*/
#include <linux/module.h>
+#include <linux/ctype.h>
#include <linux/fs.h>
#include <linux/genhd.h>
#include <linux/kdev_t.h>
#include "blk.h"
static DEFINE_MUTEX(block_class_lock);
-struct kobject *block_depr;
+static struct kobject *block_depr;
/* for extended dynamic devt allocation, currently only one major is used */
#define NR_EXT_DEVT (1 << MINORBITS)
static void disk_del_events(struct gendisk *disk);
static void disk_release_events(struct gendisk *disk);
-void part_inc_in_flight(struct request_queue *q, struct hd_struct *part, int rw)
+/*
+ * Set disk capacity and notify if the size is not currently
+ * zero and will not be set to zero
+ */
+void set_capacity_revalidate_and_notify(struct gendisk *disk, sector_t size,
+ bool revalidate)
{
- if (queue_is_mq(q))
- return;
+ sector_t capacity = get_capacity(disk);
+
+ set_capacity(disk, size);
+
+ if (revalidate)
+ revalidate_disk(disk);
- part_stat_local_inc(part, in_flight[rw]);
- if (part->partno)
- part_stat_local_inc(&part_to_disk(part)->part0, in_flight[rw]);
+ if (capacity != size && capacity != 0 && size != 0) {
+ char *envp[] = { "RESIZE=1", NULL };
+
+ kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
+ }
}
-void part_dec_in_flight(struct request_queue *q, struct hd_struct *part, int rw)
+EXPORT_SYMBOL_GPL(set_capacity_revalidate_and_notify);
+
+/*
+ * Format the device name of the indicated disk into the supplied buffer and
+ * return a pointer to that same buffer for convenience.
+ */
+char *disk_name(struct gendisk *hd, int partno, char *buf)
{
- if (queue_is_mq(q))
- return;
+ if (!partno)
+ snprintf(buf, BDEVNAME_SIZE, "%s", hd->disk_name);
+ else if (isdigit(hd->disk_name[strlen(hd->disk_name)-1]))
+ snprintf(buf, BDEVNAME_SIZE, "%sp%d", hd->disk_name, partno);
+ else
+ snprintf(buf, BDEVNAME_SIZE, "%s%d", hd->disk_name, partno);
- part_stat_local_dec(part, in_flight[rw]);
- if (part->partno)
- part_stat_local_dec(&part_to_disk(part)->part0, in_flight[rw]);
+ return buf;
}
-unsigned int part_in_flight(struct request_queue *q, struct hd_struct *part)
+const char *bdevname(struct block_device *bdev, char *buf)
+{
+ return disk_name(bdev->bd_disk, bdev->bd_part->partno, buf);
+}
+EXPORT_SYMBOL(bdevname);
+
+static void part_stat_read_all(struct hd_struct *part, struct disk_stats *stat)
{
int cpu;
- unsigned int inflight;
- if (queue_is_mq(q)) {
- return blk_mq_in_flight(q, part);
+ memset(stat, 0, sizeof(struct disk_stats));
+ for_each_possible_cpu(cpu) {
+ struct disk_stats *ptr = per_cpu_ptr(part->dkstats, cpu);
+ int group;
+
+ for (group = 0; group < NR_STAT_GROUPS; group++) {
+ stat->nsecs[group] += ptr->nsecs[group];
+ stat->sectors[group] += ptr->sectors[group];
+ stat->ios[group] += ptr->ios[group];
+ stat->merges[group] += ptr->merges[group];
+ }
+
+ stat->io_ticks += ptr->io_ticks;
}
+}
+
+static unsigned int part_in_flight(struct request_queue *q,
+ struct hd_struct *part)
+{
+ unsigned int inflight = 0;
+ int cpu;
- inflight = 0;
for_each_possible_cpu(cpu) {
inflight += part_stat_local_read_cpu(part, in_flight[0], cpu) +
part_stat_local_read_cpu(part, in_flight[1], cpu);
return inflight;
}
-void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
- unsigned int inflight[2])
+static void part_in_flight_rw(struct request_queue *q, struct hd_struct *part,
+ unsigned int inflight[2])
{
int cpu;
- if (queue_is_mq(q)) {
- blk_mq_in_flight_rw(q, part, inflight);
- return;
- }
-
inflight[0] = 0;
inflight[1] = 0;
for_each_possible_cpu(cpu) {
return part;
}
-EXPORT_SYMBOL_GPL(disk_get_part);
/**
* disk_part_iter_init - initialize partition iterator
* primarily used for stats accounting.
