rpms/qemu-kvm
7
0
Fork 0
Code Issues Pull Requests Releases Activity

* Wed Jul 24 2024 Miroslav Rezanina <mrezanin@redhat.com> - 9.0.0-5

Browse Source 
- kvm-nbd-server-do-not-poll-within-a-coroutine-context.patch [RHEL-40959]
- kvm-nbd-server-Mark-negotiation-functions-as-coroutine_f.patch [RHEL-40959]
- kvm-qio-Inherit-follow_coroutine_ctx-across-TLS.patch [RHEL-40959]
- kvm-iotests-test-NBD-TLS-iothread.patch [RHEL-40959]
- Resolves: RHEL-40959
  (Qemu hang when quit dst vm after storage migration(nbd+tls))
This commit is contained in:
Miroslav Rezanina 2024-07-24 09:37:55 -04:00
parent e6031e7a4e
commit 900580adb4
5 changed files with 961 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

276
kvm-iotests-test-NBD-TLS-iothread.patch Normal file
View File

@ -0,0 +1,276 @@
From 2f12be8abfc90dc383a221441f60bdaae6b617d2 Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Fri, 17 May 2024 21:50:15 -0500
Subject: [PATCH 4/4] iotests: test NBD+TLS+iothread
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 257: nbd/server: fix TLS negotiation across coroutine context
RH-Jira: RHEL-40959
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [4/4] 39a37bf3ae6e7046577de151ef2f6fd1fd694e62 (ebblake/centos-qemu-kvm)
Prevent regressions when using NBD with TLS in the presence of
iothreads, adding coverage the fix to qio channels made in the
previous patch.
The shell function pick_unused_port() was copied from
nbdkit.git/tests/functions.sh.in, where it had all authors from Red
Hat, agreeing to the resulting relicensing from 2-clause BSD to GPLv2.
CC: qemu-stable@nongnu.org
CC: "Richard W.M. Jones" <rjones@redhat.com>
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240531180639.1392905-6-eblake@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
(cherry picked from commit a73c99378022ebb785481e84cfe1e81097546268)
Jira: https://issues.redhat.com/browse/RHEL-40959
Signed-off-by: Eric Blake <eblake@redhat.com>
---
tests/qemu-iotests/tests/nbd-tls-iothread | 168 ++++++++++++++++++
tests/qemu-iotests/tests/nbd-tls-iothread.out | 54 ++++++
2 files changed, 222 insertions(+)
create mode 100755 tests/qemu-iotests/tests/nbd-tls-iothread
create mode 100644 tests/qemu-iotests/tests/nbd-tls-iothread.out
diff --git a/tests/qemu-iotests/tests/nbd-tls-iothread b/tests/qemu-iotests/tests/nbd-tls-iothread
new file mode 100755
index 0000000000..a2fb07206e
--- /dev/null
+++ b/tests/qemu-iotests/tests/nbd-tls-iothread
@@ -0,0 +1,168 @@
+#!/usr/bin/env bash
+# group: rw quick
+#
+# Test of NBD+TLS+iothread
+#
+# Copyright (C) 2024 Red Hat, Inc.
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation; either version 2 of the License, or
+# (at your option) any later version.
+#
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with this program. If not, see <http://www.gnu.org/licenses/>.
+#
+
+# creator
+owner=eblake@redhat.com
+
+seq=`basename $0`
+echo "QA output created by $seq"
+
+status=1 # failure is the default!
+
+_cleanup()
+{
+ _cleanup_qemu
+ _cleanup_test_img
+ rm -f "$dst_image"
+ tls_x509_cleanup
+}
+trap "_cleanup; exit \$status" 0 1 2 3 15
+
+# get standard environment, filters and checks
+cd ..
+. ./common.rc
+. ./common.filter
+. ./common.qemu
+. ./common.tls
+. ./common.nbd
+
+_supported_fmt qcow2 # Hardcoded to qcow2 command line and QMP below
+_supported_proto file
+
+# pick_unused_port
+#
+# Picks and returns an "unused" port, setting the global variable
+# $port.
+#
+# This is inherently racy, but we need it because qemu does not currently
+# permit NBD+TLS over a Unix domain socket
+pick_unused_port ()
+{
+ if ! (ss --version) >/dev/null 2>&1; then
+ _notrun "ss utility required, skipped this test"
+ fi
+
+ # Start at a random port to make it less likely that two parallel
+ # tests will conflict.
