transaction.c | Explore in Territory

// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 */

#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
#include <linux/writeback.h>
#include <linux/pagemap.h>
#include <linux/blkdev.h>
#include <linux/uuid.h>
#include <linux/timekeeping.h>
#include "misc.h"
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "locking.h"
#include "tree-log.h"
#include "volumes.h"
#include "dev-replace.h"
#include "qgroup.h"
#include "block-group.h"
#include "space-info.h"
#include "fs.h"
#include "accessors.h"
#include "extent-tree.h"
#include "root-tree.h"
#include "dir-item.h"
#include "uuid-tree.h"
#include "ioctl.h"
#include "relocation.h"
#include "scrub.h"

static struct kmem_cache *btrfs_trans_handle_cachep;

/*
 * Transaction states and transitions
 *
 * No running transaction (fs tree blocks are not modified)
 * |
 * | To next stage:
 * |  Call start_transaction() variants. Except btrfs_join_transaction_nostart().
 * V
 * Transaction N [[TRANS_STATE_RUNNING]]
 * |
 * | New trans handles can be attached to transaction N by calling all
 * | start_transaction() variants.
 * |
 * | To next stage:
 * |  Call btrfs_commit_transaction() on any trans handle attached to
 * |  transaction N
 * V
 * Transaction N [[TRANS_STATE_COMMIT_PREP]]
 * |
 * | If there are simultaneous calls to btrfs_commit_transaction() one will win
 * | the race and the rest will wait for the winner to commit the transaction.
 * |
 * | The winner will wait for previous running transaction to completely finish
 * | if there is one.
 * |
 * Transaction N [[TRANS_STATE_COMMIT_START]]
 * |
 * | Then one of the following happens:
 * | - Wait for all other trans handle holders to release.
 * |   The btrfs_commit_transaction() caller will do the commit work.
 * | - Wait for current transaction to be committed by others.
 * |   Other btrfs_commit_transaction() caller will do the commit work.
 * |
 * | At this stage, only btrfs_join_transaction*() variants can attach
 * | to this running transaction.
 * | All other variants will wait for current one to finish and attach to
 * | transaction N+1.
 * |
 * | To next stage:
 * |  Caller is chosen to commit transaction N, and all other trans handle
 * |  haven been released.
 * V
 * Transaction N [[TRANS_STATE_COMMIT_DOING]]
 * |
 * | The heavy lifting transaction work is started.
 * | From running delayed refs (modifying extent tree) to creating pending
 * | snapshots, running qgroups.
 * | In short, modify supporting trees to reflect modifications of subvolume
 * | trees.
 * |
 * | At this stage, all start_transaction() calls will wait for this
 * | transaction to finish and attach to transaction N+1.
 * |
 * | To next stage:
 * |  Until all supporting trees are updated.
 * V
 * Transaction N [[TRANS_STATE_UNBLOCKED]]
 * |						    Transaction N+1
 * | All needed trees are modified, thus we only    [[TRANS_STATE_RUNNING]]
 * | need to write them back to disk and update	    |
 * | super blocks.				    |
 * |						    |
 * | At this stage, new transaction is allowed to   |
 * | start.					    |
 * | All new start_transaction() calls will be	    |
 * | attached to transid N+1.			    |
 * |						    |
 * | To next stage:				    |
 * |  Until all tree blocks are super blocks are    |
 * |  written to block devices			    |
 * V						    |
 * Transaction N [[TRANS_STATE_COMPLETED]]	    V
 *   All tree blocks and super blocks are written.  Transaction N+1
 *   This transaction is finished and all its	    [[TRANS_STATE_COMMIT_START]]
 *   data structures will be cleaned up.	    | Life goes on
 */
static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = …;

void btrfs_put_transaction(struct btrfs_transaction *transaction)
{ … }

static noinline void switch_commit_roots(struct btrfs_trans_handle *trans)
{ … }

static inline void extwriter_counter_inc(struct btrfs_transaction *trans,
					 unsigned int type)
{ … }

static inline void extwriter_counter_dec(struct btrfs_transaction *trans,
					 unsigned int type)
{ … }

static inline void extwriter_counter_init(struct btrfs_transaction *trans,
					  unsigned int type)
{ … }

static inline int extwriter_counter_read(struct btrfs_transaction *trans)
{ … }

/*
 * To be called after doing the chunk btree updates right after allocating a new
 * chunk (after btrfs_chunk_alloc_add_chunk_item() is called), when removing a
 * chunk after all chunk btree updates and after finishing the second phase of
 * chunk allocation (btrfs_create_pending_block_groups()) in case some block
 * group had its chunk item insertion delayed to the second phase.
 */
void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
{ … }

