qemu-e2k/block/nbd-client.c

402 lines
12 KiB
C
Raw Normal View History

/*
* QEMU Block driver for NBD
*
* Copyright (C) 2008 Bull S.A.S.
* Author: Laurent Vivier <Laurent.Vivier@bull.net>
*
* Some parts:
* Copyright (C) 2007 Anthony Liguori <anthony@codemonkey.ws>
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to deal
* in the Software without restriction, including without limitation the rights
* to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
* copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
* THE SOFTWARE.
*/
#include "qemu/osdep.h"
#include "nbd-client.h"
#define HANDLE_TO_INDEX(bs, handle) ((handle) ^ ((uint64_t)(intptr_t)bs))
#define INDEX_TO_HANDLE(bs, index) ((index) ^ ((uint64_t)(intptr_t)bs))
static void nbd_recv_coroutines_enter_all(NbdClientSession *s)
{
int i;
for (i = 0; i < MAX_NBD_REQUESTS; i++) {
if (s->recv_coroutine[i]) {
qemu_coroutine_enter(s->recv_coroutine[i]);
}
}
}
static void nbd_teardown_connection(BlockDriverState *bs)
{
NbdClientSession *client = nbd_get_client_session(bs);
if (!client->ioc) { /* Already closed */
return;
}
/* finish any pending coroutines */
qio_channel_shutdown(client->ioc,
QIO_CHANNEL_SHUTDOWN_BOTH,
NULL);
nbd_recv_coroutines_enter_all(client);
nbd_client_detach_aio_context(bs);
object_unref(OBJECT(client->sioc));
client->sioc = NULL;
object_unref(OBJECT(client->ioc));
client->ioc = NULL;
}
static void nbd_reply_ready(void *opaque)
{
BlockDriverState *bs = opaque;
NbdClientSession *s = nbd_get_client_session(bs);
uint64_t i;
int ret;
if (!s->ioc) { /* Already closed */
return;
}
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->ioc, &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]);
return;
}
fail:
nbd_teardown_connection(bs);
}
static void nbd_restart_write(void *opaque)
{
BlockDriverState *bs = opaque;
qemu_coroutine_enter(nbd_get_client_session(bs)->send_coroutine);
}
static int nbd_co_send_request(BlockDriverState *bs,
struct nbd_request *request,
QEMUIOVector *qiov)
{
NbdClientSession *s = nbd_get_client_session(bs);
AioContext *aio_context;
nbd: fix the co_queue multi-adding bug When we tested the VM migartion between different hosts with NBD devices, we found if we sent a cancel command after the drive_mirror was just started, a coroutine re-enter error would occur. The stack was as follow: (gdb) bt 00) 0x00007fdfc744d885 in raise () from /lib64/libc.so.6 01) 0x00007fdfc744ee61 in abort () from /lib64/libc.so.6 02) 0x00007fdfca467cc5 in qemu_coroutine_enter (co=0x7fdfcaedb400, opaque=0x0) at qemu-coroutine.c:118 03) 0x00007fdfca467f6c in qemu_co_queue_run_restart (co=0x7fdfcaedb400) at qemu-coroutine-lock.c:59 04) 0x00007fdfca467be5 in coroutine_swap (from=0x7fdfcaf3c4e8, to=0x7fdfcaedb400) at qemu-coroutine.c:96 05) 0x00007fdfca467cea in qemu_coroutine_enter (co=0x7fdfcaedb400, opaque=0x0) at qemu-coroutine.c:123 06) 0x00007fdfca467f6c in qemu_co_queue_run_restart (co=0x7fdfcaedbdc0) at qemu-coroutine-lock.c:59 07) 0x00007fdfca467be5 in coroutine_swap (from=0x7fdfcaf3c4e8, to=0x7fdfcaedbdc0) at qemu-coroutine.c:96 08) 0x00007fdfca467cea in qemu_coroutine_enter (co=0x7fdfcaedbdc0, opaque=0x0) at qemu-coroutine.c:123 09) 0x00007fdfca4a1fa4 in nbd_recv_coroutines_enter_all (s=0x7fdfcaef7dd0) at block/nbd-client.c:41 10) 0x00007fdfca4a1ff9 in