1
The following changes since commit 474f3938d79ab36b9231c9ad3b5a9314c2aeacde:
1
The following changes since commit 9af638cc1f665712522608c5d6b8c03d8fa67666:
2
2
3
Merge remote-tracking branch 'remotes/amarkovic/tags/mips-queue-jun-21-2019' into staging (2019-06-21 15:40:50 +0100)
3
Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20200504' into staging (2020-05-04 13:37:17 +0100)
4
4
5
are available in the Git repository at:
5
are available in the Git repository at:
6
6
7
https://github.com/XanClic/qemu.git tags/pull-block-2019-06-24
7
https://github.com/stefanha/qemu.git tags/block-pull-request
8
8
9
for you to fetch changes up to ab5d4a30f7f3803ca5106b370969c1b7b54136f8:
9
for you to fetch changes up to 08b689aa6b521964b8275dd7a2564aefa5d68129:
10
10
11
iotests: Fix 205 for concurrent runs (2019-06-24 16:01:40 +0200)
11
lockable: Replace locks with lock guard macros (2020-05-04 16:07:43 +0100)
12
12
13
----------------------------------------------------------------
13
----------------------------------------------------------------
14
Block patches:
14
Pull request
15
- The SSH block driver now uses libssh instead of libssh2
16
- The VMDK block driver gets read-only support for the seSparse
17
subformat
18
- Various fixes
19
20
---
21
15
22
v2:
16
v2:
23
- Squashed Pino's fix for pre-0.8 libssh into the libssh patch
17
* Fixed stray slirp submodule change [Peter]
18
19
Fixes for the lock guard macros, code conversions to the lock guard macros, and
20
support for selecting fuzzer targets with argv[0].
24
21
25
----------------------------------------------------------------
22
----------------------------------------------------------------
26
Anton Nefedov (1):
27
iotest 134: test cluster-misaligned encrypted write
28
23
29
Klaus Birkelund Jensen (1):
24
Alexander Bulekov (1):
30
nvme: do not advertise support for unsupported arbitration mechanism
25
fuzz: select fuzz target using executable name
31
26
32
Max Reitz (1):
27
Daniel Brodsky (2):
33
iotests: Fix 205 for concurrent runs
28
lockable: fix __COUNTER__ macro to be referenced properly
29
lockable: replaced locks with lock guard macros where appropriate
34
30
35
Pino Toscano (1):
31
Simran Singhal (1):
36
ssh: switch from libssh2 to libssh
32
lockable: Replace locks with lock guard macros
37
33
38
Sam Eiderman (3):
34
include/qemu/lockable.h | 7 +++---
39
vmdk: Fix comment regarding max l1_size coverage
35
include/qemu/rcu.h | 2 +-
40
vmdk: Reduce the max bound for L1 table size
36
block/iscsi.c | 7 ++----
41
vmdk: Add read-only support for seSparse snapshots
37
block/nfs.c | 51 +++++++++++++++++++----------------------
42
38
cpus-common.c | 14 ++++-------
43
Vladimir Sementsov-Ogievskiy (1):
39
hw/display/qxl.c | 43 ++++++++++++++++------------------
44
blockdev: enable non-root nodes for transaction drive-backup source
40
hw/hyperv/hyperv.c | 15 ++++++------
45
41
hw/rdma/rdma_backend.c | 50 ++++++++++++++++++++--------------------
46
configure | 65 +-
42
hw/rdma/rdma_rm.c | 3 +--
47
block/Makefile.objs | 6 +-
43
hw/vfio/platform.c | 5 ++--
48
block/ssh.c | 652 ++++++++++--------
44
migration/migration.c | 3 +--
49
block/vmdk.c | 372 +++++++++-
45
migration/multifd.c | 8 +++----
50
blockdev.c | 2 +-
46
migration/ram.c | 3 +--
51
hw/block/nvme.c | 1 -
47
monitor/misc.c | 4 +---
52
.travis.yml | 4 +-
48
tests/qtest/fuzz/fuzz.c | 19 ++++++++-------
53
block/trace-events | 14 +-
49
ui/spice-display.c | 14 +++++------
54
docs/qemu-block-drivers.texi | 2 +-
50
util/log.c | 4 ++--
55
.../dockerfiles/debian-win32-cross.docker | 1 -
51
util/qemu-timer.c | 17 +++++++-------
56
.../dockerfiles/debian-win64-cross.docker | 1 -
52
util/rcu.c | 8 +++----
57
tests/docker/dockerfiles/fedora.docker | 4 +-
53
util/thread-pool.c | 3 +--
58
tests/docker/dockerfiles/ubuntu.docker | 2 +-
54
util/vfio-helpers.c | 5 ++--
59
tests/docker/dockerfiles/ubuntu1804.docker | 2 +-
55
21 files changed, 132 insertions(+), 153 deletions(-)
60
tests/qemu-iotests/059.out | 2 +-
61
tests/qemu-iotests/134 | 9 +
62
tests/qemu-iotests/134.out | 10 +
63
tests/qemu-iotests/205 | 2 +-
64
tests/qemu-iotests/207 | 54 +-
65
tests/qemu-iotests/207.out | 2 +-
66
20 files changed, 823 insertions(+), 384 deletions(-)
67
56
68
--
57
--
69
2.21.0
58
2.25.3
70
59
71
diff view generated by jsdifflib
Deleted patch
1
From: Klaus Birkelund Jensen <klaus@birkelund.eu>
2
1
3
The device mistakenly reports that the Weighted Round Robin with Urgent
4
Priority Class arbitration mechanism is supported.
5
6
It is not.
7
8
Signed-off-by: Klaus Birkelund Jensen <klaus.jensen@cnexlabs.com>
9
Message-id: 20190606092530.14206-1-klaus@birkelund.eu
10
Acked-by: Maxim Levitsky <mlevitsk@redhat.com>
11
Signed-off-by: Max Reitz <mreitz@redhat.com>
12
---
13
hw/block/nvme.c | 1 -
14
1 file changed, 1 deletion(-)
15
16
diff --git a/hw/block/nvme.c b/hw/block/nvme.c
17
index XXXXXXX..XXXXXXX 100644
18
--- a/hw/block/nvme.c
19
+++ b/hw/block/nvme.c
20
@@ -XXX,XX +XXX,XX @@ static void nvme_realize(PCIDevice *pci_dev, Error **errp)
21
n->bar.cap = 0;
22
NVME_CAP_SET_MQES(n->bar.cap, 0x7ff);
23
NVME_CAP_SET_CQR(n->bar.cap, 1);
24
- NVME_CAP_SET_AMS(n->bar.cap, 1);
25
NVME_CAP_SET_TO(n->bar.cap, 0xf);
26
NVME_CAP_SET_CSS(n->bar.cap, 1);
27
NVME_CAP_SET_MPSMAX(n->bar.cap, 4);
28
--
29
2.21.0
30
31
diff view generated by jsdifflib
1
From: Pino Toscano <ptoscano@redhat.com>
1
From: Alexander Bulekov <alxndr@bu.edu>
2
2
3
Rewrite the implementation of the ssh block driver to use libssh instead
3
The fuzzers are built into a binary (e.g. qemu-fuzz-i386). To select the
4
of libssh2. The libssh library has various advantages over libssh2:
4
device to fuzz/fuzz target, we usually use the --fuzz-target= argument.
5
- easier API for authentication (for example for using ssh-agent)
5
This commit allows the fuzz-target to be specified using the name of the
6
- easier API for known_hosts handling
6
executable. If the executable name ends with -target-FUZZ_TARGET, then
7
- supports newer types of keys in known_hosts
7
we select the fuzz target based on this name, rather than the
8
--fuzz-target argument. This is useful for systems such as oss-fuzz
9
where we don't have control of the arguments passed to the fuzzer.
8
10
9
Use APIs/features available in libssh 0.8 conditionally, to support
11
[Fixed incorrect indentation.
10
older versions (which are not recommended though).
12
--Stefan]
11
13
12
Adjust the iotest 207 according to the different error message, and to
14
Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
13
find the default key type for localhost (to properly compare the
15
Reviewed-by: Darren Kenny <darren.kenny@oracle.com>
14
fingerprint with).
16
Message-id: 20200421182230.6313-1-alxndr@bu.edu
15
Contributed-by: Max Reitz <mreitz@redhat.com>
17
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
18
---
19
tests/qtest/fuzz/fuzz.c | 19 +++++++++++--------
20
1 file changed, 11 insertions(+), 8 deletions(-)
16
21
17
Adjust the various Docker/Travis scripts to use libssh when available
22
diff --git a/tests/qtest/fuzz/fuzz.c b/tests/qtest/fuzz/fuzz.c
18
instead of libssh2. The mingw/mxe testing is dropped for now, as there
19
are no packages for it.
20
21
Signed-off-by: Pino Toscano <ptoscano@redhat.com>
22
Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com>
23
Acked-by: Alex Bennée <alex.bennee@linaro.org>
24
Message-id: 20190620200840.17655-1-ptoscano@redhat.com
25
Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com>
26
Message-id: 5873173.t2JhDm7DL7@lindworm.usersys.redhat.com
27
Signed-off-by: Max Reitz <mreitz@redhat.com>
28
---
29
configure | 65 +-
30
block/Makefile.objs | 6 +-
31
block/ssh.c | 652 ++++++++++--------
32
.travis.yml | 4 +-
33
block/trace-events | 14 +-
34
docs/qemu-block-drivers.texi | 2 +-
35
.../dockerfiles/debian-win32-cross.docker | 1 -
36
.../dockerfiles/debian-win64-cross.docker | 1 -
37
tests/docker/dockerfiles/fedora.docker | 4 +-
38
tests/docker/dockerfiles/ubuntu.docker | 2 +-
39
tests/docker/dockerfiles/ubuntu1804.docker | 2 +-
40
tests/qemu-iotests/207 | 54 +-
41
tests/qemu-iotests/207.out | 2 +-
42
13 files changed, 449 insertions(+), 360 deletions(-)
43
44
diff --git a/configure b/configure
45
index XXXXXXX..XXXXXXX 100755
46
--- a/configure
47
+++ b/configure
48
@@ -XXX,XX +XXX,XX @@ auth_pam=""
49
vte=""
50
virglrenderer=""
51
tpm=""
52
-libssh2=""
53
+libssh=""
54
live_block_migration="yes"
55
numa=""
56
tcmalloc="no"
57
@@ -XXX,XX +XXX,XX @@ for opt do
58
;;
59
--enable-tpm) tpm="yes"
60
;;
61
- --disable-libssh2) libssh2="no"
62
+ --disable-libssh) libssh="no"
63
;;
64
- --enable-libssh2) libssh2="yes"
65
+ --enable-libssh) libssh="yes"
66
;;
67
--disable-live-block-migration) live_block_migration="no"
68
;;
69
@@ -XXX,XX +XXX,XX @@ disabled with --disable-FEATURE, default is enabled if available:
70
coroutine-pool coroutine freelist (better performance)
71
glusterfs GlusterFS backend
72
tpm TPM support
73
- libssh2 ssh block device support
74
+ libssh ssh block device support
75
numa libnuma support
76
libxml2 for Parallels image format
77
tcmalloc tcmalloc support
78
@@ -XXX,XX +XXX,XX @@ EOF
79
fi
80
81
##########################################
82
-# libssh2 probe
83
-min_libssh2_version=1.2.8
84
-if test "$libssh2" != "no" ; then
85
- if $pkg_config --atleast-version=$min_libssh2_version libssh2; then
86
- libssh2_cflags=$($pkg_config libssh2 --cflags)
87
- libssh2_libs=$($pkg_config libssh2 --libs)
88
- libssh2=yes
89
+# libssh probe
90
+if test "$libssh" != "no" ; then
91
+ if $pkg_config --exists libssh; then
92
+ libssh_cflags=$($pkg_config libssh --cflags)
93
+ libssh_libs=$($pkg_config libssh --libs)
94
+ libssh=yes
95
else
96
- if test "$libssh2" = "yes" ; then
97
- error_exit "libssh2 >= $min_libssh2_version required for --enable-libssh2"
98
+ if test "$libssh" = "yes" ; then
99
+ error_exit "libssh required for --enable-libssh"
100
fi
101
- libssh2=no
102
+ libssh=no
103
fi
104
fi
105
106
##########################################
107
-# libssh2_sftp_fsync probe
108
+# Check for libssh 0.8
109
+# This is done like this instead of using the LIBSSH_VERSION_* and
110
+# SSH_VERSION_* macros because some distributions in the past shipped
111
+# snapshots of the future 0.8 from Git, and those snapshots did not
112
+# have updated version numbers (still referring to 0.7.0).
113
114
-if test "$libssh2" = "yes"; then
115
+if test "$libssh" = "yes"; then
116
cat > $TMPC <<EOF
117
-#include <stdio.h>
118
-#include <libssh2.h>
119
-#include <libssh2_sftp.h>
120
-int main(void) {
121
- LIBSSH2_SESSION *session;
122
- LIBSSH2_SFTP *sftp;
123
- LIBSSH2_SFTP_HANDLE *sftp_handle;
124
- session = libssh2_session_init ();
125
- sftp = libssh2_sftp_init (session);
126
- sftp_handle = libssh2_sftp_open (sftp, "/", 0, 0);
127
- libssh2_sftp_fsync (sftp_handle);
128
- return 0;
129
-}
130
+#include <libssh/libssh.h>
131
+int main(void) { return ssh_get_server_publickey(NULL, NULL); }
132
EOF
133
- # libssh2_cflags/libssh2_libs defined in previous test.
134
- if compile_prog "$libssh2_cflags" "$libssh2_libs" ; then
135
- QEMU_CFLAGS="-DHAS_LIBSSH2_SFTP_FSYNC $QEMU_CFLAGS"
136
+ if compile_prog "$libssh_cflags" "$libssh_libs"; then
137
+ libssh_cflags="-DHAVE_LIBSSH_0_8 $libssh_cflags"
138
fi
139
fi
140
141
@@ -XXX,XX +XXX,XX @@ echo "GlusterFS support $glusterfs"
142
echo "gcov $gcov_tool"
143
echo "gcov enabled $gcov"
144
echo "TPM support $tpm"
145
-echo "libssh2 support $libssh2"
146
+echo "libssh support $libssh"
147
echo "QOM debugging $qom_cast_debug"
148
echo "Live block migration $live_block_migration"
149
echo "lzo support $lzo"
150
@@ -XXX,XX +XXX,XX @@ if test "$glusterfs_iocb_has_stat" = "yes" ; then
151
echo "CONFIG_GLUSTERFS_IOCB_HAS_STAT=y" >> $config_host_mak
152
fi
153
154
-if test "$libssh2" = "yes" ; then
155
- echo "CONFIG_LIBSSH2=m" >> $config_host_mak
156
- echo "LIBSSH2_CFLAGS=$libssh2_cflags" >> $config_host_mak
157
- echo "LIBSSH2_LIBS=$libssh2_libs" >> $config_host_mak
158
+if test "$libssh" = "yes" ; then
159
+ echo "CONFIG_LIBSSH=m" >> $config_host_mak
160
+ echo "LIBSSH_CFLAGS=$libssh_cflags" >> $config_host_mak
161
+ echo "LIBSSH_LIBS=$libssh_libs" >> $config_host_mak
162
fi
163
164
if test "$live_block_migration" = "yes" ; then
165
diff --git a/block/Makefile.objs b/block/Makefile.objs
166
index XXXXXXX..XXXXXXX 100644
23
index XXXXXXX..XXXXXXX 100644
167
--- a/block/Makefile.objs
24
--- a/tests/qtest/fuzz/fuzz.c
168
+++ b/block/Makefile.objs
25
+++ b/tests/qtest/fuzz/fuzz.c
169
@@ -XXX,XX +XXX,XX @@ block-obj-$(CONFIG_CURL) += curl.o
26
@@ -XXX,XX +XXX,XX @@ static void usage(char *path)
170
block-obj-$(CONFIG_RBD) += rbd.o
27
printf(" * %s : %s\n", tmp->target->name,
171
block-obj-$(CONFIG_GLUSTERFS) += gluster.o
28
tmp->target->description);
172
block-obj-$(CONFIG_VXHS) += vxhs.o
29
}
173
-block-obj-$(CONFIG_LIBSSH2) += ssh.o
30
+ printf("Alternatively, add -target-FUZZ_TARGET to the executable name\n");
174
+block-obj-$(CONFIG_LIBSSH) += ssh.o
31
exit(0);
175
block-obj-y += accounting.o dirty-bitmap.o
176
block-obj-y += write-threshold.o
177
block-obj-y += backup.o
178
@@ -XXX,XX +XXX,XX @@ rbd.o-libs := $(RBD_LIBS)
179
gluster.o-cflags := $(GLUSTERFS_CFLAGS)
180
gluster.o-libs := $(GLUSTERFS_LIBS)
181
vxhs.o-libs := $(VXHS_LIBS)
182
-ssh.o-cflags := $(LIBSSH2_CFLAGS)
183
-ssh.o-libs := $(LIBSSH2_LIBS)
184
+ssh.o-cflags := $(LIBSSH_CFLAGS)
185
+ssh.o-libs := $(LIBSSH_LIBS)
186
block-obj-dmg-bz2-$(CONFIG_BZIP2) += dmg-bz2.o
187
block-obj-$(if $(CONFIG_DMG),m,n) += $(block-obj-dmg-bz2-y)
188
dmg-bz2.o-libs := $(BZIP2_LIBS)
189
diff --git a/block/ssh.c b/block/ssh.c
190
index XXXXXXX..XXXXXXX 100644
191
--- a/block/ssh.c
192
+++ b/block/ssh.c
193
@@ -XXX,XX +XXX,XX @@
194
195
#include "qemu/osdep.h"
196
197
-#include <libssh2.h>
198
-#include <libssh2_sftp.h>
199
+#include <libssh/libssh.h>
200
+#include <libssh/sftp.h>
201
202
#include "block/block_int.h"
203
#include "block/qdict.h"
204
@@ -XXX,XX +XXX,XX @@
205
#include "trace.h"
206
207
/*
208
- * TRACE_LIBSSH2=<bitmask> enables tracing in libssh2 itself. Note
209
- * that this requires that libssh2 was specially compiled with the
210
- * `./configure --enable-debug' option, so most likely you will have
211
- * to compile it yourself. The meaning of <bitmask> is described
212
- * here: http://www.libssh2.org/libssh2_trace.html
213
+ * TRACE_LIBSSH=<level> enables tracing in libssh itself.
214
+ * The meaning of <level> is described here:
215
+ * http://api.libssh.org/master/group__libssh__log.html
216
*/
217
-#define TRACE_LIBSSH2 0 /* or try: LIBSSH2_TRACE_SFTP */
218
+#define TRACE_LIBSSH 0 /* see: SSH_LOG_* */
219
220
typedef struct BDRVSSHState {
221
/* Coroutine. */
222
@@ -XXX,XX +XXX,XX @@ typedef struct BDRVSSHState {
223
224
/* SSH connection. */
225
int sock; /* socket */
226
- LIBSSH2_SESSION *session; /* ssh session */
227
- LIBSSH2_SFTP *sftp; /* sftp session */
228
- LIBSSH2_SFTP_HANDLE *sftp_handle; /* sftp remote file handle */
229
+ ssh_session session; /* ssh session */
230
+ sftp_session sftp; /* sftp session */
231
+ sftp_file sftp_handle; /* sftp remote file handle */
232
233
- /* See ssh_seek() function below. */
234
- int64_t offset;
235
- bool offset_op_read;
236
-
237
- /* File attributes at open. We try to keep the .filesize field
238
+ /*
239
+ * File attributes at open. We try to keep the .size field
240
* updated if it changes (eg by writing at the end of the file).
