diff mbox series

[v7,2/8] block/nbd.c: Add yank feature

Message ID 331864b96d198a6cfabd050581e94bc3452362aa.1596528468.git.lukasstraub2@web.de (mailing list archive)
State New, archived
Headers show
Series Introduce 'yank' oob qmp command to recover from hanging qemu | expand

Commit Message

Lukas Straub Aug. 4, 2020, 8:11 a.m. UTC
Register a yank function which shuts down the socket and sets
s->state = NBD_CLIENT_QUIT. This is the same behaviour as if an
error occured.

Signed-off-by: Lukas Straub <lukasstraub2@web.de>
Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
---
 block/nbd.c | 129 ++++++++++++++++++++++++++++++++--------------------
 1 file changed, 80 insertions(+), 49 deletions(-)

--
2.20.1

Comments

Daniel P. Berrangé Aug. 27, 2020, 10:31 a.m. UTC | #1
On Tue, Aug 04, 2020 at 10:11:37AM +0200, Lukas Straub wrote:
> Register a yank function which shuts down the socket and sets
> s->state = NBD_CLIENT_QUIT. This is the same behaviour as if an
> error occured.
> 
> Signed-off-by: Lukas Straub <lukasstraub2@web.de>
> Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
> ---
>  block/nbd.c | 129 ++++++++++++++++++++++++++++++++--------------------
>  1 file changed, 80 insertions(+), 49 deletions(-)

Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>


Regards,
Daniel
diff mbox series

Patch

diff --git a/block/nbd.c b/block/nbd.c
index 7bb881fef4..8632cf5340 100644
--- a/block/nbd.c
+++ b/block/nbd.c
@@ -35,6 +35,7 @@ 
 #include "qemu/option.h"
 #include "qemu/cutils.h"
 #include "qemu/main-loop.h"
+#include "qemu/atomic.h"

 #include "qapi/qapi-visit-sockets.h"
 #include "qapi/qmp/qstring.h"
@@ -43,6 +44,8 @@ 
 #include "block/nbd.h"
 #include "block/block_int.h"

+#include "qemu/yank.h"
+
 #define EN_OPTSTR ":exportname="
 #define MAX_NBD_REQUESTS    16

@@ -84,6 +87,8 @@  typedef struct BDRVNBDState {
     NBDReply reply;
     BlockDriverState *bs;

+    char *yank_name;
+
     /* Connection parameters */
     uint32_t reconnect_delay;
     SocketAddress *saddr;
@@ -93,10 +98,10 @@  typedef struct BDRVNBDState {
     char *x_dirty_bitmap;
 } BDRVNBDState;

-static QIOChannelSocket *nbd_establish_connection(SocketAddress *saddr,
-                                                  Error **errp);
-static int nbd_client_handshake(BlockDriverState *bs, QIOChannelSocket *sioc,
-                                Error **errp);
+static int nbd_establish_connection(BlockDriverState *bs, SocketAddress *saddr,
+                                    Error **errp);
+static int nbd_client_handshake(BlockDriverState *bs, Error **errp);
+static void nbd_yank(void *opaque);

 static void nbd_clear_bdrvstate(BDRVNBDState *s)
 {
@@ -109,17 +114,19 @@  static void nbd_clear_bdrvstate(BDRVNBDState *s)
     s->tlscredsid = NULL;
     g_free(s->x_dirty_bitmap);
     s->x_dirty_bitmap = NULL;
+    g_free(s->yank_name);
+    s->yank_name = NULL;
 }

 static void nbd_channel_error(BDRVNBDState *s, int ret)
 {
     if (ret == -EIO) {
-        if (s->state == NBD_CLIENT_CONNECTED) {
+        if (atomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED) {
             s->state = s->reconnect_delay ? NBD_CLIENT_CONNECTING_WAIT :
                                             NBD_CLIENT_CONNECTING_NOWAIT;
         }
     } else {
-        if (s->state == NBD_CLIENT_CONNECTED) {
+        if (atomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED) {
             qio_channel_shutdown(s->ioc, QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
         }
         s->state = NBD_CLIENT_QUIT;
@@ -170,7 +177,7 @@  static void nbd_client_attach_aio_context(BlockDriverState *bs,
      * s->connection_co is either yielded from nbd_receive_reply or from
      * nbd_co_reconnect_loop()
      */
-    if (s->state == NBD_CLIENT_CONNECTED) {
+    if (atomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED) {
         qio_channel_attach_aio_context(QIO_CHANNEL(s->ioc), new_context);
     }

