#include <asm/kmap_types.h>
#include <linux/pagemap.h>
#include <linux/btrfs.h>
+#include <linux/btrfs_tree.h>
#include <linux/workqueue.h>
#include <linux/security.h>
#include <linux/sizes.h>
#define BTRFS_COMPAT_EXTENT_TREE_V0
-/* holds pointers to all of the tree roots */
-#define BTRFS_ROOT_TREE_OBJECTID 1ULL
-
-/* stores information about which extents are in use, and reference counts */
-#define BTRFS_EXTENT_TREE_OBJECTID 2ULL
-
-/*
- * chunk tree stores translations from logical -> physical block numbering
- * the super block points to the chunk tree
- */
-#define BTRFS_CHUNK_TREE_OBJECTID 3ULL
-
-/*
- * stores information about which areas of a given device are in use.
- * one per device. The tree of tree roots points to the device tree
- */
-#define BTRFS_DEV_TREE_OBJECTID 4ULL
-
-/* one per subvolume, storing files and directories */
-#define BTRFS_FS_TREE_OBJECTID 5ULL
-
-/* directory objectid inside the root tree */
-#define BTRFS_ROOT_TREE_DIR_OBJECTID 6ULL
-
-/* holds checksums of all the data extents */
-#define BTRFS_CSUM_TREE_OBJECTID 7ULL
-
-/* holds quota configuration and tracking */
-#define BTRFS_QUOTA_TREE_OBJECTID 8ULL
-
-/* for storing items that use the BTRFS_UUID_KEY* types */
-#define BTRFS_UUID_TREE_OBJECTID 9ULL
-
-/* tracks free space in block groups. */
-#define BTRFS_FREE_SPACE_TREE_OBJECTID 10ULL
-
-/* device stats in the device tree */
-#define BTRFS_DEV_STATS_OBJECTID 0ULL
-
-/* for storing balance parameters in the root tree */
-#define BTRFS_BALANCE_OBJECTID -4ULL
-
-/* orhpan objectid for tracking unlinked/truncated files */
-#define BTRFS_ORPHAN_OBJECTID -5ULL
-
-/* does write ahead logging to speed up fsyncs */
-#define BTRFS_TREE_LOG_OBJECTID -6ULL
-#define BTRFS_TREE_LOG_FIXUP_OBJECTID -7ULL
-
-/* for space balancing */
-#define BTRFS_TREE_RELOC_OBJECTID -8ULL
-#define BTRFS_DATA_RELOC_TREE_OBJECTID -9ULL
-
-/*
- * extent checksums all have this objectid
- * this allows them to share the logging tree
- * for fsyncs
- */
-#define BTRFS_EXTENT_CSUM_OBJECTID -10ULL
-
-/* For storing free space cache */
-#define BTRFS_FREE_SPACE_OBJECTID -11ULL
-
-/*
- * The inode number assigned to the special inode for storing
- * free ino cache
- */
-#define BTRFS_FREE_INO_OBJECTID -12ULL
-
-/* dummy objectid represents multiple objectids */
-#define BTRFS_MULTIPLE_OBJECTIDS -255ULL
-
-/*
- * All files have objectids in this range.
- */
-#define BTRFS_FIRST_FREE_OBJECTID 256ULL
-#define BTRFS_LAST_FREE_OBJECTID -256ULL
-#define BTRFS_FIRST_CHUNK_TREE_OBJECTID 256ULL
-
-
-/*
- * the device items go into the chunk tree. The key is in the form
- * [ 1 BTRFS_DEV_ITEM_KEY device_id ]
- */
-#define BTRFS_DEV_ITEMS_OBJECTID 1ULL
-
-#define BTRFS_BTREE_INODE_OBJECTID 1
-
-#define BTRFS_EMPTY_SUBVOL_DIR_OBJECTID 2
-
-#define BTRFS_DEV_REPLACE_DEVID 0ULL
-
/*
* the max metadata block size. This limit is somewhat artificial,
* but the memmove costs go through the roof for larger blocks.
*/
#define BTRFS_LINK_MAX 65535U
-/* 32 bytes in various csum fields */
-#define BTRFS_CSUM_SIZE 32
-
-/* csum types */
-#define BTRFS_CSUM_TYPE_CRC32 0
-
static const int btrfs_csum_sizes[] = { 4 };
/* four bytes for CRC32 */
/* spefic to btrfs_map_block(), therefore not in include/linux/blk_types.h */
#define REQ_GET_READ_MIRRORS (1 << 30)
-#define BTRFS_FT_UNKNOWN 0
-#define BTRFS_FT_REG_FILE 1
-#define BTRFS_FT_DIR 2
-#define BTRFS_FT_CHRDEV 3
-#define BTRFS_FT_BLKDEV 4
-#define BTRFS_FT_FIFO 5
-#define BTRFS_FT_SOCK 6
-#define BTRFS_FT_SYMLINK 7
-#define BTRFS_FT_XATTR 8
-#define BTRFS_FT_MAX 9
-
/* ioprio of readahead is set to idle */
#define BTRFS_IOPRIO_READA (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_IDLE, 0))
#define BTRFS_MAX_EXTENT_SIZE SZ_128M
-/*
- * The key defines the order in the tree, and so it also defines (optimal)
- * block layout.
- *
- * objectid corresponds to the inode number.
- *
- * type tells us things about the object, and is a kind of stream selector.
- * so for a given inode, keys with type of 1 might refer to the inode data,
- * type of 2 may point to file data in the btree and type == 3 may point to
- * extents.
- *
- * offset is the starting byte offset for this key in the stream.
- *
- * btrfs_disk_key is in disk byte order. struct btrfs_key is always
- * in cpu native order. Otherwise they are identical and their sizes
- * should be the same (ie both packed)
- */
-struct btrfs_disk_key {
- __le64 objectid;
- u8 type;
- __le64 offset;
-} __attribute__ ((__packed__));
-
-struct btrfs_key {
- u64 objectid;
- u8 type;
- u64 offset;
-} __attribute__ ((__packed__));
-
struct btrfs_mapping_tree {
struct extent_map_tree map_tree;
};
-struct btrfs_dev_item {
- /* the internal btrfs device id */
- __le64 devid;
-
- /* size of the device */
- __le64 total_bytes;
-
- /* bytes used */
- __le64 bytes_used;
-
- /* optimal io alignment for this device */
- __le32 io_align;
-
- /* optimal io width for this device */
- __le32 io_width;
-
- /* minimal io size for this device */
- __le32 sector_size;
-
- /* type and info about this device */
- __le64 type;
-
- /* expected generation for this device */
- __le64 generation;
-
- /*
- * starting byte of this partition on the device,
- * to allow for stripe alignment in the future
- */
- __le64 start_offset;
-
- /* grouping information for allocation decisions */
- __le32 dev_group;
-
- /* seek speed 0-100 where 100 is fastest */
- u8 seek_speed;
-
- /* bandwidth 0-100 where 100 is fastest */
- u8 bandwidth;
-
- /* btrfs generated uuid for this device */
- u8 uuid[BTRFS_UUID_SIZE];
-
- /* uuid of FS who owns this device */
- u8 fsid[BTRFS_UUID_SIZE];
-} __attribute__ ((__packed__));
-
-struct btrfs_stripe {
- __le64 devid;
- __le64 offset;
- u8 dev_uuid[BTRFS_UUID_SIZE];
-} __attribute__ ((__packed__));
-
-struct btrfs_chunk {
- /* size of this chunk in bytes */
- __le64 length;
-
- /* objectid of the root referencing this chunk */
- __le64 owner;
-
- __le64 stripe_len;
- __le64 type;
-
- /* optimal io alignment for this chunk */
- __le32 io_align;
-
- /* optimal io width for this chunk */
- __le32 io_width;
-
- /* minimal io size for this chunk */
- __le32 sector_size;
-
- /* 2^16 stripes is quite a lot, a second limit is the size of a single
- * item in the btree
- */
- __le16 num_stripes;
-
- /* sub stripes only matter for raid10 */
- __le16 sub_stripes;
- struct btrfs_stripe stripe;
- /* additional stripes go here */
-} __attribute__ ((__packed__));
-
-#define BTRFS_FREE_SPACE_EXTENT 1
-#define BTRFS_FREE_SPACE_BITMAP 2
-
-struct btrfs_free_space_entry {
- __le64 offset;
- __le64 bytes;
- u8 type;
-} __attribute__ ((__packed__));
-
-struct btrfs_free_space_header {
- struct btrfs_disk_key location;
- __le64 generation;
- __le64 num_entries;
- __le64 num_bitmaps;
-} __attribute__ ((__packed__));
-
static inline unsigned long btrfs_chunk_item_size(int num_stripes)
{
BUG_ON(num_stripes == 0);
sizeof(struct btrfs_stripe) * (num_stripes - 1);
}
-#define BTRFS_HEADER_FLAG_WRITTEN (1ULL << 0)
-#define BTRFS_HEADER_FLAG_RELOC (1ULL << 1)
-
/*
* File system states
*/
#define BTRFS_FS_STATE_TRANS_ABORTED 2
#define BTRFS_FS_STATE_DEV_REPLACING 3
-/* Super block flags */
-/* Errors detected */
-#define BTRFS_SUPER_FLAG_ERROR (1ULL << 2)
-
-#define BTRFS_SUPER_FLAG_SEEDING (1ULL << 32)
-#define BTRFS_SUPER_FLAG_METADUMP (1ULL << 33)
-
#define BTRFS_BACKREF_REV_MAX 256
#define BTRFS_BACKREF_REV_SHIFT 56
#define BTRFS_BACKREF_REV_MASK (((u64)BTRFS_BACKREF_REV_MAX - 1) << \
* room to translate 14 chunks with 3 stripes each.
*/
#define BTRFS_SYSTEM_CHUNK_ARRAY_SIZE 2048
-#define BTRFS_LABEL_SIZE 256
/*
* just in case we somehow lose the roots and are not able to mount,
* Compat flags that we support. If any incompat flags are set other than the
* ones specified below then we will fail to mount
*/
-#define BTRFS_FEATURE_COMPAT_RO_FREE_SPACE_TREE (1ULL << 0)
-
-#define BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF (1ULL << 0)
-#define BTRFS_FEATURE_INCOMPAT_DEFAULT_SUBVOL (1ULL << 1)
-#define BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS (1ULL << 2)
-#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO (1ULL << 3)
-/*
- * some patches floated around with a second compression method
- * lets save that incompat here for when they do get in
- * Note we don't actually support it, we're just reserving the
- * number
- */
-#define BTRFS_FEATURE_INCOMPAT_COMPRESS_LZOv2 (1ULL << 4)
-
-/*
- * older kernels tried to do bigger metadata blocks, but the
- * code was pretty buggy. Lets not let them try anymore.
