[Qemu-devel] [PATCH 2/3] qga: Add guest-get-fsinfo command

[Michael Roth <mdroth@linux.vnet.ibm.com>]

From: Tomoki Sekiyama <tomoki.sekiyama@hds.com>

Add command to get mounted filesystems information in the guest.
The returned value contains a list of mountpoint paths and
corresponding disks info such as disk bus type, drive address,
and the disk controllers' PCI addresses, so that management layer
such as libvirt can resolve the disk backends.

For example, when `lsblk' result is:

    NAME           MAJ:MIN RM  SIZE RO TYPE MOUNTPOINT
    sdb              8:16   0    1G  0 disk
    `-sdb1           8:17   0 1024M  0 part
      `-vg0-lv0    253:1    0  1.4G  0 lvm  /mnt/test
    sdc              8:32   0    1G  0 disk
    `-sdc1           8:33   0  512M  0 part
      `-vg0-lv0    253:1    0  1.4G  0 lvm  /mnt/test
    vda            252:0    0   25G  0 disk
    `-vda1         252:1    0   25G  0 part /

where sdb is a SCSI disk with PCI controller 0000:00:0a.0 and ID=1,
      sdc is an IDE disk with PCI controller 0000:00:01.1, and
      vda is a virtio-blk disk with PCI device 0000:00:06.0,

guest-get-fsinfo command will return the following result:

    {"return":
     [{"name":"dm-1",
       "mountpoint":"/mnt/test",
       "disk":[
        {"bus-type":"scsi","bus":0,"unit":1,"target":0,
         "pci-controller":{"bus":0,"slot":10,"domain":0,"function":0}},
        {"bus-type":"ide","bus":0,"unit":0,"target":0,
         "pci-controller":{"bus":0,"slot":1,"domain":0,"function":1}}],
       "type":"xfs"},
      {"name":"vda1", "mountpoint":"/",
       "disk":[
        {"bus-type":"virtio","bus":0,"unit":0,"target":0,
         "pci-controller":{"bus":0,"slot":6,"domain":0,"function":0}}],
       "type":"ext4"}]}

In Linux guest, the disk information is resolved from sysfs. So far,
it only supports virtio-blk, virtio-scsi, IDE, SATA, SCSI disks on x86
hosts, and "disk" parameter may be empty for unsupported disk types.

Signed-off-by: Tomoki Sekiyama <tomoki.sekiyama@hds.com>

*updated schema to report 2.2 as initial supported version

Signed-off-by: Michael Roth <mdroth@linux.vnet.ibm.com>
---
 qga/commands-posix.c | 438 ++++++++++++++++++++++++++++++++++++++++++++++++++-
 qga/commands-win32.c |   6 +
 qga/qapi-schema.json |  79 ++++++++++
 3 files changed, 522 insertions(+), 1 deletion(-)

diff --git a/qga/commands-posix.c b/qga/commands-posix.c
index 883e3c5..6b8e9c4 100644
--- a/qga/commands-posix.c
+++ b/qga/commands-posix.c
@@ -18,6 +18,7 @@
 #include <unistd.h>
 #include <errno.h>
 #include <fcntl.h>
+#include <dirent.h>
 #include <stdio.h>
 #include <string.h>
 #include <sys/stat.h>
@@ -575,6 +576,7 @@ static void guest_file_init(void)
 typedef struct FsMount {
     char *dirname;
     char *devtype;
+    unsigned int devmajor, devminor;
     QTAILQ_ENTRY(FsMount) next;
 } FsMount;
 
@@ -596,15 +598,40 @@ static void free_fs_mount_list(FsMountList *mounts)
      }
 }
 
