vhost: make SET_VRING_ADDR, SET_FEATURES send replies
PATCH 1/1 vhost: make SET_VRING_ADDR, SET_FEATURES send replies
On vhost-user-blk migration, qemu normally sends a number of commands to enable logging if VHOST_USER_PROTOCOL_F_LOG_SHMFD is negotiated. Qemu sends VHOST_USER_SET_FEATURES to enable buffers logging and VHOST_USER_SET_VRING_ADDR per each started ring to enable "used ring" data logging.
The issue is that qemu doesn't wait for reply from the vhost daemon for these commands which may result in races between qemu expectation of logging starting and actual login starting in vhost daemon.
The race can appear as follows: on migration setup, qemu enables dirty page logging by sending VHOST_USER_SET_FEATURES. The command doesn't arrive to a vhost-user-blk daemon immediately and the daemon needs some time to turn the logging on internally. If qemu doesn't wait for reply, after sending the command, qemu may start migrate memory pages to a destination. At this time, the logging may not be actually turned on in the daemon but some guest pages, which the daemon is about to write to, may have already been transferred without logging to the destination. Since the logging wasn't turned on, those pages won't be transferred again as dirty. So we may end up with corrupted data on the destination.
The same scenario is applicable for "used ring" data logging, which is turned on with VHOST_USER_SET_VRING_ADDR command.
To resolve this issue, this patch makes qemu wait for the commands result explicilty if VHOST_USER_PROTOCOL_F_REPLY_ACK is negotiated.
--- hw/virtio/vhost-user.c | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-)
hw/virtio/vhost-user.c +28 -3
@@ -1105,10 +1105,20 @@ static int vhost_user_set_vring_addr(struct vhost_dev *dev, .hdr.size = sizeof(msg.payload.addr), }; +bool reply_supported =virtio_has_feature (dev->protocol_features, +VHOST_USER_PROTOCOL_F_REPLY_ACK ); +if (reply_supported) { + msg.hdr.flags |=VHOST_USER_NEED_REPLY_MASK ; + } +if (vhost_user_write (dev, &msg,NULL ,0 ) <0 ) {return -1 ; } +if (reply_supported) { +return process_message_reply (dev, &msg); + } +return 0 ; }
@@ -1288,7 +1298,8 @@ static int vhost_user_set_vring_call(struct vhost_dev *dev,return vhost_set_vring_file (dev,VHOST_USER_SET_VRING_CALL , file); } -static int vhost_user_set_u64 (struct vhost_dev *dev,int request,uint64_t u64) +static int vhost_user_set_u64 (struct vhost_dev *dev,int request,uint64_t u64, +bool need_reply) {VhostUserMsg msg = { .hdr.request = request,
@@ -1297,23 +1308,37 @@ static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64) .hdr.size = sizeof(msg.payload.u64), }; +if (need_reply) { +bool reply_supported =virtio_has_feature (dev->protocol_features, +VHOST_USER_PROTOCOL_F_REPLY_ACK ); +if (reply_supported) { + msg.hdr.flags |=VHOST_USER_NEED_REPLY_MASK ; + } + } +if (vhost_user_write (dev, &msg,NULL ,0 ) <0 ) {return -1 ; } +if (msg.hdr.flags &VHOST_USER_NEED_REPLY_MASK ) { +return process_message_reply (dev, &msg); + } +return 0 ; }static int vhost_user_set_features (struct vhost_dev *dev,uint64_t features) { -return vhost_user_set_u64 (dev,VHOST_USER_SET_FEATURES , features); +return vhost_user_set_u64 (dev,VHOST_USER_SET_FEATURES , features, + true); }static int vhost_user_set_protocol_features (struct vhost_dev *dev,uint64_t features) { -return vhost_user_set_u64 (dev,VHOST_USER_SET_PROTOCOL_FEATURES , features); +return vhost_user_set_u64 (dev,VHOST_USER_SET_PROTOCOL_FEATURES , features, + false); }static int vhost_user_get_u64 (struct vhost_dev *dev,int request,uint64_t *u64)
Signature · 1 line
2.25.1
Quoted 45 lines · Denis Plotnikov
On vhost-user-blk migration, qemu normally sends a number of commands to enable logging if
VHOST_USER_PROTOCOL_F_LOG_SHMFDis negotiated. Qemu sendsVHOST_USER_SET_FEATURESto enable buffers logging andVHOST_USER_SET_VRING_ADDRper each started ring to enable "used ring" data logging.
