2012-10-05 04:16:38 +04:00
|
|
|
/* Copyright (c) 2012 Coraid, Inc. See COPYING for GPL terms. */
|
2005-04-17 02:20:36 +04:00
|
|
|
/*
|
|
|
|
* aoeblk.c
|
|
|
|
* block device routines
|
|
|
|
*/
|
|
|
|
|
2010-10-28 16:15:26 +04:00
|
|
|
#include <linux/kernel.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
#include <linux/hdreg.h>
|
|
|
|
#include <linux/blkdev.h>
|
2007-12-11 02:49:13 +03:00
|
|
|
#include <linux/backing-dev.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
#include <linux/fs.h>
|
|
|
|
#include <linux/ioctl.h>
|
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 11:04:11 +03:00
|
|
|
#include <linux/slab.h>
|
2010-10-28 16:15:26 +04:00
|
|
|
#include <linux/ratelimit.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
#include <linux/genhd.h>
|
|
|
|
#include <linux/netdevice.h>
|
2010-06-02 16:28:52 +04:00
|
|
|
#include <linux/mutex.h>
|
2011-05-27 00:00:52 +04:00
|
|
|
#include <linux/export.h>
|
2005-04-17 02:20:36 +04:00
|
|
|
#include "aoe.h"
|
|
|
|
|
2010-06-02 16:28:52 +04:00
|
|
|
static DEFINE_MUTEX(aoeblk_mutex);
|
2006-12-07 07:33:20 +03:00
|
|
|
static struct kmem_cache *buf_pool_cache;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2007-05-22 00:08:01 +04:00
|
|
|
static ssize_t aoedisk_show_state(struct device *dev,
|
|
|
|
struct device_attribute *attr, char *page)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2007-05-22 00:08:01 +04:00
|
|
|
struct gendisk *disk = dev_to_disk(dev);
|
2005-04-17 02:20:36 +04:00
|
|
|
struct aoedev *d = disk->private_data;
|
|
|
|
|
|
|
|
return snprintf(page, PAGE_SIZE,
|
|
|
|
"%s%s\n",
|
|
|
|
(d->flags & DEVFL_UP) ? "up" : "down",
|
aoe: handle multiple network paths to AoE device
A remote AoE device is something can process ATA commands and is identified by
an AoE shelf number and an AoE slot number. Such a device might have more
than one network interface, and it might be reachable by more than one local
network interface. This patch tracks the available network paths available to
each AoE device, allowing them to be used more efficiently.
Andrew Morton asked about the call to msleep_interruptible in the revalidate
function. Yes, if a signal is pending, then msleep_interruptible will not
return 0. That means we will not loop but will call aoenet_xmit with a NULL
skb, which is a noop. If the system is too low on memory or the aoe driver is
too low on frames, then the user can hit control-C to interrupt the attempt to
do a revalidate. I have added a comment to the code summarizing that.
Andrew Morton asked whether the allocation performed inside addtgt could use a
more relaxed allocation like GFP_KERNEL, but addtgt is called when the aoedev
lock has been locked with spin_lock_irqsave. It would be nice to allocate the
memory under fewer restrictions, but targets are only added when the device is
being discovered, and if the target can't be added right now, we can try again
in a minute when then next AoE config query broadcast goes out.
Andrew Morton pointed out that the "too many targets" message could be printed
for failing GFP_ATOMIC allocations. The last patch in this series makes the
messages more specific.
