Series comparison

-[PULL for-5.0 0/3] Block patches
+[Qemu-devel] [PULL v2 00/12] Block patches
-The following changes since commit 8bac3ba57eecc466b7e73dabf7d19328a59f684e:
+The following changes since commit 4c55b1d0bad8a703f0499fe62e3761a0cd288da3:
-  Merge remote-tracking branch 'remotes/rth/tags/pull-rx-20200408' into staging (2020-04-09 13:23:30 +0100)
+  Merge remote-tracking branch 'remotes/armbru/tags/pull-error-2017-04-24' into staging (2017-04-24 14:49:48 +0100)
-are available in the Git repository at:
+are available in the git repository at:
-  https://github.com/stefanha/qemu.git tags/block-pull-request
+  git://github.com/codyprime/qemu-kvm-jtc.git tags/block-pull-request
-for you to fetch changes up to 5710a3e09f9b85801e5ce70797a4a511e5fc9e2c:
+for you to fetch changes up to ecfa185400ade2abc9915efa924cbad1e15a21a4:
-  async: use explicit memory barriers (2020-04-09 16:17:14 +0100)
+  qemu-iotests: _cleanup_qemu must be called on exit (2017-04-24 15:09:33 -0400)
 ----------------------------------------------------------------
-Pull request
+Pull v2, with 32-bit errors fixed.  I don't have OS X to test compile on,
+but I think it is safe to assume the cause of the compile error was the same.
 Fixes for QEMU on aarch64 ARM hosts and fdmon-io_uring.
 ----------------------------------------------------------------
-Paolo Bonzini (2):
+Ashish Mittal (2):
-  aio-wait: delegate polling of main AioContext if BQL not held
+  block/vxhs.c: Add support for a new block device type called "vxhs"
-  async: use explicit memory barriers
+  block/vxhs.c: Add qemu-iotests for new block device type "vxhs"
-Stefan Hajnoczi (1):
+Jeff Cody (10):
-  aio-posix: signal-proof fdmon-io_uring
+  qemu-iotests: exclude vxhs from image creation via protocol
   block: add bdrv_set_read_only() helper function
   block: do not set BDS read_only if copy_on_read enabled
   block: honor BDRV_O_ALLOW_RDWR when clearing bs->read_only
   block: code movement
   block: introduce bdrv_can_set_read_only()
   block: use bdrv_can_set_read_only() during reopen
   block/rbd - update variable names to more apt names
   block/rbd: Add support for reopen()
   qemu-iotests: _cleanup_qemu must be called on exit
- include/block/aio-wait.h | 22 ++++++++++++++++++++++
+ block.c                          |  56 +++-
- include/block/aio.h      | 29 ++++++++++-------------------
+ block/Makefile.objs              |   2 +
- util/aio-posix.c         | 16 ++++++++++++++--
+ block/bochs.c                    |   5 +-
- util/aio-win32.c         | 17 ++++++++++++++---
+ block/cloop.c                    |   5 +-
- util/async.c             | 16 ++++++++++++----
+ block/dmg.c                      |   6 +-
- util/fdmon-io_uring.c    | 10 ++++++++--
+ block/rbd.c                      |  65 +++--
-files changed, 80 insertions(+), 30 deletions(-)
+ block/trace-events               |  17 ++
  block/vvfat.c                    |  19 +-
  block/vxhs.c                     | 575 +++++++++++++++++++++++++++++++++++++++
  configure                        |  39 +++
  include/block/block.h            |   2 +
  qapi/block-core.json             |  23 +-
  tests/qemu-iotests/017           |   1 +
  tests/qemu-iotests/020           |   1 +
  tests/qemu-iotests/028           |   1 +
  tests/qemu-iotests/029           |   1 +
  tests/qemu-iotests/073           |   1 +
  tests/qemu-iotests/094           |  11 +-
  tests/qemu-iotests/102           |   5 +-
  tests/qemu-iotests/109           |   1 +
  tests/qemu-iotests/114           |   1 +
  tests/qemu-iotests/117           |   1 +
  tests/qemu-iotests/130           |   2 +
  tests/qemu-iotests/134           |   1 +
  tests/qemu-iotests/140           |   1 +
  tests/qemu-iotests/141           |   1 +
  tests/qemu-iotests/143           |   1 +
  tests/qemu-iotests/156           |   2 +
  tests/qemu-iotests/158           |   1 +
  tests/qemu-iotests/common        |   6 +
  tests/qemu-iotests/common.config |  13 +
  tests/qemu-iotests/common.filter |   1 +
  tests/qemu-iotests/common.rc     |  19 ++
 files changed, 844 insertions(+), 42 deletions(-)
  create mode 100644 block/vxhs.c
 --
-.25.1
+.9.3

-New patch
+[Qemu-devel] [PULL v2 01/12] block/vxhs.c: Add support for a new block device type called "vxhs"
+From: Ashish Mittal <ashmit602@gmail.com>
+Source code for the qnio library that this code loads can be downloaded from:
+https://github.com/VeritasHyperScale/libqnio.git
+Sample command line using JSON syntax:
+./x86_64-softmmu/qemu-system-x86_64 -name instance-00000008 -S -vnc 0.0.0.0:0
+-k en-us -vga cirrus -device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x5
+-msg timestamp=on
+'json:{"driver":"vxhs","vdisk-id":"c3e9095a-a5ee-4dce-afeb-2a59fb387410",
+"server":{"host":"172.172.17.4","port":"9999"}}'
+Sample command line using URI syntax:
+qemu-img convert -f raw -O raw -n
+/var/lib/nova/instances/_base/0c5eacd5ebea5ed914b6a3e7b18f1ce734c386ad
+vxhs://192.168.0.1:9999/c6718f6b-0401-441d-a8c3-1f0064d75ee0
+Sample command line using TLS credentials (run in secure mode):
+./qemu-io --object
+tls-creds-x509,id=tls0,dir=/etc/pki/qemu/vxhs,endpoint=client -c 'read
+-v 66000 2.5k' 'json:{"server.host": "127.0.0.1", "server.port": "9999",
+"vdisk-id": "/test.raw", "driver": "vxhs", "tls-creds":"tls0"}'
+[Jeff: Modified trace-events with the correct string formatting]
+Signed-off-by: Ashish Mittal <Ashish.Mittal@veritas.com>
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+Reviewed-by: Jeff Cody <jcody@redhat.com>
+Signed-off-by: Jeff Cody <jcody@redhat.com>
+Message-id: 1491277689-24949-2-git-send-email-Ashish.Mittal@veritas.com
+---
+ block/Makefile.objs  |   2 +
+ block/trace-events   |  17 ++
+ block/vxhs.c         | 575 +++++++++++++++++++++++++++++++++++++++++++++++++++
+ configure            |  39 ++++
+ qapi/block-core.json |  23 ++-
+files changed, 654 insertions(+), 2 deletions(-)
+ create mode 100644 block/vxhs.c
+diff --git a/block/Makefile.objs b/block/Makefile.objs
+index XXXXXXX..XXXXXXX 100644
+--- a/block/Makefile.objs
++++ b/block/Makefile.objs
+@@ -XXX,XX +XXX,XX @@ block-obj-$(CONFIG_LIBNFS) += nfs.o
+ block-obj-$(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-y += accounting.o dirty-bitmap.o
+ block-obj-y += write-threshold.o
+@@ -XXX,XX +XXX,XX @@ rbd.o-cflags       := $(RBD_CFLAGS)
+ 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         := $(LIBSSH2_LIBS)
+ block-obj-$(if $(CONFIG_BZIP2),m,n) += dmg-bz2.o
+diff --git a/block/trace-events b/block/trace-events
+index XXXXXXX..XXXXXXX 100644
+--- a/block/trace-events
++++ b/block/trace-events
+@@ -XXX,XX +XXX,XX @@ qed_aio_write_data(void *s, void *acb, int ret, uint64_t offset, size_t len) "s
+ qed_aio_write_prefill(void *s, void *acb, uint64_t start, size_t len, uint64_t offset) "s %p acb %p start %"PRIu64" len %zu offset %"PRIu64
+ qed_aio_write_postfill(void *s, void *acb, uint64_t start, size_t len, uint64_t offset) "s %p acb %p start %"PRIu64" len %zu offset %"PRIu64
+ qed_aio_write_main(void *s, void *acb, int ret, uint64_t offset, size_t len) "s %p acb %p ret %d offset %"PRIu64" len %zu"
++
++# block/vxhs.c
++vxhs_iio_callback(int error) "ctx is NULL: error %d"
++vxhs_iio_callback_chnfail(int err, int error) "QNIO channel failed, no i/o %d, %d"
++vxhs_iio_callback_unknwn(int opcode, int err) "unexpected opcode %d, errno %d"
++vxhs_aio_rw_invalid(int req) "Invalid I/O request iodir %d"
++vxhs_aio_rw_ioerr(char *guid, int iodir, uint64_t size, uint64_t off, void *acb, int ret, int err) "IO ERROR (vDisk %s) FOR : Read/Write = %d size = %"PRIu64" offset = %"PRIu64" ACB = %p. Error = %d, errno = %d"
++vxhs_get_vdisk_stat_err(char *guid, int ret, int err) "vDisk (%s) stat ioctl failed, ret = %d, errno = %d"
++vxhs_get_vdisk_stat(char *vdisk_guid, uint64_t vdisk_size) "vDisk %s stat ioctl returned size %"PRIu64
++vxhs_complete_aio(void *acb, uint64_t ret) "aio failed acb %p ret %"PRIu64
++vxhs_parse_uri_filename(const char *filename) "URI passed via bdrv_parse_filename %s"
++vxhs_open_vdiskid(const char *vdisk_id) "Opening vdisk-id %s"
++vxhs_open_hostinfo(char *of_vsa_addr, int port) "Adding host %s:%d to BDRVVXHSState"
++vxhs_open_iio_open(const char *host) "Failed to connect to storage agent on host %s"
++vxhs_parse_uri_hostinfo(char *host, int port) "Host: IP %s, Port %d"
++vxhs_close(char *vdisk_guid) "Closing vdisk %s"
++vxhs_get_creds(const char *cacert, const char *client_key, const char *client_cert) "cacert %s, client_key %s, client_cert %s"
+diff --git a/block/vxhs.c b/block/vxhs.c
+new file mode 100644
+index XXXXXXX..XXXXXXX
+--- /dev/null
++++ b/block/vxhs.c
+@@ -XXX,XX +XXX,XX @@
++/*
++ * QEMU Block driver for Veritas HyperScale (VxHS)
++ *
++ * Copyright (c) 2017 Veritas Technologies LLC.
++ *
++ * This work is licensed under the terms of the GNU GPL, version 2 or later.
++ * See the COPYING file in the top-level directory.
++ *
++ */
++
++#include "qemu/osdep.h"
++#include <qnio/qnio_api.h>
++#include <sys/param.h>
++#include "block/block_int.h"
++#include "qapi/qmp/qerror.h"
++#include "qapi/qmp/qdict.h"
++#include "qapi/qmp/qstring.h"
++#include "trace.h"
++#include "qemu/uri.h"
++#include "qapi/error.h"
++#include "qemu/uuid.h"
++#include "crypto/tlscredsx509.h"
++
++#define VXHS_OPT_FILENAME           "filename"
++#define VXHS_OPT_VDISK_ID           "vdisk-id"
++#define VXHS_OPT_SERVER             "server"
++#define VXHS_OPT_HOST               "host"
++#define VXHS_OPT_PORT               "port"
++
++/* Only accessed under QEMU global mutex */
++static uint32_t vxhs_ref;
++
++typedef enum {
++    VDISK_AIO_READ,
++    VDISK_AIO_WRITE,
++} VDISKAIOCmd;
++
++/*
++ * HyperScale AIO callbacks structure
++ */
++typedef struct VXHSAIOCB {
++    BlockAIOCB common;
++    int err;
++} VXHSAIOCB;
++
++typedef struct VXHSvDiskHostsInfo {
++    void *dev_handle; /* Device handle */
++    char *host; /* Host name or IP */
++    int port; /* Host's port number */
++} VXHSvDiskHostsInfo;
++
++/*
++ * Structure per vDisk maintained for state
++ */
++typedef struct BDRVVXHSState {
++    VXHSvDiskHostsInfo vdisk_hostinfo; /* Per host info */
++    char *vdisk_guid;
++    char *tlscredsid; /* tlscredsid */
++} BDRVVXHSState;
++
++static void vxhs_complete_aio_bh(void *opaque)
++{
++    VXHSAIOCB *acb = opaque;
++    BlockCompletionFunc *cb = acb->common.cb;
++    void *cb_opaque = acb->common.opaque;
++    int ret = 0;
++
++    if (acb->err != 0) {
++        trace_vxhs_complete_aio(acb, acb->err);
++        ret = (-EIO);
++    }
++
++    qemu_aio_unref(acb);
++    cb(cb_opaque, ret);
++}
++
++/*
++ * Called from a libqnio thread
++ */
++static void vxhs_iio_callback(void *ctx, uint32_t opcode, uint32_t error)
++{
++    VXHSAIOCB *acb = NULL;
++
++    switch (opcode) {
++    case IRP_READ_REQUEST:
++    case IRP_WRITE_REQUEST:
++
++        /*
++         * ctx is VXHSAIOCB*
++         * ctx is NULL if error is QNIOERROR_CHANNEL_HUP
++         */
++        if (ctx) {
++            acb = ctx;
++        } else {
++            trace_vxhs_iio_callback(error);
++            goto out;
++        }
++
++        if (error) {
++            if (!acb->err) {
++                acb->err = error;
++            }
++            trace_vxhs_iio_callback(error);
++        }
++
++        aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs),
++                                vxhs_complete_aio_bh, acb);
++        break;
++
++    default:
++        if (error == QNIOERROR_HUP) {
++            /*
++             * Channel failed, spontaneous notification,
++             * not in response to I/O
++             */
++            trace_vxhs_iio_callback_chnfail(error, errno);
++        } else {
++            trace_vxhs_iio_callback_unknwn(opcode, error);
++        }
++        break;
++    }
++out:
++    return;
++}
++
++static QemuOptsList runtime_opts = {
++    .name = "vxhs",
++    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
++    .desc = {
++        {
++            .name = VXHS_OPT_FILENAME,
++            .type = QEMU_OPT_STRING,
++            .help = "URI to the Veritas HyperScale image",
++        },
++        {
++            .name = VXHS_OPT_VDISK_ID,
++            .type = QEMU_OPT_STRING,
++            .help = "UUID of the VxHS vdisk",
++        },
++        {
++            .name = "tls-creds",
++            .type = QEMU_OPT_STRING,
++            .help = "ID of the TLS/SSL credentials to use",
++        },
++        { /* end of list */ }
++    },
++};
++
++static QemuOptsList runtime_tcp_opts = {
++    .name = "vxhs_tcp",
++    .head = QTAILQ_HEAD_INITIALIZER(runtime_tcp_opts.head),
++    .desc = {
++        {
++            .name = VXHS_OPT_HOST,
++            .type = QEMU_OPT_STRING,
++            .help = "host address (ipv4 addresses)",
++        },
++        {
++            .name = VXHS_OPT_PORT,
++            .type = QEMU_OPT_NUMBER,
++            .help = "port number on which VxHSD is listening (default 9999)",
++            .def_value_str = "9999"
++        },
++        { /* end of list */ }
++    },
++};
++
++/*
++ * Parse incoming URI and populate *options with the host
++ * and device information
++ */
++static int vxhs_parse_uri(const char *filename, QDict *options)
++{
++    URI *uri = NULL;
++    char *port;
++    int ret = 0;
++
++    trace_vxhs_parse_uri_filename(filename);
++    uri = uri_parse(filename);
++    if (!uri || !uri->server || !uri->path) {
++        uri_free(uri);
++        return -EINVAL;
++    }
++
++    qdict_put(options, VXHS_OPT_SERVER".host", qstring_from_str(uri->server));
++
++    if (uri->port) {
++        port = g_strdup_printf("%d", uri->port);
++        qdict_put(options, VXHS_OPT_SERVER".port", qstring_from_str(port));
++        g_free(port);
++    }
++
++    qdict_put(options, "vdisk-id", qstring_from_str(uri->path));
++
++    trace_vxhs_parse_uri_hostinfo(uri->server, uri->port);
++    uri_free(uri);
++
++    return ret;
++}
++
++static void vxhs_parse_filename(const char *filename, QDict *options,
++                                Error **errp)
++{
++    if (qdict_haskey(options, "vdisk-id") || qdict_haskey(options, "server")) {
++        error_setg(errp, "vdisk-id/server and a file name may not be specified "
++                         "at the same time");
++        return;
++    }
++
++    if (strstr(filename, "://")) {
++        int ret = vxhs_parse_uri(filename, options);
++        if (ret < 0) {
++            error_setg(errp, "Invalid URI. URI should be of the form "
++                       "  vxhs://<host_ip>:<port>/<vdisk-id>");
++        }
++    }
++}
++
++static int vxhs_init_and_ref(void)
++{
++    if (vxhs_ref++ == 0) {
++        if (iio_init(QNIO_VERSION, vxhs_iio_callback)) {
++            return -ENODEV;
++        }
++    }
++    return 0;
++}
++
++static void vxhs_unref(void)
++{
++    if (--vxhs_ref == 0) {
++        iio_fini();
++    }
++}
++
++static void vxhs_get_tls_creds(const char *id, char **cacert,
++                               char **key, char **cert, Error **errp)
++{
++    Object *obj;
++    QCryptoTLSCreds *creds;
++    QCryptoTLSCredsX509 *creds_x509;
++
++    obj = object_resolve_path_component(
++        object_get_objects_root(), id);
++
++    if (!obj) {
++        error_setg(errp, "No TLS credentials with id '%s'",
++                   id);
++        return;
++    }
++
++    creds_x509 = (QCryptoTLSCredsX509 *)
++        object_dynamic_cast(obj, TYPE_QCRYPTO_TLS_CREDS_X509);
++
++    if (!creds_x509) {
++        error_setg(errp, "Object with id '%s' is not TLS credentials",
++                   id);
++        return;
++    }
++
++    creds = &creds_x509->parent_obj;
++
++    if (creds->endpoint != QCRYPTO_TLS_CREDS_ENDPOINT_CLIENT) {
++        error_setg(errp,
++                   "Expecting TLS credentials with a client endpoint");
++        return;
++    }
++
++    /*
++     * Get the cacert, client_cert and client_key file names.
++     */
++    if (!creds->dir) {
++        error_setg(errp, "TLS object missing 'dir' property value");
++        return;
++    }
++
++    *cacert = g_strdup_printf("%s/%s", creds->dir,
++                              QCRYPTO_TLS_CREDS_X509_CA_CERT);
++    *cert = g_strdup_printf("%s/%s", creds->dir,
++                            QCRYPTO_TLS_CREDS_X509_CLIENT_CERT);
++    *key = g_strdup_printf("%s/%s", creds->dir,
++                           QCRYPTO_TLS_CREDS_X509_CLIENT_KEY);
++}
++
++static int vxhs_open(BlockDriverState *bs, QDict *options,
++                     int bdrv_flags, Error **errp)
++{
++    BDRVVXHSState *s = bs->opaque;
++    void *dev_handlep;
++    QDict *backing_options = NULL;
++    QemuOpts *opts = NULL;
++    QemuOpts *tcp_opts = NULL;
++    char *of_vsa_addr = NULL;
++    Error *local_err = NULL;
++    const char *vdisk_id_opt;
++    const char *server_host_opt;
++    int ret = 0;
++    char *cacert = NULL;
++    char *client_key = NULL;
++    char *client_cert = NULL;
++
++    ret = vxhs_init_and_ref();
++    if (ret < 0) {
++        ret = -EINVAL;
++        goto out;
++    }
++
++    /* Create opts info from runtime_opts and runtime_tcp_opts list */
++    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
++    tcp_opts = qemu_opts_create(&runtime_tcp_opts, NULL, 0, &error_abort);
++
++    qemu_opts_absorb_qdict(opts, options, &local_err);
++    if (local_err) {
++        ret = -EINVAL;
++        goto out;
++    }
++
++    /* vdisk-id is the disk UUID */
++    vdisk_id_opt = qemu_opt_get(opts, VXHS_OPT_VDISK_ID);
++    if (!vdisk_id_opt) {
++        error_setg(&local_err, QERR_MISSING_PARAMETER, VXHS_OPT_VDISK_ID);
++        ret = -EINVAL;
++        goto out;
++    }
++
++    /* vdisk-id may contain a leading '/' */
++    if (strlen(vdisk_id_opt) > UUID_FMT_LEN + 1) {
++        error_setg(&local_err, "vdisk-id cannot be more than %d characters",
++                   UUID_FMT_LEN);
++        ret = -EINVAL;
++        goto out;
++    }
++
++    s->vdisk_guid = g_strdup(vdisk_id_opt);
++    trace_vxhs_open_vdiskid(vdisk_id_opt);
++
++    /* get the 'server.' arguments */
++    qdict_extract_subqdict(options, &backing_options, VXHS_OPT_SERVER".");
++
++    qemu_opts_absorb_qdict(tcp_opts, backing_options, &local_err);
++    if (local_err != NULL) {
++        ret = -EINVAL;
++        goto out;
++    }
++
++    server_host_opt = qemu_opt_get(tcp_opts, VXHS_OPT_HOST);
++    if (!server_host_opt) {
++        error_setg(&local_err, QERR_MISSING_PARAMETER,
++                   VXHS_OPT_SERVER"."VXHS_OPT_HOST);
++        ret = -EINVAL;
++        goto out;
++    }
++
++    if (strlen(server_host_opt) > MAXHOSTNAMELEN) {
++        error_setg(&local_err, "server.host cannot be more than %d characters",
++                   MAXHOSTNAMELEN);
++        ret = -EINVAL;
++        goto out;
++    }
++
++    /* check if we got tls-creds via the --object argument */
++    s->tlscredsid = g_strdup(qemu_opt_get(opts, "tls-creds"));
++    if (s->tlscredsid) {
++        vxhs_get_tls_creds(s->tlscredsid, &cacert, &client_key,
++                           &client_cert, &local_err);
++        if (local_err != NULL) {
++            ret = -EINVAL;
++            goto out;
++        }
++        trace_vxhs_get_creds(cacert, client_key, client_cert);
++    }
++
++    s->vdisk_hostinfo.host = g_strdup(server_host_opt);
++    s->vdisk_hostinfo.port = g_ascii_strtoll(qemu_opt_get(tcp_opts,
++                                                          VXHS_OPT_PORT),
++                                                          NULL, 0);
++
++    trace_vxhs_open_hostinfo(s->vdisk_hostinfo.host,
++                             s->vdisk_hostinfo.port);
++
++    of_vsa_addr = g_strdup_printf("of://%s:%d",
++                                  s->vdisk_hostinfo.host,
++                                  s->vdisk_hostinfo.port);
++
++    /*
++     * Open qnio channel to storage agent if not opened before
++     */
++    dev_handlep = iio_open(of_vsa_addr, s->vdisk_guid, 0,
++                           cacert, client_key, client_cert);
++    if (dev_handlep == NULL) {
++        trace_vxhs_open_iio_open(of_vsa_addr);
++        ret = -ENODEV;
++        goto out;
++    }
++    s->vdisk_hostinfo.dev_handle = dev_handlep;
++
++out:
++    g_free(of_vsa_addr);
++    QDECREF(backing_options);
++    qemu_opts_del(tcp_opts);
++    qemu_opts_del(opts);
++    g_free(cacert);
++    g_free(client_key);
++    g_free(client_cert);
++
++    if (ret < 0) {
++        vxhs_unref();
++        error_propagate(errp, local_err);
++        g_free(s->vdisk_hostinfo.host);
++        g_free(s->vdisk_guid);
++        g_free(s->tlscredsid);
++        s->vdisk_guid = NULL;
++    }
++
++    return ret;
++}
++
++static const AIOCBInfo vxhs_aiocb_info = {
++    .aiocb_size = sizeof(VXHSAIOCB)
++};
++
++/*
++ * This allocates QEMU-VXHS callback for each IO
++ * and is passed to QNIO. When QNIO completes the work,
++ * it will be passed back through the callback.
++ */
++static BlockAIOCB *vxhs_aio_rw(BlockDriverState *bs, int64_t sector_num,
++                               QEMUIOVector *qiov, int nb_sectors,
++                               BlockCompletionFunc *cb, void *opaque,
++                               VDISKAIOCmd iodir)
++{
++    VXHSAIOCB *acb = NULL;
++    BDRVVXHSState *s = bs->opaque;
++    size_t size;
++    uint64_t offset;
++    int iio_flags = 0;
++    int ret = 0;
++    void *dev_handle = s->vdisk_hostinfo.dev_handle;
++
++    offset = sector_num * BDRV_SECTOR_SIZE;
++    size = nb_sectors * BDRV_SECTOR_SIZE;
++    acb = qemu_aio_get(&vxhs_aiocb_info, bs, cb, opaque);
++
++    /*
++     * Initialize VXHSAIOCB.
++     */
++    acb->err = 0;
++
++    iio_flags = IIO_FLAG_ASYNC;
++
++    switch (iodir) {
++    case VDISK_AIO_WRITE:
++            ret = iio_writev(dev_handle, acb, qiov->iov, qiov->niov,
++                             offset, (uint64_t)size, iio_flags);
++            break;
++    case VDISK_AIO_READ:
++            ret = iio_readv(dev_handle, acb, qiov->iov, qiov->niov,
++                            offset, (uint64_t)size, iio_flags);
++            break;
++    default:
++            trace_vxhs_aio_rw_invalid(iodir);
++            goto errout;
++    }
++
++    if (ret != 0) {
++        trace_vxhs_aio_rw_ioerr(s->vdisk_guid, iodir, size, offset,
++                                acb, ret, errno);
++        goto errout;
++    }
++    return &acb->common;
++
++errout:
++    qemu_aio_unref(acb);
++    return NULL;
++}
++
++static BlockAIOCB *vxhs_aio_readv(BlockDriverState *bs,
++                                   int64_t sector_num, QEMUIOVector *qiov,
++                                   int nb_sectors,
++                                   BlockCompletionFunc *cb, void *opaque)
++{
++    return vxhs_aio_rw(bs, sector_num, qiov, nb_sectors, cb,
++                       opaque, VDISK_AIO_READ);
++}
++
++static BlockAIOCB *vxhs_aio_writev(BlockDriverState *bs,
++                                   int64_t sector_num, QEMUIOVector *qiov,
++                                   int nb_sectors,
++                                   BlockCompletionFunc *cb, void *opaque)
++{
++    return vxhs_aio_rw(bs, sector_num, qiov, nb_sectors,
++                       cb, opaque, VDISK_AIO_WRITE);
++}
++
++static void vxhs_close(BlockDriverState *bs)
++{
++    BDRVVXHSState *s = bs->opaque;
++
++    trace_vxhs_close(s->vdisk_guid);
++
++    g_free(s->vdisk_guid);
++    s->vdisk_guid = NULL;
++
++    /*
++     * Close vDisk device
++     */
++    if (s->vdisk_hostinfo.dev_handle) {
++        iio_close(s->vdisk_hostinfo.dev_handle);
++        s->vdisk_hostinfo.dev_handle = NULL;
++    }
++
++    vxhs_unref();
++
++    /*
++     * Free the dynamically allocated host string etc
++     */
++    g_free(s->vdisk_hostinfo.host);
++    g_free(s->tlscredsid);
++    s->tlscredsid = NULL;
++    s->vdisk_hostinfo.host = NULL;
++    s->vdisk_hostinfo.port = 0;
++}
++
++static int64_t vxhs_get_vdisk_stat(BDRVVXHSState *s)
++{
++    int64_t vdisk_size = -1;
++    int ret = 0;
++    void *dev_handle = s->vdisk_hostinfo.dev_handle;
++
++    ret = iio_ioctl(dev_handle, IOR_VDISK_STAT, &vdisk_size, 0);
++    if (ret < 0) {
++        trace_vxhs_get_vdisk_stat_err(s->vdisk_guid, ret, errno);
++        return -EIO;
++    }
++
++    trace_vxhs_get_vdisk_stat(s->vdisk_guid, vdisk_size);
++    return vdisk_size;
++}
++
++/*
++ * Returns the size of vDisk in bytes. This is required
++ * by QEMU block upper block layer so that it is visible
++ * to guest.
++ */
++static int64_t vxhs_getlength(BlockDriverState *bs)
++{
++    BDRVVXHSState *s = bs->opaque;
++    int64_t vdisk_size;
++
++    vdisk_size = vxhs_get_vdisk_stat(s);
++    if (vdisk_size < 0) {
++        return -EIO;
++    }
++
++    return vdisk_size;
++}
++
++static BlockDriver bdrv_vxhs = {
++    .format_name                  = "vxhs",
++    .protocol_name                = "vxhs",
++    .instance_size                = sizeof(BDRVVXHSState),
++    .bdrv_file_open               = vxhs_open,
++    .bdrv_parse_filename          = vxhs_parse_filename,
++    .bdrv_close                   = vxhs_close,
++    .bdrv_getlength               = vxhs_getlength,
++    .bdrv_aio_readv               = vxhs_aio_readv,
++    .bdrv_aio_writev              = vxhs_aio_writev,
++};
++
++static void bdrv_vxhs_init(void)
++{
++    bdrv_register(&bdrv_vxhs);
++}
++
++block_init(bdrv_vxhs_init);
+diff --git a/configure b/configure
+index XXXXXXX..XXXXXXX 100755
+--- a/configure
++++ b/configure
+@@ -XXX,XX +XXX,XX @@ numa=""
+ tcmalloc="no"
+ jemalloc="no"
+ replication="yes"
++vxhs=""
+ supported_cpu="no"
+ supported_os="no"
+@@ -XXX,XX +XXX,XX @@ for opt do
+   ;;
+   --enable-replication) replication="yes"
+   ;;
++  --disable-vxhs) vxhs="no"
++  ;;
++  --enable-vxhs) vxhs="yes"
++  ;;
+   *)
+       echo "ERROR: unknown option $opt"
+       echo "Try '$0 --help' for more information"
+@@ -XXX,XX +XXX,XX @@ disabled with --disable-FEATURE, default is enabled if available:
+   xfsctl          xfsctl support
+   qom-cast-debug  cast debugging support
+   tools           build qemu-io, qemu-nbd and qemu-image tools
++  vxhs            Veritas HyperScale vDisk backend support
+ NOTE: The object files are built at the place where configure is launched
+ EOF
+@@ -XXX,XX +XXX,XX @@ if compile_prog "" "" ; then
+ fi
+ ##########################################
++# Veritas HyperScale block driver VxHS
++# Check if libvxhs is installed
++
++if test "$vxhs" != "no" ; then
++  cat > $TMPC <<EOF
++#include <stdint.h>
++#include <qnio/qnio_api.h>
++
++void *vxhs_callback;
++
++int main(void) {
++    iio_init(QNIO_VERSION, vxhs_callback);
++    return 0;
++}
++EOF
++  vxhs_libs="-lvxhs -lssl"
++  if compile_prog "" "$vxhs_libs" ; then
++    vxhs=yes
++  else
++    if test "$vxhs" = "yes" ; then
++      feature_not_found "vxhs block device" "Install libvxhs See github"
++    fi
++    vxhs=no
++  fi
++fi
++
++##########################################
+ # End of CC checks
+ # After here, no more $cc or $ld runs
+@@ -XXX,XX +XXX,XX @@ echo "tcmalloc support  $tcmalloc"
+ echo "jemalloc support  $jemalloc"
+ echo "avx2 optimization $avx2_opt"
+ echo "replication support $replication"
++echo "VxHS block device $vxhs"
+ if test "$sdl_too_old" = "yes"; then
+ echo "-> Your SDL version is too old - please upgrade to have SDL support"
+@@ -XXX,XX +XXX,XX @@ if test "$pthread_setname_np" = "yes" ; then
+   echo "CONFIG_PTHREAD_SETNAME_NP=y" >> $config_host_mak
+ fi
++if test "$vxhs" = "yes" ; then
++  echo "CONFIG_VXHS=y" >> $config_host_mak
++  echo "VXHS_LIBS=$vxhs_libs" >> $config_host_mak
++fi
++
+ if test "$tcg_interpreter" = "yes"; then
+   QEMU_INCLUDES="-I\$(SRC_PATH)/tcg/tci $QEMU_INCLUDES"
+ elif test "$ARCH" = "sparc64" ; then
+diff --git a/qapi/block-core.json b/qapi/block-core.json
+index XXXXXXX..XXXXXXX 100644
+--- a/qapi/block-core.json
++++ b/qapi/block-core.json
+@@ -XXX,XX +XXX,XX @@
+ #
+ # Drivers that are supported in block device operations.
+ #
++# @vxhs: Since 2.10
++#
+ # Since: 2.9
+ ##
+ { 'enum': 'BlockdevDriver',
+@@ -XXX,XX +XXX,XX @@
+             'host_device', 'http', 'https', 'iscsi', 'luks', 'nbd', 'nfs',
+             'null-aio', 'null-co', 'parallels', 'qcow', 'qcow2', 'qed',
+             'quorum', 'raw', 'rbd', 'replication', 'sheepdog', 'ssh',
+-            'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
++            'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', 'vxhs' ] }
+ ##
+ # @BlockdevOptionsFile:
+@@ -XXX,XX +XXX,XX @@
+   'data': { '*offset': 'int', '*size': 'int' } }
+ ##
++# @BlockdevOptionsVxHS:
++#
++# Driver specific block device options for VxHS
++#
++# @vdisk-id:    UUID of VxHS volume
++# @server:      vxhs server IP, port
++# @tls-creds:   TLS credentials ID
++#
++# Since: 2.10
++##
++{ 'struct': 'BlockdevOptionsVxHS',
++  'data': { 'vdisk-id': 'str',
++            'server': 'InetSocketAddressBase',
++            '*tls-creds': 'str' } }
++
++##
+ # @BlockdevOptions:
+ #
+ # Options for creating a block device.  Many options are available for all
+@@ -XXX,XX +XXX,XX @@
+       'vhdx':       'BlockdevOptionsGenericFormat',
+       'vmdk':       'BlockdevOptionsGenericCOWFormat',
+       'vpc':        'BlockdevOptionsGenericFormat',
+-      'vvfat':      'BlockdevOptionsVVFAT'
++      'vvfat':      'BlockdevOptionsVVFAT',
++      'vxhs':       'BlockdevOptionsVxHS'
+   } }
+ ##
+--
+.9.3

