--- qemu/hw/9pfs/virtio-9p.c	2018/04/24 19:02:21	1.1
+++ qemu/hw/9pfs/virtio-9p.c	2018/04/24 19:51:10	1.1.1.3
@@ -17,10 +17,14 @@
 #include "hw/virtio-pci.h"
 #include "virtio-9p.h"
 #include "fsdev/qemu-fsdev.h"
-#include "virtio-9p-debug.h"
 #include "virtio-9p-xattr.h"
-
-int debug_9p_pdu;
+#include "virtio-9p-coth.h"
+#include "trace.h"
+#include "migration.h"
+
+int open_fd_hw;
+int total_open_fd;
+static int open_fd_rc;
 
 enum {
     Oread   = 0x00,
@@ -68,359 +72,99 @@ static int omode_to_uflags(int8_t mode)
     return ret;
 }
 
-void cred_init(FsCred *credp)
-{
-    credp->fc_uid = -1;
-    credp->fc_gid = -1;
-    credp->fc_mode = -1;
-    credp->fc_rdev = -1;
-}
-
-static int v9fs_do_lstat(V9fsState *s, V9fsString *path, struct stat *stbuf)
-{
-    return s->ops->lstat(&s->ctx, path->data, stbuf);
-}
+struct dotl_openflag_map {
+    int dotl_flag;
+    int open_flag;
+};
 
-static ssize_t v9fs_do_readlink(V9fsState *s, V9fsString *path, V9fsString *buf)
+static int dotl_to_open_flags(int flags)
 {
-    ssize_t len;
-
-    buf->data = qemu_malloc(1024);
+    int i;
+    /*
+     * We have same bits for P9_DOTL_READONLY, P9_DOTL_WRONLY
+     * and P9_DOTL_NOACCESS
+     */
+    int oflags = flags & O_ACCMODE;
 
-    len = s->ops->readlink(&s->ctx, path->data, buf->data, 1024 - 1);
-    if (len > -1) {
-        buf->size = len;
-        buf->data[len] = 0;
+    struct dotl_openflag_map dotl_oflag_map[] = {
+        { P9_DOTL_CREATE, O_CREAT },
+        { P9_DOTL_EXCL, O_EXCL },
+        { P9_DOTL_NOCTTY , O_NOCTTY },
+        { P9_DOTL_TRUNC, O_TRUNC },
+        { P9_DOTL_APPEND, O_APPEND },
+        { P9_DOTL_NONBLOCK, O_NONBLOCK } ,
+        { P9_DOTL_DSYNC, O_DSYNC },
+        { P9_DOTL_FASYNC, FASYNC },
+        { P9_DOTL_DIRECT, O_DIRECT },
+        { P9_DOTL_LARGEFILE, O_LARGEFILE },
+        { P9_DOTL_DIRECTORY, O_DIRECTORY },
+        { P9_DOTL_NOFOLLOW, O_NOFOLLOW },
+        { P9_DOTL_NOATIME, O_NOATIME },
+        { P9_DOTL_SYNC, O_SYNC },
+    };
+
+    for (i = 0; i < ARRAY_SIZE(dotl_oflag_map); i++) {
+        if (flags & dotl_oflag_map[i].dotl_flag) {
+            oflags |= dotl_oflag_map[i].open_flag;
+        }
     }
 
-    return len;
-}
-
-static int v9fs_do_close(V9fsState *s, int fd)
-{
-    return s->ops->close(&s->ctx, fd);
-}
-
-static int v9fs_do_closedir(V9fsState *s, DIR *dir)
-{
-    return s->ops->closedir(&s->ctx, dir);
+    return oflags;
 }
 
-static int v9fs_do_open(V9fsState *s, V9fsString *path, int flags)
-{
-    return s->ops->open(&s->ctx, path->data, flags);
-}
-
-static DIR *v9fs_do_opendir(V9fsState *s, V9fsString *path)
-{
-    return s->ops->opendir(&s->ctx, path->data);
-}
-
-static void v9fs_do_rewinddir(V9fsState *s, DIR *dir)
-{
-    return s->ops->rewinddir(&s->ctx, dir);
-}
-
-static off_t v9fs_do_telldir(V9fsState *s, DIR *dir)
-{
-    return s->ops->telldir(&s->ctx, dir);
-}
-
-static struct dirent *v9fs_do_readdir(V9fsState *s, DIR *dir)
-{
-    return s->ops->readdir(&s->ctx, dir);
-}
-
-static void v9fs_do_seekdir(V9fsState *s, DIR *dir, off_t off)
-{
-    return s->ops->seekdir(&s->ctx, dir, off);
-}
-
-static int v9fs_do_preadv(V9fsState *s, int fd, const struct iovec *iov,
-                            int iovcnt, int64_t offset)
-{
-    return s->ops->preadv(&s->ctx, fd, iov, iovcnt, offset);
-}
-
-static int v9fs_do_pwritev(V9fsState *s, int fd, const struct iovec *iov,
-                       int iovcnt, int64_t offset)
-{
-    return s->ops->pwritev(&s->ctx, fd, iov, iovcnt, offset);
-}
-
-static int v9fs_do_chmod(V9fsState *s, V9fsString *path, mode_t mode)
-{
-    FsCred cred;
-    cred_init(&cred);
-    cred.fc_mode = mode;
-    return s->ops->chmod(&s->ctx, path->data, &cred);
-}
-
-static int v9fs_do_mknod(V9fsState *s, char *name,
-        mode_t mode, dev_t dev, uid_t uid, gid_t gid)
-{
-    FsCred cred;
-    cred_init(&cred);
-    cred.fc_uid = uid;
-    cred.fc_gid = gid;
-    cred.fc_mode = mode;
-    cred.fc_rdev = dev;
-    return s->ops->mknod(&s->ctx, name, &cred);
-}
-
-static int v9fs_do_mkdir(V9fsState *s, char *name, mode_t mode,
-                uid_t uid, gid_t gid)
-{
-    FsCred cred;
-
-    cred_init(&cred);
-    cred.fc_uid = uid;
-    cred.fc_gid = gid;
-    cred.fc_mode = mode;
-
-    return s->ops->mkdir(&s->ctx, name, &cred);
-}
-
-static int v9fs_do_fstat(V9fsState *s, int fd, struct stat *stbuf)
-{
-    return s->ops->fstat(&s->ctx, fd, stbuf);
-}
-
-static int v9fs_do_open2(V9fsState *s, char *fullname, uid_t uid, gid_t gid,
-        int flags, int mode)
-{
-    FsCred cred;
-
-    cred_init(&cred);
-    cred.fc_uid = uid;
-    cred.fc_gid = gid;
-    cred.fc_mode = mode & 07777;
-
-    return s->ops->open2(&s->ctx, fullname, flags, &cred);
-}
-
-static int v9fs_do_symlink(V9fsState *s, V9fsFidState *fidp,
-        const char *oldpath, const char *newpath, gid_t gid)
-{
-    FsCred cred;
-    cred_init(&cred);
-    cred.fc_uid = fidp->uid;
-    cred.fc_gid = gid;
-    cred.fc_mode = 0777;
-
-    return s->ops->symlink(&s->ctx, oldpath, newpath, &cred);
-}
-
-static int v9fs_do_link(V9fsState *s, V9fsString *oldpath, V9fsString *newpath)
-{
-    return s->ops->link(&s->ctx, oldpath->data, newpath->data);
-}
-
-static int v9fs_do_truncate(V9fsState *s, V9fsString *path, off_t size)
-{
-    return s->ops->truncate(&s->ctx, path->data, size);
-}
-
-static int v9fs_do_rename(V9fsState *s, V9fsString *oldpath,
-                            V9fsString *newpath)
-{
-    return s->ops->rename(&s->ctx, oldpath->data, newpath->data);
-}
-
-static int v9fs_do_chown(V9fsState *s, V9fsString *path, uid_t uid, gid_t gid)
-{
-    FsCred cred;
-    cred_init(&cred);
-    cred.fc_uid = uid;
-    cred.fc_gid = gid;
-
-    return s->ops->chown(&s->ctx, path->data, &cred);
-}
-
-static int v9fs_do_utimensat(V9fsState *s, V9fsString *path,
-                                           const struct timespec times[2])
-{
-    return s->ops->utimensat(&s->ctx, path->data, times);
-}
-
-static int v9fs_do_remove(V9fsState *s, V9fsString *path)
-{
-    return s->ops->remove(&s->ctx, path->data);
-}
-
-static int v9fs_do_fsync(V9fsState *s, int fd, int datasync)
-{
-    return s->ops->fsync(&s->ctx, fd, datasync);
-}
-
-static int v9fs_do_statfs(V9fsState *s, V9fsString *path, struct statfs *stbuf)
-{
-    return s->ops->statfs(&s->ctx, path->data, stbuf);
-}
-
-static ssize_t v9fs_do_lgetxattr(V9fsState *s, V9fsString *path,
-                             V9fsString *xattr_name,
-                             void *value, size_t size)
-{
-    return s->ops->lgetxattr(&s->ctx, path->data,
-                             xattr_name->data, value, size);
-}
-
-static ssize_t v9fs_do_llistxattr(V9fsState *s, V9fsString *path,
-                              void *value, size_t size)
-{
-    return s->ops->llistxattr(&s->ctx, path->data,
-                              value, size);
-}
-
-static int v9fs_do_lsetxattr(V9fsState *s, V9fsString *path,
-                             V9fsString *xattr_name,
-                             void *value, size_t size, int flags)
-{
-    return s->ops->lsetxattr(&s->ctx, path->data,
-                             xattr_name->data, value, size, flags);
-}
-
-static int v9fs_do_lremovexattr(V9fsState *s, V9fsString *path,
-                                V9fsString *xattr_name)
-{
-    return s->ops->lremovexattr(&s->ctx, path->data,
-                                xattr_name->data);
-}
-
-
-static void v9fs_string_init(V9fsString *str)
+void cred_init(FsCred *credp)
 {
-    str->data = NULL;
-    str->size = 0;
+    credp->fc_uid = -1;
+    credp->fc_gid = -1;
+    credp->fc_mode = -1;
+    credp->fc_rdev = -1;
 }
 
-static void v9fs_string_free(V9fsString *str)
+static int get_dotl_openflags(V9fsState *s, int oflags)
 {
-    qemu_free(str->data);
-    str->data = NULL;
-    str->size = 0;
+    int flags;
+    /*
+     * Filter the client open flags
+     */
+    flags = dotl_to_open_flags(oflags);
+    flags &= ~(O_NOCTTY | O_ASYNC | O_CREAT);
+    /*
+     * Ignore direct disk access hint until the server supports it.
+     */
+    flags &= ~O_DIRECT;
+    return flags;
 }
 
-static void v9fs_string_null(V9fsString *str)
+void v9fs_path_init(V9fsPath *path)
 {
-    v9fs_string_free(str);
+    path->data = NULL;
+    path->size = 0;
 }
 
-static int number_to_string(void *arg, char type)
+void v9fs_path_free(V9fsPath *path)
 {
-    unsigned int ret = 0;
-
-    switch (type) {
-    case 'u': {
-        unsigned int num = *(unsigned int *)arg;
-
-        do {
-            ret++;
-            num = num/10;
-        } while (num);
-        break;
-    }
-    case 'U': {
-        unsigned long num = *(unsigned long *)arg;
-        do {
-            ret++;
-            num = num/10;
-        } while (num);
-        break;
-    }
-    default:
-        printf("Number_to_string: Unknown number format\n");
-        return -1;
-    }
-
-    return ret;
+    g_free(path->data);
+    path->data = NULL;
+    path->size = 0;
 }
 
-static int GCC_FMT_ATTR(2, 0)
-v9fs_string_alloc_printf(char **strp, const char *fmt, va_list ap)
+void v9fs_path_copy(V9fsPath *lhs, V9fsPath *rhs)
 {
-    va_list ap2;
-    char *iter = (char *)fmt;
-    int len = 0;
-    int nr_args = 0;
-    char *arg_char_ptr;
-    unsigned int arg_uint;
-    unsigned long arg_ulong;
-
-    /* Find the number of %'s that denotes an argument */
-    for (iter = strstr(iter, "%"); iter; iter = strstr(iter, "%")) {
-        nr_args++;
-        iter++;
-    }
-
-    len = strlen(fmt) - 2*nr_args;
-
-    if (!nr_args) {
-        goto alloc_print;
-    }
-
-    va_copy(ap2, ap);
-
-    iter = (char *)fmt;
-
-    /* Now parse the format string */
-    for (iter = strstr(iter, "%"); iter; iter = strstr(iter, "%")) {
-        iter++;
-        switch (*iter) {
-        case 'u':
-            arg_uint = va_arg(ap2, unsigned int);
-            len += number_to_string((void *)&arg_uint, 'u');
-            break;
-        case 'l':
-            if (*++iter == 'u') {
-                arg_ulong = va_arg(ap2, unsigned long);
-                len += number_to_string((void *)&arg_ulong, 'U');
-            } else {
-                return -1;
-            }
-            break;
-        case 's':
-            arg_char_ptr = va_arg(ap2, char *);
-            len += strlen(arg_char_ptr);
-            break;
-        case 'c':
-            len += 1;
-            break;
-        default:
-            fprintf(stderr,
-		    "v9fs_string_alloc_printf:Incorrect format %c", *iter);
-            return -1;
-        }
-        iter++;
-    }
-
-alloc_print:
-    *strp = qemu_malloc((len + 1) * sizeof(**strp));
-
-    return vsprintf(*strp, fmt, ap);
+    v9fs_path_free(lhs);
+    lhs->data = g_malloc(rhs->size);
+    memcpy(lhs->data, rhs->data, rhs->size);
+    lhs->size = rhs->size;
 }
 
-static void GCC_FMT_ATTR(2, 3)
-v9fs_string_sprintf(V9fsString *str, const char *fmt, ...)
+int v9fs_name_to_path(V9fsState *s, V9fsPath *dirpath,
+                      const char *name, V9fsPath *path)
 {
-    va_list ap;
     int err;
-
-    v9fs_string_free(str);
-
-    va_start(ap, fmt);
-    err = v9fs_string_alloc_printf(&str->data, fmt, ap);
-    BUG_ON(err == -1);
-    va_end(ap);
-
-    str->size = err;
-}
-
-static void v9fs_string_copy(V9fsString *lhs, V9fsString *rhs)
-{
-    v9fs_string_free(lhs);
-    v9fs_string_sprintf(lhs, "%s", rhs->data);
+    err = s->ops->name_to_path(&s->ctx, dirpath, name, path);
+    if (err < 0) {
+        err = -errno;
+    }
+    return err;
 }
 
 /*
@@ -429,10 +173,10 @@ static void v9fs_string_copy(V9fsString
  * E.g. "a/b" is an ancestor of "a/b/c" but not of "a/bc/d".
  * As a special case, We treat s1 as ancestor of s2 if they are same!
  */
-static int v9fs_path_is_ancestor(V9fsString *s1, V9fsString *s2)
+static int v9fs_path_is_ancestor(V9fsPath *s1, V9fsPath *s2)
 {
-    if (!strncmp(s1->data, s2->data, s1->size)) {
-        if (s2->data[s1->size] == '\0' || s2->data[s1->size] == '/') {
+    if (!strncmp(s1->data, s2->data, s1->size - 1)) {
+        if (s2->data[s1->size - 1] == '\0' || s2->data[s1->size - 1] == '/') {
             return 1;
         }
     }
@@ -444,16 +188,61 @@ static size_t v9fs_string_size(V9fsStrin
     return str->size;
 }
 
-static V9fsFidState *lookup_fid(V9fsState *s, int32_t fid)
+/*
+ * returns 0 if fid got re-opened, 1 if not, < 0 on error */
+static int v9fs_reopen_fid(V9fsPDU *pdu, V9fsFidState *f)
+{
+    int err = 1;
+    if (f->fid_type == P9_FID_FILE) {
+        if (f->fs.fd == -1) {
+            do {
+                err = v9fs_co_open(pdu, f, f->open_flags);
+            } while (err == -EINTR && !pdu->cancelled);
+        }
+    } else if (f->fid_type == P9_FID_DIR) {
+        if (f->fs.dir == NULL) {
+            do {
+                err = v9fs_co_opendir(pdu, f);
+            } while (err == -EINTR && !pdu->cancelled);
+        }
+    }
+    return err;
+}
+
+static V9fsFidState *get_fid(V9fsPDU *pdu, int32_t fid)
 {
+    int err;
     V9fsFidState *f;
+    V9fsState *s = pdu->s;
 
     for (f = s->fid_list; f; f = f->next) {
+        BUG_ON(f->clunked);
         if (f->fid == fid) {
+            /*
+             * Update the fid ref upfront so that
+             * we don't get reclaimed when we yield
+             * in open later.
+             */
+            f->ref++;
+            /*
+             * check whether we need to reopen the
+             * file. We might have closed the fd
+             * while trying to free up some file
+             * descriptors.
+             */
+            err = v9fs_reopen_fid(pdu, f);
+            if (err < 0) {
+                f->ref--;
+                return NULL;
+            }
+            /*
+             * Mark the fid as referenced so that the LRU
+             * reclaim won't close the file descriptor
+             */
+            f->flags |= FID_REFERENCED;
             return f;
         }
     }
-
     return NULL;
 }
 
@@ -461,23 +250,29 @@ static V9fsFidState *alloc_fid(V9fsState
 {
     V9fsFidState *f;
 
-    f = lookup_fid(s, fid);
-    if (f) {
-        return NULL;
+    for (f = s->fid_list; f; f = f->next) {
+        /* If fid is already there return NULL */
+        BUG_ON(f->clunked);
+        if (f->fid == fid) {
+            return NULL;
+        }
     }
-
-    f = qemu_mallocz(sizeof(V9fsFidState));
-
+    f = g_malloc0(sizeof(V9fsFidState));
     f->fid = fid;
     f->fid_type = P9_FID_NONE;
-
+    f->ref = 1;
+    /*
+     * Mark the fid as referenced so that the LRU
+     * reclaim won't close the file descriptor
+     */
+    f->flags |= FID_REFERENCED;
     f->next = s->fid_list;
     s->fid_list = f;
 
     return f;
 }
 
-static int v9fs_xattr_fid_clunk(V9fsState *s, V9fsFidState *fidp)
+static int v9fs_xattr_fid_clunk(V9fsPDU *pdu, V9fsFidState *fidp)
 {
     int retval = 0;
 
@@ -495,25 +290,70 @@ static int v9fs_xattr_fid_clunk(V9fsStat
         goto free_out;
     }
     if (fidp->fs.xattr.len) {
-        retval = v9fs_do_lsetxattr(s, &fidp->path, &fidp->fs.xattr.name,
+        retval = v9fs_co_lsetxattr(pdu, &fidp->path, &fidp->fs.xattr.name,
                                    fidp->fs.xattr.value,
                                    fidp->fs.xattr.len,
                                    fidp->fs.xattr.flags);
     } else {
-        retval = v9fs_do_lremovexattr(s, &fidp->path, &fidp->fs.xattr.name);
+        retval = v9fs_co_lremovexattr(pdu, &fidp->path, &fidp->fs.xattr.name);
     }
 free_out:
     v9fs_string_free(&fidp->fs.xattr.name);
 free_value:
     if (fidp->fs.xattr.value) {
-        qemu_free(fidp->fs.xattr.value);
+        g_free(fidp->fs.xattr.value);
     }
     return retval;
 }
 
-static int free_fid(V9fsState *s, int32_t fid)
+static int free_fid(V9fsPDU *pdu, V9fsFidState *fidp)
 {
     int retval = 0;
+
+    if (fidp->fid_type == P9_FID_FILE) {
+        /* If we reclaimed the fd no need to close */
+        if (fidp->fs.fd != -1) {
+            retval = v9fs_co_close(pdu, &fidp->fs);
+        }
+    } else if (fidp->fid_type == P9_FID_DIR) {
+        if (fidp->fs.dir != NULL) {
+            retval = v9fs_co_closedir(pdu, &fidp->fs);
+        }
+    } else if (fidp->fid_type == P9_FID_XATTR) {
+        retval = v9fs_xattr_fid_clunk(pdu, fidp);
+    }
+    v9fs_path_free(&fidp->path);
+    g_free(fidp);
+    return retval;
+}
+
+static void put_fid(V9fsPDU *pdu, V9fsFidState *fidp)
+{
+    BUG_ON(!fidp->ref);
+    fidp->ref--;
+    /*
+     * Don't free the fid if it is in reclaim list
+     */
+    if (!fidp->ref && fidp->clunked) {
+        if (fidp->fid == pdu->s->root_fid) {
+            /*
+             * if the clunked fid is root fid then we
+             * have unmounted the fs on the client side.
+             * delete the migration blocker. Ideally, this
+             * should be hooked to transport close notification
+             */
+            if (pdu->s->migration_blocker) {
+                migrate_del_blocker(pdu->s->migration_blocker);
+                error_free(pdu->s->migration_blocker);
+                pdu->s->migration_blocker = NULL;
+            }
+        }
+        free_fid(pdu, fidp);
+    }
+}
+
+static V9fsFidState *clunk_fid(V9fsState *s, int32_t fid)
+{
     V9fsFidState **fidpp, *fidp;
 
     for (fidpp = &s->fid_list; *fidpp; fidpp = &(*fidpp)->next) {
@@ -521,25 +361,151 @@ static int free_fid(V9fsState *s, int32_
             break;
         }
     }
-
     if (*fidpp == NULL) {
-        return -ENOENT;
+        return NULL;
     }
-
     fidp = *fidpp;
     *fidpp = fidp->next;
+    fidp->clunked = 1;
+    return fidp;
+}
 