Signed-off-by: Ed L. Cashin <ecashin@coraid.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 15:20:00 +03:00
|
|
|
(d->flags & DEVFL_KICKME) ? ",kickme" :
|
2006-01-19 21:46:19 +03:00
|
|
|
(d->nopen && !(d->flags & DEVFL_UP)) ? ",closewait" : "");
|
|
|
|
/* I'd rather see nopen exported so we can ditch closewait */
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
2007-05-22 00:08:01 +04:00
|
|
|
static ssize_t aoedisk_show_mac(struct device *dev,
|
|
|
|
struct device_attribute *attr, char *page)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2007-05-22 00:08:01 +04:00
|
|
|
struct gendisk *disk = dev_to_disk(dev);
|
2005-04-17 02:20:36 +04:00
|
|
|
struct aoedev *d = disk->private_data;
|
aoe: handle multiple network paths to AoE device
A remote AoE device is something can process ATA commands and is identified by
an AoE shelf number and an AoE slot number. Such a device might have more
than one network interface, and it might be reachable by more than one local
network interface. This patch tracks the available network paths available to
each AoE device, allowing them to be used more efficiently.
Andrew Morton asked about the call to msleep_interruptible in the revalidate
function. Yes, if a signal is pending, then msleep_interruptible will not
return 0. That means we will not loop but will call aoenet_xmit with a NULL
skb, which is a noop. If the system is too low on memory or the aoe driver is
too low on frames, then the user can hit control-C to interrupt the attempt to
do a revalidate. I have added a comment to the code summarizing that.
Andrew Morton asked whether the allocation performed inside addtgt could use a
more relaxed allocation like GFP_KERNEL, but addtgt is called when the aoedev
lock has been locked with spin_lock_irqsave. It would be nice to allocate the
memory under fewer restrictions, but targets are only added when the device is
being discovered, and if the target can't be added right now, we can try again
in a minute when then next AoE config query broadcast goes out.
Andrew Morton pointed out that the "too many targets" message could be printed
for failing GFP_ATOMIC allocations. The last patch in this series makes the
messages more specific.
Signed-off-by: Ed L. Cashin <ecashin@coraid.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 15:20:00 +03:00
|
|
|
struct aoetgt *t = d->targets[0];
|
2005-04-17 02:20:36 +04:00
|
|
|
|
aoe: handle multiple network paths to AoE device
A remote AoE device is something can process ATA commands and is identified by
an AoE shelf number and an AoE slot number. Such a device might have more
than one network interface, and it might be reachable by more than one local
network interface. This patch tracks the available network paths available to
each AoE device, allowing them to be used more efficiently.
Andrew Morton asked about the call to msleep_interruptible in the revalidate
function. Yes, if a signal is pending, then msleep_interruptible will not
return 0. That means we will not loop but will call aoenet_xmit with a NULL
skb, which is a noop. If the system is too low on memory or the aoe driver is
too low on frames, then the user can hit control-C to interrupt the attempt to
do a revalidate. I have added a comment to the code summarizing that.
Andrew Morton asked whether the allocation performed inside addtgt could use a
more relaxed allocation like GFP_KERNEL, but addtgt is called when the aoedev
lock has been locked with spin_lock_irqsave. It would be nice to allocate the
memory under fewer restrictions, but targets are only added when the device is
being discovered, and if the target can't be added right now, we can try again
in a minute when then next AoE config query broadcast goes out.
Andrew Morton pointed out that the "too many targets" message could be printed
for failing GFP_ATOMIC allocations. The last patch in this series makes the
messages more specific.
Signed-off-by: Ed L. Cashin <ecashin@coraid.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 15:20:00 +03:00
|
|
|
if (t == NULL)
|
|
|
|
return snprintf(page, PAGE_SIZE, "none\n");
|
2008-11-25 11:40:37 +03:00
|
|
|
return snprintf(page, PAGE_SIZE, "%pm\n", t->addr);
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
2007-05-22 00:08:01 +04:00
|
|
|
static ssize_t aoedisk_show_netif(struct device *dev,
|
|
|
|
struct device_attribute *attr, char *page)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2007-05-22 00:08:01 +04:00
|
|
|
struct gendisk *disk = dev_to_disk(dev);
|
2005-04-17 02:20:36 +04:00
|
|
|
struct aoedev *d = disk->private_data;
|
aoe: handle multiple network paths to AoE device
A remote AoE device is something can process ATA commands and is identified by
an AoE shelf number and an AoE slot number. Such a device might have more
than one network interface, and it might be reachable by more than one local
network interface. This patch tracks the available network paths available to
each AoE device, allowing them to be used more efficiently.