-New patch
+[Qemu-devel] [PULL v2 02/12] block/vxhs.c: Add qemu-iotests for new block device type "vxhs"
+From: Ashish Mittal <ashmit602@gmail.com>
+These changes use a vxhs test server that is a part of the following
+repository:
+https://github.com/VeritasHyperScale/libqnio.git
+Signed-off-by: Ashish Mittal <Ashish.Mittal@veritas.com>
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+Reviewed-by: Jeff Cody <jcody@redhat.com>
+Signed-off-by: Jeff Cody <jcody@redhat.com>
+Message-id: 1491277689-24949-3-git-send-email-Ashish.Mittal@veritas.com
+---
+ tests/qemu-iotests/common        |  6 ++++++
+ tests/qemu-iotests/common.config | 13 +++++++++++++
+ tests/qemu-iotests/common.filter |  1 +
+ tests/qemu-iotests/common.rc     | 19 +++++++++++++++++++
+files changed, 39 insertions(+)
+diff --git a/tests/qemu-iotests/common b/tests/qemu-iotests/common
+index XXXXXXX..XXXXXXX 100644
+--- a/tests/qemu-iotests/common
++++ b/tests/qemu-iotests/common
+@@ -XXX,XX +XXX,XX @@ check options
+     -ssh                test ssh
+     -nfs                test nfs
+     -luks               test luks
++    -vxhs               test vxhs
+     -xdiff              graphical mode diff
+     -nocache            use O_DIRECT on backing file
+     -misalign           misalign memory allocations
+@@ -XXX,XX +XXX,XX @@ testlist options
+             xpand=false
+             ;;
++        -vxhs)
++            IMGPROTO=vxhs
++            xpand=false
++            ;;
++
+         -ssh)
+             IMGPROTO=ssh
+             xpand=false
+diff --git a/tests/qemu-iotests/common.config b/tests/qemu-iotests/common.config
+index XXXXXXX..XXXXXXX 100644
+--- a/tests/qemu-iotests/common.config
++++ b/tests/qemu-iotests/common.config
+@@ -XXX,XX +XXX,XX @@ if [ -z "$QEMU_NBD_PROG" ]; then
+     export QEMU_NBD_PROG="`set_prog_path qemu-nbd`"
+ fi
++if [ -z "$QEMU_VXHS_PROG" ]; then
++    export QEMU_VXHS_PROG="`set_prog_path qnio_server`"
++fi
++
+ _qemu_wrapper()
+ {
+     (
+@@ -XXX,XX +XXX,XX @@ _qemu_nbd_wrapper()
+     )
+ }
++_qemu_vxhs_wrapper()
++{
++    (
++        echo $BASHPID > "${TEST_DIR}/qemu-vxhs.pid"
++        exec "$QEMU_VXHS_PROG" $QEMU_VXHS_OPTIONS "$@"
++    )
++}
++
+ export QEMU=_qemu_wrapper
+ export QEMU_IMG=_qemu_img_wrapper
+ export QEMU_IO=_qemu_io_wrapper
+ export QEMU_NBD=_qemu_nbd_wrapper
++export QEMU_VXHS=_qemu_vxhs_wrapper
+ QEMU_IMG_EXTRA_ARGS=
+ if [ "$IMGOPTSSYNTAX" = "true" ]; then
+diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
+index XXXXXXX..XXXXXXX 100644
+--- a/tests/qemu-iotests/common.filter
++++ b/tests/qemu-iotests/common.filter
+@@ -XXX,XX +XXX,XX @@ _filter_img_info()
+         -e "s#$TEST_DIR#TEST_DIR#g" \
+         -e "s#$IMGFMT#IMGFMT#g" \
+         -e 's#nbd://127.0.0.1:10810$#TEST_DIR/t.IMGFMT#g' \
++        -e 's#json.*vdisk-id.*vxhs"}}#TEST_DIR/t.IMGFMT#' \
+         -e "/encrypted: yes/d" \
+         -e "/cluster_size: [0-9]\\+/d" \
+         -e "/table_size: [0-9]\\+/d" \
+diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc
+index XXXXXXX..XXXXXXX 100644
+--- a/tests/qemu-iotests/common.rc
++++ b/tests/qemu-iotests/common.rc
+@@ -XXX,XX +XXX,XX @@ else
+     elif [ "$IMGPROTO" = "nfs" ]; then
+         TEST_DIR="nfs://127.0.0.1/$TEST_DIR"
+         TEST_IMG=$TEST_DIR/t.$IMGFMT
++    elif [ "$IMGPROTO" = "vxhs" ]; then
++        TEST_IMG_FILE=$TEST_DIR/t.$IMGFMT
++        TEST_IMG="vxhs://127.0.0.1:9999/t.$IMGFMT"
+     else
+         TEST_IMG=$IMGPROTO:$TEST_DIR/t.$IMGFMT
+     fi
+@@ -XXX,XX +XXX,XX @@ _make_test_img()
+         eval "$QEMU_NBD -v -t -b 127.0.0.1 -p 10810 -f $IMGFMT  $TEST_IMG_FILE >/dev/null &"
+         sleep 1 # FIXME: qemu-nbd needs to be listening before we continue
+     fi
++
++    # Start QNIO server on image directory for vxhs protocol
++    if [ $IMGPROTO = "vxhs" ]; then
++        eval "$QEMU_VXHS -d  $TEST_DIR > /dev/null &"
++        sleep 1 # Wait for server to come up.
++    fi
+ }
+ _rm_test_img()
+@@ -XXX,XX +XXX,XX @@ _cleanup_test_img()
+             fi
+             rm -f "$TEST_IMG_FILE"
+             ;;
++        vxhs)
++            if [ -f "${TEST_DIR}/qemu-vxhs.pid" ]; then
++                local QEMU_VXHS_PID
++                read QEMU_VXHS_PID < "${TEST_DIR}/qemu-vxhs.pid"
++                kill ${QEMU_VXHS_PID} >/dev/null 2>&1
++                rm -f "${TEST_DIR}/qemu-vxhs.pid"
++            fi
++            rm -f "$TEST_IMG_FILE"
++            ;;
++
+         file)
+             _rm_test_img "$TEST_DIR/t.$IMGFMT"
+             _rm_test_img "$TEST_DIR/t.$IMGFMT.orig"
+--
+.9.3

