During initialization, the channel initialization code schedules the tasklet to scan the VMBUS receive event page (i.e. simulates an interrupt). The problem was that it invokes the tasklet on a different CPU from where it normally runs and therefore if an event is present, it will clear the bit but not find the associated channel. This can lead to missed events, typically stuck tasks, during bootup when sub channels are being initialized. Typically seen as stuck boot with 8 or more CPU's. This patch is for 4.10 and 4.9; but was introduced by fix to solve a race on updates. It is not necessary for 4.11 and later since commit 631e63a9f346 ("vmbus: change to per channel tasklet"). which eliminated the common tasklet which caused the problem. Cc: stable@xxxxxxxxxxxxxxx Fixes: 638fea33aee8 ("Drivers: hv: vmbus: fix the race when querying & updating the percpu list") Signed-off-by: Stephen Hemminger <sthemmin@xxxxxxxxxxxxx> --- Patch is against linux-4.10.y branch v3 - avoid possible preempt race v2 - simplify only change hv_event_tasklet_enable drivers/hv/channel_mgmt.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c index 0af7e39006c8..74afef6271f0 100644 --- a/drivers/hv/channel_mgmt.c +++ b/drivers/hv/channel_mgmt.c @@ -361,8 +361,17 @@ void hv_event_tasklet_enable(struct vmbus_channel *channel) tasklet = hv_context.event_dpc[channel->target_cpu]; tasklet_enable(tasklet); - /* In case there is any pending event */ - tasklet_schedule(tasklet); + /* + * In case there is any pending event schedule a rescan + * but must be on the correct CPU for the channel. + */ + if (channel->target_cpu == get_cpu()) + tasklet_schedule(tasklet); + else + smp_call_function_single(channel->target_cpu, + (smp_call_func_t)tasklet_schedule, + tasklet, false); + put_cpu(); } void hv_process_channel_removal(struct vmbus_channel *channel, u32 relid) -- 2.11.0