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/sort.h>
#include <linux/btrfs.h>
#include "async-thread.h"
#include "messages.h"
#include "tree-checker.h"
#include "rcu-string.h"

#define BTRFS_MAX_DATA_CHUNK_SIZE	(10ULL * SZ_1G)

extern struct mutex uuid_mutex;

#define BTRFS_STRIPE_LEN	SZ_64K

/* Used by sanity check for btrfs_raid_types. */
#define const_ffs(n) (__builtin_ctzll(n) + 1)

/*
 * The conversion from BTRFS_BLOCK_GROUP_* bits to btrfs_raid_type requires
 * RAID0 always to be the lowest profile bit.
 * Although it's part of on-disk format and should never change, do extra
 * compile-time sanity checks.
 */
static_assert(const_ffs(BTRFS_BLOCK_GROUP_RAID0) <
	      const_ffs(BTRFS_BLOCK_GROUP_PROFILE_MASK & ~BTRFS_BLOCK_GROUP_RAID0));
static_assert(const_ilog2(BTRFS_BLOCK_GROUP_RAID0) >
	      ilog2(BTRFS_BLOCK_GROUP_TYPE_MASK));

/* ilog2() can handle both constants and variables */
#define BTRFS_BG_FLAG_TO_INDEX(profile)					\
	ilog2((profile) >> (ilog2(BTRFS_BLOCK_GROUP_RAID0) - 1))

enum btrfs_raid_types {
	/* SINGLE is the special one as it doesn't have on-disk bit. */
	BTRFS_RAID_SINGLE  = 0,

	BTRFS_RAID_RAID0   = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID0),
	BTRFS_RAID_RAID1   = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID1),
	BTRFS_RAID_DUP	   = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_DUP),
	BTRFS_RAID_RAID10  = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID10),
	BTRFS_RAID_RAID5   = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID5),
	BTRFS_RAID_RAID6   = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID6),
	BTRFS_RAID_RAID1C3 = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID1C3),
	BTRFS_RAID_RAID1C4 = BTRFS_BG_FLAG_TO_INDEX(BTRFS_BLOCK_GROUP_RAID1C4),

	BTRFS_NR_RAID_TYPES
};

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 */
	u32 stripe_len;
	/* offset of address in stripe */
	u32 stripe_offset;
	/* number of stripe where address falls */
	u64 stripe_nr;
	/* 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)	\
	seqcount_init(&device->data_seqcount)
#else
#define btrfs_device_data_ordered_init(device) 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;

	/*
	 * Device's major-minor number. Must be set even if the device is not
	 * opened (bdev == NULL), unless the device is missing.
	 */
	dev_t devt;
	unsigned long dev_state;
	blk_status_t last_flush_error;

#ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
	seqcount_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;

	/* Bio used for flushing device barriers */
	struct bio flush_bio;
	struct completion flush_wait;

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

	/* 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;

	/* Bandwidth limit for scrub, in bytes */
	u64 scrub_speed_max;
};

/*
 * Block group or device which contains an active swapfile. Used for preventing
 * unsafe operations while a swapfile is active.
 *
 * These are sorted on (ptr, inode) (note that a block group or device can
 * contain more than one swapfile). We compare the pointer values because we
 * don't actually care what the object is, we just need a quick check whether
 * the object exists in the rbtree.
 */
struct btrfs_swapfile_pin {
	struct rb_node node;
	void *ptr;
	struct inode *inode;
	/*
	 * If true, ptr points to a struct btrfs_block_group. Otherwise, ptr
	 * points to a struct btrfs_device.
	 */
	bool is_block_group;
	/*
	 * Only used when 'is_block_group' is true and it is the number of
	 * extents used by a swapfile for this block group ('ptr' field).
	 */
	int bg_extent_count;
};

/*
 * 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)		\
{									\
	preempt_disable();						\
	write_seqcount_begin(&dev->data_seqcount);			\
	dev->name = size;						\
	write_seqcount_end(&dev->data_seqcount);			\
	preempt_enable();						\
}
#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,
	BTRFS_CHUNK_ALLOC_ZONED,
};

/*
 * 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;

	/*
	 * Number of devices under this fsid including missing and
	 * replace-target device and excludes seed devices.
	 */
	u64 num_devices;

	/*
	 * The number of devices that successfully opened, including
	 * replace-target, excludes seed devices.
	 */
	u64 open_devices;

	/* The number of devices that are under the chunk allocation list. */
	u64 rw_devices;

	/* Count of missing devices under this fsid excluding seed device. */
	u64 missing_devices;
	u64 total_rw_bytes;

	/*
	 * Count of devices from btrfs_super_block::num_devices for this fsid,
	 * which includes the seed device, excludes the transient replace-target
	 * device.
	 */
	u64 total_devices;

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

	/*
	 * The mount device or a device with highest generation after removal
	 * or replace.
	 */
	struct btrfs_device *latest_dev;

	/* 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;
	/* Devices support TRIM/discard commands */
	bool discardable;

	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_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)

struct btrfs_io_stripe {
	struct btrfs_device *dev;
	union {
		/* Block mapping */
		u64 physical;
		/* For the endio handler */
		struct btrfs_io_context *bioc;
	};
};

struct btrfs_discard_stripe {
	struct btrfs_device *dev;
	u64 physical;
	u64 length;
};

/*
 * Context for IO subsmission for device stripe.
 *
 * - Track the unfinished mirrors for mirror based profiles
 *   Mirror based profiles are SINGLE/DUP/RAID1/RAID10.
 *
 * - Contain the logical -> physical mapping info
 *   Used by submit_stripe_bio() for mapping logical bio
 *   into physical device address.
 *
 * - Contain device replace info
 *   Used by handle_ops_on_dev_replace() to copy logical bios
 *   into the new device.
 *
 * - Contain RAID56 full stripe logical bytenrs
 */
struct btrfs_io_context {
	refcount_t refs;
	struct btrfs_fs_info *fs_info;
	u64 map_type; /* get from map_lookup->type */
	struct bio *orig_bio;
	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_io_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;
	u32 stripe_len;
	int num_stripes;
	int sub_stripes;
	int verified_stripes; /* For mount time dev extent verification */
	struct btrfs_io_stripe stripes[];
};

#define map_lookup_size(n) (sizeof(struct map_lookup) + \
			    (sizeof(struct btrfs_io_stripe) * (n)))

struct btrfs_balance_args;
struct btrfs_balance_progress;
struct btrfs_balance_control {
	struct btrfs_balance_args data;
	struct btrfs_balance_args