From: Michael Kelley <mhkelley@outlook.com>
To: "gregkh@linuxfoundation.org" <gregkh@linuxfoundation.org>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"devel@linuxdriverproject.org" <devel@linuxdriverproject.org>,
"olaf@aepfle.de" <olaf@aepfle.de>,
"apw@canonical.com" <apw@canonical.com>,
"vkuznets@redhat.com" <vkuznets@redhat.com>,
"jasowang@redhat.com" <jasowang@redhat.com>,
"leann.ogasawara@canonical.com" <leann.ogasawara@canonical.com>,
"marcelo.cerri@canonical.com" <marcelo.cerri@canonical.com>,
"sthemmin@microsoft.com" <sthemmin@microsoft.com>,
"kys@microsoft.com" <kys@microsoft.com>
Cc: "mikelley@microsoft.com" <mikelley@microsoft.com>
Subject: [PATCH v2 char-misc 1/1] Drivers: hv: vmbus: Fix ring buffer signaling
Date: Fri, 16 Feb 2018 23:05:33 +0000 [thread overview]
Message-ID: <SN6PR1901MB20450EF7C8CC4112381274B9CBCB0@SN6PR1901MB2045.namprd19.prod.outlook.com> (raw)
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 <mhkelley@outlook.com>
---
Changes in v2:
* Restructured to do signaling calcuations only if needed. Makes
the most common path faster [KY Srinivasan, Steve Hemminger]
* Moved bytes read calculation to new routine hv_pkt_iter_bytes_read
[Steve Hemminger]
---
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 50e0714..8699bb9 100644
--- a/drivers/hv/ring_buffer.c
+++ b/drivers/hv/ring_buffer.c
@@ -417,13 +417,24 @@ struct vmpacket_descriptor *
}
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
@@ -431,8 +442,12 @@ 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:
@@ -446,26 +461,29 @@ 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);
}
--
1.8.3.1
_______________________________________________
devel mailing list
devel@linuxdriverproject.org
http://driverdev.linuxdriverproject.org/mailman/listinfo/driverdev-devel
next reply other threads:[~2018-02-16 23:05 UTC|newest]
Thread overview: 2+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-02-16 23:05 Michael Kelley [this message]
2018-02-27 0:10 ` [PATCH v2 char-misc 1/1] Drivers: hv: vmbus: Fix ring buffer signaling Stephen Hemminger
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=SN6PR1901MB20450EF7C8CC4112381274B9CBCB0@SN6PR1901MB2045.namprd19.prod.outlook.com \
--to=mhkelley@outlook.com \
--cc=apw@canonical.com \
--cc=devel@linuxdriverproject.org \
--cc=gregkh@linuxfoundation.org \
--cc=jasowang@redhat.com \
--cc=kys@microsoft.com \
--cc=leann.ogasawara@canonical.com \
--cc=linux-kernel@vger.kernel.org \
--cc=marcelo.cerri@canonical.com \
--cc=mikelley@microsoft.com \
--cc=olaf@aepfle.de \
--cc=sthemmin@microsoft.com \
--cc=vkuznets@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).