Merge remote-tracking branch 'remotes/maxreitz/tags/pull-block-2019-06-24' into staging

Block patches:
- The SSH block driver now uses libssh instead of libssh2
- The VMDK block driver gets read-only support for the seSparse
  subformat
- Various fixes

# gpg: Signature made Mon 24 Jun 2019 15:42:56 BST
# gpg:                using RSA key 91BEB60A30DB3E8857D11829F407DB0061D5CF40
# gpg:                issuer "mreitz@redhat.com"
# gpg: Good signature from "Max Reitz <mreitz@redhat.com>" [full]
# Primary key fingerprint: 91BE B60A 30DB 3E88 57D1  1829 F407 DB00 61D5 CF40

* remotes/maxreitz/tags/pull-block-2019-06-24:
  iotests: Fix 205 for concurrent runs
  ssh: switch from libssh2 to libssh
  vmdk: Add read-only support for seSparse snapshots
  vmdk: Reduce the max bound for L1 table size
  vmdk: Fix comment regarding max l1_size coverage
  iotest 134: test cluster-misaligned encrypted write
  blockdev: enable non-root nodes for transaction drive-backup source
  nvme: do not advertise support for unsupported arbitration mechanism

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

4 files changed, 723 insertions, 321 deletions

diff --git a/block/Makefile.objs b/block/Makefile.objs
index dbd1522722..35f3bca4d9 100644
--- a/block/Makefile.objs
+++ b/block/Makefile.objs
@@ -31,7 +31,7 @@ block-obj-$(CONFIG_CURL) += curl.o
 block-obj-$(CONFIG_RBD) += rbd.o
 block-obj-$(CONFIG_GLUSTERFS) += gluster.o
 block-obj-$(CONFIG_VXHS) += vxhs.o
-block-obj-$(CONFIG_LIBSSH2) += ssh.o
+block-obj-$(CONFIG_LIBSSH) += ssh.o
 block-obj-y += accounting.o dirty-bitmap.o
 block-obj-y += write-threshold.o
 block-obj-y += backup.o
@@ -52,8 +52,8 @@ rbd.o-libs         := $(RBD_LIBS)
 gluster.o-cflags   := $(GLUSTERFS_CFLAGS)
 gluster.o-libs     := $(GLUSTERFS_LIBS)
 vxhs.o-libs        := $(VXHS_LIBS)
-ssh.o-cflags       := $(LIBSSH2_CFLAGS)
-ssh.o-libs         := $(LIBSSH2_LIBS)
+ssh.o-cflags       := $(LIBSSH_CFLAGS)
+ssh.o-libs         := $(LIBSSH_LIBS)
 block-obj-dmg-bz2-$(CONFIG_BZIP2) += dmg-bz2.o
 block-obj-$(if $(CONFIG_DMG),m,n) += $(block-obj-dmg-bz2-y)
 dmg-bz2.o-libs     := $(BZIP2_LIBS)
diff --git a/block/ssh.c b/block/ssh.c
index 6da7b9cbfe..501933b855 100644
--- a/block/ssh.c
+++ b/block/ssh.c
@@ -24,8 +24,8 @@
 
 #include "qemu/osdep.h"
 
-#include <libssh2.h>
-#include <libssh2_sftp.h>
+#include <libssh/libssh.h>
+#include <libssh/sftp.h>
 
 #include "block/block_int.h"
 #include "block/qdict.h"
@@ -46,13 +46,11 @@
 #include "trace.h"
 
 /*
- * TRACE_LIBSSH2=<bitmask> enables tracing in libssh2 itself.  Note
- * that this requires that libssh2 was specially compiled with the
- * `./configure --enable-debug' option, so most likely you will have
- * to compile it yourself.  The meaning of <bitmask> is described
- * here: http://www.libssh2.org/libssh2_trace.html
+ * TRACE_LIBSSH=<level> enables tracing in libssh itself.
+ * The meaning of <level> is described here:
+ * http://api.libssh.org/master/group__libssh__log.html
  */
-#define TRACE_LIBSSH2 0 /* or try: LIBSSH2_TRACE_SFTP */
+#define TRACE_LIBSSH  0 /* see: SSH_LOG_* */
 
 typedef struct BDRVSSHState {
     /* Coroutine. */
@@ -60,18 +58,15 @@ typedef struct BDRVSSHState {
 
     /* SSH connection. */
     int sock;                         /* socket */
-    LIBSSH2_SESSION *session;         /* ssh session */
-    LIBSSH2_SFTP *sftp;               /* sftp session */
-    LIBSSH2_SFTP_HANDLE *sftp_handle; /* sftp remote file handle */
+    ssh_session session;              /* ssh session */
+    sftp_session sftp;                /* sftp session */
+    sftp_file sftp_handle;            /* sftp remote file handle */
 
-    /* See ssh_seek() function below. */
-    int64_t offset;
-    bool offset_op_read;
-
-    /* File attributes at open.  We try to keep the .filesize field
+    /*
+     * File attributes at open.  We try to keep the .size field
      * updated if it changes (eg by writing at the end of the file).
      */
-    LIBSSH2_SFTP_ATTRIBUTES attrs;
+    sftp_attributes attrs;
 
     InetSocketAddress *inet;
 
@@ -91,7 +86,6 @@ static void ssh_state_init(BDRVSSHState *s)
 {
     memset(s, 0, sizeof *s);
     s->sock = -1;
-    s->offset = -1;
     qemu_co_mutex_init(&s->lock);
 }
 
@@ -99,20 +93,18 @@ static void ssh_state_free(BDRVSSHState *s)
 {
     g_free(s->user);
 
+    if (s->attrs) {
+        sftp_attributes_free(s->attrs);
+    }
     if (s->sftp_handle) {
-        libssh2_sftp_close(s->sftp_handle);
+        sftp_close(s->sftp_handle);
     }
     if (s->sftp) {
-        libssh2_sftp_shutdown(s->sftp);
+        sftp_free(s->sftp);
     }
     if (s->session) {
-        libssh2_session_disconnect(s->session,
-                                   "from qemu ssh client: "
-                                   "user closed the connection");
-        libssh2_session_free(s->session);
-    }
-    if (s->sock >= 0) {
-        close(s->sock);
+        ssh_disconnect(s->session);
+        ssh_free(s->session); /* This frees s->sock */
     }
 }
 
@@ -127,13 +119,13 @@ session_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
     va_end(args);
 
     if (s->session) {
-        char *ssh_err;
+        const char *ssh_err;
         int ssh_err_code;
 
-        /* This is not an errno.  See <libssh2.h>. */
-        ssh_err_code = libssh2_session_last_error(s->session,
-                                                  &ssh_err, NULL, 0);
-        error_setg(errp, "%s: %s (libssh2 error code: %d)",
+        /* This is not an errno.  See <libssh/libssh.h>. */
+        ssh_err = ssh_get_error(s->session);
+        ssh_err_code = ssh_get_error_code(s->session);
+        error_setg(errp, "%s: %s (libssh error code: %d)",
                    msg, ssh_err, ssh_err_code);
     } else {
         error_setg(errp, "%s", msg);
@@ -152,18 +144,18 @@ sftp_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
     va_end(args);
 
     if (s->sftp) {
-        char *ssh_err;
+        const char *ssh_err;
         int ssh_err_code;
-        unsigned long sftp_err_code;
+        int sftp_err_code;
 
-        /* This is not an errno.  See <libssh2.h>. */
-        ssh_err_code = libssh2_session_last_error(s->session,
-                                                  &ssh_err, NULL, 0);
-        /* See <libssh2_sftp.h>. */
-        sftp_err_code = libssh2_sftp_last_error((s)->sftp);
+        /* This is not an errno.  See <libssh/libssh.h>. */
+        ssh_err = ssh_get_error(s->session);
+        ssh_err_code = ssh_get_error_code(s->session);
+        /* See <libssh/sftp.h>. */
+        sftp_err_code = sftp_get_error(s->sftp);
 
         error_setg(errp,
-                   "%s: %s (libssh2 error code: %d, sftp error code: %lu)",
+                   "%s: %s (libssh error code: %d, sftp error code: %d)",
                    msg, ssh_err, ssh_err_code, sftp_err_code);
     } else {
         error_setg(errp, "%s", msg);
@@ -173,15 +165,15 @@ sftp_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
 
 static void sftp_error_trace(BDRVSSHState *s, const char *op)
 {
-    char *ssh_err;
+    const char *ssh_err;
     int ssh_err_code;
-    unsigned long sftp_err_code;
+    int sftp_err_code;
 
