Hello,
DESCRIPTION
This patchset fixes old problem with hungup of both rx/tx sides and adds
test for it. This happens due to non-default SO_RCVLOWAT value and
deferred credit update in virtio/vsock. Link to previous old patchset:
https://lore.kernel.org/netdev/[email protected]/
Here is what happens step by step:
TEST
INITIAL CONDITIONS
1) Vsock buffer size is 128KB.
2) Maximum packet size is also 64KB as defined in header (yes it is
hardcoded, just to remind about that value).
3) SO_RCVLOWAT is default, e.g. 1 byte.
STEPS
SENDER RECEIVER
1) sends 128KB + 1 byte in a
single buffer. 128KB will
be sent, but for 1 byte
sender will wait for free
space at peer. Sender goes
to sleep.
2) reads 64KB, credit update not sent
3) sets SO_RCVLOWAT to 64KB + 1
4) poll() -> wait forever, there is
only 64KB available to read.
So in step 4) receiver also goes to sleep, waiting for enough data or
connection shutdown message from the sender. Idea to fix it is that rx
kicks tx side to continue transmission (and may be close connection)
when rx changes number of bytes to be woken up (e.g. SO_RCVLOWAT) and
this value is bigger than number of available bytes to read.
I've added small test for this, but not sure as it uses hardcoded value
for maximum packet length, this value is defined in kernel header and
used to control deferred credit update. And as this is not available to
userspace, I can't control test parameters correctly (if one day this
define will be changed - test may become useless).
Head for this patchset is:
https://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next.git/commit/?id=f1be1e04c76bb9c44789d3575bba4418cf0ea359
Link to v1:
https://lore.kernel.org/netdev/[email protected]/
Link to v2:
https://lore.kernel.org/netdev/[email protected]/
Link to v3:
https://lore.kernel.org/netdev/[email protected]/
Changelog:
v1 -> v2:
* Patchset rebased and tested on new HEAD of net-next (see hash above).
* New patch is added as 0001 - it removes return from SO_RCVLOWAT set
callback in 'af_vsock.c' when transport callback is set - with that
we can set 'sk_rcvlowat' only once in 'af_vsock.c' and in future do
not copy-paste it to every transport. It was discussed in v1.
* See per-patch changelog after ---.
v2 -> v3:
* See changelog after --- in 0003 only (0001 and 0002 still same).
v3 -> v4:
* Patchset rebased and tested on new HEAD of net-next (see hash above).
* See per-patch changelog after ---.
Arseniy Krasnov (3):
vsock: update SO_RCVLOWAT setting callback
virtio/vsock: send credit update during setting SO_RCVLOWAT
vsock/test: SO_RCVLOWAT + deferred credit update test
drivers/vhost/vsock.c | 3 +-
include/linux/virtio_vsock.h | 1 +
include/net/af_vsock.h | 2 +-
net/vmw_vsock/af_vsock.c | 9 +-
net/vmw_vsock/hyperv_transport.c | 4 +-
net/vmw_vsock/virtio_transport.c | 3 +-
net/vmw_vsock/virtio_transport_common.c | 27 +++++
net/vmw_vsock/vsock_loopback.c | 3 +-
tools/testing/vsock/vsock_test.c | 149 ++++++++++++++++++++++++
9 files changed, 193 insertions(+), 8 deletions(-)
--
2.25.1
Do not return if transport callback for SO_RCVLOWAT is set (only in
error case). In this case we don't need to set 'sk_rcvlowat' field in
each transport - only in 'vsock_set_rcvlowat()'. Also, if 'sk_rcvlowat'
is now set only in af_vsock.c, change callback name from 'set_rcvlowat'
to 'notify_set_rcvlowat'.
Signed-off-by: Arseniy Krasnov <[email protected]>
---
Changelog:
v3 -> v4:
* Rename 'set_rcvlowat' to 'notify_set_rcvlowat'.
* Commit message updated.
