From: Bob Liu <bob.liu@oracle.com>
To: xen-devel@lists.xen.org
Cc: david.vrabel@citrix.com, linux-kernel@vger.kernel.org,
roger.pau@citrix.com, konrad.wilk@oracle.com,
felipe.franciosi@citrix.com, axboe@fb.com, hch@infradead.org,
avanzini.arianna@gmail.com, rafal.mielniczuk@citrix.com,
boris.ostrovsky@oracle.com, jonathan.davies@citrix.com,
Bob Liu <bob.liu@oracle.com>
Subject: [PATCH v3 6/9] xen/blkfront: negotiate the number of hw queues/rings with backend
Date: Sat, 5 Sep 2015 20:39:39 +0800 [thread overview]
Message-ID: <1441456782-31318-7-git-send-email-bob.liu@oracle.com> (raw)
In-Reply-To: <1441456782-31318-1-git-send-email-bob.liu@oracle.com>
The max number of hardware queues for xen/blkfront is set by parameter
'max_queues', while the number xen/blkback supported is notified through
xenstore("multi-queue-max-queues").
The negotiated number was the smaller one, and was written back to
xen/blkback as "multi-queue-num-queues".
Signed-off-by: Bob Liu <bob.liu@oracle.com>
---
drivers/block/xen-blkfront.c | 142 ++++++++++++++++++++++++++++++++----------
1 file changed, 108 insertions(+), 34 deletions(-)
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index 1cae76b..1aa66c9 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -107,6 +107,10 @@ static unsigned int xen_blkif_max_ring_order;
module_param_named(max_ring_page_order, xen_blkif_max_ring_order, int, S_IRUGO);
MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the shared ring");
+static unsigned int xen_blkif_max_queues;
+module_param_named(max_queues, xen_blkif_max_queues, uint, S_IRUGO);
+MODULE_PARM_DESC(max_queues, "Maximum number of hardware queues/rings per virtual disk");
+
#define BLK_RING_SIZE(dinfo) __CONST_RING_SIZE(blkif, PAGE_SIZE * (dinfo)->pages_per_ring)
#define BLK_MAX_RING_SIZE __CONST_RING_SIZE(blkif, PAGE_SIZE * XENBUS_MAX_RING_PAGES)
/*
@@ -114,6 +118,7 @@ MODULE_PARM_DESC(max_ring_page_order, "Maximum order of pages to be used for the
* characters are enough. Define to 20 to keep consist with backend.
*/
#define RINGREF_NAME_LEN (20)
+#define QUEUE_NAME_LEN (12)
/*
* Per-ring info.
@@ -687,7 +692,7 @@ static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size,
memset(&dinfo->tag_set, 0, sizeof(dinfo->tag_set));
dinfo->tag_set.ops = &blkfront_mq_ops;
- dinfo->tag_set.nr_hw_queues = 1;
+ dinfo->tag_set.nr_hw_queues = dinfo->nr_rings;
dinfo->tag_set.queue_depth = BLK_RING_SIZE(dinfo);
dinfo->tag_set.numa_node = NUMA_NO_NODE;
dinfo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
@@ -1350,6 +1355,51 @@ fail:
return err;
}
+static int write_per_ring_nodes(struct xenbus_transaction xbt,
+ struct blkfront_ring_info *rinfo, const char *dir)
+{
+ int err, i;
+ const char *message = NULL;
+ struct blkfront_dev_info *dinfo = rinfo->dinfo;
+
+ if (dinfo->pages_per_ring == 1) {
+ err = xenbus_printf(xbt, dir, "ring-ref", "%u", rinfo->ring_ref[0]);
+ if (err) {
+ message = "writing ring-ref";
+ goto abort_transaction;
+ }
+ pr_info("%s: write ring-ref:%d\n", dir, rinfo->ring_ref[0]);
+ } else {
+ for (i = 0; i < dinfo->pages_per_ring; i++) {
+ char ring_ref_name[RINGREF_NAME_LEN];
+
+ snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", i);
+ err = xenbus_printf(xbt, dir, ring_ref_name,
+ "%u", rinfo->ring_ref[i]);
+ if (err) {
+ message = "writing ring-ref";
+ goto abort_transaction;
+ }
+ pr_info("%s: write ring-ref:%d\n", dir, rinfo->ring_ref[i]);
+ }
+ }
+