-    /* This is not an errno.  See <libssh2.h>. */
-    ssh_err_code = libssh2_session_last_error(s->session,
-                                              &ssh_err, NULL, 0);
-    /* See <libssh2_sftp.h>. */
-    sftp_err_code = libssh2_sftp_last_error((s)->sftp);
+    /* This is not an errno.  See <libssh/libssh.h>. */
+    ssh_err = ssh_get_error(s->session);
+    ssh_err_code = ssh_get_error_code(s->session);
+    /* See <libssh/sftp.h>. */
+    sftp_err_code = sftp_get_error(s->sftp);
 
     trace_sftp_error(op, ssh_err, ssh_err_code, sftp_err_code);
 }
@@ -282,82 +274,120 @@ static void ssh_parse_filename(const char *filename, QDict *options,
     parse_uri(filename, options, errp);
 }
 
-static int check_host_key_knownhosts(BDRVSSHState *s,
-                                     const char *host, int port, Error **errp)
+static int check_host_key_knownhosts(BDRVSSHState *s, Error **errp)
 {
-    const char *home;
-    char *knh_file = NULL;
-    LIBSSH2_KNOWNHOSTS *knh = NULL;
-    struct libssh2_knownhost *found;
-    int ret, r;
-    const char *hostkey;
-    size_t len;
-    int type;
-
-    hostkey = libssh2_session_hostkey(s->session, &len, &type);
-    if (!hostkey) {
+    int ret;
+#ifdef HAVE_LIBSSH_0_8
+    enum ssh_known_hosts_e state;
+    int r;
+    ssh_key pubkey;
+    enum ssh_keytypes_e pubkey_type;
+    unsigned char *server_hash = NULL;
+    size_t server_hash_len;
+    char *fingerprint = NULL;
+
+    state = ssh_session_is_known_server(s->session);
+    trace_ssh_server_status(state);
+
+    switch (state) {
+    case SSH_KNOWN_HOSTS_OK:
+        /* OK */
+        trace_ssh_check_host_key_knownhosts();
+        break;
+    case SSH_KNOWN_HOSTS_CHANGED:
         ret = -EINVAL;
-        session_error_setg(errp, s, "failed to read remote host key");
+        r = ssh_get_server_publickey(s->session, &pubkey);
+        if (r == 0) {
+            r = ssh_get_publickey_hash(pubkey, SSH_PUBLICKEY_HASH_SHA256,
+                                       &server_hash, &server_hash_len);
+            pubkey_type = ssh_key_type(pubkey);
+            ssh_key_free(pubkey);
+        }
+        if (r == 0) {
+            fingerprint = ssh_get_fingerprint_hash(SSH_PUBLICKEY_HASH_SHA256,
+                                                   server_hash,
+                                                   server_hash_len);
+            ssh_clean_pubkey_hash(&server_hash);
+        }
+        if (fingerprint) {
+            error_setg(errp,
+                       "host key (%s key with fingerprint %s) does not match "
+                       "the one in known_hosts; this may be a possible attack",
+                       ssh_key_type_to_char(pubkey_type), fingerprint);
+            ssh_string_free_char(fingerprint);
+        } else  {
+            error_setg(errp,
+                       "host key does not match the one in known_hosts; this "
+                       "may be a possible attack");
+        }
         goto out;
-    }
-
-    knh = libssh2_knownhost_init(s->session);
-    if (!knh) {
+    case SSH_KNOWN_HOSTS_OTHER:
         ret = -EINVAL;
-        session_error_setg(errp, s,
-                           "failed to initialize known hosts support");
+        error_setg(errp,
+                   "host key for this server not found, another type exists");
+        goto out;
+    case SSH_KNOWN_HOSTS_UNKNOWN:
+        ret = -EINVAL;
+        error_setg(errp, "no host key was found in known_hosts");
+        goto out;
+    case SSH_KNOWN_HOSTS_NOT_FOUND:
+        ret = -ENOENT;
+        error_setg(errp, "known_hosts file not found");
+        goto out;
+    case SSH_KNOWN_HOSTS_ERROR:
+        ret = -EINVAL;
+        error_setg(errp, "error while checking the host");
+        goto out;
+    default:
+        ret = -EINVAL;
+        error_setg(errp, "error while checking for known server (%d)", state);
         goto out;
     }
+#else /* !HAVE_LIBSSH_0_8 */
+    int state;
 
-    home = getenv("HOME");
-    if (home) {
-        knh_file = g_strdup_printf("%s/.ssh/known_hosts", home);
-    } else {
-        knh_file = g_strdup_printf("/root/.ssh/known_hosts");
-    }
-
-    /* Read all known hosts from OpenSSH-style known_hosts file. */
-    libssh2_knownhost_readfile(knh, knh_file, LIBSSH2_KNOWNHOST_FILE_OPENSSH);
+    state = ssh_is_server_known(s->session);
+    trace_ssh_server_status(state);
 
-    r = libssh2_knownhost_checkp(knh, host, port, hostkey, len,
-                                 LIBSSH2_KNOWNHOST_TYPE_PLAIN|
-                                 LIBSSH2_KNOWNHOST_KEYENC_RAW,
-                                 &found);
-    switch (r) {
-    case LIBSSH2_KNOWNHOST_CHECK_MATCH:
+    switch (state) {
+    case SSH_SERVER_KNOWN_OK:
         /* OK */
-        trace_ssh_check_host_key_knownhosts(found->key);
+        trace_ssh_check_host_key_knownhosts();
         break;
-    case LIBSSH2_KNOWNHOST_CHECK_MISMATCH:
+    case SSH_SERVER_KNOWN_CHANGED:
         ret = -EINVAL;
-        session_error_setg(errp, s,
-                      "host key does not match the one in known_hosts"
-                      " (found key %s)", found->key);
+        error_setg(errp,
+                   "host key does not match the one in known_hosts; this "
+                   "may be a possible attack");
         goto out;
-    case LIBSSH2_KNOWNHOST_CHECK_NOTFOUND:
+    case SSH_SERVER_FOUND_OTHER:
         ret = -EINVAL;
-        session_error_setg(errp, s, "no host key was found in known_hosts");
+        error_setg(errp,
+                   "host key for this server not found, another type exists");
+        goto out;
+    case SSH_SERVER_FILE_NOT_FOUND:
+        ret = -ENOENT;
+        error_setg(errp, "known_hosts file not found");
         goto out;
-    case LIBSSH2_KNOWNHOST_CHECK_FAILURE:
+    case SSH_SERVER_NOT_KNOWN:
         ret = -EINVAL;
-        session_error_setg(errp, s,
-                      "failure matching the host key with known_hosts");
+        error_setg(errp, "no host key was found in known_hosts");
+        goto out;
+    case SSH_SERVER_ERROR:
+        ret = -EINVAL;
+        error_setg(errp, "server error");
         goto out;
     default:
         ret = -EINVAL;
-        session_error_setg(errp, s, "unknown error matching the host key"
-                      " with known_hosts (%d)", r);
+        error_setg(errp, "error while checking for known server (%d)", state);
         goto out;
     }
+#endif /* !HAVE_LIBSSH_0_8 */
 
     /* known_hosts checking successful. */
     ret = 0;
 
  out:
-    if (knh != NULL) {
-        libssh2_knownhost_free(knh);
-    }
-    g_free(knh_file);
     return ret;
 }
 
@@ -401,18 +431,34 @@ static int compare_fingerprint(const unsigned char *fingerprint, size_t len,
 
 static int
 check_host_key_hash(BDRVSSHState *s, const char *hash,
-                    int hash_type, size_t fingerprint_len, Error **errp)
+                    enum ssh_publickey_hash_type type, Error **errp)
 {
-    const char *fingerprint;
-
-    fingerprint = libssh2_hostkey_hash(s->session, hash_type);
-    if (!fingerprint) {
+    int r;
+    ssh_key pubkey;
+    unsigned char *server_hash;
+    size_t server_hash_len;
+
+#ifdef HAVE_LIBSSH_0_8
+    r = ssh_get_server_publickey(s->session, &pubkey);
+#else
+    r = ssh_get_publickey(s->session, &pubkey);
+#endif
+    if (r != SSH_OK) {
         session_error_setg(errp, s, "failed to read remote host key");
         return -EINVAL;
     }
 
