#include <linux/blkdev.h>
#include <linux/init.h>
#include <linux/spinlock.h>
+#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/slab.h>
#include <linux/kmod.h>
*/
struct hd_struct *disk_get_part(struct gendisk *disk, int partno)
{
- struct hd_struct *part;
+ struct hd_struct *part = NULL;
+ struct disk_part_tbl *ptbl;
- if (unlikely(partno < 0 || partno >= disk_max_parts(disk)))
+ if (unlikely(partno < 0))
return NULL;
+
rcu_read_lock();
- part = rcu_dereference(disk->__part[partno]);
- if (part)
- get_device(part_to_dev(part));
+
+ ptbl = rcu_dereference(disk->part_tbl);
+ if (likely(partno < ptbl->len)) {
+ part = rcu_dereference(ptbl->part[partno]);
+ if (part)
+ get_device(part_to_dev(part));
+ }
+
rcu_read_unlock();
return part;
void disk_part_iter_init(struct disk_part_iter *piter, struct gendisk *disk,
unsigned int flags)
{
+ struct disk_part_tbl *ptbl;
+
+ rcu_read_lock();
+ ptbl = rcu_dereference(disk->part_tbl);
+
piter->disk = disk;
piter->part = NULL;
if (flags & DISK_PITER_REVERSE)
- piter->idx = disk_max_parts(piter->disk) - 1;
- else if (flags & DISK_PITER_INCL_PART0)
+ piter->idx = ptbl->len - 1;
+ else if (flags & (DISK_PITER_INCL_PART0 | DISK_PITER_INCL_EMPTY_PART0))
piter->idx = 0;
else
piter->idx = 1;
piter->flags = flags;
+
+ rcu_read_unlock();
}
EXPORT_SYMBOL_GPL(disk_part_iter_init);
*/
struct hd_struct *disk_part_iter_next(struct disk_part_iter *piter)
{
+ struct disk_part_tbl *ptbl;
int inc, end;
/* put the last partition */
disk_put_part(piter->part);
piter->part = NULL;
+ /* get part_tbl */
rcu_read_lock();
+ ptbl = rcu_dereference(piter->disk->part_tbl);
/* determine iteration parameters */
if (piter->flags & DISK_PITER_REVERSE) {
inc = -1;
- if (piter->flags & DISK_PITER_INCL_PART0)
+ if (piter->flags & (DISK_PITER_INCL_PART0 |
+ DISK_PITER_INCL_EMPTY_PART0))
end = -1;
else
end = 0;
} else {
inc = 1;
- end = disk_max_parts(piter->disk);
+ end = ptbl->len;
}
/* iterate to the next partition */
for (; piter->idx != end; piter->idx += inc) {
struct hd_struct *part;
- part = rcu_dereference(piter->disk->__part[piter->idx]);
+ part = rcu_dereference(ptbl->part[piter->idx]);
if (!part)
continue;
- if (!(piter->flags & DISK_PITER_INCL_EMPTY) && !part->nr_sects)
+ if (!part->nr_sects &&
+ !(piter->flags & DISK_PITER_INCL_EMPTY) &&
+ !(piter->flags & DISK_PITER_INCL_EMPTY_PART0 &&
+ piter->idx == 0))
continue;
get_device(part_to_dev(part));
}
EXPORT_SYMBOL_GPL(disk_part_iter_exit);
+static inline int sector_in_part(struct hd_struct *part, sector_t sector)
+{
+ return part->start_sect <= sector &&
+ sector < part->start_sect + part->nr_sects;
+}
+
/**
* disk_map_sector_rcu - map sector to partition
* @disk: gendisk of interest
* while preemption is disabled.
*
* RETURNS:
- * Found partition on success, NULL if there's no matching partition.
