linux-rdma.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alex Chiang <achiang@hp.com>
To: rdreier@cisco.com
Cc: linux-rdma@vger.kernel.org, justin.chen@hp.com,
	linux-kernel@vger.kernel.org
Subject: [PATCH v2 05/18] IB/uverbs: increase maximum devices supported
Date: Tue, 02 Feb 2010 12:08:09 -0700	[thread overview]
Message-ID: <20100202190809.28217.50581.stgit@bob.kio> (raw)
In-Reply-To: <20100202185235.28217.64521.stgit@bob.kio>

Some large systems may support more than IB_UVERBS_MAX_DEVICES
(currently 32).

This change allows us to support more devices in a backwards-compatible
manner. The first IB_UVERBS_MAX_DEVICES keep the same major/minor
device numbers that they've always had.

If there are more than IB_UVERBS_MAX_DEVICES, we then dynamically
request a new major device number (new minors start at 0).

This change increases the maximum number of HCAs to 64 (from 32).

Signed-off-by: Alex Chiang <achiang@hp.com>
---

 drivers/infiniband/core/uverbs_main.c |   56 +++++++++++++++++++++++++++++----
 1 files changed, 50 insertions(+), 6 deletions(-)

diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 8c594cd..38b9085 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -728,6 +728,34 @@ static ssize_t show_abi_version(struct class *class, char *buf)
 }
 static CLASS_ATTR(abi_version, S_IRUGO, show_abi_version, NULL);
 
+static dev_t oflo_maj;
+static DECLARE_BITMAP(oflo_map, IB_UVERBS_MAX_DEVICES);
+
+/*
+ * If we have more than IB_UVERBS_MAX_DEVICES, dynamically overflow by
+ * requesting a new major number and doubling the number of max devices we
+ * support. It's stupid, but simple.
+ */
+static int find_oflo_devnum(void)
+{
+	int ret;
+
+	if (!oflo_maj) {
+		ret = alloc_chrdev_region(&oflo_maj, 0, IB_UVERBS_MAX_DEVICES,
+					  "infiniband_verbs");
+		if (ret) {
+			printk(KERN_ERR "user_verbs: couldn't register dynamic device number\n");
+			return ret;
+		}
+	}
+
+	ret = find_first_zero_bit(oflo_map, IB_UVERBS_MAX_DEVICES);
+	if (ret >= IB_UVERBS_MAX_DEVICES)
+		return -1;
+
+	return ret;
+}
+
 static void ib_uverbs_add_one(struct ib_device *device)
 {
 	int devnum;
@@ -748,11 +776,19 @@ static void ib_uverbs_add_one(struct ib_device *device)
 	devnum = find_first_zero_bit(dev_map, IB_UVERBS_MAX_DEVICES);
 	if (devnum >= IB_UVERBS_MAX_DEVICES) {
 		spin_unlock(&map_lock);
-		goto err;
+		devnum = find_oflo_devnum();
+		if (devnum < 0)
+			goto err;
+
+		spin_lock(&map_lock);
+		uverbs_dev->devnum = devnum + IB_UVERBS_MAX_DEVICES;
+		base = devnum + oflo_maj;
+		set_bit(devnum, oflo_map);
+	} else {
+		uverbs_dev->devnum = devnum;
+		base = devnum + IB_UVERBS_BASE_DEV;
+		set_bit(devnum, dev_map);
 	}
-	uverbs_dev->devnum = devnum;
-	base = devnum + IB_UVERBS_BASE_DEV;
-	set_bit(devnum, dev_map);
 	spin_unlock(&map_lock);
 
 	uverbs_dev->ib_dev           = device;
@@ -785,7 +821,10 @@ err_class:
 
 err_cdev:
 	cdev_del(&uverbs_dev->cdev);
-	clear_bit(devnum, dev_map);
+	if (uverbs_dev->devnum < IB_UVERBS_MAX_DEVICES)
+		clear_bit(devnum, dev_map);
+	else
+		clear_bit(devnum, oflo_map);
 
 err:
 	kref_put(&uverbs_dev->ref, ib_uverbs_release_dev);
@@ -805,7 +844,10 @@ static void ib_uverbs_remove_one(struct ib_device *device)
 	device_destroy(uverbs_class, uverbs_dev->cdev.dev);
 	cdev_del(&uverbs_dev->cdev);
 
