#include <linux/mutex.h>
#include <linux/idr.h>
#include <linux/log2.h>
+#include <linux/ctype.h>
#include "blk.h"
disk->slave_dir = kobject_create_and_add("slaves", &ddev->kobj);
/* No minors to use for partitions */
- if (!disk_partitionable(disk))
+ if (!disk_part_scan_enabled(disk))
goto exit;
/* No such device (e.g., media were just removed) */
register_disk(disk);
blk_register_queue(disk);
+ /*
+ * Take an extra ref on queue which will be put on disk_release()
+ * so that it sticks around as long as @disk is there.
+ */
+ WARN_ON_ONCE(blk_get_queue(disk->queue));
+
retval = sysfs_create_link(&disk_to_dev(disk)->kobj, &bdi->dev->kobj,
"bdi");
WARN_ON(retval);
char buf[BDEVNAME_SIZE];
/* Don't show non-partitionable removeable devices or empty devices */
- if (!get_capacity(sgp) || (!disk_partitionable(sgp) &&
+ if (!get_capacity(sgp) || (!disk_max_parts(sgp) &&
(sgp->flags & GENHD_FL_REMOVABLE)))
return 0;
if (sgp->flags & GENHD_FL_SUPPRESS_PARTITION_INFO)
subsys_initcall(genhd_device_init);
+static ssize_t alias_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct gendisk *disk = dev_to_disk(dev);
+ ssize_t ret = 0;
+
+ if (disk->alias)
+ ret = snprintf(buf, ALIAS_LEN, "%s\n", disk->alias);
+ return ret;
+}
+
+static ssize_t alias_store(struct device *dev, struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct gendisk *disk = dev_to_disk(dev);
+ char *alias;
+ char *envp[] = { NULL, NULL };
+ unsigned char c;
+ int i;
+ ssize_t ret = count;
+
+ if (!count)
+ return -EINVAL;
+
+ if (count >= ALIAS_LEN) {
+ printk(KERN_ERR "alias: alias is too long\n");
+ return -EINVAL;
+ }
+
+ /* Validation check */
+ for (i = 0; i < count; i++) {
+ c = buf[i];
+ if (i == count - 1 && c == '\n')
+ break;
+ if (!isalnum(c) && c != '_' && c != '-') {
+ printk(KERN_ERR "alias: invalid alias\n");
+ return -EINVAL;
+ }
+ }
+
+ if (disk->alias) {
+ printk(KERN_INFO "alias: %s is already assigned (%s)\n",
+ disk->disk_name, disk->alias);
+ return -EINVAL;
+ }
+
+ alias = kasprintf(GFP_KERNEL, "%s", buf);
+ if (!alias)
+ return -ENOMEM;
+
+ if (alias[count - 1] == '\n')
+ alias[count - 1] = '\0';
+
+ envp[0] = kasprintf(GFP_KERNEL, "ALIAS=%s", alias);
+ if (!envp[0]) {
+ kfree(alias);
+ return -ENOMEM;
+ }
+
+ disk->alias = alias;
+ printk(KERN_INFO "alias: assigned %s to %s\n", alias, disk->disk_name);
+
+ kobject_uevent_env(&dev->kobj, KOBJ_ADD, envp);
+
+ kfree(envp[0]);
+ return ret;
+}
+
static ssize_t disk_range_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue));
}
+static DEVICE_ATTR(alias, S_IRUGO|S_IWUSR, alias_show, alias_store);
static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
#endif
static struct attribute *disk_attrs[] = {
+ &dev_attr_alias.attr,
&dev_attr_range.attr,
&dev_attr_ext_range.attr,
&dev_attr_removable.attr,
disk_replace_part_tbl(disk, NULL);
free_part_stats(&disk->part0);
free_part_info(&disk->part0);
+ if (disk->queue)
+ blk_put_queue(disk->queue);
kfree(disk);
}
struct class block_class = {
cpu = part_stat_lock();
part_round_stats(cpu, hd);
part_stat_unlock();
- seq_printf(seqf, "%4d %7d %s %lu %lu %llu "
- "%u %lu %lu %llu %u %u %u %u\n",
+ seq_printf(seqf, "%4d %7d %s %lu %lu %lu "
+ "%u %lu %lu %lu %u %u %u %u\n",
MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
disk_name(gp, hd->partno, buf),
part_stat_read(hd, ios[READ]),
part_stat_read(hd, merges[READ]),
- (unsigned long long)part_stat_read(hd, sectors[READ]),
+ part_stat_read(hd, sectors[READ]),
jiffies_to_msecs(part_stat_read(hd, ticks[READ])),
part_stat_read(hd, ios[WRITE]),
part_stat_read(hd, merges[WRITE]),
- (unsigned long long)part_stat_read(hd, sectors[WRITE]),
+ part_stat_read(hd, sectors[WRITE]),
jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])),
part_in_flight(hd),
jiffies_to_msecs(part_stat_read(hd, io_ticks)),
#include <linux/kthread.h>
#include <linux/splice.h>
#include <linux/sysfs.h>
+#include <linux/miscdevice.h>
+ #include <linux/falloc.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;
return lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock);
}
-/**
- * do_lo_send_aops - helper for writing data to a loop device
- *
- * This is the fast version for backing filesystems which implement the address
- * space operations write_begin and write_end.
- */
-static int do_lo_send_aops(struct loop_device *lo, struct bio_vec *bvec,
- loff_t pos, struct page *unused)
-{
- struct file *file = lo->lo_backing_file; /* kudos to NFsckingS */
- struct address_space *mapping = file->f_mapping;
- pgoff_t index;
- unsigned offset, bv_offs;
- int len, ret;
-
- mutex_lock(&mapping->host->i_mutex);
- index = pos >> PAGE_CACHE_SHIFT;
- offset = pos & ((pgoff_t)PAGE_CACHE_SIZE - 1);
- bv_offs = bvec->bv_offset;
- len = bvec->bv_len;
- while (len > 0) {
- sector_t IV;
- unsigned size, copied;
- int transfer_result;
- struct page *page;
- void *fsdata;
-
- IV = ((sector_t)index << (PAGE_CACHE_SHIFT - 9))+(offset >> 9);
- size = PAGE_CACHE_SIZE - offset;
- if (size > len)
- size = len;
-
- ret = pagecache_write_begin(file, mapping, pos, size, 0,
- &page, &fsdata);
- if (ret)
- goto fail;
-
- file_update_time(file);
-
- transfer_result = lo_do_transfer(lo, WRITE, page, offset,
- bvec->bv_page, bv_offs, size, IV);
- copied = size;
- if (unlikely(transfer_result))
- copied = 0;
-
- ret = pagecache_write_end(file, mapping, pos, size, copied,
- page, fsdata);
- if (ret < 0 || ret != copied)
- goto fail;
-
- if (unlikely(transfer_result))
- goto fail;
-
- bv_offs += copied;
- len -= copied;
- offset = 0;
- index++;
- pos += copied;
- }
- ret = 0;
-out:
- mutex_unlock(&mapping->host->i_mutex);
- return ret;
-fail:
- ret = -1;
- goto out;
-}
-
/**
* __do_lo_send_write - helper for writing data to a loop device
*
/**
* do_lo_send_direct_write - helper for writing data to a loop device
*
- * This is the fast, non-transforming version for backing filesystems which do
- * not implement the address space operations write_begin and write_end.