-    if(compare_fingerprint((unsigned char *) fingerprint, fingerprint_len,
-                           hash) != 0) {
+    r = ssh_get_publickey_hash(pubkey, type, &server_hash, &server_hash_len);
+    ssh_key_free(pubkey);
+    if (r != 0) {
+        session_error_setg(errp, s,
+                           "failed reading the hash of the server SSH key");
+        return -EINVAL;
+    }
+
+    r = compare_fingerprint(server_hash, server_hash_len, hash);
+    ssh_clean_pubkey_hash(&server_hash);
+    if (r != 0) {
         error_setg(errp, "remote host key does not match host_key_check '%s'",
                    hash);
         return -EPERM;
@@ -421,8 +467,7 @@ check_host_key_hash(BDRVSSHState *s, const char *hash,
     return 0;
 }
 
-static int check_host_key(BDRVSSHState *s, const char *host, int port,
-                          SshHostKeyCheck *hkc, Error **errp)
+static int check_host_key(BDRVSSHState *s, SshHostKeyCheck *hkc, Error **errp)
 {
     SshHostKeyCheckMode mode;
 
@@ -438,15 +483,15 @@ static int check_host_key(BDRVSSHState *s, const char *host, int port,
     case SSH_HOST_KEY_CHECK_MODE_HASH:
         if (hkc->u.hash.type == SSH_HOST_KEY_CHECK_HASH_TYPE_MD5) {
             return check_host_key_hash(s, hkc->u.hash.hash,
-                                       LIBSSH2_HOSTKEY_HASH_MD5, 16, errp);
+                                       SSH_PUBLICKEY_HASH_MD5, errp);
         } else if (hkc->u.hash.type == SSH_HOST_KEY_CHECK_HASH_TYPE_SHA1) {
             return check_host_key_hash(s, hkc->u.hash.hash,
-                                       LIBSSH2_HOSTKEY_HASH_SHA1, 20, errp);
+                                       SSH_PUBLICKEY_HASH_SHA1, errp);
         }
         g_assert_not_reached();
         break;
     case SSH_HOST_KEY_CHECK_MODE_KNOWN_HOSTS:
-        return check_host_key_knownhosts(s, host, port, errp);
+        return check_host_key_knownhosts(s, errp);
     default:
         g_assert_not_reached();
     }
@@ -454,60 +499,43 @@ static int check_host_key(BDRVSSHState *s, const char *host, int port,
     return -EINVAL;
 }
 
-static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
+static int authenticate(BDRVSSHState *s, Error **errp)
 {
     int r, ret;
-    const char *userauthlist;
-    LIBSSH2_AGENT *agent = NULL;
-    struct libssh2_agent_publickey *identity;
-    struct libssh2_agent_publickey *prev_identity = NULL;
+    int method;
 
-    userauthlist = libssh2_userauth_list(s->session, user, strlen(user));
-    if (strstr(userauthlist, "publickey") == NULL) {
+    /* Try to authenticate with the "none" method. */
+    r = ssh_userauth_none(s->session, NULL);
+    if (r == SSH_AUTH_ERROR) {
         ret = -EPERM;
-        error_setg(errp,
-                "remote server does not support \"publickey\" authentication");
+        session_error_setg(errp, s, "failed to authenticate using none "
+                                    "authentication");
         goto out;
-    }
-
-    /* Connect to ssh-agent and try each identity in turn. */
-    agent = libssh2_agent_init(s->session);
-    if (!agent) {
-        ret = -EINVAL;
-        session_error_setg(errp, s, "failed to initialize ssh-agent support");
-        goto out;
-    }
-    if (libssh2_agent_connect(agent)) {
-        ret = -ECONNREFUSED;
-        session_error_setg(errp, s, "failed to connect to ssh-agent");
-        goto out;
-    }
-    if (libssh2_agent_list_identities(agent)) {
-        ret = -EINVAL;
-        session_error_setg(errp, s,
-                           "failed requesting identities from ssh-agent");
+    } else if (r == SSH_AUTH_SUCCESS) {
+        /* Authenticated! */
+        ret = 0;
         goto out;
     }
 
-    for(;;) {
-        r = libssh2_agent_get_identity(agent, &identity, prev_identity);
-        if (r == 1) {           /* end of list */
-            break;
-        }
-        if (r < 0) {
+    method = ssh_userauth_list(s->session, NULL);
+    trace_ssh_auth_methods(method);
+
+    /*
+     * Try to authenticate with publickey, using the ssh-agent
+     * if available.
+     */
+    if (method & SSH_AUTH_METHOD_PUBLICKEY) {
+        r = ssh_userauth_publickey_auto(s->session, NULL, NULL);
+        if (r == SSH_AUTH_ERROR) {
             ret = -EINVAL;
-            session_error_setg(errp, s,
-                               "failed to obtain identity from ssh-agent");
+            session_error_setg(errp, s, "failed to authenticate using "
+                                        "publickey authentication");
             goto out;
-        }
-        r = libssh2_agent_userauth(agent, user, identity);
-        if (r == 0) {
+        } else if (r == SSH_AUTH_SUCCESS) {
             /* Authenticated! */
             ret = 0;
             goto out;
         }
-        /* Failed to authenticate with this identity, try the next one. */
-        prev_identity = identity;
     }
 
     ret = -EPERM;
@@ -515,13 +543,6 @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
                "and the identities held by your ssh-agent");
 
  out:
-    if (agent != NULL) {
-        /* Note: libssh2 implementation implicitly calls
-         * libssh2_agent_disconnect if necessary.
-         */
-        libssh2_agent_free(agent);
-    }
-
     return ret;
 }
 
@@ -640,7 +661,8 @@ static int connect_to_ssh(BDRVSSHState *s, BlockdevOptionsSsh *opts,
                           int ssh_flags, int creat_mode, Error **errp)
 {
     int r, ret;
-    long port = 0;
+    unsigned int port = 0;
+    int new_sock = -1;
 
     if (opts->has_user) {
         s->user = g_strdup(opts->user);
@@ -657,71 +679,147 @@ static int connect_to_ssh(BDRVSSHState *s, BlockdevOptionsSsh *opts,
     s->inet = opts->server;
     opts->server = NULL;
 
-    if (qemu_strtol(s->inet->port, NULL, 10, &port) < 0) {
+    if (qemu_strtoui(s->inet->port, NULL, 10, &port) < 0) {
         error_setg(errp, "Use only numeric port value");
         ret = -EINVAL;
         goto err;
     }
 
     /* Open the socket and connect. */
-    s->sock = inet_connect_saddr(s->inet, errp);
-    if (s->sock < 0) {
+    new_sock = inet_connect_saddr(s->inet, errp);
+    if (new_sock < 0) {
         ret = -EIO;
         goto err;
     }
 
+    /*
+     * Try to disable the Nagle algorithm on TCP sockets to reduce latency,
+     * but do not fail if it cannot be disabled.
+     */
+    r = socket_set_nodelay(new_sock);
+    if (r < 0) {
+        warn_report("can't set TCP_NODELAY for the ssh server %s: %s",
+                    s->inet->host, strerror(errno));
+    }
+
     /* Create SSH session. */
-    s->session = libssh2_session_init();
+    s->session = ssh_new();
     if (!s->session) {
         ret = -EINVAL;
-        session_error_setg(errp, s, "failed to initialize libssh2 session");
+        session_error_setg(errp, s, "failed to initialize libssh session");
         goto err;
     }
 
-#if TRACE_LIBSSH2 != 0
-    libssh2_trace(s->session, TRACE_LIBSSH2);
-#endif
+    /*
+     * Make sure we are in blocking mode during the connection and
+     * authentication phases.
+     */
+    ssh_set_blocking(s->session, 1);
 
