QEMU-Devel Archive on lore.kernel.org
 help / color / Atom feed
From: Kirti Wankhede <kwankhede@nvidia.com>
To: <alex.williamson@redhat.com>, <cjia@nvidia.com>
Cc: Zhengxiao.zx@Alibaba-inc.com, kevin.tian@intel.com,
	yi.l.liu@intel.com, yan.y.zhao@intel.com, eskultet@redhat.com,
	ziye.yang@intel.com, qemu-devel@nongnu.org, cohuck@redhat.com,
	shuangtai.tst@alibaba-inc.com, dgilbert@redhat.com,
	zhi.a.wang@intel.com, mlevitsk@redhat.com, pasic@linux.ibm.com,
	aik@ozlabs.ru, Kirti Wankhede <kwankhede@nvidia.com>,
	eauger@redhat.com, felipe@nutanix.com,
	jonathan.davies@nutanix.com, changpeng.liu@intel.com,
	Ken.Xue@amd.com
Subject: [PATCH v16 QEMU 15/16] vfio: Add ioctl to get dirty pages bitmap during dma unmap.
Date: Wed, 25 Mar 2020 02:39:13 +0530
Message-ID: <1585084154-29461-16-git-send-email-kwankhede@nvidia.com> (raw)
In-Reply-To: <1585084154-29461-1-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.

Note: This patch is not yet tested. I'm trying to see how I can test this code
path.

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              | 83 ++++++++++++++++++++++++++++++++++++++++---
 include/hw/vfio/vfio-common.h |  1 +
 2 files changed, 80 insertions(+), 4 deletions(-)

diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 6d41e1ac5c2f..e0f91841bc82 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -311,11 +311,77 @@ static bool vfio_devices_are_stopped_and_saving(void)
     return true;
 }
 
+static bool vfio_devices_are_running_and_saving(void)
+{
+    VFIOGroup *group;
+    VFIODevice *vbasedev;
+
+    QLIST_FOREACH(group, &vfio_group_list, next) {
+        QLIST_FOREACH(vbasedev, &group->device_list, next) {
+            if ((vbasedev->device_state & VFIO_DEVICE_STATE_SAVING) &&
+                (vbasedev->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));
+    if (!unmap) {
+        return -ENOMEM;
+    }
+
+    unmap->argsz = sizeof(*unmap) + sizeof(*bitmap);
+    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, 64) / 8;
+    bitmap->data = g_malloc0(bitmap->size);
+    if (!bitmap->data) {
+        error_report("UNMAP: Error allocating bitmap of size 0x%llx",
+                     bitmap->size);
+        g_free(unmap);
+        return -ENOMEM;
+    }
+
+    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 : %d", -errno);
+    }
+
+    g_free(bitmap->data);
+    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),
@@ -324,6 +390,11 @@ static int vfio_dma_unmap(VFIOContainer *container,
         .size = size,
     };
 
+    if (iotlb && container->dirty_pages_supported &&
+        vfio_devices_are_running_and_saving()) {
+        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
@@ -371,7 +442,7 @@ 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;
     }
@@ -519,7 +590,7 @@ 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)",
@@ -822,7 +893,7 @@ 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)",
@@ -1479,6 +1550,7 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
     container->space = space;
     container->fd = fd;
     container->error = NULL;
+    container->dirty_pages_supported = false;
     QLIST_INIT(&container->giommu_list);
     QLIST_INIT(&container->hostwin_list);
 
@@ -1509,6 +1581,9 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as,
         }
         vfio_host_win_add(container, 0, (hwaddr)-1, info.iova_pgsizes);
         container->pgsizes = info.iova_pgsizes;
+        if (info.flags & VFIO_IOMMU_INFO_DIRTY_PGS) {
+            container->dirty_pages_supported = true;
+        }
         break;
     }
     case VFIO_SPAPR_TCE_v2_IOMMU:
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index c78033e4149d..8ab741463d50 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -79,6 +79,7 @@ typedef struct VFIOContainer {
     unsigned iommu_type;
     Error *error;
     bool initialized;
+    bool dirty_pages_supported;
     unsigned long pgsizes;
     QLIST_HEAD(, VFIOGuestIOMMU) giommu_list;
     QLIST_HEAD(, VFIOHostDMAWindow) hostwin_list;
-- 
2.7.0



