Drivers: hv: vmbus: Replace the per-CPU channel lists with a global array of channels

When Hyper-V sends an interrupt to the guest, the guest has to figure
out which channel the interrupt is associated with.  Hyper-V sets a bit
in a memory page that is shared with the guest, indicating a particular
"relid" that the interrupt is associated with.  The current Linux code
then uses a set of per-CPU linked lists to map a given "relid" to a
pointer to a channel structure.

This design introduces a synchronization problem if the CPU that Hyper-V
will interrupt for a certain channel is changed.  If the interrupt comes
on the "old CPU" and the channel was already moved to the per-CPU list
of the "new CPU", then the relid -> channel mapping will fail and the
interrupt is dropped.  Similarly, if the interrupt comes on the new CPU
but the channel was not moved to the per-CPU list of the new CPU, then
the mapping will fail and the interrupt is dropped.

Relids are integers ranging from 0 to 2047.  The mapping from relids to
channel structures can be done by setting up an array with 2048 entries,
each entry being a pointer to a channel structure (hence total size ~16K
bytes, which is not a problem).  The array is global, so there are no
per-CPU linked lists to update.  The array can be searched and updated
by loading from/storing to the array at the specified index.  With no
per-CPU data structures, the above mentioned synchronization problem is
avoided and the relid2channel() function gets simpler.

Suggested-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Andrea Parri (Microsoft) <parri.andrea@gmail.com>
Link: https://lore.kernel.org/r/20200406001514.19876-4-parri.andrea@gmail.com
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>

1 files changed, 29 insertions, 19 deletions

diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 1f3e69d18d35..21a01bca7fcd 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -1252,33 +1252,39 @@ static void vmbus_chan_sched(struct hv_per_cpu_context *hv_cpu)
 		if (relid == 0)
 			continue;
 
+		/*
+		 * Pairs with the kfree_rcu() in vmbus_chan_release().
+		 * Guarantees that the channel data structure doesn't
+		 * get freed while the channel pointer below is being
+		 * dereferenced.
+		 */
 		rcu_read_lock();
 
 		/* Find channel based on relid */
-		list_for_each_entry_rcu(channel, &hv_cpu->chan_list, percpu_list) {
-			if (channel->offermsg.child_relid != relid)
-				continue;
+		channel = relid2channel(relid);
+		if (channel == NULL)
+			goto sched_unlock_rcu;
 
-			if (channel->rescind)
-				continue;
+		if (channel->rescind)
+			goto sched_unlock_rcu;
 
-			trace_vmbus_chan_sched(channel);
+		trace_vmbus_chan_sched(channel);
 
-			++channel->interrupts;
+		++channel->interrupts;
 
-			switch (channel->callback_mode) {
-			case HV_CALL_ISR:
-				vmbus_channel_isr(channel);
-				break;
+		switch (channel->callback_mode) {
+		case HV_CALL_ISR:
+			vmbus_channel_isr(channel);
+			break;
 
-			case HV_CALL_BATCHED:
-				hv_begin_read(&channel->inbound);
-				/* fallthrough */
-			case HV_CALL_DIRECT:
-				tasklet_schedule(&channel->callback_event);
-			}
+		case HV_CALL_BATCHED:
+			hv_begin_read(&channel->inbound);
+			fallthrough;
+		case HV_CALL_DIRECT:
+			tasklet_schedule(&channel->callback_event);
 		}
 
+sched_unlock_rcu:
 		rcu_read_unlock();
 	}
 }
@@ -2264,9 +2270,12 @@ static int vmbus_bus_suspend(struct device *dev)
 
 	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
 		/*
-		 * Invalidate the field. Upon resume, vmbus_onoffer() will fix
-		 * up the field, and the other fields (if necessary).
+		 * Remove the channel from the array of channels and invalidate
+		 * the channel's relid.  Upon resume, vmbus_onoffer() will fix
+		 * up the relid (and other fields, if necessary) and add the
+		 * channel back to the array.
 		 */
+		vmbus_channel_unmap_relid(channel);
 		channel->offermsg.child_relid = INVALID_RELID;
 
 		if (is_hvsock_channel(channel)) {
@@ -2502,6 +2511,7 @@ static void __exit vmbus_exit(void)
 	hv_debug_rm_all_dir();
 
 	vmbus_free_channels();
+	kfree(vmbus_connection.channels);
 
 	if (ms_hyperv.misc_features & HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE) {
 		kmsg_dump_unregister(&hv_kmsg_dumper);