summaryrefslogtreecommitdiff
path: root/fs/btrfs/transaction.h
diff options
context:
space:
mode:
Diffstat (limited to 'fs/btrfs/transaction.h')
-rw-r--r--fs/btrfs/transaction.h178
1 files changed, 128 insertions, 50 deletions
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index f1ba78949d1b..18ef069197e5 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -6,17 +6,39 @@
#ifndef BTRFS_TRANSACTION_H
#define BTRFS_TRANSACTION_H
+#include <linux/atomic.h>
#include <linux/refcount.h>
+#include <linux/list.h>
+#include <linux/time64.h>
+#include <linux/mutex.h>
+#include <linux/wait.h>
#include "btrfs_inode.h"
#include "delayed-ref.h"
-#include "ctree.h"
+
+struct dentry;
+struct inode;
+struct btrfs_pending_snapshot;
+struct btrfs_fs_info;
+struct btrfs_root_item;
+struct btrfs_root;
+struct btrfs_path;
+
+/*
+ * Signal that a direct IO write is in progress, to avoid deadlock for sync
+ * direct IO writes when fsync is called during the direct IO write path.
+ */
+#define BTRFS_TRANS_DIO_WRITE_STUB ((void *) 1)
+
+/* Radix-tree tag for roots that are part of the transaction. */
+#define BTRFS_ROOT_TRANS_TAG 0
enum btrfs_trans_state {
TRANS_STATE_RUNNING,
- TRANS_STATE_BLOCKED,
+ TRANS_STATE_COMMIT_PREP,
TRANS_STATE_COMMIT_START,
TRANS_STATE_COMMIT_DOING,
TRANS_STATE_UNBLOCKED,
+ TRANS_STATE_SUPER_COMMITTED,
TRANS_STATE_COMPLETED,
TRANS_STATE_MAX,
};
@@ -51,7 +73,7 @@ struct btrfs_transaction {
wait_queue_head_t writer_wait;
wait_queue_head_t commit_wait;
struct list_head pending_snapshots;
- struct list_head pending_chunks;
+ struct list_head dev_update_list;
struct list_head switch_commits;
struct list_head dirty_bgs;
@@ -72,6 +94,7 @@ struct btrfs_transaction {
*/
struct list_head io_bgs;
struct list_head dropped_roots;
+ struct extent_io_tree pinned_extents;
/*
* we need to make sure block group deletion doesn't race with
@@ -80,56 +103,78 @@ struct btrfs_transaction {
*/
struct mutex cache_write_mutex;
spinlock_t dirty_bgs_lock;
- unsigned int num_dirty_bgs;
/* Protected by spin lock fs_info->unused_bgs_lock. */
struct list_head deleted_bgs;
spinlock_t dropped_roots_lock;
struct btrfs_delayed_ref_root delayed_refs;
struct btrfs_fs_info *fs_info;
-};
-#define __TRANS_FREEZABLE (1U << 0)
+ /*
+ * Number of ordered extents the transaction must wait for before
+ * committing. These are ordered extents started by a fast fsync.
+ */
+ atomic_t pending_ordered;
+ wait_queue_head_t pending_wait;
+};
-#define __TRANS_START (1U << 9)
-#define __TRANS_ATTACH (1U << 10)
-#define __TRANS_JOIN (1U << 11)
-#define __TRANS_JOIN_NOLOCK (1U << 12)
-#define __TRANS_DUMMY (1U << 13)
+enum {
+ ENUM_BIT(__TRANS_FREEZABLE),
+ ENUM_BIT(__TRANS_START),
+ ENUM_BIT(__TRANS_ATTACH),
+ ENUM_BIT(__TRANS_JOIN),
+ ENUM_BIT(__TRANS_JOIN_NOLOCK),
+ ENUM_BIT(__TRANS_DUMMY),
+ ENUM_BIT(__TRANS_JOIN_NOSTART),
+};
#define TRANS_START (__TRANS_START | __TRANS_FREEZABLE)
#define TRANS_ATTACH (__TRANS_ATTACH)
#define TRANS_JOIN (__TRANS_JOIN | __TRANS_FREEZABLE)
#define TRANS_JOIN_NOLOCK (__TRANS_JOIN_NOLOCK)
+#define TRANS_JOIN_NOSTART (__TRANS_JOIN_NOSTART)
#define TRANS_EXTWRITERS (__TRANS_START | __TRANS_ATTACH)
-#define BTRFS_SEND_TRANS_STUB ((void *)1)
-
struct btrfs_trans_handle {
u64 transid;
u64 bytes_reserved;
+ u64 delayed_refs_bytes_reserved;
u64 chunk_bytes_reserved;
unsigned long delayed_ref_updates;
+ unsigned long delayed_ref_csum_deletions;
struct btrfs_transaction *transaction;
struct btrfs_block_rsv *block_rsv;
struct btrfs_block_rsv *orig_rsv;
+ /* Set by a task that wants to create a snapshot. */
+ struct btrfs_pending_snapshot *pending_snapshot;
refcount_t use_count;
unsigned int type;
+ /*
+ * Error code of transaction abort, set outside of locks and must use
+ * the READ_ONCE/WRITE_ONCE access
+ */
short aborted;
bool adding_csums;
bool allocating_chunk;
- bool can_flush_pending_bgs;
+ bool removing_chunk;
bool reloc_reserved;
- bool sync;
- bool dirty;
- struct btrfs_root *root;
+ bool in_fsync;
struct btrfs_fs_info *fs_info;
struct list_head new_bgs;
+ struct btrfs_block_rsv delayed_rsv;
};
+/*
+ * The abort status can be changed between calls and is not protected by locks.
