diff options
Diffstat (limited to 'include/linux/jbd2.h')
| -rw-r--r-- | include/linux/jbd2.h | 1121 |
1 files changed, 773 insertions, 348 deletions
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h index d5b50a19463c..f5eaf76198f3 100644 --- a/include/linux/jbd2.h +++ b/include/linux/jbd2.h @@ -1,3 +1,4 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/include/linux/jbd2.h * @@ -5,10 +6,6 @@ * * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved * - * This file is part of the Linux kernel and is made available under - * the terms of the GNU General Public License, version 2, or at your - * option, any later version, incorporated herein by reference. - * * Definitions for transaction data structures for the buffer cache * filesystem journaling support. */ @@ -29,7 +26,9 @@ #include <linux/mutex.h> #include <linux/timer.h> #include <linux/slab.h> -#include <crypto/hash.h> +#include <linux/bit_spinlock.h> +#include <linux/blkdev.h> +#include <linux/crc32c.h> #endif #define journal_oom_retry 1 @@ -55,20 +54,20 @@ * CONFIG_JBD2_DEBUG is on. */ #define JBD2_EXPENSIVE_CHECKING -extern ushort jbd2_journal_enable_debug; void __jbd2_debug(int level, const char *file, const char *func, unsigned int line, const char *fmt, ...); -#define jbd_debug(n, fmt, a...) \ +#define jbd2_debug(n, fmt, a...) \ __jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a) #else -#define jbd_debug(n, fmt, a...) /**/ +#define jbd2_debug(n, fmt, a...) no_printk(fmt, ##a) #endif extern void *jbd2_alloc(size_t size, gfp_t flags); extern void jbd2_free(void *ptr, size_t size); #define JBD2_MIN_JOURNAL_BLOCKS 1024 +#define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256 #ifdef __KERNEL__ @@ -159,7 +158,11 @@ typedef struct journal_header_s * journal_block_tag (in the descriptor). The other h_chksum* fields are * not used. * - * Checksum v1 and v2 are mutually exclusive features. + * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses + * journal_block_tag3_t to store a full 32-bit checksum. Everything else + * is the same as v2. + * + * Checksum v1, v2, and v3 are mutually exclusive features. */ struct commit_header { __be32 h_magic; @@ -179,6 +182,14 @@ struct commit_header { * raw struct shouldn't be used for pointer math or sizeof() - use * journal_tag_bytes(journal) instead to compute this. */ +typedef struct journal_block_tag3_s +{ + __be32 t_blocknr; /* The on-disk block number */ + __be32 t_flags; /* See below */ + __be32 t_blocknr_high; /* most-significant high 32bits. */ + __be32 t_checksum; /* crc32c(uuid+seq+block) */ +} journal_block_tag3_t; + typedef struct journal_block_tag_s { __be32 t_blocknr; /* The on-disk block number */ @@ -187,10 +198,7 @@ typedef struct journal_block_tag_s __be32 t_blocknr_high; /* most-significant high 32bits. */ } journal_block_tag_t; -#define JBD2_TAG_SIZE32 (offsetof(journal_block_tag_t, t_blocknr_high)) -#define JBD2_TAG_SIZE64 (sizeof(journal_block_tag_t)) - -/* Tail of descriptor block, for checksumming */ +/* Tail of descriptor or revoke block, for checksumming */ struct jbd2_journal_block_tail { __be32 t_checksum; /* crc32c(uuid+descr_block) */ }; @@ -205,11 +213,6 @@ typedef struct jbd2_journal_revoke_header_s __be32 r_count; /* Count of bytes used in the block */ } jbd2_journal_revoke_header_t; -/* Tail of revoke block, for checksumming */ -struct jbd2_journal_revoke_tail { - __be32 r_checksum; /* crc32c(uuid+revoke_block) */ -}; - /* Definitions for the journal tag flags word: */ #define JBD2_FLAG_ESCAPE 1 /* on-disk block is escaped */ #define JBD2_FLAG_SAME_UUID 2 /* block has same uuid as previous */ @@ -260,7 +263,12 @@ typedef struct journal_superblock_s /* 0x0050 */ __u8 s_checksum_type; /* checksum type */ __u8 s_padding2[3]; - __u32 s_padding[42]; +/* 0x0054 */ + __be32 s_num_fc_blks; /* Number of fast commit blocks */ + __be32 s_head; /* blocknr of head of log, only uptodate + * while the filesystem is clean */ +/* 0x005C */ + __u32 s_padding[40]; __be32 s_checksum; /* crc32c(superblock) */ /* 0x0100 */ @@ -268,22 +276,16 @@ typedef struct journal_superblock_s /* 0x0400 */ } journal_superblock_t; -#define JBD2_HAS_COMPAT_FEATURE(j,mask) \ - ((j)->j_format_version >= 2 && \ - ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask)))) -#define JBD2_HAS_RO_COMPAT_FEATURE(j,mask) \ - ((j)->j_format_version >= 2 && \ - ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask)))) -#define JBD2_HAS_INCOMPAT_FEATURE(j,mask) \ - ((j)->j_format_version >= 2 && \ - ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask)))) - -#define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 +#define JBD2_FEATURE_COMPAT_CHECKSUM 0x00000001 #define JBD2_FEATURE_INCOMPAT_REVOKE 0x00000001 #define JBD2_FEATURE_INCOMPAT_64BIT 0x00000002 #define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT 0x00000004 #define JBD2_FEATURE_INCOMPAT_CSUM_V2 0x00000008 +#define JBD2_FEATURE_INCOMPAT_CSUM_V3 0x00000010 +#define JBD2_FEATURE_INCOMPAT_FAST_COMMIT 0x00000020 + +/* See "journal feature predicate functions" below */ /* Features known to this kernel version: */ #define JBD2_KNOWN_COMPAT_FEATURES JBD2_FEATURE_COMPAT_CHECKSUM @@ -291,7 +293,9 @@ typedef struct journal_superblock_s #define JBD2_KNOWN_INCOMPAT_FEATURES (JBD2_FEATURE_INCOMPAT_REVOKE | \ JBD2_FEATURE_INCOMPAT_64BIT | \ JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \ - JBD2_FEATURE_INCOMPAT_CSUM_V2) + JBD2_FEATURE_INCOMPAT_CSUM_V2 | \ + JBD2_FEATURE_INCOMPAT_CSUM_V3 | \ + JBD2_FEATURE_INCOMPAT_FAST_COMMIT) #ifdef __KERNEL__ @@ -306,7 +310,6 @@ enum jbd_state_bits { BH_Revoked, /* Has been revoked from the log */ BH_RevokeValid, /* Revoked flag is valid */ BH_JBDDirty, /* Is dirty but journaled */ - BH_State, /* Pins most journal_head state */ BH_JournalHead, /* Pins bh->b_private and jh->b_bh */ BH_Shadow, /* IO on shadow buffer is running */ BH_Verified, /* Metadata block has been verified ok */ @@ -325,7 +328,25 @@ BUFFER_FNS(Freed, freed) BUFFER_FNS(Shadow, shadow) BUFFER_FNS(Verified, verified) -#include <linux/jbd_common.h> +static inline struct buffer_head *jh2bh(struct journal_head *jh) +{ + return jh->b_bh; +} + +static inline struct journal_head *bh2jh(struct buffer_head *bh) +{ + return bh->b_private; +} + +static inline void jbd_lock_bh_journal_head(struct buffer_head *bh) +{ + bit_spin_lock(BH_JournalHead, &bh->b_state); +} + +static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh) +{ + bit_spin_unlock(BH_JournalHead, &bh->b_state); +} #define J_ASSERT(assert) BUG_ON(!