-New patch
+[Qemu-devel] [PULL v2 03/12] qemu-iotests: exclude vxhs from image creation via protocol
+The protocol VXHS does not support image creation.  Some tests expect
+to be able to create images through the protocol.  Exclude VXHS from
+these tests.
+Signed-off-by: Jeff Cody <jcody@redhat.com>
+---
+ tests/qemu-iotests/017 | 1 +
+ tests/qemu-iotests/020 | 1 +
+ tests/qemu-iotests/029 | 1 +
+ tests/qemu-iotests/073 | 1 +
+ tests/qemu-iotests/114 | 1 +
+ tests/qemu-iotests/130 | 1 +
+ tests/qemu-iotests/134 | 1 +
+ tests/qemu-iotests/156 | 1 +
+ tests/qemu-iotests/158 | 1 +
+files changed, 9 insertions(+)
+diff --git a/tests/qemu-iotests/017 b/tests/qemu-iotests/017
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/017
++++ b/tests/qemu-iotests/017
+@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
+ # Any format supporting backing files
+ _supported_fmt qcow qcow2 vmdk qed
+ _supported_proto generic
++_unsupported_proto vxhs
+ _supported_os Linux
+ _unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat"
+diff --git a/tests/qemu-iotests/020 b/tests/qemu-iotests/020
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/020
++++ b/tests/qemu-iotests/020
+@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
+ # Any format supporting backing files
+ _supported_fmt qcow qcow2 vmdk qed
+ _supported_proto generic
++_unsupported_proto vxhs
+ _supported_os Linux
+ _unsupported_imgopts "subformat=monolithicFlat" \
+                      "subformat=twoGbMaxExtentFlat" \
+diff --git a/tests/qemu-iotests/029 b/tests/qemu-iotests/029
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/029
++++ b/tests/qemu-iotests/029
+@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
+ # Any format supporting intenal snapshots
+ _supported_fmt qcow2
+ _supported_proto generic
++_unsupported_proto vxhs
+ _supported_os Linux
+ # Internal snapshots are (currently) impossible with refcount_bits=1
+ _unsupported_imgopts 'refcount_bits=1[^0-9]'
+diff --git a/tests/qemu-iotests/073 b/tests/qemu-iotests/073
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/073
++++ b/tests/qemu-iotests/073
+@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
+ _supported_fmt qcow2
+ _supported_proto generic
++_unsupported_proto vxhs
+ _supported_os Linux
+ CLUSTER_SIZE=64k
+diff --git a/tests/qemu-iotests/114 b/tests/qemu-iotests/114
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/114
++++ b/tests/qemu-iotests/114
+@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
+ _supported_fmt qcow2
+ _supported_proto generic
++_unsupported_proto vxhs
+ _supported_os Linux
+diff --git a/tests/qemu-iotests/130 b/tests/qemu-iotests/130
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/130
++++ b/tests/qemu-iotests/130
+@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
+ _supported_fmt qcow2
+ _supported_proto generic
++_unsupported_proto vxhs
+ _supported_os Linux
+ qemu_comm_method="monitor"
+diff --git a/tests/qemu-iotests/134 b/tests/qemu-iotests/134
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/134
++++ b/tests/qemu-iotests/134
+@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
+ _supported_fmt qcow2
+ _supported_proto generic
++_unsupported_proto vxhs
+ _supported_os Linux
+diff --git a/tests/qemu-iotests/156 b/tests/qemu-iotests/156
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/156
++++ b/tests/qemu-iotests/156
+@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
+ _supported_fmt qcow2 qed
+ _supported_proto generic
++_unsupported_proto vxhs
+ _supported_os Linux
+ # Create source disk
+diff --git a/tests/qemu-iotests/158 b/tests/qemu-iotests/158
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/158
++++ b/tests/qemu-iotests/158
+@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
+ _supported_fmt qcow2
+ _supported_proto generic
++_unsupported_proto vxhs
+ _supported_os Linux
+--
+.9.3

-New patch
+[Qemu-devel] [PULL v2 04/12] block: add bdrv_set_read_only() helper function
+We have a helper wrapper for checking for the BDS read_only flag,
+add a helper wrapper to set the read_only flag as well.
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+Signed-off-by: Jeff Cody <jcody@redhat.com>
+Reviewed-by: John Snow <jsnow@redhat.com>
+Message-id: 9b18972d05f5fa2ac16c014f0af98d680553048d.1491597120.git.jcody@redhat.com
+---
+ block.c               | 5 +++++
+ block/bochs.c         | 2 +-
+ block/cloop.c         | 2 +-
+ block/dmg.c           | 2 +-
+ block/rbd.c           | 2 +-
+ block/vvfat.c         | 4 ++--
+ include/block/block.h | 1 +
+files changed, 12 insertions(+), 6 deletions(-)
+diff --git a/block.c b/block.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block.c
++++ b/block.c
+@@ -XXX,XX +XXX,XX @@ void path_combine(char *dest, int dest_size,
+     }
+ }
++void bdrv_set_read_only(BlockDriverState *bs, bool read_only)
++{
++    bs->read_only = read_only;
++}
++
+ void bdrv_get_full_backing_filename_from_filename(const char *backed,
+                                                   const char *backing,
+                                                   char *dest, size_t sz,
+diff --git a/block/bochs.c b/block/bochs.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block/bochs.c
++++ b/block/bochs.c
+@@ -XXX,XX +XXX,XX @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
+         return -EINVAL;
+     }
+-    bs->read_only = true; /* no write support yet */
++    bdrv_set_read_only(bs, true); /* no write support yet */
+     ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));
+     if (ret < 0) {
+diff --git a/block/cloop.c b/block/cloop.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block/cloop.c
++++ b/block/cloop.c
+@@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
+         return -EINVAL;
+     }
+-    bs->read_only = true;
++    bdrv_set_read_only(bs, true);
+     /* read header */
+     ret = bdrv_pread(bs->file, 128, &s->block_size, 4);
+diff --git a/block/dmg.c b/block/dmg.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block/dmg.c
++++ b/block/dmg.c
+@@ -XXX,XX +XXX,XX @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
+     }
+     block_module_load_one("dmg-bz2");
+-    bs->read_only = true;
++    bdrv_set_read_only(bs, true);
+     s->n_chunks = 0;
+     s->offsets = s->lengths = s->sectors = s->sectorcounts = NULL;
+diff --git a/block/rbd.c b/block/rbd.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block/rbd.c
++++ b/block/rbd.c
+@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
+         goto failed_open;
+     }
+-    bs->read_only = (s->snap != NULL);
++    bdrv_set_read_only(bs, (s->snap != NULL));
+     qemu_opts_del(opts);
+     return 0;
+diff --git a/block/vvfat.c b/block/vvfat.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block/vvfat.c
++++ b/block/vvfat.c
+@@ -XXX,XX +XXX,XX @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
+     s->current_cluster=0xffffffff;
+     /* read only is the default for safety */
+-    bs->read_only = true;
++    bdrv_set_read_only(bs, true);
+     s->qcow = NULL;
+     s->qcow_filename = NULL;
+     s->fat2 = NULL;
+@@ -XXX,XX +XXX,XX @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
+         if (ret < 0) {
+             goto fail;
+         }
+-        bs->read_only = false;
++        bdrv_set_read_only(bs, false);
+     }
+     bs->total_sectors = cyls * heads * secs;
+diff --git a/include/block/block.h b/include/block/block.h
+index XXXXXXX..XXXXXXX 100644
+--- a/include/block/block.h
++++ b/include/block/block.h
+@@ -XXX,XX +XXX,XX @@ int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
+                             int64_t sector_num, int nb_sectors, int *pnum);
+ bool bdrv_is_read_only(BlockDriverState *bs);
++void bdrv_set_read_only(BlockDriverState *bs, bool read_only);
+ bool bdrv_is_sg(BlockDriverState *bs);
+ bool bdrv_is_inserted(BlockDriverState *bs);
+ int bdrv_media_changed(BlockDriverState *bs);
+--
+.9.3

-[PULL for-5.0 3/3] async: use explicit memory barriers
+[Qemu-devel] [PULL v2 05/12] block: do not set BDS read_only if copy_on_read enabled
-From: Paolo Bonzini <pbonzini@redhat.com>
+A few block drivers will set the BDS read_only flag from their
 .bdrv_open() function.  This means the bs->read_only flag could
 be set after we enable copy_on_read, as the BDRV_O_COPY_ON_READ
 flag check occurs prior to the call to bdrv->bdrv_open().
-When using C11 atomics, non-seqcst reads and writes do not participate
+This adds an error return to bdrv_set_read_only(), and an error will be
-in the total order of seqcst operations.  In util/async.c and util/aio-posix.c,
+return if we try to set the BDS to read_only while copy_on_read is
-in particular, the pattern that we use
+enabled.
-          write ctx->notify_me                 write bh->scheduled
+This patch also changes the behavior of vvfat.  Before, vvfat could
-          read bh->scheduled                   read ctx->notify_me
+override the drive 'readonly' flag with its own, internal 'rw' flag.
           if !bh->scheduled, sleep             if ctx->notify_me, notify
-needs to use seqcst operations for both the write and the read.  In
+For instance, this -drive parameter would result in a writable image:
 general this is something that we do not want, because there can be
 many sources that are polled in addition to bottom halves.  The
 alternative is to place a seqcst memory barrier between the write
 and the read.  This also comes with a disadvantage, in that the
 memory barrier is implicit on strongly-ordered architectures and
 it wastes a few dozen clock cycles.
-Fortunately, ctx->notify_me is never written concurrently by two
+"-drive format=vvfat,dir=/tmp/vvfat,rw,if=virtio,readonly=on"
 threads, so we can assert that and relax the writes to ctx->notify_me.
 The resulting solution works and performs well on both aarch64 and x86.
-Note that the atomic_set/atomic_read combination is not an atomic
+This is not correct.  Now, attempting to use the above -drive parameter
-read-modify-write, and therefore it is even weaker than C11 ATOMIC_RELAXED;
+will result in an error (i.e., 'rw' is incompatible with 'readonly=on').
 on x86, ATOMIC_RELAXED compiles to a locked operation.
-Analyzed-by: Ying Fang <fangying1@huawei.com>
+Signed-off-by: Jeff Cody <jcody@redhat.com>
-Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
-Tested-by: Ying Fang <fangying1@huawei.com>
+Reviewed-by: John Snow <jsnow@redhat.com>
-Message-Id: <20200407140746.8041-6-pbonzini@redhat.com>
+Message-id: 0c5b4c1cc2c651471b131f21376dfd5ea24d2196.1491597120.git.jcody@redhat.com
 Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
 ---
- util/aio-posix.c | 16 ++++++++++++++--
+ block.c               | 10 +++++++++-
- util/aio-win32.c | 17 ++++++++++++++---
+ block/bochs.c         |  5 ++++-
- util/async.c     | 16 ++++++++++++----
+ block/cloop.c         |  5 ++++-
-files changed, 40 insertions(+), 9 deletions(-)
+ block/dmg.c           |  6 +++++-
  block/rbd.c           | 11 ++++++++++-
  block/vvfat.c         | 19 +++++++++++++++----
  include/block/block.h |  2 +-
 files changed, 48 insertions(+), 10 deletions(-)
-diff --git a/util/aio-posix.c b/util/aio-posix.c
+diff --git a/block.c b/block.c
 index XXXXXXX..XXXXXXX 100644
---- a/util/aio-posix.c
+--- a/block.c
-+++ b/util/aio-posix.c
++++ b/block.c
-@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
+@@ -XXX,XX +XXX,XX @@ void path_combine(char *dest, int dest_size,
      int64_t timeout;
      int64_t start = 0;
 +    /*
 +     * There cannot be two concurrent aio_poll calls for the same AioContext (or
 +     * an aio_poll concurrent with a GSource prepare/check/dispatch callback).
 +     * We rely on this below to avoid slow locked accesses to ctx->notify_me.
 +     */
      assert(in_aio_context_home_thread(ctx));
      /* aio_notify can avoid the expensive event_notifier_set if
@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
       * so disable the optimization now.
       */
      if (blocking) {
 -        atomic_add(&ctx->notify_me, 2);
 +        atomic_set(&ctx->notify_me, atomic_read(&ctx->notify_me) + 2);
 +        /*
 +         * Write ctx->notify_me before computing the timeout
 +         * (reading bottom half flags, etc.).  Pairs with
 +         * smp_mb in aio_notify().
 +         */
 +        smp_mb();
      }
+ }
-     qemu_lockcnt_inc(&ctx->list_lock);
-@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
+-void bdrv_set_read_only(BlockDriverState *bs, bool read_only)
 +int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
  {
 +    /* Do not set read_only if copy_on_read is enabled */
 +    if (bs->copy_on_read && read_only) {
 +        error_setg(errp, "Can't set node '%s' to r/o with copy-on-read enabled",
 +                   bdrv_get_device_or_node_name(bs));
 +        return -EINVAL;
 +    }
 +
      bs->read_only = read_only;
 +    return 0;
  }
  void bdrv_get_full_backing_filename_from_filename(const char *backed,
 diff --git a/block/bochs.c b/block/bochs.c
 index XXXXXXX..XXXXXXX 100644
 --- a/block/bochs.c
 +++ b/block/bochs.c
@@ -XXX,XX +XXX,XX @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
          return -EINVAL;
      }
-     if (blocking) {
+-    bdrv_set_read_only(bs, true); /* no write support yet */
--        atomic_sub(&ctx->notify_me, 2);
++    ret = bdrv_set_read_only(bs, true, errp); /* no write support yet */
-+        /* Finish the poll before clearing the flag.  */
++    if (ret < 0) {
-+        atomic_store_release(&ctx->notify_me, atomic_read(&ctx->notify_me) - 2);
++        return ret;
-         aio_notify_accept(ctx);
++    }
      ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));
      if (ret < 0) {
 diff --git a/block/cloop.c b/block/cloop.c
 index XXXXXXX..XXXXXXX 100644
 --- a/block/cloop.c
 +++ b/block/cloop.c
@@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
          return -EINVAL;
      }
-diff --git a/util/aio-win32.c b/util/aio-win32.c
+-    bdrv_set_read_only(bs, true);
 +    ret = bdrv_set_read_only(bs, true, errp);
 +    if (ret < 0) {
 +        return ret;
 +    }
      /* read header */
      ret = bdrv_pread(bs->file, 128, &s->block_size, 4);
 diff --git a/block/dmg.c b/block/dmg.c
 index XXXXXXX..XXXXXXX 100644
---- a/util/aio-win32.c
+--- a/block/dmg.c
-+++ b/util/aio-win32.c
++++ b/block/dmg.c
-@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
+@@ -XXX,XX +XXX,XX @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
-     int count;
+         return -EINVAL;
      int timeout;
 +    /*
 +     * There cannot be two concurrent aio_poll calls for the same AioContext (or
 +     * an aio_poll concurrent with a GSource prepare/check/dispatch callback).
 +     * We rely on this below to avoid slow locked accesses to ctx->notify_me.
 +     */
 +    assert(in_aio_context_home_thread(ctx));
      progress = false;
      /* aio_notify can avoid the expensive event_notifier_set if
@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
       * so disable the optimization now.
       */
      if (blocking) {
 -        atomic_add(&ctx->notify_me, 2);
 +        atomic_set(&ctx->notify_me, atomic_read(&ctx->notify_me) + 2);
 +        /*
 +         * Write ctx->notify_me before computing the timeout
 +         * (reading bottom half flags, etc.).  Pairs with
 +         * smp_mb in aio_notify().
 +         */
 +        smp_mb();
      }
-     qemu_lockcnt_inc(&ctx->list_lock);
++    ret = bdrv_set_read_only(bs, true, errp);
-@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
++    if (ret < 0) {
-         ret = WaitForMultipleObjects(count, events, FALSE, timeout);
++        return ret;
-         if (blocking) {
++    }
-             assert(first);
++
--            assert(in_aio_context_home_thread(ctx));
+     block_module_load_one("dmg-bz2");
--            atomic_sub(&ctx->notify_me, 2);
+-    bdrv_set_read_only(bs, true);
-+            atomic_store_release(&ctx->notify_me, atomic_read(&ctx->notify_me) - 2);
-             aio_notify_accept(ctx);
+     s->n_chunks = 0;
      s->offsets = s->lengths = s->sectors = s->sectorcounts = NULL;
 diff --git a/block/rbd.c b/block/rbd.c
 index XXXXXXX..XXXXXXX 100644
 --- a/block/rbd.c
 +++ b/block/rbd.c
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
          goto failed_shutdown;
      }
 +    /* rbd_open is always r/w */
      r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
      if (r < 0) {
          error_setg_errno(errp, -r, "error reading header from %s", s->name);
          goto failed_open;
      }
 -    bdrv_set_read_only(bs, (s->snap != NULL));
 +    /* If we are using an rbd snapshot, we must be r/o, otherwise
 +     * leave as-is */
 +    if (s->snap != NULL) {
 +        r = bdrv_set_read_only(bs, true, &local_err);
 +        if (r < 0) {
 +            error_propagate(errp, local_err);
 +            goto failed_open;
 +        }
 +    }
      qemu_opts_del(opts);
      return 0;
 diff --git a/block/vvfat.c b/block/vvfat.c
 index XXXXXXX..XXXXXXX 100644
 --- a/block/vvfat.c
 +++ b/block/vvfat.c
@@ -XXX,XX +XXX,XX @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
      s->current_cluster=0xffffffff;
 -    /* read only is the default for safety */
 -    bdrv_set_read_only(bs, true);
      s->qcow = NULL;
      s->qcow_filename = NULL;
      s->fat2 = NULL;
@@ -XXX,XX +XXX,XX @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
      s->sector_count = cyls * heads * secs - (s->first_sectors_number - 1);
      if (qemu_opt_get_bool(opts, "rw", false)) {
 -        ret = enable_write_target(bs, errp);
 +        if (!bdrv_is_read_only(bs)) {
 +            ret = enable_write_target(bs, errp);
 +            if (ret < 0) {
 +                goto fail;
 +            }
 +        } else {
 +            ret = -EPERM;
 +            error_setg(errp,
 +                       "Unable to set VVFAT to 'rw' when drive is read-only");
 +            goto fail;
 +        }
 +    } else  {
 +        /* read only is the default for safety */
 +        ret = bdrv_set_read_only(bs, true, &local_err);
          if (ret < 0) {
 +            error_propagate(errp, local_err);
              goto fail;
          }
+-        bdrv_set_read_only(bs, false);
-diff --git a/util/async.c b/util/async.c
+     }
      bs->total_sectors = cyls * heads * secs;
 diff --git a/include/block/block.h b/include/block/block.h
 index XXXXXXX..XXXXXXX 100644
---- a/util/async.c
+--- a/include/block/block.h
-+++ b/util/async.c
++++ b/include/block/block.h
-@@ -XXX,XX +XXX,XX @@ aio_ctx_prepare(GSource *source, gint    *timeout)
+@@ -XXX,XX +XXX,XX @@ int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
- {
+                             int64_t sector_num, int nb_sectors, int *pnum);
-     AioContext *ctx = (AioContext *) source;
+ bool bdrv_is_read_only(BlockDriverState *bs);
--    atomic_or(&ctx->notify_me, 1);
+-void bdrv_set_read_only(BlockDriverState *bs, bool read_only);
-+    atomic_set(&ctx->notify_me, atomic_read(&ctx->notify_me) | 1);
++int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp);
-+
+ bool bdrv_is_sg(BlockDriverState *bs);
-+    /*
+ bool bdrv_is_inserted(BlockDriverState *bs);
-+     * Write ctx->notify_me before computing the timeout
+ int bdrv_media_changed(BlockDriverState *bs);
 +     * (reading bottom half flags, etc.).  Pairs with
 +     * smp_mb in aio_notify().
 +     */
 +    smp_mb();
      /* We assume there is no timeout already supplied */
      *timeout = qemu_timeout_ns_to_ms(aio_compute_timeout(ctx));
@@ -XXX,XX +XXX,XX @@ aio_ctx_check(GSource *source)
      QEMUBH *bh;
      BHListSlice *s;
 -    atomic_and(&ctx->notify_me, ~1);
 +    /* Finish computing the timeout before clearing the flag.  */
 +    atomic_store_release(&ctx->notify_me, atomic_read(&ctx->notify_me) & ~1);
      aio_notify_accept(ctx);
      QSLIST_FOREACH_RCU(bh, &ctx->bh_list, next) {
@@ -XXX,XX +XXX,XX @@ LuringState *aio_get_linux_io_uring(AioContext *ctx)
  void aio_notify(AioContext *ctx)
  {
      /* Write e.g. bh->scheduled before reading ctx->notify_me.  Pairs
 -     * with atomic_or in aio_ctx_prepare or atomic_add in aio_poll.
 +     * with smp_mb in aio_ctx_prepare or aio_poll.
       */
      smp_mb();
 -    if (ctx->notify_me) {
 +    if (atomic_read(&ctx->notify_me)) {
          event_notifier_set(&ctx->notifier);
          atomic_mb_set(&ctx->notified, true);
      }
 --
-.25.1
+.9.3

-New patch
+[Qemu-devel] [PULL v2 06/12] block: honor BDRV_O_ALLOW_RDWR when clearing bs->read_only
+The BDRV_O_ALLOW_RDWR flag allows / prohibits the changing of
+the BDS 'read_only' state, but there are a few places where it
+is ignored.  In the bdrv_set_read_only() helper, make sure to
+honor the flag.
+Signed-off-by: Jeff Cody <jcody@redhat.com>
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+Reviewed-by: John Snow <jsnow@redhat.com>
+Message-id: be2e5fb2d285cbece2b6d06bed54a6f56520d251.1491597120.git.jcody@redhat.com
+---
+ block.c | 7 +++++++
+file changed, 7 insertions(+)
+diff --git a/block.c b/block.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block.c
++++ b/block.c
+@@ -XXX,XX +XXX,XX @@ int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
+         return -EINVAL;
+     }
++    /* Do not clear read_only if it is prohibited */
++    if (!read_only && !(bs->open_flags & BDRV_O_ALLOW_RDWR)) {
++        error_setg(errp, "Node '%s' is read only",
++                   bdrv_get_device_or_node_name(bs));
++        return -EPERM;
++    }
++
+     bs->read_only = read_only;
+     return 0;
+ }
+--
+.9.3