241
*/
242
- LIBSSH2_SFTP_ATTRIBUTES attrs;
243
+ sftp_attributes attrs;
244
245
InetSocketAddress *inet;
246
247
@@ -XXX,XX +XXX,XX @@ static void ssh_state_init(BDRVSSHState *s)
248
{
249
memset(s, 0, sizeof *s);
250
s->sock = -1;
251
- s->offset = -1;
252
qemu_co_mutex_init(&s->lock);
253
}
32
}
254
33
255
@@ -XXX,XX +XXX,XX @@ static void ssh_state_free(BDRVSSHState *s)
34
@@ -XXX,XX +XXX,XX @@ int LLVMFuzzerInitialize(int *argc, char ***argv, char ***envp)
256
{
35
module_call_init(MODULE_INIT_QOM);
257
g_free(s->user);
36
module_call_init(MODULE_INIT_LIBQOS);
258
37
259
+ if (s->attrs) {
38
- if (*argc <= 1) {
260
+ sftp_attributes_free(s->attrs);
39
+ target_name = strstr(**argv, "-target-");
261
+ }
40
+ if (target_name) { /* The binary name specifies the target */
262
if (s->sftp_handle) {
41
+ target_name += strlen("-target-");
263
- libssh2_sftp_close(s->sftp_handle);
42
+ } else if (*argc > 1) { /* The target is specified as an argument */
264
+ sftp_close(s->sftp_handle);
43
+ target_name = (*argv)[1];
44
+ if (!strstr(target_name, "--fuzz-target=")) {
45
+ usage(**argv);
46
+ }
47
+ target_name += strlen("--fuzz-target=");
48
+ } else {
49
usage(**argv);
265
}
50
}
266
if (s->sftp) {
51
267
- libssh2_sftp_shutdown(s->sftp);
52
/* Identify the fuzz target */
268
+ sftp_free(s->sftp);
53
- target_name = (*argv)[1];
269
}
54
- if (!strstr(target_name, "--fuzz-target=")) {
270
if (s->session) {
55
- usage(**argv);
271
- libssh2_session_disconnect(s->session,
272
- "from qemu ssh client: "
273
- "user closed the connection");
274
- libssh2_session_free(s->session);
275
- }
276
- if (s->sock >= 0) {
277
- close(s->sock);
278
+ ssh_disconnect(s->session);
279
+ ssh_free(s->session); /* This frees s->sock */
280
}
281
}
282
283
@@ -XXX,XX +XXX,XX @@ session_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
284
va_end(args);
285
286
if (s->session) {
287
- char *ssh_err;
288
+ const char *ssh_err;
289
int ssh_err_code;
290
291
- /* This is not an errno. See <libssh2.h>. */
292
- ssh_err_code = libssh2_session_last_error(s->session,
293
- &ssh_err, NULL, 0);
294
- error_setg(errp, "%s: %s (libssh2 error code: %d)",
295
+ /* This is not an errno. See <libssh/libssh.h>. */
296
+ ssh_err = ssh_get_error(s->session);
297
+ ssh_err_code = ssh_get_error_code(s->session);
298
+ error_setg(errp, "%s: %s (libssh error code: %d)",
299
msg, ssh_err, ssh_err_code);
300
} else {
301
error_setg(errp, "%s", msg);
302
@@ -XXX,XX +XXX,XX @@ sftp_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
303
va_end(args);
304
305
if (s->sftp) {
306
- char *ssh_err;
307
+ const char *ssh_err;
308
int ssh_err_code;
309
- unsigned long sftp_err_code;
310
+ int sftp_err_code;
311
312
- /* This is not an errno. See <libssh2.h>. */
313
- ssh_err_code = libssh2_session_last_error(s->session,
314
- &ssh_err, NULL, 0);
315
- /* See <libssh2_sftp.h>. */
316
- sftp_err_code = libssh2_sftp_last_error((s)->sftp);
317
+ /* This is not an errno. See <libssh/libssh.h>. */
318
+ ssh_err = ssh_get_error(s->session);
319
+ ssh_err_code = ssh_get_error_code(s->session);
320
+ /* See <libssh/sftp.h>. */
321
+ sftp_err_code = sftp_get_error(s->sftp);
322
323
error_setg(errp,
324
- "%s: %s (libssh2 error code: %d, sftp error code: %lu)",
325
+ "%s: %s (libssh error code: %d, sftp error code: %d)",
326
msg, ssh_err, ssh_err_code, sftp_err_code);
327
} else {
328
error_setg(errp, "%s", msg);
329
@@ -XXX,XX +XXX,XX @@ sftp_error_setg(Error **errp, BDRVSSHState *s, const char *fs, ...)
330
331
static void sftp_error_trace(BDRVSSHState *s, const char *op)
332
{
333
- char *ssh_err;
334
+ const char *ssh_err;
335
int ssh_err_code;
336
- unsigned long sftp_err_code;
337
+ int sftp_err_code;
338
339
- /* This is not an errno. See <libssh2.h>. */
340
- ssh_err_code = libssh2_session_last_error(s->session,
341
- &ssh_err, NULL, 0);
342
- /* See <libssh2_sftp.h>. */
343
- sftp_err_code = libssh2_sftp_last_error((s)->sftp);
344
+ /* This is not an errno. See <libssh/libssh.h>. */
345
+ ssh_err = ssh_get_error(s->session);
346
+ ssh_err_code = ssh_get_error_code(s->session);
347
+ /* See <libssh/sftp.h>. */
348
+ sftp_err_code = sftp_get_error(s->sftp);
349
350
trace_sftp_error(op, ssh_err, ssh_err_code, sftp_err_code);
351
}
352
@@ -XXX,XX +XXX,XX @@ static void ssh_parse_filename(const char *filename, QDict *options,
353
parse_uri(filename, options, errp);
354
}
355
356
-static int check_host_key_knownhosts(BDRVSSHState *s,
357
- const char *host, int port, Error **errp)
358
+static int check_host_key_knownhosts(BDRVSSHState *s, Error **errp)
359
{
360
- const char *home;
361
- char *knh_file = NULL;
362
- LIBSSH2_KNOWNHOSTS *knh = NULL;
363
- struct libssh2_knownhost *found;
364
- int ret, r;
365
- const char *hostkey;
366
- size_t len;
367
- int type;
368
-
369
- hostkey = libssh2_session_hostkey(s->session, &len, &type);
370
- if (!hostkey) {
371
+ int ret;
372
+#ifdef HAVE_LIBSSH_0_8
373
+ enum ssh_known_hosts_e state;
374
+ int r;
375
+ ssh_key pubkey;
376
+ enum ssh_keytypes_e pubkey_type;
377
+ unsigned char *server_hash = NULL;
378
+ size_t server_hash_len;
379
+ char *fingerprint = NULL;
380
+
381
+ state = ssh_session_is_known_server(s->session);
382
+ trace_ssh_server_status(state);
383
+
384
+ switch (state) {
385
+ case SSH_KNOWN_HOSTS_OK:
386
+ /* OK */
387
+ trace_ssh_check_host_key_knownhosts();
388
+ break;
389
+ case SSH_KNOWN_HOSTS_CHANGED:
390
ret = -EINVAL;
391
- session_error_setg(errp, s, "failed to read remote host key");
392
+ r = ssh_get_server_publickey(s->session, &pubkey);
393
+ if (r == 0) {
394
+ r = ssh_get_publickey_hash(pubkey, SSH_PUBLICKEY_HASH_SHA256,
395
+ &server_hash, &server_hash_len);
396
+ pubkey_type = ssh_key_type(pubkey);
397
+ ssh_key_free(pubkey);
398
+ }
399
+ if (r == 0) {
400
+ fingerprint = ssh_get_fingerprint_hash(SSH_PUBLICKEY_HASH_SHA256,
401
+ server_hash,
402
+ server_hash_len);
403
+ ssh_clean_pubkey_hash(&server_hash);
404
+ }
405
+ if (fingerprint) {
406
+ error_setg(errp,
407
+ "host key (%s key with fingerprint %s) does not match "
408
+ "the one in known_hosts; this may be a possible attack",
409
+ ssh_key_type_to_char(pubkey_type), fingerprint);
410
+ ssh_string_free_char(fingerprint);
411
+ } else {
412
+ error_setg(errp,
413
+ "host key does not match the one in known_hosts; this "
414
+ "may be a possible attack");
415
+ }
416
goto out;
417
- }
56
- }
418
-
57
-
419
- knh = libssh2_knownhost_init(s->session);
58
- target_name += strlen("--fuzz-target=");
420
- if (!knh) {
421
+ case SSH_KNOWN_HOSTS_OTHER:
422
ret = -EINVAL;
423
- session_error_setg(errp, s,
424
- "failed to initialize known hosts support");
425
+ error_setg(errp,
426
+ "host key for this server not found, another type exists");
427
+ goto out;
428
+ case SSH_KNOWN_HOSTS_UNKNOWN:
429
+ ret = -EINVAL;
430
+ error_setg(errp, "no host key was found in known_hosts");
431
+ goto out;
432
+ case SSH_KNOWN_HOSTS_NOT_FOUND:
433
+ ret = -ENOENT;
434
+ error_setg(errp, "known_hosts file not found");
435
+ goto out;
436
+ case SSH_KNOWN_HOSTS_ERROR:
437
+ ret = -EINVAL;
438
+ error_setg(errp, "error while checking the host");
439
+ goto out;
440
+ default:
441
+ ret = -EINVAL;
442
+ error_setg(errp, "error while checking for known server (%d)", state);
443
goto out;
444
}
445
+#else /* !HAVE_LIBSSH_0_8 */
446
+ int state;
447
448
- home = getenv("HOME");
449
- if (home) {
450
- knh_file = g_strdup_printf("%s/.ssh/known_hosts", home);
451
- } else {
452
- knh_file = g_strdup_printf("/root/.ssh/known_hosts");
453
- }
454
-
59
-
455
- /* Read all known hosts from OpenSSH-style known_hosts file. */
60
fuzz_target = fuzz_get_target(target_name);
456
- libssh2_knownhost_readfile(knh, knh_file, LIBSSH2_KNOWNHOST_FILE_OPENSSH);
61
if (!fuzz_target) {
457
+ state = ssh_is_server_known(s->session);
62
usage(**argv);
458
+ trace_ssh_server_status(state);
459
460
- r = libssh2_knownhost_checkp(knh, host, port, hostkey, len,
461
- LIBSSH2_KNOWNHOST_TYPE_PLAIN|
462
- LIBSSH2_KNOWNHOST_KEYENC_RAW,
463
- &found);
464
- switch (r) {
465
- case LIBSSH2_KNOWNHOST_CHECK_MATCH:
466
+ switch (state) {
467
+ case SSH_SERVER_KNOWN_OK:
468
/* OK */
469
- trace_ssh_check_host_key_knownhosts(found->key);
470
+ trace_ssh_check_host_key_knownhosts();
471
break;
472
- case LIBSSH2_KNOWNHOST_CHECK_MISMATCH:
473
+ case SSH_SERVER_KNOWN_CHANGED:
474
ret = -EINVAL;
475
- session_error_setg(errp, s,
476
- "host key does not match the one in known_hosts"
477
- " (found key %s)", found->key);
478
+ error_setg(errp,
479
+ "host key does not match the one in known_hosts; this "
480
+ "may be a possible attack");
481
goto out;
482
- case LIBSSH2_KNOWNHOST_CHECK_NOTFOUND:
483
+ case SSH_SERVER_FOUND_OTHER:
484
ret = -EINVAL;
485
- session_error_setg(errp, s, "no host key was found in known_hosts");
486
+ error_setg(errp,
487
+ "host key for this server not found, another type exists");
488
+ goto out;
489
+ case SSH_SERVER_FILE_NOT_FOUND:
490
+ ret = -ENOENT;
491
+ error_setg(errp, "known_hosts file not found");
492
goto out;
493
- case LIBSSH2_KNOWNHOST_CHECK_FAILURE:
494
+ case SSH_SERVER_NOT_KNOWN:
495
ret = -EINVAL;
496
- session_error_setg(errp, s,
497
- "failure matching the host key with known_hosts");
498
+ error_setg(errp, "no host key was found in known_hosts");
499
+ goto out;
500
+ case SSH_SERVER_ERROR:
501
+ ret = -EINVAL;
502
+ error_setg(errp, "server error");
503
goto out;
504
default:
505
ret = -EINVAL;
506
- session_error_setg(errp, s, "unknown error matching the host key"
507
- " with known_hosts (%d)", r);
508
+ error_setg(errp, "error while checking for known server (%d)", state);
509
goto out;
510
}
511
+#endif /* !HAVE_LIBSSH_0_8 */
512
513
/* known_hosts checking successful. */
514
ret = 0;
515
516
out:
517
- if (knh != NULL) {
518
- libssh2_knownhost_free(knh);
519
- }
520
- g_free(knh_file);
521
return ret;
522
}
523
524
@@ -XXX,XX +XXX,XX @@ static int compare_fingerprint(const unsigned char *fingerprint, size_t len,
525
526
static int
527
check_host_key_hash(BDRVSSHState *s, const char *hash,
528
- int hash_type, size_t fingerprint_len, Error **errp)
529
+ enum ssh_publickey_hash_type type, Error **errp)
530
{
531
- const char *fingerprint;
532
-
533
- fingerprint = libssh2_hostkey_hash(s->session, hash_type);
534
- if (!fingerprint) {
535
+ int r;
536
+ ssh_key pubkey;
537
+ unsigned char *server_hash;
538
+ size_t server_hash_len;
539
+
540
+#ifdef HAVE_LIBSSH_0_8
541
+ r = ssh_get_server_publickey(s->session, &pubkey);
542
+#else
543
+ r = ssh_get_publickey(s->session, &pubkey);
544
+#endif
545
+ if (r != SSH_OK) {
546
session_error_setg(errp, s, "failed to read remote host key");
547
return -EINVAL;
548
}
549
550
- if(compare_fingerprint((unsigned char *) fingerprint, fingerprint_len,
551
- hash) != 0) {
552
+ r = ssh_get_publickey_hash(pubkey, type, &server_hash, &server_hash_len);
553
+ ssh_key_free(pubkey);
554
+ if (r != 0) {
555
+ session_error_setg(errp, s,
556
+ "failed reading the hash of the server SSH key");
557
+ return -EINVAL;
558
+ }
559
+
560
+ r = compare_fingerprint(server_hash, server_hash_len, hash);
561
+ ssh_clean_pubkey_hash(&server_hash);
562
+ if (r != 0) {
563
error_setg(errp, "remote host key does not match host_key_check '%s'",
564
hash);
565
return -EPERM;
566
@@ -XXX,XX +XXX,XX @@ check_host_key_hash(BDRVSSHState *s, const char *hash,
567
return 0;
568
}
569
570
-static int check_host_key(BDRVSSHState *s, const char *host, int port,
571
- SshHostKeyCheck *hkc, Error **errp)
572
+static int check_host_key(BDRVSSHState *s, SshHostKeyCheck *hkc, Error **errp)
573
{
574
SshHostKeyCheckMode mode;
575
576
@@ -XXX,XX +XXX,XX @@ static int check_host_key(BDRVSSHState *s, const char *host, int port,
577
case SSH_HOST_KEY_CHECK_MODE_HASH:
578
if (hkc->u.hash.type == SSH_HOST_KEY_CHECK_HASH_TYPE_MD5) {
579
return check_host_key_hash(s, hkc->u.hash.hash,
580
- LIBSSH2_HOSTKEY_HASH_MD5, 16, errp);
581
+ SSH_PUBLICKEY_HASH_MD5, errp);
582
} else if (hkc->u.hash.type == SSH_HOST_KEY_CHECK_HASH_TYPE_SHA1) {
583
return check_host_key_hash(s, hkc->u.hash.hash,
584
- LIBSSH2_HOSTKEY_HASH_SHA1, 20, errp);
585
+ SSH_PUBLICKEY_HASH_SHA1, errp);
586
}
587
g_assert_not_reached();
588
break;
589
case SSH_HOST_KEY_CHECK_MODE_KNOWN_HOSTS:
590
- return check_host_key_knownhosts(s, host, port, errp);
591
+ return check_host_key_knownhosts(s, errp);
592
default:
593
g_assert_not_reached();
594
}
595
@@ -XXX,XX +XXX,XX @@ static int check_host_key(BDRVSSHState *s, const char *host, int port,
596
return -EINVAL;
597
}
598
599
-static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
600
+static int authenticate(BDRVSSHState *s, Error **errp)
601
{
602
int r, ret;
603
- const char *userauthlist;
604
- LIBSSH2_AGENT *agent = NULL;
605
- struct libssh2_agent_publickey *identity;
606
- struct libssh2_agent_publickey *prev_identity = NULL;
607
+ int method;
608
609
- userauthlist = libssh2_userauth_list(s->session, user, strlen(user));
610
- if (strstr(userauthlist, "publickey") == NULL) {
611
+ /* Try to authenticate with the "none" method. */
612
+ r = ssh_userauth_none(s->session, NULL);
613
+ if (r == SSH_AUTH_ERROR) {
614
ret = -EPERM;
615
- error_setg(errp,
616
- "remote server does not support \"publickey\" authentication");
617
+ session_error_setg(errp, s, "failed to authenticate using none "
618
+ "authentication");
619
goto out;
620
- }
621
-
622
- /* Connect to ssh-agent and try each identity in turn. */
623
- agent = libssh2_agent_init(s->session);
624
- if (!agent) {
625
- ret = -EINVAL;
626
- session_error_setg(errp, s, "failed to initialize ssh-agent support");
627
- goto out;
628
- }
629
- if (libssh2_agent_connect(agent)) {
630
- ret = -ECONNREFUSED;
631
- session_error_setg(errp, s, "failed to connect to ssh-agent");
632
- goto out;
633
- }
634
- if (libssh2_agent_list_identities(agent)) {
635
- ret = -EINVAL;
636
- session_error_setg(errp, s,
637
- "failed requesting identities from ssh-agent");
638
+ } else if (r == SSH_AUTH_SUCCESS) {
639
+ /* Authenticated! */
640
+ ret = 0;
641
goto out;
642
}
643
644
- for(;;) {
645
- r = libssh2_agent_get_identity(agent, &identity, prev_identity);
646
- if (r == 1) { /* end of list */
647
- break;
648
- }
649
- if (r < 0) {
650
+ method = ssh_userauth_list(s->session, NULL);
651
+ trace_ssh_auth_methods(method);
652
+
653
+ /*
654
+ * Try to authenticate with publickey, using the ssh-agent
655
+ * if available.
656
+ */
657
+ if (method & SSH_AUTH_METHOD_PUBLICKEY) {
658
+ r = ssh_userauth_publickey_auto(s->session, NULL, NULL);
659
+ if (r == SSH_AUTH_ERROR) {
660
ret = -EINVAL;
661
- session_error_setg(errp, s,
662
- "failed to obtain identity from ssh-agent");
663
+ session_error_setg(errp, s, "failed to authenticate using "
664
+ "publickey authentication");
665
goto out;
666
- }
667
- r = libssh2_agent_userauth(agent, user, identity);
668
- if (r == 0) {
669
+ } else if (r == SSH_AUTH_SUCCESS) {
670
/* Authenticated! */
671
ret = 0;
672
goto out;
673
}
674
- /* Failed to authenticate with this identity, try the next one. */
675
- prev_identity = identity;
676
}
677
678
ret = -EPERM;
679
@@ -XXX,XX +XXX,XX @@ static int authenticate(BDRVSSHState *s, const char *user, Error **errp)
680
"and the identities held by your ssh-agent");
681
682
out:
683
- if (agent != NULL) {
684
- /* Note: libssh2 implementation implicitly calls
685
- * libssh2_agent_disconnect if necessary.
