Split nbd block client code

Signed-off-by: Marc-André Lureau <marcandre.lureau@redhat.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>

1 files changed, 28 insertions, 345 deletions

diff --git a/block/nbd.c b/block/nbd.c
index c8deeee67f..be75ba074c 100644
--- a/block/nbd.c
+++ b/block/nbd.c
@@ -26,8 +26,7 @@
  * THE SOFTWARE.
  */
 
-#include "qemu-common.h"
-#include "block/nbd.h"
+#include "block/nbd-client.h"
 #include "qemu/uri.h"
 #include "block/block_int.h"
 #include "qemu/module.h"
@@ -40,37 +39,9 @@
 
 #define EN_OPTSTR ":exportname="
 
-/* #define DEBUG_NBD */
-
-#if defined(DEBUG_NBD)
-#define logout(fmt, ...) \
-                fprintf(stderr, "nbd\t%-24s" fmt, __func__, ##__VA_ARGS__)
-#else
-#define logout(fmt, ...) ((void)0)
-#endif
-
-#define MAX_NBD_REQUESTS	16
-#define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
-#define INDEX_TO_HANDLE(bs, index)  ((index)  ^ ((uint64_t)(intptr_t)bs))
-
 typedef struct BDRVNBDState {
-    int sock;
-    uint32_t nbdflags;
-    off_t size;
-    size_t blocksize;
-
-    CoMutex send_mutex;
-    CoMutex free_sema;
-    Coroutine *send_coroutine;
-    int in_flight;
-
-    Coroutine *recv_coroutine[MAX_NBD_REQUESTS];
-    struct nbd_reply reply;
-
-    bool is_unix;
+    NbdClientSession client;
     QemuOpts *socket_opts;
-
-    char *export_name; /* An NBD server may export several devices */
 } BDRVNBDState;
 
 static int nbd_parse_uri(const char *filename, QDict *options)
@@ -227,9 +198,9 @@ static int nbd_config(BDRVNBDState *s, QDict *options)
                           "be used at the same time.");
             return -EINVAL;
         }
-        s->is_unix = true;
+        s->client.is_unix = true;
     } else if (qdict_haskey(options, "host")) {
-        s->is_unix = false;
+        s->client.is_unix = false;
     } else {
         return -EINVAL;
     }
@@ -247,162 +218,20 @@ static int nbd_config(BDRVNBDState *s, QDict *options)
         qemu_opt_set_number(s->socket_opts, "port", NBD_DEFAULT_PORT);
     }
 
-    s->export_name = g_strdup(qdict_get_try_str(options, "export"));
-    if (s->export_name) {
+    s->client.export_name = g_strdup(qdict_get_try_str(options, "export"));
+    if (s->client.export_name) {
         qdict_del(options, "export");
     }
 
