Drivers: hv: utils: run polling callback always in interrupt context

All channel interrupts are bound to specific VCPUs in the guest
at the point channel is created. While currently, we invoke the
polling function on the correct CPU (the CPU to which the channel
is bound to) in some cases we may run the polling function in
a non-interrupt context. This  potentially can cause an issue as the
polling function can be interrupted by the channel callback function.
Fix the issue by running the polling function on the appropriate CPU
at interrupt level. Additional details of the issue being addressed by
this patch are given below:

Currently hv_fcopy_onchannelcallback is called from interrupts and also
via the ->write function of hv_utils. Since the used global variables to
maintain state are not thread safe the state can get out of sync.
This affects the variable state as well as the channel inbound buffer.

As suggested by KY adjust hv_poll_channel to always run the given
callback on the cpu which the channel is bound to. This avoids the need
for locking because all the util services are single threaded and only
one transaction is active at any given point in time.

Additionally, remove the context variable, they will always be the same as
recv_channel.

Signed-off-by: Olaf Hering <olaf@aepfle.de>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

1 files changed, 11 insertions, 18 deletions

diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index 815405f2e777..a548ae42c927 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -53,7 +53,6 @@ static struct {
 	struct vmbus_channel *recv_channel; /* chn we got the request */
 	u64 recv_req_id; /* request ID. */
 	struct hv_vss_msg  *msg; /* current message */
-	void *vss_context; /* for the channel callback */
 } vss_transaction;
 
 
@@ -74,6 +73,13 @@ static void vss_timeout_func(struct work_struct *dummy);
 static DECLARE_DELAYED_WORK(vss_timeout_work, vss_timeout_func);
 static DECLARE_WORK(vss_send_op_work, vss_send_op);
 
+static void vss_poll_wrapper(void *channel)
+{
+	/* Transaction is finished, reset the state here to avoid races. */
+	vss_transaction.state = HVUTIL_READY;
+	hv_vss_onchannelcallback(channel);
+}
+
 /*
  * Callback when data is received from user mode.
  */
@@ -86,12 +92,7 @@ static void vss_timeout_func(struct work_struct *dummy)
 	pr_warn("VSS: timeout waiting for daemon to reply\n");
 	vss_respond_to_host(HV_E_FAIL);
 
-	/* Transaction is finished, reset the state. */
-	if (vss_transaction.state > HVUTIL_READY)
-		vss_transaction.state = HVUTIL_READY;
-
-	hv_poll_channel(vss_transaction.vss_context,
-			hv_vss_onchannelcallback);
+	hv_poll_channel(vss_transaction.recv_channel, vss_poll_wrapper);
 }
 
 static int vss_handle_handshake(struct hv_vss_msg *vss_msg)
@@ -138,9 +139,8 @@ static int vss_on_msg(void *msg, int len)
 		if (cancel_delayed_work_sync(&vss_timeout_work)) {
 			vss_respond_to_host(vss_msg->error);
 			/* Transaction is finished, reset the state. */
-			vss_transaction.state = HVUTIL_READY;
-			hv_poll_channel(vss_transaction.vss_context,
-					hv_vss_onchannelcallback);
+			hv_poll_channel(vss_transaction.recv_channel,
+					vss_poll_wrapper);
 		}
 	} else {
 		/* This is a spurious call! */
@@ -238,15 +238,8 @@ void hv_vss_onchannelcallback(void *context)
 	struct icmsg_hdr *icmsghdrp;
 	struct icmsg_negotiate *negop = NULL;
 
-	if (vss_transaction.state > HVUTIL_READY) {
-		/*
-		 * We will defer processing this callback once
-		 * the current transaction is complete.
-		 */
-		vss_transaction.vss_context = context;
+	if (vss_transaction.state > HVUTIL_READY)
 		return;
-	}
-	vss_transaction.vss_context = NULL;
 
 	vmbus_recvpacket(channel, recv_buffer, PAGE_SIZE * 2, &recvlen,
 			 &requestid);