include/net/af_vsock.h | 2 +-
net/vmw_vsock/af_vsock.c | 9 +++++++--
net/vmw_vsock/hyperv_transport.c | 4 ++--
3 files changed, 10 insertions(+), 5 deletions(-)
diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
index e302c0e804d0..535701efc1e5 100644
--- a/include/net/af_vsock.h
+++ b/include/net/af_vsock.h
@@ -137,7 +137,6 @@ struct vsock_transport {
u64 (*stream_rcvhiwat)(struct vsock_sock *);
bool (*stream_is_active)(struct vsock_sock *);
bool (*stream_allow)(u32 cid, u32 port);
- int (*set_rcvlowat)(struct vsock_sock *vsk, int val);
/* SEQ_PACKET. */
ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
@@ -168,6 +167,7 @@ struct vsock_transport {
struct vsock_transport_send_notify_data *);
/* sk_lock held by the caller */
void (*notify_buffer_size)(struct vsock_sock *, u64 *);
+ int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val);
/* Shutdown. */
int (*shutdown)(struct vsock_sock *, int);
diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
index 816725af281f..54ba7316f808 100644
--- a/net/vmw_vsock/af_vsock.c
+++ b/net/vmw_vsock/af_vsock.c
@@ -2264,8 +2264,13 @@ static int vsock_set_rcvlowat(struct sock *sk, int val)
transport = vsk->transport;
- if (transport && transport->set_rcvlowat)
- return transport->set_rcvlowat(vsk, val);
+ if (transport && transport->notify_set_rcvlowat) {
+ int err;
+
+ err = transport->notify_set_rcvlowat(vsk, val);
+ if (err)
+ return err;
+ }
WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
return 0;
diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
index 7cb1a9d2cdb4..e2157e387217 100644
--- a/net/vmw_vsock/hyperv_transport.c
+++ b/net/vmw_vsock/hyperv_transport.c
@@ -816,7 +816,7 @@ int hvs_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written,
}
static
-int hvs_set_rcvlowat(struct vsock_sock *vsk, int val)
+int hvs_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
{
return -EOPNOTSUPP;
}
@@ -856,7 +856,7 @@ static struct vsock_transport hvs_transport = {
.notify_send_pre_enqueue = hvs_notify_send_pre_enqueue,
.notify_send_post_enqueue = hvs_notify_send_post_enqueue,
- .set_rcvlowat = hvs_set_rcvlowat
+ .notify_set_rcvlowat = hvs_notify_set_rcvlowat
};
static bool hvs_check_transport(struct vsock_sock *vsk)
--
2.25.1
Send credit update message when SO_RCVLOWAT is updated and it is bigger
than number of bytes in rx queue. It is needed, because 'poll()' will
wait until number of bytes in rx queue will be not smaller than
SO_RCVLOWAT, so kick sender to send more data. Otherwise mutual hungup
for tx/rx is possible: sender waits for free space and receiver is
waiting data in 'poll()'.
Signed-off-by: Arseniy Krasnov <[email protected]>
---
Changelog:
v1 -> v2:
* Update commit message by removing 'This patch adds XXX' manner.
* Do not initialize 'send_update' variable - set it directly during
first usage.
v3 -> v4:
* Fit comment in 'virtio_transport_notify_set_rcvlowat()' to 80 chars.
drivers/vhost/vsock.c | 3 ++-
include/linux/virtio_vsock.h | 1 +
net/vmw_vsock/virtio_transport.c | 3 ++-
net/vmw_vsock/virtio_transport_common.c | 27 +++++++++++++++++++++++++
net/vmw_vsock/vsock_loopback.c | 3 ++-
5 files changed, 34 insertions(+), 3 deletions(-)
diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index f75731396b7e..c5e58a60a546 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -449,8 +449,9 @@ static struct virtio_transport vhost_transport = {
.notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue,
.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
.notify_buffer_size = virtio_transport_notify_buffer_size,
+ .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat,
- .read_skb = virtio_transport_read_skb,
+ .read_skb = virtio_transport_read_skb
},
.send_pkt = vhost_transport_send_pkt,
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index ebb3ce63d64d..c82089dee0c8 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -256,4 +256,5 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit);
void virtio_transport_deliver_tap_pkt(struct sk_buff *skb);
int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list);
int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t read_actor);
+int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val);
#endif /* _LINUX_VIRTIO_VSOCK_H */
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index af5bab1acee1..8b7bb7ca8ea5 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -537,8 +537,9 @@ static struct virtio_transport virtio_transport = {
.notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue,
.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
.notify_buffer_size = virtio_transport_notify_buffer_size,
+ .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat,
- .read_skb = virtio_transport_read_skb,
+ .read_skb = virtio_transport_read_skb
},
.send_pkt = virtio_transport_send_pkt,
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index f6dc896bf44c..1cb556ad4597 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -1684,6 +1684,33 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto
}
EXPORT_SYMBOL_GPL(virtio_transport_read_skb);
+int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
+{
+ struct virtio_vsock_sock *vvs = vsk->trans;
+ bool send_update;
+
+ spin_lock_bh(&vvs->rx_lock);
+
+ /* If number of available bytes is less than new SO_RCVLOWAT value,
+ * kick sender to send more data, because sender may sleep in its
+ * 'send()' syscall waiting for enough space at our side.
+ */
+ send_update = vvs->rx_bytes < val;
+
+ spin_unlock_bh(&vvs->rx_lock);
+
+ if (send_update) {
+ int err;
+
+ err = virtio_transport_send_credit_update(vsk);
+ if (err < 0)
+ return err;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(virtio_transport_notify_set_rcvlowat);
+
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Asias He");
MODULE_DESCRIPTION("common code for virtio vsock");
diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
index 048640167411..454f69838c2a 100644
--- a/net/vmw_vsock/vsock_loopback.c
+++ b/net/vmw_vsock/vsock_loopback.c
@@ -96,8 +96,9 @@ static struct virtio_transport loopback_transport = {
.notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue,
.notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
.notify_buffer_size = virtio_transport_notify_buffer_size,
+ .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat,
- .read_skb = virtio_transport_read_skb,
+ .read_skb = virtio_transport_read_skb
},
.send_pkt = vsock_loopback_send_pkt,
--
2.25.1
Test which checks, that updating SO_RCVLOWAT value also sends credit
update message. Otherwise mutual hungup may happen when receiver didn't
send credit update and then calls 'poll()' with non default SO_RCVLOWAT
value (e.g. waiting enough bytes to read), while sender waits for free
space at receiver's side. Important thing is that this test relies on
kernel's define for maximum packet size for virtio transport and this
value is not exported to user: VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (this
define is used to control moment when to send credit update message).