- * It uses the write file operation which should be present on all writeable
- * filesystems.
+ * This is the fast, non-transforming version that does not need double
+ * buffering.
*/
static int do_lo_send_direct_write(struct loop_device *lo,
struct bio_vec *bvec, loff_t pos, struct page *page)
/**
* do_lo_send_write - helper for writing data to a loop device
*
- * This is the slow, transforming version for filesystems which do not
- * implement the address space operations write_begin and write_end. It
- * uses the write file operation which should be present on all writeable
- * filesystems.
- *
- * Using fops->write is slower than using aops->{prepare,commit}_write in the
- * transforming case because we need to double buffer the data as we cannot do
- * the transformations in place as we do not have direct access to the
- * destination pages of the backing file.
+ * This is the slow, transforming version that needs to double buffer the
+ * data as it cannot do the transformations in place without having direct
+ * access to the destination pages of the backing file.
*/
static int do_lo_send_write(struct loop_device *lo, struct bio_vec *bvec,
loff_t pos, struct page *page)
struct page *page = NULL;
int i, ret = 0;
- do_lo_send = do_lo_send_aops;
- if (!(lo->lo_flags & LO_FLAGS_USE_AOPS)) {
+ if (lo->transfer != transfer_none) {
+ page = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
+ if (unlikely(!page))
+ goto fail;
+ kmap(page);
+ do_lo_send = do_lo_send_write;
+ } else {
do_lo_send = do_lo_send_direct_write;
- if (lo->transfer != transfer_none) {
- page = alloc_page(GFP_NOIO | __GFP_HIGHMEM);
- if (unlikely(!page))
- goto fail;
- kmap(page);
- do_lo_send = do_lo_send_write;
- }
}
+
bio_for_each_segment(bvec, bio, i) {
ret = do_lo_send(lo, bvec, pos, page);
if (ret < 0)
}
}
+ /*
+ * We use punch hole to reclaim the free space used by the
+ * image a.k.a. discard. However we do support discard if
+ * encryption is enabled, because it may give an attacker
+ * useful information.
+ */
+ if (bio->bi_rw & REQ_DISCARD) {
+ struct file *file = lo->lo_backing_file;
+ int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
+
+ if ((!file->f_op->fallocate) ||
+ lo->lo_encrypt_key_size) {
+ ret = -EOPNOTSUPP;
+ goto out;
+ }
+ ret = file->f_op->fallocate(file, mode, pos,
+ bio->bi_size);
+ if (unlikely(ret && ret != -EINVAL &&
+ ret != -EOPNOTSUPP))
+ ret = -EIO;
+ goto out;
+ }
+
ret = lo_send(lo, bio, pos);
if ((bio->bi_rw & REQ_FUA) && !ret) {
return bio_list_pop(&lo->lo_bio_list);
}
-static int loop_make_request(struct request_queue *q, struct bio *old_bio)
+static void loop_make_request(struct request_queue *q, struct bio *old_bio)
{
struct loop_device *lo = q->queuedata;
int rw = bio_rw(old_bio);
loop_add_bio(lo, old_bio);
wake_up(&lo->lo_event);
spin_unlock_irq(&lo->lo_lock);
- return 0;
+ return;
out:
spin_unlock_irq(&lo->lo_lock);
bio_io_error(old_bio);
- return 0;
}
struct switch_request {
goto out_putf;
fput(old_file);
- if (max_part > 0)
+ if (lo->lo_flags & LO_FLAGS_PARTSCAN)
ioctl_by_bdev(bdev, BLKRRPART, 0);
return 0;
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) \
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);
return sprintf(buf, "%s\n", autoclear ? "1" : "0");
}
+ static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
+ {
+ int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN);
+
+ return sprintf(buf, "%s\n", partscan ? "1" : "0");
+ }
+
LOOP_ATTR_RO(backing_file);
LOOP_ATTR_RO(offset);
LOOP_ATTR_RO(sizelimit);
LOOP_ATTR_RO(autoclear);
+ LOOP_ATTR_RO(partscan);
static struct attribute *loop_attrs[] = {
&loop_attr_backing_file.attr,
&loop_attr_offset.attr,
&loop_attr_sizelimit.attr,
&loop_attr_autoclear.attr,
+ &loop_attr_partscan.attr,
NULL,
};
&loop_attribute_group);
}
+ static void loop_config_discard(struct loop_device *lo)
+ {
+ struct file *file = lo->lo_backing_file;
+ struct inode *inode = file->f_mapping->host;
+ struct request_queue *q = lo->lo_queue;
+
+ /*
+ * We use punch hole to reclaim the free space used by the
+ * image a.k.a. discard. However we do support discard if
+ * encryption is enabled, because it may give an attacker
+ * useful information.
+ */
+ if ((!file->f_op->fallocate) ||
+ lo->lo_encrypt_key_size) {
+ q->limits.discard_granularity = 0;
+ q->limits.discard_alignment = 0;
+ q->limits.max_discard_sectors = 0;
+ q->limits.discard_zeroes_data = 0;
+ queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
+ return;
+ }
+
+ q->limits.discard_granularity = inode->i_sb->s_blocksize;
+ q->limits.discard_alignment = inode->i_sb->s_blocksize;
+ q->limits.max_discard_sectors = UINT_MAX >> 9;
+ q->limits.discard_zeroes_data = 1;
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
+ }
+
static int loop_set_fd(struct loop_device *lo, fmode_t mode,
struct block_device *bdev, unsigned int arg)
{
mapping = file->f_mapping;
inode = mapping->host;
- if (!(file->f_mode & FMODE_WRITE))
- lo_flags |= LO_FLAGS_READ_ONLY;
-
error = -EINVAL;
- if (S_ISREG(inode->i_mode) || S_ISBLK(inode->i_mode)) {
- const struct address_space_operations *aops = mapping->a_ops;
-
- if (aops->write_begin)
- lo_flags |= LO_FLAGS_USE_AOPS;
- if (!(lo_flags & LO_FLAGS_USE_AOPS) && !file->f_op->write)
- lo_flags |= LO_FLAGS_READ_ONLY;
+ if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
+ goto out_putf;
- lo_blocksize = S_ISBLK(inode->i_mode) ?