The issue is that qemu doesn't wait for reply from the vhost daemon for these commands which may result in races between qemu expectation of logging starting and actual login starting in vhost daemon.The race can appear as follows: on migration setup, qemu enables dirty page logging by sending
VHOST_USER_SET_FEATURES. The command doesn't arrive to a vhost-user-blk daemon immediately and the daemon needs some time to turn the logging on internally. If qemu doesn't wait for reply, after sending the command, qemu may start migrate memory pages to a destination. At this time, the logging may not be actually turned on in the daemon but some guest pages, which the daemon is about to write to, may have already been transferred without logging to the destination. Since the logging wasn't turned on, those pages won't be transferred again as dirty. So we may end up with corrupted data on the destination.
The same scenario is applicable for "used ring" data logging, which is turned on withVHOST_USER_SET_VRING_ADDRcommand.To resolve this issue, this patch makes qemu wait for the commands result explicilty if
VHOST_USER_PROTOCOL_F_REPLY_ACKis negotiated.Signed-off-by Denis Plotnikov <[email protected]>--- hw/virtio/vhost-user.c | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-)hw/virtio/vhost-user.c +6
-0@@ -1105,10 +1105,20 @@ static int vhost_user_set_vring_addr(struct vhost_dev *dev, .hdr.size = sizeof(msg.payload.addr), }; +bool reply_supported =virtio_has_feature (dev->protocol_features, +VHOST_USER_PROTOCOL_F_REPLY_ACK ); +if (reply_supported) { + msg.hdr.flags |=VHOST_USER_NEED_REPLY_MASK ; + } +if (vhost_user_write (dev, &msg,NULL ,0 ) <0 ) {
hw/virtio/vhost-user.c static int vhost_user_set_vring_addr(struct vhost_dev *dev, · line 1124
Quoted 10 lines
hw/virtio/vhost-user.c +4
-0return -1 ; } +if (reply_supported) { +return process_message_reply (dev, &msg); + } +return 0 ; }
Same - can we limit this to when logging is being enabled?
Quoted 31 lines
hw/virtio/vhost-user.c +14
-1@@ -1288,7 +1298,8 @@ static int vhost_user_set_vring_call(struct vhost_dev *dev,return vhost_set_vring_file (dev,VHOST_USER_SET_VRING_CALL , file); } -static int vhost_user_set_u64 (struct vhost_dev *dev,int request,uint64_t u64) +static int vhost_user_set_u64 (struct vhost_dev *dev,int request,uint64_t u64, +bool need_reply) {VhostUserMsg msg = { .hdr.request = request,@@ -1297,23 +1308,37 @@ static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64) .hdr.size = sizeof(msg.payload.u64), }; +if (need_reply) { +bool reply_supported =virtio_has_feature (dev->protocol_features, +VHOST_USER_PROTOCOL_F_REPLY_ACK ); +if (reply_supported) { + msg.hdr.flags |=VHOST_USER_NEED_REPLY_MASK ; + } + } +if (vhost_user_write (dev, &msg,NULL ,0 ) <0 ) {return -1 ; } +if (msg.hdr.flags &VHOST_USER_NEED_REPLY_MASK ) { +return process_message_reply (dev, &msg); + } +return 0 ;
hw/virtio/vhost-user.c static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64) · line 1336
Quoted 10 lines
hw/virtio/vhost-user.c +2
-1}static int vhost_user_set_features (struct vhost_dev *dev,uint64_t features) { -return vhost_user_set_u64 (dev,VHOST_USER_SET_FEATURES , features); +return vhost_user_set_u64 (dev,VHOST_USER_SET_FEATURES , features, + true); }
Same here. In fact,
Quoted 11 lines
hw/virtio/vhost-user.c +2
-1static int vhost_user_set_protocol_features (struct vhost_dev *dev,uint64_t features) { -return vhost_user_set_u64 (dev,VHOST_USER_SET_PROTOCOL_FEATURES , features); +return vhost_user_set_u64 (dev,VHOST_USER_SET_PROTOCOL_FEATURES , features, + false); }static int vhost_user_get_u64 (struct vhost_dev *dev,int request,uint64_t *u64)Signature · 1 line
2.25.1
Quoted 49 lines · Michael S. Tsirkin
Quoted 48 lines · Denis Plotnikov
On vhost-user-blk migration, qemu normally sends a number of commands to enable logging if
VHOST_USER_PROTOCOL_F_LOG_SHMFDis negotiated. Qemu sendsVHOST_USER_SET_FEATURESto enable buffers logging andVHOST_USER_SET_VRING_ADDRper each started ring to enable "used ring" data logging.
The issue is that qemu doesn't wait for reply from the vhost daemon for these commands which may result in races between qemu expectation of logging starting and actual login starting in vhost daemon.The race can appear as follows: on migration setup, qemu enables dirty page logging by sending
VHOST_USER_SET_FEATURES. The command doesn't arrive to a vhost-user-blk daemon immediately and the daemon needs some time to turn the logging on internally. If qemu doesn't wait for reply, after sending the command, qemu may start migrate memory pages to a destination. At this time, the logging may not be actually turned on in the daemon but some guest pages, which the daemon is about to write to, may have already been transferred without logging to the destination. Since the logging wasn't turned on, those pages won't be transferred again as dirty. So we may end up with corrupted data on the destination.