Andrew Morton asked about the call to msleep_interruptible in the revalidate
function. Yes, if a signal is pending, then msleep_interruptible will not
return 0. That means we will not loop but will call aoenet_xmit with a NULL
skb, which is a noop. If the system is too low on memory or the aoe driver is
too low on frames, then the user can hit control-C to interrupt the attempt to
do a revalidate. I have added a comment to the code summarizing that.
Andrew Morton asked whether the allocation performed inside addtgt could use a
more relaxed allocation like GFP_KERNEL, but addtgt is called when the aoedev
lock has been locked with spin_lock_irqsave. It would be nice to allocate the
memory under fewer restrictions, but targets are only added when the device is
being discovered, and if the target can't be added right now, we can try again
in a minute when then next AoE config query broadcast goes out.
Andrew Morton pointed out that the "too many targets" message could be printed
for failing GFP_ATOMIC allocations. The last patch in this series makes the
messages more specific.
Signed-off-by: Ed L. Cashin <ecashin@coraid.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 15:20:00 +03:00
|
|
|
struct net_device *nds[8], **nd, **nnd, **ne;
|
|
|
|
struct aoetgt **t, **te;
|
|
|
|
struct aoeif *ifp, *e;
|
|
|
|
char *p;
|
|
|
|
|
|
|
|
memset(nds, 0, sizeof nds);
|
|
|
|
nd = nds;
|
|
|
|
ne = nd + ARRAY_SIZE(nds);
|
|
|
|
t = d->targets;
|
|
|
|
te = t + NTARGETS;
|
|
|
|
for (; t < te && *t; t++) {
|
|
|
|
ifp = (*t)->ifs;
|
|
|
|
e = ifp + NAOEIFS;
|
|
|
|
for (; ifp < e && ifp->nd; ifp++) {
|
|
|
|
for (nnd = nds; nnd < nd; nnd++)
|
|
|
|
if (*nnd == ifp->nd)
|
|
|
|
break;
|
|
|
|
if (nnd == nd && nd != ne)
|
|
|
|
*nd++ = ifp->nd;
|
|
|
|
}
|
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
|
aoe: handle multiple network paths to AoE device
A remote AoE device is something can process ATA commands and is identified by
an AoE shelf number and an AoE slot number. Such a device might have more
than one network interface, and it might be reachable by more than one local
network interface. This patch tracks the available network paths available to
each AoE device, allowing them to be used more efficiently.
Andrew Morton asked about the call to msleep_interruptible in the revalidate
function. Yes, if a signal is pending, then msleep_interruptible will not
return 0. That means we will not loop but will call aoenet_xmit with a NULL
skb, which is a noop. If the system is too low on memory or the aoe driver is
too low on frames, then the user can hit control-C to interrupt the attempt to
do a revalidate. I have added a comment to the code summarizing that.
Andrew Morton asked whether the allocation performed inside addtgt could use a
more relaxed allocation like GFP_KERNEL, but addtgt is called when the aoedev
lock has been locked with spin_lock_irqsave. It would be nice to allocate the
memory under fewer restrictions, but targets are only added when the device is
being discovered, and if the target can't be added right now, we can try again
in a minute when then next AoE config query broadcast goes out.
Andrew Morton pointed out that the "too many targets" message could be printed
for failing GFP_ATOMIC allocations. The last patch in this series makes the
messages more specific.