/*
 * either allocate a new transaction or hop into the existing one
 */
static noinline int join_transaction(struct btrfs_fs_info *fs_info,
				     unsigned int type)
{ … }

/*
 * This does all the record keeping required to make sure that a shareable root
 * is properly recorded in a given transaction.  This is required to make sure
 * the old root from before we joined the transaction is deleted when the
 * transaction commits.
 */
static int record_root_in_trans(struct btrfs_trans_handle *trans,
			       struct btrfs_root *root,
			       int force)
{ … }


void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
			    struct btrfs_root *root)
{ … }

int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
			       struct btrfs_root *root)
{ … }

static inline int is_transaction_blocked(struct btrfs_transaction *trans)
{ … }

/* wait for commit against the current transaction to become unblocked
 * when this is done, it is safe to start a new transaction, but the current
 * transaction might not be fully on disk.
 */
static void wait_current_trans(struct btrfs_fs_info *fs_info)
{ … }

static int may_wait_transaction(struct btrfs_fs_info *fs_info, int type)
{ … }

static inline bool need_reserve_reloc_root(struct btrfs_root *root)
{ … }

static int btrfs_reserve_trans_metadata(struct btrfs_fs_info *fs_info,
					enum btrfs_reserve_flush_enum flush,
					u64 num_bytes,
					u64 *delayed_refs_bytes)
{ … }

static struct btrfs_trans_handle *
start_transaction(struct btrfs_root *root, unsigned int num_items,
		  unsigned int type, enum btrfs_reserve_flush_enum flush,
		  bool enforce_qgroups)
{ … }

struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
						   unsigned int num_items)
{ … }

struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
					struct btrfs_root *root,
					unsigned int num_items)
{ … }

struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
{ … }

struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root)
{ … }

/*
 * Similar to regular join but it never starts a transaction when none is
 * running or when there's a running one at a state >= TRANS_STATE_UNBLOCKED.
 * This is similar to btrfs_attach_transaction() but it allows the join to
 * happen if the transaction commit already started but it's not yet in the
 * "doing" phase (the state is < TRANS_STATE_COMMIT_DOING).
 */
struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root)
{ … }

/*
 * Catch the running transaction.
 *
 * It is used when we want to commit the current the transaction, but
 * don't want to start a new one.
 *
 * Note: If this function return -ENOENT, it just means there is no
 * running transaction. But it is possible that the inactive transaction
 * is still in the memory, not fully on disk. If you hope there is no
 * inactive transaction in the fs when -ENOENT is returned, you should
 * invoke
 *     btrfs_attach_transaction_barrier()
 */
struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root)
{ … }

/*
 * Catch the running transaction.
 *
 * It is similar to the above function, the difference is this one
 * will wait for all the inactive transactions until they fully
 * complete.
 */
struct btrfs_trans_handle *
btrfs_attach_transaction_barrier(struct btrfs_root *root)
{ … }

/* Wait for a transaction commit to reach at least the given state. */
static noinline void wait_for_commit(struct btrfs_transaction *commit,
				     const enum btrfs_trans_state min_state)
{ … }

int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid)
{ … }

void btrfs_throttle(struct btrfs_fs_info *fs_info)
{ … }

bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans)
{ … }

static void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans)

{ … }

static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
				   int throttle)
{ … }

int btrfs_end_transaction(struct btrfs_trans_handle *trans)
{ … }

int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans)
{ … }

/*
 * when btree blocks are allocated, they have some corresponding bits set for
 * them in one of two extent_io trees.  This is used to make sure all of
 * those extents are sent to disk but does not wait on them
 */
int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
			       struct extent_io_tree *dirty_pages, int mark)
{ … }

/*
 * when btree blocks are allocated, they have some corresponding bits set for
 * them in one of two extent_io trees.  This is used to make sure all of
 * those extents are on disk for transaction or log commit.  We wait
 * on all the pages and clear them from the dirty pages state tree
 */
static int __btrfs_wait_marked_extents(struct btrfs_fs_info *fs_info,
				       struct extent_io_tree *dirty_pages)
{ … }

static int btrfs_wait_extents(struct btrfs_fs_info *fs_info,
		       struct extent_io_tree *dirty_pages)
{ … }

int btrfs_wait_tree_log_extents(struct btrfs_root *log_root, int mark)
{ … }

/*
 * When btree blocks are allocated the corresponding extents are marked dirty.
 * This function ensures such extents are persisted on disk for transaction or
 * log commit.
 *
 * @trans: transaction whose dirty pages we'd like to write
 */
static int btrfs_write_and_wait_transaction(struct btrfs_trans_handle *trans)
{ … }

