From 2c94e2714c728354d2924c04dec97f12e31742ad Mon Sep 17 00:00:00 2001 From: Kashyap Chamarthy Date: Tue, 29 Aug 2017 18:50:58 +0200 Subject: [PATCH 01/11] qemu-iotests: Extend non-shared storage migration test (194) This is the follow-up patch that was discussed[*] as part of feedback to qemu-iotest 194. Changes in this patch: - Supply 'job-id' parameter to `drive-mirror` invocation. - Once migration completes, issue QMP `block-job-cancel` command on the source QEMU to gracefully complete `drive-mirror` operation. - Once the BLOCK_JOB_COMPLETED event is emitted, stop the NBD server on the destination QEMU. - Check for both the events: MIGRATION and BLOCK_JOB_COMPLETED. With the above, the test will also be (almost) in sync with the procedure outlined in the document 'live-block-operations.rst'[+] (section: "QMP invocation for live storage migration with ``drive-mirror`` + NBD"). [*] https://lists.nongnu.org/archive/html/qemu-devel/2017-08/msg04820.html -- qemu-iotests: add 194 non-shared storage migration test [+] https://git.qemu.org/gitweb.cgi?p=qemu.git;a=blob;f=docs/interop/live-block-operations.rst Signed-off-by: Kashyap Chamarthy Message-Id: <20170829165058.8229-1-kchamart@redhat.com> Reviewed-by: Stefan Hajnoczi Signed-off-by: Eric Blake --- tests/qemu-iotests/194 | 23 +++++++++++++++++------ tests/qemu-iotests/194.out | 11 ++++++++--- 2 files changed, 25 insertions(+), 9 deletions(-) diff --git a/tests/qemu-iotests/194 b/tests/qemu-iotests/194 index 8028111e21..a3e3bad664 100755 --- a/tests/qemu-iotests/194 +++ b/tests/qemu-iotests/194 @@ -46,16 +46,17 @@ iotests.log('Launching NBD server on destination...') iotests.log(dest_vm.qmp('nbd-server-start', addr={'type': 'unix', 'data': {'path': nbd_sock_path}})) iotests.log(dest_vm.qmp('nbd-server-add', device='drive0', writable=True)) -iotests.log('Starting drive-mirror on source...') +iotests.log('Starting `drive-mirror` on source...') iotests.log(source_vm.qmp( 'drive-mirror', device='drive0', target='nbd+unix:///drive0?socket={0}'.format(nbd_sock_path), sync='full', format='raw', # always raw, the server handles the format - mode='existing')) + mode='existing', + job_id='mirror-job0')) -iotests.log('Waiting for drive-mirror to complete...') +iotests.log('Waiting for `drive-mirror` to complete...') iotests.log(source_vm.event_wait('BLOCK_JOB_READY'), filters=[iotests.filter_qmp_event]) @@ -67,7 +68,17 @@ dest_vm.qmp('migrate-set-capabilities', iotests.log(source_vm.qmp('migrate', uri='unix:{0}'.format(migration_sock_path))) while True: - event = source_vm.event_wait('MIGRATION') - iotests.log(event, filters=[iotests.filter_qmp_event]) - if event['data']['status'] in ('completed', 'failed'): + event1 = source_vm.event_wait('MIGRATION') + iotests.log(event1, filters=[iotests.filter_qmp_event]) + if event1['data']['status'] in ('completed', 'failed'): + iotests.log('Gracefully ending the `drive-mirror` job on source...') + iotests.log(source_vm.qmp('block-job-cancel', device='mirror-job0')) + break + +while True: + event2 = source_vm.event_wait('BLOCK_JOB_COMPLETED') + iotests.log(event2, filters=[iotests.filter_qmp_event]) + if event2['event'] == 'BLOCK_JOB_COMPLETED': + iotests.log('Stopping the NBD server on destination...') + iotests.log(dest_vm.qmp('nbd-server-stop')) break diff --git a/tests/qemu-iotests/194.out b/tests/qemu-iotests/194.out index ae501fecac..50ac50da5e 100644 --- a/tests/qemu-iotests/194.out +++ b/tests/qemu-iotests/194.out @@ -2,12 +2,17 @@ Launching VMs... Launching NBD server on destination... {u'return': {}} {u'return': {}} -Starting drive-mirror on source... +Starting `drive-mirror` on source... {u'return': {}} -Waiting for drive-mirror to complete... -{u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'device': u'drive0', u'type': u'mirror', u'speed': 0, u'len': 1073741824, u'offset': 1073741824}, u'event': u'BLOCK_JOB_READY'} +Waiting for `drive-mirror` to complete... +{u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'device': u'mirror-job0', u'type': u'mirror', u'speed': 0, u'len': 1073741824, u'offset': 1073741824}, u'event': u'BLOCK_JOB_READY'} Starting migration... {u'return': {}} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'setup'}, u'event': u'MIGRATION'} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'active'}, u'event': u'MIGRATION'} {u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'status': u'completed'}, u'event': u'MIGRATION'} +Gracefully ending the `drive-mirror` job on source... +{u'return': {}} +{u'timestamp': {u'seconds': 'SECS', u'microseconds': 