nbd_teardown_connection (client=0x7fdfcaef7dd0) at block/nbd-client.c:50 11) 0x00007fdfca4a20f0 in nbd_reply_ready (opaque=0x7fdfcaef7dd0) at block/nbd-client.c:92 12) 0x00007fdfca45ed80 in aio_dispatch (ctx=0x7fdfcae15e90) at aio-posix.c:144 13) 0x00007fdfca45ef1b in aio_poll (ctx=0x7fdfcae15e90, blocking=false) at aio-posix.c:222 14) 0x00007fdfca448c34 in aio_ctx_dispatch (source=0x7fdfcae15e90, callback=0x0, user_data=0x0) at async.c:212 15) 0x00007fdfc8f2f69a in g_main_context_dispatch () from /usr/lib64/libglib-2.0.so.0 16) 0x00007fdfca45c391 in glib_pollfds_poll () at main-loop.c:190 17) 0x00007fdfca45c489 in os_host_main_loop_wait (timeout=1483677098) at main-loop.c:235 18) 0x00007fdfca45c57b in main_loop_wait (nonblocking=0) at main-loop.c:484 19) 0x00007fdfca25f403 in main_loop () at vl.c:2249 20) 0x00007fdfca266fc2 in main (argc=42, argv=0x7ffff517d638, envp=0x7ffff517d790) at vl.c:4814 We find the nbd_recv_coroutines_enter_all function (triggered by a cancel command or a network connection breaking down) will enter a coroutine which is waiting for the sending lock. If the lock is still held by another coroutine, the entering coroutine will be added into the co_queue again. Latter, when the lock is released, a coroutine re-enter error will occur. This bug can be fixed simply by delaying the setting of recv_coroutine as suggested by paolo. After applying this patch, we have tested the cancel operation in mirror phase looply for more than 5 hous and everything is fine. Without this patch, a coroutine re-enter error will occur in 5 minutes. Signed-off-by: Bn Wu <wu.wubin@huawei.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 1423552846-3896-1-git-send-email-wu.wubin@huawei.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2015-02-10 08:20:46 +01:00
int rc, ret, i;
qemu_co_mutex_lock(&s->send_mutex);
nbd: fix the co_queue multi-adding bug When we tested the VM migartion between different hosts with NBD devices, we found if we sent a cancel command after the drive_mirror was just started, a coroutine re-enter error would occur. The stack was as follow: (gdb) bt 00) 0x00007fdfc744d885 in raise () from /lib64/libc.so.6 01) 0x00007fdfc744ee61 in abort () from /lib64/libc.so.6 02) 0x00007fdfca467cc5 in qemu_coroutine_enter (co=0x7fdfcaedb400, opaque=0x0) at qemu-coroutine.c:118 03) 0x00007fdfca467f6c in qemu_co_queue_run_restart (co=0x7fdfcaedb400) at qemu-coroutine-lock.c:59 04) 0x00007fdfca467be5 in coroutine_swap (from=0x7fdfcaf3c4e8, to=0x7fdfcaedb400) at qemu-coroutine.c:96 05) 0x00007fdfca467cea in qemu_coroutine_enter (co=0x7fdfcaedb400, opaque=0x0) at qemu-coroutine.c:123 06) 0x00007fdfca467f6c in qemu_co_queue_run_restart (co=0x7fdfcaedbdc0) at qemu-coroutine-lock.c:59 07) 0x00007fdfca467be5 in coroutine_swap (from=0x7fdfcaf3c4e8, to=0x7fdfcaedbdc0) at qemu-coroutine.c:96 08) 0x00007fdfca467cea in qemu_coroutine_enter (co=0x7fdfcaedbdc0, opaque=0x0) at qemu-coroutine.c:123 09) 0x00007fdfca4a1fa4 in nbd_recv_coroutines_enter_all (s=0x7fdfcaef7dd0) at block/nbd-client.c:41 10) 0x00007fdfca4a1ff9 in nbd_teardown_connection (client=0x7fdfcaef7dd0) at block/nbd-client.c:50 11) 0x00007fdfca4a20f0 in nbd_reply_ready (opaque=0x7fdfcaef7dd0) at block/nbd-client.c:92 12) 0x00007fdfca45ed80 in aio_dispatch (ctx=0x7fdfcae15e90) at