From: Dexuan Cui <decui@microsoft.com>
Date: Wed, 14 Jan 2015 09:55:10 +0000 (-0800)
Subject: hv: hv_fcopy: drop the obsolete message on transfer failure
X-Git-Tag: v4.0-rc1~84^2~33
X-Git-Url: https://git.kernel.dk/?a=commitdiff_plain;h=d9b1652947c695d247b5e4603a16213ec55661ed;p=linux-2.6-block.git

hv: hv_fcopy: drop the obsolete message on transfer failure

In the case the user-space daemon crashes, hangs or is killed, we
need to down the semaphore, otherwise, after the daemon starts next
time, the obsolete data in fcopy_transaction.message or
fcopy_transaction.fcopy_msg will be used immediately.

Cc: Jason Wang <jasowang@redhat.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---

diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index 23b2ce294c4c..cd453e4b2a07 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -86,6 +86,18 @@ static void fcopy_work_func(struct work_struct *dummy)
 	 * process the pending transaction.
 	 */
 	fcopy_respond_to_host(HV_E_FAIL);
+
+	/* In the case the user-space daemon crashes, hangs or is killed, we
+	 * need to down the semaphore, otherwise, after the daemon starts next
+	 * time, the obsolete data in fcopy_transaction.message or
+	 * fcopy_transaction.fcopy_msg will be used immediately.
+	 *
+	 * NOTE: fcopy_read() happens to get the semaphore (very rare)? We're
+	 * still OK, because we've reported the failure to the host.
+	 */
+	if (down_trylock(&fcopy_transaction.read_sema))
+		;
+
 }
 
 static int fcopy_handle_handshake(u32 version)
@@ -344,6 +356,14 @@ static int fcopy_open(struct inode *inode, struct file *f)
 	return 0;
 }
 
+/* XXX: there are still some tricky corner cases, e.g.,
+ * 1) In a SMP guest, when fcopy_release() runs between
+ * schedule_delayed_work() and fcopy_send_data(), there is
+ * still a chance an obsolete message will be queued.
+ *
+ * 2) When the fcopy daemon is running, if we unload the driver,
+ * we'll notice a kernel oops when we kill the daemon later.
+ */
 static int fcopy_release(struct inode *inode, struct file *f)
 {
 	/*
@@ -351,6 +371,13 @@ static int fcopy_release(struct inode *inode, struct file *f)
 	 */
 	in_hand_shake = true;
 	opened = false;
+
+	if (cancel_delayed_work_sync(&fcopy_work)) {
+		/* We haven't up()-ed the semaphore(very rare)? */
+		if (down_trylock(&fcopy_transaction.read_sema))
+			;
+		fcopy_respond_to_host(HV_E_FAIL);
+	}
 	return 0;
 }