686
- */
687
- libssh2_agent_free(agent);
688
- }
689
-
690
return ret;
691
}
692
693
@@ -XXX,XX +XXX,XX @@ static int connect_to_ssh(BDRVSSHState *s, BlockdevOptionsSsh *opts,
694
int ssh_flags, int creat_mode, Error **errp)
695
{
696
int r, ret;
697
- long port = 0;
698
+ unsigned int port = 0;
699
+ int new_sock = -1;
700
701
if (opts->has_user) {
702
s->user = g_strdup(opts->user);
703
@@ -XXX,XX +XXX,XX @@ static int connect_to_ssh(BDRVSSHState *s, BlockdevOptionsSsh *opts,
704
s->inet = opts->server;
705
opts->server = NULL;
706
707
- if (qemu_strtol(s->inet->port, NULL, 10, &port) < 0) {
708
+ if (qemu_strtoui(s->inet->port, NULL, 10, &port) < 0) {
709
error_setg(errp, "Use only numeric port value");
710
ret = -EINVAL;
711
goto err;
712
}
713
714
/* Open the socket and connect. */
715
- s->sock = inet_connect_saddr(s->inet, errp);
716
- if (s->sock < 0) {
717
+ new_sock = inet_connect_saddr(s->inet, errp);
718
+ if (new_sock < 0) {
719
ret = -EIO;
720
goto err;
721
}
722
723
+ /*
724
+ * Try to disable the Nagle algorithm on TCP sockets to reduce latency,
725
+ * but do not fail if it cannot be disabled.
726
+ */
727
+ r = socket_set_nodelay(new_sock);
728
+ if (r < 0) {
729
+ warn_report("can't set TCP_NODELAY for the ssh server %s: %s",
730
+ s->inet->host, strerror(errno));
731
+ }
732
+
733
/* Create SSH session. */
734
- s->session = libssh2_session_init();
735
+ s->session = ssh_new();
736
if (!s->session) {
737
ret = -EINVAL;
738
- session_error_setg(errp, s, "failed to initialize libssh2 session");
739
+ session_error_setg(errp, s, "failed to initialize libssh session");
740
goto err;
741
}
742
743
-#if TRACE_LIBSSH2 != 0
744
- libssh2_trace(s->session, TRACE_LIBSSH2);
745
-#endif
746
+ /*
747
+ * Make sure we are in blocking mode during the connection and
748
+ * authentication phases.
749
+ */
750
+ ssh_set_blocking(s->session, 1);
751
752
- r = libssh2_session_handshake(s->session, s->sock);
753
- if (r != 0) {
754
+ r = ssh_options_set(s->session, SSH_OPTIONS_USER, s->user);
755
+ if (r < 0) {
756
+ ret = -EINVAL;
757
+ session_error_setg(errp, s,
758
+ "failed to set the user in the libssh session");
759
+ goto err;
760
+ }
761
+
762
+ r = ssh_options_set(s->session, SSH_OPTIONS_HOST, s->inet->host);
763
+ if (r < 0) {
764
+ ret = -EINVAL;
765
+ session_error_setg(errp, s,
766
+ "failed to set the host in the libssh session");
767
+ goto err;
768
+ }
769
+
770
+ if (port > 0) {
771
+ r = ssh_options_set(s->session, SSH_OPTIONS_PORT, &port);
772
+ if (r < 0) {
773
+ ret = -EINVAL;
774
+ session_error_setg(errp, s,
775
+ "failed to set the port in the libssh session");
776
+ goto err;
777
+ }
778
+ }
779
+
780
+ r = ssh_options_set(s->session, SSH_OPTIONS_COMPRESSION, "none");
781
+ if (r < 0) {
782
+ ret = -EINVAL;
783
+ session_error_setg(errp, s,
784
+ "failed to disable the compression in the libssh "
785
+ "session");
786
+ goto err;
787
+ }
788
+
789
+ /* Read ~/.ssh/config. */
790
+ r = ssh_options_parse_config(s->session, NULL);
791
+ if (r < 0) {
792
+ ret = -EINVAL;
793
+ session_error_setg(errp, s, "failed to parse ~/.ssh/config");
794
+ goto err;
795
+ }
796
+
797
+ r = ssh_options_set(s->session, SSH_OPTIONS_FD, &new_sock);
798
+ if (r < 0) {
799
+ ret = -EINVAL;
800
+ session_error_setg(errp, s,
801
+ "failed to set the socket in the libssh session");
802
+ goto err;
803
+ }
804
+ /* libssh took ownership of the socket. */
805
+ s->sock = new_sock;
806
+ new_sock = -1;
807
+
808
+ /* Connect. */
809
+ r = ssh_connect(s->session);
810
+ if (r != SSH_OK) {
811
ret = -EINVAL;
812
session_error_setg(errp, s, "failed to establish SSH session");
813
goto err;
814
}
815
816
/* Check the remote host's key against known_hosts. */
817
- ret = check_host_key(s, s->inet->host, port, opts->host_key_check, errp);
818
+ ret = check_host_key(s, opts->host_key_check, errp);
819
if (ret < 0) {
820
goto err;
821
}
822
823
/* Authenticate. */
824
- ret = authenticate(s, s->user, errp);
825
+ ret = authenticate(s, errp);
826
if (ret < 0) {
827
goto err;
828
}
829
830
/* Start SFTP. */
831
- s->sftp = libssh2_sftp_init(s->session);
832
+ s->sftp = sftp_new(s->session);
833
if (!s->sftp) {
834
- session_error_setg(errp, s, "failed to initialize sftp handle");
835
+ session_error_setg(errp, s, "failed to create sftp handle");
836
+ ret = -EINVAL;
837
+ goto err;
838
+ }
839
+
840
+ r = sftp_init(s->sftp);
841
+ if (r < 0) {
842
+ sftp_error_setg(errp, s, "failed to initialize sftp handle");
843
ret = -EINVAL;
844
goto err;
845
}
846
847
/* Open the remote file. */
848
trace_ssh_connect_to_ssh(opts->path, ssh_flags, creat_mode);
849
- s->sftp_handle = libssh2_sftp_open(s->sftp, opts->path, ssh_flags,
850
- creat_mode);
851
+ s->sftp_handle = sftp_open(s->sftp, opts->path, ssh_flags, creat_mode);
852
if (!s->sftp_handle) {
853
- session_error_setg(errp, s, "failed to open remote file '%s'",
854
- opts->path);
855
+ sftp_error_setg(errp, s, "failed to open remote file '%s'",
856
+ opts->path);
857
ret = -EINVAL;
858
goto err;
859
}
860
861
- r = libssh2_sftp_fstat(s->sftp_handle, &s->attrs);
862
- if (r < 0) {
863
+ /* Make sure the SFTP file is handled in blocking mode. */
864
+ sftp_file_set_blocking(s->sftp_handle);
865
+
866
+ s->attrs = sftp_fstat(s->sftp_handle);
867
+ if (!s->attrs) {
868
sftp_error_setg(errp, s, "failed to read file attributes");
869
return -EINVAL;
870
}
871
@@ -XXX,XX +XXX,XX @@ static int connect_to_ssh(BDRVSSHState *s, BlockdevOptionsSsh *opts,
872
return 0;
873
874
err:
875
+ if (s->attrs) {
876
+ sftp_attributes_free(s->attrs);
877
+ }
878
+ s->attrs = NULL;
879
if (s->sftp_handle) {
880
- libssh2_sftp_close(s->sftp_handle);
881
+ sftp_close(s->sftp_handle);
882
}
883
s->sftp_handle = NULL;
884
if (s->sftp) {
885
- libssh2_sftp_shutdown(s->sftp);
886
+ sftp_free(s->sftp);
887
}
888
s->sftp = NULL;
889
if (s->session) {
890
- libssh2_session_disconnect(s->session,
891
- "from qemu ssh client: "
892
- "error opening connection");
893
- libssh2_session_free(s->session);
894
+ ssh_disconnect(s->session);
895
+ ssh_free(s->session);
896
}
897
s->session = NULL;
898
+ s->sock = -1;
899
+ if (new_sock >= 0) {
900
+ close(new_sock);
901
+ }
902
903
return ret;
904
}
905
@@ -XXX,XX +XXX,XX @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
906
907
ssh_state_init(s);
908
909
- ssh_flags = LIBSSH2_FXF_READ;
910
+ ssh_flags = 0;
911
if (bdrv_flags & BDRV_O_RDWR) {
912
- ssh_flags |= LIBSSH2_FXF_WRITE;
913
+ ssh_flags |= O_RDWR;
914
+ } else {
915
+ ssh_flags |= O_RDONLY;
916
}
917
918
opts = ssh_parse_options(options, errp);
919
@@ -XXX,XX +XXX,XX @@ static int ssh_file_open(BlockDriverState *bs, QDict *options, int bdrv_flags,
920
}
921
922
/* Go non-blocking. */
923
- libssh2_session_set_blocking(s->session, 0);
924
+ ssh_set_blocking(s->session, 0);
925
926
qapi_free_BlockdevOptionsSsh(opts);
927
928
return 0;
929
930
err:
931
- if (s->sock >= 0) {
932
- close(s->sock);
933
- }
934
- s->sock = -1;
935
-
936
qapi_free_BlockdevOptionsSsh(opts);
937
938
return ret;
939
@@ -XXX,XX +XXX,XX @@ static int ssh_grow_file(BDRVSSHState *s, int64_t offset, Error **errp)
940
{
941
ssize_t ret;
942
char c[1] = { '\0' };
943
- int was_blocking = libssh2_session_get_blocking(s->session);
944
+ int was_blocking = ssh_is_blocking(s->session);
945
946
/* offset must be strictly greater than the current size so we do
947
* not overwrite anything */
948
- assert(offset > 0 && offset > s->attrs.filesize);
949
+ assert(offset > 0 && offset > s->attrs->size);
950
951
- libssh2_session_set_blocking(s->session, 1);
952
+ ssh_set_blocking(s->session, 1);
953
954
- libssh2_sftp_seek64(s->sftp_handle, offset - 1);
955
- ret = libssh2_sftp_write(s->sftp_handle, c, 1);
956
+ sftp_seek64(s->sftp_handle, offset - 1);
957
+ ret = sftp_write(s->sftp_handle, c, 1);
958
959
- libssh2_session_set_blocking(s->session, was_blocking);
960
+ ssh_set_blocking(s->session, was_blocking);
961
962
if (ret < 0) {
963
sftp_error_setg(errp, s, "Failed to grow file");
964
return -EIO;
965
}
966
967
- s->attrs.filesize = offset;
968
+ s->attrs->size = offset;
969
return 0;
970
}
971
972
@@ -XXX,XX +XXX,XX @@ static int ssh_co_create(BlockdevCreateOptions *options, Error **errp)
973
ssh_state_init(&s);
974
975
ret = connect_to_ssh(&s, opts->location,
976
- LIBSSH2_FXF_READ|LIBSSH2_FXF_WRITE|
977
- LIBSSH2_FXF_CREAT|LIBSSH2_FXF_TRUNC,
978
+ O_RDWR | O_CREAT | O_TRUNC,
979
0644, errp);
980
if (ret < 0) {
981
goto fail;
982
@@ -XXX,XX +XXX,XX @@ static int ssh_has_zero_init(BlockDriverState *bs)
983
/* Assume false, unless we can positively prove it's true. */
984
int has_zero_init = 0;
985
986
- if (s->attrs.flags & LIBSSH2_SFTP_ATTR_PERMISSIONS) {
987
- if (s->attrs.permissions & LIBSSH2_SFTP_S_IFREG) {
988
- has_zero_init = 1;
989
- }
990
+ if (s->attrs->type == SSH_FILEXFER_TYPE_REGULAR) {
991
+ has_zero_init = 1;
992
}
993
994
return has_zero_init;
995
@@ -XXX,XX +XXX,XX @@ static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs)
996
.co = qemu_coroutine_self()
997
};
998
999
- r = libssh2_session_block_directions(s->session);
1000
+ r = ssh_get_poll_flags(s->session);
1001
1002
- if (r & LIBSSH2_SESSION_BLOCK_INBOUND) {
1003
+ if (r & SSH_READ_PENDING) {
1004
rd_handler = restart_coroutine;
1005
}
1006
- if (r & LIBSSH2_SESSION_BLOCK_OUTBOUND) {
1007
+ if (r & SSH_WRITE_PENDING) {
1008
wr_handler = restart_coroutine;
1009
}
1010
1011
@@ -XXX,XX +XXX,XX @@ static coroutine_fn void co_yield(BDRVSSHState *s, BlockDriverState *bs)
1012
trace_ssh_co_yield_back(s->sock);
1013
}
1014
1015
-/* SFTP has a function `libssh2_sftp_seek64' which seeks to a position
1016
- * in the remote file. Notice that it just updates a field in the
1017
- * sftp_handle structure, so there is no network traffic and it cannot
1018
- * fail.
1019
- *
1020
- * However, `libssh2_sftp_seek64' does have a catastrophic effect on
1021
- * performance since it causes the handle to throw away all in-flight
1022
- * reads and buffered readahead data. Therefore this function tries
1023
- * to be intelligent about when to call the underlying libssh2 function.
1024
- */
1025
-#define SSH_SEEK_WRITE 0
1026
-#define SSH_SEEK_READ 1
1027
-#define SSH_SEEK_FORCE 2
1028
-
1029
-static void ssh_seek(BDRVSSHState *s, int64_t offset, int flags)
1030
-{
1031
- bool op_read = (flags & SSH_SEEK_READ) != 0;
1032
- bool force = (flags & SSH_SEEK_FORCE) != 0;
1033
-
1034
- if (force || op_read != s->offset_op_read || offset != s->offset) {
1035
- trace_ssh_seek(offset);
1036
- libssh2_sftp_seek64(s->sftp_handle, offset);
1037
- s->offset = offset;
1038
- s->offset_op_read = op_read;
1039
- }
1040
-}
1041
-
1042
static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
1043
int64_t offset, size_t size,
1044
QEMUIOVector *qiov)
1045
@@ -XXX,XX +XXX,XX @@ static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
1046
1047
trace_ssh_read(offset, size);
1048
1049
- ssh_seek(s, offset, SSH_SEEK_READ);
1050
+ trace_ssh_seek(offset);
1051
+ sftp_seek64(s->sftp_handle, offset);
1052
1053
/* This keeps track of the current iovec element ('i'), where we
1054
* will write to next ('buf'), and the end of the current iovec
1055
@@ -XXX,XX +XXX,XX @@ static coroutine_fn int ssh_read(BDRVSSHState *s, BlockDriverState *bs,
1056
buf = i->iov_base;
1057
end_of_vec = i->iov_base + i->iov_len;
1058
1059
- /* libssh2 has a hard-coded limit of 2000 bytes per request,
1060
- * although it will also do readahead behind our backs. Therefore
1061
- * we may have to do repeated reads here until we have read 'size'
1062
- * bytes.
1063
- */
1064
for (got = 0; got < size; ) {
1065
+ size_t request_read_size;
1066
again:
1067
- trace_ssh_read_buf(buf, end_of_vec - buf);
1068
- r = libssh2_sftp_read(s->sftp_handle, buf, end_of_vec - buf);
1069
- trace_ssh_read_return(r);
1070
+ /*
1071
+ * The size of SFTP packets is limited to 32K bytes, so limit
1072
+ * the amount of data requested to 16K, as libssh currently
1073
+ * does not handle multiple requests on its own.
1074
+ */
1075
+ request_read_size = MIN(end_of_vec - buf, 16384);
1076
+ trace_ssh_read_buf(buf, end_of_vec - buf, request_read_size);
1077
+ r = sftp_read(s->sftp_handle, buf, request_read_size);
1078
+ trace_ssh_read_return(r, sftp_get_error(s->sftp));
1079
1080
- if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
1081
+ if (r == SSH_AGAIN) {
1082
co_yield(s, bs);
1083
goto again;
1084
}
1085
- if (r < 0) {
1086
- sftp_error_trace(s, "read");
1087
- s->offset = -1;
1088
- return -EIO;
1089
- }
1090
- if (r == 0) {
1091
+ if (r == SSH_EOF || (r == 0 && sftp_get_error(s->sftp) == SSH_FX_EOF)) {
1092
/* EOF: Short read so pad the buffer with zeroes and return it. */
1093
qemu_iovec_memset(qiov, got, 0, size - got);
1094
return 0;
1095
}
1096
+ if (r <= 0) {
1097
+ sftp_error_trace(s, "read");
1098
+ return -EIO;
1099
+ }
1100
1101
got += r;
1102
buf += r;
1103
- s->offset += r;
1104
if (buf >= end_of_vec && got < size) {
1105
i++;
1106
buf = i->iov_base;
1107
@@ -XXX,XX +XXX,XX @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
1108
1109
trace_ssh_write(offset, size);
1110
1111
- ssh_seek(s, offset, SSH_SEEK_WRITE);
1112
+ trace_ssh_seek(offset);
1113
+ sftp_seek64(s->sftp_handle, offset);
1114
1115
/* This keeps track of the current iovec element ('i'), where we
1116
* will read from next ('buf'), and the end of the current iovec
1117
@@ -XXX,XX +XXX,XX @@ static int ssh_write(BDRVSSHState *s, BlockDriverState *bs,
1118
end_of_vec = i->iov_base + i->iov_len;
1119
1120
for (written = 0; written < size; ) {
1121
+ size_t request_write_size;
1122
again:
1123
- trace_ssh_write_buf(buf, end_of_vec - buf);
1124
- r = libssh2_sftp_write(s->sftp_handle, buf, end_of_vec - buf);
1125
- trace_ssh_write_return(r);
1126
+ /*
1127
+ * Avoid too large data packets, as libssh currently does not
1128
+ * handle multiple requests on its own.
1129
+ */
1130
+ request_write_size = MIN(end_of_vec - buf, 131072);
1131
+ trace_ssh_write_buf(buf, end_of_vec - buf, request_write_size);
1132
+ r = sftp_write(s->sftp_handle, buf, request_write_size);
1133
+ trace_ssh_write_return(r, sftp_get_error(s->sftp));
1134
1135
- if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
1136
+ if (r == SSH_AGAIN) {
1137
co_yield(s, bs);
1138
goto again;
1139
}
1140
if (r < 0) {
1141
sftp_error_trace(s, "write");
1142
- s->offset = -1;
1143
return -EIO;
1144
}
1145
- /* The libssh2 API is very unclear about this. A comment in
1146
- * the code says "nothing was acked, and no EAGAIN was
1147
- * received!" which apparently means that no data got sent
1148
- * out, and the underlying channel didn't return any EAGAIN
1149
- * indication. I think this is a bug in either libssh2 or
1150
- * OpenSSH (server-side). In any case, forcing a seek (to
1151
- * discard libssh2 internal buffers), and then trying again
1152
- * works for me.