If this value or its usage will be changed in kernel - this test may
become useless/broken.
Signed-off-by: Arseniy Krasnov <[email protected]>
---
Changelog:
v1 -> v2:
* Update commit message by removing 'This patch adds XXX' manner.
* Update commit message by adding details about dependency for this
test from kernel internal define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE.
* Add comment for this dependency in 'vsock_test.c' where this define
is duplicated.
v2 -> v3:
* Replace synchronization based on control TCP socket with vsock
data socket - this is needed to allow sender transmit data only
when new buffer size of receiver is visible to sender. Otherwise
there is race and test fails sometimes.
v3 -> v4:
* Replace 'recv_buf()' to 'recv(MSG_DONTWAIT)' in last read operation
in server part. This is needed to ensure that 'poll()' wake up us
when number of bytes ready to read is equal to SO_RCVLOWAT value.
tools/testing/vsock/vsock_test.c | 149 +++++++++++++++++++++++++++++++
1 file changed, 149 insertions(+)
diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
index 01fa816868bc..68f7037834db 100644
--- a/tools/testing/vsock/vsock_test.c
+++ b/tools/testing/vsock/vsock_test.c
@@ -1232,6 +1232,150 @@ static void test_double_bind_connect_client(const struct test_opts *opts)
}
}
+#define RCVLOWAT_CREDIT_UPD_BUF_SIZE (1024 * 128)
+/* This define is the same as in 'include/linux/virtio_vsock.h':
+ * it is used to decide when to send credit update message during
+ * reading from rx queue of a socket. Value and its usage in
+ * kernel is important for this test.
+ */
+#define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64)
+
+static void test_stream_rcvlowat_def_cred_upd_client(const struct test_opts *opts)
+{
+ size_t buf_size;
+ void *buf;
+ int fd;
+
+ fd = vsock_stream_connect(opts->peer_cid, 1234);
+ if (fd < 0) {
+ perror("connect");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Send 1 byte more than peer's buffer size. */
+ buf_size = RCVLOWAT_CREDIT_UPD_BUF_SIZE + 1;
+
+ buf = malloc(buf_size);
+ if (!buf) {
+ perror("malloc");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Wait until peer sets needed buffer size. */
+ recv_byte(fd, 1, 0);
+
+ if (send(fd, buf, buf_size, 0) != buf_size) {
+ perror("send failed");
+ exit(EXIT_FAILURE);
+ }
+
+ free(buf);
+ close(fd);
+}
+
+static void test_stream_rcvlowat_def_cred_upd_server(const struct test_opts *opts)
+{
+ size_t recv_buf_size;
+ struct pollfd fds;
+ size_t buf_size;
+ void *buf;
+ int fd;
+
+ fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
+ if (fd < 0) {
+ perror("accept");
+ exit(EXIT_FAILURE);
+ }
+
+ buf_size = RCVLOWAT_CREDIT_UPD_BUF_SIZE;
+
+ if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE,
+ &buf_size, sizeof(buf_size))) {
+ perror("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Send one dummy byte here, because 'setsockopt()' above also
+ * sends special packet which tells sender to update our buffer
+ * size. This 'send_byte()' will serialize such packet with data
+ * reads in a loop below. Sender starts transmission only when
+ * it receives this single byte.
+ */
+ send_byte(fd, 1, 0);
+
+ buf = malloc(buf_size);
+ if (!buf) {
+ perror("malloc");
+ exit(EXIT_FAILURE);
+ }
+
+ /* Wait until there will be 128KB of data in rx queue. */
+ while (1) {
+ ssize_t res;
+
+ res = recv(fd, buf, buf_size, MSG_PEEK);
+ if (res == buf_size)
+ break;
+
+ if (res <= 0) {
+ fprintf(stderr, "unexpected 'recv()' return: %zi\n", res);
+ exit(EXIT_FAILURE);
+ }
+ }
+
+ /* There is 128KB of data in the socket's rx queue,
+ * dequeue first 64KB, credit update is not sent.
+ */
+ recv_buf_size = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE;
+ recv_buf(fd, buf, recv_buf_size, 0, recv_buf_size);
+ recv_buf_size++;
+
+ /* Updating SO_RCVLOWAT will send credit update. */
+ if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT,
+ &recv_buf_size, sizeof(recv_buf_size))) {
+ perror("setsockopt(SO_RCVLOWAT)");
+ exit(EXIT_FAILURE);
+ }
+
+ memset(&fds, 0, sizeof(fds));
+ fds.fd = fd;
+ fds.events = POLLIN | POLLRDNORM | POLLERR |
+ POLLRDHUP | POLLHUP;
+
+ /* This 'poll()' will return once we receive last byte
+ * sent by client.