- */
-#define BTRFS_FEATURE_INCOMPAT_BIG_METADATA (1ULL << 5)
-
-#define BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF (1ULL << 6)
-#define BTRFS_FEATURE_INCOMPAT_RAID56 (1ULL << 7)
-#define BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA (1ULL << 8)
-#define BTRFS_FEATURE_INCOMPAT_NO_HOLES (1ULL << 9)
-
#define BTRFS_FEATURE_COMPAT_SUPP 0ULL
#define BTRFS_FEATURE_COMPAT_SAFE_SET 0ULL
#define BTRFS_FEATURE_COMPAT_SAFE_CLEAR 0ULL
unsigned int need_commit_sem:1;
unsigned int skip_release_on_error:1;
};
-
-/*
- * items in the extent btree are used to record the objectid of the
- * owner of the block and the number of references
- */
-
-struct btrfs_extent_item {
- __le64 refs;
- __le64 generation;
- __le64 flags;
-} __attribute__ ((__packed__));
-
-struct btrfs_extent_item_v0 {
- __le32 refs;
-} __attribute__ ((__packed__));
-
#define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r) >> 4) - \
sizeof(struct btrfs_item))
-
-#define BTRFS_EXTENT_FLAG_DATA (1ULL << 0)
-#define BTRFS_EXTENT_FLAG_TREE_BLOCK (1ULL << 1)
-
-/* following flags only apply to tree blocks */
-
-/* use full backrefs for extent pointers in the block */
-#define BTRFS_BLOCK_FLAG_FULL_BACKREF (1ULL << 8)
-
-/*
- * this flag is only used internally by scrub and may be changed at any time
- * it is only declared here to avoid collisions
- */
-#define BTRFS_EXTENT_FLAG_SUPER (1ULL << 48)
-
-struct btrfs_tree_block_info {
- struct btrfs_disk_key key;
- u8 level;
-} __attribute__ ((__packed__));
-
-struct btrfs_extent_data_ref {
- __le64 root;
- __le64 objectid;
- __le64 offset;
- __le32 count;
-} __attribute__ ((__packed__));
-
-struct btrfs_shared_data_ref {
- __le32 count;
-} __attribute__ ((__packed__));
-
-struct btrfs_extent_inline_ref {
- u8 type;
- __le64 offset;
-} __attribute__ ((__packed__));
-
-/* old style backrefs item */
-struct btrfs_extent_ref_v0 {
- __le64 root;
- __le64 generation;
- __le64 objectid;
- __le32 count;
-} __attribute__ ((__packed__));
-
-
-/* dev extents record free space on individual devices. The owner
- * field points back to the chunk allocation mapping tree that allocated
- * the extent. The chunk tree uuid field is a way to double check the owner
- */
-struct btrfs_dev_extent {
- __le64 chunk_tree;
- __le64 chunk_objectid;
- __le64 chunk_offset;
- __le64 length;
- u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
-} __attribute__ ((__packed__));
-
-struct btrfs_inode_ref {
- __le64 index;
- __le16 name_len;
- /* name goes here */
-} __attribute__ ((__packed__));
-
-struct btrfs_inode_extref {
- __le64 parent_objectid;
- __le64 index;
- __le16 name_len;
- __u8 name[0];
- /* name goes here */
-} __attribute__ ((__packed__));
-
-struct btrfs_timespec {
- __le64 sec;
- __le32 nsec;
-} __attribute__ ((__packed__));
-
-struct btrfs_inode_item {
- /* nfs style generation number */
- __le64 generation;
- /* transid that last touched this inode */
- __le64 transid;
- __le64 size;
- __le64 nbytes;
- __le64 block_group;
- __le32 nlink;
- __le32 uid;
- __le32 gid;
- __le32 mode;
- __le64 rdev;
- __le64 flags;
-
- /* modification sequence number for NFS */
- __le64 sequence;
-
- /*
- * a little future expansion, for more than this we can
- * just grow the inode item and version it
- */
- __le64 reserved[4];
- struct btrfs_timespec atime;
- struct btrfs_timespec ctime;
- struct btrfs_timespec mtime;
- struct btrfs_timespec otime;
-} __attribute__ ((__packed__));
-
-struct btrfs_dir_log_item {
- __le64 end;
-} __attribute__ ((__packed__));
-
-struct btrfs_dir_item {
- struct btrfs_disk_key location;
- __le64 transid;
- __le16 data_len;
- __le16 name_len;
- u8 type;
-} __attribute__ ((__packed__));
-
-#define BTRFS_ROOT_SUBVOL_RDONLY (1ULL << 0)
-
-/*
- * Internal in-memory flag that a subvolume has been marked for deletion but
- * still visible as a directory
- */
-#define BTRFS_ROOT_SUBVOL_DEAD (1ULL << 48)
-
-struct btrfs_root_item {
- struct btrfs_inode_item inode;
- __le64 generation;
- __le64 root_dirid;
- __le64 bytenr;
- __le64 byte_limit;
- __le64 bytes_used;
- __le64 last_snapshot;
- __le64 flags;
- __le32 refs;
- struct btrfs_disk_key drop_progress;
- u8 drop_level;
- u8 level;
-
- /*
- * The following fields appear after subvol_uuids+subvol_times
- * were introduced.
- */
-
- /*
- * This generation number is used to test if the new fields are valid
- * and up to date while reading the root item. Every time the root item
- * is written out, the "generation" field is copied into this field. If
- * anyone ever mounted the fs with an older kernel, we will have
- * mismatching generation values here and thus must invalidate the
- * new fields. See btrfs_update_root and btrfs_find_last_root for
- * details.
- * the offset of generation_v2 is also used as the start for the memset
- * when invalidating the fields.
- */
- __le64 generation_v2;
- u8 uuid[BTRFS_UUID_SIZE];
- u8 parent_uuid[BTRFS_UUID_SIZE];
- u8 received_uuid[BTRFS_UUID_SIZE];
- __le64 ctransid; /* updated when an inode changes */
- __le64 otransid; /* trans when created */
- __le64 stransid; /* trans when sent. non-zero for received subvol */
- __le64 rtransid; /* trans when received. non-zero for received subvol */
- struct btrfs_timespec ctime;
- struct btrfs_timespec otime;
- struct btrfs_timespec stime;
- struct btrfs_timespec rtime;
- __le64 reserved[8]; /* for future */
-} __attribute__ ((__packed__));
-
-/*
- * this is used for both forward and backward root refs
- */
-struct btrfs_root_ref {
- __le64 dirid;
- __le64 sequence;
- __le16 name_len;
-} __attribute__ ((__packed__));
-
-struct btrfs_disk_balance_args {
- /*
- * profiles to operate on, single is denoted by
- * BTRFS_AVAIL_ALLOC_BIT_SINGLE
- */
- __le64 profiles;
-
- /*
- * usage filter
- * BTRFS_BALANCE_ARGS_USAGE with a single value means '0..N'
- * BTRFS_BALANCE_ARGS_USAGE_RANGE - range syntax, min..max
- */
- union {
- __le64 usage;
- struct {
- __le32 usage_min;
- __le32 usage_max;
- };
- };
-
- /* devid filter */
- __le64 devid;
-
- /* devid subset filter [pstart..pend) */
- __le64 pstart;
- __le64 pend;
-
- /* btrfs virtual address space subset filter [vstart..vend) */
- __le64 vstart;
- __le64 vend;
-
- /*
- * profile to convert to, single is denoted by
- * BTRFS_AVAIL_ALLOC_BIT_SINGLE
- */
- __le64 target;
-
- /* BTRFS_BALANCE_ARGS_* */
- __le64 flags;
-
- /*
- * BTRFS_BALANCE_ARGS_LIMIT with value 'limit'
- * BTRFS_BALANCE_ARGS_LIMIT_RANGE - the extend version can use minimum
- * and maximum
- */
- union {
- __le64 limit;
- struct {
- __le32 limit_min;
- __le32 limit_max;
- };
- };
-
- /*
- * Process chunks that cross stripes_min..stripes_max devices,
- * BTRFS_BALANCE_ARGS_STRIPES_RANGE
- */
- __le32 stripes_min;
- __le32 stripes_max;
-
- __le64 unused[6];
-} __attribute__ ((__packed__));
-
-/*
- * store balance parameters to disk so that balance can be properly
- * resumed after crash or unmount
- */
-struct btrfs_balance_item {
- /* BTRFS_BALANCE_* */
- __le64 flags;
-
- struct btrfs_disk_balance_args data;
- struct btrfs_disk_balance_args meta;
- struct btrfs_disk_balance_args sys;
-
- __le64 unused[4];
-} __attribute__ ((__packed__));
-
-#define BTRFS_FILE_EXTENT_INLINE 0
-#define BTRFS_FILE_EXTENT_REG 1
-#define BTRFS_FILE_EXTENT_PREALLOC 2
-
-struct btrfs_file_extent_item {
- /*
- * transaction id that created this extent
- */
- __le64 generation;
- /*
- * max number of bytes to hold this extent in ram
- * when we split a compressed extent we can't know how big
- * each of the resulting pieces will be. So, this is
- * an upper limit on the size of the extent in ram instead of
- * an exact limit.
- */
- __le64 ram_bytes;
-
- /*
- * 32 bits for the various ways we might encode the data,
- * including compression and encryption. If any of these
- * are set to something a given disk format doesn't understand
- * it is treated like an incompat flag for reading and writing,
- * but not for stat.
- */
- u8 compression;
- u8 encryption;
- __le16 other_encoding; /* spare for later use */
-
- /* are we inline data or a real extent? */
- u8 type;
-
- /*
- * disk space consumed by the extent, checksum blocks are included
- * in these numbers
- *
- * At this offset in the structure, the inline extent data start.
- */
- __le64 disk_bytenr;
- __le64 disk_num_bytes;
- /*
- * the logical offset in file blocks (no csums)
- * this extent record is for. This allows a file extent to point
- * into the middle of an existing extent on disk, sharing it
- * between two snapshots (useful if some bytes in the middle of the
- * extent have changed
- */
- __le64 offset;
- /*
- * the logical number of file blocks (no csums included). This
- * always reflects the size uncompressed and without encoding.
- */
- __le64 num_bytes;
-
-} __attribute__ ((__packed__));
-
-struct btrfs_csum_item {
- u8 csum;
-} __attribute__ ((__packed__));
-
-struct btrfs_dev_stats_item {
- /*
- * grow this item struct at the end for future enhancements and keep
- * the existing values unchanged
- */
- __le64 values[BTRFS_DEV_STAT_VALUES_MAX];
-} __attribute__ ((__packed__));
-
-#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_ALWAYS 0
-#define BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_AVOID 1
-#define BTRFS_DEV_REPLACE_ITEM_STATE_NEVER_STARTED 0
-#define BTRFS_DEV_REPLACE_ITEM_STATE_STARTED 1
-#define BTRFS_DEV_REPLACE_ITEM_STATE_SUSPENDED 2
-#define BTRFS_DEV_REPLACE_ITEM_STATE_FINISHED 3
-#define BTRFS_DEV_REPLACE_ITEM_STATE_CANCELED 4
-
struct btrfs_dev_replace {
u64 replace_state; /* see #define above */
u64 time_started; /* seconds since 1-Jan-1970 */
struct btrfs_scrub_progress scrub_progress;
};
-struct btrfs_dev_replace_item {
- /*
- * grow this item struct at the end for future enhancements and keep
- * the existing values unchanged
- */
- __le64 src_devid;
- __le64 cursor_left;
- __le64 cursor_right;
- __le64 cont_reading_from_srcdev_mode;
-
- __le64 replace_state;
- __le64 time_started;
- __le64 time_stopped;
- __le64 num_write_errors;
- __le64 num_uncorrectable_read_errors;
-} __attribute__ ((__packed__));
-
-/* different types of block groups (and chunks) */
-#define BTRFS_BLOCK_GROUP_DATA (1ULL << 0)
-#define BTRFS_BLOCK_GROUP_SYSTEM (1ULL << 1)
-#define BTRFS_BLOCK_GROUP_METADATA (1ULL << 2)
-#define BTRFS_BLOCK_GROUP_RAID0 (1ULL << 3)
-#define BTRFS_BLOCK_GROUP_RAID1 (1ULL << 4)
-#define BTRFS_BLOCK_GROUP_DUP (1ULL << 5)
-#define BTRFS_BLOCK_GROUP_RAID10 (1ULL << 6)
-#define BTRFS_BLOCK_GROUP_RAID5 (1ULL << 7)
-#define BTRFS_BLOCK_GROUP_RAID6 (1ULL << 8)
-#define BTRFS_BLOCK_GROUP_RESERVED (BTRFS_AVAIL_ALLOC_BIT_SINGLE | \
- BTRFS_SPACE_INFO_GLOBAL_RSV)
-
-enum btrfs_raid_types {
- BTRFS_RAID_RAID10,
- BTRFS_RAID_RAID1,
- BTRFS_RAID_DUP,
- BTRFS_RAID_RAID0,
- BTRFS_RAID_SINGLE,
- BTRFS_RAID_RAID5,
- BTRFS_RAID_RAID6,
- BTRFS_NR_RAID_TYPES
-};
-
-#define BTRFS_BLOCK_GROUP_TYPE_MASK (BTRFS_BLOCK_GROUP_DATA | \
- BTRFS_BLOCK_GROUP_SYSTEM | \
- BTRFS_BLOCK_GROUP_METADATA)
-
-#define BTRFS_BLOCK_GROUP_PROFILE_MASK (BTRFS_BLOCK_GROUP_RAID0 | \
- BTRFS_BLOCK_GROUP_RAID1 | \
- BTRFS_BLOCK_GROUP_RAID5 | \
- BTRFS_BLOCK_GROUP_RAID6 | \
- BTRFS_BLOCK_GROUP_DUP | \
- BTRFS_BLOCK_GROUP_RAID10)
-#define BTRFS_BLOCK_GROUP_RAID56_MASK (BTRFS_BLOCK_GROUP_RAID5 | \
- BTRFS_BLOCK_GROUP_RAID6)
-
-/*
- * We need a bit for restriper to be able to tell when chunks of type
- * SINGLE are available. This "extended" profile format is used in
- * fs_info->avail_*_alloc_bits (in-memory) and balance item fields
- * (on-disk). The corresponding on-disk bit in chunk.type is reserved
- * to avoid remappings between two formats in future.
- */
-#define BTRFS_AVAIL_ALLOC_BIT_SINGLE (1ULL << 48)
-
-/*
- * A fake block group type that is used to communicate global block reserve
- * size to userspace via the SPACE_INFO ioctl.