-New patch
+[Qemu-devel] [PULL v2 07/12] block: code movement
+Move bdrv_is_read_only() up with its friends.
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+Reviewed-by: John Snow <jsnow@redhat.com>
+Signed-off-by: Jeff Cody <jcody@redhat.com>
+Message-id: 73b2399459760c32506f9407efb9dddb3a2789de.1491597120.git.jcody@redhat.com
+---
+ block.c | 10 +++++-----
+file changed, 5 insertions(+), 5 deletions(-)
+diff --git a/block.c b/block.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block.c
++++ b/block.c
+@@ -XXX,XX +XXX,XX @@ void path_combine(char *dest, int dest_size,
+     }
+ }
++bool bdrv_is_read_only(BlockDriverState *bs)
++{
++    return bs->read_only;
++}
++
+ int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
+ {
+     /* Do not set read_only if copy_on_read is enabled */
+@@ -XXX,XX +XXX,XX @@ void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr)
+     *nb_sectors_ptr = nb_sectors < 0 ? 0 : nb_sectors;
+ }
+-bool bdrv_is_read_only(BlockDriverState *bs)
+-{
+-    return bs->read_only;
+-}
+-
+ bool bdrv_is_sg(BlockDriverState *bs)
+ {
+     return bs->sg;
+--
+.9.3

-New patch
+[Qemu-devel] [PULL v2 08/12] block: introduce bdrv_can_set_read_only()
+Introduce check function for setting read_only flags.  Will return < 0 on
+error, with appropriate Error value set.  Does not alter any flags.
+Signed-off-by: Jeff Cody <jcody@redhat.com>
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+Reviewed-by: John Snow <jsnow@redhat.com>
+Message-id: e2bba34ac3bc76a0c42adc390413f358ae0566e8.1491597120.git.jcody@redhat.com
+---
+ block.c               | 14 +++++++++++++-
+ include/block/block.h |  1 +
+files changed, 14 insertions(+), 1 deletion(-)
+diff --git a/block.c b/block.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block.c
++++ b/block.c
+@@ -XXX,XX +XXX,XX @@ bool bdrv_is_read_only(BlockDriverState *bs)
+     return bs->read_only;
+ }
+-int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
++int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
+ {
+     /* Do not set read_only if copy_on_read is enabled */
+     if (bs->copy_on_read && read_only) {
+@@ -XXX,XX +XXX,XX @@ int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
+         return -EPERM;
+     }
++    return 0;
++}
++
++int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
++{
++    int ret = 0;
++
++    ret = bdrv_can_set_read_only(bs, read_only, errp);
++    if (ret < 0) {
++        return ret;
++    }
++
+     bs->read_only = read_only;
+     return 0;
+ }
+diff --git a/include/block/block.h b/include/block/block.h
+index XXXXXXX..XXXXXXX 100644
+--- a/include/block/block.h
++++ b/include/block/block.h
+@@ -XXX,XX +XXX,XX @@ int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
+                             int64_t sector_num, int nb_sectors, int *pnum);
+ bool bdrv_is_read_only(BlockDriverState *bs);
++int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, Error **errp);
+ int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp);
+ bool bdrv_is_sg(BlockDriverState *bs);
+ bool bdrv_is_inserted(BlockDriverState *bs);
+--
+.9.3

-New patch
+[Qemu-devel] [PULL v2 09/12] block: use bdrv_can_set_read_only() during reopen
+Signed-off-by: Jeff Cody <jcody@redhat.com>
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
+Reviewed-by: John Snow <jsnow@redhat.com>
+Message-id: 00aed7ffdd7be4b9ed9ce1007d50028a72b34ebe.1491597120.git.jcody@redhat.com
+---
+ block.c | 14 ++++++++------
+file changed, 8 insertions(+), 6 deletions(-)
+diff --git a/block.c b/block.c
+index XXXXXXX..XXXXXXX 100644
+--- a/block.c
++++ b/block.c
+@@ -XXX,XX +XXX,XX @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
+     BlockDriver *drv;
+     QemuOpts *opts;
+     const char *value;
++    bool read_only;
+     assert(reopen_state != NULL);
+     assert(reopen_state->bs->drv != NULL);
+@@ -XXX,XX +XXX,XX @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
+         qdict_put(reopen_state->options, "driver", qstring_from_str(value));
+     }
+-    /* if we are to stay read-only, do not allow permission change
+-     * to r/w */
+-    if (!(reopen_state->bs->open_flags & BDRV_O_ALLOW_RDWR) &&
+-        reopen_state->flags & BDRV_O_RDWR) {
+-        error_setg(errp, "Node '%s' is read only",
+-                   bdrv_get_device_or_node_name(reopen_state->bs));
++    /* If we are to stay read-only, do not allow permission change
++     * to r/w. Attempting to set to r/w may fail if either BDRV_O_ALLOW_RDWR is
++     * not set, or if the BDS still has copy_on_read enabled */
++    read_only = !(reopen_state->flags & BDRV_O_RDWR);
++    ret = bdrv_can_set_read_only(reopen_state->bs, read_only, &local_err);
++    if (local_err) {
++        error_propagate(errp, local_err);
+         goto error;
+     }
+--
+.9.3

-[PULL for-5.0 1/3] aio-posix: signal-proof fdmon-io_uring
+[Qemu-devel] [PULL v2 10/12] block/rbd - update variable names to more apt names
-The io_uring_enter(2) syscall returns with errno=EINTR when interrupted
+Update 'clientname' to be 'user', which tracks better with both
-by a signal.  Retry the syscall in this case.
+the QAPI and rados variable naming.
-It's essential to do this in the io_uring_submit_and_wait() case.  My
+Update 'name' to be 'image_name', as it indicates the rbd image.
-interpretation of the Linux v5.5 io_uring_enter(2) code is that it
+Naming it 'image' would have been ideal, but we are using that for
-shouldn't affect the io_uring_submit() case, but there is no guarantee
+the rados_image_t value returned by rbd_open().
 this will always be the case.  Let's check for -EINTR around both APIs.
-Note that the liburing APIs have -errno return values.
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
 Signed-off-by: Jeff Cody <jcody@redhat.com>
 Reviewed-by: John Snow <jsnow@redhat.com>
 Message-id: b7ec1fb2e1cf36f9b6911631447a5b0422590b7d.1491597120.git.jcody@redhat.com
 ---
  block/rbd.c | 33 +++++++++++++++++----------------
 file changed, 17 insertions(+), 16 deletions(-)
-Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+diff --git a/block/rbd.c b/block/rbd.c
-Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
+index XXXXXXX..XXXXXXX 100644
-Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
+--- a/block/rbd.c
-Message-id: 20200408091139.273851-1-stefanha@redhat.com
++++ b/block/rbd.c
-Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
+@@ -XXX,XX +XXX,XX @@ typedef struct BDRVRBDState {
----
+     rados_t cluster;
- util/fdmon-io_uring.c | 10 ++++++++--
+     rados_ioctx_t io_ctx;
-file changed, 8 insertions(+), 2 deletions(-)
+     rbd_image_t image;
 -    char *name;
 +    char *image_name;
      char *snap;
  } BDRVRBDState;
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
      int64_t bytes = 0;
      int64_t objsize;
      int obj_order = 0;
 -    const char *pool, *name, *conf, *clientname, *keypairs;
 +    const char *pool, *image_name, *conf, *user, *keypairs;
      const char *secretid;
      rados_t cluster;
      rados_ioctx_t io_ctx;
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
       */
      pool       = qdict_get_try_str(options, "pool");
      conf       = qdict_get_try_str(options, "conf");
 -    clientname = qdict_get_try_str(options, "user");
 -    name       = qdict_get_try_str(options, "image");
 +    user       = qdict_get_try_str(options, "user");
 +    image_name = qdict_get_try_str(options, "image");
      keypairs   = qdict_get_try_str(options, "=keyvalue-pairs");
 -    ret = rados_create(&cluster, clientname);
 +    ret = rados_create(&cluster, user);
      if (ret < 0) {
          error_setg_errno(errp, -ret, "error initializing");
          goto exit;
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
          goto shutdown;
      }
 -    ret = rbd_create(io_ctx, name, bytes, &obj_order);
 +    ret = rbd_create(io_ctx, image_name, bytes, &obj_order);
      if (ret < 0) {
          error_setg_errno(errp, -ret, "error rbd create");
      }
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
                           Error **errp)
  {
      BDRVRBDState *s = bs->opaque;
 -    const char *pool, *snap, *conf, *clientname, *name, *keypairs;
 +    const char *pool, *snap, *conf, *user, *image_name, *keypairs;
      const char *secretid;
      QemuOpts *opts;
      Error *local_err = NULL;
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
      pool           = qemu_opt_get(opts, "pool");
      conf           = qemu_opt_get(opts, "conf");
      snap           = qemu_opt_get(opts, "snapshot");
 -    clientname     = qemu_opt_get(opts, "user");
 -    name           = qemu_opt_get(opts, "image");
 +    user           = qemu_opt_get(opts, "user");
 +    image_name     = qemu_opt_get(opts, "image");
      keypairs       = qemu_opt_get(opts, "=keyvalue-pairs");
 -    if (!pool || !name) {
 +    if (!pool || !image_name) {
          error_setg(errp, "Parameters 'pool' and 'image' are required");
          r = -EINVAL;
          goto failed_opts;
      }
 -    r = rados_create(&s->cluster, clientname);
 +    r = rados_create(&s->cluster, user);
      if (r < 0) {
          error_setg_errno(errp, -r, "error initializing");
          goto failed_opts;
      }
      s->snap = g_strdup(snap);
 -    s->name = g_strdup(name);
 +    s->image_name = g_strdup(image_name);
      /* try default location when conf=NULL, but ignore failure */
      r = rados_conf_read_file(s->cluster, conf);
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
      }
      /* rbd_open is always r/w */
 -    r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
 +    r = rbd_open(s->io_ctx, s->image_name, &s->image, s->snap);
      if (r < 0) {
 -        error_setg_errno(errp, -r, "error reading header from %s", s->name);
 +        error_setg_errno(errp, -r, "error reading header from %s",
 +                         s->image_name);
          goto failed_open;
      }
@@ -XXX,XX +XXX,XX @@ failed_open:
  failed_shutdown:
      rados_shutdown(s->cluster);
      g_free(s->snap);
 -    g_free(s->name);
 +    g_free(s->image_name);
  failed_opts:
      qemu_opts_del(opts);
      g_free(mon_host);
@@ -XXX,XX +XXX,XX @@ static void qemu_rbd_close(BlockDriverState *bs)
      rbd_close(s->image);
      rados_ioctx_destroy(s->io_ctx);
      g_free(s->snap);
 -    g_free(s->name);
 +    g_free(s->image_name);
      rados_shutdown(s->cluster);
  }
 --
 .9.3
-diff --git a/util/fdmon-io_uring.c b/util/fdmon-io_uring.c
-index XXXXXXX..XXXXXXX 100644
---- a/util/fdmon-io_uring.c
-+++ b/util/fdmon-io_uring.c
-@@ -XXX,XX +XXX,XX @@ static struct io_uring_sqe *get_sqe(AioContext *ctx)
-     }
-     /* No free sqes left, submit pending sqes first */
--    ret = io_uring_submit(ring);
-+    do {
-+        ret = io_uring_submit(ring);
-+    } while (ret == -EINTR);
-+
-     assert(ret > 1);
-     sqe = io_uring_get_sqe(ring);
-     assert(sqe);
-@@ -XXX,XX +XXX,XX @@ static int fdmon_io_uring_wait(AioContext *ctx, AioHandlerList *ready_list,
-     fill_sq_ring(ctx);
--    ret = io_uring_submit_and_wait(&ctx->fdmon_io_uring, wait_nr);
-+    do {
-+        ret = io_uring_submit_and_wait(&ctx->fdmon_io_uring, wait_nr);
-+    } while (ret == -EINTR);
-+
-     assert(ret >= 0);
-     return process_cq_ring(ctx, ready_list);
---
-.25.1

-[PULL for-5.0 2/3] aio-wait: delegate polling of main AioContext if BQL not held
+[Qemu-devel] [PULL v2 11/12] block/rbd: Add support for reopen()
-From: Paolo Bonzini <pbonzini@redhat.com>
+This adds support for reopen in rbd, for changing between r/w and r/o.
-Any thread that is not a iothread returns NULL for qemu_get_current_aio_context().
+Note, that this is only a flag change, but we will block a change from
-As a result, it would also return true for
+r/o to r/w if we are using an RBD internal snapshot.
 in_aio_context_home_thread(qemu_get_aio_context()), causing
 AIO_WAIT_WHILE to invoke aio_poll() directly.  This is incorrect
 if the BQL is not held, because aio_poll() does not expect to
 run concurrently from multiple threads, and it can actually
 happen when savevm writes to the vmstate file from the
 migration thread.
-Therefore, restrict in_aio_context_home_thread to return true
+Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
-for the main AioContext only if the BQL is held.
+Signed-off-by: Jeff Cody <jcody@redhat.com>
 Reviewed-by: John Snow <jsnow@redhat.com>
 Message-id: d4e87539167ec6527d44c97b164eabcccf96e4f3.1491597120.git.jcody@redhat.com
 ---
  block/rbd.c | 21 +++++++++++++++++++++
 file changed, 21 insertions(+)
-The function is moved to aio-wait.h because it is mostly used
+diff --git a/block/rbd.c b/block/rbd.c
 there and to avoid a circular reference between main-loop.h
 and block/aio.h.
 Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
 Message-Id: <20200407140746.8041-5-pbonzini@redhat.com>
 Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
 ---
  include/block/aio-wait.h | 22 ++++++++++++++++++++++
  include/block/aio.h      | 29 ++++++++++-------------------
 files changed, 32 insertions(+), 19 deletions(-)
 diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
 index XXXXXXX..XXXXXXX 100644
---- a/include/block/aio-wait.h
+--- a/block/rbd.c
-+++ b/include/block/aio-wait.h
++++ b/block/rbd.c
-@@ -XXX,XX +XXX,XX @@
+@@ -XXX,XX +XXX,XX @@ failed_opts:
- #define QEMU_AIO_WAIT_H
+     return r;
+ }
- #include "block/aio.h"
-+#include "qemu/main-loop.h"
++
++/* Since RBD is currently always opened R/W via the API,
- /**
++ * we just need to check if we are using a snapshot or not, in
-  * AioWait:
++ * order to determine if we will allow it to be R/W */
-@@ -XXX,XX +XXX,XX @@ void aio_wait_kick(void);
++static int qemu_rbd_reopen_prepare(BDRVReopenState *state,
-  */
++                                   BlockReopenQueue *queue, Error **errp)
  void aio_wait_bh_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque);
 +/**
 + * in_aio_context_home_thread:
 + * @ctx: the aio context
 + *
 + * Return whether we are running in the thread that normally runs @ctx.  Note
 + * that acquiring/releasing ctx does not affect the outcome, each AioContext
 + * still only has one home thread that is responsible for running it.
 + */
 +static inline bool in_aio_context_home_thread(AioContext *ctx)
 +{
-+    if (ctx == qemu_get_current_aio_context()) {
++    BDRVRBDState *s = state->bs->opaque;
-+        return true;
++    int ret = 0;
 +
 +    if (s->snap && state->flags & BDRV_O_RDWR) {
 +        error_setg(errp,
 +                   "Cannot change node '%s' to r/w when using RBD snapshot",
 +                   bdrv_get_device_or_node_name(state->bs));
 +        ret = -EINVAL;
 +    }
 +
-+    if (ctx == qemu_get_aio_context()) {
++    return ret;
 +        return qemu_mutex_iothread_locked();
 +    } else {
 +        return false;
 +    }
 +}
 +
- #endif /* QEMU_AIO_WAIT_H */
+ static void qemu_rbd_close(BlockDriverState *bs)
-diff --git a/include/block/aio.h b/include/block/aio.h
+ {
-index XXXXXXX..XXXXXXX 100644
+     BDRVRBDState *s = bs->opaque;
---- a/include/block/aio.h
+@@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_rbd = {
-+++ b/include/block/aio.h
+     .bdrv_parse_filename    = qemu_rbd_parse_filename,
-@@ -XXX,XX +XXX,XX @@ struct AioContext {
+     .bdrv_file_open         = qemu_rbd_open,
-     AioHandlerList deleted_aio_handlers;
+     .bdrv_close             = qemu_rbd_close,
++    .bdrv_reopen_prepare    = qemu_rbd_reopen_prepare,
-     /* Used to avoid unnecessary event_notifier_set calls in aio_notify;
+     .bdrv_create            = qemu_rbd_create,
--     * accessed with atomic primitives.  If this field is 0, everything
+     .bdrv_has_zero_init     = bdrv_has_zero_init_1,
--     * (file descriptors, bottom halves, timers) will be re-evaluated
+     .bdrv_get_info          = qemu_rbd_getinfo,
 -     * before the next blocking poll(), thus the event_notifier_set call
 -     * can be skipped.  If it is non-zero, you may need to wake up a
 -     * concurrent aio_poll or the glib main event loop, making
 -     * event_notifier_set necessary.
 +     * only written from the AioContext home thread, or under the BQL in
 +     * the case of the main AioContext.  However, it is read from any
 +     * thread so it is still accessed with atomic primitives.
 +     *
 +     * If this field is 0, everything (file descriptors, bottom halves,
 +     * timers) will be re-evaluated before the next blocking poll() or
 +     * io_uring wait; therefore, the event_notifier_set call can be
 +     * skipped.  If it is non-zero, you may need to wake up a concurrent
 +     * aio_poll or the glib main event loop, making event_notifier_set
 +     * necessary.
       *
       * Bit 0 is reserved for GSource usage of the AioContext, and is 1
       * between a call to aio_ctx_prepare and the next call to aio_ctx_check.
@@ -XXX,XX +XXX,XX @@ void aio_co_enter(AioContext *ctx, struct Coroutine *co);
   */
  AioContext *qemu_get_current_aio_context(void);
 -/**
 - * in_aio_context_home_thread:
 - * @ctx: the aio context
 - *
 - * Return whether we are running in the thread that normally runs @ctx.  Note
 - * that acquiring/releasing ctx does not affect the outcome, each AioContext
 - * still only has one home thread that is responsible for running it.
 - */
 -static inline bool in_aio_context_home_thread(AioContext *ctx)
 -{
 -    return ctx == qemu_get_current_aio_context();
 -}
 -
  /**
   * aio_context_setup:
   * @ctx: the aio context
 --
-.25.1
+.9.3