/*
 * this is used to update the root pointer in the tree of tree roots.
 *
 * But, in the case of the extent allocation tree, updating the root
 * pointer may allocate blocks which may change the root of the extent
 * allocation tree.
 *
 * So, this loops and repeats and makes sure the cowonly root didn't
 * change while the root pointer was being updated in the metadata.
 */
static int update_cowonly_root(struct btrfs_trans_handle *trans,
			       struct btrfs_root *root)
{ … }

/*
 * update all the cowonly tree roots on disk
 *
 * The error handling in this function may not be obvious. Any of the
 * failures will cause the file system to go offline. We still need
 * to clean up the delayed refs.
 */
static noinline int commit_cowonly_roots(struct btrfs_trans_handle *trans)
{ … }

/*
 * If we had a pending drop we need to see if there are any others left in our
 * dead roots list, and if not clear our bit and wake any waiters.
 */
void btrfs_maybe_wake_unfinished_drop(struct btrfs_fs_info *fs_info)
{ … }

/*
 * dead roots are old snapshots that need to be deleted.  This allocates
 * a dirty root struct and adds it into the list of dead roots that need to
 * be deleted
 */
void btrfs_add_dead_root(struct btrfs_root *root)
{ … }

/*
 * Update each subvolume root and its relocation root, if it exists, in the tree
 * of tree roots. Also free log roots if they exist.
 */
static noinline int commit_fs_roots(struct btrfs_trans_handle *trans)
{ … }

/*
 * Do all special snapshot related qgroup dirty hack.
 *
 * Will do all needed qgroup inherit and dirty hack like switch commit
 * roots inside one transaction and write all btree into disk, to make
 * qgroup works.
 */
static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
				   struct btrfs_root *src,
				   struct btrfs_root *parent,
				   struct btrfs_qgroup_inherit *inherit,
				   u64 dst_objectid)
{ … }

/*
 * new snapshots need to be created at a very specific time in the
 * transaction commit.  This does the actual creation.
 *
 * Note:
 * If the error which may affect the commitment of the current transaction
 * happens, we should return the error number. If the error which just affect
 * the creation of the pending snapshots, just return 0.
 */
static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
				   struct btrfs_pending_snapshot *pending)
{ … }

/*
 * create all the snapshots we've scheduled for creation
 */
static noinline int create_pending_snapshots(struct btrfs_trans_handle *trans)
{ … }

static void update_super_roots(struct btrfs_fs_info *fs_info)
{ … }

int btrfs_transaction_blocked(struct btrfs_fs_info *info)
{ … }

void btrfs_commit_transaction_async(struct btrfs_trans_handle *trans)
{ … }

/*
 * If there is a running transaction commit it or if it's already committing,
 * wait for its commit to complete. Does not start and commit a new transaction
 * if there isn't any running.
 */
int btrfs_commit_current_transaction(struct btrfs_root *root)
{ … }

static void cleanup_transaction(struct btrfs_trans_handle *trans, int err)
{ … }

/*
 * Release reserved delayed ref space of all pending block groups of the
 * transaction and remove them from the list
 */
static void btrfs_cleanup_pending_block_groups(struct btrfs_trans_handle *trans)
{ … }

static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
{ … }

static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
{ … }

/*
 * Add a pending snapshot associated with the given transaction handle to the
 * respective handle. This must be called after the transaction commit started
 * and while holding fs_info->trans_lock.
 * This serves to guarantee a caller of btrfs_commit_transaction() that it can
 * safely free the pending snapshot pointer in case btrfs_commit_transaction()
 * returns an error.
 */
static void add_pending_snapshot(struct btrfs_trans_handle *trans)
{ … }

static void update_commit_stats(struct btrfs_fs_info *fs_info, ktime_t interval)
{ … }

int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
{ … }

/*
 * return < 0 if error
 * 0 if there are no more dead_roots at the time of call
 * 1 there are more to be processed, call me again
 *
 * The return value indicates there are certainly more snapshots to delete, but
 * if there comes a new one during processing, it may return 0. We don't mind,
 * because btrfs_commit_super will poke cleaner thread and it will process it a
 * few seconds later.
 */
int btrfs_clean_one_deleted_snapshot(struct btrfs_fs_info *fs_info)
{ … }

/*
 * We only mark the transaction aborted and then set the file system read-only.
 * This will prevent new transactions from starting or trying to join this
 * one.
 *
 * This means that error recovery at the call site is limited to freeing
 * any local memory allocations and passing the error code up without
 * further cleanup. The transaction should complete as it normally would
 * in the call path but will return -EIO.
 *
 * We'll complete the cleanup in btrfs_end_transaction and
 * btrfs_commit_transaction.
 */
void __cold __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
				      const char *function,
				      unsigned int line, int error, bool first_hit)
{ … }

int __init btrfs_transaction_init(void)
{ … }

void __cold btrfs_transaction_exit(void)
{ … }
linux/fs/btrfs/transaction.c