@@ -237,20 +244,20 @@  static void nbd_teardown_connection(BlockDriverState *bs)

 static bool nbd_client_connecting(BDRVNBDState *s)
 {
-    return s->state == NBD_CLIENT_CONNECTING_WAIT ||
-        s->state == NBD_CLIENT_CONNECTING_NOWAIT;
+    NBDClientState state = atomic_load_acquire(&s->state);
+    return state == NBD_CLIENT_CONNECTING_WAIT ||
+        state == NBD_CLIENT_CONNECTING_NOWAIT;
 }

 static bool nbd_client_connecting_wait(BDRVNBDState *s)
 {
-    return s->state == NBD_CLIENT_CONNECTING_WAIT;
+    return atomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTING_WAIT;
 }

 static coroutine_fn void nbd_reconnect_attempt(BDRVNBDState *s)
 {
     int ret;
     Error *local_err = NULL;
-    QIOChannelSocket *sioc;

     if (!nbd_client_connecting(s)) {
         return;
@@ -283,21 +290,21 @@  static coroutine_fn void nbd_reconnect_attempt(BDRVNBDState *s)
     /* Finalize previous connection if any */
     if (s->ioc) {
         nbd_client_detach_aio_context(s->bs);
+        yank_unregister_function(s->yank_name, nbd_yank, s->bs);
         object_unref(OBJECT(s->sioc));
         s->sioc = NULL;
         object_unref(OBJECT(s->ioc));
         s->ioc = NULL;
     }

-    sioc = nbd_establish_connection(s->saddr, &local_err);
-    if (!sioc) {
+    if (nbd_establish_connection(s->bs, s->saddr, &local_err) < 0) {
         ret = -ECONNREFUSED;
         goto out;
     }

     bdrv_dec_in_flight(s->bs);

-    ret = nbd_client_handshake(s->bs, sioc, &local_err);
+    ret = nbd_client_handshake(s->bs, &local_err);

     if (s->drained) {
         s->wait_drained_end = true;
@@ -334,7 +341,7 @@  static coroutine_fn void nbd_co_reconnect_loop(BDRVNBDState *s)
     nbd_reconnect_attempt(s);

     while (nbd_client_connecting(s)) {
-        if (s->state == NBD_CLIENT_CONNECTING_WAIT &&
+        if (atomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTING_WAIT &&
             qemu_clock_get_ns(QEMU_CLOCK_REALTIME) - start_time_ns > delay_ns)
         {
             s->state = NBD_CLIENT_CONNECTING_NOWAIT;
@@ -371,7 +378,7 @@  static coroutine_fn void nbd_connection_entry(void *opaque)
     int ret = 0;
     Error *local_err = NULL;

-    while (s->state != NBD_CLIENT_QUIT) {
+    while (atomic_load_acquire(&s->state) != NBD_CLIENT_QUIT) {
         /*
          * The NBD client can only really be considered idle when it has
          * yielded from qio_channel_readv_all_eof(), waiting for data. This is
@@ -386,7 +393,7 @@  static coroutine_fn void nbd_connection_entry(void *opaque)
             nbd_co_reconnect_loop(s);
         }

-        if (s->state != NBD_CLIENT_CONNECTED) {
+        if (atomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) {
             continue;
         }

@@ -441,6 +448,7 @@  static coroutine_fn void nbd_connection_entry(void *opaque)
     s->connection_co = NULL;
     if (s->ioc) {
         nbd_client_detach_aio_context(s->bs);
+        yank_unregister_function(s->yank_name, nbd_yank, s->bs);
         object_unref(OBJECT(s->sioc));
         s->sioc = NULL;
         object_unref(OBJECT(s->ioc));
@@ -465,7 +473,7 @@  static int nbd_co_send_request(BlockDriverState *bs,
         qemu_co_queue_wait(&s->free_sema, &s->send_mutex);
     }