Signed-off-by: Ed L. Cashin <ecashin@coraid.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 15:20:00 +03:00
|
|
|
ne = nd;
|
|
|
|
nd = nds;
|
|
|
|
if (*nd == NULL)
|
|
|
|
return snprintf(page, PAGE_SIZE, "none\n");
|
|
|
|
for (p = page; nd < ne; nd++)
|
|
|
|
p += snprintf(p, PAGE_SIZE - (p-page), "%s%s",
|
|
|
|
p == page ? "" : ",", (*nd)->name);
|
|
|
|
p += snprintf(p, PAGE_SIZE - (p-page), "\n");
|
|
|
|
return p-page;
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
2005-04-29 18:24:25 +04:00
|
|
|
/* firmware version */
|
2007-05-22 00:08:01 +04:00
|
|
|
static ssize_t aoedisk_show_fwver(struct device *dev,
|
|
|
|
struct device_attribute *attr, char *page)
|
2005-04-29 18:24:25 +04:00
|
|
|
{
|
2007-05-22 00:08:01 +04:00
|
|
|
struct gendisk *disk = dev_to_disk(dev);
|
2005-04-29 18:24:25 +04:00
|
|
|
struct aoedev *d = disk->private_data;
|
|
|
|
|
|
|
|
return snprintf(page, PAGE_SIZE, "0x%04x\n", (unsigned int) d->fw_ver);
|
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2007-05-22 00:08:01 +04:00
|
|
|
static DEVICE_ATTR(state, S_IRUGO, aoedisk_show_state, NULL);
|
|
|
|
static DEVICE_ATTR(mac, S_IRUGO, aoedisk_show_mac, NULL);
|
|
|
|
static DEVICE_ATTR(netif, S_IRUGO, aoedisk_show_netif, NULL);
|
|
|
|
static struct device_attribute dev_attr_firmware_version = {
|
2008-10-19 07:28:50 +04:00
|
|
|
.attr = { .name = "firmware-version", .mode = S_IRUGO },
|
2007-05-22 00:08:01 +04:00
|
|
|
.show = aoedisk_show_fwver,
|
2005-04-29 18:24:25 +04:00
|
|
|
};
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2002-04-09 23:14:34 +04:00
|
|
|
static struct attribute *aoe_attrs[] = {
|
2007-05-22 00:08:01 +04:00
|
|
|
&dev_attr_state.attr,
|
|
|
|
&dev_attr_mac.attr,
|
|
|
|
&dev_attr_netif.attr,
|
|
|
|
&dev_attr_firmware_version.attr,
|
|
|
|
NULL,
|
2002-04-09 23:14:34 +04:00
|
|
|
};
|
|
|
|
|
|
|
|
static const struct attribute_group attr_group = {
|
|
|
|
.attrs = aoe_attrs,
|
|
|
|
};
|
|
|
|
|
|
|
|
static int
|
2005-04-17 02:20:36 +04:00
|
|
|
aoedisk_add_sysfs(struct aoedev *d)
|
|
|
|
{
|
2008-08-25 14:56:05 +04:00
|
|
|
return sysfs_create_group(&disk_to_dev(d->gd)->kobj, &attr_group);
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
|
|
|
void
|
|
|
|
aoedisk_rm_sysfs(struct aoedev *d)
|
|
|
|
{
|
2008-08-25 14:56:05 +04:00
|
|
|
sysfs_remove_group(&disk_to_dev(d->gd)->kobj, &attr_group);
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2008-03-02 17:23:18 +03:00
|
|
|
aoeblk_open(struct block_device *bdev, fmode_t mode)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2008-03-02 17:23:18 +03:00
|
|
|
struct aoedev *d = bdev->bd_disk->private_data;
|
2005-04-17 02:20:36 +04:00
|
|
|
ulong flags;
|
|
|
|
|
2010-06-02 16:28:52 +04:00
|
|
|
mutex_lock(&aoeblk_mutex);
|
2005-04-17 02:20:36 +04:00
|
|
|
spin_lock_irqsave(&d->lock, flags);
|
|
|
|
if (d->flags & DEVFL_UP) {
|
|
|
|