- */
-#define BTRFS_SPACE_INFO_GLOBAL_RSV (1ULL << 49)
-
-#define BTRFS_EXTENDED_PROFILE_MASK (BTRFS_BLOCK_GROUP_PROFILE_MASK | \
- BTRFS_AVAIL_ALLOC_BIT_SINGLE)
-
-static inline u64 chunk_to_extended(u64 flags)
-{
- if ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0)
- flags |= BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-
- return flags;
-}
-static inline u64 extended_to_chunk(u64 flags)
-{
- return flags & ~BTRFS_AVAIL_ALLOC_BIT_SINGLE;
-}
-
-struct btrfs_block_group_item {
- __le64 used;
- __le64 chunk_objectid;
- __le64 flags;
-} __attribute__ ((__packed__));
-
-struct btrfs_free_space_info {
- __le32 extent_count;
- __le32 flags;
-} __attribute__ ((__packed__));
-
-#define BTRFS_FREE_SPACE_USING_BITMAPS (1ULL << 0)
-
-#define BTRFS_QGROUP_LEVEL_SHIFT 48
-static inline u64 btrfs_qgroup_level(u64 qgroupid)
-{
- return qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT;
-}
-
-/*
- * is subvolume quota turned on?
- */
-#define BTRFS_QGROUP_STATUS_FLAG_ON (1ULL << 0)
-/*
- * RESCAN is set during the initialization phase
- */
-#define BTRFS_QGROUP_STATUS_FLAG_RESCAN (1ULL << 1)
-/*
- * Some qgroup entries are known to be out of date,
- * either because the configuration has changed in a way that
- * makes a rescan necessary, or because the fs has been mounted
- * with a non-qgroup-aware version.
- * Turning qouta off and on again makes it inconsistent, too.
- */
-#define BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT (1ULL << 2)
-
-#define BTRFS_QGROUP_STATUS_VERSION 1
-
-struct btrfs_qgroup_status_item {
- __le64 version;
- /*
- * the generation is updated during every commit. As older
- * versions of btrfs are not aware of qgroups, it will be
- * possible to detect inconsistencies by checking the
- * generation on mount time
- */
- __le64 generation;
-
- /* flag definitions see above */
- __le64 flags;
-
- /*
- * only used during scanning to record the progress
- * of the scan. It contains a logical address
- */
- __le64 rescan;
-} __attribute__ ((__packed__));
-
-struct btrfs_qgroup_info_item {
- __le64 generation;
- __le64 rfer;
- __le64 rfer_cmpr;
- __le64 excl;
- __le64 excl_cmpr;
-} __attribute__ ((__packed__));
-
-/* flags definition for qgroup limits */
-#define BTRFS_QGROUP_LIMIT_MAX_RFER (1ULL << 0)
-#define BTRFS_QGROUP_LIMIT_MAX_EXCL (1ULL << 1)
-#define BTRFS_QGROUP_LIMIT_RSV_RFER (1ULL << 2)
-#define BTRFS_QGROUP_LIMIT_RSV_EXCL (1ULL << 3)
-#define BTRFS_QGROUP_LIMIT_RFER_CMPR (1ULL << 4)
-#define BTRFS_QGROUP_LIMIT_EXCL_CMPR (1ULL << 5)
-
-struct btrfs_qgroup_limit_item {
- /*
- * only updated when any of the other values change
- */
- __le64 flags;
- __le64 max_rfer;
- __le64 max_excl;
- __le64 rsv_rfer;
- __le64 rsv_excl;
-} __attribute__ ((__packed__));
-
/* For raid type sysfs entries */
struct raid_kobject {
int raid_type;
struct btrfs_io_ctl io_ctl;
+ /*
+ * Incremented when doing extent allocations and holding a read lock
+ * on the space_info's groups_sem semaphore.
+ * Decremented when an ordered extent that represents an IO against this
+ * block group's range is created (after it's added to its inode's
+ * root's list of ordered extents) or immediately after the allocation
+ * if it's a metadata extent or fallocate extent (for these cases we
+ * don't create ordered extents).
+ */
+ atomic_t reservations;
+
+ /*
+ * Incremented while holding the spinlock *lock* by a task checking if
+ * it can perform a nocow write (incremented if the value for the *ro*
+ * field is 0). Decremented by such tasks once they create an ordered
+ * extent or before that if some error happens before reaching that step.
+ * This is to prevent races between block group relocation and nocow
+ * writes through direct IO.
+ */
+ atomic_t nocow_writers;
+
/* Lock for free space tree operations. */
struct mutex free_space_lock;
atomic_t qgroup_meta_rsv;
};
-struct btrfs_ioctl_defrag_range_args {
- /* start of the defrag operation */
- __u64 start;
-
- /* number of bytes to defrag, use (u64)-1 to say all */
- __u64 len;
-
- /*
- * flags for the operation, which can include turning
- * on compression for this one defrag
- */
- __u64 flags;
-
- /*
- * any extent bigger than this will be considered
- * already defragged. Use 0 to take the kernel default
- * Use 1 to say every single extent must be rewritten
- */
- __u32 extent_thresh;
-
- /*
- * which compression method to use if turning on compression
- * for this defrag operation. If unspecified, zlib will
- * be used
- */
- __u32 compress_type;
-
- /* spare for later */
- __u32 unused[4];
-};
-
-
-/*
- * inode items have the data typically returned from stat and store other
- * info about object characteristics. There is one for every file and dir in
- * the FS
- */
-#define BTRFS_INODE_ITEM_KEY 1
-#define BTRFS_INODE_REF_KEY 12
-#define BTRFS_INODE_EXTREF_KEY 13
-#define BTRFS_XATTR_ITEM_KEY 24
-#define BTRFS_ORPHAN_ITEM_KEY 48
-/* reserve 2-15 close to the inode for later flexibility */
-
-/*
- * dir items are the name -> inode pointers in a directory. There is one
- * for every name in a directory.
- */
-#define BTRFS_DIR_LOG_ITEM_KEY 60
-#define BTRFS_DIR_LOG_INDEX_KEY 72
-#define BTRFS_DIR_ITEM_KEY 84
-#define BTRFS_DIR_INDEX_KEY 96
-/*
- * extent data is for file data
- */
-#define BTRFS_EXTENT_DATA_KEY 108
-
-/*
- * extent csums are stored in a separate tree and hold csums for
- * an entire extent on disk.
- */
-#define BTRFS_EXTENT_CSUM_KEY 128
-
-/*
- * root items point to tree roots. They are typically in the root
- * tree used by the super block to find all the other trees
- */
-#define BTRFS_ROOT_ITEM_KEY 132
-
-/*
- * root backrefs tie subvols and snapshots to the directory entries that
- * reference them
- */
-#define BTRFS_ROOT_BACKREF_KEY 144
-
-/*
- * root refs make a fast index for listing all of the snapshots and
- * subvolumes referenced by a given root. They point directly to the
- * directory item in the root that references the subvol
- */
-#define BTRFS_ROOT_REF_KEY 156
-
-/*
- * extent items are in the extent map tree. These record which blocks
- * are used, and how many references there are to each block
- */
-#define BTRFS_EXTENT_ITEM_KEY 168
-
-/*
- * The same as the BTRFS_EXTENT_ITEM_KEY, except it's metadata we already know
- * the length, so we save the level in key->offset instead of the length.
- */
-#define BTRFS_METADATA_ITEM_KEY 169
-
-#define BTRFS_TREE_BLOCK_REF_KEY 176
-
-#define BTRFS_EXTENT_DATA_REF_KEY 178
-
-#define BTRFS_EXTENT_REF_V0_KEY 180
-
-#define BTRFS_SHARED_BLOCK_REF_KEY 182
-
-#define BTRFS_SHARED_DATA_REF_KEY 184
-
-/*
- * block groups give us hints into the extent allocation trees. Which
- * blocks are free etc etc
- */
-#define BTRFS_BLOCK_GROUP_ITEM_KEY 192
-
-/*
- * Every block group is represented in the free space tree by a free space info
- * item, which stores some accounting information. It is keyed on
- * (block_group_start, FREE_SPACE_INFO, block_group_length).
- */
-#define BTRFS_FREE_SPACE_INFO_KEY 198
-
-/*
- * A free space extent tracks an extent of space that is free in a block group.
- * It is keyed on (start, FREE_SPACE_EXTENT, length).
- */
-#define BTRFS_FREE_SPACE_EXTENT_KEY 199
-
-/*
- * When a block group becomes very fragmented, we convert it to use bitmaps
- * instead of extents. A free space bitmap is keyed on
- * (start, FREE_SPACE_BITMAP, length); the corresponding item is a bitmap with
- * (length / sectorsize) bits.
- */
-#define BTRFS_FREE_SPACE_BITMAP_KEY 200
-
-#define BTRFS_DEV_EXTENT_KEY 204
-#define BTRFS_DEV_ITEM_KEY 216
-#define BTRFS_CHUNK_ITEM_KEY 228
-
-/*
- * Records the overall state of the qgroups.
- * There's only one instance of this key present,
- * (0, BTRFS_QGROUP_STATUS_KEY, 0)
- */
-#define BTRFS_QGROUP_STATUS_KEY 240
-/*
- * Records the currently used space of the qgroup.
- * One key per qgroup, (0, BTRFS_QGROUP_INFO_KEY, qgroupid).
- */
-#define BTRFS_QGROUP_INFO_KEY 242
-/*
- * Contains the user configured limits for the qgroup.
- * One key per qgroup, (0, BTRFS_QGROUP_LIMIT_KEY, qgroupid).
- */
-#define BTRFS_QGROUP_LIMIT_KEY 244
-/*
- * Records the child-parent relationship of qgroups. For
- * each relation, 2 keys are present:
- * (childid, BTRFS_QGROUP_RELATION_KEY, parentid)
- * (parentid, BTRFS_QGROUP_RELATION_KEY, childid)
- */
-#define BTRFS_QGROUP_RELATION_KEY 246
-
-/*
- * Obsolete name, see BTRFS_TEMPORARY_ITEM_KEY.
- */
-#define BTRFS_BALANCE_ITEM_KEY 248
-
-/*
- * The key type for tree items that are stored persistently, but do not need to
- * exist for extended period of time. The items can exist in any tree.
- *
- * [subtype, BTRFS_TEMPORARY_ITEM_KEY, data]
- *
- * Existing items:
- *
- * - balance status item
- * (BTRFS_BALANCE_OBJECTID, BTRFS_TEMPORARY_ITEM_KEY, 0)
- */
-#define BTRFS_TEMPORARY_ITEM_KEY 248
-
-/*
- * Obsolete name, see BTRFS_PERSISTENT_ITEM_KEY
- */
-#define BTRFS_DEV_STATS_KEY 249
-
-/*
- * The key type for tree items that are stored persistently and usually exist
- * for a long period, eg. filesystem lifetime. The item kinds can be status
- * information, stats or preference values. The item can exist in any tree.
- *
- * [subtype, BTRFS_PERSISTENT_ITEM_KEY, data]
- *
- * Existing items:
- *
- * - device statistics, store IO stats in the device tree, one key for all
- * stats
- * (BTRFS_DEV_STATS_OBJECTID, BTRFS_DEV_STATS_KEY, 0)
- */
-#define BTRFS_PERSISTENT_ITEM_KEY 249
-
-/*
- * Persistantly stores the device replace state in the device tree.
- * The key is built like this: (0, BTRFS_DEV_REPLACE_KEY, 0).
- */
-#define BTRFS_DEV_REPLACE_KEY 250
-
-/*
- * Stores items that allow to quickly map UUIDs to something else.
- * These items are part of the filesystem UUID tree.
- * The key is built like this:
- * (UUID_upper_64_bits, BTRFS_UUID_KEY*, UUID_lower_64_bits).
- */
-#if BTRFS_UUID_SIZE != 16
-#error "UUID items require BTRFS_UUID_SIZE == 16!"
-#endif
-#define BTRFS_UUID_KEY_SUBVOL 251 /* for UUIDs assigned to subvols */
-#define BTRFS_UUID_KEY_RECEIVED_SUBVOL 252 /* for UUIDs assigned to
- * received subvols */
-
-/*
- * string items are for debugging. They just store a short string of
- * data in the FS
- */
-#define BTRFS_STRING_ITEM_KEY 253
-
/*
* Flags for mount options.
*
struct btrfs_root *root);
int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
+ void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
+ const u64 start);
+ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg);
+ bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
+ void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr);
+ void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg);
void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
struct btrfs_root *root, unsigned long count);
/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
+long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
int btrfs_ioctl_get_supported_features(void __user *arg);
void btrfs_update_iflags(struct inode *inode);
void btrfs_inherit_iflags(struct inode *inode, struct inode *dir);
#define ASSERT(expr) ((void)0)
#endif
-#define btrfs_assert()
__printf(5, 6)
__cold
-void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...);
const char *btrfs_decode_error(int errno);
struct btrfs_root *root, const char *function,
unsigned int line, int errno);
+/*
+ * Call btrfs_abort_transaction as early as possible when an error condition is
+ * detected, that way the exact line number is reported.
