path: root/fs/btrfs/volumes.h

/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#ifndef BTRFS_VOLUMES_H
#define BTRFS_VOLUMES_H

#include <linux/bio.h>
#include <linux/sort.h>
#include <linux/btrfs.h>
#include "async-thread.h"

#define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)

extern struct mutex uuid_mutex;

#define BTRFS_STRIPE_LEN	SZ_64K

struct btrfs_io_geometry {
	/* remaining bytes before crossing a stripe */
	u64 len;
	/* offset of logical address in chunk */
	u64 offset;
	/* length of single IO stripe */
	u64 stripe_len;
	/* number of stripe where address falls */
	u64 stripe_nr;
	/* offset of address in stripe */
	u64 stripe_offset;
	/* offset of raid56 stripe into the chunk */
	u64 raid56_stripe_offset;
};

/*
 * Use sequence counter to get consistent device stat data on
 * 32-bit processors.
 */
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define __BTRFS_NEED_DEVICE_DATA_ORDERED
#define btrfs_device_data_ordered_init(device, info)				\
	seqcount_mutex_init(&device->data_seqcount, &info->chunk_mutex)
#else
#define btrfs_device_data_ordered_init(device, info) do { } while (0)
#endif

#define BTRFS_DEV_STATE_WRITEABLE	(0)
#define BTRFS_DEV_STATE_IN_FS_METADATA	(1)
#define BTRFS_DEV_STATE_MISSING		(2)
#define BTRFS_DEV_STATE_REPLACE_TGT	(3)
#define BTRFS_DEV_STATE_FLUSH_SENT	(4)
#define BTRFS_DEV_STATE_NO_READA	(5)

struct btrfs_zoned_device_info;

struct btrfs_device {
	struct list_head dev_list; /* device_list_mutex */
	struct list_head dev_alloc_list; /* chunk mutex */
	struct list_head post_commit_list; /* chunk mutex */
	struct btrfs_fs_devices *fs_devices;
	struct btrfs_fs_info *fs_info;

	struct rcu_string __rcu *name;

	u64 generation;

	struct block_device *bdev;

	struct btrfs_zoned_device_info *zone_info;

	/* the mode sent to blkdev_get */
	fmode_t mode;

	unsigned long dev_state;
	blk_status_t last_flush_error;

#ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
	/* A seqcount_t with associated chunk_mutex (for lockdep) */
	seqcount_mutex_t data_seqcount;
#endif

	/* the internal btrfs device id */
	u64 devid;

	/* size of the device in memory */
	u64 total_bytes;

	/* size of the device on disk */
	u64 disk_total_bytes;

	/* bytes used */
	u64 bytes_used;

	/* optimal io alignment for this device */
	u32 io_align;

	/* optimal io width for this device */
	u32 io_width;
	/* type and info about this device */
	u64 type;

	/* minimal io size for this device */
	u32 sector_size;

	/* physical drive uuid (or lvm uuid) */
	u8 uuid[BTRFS_UUID_SIZE];

	/*
	 * size of the device on the current transaction
	 *
	 * This variant is update when committing the transaction,
	 * and protected by chunk mutex
	 */
	u64 commit_total_bytes;

	/* bytes used on the current transaction */
	u64 commit_bytes_used;

	/* for sending down flush barriers */
	struct bio *flush_bio;
	struct completion flush_wait;

	/* per-device scrub information */
	struct scrub_ctx *scrub_ctx;

	/* readahead state */
	atomic_t reada_in_flight;
	u64 reada_next;
	struct reada_zone *reada_curr_zone;
	struct radix_tree_root reada_zones;
	struct radix_tree_root reada_extents;

	/* disk I/O failure stats. For detailed description refer to
	 * enum btrfs_dev_stat_values in ioctl.h */
	int dev_stats_valid;