-New patch
+[Qemu-devel] [PULL v2 12/12] qemu-iotests: _cleanup_qemu must be called on exit
+For the tests that use the common.qemu functions for running a QEMU
+process, _cleanup_qemu must be called in the exit function.
+If it is not, if the qemu process aborts, then not all of the droppings
+are cleaned up (e.g. pidfile, fifos).
+This updates those tests that did not have a cleanup in qemu-iotests.
+(I swapped spaces for tabs in test 102 as well)
+Reported-by: Eric Blake <eblake@redhat.com>
+Reviewed-by: Eric Blake <eblake@redhat.com>
+Signed-off-by: Jeff Cody <jcody@redhat.com>
+Message-id: d59c2f6ad6c1da8b9b3c7f357c94a7122ccfc55a.1492544096.git.jcody@redhat.com
+---
+ tests/qemu-iotests/028 |  1 +
+ tests/qemu-iotests/094 | 11 ++++++++---
+ tests/qemu-iotests/102 |  5 +++--
+ tests/qemu-iotests/109 |  1 +
+ tests/qemu-iotests/117 |  1 +
+ tests/qemu-iotests/130 |  1 +
+ tests/qemu-iotests/140 |  1 +
+ tests/qemu-iotests/141 |  1 +
+ tests/qemu-iotests/143 |  1 +
+ tests/qemu-iotests/156 |  1 +
+files changed, 19 insertions(+), 5 deletions(-)
+diff --git a/tests/qemu-iotests/028 b/tests/qemu-iotests/028
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/028
++++ b/tests/qemu-iotests/028
+@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
+ _cleanup()
+ {
++    _cleanup_qemu
+     rm -f "${TEST_IMG}.copy"
+     _cleanup_test_img
+ }
+diff --git a/tests/qemu-iotests/094 b/tests/qemu-iotests/094
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/094
++++ b/tests/qemu-iotests/094
+@@ -XXX,XX +XXX,XX @@ echo "QA output created by $seq"
+ here="$PWD"
+ status=1    # failure is the default!
+-trap "exit \$status" 0 1 2 3 15
++_cleanup()
++{
++    _cleanup_qemu
++    _cleanup_test_img
++    rm -f "$TEST_DIR/source.$IMGFMT"
++}
++
++trap "_cleanup; exit \$status" 0 1 2 3 15
+ # get standard environment, filters and checks
+ . ./common.rc
+@@ -XXX,XX +XXX,XX @@ _send_qemu_cmd $QEMU_HANDLE \
+ wait=1 _cleanup_qemu
+-_cleanup_test_img
+-rm -f "$TEST_DIR/source.$IMGFMT"
+ # success, all done
+ echo '*** done'
+diff --git a/tests/qemu-iotests/102 b/tests/qemu-iotests/102
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/102
++++ b/tests/qemu-iotests/102
+@@ -XXX,XX +XXX,XX @@ seq=$(basename $0)
+ echo "QA output created by $seq"
+ here=$PWD
+-status=1    # failure is the default!
++status=1    # failure is the default!
+ _cleanup()
+ {
+-    _cleanup_test_img
++    _cleanup_qemu
++    _cleanup_test_img
+ }
+ trap "_cleanup; exit \$status" 0 1 2 3 15
+diff --git a/tests/qemu-iotests/109 b/tests/qemu-iotests/109
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/109
++++ b/tests/qemu-iotests/109
+@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
+ _cleanup()
+ {
++    _cleanup_qemu
+     rm -f $TEST_IMG.src
+     _cleanup_test_img
+ }
+diff --git a/tests/qemu-iotests/117 b/tests/qemu-iotests/117
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/117
++++ b/tests/qemu-iotests/117
+@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
+ _cleanup()
+ {
++    _cleanup_qemu
+     _cleanup_test_img
+ }
+ trap "_cleanup; exit \$status" 0 1 2 3 15
+diff --git a/tests/qemu-iotests/130 b/tests/qemu-iotests/130
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/130
++++ b/tests/qemu-iotests/130
+@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
+ _cleanup()
+ {
++    _cleanup_qemu
+     _cleanup_test_img
+ }
+ trap "_cleanup; exit \$status" 0 1 2 3 15
+diff --git a/tests/qemu-iotests/140 b/tests/qemu-iotests/140
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/140
++++ b/tests/qemu-iotests/140
+@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
+ _cleanup()
+ {
++    _cleanup_qemu
+     _cleanup_test_img
+     rm -f "$TEST_DIR/nbd"
+ }
+diff --git a/tests/qemu-iotests/141 b/tests/qemu-iotests/141
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/141
++++ b/tests/qemu-iotests/141
+@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
+ _cleanup()
+ {
++    _cleanup_qemu
+     _cleanup_test_img
+     rm -f "$TEST_DIR/{b,m,o}.$IMGFMT"
+ }
+diff --git a/tests/qemu-iotests/143 b/tests/qemu-iotests/143
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/143
++++ b/tests/qemu-iotests/143
+@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
+ _cleanup()
+ {
++    _cleanup_qemu
+     rm -f "$TEST_DIR/nbd"
+ }
+ trap "_cleanup; exit \$status" 0 1 2 3 15
+diff --git a/tests/qemu-iotests/156 b/tests/qemu-iotests/156
+index XXXXXXX..XXXXXXX 100755
+--- a/tests/qemu-iotests/156
++++ b/tests/qemu-iotests/156
+@@ -XXX,XX +XXX,XX @@ status=1    # failure is the default!
+ _cleanup()
+ {
++    _cleanup_qemu
+     rm -f "$TEST_IMG{,.target}{,.backing,.overlay}"
+ }
+ trap "_cleanup; exit \$status" 0 1 2 3 15
+--
+.9.3

The following changes since commit 8bac3ba57eecc466b7e73dabf7d19328a59f684e:

Merge remote-tracking branch 'remotes/rth/tags/pull-rx-20200408' into staging (2020-04-09 13:23:30 +0100)

are available in the Git repository at:

https://github.com/stefanha/qemu.git tags/block-pull-request

for you to fetch changes up to 5710a3e09f9b85801e5ce70797a4a511e5fc9e2c:

async: use explicit memory barriers (2020-04-09 16:17:14 +0100)

----------------------------------------------------------------
Pull request

Fixes for QEMU on aarch64 ARM hosts and fdmon-io_uring.

----------------------------------------------------------------

Paolo Bonzini (2):
  aio-wait: delegate polling of main AioContext if BQL not held
  async: use explicit memory barriers

Stefan Hajnoczi (1):
  aio-posix: signal-proof fdmon-io_uring

include/block/aio-wait.h | 22 ++++++++++++++++++++++
 include/block/aio.h      | 29 ++++++++++-------------------
 util/aio-posix.c         | 16 ++++++++++++++--
 util/aio-win32.c         | 17 ++++++++++++++---
 util/async.c             | 16 ++++++++++++----
 util/fdmon-io_uring.c    | 10 ++++++++--
 6 files changed, 80 insertions(+), 30 deletions(-)

-- 
2.25.1

The io_uring_enter(2) syscall returns with errno=EINTR when interrupted
by a signal.  Retry the syscall in this case.

It's essential to do this in the io_uring_submit_and_wait() case.  My
interpretation of the Linux v5.5 io_uring_enter(2) code is that it
shouldn't affect the io_uring_submit() case, but there is no guarantee
this will always be the case.  Let's check for -EINTR around both APIs.

Note that the liburing APIs have -errno return values.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
Message-id: 20200408091139.273851-1-stefanha@redhat.com
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 util/fdmon-io_uring.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/util/fdmon-io_uring.c b/util/fdmon-io_uring.c
index XXXXXXX..XXXXXXX 100644
--- a/util/fdmon-io_uring.c
+++ b/util/fdmon-io_uring.c
@@ -XXX,XX +XXX,XX @@ static struct io_uring_sqe *get_sqe(AioContext *ctx)
     }
 
     /* No free sqes left, submit pending sqes first */
-    ret = io_uring_submit(ring);
+    do {
+        ret = io_uring_submit(ring);
+    } while (ret == -EINTR);
+
     assert(ret > 1);
     sqe = io_uring_get_sqe(ring);
     assert(sqe);
@@ -XXX,XX +XXX,XX @@ static int fdmon_io_uring_wait(AioContext *ctx, AioHandlerList *ready_list,
 
     fill_sq_ring(ctx);
 
-    ret = io_uring_submit_and_wait(&ctx->fdmon_io_uring, wait_nr);
+    do {
+        ret = io_uring_submit_and_wait(&ctx->fdmon_io_uring, wait_nr);
+    } while (ret == -EINTR);
+
     assert(ret >= 0);
 
     return process_cq_ring(ctx, ready_list);
-- 
2.25.1

From: Paolo Bonzini <pbonzini@redhat.com>

Any thread that is not a iothread returns NULL for qemu_get_current_aio_context().
As a result, it would also return true for
in_aio_context_home_thread(qemu_get_aio_context()), causing
AIO_WAIT_WHILE to invoke aio_poll() directly.  This is incorrect
if the BQL is not held, because aio_poll() does not expect to
run concurrently from multiple threads, and it can actually
happen when savevm writes to the vmstate file from the
migration thread.

Therefore, restrict in_aio_context_home_thread to return true
for the main AioContext only if the BQL is held.

The function is moved to aio-wait.h because it is mostly used
there and to avoid a circular reference between main-loop.h
and block/aio.h.

Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20200407140746.8041-5-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 include/block/aio-wait.h | 22 ++++++++++++++++++++++
 include/block/aio.h      | 29 ++++++++++-------------------
 2 files changed, 32 insertions(+), 19 deletions(-)

diff --git a/include/block/aio-wait.h b/include/block/aio-wait.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/aio-wait.h
+++ b/include/block/aio-wait.h
@@ -XXX,XX +XXX,XX @@
 #define QEMU_AIO_WAIT_H
 
 #include "block/aio.h"
+#include "qemu/main-loop.h"
 
 /**
  * AioWait:
@@ -XXX,XX +XXX,XX @@ void aio_wait_kick(void);
  */
 void aio_wait_bh_oneshot(AioContext *ctx, QEMUBHFunc *cb, void *opaque);
 
+/**
+ * in_aio_context_home_thread:
+ * @ctx: the aio context
+ *
+ * Return whether we are running in the thread that normally runs @ctx.  Note
+ * that acquiring/releasing ctx does not affect the outcome, each AioContext
+ * still only has one home thread that is responsible for running it.
+ */
+static inline bool in_aio_context_home_thread(AioContext *ctx)
+{
+    if (ctx == qemu_get_current_aio_context()) {
+        return true;
+    }
+
+    if (ctx == qemu_get_aio_context()) {
+        return qemu_mutex_iothread_locked();
+    } else {
+        return false;
+    }
+}
+
 #endif /* QEMU_AIO_WAIT_H */
diff --git a/include/block/aio.h b/include/block/aio.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/aio.h
+++ b/include/block/aio.h
@@ -XXX,XX +XXX,XX @@ struct AioContext {
     AioHandlerList deleted_aio_handlers;
 
     /* Used to avoid unnecessary event_notifier_set calls in aio_notify;
-     * accessed with atomic primitives.  If this field is 0, everything
-     * (file descriptors, bottom halves, timers) will be re-evaluated
-     * before the next blocking poll(), thus the event_notifier_set call
-     * can be skipped.  If it is non-zero, you may need to wake up a
-     * concurrent aio_poll or the glib main event loop, making
-     * event_notifier_set necessary.
+     * only written from the AioContext home thread, or under the BQL in
+     * the case of the main AioContext.  However, it is read from any
+     * thread so it is still accessed with atomic primitives.
+     *
+     * If this field is 0, everything (file descriptors, bottom halves,
+     * timers) will be re-evaluated before the next blocking poll() or
+     * io_uring wait; therefore, the event_notifier_set call can be
+     * skipped.  If it is non-zero, you may need to wake up a concurrent
+     * aio_poll or the glib main event loop, making event_notifier_set
+     * necessary.
      *
      * Bit 0 is reserved for GSource usage of the AioContext, and is 1
      * between a call to aio_ctx_prepare and the next call to aio_ctx_check.
@@ -XXX,XX +XXX,XX @@ void aio_co_enter(AioContext *ctx, struct Coroutine *co);
  */
 AioContext *qemu_get_current_aio_context(void);
 
-/**
- * in_aio_context_home_thread:
- * @ctx: the aio context
- *
- * Return whether we are running in the thread that normally runs @ctx.  Note
- * that acquiring/releasing ctx does not affect the outcome, each AioContext
- * still only has one home thread that is responsible for running it.
- */
-static inline bool in_aio_context_home_thread(AioContext *ctx)
-{
-    return ctx == qemu_get_current_aio_context();
-}
-
 /**
  * aio_context_setup:
  * @ctx: the aio context
-- 
2.25.1

From: Paolo Bonzini <pbonzini@redhat.com>

When using C11 atomics, non-seqcst reads and writes do not participate
in the total order of seqcst operations.  In util/async.c and util/aio-posix.c,
in particular, the pattern that we use

write ctx->notify_me                 write bh->scheduled
          read bh->scheduled                   read ctx->notify_me
          if !bh->scheduled, sleep             if ctx->notify_me, notify

needs to use seqcst operations for both the write and the read.  In
general this is something that we do not want, because there can be
many sources that are polled in addition to bottom halves.  The
alternative is to place a seqcst memory barrier between the write
and the read.  This also comes with a disadvantage, in that the
memory barrier is implicit on strongly-ordered architectures and
it wastes a few dozen clock cycles.

Fortunately, ctx->notify_me is never written concurrently by two
threads, so we can assert that and relax the writes to ctx->notify_me.
The resulting solution works and performs well on both aarch64 and x86.

Note that the atomic_set/atomic_read combination is not an atomic
read-modify-write, and therefore it is even weaker than C11 ATOMIC_RELAXED;
on x86, ATOMIC_RELAXED compiles to a locked operation.

Analyzed-by: Ying Fang <fangying1@huawei.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Tested-by: Ying Fang <fangying1@huawei.com>
Message-Id: <20200407140746.8041-6-pbonzini@redhat.com>
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 util/aio-posix.c | 16 ++++++++++++++--
 util/aio-win32.c | 17 ++++++++++++++---
 util/async.c     | 16 ++++++++++++----
 3 files changed, 40 insertions(+), 9 deletions(-)

diff --git a/util/aio-posix.c b/util/aio-posix.c
index XXXXXXX..XXXXXXX 100644
--- a/util/aio-posix.c
+++ b/util/aio-posix.c
@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
     int64_t timeout;
     int64_t start = 0;
 
+    /*
+     * There cannot be two concurrent aio_poll calls for the same AioContext (or
+     * an aio_poll concurrent with a GSource prepare/check/dispatch callback).
+     * We rely on this below to avoid slow locked accesses to ctx->notify_me.
+     */
     assert(in_aio_context_home_thread(ctx));
 
     /* aio_notify can avoid the expensive event_notifier_set if
@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
      * so disable the optimization now.
      */
     if (blocking) {
-        atomic_add(&ctx->notify_me, 2);
+        atomic_set(&ctx->notify_me, atomic_read(&ctx->notify_me) + 2);
+        /*
+         * Write ctx->notify_me before computing the timeout
+         * (reading bottom half flags, etc.).  Pairs with
+         * smp_mb in aio_notify().
+         */
+        smp_mb();
     }
 
     qemu_lockcnt_inc(&ctx->list_lock);
@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
     }
 
     if (blocking) {
-        atomic_sub(&ctx->notify_me, 2);
+        /* Finish the poll before clearing the flag.  */
+        atomic_store_release(&ctx->notify_me, atomic_read(&ctx->notify_me) - 2);
         aio_notify_accept(ctx);
     }
 
diff --git a/util/aio-win32.c b/util/aio-win32.c
index XXXXXXX..XXXXXXX 100644
--- a/util/aio-win32.c
+++ b/util/aio-win32.c
@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
     int count;
     int timeout;
 
+    /*
+     * There cannot be two concurrent aio_poll calls for the same AioContext (or
+     * an aio_poll concurrent with a GSource prepare/check/dispatch callback).
+     * We rely on this below to avoid slow locked accesses to ctx->notify_me.
+     */
+    assert(in_aio_context_home_thread(ctx));
     progress = false;
 
     /* aio_notify can avoid the expensive event_notifier_set if
@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
      * so disable the optimization now.
      */
     if (blocking) {
-        atomic_add(&ctx->notify_me, 2);
+        atomic_set(&ctx->notify_me, atomic_read(&ctx->notify_me) + 2);
+        /*
+         * Write ctx->notify_me before computing the timeout
+         * (reading bottom half flags, etc.).  Pairs with
+         * smp_mb in aio_notify().
+         */
+        smp_mb();
     }
 
     qemu_lockcnt_inc(&ctx->list_lock);
@@ -XXX,XX +XXX,XX @@ bool aio_poll(AioContext *ctx, bool blocking)
         ret = WaitForMultipleObjects(count, events, FALSE, timeout);
         if (blocking) {
             assert(first);
-            assert(in_aio_context_home_thread(ctx));
-            atomic_sub(&ctx->notify_me, 2);
+            atomic_store_release(&ctx->notify_me, atomic_read(&ctx->notify_me) - 2);
             aio_notify_accept(ctx);
         }
 
diff --git a/util/async.c b/util/async.c
index XXXXXXX..XXXXXXX 100644
--- a/util/async.c
+++ b/util/async.c
@@ -XXX,XX +XXX,XX @@ aio_ctx_prepare(GSource *source, gint    *timeout)
 {
     AioContext *ctx = (AioContext *) source;
 
-    atomic_or(&ctx->notify_me, 1);
+    atomic_set(&ctx->notify_me, atomic_read(&ctx->notify_me) | 1);
+
+    /*
+     * Write ctx->notify_me before computing the timeout
+     * (reading bottom half flags, etc.).  Pairs with
+     * smp_mb in aio_notify().
+     */
+    smp_mb();
 
     /* We assume there is no timeout already supplied */
     *timeout = qemu_timeout_ns_to_ms(aio_compute_timeout(ctx));
@@ -XXX,XX +XXX,XX @@ aio_ctx_check(GSource *source)
     QEMUBH *bh;
     BHListSlice *s;
 
-    atomic_and(&ctx->notify_me, ~1);
+    /* Finish computing the timeout before clearing the flag.  */
+    atomic_store_release(&ctx->notify_me, atomic_read(&ctx->notify_me) & ~1);
     aio_notify_accept(ctx);
 
     QSLIST_FOREACH_RCU(bh, &ctx->bh_list, next) {
@@ -XXX,XX +XXX,XX @@ LuringState *aio_get_linux_io_uring(AioContext *ctx)
 void aio_notify(AioContext *ctx)
 {
     /* Write e.g. bh->scheduled before reading ctx->notify_me.  Pairs
-     * with atomic_or in aio_ctx_prepare or atomic_add in aio_poll.
+     * with smp_mb in aio_ctx_prepare or aio_poll.
      */
     smp_mb();
-    if (ctx->notify_me) {
+    if (atomic_read(&ctx->notify_me)) {
         event_notifier_set(&ctx->notifier);
         atomic_mb_set(&ctx->notified, true);
     }
-- 
2.25.1

The following changes since commit 4c55b1d0bad8a703f0499fe62e3761a0cd288da3:

Merge remote-tracking branch 'remotes/armbru/tags/pull-error-2017-04-24' into staging (2017-04-24 14:49:48 +0100)

are available in the git repository at:

git://github.com/codyprime/qemu-kvm-jtc.git tags/block-pull-request

for you to fetch changes up to ecfa185400ade2abc9915efa924cbad1e15a21a4:

qemu-iotests: _cleanup_qemu must be called on exit (2017-04-24 15:09:33 -0400)

----------------------------------------------------------------
Pull v2, with 32-bit errors fixed.  I don't have OS X to test compile on,
but I think it is safe to assume the cause of the compile error was the same.
----------------------------------------------------------------

Ashish Mittal (2):
  block/vxhs.c: Add support for a new block device type called "vxhs"
  block/vxhs.c: Add qemu-iotests for new block device type "vxhs"

Jeff Cody (10):
  qemu-iotests: exclude vxhs from image creation via protocol
  block: add bdrv_set_read_only() helper function
  block: do not set BDS read_only if copy_on_read enabled
  block: honor BDRV_O_ALLOW_RDWR when clearing bs->read_only
  block: code movement
  block: introduce bdrv_can_set_read_only()
  block: use bdrv_can_set_read_only() during reopen
  block/rbd - update variable names to more apt names
  block/rbd: Add support for reopen()
  qemu-iotests: _cleanup_qemu must be called on exit

-- 
2.9.3

From: Ashish Mittal <ashmit602@gmail.com>

Source code for the qnio library that this code loads can be downloaded from:
https://github.com/VeritasHyperScale/libqnio.git

Sample command line using JSON syntax:
./x86_64-softmmu/qemu-system-x86_64 -name instance-00000008 -S -vnc 0.0.0.0:0
-k en-us -vga cirrus -device virtio-balloon-pci,id=balloon0,bus=pci.0,addr=0x5
-msg timestamp=on
'json:{"driver":"vxhs","vdisk-id":"c3e9095a-a5ee-4dce-afeb-2a59fb387410",
"server":{"host":"172.172.17.4","port":"9999"}}'

Sample command line using URI syntax:
qemu-img convert -f raw -O raw -n
/var/lib/nova/instances/_base/0c5eacd5ebea5ed914b6a3e7b18f1ce734c386ad
vxhs://192.168.0.1:9999/c6718f6b-0401-441d-a8c3-1f0064d75ee0

Sample command line using TLS credentials (run in secure mode):
./qemu-io --object
tls-creds-x509,id=tls0,dir=/etc/pki/qemu/vxhs,endpoint=client -c 'read
-v 66000 2.5k' 'json:{"server.host": "127.0.0.1", "server.port": "9999",
"vdisk-id": "/test.raw", "driver": "vxhs", "tls-creds":"tls0"}'

[Jeff: Modified trace-events with the correct string formatting]