- inode->i_bdev->bd_block_size : PAGE_SIZE;
+ if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
+ !file->f_op->write)
+ lo_flags |= LO_FLAGS_READ_ONLY;
- error = 0;
- } else {
- goto out_putf;
- }
+ lo_blocksize = S_ISBLK(inode->i_mode) ?
+ inode->i_bdev->bd_block_size : PAGE_SIZE;
+ error = -EFBIG;
size = get_loop_size(lo, file);
-
- if ((loff_t)(sector_t)size != size) {
- error = -EFBIG;
+ if ((loff_t)(sector_t)size != size)
goto out_putf;
- }
- if (!(mode & FMODE_WRITE))
- lo_flags |= LO_FLAGS_READ_ONLY;
+ error = 0;
set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);
}
lo->lo_state = Lo_bound;
wake_up_process(lo->lo_thread);
- if (max_part > 0)
+ if (part_shift)
+ lo->lo_flags |= LO_FLAGS_PARTSCAN;
+ if (lo->lo_flags & LO_FLAGS_PARTSCAN)
ioctl_by_bdev(bdev, BLKRRPART, 0);
return 0;
return err;
}
- static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev)
+ static int loop_clr_fd(struct loop_device *lo)
{
struct file *filp = lo->lo_backing_file;
gfp_t gfp = lo->old_gfp_mask;
+ struct block_device *bdev = lo->lo_device;
if (lo->lo_state != Lo_bound)
return -ENXIO;
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;
lo->lo_offset = 0;
lo->lo_sizelimit = 0;
lo->lo_encrypt_key_size = 0;
- lo->lo_flags = 0;
lo->lo_thread = NULL;
memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
lo->lo_state = Lo_unbound;
/* This is safe: open() is still holding a reference. */
module_put(THIS_MODULE);
- if (max_part > 0 && bdev)
+ if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev)
ioctl_by_bdev(bdev, BLKRRPART, 0);
+ lo->lo_flags = 0;
+ if (!part_shift)
+ lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
mutex_unlock(&lo->lo_ctl_mutex);
/*
* Need not hold lo_ctl_mutex to fput backing file.
if (figure_loop_size(lo))
return -EFBIG;
}
+ loop_config_discard(lo);
memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
(info->lo_flags & LO_FLAGS_AUTOCLEAR))
lo->lo_flags ^= LO_FLAGS_AUTOCLEAR;
+ if ((info->lo_flags & LO_FLAGS_PARTSCAN) &&
+ !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
+ lo->lo_flags |= LO_FLAGS_PARTSCAN;
+ lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
+ ioctl_by_bdev(lo->lo_device, BLKRRPART, 0);
+ }
+
lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
lo->lo_init[0] = info->lo_init[0];
lo->lo_init[1] = info->lo_init[1];
break;
case LOOP_CLR_FD:
/* loop_clr_fd would have unlocked lo_ctl_mutex on success */
- err = loop_clr_fd(lo, bdev);
+ err = loop_clr_fd(lo);
if (!err)
goto out_unlocked;
break;
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)
* In autoclear mode, stop the loop thread
* and remove configuration after last close.
*/
- err = loop_clr_fd(lo, NULL);
+ err = loop_clr_fd(lo);
if (!err)
goto out_unlocked;
} else {
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)
if (!disk)
goto out_free_queue;
+ /*
+ * Disable partition scanning by default. The in-kernel partition
+ * scanning can be requested individually per-device during its
+ * setup. Userspace can always add and remove partitions from all
+ * devices. The needed partition minors are allocated from the
+ * extended minor space, the main loop device numbers will continue
+ * to match the loop minors, regardless of the number of partitions
+ * used.
+ *
+ * If max_part is given, partition scanning is globally enabled for
+ * all loop devices. The minors for the main loop devices will be
+ * multiples of max_part.
+ *
+ * Note: Global-for-all-devices, set-only-at-init, read-only module
+ * parameteters like 'max_loop' and 'max_part' make things needlessly
+ * complicated, are too static, inflexible and may surprise
+ * userspace tools. Parameters like this in general should be avoided.
+ */
+ if (!part_shift)
+ disk->flags |= GENHD_FL_NO_PART_SCAN;
+ disk->flags |= GENHD_FL_EXT_DEVT;
mutex_init(&lo->lo_ctl_mutex);
lo->lo_number = i;
lo->lo_thread = NULL;
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) {
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);
#include <linux/list.h>
#include <linux/delay.h>
#include <linux/freezer.h>
+ #include <linux/loop.h>
+ #include <linux/falloc.h>
+ #include <linux/fs.h>
#include <xen/events.h>
#include <xen/page.h>
static void print_stats(struct xen_blkif *blkif)
{
- pr_info("xen-blkback (%s): oo %3d | rd %4d | wr %4d | f %4d\n",
+ pr_info("xen-blkback (%s): oo %3d | rd %4d | wr %4d | f %4d"
+ " | ds %4d\n",
current->comm, blkif->st_oo_req,
- blkif->st_rd_req, blkif->st_wr_req, blkif->st_f_req);
+ blkif->st_rd_req, blkif->st_wr_req,
+ blkif->st_f_req, blkif->st_ds_req);
blkif->st_print = jiffies + msecs_to_jiffies(10 * 1000);
blkif->st_rd_req = 0;
blkif->st_wr_req = 0;
blkif->st_oo_req = 0;
+ blkif->st_ds_req = 0;
}
int xen_blkif_schedule(void *arg)
continue;
ret = m2p_add_override(PFN_DOWN(map[i].dev_bus_addr),
- blkbk->pending_page(pending_req, i), false);
+ blkbk->pending_page(pending_req, i), NULL);
if (ret) {
pr_alert(DRV_PFX "Failed to install M2P override for %lx (ret: %d)\n",
(unsigned long)map[i].dev_bus_addr, ret);
return ret;
}
+ static void xen_blk_discard(struct xen_blkif *blkif, struct blkif_request *req)
+ {
+ int err = 0;
+ int status = BLKIF_RSP_OKAY;
+ struct block_device *bdev = blkif->vbd.bdev;
+
+ if (blkif->blk_backend_type == BLKIF_BACKEND_PHY)
+ /* just forward the discard request */
+ err = blkdev_issue_discard(bdev,
+ req->u.discard.sector_number,
+ req->u.discard.nr_sectors,
+ GFP_KERNEL, 0);
+ else if (blkif->blk_backend_type == BLKIF_BACKEND_FILE) {
+ /* punch a hole in the backing file */
+ struct loop_device *lo = bdev->bd_disk->private_data;
+ struct file *file = lo->lo_backing_file;
+
+ if (file->f_op->fallocate)
+ err = file->f_op->fallocate(file,
+ FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE,
+ req->u.discard.sector_number << 9,
+ req->u.discard.nr_sectors << 9);
