What about the following simplification. If on older hosts you can avoid more 
code
and the additional barrier. Also cleanup comment wording somewhat.



From de2d566d9092cbbc8e5974dea581617ef787ff69 Mon Sep 17 00:00:00 2001
From: Michael Kelley <mhkel...@outlook.com>
Date: Sat, 10 Feb 2018 20:48:49 +0000
Subject: [PATCH 1/9] Drivers: hv: vmbus: Fix ring buffer signaling

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")
Signed-off-by: Michael Kelley <mhkel...@outlook.com>
---
 drivers/hv/ring_buffer.c | 67 +++++++++++++++++++++++++++++-------------------
 1 file changed, 40 insertions(+), 27 deletions(-)

diff --git a/drivers/hv/ring_buffer.c b/drivers/hv/ring_buffer.c
index 50e071444a5c..d27cbb66279c 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -417,13 +417,25 @@ __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)
+{
+       if (rbi->ring_buffer->read_index < rbi->priv_read_index)
+               return rbi->priv_read_index - rbi->ring_buffer->read_index;
+       else
+               return rbi->ring_datasize -
+                       rbi->ring_buffer->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;
+       u32 delta = hv_pkt_iter_bytes_read(rbi);
+       u32 pending_sz;
 
        /*
         * Make sure all reads are done before we update the read index since
@@ -433,39 +445,40 @@ void hv_pkt_iter_close(struct vmbus_channel *channel)
        virt_rmb();
        rbi->ring_buffer->read_index = rbi->priv_read_index;
 
+       /* Older versions do not require signalling */
+       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:
-        * If the reading of the pend_sz (in this function)
-        * were to be reordered and read before we commit the new read
-        * index (in the calling function)  we could
-        * have a problem. If the host were to set the pending_sz after we
-        * have sampled pending_sz and go to sleep before we commit the
-        * read index, we could miss sending the interrupt. Issue a full
-        * memory barrier to address this.
+        * If the reading of the pend_sz were to be reordered and read
+        * before we commit the new read index then we would have a
+        * problem. If the host were to set the pending_sz after we
+        * have sampled pending_sz and go to sleep before we commit
+        * the read index, we could miss sending the interrupt.
         */
        virt_mb();
 
-       /* If host has disabled notifications then skip */
-       if (rbi->ring_buffer->interrupt_mask)
-               return;
+       pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz);
 
-       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);
 
-               /*
-                * 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. Also handles case where
+        * pending_sz is zero then host has nothing pending and does
+        * not need to be  signaled.
+        */
+       if (curr_write_sz - delta > pending_sz)
+               return;
 
-               /* If pending write will not fit, don't give false hope. */
-               if (hv_get_bytes_to_write(rbi) < 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

Reply via email to