+ */
+ if (poll(&fds, 1, -1) < 0) {
+ perror("poll");
+ exit(EXIT_FAILURE);
+ }
+
+ if (fds.revents & POLLERR) {
+ fprintf(stderr, "'poll()' error\n");
+ exit(EXIT_FAILURE);
+ }
+
+ if (fds.revents & (POLLIN | POLLRDNORM)) {
+ ssize_t res;
+
+ res = recv(fd, buf, recv_buf_size, MSG_DONTWAIT);
+ if (res != recv_buf_size) {
+ fprintf(stderr, "recv(2), expected %zu, got %zu\n",
+ recv_buf_size, res);
+ exit(EXIT_FAILURE);
+ }
+ } else {
+ /* These flags must be set, as there is at
+ * least 64KB of data ready to read.
+ */
+ fprintf(stderr, "POLLIN | POLLRDNORM expected\n");
+ exit(EXIT_FAILURE);
+ }
+
+ free(buf);
+ close(fd);
+}
+
static struct test_case test_cases[] = {
{
.name = "SOCK_STREAM connection reset",
@@ -1342,6 +1486,11 @@ static struct test_case test_cases[] = {
.run_client = test_double_bind_connect_client,
.run_server = test_double_bind_connect_server,
},
+ {
+ .name = "SOCK_STREAM virtio SO_RCVLOWAT + deferred cred update",
+ .run_client = test_stream_rcvlowat_def_cred_upd_client,
+ .run_server = test_stream_rcvlowat_def_cred_upd_server,
+ },
{},
};
--
2.25.1
On Thu, Nov 30, 2023 at 12:25:17AM +0300, Arseniy Krasnov wrote:
>Do not return if transport callback for SO_RCVLOWAT is set (only in
>error case). In this case we don't need to set 'sk_rcvlowat' field in
>each transport - only in 'vsock_set_rcvlowat()'. Also, if 'sk_rcvlowat'
>is now set only in af_vsock.c, change callback name from 'set_rcvlowat'
>to 'notify_set_rcvlowat'.
>
>Signed-off-by: Arseniy Krasnov <[email protected]>
>---
> Changelog:
> v3 -> v4:
> * Rename 'set_rcvlowat' to 'notify_set_rcvlowat'.
> * Commit message updated.
Reviewed-by: Stefano Garzarella <[email protected]>
>
> include/net/af_vsock.h | 2 +-
> net/vmw_vsock/af_vsock.c | 9 +++++++--
> net/vmw_vsock/hyperv_transport.c | 4 ++--
> 3 files changed, 10 insertions(+), 5 deletions(-)
>
>diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
>index e302c0e804d0..535701efc1e5 100644
>--- a/include/net/af_vsock.h
>+++ b/include/net/af_vsock.h
>@@ -137,7 +137,6 @@ struct vsock_transport {
> u64 (*stream_rcvhiwat)(struct vsock_sock *);
> bool (*stream_is_active)(struct vsock_sock *);
> bool (*stream_allow)(u32 cid, u32 port);
>- int (*set_rcvlowat)(struct vsock_sock *vsk, int val);
>
> /* SEQ_PACKET. */
> ssize_t (*seqpacket_dequeue)(struct vsock_sock *vsk, struct msghdr *msg,
>@@ -168,6 +167,7 @@ struct vsock_transport {
> struct vsock_transport_send_notify_data *);
> /* sk_lock held by the caller */
> void (*notify_buffer_size)(struct vsock_sock *, u64 *);
>+ int (*notify_set_rcvlowat)(struct vsock_sock *vsk, int val);
>
> /* Shutdown. */
> int (*shutdown)(struct vsock_sock *, int);
>diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
>index 816725af281f..54ba7316f808 100644
>--- a/net/vmw_vsock/af_vsock.c
>+++ b/net/vmw_vsock/af_vsock.c
>@@ -2264,8 +2264,13 @@ static int vsock_set_rcvlowat(struct sock *sk, int val)
>
> transport = vsk->transport;
>
>- if (transport && transport->set_rcvlowat)
>- return transport->set_rcvlowat(vsk, val);
>+ if (transport && transport->notify_set_rcvlowat) {
>+ int err;
>+
>+ err = transport->notify_set_rcvlowat(vsk, val);
>+ if (err)
>+ return err;
>+ }
>
> WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
> return 0;
>diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c
>index 7cb1a9d2cdb4..e2157e387217 100644
>--- a/net/vmw_vsock/hyperv_transport.c
>+++ b/net/vmw_vsock/hyperv_transport.c
>@@ -816,7 +816,7 @@ int hvs_notify_send_post_enqueue(struct vsock_sock *vsk, ssize_t written,
> }
>
> static
>-int hvs_set_rcvlowat(struct vsock_sock *vsk, int val)
>+int hvs_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
> {
> return -EOPNOTSUPP;
> }
>@@ -856,7 +856,7 @@ static struct vsock_transport hvs_transport = {
> .notify_send_pre_enqueue = hvs_notify_send_pre_enqueue,
> .notify_send_post_enqueue = hvs_notify_send_post_enqueue,
>
>- .set_rcvlowat = hvs_set_rcvlowat
>+ .notify_set_rcvlowat = hvs_notify_set_rcvlowat
> };
>
> static bool hvs_check_transport(struct vsock_sock *vsk)
>--
>2.25.1
>
On Thu, Nov 30, 2023 at 12:25:18AM +0300, Arseniy Krasnov wrote:
>Send credit update message when SO_RCVLOWAT is updated and it is bigger
>than number of bytes in rx queue. It is needed, because 'poll()' will
>wait until number of bytes in rx queue will be not smaller than
>SO_RCVLOWAT, so kick sender to send more data. Otherwise mutual hungup
>for tx/rx is possible: sender waits for free space and receiver is
>waiting data in 'poll()'.
