[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Message-Id: <20180305052408.19475-1-kys@exchange.microsoft.com>
Date: Sun, 4 Mar 2018 22:24:08 -0700
From: kys@...hange.microsoft.com
To: gregkh@...uxfoundation.org, linux-kernel@...r.kernel.org,
devel@...uxdriverproject.org, olaf@...fle.de, apw@...onical.com,
vkuznets@...hat.com, jasowang@...hat.com,
leann.ogasawara@...onical.com, marcelo.cerri@...onical.com,
sthemmin@...rosoft.com
Cc: Michael Kelley <mhkelley@...look.com>,
Stable <stable@...r.kernel.org>,
"K . Y . Srinivasan" <kys@...rosoft.com>
Subject: [PATCH 1/1] Drivers: hv: vmbus: Fix ring buffer signaling
From: Michael Kelley <mhkelley@...look.com>
Fix bugs in signaling the Hyper-V host when freeing space in the
host->guest ring buffer:
1. The interrupt_mask must not be used to determine whether to signal
on the host->guest ring buffer
2. The ring buffer write_index must be read (via hv_get_bytes_to_write)
*after* pending_send_sz is read in order to avoid a race condition
3. Comparisons with pending_send_sz must treat the "equals" case as
not-enough-space
4. Don't signal if the pending_send_sz feature is not present. Older
versions of Hyper-V that don't implement this feature will poll.
Fixes: 03bad714a161 ("vmbus: more host signalling avoidance")
Cc: Stable <stable@...r.kernel.org> # 4.14 and above
Signed-off-by: Michael Kelley <mhkelley@...look.com>
Signed-off-by: K. Y. Srinivasan <kys@...rosoft.com>
---
drivers/hv/ring_buffer.c | 52 ++++++++++++++++++++++++++++++++----------------
1 file changed, 35 insertions(+), 17 deletions(-)
diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 1aa17795727b..3cd7f29906ae 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -376,13 +376,24 @@ __hv_pkt_iter_next(struct vmbus_channel *channel,
}
EXPORT_SYMBOL_GPL(__hv_pkt_iter_next);
+/* How many bytes were read in this iterator cycle */
+static u32 hv_pkt_iter_bytes_read(const struct hv_ring_buffer_info *rbi,
+ u32 start_read_index)
+{
+ if (rbi->priv_read_index >= start_read_index)
+ return rbi->priv_read_index - start_read_index;
+ else
+ return rbi->ring_datasize - start_read_index +
+ rbi->priv_read_index;
+}
+
/*
* Update host ring buffer after iterating over packets.
*/
void hv_pkt_iter_close(struct vmbus_channel *channel)
{
struct hv_ring_buffer_info *rbi = &channel->inbound;
- u32 orig_write_sz = hv_get_bytes_to_write(rbi);
+ u32 curr_write_sz, pending_sz, bytes_read, start_read_index;
/*
* Make sure all reads are done before we update the read index since
@@ -390,8 +401,12 @@ void hv_pkt_iter_close(struct vmbus_channel *channel)
* is updated.
*/
virt_rmb();
+ start_read_index = rbi->ring_buffer->read_index;
rbi->ring_buffer->read_index = rbi->priv_read_index;
+ if (!rbi->ring_buffer->feature_bits.feat_pending_send_sz)
+ return;
+
/*
* Issue a full memory barrier before making the signaling decision.
* Here is the reason for having this barrier:
@@ -405,26 +420,29 @@ void hv_pkt_iter_close(struct vmbus_channel *channel)
*/
virt_mb();
- /* If host has disabled notifications then skip */
- if (rbi->ring_buffer->interrupt_mask)
+ pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz);
+ if (!pending_sz)
return;
- if (rbi->ring_buffer->feature_bits.feat_pending_send_sz) {
- u32 pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz);
+ /*
+ * Ensure the read of write_index in hv_get_bytes_to_write()
+ * happens after the read of pending_send_sz.
+ */
+ virt_rmb();
+ curr_write_sz = hv_get_bytes_to_write(rbi);
+ bytes_read = hv_pkt_iter_bytes_read(rbi, start_read_index);
- /*
- * If there was space before we began iteration,
- * then host was not blocked. Also handles case where
- * pending_sz is zero then host has nothing pending
- * and does not need to be signaled.
- */
- if (orig_write_sz > pending_sz)
- return;
+ /*
+ * If there was space before we began iteration,
+ * then host was not blocked.
+ */
- /* If pending write will not fit, don't give false hope. */
- if (hv_get_bytes_to_write(rbi) < pending_sz)
- return;
- }
+ if (curr_write_sz - bytes_read > pending_sz)
+ return;
+
+ /* If pending write will not fit, don't give false hope. */
+ if (curr_write_sz <= pending_sz)
+ return;
vmbus_setevent(channel);
}
--
2.15.1
Powered by blists - more mailing lists