+static int dev_major_minor(const char *devpath,
+                           unsigned int *devmajor, unsigned int *devminor)
+{
+    struct stat st;
+
+    *devmajor = 0;
+    *devminor = 0;
+
+    if (stat(devpath, &st) < 0) {
+        slog("failed to stat device file '%s': %s", devpath, strerror(errno));
+        return -1;
+    }
+    if (S_ISDIR(st.st_mode)) {
+        /* It is bind mount */
+        return -2;
+    }
+    if (S_ISBLK(st.st_mode)) {
+        *devmajor = major(st.st_rdev);
+        *devminor = minor(st.st_rdev);
+        return 0;
+    }
+    return -1;
+}
+
 /*
  * Walk the mount table and build a list of local file systems
  */
-static void build_fs_mount_list(FsMountList *mounts, Error **errp)
+static void build_fs_mount_list_from_mtab(FsMountList *mounts, Error **errp)
 {
     struct mntent *ment;
     FsMount *mount;
     char const *mtab = "/proc/self/mounts";
     FILE *fp;
+    unsigned int devmajor, devminor;
 
     fp = setmntent(mtab, "r");
     if (!fp) {
@@ -624,20 +651,423 @@ static void build_fs_mount_list(FsMountList *mounts, Error **errp)
             (strcmp(ment->mnt_type, "cifs") == 0)) {
             continue;
         }
+        if (dev_major_minor(ment->mnt_fsname, &devmajor, &devminor) == -2) {
+            /* Skip bind mounts */
+            continue;
+        }
 
         mount = g_malloc0(sizeof(FsMount));
         mount->dirname = g_strdup(ment->mnt_dir);
         mount->devtype = g_strdup(ment->mnt_type);
+        mount->devmajor = devmajor;
+        mount->devminor = devminor;
 
         QTAILQ_INSERT_TAIL(mounts, mount, next);
     }
 
     endmntent(fp);
 }
+
+static void decode_mntname(char *name, int len)
+{
+    int i, j = 0;
+    for (i = 0; i <= len; i++) {
+        if (name[i] != '\\') {
+            name[j++] = name[i];
+        } else if (name[i + 1] == '\\') {
+            name[j++] = '\\';
+            i++;
+        } else if (name[i + 1] >= '0' && name[i + 1] <= '3' &&
+                   name[i + 2] >= '0' && name[i + 2] <= '7' &&
+                   name[i + 3] >= '0' && name[i + 3] <= '7') {
+            name[j++] = (name[i + 1] - '0') * 64 +
+                        (name[i + 2] - '0') * 8 +
+                        (name[i + 3] - '0');
+            i += 3;
+        } else {
+            name[j++] = name[i];
+        }
+    }
+}
+
+static void build_fs_mount_list(FsMountList *mounts, Error **errp)
+{
+    FsMount *mount;
+    char const *mountinfo = "/proc/self/mountinfo";
+    FILE *fp;
+    char *line = NULL, *dash;
+    size_t n;
+    char check;
+    unsigned int devmajor, devminor;
+    int ret, dir_s, dir_e, type_s, type_e, dev_s, dev_e;
+
+    fp = fopen(mountinfo, "r");
+    if (!fp) {
+        build_fs_mount_list_from_mtab(mounts, errp);
+        return;
+    }
+
+    while (getline(&line, &n, fp) != -1) {
+        ret = sscanf(line, "%*u %*u %u:%u %*s %n%*s%n%c",
+                     &devmajor, &devminor, &dir_s, &dir_e, &check);
+        if (ret < 3) {
+            continue;
+        }
+        dash = strstr(line + dir_e, " - ");
+        if (!dash) {
+            continue;
+        }
+        ret = sscanf(dash, " - %n%*s%n %n%*s%n%c",
+                     &type_s, &type_e, &dev_s, &dev_e, &check);
+        if (ret < 1) {
+            continue;
+        }
+        line[dir_e] = 0;
+        dash[type_e] = 0;
+        dash[dev_e] = 0;
+        decode_mntname(line + dir_s, dir_e - dir_s);
+        decode_mntname(dash + dev_s, dev_e - dev_s);
+        if (devmajor == 0) {
+            /* btrfs reports major number = 0 */
+            if (strcmp("btrfs", dash + type_s) != 0 ||
+                dev_major_minor(dash + dev_s, &devmajor, &devminor) < 0) {
+                continue;
+            }
+        }
+
+        mount = g_malloc0(sizeof(FsMount));
+        mount->dirname = g_strdup(line + dir_s);
+        mount->devtype = g_strdup(dash + type_s);
+        mount->devmajor = devmajor;
+        mount->devminor = devminor;
+
+        QTAILQ_INSERT_TAIL(mounts, mount, next);
+    }
+    free(line);
+
+    fclose(fp);
+}
 #endif
 