>
>Signed-off-by: Arseniy Krasnov <[email protected]>
>---
> Changelog:
> v1 -> v2:
> * Update commit message by removing 'This patch adds XXX' manner.
> * Do not initialize 'send_update' variable - set it directly during
> first usage.
> v3 -> v4:
> * Fit comment in 'virtio_transport_notify_set_rcvlowat()' to 80 chars.
>
> drivers/vhost/vsock.c | 3 ++-
> include/linux/virtio_vsock.h | 1 +
> net/vmw_vsock/virtio_transport.c | 3 ++-
> net/vmw_vsock/virtio_transport_common.c | 27 +++++++++++++++++++++++++
> net/vmw_vsock/vsock_loopback.c | 3 ++-
> 5 files changed, 34 insertions(+), 3 deletions(-)
>
>diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
>index f75731396b7e..c5e58a60a546 100644
>--- a/drivers/vhost/vsock.c
>+++ b/drivers/vhost/vsock.c
>@@ -449,8 +449,9 @@ static struct virtio_transport vhost_transport = {
> .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue,
> .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
> .notify_buffer_size = virtio_transport_notify_buffer_size,
>+ .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat,
>
>- .read_skb = virtio_transport_read_skb,
>+ .read_skb = virtio_transport_read_skb
I think it is better to avoid this change, so when we will need to add
new callbacks, we don't need to edit this line again.
Please avoid it also in the other place in this patch.
The rest LGTM.
Thanks,
Stefano
> },
>
> .send_pkt = vhost_transport_send_pkt,
>diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
>index ebb3ce63d64d..c82089dee0c8 100644
>--- a/include/linux/virtio_vsock.h
>+++ b/include/linux/virtio_vsock.h
>@@ -256,4 +256,5 @@ void virtio_transport_put_credit(struct
>virtio_vsock_sock *vvs, u32 credit);
> void virtio_transport_deliver_tap_pkt(struct sk_buff *skb);
> int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list);
> int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t read_actor);
>+int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val);
> #endif /* _LINUX_VIRTIO_VSOCK_H */
>diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
>index af5bab1acee1..8b7bb7ca8ea5 100644
>--- a/net/vmw_vsock/virtio_transport.c
>+++ b/net/vmw_vsock/virtio_transport.c
>@@ -537,8 +537,9 @@ static struct virtio_transport virtio_transport = {
> .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue,
> .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
> .notify_buffer_size = virtio_transport_notify_buffer_size,
>+ .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat,
>
>- .read_skb = virtio_transport_read_skb,
>+ .read_skb = virtio_transport_read_skb
> },
>
> .send_pkt = virtio_transport_send_pkt,
>diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
>index f6dc896bf44c..1cb556ad4597 100644
>--- a/net/vmw_vsock/virtio_transport_common.c
>+++ b/net/vmw_vsock/virtio_transport_common.c
>@@ -1684,6 +1684,33 @@ int virtio_transport_read_skb(struct vsock_sock
>*vsk, skb_read_actor_t recv_acto
> }
> EXPORT_SYMBOL_GPL(virtio_transport_read_skb);
>
>+int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
>+{
>+ struct virtio_vsock_sock *vvs = vsk->trans;
>+ bool send_update;
>+
>+ spin_lock_bh(&vvs->rx_lock);
>+
>+ /* If number of available bytes is less than new SO_RCVLOWAT value,
>+ * kick sender to send more data, because sender may sleep in its
>+ * 'send()' syscall waiting for enough space at our side.
