Drivers: hv: vmbus: finally fix hv_need_to_signal_on_read()
Commit a389fcfd2cb5 ("Drivers: hv: vmbus: Fix signaling logic in
hv_need_to_signal_on_read()")
added the proper mb(), but removed the test "prev_write_sz < pending_sz"
when making the signal decision.
As a result, the guest can signal the host unnecessarily,
and then the host can throttle the guest because the host
thinks the guest is buggy or malicious; finally the user
running stress test can perceive intermittent freeze of
the guest.
This patch brings back the test, and properly handles the
in-place consumption APIs used by NetVSC (see get_next_pkt_raw(),
put_pkt_raw() and commit_rd_index()).
Fixes: a389fcfd2cb5 ("Drivers: hv: vmbus: Fix signaling logic in
hv_need_to_signal_on_read()")
Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reported-by: Rolf Neugebauer <rolf.neugebauer@docker.com>
Tested-by: Rolf Neugebauer <rolf.neugebauer@docker.com>
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: K. Y. Srinivasan <kys@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index 42fe43f..183efde 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -128,6 +128,7 @@
u32 ring_data_startoffset;
u32 priv_write_index;
u32 priv_read_index;
+ u32 cached_read_index;
};
/*
@@ -180,6 +181,19 @@
return write;
}
+static inline u32 hv_get_cached_bytes_to_write(
+ const struct hv_ring_buffer_info *rbi)
+{
+ u32 read_loc, write_loc, dsize, write;
+
+ dsize = rbi->ring_datasize;
+ read_loc = rbi->cached_read_index;
+ write_loc = rbi->ring_buffer->write_index;
+
+ write = write_loc >= read_loc ? dsize - (write_loc - read_loc) :
+ read_loc - write_loc;
+ return write;
+}
/*
* VMBUS version is 32 bit entity broken up into
* two 16 bit quantities: major_number. minor_number.
@@ -1488,7 +1502,7 @@
static inline void hv_signal_on_read(struct vmbus_channel *channel)
{
- u32 cur_write_sz;
+ u32 cur_write_sz, cached_write_sz;
u32 pending_sz;
struct hv_ring_buffer_info *rbi = &channel->inbound;
@@ -1512,12 +1526,24 @@
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)
vmbus_setevent(channel);
return;
}
+static inline void
+init_cached_read_index(struct vmbus_channel *channel)
+{
+ struct hv_ring_buffer_info *rbi = &channel->inbound;
+
+ rbi->cached_read_index = rbi->ring_buffer->read_index;
+}
+
/*
* An API to support in-place processing of incoming VMBUS packets.
*/
@@ -1569,6 +1595,8 @@
* This call commits the read index and potentially signals the host.
* Here is the pattern for using the "in-place" consumption APIs:
*
+ * init_cached_read_index();
+ *
* while (get_next_pkt_raw() {
* process the packet "in-place";
* put_pkt_raw();