 #if defined(CONFIG_FSFREEZE)
 
+static char *get_pci_driver(char const *syspath, int pathlen, Error **errp)
+{
+    char *path;
+    char *dpath;
+    char *driver = NULL;
+    char buf[PATH_MAX];
+    ssize_t len;
+
+    path = g_strndup(syspath, pathlen);
+    dpath = g_strdup_printf("%s/driver", path);
+    len = readlink(dpath, buf, sizeof(buf) - 1);
+    if (len != -1) {
+        buf[len] = 0;
+        driver = g_strdup(basename(buf));
+    }
+    g_free(dpath);
+    g_free(path);
+    return driver;
+}
+
+static int compare_uint(const void *_a, const void *_b)
+{
+    unsigned int a = *(unsigned int *)_a;
+    unsigned int b = *(unsigned int *)_b;
+
+    return a < b ? -1 : a > b ? 1 : 0;
+}
+
+/* Walk the specified sysfs and build a sorted list of host or ata numbers */
+static int build_hosts(char const *syspath, char const *host, bool ata,
+                       unsigned int *hosts, int hosts_max, Error **errp)
+{
+    char *path;
+    DIR *dir;
+    struct dirent *entry;
+    int i = 0;
+
+    path = g_strndup(syspath, host - syspath);
+    dir = opendir(path);
+    if (!dir) {
+        error_setg_errno(errp, errno, "opendir(\"%s\")", path);
+        g_free(path);
+        return -1;
+    }
+
+    while (i < hosts_max) {
+        entry = readdir(dir);
+        if (!entry) {
+            break;
+        }
+        if (ata && sscanf(entry->d_name, "ata%d", hosts + i) == 1) {
+            ++i;
+        } else if (!ata && sscanf(entry->d_name, "host%d", hosts + i) == 1) {
+            ++i;
+        }
+    }
+
+    qsort(hosts, i, sizeof(hosts[0]), compare_uint);
+
+    g_free(path);
+    closedir(dir);
+    return i;
+}
+
+/* Store disk device info specified by @sysfs into @fs */
+static void build_guest_fsinfo_for_real_device(char const *syspath,
+                                               GuestFilesystemInfo *fs,
+                                               Error **errp)
+{
+    unsigned int pci[4], host, hosts[8], tgt[3];
+    int i, nhosts = 0, pcilen;
+    GuestDiskAddress *disk;
+    GuestPCIAddress *pciaddr;
+    GuestDiskAddressList *list = NULL;
+    bool has_ata = false, has_host = false, has_tgt = false;
+    char *p, *q, *driver = NULL;
+
+    p = strstr(syspath, "/devices/pci");
+    if (!p || sscanf(p + 12, "%*x:%*x/%x:%x:%x.%x%n",
+                     pci, pci + 1, pci + 2, pci + 3, &pcilen) < 4) {
+        g_debug("only pci device is supported: sysfs path \"%s\"", syspath);
+        return;
+    }
+
+    driver = get_pci_driver(syspath, (p + 12 + pcilen) - syspath, errp);
+    if (!driver) {
+        goto cleanup;
+    }
+
+    p = strstr(syspath, "/target");
+    if (p && sscanf(p + 7, "%*u:%*u:%*u/%*u:%u:%u:%u",
+                    tgt, tgt + 1, tgt + 2) == 3) {
+        has_tgt = true;
+    }
+
+    p = strstr(syspath, "/ata");
+    if (p) {
+        q = p + 4;
+        has_ata = true;
+    } else {
+        p = strstr(syspath, "/host");
+        q = p + 5;
+    }
+    if (p && sscanf(q, "%u", &host) == 1) {
+        has_host = true;
+        nhosts = build_hosts(syspath, p, has_ata, hosts,
+                             sizeof(hosts) / sizeof(hosts[0]), errp);
+        if (nhosts < 0) {
+            goto cleanup;