d->nopen++;
|
|
|
|
spin_unlock_irqrestore(&d->lock, flags);
|
2010-06-02 16:28:52 +04:00
|
|
|
mutex_unlock(&aoeblk_mutex);
|
2005-04-17 02:20:36 +04:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
spin_unlock_irqrestore(&d->lock, flags);
|
2010-06-02 16:28:52 +04:00
|
|
|
mutex_unlock(&aoeblk_mutex);
|
2005-04-17 02:20:36 +04:00
|
|
|
return -ENODEV;
|
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2008-03-02 17:23:18 +03:00
|
|
|
aoeblk_release(struct gendisk *disk, fmode_t mode)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2008-03-02 17:23:18 +03:00
|
|
|
struct aoedev *d = disk->private_data;
|
2005-04-17 02:20:36 +04:00
|
|
|
ulong flags;
|
|
|
|
|
|
|
|
spin_lock_irqsave(&d->lock, flags);
|
|
|
|
|
2006-01-19 21:46:27 +03:00
|
|
|
if (--d->nopen == 0) {
|
2005-04-17 02:20:36 +04:00
|
|
|
spin_unlock_irqrestore(&d->lock, flags);
|
|
|
|
aoecmd_cfg(d->aoemajor, d->aoeminor);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
spin_unlock_irqrestore(&d->lock, flags);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2011-09-12 14:12:01 +04:00
|
|
|
static void
|
2012-10-05 04:16:23 +04:00
|
|
|
aoeblk_request(struct request_queue *q)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
|
|
|
struct aoedev *d;
|
2012-10-05 04:16:23 +04:00
|
|
|
struct request *rq;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2012-10-05 04:16:23 +04:00
|
|
|
d = q->queuedata;
|
2005-04-17 02:20:36 +04:00
|
|
|
if ((d->flags & DEVFL_UP) == 0) {
|
2010-10-28 16:15:26 +04:00
|
|
|
pr_info_ratelimited("aoe: device %ld.%d is not up\n",
|
2006-09-20 22:36:51 +04:00
|
|
|
d->aoemajor, d->aoeminor);
|
2012-10-05 04:16:23 +04:00
|
|
|
while ((rq = blk_peek_request(q))) {
|
|
|
|
blk_start_request(rq);
|
|
|
|
aoe_end_request(d, rq, 1);
|
|
|
|
}
|
2011-09-12 14:12:01 +04:00
|
|
|
return;
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
2006-01-19 21:46:19 +03:00
|
|
|
aoecmd_work(d);
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
static int
|
2006-01-08 12:02:50 +03:00
|
|
|
aoeblk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
|
2005-04-17 02:20:36 +04:00
|
|
|
{
|
2006-01-08 12:02:50 +03:00
|
|
|
struct aoedev *d = bdev->bd_disk->private_data;
|
2005-04-17 02:20:36 +04:00
|
|
|
|
|
|
|
if ((d->flags & DEVFL_UP) == 0) {
|
2006-09-20 22:36:51 +04:00
|
|
|
printk(KERN_ERR "aoe: disk not up\n");
|
2005-04-17 02:20:36 +04:00
|
|
|
return -ENODEV;
|
|
|
|
}
|
|
|
|
|
2006-01-08 12:02:50 +03:00
|
|
|
geo->cylinders = d->geo.cylinders;
|
|
|
|
geo->heads = d->geo.heads;
|
|
|
|
geo->sectors = d->geo.sectors;
|
|
|
|
return 0;
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
|
|
|
|
2009-09-22 04:01:13 +04:00
|
|
|
static const struct block_device_operations aoe_bdops = {
|
2008-03-02 17:23:18 +03:00
|
|
|
.open = aoeblk_open,
|
|
|
|
.release = aoeblk_release,
|
2006-01-08 12:02:50 +03:00
|
|
|