>+ */
>+ send_update = vvs->rx_bytes < val;
>+
>+ spin_unlock_bh(&vvs->rx_lock);
>+
>+ if (send_update) {
>+ int err;
>+
>+ err = virtio_transport_send_credit_update(vsk);
>+ if (err < 0)
>+ return err;
>+ }
>+
>+ return 0;
>+}
>+EXPORT_SYMBOL_GPL(virtio_transport_notify_set_rcvlowat);
>+
> MODULE_LICENSE("GPL v2");
> MODULE_AUTHOR("Asias He");
> MODULE_DESCRIPTION("common code for virtio vsock");
>diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
>index 048640167411..454f69838c2a 100644
>--- a/net/vmw_vsock/vsock_loopback.c
>+++ b/net/vmw_vsock/vsock_loopback.c
>@@ -96,8 +96,9 @@ static struct virtio_transport loopback_transport = {
> .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue,
> .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
> .notify_buffer_size = virtio_transport_notify_buffer_size,
>+ .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat,
>
>- .read_skb = virtio_transport_read_skb,
>+ .read_skb = virtio_transport_read_skb
> },
>
> .send_pkt = vsock_loopback_send_pkt,
>--
>2.25.1
>
On Thu, Nov 30, 2023 at 12:25:19AM +0300, Arseniy Krasnov wrote:
>Test which checks, that updating SO_RCVLOWAT value also sends credit
>update message. Otherwise mutual hungup may happen when receiver didn't
>send credit update and then calls 'poll()' with non default SO_RCVLOWAT
>value (e.g. waiting enough bytes to read), while sender waits for free
>space at receiver's side. Important thing is that this test relies on
>kernel's define for maximum packet size for virtio transport and this
>value is not exported to user: VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (this
>define is used to control moment when to send credit update message).
>If this value or its usage will be changed in kernel - this test may
>become useless/broken.
>
>Signed-off-by: Arseniy Krasnov <[email protected]>
>---
> Changelog:
> v1 -> v2:
> * Update commit message by removing 'This patch adds XXX' manner.
> * Update commit message by adding details about dependency for this
> test from kernel internal define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE.
> * Add comment for this dependency in 'vsock_test.c' where this define
> is duplicated.
> v2 -> v3:
> * Replace synchronization based on control TCP socket with vsock
> data socket - this is needed to allow sender transmit data only
> when new buffer size of receiver is visible to sender. Otherwise
> there is race and test fails sometimes.
> v3 -> v4:
> * Replace 'recv_buf()' to 'recv(MSG_DONTWAIT)' in last read operation
> in server part. This is needed to ensure that 'poll()' wake up us
> when number of bytes ready to read is equal to SO_RCVLOWAT value.
>
> tools/testing/vsock/vsock_test.c | 149 +++++++++++++++++++++++++++++++
> 1 file changed, 149 insertions(+)
>
>diff --git a/tools/testing/vsock/vsock_test.c b/tools/testing/vsock/vsock_test.c
>index 01fa816868bc..68f7037834db 100644
>--- a/tools/testing/vsock/vsock_test.c
>+++ b/tools/testing/vsock/vsock_test.c
>@@ -1232,6 +1232,150 @@ static void test_double_bind_connect_client(const struct test_opts *opts)
> }
> }
>
>+#define RCVLOWAT_CREDIT_UPD_BUF_SIZE (1024 * 128)
>+/* This define is the same as in 'include/linux/virtio_vsock.h':
>+ * it is used to decide when to send credit update message during
>+ * reading from rx queue of a socket. Value and its usage in
>+ * kernel is important for this test.
>+ */
>+#define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE (1024 * 64)
>+
>+static void test_stream_rcvlowat_def_cred_upd_client(const struct test_opts *opts)
>+{
>+ size_t buf_size;
>+ void *buf;
>+ int fd;
>+
>+ fd = vsock_stream_connect(opts->peer_cid, 1234);
>+ if (fd < 0) {
>+ perror("connect");
>+ exit(EXIT_FAILURE);
>+ }
>+
>+ /* Send 1 byte more than peer's buffer size. */
>+ buf_size = RCVLOWAT_CREDIT_UPD_BUF_SIZE + 1;
>+
>+ buf = malloc(buf_size);
>+ if (!buf) {
>+ perror("malloc");
>+ exit(EXIT_FAILURE);
>+ }
>+
>+ /* Wait until peer sets needed buffer size. */
>+ recv_byte(fd, 1, 0);
>+
>+ if (send(fd, buf, buf_size, 0) != buf_size) {
>+ perror("send failed");
>+ exit(EXIT_FAILURE);
>+ }
>+
>+ free(buf);
>+ close(fd);
>+}
>+
>+static void test_stream_rcvlowat_def_cred_upd_server(const struct test_opts *opts)
>+{
>+ size_t recv_buf_size;
>+ struct pollfd fds;
>+ size_t buf_size;
>+ void *buf;
>+ int fd;
>+
>+ fd = vsock_stream_accept(VMADDR_CID_ANY, 1234, NULL);
>+ if (fd < 0) {
>+ perror("accept");
>+ exit(EXIT_FAILURE);
>+ }
>+
>+ buf_size = RCVLOWAT_CREDIT_UPD_BUF_SIZE;
>+
>+ if (setsockopt(fd, AF_VSOCK, SO_VM_SOCKETS_BUFFER_SIZE,
>+ &buf_size, sizeof(buf_size))) {
>+ perror("setsockopt(SO_VM_SOCKETS_BUFFER_SIZE)");
>+ exit(EXIT_FAILURE);
>+ }
>+
>+ /* Send one dummy byte here, because 'setsockopt()' above also
>+ * sends special packet which tells sender to update our buffer
>+ * size. This 'send_byte()' will serialize such packet with data
>+ * reads in a loop below. Sender starts transmission only when
>+ * it receives this single byte.