+ else
+ err = -EOPNOTSUPP;
+ } else
+ err = -EOPNOTSUPP;
+
+ if (err == -EOPNOTSUPP) {
+ pr_debug(DRV_PFX "discard op failed, not supported\n");
+ status = BLKIF_RSP_EOPNOTSUPP;
+ } else if (err)
+ status = BLKIF_RSP_ERROR;
+
+ make_response(blkif, req->id, req->operation, status);
+ }
+
+ static void xen_blk_drain_io(struct xen_blkif *blkif)
+ {
+ atomic_set(&blkif->drain, 1);
+ do {
+ /* The initial value is one, and one refcnt taken at the
+ * start of the xen_blkif_schedule thread. */
+ if (atomic_read(&blkif->refcnt) <= 2)
+ break;
+ wait_for_completion_interruptible_timeout(
+ &blkif->drain_complete, HZ);
+
+ if (!atomic_read(&blkif->drain))
+ break;
+ } while (!kthread_should_stop());
+ atomic_set(&blkif->drain, 0);
+ }
+
/*
* Completion callback on the bio's. Called as bh->b_end_io()
*/
pr_debug(DRV_PFX "flush diskcache op failed, not supported\n");
xen_blkbk_flush_diskcache(XBT_NIL, pending_req->blkif->be, 0);
pending_req->status = BLKIF_RSP_EOPNOTSUPP;
+ } else if ((pending_req->operation == BLKIF_OP_WRITE_BARRIER) &&
+ (error == -EOPNOTSUPP)) {
+ pr_debug(DRV_PFX "write barrier op failed, not supported\n");
+ xen_blkbk_barrier(XBT_NIL, pending_req->blkif->be, 0);
+ pending_req->status = BLKIF_RSP_EOPNOTSUPP;
} else if (error) {
pr_debug(DRV_PFX "Buffer not up-to-date at end of operation,"
" error=%d\n", error);
make_response(pending_req->blkif, pending_req->id,
pending_req->operation, pending_req->status);
xen_blkif_put(pending_req->blkif);
+ if (atomic_read(&pending_req->blkif->refcnt) <= 2) {
+ if (atomic_read(&pending_req->blkif->drain))
+ complete(&pending_req->blkif->drain_complete);
+ }
free_req(pending_req);
}
}
return more_to_do;
}
-
/*
* Transmutation of the 'struct blkif_request' to a proper 'struct bio'
* and call the 'submit_bio' to pass it to the underlying storage.
int i, nbio = 0;
int operation;
struct blk_plug plug;
+ bool drain = false;
switch (req->operation) {
case BLKIF_OP_READ:
blkif->st_wr_req++;
operation = WRITE_ODIRECT;
break;
+ case BLKIF_OP_WRITE_BARRIER:
+ drain = true;
case BLKIF_OP_FLUSH_DISKCACHE:
blkif->st_f_req++;
operation = WRITE_FLUSH;
break;
- case BLKIF_OP_WRITE_BARRIER:
+ case BLKIF_OP_DISCARD:
+ blkif->st_ds_req++;
+ operation = REQ_DISCARD;
+ break;
default:
operation = 0; /* make gcc happy */
goto fail_response;
/* Check that the number of segments is sane. */
nseg = req->nr_segments;
- if (unlikely(nseg == 0 && operation != WRITE_FLUSH) ||
+ if (unlikely(nseg == 0 && operation != WRITE_FLUSH &&
+ operation != REQ_DISCARD) ||
unlikely(nseg > BLKIF_MAX_SEGMENTS_PER_REQUEST)) {
pr_debug(DRV_PFX "Bad number of segments in request (%d)\n",
nseg);
}
}
+ /* Wait on all outstanding I/O's and once that has been completed
+ * issue the WRITE_FLUSH.
+ */
+ if (drain)
+ xen_blk_drain_io(pending_req->blkif);
+
/*
* If we have failed at this point, we need to undo the M2P override,
* set gnttab_set_unmap_op on all of the grant references and perform
* the hypercall to unmap the grants - that is all done in
* xen_blkbk_unmap.
*/
- if (xen_blkbk_map(req, pending_req, seg))
+ if (operation != REQ_DISCARD && xen_blkbk_map(req, pending_req, seg))
goto fail_flush;
- /* This corresponding xen_blkif_put is done in __end_block_io_op */
+ /*
+ * This corresponding xen_blkif_put is done in __end_block_io_op, or
+ * below (in "!bio") if we are handling a BLKIF_OP_DISCARD.
+ */
xen_blkif_get(blkif);
for (i = 0; i < nseg; i++) {
preq.sector_number += seg[i].nsec;
}
- /* This will be hit if the operation was a flush. */
+ /* This will be hit if the operation was a flush or discard. */
if (!bio) {
- BUG_ON(operation != WRITE_FLUSH);
+ BUG_ON(operation != WRITE_FLUSH && operation != REQ_DISCARD);
- bio = bio_alloc(GFP_KERNEL, 0);
- if (unlikely(bio == NULL))
- goto fail_put_bio;
+ if (operation == WRITE_FLUSH) {
+ bio = bio_alloc(GFP_KERNEL, 0);
+ if (unlikely(bio == NULL))
+ goto fail_put_bio;
- biolist[nbio++] = bio;
- bio->bi_bdev = preq.bdev;
- bio->bi_private = pending_req;
- bio->bi_end_io = end_block_io_op;
+ biolist[nbio++] = bio;
+ bio->bi_bdev = preq.bdev;
+ bio->bi_private = pending_req;
+ bio->bi_end_io = end_block_io_op;
+ } else if (operation == REQ_DISCARD) {
+ xen_blk_discard(blkif, req);
+ xen_blkif_put(blkif);
+ free_req(pending_req);
+ return 0;
+ }
}
/*
if (operation == READ)
blkif->st_rd_sect += preq.nr_sects;
- else if (operation == WRITE || operation == WRITE_FLUSH)
+ else if (operation & WRITE)
blkif->st_wr_sect += preq.nr_sects;
return 0;
mmap_pages = xen_blkif_reqs * BLKIF_MAX_SEGMENTS_PER_REQUEST;
- blkbk->pending_reqs = kmalloc(sizeof(blkbk->pending_reqs[0]) *
+ blkbk->pending_reqs = kzalloc(sizeof(blkbk->pending_reqs[0]) *
xen_blkif_reqs, GFP_KERNEL);
- blkbk->pending_grant_handles = kzalloc(sizeof(blkbk->pending_grant_handles[0]) *
+ blkbk->pending_grant_handles = kmalloc(sizeof(blkbk->pending_grant_handles[0]) *
mmap_pages, GFP_KERNEL);
blkbk->pending_pages = kzalloc(sizeof(blkbk->pending_pages[0]) *
mmap_pages, GFP_KERNEL);
if (rc)
goto failed_init;
- memset(blkbk->pending_reqs, 0, sizeof(blkbk->pending_reqs));
-
INIT_LIST_HEAD(&blkbk->pending_free);
spin_lock_init(&blkbk->pending_free_lock);
init_waitqueue_head(&blkbk->pending_free_wq);
#ifndef __XEN_BLKIF__BACKEND__COMMON_H__
#define __XEN_BLKIF__BACKEND__COMMON_H__
-#include <linux/version.h>
#include <linux/module.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
/* i386 protocol version */
#pragma pack(push, 4)
+
+ struct blkif_x86_32_request_rw {
+ blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */
+ struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ };
+
+ struct blkif_x86_32_request_discard {
+ blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */
+ uint64_t nr_sectors;
+ };
+
struct blkif_x86_32_request {
uint8_t operation; /* BLKIF_OP_??? */
