init_completion(&channel->rescind_event);
INIT_LIST_HEAD(&channel->sc_list);
- INIT_LIST_HEAD(&channel->percpu_list);
tasklet_init(&channel->callback_event,
vmbus_on_event, (unsigned long)channel);
kobject_put(&channel->kobj);
}
-static void percpu_channel_enq(void *arg)
+void vmbus_channel_map_relid(struct vmbus_channel *channel)
{
- struct vmbus_channel *channel = arg;
- struct hv_per_cpu_context *hv_cpu
- = this_cpu_ptr(hv_context.cpu_context);
-
- list_add_tail_rcu(&channel->percpu_list, &hv_cpu->chan_list);
+ if (WARN_ON(channel->offermsg.child_relid >= MAX_CHANNEL_RELIDS))
+ return;
+ /*
+ * The mapping of the channel's relid is visible from the CPUs that
+ * execute vmbus_chan_sched() by the time that vmbus_chan_sched() will
+ * execute:
+ *
+ * (a) In the "normal (i.e., not resuming from hibernation)" path,
+ * the full barrier in smp_store_mb() guarantees that the store
+ * is propagated to all CPUs before the add_channel_work work
+ * is queued. In turn, add_channel_work is queued before the
+ * channel's ring buffer is allocated/initialized and the
+ * OPENCHANNEL message for the channel is sent in vmbus_open().
+ * Hyper-V won't start sending the interrupts for the channel
+ * before the OPENCHANNEL message is acked. The memory barrier
+ * in vmbus_chan_sched() -> sync_test_and_clear_bit() ensures
+ * that vmbus_chan_sched() must find the channel's relid in
+ * recv_int_page before retrieving the channel pointer from the
+ * array of channels.
+ *
+ * (b) In the "resuming from hibernation" path, the smp_store_mb()
+ * guarantees that the store is propagated to all CPUs before
+ * the VMBus connection is marked as ready for the resume event
+ * (cf. check_ready_for_resume_event()). The interrupt handler
+ * of the VMBus driver and vmbus_chan_sched() can not run before
+ * vmbus_bus_resume() has completed execution (cf. resume_noirq).
+ */
+ smp_store_mb(
+ vmbus_connection.channels[channel->offermsg.child_relid],
+ channel);
}
-static void percpu_channel_deq(void *arg)
+void vmbus_channel_unmap_relid(struct vmbus_channel *channel)
{
- struct vmbus_channel *channel = arg;
-
- list_del_rcu(&channel->percpu_list);
+ if (WARN_ON(channel->offermsg.child_relid >= MAX_CHANNEL_RELIDS))
+ return;
+ WRITE_ONCE(
+ vmbus_connection.channels[channel->offermsg.child_relid],
+ NULL);
}
-
static void vmbus_release_relid(u32 relid)
{
struct vmbus_channel_relid_released msg;
struct vmbus_channel *primary_channel;
unsigned long flags;
- BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex));
+ lockdep_assert_held(&vmbus_connection.channel_mutex);
BUG_ON(!channel->rescind);
- if (channel->target_cpu != get_cpu()) {
- put_cpu();
- smp_call_function_single(channel->target_cpu,
- percpu_channel_deq, channel, true);
- } else {
- percpu_channel_deq(channel);
- put_cpu();
- }
+ /*
+ * hv_process_channel_removal() could find INVALID_RELID only for
+ * hv_sock channels. See the inline comments in vmbus_onoffer().
+ */
+ WARN_ON(channel->offermsg.child_relid == INVALID_RELID &&
+ !is_hvsock_channel(channel));
+
+ /*
+ * Upon suspend, an in-use hv_sock channel is removed from the array of
+ * channels and the relid is invalidated. After hibernation, when the
+ * user-space appplication destroys the channel, it's unnecessary and
+ * unsafe to remove the channel from the array of channels. See also
+ * the inline comments before the call of vmbus_release_relid() below.
+ */
+ if (channel->offermsg.child_relid != INVALID_RELID)
+ vmbus_channel_unmap_relid(channel);
if (channel->primary_channel == NULL) {
list_del(&channel->listentry);
init_vp_index(newchannel, dev_type);
- if (newchannel->target_cpu != get_cpu()) {
- put_cpu();
- smp_call_function_single(newchannel->target_cpu,
- percpu_channel_enq,
- newchannel, true);
- } else {
- percpu_channel_enq(newchannel);
- put_cpu();
- }
-
/*
* This state is used to indicate a successful open
* so that when we do close the channel normally, we
spin_unlock_irqrestore(&primary_channel->lock, flags);
}
- mutex_unlock(&vmbus_connection.channel_mutex);
+ /* vmbus_process_offer() has mapped the channel. */
+ vmbus_channel_unmap_relid(newchannel);
- if (newchannel->target_cpu != get_cpu()) {
- put_cpu();
- smp_call_function_single(newchannel->target_cpu,
- percpu_channel_deq,
- newchannel, true);
- } else {
- percpu_channel_deq(newchannel);
- put_cpu();
- }
+ mutex_unlock(&vmbus_connection.channel_mutex);
vmbus_release_relid(newchannel->offermsg.child_relid);
spin_unlock_irqrestore(&channel->lock, flags);
}
+ vmbus_channel_map_relid(newchannel);
+
mutex_unlock(&vmbus_connection.channel_mutex);
/*
oldchannel = find_primary_channel_by_offer(offer);
if (oldchannel != NULL) {
- atomic_dec(&vmbus_connection.offer_in_progress);
-
/*
* We're resuming from hibernation: all the sub-channel and
* hv_sock channels we had before the hibernation should have
* primary channel that we had before the hibernation.
