1 files changed, 82 insertions, 77 deletions

diff --git a/hw/9pfs/9p.c b/hw/9pfs/9p.c
index 2ffd96ade9..7bb994bbf2 100644
--- a/hw/9pfs/9p.c
+++ b/hw/9pfs/9p.c
@@ -314,8 +314,8 @@ static V9fsFidState *alloc_fid(V9fsState *s, int32_t fid)
     f->next = s->fid_list;
     s->fid_list = f;
 
-    v9fs_readdir_init(&f->fs.dir);
-    v9fs_readdir_init(&f->fs_reclaim.dir);
+    v9fs_readdir_init(s->proto_version, &f->fs.dir);
+    v9fs_readdir_init(s->proto_version, &f->fs_reclaim.dir);
 
     return f;
 }
@@ -972,30 +972,6 @@ 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;
@@ -2252,7 +2228,14 @@ static void coroutine_fn v9fs_read(void *opaque)
         goto out_nofid;
     }
     if (fidp->fid_type == P9_FID_DIR) {
-
+        if (s->proto_version != V9FS_PROTO_2000U) {
+            warn_report_once(
+                "9p: bad client: T_read request on directory only expected "
+                "with 9P2000.u protocol version"
+            );
+            err = -EOPNOTSUPP;
+            goto out;
+        }
         if (off == 0) {
             v9fs_co_rewinddir(pdu, fidp);
         }
@@ -2313,7 +2296,13 @@ out_nofid:
     pdu_complete(pdu, err);
 }
 
-static size_t v9fs_readdir_data_size(V9fsString *name)
+/**
+ * Returns size required in Rreaddir response for the passed dirent @p name.
+ *
+ * @param name - directory entry's name (i.e. file name, directory name)
+ * @returns required size in bytes
+ */
+size_t v9fs_readdir_response_size(V9fsString *name)
 {
     /*
      * Size of each dirent on the wire: size of qid (13) + size of offset (8)
@@ -2322,62 +2311,74 @@ static size_t v9fs_readdir_data_size(V9fsString *name)
     return 24 + v9fs_string_size(name);
 }
 
+static void v9fs_free_dirents(struct V9fsDirEnt *e)
+{
+    struct V9fsDirEnt *next = NULL;
+
+    for (; e; e = next) {
+        next = e->next;
+        g_free(e->dent);
+        g_free(e->st);
+        g_free(e);
+    }
+}
+
 static int coroutine_fn v9fs_do_readdir(V9fsPDU *pdu, V9fsFidState *fidp,
-                                        int32_t max_count)
+                                        off_t offset, int32_t max_count)
 {
     size_t size;
     V9fsQID qid;
     V9fsString name;
     int len, err = 0;
     int32_t count = 0;
-    off_t saved_dir_pos;
     struct dirent *dent;
+    struct stat *st;
+    struct V9fsDirEnt *entries = NULL;
 
-    /* save the directory position */
-    saved_dir_pos = v9fs_co_telldir(pdu, fidp);
-    if (saved_dir_pos < 0) {
-        return saved_dir_pos;
-    }
-
-    while (1) {
-        v9fs_readdir_lock(&fidp->fs.dir);
+    /*
+     * inode remapping requires the device id, which in turn might be
+     * different for different directory entries, so if inode remapping is
+     * enabled we have to make a full stat for each directory entry
+     */
+    const bool dostat = pdu->s->ctx.export_flags & V9FS_REMAP_INODES;
 
-        err = v9fs_co_readdir(pdu, fidp, &dent);
-        if (err || !dent) {
-            break;
-        }
-        v9fs_string_init(&name);
-        v9fs_string_sprintf(&name, "%s", dent->d_name);
-        if ((count + v9fs_readdir_data_size(&name)) > max_count) {
-            v9fs_readdir_unlock(&fidp->fs.dir);
+    /*
+     * Fetch all required directory entries altogether on a background IO
+     * thread from fs driver. We don't want to do that for each entry
+     * individually, because hopping between threads (this main IO thread
+     * and background IO driver thread) would sum up to huge latencies.
+     */
+    count = v9fs_co_readdir_many(pdu, fidp, &entries, offset, max_count,
+                                 dostat);
+    if (count < 0) {
+        err = count;
+        count = 0;
+        goto out;
+    }
+    count = 0;
 
-            /* Ran out of buffer. Set dir back to old position and return */
-            v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
-            v9fs_string_free(&name);
-            return count;
-        }
+    for (struct V9fsDirEnt *e = entries; e; e = e->next) {
+        dent = e->dent;
 
         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);
+            st = e->st;
+            /* e->st should never be NULL, but just to be sure */
+            if (!st) {
+                err = -1;
+                break;
+            }
+
+            /* remap inode */
+            err = stat_to_qid(pdu, st, &qid);
             if (err < 0) {
-                v9fs_readdir_unlock(&fidp->fs.dir);
-                v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
-                v9fs_string_free(&name);
-                return err;
+                break;
             }
         } 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
+             * latter reason we don't call stat_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
@@ -2390,25 +2391,26 @@ static int coroutine_fn v9fs_do_readdir(V9fsPDU *pdu, V9fsFidState *fidp,
             qid.version = 0;
         }
 
+        v9fs_string_init(&name);
+        v9fs_string_sprintf(&name, "%s", dent->d_name);
+
         /* 11 = 7 + 4 (7 = start offset, 4 = space for storing count) */
         len = pdu_marshal(pdu, 11 + count, "Qqbs",
                           &qid, dent->d_off,
                           dent->d_type, &name);
 
-        v9fs_readdir_unlock(&fidp->fs.dir);
+        v9fs_string_free(&name);
 
         if (len < 0) {
-            v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
-            v9fs_string_free(&name);
-            return len;
+            err = len;
+            break;
         }
+
         count += len;
-        v9fs_string_free(&name);
-        saved_dir_pos = dent->d_off;
     }
 
-    v9fs_readdir_unlock(&fidp->fs.dir);
-
+out:
+    v9fs_free_dirents(entries);
     if (err < 0) {
         return err;
     }
@@ -2451,12 +2453,15 @@ static void coroutine_fn v9fs_readdir(void *opaque)
         retval = -EINVAL;
         goto out;
     }
-    if (initial_offset == 0) {
-        v9fs_co_rewinddir(pdu, fidp);
-    } else {
-        v9fs_co_seekdir(pdu, fidp, initial_offset);
+    if (s->proto_version != V9FS_PROTO_2000L) {
+        warn_report_once(
+            "9p: bad client: T_readdir request only expected with 9P2000.L "
+            "protocol version"
+        );
+        retval = -EOPNOTSUPP;
+        goto out;
     }
-    count = v9fs_do_readdir(pdu, fidp, max_count);
+    count = v9fs_do_readdir(pdu, fidp, (off_t) initial_offset, max_count);
     if (count < 0) {
         retval = count;
         goto out;