(assert)) @@ -355,48 +376,97 @@ BUFFER_FNS(Verified, verified) /* Flags in jbd_inode->i_flags */ #define __JI_COMMIT_RUNNING 0 -/* Commit of the inode data in progress. We use this flag to protect us from +#define __JI_WRITE_DATA 1 +#define __JI_WAIT_DATA 2 + +/* + * Commit of the inode data in progress. We use this flag to protect us from * concurrent deletion of inode. We cannot use reference to inode for this * since we cannot afford doing last iput() on behalf of kjournald */ #define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING) +/* Write allocated dirty buffers in this inode before commit */ +#define JI_WRITE_DATA (1 << __JI_WRITE_DATA) +/* Wait for outstanding data writes for this inode before commit */ +#define JI_WAIT_DATA (1 << __JI_WAIT_DATA) /** - * struct jbd_inode is the structure linking inodes in ordered mode - * present in a transaction so that we can sync them during commit. + * struct jbd2_inode - The jbd_inode type is the structure linking inodes in + * ordered mode present in a transaction so that we can sync them during commit. */ struct jbd2_inode { - /* Which transaction does this inode belong to? Either the running - * transaction or the committing one. [j_list_lock] */ + /** + * @i_transaction: + * + * Which transaction does this inode belong to? Either the running + * transaction or the committing one. [j_list_lock] + */ transaction_t *i_transaction; - /* Pointer to the running transaction modifying inode's data in case - * there is already a committing transaction touching it. [j_list_lock] */ + /** + * @i_next_transaction: + * + * Pointer to the running transaction modifying inode's data in case + * there is already a committing transaction touching it. [j_list_lock] + */ transaction_t *i_next_transaction; - /* List of inodes in the i_transaction [j_list_lock] */ + /** + * @i_list: List of inodes in the i_transaction [j_list_lock] + */ struct list_head i_list; - /* VFS inode this inode belongs to [constant during the lifetime - * of the structure] */ + /** + * @i_vfs_inode: + * + * VFS inode this inode belongs to [constant for lifetime of structure] + */ struct inode *i_vfs_inode; - /* Flags of inode [j_list_lock] */ + /** + * @i_flags: Flags of inode [j_list_lock] + */ unsigned long i_flags; + + /** + * @i_dirty_start: + * + * Offset in bytes where the dirty range for this inode starts. + * [j_list_lock] + */ + loff_t i_dirty_start; + + /** + * @i_dirty_end: + * + * Inclusive offset in bytes where the dirty range for this inode + * ends. [j_list_lock] + */ + loff_t i_dirty_end; }; struct jbd2_revoke_table_s; /** - * struct handle_s - The handle_s type is the concrete type associated with - * handle_t. + * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete + * type associated with handle_t. * @h_transaction: Which compound transaction is this update a part of? - * @h_buffer_credits: Number of remaining buffers we are allowed to dirty. - * @h_ref: Reference count on this handle - * @h_err: Field for caller's use to track errors through large fs operations - * @h_sync: flag for sync-on-close - * @h_jdata: flag to force data journaling - * @h_aborted: flag indicating fatal error on handle + * @h_journal: Which journal handle belongs to - used iff h_reserved set. + * @h_rsv_handle: Handle reserved for finishing the logical operation. + * @h_total_credits: Number of remaining buffers we are allowed to add to + * journal. These are dirty buffers and revoke descriptor blocks. + * @h_revoke_credits: Number of remaining revoke records available for handle + * @h_ref: Reference count on this handle. + * @h_err: Field for caller's use to track errors through large fs operations. + * @h_sync: Flag for sync-on-close. + * @h_reserved: Flag for handle for reserved credits. + * @h_aborted: Flag indicating fatal error on handle. + * @h_type: For handle statistics. + * @h_line_no: For handle statistics. + * @h_start_jiffies: Handle Start time. + * @h_requested_credits: Holds @h_total_credits after handle is started. + * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started. + * @saved_alloc_context: Saved context while transaction is open. **/ /* Docbook can't yet cope with the bit fields, but will leave the documentation @@ -406,39 +476,29 @@ struct jbd2_revoke_table_s; struct jbd2_journal_handle { union { - /* Which compound transaction is this update a part of? */ transaction_t *h_transaction; /* Which journal handle belongs to - used iff h_reserved set */ journal_t *h_journal; }; - /* Handle reserved for finishing the logical operation */ handle_t *h_rsv_handle; - - /* Number of remaining buffers we are allowed to dirty: */ - int h_buffer_credits; - - /* Reference count on this handle */ + int h_total_credits; + int h_revoke_credits; + int h_revoke_credits_requested; int h_ref; - - /* Field for caller's use to track errors through large fs */ - /* operations */ int h_err; /* Flags [no locking] */ - unsigned int h_sync: 1; /* sync-on-close */ - unsigned int h_jdata: 1; /* force data journaling */ - unsigned int h_reserved: 1; /* handle with reserved credits */ - unsigned int h_aborted: 1; /* fatal error on handle */ - unsigned int h_type: 8; /* for handle statistics */ - unsigned int h_line_no: 16; /* for handle statistics */ + unsigned int h_sync: 1; + unsigned int h_reserved: 1; + unsigned int h_aborted: 1; + unsigned int h_type: 8; + unsigned int h_line_no: 16; unsigned long h_start_jiffies; unsigned int h_requested_credits; -#ifdef CONFIG_DEBUG_LOCK_ALLOC - struct lockdep_map h_lockdep_map; -#endif + unsigned int saved_alloc_context; }; @@ -466,6 +526,7 @@ struct transaction_chp_stats_s { * The transaction keeps track of all of the buffers modified by a * running transaction, and all of the buffers committed but not yet * flushed to home for finished transactions. + * (Locking Documentation improved by LockDoc) */ /* @@ -475,15 +536,12 @@ struct transaction_chp_stats_s { * ->jbd_lock_bh_journal_head() (This is "innermost") * * j_state_lock - * ->jbd_lock_bh_state() + * ->b_state_lock * - * jbd_lock_bh_state() + * b_state_lock * ->j_list_lock * * j_state_lock - * ->t_handle_lock - * - * j_state_lock * ->j_list_lock (journal_unmap_buffer) * */ @@ -507,6 +565,7 @@ struct transaction_s enum { T_RUNNING, T_LOCKED, + T_SWITCH, T_FLUSH, T_COMMIT, T_COMMIT_DFLUSH, @@ -520,18 +579,22 @@ struct transaction_s */ unsigned long t_log_start; - /* Number of buffers on the t_buffers list [j_list_lock] */ + /* + * Number of buffers on the t_buffers list [j_list_lock, no locks + * needed for jbd2 thread] + */ int t_nr_buffers; /* * Doubly-linked circular list of all buffers reserved but not yet - * modified by this transaction [j_list_lock] + * modified by this transaction [j_list_lock, no