From: Kirti Wankhede <kwankhede@nvidia.com>
To: <alex.williamson@redhat.com>, <cjia@nvidia.com>
Cc: cohuck@redhat.com, zhi.wang.linux@gmail.com, aik@ozlabs.ru,
Zhengxiao.zx@Alibaba-inc.com, shuangtai.tst@alibaba-inc.com,
qemu-devel@nongnu.org, peterx@redhat.com,
Kirti Wankhede <kwankhede@nvidia.com>,
eauger@redhat.com, yi.l.liu@intel.com, quintela@redhat.com,
ziye.yang@intel.com, armbru@redhat.com, mlevitsk@redhat.com,
pasic@linux.ibm.com, felipe@nutanix.com, zhi.a.wang@intel.com,
mcrossley@nvidia.com, kevin.tian@intel.com, yan.y.zhao@intel.com,
dgilbert@redhat.com, changpeng.liu@intel.com,
eskultet@redhat.com, Ken.Xue@amd.com,
jonathan.davies@nutanix.com, pbonzini@redhat.com,
dnigam@nvidia.com
Subject: [PATCH v27 15/17] vfio: Add ioctl to get dirty pages bitmap during dma unmap
Date: Thu, 22 Oct 2020 16:42:05 +0530 [thread overview]
Message-ID: <1603365127-14202-16-git-send-email-kwankhede@nvidia.com> (raw)
In-Reply-To: <1603365127-14202-1-git-send-email-kwankhede@nvidia.com>
With vIOMMU, IO virtual address range can get unmapped while in pre-copy
phase of migration. In that case, unmap ioctl should return pages pinned
in that range and QEMU should find its correcponding guest physical
addresses and report those dirty.
Suggested-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Kirti Wankhede <kwankhede@nvidia.com>
Reviewed-by: Neo Jia <cjia@nvidia.com>
---
hw/vfio/common.c | 96 +++++++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 92 insertions(+), 4 deletions(-)
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 98c2b1f9b190..9c879e5c0f62 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -321,11 +321,94 @@ static bool vfio_devices_all_stopped_and_saving(VFIOContainer *container)
return true;
}
+static bool vfio_devices_all_running_and_saving(VFIOContainer *container)
+{
+ VFIOGroup *group;
+ VFIODevice *vbasedev;
+ MigrationState *ms = migrate_get_current();
+
+ if (!migration_is_setup_or_active(ms->state)) {
+ return false;
+ }
+
+ QLIST_FOREACH(group, &container->group_list, container_next) {
+ QLIST_FOREACH(vbasedev, &group->device_list, next) {
+ VFIOMigration *migration = vbasedev->migration;
+
+ if (!migration) {
+ return false;
+ }
+
+ if ((migration->device_state & VFIO_DEVICE_STATE_SAVING) &&
+ (migration->device_state & VFIO_DEVICE_STATE_RUNNING)) {
+ continue;
+ } else {
+ return false;
+ }
+ }
+ }
+ return true;
+}
+
+static int vfio_dma_unmap_bitmap(VFIOContainer *container,
+ hwaddr iova, ram_addr_t size,
+ IOMMUTLBEntry *iotlb)
+{
+ struct vfio_iommu_type1_dma_unmap *unmap;
+ struct vfio_bitmap *bitmap;
+ uint64_t pages = TARGET_PAGE_ALIGN(size) >> TARGET_PAGE_BITS;
+ int ret;
+
+ unmap = g_malloc0(sizeof(*unmap) + sizeof(*bitmap));
+
+ unmap->argsz = sizeof(*unmap) + sizeof(*bitmap);
+ unmap->iova = iova;
+ unmap->size = size;
+ unmap->flags |= VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP;
+ bitmap = (struct vfio_bitmap *)&unmap->data;
+
+ /*
+ * cpu_physical_memory_set_dirty_lebitmap() expects pages in bitmap of
+ * TARGET_PAGE_SIZE to mark those dirty. Hence set bitmap_pgsize to
+ * TARGET_PAGE_SIZE.
+ */
+
+ bitmap->pgsize = TARGET_PAGE_SIZE;
+ bitmap->size = ROUND_UP(pages, sizeof(__u64) * BITS_PER_BYTE) /
+ BITS_PER_BYTE;
+
+ if (bitmap->size > container->max_dirty_bitmap_size) {
+ error_report("UNMAP: Size of bitmap too big 0x%llx", bitmap->size);
+ ret = -E2BIG;
+ goto unmap_exit;
+ }
+
+ bitmap->data = g_try_malloc0(bitmap->size);
+ if (!bitmap->data) {
+ ret = -ENOMEM;
+ goto unmap_exit;
+ }
+
+ ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
+ if (!ret) {
+ cpu_physical_memory_set_dirty_lebitmap((uint64_t *)bitmap->data,
+ iotlb->translated_addr, pages);
+ } else {
+ error_report("VFIO_UNMAP_DMA with DIRTY_BITMAP : %m");
+ }
+
+ g_free(bitmap->data);
+unmap_exit:
+ g_free(unmap);
+ return ret;
+}
+
/*
* DMA - Mapping and unmapping for the "type1" IOMMU interface used on x86
*/
static int vfio_dma_unmap(VFIOContainer *container,
- hwaddr iova, ram_addr_t size)
+ hwaddr iova, ram_addr_t size,
+ IOMMUTLBEntry *iotlb)
{
struct vfio_iommu_type1_dma_unmap unmap = {
.argsz = sizeof(unmap),
@@ -334,6 +417,11 @@ static int vfio_dma_unmap(VFIOContainer *container,
.size = size,
};
+ if (iotlb && container->dirty_pages_supported &&
+ vfio_devices_all_running_and_saving(container)) {
+ return vfio_dma_unmap_bitmap(container, iova, size, iotlb);
+ }
+
while (ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
/*
* The type1 backend has an off-by-one bug in the kernel (71a7d3d78e3c
@@ -381,7 +469,7 @@ static int vfio_dma_map(VFIOContainer *container, hwaddr iova,
* the VGA ROM space.