+ port=$(( 50000 + (RANDOM%15000) ))
+ while ss -ltn | grep -sqE ":$port\b"; do
+ ((port++))
+ if [ $port -eq 65000 ]; then port=50000; fi
+ done
+ echo picked unused port
+}
+
+tls_x509_init
+
+size=1G
+DST_IMG="$TEST_DIR/dst.qcow2"
+
+echo
+echo "== preparing TLS creds and spare port =="
+
+pick_unused_port
+tls_x509_create_root_ca "ca1"
+tls_x509_create_server "ca1" "server1"
+tls_x509_create_client "ca1" "client1"
+tls_obj_base=tls-creds-x509,id=tls0,verify-peer=true,dir="${tls_dir}"
+
+echo
+echo "== preparing image =="
+
+_make_test_img $size
+$QEMU_IMG create -f qcow2 "$DST_IMG" $size | _filter_img_create
+
+echo
+echo === Starting Src QEMU ===
+echo
+
+_launch_qemu -machine q35 \
+ -object iothread,id=iothread0 \
+ -object "${tls_obj_base}"/client1,endpoint=client \
+ -device '{"driver":"pcie-root-port", "id":"root0", "multifunction":true,
+ "bus":"pcie.0"}' \
+ -device '{"driver":"virtio-scsi-pci", "id":"virtio_scsi_pci0",
+ "bus":"root0", "iothread":"iothread0"}' \
+ -device '{"driver":"scsi-hd", "id":"image1", "drive":"drive_image1",
+ "bus":"virtio_scsi_pci0.0"}' \
+ -blockdev '{"driver":"file", "cache":{"direct":true, "no-flush":false},
+ "filename":"'"$TEST_IMG"'", "node-name":"drive_sys1"}' \
+ -blockdev '{"driver":"qcow2", "node-name":"drive_image1",
+ "file":"drive_sys1"}'
+h1=$QEMU_HANDLE
+_send_qemu_cmd $h1 '{"execute": "qmp_capabilities"}' 'return'
+
+echo
+echo === Starting Dst VM2 ===
+echo
+
+_launch_qemu -machine q35 \
+ -object iothread,id=iothread0 \
+ -object "${tls_obj_base}"/server1,endpoint=server \
+ -device '{"driver":"pcie-root-port", "id":"root0", "multifunction":true,
+ "bus":"pcie.0"}' \
+ -device '{"driver":"virtio-scsi-pci", "id":"virtio_scsi_pci0",
+ "bus":"root0", "iothread":"iothread0"}' \
+ -device '{"driver":"scsi-hd", "id":"image1", "drive":"drive_image1",
+ "bus":"virtio_scsi_pci0.0"}' \
+ -blockdev '{"driver":"file", "cache":{"direct":true, "no-flush":false},
+ "filename":"'"$DST_IMG"'", "node-name":"drive_sys1"}' \
+ -blockdev '{"driver":"qcow2", "node-name":"drive_image1",
+ "file":"drive_sys1"}' \
+ -incoming defer
+h2=$QEMU_HANDLE
+_send_qemu_cmd $h2 '{"execute": "qmp_capabilities"}' 'return'
+
+echo
+echo === Dst VM: Enable NBD server for incoming storage migration ===
+echo
+
+_send_qemu_cmd $h2 '{"execute": "nbd-server-start", "arguments":
+ {"addr": {"type": "inet", "data": {"host": "127.0.0.1", "port": "'$port'"}},
+ "tls-creds": "tls0"}}' '{"return": {}}' | sed "s/\"$port\"/PORT/g"
+_send_qemu_cmd $h2 '{"execute": "block-export-add", "arguments":
+ {"node-name": "drive_image1", "type": "nbd", "writable": true,
+ "id": "drive_image1"}}' '{"return": {}}'
+
+echo
+echo === Src VM: Mirror to dst NBD for outgoing storage migration ===
+echo
+
+_send_qemu_cmd $h1 '{"execute": "blockdev-add", "arguments":
+ {"node-name": "mirror", "driver": "nbd",
+ "server": {"type": "inet", "host": "127.0.0.1", "port": "'$port'"},
+ "export": "drive_image1", "tls-creds": "tls0",
+ "tls-hostname": "127.0.0.1"}}' '{"return": {}}' | sed "s/\"$port\"/PORT/g"
+_send_qemu_cmd $h1 '{"execute": "blockdev-mirror", "arguments":
+ {"sync": "full", "device": "drive_image1", "target": "mirror",
+ "job-id": "drive_image1_53"}}' '{"return": {}}'
+_timed_wait_for $h1 '"ready"'
+
+echo
+echo === Cleaning up ===
+echo
+
+_send_qemu_cmd $h1 '{"execute":"quit"}' ''
+_send_qemu_cmd $h2 '{"execute":"quit"}' ''
+
+echo "*** done"
+rm -f $seq.full
+status=0
diff --git a/tests/qemu-iotests/tests/nbd-tls-iothread.out b/tests/qemu-iotests/tests/nbd-tls-iothread.out
new file mode 100644
index 0000000000..1d83d4f903
--- /dev/null
+++ b/tests/qemu-iotests/tests/nbd-tls-iothread.out
@@ -0,0 +1,54 @@
+QA output created by nbd-tls-iothread
+
+== preparing TLS creds and spare port ==
+picked unused port
+Generating a self signed certificate...
+Generating a signed certificate...
+Generating a signed certificate...