>+ */
>+ send_byte(fd, 1, 0);
>+
>+ buf = malloc(buf_size);
>+ if (!buf) {
>+ perror("malloc");
>+ exit(EXIT_FAILURE);
>+ }
>+
>+ /* Wait until there will be 128KB of data in rx queue. */
>+ while (1) {
>+ ssize_t res;
>+
>+ res = recv(fd, buf, buf_size, MSG_PEEK);
>+ if (res == buf_size)
>+ break;
>+
>+ if (res <= 0) {
>+ fprintf(stderr, "unexpected 'recv()' return: %zi\n", res);
>+ exit(EXIT_FAILURE);
>+ }
>+ }
>+
>+ /* There is 128KB of data in the socket's rx queue,
>+ * dequeue first 64KB, credit update is not sent.
>+ */
>+ recv_buf_size = VIRTIO_VSOCK_MAX_PKT_BUF_SIZE;
>+ recv_buf(fd, buf, recv_buf_size, 0, recv_buf_size);
>+ recv_buf_size++;
>+
>+ /* Updating SO_RCVLOWAT will send credit update. */
>+ if (setsockopt(fd, SOL_SOCKET, SO_RCVLOWAT,
>+ &recv_buf_size, sizeof(recv_buf_size))) {
>+ perror("setsockopt(SO_RCVLOWAT)");
>+ exit(EXIT_FAILURE);
>+ }
>+
>+ memset(&fds, 0, sizeof(fds));
>+ fds.fd = fd;
>+ fds.events = POLLIN | POLLRDNORM | POLLERR |
>+ POLLRDHUP | POLLHUP;
>+
>+ /* This 'poll()' will return once we receive last byte
>+ * sent by client.
>+ */
>+ if (poll(&fds, 1, -1) < 0) {
>+ perror("poll");
>+ exit(EXIT_FAILURE);
>+ }
>+
>+ if (fds.revents & POLLERR) {
>+ fprintf(stderr, "'poll()' error\n");
>+ exit(EXIT_FAILURE);
>+ }
>+
>+ if (fds.revents & (POLLIN | POLLRDNORM)) {
>+ ssize_t res;
>+
>+ res = recv(fd, buf, recv_buf_size, MSG_DONTWAIT);
>+ if (res != recv_buf_size) {
>+ fprintf(stderr, "recv(2), expected %zu, got %zu\n",
>+ recv_buf_size, res);
>+ exit(EXIT_FAILURE);
>+ }
Why not just passing MSG_DONTWAIT to recv_buf()?
Thanks,
Stefano
>+ } else {
>+ /* These flags must be set, as there is at
>+ * least 64KB of data ready to read.
>+ */
>+ fprintf(stderr, "POLLIN | POLLRDNORM expected\n");
>+ exit(EXIT_FAILURE);
>+ }
>+
>+ free(buf);
>+ close(fd);
>+}
>+
> static struct test_case test_cases[] = {
> {
> .name = "SOCK_STREAM connection reset",
>@@ -1342,6 +1486,11 @@ static struct test_case test_cases[] = {
> .run_client = test_double_bind_connect_client,
> .run_server = test_double_bind_connect_server,
> },
>+ {
>+ .name = "SOCK_STREAM virtio SO_RCVLOWAT + deferred cred update",
>+ .run_client = test_stream_rcvlowat_def_cred_upd_client,
>+ .run_server = test_stream_rcvlowat_def_cred_upd_server,
>+ },
> {},
> };
>
>--
>2.25.1
>
On 30.11.2023 11:38, Stefano Garzarella wrote:
> On Thu, Nov 30, 2023 at 12:25:18AM +0300, Arseniy Krasnov wrote:
>> Send credit update message when SO_RCVLOWAT is updated and it is bigger
>> than number of bytes in rx queue. It is needed, because 'poll()' will
>> wait until number of bytes in rx queue will be not smaller than
>> SO_RCVLOWAT, so kick sender to send more data. Otherwise mutual hungup
>> for tx/rx is possible: sender waits for free space and receiver is
>> waiting data in 'poll()'.
>>
>> Signed-off-by: Arseniy Krasnov <[email protected]>
>> ---
>> Changelog:
>> v1 -> v2:
>> * Update commit message by removing 'This patch adds XXX' manner.
>> * Do not initialize 'send_update' variable - set it directly during
>> first usage.
>> v3 -> v4:
>> * Fit comment in 'virtio_transport_notify_set_rcvlowat()' to 80 chars.