uint8_t nr_segments; /* number of segments */
blkif_vdev_t handle; /* only for read/write requests */
uint64_t id; /* private guest value, echoed in resp */
- blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */
- struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ union {
+ struct blkif_x86_32_request_rw rw;
+ struct blkif_x86_32_request_discard discard;
+ } u;
};
struct blkif_x86_32_response {
uint64_t id; /* copied from request */
#pragma pack(pop)
/* x86_64 protocol version */
+
+ struct blkif_x86_64_request_rw {
+ blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */
+ struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ };
+
+ struct blkif_x86_64_request_discard {
+ blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */
+ uint64_t nr_sectors;
+ };
+
struct blkif_x86_64_request {
uint8_t operation; /* BLKIF_OP_??? */
uint8_t nr_segments; /* number of segments */
blkif_vdev_t handle; /* only for read/write requests */
uint64_t __attribute__((__aligned__(8))) id;
- blkif_sector_t sector_number;/* start sector idx on disk (r/w only) */
- struct blkif_request_segment seg[BLKIF_MAX_SEGMENTS_PER_REQUEST];
+ union {
+ struct blkif_x86_64_request_rw rw;
+ struct blkif_x86_64_request_discard discard;
+ } u;
};
struct blkif_x86_64_response {
uint64_t __attribute__((__aligned__(8))) id;
BLKIF_PROTOCOL_X86_64 = 3,
};
+ enum blkif_backend_type {
+ BLKIF_BACKEND_PHY = 1,
+ BLKIF_BACKEND_FILE = 2,
+ };
+
struct xen_vbd {
/* What the domain refers to this vbd as. */
blkif_vdev_t handle;
unsigned int irq;
/* Comms information. */
enum blkif_protocol blk_protocol;
+ enum blkif_backend_type blk_backend_type;
union blkif_back_rings blk_rings;
struct vm_struct *blk_ring_area;
/* The VBD attached to this interface. */
atomic_t refcnt;
wait_queue_head_t wq;
+ /* for barrier (drain) requests */
+ struct completion drain_complete;
+ atomic_t drain;
/* One thread per one blkif. */
struct task_struct *xenblkd;
unsigned int waiting_reqs;
int st_wr_req;
int st_oo_req;
int st_f_req;
+ int st_ds_req;
int st_rd_sect;
int st_wr_sect;
struct phys_req {
unsigned short dev;
- unsigned short nr_sects;
+ blkif_sector_t nr_sects;
struct block_device *bdev;
blkif_sector_t sector_number;
};
int xen_blkbk_flush_diskcache(struct xenbus_transaction xbt,
struct backend_info *be, int state);
+ int xen_blkbk_barrier(struct xenbus_transaction xbt,
+ struct backend_info *be, int state);
struct xenbus_device *xen_blkbk_xenbus(struct backend_info *be);
static inline void blkif_get_x86_32_req(struct blkif_request *dst,
dst->nr_segments = src->nr_segments;
dst->handle = src->handle;
dst->id = src->id;
- dst->u.rw.sector_number = src->sector_number;
- barrier();
- if (n > dst->nr_segments)
- n = dst->nr_segments;
- for (i = 0; i < n; i++)
- dst->u.rw.seg[i] = src->seg[i];
+ switch (src->operation) {
+ case BLKIF_OP_READ:
+ case BLKIF_OP_WRITE:
+ case BLKIF_OP_WRITE_BARRIER:
+ case BLKIF_OP_FLUSH_DISKCACHE:
+ dst->u.rw.sector_number = src->u.rw.sector_number;
+ barrier();
+ if (n > dst->nr_segments)
+ n = dst->nr_segments;
+ for (i = 0; i < n; i++)
+ dst->u.rw.seg[i] = src->u.rw.seg[i];
+ break;
+ case BLKIF_OP_DISCARD:
+ dst->u.discard.sector_number = src->u.discard.sector_number;
+ dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
+ break;
+ default:
+ break;
+ }
}
static inline void blkif_get_x86_64_req(struct blkif_request *dst,
dst->nr_segments = src->nr_segments;
dst->handle = src->handle;
dst->id = src->id;
- dst->u.rw.sector_number = src->sector_number;
- barrier();
- if (n > dst->nr_segments)
- n = dst->nr_segments;
- for (i = 0; i < n; i++)
- dst->u.rw.seg[i] = src->seg[i];
+ switch (src->operation) {
+ case BLKIF_OP_READ:
+ case BLKIF_OP_WRITE:
+ case BLKIF_OP_WRITE_BARRIER:
+ case BLKIF_OP_FLUSH_DISKCACHE:
+ dst->u.rw.sector_number = src->u.rw.sector_number;
+ barrier();
+ if (n > dst->nr_segments)
+ n = dst->nr_segments;
+ for (i = 0; i < n; i++)
+ dst->u.rw.seg[i] = src->u.rw.seg[i];
+ break;
+ case BLKIF_OP_DISCARD:
+ dst->u.discard.sector_number = src->u.discard.sector_number;
+ dst->u.discard.nr_sectors = src->u.discard.nr_sectors;
+ break;
+ default:
+ break;
+ }
}
#endif /* __XEN_BLKIF__BACKEND__COMMON_H__ */
spin_lock_init(&blkif->blk_ring_lock);
atomic_set(&blkif->refcnt, 1);
init_waitqueue_head(&blkif->wq);
+ init_completion(&blkif->drain_complete);
+ atomic_set(&blkif->drain, 0);
blkif->st_print = jiffies;
init_waitqueue_head(&blkif->waiting_to_free);
VBD_SHOW(rd_req, "%d\n", be->blkif->st_rd_req);
VBD_SHOW(wr_req, "%d\n", be->blkif->st_wr_req);
VBD_SHOW(f_req, "%d\n", be->blkif->st_f_req);
+ VBD_SHOW(ds_req, "%d\n", be->blkif->st_ds_req);
VBD_SHOW(rd_sect, "%d\n", be->blkif->st_rd_sect);
VBD_SHOW(wr_sect, "%d\n", be->blkif->st_wr_sect);
&dev_attr_rd_req.attr,
&dev_attr_wr_req.attr,
&dev_attr_f_req.attr,
+ &dev_attr_ds_req.attr,
&dev_attr_rd_sect.attr,
&dev_attr_wr_sect.attr,
NULL
return err;
}
+ int xen_blkbk_discard(struct xenbus_transaction xbt, struct backend_info *be)
+ {
+ struct xenbus_device *dev = be->dev;
+ struct xen_blkif *blkif = be->blkif;
+ char *type;
+ int err;
+ int state = 0;
+
+ type = xenbus_read(XBT_NIL, dev->nodename, "type", NULL);
+ if (!IS_ERR(type)) {
+ if (strncmp(type, "file", 4) == 0) {
+ state = 1;
+ blkif->blk_backend_type = BLKIF_BACKEND_FILE;
+ }
+ if (strncmp(type, "phy", 3) == 0) {
+ struct block_device *bdev = be->blkif->vbd.bdev;
+ struct request_queue *q = bdev_get_queue(bdev);
+ if (blk_queue_discard(q)) {
+ err = xenbus_printf(xbt, dev->nodename,
+ "discard-granularity", "%u",
+ q->limits.discard_granularity);
+ if (err) {
+ xenbus_dev_fatal(dev, err,
+ "writing discard-granularity");
+ goto kfree;
+ }
+ err = xenbus_printf(xbt, dev->nodename,
+ "discard-alignment", "%u",
+ q->limits.discard_alignment);
+ if (err) {
+ xenbus_dev_fatal(dev, err,