+
+== preparing image ==
+Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=1073741824
+Formatting 'TEST_DIR/dst.IMGFMT', fmt=IMGFMT size=1073741824
+
+=== Starting Src QEMU ===
+
+{"execute": "qmp_capabilities"}
+{"return": {}}
+
+=== Starting Dst VM2 ===
+
+{"execute": "qmp_capabilities"}
+{"return": {}}
+
+=== Dst VM: Enable NBD server for incoming storage migration ===
+
+{"execute": "nbd-server-start", "arguments":
+ {"addr": {"type": "inet", "data": {"host": "127.0.0.1", "port": PORT}},
+ "tls-creds": "tls0"}}
+{"return": {}}
+{"execute": "block-export-add", "arguments":
+ {"node-name": "drive_image1", "type": "nbd", "writable": true,
+ "id": "drive_image1"}}
+{"return": {}}
+
+=== Src VM: Mirror to dst NBD for outgoing storage migration ===
+
+{"execute": "blockdev-add", "arguments":
+ {"node-name": "mirror", "driver": "nbd",
+ "server": {"type": "inet", "host": "127.0.0.1", "port": PORT},
+ "export": "drive_image1", "tls-creds": "tls0",
+ "tls-hostname": "127.0.0.1"}}
+{"return": {}}
+{"execute": "blockdev-mirror", "arguments":
+ {"sync": "full", "device": "drive_image1", "target": "mirror",
+ "job-id": "drive_image1_53"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "created", "id": "drive_image1_53"}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "running", "id": "drive_image1_53"}}
+{"return": {}}
+{"timestamp": {"seconds": TIMESTAMP, "microseconds": TIMESTAMP}, "event": "JOB_STATUS_CHANGE", "data": {"status": "ready", "id": "drive_image1_53"}}
+
+=== Cleaning up ===
+
+{"execute":"quit"}
+{"execute":"quit"}
+*** done
--
2.39.3

330
kvm-nbd-server-Mark-negotiation-functions-as-coroutine_f.patch Normal file
View File

@ -0,0 +1,330 @@
From 55e78a14c6a6956a3ac65f36b9b8b8c49eff959b Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Mon, 8 Apr 2024 11:00:44 -0500
Subject: [PATCH 2/4] nbd/server: Mark negotiation functions as coroutine_fn
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 257: nbd/server: fix TLS negotiation across coroutine context
RH-Jira: RHEL-40959
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [2/4] f364e5cd2a9eac2d4f6af2841479f1dfb2f8df58 (ebblake/centos-qemu-kvm)
nbd_negotiate() is already marked coroutine_fn. And given the fix in
the previous patch to have nbd_negotiate_handle_starttls not create
and wait on a g_main_loop (as that would violate coroutine
constraints), it is worth marking the rest of the related static
functions reachable only during option negotiation as also being
coroutine_fn.
Suggested-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240408160214.1200629-6-eblake@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
[eblake: drop one spurious coroutine_fn marking]
Signed-off-by: Eric Blake <eblake@redhat.com>
Jira: https://issues.redhat.com/browse/RHEL-40959
(cherry picked from commit 4fa333e08dd96395a99ea8dd9e4c73a29dd23344)
Signed-off-by: Eric Blake <eblake@redhat.com>
---
nbd/server.c | 102 +++++++++++++++++++++++++++++----------------------
1 file changed, 59 insertions(+), 43 deletions(-)
diff --git a/nbd/server.c b/nbd/server.c
index 98ae0e1632..892797bb11 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -195,8 +195,9 @@ static inline void set_be_option_rep(NBDOptionReply *rep, uint32_t option,
/* Send a reply header, including length, but no payload.
* Return -errno on error, 0 on success. */
-static int nbd_negotiate_send_rep_len(NBDClient *client, uint32_t type,
- uint32_t len, Error **errp)
+static coroutine_fn int
+nbd_negotiate_send_rep_len(NBDClient *client, uint32_t type,
+ uint32_t len, Error **errp)
{
NBDOptionReply rep;
@@ -211,15 +212,15 @@ static int nbd_negotiate_send_rep_len(NBDClient *client, uint32_t type,
/* Send a reply header with default 0 length.
* Return -errno on error, 0 on success. */
-static int nbd_negotiate_send_rep(NBDClient *client, uint32_t type,
- Error **errp)
+static coroutine_fn int
+nbd_negotiate_send_rep(NBDClient *client, uint32_t type, Error **errp)
{
return nbd_negotiate_send_rep_len(client, type, 0, errp);
}
/* Send an error reply.
* Return -errno on error, 0 on success. */
-static int G_GNUC_PRINTF(4, 0)
+static coroutine_fn int G_GNUC_PRINTF(4, 0)
nbd_negotiate_send_rep_verr(NBDClient *client, uint32_t type,
Error **errp, const char *fmt, va_list va)
{
@@ -259,7 +260,7 @@ nbd_sanitize_name(const char *name)
/* Send an error reply.
* Return -errno on error, 0 on success. */
-static int G_GNUC_PRINTF(4, 5)
+static coroutine_fn int G_GNUC_PRINTF(4, 5)
nbd_negotiate_send_rep_err(NBDClient *client, uint32_t type,
Error **errp, const char *fmt, ...)
{
@@ -275,7 +276,7 @@ nbd_negotiate_send_rep_err(NBDClient *client, uint32_t type,
/* Drop remainder of the current option, and send a reply with the
* given error type and message. Return -errno on read or write
* failure; or 0 if connection is still live. */
-static int G_GNUC_PRINTF(4, 0)
+static coroutine_fn int G_GNUC_PRINTF(4, 0)
nbd_opt_vdrop(NBDClient *client, uint32_t type, Error **errp,
const char *fmt, va_list va)
{
@@ -288,7 +289,7 @@ nbd_opt_vdrop(NBDClient *client, uint32_t type, Error **errp,
return ret;
}
-static int G_GNUC_PRINTF(4, 5)
+static coroutine_fn int G_GNUC_PRINTF(4, 5)
nbd_opt_drop(NBDClient *client, uint32_t type, Error **errp,
const char *fmt, ...)
{
@@ -302,7 +303,7 @@ nbd_opt_drop(NBDClient *client, uint32_t type, Error **errp,
return ret;
}
-static int G_GNUC_PRINTF(3, 4)
+static coroutine_fn int G_GNUC_PRINTF(3, 4)
nbd_opt_invalid(NBDClient *client, Error **errp, const char *fmt, ...)