-    if (fidp->fid_type == P9_FID_FILE) {
-        v9fs_do_close(s, fidp->fs.fd);
-    } else if (fidp->fid_type == P9_FID_DIR) {
-        v9fs_do_closedir(s, fidp->fs.dir);
-    } else if (fidp->fid_type == P9_FID_XATTR) {
-        retval = v9fs_xattr_fid_clunk(s, fidp);
+void v9fs_reclaim_fd(V9fsPDU *pdu)
+{
+    int reclaim_count = 0;
+    V9fsState *s = pdu->s;
+    V9fsFidState *f, *reclaim_list = NULL;
+
+    for (f = s->fid_list; f; f = f->next) {
+        /*
+         * Unlink fids cannot be reclaimed. Check
+         * for them and skip them. Also skip fids
+         * currently being operated on.
+         */
+        if (f->ref || f->flags & FID_NON_RECLAIMABLE) {
+            continue;
+        }
+        /*
+         * if it is a recently referenced fid
+         * we leave the fid untouched and clear the
+         * reference bit. We come back to it later
+         * in the next iteration. (a simple LRU without
+         * moving list elements around)
+         */
+        if (f->flags & FID_REFERENCED) {
+            f->flags &= ~FID_REFERENCED;
+            continue;
+        }
+        /*
+         * Add fids to reclaim list.
+         */
+        if (f->fid_type == P9_FID_FILE) {
+            if (f->fs.fd != -1) {
+                /*
+                 * Up the reference count so that
+                 * a clunk request won't free this fid
+                 */
+                f->ref++;
+                f->rclm_lst = reclaim_list;
+                reclaim_list = f;
+                f->fs_reclaim.fd = f->fs.fd;
+                f->fs.fd = -1;
+                reclaim_count++;
+            }
+        } else if (f->fid_type == P9_FID_DIR) {
+            if (f->fs.dir != NULL) {
+                /*
+                 * Up the reference count so that
+                 * a clunk request won't free this fid
+                 */
+                f->ref++;
+                f->rclm_lst = reclaim_list;
+                reclaim_list = f;
+                f->fs_reclaim.dir = f->fs.dir;
+                f->fs.dir = NULL;
+                reclaim_count++;
+            }
+        }
+        if (reclaim_count >= open_fd_rc) {
+            break;
+        }
+    }
+    /*
+     * Now close the fid in reclaim list. Free them if they
+     * are already clunked.
+     */
+    while (reclaim_list) {
+        f = reclaim_list;
+        reclaim_list = f->rclm_lst;
+        if (f->fid_type == P9_FID_FILE) {
+            v9fs_co_close(pdu, &f->fs_reclaim);
+        } else if (f->fid_type == P9_FID_DIR) {
+            v9fs_co_closedir(pdu, &f->fs_reclaim);
+        }
+        f->rclm_lst = NULL;
+        /*
+         * Now drop the fid reference, free it
+         * if clunked.
+         */
+        put_fid(pdu, f);
     }
-    v9fs_string_free(&fidp->path);
-    qemu_free(fidp);
+}
 
-    return retval;
+static int v9fs_mark_fids_unreclaim(V9fsPDU *pdu, V9fsPath *path)
+{
+    int err;
+    V9fsState *s = pdu->s;
+    V9fsFidState *fidp, head_fid;
+
+    head_fid.next = s->fid_list;
+    for (fidp = s->fid_list; fidp; fidp = fidp->next) {
+        if (fidp->path.size != path->size) {
+            continue;
+        }
+        if (!memcmp(fidp->path.data, path->data, path->size)) {
+            /* Mark the fid non reclaimable. */
+            fidp->flags |= FID_NON_RECLAIMABLE;
+
+            /* reopen the file/dir if already closed */
+            err = v9fs_reopen_fid(pdu, fidp);
+            if (err < 0) {
+                return -1;
+            }
+            /*
+             * Go back to head of fid list because
+             * the list could have got updated when
+             * switched to the worker thread
+             */
+            if (err == 0) {
+                fidp = &head_fid;
+            }
+        }
+    }
+    return 0;
+}
+
+static void virtfs_reset(V9fsPDU *pdu)
+{
+    V9fsState *s = pdu->s;
+    V9fsFidState *fidp = NULL;
+
+    /* Free all fids */
+    while (s->fid_list) {
+        fidp = s->fid_list;
+        s->fid_list = fidp->next;
+
+        if (fidp->ref) {
+            fidp->clunked = 1;
+        } else {
+            free_fid(pdu, fidp);
+        }
+    }
+    if (fidp) {
+        /* One or more unclunked fids found... */
+        error_report("9pfs:%s: One or more uncluncked fids "
+                     "found during reset", __func__);
+    }
+    return;
 }
 
 #define P9_QID_TYPE_DIR         0x80
@@ -572,6 +538,7 @@ static void stat_to_qid(const struct sta
 {
     size_t 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);
@@ -584,16 +551,15 @@ static void stat_to_qid(const struct sta
     }
 }
 
-static int fid_to_qid(V9fsState *s, V9fsFidState *fidp, V9fsQID *qidp)
+static int fid_to_qid(V9fsPDU *pdu, V9fsFidState *fidp, V9fsQID *qidp)
 {
     struct stat stbuf;
     int err;
 
-    err = v9fs_do_lstat(s, &fidp->path, &stbuf);
-    if (err) {
+    err = v9fs_co_lstat(pdu, &fidp->path, &stbuf);
+    if (err < 0) {
         return err;
     }
-
     stat_to_qid(&stbuf, qidp);
     return 0;
 }
@@ -603,8 +569,9 @@ static V9fsPDU *alloc_pdu(V9fsState *s)
     V9fsPDU *pdu = NULL;
 
     if (!QLIST_EMPTY(&s->free_list)) {
-	pdu = QLIST_FIRST(&s->free_list);
-	QLIST_REMOVE(pdu, next);
+        pdu = QLIST_FIRST(&s->free_list);
+        QLIST_REMOVE(pdu, next);
+        QLIST_INSERT_HEAD(&s->active_list, pdu, next);
     }
     return pdu;
 }
@@ -612,264 +579,22 @@ static V9fsPDU *alloc_pdu(V9fsState *s)
 static void free_pdu(V9fsState *s, V9fsPDU *pdu)
 {
     if (pdu) {
-        if (debug_9p_pdu) {
-            pprint_pdu(pdu);
-        }
-        QLIST_INSERT_HEAD(&s->free_list, pdu, next);
-    }
-}
-
-size_t pdu_packunpack(void *addr, struct iovec *sg, int sg_count,
-                        size_t offset, size_t size, int pack)
-{
-    int i = 0;
-    size_t copied = 0;
-
-    for (i = 0; size && i < sg_count; i++) {
-        size_t len;
-        if (offset >= sg[i].iov_len) {
-            /* skip this sg */
-            offset -= sg[i].iov_len;
-            continue;
-        } else {
-            len = MIN(sg[i].iov_len - offset, size);
-            if (pack) {
-                memcpy(sg[i].iov_base + offset, addr, len);
-            } else {
-                memcpy(addr, sg[i].iov_base + offset, len);
-            }
-            size -= len;
-            copied += len;
-            addr += len;
-            if (size) {
-                offset = 0;
-                continue;
-            }
-        }
-    }
-
-    return copied;
-}
-
-static size_t pdu_unpack(void *dst, V9fsPDU *pdu, size_t offset, size_t size)
-{
-    return pdu_packunpack(dst, pdu->elem.out_sg, pdu->elem.out_num,
-                         offset, size, 0);
-}
-
-static size_t pdu_pack(V9fsPDU *pdu, size_t offset, const void *src,
-                        size_t size)
-{
-    return pdu_packunpack((void *)src, pdu->elem.in_sg, pdu->elem.in_num,
-                             offset, size, 1);
-}
-
-static int pdu_copy_sg(V9fsPDU *pdu, size_t offset, int rx, struct iovec *sg)
-{
-    size_t pos = 0;
-    int i, j;
-    struct iovec *src_sg;
-    unsigned int num;
-
-    if (rx) {
-        src_sg = pdu->elem.in_sg;
-        num = pdu->elem.in_num;
-    } else {
-        src_sg = pdu->elem.out_sg;
-        num = pdu->elem.out_num;
-    }
-
-    j = 0;
-    for (i = 0; i < num; i++) {
-        if (offset <= pos) {
-            sg[j].iov_base = src_sg[i].iov_base;
-            sg[j].iov_len = src_sg[i].iov_len;
-            j++;
-        } else if (offset < (src_sg[i].iov_len + pos)) {
-            sg[j].iov_base = src_sg[i].iov_base;
-            sg[j].iov_len = src_sg[i].iov_len;
-            sg[j].iov_base += (offset - pos);
-            sg[j].iov_len -= (offset - pos);
-            j++;
-        }
-        pos += src_sg[i].iov_len;
-    }
-
-    return j;
-}
-
-static size_t pdu_unmarshal(V9fsPDU *pdu, size_t offset, const char *fmt, ...)
-{
-    size_t old_offset = offset;
-    va_list ap;
-    int i;
-
-    va_start(ap, fmt);
-    for (i = 0; fmt[i]; i++) {
-        switch (fmt[i]) {
-        case 'b': {
-            uint8_t *valp = va_arg(ap, uint8_t *);
-            offset += pdu_unpack(valp, pdu, offset, sizeof(*valp));
-            break;
-        }
-        case 'w': {
-            uint16_t val, *valp;
-            valp = va_arg(ap, uint16_t *);
-            offset += pdu_unpack(&val, pdu, offset, sizeof(val));
-            *valp = le16_to_cpu(val);
-            break;
-        }
-        case 'd': {
-            uint32_t val, *valp;
-            valp = va_arg(ap, uint32_t *);
-            offset += pdu_unpack(&val, pdu, offset, sizeof(val));
-            *valp = le32_to_cpu(val);
-            break;
-        }
-        case 'q': {
-            uint64_t val, *valp;
-            valp = va_arg(ap, uint64_t *);
-            offset += pdu_unpack(&val, pdu, offset, sizeof(val));
-            *valp = le64_to_cpu(val);
-            break;
-        }
-        case 'v': {
-            struct iovec *iov = va_arg(ap, struct iovec *);
-            int *iovcnt = va_arg(ap, int *);
-            *iovcnt = pdu_copy_sg(pdu, offset, 0, iov);
-            break;
-        }
-        case 's': {
-            V9fsString *str = va_arg(ap, V9fsString *);
-            offset += pdu_unmarshal(pdu, offset, "w", &str->size);
-            /* FIXME: sanity check str->size */
-            str->data = qemu_malloc(str->size + 1);
-            offset += pdu_unpack(str->data, pdu, offset, str->size);
-            str->data[str->size] = 0;
-            break;
-        }
-        case 'Q': {
-            V9fsQID *qidp = va_arg(ap, V9fsQID *);
-            offset += pdu_unmarshal(pdu, offset, "bdq",
-                        &qidp->type, &qidp->version, &qidp->path);
-            break;
-        }
-        case 'S': {
-            V9fsStat *statp = va_arg(ap, V9fsStat *);
-            offset += pdu_unmarshal(pdu, offset, "wwdQdddqsssssddd",
-                        &statp->size, &statp->type, &statp->dev,
-                        &statp->qid, &statp->mode, &statp->atime,
-                        &statp->mtime, &statp->length,
-                        &statp->name, &statp->uid, &statp->gid,
-                        &statp->muid, &statp->extension,
-                        &statp->n_uid, &statp->n_gid,
-                        &statp->n_muid);
-            break;
-        }
-        case 'I': {
-            V9fsIattr *iattr = va_arg(ap, V9fsIattr *);
-            offset += pdu_unmarshal(pdu, offset, "ddddqqqqq",
-                        &iattr->valid, &iattr->mode,
-                        &iattr->uid, &iattr->gid, &iattr->size,
-                        &iattr->atime_sec, &iattr->atime_nsec,
-                        &iattr->mtime_sec, &iattr->mtime_nsec);
-            break;
-        }
-        default:
-            break;
-        }
-    }
-
-    va_end(ap);
-
-    return offset - old_offset;
-}
-
-static size_t pdu_marshal(V9fsPDU *pdu, size_t offset, const char *fmt, ...)
-{
-    size_t old_offset = offset;
-    va_list ap;
-    int i;
-
-    va_start(ap, fmt);
-    for (i = 0; fmt[i]; i++) {
-        switch (fmt[i]) {
-        case 'b': {
-            uint8_t val = va_arg(ap, int);
-            offset += pdu_pack(pdu, offset, &val, sizeof(val));
-            break;
-        }
-        case 'w': {
-            uint16_t val;
-            cpu_to_le16w(&val, va_arg(ap, int));
-            offset += pdu_pack(pdu, offset, &val, sizeof(val));
-            break;
-        }
-        case 'd': {
-            uint32_t val;
-            cpu_to_le32w(&val, va_arg(ap, uint32_t));
-            offset += pdu_pack(pdu, offset, &val, sizeof(val));
-            break;
-        }
-        case 'q': {
-            uint64_t val;
-            cpu_to_le64w(&val, va_arg(ap, uint64_t));
-            offset += pdu_pack(pdu, offset, &val, sizeof(val));
-            break;
-        }
-        case 'v': {
-            struct iovec *iov = va_arg(ap, struct iovec *);
-            int *iovcnt = va_arg(ap, int *);
-            *iovcnt = pdu_copy_sg(pdu, offset, 1, iov);
-            break;
-        }
-        case 's': {
-            V9fsString *str = va_arg(ap, V9fsString *);
-            offset += pdu_marshal(pdu, offset, "w", str->size);
-            offset += pdu_pack(pdu, offset, str->data, str->size);
-            break;
-        }
-        case 'Q': {
-            V9fsQID *qidp = va_arg(ap, V9fsQID *);
-            offset += pdu_marshal(pdu, offset, "bdq",
-                        qidp->type, qidp->version, qidp->path);
-            break;
-        }
-        case 'S': {
-            V9fsStat *statp = va_arg(ap, V9fsStat *);
-            offset += pdu_marshal(pdu, offset, "wwdQdddqsssssddd",
-                        statp->size, statp->type, statp->dev,
-                        &statp->qid, statp->mode, statp->atime,
-                        statp->mtime, statp->length, &statp->name,
-                        &statp->uid, &statp->gid, &statp->muid,
-                        &statp->extension, statp->n_uid,
-                        statp->n_gid, statp->n_muid);
-            break;
-        }
-        case 'A': {
-            V9fsStatDotl *statp = va_arg(ap, V9fsStatDotl *);
-            offset += pdu_marshal(pdu, offset, "qQdddqqqqqqqqqqqqqqq",
-                        statp->st_result_mask,
-                        &statp->qid, statp->st_mode,
-                        statp->st_uid, statp->st_gid,
-                        statp->st_nlink, statp->st_rdev,
-                        statp->st_size, statp->st_blksize, statp->st_blocks,
-                        statp->st_atime_sec, statp->st_atime_nsec,
-                        statp->st_mtime_sec, statp->st_mtime_nsec,
-                        statp->st_ctime_sec, statp->st_ctime_nsec,
-                        statp->st_btime_sec, statp->st_btime_nsec,
-                        statp->st_gen, statp->st_data_version);
-            break;
-        }
-        default:
-            break;
+        /*
+         * Cancelled pdu are added back to the freelist
+         * by flush request .
+         */
+        if (!pdu->cancelled) {
+            QLIST_REMOVE(pdu, next);
+            QLIST_INSERT_HEAD(&s->free_list, pdu, next);
         }
     }
-    va_end(ap);
-
-    return offset - old_offset;
 }
 
+/*
+ * We don't do error checking for pdu_marshal/unmarshal here
+ * because we always expect to have enough space to encode
+ * error details
+ */
 static void complete_pdu(V9fsState *s, V9fsPDU *pdu, ssize_t len)
 {
     int8_t id = pdu->id + 1; /* Response */
@@ -893,6 +618,7 @@ static void complete_pdu(V9fsState *s, V
         if (s->proto_version == V9FS_PROTO_2000L) {
             id = P9_RLERROR;
         }
+        trace_v9fs_rerror(pdu->tag, pdu->id, err); /* Trace ERROR */
     }
 
     /* fill out the header */
@@ -908,6 +634,9 @@ static void complete_pdu(V9fsState *s, V
     /* FIXME: we should batch these completions */
     virtio_notify(&s->vdev, s->vq);
 
+    /* Now wakeup anybody waiting in flush for this request */
+    qemu_co_queue_next(&pdu->complete);
+
     free_pdu(s, pdu);
 }
 
@@ -978,6 +707,15 @@ static int donttouch_stat(V9fsStat *stat
     return 0;
 }
 
+static void v9fs_stat_init(V9fsStat *stat)
+{
+    v9fs_string_init(&stat->name);
+    v9fs_string_init(&stat->uid);
+    v9fs_string_init(&stat->gid);
+    v9fs_string_init(&stat->muid);
+    v9fs_string_init(&stat->extension);
+}
+
 static void v9fs_stat_free(V9fsStat *stat)
 {
     v9fs_string_free(&stat->name);
@@ -1027,7 +765,7 @@ static uint32_t stat_to_v9mode(const str
     return mode;
 }
 
-static int stat_to_v9stat(V9fsState *s, V9fsString *name,
+static int stat_to_v9stat(V9fsPDU *pdu, V9fsPath *name,
                             const struct stat *stbuf,
                             V9fsStat *v9stat)
 {
@@ -1053,13 +791,10 @@ static int stat_to_v9stat(V9fsState *s,
     v9fs_string_null(&v9stat->extension);
 
     if (v9stat->mode & P9_STAT_MODE_SYMLINK) {
-        err = v9fs_do_readlink(s, name, &v9stat->extension);
-        if (err == -1) {
-            err = -errno;
+        err = v9fs_co_readlink(pdu, name, &v9stat->extension);
+        if (err < 0) {
             return err;
         }
-        v9stat->extension.data[err] = 0;
-        v9stat->extension.size = err;
     } else if (v9stat->mode & P9_STAT_MODE_DEVICE) {
         v9fs_string_sprintf(&v9stat->extension, "%c %u %u",
                 S_ISCHR(stbuf->st_mode) ? 'c' : 'b',
@@ -1108,7 +843,7 @@ static int stat_to_v9stat(V9fsState *s,
 
 
 static void stat_to_v9stat_dotl(V9fsState *s, const struct stat *stbuf,
-                            V9fsStatDotl *v9lstat)
+                                V9fsStatDotl *v9lstat)
 {
     memset(v9lstat, 0, sizeof(*v9lstat));
 
@@ -1132,42 +867,6 @@ static void stat_to_v9stat_dotl(V9fsStat
     stat_to_qid(stbuf, &v9lstat->qid);
 }
 
-static struct iovec *adjust_sg(struct iovec *sg, int len, int *iovcnt)
-{
-    while (len && *iovcnt) {
-        if (len < sg->iov_len) {
-            sg->iov_len -= len;
-            sg->iov_base += len;
-            len = 0;
-        } else {
-            len -= sg->iov_len;
-            sg++;
-            *iovcnt -= 1;
-        }
-    }
-
-    return sg;
-}
-
-static struct iovec *cap_sg(struct iovec *sg, int cap, int *cnt)
-{
-    int i;
-    int total = 0;
-
-    for (i = 0; i < *cnt; i++) {
-        if ((total + sg[i].iov_len) > cap) {
-            sg[i].iov_len -= ((total + sg[i].iov_len) - cap);
-            i++;
-            break;
-        }
-        total += sg[i].iov_len;
-    }
-
-    *cnt = i;
-
-    return sg;
-}
-
 static void print_sg(struct iovec *sg, int cnt)
 {
     int i;
@@ -1182,21 +881,40 @@ static void print_sg(struct iovec *sg, i
     printf("}\n");
 }
 
-static void v9fs_fix_path(V9fsString *dst, V9fsString *src, int len)
+/* Will call this only for path name based fid */
+static void v9fs_fix_path(V9fsPath *dst, V9fsPath *src, int len)
 {
-    V9fsString str;
-    v9fs_string_init(&str);
-    v9fs_string_copy(&str, dst);
-    v9fs_string_sprintf(dst, "%s%s", src->data, str.data+len);
-    v9fs_string_free(&str);
+    V9fsPath str;
+    v9fs_path_init(&str);
+    v9fs_path_copy(&str, dst);
+    v9fs_string_sprintf((V9fsString *)dst, "%s%s", src->data, str.data+len);
+    v9fs_path_free(&str);
+    /* +1 to include terminating NULL */
+    dst->size++;
 }
 
-static void v9fs_version(V9fsState *s, V9fsPDU *pdu)
+static inline bool is_ro_export(FsContext *ctx)
 {
+    return ctx->export_flags & V9FS_RDONLY;
+}
+
+static void v9fs_version(void *opaque)
+{
+    ssize_t err;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
     V9fsString version;
     size_t offset = 7;
 
-    pdu_unmarshal(pdu, offset, "ds", &s->msize, &version);
+    v9fs_string_init(&version);
+    err = pdu_unmarshal(pdu, offset, "ds", &s->msize, &version);
+    if (err < 0) {
+        offset = err;
+        goto out;
+    }
+    trace_v9fs_version(pdu->tag, pdu->id, s->msize, version.data);
+
+    virtfs_reset(pdu);
 
     if (!strcmp(version.data, "9P2000.u")) {
         s->proto_version = V9FS_PROTO_2000U;
@@ -1206,1087 +924,973 @@ static void v9fs_version(V9fsState *s, V
         v9fs_string_sprintf(&version, "unknown");
     }
 
-    offset += pdu_marshal(pdu, offset, "ds", s->msize, &version);
+    err = pdu_marshal(pdu, offset, "ds", s->msize, &version);
+    if (err < 0) {
+        offset = err;
+        goto out;
+    }
+    offset += err;
+    trace_v9fs_version_return(pdu->tag, pdu->id, s->msize, version.data);
+out:
     complete_pdu(s, pdu, offset);
-
     v9fs_string_free(&version);
+    return;
 }
 