+        }
+    }
+
+    pciaddr = g_malloc0(sizeof(*pciaddr));
+    pciaddr->domain = pci[0];
+    pciaddr->bus = pci[1];
+    pciaddr->slot = pci[2];
+    pciaddr->function = pci[3];
+
+    disk = g_malloc0(sizeof(*disk));
+    disk->pci_controller = pciaddr;
+
+    list = g_malloc0(sizeof(*list));
+    list->value = disk;
+
+    if (strcmp(driver, "ata_piix") == 0) {
+        /* a host per ide bus, target*:0:<unit>:0 */
+        if (!has_host || !has_tgt) {
+            g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver);
+            goto cleanup;
+        }
+        for (i = 0; i < nhosts; i++) {
+            if (host == hosts[i]) {
+                disk->bus_type = GUEST_DISK_BUS_TYPE_IDE;
+                disk->bus = i;
+                disk->unit = tgt[1];
+                break;
+            }
+        }
+        if (i >= nhosts) {
+            g_debug("no host for '%s' (driver '%s')", syspath, driver);
+            goto cleanup;
+        }
+    } else if (strcmp(driver, "sym53c8xx") == 0) {
+        /* scsi(LSI Logic): target*:0:<unit>:0 */
+        if (!has_tgt) {
+            g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver);
+            goto cleanup;
+        }
+        disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI;
+        disk->unit = tgt[1];
+    } else if (strcmp(driver, "virtio-pci") == 0) {
+        if (has_tgt) {
+            /* virtio-scsi: target*:0:0:<unit> */
+            disk->bus_type = GUEST_DISK_BUS_TYPE_SCSI;
+            disk->unit = tgt[2];
+        } else {
+            /* virtio-blk: 1 disk per 1 device */
+            disk->bus_type = GUEST_DISK_BUS_TYPE_VIRTIO;
+        }
+    } else if (strcmp(driver, "ahci") == 0) {
+        /* ahci: 1 host per 1 unit */
+        if (!has_host || !has_tgt) {
+            g_debug("invalid sysfs path '%s' (driver '%s')", syspath, driver);
+            goto cleanup;
+        }
+        for (i = 0; i < nhosts; i++) {
+            if (host == hosts[i]) {
+                disk->unit = i;
+                disk->bus_type = GUEST_DISK_BUS_TYPE_SATA;
+                break;
+            }
+        }
+        if (i >= nhosts) {
+            g_debug("no host for '%s' (driver '%s')", syspath, driver);
+            goto cleanup;
+        }
+    } else {
+        g_debug("unknown driver '%s' (sysfs path '%s')", driver, syspath);
+        goto cleanup;
+    }
+
+    list->next = fs->disk;
+    fs->disk = list;
+    g_free(driver);
+    return;
+
+cleanup:
+    if (list) {
+        qapi_free_GuestDiskAddressList(list);
+    }
+    g_free(driver);
+}
+
+static void build_guest_fsinfo_for_device(char const *devpath,
+                                          GuestFilesystemInfo *fs,
+                                          Error **errp);
+
+/* Store a list of slave devices of virtual volume specified by @syspath into
+ * @fs */
+static void build_guest_fsinfo_for_virtual_device(char const *syspath,
+                                                  GuestFilesystemInfo *fs,
+                                                  Error **errp)
+{
+    DIR *dir;
+    char *dirpath;
+    struct dirent entry, *result;
+
+    dirpath = g_strdup_printf("%s/slaves", syspath);