1153
- */
1154
- if (r == 0) {
1155
- ssh_seek(s, offset + written, SSH_SEEK_WRITE|SSH_SEEK_FORCE);
1156
- co_yield(s, bs);
1157
- goto again;
1158
- }
1159
1160
written += r;
1161
buf += r;
1162
- s->offset += r;
1163
if (buf >= end_of_vec && written < size) {
1164
i++;
1165
buf = i->iov_base;
1166
end_of_vec = i->iov_base + i->iov_len;
1167
}
1168
1169
- if (offset + written > s->attrs.filesize)
1170
- s->attrs.filesize = offset + written;
1171
+ if (offset + written > s->attrs->size) {
1172
+ s->attrs->size = offset + written;
1173
+ }
1174
}
1175
1176
return 0;
1177
@@ -XXX,XX +XXX,XX @@ static void unsafe_flush_warning(BDRVSSHState *s, const char *what)
1178
}
1179
}
1180
1181
-#ifdef HAS_LIBSSH2_SFTP_FSYNC
1182
+#ifdef HAVE_LIBSSH_0_8
1183
1184
static coroutine_fn int ssh_flush(BDRVSSHState *s, BlockDriverState *bs)
1185
{
1186
int r;
1187
1188
trace_ssh_flush();
1189
+
1190
+ if (!sftp_extension_supported(s->sftp, "fsync@openssh.com", "1")) {
1191
+ unsafe_flush_warning(s, "OpenSSH >= 6.3");
1192
+ return 0;
1193
+ }
1194
again:
1195
- r = libssh2_sftp_fsync(s->sftp_handle);
1196
- if (r == LIBSSH2_ERROR_EAGAIN || r == LIBSSH2_ERROR_TIMEOUT) {
1197
+ r = sftp_fsync(s->sftp_handle);
1198
+ if (r == SSH_AGAIN) {
1199
co_yield(s, bs);
1200
goto again;
1201
}
1202
- if (r == LIBSSH2_ERROR_SFTP_PROTOCOL &&
1203
- libssh2_sftp_last_error(s->sftp) == LIBSSH2_FX_OP_UNSUPPORTED) {
1204
- unsafe_flush_warning(s, "OpenSSH >= 6.3");
1205
- return 0;
1206
- }
1207
if (r < 0) {
1208
sftp_error_trace(s, "fsync");
1209
return -EIO;
1210
@@ -XXX,XX +XXX,XX @@ static coroutine_fn int ssh_co_flush(BlockDriverState *bs)
1211
return ret;
1212
}
1213
1214
-#else /* !HAS_LIBSSH2_SFTP_FSYNC */
1215
+#else /* !HAVE_LIBSSH_0_8 */
1216
1217
static coroutine_fn int ssh_co_flush(BlockDriverState *bs)
1218
{
1219
BDRVSSHState *s = bs->opaque;
1220
1221
- unsafe_flush_warning(s, "libssh2 >= 1.4.4");
1222
+ unsafe_flush_warning(s, "libssh >= 0.8.0");
1223
return 0;
1224
}
1225
1226
-#endif /* !HAS_LIBSSH2_SFTP_FSYNC */
1227
+#endif /* !HAVE_LIBSSH_0_8 */
1228
1229
static int64_t ssh_getlength(BlockDriverState *bs)
1230
{
1231
BDRVSSHState *s = bs->opaque;
1232
int64_t length;
1233
1234
- /* Note we cannot make a libssh2 call here. */
1235
- length = (int64_t) s->attrs.filesize;
1236
+ /* Note we cannot make a libssh call here. */
1237
+ length = (int64_t) s->attrs->size;
1238
trace_ssh_getlength(length);
1239
1240
return length;
1241
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn ssh_co_truncate(BlockDriverState *bs, int64_t offset,
1242
return -ENOTSUP;
1243
}
1244
1245
- if (offset < s->attrs.filesize) {
1246
+ if (offset < s->attrs->size) {
1247
error_setg(errp, "ssh driver does not support shrinking files");
1248
return -ENOTSUP;
1249
}
1250
1251
- if (offset == s->attrs.filesize) {
1252
+ if (offset == s->attrs->size) {
1253
return 0;
1254
}
1255
1256
@@ -XXX,XX +XXX,XX @@ static void bdrv_ssh_init(void)
1257
{
1258
int r;
1259
1260
- r = libssh2_init(0);
1261
+ r = ssh_init();
1262
if (r != 0) {
1263
- fprintf(stderr, "libssh2 initialization failed, %d\n", r);
1264
+ fprintf(stderr, "libssh initialization failed, %d\n", r);
1265
exit(EXIT_FAILURE);
1266
}
1267
1268
+#if TRACE_LIBSSH != 0
1269
+ ssh_set_log_level(TRACE_LIBSSH);
1270
+#endif
1271
+
1272
bdrv_register(&bdrv_ssh);
1273
}
1274
1275
diff --git a/.travis.yml b/.travis.yml
1276
index XXXXXXX..XXXXXXX 100644
1277
--- a/.travis.yml
1278
+++ b/.travis.yml
1279
@@ -XXX,XX +XXX,XX @@ addons:
1280
- libseccomp-dev
1281
- libspice-protocol-dev
1282
- libspice-server-dev
1283
- - libssh2-1-dev
1284
+ - libssh-dev
1285
- liburcu-dev
1286
- libusb-1.0-0-dev
1287
- libvte-2.91-dev
1288
@@ -XXX,XX +XXX,XX @@ matrix:
1289
- libseccomp-dev
1290
- libspice-protocol-dev
1291
- libspice-server-dev
1292
- - libssh2-1-dev
1293
+ - libssh-dev
1294
- liburcu-dev
1295
- libusb-1.0-0-dev
1296
- libvte-2.91-dev
1297
diff --git a/block/trace-events b/block/trace-events
1298
index XXXXXXX..XXXXXXX 100644
1299
--- a/block/trace-events
1300
+++ b/block/trace-events
1301
@@ -XXX,XX +XXX,XX @@ nbd_client_connect_success(const char *export_name) "export '%s'"
1302
# ssh.c
1303
ssh_restart_coroutine(void *co) "co=%p"
1304
ssh_flush(void) "fsync"
1305
-ssh_check_host_key_knownhosts(const char *key) "host key OK: %s"
1306
+ssh_check_host_key_knownhosts(void) "host key OK"
1307
ssh_connect_to_ssh(char *path, int flags, int mode) "opening file %s flags=0x%x creat_mode=0%o"
1308
ssh_co_yield(int sock, void *rd_handler, void *wr_handler) "s->sock=%d rd_handler=%p wr_handler=%p"
1309
ssh_co_yield_back(int sock) "s->sock=%d - back"
1310
ssh_getlength(int64_t length) "length=%" PRIi64
1311
ssh_co_create_opts(uint64_t size) "total_size=%" PRIu64
1312
ssh_read(int64_t offset, size_t size) "offset=%" PRIi64 " size=%zu"
1313
-ssh_read_buf(void *buf, size_t size) "sftp_read buf=%p size=%zu"
1314
-ssh_read_return(ssize_t ret) "sftp_read returned %zd"
1315
+ssh_read_buf(void *buf, size_t size, size_t actual_size) "sftp_read buf=%p size=%zu (actual size=%zu)"
1316
+ssh_read_return(ssize_t ret, int sftp_err) "sftp_read returned %zd (sftp error=%d)"
1317
ssh_write(int64_t offset, size_t size) "offset=%" PRIi64 " size=%zu"
1318
-ssh_write_buf(void *buf, size_t size) "sftp_write buf=%p size=%zu"
1319
-ssh_write_return(ssize_t ret) "sftp_write returned %zd"
1320
+ssh_write_buf(void *buf, size_t size, size_t actual_size) "sftp_write buf=%p size=%zu (actual size=%zu)"
1321
+ssh_write_return(ssize_t ret, int sftp_err) "sftp_write returned %zd (sftp error=%d)"
1322
ssh_seek(int64_t offset) "seeking to offset=%" PRIi64
1323
+ssh_auth_methods(int methods) "auth methods=0x%x"
1324
+ssh_server_status(int status) "server status=%d"
1325
1326
# curl.c
1327
curl_timer_cb(long timeout_ms) "timer callback timeout_ms %ld"
1328
@@ -XXX,XX +XXX,XX @@ sheepdog_snapshot_create(const char *sn_name, const char *id) "%s %s"
1329
sheepdog_snapshot_create_inode(const char *name, uint32_t snap, uint32_t vdi) "s->inode: name %s snap_id 0x%" PRIx32 " vdi 0x%" PRIx32
1330
1331
# ssh.c
1332
-sftp_error(const char *op, const char *ssh_err, int ssh_err_code, unsigned long sftp_err_code) "%s failed: %s (libssh2 error code: %d, sftp error code: %lu)"
1333
+sftp_error(const char *op, const char *ssh_err, int ssh_err_code, int sftp_err_code) "%s failed: %s (libssh error code: %d, sftp error code: %d)"
1334
diff --git a/docs/qemu-block-drivers.texi b/docs/qemu-block-drivers.texi
1335
index XXXXXXX..XXXXXXX 100644
1336
--- a/docs/qemu-block-drivers.texi
1337
+++ b/docs/qemu-block-drivers.texi
1338
@@ -XXX,XX +XXX,XX @@ print a warning when @code{fsync} is not supported:
1339
1340
warning: ssh server @code{ssh.example.com:22} does not support fsync
1341
1342
-With sufficiently new versions of libssh2 and OpenSSH, @code{fsync} is
1343
+With sufficiently new versions of libssh and OpenSSH, @code{fsync} is
1344
supported.
1345
1346
@node disk_images_nvme
1347
diff --git a/tests/docker/dockerfiles/debian-win32-cross.docker b/tests/docker/dockerfiles/debian-win32-cross.docker
1348
index XXXXXXX..XXXXXXX 100644
1349
--- a/tests/docker/dockerfiles/debian-win32-cross.docker
1350
+++ b/tests/docker/dockerfiles/debian-win32-cross.docker
1351
@@ -XXX,XX +XXX,XX @@ RUN DEBIAN_FRONTEND=noninteractive eatmydata \
1352
mxe-$TARGET-w64-mingw32.shared-curl \
1353
mxe-$TARGET-w64-mingw32.shared-glib \
1354
mxe-$TARGET-w64-mingw32.shared-libgcrypt \
1355
- mxe-$TARGET-w64-mingw32.shared-libssh2 \
1356
mxe-$TARGET-w64-mingw32.shared-libusb1 \
1357
mxe-$TARGET-w64-mingw32.shared-lzo \
1358
mxe-$TARGET-w64-mingw32.shared-nettle \
1359
diff --git a/tests/docker/dockerfiles/debian-win64-cross.docker b/tests/docker/dockerfiles/debian-win64-cross.docker
1360
index XXXXXXX..XXXXXXX 100644
1361
--- a/tests/docker/dockerfiles/debian-win64-cross.docker
1362
+++ b/tests/docker/dockerfiles/debian-win64-cross.docker
1363
@@ -XXX,XX +XXX,XX @@ RUN DEBIAN_FRONTEND=noninteractive eatmydata \
1364
mxe-$TARGET-w64-mingw32.shared-curl \
1365
mxe-$TARGET-w64-mingw32.shared-glib \
1366
mxe-$TARGET-w64-mingw32.shared-libgcrypt \
1367
- mxe-$TARGET-w64-mingw32.shared-libssh2 \
1368
mxe-$TARGET-w64-mingw32.shared-libusb1 \
1369
mxe-$TARGET-w64-mingw32.shared-lzo \
1370
mxe-$TARGET-w64-mingw32.shared-nettle \
1371
diff --git a/tests/docker/dockerfiles/fedora.docker b/tests/docker/dockerfiles/fedora.docker
1372
index XXXXXXX..XXXXXXX 100644
1373
--- a/tests/docker/dockerfiles/fedora.docker
1374
+++ b/tests/docker/dockerfiles/fedora.docker
1375
@@ -XXX,XX +XXX,XX @@ ENV PACKAGES \
1376
libpng-devel \
1377
librbd-devel \
1378
libseccomp-devel \
1379
- libssh2-devel \
1380
+ libssh-devel \
1381
libubsan \
1382
libusbx-devel \
1383
libxml2-devel \
1384
@@ -XXX,XX +XXX,XX @@ ENV PACKAGES \
1385
mingw32-gtk3 \
1386
mingw32-libjpeg-turbo \
1387
mingw32-libpng \
1388
- mingw32-libssh2 \
1389
mingw32-libtasn1 \
1390
mingw32-nettle \
1391
mingw32-pixman \
1392
@@ -XXX,XX +XXX,XX @@ ENV PACKAGES \
1393
mingw64-gtk3 \
1394
mingw64-libjpeg-turbo \
1395
mingw64-libpng \
1396
- mingw64-libssh2 \
1397
mingw64-libtasn1 \
1398
mingw64-nettle \
1399
mingw64-pixman \
1400
diff --git a/tests/docker/dockerfiles/ubuntu.docker b/tests/docker/dockerfiles/ubuntu.docker
1401
index XXXXXXX..XXXXXXX 100644
1402
--- a/tests/docker/dockerfiles/ubuntu.docker
1403
+++ b/tests/docker/dockerfiles/ubuntu.docker
1404
@@ -XXX,XX +XXX,XX @@ ENV PACKAGES flex bison \
1405
libsnappy-dev \
1406
libspice-protocol-dev \
1407
libspice-server-dev \
1408
- libssh2-1-dev \
1409
+ libssh-dev \
1410
libusb-1.0-0-dev \
1411
libusbredirhost-dev \
1412
libvdeplug-dev \
1413
diff --git a/tests/docker/dockerfiles/ubuntu1804.docker b/tests/docker/dockerfiles/ubuntu1804.docker
1414
index XXXXXXX..XXXXXXX 100644
1415
--- a/tests/docker/dockerfiles/ubuntu1804.docker
1416
+++ b/tests/docker/dockerfiles/ubuntu1804.docker
1417
@@ -XXX,XX +XXX,XX @@ ENV PACKAGES flex bison \
1418
libsnappy-dev \
1419
libspice-protocol-dev \
1420
libspice-server-dev \
1421
- libssh2-1-dev \
1422
+ libssh-dev \
1423
libusb-1.0-0-dev \
1424
libusbredirhost-dev \
1425
libvdeplug-dev \
1426
diff --git a/tests/qemu-iotests/207 b/tests/qemu-iotests/207
1427
index XXXXXXX..XXXXXXX 100755
1428
--- a/tests/qemu-iotests/207
1429
+++ b/tests/qemu-iotests/207
1430
@@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.img') as disk_path, \
1431
1432
iotests.img_info_log(remote_path)
1433
1434
- md5_key = subprocess.check_output(
1435
- 'ssh-keyscan -t rsa 127.0.0.1 2>/dev/null | grep -v "\\^#" | ' +
1436
- 'cut -d" " -f3 | base64 -d | md5sum -b | cut -d" " -f1',
1437
- shell=True).rstrip().decode('ascii')
1438
+ keys = subprocess.check_output(
1439
+ 'ssh-keyscan 127.0.0.1 2>/dev/null | grep -v "\\^#" | ' +
1440
+ 'cut -d" " -f3',
1441
+ shell=True).rstrip().decode('ascii').split('\n')
1442
+
1443
+ # Mappings of base64 representations to digests
1444
+ md5_keys = {}
1445
+ sha1_keys = {}
1446
+
1447
+ for key in keys:
1448
+ md5_keys[key] = subprocess.check_output(
1449
+ 'echo %s | base64 -d | md5sum -b | cut -d" " -f1' % key,
1450
+ shell=True).rstrip().decode('ascii')
1451
+
1452
+ sha1_keys[key] = subprocess.check_output(
1453
+ 'echo %s | base64 -d | sha1sum -b | cut -d" " -f1' % key,
1454
+ shell=True).rstrip().decode('ascii')
1455
1456
vm.launch()
1457
+
1458
+ # Find correct key first
1459
+ matching_key = None
1460
+ for key in keys:
1461
+ result = vm.qmp('blockdev-add',
1462
+ driver='ssh', node_name='node0', path=disk_path,
1463
+ server={
1464
+ 'host': '127.0.0.1',
1465
+ 'port': '22',
1466
+ }, host_key_check={
1467
+ 'mode': 'hash',
1468
+ 'type': 'md5',
1469
+ 'hash': md5_keys[key],
1470
+ })
1471
+
1472
+ if 'error' not in result:
1473
+ vm.qmp('blockdev-del', node_name='node0')
1474
+ matching_key = key
1475
+ break
1476
+
1477
+ if matching_key is None:
1478
+ vm.shutdown()
1479
+ iotests.notrun('Did not find a key that fits 127.0.0.1')
1480
+
1481
blockdev_create(vm, { 'driver': 'ssh',
1482
'location': {
1483
'path': disk_path,
1484
@@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.img') as disk_path, \
1485
'host-key-check': {
1486
'mode': 'hash',
1487
'type': 'md5',
1488
- 'hash': md5_key,
1489
+ 'hash': md5_keys[matching_key],
1490
}
1491
},
1492
'size': 8388608 })
1493
@@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.img') as disk_path, \
1494
1495
iotests.img_info_log(remote_path)
1496
1497
- sha1_key = subprocess.check_output(
1498
- 'ssh-keyscan -t rsa 127.0.0.1 2>/dev/null | grep -v "\\^#" | ' +
1499
- 'cut -d" " -f3 | base64 -d | sha1sum -b | cut -d" " -f1',
1500
- shell=True).rstrip().decode('ascii')
1501
-
1502
vm.launch()
1503
blockdev_create(vm, { 'driver': 'ssh',
1504
'location': {
1505
@@ -XXX,XX +XXX,XX @@ with iotests.FilePath('t.img') as disk_path, \
1506
'host-key-check': {
1507
'mode': 'hash',
1508
'type': 'sha1',
1509
- 'hash': sha1_key,
1510
+ 'hash': sha1_keys[matching_key],
1511
}
1512
},
1513
'size': 4194304 })
1514
diff --git a/tests/qemu-iotests/207.out b/tests/qemu-iotests/207.out
1515
index XXXXXXX..XXXXXXX 100644
1516
--- a/tests/qemu-iotests/207.out
1517
+++ b/tests/qemu-iotests/207.out
1518
@@ -XXX,XX +XXX,XX @@ virtual size: 4 MiB (4194304 bytes)
1519
1520
{"execute": "blockdev-create", "arguments": {"job-id": "job0", "options": {"driver": "ssh", "location": {"host-key-check": {"mode": "none"}, "path": "/this/is/not/an/existing/path", "server": {"host": "127.0.0.1", "port": "22"}}, "size": 4194304}}}
1521
{"return": {}}
1522
-Job failed: failed to open remote file '/this/is/not/an/existing/path': Failed opening remote file (libssh2 error code: -31)
1523
+Job failed: failed to open remote file '/this/is/not/an/existing/path': SFTP server: No such file (libssh error code: 1, sftp error code: 2)
1524
{"execute": "job-dismiss", "arguments": {"id": "job0"}}
1525
{"return": {}}
1526
1527
--
63
--
1528
2.21.0
64
2.25.3
1529
65
1530
diff view generated by jsdifflib
1
Tests should place their files into the test directory. This includes
1
From: Daniel Brodsky <dnbrdsky@gmail.com>
2
Unix sockets. 205 currently fails to do so, which prevents it from
3
being run concurrently.
