Drivers: hv: vm_bus: Handle vmbus rescind calls after vmbus is suspended

Add a flag to indicate that the vmbus is suspended so we should ignore
any offer message. Add a new work_queue for rescind msg, so we could drain
it along with other offer work_queues upon suspension.
It was observed that in some hibernation related scenario testing, after
vmbus_bus_suspend() we get rescind offer message for the vmbus. This would
lead to processing of a rescind message for a channel that has already been
suspended.

Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Link: https://lore.kernel.org/r/20220711041147.GA5569@linuxonhyperv3.guj3yctzbm1etfxqx2vob5hsef.xx.internal.cloudapp.net
Signed-off-by: Wei Liu <wei.liu@kernel.org>
This commit is contained in:
Shradha Gupta 2022-07-10 21:11:47 -07:00 committed by Wei Liu
parent 32346491dd
commit 52be93558a
3 changed files with 37 additions and 8 deletions

View File

@ -171,6 +171,14 @@ int vmbus_connect(void)
goto cleanup;
}
vmbus_connection.rescind_work_queue =
create_workqueue("hv_vmbus_rescind");
if (!vmbus_connection.rescind_work_queue) {
ret = -ENOMEM;
goto cleanup;
}
vmbus_connection.ignore_any_offer_msg = false;
vmbus_connection.handle_primary_chan_wq =
create_workqueue("hv_pri_chan");
if (!vmbus_connection.handle_primary_chan_wq) {
@ -357,6 +365,9 @@ void vmbus_disconnect(void)
if (vmbus_connection.handle_primary_chan_wq)
destroy_workqueue(vmbus_connection.handle_primary_chan_wq);
if (vmbus_connection.rescind_work_queue)
destroy_workqueue(vmbus_connection.rescind_work_queue);
if (vmbus_connection.work_queue)
destroy_workqueue(vmbus_connection.work_queue);

View File

@ -261,6 +261,13 @@ struct vmbus_connection {
struct workqueue_struct *work_queue;
struct workqueue_struct *handle_primary_chan_wq;
struct workqueue_struct *handle_sub_chan_wq;
struct workqueue_struct *rescind_work_queue;
/*
* On suspension of the vmbus, the accumulated offer messages
* must be dropped.
*/
bool ignore_any_offer_msg;
/*
* The number of sub-channels and hv_sock channels that should be

View File

@ -1160,7 +1160,9 @@ void vmbus_on_msg_dpc(unsigned long data)
* work queue: the RESCIND handler can not start to
* run before the OFFER handler finishes.
*/
schedule_work(&ctx->work);
if (vmbus_connection.ignore_any_offer_msg)
break;
queue_work(vmbus_connection.rescind_work_queue, &ctx->work);
break;
case CHANNELMSG_OFFERCHANNEL:
@ -1186,6 +1188,8 @@ void vmbus_on_msg_dpc(unsigned long data)
* to the CPUs which will execute the offer & rescind
* works by the time these works will start execution.
*/
if (vmbus_connection.ignore_any_offer_msg)
break;
atomic_inc(&vmbus_connection.offer_in_progress);
fallthrough;
@ -2446,15 +2450,20 @@ acpi_walk_err:
#ifdef CONFIG_PM_SLEEP
static int vmbus_bus_suspend(struct device *dev)
{
struct hv_per_cpu_context *hv_cpu = per_cpu_ptr(
hv_context.cpu_context, VMBUS_CONNECT_CPU);
struct vmbus_channel *channel, *sc;
while (atomic_read(&vmbus_connection.offer_in_progress) != 0) {
/*
* We wait here until the completion of any channel
* offers that are currently in progress.
*/
usleep_range(1000, 2000);
}
tasklet_disable(&hv_cpu->msg_dpc);
vmbus_connection.ignore_any_offer_msg = true;
/* The tasklet_enable() takes care of providing a memory barrier */
tasklet_enable(&hv_cpu->msg_dpc);
/* Drain all the workqueues as we are in suspend */
drain_workqueue(vmbus_connection.rescind_work_queue);
drain_workqueue(vmbus_connection.work_queue);
drain_workqueue(vmbus_connection.handle_primary_chan_wq);
drain_workqueue(vmbus_connection.handle_sub_chan_wq);
mutex_lock(&vmbus_connection.channel_mutex);
list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
@ -2531,6 +2540,8 @@ static int vmbus_bus_resume(struct device *dev)
size_t msgsize;
int ret;
vmbus_connection.ignore_any_offer_msg = false;
/*
* We only use the 'vmbus_proto_version', which was in use before
* hibernation, to re-negotiate with the host.