.getgeo = aoeblk_getgeo,
|
2005-04-17 02:20:36 +04:00
|
|
|
.owner = THIS_MODULE,
|
|
|
|
};
|
|
|
|
|
|
|
|
/* alloc_disk and add_disk can sleep */
|
|
|
|
void
|
|
|
|
aoeblk_gdalloc(void *vp)
|
|
|
|
{
|
|
|
|
struct aoedev *d = vp;
|
|
|
|
struct gendisk *gd;
|
2012-10-05 04:16:23 +04:00
|
|
|
mempool_t *mp;
|
|
|
|
struct request_queue *q;
|
|
|
|
enum { KB = 1024, MB = KB * KB, READ_AHEAD = 2 * MB, };
|
2005-04-17 02:20:36 +04:00
|
|
|
ulong flags;
|
|
|
|
|
|
|
|
gd = alloc_disk(AOE_PARTITIONS);
|
|
|
|
if (gd == NULL) {
|
2012-10-05 04:16:23 +04:00
|
|
|
pr_err("aoe: cannot allocate disk structure for %ld.%d\n",
|
2006-09-20 22:36:49 +04:00
|
|
|
d->aoemajor, d->aoeminor);
|
2007-12-11 02:49:13 +03:00
|
|
|
goto err;
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
|
|
|
|
2012-10-05 04:16:23 +04:00
|
|
|
mp = mempool_create(MIN_BUFS, mempool_alloc_slab, mempool_free_slab,
|
|
|
|
buf_pool_cache);
|
|
|
|
if (mp == NULL) {
|
2008-02-08 15:20:08 +03:00
|
|
|
printk(KERN_ERR "aoe: cannot allocate bufpool for %ld.%d\n",
|
2006-09-20 22:36:49 +04:00
|
|
|
d->aoemajor, d->aoeminor);
|
2007-12-11 02:49:13 +03:00
|
|
|
goto err_disk;
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
2012-10-05 04:16:23 +04:00
|
|
|
q = blk_init_queue(aoeblk_request, &d->lock);
|
|
|
|
if (q == NULL) {
|
|
|
|
pr_err("aoe: cannot allocate block queue for %ld.%d\n",
|
|
|
|
d->aoemajor, d->aoeminor);
|
|
|
|
mempool_destroy(mp);
|
|
|
|
goto err_disk;
|
|
|
|
}
|
2005-04-17 02:20:36 +04:00
|
|
|
|
2009-09-09 16:10:18 +04:00
|
|
|
d->blkq = blk_alloc_queue(GFP_KERNEL);
|
|
|
|
if (!d->blkq)
|
2007-12-11 02:49:13 +03:00
|
|
|
goto err_mempool;
|
2009-06-12 16:45:52 +04:00
|
|
|
d->blkq->backing_dev_info.name = "aoe";
|
2009-09-09 16:10:18 +04:00
|
|
|
if (bdi_init(&d->blkq->backing_dev_info))
|
|
|
|
goto err_blkq;
|
2007-12-11 02:49:13 +03:00
|
|
|
spin_lock_irqsave(&d->lock, flags);
|
2012-10-05 04:16:20 +04:00
|
|
|
blk_queue_max_hw_sectors(d->blkq, BLK_DEF_MAX_SECTORS);
|
2012-10-05 04:16:23 +04:00
|
|
|
q->backing_dev_info.ra_pages = READ_AHEAD / PAGE_CACHE_SIZE;
|
|
|
|
d->bufpool = mp;
|
|
|
|
d->blkq = gd->queue = q;
|
|
|
|
q->queuedata = d;
|
|
|
|
d->gd = gd;
|
2005-04-17 02:20:36 +04:00
|
|
|
gd->major = AOE_MAJOR;
|
2012-10-05 04:16:40 +04:00
|
|
|
gd->first_minor = d->sysminor;
|
2005-04-17 02:20:36 +04:00
|
|
|
gd->fops = &aoe_bdops;
|
|
|
|
gd->private_data = d;
|
2008-08-25 14:56:07 +04:00
|
|
|
set_capacity(gd, d->ssize);
|
aoe: handle multiple network paths to AoE device
A remote AoE device is something can process ATA commands and is identified by
an AoE shelf number and an AoE slot number. Such a device might have more
than one network interface, and it might be reachable by more than one local
network interface. This patch tracks the available network paths available to
each AoE device, allowing them to be used more efficiently.