*/
if (ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0 ||
- (errno == EBUSY && vfio_dma_unmap(container, iova, size) == 0 &&
+ (errno == EBUSY && vfio_dma_unmap(container, iova, size, NULL) == 0 &&
ioctl(container->fd, VFIO_IOMMU_MAP_DMA, &map) == 0)) {
return 0;
}
@@ -531,7 +619,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb)
iotlb->addr_mask + 1, vaddr, ret);
}
} else {
- ret = vfio_dma_unmap(container, iova, iotlb->addr_mask + 1);
+ ret = vfio_dma_unmap(container, iova, iotlb->addr_mask + 1, iotlb);
if (ret) {
error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx") = %d (%m)",
@@ -834,7 +922,7 @@ static void vfio_listener_region_del(MemoryListener *listener,
}
if (try_unmap) {
- ret = vfio_dma_unmap(container, iova, int128_get64(llsize));
+ ret = vfio_dma_unmap(container, iova, int128_get64(llsize), NULL);
if (ret) {
error_report("vfio_dma_unmap(%p, 0x%"HWADDR_PRIx", "
"0x%"HWADDR_PRIx") = %d (%m)",
--
2.7.0
next prev parent reply other threads:[~2020-10-22 12:11 UTC|newest]
Thread overview: 36+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-10-22 11:11 [PATCH v27 00/17] Add migration support for VFIO devices Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 01/17] vfio: Add function to unmap VFIO region Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 02/17] vfio: Add vfio_get_object callback to VFIODeviceOps Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 03/17] vfio: Add save and load functions for VFIO PCI devices Kirti Wankhede
2020-10-22 14:06 ` Alex Williamson
2020-10-22 15:52 ` Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 04/17] vfio: Add migration region initialization and finalize function Kirti Wankhede
2020-10-22 14:22 ` Alex Williamson
2020-10-22 16:16 ` Kirti Wankhede
2020-10-23 11:17 ` Cornelia Huck
2020-10-22 11:11 ` [PATCH v27 05/17] vfio: Add VM state change handler to know state of VM Kirti Wankhede
2020-10-22 16:35 ` Alex Williamson
2020-10-22 17:41 ` Kirti Wankhede
2020-10-22 18:29 ` Alex Williamson
2020-10-22 11:11 ` [PATCH v27 06/17] vfio: Add migration state change notifier Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 07/17] vfio: Register SaveVMHandlers for VFIO device Kirti Wankhede
2020-10-22 18:51 ` Alex Williamson
2020-10-23 7:12 ` Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 08/17] vfio: Add save state functions to SaveVMHandlers Kirti Wankhede
2020-10-22 11:11 ` [PATCH v27 09/17] vfio: Add load " Kirti Wankhede
2020-10-22 19:50 ` Alex Williamson
2020-10-23 9:59 ` Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 10/17] memory: Set DIRTY_MEMORY_MIGRATION when IOMMU is enabled Kirti Wankhede
2020-10-22 19:52 ` Alex Williamson
2020-10-22 11:12 ` [PATCH v27 11/17] vfio: Get migration capability flags for container Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 12/17] vfio: Add function to start and stop dirty pages tracking Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 13/17] vfio: Add vfio_listener_log_sync to mark dirty pages Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 14/17] vfio: Dirty page tracking when vIOMMU is enabled Kirti Wankhede
2020-10-22 20:37 ` Alex Williamson
2020-10-23 7:55 ` Kirti Wankhede
2020-10-22 11:12 ` Kirti Wankhede [this message]
2020-10-22 11:12 ` [PATCH v27 16/17] vfio: Make vfio-pci device migration capable Kirti Wankhede
2020-10-22 11:12 ` [PATCH v27 17/17] qapi: Add VFIO devices migration stats in Migration stats Kirti Wankhede
2020-10-22 22:18 ` Alex Williamson
2020-10-23 10:21 ` Kirti Wankhede
2020-10-22 21:28 ` [PATCH v27 00/17] Add migration support for VFIO devices Alex Williamson
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=1603365127-14202-16-git-send-email-kwankhede@nvidia.com \
--to=kwankhede@nvidia.com \
--cc=Ken.Xue@amd.com \
--cc=Zhengxiao.zx@Alibaba-inc.com \
--cc=aik@ozlabs.ru \
--cc=alex.williamson@redhat.com \
--cc=armbru@redhat.com \
--cc=changpeng.liu@intel.com \
--cc=cjia@nvidia.com \
--cc=cohuck@redhat.com \
--cc=dgilbert@redhat.com \
--cc=dnigam@nvidia.com \
--cc=eauger@redhat.com \
--cc=eskultet@redhat.com \
--cc=felipe@nutanix.com \
--cc=jonathan.davies@nutanix.com \
--cc=kevin.tian@intel.com \
--cc=mcrossley@nvidia.com \
--cc=mlevitsk@redhat.com \
--cc=pasic@linux.ibm.com \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=quintela@redhat.com \
--cc=shuangtai.tst@alibaba-inc.com \
--cc=yan.y.zhao@intel.com \
--cc=yi.l.liu@intel.com \
--cc=zhi.a.wang@intel.com \
--cc=zhi.wang.linux@gmail.com \
--cc=ziye.yang@intel.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).