+ * Found partition on success, part0 is returned if no partition matches
*/
struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
{
+ struct disk_part_tbl *ptbl;
+ struct hd_struct *part;
int i;
- for (i = 1; i < disk_max_parts(disk); i++) {
- struct hd_struct *part = rcu_dereference(disk->__part[i]);
+ ptbl = rcu_dereference(disk->part_tbl);
+
+ part = rcu_dereference(ptbl->last_lookup);
+ if (part && sector_in_part(part, sector))
+ return part;
+
+ for (i = 1; i < ptbl->len; i++) {
+ part = rcu_dereference(ptbl->part[i]);
- if (part && part->start_sect <= sector &&
- sector < part->start_sect + part->nr_sects)
+ if (part && sector_in_part(part, sector)) {
+ rcu_assign_pointer(ptbl->last_lookup, part);
return part;
+ }
}
- return NULL;
+ return &disk->part0;
}
EXPORT_SYMBOL_GPL(disk_map_sector_rcu);
}
#endif /* CONFIG_PROC_FS */
+/**
+ * register_blkdev - register a new block device
+ *
+ * @major: the requested major device number [1..255]. If @major=0, try to
+ * allocate any unused major number.
+ * @name: the name of the new block device as a zero terminated string
+ *
+ * The @name must be unique within the system.
+ *
+ * The return value depends on the @major input parameter.
+ * - if a major device number was requested in range [1..255] then the
+ * function returns zero on success, or a negative error code
+ * - if any unused major number was requested with @major=0 parameter
+ * then the return value is the allocated major number in range
+ * [1..255] or a negative error code otherwise
+ */
int register_blkdev(unsigned int major, const char *name)
{
struct blk_major_name **n, *p;
/**
* blk_alloc_devt - allocate a dev_t for a partition
* @part: partition to allocate dev_t for
- * @gfp_mask: memory allocation flag
* @devt: out parameter for resulting dev_t
*
* Allocate a dev_t for block device.
*
* This function registers the partitioning information in @disk
* with the kernel.
+ *
+ * FIXME: error handling
*/
void add_disk(struct gendisk *disk)
{
struct backing_dev_info *bdi;
+ dev_t devt;
int retval;
+ /* minors == 0 indicates to use ext devt from part0 and should
+ * be accompanied with EXT_DEVT flag. Make sure all
+ * parameters make sense.
+ */
+ WARN_ON(disk->minors && !(disk->major || disk->first_minor));
+ WARN_ON(!disk->minors && !(disk->flags & GENHD_FL_EXT_DEVT));
+
disk->flags |= GENHD_FL_UP;
- disk_to_dev(disk)->devt = MKDEV(disk->major, disk->first_minor);
+
+ retval = blk_alloc_devt(&disk->part0, &devt);
+ if (retval) {
+ WARN_ON(1);
+ return;
+ }
+ disk_to_dev(disk)->devt = devt;
+
+ /* ->major and ->first_minor aren't supposed to be
+ * dereferenced from here on, but set them just in case.
+ */
+ disk->major = MAJOR(devt);
+ disk->first_minor = MINOR(devt);
+
blk_register_region(disk_devt(disk), disk->minors, NULL,
exact_match, exact_lock, disk);
register_disk(disk);
/**
* get_gendisk - get partitioning information for a given device
* @devt: device to get partitioning information for
- * @part: returned partition index
+ * @partno: returned partition index
*
* This function gets the structure containing partitioning
* information for the given device @devt.
* RETURNS:
* Resulting block_device on success, NULL on failure.
*/
-extern struct block_device *bdget_disk(struct gendisk *disk, int partno)
+struct block_device *bdget_disk(struct gendisk *disk, int partno)
{
struct hd_struct *part;
struct block_device *bdev = NULL;
part = disk_get_part(disk, partno);
- if (part && (part->nr_sects || partno == 0))
+ if (part)
bdev = bdget(part_devt(part));
disk_put_part(part);
* numbers in hex - the same format as the root=
* option takes.
