9p: Added virtfs option 'multidevs=remap|forbid|warn'

'warn' (default): Only log an error message (once) on host if more than one
device is shared by same export, except of that just ignore this config
error though. This is the default behaviour for not breaking existing
installations implying that they really know what they are doing.

'forbid': Like 'warn', but except of just logging an error this
also denies access of guest to additional devices.

'remap': Allows to share more than one device per export by remapping
inodes from host to guest appropriately. To support multiple devices on the
9p share, and avoid qid path collisions we take the device id as input to
generate a unique QID path. The lowest 48 bits of the path will be set
equal to the file inode, and the top bits will be uniquely assigned based
on the top 16 bits of the inode and the device id.

Signed-off-by: Antonios Motakis <antonios.motakis@huawei.com>
[CS: - Rebased to https://github.com/gkurz/qemu/commits/9p-next
       (SHA1 7fc4c49e91).
     - Added virtfs option 'multidevs', original patch simply did the inode
       remapping without being asked.
     - Updated hash calls to new xxhash API.
     - Updated docs for new option 'multidevs'.
     - Fixed v9fs_do_readdir() not having remapped inodes.
     - Log error message when running out of prefixes in
       qid_path_prefixmap().
     - Fixed definition of QPATH_INO_MASK.
     - Wrapped qpp_table initialization to dedicated qpp_table_init()
       function.
     - Dropped unnecessary parantheses in qpp_lookup_func().
     - Dropped unnecessary g_malloc0() result checks. ]
Signed-off-by: Christian Schoenebeck <qemu_oss@crudebyte.com>
[groug: - Moved "multidevs" parsing to the local backend.
        - Added hint to invalid multidevs option error.
	- Turn "remap" into "x-remap". ]
Signed-off-by: Greg Kurz <groug@kaod.org>

1 files changed, 167 insertions, 21 deletions

diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c
index 5a895ae..8eb89c5 100644
--- a/hw/9pfs/9p.c
+++ b/hw/9pfs/9p.c
@@ -26,6 +26,7 @@
 #include "trace.h"
 #include "migration/blocker.h"
 #include "sysemu/qtest.h"
+#include "qemu/xxhash.h"
 
 int open_fd_hw;
 int total_open_fd;
@@ -572,23 +573,117 @@ static void coroutine_fn virtfs_reset(V9fsPDU *pdu)
                                 P9_STAT_MODE_NAMED_PIPE |   \
                                 P9_STAT_MODE_SOCKET)
 
-/* This is the algorithm from ufs in spfs */
+/* creative abuse of tb_hash_func7, which is based on xxhash */
+static uint32_t qpp_hash(QppEntry e)
+{
+    return qemu_xxhash7(e.ino_prefix, e.dev, 0, 0, 0);
+}
+
+static bool qpp_lookup_func(const void *obj, const void *userp)
+{
+    const QppEntry *e1 = obj, *e2 = userp;
+    return e1->dev == e2->dev && e1->ino_prefix == e2->ino_prefix;
+}
+
+static void qpp_table_remove(void *p, uint32_t h, void *up)
+{
+    g_free(p);
+}
+
+static void qpp_table_destroy(struct qht *ht)
+{
+    if (!ht || !ht->map) {
+        return;
+    }
+    qht_iter(ht, qpp_table_remove, NULL);
+    qht_destroy(ht);
+}
+
+static void qpp_table_init(struct qht *ht)
+{
+    qht_init(ht, qpp_lookup_func, 1, QHT_MODE_AUTO_RESIZE);
+}
+
+/*
+ * stat_to_qid needs to map inode number (64 bits) and device id (32 bits)
+ * to a unique QID path (64 bits). To avoid having to map and keep track
+ * of up to 2^64 objects, we map only the 16 highest bits of the inode plus
+ * the device id to the 16 highest bits of the QID path. The 48 lowest bits
+ * of the QID path equal to the lowest bits of the inode number.
+ *
+ * This takes advantage of the fact that inode number are usually not
+ * random but allocated sequentially, so we have fewer items to keep
+ * track of.
+ */
+static int qid_path_prefixmap(V9fsPDU *pdu, const struct stat *stbuf,
+                              uint64_t *path)
+{
+    QppEntry lookup = {
+        .dev = stbuf->st_dev,
+        .ino_prefix = (uint16_t) (stbuf->st_ino >> 48)
+    }, *val;
+    uint32_t hash = qpp_hash(lookup);
+
+    val = qht_lookup(&pdu->s->qpp_table, &lookup, hash);
+
+    if (!val) {
+        if (pdu->s->qp_prefix_next == 0) {
+            /* we ran out of prefixes */
+            error_report_once(
+                "9p: No more prefixes available for remapping inodes from "
+                "host to guest."
+            );
+            return -ENFILE;
+        }
+
+        val = g_malloc0(sizeof(QppEntry));
+        *val = lookup;
+
+        /* new unique inode prefix and device combo */
+        val->qp_prefix = pdu->s->qp_prefix_next++;
+        qht_insert(&pdu->s->qpp_table, val, hash, NULL);
+    }
+
+    *path = ((uint64_t)val->qp_prefix << 48) | (stbuf->st_ino & QPATH_INO_MASK);
+    return 0;
+}
+
 static int stat_to_qid(V9fsPDU *pdu, const struct stat *stbuf, V9fsQID *qidp)
 {
+    int err;
     size_t size;
 
