[PATCH RFC 18/19] vfio-user: migration support

[Elena Ufimtseva]

From: John G Johnson <john.g.johnson@oracle.com>

Send migration region operations to remote server.
Send VFIO_USER_USER_DIRTY_PAGES to get remote dirty bitmap.

Signed-off-by: John G Johnson <john.g.johnson@oracle.com>
Signed-off-by: Elena Ufimtseva <elena.ufimtseva@oracle.com>
Signed-off-by: Jagannathan Raman <jag.raman@oracle.com>
---
 hw/vfio/user.h      | 17 +++++++++++++++
 hw/vfio/common.c    | 51 ++++++++++++++++++++++++++++++++++++---------
 hw/vfio/migration.c | 35 ++++++++++++++++++-------------
 hw/vfio/pci.c       |  7 +++++++
 hw/vfio/user.c      | 45 +++++++++++++++++++++++++++++++++++++++
 5 files changed, 130 insertions(+), 25 deletions(-)

diff --git a/hw/vfio/user.h b/hw/vfio/user.h
index 95c2fb1707..eeb328c0a9 100644
--- a/hw/vfio/user.h
+++ b/hw/vfio/user.h
@@ -230,6 +230,20 @@ struct vfio_user_irq_set {
     uint32_t count;
 };
 
+/* imported from struct vfio_iommu_type1_dirty_bitmap_get */
+struct vfio_user_bitmap_range {
+    uint64_t iova;
+    uint64_t size;
+    struct vfio_user_bitmap bitmap;
+};
+
+/* imported from struct vfio_iommu_type1_dirty_bitmap */
+struct vfio_user_dirty_pages {
+    vfio_user_hdr_t hdr;
+    uint32_t argsz;
+    uint32_t flags;
+};
+
 void vfio_user_recv(void *opaque);
 void vfio_user_send_reply(VFIOProxy *proxy, char *buf, int ret);
 VFIOProxy *vfio_user_connect_dev(char *sockname, Error **errp);
@@ -255,4 +269,7 @@ void vfio_user_set_reqhandler(VFIODevice *vbasdev,
                                              void *reqarg);
 int vfio_user_set_irqs(VFIODevice *vbasedev, struct vfio_irq_set *irq);
 void vfio_user_reset(VFIODevice *vbasedev);
+int vfio_user_dirty_bitmap(VFIOProxy *proxy,
+                           struct vfio_iommu_type1_dirty_bitmap *bitmap,
+                           struct vfio_iommu_type1_dirty_bitmap_get *range);
 #endif /* VFIO_USER_H */
diff --git a/hw/vfio/common.c b/hw/vfio/common.c
index 953d9e7b55..bd31731c0f 100644
--- a/hw/vfio/common.c
+++ b/hw/vfio/common.c
@@ -460,7 +460,11 @@ static int vfio_dma_unmap_bitmap(VFIOContainer *container,
         goto unmap_exit;
     }
 
-    ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
+    if (container->proxy != NULL) {
+        ret = vfio_user_dma_unmap(container->proxy, unmap, bitmap);
+    } else {
+        ret = ioctl(container->fd, VFIO_IOMMU_UNMAP_DMA, unmap);
+    }
     if (!ret) {
         cpu_physical_memory_set_dirty_lebitmap((unsigned long *)bitmap->data,
                 iotlb->translated_addr, pages);
@@ -1278,10 +1282,19 @@ static void vfio_set_dirty_page_tracking(VFIOContainer 
*container, bool start)
         dirty.flags = VFIO_IOMMU_DIRTY_PAGES_FLAG_STOP;
     }
 
-    ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty);
-    if (ret) {
-        error_report("Failed to set dirty tracking flag 0x%x errno: %d",
-                     dirty.flags, errno);
+    if (container->proxy != NULL) {
+        ret = vfio_user_dirty_bitmap(container->proxy, &dirty, NULL);
+        if (ret) {
+            error_report("Failed to set dirty tracking flag 0x%x errno: %d",
+                         dirty.flags, -ret);
+        }
+    } else {
+        ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, &dirty);
+        if (ret) {
+            error_report("Failed to set dirty tracking flag 0x%x errno: %d",
+                         dirty.flags, errno);
+            ret = -errno;
+        }
     }
 }
 
@@ -1331,7 +1344,11 @@ static int vfio_get_dirty_bitmap(VFIOContainer 
*container, uint64_t iova,
         goto err_out;
     }
 
-    ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap);
+    if (container->proxy != NULL) {
+        ret = vfio_user_dirty_bitmap(container->proxy, dbitmap, range);
+    } else {
+        ret = ioctl(container->fd, VFIO_IOMMU_DIRTY_PAGES, dbitmap);
+    }
     if (ret) {
         error_report("Failed to get dirty bitmap for iova: 0x%"PRIx64
                 " size: 0x%"PRIx64" err: %d", (uint64_t)range->iova,
@@ -2282,6 +2299,12 @@ void vfio_connect_proxy(VFIOProxy *proxy, VFIOGroup 
*group, AddressSpace *as)
     VFIOAddressSpace *space;
     VFIOContainer *container;
 