-    r = libssh2_session_handshake(s->session, s->sock);
-    if (r != 0) {
+    r = ssh_options_set(s->session, SSH_OPTIONS_USER, s->user);
+    if (r < 0) {
+        ret = -EINVAL;
+        session_error_setg(errp, s,
+                           "failed to set the user in the libssh session");
+        goto err;
+    }
+
+    r = ssh_options_set(s->session, SSH_OPTIONS_HOST, s->inet->host);
+    if (r < 0) {
+        ret = -EINVAL;
+        session_error_setg(errp, s,
+                           "failed to set the host in the libssh session");
+        goto err;
+    }
+
+    if (port > 0) {
+        r = ssh_options_set(s->session, SSH_OPTIONS_PORT, &port);
+        if (r < 0) {
+            ret = -EINVAL;
+            session_error_setg(errp, s,
+                               "failed to set the port in the libssh session");
+            goto err;
+        }
+    }
+
+    r = ssh_options_set(s->session, SSH_OPTIONS_COMPRESSION, "none");
+    if (r < 0) {
+        ret = -EINVAL;
+        session_error_setg(errp, s,
+                           "failed to disable the compression in the libssh "
+                           "session");
+        goto err;
+    }
+
+    /* Read ~/.ssh/config. */
+    r = ssh_options_parse_config(s->session, NULL);
+    if (r < 0) {
+        ret = -EINVAL;
+        session_error_setg(errp, s, "failed to parse ~/.ssh/config");
+        goto err;
+    }
+
+    r = ssh_options_set(s->session, SSH_OPTIONS_FD, &new_sock);
+    if (r < 0) {
+        ret = -EINVAL;
+        session_error_setg(errp, s,
+                           "failed to set the socket in the libssh session");
+        goto err;
+    }
+    /* libssh took ownership of the socket. */
+    s->sock = new_sock;
+    new_sock = -1;
+
+    /* Connect. */
+    r = ssh_connect(s->session);
+    if (r != SSH_OK) {
         ret = -EINVAL;
         session_error_setg(errp, s, "failed to establish SSH session");
         goto err;
     }
 
     /* Check the remote host's key against known_hosts. */
-    ret = check_host_key(s, s->inet->host, port, opts->host_key_check, errp);
+    ret = check_host_key(s, opts->host_key_check, errp);
     if (ret < 0) {
         goto err;
     }
 
     /* Authenticate. */
-    ret = authenticate(s, s->user, errp);
+    ret = authenticate(s, errp);
     if (ret < 0) {
         goto err;
     }
 
     /* Start SFTP. */
-    s->sftp = libssh2_sftp_init(s->session);
+    s->sftp = sftp_new(s->session);
     if (!s->sftp) {
-        session_error_setg(errp, s, "failed to initialize sftp handle");
+        session_error_setg(errp, s, "failed to create sftp handle");
+        ret = -EINVAL;
+        goto err;
+    }
+
+    r = sftp_init(s->sftp);
+    if (r < 0) {
+        sftp_error_setg(errp, s, "failed to initialize sftp handle");
         ret = -EINVAL;
         goto err;
     }
 
     /* Open the remote file. */
     trace_ssh_connect_to_ssh(opts->path, ssh_flags, creat_mode);
-    s->sftp_handle = libssh2_sftp_open(s->sftp, opts->path, ssh_flags,
-                                       creat_mode);
+    s->sftp_handle = sftp_open(s->sftp, opts->path, ssh_flags, creat_mode);
     if (!s->sftp_handle) {
-        session_error_setg(errp, s, "failed to open remote file '%s'",
-                           opts->path);
+        sftp_error_setg(errp, s, "failed to open remote file '%s'",
+                        opts->path);
         ret = -EINVAL;
         goto err;
     }
 
-    r = libssh2_sftp_fstat(s->sftp_handle, &s->attrs);
-    if (r < 0) {
+    /* Make sure the SFTP file is handled in blocking mode. */
+    sftp_file_set_blocking(s->sftp_handle);
+
+    s->attrs = sftp_fstat(s->sftp_handle);
+    if (!s->attrs) {
         sftp_error_setg(errp, s, "failed to read file attributes");
         return -EINVAL;
     }
@@ -729,21 +827,27 @@ static int connect_to_ssh(BDRVSSHState *s, BlockdevOptionsSsh *opts,
     return 0;
 
  err:
+    if (s->attrs) {
+        sftp_attributes_free(s->attrs);
+    }
+    s->attrs = NULL;
     if (s->sftp_handle) {
-        libssh2_sftp_close(s->sftp_handle);
+        sftp_close(s->sftp_handle);
     }
     s->sftp_handle = NULL;
     if (s->sftp) {
-        libssh2_sftp_shutdown(s->sftp);
+        sftp_free(s->sftp);
     }
     s->sftp = NULL;
     if (s->session) {
-        libssh2_session_disconnect(s->session,
-                                   "from qemu ssh client: "
-                                   "error opening connection");
-        libssh2_session_free(s->session);
+        ssh_disconnect(s->session);
+        ssh_free(s->session);
     }
     s->session = NULL;
+    s->sock = -1;
+    if (new_sock >= 0) {
+        close(new_sock);
+    }
 
     return ret;
 }
@@ -758,9 +862,11 @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
 
     ssh_state_init(s);
 
-    ssh_flags = LIBSSH2_FXF_READ;
+    ssh_flags = 0;
     if (bdrv_flags & BDRV_O_RDWR) {
-        ssh_flags |= LIBSSH2_FXF_WRITE;
+        ssh_flags |= O_RDWR;
+    } else {
+        ssh_flags |= O_RDONLY;
     }
 
     opts = ssh_parse_options(options, errp);
@@ -775,18 +881,13 @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
     }
 
     /* Go non-blocking. */
-    libssh2_session_set_blocking(s->session, 0);
+    ssh_set_blocking(s->session, 0);
 
     qapi_free_BlockdevOptionsSsh(opts);
 
     return 0;
 
  err:
-    if (s->sock >= 0) {
-        close(s->sock);
-    }
-    s->sock = -1;
-
     qapi_free_BlockdevOptionsSsh(opts);
 
     return ret;
@@ -797,25 +898,25 @@ static int ssh_grow_file(BDRVSSHState *s, int64_t offset, Error **errp)
 {
     ssize_t ret;
     char c[1] = { '\0' };
-    int was_blocking = libssh2_session_get_blocking(s->session);
+    int was_blocking = ssh_is_blocking(s->session);
 
     /* offset must be strictly greater than the current size so we do
      * not overwrite anything */
-    assert(offset > 0 && offset > s->attrs.filesize);
+    assert(offset > 0 && offset > s->attrs->size);
 
-    libssh2_session_set_blocking(s->session, 1);
+    ssh_set_blocking(s->session, 1);
 
-    libssh2_sftp_seek64(s->sftp_handle, offset - 1);
-    ret = libssh2_sftp_write(s->sftp_handle, c, 1);
+    sftp_seek64(s->sftp_handle, offset - 1);
+    ret = sftp_write(s->sftp_handle, c, 1);
 
-    libssh2_session_set_blocking(s->session, was_blocking);
+    ssh_set_blocking(s->session, was_blocking);
 
     if (ret < 0) {
         sftp_error_setg(errp, s, "Failed to grow file");
         return -EIO;
     }
 
-    s->attrs.filesize = offset;
+    s->attrs->size = offset;
     return 0;
 }
 
@@ -843,8 +944,7 @@ static int ssh_co_create(BlockdevCreateOptions *options, Error **errp)
     ssh_state_init(&s);
 
     ret = connect_to_ssh(&s, opts->location,
-                         LIBSSH2_FXF_READ|LIBSSH2_FXF_WRITE|
-                         LIBSSH2_FXF_CREAT|LIBSSH2_FXF_TRUNC,
+                         O_RDWR | O_CREAT | O_TRUNC,
                          0644, errp);
     if (ret < 0) {
         goto fail;
@@ -913,10 +1013,8 @@ static int ssh_has_zero_init(BlockDriverState *bs)
     /* Assume false, unless we can positively prove it's true. */
     int has_zero_init = 0;
 
-    if (s->attrs.flags & LIBSSH2_SFTP_ATTR_PERMISSIONS) {
-        if (s->attrs.permissions & LIBSSH2_SFTP_S_IFREG) {
-            has_zero_init = 1;
-        }
+    if (s->attrs->type == SSH_FILEXFER_TYPE_REGULAR) {
+        has_zero_init = 1;
     }
 
     return has_zero_init;
@@ -953,12 +1051,12 @@ static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs)
         .co = qemu_coroutine_self()
     };
 
-    r = libssh2_session_block_directions(s->session);
+    r = ssh_get_poll_flags(s->session);
 
-    if (r & LIBSSH2_SESSION_BLOCK_INBOUND) {
+    if (r & SSH_READ_PENDING) {
         rd_handler = restart_coroutine;
     }
-    if (r & LIBSSH2_SESSION_BLOCK_OUTBOUND) {
+    if (r & SSH_WRITE_PENDING) {
         wr_handler = restart_coroutine;
     }
 
@@ -970,33 +1068,6 @@ static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs)
     trace_ssh_co_yield_back(s->sock);
 }
 