-static void v9fs_attach(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_attach(void *opaque)
 {
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
     int32_t fid, afid, n_uname;
     V9fsString uname, aname;
     V9fsFidState *fidp;
-    V9fsQID qid;
     size_t offset = 7;
+    V9fsQID qid;
     ssize_t err;
 
-    pdu_unmarshal(pdu, offset, "ddssd", &fid, &afid, &uname, &aname, &n_uname);
+    v9fs_string_init(&uname);
+    v9fs_string_init(&aname);
+    err = pdu_unmarshal(pdu, offset, "ddssd", &fid,
+                        &afid, &uname, &aname, &n_uname);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_attach(pdu->tag, pdu->id, fid, afid, uname.data, aname.data);
 
     fidp = alloc_fid(s, fid);
     if (fidp == NULL) {
         err = -EINVAL;
-        goto out;
+        goto out_nofid;
     }
-
     fidp->uid = n_uname;
-
-    v9fs_string_sprintf(&fidp->path, "%s", "/");
-    err = fid_to_qid(s, fidp, &qid);
-    if (err) {
+    err = v9fs_co_name_to_path(pdu, NULL, "/", &fidp->path);
+    if (err < 0) {
         err = -EINVAL;
-        free_fid(s, fid);
+        clunk_fid(s, fid);
         goto out;
     }
-
-    offset += pdu_marshal(pdu, offset, "Q", &qid);
-
-    err = offset;
-out:
-    complete_pdu(s, pdu, err);
-    v9fs_string_free(&uname);
-    v9fs_string_free(&aname);
-}
-
-static void v9fs_stat_post_lstat(V9fsState *s, V9fsStatState *vs, int err)
-{
-    if (err == -1) {
-        err = -errno;
+    err = fid_to_qid(pdu, fidp, &qid);
+    if (err < 0) {
+        err = -EINVAL;
+        clunk_fid(s, fid);
         goto out;
     }
-
-    err = stat_to_v9stat(s, &vs->fidp->path, &vs->stbuf, &vs->v9stat);
-    if (err) {
+    err = pdu_marshal(pdu, offset, "Q", &qid);
+    if (err < 0) {
+        clunk_fid(s, fid);
         goto out;
     }
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "wS", 0, &vs->v9stat);
-    err = vs->offset;
-
+    err += offset;
+    trace_v9fs_attach_return(pdu->tag, pdu->id,
+                             qid.type, qid.version, qid.path);
+    s->root_fid = fid;
+    /* disable migration */
+    error_set(&s->migration_blocker, QERR_VIRTFS_FEATURE_BLOCKS_MIGRATION,
+              s->ctx.fs_root ? s->ctx.fs_root : "NULL", s->tag);
+    migrate_add_blocker(s->migration_blocker);
 out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_stat_free(&vs->v9stat);
-    qemu_free(vs);
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(s, pdu, err);
+    v9fs_string_free(&uname);
+    v9fs_string_free(&aname);
 }
 
-static void v9fs_stat(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_stat(void *opaque)
 {
     int32_t fid;
-    V9fsStatState *vs;
+    V9fsStat v9stat;
     ssize_t err = 0;
+    size_t offset = 7;
+    struct stat stbuf;
+    V9fsFidState *fidp;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    memset(&vs->v9stat, 0, sizeof(vs->v9stat));
-
-    pdu_unmarshal(vs->pdu, vs->offset, "d", &fid);
+    err = pdu_unmarshal(pdu, offset, "d", &fid);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_stat(pdu->tag, pdu->id, fid);
 
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
         err = -ENOENT;
+        goto out_nofid;
+    }
+    err = v9fs_co_lstat(pdu, &fidp->path, &stbuf);
+    if (err < 0) {
         goto out;
     }
-
-    err = v9fs_do_lstat(s, &vs->fidp->path, &vs->stbuf);
-    v9fs_stat_post_lstat(s, vs, err);
-    return;
-
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_stat_free(&vs->v9stat);
-    qemu_free(vs);
-}
-
-static void v9fs_getattr_post_lstat(V9fsState *s, V9fsStatStateDotl *vs,
-                                                                int err)
-{
-    if (err == -1) {
-        err = -errno;
+    err = stat_to_v9stat(pdu, &fidp->path, &stbuf, &v9stat);
+    if (err < 0) {
         goto out;
     }
-
-    stat_to_v9stat_dotl(s, &vs->stbuf, &vs->v9stat_dotl);
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "A", &vs->v9stat_dotl);
-    err = vs->offset;
-
+    err = pdu_marshal(pdu, offset, "wS", 0, &v9stat);
+    if (err < 0) {
+        v9fs_stat_free(&v9stat);
+        goto out;
+    }
+    trace_v9fs_stat_return(pdu->tag, pdu->id, v9stat.mode,
+                           v9stat.atime, v9stat.mtime, v9stat.length);
+    err += offset;
+    v9fs_stat_free(&v9stat);
 out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(s, pdu, err);
 }
 
-static void v9fs_getattr(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_getattr(void *opaque)
 {
     int32_t fid;
-    V9fsStatStateDotl *vs;
-    ssize_t err = 0;
+    size_t offset = 7;
+    ssize_t retval = 0;
+    struct stat stbuf;
     V9fsFidState *fidp;
     uint64_t request_mask;
+    V9fsStatDotl v9stat_dotl;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    memset(&vs->v9stat_dotl, 0, sizeof(vs->v9stat_dotl));
-
-    pdu_unmarshal(vs->pdu, vs->offset, "dq", &fid, &request_mask);
+    retval = pdu_unmarshal(pdu, offset, "dq", &fid, &request_mask);
+    if (retval < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_getattr(pdu->tag, pdu->id, fid, request_mask);
 
-    fidp = lookup_fid(s, fid);
+    fidp = get_fid(pdu, fid);
     if (fidp == NULL) {
-        err = -ENOENT;
-        goto out;
+        retval = -ENOENT;
+        goto out_nofid;
     }
-
-    /* Currently we only support BASIC fields in stat, so there is no
+    /*
+     * Currently we only support BASIC fields in stat, so there is no
      * need to look at request_mask.
      */
-    err = v9fs_do_lstat(s, &fidp->path, &vs->stbuf);
-    v9fs_getattr_post_lstat(s, vs, err);
-    return;
-
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-/* From Linux kernel code */
-#define ATTR_MODE    (1 << 0)
-#define ATTR_UID     (1 << 1)
-#define ATTR_GID     (1 << 2)
-#define ATTR_SIZE    (1 << 3)
-#define ATTR_ATIME   (1 << 4)
-#define ATTR_MTIME   (1 << 5)
-#define ATTR_CTIME   (1 << 6)
-#define ATTR_MASK    127
-#define ATTR_ATIME_SET  (1 << 7)
-#define ATTR_MTIME_SET  (1 << 8)
-
-static void v9fs_setattr_post_truncate(V9fsState *s, V9fsSetattrState *vs,
-                                                                  int err)
-{
-    if (err == -1) {
-        err = -errno;
+    retval = v9fs_co_lstat(pdu, &fidp->path, &stbuf);
+    if (retval < 0) {
         goto out;
     }
-    err = vs->offset;
+    stat_to_v9stat_dotl(s, &stbuf, &v9stat_dotl);
 
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_setattr_post_chown(V9fsState *s, V9fsSetattrState *vs, int err)
-{
-    if (err == -1) {
-        err = -errno;
-        goto out;
+    /*  fill st_gen if requested and supported by underlying fs */
+    if (request_mask & P9_STATS_GEN) {
+        retval = v9fs_co_st_gen(pdu, &fidp->path, stbuf.st_mode, &v9stat_dotl);
+        if (retval < 0) {
+            goto out;
+        }
+        v9stat_dotl.st_result_mask |= P9_STATS_GEN;
     }
-
-    if (vs->v9iattr.valid & (ATTR_SIZE)) {
-        err = v9fs_do_truncate(s, &vs->fidp->path, vs->v9iattr.size);
+    retval = pdu_marshal(pdu, offset, "A", &v9stat_dotl);
+    if (retval < 0) {
+        goto out;
     }
-    v9fs_setattr_post_truncate(s, vs, err);
-    return;
-
+    retval += offset;
+    trace_v9fs_getattr_return(pdu->tag, pdu->id, v9stat_dotl.st_result_mask,
+                              v9stat_dotl.st_mode, v9stat_dotl.st_uid,
+                              v9stat_dotl.st_gid);
 out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(s, pdu, retval);
 }
 
-static void v9fs_setattr_post_utimensat(V9fsState *s, V9fsSetattrState *vs,
-                                                                   int err)
-{
-    if (err == -1) {
-        err = -errno;
-        goto out;
-    }
-
-    /* If the only valid entry in iattr is ctime we can call
-     * chown(-1,-1) to update the ctime of the file
-     */
-    if ((vs->v9iattr.valid & (ATTR_UID | ATTR_GID)) ||
-            ((vs->v9iattr.valid & ATTR_CTIME)
-            && !((vs->v9iattr.valid & ATTR_MASK) & ~ATTR_CTIME))) {
-        if (!(vs->v9iattr.valid & ATTR_UID)) {
-            vs->v9iattr.uid = -1;
-        }
-        if (!(vs->v9iattr.valid & ATTR_GID)) {
-            vs->v9iattr.gid = -1;
-        }
-        err = v9fs_do_chown(s, &vs->fidp->path, vs->v9iattr.uid,
-                                                vs->v9iattr.gid);
-    }
-    v9fs_setattr_post_chown(s, vs, err);
-    return;
+/* Attribute flags */
+#define P9_ATTR_MODE       (1 << 0)
+#define P9_ATTR_UID        (1 << 1)
+#define P9_ATTR_GID        (1 << 2)
+#define P9_ATTR_SIZE       (1 << 3)
+#define P9_ATTR_ATIME      (1 << 4)
+#define P9_ATTR_MTIME      (1 << 5)
+#define P9_ATTR_CTIME      (1 << 6)
+#define P9_ATTR_ATIME_SET  (1 << 7)
+#define P9_ATTR_MTIME_SET  (1 << 8)
 
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
+#define P9_ATTR_MASK    127
 
-static void v9fs_setattr_post_chmod(V9fsState *s, V9fsSetattrState *vs, int err)
+static void v9fs_setattr(void *opaque)
 {
-    if (err == -1) {
-        err = -errno;
-        goto out;
+    int err = 0;
+    int32_t fid;
+    V9fsFidState *fidp;
+    size_t offset = 7;
+    V9fsIattr v9iattr;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
+
+    err = pdu_unmarshal(pdu, offset, "dI", &fid, &v9iattr);
+    if (err < 0) {
+        goto out_nofid;
     }
 
-    if (vs->v9iattr.valid & (ATTR_ATIME | ATTR_MTIME)) {
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
+        err = -EINVAL;
+        goto out_nofid;
+    }
+    if (v9iattr.valid & P9_ATTR_MODE) {
+        err = v9fs_co_chmod(pdu, &fidp->path, v9iattr.mode);
+        if (err < 0) {
+            goto out;
+        }
+    }
+    if (v9iattr.valid & (P9_ATTR_ATIME | P9_ATTR_MTIME)) {
         struct timespec times[2];
-        if (vs->v9iattr.valid & ATTR_ATIME) {
-            if (vs->v9iattr.valid & ATTR_ATIME_SET) {
-                times[0].tv_sec = vs->v9iattr.atime_sec;
-                times[0].tv_nsec = vs->v9iattr.atime_nsec;
+        if (v9iattr.valid & P9_ATTR_ATIME) {
+            if (v9iattr.valid & P9_ATTR_ATIME_SET) {
+                times[0].tv_sec = v9iattr.atime_sec;
+                times[0].tv_nsec = v9iattr.atime_nsec;
             } else {
                 times[0].tv_nsec = UTIME_NOW;
             }
         } else {
             times[0].tv_nsec = UTIME_OMIT;
         }
-
-        if (vs->v9iattr.valid & ATTR_MTIME) {
-            if (vs->v9iattr.valid & ATTR_MTIME_SET) {
-                times[1].tv_sec = vs->v9iattr.mtime_sec;
-                times[1].tv_nsec = vs->v9iattr.mtime_nsec;
+        if (v9iattr.valid & P9_ATTR_MTIME) {
+            if (v9iattr.valid & P9_ATTR_MTIME_SET) {
+                times[1].tv_sec = v9iattr.mtime_sec;
+                times[1].tv_nsec = v9iattr.mtime_nsec;
             } else {
                 times[1].tv_nsec = UTIME_NOW;
             }
         } else {
             times[1].tv_nsec = UTIME_OMIT;
         }
-        err = v9fs_do_utimensat(s, &vs->fidp->path, times);
-    }
-    v9fs_setattr_post_utimensat(s, vs, err);
-    return;
-
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_setattr(V9fsState *s, V9fsPDU *pdu)
-{
-    int32_t fid;
-    V9fsSetattrState *vs;
-    int err = 0;
-
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    pdu_unmarshal(pdu, vs->offset, "dI", &fid, &vs->v9iattr);
-
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
-        err = -EINVAL;
-        goto out;
+        err = v9fs_co_utimensat(pdu, &fidp->path, times);
+        if (err < 0) {
+            goto out;
+        }
     }
-
-    if (vs->v9iattr.valid & ATTR_MODE) {
-        err = v9fs_do_chmod(s, &vs->fidp->path, vs->v9iattr.mode);
+    /*
+     * If the only valid entry in iattr is ctime we can call
+     * chown(-1,-1) to update the ctime of the file
+     */
+    if ((v9iattr.valid & (P9_ATTR_UID | P9_ATTR_GID)) ||
+        ((v9iattr.valid & P9_ATTR_CTIME)
+         && !((v9iattr.valid & P9_ATTR_MASK) & ~P9_ATTR_CTIME))) {
+        if (!(v9iattr.valid & P9_ATTR_UID)) {
+            v9iattr.uid = -1;
+        }
+        if (!(v9iattr.valid & P9_ATTR_GID)) {
+            v9iattr.gid = -1;
+        }
+        err = v9fs_co_chown(pdu, &fidp->path, v9iattr.uid,
+                            v9iattr.gid);
+        if (err < 0) {
+            goto out;
+        }
     }
-
-    v9fs_setattr_post_chmod(s, vs, err);
-    return;
-
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_walk_complete(V9fsState *s, V9fsWalkState *vs, int err)
-{
-    complete_pdu(s, vs->pdu, err);
-
-    if (vs->nwnames && vs->nwnames <= P9_MAXWELEM) {
-        for (vs->name_idx = 0; vs->name_idx < vs->nwnames; vs->name_idx++) {
-            v9fs_string_free(&vs->wnames[vs->name_idx]);
+    if (v9iattr.valid & (P9_ATTR_SIZE)) {
+        err = v9fs_co_truncate(pdu, &fidp->path, v9iattr.size);
+        if (err < 0) {
+            goto out;
         }
-
-        qemu_free(vs->wnames);
-        qemu_free(vs->qids);
     }
+    err = offset;
+out:
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(s, pdu, err);
 }
 
-static void v9fs_walk_marshal(V9fsWalkState *vs)
+static int v9fs_walk_marshal(V9fsPDU *pdu, uint16_t nwnames, V9fsQID *qids)
 {
     int i;
-    vs->offset = 7;
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "w", vs->nwnames);
-
-    for (i = 0; i < vs->nwnames; i++) {
-        vs->offset += pdu_marshal(vs->pdu, vs->offset, "Q", &vs->qids[i]);
-    }
-}
-
-static void v9fs_walk_post_newfid_lstat(V9fsState *s, V9fsWalkState *vs,
-                                                                int err)
-{
-    if (err == -1) {
-        free_fid(s, vs->newfidp->fid);
-        v9fs_string_free(&vs->path);
-        err = -ENOENT;
-        goto out;
-    }
-
-    stat_to_qid(&vs->stbuf, &vs->qids[vs->name_idx]);
-
-    vs->name_idx++;
-    if (vs->name_idx < vs->nwnames) {
-        v9fs_string_sprintf(&vs->path, "%s/%s", vs->newfidp->path.data,
-                                            vs->wnames[vs->name_idx].data);
-        v9fs_string_copy(&vs->newfidp->path, &vs->path);
-
-        err = v9fs_do_lstat(s, &vs->newfidp->path, &vs->stbuf);
-        v9fs_walk_post_newfid_lstat(s, vs, err);
-        return;
-    }
-
-    v9fs_string_free(&vs->path);
-    v9fs_walk_marshal(vs);
-    err = vs->offset;
-out:
-    v9fs_walk_complete(s, vs, err);
-}
+    ssize_t err;
+    size_t offset = 7;
 
-static void v9fs_walk_post_oldfid_lstat(V9fsState *s, V9fsWalkState *vs,
-        int err)
-{
-    if (err == -1) {
-        v9fs_string_free(&vs->path);
-        err = -ENOENT;
-        goto out;
+    err = pdu_marshal(pdu, offset, "w", nwnames);
+    if (err < 0) {
+        return err;
     }
-
-    stat_to_qid(&vs->stbuf, &vs->qids[vs->name_idx]);
-    vs->name_idx++;
-    if (vs->name_idx < vs->nwnames) {
-
-        v9fs_string_sprintf(&vs->path, "%s/%s",
-                vs->fidp->path.data, vs->wnames[vs->name_idx].data);
-        v9fs_string_copy(&vs->fidp->path, &vs->path);
-
-        err = v9fs_do_lstat(s, &vs->fidp->path, &vs->stbuf);
-        v9fs_walk_post_oldfid_lstat(s, vs, err);
-        return;
+    offset += err;
+    for (i = 0; i < nwnames; i++) {
+        err = pdu_marshal(pdu, offset, "Q", &qids[i]);
+        if (err < 0) {
+            return err;
+        }
+        offset += err;
     }
-
-    v9fs_string_free(&vs->path);
-    v9fs_walk_marshal(vs);
-    err = vs->offset;
-out:
-    v9fs_walk_complete(s, vs, err);
+    return offset;
 }
 
-static void v9fs_walk(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_walk(void *opaque)
 {
+    int name_idx;
+    V9fsQID *qids = NULL;
+    int i, err = 0;
+    V9fsPath dpath, path;
+    uint16_t nwnames;
+    struct stat stbuf;
+    size_t offset = 7;
     int32_t fid, newfid;
-    V9fsWalkState *vs;
-    int err = 0;
-    int i;
-
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->wnames = NULL;
-    vs->qids = NULL;
-    vs->offset = 7;
-
-    vs->offset += pdu_unmarshal(vs->pdu, vs->offset, "ddw", &fid,
-                                            &newfid, &vs->nwnames);
+    V9fsString *wnames = NULL;
+    V9fsFidState *fidp;
+    V9fsFidState *newfidp = NULL;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-    if (vs->nwnames && vs->nwnames <= P9_MAXWELEM) {
-        vs->wnames = qemu_mallocz(sizeof(vs->wnames[0]) * vs->nwnames);
+    err = pdu_unmarshal(pdu, offset, "ddw", &fid, &newfid, &nwnames);
+    if (err < 0) {
+        complete_pdu(s, pdu, err);
+        return ;
+    }
+    offset += err;
 
-        vs->qids = qemu_mallocz(sizeof(vs->qids[0]) * vs->nwnames);
+    trace_v9fs_walk(pdu->tag, pdu->id, fid, newfid, nwnames);
 
-        for (i = 0; i < vs->nwnames; i++) {
-            vs->offset += pdu_unmarshal(vs->pdu, vs->offset, "s",
-                                            &vs->wnames[i]);
+    if (nwnames && nwnames <= P9_MAXWELEM) {
+        wnames = g_malloc0(sizeof(wnames[0]) * nwnames);
+        qids   = g_malloc0(sizeof(qids[0]) * nwnames);
+        for (i = 0; i < nwnames; i++) {
+            err = pdu_unmarshal(pdu, offset, "s", &wnames[i]);
+            if (err < 0) {
+                goto out_nofid;
+            }
+            offset += err;
         }
-    } else if (vs->nwnames > P9_MAXWELEM) {
+    } else if (nwnames > P9_MAXWELEM) {
         err = -EINVAL;
-        goto out;
+        goto out_nofid;
     }
-
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
         err = -ENOENT;
-        goto out;
+        goto out_nofid;
     }
-
-    /* FIXME: is this really valid? */
-    if (fid == newfid) {
-
-        BUG_ON(vs->fidp->fid_type != P9_FID_NONE);
-        v9fs_string_init(&vs->path);
-        vs->name_idx = 0;
-
-        if (vs->name_idx < vs->nwnames) {
-            v9fs_string_sprintf(&vs->path, "%s/%s",
-                vs->fidp->path.data, vs->wnames[vs->name_idx].data);
-            v9fs_string_copy(&vs->fidp->path, &vs->path);
-
-            err = v9fs_do_lstat(s, &vs->fidp->path, &vs->stbuf);
-            v9fs_walk_post_oldfid_lstat(s, vs, err);
-            return;
+    v9fs_path_init(&dpath);
+    v9fs_path_init(&path);
+    /*
+     * Both dpath and path initially poin to fidp.
+     * Needed to handle request with nwnames == 0
+     */
+    v9fs_path_copy(&dpath, &fidp->path);
+    v9fs_path_copy(&path, &fidp->path);
+    for (name_idx = 0; name_idx < nwnames; name_idx++) {
+        err = v9fs_co_name_to_path(pdu, &dpath, wnames[name_idx].data, &path);
+        if (err < 0) {
+            goto out;
+        }
+        err = v9fs_co_lstat(pdu, &path, &stbuf);
+        if (err < 0) {
+            goto out;
         }
+        stat_to_qid(&stbuf, &qids[name_idx]);
+        v9fs_path_copy(&dpath, &path);
+    }
+    if (fid == newfid) {
+        BUG_ON(fidp->fid_type != P9_FID_NONE);
+        v9fs_path_copy(&fidp->path, &path);
     } else {
-        vs->newfidp = alloc_fid(s, newfid);
-        if (vs->newfidp == NULL) {
+        newfidp = alloc_fid(s, newfid);
+        if (newfidp == NULL) {
             err = -EINVAL;
             goto out;
         }
-
-        vs->newfidp->uid = vs->fidp->uid;
-        v9fs_string_init(&vs->path);
-        vs->name_idx = 0;
-        v9fs_string_copy(&vs->newfidp->path, &vs->fidp->path);
-
-        if (vs->name_idx < vs->nwnames) {
-            v9fs_string_sprintf(&vs->path, "%s/%s", vs->newfidp->path.data,
-                                vs->wnames[vs->name_idx].data);
-            v9fs_string_copy(&vs->newfidp->path, &vs->path);
-
-            err = v9fs_do_lstat(s, &vs->newfidp->path, &vs->stbuf);
-            v9fs_walk_post_newfid_lstat(s, vs, err);
-            return;
-        }
+        newfidp->uid = fidp->uid;
+        v9fs_path_copy(&newfidp->path, &path);
     }
-
-    v9fs_walk_marshal(vs);
-    err = vs->offset;
+    err = v9fs_walk_marshal(pdu, nwnames, qids);
+    trace_v9fs_walk_return(pdu->tag, pdu->id, nwnames, qids);
 out:
-    v9fs_walk_complete(s, vs, err);
+    put_fid(pdu, fidp);
+    if (newfidp) {
+        put_fid(pdu, newfidp);
+    }
+    v9fs_path_free(&dpath);
+    v9fs_path_free(&path);
+out_nofid:
+    complete_pdu(s, pdu, err);
+    if (nwnames && nwnames <= P9_MAXWELEM) {
+        for (name_idx = 0; name_idx < nwnames; name_idx++) {
+            v9fs_string_free(&wnames[name_idx]);
+        }
+        g_free(wnames);
+        g_free(qids);
+    }
+    return;
 }
 