Andrew Morton asked about the call to msleep_interruptible in the revalidate
function. Yes, if a signal is pending, then msleep_interruptible will not
return 0. That means we will not loop but will call aoenet_xmit with a NULL
skb, which is a noop. If the system is too low on memory or the aoe driver is
too low on frames, then the user can hit control-C to interrupt the attempt to
do a revalidate. I have added a comment to the code summarizing that.
Andrew Morton asked whether the allocation performed inside addtgt could use a
more relaxed allocation like GFP_KERNEL, but addtgt is called when the aoedev
lock has been locked with spin_lock_irqsave. It would be nice to allocate the
memory under fewer restrictions, but targets are only added when the device is
being discovered, and if the target can't be added right now, we can try again
in a minute when then next AoE config query broadcast goes out.
Andrew Morton pointed out that the "too many targets" message could be printed
for failing GFP_ATOMIC allocations. The last patch in this series makes the
messages more specific.
Signed-off-by: Ed L. Cashin <ecashin@coraid.com>
Cc: Greg KH <greg@kroah.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 15:20:00 +03:00
|
|
|
snprintf(gd->disk_name, sizeof gd->disk_name, "etherd/e%ld.%d",
|
2005-04-17 02:20:36 +04:00
|
|
|
d->aoemajor, d->aoeminor);
|
|
|
|
|
2006-01-19 21:46:19 +03:00
|
|
|
d->flags &= ~DEVFL_GDALLOC;
|
2005-04-17 02:20:36 +04:00
|
|
|
d->flags |= DEVFL_UP;
|
|
|
|
|
|
|
|
spin_unlock_irqrestore(&d->lock, flags);
|
|
|
|
|
|
|
|
add_disk(gd);
|
|
|
|
aoedisk_add_sysfs(d);
|
2007-12-11 02:49:13 +03:00
|
|
|
return;
|
|
|
|
|
2009-09-09 16:10:18 +04:00
|
|
|
err_blkq:
|
|
|
|
blk_cleanup_queue(d->blkq);
|
|
|
|
d->blkq = NULL;
|
2007-12-11 02:49:13 +03:00
|
|
|
err_mempool:
|
|
|
|
mempool_destroy(d->bufpool);
|
|
|
|
err_disk:
|
|
|
|
put_disk(gd);
|
|
|
|
err:
|
|
|
|
spin_lock_irqsave(&d->lock, flags);
|
|
|
|
d->flags &= ~DEVFL_GDALLOC;
|
|
|
|
spin_unlock_irqrestore(&d->lock, flags);
|
2005-04-17 02:20:36 +04:00
|
|
|
}
|
|
|
|
|
|
|
|
void
|
|
|
|
aoeblk_exit(void)
|
|
|
|
{
|
|
|
|
kmem_cache_destroy(buf_pool_cache);
|
|
|
|
}
|
|
|
|
|
|
|
|
int __init
|
|
|
|
aoeblk_init(void)
|
|
|
|
{
|
2007-07-20 05:11:58 +04:00
|
|
|
buf_pool_cache = kmem_cache_create("aoe_bufs",
|
2005-04-17 02:20:36 +04:00
|
|
|
sizeof(struct buf),
|
2007-07-20 05:11:58 +04:00
|
|
|
0, 0, NULL);
|
2005-04-17 02:20:36 +04:00
|
|
|
if (buf_pool_cache == NULL)
|
|
|
|
return -ENOMEM;
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|