locks needed fo + * jbd2 thread] */ struct journal_head *t_reserved_list; /* * Doubly-linked circular list of all metadata buffers owned by this - * transaction [j_list_lock] + * transaction [j_list_lock, no locks needed for jbd2 thread] */ struct journal_head *t_buffers; @@ -549,30 +612,23 @@ struct transaction_s struct journal_head *t_checkpoint_list; /* - * Doubly-linked circular list of all buffers submitted for IO while - * checkpointing. [j_list_lock] - */ - struct journal_head *t_checkpoint_io_list; - - /* - * Doubly-linked circular list of metadata buffers being shadowed by log - * IO. The IO buffers on the iobuf list and the shadow buffers on this - * list match each other one for one at all times. [j_list_lock] + * Doubly-linked circular list of metadata buffers being + * shadowed by log IO. The IO buffers on the iobuf list and + * the shadow buffers on this list match each other one for + * one at all times. [j_list_lock, no locks needed for jbd2 + * thread] */ struct journal_head *t_shadow_list; /* - * List of inodes whose data we've modified in data=ordered mode. + * List of inodes associated with the transaction; e.g., ext4 uses + * this to track inodes in data=ordered and data=journal mode that + * need special handling on transaction commit; also used by ocfs2. * [j_list_lock] */ struct list_head t_inode_list; /* - * Protects info related to handles - */ - spinlock_t t_handle_lock; - - /* * Longest time some handle had to wait for running transaction */ unsigned long t_max_wait; @@ -583,28 +639,41 @@ struct transaction_s unsigned long t_start; /* - * When commit was requested + * When commit was requested [j_state_lock] */ unsigned long t_requested; /* - * Checkpointing stats [j_checkpoint_sem] + * Checkpointing stats [j_list_lock] */ struct transaction_chp_stats_s t_chp_stats; /* * Number of outstanding updates running on this transaction - * [t_handle_lock] + * [none] */ atomic_t t_updates; /* - * Number of buffers reserved for use by all handles in this transaction - * handle but not yet modified. [t_handle_lock] + * Number of blocks reserved for this transaction in the journal. + * This is including all credits reserved when starting transaction + * handles as well as all journal descriptor blocks needed for this + * transaction. [none] */ atomic_t t_outstanding_credits; /* + * Number of revoke records for this transaction added by already + * stopped handles. [none] + */ + atomic_t t_outstanding_revokes; + + /* + * How many handles used this transaction? [none] + */ + atomic_t t_handle_count; + + /* * Forward and backward links for the circular list of all transactions * awaiting checkpoint. [j_list_lock] */ @@ -622,11 +691,6 @@ struct transaction_s ktime_t t_start_time; /* - * How many handles used this transaction? [t_handle_lock] - */ - atomic_t t_handle_count; - - /* * This transaction is being forced and some process is * waiting for it to finish. */ @@ -634,12 +698,6 @@ struct transaction_s /* Disk flush needs to be sent to fs partition [no locking] */ int t_need_data_flush; - - /* - * For use by the filesystem to store fs-specific data - * structures associated with the transaction - */ - struct list_head t_private_list; }; struct transaction_run_stats_s { @@ -672,233 +730,326 @@ jbd2_time_diff(unsigned long start, unsigned long end) #define JBD2_NR_BATCH 64 +enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY}; + +#define JBD2_FC_REPLAY_STOP 0 +#define JBD2_FC_REPLAY_CONTINUE 1 + /** * struct journal_s - The journal_s type is the concrete type associated with * journal_t. - * @j_flags: General journaling state flags - * @j_errno: Is there an outstanding uncleared error on the journal (from a - * prior abort)? - * @j_sb_buffer: First part of superblock buffer - * @j_superblock: Second part of superblock buffer - * @j_format_version: Version of the superblock format - * @j_state_lock: Protect the various scalars in the journal - * @j_barrier_count: Number of processes waiting to create a barrier lock - * @j_barrier: The barrier lock itself - * @j_running_transaction: The current running transaction.. - * @j_committing_transaction: the transaction we are pushing to disk - * @j_checkpoint_transactions: a linked circular list of all transactions - * waiting for checkpointing - * @j_wait_transaction_locked: Wait queue for waiting for a locked transaction - * to start committing, or for a barrier lock to be released - * @j_wait_done_commit: Wait queue for waiting for commit to complete - * @j_wait_commit: Wait queue to trigger commit - * @j_wait_updates: Wait queue to wait for updates to complete - * @j_wait_reserved: Wait queue to wait for reserved buffer credits to drop - * @j_checkpoint_mutex: Mutex for locking against concurrent checkpoints - * @j_head: Journal head - identifies the first unused block in the journal - * @j_tail: Journal tail - identifies the oldest still-used block in the - * journal. - * @j_free: Journal free - how many free blocks are there in the journal? - * @j_first: The block number of the first usable block - * @j_last: The block number one beyond the last usable block - * @j_dev: Device where we store the journal - * @j_blocksize: blocksize for the location where we store the journal. - * @j_blk_offset: starting block offset for into the device where we store the - * journal - * @j_fs_dev: Device which holds the client fs. For internal journal this will - * be equal to j_dev - * @j_reserved_credits: Number of buffers reserved from the running transaction - * @j_maxlen: Total maximum capacity of the journal region on disk. - * @j_list_lock: Protects the buffer lists and internal buffer state. - * @j_inode: Optional inode where we store the journal. If present, all journal - * block numbers are mapped into this inode via bmap(). - * @j_tail_sequence: Sequence number of the oldest transaction in the log - * @j_transaction_sequence: Sequence number of the next transaction to grant - * @j_commit_sequence: Sequence number of the most recently committed - * transaction - * @j_commit_request: Sequence number of the most recent transaction wanting - * commit - * @j_uuid: Uuid of client object. - * @j_task: Pointer to the current commit thread for this journal - * @j_max_transaction_buffers: Maximum number of metadata buffers to allow in a - * single compound commit transaction - * @j_commit_interval: What is the maximum transaction lifetime before we begin - * a commit? - * @j_commit_timer: The timer used to wakeup the commit thread - * @j_revoke_lock: Protect the revoke table - * @j_revoke: The revoke table - maintains the list of revoked blocks in the - * current transaction. - * @j_revoke_table: alternate revoke tables for j_revoke - * @j_wbuf: array of buffer_heads for jbd2_journal_commit_transaction - * @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the - * number that will fit in j_blocksize - * @j_last_sync_writer: most recent pid which did a synchronous write - * @j_history: Buffer storing the transactions statistics history - * @j_history_max: Maximum number of transactions in the statistics history - * @j_history_cur: Current number of transactions in the statistics history - * @j_history_lock: Protect the transactions statistics history - * @j_proc_entry: procfs entry for the jbd statistics directory - * @j_stats: Overall statistics - * @j_private: An opaque pointer to fs-private information. */ - struct journal_s { - /* General journaling state flags [j_state_lock] */ + /** + * @j_flags: General journaling state flags [j_state_lock, + * no lock for quick racy checks] + */ unsigned long j_flags; - /* + /** + * @j_errno: + * * Is there an outstanding uncleared error on the journal (from a prior * abort)? [j_state_lock] */ int j_errno; - /* The superblock buffer */ + /** + * @j_abort_mutex: Lock the whole aborting procedure. + */ + struct mutex j_abort_mutex; + + /** + * @j_sb_buffer: The first part of the superblock buffer. + */ struct buffer_head *j_sb_buffer; - journal_superblock_t *j_superblock; - /* Version of the superblock format */ - int j_format_version; + /** + * @j_superblock: The second part of the superblock buffer. + */ + journal_superblock_t *j_superblock; - /* - * Protect the various scalars in the journal + /** + * @j_state_lock: Protect the various scalars in the journal. */ rwlock_t j_state_lock; - /* - * Number of processes waiting to create a barrier lock [j_state_lock] + /** + * @j_barrier_count: + * + * Number of processes waiting to create a barrier lock [j_state_lock, + * no lock for quick racy checks] */ int j_barrier_count; - /* The barrier lock itself */ + /** + * @j_barrier: The barrier lock itself. + */ struct mutex j_barrier; - /* + /** + * @j_running_transaction: + * * Transactions: The current running transaction... - * [j_state_lock] [caller holding open handle] + * [j_state_lock, no lock for quick racy checks] [caller holding + * open handle] */ transaction_t *j_running_transaction; - /* + /** + * @j_committing_transaction: + * * the transaction we are pushing to disk * [j_state_lock] [caller holding open handle] */ transaction_t *j_committing_transaction; - /* + /** + * @j_checkpoint_transactions: + * * ... and a linked circular list of all transactions waiting for * checkpointing. [j_list_lock] */ transaction_t *j_checkpoint_transactions; - /* + /** + * @j_wait_transaction_locked: + * * Wait queue for waiting for a locked transaction to start committing, - * or for a barrier lock to be released + * or for a barrier lock to be released. */ wait_queue_head_t j_wait_transaction_locked; - /* Wait queue for waiting for commit to complete */ + /** + * @j_wait_done_commit: Wait queue for waiting for commit to complete. + */ wait_queue_head_t j_wait_done_commit; - /* Wait queue to trigger commit */ + /** + * @j_wait_commit: Wait queue to trigger commit. + */ wait_queue_head_t j_wait_commit; - /* Wait queue to wait for updates to complete */ + /** + * @j_wait_updates: Wait queue to wait for updates to complete. + */ wait_queue_head_t j_wait_updates; - /* Wait queue to wait for reserved buffer credits to drop */ + /** + * @j_wait_reserved: + * + * Wait queue to wait for reserved buffer credits to drop. + */ wait_queue_head_t j_wait_reserved; - /* Semaphore for locking against concurrent checkpoints */ + /** + * @j_fc_wait: + * + * Wait queue to wait for completion of async fast commits. + */ + wait_queue_head_t j_fc_wait; + + /** + * @j_checkpoint_mutex: + * + * Semaphore for locking against concurrent checkpoints. + */ struct mutex j_checkpoint_mutex; - /* + /** + * @j_chkpt_bhs: + * * List of buffer heads used by the checkpoint routine. This * was moved from jbd2_log_do_checkpoint() to reduce stack * usage. Access to this array is controlled by the - * j_checkpoint_mutex. [j_checkpoint_mutex] + * @j_checkpoint_mutex. [j_checkpoint_mutex] */ struct buffer_head *j_chkpt_bhs[JBD2_NR_BATCH]; - - /* + + /** + * @j_shrinker: + * + * Journal head shrinker, reclaim buffer's journal head which + * has been written back. + */ + struct shrinker *j_shrinker; + + /** + * @j_checkpoint_jh_count: + * + * Number of journal buffers on the checkpoint list. [j_list_lock] + */ + struct percpu_counter j_checkpoint_jh_count; + + /** + * @j_shrink_transaction: + * + * Record next transaction will shrink on the checkpoint list. + * [j_list_lock] + */ + transaction_t *j_shrink_transaction; + + /** + * @j_head: + * * Journal head: identifies the first unused block in the journal. * [j_state_lock] */ unsigned long j_head; - /* + /** + * @j_tail: + * * Journal tail: identifies the oldest still-used block in the journal. * [j_state_lock] */ unsigned long j_tail; - /* + /** + * @j_free: + * * Journal free: how many free blocks are there in the journal? * [j_state_lock] */ unsigned long j_free; - /* - * Journal start and end: the block numbers of the first usable block - * and one beyond the last usable block in the journal. [j_state_lock] + /** + * @j_first: + * + * The block number of the first usable block in the journal + * [j_state_lock]. */ unsigned long j_first; + + /** + * @j_last: + * + * The block number one beyond the last usable block in the journal + * [j_state_lock]. + */ unsigned long j_last; - /* - * Device, blocksize and starting block offset for the location where we - * store the journal. + /** + * @j_fc_first: + * + * The block number of the first fast commit block in the journal + * [j_state_lock]. + */ + unsigned long j_fc_first; + + /** + * @j_fc_off: + * + * Number of fast commit blocks currently allocated. Accessed only + * during fast commit. Currently only process can do fast commit, so + * this field is not protected by any lock. + */ + unsigned long j_fc_off; + + /** + * @j_fc_last: + * + * The block number one beyond the last fast commit block in the journal + * [j_state_lock]. + */ + unsigned long j_fc_last; + + /** + * @j_dev: Device where we store the journal. */ struct block_device *j_dev; + + /** + * @j_blocksize: Block size for the location where we store the journal. + */ int j_blocksize; + + /** + * @j_blk_offset: + * + * Starting block offset into the device where we store the journal. + */ unsigned long long j_blk_offset; + + /** + * @j_devname: Journal device name. + */ char