     return 0;
 }
 
-
-static void nbd_coroutine_start(BDRVNBDState *s, struct nbd_request *request)
-{
-    int i;
-
-    /* Poor man semaphore.  The free_sema is locked when no other request
-     * can be accepted, and unlocked after receiving one reply.  */
-    if (s->in_flight >= MAX_NBD_REQUESTS - 1) {
-        qemu_co_mutex_lock(&s->free_sema);
-        assert(s->in_flight < MAX_NBD_REQUESTS);
-    }
-    s->in_flight++;
-
-    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
-        if (s->recv_coroutine[i] == NULL) {
-            s->recv_coroutine[i] = qemu_coroutine_self();
-            break;
-        }
-    }
-
-    assert(i < MAX_NBD_REQUESTS);
-    request->handle = INDEX_TO_HANDLE(s, i);
-}
-
-static void nbd_reply_ready(void *opaque)
-{
-    BDRVNBDState *s = opaque;
-    uint64_t i;
-    int ret;
-
-    if (s->reply.handle == 0) {
-        /* No reply already in flight.  Fetch a header.  It is possible
-         * that another thread has done the same thing in parallel, so
-         * the socket is not readable anymore.
-         */
-        ret = nbd_receive_reply(s->sock, &s->reply);
-        if (ret == -EAGAIN) {
-            return;
-        }
-        if (ret < 0) {
-            s->reply.handle = 0;
-            goto fail;
-        }
-    }
-
-    /* There's no need for a mutex on the receive side, because the
-     * handler acts as a synchronization point and ensures that only
-     * one coroutine is called until the reply finishes.  */
-    i = HANDLE_TO_INDEX(s, s->reply.handle);
-    if (i >= MAX_NBD_REQUESTS) {
-        goto fail;
-    }
-
-    if (s->recv_coroutine[i]) {
-        qemu_coroutine_enter(s->recv_coroutine[i], NULL);
-        return;
-    }
-
-fail:
-    for (i = 0; i < MAX_NBD_REQUESTS; i++) {
-        if (s->recv_coroutine[i]) {
-            qemu_coroutine_enter(s->recv_coroutine[i], NULL);
-        }
-    }
-}
-
-static void nbd_restart_write(void *opaque)
-{
-    BDRVNBDState *s = opaque;
-    qemu_coroutine_enter(s->send_coroutine, NULL);
-}
-
-static int nbd_co_send_request(BDRVNBDState *s, struct nbd_request *request,
-                               QEMUIOVector *qiov, int offset)
-{
-    int rc, ret;
-
-    qemu_co_mutex_lock(&s->send_mutex);
-    s->send_coroutine = qemu_coroutine_self();
-    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, nbd_restart_write, s);
-    if (qiov) {
-        if (!s->is_unix) {
-            socket_set_cork(s->sock, 1);
-        }
-        rc = nbd_send_request(s->sock, request);
-        if (rc >= 0) {
-            ret = qemu_co_sendv(s->sock, qiov->iov, qiov->niov,
-                                offset, request->len);
-            if (ret != request->len) {
-                rc = -EIO;
-            }
-        }
-        if (!s->is_unix) {
-            socket_set_cork(s->sock, 0);
-        }
-    } else {
-        rc = nbd_send_request(s->sock, request);
-    }
-    qemu_aio_set_fd_handler(s->sock, nbd_reply_ready, NULL, s);
-    s->send_coroutine = NULL;
-    qemu_co_mutex_unlock(&s->send_mutex);
-    return rc;
-}
-
-static void nbd_co_receive_reply(BDRVNBDState *s, struct nbd_request *request,
-                                 struct nbd_reply *reply,
-                                 QEMUIOVector *qiov, int offset)
-{
-    int ret;
-
-    /* Wait until we're woken up by the read handler.  TODO: perhaps
-     * peek at the next reply and avoid yielding if it's ours?  */
-    qemu_coroutine_yield();
-    *reply = s->reply;
-    if (reply->handle != request->handle) {
-        reply->error = EIO;
-    } else {
-        if (qiov && reply->error == 0) {
-            ret = qemu_co_recvv(s->sock, qiov->iov, qiov->niov,
-                                offset, request->len);
-            if (ret != request->len) {
-                reply->error = EIO;
-            }
-        }
-
-        /* Tell the read handler to read another header.  */
-        s->reply.handle = 0;
-    }
-}
-
-static void nbd_coroutine_end(BDRVNBDState *s, struct nbd_request *request)
-{
-    int i = HANDLE_TO_INDEX(s, request->handle);
-    s->recv_coroutine[i] = NULL;
-    if (s->in_flight-- == MAX_NBD_REQUESTS) {
-        qemu_co_mutex_unlock(&s->free_sema);
-    }
-}
-
 static int nbd_establish_connection(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
     int sock;
-    int ret;
-    off_t size;
-    size_t blocksize;
 
-    if (s->is_unix) {
+    if (s->client.is_unix) {
         sock = unix_socket_outgoing(qemu_opt_get(s->socket_opts, "path"));
     } else {
         sock = tcp_socket_outgoing_opts(s->socket_opts);
@@ -417,50 +246,14 @@ static int nbd_establish_connection(BlockDriverState *bs)
         return -errno;
     }
 
-    /* NBD handshake */
-    ret = nbd_receive_negotiate(sock, s->export_name, &s->nbdflags, &size,
-                                &blocksize);
-    if (ret < 0) {
-        logout("Failed to negotiate with the NBD server\n");
-        closesocket(sock);
-        return ret;
-    }
-
-    /* Now that we're connected, set the socket to be non-blocking and
-     * kick the reply mechanism.  */
-    qemu_set_nonblock(sock);
-    qemu_aio_set_fd_handler(sock, nbd_reply_ready, NULL, s);
-
-    s->sock = sock;
-    s->size = size;
-    s->blocksize = blocksize;
-
-    logout("Established connection with NBD server\n");
-    return 0;
-}
-
-static void nbd_teardown_connection(BlockDriverState *bs)
-{
-    BDRVNBDState *s = bs->opaque;
-    struct nbd_request request;
-
-    request.type = NBD_CMD_DISC;
-    request.from = 0;
-    request.len = 0;
-    nbd_send_request(s->sock, &request);
-
-    qemu_aio_set_fd_handler(s->sock, NULL, NULL, NULL);
-    closesocket(s->sock);
+    return sock;
 }
 
 static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
                     Error **errp)
 {
     BDRVNBDState *s = bs->opaque;
-    int result;
-
-    qemu_co_mutex_init(&s->send_mutex);
-    qemu_co_mutex_init(&s->free_sema);
+    int result, sock;
 
     /* Pop the config into our state object. Exit if invalid. */
     result = nbd_config(s, options);
@@ -471,172 +264,62 @@ static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
     /* establish TCP connection, return error if it fails
      * TODO: Configurable retry-until-timeout behaviour.
      */
-    result = nbd_establish_connection(bs);
-
-    return result;
-}
-
-static int nbd_co_readv_1(BlockDriverState *bs, int64_t sector_num,
-                          int nb_sectors, QEMUIOVector *qiov,
-                          int offset)
-{
-    BDRVNBDState *s = bs->opaque;
-    struct nbd_request request;
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    request.type = NBD_CMD_READ;
-    request.from = sector_num * 512;
-    request.len = nb_sectors * 512;
-
-    nbd_coroutine_start(s, &request);
-    ret = nbd_co_send_request(s, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(s, &request, &reply, qiov, offset);
-    }
-    nbd_coroutine_end(s, &request);
-    return -reply.error;
-
-}
-
-static int nbd_co_writev_1(BlockDriverState *bs, int64_t sector_num,
-                           int nb_sectors, QEMUIOVector *qiov,
-                           int offset)
-{
-    BDRVNBDState *s = bs->opaque;
-    struct nbd_request request;
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    request.type = NBD_CMD_WRITE;
-    if (!bdrv_enable_write_cache(bs) && (s->nbdflags & NBD_FLAG_SEND_FUA)) {
-        request.type |= NBD_CMD_FLAG_FUA;
+    sock = nbd_establish_connection(bs);
+    if (sock < 0) {
+        return sock;
     }
 
