[Qemu-devel] [RFC PATCH 6/7] virtio-fs: Allow mapping of meta data version table

[Dr. David Alan Gilbert (git)]

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

The 'meta data version table' is a block of shared memory mapped between
multiple QEMUs and fuse daemons, so that they can be informed
of metadata updates.  It's typically a shmfs file, and
it's specified as :

   -device 
vhost-user-fs-pci,chardev=char0,tag=myfs,cache-size=1G,versiontable=/dev/shm/mdvt1

It gets mapped into the PCI bar after the data cache; it's read only.

Signed-off-by: Dr. David Alan Gilbert <address@hidden>
---
 hw/virtio/vhost-user-fs.c                  | 36 ++++++++++++++++++++++
 hw/virtio/virtio-pci.c                     | 16 ++++++++--
 include/hw/virtio/vhost-user-fs.h          |  4 +++
 include/standard-headers/linux/virtio_fs.h |  1 +
 4 files changed, 55 insertions(+), 2 deletions(-)

diff --git a/hw/virtio/vhost-user-fs.c b/hw/virtio/vhost-user-fs.c
index bbb15477e5..a39ecd3a16 100644
--- a/hw/virtio/vhost-user-fs.c
+++ b/hw/virtio/vhost-user-fs.c
@@ -296,6 +296,7 @@ static void vuf_device_realize(DeviceState *dev, Error 
**errp)
     unsigned int i;
     size_t len;
     int ret;
+    int mdvtfd = -1;
 
     if (!fs->conf.chardev.chr) {
         error_setg(errp, "missing chardev");
@@ -338,6 +339,31 @@ static void vuf_device_realize(DeviceState *dev, Error 
**errp)
                          "no smaller than the page size");
         return;
     }
+
+    if (fs->conf.mdvtpath) {
+        struct stat statbuf;
+
+        mdvtfd = open(fs->conf.mdvtpath, O_RDWR);
+        if (mdvtfd < 0) {
+            error_setg_errno(errp, errno,
+                             "Failed to open meta-data version table '%s'",
+                             fs->conf.mdvtpath);
+
+            return;
+        }
+        if (fstat(mdvtfd, &statbuf) == -1) {
+            error_setg_errno(errp, errno,
+                             "Failed to stat meta-data version table '%s'",
+                             fs->conf.mdvtpath);
+            close(mdvtfd);
+            return;
+        }
+
+        fs->mdvt_size = statbuf.st_size;
+    }
+    fprintf(stderr, "%s: cachesize=%zd mdvt_size=%zd\n", __func__,
+            fs->conf.cache_size, fs->mdvt_size);
+
     /* We need a region with some host memory, 'ram' is the easiest */
     memory_region_init_ram_nomigrate(&fs->cache, OBJECT(vdev),
                        "virtio-fs-cache",
@@ -348,6 +374,15 @@ static void vuf_device_realize(DeviceState *dev, Error 
**errp)
     mprotect(memory_region_get_ram_ptr(&fs->cache), fs->conf.cache_size,
              PROT_NONE);
 
+
+    if (mdvtfd) {
+        memory_region_init_ram_from_fd(&fs->mdvt, OBJECT(vdev),
+                       "virtio-fs-mdvt",
+                       fs->mdvt_size, true, mdvtfd, NULL);
+        /* The version table is read-only by the guest */
+        memory_region_set_readonly(&fs->mdvt, true);
+    }
+
     fs->vhost_user = vhost_user_init();
     if (!fs->vhost_user) {
         error_setg(errp, "failed to initialize vhost-user");
@@ -416,6 +451,7 @@ static Property vuf_properties[] = {
     DEFINE_PROP_UINT16("queue-size", VHostUserFS, conf.queue_size, 128),
     DEFINE_PROP_STRING("vhostfd", VHostUserFS, conf.vhostfd),
     DEFINE_PROP_SIZE("cache-size", VHostUserFS, conf.cache_size, 1ull << 30),
+    DEFINE_PROP_STRING("versiontable", VHostUserFS, conf.mdvtpath),
     DEFINE_PROP_END_OF_LIST(),
 };
 
diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c
index e819a29fb1..d8785b78bf 100644
--- a/hw/virtio/virtio-pci.c
+++ b/hw/virtio/virtio-pci.c
@@ -2680,20 +2680,32 @@ static void vhost_user_fs_pci_realize(VirtIOPCIProxy 
*vpci_dev, Error **errp)
     VHostUserFSPCI *dev = VHOST_USER_FS_PCI(vpci_dev);
     DeviceState *vdev = DEVICE(&dev->vdev);
     uint64_t cachesize;
+    uint64_t totalsize;
 
     qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus));
     object_property_set_bool(OBJECT(vdev), true, "realized", errp);
     cachesize = memory_region_size(&dev->vdev.cache);
 
+    /* PCIe bar needs to be a power of 2 */
+    totalsize = pow2ceil(cachesize + dev->vdev.mdvt_size);
+
     /* The bar starts with the data/DAX cache
-     * Others will be added later.
+     * followed by the metadata cache.
      */
     memory_region_init(&dev->cachebar, OBJECT(vpci_dev),
-                       "vhost-fs-pci-cachebar", cachesize);
+                       "vhost-fs-pci-cachebar", totalsize);
     memory_region_add_subregion(&dev->cachebar, 0, &dev->vdev.cache);
     virtio_pci_add_shm_cap(vpci_dev, VIRTIO_FS_PCI_CACHE_BAR, 0, cachesize,
                            VIRTIO_FS_PCI_SHMCAP_ID_CACHE);
 
+    if (dev->vdev.mdvt_size) {
+        memory_region_add_subregion(&dev->cachebar, cachesize,
+                                    &dev->vdev.mdvt);
+        virtio_pci_add_shm_cap(vpci_dev, VIRTIO_FS_PCI_CACHE_BAR,
+                               cachesize, dev->vdev.mdvt_size,
+                               VIRTIO_FS_PCI_SHMCAP_ID_VERTAB);
+    }
+
     /* After 'realized' so the memory region exists */
     pci_register_bar(&vpci_dev->pci_dev, VIRTIO_FS_PCI_CACHE_BAR,
                      PCI_BASE_ADDRESS_SPACE_MEMORY |
diff --git a/include/hw/virtio/vhost-user-fs.h 
b/include/hw/virtio/vhost-user-fs.h
index 9989bcd9e7..281ae0a52d 100644
--- a/include/hw/virtio/vhost-user-fs.h
+++ b/include/hw/virtio/vhost-user-fs.h
@@ -48,6 +48,7 @@ typedef struct {
     uint16_t queue_size;
     char *vhostfd;
     size_t cache_size;
+    char *mdvtpath;
 } VHostUserFSConf;
 
 typedef struct {
@@ -60,6 +61,9 @@ typedef struct {
 
     /*< public >*/
     MemoryRegion cache;
+    /* Metadata version table */
+    size_t mdvt_size;
+    MemoryRegion mdvt;
 } VHostUserFS;
 
 /* Callbacks from the vhost-user code for slave commands */
diff --git a/include/standard-headers/linux/virtio_fs.h 
b/include/standard-headers/linux/virtio_fs.h
index b5f137ca79..77fa651073 100644
--- a/include/standard-headers/linux/virtio_fs.h
+++ b/include/standard-headers/linux/virtio_fs.h
@@ -42,5 +42,6 @@ struct virtio_fs_config {
 
 /* For the id field in virtio_pci_shm_cap */
 #define VIRTIO_FS_PCI_SHMCAP_ID_CACHE 0
+#define VIRTIO_FS_PCI_SHMCAP_ID_VERTAB 1
 
 #endif /* _LINUX_VIRTIO_FS_H */
-- 
2.19.2