j_devname[BDEVNAME_SIZE+24]; - /* + /** + * @j_fs_dev: + * * Device which holds the client fs. For internal journal this will be * equal to j_dev. */ struct block_device *j_fs_dev; - /* Total maximum capacity of the journal region on disk. */ - unsigned int j_maxlen; + /** + * @j_fs_dev_wb_err: + * + * Records the errseq of the client fs's backing block device. + */ + errseq_t j_fs_dev_wb_err; + + /** + * @j_total_len: Total maximum capacity of the journal region on disk. + */ + unsigned int j_total_len; - /* Number of buffers reserved from the running transaction */ + /** + * @j_reserved_credits: + * + * Number of buffers reserved from the running transaction. + */ atomic_t j_reserved_credits; - /* - * Protects the buffer lists and internal buffer state. + /** + * @j_list_lock: Protects the buffer lists and internal buffer state. */ spinlock_t j_list_lock; - /* Optional inode where we store the journal. If present, all */ - /* journal block numbers are mapped into this inode via */ - /* bmap(). */ + /** + * @j_inode: + * + * Optional inode where we store the journal. If present, all + * journal block numbers are mapped into this inode via bmap(). + */ struct inode *j_inode; - /* + /** + * @j_tail_sequence: + * * Sequence number of the oldest transaction in the log [j_state_lock] */ tid_t j_tail_sequence; - /* + /** + * @j_transaction_sequence: + * * Sequence number of the next transaction to grant [j_state_lock] */ tid_t j_transaction_sequence; - /* + /** + * @j_commit_sequence: + * * Sequence number of the most recently committed transaction - * [j_state_lock]. + * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_sequence; - /* + /** + * @j_commit_request: + * * Sequence number of the most recent transaction wanting commit - * [j_state_lock] + * [j_state_lock, no lock for quick racy checks] */ tid_t j_commit_request; - /* + /** + * @j_uuid: + * * Journal uuid: identifies the object (filesystem, LVM volume etc) * backed by this journal. This will eventually be replaced by an array * of uuids, allowing us to index multiple devices within a single @@ -906,84 +1057,326 @@ struct journal_s */ __u8 j_uuid[16]; - /* Pointer to the current commit thread for this journal */ + /** + * @j_task: Pointer to the current commit thread for this journal. + */ struct task_struct *j_task; - /* + /** + * @j_max_transaction_buffers: + * * Maximum number of metadata buffers to allow in a single compound - * commit transaction + * commit transaction. */ int j_max_transaction_buffers; - /* + /** + * @j_revoke_records_per_block: + * + * Number of revoke records that fit in one descriptor block. + */ + int j_revoke_records_per_block; + + /** + * @j_transaction_overhead_buffers: + * + * Number of blocks each transaction needs for its own bookkeeping + */ + int j_transaction_overhead_buffers; + + /** + * @j_commit_interval: + * * What is the maximum transaction lifetime before we begin a commit? */ unsigned long j_commit_interval; - /* The timer used to wakeup the commit thread: */ + /** + * @j_commit_timer: The timer used to wakeup the commit thread. + */ struct timer_list j_commit_timer; - /* - * The revoke table: maintains the list of revoked blocks in the - * current transaction. [j_revoke_lock] + /** + * @j_revoke_lock: Protect the revoke table. */ spinlock_t j_revoke_lock; + + /** + * @j_revoke: + * + * The revoke table - maintains the list of revoked blocks in the + * current transaction. + */ struct jbd2_revoke_table_s *j_revoke; + + /** + * @j_revoke_table: Alternate revoke tables for j_revoke. + */ struct jbd2_revoke_table_s *j_revoke_table[2]; - /* - * array of bhs for jbd2_journal_commit_transaction + /** + * @j_wbuf: Array of bhs for jbd2_journal_commit_transaction. */ struct buffer_head **j_wbuf; + + /** + * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only + * during a fast commit. Currently only process can do fast commit, so + * this field is not protected by any lock. + */ + struct buffer_head **j_fc_wbuf; + + /** + * @j_wbufsize: + * + * Size of @j_wbuf array. + */ int j_wbufsize; - /* - * this is the pid of hte last person to run a synchronous operation - * through the journal + /** + * @j_fc_wbufsize: + * + * Size of @j_fc_wbuf array. + */ + int j_fc_wbufsize; + + /** + * @j_last_sync_writer: + * + * The pid of the last person to run a synchronous operation + * through the journal. */ pid_t j_last_sync_writer; - /* - * the average amount of time in nanoseconds it takes to commit a + /** + * @j_average_commit_time: + * + * The average amount of time in nanoseconds it takes to commit a * transaction to disk. [j_state_lock] */ u64 j_average_commit_time; - /* - * minimum and maximum times that we should wait for - * additional filesystem operations to get batched into a - * synchronous handle in microseconds + /** + * @j_min_batch_time: + * + * Minimum time that we should wait for additional filesystem operations + * to get batched into a synchronous handle in microseconds. */ u32 j_min_batch_time; + + /** + * @j_max_batch_time: + * + * Maximum time that we should wait for additional filesystem operations + * to get batched into a synchronous handle in microseconds. + */ u32 j_max_batch_time; - /* This function is called when a transaction is closed */ + /** + * @j_commit_callback: + * + * This function is called when a transaction is closed. + */ void (*j_commit_callback)(journal_t *, transaction_t *); + /** + * @j_submit_inode_data_buffers: + * + * This function is called for all inodes associated with the + * committing transaction marked with JI_WRITE_DATA flag + * before we start to write out the transaction to the journal. + */ + int (*j_submit_inode_data_buffers) + (struct jbd2_inode *); + + /** + * @j_finish_inode_data_buffers: + * + * This function is called for all inodes associated with the + * committing transaction marked with JI_WAIT_DATA flag + * after we have written the transaction to the journal + * but before we write out the commit block. + */ + int (*j_finish_inode_data_buffers) + (struct jbd2_inode *); + /* * Journal statistics */ + + /** + * @j_history_lock: Protect the transactions statistics history. + */ spinlock_t j_history_lock; + + /** + * @j_proc_entry: procfs entry for the jbd statistics directory. + */ struct proc_dir_entry *j_proc_entry; + + /** + * @j_stats: Overall statistics. + */ struct transaction_stats_s j_stats; - /* Failed journal commit ID */ + /** + * @j_failed_commit: Failed journal commit ID. + */ unsigned int j_failed_commit; - /* + /** + * @j_private: + * * An opaque pointer to fs-private information. ext3 puts its - * superblock pointer here + * superblock pointer here. */ void *j_private; - /* Reference to checksum algorithm driver via cryptoapi */ - struct crypto_shash *j_chksum_driver; - - /* Precomputed journal UUID checksum for seeding other checksums */ + /** + * @j_csum_seed: + * + * Precomputed journal UUID checksum for seeding other checksums. + */ __u32 j_csum_seed; + +#ifdef CONFIG_DEBUG_LOCK_ALLOC + /** + * @j_trans_commit_map: + * + * Lockdep entity to track transaction commit dependencies. Handles + * hold this "lock" for read, when we wait for commit, we acquire the + * "lock" for writing. This matches the properties of jbd2 journalling + * where the running transaction has to wait for all handles to be + * dropped to commit that transaction and also acquiring a handle may + * require transaction commit to finish. + */ + struct lockdep_map j_trans_commit_map; +#endif + /** + * @jbd2_trans_commit_key: + * + * "struct lock_class_key" for @j_trans_commit_map + */ + struct lock_class_key jbd2_trans_commit_key; + + /** + * @j_fc_cleanup_callback: + * + * Clean-up after fast commit or full commit. JBD2 calls this function + * after every commit operation. + */ + void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid); + + /** + * @j_fc_replay_callback: + * + * File-system specific function that performs replay of a fast + * commit. JBD2 calls this function for each fast commit block found in + * the journal. This function should return JBD2_FC_REPLAY_CONTINUE + * to indicate that the block was processed correctly and more fast + * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP + * indicates the end of replay (no more blocks remaining). A negative + * return value indicates error. + */ + int (*j_fc_replay_callback)(struct journal_s *journal, + struct buffer_head *bh, + enum passtype pass, int off, + tid_t expected_commit_id); + + /** + * @j_bmap: + * + * Bmap function that should be used instead of the generic + * VFS bmap function. + */ + int (*j_bmap)(struct journal_s *journal, sector_t *block); }; +#define jbd2_might_wait_for_commit(j) \ + do { \ + rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \ + rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \ + } while (0) + +/* + * We can support any known requested features iff the + * superblock is not in version 1. Otherwise we fail to support any + * extended sb features. + */ +static inline bool jbd2_format_support_feature(journal_t *j) +{ + return j->j_superblock->s_header.h_blocktype != + cpu_to_be32(JBD2_SUPERBLOCK_V1); +} + +/* journal feature predicate functions */ +#define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \ +static inline bool jbd2_has_feature_##name(journal_t *j) \ +{ \ + return (jbd2_format_support_feature(j) && \ + ((j)->j_superblock->s_feature_compat & \ + cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \ +} \ +static inline void jbd2_set_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_compat |= \ + cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ +} \ +static inline void jbd2_clear_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_compat &= \ + ~cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \ +} + +#define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \ +static inline bool jbd2_has_feature_##name(journal_t *j) \ +{ \ + return (jbd2_format_support_feature(j) && \ + ((j)->j_superblock->s_feature_ro_compat & \ + cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \ +} \ +static inline void jbd2_set_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_ro_compat |= \ + cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ +} \ +static inline void jbd2_clear_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_ro_compat &= \ + ~cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \ +} + +#define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \ +static inline bool jbd2_has_feature_##name(journal_t *j) \ +{ \ + return (jbd2_format_support_feature(j) && \ + ((j)->j_superblock->s_feature_incompat & \ + cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \ +} \ +static inline void jbd2_set_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_incompat |= \ + cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ +} \ +static inline void jbd2_clear_feature_##name(journal_t *j) \ +{ \ + (j)->j_superblock->s_feature_incompat &= \ + ~cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \ +} + +JBD2_FEATURE_COMPAT_FUNCS(checksum, CHECKSUM) + +JBD2_FEATURE_INCOMPAT_FUNCS(revoke, REVOKE) +JBD2_FEATURE_INCOMPAT_FUNCS(64bit, 64BIT) +JBD2_FEATURE_INCOMPAT_FUNCS(async_commit, ASYNC_COMMIT) +JBD2_FEATURE_INCOMPAT_FUNCS(csum2, CSUM_V2) +JBD2_FEATURE_INCOMPAT_FUNCS(csum3, CSUM_V3) +JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit, FAST_COMMIT) + +/* Journal high priority write IO operation flags */ +#define JBD2_JOURNAL_REQ_FLAGS (REQ_META | REQ_SYNC | REQ_IDLE) + /* * Journal flag definitions */ @@ -993,9 +1386,15 @@ struct journal_s #define JBD2_FLUSHED 0x008 /* The journal superblock has been flushed */ #define JBD2_LOADED 0x010 /* The journal superblock has been loaded */ #define JBD2_BARRIER 0x020 /* Use IDE barriers */ -#define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file - * data write error in ordered - * mode */ +#define JBD2_CYCLE_RECORD 0x080 /* Journal cycled record log on + * clean and empty filesystem + * logging area */ +#define JBD2_FAST_COMMIT_ONGOING 0x100 /* Fast commit is ongoing */ +#define JBD2_FULL_COMMIT_ONGOING 0x200 /* Full commit is ongoing */ +#define JBD2_JOURNAL_FLUSH_DISCARD 0x0001 +#define JBD2_JOURNAL_FLUSH_ZEROOUT 0x0002 +#define JBD2_JOURNAL_FLUSH_VALID (JBD2_JOURNAL_FLUSH_DISCARD | \ + JBD2_JOURNAL_FLUSH_ZEROOUT) /* * Function declarations for the journaling transaction and buffer @@ -1003,13 +1402,10 @@ struct journal_s */ /* Filing buffers */ -extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *); -extern void __jbd2_journal_refile_buffer(struct journal_head *); +extern bool __jbd2_journal_refile_buffer(struct journal_head *); extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *); extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_free_buffer(struct journal_head *bh); extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int); -extern void __journal_clean_data_list(transaction_t *transaction); static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh) { list_add_tail(&bh->b_assoc_buffers, head); @@ -1020,19 +1416,25 @@ static inline void jbd2_unfile_log_bh(struct buffer_head *bh) } /* Log buffer allocation */ -struct buffer_head *jbd2_journal_get_descriptor_buffer(journal_t *journal); +struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int); +void