+ */
+#define btrfs_abort_transaction(trans, root, errno) \
+do { \
+ /* Report first abort since mount */ \
+ if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \
+ &((root)->fs_info->fs_state))) { \
+ WARN(1, KERN_DEBUG \
+ "BTRFS: Transaction aborted (error %d)\n", \
+ (errno)); \
+ } \
+ __btrfs_abort_transaction((trans), (root), __func__, \
+ __LINE__, (errno)); \
+} while (0)
+
+#define btrfs_handle_fs_error(fs_info, errno, fmt, args...) \
+do { \
+ __btrfs_handle_fs_error((fs_info), __func__, __LINE__, \
+ (errno), fmt, ##args); \
+} while (0)
+
+__printf(5, 6)
+__cold
+void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
+ unsigned int line, int errno, const char *fmt, ...);
+/*
+ * If BTRFS_MOUNT_PANIC_ON_FATAL_ERROR is in mount_opt, __btrfs_panic
+ * will panic(). Otherwise we BUG() here.
+ */
+#define btrfs_panic(fs_info, errno, fmt, args...) \
+do { \
+ __btrfs_panic(fs_info, __func__, __LINE__, errno, fmt, ##args); \
+ BUG(); \
+} while (0)
+
+
+/* compatibility and incompatibility defines */
+
#define btrfs_set_fs_incompat(__fs_info, opt) \
__btrfs_set_fs_incompat((__fs_info), BTRFS_FEATURE_INCOMPAT_##opt)
return !!(btrfs_super_compat_ro_flags(disk_super) & flag);
}
-/*
- * Call btrfs_abort_transaction as early as possible when an error condition is
- * detected, that way the exact line number is reported.
- */
-#define btrfs_abort_transaction(trans, root, errno) \
-do { \
- /* Report first abort since mount */ \
- if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \
- &((root)->fs_info->fs_state))) { \
- WARN(1, KERN_DEBUG \
- "BTRFS: Transaction aborted (error %d)\n", \
- (errno)); \
- } \
- __btrfs_abort_transaction((trans), (root), __func__, \
- __LINE__, (errno)); \
-} while (0)
-
-#define btrfs_std_error(fs_info, errno, fmt, args...) \
-do { \
- __btrfs_std_error((fs_info), __func__, __LINE__, \
- (errno), fmt, ##args); \
-} while (0)
-
-__printf(5, 6)
-__cold
-void __btrfs_panic(struct btrfs_fs_info *fs_info, const char *function,
- unsigned int line, int errno, const char *fmt, ...);
-
-/*
- * If BTRFS_MOUNT_PANIC_ON_FATAL_ERROR is in mount_opt, __btrfs_panic
- * will panic(). Otherwise we BUG() here.
- */
-#define btrfs_panic(fs_info, errno, fmt, args...) \
-do { \
- __btrfs_panic(fs_info, __func__, __LINE__, errno, fmt, ##args); \
- BUG(); \
-} while (0)
-
/* acl.c */
#ifdef CONFIG_BTRFS_FS_POSIX_ACL
struct posix_acl *btrfs_get_acl(struct inode *inode, int type);
struct btrfs_fs_info *fs_info,
struct btrfs_device *srcdev,
struct btrfs_device *tgtdev);
-static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid,
- char *srcdev_name,
- struct btrfs_device **device);
static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info);
static int btrfs_dev_replace_kthread(void *data);
static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info);
dev_replace->cursor_left_last_write_of_item;
}
-int btrfs_dev_replace_start(struct btrfs_root *root,
- struct btrfs_ioctl_dev_replace_args *args)
+int btrfs_dev_replace_start(struct btrfs_root *root, char *tgtdev_name,
+ u64 srcdevid, char *srcdev_name, int read_src)
{
struct btrfs_trans_handle *trans;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_device *tgt_device = NULL;
struct btrfs_device *src_device = NULL;
- switch (args->start.cont_reading_from_srcdev_mode) {
- case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS:
- case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID:
- break;
- default:
- return -EINVAL;
- }
-
- if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
- args->start.tgtdev_name[0] == '\0')
- return -EINVAL;
-
/* the disk copy procedure reuses the scrub code */
mutex_lock(&fs_info->volume_mutex);
- ret = btrfs_dev_replace_find_srcdev(root, args->start.srcdevid,
- args->start.srcdev_name,
- &src_device);
+ ret = btrfs_find_device_by_devspec(root, srcdevid,
+ srcdev_name, &src_device);
if (ret) {
mutex_unlock(&fs_info->volume_mutex);
return ret;
}
- ret = btrfs_init_dev_replace_tgtdev(root, args->start.tgtdev_name,
+ ret = btrfs_init_dev_replace_tgtdev(root, tgtdev_name,
src_device, &tgt_device);
mutex_unlock(&fs_info->volume_mutex);
if (ret)
break;
case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
- args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED;
+ ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED;
goto leave;
}
- dev_replace->cont_reading_from_srcdev_mode =
- args->start.cont_reading_from_srcdev_mode;
+ dev_replace->cont_reading_from_srcdev_mode = read_src;
WARN_ON(!src_device);
dev_replace->srcdev = src_device;
WARN_ON(!tgt_device);
dev_replace->tgtdev = tgt_device;
- btrfs_info_in_rcu(root->fs_info,
+ btrfs_info_in_rcu(fs_info,
"dev_replace from %s (devid %llu) to %s started",
src_device->missing ? "<missing disk>" :
rcu_str_deref(src_device->name),
dev_replace->item_needs_writeback = 1;
atomic64_set(&dev_replace->num_write_errors, 0);
atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0);
- args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
btrfs_dev_replace_unlock(dev_replace, 1);
ret = btrfs_sysfs_add_device_link(tgt_device->fs_devices, tgt_device);
if (ret)
- btrfs_err(root->fs_info, "kobj add dev failed %d\n", ret);
+ btrfs_err(fs_info, "kobj add dev failed %d\n", ret);
- btrfs_wait_ordered_roots(fs_info, -1);
+ btrfs_wait_ordered_roots(root->fs_info, -1, 0, (u64)-1);
/* force writing the updated state information to disk */
trans = btrfs_start_transaction(root, 0);
btrfs_device_get_total_bytes(src_device),
&dev_replace->scrub_progress, 0, 1);
- ret = btrfs_dev_replace_finishing(root->fs_info, ret);
- /* don't warn if EINPROGRESS, someone else might be running scrub */
+ ret = btrfs_dev_replace_finishing(fs_info, ret);
if (ret == -EINPROGRESS) {
- args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
- ret = 0;
+ ret = BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS;
} else {
WARN_ON(ret);
}
return ret;
}
+int btrfs_dev_replace_by_ioctl(struct btrfs_root *root,
+ struct btrfs_ioctl_dev_replace_args *args)
+{
+ int ret;
+
+ switch (args->start.cont_reading_from_srcdev_mode) {
+ case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS:
+ case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID:
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
+ args->start.tgtdev_name[0] == '\0')
+ return -EINVAL;
+
+ ret = btrfs_dev_replace_start(root, args->start.tgtdev_name,
+ args->start.srcdevid,
+ args->start.srcdev_name,
+ args->start.cont_reading_from_srcdev_mode);
+ args->result = ret;
+ /* don't warn if EINPROGRESS, someone else might be running scrub */
+ if (ret == BTRFS_IOCTL_DEV_REPLACE_RESULT_SCRUB_INPROGRESS)
+ ret = 0;
+
+ return ret;
+}
+
/*
* blocked until all flighting bios are finished.
*/
mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
return ret;
}
- btrfs_wait_ordered_roots(root->fs_info, -1);
+ btrfs_wait_ordered_roots(root->fs_info, -1, 0, (u64)-1);
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ASSERT(list_empty(&src_device->resized_list));
tgt_device->commit_total_bytes = src_device->commit_total_bytes;
tgt_device->commit_bytes_used = src_device->bytes_used;
- if (fs_info->sb->s_bdev == src_device->bdev)
- fs_info->sb->s_bdev = tgt_device->bdev;
- if (fs_info->fs_devices->latest_bdev == src_device->bdev)
- fs_info->fs_devices->latest_bdev = tgt_device->bdev;
+
+ btrfs_assign_next_active_device(fs_info, src_device, tgt_device);
+
list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
fs_info->fs_devices->rw_devices++;
write_unlock(&em_tree->lock);
}
-static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid,
- char *srcdev_name,
- struct btrfs_device **device)
-{
- int ret;
-
- if (srcdevid) {
- ret = 0;
- *device = btrfs_find_device(root->fs_info, srcdevid, NULL,
- NULL);
- if (!*device)
- ret = -ENOENT;
- } else {
- ret = btrfs_find_device_missing_or_by_path(root, srcdev_name,
- device);
- }
- return ret;
-}
-
void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_dev_replace_args *args)
{
return readonly;
}
+ bool btrfs_inc_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
+ {
+ struct btrfs_block_group_cache *bg;
+ bool ret = true;
+
+ bg = btrfs_lookup_block_group(fs_info, bytenr);
+ if (!bg)
+ return false;
+
+ spin_lock(&bg->lock);
+ if (bg->ro)
+ ret = false;
+ else
+ atomic_inc(&bg->nocow_writers);
+ spin_unlock(&bg->lock);
+
+ /* no put on block group, done by btrfs_dec_nocow_writers */
+ if (!ret)
+ btrfs_put_block_group(bg);
+
+ return ret;
+
+ }
+
+ void btrfs_dec_nocow_writers(struct btrfs_fs_info *fs_info, u64 bytenr)
+ {
+ struct btrfs_block_group_cache *bg;
+
+ bg = btrfs_lookup_block_group(fs_info, bytenr);
+ ASSERT(bg);
+ if (atomic_dec_and_test(&bg->nocow_writers))
+ wake_up_atomic_t(&bg->nocow_writers);
+ /*
+ * Once for our lookup and once for the lookup done by a previous call
+ * to btrfs_inc_nocow_writers()
+ */
+ btrfs_put_block_group(bg);
+ btrfs_put_block_group(bg);
+ }
+
+ static int btrfs_wait_nocow_writers_atomic_t(atomic_t *a)
+ {
+ schedule();
+ return 0;
+ }
+
+ void btrfs_wait_nocow_writers(struct btrfs_block_group_cache *bg)
+ {
+ wait_on_atomic_t(&bg->nocow_writers,
+ btrfs_wait_nocow_writers_atomic_t,
+ TASK_UNINTERRUPTIBLE);
+ }
+
static const char *alloc_name(u64 flags)
{
switch (flags) {
if (need_commit > 0) {
btrfs_start_delalloc_roots(fs_info, 0, -1);
- btrfs_wait_ordered_roots(fs_info, -1);
+ btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
}
trans = btrfs_join_transaction(root);
*/
btrfs_start_delalloc_roots(root->fs_info, 0, nr_items);
if (!current->journal_info)
- btrfs_wait_ordered_roots(root->fs_info, nr_items);
+ btrfs_wait_ordered_roots(root->fs_info, nr_items,
+ 0, (u64)-1);
}
}
/* Calc the number of the pages we need flush for space reservation */
items = calc_reclaim_items_nr(root, to_reclaim);
- to_reclaim = items * EXTENT_SIZE_PER_ITEM;
+ to_reclaim = (u64)items * EXTENT_SIZE_PER_ITEM;
trans = (struct btrfs_trans_handle *)current->journal_info;
block_rsv = &root->fs_info->delalloc_block_rsv;
if (trans)
return;
if (wait_ordered)
- btrfs_wait_ordered_roots(root->fs_info, items);
+ btrfs_wait_ordered_roots(root->fs_info, items,
+ 0, (u64)-1);
return;
}
loops++;
if (wait_ordered && !trans) {
- btrfs_wait_ordered_roots(root->fs_info, items);
+ btrfs_wait_ordered_roots(root->fs_info, items,
+ 0, (u64)-1);
} else {
time_left = schedule_timeout_killable(1);
if (time_left)
return 0;
}
+ static void
+ btrfs_inc_block_group_reservations(struct btrfs_block_group_cache *bg)
+ {
+ atomic_inc(&bg->reservations);
+ }
+
+ void btrfs_dec_block_group_reservations(struct btrfs_fs_info *fs_info,
+ const u64 start)
+ {
+ struct btrfs_block_group_cache *bg;
+
+ bg = btrfs_lookup_block_group(fs_info, start);
+ ASSERT(bg);
+ if (atomic_dec_and_test(&bg->reservations))
+ wake_up_atomic_t(&bg->reservations);
+ btrfs_put_block_group(bg);
+ }
+
+ static int btrfs_wait_bg_reservations_atomic_t(atomic_t *a)
+ {
+ schedule();
+ return 0;
+ }
+
+ void btrfs_wait_block_group_reservations(struct btrfs_block_group_cache *bg)
+ {
+ struct btrfs_space_info *space_info = bg->space_info;
+
+ ASSERT(bg->ro);
+
+ if (!(bg->flags & BTRFS_BLOCK_GROUP_DATA))
+ return;
+
+ /*
+ * Our block group is read only but before we set it to read only,
+ * some task might have had allocated an extent from it already, but it
+ * has not yet created a respective ordered extent (and added it to a
+ * root's list of ordered extents).