-    if (s->state != NBD_CLIENT_CONNECTED) {
+    if (atomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) {
         rc = -EIO;
         goto err;
     }
@@ -492,7 +500,7 @@  static int nbd_co_send_request(BlockDriverState *bs,
     if (qiov) {
         qio_channel_set_cork(s->ioc, true);
         rc = nbd_send_request(s->ioc, request);
-        if (rc >= 0 && s->state == NBD_CLIENT_CONNECTED) {
+        if (rc >= 0 && atomic_load_acquire(&s->state) == NBD_CLIENT_CONNECTED) {
             if (qio_channel_writev_all(s->ioc, qiov->iov, qiov->niov,
                                        NULL) < 0) {
                 rc = -EIO;
@@ -807,7 +815,7 @@  static coroutine_fn int nbd_co_do_receive_one_chunk(
     s->requests[i].receiving = true;
     qemu_coroutine_yield();
     s->requests[i].receiving = false;
-    if (s->state != NBD_CLIENT_CONNECTED) {
+    if (atomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) {
         error_setg(errp, "Connection closed");
         return -EIO;
     }
@@ -966,7 +974,7 @@  static bool nbd_reply_chunk_iter_receive(BDRVNBDState *s,
     NBDReply local_reply;
     NBDStructuredReplyChunk *chunk;
     Error *local_err = NULL;
-    if (s->state != NBD_CLIENT_CONNECTED) {
+    if (atomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) {
         error_setg(&local_err, "Connection closed");
         nbd_iter_channel_error(iter, -EIO, &local_err);
         goto break_loop;
@@ -991,7 +999,8 @@  static bool nbd_reply_chunk_iter_receive(BDRVNBDState *s,
     }

     /* Do not execute the body of NBD_FOREACH_REPLY_CHUNK for simple reply. */
-    if (nbd_reply_is_simple(reply) || s->state != NBD_CLIENT_CONNECTED) {
+    if (nbd_reply_is_simple(reply) ||
+        atomic_load_acquire(&s->state) != NBD_CLIENT_CONNECTED) {
         goto break_loop;
     }

@@ -1423,6 +1432,15 @@  static int nbd_client_reopen_prepare(BDRVReopenState *state,
     return 0;
 }

+static void nbd_yank(void *opaque)
+{
+    BlockDriverState *bs = opaque;
+    BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
+
+    atomic_store_release(&s->state, NBD_CLIENT_QUIT);
+    qio_channel_shutdown(QIO_CHANNEL(s->sioc), QIO_CHANNEL_SHUTDOWN_BOTH, NULL);
+}
+
 static void nbd_client_close(BlockDriverState *bs)
 {
     BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
@@ -1435,52 +1453,53 @@  static void nbd_client_close(BlockDriverState *bs)
     nbd_teardown_connection(bs);
 }

-static QIOChannelSocket *nbd_establish_connection(SocketAddress *saddr,
-                                                  Error **errp)
+static int nbd_establish_connection(BlockDriverState *bs,
+                                    SocketAddress *saddr,
+                                    Error **errp)
 {
     ERRP_GUARD();
-    QIOChannelSocket *sioc;
+    BDRVNBDState *s = (BDRVNBDState *)bs->opaque;

-    sioc = qio_channel_socket_new();
-    qio_channel_set_name(QIO_CHANNEL(sioc), "nbd-client");
+    s->sioc = qio_channel_socket_new();
+    qio_channel_set_name(QIO_CHANNEL(s->sioc), "nbd-client");
+    yank_register_function(s->yank_name, nbd_yank, bs);

-    qio_channel_socket_connect_sync(sioc, saddr, errp);
+    qio_channel_socket_connect_sync(s->sioc, saddr, errp);
     if (*errp) {
-        object_unref(OBJECT(sioc));
-        return NULL;
+        yank_unregister_function(s->yank_name, nbd_yank, bs);
+        object_unref(OBJECT(s->sioc));
+        s->sioc = NULL;
+        return -1;
     }

-    qio_channel_set_delay(QIO_CHANNEL(sioc), false);
+    qio_channel_set_delay(QIO_CHANNEL(s->sioc), false);

