All of lore.kernel.org
 help / color / mirror / Atom feed
From: Hannes Reinecke <hare@suse.de>
To: Linux Kernel <linux-kernel@vger.kernel.org>
Subject: [PATCH] Disable partition scan
Date: Wed, 27 Aug 2008 12:31:39 +0200	[thread overview]
Message-ID: <48B52D0B.2090104@suse.de> (raw)

[-- Attachment #1: Type: text/plain, Size: 957 bytes --]

Hi all,

for some setups (eg dmraid or multipathing) the in-kernel partition scan
is pointless; the (block) partitions won't be used anywhere. Instead the
system will be using kpartx-generated device-mapper devices.
Worse, on some setups (RAID0 dmraid or active/passive multipath devices)
the in-kernel partition scan will generate plenty of I/O errors as the
partitions table might not be accessible or invalid for this device.

This patch implements a new kernel command-line option 'no_partition_scan'
which will switch off the partition scan globally. The partition scan can
be re-enabled for individual devices by echoing any positive number smaller
than the number of minors into
/sys/class/block/XXX/range

and rescanning the device.

Please apply.

Cheers,

Hannes
-- 
Dr. Hannes Reinecke		      zSeries & Storage
hare@suse.de			      +49 911 74053 688
SUSE LINUX Products GmbH, Maxfeldstr. 5, 90409 Nürnberg
GF: Markus Rex, HRB 16746 (AG Nürnberg)

[-- Attachment #2: no-partition-scan --]
[-- Type: text/plain, Size: 5561 bytes --]

Disable partition scan

For some setups (multipath or dmraid) the in-kernel partition scan
is pointless as the (block) partitions won't be used anywhere.
Worse, it might trigger I/O errors as the partition table might not
be accessible (eg for the passive path of a multipath device) or
even invalid (eg for RAID0 dmraid).
This patch allows to switch off the in-kernel partition scan by adding
'no_partition_scan' to the kernel commandline. Partitions scan can be
allowed for individual disk by echoing a positive number into
/sys/block/XXX/range and rescan the disk.

Signed-off-by: Hannes Reinecke <hare@suse.de>

diff --git a/block/genhd.c b/block/genhd.c
index 656c2c7..3d6a53b 100644
--- a/block/genhd.c
+++ b/block/genhd.c
@@ -173,6 +173,18 @@ static int exact_lock(dev_t devt, void *data)
 	return 0;
 }
 
+static int __read_mostly no_partition_scan;
+
+static int __init no_partition_scan_setup(char *str)
+{
+	no_partition_scan = 1;
+	printk(KERN_INFO "genhd: omit partition scan.\n");
+
+	return 1;
+}
+
+__setup("no_partition_scan", no_partition_scan_setup);
+
 /**
  * add_disk - add partitioning information to kernel list
  * @disk: per-device partitioning information
@@ -186,6 +198,8 @@ void add_disk(struct gendisk *disk)
 	int retval;
 
 	disk->flags |= GENHD_FL_UP;
+	if (no_partition_scan)
+		disk->flags |= GENHD_FL_NO_PARTITION_SCAN;
 	blk_register_region(MKDEV(disk->major, disk->first_minor),
 			    disk->minors, NULL, exact_match, exact_lock, disk);
 	register_disk(disk);
@@ -419,7 +433,27 @@ static ssize_t disk_range_show(struct device *dev,
 {
 	struct gendisk *disk = dev_to_disk(dev);
 
-	return sprintf(buf, "%d\n", disk->minors);
+	return sprintf(buf, "%d\n",
+		       (disk->flags & GENHD_FL_NO_PARTITION_SCAN ? 0 : disk->minors));
+}
+
+static ssize_t disk_range_store(struct device *dev,
+				struct device_attribute *attr,
+				const char *buf, size_t count)
+{
+	struct gendisk *disk = dev_to_disk(dev);
+	int i;
+
+	if (count > 0 && sscanf(buf, "%d", &i) > 0) {
+		if (i == 0)
+			disk->flags |= GENHD_FL_NO_PARTITION_SCAN;
+		else if (i <= disk->minors)
+			disk->flags &= ~GENHD_FL_NO_PARTITION_SCAN;
+		else
+			count = -EINVAL;
+	}
+
+	return count;
 }
 
 static ssize_t disk_removable_show(struct device *dev,
@@ -509,7 +543,7 @@ static ssize_t disk_fail_store(struct device *dev,
 