-static int32_t get_iounit(V9fsState *s, V9fsString *name)
+static int32_t get_iounit(V9fsPDU *pdu, V9fsPath *path)
 {
     struct statfs stbuf;
     int32_t iounit = 0;
+    V9fsState *s = pdu->s;
 
     /*
      * iounit should be multiples of f_bsize (host filesystem block size
      * and as well as less than (client msize - P9_IOHDRSZ))
      */
-    if (!v9fs_do_statfs(s, name, &stbuf)) {
+    if (!v9fs_co_statfs(pdu, path, &stbuf)) {
         iounit = stbuf.f_bsize;
         iounit *= (s->msize - P9_IOHDRSZ)/stbuf.f_bsize;
     }
-
     if (!iounit) {
         iounit = s->msize - P9_IOHDRSZ;
     }
     return iounit;
 }
 
-static void v9fs_open_post_opendir(V9fsState *s, V9fsOpenState *vs, int err)
-{
-    if (vs->fidp->fs.dir == NULL) {
-        err = -errno;
-        goto out;
-    }
-    vs->fidp->fid_type = P9_FID_DIR;
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "Qd", &vs->qid, 0);
-    err = vs->offset;
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-
-}
-
-static void v9fs_open_post_getiounit(V9fsState *s, V9fsOpenState *vs)
-{
-    int err;
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "Qd", &vs->qid, vs->iounit);
-    err = vs->offset;
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_open_post_open(V9fsState *s, V9fsOpenState *vs, int err)
-{
-    if (vs->fidp->fs.fd == -1) {
-        err = -errno;
-        goto out;
-    }
-    vs->fidp->fid_type = P9_FID_FILE;
-    vs->iounit = get_iounit(s, &vs->fidp->path);
-    v9fs_open_post_getiounit(s, vs);
-    return;
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_open_post_lstat(V9fsState *s, V9fsOpenState *vs, int err)
+static void v9fs_open(void *opaque)
 {
     int flags;
-
-    if (err) {
-        err = -errno;
-        goto out;
-    }
-
-    stat_to_qid(&vs->stbuf, &vs->qid);
-
-    if (S_ISDIR(vs->stbuf.st_mode)) {
-        vs->fidp->fs.dir = v9fs_do_opendir(s, &vs->fidp->path);
-        v9fs_open_post_opendir(s, vs, err);
-    } else {
-        if (s->proto_version == V9FS_PROTO_2000L) {
-            flags = vs->mode;
-            flags &= ~(O_NOCTTY | O_ASYNC | O_CREAT);
-            /* Ignore direct disk access hint until the server supports it. */
-            flags &= ~O_DIRECT;
-        } else {
-            flags = omode_to_uflags(vs->mode);
-        }
-        vs->fidp->fs.fd = v9fs_do_open(s, &vs->fidp->path, flags);
-        v9fs_open_post_open(s, vs, err);
-    }
-    return;
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_open(V9fsState *s, V9fsPDU *pdu)
-{
     int32_t fid;
-    V9fsOpenState *vs;
+    int32_t mode;
+    V9fsQID qid;
+    int iounit = 0;
     ssize_t err = 0;
-
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-    vs->mode = 0;
+    size_t offset = 7;
+    struct stat stbuf;
+    V9fsFidState *fidp;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
     if (s->proto_version == V9FS_PROTO_2000L) {
-        pdu_unmarshal(vs->pdu, vs->offset, "dd", &fid, &vs->mode);
+        err = pdu_unmarshal(pdu, offset, "dd", &fid, &mode);
     } else {
-        pdu_unmarshal(vs->pdu, vs->offset, "db", &fid, &vs->mode);
+        uint8_t modebyte;
+        err = pdu_unmarshal(pdu, offset, "db", &fid, &modebyte);
+        mode = modebyte;
     }
-
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
-        err = -ENOENT;
-        goto out;
+    if (err < 0) {
+        goto out_nofid;
     }
+    trace_v9fs_open(pdu->tag, pdu->id, fid, mode);
 
-    BUG_ON(vs->fidp->fid_type != P9_FID_NONE);
-
-    err = v9fs_do_lstat(s, &vs->fidp->path, &vs->stbuf);
-
-    v9fs_open_post_lstat(s, vs, err);
-    return;
-out:
-    complete_pdu(s, pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_post_lcreate(V9fsState *s, V9fsLcreateState *vs, int err)
-{
-    if (err == 0) {
-        v9fs_string_copy(&vs->fidp->path, &vs->fullname);
-        stat_to_qid(&vs->stbuf, &vs->qid);
-        vs->offset += pdu_marshal(vs->pdu, vs->offset, "Qd", &vs->qid,
-                vs->iounit);
-        err = vs->offset;
-    } else {
-        vs->fidp->fid_type = P9_FID_NONE;
-        err = -errno;
-        if (vs->fidp->fs.fd > 0) {
-            close(vs->fidp->fs.fd);
-        }
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
+        err = -ENOENT;
+        goto out_nofid;
     }
+    BUG_ON(fidp->fid_type != P9_FID_NONE);
 
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    v9fs_string_free(&vs->fullname);
-    qemu_free(vs);
-}
-
-static void v9fs_lcreate_post_get_iounit(V9fsState *s, V9fsLcreateState *vs,
-        int err)
-{
-    if (err) {
-        err = -errno;
+    err = v9fs_co_lstat(pdu, &fidp->path, &stbuf);
+    if (err < 0) {
         goto out;
     }
-    err = v9fs_do_lstat(s, &vs->fullname, &vs->stbuf);
-
-out:
-    v9fs_post_lcreate(s, vs, err);
-}
-
-static void v9fs_lcreate_post_do_open2(V9fsState *s, V9fsLcreateState *vs,
-        int err)
-{
-    if (vs->fidp->fs.fd == -1) {
-        err = -errno;
-        goto out;
+    stat_to_qid(&stbuf, &qid);
+    if (S_ISDIR(stbuf.st_mode)) {
+        err = v9fs_co_opendir(pdu, fidp);
+        if (err < 0) {
+            goto out;
+        }
+        fidp->fid_type = P9_FID_DIR;
+        err = pdu_marshal(pdu, offset, "Qd", &qid, 0);
+        if (err < 0) {
+            goto out;
+        }
+        err += offset;
+    } else {
+        if (s->proto_version == V9FS_PROTO_2000L) {
+            flags = get_dotl_openflags(s, mode);
+        } else {
+            flags = omode_to_uflags(mode);
+        }
+        if (is_ro_export(&s->ctx)) {
+            if (mode & O_WRONLY || mode & O_RDWR ||
+                mode & O_APPEND || mode & O_TRUNC) {
+                err = -EROFS;
+                goto out;
+            }
+        }
+        err = v9fs_co_open(pdu, fidp, flags);
+        if (err < 0) {
+            goto out;
+        }
+        fidp->fid_type = P9_FID_FILE;
+        fidp->open_flags = flags;
+        if (flags & O_EXCL) {
+            /*
+             * We let the host file system do O_EXCL check
+             * We should not reclaim such fd
+             */
+            fidp->flags |= FID_NON_RECLAIMABLE;
+        }
+        iounit = get_iounit(pdu, &fidp->path);
+        err = pdu_marshal(pdu, offset, "Qd", &qid, iounit);
+        if (err < 0) {
+            goto out;
+        }
+        err += offset;
     }
-    vs->fidp->fid_type = P9_FID_FILE;
-    vs->iounit =  get_iounit(s, &vs->fullname);
-    v9fs_lcreate_post_get_iounit(s, vs, err);
-    return;
-
+    trace_v9fs_open_return(pdu->tag, pdu->id,
+                           qid.type, qid.version, qid.path, iounit);
 out:
-    v9fs_post_lcreate(s, vs, err);
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(s, pdu, err);
 }
 
-static void v9fs_lcreate(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_lcreate(void *opaque)
 {
     int32_t dfid, flags, mode;
     gid_t gid;
-    V9fsLcreateState *vs;
     ssize_t err = 0;
+    ssize_t offset = 7;
+    V9fsString name;
+    V9fsFidState *fidp;
+    struct stat stbuf;
+    V9fsQID qid;
+    int32_t iounit;
+    V9fsPDU *pdu = opaque;
 
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    v9fs_string_init(&vs->fullname);
-
-    pdu_unmarshal(vs->pdu, vs->offset, "dsddd", &dfid, &vs->name, &flags,
-            &mode, &gid);
+    v9fs_string_init(&name);
+    err = pdu_unmarshal(pdu, offset, "dsddd", &dfid,
+                        &name, &flags, &mode, &gid);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_lcreate(pdu->tag, pdu->id, dfid, flags, mode, gid);
 
-    vs->fidp = lookup_fid(s, dfid);
-    if (vs->fidp == NULL) {
+    fidp = get_fid(pdu, dfid);
+    if (fidp == NULL) {
         err = -ENOENT;
-        goto out;
+        goto out_nofid;
     }
 
-    v9fs_string_sprintf(&vs->fullname, "%s/%s", vs->fidp->path.data,
-             vs->name.data);
-
-    /* Ignore direct disk access hint until the server supports it. */
-    flags &= ~O_DIRECT;
-
-    vs->fidp->fs.fd = v9fs_do_open2(s, vs->fullname.data, vs->fidp->uid,
-            gid, flags, mode);
-    v9fs_lcreate_post_do_open2(s, vs, err);
-    return;
-
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
-}
-
-static void v9fs_post_do_fsync(V9fsState *s, V9fsPDU *pdu, int err)
-{
-    if (err == -1) {
-        err = -errno;
+    flags = get_dotl_openflags(pdu->s, flags);
+    err = v9fs_co_open2(pdu, fidp, &name, gid,
+                        flags | O_CREAT, mode, &stbuf);
+    if (err < 0) {
+        goto out;
     }
-    complete_pdu(s, pdu, err);
+    fidp->fid_type = P9_FID_FILE;
+    fidp->open_flags = flags;
+    if (flags & O_EXCL) {
+        /*
+         * We let the host file system do O_EXCL check
+         * We should not reclaim such fd
+         */
+        fidp->flags |= FID_NON_RECLAIMABLE;
+    }
+    iounit =  get_iounit(pdu, &fidp->path);
+    stat_to_qid(&stbuf, &qid);
+    err = pdu_marshal(pdu, offset, "Qd", &qid, iounit);
+    if (err < 0) {
+        goto out;
+    }
+    err += offset;
+    trace_v9fs_lcreate_return(pdu->tag, pdu->id,
+                              qid.type, qid.version, qid.path, iounit);
+out:
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(pdu->s, pdu, err);
+    v9fs_string_free(&name);
 }
 
-static void v9fs_fsync(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_fsync(void *opaque)
 {
+    int err;
     int32_t fid;
+    int datasync;
     size_t offset = 7;
     V9fsFidState *fidp;
-    int datasync;
-    int err;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
+
+    err = pdu_unmarshal(pdu, offset, "dd", &fid, &datasync);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_fsync(pdu->tag, pdu->id, fid, datasync);
 
-    pdu_unmarshal(pdu, offset, "dd", &fid, &datasync);
-    fidp = lookup_fid(s, fid);
+    fidp = get_fid(pdu, fid);
     if (fidp == NULL) {
         err = -ENOENT;
-        v9fs_post_do_fsync(s, pdu, err);
-        return;
+        goto out_nofid;
+    }
+    err = v9fs_co_fsync(pdu, fidp, datasync);
+    if (!err) {
+        err = offset;
     }
-    err = v9fs_do_fsync(s, fidp->fs.fd, datasync);
-    v9fs_post_do_fsync(s, pdu, err);
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(s, pdu, err);
 }
 
-static void v9fs_clunk(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_clunk(void *opaque)
 {
+    int err;
     int32_t fid;
     size_t offset = 7;
-    int err;
-
-    pdu_unmarshal(pdu, offset, "d", &fid);
+    V9fsFidState *fidp;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-    err = free_fid(s, fid);
+    err = pdu_unmarshal(pdu, offset, "d", &fid);
     if (err < 0) {
-        goto out;
+        goto out_nofid;
     }
+    trace_v9fs_clunk(pdu->tag, pdu->id, fid);
 
-    offset = 7;
+    fidp = clunk_fid(s, fid);
+    if (fidp == NULL) {
+        err = -ENOENT;
+        goto out_nofid;
+    }
+    /*
+     * Bump the ref so that put_fid will
+     * free the fid.
+     */
+    fidp->ref++;
     err = offset;
-out:
+
+    put_fid(pdu, fidp);
+out_nofid:
     complete_pdu(s, pdu, err);
 }
 
-static void v9fs_read_post_readdir(V9fsState *, V9fsReadState *, ssize_t);
-
-static void v9fs_read_post_seekdir(V9fsState *s, V9fsReadState *vs, ssize_t err)
+static int v9fs_xattr_read(V9fsState *s, V9fsPDU *pdu, V9fsFidState *fidp,
+                           uint64_t off, uint32_t max_count)
 {
-    if (err) {
-        goto out;
-    }
-    v9fs_stat_free(&vs->v9stat);
-    v9fs_string_free(&vs->name);
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", vs->count);
-    vs->offset += vs->count;
-    err = vs->offset;
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-    return;
-}
+    ssize_t err;
+    size_t offset = 7;
+    int read_count;
+    int64_t xattr_len;
 
-static void v9fs_read_post_dir_lstat(V9fsState *s, V9fsReadState *vs,
-                                    ssize_t err)
-{
-    if (err) {
-        err = -errno;
-        goto out;
+    xattr_len = fidp->fs.xattr.len;
+    read_count = xattr_len - off;
+    if (read_count > max_count) {
+        read_count = max_count;
+    } else if (read_count < 0) {
+        /*
+         * read beyond XATTR value
+         */
+        read_count = 0;
     }
-    err = stat_to_v9stat(s, &vs->name, &vs->stbuf, &vs->v9stat);
-    if (err) {
-        goto out;
+    err = pdu_marshal(pdu, offset, "d", read_count);
+    if (err < 0) {
+        return err;
     }
-
-    vs->len = pdu_marshal(vs->pdu, vs->offset + 4 + vs->count, "S",
-                            &vs->v9stat);
-    if ((vs->len != (vs->v9stat.size + 2)) ||
-            ((vs->count + vs->len) > vs->max_count)) {
-        v9fs_do_seekdir(s, vs->fidp->fs.dir, vs->dir_pos);
-        v9fs_read_post_seekdir(s, vs, err);
-        return;
+    offset += err;
+    err = v9fs_pack(pdu->elem.in_sg, pdu->elem.in_num, offset,
+                    ((char *)fidp->fs.xattr.value) + off,
+                    read_count);
+    if (err < 0) {
+        return err;
     }
-    vs->count += vs->len;
-    v9fs_stat_free(&vs->v9stat);
-    v9fs_string_free(&vs->name);
-    vs->dir_pos = vs->dent->d_off;
-    vs->dent = v9fs_do_readdir(s, vs->fidp->fs.dir);
-    v9fs_read_post_readdir(s, vs, err);
-    return;
-out:
-    v9fs_do_seekdir(s, vs->fidp->fs.dir, vs->dir_pos);
-    v9fs_read_post_seekdir(s, vs, err);
-    return;
-
+    offset += err;
+    return offset;
 }
 
-static void v9fs_read_post_readdir(V9fsState *s, V9fsReadState *vs, ssize_t err)
+static int v9fs_do_readdir_with_stat(V9fsPDU *pdu,
+                                     V9fsFidState *fidp, uint32_t max_count)
 {
-    if (vs->dent) {
-        memset(&vs->v9stat, 0, sizeof(vs->v9stat));
-        v9fs_string_init(&vs->name);
-        v9fs_string_sprintf(&vs->name, "%s/%s", vs->fidp->path.data,
-                            vs->dent->d_name);
-        err = v9fs_do_lstat(s, &vs->name, &vs->stbuf);
-        v9fs_read_post_dir_lstat(s, vs, err);
-        return;
-    }
-
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", vs->count);
-    vs->offset += vs->count;
-    err = vs->offset;
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-    return;
-}
+    V9fsPath path;
+    V9fsStat v9stat;
+    int len, err = 0;
+    int32_t count = 0;
+    struct stat stbuf;
+    off_t saved_dir_pos;
+    struct dirent *dent, *result;
 
-static void v9fs_read_post_telldir(V9fsState *s, V9fsReadState *vs, ssize_t err)
-{
-    vs->dent = v9fs_do_readdir(s, vs->fidp->fs.dir);
-    v9fs_read_post_readdir(s, vs, err);
-    return;
-}
+    /* save the directory position */
+    saved_dir_pos = v9fs_co_telldir(pdu, fidp);
+    if (saved_dir_pos < 0) {
+        return saved_dir_pos;
+    }
 
-static void v9fs_read_post_rewinddir(V9fsState *s, V9fsReadState *vs,
-                                       ssize_t err)
-{
-    vs->dir_pos = v9fs_do_telldir(s, vs->fidp->fs.dir);
-    v9fs_read_post_telldir(s, vs, err);
-    return;
-}
+    dent = g_malloc(sizeof(struct dirent));
 
-static void v9fs_read_post_preadv(V9fsState *s, V9fsReadState *vs, ssize_t err)
-{
-    if (err  < 0) {
-        /* IO error return the error */
-        err = -errno;
-        goto out;
-    }
-    vs->total += vs->len;
-    vs->sg = adjust_sg(vs->sg, vs->len, &vs->cnt);
-    if (vs->total < vs->count && vs->len > 0) {
-        do {
-            if (0) {
-                print_sg(vs->sg, vs->cnt);
-            }
-            vs->len = v9fs_do_preadv(s, vs->fidp->fs.fd, vs->sg, vs->cnt,
-                      vs->off);
-            if (vs->len > 0) {
-                vs->off += vs->len;
-            }
-        } while (vs->len == -1 && errno == EINTR);
-        if (vs->len == -1) {
-            err  = -errno;
+    while (1) {
+        v9fs_path_init(&path);
+        err = v9fs_co_readdir_r(pdu, fidp, dent, &result);
+        if (err || !result) {
+            break;
         }
-        v9fs_read_post_preadv(s, vs, err);
-        return;
+        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_v9stat(pdu, &path, &stbuf, &v9stat);
+        if (err < 0) {
+            goto out;
+        }
+        /* 11 = 7 + 4 (7 = start offset, 4 = space for storing count) */
+        len = pdu_marshal(pdu, 11 + count, "S", &v9stat);
+        if ((len != (v9stat.size + 2)) || ((count + len) > max_count)) {
+            /* Ran out of buffer. Set dir back to old position and return */
+            v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
+            v9fs_stat_free(&v9stat);
+            v9fs_path_free(&path);
+            g_free(dent);
+            return count;
+        }
+        count += len;
+        v9fs_stat_free(&v9stat);
+        v9fs_path_free(&path);
+        saved_dir_pos = dent->d_off;
     }
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", vs->total);
-    vs->offset += vs->count;
-    err = vs->offset;
-
 out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+    g_free(dent);
+    v9fs_path_free(&path);
+    if (err < 0) {
+        return err;
+    }
+    return count;
 }
 
-static void v9fs_xattr_read(V9fsState *s, V9fsReadState *vs)
-{
-    ssize_t err = 0;
-    int read_count;
-    int64_t xattr_len;
-
-    xattr_len = vs->fidp->fs.xattr.len;
-    read_count = xattr_len - vs->off;
-    if (read_count > vs->count) {
-        read_count = vs->count;
-    } else if (read_count < 0) {
-        /*
-         * read beyond XATTR value
-         */
-        read_count = 0;
+/*
+ * Create a QEMUIOVector for a sub-region of PDU iovecs
+ *
+ * @qiov:       uninitialized QEMUIOVector
+ * @skip:       number of bytes to skip from beginning of PDU
+ * @size:       number of bytes to include
+ * @is_write:   true - write, false - read
+ *
+ * The resulting QEMUIOVector has heap-allocated iovecs and must be cleaned up
+ * with qemu_iovec_destroy().
+ */
+static void v9fs_init_qiov_from_pdu(QEMUIOVector *qiov, V9fsPDU *pdu,
+                                    uint64_t skip, size_t size,
+                                    bool is_write)
+{
+    QEMUIOVector elem;
+    struct iovec *iov;
+    unsigned int niov;
+
+    if (is_write) {
+        iov = pdu->elem.out_sg;
+        niov = pdu->elem.out_num;
+    } else {
+        iov = pdu->elem.in_sg;
+        niov = pdu->elem.in_num;
     }
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", read_count);
-    vs->offset += pdu_pack(vs->pdu, vs->offset,
-                           ((char *)vs->fidp->fs.xattr.value) + vs->off,
-                           read_count);
-    err = vs->offset;
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+
+    qemu_iovec_init_external(&elem, iov, niov);
+    qemu_iovec_init(qiov, niov);
+    qemu_iovec_copy(qiov, &elem, skip, size);
 }
 
