[PATCH 4.9 32/48] vmbus: fix missing signaling in hv_signal_on_read()

[Greg Kroah-Hartman]

4.9-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Dexuan Cui <decui@xxxxxxxxxxxxx>

[Fixes upstream in a much larger set of patches that are not worth backporting
to 4.9 - gregkh]

When the space available before start of reading (cached_write_sz)
is the same as the host required space (pending_sz), we need to
still signal host.

Fixes: 433e19cf33d3 ("Drivers: hv: vmbus: finally fix hv_need_to_signal_on_read()")

Signed-off-by: John Starks <jon.Starks@xxxxxxxxxxxxx>
Signed-off-by: Dexuan Cui <decui@xxxxxxxxxxxxx>
Signed-off-by: Stephen Hemminger <sthemmin@xxxxxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---

Hi Greg, as we discussed, I'm resending this patch, and please only apply
it to linux-4.9.y (i.e. v4.9.57 as of today).

 include/linux/hyperv.h |    4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1521,11 +1521,11 @@ static inline  void hv_signal_on_read(st
 
 	cur_write_sz = hv_get_bytes_to_write(rbi);
 
-	if (cur_write_sz < pending_sz)
+	if (cur_write_sz <= pending_sz)
 		return;
 
 	cached_write_sz = hv_get_cached_bytes_to_write(rbi);
-	if (cached_write_sz < pending_sz)
+	if (cached_write_sz <= pending_sz)
 		vmbus_setevent(channel);
 
 	return;