-/* SFTP has a function `libssh2_sftp_seek64' which seeks to a position
- * in the remote file.  Notice that it just updates a field in the
- * sftp_handle structure, so there is no network traffic and it cannot
- * fail.
- *
- * However, `libssh2_sftp_seek64' does have a catastrophic effect on
- * performance since it causes the handle to throw away all in-flight
- * reads and buffered readahead data.  Therefore this function tries
- * to be intelligent about when to call the underlying libssh2 function.
- */
-#define SSH_SEEK_WRITE 0
-#define SSH_SEEK_READ  1
-#define SSH_SEEK_FORCE 2
-
-static void ssh_seek(BDRVSSHState *s, int64_t offset, int flags)
-{
-    bool op_read = (flags & SSH_SEEK_READ) != 0;
-    bool force = (flags & SSH_SEEK_FORCE) != 0;
-
-    if (force || op_read != s->offset_op_read || offset != s->offset) {
-        trace_ssh_seek(offset);
-        libssh2_sftp_seek64(s->sftp_handle, offset);
-        s->offset = offset;
-        s->offset_op_read = op_read;
-    }
-}
-
 static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
                                  int64_t offset, size_t size,
                                  QEMUIOVector *qiov)
@@ -1008,7 +1079,8 @@ static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
 
     trace_ssh_read(offset, size);
 
-    ssh_seek(s, offset, SSH_SEEK_READ);
+    trace_ssh_seek(offset);
+    sftp_seek64(s->sftp_handle, offset);
 
     /* This keeps track of the current iovec element ('i'), where we
      * will write to next ('buf'), and the end of the current iovec
@@ -1018,35 +1090,35 @@ static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
     buf = i->iov_base;
     end_of_vec = i->iov_base + i->iov_len;
 
-    /* libssh2 has a hard-coded limit of 2000 bytes per request,
-     * although it will also do readahead behind our backs.  Therefore
-     * we may have to do repeated reads here until we have read 'size'
-     * bytes.
-     */
     for (got = 0; got < size; ) {
+        size_t request_read_size;
     again:
-        trace_ssh_read_buf(buf, end_of_vec - buf);
-        r = libssh2_sftp_read(s->sftp_handle, buf, end_of_vec - buf);
-        trace_ssh_read_return(r);
+        /*
+         * The size of SFTP packets is limited to 32K bytes, so limit
+         * the amount of data requested to 16K, as libssh currently
+         * does not handle multiple requests on its own.
+         */
+        request_read_size = MIN(end_of_vec - buf, 16384);
+        trace_ssh_read_buf(buf, end_of_vec - buf, request_read_size);
+        r = sftp_read(s->sftp_handle, buf, request_read_size);
+        trace_ssh_read_return(r, sftp_get_error(s->sftp));
 
-        if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
+        if (r == SSH_AGAIN) {
             co_yield(s, bs);
             goto again;
         }
-        if (r < 0) {
-            sftp_error_trace(s, "read");
-            s->offset = -1;
-            return -EIO;
-        }
-        if (r == 0) {
+        if (r == SSH_EOF || (r == 0 && sftp_get_error(s->sftp) == SSH_FX_EOF)) {
             /* EOF: Short read so pad the buffer with zeroes and return it. */
             qemu_iovec_memset(qiov, got, 0, size - got);
             return 0;
         }
+        if (r <= 0) {
+            sftp_error_trace(s, "read");
+            return -EIO;
+        }
 
         got += r;
         buf += r;
-        s->offset += r;
         if (buf >= end_of_vec && got < size) {
             i++;
             buf = i->iov_base;
@@ -1083,7 +1155,8 @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
 
     trace_ssh_write(offset, size);
 
-    ssh_seek(s, offset, SSH_SEEK_WRITE);
+    trace_ssh_seek(offset);
+    sftp_seek64(s->sftp_handle, offset);
 
     /* This keeps track of the current iovec element ('i'), where we
      * will read from next ('buf'), and the end of the current iovec
@@ -1094,46 +1167,37 @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
     end_of_vec = i->iov_base + i->iov_len;
 
     for (written = 0; written < size; ) {
+        size_t request_write_size;
     again:
-        trace_ssh_write_buf(buf, end_of_vec - buf);
-        r = libssh2_sftp_write(s->sftp_handle, buf, end_of_vec - buf);
-        trace_ssh_write_return(r);
+        /*
+         * Avoid too large data packets, as libssh currently does not
+         * handle multiple requests on its own.
+         */
+        request_write_size = MIN(end_of_vec - buf, 131072);
+        trace_ssh_write_buf(buf, end_of_vec - buf, request_write_size);
+        r = sftp_write(s->sftp_handle, buf, request_write_size);
+        trace_ssh_write_return(r, sftp_get_error(s->sftp));
 
-        if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
+        if (r == SSH_AGAIN) {
             co_yield(s, bs);
             goto again;
         }
         if (r < 0) {
             sftp_error_trace(s, "write");
-            s->offset = -1;
             return -EIO;
         }
-        /* The libssh2 API is very unclear about this.  A comment in
-         * the code says "nothing was acked, and no EAGAIN was
-         * received!" which apparently means that no data got sent
-         * out, and the underlying channel didn't return any EAGAIN
-         * indication.  I think this is a bug in either libssh2 or
-         * OpenSSH (server-side).  In any case, forcing a seek (to
-         * discard libssh2 internal buffers), and then trying again
-         * works for me.
-         */
-        if (r == 0) {
-            ssh_seek(s, offset + written, SSH_SEEK_WRITE|SSH_SEEK_FORCE);
-            co_yield(s, bs);
-            goto again;
-        }
 
         written += r;
         buf += r;
-        s->offset += r;
         if (buf >= end_of_vec && written < size) {
             i++;
             buf = i->iov_base;
             end_of_vec = i->iov_base + i->iov_len;
         }
 
-        if (offset + written > s->attrs.filesize)
-            s->attrs.filesize = offset + written;
+        if (offset + written > s->attrs->size) {
+            s->attrs->size = offset + written;
+        }
     }
 
     return 0;
@@ -1168,24 +1232,24 @@ static void unsafe_flush_warning(BDRVSSHState *s, const char *what)
     }
 }
 
-#ifdef HAS_LIBSSH2_SFTP_FSYNC
+#ifdef HAVE_LIBSSH_0_8
 
 static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs)
 {
     int r;
 
     trace_ssh_flush();
+
+    if (!sftp_extension_supported(s->sftp, "fsync@openssh.com", "1")) {
+        unsafe_flush_warning(s, "OpenSSH >= 6.3");
+        return 0;
+    }
  again:
-    r = libssh2_sftp_fsync(s->sftp_handle);
-    if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
+    r = sftp_fsync(s->sftp_handle);
+    if (r == SSH_AGAIN) {
         co_yield(s, bs);
         goto again;
     }
-    if (r == LIBSSH2_ERROR_SFTP_PROTOCOL &&
-        libssh2_sftp_last_error(s->sftp) == LIBSSH2_FX_OP_UNSUPPORTED) {
-        unsafe_flush_warning(s, "OpenSSH >= 6.3");
-        return 0;
-    }
     if (r < 0) {
         sftp_error_trace(s, "fsync");
         return -EIO;
@@ -1206,25 +1270,25 @@ static coroutine_fn int ssh_co_flush(BlockDriverState *bs)
     return ret;
 }
 
-#else /* !HAS_LIBSSH2_SFTP_FSYNC */
+#else /* !HAVE_LIBSSH_0_8 */
 
 static coroutine_fn int ssh_co_flush(BlockDriverState *bs)
 {
     BDRVSSHState *s = bs->opaque;
 
-    unsafe_flush_warning(s, "libssh2 >= 1.4.4");
+    unsafe_flush_warning(s, "libssh >= 0.8.0");
     return 0;
 }
 
-#endif /* !HAS_LIBSSH2_SFTP_FSYNC */
+#endif /* !HAVE_LIBSSH_0_8 */
 
 static int64_t ssh_getlength(BlockDriverState *bs)
 {
     BDRVSSHState *s = bs->opaque;
     int64_t length;
 
-    /* Note we cannot make a libssh2 call here. */
-    length = (int64_t) s->attrs.filesize;
+    /* Note we cannot make a libssh call here. */
+    length = (int64_t) s->attrs->size;
     trace_ssh_getlength(length);
 
     return length;
@@ -1241,12 +1305,12 @@ static int coroutine_fn ssh_co_truncate(BlockDriverState *bs, int64_t offset,
         return -ENOTSUP;
     }
 
-    if (offset < s->attrs.filesize) {
+    if (offset < s->attrs->size) {
         error_setg(errp, "ssh driver does not support shrinking files");
         return -ENOTSUP;
     }
 
-    if (offset == s->attrs.filesize) {
+    if (offset == s->attrs->size) {
         return 0;
     }
 