-static void v9fs_read(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_read(void *opaque)
 {
     int32_t fid;
-    V9fsReadState *vs;
+    uint64_t off;
     ssize_t err = 0;
+    int32_t count = 0;
+    size_t offset = 7;
+    uint32_t max_count;
+    V9fsFidState *fidp;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-    vs->total = 0;
-    vs->len = 0;
-    vs->count = 0;
-
-    pdu_unmarshal(vs->pdu, vs->offset, "dqd", &fid, &vs->off, &vs->count);
+    err = pdu_unmarshal(pdu, offset, "dqd", &fid, &off, &max_count);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_read(pdu->tag, pdu->id, fid, off, max_count);
 
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
         err = -EINVAL;
-        goto out;
+        goto out_nofid;
     }
+    if (fidp->fid_type == P9_FID_DIR) {
 
-    if (vs->fidp->fid_type == P9_FID_DIR) {
-        vs->max_count = vs->count;
-        vs->count = 0;
-        if (vs->off == 0) {
-            v9fs_do_rewinddir(s, vs->fidp->fs.dir);
+        if (off == 0) {
+            v9fs_co_rewinddir(pdu, fidp);
         }
-        v9fs_read_post_rewinddir(s, vs, err);
-        return;
-    } else if (vs->fidp->fid_type == P9_FID_FILE) {
-        vs->sg = vs->iov;
-        pdu_marshal(vs->pdu, vs->offset + 4, "v", vs->sg, &vs->cnt);
-        vs->sg = cap_sg(vs->sg, vs->count, &vs->cnt);
-        if (vs->total <= vs->count) {
-            vs->len = v9fs_do_preadv(s, vs->fidp->fs.fd, vs->sg, vs->cnt,
-                                    vs->off);
-            if (vs->len > 0) {
-                vs->off += vs->len;
+        count = v9fs_do_readdir_with_stat(pdu, fidp, max_count);
+        if (count < 0) {
+            err = count;
+            goto out;
+        }
+        err = pdu_marshal(pdu, offset, "d", count);
+        if (err < 0) {
+            goto out;
+        }
+        err += offset + count;
+    } else if (fidp->fid_type == P9_FID_FILE) {
+        QEMUIOVector qiov_full;
+        QEMUIOVector qiov;
+        int32_t len;
+
+        v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset + 4, max_count, false);
+        qemu_iovec_init(&qiov, qiov_full.niov);
+        do {
+            qemu_iovec_reset(&qiov);
+            qemu_iovec_copy(&qiov, &qiov_full, count, qiov_full.size - count);
+            if (0) {
+                print_sg(qiov.iov, qiov.niov);
             }
-            err = vs->len;
-            v9fs_read_post_preadv(s, vs, err);
+            /* Loop in case of EINTR */
+            do {
+                len = v9fs_co_preadv(pdu, fidp, qiov.iov, qiov.niov, off);
+                if (len >= 0) {
+                    off   += len;
+                    count += len;
+                }
+            } while (len == -EINTR && !pdu->cancelled);
+            if (len < 0) {
+                /* IO error return the error */
+                err = len;
+                goto out;
+            }
+        } while (count < max_count && len > 0);
+        err = pdu_marshal(pdu, offset, "d", count);
+        if (err < 0) {
+            goto out;
         }
-        return;
-    } else if (vs->fidp->fid_type == P9_FID_XATTR) {
-        v9fs_xattr_read(s, vs);
-        return;
+        err += offset + count;
+        qemu_iovec_destroy(&qiov);
+        qemu_iovec_destroy(&qiov_full);
+    } else if (fidp->fid_type == P9_FID_XATTR) {
+        err = v9fs_xattr_read(s, pdu, fidp, off, max_count);
     } else {
         err = -EINVAL;
     }
+    trace_v9fs_read_return(pdu->tag, pdu->id, count, err);
 out:
+    put_fid(pdu, fidp);
+out_nofid:
     complete_pdu(s, pdu, err);
-    qemu_free(vs);
 }
 
-typedef struct V9fsReadDirState {
-    V9fsPDU *pdu;
-    V9fsFidState *fidp;
-    V9fsQID qid;
-    off_t saved_dir_pos;
-    struct dirent *dent;
-    int32_t count;
-    int32_t max_count;
-    size_t offset;
-    int64_t initial_offset;
-    V9fsString name;
-} V9fsReadDirState;
-
-static void v9fs_readdir_post_seekdir(V9fsState *s, V9fsReadDirState *vs)
+static size_t v9fs_readdir_data_size(V9fsString *name)
 {
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", vs->count);
-    vs->offset += vs->count;
-    complete_pdu(s, vs->pdu, vs->offset);
-    qemu_free(vs);
-    return;
+    /*
+     * Size of each dirent on the wire: size of qid (13) + size of offset (8)
+     * size of type (1) + size of name.size (2) + strlen(name.data)
+     */
+    return 24 + v9fs_string_size(name);
 }
 
-/* Size of each dirent on the wire: size of qid (13) + size of offset (8)
- * size of type (1) + size of name.size (2) + strlen(name.data)
- */
-#define V9_READDIR_DATA_SZ (24 + strlen(vs->name.data))
-
-static void v9fs_readdir_post_readdir(V9fsState *s, V9fsReadDirState *vs)
+static int v9fs_do_readdir(V9fsPDU *pdu,
+                           V9fsFidState *fidp, int32_t max_count)
 {
-    int len;
     size_t size;
+    V9fsQID qid;
+    V9fsString name;
+    int len, err = 0;
+    int32_t count = 0;
+    off_t saved_dir_pos;
+    struct dirent *dent, *result;
 
-    if (vs->dent) {
-        v9fs_string_init(&vs->name);
-        v9fs_string_sprintf(&vs->name, "%s", vs->dent->d_name);
+    /* save the directory position */
+    saved_dir_pos = v9fs_co_telldir(pdu, fidp);
+    if (saved_dir_pos < 0) {
+        return saved_dir_pos;
+    }
+
+    dent = g_malloc(sizeof(struct dirent));
 
-        if ((vs->count + V9_READDIR_DATA_SZ) > vs->max_count) {
+    while (1) {
+        err = v9fs_co_readdir_r(pdu, fidp, dent, &result);
+        if (err || !result) {
+            break;
+        }
+        v9fs_string_init(&name);
+        v9fs_string_sprintf(&name, "%s", dent->d_name);
+        if ((count + v9fs_readdir_data_size(&name)) > max_count) {
             /* Ran out of buffer. Set dir back to old position and return */
-            v9fs_do_seekdir(s, vs->fidp->fs.dir, vs->saved_dir_pos);
-            v9fs_readdir_post_seekdir(s, vs);
-            return;
+            v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
+            v9fs_string_free(&name);
+            g_free(dent);
+            return count;
         }
-
-        /* Fill up just the path field of qid because the client uses
+        /*
+         * 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(vs->dent->d_ino), sizeof(vs->qid.path));
-        memcpy(&vs->qid.path, &vs->dent->d_ino, size);
+        size = MIN(sizeof(dent->d_ino), sizeof(qid.path));
+        memcpy(&qid.path, &dent->d_ino, size);
         /* Fill the other fields with dummy values */
-        vs->qid.type = 0;
-        vs->qid.version = 0;
+        qid.type = 0;
+        qid.version = 0;
 
-        len = pdu_marshal(vs->pdu, vs->offset+4+vs->count, "Qqbs",
-                              &vs->qid, vs->dent->d_off,
-                              vs->dent->d_type, &vs->name);
-        vs->count += len;
-        v9fs_string_free(&vs->name);
-        vs->saved_dir_pos = vs->dent->d_off;
-        vs->dent = v9fs_do_readdir(s, vs->fidp->fs.dir);
-        v9fs_readdir_post_readdir(s, vs);
-        return;
+        /* 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);
+        if (len < 0) {
+            v9fs_co_seekdir(pdu, fidp, saved_dir_pos);
+            v9fs_string_free(&name);
+            g_free(dent);
+            return len;
+        }
+        count += len;
+        v9fs_string_free(&name);
+        saved_dir_pos = dent->d_off;
     }
-
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", vs->count);
-    vs->offset += vs->count;
-    complete_pdu(s, vs->pdu, vs->offset);
-    qemu_free(vs);
-    return;
-}
-
-static void v9fs_readdir_post_telldir(V9fsState *s, V9fsReadDirState *vs)
-{
-    vs->dent = v9fs_do_readdir(s, vs->fidp->fs.dir);
-    v9fs_readdir_post_readdir(s, vs);
-    return;
-}
-
-static void v9fs_readdir_post_setdir(V9fsState *s, V9fsReadDirState *vs)
-{
-    vs->saved_dir_pos = v9fs_do_telldir(s, vs->fidp->fs.dir);
-    v9fs_readdir_post_telldir(s, vs);
-    return;
+    g_free(dent);
+    if (err < 0) {
+        return err;
+    }
+    return count;
 }
 
-static void v9fs_readdir(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_readdir(void *opaque)
 {
     int32_t fid;
-    V9fsReadDirState *vs;
-    ssize_t err = 0;
+    V9fsFidState *fidp;
+    ssize_t retval = 0;
     size_t offset = 7;
+    uint64_t initial_offset;
+    int32_t count;
+    uint32_t max_count;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
+
+    retval = pdu_unmarshal(pdu, offset, "dqd", &fid,
+                           &initial_offset, &max_count);
+    if (retval < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_readdir(pdu->tag, pdu->id, fid, initial_offset, max_count);
 
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-    vs->count = 0;
-
-    pdu_unmarshal(vs->pdu, offset, "dqd", &fid, &vs->initial_offset,
-                                                        &vs->max_count);
-
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL || !(vs->fidp->fs.dir)) {
-        err = -EINVAL;
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
+        retval = -EINVAL;
+        goto out_nofid;
+    }
+    if (!fidp->fs.dir) {
+        retval = -EINVAL;
         goto out;
     }
-
-    if (vs->initial_offset == 0) {
-        v9fs_do_rewinddir(s, vs->fidp->fs.dir);
+    if (initial_offset == 0) {
+        v9fs_co_rewinddir(pdu, fidp);
     } else {
-        v9fs_do_seekdir(s, vs->fidp->fs.dir, vs->initial_offset);
+        v9fs_co_seekdir(pdu, fidp, initial_offset);
     }
-
-    v9fs_readdir_post_setdir(s, vs);
-    return;
-
-out:
-    complete_pdu(s, pdu, err);
-    qemu_free(vs);
-    return;
-}
-
-static void v9fs_write_post_pwritev(V9fsState *s, V9fsWriteState *vs,
-                                   ssize_t err)
-{
-    if (err  < 0) {
-        /* IO error return the error */
-        err = -errno;
+    count = v9fs_do_readdir(pdu, fidp, max_count);
+    if (count < 0) {
+        retval = count;
         goto out;
     }
-    vs->total += vs->len;
-    vs->sg = adjust_sg(vs->sg, vs->len, &vs->cnt);
-    if (vs->total < vs->count && vs->len > 0) {
-        do {
-            if (0) {
-                print_sg(vs->sg, vs->cnt);
-            }
-            vs->len = v9fs_do_pwritev(s, vs->fidp->fs.fd, vs->sg, vs->cnt,
-                      vs->off);
-            if (vs->len > 0) {
-                vs->off += vs->len;
-            }
-        } while (vs->len == -1 && errno == EINTR);
-        if (vs->len == -1) {
-            err  = -errno;
-        }
-        v9fs_write_post_pwritev(s, vs, err);
-        return;
+    retval = pdu_marshal(pdu, offset, "d", count);
+    if (retval < 0) {
+        goto out;
     }
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", vs->total);
-    err = vs->offset;
+    retval += count + offset;
+    trace_v9fs_readdir_return(pdu->tag, pdu->id, count, retval);
 out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(s, pdu, retval);
 }
 
-static void v9fs_xattr_write(V9fsState *s, V9fsWriteState *vs)
+static int v9fs_xattr_write(V9fsState *s, V9fsPDU *pdu, V9fsFidState *fidp,
+                            uint64_t off, uint32_t count,
+                            struct iovec *sg, int cnt)
 {
     int i, to_copy;
     ssize_t err = 0;
     int write_count;
     int64_t xattr_len;
+    size_t offset = 7;
+
 
-    xattr_len = vs->fidp->fs.xattr.len;
-    write_count = xattr_len - vs->off;
-    if (write_count > vs->count) {
-        write_count = vs->count;
+    xattr_len = fidp->fs.xattr.len;
+    write_count = xattr_len - off;
+    if (write_count > count) {
+        write_count = count;
     } else if (write_count < 0) {
         /*
          * write beyond XATTR value len specified in
@@ -2295,224 +1899,201 @@ static void v9fs_xattr_write(V9fsState *
         err = -ENOSPC;
         goto out;
     }
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "d", write_count);
-    err = vs->offset;
-    vs->fidp->fs.xattr.copied_len += write_count;
+    err = pdu_marshal(pdu, offset, "d", write_count);
+    if (err < 0) {
+        return err;
+    }
+    err += offset;
+    fidp->fs.xattr.copied_len += write_count;
     /*
      * Now copy the content from sg list
      */
-    for (i = 0; i < vs->cnt; i++) {
-        if (write_count > vs->sg[i].iov_len) {
-            to_copy = vs->sg[i].iov_len;
+    for (i = 0; i < cnt; i++) {
+        if (write_count > sg[i].iov_len) {
+            to_copy = sg[i].iov_len;
         } else {
             to_copy = write_count;
         }
-        memcpy((char *)vs->fidp->fs.xattr.value + vs->off,
-               vs->sg[i].iov_base, to_copy);
+        memcpy((char *)fidp->fs.xattr.value + off, sg[i].iov_base, to_copy);
         /* updating vs->off since we are not using below */
-        vs->off += to_copy;
+        off += to_copy;
         write_count -= to_copy;
     }
 out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+    return err;
 }
 
-static void v9fs_write(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_write(void *opaque)
 {
-    int32_t fid;
-    V9fsWriteState *vs;
     ssize_t err;
+    int32_t fid;
+    uint64_t off;
+    uint32_t count;
+    int32_t len = 0;
+    int32_t total = 0;
+    size_t offset = 7;
+    V9fsFidState *fidp;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
+    QEMUIOVector qiov_full;
+    QEMUIOVector qiov;
 
-    vs = qemu_malloc(sizeof(*vs));
-
-    vs->pdu = pdu;
-    vs->offset = 7;
-    vs->sg = vs->iov;
-    vs->total = 0;
-    vs->len = 0;
-
-    pdu_unmarshal(vs->pdu, vs->offset, "dqdv", &fid, &vs->off, &vs->count,
-                  vs->sg, &vs->cnt);
+    err = pdu_unmarshal(pdu, offset, "dqd", &fid, &off, &count);
+    if (err < 0) {
+        return complete_pdu(s, pdu, err);
+    }
+    offset += err;
+    v9fs_init_qiov_from_pdu(&qiov_full, pdu, offset, count, true);
+    trace_v9fs_write(pdu->tag, pdu->id, fid, off, count, qiov_full.niov);
 
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
         err = -EINVAL;
-        goto out;
+        goto out_nofid;
     }
-
-    if (vs->fidp->fid_type == P9_FID_FILE) {
-        if (vs->fidp->fs.fd == -1) {
+    if (fidp->fid_type == P9_FID_FILE) {
+        if (fidp->fs.fd == -1) {
             err = -EINVAL;
             goto out;
         }
-    } else if (vs->fidp->fid_type == P9_FID_XATTR) {
+    } else if (fidp->fid_type == P9_FID_XATTR) {
         /*
          * setxattr operation
          */
-        v9fs_xattr_write(s, vs);
-        return;
+        err = v9fs_xattr_write(s, pdu, fidp, off, count,
+                               qiov_full.iov, qiov_full.niov);
+        goto out;
     } else {
         err = -EINVAL;
         goto out;
     }
-    vs->sg = cap_sg(vs->sg, vs->count, &vs->cnt);
-    if (vs->total <= vs->count) {
-        vs->len = v9fs_do_pwritev(s, vs->fidp->fs.fd, vs->sg, vs->cnt, vs->off);
-        if (vs->len > 0) {
-            vs->off += vs->len;
+    qemu_iovec_init(&qiov, qiov_full.niov);
+    do {
+        qemu_iovec_reset(&qiov);
+        qemu_iovec_copy(&qiov, &qiov_full, total, qiov_full.size - total);
+        if (0) {
+            print_sg(qiov.iov, qiov.niov);
         }
-        err = vs->len;
-        v9fs_write_post_pwritev(s, vs, err);
-    }
-    return;
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_create_post_getiounit(V9fsState *s, V9fsCreateState *vs)
-{
-    int err;
-    v9fs_string_copy(&vs->fidp->path, &vs->fullname);
-    stat_to_qid(&vs->stbuf, &vs->qid);
-
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "Qd", &vs->qid, vs->iounit);
-    err = vs->offset;
-
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    v9fs_string_free(&vs->extension);
-    v9fs_string_free(&vs->fullname);
-    qemu_free(vs);
-}
-
-static void v9fs_post_create(V9fsState *s, V9fsCreateState *vs, int err)
-{
-    if (err == 0) {
-        vs->iounit = get_iounit(s, &vs->fidp->path);
-        v9fs_create_post_getiounit(s, vs);
-        return;
-    }
-
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    v9fs_string_free(&vs->extension);
-    v9fs_string_free(&vs->fullname);
-    qemu_free(vs);
-}
-
-static void v9fs_create_post_perms(V9fsState *s, V9fsCreateState *vs, int err)
-{
-    if (err) {
-        err = -errno;
-    }
-    v9fs_post_create(s, vs, err);
-}
-
-static void v9fs_create_post_opendir(V9fsState *s, V9fsCreateState *vs,
-                                                                    int err)
-{
-    if (!vs->fidp->fs.dir) {
-        err = -errno;
-    }
-    vs->fidp->fid_type = P9_FID_DIR;
-    v9fs_post_create(s, vs, err);
-}
-
-static void v9fs_create_post_dir_lstat(V9fsState *s, V9fsCreateState *vs,
-                                                                    int err)
-{
-    if (err) {
-        err = -errno;
-        goto out;
-    }
-
-    vs->fidp->fs.dir = v9fs_do_opendir(s, &vs->fullname);
-    v9fs_create_post_opendir(s, vs, err);
-    return;
-
-out:
-    v9fs_post_create(s, vs, err);
-}
+        /* Loop in case of EINTR */
+        do {
+            len = v9fs_co_pwritev(pdu, fidp, qiov.iov, qiov.niov, off);
+            if (len >= 0) {
+                off   += len;
+                total += len;
+            }
+        } while (len == -EINTR && !pdu->cancelled);
+        if (len < 0) {
+            /* IO error return the error */
+            err = len;
+            goto out_qiov;
+        }
+    } while (total < count && len > 0);
 
-static void v9fs_create_post_mkdir(V9fsState *s, V9fsCreateState *vs, int err)
-{
-    if (err) {
-        err = -errno;
+    offset = 7;
+    err = pdu_marshal(pdu, offset, "d", total);
+    if (err < 0) {
         goto out;
     }
-
-    err = v9fs_do_lstat(s, &vs->fullname, &vs->stbuf);
-    v9fs_create_post_dir_lstat(s, vs, err);
-    return;
-
-out:
-    v9fs_post_create(s, vs, err);
-}
-
-static void v9fs_create_post_fstat(V9fsState *s, V9fsCreateState *vs, int err)
-{
-    if (err) {
-        vs->fidp->fid_type = P9_FID_NONE;
-        close(vs->fidp->fs.fd);
-        err = -errno;
-    }
-    v9fs_post_create(s, vs, err);
-    return;
+    err += offset;
+    trace_v9fs_write_return(pdu->tag, pdu->id, total, err);
+out_qiov:
+    qemu_iovec_destroy(&qiov);
+out:
+    put_fid(pdu, fidp);
+out_nofid:
+    qemu_iovec_destroy(&qiov_full);
+    complete_pdu(s, pdu, err);
 }
 
-static void v9fs_create_post_open2(V9fsState *s, V9fsCreateState *vs, int err)
+static void v9fs_create(void *opaque)
 {
-    if (vs->fidp->fs.fd == -1) {
-        err = -errno;
-        goto out;
+    int32_t fid;
+    int err = 0;
+    size_t offset = 7;
+    V9fsFidState *fidp;
+    V9fsQID qid;
+    int32_t perm;
+    int8_t mode;
+    V9fsPath path;
+    struct stat stbuf;
+    V9fsString name;
+    V9fsString extension;
+    int iounit;
+    V9fsPDU *pdu = opaque;
+
+    v9fs_path_init(&path);
+    v9fs_string_init(&name);
+    v9fs_string_init(&extension);
+    err = pdu_unmarshal(pdu, offset, "dsdbs", &fid, &name,
+                        &perm, &mode, &extension);
+    if (err < 0) {
+        goto out_nofid;
     }
-    vs->fidp->fid_type = P9_FID_FILE;
-    err = v9fs_do_fstat(s, vs->fidp->fs.fd, &vs->stbuf);
-    v9fs_create_post_fstat(s, vs, err);
-
-    return;
-
-out:
-    v9fs_post_create(s, vs, err);
-
-}
+    trace_v9fs_create(pdu->tag, pdu->id, fid, name.data, perm, mode);
 