+ err = xenbus_printf(xbt, dir, "event-channel", "%u", rinfo->evtchn);
+ if (err) {
+ message = "writing event-channel";
+ goto abort_transaction;
+ }
+ pr_info("%s: write event-channel:%d\n", dir, rinfo->evtchn);
+
+ return 0;
+
+abort_transaction:
+ xenbus_transaction_end(xbt, 1);
+ if (message)
+ xenbus_dev_fatal(dinfo->xbdev, err, "%s", message);
+
+ return err;
+}
/* Common code used when first setting up, and when resuming. */
static int talk_to_blkback(struct xenbus_device *dev,
@@ -1386,45 +1436,51 @@ again:
goto out;
}
+ if (dinfo->pages_per_ring > 1) {
+ err = xenbus_printf(xbt, dev->nodename, "ring-page-order", "%u",
+ ring_page_order);
+ if (err) {
+ message = "writing ring-page-order";
+ goto abort_transaction;
+ }
+ }
+
+ /* We already got the number of queues in _probe */
if (dinfo->nr_rings == 1) {
rinfo = &dinfo->rinfo[0];
- if (dinfo->pages_per_ring == 1) {
- err = xenbus_printf(xbt, dev->nodename,
- "ring-ref", "%u", rinfo->ring_ref[0]);
- if (err) {
- message = "writing ring-ref";
- goto abort_transaction;
- }
- } else {
- err = xenbus_printf(xbt, dev->nodename,
- "ring-page-order", "%u", ring_page_order);
- if (err) {
- message = "writing ring-page-order";
- goto abort_transaction;
- }
-
- for (i = 0; i < dinfo->pages_per_ring; i++) {
- char ring_ref_name[RINGREF_NAME_LEN];
+ err = write_per_ring_nodes(xbt, &dinfo->rinfo[0], dev->nodename);
+ if (err)
+ goto out;
+ } else {
+ char *path;
+ size_t pathsize;
- snprintf(ring_ref_name, RINGREF_NAME_LEN, "ring-ref%u", i);
- err = xenbus_printf(xbt, dev->nodename, ring_ref_name,
- "%u", rinfo->ring_ref[i]);
- if (err) {
- message = "writing ring-ref";
- goto abort_transaction;
- }
- }
- }
- err = xenbus_printf(xbt, dev->nodename,
- "event-channel", "%u", rinfo->evtchn);
+ err = xenbus_printf(xbt, dev->nodename, "multi-queue-num-queues", "%u",
+ dinfo->nr_rings);
if (err) {
- message = "writing event-channel";
+ message = "writing multi-queue-num-queues";
goto abort_transaction;
}
- } else {
- /* Not supported at this stage */
- goto abort_transaction;
+
+ pathsize = strlen(dev->nodename) + QUEUE_NAME_LEN;
+ path = kzalloc(pathsize, GFP_KERNEL);
+ if (!path) {
+ err = -ENOMEM;
+ message = "ENOMEM while writing ring references";
+ goto abort_transaction;
+ }
+
+ for (i = 0; i < dinfo->nr_rings; i++) {
+ memset(path, 0, pathsize);
+ snprintf(path, pathsize, "%s/queue-%u", dev->nodename, i);
+ err = write_per_ring_nodes(xbt, &dinfo->rinfo[i], path);
+ if (err) {
+ kfree(path);
+ goto out;
+ }
+ }
+ kfree(path);
}
err = xenbus_printf(xbt, dev->nodename, "protocol", "%s",
@@ -1480,6 +1536,7 @@ static int blkfront_probe(struct xenbus_device *dev,
int err, vdevice, r_index;
struct blkfront_dev_info *dinfo;
struct blkfront_ring_info *rinfo;
+ unsigned int back_max_queues = 0;
/* FIXME: Use dynamic device id if this is not set. */
err = xenbus_scanf(XBT_NIL, dev->nodename,
@@ -1534,7 +1591,17 @@ static int blkfront_probe(struct xenbus_device *dev,
dinfo->vdevice = vdevice;
dinfo->connected = BLKIF_STATE_DISCONNECTED;
- dinfo->nr_rings = 1;
+ /* Check if backend supports multiple queues */
+ err = xenbus_scanf(XBT_NIL, dinfo->xbdev->otherend,
+ "multi-queue-max-queues", "%u", &back_max_queues);
+ if (err < 0)
+ back_max_queues = 1;
+
+ dinfo->nr_rings = min(back_max_queues, xen_blkif_max_queues);
+ if (dinfo->nr_rings <= 0)
+ dinfo->nr_rings = 1;
+ pr_info("dinfo->nr_rings:%u, backend support max-queues:%u\n", dinfo->nr_rings, back_max_queues);
+