jbd2_descriptor_block_csum_set(journal_t *, struct buffer_head *); int jbd2_journal_next_log_block(journal_t *, unsigned long long *); int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid, unsigned long *block); -void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); +int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block); /* Commit management */ extern void jbd2_journal_commit_transaction(journal_t *); /* Checkpoint list management */ -int __jbd2_journal_clean_checkpoint_list(journal_t *journal); +enum jbd2_shrink_type {JBD2_SHRINK_DESTROY, JBD2_SHRINK_BUSY_STOP, JBD2_SHRINK_BUSY_SKIP}; + +void __jbd2_journal_clean_checkpoint_list(journal_t *journal, enum jbd2_shrink_type type); +unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan); int __jbd2_journal_remove_checkpoint(struct journal_head *); +int jbd2_journal_try_remove_checkpoint(struct journal_head *jh); +void jbd2_journal_destroy_checkpoint(journal_t *journal); void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *); @@ -1071,12 +1473,9 @@ extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction, struct buffer_head **bh_out, sector_t blocknr); -/* Transaction locking */ -extern void __wait_on_journal (journal_t *); - /* Transaction cache support */ extern void jbd2_journal_destroy_transaction_cache(void); -extern int jbd2_journal_init_transaction_cache(void); +extern int __init jbd2_journal_init_transaction_cache(void); extern void jbd2_journal_free_transaction(transaction_t *); /* @@ -1103,14 +1502,16 @@ static inline handle_t *journal_current_handle(void) extern handle_t *jbd2_journal_start(journal_t *, int nblocks); extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks, - gfp_t gfp_mask, unsigned int type, - unsigned int line_no); + int revoke_records, gfp_t gfp_mask, + unsigned int type, unsigned int line_no); extern int jbd2_journal_restart(handle_t *, int nblocks); -extern int jbd2__journal_restart(handle_t *, int nblocks, gfp_t gfp_mask); +extern int jbd2__journal_restart(handle_t *, int nblocks, + int revoke_records, gfp_t gfp_mask); extern int jbd2_journal_start_reserved(handle_t *handle, unsigned int type, unsigned int line_no); extern void jbd2_journal_free_reserved(handle_t *handle); -extern int jbd2_journal_extend (handle_t *, int nblocks); +extern int jbd2_journal_extend(handle_t *handle, int nblocks, + int revoke_records); extern int jbd2_journal_get_write_access(handle_t *, struct buffer_head *); extern int jbd2_journal_get_create_access (handle_t *, struct buffer_head *); extern int jbd2_journal_get_undo_access(handle_t *, struct buffer_head *); @@ -1118,15 +1519,16 @@ void jbd2_journal_set_triggers(struct buffer_head *, struct jbd2_buffer_trigger_type *type); extern int jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *); extern int jbd2_journal_forget (handle_t *, struct buffer_head *); -extern void journal_sync_buffer (struct buffer_head *); -extern int jbd2_journal_invalidatepage(journal_t *, - struct page *, unsigned int, unsigned int); -extern int jbd2_journal_try_to_free_buffers(journal_t *, struct page *, gfp_t); +int jbd2_journal_invalidate_folio(journal_t *, struct folio *, + size_t offset, size_t length); +bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio); extern int jbd2_journal_stop(handle_t *); -extern int jbd2_journal_flush (journal_t *); +extern int jbd2_journal_flush(journal_t *journal, unsigned int flags); extern void jbd2_journal_lock_updates (journal_t *); extern void jbd2_journal_unlock_updates (journal_t *); +void jbd2_journal_wait_updates(journal_t *); + extern journal_t * jbd2_journal_init_dev(struct block_device *bdev, struct block_device *fs_dev, unsigned long long start, int len, int bsize); @@ -1146,9 +1548,8 @@ extern int jbd2_journal_recover (journal_t *journal); extern int jbd2_journal_wipe (journal_t *, int); extern int jbd2_journal_skip_recovery (journal_t *); extern void jbd2_journal_update_sb_errno(journal_t *); -extern void jbd2_journal_update_sb_log_tail (journal_t *, tid_t, - unsigned long, int); -extern void __jbd2_journal_abort_hard (journal_t *); +extern int jbd2_journal_update_sb_log_tail (journal_t *, tid_t, + unsigned long, blk_opf_t); extern void jbd2_journal_abort (journal_t *, int); extern int jbd2_journal_errno (journal_t *); extern void jbd2_journal_ack_err (journal_t *); @@ -1156,7 +1557,14 @@ extern int jbd2_journal_clear_err (journal_t *); extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *); extern int jbd2_journal_force_commit(journal_t *); extern int jbd2_journal_force_commit_nested(journal_t *); -extern int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode); +extern int jbd2_journal_inode_ranged_write(handle_t *handle, + struct jbd2_inode *inode, loff_t start_byte, + loff_t length); +extern int jbd2_journal_inode_ranged_wait(handle_t *handle, + struct jbd2_inode *inode, loff_t start_byte, + loff_t length); +extern int jbd2_journal_finish_inode_data_buffers( + struct jbd2_inode *jinode); extern int jbd2_journal_begin_ordered_truncate(journal_t *journal, struct jbd2_inode *inode, loff_t new_size); extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode); @@ -1174,10 +1582,13 @@ void jbd2_journal_put_journal_head(struct journal_head *jh); */ extern struct kmem_cache *jbd2_handle_cache; -static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags) -{ - return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ +#define jbd2_alloc_handle(_gfp_flags) \ + ((handle_t *)kmem_cache_zalloc(jbd2_handle_cache, _gfp_flags)) static inline void jbd2_free_handle(handle_t *handle) { @@ -1190,10 +1601,13 @@ static inline void jbd2_free_handle(handle_t *handle) */ extern struct kmem_cache *jbd2_inode_cache; -static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags) -{ - return kmem_cache_alloc(jbd2_inode_cache, gfp_flags); -} +/* + * This specialized allocator has to be a macro for its allocations to be + * accounted separately (to have a separate alloc_tag). The typecast is + * intentional to enforce typesafety. + */ +#define jbd2_alloc_inode(_gfp_flags) \ + ((struct jbd2_inode *)kmem_cache_alloc(jbd2_inode_cache, _gfp_flags)) static inline void jbd2_free_inode(struct jbd2_inode *jinode) { @@ -1203,16 +1617,18 @@ static inline void jbd2_free_inode(struct jbd2_inode *jinode) /* Primary revoke support */ #define JOURNAL_REVOKE_DEFAULT_HASH 256 extern int jbd2_journal_init_revoke(journal_t *, int); -extern void jbd2_journal_destroy_revoke_caches(void); -extern int jbd2_journal_init_revoke_caches(void); +extern void jbd2_journal_destroy_revoke_record_cache(void); +extern void jbd2_journal_destroy_revoke_table_cache(void); +extern