Signed-off-by: Ashish Mittal <Ashish.Mittal@veritas.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Message-id: 1491277689-24949-2-git-send-email-Ashish.Mittal@veritas.com
---
 block/Makefile.objs  |   2 +
 block/trace-events   |  17 ++
 block/vxhs.c         | 575 +++++++++++++++++++++++++++++++++++++++++++++++++++
 configure            |  39 ++++
 qapi/block-core.json |  23 ++-
 5 files changed, 654 insertions(+), 2 deletions(-)
 create mode 100644 block/vxhs.c

diff --git a/block/Makefile.objs b/block/Makefile.objs
index XXXXXXX..XXXXXXX 100644
--- a/block/Makefile.objs
+++ b/block/Makefile.objs
@@ -XXX,XX +XXX,XX @@ block-obj-$(CONFIG_LIBNFS) += nfs.o
 block-obj-$(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-y += accounting.o dirty-bitmap.o
 block-obj-y += write-threshold.o
@@ -XXX,XX +XXX,XX @@ rbd.o-cflags       := $(RBD_CFLAGS)
 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         := $(LIBSSH2_LIBS)
 block-obj-$(if $(CONFIG_BZIP2),m,n) += dmg-bz2.o
diff --git a/block/trace-events b/block/trace-events
index XXXXXXX..XXXXXXX 100644
--- a/block/trace-events
+++ b/block/trace-events
@@ -XXX,XX +XXX,XX @@ qed_aio_write_data(void *s, void *acb, int ret, uint64_t offset, size_t len) "s
 qed_aio_write_prefill(void *s, void *acb, uint64_t start, size_t len, uint64_t offset) "s %p acb %p start %"PRIu64" len %zu offset %"PRIu64
 qed_aio_write_postfill(void *s, void *acb, uint64_t start, size_t len, uint64_t offset) "s %p acb %p start %"PRIu64" len %zu offset %"PRIu64
 qed_aio_write_main(void *s, void *acb, int ret, uint64_t offset, size_t len) "s %p acb %p ret %d offset %"PRIu64" len %zu"
+
+# block/vxhs.c
+vxhs_iio_callback(int error) "ctx is NULL: error %d"
+vxhs_iio_callback_chnfail(int err, int error) "QNIO channel failed, no i/o %d, %d"
+vxhs_iio_callback_unknwn(int opcode, int err) "unexpected opcode %d, errno %d"
+vxhs_aio_rw_invalid(int req) "Invalid I/O request iodir %d"
+vxhs_aio_rw_ioerr(char *guid, int iodir, uint64_t size, uint64_t off, void *acb, int ret, int err) "IO ERROR (vDisk %s) FOR : Read/Write = %d size = %"PRIu64" offset = %"PRIu64" ACB = %p. Error = %d, errno = %d"
+vxhs_get_vdisk_stat_err(char *guid, int ret, int err) "vDisk (%s) stat ioctl failed, ret = %d, errno = %d"
+vxhs_get_vdisk_stat(char *vdisk_guid, uint64_t vdisk_size) "vDisk %s stat ioctl returned size %"PRIu64
+vxhs_complete_aio(void *acb, uint64_t ret) "aio failed acb %p ret %"PRIu64
+vxhs_parse_uri_filename(const char *filename) "URI passed via bdrv_parse_filename %s"
+vxhs_open_vdiskid(const char *vdisk_id) "Opening vdisk-id %s"
+vxhs_open_hostinfo(char *of_vsa_addr, int port) "Adding host %s:%d to BDRVVXHSState"
+vxhs_open_iio_open(const char *host) "Failed to connect to storage agent on host %s"
+vxhs_parse_uri_hostinfo(char *host, int port) "Host: IP %s, Port %d"
+vxhs_close(char *vdisk_guid) "Closing vdisk %s"
+vxhs_get_creds(const char *cacert, const char *client_key, const char *client_cert) "cacert %s, client_key %s, client_cert %s"
diff --git a/block/vxhs.c b/block/vxhs.c
new file mode 100644
index XXXXXXX..XXXXXXX
--- /dev/null
+++ b/block/vxhs.c
@@ -XXX,XX +XXX,XX @@
+/*
+ * QEMU Block driver for Veritas HyperScale (VxHS)
+ *
+ * Copyright (c) 2017 Veritas Technologies LLC.
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or later.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu/osdep.h"
+#include <qnio/qnio_api.h>
+#include <sys/param.h>
+#include "block/block_int.h"
+#include "qapi/qmp/qerror.h"
+#include "qapi/qmp/qdict.h"
+#include "qapi/qmp/qstring.h"
+#include "trace.h"
+#include "qemu/uri.h"
+#include "qapi/error.h"
+#include "qemu/uuid.h"
+#include "crypto/tlscredsx509.h"
+
+#define VXHS_OPT_FILENAME           "filename"
+#define VXHS_OPT_VDISK_ID           "vdisk-id"
+#define VXHS_OPT_SERVER             "server"
+#define VXHS_OPT_HOST               "host"
+#define VXHS_OPT_PORT               "port"
+
+/* Only accessed under QEMU global mutex */
+static uint32_t vxhs_ref;
+
+typedef enum {
+    VDISK_AIO_READ,
+    VDISK_AIO_WRITE,
+} VDISKAIOCmd;
+
+/*
+ * HyperScale AIO callbacks structure
+ */
+typedef struct VXHSAIOCB {
+    BlockAIOCB common;
+    int err;
+} VXHSAIOCB;
+
+typedef struct VXHSvDiskHostsInfo {
+    void *dev_handle; /* Device handle */
+    char *host; /* Host name or IP */
+    int port; /* Host's port number */
+} VXHSvDiskHostsInfo;
+
+/*
+ * Structure per vDisk maintained for state
+ */
+typedef struct BDRVVXHSState {
+    VXHSvDiskHostsInfo vdisk_hostinfo; /* Per host info */
+    char *vdisk_guid;
+    char *tlscredsid; /* tlscredsid */
+} BDRVVXHSState;
+
+static void vxhs_complete_aio_bh(void *opaque)
+{
+    VXHSAIOCB *acb = opaque;
+    BlockCompletionFunc *cb = acb->common.cb;
+    void *cb_opaque = acb->common.opaque;
+    int ret = 0;
+
+    if (acb->err != 0) {
+        trace_vxhs_complete_aio(acb, acb->err);
+        ret = (-EIO);
+    }
+
+    qemu_aio_unref(acb);
+    cb(cb_opaque, ret);
+}
+
+/*
+ * Called from a libqnio thread
+ */
+static void vxhs_iio_callback(void *ctx, uint32_t opcode, uint32_t error)
+{
+    VXHSAIOCB *acb = NULL;
+
+    switch (opcode) {
+    case IRP_READ_REQUEST:
+    case IRP_WRITE_REQUEST:
+
+        /*
+         * ctx is VXHSAIOCB*
+         * ctx is NULL if error is QNIOERROR_CHANNEL_HUP
+         */
+        if (ctx) {
+            acb = ctx;
+        } else {
+            trace_vxhs_iio_callback(error);
+            goto out;
+        }
+
+        if (error) {
+            if (!acb->err) {
+                acb->err = error;
+            }
+            trace_vxhs_iio_callback(error);
+        }
+
+        aio_bh_schedule_oneshot(bdrv_get_aio_context(acb->common.bs),
+                                vxhs_complete_aio_bh, acb);
+        break;
+
+    default:
+        if (error == QNIOERROR_HUP) {
+            /*
+             * Channel failed, spontaneous notification,
+             * not in response to I/O
+             */
+            trace_vxhs_iio_callback_chnfail(error, errno);
+        } else {
+            trace_vxhs_iio_callback_unknwn(opcode, error);
+        }
+        break;
+    }
+out:
+    return;
+}
+
+static QemuOptsList runtime_opts = {
+    .name = "vxhs",
+    .head = QTAILQ_HEAD_INITIALIZER(runtime_opts.head),
+    .desc = {
+        {
+            .name = VXHS_OPT_FILENAME,
+            .type = QEMU_OPT_STRING,
+            .help = "URI to the Veritas HyperScale image",
+        },
+        {
+            .name = VXHS_OPT_VDISK_ID,
+            .type = QEMU_OPT_STRING,
+            .help = "UUID of the VxHS vdisk",
+        },
+        {
+            .name = "tls-creds",
+            .type = QEMU_OPT_STRING,
+            .help = "ID of the TLS/SSL credentials to use",
+        },
+        { /* end of list */ }
+    },
+};
+
+static QemuOptsList runtime_tcp_opts = {
+    .name = "vxhs_tcp",
+    .head = QTAILQ_HEAD_INITIALIZER(runtime_tcp_opts.head),
+    .desc = {
+        {
+            .name = VXHS_OPT_HOST,
+            .type = QEMU_OPT_STRING,
+            .help = "host address (ipv4 addresses)",
+        },
+        {
+            .name = VXHS_OPT_PORT,
+            .type = QEMU_OPT_NUMBER,
+            .help = "port number on which VxHSD is listening (default 9999)",
+            .def_value_str = "9999"
+        },
+        { /* end of list */ }
+    },
+};
+
+/*
+ * Parse incoming URI and populate *options with the host
+ * and device information
+ */
+static int vxhs_parse_uri(const char *filename, QDict *options)
+{
+    URI *uri = NULL;
+    char *port;
+    int ret = 0;
+
+    trace_vxhs_parse_uri_filename(filename);
+    uri = uri_parse(filename);
+    if (!uri || !uri->server || !uri->path) {
+        uri_free(uri);
+        return -EINVAL;
+    }
+
+    qdict_put(options, VXHS_OPT_SERVER".host", qstring_from_str(uri->server));
+
+    if (uri->port) {
+        port = g_strdup_printf("%d", uri->port);
+        qdict_put(options, VXHS_OPT_SERVER".port", qstring_from_str(port));
+        g_free(port);
+    }
+
+    qdict_put(options, "vdisk-id", qstring_from_str(uri->path));
+
+    trace_vxhs_parse_uri_hostinfo(uri->server, uri->port);
+    uri_free(uri);
+
+    return ret;
+}
+
+static void vxhs_parse_filename(const char *filename, QDict *options,
+                                Error **errp)
+{
+    if (qdict_haskey(options, "vdisk-id") || qdict_haskey(options, "server")) {
+        error_setg(errp, "vdisk-id/server and a file name may not be specified "
+                         "at the same time");
+        return;
+    }
+
+    if (strstr(filename, "://")) {
+        int ret = vxhs_parse_uri(filename, options);
+        if (ret < 0) {
+            error_setg(errp, "Invalid URI. URI should be of the form "
+                       "  vxhs://<host_ip>:<port>/<vdisk-id>");
+        }
+    }
+}
+
+static int vxhs_init_and_ref(void)
+{
+    if (vxhs_ref++ == 0) {
+        if (iio_init(QNIO_VERSION, vxhs_iio_callback)) {
+            return -ENODEV;
+        }
+    }
+    return 0;
+}
+
+static void vxhs_unref(void)
+{
+    if (--vxhs_ref == 0) {
+        iio_fini();
+    }
+}
+
+static void vxhs_get_tls_creds(const char *id, char **cacert,
+                               char **key, char **cert, Error **errp)
+{
+    Object *obj;
+    QCryptoTLSCreds *creds;
+    QCryptoTLSCredsX509 *creds_x509;
+
+    obj = object_resolve_path_component(
+        object_get_objects_root(), id);
+
+    if (!obj) {
+        error_setg(errp, "No TLS credentials with id '%s'",
+                   id);
+        return;
+    }
+
+    creds_x509 = (QCryptoTLSCredsX509 *)
+        object_dynamic_cast(obj, TYPE_QCRYPTO_TLS_CREDS_X509);
+
+    if (!creds_x509) {
+        error_setg(errp, "Object with id '%s' is not TLS credentials",
+                   id);
+        return;
+    }
+
+    creds = &creds_x509->parent_obj;
+
+    if (creds->endpoint != QCRYPTO_TLS_CREDS_ENDPOINT_CLIENT) {
+        error_setg(errp,
+                   "Expecting TLS credentials with a client endpoint");
+        return;
+    }
+
+    /*
+     * Get the cacert, client_cert and client_key file names.
+     */
+    if (!creds->dir) {
+        error_setg(errp, "TLS object missing 'dir' property value");
+        return;
+    }
+
+    *cacert = g_strdup_printf("%s/%s", creds->dir,
+                              QCRYPTO_TLS_CREDS_X509_CA_CERT);
+    *cert = g_strdup_printf("%s/%s", creds->dir,
+                            QCRYPTO_TLS_CREDS_X509_CLIENT_CERT);
+    *key = g_strdup_printf("%s/%s", creds->dir,
+                           QCRYPTO_TLS_CREDS_X509_CLIENT_KEY);
+}
+
+static int vxhs_open(BlockDriverState *bs, QDict *options,
+                     int bdrv_flags, Error **errp)
+{
+    BDRVVXHSState *s = bs->opaque;
+    void *dev_handlep;
+    QDict *backing_options = NULL;
+    QemuOpts *opts = NULL;
+    QemuOpts *tcp_opts = NULL;
+    char *of_vsa_addr = NULL;
+    Error *local_err = NULL;
+    const char *vdisk_id_opt;
+    const char *server_host_opt;
+    int ret = 0;
+    char *cacert = NULL;
+    char *client_key = NULL;
+    char *client_cert = NULL;
+
+    ret = vxhs_init_and_ref();
+    if (ret < 0) {
+        ret = -EINVAL;
+        goto out;
+    }
+
+    /* Create opts info from runtime_opts and runtime_tcp_opts list */
+    opts = qemu_opts_create(&runtime_opts, NULL, 0, &error_abort);
+    tcp_opts = qemu_opts_create(&runtime_tcp_opts, NULL, 0, &error_abort);
+
+    qemu_opts_absorb_qdict(opts, options, &local_err);
+    if (local_err) {
+        ret = -EINVAL;
+        goto out;
+    }
+
+    /* vdisk-id is the disk UUID */
+    vdisk_id_opt = qemu_opt_get(opts, VXHS_OPT_VDISK_ID);
+    if (!vdisk_id_opt) {
+        error_setg(&local_err, QERR_MISSING_PARAMETER, VXHS_OPT_VDISK_ID);
+        ret = -EINVAL;
+        goto out;
+    }
+
+    /* vdisk-id may contain a leading '/' */
+    if (strlen(vdisk_id_opt) > UUID_FMT_LEN + 1) {
+        error_setg(&local_err, "vdisk-id cannot be more than %d characters",
+                   UUID_FMT_LEN);
+        ret = -EINVAL;
+        goto out;
+    }
+
+    s->vdisk_guid = g_strdup(vdisk_id_opt);
+    trace_vxhs_open_vdiskid(vdisk_id_opt);
+
+    /* get the 'server.' arguments */
+    qdict_extract_subqdict(options, &backing_options, VXHS_OPT_SERVER".");
+
+    qemu_opts_absorb_qdict(tcp_opts, backing_options, &local_err);
+    if (local_err != NULL) {
+        ret = -EINVAL;
+        goto out;
+    }
+
+    server_host_opt = qemu_opt_get(tcp_opts, VXHS_OPT_HOST);
+    if (!server_host_opt) {
+        error_setg(&local_err, QERR_MISSING_PARAMETER,
+                   VXHS_OPT_SERVER"."VXHS_OPT_HOST);
+        ret = -EINVAL;
+        goto out;
+    }
+
+    if (strlen(server_host_opt) > MAXHOSTNAMELEN) {
+        error_setg(&local_err, "server.host cannot be more than %d characters",
+                   MAXHOSTNAMELEN);
+        ret = -EINVAL;
+        goto out;
+    }
+
+    /* check if we got tls-creds via the --object argument */
+    s->tlscredsid = g_strdup(qemu_opt_get(opts, "tls-creds"));
+    if (s->tlscredsid) {
+        vxhs_get_tls_creds(s->tlscredsid, &cacert, &client_key,
+                           &client_cert, &local_err);
+        if (local_err != NULL) {
+            ret = -EINVAL;
+            goto out;
+        }
+        trace_vxhs_get_creds(cacert, client_key, client_cert);
+    }
+
+    s->vdisk_hostinfo.host = g_strdup(server_host_opt);
+    s->vdisk_hostinfo.port = g_ascii_strtoll(qemu_opt_get(tcp_opts,
+                                                          VXHS_OPT_PORT),
+                                                          NULL, 0);
+
+    trace_vxhs_open_hostinfo(s->vdisk_hostinfo.host,
+                             s->vdisk_hostinfo.port);
+
+    of_vsa_addr = g_strdup_printf("of://%s:%d",
+                                  s->vdisk_hostinfo.host,
+                                  s->vdisk_hostinfo.port);
+
+    /*
+     * Open qnio channel to storage agent if not opened before
+     */
+    dev_handlep = iio_open(of_vsa_addr, s->vdisk_guid, 0,
+                           cacert, client_key, client_cert);
+    if (dev_handlep == NULL) {
+        trace_vxhs_open_iio_open(of_vsa_addr);
+        ret = -ENODEV;
+        goto out;
+    }
+    s->vdisk_hostinfo.dev_handle = dev_handlep;
+
+out:
+    g_free(of_vsa_addr);
+    QDECREF(backing_options);
+    qemu_opts_del(tcp_opts);
+    qemu_opts_del(opts);
+    g_free(cacert);
+    g_free(client_key);
+    g_free(client_cert);
+
+    if (ret < 0) {
+        vxhs_unref();
+        error_propagate(errp, local_err);
+        g_free(s->vdisk_hostinfo.host);
+        g_free(s->vdisk_guid);
+        g_free(s->tlscredsid);
+        s->vdisk_guid = NULL;
+    }
+
+    return ret;
+}
+
+static const AIOCBInfo vxhs_aiocb_info = {
+    .aiocb_size = sizeof(VXHSAIOCB)
+};
+
+/*
+ * This allocates QEMU-VXHS callback for each IO
+ * and is passed to QNIO. When QNIO completes the work,
+ * it will be passed back through the callback.
+ */
+static BlockAIOCB *vxhs_aio_rw(BlockDriverState *bs, int64_t sector_num,
+                               QEMUIOVector *qiov, int nb_sectors,
+                               BlockCompletionFunc *cb, void *opaque,
+                               VDISKAIOCmd iodir)
+{
+    VXHSAIOCB *acb = NULL;
+    BDRVVXHSState *s = bs->opaque;
+    size_t size;
+    uint64_t offset;
+    int iio_flags = 0;
+    int ret = 0;
+    void *dev_handle = s->vdisk_hostinfo.dev_handle;
+
+    offset = sector_num * BDRV_SECTOR_SIZE;
+    size = nb_sectors * BDRV_SECTOR_SIZE;
+    acb = qemu_aio_get(&vxhs_aiocb_info, bs, cb, opaque);
+
+    /*
+     * Initialize VXHSAIOCB.
+     */
+    acb->err = 0;
+
+    iio_flags = IIO_FLAG_ASYNC;
+
+    switch (iodir) {
+    case VDISK_AIO_WRITE:
+            ret = iio_writev(dev_handle, acb, qiov->iov, qiov->niov,
+                             offset, (uint64_t)size, iio_flags);
+            break;
+    case VDISK_AIO_READ:
+            ret = iio_readv(dev_handle, acb, qiov->iov, qiov->niov,
+                            offset, (uint64_t)size, iio_flags);
+            break;
+    default:
+            trace_vxhs_aio_rw_invalid(iodir);
+            goto errout;
+    }
+
+    if (ret != 0) {
+        trace_vxhs_aio_rw_ioerr(s->vdisk_guid, iodir, size, offset,
+                                acb, ret, errno);
+        goto errout;
+    }
+    return &acb->common;
+
+errout:
+    qemu_aio_unref(acb);
+    return NULL;
+}
+
+static BlockAIOCB *vxhs_aio_readv(BlockDriverState *bs,
+                                   int64_t sector_num, QEMUIOVector *qiov,
+                                   int nb_sectors,
+                                   BlockCompletionFunc *cb, void *opaque)
+{
+    return vxhs_aio_rw(bs, sector_num, qiov, nb_sectors, cb,
+                       opaque, VDISK_AIO_READ);
+}
+
+static BlockAIOCB *vxhs_aio_writev(BlockDriverState *bs,
+                                   int64_t sector_num, QEMUIOVector *qiov,
+                                   int nb_sectors,
+                                   BlockCompletionFunc *cb, void *opaque)
+{
+    return vxhs_aio_rw(bs, sector_num, qiov, nb_sectors,
+                       cb, opaque, VDISK_AIO_WRITE);
+}
+
+static void vxhs_close(BlockDriverState *bs)
+{
+    BDRVVXHSState *s = bs->opaque;
+
+    trace_vxhs_close(s->vdisk_guid);
+
+    g_free(s->vdisk_guid);
+    s->vdisk_guid = NULL;
+
+    /*
+     * Close vDisk device
+     */
+    if (s->vdisk_hostinfo.dev_handle) {
+        iio_close(s->vdisk_hostinfo.dev_handle);
+        s->vdisk_hostinfo.dev_handle = NULL;
+    }
+
+    vxhs_unref();
+
+    /*
+     * Free the dynamically allocated host string etc
+     */
+    g_free(s->vdisk_hostinfo.host);
+    g_free(s->tlscredsid);
+    s->tlscredsid = NULL;
+    s->vdisk_hostinfo.host = NULL;
+    s->vdisk_hostinfo.port = 0;
+}
+
+static int64_t vxhs_get_vdisk_stat(BDRVVXHSState *s)
+{
+    int64_t vdisk_size = -1;
+    int ret = 0;
+    void *dev_handle = s->vdisk_hostinfo.dev_handle;
+
+    ret = iio_ioctl(dev_handle, IOR_VDISK_STAT, &vdisk_size, 0);
+    if (ret < 0) {
+        trace_vxhs_get_vdisk_stat_err(s->vdisk_guid, ret, errno);
+        return -EIO;
+    }
+
+    trace_vxhs_get_vdisk_stat(s->vdisk_guid, vdisk_size);
+    return vdisk_size;
+}
+
+/*
+ * Returns the size of vDisk in bytes. This is required
+ * by QEMU block upper block layer so that it is visible
+ * to guest.
+ */
+static int64_t vxhs_getlength(BlockDriverState *bs)
+{
+    BDRVVXHSState *s = bs->opaque;
+    int64_t vdisk_size;
+
+    vdisk_size = vxhs_get_vdisk_stat(s);
+    if (vdisk_size < 0) {
+        return -EIO;
+    }
+
+    return vdisk_size;
+}
+
+static BlockDriver bdrv_vxhs = {
+    .format_name                  = "vxhs",
+    .protocol_name                = "vxhs",
+    .instance_size                = sizeof(BDRVVXHSState),
+    .bdrv_file_open               = vxhs_open,
+    .bdrv_parse_filename          = vxhs_parse_filename,
+    .bdrv_close                   = vxhs_close,
+    .bdrv_getlength               = vxhs_getlength,
+    .bdrv_aio_readv               = vxhs_aio_readv,
+    .bdrv_aio_writev              = vxhs_aio_writev,
+};
+
+static void bdrv_vxhs_init(void)
+{
+    bdrv_register(&bdrv_vxhs);
+}
+
+block_init(bdrv_vxhs_init);
diff --git a/configure b/configure
index XXXXXXX..XXXXXXX 100755
--- a/configure
+++ b/configure
@@ -XXX,XX +XXX,XX @@ numa=""
 tcmalloc="no"
 jemalloc="no"
 replication="yes"
+vxhs=""
 
 supported_cpu="no"
 supported_os="no"
@@ -XXX,XX +XXX,XX @@ for opt do
   ;;
   --enable-replication) replication="yes"
   ;;
+  --disable-vxhs) vxhs="no"
+  ;;
+  --enable-vxhs) vxhs="yes"
+  ;;
   *)
       echo "ERROR: unknown option $opt"
       echo "Try '$0 --help' for more information"
@@ -XXX,XX +XXX,XX @@ disabled with --disable-FEATURE, default is enabled if available:
   xfsctl          xfsctl support
   qom-cast-debug  cast debugging support
   tools           build qemu-io, qemu-nbd and qemu-image tools
+  vxhs            Veritas HyperScale vDisk backend support
 