{
int ret;
@@ -319,8 +320,9 @@ nbd_opt_invalid(NBDClient *client, Error **errp, const char *fmt, ...)
* If @check_nul, require that no NUL bytes appear in buffer.
* Return -errno on I/O error, 0 if option was completely handled by
* sending a reply about inconsistent lengths, or 1 on success. */
-static int nbd_opt_read(NBDClient *client, void *buffer, size_t size,
- bool check_nul, Error **errp)
+static coroutine_fn int
+nbd_opt_read(NBDClient *client, void *buffer, size_t size,
+ bool check_nul, Error **errp)
{
if (size > client->optlen) {
return nbd_opt_invalid(client, errp,
@@ -343,7 +345,8 @@ static int nbd_opt_read(NBDClient *client, void *buffer, size_t size,
/* Drop size bytes from the unparsed payload of the current option.
* Return -errno on I/O error, 0 if option was completely handled by
* sending a reply about inconsistent lengths, or 1 on success. */
-static int nbd_opt_skip(NBDClient *client, size_t size, Error **errp)
+static coroutine_fn int
+nbd_opt_skip(NBDClient *client, size_t size, Error **errp)
{
if (size > client->optlen) {
return nbd_opt_invalid(client, errp,
@@ -366,8 +369,9 @@ static int nbd_opt_skip(NBDClient *client, size_t size, Error **errp)
* Return -errno on I/O error, 0 if option was completely handled by
* sending a reply about inconsistent lengths, or 1 on success.
*/
-static int nbd_opt_read_name(NBDClient *client, char **name, uint32_t *length,
- Error **errp)
+static coroutine_fn int
+nbd_opt_read_name(NBDClient *client, char **name, uint32_t *length,
+ Error **errp)
{
int ret;
uint32_t len;
@@ -402,8 +406,8 @@ static int nbd_opt_read_name(NBDClient *client, char **name, uint32_t *length,
/* Send a single NBD_REP_SERVER reply to NBD_OPT_LIST, including payload.
* Return -errno on error, 0 on success. */
-static int nbd_negotiate_send_rep_list(NBDClient *client, NBDExport *exp,
- Error **errp)
+static coroutine_fn int
+nbd_negotiate_send_rep_list(NBDClient *client, NBDExport *exp, Error **errp)
{
ERRP_GUARD();
size_t name_len, desc_len;
@@ -444,7 +448,8 @@ static int nbd_negotiate_send_rep_list(NBDClient *client, NBDExport *exp,
/* Process the NBD_OPT_LIST command, with a potential series of replies.
* Return -errno on error, 0 on success. */
-static int nbd_negotiate_handle_list(NBDClient *client, Error **errp)
+static coroutine_fn int
+nbd_negotiate_handle_list(NBDClient *client, Error **errp)
{
NBDExport *exp;
assert(client->opt == NBD_OPT_LIST);
@@ -459,7 +464,8 @@ static int nbd_negotiate_handle_list(NBDClient *client, Error **errp)
return nbd_negotiate_send_rep(client, NBD_REP_ACK, errp);
}
-static void nbd_check_meta_export(NBDClient *client, NBDExport *exp)
+static coroutine_fn void
+nbd_check_meta_export(NBDClient *client, NBDExport *exp)
{
if (exp != client->contexts.exp) {
client->contexts.count = 0;
@@ -468,8 +474,9 @@ static void nbd_check_meta_export(NBDClient *client, NBDExport *exp)
/* Send a reply to NBD_OPT_EXPORT_NAME.
* Return -errno on error, 0 on success. */
-static int nbd_negotiate_handle_export_name(NBDClient *client, bool no_zeroes,
- Error **errp)
+static coroutine_fn int
+nbd_negotiate_handle_export_name(NBDClient *client, bool no_zeroes,
+ Error **errp)
{
ERRP_GUARD();
g_autofree char *name = NULL;
@@ -536,9 +543,9 @@ static int nbd_negotiate_handle_export_name(NBDClient *client, bool no_zeroes,
/* Send a single NBD_REP_INFO, with a buffer @buf of @length bytes.
* The buffer does NOT include the info type prefix.
* Return -errno on error, 0 if ready to send more. */
-static int nbd_negotiate_send_info(NBDClient *client,
- uint16_t info, uint32_t length, void *buf,
- Error **errp)
+static coroutine_fn int
+nbd_negotiate_send_info(NBDClient *client, uint16_t info, uint32_t length,
+ void *buf, Error **errp)
{
int rc;
@@ -565,7 +572,8 @@ static int nbd_negotiate_send_info(NBDClient *client,
* -errno transmission error occurred or @fatal was requested, errp is set
* 0 error message successfully sent to client, errp is not set
*/
-static int nbd_reject_length(NBDClient *client, bool fatal, Error **errp)
+static coroutine_fn int
+nbd_reject_length(NBDClient *client, bool fatal, Error **errp)
{
int ret;
@@ -583,7 +591,8 @@ static int nbd_reject_length(NBDClient *client, bool fatal, Error **errp)
/* Handle NBD_OPT_INFO and NBD_OPT_GO.