-static void v9fs_create_post_lstat(V9fsState *s, V9fsCreateState *vs, int err)
-{
-
-    if (err == 0 || errno != ENOENT) {
-        err = -errno;
-        goto out;
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
+        err = -EINVAL;
+        goto out_nofid;
     }
-
-    if (vs->perm & P9_STAT_MODE_DIR) {
-        err = v9fs_do_mkdir(s, vs->fullname.data, vs->perm & 0777,
-                vs->fidp->uid, -1);
-        v9fs_create_post_mkdir(s, vs, err);
-    } else if (vs->perm & P9_STAT_MODE_SYMLINK) {
-        err = v9fs_do_symlink(s, vs->fidp, vs->extension.data,
-                vs->fullname.data, -1);
-        v9fs_create_post_perms(s, vs, err);
-    } else if (vs->perm & P9_STAT_MODE_LINK) {
-        int32_t nfid = atoi(vs->extension.data);
-        V9fsFidState *nfidp = lookup_fid(s, nfid);
-        if (nfidp == NULL) {
-            err = -errno;
-            v9fs_post_create(s, vs, err);
+    if (perm & P9_STAT_MODE_DIR) {
+        err = v9fs_co_mkdir(pdu, fidp, &name, perm & 0777,
+                            fidp->uid, -1, &stbuf);
+        if (err < 0) {
+            goto out;
+        }
+        err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path);
+        if (err < 0) {
+            goto out;
+        }
+        v9fs_path_copy(&fidp->path, &path);
+        err = v9fs_co_opendir(pdu, fidp);
+        if (err < 0) {
+            goto out;
+        }
+        fidp->fid_type = P9_FID_DIR;
+    } else if (perm & P9_STAT_MODE_SYMLINK) {
+        err = v9fs_co_symlink(pdu, fidp, &name,
+                              extension.data, -1 , &stbuf);
+        if (err < 0) {
+            goto out;
         }
-        err = v9fs_do_link(s, &nfidp->path, &vs->fullname);
-        v9fs_create_post_perms(s, vs, err);
-    } else if (vs->perm & P9_STAT_MODE_DEVICE) {
+        err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path);
+        if (err < 0) {
+            goto out;
+        }
+        v9fs_path_copy(&fidp->path, &path);
+    } else if (perm & P9_STAT_MODE_LINK) {
+        int32_t ofid = atoi(extension.data);
+        V9fsFidState *ofidp = get_fid(pdu, ofid);
+        if (ofidp == NULL) {
+            err = -EINVAL;
+            goto out;
+        }
+        err = v9fs_co_link(pdu, ofidp, fidp, &name);
+        put_fid(pdu, ofidp);
+        if (err < 0) {
+            goto out;
+        }
+        err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path);
+        if (err < 0) {
+            fidp->fid_type = P9_FID_NONE;
+            goto out;
+        }
+        v9fs_path_copy(&fidp->path, &path);
+        err = v9fs_co_lstat(pdu, &fidp->path, &stbuf);
+        if (err < 0) {
+            fidp->fid_type = P9_FID_NONE;
+            goto out;
+        }
+    } else if (perm & P9_STAT_MODE_DEVICE) {
         char ctype;
         uint32_t major, minor;
         mode_t nmode = 0;
 
-        if (sscanf(vs->extension.data, "%c %u %u", &ctype, &major,
-                                        &minor) != 3) {
+        if (sscanf(extension.data, "%c %u %u", &ctype, &major, &minor) != 3) {
             err = -errno;
-            v9fs_post_create(s, vs, err);
+            goto out;
         }
 
         switch (ctype) {
@@ -2524,665 +2105,709 @@ static void v9fs_create_post_lstat(V9fsS
             break;
         default:
             err = -EIO;
-            v9fs_post_create(s, vs, err);
+            goto out;
         }
 
-        nmode |= vs->perm & 0777;
-        err = v9fs_do_mknod(s, vs->fullname.data, nmode,
-                makedev(major, minor), vs->fidp->uid, -1);
-        v9fs_create_post_perms(s, vs, err);
-    } else if (vs->perm & P9_STAT_MODE_NAMED_PIPE) {
-        err = v9fs_do_mknod(s, vs->fullname.data, S_IFIFO | (vs->perm & 0777),
-                0, vs->fidp->uid, -1);
-        v9fs_post_create(s, vs, err);
-    } else if (vs->perm & P9_STAT_MODE_SOCKET) {
-        err = v9fs_do_mknod(s, vs->fullname.data, S_IFSOCK | (vs->perm & 0777),
-                0, vs->fidp->uid, -1);
-        v9fs_post_create(s, vs, err);
+        nmode |= perm & 0777;
+        err = v9fs_co_mknod(pdu, fidp, &name, fidp->uid, -1,
+                            makedev(major, minor), nmode, &stbuf);
+        if (err < 0) {
+            goto out;
+        }
+        err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path);
+        if (err < 0) {
+            goto out;
+        }
+        v9fs_path_copy(&fidp->path, &path);
+    } else if (perm & P9_STAT_MODE_NAMED_PIPE) {
+        err = v9fs_co_mknod(pdu, fidp, &name, fidp->uid, -1,
+                            0, S_IFIFO | (perm & 0777), &stbuf);
+        if (err < 0) {
+            goto out;
+        }
+        err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path);
+        if (err < 0) {
+            goto out;
+        }
+        v9fs_path_copy(&fidp->path, &path);
+    } else if (perm & P9_STAT_MODE_SOCKET) {
+        err = v9fs_co_mknod(pdu, fidp, &name, fidp->uid, -1,
+                            0, S_IFSOCK | (perm & 0777), &stbuf);
+        if (err < 0) {
+            goto out;
+        }
+        err = v9fs_co_name_to_path(pdu, &fidp->path, name.data, &path);
+        if (err < 0) {
+            goto out;
+        }
+        v9fs_path_copy(&fidp->path, &path);
     } else {
-        vs->fidp->fs.fd = v9fs_do_open2(s, vs->fullname.data, vs->fidp->uid,
-                -1, omode_to_uflags(vs->mode)|O_CREAT, vs->perm);
-
-        v9fs_create_post_open2(s, vs, err);
+        err = v9fs_co_open2(pdu, fidp, &name, -1,
+                            omode_to_uflags(mode)|O_CREAT, perm, &stbuf);
+        if (err < 0) {
+            goto out;
+        }
+        fidp->fid_type = P9_FID_FILE;
+        fidp->open_flags = omode_to_uflags(mode);
+        if (fidp->open_flags & O_EXCL) {
+            /*
+             * We let the host file system do O_EXCL check
+             * We should not reclaim such fd
+             */
+            fidp->flags |= FID_NON_RECLAIMABLE;
+        }
     }
-
-    return;
-
+    iounit = get_iounit(pdu, &fidp->path);
+    stat_to_qid(&stbuf, &qid);
+    err = pdu_marshal(pdu, offset, "Qd", &qid, iounit);
+    if (err < 0) {
+        goto out;
+    }
+    err += offset;
+    trace_v9fs_create_return(pdu->tag, pdu->id,
+                             qid.type, qid.version, qid.path, iounit);
 out:
-    v9fs_post_create(s, vs, err);
+    put_fid(pdu, fidp);
+out_nofid:
+   complete_pdu(pdu->s, pdu, err);
+   v9fs_string_free(&name);
+   v9fs_string_free(&extension);
+   v9fs_path_free(&path);
 }
 
-static void v9fs_create(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_symlink(void *opaque)
 {
-    int32_t fid;
-    V9fsCreateState *vs;
+    V9fsPDU *pdu = opaque;
+    V9fsString name;
+    V9fsString symname;
+    V9fsFidState *dfidp;
+    V9fsQID qid;
+    struct stat stbuf;
+    int32_t dfid;
     int err = 0;
+    gid_t gid;
+    size_t offset = 7;
 
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    v9fs_string_init(&vs->fullname);
-
-    pdu_unmarshal(vs->pdu, vs->offset, "dsdbs", &fid, &vs->name,
-                                &vs->perm, &vs->mode, &vs->extension);
+    v9fs_string_init(&name);
+    v9fs_string_init(&symname);
+    err = pdu_unmarshal(pdu, offset, "dssd", &dfid, &name, &symname, &gid);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_symlink(pdu->tag, pdu->id, dfid, name.data, symname.data, gid);
 
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
+    dfidp = get_fid(pdu, dfid);
+    if (dfidp == NULL) {
         err = -EINVAL;
-        goto out;
+        goto out_nofid;
     }
-
-    v9fs_string_sprintf(&vs->fullname, "%s/%s", vs->fidp->path.data,
-                                                        vs->name.data);
-
-    err = v9fs_do_lstat(s, &vs->fullname, &vs->stbuf);
-    v9fs_create_post_lstat(s, vs, err);
-    return;
-
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    v9fs_string_free(&vs->extension);
-    qemu_free(vs);
-}
-
-static void v9fs_post_symlink(V9fsState *s, V9fsSymlinkState *vs, int err)
-{
-    if (err == 0) {
-        stat_to_qid(&vs->stbuf, &vs->qid);
-        vs->offset += pdu_marshal(vs->pdu, vs->offset, "Q", &vs->qid);
-        err = vs->offset;
-    } else {
-        err = -errno;
+    err = v9fs_co_symlink(pdu, dfidp, &name, symname.data, gid, &stbuf);
+    if (err < 0) {
+        goto out;
     }
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    v9fs_string_free(&vs->symname);
-    v9fs_string_free(&vs->fullname);
-    qemu_free(vs);
-}
-
-static void v9fs_symlink_post_do_symlink(V9fsState *s, V9fsSymlinkState *vs,
-        int err)
-{
-    if (err) {
+    stat_to_qid(&stbuf, &qid);
+    err =  pdu_marshal(pdu, offset, "Q", &qid);
+    if (err < 0) {
         goto out;
     }
-    err = v9fs_do_lstat(s, &vs->fullname, &vs->stbuf);
-out:
-    v9fs_post_symlink(s, vs, err);
+    err += offset;
+    trace_v9fs_symlink_return(pdu->tag, pdu->id,
+                              qid.type, qid.version, qid.path);
+out:
+    put_fid(pdu, dfidp);
+out_nofid:
+    complete_pdu(pdu->s, pdu, err);
+    v9fs_string_free(&name);
+    v9fs_string_free(&symname);
 }
 
-static void v9fs_symlink(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_flush(void *opaque)
 {
-    int32_t dfid;
-    V9fsSymlinkState *vs;
-    int err = 0;
-    gid_t gid;
-
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    v9fs_string_init(&vs->fullname);
-
-    pdu_unmarshal(vs->pdu, vs->offset, "dssd", &dfid, &vs->name,
-            &vs->symname, &gid);
+    ssize_t err;
+    int16_t tag;
+    size_t offset = 7;
+    V9fsPDU *cancel_pdu;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-    vs->dfidp = lookup_fid(s, dfid);
-    if (vs->dfidp == NULL) {
-        err = -EINVAL;
-        goto out;
+    err = pdu_unmarshal(pdu, offset, "w", &tag);
+    if (err < 0) {
+        complete_pdu(s, pdu, err);
+        return;
     }
+    trace_v9fs_flush(pdu->tag, pdu->id, tag);
 
-    v9fs_string_sprintf(&vs->fullname, "%s/%s", vs->dfidp->path.data,
-            vs->name.data);
-    err = v9fs_do_symlink(s, vs->dfidp, vs->symname.data,
-            vs->fullname.data, gid);
-    v9fs_symlink_post_do_symlink(s, vs, err);
-    return;
-
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    v9fs_string_free(&vs->symname);
-    qemu_free(vs);
-}
-
-static void v9fs_flush(V9fsState *s, V9fsPDU *pdu)
-{
-    /* A nop call with no return */
+    QLIST_FOREACH(cancel_pdu, &s->active_list, next) {
+        if (cancel_pdu->tag == tag) {
+            break;
+        }
+    }
+    if (cancel_pdu) {
+        cancel_pdu->cancelled = 1;
+        /*
+         * Wait for pdu to complete.
+         */
+        qemu_co_queue_wait(&cancel_pdu->complete);
+        cancel_pdu->cancelled = 0;
+        free_pdu(pdu->s, cancel_pdu);
+    }
     complete_pdu(s, pdu, 7);
+    return;
 }
 
-static void v9fs_link(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_link(void *opaque)
 {
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
     int32_t dfid, oldfid;
     V9fsFidState *dfidp, *oldfidp;
-    V9fsString name, fullname;
+    V9fsString name;
     size_t offset = 7;
     int err = 0;
 
-    v9fs_string_init(&fullname);
-
-    pdu_unmarshal(pdu, offset, "dds", &dfid, &oldfid, &name);
+    v9fs_string_init(&name);
+    err = pdu_unmarshal(pdu, offset, "dds", &dfid, &oldfid, &name);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_link(pdu->tag, pdu->id, dfid, oldfid, name.data);
 
-    dfidp = lookup_fid(s, dfid);
+    dfidp = get_fid(pdu, dfid);
     if (dfidp == NULL) {
-        err = -errno;
-        goto out;
+        err = -ENOENT;
+        goto out_nofid;
     }
 
-    oldfidp = lookup_fid(s, oldfid);
+    oldfidp = get_fid(pdu, oldfid);
     if (oldfidp == NULL) {
-        err = -errno;
+        err = -ENOENT;
         goto out;
     }
-
-    v9fs_string_sprintf(&fullname, "%s/%s", dfidp->path.data, name.data);
-    err = offset;
-    err = v9fs_do_link(s, &oldfidp->path, &fullname);
-    if (err) {
-        err = -errno;
+    err = v9fs_co_link(pdu, oldfidp, dfidp, &name);
+    if (!err) {
+        err = offset;
     }
-    v9fs_string_free(&fullname);
-
 out:
+    put_fid(pdu, dfidp);
+out_nofid:
     v9fs_string_free(&name);
     complete_pdu(s, pdu, err);
 }
 
-static void v9fs_remove_post_remove(V9fsState *s, V9fsRemoveState *vs,
-                                                                int err)
+/* Only works with path name based fid */
+static void v9fs_remove(void *opaque)
 {
+    int32_t fid;
+    int err = 0;
+    size_t offset = 7;
+    V9fsFidState *fidp;
+    V9fsPDU *pdu = opaque;
+
+    err = pdu_unmarshal(pdu, offset, "d", &fid);
     if (err < 0) {
-        err = -errno;
-    } else {
-        err = vs->offset;
+        goto out_nofid;
     }
+    trace_v9fs_remove(pdu->tag, pdu->id, fid);
 
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
+        err = -EINVAL;
+        goto out_nofid;
+    }
+    /* if fs driver is not path based, return EOPNOTSUPP */
+    if (!(pdu->s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT)) {
+        err = -EOPNOTSUPP;
+        goto out_err;
+    }
+    /*
+     * IF the file is unlinked, we cannot reopen
+     * the file later. So don't reclaim fd
+     */
+    err = v9fs_mark_fids_unreclaim(pdu, &fidp->path);
+    if (err < 0) {
+        goto out_err;
+    }
+    err = v9fs_co_remove(pdu, &fidp->path);
+    if (!err) {
+        err = offset;
+    }
+out_err:
     /* For TREMOVE we need to clunk the fid even on failed remove */
-    free_fid(s, vs->fidp->fid);
-
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+    clunk_fid(pdu->s, fidp->fid);
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(pdu->s, pdu, err);
 }
 
-static void v9fs_remove(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_unlinkat(void *opaque)
 {
-    int32_t fid;
-    V9fsRemoveState *vs;
     int err = 0;
+    V9fsString name;
+    int32_t dfid, flags;
+    size_t offset = 7;
+    V9fsPath path;
+    V9fsFidState *dfidp;
+    V9fsPDU *pdu = opaque;
 
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    pdu_unmarshal(vs->pdu, vs->offset, "d", &fid);
-
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
+    v9fs_string_init(&name);
+    err = pdu_unmarshal(pdu, offset, "dsd", &dfid, &name, &flags);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    dfidp = get_fid(pdu, dfid);
+    if (dfidp == NULL) {
         err = -EINVAL;
-        goto out;
+        goto out_nofid;
     }
-
-    err = v9fs_do_remove(s, &vs->fidp->path);
-    v9fs_remove_post_remove(s, vs, err);
-    return;
-
-out:
-    complete_pdu(s, pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_wstat_post_truncate(V9fsState *s, V9fsWstatState *vs, int err)
-{
+    /*
+     * IF the file is unlinked, we cannot reopen
+     * the file later. So don't reclaim fd
+     */
+    v9fs_path_init(&path);
+    err = v9fs_co_name_to_path(pdu, &dfidp->path, name.data, &path);
     if (err < 0) {
-        goto out;
+        goto out_err;
     }
-
-    err = vs->offset;
-
-out:
-    v9fs_stat_free(&vs->v9stat);
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_wstat_post_rename(V9fsState *s, V9fsWstatState *vs, int err)
-{
+    err = v9fs_mark_fids_unreclaim(pdu, &path);
     if (err < 0) {
-        goto out;
-    }
-    if (vs->v9stat.length != -1) {
-        if (v9fs_do_truncate(s, &vs->fidp->path, vs->v9stat.length) < 0) {
-            err = -errno;
-        }
+        goto out_err;
     }
-    v9fs_wstat_post_truncate(s, vs, err);
-    return;
-
-out:
-    v9fs_stat_free(&vs->v9stat);
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+    err = v9fs_co_unlinkat(pdu, &dfidp->path, &name, flags);
+    if (!err) {
+        err = offset;
+    }
+out_err:
+    put_fid(pdu, dfidp);
+    v9fs_path_free(&path);
+out_nofid:
+    complete_pdu(pdu->s, pdu, err);
+    v9fs_string_free(&name);
 }
 
-static int v9fs_complete_rename(V9fsState *s, V9fsRenameState *vs)
+
+/* Only works with path name based fid */
+static int v9fs_complete_rename(V9fsPDU *pdu, V9fsFidState *fidp,
+                                int32_t newdirfid, V9fsString *name)
 {
+    char *end;
     int err = 0;
+    V9fsPath new_path;
+    V9fsFidState *tfidp;
+    V9fsState *s = pdu->s;
+    V9fsFidState *dirfidp = NULL;
     char *old_name, *new_name;
-    char *end;
-
-    if (vs->newdirfid != -1) {
-        V9fsFidState *dirfidp;
-        dirfidp = lookup_fid(s, vs->newdirfid);
 
+    v9fs_path_init(&new_path);
+    if (newdirfid != -1) {
+        dirfidp = get_fid(pdu, newdirfid);
         if (dirfidp == NULL) {
             err = -ENOENT;
-            goto out;
+            goto out_nofid;
         }
-
         BUG_ON(dirfidp->fid_type != P9_FID_NONE);
-
-        new_name = qemu_mallocz(dirfidp->path.size + vs->name.size + 2);
-
-        strcpy(new_name, dirfidp->path.data);
-        strcat(new_name, "/");
-        strcat(new_name + dirfidp->path.size, vs->name.data);
+        v9fs_co_name_to_path(pdu, &dirfidp->path, name->data, &new_path);
     } else {
-        old_name = vs->fidp->path.data;
+        old_name = fidp->path.data;
         end = strrchr(old_name, '/');
         if (end) {
             end++;
         } else {
             end = old_name;
         }
-        new_name = qemu_mallocz(end - old_name + vs->name.size + 1);
-
+        new_name = g_malloc0(end - old_name + name->size + 1);
         strncat(new_name, old_name, end - old_name);
-        strncat(new_name + (end - old_name), vs->name.data, vs->name.size);
+        strncat(new_name + (end - old_name), name->data, name->size);
+        v9fs_co_name_to_path(pdu, NULL, new_name, &new_path);
+        g_free(new_name);
     }
-
-    v9fs_string_free(&vs->name);
-    vs->name.data = qemu_strdup(new_name);
-    vs->name.size = strlen(new_name);
-
-    if (strcmp(new_name, vs->fidp->path.data) != 0) {
-        if (v9fs_do_rename(s, &vs->fidp->path, &vs->name)) {
-            err = -errno;
-        } else {
-            V9fsFidState *fidp;
-            /*
-            * Fixup fid's pointing to the old name to
-            * start pointing to the new name
-            */
-            for (fidp = s->fid_list; fidp; fidp = fidp->next) {
-                if (vs->fidp == fidp) {
-                    /*
-                    * we replace name of this fid towards the end so
-                    * that our below v9fs_path_is_ancestor check will
-                    * work
-                    */
-                    continue;
-                }
-                if (v9fs_path_is_ancestor(&vs->fidp->path, &fidp->path)) {
-                    /* replace the name */
-                    v9fs_fix_path(&fidp->path, &vs->name,
-                                  strlen(vs->fidp->path.data));
-                }
-            }
-            v9fs_string_copy(&vs->fidp->path, &vs->name);
+    err = v9fs_co_rename(pdu, &fidp->path, &new_path);
+    if (err < 0) {
+        goto out;
+    }
+    /*
+     * Fixup fid's pointing to the old name to
+     * start pointing to the new name
+     */
+    for (tfidp = s->fid_list; tfidp; tfidp = tfidp->next) {
+        if (v9fs_path_is_ancestor(&fidp->path, &tfidp->path)) {
+            /* replace the name */
+            v9fs_fix_path(&tfidp->path, &new_path, strlen(fidp->path.data));
         }
     }
 out:
-    v9fs_string_free(&vs->name);
+    if (dirfidp) {
+        put_fid(pdu, dirfidp);
+    }
+    v9fs_path_free(&new_path);
+out_nofid:
     return err;
 }
 