*
* CONTEXT:
- * RCU read locked. The returned partition pointer is valid only
- * while preemption is disabled.
+ * RCU read locked. The returned partition pointer is always valid
+ * because its refcount is grabbed except for part0, which lifetime
+ * is same with the disk.
*
* RETURNS:
* Found partition on success, part0 is returned if no partition matches
+ * or the matched partition is being deleted.
*/
struct hd_struct *disk_map_sector_rcu(struct gendisk *disk, sector_t sector)
{
struct hd_struct *part;
int i;
+ rcu_read_lock();
ptbl = rcu_dereference(disk->part_tbl);
part = rcu_dereference(ptbl->last_lookup);
- if (part && sector_in_part(part, sector))
- return part;
+ if (part && sector_in_part(part, sector) && hd_struct_try_get(part))
+ goto out_unlock;
for (i = 1; i < ptbl->len; i++) {
part = rcu_dereference(ptbl->part[i]);
if (part && sector_in_part(part, sector)) {
+ /*
+ * only live partition can be cached for lookup,
+ * so use-after-free on cached & deleting partition
+ * can be avoided
+ */
+ if (!hd_struct_try_get(part))
+ break;
rcu_assign_pointer(ptbl->last_lookup, part);
- return part;
+ goto out_unlock;
}
}
- return &disk->part0;
+
+ part = &disk->part0;
+out_unlock:
+ rcu_read_unlock();
+ return part;
}
-EXPORT_SYMBOL_GPL(disk_map_sector_rcu);
/**
* disk_has_partitions
disk->flags |= GENHD_FL_SUPPRESS_PARTITION_INFO;
disk->flags |= GENHD_FL_NO_PART_SCAN;
} else {
+ struct backing_dev_info *bdi = disk->queue->backing_dev_info;
+ struct device *dev = disk_to_dev(disk);
int ret;
/* Register BDI before referencing it from bdev */
- disk_to_dev(disk)->devt = devt;
- ret = bdi_register_owner(disk->queue->backing_dev_info,
- disk_to_dev(disk));
+ dev->devt = devt;
+ ret = bdi_register(bdi, "%u:%u", MAJOR(devt), MINOR(devt));
WARN_ON(ret);
+ bdi_set_owner(bdi, dev);
blk_register_region(disk_devt(disk), disk->minors, NULL,
exact_match, exact_lock, disk);
}
}
EXPORT_SYMBOL(device_add_disk_no_queue_reg);
+static void invalidate_partition(struct gendisk *disk, int partno)
+{
+ struct block_device *bdev;
+
+ bdev = bdget_disk(disk, partno);
+ if (!bdev)
+ return;
+
+ fsync_bdev(bdev);
+ __invalidate_device(bdev, true);
+
+ /*
+ * Unhash the bdev inode for this device so that it gets evicted as soon
+ * as last inode reference is dropped.
+ */
+ remove_inode_hash(bdev->bd_inode);
+ bdput(bdev);
+}
+
void del_gendisk(struct gendisk *disk)
{
struct disk_part_iter piter;
DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
while ((part = disk_part_iter_next(&piter))) {
invalidate_partition(disk, part->partno);
- bdev_unhash_inode(part_devt(part));
- delete_partition(disk, part->partno);
+ delete_partition(disk, part);
}
disk_part_iter_exit(&piter);
invalidate_partition(disk, 0);
- bdev_unhash_inode(disk_devt(disk));
set_capacity(disk, 0);
disk->flags &= ~GENHD_FL_UP;
up_write(&disk->lookup_sem);
}
return disk;
}
-EXPORT_SYMBOL(get_gendisk);
/**
* bdget_disk - do bdget() by gendisk and partition number
return sprintf(buf, "%d\n", get_disk_ro(disk) ? 1 : 0);
}
+ssize_t part_size_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+
+ return sprintf(buf, "%llu\n",
