From: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
To: qemu-devel@nongnu.org
Cc: Kevin Wolf <kwolf@redhat.com>,
Anthony Liguori <aliguori@us.ibm.com>,
Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>,
kvm@vger.kernel.org, "Michael S. Tsirkin" <mst@redhat.com>,
Khoa Huynh <khoa@us.ibm.com>, Paolo Bonzini <pbonzini@redhat.com>,
Asias He <asias@redhat.com>
Subject: [Qemu-devel] [RFC v9 19/27] virtio-blk: Disable guest->host notifies while processing vring
Date: Wed, 18 Jul 2012 16:07:46 +0100 [thread overview]
Message-ID: <1342624074-24650-20-git-send-email-stefanha@linux.vnet.ibm.com> (raw)
In-Reply-To: <1342624074-24650-1-git-send-email-stefanha@linux.vnet.ibm.com>
---
hw/dataplane/vring.h | 28 +++++++++++++++++++++++-----
hw/virtio-blk.c | 47 +++++++++++++++++++++++++++++++++++------------
2 files changed, 58 insertions(+), 17 deletions(-)
diff --git a/hw/dataplane/vring.h b/hw/dataplane/vring.h
index 44ef4a9..cdd4d4a 100644
--- a/hw/dataplane/vring.h
+++ b/hw/dataplane/vring.h
@@ -69,11 +69,29 @@ static void vring_setup(Vring *vring, VirtIODevice *vdev, int n)
vring->vr.desc, vring->vr.avail, vring->vr.used);
}
+/* Are there more descriptors available? */
static bool vring_more_avail(Vring *vring)
{
return vring->vr.avail->idx != vring->last_avail_idx;
}
+/* Hint to disable guest->host notifies */
+static void vring_disable_cb(Vring *vring)
+{
+ vring->vr.used->flags |= VRING_USED_F_NO_NOTIFY;
+}
+
+/* Re-enable guest->host notifies
+ *
+ * Returns false if there are more descriptors in the ring.
+ */
+static bool vring_enable_cb(Vring *vring)
+{
+ vring->vr.used->flags &= ~VRING_USED_F_NO_NOTIFY;
+ __sync_synchronize(); /* mb() */
+ return !vring_more_avail(vring);
+}
+
/* This is stolen from linux-2.6/drivers/vhost/vhost.c. */
static bool get_indirect(Vring *vring,
struct iovec iov[], struct iovec *iov_end,
@@ -160,7 +178,7 @@ static bool get_indirect(Vring *vring,
*
* Stolen from linux-2.6/drivers/vhost/vhost.c.
*/
-static unsigned int vring_pop(Vring *vring,
+static int vring_pop(Vring *vring,
struct iovec iov[], struct iovec *iov_end,
unsigned int *out_num, unsigned int *in_num)
{
@@ -178,9 +196,9 @@ static unsigned int vring_pop(Vring *vring,
exit(1);
}
- /* If there's nothing new since last we looked, return invalid. */
+ /* If there's nothing new since last we looked. */
if (avail_idx == last_avail_idx)
- return num;
+ return -EAGAIN;
/* Only get avail ring entries after they have been exposed by guest. */
__sync_synchronize(); /* smp_rmb() */
@@ -215,7 +233,7 @@ static unsigned int vring_pop(Vring *vring,
desc = vring->vr.desc[i];
if (desc.flags & VRING_DESC_F_INDIRECT) {
if (!get_indirect(vring, iov, iov_end, out_num, in_num, &desc)) {
- return num; /* not enough iovecs, stop for now */
+ return -ENOBUFS; /* not enough iovecs, stop for now */
}
continue;
}
@@ -225,7 +243,7 @@ static unsigned int vring_pop(Vring *vring,
* with the current set.
*/
if (iov >= iov_end) {
- return num;
+ return -ENOBUFS;
}
iov->iov_base = phys_to_host(vring, desc.addr);
diff --git a/hw/virtio-blk.c b/hw/virtio-blk.c
index efeffa0..f67fdb7 100644
--- a/hw/virtio-blk.c
+++ b/hw/virtio-blk.c
@@ -202,7 +202,8 @@ static bool handle_notify(EventHandler *handler)
* accept more I/O. This is not implemented yet.
*/
struct iovec iovec[VRING_MAX];
- struct iovec *iov, *end = &iovec[VRING_MAX];
+ struct iovec *end = &iovec[VRING_MAX];
+ struct iovec *iov = iovec;
/* When a request is read from the vring, the index of the first descriptor
* (aka head) is returned so that the completed request can be pushed onto
@@ -211,19 +212,41 @@ static bool handle_notify(EventHandler *handler)
* The number of hypervisor read-only iovecs is out_num. The number of
* hypervisor write-only iovecs is in_num.
