7 files changed, 274 insertions, 99 deletions

diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 717d6e4e18d3..6f07ec1c2f58 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -256,6 +256,21 @@ config BLK_DEV_LOOP
 
           Most users will answer N here.
 
+config BLK_DEV_LOOP_MIN_COUNT
+        int "Number of loop devices to pre-create at init time"
+        depends on BLK_DEV_LOOP
+        default 8
+        help
+          Static number of loop devices to be unconditionally pre-created
+          at init time.
+
+          This default value can be overwritten on the kernel command
+          line or with module-parameter loop.max_loop.
+
+          The historic default is 8. If a late 2011 version of losetup(8)
+          is used, it can be set to 0, since needed loop devices can be
+          dynamically allocated with the /dev/loop-control interface.
+
 config BLK_DEV_CRYPTOLOOP
         tristate "Cryptoloop Support"
         select CRYPTO
@@ -471,7 +486,7 @@ config XEN_BLKDEV_FRONTEND
           in another domain which drives the actual block device.
 
 config XEN_BLKDEV_BACKEND
-        tristate "Block-device backend driver"
+        tristate "Xen block-device backend driver"
         depends on XEN_BACKEND
         help
           The block-device backend driver allows the kernel to export its
diff --git a/drivers/block/cciss_scsi.c b/drivers/block/cciss_scsi.c
index 696100241a6f..951a4e33b92b 100644
--- a/drivers/block/cciss_scsi.c
+++ b/drivers/block/cciss_scsi.c
@@ -33,7 +33,7 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 #include <scsi/scsi_cmnd.h>
 #include <scsi/scsi_device.h>
diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c
index 20de58d6df40..af2a25049bce 100644
--- a/drivers/block/drbd/drbd_nl.c
+++ b/drivers/block/drbd/drbd_nl.c
@@ -1829,10 +1829,10 @@ static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *n
 
         /* silently ignore cpu mask on UP kernel */
         if (nr_cpu_ids > 1 && sc.cpu_mask[0] != 0) {
-                err = __bitmap_parse(sc.cpu_mask, 32, 0,
+                err = bitmap_parse(sc.cpu_mask, 32,
                                 cpumask_bits(new_cpu_mask), nr_cpu_ids);
                 if (err) {
-                        dev_warn(DEV, "__bitmap_parse() failed with %d\n", err);
+                        dev_warn(DEV, "bitmap_parse() failed with %d\n", err);
                         retcode = ERR_CPU_MASK_PARSE;
                         goto fail;
                 }
diff --git a/drivers/block/loop.c b/drivers/block/loop.c
index 76c8da78212b..4720c7ade0ae 100644
--- a/drivers/block/loop.c
+++ b/drivers/block/loop.c
@@ -75,11 +75,11 @@
 #include <linux/kthread.h>
 #include <linux/splice.h>
 #include <linux/sysfs.h>
-
+#include <linux/miscdevice.h>
 #include <asm/uaccess.h>
 
-static LIST_HEAD(loop_devices);
-static DEFINE_MUTEX(loop_devices_mutex);
+static DEFINE_IDR(loop_index_idr);
+static DEFINE_MUTEX(loop_index_mutex);
 
 static int max_part;
 static int part_shift;
@@ -722,17 +722,10 @@ static inline int is_loop_device(struct file *file)
 static ssize_t loop_attr_show(struct device *dev, char *page,
                               ssize_t (*callback)(struct loop_device *, char *))
 {
-        struct loop_device *l, *lo = NULL;
-
-        mutex_lock(&loop_devices_mutex);
-        list_for_each_entry(l, &loop_devices, lo_list)
-                if (disk_to_dev(l->lo_disk) == dev) {
-                        lo = l;
-                        break;
-                }
-        mutex_unlock(&loop_devices_mutex);
+        struct gendisk *disk = dev_to_disk(dev);
+        struct loop_device *lo = disk->private_data;
 
-        return lo ? callback(lo, page) : -EIO;
+        return callback(lo, page);
 }
 
 #define LOOP_ATTR_RO(_name)                                             \
@@ -750,10 +743,10 @@ static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
         ssize_t ret;
         char *p = NULL;
 