 #endif
 
-static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
+static DEVICE_ATTR(range, S_IRUGO|S_IWUSR, disk_range_show, disk_range_store);
 static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
 static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
 static DEVICE_ATTR(size, S_IRUGO, disk_size_show, NULL);
diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c
diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c
index 4225109..dfcdef1 100644
--- a/drivers/block/virtio_blk.c
+++ b/drivers/block/virtio_blk.c
@@ -72,7 +72,7 @@ static void blk_done(struct virtqueue *vq)
 static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 		   struct request *req)
 {
-	unsigned long num, out, in;
+	unsigned long num, out = 1, in = 1;
 	struct virtblk_req *vbr;
 
 	vbr = mempool_alloc(vblk->pool, GFP_ATOMIC);
@@ -100,19 +100,26 @@ static bool do_req(struct request_queue *q, struct virtio_blk *vblk,
 	/* This init could be done at vblk creation time */
 	sg_init_table(vblk->sg, VIRTIO_MAX_SG);
 	sg_set_buf(&vblk->sg[0], &vbr->out_hdr, sizeof(vbr->out_hdr));
-	num = blk_rq_map_sg(q, vbr->req, vblk->sg+1);
-	sg_set_buf(&vblk->sg[num+1], &vbr->status, sizeof(vbr->status));
-
-	if (rq_data_dir(vbr->req) == WRITE) {
-		vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
-		out = 1 + num;
-		in = 1;
-	} else {
-		vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
-		out = 1;
-		in = 1 + num;
+	if (blk_pc_request(vbr->req)) {
+		sg_set_buf(&vblk->sg[out], &vbr->req->cmd, vbr->req->cmd_len);
+		out++;
+	}
+	num = blk_rq_map_sg(q, vbr->req, vblk->sg+out);
+	sg_set_buf(&vblk->sg[num+out], &vbr->status, sizeof(vbr->status));
+	if (blk_pc_request(vbr->req)) {
+		sg_set_buf(&vblk->sg[num+out+1], &vbr->req->sense, 96);
+		in++;
 	}
 
+	if (vbr->req->data_len) {
+		if (rq_data_dir(vbr->req) == WRITE) {
+			vbr->out_hdr.type |= VIRTIO_BLK_T_OUT;
+			out += num;
+		} else {
+			vbr->out_hdr.type |= VIRTIO_BLK_T_IN;
+			in += num;
+		}
+	}
 	if (vblk->vq->vq_ops->add_buf(vblk->vq, vblk->sg, out, in, vbr)) {
 		mempool_free(vbr, vblk->pool);
 		return false;
diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 7d6b34e..a73f6dc 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -485,6 +485,8 @@ int rescan_partitions(struct gendisk *disk, struct block_device *bdev)
 		delete_partition(disk, p);
 	if (disk->fops->revalidate_disk)
 		disk->fops->revalidate_disk(disk);
+	if (disk->flags & GENHD_FL_NO_PARTITION_SCAN)
+		return 0;
 	if (!get_capacity(disk) || !(state = check_partition(disk, bdev)))
 		return 0;
 	if (IS_ERR(state))	/* I/O error reading the partition table */
diff --git a/include/linux/genhd.h b/include/linux/genhd.h
index 118216f..87c45ad 100644
--- a/include/linux/genhd.h
+++ b/include/linux/genhd.h
@@ -109,6 +109,7 @@ struct hd_struct {
 #define GENHD_FL_UP				16
 #define GENHD_FL_SUPPRESS_PARTITION_INFO	32
 #define GENHD_FL_FAIL				64
+#define GENHD_FL_NO_PARTITION_SCAN		128
 
 #define BLK_SCSI_MAX_CMDS	(256)
 #define BLK_SCSI_CMD_PER_LONG	(BLK_SCSI_MAX_CMDS / (sizeof(long) * 8))
diff --git a/include/linux/virtio_blk.h b/include/linux/virtio_blk.h

             reply	other threads:[~2008-08-27 10:31 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-08-27 10:31 Hannes Reinecke [this message]
2008-08-27 12:30 ` [PATCH] Disable partition scan Hannes Reinecke
2008-08-28 12:00   ` Randy.Dunlap
  -- strict thread matches above, loose matches on Subject: below --
2009-09-12 11:45 devzero
2009-09-14  6:33 ` Hannes Reinecke
2009-09-14 20:59 devzero

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=48B52D0B.2090104@suse.de \
    --to=hare@suse.de \
    --cc=linux-kernel@vger.kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.