Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 2cddfe7..fe2b876 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -16,9 +16,9 @@
#include <linux/backing-dev.h>
#include <linux/wait.h>
#include <linux/slab.h>
-#include <linux/kobject.h>
#include <trace/events/btrfs.h>
#include <asm/kmap_types.h>
+#include <asm/unaligned.h>
#include <linux/pagemap.h>
#include <linux/btrfs.h>
#include <linux/btrfs_tree.h>
@@ -31,25 +31,34 @@
#include "extent_io.h"
#include "extent_map.h"
#include "async-thread.h"
+#include "block-rsv.h"
struct btrfs_trans_handle;
struct btrfs_transaction;
struct btrfs_pending_snapshot;
+struct btrfs_delayed_ref_root;
+struct btrfs_space_info;
+struct btrfs_block_group_cache;
extern struct kmem_cache *btrfs_trans_handle_cachep;
extern struct kmem_cache *btrfs_bit_radix_cachep;
extern struct kmem_cache *btrfs_path_cachep;
extern struct kmem_cache *btrfs_free_space_cachep;
+extern struct kmem_cache *btrfs_free_space_bitmap_cachep;
struct btrfs_ordered_sum;
-
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-#define STATIC noinline
-#else
-#define STATIC static noinline
-#endif
+struct btrfs_ref;
#define BTRFS_MAGIC 0x4D5F53665248425FULL /* ascii _BHRfS_M, no null */
-#define BTRFS_MAX_MIRRORS 3
+/*
+ * Maximum number of mirrors that can be available for all profiles counting
+ * the target device of dev-replace as one. During an active device replace
+ * procedure, the target device of the copy operation is a mirror for the
+ * filesystem data as well that can be used to read data in order to repair
+ * read errors on other disks.
+ *
+ * Current value is derived from RAID1 with 2 copies.
+ */
+#define BTRFS_MAX_MIRRORS (2 + 1)
#define BTRFS_MAX_LEVEL 8
@@ -74,9 +83,6 @@
*/
#define BTRFS_LINK_MAX 65535U
-/* four bytes for CRC32 */
-static const int btrfs_csum_sizes[] = { 4 };
-
#define BTRFS_EMPTY_DIR_SIZE 0
/* ioprio of readahead is set to idle */
@@ -103,10 +109,6 @@
return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE);
}
-struct btrfs_mapping_tree {
- struct extent_map_tree map_tree;
-};
-
static inline unsigned long btrfs_chunk_item_size(int num_stripes)
{
BUG_ON(num_stripes == 0);
@@ -115,13 +117,26 @@
}
/*
- * File system states
+ * Runtime (in-memory) states of filesystem
*/
-#define BTRFS_FS_STATE_ERROR 0
-#define BTRFS_FS_STATE_REMOUNTING 1
-#define BTRFS_FS_STATE_TRANS_ABORTED 2
-#define BTRFS_FS_STATE_DEV_REPLACING 3
-#define BTRFS_FS_STATE_DUMMY_FS_INFO 4
+enum {
+ /* Global indicator of serious filesystem errors */
+ BTRFS_FS_STATE_ERROR,
+ /*
+ * Filesystem is being remounted, allow to skip some operations, like
+ * defrag
+ */
+ BTRFS_FS_STATE_REMOUNTING,
+ /* Track if a transaction abort has been reported on this filesystem */
+ BTRFS_FS_STATE_TRANS_ABORTED,
+ /*
+ * Bio operations should be blocked on this filesystem because a source
+ * or target device is being destroyed as part of a device replace
+ */
+ BTRFS_FS_STATE_DEV_REPLACING,
+ /* The btrfs_fs_info created for self-tests */
+ BTRFS_FS_STATE_DUMMY_FS_INFO,
+};
#define BTRFS_BACKREF_REV_MAX 256
#define BTRFS_BACKREF_REV_SHIFT 56
@@ -201,9 +216,10 @@
* it currently lacks any block count etc etc
*/
struct btrfs_super_block {
- u8 csum[BTRFS_CSUM_SIZE];
/* the first 4 fields must match struct btrfs_header */
- u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
+ u8 csum[BTRFS_CSUM_SIZE];
+ /* FS specific UUID, visible to user */
+ u8 fsid[BTRFS_FSID_SIZE];
__le64 bytenr; /* this block number */
__le64 flags;
@@ -240,8 +256,11 @@
__le64 cache_generation;
__le64 uuid_tree_generation;
+ /* the UUID written into btree blocks */
+ u8 metadata_uuid[BTRFS_FSID_SIZE];
+
/* future expansion */
- __le64 reserved[30];
+ __le64 reserved[28];
u8 sys_chunk_array[BTRFS_SYSTEM_CHUNK_ARRAY_SIZE];
struct btrfs_root_backup super_roots[BTRFS_NUM_BACKUP_ROOTS];
} __attribute__ ((__packed__));
@@ -271,7 +290,8 @@
BTRFS_FEATURE_INCOMPAT_RAID56 | \
BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF | \
BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA | \
- BTRFS_FEATURE_INCOMPAT_NO_HOLES)
+ BTRFS_FEATURE_INCOMPAT_NO_HOLES | \
+ BTRFS_FEATURE_INCOMPAT_METADATA_UUID)
#define BTRFS_FEATURE_INCOMPAT_SAFE_SET \
(BTRFS_FEATURE_INCOMPAT_EXTENDED_IREF)
@@ -322,7 +342,7 @@
* The slots array records the index of the item or block pointer
* used while walking the tree.
*/
-enum { READA_NONE = 0, READA_BACK, READA_FORWARD };
+enum { READA_NONE, READA_BACK, READA_FORWARD };
struct btrfs_path {
struct extent_buffer *nodes[BTRFS_MAX_LEVEL];
int slots[BTRFS_MAX_LEVEL];
@@ -366,122 +386,12 @@
struct btrfs_device *tgtdev;
struct mutex lock_finishing_cancel_unmount;
- rwlock_t lock;
- atomic_t read_locks;
- atomic_t blocking_readers;
- wait_queue_head_t read_lock_wq;
+ struct rw_semaphore rwsem;
struct btrfs_scrub_progress scrub_progress;
-};
-/* For raid type sysfs entries */
-struct raid_kobject {
- u64 flags;
- struct kobject kobj;
- struct list_head list;
-};
-
-struct btrfs_space_info {
- spinlock_t lock;
-
- u64 total_bytes; /* total bytes in the space,
- this doesn't take mirrors into account */
- u64 bytes_used; /* total bytes used,
- this doesn't take mirrors into account */
- u64 bytes_pinned; /* total bytes pinned, will be freed when the
- transaction finishes */
- u64 bytes_reserved; /* total bytes the allocator has reserved for
- current allocations */
- u64 bytes_may_use; /* number of bytes that may be used for
- delalloc/allocations */
- u64 bytes_readonly; /* total bytes that are read only */
-
- u64 max_extent_size; /* This will hold the maximum extent size of
- the space info if we had an ENOSPC in the
- allocator. */
-
- unsigned int full:1; /* indicates that we cannot allocate any more
- chunks for this space */
- unsigned int chunk_alloc:1; /* set if we are allocating a chunk */
-
- unsigned int flush:1; /* set if we are trying to make space */
-
- unsigned int force_alloc; /* set if we need to force a chunk
- alloc for this space */
-
- u64 disk_used; /* total bytes used on disk */
- u64 disk_total; /* total bytes on disk, takes mirrors into
- account */
-
- u64 flags;
-
- /*
- * bytes_pinned is kept in line with what is actually pinned, as in
- * we've called update_block_group and dropped the bytes_used counter
- * and increased the bytes_pinned counter. However this means that
- * bytes_pinned does not reflect the bytes that will be pinned once the
- * delayed refs are flushed, so this counter is inc'ed every time we
- * call btrfs_free_extent so it is a realtime count of what will be
- * freed once the transaction is committed. It will be zeroed every
- * time the transaction commits.