-static void v9fs_rename_post_rename(V9fsState *s, V9fsRenameState *vs, int err)
+/* Only works with path name based fid */
+static void v9fs_rename(void *opaque)
 {
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
+    int32_t fid;
+    ssize_t err = 0;
+    size_t offset = 7;
+    V9fsString name;
+    int32_t newdirfid;
+    V9fsFidState *fidp;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-static void v9fs_wstat_post_chown(V9fsState *s, V9fsWstatState *vs, int err)
-{
+    v9fs_string_init(&name);
+    err = pdu_unmarshal(pdu, offset, "dds", &fid, &newdirfid, &name);
     if (err < 0) {
+        goto out_nofid;
+    }
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
+        err = -ENOENT;
+        goto out_nofid;
+    }
+    BUG_ON(fidp->fid_type != P9_FID_NONE);
+    /* if fs driver is not path based, return EOPNOTSUPP */
+    if (!(pdu->s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT)) {
+        err = -EOPNOTSUPP;
         goto out;
     }
+    v9fs_path_write_lock(s);
+    err = v9fs_complete_rename(pdu, fidp, newdirfid, &name);
+    v9fs_path_unlock(s);
+    if (!err) {
+        err = offset;
+    }
+out:
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(s, pdu, err);
+    v9fs_string_free(&name);
+}
 
-    if (vs->v9stat.name.size != 0) {
-        V9fsRenameState *vr;
+static void v9fs_fix_fid_paths(V9fsPDU *pdu, V9fsPath *olddir,
+                               V9fsString *old_name, V9fsPath *newdir,
+                               V9fsString *new_name)
+{
+    V9fsFidState *tfidp;
+    V9fsPath oldpath, newpath;
+    V9fsState *s = pdu->s;
 
-        vr = qemu_mallocz(sizeof(V9fsRenameState));
-        vr->newdirfid = -1;
-        vr->pdu = vs->pdu;
-        vr->fidp = vs->fidp;
-        vr->offset = vs->offset;
-        vr->name.size = vs->v9stat.name.size;
-        vr->name.data = qemu_strdup(vs->v9stat.name.data);
 
-        err = v9fs_complete_rename(s, vr);
-        qemu_free(vr);
-    }
-    v9fs_wstat_post_rename(s, vs, err);
-    return;
+    v9fs_path_init(&oldpath);
+    v9fs_path_init(&newpath);
+    v9fs_co_name_to_path(pdu, olddir, old_name->data, &oldpath);
+    v9fs_co_name_to_path(pdu, newdir, new_name->data, &newpath);
 
-out:
-    v9fs_stat_free(&vs->v9stat);
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+    /*
+     * Fixup fid's pointing to the old name to
+     * start pointing to the new name
+     */
+    for (tfidp = s->fid_list; tfidp; tfidp = tfidp->next) {
+        if (v9fs_path_is_ancestor(&oldpath, &tfidp->path)) {
+            /* replace the name */
+            v9fs_fix_path(&tfidp->path, &newpath, strlen(oldpath.data));
+        }
+    }
+    v9fs_path_free(&oldpath);
+    v9fs_path_free(&newpath);
 }
 
-static void v9fs_rename(V9fsState *s, V9fsPDU *pdu)
+static int v9fs_complete_renameat(V9fsPDU *pdu, int32_t olddirfid,
+                                  V9fsString *old_name, int32_t newdirfid,
+                                  V9fsString *new_name)
 {
-    int32_t fid;
-    V9fsRenameState *vs;
-    ssize_t err = 0;
-
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    pdu_unmarshal(vs->pdu, vs->offset, "dds", &fid, &vs->newdirfid, &vs->name);
+    int err = 0;
+    V9fsState *s = pdu->s;
+    V9fsFidState *newdirfidp = NULL, *olddirfidp = NULL;
 
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
+    olddirfidp = get_fid(pdu, olddirfid);
+    if (olddirfidp == NULL) {
         err = -ENOENT;
         goto out;
     }
+    if (newdirfid != -1) {
+        newdirfidp = get_fid(pdu, newdirfid);
+        if (newdirfidp == NULL) {
+            err = -ENOENT;
+            goto out;
+        }
+    } else {
+        newdirfidp = get_fid(pdu, olddirfid);
+    }
 
-    BUG_ON(vs->fidp->fid_type != P9_FID_NONE);
-
-    err = v9fs_complete_rename(s, vs);
-    v9fs_rename_post_rename(s, vs, err);
-    return;
+    err = v9fs_co_renameat(pdu, &olddirfidp->path, old_name,
+                           &newdirfidp->path, new_name);
+    if (err < 0) {
+        goto out;
+    }
+    if (s->ctx.export_flags & V9FS_PATHNAME_FSCONTEXT) {
+        /* Only for path based fid  we need to do the below fixup */
+        v9fs_fix_fid_paths(pdu, &olddirfidp->path, old_name,
+                           &newdirfidp->path, new_name);
+    }
 out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+    if (olddirfidp) {
+        put_fid(pdu, olddirfidp);
+    }
+    if (newdirfidp) {
+        put_fid(pdu, newdirfidp);
+    }
+    return err;
 }
 
-static void v9fs_wstat_post_utime(V9fsState *s, V9fsWstatState *vs, int err)
+static void v9fs_renameat(void *opaque)
 {
+    ssize_t err = 0;
+    size_t offset = 7;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
+    int32_t olddirfid, newdirfid;
+    V9fsString old_name, new_name;
+
+    v9fs_string_init(&old_name);
+    v9fs_string_init(&new_name);
+    err = pdu_unmarshal(pdu, offset, "dsds", &olddirfid,
+                        &old_name, &newdirfid, &new_name);
     if (err < 0) {
-        goto out;
+        goto out_err;
     }
 
-    if (vs->v9stat.n_gid != -1 || vs->v9stat.n_uid != -1) {
-        if (v9fs_do_chown(s, &vs->fidp->path, vs->v9stat.n_uid,
-                    vs->v9stat.n_gid)) {
-            err = -errno;
-        }
+    v9fs_path_write_lock(s);
+    err = v9fs_complete_renameat(pdu, olddirfid,
+                                 &old_name, newdirfid, &new_name);
+    v9fs_path_unlock(s);
+    if (!err) {
+        err = offset;
     }
-    v9fs_wstat_post_chown(s, vs, err);
-    return;
 
-out:
-    v9fs_stat_free(&vs->v9stat);
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+out_err:
+    complete_pdu(s, pdu, err);
+    v9fs_string_free(&old_name);
+    v9fs_string_free(&new_name);
 }
 
-static void v9fs_wstat_post_chmod(V9fsState *s, V9fsWstatState *vs, int err)
+static void v9fs_wstat(void *opaque)
 {
+    int32_t fid;
+    int err = 0;
+    int16_t unused;
+    V9fsStat v9stat;
+    size_t offset = 7;
+    struct stat stbuf;
+    V9fsFidState *fidp;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
+
+    v9fs_stat_init(&v9stat);
+    err = pdu_unmarshal(pdu, offset, "dwS", &fid, &unused, &v9stat);
     if (err < 0) {
-        goto out;
+        goto out_nofid;
     }
+    trace_v9fs_wstat(pdu->tag, pdu->id, fid,
+                     v9stat.mode, v9stat.atime, v9stat.mtime);
 
-    if (vs->v9stat.mtime != -1 || vs->v9stat.atime != -1) {
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
+        err = -EINVAL;
+        goto out_nofid;
+    }
+    /* do we need to sync the file? */
+    if (donttouch_stat(&v9stat)) {
+        err = v9fs_co_fsync(pdu, fidp, 0);
+        goto out;
+    }
+    if (v9stat.mode != -1) {
+        uint32_t v9_mode;
+        err = v9fs_co_lstat(pdu, &fidp->path, &stbuf);
+        if (err < 0) {
+            goto out;
+        }
+        v9_mode = stat_to_v9mode(&stbuf);
+        if ((v9stat.mode & P9_STAT_MODE_TYPE_BITS) !=
+            (v9_mode & P9_STAT_MODE_TYPE_BITS)) {
+            /* Attempting to change the type */
+            err = -EIO;
+            goto out;
+        }
+        err = v9fs_co_chmod(pdu, &fidp->path,
+                            v9mode_to_mode(v9stat.mode,
+                                           &v9stat.extension));
+        if (err < 0) {
+            goto out;
+        }
+    }
+    if (v9stat.mtime != -1 || v9stat.atime != -1) {
         struct timespec times[2];
-        if (vs->v9stat.atime != -1) {
-            times[0].tv_sec = vs->v9stat.atime;
+        if (v9stat.atime != -1) {
+            times[0].tv_sec = v9stat.atime;
             times[0].tv_nsec = 0;
         } else {
             times[0].tv_nsec = UTIME_OMIT;
         }
-        if (vs->v9stat.mtime != -1) {
-            times[1].tv_sec = vs->v9stat.mtime;
+        if (v9stat.mtime != -1) {
+            times[1].tv_sec = v9stat.mtime;
             times[1].tv_nsec = 0;
         } else {
             times[1].tv_nsec = UTIME_OMIT;
         }
-
-        if (v9fs_do_utimensat(s, &vs->fidp->path, times)) {
-            err = -errno;
+        err = v9fs_co_utimensat(pdu, &fidp->path, times);
+        if (err < 0) {
+            goto out;
         }
     }
-
-    v9fs_wstat_post_utime(s, vs, err);
-    return;
-
-out:
-    v9fs_stat_free(&vs->v9stat);
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_wstat_post_fsync(V9fsState *s, V9fsWstatState *vs, int err)
-{
-    if (err == -1) {
-        err = -errno;
-    }
-    v9fs_stat_free(&vs->v9stat);
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_wstat_post_lstat(V9fsState *s, V9fsWstatState *vs, int err)
-{
-    uint32_t v9_mode;
-
-    if (err == -1) {
-        err = -errno;
-        goto out;
-    }
-
-    v9_mode = stat_to_v9mode(&vs->stbuf);
-
-    if ((vs->v9stat.mode & P9_STAT_MODE_TYPE_BITS) !=
-        (v9_mode & P9_STAT_MODE_TYPE_BITS)) {
-            /* Attempting to change the type */
-            err = -EIO;
+    if (v9stat.n_gid != -1 || v9stat.n_uid != -1) {
+        err = v9fs_co_chown(pdu, &fidp->path, v9stat.n_uid, v9stat.n_gid);
+        if (err < 0) {
             goto out;
+        }
     }
-
-    if (v9fs_do_chmod(s, &vs->fidp->path, v9mode_to_mode(vs->v9stat.mode,
-                    &vs->v9stat.extension))) {
-            err = -errno;
-     }
-    v9fs_wstat_post_chmod(s, vs, err);
-    return;
-
-out:
-    v9fs_stat_free(&vs->v9stat);
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_wstat(V9fsState *s, V9fsPDU *pdu)
-{
-    int32_t fid;
-    V9fsWstatState *vs;
-    int err = 0;
-
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    pdu_unmarshal(pdu, vs->offset, "dwS", &fid, &vs->unused, &vs->v9stat);
-
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
-        err = -EINVAL;
-        goto out;
-    }
-
-    /* do we need to sync the file? */
-    if (donttouch_stat(&vs->v9stat)) {
-        err = v9fs_do_fsync(s, vs->fidp->fs.fd, 0);
-        v9fs_wstat_post_fsync(s, vs, err);
-        return;
+    if (v9stat.name.size != 0) {
+        err = v9fs_complete_rename(pdu, fidp, -1, &v9stat.name);
+        if (err < 0) {
+            goto out;
+        }
     }
-
-    if (vs->v9stat.mode != -1) {
-        err = v9fs_do_lstat(s, &vs->fidp->path, &vs->stbuf);
-        v9fs_wstat_post_lstat(s, vs, err);
-        return;
+    if (v9stat.length != -1) {
+        err = v9fs_co_truncate(pdu, &fidp->path, v9stat.length);
+        if (err < 0) {
+            goto out;
+        }
     }
-
-    v9fs_wstat_post_chmod(s, vs, err);
-    return;
-
+    err = offset;
 out:
-    v9fs_stat_free(&vs->v9stat);
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+    put_fid(pdu, fidp);
+out_nofid:
+    v9fs_stat_free(&v9stat);
+    complete_pdu(s, pdu, err);
 }
 
-static void v9fs_statfs_post_statfs(V9fsState *s, V9fsStatfsState *vs, int err)
+static int v9fs_fill_statfs(V9fsState *s, V9fsPDU *pdu, struct statfs *stbuf)
 {
+    uint32_t f_type;
+    uint32_t f_bsize;
+    uint64_t f_blocks;
+    uint64_t f_bfree;
+    uint64_t f_bavail;
+    uint64_t f_files;
+    uint64_t f_ffree;
+    uint64_t fsid_val;
+    uint32_t f_namelen;
+    size_t offset = 7;
     int32_t bsize_factor;
 
-    if (err) {
-        err = -errno;
-        goto out;
-    }
-
     /*
      * compute bsize factor based on host file system block size
      * and client msize
      */
-    bsize_factor = (s->msize - P9_IOHDRSZ)/vs->stbuf.f_bsize;
+    bsize_factor = (s->msize - P9_IOHDRSZ)/stbuf->f_bsize;
     if (!bsize_factor) {
         bsize_factor = 1;
     }
-    vs->v9statfs.f_type = vs->stbuf.f_type;
-    vs->v9statfs.f_bsize = vs->stbuf.f_bsize;
-    vs->v9statfs.f_bsize *= bsize_factor;
+    f_type  = stbuf->f_type;
+    f_bsize = stbuf->f_bsize;
+    f_bsize *= bsize_factor;
     /*
      * f_bsize is adjusted(multiplied) by bsize factor, so we need to
      * adjust(divide) the number of blocks, free blocks and available
      * blocks by bsize factor
      */
-    vs->v9statfs.f_blocks = vs->stbuf.f_blocks/bsize_factor;
-    vs->v9statfs.f_bfree = vs->stbuf.f_bfree/bsize_factor;
-    vs->v9statfs.f_bavail = vs->stbuf.f_bavail/bsize_factor;
-    vs->v9statfs.f_files = vs->stbuf.f_files;
-    vs->v9statfs.f_ffree = vs->stbuf.f_ffree;
-    vs->v9statfs.fsid_val = (unsigned int) vs->stbuf.f_fsid.__val[0] |
-			(unsigned long long)vs->stbuf.f_fsid.__val[1] << 32;
-    vs->v9statfs.f_namelen = vs->stbuf.f_namelen;
-
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "ddqqqqqqd",
-         vs->v9statfs.f_type, vs->v9statfs.f_bsize, vs->v9statfs.f_blocks,
-         vs->v9statfs.f_bfree, vs->v9statfs.f_bavail, vs->v9statfs.f_files,
-         vs->v9statfs.f_ffree, vs->v9statfs.fsid_val,
-         vs->v9statfs.f_namelen);
-
-out:
-    complete_pdu(s, vs->pdu, vs->offset);
-    qemu_free(vs);
+    f_blocks = stbuf->f_blocks/bsize_factor;
+    f_bfree  = stbuf->f_bfree/bsize_factor;
+    f_bavail = stbuf->f_bavail/bsize_factor;
+    f_files  = stbuf->f_files;
+    f_ffree  = stbuf->f_ffree;
+    fsid_val = (unsigned int) stbuf->f_fsid.__val[0] |
+               (unsigned long long)stbuf->f_fsid.__val[1] << 32;
+    f_namelen = stbuf->f_namelen;
+
+    return pdu_marshal(pdu, offset, "ddqqqqqqd",
+                       f_type, f_bsize, f_blocks, f_bfree,
+                       f_bavail, f_files, f_ffree,
+                       fsid_val, f_namelen);
 }
 
-static void v9fs_statfs(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_statfs(void *opaque)
 {
-    V9fsStatfsState *vs;
-    ssize_t err = 0;
-
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    memset(&vs->v9statfs, 0, sizeof(vs->v9statfs));
-
-    pdu_unmarshal(vs->pdu, vs->offset, "d", &vs->fid);
+    int32_t fid;
+    ssize_t retval = 0;
+    size_t offset = 7;
+    V9fsFidState *fidp;
+    struct statfs stbuf;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-    vs->fidp = lookup_fid(s, vs->fid);
-    if (vs->fidp == NULL) {
-        err = -ENOENT;
-        goto out;
+    retval = pdu_unmarshal(pdu, offset, "d", &fid);
+    if (retval < 0) {
+        goto out_nofid;
     }
-
-    err = v9fs_do_statfs(s, &vs->fidp->path, &vs->stbuf);
-    v9fs_statfs_post_statfs(s, vs, err);
-    return;
-
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
-}
-
-static void v9fs_mknod_post_lstat(V9fsState *s, V9fsMkState *vs, int err)
-{
-    if (err == -1) {
-        err = -errno;
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
+        retval = -ENOENT;
+        goto out_nofid;
+    }
+    retval = v9fs_co_statfs(pdu, &fidp->path, &stbuf);
+    if (retval < 0) {
         goto out;
     }
-
-    stat_to_qid(&vs->stbuf, &vs->qid);
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "Q", &vs->qid);
-    err = vs->offset;
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->fullname);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
-}
-
-static void v9fs_mknod_post_mknod(V9fsState *s, V9fsMkState *vs, int err)
-{
-    if (err == -1) {
-        err = -errno;
+    retval = v9fs_fill_statfs(s, pdu, &stbuf);
+    if (retval < 0) {
         goto out;
     }
-
-    err = v9fs_do_lstat(s, &vs->fullname, &vs->stbuf);
-    v9fs_mknod_post_lstat(s, vs, err);
-    return;
+    retval += offset;
 out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->fullname);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(s, pdu, retval);
+    return;
 }
 
-static void v9fs_mknod(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_mknod(void *opaque)
 {
+
+    int mode;
+    gid_t gid;
     int32_t fid;
-    V9fsMkState *vs;
+    V9fsQID qid;
     int err = 0;
-    V9fsFidState *fidp;
-    gid_t gid;
-    int mode;
     int major, minor;
+    size_t offset = 7;
+    V9fsString name;
+    struct stat stbuf;
+    V9fsFidState *fidp;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    v9fs_string_init(&vs->fullname);
-    pdu_unmarshal(vs->pdu, vs->offset, "dsdddd", &fid, &vs->name, &mode,
-        &major, &minor, &gid);
+    v9fs_string_init(&name);
+    err = pdu_unmarshal(pdu, offset, "dsdddd", &fid, &name, &mode,
+                        &major, &minor, &gid);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_mknod(pdu->tag, pdu->id, fid, mode, major, minor);
 
-    fidp = lookup_fid(s, fid);
+    fidp = get_fid(pdu, fid);
     if (fidp == NULL) {
         err = -ENOENT;
+        goto out_nofid;
+    }
+    err = v9fs_co_mknod(pdu, fidp, &name, fidp->uid, gid,
+                        makedev(major, minor), mode, &stbuf);
+    if (err < 0) {
         goto out;
     }
-
-    v9fs_string_sprintf(&vs->fullname, "%s/%s", fidp->path.data, vs->name.data);
-    err = v9fs_do_mknod(s, vs->fullname.data, mode, makedev(major, minor),
-        fidp->uid, gid);
-    v9fs_mknod_post_mknod(s, vs, err);
-    return;
-
+    stat_to_qid(&stbuf, &qid);
+    err = pdu_marshal(pdu, offset, "Q", &qid);
+    if (err < 0) {
+        goto out;
+    }
+    err += offset;
+    trace_v9fs_mknod_return(pdu->tag, pdu->id,
+                            qid.type, qid.version, qid.path);
 out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->fullname);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(s, pdu, err);
+    v9fs_string_free(&name);
 }
 
 /*
@@ -3193,384 +2818,341 @@ out:
  * do any thing in * qemu 9p server side lock code path.
  * So when a TLOCK request comes, always return success
  */
-
-static void v9fs_lock(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_lock(void *opaque)
 {
+    int8_t status;
+    V9fsFlock flock;
+    size_t offset = 7;
+    struct stat stbuf;
+    V9fsFidState *fidp;
     int32_t fid, err = 0;
-    V9fsLockState *vs;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-    vs = qemu_mallocz(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    vs->flock = qemu_malloc(sizeof(*vs->flock));
-    pdu_unmarshal(vs->pdu, vs->offset, "dbdqqds", &fid, &vs->flock->type,
-                &vs->flock->flags, &vs->flock->start, &vs->flock->length,
-                            &vs->flock->proc_id, &vs->flock->client_id);
+    status = P9_LOCK_ERROR;
+    v9fs_string_init(&flock.client_id);
+    err = pdu_unmarshal(pdu, offset, "dbdqqds", &fid, &flock.type,
+                        &flock.flags, &flock.start, &flock.length,
+                        &flock.proc_id, &flock.client_id);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_lock(pdu->tag, pdu->id, fid,
+                    flock.type, flock.start, flock.length);
 
-    vs->status = P9_LOCK_ERROR;
 
     /* We support only block flag now (that too ignored currently) */
-    if (vs->flock->flags & ~P9_LOCK_FLAGS_BLOCK) {
+    if (flock.flags & ~P9_LOCK_FLAGS_BLOCK) {
         err = -EINVAL;
-        goto out;
+        goto out_nofid;
     }
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
         err = -ENOENT;
-        goto out;
+        goto out_nofid;
     }
-
-    err = v9fs_do_fstat(s, vs->fidp->fs.fd, &vs->stbuf);
+    err = v9fs_co_fstat(pdu, fidp, &stbuf);
     if (err < 0) {
-        err = -errno;
         goto out;
     }
-    vs->status = P9_LOCK_SUCCESS;
+    status = P9_LOCK_SUCCESS;
 out:
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "b", vs->status);
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs->flock);
-    qemu_free(vs);
+    put_fid(pdu, fidp);
+out_nofid:
+    err = pdu_marshal(pdu, offset, "b", status);
+    if (err > 0) {
+        err += offset;
+    }
+    trace_v9fs_lock_return(pdu->tag, pdu->id, status);
+    complete_pdu(s, pdu, err);
+    v9fs_string_free(&flock.client_id);
 }
 