 NOTE: The object files are built at the place where configure is launched
 EOF
@@ -XXX,XX +XXX,XX @@ if compile_prog "" "" ; then
 fi
 
 ##########################################
+# Veritas HyperScale block driver VxHS
+# Check if libvxhs is installed
+
+if test "$vxhs" != "no" ; then
+  cat > $TMPC <<EOF
+#include <stdint.h>
+#include <qnio/qnio_api.h>
+
+void *vxhs_callback;
+
+int main(void) {
+    iio_init(QNIO_VERSION, vxhs_callback);
+    return 0;
+}
+EOF
+  vxhs_libs="-lvxhs -lssl"
+  if compile_prog "" "$vxhs_libs" ; then
+    vxhs=yes
+  else
+    if test "$vxhs" = "yes" ; then
+      feature_not_found "vxhs block device" "Install libvxhs See github"
+    fi
+    vxhs=no
+  fi
+fi
+
+##########################################
 # End of CC checks
 # After here, no more $cc or $ld runs
 
@@ -XXX,XX +XXX,XX @@ echo "tcmalloc support  $tcmalloc"
 echo "jemalloc support  $jemalloc"
 echo "avx2 optimization $avx2_opt"
 echo "replication support $replication"
+echo "VxHS block device $vxhs"
 
 if test "$sdl_too_old" = "yes"; then
 echo "-> Your SDL version is too old - please upgrade to have SDL support"
@@ -XXX,XX +XXX,XX @@ if test "$pthread_setname_np" = "yes" ; then
   echo "CONFIG_PTHREAD_SETNAME_NP=y" >> $config_host_mak
 fi
 
+if test "$vxhs" = "yes" ; then
+  echo "CONFIG_VXHS=y" >> $config_host_mak
+  echo "VXHS_LIBS=$vxhs_libs" >> $config_host_mak
+fi
+
 if test "$tcg_interpreter" = "yes"; then
   QEMU_INCLUDES="-I\$(SRC_PATH)/tcg/tci $QEMU_INCLUDES"
 elif test "$ARCH" = "sparc64" ; then
diff --git a/qapi/block-core.json b/qapi/block-core.json
index XXXXXXX..XXXXXXX 100644
--- a/qapi/block-core.json
+++ b/qapi/block-core.json
@@ -XXX,XX +XXX,XX @@
 #
 # Drivers that are supported in block device operations.
 #
+# @vxhs: Since 2.10
+#
 # Since: 2.9
 ##
 { 'enum': 'BlockdevDriver',
@@ -XXX,XX +XXX,XX @@
             'host_device', 'http', 'https', 'iscsi', 'luks', 'nbd', 'nfs',
             'null-aio', 'null-co', 'parallels', 'qcow', 'qcow2', 'qed',
             'quorum', 'raw', 'rbd', 'replication', 'sheepdog', 'ssh',
-            'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat' ] }
+            'vdi', 'vhdx', 'vmdk', 'vpc', 'vvfat', 'vxhs' ] }
 
 ##
 # @BlockdevOptionsFile:
@@ -XXX,XX +XXX,XX @@
   'data': { '*offset': 'int', '*size': 'int' } }
 
 ##
+# @BlockdevOptionsVxHS:
+#
+# Driver specific block device options for VxHS
+#
+# @vdisk-id:    UUID of VxHS volume
+# @server:      vxhs server IP, port
+# @tls-creds:   TLS credentials ID
+#
+# Since: 2.10
+##
+{ 'struct': 'BlockdevOptionsVxHS',
+  'data': { 'vdisk-id': 'str',
+            'server': 'InetSocketAddressBase',
+            '*tls-creds': 'str' } }
+
+##
 # @BlockdevOptions:
 #
 # Options for creating a block device.  Many options are available for all
@@ -XXX,XX +XXX,XX @@
       'vhdx':       'BlockdevOptionsGenericFormat',
       'vmdk':       'BlockdevOptionsGenericCOWFormat',
       'vpc':        'BlockdevOptionsGenericFormat',
-      'vvfat':      'BlockdevOptionsVVFAT'
+      'vvfat':      'BlockdevOptionsVVFAT',
+      'vxhs':       'BlockdevOptionsVxHS'
   } }
 
 ##
-- 
2.9.3

From: Ashish Mittal <ashmit602@gmail.com>

These changes use a vxhs test server that is a part of the following
repository:
https://github.com/VeritasHyperScale/libqnio.git

Signed-off-by: Ashish Mittal <Ashish.Mittal@veritas.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Jeff Cody <jcody@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Message-id: 1491277689-24949-3-git-send-email-Ashish.Mittal@veritas.com
---
 tests/qemu-iotests/common        |  6 ++++++
 tests/qemu-iotests/common.config | 13 +++++++++++++
 tests/qemu-iotests/common.filter |  1 +
 tests/qemu-iotests/common.rc     | 19 +++++++++++++++++++
 4 files changed, 39 insertions(+)

diff --git a/tests/qemu-iotests/common b/tests/qemu-iotests/common
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common
+++ b/tests/qemu-iotests/common
@@ -XXX,XX +XXX,XX @@ check options
     -ssh                test ssh
     -nfs                test nfs
     -luks               test luks
+    -vxhs               test vxhs
     -xdiff              graphical mode diff
     -nocache            use O_DIRECT on backing file
     -misalign           misalign memory allocations
@@ -XXX,XX +XXX,XX @@ testlist options
             xpand=false
             ;;
 
+        -vxhs)
+            IMGPROTO=vxhs
+            xpand=false
+            ;;
+
         -ssh)
             IMGPROTO=ssh
             xpand=false
diff --git a/tests/qemu-iotests/common.config b/tests/qemu-iotests/common.config
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.config
+++ b/tests/qemu-iotests/common.config
@@ -XXX,XX +XXX,XX @@ if [ -z "$QEMU_NBD_PROG" ]; then
     export QEMU_NBD_PROG="`set_prog_path qemu-nbd`"
 fi
 
+if [ -z "$QEMU_VXHS_PROG" ]; then
+    export QEMU_VXHS_PROG="`set_prog_path qnio_server`"
+fi
+
 _qemu_wrapper()
 {
     (
@@ -XXX,XX +XXX,XX @@ _qemu_nbd_wrapper()
     )
 }
 
+_qemu_vxhs_wrapper()
+{
+    (
+        echo $BASHPID > "${TEST_DIR}/qemu-vxhs.pid"
+        exec "$QEMU_VXHS_PROG" $QEMU_VXHS_OPTIONS "$@"
+    )
+}
+
 export QEMU=_qemu_wrapper
 export QEMU_IMG=_qemu_img_wrapper
 export QEMU_IO=_qemu_io_wrapper
 export QEMU_NBD=_qemu_nbd_wrapper
+export QEMU_VXHS=_qemu_vxhs_wrapper
 
 QEMU_IMG_EXTRA_ARGS=
 if [ "$IMGOPTSSYNTAX" = "true" ]; then
diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.filter
+++ b/tests/qemu-iotests/common.filter
@@ -XXX,XX +XXX,XX @@ _filter_img_info()
         -e "s#$TEST_DIR#TEST_DIR#g" \
         -e "s#$IMGFMT#IMGFMT#g" \
         -e 's#nbd://127.0.0.1:10810$#TEST_DIR/t.IMGFMT#g' \
+        -e 's#json.*vdisk-id.*vxhs"}}#TEST_DIR/t.IMGFMT#' \
         -e "/encrypted: yes/d" \
         -e "/cluster_size: [0-9]\\+/d" \
         -e "/table_size: [0-9]\\+/d" \
diff --git a/tests/qemu-iotests/common.rc b/tests/qemu-iotests/common.rc
index XXXXXXX..XXXXXXX 100644
--- a/tests/qemu-iotests/common.rc
+++ b/tests/qemu-iotests/common.rc
@@ -XXX,XX +XXX,XX @@ else
     elif [ "$IMGPROTO" = "nfs" ]; then
         TEST_DIR="nfs://127.0.0.1/$TEST_DIR"
         TEST_IMG=$TEST_DIR/t.$IMGFMT
+    elif [ "$IMGPROTO" = "vxhs" ]; then
+        TEST_IMG_FILE=$TEST_DIR/t.$IMGFMT
+        TEST_IMG="vxhs://127.0.0.1:9999/t.$IMGFMT"
     else
         TEST_IMG=$IMGPROTO:$TEST_DIR/t.$IMGFMT
     fi
@@ -XXX,XX +XXX,XX @@ _make_test_img()
         eval "$QEMU_NBD -v -t -b 127.0.0.1 -p 10810 -f $IMGFMT  $TEST_IMG_FILE >/dev/null &"
         sleep 1 # FIXME: qemu-nbd needs to be listening before we continue
     fi
+
+    # Start QNIO server on image directory for vxhs protocol
+    if [ $IMGPROTO = "vxhs" ]; then
+        eval "$QEMU_VXHS -d  $TEST_DIR > /dev/null &"
+        sleep 1 # Wait for server to come up.
+    fi
 }
 
 _rm_test_img()
@@ -XXX,XX +XXX,XX @@ _cleanup_test_img()
             fi
             rm -f "$TEST_IMG_FILE"
             ;;
+        vxhs)
+            if [ -f "${TEST_DIR}/qemu-vxhs.pid" ]; then
+                local QEMU_VXHS_PID
+                read QEMU_VXHS_PID < "${TEST_DIR}/qemu-vxhs.pid"
+                kill ${QEMU_VXHS_PID} >/dev/null 2>&1
+                rm -f "${TEST_DIR}/qemu-vxhs.pid"
+            fi
+            rm -f "$TEST_IMG_FILE"
+            ;;
+
         file)
             _rm_test_img "$TEST_DIR/t.$IMGFMT"
             _rm_test_img "$TEST_DIR/t.$IMGFMT.orig"
-- 
2.9.3

The protocol VXHS does not support image creation.  Some tests expect
to be able to create images through the protocol.  Exclude VXHS from
these tests.

diff --git a/tests/qemu-iotests/017 b/tests/qemu-iotests/017
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/017
+++ b/tests/qemu-iotests/017
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # Any format supporting backing files
 _supported_fmt qcow qcow2 vmdk qed
 _supported_proto generic
+_unsupported_proto vxhs
 _supported_os Linux
 _unsupported_imgopts "subformat=monolithicFlat" "subformat=twoGbMaxExtentFlat"
 
diff --git a/tests/qemu-iotests/020 b/tests/qemu-iotests/020
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/020
+++ b/tests/qemu-iotests/020
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # Any format supporting backing files
 _supported_fmt qcow qcow2 vmdk qed
 _supported_proto generic
+_unsupported_proto vxhs
 _supported_os Linux
 _unsupported_imgopts "subformat=monolithicFlat" \
                      "subformat=twoGbMaxExtentFlat" \
diff --git a/tests/qemu-iotests/029 b/tests/qemu-iotests/029
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/029
+++ b/tests/qemu-iotests/029
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 # Any format supporting intenal snapshots
 _supported_fmt qcow2
 _supported_proto generic
+_unsupported_proto vxhs
 _supported_os Linux
 # Internal snapshots are (currently) impossible with refcount_bits=1
 _unsupported_imgopts 'refcount_bits=1[^0-9]'
diff --git a/tests/qemu-iotests/073 b/tests/qemu-iotests/073
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/073
+++ b/tests/qemu-iotests/073
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2
 _supported_proto generic
+_unsupported_proto vxhs
 _supported_os Linux
 
 CLUSTER_SIZE=64k
diff --git a/tests/qemu-iotests/114 b/tests/qemu-iotests/114
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/114
+++ b/tests/qemu-iotests/114
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2
 _supported_proto generic
+_unsupported_proto vxhs
 _supported_os Linux
 
 
diff --git a/tests/qemu-iotests/130 b/tests/qemu-iotests/130
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/130
+++ b/tests/qemu-iotests/130
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2
 _supported_proto generic
+_unsupported_proto vxhs
 _supported_os Linux
 
 qemu_comm_method="monitor"
diff --git a/tests/qemu-iotests/134 b/tests/qemu-iotests/134
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/134
+++ b/tests/qemu-iotests/134
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2
 _supported_proto generic
+_unsupported_proto vxhs
 _supported_os Linux
 
 
diff --git a/tests/qemu-iotests/156 b/tests/qemu-iotests/156
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/156
+++ b/tests/qemu-iotests/156
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2 qed
 _supported_proto generic
+_unsupported_proto vxhs
 _supported_os Linux
 
 # Create source disk
diff --git a/tests/qemu-iotests/158 b/tests/qemu-iotests/158
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/158
+++ b/tests/qemu-iotests/158
@@ -XXX,XX +XXX,XX @@ trap "_cleanup; exit \$status" 0 1 2 3 15
 
 _supported_fmt qcow2
 _supported_proto generic
+_unsupported_proto vxhs
 _supported_os Linux
 
 
-- 
2.9.3

We have a helper wrapper for checking for the BDS read_only flag,
add a helper wrapper to set the read_only flag as well.

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Message-id: 9b18972d05f5fa2ac16c014f0af98d680553048d.1491597120.git.jcody@redhat.com
---
 block.c               | 5 +++++
 block/bochs.c         | 2 +-
 block/cloop.c         | 2 +-
 block/dmg.c           | 2 +-
 block/rbd.c           | 2 +-
 block/vvfat.c         | 4 ++--
 include/block/block.h | 1 +
 7 files changed, 12 insertions(+), 6 deletions(-)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ void path_combine(char *dest, int dest_size,
     }
 }
 
+void bdrv_set_read_only(BlockDriverState *bs, bool read_only)
+{
+    bs->read_only = read_only;
+}
+
 void bdrv_get_full_backing_filename_from_filename(const char *backed,
                                                   const char *backing,
                                                   char *dest, size_t sz,
diff --git a/block/bochs.c b/block/bochs.c
index XXXXXXX..XXXXXXX 100644
--- a/block/bochs.c
+++ b/block/bochs.c
@@ -XXX,XX +XXX,XX @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
         return -EINVAL;
     }
 
-    bs->read_only = true; /* no write support yet */
+    bdrv_set_read_only(bs, true); /* no write support yet */
 
     ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));
     if (ret < 0) {
diff --git a/block/cloop.c b/block/cloop.c
index XXXXXXX..XXXXXXX 100644
--- a/block/cloop.c
+++ b/block/cloop.c
@@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         return -EINVAL;
     }
 
-    bs->read_only = true;
+    bdrv_set_read_only(bs, true);
 
     /* read header */
     ret = bdrv_pread(bs->file, 128, &s->block_size, 4);
diff --git a/block/dmg.c b/block/dmg.c
index XXXXXXX..XXXXXXX 100644
--- a/block/dmg.c
+++ b/block/dmg.c
@@ -XXX,XX +XXX,XX @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     block_module_load_one("dmg-bz2");
-    bs->read_only = true;
+    bdrv_set_read_only(bs, true);
 
     s->n_chunks = 0;
     s->offsets = s->lengths = s->sectors = s->sectorcounts = NULL;
diff --git a/block/rbd.c b/block/rbd.c
index XXXXXXX..XXXXXXX 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
         goto failed_open;
     }
 
-    bs->read_only = (s->snap != NULL);
+    bdrv_set_read_only(bs, (s->snap != NULL));
 
     qemu_opts_del(opts);
     return 0;
diff --git a/block/vvfat.c b/block/vvfat.c
index XXXXXXX..XXXXXXX 100644
--- a/block/vvfat.c
+++ b/block/vvfat.c
@@ -XXX,XX +XXX,XX @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
     s->current_cluster=0xffffffff;
 
     /* read only is the default for safety */
-    bs->read_only = true;
+    bdrv_set_read_only(bs, true);
     s->qcow = NULL;
     s->qcow_filename = NULL;
     s->fat2 = NULL;
@@ -XXX,XX +XXX,XX @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
         if (ret < 0) {
             goto fail;
         }
-        bs->read_only = false;
+        bdrv_set_read_only(bs, false);
     }
 
     bs->total_sectors = cyls * heads * secs;
diff --git a/include/block/block.h b/include/block/block.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -XXX,XX +XXX,XX @@ int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
                             int64_t sector_num, int nb_sectors, int *pnum);
 
 bool bdrv_is_read_only(BlockDriverState *bs);
+void bdrv_set_read_only(BlockDriverState *bs, bool read_only);
 bool bdrv_is_sg(BlockDriverState *bs);
 bool bdrv_is_inserted(BlockDriverState *bs);
 int bdrv_media_changed(BlockDriverState *bs);
-- 
2.9.3

A few block drivers will set the BDS read_only flag from their
.bdrv_open() function.  This means the bs->read_only flag could
be set after we enable copy_on_read, as the BDRV_O_COPY_ON_READ
flag check occurs prior to the call to bdrv->bdrv_open().

This adds an error return to bdrv_set_read_only(), and an error will be
return if we try to set the BDS to read_only while copy_on_read is
enabled.

This patch also changes the behavior of vvfat.  Before, vvfat could
override the drive 'readonly' flag with its own, internal 'rw' flag.

For instance, this -drive parameter would result in a writable image:

"-drive format=vvfat,dir=/tmp/vvfat,rw,if=virtio,readonly=on"

This is not correct.  Now, attempting to use the above -drive parameter
will result in an error (i.e., 'rw' is incompatible with 'readonly=on').