+    if (QLIST_EMPTY(&vfio_group_list)) {
+        qemu_register_reset(vfio_reset_handler, NULL);
+    }
+
+    QLIST_INSERT_HEAD(&vfio_group_list, group, next);
+
     /*
      * try to mirror vfio_connect_container()
      * as much as possible
@@ -2292,18 +2315,26 @@ void vfio_connect_proxy(VFIOProxy *proxy, VFIOGroup 
*group, AddressSpace *as)
     container = g_malloc0(sizeof(*container));
     container->space = space;
     container->fd = -1;
+    QLIST_INIT(&container->giommu_list);
     QLIST_INIT(&container->hostwin_list);
     container->proxy = proxy;
 
+    /*
+     * The proxy uses a SW IOMMU in lieu of the HW one
+     * used in the ioctl() version.  Use TYPE1 with the
+     * target's page size for maximum capatibility
+     */
     container->iommu_type = VFIO_TYPE1_IOMMU;
-    vfio_host_win_add(container, 0, (hwaddr)-1, 4096);
-    container->pgsizes = 4096;
+    vfio_host_win_add(container, 0, (hwaddr)-1, TARGET_PAGE_SIZE);
+    container->pgsizes = TARGET_PAGE_SIZE;
+
+    container->dirty_pages_supported = true;
+    container->max_dirty_bitmap_size = VFIO_USER_DEF_MAX_XFER;
+    container->dirty_pgsizes = TARGET_PAGE_SIZE;
 
     QLIST_INIT(&container->group_list);
     QLIST_INSERT_HEAD(&space->containers, container, next);
 
-    QLIST_INIT(&container->giommu_list);
-
     group->container = container;
     QLIST_INSERT_HEAD(&container->group_list, group, container_next);
 
diff --git a/hw/vfio/migration.c b/hw/vfio/migration.c
index 82f654afb6..8005b1171a 100644
--- a/hw/vfio/migration.c
+++ b/hw/vfio/migration.c
@@ -27,6 +27,7 @@
 #include "pci.h"
 #include "trace.h"
 #include "hw/hw.h"
+#include "user.h"
 
 /*
  * Flags to be used as unique delimiters for VFIO devices in the migration
@@ -49,10 +50,18 @@ static int64_t bytes_transferred;
 static inline int vfio_mig_access(VFIODevice *vbasedev, void *val, int count,
                                   off_t off, bool iswrite)
 {
+    VFIORegion *region = &vbasedev->migration->region;
     int ret;
 
-    ret = iswrite ? pwrite(vbasedev->fd, val, count, off) :
-                    pread(vbasedev->fd, val, count, off);
+    if (vbasedev->proxy != NULL) {
+        ret = iswrite ?
+            vfio_user_region_write(vbasedev, region->nr, off, count, val) :
+            vfio_user_region_read(vbasedev, region->nr, off, count, val);
+    } else {
+        off += region->fd_offset;
+        ret = iswrite ? pwrite(vbasedev->fd, val, count, off) :
+                        pread(vbasedev->fd, val, count, off);
+    }
     if (ret < count) {
         error_report("vfio_mig_%s %d byte %s: failed at offset 0x%"
                      HWADDR_PRIx", err: %s", iswrite ? "write" : "read", count,
@@ -111,9 +120,7 @@ static int vfio_migration_set_state(VFIODevice *vbasedev, 
uint32_t mask,
                                     uint32_t value)
 {
     VFIOMigration *migration = vbasedev->migration;
-    VFIORegion *region = &migration->region;
-    off_t dev_state_off = region->fd_offset +
-                          VFIO_MIG_STRUCT_OFFSET(device_state);
+    off_t dev_state_off = VFIO_MIG_STRUCT_OFFSET(device_state);
     uint32_t device_state;
     int ret;
 
@@ -201,13 +208,13 @@ static int vfio_save_buffer(QEMUFile *f, VFIODevice 
*vbasedev, uint64_t *size)
     int ret;
 
     ret = vfio_mig_read(vbasedev, &data_offset, sizeof(data_offset),
-                      region->fd_offset + VFIO_MIG_STRUCT_OFFSET(data_offset));
+                        VFIO_MIG_STRUCT_OFFSET(data_offset));
     if (ret < 0) {
         return ret;
     }
 
     ret = vfio_mig_read(vbasedev, &data_size, sizeof(data_size),
-                        region->fd_offset + VFIO_MIG_STRUCT_OFFSET(data_size));
+                        VFIO_MIG_STRUCT_OFFSET(data_size));
     if (ret < 0) {
         return ret;
     }
@@ -233,8 +240,7 @@ static int vfio_save_buffer(QEMUFile *f, VFIODevice 
*vbasedev, uint64_t *size)
             }
             buf_allocated = true;
 