@@ -1341,12 +1405,16 @@ static void bdrv_ssh_init(void)
 {
     int r;
 
-    r = libssh2_init(0);
+    r = ssh_init();
     if (r != 0) {
-        fprintf(stderr, "libssh2 initialization failed, %d\n", r);
+        fprintf(stderr, "libssh initialization failed, %d\n", r);
         exit(EXIT_FAILURE);
     }
 
+#if TRACE_LIBSSH != 0
+    ssh_set_log_level(TRACE_LIBSSH);
+#endif
+
     bdrv_register(&bdrv_ssh);
 }
 
diff --git a/block/trace-events b/block/trace-events
index 9ccea755da..d724df0117 100644
--- a/block/trace-events
+++ b/block/trace-events
@@ -171,19 +171,21 @@ nbd_client_connect_success(const char *export_name) "export '%s'"
 # ssh.c
 ssh_restart_coroutine(void *co) "co=%p"
 ssh_flush(void) "fsync"
-ssh_check_host_key_knownhosts(const char *key) "host key OK: %s"
+ssh_check_host_key_knownhosts(void) "host key OK"
 ssh_connect_to_ssh(char *path, int flags, int mode) "opening file %s flags=0x%x creat_mode=0%o"
 ssh_co_yield(int sock, void *rd_handler, void *wr_handler) "s->sock=%d rd_handler=%p wr_handler=%p"
 ssh_co_yield_back(int sock) "s->sock=%d - back"
 ssh_getlength(int64_t length) "length=%" PRIi64
 ssh_co_create_opts(uint64_t size) "total_size=%" PRIu64
 ssh_read(int64_t offset, size_t size) "offset=%" PRIi64 " size=%zu"
-ssh_read_buf(void *buf, size_t size) "sftp_read buf=%p size=%zu"
-ssh_read_return(ssize_t ret) "sftp_read returned %zd"
+ssh_read_buf(void *buf, size_t size, size_t actual_size) "sftp_read buf=%p size=%zu (actual size=%zu)"
+ssh_read_return(ssize_t ret, int sftp_err) "sftp_read returned %zd (sftp error=%d)"
 ssh_write(int64_t offset, size_t size) "offset=%" PRIi64 " size=%zu"
-ssh_write_buf(void *buf, size_t size) "sftp_write buf=%p size=%zu"
-ssh_write_return(ssize_t ret) "sftp_write returned %zd"
+ssh_write_buf(void *buf, size_t size, size_t actual_size) "sftp_write buf=%p size=%zu (actual size=%zu)"
+ssh_write_return(ssize_t ret, int sftp_err) "sftp_write returned %zd (sftp error=%d)"
 ssh_seek(int64_t offset) "seeking to offset=%" PRIi64
+ssh_auth_methods(int methods) "auth methods=0x%x"
+ssh_server_status(int status) "server status=%d"
 
 # curl.c
 curl_timer_cb(long timeout_ms) "timer callback timeout_ms %ld"
@@ -216,4 +218,4 @@ sheepdog_snapshot_create(const char *sn_name, const char *id) "%s %s"
 sheepdog_snapshot_create_inode(const char *name, uint32_t snap, uint32_t vdi) "s->inode: name %s snap_id 0x%" PRIx32 " vdi 0x%" PRIx32
 
 # ssh.c
-sftp_error(const char *op, const char *ssh_err, int ssh_err_code, unsigned long sftp_err_code) "%s failed: %s (libssh2 error code: %d, sftp error code: %lu)"
+sftp_error(const char *op, const char *ssh_err, int ssh_err_code, int sftp_err_code) "%s failed: %s (libssh error code: %d, sftp error code: %d)"
diff --git a/block/vmdk.c b/block/vmdk.c
index 51067c774f..bd36ece125 100644
--- a/block/vmdk.c
+++ b/block/vmdk.c
@@ -91,6 +91,44 @@ typedef struct {
     uint16_t compressAlgorithm;
 } QEMU_PACKED VMDK4Header;
 
+typedef struct VMDKSESparseConstHeader {
+    uint64_t magic;
+    uint64_t version;
+    uint64_t capacity;
+    uint64_t grain_size;
+    uint64_t grain_table_size;
+    uint64_t flags;
+    uint64_t reserved1;
+    uint64_t reserved2;
+    uint64_t reserved3;
+    uint64_t reserved4;
+    uint64_t volatile_header_offset;
+    uint64_t volatile_header_size;
+    uint64_t journal_header_offset;
+    uint64_t journal_header_size;
+    uint64_t journal_offset;
+    uint64_t journal_size;
+    uint64_t grain_dir_offset;
+    uint64_t grain_dir_size;
+    uint64_t grain_tables_offset;
+    uint64_t grain_tables_size;
+    uint64_t free_bitmap_offset;
+    uint64_t free_bitmap_size;
+    uint64_t backmap_offset;
+    uint64_t backmap_size;
+    uint64_t grains_offset;
+    uint64_t grains_size;
+    uint8_t pad[304];
+} QEMU_PACKED VMDKSESparseConstHeader;
+
+typedef struct VMDKSESparseVolatileHeader {
+    uint64_t magic;
+    uint64_t free_gt_number;
+    uint64_t next_txn_seq_number;
+    uint64_t replay_journal;
+    uint8_t pad[480];
+} QEMU_PACKED VMDKSESparseVolatileHeader;
+
 #define L2_CACHE_SIZE 16
 
 typedef struct VmdkExtent {
@@ -99,19 +137,23 @@ typedef struct VmdkExtent {
     bool compressed;
     bool has_marker;
     bool has_zero_grain;
+    bool sesparse;
+    uint64_t sesparse_l2_tables_offset;
+    uint64_t sesparse_clusters_offset;
+    int32_t entry_size;
     int version;
     int64_t sectors;
     int64_t end_sector;
     int64_t flat_start_offset;
     int64_t l1_table_offset;
     int64_t l1_backup_table_offset;
-    uint32_t *l1_table;
+    void *l1_table;
     uint32_t *l1_backup_table;
     unsigned int l1_size;
     uint32_t l1_entry_sectors;
 
     unsigned int l2_size;
-    uint32_t *l2_cache;
+    void *l2_cache;
     uint32_t l2_cache_offsets[L2_CACHE_SIZE];
     uint32_t l2_cache_counts[L2_CACHE_SIZE];
 
@@ -425,11 +467,22 @@ static int vmdk_add_extent(BlockDriverState *bs,
         error_setg(errp, "Invalid granularity, image may be corrupt");
         return -EFBIG;
     }
-    if (l1_size > 512 * 1024 * 1024) {
-        /* Although with big capacity and small l1_entry_sectors, we can get a
+    if (l1_size > 32 * 1024 * 1024) {
+        /*
+         * Although with big capacity and small l1_entry_sectors, we can get a
          * big l1_size, we don't want unbounded value to allocate the table.
-         * Limit it to 512M, which is 16PB for default cluster and L2 table
-         * size */
+         * Limit it to 32M, which is enough to store:
+         *     8TB  - for both VMDK3 & VMDK4 with
+         *            minimal cluster size: 512B
+         *            minimal L2 table size: 512 entries
+         *            8 TB is still more than the maximal value supported for
+         *            VMDK3 & VMDK4 which is 2TB.
+         *     64TB - for "ESXi seSparse Extent"
+         *            minimal cluster size: 512B (default is 4KB)
+         *            L2 table size: 4096 entries (const).
+         *            64TB is more than the maximal value supported for
+         *            seSparse VMDKs (which is slightly less than 64TB)
+         */
         error_setg(errp, "L1 size too big");
         return -EFBIG;
     }
@@ -454,6 +507,7 @@ static int vmdk_add_extent(BlockDriverState *bs,
     extent->l2_size = l2_size;
     extent->cluster_sectors = flat ? sectors : cluster_sectors;
     extent->next_cluster_sector = ROUND_UP(nb_sectors, cluster_sectors);
+    extent->entry_size = sizeof(uint32_t);
 
     if (s->num_extents > 1) {
         extent->end_sector = (*(extent - 1)).end_sector + extent->sectors;
@@ -475,7 +529,7 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
     int i;
 