Signed-off-by: Jeff Cody <jcody@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Message-id: 0c5b4c1cc2c651471b131f21376dfd5ea24d2196.1491597120.git.jcody@redhat.com
---
 block.c               | 10 +++++++++-
 block/bochs.c         |  5 ++++-
 block/cloop.c         |  5 ++++-
 block/dmg.c           |  6 +++++-
 block/rbd.c           | 11 ++++++++++-
 block/vvfat.c         | 19 +++++++++++++++----
 include/block/block.h |  2 +-
 7 files changed, 48 insertions(+), 10 deletions(-)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ void path_combine(char *dest, int dest_size,
     }
 }
 
-void bdrv_set_read_only(BlockDriverState *bs, bool read_only)
+int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
 {
+    /* Do not set read_only if copy_on_read is enabled */
+    if (bs->copy_on_read && read_only) {
+        error_setg(errp, "Can't set node '%s' to r/o with copy-on-read enabled",
+                   bdrv_get_device_or_node_name(bs));
+        return -EINVAL;
+    }
+
     bs->read_only = read_only;
+    return 0;
 }
 
 void bdrv_get_full_backing_filename_from_filename(const char *backed,
diff --git a/block/bochs.c b/block/bochs.c
index XXXXXXX..XXXXXXX 100644
--- a/block/bochs.c
+++ b/block/bochs.c
@@ -XXX,XX +XXX,XX @@ static int bochs_open(BlockDriverState *bs, QDict *options, int flags,
         return -EINVAL;
     }
 
-    bdrv_set_read_only(bs, true); /* no write support yet */
+    ret = bdrv_set_read_only(bs, true, errp); /* no write support yet */
+    if (ret < 0) {
+        return ret;
+    }
 
     ret = bdrv_pread(bs->file, 0, &bochs, sizeof(bochs));
     if (ret < 0) {
diff --git a/block/cloop.c b/block/cloop.c
index XXXXXXX..XXXXXXX 100644
--- a/block/cloop.c
+++ b/block/cloop.c
@@ -XXX,XX +XXX,XX @@ static int cloop_open(BlockDriverState *bs, QDict *options, int flags,
         return -EINVAL;
     }
 
-    bdrv_set_read_only(bs, true);
+    ret = bdrv_set_read_only(bs, true, errp);
+    if (ret < 0) {
+        return ret;
+    }
 
     /* read header */
     ret = bdrv_pread(bs->file, 128, &s->block_size, 4);
diff --git a/block/dmg.c b/block/dmg.c
index XXXXXXX..XXXXXXX 100644
--- a/block/dmg.c
+++ b/block/dmg.c
@@ -XXX,XX +XXX,XX @@ static int dmg_open(BlockDriverState *bs, QDict *options, int flags,
         return -EINVAL;
     }
 
+    ret = bdrv_set_read_only(bs, true, errp);
+    if (ret < 0) {
+        return ret;
+    }
+
     block_module_load_one("dmg-bz2");
-    bdrv_set_read_only(bs, true);
 
     s->n_chunks = 0;
     s->offsets = s->lengths = s->sectors = s->sectorcounts = NULL;
diff --git a/block/rbd.c b/block/rbd.c
index XXXXXXX..XXXXXXX 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
         goto failed_shutdown;
     }
 
+    /* rbd_open is always r/w */
     r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
     if (r < 0) {
         error_setg_errno(errp, -r, "error reading header from %s", s->name);
         goto failed_open;
     }
 
-    bdrv_set_read_only(bs, (s->snap != NULL));
+    /* If we are using an rbd snapshot, we must be r/o, otherwise
+     * leave as-is */
+    if (s->snap != NULL) {
+        r = bdrv_set_read_only(bs, true, &local_err);
+        if (r < 0) {
+            error_propagate(errp, local_err);
+            goto failed_open;
+        }
+    }
 
     qemu_opts_del(opts);
     return 0;
diff --git a/block/vvfat.c b/block/vvfat.c
index XXXXXXX..XXXXXXX 100644
--- a/block/vvfat.c
+++ b/block/vvfat.c
@@ -XXX,XX +XXX,XX @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
 
     s->current_cluster=0xffffffff;
 
-    /* read only is the default for safety */
-    bdrv_set_read_only(bs, true);
     s->qcow = NULL;
     s->qcow_filename = NULL;
     s->fat2 = NULL;
@@ -XXX,XX +XXX,XX @@ static int vvfat_open(BlockDriverState *bs, QDict *options, int flags,
     s->sector_count = cyls * heads * secs - (s->first_sectors_number - 1);
 
     if (qemu_opt_get_bool(opts, "rw", false)) {
-        ret = enable_write_target(bs, errp);
+        if (!bdrv_is_read_only(bs)) {
+            ret = enable_write_target(bs, errp);
+            if (ret < 0) {
+                goto fail;
+            }
+        } else {
+            ret = -EPERM;
+            error_setg(errp,
+                       "Unable to set VVFAT to 'rw' when drive is read-only");
+            goto fail;
+        }
+    } else  {
+        /* read only is the default for safety */
+        ret = bdrv_set_read_only(bs, true, &local_err);
         if (ret < 0) {
+            error_propagate(errp, local_err);
             goto fail;
         }
-        bdrv_set_read_only(bs, false);
     }
 
     bs->total_sectors = cyls * heads * secs;
diff --git a/include/block/block.h b/include/block/block.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -XXX,XX +XXX,XX @@ int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
                             int64_t sector_num, int nb_sectors, int *pnum);
 
 bool bdrv_is_read_only(BlockDriverState *bs);
-void bdrv_set_read_only(BlockDriverState *bs, bool read_only);
+int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp);
 bool bdrv_is_sg(BlockDriverState *bs);
 bool bdrv_is_inserted(BlockDriverState *bs);
 int bdrv_media_changed(BlockDriverState *bs);
-- 
2.9.3

The BDRV_O_ALLOW_RDWR flag allows / prohibits the changing of
the BDS 'read_only' state, but there are a few places where it
is ignored.  In the bdrv_set_read_only() helper, make sure to
honor the flag.

Signed-off-by: Jeff Cody <jcody@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Message-id: be2e5fb2d285cbece2b6d06bed54a6f56520d251.1491597120.git.jcody@redhat.com
---
 block.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
         return -EINVAL;
     }
 
+    /* Do not clear read_only if it is prohibited */
+    if (!read_only && !(bs->open_flags & BDRV_O_ALLOW_RDWR)) {
+        error_setg(errp, "Node '%s' is read only",
+                   bdrv_get_device_or_node_name(bs));
+        return -EPERM;
+    }
+
     bs->read_only = read_only;
     return 0;
 }
-- 
2.9.3

Move bdrv_is_read_only() up with its friends.

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Message-id: 73b2399459760c32506f9407efb9dddb3a2789de.1491597120.git.jcody@redhat.com
---
 block.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ void path_combine(char *dest, int dest_size,
     }
 }
 
+bool bdrv_is_read_only(BlockDriverState *bs)
+{
+    return bs->read_only;
+}
+
 int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
 {
     /* Do not set read_only if copy_on_read is enabled */
@@ -XXX,XX +XXX,XX @@ void bdrv_get_geometry(BlockDriverState *bs, uint64_t *nb_sectors_ptr)
     *nb_sectors_ptr = nb_sectors < 0 ? 0 : nb_sectors;
 }
 
-bool bdrv_is_read_only(BlockDriverState *bs)
-{
-    return bs->read_only;
-}
-
 bool bdrv_is_sg(BlockDriverState *bs)
 {
     return bs->sg;
-- 
2.9.3

Introduce check function for setting read_only flags.  Will return < 0 on
error, with appropriate Error value set.  Does not alter any flags.

Signed-off-by: Jeff Cody <jcody@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Message-id: e2bba34ac3bc76a0c42adc390413f358ae0566e8.1491597120.git.jcody@redhat.com
---
 block.c               | 14 +++++++++++++-
 include/block/block.h |  1 +
 2 files changed, 14 insertions(+), 1 deletion(-)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ bool bdrv_is_read_only(BlockDriverState *bs)
     return bs->read_only;
 }
 
-int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
+int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
 {
     /* Do not set read_only if copy_on_read is enabled */
     if (bs->copy_on_read && read_only) {
@@ -XXX,XX +XXX,XX @@ int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
         return -EPERM;
     }
 
+    return 0;
+}
+
+int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp)
+{
+    int ret = 0;
+
+    ret = bdrv_can_set_read_only(bs, read_only, errp);
+    if (ret < 0) {
+        return ret;
+    }
+
     bs->read_only = read_only;
     return 0;
 }
diff --git a/include/block/block.h b/include/block/block.h
index XXXXXXX..XXXXXXX 100644
--- a/include/block/block.h
+++ b/include/block/block.h
@@ -XXX,XX +XXX,XX @@ int bdrv_is_allocated_above(BlockDriverState *top, BlockDriverState *base,
                             int64_t sector_num, int nb_sectors, int *pnum);
 
 bool bdrv_is_read_only(BlockDriverState *bs);
+int bdrv_can_set_read_only(BlockDriverState *bs, bool read_only, Error **errp);
 int bdrv_set_read_only(BlockDriverState *bs, bool read_only, Error **errp);
 bool bdrv_is_sg(BlockDriverState *bs);
 bool bdrv_is_inserted(BlockDriverState *bs);
-- 
2.9.3

Signed-off-by: Jeff Cody <jcody@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Message-id: 00aed7ffdd7be4b9ed9ce1007d50028a72b34ebe.1491597120.git.jcody@redhat.com
---
 block.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/block.c b/block.c
index XXXXXXX..XXXXXXX 100644
--- a/block.c
+++ b/block.c
@@ -XXX,XX +XXX,XX @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
     BlockDriver *drv;
     QemuOpts *opts;
     const char *value;
+    bool read_only;
 
     assert(reopen_state != NULL);
     assert(reopen_state->bs->drv != NULL);
@@ -XXX,XX +XXX,XX @@ int bdrv_reopen_prepare(BDRVReopenState *reopen_state, BlockReopenQueue *queue,
         qdict_put(reopen_state->options, "driver", qstring_from_str(value));
     }
 
-    /* if we are to stay read-only, do not allow permission change
-     * to r/w */
-    if (!(reopen_state->bs->open_flags & BDRV_O_ALLOW_RDWR) &&
-        reopen_state->flags & BDRV_O_RDWR) {
-        error_setg(errp, "Node '%s' is read only",
-                   bdrv_get_device_or_node_name(reopen_state->bs));
+    /* If we are to stay read-only, do not allow permission change
+     * to r/w. Attempting to set to r/w may fail if either BDRV_O_ALLOW_RDWR is
+     * not set, or if the BDS still has copy_on_read enabled */
+    read_only = !(reopen_state->flags & BDRV_O_RDWR);
+    ret = bdrv_can_set_read_only(reopen_state->bs, read_only, &local_err);
+    if (local_err) {
+        error_propagate(errp, local_err);
         goto error;
     }
 
-- 
2.9.3

Update 'clientname' to be 'user', which tracks better with both
the QAPI and rados variable naming.

Update 'name' to be 'image_name', as it indicates the rbd image.
Naming it 'image' would have been ideal, but we are using that for
the rados_image_t value returned by rbd_open().

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Message-id: b7ec1fb2e1cf36f9b6911631447a5b0422590b7d.1491597120.git.jcody@redhat.com
---
 block/rbd.c | 33 +++++++++++++++++----------------
 1 file changed, 17 insertions(+), 16 deletions(-)

diff --git a/block/rbd.c b/block/rbd.c
index XXXXXXX..XXXXXXX 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -XXX,XX +XXX,XX @@ typedef struct BDRVRBDState {
     rados_t cluster;
     rados_ioctx_t io_ctx;
     rbd_image_t image;
-    char *name;
+    char *image_name;
     char *snap;
 } BDRVRBDState;
 
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
     int64_t bytes = 0;
     int64_t objsize;
     int obj_order = 0;
-    const char *pool, *name, *conf, *clientname, *keypairs;
+    const char *pool, *image_name, *conf, *user, *keypairs;
     const char *secretid;
     rados_t cluster;
     rados_ioctx_t io_ctx;
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
      */
     pool       = qdict_get_try_str(options, "pool");
     conf       = qdict_get_try_str(options, "conf");
-    clientname = qdict_get_try_str(options, "user");
-    name       = qdict_get_try_str(options, "image");
+    user       = qdict_get_try_str(options, "user");
+    image_name = qdict_get_try_str(options, "image");
     keypairs   = qdict_get_try_str(options, "=keyvalue-pairs");
 
-    ret = rados_create(&cluster, clientname);
+    ret = rados_create(&cluster, user);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "error initializing");
         goto exit;
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_create(const char *filename, QemuOpts *opts, Error **errp)
         goto shutdown;
     }
 
-    ret = rbd_create(io_ctx, name, bytes, &obj_order);
+    ret = rbd_create(io_ctx, image_name, bytes, &obj_order);
     if (ret < 0) {
         error_setg_errno(errp, -ret, "error rbd create");
     }
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
                          Error **errp)
 {
     BDRVRBDState *s = bs->opaque;
-    const char *pool, *snap, *conf, *clientname, *name, *keypairs;
+    const char *pool, *snap, *conf, *user, *image_name, *keypairs;
     const char *secretid;
     QemuOpts *opts;
     Error *local_err = NULL;
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
     pool           = qemu_opt_get(opts, "pool");
     conf           = qemu_opt_get(opts, "conf");
     snap           = qemu_opt_get(opts, "snapshot");
-    clientname     = qemu_opt_get(opts, "user");
-    name           = qemu_opt_get(opts, "image");
+    user           = qemu_opt_get(opts, "user");
+    image_name     = qemu_opt_get(opts, "image");
     keypairs       = qemu_opt_get(opts, "=keyvalue-pairs");
 
-    if (!pool || !name) {
+    if (!pool || !image_name) {
         error_setg(errp, "Parameters 'pool' and 'image' are required");
         r = -EINVAL;
         goto failed_opts;
     }
 
-    r = rados_create(&s->cluster, clientname);
+    r = rados_create(&s->cluster, user);
     if (r < 0) {
         error_setg_errno(errp, -r, "error initializing");
         goto failed_opts;
     }
 
     s->snap = g_strdup(snap);
-    s->name = g_strdup(name);
+    s->image_name = g_strdup(image_name);
 
     /* try default location when conf=NULL, but ignore failure */
     r = rados_conf_read_file(s->cluster, conf);
@@ -XXX,XX +XXX,XX @@ static int qemu_rbd_open(BlockDriverState *bs, QDict *options, int flags,
     }
 
     /* rbd_open is always r/w */
-    r = rbd_open(s->io_ctx, s->name, &s->image, s->snap);
+    r = rbd_open(s->io_ctx, s->image_name, &s->image, s->snap);
     if (r < 0) {
-        error_setg_errno(errp, -r, "error reading header from %s", s->name);
+        error_setg_errno(errp, -r, "error reading header from %s",
+                         s->image_name);
         goto failed_open;
     }
 
@@ -XXX,XX +XXX,XX @@ failed_open:
 failed_shutdown:
     rados_shutdown(s->cluster);
     g_free(s->snap);
-    g_free(s->name);
+    g_free(s->image_name);
 failed_opts:
     qemu_opts_del(opts);
     g_free(mon_host);
@@ -XXX,XX +XXX,XX @@ static void qemu_rbd_close(BlockDriverState *bs)
     rbd_close(s->image);
     rados_ioctx_destroy(s->io_ctx);
     g_free(s->snap);
-    g_free(s->name);
+    g_free(s->image_name);
     rados_shutdown(s->cluster);
 }
 
-- 
2.9.3

This adds support for reopen in rbd, for changing between r/w and r/o.

Note, that this is only a flag change, but we will block a change from
r/o to r/w if we are using an RBD internal snapshot.

Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Reviewed-by: John Snow <jsnow@redhat.com>
Message-id: d4e87539167ec6527d44c97b164eabcccf96e4f3.1491597120.git.jcody@redhat.com
---
 block/rbd.c | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)

diff --git a/block/rbd.c b/block/rbd.c
index XXXXXXX..XXXXXXX 100644
--- a/block/rbd.c
+++ b/block/rbd.c
@@ -XXX,XX +XXX,XX @@ failed_opts:
     return r;
 }
 
+
+/* Since RBD is currently always opened R/W via the API,
+ * we just need to check if we are using a snapshot or not, in
+ * order to determine if we will allow it to be R/W */
+static int qemu_rbd_reopen_prepare(BDRVReopenState *state,
+                                   BlockReopenQueue *queue, Error **errp)
+{
+    BDRVRBDState *s = state->bs->opaque;
+    int ret = 0;
+
+    if (s->snap && state->flags & BDRV_O_RDWR) {
+        error_setg(errp,
+                   "Cannot change node '%s' to r/w when using RBD snapshot",
+                   bdrv_get_device_or_node_name(state->bs));
+        ret = -EINVAL;
+    }
+
+    return ret;
+}
+
 static void qemu_rbd_close(BlockDriverState *bs)
 {
     BDRVRBDState *s = bs->opaque;
@@ -XXX,XX +XXX,XX @@ static BlockDriver bdrv_rbd = {
     .bdrv_parse_filename    = qemu_rbd_parse_filename,
     .bdrv_file_open         = qemu_rbd_open,
     .bdrv_close             = qemu_rbd_close,
+    .bdrv_reopen_prepare    = qemu_rbd_reopen_prepare,
     .bdrv_create            = qemu_rbd_create,
     .bdrv_has_zero_init     = bdrv_has_zero_init_1,
     .bdrv_get_info          = qemu_rbd_getinfo,
-- 
2.9.3

For the tests that use the common.qemu functions for running a QEMU
process, _cleanup_qemu must be called in the exit function.

If it is not, if the qemu process aborts, then not all of the droppings
are cleaned up (e.g. pidfile, fifos).

This updates those tests that did not have a cleanup in qemu-iotests.

(I swapped spaces for tabs in test 102 as well)

Reported-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Eric Blake <eblake@redhat.com>
Signed-off-by: Jeff Cody <jcody@redhat.com>
Message-id: d59c2f6ad6c1da8b9b3c7f357c94a7122ccfc55a.1492544096.git.jcody@redhat.com
---
 tests/qemu-iotests/028 |  1 +
 tests/qemu-iotests/094 | 11 ++++++++---
 tests/qemu-iotests/102 |  5 +++--
 tests/qemu-iotests/109 |  1 +
 tests/qemu-iotests/117 |  1 +
 tests/qemu-iotests/130 |  1 +
 tests/qemu-iotests/140 |  1 +
 tests/qemu-iotests/141 |  1 +
 tests/qemu-iotests/143 |  1 +
 tests/qemu-iotests/156 |  1 +
 10 files changed, 19 insertions(+), 5 deletions(-)

diff --git a/tests/qemu-iotests/028 b/tests/qemu-iotests/028
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/028
+++ b/tests/qemu-iotests/028
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
+    _cleanup_qemu
     rm -f "${TEST_IMG}.copy"
     _cleanup_test_img
 }
diff --git a/tests/qemu-iotests/094 b/tests/qemu-iotests/094
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/094
+++ b/tests/qemu-iotests/094
@@ -XXX,XX +XXX,XX @@ echo "QA output created by $seq"
 here="$PWD"
 status=1	# failure is the default!
 
-trap "exit \$status" 0 1 2 3 15
+_cleanup()
+{
+    _cleanup_qemu
+    _cleanup_test_img
+    rm -f "$TEST_DIR/source.$IMGFMT"
+}
+
+trap "_cleanup; exit \$status" 0 1 2 3 15
 
 # get standard environment, filters and checks
 . ./common.rc
@@ -XXX,XX +XXX,XX @@ _send_qemu_cmd $QEMU_HANDLE \
 
 wait=1 _cleanup_qemu
 
-_cleanup_test_img
-rm -f "$TEST_DIR/source.$IMGFMT"
 
 # success, all done
 echo '*** done'
diff --git a/tests/qemu-iotests/102 b/tests/qemu-iotests/102
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/102
+++ b/tests/qemu-iotests/102
@@ -XXX,XX +XXX,XX @@ seq=$(basename $0)
 echo "QA output created by $seq"
 
 here=$PWD
-status=1	# failure is the default!
+status=1    # failure is the default!
 
 _cleanup()
 {
-	_cleanup_test_img
+    _cleanup_qemu
+    _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
 
diff --git a/tests/qemu-iotests/109 b/tests/qemu-iotests/109
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/109
+++ b/tests/qemu-iotests/109
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
+    _cleanup_qemu
     rm -f $TEST_IMG.src
 	_cleanup_test_img
 }
diff --git a/tests/qemu-iotests/117 b/tests/qemu-iotests/117
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/117
+++ b/tests/qemu-iotests/117
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
+    _cleanup_qemu
 	_cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/130 b/tests/qemu-iotests/130
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/130
+++ b/tests/qemu-iotests/130
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
+    _cleanup_qemu
     _cleanup_test_img
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/140 b/tests/qemu-iotests/140
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/140
+++ b/tests/qemu-iotests/140
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
+    _cleanup_qemu
     _cleanup_test_img
     rm -f "$TEST_DIR/nbd"
 }
diff --git a/tests/qemu-iotests/141 b/tests/qemu-iotests/141
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/141
+++ b/tests/qemu-iotests/141
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
+    _cleanup_qemu
     _cleanup_test_img
     rm -f "$TEST_DIR/{b,m,o}.$IMGFMT"
 }
diff --git a/tests/qemu-iotests/143 b/tests/qemu-iotests/143
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/143
+++ b/tests/qemu-iotests/143
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
+    _cleanup_qemu
     rm -f "$TEST_DIR/nbd"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
diff --git a/tests/qemu-iotests/156 b/tests/qemu-iotests/156
index XXXXXXX..XXXXXXX 100755
--- a/tests/qemu-iotests/156
+++ b/tests/qemu-iotests/156
@@ -XXX,XX +XXX,XX @@ status=1	# failure is the default!
 
 _cleanup()
 {
+    _cleanup_qemu
     rm -f "$TEST_IMG{,.target}{,.backing,.overlay}"
 }
 trap "_cleanup; exit \$status" 0 1 2 3 15
-- 
2.9.3