+ "writing discard-alignment");
+ goto kfree;
+ }
+ state = 1;
+ blkif->blk_backend_type = BLKIF_BACKEND_PHY;
+ }
+ }
+ } else {
+ err = PTR_ERR(type);
+ xenbus_dev_fatal(dev, err, "reading type");
+ goto out;
+ }
+
+ err = xenbus_printf(xbt, dev->nodename, "feature-discard",
+ "%d", state);
+ if (err)
+ xenbus_dev_fatal(dev, err, "writing feature-discard");
+ kfree:
+ kfree(type);
+ out:
+ return err;
+ }
+ int xen_blkbk_barrier(struct xenbus_transaction xbt,
+ struct backend_info *be, int state)
+ {
+ struct xenbus_device *dev = be->dev;
+ int err;
+
+ err = xenbus_printf(xbt, dev->nodename, "feature-barrier",
+ "%d", state);
+ if (err)
+ xenbus_dev_fatal(dev, err, "writing feature-barrier");
+
+ return err;
+ }
+
/*
* Entry point to this code when a new device is created. Allocate the basic
* structures, and watch the store waiting for the hotplug scripts to tell us
break;
case XenbusStateClosing:
- xen_blkif_disconnect(be->blkif);
xenbus_switch_state(dev, XenbusStateClosing);
break;
case XenbusStateClosed:
+ xen_blkif_disconnect(be->blkif);
xenbus_switch_state(dev, XenbusStateClosed);
if (xenbus_dev_is_online(dev))
break;
if (err)
goto abort;
+ err = xen_blkbk_discard(xbt, be);
+
+ /* If we can't advertise it is OK. */
+ err = xen_blkbk_barrier(xbt, be, be->blkif->vbd.flush_support);
+
err = xenbus_printf(xbt, dev->nodename, "sectors", "%llu",
(unsigned long long)vbd_sz(&be->blkif->vbd));
if (err) {
unsigned long shadow_free;
unsigned int feature_flush;
unsigned int flush_op;
+ unsigned int feature_discard;
+ unsigned int discard_granularity;
+ unsigned int discard_alignment;
int is_ready;
};
#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 */
ring_req->operation = info->flush_op;
}
- ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg);
- BUG_ON(ring_req->nr_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);
+ if (unlikely(req->cmd_flags & REQ_DISCARD)) {
+ /* id, sector_number and handle are set above. */
+ ring_req->operation = BLKIF_OP_DISCARD;
+ ring_req->nr_segments = 0;
+ ring_req->u.discard.nr_sectors = blk_rq_sectors(req);
+ } else {
+ ring_req->nr_segments = blk_rq_map_sg(req->q, req, info->sg);
+ BUG_ON(ring_req->nr_segments > BLKIF_MAX_SEGMENTS_PER_REQUEST);
- for_each_sg(info->sg, sg, ring_req->nr_segments, i) {
- buffer_mfn = pfn_to_mfn(page_to_pfn(sg_page(sg)));
- fsect = sg->offset >> 9;
- lsect = fsect + (sg->length >> 9) - 1;
- /* install a grant reference. */
- ref = gnttab_claim_grant_reference(&gref_head);
- BUG_ON(ref == -ENOSPC);
+ for_each_sg(info->sg, sg, ring_req->nr_segments, i) {
+ buffer_mfn = pfn_to_mfn(page_to_pfn(sg_page(sg)));
+ fsect = sg->offset >> 9;
+ lsect = fsect + (sg->length >> 9) - 1;
+ /* install a grant reference. */
+ ref = gnttab_claim_grant_reference(&gref_head);
+ BUG_ON(ref == -ENOSPC);
- gnttab_grant_foreign_access_ref(
- ref,
- info->xbdev->otherend_id,
- buffer_mfn,
- rq_data_dir(req) );
-
- info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn);
- ring_req->u.rw.seg[i] =
- (struct blkif_request_segment) {
- .gref = ref,
- .first_sect = fsect,
- .last_sect = lsect };
+ gnttab_grant_foreign_access_ref(
+ ref,
+ info->xbdev->otherend_id,
+ buffer_mfn,
+ rq_data_dir(req));
+
+ info->shadow[id].frame[i] = mfn_to_pfn(buffer_mfn);
+ ring_req->u.rw.seg[i] =
+ (struct blkif_request_segment) {
+ .gref = ref,
+ .first_sect = fsect,
+ .last_sect = lsect };
+ }
}
info->ring.req_prod_pvt++;
blk_start_request(req);
- if (req->cmd_type != REQ_TYPE_FS) {
+ if ((req->cmd_type != REQ_TYPE_FS) ||
+ ((req->cmd_flags & (REQ_FLUSH | REQ_FUA)) &&
+ !info->flush_op)) {
__blk_end_request_all(req, -EIO);
continue;
}
static int xlvbd_init_blk_queue(struct gendisk *gd, u16 sector_size)
{
struct request_queue *rq;
+ struct blkfront_info *info = gd->private_data;
rq = blk_init_queue(do_blkif_request, &blkif_io_lock);
if (rq == NULL)
queue_flag_set_unlocked(QUEUE_FLAG_VIRT, rq);
+ if (info->feature_discard) {
+ queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, rq);
+ blk_queue_max_discard_sectors(rq, get_capacity(gd));
+ rq->limits.discard_granularity = info->discard_granularity;
+ rq->limits.discard_alignment = info->discard_alignment;
+ }
+
/* Hard sector size and max sectors impersonate the equiv. hardware. */
blk_queue_logical_block_size(rq, sector_size);
blk_queue_max_hw_sectors(rq, 512);
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);
error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO;
switch (bret->operation) {
+ case BLKIF_OP_DISCARD:
+ if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
+ struct request_queue *rq = info->rq;
+ printk(KERN_WARNING "blkfront: %s: discard op failed\n",
+ info->gd->disk_name);
+ error = -EOPNOTSUPP;
+ info->feature_discard = 0;
+ queue_flag_clear(QUEUE_FLAG_DISCARD, rq);
+ }
+ __blk_end_request_all(req, error);
+ break;
case BLKIF_OP_FLUSH_DISKCACHE:
case BLKIF_OP_WRITE_BARRIER:
if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) {
bdput(bdev);
}
+ static void blkfront_setup_discard(struct blkfront_info *info)
+ {
+ int err;
+ char *type;
+ unsigned int discard_granularity;
+ unsigned int discard_alignment;
+
+ type = xenbus_read(XBT_NIL, info->xbdev->otherend, "type", NULL);
+ if (IS_ERR(type))
+ return;
+
+ if (strncmp(type, "phy", 3) == 0) {
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "discard-granularity", "%u", &discard_granularity,
+ "discard-alignment", "%u", &discard_alignment,
+ NULL);
+ if (!err) {
+ info->feature_discard = 1;
+ info->discard_granularity = discard_granularity;
+ info->discard_alignment = discard_alignment;
+ }
+ } else if (strncmp(type, "file", 4) == 0)
+ info->feature_discard = 1;
+
+ kfree(type);
+ }
+
/*
* Invoked when the backend is finally 'ready' (and has told produced
* the details about the physical device - #sectors, size, etc).