-        mutex_lock(&lo->lo_ctl_mutex);
+        spin_lock_irq(&lo->lo_lock);
         if (lo->lo_backing_file)
                 p = d_path(&lo->lo_backing_file->f_path, buf, PAGE_SIZE - 1);
-        mutex_unlock(&lo->lo_ctl_mutex);
+        spin_unlock_irq(&lo->lo_lock);
 
         if (IS_ERR_OR_NULL(p))
                 ret = PTR_ERR(p);
@@ -1007,7 +1000,9 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
 
         kthread_stop(lo->lo_thread);
 
+        spin_lock_irq(&lo->lo_lock);
         lo->lo_backing_file = NULL;
+        spin_unlock_irq(&lo->lo_lock);
 
         loop_release_xfer(lo);
         lo->transfer = NULL;
@@ -1485,13 +1480,22 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
 
 static int lo_open(struct block_device *bdev, fmode_t mode)
 {
-        struct loop_device *lo = bdev->bd_disk->private_data;
+        struct loop_device *lo;
+        int err = 0;
+
+        mutex_lock(&loop_index_mutex);
+        lo = bdev->bd_disk->private_data;
+        if (!lo) {
+                err = -ENXIO;
+                goto out;
+        }
 
         mutex_lock(&lo->lo_ctl_mutex);
         lo->lo_refcnt++;
         mutex_unlock(&lo->lo_ctl_mutex);
-
-        return 0;
+out:
+        mutex_unlock(&loop_index_mutex);
+        return err;
 }
 
 static int lo_release(struct gendisk *disk, fmode_t mode)
@@ -1557,40 +1561,71 @@ int loop_register_transfer(struct loop_func_table *funcs)
         return 0;
 }
 
+static int unregister_transfer_cb(int id, void *ptr, void *data)
+{
+        struct loop_device *lo = ptr;
+        struct loop_func_table *xfer = data;
+
+        mutex_lock(&lo->lo_ctl_mutex);
+        if (lo->lo_encryption == xfer)
+                loop_release_xfer(lo);
+        mutex_unlock(&lo->lo_ctl_mutex);
+        return 0;
+}
+
 int loop_unregister_transfer(int number)
 {
         unsigned int n = number;
-        struct loop_device *lo;
         struct loop_func_table *xfer;
 
         if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL)
                 return -EINVAL;
 
         xfer_funcs[n] = NULL;
-
-        list_for_each_entry(lo, &loop_devices, lo_list) {
-                mutex_lock(&lo->lo_ctl_mutex);
-
-                if (lo->lo_encryption == xfer)
-                        loop_release_xfer(lo);
-
-                mutex_unlock(&lo->lo_ctl_mutex);
-        }
-
+        idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer);
         return 0;
 }
 
 EXPORT_SYMBOL(loop_register_transfer);
 EXPORT_SYMBOL(loop_unregister_transfer);
 
-static struct loop_device *loop_alloc(int i)
+static int loop_add(struct loop_device **l, int i)
 {
         struct loop_device *lo;
         struct gendisk *disk;
+        int err;
 
         lo = kzalloc(sizeof(*lo), GFP_KERNEL);
-        if (!lo)
+        if (!lo) {
+                err = -ENOMEM;
                 goto out;
+        }
+
+        err = idr_pre_get(&loop_index_idr, GFP_KERNEL);
+        if (err < 0)
+                goto out_free_dev;
+
+        if (i >= 0) {
+                int m;
+
+                /* create specific i in the index */
+                err = idr_get_new_above(&loop_index_idr, lo, i, &m);
+                if (err >= 0 && i != m) {
+                        idr_remove(&loop_index_idr, m);
+                        err = -EEXIST;
+                }
+        } else if (i == -1) {
+                int m;
+
+                /* get next free nr */
+                err = idr_get_new(&loop_index_idr, lo, &m);
+                if (err >= 0)
+                        i = m;
+        } else {
+                err = -EINVAL;
+        }
+        if (err < 0)
+                goto out_free_dev;
 
         lo->lo_queue = blk_alloc_queue(GFP_KERNEL);
         if (!lo->lo_queue)
@@ -1611,81 +1646,158 @@ static struct loop_device *loop_alloc(int i)
         disk->private_data      = lo;
         disk->queue             = lo->lo_queue;
         sprintf(disk->disk_name, "loop%d", i);
-        return lo;
+        add_disk(disk);
+        *l = lo;
+        return lo->lo_number;
 
 out_free_queue:
         blk_cleanup_queue(lo->lo_queue);
 out_free_dev:
         kfree(lo);
 out:
-        return NULL;
+        return err;
 }
 
