ltykernel@xxxxxxxxx writes:
> From: Tianyu Lan <Tianyu.Lan@xxxxxxxxxxxxx>
>
> Customer reported Hyper-V VM still responded network traffic
> ack packets after kernel panic with kernel parameter "panic=0”.
> This becauses vmbus driver interrupt handler still works
> on the panic cpu after kernel panic. Panic cpu falls into
> infinite loop of panic() with interrupt enabled at that point.
> Vmbus driver can still handle network traffic.
>
> This confuses remote service that the panic system is still
> alive when it gets ack packets. Unload vmbus channel in hv panic
> callback and fix it.
>
> vmbus_initiate_unload() maybe double called during panic process
> (e.g, hyperv_panic_event() and hv_crash_handler()). So check
> and set connection state in vmbus_initiate_unload() to resolve
> reenter issue.
>
> Signed-off-by: Tianyu Lan <Tianyu.Lan@xxxxxxxxxxxxx>
> ---
> drivers/hv/channel_mgmt.c | 5 +++++
> drivers/hv/vmbus_drv.c | 17 +++++++++--------
> 2 files changed, 14 insertions(+), 8 deletions(-)
>
> diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
> index 0370364169c4..893493f2b420 100644
> --- a/drivers/hv/channel_mgmt.c
> +++ b/drivers/hv/channel_mgmt.c
> @@ -839,6 +839,9 @@ void vmbus_initiate_unload(bool crash)
> {
> struct vmbus_channel_message_header hdr;
>
> + if (vmbus_connection.conn_state == DISCONNECTED)
> + return;
> +
To make this less racy, can we do something like
if (xchg(&vmbus_connection.conn_state, DISCONNECTED) == DISCONNECTED)
return;
?
> /* Pre-Win2012R2 hosts don't support reconnect */
> if (vmbus_proto_version < VERSION_WIN8_1)
> return;
> @@ -857,6 +860,8 @@ void vmbus_initiate_unload(bool crash)
> wait_for_completion(&vmbus_connection.unload_event);
> else
> vmbus_wait_for_unload();
> +
> + vmbus_connection.conn_state = DISCONNECTED;
> }
>
> static void check_ready_for_resume_event(void)
> diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
> index 029378c27421..b56b9fb9bd90 100644
> --- a/drivers/hv/vmbus_drv.c
> +++ b/drivers/hv/vmbus_drv.c
> @@ -53,9 +53,12 @@ static int hyperv_panic_event(struct notifier_block *nb, unsigned long val,
> {
> struct pt_regs *regs;
>
> - regs = current_pt_regs();
> + vmbus_initiate_unload(true);
>
> - hyperv_report_panic(regs, val);
> + if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
With Michael's effors to make code in drivers/hv arch agnostic, I think
we need a better, arch-neutral way.
> + regs = current_pt_regs();
> + hyperv_report_panic(regs, val);
> + }
> return NOTIFY_DONE;
> }
>
> @@ -1391,10 +1394,12 @@ static int vmbus_bus_init(void)
> }
>
> register_die_notifier(&hyperv_die_block);
> - atomic_notifier_chain_register(&panic_notifier_list,
> - &hyperv_panic_block);
> }
>
> + /* Vmbus channel is unloaded in panic callback when panic happens.*/
> + atomic_notifier_chain_register(&panic_notifier_list,
> + &hyperv_panic_block);
> +
> vmbus_request_offers();
>
> return 0;
> @@ -2204,8 +2209,6 @@ static int vmbus_bus_suspend(struct device *dev)
>
> vmbus_initiate_unload(false);
>
> - vmbus_connection.conn_state = DISCONNECTED;
> -
> /* Reset the event for the next resume. */
> reinit_completion(&vmbus_connection.ready_for_resume_event);
>
> @@ -2289,7 +2292,6 @@ static void hv_kexec_handler(void)
> {
> hv_stimer_global_cleanup();
> vmbus_initiate_unload(false);
> - vmbus_connection.conn_state = DISCONNECTED;
> /* Make sure conn_state is set as hv_synic_cleanup checks for it */
> mb();
> cpuhp_remove_state(hyperv_cpuhp_online);
> @@ -2306,7 +2308,6 @@ static void hv_crash_handler(struct pt_regs *regs)
> * doing the cleanup for current CPU only. This should be sufficient
> * for kdump.
> */
> - vmbus_connection.conn_state = DISCONNECTED;
> cpu = smp_processor_id();
> hv_stimer_cleanup(cpu);
> hv_synic_disable_regs(cpu);
--
Vitaly