unsigned long sector_size;
unsigned int binfo;
int err;
- int barrier, flush;
+ int barrier, flush, discard;
switch (info->connected) {
case BLKIF_STATE_CONNECTED:
info->feature_flush = REQ_FLUSH;
info->flush_op = BLKIF_OP_FLUSH_DISKCACHE;
}
-
+
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "feature-discard", "%d", &discard,
+ NULL);
+
+ if (!err && discard)
+ blkfront_setup_discard(info);
+
err = xlvbd_alloc_gendisk(sectors, info, binfo, sector_size);
if (err) {
xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
static int __init xlblk_init(void)
{
+ int ret;
+
if (!xen_domain())
return -ENODEV;
return -ENODEV;
}
- return xenbus_register_frontend(&blkfront);
+ ret = xenbus_register_frontend(&blkfront);
+ if (ret) {
+ unregister_blkdev(XENVBD_MAJOR, DEV_NAME);
+ return ret;
+ }
+
+ return 0;
}
module_init(xlblk_init);
BUG_ON(entry < 0 || entry >= HPSA_MAX_SCSI_DEVS_PER_HBA);
removed[*nremoved] = h->dev[entry];
(*nremoved)++;
+
+ /*
+ * New physical devices won't have target/lun assigned yet
+ * so we need to preserve the values in the slot we are replacing.
+ */
+ if (new_entry->target == -1) {
+ new_entry->target = h->dev[entry]->target;
+ new_entry->lun = h->dev[entry]->lun;
+ }
+
h->dev[entry] = new_entry;
added[*nadded] = new_entry;
(*nadded)++;
}
static int hpsa_update_device_info(struct ctlr_info *h,
- unsigned char scsi3addr[], struct hpsa_scsi_dev_t *this_device)
+ unsigned char scsi3addr[], struct hpsa_scsi_dev_t *this_device,
+ unsigned char *is_OBDR_device)
{
-#define OBDR_TAPE_INQ_SIZE 49
+
+#define OBDR_SIG_OFFSET 43
+#define OBDR_TAPE_SIG "$DR-10"
+#define OBDR_SIG_LEN (sizeof(OBDR_TAPE_SIG) - 1)
+#define OBDR_TAPE_INQ_SIZE (OBDR_SIG_OFFSET + OBDR_SIG_LEN)
+
unsigned char *inq_buff;
+ unsigned char *obdr_sig;
inq_buff = kzalloc(OBDR_TAPE_INQ_SIZE, GFP_KERNEL);
if (!inq_buff)
else
this_device->raid_level = RAID_UNKNOWN;
+ if (is_OBDR_device) {
+ /* See if this is a One-Button-Disaster-Recovery device
+ * by looking for "$DR-10" at offset 43 in inquiry data.
+ */
+ obdr_sig = &inq_buff[OBDR_SIG_OFFSET];
+ *is_OBDR_device = (this_device->devtype == TYPE_ROM &&
+ strncmp(obdr_sig, OBDR_TAPE_SIG,
+ OBDR_SIG_LEN) == 0);
+ }
+
kfree(inq_buff);
return 0;
return 0;
}
- if (hpsa_update_device_info(h, scsi3addr, this_device))
+ if (hpsa_update_device_info(h, scsi3addr, this_device, NULL))
return 0;
(*nmsa2xxx_enclosures)++;
hpsa_set_bus_target_lun(this_device, bus, target, 0);
*/
struct ReportLUNdata *physdev_list = NULL;
struct ReportLUNdata *logdev_list = NULL;
- unsigned char *inq_buff = NULL;
u32 nphysicals = 0;
u32 nlogicals = 0;
u32 ndev_allocated = 0;
GFP_KERNEL);
physdev_list = kzalloc(reportlunsize, GFP_KERNEL);
logdev_list = kzalloc(reportlunsize, GFP_KERNEL);
- inq_buff = kmalloc(OBDR_TAPE_INQ_SIZE, GFP_KERNEL);
tmpdevice = kzalloc(sizeof(*tmpdevice), GFP_KERNEL);
- if (!currentsd || !physdev_list || !logdev_list ||
- !inq_buff || !tmpdevice) {
+ if (!currentsd || !physdev_list || !logdev_list || !tmpdevice) {
dev_err(&h->pdev->dev, "out of memory\n");
goto out;
}
/* adjust our table of devices */
nmsa2xxx_enclosures = 0;
for (i = 0; i < nphysicals + nlogicals + 1; i++) {
- u8 *lunaddrbytes;
+ u8 *lunaddrbytes, is_OBDR = 0;
/* Figure out where the LUN ID info is coming from */
lunaddrbytes = figure_lunaddrbytes(h, raid_ctlr_position,
continue;
/* Get device type, vendor, model, device id */
- if (hpsa_update_device_info(h, lunaddrbytes, tmpdevice))
+ if (hpsa_update_device_info(h, lunaddrbytes, tmpdevice,
+ &is_OBDR))
continue; /* skip it if we can't talk to it. */
figure_bus_target_lun(h, lunaddrbytes, &bus, &target, &lun,
tmpdevice);
hpsa_set_bus_target_lun(this_device, bus, target, lun);
switch (this_device->devtype) {
- case TYPE_ROM: {
+ case TYPE_ROM:
/* We don't *really* support actual CD-ROM devices,
* just "One Button Disaster Recovery" tape drive
* which temporarily pretends to be a CD-ROM drive.