>>
>> drivers/vhost/vsock.c | 3 ++-
>> include/linux/virtio_vsock.h | 1 +
>> net/vmw_vsock/virtio_transport.c | 3 ++-
>> net/vmw_vsock/virtio_transport_common.c | 27 +++++++++++++++++++++++++
>> net/vmw_vsock/vsock_loopback.c | 3 ++-
>> 5 files changed, 34 insertions(+), 3 deletions(-)
>>
>> diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
>> index f75731396b7e..c5e58a60a546 100644
>> --- a/drivers/vhost/vsock.c
>> +++ b/drivers/vhost/vsock.c
>> @@ -449,8 +449,9 @@ static struct virtio_transport vhost_transport = {
>> .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue,
>> .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
>> .notify_buffer_size = virtio_transport_notify_buffer_size,
>> + .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat,
>>
>> - .read_skb = virtio_transport_read_skb,
>> + .read_skb = virtio_transport_read_skb
>
> I think it is better to avoid this change, so when we will need to add
> new callbacks, we don't need to edit this line again.
>
> Please avoid it also in the other place in this patch.
>
> The rest LGTM.
Yes, I see, I thought about that, but chose beauty instead of pragmatism :)
Ok, I'll fix it:)
Thanks, Arseniy
>
> Thanks,
> Stefano
>
>> },
>>
>> .send_pkt = vhost_transport_send_pkt,
>> diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
>> index ebb3ce63d64d..c82089dee0c8 100644
>> --- a/include/linux/virtio_vsock.h
>> +++ b/include/linux/virtio_vsock.h
>> @@ -256,4 +256,5 @@ void virtio_transport_put_credit(struct virtio_vsock_sock *vvs, u32 credit);
>> void virtio_transport_deliver_tap_pkt(struct sk_buff *skb);
>> int virtio_transport_purge_skbs(void *vsk, struct sk_buff_head *list);
>> int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t read_actor);
>> +int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val);
>> #endif /* _LINUX_VIRTIO_VSOCK_H */
>> diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
>> index af5bab1acee1..8b7bb7ca8ea5 100644
>> --- a/net/vmw_vsock/virtio_transport.c
>> +++ b/net/vmw_vsock/virtio_transport.c
>> @@ -537,8 +537,9 @@ static struct virtio_transport virtio_transport = {
>> .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue,
>> .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
>> .notify_buffer_size = virtio_transport_notify_buffer_size,
>> + .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat,
>>
>> - .read_skb = virtio_transport_read_skb,
>> + .read_skb = virtio_transport_read_skb
>> },
>>
>> .send_pkt = virtio_transport_send_pkt,
>> diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
>> index f6dc896bf44c..1cb556ad4597 100644
>> --- a/net/vmw_vsock/virtio_transport_common.c
>> +++ b/net/vmw_vsock/virtio_transport_common.c
>> @@ -1684,6 +1684,33 @@ int virtio_transport_read_skb(struct vsock_sock *vsk, skb_read_actor_t recv_acto
>> }
>> EXPORT_SYMBOL_GPL(virtio_transport_read_skb);
>>
>> +int virtio_transport_notify_set_rcvlowat(struct vsock_sock *vsk, int val)
>> +{
>> + struct virtio_vsock_sock *vvs = vsk->trans;
>> + bool send_update;
>> +
>> + spin_lock_bh(&vvs->rx_lock);
>> +
>> + /* If number of available bytes is less than new SO_RCVLOWAT value,
>> + * kick sender to send more data, because sender may sleep in its
>> + * 'send()' syscall waiting for enough space at our side.
>> + */
>> + send_update = vvs->rx_bytes < val;
>> +
>> + spin_unlock_bh(&vvs->rx_lock);
>> +
>> + if (send_update) {
>> + int err;
>> +
>> + err = virtio_transport_send_credit_update(vsk);
>> + if (err < 0)
>> + return err;
>> + }
>> +
>> + return 0;
>> +}
>> +EXPORT_SYMBOL_GPL(virtio_transport_notify_set_rcvlowat);
>> +
>> MODULE_LICENSE("GPL v2");
>> MODULE_AUTHOR("Asias He");
>> MODULE_DESCRIPTION("common code for virtio vsock");
>> diff --git a/net/vmw_vsock/vsock_loopback.c b/net/vmw_vsock/vsock_loopback.c
>> index 048640167411..454f69838c2a 100644
>> --- a/net/vmw_vsock/vsock_loopback.c
>> +++ b/net/vmw_vsock/vsock_loopback.c
>> @@ -96,8 +96,9 @@ static struct virtio_transport loopback_transport = {
>> .notify_send_pre_enqueue = virtio_transport_notify_send_pre_enqueue,
>> .notify_send_post_enqueue = virtio_transport_notify_send_post_enqueue,
>> .notify_buffer_size = virtio_transport_notify_buffer_size,
>> + .notify_set_rcvlowat = virtio_transport_notify_set_rcvlowat,
>>
>> - .read_skb = virtio_transport_read_skb,
>> + .read_skb = virtio_transport_read_skb
>> },
>>
>> .send_pkt = vsock_loopback_send_pkt,
>> --
>> 2.25.1
>>
>