aio-posix.c:144 13) 0x00007fdfca45ef1b in aio_poll (ctx=0x7fdfcae15e90, blocking=false) at aio-posix.c:222 14) 0x00007fdfca448c34 in aio_ctx_dispatch (source=0x7fdfcae15e90, callback=0x0, user_data=0x0) at async.c:212 15) 0x00007fdfc8f2f69a in g_main_context_dispatch () from /usr/lib64/libglib-2.0.so.0 16) 0x00007fdfca45c391 in glib_pollfds_poll () at main-loop.c:190 17) 0x00007fdfca45c489 in os_host_main_loop_wait (timeout=1483677098) at main-loop.c:235 18) 0x00007fdfca45c57b in main_loop_wait (nonblocking=0) at main-loop.c:484 19) 0x00007fdfca25f403 in main_loop () at vl.c:2249 20) 0x00007fdfca266fc2 in main (argc=42, argv=0x7ffff517d638, envp=0x7ffff517d790) at vl.c:4814 We find the nbd_recv_coroutines_enter_all function (triggered by a cancel command or a network connection breaking down) will enter a coroutine which is waiting for the sending lock. If the lock is still held by another coroutine, the entering coroutine will be added into the co_queue again. Latter, when the lock is released, a coroutine re-enter error will occur. This bug can be fixed simply by delaying the setting of recv_coroutine as suggested by paolo. After applying this patch, we have tested the cancel operation in mirror phase looply for more than 5 hous and everything is fine. Without this patch, a coroutine re-enter error will occur in 5 minutes. Signed-off-by: Bn Wu <wu.wubin@huawei.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 1423552846-3896-1-git-send-email-wu.wubin@huawei.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2015-02-10 08:20:46 +01:00
for (i = 0; i < MAX_NBD_REQUESTS; i++) {
if (s->recv_coroutine[i] == NULL) {
s->recv_coroutine[i] = qemu_coroutine_self();
break;
}
}
g_assert(qemu_in_coroutine());
nbd: fix the co_queue multi-adding bug When we tested the VM migartion between different hosts with NBD devices, we found if we sent a cancel command after the drive_mirror was just started, a coroutine re-enter error would occur. The stack was as follow: (gdb) bt 00) 0x00007fdfc744d885 in raise () from /lib64/libc.so.6 01) 0x00007fdfc744ee61 in abort () from /lib64/libc.so.6 02) 0x00007fdfca467cc5 in qemu_coroutine_enter (co=0x7fdfcaedb400, opaque=0x0) at qemu-coroutine.c:118 03) 0x00007fdfca467f6c in qemu_co_queue_run_restart (co=0x7fdfcaedb400) at qemu-coroutine-lock.c:59 04) 0x00007fdfca467be5 in coroutine_swap (from=0x7fdfcaf3c4e8, to=0x7fdfcaedb400) at qemu-coroutine.c:96 05) 0x00007fdfca467cea in qemu_coroutine_enter (co=0x7fdfcaedb400, opaque=0x0) at qemu-coroutine.c:123 06) 0x00007fdfca467f6c in qemu_co_queue_run_restart (co=0x7fdfcaedbdc0) at qemu-coroutine-lock.c:59 07) 0x00007fdfca467be5 in coroutine_swap (from=0x7fdfcaf3c4e8, to=0x7fdfcaedbdc0) at qemu-coroutine.c:96 08) 0x00007fdfca467cea in qemu_coroutine_enter (co=0x7fdfcaedbdc0, opaque=0x0) at qemu-coroutine.c:123 09) 0x00007fdfca4a1fa4 in nbd_recv_coroutines_enter_all (s=0x7fdfcaef7dd0) at block/nbd-client.c:41 10) 0x00007fdfca4a1ff9 in nbd_teardown_connection (client=0x7fdfcaef7dd0) at block/nbd-client.c:50 11) 0x00007fdfca4a20f0 in nbd_reply_ready (opaque=0x7fdfcaef7dd0) at block/nbd-client.c:92 12) 0x00007fdfca45ed80 in aio_dispatch (ctx=0x7fdfcae15e90) at aio-posix.c:144 13) 0x00007fdfca45ef1b in aio_poll (ctx=0x7fdfcae15e90, blocking=false) at aio-posix.c:222 14) 