	/* Counter to record the change of device stats */
	atomic_t dev_stats_ccnt;
	atomic_t dev_stat_values[BTRFS_DEV_STAT_VALUES_MAX];

	struct extent_io_tree alloc_state;

	struct completion kobj_unregister;
	/* For sysfs/FSID/devinfo/devid/ */
	struct kobject devid_kobj;
};

/*
 * If we read those variants at the context of their own lock, we needn't
 * use the following helpers, reading them directly is safe.
 */
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#define BTRFS_DEVICE_GETSET_FUNCS(name)					\
static inline u64							\
btrfs_device_get_##name(const struct btrfs_device *dev)			\
{									\
	u64 size;							\
	unsigned int seq;						\
									\
	do {								\
		seq = read_seqcount_begin(&dev->data_seqcount);		\
		size = dev->name;					\
	} while (read_seqcount_retry(&dev->data_seqcount, seq));	\
	return size;							\
}									\
									\
static inline void							\
btrfs_device_set_##name(struct btrfs_device *dev, u64 size)		\
{									\
	write_seqcount_begin(&dev->data_seqcount);			\
	dev->name = size;						\
	write_seqcount_end(&dev->data_seqcount);			\
}
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
#define BTRFS_DEVICE_GETSET_FUNCS(name)					\
static inline u64							\
btrfs_device_get_##name(const struct btrfs_device *dev)			\
{									\
	u64 size;							\
									\
	preempt_disable();						\
	size = dev->name;						\
	preempt_enable();						\
	return size;							\
}									\
									\
static inline void							\
btrfs_device_set_##name(struct btrfs_device *dev, u64 size)		\
{									\
	preempt_disable();						\
	dev->name = size;						\
	preempt_enable();						\
}
#else
#define BTRFS_DEVICE_GETSET_FUNCS(name)					\
static inline u64							\
btrfs_device_get_##name(const struct btrfs_device *dev)			\
{									\
	return dev->name;						\
}									\
									\
static inline void							\
btrfs_device_set_##name(struct btrfs_device *dev, u64 size)		\
{									\
	dev->name = size;						\
}
#endif

BTRFS_DEVICE_GETSET_FUNCS(total_bytes);
BTRFS_DEVICE_GETSET_FUNCS(disk_total_bytes);
BTRFS_DEVICE_GETSET_FUNCS(bytes_used);

enum btrfs_chunk_allocation_policy {
	BTRFS_CHUNK_ALLOC_REGULAR,
};

/*
 * Read policies for mirrored block group profiles, read picks the stripe based
 * on these policies.
 */
enum btrfs_read_policy {
	/* Use process PID to choose the stripe */
	BTRFS_READ_POLICY_PID,
	BTRFS_NR_READ_POLICY,
};

struct btrfs_fs_devices {
	u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
	u8 metadata_uuid[BTRFS_FSID_SIZE];
	bool fsid_change;
	struct list_head fs_list;

	u64 num_devices;
	u64 open_devices;
	u64 rw_devices;
	u64 missing_devices;
	u64 total_rw_bytes;
	u64 total_devices;

	/* Highest generation number of seen devices */
	u64 latest_generation;

	struct block_device *latest_bdev;

	/* all of the devices in the FS, protected by a mutex
	 * so we can safely walk it to write out the supers without
	 * worrying about add/remove by the multi-device code.
	 * Scrubbing super can kick off supers writing by holding
	 * this mutex lock.
	 */
	struct mutex device_list_mutex;

	/* List of all devices, protected by device_list_mutex */
	struct list_head devices;

	/*
	 * Devices which can satisfy space allocation. Protected by
	 * chunk_mutex
	 */
	struct list_head alloc_list;

	struct list_head seed_list;
	bool seeding;

	int opened;

	/* set when we find or add a device that doesn't have the
	 * nonrot flag set
	 */
	bool rotating;

	struct btrfs_fs_info *fs_info;
	/* sysfs kobjects */
	struct kobject fsid_kobj;
	struct kobject *devices_kobj;
	struct kobject *devinfo_kobj;
	struct completion kobj_unregister;

	enum btrfs_chunk_allocation_policy chunk_alloc_policy;