The same scenario is applicable for "used ring" data logging, which is turned on withVHOST_USER_SET_VRING_ADDRcommand.To resolve this issue, this patch makes qemu wait for the commands result explicilty if
VHOST_USER_PROTOCOL_F_REPLY_ACKis negotiated.Signed-off-by Denis Plotnikov <[email protected]>--- hw/virtio/vhost-user.c | 31 ++++++++++++++++++++++++++++--- 1 file changed, 28 insertions(+), 3 deletions(-)hw/virtio/vhost-user.c +6
-0@@ -1105,10 +1105,20 @@ static int vhost_user_set_vring_addr(struct vhost_dev *dev, .hdr.size = sizeof(msg.payload.addr), }; +bool reply_supported =virtio_has_feature (dev->protocol_features, +VHOST_USER_PROTOCOL_F_REPLY_ACK ); +if (reply_supported) { + msg.hdr.flags |=VHOST_USER_NEED_REPLY_MASK ; + } +if (vhost_user_write (dev, &msg,NULL ,0 ) <0 ) {return -1 ; }
Quoted 8 lines
hw/virtio/vhost-user.c static int vhost_user_set_vring_addr(struct vhost_dev *dev, · line 1124
Quoted 7 lines
hw/virtio/vhost-user.c +4
-0+if (reply_supported) { +return process_message_reply (dev, &msg); + } +return 0 ; }Same - can we limit this to when logging is being enabled?
I think it's possible but do we really need some additional complexity?
Do you bother about delays on device initialization? Would the reply for the command introduce significant device initialization time delay? In my understanding, this is done rarely on vhost-user device initialization. So, may be we can afford it to be a little bit longer?
According to the migration case, in my understanding, major time the migration of vhost-user should be done with logging enabled. Otherwise it's hard to tell how to make sure that the memory migrates with consistent data. So here we shouldn't care too much about setup speed and should care more about data consistency. What do you think?
Thanks!
Denis
Quoted 55 lines
Quoted 32 lines
hw/virtio/vhost-user.c +14
-1@@ -1288,7 +1298,8 @@ static int vhost_user_set_vring_call(struct vhost_dev *dev,return vhost_set_vring_file (dev,VHOST_USER_SET_VRING_CALL , file); } -static int vhost_user_set_u64 (struct vhost_dev *dev,int request,uint64_t u64) +static int vhost_user_set_u64 (struct vhost_dev *dev,int request,uint64_t u64, +bool need_reply) {VhostUserMsg msg = { .hdr.request = request,@@ -1297,23 +1308,37 @@ static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64) .hdr.size = sizeof(msg.payload.u64), }; +if (need_reply) { +bool reply_supported =virtio_has_feature (dev->protocol_features, +VHOST_USER_PROTOCOL_F_REPLY_ACK ); +if (reply_supported) { + msg.hdr.flags |=VHOST_USER_NEED_REPLY_MASK ; + } + } +if (vhost_user_write (dev, &msg,NULL ,0 ) <0 ) {return -1 ; } +if (msg.hdr.flags &VHOST_USER_NEED_REPLY_MASK ) { +return process_message_reply (dev, &msg); + } +return 0 ;hw/virtio/vhost-user.c static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64) · line 1336
Quoted 10 lines
hw/virtio/vhost-user.c +2
-1}static int vhost_user_set_features (struct vhost_dev *dev,uint64_t features) { -return vhost_user_set_u64 (dev,VHOST_USER_SET_FEATURES , features); +return vhost_user_set_u64 (dev,VHOST_USER_SET_FEATURES , features, + true); }Same here. In fact,
Quoted 11 lines
hw/virtio/vhost-user.c +2
-1static int vhost_user_set_protocol_features (struct vhost_dev *dev,uint64_t features) { -return vhost_user_set_u64 (dev,VHOST_USER_SET_PROTOCOL_FEATURES , features); +return vhost_user_set_u64 (dev,VHOST_USER_SET_PROTOCOL_FEATURES , features, + false); }static int vhost_user_get_u64 (struct vhost_dev *dev,int request,uint64_t *u64)Signature · 1 line
2.25.1
Quoted 60 lines · Denis Plotnikov
Quoted 47 lines · Michael S. Tsirkin
Quoted 46 lines · Denis Plotnikov
On vhost-user-blk migration, qemu normally sends a number of commands to enable logging if
VHOST_USER_PROTOCOL_F_LOG_SHMFDis negotiated. Qemu sendsVHOST_USER_SET_FEATURESto enable buffers logging andVHOST_USER_SET_VRING_ADDRper each started ring to enable "used ring" data logging.