'USECS'}, u'data': {u'device': u'mirror-job0', u'type': u'mirror', u'speed': 0, u'len': 1073741824, u'offset': 1073741824}, u'event': u'BLOCK_JOB_COMPLETED'} +Stopping the NBD server on destination... +{u'return': {}} From 3c2d5183f9fa4eac3d17d841e26da65a0181ae7b Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Tue, 29 Aug 2017 13:27:43 +0100 Subject: [PATCH 02/11] nbd-client: avoid read_reply_co entry if send failed The following segfault is encountered if the NBD server closes the UNIX domain socket immediately after negotiation: Program terminated with signal SIGSEGV, Segmentation fault. #0 aio_co_schedule (ctx=0x0, co=0xd3c0ff2ef0) at util/async.c:441 441 QSLIST_INSERT_HEAD_ATOMIC(&ctx->scheduled_coroutines, (gdb) bt #0 0x000000d3c01a50f8 in aio_co_schedule (ctx=0x0, co=0xd3c0ff2ef0) at util/async.c:441 #1 0x000000d3c012fa90 in nbd_coroutine_end (bs=bs@entry=0xd3c0fec650, request=) at block/nbd-client.c:207 #2 0x000000d3c012fb58 in nbd_client_co_preadv (bs=0xd3c0fec650, offset=0, bytes=, qiov=0x7ffc10a91b20, flags=0) at block/nbd-client.c:237 #3 0x000000d3c0128e63 in bdrv_driver_preadv (bs=bs@entry=0xd3c0fec650, offset=offset@entry=0, bytes=bytes@entry=512, qiov=qiov@entry=0x7ffc10a91b20, flags=0) at block/io.c:836 #4 0x000000d3c012c3e0 in bdrv_aligned_preadv (child=child@entry=0xd3c0ff51d0, req=req@entry=0x7f31885d6e90, offset=offset@entry=0, bytes=bytes@entry=512, align=align@entry=1, qiov=qiov@entry=0x7ffc10a91b20, f +lags=0) at block/io.c:1086 #5 0x000000d3c012c6b8 in bdrv_co_preadv (child=0xd3c0ff51d0, offset=offset@entry=0, bytes=bytes@entry=512, qiov=qiov@entry=0x7ffc10a91b20, flags=flags@entry=0) at block/io.c:1182 #6 0x000000d3c011cc17 in blk_co_preadv (blk=0xd3c0ff4f80, offset=0, bytes=512, qiov=0x7ffc10a91b20, flags=0) at block/block-backend.c:1032 #7 0x000000d3c011ccec in blk_read_entry (opaque=0x7ffc10a91b40) at block/block-backend.c:1079 #8 0x000000d3c01bbb96 in coroutine_trampoline (i0=, i1=) at util/coroutine-ucontext.c:79 #9 0x00007f3196cb8600 in __start_context () at /lib64/libc.so.6 The problem is that nbd_client_init() uses nbd_client_attach_aio_context() -> aio_co_schedule(new_context, client->read_reply_co). Execution of read_reply_co is deferred to a BH which doesn't run until later. In the mean time blk_co_preadv() can be called and nbd_coroutine_end() calls aio_wake() on read_reply_co. At this point in time read_reply_co's ctx isn't set because it has never been entered yet. This patch simplifies the nbd_co_send_request() -> nbd_co_receive_reply() -> nbd_coroutine_end() lifecycle to just nbd_co_send_request() -> nbd_co_receive_reply(). The request is "ended" if an error occurs at any point. Callers no longer have to invoke nbd_coroutine_end(). This cleanup also eliminates the segfault because we don't call aio_co_schedule() to wake up s->read_reply_co if sending the request failed. It is only necessary to wake up s->read_reply_co if a reply was received. Note this only happens with UNIX domain sockets on Linux. It doesn't seem possible to reproduce this with TCP sockets. Suggested-by: Paolo Bonzini Signed-off-by: Stefan Hajnoczi Message-Id: <20170829122745.14309-2-stefanha@redhat.com> Signed-off-by: Eric Blake --- block/nbd-client.c | 25 +++++++++---------------- 1 file changed, 9 insertions(+), 16 deletions(-) diff --git a/block/nbd-client.c b/block/nbd-client.c index 25bcaa2346..ea728fffc8 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -144,12 +144,12 @@ static int nbd_co_send_request(BlockDriverState *bs, request->handle = INDEX_TO_HANDLE(s, i); if (s->quit) { - qemu_co_mutex_unlock(&s->send_mutex); - return -EIO; + rc = -EIO; + goto err; } if (!s->ioc) { - qemu_co_mutex_unlock(&s->send_mutex); - return -EPIPE; + rc = -EPIPE; + goto err; } if (qiov) { @@ -166,8 +166,13 @@ static int nbd_co_send_request(BlockDriverState *bs, } else { rc = nbd_send_request(s->ioc, request); } + +err: if (rc < 0) { s->quit = true; + s->requests[i].coroutine = NULL; + s->in_flight--; + qemu_co_queue_next(&s->free_sema); } qemu_co_mutex_unlock(&s->send_mutex); return rc; @@ -201,13 +206,6 @@ static void nbd_co_receive_reply(NBDClientSession *s, /* Tell the read handler to read another header. */ s->reply.handle = 0; } -} - -static void nbd_coroutine_end(BlockDriverState *bs, - NBDRequest *request) -{ - NBDClientSession *s = nbd_get_client_session(bs); - int i = HANDLE_TO_INDEX(s, request->handle); s->requests[i].coroutine = NULL; @@ -243,7 +241,6 @@ int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset, } else { nbd_co_receive_reply(client, &request, &reply, qiov); } - nbd_coroutine_end(bs, &request); return -reply.error; } @@ -272,7 +269,6 @@ int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset, } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(bs, &request); return -reply.error; } @@ -306,7 +302,6 @@ int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(bs, &request); return -reply.error; } @@ -330,7 +325,6 @@ int nbd_client_co_flush(BlockDriverState *bs) } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(bs, &request); return -reply.error; } @@ -355,7 +349,6 @@ int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes) } else { nbd_co_receive_reply(client, &request, &reply, NULL); } - nbd_coroutine_end(bs, &request); return -reply.error; } From 6e592fc92234a58c7156c385840633c17dedd24f Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Tue, 29 Aug 2017 13:27:44 +0100 Subject: [PATCH 03/11] qemu-iotests: improve nbd-fault-injector.py startup protocol Currently 083 waits for the nbd-fault-injector.py server to start up by looping until netstat shows the TCP listen socket. The startup protocol can be simplified by passing a 0 port number to nbd-fault-injector.py. The kernel will allocate a port in bind(2) and the final port number can be printed by nbd-fault-injector.py. This should make it slightly nicer and less TCP-specific to wait for server startup. This patch changes nbd-fault-injector.py, the next one will rewrite server startup in 083. Reviewed-by: Eric Blake Signed-off-by: Stefan Hajnoczi Message-Id: <20170829122745.14309-3-stefanha@redhat.com> Signed-off-by: Eric Blake --- tests/qemu-iotests/nbd-fault-injector.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/tests/qemu-iotests/nbd-fault-injector.py b/tests/qemu-iotests/nbd-fault-injector.py index 6c07191a5a..1c10dcb51c 100755 --- a/tests/qemu-iotests/nbd-fault-injector.py +++ b/tests/qemu-iotests/nbd-fault-injector.py @@ -235,11 +235,15 @@ def open_socket(path): sock = socket.socket() sock.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1) sock.bind((host, int(port))) + + # If given port was 0 the final port number is now available + path = '%s:%d' % sock.getsockname() else: sock = socket.socket(socket.AF_UNIX) sock.bind(path) sock.listen(0) print 'Listening on %s' % path + sys.stdout.flush() # another process may be waiting, show message now return sock def usage(args): From 02d2d860d25e439f0e88658c701668ab684568fb Mon Sep 17 00:00:00 2001 From: Stefan Hajnoczi Date: Tue, 29 Aug 2017 13:27:45 +0100 Subject: [PATCH 04/11] qemu-iotests: test NBD over UNIX domain sockets in 083 083 only tests TCP. Some failures might be specific to UNIX domain sockets. A few adjustments are necessary: 1. Generating a port number and waiting for server startup is TCP-specific. Use the new nbd-fault-injector.py startup protocol to fetch the address. This is a little more elegant because we don't need netstat anymore. 2. The NBD filter does not work for the UNIX domain sockets URIs we generate and must be extended. 3. Run all tests twice: once for TCP and once for UNIX domain sockets. Reviewed-by: Eric Blake Signed-off-by: Stefan Hajnoczi Message-Id: <20170829122745.14309-4-stefanha@redhat.com> Signed-off-by: Eric Blake --- tests/qemu-iotests/083 | 138 ++++++++++++++++++----------- tests/qemu-iotests/083.out | 145 +++++++++++++++++++++++++++---- tests/qemu-iotests/common.filter | 4 +- 3 files changed, 215 insertions(+), 72 deletions(-) diff --git a/tests/qemu-iotests/083 b/tests/qemu-iotests/083 index bff9360048..0306f112da 100755 --- a/tests/qemu-iotests/083 +++ b/tests/qemu-iotests/083 @@ -27,6 +27,14 @@ echo "QA output created by $seq" here=`pwd` status=1 # failure is the default! +_cleanup() +{ + rm -f nbd.sock + rm -f nbd-fault-injector.out + rm -f nbd-fault-injector.conf +} +trap "_cleanup; exit \$status" 0 1 2 3 15 + # get standard environment, filters and checks . ./common.rc . ./common.filter @@ -35,81 +43,105 @@ _supported_fmt generic _supported_proto nbd _supported_os Linux -# Pick a TCP port based on our pid. This way multiple instances of this test -# can run in parallel without conflicting. -choose_tcp_port() { - echo $((($$ % 31744) + 1024)) # 1024 <= port < 32768 -} - -wait_for_tcp_port() { - while ! (netstat --tcp --listening --numeric | \ - grep "$1.*0\\.0\\.0\\.0:\\*.