	/* Policy used to read the mirrored stripes */
	enum btrfs_read_policy read_policy;
};

#define BTRFS_BIO_INLINE_CSUM_SIZE	64

#define BTRFS_MAX_DEVS(info) ((BTRFS_MAX_ITEM_SIZE(info)	\
			- sizeof(struct btrfs_chunk))		\
			/ sizeof(struct btrfs_stripe) + 1)

#define BTRFS_MAX_DEVS_SYS_CHUNK ((BTRFS_SYSTEM_CHUNK_ARRAY_SIZE	\
				- 2 * sizeof(struct btrfs_disk_key)	\
				- 2 * sizeof(struct btrfs_chunk))	\
				/ sizeof(struct btrfs_stripe) + 1)

/*
 * we need the mirror number and stripe index to be passed around
 * the call chain while we are processing end_io (especially errors).
 * Really, what we need is a btrfs_bio structure that has this info
 * and is properly sized with its stripe array, but we're not there
 * quite yet.  We have our own btrfs bioset, and all of the bios
 * we allocate are actually btrfs_io_bios.  We'll cram as much of
 * struct btrfs_bio as we can into this over time.
 */
struct btrfs_io_bio {
	unsigned int mirror_num;
	struct btrfs_device *device;
	u64 logical;
	u8 *csum;
	u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
	struct bvec_iter iter;
	/*
	 * This member must come last, bio_alloc_bioset will allocate enough
	 * bytes for entire btrfs_io_bio but relies on bio being last.
	 */
	struct bio bio;
};

static inline struct btrfs_io_bio *btrfs_io_bio(struct bio *bio)
{
	return container_of(bio, struct btrfs_io_bio, bio);
}

static inline void btrfs_io_bio_free_csum(struct btrfs_io_bio *io_bio)
{
	if (io_bio->csum != io_bio->csum_inline) {
		kfree(io_bio->csum);
		io_bio->csum = NULL;
	}
}

struct btrfs_bio_stripe {
	struct btrfs_device *dev;
	u64 physical;
	u64 length; /* only used for discard mappings */
};

struct btrfs_bio {
	refcount_t refs;
	atomic_t stripes_pending;
	struct btrfs_fs_info *fs_info;
	u64 map_type; /* get from map_lookup->type */
	bio_end_io_t *end_io;
	struct bio *orig_bio;
	void *private;
	atomic_t error;
	int max_errors;
	int num_stripes;
	int mirror_num;
	int num_tgtdevs;
	int *tgtdev_map;
	/*
	 * logical block numbers for the start of each stripe
	 * The last one or two are p/q.  These are sorted,
	 * so raid_map[0] is the start of our full stripe
	 */
	u64 *raid_map;
	struct btrfs_bio_stripe stripes[];
};

struct btrfs_device_info {
	struct btrfs_device *dev;
	u64 dev_offset;
	u64 max_avail;
	u64 total_avail;
};

struct btrfs_raid_attr {
	u8 sub_stripes;		/* sub_stripes info for map */
	u8 dev_stripes;		/* stripes per dev */
	u8 devs_max;		/* max devs to use */
	u8 devs_min;		/* min devs needed */
	u8 tolerated_failures;	/* max tolerated fail devs */
	u8 devs_increment;	/* ndevs has to be a multiple of this */
	u8 ncopies;		/* how many copies to data has */
	u8 nparity;		/* number of stripes worth of bytes to store
				 * parity information */
	u8 mindev_error;	/* error code if min devs requisite is unmet */
	const char raid_name[8]; /* name of the raid */
	u64 bg_flag;		/* block group flag of the raid */
};

extern const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES];

struct map_lookup {
	u64 type;
	int io_align;
	int io_width;
	u64 stripe_len;
	int num_stripes;
	int sub_stripes