*/
- printk("%s %10llu %s",
- bdevt_str(disk_devt(disk), devt_buf),
- (unsigned long long)get_capacity(disk) >> 1,
- disk_name(disk, 0, name_buf));
- if (disk->driverfs_dev != NULL &&
- disk->driverfs_dev->driver != NULL)
- printk(" driver: %s\n",
- disk->driverfs_dev->driver->name);
- else
- printk(" (driver?)\n");
+ disk_part_iter_init(&piter, disk, DISK_PITER_INCL_PART0);
+ while ((part = disk_part_iter_next(&piter))) {
+ bool is_part0 = part == &disk->part0;
- /* now show the partitions */
- disk_part_iter_init(&piter, disk, 0);
- while ((part = disk_part_iter_next(&piter)))
- printk(" %s %10llu %s\n",
+ printk("%s%s %10llu %s", is_part0 ? "" : " ",
bdevt_str(part_devt(part), devt_buf),
(unsigned long long)part->nr_sects >> 1,
disk_name(disk, part->partno, name_buf));
+ if (is_part0) {
+ if (disk->driverfs_dev != NULL &&
+ disk->driverfs_dev->driver != NULL)
+ printk(" driver: %s\n",
+ disk->driverfs_dev->driver->name);
+ else
+ printk(" (driver?)\n");
+ } else
+ printk("\n");
+ }
disk_part_iter_exit(&piter);
}
class_dev_iter_exit(&iter);
struct class_dev_iter *iter;
struct device *dev;
- iter = kmalloc(GFP_KERNEL, sizeof(*iter));
+ iter = kmalloc(sizeof(*iter), GFP_KERNEL);
if (!iter)
return ERR_PTR(-ENOMEM);
static void *p;
p = disk_seqf_start(seqf, pos);
- if (!IS_ERR(p) && p)
+ if (!IS_ERR(p) && p && !*pos)
seq_puts(seqf, "major minor #blocks name\n\n");
return p;
}
return 0;
/* show the full disk and all non-0 size partitions of it */
- seq_printf(seqf, "%4d %7d %10llu %s\n",
- MAJOR(disk_devt(sgp)), MINOR(disk_devt(sgp)),
- (unsigned long long)get_capacity(sgp) >> 1,
- disk_name(sgp, 0, buf));
-
- disk_part_iter_init(&piter, sgp, 0);
+ disk_part_iter_init(&piter, sgp, DISK_PITER_INCL_PART0);
while ((part = disk_part_iter_next(&piter)))
seq_printf(seqf, "%4d %7d %10llu %s\n",
MAJOR(part_devt(part)), MINOR(part_devt(part)),
return 0;
}
-const struct seq_operations partitions_op = {
+static const struct seq_operations partitions_op = {
.start = show_partition_start,
.next = disk_seqf_next,
.stop = disk_seqf_stop,
.show = show_partition
};
+
+static int partitions_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &partitions_op);
+}
+
+static const struct file_operations proc_partitions_operations = {
+ .open = partitions_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
#endif
bdev_map = kobj_map_init(base_probe, &block_class_lock);
blk_dev_init();
+ register_blkdev(BLOCK_EXT_MAJOR, "blkext");
+
#ifndef CONFIG_SYSFS_DEPRECATED
/* create top-level block dir */
block_depr = kobject_create_and_add("block", NULL);
return sprintf(buf, "%x\n", disk->flags);
}
-static ssize_t disk_stat_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct gendisk *disk = dev_to_disk(dev);
- int cpu;
-
- cpu = disk_stat_lock();
- disk_round_stats(cpu, disk);
- disk_stat_unlock();
- return sprintf(buf,
- "%8lu %8lu %8llu %8u "
- "%8lu %8lu %8llu %8u "
- "%8u %8u %8u"
- "\n",
- disk_stat_read(disk, ios[READ]),
- disk_stat_read(disk, merges[READ]),
- (unsigned long long)disk_stat_read(disk, sectors[READ]),
- jiffies_to_msecs(disk_stat_read(disk, ticks[READ])),
- disk_stat_read(disk, ios[WRITE]),
- disk_stat_read(disk, merges[WRITE]),
- (unsigned long long)disk_stat_read(disk, sectors[WRITE]),
- jiffies_to_msecs(disk_stat_read(disk, ticks[WRITE])),
- disk->in_flight,
- jiffies_to_msecs(disk_stat_read(disk, io_ticks)),
- jiffies_to_msecs(disk_stat_read(disk, time_in_queue)));
-}
-
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);
static DEVICE_ATTR(ro, S_IRUGO, disk_ro_show, NULL);
static DEVICE_ATTR(size, S_IRUGO, part_size_show, NULL);
static DEVICE_ATTR(capability, S_IRUGO, disk_capability_show, NULL);
-static DEVICE_ATTR(stat, S_IRUGO, disk_stat_show, NULL);
+static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
#ifdef CONFIG_FAIL_MAKE_REQUEST
static struct device_attribute dev_attr_fail =
__ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
#endif
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+static struct device_attribute dev_attr_fail_timeout =
+ __ATTR(io-timeout-fail, S_IRUGO|S_IWUSR, part_timeout_show,
+ part_timeout_store);
+#endif
static struct attribute *disk_attrs[] = {
&dev_attr_range.attr,
#ifdef CONFIG_FAIL_MAKE_REQUEST
&dev_attr_fail.attr,
#endif
+#ifdef CONFIG_FAIL_IO_TIMEOUT
+ &dev_attr_fail_timeout.attr,
+#endif
NULL
};
NULL
};
+static void disk_free_ptbl_rcu_cb(struct rcu_head *head)
+{
+ struct disk_part_tbl *ptbl =
+ container_of(head, struct disk_part_tbl, rcu_head);
+
+ kfree(ptbl);
+}
+
+/**
+ * disk_replace_part_tbl - replace disk->part_tbl in RCU-safe way
+ * @disk: disk to replace part_tbl for
+ * @new_ptbl: new part_tbl to install
+ *
+ * Replace disk->part_tbl with @new_ptbl in RCU-safe way. The
+ * original ptbl is freed using RCU callback.