*/
+ /*
+ * { Initially: channel relid = INVALID_RELID,
+ * channels[valid_relid] = NULL }
+ *
+ * CPU1 CPU2
+ *
+ * [vmbus_onoffer()] [vmbus_device_release()]
+ *
+ * LOCK channel_mutex LOCK channel_mutex
+ * STORE channel relid = valid_relid LOAD r1 = channel relid
+ * MAP_RELID channel if (r1 != INVALID_RELID)
+ * UNLOCK channel_mutex UNMAP_RELID channel
+ * UNLOCK channel_mutex
+ *
+ * Forbids: r1 == valid_relid &&
+ * channels[valid_relid] == channel
+ *
+ * Note. r1 can be INVALID_RELID only for an hv_sock channel.
+ * None of the hv_sock channels which were present before the
+ * suspend are re-offered upon the resume. See the WARN_ON()
+ * in hv_process_channel_removal().
+ */
+ mutex_lock(&vmbus_connection.channel_mutex);
+
+ atomic_dec(&vmbus_connection.offer_in_progress);
+
WARN_ON(oldchannel->offermsg.child_relid != INVALID_RELID);
/* Fix up the relid. */
oldchannel->offermsg.child_relid = offer->child_relid;
offer_sz = sizeof(*offer);
- if (memcmp(offer, &oldchannel->offermsg, offer_sz) == 0) {
- check_ready_for_resume_event();
- return;
+ if (memcmp(offer, &oldchannel->offermsg, offer_sz) != 0) {
+ /*
+ * This is not an error, since the host can also change
+ * the other field(s) of the offer, e.g. on WS RS5
+ * (Build 17763), the offer->connection_id of the
+ * Mellanox VF vmbus device can change when the host
+ * reoffers the device upon resume.
+ */
+ pr_debug("vmbus offer changed: relid=%d\n",
+ offer->child_relid);
+
+ print_hex_dump_debug("Old vmbus offer: ",
+ DUMP_PREFIX_OFFSET, 16, 4,
+ &oldchannel->offermsg, offer_sz,
+ false);
+ print_hex_dump_debug("New vmbus offer: ",
+ DUMP_PREFIX_OFFSET, 16, 4,
+ offer, offer_sz, false);
+
+ /* Fix up the old channel. */
+ vmbus_setup_channel_state(oldchannel, offer);
}
- /*
- * This is not an error, since the host can also change the
- * other field(s) of the offer, e.g. on WS RS5 (Build 17763),
- * the offer->connection_id of the Mellanox VF vmbus device
- * can change when the host reoffers the device upon resume.
- */
- pr_debug("vmbus offer changed: relid=%d\n",
- offer->child_relid);
-
- print_hex_dump_debug("Old vmbus offer: ", DUMP_PREFIX_OFFSET,
- 16, 4, &oldchannel->offermsg, offer_sz,
- false);
- print_hex_dump_debug("New vmbus offer: ", DUMP_PREFIX_OFFSET,
- 16, 4, offer, offer_sz, false);
-
- /* Fix up the old channel. */
- vmbus_setup_channel_state(oldchannel, offer);
-
+ /* Add the channel back to the array of channels. */
+ vmbus_channel_map_relid(oldchannel);
check_ready_for_resume_event();
+ mutex_unlock(&vmbus_connection.channel_mutex);
return;
}
*
* CPU1 CPU2
*
- * [vmbus_process_offer()] [vmbus_onoffer_rescind()]
+ * [vmbus_onoffer()] [vmbus_onoffer_rescind()]
*
* LOCK channel_mutex WAIT_ON offer_in_progress == 0
* DECREMENT offer_in_progress LOCK channel_mutex
- * INSERT chn_list SEARCH chn_list
+ * STORE channels[] LOAD channels[]
* UNLOCK channel_mutex UNLOCK channel_mutex
*
- * Forbids: CPU2's SEARCH from *not* seeing CPU1's INSERT
+ * Forbids: CPU2's LOAD from *not* seeing CPU1's STORE
*/
while (atomic_read(&vmbus_connection.offer_in_progress) != 0) {
projects / linux-2.6-block.git / commitdiff