* device by checking for "$DR-10" in bytes 43-48 of
* the inquiry data.
*/
- char obdr_sig[7];
-#define OBDR_TAPE_SIG "$DR-10"
- strncpy(obdr_sig, &inq_buff[43], 6);
- obdr_sig[6] = '\0';
- if (strncmp(obdr_sig, OBDR_TAPE_SIG, 6) != 0)
- /* Not OBDR device, ignore it. */
- break;
- }
- ncurrent++;
+ if (is_OBDR)
+ ncurrent++;
break;
case TYPE_DISK:
if (i < nphysicals)
for (i = 0; i < ndev_allocated; i++)
kfree(currentsd[i]);
kfree(currentsd);
- kfree(inq_buff);
kfree(physdev_list);
kfree(logdev_list);
}
pmcsr &= ~PCI_PM_CTRL_STATE_MASK;
pmcsr |= PCI_D0;
pci_write_config_word(pdev, pos + PCI_PM_CTRL, pmcsr);
+
+ /*
+ * The P600 requires a small delay when changing states.
+ * Otherwise we may think the board did not reset and we bail.
+ * This for kdump only and is particular to the P600.
+ */
+ msleep(500);
}
return 0;
}
} else {
use_doorbell = misc_fw_support & MISC_FW_DOORBELL_RESET;
if (use_doorbell) {
- dev_warn(&pdev->dev, "Controller claims that "
- "'Bit 2 doorbell reset' is "
- "supported, but not 'bit 5 doorbell reset'. "
- "Firmware update is recommended.\n");
+ dev_warn(&pdev->dev, "Soft reset not supported. "
+ "Firmware update is required.\n");
rc = -ENOTSUPP; /* try soft reset */
goto unmap_cfgtable;
}
if (!bdev->bd_disk)
return;
- if (disk_partitionable(bdev->bd_disk))
+ if (disk_part_scan_enabled(bdev->bd_disk))
bdev->bd_invalidated = 1;
}
static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
{
struct gendisk *disk;
+ struct module *owner;
int ret;
int partno;
int perm = 0;
disk = get_gendisk(bdev->bd_dev, &partno);
if (!disk)
goto out;
+ owner = disk->fops->owner;
disk_block_events(disk);
mutex_lock_nested(&bdev->bd_mutex, for_part);
bdev->bd_disk = NULL;
mutex_unlock(&bdev->bd_mutex);
disk_unblock_events(disk);
- module_put(disk->fops->owner);
put_disk(disk);
+ module_put(owner);
goto restart;
}
}
goto out_unlock_bdev;
}
/* only one opener holds refs to the module and disk */
- module_put(disk->fops->owner);
put_disk(disk);
+ module_put(owner);
}
bdev->bd_openers++;
if (for_part)
out_unlock_bdev:
mutex_unlock(&bdev->bd_mutex);
disk_unblock_events(disk);
- module_put(disk->fops->owner);
put_disk(disk);
+ module_put(owner);
out:
bdput(bdev);
WARN_ON_ONCE(bdev->bd_holders);
sync_blockdev(bdev);
kill_bdev(bdev);
+ /* ->release can cause the old bdi to disappear,
+ * so must switch it out first
+ */
+ bdev_inode_switch_bdi(bdev->bd_inode,
+ &default_backing_dev_info);
}
if (bdev->bd_contains == bdev) {
if (disk->fops->release)
if (!bdev->bd_openers) {
struct module *owner = disk->fops->owner;
- put_disk(disk);
- module_put(owner);
disk_put_part(bdev->bd_part);
bdev->bd_part = NULL;
bdev->bd_disk = NULL;
- bdev_inode_switch_bdi(bdev->bd_inode,
- &default_backing_dev_info);
if (bdev != bdev->bd_contains)
victim = bdev->bd_contains;
bdev->bd_contains = NULL;
+
+ put_disk(disk);
+ module_put(owner);
}
mutex_unlock(&bdev->bd_mutex);
bdput(bdev);
#define dev_to_part(device) container_of((device), struct hd_struct, __dev)
#define disk_to_dev(disk) (&(disk)->part0.__dev)
#define part_to_dev(part) (&((part)->__dev))
+#define alias_name(disk) ((disk)->alias ? (disk)->alias : \
+ (disk)->disk_name)
extern struct device_type part_type;
extern struct kobject *block_depr;
#define DISK_MAX_PARTS 256
#define DISK_NAME_LEN 32
+#define ALIAS_LEN 256
#include <linux/major.h>
#include <linux/device.h>
#define GENHD_FL_EXT_DEVT 64 /* allow extended devt */
#define GENHD_FL_NATIVE_CAPACITY 128
#define GENHD_FL_BLOCK_EVENTS_ON_EXCL_WRITE 256
+ #define GENHD_FL_NO_PART_SCAN 512
enum {
DISK_EVENT_MEDIA_CHANGE = 1 << 0, /* media changed */
* disks that can't be partitioned. */
char disk_name[DISK_NAME_LEN]; /* name of major driver */
+ char *alias; /* alias name of disk */
char *(*devnode)(struct gendisk *gd, mode_t *mode);
unsigned int events; /* supported events */
return disk->minors;
}
- static inline bool disk_partitionable(struct gendisk *disk)
+ static inline bool disk_part_scan_enabled(struct gendisk *disk)
{
- return disk_max_parts(disk) > 1;
+ return disk_max_parts(disk) > 1 &&
+ !(disk->flags & GENHD_FL_NO_PART_SCAN);
}
static inline dev_t disk_devt(struct gendisk *disk)
struct request_queue *lo_queue;
struct gendisk *lo_disk;
- struct list_head lo_list;
};
#endif /* __KERNEL__ */
*/
enum {
LO_FLAGS_READ_ONLY = 1,
- LO_FLAGS_USE_AOPS = 2,
LO_FLAGS_AUTOCLEAR = 4,
+ LO_FLAGS_PARTSCAN = 8,
};
#include <asm/posix_types.h> /* for __kernel_old_dev_t */
#define LOOP_CHANGE_FD 0x4C06
#define LOOP_SET_CAPACITY 0x4C07
+/* /dev/loop-control interface */
+#define LOOP_CTL_ADD 0x4C80
+#define LOOP_CTL_REMOVE 0x4C81
+#define LOOP_CTL_GET_FREE 0x4C82
#endif