4
2
5
Signed-off-by: Max Reitz <mreitz@redhat.com>
3
- __COUNTER__ doesn't work with ## concat
6
Message-id: 20190618210238.9524-1-mreitz@redhat.com
4
- replaced ## with glue() macro so __COUNTER__ is evaluated
7
Reviewed-by: Eric Blake <eblake@redhat.com>
5
8
Signed-off-by: Max Reitz <mreitz@redhat.com>
6
Fixes: 3284c3ddc4
7
8
Signed-off-by: Daniel Brodsky <dnbrdsky@gmail.com>
9
Message-id: 20200404042108.389635-2-dnbrdsky@gmail.com
10
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
9
---
11
---
10
tests/qemu-iotests/205 | 2 +-
12
include/qemu/lockable.h | 7 ++++---
11
1 file changed, 1 insertion(+), 1 deletion(-)
13
include/qemu/rcu.h | 2 +-
14
2 files changed, 5 insertions(+), 4 deletions(-)
12
15
13
diff --git a/tests/qemu-iotests/205 b/tests/qemu-iotests/205
16
diff --git a/include/qemu/lockable.h b/include/qemu/lockable.h
14
index XXXXXXX..XXXXXXX 100755
17
index XXXXXXX..XXXXXXX 100644
15
--- a/tests/qemu-iotests/205
18
--- a/include/qemu/lockable.h
16
+++ b/tests/qemu-iotests/205
19
+++ b/include/qemu/lockable.h
17
@@ -XXX,XX +XXX,XX @@ import iotests
20
@@ -XXX,XX +XXX,XX @@ G_DEFINE_AUTOPTR_CLEANUP_FUNC(QemuLockable, qemu_lockable_auto_unlock)
18
import time
21
* }
19
from iotests import qemu_img_create, qemu_io, filter_qemu_io, QemuIoInteractive
22
*/
20
23
#define WITH_QEMU_LOCK_GUARD(x) \
21
-nbd_sock = 'nbd_sock'
24
- WITH_QEMU_LOCK_GUARD_((x), qemu_lockable_auto##__COUNTER__)
22
+nbd_sock = os.path.join(iotests.test_dir, 'nbd_sock')
25
+ WITH_QEMU_LOCK_GUARD_((x), glue(qemu_lockable_auto, __COUNTER__))
23
nbd_uri = 'nbd+unix:///exp?socket=' + nbd_sock
26
24
disk = os.path.join(iotests.test_dir, 'disk')
27
/**
25
28
* QEMU_LOCK_GUARD - Lock an object until the end of the scope
29
@@ -XXX,XX +XXX,XX @@ G_DEFINE_AUTOPTR_CLEANUP_FUNC(QemuLockable, qemu_lockable_auto_unlock)
30
* return; <-- mutex is automatically unlocked
31
* }
32
*/
33
-#define QEMU_LOCK_GUARD(x) \
34
- g_autoptr(QemuLockable) qemu_lockable_auto##__COUNTER__ = \
35
+#define QEMU_LOCK_GUARD(x) \
36
+ g_autoptr(QemuLockable) \
37
+ glue(qemu_lockable_auto, __COUNTER__) G_GNUC_UNUSED = \
38
qemu_lockable_auto_lock(QEMU_MAKE_LOCKABLE((x)))
39
40
#endif
41
diff --git a/include/qemu/rcu.h b/include/qemu/rcu.h
42
index XXXXXXX..XXXXXXX 100644
43
--- a/include/qemu/rcu.h
44
+++ b/include/qemu/rcu.h
45
@@ -XXX,XX +XXX,XX @@ static inline void rcu_read_auto_unlock(RCUReadAuto *r)
46
G_DEFINE_AUTOPTR_CLEANUP_FUNC(RCUReadAuto, rcu_read_auto_unlock)
47
48
#define WITH_RCU_READ_LOCK_GUARD() \
49
- WITH_RCU_READ_LOCK_GUARD_(_rcu_read_auto##__COUNTER__)
50
+ WITH_RCU_READ_LOCK_GUARD_(glue(_rcu_read_auto, __COUNTER__))
51
52
#define WITH_RCU_READ_LOCK_GUARD_(var) \
53
for (g_autoptr(RCUReadAuto) var = rcu_read_auto_lock(); \
26
--
54
--
27
2.21.0
55
2.25.3
28
56
29
diff view generated by jsdifflib
1
From: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
1
From: Daniel Brodsky <dnbrdsky@gmail.com>
2
2
3
We forget to enable it for transaction .prepare, while it is already
3
- ran regexp "qemu_mutex_lock\(.*\).*\n.*if" to find targets
4
enabled in do_drive_backup since commit a2d665c1bc362
4
- replaced result with QEMU_LOCK_GUARD if all unlocks at function end
5
"blockdev: loosen restrictions on drive-backup source node"
5
- replaced result with WITH_QEMU_LOCK_GUARD if unlock not at end
6
6
7
Signed-off-by: Vladimir Sementsov-Ogievskiy <vsementsov@virtuozzo.com>
7
Signed-off-by: Daniel Brodsky <dnbrdsky@gmail.com>
8
Message-id: 20190618140804.59214-1-vsementsov@virtuozzo.com
8
Reviewed-by: Juan Quintela <quintela@redhat.com>
9
Reviewed-by: John Snow <jsnow@redhat.com>
9
Message-id: 20200404042108.389635-3-dnbrdsky@gmail.com
10
Signed-off-by: Max Reitz <mreitz@redhat.com>
10
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
11
---
11
---
12
blockdev.c | 2 +-
12
block/iscsi.c | 7 ++----
13
1 file changed, 1 insertion(+), 1 deletion(-)
13
block/nfs.c | 51 ++++++++++++++++++++-----------------------
14
cpus-common.c | 14 +++++-------
15
hw/display/qxl.c | 43 +++++++++++++++++-------------------
16
hw/vfio/platform.c | 5 ++---
17
migration/migration.c | 3 +--
18
migration/multifd.c | 8 +++----
19
migration/ram.c | 3 +--
20
monitor/misc.c | 4 +---
21
ui/spice-display.c | 14 ++++++------
22
util/log.c | 4 ++--
23
util/qemu-timer.c | 17 +++++++--------
24
util/rcu.c | 8 +++----
25
util/thread-pool.c | 3 +--
26
util/vfio-helpers.c | 5 ++---
27
15 files changed, 83 insertions(+), 106 deletions(-)
14
28
15
diff --git a/blockdev.c b/blockdev.c
29
diff --git a/block/iscsi.c b/block/iscsi.c
16
index XXXXXXX..XXXXXXX 100644
30
index XXXXXXX..XXXXXXX 100644
17
--- a/blockdev.c
31
--- a/block/iscsi.c
18
+++ b/blockdev.c
32
+++ b/block/iscsi.c
19
@@ -XXX,XX +XXX,XX @@ static void drive_backup_prepare(BlkActionState *common, Error **errp)
33
@@ -XXX,XX +XXX,XX @@ static void iscsi_nop_timed_event(void *opaque)
20
assert(common->action->type == TRANSACTION_ACTION_KIND_DRIVE_BACKUP);
34
{
21
backup = common->action->u.drive_backup.data;
35
IscsiLun *iscsilun = opaque;
22
36
23
- bs = qmp_get_root_bs(backup->device, errp);
37
- qemu_mutex_lock(&iscsilun->mutex);
24
+ bs = bdrv_lookup_bs(backup->device, backup->device, errp);
38
+ QEMU_LOCK_GUARD(&iscsilun->mutex);
25
if (!bs) {
39
if (iscsi_get_nops_in_flight(iscsilun->iscsi) >= MAX_NOP_FAILURES) {
40
error_report("iSCSI: NOP timeout. Reconnecting...");
41
iscsilun->request_timed_out = true;
42
} else if (iscsi_nop_out_async(iscsilun->iscsi, NULL, NULL, 0, NULL) != 0) {
43
error_report("iSCSI: failed to sent NOP-Out. Disabling NOP messages.");
44
- goto out;
45
+ return;
46
}
47
48
timer_mod(iscsilun->nop_timer, qemu_clock_get_ms(QEMU_CLOCK_REALTIME) + NOP_INTERVAL);
49
iscsi_set_events(iscsilun);
50
-
51
-out:
52
- qemu_mutex_unlock(&iscsilun->mutex);
53
}
54
55
static void iscsi_readcapacity_sync(IscsiLun *iscsilun, Error **errp)
56
diff --git a/block/nfs.c b/block/nfs.c
57
index XXXXXXX..XXXXXXX 100644
58
--- a/block/nfs.c
59
+++ b/block/nfs.c
60
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn nfs_co_preadv(BlockDriverState *bs, uint64_t offset,
61
nfs_co_init_task(bs, &task);
62
task.iov = iov;
63
64
- qemu_mutex_lock(&client->mutex);
65
- if (nfs_pread_async(client->context, client->fh,
66
- offset, bytes, nfs_co_generic_cb, &task) != 0) {
67
- qemu_mutex_unlock(&client->mutex);
68
- return -ENOMEM;
69
- }
70
+ WITH_QEMU_LOCK_GUARD(&client->mutex) {
71
+ if (nfs_pread_async(client->context, client->fh,
72
+ offset, bytes, nfs_co_generic_cb, &task) != 0) {
73
+ return -ENOMEM;
74
+ }
75
76
- nfs_set_events(client);
77
- qemu_mutex_unlock(&client->mutex);
78
+ nfs_set_events(client);
79
+ }
80
while (!task.complete) {
81
qemu_coroutine_yield();
82
}
83
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn nfs_co_pwritev(BlockDriverState *bs, uint64_t offset,
84
buf = iov->iov[0].iov_base;
85
}
86
87
- qemu_mutex_lock(&client->mutex);
88
- if (nfs_pwrite_async(client->context, client->fh,
89
- offset, bytes, buf,
90
- nfs_co_generic_cb, &task) != 0) {
91
- qemu_mutex_unlock(&client->mutex);
92
- if (my_buffer) {
93
- g_free(buf);
94
+ WITH_QEMU_LOCK_GUARD(&client->mutex) {
95
+ if (nfs_pwrite_async(client->context, client->fh,
96
+ offset, bytes, buf,
97
+ nfs_co_generic_cb, &task) != 0) {
98
+ if (my_buffer) {
99
+ g_free(buf);
100
+ }
101
+ return -ENOMEM;
102
}
103
- return -ENOMEM;
104
- }
105
106
- nfs_set_events(client);
107
- qemu_mutex_unlock(&client->mutex);
108
+ nfs_set_events(client);
109
+ }
110
while (!task.complete) {
111
qemu_coroutine_yield();
112
}
113
@@ -XXX,XX +XXX,XX @@ static int coroutine_fn nfs_co_flush(BlockDriverState *bs)
114
115
nfs_co_init_task(bs, &task);
116
117
- qemu_mutex_lock(&client->mutex);
118
- if (nfs_fsync_async(client->context, client->fh, nfs_co_generic_cb,
119
- &task) != 0) {
120
- qemu_mutex_unlock(&client->mutex);
121
- return -ENOMEM;
122
- }
123
+ WITH_QEMU_LOCK_GUARD(&client->mutex) {
124
+ if (nfs_fsync_async(client->context, client->fh, nfs_co_generic_cb,
125
+ &task) != 0) {
126
+ return -ENOMEM;
127
+ }
128
129
- nfs_set_events(client);
130
- qemu_mutex_unlock(&client->mutex);
131
+ nfs_set_events(client);
132
+ }
133
while (!task.complete) {
134
qemu_coroutine_yield();
135
}
136
diff --git a/cpus-common.c b/cpus-common.c
137
index XXXXXXX..XXXXXXX 100644
138
--- a/cpus-common.c
139
+++ b/cpus-common.c
140
@@ -XXX,XX +XXX,XX @@
141
#include "exec/cpu-common.h"
142
#include "hw/core/cpu.h"
143
#include "sysemu/cpus.h"
144
+#include "qemu/lockable.h"
145
146
static QemuMutex qemu_cpu_list_lock;
147
static QemuCond exclusive_cond;
148
@@ -XXX,XX +XXX,XX @@ static int cpu_get_free_index(void)
149
150
void cpu_list_add(CPUState *cpu)
151
{
152
- qemu_mutex_lock(&qemu_cpu_list_lock);
153
+ QEMU_LOCK_GUARD(&qemu_cpu_list_lock);
154
if (cpu->cpu_index == UNASSIGNED_CPU_INDEX) {
155
cpu->cpu_index = cpu_get_free_index();
156
assert(cpu->cpu_index != UNASSIGNED_CPU_INDEX);
157
@@ -XXX,XX +XXX,XX @@ void cpu_list_add(CPUState *cpu)
158
assert(!cpu_index_auto_assigned);
159
}
160
QTAILQ_INSERT_TAIL_RCU(&cpus, cpu, node);
161
- qemu_mutex_unlock(&qemu_cpu_list_lock);
162
}
163
164
void cpu_list_remove(CPUState *cpu)
165
{
166
- qemu_mutex_lock(&qemu_cpu_list_lock);
167
+ QEMU_LOCK_GUARD(&qemu_cpu_list_lock);
168
if (!QTAILQ_IN_USE(cpu, node)) {
169
/* there is nothing to undo since cpu_exec_init() hasn't been called */
170
- qemu_mutex_unlock(&qemu_cpu_list_lock);
26
return;
171
return;
27
}
172
}
173
174
@@ -XXX,XX +XXX,XX @@ void cpu_list_remove(CPUState *cpu)
175
176
QTAILQ_REMOVE_RCU(&cpus, cpu, node);
177
cpu->cpu_index = UNASSIGNED_CPU_INDEX;
178
- qemu_mutex_unlock(&qemu_cpu_list_lock);
179
}
180
181
struct qemu_work_item {
182
@@ -XXX,XX +XXX,XX @@ void cpu_exec_start(CPUState *cpu)
183
* see cpu->running == true, and it will kick the CPU.
184
*/
185
if (unlikely(atomic_read(&pending_cpus))) {
186
- qemu_mutex_lock(&qemu_cpu_list_lock);
187
+ QEMU_LOCK_GUARD(&qemu_cpu_list_lock);
188
if (!cpu->has_waiter) {
189
/* Not counted in pending_cpus, let the exclusive item
190
* run. Since we have the lock, just set cpu->running to true
191
@@ -XXX,XX +XXX,XX @@ void cpu_exec_start(CPUState *cpu)
192
* waiter at cpu_exec_end.
193
*/
194
}
195
- qemu_mutex_unlock(&qemu_cpu_list_lock);
196
}
197
}
198
199
@@ -XXX,XX +XXX,XX @@ void cpu_exec_end(CPUState *cpu)
200
* next cpu_exec_start.
201
*/
202
if (unlikely(atomic_read(&pending_cpus))) {
203
- qemu_mutex_lock(&qemu_cpu_list_lock);
204
+ QEMU_LOCK_GUARD(&qemu_cpu_list_lock);
205
if (cpu->has_waiter) {
206
cpu->has_waiter = false;
207
atomic_set(&pending_cpus, pending_cpus - 1);
208
@@ -XXX,XX +XXX,XX @@ void cpu_exec_end(CPUState *cpu)
209
qemu_cond_signal(&exclusive_cond);
210
}
211
}
212
- qemu_mutex_unlock(&qemu_cpu_list_lock);
213
}
214
}
215
216
diff --git a/hw/display/qxl.c b/hw/display/qxl.c
217
index XXXXXXX..XXXXXXX 100644
218
--- a/hw/display/qxl.c
219
+++ b/hw/display/qxl.c
220
@@ -XXX,XX +XXX,XX @@ static int qxl_track_command(PCIQXLDevice *qxl, struct QXLCommandExt *ext)
221
cmd->u.surface_create.stride);
222
return 1;
223
}
224
- qemu_mutex_lock(&qxl->track_lock);
225
- if (cmd->type == QXL_SURFACE_CMD_CREATE) {
226
- qxl->guest_surfaces.cmds[id] = ext->cmd.data;
227
- qxl->guest_surfaces.count++;
228
- if (qxl->guest_surfaces.max < qxl->guest_surfaces.count)
229
- qxl->guest_surfaces.max = qxl->guest_surfaces.count;
230
+ WITH_QEMU_LOCK_GUARD(&qxl->track_lock) {
231
+ if (cmd->type == QXL_SURFACE_CMD_CREATE) {
232
+ qxl->guest_surfaces.cmds[id] = ext->cmd.data;
233
+ qxl->guest_surfaces.count++;
234
+ if (qxl->guest_surfaces.max < qxl->guest_surfaces.count) {
235
+ qxl->guest_surfaces.max = qxl->guest_surfaces.count;
236
+ }
237
+ }
238
+ if (cmd->type == QXL_SURFACE_CMD_DESTROY) {
239
+ qxl->guest_surfaces.cmds[id] = 0;
240
+ qxl->guest_surfaces.count--;
241
+ }
242
}
243
- if (cmd->type == QXL_SURFACE_CMD_DESTROY) {
244
- qxl->guest_surfaces.cmds[id] = 0;
245
- qxl->guest_surfaces.count--;
246
- }
247
- qemu_mutex_unlock(&qxl->track_lock);
248
break;
249
}
250
case QXL_CMD_CURSOR:
251
@@ -XXX,XX +XXX,XX @@ static void interface_update_area_complete(QXLInstance *sin,
252
int i;
253
int qxl_i;
254
255
- qemu_mutex_lock(&qxl->ssd.lock);
256
+ QEMU_LOCK_GUARD(&qxl->ssd.lock);
257
if (surface_id != 0 || !num_updated_rects ||
258
!qxl->render_update_cookie_num) {
259
- qemu_mutex_unlock(&qxl->ssd.lock);
260
return;
261
}
262
trace_qxl_interface_update_area_complete(qxl->id, surface_id, dirty->left,
263
@@ -XXX,XX +XXX,XX @@ static void interface_update_area_complete(QXLInstance *sin,
264
* Don't bother copying or scheduling the bh since we will flip
265
* the whole area anyway on completion of the update_area async call
266
*/
267
- qemu_mutex_unlock(&qxl->ssd.lock);
268
return;
269
}
270
qxl_i = qxl->num_dirty_rects;
271
@@ -XXX,XX +XXX,XX @@ static void interface_update_area_complete(QXLInstance *sin,
272
trace_qxl_interface_update_area_complete_schedule_bh(qxl->id,
273
qxl->num_dirty_rects);
274
qemu_bh_schedule(qxl->update_area_bh);
275
- qemu_mutex_unlock(&qxl->ssd.lock);
276
}
277
278
/* called from spice server thread context only */
279
@@ -XXX,XX +XXX,XX @@ static void ioport_write(void *opaque, hwaddr addr,
280
case QXL_IO_MONITORS_CONFIG_ASYNC:
281
async_common:
282
async = QXL_ASYNC;
283
- qemu_mutex_lock(&d->async_lock);
284
- if (d->current_async != QXL_UNDEFINED_IO) {
285
- qxl_set_guest_bug(d, "%d async started before last (%d) complete",
286
- io_port, d->current_async);
287
- qemu_mutex_unlock(&d->async_lock);
288
- return;
289
+ WITH_QEMU_LOCK_GUARD(&d->async_lock) {
290
+ if (d->current_async != QXL_UNDEFINED_IO) {
291
+ qxl_set_guest_bug(d, "%d async started before last (%d) complete",
292
+ io_port, d->current_async);
293
+ return;
294
+ }
295
+ d->current_async = orig_io_port;
296
}
297
- d->current_async = orig_io_port;
298
- qemu_mutex_unlock(&d->async_lock);
299
break;
300
default:
301
break;
302
diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c
303
index XXXXXXX..XXXXXXX 100644
304
--- a/hw/vfio/platform.c
305
+++ b/hw/vfio/platform.c
306
@@ -XXX,XX +XXX,XX @@
307
#include "hw/vfio/vfio-platform.h"
308
#include "migration/vmstate.h"
309
#include "qemu/error-report.h"
310
+#include "qemu/lockable.h"
311
#include "qemu/main-loop.h"
312
#include "qemu/module.h"
313
#include "qemu/range.h"
314
@@ -XXX,XX +XXX,XX @@ static void vfio_intp_interrupt(VFIOINTp *intp)
315
VFIOPlatformDevice *vdev = intp->vdev;
316
bool delay_handling = false;
317
318
- qemu_mutex_lock(&vdev->intp_mutex);
319
+ QEMU_LOCK_GUARD(&vdev->intp_mutex);
320
if (intp->state == VFIO_IRQ_INACTIVE) {
321
QLIST_FOREACH(tmp, &vdev->intp_list, next) {
322
if (tmp->state == VFIO_IRQ_ACTIVE ||
323
@@ -XXX,XX +XXX,XX @@ static void vfio_intp_interrupt(VFIOINTp *intp)
324
QSIMPLEQ_INSERT_TAIL(&vdev->pending_intp_queue,