+    dir = opendir(dirpath);
+    if (!dir) {
+        error_setg_errno(errp, errno, "opendir(\"%s\")", dirpath);
+        g_free(dirpath);
+        return;
+    }
+    g_free(dirpath);
+
+    for (;;) {
+        if (readdir_r(dir, &entry, &result) != 0) {
+            error_setg_errno(errp, errno, "readdir_r(\"%s\")", dirpath);
+            break;
+        }
+        if (!result) {
+            break;
+        }
+
+        if (entry.d_type == DT_LNK) {
+            g_debug(" slave device '%s'", entry.d_name);
+            dirpath = g_strdup_printf("%s/slaves/%s", syspath, entry.d_name);
+            build_guest_fsinfo_for_device(dirpath, fs, errp);
+            g_free(dirpath);
+
+            if (*errp) {
+                break;
+            }
+        }
+    }
+
+    closedir(dir);
+}
+
+/* Dispatch to functions for virtual/real device */
+static void build_guest_fsinfo_for_device(char const *devpath,
+                                          GuestFilesystemInfo *fs,
+                                          Error **errp)
+{
+    char *syspath = realpath(devpath, NULL);
+
+    if (!syspath) {
+        error_setg_errno(errp, errno, "realpath(\"%s\")", devpath);
+        return;
+    }
+
+    if (!fs->name) {
+        fs->name = g_strdup(basename(syspath));
+    }
+
+    g_debug("  parse sysfs path '%s'", syspath);
+
+    if (strstr(syspath, "/devices/virtual/block/")) {
+        build_guest_fsinfo_for_virtual_device(syspath, fs, errp);
+    } else {
+        build_guest_fsinfo_for_real_device(syspath, fs, errp);
+    }
+
+    free(syspath);
+}
+
+/* Return a list of the disk device(s)' info which @mount lies on */
+static GuestFilesystemInfo *build_guest_fsinfo(struct FsMount *mount,
+                                               Error **errp)
+{
+    GuestFilesystemInfo *fs = g_malloc0(sizeof(*fs));
+    char *devpath = g_strdup_printf("/sys/dev/block/%u:%u",
+                                    mount->devmajor, mount->devminor);
+
+    fs->mountpoint = g_strdup(mount->dirname);
+    fs->type = g_strdup(mount->devtype);
+    build_guest_fsinfo_for_device(devpath, fs, errp);
+
+    g_free(devpath);
+    return fs;
+}
+
+GuestFilesystemInfoList *qmp_guest_get_fsinfo(Error **errp)
+{
+    FsMountList mounts;
+    struct FsMount *mount;
+    GuestFilesystemInfoList *new, *ret = NULL;
+    Error *local_err = NULL;
+
+    QTAILQ_INIT(&mounts);
+    build_fs_mount_list(&mounts, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
+        return NULL;
+    }
+
+    QTAILQ_FOREACH(mount, &mounts, next) {
+        g_debug("Building guest fsinfo for '%s'", mount->dirname);
+
+        new = g_malloc0(sizeof(*ret));
+        new->value = build_guest_fsinfo(mount, &local_err);
+        new->next = ret;
+        ret = new;
+        if (local_err) {
+            error_propagate(errp, local_err);
+            qapi_free_GuestFilesystemInfoList(ret);
+            ret = NULL;
+            break;
+        }
+    }
+
+    free_fs_mount_list(&mounts);
+    return ret;
+}
+
+
 typedef enum {
     FSFREEZE_HOOK_THAW = 0,
     FSFREEZE_HOOK_FREEZE,
@@ -1481,6 +1911,12 @@ int64_t qmp_guest_set_vcpus(GuestLogicalProcessorList *vcpus, Error **errp)
 