+ * Therefore wait for any task currently allocating extents, since the
+ * block group's reservations counter is incremented while a read lock
+ * on the groups' semaphore is held and decremented after releasing
+ * the read access on that semaphore and creating the ordered extent.
+ */
+ down_write(&space_info->groups_sem);
+ up_write(&space_info->groups_sem);
+
+ wait_on_atomic_t(&bg->reservations,
+ btrfs_wait_bg_reservations_atomic_t,
+ TASK_UNINTERRUPTIBLE);
+ }
+
/**
* btrfs_update_reserved_bytes - update the block_group and space info counters
* @cache: The cache we are manipulating
int delalloc)
{
struct btrfs_block_group_cache *used_bg = NULL;
- bool locked = false;
-again:
+
spin_lock(&cluster->refill_lock);
- if (locked) {
- if (used_bg == cluster->block_group)
+ while (1) {
+ used_bg = cluster->block_group;
+ if (!used_bg)
+ return NULL;
+
+ if (used_bg == block_group)
return used_bg;
- up_read(&used_bg->data_rwsem);
- btrfs_put_block_group(used_bg);
- }
+ btrfs_get_block_group(used_bg);
- used_bg = cluster->block_group;
- if (!used_bg)
- return NULL;
+ if (!delalloc)
+ return used_bg;
- if (used_bg == block_group)
- return used_bg;
+ if (down_read_trylock(&used_bg->data_rwsem))
+ return used_bg;
- btrfs_get_block_group(used_bg);
+ spin_unlock(&cluster->refill_lock);
- if (!delalloc)
- return used_bg;
+ down_read(&used_bg->data_rwsem);
- if (down_read_trylock(&used_bg->data_rwsem))
- return used_bg;
+ spin_lock(&cluster->refill_lock);
+ if (used_bg == cluster->block_group)
+ return used_bg;
- spin_unlock(&cluster->refill_lock);
- down_read(&used_bg->data_rwsem);
- locked = true;
- goto again;
+ up_read(&used_bg->data_rwsem);
+ btrfs_put_block_group(used_bg);
+ }
}
static inline void
btrfs_add_free_space(block_group, offset, num_bytes);
goto loop;
}
+ btrfs_inc_block_group_reservations(block_group);
/* we are all good, lets return */
ins->objectid = search_start;
WARN_ON(num_bytes < root->sectorsize);
ret = find_free_extent(root, num_bytes, empty_size, hint_byte, ins,
flags, delalloc);
-
- if (ret == -ENOSPC) {
+ if (!ret && !is_data) {
+ btrfs_dec_block_group_reservations(root->fs_info,
+ ins->objectid);
+ } else if (ret == -ENOSPC) {
if (!final_tried && ins->offset) {
num_bytes = min(num_bytes >> 1, ins->offset);
num_bytes = round_down(num_bytes, root->sectorsize);
if (!for_reloc && root_dropped == false)
btrfs_add_dead_root(root);
if (err && err != -EAGAIN)
- btrfs_std_error(root->fs_info, err, NULL);
+ btrfs_handle_fs_error(root->fs_info, err, NULL);
return err;
}
async_extent->ram_size - 1, 0);
goto out_free_reserve;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
/*
* clear dirty, set writeback and unlock the pages.
}
return;
out_free_reserve:
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_free:
extent_clear_unlock_delalloc(inode, async_extent->start,
goto out_drop_extent_cache;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
+
if (disk_num_bytes < cur_alloc_size)
break;
out_drop_extent_cache:
btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0);
out_reserve:
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
out_unlock:
extent_clear_unlock_delalloc(inode, start, end, locked_page,
*/
if (csum_exist_in_range(root, disk_bytenr, num_bytes))
goto out_check;
+ if (!btrfs_inc_nocow_writers(root->fs_info,
+ disk_bytenr))
+ goto out_check;
nocow = 1;
} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
extent_end = found_key.offset +
path->slots[0]++;
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
+ if (nocow)
+ btrfs_dec_nocow_writers(root->fs_info,
+ disk_bytenr);
goto next_slot;
}
if (!nocow) {
if (ret) {
if (!nolock && nocow)
btrfs_end_write_no_snapshoting(root);
+ if (nocow)
+ btrfs_dec_nocow_writers(root->fs_info,
+ disk_bytenr);
goto error;
}
cow_start = (u64)-1;
ret = btrfs_add_ordered_extent(inode, cur_offset, disk_bytenr,
num_bytes, num_bytes, type);
+ if (nocow)
+ btrfs_dec_nocow_writers(root->fs_info, disk_bytenr);
BUG_ON(ret); /* -ENOMEM */
if (root->root_key.objectid ==
return em;
}
+ static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
+ const u64 start,
+ const u64 len,
+ const u64 orig_start,
+ const u64 block_start,
+ const u64 block_len,
+ const u64 orig_block_len,
+ const u64 ram_bytes,
+ const int type)
+ {
+ struct extent_map *em = NULL;
+ int ret;
+
+ down_read(&BTRFS_I(inode)->dio_sem);
+ if (type != BTRFS_ORDERED_NOCOW) {
+ em = create_pinned_em(inode, start, len, orig_start,
+ block_start, block_len, orig_block_len,
+ ram_bytes, type);
+ if (IS_ERR(em))
+ goto out;
+ }
+ ret = btrfs_add_ordered_extent_dio(inode, start, block_start,
+ len, block_len, type);
+ if (ret) {
+ if (em) {
+ free_extent_map(em);
+ btrfs_drop_extent_cache(inode, start,
+ start + len - 1, 0);
+ }
+ em = ERR_PTR(ret);
+ }
+ out:
+ up_read(&BTRFS_I(inode)->dio_sem);
+
+ return em;
+ }
+
static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
u64 start, u64 len)
{
if (ret)
return ERR_PTR(ret);
- /*
- * Create the ordered extent before the extent map. This is to avoid
- * races with the fast fsync path that would lead to it logging file
- * extent items that point to disk extents that were not yet written to.
- * The fast fsync path collects ordered extents into a local list and
- * then collects all the new extent maps, so we must create the ordered
- * extent first and make sure the fast fsync path collects any new
- * ordered extents after collecting new extent maps as well.
- * The fsync path simply can not rely on inode_dio_wait() because it
- * causes deadlock with AIO.
- */
- ret = btrfs_add_ordered_extent_dio(inode, start, ins.objectid,
- ins.offset, ins.offset, 0);
- if (ret) {
+ em = btrfs_create_dio_extent(inode, start, ins.offset, start,
+ ins.objectid, ins.offset, ins.offset,
+ ins.offset, 0);
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
+ if (IS_ERR(em))
btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
- return ERR_PTR(ret);
- }
-
- em = create_pinned_em(inode, start, ins.offset, start, ins.objectid,
- ins.offset, ins.offset, ins.offset, 0);
- if (IS_ERR(em)) {
- struct btrfs_ordered_extent *oe;
- btrfs_free_reserved_extent(root, ins.objectid, ins.offset, 1);
- oe = btrfs_lookup_ordered_extent(inode, start);
- ASSERT(oe);
- if (WARN_ON(!oe))
- return em;
- set_bit(BTRFS_ORDERED_IOERR, &oe->flags);
- set_bit(BTRFS_ORDERED_IO_DONE, &oe->flags);
- btrfs_remove_ordered_extent(inode, oe);
- /* Once for our lookup and once for the ordered extents tree. */
- btrfs_put_ordered_extent(oe);
- btrfs_put_ordered_extent(oe);
- }
return em;
}
block_start = em->block_start + (start - em->start);
if (can_nocow_extent(inode, start, &len, &orig_start,
- &orig_block_len, &ram_bytes) == 1) {
+ &orig_block_len, &ram_bytes) == 1 &&
+ btrfs_inc_nocow_writers(root->fs_info, block_start)) {
+ struct extent_map *em2;
+
+ em2 = btrfs_create_dio_extent(inode, start, len,
+ orig_start, block_start,
+ len, orig_block_len,
+ ram_bytes, type);
+ btrfs_dec_nocow_writers(root->fs_info, block_start);
if (type == BTRFS_ORDERED_PREALLOC) {
free_extent_map(em);
- em = create_pinned_em(inode, start, len,
- orig_start,
- block_start, len,
- orig_block_len,
- ram_bytes, type);
- if (IS_ERR(em)) {
- ret = PTR_ERR(em);
- goto unlock_err;
- }
+ em = em2;
}
-
- ret = btrfs_add_ordered_extent_dio(inode, start,
- block_start, len, len, type);
- if (ret) {
- free_extent_map(em);
+ if (em2 && IS_ERR(em2)) {
+ ret = PTR_ERR(em2);
goto unlock_err;
}
goto unlock;
INIT_LIST_HEAD(&ei->delalloc_inodes);
INIT_LIST_HEAD(&ei->delayed_iput);
RB_CLEAR_NODE(&ei->rb_node);
+ init_rwsem(&ei->dio_sem);
return inode;
}
return 0;
}
+ static int btrfs_rename_exchange(struct inode *old_dir,
+ struct dentry *old_dentry,
+ struct inode *new_dir,
+ struct dentry *new_dentry)
+ {
+ struct btrfs_trans_handle *trans;
+ struct btrfs_root *root = BTRFS_I(old_dir)->root;
+ struct btrfs_root *dest = BTRFS_I(new_dir)->root;
+ struct inode *new_inode = new_dentry->d_inode;
+ struct inode *old_inode = old_dentry->d_inode;
+ struct timespec ctime = CURRENT_TIME;
+ struct dentry *parent;
+ u64 old_ino = btrfs_ino(old_inode);
+ u64 new_ino = btrfs_ino(new_inode);
+ u64 old_idx = 0;
+ u64 new_idx = 0;
+ u64 root_objectid;
+ int ret;
+ bool root_log_pinned = false;
+ bool dest_log_pinned = false;
+
+ /* we only allow rename subvolume link between subvolumes */
+ if (old_ino != BTRFS_FIRST_FREE_OBJECTID && root != dest)
+ return -EXDEV;
+
+ /* close the race window with snapshot create/destroy ioctl */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
+ down_read(&root->fs_info->subvol_sem);
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
+ down_read(&dest->fs_info->subvol_sem);
+
+ /*
+ * We want to reserve the absolute worst case amount of items. So if
+ * both inodes are subvols and we need to unlink them then that would
+ * require 4 item modifications, but if they are both normal inodes it
+ * would require 5 item modifications, so we'll assume their normal
+ * inodes. So 5 * 2 is 10, plus 2 for the new links, so 12 total items
+ * should cover the worst case number of items we'll modify.
+ */
+ trans = btrfs_start_transaction(root, 12);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_notrans;
+ }
+
+ /*
+ * We need to find a free sequence number both in the source and
+ * in the destination directory for the exchange.