+ (unsigned long long)part_nr_sects_read(p));
+}
+
+ssize_t part_stat_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+ struct request_queue *q = part_to_disk(p)->queue;
+ struct disk_stats stat;
+ unsigned int inflight;
+
+ part_stat_read_all(p, &stat);
+ if (queue_is_mq(q))
+ inflight = blk_mq_in_flight(q, p);
+ else
+ inflight = part_in_flight(q, p);
+
+ return sprintf(buf,
+ "%8lu %8lu %8llu %8u "
+ "%8lu %8lu %8llu %8u "
+ "%8u %8u %8u "
+ "%8lu %8lu %8llu %8u "
+ "%8lu %8u"
+ "\n",
+ stat.ios[STAT_READ],
+ stat.merges[STAT_READ],
+ (unsigned long long)stat.sectors[STAT_READ],
+ (unsigned int)div_u64(stat.nsecs[STAT_READ], NSEC_PER_MSEC),
+ stat.ios[STAT_WRITE],
+ stat.merges[STAT_WRITE],
+ (unsigned long long)stat.sectors[STAT_WRITE],
+ (unsigned int)div_u64(stat.nsecs[STAT_WRITE], NSEC_PER_MSEC),
+ inflight,
+ jiffies_to_msecs(stat.io_ticks),
+ (unsigned int)div_u64(stat.nsecs[STAT_READ] +
+ stat.nsecs[STAT_WRITE] +
+ stat.nsecs[STAT_DISCARD] +
+ stat.nsecs[STAT_FLUSH],
+ NSEC_PER_MSEC),
+ stat.ios[STAT_DISCARD],
+ stat.merges[STAT_DISCARD],
+ (unsigned long long)stat.sectors[STAT_DISCARD],
+ (unsigned int)div_u64(stat.nsecs[STAT_DISCARD], NSEC_PER_MSEC),
+ stat.ios[STAT_FLUSH],
+ (unsigned int)div_u64(stat.nsecs[STAT_FLUSH], NSEC_PER_MSEC));
+}
+
+ssize_t part_inflight_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+ struct request_queue *q = part_to_disk(p)->queue;
+ unsigned int inflight[2];
+
+ if (queue_is_mq(q))
+ blk_mq_in_flight_rw(q, p, inflight);
+ else
+ part_in_flight_rw(q, p, inflight);
+
+ return sprintf(buf, "%8u %8u\n", inflight[0], inflight[1]);
+}
+
static ssize_t disk_capability_show(struct device *dev,
struct device_attribute *attr, char *buf)
{
static DEVICE_ATTR(stat, 0444, part_stat_show, NULL);
static DEVICE_ATTR(inflight, 0444, part_inflight_show, NULL);
static DEVICE_ATTR(badblocks, 0644, disk_badblocks_show, disk_badblocks_store);
+
#ifdef CONFIG_FAIL_MAKE_REQUEST
+ssize_t part_fail_show(struct device *dev,
+ struct device_attribute *attr, char *buf)
+{
+ struct hd_struct *p = dev_to_part(dev);
+
+ return sprintf(buf, "%d\n", p->make_it_fail);
+}
+
+ssize_t part_fail_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct hd_struct *p = dev_to_part(dev);
+ int i;
+
+ if (count > 0 && sscanf(buf, "%d", &i) > 0)
+ p->make_it_fail = (i == 0) ? 0 : 1;
+
+ return count;
+}
+
static struct device_attribute dev_attr_fail =
__ATTR(make-it-fail, 0644, part_fail_show, part_fail_store);
-#endif
+#endif /* CONFIG_FAIL_MAKE_REQUEST */
+
#ifdef CONFIG_FAIL_IO_TIMEOUT
static struct device_attribute dev_attr_fail_timeout =
__ATTR(io-timeout-fail, 0644, part_timeout_show, part_timeout_store);
{
struct gendisk *disk = dev_to_disk(dev);
- if (disk->devnode)
- return disk->devnode(disk, mode);
+ if (disk->fops->devnode)
+ return disk->fops->devnode(disk, mode);
return NULL;
}
struct hd_struct *hd;
char buf[BDEVNAME_SIZE];
unsigned int inflight;
+ struct disk_stats stat;
/*
if (&disk_to_dev(gp)->kobj.entry == block_class.devices.next)
disk_part_iter_init(&piter, gp, DISK_PITER_INCL_EMPTY_PART0);
while ((hd = disk_part_iter_next(&piter))) {