- */
- struct percpu_counter total_bytes_pinned;
-
- struct list_head list;
- /* Protected by the spinlock 'lock'. */
- struct list_head ro_bgs;
- struct list_head priority_tickets;
- struct list_head tickets;
- /*
- * tickets_id just indicates the next ticket will be handled, so note
- * it's not stored per ticket.
- */
- u64 tickets_id;
-
- struct rw_semaphore groups_sem;
- /* for block groups in our same type */
- struct list_head block_groups[BTRFS_NR_RAID_TYPES];
- wait_queue_head_t wait;
-
- struct kobject kobj;
- struct kobject *block_group_kobjs[BTRFS_NR_RAID_TYPES];
-};
-
-#define BTRFS_BLOCK_RSV_GLOBAL 1
-#define BTRFS_BLOCK_RSV_DELALLOC 2
-#define BTRFS_BLOCK_RSV_TRANS 3
-#define BTRFS_BLOCK_RSV_CHUNK 4
-#define BTRFS_BLOCK_RSV_DELOPS 5
-#define BTRFS_BLOCK_RSV_EMPTY 6
-#define BTRFS_BLOCK_RSV_TEMP 7
-
-struct btrfs_block_rsv {
- u64 size;
- u64 reserved;
- struct btrfs_space_info *space_info;
- spinlock_t lock;
- unsigned short full;
- unsigned short type;
- unsigned short failfast;
-
- /*
- * Qgroup equivalent for @size @reserved
- *
- * Unlike normal @size/@reserved for inode rsv, qgroup doesn't care
- * about things like csum size nor how many tree blocks it will need to
- * reserve.
- *
- * Qgroup cares more about net change of the extent usage.
- *
- * So for one newly inserted file extent, in worst case it will cause
- * leaf split and level increase, nodesize for each file extent is
- * already too much.
- *
- * In short, qgroup_size/reserved is the upper limit of possible needed
- * qgroup metadata reservation.
- */
- u64 qgroup_rsv_size;
- u64 qgroup_rsv_reserved;
+ struct percpu_counter bio_counter;
+ wait_queue_head_t replace_wait;
};
/*
@@ -513,45 +423,11 @@
};
enum btrfs_caching_type {
- BTRFS_CACHE_NO = 0,
- BTRFS_CACHE_STARTED = 1,
- BTRFS_CACHE_FAST = 2,
- BTRFS_CACHE_FINISHED = 3,
- BTRFS_CACHE_ERROR = 4,
-};
-
-enum btrfs_disk_cache_state {
- BTRFS_DC_WRITTEN = 0,
- BTRFS_DC_ERROR = 1,
- BTRFS_DC_CLEAR = 2,
- BTRFS_DC_SETUP = 3,
-};
-
-struct btrfs_caching_control {
- struct list_head list;
- struct mutex mutex;
- wait_queue_head_t wait;
- struct btrfs_work work;
- struct btrfs_block_group_cache *block_group;
- u64 progress;
- refcount_t count;
-};
-
-/* Once caching_thread() finds this much free space, it will wake up waiters. */
-#define CACHING_CTL_WAKE_UP SZ_2M
-
-struct btrfs_io_ctl {
- void *cur, *orig;
- struct page *page;
- struct page **pages;
- struct btrfs_fs_info *fs_info;
- struct inode *inode;
- unsigned long size;
- int index;
- int num_pages;
- int entries;
- int bitmaps;
- unsigned check_crcs:1;
+ BTRFS_CACHE_NO,
+ BTRFS_CACHE_STARTED,
+ BTRFS_CACHE_FAST,
+ BTRFS_CACHE_FINISHED,
+ BTRFS_CACHE_ERROR,
};
/*
@@ -562,120 +438,6 @@
struct mutex lock;
};
-struct btrfs_block_group_cache {
- struct btrfs_key key;
- struct btrfs_block_group_item item;
- struct btrfs_fs_info *fs_info;
- struct inode *inode;
- spinlock_t lock;
- u64 pinned;
- u64 reserved;
- u64 delalloc_bytes;
- u64 bytes_super;
- u64 flags;
- u64 cache_generation;
-
- /*
- * If the free space extent count exceeds this number, convert the block
- * group to bitmaps.
- */
- u32 bitmap_high_thresh;
-
- /*
- * If the free space extent count drops below this number, convert the
- * block group back to extents.
- */
- u32 bitmap_low_thresh;
-
- /*
- * It is just used for the delayed data space allocation because
- * only the data space allocation and the relative metadata update
- * can be done cross the transaction.
- */
- struct rw_semaphore data_rwsem;
-
- /* for raid56, this is a full stripe, without parity */
- unsigned long full_stripe_len;
-
- unsigned int ro;
- unsigned int iref:1;
- unsigned int has_caching_ctl:1;
- unsigned int removed:1;
-
- int disk_cache_state;
-
- /* cache tracking stuff */
- int cached;
- struct btrfs_caching_control *caching_ctl;
- u64 last_byte_to_unpin;
-
- struct btrfs_space_info *space_info;
-
- /* free space cache stuff */
- struct btrfs_free_space_ctl *free_space_ctl;
-
- /* block group cache stuff */
- struct rb_node cache_node;
-
- /* for block groups in the same raid type */
- struct list_head list;
-
- /* usage count */
- atomic_t count;
-
- /* List of struct btrfs_free_clusters for this block group.
- * Today it will only have one thing on it, but that may change
- */
- struct list_head cluster_list;
-
- /* For delayed block group creation or deletion of empty block groups */
- struct list_head bg_list;
-
- /* For read-only block groups */
- struct list_head ro_list;
-
- atomic_t trimming;
-
- /* For dirty block groups */
- struct list_head dirty_list;
- struct list_head io_list;
-
- 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;
-
- /*
- * Does the block group need to be added to the free space tree?
- * Protected by free_space_lock.
- */
- int needs_free_space;
-
- /* Record locked full stripes for RAID5/6 block group */
- struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
-};
-
/* delayed seq elem */
struct seq_list {
struct list_head list;
@@ -691,22 +453,6 @@
ORPHAN_CLEANUP_DONE = 2,
};
-/* used by the raid56 code to lock stripes for read/modify/write */
-struct btrfs_stripe_hash {
- struct list_head hash_list;
- spinlock_t lock;
-};
-
-/* used by the raid56 code to lock stripes for read/modify/write */
-struct btrfs_stripe_hash_table {
- struct list_head stripe_cache;
- spinlock_t cache_lock;
- int cache_size;
- struct btrfs_stripe_hash table[];
-};
-
-#define BTRFS_STRIPE_HASH_TABLE_BITS 11
-
void btrfs_init_async_reclaim_work(struct work_struct *work);
/* fs_info */
@@ -716,41 +462,71 @@
struct btrfs_balance_control;
struct btrfs_delayed_root;
-#define BTRFS_FS_BARRIER 1
-#define BTRFS_FS_CLOSING_START 2
-#define BTRFS_FS_CLOSING_DONE 3
-#define BTRFS_FS_LOG_RECOVERING 4
-#define BTRFS_FS_OPEN 5
-#define BTRFS_FS_QUOTA_ENABLED 6
-#define BTRFS_FS_UPDATE_UUID_TREE_GEN 9
-#define BTRFS_FS_CREATING_FREE_SPACE_TREE 10
-#define BTRFS_FS_BTREE_ERR 11
-#define BTRFS_FS_LOG1_ERR 12
-#define BTRFS_FS_LOG2_ERR 13
-#define BTRFS_FS_QUOTA_OVERRIDE 14
-/* Used to record internally whether fs has been frozen */
-#define BTRFS_FS_FROZEN 15
-
/*
- * Indicate that a whole-filesystem exclusive operation is running
- * (device replace, resize, device add/delete, balance)
+ * 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.