+ */
+ ret = btrfs_set_inode_index(new_dir, &old_idx);
+ if (ret)
+ goto out_fail;
+ ret = btrfs_set_inode_index(old_dir, &new_idx);
+ if (ret)
+ goto out_fail;
+
+ BTRFS_I(old_inode)->dir_index = 0ULL;
+ BTRFS_I(new_inode)->dir_index = 0ULL;
+
+ /* Reference for the source. */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ /* force full log commit if subvolume involved. */
+ btrfs_set_log_full_commit(root->fs_info, trans);
+ } else {
+ btrfs_pin_log_trans(root);
+ root_log_pinned = true;
+ ret = btrfs_insert_inode_ref(trans, dest,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len,
+ old_ino,
+ btrfs_ino(new_dir), old_idx);
+ if (ret)
+ goto out_fail;
+ }
+
+ /* And now for the dest. */
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ /* force full log commit if subvolume involved. */
+ btrfs_set_log_full_commit(dest->fs_info, trans);
+ } else {
+ btrfs_pin_log_trans(dest);
+ dest_log_pinned = true;
+ ret = btrfs_insert_inode_ref(trans, root,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len,
+ new_ino,
+ btrfs_ino(old_dir), new_idx);
+ if (ret)
+ goto out_fail;
+ }
+
+ /* Update inode version and ctime/mtime. */
+ inode_inc_iversion(old_dir);
+ inode_inc_iversion(new_dir);
+ inode_inc_iversion(old_inode);
+ inode_inc_iversion(new_inode);
+ old_dir->i_ctime = old_dir->i_mtime = ctime;
+ new_dir->i_ctime = new_dir->i_mtime = ctime;
+ old_inode->i_ctime = ctime;
+ new_inode->i_ctime = ctime;
+
+ if (old_dentry->d_parent != new_dentry->d_parent) {
+ btrfs_record_unlink_dir(trans, old_dir, old_inode, 1);
+ btrfs_record_unlink_dir(trans, new_dir, new_inode, 1);
+ }
+
+ /* src is a subvolume */
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
+ ret = btrfs_unlink_subvol(trans, root, old_dir,
+ root_objectid,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len);
+ } else { /* src is an inode */
+ ret = __btrfs_unlink_inode(trans, root, old_dir,
+ old_dentry->d_inode,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len);
+ if (!ret)
+ ret = btrfs_update_inode(trans, root, old_inode);
+ }
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ /* dest is a subvolume */
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID) {
+ root_objectid = BTRFS_I(new_inode)->root->root_key.objectid;
+ ret = btrfs_unlink_subvol(trans, dest, new_dir,
+ root_objectid,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len);
+ } else { /* dest is an inode */
+ ret = __btrfs_unlink_inode(trans, dest, new_dir,
+ new_dentry->d_inode,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len);
+ if (!ret)
+ ret = btrfs_update_inode(trans, dest, new_inode);
+ }
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ ret = btrfs_add_link(trans, new_dir, old_inode,
+ new_dentry->d_name.name,
+ new_dentry->d_name.len, 0, old_idx);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ ret = btrfs_add_link(trans, old_dir, new_inode,
+ old_dentry->d_name.name,
+ old_dentry->d_name.len, 0, new_idx);
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
+
+ if (old_inode->i_nlink == 1)
+ BTRFS_I(old_inode)->dir_index = old_idx;
+ if (new_inode->i_nlink == 1)
+ BTRFS_I(new_inode)->dir_index = new_idx;
+
+ if (root_log_pinned) {
+ parent = new_dentry->d_parent;
+ btrfs_log_new_name(trans, old_inode, old_dir, parent);
+ btrfs_end_log_trans(root);
+ root_log_pinned = false;
+ }
+ if (dest_log_pinned) {
+ parent = old_dentry->d_parent;
+ btrfs_log_new_name(trans, new_inode, new_dir, parent);
+ btrfs_end_log_trans(dest);
+ dest_log_pinned = false;
+ }
+ out_fail:
+ /*
+ * If we have pinned a log and an error happened, we unpin tasks
+ * trying to sync the log and force them to fallback to a transaction
+ * commit if the log currently contains any of the inodes involved in
+ * this rename operation (to ensure we do not persist a log with an
+ * inconsistent state for any of these inodes or leading to any
+ * inconsistencies when replayed). If the transaction was aborted, the
+ * abortion reason is propagated to userspace when attempting to commit
+ * the transaction. If the log does not contain any of these inodes, we
+ * allow the tasks to sync it.
+ */
+ if (ret && (root_log_pinned || dest_log_pinned)) {
+ if (btrfs_inode_in_log(old_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(new_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(old_inode, root->fs_info->generation) ||
+ (new_inode &&
+ btrfs_inode_in_log(new_inode, root->fs_info->generation)))
+ btrfs_set_log_full_commit(root->fs_info, trans);
+
+ if (root_log_pinned) {
+ btrfs_end_log_trans(root);
+ root_log_pinned = false;
+ }
+ if (dest_log_pinned) {
+ btrfs_end_log_trans(dest);
+ dest_log_pinned = false;
+ }
+ }
+ ret = btrfs_end_transaction(trans, root);
+ out_notrans:
+ if (new_ino == BTRFS_FIRST_FREE_OBJECTID)
+ up_read(&dest->fs_info->subvol_sem);
+ if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
+ up_read(&root->fs_info->subvol_sem);
+
+ return ret;
+ }
+
+ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root,
+ struct inode *dir,
+ struct dentry *dentry)
+ {
+ int ret;
+ struct inode *inode;
+ u64 objectid;
+ u64 index;
+
+ ret = btrfs_find_free_ino(root, &objectid);
+ if (ret)
+ return ret;
+
+ inode = btrfs_new_inode(trans, root, dir,
+ dentry->d_name.name,
+ dentry->d_name.len,
+ btrfs_ino(dir),
+ objectid,
+ S_IFCHR | WHITEOUT_MODE,
+ &index);
+
+ if (IS_ERR(inode)) {
+ ret = PTR_ERR(inode);
+ return ret;
+ }
+
+ inode->i_op = &btrfs_special_inode_operations;
+ init_special_inode(inode, inode->i_mode,
+ WHITEOUT_DEV);
+
+ ret = btrfs_init_inode_security(trans, inode, dir,
+ &dentry->d_name);
+ if (ret)
+ goto out;
+
+ ret = btrfs_add_nondir(trans, dir, dentry,
+ inode, 0, index);
+ if (ret)
+ goto out;
+
+ ret = btrfs_update_inode(trans, root, inode);
+ out:
+ unlock_new_inode(inode);
+ if (ret)
+ inode_dec_link_count(inode);
+ iput(inode);
+
+ return ret;
+ }
+
static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
- struct inode *new_dir, struct dentry *new_dentry)
+ struct inode *new_dir, struct dentry *new_dentry,
+ unsigned int flags)
{
struct btrfs_trans_handle *trans;
+ unsigned int trans_num_items;
struct btrfs_root *root = BTRFS_I(old_dir)->root;
struct btrfs_root *dest = BTRFS_I(new_dir)->root;
struct inode *new_inode = d_inode(new_dentry);
u64 root_objectid;
int ret;
u64 old_ino = btrfs_ino(old_inode);
+ bool log_pinned = false;
if (btrfs_ino(new_dir) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
return -EPERM;
* We want to reserve the absolute worst case amount of items. So if
* both inodes are subvols and we need to unlink them then that would
* require 4 item modifications, but if they are both normal inodes it
- * would require 5 item modifications, so we'll assume their normal
+ * would require 5 item modifications, so we'll assume they are normal
* inodes. So 5 * 2 is 10, plus 1 for the new link, so 11 total items
* should cover the worst case number of items we'll modify.
+ * If our rename has the whiteout flag, we need more 5 units for the
+ * new inode (1 inode item, 1 inode ref, 2 dir items and 1 xattr item
+ * when selinux is enabled).
*/
- trans = btrfs_start_transaction(root, 11);
+ trans_num_items = 11;
+ if (flags & RENAME_WHITEOUT)
+ trans_num_items += 5;
+ trans = btrfs_start_transaction(root, trans_num_items);
if (IS_ERR(trans)) {
- ret = PTR_ERR(trans);
- goto out_notrans;
- }
+ ret = PTR_ERR(trans);
+ goto out_notrans;
+ }
if (dest != root)
btrfs_record_root_in_trans(trans, dest);
/* force full log commit if subvolume involved. */
btrfs_set_log_full_commit(root->fs_info, trans);
} else {
+ btrfs_pin_log_trans(root);
+ log_pinned = true;
ret = btrfs_insert_inode_ref(trans, dest,
new_dentry->d_name.name,
new_dentry->d_name.len,
btrfs_ino(new_dir), index);
if (ret)
goto out_fail;
- /*
- * this is an ugly little race, but the rename is required
- * to make sure that if we crash, the inode is either at the
- * old name or the new one. pinning the log transaction lets
- * us make sure we don't allow a log commit to come in after
- * we unlink the name but before we add the new name back in.
- */
- btrfs_pin_log_trans(root);
}
inode_inc_iversion(old_dir);
if (old_inode->i_nlink == 1)
BTRFS_I(old_inode)->dir_index = index;
- if (old_ino != BTRFS_FIRST_FREE_OBJECTID) {
+ if (log_pinned) {
struct dentry *parent = new_dentry->d_parent;
+
btrfs_log_new_name(trans, old_inode, old_dir, parent);
btrfs_end_log_trans(root);
+ log_pinned = false;
+ }
+
+ if (flags & RENAME_WHITEOUT) {
+ ret = btrfs_whiteout_for_rename(trans, root, old_dir,
+ old_dentry);
+
+ if (ret) {
+ btrfs_abort_transaction(trans, root, ret);
+ goto out_fail;
+ }
}
out_fail:
+ /*
+ * If we have pinned the log and an error happened, we unpin tasks
+ * trying to sync the log and force them to fallback to a transaction
+ * commit if the log currently contains any of the inodes involved in
+ * this rename operation (to ensure we do not persist a log with an
+ * inconsistent state for any of these inodes or leading to any
+ * inconsistencies when replayed). If the transaction was aborted, the
+ * abortion reason is propagated to userspace when attempting to commit
+ * the transaction. If the log does not contain any of these inodes, we
+ * allow the tasks to sync it.
+ */
+ if (ret && log_pinned) {
+ if (btrfs_inode_in_log(old_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(new_dir, root->fs_info->generation) ||
+ btrfs_inode_in_log(old_inode, root->fs_info->generation) ||
+ (new_inode &&
+ btrfs_inode_in_log(new_inode, root->fs_info->generation)))
+ btrfs_set_log_full_commit(root->fs_info, trans);
+
+ btrfs_end_log_trans(root);
+ log_pinned = false;
+ }
btrfs_end_transaction(trans, root);
out_notrans:
if (old_ino == BTRFS_FIRST_FREE_OBJECTID)
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
- if (flags & ~RENAME_NOREPLACE)
+ if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
- return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry);
+ if (flags & RENAME_EXCHANGE)
+ return btrfs_rename_exchange(old_dir, old_dentry, new_dir,
+ new_dentry);
+
+ return btrfs_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
}
static void btrfs_run_delalloc_work(struct btrfs_work *work)
btrfs_end_transaction(trans, root);
break;
}
+ btrfs_dec_block_group_reservations(root->fs_info, ins.objectid);
last_alloc = ins.offset;
ret = insert_reserved_file_extent(trans, inode,
.iterate = btrfs_real_readdir,
.unlocked_ioctl = btrfs_ioctl,
#ifdef CONFIG_COMPAT
- .compat_ioctl = btrfs_ioctl,
+ .compat_ioctl = btrfs_compat_ioctl,
#endif
.release = btrfs_release_file,
.fsync = btrfs_sync_file,
if (flags & BTRFS_INODE_NODATACOW)
iflags |= FS_NOCOW_FL;
- if ((flags & BTRFS_INODE_COMPRESS) && !(flags & BTRFS_INODE_NOCOMPRESS))
- iflags |= FS_COMPR_FL;
- else if (flags & BTRFS_INODE_NOCOMPRESS)
+ if (flags & BTRFS_INODE_NOCOMPRESS)
iflags |= FS_NOCOMP_FL;
+ else if (flags & BTRFS_INODE_COMPRESS)
+ iflags |= FS_COMPR_FL;
return iflags;
}
{
struct btrfs_trans_handle *trans;
struct btrfs_key key;
- struct btrfs_root_item root_item;
+ struct btrfs_root_item *root_item;
struct btrfs_inode_item *inode_item;
struct extent_buffer *leaf;
struct btrfs_root *root = BTRFS_I(dir)->root;
u64 qgroup_reserved;
uuid_le new_uuid;
+ root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
+ if (!root_item)
+ return -ENOMEM;
+
ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
if (ret)
- return ret;
+ goto fail_free;
/*
* Don't create subvolume whose level is not zero. Or qgroup will be
* screwed up since it assume subvolme qgroup's level to be 0.