*/
- unsigned int head, out_num = 0, in_num = 0;
+ int head;
+ unsigned int out_num = 0, in_num = 0;
- for (iov = iovec; ; iov += out_num + in_num) {
- head = vring_pop(&s->vring, iov, end, &out_num, &in_num);
- if (head >= vring_get_num(&s->vring)) {
- break; /* no more requests */
- }
+ for (;;) {
+ /* Disable guest->host notifies to avoid unnecessary vmexits */
+ vring_disable_cb(&s->vring);
+
+ for (;;) {
+ head = vring_pop(&s->vring, iov, end, &out_num, &in_num);
+ if (head < 0) {
+ break; /* no more requests */
+ }
- /*
- fprintf(stderr, "out_num=%u in_num=%u head=%u\n", out_num, in_num, head);
- */
+ /*
+ fprintf(stderr, "out_num=%u in_num=%u head=%d\n", out_num, in_num, head);
+ */
- process_request(&s->ioqueue, iov, out_num, in_num, head);
+ process_request(&s->ioqueue, iov, out_num, in_num, head);
+ iov += out_num + in_num;
+ }
+
+ if (likely(head == -EAGAIN)) { /* vring emptied */
+ /* Re-enable guest->host notifies and stop processing the vring.
+ * But if the guest has snuck in more descriptors, keep processing.
+ */
+ if (likely(vring_enable_cb(&s->vring))) {
+ break;
+ }
+ } else { /* head == -ENOBUFS, cannot continue since iovecs[] is depleted */
+ /* Since there are no iovecs[] left, stop processing for now. Do
+ * not re-enable guest->host notifies since the I/O completion
+ * handler knows to check for more vring descriptors anyway.
+ */
+ break;
+ }
}
/* Submit requests, if any */
@@ -247,7 +270,7 @@ static bool handle_io(EventHandler *handler)
* so check again. There should now be enough resources to process more
* requests.
*/
- if (vring_more_avail(&s->vring)) {
+ if (unlikely(vring_more_avail(&s->vring))) {
return handle_notify(&s->notify_handler);
}
--
1.7.10.4
next prev parent reply other threads:[~2012-07-18 15:08 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-07-18 15:07 [Qemu-devel] [RFC v9 00/27] virtio: virtio-blk data plane Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 01/27] virtio-blk: Remove virtqueue request handling code Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 02/27] virtio-blk: Set up host notifier for data plane Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 03/27] virtio-blk: Data plane thread event loop Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 04/27] virtio-blk: Map vring Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 05/27] virtio-blk: Do cheapest possible memory mapping Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 06/27] virtio-blk: Take PCI memory range into account Stefan Hajnoczi
2012-07-18 18:29 ` Michael S. Tsirkin
2012-07-19 9:14 ` Stefan Hajnoczi
2012-07-19 9:16 ` Stefan Hajnoczi
2012-07-19 9:29 ` Avi Kivity
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 07/27] virtio-blk: Put dataplane code into its own directory Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 08/27] virtio-blk: Read requests from the vring Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 09/27] virtio-blk: Add Linux AIO queue Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 10/27] virtio-blk: Stop data plane thread cleanly Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 11/27] virtio-blk: Indirect vring and flush support Stefan Hajnoczi
2012-07-18 18:28 ` Michael S. Tsirkin
2012-07-18 19:02 ` Michael S. Tsirkin
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 12/27] virtio-blk: Add workaround for BUG_ON() dependency in virtio_ring.h Stefan Hajnoczi
2012-07-18 19:03 ` Michael S. Tsirkin
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 13/27] virtio-blk: Increase max requests for indirect vring Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 14/27] virtio-blk: Use pthreads instead of qemu-thread Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 15/27] notifier: Add a function to set the notifier Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 16/27] virtio-blk: Kick data plane thread using event notifier set Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 17/27] virtio-blk: Use guest notifier to raise interrupts Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 18/27] virtio-blk: Call ioctl() directly instead of irqfd Stefan Hajnoczi
2012-07-18 15:40 ` Michael S. Tsirkin
2012-07-19 9:11 ` Stefan Hajnoczi
2012-07-19 9:19 ` Michael S. Tsirkin
2012-07-18 15:07 ` Stefan Hajnoczi [this message]
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 20/27] virtio-blk: Add ioscheduler to detect mergable requests Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 21/27] virtio-blk: Add basic request merging Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 22/27] virtio-blk: Fix " Stefan Hajnoczi
2012-07-18 19:04 ` Michael S. Tsirkin
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 23/27] virtio-blk: Stub out SCSI commands Stefan Hajnoczi
2012-07-18 19:05 ` Michael S. Tsirkin
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 24/27] virtio-blk: fix incorrect length Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 25/27] msix: fix irqchip breakage in msix_try_notify_from_thread() Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 26/27] msix: use upstream kvm_irqchip_set_irq() Stefan Hajnoczi
2012-07-18 15:07 ` [Qemu-devel] [RFC v9 27/27] virtio-blk: add EVENT_IDX support to dataplane Stefan Hajnoczi
2012-07-18 15:43 ` [Qemu-devel] [RFC v9 00/27] virtio: virtio-blk data plane Michael S. Tsirkin
2012-07-18 16:18 ` Khoa Huynh
2012-07-18 16:41 ` Khoa Huynh
2012-07-18 15:49 ` Michael S. Tsirkin
2012-07-19 9:48 ` Stefan Hajnoczi
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=1342624074-24650-20-git-send-email-stefanha@linux.vnet.ibm.com \
--to=stefanha@linux.vnet.ibm.com \
--cc=aliguori@us.ibm.com \
--cc=asias@redhat.com \
--cc=khoa@us.ibm.com \
--cc=kvm@vger.kernel.org \
--cc=kwolf@redhat.com \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
/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).