-    request.from = sector_num * 512;
-    request.len = nb_sectors * 512;
-
-    nbd_coroutine_start(s, &request);
-    ret = nbd_co_send_request(s, &request, qiov, offset);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(s, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(s, &request);
-    return -reply.error;
+    /* NBD handshake */
+    return nbd_client_session_init(&s->client, bs, sock);
 }
 
-/* qemu-nbd has a limit of slightly less than 1M per request.  Try to
- * remain aligned to 4K. */
-#define NBD_MAX_SECTORS 2040
-
 static int nbd_co_readv(BlockDriverState *bs, int64_t sector_num,
                         int nb_sectors, QEMUIOVector *qiov)
 {
-    int offset = 0;
-    int ret;
-    while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_readv_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
-        if (ret < 0) {
-            return ret;
-        }
-        offset += NBD_MAX_SECTORS * 512;
-        sector_num += NBD_MAX_SECTORS;
-        nb_sectors -= NBD_MAX_SECTORS;
-    }
-    return nbd_co_readv_1(bs, sector_num, nb_sectors, qiov, offset);
+    BDRVNBDState *s = bs->opaque;
+
+    return nbd_client_session_co_readv(&s->client, sector_num,
+                                       nb_sectors, qiov);
 }
 
 static int nbd_co_writev(BlockDriverState *bs, int64_t sector_num,
                          int nb_sectors, QEMUIOVector *qiov)
 {
-    int offset = 0;
-    int ret;
-    while (nb_sectors > NBD_MAX_SECTORS) {
-        ret = nbd_co_writev_1(bs, sector_num, NBD_MAX_SECTORS, qiov, offset);
-        if (ret < 0) {
-            return ret;
-        }
-        offset += NBD_MAX_SECTORS * 512;
-        sector_num += NBD_MAX_SECTORS;
-        nb_sectors -= NBD_MAX_SECTORS;
-    }
-    return nbd_co_writev_1(bs, sector_num, nb_sectors, qiov, offset);
+    BDRVNBDState *s = bs->opaque;
+
+    return nbd_client_session_co_writev(&s->client, sector_num,
+                                        nb_sectors, qiov);
 }
 
 static int nbd_co_flush(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
-    struct nbd_request request;
-    struct nbd_reply reply;
-    ssize_t ret;
-
-    if (!(s->nbdflags & NBD_FLAG_SEND_FLUSH)) {
-        return 0;
-    }
 
-    request.type = NBD_CMD_FLUSH;
-    if (s->nbdflags & NBD_FLAG_SEND_FUA) {
-        request.type |= NBD_CMD_FLAG_FUA;
-    }
-
-    request.from = 0;
-    request.len = 0;
-
-    nbd_coroutine_start(s, &request);
-    ret = nbd_co_send_request(s, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(s, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(s, &request);
-    return -reply.error;
+    return nbd_client_session_co_flush(&s->client);
 }
 
 static int nbd_co_discard(BlockDriverState *bs, int64_t sector_num,
                           int nb_sectors)
 {
     BDRVNBDState *s = bs->opaque;
-    struct nbd_request request;
-    struct nbd_reply reply;
-    ssize_t ret;
 
-    if (!(s->nbdflags & NBD_FLAG_SEND_TRIM)) {
-        return 0;
-    }
-    request.type = NBD_CMD_TRIM;
-    request.from = sector_num * 512;
-    request.len = nb_sectors * 512;
-
-    nbd_coroutine_start(s, &request);
-    ret = nbd_co_send_request(s, &request, NULL, 0);
-    if (ret < 0) {
-        reply.error = -ret;
-    } else {
-        nbd_co_receive_reply(s, &request, &reply, NULL, 0);
-    }
-    nbd_coroutine_end(s, &request);
-    return -reply.error;
+    return nbd_client_session_co_discard(&s->client, sector_num,
+                                         nb_sectors);
 }
 
 static void nbd_close(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
-    g_free(s->export_name);
-    qemu_opts_del(s->socket_opts);
 
-    nbd_teardown_connection(bs);
+    qemu_opts_del(s->socket_opts);
+    nbd_client_session_close(&s->client);
 }
 
 static int64_t nbd_getlength(BlockDriverState *bs)
 {
     BDRVNBDState *s = bs->opaque;
 
-    return s->size;
+    return s->client.size;
 }
 
 static BlockDriver bdrv_nbd = {