0x00007fdfca448c34 in aio_ctx_dispatch (source=0x7fdfcae15e90, callback=0x0, user_data=0x0) at async.c:212 15) 0x00007fdfc8f2f69a in g_main_context_dispatch () from /usr/lib64/libglib-2.0.so.0 16) 0x00007fdfca45c391 in glib_pollfds_poll () at main-loop.c:190 17) 0x00007fdfca45c489 in os_host_main_loop_wait (timeout=1483677098) at main-loop.c:235 18) 0x00007fdfca45c57b in main_loop_wait (nonblocking=0) at main-loop.c:484 19) 0x00007fdfca25f403 in main_loop () at vl.c:2249 20) 0x00007fdfca266fc2 in main (argc=42, argv=0x7ffff517d638, envp=0x7ffff517d790) at vl.c:4814 We find the nbd_recv_coroutines_enter_all function (triggered by a cancel command or a network connection breaking down) will enter a coroutine which is waiting for the sending lock. If the lock is still held by another coroutine, the entering coroutine will be added into the co_queue again. Latter, when the lock is released, a coroutine re-enter error will occur. This bug can be fixed simply by delaying the setting of recv_coroutine as suggested by paolo. After applying this patch, we have tested the cancel operation in mirror phase looply for more than 5 hous and everything is fine. Without this patch, a coroutine re-enter error will occur in 5 minutes. Signed-off-by: Bn Wu <wu.wubin@huawei.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 1423552846-3896-1-git-send-email-wu.wubin@huawei.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2015-02-10 08:20:46 +01:00
assert(i < MAX_NBD_REQUESTS);
request->handle = INDEX_TO_HANDLE(s, i);
if (!s->ioc) {
qemu_co_mutex_unlock(&s->send_mutex);
return -EPIPE;
}
s->send_coroutine = qemu_coroutine_self();
aio_context = bdrv_get_aio_context(bs);
nbd: fix the co_queue multi-adding bug When we tested the VM migartion between different hosts with NBD devices, we found if we sent a cancel command after the drive_mirror was just started, a coroutine re-enter error would occur. The stack was as follow: (gdb) bt 00) 0x00007fdfc744d885 in raise () from /lib64/libc.so.6 01) 0x00007fdfc744ee61 in abort () from /lib64/libc.so.6 02) 0x00007fdfca467cc5 in qemu_coroutine_enter (co=0x7fdfcaedb400, opaque=0x0) at qemu-coroutine.c:118 03) 0x00007fdfca467f6c in qemu_co_queue_run_restart (co=0x7fdfcaedb400) at qemu-coroutine-lock.c:59 04) 0x00007fdfca467be5 in coroutine_swap (from=0x7fdfcaf3c4e8, to=0x7fdfcaedb400) at qemu-coroutine.c:96 05) 0x00007fdfca467cea in qemu_coroutine_enter (co=0x7fdfcaedb400, opaque=0x0) at qemu-coroutine.c:123 06) 0x00007fdfca467f6c in qemu_co_queue_run_restart (co=0x7fdfcaedbdc0) at qemu-coroutine-lock.c:59 07) 0x00007fdfca467be5 in coroutine_swap (from=0x7fdfcaf3c4e8, to=0x7fdfcaedbdc0) at qemu-coroutine.c:96 08) 0x00007fdfca467cea in qemu_coroutine_enter (co=0x7fdfcaedbdc0, opaque=0x0) at qemu-coroutine.c:123 09) 0x00007fdfca4a1fa4 in nbd_recv_coroutines_enter_all (s=0x7fdfcaef7dd0) at block/nbd-client.c:41 10) 0x00007fdfca4a1ff9 in nbd_teardown_connection (client=0x7fdfcaef7dd0) at block/nbd-client.c:50 11) 0x00007fdfca4a20f0 in nbd_reply_ready (opaque=0x7fdfcaef7dd0) at block/nbd-client.c:92 12) 0x00007fdfca45ed80 in aio_dispatch (ctx=0x7fdfcae15e90) at aio-posix.c:144 13) 0x00007fdfca45ef1b in aio_poll (ctx=0x7fdfcae15e90, blocking=false) at aio-posix.c:222 14) 0x00007fdfca448c34 in aio_ctx_dispatch (source=0x7fdfcae15e90, callback=0x0, user_data=0x0) at async.c:212 15) 0x00007fdfc8f2f69a in g_main_context_dispatch () from /usr/lib64/libglib-2.0.so.0 16) 0x00007fdfca45c391 in glib_pollfds_poll () at main-loop.c:190 17) 0x00007fdfca45c489 in os_host_main_loop_wait (timeout=1483677098) at main-loop.c:235 18) 0x00007fdfca45c57b in main_loop_wait (nonblocking=0) at main-loop.c:484 19) 0x00007fdfca25f403 in main_loop () at vl.c:2249 20) 0x00007fdfca266fc2 in main (argc=42, argv=0x7ffff517d638, envp=0x7ffff517d790) at vl.c:4814 We find the nbd_recv_coroutines_enter_all function (triggered by a cancel command or a network connection breaking down) will enter a coroutine which is waiting for the sending lock. If the lock is still held by another coroutine, the entering coroutine will be added into the co_queue again. Latter, when the lock is released, a coroutine re-enter error will occur. This bug can be fixed simply by delaying the setting of recv_coroutine as suggested by paolo. After applying this patch, we have tested the cancel operation in mirror phase looply for more than 5 hous and everything is fine. Without this patch, a coroutine re-enter error will occur in 5 minutes. Signed-off-by: Bn Wu <wu.wubin@huawei.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 1423552846-3896-1-git-send-email-wu.wubin@huawei.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2015-02-10 08:20:46 +01:00
aio_set_fd_handler(aio_context, s->sioc->fd, false,
nbd_reply_ready, nbd_restart_write, bs);
if (qiov) {
qio_channel_set_cork(s->ioc, true);
rc = nbd_send_request(s->ioc, request);
if (rc >= 0) {
ret = nbd_wr_syncv(s->ioc, qiov->iov, qiov->niov, request->len,
false);
if (ret != request->len) {
rc = -EIO;
}
}
qio_channel_set_cork(s->ioc, false);
} else {
rc = nbd_send_request(s->ioc, request);
}
aio_set_fd_handler(aio_context, s->sioc->fd, false,
nbd_reply_ready, NULL, bs);
s->send_coroutine = NULL;
qemu_co_mutex_unlock(&s->send_mutex);
return rc;
}
static void nbd_co_receive_reply(NbdClientSession *s,
struct nbd_request *request,
struct nbd_reply *reply,
QEMUIOVector *qiov)
{
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 ||
!s->ioc) {
reply->error = EIO;
} else {
if (qiov && reply->error == 0) {
ret = nbd_wr_syncv(s->ioc, qiov->iov, qiov->niov, request->len,
true);
if (ret != request->len) {
reply->error = EIO;
}
}
/* Tell the read handler to read another header. */
s->reply.handle = 0;
}
}
static void nbd_coroutine_start(NbdClientSession *s,
struct nbd_request *request)
{
/* 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++;
nbd: fix the co_queue multi-adding bug When we tested the VM migartion between different hosts with NBD devices, we found if we sent a cancel command after the drive_mirror was just started, a coroutine re-enter error would occur. The stack was as follow: (gdb) bt 00) 0x00007fdfc744d885 in raise () from /lib64/libc.so.6 01) 0x00007fdfc744ee61 in abort () from /lib64/libc.so.6 02) 0x00007fdfca467cc5 in qemu_coroutine_enter (co=0x7fdfcaedb400, opaque=0x0) at qemu-coroutine.c:118 03) 0x00007fdfca467f6c in qemu_co_queue_run_restart (co=0x7fdfcaedb400) at qemu-coroutine-lock.c:59 04) 0x00007fdfca467be5 in coroutine_swap (from=0x7fdfcaf3c4e8, to=0x7fdfcaedb400) at qemu-coroutine.c:96 05) 0x00007fdfca467cea in qemu_coroutine_enter (co=0x7fdfcaedb400, opaque=0x0) at qemu-coroutine.c:123 06) 0x00007fdfca467f6c in qemu_co_queue_run_restart (co=0x7fdfcaedbdc0) at qemu-coroutine-lock.c:59 07) 0x00007fdfca467be5 in coroutine_swap (from=0x7fdfcaf3c4e8, to=0x7fdfcaedbdc0) at qemu-coroutine.c:96 08) 0x00007fdfca467cea in qemu_coroutine_enter (co=0x7fdfcaedbdc0, opaque=0x0) at qemu-coroutine.c:123 09) 0x00007fdfca4a1fa4 in nbd_recv_coroutines_enter_all (s=0x7fdfcaef7dd0) at block/nbd-client.c:41 10) 0x00007fdfca4a1ff9 in nbd_teardown_connection (client=0x7fdfcaef7dd0) at block/nbd-client.c:50 11) 0x00007fdfca4a20f0 in nbd_reply_ready (opaque=0x7fdfcaef7dd0) at block/nbd-client.c:92 12) 0x00007fdfca45ed80 in aio_dispatch (ctx=0x7fdfcae15e90) at aio-posix.c:144 13) 0x00007fdfca45ef1b in aio_poll (ctx=0x7fdfcae15e90, blocking=false) at aio-posix.c:222 14) 0x00007fdfca448c34 in aio_ctx_dispatch (source=0x7fdfcae15e90, callback=0x0, user_data=0x0) at async.c:212 15) 0x00007fdfc8f2f69a in g_main_context_dispatch () from /usr/lib64/libglib-2.0.so.0 16) 0x00007fdfca45c391 in glib_pollfds_poll () at main-loop.c:190 17) 0x00007fdfca45c489 in os_host_main_loop_wait (timeout=1483677098) at main-loop.c:235 18) 0x00007fdfca45c57b in main_loop_wait (nonblocking=0) at main-loop.c:484 19) 0x00007fdfca25f403 in main_loop () at vl.c:2249 20) 0x00007fdfca266fc2 in main (argc=42, argv=0x7ffff517d638, envp=0x7ffff517d790) at vl.c:4814 We find the nbd_recv_coroutines_enter_all function (triggered by a cancel command or a network connection breaking down) will enter a coroutine which is waiting for the sending lock. If the lock is still held by another coroutine, the entering coroutine will be added into the co_queue again. Latter, when the lock is released, a coroutine re-enter error will occur. This bug can be fixed simply by delaying the setting of recv_coroutine as suggested by paolo. After applying this patch, we have tested the cancel operation in mirror phase looply for more than 5 hous and everything is fine. Without this patch, a coroutine re-enter error will occur in 5 minutes. Signed-off-by: Bn Wu <wu.wubin@huawei.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 1423552846-3896-1-git-send-email-wu.wubin@huawei.com Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
2015-02-10 08:20:46 +01:00
/* s->recv_coroutine[i] is set as soon as we get the send_lock. */
}
static void nbd_coroutine_end(NbdClientSession *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);
}
}
int nbd_client_co_readv(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, QEMUIOVector *qiov)
{
NbdClientSession *client = nbd_get_client_session(bs);
struct nbd_request request = { .type = NBD_CMD_READ };
struct nbd_reply reply;
ssize_t ret;
assert(nb_sectors <= NBD_MAX_SECTORS);
request.from = sector_num * 512;
request.len = nb_sectors * 512;
nbd_coroutine_start(client, &request);
ret = nbd_co_send_request(bs, &request, NULL);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, qiov);
}
nbd_coroutine_end(client, &request);
return -reply.error;
}
int nbd_client_co_writev(BlockDriverState *bs, int64_t sector_num,
int nb_sectors, QEMUIOVector *qiov, int flags)
{
NbdClientSession *client = nbd_get_client_session(bs);
struct nbd_request request = { .type = NBD_CMD_WRITE };
struct nbd_reply reply;
ssize_t ret;