-static void loop_free(struct loop_device *lo)
+static void loop_remove(struct loop_device *lo)
 {
+        del_gendisk(lo->lo_disk);
         blk_cleanup_queue(lo->lo_queue);
         put_disk(lo->lo_disk);
-        list_del(&lo->lo_list);
         kfree(lo);
 }
 
-static struct loop_device *loop_init_one(int i)
+static int find_free_cb(int id, void *ptr, void *data)
+{
+        struct loop_device *lo = ptr;
+        struct loop_device **l = data;
+
+        if (lo->lo_state == Lo_unbound) {
+                *l = lo;
+                return 1;
+        }
+        return 0;
+}
+
+static int loop_lookup(struct loop_device **l, int i)
 {
         struct loop_device *lo;
+        int ret = -ENODEV;
 
-        list_for_each_entry(lo, &loop_devices, lo_list) {
-                if (lo->lo_number == i)
-                        return lo;
+        if (i < 0) {
+                int err;
+
+                err = idr_for_each(&loop_index_idr, &find_free_cb, &lo);
+                if (err == 1) {
+                        *l = lo;
+                        ret = lo->lo_number;
+                }
+                goto out;
         }
 
-        lo = loop_alloc(i);
+        /* lookup and return a specific i */
+        lo = idr_find(&loop_index_idr, i);
         if (lo) {
-                add_disk(lo->lo_disk);
-                list_add_tail(&lo->lo_list, &loop_devices);
+                *l = lo;
+                ret = lo->lo_number;
         }
-        return lo;
-}
-
-static void loop_del_one(struct loop_device *lo)
-{
-        del_gendisk(lo->lo_disk);
-        loop_free(lo);
+out:
+        return ret;
 }
 
 static struct kobject *loop_probe(dev_t dev, int *part, void *data)
 {
         struct loop_device *lo;
         struct kobject *kobj;
+        int err;
 
-        mutex_lock(&loop_devices_mutex);
-        lo = loop_init_one(MINOR(dev) >> part_shift);
-        kobj = lo ? get_disk(lo->lo_disk) : ERR_PTR(-ENOMEM);
-        mutex_unlock(&loop_devices_mutex);
+        mutex_lock(&loop_index_mutex);
+        err = loop_lookup(&lo, MINOR(dev) >> part_shift);
+        if (err < 0)
+                err = loop_add(&lo, MINOR(dev) >> part_shift);
+        if (err < 0)
+                kobj = ERR_PTR(err);
+        else
+                kobj = get_disk(lo->lo_disk);
+        mutex_unlock(&loop_index_mutex);
 
         *part = 0;
         return kobj;
 }
 
+static long loop_control_ioctl(struct file *file, unsigned int cmd,
+                               unsigned long parm)
+{
+        struct loop_device *lo;
+        int ret = -ENOSYS;
+
+        mutex_lock(&loop_index_mutex);
+        switch (cmd) {
+        case LOOP_CTL_ADD:
+                ret = loop_lookup(&lo, parm);
+                if (ret >= 0) {
+                        ret = -EEXIST;
+                        break;
+                }
+                ret = loop_add(&lo, parm);
+                break;
+        case LOOP_CTL_REMOVE:
+                ret = loop_lookup(&lo, parm);
+                if (ret < 0)
+                        break;
+                mutex_lock(&lo->lo_ctl_mutex);
+                if (lo->lo_state != Lo_unbound) {
+                        ret = -EBUSY;
+                        mutex_unlock(&lo->lo_ctl_mutex);
+                        break;
+                }
+                if (lo->lo_refcnt > 0) {
+                        ret = -EBUSY;
+                        mutex_unlock(&lo->lo_ctl_mutex);
+                        break;
+                }
+                lo->lo_disk->private_data = NULL;
+                mutex_unlock(&lo->lo_ctl_mutex);
+                idr_remove(&loop_index_idr, lo->lo_number);
+                loop_remove(lo);
+                break;
+        case LOOP_CTL_GET_FREE:
+                ret = loop_lookup(&lo, -1);
+                if (ret >= 0)
+                        break;
+                ret = loop_add(&lo, -1);
+        }
+        mutex_unlock(&loop_index_mutex);
+
+        return ret;
+}
+
+static const struct file_operations loop_ctl_fops = {
+        .open           = nonseekable_open,
+        .unlocked_ioctl = loop_control_ioctl,
+        .compat_ioctl   = loop_control_ioctl,
+        .owner          = THIS_MODULE,
+        .llseek         = noop_llseek,
+};
+
+static struct miscdevice loop_misc = {
+        .minor          = LOOP_CTRL_MINOR,
+        .name           = "loop-control",
+        .fops           = &loop_ctl_fops,
+};
+
+MODULE_ALIAS_MISCDEV(LOOP_CTRL_MINOR);
+MODULE_ALIAS("devname:loop-control");
+
 static int __init loop_init(void)
 {
         int i, nr;
         unsigned long range;
-        struct loop_device *lo, *next;
+        struct loop_device *lo;
+        int err;
 