325
intp, pqnext);
326
ret = event_notifier_test_and_clear(intp->interrupt);
327
- qemu_mutex_unlock(&vdev->intp_mutex);
328
return;
329
}
330
331
@@ -XXX,XX +XXX,XX @@ static void vfio_intp_interrupt(VFIOINTp *intp)
332
qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) +
333
vdev->mmap_timeout);
334
}
335
- qemu_mutex_unlock(&vdev->intp_mutex);
336
}
337
338
/**
339
diff --git a/migration/migration.c b/migration/migration.c
340
index XXXXXXX..XXXXXXX 100644
341
--- a/migration/migration.c
342
+++ b/migration/migration.c
343
@@ -XXX,XX +XXX,XX @@ static void migrate_fd_cleanup_bh(void *opaque)
344
345
void migrate_set_error(MigrationState *s, const Error *error)
346
{
347
- qemu_mutex_lock(&s->error_mutex);
348
+ QEMU_LOCK_GUARD(&s->error_mutex);
349
if (!s->error) {
350
s->error = error_copy(error);
351
}
352
- qemu_mutex_unlock(&s->error_mutex);
353
}
354
355
void migrate_fd_error(MigrationState *s, const Error *error)
356
diff --git a/migration/multifd.c b/migration/multifd.c
357
index XXXXXXX..XXXXXXX 100644
358
--- a/migration/multifd.c
359
+++ b/migration/multifd.c
360
@@ -XXX,XX +XXX,XX @@ void multifd_recv_sync_main(void)
361
for (i = 0; i < migrate_multifd_channels(); i++) {
362
MultiFDRecvParams *p = &multifd_recv_state->params[i];
363
364
- qemu_mutex_lock(&p->mutex);
365
- if (multifd_recv_state->packet_num < p->packet_num) {
366
- multifd_recv_state->packet_num = p->packet_num;
367
+ WITH_QEMU_LOCK_GUARD(&p->mutex) {
368
+ if (multifd_recv_state->packet_num < p->packet_num) {
369
+ multifd_recv_state->packet_num = p->packet_num;
370
+ }
371
}
372
- qemu_mutex_unlock(&p->mutex);
373
trace_multifd_recv_sync_main_signal(p->id);
374
qemu_sem_post(&p->sem_sync);
375
}
376
diff --git a/migration/ram.c b/migration/ram.c
377
index XXXXXXX..XXXXXXX 100644
378
--- a/migration/ram.c
379
+++ b/migration/ram.c
380
@@ -XXX,XX +XXX,XX @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
381
return NULL;
382
}
383
384
- qemu_mutex_lock(&rs->src_page_req_mutex);
385
+ QEMU_LOCK_GUARD(&rs->src_page_req_mutex);
386
if (!QSIMPLEQ_EMPTY(&rs->src_page_requests)) {
387
struct RAMSrcPageRequest *entry =
388
QSIMPLEQ_FIRST(&rs->src_page_requests);
389
@@ -XXX,XX +XXX,XX @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset)
390
migration_consume_urgent_request();
391
}
392
}
393
- qemu_mutex_unlock(&rs->src_page_req_mutex);
394
395
return block;
396
}
397
diff --git a/monitor/misc.c b/monitor/misc.c
398
index XXXXXXX..XXXXXXX 100644
399
--- a/monitor/misc.c
400
+++ b/monitor/misc.c
401
@@ -XXX,XX +XXX,XX @@ AddfdInfo *monitor_fdset_add_fd(int fd, bool has_fdset_id, int64_t fdset_id,
402
MonFdsetFd *mon_fdset_fd;
403
AddfdInfo *fdinfo;
404
405
- qemu_mutex_lock(&mon_fdsets_lock);
406
+ QEMU_LOCK_GUARD(&mon_fdsets_lock);
407
if (has_fdset_id) {
408
QLIST_FOREACH(mon_fdset, &mon_fdsets, next) {
409
/* Break if match found or match impossible due to ordering by ID */
410
@@ -XXX,XX +XXX,XX @@ AddfdInfo *monitor_fdset_add_fd(int fd, bool has_fdset_id, int64_t fdset_id,
411
if (fdset_id < 0) {
412
error_setg(errp, QERR_INVALID_PARAMETER_VALUE, "fdset-id",
413
"a non-negative value");
414
- qemu_mutex_unlock(&mon_fdsets_lock);
415
return NULL;
416
}
417
/* Use specified fdset ID */
418
@@ -XXX,XX +XXX,XX @@ AddfdInfo *monitor_fdset_add_fd(int fd, bool has_fdset_id, int64_t fdset_id,
419
fdinfo->fdset_id = mon_fdset->id;
420
fdinfo->fd = mon_fdset_fd->fd;
421
422
- qemu_mutex_unlock(&mon_fdsets_lock);
423
return fdinfo;
424
}
425
426
diff --git a/ui/spice-display.c b/ui/spice-display.c
427
index XXXXXXX..XXXXXXX 100644
428
--- a/ui/spice-display.c
429
+++ b/ui/spice-display.c
430
@@ -XXX,XX +XXX,XX @@
431
#include "qemu/osdep.h"
432
#include "ui/qemu-spice.h"
433
#include "qemu/timer.h"
434
+#include "qemu/lockable.h"
435
#include "qemu/main-loop.h"
436
#include "qemu/option.h"
437
#include "qemu/queue.h"
438
@@ -XXX,XX +XXX,XX @@ void qemu_spice_display_refresh(SimpleSpiceDisplay *ssd)
439
{
440
graphic_hw_update(ssd->dcl.con);
441
442
- qemu_mutex_lock(&ssd->lock);
443
- if (QTAILQ_EMPTY(&ssd->updates) && ssd->ds) {
444
- qemu_spice_create_update(ssd);
445
- ssd->notify++;
446
+ WITH_QEMU_LOCK_GUARD(&ssd->lock) {
447
+ if (QTAILQ_EMPTY(&ssd->updates) && ssd->ds) {
448
+ qemu_spice_create_update(ssd);
449
+ ssd->notify++;
450
+ }
451
}
452
- qemu_mutex_unlock(&ssd->lock);
453
454
trace_qemu_spice_display_refresh(ssd->qxl.id, ssd->notify);
455
if (ssd->notify) {
456
@@ -XXX,XX +XXX,XX @@ static int interface_get_cursor_command(QXLInstance *sin, QXLCommandExt *ext)
457
SimpleSpiceDisplay *ssd = container_of(sin, SimpleSpiceDisplay, qxl);
458
int ret;
459
460
- qemu_mutex_lock(&ssd->lock);
461
+ QEMU_LOCK_GUARD(&ssd->lock);
462
if (ssd->ptr_define) {
463
*ext = ssd->ptr_define->ext;
464
ssd->ptr_define = NULL;
465
@@ -XXX,XX +XXX,XX @@ static int interface_get_cursor_command(QXLInstance *sin, QXLCommandExt *ext)
466
} else {
467
ret = false;
468
}
469
- qemu_mutex_unlock(&ssd->lock);
470
return ret;
471
}
472
473
diff --git a/util/log.c b/util/log.c
474
index XXXXXXX..XXXXXXX 100644
475
--- a/util/log.c
476
+++ b/util/log.c
477
@@ -XXX,XX +XXX,XX @@
478
#include "qemu/cutils.h"
479
#include "trace/control.h"
480
#include "qemu/thread.h"
481
+#include "qemu/lockable.h"
482
483
static char *logfilename;
484
static QemuMutex qemu_logfile_mutex;
485
@@ -XXX,XX +XXX,XX @@ void qemu_set_log(int log_flags)
486
if (qemu_loglevel && (!is_daemonized() || logfilename)) {
487
need_to_open_file = true;
488
}
489
- qemu_mutex_lock(&qemu_logfile_mutex);
490
+ QEMU_LOCK_GUARD(&qemu_logfile_mutex);
491
if (qemu_logfile && !need_to_open_file) {
492
logfile = qemu_logfile;
493
atomic_rcu_set(&qemu_logfile, NULL);
494
@@ -XXX,XX +XXX,XX @@ void qemu_set_log(int log_flags)
495
}
496
atomic_rcu_set(&qemu_logfile, logfile);
497
}
498
- qemu_mutex_unlock(&qemu_logfile_mutex);
499
}
500
501
void qemu_log_needs_buffers(void)
502
diff --git a/util/qemu-timer.c b/util/qemu-timer.c
503
index XXXXXXX..XXXXXXX 100644
504
--- a/util/qemu-timer.c
505
+++ b/util/qemu-timer.c
506
@@ -XXX,XX +XXX,XX @@ void timer_mod_anticipate_ns(QEMUTimer *ts, int64_t expire_time)
507
QEMUTimerList *timer_list = ts->timer_list;
508
bool rearm;
509
510
- qemu_mutex_lock(&timer_list->active_timers_lock);
511
- if (ts->expire_time == -1 || ts->expire_time > expire_time) {
512
- if (ts->expire_time != -1) {
513
- timer_del_locked(timer_list, ts);
514
+ WITH_QEMU_LOCK_GUARD(&timer_list->active_timers_lock) {
515
+ if (ts->expire_time == -1 || ts->expire_time > expire_time) {
516
+ if (ts->expire_time != -1) {
517
+ timer_del_locked(timer_list, ts);
518
+ }
519
+ rearm = timer_mod_ns_locked(timer_list, ts, expire_time);
520
+ } else {
521
+ rearm = false;
522
}
523
- rearm = timer_mod_ns_locked(timer_list, ts, expire_time);
524
- } else {
525
- rearm = false;
526
}
527
- qemu_mutex_unlock(&timer_list->active_timers_lock);
528
-
529
if (rearm) {
530
timerlist_rearm(timer_list);
531
}
532
diff --git a/util/rcu.c b/util/rcu.c
533
index XXXXXXX..XXXXXXX 100644
534
--- a/util/rcu.c
535
+++ b/util/rcu.c
536
@@ -XXX,XX +XXX,XX @@
537
#include "qemu/atomic.h"
538
#include "qemu/thread.h"
539
#include "qemu/main-loop.h"
540
+#include "qemu/lockable.h"
541
#if defined(CONFIG_MALLOC_TRIM)
542
#include <malloc.h>
543
#endif
544
@@ -XXX,XX +XXX,XX @@ static void wait_for_readers(void)
545
546
void synchronize_rcu(void)
547
{
548
- qemu_mutex_lock(&rcu_sync_lock);
549
+ QEMU_LOCK_GUARD(&rcu_sync_lock);
550
551
/* Write RCU-protected pointers before reading p_rcu_reader->ctr.
552
* Pairs with smp_mb_placeholder() in rcu_read_lock().
553
*/
554
smp_mb_global();
555
556
- qemu_mutex_lock(&rcu_registry_lock);
557
+ QEMU_LOCK_GUARD(&rcu_registry_lock);
558
if (!QLIST_EMPTY(&registry)) {
559
/* In either case, the atomic_mb_set below blocks stores that free
560
* old RCU-protected pointers.
561
@@ -XXX,XX +XXX,XX @@ void synchronize_rcu(void)
562
563
wait_for_readers();
564
}
565
-
566
- qemu_mutex_unlock(&rcu_registry_lock);
567
- qemu_mutex_unlock(&rcu_sync_lock);
568
}
569
570
571
diff --git a/util/thread-pool.c b/util/thread-pool.c
572
index XXXXXXX..XXXXXXX 100644
573
--- a/util/thread-pool.c
574
+++ b/util/thread-pool.c
575
@@ -XXX,XX +XXX,XX @@ static void thread_pool_cancel(BlockAIOCB *acb)
576
577
trace_thread_pool_cancel(elem, elem->common.opaque);
578
579
- qemu_mutex_lock(&pool->lock);
580
+ QEMU_LOCK_GUARD(&pool->lock);
581
if (elem->state == THREAD_QUEUED &&
582
/* No thread has yet started working on elem. we can try to "steal"
583
* the item from the worker if we can get a signal from the
584
@@ -XXX,XX +XXX,XX @@ static void thread_pool_cancel(BlockAIOCB *acb)
585
elem->ret = -ECANCELED;
586
}
587
588
- qemu_mutex_unlock(&pool->lock);
589
}
590
591
static AioContext *thread_pool_get_aio_context(BlockAIOCB *acb)
592
diff --git a/util/vfio-helpers.c b/util/vfio-helpers.c
593
index XXXXXXX..XXXXXXX 100644
594
--- a/util/vfio-helpers.c
595
+++ b/util/vfio-helpers.c
596
@@ -XXX,XX +XXX,XX @@
597
#include "standard-headers/linux/pci_regs.h"
598
#include "qemu/event_notifier.h"
599
#include "qemu/vfio-helpers.h"
600
+#include "qemu/lockable.h"
601
#include "trace.h"
602
603
#define QEMU_VFIO_DEBUG 0
604
@@ -XXX,XX +XXX,XX @@ int qemu_vfio_dma_reset_temporary(QEMUVFIOState *s)
605
.size = QEMU_VFIO_IOVA_MAX - s->high_water_mark,
606
};
607
trace_qemu_vfio_dma_reset_temporary(s);
608
- qemu_mutex_lock(&s->lock);
609
+ QEMU_LOCK_GUARD(&s->lock);
610
if (ioctl(s->container, VFIO_IOMMU_UNMAP_DMA, &unmap)) {
611
error_report("VFIO_UNMAP_DMA failed: %s", strerror(errno));
612
- qemu_mutex_unlock(&s->lock);
613
return -errno;
614
}
615
s->high_water_mark = QEMU_VFIO_IOVA_MAX;
616
- qemu_mutex_unlock(&s->lock);
617
return 0;
618
}
619
28
--
620
--
29
2.21.0
621
2.25.3
30
622
31
diff view generated by jsdifflib
Deleted patch
1
From: Anton Nefedov <anton.nefedov@virtuozzo.com>
2
1
3
COW (even empty/zero) areas require encryption too
4
5
Signed-off-by: Anton Nefedov <anton.nefedov@virtuozzo.com>
6
Reviewed-by: Eric Blake <eblake@redhat.com>
7
Reviewed-by: Max Reitz <mreitz@redhat.com>
8
Reviewed-by: Alberto Garcia <berto@igalia.com>
9
Message-id: 20190516143028.81155-1-anton.nefedov@virtuozzo.com
10
Signed-off-by: Max Reitz <mreitz@redhat.com>
11
---
12
tests/qemu-iotests/134 | 9 +++++++++
13
tests/qemu-iotests/134.out | 10 ++++++++++
14
2 files changed, 19 insertions(+)
15
16
diff --git a/tests/qemu-iotests/134 b/tests/qemu-iotests/134
17
index XXXXXXX..XXXXXXX 100755
18
--- a/tests/qemu-iotests/134
19
+++ b/tests/qemu-iotests/134
20
@@ -XXX,XX +XXX,XX @@ echo
21
echo "== reading whole image =="
22
$QEMU_IO --object $SECRET -c "read 0 $size" --image-opts $IMGSPEC | _filter_qemu_io | _filter_testdir
23
24
+echo
25
+echo "== rewriting cluster part =="
26
+$QEMU_IO --object $SECRET -c "write -P 0xb 512 512" --image-opts $IMGSPEC | _filter_qemu_io | _filter_testdir
27
+
28
+echo
29
+echo "== verify pattern =="
30
+$QEMU_IO --object $SECRET -c "read -P 0 0 512" --image-opts $IMGSPEC | _filter_qemu_io | _filter_testdir
31
+$QEMU_IO --object $SECRET -c "read -P 0xb 512 512" --image-opts $IMGSPEC | _filter_qemu_io | _filter_testdir
32
+
33
echo
34
echo "== rewriting whole image =="
35
$QEMU_IO --object $SECRET -c "write -P 0xa 0 $size" --image-opts $IMGSPEC | _filter_qemu_io | _filter_testdir
36
diff --git a/tests/qemu-iotests/134.out b/tests/qemu-iotests/134.out
37
index XXXXXXX..XXXXXXX 100644
38
--- a/tests/qemu-iotests/134.out
39
+++ b/tests/qemu-iotests/134.out
40
@@ -XXX,XX +XXX,XX @@ Formatting 'TEST_DIR/t.IMGFMT', fmt=IMGFMT size=134217728 encryption=on encrypt.
41
read 134217728/134217728 bytes at offset 0
42
128 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
43
44
+== rewriting cluster part ==
45
+wrote 512/512 bytes at offset 512
46
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
47
+
48
+== verify pattern ==
49
+read 512/512 bytes at offset 0
50
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
51
+read 512/512 bytes at offset 512
52
+512 bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
53
+
54
== rewriting whole image ==
55
wrote 134217728/134217728 bytes at offset 0
56
128 MiB, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec)
57
--
58
2.21.0
59
60
diff view generated by jsdifflib
Deleted patch
1
From: Sam Eiderman <shmuel.eiderman@oracle.com>
2
1
3
Commit b0651b8c246d ("vmdk: Move l1_size check into vmdk_add_extent")
4
extended the l1_size check from VMDK4 to VMDK3 but did not update the
5
default coverage in the moved comment.
6
7
The previous vmdk4 calculation:
8
9
(512 * 1024 * 1024) * 512(l2 entries) * 65536(grain) = 16PB
10
11
The added vmdk3 calculation:
12
13
(512 * 1024 * 1024) * 4096(l2 entries) * 512(grain) = 1PB
14
15
Adding the calculation of vmdk3 to the comment.
16
17
In any case, VMware does not offer virtual disks more than 2TB for
18
vmdk4/vmdk3 or 64TB for the new undocumented seSparse format which is
19
not implemented yet in qemu.
20
21
Reviewed-by: Karl Heubaum <karl.heubaum@oracle.com>
22
Reviewed-by: Eyal Moscovici <eyal.moscovici@oracle.com>
23
Reviewed-by: Liran Alon <liran.alon@oracle.com>
24
Reviewed-by: Arbel Moshe <arbel.moshe@oracle.com>
25
Signed-off-by: Sam Eiderman <shmuel.eiderman@oracle.com>
26
Message-id: 20190620091057.47441-2-shmuel.eiderman@oracle.com
27
Reviewed-by: yuchenlin <yuchenlin@synology.com>
28
Reviewed-by: Max Reitz <mreitz@redhat.com>
29
Signed-off-by: Max Reitz <mreitz@redhat.com>
30
---
31
block/vmdk.c | 11 ++++++++---
32
1 file changed, 8 insertions(+), 3 deletions(-)
33
34
diff --git a/block/vmdk.c b/block/vmdk.c
35
index XXXXXXX..XXXXXXX 100644
36
--- a/block/vmdk.c
37
+++ b/block/vmdk.c
38
@@ -XXX,XX +XXX,XX @@ static int vmdk_add_extent(BlockDriverState *bs,
39
return -EFBIG;
40
}
41
if (l1_size > 512 * 1024 * 1024) {
42
- /* Although with big capacity and small l1_entry_sectors, we can get a
43
+ /*
44
+ * Although with big capacity and small l1_entry_sectors, we can get a
45
* big l1_size, we don't want unbounded value to allocate the table.
46
- * Limit it to 512M, which is 16PB for default cluster and L2 table
47
- * size */
48
+ * Limit it to 512M, which is:
49
+ * 16PB - for default "Hosted Sparse Extent" (VMDK4)
50
+ * cluster size: 64KB, L2 table size: 512 entries
51
+ * 1PB - for default "ESXi Host Sparse Extent" (VMDK3/vmfsSparse)
52
+ * cluster size: 512B, L2 table size: 4096 entries
53
+ */
54
error_setg(errp, "L1 size too big");
55
return -EFBIG;
56
}
57
--
58
2.21.0
59
60
diff view generated by jsdifflib
Deleted patch
1
From: Sam Eiderman <shmuel.eiderman@oracle.com>
2
1
3
512M of L1 entries is a very loose bound, only 32M are required to store
4
the maximal supported VMDK file size of 2TB.
5
6
Fixed qemu-iotest 59# - now failure occures before on impossible L1
7
table size.