if (flags & BDRV_REQ_FUA) {
assert(client->nbdflags & NBD_FLAG_SEND_FUA);
request.type |= NBD_CMD_FLAG_FUA;
}
assert(nb_sectors <= NBD_MAX_SECTORS);
request.from = sector_num * 512;
request.len = nb_sectors * 512;
nbd_coroutine_start(client, &request);
ret = nbd_co_send_request(bs, &request, qiov);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, NULL);
}
nbd_coroutine_end(client, &request);
return -reply.error;
}
int nbd_client_co_flush(BlockDriverState *bs)
{
NbdClientSession *client = nbd_get_client_session(bs);
struct nbd_request request = { .type = NBD_CMD_FLUSH };
struct nbd_reply reply;
ssize_t ret;
if (!(client->nbdflags & NBD_FLAG_SEND_FLUSH)) {
return 0;
}
request.from = 0;
request.len = 0;
nbd_coroutine_start(client, &request);
ret = nbd_co_send_request(bs, &request, NULL);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, NULL);
}
nbd_coroutine_end(client, &request);
return -reply.error;
}
int nbd_client_co_discard(BlockDriverState *bs, int64_t sector_num,
int nb_sectors)
{
NbdClientSession *client = nbd_get_client_session(bs);
struct nbd_request request = { .type = NBD_CMD_TRIM };
struct nbd_reply reply;
ssize_t ret;
if (!(client->nbdflags & NBD_FLAG_SEND_TRIM)) {
return 0;
}
request.from = sector_num * 512;
request.len = nb_sectors * 512;
nbd_coroutine_start(client, &request);
ret = nbd_co_send_request(bs, &request, NULL);
if (ret < 0) {
reply.error = -ret;
} else {
nbd_co_receive_reply(client, &request, &reply, NULL);
}
nbd_coroutine_end(client, &request);
return -reply.error;
}
void nbd_client_detach_aio_context(BlockDriverState *bs)
{
aio_set_fd_handler(bdrv_get_aio_context(bs),
nbd_get_client_session(bs)->sioc->fd,
false, NULL, NULL, NULL);
}
void nbd_client_attach_aio_context(BlockDriverState *bs,
AioContext *new_context)
{
aio_set_fd_handler(new_context, nbd_get_client_session(bs)->sioc->fd,
false, nbd_reply_ready, NULL, bs);
}
void nbd_client_close(BlockDriverState *bs)
{
NbdClientSession *client = nbd_get_client_session(bs);
struct nbd_request request = {
.type = NBD_CMD_DISC,
.from = 0,
.len = 0
};
if (client->ioc == NULL) {
return;
}
nbd_send_request(client->ioc, &request);
nbd_teardown_connection(bs);
}
int nbd_client_init(BlockDriverState *bs,
QIOChannelSocket *sioc,
const char *export,
QCryptoTLSCreds *tlscreds,
const char *hostname,
Error **errp)
{
NbdClientSession *client = nbd_get_client_session(bs);
int ret;
/* NBD handshake */
logout("session init %s\n", export);
qio_channel_set_blocking(QIO_CHANNEL(sioc), true, NULL);
ret = nbd_receive_negotiate(QIO_CHANNEL(sioc), export,
&client->nbdflags,
tlscreds, hostname,
&client->ioc,
&client->size, errp);
if (ret < 0) {
logout("Failed to negotiate with the NBD server\n");
return ret;
}
if (client->nbdflags & NBD_FLAG_SEND_FUA) {
bs->supported_write_flags = BDRV_REQ_FUA;
}
qemu_co_mutex_init(&client->send_mutex);
qemu_co_mutex_init(&client->free_sema);
client->sioc = sioc;
object_ref(OBJECT(client->sioc));
if (!client->ioc) {
client->ioc = QIO_CHANNEL(sioc);
object_ref(OBJECT(client->ioc));
}
/* Now that we're connected, set the socket to be non-blocking and
* kick the reply mechanism. */
qio_channel_set_blocking(QIO_CHANNEL(sioc), false, NULL);
nbd_client_attach_aio_context(bs, bdrv_get_aio_context(bs));
logout("Established connection with NBD server\n");
return 0;
}