*LISTEN") >/dev/null 2>&1; do - sleep 0.1 - done -} - check_disconnect() { + local event export_name=foo extra_args nbd_addr nbd_url proto when + + while true; do + case $1 in + --classic-negotiation) + shift + extra_args=--classic-negotiation + export_name= + ;; + --tcp) + shift + proto=tcp + ;; + --unix) + shift + proto=unix + ;; + *) + break + ;; + esac + done + event=$1 when=$2 - negotiation=$3 echo "=== Check disconnect $when $event ===" echo - port=$(choose_tcp_port) - cat > "$TEST_DIR/nbd-fault-injector.conf" <"$TEST_DIR/nbd-fault-injector.out" 2>&1 & + + # Wait for server to be ready + while ! grep -q 'Listening on ' "$TEST_DIR/nbd-fault-injector.out"; do + sleep 0.1 + done + + # Extract the final address (port number has now been assigned in tcp case) + nbd_addr=$(sed 's/Listening on \(.*\)$/\1/' "$TEST_DIR/nbd-fault-injector.out") + + if [ "$proto" = "tcp" ]; then + nbd_url="nbd+tcp://$nbd_addr/$export_name" + else + nbd_url="nbd+unix:///$export_name?socket=$nbd_addr" fi - $PYTHON nbd-fault-injector.py $extra_args "127.0.0.1:$port" "$TEST_DIR/nbd-fault-injector.conf" >/dev/null 2>&1 & - wait_for_tcp_port "127\\.0\\.0\\.1:$port" $QEMU_IO -c "read 0 512" "$nbd_url" 2>&1 | _filter_qemu_io | _filter_nbd echo } -for event in neg1 "export" neg2 request reply data; do - for when in before after; do - check_disconnect "$event" "$when" +for proto in tcp unix; do + for event in neg1 "export" neg2 request reply data; do + for when in before after; do + check_disconnect "--$proto" "$event" "$when" + done + + # Also inject short replies from the NBD server + case "$event" in + neg1) + for when in 8 16; do + check_disconnect "--$proto" "$event" "$when" + done + ;; + "export") + for when in 4 12 16; do + check_disconnect "--$proto" "$event" "$when" + done + ;; + neg2) + for when in 8 10; do + check_disconnect "--$proto" "$event" "$when" + done + ;; + reply) + for when in 4 8; do + check_disconnect "--$proto" "$event" "$when" + done + ;; + esac done - # Also inject short replies from the NBD server - case "$event" in - neg1) - for when in 8 16; do - check_disconnect "$event" "$when" - done - ;; - "export") - for when in 4 12 16; do - check_disconnect "$event" "$when" - done - ;; - neg2) - for when in 8 10; do - check_disconnect "$event" "$when" - done - ;; - reply) - for when in 4 8; do - check_disconnect "$event" "$when" - done - ;; - esac -done - -# Also check classic negotiation without export information -for when in before 8 16 24 28 after; do - check_disconnect "neg-classic" "$when" --classic-negotiation + # Also check classic negotiation without export information + for when in before 8 16 24 28 after; do + check_disconnect "--$proto" --classic-negotiation "neg-classic" "$when" + done done # success, all done diff --git a/tests/qemu-iotests/083.out b/tests/qemu-iotests/083.out index a24c6bfece..a7fb081889 100644 --- a/tests/qemu-iotests/083.out +++ b/tests/qemu-iotests/083.out @@ -1,43 +1,43 @@ QA output created by 083 === Check disconnect before neg1 === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect after neg1 === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect 8 neg1 === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect 16 neg1 === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect before export === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect after export === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect 4 export === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect 12 export === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect 16 export === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect before neg2 === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect after neg2 === @@ -45,11 +45,11 @@ read failed: Input/output error === Check disconnect 8 neg2 === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect 10 neg2 === -can't open device nbd:127.0.0.1:PORT:exportname=foo +can't open device nbd+tcp://127.0.0.1:PORT/foo === Check disconnect before request === @@ -88,23 +88,134 @@ read 512/512 bytes at offset 0 === Check disconnect before neg-classic === -can't open device nbd:127.0.0.1:PORT +can't open device nbd+tcp://127.0.0.1:PORT/ === Check disconnect 8 neg-classic === -can't open device nbd:127.0.0.1:PORT +can't open device nbd+tcp://127.0.0.1:PORT/ === Check disconnect 16 neg-classic === -can't open device nbd:127.0.0.1:PORT +can't open device nbd+tcp://127.0.0.1:PORT/ === Check disconnect 24 neg-classic === -can't open device nbd:127.0.0.1:PORT +can't open device nbd+tcp://127.0.0.1:PORT/ === Check disconnect 28 neg-classic === -can't open device nbd:127.0.0.1:PORT +can't open device nbd+tcp://127.0.0.1:PORT/ + +=== Check disconnect after neg-classic === + +read failed: Input/output error + +=== Check disconnect before neg1 === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect after neg1 === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect 8 neg1 === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect 16 neg1 === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect before export === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect after export === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect 4 export === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect 12 export === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect 16 export === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect before neg2 === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect after neg2 === + +read failed: Input/output error + +=== Check disconnect 8 neg2 === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect 10 neg2 === + +can't open device nbd+unix:///foo?socket=TEST_DIR/nbd.sock + +=== Check disconnect before request === + +read failed: Input/output error + +=== Check disconnect after request === + +read failed: Input/output error + +=== Check disconnect before reply === + +read failed: Input/output error + +=== Check disconnect after reply === + +read failed: Input/output error + +=== Check disconnect 4 reply === + +read failed +read failed: Input/output error + +=== Check disconnect 8 reply === + +read failed +read failed: Input/output error + +=== Check disconnect before data === + +read failed: Input/output error + +=== Check disconnect after data === + +read 512/512 bytes at offset 0 +512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) + +=== Check disconnect before neg-classic === + +can't open device nbd+unix:///?socket=TEST_DIR/nbd.sock + +=== Check disconnect 8 neg-classic === + +can't open device nbd+unix:///?socket=TEST_DIR/nbd.sock + +=== Check disconnect 16 neg-classic === + +can't open device nbd+unix:///?socket=TEST_DIR/nbd.sock + +=== Check disconnect 24 neg-classic === + +can't open device nbd+unix:///?socket=TEST_DIR/nbd.sock + +=== Check disconnect 28 neg-classic === + +can't open device nbd+unix:///?socket=TEST_DIR/nbd.sock === Check disconnect after neg-classic === diff --git a/tests/qemu-iotests/common.filter b/tests/qemu-iotests/common.filter index 7a58e57317..9d5442ecd9 100644 --- a/tests/qemu-iotests/common.filter +++ b/tests/qemu-iotests/common.filter @@ -170,9 +170,9 @@ _filter_nbd() # # Filter out the TCP port number since this changes between runs. sed -e '/nbd\/.*\.c:/d' \ - -e 's#nbd:\(//\)\?127\.0\.0\.1:[0-9]*#nbd:\1127.0.0.1:PORT#g' \ + -e 's#127\.0\.0\.1:[0-9]*#127.0.0.1:PORT#g' \ -e "s#?socket=$TEST_DIR#?socket=TEST_DIR#g" \ - -e 's#\(exportname=foo\|PORT\): Failed to .*$#\1#' + -e 's#\(foo\|PORT/\?\|.sock\): Failed to .*$#\1#' } # make sure this script returns success From a0acf3a8f716946d7c425870bd05bc6dfe7667a2 Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Fri, 4 Aug 2017 18:14:24 +0300 Subject: [PATCH 05/11] nbd/client: fix nbd_opt_go Do not send NBD_OPT_ABORT to the broken server. After sending NBD_REP_ACK on NBD_OPT_GO server is most probably in transmission phase, when option sending is finished. Signed-off-by: Vladimir Sementsov-Ogievskiy Message-Id: <20170804151440.320927-2-vsementsov@virtuozzo.com> Signed-off-by: Eric Blake --- nbd/client.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/nbd/client.c b/nbd/client.c index 0a17de80b5..f1c16b588f 100644 --- a/nbd/client.c +++ b/nbd/client.c @@ -399,12 +399,10 @@ static int nbd_opt_go(QIOChannel *ioc, const char *wantname, phase, but make sure it sent flags */ if (len) { error_setg(errp, "server sent invalid NBD_REP_ACK"); - nbd_send_opt_abort(ioc); return -1; } if (!info->flags) { error_setg(errp, "broken server omitted NBD_INFO_EXPORT"); - nbd_send_opt_abort(ioc); return -1; } trace_nbd_opt_go_success(); From ab01df1fe21c013d1fd9e3f4c782430741c7dd33 Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Fri, 4 Aug 2017 18:14:25 +0300 Subject: [PATCH 06/11] nbd/client: refactor nbd_read_eof Refactor nbd_read_eof to return 1 on success, 0 on eof, when no data was read and <0 for other cases, because returned size of read data is not actually used. Signed-off-by: Vladimir Sementsov-Ogievskiy Message-Id: <20170804151440.320927-3-vsementsov@virtuozzo.com> [eblake: tweak function comments, rebase to test 083 enhancements] Signed-off-by: Eric Blake --- nbd/client.c | 5 ----- nbd/nbd-internal.h | 33 ++++++++++++++++++++++++--------- tests/qemu-iotests/083.out | 8 ++++---- 3 files changed, 28 insertions(+), 18 deletions(-) diff --git a/nbd/client.c b/nbd/client.c index f1c16b588f..4556056daa 100644 --- a/nbd/client.c +++ b/nbd/client.c @@ -925,11 +925,6 @@ ssize_t nbd_receive_reply(QIOChannel *ioc, NBDReply *reply, Error **errp) return ret; } - if (ret != sizeof(buf)) { - error_setg(errp, "read failed"); - return -EINVAL; - } - /* Reply [ 0 .. 