 /*
  * When a TGETLOCK request comes, always return success because all lock
  * handling is done by client's VFS layer.
  */
-
-static void v9fs_getlock(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_getlock(void *opaque)
 {
+    size_t offset = 7;
+    struct stat stbuf;
+    V9fsFidState *fidp;
+    V9fsGetlock glock;
     int32_t fid, err = 0;
-    V9fsGetlockState *vs;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-    vs = qemu_mallocz(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    vs->glock = qemu_malloc(sizeof(*vs->glock));
-    pdu_unmarshal(vs->pdu, vs->offset, "dbqqds", &fid, &vs->glock->type,
-                &vs->glock->start, &vs->glock->length, &vs->glock->proc_id,
-		&vs->glock->client_id);
+    v9fs_string_init(&glock.client_id);
+    err = pdu_unmarshal(pdu, offset, "dbqqds", &fid, &glock.type,
+                        &glock.start, &glock.length, &glock.proc_id,
+                        &glock.client_id);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_getlock(pdu->tag, pdu->id, fid,
+                       glock.type, glock.start, glock.length);
 
-    vs->fidp = lookup_fid(s, fid);
-    if (vs->fidp == NULL) {
+    fidp = get_fid(pdu, fid);
+    if (fidp == NULL) {
         err = -ENOENT;
-        goto out;
+        goto out_nofid;
     }
-
-    err = v9fs_do_fstat(s, vs->fidp->fs.fd, &vs->stbuf);
+    err = v9fs_co_fstat(pdu, fidp, &stbuf);
     if (err < 0) {
-        err = -errno;
-        goto out;
-    }
-    vs->glock->type = F_UNLCK;
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "bqqds", vs->glock->type,
-                vs->glock->start, vs->glock->length, vs->glock->proc_id,
-		&vs->glock->client_id);
-out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs->glock);
-    qemu_free(vs);
-}
-
-static void v9fs_mkdir_post_lstat(V9fsState *s, V9fsMkState *vs, int err)
-{
-    if (err == -1) {
-        err = -errno;
         goto out;
     }
-
-    stat_to_qid(&vs->stbuf, &vs->qid);
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "Q", &vs->qid);
-    err = vs->offset;
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->fullname);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
-}
-
-static void v9fs_mkdir_post_mkdir(V9fsState *s, V9fsMkState *vs, int err)
-{
-    if (err == -1) {
-        err = -errno;
+    glock.type = P9_LOCK_TYPE_UNLCK;
+    err = pdu_marshal(pdu, offset, "bqqds", glock.type,
+                          glock.start, glock.length, glock.proc_id,
+                          &glock.client_id);
+    if (err < 0) {
         goto out;
     }
-
-    err = v9fs_do_lstat(s, &vs->fullname, &vs->stbuf);
-    v9fs_mkdir_post_lstat(s, vs, err);
-    return;
+    err += offset;
+    trace_v9fs_getlock_return(pdu->tag, pdu->id, glock.type, glock.start,
+                              glock.length, glock.proc_id);
 out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->fullname);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(s, pdu, err);
+    v9fs_string_free(&glock.client_id);
 }
 
-static void v9fs_mkdir(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_mkdir(void *opaque)
 {
+    V9fsPDU *pdu = opaque;
+    size_t offset = 7;
     int32_t fid;
-    V9fsMkState *vs;
-    int err = 0;
+    struct stat stbuf;
+    V9fsQID qid;
+    V9fsString name;
     V9fsFidState *fidp;
     gid_t gid;
     int mode;
+    int err = 0;
 
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    v9fs_string_init(&vs->fullname);
-    pdu_unmarshal(vs->pdu, vs->offset, "dsdd", &fid, &vs->name, &mode,
-        &gid);
+    v9fs_string_init(&name);
+    err = pdu_unmarshal(pdu, offset, "dsdd", &fid, &name, &mode, &gid);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_mkdir(pdu->tag, pdu->id, fid, name.data, mode, gid);
 
-    fidp = lookup_fid(s, fid);
+    fidp = get_fid(pdu, fid);
     if (fidp == NULL) {
         err = -ENOENT;
-        goto out;
+        goto out_nofid;
     }
-
-    v9fs_string_sprintf(&vs->fullname, "%s/%s", fidp->path.data, vs->name.data);
-    err = v9fs_do_mkdir(s, vs->fullname.data, mode, fidp->uid, gid);
-    v9fs_mkdir_post_mkdir(s, vs, err);
-    return;
-
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->fullname);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
-}
-
-static void v9fs_post_xattr_getvalue(V9fsState *s, V9fsXattrState *vs, int err)
-{
-
+    err = v9fs_co_mkdir(pdu, fidp, &name, mode, fidp->uid, gid, &stbuf);
     if (err < 0) {
-        err = -errno;
-        free_fid(s, vs->xattr_fidp->fid);
         goto out;
     }
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "q", vs->size);
-    err = vs->offset;
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
-    return;
-}
-
-static void v9fs_post_xattr_check(V9fsState *s, V9fsXattrState *vs, ssize_t err)
-{
+    stat_to_qid(&stbuf, &qid);
+    err = pdu_marshal(pdu, offset, "Q", &qid);
     if (err < 0) {
-        err = -errno;
-        free_fid(s, vs->xattr_fidp->fid);
         goto out;
     }
-    /*
-     * Read the xattr value
-     */
-    vs->xattr_fidp->fs.xattr.len = vs->size;
-    vs->xattr_fidp->fid_type = P9_FID_XATTR;
-    vs->xattr_fidp->fs.xattr.copied_len = -1;
-    if (vs->size) {
-        vs->xattr_fidp->fs.xattr.value = qemu_malloc(vs->size);
-        err = v9fs_do_lgetxattr(s, &vs->xattr_fidp->path,
-                                &vs->name, vs->xattr_fidp->fs.xattr.value,
-                                vs->xattr_fidp->fs.xattr.len);
-    }
-    v9fs_post_xattr_getvalue(s, vs, err);
-    return;
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
+    err += offset;
+    trace_v9fs_mkdir_return(pdu->tag, pdu->id,
+                            qid.type, qid.version, qid.path, err);
+out:
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(pdu->s, pdu, err);
+    v9fs_string_free(&name);
 }
 
-static void v9fs_post_lxattr_getvalue(V9fsState *s,
-                                      V9fsXattrState *vs, int err)
+static void v9fs_xattrwalk(void *opaque)
 {
-    if (err < 0) {
-        err = -errno;
-        free_fid(s, vs->xattr_fidp->fid);
-        goto out;
-    }
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "q", vs->size);
-    err = vs->offset;
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
-    return;
-}
+    int64_t size;
+    V9fsString name;
+    ssize_t err = 0;
+    size_t offset = 7;
+    int32_t fid, newfid;
+    V9fsFidState *file_fidp;
+    V9fsFidState *xattr_fidp = NULL;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-static void v9fs_post_lxattr_check(V9fsState *s,
-                                   V9fsXattrState *vs, ssize_t err)
-{
+    v9fs_string_init(&name);
+    err = pdu_unmarshal(pdu, offset, "dds", &fid, &newfid, &name);
     if (err < 0) {
-        err = -errno;
-        free_fid(s, vs->xattr_fidp->fid);
-        goto out;
-    }
-    /*
-     * Read the xattr value
-     */
-    vs->xattr_fidp->fs.xattr.len = vs->size;
-    vs->xattr_fidp->fid_type = P9_FID_XATTR;
-    vs->xattr_fidp->fs.xattr.copied_len = -1;
-    if (vs->size) {
-        vs->xattr_fidp->fs.xattr.value = qemu_malloc(vs->size);
-        err = v9fs_do_llistxattr(s, &vs->xattr_fidp->path,
-                                 vs->xattr_fidp->fs.xattr.value,
-                                 vs->xattr_fidp->fs.xattr.len);
+        goto out_nofid;
     }
-    v9fs_post_lxattr_getvalue(s, vs, err);
-    return;
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
-}
-
-static void v9fs_xattrwalk(V9fsState *s, V9fsPDU *pdu)
-{
-    ssize_t err = 0;
-    V9fsXattrState *vs;
-    int32_t fid, newfid;
+    trace_v9fs_xattrwalk(pdu->tag, pdu->id, fid, newfid, name.data);
 
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    pdu_unmarshal(vs->pdu, vs->offset, "dds", &fid, &newfid, &vs->name);
-    vs->file_fidp = lookup_fid(s, fid);
-    if (vs->file_fidp == NULL) {
+    file_fidp = get_fid(pdu, fid);
+    if (file_fidp == NULL) {
         err = -ENOENT;
-        goto out;
+        goto out_nofid;
     }
-
-    vs->xattr_fidp = alloc_fid(s, newfid);
-    if (vs->xattr_fidp == NULL) {
+    xattr_fidp = alloc_fid(s, newfid);
+    if (xattr_fidp == NULL) {
         err = -EINVAL;
         goto out;
     }
-
-    v9fs_string_copy(&vs->xattr_fidp->path, &vs->file_fidp->path);
-    if (vs->name.data[0] == 0) {
+    v9fs_path_copy(&xattr_fidp->path, &file_fidp->path);
+    if (name.data == NULL) {
         /*
          * listxattr request. Get the size first
          */
-        vs->size = v9fs_do_llistxattr(s, &vs->xattr_fidp->path,
-                                      NULL, 0);
-        if (vs->size < 0) {
-            err = vs->size;
+        size = v9fs_co_llistxattr(pdu, &xattr_fidp->path, NULL, 0);
+        if (size < 0) {
+            err = size;
+            clunk_fid(s, xattr_fidp->fid);
+            goto out;
+        }
+        /*
+         * Read the xattr value
+         */
+        xattr_fidp->fs.xattr.len = size;
+        xattr_fidp->fid_type = P9_FID_XATTR;
+        xattr_fidp->fs.xattr.copied_len = -1;
+        if (size) {
+            xattr_fidp->fs.xattr.value = g_malloc(size);
+            err = v9fs_co_llistxattr(pdu, &xattr_fidp->path,
+                                     xattr_fidp->fs.xattr.value,
+                                     xattr_fidp->fs.xattr.len);
+            if (err < 0) {
+                clunk_fid(s, xattr_fidp->fid);
+                goto out;
+            }
         }
-        v9fs_post_lxattr_check(s, vs, err);
-        return;
+        err = pdu_marshal(pdu, offset, "q", size);
+        if (err < 0) {
+            goto out;
+        }
+        err += offset;
     } else {
         /*
          * specific xattr fid. We check for xattr
          * presence also collect the xattr size
          */
-        vs->size = v9fs_do_lgetxattr(s, &vs->xattr_fidp->path,
-                                     &vs->name, NULL, 0);
-        if (vs->size < 0) {
-            err = vs->size;
+        size = v9fs_co_lgetxattr(pdu, &xattr_fidp->path,
+                                 &name, NULL, 0);
+        if (size < 0) {
+            err = size;
+            clunk_fid(s, xattr_fidp->fid);
+            goto out;
         }
-        v9fs_post_xattr_check(s, vs, err);
-        return;
+        /*
+         * Read the xattr value
+         */
+        xattr_fidp->fs.xattr.len = size;
+        xattr_fidp->fid_type = P9_FID_XATTR;
+        xattr_fidp->fs.xattr.copied_len = -1;
+        if (size) {
+            xattr_fidp->fs.xattr.value = g_malloc(size);
+            err = v9fs_co_lgetxattr(pdu, &xattr_fidp->path,
+                                    &name, xattr_fidp->fs.xattr.value,
+                                    xattr_fidp->fs.xattr.len);
+            if (err < 0) {
+                clunk_fid(s, xattr_fidp->fid);
+                goto out;
+            }
+        }
+        err = pdu_marshal(pdu, offset, "q", size);
+        if (err < 0) {
+            goto out;
+        }
+        err += offset;
     }
+    trace_v9fs_xattrwalk_return(pdu->tag, pdu->id, size);
 out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
+    put_fid(pdu, file_fidp);
+    if (xattr_fidp) {
+        put_fid(pdu, xattr_fidp);
+    }
+out_nofid:
+    complete_pdu(s, pdu, err);
+    v9fs_string_free(&name);
 }
 
-static void v9fs_xattrcreate(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_xattrcreate(void *opaque)
 {
     int flags;
     int32_t fid;
+    int64_t size;
     ssize_t err = 0;
-    V9fsXattrState *vs;
-
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
+    V9fsString name;
+    size_t offset = 7;
+    V9fsFidState *file_fidp;
+    V9fsFidState *xattr_fidp;
+    V9fsPDU *pdu = opaque;
+    V9fsState *s = pdu->s;
 
-    pdu_unmarshal(vs->pdu, vs->offset, "dsqd",
-                  &fid, &vs->name, &vs->size, &flags);
+    v9fs_string_init(&name);
+    err = pdu_unmarshal(pdu, offset, "dsqd", &fid, &name, &size, &flags);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_xattrcreate(pdu->tag, pdu->id, fid, name.data, size, flags);
 
-    vs->file_fidp = lookup_fid(s, fid);
-    if (vs->file_fidp == NULL) {
+    file_fidp = get_fid(pdu, fid);
+    if (file_fidp == NULL) {
         err = -EINVAL;
-        goto out;
+        goto out_nofid;
     }
-
     /* Make the file fid point to xattr */
-    vs->xattr_fidp = vs->file_fidp;
-    vs->xattr_fidp->fid_type = P9_FID_XATTR;
-    vs->xattr_fidp->fs.xattr.copied_len = 0;
-    vs->xattr_fidp->fs.xattr.len = vs->size;
-    vs->xattr_fidp->fs.xattr.flags = flags;
-    v9fs_string_init(&vs->xattr_fidp->fs.xattr.name);
-    v9fs_string_copy(&vs->xattr_fidp->fs.xattr.name, &vs->name);
-    if (vs->size)
-        vs->xattr_fidp->fs.xattr.value = qemu_malloc(vs->size);
-    else
-        vs->xattr_fidp->fs.xattr.value = NULL;
-
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->name);
-    qemu_free(vs);
-}
-
-static void v9fs_readlink_post_readlink(V9fsState *s, V9fsReadLinkState *vs,
-                                                    int err)
-{
-    if (err < 0) {
-        err = -errno;
-        goto out;
+    xattr_fidp = file_fidp;
+    xattr_fidp->fid_type = P9_FID_XATTR;
+    xattr_fidp->fs.xattr.copied_len = 0;
+    xattr_fidp->fs.xattr.len = size;
+    xattr_fidp->fs.xattr.flags = flags;
+    v9fs_string_init(&xattr_fidp->fs.xattr.name);
+    v9fs_string_copy(&xattr_fidp->fs.xattr.name, &name);
+    if (size) {
+        xattr_fidp->fs.xattr.value = g_malloc(size);
+    } else {
+        xattr_fidp->fs.xattr.value = NULL;
     }
-    vs->offset += pdu_marshal(vs->pdu, vs->offset, "s", &vs->target);
-    err = vs->offset;
-out:
-    complete_pdu(s, vs->pdu, err);
-    v9fs_string_free(&vs->target);
-    qemu_free(vs);
+    err = offset;
+    put_fid(pdu, file_fidp);
+out_nofid:
+    complete_pdu(s, pdu, err);
+    v9fs_string_free(&name);
 }
 
-static void v9fs_readlink(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_readlink(void *opaque)
 {
+    V9fsPDU *pdu = opaque;
+    size_t offset = 7;
+    V9fsString target;
     int32_t fid;
-    V9fsReadLinkState *vs;
     int err = 0;
     V9fsFidState *fidp;
 
-    vs = qemu_malloc(sizeof(*vs));
-    vs->pdu = pdu;
-    vs->offset = 7;
-
-    pdu_unmarshal(vs->pdu, vs->offset, "d", &fid);
-
-    fidp = lookup_fid(s, fid);
+    err = pdu_unmarshal(pdu, offset, "d", &fid);
+    if (err < 0) {
+        goto out_nofid;
+    }
+    trace_v9fs_readlink(pdu->tag, pdu->id, fid);
+    fidp = get_fid(pdu, fid);
     if (fidp == NULL) {
         err = -ENOENT;
-        goto out;
+        goto out_nofid;
     }
 
-    v9fs_string_init(&vs->target);
-    err = v9fs_do_readlink(s, &fidp->path, &vs->target);
-    v9fs_readlink_post_readlink(s, vs, err);
-    return;
+    v9fs_string_init(&target);
+    err = v9fs_co_readlink(pdu, &fidp->path, &target);
+    if (err < 0) {
+        goto out;
+    }
+    err = pdu_marshal(pdu, offset, "s", &target);
+    if (err < 0) {
+        v9fs_string_free(&target);
+        goto out;
+    }
+    err += offset;
+    trace_v9fs_readlink_return(pdu->tag, pdu->id, target.data);
+    v9fs_string_free(&target);
 out:
-    complete_pdu(s, vs->pdu, err);
-    qemu_free(vs);
+    put_fid(pdu, fidp);
+out_nofid:
+    complete_pdu(pdu->s, pdu, err);
 }
 
-typedef void (pdu_handler_t)(V9fsState *s, V9fsPDU *pdu);
-
-static pdu_handler_t *pdu_handlers[] = {
+static CoroutineEntry *pdu_co_handlers[] = {
     [P9_TREADDIR] = v9fs_readdir,
     [P9_TSTATFS] = v9fs_statfs,
     [P9_TGETATTR] = v9fs_getattr,
@@ -3581,7 +3163,9 @@ static pdu_handler_t *pdu_handlers[] = {
     [P9_TRENAME] = v9fs_rename,
     [P9_TLOCK] = v9fs_lock,
     [P9_TGETLOCK] = v9fs_getlock,
+    [P9_TRENAMEAT] = v9fs_renameat,
     [P9_TREADLINK] = v9fs_readlink,
+    [P9_TUNLINKAT] = v9fs_unlinkat,
     [P9_TMKDIR] = v9fs_mkdir,
     [P9_TVERSION] = v9fs_version,
     [P9_TLOPEN] = v9fs_open,
@@ -3605,25 +3189,62 @@ static pdu_handler_t *pdu_handlers[] = {
     [P9_TREMOVE] = v9fs_remove,
 };
 
-static void v9fs_op_not_supp(V9fsState *s, V9fsPDU *pdu)
+static void v9fs_op_not_supp(void *opaque)
+{
+    V9fsPDU *pdu = opaque;
+    complete_pdu(pdu->s, pdu, -EOPNOTSUPP);
+}
+
+static void v9fs_fs_ro(void *opaque)
 {
-    complete_pdu(s, pdu, -EOPNOTSUPP);
+    V9fsPDU *pdu = opaque;
+    complete_pdu(pdu->s, pdu, -EROFS);
+}
+
+static inline bool is_read_only_op(V9fsPDU *pdu)
+{
+    switch (pdu->id) {
+    case P9_TREADDIR:
+    case P9_TSTATFS:
+    case P9_TGETATTR:
+    case P9_TXATTRWALK:
+    case P9_TLOCK:
+    case P9_TGETLOCK:
+    case P9_TREADLINK:
+    case P9_TVERSION:
+    case P9_TLOPEN:
+    case P9_TATTACH:
+    case P9_TSTAT:
+    case P9_TWALK:
+    case P9_TCLUNK:
+    case P9_TFSYNC:
+    case P9_TOPEN:
+    case P9_TREAD:
+    case P9_TAUTH:
+    case P9_TFLUSH:
+        return 1;
+    default:
+        return 0;
+    }
 }
 
 static void submit_pdu(V9fsState *s, V9fsPDU *pdu)
 {
-    pdu_handler_t *handler;
+    Coroutine *co;
+    CoroutineEntry *handler;
 
-    if (debug_9p_pdu) {
-        pprint_pdu(pdu);
-    }
-    if (pdu->id >= ARRAY_SIZE(pdu_handlers) ||
-        (pdu_handlers[pdu->id] == NULL)) {
+    if (pdu->id >= ARRAY_SIZE(pdu_co_handlers) ||
+        (pdu_co_handlers[pdu->id] == NULL)) {
         handler = v9fs_op_not_supp;
     } else {
-        handler = pdu_handlers[pdu->id];
+        handler = pdu_co_handlers[pdu->id];
     }
-    handler(s, pdu);
+
+    if (is_ro_export(&s->ctx) && !is_read_only_op(pdu)) {
+        handler = v9fs_fs_ro;
+    }
+    co = qemu_coroutine_create(handler);
+    qemu_coroutine_enter(co, pdu);
 }
 
 void handle_9p_output(VirtIODevice *vdev, VirtQueue *vq)
@@ -3635,18 +3256,28 @@ void handle_9p_output(VirtIODevice *vdev
     while ((pdu = alloc_pdu(s)) &&
             (len = virtqueue_pop(vq, &pdu->elem)) != 0) {
         uint8_t *ptr;
-
+        pdu->s = s;
         BUG_ON(pdu->elem.out_num == 0 || pdu->elem.in_num == 0);
         BUG_ON(pdu->elem.out_sg[0].iov_len < 7);
 
         ptr = pdu->elem.out_sg[0].iov_base;
 
-        memcpy(&pdu->size, ptr, 4);
+        pdu->size = le32_to_cpu(*(uint32_t *)ptr);
         pdu->id = ptr[4];
-        memcpy(&pdu->tag, ptr + 5, 2);
-
+        pdu->tag = le16_to_cpu(*(uint16_t *)(ptr + 5));
+        qemu_co_queue_init(&pdu->complete);
         submit_pdu(s, pdu);
     }
-
     free_pdu(s, pdu);
 }
+
+void virtio_9p_set_fd_limit(void)
+{
+    struct rlimit rlim;
+    if (getrlimit(RLIMIT_NOFILE, &rlim) < 0) {
+        fprintf(stderr, "Failed to get the resource limit\n");
+        exit(1);
+    }
+    open_fd_hw = rlim.rlim_cur - MIN(400, rlim.rlim_cur/3);
+    open_fd_rc = rlim.rlim_cur/2;
+}