Drivers: hv: vmbus: Raise retry/wait limits in vmbus_post_msg()
commit c0bb03924f1a80e7f65900e36c8e6b3dc167c5f8 upstream.
DoS protection conditions were altered in WS2016 and now it's easy to get
-EAGAIN returned from vmbus_post_msg() (e.g. when we try changing MTU on a
netvsc device in a loop). All vmbus_post_msg() callers don't retry the
operation and we usually end up with a non-functional device or crash.
While host's DoS protection conditions are unknown to me my tests show that
it can take up to 10 seconds before the message is sent so doing udelay()
is not an option, we really need to sleep. Almost all vmbus_post_msg()
callers are ready to sleep but there is one special case:
vmbus_initiate_unload() which can be called from interrupt/NMI context and
we can't sleep there. I'm also not sure about the lonely
vmbus_send_tl_connect_request() which has no in-tree users but its external
users are most likely waiting for the host to reply so sleeping there is
also appropriate.
Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 5fb4c6d..d5b8d9f 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -181,7 +181,7 @@
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
ret = vmbus_post_msg(open_msg,
- sizeof(struct vmbus_channel_open_channel));
+ sizeof(struct vmbus_channel_open_channel), true);
if (ret != 0) {
err = ret;
@@ -233,7 +233,7 @@
conn_msg.guest_endpoint_id = *shv_guest_servie_id;
conn_msg.host_service_id = *shv_host_servie_id;
- return vmbus_post_msg(&conn_msg, sizeof(conn_msg));
+ return vmbus_post_msg(&conn_msg, sizeof(conn_msg), true);
}
EXPORT_SYMBOL_GPL(vmbus_send_tl_connect_request);
@@ -419,7 +419,7 @@
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
ret = vmbus_post_msg(gpadlmsg, msginfo->msgsize -
- sizeof(*msginfo));
+ sizeof(*msginfo), true);
if (ret != 0)
goto cleanup;
@@ -433,8 +433,8 @@
gpadl_body->gpadl = next_gpadl_handle;
ret = vmbus_post_msg(gpadl_body,
- submsginfo->msgsize -
- sizeof(*submsginfo));
+ submsginfo->msgsize - sizeof(*submsginfo),
+ true);
if (ret != 0)
goto cleanup;
@@ -485,8 +485,8 @@
list_add_tail(&info->msglistentry,
&vmbus_connection.chn_msg_list);
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
- ret = vmbus_post_msg(msg,
- sizeof(struct vmbus_channel_gpadl_teardown));
+ ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_gpadl_teardown),
+ true);
if (ret)
goto post_msg_err;
@@ -557,7 +557,8 @@
msg->header.msgtype = CHANNELMSG_CLOSECHANNEL;
msg->child_relid = channel->offermsg.child_relid;
- ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel));
+ ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel),
+ true);
if (ret) {
pr_err("Close failed: close post msg return is %d\n", ret);
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index caf3418..f3a8b52 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -321,7 +321,8 @@
memset(&msg, 0, sizeof(struct vmbus_channel_relid_released));
msg.child_relid = relid;
msg.header.msgtype = CHANNELMSG_RELID_RELEASED;
- vmbus_post_msg(&msg, sizeof(struct vmbus_channel_relid_released));
+ vmbus_post_msg(&msg, sizeof(struct vmbus_channel_relid_released),
+ true);
}
void hv_event_tasklet_disable(struct vmbus_channel *channel)
@@ -728,7 +729,8 @@
init_completion(&vmbus_connection.unload_event);
memset(&hdr, 0, sizeof(struct vmbus_channel_message_header));
hdr.msgtype = CHANNELMSG_UNLOAD;
- vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header));
+ vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header),
+ !crash);
/*
* vmbus_initiate_unload() is also called on crash and the crash can be
@@ -1116,8 +1118,8 @@
msg->msgtype = CHANNELMSG_REQUESTOFFERS;
- ret = vmbus_post_msg(msg,
- sizeof(struct vmbus_channel_message_header));
+ ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_message_header),
+ true);
if (ret != 0) {
pr_err("Unable to request offers - %d\n", ret);
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 78e6368..840b6db 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -110,7 +110,8 @@
spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
ret = vmbus_post_msg(msg,
- sizeof(struct vmbus_channel_initiate_contact));
+ sizeof(struct vmbus_channel_initiate_contact),
+ true);
if (ret != 0) {
spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
list_del(&msginfo->msglistentry);
@@ -434,7 +435,7 @@
/*
* vmbus_post_msg - Send a msg on the vmbus's message connection
*/
-int vmbus_post_msg(void *buffer, size_t buflen)
+int vmbus_post_msg(void *buffer, size_t buflen, bool can_sleep)
{
union hv_connection_id conn_id;
int ret = 0;
@@ -449,7 +450,7 @@
* insufficient resources. Retry the operation a couple of
* times before giving up.
*/
- while (retries < 20) {
+ while (retries < 100) {
ret = hv_post_message(conn_id, 1, buffer, buflen);
switch (ret) {
@@ -472,8 +473,14 @@
}
retries++;
- udelay(usec);
- if (usec < 2048)
+ if (can_sleep && usec > 1000)
+ msleep(usec / 1000);
+ else if (usec < MAX_UDELAY_MS * 1000)
+ udelay(usec);
+ else
+ mdelay(usec / 1000);
+
+ if (usec < 256000)
usec *= 2;
}
return ret;
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 2b13f2a..8d7f865 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -683,7 +683,7 @@
int vmbus_connect(void);
void vmbus_disconnect(void);
-int vmbus_post_msg(void *buffer, size_t buflen);
+int vmbus_post_msg(void *buffer, size_t buflen, bool can_sleep);
void vmbus_on_event(unsigned long data);
void vmbus_on_msg_dpc(unsigned long data);