-	clear_bit(uverbs_dev->devnum, dev_map);
+	if (uverbs_dev->devnum < IB_UVERBS_MAX_DEVICES)
+		clear_bit(uverbs_dev->devnum, dev_map);
+	else
+		clear_bit(uverbs_dev->devnum - IB_UVERBS_MAX_DEVICES, oflo_map);
 
 	kref_put(&uverbs_dev->ref, ib_uverbs_release_dev);
 	wait_for_completion(&uverbs_dev->comp);
@@ -895,6 +937,8 @@ static void __exit ib_uverbs_cleanup(void)
 	unregister_filesystem(&uverbs_event_fs);
 	class_destroy(uverbs_class);
 	unregister_chrdev_region(IB_UVERBS_BASE_DEV, IB_UVERBS_MAX_DEVICES);
+	if (oflo_maj)
+		unregister_chrdev_region(oflo_maj, IB_UVERBS_MAX_DEVICES);
 	idr_destroy(&ib_uverbs_pd_idr);
 	idr_destroy(&ib_uverbs_mr_idr);
 	idr_destroy(&ib_uverbs_mw_idr);

  parent reply	other threads:[~2010-02-02 19:08 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-02-02 19:07 [PATCH v2 00/18] Increase maximum number of Infiniband HCAs per system Alex Chiang
2010-02-02 19:07 ` [PATCH v2 01/18] IB/uverbs: convert *cdev to cdev in struct ib_uverbs_device Alex Chiang
2010-02-02 19:07 ` [PATCH v2 03/18] IB/uverbs: use stack variable 'devnum' in ib_uverbs_add_one Alex Chiang
2010-02-02 19:08 ` Alex Chiang [this message]
2010-02-02 19:08 ` [PATCH v2 08/18] IB/umad: convert cdev pointers to embedded structs in struct ib_umad_port Alex Chiang
2010-02-02 19:08 ` [PATCH v2 10/18] IB/umad: use stack variable 'devnum' in ib_umad_init_port Alex Chiang
2010-02-02 19:08 ` [PATCH v2 11/18] IB/umad: use stack variable 'base' " Alex Chiang
2010-02-02 19:08 ` [PATCH v2 12/18] IB/umad: increase maximum devices supported Alex Chiang
     [not found] ` <20100202185235.28217.64521.stgit-tBlMHHroXgg@public.gmane.org>
2010-02-02 19:07   ` [PATCH v2 02/18] IB/uverbs: remove dev_table Alex Chiang
2010-02-02 19:08   ` [PATCH v2 04/18] IB/uverbs: use stack variable 'base' in ib_uverbs_add_one Alex Chiang
2010-02-02 19:08   ` [PATCH v2 06/18] IB/uverbs: pack struct ib_uverbs_event_file tighter Alex Chiang
2010-02-02 19:08   ` [PATCH v2 07/18] IB/uverbs: whitespace cleanup Alex Chiang
2010-02-02 19:08   ` [PATCH v2 09/18] IB/umad: remove port_table[] Alex Chiang
2010-02-02 19:08   ` [PATCH v2 13/18] IB/umad: clean whitespace Alex Chiang
2010-02-02 19:08   ` [PATCH v2 14/18] IB/ucm: use stack variable 'devnum' in ib_ucm_add_one Alex Chiang
2010-02-02 19:09   ` [PATCH v2 16/18] IB/ucm: increase maximum devices supported Alex Chiang
2010-02-02 19:09   ` [PATCH v2 17/18] IB/ucm: clean whitespace errors Alex Chiang
2010-02-02 19:09   ` [PATCH v2 18/18] IB/core: pack struct ib_device a little tighter Alex Chiang
     [not found]     ` <20100202190916.28217.90954.stgit-tBlMHHroXgg@public.gmane.org>
2010-02-24 18:24       ` Roland Dreier
2010-02-02 19:09 ` [PATCH v2 15/18] IB/ucm: use stack variable 'base' in ib_ucm_add_one Alex Chiang
2010-02-08 21:30 ` [PATCH v2 00/18] Increase maximum number of Infiniband HCAs per system Alex Chiang

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=20100202190809.28217.50581.stgit@bob.kio \
    --to=achiang@hp.com \
    --cc=justin.chen@hp.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=rdreier@cisco.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).