+ *
+ * LOCKING:
+ * Matching bd_mutx locked.
+ */
+static void disk_replace_part_tbl(struct gendisk *disk,
+ struct disk_part_tbl *new_ptbl)
+{
+ struct disk_part_tbl *old_ptbl = disk->part_tbl;
+
+ rcu_assign_pointer(disk->part_tbl, new_ptbl);
+
+ if (old_ptbl) {
+ rcu_assign_pointer(old_ptbl->last_lookup, NULL);
+ call_rcu(&old_ptbl->rcu_head, disk_free_ptbl_rcu_cb);
+ }
+}
+
+/**
+ * disk_expand_part_tbl - expand disk->part_tbl
+ * @disk: disk to expand part_tbl for
+ * @partno: expand such that this partno can fit in
+ *
+ * Expand disk->part_tbl such that @partno can fit in. disk->part_tbl
+ * uses RCU to allow unlocked dereferencing for stats and other stuff.
+ *
+ * LOCKING:
+ * Matching bd_mutex locked, might sleep.
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int disk_expand_part_tbl(struct gendisk *disk, int partno)
+{
+ struct disk_part_tbl *old_ptbl = disk->part_tbl;
+ struct disk_part_tbl *new_ptbl;
+ int len = old_ptbl ? old_ptbl->len : 0;
+ int target = partno + 1;
+ size_t size;
+ int i;
+
+ /* disk_max_parts() is zero during initialization, ignore if so */
+ if (disk_max_parts(disk) && target > disk_max_parts(disk))
+ return -EINVAL;
+
+ if (target <= len)
+ return 0;
+
+ size = sizeof(*new_ptbl) + target * sizeof(new_ptbl->part[0]);
+ new_ptbl = kzalloc_node(size, GFP_KERNEL, disk->node_id);
+ if (!new_ptbl)
+ return -ENOMEM;
+
+ INIT_RCU_HEAD(&new_ptbl->rcu_head);
+ new_ptbl->len = target;
+
+ for (i = 0; i < len; i++)
+ rcu_assign_pointer(new_ptbl->part[i], old_ptbl->part[i]);
+
+ disk_replace_part_tbl(disk, new_ptbl);
+ return 0;
+}
+
static void disk_release(struct device *dev)
{
struct gendisk *disk = dev_to_disk(dev);
kfree(disk->random);
- kfree(disk->__part);
- free_disk_stats(disk);
+ disk_replace_part_tbl(disk, NULL);
+ free_part_stats(&disk->part0);
kfree(disk);
}
struct class block_class = {
"\n\n");
*/
- cpu = disk_stat_lock();
- disk_round_stats(cpu, gp);
- disk_stat_unlock();
- seq_printf(seqf, "%4d %7d %s %lu %lu %llu %u %lu %lu %llu %u %u %u %u\n",
- MAJOR(disk_devt(gp)), MINOR(disk_devt(gp)),
- disk_name(gp, 0, buf),
- disk_stat_read(gp, ios[0]), disk_stat_read(gp, merges[0]),
- (unsigned long long)disk_stat_read(gp, sectors[0]),
- jiffies_to_msecs(disk_stat_read(gp, ticks[0])),
- disk_stat_read(gp, ios[1]), disk_stat_read(gp, merges[1]),
- (unsigned long long)disk_stat_read(gp, sectors[1]),
- jiffies_to_msecs(disk_stat_read(gp, ticks[1])),
- gp->in_flight,
- jiffies_to_msecs(disk_stat_read(gp, io_ticks)),
- jiffies_to_msecs(disk_stat_read(gp, time_in_queue)));
-
- /* now show all non-0 size partitions of it */
- disk_part_iter_init(&piter, gp, 0);
+ disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
while ((hd = disk_part_iter_next(&piter))) {
- cpu = disk_stat_lock();
+ cpu = part_stat_lock();
part_round_stats(cpu, hd);
- disk_stat_unlock();
+ part_stat_unlock();
