aoe: user can ask driver to forget previously detected devices

When an AoE device is detected, the kernel is informed, and a new block device
is created.  If the device is unused, the block device corresponding to remote
device that is no longer available may be removed from the system by telling
the aoe driver to "flush" its list of devices.

Without this patch, software like GPFS and LVM may attempt to read from AoE
devices that were discovered earlier but are no longer present, blocking until
the I/O attempt times out.

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>

5 files changed, 77 insertions, 19 deletions

diff --git a/Documentation/aoe/mkdevs.sh b/Documentation/aoe/mkdevs.sh
index 97374aacacb2..44c0ab702432 100644
--- a/Documentation/aoe/mkdevs.sh
+++ b/Documentation/aoe/mkdevs.sh
@@ -29,6 +29,8 @@ rm -f $dir/interfaces
 mknod -m 0200 $dir/interfaces c $MAJOR 4
 rm -f $dir/revalidate
 mknod -m 0200 $dir/revalidate c $MAJOR 5
+rm -f $dir/flush
+mknod -m 0200 $dir/flush c $MAJOR 6
 
 export n_partitions
 mkshelf=`echo $0 | sed 's!mkdevs!mkshelf!'`
diff --git a/Documentation/aoe/udev.txt b/Documentation/aoe/udev.txt
index 17e76c4f918e..8686e789542e 100644
--- a/Documentation/aoe/udev.txt
+++ b/Documentation/aoe/udev.txt
@@ -20,6 +20,7 @@ SUBSYSTEM=="aoe", KERNEL=="discover",	NAME="etherd/%k", GROUP="disk", MODE="0220
 SUBSYSTEM=="aoe", KERNEL=="err",        NAME="etherd/%k", GROUP="disk", MODE="0440"
 SUBSYSTEM=="aoe", KERNEL=="interfaces", NAME="etherd/%k", GROUP="disk", MODE="0220"
 SUBSYSTEM=="aoe", KERNEL=="revalidate", NAME="etherd/%k", GROUP="disk", MODE="0220"
+SUBSYSTEM=="aoe", KERNEL=="flush",      NAME="etherd/%k", GROUP="disk", MODE="0220"
 
 # aoe block devices     
 KERNEL=="etherd*",       NAME="%k", GROUP="disk"
diff --git a/drivers/block/aoe/aoe.h b/drivers/block/aoe/aoe.h
index aecaac3f2e58..2248ab226576 100644
--- a/drivers/block/aoe/aoe.h
+++ b/drivers/block/aoe/aoe.h
@@ -191,6 +191,7 @@ struct aoedev *aoedev_by_aoeaddr(int maj, int min);
 struct aoedev *aoedev_by_sysminor_m(ulong sysminor);
 void aoedev_downdev(struct aoedev *d);
 int aoedev_isbusy(struct aoedev *d);
+int aoedev_flush(const char __user *str, size_t size);
 
 int aoenet_init(void);
 void aoenet_exit(void);
diff --git a/drivers/block/aoe/aoechr.c b/drivers/block/aoe/aoechr.c
index f1124664c5c9..1bc85aa2271f 100644
--- a/drivers/block/aoe/aoechr.c
+++ b/drivers/block/aoe/aoechr.c
@@ -15,6 +15,7 @@ enum {
         MINOR_DISCOVER,
         MINOR_INTERFACES,
         MINOR_REVALIDATE,
+        MINOR_FLUSH,
         MSGSZ = 2048,
         NMSG = 100,             /* message backlog to retain */
 };
@@ -43,6 +44,7 @@ static struct aoe_chardev chardevs[] = {
         { MINOR_DISCOVER, "discover" },
         { MINOR_INTERFACES, "interfaces" },
         { MINOR_REVALIDATE, "revalidate" },
+        { MINOR_FLUSH, "flush" },
 };
 
 static int
@@ -158,6 +160,9 @@ aoechr_write(struct file *filp, const char __user *buf, size_t cnt, loff_t *offp
                 break;
         case MINOR_REVALIDATE:
                 ret = revalidate(buf, cnt);
+                break;
+        case MINOR_FLUSH:
+                ret = aoedev_flush(buf, cnt);
         }
         if (ret == 0)
                 ret = cnt;
diff --git a/drivers/block/aoe/aoedev.c b/drivers/block/aoe/aoedev.c
index a4d625aefeaa..e26f6f4a28a2 100644
--- a/drivers/block/aoe/aoedev.c
+++ b/drivers/block/aoe/aoedev.c
@@ -9,6 +9,10 @@
 #include <linux/netdevice.h>
 #include "aoe.h"
 
+static void dummy_timer(ulong);
+static void aoedev_freedev(struct aoedev *);
+static void freetgt(struct aoetgt *t);
+
 static struct aoedev *devlist;
 static spinlock_t devlist_lock;
 
@@ -108,6 +112,70 @@ aoedev_downdev(struct aoedev *d)
         d->flags &= ~DEVFL_UP;
 }
 
+static void
+aoedev_freedev(struct aoedev *d)
+{
+        struct aoetgt **t, **e;
+
+        if (d->gd) {
+                aoedisk_rm_sysfs(d);
+                del_gendisk(d->gd);
+                put_disk(d->gd);
+        }
+        t = d->targets;
+        e = t + NTARGETS;
+        for (; t < e && *t; t++)
+                freetgt(*t);
+        if (d->bufpool)
+                mempool_destroy(d->bufpool);
+        kfree(d);
+}
+
+int
+aoedev_flush(const char __user *str, size_t cnt)
+{
+        ulong flags;
+        struct aoedev *d, **dd;
+        struct aoedev *rmd = NULL;
+        char buf[16];
+        int all = 0;
+
+        if (cnt >= 3) {
+                if (cnt > sizeof buf)
+                        cnt = sizeof buf;
+                if (copy_from_user(buf, str, cnt))
+                        return -EFAULT;
+                all = !strncmp(buf, "all", 3);
+        }
+
+        flush_scheduled_work();
+        spin_lock_irqsave(&devlist_lock, flags);
+        dd = &devlist;
+        while ((d = *dd)) {
+                spin_lock(&d->lock);
+                if ((!all && (d->flags & DEVFL_UP))
+                || (d->flags & (DEVFL_GDALLOC|DEVFL_NEWSIZE))
+                || d->nopen) {
+                        spin_unlock(&d->lock);
+                        dd = &d->next;
+                        continue;
+                }
+                *dd = d->next;
+                aoedev_downdev(d);
+                d->flags |= DEVFL_TKILL;
+                spin_unlock(&d->lock);
+                d->next = rmd;
+                rmd = d;
+        }
+        spin_unlock_irqrestore(&devlist_lock, flags);
+        while ((d = rmd)) {
+                rmd = d->next;
+                del_timer_sync(&d->timer);
+                aoedev_freedev(d);      /* must be able to sleep */
+        }
+        return 0;
+}
+
 /* find it or malloc it */
 struct aoedev *
 aoedev_by_sysminor_m(ulong sysminor)
@@ -161,25 +229,6 @@ freetgt(struct aoetgt *t)
         kfree(t);
 }
 
-static void
-aoedev_freedev(struct aoedev *d)
-{
-        struct aoetgt **t, **e;
-
-        if (d->gd) {
-                aoedisk_rm_sysfs(d);
-                del_gendisk(d->gd);
-                put_disk(d->gd);
-        }
-        t = d->targets;
-        e = t + NTARGETS;
-        for (; t < e && *t; t++)
-                freetgt(*t);
-        if (d->bufpool)
-                mempool_destroy(d->bufpool);
-        kfree(d);
-}
-
 void
 aoedev_exit(void)
 {