     /* read the L1 table */
-    l1_size = extent->l1_size * sizeof(uint32_t);
+    l1_size = extent->l1_size * extent->entry_size;
     extent->l1_table = g_try_malloc(l1_size);
     if (l1_size && extent->l1_table == NULL) {
         return -ENOMEM;
@@ -493,10 +547,16 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
         goto fail_l1;
     }
     for (i = 0; i < extent->l1_size; i++) {
-        le32_to_cpus(&extent->l1_table[i]);
+        if (extent->entry_size == sizeof(uint64_t)) {
+            le64_to_cpus((uint64_t *)extent->l1_table + i);
+        } else {
+            assert(extent->entry_size == sizeof(uint32_t));
+            le32_to_cpus((uint32_t *)extent->l1_table + i);
+        }
     }
 
     if (extent->l1_backup_table_offset) {
+        assert(!extent->sesparse);
         extent->l1_backup_table = g_try_malloc(l1_size);
         if (l1_size && extent->l1_backup_table == NULL) {
             ret = -ENOMEM;
@@ -519,7 +579,7 @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
     }
 
     extent->l2_cache =
-        g_new(uint32_t, extent->l2_size * L2_CACHE_SIZE);
+        g_malloc(extent->entry_size * extent->l2_size * L2_CACHE_SIZE);
     return 0;
  fail_l1b:
     g_free(extent->l1_backup_table);
@@ -565,6 +625,205 @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs,
     return ret;
 }
 
+#define SESPARSE_CONST_HEADER_MAGIC UINT64_C(0x00000000cafebabe)
+#define SESPARSE_VOLATILE_HEADER_MAGIC UINT64_C(0x00000000cafecafe)
+
+/* Strict checks - format not officially documented */
+static int check_se_sparse_const_header(VMDKSESparseConstHeader *header,
+                                        Error **errp)
+{
+    header->magic = le64_to_cpu(header->magic);
+    header->version = le64_to_cpu(header->version);
+    header->grain_size = le64_to_cpu(header->grain_size);
+    header->grain_table_size = le64_to_cpu(header->grain_table_size);
+    header->flags = le64_to_cpu(header->flags);
+    header->reserved1 = le64_to_cpu(header->reserved1);
+    header->reserved2 = le64_to_cpu(header->reserved2);
+    header->reserved3 = le64_to_cpu(header->reserved3);
+    header->reserved4 = le64_to_cpu(header->reserved4);
+
+    header->volatile_header_offset =
+        le64_to_cpu(header->volatile_header_offset);
+    header->volatile_header_size = le64_to_cpu(header->volatile_header_size);
+
+    header->journal_header_offset = le64_to_cpu(header->journal_header_offset);
+    header->journal_header_size = le64_to_cpu(header->journal_header_size);
+
+    header->journal_offset = le64_to_cpu(header->journal_offset);
+    header->journal_size = le64_to_cpu(header->journal_size);
+
+    header->grain_dir_offset = le64_to_cpu(header->grain_dir_offset);
+    header->grain_dir_size = le64_to_cpu(header->grain_dir_size);
+
+    header->grain_tables_offset = le64_to_cpu(header->grain_tables_offset);
+    header->grain_tables_size = le64_to_cpu(header->grain_tables_size);
+
+    header->free_bitmap_offset = le64_to_cpu(header->free_bitmap_offset);
+    header->free_bitmap_size = le64_to_cpu(header->free_bitmap_size);
+
+    header->backmap_offset = le64_to_cpu(header->backmap_offset);
+    header->backmap_size = le64_to_cpu(header->backmap_size);
+
+    header->grains_offset = le64_to_cpu(header->grains_offset);
+    header->grains_size = le64_to_cpu(header->grains_size);
+
+    if (header->magic != SESPARSE_CONST_HEADER_MAGIC) {
+        error_setg(errp, "Bad const header magic: 0x%016" PRIx64,
+                   header->magic);
+        return -EINVAL;
+    }
+
+    if (header->version != 0x0000000200000001) {
+        error_setg(errp, "Unsupported version: 0x%016" PRIx64,
+                   header->version);
+        return -ENOTSUP;
+    }
+
+    if (header->grain_size != 8) {
+        error_setg(errp, "Unsupported grain size: %" PRIu64,
+                   header->grain_size);
+        return -ENOTSUP;
+    }
+
+    if (header->grain_table_size != 64) {
+        error_setg(errp, "Unsupported grain table size: %" PRIu64,
+                   header->grain_table_size);
+        return -ENOTSUP;
+    }
+
+    if (header->flags != 0) {
+        error_setg(errp, "Unsupported flags: 0x%016" PRIx64,
+                   header->flags);
+        return -ENOTSUP;
+    }
+
+    if (header->reserved1 != 0 || header->reserved2 != 0 ||
+        header->reserved3 != 0 || header->reserved4 != 0) {
+        error_setg(errp, "Unsupported reserved bits:"
+                   " 0x%016" PRIx64 " 0x%016" PRIx64
+                   " 0x%016" PRIx64 " 0x%016" PRIx64,
+                   header->reserved1, header->reserved2,
+                   header->reserved3, header->reserved4);
+        return -ENOTSUP;
+    }
+
+    /* check that padding is 0 */
+    if (!buffer_is_zero(header->pad, sizeof(header->pad))) {
+        error_setg(errp, "Unsupported non-zero const header padding");
+        return -ENOTSUP;
+    }
+
+    return 0;
+}
+
+static int check_se_sparse_volatile_header(VMDKSESparseVolatileHeader *header,
+                                           Error **errp)
+{
+    header->magic = le64_to_cpu(header->magic);
+    header->free_gt_number = le64_to_cpu(header->free_gt_number);
+    header->next_txn_seq_number = le64_to_cpu(header->next_txn_seq_number);
+    header->replay_journal = le64_to_cpu(header->replay_journal);
+
+    if (header->magic != SESPARSE_VOLATILE_HEADER_MAGIC) {
+        error_setg(errp, "Bad volatile header magic: 0x%016" PRIx64,
+                   header->magic);
+        return -EINVAL;
+    }
+
+    if (header->replay_journal) {
+        error_setg(errp, "Image is dirty, Replaying journal not supported");
+        return -ENOTSUP;
+    }
+
+    /* check that padding is 0 */
+    if (!buffer_is_zero(header->pad, sizeof(header->pad))) {
+        error_setg(errp, "Unsupported non-zero volatile header padding");
+        return -ENOTSUP;
+    }
+
+    return 0;
+}
+
+static int vmdk_open_se_sparse(BlockDriverState *bs,
+                               BdrvChild *file,
+                               int flags, Error **errp)
+{
+    int ret;
+    VMDKSESparseConstHeader const_header;
+    VMDKSESparseVolatileHeader volatile_header;
+    VmdkExtent *extent;
+
+    ret = bdrv_apply_auto_read_only(bs,
+            "No write support for seSparse images available", errp);
+    if (ret < 0) {
+        return ret;
+    }
+
+    assert(sizeof(const_header) == SECTOR_SIZE);
+
+    ret = bdrv_pread(file, 0, &const_header, sizeof(const_header));
+    if (ret < 0) {
+        bdrv_refresh_filename(file->bs);
+        error_setg_errno(errp, -ret,
+                         "Could not read const header from file '%s'",
+                         file->bs->filename);
+        return ret;
+    }
+
+    /* check const header */
+    ret = check_se_sparse_const_header(&const_header, errp);
+    if (ret < 0) {
+        return ret;
+    }
+
+    assert(sizeof(volatile_header) == SECTOR_SIZE);
+
+    ret = bdrv_pread(file,
+                     const_header.volatile_header_offset * SECTOR_SIZE,
+                     &volatile_header, sizeof(volatile_header));
+    if (ret < 0) {
+        bdrv_refresh_filename(file->bs);
+        error_setg_errno(errp, -ret,
+                         "Could not read volatile header from file '%s'",
+                         file->bs->filename);
+        return ret;
+    }
+
+    /* check volatile header */
+    ret = check_se_sparse_volatile_header(&volatile_header, errp);
+    if (ret < 0) {
+        return ret;
+    }
+
+    ret = vmdk_add_extent(bs, file, false,
+                          const_header.capacity,
+                          const_header.grain_dir_offset * SECTOR_SIZE,
+                          0,
+                          const_header.grain_dir_size *
+                          SECTOR_SIZE / sizeof(uint64_t),
+                          const_header.grain_table_size *
+                          SECTOR_SIZE / sizeof(uint64_t),
+                          const_header.grain_size,
+                          &extent,
+                          errp);
+    if (ret < 0) {
+        return ret;
+    }
+
+    extent->sesparse = true;
+    extent->sesparse_l2_tables_offset = const_header.grain_tables_offset;
+    extent->sesparse_clusters_offset = const_header.grains_offset;
+    extent->entry_size = sizeof(uint64_t);
+
+    ret = vmdk_init_tables(bs, extent, errp);
+    if (ret) {
+        /* free extent allocated by vmdk_add_extent */
+        vmdk_free_last_extent(bs);
+    }
+
+    return ret;
+}
+
 static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
                                QDict *options, Error **errp);
 