 #if !defined(CONFIG_FSFREEZE)
 
+GuestFilesystemInfoList *qmp_guest_get_fsinfo(Error **errp)
+{
+    error_set(errp, QERR_UNSUPPORTED);
+    return NULL;
+}
+
 GuestFsfreezeStatus qmp_guest_fsfreeze_status(Error **errp)
 {
     error_set(errp, QERR_UNSUPPORTED);
diff --git a/qga/commands-win32.c b/qga/commands-win32.c
index 94877e9..3b667f5 100644
--- a/qga/commands-win32.c
+++ b/qga/commands-win32.c
@@ -152,6 +152,12 @@ void qmp_guest_file_flush(int64_t handle, Error **errp)
     error_set(errp, QERR_UNSUPPORTED);
 }
 
+GuestFilesystemInfoList *qmp_guest_get_fsinfo(Error **errp)
+{
+    error_set(errp, QERR_UNSUPPORTED);
+    return NULL;
+}
+
 /*
  * Return status of freeze/thaw
  */
diff --git a/qga/qapi-schema.json b/qga/qapi-schema.json
index 14b2aec..376e79f 100644
--- a/qga/qapi-schema.json
+++ b/qga/qapi-schema.json
@@ -659,3 +659,82 @@
 { 'command': 'guest-set-vcpus',
   'data':    {'vcpus': ['GuestLogicalProcessor'] },
   'returns': 'int' }
+
+##
+# @GuestDiskBusType
+#
+# An enumeration of bus type of disks
+#
+# @ide: IDE disks
+# @fdc: floppy disks
+# @scsi: SCSI disks
+# @virtio: virtio disks
+# @xen: Xen disks
+# @usb: USB disks
+# @uml: UML disks
+# @sata: SATA disks
+# @sd: SD cards
+#
+# Since: 2.2
+##
+{ 'enum': 'GuestDiskBusType',
+  'data': [ 'ide', 'fdc', 'scsi', 'virtio', 'xen', 'usb', 'uml', 'sata',
+            'sd' ] }
+
+##
+# @GuestPCIAddress:
+#
+# @domain: domain id
+# @bus: bus id
+# @slot: slot id
+# @function: function id
+#
+# Since: 2.2
+##
+{ 'type': 'GuestPCIAddress',
+  'data': {'domain': 'int', 'bus': 'int',
+           'slot': 'int', 'function': 'int'} }
+
+##
+# @GuestDiskAddress:
+#
+# @pci-controller: controller's PCI address
+# @type: bus type
+# @bus: bus id
+# @target: target id
+# @unit: unit id
+#
+# Since: 2.2
+##
+{ 'type': 'GuestDiskAddress',
+  'data': {'pci-controller': 'GuestPCIAddress',
+           'bus-type': 'GuestDiskBusType',
+           'bus': 'int', 'target': 'int', 'unit': 'int'} }
+
+##
+# @GuestFilesystemInfo
+#
+# @name: disk name
+# @mountpoint: mount point path
+# @type: file system type string
+# @disk: an array of disk hardware information that the volume lies on,
+#        which may be empty if the disk type is not supported
+#
+# Since: 2.2
+##
+{ 'type': 'GuestFilesystemInfo',
+  'data': {'name': 'str', 'mountpoint': 'str', 'type': 'str',
+           'disk': ['GuestDiskAddress']} }
+
+##
+# @guest-get-fsinfo:
+#
+# Returns: The list of filesystems information mounted in the guest.
+#          The returned mountpoints may be specified to
+#          @guest-fsfreeze-freeze-list.
+#          Network filesystems (such as CIFS and NFS) are not listed.
+#
+# Since: 2.2
+##
+{ 'command': 'guest-get-fsinfo',
+  'returns': ['GuestFilesystemInfo'] }
-- 
1.9.1