-    if (pdu->s->dev_id != stbuf->st_dev) {
-        warn_report_once(
-            "9p: Multiple devices detected in same VirtFS export, "
-            "which might lead to file ID collisions and severe "
-            "misbehaviours on guest! You should use a separate "
-            "export for each device shared from host."
-        );
+    if (pdu->s->ctx.export_flags & V9FS_REMAP_INODES) {
+        /* map inode+device to qid path (fast path) */
+        err = qid_path_prefixmap(pdu, stbuf, &qidp->path);
+        if (err) {
+            return err;
+        }
+    } else {
+        if (pdu->s->dev_id != stbuf->st_dev) {
+            if (pdu->s->ctx.export_flags & V9FS_FORBID_MULTIDEVS) {
+                error_report_once(
+                    "9p: Multiple devices detected in same VirtFS export. "
+                    "Access of guest to additional devices is (partly) "
+                    "denied due to virtfs option 'multidevs=forbid' being "
+                    "effective."
+                );
+                return -ENODEV;
+            } else {
+                warn_report_once(
+                    "9p: Multiple devices detected in same VirtFS export, "
+                    "which might lead to file ID collisions and severe "
+                    "misbehaviours on guest! You should either use a "
+                    "separate export for each device shared from host or "
+                    "use virtfs option 'multidevs=remap'!"
+                );
+            }
+        }
+        memset(&qidp->path, 0, sizeof(qidp->path));
+        size = MIN(sizeof(stbuf->st_ino), sizeof(qidp->path));
+        memcpy(&qidp->path, &stbuf->st_ino, size);
     }
 
-    memset(&qidp->path, 0, sizeof(qidp->path));
-    size = MIN(sizeof(stbuf->st_ino), sizeof(qidp->path));
-    memcpy(&qidp->path, &stbuf->st_ino, size);
     qidp->version = stbuf->st_mtime ^ (stbuf->st_size << 8);
     qidp->type = 0;
     if (S_ISDIR(stbuf->st_mode)) {
@@ -618,6 +713,30 @@ static int coroutine_fn fid_to_qid(V9fsPDU *pdu, V9fsFidState *fidp,
     return 0;
 }
 
+static int coroutine_fn dirent_to_qid(V9fsPDU *pdu, V9fsFidState *fidp,
+                                      struct dirent *dent, V9fsQID *qidp)
+{
+    struct stat stbuf;
+    V9fsPath path;
+    int err;
+
+    v9fs_path_init(&path);
+
+    err = v9fs_co_name_to_path(pdu, &fidp->path, dent->d_name, &path);
+    if (err < 0) {
+        goto out;
+    }
+    err = v9fs_co_lstat(pdu, &path, &stbuf);
+    if (err < 0) {
+        goto out;
+    }
+    err = stat_to_qid(pdu, &stbuf, qidp);
+
+out:
+    v9fs_path_free(&path);
+    return err;
+}
+
 V9fsPDU *pdu_alloc(V9fsState *s)
 {
     V9fsPDU *pdu = NULL;
@@ -1966,16 +2085,39 @@ static int coroutine_fn v9fs_do_readdir(V9fsPDU *pdu, V9fsFidState *fidp,
             v9fs_string_free(&name);
             return count;
         }
-        /*
-         * Fill up just the path field of qid because the client uses
-         * only that. To fill the entire qid structure we will have
-         * to stat each dirent found, which is expensive
-         */
-        size = MIN(sizeof(dent->d_ino), sizeof(qid.path));
-        memcpy(&qid.path, &dent->d_ino, size);
-        /* Fill the other fields with dummy values */
-        qid.type = 0;
-        qid.version = 0;
+
+        if (pdu->s->ctx.export_flags & V9FS_REMAP_INODES) {
+            /*
+             * dirent_to_qid() implies expensive stat call for each entry,
+             * we must do that here though since inode remapping requires
+             * the device id, which in turn might be different for
+             * different entries; we cannot make any assumption to avoid
+             * that here.
+             */
+            err = dirent_to_qid(pdu, fidp, dent, &qid);
+            if (err < 0) {
+                v9fs_readdir_unlock(&fidp->fs.dir);
+                v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
+                v9fs_string_free(&name);
+                return err;
+            }
+        } else {
+            /*
+             * Fill up just the path field of qid because the client uses
+             * only that. To fill the entire qid structure we will have
+             * to stat each dirent found, which is expensive. For the
+             * latter reason we don't call dirent_to_qid() here. Only drawback
+             * is that no multi-device export detection of stat_to_qid()
+             * would be done and provided as error to the user here. But
+             * user would get that error anyway when accessing those
+             * files/dirs through other ways.
+             */
+            size = MIN(sizeof(dent->d_ino), sizeof(qid.path));
+            memcpy(&qid.path, &dent->d_ino, size);
+            /* Fill the other fields with dummy values */
+            qid.type = 0;
+            qid.version = 0;
+        }
 
         /* 11 = 7 + 4 (7 = start offset, 4 = space for storing count) */
         len = pdu_marshal(pdu, 11 + count, "Qqbs",
@@ -3676,6 +3818,9 @@ int v9fs_device_realize_common(V9fsState *s, const V9fsTransport *t,
 
     s->dev_id = stat.st_dev;
 
+    qpp_table_init(&s->qpp_table);
+    s->qp_prefix_next = 1; /* reserve 0 to detect overflow */
+
     s->ctx.fst = &fse->fst;
     fsdev_throttle_init(s->ctx.fst);
 
@@ -3697,6 +3842,7 @@ void v9fs_device_unrealize_common(V9fsState *s, Error **errp)
         fsdev_throttle_cleanup(s->ctx.fst);
     }
     g_free(s->tag);
+    qpp_table_destroy(&s->qpp_table);
     g_free(s->ctx.fs_root);
 }