(DeviceState *dev)
@@ -482,6 +489,7 @@ static void virtio_mem_device_unrealize(DeviceState *dev)
     VirtIODevice *vdev = VIRTIO_DEVICE(dev);
     VirtIOMEM *vmem = VIRTIO_MEM(dev);
 
+    precopy_remove_notifier(&vmem->precopy_notifier);
     qemu_unregister_reset(virtio_mem_system_reset, vmem);
     vmstate_unregister_ram(&vmem->memdev->mr, DEVICE(vmem));
     host_memory_backend_set_mapped(vmem->memdev, false);
@@ -756,12 +764,56 @@ static void virtio_mem_set_block_size(Object *obj, Visitor *v, const char *name,
     vmem->block_size = value;
 }
 
+static void virtio_mem_precopy_exclude_unplugged(VirtIOMEM *vmem)
+{
+    void * const host = qemu_ram_get_host_addr(vmem->memdev->mr.ram_block);
+    unsigned long first_zero_bit, last_zero_bit;
+    uint64_t offset, length;
+
+    /*
+     * Find consecutive unplugged blocks and exclude them from migration.
+     *
+     * Note: Blocks cannot get (un)plugged during precopy, no locking needed.
+     */
+    first_zero_bit = find_first_zero_bit(vmem->bitmap, vmem->bitmap_size);
+    while (first_zero_bit < vmem->bitmap_size) {
+        offset = first_zero_bit * vmem->block_size;
+        last_zero_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size,
+                                      first_zero_bit + 1) - 1;
+        length = (last_zero_bit - first_zero_bit + 1) * vmem->block_size;
+
+        qemu_guest_free_page_hint(host + offset, length);
+        first_zero_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size,
+                                            last_zero_bit + 2);
+    }
+}
+
+static int virtio_mem_precopy_notify(NotifierWithReturn *n, void *data)
+{
+    VirtIOMEM *vmem = container_of(n, VirtIOMEM, precopy_notifier);
+    PrecopyNotifyData *pnd = data;
+
+    switch (pnd->reason) {
+    case PRECOPY_NOTIFY_SETUP:
+        precopy_enable_free_page_optimization();
+        break;
+    case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC:
+        virtio_mem_precopy_exclude_unplugged(vmem);
+        break;
+    default:
+        break;
+    }
+
+    return 0;
+}
+
 static void virtio_mem_instance_init(Object *obj)
 {
     VirtIOMEM *vmem = VIRTIO_MEM(obj);
 
     vmem->block_size = VIRTIO_MEM_MIN_BLOCK_SIZE;
     notifier_list_init(&vmem->size_change_notifiers);
+    vmem->precopy_notifier.notify = virtio_mem_precopy_notify;
 
     object_property_add(obj, VIRTIO_MEM_SIZE_PROP, "size", virtio_mem_get_size,
                         NULL, NULL, NULL);
diff --git a/include/hw/virtio/virtio-mem.h b/include/hw/virtio/virtio-mem.h
index b74c77cd42..0778224964 100644
--- a/include/hw/virtio/virtio-mem.h
+++ b/include/hw/virtio/virtio-mem.h
@@ -67,6 +67,9 @@ typedef struct VirtIOMEM {
 
     /* notifiers to notify when "size" changes */
     NotifierList size_change_notifiers;
+
+    /* don't migrate unplugged memory */
+    NotifierWithReturn precopy_notifier;
 } VirtIOMEM;
 
 typedef struct VirtIOMEMClass {
-- 
2.26.2



  parent reply	other threads:[~2020-06-10 11:56 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-10 11:53 [PATCH v4 00/21] virtio-mem: Paravirtualized memory hot(un)plug David Hildenbrand
2020-06-10 11:53 ` David Hildenbrand
2020-06-10 11:53 ` [PATCH v4 01/21] exec: Introduce ram_block_discard_(disable|require)() David Hildenbrand
2020-06-10 11:53   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 02/21] vfio: Convert to ram_block_discard_disable() David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 13:04   ` Tony Krowiak
2020-06-10 13:04     ` Tony Krowiak
2020-06-10 14:13     ` David Hildenbrand
2020-06-10 14:13       ` David Hildenbrand
2020-06-16 11:15   ` Cornelia Huck
2020-06-16 11:15     ` Cornelia Huck
2020-06-10 11:54 ` [PATCH v4 03/21] accel/kvm: " David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 04/21] s390x/pv: " David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-16 11:17   ` Cornelia Huck
2020-06-16 11:17     ` Cornelia Huck
2020-06-10 11:54 ` [PATCH v4 05/21] virtio-balloon: Rip out qemu_balloon_inhibit() David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-16 10:56   ` Dr. David Alan Gilbert
2020-06-16 10:56     ` Dr. David Alan Gilbert
2020-06-24 15:32   ` Michael S. Tsirkin
2020-06-24 15:32     ` Michael S. Tsirkin
2020-06-10 11:54 ` [PATCH v4 06/21] target/i386: sev: Use ram_block_discard_disable() David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 07/21] migration/rdma: " David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 08/21] migration/colo: " David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 09/21] linux-headers: update to contain virtio-mem David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 10/21] virtio-mem: Paravirtualized memory hot(un)plug David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 11/21] virtio-pci: Proxy for virtio-mem David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 12/21] MAINTAINERS: Add myself as virtio-mem maintainer David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 13/21] hmp: Handle virtio-mem when printing memory device info David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-17 17:53   ` Dr. David Alan Gilbert
2020-06-17 17:53     ` Dr. David Alan Gilbert
2020-06-17 17:54   ` Dr. David Alan Gilbert
2020-06-17 17:54     ` Dr. David Alan Gilbert
2020-06-10 11:54 ` [PATCH v4 14/21] numa: Handle virtio-mem in NUMA stats David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 15/21] pc: Support for virtio-mem-pci David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 16/21] virtio-mem: Allow notifiers for size changes David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 17/21] virtio-pci: Send qapi events when the virtio-mem " David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 18/21] virtio-mem: Migration sanity checks David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-17 17:59   ` Dr. David Alan Gilbert
2020-06-17 17:59     ` Dr. David Alan Gilbert
2020-06-18 10:39     ` David Hildenbrand
2020-06-18 10:39       ` David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 19/21] virtio-mem: Add trace events David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-10 11:54 ` David Hildenbrand [this message]
2020-06-10 11:54   ` [PATCH v4 20/21] virtio-mem: Exclude unplugged memory during migration David Hildenbrand
2020-06-10 11:54 ` [PATCH v4 21/21] numa: Auto-enable NUMA when any memory devices are possible David Hildenbrand
2020-06-10 11:54   ` David Hildenbrand
2020-06-24 15:33 ` [PATCH v4 00/21] virtio-mem: Paravirtualized memory hot(un)plug Michael S. Tsirkin
2020-06-24 15:33   ` Michael S. Tsirkin
2020-06-24 15:40   ` David Hildenbrand
2020-06-24 15:40     ` David Hildenbrand

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200610115419.51688-21-david@redhat.com \
    --to=david@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=ehabkost@redhat.com \
    --cc=kvm@vger.kernel.org \
    --cc=mst@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=qemu-devel@nongnu.org \
    --cc=qemu-s390x@nongnu.org \
    --cc=rth@twiddle.net \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.