-        /*
-         * loop module now has a feature to instantiate underlying device
-         * structure on-demand, provided that there is an access dev node.
-         * However, this will not work well with user space tool that doesn't
-         * know about such "feature".  In order to not break any existing
-         * tool, we do the following:
-         *
-         * (1) if max_loop is specified, create that many upfront, and this
-         *     also becomes a hard limit.
-         * (2) if max_loop is not specified, create 8 loop device on module
-         *     load, user can further extend loop device by create dev node
-         *     themselves and have kernel automatically instantiate actual
-         *     device on-demand.
-         */
+        err = misc_register(&loop_misc);
+        if (err < 0)
+                return err;
 
         part_shift = 0;
         if (max_part > 0) {
@@ -1708,57 +1820,60 @@ static int __init loop_init(void)
         if (max_loop > 1UL << (MINORBITS - part_shift))
                 return -EINVAL;
 
+        /*
+         * If max_loop is specified, create that many devices upfront.
+         * This also becomes a hard limit. If max_loop is not specified,
+         * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module
+         * init time. Loop devices can be requested on-demand with the
+         * /dev/loop-control interface, or be instantiated by accessing
+         * a 'dead' device node.
+         */
         if (max_loop) {
                 nr = max_loop;
                 range = max_loop << part_shift;
         } else {
-                nr = 8;
+                nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT;
                 range = 1UL << MINORBITS;
         }
 
         if (register_blkdev(LOOP_MAJOR, "loop"))
                 return -EIO;
 
-        for (i = 0; i < nr; i++) {
-                lo = loop_alloc(i);
-                if (!lo)
-                        goto Enomem;
-                list_add_tail(&lo->lo_list, &loop_devices);
-        }
-
-        /* point of no return */
-
-        list_for_each_entry(lo, &loop_devices, lo_list)
-                add_disk(lo->lo_disk);
-
         blk_register_region(MKDEV(LOOP_MAJOR, 0), range,
                                   THIS_MODULE, loop_probe, NULL, NULL);
 
+        /* pre-create number of devices given by config or max_loop */
+        mutex_lock(&loop_index_mutex);
+        for (i = 0; i < nr; i++)
+                loop_add(&lo, i);
+        mutex_unlock(&loop_index_mutex);
+
         printk(KERN_INFO "loop: module loaded\n");
         return 0;
+}
 
-Enomem:
-        printk(KERN_INFO "loop: out of memory\n");
-
-        list_for_each_entry_safe(lo, next, &loop_devices, lo_list)
-                loop_free(lo);
+static int loop_exit_cb(int id, void *ptr, void *data)
+{
+        struct loop_device *lo = ptr;
 
-        unregister_blkdev(LOOP_MAJOR, "loop");
-        return -ENOMEM;
+        loop_remove(lo);
+        return 0;
 }
 
 static void __exit loop_exit(void)
 {
         unsigned long range;
-        struct loop_device *lo, *next;
 
         range = max_loop ? max_loop << part_shift : 1UL << MINORBITS;
 
-        list_for_each_entry_safe(lo, next, &loop_devices, lo_list)
-                loop_del_one(lo);
+        idr_for_each(&loop_index_idr, &loop_exit_cb, NULL);
+        idr_remove_all(&loop_index_idr);
+        idr_destroy(&loop_index_idr);
 
         blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);
         unregister_blkdev(LOOP_MAJOR, "loop");
+
+        misc_deregister(&loop_misc);
 }
 
 module_init(loop_init);
diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
index 2c09102adbaa..fe3c3249cec4 100644
--- a/drivers/block/rbd.c
+++ b/drivers/block/rbd.c
@@ -630,6 +630,14 @@ static int rbd_get_num_segments(struct rbd_image_header *header,
 }
 