-    return sioc;
+    return 0;
 }

-/* nbd_client_handshake takes ownership on sioc. On failure it is unref'ed. */
-static int nbd_client_handshake(BlockDriverState *bs, QIOChannelSocket *sioc,
-                                Error **errp)
+/* nbd_client_handshake takes ownership on s->sioc. On failure it's unref'ed. */
+static int nbd_client_handshake(BlockDriverState *bs, Error **errp)
 {
     BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
     AioContext *aio_context = bdrv_get_aio_context(bs);
     int ret;

     trace_nbd_client_handshake(s->export);
-
-    s->sioc = sioc;
-
-    qio_channel_set_blocking(QIO_CHANNEL(sioc), false, NULL);
-    qio_channel_attach_aio_context(QIO_CHANNEL(sioc), aio_context);
+    qio_channel_set_blocking(QIO_CHANNEL(s->sioc), false, NULL);
+    qio_channel_attach_aio_context(QIO_CHANNEL(s->sioc), aio_context);

     s->info.request_sizes = true;
     s->info.structured_reply = true;
     s->info.base_allocation = true;
     s->info.x_dirty_bitmap = g_strdup(s->x_dirty_bitmap);
     s->info.name = g_strdup(s->export ?: "");
-    ret = nbd_receive_negotiate(aio_context, QIO_CHANNEL(sioc), s->tlscreds,
+    ret = nbd_receive_negotiate(aio_context, QIO_CHANNEL(s->sioc), s->tlscreds,
                                 s->hostname, &s->ioc, &s->info, errp);
     g_free(s->info.x_dirty_bitmap);
     g_free(s->info.name);
     if (ret < 0) {
-        object_unref(OBJECT(sioc));
+        yank_unregister_function(s->yank_name, nbd_yank, bs);
+        object_unref(OBJECT(s->sioc));
         s->sioc = NULL;
         return ret;
     }
@@ -1508,7 +1527,7 @@  static int nbd_client_handshake(BlockDriverState *bs, QIOChannelSocket *sioc,
     }

     if (!s->ioc) {
-        s->ioc = QIO_CHANNEL(sioc);
+        s->ioc = QIO_CHANNEL(s->sioc);
         object_ref(OBJECT(s->ioc));
     }

@@ -1524,9 +1543,10 @@  static int nbd_client_handshake(BlockDriverState *bs, QIOChannelSocket *sioc,
     {
         NBDRequest request = { .type = NBD_CMD_DISC };

-        nbd_send_request(s->ioc ?: QIO_CHANNEL(sioc), &request);
+        nbd_send_request(s->ioc ?: QIO_CHANNEL(s->sioc), &request);

-        object_unref(OBJECT(sioc));
+        yank_unregister_function(s->yank_name, nbd_yank, bs);
+        object_unref(OBJECT(s->sioc));
         s->sioc = NULL;

         return ret;
@@ -1918,7 +1938,6 @@  static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
 {
     int ret;
     BDRVNBDState *s = (BDRVNBDState *)bs->opaque;
-    QIOChannelSocket *sioc;

     ret = nbd_process_options(bs, options, errp);
     if (ret < 0) {
@@ -1929,17 +1948,28 @@  static int nbd_open(BlockDriverState *bs, QDict *options, int flags,
     qemu_co_mutex_init(&s->send_mutex);
     qemu_co_queue_init(&s->free_sema);

+    s->yank_name = g_strconcat("blockdev:", bs->node_name, NULL);
+    yank_register_instance(s->yank_name, errp);
+    if (*errp) {
+        g_free(s->yank_name);
+        s->yank_name = NULL;
+        return -EEXIST;
+    }
+
     /*
      * establish TCP connection, return error if it fails
      * TODO: Configurable retry-until-timeout behaviour.
      */
-    sioc = nbd_establish_connection(s->saddr, errp);
-    if (!sioc) {
+    if (nbd_establish_connection(bs, s->saddr, errp) < 0) {
+        yank_unregister_instance(s->yank_name);
+        g_free(s->yank_name);
+        s->yank_name = NULL;
         return -ECONNREFUSED;
     }

-    ret = nbd_client_handshake(bs, sioc, errp);
+    ret = nbd_client_handshake(bs, errp);
     if (ret < 0) {
+        yank_unregister_instance(s->yank_name);
         nbd_clear_bdrvstate(s);
         return ret;
     }
@@ -1997,6 +2027,7 @@  static void nbd_close(BlockDriverState *bs)
     BDRVNBDState *s = bs->opaque;

     nbd_client_close(bs);
+    yank_unregister_instance(s->yank_name);
     nbd_clear_bdrvstate(s);
 }