3] magic (NBD_REPLY_MAGIC) [ 4 .. 7] error (0 == no error) diff --git a/nbd/nbd-internal.h b/nbd/nbd-internal.h index 396ddb4d3e..03549e3f39 100644 --- a/nbd/nbd-internal.h +++ b/nbd/nbd-internal.h @@ -77,21 +77,36 @@ #define NBD_ESHUTDOWN 108 /* nbd_read_eof - * Tries to read @size bytes from @ioc. Returns number of bytes actually read. - * May return a value >= 0 and < size only on EOF, i.e. when iteratively called - * qio_channel_readv() returns 0. So, there is no need to call nbd_read_eof - * iteratively. + * Tries to read @size bytes from @ioc. + * Returns 1 on success + * 0 on eof, when no data was read (errp is not set) + * negative errno on failure (errp is set) */ -static inline ssize_t nbd_read_eof(QIOChannel *ioc, void *buffer, size_t size, - Error **errp) +static inline int nbd_read_eof(QIOChannel *ioc, void *buffer, size_t size, + Error **errp) { struct iovec iov = { .iov_base = buffer, .iov_len = size }; + ssize_t ret; + /* Sockets are kept in blocking mode in the negotiation phase. After * that, a non-readable socket simply means that another thread stole * our request/reply. Synchronization is done with recv_coroutine, so * that this is coroutine-safe. */ - return nbd_rwv(ioc, &iov, 1, size, true, errp); + + assert(size); + + ret = nbd_rwv(ioc, &iov, 1, size, true, errp); + if (ret <= 0) { + return ret; + } + + if (ret != size) { + error_setg(errp, "End of file"); + return -EINVAL; + } + + return 1; } /* nbd_read @@ -100,9 +115,9 @@ static inline ssize_t nbd_read_eof(QIOChannel *ioc, void *buffer, size_t size, static inline int nbd_read(QIOChannel *ioc, void *buffer, size_t size, Error **errp) { - ssize_t ret = nbd_read_eof(ioc, buffer, size, errp); + int ret = nbd_read_eof(ioc, buffer, size, errp); - if (ret >= 0 && ret != size) { + if (ret == 0) { ret = -EINVAL; error_setg(errp, "End of file"); } diff --git a/tests/qemu-iotests/083.out b/tests/qemu-iotests/083.out index a7fb081889..fb71b6f8ad 100644 --- a/tests/qemu-iotests/083.out +++ b/tests/qemu-iotests/083.out @@ -69,12 +69,12 @@ read failed: Input/output error === Check disconnect 4 reply === -read failed +End of file read failed: Input/output error === Check disconnect 8 reply === -read failed +End of file read failed: Input/output error === Check disconnect before data === @@ -180,12 +180,12 @@ read failed: Input/output error === Check disconnect 4 reply === -read failed +End of file read failed: Input/output error === Check disconnect 8 reply === -read failed +End of file read failed: Input/output error === Check disconnect before data === From ba8456442b597848fb5585273c47de8476c3a0c1 Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Fri, 4 Aug 2017 18:14:26 +0300 Subject: [PATCH 07/11] nbd/client: refactor nbd_receive_reply Refactor nbd_receive_reply to return 1 on success, 0 on eof, when no data was read and <0 for other cases, because returned size of read data is not actually used. Signed-off-by: Vladimir Sementsov-Ogievskiy Message-Id: <20170804151440.320927-4-vsementsov@virtuozzo.com> [eblake: tweak function comments] Signed-off-by: Eric Blake --- include/block/nbd.h | 2 +- nbd/client.c | 12 +++++++++--- 2 files changed, 10 insertions(+), 4 deletions(-) diff --git a/include/block/nbd.h b/include/block/nbd.h index 9c3d0a5868..f7450608b4 100644 --- a/include/block/nbd.h +++ b/include/block/nbd.h @@ -164,7 +164,7 @@ int nbd_receive_negotiate(QIOChannel *ioc, const char *name, int nbd_init(int fd, QIOChannelSocket *sioc, NBDExportInfo *info, Error **errp); ssize_t nbd_send_request(QIOChannel *ioc, NBDRequest *request); -ssize_t nbd_receive_reply(QIOChannel *ioc, NBDReply *reply, Error **errp); +int nbd_receive_reply(QIOChannel *ioc, NBDReply *reply, Error **errp); int nbd_client(int fd); int nbd_disconnect(int fd); diff --git a/nbd/client.c b/nbd/client.c index 4556056daa..f8c213bc96 100644 --- a/nbd/client.c +++ b/nbd/client.c @@ -914,11 +914,16 @@ ssize_t nbd_send_request(QIOChannel *ioc, NBDRequest *request) return nbd_write(ioc, buf, sizeof(buf), NULL); } -ssize_t nbd_receive_reply(QIOChannel *ioc, NBDReply *reply, Error **errp) +/* nbd_receive_reply + * Returns 1 on success + * 0 on eof, when no data was read (errp is not set) + * negative errno on failure (errp is set) + */ +int nbd_receive_reply(QIOChannel *ioc, NBDReply *reply, Error **errp) { uint8_t buf[NBD_REPLY_SIZE]; uint32_t magic; - ssize_t ret; + int ret; ret = nbd_read_eof(ioc, buf, sizeof(buf), errp); if (ret <= 0) { @@ -948,6 +953,7 @@ ssize_t nbd_receive_reply(QIOChannel *ioc, NBDReply *reply, Error **errp) error_setg(errp, "invalid magic (got 0x%" PRIx32 ")", magic); return -EINVAL; } - return sizeof(buf); + + return 1; } From 490dc5ed9bfbaf50ed8186c9729a81f530a11188 Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Fri, 4 Aug 2017 18:14:27 +0300 Subject: [PATCH 08/11] nbd/client: fix nbd_send_request to return int Fix nbd_send_request to return int, as it returns a return value of nbd_write (which is int), and the only user of nbd_send_request's return value (nbd_co_send_request) consider it as int too. Signed-off-by: Vladimir Sementsov-Ogievskiy Message-Id: <20170804151440.320927-5-vsementsov@virtuozzo.com> Signed-off-by: Eric Blake --- include/block/nbd.h | 2 +- nbd/client.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/block/nbd.h b/include/block/nbd.h index f7450608b4..040cdd2e60 100644 --- a/include/block/nbd.h +++ b/include/block/nbd.h @@ -163,7 +163,7 @@ int nbd_receive_negotiate(QIOChannel *ioc, const char *name, Error **errp); int nbd_init(int fd, QIOChannelSocket *sioc, NBDExportInfo *info, Error **errp); -ssize_t nbd_send_request(QIOChannel *ioc, NBDRequest *request); +int nbd_send_request(QIOChannel *ioc, NBDRequest *request); int nbd_receive_reply(QIOChannel *ioc, NBDReply *reply, Error **errp); int nbd_client(int fd); int nbd_disconnect(int fd); diff --git a/nbd/client.c b/nbd/client.c index f8c213bc96..68a0bc1ffc 100644 --- a/nbd/client.c +++ b/nbd/client.c @@ -896,7 +896,7 @@ int nbd_disconnect(int fd) } #endif -ssize_t nbd_send_request(QIOChannel *ioc, NBDRequest *request) +int nbd_send_request(QIOChannel *ioc, NBDRequest *request) { uint8_t buf[NBD_REQUEST_SIZE]; From 6faa077772db366e5d2198ec0a14a50d0ccde1c6 Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Fri, 4 Aug 2017 18:14:28 +0300 Subject: [PATCH 09/11] block/nbd-client: get rid of ssize_t Use int variable for nbd_co_send_request return value (as nbd_co_send_request returns int). Signed-off-by: Vladimir Sementsov-Ogievskiy Message-Id: <20170804151440.320927-6-vsementsov@virtuozzo.com> Signed-off-by: Eric Blake --- block/nbd-client.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/block/nbd-client.c b/block/nbd-client.c index ea728fffc8..1e393cf26f 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -230,7 +230,7 @@ int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset, .len = bytes, }; NBDReply reply; - ssize_t ret; + int ret; assert(bytes <= NBD_MAX_BUFFER_SIZE); assert(!flags); @@ -254,7 +254,7 @@ int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset, .len = bytes, }; NBDReply reply; - ssize_t ret; + int ret; if (flags & BDRV_REQ_FUA) { assert(client->info.flags & NBD_FLAG_SEND_FUA); @@ -275,7 +275,7 @@ int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset, int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, BdrvRequestFlags flags) { - ssize_t ret; + int ret; NBDClientSession *client = nbd_get_client_session(bs); NBDRequest request = { .type = NBD_CMD_WRITE_ZEROES, @@ -310,7 +310,7 @@ int nbd_client_co_flush(BlockDriverState *bs) NBDClientSession *client = nbd_get_client_session(bs); NBDRequest request = { .type = NBD_CMD_FLUSH }; NBDReply reply; - ssize_t ret; + int ret; if (!(client->info.flags & NBD_FLAG_SEND_FLUSH)) { return 0; @@ -337,7 +337,7 @@ int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes) .len = bytes, }; NBDReply reply; - ssize_t ret; + int ret; if (!(client->info.flags & NBD_FLAG_SEND_TRIM)) { return 0; From 07b1b99c78e4b9479922fbe2d05a87ef810e6b7e Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Fri, 4 Aug 2017 18:14:31 +0300 Subject: [PATCH 10/11] block/nbd-client: rename nbd_recv_coroutines_enter_all Rename nbd_recv_coroutines_enter_all to nbd_recv_coroutines_wake_all, as it most probably just adds all recv coroutines into co_queue_wakeup, rather than directly enter them. Signed-off-by: Vladimir Sementsov-Ogievskiy Message-Id: <20170804151440.320927-9-vsementsov@virtuozzo.com> [eblake: tweak commit message] Signed-off-by: Eric Blake --- block/nbd-client.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/block/nbd-client.c b/block/nbd-client.c index 1e393cf26f..322b725ff9 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -34,7 +34,7 @@ #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) +static void nbd_recv_coroutines_wake_all(NBDClientSession *s) { int i; @@ -112,7 +112,7 @@ static coroutine_fn void nbd_read_reply_entry(void *opaque) } s->quit = true; - nbd_recv_coroutines_enter_all(s); + nbd_recv_coroutines_wake_all(s); s->read_reply_co = NULL; } From f35dff7e13b84d3fffe1103c2c69afd81df5e4f5 Mon Sep 17 00:00:00 2001 From: Vladimir Sementsov-Ogievskiy Date: Tue, 29 Aug 2017 16:48:31 -0500 Subject: [PATCH 11/11] block/nbd-client: refactor request send/receive Add nbd_co_request, to remove code duplications in nbd_client_co_{pwrite,pread,...