dinfo->rinfo = kzalloc(sizeof(*rinfo) * dinfo->nr_rings, GFP_KERNEL);
if (!dinfo->rinfo) {
xenbus_dev_fatal(dev, -ENOMEM, "allocating ring_info structure");
@@ -2257,6 +2324,7 @@ static struct xenbus_driver blkfront_driver = {
static int __init xlblk_init(void)
{
int ret;
+ int nr_cpus = num_online_cpus();
if (!xen_domain())
return -ENODEV;
@@ -2267,6 +2335,12 @@ static int __init xlblk_init(void)
xen_blkif_max_ring_order = 0;
}
+ if (xen_blkif_max_queues > nr_cpus) {
+ pr_info("Invalid max_queues (%d), will use default max: %d.\n",
+ xen_blkif_max_queues, nr_cpus);
+ xen_blkif_max_queues = nr_cpus;
+ }
+
if (!xen_has_pv_disk_devices())
return -ENODEV;
--
1.7.10.4
next prev parent reply other threads:[~2015-09-05 12:41 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2015-09-05 12:39 [PATCH v3 0/9] xen-block: support multi hardware-queues/rings Bob Liu
2015-09-05 12:39 ` [PATCH v3 1/9] xen-blkfront: convert to blk-mq APIs Bob Liu
2015-09-23 20:31 ` Konrad Rzeszutek Wilk
2015-09-23 21:12 ` Konrad Rzeszutek Wilk
2015-09-05 12:39 ` [PATCH v3 2/9] xen-block: add document for mutli hardware queues/rings Bob Liu
2015-09-23 20:32 ` Konrad Rzeszutek Wilk
2015-10-02 16:04 ` Roger Pau Monné
2015-10-02 16:12 ` [Xen-devel] " Wei Liu
2015-10-02 16:22 ` Roger Pau Monné
2015-10-02 23:55 ` Bob Liu
2015-09-05 12:39 ` [PATCH v3 3/9] xen/blkfront: separate per ring information out of device info Bob Liu
2015-10-02 17:02 ` Roger Pau Monné
2015-10-03 0:34 ` Bob Liu
2015-10-05 15:17 ` Roger Pau Monné
2015-10-10 8:30 ` Bob Liu
2015-10-19 9:42 ` Roger Pau Monné
2015-09-05 12:39 ` [PATCH v3 4/9] xen/blkfront: pseudo support for multi hardware queues/rings Bob Liu
2015-10-05 10:52 ` Roger Pau Monné
2015-10-07 10:28 ` Bob Liu
2015-09-05 12:39 ` [PATCH v3 5/9] xen/blkfront: convert per device io_lock to per ring ring_lock Bob Liu
2015-10-05 14:13 ` Roger Pau Monné
2015-10-07 10:34 ` Bob Liu
2015-09-05 12:39 ` Bob Liu [this message]
2015-10-05 14:40 ` [PATCH v3 6/9] xen/blkfront: negotiate the number of hw queues/rings with backend Roger Pau Monné
2015-10-07 10:39 ` Bob Liu
2015-10-07 11:46 ` Roger Pau Monné
2015-10-07 12:19 ` Bob Liu
2015-09-05 12:39 ` [PATCH v3 7/9] xen/blkback: separate ring information out of struct xen_blkif Bob Liu
2015-10-05 14:55 ` Roger Pau Monné
2015-10-07 10:41 ` Bob Liu
2015-10-10 4:08 ` Bob Liu
2015-10-19 9:36 ` Roger Pau Monné
2015-10-19 10:03 ` Bob Liu
2015-10-05 14:55 ` Roger Pau Monné
2015-09-05 12:39 ` [PATCH v3 8/9] xen/blkback: pseudo support for multi hardware queues/rings Bob Liu
2015-10-05 15:08 ` Roger Pau Monné
2015-10-07 10:50 ` Bob Liu
2015-10-07 11:49 ` Roger Pau Monné
2015-09-05 12:39 ` [PATCH v3 9/9] xen/blkback: get number of hardware queues/rings from blkfront Bob Liu
2015-10-05 15:15 ` Roger Pau Monné
2015-10-07 10:54 ` Bob Liu
2015-10-02 9:57 ` [PATCH v3 0/9] xen-block: support multi hardware-queues/rings Rafal Mielniczuk
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=1441456782-31318-7-git-send-email-bob.liu@oracle.com \
--to=bob.liu@oracle.com \
--cc=avanzini.arianna@gmail.com \
--cc=axboe@fb.com \
--cc=boris.ostrovsky@oracle.com \
--cc=david.vrabel@citrix.com \
--cc=felipe.franciosi@citrix.com \
--cc=hch@infradead.org \
--cc=jonathan.davies@citrix.com \
--cc=konrad.wilk@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=rafal.mielniczuk@citrix.com \
--cc=roger.pau@citrix.com \
--cc=xen-devel@lists.xen.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).