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"}'

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 = %lu offset = %lu 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 %lu"

+vxhs_complete_aio(void *acb, uint64_t ret) "aio failed acb %p ret %ld"

+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.

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 +

9 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

--

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(-)