} functions. Also this is needed for further refactoring. Signed-off-by: Vladimir Sementsov-Ogievskiy Message-Id: <20170804151440.320927-8-vsementsov@virtuozzo.com> [eblake: make nbd_co_request a wrapper, rather than merging two existing functions] Signed-off-by: Eric Blake --- block/nbd-client.c | 73 +++++++++++++++++----------------------------- 1 file changed, 26 insertions(+), 47 deletions(-) diff --git a/block/nbd-client.c b/block/nbd-client.c index 322b725ff9..f0dbea24d3 100644 --- a/block/nbd-client.c +++ b/block/nbd-client.c @@ -220,28 +220,40 @@ static void nbd_co_receive_reply(NBDClientSession *s, qemu_co_mutex_unlock(&s->send_mutex); } +static int nbd_co_request(BlockDriverState *bs, + NBDRequest *request, + QEMUIOVector *qiov) +{ + NBDClientSession *client = nbd_get_client_session(bs); + NBDReply reply; + int ret; + + assert(!qiov || request->type == NBD_CMD_WRITE || + request->type == NBD_CMD_READ); + ret = nbd_co_send_request(bs, request, + request->type == NBD_CMD_WRITE ? qiov : NULL); + if (ret < 0) { + reply.error = -ret; + } else { + nbd_co_receive_reply(client, request, &reply, + request->type == NBD_CMD_READ ? qiov : NULL); + } + return -reply.error; +} + int nbd_client_co_preadv(BlockDriverState *bs, uint64_t offset, uint64_t bytes, QEMUIOVector *qiov, int flags) { - NBDClientSession *client = nbd_get_client_session(bs); NBDRequest request = { .type = NBD_CMD_READ, .from = offset, .len = bytes, }; - NBDReply reply; - int ret; assert(bytes <= NBD_MAX_BUFFER_SIZE); assert(!flags); - ret = nbd_co_send_request(bs, &request, NULL); - if (ret < 0) { - reply.error = -ret; - } else { - nbd_co_receive_reply(client, &request, &reply, qiov); - } - return -reply.error; + return nbd_co_request(bs, &request, qiov); } int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset, @@ -253,8 +265,6 @@ int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset, .from = offset, .len = bytes, }; - NBDReply reply; - int ret; if (flags & BDRV_REQ_FUA) { assert(client->info.flags & NBD_FLAG_SEND_FUA); @@ -263,26 +273,18 @@ int nbd_client_co_pwritev(BlockDriverState *bs, uint64_t offset, assert(bytes <= NBD_MAX_BUFFER_SIZE); - ret = nbd_co_send_request(bs, &request, qiov); - if (ret < 0) { - reply.error = -ret; - } else { - nbd_co_receive_reply(client, &request, &reply, NULL); - } - return -reply.error; + return nbd_co_request(bs, &request, qiov); } int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, int bytes, BdrvRequestFlags flags) { - int ret; NBDClientSession *client = nbd_get_client_session(bs); NBDRequest request = { .type = NBD_CMD_WRITE_ZEROES, .from = offset, .len = bytes, }; - NBDReply reply; if (!(client->info.flags & NBD_FLAG_SEND_WRITE_ZEROES)) { return -ENOTSUP; @@ -296,21 +298,13 @@ int nbd_client_co_pwrite_zeroes(BlockDriverState *bs, int64_t offset, request.flags |= NBD_CMD_FLAG_NO_HOLE; } - ret = nbd_co_send_request(bs, &request, NULL); - if (ret < 0) { - reply.error = -ret; - } else { - nbd_co_receive_reply(client, &request, &reply, NULL); - } - return -reply.error; + return nbd_co_request(bs, &request, NULL); } int nbd_client_co_flush(BlockDriverState *bs) { NBDClientSession *client = nbd_get_client_session(bs); NBDRequest request = { .type = NBD_CMD_FLUSH }; - NBDReply reply; - int ret; if (!(client->info.flags & NBD_FLAG_SEND_FLUSH)) { return 0; @@ -319,13 +313,7 @@ int nbd_client_co_flush(BlockDriverState *bs) request.from = 0; request.len = 0; - ret = nbd_co_send_request(bs, &request, NULL); - if (ret < 0) { - reply.error = -ret; - } else { - nbd_co_receive_reply(client, &request, &reply, NULL); - } - return -reply.error; + return nbd_co_request(bs, &request, NULL); } int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes) @@ -336,21 +324,12 @@ int nbd_client_co_pdiscard(BlockDriverState *bs, int64_t offset, int bytes) .from = offset, .len = bytes, }; - NBDReply reply; - int ret; if (!(client->info.flags & NBD_FLAG_SEND_TRIM)) { return 0; } - ret = nbd_co_send_request(bs, &request, NULL); - if (ret < 0) { - reply.error = -ret; - } else { - nbd_co_receive_reply(client, &request, &reply, NULL); - } - return -reply.error; - + return nbd_co_request(bs, &request, NULL); } void nbd_client_detach_aio_context(BlockDriverState *bs)