*/
-#define BTRFS_FS_EXCL_OP 16
+struct btrfs_swapfile_pin {
+ struct rb_node node;
+ void *ptr;
+ struct inode *inode;
+ /*
+ * If true, ptr points to a struct btrfs_block_group_cache. Otherwise,
+ * ptr points to a struct btrfs_device.
+ */
+ bool is_block_group;
+};
-/*
- * To info transaction_kthread we need an immediate commit so it doesn't
- * need to wait for commit_interval
- */
-#define BTRFS_FS_NEED_ASYNC_COMMIT 17
+bool btrfs_pinned_by_swapfile(struct btrfs_fs_info *fs_info, void *ptr);
-/*
- * Indicate that balance has been set up from the ioctl and is in the main
- * phase. The fs_info::balance_ctl is initialized.
- */
-#define BTRFS_FS_BALANCE_RUNNING 18
+enum {
+ BTRFS_FS_BARRIER,
+ BTRFS_FS_CLOSING_START,
+ BTRFS_FS_CLOSING_DONE,
+ BTRFS_FS_LOG_RECOVERING,
+ BTRFS_FS_OPEN,
+ BTRFS_FS_QUOTA_ENABLED,
+ BTRFS_FS_UPDATE_UUID_TREE_GEN,
+ BTRFS_FS_CREATING_FREE_SPACE_TREE,
+ BTRFS_FS_BTREE_ERR,
+ BTRFS_FS_LOG1_ERR,
+ BTRFS_FS_LOG2_ERR,
+ BTRFS_FS_QUOTA_OVERRIDE,
+ /* Used to record internally whether fs has been frozen */
+ BTRFS_FS_FROZEN,
+ /*
+ * Indicate that a whole-filesystem exclusive operation is running
+ * (device replace, resize, device add/delete, balance)
+ */
+ BTRFS_FS_EXCL_OP,
+ /*
+ * To info transaction_kthread we need an immediate commit so it
+ * doesn't need to wait for commit_interval
+ */
+ BTRFS_FS_NEED_ASYNC_COMMIT,
+ /*
+ * Indicate that balance has been set up from the ioctl and is in the
+ * main phase. The fs_info::balance_ctl is initialized.
+ * Set and cleared while holding fs_info::balance_mutex.
+ */
+ BTRFS_FS_BALANCE_RUNNING,
+
+ /* Indicate that the cleaner thread is awake and doing something. */
+ BTRFS_FS_CLEANER_RUNNING,
+
+ /*
+ * The checksumming has an optimized version and is considered fast,
+ * so we don't need to offload checksums to workqueues.
+ */
+ BTRFS_FS_CSUM_IMPL_FAST,
+};
struct btrfs_fs_info {
- u8 fsid[BTRFS_FSID_SIZE];
u8 chunk_tree_uuid[BTRFS_UUID_SIZE];
unsigned long flags;
struct btrfs_root *extent_root;
@@ -781,7 +557,7 @@
struct extent_io_tree *pinned_extents;
/* logical->physical extent mapping */
- struct btrfs_mapping_tree mapping_tree;
+ struct extent_map_tree mapping_tree;
/*
* block reservation for extent, checksum, root tree and
@@ -794,6 +570,8 @@
struct btrfs_block_rsv chunk_block_rsv;
/* block reservation for delayed operations */
struct btrfs_block_rsv delayed_block_rsv;
+ /* block reservation for delayed refs */
+ struct btrfs_block_rsv delayed_refs_rsv;
struct btrfs_block_rsv empty_block_rsv;
@@ -890,7 +668,8 @@
spinlock_t delayed_iput_lock;
struct list_head delayed_iputs;
- struct mutex cleaner_delayed_iput_mutex;
+ atomic_t nr_delayed_iputs;
+ wait_queue_head_t delayed_iputs_wait;
/* this protects tree_mod_seq_list */
spinlock_t tree_mod_seq_lock;
@@ -955,21 +734,18 @@
struct btrfs_workqueue *fixup_workers;
struct btrfs_workqueue *delayed_workers;
- /* the extent workers do delayed refs on the extent allocation tree */
- struct btrfs_workqueue *extent_workers;
struct task_struct *transaction_kthread;
struct task_struct *cleaner_kthread;
u32 thread_pool_size;
struct kobject *space_info_kobj;
- struct list_head pending_raid_kobjs;
- spinlock_t pending_raid_kobjs_lock; /* uncontended */
u64 total_pinned;
/* used to keep from writing metadata until there is a nice batch */
struct percpu_counter dirty_metadata_bytes;
struct percpu_counter delalloc_bytes;
+ struct percpu_counter dio_bytes;
s32 dirty_metadata_batch;
s32 delalloc_batch;
@@ -1030,10 +806,13 @@
atomic_t scrubs_paused;
atomic_t scrub_cancel_req;
wait_queue_head_t scrub_pause_wait;
- int scrub_workers_refcnt;
+ /*
+ * The worker pointers are NULL iff the refcount is 0, ie. scrub is not
+ * running.
+ */
+ refcount_t scrub_workers_refcnt;
struct btrfs_workqueue *scrub_workers;
struct btrfs_workqueue *scrub_wr_completion_workers;
- struct btrfs_workqueue *scrub_nocow_workers;
struct btrfs_workqueue *scrub_parity_workers;
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
@@ -1044,10 +823,7 @@
/* holds configuration and tracking. Protected by qgroup_lock */
struct rb_root qgroup_tree;
- struct rb_root qgroup_op_tree;
spinlock_t qgroup_lock;
- spinlock_t qgroup_op_lock;
- atomic_t qgroup_op_seq;
/*
* used to avoid frequently calling ulist_alloc()/ulist_free()
@@ -1094,9 +870,6 @@
/* device replace state */
struct btrfs_dev_replace dev_replace;
- struct percpu_counter bio_counter;
- wait_queue_head_t replace_wait;
-
struct semaphore uuid_tree_rescan_sem;
/* Used to reclaim the metadata space in the background. */
@@ -1107,20 +880,23 @@
struct mutex unused_bg_unpin_mutex;
struct mutex delete_unused_bgs_mutex;
- /* For btrfs to record security options */
- struct security_mnt_opts security_opts;
-
- /*
- * Chunks that can't be freed yet (under a trim/discard operation)
- * and will be latter freed. Protected by fs_info->chunk_mutex.
- */
- struct list_head pinned_chunks;
-
/* Cached block sizes */
u32 nodesize;
u32 sectorsize;
u32 stripesize;
+ /* Block groups and devices containing active swapfiles. */
+ spinlock_t swapfile_pins_lock;
+ struct rb_root swapfile_pins;
+
+ struct crypto_shash *csum_shash;
+
+ /*
+ * Number of send operations in progress.
+ * Updated while holding fs_info::balance_mutex.
+ */
+ int send_in_progress;
+
#ifdef CONFIG_BTRFS_FS_REF_VERIFY
spinlock_t ref_verify_lock;
struct rb_root block_tree;
@@ -1140,22 +916,44 @@
/*
* The state of btrfs root
*/
+enum {
+ /*
+ * btrfs_record_root_in_trans is a multi-step process, and it can race
+ * with the balancing code. But the race is very small, and only the
+ * first time the root is added to each transaction. So IN_TRANS_SETUP
+ * is used to tell us when more checks are required
+ */
+ BTRFS_ROOT_IN_TRANS_SETUP,
+ BTRFS_ROOT_REF_COWS,
+ BTRFS_ROOT_TRACK_DIRTY,
+ BTRFS_ROOT_IN_RADIX,
+ BTRFS_ROOT_ORPHAN_ITEM_INSERTED,
+ BTRFS_ROOT_DEFRAG_RUNNING,
+ BTRFS_ROOT_FORCE_COW,
+ BTRFS_ROOT_MULTI_LOG_TASKS,
+ BTRFS_ROOT_DIRTY,
+ BTRFS_ROOT_DELETING,
+
+ /*
+ * Reloc tree is orphan, only kept here for qgroup delayed subtree scan
+ *
+ * Set for the subvolume tree owning the reloc tree.
+ */
+ BTRFS_ROOT_DEAD_RELOC_TREE,
+ /* Mark dead root stored on device whose cleanup needs to be resumed */
+ BTRFS_ROOT_DEAD_TREE,
+};
+
/*
- * btrfs_record_root_in_trans is a multi-step process,
- * and it can race with the balancing code. But the
- * race is very small, and only the first time the root
- * is added to each transaction. So IN_TRANS_SETUP
- * is used to tell us when more checks are required
+ * Record swapped tree blocks of a subvolume tree for delayed subtree trace
+ * code. For detail check comment in fs/btrfs/qgroup.c.
*/
-#define BTRFS_ROOT_IN_TRANS_SETUP 0
-#define BTRFS_ROOT_REF_COWS 1
-#define BTRFS_ROOT_TRACK_DIRTY 2
-#define BTRFS_ROOT_IN_RADIX 3
-#define BTRFS_ROOT_ORPHAN_ITEM_INSERTED 4
-#define BTRFS_ROOT_DEFRAG_RUNNING 5
-#define BTRFS_ROOT_FORCE_COW 6
-#define BTRFS_ROOT_MULTI_LOG_TASKS 7
-#define BTRFS_ROOT_DIRTY 8
+struct btrfs_qgroup_swapped_blocks {
+ spinlock_t lock;
+ /* RM_EMPTY_ROOT() of above blocks[] */
+ bool swapped;
+ struct rb_root blocks[BTRFS_MAX_LEVEL];
+};
/*
* in ram representation of the tree. extent_root is used for all allocations
@@ -1202,18 +1000,12 @@
int last_log_commit;
pid_t log_start_pid;
- u64 objectid;
u64 last_trans;
u32 type;
u64 highest_objectid;
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- /* only used with CONFIG_BTRFS_FS_RUN_SANITY_TESTS is enabled */
- u64 alloc_bytenr;
-#endif
-
u64 defrag_trans_start;
struct btrfs_key defrag_progress;
struct btrfs_key defrag_max;
@@ -1274,10 +1066,24 @@
u64 nr_ordered_extents;
/*
+ * Not empty if this subvolume root has gone through tree block swap
+ * (relocation)
+ *
+ * Will be used by reloc_control::dirty_subvol_roots.
+ */
+ struct list_head reloc_dirty_list;
+
+ /*
* Number of currently running SEND ioctls to prevent
* manipulation with the read-only status via SUBVOL_SETFLAGS
*/
int send_in_progress;
+ /*
+ * Number of currently running deduplication operations that have a
+ * destination inode belonging to this root. Protected by the lock
+ * root_item_lock.
+ */
+ int dedupe_in_progress;
struct btrfs_subvolume_writers *subv_writers;
atomic_t will_be_snapshotted;
atomic_t snapshot_force_cow;
@@ -1286,6 +1092,26 @@
spinlock_t qgroup_meta_rsv_lock;
u64 qgroup_meta_rsv_pertrans;
u64 qgroup_meta_rsv_prealloc;
+
+ /* Number of active swapfiles */
+ atomic_t nr_swapfiles;
+
+ /* Record pairs of swapped blocks for qgroup */
+ struct btrfs_qgroup_swapped_blocks swapped_blocks;
+
+#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+ u64 alloc_bytenr;
+#endif
+};
+
+struct btrfs_clone_extent_info {
+ u64 disk_offset;
+ u64 disk_len;
+ u64 data_offset;
+ u64 data_len;
+ u64 file_offset;
+ char *extent_buf;
+ u32 item_size;
};
struct btrfs_file_private {
@@ -1386,19 +1212,6 @@
btrfs_clear_opt(fs_info->mount_opt, opt); \
}
-#ifdef CONFIG_BTRFS_DEBUG
-static inline int
-btrfs_should_fragment_free_space(struct btrfs_block_group_cache *block_group)
-{
- struct btrfs_fs_info *fs_info = block_group->fs_info;
-
- return (btrfs_test_opt(fs_info, FRAGMENT_METADATA) &&
- block_group->flags & BTRFS_BLOCK_GROUP_METADATA) ||
- (btrfs_test_opt(fs_info, FRAGMENT_DATA) &&
- block_group->flags & BTRFS_BLOCK_GROUP_DATA);
-}
-#endif
-
/*
* Requests for changes that need to be done during transaction commit.
*
@@ -1460,6 +1273,21 @@
#define BTRFS_INODE_ROOT_ITEM_INIT (1 << 31)
+#define BTRFS_INODE_FLAG_MASK \
+ (BTRFS_INODE_NODATASUM | \
+ BTRFS_INODE_NODATACOW | \
+ BTRFS_INODE_READONLY | \
+ BTRFS_INODE_NOCOMPRESS | \
+ BTRFS_INODE_PREALLOC | \
+ BTRFS_INODE_SYNC | \
+ BTRFS_INODE_IMMUTABLE | \
+ BTRFS_INODE_APPEND | \
+ BTRFS_INODE_NODUMP | \
+ BTRFS_INODE_NOATIME | \
+ BTRFS_INODE_DIRSYNC | \
+ BTRFS_INODE_COMPRESS | \
+ BTRFS_INODE_ROOT_ITEM_INIT)
+
struct btrfs_map_token {
const struct extent_buffer *eb;
char *kaddr;
@@ -1469,8 +1297,10 @@
#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) \
((bytes) >> (fs_info)->sb->s_blocksize_bits)
-static inline void btrfs_init_map_token (struct btrfs_map_token *token)
+static inline void btrfs_init_map_token(struct btrfs_map_token *token,
+ struct extent_buffer *eb)
{
+ token->eb = eb;
token->kaddr = NULL;
}
@@ -1501,17 +1331,10 @@
void btrfs_set_token_##bits(struct extent_buffer *eb, const void *ptr, \
unsigned long off, u##bits val, \
struct btrfs_map_token *token); \
-static inline u##bits btrfs_get_##bits(const struct extent_buffer *eb, \
- const void *ptr, \
- unsigned long off) \
-{ \
- return btrfs_get_token_##bits(eb, ptr, off, NULL); \
-} \
-static inline void btrfs_set_##bits(struct extent_buffer *eb, void *ptr,\
- unsigned long off, u##bits val) \
-{ \
- btrfs_set_token_##bits(eb, ptr, off, val, NULL); \
-}
+u##bits btrfs_get_##bits(const struct extent_buffer *eb, \
+ const void *ptr, unsigned long off); \
+void btrfs_set_##bits(struct extent_buffer *eb, void *ptr, \
+ unsigned long off, u##bits val);
DECLARE_BTRFS_SETGET_BITS(8)
DECLARE_BTRFS_SETGET_BITS(16)
@@ -2053,16 +1876,6 @@
btrfs_disk_key_to_cpu(key, &disk_key);
}
-static inline u8 btrfs_key_type(const struct btrfs_key *key)
-{
- return key->type;
-}
-
-static inline void btrfs_set_key_type(struct btrfs_key *key, u8 val)
-{
- key->type = val;
-}
-
/* struct btrfs_header */
BTRFS_SETGET_HEADER_FUNCS(header_bytenr, struct btrfs_header, bytenr, 64);
BTRFS_SETGET_HEADER_FUNCS(header_generation, struct btrfs_header,
@@ -2083,18 +1896,16 @@
return (btrfs_header_flags(eb) & flag) == flag;
}
-static inline int btrfs_set_header_flag(struct extent_buffer *eb, u64 flag)
+static inline void btrfs_set_header_flag(struct extent_buffer *eb, u64 flag)
{
u64 flags = btrfs_header_flags(eb);
btrfs_set_header_flags(eb, flags | flag);
- return (flags & flag) == flag;
}
-static inline int btrfs_clear_header_flag(struct extent_buffer *eb, u64 flag)
+static inline void btrfs_clear_header_flag(struct extent_buffer *eb, u64 flag)
{
u64 flags = btrfs_header_flags(eb);
btrfs_set_header_flags(eb, flags & ~flag);
- return (flags & flag) == flag;
}
static inline int btrfs_header_backref_rev(const struct extent_buffer *eb)
@@ -2350,28 +2161,20 @@
BTRFS_SETGET_STACK_FUNCS(super_uuid_tree_generation, struct btrfs_super_block,
uuid_tree_generation, 64);
-static inline int btrfs_super_csum_size(const struct btrfs_super_block *s)
-{
- u16 t = btrfs_super_csum_type(s);
- /*
- * csum type is validated at mount time
- */
- return btrfs_csum_sizes[t];
-}
-
+int btrfs_super_csum_size(const struct btrfs_super_block *s);
+const char *btrfs_super_csum_name(u16 csum_type);
/*
* The leaf data grows from end-to-front in the node.
* this returns the address of the start of the last item,
* which is the stop of the leaf data stack
*/
-static inline unsigned int leaf_data_end(const struct btrfs_fs_info *fs_info,
- const struct extent_buffer *leaf)
+static inline unsigned int leaf_data_end(const struct extent_buffer *leaf)
{
u32 nr = btrfs_header_nritems(leaf);
if (nr == 0)
- return BTRFS_LEAF_DATA_SIZE(fs_info);
+ return BTRFS_LEAF_DATA_SIZE(leaf->fs_info);
return btrfs_item_offset_nr(leaf, nr - 1);
}
@@ -2432,30 +2235,6 @@
return btrfs_item_size(eb, e) - BTRFS_FILE_EXTENT_INLINE_DATA_START;
}
-/* btrfs_dev_stats_item */
-static inline u64 btrfs_dev_stats_value(const struct extent_buffer *eb,
- const struct btrfs_dev_stats_item *ptr,
- int index)
-{
- u64 val;
-
- read_extent_buffer(eb, &val,
- offsetof(struct btrfs_dev_stats_item, values) +
- ((unsigned long)ptr) + (index * sizeof(u64)),
- sizeof(val));
- return val;
-}
-
-static inline void btrfs_set_dev_stats_value(struct extent_buffer *eb,
- struct btrfs_dev_stats_item *ptr,
- int index, u64 val)
-{
- write_extent_buffer(eb, &val,
- offsetof(struct btrfs_dev_stats_item, values) +
- ((unsigned long)ptr) + (index * sizeof(u64)),
- sizeof(val));
-}
-
/* btrfs_qgroup_status_item */
BTRFS_SETGET_FUNCS(qgroup_status_generation, struct btrfs_qgroup_status_item,
generation, 64);
@@ -2551,6 +2330,16 @@
((unsigned long)(BTRFS_LEAF_DATA_OFFSET + \
btrfs_item_offset_nr(leaf, slot)))
+static inline u32 btrfs_crc32c(u32 crc, const void *address, unsigned length)
+{
+ return crc32c(crc, address, length);
+}
+
+static inline void btrfs_crc32c_final(u32 crc, u8 *result)
+{
+ put_unaligned_le32(~crc, result);
+}
+
static inline u64 btrfs_name_hash(const char *name, int len)
{
return crc32c((u32)~1, name, len);
@@ -2565,12 +2354,6 @@
return (u64) crc32c(parent_objectid, name, len);
}
-static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info)
-{
- return ((space_info->flags & BTRFS_BLOCK_GROUP_METADATA) &&
- (space_info->flags & BTRFS_BLOCK_GROUP_DATA));
-}
-
static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
{
return mapping_gfp_constraint(mapping, ~__GFP_FS);
@@ -2579,49 +2362,47 @@
/* extent-tree.c */
enum btrfs_inline_ref_type {
- BTRFS_REF_TYPE_INVALID = 0,
- BTRFS_REF_TYPE_BLOCK = 1,
- BTRFS_REF_TYPE_DATA = 2,
- BTRFS_REF_TYPE_ANY = 3,
+ BTRFS_REF_TYPE_INVALID,
+ BTRFS_REF_TYPE_BLOCK,
+ BTRFS_REF_TYPE_DATA,
+ BTRFS_REF_TYPE_ANY,
};
int btrfs_get_extent_inline_ref_type(const struct extent_buffer *eb,
struct btrfs_extent_inline_ref *iref,
enum btrfs_inline_ref_type is_data);
+u64 hash_extent_data_ref(u64 root_objectid, u64 owner, u64 offset);
u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes);
-static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info,
- unsigned num_items)
+/*
+ * Use this if we would be adding new items, as we could split nodes as we cow
+ * down the tree.
+ */
+static inline u64 btrfs_calc_insert_metadata_size(struct btrfs_fs_info *fs_info,
+ unsigned num_items)
{
return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
}
/*
- * Doing a truncate won't result in new nodes or leaves, just what we need for
- * COW.
+ * Doing a truncate or a modification won't result in new nodes or leaves, just
+ * what we need for COW.
*/
-static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info,
+static inline u64 btrfs_calc_metadata_size(struct btrfs_fs_info *fs_info,
unsigned num_items)
{
return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
}
-int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info);
-int btrfs_check_space_for_delayed_refs(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info);
-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_add_excluded_extent(struct btrfs_fs_info *fs_info,
+ u64 start, u64 num_bytes);
+void btrfs_free_excluded_extents(struct btrfs_block_group_cache *cache);
int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
unsigned long count);
-int btrfs_async_run_delayed_refs(struct btrfs_fs_info *fs_info,
- unsigned long count, u64 transid, int wait);
+void btrfs_cleanup_ref_head_accounting(struct btrfs_fs_info *fs_info,
+ struct btrfs_delayed_ref_root *delayed_refs,
+ struct btrfs_delayed_ref_head *head);
int btrfs_lookup_data_extent(struct btrfs_fs_info *fs_info, u64 start, u64 len);
int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr,
@@ -2630,15 +2411,9 @@
u64 bytenr, u64 num, int reserved);
int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info,
u64 bytenr, u64 num_bytes);
-int btrfs_exclude_logged_extents(struct btrfs_fs_info *fs_info,
- struct extent_buffer *eb);
+int btrfs_exclude_logged_extents(struct extent_buffer *eb);
int btrfs_cross_ref_exist(struct btrfs_root *root,
u64 objectid, u64 offset, u64 bytenr);
-struct btrfs_block_group_cache *btrfs_lookup_block_group(
- struct btrfs_fs_info *info,
- u64 bytenr);
-void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
-void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
u64 parent, u64 root_objectid,
@@ -2664,13 +2439,9 @@
int btrfs_dec_ref(struct btrfs_trans_handle *trans, struct btrfs_root *root,
struct extent_buffer *buf, int full_backref);
int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info,
u64 bytenr, u64 num_bytes, u64 flags,
int level, int is_data);
-int btrfs_free_extent(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
- u64 owner, u64 offset);
+int btrfs_free_extent(struct btrfs_trans_handle *trans, struct btrfs_ref *ref);
int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
u64 start, u64 len, int delalloc);
@@ -2679,35 +2450,11 @@
void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info);
int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans);
int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
- struct btrfs_root *root,
- u64 bytenr, u64 num_bytes, u64 parent,
- u64 root_objectid, u64 owner, u64 offset);
+ struct btrfs_ref *generic_ref);
-int btrfs_start_dirty_block_groups(struct btrfs_trans_handle *trans);
-int btrfs_write_dirty_block_groups(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info);
-int btrfs_setup_space_cache(struct btrfs_trans_handle *trans,
- struct btrfs_fs_info *fs_info);
int btrfs_extent_readonly(struct btrfs_fs_info *fs_info, u64 bytenr);
-int btrfs_free_block_groups(struct btrfs_fs_info *info);
-int btrfs_read_block_groups(struct btrfs_fs_info *info);
-int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr);
-int btrfs_make_block_group(struct btrfs_trans_handle *trans,
- u64 bytes_used, u64 type, u64 chunk_offset,
- u64 size);
-void btrfs_add_raid_kobjects(struct btrfs_fs_info *fs_info);
-struct btrfs_trans_handle *btrfs_start_trans_remove_block_group(
- struct btrfs_fs_info *fs_info,
- const u64 chunk_offset);
-int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
- u64 group_start, struct extent_map *em);
-void btrfs_delete_unused_bgs(struct btrfs_fs_info *fs_info);
void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
-void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans);
-u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info);
-u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info);
-u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info);
void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
enum btrfs_reserve_flush_enum {
@@ -2718,75 +2465,36 @@
* case, use FLUSH LIMIT
*/
BTRFS_RESERVE_FLUSH_LIMIT,
+ BTRFS_RESERVE_FLUSH_EVICT,
BTRFS_RESERVE_FLUSH_ALL,
};
enum btrfs_flush_state {
FLUSH_DELAYED_ITEMS_NR = 1,
FLUSH_DELAYED_ITEMS = 2,
- FLUSH_DELALLOC = 3,
- FLUSH_DELALLOC_WAIT = 4,
- ALLOC_CHUNK = 5,
- COMMIT_TRANS = 6,
+ FLUSH_DELAYED_REFS_NR = 3,
+ FLUSH_DELAYED_REFS = 4,
+ FLUSH_DELALLOC = 5,
+ FLUSH_DELALLOC_WAIT = 6,
+ ALLOC_CHUNK = 7,
+ ALLOC_CHUNK_FORCE = 8,
+ RUN_DELAYED_IPUTS = 9,
+ COMMIT_TRANS = 10,
};
-int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
-int btrfs_check_data_free_space(struct inode *inode,
- struct extent_changeset **reserved, u64 start, u64 len);
-void btrfs_free_reserved_data_space(struct inode *inode,
- struct extent_changeset *reserved, u64 start, u64 len);
-void btrfs_delalloc_release_space(struct inode *inode,
- struct extent_changeset *reserved,
- u64 start, u64 len, bool qgroup_free);
-void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
- u64 len);
-void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
struct btrfs_block_rsv *rsv,
int nitems, bool use_global_rsv);
void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
struct btrfs_block_rsv *rsv);
-void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes,
- bool qgroup_free);
+void btrfs_delalloc_release_extents(struct btrfs_inode *inode, u64 num_bytes);
int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
-void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes,
- bool qgroup_free);
-int btrfs_delalloc_reserve_space(struct inode *inode,
- struct extent_changeset **reserved, u64 start, u64 len);
-void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
-struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info,
- unsigned short type);
-void btrfs_init_metadata_block_rsv(struct btrfs_fs_info *fs_info,
- struct btrfs_block_rsv *rsv,
- unsigned short type);
-void btrfs_free_block_rsv(struct btrfs_fs_info *fs_info,
- struct btrfs_block_rsv *rsv);
-int btrfs_block_rsv_add(struct btrfs_root *root,
- struct btrfs_block_rsv *block_rsv, u64 num_bytes,
- enum btrfs_reserve_flush_enum flush);
-int btrfs_block_rsv_check(struct btrfs_block_rsv *block_rsv, int min_factor);
-int btrfs_block_rsv_refill(struct btrfs_root *root,
- struct btrfs_block_rsv *block_rsv, u64 min_reserved,
- enum btrfs_reserve_flush_enum flush);
-int btrfs_block_rsv_migrate(struct btrfs_block_rsv *src_rsv,
- struct btrfs_block_rsv *dst_rsv, u64 num_bytes,
- int update_size);
-int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
- struct btrfs_block_rsv *dest, u64 num_bytes,
- int min_factor);
-void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
- struct btrfs_block_rsv *block_rsv,
- u64 num_bytes);
-int btrfs_inc_block_group_ro(struct btrfs_block_group_cache *cache);
-void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
-void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
u64 btrfs_account_ro_block_groups_free_space(struct btrfs_space_info *sinfo);
int btrfs_error_unpin_extent_range(struct btrfs_fs_info *fs_info,
u64 start, u64 end);
int btrfs_discard_extent(struct btrfs_fs_info *fs_info, u64 bytenr,
u64 num_bytes, u64 *actual_bytes);
-int btrfs_force_chunk_alloc(struct btrfs_trans_handle *trans, u64 type);
int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range);
int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
@@ -2795,10 +2503,6 @@
int btrfs_start_write_no_snapshotting(struct btrfs_root *root);
void btrfs_end_write_no_snapshotting(struct btrfs_root *root);
void btrfs_wait_for_snapshot_creation(struct btrfs_root *root);
-void check_system_chunk(struct btrfs_trans_handle *trans, const u64 type);
-u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
- u64 start, u64 end);
-void btrfs_mark_bg_unused(struct btrfs_block_group_cache *bg);
/* ctree.c */
int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
@@ -2821,20 +2525,9 @@
int btrfs_search_forward(struct btrfs_root *root, struct btrfs_key *min_key,
struct btrfs_path *path,
u64 min_trans);
-enum btrfs_compare_tree_result {
- BTRFS_COMPARE_TREE_NEW,
- BTRFS_COMPARE_TREE_DELETED,
- BTRFS_COMPARE_TREE_CHANGED,
- BTRFS_COMPARE_TREE_SAME,
-};
-typedef int (*btrfs_changed_cb_t)(struct btrfs_path *left_path,
- struct btrfs_path *right_path,
- struct btrfs_key *key,
- enum btrfs_compare_tree_result result,
- void *ctx);
-int btrfs_compare_trees(struct btrfs_root *left_root,
- struct btrfs_root *right_root,
- btrfs_changed_cb_t cb, void *ctx);
+struct extent_buffer *btrfs_read_node_slot(struct extent_buffer *parent,
+ int slot);
+
int btrfs_cow_block(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct extent_buffer *buf,
struct extent_buffer *parent, int parent_slot,
@@ -2845,10 +2538,8 @@
struct extent_buffer **cow_ret, u64 new_root_objectid);
int btrfs_block_can_be_shared(struct btrfs_root *root,
struct extent_buffer *buf);
-void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
- u32 data_size);
-void btrfs_truncate_item(struct btrfs_fs_info *fs_info,
- struct btrfs_path *path, u32 new_size, int from_end);
+void btrfs_extend_item(struct btrfs_path *path, u32 data_size);
+void btrfs_truncate_item(struct btrfs_path *path, u32 new_size, int from_end);
int btrfs_split_item(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_path *path,
@@ -2877,8 +2568,6 @@
struct btrfs_path *btrfs_alloc_path(void);
void btrfs_free_path(struct btrfs_path *p);
void btrfs_set_path_blocking(struct btrfs_path *p);
-void btrfs_clear_path_blocking(struct btrfs_path *p,
- struct extent_buffer *held, int held_rw);
void btrfs_unlock_up_safe(struct btrfs_path *p, int level);
int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
@@ -2926,8 +2615,7 @@
{
return btrfs_next_old_item(root, p, 0);
}
-int btrfs_leaf_free_space(struct btrfs_fs_info *fs_info,
- struct extent_buffer *leaf);
+int btrfs_leaf_free_space(struct extent_buffer *leaf);
int __must_check btrfs_drop_snapshot(struct btrfs_root *root,
struct btrfs_block_rsv *block_rsv,
int update_ref, int for_reloc);
@@ -2972,7 +2660,6 @@
kfree(fs_info->free_space_root);
kfree(fs_info->super_copy);
kfree(fs_info->super_for_commit);
- security_free_mnt_opts(&fs_info->security_opts);
kvfree(fs_info);
}
@@ -3021,8 +2708,7 @@
/* dir-item.c */
int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
const char *name, int name_len);
-int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,
- struct btrfs_root *root, const char *name,
+int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, const char *name,
int name_len, struct btrfs_inode *dir,
struct btrfs_key *location, u8 type, u64 index);
struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans,
@@ -3090,19 +2776,18 @@
u64 inode_objectid, u64 ref_objectid, int ins_len,
int cow);
-int btrfs_find_name_in_backref(struct extent_buffer *leaf, int slot,
- const char *name,
- int name_len, struct btrfs_inode_ref **ref_ret);
-int btrfs_find_name_in_ext_backref(struct extent_buffer *leaf, int slot,
- u64 ref_objectid, const char *name,
- int name_len,
- struct btrfs_inode_extref **extref_ret);
-
+struct btrfs_inode_ref *btrfs_find_name_in_backref(struct extent_buffer *leaf,
+ int slot, const char *name,
+ int name_len);
+struct btrfs_inode_extref *btrfs_find_name_in_ext_backref(
+ struct extent_buffer *leaf, int slot, u64 ref_objectid,
+ const char *name, int name_len);
/* file-item.c */
struct btrfs_dio_private;
int btrfs_del_csums(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info, u64 bytenr, u64 len);
-blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst);
+blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
+ u8 *dst);
blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio,
u64 logical_offset);
int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
@@ -3130,8 +2815,7 @@
/* inode.c */
struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
- struct page *page, size_t pg_offset, u64 start,
- u64 len, int create);
+ u64 start, u64 len);
noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
u64 *orig_start, u64 *orig_block_len,
u64 *ram_bytes);
@@ -3155,18 +2839,25 @@
struct inode *inode, u64 new_size,
u32 min_type);
-int btrfs_start_delalloc_inodes(struct btrfs_root *root);
+int btrfs_start_delalloc_snapshot(struct btrfs_root *root);
int btrfs_start_delalloc_roots(struct btrfs_fs_info *fs_info, int nr);
int btrfs_set_extent_delalloc(struct inode *inode, u64 start, u64 end,
unsigned int extra_bits,
- struct extent_state **cached_state, int dedupe);
+ struct extent_state **cached_state);
int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
struct btrfs_root *new_root,
struct btrfs_root *parent_root,
u64 new_dirid);
-int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
- size_t size, struct bio *bio,
- unsigned long bio_flags);
+ void btrfs_set_delalloc_extent(struct inode *inode, struct extent_state *state,
+ unsigned *bits);
+void btrfs_clear_delalloc_extent(struct inode *inode,
+ struct extent_state *state, unsigned *bits);
+void btrfs_merge_delalloc_extent(struct inode *inode, struct extent_state *new,
+ struct extent_state *other);
+void btrfs_split_delalloc_extent(struct inode *inode,
+ struct extent_state *orig, u64 split);
+int btrfs_bio_fits_in_stripe(struct page *page, size_t size, struct bio *bio,
+ unsigned long bio_flags);
void btrfs_set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end);
vm_fault_t btrfs_page_mkwrite(struct vm_fault *vmf);
int btrfs_readpage(struct file *file, struct page *page);
@@ -3174,14 +2865,18 @@
int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
struct inode *btrfs_alloc_inode(struct super_block *sb);
void btrfs_destroy_inode(struct inode *inode);
+void btrfs_free_inode(struct inode *inode);
int btrfs_drop_inode(struct inode *inode);
int __init btrfs_init_cachep(void);
void __cold btrfs_destroy_cachep(void);
+struct inode *btrfs_iget_path(struct super_block *s, struct btrfs_key *location,
+ struct btrfs_root *root, int *new,
+ struct btrfs_path *path);
struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
struct btrfs_root *root, int *was_new);
struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
- struct page *page, size_t pg_offset,
- u64 start, u64 end, int create);
+ struct page *page, size_t pg_offset,
+ u64 start, u64 end, int create);
int btrfs_update_inode(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct inode *inode);
@@ -3193,6 +2888,7 @@
int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size);
void btrfs_add_delayed_iput(struct inode *inode);
void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info);
+int btrfs_wait_on_delayed_iputs(struct btrfs_fs_info *fs_info);
int btrfs_prealloc_file_range(struct inode *inode, int mode,
u64 start, u64 num_bytes, u64 min_size,
loff_t actual_len, u64 *alloc_hint);
@@ -3200,10 +2896,13 @@
struct btrfs_trans_handle *trans, int mode,
u64 start, u64 num_bytes, u64 min_size,
loff_t actual_len, u64 *alloc_hint);
+int btrfs_run_delalloc_range(struct inode *inode, struct page *locked_page,
+ u64 start, u64 end, int *page_started, unsigned long *nr_written,
+ struct writeback_control *wbc);
+int btrfs_writepage_cow_fixup(struct page *page, u64 start, u64 end);
+void btrfs_writepage_endio_finish_ordered(struct page *page, u64 start,
+ u64 end, int uptodate);
extern const struct dentry_operations btrfs_dentry_operations;
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
-void btrfs_test_inode_set_ops(struct inode *inode);
-#endif
/* ioctl.c */
long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
@@ -3218,9 +2917,6 @@
struct btrfs_ioctl_space_info *space);
void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
struct btrfs_ioctl_balance_args *bargs);
-int btrfs_dedupe_file_range(struct file *src_file, loff_t src_loff,
- struct file *dst_file, loff_t dst_loff,
- u64 olen);
/* file.c */
int __init btrfs_auto_defrag_init(void);
@@ -3243,6 +2939,10 @@
int btrfs_drop_extents(struct btrfs_trans_handle *trans,
struct btrfs_root *root, struct inode *inode, u64 start,
u64 end, int drop_cache);
+int btrfs_punch_hole_range(struct inode *inode, struct btrfs_path *path,
+ const u64 start, const u64 end,
+ struct btrfs_clone_extent_info *clone_info,
+ struct btrfs_trans_handle **trans_out);
int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
struct btrfs_inode *inode, u64 start, u64 end);
int btrfs_release_file(struct inode *inode, struct file *file);
@@ -3250,19 +2950,14 @@
size_t num_pages, loff_t pos, size_t write_bytes,
struct extent_state **cached);
int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end);
-int btrfs_clone_file_range(struct file *file_in, loff_t pos_in,
- struct file *file_out, loff_t pos_out, u64 len);
+loff_t btrfs_remap_file_range(struct file *file_in, loff_t pos_in,
+ struct file *file_out, loff_t pos_out,
+ loff_t len, unsigned int remap_flags);
/* tree-defrag.c */
int btrfs_defrag_leaves(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
-/* sysfs.c */
-int __init btrfs_init_sysfs(void);
-void __cold btrfs_exit_sysfs(void);
-int btrfs_sysfs_add_mounted(struct btrfs_fs_info *fs_info);
-void btrfs_sysfs_remove_mounted(struct btrfs_fs_info *fs_info);
-
/* super.c */
int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
unsigned long new_flags);
@@ -3353,31 +3048,17 @@
#if defined(CONFIG_DYNAMIC_DEBUG)
#define btrfs_debug(fs_info, fmt, args...) \
-do { \
- DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \
- if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \
- btrfs_printk(fs_info, KERN_DEBUG fmt, ##args); \
-} while (0)
-#define btrfs_debug_in_rcu(fs_info, fmt, args...) \
-do { \
- DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \
- if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \
- btrfs_printk_in_rcu(fs_info, KERN_DEBUG fmt, ##args); \
-} while (0)
+ _dynamic_func_call_no_desc(fmt, btrfs_printk, \
+ fs_info, KERN_DEBUG fmt, ##args)
+#define btrfs_debug_in_rcu(fs_info, fmt, args...) \
+ _dynamic_func_call_no_desc(fmt, btrfs_printk_in_rcu, \
+ fs_info, KERN_DEBUG fmt, ##args)
#define btrfs_debug_rl_in_rcu(fs_info, fmt, args...) \
-do { \
- DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \
- if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \
- btrfs_printk_rl_in_rcu(fs_info, KERN_DEBUG fmt, \
- ##args);\
-} while (0)
-#define btrfs_debug_rl(fs_info, fmt, args...) \
-do { \
- DEFINE_DYNAMIC_DEBUG_METADATA(descriptor, fmt); \
- if (unlikely(descriptor.flags & _DPRINTK_FLAGS_PRINT)) \
- btrfs_printk_ratelimited(fs_info, KERN_DEBUG fmt, \
- ##args); \
-} while (0)
+ _dynamic_func_call_no_desc(fmt, btrfs_printk_rl_in_rcu, \
+ fs_info, KERN_DEBUG fmt, ##args)
+#define btrfs_debug_rl(fs_info, fmt, args...) \
+ _dynamic_func_call_no_desc(fmt, btrfs_printk_ratelimited, \
+ fs_info, KERN_DEBUG fmt, ##args)
#elif defined(DEBUG)
#define btrfs_debug(fs_info, fmt, args...) \
btrfs_printk(fs_info, KERN_DEBUG fmt, ##args)
@@ -3428,20 +3109,26 @@
rcu_read_unlock(); \
} while (0)
-#ifdef CONFIG_BTRFS_ASSERT
-
__cold
static inline void assfail(const char *expr, const char *file, int line)
{
- pr_err("assertion failed: %s, file: %s, line: %d\n",
- expr, file, line);
- BUG();
+ if (IS_ENABLED(CONFIG_BTRFS_ASSERT)) {
+ pr_err("assertion failed: %s, in %s:%d\n", expr, file, line);
+ BUG();
+ }
}
#define ASSERT(expr) \
(likely(expr) ? (void)0 : assfail(#expr, __FILE__, __LINE__))
+
+/*
+ * Use that for functions that are conditionally exported for sanity tests but
+ * otherwise static
+ */
+#ifndef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+#define EXPORT_FOR_TESTS static
#else
-#define ASSERT(expr) ((void)0)
+#define EXPORT_FOR_TESTS
#endif
__cold
@@ -3510,10 +3197,11 @@
/* compatibility and incompatibility defines */
#define btrfs_set_fs_incompat(__fs_info, opt) \
- __btrfs_set_fs_incompat((__fs_info), BTRFS_FEATURE_INCOMPAT_##opt)
+ __btrfs_set_fs_incompat((__fs_info), BTRFS_FEATURE_INCOMPAT_##opt, \
+ #opt)
static inline void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info,
- u64 flag)
+ u64 flag, const char* name)
{
struct btrfs_super_block *disk_super;
u64 features;
@@ -3526,18 +3214,20 @@
if (!(features & flag)) {
features |= flag;
btrfs_set_super_incompat_flags(disk_super, features);
- btrfs_info(fs_info, "setting %llu feature flag",
- flag);
+ btrfs_info(fs_info,
+ "setting incompat feature flag for %s (0x%llx)",
+ name, flag);
}
spin_unlock(&fs_info->super_lock);
}
}
#define btrfs_clear_fs_incompat(__fs_info, opt) \
- __btrfs_clear_fs_incompat((__fs_info), BTRFS_FEATURE_INCOMPAT_##opt)
+ __btrfs_clear_fs_incompat((__fs_info), BTRFS_FEATURE_INCOMPAT_##opt, \
+ #opt)
static inline void __btrfs_clear_fs_incompat(struct btrfs_fs_info *fs_info,
- u64 flag)
+ u64 flag, const char* name)
{
struct btrfs_super_block *disk_super;
u64 features;
@@ -3550,8 +3240,9 @@
if (features & flag) {
features &= ~flag;
btrfs_set_super_incompat_flags(disk_super, features);
- btrfs_info(fs_info, "clearing %llu feature flag",
- flag);
+ btrfs_info(fs_info,
+ "clearing incompat feature flag for %s (0x%llx)",
+ name, flag);
}
spin_unlock(&fs_info->super_lock);
}
@@ -3568,10 +3259,11 @@
}
#define btrfs_set_fs_compat_ro(__fs_info, opt) \
- __btrfs_set_fs_compat_ro((__fs_info), BTRFS_FEATURE_COMPAT_RO_##opt)
+ __btrfs_set_fs_compat_ro((__fs_info), BTRFS_FEATURE_COMPAT_RO_##opt, \
+ #opt)
static inline void __btrfs_set_fs_compat_ro(struct btrfs_fs_info *fs_info,
- u64 flag)
+ u64 flag, const char *name)
{
struct btrfs_super_block *disk_super;
u64 features;
@@ -3584,18 +3276,20 @@
if (!(features & flag)) {
features |= flag;
btrfs_set_super_compat_ro_flags(disk_super, features);
- btrfs_info(fs_info, "setting %llu ro feature flag",
- flag);
+ btrfs_info(fs_info,
+ "setting compat-ro feature flag for %s (0x%llx)",
+ name, flag);
}
spin_unlock(&fs_info->super_lock);
}
}
#define btrfs_clear_fs_compat_ro(__fs_info, opt) \
- __btrfs_clear_fs_compat_ro((__fs_info), BTRFS_FEATURE_COMPAT_RO_##opt)
+ __btrfs_clear_fs_compat_ro((__fs_info), BTRFS_FEATURE_COMPAT_RO_##opt, \
+ #opt)
static inline void __btrfs_clear_fs_compat_ro(struct btrfs_fs_info *fs_info,
- u64 flag)
+ u64 flag, const char *name)
{
struct btrfs_super_block *disk_super;
u64 features;
@@ -3608,8 +3302,9 @@
if (features & flag) {
features &= ~flag;
btrfs_set_super_compat_ro_flags(disk_super, features);
- btrfs_info(fs_info, "clearing %llu ro feature flag",
- flag);
+ btrfs_info(fs_info,
+ "clearing compat-ro feature flag for %s (0x%llx)",
+ name, flag);
}
spin_unlock(&fs_info->super_lock);
}
@@ -3664,8 +3359,7 @@
void btrfs_scrub_pause(struct btrfs_fs_info *fs_info);
void btrfs_scrub_continue(struct btrfs_fs_info *fs_info);
int btrfs_scrub_cancel(struct btrfs_fs_info *info);
-int btrfs_scrub_cancel_dev(struct btrfs_fs_info *info,
- struct btrfs_device *dev);
+int btrfs_scrub_cancel_dev(struct btrfs_device *dev);
int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid,
struct btrfs_scrub_progress *progress);
static inline void btrfs_init_full_stripe_locks_tree(
@@ -3714,41 +3408,22 @@
return signal_pending(current);
}
+#define in_range(b, first, len) ((b) >= (first) && (b) < (first) + (len))
+
/* Sanity test specific functions */
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
+void btrfs_test_inode_set_ops(struct inode *inode);
void btrfs_test_destroy_inode(struct inode *inode);
-#endif
static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
{
-#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
- if (unlikely(test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO,
- &fs_info->fs_state)))
- return 1;
-#endif
+ return test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
+}
+#else
+static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
+{
return 0;
}
-
-static inline void cond_wake_up(struct wait_queue_head *wq)
-{
- /*
- * This implies a full smp_mb barrier, see comments for
- * waitqueue_active why.
- */
- if (wq_has_sleeper(wq))
- wake_up(wq);
-}
-
-static inline void cond_wake_up_nomb(struct wait_queue_head *wq)
-{
- /*
- * Special case for conditional wakeup where the barrier required for
- * waitqueue_active is implied by some of the preceding code. Eg. one
- * of such atomic operations (atomic_dec_and_return, ...), or a
- * unlock/lock sequence, etc.
- */
- if (waitqueue_active(wq))
- wake_up(wq);
-}
+#endif
#endif