*/
- if (btrfs_qgroup_level(objectid))
- return -ENOSPC;
+ if (btrfs_qgroup_level(objectid)) {
+ ret = -ENOSPC;
+ goto fail_free;
+ }
btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
/*
ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
8, &qgroup_reserved, false);
if (ret)
- return ret;
+ goto fail_free;
trans = btrfs_start_transaction(root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
btrfs_subvolume_release_metadata(root, &block_rsv,
qgroup_reserved);
- return ret;
+ goto fail_free;
}
trans->block_rsv = &block_rsv;
trans->bytes_reserved = block_rsv.size;
BTRFS_UUID_SIZE);
btrfs_mark_buffer_dirty(leaf);
- memset(&root_item, 0, sizeof(root_item));
-
- inode_item = &root_item.inode;
+ inode_item = &root_item->inode;
btrfs_set_stack_inode_generation(inode_item, 1);
btrfs_set_stack_inode_size(inode_item, 3);
btrfs_set_stack_inode_nlink(inode_item, 1);
btrfs_set_stack_inode_nbytes(inode_item, root->nodesize);
btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);
- btrfs_set_root_flags(&root_item, 0);
- btrfs_set_root_limit(&root_item, 0);
+ btrfs_set_root_flags(root_item, 0);
+ btrfs_set_root_limit(root_item, 0);
btrfs_set_stack_inode_flags(inode_item, BTRFS_INODE_ROOT_ITEM_INIT);
- btrfs_set_root_bytenr(&root_item, leaf->start);
- btrfs_set_root_generation(&root_item, trans->transid);
- btrfs_set_root_level(&root_item, 0);
- btrfs_set_root_refs(&root_item, 1);
- btrfs_set_root_used(&root_item, leaf->len);
- btrfs_set_root_last_snapshot(&root_item, 0);
+ btrfs_set_root_bytenr(root_item, leaf->start);
+ btrfs_set_root_generation(root_item, trans->transid);
+ btrfs_set_root_level(root_item, 0);
+ btrfs_set_root_refs(root_item, 1);
+ btrfs_set_root_used(root_item, leaf->len);
+ btrfs_set_root_last_snapshot(root_item, 0);
- btrfs_set_root_generation_v2(&root_item,
- btrfs_root_generation(&root_item));
+ btrfs_set_root_generation_v2(root_item,
+ btrfs_root_generation(root_item));
uuid_le_gen(&new_uuid);
- memcpy(root_item.uuid, new_uuid.b, BTRFS_UUID_SIZE);
- btrfs_set_stack_timespec_sec(&root_item.otime, cur_time.tv_sec);
- btrfs_set_stack_timespec_nsec(&root_item.otime, cur_time.tv_nsec);
- root_item.ctime = root_item.otime;
- btrfs_set_root_ctransid(&root_item, trans->transid);
- btrfs_set_root_otransid(&root_item, trans->transid);
+ memcpy(root_item->uuid, new_uuid.b, BTRFS_UUID_SIZE);
+ btrfs_set_stack_timespec_sec(&root_item->otime, cur_time.tv_sec);
+ btrfs_set_stack_timespec_nsec(&root_item->otime, cur_time.tv_nsec);
+ root_item->ctime = root_item->otime;
+ btrfs_set_root_ctransid(root_item, trans->transid);
+ btrfs_set_root_otransid(root_item, trans->transid);
btrfs_tree_unlock(leaf);
free_extent_buffer(leaf);
leaf = NULL;
- btrfs_set_root_dirid(&root_item, new_dirid);
+ btrfs_set_root_dirid(root_item, new_dirid);
key.objectid = objectid;
key.offset = 0;
key.type = BTRFS_ROOT_ITEM_KEY;
ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
- &root_item);
+ root_item);
if (ret)
goto fail;
BUG_ON(ret);
ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root,
- root_item.uuid, BTRFS_UUID_KEY_SUBVOL,
+ root_item->uuid, BTRFS_UUID_KEY_SUBVOL,
objectid);
if (ret)
btrfs_abort_transaction(trans, root, ret);
fail:
+ kfree(root_item);
trans->block_rsv = NULL;
trans->bytes_reserved = 0;
btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
d_instantiate(dentry, inode);
}
return ret;
+
+fail_free:
+ kfree(root_item);
+ return ret;
}
static void btrfs_wait_for_no_snapshoting_writes(struct btrfs_root *root)
if (ret)
goto dec_and_free;
- btrfs_wait_ordered_extents(root, -1);
+ btrfs_wait_ordered_extents(root, -1, 0, (u64)-1);
btrfs_init_block_rsv(&pending_snapshot->block_rsv,
BTRFS_BLOCK_RSV_TEMP);
return ret;
}
-static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
+static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
{
struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
- struct btrfs_ioctl_vol_args *vol_args;
+ struct btrfs_ioctl_vol_args_v2 *vol_args;
int ret;
if (!capable(CAP_SYS_ADMIN))
goto err_drop;
}
- vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+ /* Check for compatibility reject unknown flags */
+ if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED)
+ return -EOPNOTSUPP;
if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
1)) {
}
mutex_lock(&root->fs_info->volume_mutex);
- ret = btrfs_rm_device(root, vol_args->name);
+ if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) {
+ ret = btrfs_rm_device(root, NULL, vol_args->devid);
+ } else {
+ vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
+ ret = btrfs_rm_device(root, vol_args->name, 0);
+ }
mutex_unlock(&root->fs_info->volume_mutex);
atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
- if (!ret)
- btrfs_info(root->fs_info, "disk deleted %s",vol_args->name);
-
+ if (!ret) {
+ if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID)
+ btrfs_info(root->fs_info, "device deleted: id %llu",
+ vol_args->devid);
+ else
+ btrfs_info(root->fs_info, "device deleted: %s",
+ vol_args->name);
+ }
out:
kfree(vol_args);
err_drop:
return ret;
}
+static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
+{
+ struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
+ struct btrfs_ioctl_vol_args *vol_args;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ ret = mnt_want_write_file(file);
+ if (ret)
+ return ret;
+
+ if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
+ 1)) {
+ ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
+ goto out_drop_write;
+ }
+
+ vol_args = memdup_user(arg, sizeof(*vol_args));
+ if (IS_ERR(vol_args)) {
+ ret = PTR_ERR(vol_args);
+ goto out;
+ }
+
+ vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
+ mutex_lock(&root->fs_info->volume_mutex);
+ ret = btrfs_rm_device(root, vol_args->name, 0);
+ mutex_unlock(&root->fs_info->volume_mutex);
+
+ if (!ret)
+ btrfs_info(root->fs_info, "disk deleted %s",vol_args->name);
+ kfree(vol_args);
+out:
+ atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
+out_drop_write:
+ mnt_drop_write_file(file);
+
+ return ret;
+}
+
static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg)
{
struct btrfs_ioctl_fs_info_args *fi_args;
u64 last_dest_end = destoff;
ret = -ENOMEM;
- buf = vmalloc(root->nodesize);
- if (!buf)
- return ret;
+ buf = kmalloc(root->nodesize, GFP_KERNEL | __GFP_NOWARN);
+ if (!buf) {
+ buf = vmalloc(root->nodesize);
+ if (!buf)
+ return ret;
+ }
path = btrfs_alloc_path();
if (!path) {
- vfree(buf);
+ kvfree(buf);
return ret;
}
out:
btrfs_free_path(path);
- vfree(buf);
+ kvfree(buf);
return ret;
}
1)) {
ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
} else {
- ret = btrfs_dev_replace_start(root, p);
+ ret = btrfs_dev_replace_by_ioctl(root, p);
atomic_set(
&root->fs_info->mutually_exclusive_operation_running,
0);
/* update qgroup status and info */
err = btrfs_run_qgroups(trans, root->fs_info);
if (err < 0)
- btrfs_std_error(root->fs_info, ret,
- "failed to update qgroup status and info\n");
+ btrfs_handle_fs_error(root->fs_info, err,
+ "failed to update qgroup status and info");
err = btrfs_end_transaction(trans, root);
if (err && !ret)
ret = err;
if (ret)
return ret;
+ ret = mnt_want_write_file(file);
+ if (ret)
+ return ret;
+
trans = btrfs_start_transaction(root, 0);
- if (IS_ERR(trans))
- return PTR_ERR(trans);
+ if (IS_ERR(trans)) {
+ ret = PTR_ERR(trans);
+ goto out_drop_write;
+ }
spin_lock(&root->fs_info->super_lock);
newflags = btrfs_super_compat_flags(super_block);
btrfs_set_super_incompat_flags(super_block, newflags);
spin_unlock(&root->fs_info->super_lock);
- return btrfs_commit_transaction(trans, root);
+ ret = btrfs_commit_transaction(trans, root);
+out_drop_write:
+ mnt_drop_write_file(file);
+
+ return ret;
}
long btrfs_ioctl(struct file *file, unsigned int
return btrfs_ioctl_add_dev(root, argp);
case BTRFS_IOC_RM_DEV:
return btrfs_ioctl_rm_dev(file, argp);
+ case BTRFS_IOC_RM_DEV_V2:
+ return btrfs_ioctl_rm_dev_v2(file, argp);
case BTRFS_IOC_FS_INFO:
return btrfs_ioctl_fs_info(root, argp);
case BTRFS_IOC_DEV_INFO:
return -ENOTTY;
}
+
+#ifdef CONFIG_COMPAT
+long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+ switch (cmd) {
+ case FS_IOC32_GETFLAGS:
+ cmd = FS_IOC_GETFLAGS;
+ break;
+ case FS_IOC32_SETFLAGS:
+ cmd = FS_IOC_SETFLAGS;
+ break;
+ case FS_IOC32_GETVERSION:
+ cmd = FS_IOC_GETVERSION;
+ break;
+ default:
+ return -ENOIOCTLCMD;
+ }
+
+ return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
+}
+#endif
}
out:
if (ret) {
- btrfs_std_error(root->fs_info, ret, NULL);
+ btrfs_handle_fs_error(root->fs_info, ret, NULL);
if (!list_empty(&reloc_roots))
free_reloc_roots(&reloc_roots);
btrfs_info(extent_root->fs_info, "relocating block group %llu flags %llu",
rc->block_group->key.objectid, rc->block_group->flags);
- ret = btrfs_start_delalloc_roots(fs_info, 0, -1);
- if (ret < 0) {
- err = ret;
- goto out;
- }
- btrfs_wait_ordered_roots(fs_info, -1);
+ btrfs_wait_block_group_reservations(rc->block_group);
+ btrfs_wait_nocow_writers(rc->block_group);
+ btrfs_wait_ordered_roots(fs_info, -1,
+ rc->block_group->key.objectid,
+ rc->block_group->key.offset);
while (1) {
mutex_lock(&fs_info->cleaner_mutex);
return errstr;
}
-static void save_error_info(struct btrfs_fs_info *fs_info)
-{
- /*
- * today we only save the error info into ram. Long term we'll
- * also send it down to the disk
- */
- set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
-}
-
/* btrfs handle error by forcing the filesystem readonly */
static void btrfs_handle_error(struct btrfs_fs_info *fs_info)
{
}
/*
- * __btrfs_std_error decodes expected errors from the caller and
+ * __btrfs_handle_fs_error decodes expected errors from the caller and
* invokes the approciate error response.
*/
__cold
-void __btrfs_std_error(struct btrfs_fs_info *fs_info, const char *function,
+void __btrfs_handle_fs_error(struct btrfs_fs_info *fs_info, const char *function,
unsigned int line, int errno, const char *fmt, ...)
{
struct super_block *sb = fs_info->sb;
}
#endif
+ /*
+ * Today we only save the error info to memory. Long term we'll
+ * also send it down to the disk
+ */
+ set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);
+
/* Don't go through full error handling during mount */
- save_error_info(fs_info);
if (sb->s_flags & MS_BORN)
btrfs_handle_error(fs_info);
}
/* Wake up anybody who may be waiting on this transaction */
wake_up(&root->fs_info->transaction_wait);
wake_up(&root->fs_info->transaction_blocked_wait);
- __btrfs_std_error(root->fs_info, function, line, errno, NULL);
+ __btrfs_handle_fs_error(root->fs_info, function, line, errno, NULL);
}
/*
* __btrfs_panic decodes unexpected, fatal errors from the caller,
return 0;
}
- btrfs_wait_ordered_roots(fs_info, -1);
+ btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
trans = btrfs_attach_transaction_barrier(root);
if (IS_ERR(trans)) {
memcpy(&fs_info->security_opts, sec_opts, sizeof(*sec_opts));
} else {
/*
- * Since SELinux(the only one supports security_mnt_opts) does
- * NOT support changing context during remount/mount same sb,
- * This must be the same or part of the same security options,
- * just free it.
+ * Since SELinux (the only one supporting security_mnt_opts)
+ * does NOT support changing context during remount/mount of
+ * the same sb, this must be the same or part of the same
+ * security options, just free it.
*/
security_free_mnt_opts(sec_opts);
}
unsigned long old_opts)
{
/*
- * We need cleanup all defragable inodes if the autodefragment is
- * close or the fs is R/O.
+ * We need to cleanup all defragable inodes if the autodefragment is
+ * close or the filesystem is read only.