int __init jbd2_journal_init_revoke_record_cache(void); +extern int __init jbd2_journal_init_revoke_table_cache(void); +struct jbd2_revoke_table_s *jbd2_journal_init_revoke_table(int hash_size); +void jbd2_journal_destroy_revoke_table(struct jbd2_revoke_table_s *table); extern void jbd2_journal_destroy_revoke(journal_t *); extern int jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *); -extern int jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); -extern void jbd2_journal_write_revoke_records(journal_t *journal, - transaction_t *transaction, - struct list_head *log_bufs, - int write_op); +extern void jbd2_journal_cancel_revoke(handle_t *, struct journal_head *); +extern void jbd2_journal_write_revoke_records(transaction_t *transaction, + struct list_head *log_bufs); /* Recovery revoke support */ extern int jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t); @@ -1229,9 +1645,9 @@ extern void jbd2_clear_buffer_revoked_flags(journal_t *journal); */ int jbd2_log_start_commit(journal_t *journal, tid_t tid); -int __jbd2_log_start_commit(journal_t *journal, tid_t tid); int jbd2_journal_start_commit(journal_t *journal, tid_t *tid); int jbd2_log_wait_commit(journal_t *journal, tid_t tid); +int jbd2_transaction_committed(journal_t *journal, tid_t tid); int jbd2_complete_transaction(journal_t *journal, tid_t tid); int jbd2_log_do_checkpoint(journal_t *journal); int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid); @@ -1240,14 +1656,15 @@ void __jbd2_log_wait_for_space(journal_t *journal); extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *); extern int jbd2_cleanup_journal_tail(journal_t *); -/* Debugging code only: */ - -#define jbd_ENOSYS() \ -do { \ - printk (KERN_ERR "JBD unimplemented function %s\n", __func__); \ - current->state = TASK_UNINTERRUPTIBLE; \ - schedule(); \ -} while (1) +/* Fast commit related APIs */ +int jbd2_fc_begin_commit(journal_t *journal, tid_t tid); +int jbd2_fc_end_commit(journal_t *journal); +int jbd2_fc_end_commit_fallback(journal_t *journal); +int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out); +int jbd2_submit_inode_data(journal_t *journal, struct jbd2_inode *jinode); +int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode); +int jbd2_fc_wait_bufs(journal_t *journal, int num_blks); +void jbd2_fc_release_bufs(journal_t *journal); /* * is_journal_abort @@ -1276,6 +1693,25 @@ static inline void jbd2_journal_abort_handle(handle_t *handle) handle->h_aborted = 1; } +static inline void jbd2_init_fs_dev_write_error(journal_t *journal) +{ + struct address_space *mapping = journal->j_fs_dev->bd_mapping; + + /* + * Save the original wb_err value of client fs's bdev mapping which + * could be used to detect the client fs's metadata async write error. + */ + errseq_check_and_advance(&mapping->wb_err, &journal->j_fs_dev_wb_err); +} + +static inline int jbd2_check_fs_dev_write_error(journal_t *journal) +{ + struct address_space *mapping = journal->j_fs_dev->bd_mapping; + + return errseq_check(&mapping->wb_err, + READ_ONCE(journal->j_fs_dev_wb_err)); +} + #endif /* __KERNEL__ */ /* Comparison functions for transaction IDs: perform comparisons using @@ -1293,23 +1729,20 @@ static inline int tid_geq(tid_t x, tid_t y) return (difference >= 0); } -extern int jbd2_journal_blocks_per_page(struct inode *inode); +extern int jbd2_journal_blocks_per_folio(struct inode *inode); extern size_t journal_tag_bytes(journal_t *journal); -/* - * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for - * transaction control blocks. - */ -#define JBD2_CONTROL_BLOCKS_SHIFT 5 +static inline int jbd2_journal_has_csum_v2or3(journal_t *journal) +{ + return jbd2_has_feature_csum2(journal) || + jbd2_has_feature_csum3(journal); +} -/* - * Return the minimum number of blocks which must be free in the journal - * before a new transaction may be started. Must be called under j_state_lock. - */ -static inline int jbd2_space_needed(journal_t *journal) +static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb) { - int nblocks = journal->j_max_transaction_buffers; - return nblocks + (nblocks >> JBD2_CONTROL_BLOCKS_SHIFT); + int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks); + + return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS; } /* @@ -1318,16 +1751,13 @@ static inline int jbd2_space_needed(journal_t *journal) static inline unsigned long jbd2_log_space_left(journal_t *journal) { /* Allow for rounding errors */ - unsigned long free = journal->j_free - 32; + long free = journal->j_free - 32; if (journal->j_committing_transaction) { - unsigned long committing = atomic_read(&journal-> - j_committing_transaction->t_outstanding_credits); - - /* Transaction + control blocks */ - free -= committing + (committing >> JBD2_CONTROL_BLOCKS_SHIFT); + free -= atomic_read(&journal-> + j_committing_transaction->t_outstanding_credits); } - return free; + return max_t(long, free, 0); } /* @@ -1342,31 +1772,9 @@ static inline unsigned long jbd2_log_space_left(journal_t *journal) #define BJ_Reserved 4 /* Buffer is reserved for access by journal */ #define BJ_Types 5 -extern int jbd_blocks_per_page(struct inode *inode); - -/* JBD uses a CRC32 checksum */ -#define JBD_MAX_CHECKSUM_SIZE 4 - -static inline u32 jbd2_chksum(journal_t *journal, u32 crc, - const void *address, unsigned int length) +static inline u32 jbd2_chksum(u32 crc, const void *address, unsigned int length) { - struct { - struct shash_desc shash; - char ctx[JBD_MAX_CHECKSUM_SIZE]; - } desc; - int err; - - BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) > - JBD_MAX_CHECKSUM_SIZE); - - desc.shash.tfm = journal->j_chksum_driver; - desc.shash.flags = 0; - *(u32 *)desc.ctx = crc; - - err = crypto_shash_update(&desc.shash, address, length); - BUG_ON(err); - - return *(u32 *)desc.ctx; + return crc32c(crc, address, length); } /* Return most recent uncommitted transaction */ @@ -1382,6 +1790,20 @@ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) return tid; } +static inline int jbd2_handle_buffer_credits(handle_t *handle) +{ + journal_t *journal; + + if (!handle->h_reserved) + journal = handle->h_transaction->t_journal; + else + journal = handle->h_journal; + + return handle->h_total_credits - + DIV_ROUND_UP(handle->h_revoke_credits_requested, + journal->j_revoke_records_per_block); +} + #ifdef __KERNEL__ #define buffer_trace_init(bh) do {} while (0) @@ -1393,4 +1815,7 @@ static inline tid_t jbd2_get_latest_transaction(journal_t *journal) #endif /* __KERNEL__ */ +#define EFSBADCRC EBADMSG /* Bad CRC detected */ +#define EFSCORRUPTED EUCLEAN /* Filesystem is corrupted */ + #endif /* _LINUX_JBD2_H */ |