path: root/block/genhd.c

// SPDX-License-Identifier: GPL-2.0
/*
 *  gendisk handling
 *
 * Portions Copyright (C) 2020 Christoph Hellwig
 */

#include <linux/module.h>
#include <linux/ctype.h>
#include <linux/fs.h>
#include <linux/kdev_t.h>
#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.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>
#include <linux/major.h>
#include <linux/mutex.h>
#include <linux/idr.h>
#include <linux/log2.h>
#include <linux/pm_runtime.h>
#include <linux/badblocks.h>
#include <linux/part_stat.h>
#include <linux/blktrace_api.h>

#include "blk-throttle.h"
#include "blk.h"
#include "blk-mq-sched.h"
#include "blk-rq-qos.h"
#include "blk-cgroup.h"

static struct kobject *block_depr;

/*
 * Unique, monotonically increasing sequential number associated with block
 * devices instances (i.e. incremented each time a device is attached).
 * Associating uevents with block devices in userspace is difficult and racy:
 * the uevent netlink socket is lossy, and on slow and overloaded systems has
 * a very high latency.
 * Block devices do not have exclusive owners in userspace, any process can set
 * one up (e.g. loop devices). Moreover, device names can be reused (e.g. loop0
 * can be reused again and again).
 * A userspace process setting up a block device and watching for its events
 * cannot thus reliably tell whether an event relates to the device it just set
 * up or another earlier instance with the same name.
 * This sequential number allows userspace processes to solve this problem, and
 * uniquely associate an uevent to the lifetime to a device.
 */
static atomic64_t diskseq;

/* for extended dynamic devt allocation, currently only one major is used */
#define NR_EXT_DEVT		(1 << MINORBITS)
static DEFINE_IDA(ext_devt_ida);

void set_capacity(struct gendisk *disk, sector_t sectors)
{
	if (sectors > BLK_DEV_MAX_SECTORS) {
		pr_warn_once("%s: truncate capacity from %lld to %lld\n",
				disk->disk_name, sectors,
				BLK_DEV_MAX_SECTORS);
		sectors = BLK_DEV_MAX_SECTORS;
	}

	bdev_set_nr_sectors(disk->part0, sectors);
}
EXPORT_SYMBOL(set_capacity);

/*
 * Set disk capacity and notify if the size is not currently zero and will not
 * be set to zero.  Returns true if a uevent was sent, otherwise false.
 */
bool set_capacity_and_notify(struct gendisk *disk, sector_t size)
{
	sector_t capacity = get_capacity(disk);
	char *envp[] = { "RESIZE=1", NULL };

	set_capacity(disk, size);

	/*
	 * Only print a message and send a uevent if the gendisk is user visible
	 * and alive.  This avoids spamming the log and udev when setting the
	 * initial capacity during probing.
	 */
	if (size == capacity ||
	    !disk_live(disk) ||
	    (disk->flags & GENHD_FL_HIDDEN))
		return false;

	pr_info_ratelimited("%s: detected capacity change from %lld to %lld\n",
		disk->disk_name, capacity, size);

	/*
	 * Historically we did not send a uevent for changes to/from an empty
	 * device.
	 */
	if (!capacity || !size)
		return false;
	kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp);
	return true;
}
EXPORT_SYMBOL_GPL(set_capacity_and_notify);

static void part_stat_read_all(struct block_device *part,
		struct disk_stats *stat)
{
	int cpu;

	memset(stat, 0, sizeof(struct disk_stats));
	for_each_possible_cpu(cpu) {
		struct disk_stats *ptr = per_cpu_ptr(part->bd_stats, 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 void bdev_count_inflight_rw(struct block_device *part,
		unsigned int inflight[2], bool mq_driver)
{
	int write = 0;
	int read = 0;
	int cpu;

	if (mq_driver) {
		blk_mq_in_driver_rw(part, inflight);
		return;
	}

	for_each_possible_cpu(cpu) {
		read += part_stat_local_read_cpu(part, in_flight[READ], cpu);
		write += part_stat_local_read_cpu(part, in_flight[WRITE], cpu);
	}

	/*
	 * While iterating all CPUs, some IOs may be issued from a CPU already
	 * traversed and complete on a CPU that has not yet been traversed,
	 * causing the inflight number to be negative.
	 */
	inflight[READ] = read > 0 ? read : 0;
	inflight[WRITE] = write > 0 ? write : 0;
}

/**
 * bdev_count_inflight - get the number of inflight IOs for a block device.
 *
 * @part: the block device.
 *
 * Inflight here means started IO accounting, from bdev_start_io_acct() for
 * bio-based block device, and from blk_account_io_start() for rq-based block
 * device.
 */
unsigned int bdev_count_inflight(struct block_device *part)
{
	unsigned int inflight[2] = {0};

	bdev_count_inflight_rw(part, inflight, false);

	return inflight[READ] + inflight[WRITE];
}
EXPORT_SYMBOL_GPL(bdev_count_inflight);

/*
 * Can be deleted altogether. Later.
 *
 */
#define BLKDEV_MAJOR_HASH_SIZE 255
static struct blk_major_name {
	struct blk_major_name *next;
	int major;
	char name[16];
#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD
	void (*probe)(dev_t devt);
#endif
} *major_names[BLKDEV_MAJOR_HASH_SIZE];
static DEFINE_MUTEX(major_names_lock);
static DEFINE_SPINLOCK(major_names_spinlock);

/* index in the above - for now: assume no multimajor ranges */
static inline int major_to_index(unsigned major)
{
	return major % BLKDEV_MAJOR_HASH_SIZE;
}

#ifdef CONFIG_PROC_FS
void blkdev_show(struct seq_file *seqf, off_t offset)
{
	struct blk_major_name *dp;

	spin_lock(&major_names_spinlock);
	for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next)
		if (dp->major == offset)
			seq_printf(seqf, "%3d %s\n", dp->major, dp->name);
	spin_unlock(&major_names