*/
if (btrfs_raw_test_opt(old_opts, AUTO_DEFRAG) &&
(!btrfs_raw_test_opt(fs_info->mount_opt, AUTO_DEFRAG) ||
struct btrfs_block_rsv *block_rsv = &fs_info->global_block_rsv;
int ret;
u64 thresh = 0;
+ int mixed = 0;
/*
- * holding chunk_muext to avoid allocating new chunks, holding
+ * holding chunk_mutex to avoid allocating new chunks, holding
* device_list_mutex to avoid the device being removed
*/
rcu_read_lock();
}
}
}
- if (found->flags & BTRFS_BLOCK_GROUP_METADATA)
- total_free_meta += found->disk_total - found->disk_used;
+
+ /*
+ * Metadata in mixed block goup profiles are accounted in data
+ */
+ if (!mixed && found->flags & BTRFS_BLOCK_GROUP_METADATA) {
+ if (found->flags & BTRFS_BLOCK_GROUP_DATA)
+ mixed = 1;
+ else
+ total_free_meta += found->disk_total -
+ found->disk_used;
+ }
total_used += found->disk_used;
}
/* Account global block reserve as used, it's in logical size already */
spin_lock(&block_rsv->lock);
- buf->f_bfree -= block_rsv->size >> bits;
+ /* Mixed block groups accounting is not byte-accurate, avoid overflow */
+ if (buf->f_bfree >= block_rsv->size >> bits)
+ buf->f_bfree -= block_rsv->size >> bits;
+ else
+ buf->f_bfree = 0;
spin_unlock(&block_rsv->lock);
buf->f_bavail = div_u64(total_free_data, factor);
*/
thresh = 4 * 1024 * 1024;
- if (total_free_meta - thresh < block_rsv->size)
+ if (!mixed && total_free_meta - thresh < block_rsv->size)
buf->f_bavail = 0;
buf->f_type = BTRFS_SUPER_MAGIC;
* when the transaction commits
*/
static int record_root_in_trans(struct btrfs_trans_handle *trans,
- struct btrfs_root *root)
+ struct btrfs_root *root,
+ int force)
{
- if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
- root->last_trans < trans->transid) {
+ if ((test_bit(BTRFS_ROOT_REF_COWS, &root->state) &&
+ root->last_trans < trans->transid) || force) {
WARN_ON(root == root->fs_info->extent_root);
WARN_ON(root->commit_root != root->node);
smp_wmb();
spin_lock(&root->fs_info->fs_roots_radix_lock);
- if (root->last_trans == trans->transid) {
+ if (root->last_trans == trans->transid && !force) {
spin_unlock(&root->fs_info->fs_roots_radix_lock);
return 0;
}
return 0;
mutex_lock(&root->fs_info->reloc_mutex);
- record_root_in_trans(trans, root);
+ record_root_in_trans(trans, root, 0);
mutex_unlock(&root->fs_info->reloc_mutex);
return 0;
return ret;
}
+/* Bisesctability fixup, remove in 4.8 */
+#ifndef btrfs_std_error
+#define btrfs_std_error btrfs_handle_fs_error
+#endif
+
+/*
+ * Do all special snapshot related qgroup dirty hack.
+ *
+ * Will do all needed qgroup inherit and dirty hack like switch commit
+ * roots inside one transaction and write all btree into disk, to make
+ * qgroup works.
+ */
+static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
+ struct btrfs_root *src,
+ struct btrfs_root *parent,
+ struct btrfs_qgroup_inherit *inherit,
+ u64 dst_objectid)
+{
+ struct btrfs_fs_info *fs_info = src->fs_info;
+ int ret;
+
+ /*
+ * Save some performance in the case that qgroups are not
+ * enabled. If this check races with the ioctl, rescan will
+ * kick in anyway.
+ */
+ mutex_lock(&fs_info->qgroup_ioctl_lock);
+ if (!fs_info->quota_enabled) {
+ mutex_unlock(&fs_info->qgroup_ioctl_lock);
+ return 0;
+ }
+ mutex_unlock(&fs_info->qgroup_ioctl_lock);
+
+ /*
+ * We are going to commit transaction, see btrfs_commit_transaction()
+ * comment for reason locking tree_log_mutex
+ */
+ mutex_lock(&fs_info->tree_log_mutex);
+
+ ret = commit_fs_roots(trans, src);
+ if (ret)
+ goto out;
+ ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
+ if (ret < 0)
+ goto out;
+ ret = btrfs_qgroup_account_extents(trans, fs_info);
+ if (ret < 0)
+ goto out;
+
+ /* Now qgroup are all updated, we can inherit it to new qgroups */
+ ret = btrfs_qgroup_inherit(trans, fs_info,
+ src->root_key.objectid, dst_objectid,
+ inherit);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * Now we do a simplified commit transaction, which will:
+ * 1) commit all subvolume and extent tree
+ * To ensure all subvolume and extent tree have a valid
+ * commit_root to accounting later insert_dir_item()
+ * 2) write all btree blocks onto disk
+ * This is to make sure later btree modification will be cowed
+ * Or commit_root can be populated and cause wrong qgroup numbers
+ * In this simplified commit, we don't really care about other trees
+ * like chunk and root tree, as they won't affect qgroup.
+ * And we don't write super to avoid half committed status.
+ */
+ ret = commit_cowonly_roots(trans, src);
+ if (ret)
+ goto out;
+ switch_commit_roots(trans->transaction, fs_info);
+ ret = btrfs_write_and_wait_transaction(trans, src);
+ if (ret)
+ btrfs_std_error(fs_info, ret,
+ "Error while writing out transaction for qgroup");
+
+out:
+ mutex_unlock(&fs_info->tree_log_mutex);
+
+ /*
+ * Force parent root to be updated, as we recorded it before so its
+ * last_trans == cur_transid.
+ * Or it won't be committed again onto disk after later
+ * insert_dir_item()
+ */
+ if (!ret)
+ record_root_in_trans(trans, parent, 1);
+ return ret;
+}
+
/*
* new snapshots need to be created at a very specific time in the
* transaction commit. This does the actual creation.
dentry = pending->dentry;
parent_inode = pending->dir;
parent_root = BTRFS_I(parent_inode)->root;
- record_root_in_trans(trans, parent_root);
+ record_root_in_trans(trans, parent_root, 0);
cur_time = current_fs_time(parent_inode->i_sb);
goto fail;
}
- record_root_in_trans(trans, root);
+ record_root_in_trans(trans, root, 0);
btrfs_set_root_last_snapshot(&root->root_item, trans->transid);
memcpy(new_root_item, &root->root_item, sizeof(*new_root_item));
btrfs_check_and_init_root_item(new_root_item);
goto fail;
}
+ /*
+ * Do special qgroup accounting for snapshot, as we do some qgroup
+ * snapshot hack to do fast snapshot.
+ * To co-operate with that hack, we do hack again.
+ * Or snapshot will be greatly slowed down by a subtree qgroup rescan
+ */
+ ret = qgroup_account_snapshot(trans, root, parent_root,
+ pending->inherit, objectid);
+ if (ret < 0)
+ goto fail;
+
ret = btrfs_insert_dir_item(trans, parent_root,
dentry->d_name.name, dentry->d_name.len,
parent_inode, &key,
goto fail;
}
- /*
- * account qgroup counters before qgroup_inherit()
- */
- ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
- if (ret)
- goto fail;
- ret = btrfs_qgroup_account_extents(trans, fs_info);
- if (ret)
- goto fail;
- ret = btrfs_qgroup_inherit(trans, fs_info,
- root->root_key.objectid,
- objectid, pending->inherit);
- if (ret) {
- btrfs_abort_transaction(trans, root, ret);
- goto fail;
- }
-
fail:
pending->error = ret;
dir_item_existed:
static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
{
if (btrfs_test_opt(fs_info->tree_root, FLUSHONCOMMIT))
- btrfs_wait_ordered_roots(fs_info, -1);
+ btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
}
static inline void
ret = btrfs_write_and_wait_transaction(trans, root);
if (ret) {
- btrfs_std_error(root->fs_info, ret,
+ btrfs_handle_fs_error(root->fs_info, ret,
"Error while writing out transaction");
mutex_unlock(&root->fs_info->tree_log_mutex);
goto scrub_continue;
INIT_LIST_HEAD(&extents);
+ down_write(&BTRFS_I(inode)->dio_sem);
write_lock(&tree->lock);
test_gen = root->fs_info->last_trans_committed;
}
list_sort(NULL, &extents, extent_cmp);
+ btrfs_get_logged_extents(inode, logged_list, start, end);
/*
- * Collect any new ordered extents within the range. This is to
- * prevent logging file extent items without waiting for the disk
- * location they point to being written. We do this only to deal
- * with races against concurrent lockless direct IO writes.
+ * Some ordered extents started by fsync might have completed
+ * before we could collect them into the list logged_list, which
+ * means they're gone, not in our logged_list nor in the inode's
+ * ordered tree. We want the application/user space to know an
+ * error happened while attempting to persist file data so that
+ * it can take proper action. If such error happened, we leave
+ * without writing to the log tree and the fsync must report the
+ * file data write error and not commit the current transaction.
*/
- btrfs_get_logged_extents(inode, logged_list, start, end);
+ ret = btrfs_inode_check_errors(inode);
+ if (ret)
+ ctx->io_err = ret;
process:
while (!list_empty(&extents)) {
em = list_entry(extents.next, struct extent_map, list);
}
WARN_ON(!list_empty(&extents));
write_unlock(&tree->lock);
+ up_write(&BTRFS_I(inode)->dio_sem);
btrfs_release_path(path);
return ret;
mutex_lock(&BTRFS_I(inode)->log_mutex);
- /*
- * Collect ordered extents only if we are logging data. This is to
- * ensure a subsequent request to log this inode in LOG_INODE_ALL mode
- * will process the ordered extents if they still exists at the time,
- * because when we collect them we test and set for the flag
- * BTRFS_ORDERED_LOGGED to prevent multiple log requests to process the
- * same ordered extents. The consequence for the LOG_INODE_ALL log mode
- * not processing the ordered extents is that we end up logging the
- * corresponding file extent items, based on the extent maps in the
- * inode's extent_map_tree's modified_list, without logging the
- * respective checksums (since the may still be only attached to the
- * ordered extents and have not been inserted in the csum tree by
- * btrfs_finish_ordered_io() yet).
- */
- if (inode_only == LOG_INODE_ALL)
- btrfs_get_logged_extents(inode, &logged_list, start, end);
-
/*
* a brute force approach to making sure we get the most uptodate
* copies of everything.
goto out_unlock;
}
if (fast_search) {
- /*
- * Some ordered extents started by fsync might have completed
- * before we collected the ordered extents in logged_list, which
- * means they're gone, not in our logged_list nor in the inode's
- * ordered tree. We want the application/user space to know an
- * error happened while attempting to persist file data so that
- * it can take proper action. If such error happened, we leave
- * without writing to the log tree and the fsync must report the
- * file data write error and not commit the current transaction.
- */
- err = btrfs_inode_check_errors(inode);
- if (err) {
- ctx->io_err = err;
- goto out_unlock;
- }
ret = btrfs_log_changed_extents(trans, root, inode, dst_path,
&logged_list, ctx, start, end);
if (ret) {
}
ctx->log_new_dentries = false;
- if (type == BTRFS_FT_DIR)
+ if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK)
log_mode = LOG_INODE_ALL;
btrfs_release_path(path);
ret = btrfs_log_inode(trans, root, di_inode,
if (IS_ERR(dir_inode))
continue;
+ if (ctx)
+ ctx->log_new_dentries = false;
ret = btrfs_log_inode(trans, root, dir_inode,
LOG_INODE_ALL, 0, LLONG_MAX, ctx);
if (!ret &&
btrfs_must_commit_transaction(trans, dir_inode))
ret = 1;
+ if (!ret && ctx && ctx->log_new_dentries)
+ ret = log_new_dir_dentries(trans, root,
+ dir_inode, ctx);
iput(dir_inode);
if (ret)
goto out;
ret = walk_log_tree(trans, log_root_tree, &wc);
if (ret) {
- btrfs_std_error(fs_info, ret, "Failed to pin buffers while "
+ btrfs_handle_fs_error(fs_info, ret, "Failed to pin buffers while "
"recovering log root tree.");
goto error;
}
ret = btrfs_search_slot(NULL, log_root_tree, &key, path, 0, 0);
if (ret < 0) {
- btrfs_std_error(fs_info, ret,
+ btrfs_handle_fs_error(fs_info, ret,
"Couldn't find tree log root.");
goto error;
}
log = btrfs_read_fs_root(log_root_tree, &found_key);
if (IS_ERR(log)) {
ret = PTR_ERR(log);
- btrfs_std_error(fs_info, ret,
+ btrfs_handle_fs_error(fs_info, ret,
"Couldn't read tree log root.");
goto error;
}
free_extent_buffer(log->node);
free_extent_buffer(log->commit_root);
kfree(log);
- btrfs_std_error(fs_info, ret, "Couldn't read target root "
+ btrfs_handle_fs_error(fs_info, ret, "Couldn't read target root "
"for tree log recovery.");
goto error;
}
* into the file. When the file is logged we check it and
* don't log the parents if the file is fully on disk.
*/
- if (S_ISREG(inode->i_mode)) {
- mutex_lock(&BTRFS_I(inode)->log_mutex);
- BTRFS_I(inode)->last_unlink_trans = trans->transid;
- mutex_unlock(&BTRFS_I(inode)->log_mutex);
- }
+ mutex_lock(&BTRFS_I(inode)->log_mutex);
+ BTRFS_I(inode)->last_unlink_trans = trans->transid;
+ mutex_unlock(&BTRFS_I(inode)->log_mutex);
/*
* if this directory was already logged any new
projects / linux-beck.git / commitdiff