@@ -842,6 +1101,7 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
          * RW [size in sectors] SPARSE "file-name.vmdk"
          * RW [size in sectors] VMFS "file-name.vmdk"
          * RW [size in sectors] VMFSSPARSE "file-name.vmdk"
+         * RW [size in sectors] SESPARSE "file-name.vmdk"
          */
         flat_offset = -1;
         matches = sscanf(p, "%10s %" SCNd64 " %10s \"%511[^\n\r\"]\" %" SCNd64,
@@ -864,7 +1124,8 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
 
         if (sectors <= 0 ||
             (strcmp(type, "FLAT") && strcmp(type, "SPARSE") &&
-             strcmp(type, "VMFS") && strcmp(type, "VMFSSPARSE")) ||
+             strcmp(type, "VMFS") && strcmp(type, "VMFSSPARSE") &&
+             strcmp(type, "SESPARSE")) ||
             (strcmp(access, "RW"))) {
             continue;
         }
@@ -917,6 +1178,13 @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
                 return ret;
             }
             extent = &s->extents[s->num_extents - 1];
+        } else if (!strcmp(type, "SESPARSE")) {
+            ret = vmdk_open_se_sparse(bs, extent_file, bs->open_flags, errp);
+            if (ret) {
+                bdrv_unref_child(bs, extent_file);
+                return ret;
+            }
+            extent = &s->extents[s->num_extents - 1];
         } else {
             error_setg(errp, "Unsupported extent type '%s'", type);
             bdrv_unref_child(bs, extent_file);
@@ -951,6 +1219,7 @@ static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
     if (strcmp(ct, "monolithicFlat") &&
         strcmp(ct, "vmfs") &&
         strcmp(ct, "vmfsSparse") &&
+        strcmp(ct, "seSparse") &&
         strcmp(ct, "twoGbMaxExtentSparse") &&
         strcmp(ct, "twoGbMaxExtentFlat")) {
         error_setg(errp, "Unsupported image type '%s'", ct);
@@ -1201,10 +1470,12 @@ static int get_cluster_offset(BlockDriverState *bs,
 {
     unsigned int l1_index, l2_offset, l2_index;
     int min_index, i, j;
-    uint32_t min_count, *l2_table;
+    uint32_t min_count;
+    void *l2_table;
     bool zeroed = false;
     int64_t ret;
     int64_t cluster_sector;
+    unsigned int l2_size_bytes = extent->l2_size * extent->entry_size;
 
     if (m_data) {
         m_data->valid = 0;
@@ -1219,7 +1490,36 @@ static int get_cluster_offset(BlockDriverState *bs,
     if (l1_index >= extent->l1_size) {
         return VMDK_ERROR;
     }
-    l2_offset = extent->l1_table[l1_index];
+    if (extent->sesparse) {
+        uint64_t l2_offset_u64;
+
+        assert(extent->entry_size == sizeof(uint64_t));
+
+        l2_offset_u64 = ((uint64_t *)extent->l1_table)[l1_index];
+        if (l2_offset_u64 == 0) {
+            l2_offset = 0;
+        } else if ((l2_offset_u64 & 0xffffffff00000000) != 0x1000000000000000) {
+            /*
+             * Top most nibble is 0x1 if grain table is allocated.
+             * strict check - top most 4 bytes must be 0x10000000 since max
+             * supported size is 64TB for disk - so no more than 64TB / 16MB
+             * grain directories which is smaller than uint32,
+             * where 16MB is the only supported default grain table coverage.
+             */
+            return VMDK_ERROR;
+        } else {
+            l2_offset_u64 = l2_offset_u64 & 0x00000000ffffffff;
+            l2_offset_u64 = extent->sesparse_l2_tables_offset +
+                l2_offset_u64 * l2_size_bytes / SECTOR_SIZE;
+            if (l2_offset_u64 > 0x00000000ffffffff) {
+                return VMDK_ERROR;
+            }
+            l2_offset = (unsigned int)(l2_offset_u64);
+        }
+    } else {
+        assert(extent->entry_size == sizeof(uint32_t));
+        l2_offset = ((uint32_t *)extent->l1_table)[l1_index];
+    }
     if (!l2_offset) {
         return VMDK_UNALLOC;
     }
@@ -1231,7 +1531,7 @@ static int get_cluster_offset(BlockDriverState *bs,
                     extent->l2_cache_counts[j] >>= 1;
                 }
             }
-            l2_table = extent->l2_cache + (i * extent->l2_size);
+            l2_table = (char *)extent->l2_cache + (i * l2_size_bytes);
             goto found;
         }
     }
@@ -1244,13 +1544,13 @@ static int get_cluster_offset(BlockDriverState *bs,
             min_index = i;
         }
     }
-    l2_table = extent->l2_cache + (min_index * extent->l2_size);
+    l2_table = (char *)extent->l2_cache + (min_index * l2_size_bytes);
     BLKDBG_EVENT(extent->file, BLKDBG_L2_LOAD);
     if (bdrv_pread(extent->file,
                 (int64_t)l2_offset * 512,
                 l2_table,
-                extent->l2_size * sizeof(uint32_t)
-            ) != extent->l2_size * sizeof(uint32_t)) {
+                l2_size_bytes
+            ) != l2_size_bytes) {
         return VMDK_ERROR;
     }
 
@@ -1258,16 +1558,45 @@ static int get_cluster_offset(BlockDriverState *bs,
     extent->l2_cache_counts[min_index] = 1;
  found:
     l2_index = ((offset >> 9) / extent->cluster_sectors) % extent->l2_size;
-    cluster_sector = le32_to_cpu(l2_table[l2_index]);
 
-    if (extent->has_zero_grain && cluster_sector == VMDK_GTE_ZEROED) {
-        zeroed = true;
+    if (extent->sesparse) {
+        cluster_sector = le64_to_cpu(((uint64_t *)l2_table)[l2_index]);
+        switch (cluster_sector & 0xf000000000000000) {
+        case 0x0000000000000000:
+            /* unallocated grain */
+            if (cluster_sector != 0) {
+                return VMDK_ERROR;
+            }
+            break;
+        case 0x1000000000000000:
+            /* scsi-unmapped grain - fallthrough */
+        case 0x2000000000000000:
+            /* zero grain */
+            zeroed = true;
+            break;
+        case 0x3000000000000000:
+            /* allocated grain */
+            cluster_sector = (((cluster_sector & 0x0fff000000000000) >> 48) |
+                              ((cluster_sector & 0x0000ffffffffffff) << 12));
+            cluster_sector = extent->sesparse_clusters_offset +
+                cluster_sector * extent->cluster_sectors;
+            break;
+        default:
+            return VMDK_ERROR;
+        }
+    } else {
+        cluster_sector = le32_to_cpu(((uint32_t *)l2_table)[l2_index]);
+
+        if (extent->has_zero_grain && cluster_sector == VMDK_GTE_ZEROED) {
+            zeroed = true;
+        }
     }
 
     if (!cluster_sector || zeroed) {
         if (!allocate) {
             return zeroed ? VMDK_ZEROED : VMDK_UNALLOC;
         }
+        assert(!extent->sesparse);
 
         if (extent->next_cluster_sector >= VMDK_EXTENT_MAX_SECTORS) {
             return VMDK_ERROR;
@@ -1291,7 +1620,7 @@ static int get_cluster_offset(BlockDriverState *bs,
             m_data->l1_index = l1_index;
             m_data->l2_index = l2_index;
             m_data->l2_offset = l2_offset;
-            m_data->l2_cache_entry = &l2_table[l2_index];
+            m_data->l2_cache_entry = ((uint32_t *)l2_table) + l2_index;
         }
     }
     *cluster_offset = cluster_sector << BDRV_SECTOR_BITS;
@@ -1617,6 +1946,9 @@ static int vmdk_pwritev(BlockDriverState *bs, uint64_t offset,
         if (!extent) {
             return -EIO;
         }
+        if (extent->sesparse) {
+            return -ENOTSUP;
+        }
         offset_in_cluster = vmdk_find_offset_in_cluster(extent, offset);
         n_bytes = MIN(bytes, extent->cluster_sectors * BDRV_SECTOR_SIZE
                              - offset_in_cluster);