8
9
Reviewed-by: Karl Heubaum <karl.heubaum@oracle.com>
10
Reviewed-by: Eyal Moscovici <eyal.moscovici@oracle.com>
11
Reviewed-by: Liran Alon <liran.alon@oracle.com>
12
Reviewed-by: Arbel Moshe <arbel.moshe@oracle.com>
13
Signed-off-by: Sam Eiderman <shmuel.eiderman@oracle.com>
14
Message-id: 20190620091057.47441-3-shmuel.eiderman@oracle.com
15
Reviewed-by: Max Reitz <mreitz@redhat.com>
16
Signed-off-by: Max Reitz <mreitz@redhat.com>
17
---
18
block/vmdk.c | 13 +++++++------
19
tests/qemu-iotests/059.out | 2 +-
20
2 files changed, 8 insertions(+), 7 deletions(-)
21
22
diff --git a/block/vmdk.c b/block/vmdk.c
23
index XXXXXXX..XXXXXXX 100644
24
--- a/block/vmdk.c
25
+++ b/block/vmdk.c
26
@@ -XXX,XX +XXX,XX @@ static int vmdk_add_extent(BlockDriverState *bs,
27
error_setg(errp, "Invalid granularity, image may be corrupt");
28
return -EFBIG;
29
}
30
- if (l1_size > 512 * 1024 * 1024) {
31
+ if (l1_size > 32 * 1024 * 1024) {
32
/*
33
* Although with big capacity and small l1_entry_sectors, we can get a
34
* big l1_size, we don't want unbounded value to allocate the table.
35
- * Limit it to 512M, which is:
36
- * 16PB - for default "Hosted Sparse Extent" (VMDK4)
37
- * cluster size: 64KB, L2 table size: 512 entries
38
- * 1PB - for default "ESXi Host Sparse Extent" (VMDK3/vmfsSparse)
39
- * cluster size: 512B, L2 table size: 4096 entries
40
+ * Limit it to 32M, which is enough to store:
41
+ * 8TB - for both VMDK3 & VMDK4 with
42
+ * minimal cluster size: 512B
43
+ * minimal L2 table size: 512 entries
44
+ * 8 TB is still more than the maximal value supported for
45
+ * VMDK3 & VMDK4 which is 2TB.
46
*/
47
error_setg(errp, "L1 size too big");
48
return -EFBIG;
49
diff --git a/tests/qemu-iotests/059.out b/tests/qemu-iotests/059.out
50
index XXXXXXX..XXXXXXX 100644
51
--- a/tests/qemu-iotests/059.out
52
+++ b/tests/qemu-iotests/059.out
53
@@ -XXX,XX +XXX,XX @@ Offset Length Mapped to File
54
0x140000000 0x10000 0x50000 TEST_DIR/t-s003.vmdk
55
56
=== Testing afl image with a very large capacity ===
57
-qemu-img: Can't get image size 'TEST_DIR/afl9.IMGFMT': File too large
58
+qemu-img: Could not open 'TEST_DIR/afl9.IMGFMT': L1 size too big
59
*** done
60
--
61
2.21.0
62
63
diff view generated by jsdifflib
1
From: Sam Eiderman <shmuel.eiderman@oracle.com>
1
From: Simran Singhal <singhalsimran0@gmail.com>
2
2
3
Until ESXi 6.5 VMware used the vmfsSparse format for snapshots (VMDK3 in
3
Replace manual lock()/unlock() calls with lock guard macros
4
QEMU).
4
(QEMU_LOCK_GUARD/WITH_QEMU_LOCK_GUARD).
5
5
6
This format was lacking in the following:
6
Signed-off-by: Simran Singhal <singhalsimran0@gmail.com>
7
Reviewed-by: Yuval Shaia <yuval.shaia.ml@gmail.com>
8
Reviewed-by: Marcel Apfelbaum<marcel.apfelbaum@gmail.com>
9
Tested-by: Yuval Shaia <yuval.shaia.ml@gmail.com>
10
Message-id: 20200402065035.GA15477@simran-Inspiron-5558
11
Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
12
---
13
hw/hyperv/hyperv.c | 15 ++++++-------
14
hw/rdma/rdma_backend.c | 50 +++++++++++++++++++++---------------------
15
hw/rdma/rdma_rm.c | 3 +--
16
3 files changed, 33 insertions(+), 35 deletions(-)
7
17
8
* Grain directory (L1) and grain table (L2) entries were 32-bit,
18
diff --git a/hw/hyperv/hyperv.c b/hw/hyperv/hyperv.c
9
allowing access to only 2TB (slightly less) of data.
10
* The grain size (default) was 512 bytes - leading to data
11
fragmentation and many grain tables.
12
* For space reclamation purposes, it was necessary to find all the
13
grains which are not pointed to by any grain table - so a reverse
14
mapping of "offset of grain in vmdk" to "grain table" must be
15
constructed - which takes large amounts of CPU/RAM.
16
17
The format specification can be found in VMware's documentation:
18
https://www.vmware.com/support/developer/vddk/vmdk_50_technote.pdf
19
20
In ESXi 6.5, to support snapshot files larger than 2TB, a new format was
21
introduced: SESparse (Space Efficient).
22
23
This format fixes the above issues:
24
25
* All entries are now 64-bit.
26
* The grain size (default) is 4KB.
27
* Grain directory and grain tables are now located at the beginning
28
of the file.
29
+ seSparse format reserves space for all grain tables.
30
+ Grain tables can be addressed using an index.
31
+ Grains are located in the end of the file and can also be
32
addressed with an index.
33
- seSparse vmdks of large disks (64TB) have huge preallocated
34
headers - mainly due to L2 tables, even for empty snapshots.
35
* The header contains a reverse mapping ("backmap") of "offset of
36
grain in vmdk" to "grain table" and a bitmap ("free bitmap") which
37
specifies for each grain - whether it is allocated or not.
38
Using these data structures we can implement space reclamation
39
efficiently.
40
* Due to the fact that the header now maintains two mappings:
41
* The regular one (grain directory & grain tables)
42
* A reverse one (backmap and free bitmap)
43
These data structures can lose consistency upon crash and result
44
in a corrupted VMDK.
45
Therefore, a journal is also added to the VMDK and is replayed
46
when the VMware reopens the file after a crash.
47
48
Since ESXi 6.7 - SESparse is the only snapshot format available.
49
50
Unfortunately, VMware does not provide documentation regarding the new
51
seSparse format.
52
53
This commit is based on black-box research of the seSparse format.
54
Various in-guest block operations and their effect on the snapshot file
55
were tested.
56
57
The only VMware provided source of information (regarding the underlying
58
implementation) was a log file on the ESXi:
59
60
/var/log/hostd.log
61
62
Whenever an seSparse snapshot is created - the log is being populated
63
with seSparse records.
64
65
Relevant log records are of the form:
66
67
[...] Const Header:
68
[...] constMagic = 0xcafebabe
69
[...] version = 2.1
70
[...] capacity = 204800
71
[...] grainSize = 8
72
[...] grainTableSize = 64
73
[...] flags = 0
74
[...] Extents:
75
[...] Header : <1 : 1>
76
[...] JournalHdr : <2 : 2>
77
[...] Journal : <2048 : 2048>
78
[...] GrainDirectory : <4096 : 2048>
79
[...] GrainTables : <6144 : 2048>
80
[...] FreeBitmap : <8192 : 2048>
81
[...] BackMap : <10240 : 2048>
82
[...] Grain : <12288 : 204800>
83
[...] Volatile Header:
84
[...] volatileMagic = 0xcafecafe
85
[...] FreeGTNumber = 0
86
[...] nextTxnSeqNumber = 0
87
[...] replayJournal = 0
88
89
The sizes that are seen in the log file are in sectors.
90
Extents are of the following format: <offset : size>
91
92
This commit is a strict implementation which enforces:
93
* magics
94
* version number 2.1
95
* grain size of 8 sectors (4KB)
96
* grain table size of 64 sectors
97
* zero flags
98
* extent locations
99
100
Additionally, this commit proivdes only a subset of the functionality
101
offered by seSparse's format:
102
* Read-only
103
* No journal replay
104
* No space reclamation
105
* No unmap support
106
107
Hence, journal header, journal, free bitmap and backmap extents are
108
unused, only the "classic" (L1 -> L2 -> data) grain access is
109
implemented.
110
111
However there are several differences in the grain access itself.
112
Grain directory (L1):
113
* Grain directory entries are indexes (not offsets) to grain
114
tables.
115
* Valid grain directory entries have their highest nibble set to
116
0x1.
117
* Since grain tables are always located in the beginning of the
118
file - the index can fit into 32 bits - so we can use its low
119
part if it's valid.
120
Grain table (L2):
121
* Grain table entries are indexes (not offsets) to grains.
122
* If the highest nibble of the entry is:
123
0x0:
124
The grain in not allocated.
125
The rest of the bytes are 0.
126
0x1:
127
The grain is unmapped - guest sees a zero grain.
128
The rest of the bits point to the previously mapped grain,
129
see 0x3 case.
130
0x2:
131
The grain is zero.
132
0x3:
133
The grain is allocated - to get the index calculate:
134
((entry & 0x0fff000000000000) >> 48) |
135
((entry & 0x0000ffffffffffff) << 12)
136
* The difference between 0x1 and 0x2 is that 0x1 is an unallocated
137
grain which results from the guest using sg_unmap to unmap the
138
grain - but the grain itself still exists in the grain extent - a
139
space reclamation procedure should delete it.
140
Unmapping a zero grain has no effect (0x2 will not change to 0x1)
141
but unmapping an unallocated grain will (0x0 to 0x1) - naturally.
142
143
In order to implement seSparse some fields had to be changed to support
144
both 32-bit and 64-bit entry sizes.
145
146
Reviewed-by: Karl Heubaum <karl.heubaum@oracle.com>
147
Reviewed-by: Eyal Moscovici <eyal.moscovici@oracle.com>
148
Reviewed-by: Arbel Moshe <arbel.moshe@oracle.com>
149
Signed-off-by: Sam Eiderman <shmuel.eiderman@oracle.com>
150
Message-id: 20190620091057.47441-4-shmuel.eiderman@oracle.com
151
Signed-off-by: Max Reitz <mreitz@redhat.com>
152
---
153
block/vmdk.c | 358 ++++++++++++++++++++++++++++++++++++++++++++++++---
154
1 file changed, 342 insertions(+), 16 deletions(-)
155
156
diff --git a/block/vmdk.c b/block/vmdk.c
157
index XXXXXXX..XXXXXXX 100644
19
index XXXXXXX..XXXXXXX 100644
158
--- a/block/vmdk.c
20
--- a/hw/hyperv/hyperv.c
159
+++ b/block/vmdk.c
21
+++ b/hw/hyperv/hyperv.c
160
@@ -XXX,XX +XXX,XX @@ typedef struct {
22
@@ -XXX,XX +XXX,XX @@
161
uint16_t compressAlgorithm;
23
#include "sysemu/kvm.h"
162
} QEMU_PACKED VMDK4Header;
24
#include "qemu/bitops.h"
163
25
#include "qemu/error-report.h"
164
+typedef struct VMDKSESparseConstHeader {
26
+#include "qemu/lockable.h"
165
+ uint64_t magic;
27
#include "qemu/queue.h"
166
+ uint64_t version;
28
#include "qemu/rcu.h"
167
+ uint64_t capacity;
29
#include "qemu/rcu_queue.h"
168
+ uint64_t grain_size;
30
@@ -XXX,XX +XXX,XX @@ int hyperv_set_msg_handler(uint32_t conn_id, HvMsgHandler handler, void *data)
169
+ uint64_t grain_table_size;
31
int ret;
170
+ uint64_t flags;
32
MsgHandler *mh;
171
+ uint64_t reserved1;
33
172
+ uint64_t reserved2;
34
- qemu_mutex_lock(&handlers_mutex);
173
+ uint64_t reserved3;
35
+ QEMU_LOCK_GUARD(&handlers_mutex);
174
+ uint64_t reserved4;
36
QLIST_FOREACH(mh, &msg_handlers, link) {
175
+ uint64_t volatile_header_offset;
37
if (mh->conn_id == conn_id) {
176
+ uint64_t volatile_header_size;
38
if (handler) {
177
+ uint64_t journal_header_offset;
39
@@ -XXX,XX +XXX,XX @@ int hyperv_set_msg_handler(uint32_t conn_id, HvMsgHandler handler, void *data)
178
+ uint64_t journal_header_size;
40
g_free_rcu(mh, rcu);
179
+ uint64_t journal_offset;
41
ret = 0;
180
+ uint64_t journal_size;
42
}
181
+ uint64_t grain_dir_offset;
43
- goto unlock;
182
+ uint64_t grain_dir_size;
44
+ return ret;
183
+ uint64_t grain_tables_offset;
45
}
184
+ uint64_t grain_tables_size;
46
}
185
+ uint64_t free_bitmap_offset;
47
186
+ uint64_t free_bitmap_size;
48
@@ -XXX,XX +XXX,XX @@ int hyperv_set_msg_handler(uint32_t conn_id, HvMsgHandler handler, void *data)
187
+ uint64_t backmap_offset;
49
} else {
188
+ uint64_t backmap_size;
50
ret = -ENOENT;
189
+ uint64_t grains_offset;
51
}
190
+ uint64_t grains_size;
52
-unlock:
191
+ uint8_t pad[304];
53
- qemu_mutex_unlock(&handlers_mutex);
192
+} QEMU_PACKED VMDKSESparseConstHeader;
193
+
54
+
194
+typedef struct VMDKSESparseVolatileHeader {
195
+ uint64_t magic;
196
+ uint64_t free_gt_number;
197
+ uint64_t next_txn_seq_number;
198
+ uint64_t replay_journal;
199
+ uint8_t pad[480];
200
+} QEMU_PACKED VMDKSESparseVolatileHeader;
201
+
202
#define L2_CACHE_SIZE 16
203
204
typedef struct VmdkExtent {
205
@@ -XXX,XX +XXX,XX @@ typedef struct VmdkExtent {
206
bool compressed;
207
bool has_marker;
208
bool has_zero_grain;
209
+ bool sesparse;
210
+ uint64_t sesparse_l2_tables_offset;
211
+ uint64_t sesparse_clusters_offset;
212
+ int32_t entry_size;
213
int version;
214
int64_t sectors;
215
int64_t end_sector;
216
int64_t flat_start_offset;
217
int64_t l1_table_offset;
218
int64_t l1_backup_table_offset;
219
- uint32_t *l1_table;
220
+ void *l1_table;
221
uint32_t *l1_backup_table;
222
unsigned int l1_size;
223
uint32_t l1_entry_sectors;
224
225
unsigned int l2_size;
226
- uint32_t *l2_cache;
227
+ void *l2_cache;
228
uint32_t l2_cache_offsets[L2_CACHE_SIZE];
229
uint32_t l2_cache_counts[L2_CACHE_SIZE];
230
231
@@ -XXX,XX +XXX,XX @@ static int vmdk_add_extent(BlockDriverState *bs,
232
* minimal L2 table size: 512 entries
233
* 8 TB is still more than the maximal value supported for
234
* VMDK3 & VMDK4 which is 2TB.
235
+ * 64TB - for "ESXi seSparse Extent"
236
+ * minimal cluster size: 512B (default is 4KB)
237
+ * L2 table size: 4096 entries (const).