 /*
+ * returns the size of an object in the image
+ */
+static u64 rbd_obj_bytes(struct rbd_image_header *header)
+{
+        return 1 << header->obj_order;
+}
+
+/*
  * bio helpers
  */
 
@@ -1253,6 +1261,35 @@ fail:
         return ret;
 }
 
+/*
+ * Request sync osd unwatch
+ */
+static int rbd_req_sync_unwatch(struct rbd_device *dev,
+                                const char *obj)
+{
+        struct ceph_osd_req_op *ops;
+
+        int ret = rbd_create_rw_ops(&ops, 1, CEPH_OSD_OP_WATCH, 0);
+        if (ret < 0)
+                return ret;
+
+        ops[0].watch.ver = 0;
+        ops[0].watch.cookie = cpu_to_le64(dev->watch_event->cookie);
+        ops[0].watch.flag = 0;
+
+        ret = rbd_req_sync_op(dev, NULL,
+                              CEPH_NOSNAP,
+                              0,
+                              CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ONDISK,
+                              ops,
+                              1, obj, 0, 0, NULL, NULL, NULL);
+
+        rbd_destroy_ops(ops);
+        ceph_osdc_cancel_event(dev->watch_event);
+        dev->watch_event = NULL;
+        return ret;
+}
+
 struct rbd_notify_info {
         struct rbd_device *dev;
 };
@@ -1736,6 +1773,13 @@ static int rbd_init_disk(struct rbd_device *rbd_dev)
         q = blk_init_queue(rbd_rq_fn, &rbd_dev->lock);
         if (!q)
                 goto out_disk;
+
+        /* set io sizes to object size */
+        blk_queue_max_hw_sectors(q, rbd_obj_bytes(&rbd_dev->header) / 512ULL);
+        blk_queue_max_segment_size(q, rbd_obj_bytes(&rbd_dev->header));
+        blk_queue_io_min(q, rbd_obj_bytes(&rbd_dev->header));
+        blk_queue_io_opt(q, rbd_obj_bytes(&rbd_dev->header));
+
         blk_queue_merge_bvec(q, rbd_merge_bvec);
         disk->queue = q;
 
@@ -2290,7 +2334,7 @@ static void rbd_dev_release(struct device *dev)
                 ceph_osdc_unregister_linger_request(&rbd_dev->client->osdc,
                                                     rbd_dev->watch_request);
         if (rbd_dev->watch_event)
-                ceph_osdc_cancel_event(rbd_dev->watch_event);
+                rbd_req_sync_unwatch(rbd_dev, rbd_dev->obj_md_name);
 
         rbd_put_client(rbd_dev);
 
diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c
index 773bfa792777..ae3e167e17ad 100644
--- a/drivers/block/swim3.c
+++ b/drivers/block/swim3.c
@@ -1184,6 +1184,7 @@ static struct of_device_id swim3_match[] =
         {
         .compatible     = "swim3"
         },
+        { /* end of list */ }
 };
 
 static struct macio_driver swim3_driver =
diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
index b536a9cef917..9ea8c2576c70 100644
--- a/drivers/block/xen-blkfront.c
+++ b/drivers/block/xen-blkfront.c
@@ -123,8 +123,8 @@ static DEFINE_SPINLOCK(minor_lock);
 #define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED))
 #define EMULATED_HD_DISK_MINOR_OFFSET (0)
 #define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256)
-#define EMULATED_SD_DISK_MINOR_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET + (4 * 16))
-#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_HD_DISK_NAME_OFFSET + 4)
+#define EMULATED_SD_DISK_MINOR_OFFSET (0)
+#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_SD_DISK_MINOR_OFFSET / 256)
 
 #define DEV_NAME        "xvd"   /* name in /dev */
 
@@ -529,7 +529,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
                 minor = BLKIF_MINOR_EXT(info->vdevice);
                 nr_parts = PARTS_PER_EXT_DISK;
                 offset = minor / nr_parts;
-                if (xen_hvm_domain() && offset <= EMULATED_HD_DISK_NAME_OFFSET + 4)
+                if (xen_hvm_domain() && offset < EMULATED_HD_DISK_NAME_OFFSET + 4)
                         printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with "
                                         "emulated IDE disks,\n\t choose an xvd device name"
                                         "from xvde on\n", info->vdevice);