The issue is that qemu doesn't wait for reply from the vhost daemon for these commands which may result in races between qemu expectation of logging starting and actual login starting in vhost daemon.The race can appear as follows: on migration setup, qemu enables dirty page logging by sending
VHOST_USER_SET_FEATURES. The command doesn't arrive to a vhost-user-blk daemon immediately and the daemon needs some time to turn the logging on internally. If qemu doesn't wait for reply, after sending the command, qemu may start migrate memory pages to a destination. At this time, the logging may not be actually turned on in the daemon but some guest pages, which the daemon is about to write to, may have already been transferred without logging to the destination. Since the logging wasn't turned on, those pages won't be transferred again as dirty. So we may end up with corrupted data on the destination.
The same scenario is applicable for "used ring" data logging, which is turned on withVHOST_USER_SET_VRING_ADDRcommand.To resolve this issue, this patch makes qemu wait for the commands result explicilty if
VHOST_USER_PROTOCOL_F_REPLY_ACKis negotiated.Signed-off-by Denis Plotnikov <[email protected]>---
hw/virtio/vhost-user.c| 31 ++++++++++++++++++++++++++++---1 file changed, 28 insertions(+), 3 deletions(-)hw/virtio/vhost-user.c +5
-0@@ -1105,10 +1105,20 @@ static int vhost_user_set_vring_addr(structvhost_dev *dev, .hdr.size = sizeof(msg.payload.addr), }; + bool reply_supported = virtio_has_feature(dev->protocol_features, +VHOST_USER_PROTOCOL_F_REPLY_ACK ); + if (reply_supported) { + msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK; + } + if (vhost_user_write(dev, &msg, NULL, 0) < 0) { return -1;Quoted 8 lines
hw/virtio/vhost-user.c static int vhost_user_set_vring_addr(struct vhost_dev *dev, · line 1123
Quoted 7 lines
hw/virtio/vhost-user.c +3
-0} + if (reply_supported) { + return process_message_reply(dev, &msg); + } + return 0; }Same - can we limit this to when logging is being enabled?
I think it's possible but do we really need some additional complexity?
Quoted 7 lines
Do you bother about delays on device initialization? Would the reply for the command introduce significant device initialization time delay? In my understanding, this is done rarely on vhost-user device initialization. So, may be we can afford it to be a little bit longer?
According to the migration case, in my understanding, major time the migration of vhost-user should be done with logging enabled. Otherwise it's hard to tell how to make sure that the memory migrates with consistent data. So here we shouldn't care too much about setup speed and should care more about data consistency. What do you think?
Thanks!
Denis
please, let me know if my points above seem to be unreasonable and I'll send another version with reply sending only when logging is enabled.
Thanks!
Denis
Quoted 56 lines
Quoted 56 lines
Quoted 32 lines
hw/virtio/vhost-user.c +2
-0@@ -1288,7 +1298,8 @@ static int vhost_user_set_vring_call(structvhost_dev *dev, return vhost_set_vring_file(dev, VHOST_USER_SET_VRING_CALL, file); } -static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64) +static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64, + bool need_reply) {VhostUserMsg msg = {
.hdr.request = request,hw/virtio/vhost-user.c +9
-0@@ -1297,23 +1308,37 @@ static int vhost_user_set_u64(struct vhost_dev *dev, int request, uint64_t u64) .hdr.size = sizeof(msg.payload.u64), }; + if (need_reply) { + bool reply_supported =virtio_has_feature (dev->protocol_features, +VHOST_USER_PROTOCOL_F_REPLY_ACK ); + if (reply_supported) { + msg.hdr.flags |= VHOST_USER_NEED_REPLY_MASK; + } + } + if (vhost_user_write(dev, &msg, NULL, 0) < 0) { return -1; } + if (msg.hdr.flags & VHOST_USER_NEED_REPLY_MASK) { + return process_message_reply(dev, &msg); + }hw/virtio/vhost-user.c static int vhost_user_set_u64(struct · line 1334
Quoted 10 lines
hw/virtio/vhost-user.c +3
-1+ return 0; } static int vhost_user_set_features(struct vhost_dev *dev, uint64_t features) { - return vhost_user_set_u64(dev, VHOST_USER_SET_FEATURES, features); + return vhost_user_set_u64(dev, VHOST_USER_SET_FEATURES, features, + true); }Same here. In fact,
Quoted 12 lines
hw/virtio/vhost-user.c +2
-1static int vhost_user_set_protocol_features(struct vhost_dev *dev, uint64_t features) { - return vhost_user_set_u64(dev, VHOST_USER_SET_PROTOCOL_FEATURES, features); + return vhost_user_set_u64(dev,VHOST_USER_SET_PROTOCOL_FEATURES , features, + false); }static int
vhost_user_get_u64(struct vhost_dev *dev, int request, uint64_t *u64)Signature · 1 line
2.25.1