238
+ * 64TB is more than the maximal value supported for
239
+ * seSparse VMDKs (which is slightly less than 64TB)
240
*/
241
error_setg(errp, "L1 size too big");
242
return -EFBIG;
243
@@ -XXX,XX +XXX,XX @@ static int vmdk_add_extent(BlockDriverState *bs,
244
extent->l2_size = l2_size;
245
extent->cluster_sectors = flat ? sectors : cluster_sectors;
246
extent->next_cluster_sector = ROUND_UP(nb_sectors, cluster_sectors);
247
+ extent->entry_size = sizeof(uint32_t);
248
249
if (s->num_extents > 1) {
250
extent->end_sector = (*(extent - 1)).end_sector + extent->sectors;
251
@@ -XXX,XX +XXX,XX @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
252
int i;
253
254
/* read the L1 table */
255
- l1_size = extent->l1_size * sizeof(uint32_t);
256
+ l1_size = extent->l1_size * extent->entry_size;
257
extent->l1_table = g_try_malloc(l1_size);
258
if (l1_size && extent->l1_table == NULL) {
259
return -ENOMEM;
260
@@ -XXX,XX +XXX,XX @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
261
goto fail_l1;
262
}
263
for (i = 0; i < extent->l1_size; i++) {
264
- le32_to_cpus(&extent->l1_table[i]);
265
+ if (extent->entry_size == sizeof(uint64_t)) {
266
+ le64_to_cpus((uint64_t *)extent->l1_table + i);
267
+ } else {
268
+ assert(extent->entry_size == sizeof(uint32_t));
269
+ le32_to_cpus((uint32_t *)extent->l1_table + i);
270
+ }
271
}
272
273
if (extent->l1_backup_table_offset) {
274
+ assert(!extent->sesparse);
275
extent->l1_backup_table = g_try_malloc(l1_size);
276
if (l1_size && extent->l1_backup_table == NULL) {
277
ret = -ENOMEM;
278
@@ -XXX,XX +XXX,XX @@ static int vmdk_init_tables(BlockDriverState *bs, VmdkExtent *extent,
279
}
280
281
extent->l2_cache =
282
- g_new(uint32_t, extent->l2_size * L2_CACHE_SIZE);
283
+ g_malloc(extent->entry_size * extent->l2_size * L2_CACHE_SIZE);
284
return 0;
285
fail_l1b:
286
g_free(extent->l1_backup_table);
287
@@ -XXX,XX +XXX,XX @@ static int vmdk_open_vmfs_sparse(BlockDriverState *bs,
288
return ret;
55
return ret;
289
}
56
}
290
57
291
+#define SESPARSE_CONST_HEADER_MAGIC UINT64_C(0x00000000cafebabe)
58
@@ -XXX,XX +XXX,XX @@ static int set_event_flag_handler(uint32_t conn_id, EventNotifier *notifier)
292
+#define SESPARSE_VOLATILE_HEADER_MAGIC UINT64_C(0x00000000cafecafe)
59
int ret;
293
+
60
EventFlagHandler *handler;
294
+/* Strict checks - format not officially documented */
61
295
+static int check_se_sparse_const_header(VMDKSESparseConstHeader *header,
62
- qemu_mutex_lock(&handlers_mutex);
296
+ Error **errp)
63
+ QEMU_LOCK_GUARD(&handlers_mutex);
297
+{
64
QLIST_FOREACH(handler, &event_flag_handlers, link) {
298
+ header->magic = le64_to_cpu(header->magic);
65
if (handler->conn_id == conn_id) {
299
+ header->version = le64_to_cpu(header->version);
66
if (notifier) {
300
+ header->grain_size = le64_to_cpu(header->grain_size);
67
@@ -XXX,XX +XXX,XX @@ static int set_event_flag_handler(uint32_t conn_id, EventNotifier *notifier)
301
+ header->grain_table_size = le64_to_cpu(header->grain_table_size);
68
g_free_rcu(handler, rcu);
302
+ header->flags = le64_to_cpu(header->flags);
69
ret = 0;
303
+ header->reserved1 = le64_to_cpu(header->reserved1);
304
+ header->reserved2 = le64_to_cpu(header->reserved2);
305
+ header->reserved3 = le64_to_cpu(header->reserved3);
306
+ header->reserved4 = le64_to_cpu(header->reserved4);
307
+
308
+ header->volatile_header_offset =
309
+ le64_to_cpu(header->volatile_header_offset);
310
+ header->volatile_header_size = le64_to_cpu(header->volatile_header_size);
311
+
312
+ header->journal_header_offset = le64_to_cpu(header->journal_header_offset);
313
+ header->journal_header_size = le64_to_cpu(header->journal_header_size);
314
+
315
+ header->journal_offset = le64_to_cpu(header->journal_offset);
316
+ header->journal_size = le64_to_cpu(header->journal_size);
317
+
318
+ header->grain_dir_offset = le64_to_cpu(header->grain_dir_offset);
319
+ header->grain_dir_size = le64_to_cpu(header->grain_dir_size);
320
+
321
+ header->grain_tables_offset = le64_to_cpu(header->grain_tables_offset);
322
+ header->grain_tables_size = le64_to_cpu(header->grain_tables_size);
323
+
324
+ header->free_bitmap_offset = le64_to_cpu(header->free_bitmap_offset);
325
+ header->free_bitmap_size = le64_to_cpu(header->free_bitmap_size);
326
+
327
+ header->backmap_offset = le64_to_cpu(header->backmap_offset);
328
+ header->backmap_size = le64_to_cpu(header->backmap_size);
329
+
330
+ header->grains_offset = le64_to_cpu(header->grains_offset);
331
+ header->grains_size = le64_to_cpu(header->grains_size);
332
+
333
+ if (header->magic != SESPARSE_CONST_HEADER_MAGIC) {
334
+ error_setg(errp, "Bad const header magic: 0x%016" PRIx64,
335
+ header->magic);
336
+ return -EINVAL;
337
+ }
338
+
339
+ if (header->version != 0x0000000200000001) {
340
+ error_setg(errp, "Unsupported version: 0x%016" PRIx64,
341
+ header->version);
342
+ return -ENOTSUP;
343
+ }
344
+
345
+ if (header->grain_size != 8) {
346
+ error_setg(errp, "Unsupported grain size: %" PRIu64,
347
+ header->grain_size);
348
+ return -ENOTSUP;
349
+ }
350
+
351
+ if (header->grain_table_size != 64) {
352
+ error_setg(errp, "Unsupported grain table size: %" PRIu64,
353
+ header->grain_table_size);
354
+ return -ENOTSUP;
355
+ }
356
+
357
+ if (header->flags != 0) {
358
+ error_setg(errp, "Unsupported flags: 0x%016" PRIx64,
359
+ header->flags);
360
+ return -ENOTSUP;
361
+ }
362
+
363
+ if (header->reserved1 != 0 || header->reserved2 != 0 ||
364
+ header->reserved3 != 0 || header->reserved4 != 0) {
365
+ error_setg(errp, "Unsupported reserved bits:"
366
+ " 0x%016" PRIx64 " 0x%016" PRIx64
367
+ " 0x%016" PRIx64 " 0x%016" PRIx64,
368
+ header->reserved1, header->reserved2,
369
+ header->reserved3, header->reserved4);
370
+ return -ENOTSUP;
371
+ }
372
+
373
+ /* check that padding is 0 */
374
+ if (!buffer_is_zero(header->pad, sizeof(header->pad))) {
375
+ error_setg(errp, "Unsupported non-zero const header padding");
376
+ return -ENOTSUP;
377
+ }
378
+
379
+ return 0;
380
+}
381
+
382
+static int check_se_sparse_volatile_header(VMDKSESparseVolatileHeader *header,
383
+ Error **errp)
384
+{
385
+ header->magic = le64_to_cpu(header->magic);
386
+ header->free_gt_number = le64_to_cpu(header->free_gt_number);
387
+ header->next_txn_seq_number = le64_to_cpu(header->next_txn_seq_number);
388
+ header->replay_journal = le64_to_cpu(header->replay_journal);
389
+
390
+ if (header->magic != SESPARSE_VOLATILE_HEADER_MAGIC) {
391
+ error_setg(errp, "Bad volatile header magic: 0x%016" PRIx64,
392
+ header->magic);
393
+ return -EINVAL;
394
+ }
395
+
396
+ if (header->replay_journal) {
397
+ error_setg(errp, "Image is dirty, Replaying journal not supported");
398
+ return -ENOTSUP;
399
+ }
400
+
401
+ /* check that padding is 0 */
402
+ if (!buffer_is_zero(header->pad, sizeof(header->pad))) {
403
+ error_setg(errp, "Unsupported non-zero volatile header padding");
404
+ return -ENOTSUP;
405
+ }
406
+
407
+ return 0;
408
+}
409
+
410
+static int vmdk_open_se_sparse(BlockDriverState *bs,
411
+ BdrvChild *file,
412
+ int flags, Error **errp)
413
+{
414
+ int ret;
415
+ VMDKSESparseConstHeader const_header;
416
+ VMDKSESparseVolatileHeader volatile_header;
417
+ VmdkExtent *extent;
418
+
419
+ ret = bdrv_apply_auto_read_only(bs,
420
+ "No write support for seSparse images available", errp);
421
+ if (ret < 0) {
422
+ return ret;
423
+ }
424
+
425
+ assert(sizeof(const_header) == SECTOR_SIZE);
426
+
427
+ ret = bdrv_pread(file, 0, &const_header, sizeof(const_header));
428
+ if (ret < 0) {
429
+ bdrv_refresh_filename(file->bs);
430
+ error_setg_errno(errp, -ret,
431
+ "Could not read const header from file '%s'",
432
+ file->bs->filename);
433
+ return ret;
434
+ }
435
+
436
+ /* check const header */
437
+ ret = check_se_sparse_const_header(&const_header, errp);
438
+ if (ret < 0) {
439
+ return ret;
440
+ }
441
+
442
+ assert(sizeof(volatile_header) == SECTOR_SIZE);
443
+
444
+ ret = bdrv_pread(file,
445
+ const_header.volatile_header_offset * SECTOR_SIZE,
446
+ &volatile_header, sizeof(volatile_header));
447
+ if (ret < 0) {
448
+ bdrv_refresh_filename(file->bs);
449
+ error_setg_errno(errp, -ret,
450
+ "Could not read volatile header from file '%s'",
451
+ file->bs->filename);
452
+ return ret;
453
+ }
454
+
455
+ /* check volatile header */
456
+ ret = check_se_sparse_volatile_header(&volatile_header, errp);
457
+ if (ret < 0) {
458
+ return ret;
459
+ }
460
+
461
+ ret = vmdk_add_extent(bs, file, false,
462
+ const_header.capacity,
463
+ const_header.grain_dir_offset * SECTOR_SIZE,
464
+ 0,
465
+ const_header.grain_dir_size *
466
+ SECTOR_SIZE / sizeof(uint64_t),
467
+ const_header.grain_table_size *
468
+ SECTOR_SIZE / sizeof(uint64_t),
469
+ const_header.grain_size,
470
+ &extent,
471
+ errp);
472
+ if (ret < 0) {
473
+ return ret;
474
+ }
475
+
476
+ extent->sesparse = true;
477
+ extent->sesparse_l2_tables_offset = const_header.grain_tables_offset;
478
+ extent->sesparse_clusters_offset = const_header.grains_offset;
479
+ extent->entry_size = sizeof(uint64_t);
480
+
481
+ ret = vmdk_init_tables(bs, extent, errp);
482
+ if (ret) {
483
+ /* free extent allocated by vmdk_add_extent */
484
+ vmdk_free_last_extent(bs);
485
+ }
486
+
487
+ return ret;
488
+}
489
+
490
static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
491
QDict *options, Error **errp);
492
493
@@ -XXX,XX +XXX,XX @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
494
* RW [size in sectors] SPARSE "file-name.vmdk"
495
* RW [size in sectors] VMFS "file-name.vmdk"
496
* RW [size in sectors] VMFSSPARSE "file-name.vmdk"
497
+ * RW [size in sectors] SESPARSE "file-name.vmdk"
498
*/
499
flat_offset = -1;
500
matches = sscanf(p, "%10s %" SCNd64 " %10s \"%511[^\n\r\"]\" %" SCNd64,
501
@@ -XXX,XX +XXX,XX @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
502
503
if (sectors <= 0 ||
504
(strcmp(type, "FLAT") && strcmp(type, "SPARSE") &&
505
- strcmp(type, "VMFS") && strcmp(type, "VMFSSPARSE")) ||
506
+ strcmp(type, "VMFS") && strcmp(type, "VMFSSPARSE") &&
507
+ strcmp(type, "SESPARSE")) ||
508
(strcmp(access, "RW"))) {
509
continue;
510
}
511
@@ -XXX,XX +XXX,XX @@ static int vmdk_parse_extents(const char *desc, BlockDriverState *bs,
512
return ret;
513
}
70
}
514
extent = &s->extents[s->num_extents - 1];
71
- goto unlock;
515
+ } else if (!strcmp(type, "SESPARSE")) {
72
+ return ret;
516
+ ret = vmdk_open_se_sparse(bs, extent_file, bs->open_flags, errp);
517
+ if (ret) {
518
+ bdrv_unref_child(bs, extent_file);
519
+ return ret;
520
+ }
521
+ extent = &s->extents[s->num_extents - 1];
522
} else {
523
error_setg(errp, "Unsupported extent type '%s'", type);
524
bdrv_unref_child(bs, extent_file);
525
@@ -XXX,XX +XXX,XX @@ static int vmdk_open_desc_file(BlockDriverState *bs, int flags, char *buf,
526
if (strcmp(ct, "monolithicFlat") &&
527
strcmp(ct, "vmfs") &&
528
strcmp(ct, "vmfsSparse") &&
529
+ strcmp(ct, "seSparse") &&
530
strcmp(ct, "twoGbMaxExtentSparse") &&
531
strcmp(ct, "twoGbMaxExtentFlat")) {
532
error_setg(errp, "Unsupported image type '%s'", ct);
533
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
534
{
535
unsigned int l1_index, l2_offset, l2_index;
536
int min_index, i, j;
537
- uint32_t min_count, *l2_table;
538
+ uint32_t min_count;
539
+ void *l2_table;
540
bool zeroed = false;
541
int64_t ret;
542
int64_t cluster_sector;
543
+ unsigned int l2_size_bytes = extent->l2_size * extent->entry_size;
544
545
if (m_data) {
546
m_data->valid = 0;
547
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
548
if (l1_index >= extent->l1_size) {
549
return VMDK_ERROR;
550
}
551
- l2_offset = extent->l1_table[l1_index];
552
+ if (extent->sesparse) {
553
+ uint64_t l2_offset_u64;
554
+
555
+ assert(extent->entry_size == sizeof(uint64_t));
556
+
557
+ l2_offset_u64 = ((uint64_t *)extent->l1_table)[l1_index];
558
+ if (l2_offset_u64 == 0) {
559
+ l2_offset = 0;
560
+ } else if ((l2_offset_u64 & 0xffffffff00000000) != 0x1000000000000000) {
561
+ /*
562
+ * Top most nibble is 0x1 if grain table is allocated.
563
+ * strict check - top most 4 bytes must be 0x10000000 since max
564
+ * supported size is 64TB for disk - so no more than 64TB / 16MB
565
+ * grain directories which is smaller than uint32,
566
+ * where 16MB is the only supported default grain table coverage.
567
+ */
568
+ return VMDK_ERROR;
569
+ } else {
570
+ l2_offset_u64 = l2_offset_u64 & 0x00000000ffffffff;
571
+ l2_offset_u64 = extent->sesparse_l2_tables_offset +
572
+ l2_offset_u64 * l2_size_bytes / SECTOR_SIZE;
573
+ if (l2_offset_u64 > 0x00000000ffffffff) {
574
+ return VMDK_ERROR;
575
+ }
576
+ l2_offset = (unsigned int)(l2_offset_u64);
577
+ }
578
+ } else {
579
+ assert(extent->entry_size == sizeof(uint32_t));
580
+ l2_offset = ((uint32_t *)extent->l1_table)[l1_index];
581
+ }
582
if (!l2_offset) {
583
return VMDK_UNALLOC;
584
}
585
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
586
extent->l2_cache_counts[j] >>= 1;
587
}
588
}
589
- l2_table = extent->l2_cache + (i * extent->l2_size);
590
+ l2_table = (char *)extent->l2_cache + (i * l2_size_bytes);
591
goto found;
592
}
73
}
593
}
74
}
594
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
75
595
min_index = i;
76
@@ -XXX,XX +XXX,XX @@ static int set_event_flag_handler(uint32_t conn_id, EventNotifier *notifier)
596
}
77
} else {
78
ret = -ENOENT;
597
}
79
}
598
- l2_table = extent->l2_cache + (min_index * extent->l2_size);
80
-unlock:
599
+ l2_table = (char *)extent->l2_cache + (min_index * l2_size_bytes);
81
- qemu_mutex_unlock(&handlers_mutex);
600
BLKDBG_EVENT(extent->file, BLKDBG_L2_LOAD);
82
+
601
if (bdrv_pread(extent->file,
83
return ret;
602
(int64_t)l2_offset * 512,
84
}
603
l2_table,
85
604
- extent->l2_size * sizeof(uint32_t)
86
diff --git a/hw/rdma/rdma_backend.c b/hw/rdma/rdma_backend.c
605
- ) != extent->l2_size * sizeof(uint32_t)) {
87
index XXXXXXX..XXXXXXX 100644
606
+ l2_size_bytes
88
--- a/hw/rdma/rdma_backend.c
607
+ ) != l2_size_bytes) {
89
+++ b/hw/rdma/rdma_backend.c
608
return VMDK_ERROR;
90
@@ -XXX,XX +XXX,XX @@ static int rdma_poll_cq(RdmaDeviceResources *rdma_dev_res, struct ibv_cq *ibcq)
91
struct ibv_wc wc[2];
92
RdmaProtectedGSList *cqe_ctx_list;
93
94
- qemu_mutex_lock(&rdma_dev_res->lock);
95
- do {
96
- ne = ibv_poll_cq(ibcq, ARRAY_SIZE(wc), wc);
97
+ WITH_QEMU_LOCK_GUARD(&rdma_dev_res->lock) {
98
+ do {
99
+ ne = ibv_poll_cq(ibcq, ARRAY_SIZE(wc), wc);
100
101
- trace_rdma_poll_cq(ne, ibcq);
102
+ trace_rdma_poll_cq(ne, ibcq);
103
104
- for (i = 0; i < ne; i++) {
105
- bctx = rdma_rm_get_cqe_ctx(rdma_dev_res, wc[i].wr_id);
106
- if (unlikely(!bctx)) {
107
- rdma_error_report("No matching ctx for req %"PRId64,
108
- wc[i].wr_id);
109
- continue;
110
- }
111
+ for (i = 0; i < ne; i++) {
112
+ bctx = rdma_rm_get_cqe_ctx(rdma_dev_res, wc[i].wr_id);
113
+ if (unlikely(!bctx)) {
114
+ rdma_error_report("No matching ctx for req %"PRId64,
115
+ wc[i].wr_id);
116
+ continue;
117
+ }
118
119
- comp_handler(bctx->up_ctx, &wc[i]);
120
+ comp_handler(bctx->up_ctx, &wc[i]);
121
122
- if (bctx->backend_qp) {
123
- cqe_ctx_list = &bctx->backend_qp->cqe_ctx_list;
124
- } else {
125
- cqe_ctx_list = &bctx->backend_srq->cqe_ctx_list;
126
- }
127
+ if (bctx->backend_qp) {
128
+ cqe_ctx_list = &bctx->backend_qp->cqe_ctx_list;
129
+ } else {
130
+ cqe_ctx_list = &bctx->backend_srq->cqe_ctx_list;
131
+ }
132
133
- rdma_protected_gslist_remove_int32(cqe_ctx_list, wc[i].wr_id);
134
- rdma_rm_dealloc_cqe_ctx(rdma_dev_res, wc[i].wr_id);
135
- g_free(bctx);
136
- }
137
- total_ne += ne;
138
- } while (ne > 0);
139
- atomic_sub(&rdma_dev_res->stats.missing_cqe, total_ne);
140
- qemu_mutex_unlock(&rdma_dev_res->lock);
141
+ rdma_protected_gslist_remove_int32(cqe_ctx_list, wc[i].wr_id);
142
+ rdma_rm_dealloc_cqe_ctx(rdma_dev_res, wc[i].wr_id);
143
+ g_free(bctx);
144
+ }
145
+ total_ne += ne;
146
+ } while (ne > 0);
147
+ atomic_sub(&rdma_dev_res->stats.missing_cqe, total_ne);
148
+ }
149
150
if (ne < 0) {
151
rdma_error_report("ibv_poll_cq fail, rc=%d, errno=%d", ne, errno);
152
diff --git a/hw/rdma/rdma_rm.c b/hw/rdma/rdma_rm.c
153
index XXXXXXX..XXXXXXX 100644
154
--- a/hw/rdma/rdma_rm.c
155
+++ b/hw/rdma/rdma_rm.c
156
@@ -XXX,XX +XXX,XX @@ static inline void rdma_res_tbl_dealloc(RdmaRmResTbl *tbl, uint32_t handle)
157
{
158
trace_rdma_res_tbl_dealloc(tbl->name, handle);
159
160
- qemu_mutex_lock(&tbl->lock);
161
+ QEMU_LOCK_GUARD(&tbl->lock);
162
163
if (handle < tbl->tbl_sz) {
164
clear_bit(handle, tbl->bitmap);
165
tbl->used--;
609
}
166
}
610
167
611
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
168
- qemu_mutex_unlock(&tbl->lock);
612
extent->l2_cache_counts[min_index] = 1;
169
}
613
found:
170
614
l2_index = ((offset >> 9) / extent->cluster_sectors) % extent->l2_size;
171
int rdma_rm_alloc_pd(RdmaDeviceResources *dev_res, RdmaBackendDev *backend_dev,
615
- cluster_sector = le32_to_cpu(l2_table[l2_index]);
616
617
- if (extent->has_zero_grain && cluster_sector == VMDK_GTE_ZEROED) {
618
- zeroed = true;
619
+ if (extent->sesparse) {
620
+ cluster_sector = le64_to_cpu(((uint64_t *)l2_table)[l2_index]);
621
+ switch (cluster_sector & 0xf000000000000000) {
622
+ case 0x0000000000000000:
623
+ /* unallocated grain */
624
+ if (cluster_sector != 0) {
625
+ return VMDK_ERROR;
626
+ }
627
+ break;
628
+ case 0x1000000000000000:
629
+ /* scsi-unmapped grain - fallthrough */
630
+ case 0x2000000000000000:
631
+ /* zero grain */
632
+ zeroed = true;
633
+ break;
634
+ case 0x3000000000000000:
635
+ /* allocated grain */
636
+ cluster_sector = (((cluster_sector & 0x0fff000000000000) >> 48) |
637
+ ((cluster_sector & 0x0000ffffffffffff) << 12));
638
+ cluster_sector = extent->sesparse_clusters_offset +
639
+ cluster_sector * extent->cluster_sectors;
640
+ break;
641
+ default:
642
+ return VMDK_ERROR;
643
+ }
644
+ } else {
645
+ cluster_sector = le32_to_cpu(((uint32_t *)l2_table)[l2_index]);
646
+
647
+ if (extent->has_zero_grain && cluster_sector == VMDK_GTE_ZEROED) {
648
+ zeroed = true;
649
+ }
650
}
651
652
if (!cluster_sector || zeroed) {
653
if (!allocate) {
654
return zeroed ? VMDK_ZEROED : VMDK_UNALLOC;
655
}
656
+ assert(!extent->sesparse);
657
658
if (extent->next_cluster_sector >= VMDK_EXTENT_MAX_SECTORS) {
659
return VMDK_ERROR;
660
@@ -XXX,XX +XXX,XX @@ static int get_cluster_offset(BlockDriverState *bs,
661
m_data->l1_index = l1_index;
662
m_data->l2_index = l2_index;
663
m_data->l2_offset = l2_offset;
664
- m_data->l2_cache_entry = &l2_table[l2_index];
665
+ m_data->l2_cache_entry = ((uint32_t *)l2_table) + l2_index;
666
}
667
}
668
*cluster_offset = cluster_sector << BDRV_SECTOR_BITS;
669
@@ -XXX,XX +XXX,XX @@ static int vmdk_pwritev(BlockDriverState *bs, uint64_t offset,
670
if (!extent) {
671
return -EIO;
672
}
673
+ if (extent->sesparse) {
674
+ return -ENOTSUP;
675
+ }
676
offset_in_cluster = vmdk_find_offset_in_cluster(extent, offset);
677
n_bytes = MIN(bytes, extent->cluster_sectors * BDRV_SECTOR_SIZE
678
- offset_in_cluster);
679
--
172
--
680
2.21.0
173
2.25.3
681
174
682
diff view generated by jsdifflib