seq_printf(seqf, "%4d %7d %s %lu %lu %llu "
"%u %lu %lu %llu %u %u %u %u\n",
MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
return 0;
}
-const struct seq_operations diskstats_op = {
+static const struct seq_operations diskstats_op = {
.start = disk_seqf_start,
.next = disk_seqf_next,
.stop = disk_seqf_stop,
.show = diskstats_show
};
+
+static int diskstats_open(struct inode *inode, struct file *file)
+{
+ return seq_open(file, &diskstats_op);
+}
+
+static const struct file_operations proc_diskstats_operations = {
+ .open = diskstats_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = seq_release,
+};
+
+static int __init proc_genhd_init(void)
+{
+ proc_create("diskstats", 0, NULL, &proc_diskstats_operations);
+ proc_create("partitions", 0, NULL, &proc_partitions_operations);
+ return 0;
+}
+module_init(proc_genhd_init);
#endif /* CONFIG_PROC_FS */
static void media_change_notify_thread(struct work_struct *work)
struct gendisk *disk = dev_to_disk(dev);
struct hd_struct *part;
- if (strcmp(dev->bus_id, name))
+ if (strcmp(dev_name(dev), name))
continue;
+ if (partno < disk->minors) {
+ /* We need to return the right devno, even
+ * if the partition doesn't exist yet.
+ */
+ devt = MKDEV(MAJOR(dev->devt),
+ MINOR(dev->devt) + partno);
+ break;
+ }
part = disk_get_part(disk, partno);
- if (part && (part->nr_sects || partno == 0)) {
+ if (part) {
devt = part_devt(part);
disk_put_part(part);
break;
{
return alloc_disk_node(minors, -1);
}
+EXPORT_SYMBOL(alloc_disk);
struct gendisk *alloc_disk_node(int minors, int node_id)
{
- return alloc_disk_ext_node(minors, 0, node_id);
-}
-
-struct gendisk *alloc_disk_ext(int minors, int ext_minors)
-{
- return alloc_disk_ext_node(minors, ext_minors, -1);
-}
-
-struct gendisk *alloc_disk_ext_node(int minors, int ext_minors, int node_id)
-{
struct gendisk *disk;
disk = kmalloc_node(sizeof(struct gendisk),
GFP_KERNEL | __GFP_ZERO, node_id);
if (disk) {
- int tot_minors = minors + ext_minors;
- int size = tot_minors * sizeof(struct hd_struct *);
-
- if (!init_disk_stats(disk)) {
+ if (!init_part_stats(&disk->part0)) {
kfree(disk);
return NULL;
}
-
- disk->__part = kmalloc_node(size, GFP_KERNEL | __GFP_ZERO,
- node_id);
- if (!disk->__part) {
- free_disk_stats(disk);
+ disk->node_id = node_id;
+ if (disk_expand_part_tbl(disk, 0)) {
+ free_part_stats(&disk->part0);
kfree(disk);
return NULL;
}
- disk->__part[0] = &disk->part0;
+ disk->part_tbl->part[0] = &disk->part0;
disk->minors = minors;
- disk->ext_minors = ext_minors;
rand_initialize_disk(disk);
disk_to_dev(disk)->class = &block_class;
disk_to_dev(disk)->type = &disk_type;
}
return disk;
}
-
-EXPORT_SYMBOL(alloc_disk);
EXPORT_SYMBOL(alloc_disk_node);
-EXPORT_SYMBOL(alloc_disk_ext);
-EXPORT_SYMBOL(alloc_disk_ext_node);
struct kobject *get_disk(struct gendisk *disk)
{
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff