summaryrefslogtreecommitdiff
path: root/fs/btrfs/fs.h
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/fs.h')
-rw-r--r--fs/btrfs/fs.h161
1 files changed, 109 insertions, 52 deletions
diff --git a/fs/btrfs/fs.h b/fs/btrfs/fs.h
index 93f5c57ea4e3..4394de12a767 100644
--- a/fs/btrfs/fs.h
+++ b/fs/btrfs/fs.h
@@ -9,16 +9,15 @@
#include <linux/compiler.h>
#include <linux/math.h>
#include <linux/atomic.h>
-#include <linux/blkdev.h>
#include <linux/percpu_counter.h>
#include <linux/completion.h>
#include <linux/lockdep.h>
#include <linux/spinlock.h>
#include <linux/mutex.h>
-#include <linux/rwlock_types.h>
#include <linux/rwsem.h>
#include <linux/semaphore.h>
#include <linux/list.h>
+#include <linux/pagemap.h>
#include <linux/radix-tree.h>
#include <linux/workqueue.h>
#include <linux/wait.h>
@@ -30,7 +29,6 @@
#include "extent-io-tree.h"
#include "async-thread.h"
#include "block-rsv.h"
-#include "fs.h"
struct inode;
struct super_block;
@@ -49,6 +47,18 @@ struct btrfs_subpage_info;
struct btrfs_stripe_hash_table;
struct btrfs_space_info;
+/*
+ * Minimum data and metadata block size.
+ *
+ * Normally it's 4K, but for testing subpage block size on 4K page systems, we
+ * allow DEBUG builds to accept 2K page size.
+ */
+#ifdef CONFIG_BTRFS_DEBUG
+#define BTRFS_MIN_BLOCKSIZE (SZ_2K)
+#else
+#define BTRFS_MIN_BLOCKSIZE (SZ_4K)
+#endif
+
#define BTRFS_MAX_EXTENT_SIZE SZ_128M
#define BTRFS_OLDEST_GENERATION 0ULL
@@ -100,11 +110,16 @@ enum {
/* The btrfs_fs_info created for self-tests */
BTRFS_FS_STATE_DUMMY_FS_INFO,
- BTRFS_FS_STATE_NO_CSUMS,
+ /* Checksum errors are ignored. */
+ BTRFS_FS_STATE_NO_DATA_CSUMS,
+ BTRFS_FS_STATE_SKIP_META_CSUMS,
/* Indicates there was an error cleaning up a log tree. */
BTRFS_FS_STATE_LOG_CLEANUP_ERROR,
+ /* No more delayed iput can be queued. */
+ BTRFS_FS_STATE_NO_DELAYED_IPUT,
+
BTRFS_FS_STATE_COUNT
};
@@ -195,37 +210,39 @@ enum {
* Note: don't forget to add new options to btrfs_show_options()
*/
enum {
- BTRFS_MOUNT_NODATASUM = (1UL << 0),
- BTRFS_MOUNT_NODATACOW = (1UL << 1),
- BTRFS_MOUNT_NOBARRIER = (1UL << 2),
- BTRFS_MOUNT_SSD = (1UL << 3),
- BTRFS_MOUNT_DEGRADED = (1UL << 4),
- BTRFS_MOUNT_COMPRESS = (1UL << 5),
- BTRFS_MOUNT_NOTREELOG = (1UL << 6),
- BTRFS_MOUNT_FLUSHONCOMMIT = (1UL << 7),
- BTRFS_MOUNT_SSD_SPREAD = (1UL << 8),
- BTRFS_MOUNT_NOSSD = (1UL << 9),
- BTRFS_MOUNT_DISCARD_SYNC = (1UL << 10),
- BTRFS_MOUNT_FORCE_COMPRESS = (1UL << 11),
- BTRFS_MOUNT_SPACE_CACHE = (1UL << 12),
- BTRFS_MOUNT_CLEAR_CACHE = (1UL << 13),
- BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED = (1UL << 14),
- BTRFS_MOUNT_ENOSPC_DEBUG = (1UL << 15),
- BTRFS_MOUNT_AUTO_DEFRAG = (1UL << 16),
- BTRFS_MOUNT_USEBACKUPROOT = (1UL << 17),
- BTRFS_MOUNT_SKIP_BALANCE = (1UL << 18),
- BTRFS_MOUNT_PANIC_ON_FATAL_ERROR = (1UL << 19),
- BTRFS_MOUNT_RESCAN_UUID_TREE = (1UL << 20),
- BTRFS_MOUNT_FRAGMENT_DATA = (1UL << 21),
- BTRFS_MOUNT_FRAGMENT_METADATA = (1UL << 22),
- BTRFS_MOUNT_FREE_SPACE_TREE = (1UL << 23),
- BTRFS_MOUNT_NOLOGREPLAY = (1UL << 24),
- BTRFS_MOUNT_REF_VERIFY = (1UL << 25),
- BTRFS_MOUNT_DISCARD_ASYNC = (1UL << 26),
- BTRFS_MOUNT_IGNOREBADROOTS = (1UL << 27),
- BTRFS_MOUNT_IGNOREDATACSUMS = (1UL << 28),
- BTRFS_MOUNT_NODISCARD = (1UL << 29),
- BTRFS_MOUNT_NOSPACECACHE = (1UL << 30),
+ BTRFS_MOUNT_NODATASUM = (1ULL << 0),
+ BTRFS_MOUNT_NODATACOW = (1ULL << 1),
+ BTRFS_MOUNT_NOBARRIER = (1ULL << 2),
+ BTRFS_MOUNT_SSD = (1ULL << 3),
+ BTRFS_MOUNT_DEGRADED = (1ULL << 4),
+ BTRFS_MOUNT_COMPRESS = (1ULL << 5),
+ BTRFS_MOUNT_NOTREELOG = (1ULL << 6),
+ BTRFS_MOUNT_FLUSHONCOMMIT = (1ULL << 7),
+ BTRFS_MOUNT_SSD_SPREAD = (1ULL << 8),
+ BTRFS_MOUNT_NOSSD = (1ULL << 9),
+ BTRFS_MOUNT_DISCARD_SYNC = (1ULL << 10),
+ BTRFS_MOUNT_FORCE_COMPRESS = (1ULL << 11),
+ BTRFS_MOUNT_SPACE_CACHE = (1ULL << 12),
+ BTRFS_MOUNT_CLEAR_CACHE = (1ULL << 13),
+ BTRFS_MOUNT_USER_SUBVOL_RM_ALLOWED = (1ULL << 14),
+ BTRFS_MOUNT_ENOSPC_DEBUG = (1ULL << 15),
+ BTRFS_MOUNT_AUTO_DEFRAG = (1ULL << 16),
+ BTRFS_MOUNT_USEBACKUPROOT = (1ULL << 17),
+ BTRFS_MOUNT_SKIP_BALANCE = (1ULL << 18),
+ BTRFS_MOUNT_PANIC_ON_FATAL_ERROR = (1ULL << 19),
+ BTRFS_MOUNT_RESCAN_UUID_TREE = (1ULL << 20),
+ BTRFS_MOUNT_FRAGMENT_DATA = (1ULL << 21),
+ BTRFS_MOUNT_FRAGMENT_METADATA = (1ULL << 22),
+ BTRFS_MOUNT_FREE_SPACE_TREE = (1ULL << 23),
+ BTRFS_MOUNT_NOLOGREPLAY = (1ULL << 24),
+ BTRFS_MOUNT_REF_VERIFY = (1ULL << 25),
+ BTRFS_MOUNT_DISCARD_ASYNC = (1ULL << 26),
+ BTRFS_MOUNT_IGNOREBADROOTS = (1ULL << 27),
+ BTRFS_MOUNT_IGNOREDATACSUMS = (1ULL << 28),
+ BTRFS_MOUNT_NODISCARD = (1ULL << 29),
+ BTRFS_MOUNT_NOSPACECACHE = (1ULL << 30),
+ BTRFS_MOUNT_IGNOREMETACSUMS = (1ULL << 31),
+ BTRFS_MOUNT_IGNORESUPERFLAGS = (1ULL << 32),
};
/*
@@ -261,10 +278,10 @@ enum {
BTRFS_FEATURE_INCOMPAT_ZONED | \
BTRFS_FEATURE_INCOMPAT_SIMPLE_QUOTA)
-#ifdef CONFIG_BTRFS_DEBUG
+#ifdef CONFIG_BTRFS_EXPERIMENTAL
/*
* Features under developmen like Extent tree v2 support is enabled
- * only under CONFIG_BTRFS_DEBUG.
+ * only under CONFIG_BTRFS_EXPERIMENTAL
*/
#define BTRFS_FEATURE_INCOMPAT_SUPP \
(BTRFS_FEATURE_INCOMPAT_SUPP_STABLE | \
@@ -283,6 +300,7 @@ enum {
#define BTRFS_FEATURE_INCOMPAT_SAFE_CLEAR 0ULL
#define BTRFS_DEFAULT_COMMIT_INTERVAL (30)
+#define BTRFS_WARNING_COMMIT_INTERVAL (300)
#define BTRFS_DEFAULT_MAX_INLINE (2048)
struct btrfs_dev_replace {
@@ -315,6 +333,8 @@ struct btrfs_dev_replace {
struct percpu_counter bio_counter;
wait_queue_head_t replace_wait;
+
+ struct task_struct *replace_task;
};
/*
@@ -452,6 +472,8 @@ struct btrfs_fs_info {
struct btrfs_block_rsv delayed_block_rsv;
/* Block reservation for delayed refs */
struct btrfs_block_rsv delayed_refs_rsv;
+ /* Block reservation for treelog tree */
+ struct btrfs_block_rsv treelog_rsv;
struct btrfs_block_rsv empty_block_rsv;
@@ -479,10 +501,10 @@ struct btrfs_fs_info {
* required instead of the faster short fsync log commits
*/
u64 last_trans_log_full_commit;
- unsigned long mount_opt;
+ unsigned long long mount_opt;
- unsigned long compress_type:4;
- unsigned int compress_level;
+ int compress_type;
+ int compress_level;
u32 commit_interval;
/*
* It is a suggestive number, the read side is safe even it gets a
@@ -623,6 +645,9 @@ struct btrfs_fs_info {
struct kobject *qgroups_kobj;
struct kobject *discard_kobj;
+ /* Track the number of blocks (sectors) read by the filesystem. */
+ struct percpu_counter stats_read_blocks;
+
/* Used to keep from writing metadata until there is a nice batch */
struct percpu_counter dirty_metadata_bytes;
struct percpu_counter delalloc_bytes;
@@ -630,6 +655,12 @@ struct btrfs_fs_info {
s32 dirty_metadata_batch;
s32 delalloc_batch;
+ struct percpu_counter evictable_extent_maps;
+ u64 em_shrinker_last_root;
+ u64 em_shrinker_last_ino;
+ atomic64_t em_shrinker_nr_to_scan;
+ struct work_struct em_shrinker_work;
+
/* Protected by 'trans_lock'. */
struct list_head dirty_cowonly_roots;
@@ -697,7 +728,6 @@ struct btrfs_fs_info {
*/
refcount_t scrub_workers_refcnt;
struct workqueue_struct *scrub_workers;
- struct btrfs_subpage_info *subpage_info;
struct btrfs_discard_ctl discard_ctl;
@@ -749,10 +779,8 @@ struct btrfs_fs_info {
struct btrfs_delayed_root *delayed_root;
- /* Extent buffer radix tree */
- spinlock_t buffer_lock;
/* Entries are eb->start / sectorsize */
- struct radix_tree_root buffer_radix;
+ struct xarray buffer_tree;
/* Next backup root to be overwritten */
int backup_root_index;
@@ -869,17 +897,19 @@ struct btrfs_fs_info {
#endif
};
-#define page_to_inode(_page) (BTRFS_I(_Generic((_page), \
- struct page *: (_page))->mapping->host))
#define folio_to_inode(_folio) (BTRFS_I(_Generic((_folio), \
struct folio *: (_folio))->mapping->host))
-#define page_to_fs_info(_page) (page_to_inode(_page)->root->fs_info)
#define folio_to_fs_info(_folio) (folio_to_inode(_folio)->root->fs_info)
#define inode_to_fs_info(_inode) (BTRFS_I(_Generic((_inode), \
struct inode *: (_inode)))->root->fs_info)
+static inline gfp_t btrfs_alloc_write_mask(struct address_space *mapping)
+{
+ return mapping_gfp_constraint(mapping, ~__GFP_FS);
+}
+
static inline u64 btrfs_get_fs_generation(const struct btrfs_fs_info *fs_info)
{
return READ_ONCE(fs_info->generation);
@@ -946,6 +976,8 @@ static inline u64 btrfs_calc_metadata_size(const struct btrfs_fs_info *fs_info,
#define BTRFS_MAX_EXTENT_ITEM_SIZE(r) ((BTRFS_LEAF_DATA_SIZE(r->fs_info) >> 4) - \
sizeof(struct btrfs_item))
+#define BTRFS_BYTES_TO_BLKS(fs_info, bytes) ((bytes) >> (fs_info)->sectorsize_bits)
+
static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info)
{
return IS_ENABLED(CONFIG_BLK_DEV_ZONED) && fs_info->zone_size > 0;
@@ -954,7 +986,7 @@ static inline bool btrfs_is_zoned(const struct btrfs_fs_info *fs_info)
/*
* Count how many fs_info->max_extent_size cover the @size
*/
-static inline u32 count_max_extents(struct btrfs_fs_info *fs_info, u64 size)
+static inline u32 count_max_extents(const struct btrfs_fs_info *fs_info, u64 size)
{
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
if (!fs_info)
@@ -964,6 +996,12 @@ static inline u32 count_max_extents(struct btrfs_fs_info *fs_info, u64 size)
return div_u64(size + fs_info->max_extent_size - 1, fs_info->max_extent_size);
}
+static inline unsigned int btrfs_blocks_per_folio(const struct btrfs_fs_info *fs_info,
+ const struct folio *folio)
+{
+ return folio_size(folio) >> fs_info->sectorsize_bits;
+}
+
bool btrfs_exclop_start(struct btrfs_fs_info *fs_info,
enum btrfs_exclusive_operation type);
bool btrfs_exclop_start_try_lock(struct btrfs_fs_info *fs_info,
@@ -975,6 +1013,17 @@ void btrfs_exclop_balance(struct btrfs_fs_info *fs_info,
int btrfs_check_ioctl_vol_args_path(const struct btrfs_ioctl_vol_args *vol_args);
+u16 btrfs_csum_type_size(u16 type);
+int btrfs_super_csum_size(const struct btrfs_super_block *s);
+const char *btrfs_super_csum_name(u16 csum_type);
+const char *btrfs_super_csum_driver(u16 csum_type);
+size_t __attribute_const__ btrfs_get_num_csums(void);
+
+static inline bool btrfs_is_empty_uuid(const u8 *uuid)
+{
+ return uuid_is_null((const uuid_t *)uuid);
+}
+
/* Compatibility and incompatibility defines */
void __btrfs_set_fs_incompat(struct btrfs_fs_info *fs_info, u64 flag,
const char *name);
@@ -1015,7 +1064,7 @@ void __btrfs_clear_fs_compat_ro(struct btrfs_fs_info *fs_info, u64 flag,
#define btrfs_test_opt(fs_info, opt) ((fs_info)->mount_opt & \
BTRFS_MOUNT_##opt)
-static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
+static inline int btrfs_fs_closing(const struct btrfs_fs_info *fs_info)
{
/* Do it this way so we only ever do one test_bit in the normal case. */
if (test_bit(BTRFS_FS_CLOSING_START, &fs_info->flags)) {
@@ -1034,7 +1083,7 @@ static inline int btrfs_fs_closing(struct btrfs_fs_info *fs_info)
* since setting and checking for SB_RDONLY in the superblock's flags is not
* atomic.
*/
-static inline int btrfs_need_cleaner_sleep(struct btrfs_fs_info *fs_info)
+static inline int btrfs_need_cleaner_sleep(const struct btrfs_fs_info *fs_info)
{
return test_bit(BTRFS_FS_STATE_RO, &fs_info->fs_state) ||
btrfs_fs_closing(fs_info);
@@ -1051,11 +1100,19 @@ static inline void btrfs_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
(unlikely(test_bit(BTRFS_FS_STATE_LOG_CLEANUP_ERROR, \
&(fs_info)->fs_state)))
+/*
+ * We use folio flag owner_2 to indicate there is an ordered extent with
+ * unfinished IO.
+ */
+#define folio_test_ordered(folio) folio_test_owner_2(folio)
+#define folio_set_ordered(folio) folio_set_owner_2(folio)
+#define folio_clear_ordered(folio) folio_clear_owner_2(folio)
+
#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
#define EXPORT_FOR_TESTS
-static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
+static inline int btrfs_is_testing(const struct btrfs_fs_info *fs_info)
{
return test_bit(BTRFS_FS_STATE_DUMMY_FS_INFO, &fs_info->fs_state);
}
@@ -1066,7 +1123,7 @@ void btrfs_test_destroy_inode(struct inode *inode);
#define EXPORT_FOR_TESTS static
-static inline int btrfs_is_testing(struct btrfs_fs_info *fs_info)
+static inline int btrfs_is_testing(const struct btrfs_fs_info *fs_info)
{
return 0;
}
generated by cgit (git 2.34.1) at 2025-07-23 07:19:19 +0000