| Message ID | 20210704080820.88746-1-arseny.krasnov@kaspersky.com |
|---|---|
| Headers | show |
| Series | Improve SOCK_SEQPACKET receive logic | expand |
On 04.07.2021 12:54, Michael S. Tsirkin wrote: > On Sun, Jul 04, 2021 at 12:23:03PM +0300, Arseny Krasnov wrote: >> On 04.07.2021 11:30, Michael S. Tsirkin wrote: >>> On Sun, Jul 04, 2021 at 11:08:13AM +0300, Arseny Krasnov wrote: >>>> This patchset modifies receive logic for SOCK_SEQPACKET. >>>> Difference between current implementation and this version is that >>>> now reader is woken up when there is at least one RW packet in rx >>>> queue of socket and data is copied to user's buffer, while merged >>>> approach wake up user only when whole message is received and kept >>>> in queue. New implementation has several advantages: >>>> 1) There is no limit for message length. Merged approach requires >>>> that length must be smaller than 'peer_buf_alloc', otherwise >>>> transmission will stuck. >>>> 2) There is no need to keep whole message in queue, thus no >>>> 'kmalloc()' memory will be wasted until EOR is received. >>>> >>>> Also new approach has some feature: as fragments of message >>>> are copied until EOR is received, it is possible that part of >>>> message will be already in user's buffer, while rest of message >>>> still not received. And if user will be interrupted by signal or >>>> timeout with part of message in buffer, it will exit receive loop, >>>> leaving rest of message in queue. To solve this problem special >>>> callback was added to transport: it is called when user was forced >>>> to leave exit loop and tells transport to drop any packet until >>>> EOR met. >>> Sorry about commenting late in the game. I'm a bit lost >>> >>> >>> SOCK_SEQPACKET >>> Provides sequenced, reliable, bidirectional, connection-mode transmission paths for records. A record can be sent using one or more output operations and received using one or more input operations, but a single operation never transfers part of more than one record. Record boundaries are visible to the receiver via the MSG_EOR flag. >>> >>> it's supposed to be reliable - how is it legal to drop packets? >> Sorry, seems i need to rephrase description. "Packet" here means fragment of record(message) at transport >> >> layer. As this is SEQPACKET mode, receiver could get only whole message or error, so if only several fragments >> >> of message was copied (if signal received for example) we can't return it to user - it breaks SEQPACKET sense. I think, >> >> in this case we can drop rest of record's fragments legally. >> >> >> Thank You > Would not that violate the reliable property? IIUC it's only ok to > return an error if socket gets closed. Just like e.g. TCP ... > Sorry for late answer, yes You're right, seems this is unwanted drop... Lets wait for Stefano Garzarella feedback Thank You > >>> >>>> When EOR is found, this mode is disabled and normal packet >>>> processing started. Note, that when 'drop until EOR' mode is on, >>>> incoming packets still inserted in queue, reader will be woken up, >>>> tries to copy data, but nothing will be copied until EOR found. >>>> It was possible to drain such unneeded packets it rx work without >>>> kicking user, but implemented way is simplest. Anyway, i think >>>> such cases are rare. >>>> New test also added - it tries to copy to invalid user's >>>> buffer. >>>> >>>> Arseny Krasnov (16): >>>> af_vsock/virtio/vsock: change seqpacket receive logic >>>> af_vsock/virtio/vsock: remove 'seqpacket_has_data' callback >>>> virtio/vsock: remove 'msg_count' based logic >>>> af_vsock/virtio/vsock: add 'seqpacket_drop()' callback >>>> virtio/vsock: remove record size limit for SEQPACKET >>>> vsock_test: SEQPACKET read to broken buffer >>>> >>>> drivers/vhost/vsock.c | 2 +- >>>> include/linux/virtio_vsock.h | 7 +- >>>> include/net/af_vsock.h | 4 +- >>>> net/vmw_vsock/af_vsock.c | 44 ++++---- >>>> net/vmw_vsock/virtio_transport.c | 2 +- >>>> net/vmw_vsock/virtio_transport_common.c | 103 ++++++++----------- >>>> net/vmw_vsock/vsock_loopback.c | 2 +- >>>> tools/testing/vsock/vsock_test.c | 120 ++++++++++++++++++++++ >>>> 8 files changed, 193 insertions(+), 91 deletions(-) >>>> >>>> v1 -> v2: >>>> Patches reordered and reorganized. >>>> >>>> Signed-off-by: Arseny Krasnov <arseny.krasnov@kaspersky.com> >>>> --- >>>> cv.txt | 0 >>>> 1 file changed, 0 insertions(+), 0 deletions(-) >>>> create mode 100644 cv.txt >>>> >>>> diff --git a/cv.txt b/cv.txt >>>> new file mode 100644 >>>> index 000000000000..e69de29bb2d1 >>>> -- >>>> 2.25.1 >
This patchset modifies receive logic for SOCK_SEQPACKET. Difference between current implementation and this version is that now reader is woken up when there is at least one RW packet in rx queue of socket and data is copied to user's buffer, while merged approach wake up user only when whole message is received and kept in queue. New implementation has several advantages: 1) There is no limit for message length. Merged approach requires that length must be smaller than 'peer_buf_alloc', otherwise transmission will stuck. 2) There is no need to keep whole message in queue, thus no 'kmalloc()' memory will be wasted until EOR is received. Also new approach has some feature: as fragments of message are copied until EOR is received, it is possible that part of message will be already in user's buffer, while rest of message still not received. And if user will be interrupted by signal or timeout with part of message in buffer, it will exit receive loop, leaving rest of message in queue. To solve this problem special callback was added to transport: it is called when user was forced to leave exit loop and tells transport to drop any packet until EOR met. When EOR is found, this mode is disabled and normal packet processing started. Note, that when 'drop until EOR' mode is on, incoming packets still inserted in queue, reader will be woken up, tries to copy data, but nothing will be copied until EOR found. It was possible to drain such unneeded packets it rx work without kicking user, but implemented way is simplest. Anyway, i think such cases are rare. New test also added - it tries to copy to invalid user's buffer. Arseny Krasnov (16): af_vsock/virtio/vsock: change seqpacket receive logic af_vsock/virtio/vsock: remove 'seqpacket_has_data' callback virtio/vsock: remove 'msg_count' based logic af_vsock/virtio/vsock: add 'seqpacket_drop()' callback virtio/vsock: remove record size limit for SEQPACKET vsock_test: SEQPACKET read to broken buffer drivers/vhost/vsock.c | 2 +- include/linux/virtio_vsock.h | 7 +- include/net/af_vsock.h | 4 +- net/vmw_vsock/af_vsock.c | 44 ++++---- net/vmw_vsock/virtio_transport.c | 2 +- net/vmw_vsock/virtio_transport_common.c | 103 ++++++++----------- net/vmw_vsock/vsock_loopback.c | 2 +- tools/testing/vsock/vsock_test.c | 120 ++++++++++++++++++++++ 8 files changed, 193 insertions(+), 91 deletions(-) v1 -> v2: Patches reordered and reorganized. Signed-off-by: Arseny Krasnov <arseny.krasnov@kaspersky.com> --- cv.txt | 0 1 file changed, 0 insertions(+), 0 deletions(-) create mode 100644 cv.txt diff --git a/cv.txt b/cv.txt new file mode 100644 index 000000000000..e69de29bb2d1