-            ret = vfio_mig_read(vbasedev, buf, sec_size,
-                                region->fd_offset + data_offset);
+            ret = vfio_mig_read(vbasedev, buf, sec_size, data_offset);
             if (ret < 0) {
                 g_free(buf);
                 return ret;
@@ -269,7 +275,7 @@ static int vfio_load_buffer(QEMUFile *f, VFIODevice 
*vbasedev,
 
     do {
         ret = vfio_mig_read(vbasedev, &data_offset, sizeof(data_offset),
-                      region->fd_offset + VFIO_MIG_STRUCT_OFFSET(data_offset));
+                            VFIO_MIG_STRUCT_OFFSET(data_offset));
         if (ret < 0) {
             return ret;
         }
@@ -309,8 +315,8 @@ static int vfio_load_buffer(QEMUFile *f, VFIODevice 
*vbasedev,
             qemu_get_buffer(f, buf, sec_size);
 
             if (buf_alloc) {
-                ret = vfio_mig_write(vbasedev, buf, sec_size,
-                        region->fd_offset + data_offset);
+
+                ret = vfio_mig_write(vbasedev, buf, sec_size, data_offset);
                 g_free(buf);
 
                 if (ret < 0) {
@@ -322,7 +328,7 @@ static int vfio_load_buffer(QEMUFile *f, VFIODevice 
*vbasedev,
         }
 
         ret = vfio_mig_write(vbasedev, &report_size, sizeof(report_size),
-                        region->fd_offset + VFIO_MIG_STRUCT_OFFSET(data_size));
+                             VFIO_MIG_STRUCT_OFFSET(data_size));
         if (ret < 0) {
             return ret;
         }
@@ -334,12 +340,11 @@ static int vfio_load_buffer(QEMUFile *f, VFIODevice 
*vbasedev,
 static int vfio_update_pending(VFIODevice *vbasedev)
 {
     VFIOMigration *migration = vbasedev->migration;
-    VFIORegion *region = &migration->region;
     uint64_t pending_bytes = 0;
     int ret;
 
     ret = vfio_mig_read(vbasedev, &pending_bytes, sizeof(pending_bytes),
-                    region->fd_offset + VFIO_MIG_STRUCT_OFFSET(pending_bytes));
+                        VFIO_MIG_STRUCT_OFFSET(pending_bytes));
     if (ret < 0) {
         migration->pending_bytes = 0;
         return ret;
diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c
index bed8eaa4c2..36f8524e7c 100644
--- a/hw/vfio/pci.c
+++ b/hw/vfio/pci.c
@@ -3633,6 +3633,13 @@ static void vfio_user_pci_realize(PCIDevice *pdev, Error 
**errp)
         }
     }
 
+    if (!pdev->failover_pair_id) {
+        ret = vfio_migration_probe(&vdev->vbasedev, errp);
+        if (ret) {
+            error_report("%s: Migration disabled", vdev->vbasedev.name);
+        }
+    }
+
     vfio_register_err_notifier(vdev);
     vfio_register_req_notifier(vdev);
 
diff --git a/hw/vfio/user.c b/hw/vfio/user.c
index 8917596a2f..eceaeeccea 100644
--- a/hw/vfio/user.c
+++ b/hw/vfio/user.c
@@ -917,3 +917,48 @@ void vfio_user_reset(VFIODevice *vbasedev)
         error_printf("reset reply error %d\n", msg.error_reply);
     }
 }
+
+int vfio_user_dirty_bitmap(VFIOProxy *proxy,
+                           struct vfio_iommu_type1_dirty_bitmap *cmd,
+                           struct vfio_iommu_type1_dirty_bitmap_get *dbitmap)
+{
+    g_autofree struct {
+        struct vfio_user_dirty_pages msg;
+        struct vfio_user_bitmap_range range;
+    } *msgp = NULL;
+    int msize, rsize;
+
+    /*
+     * If just the command is sent, the returned bitmap isn't needed.
+     * The bitmap structs are different from the ioctl() versions,
+     * ioctl() returns the bitmap in a local VA
+     */
+    if (dbitmap != NULL) {
+        msize = sizeof(*msgp);
+        rsize = msize + dbitmap->bitmap.size;
+        msgp = g_malloc0(rsize);
+        msgp->range.iova = dbitmap->iova;
+        msgp->range.size = dbitmap->size;
+        msgp->range.bitmap.pgsize = dbitmap->bitmap.pgsize;
+        msgp->range.bitmap.size = dbitmap->bitmap.size;
+    } else {
+        msize = rsize = sizeof(struct vfio_user_dirty_pages);
+        msgp = g_malloc0(rsize);
+    }
+
+    vfio_user_request_msg(&msgp->msg.hdr, VFIO_USER_DIRTY_PAGES, msize, 0);
+    msgp->msg.argsz = msize - sizeof(msgp->msg.hdr);
+    msgp->msg.flags = cmd->flags;
+
+    vfio_user_send_recv(proxy, &msgp->msg.hdr, NULL, rsize);
+    if (msgp->msg.hdr.flags & VFIO_USER_ERROR) {
+        return -msgp->msg.hdr.error_reply;
+    }
+
+    if (dbitmap != NULL) {
+        memcpy(dbitmap->bitmap.data, &msgp->range.bitmap.data,
+               dbitmap->bitmap.size);
+    }
+
+    return 0;
+}
-- 
2.25.1