  parent reply index

Thread overview: 74+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-24 21:08 [PATCH v16 QEMU 00/16] Add migration support for VFIO devices Kirti Wankhede
2020-03-24 21:08 ` [PATCH v16 QEMU 01/16] vfio: KABI for migration interface - Kernel header placeholder Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 02/16] vfio: Add function to unmap VFIO region Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 03/16] vfio: Add vfio_get_object callback to VFIODeviceOps Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 04/16] vfio: Add save and load functions for VFIO PCI devices Kirti Wankhede
2020-03-25 19:56   ` Alex Williamson
2020-03-26 17:29     ` Dr. David Alan Gilbert
2020-03-26 17:38       ` Alex Williamson
2020-05-04 23:18     ` Kirti Wankhede
2020-05-05  4:37       ` Alex Williamson
2020-05-06  6:11         ` Yan Zhao
2020-05-06 19:48           ` Kirti Wankhede
2020-05-06 20:03             ` Alex Williamson
2020-05-07  5:40               ` Kirti Wankhede
2020-05-07 18:14                 ` Alex Williamson
2020-03-26 17:46   ` Dr. David Alan Gilbert
2020-05-04 23:19     ` Kirti Wankhede
2020-04-07  4:10   ` Longpeng (Mike, Cloud Infrastructure Service Product Dept.)
2020-05-04 23:21     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 05/16] vfio: Add migration region initialization and finalize function Kirti Wankhede
2020-03-26 17:52   ` Dr. David Alan Gilbert
2020-05-04 23:19     ` Kirti Wankhede
2020-05-19 19:32       ` Dr. David Alan Gilbert
2020-03-24 21:09 ` [PATCH v16 QEMU 06/16] vfio: Add VM state change handler to know state of VM Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 07/16] vfio: Add migration state change notifier Kirti Wankhede
2020-04-01 11:27   ` Dr. David Alan Gilbert
2020-05-04 23:20     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 08/16] vfio: Register SaveVMHandlers for VFIO device Kirti Wankhede
2020-03-25 21:02   ` Alex Williamson
2020-05-04 23:19     ` Kirti Wankhede
2020-05-05  4:37       ` Alex Williamson
2020-05-06  6:38         ` Yan Zhao
2020-05-06  9:58           ` Cornelia Huck
2020-05-06 16:53             ` Dr. David Alan Gilbert
2020-05-06 19:30               ` Kirti Wankhede
2020-05-07  6:37                 ` Cornelia Huck
2020-05-07 20:29                 ` Alex Williamson
2020-04-01 17:36   ` Dr. David Alan Gilbert
2020-05-04 23:20     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 09/16] vfio: Add save state functions to SaveVMHandlers Kirti Wankhede
2020-03-25 22:03   ` Alex Williamson
2020-05-04 23:18     ` Kirti Wankhede
2020-05-05  4:37       ` Alex Williamson
2020-05-11  9:53         ` Kirti Wankhede
2020-05-11 15:59           ` Alex Williamson
2020-05-12  2:06           ` Yan Zhao
2020-05-09  5:31   ` Yan Zhao
2020-05-11 10:22     ` Kirti Wankhede
2020-05-12  0:50       ` Yan Zhao
2020-03-24 21:09 ` [PATCH v16 QEMU 10/16] vfio: Add load " Kirti Wankhede
2020-03-25 22:36   ` Alex Williamson
2020-04-01 18:58   ` Dr. David Alan Gilbert
2020-05-04 23:20     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 11/16] iommu: add callback to get address limit IOMMU supports Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 12/16] memory: Set DIRTY_MEMORY_MIGRATION when IOMMU is enabled Kirti Wankhede
2020-04-01 19:00   ` Dr. David Alan Gilbert
2020-04-01 19:42     ` Alex Williamson
2020-03-24 21:09 ` [PATCH v16 QEMU 13/16] vfio: Add function to start and stop dirty pages tracking Kirti Wankhede
2020-03-26 19:10   ` Alex Williamson
2020-05-04 23:20     ` Kirti Wankhede
2020-04-01 19:03   ` Dr. David Alan Gilbert
2020-05-04 23:21     ` Kirti Wankhede
2020-03-24 21:09 ` [PATCH v16 QEMU 14/16] vfio: Add vfio_listener_log_sync to mark dirty pages Kirti Wankhede
2020-03-25  2:19   ` Yan Zhao
2020-03-26 19:46   ` Alex Williamson
2020-04-01 19:08     ` Dr. David Alan Gilbert
2020-04-01  5:50   ` Yan Zhao
2020-04-03 20:11     ` Kirti Wankhede
2020-03-24 21:09 ` Kirti Wankhede [this message]
2020-03-24 21:09 ` [PATCH v16 QEMU 16/16] vfio: Make vfio-pci device migration capable Kirti Wankhede
2020-03-24 23:36 ` [PATCH v16 QEMU 00/16] Add migration support for VFIO devices no-reply
2020-03-31 18:34 ` Alex Williamson
2020-04-01  6:41   ` Yan Zhao
2020-04-01 18:34     ` 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=1585084154-29461-16-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=changpeng.liu@intel.com \
    --cc=cjia@nvidia.com \
    --cc=cohuck@redhat.com \
    --cc=dgilbert@redhat.com \
    --cc=eauger@redhat.com \
    --cc=eskultet@redhat.com \
    --cc=felipe@nutanix.com \
    --cc=jonathan.davies@nutanix.com \
    --cc=kevin.tian@intel.com \
    --cc=mlevitsk@redhat.com \
    --cc=pasic@linux.ibm.com \
    --cc=qemu-devel@nongnu.org \
    --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=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

QEMU-Devel Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/qemu-devel/0 qemu-devel/git/0.git
	git clone --mirror https://lore.kernel.org/qemu-devel/1 qemu-devel/git/1.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 qemu-devel qemu-devel/ https://lore.kernel.org/qemu-devel \
		qemu-devel@nongnu.org
	public-inbox-index qemu-devel

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.nongnu.qemu-devel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git