[PATCH 2/3] Drivers: hv: vmbus: avoid scheduling in interrupt context in vmbus_initiate_unload()

[Vitaly Kuznetsov]

We have to call vmbus_initiate_unload() on crash to make kdump work but
the crash can also be happening in interrupt (e.g. Sysrq + c results in
such) where we can't schedule or the following will happen:

[  314.905786] bad: scheduling from the idle thread!

Just skipping the wait (and even adding some random wait here) won't help:
to make host-side magic working we're supposed to receive CHANNELMSG_UNLOAD
(and actually confirm the fact that we received it) but we can't use
interrupt-base path (vmbus_isr()-> vmbus_on_msg_dpc()). Implement a simple
busy wait ignoring all the other messages and use it if we're in an
interrupt context.

Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
---
 drivers/hv/channel_mgmt.c | 44 +++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 43 insertions(+), 1 deletion(-)

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 82c6860..763d0c1 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -28,6 +28,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/completion.h>
+#include <linux/delay.h>
 #include <linux/hyperv.h>
 
 #include "hyperv_vmbus.h"
@@ -509,6 +510,40 @@ static void init_vp_index(struct vmbus_channel *channel, const uuid_le *type_gui
 	channel->target_vp = hv_context.vp_index[cur_cpu];
 }
 
+static void vmbus_wait_for_unload(void)
+{
+	int cpu = smp_processor_id();
+	void *page_addr = hv_context.synic_message_page[cpu];
+	struct hv_message *msg = (struct hv_message *)page_addr +
+				  VMBUS_MESSAGE_SINT;
+	struct vmbus_channel_message_header *hdr;
+	bool unloaded = false;
+
+	while (1) {
+		if (msg->header.message_type == HVMSG_NONE) {
+			mdelay(10);
+			continue;
+		}
+
+		hdr = (struct vmbus_channel_message_header *)msg->u.payload;
+		if (hdr->msgtype == CHANNELMSG_UNLOAD_RESPONSE)
+			unloaded = true;
+
+		msg->header.message_type = HVMSG_NONE;
+		/*
+		 * header.message_type needs to be written before we do
+		 * wrmsrl() below.
+		 */
+		mb();
+
+		if (msg->header.message_flags.msg_pending)
+			wrmsrl(HV_X64_MSR_EOM, 0);
+
+		if (unloaded)
+			break;
+	}
+}
+
 /*
  * vmbus_unload_response - Handler for the unload response.
  */
@@ -534,7 +569,14 @@ void vmbus_initiate_unload(void)
 	hdr.msgtype = CHANNELMSG_UNLOAD;
 	vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header));
 
-	wait_for_completion(&vmbus_connection.unload_event);
+	/*
+	 * vmbus_initiate_unload() is also called on crash and the crash can be
+	 * happening in an interrupt context, where scheduling is impossible.
+	 */
+	if (!in_interrupt())
+		wait_for_completion(&vmbus_connection.unload_event);
+	else
+		vmbus_wait_for_unload();
 }
 
 /*
-- 
2.5.0