- inflight = part_in_flight(gp->queue, hd);
+ part_stat_read_all(hd, &stat);
+ if (queue_is_mq(gp->queue))
+ inflight = blk_mq_in_flight(gp->queue, hd);
+ else
+ inflight = part_in_flight(gp->queue, hd);
+
seq_printf(seqf, "%4d %7d %s "
"%lu %lu %lu %u "
"%lu %lu %lu %u "
"\n",
MAJOR(part_devt(hd)), MINOR(part_devt(hd)),
disk_name(gp, hd->partno, buf),
- part_stat_read(hd, ios[STAT_READ]),
- part_stat_read(hd, merges[STAT_READ]),
- part_stat_read(hd, sectors[STAT_READ]),
- (unsigned int)part_stat_read_msecs(hd, STAT_READ),
- part_stat_read(hd, ios[STAT_WRITE]),
- part_stat_read(hd, merges[STAT_WRITE]),
- part_stat_read(hd, sectors[STAT_WRITE]),
- (unsigned int)part_stat_read_msecs(hd, STAT_WRITE),
+ stat.ios[STAT_READ],
+ stat.merges[STAT_READ],
+ stat.sectors[STAT_READ],
+ (unsigned int)div_u64(stat.nsecs[STAT_READ],
+ NSEC_PER_MSEC),
+ stat.ios[STAT_WRITE],
+ stat.merges[STAT_WRITE],
+ stat.sectors[STAT_WRITE],
+ (unsigned int)div_u64(stat.nsecs[STAT_WRITE],
+ NSEC_PER_MSEC),
inflight,
- jiffies_to_msecs(part_stat_read(hd, io_ticks)),
- jiffies_to_msecs(part_stat_read(hd, time_in_queue)),
- part_stat_read(hd, ios[STAT_DISCARD]),
- part_stat_read(hd, merges[STAT_DISCARD]),
- part_stat_read(hd, sectors[STAT_DISCARD]),
- (unsigned int)part_stat_read_msecs(hd, STAT_DISCARD),
- part_stat_read(hd, ios[STAT_FLUSH]),
- (unsigned int)part_stat_read_msecs(hd, STAT_FLUSH)
+ jiffies_to_msecs(stat.io_ticks),
+ (unsigned int)div_u64(stat.nsecs[STAT_READ] +
+ stat.nsecs[STAT_WRITE] +
+ stat.nsecs[STAT_DISCARD] +
+ stat.nsecs[STAT_FLUSH],
+ NSEC_PER_MSEC),
+ stat.ios[STAT_DISCARD],
+ stat.merges[STAT_DISCARD],
+ stat.sectors[STAT_DISCARD],
+ (unsigned int)div_u64(stat.nsecs[STAT_DISCARD],
+ NSEC_PER_MSEC),
+ stat.ios[STAT_FLUSH],
+ (unsigned int)div_u64(stat.nsecs[STAT_FLUSH],
+ NSEC_PER_MSEC)
);
}
disk_part_iter_exit(&piter);
class_dev_iter_exit(&iter);
return devt;
}
-EXPORT_SYMBOL(blk_lookup_devt);
struct gendisk *__alloc_disk_node(int minors, int node_id)
{
disk = kzalloc_node(sizeof(struct gendisk), GFP_KERNEL, node_id);
if (disk) {
- if (!init_part_stats(&disk->part0)) {
+ disk->part0.dkstats = alloc_percpu(struct disk_stats);
+ if (!disk->part0.dkstats) {
kfree(disk);
return NULL;
}
init_rwsem(&disk->lookup_sem);
disk->node_id = node_id;
if (disk_expand_part_tbl(disk, 0)) {
- free_part_stats(&disk->part0);
+ free_percpu(disk->part0.dkstats);
kfree(disk);
return NULL;
}
* TODO: Ideally set_capacity() and get_capacity() should be
* converted to make use of bd_mutex and sequence counters.
*/
- seqcount_init(&disk->part0.nr_sects_seq);
+ hd_sects_seq_init(&disk->part0);
if (hd_ref_init(&disk->part0)) {
hd_free_part(&disk->part0);
kfree(disk);
EXPORT_SYMBOL(bdev_read_only);
-int invalidate_partition(struct gendisk *disk, int partno)
-{
- int res = 0;
- struct block_device *bdev = bdget_disk(disk, partno);
- if (bdev) {
- fsync_bdev(bdev);
- res = __invalidate_device(bdev, true);
- bdput(bdev);
- }
- return res;
-}
-
-EXPORT_SYMBOL(invalidate_partition);
-
/*
* Disk events - monitor disk events like media change and eject request.
*/
projects / linux-block.git / blobdiff