* Return -errno on error, 0 if ready for next option, and 1 to move
* into transmission phase. */
-static int nbd_negotiate_handle_info(NBDClient *client, Error **errp)
+static coroutine_fn int
+nbd_negotiate_handle_info(NBDClient *client, Error **errp)
{
int rc;
g_autofree char *name = NULL;
@@ -755,7 +764,8 @@ struct NBDTLSServerHandshakeData {
Coroutine *co;
};
-static void nbd_server_tls_handshake(QIOTask *task, void *opaque)
+static void
+nbd_server_tls_handshake(QIOTask *task, void *opaque)
{
struct NBDTLSServerHandshakeData *data = opaque;
@@ -768,8 +778,8 @@ static void nbd_server_tls_handshake(QIOTask *task, void *opaque)
/* Handle NBD_OPT_STARTTLS. Return NULL to drop connection, or else the
* new channel for all further (now-encrypted) communication. */
-static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client,
- Error **errp)
+static coroutine_fn QIOChannel *
+nbd_negotiate_handle_starttls(NBDClient *client, Error **errp)
{
QIOChannel *ioc;
QIOChannelTLS *tioc;
@@ -821,10 +831,9 @@ static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client,
*
* For NBD_OPT_LIST_META_CONTEXT @context_id is ignored, 0 is used instead.
*/
-static int nbd_negotiate_send_meta_context(NBDClient *client,
- const char *context,
- uint32_t context_id,
- Error **errp)
+static coroutine_fn int
+nbd_negotiate_send_meta_context(NBDClient *client, const char *context,
+ uint32_t context_id, Error **errp)
{
NBDOptionReplyMetaContext opt;
struct iovec iov[] = {
@@ -849,8 +858,9 @@ static int nbd_negotiate_send_meta_context(NBDClient *client,
* Return true if @query matches @pattern, or if @query is empty when
* the @client is performing _LIST_.
*/
-static bool nbd_meta_empty_or_pattern(NBDClient *client, const char *pattern,
- const char *query)
+static coroutine_fn bool
+nbd_meta_empty_or_pattern(NBDClient *client, const char *pattern,
+ const char *query)
{
if (!*query) {
trace_nbd_negotiate_meta_query_parse("empty");
@@ -867,7 +877,8 @@ static bool nbd_meta_empty_or_pattern(NBDClient *client, const char *pattern,
/*
* Return true and adjust @str in place if it begins with @prefix.
*/
-static bool nbd_strshift(const char **str, const char *prefix)
+static coroutine_fn bool
+nbd_strshift(const char **str, const char *prefix)
{
size_t len = strlen(prefix);
@@ -883,8 +894,9 @@ static bool nbd_strshift(const char **str, const char *prefix)
* Handle queries to 'base' namespace. For now, only the base:allocation
* context is available. Return true if @query has been handled.
*/
-static bool nbd_meta_base_query(NBDClient *client, NBDMetaContexts *meta,
- const char *query)
+static coroutine_fn bool
+nbd_meta_base_query(NBDClient *client, NBDMetaContexts *meta,
+ const char *query)
{
if (!nbd_strshift(&query, "base:")) {
return false;
@@ -903,8 +915,9 @@ static bool nbd_meta_base_query(NBDClient *client, NBDMetaContexts *meta,
* and qemu:allocation-depth contexts are available. Return true if @query
* has been handled.
*/
-static bool nbd_meta_qemu_query(NBDClient *client, NBDMetaContexts *meta,
- const char *query)
+static coroutine_fn bool
+nbd_meta_qemu_query(NBDClient *client, NBDMetaContexts *meta,
+ const char *query)
{
size_t i;
@@ -968,8 +981,9 @@ static bool nbd_meta_qemu_query(NBDClient *client, NBDMetaContexts *meta,
*
* Return -errno on I/O error, 0 if option was completely handled by
* sending a reply about inconsistent lengths, or 1 on success. */
-static int nbd_negotiate_meta_query(NBDClient *client,
- NBDMetaContexts *meta, Error **errp)
+static coroutine_fn int
+nbd_negotiate_meta_query(NBDClient *client,
+ NBDMetaContexts *meta, Error **errp)
{
int ret;
g_autofree char *query = NULL;
@@ -1008,7 +1022,8 @@ static int nbd_negotiate_meta_query(NBDClient *client,
* Handle NBD_OPT_LIST_META_CONTEXT and NBD_OPT_SET_META_CONTEXT
*
* Return -errno on I/O error, or 0 if option was completely handled. */
-static int nbd_negotiate_meta_queries(NBDClient *client, Error **errp)
+static coroutine_fn int
+nbd_negotiate_meta_queries(NBDClient *client, Error **errp)
{
int ret;
g_autofree char *export_name = NULL;
@@ -1136,7 +1151,8 @@ static int nbd_negotiate_meta_queries(NBDClient *client, Error **errp)
* 1 if client sent NBD_OPT_ABORT, i.e. on valid disconnect,
* errp is not set
*/
-static int nbd_negotiate_options(NBDClient *client, Error **errp)
+static coroutine_fn int
+nbd_negotiate_options(NBDClient *client, Error **errp)
{
uint32_t flags;
bool fixedNewstyle = false;
--
2.39.3

208
kvm-nbd-server-do-not-poll-within-a-coroutine-context.patch Normal file
View File

@ -0,0 +1,208 @@
From 484fe3af54a3e421be9e370d47eabe0d8cc5c50d Mon Sep 17 00:00:00 2001
From: Zhu Yangyang <zhuyangyang14@huawei.com>
Date: Mon, 8 Apr 2024 11:00:43 -0500
Subject: [PATCH 1/4] nbd/server: do not poll within a coroutine context
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 257: nbd/server: fix TLS negotiation across coroutine context
RH-Jira: RHEL-40959
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/4] 379f38d46d204890e47a5eb744292d728badc7db (ebblake/centos-qemu-kvm)
Coroutines are not supposed to block. Instead, they should yield.
The client performs TLS upgrade outside of an AIOContext, during
synchronous handshake; this still requires g_main_loop. But the
server responds to TLS upgrade inside a coroutine, so a nested
g_main_loop is wrong. Since the two callbacks no longer share more
than the setting of data.complete and data.error, it's just as easy to
use static helpers instead of trying to share a common code path. It
is also possible to add assertions that no other code is interfering
with the eventual path to qio reaching the callback, whether or not it
required a yield or main loop.
Fixes: f95910f ("nbd: implement TLS support in the protocol negotiation")
Signed-off-by: Zhu Yangyang <zhuyangyang14@huawei.com>
[eblake: move callbacks to their use point, add assertions]
Signed-off-by: Eric Blake <eblake@redhat.com>
Message-ID: <20240408160214.1200629-5-eblake@redhat.com>
Reviewed-by: Vladimir Sementsov-Ogievskiy <vsementsov@yandex-team.ru>
Jira: https://issues.redhat.com/browse/RHEL-40959
(cherry picked from commit ae6d91a7e9b77abb029ed3fa9fad461422286942)
Signed-off-by: Eric Blake <eblake@redhat.com>
---
nbd/client.c | 28 ++++++++++++++++++++++++----
nbd/common.c | 11 -----------
nbd/nbd-internal.h | 10 ----------
nbd/server.c | 28 +++++++++++++++++++++++-----
4 files changed, 47 insertions(+), 30 deletions(-)
diff --git a/nbd/client.c b/nbd/client.c
index 29ffc609a4..c89c750467 100644
--- a/nbd/client.c
+++ b/nbd/client.c
@@ -596,13 +596,31 @@ static int nbd_request_simple_option(QIOChannel *ioc, int opt, bool strict,
return 1;
}
+/* Callback to learn when QIO TLS upgrade is complete */
+struct NBDTLSClientHandshakeData {
+ bool complete;
+ Error *error;
+ GMainLoop *loop;
+};
+
+static void nbd_client_tls_handshake(QIOTask *task, void *opaque)
+{
+ struct NBDTLSClientHandshakeData *data = opaque;
+
+ qio_task_propagate_error(task, &data->error);
+ data->complete = true;
+ if (data->loop) {
+ g_main_loop_quit(data->loop);
+ }
+}
+
static QIOChannel *nbd_receive_starttls(QIOChannel *ioc,
QCryptoTLSCreds *tlscreds,
const char *hostname, Error **errp)
{
int ret;
QIOChannelTLS *tioc;
- struct NBDTLSHandshakeData data = { 0 };
+ struct NBDTLSClientHandshakeData data = { 0 };
ret = nbd_request_simple_option(ioc, NBD_OPT_STARTTLS, true, errp);
if (ret <= 0) {
@@ -619,18 +637,20 @@ static QIOChannel *nbd_receive_starttls(QIOChannel *ioc,
return NULL;
}
qio_channel_set_name(QIO_CHANNEL(tioc), "nbd-client-tls");
- data.loop = g_main_loop_new(g_main_context_default(), FALSE);
trace_nbd_receive_starttls_tls_handshake();
qio_channel_tls_handshake(tioc,
- nbd_tls_handshake,
+ nbd_client_tls_handshake,
&data,
NULL,
NULL);
if (!data.complete) {
+ data.loop = g_main_loop_new(g_main_context_default(), FALSE);
g_main_loop_run(data.loop);
+ assert(data.complete);
+ g_main_loop_unref(data.loop);
}
- g_main_loop_unref(data.loop);
+
if (data.error) {
error_propagate(errp, data.error);
object_unref(OBJECT(tioc));
diff --git a/nbd/common.c b/nbd/common.c
index 3247c1d618..589a748cfe 100644
--- a/nbd/common.c
+++ b/nbd/common.c
@@ -47,17 +47,6 @@ int nbd_drop(QIOChannel *ioc, size_t size, Error **errp)
}
-void nbd_tls_handshake(QIOTask *task,
- void *opaque)
-{
- struct NBDTLSHandshakeData *data = opaque;
-
- qio_task_propagate_error(task, &data->error);
- data->complete = true;
- g_main_loop_quit(data->loop);
-}
-
-
const char *nbd_opt_lookup(uint32_t opt)
{
switch (opt) {
diff --git a/nbd/nbd-internal.h b/nbd/nbd-internal.h
index dfa02f77ee..91895106a9 100644
--- a/nbd/nbd-internal.h
+++ b/nbd/nbd-internal.h
@@ -72,16 +72,6 @@ static inline int nbd_write(QIOChannel *ioc, const void *buffer, size_t size,
return qio_channel_write_all(ioc, buffer, size, errp) < 0 ? -EIO : 0;
}
-struct NBDTLSHandshakeData {
- GMainLoop *loop;
- bool complete;
- Error *error;
-};
-
-
-void nbd_tls_handshake(QIOTask *task,
- void *opaque);
-
int nbd_drop(QIOChannel *ioc, size_t size, Error **errp);
#endif
diff --git a/nbd/server.c b/nbd/server.c
index c3484cc1eb..98ae0e1632 100644
--- a/nbd/server.c
+++ b/nbd/server.c
@@ -748,6 +748,23 @@ static int nbd_negotiate_handle_info(NBDClient *client, Error **errp)
return rc;
}
+/* Callback to learn when QIO TLS upgrade is complete */
+struct NBDTLSServerHandshakeData {
+ bool complete;
+ Error *error;
+ Coroutine *co;
+};
+
+static void nbd_server_tls_handshake(QIOTask *task, void *opaque)
+{
+ struct NBDTLSServerHandshakeData *data = opaque;
+
+ qio_task_propagate_error(task, &data->error);
+ data->complete = true;
+ if (!qemu_coroutine_entered(data->co)) {
+ aio_co_wake(data->co);
+ }
+}
/* Handle NBD_OPT_STARTTLS. Return NULL to drop connection, or else the
* new channel for all further (now-encrypted) communication. */
@@ -756,7 +773,7 @@ static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client,
{
QIOChannel *ioc;
QIOChannelTLS *tioc;
- struct NBDTLSHandshakeData data = { 0 };
+ struct NBDTLSServerHandshakeData data = { 0 };
assert(client->opt == NBD_OPT_STARTTLS);
@@ -777,17 +794,18 @@ static QIOChannel *nbd_negotiate_handle_starttls(NBDClient *client,
qio_channel_set_name(QIO_CHANNEL(tioc), "nbd-server-tls");
trace_nbd_negotiate_handle_starttls_handshake();
- data.loop = g_main_loop_new(g_main_context_default(), FALSE);
+ data.co = qemu_coroutine_self();
qio_channel_tls_handshake(tioc,
- nbd_tls_handshake,
+ nbd_server_tls_handshake,
&data,
NULL,
NULL);
if (!data.complete) {
- g_main_loop_run(data.loop);
+ qemu_coroutine_yield();
+ assert(data.complete);
}
- g_main_loop_unref(data.loop);
+
if (data.error) {
object_unref(OBJECT(tioc));
error_propagate(errp, data.error);
--
2.39.3

130
kvm-qio-Inherit-follow_coroutine_ctx-across-TLS.patch Normal file
View File

@ -0,0 +1,130 @@
From 120a2c8a7d936e24948f8f4ada6b781b6cbc9931 Mon Sep 17 00:00:00 2001
From: Eric Blake <eblake@redhat.com>
Date: Fri, 17 May 2024 21:50:14 -0500
Subject: [PATCH 3/4] qio: Inherit follow_coroutine_ctx across TLS
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
RH-Author: Eric Blake <eblake@redhat.com>
RH-MergeRequest: 257: nbd/server: fix TLS negotiation across coroutine context
RH-Jira: RHEL-40959
RH-Acked-by: Stefan Hajnoczi <stefanha@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [3/4] b7fd03af5985bbc5504b1a8e2f5cd165f6e438e5 (ebblake/centos-qemu-kvm)
Since qemu 8.2, the combination of NBD + TLS + iothread crashes on an
assertion failure:
qemu-kvm: ../io/channel.c:534: void qio_channel_restart_read(void *): Assertion `qemu_get_current_aio_context() == qemu_coroutine_get_aio_context(co)' failed.
It turns out that when we removed AioContext locking, we did so by
having NBD tell its qio channels that it wanted to opt in to
qio_channel_set_follow_coroutine_ctx(); but while we opted in on the
main channel, we did not opt in on the TLS wrapper channel.
qemu-iotests has coverage of NBD+iothread and NBD+TLS, but apparently
no coverage of NBD+TLS+iothread, or we would have noticed this
regression sooner. (I'll add that in the next patch)
But while we could manually opt in to the TLS channel in nbd/server.c
(a one-line change), it is more generic if all qio channels that wrap
other channels inherit the follow status, in the same way that they
inherit feature bits.
CC: Stefan Hajnoczi <stefanha@redhat.com>
CC: Daniel P. Berrangé <berrange@redhat.com>
CC: qemu-stable@nongnu.org
Fixes: https://issues.redhat.com/browse/RHEL-34786
Fixes: 06e0f098 ("io: follow coroutine AioContext in qio_channel_yield()", v8.2.0)
Signed-off-by: Eric Blake <eblake@redhat.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Reviewed-by: Daniel P. Berrangé <berrange@redhat.com>
Message-ID: <20240518025246.791593-5-eblake@redhat.com>
(cherry picked from commit 199e84de1c903ba5aa1f7256310bbc4a20dd930b)
Jira: https://issues.redhat.com/browse/RHEL-40959
Signed-off-by: Eric Blake <eblake@redhat.com>
---
io/channel-tls.c | 26 +++++++++++++++-----------
io/channel-websock.c | 1 +
2 files changed, 16 insertions(+), 11 deletions(-)
diff --git a/io/channel-tls.c b/io/channel-tls.c
index 1d9c9c72bf..67b9700006 100644
--- a/io/channel-tls.c
+++ b/io/channel-tls.c
@@ -69,37 +69,40 @@ qio_channel_tls_new_server(QIOChannel *master,
const char *aclname,
Error **errp)
{
- QIOChannelTLS *ioc;
+ QIOChannelTLS *tioc;
+ QIOChannel *ioc;
- ioc = QIO_CHANNEL_TLS(object_new(TYPE_QIO_CHANNEL_TLS));
+ tioc = QIO_CHANNEL_TLS(object_new(TYPE_QIO_CHANNEL_TLS));
+ ioc = QIO_CHANNEL(tioc);
- ioc->master = master;
+ tioc->master = master;
+ ioc->follow_coroutine_ctx = master->follow_coroutine_ctx;
if (qio_channel_has_feature(master, QIO_CHANNEL_FEATURE_SHUTDOWN)) {
- qio_channel_set_feature(QIO_CHANNEL(ioc), QIO_CHANNEL_FEATURE_SHUTDOWN);
+ qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN);
}
object_ref(OBJECT(master));
- ioc->session = qcrypto_tls_session_new(
+ tioc->session = qcrypto_tls_session_new(
creds,
NULL,
aclname,
QCRYPTO_TLS_CREDS_ENDPOINT_SERVER,
errp);
- if (!ioc->session) {
+ if (!tioc->session) {
goto error;
}
qcrypto_tls_session_set_callbacks(
- ioc->session,
+ tioc->session,
qio_channel_tls_write_handler,
qio_channel_tls_read_handler,
- ioc);
+ tioc);
- trace_qio_channel_tls_new_server(ioc, master, creds, aclname);
- return ioc;
+ trace_qio_channel_tls_new_server(tioc, master, creds, aclname);
+ return tioc;
error:
- object_unref(OBJECT(ioc));
+ object_unref(OBJECT(tioc));
return NULL;
}
@@ -116,6 +119,7 @@ qio_channel_tls_new_client(QIOChannel *master,
ioc = QIO_CHANNEL(tioc);
tioc->master = master;
+ ioc->follow_coroutine_ctx = master->follow_coroutine_ctx;
if (qio_channel_has_feature(master, QIO_CHANNEL_FEATURE_SHUTDOWN)) {
qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN);
}
diff --git a/io/channel-websock.c b/io/channel-websock.c
index a12acc27cf..de39f0d182 100644
--- a/io/channel-websock.c
+++ b/io/channel-websock.c
@@ -883,6 +883,7 @@ qio_channel_websock_new_server(QIOChannel *master)
ioc = QIO_CHANNEL(wioc);
wioc->master = master;
+ ioc->follow_coroutine_ctx = master->follow_coroutine_ctx;
if (qio_channel_has_feature(master, QIO_CHANNEL_FEATURE_SHUTDOWN)) {
qio_channel_set_feature(ioc, QIO_CHANNEL_FEATURE_SHUTDOWN);
}
--
2.39.3

18
qemu-kvm.spec
View File

@ -143,7 +143,7 @@ Obsoletes: %{name}-block-ssh <= %{epoch}:%{version} \
Summary: QEMU is a machine emulator and virtualizer
Name: qemu-kvm
Version: 9.0.0
Release: 4%{?rcrel}%{?dist}%{?cc_suffix}
Release: 5%{?rcrel}%{?dist}%{?cc_suffix}
# Epoch because we pushed a qemu-1.0 package. AIUI this can't ever be dropped
# Epoch 15 used for RHEL 8
# Epoch 17 used for RHEL 9 (due to release versioning offset in RHEL 8.5)
@ -222,6 +222,14 @@ Patch34: kvm-iotests-244-Don-t-store-data-file-with-protocol-in-i.patch
Patch35: kvm-iotests-270-Don-t-store-data-file-with-json-prefix-i.patch
# For RHEL-46239 - CVE-2024-4467 qemu-kvm: QEMU: 'qemu-img info' leads to host file read/write [rhel-10.0]
Patch36: kvm-block-Parse-filenames-only-when-explicitly-requested.patch
# For RHEL-40959 - Qemu hang when quit dst vm after storage migration(nbd+tls)
Patch37: kvm-nbd-server-do-not-poll-within-a-coroutine-context.patch
# For RHEL-40959 - Qemu hang when quit dst vm after storage migration(nbd+tls)
Patch38: kvm-nbd-server-Mark-negotiation-functions-as-coroutine_f.patch
# For RHEL-40959 - Qemu hang when quit dst vm after storage migration(nbd+tls)
Patch39: kvm-qio-Inherit-follow_coroutine_ctx-across-TLS.patch
# For RHEL-40959 - Qemu hang when quit dst vm after storage migration(nbd+tls)
Patch40: kvm-iotests-test-NBD-TLS-iothread.patch
%if %{have_clang}
BuildRequires: clang
@ -1287,6 +1295,14 @@ useradd -r -u 107 -g qemu -G kvm -d / -s /sbin/nologin \
%endif
%changelog
* Wed Jul 24 2024 Miroslav Rezanina <mrezanin@redhat.com> - 9.0.0-5
- kvm-nbd-server-do-not-poll-within-a-coroutine-context.patch [RHEL-40959]
- kvm-nbd-server-Mark-negotiation-functions-as-coroutine_f.patch [RHEL-40959]
- kvm-qio-Inherit-follow_coroutine_ctx-across-TLS.patch [RHEL-40959]
- kvm-iotests-test-NBD-TLS-iothread.patch [RHEL-40959]
- Resolves: RHEL-40959
(Qemu hang when quit dst vm after storage migration(nbd+tls))
* Thu Jul 04 2024 Miroslav Rezanina <mrezanin@redhat.com> - 9.0.0-4
- kvm-qcow2-Don-t-open-data_file-with-BDRV_O_NO_IO.patch [RHEL-46239]
- kvm-iotests-244-Don-t-store-data-file-with-protocol-in-i.patch [RHEL-46239]