+ * This accepts btrfs_transaction and btrfs_trans_handle as types. Once it's
+ * set to a non-zero value it does not change, so the macro should be in checks
+ * but is not necessary for further reads of the value.
+ */
+#define TRANS_ABORTED(trans) (unlikely(READ_ONCE((trans)->aborted)))
+
struct btrfs_pending_snapshot {
struct dentry *dentry;
- struct inode *dir;
+ struct btrfs_inode *dir;
struct btrfs_root *root;
struct btrfs_root_item *root_item;
struct btrfs_root *snap;
@@ -139,18 +184,20 @@ struct btrfs_pending_snapshot {
struct btrfs_block_rsv block_rsv;
/* extra metadata reservation for relocation */
int error;
+ /* Preallocated anonymous block device number */
+ dev_t anon_dev;
bool readonly;
struct list_head list;
};
static inline void btrfs_set_inode_last_trans(struct btrfs_trans_handle *trans,
- struct inode *inode)
+ struct btrfs_inode *inode)
{
- spin_lock(&BTRFS_I(inode)->lock);
- BTRFS_I(inode)->last_trans = trans->transaction->transid;
- BTRFS_I(inode)->last_sub_trans = BTRFS_I(inode)->root->log_transid;
- BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->root->last_log_commit;
- spin_unlock(&BTRFS_I(inode)->lock);
+ spin_lock(&inode->lock);
+ inode->last_trans = trans->transaction->transid;
+ inode->last_sub_trans = btrfs_get_root_log_transid(inode->root);
+ inode->last_log_commit = inode->last_sub_trans - 1;
+ spin_unlock(&inode->lock);
}
/*
@@ -176,55 +223,86 @@ static inline void btrfs_clear_skip_qgroup(struct btrfs_trans_handle *trans)
delayed_refs->qgroup_to_skip = 0;
}
+/*
+ * We want the transaction abort to print stack trace only for errors where the
+ * cause could be a bug, eg. due to ENOSPC, and not for common errors that are
+ * caused by external factors.
+ */
+static inline bool btrfs_abort_should_print_stack(int error)
+{
+ switch (error) {
+ case -EIO:
+ case -EROFS:
+ case -ENOMEM:
+ return false;
+ }
+ return true;
+}
+
+/*
+ * Call btrfs_abort_transaction as early as possible when an error condition is
+ * detected, that way the exact stack trace is reported for some errors.
+ */
+#define btrfs_abort_transaction(trans, error) \
+do { \
+ bool __first = false; \
+ /* Report first abort since mount */ \
+ if (!test_and_set_bit(BTRFS_FS_STATE_TRANS_ABORTED, \
+ &((trans)->fs_info->fs_state))) { \
+ __first = true; \
+ if (WARN(btrfs_abort_should_print_stack(error), \
+ KERN_ERR \
+ "BTRFS: Transaction aborted (error %d)\n", \
+ (error))) { \
+ /* Stack trace printed. */ \
+ } else { \
+ btrfs_err((trans)->fs_info, \
+ "Transaction aborted (error %d)", \
+ (error)); \
+ } \
+ } \
+ __btrfs_abort_transaction((trans), __func__, \
+ __LINE__, (error), __first); \
+} while (0)
+
int btrfs_end_transaction(struct btrfs_trans_handle *trans);
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,
- int min_factor);
+ unsigned int num_items);
struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root);
-struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_join_transaction_spacecache(struct btrfs_root *root);
+struct btrfs_trans_handle *btrfs_join_transaction_nostart(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root);
struct btrfs_trans_handle *btrfs_attach_transaction_barrier(
struct btrfs_root *root);
int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid);
void btrfs_add_dead_root(struct btrfs_root *root);
-int btrfs_defrag_root(struct btrfs_root *root);
-int btrfs_clean_one_deleted_snapshot(struct btrfs_root *root);
+void btrfs_maybe_wake_unfinished_drop(struct btrfs_fs_info *fs_info);
+int btrfs_clean_one_deleted_snapshot(struct btrfs_fs_info *fs_info);
int btrfs_commit_transaction(struct btrfs_trans_handle *trans);
-int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
- int wait_for_unblock);
-
-/*
- * Try to commit transaction asynchronously, so this is safe to call
- * even holding a spinlock.
- *
- * It's done by informing transaction_kthread to commit transaction without
- * waiting for commit interval.
- */
-static inline void btrfs_commit_transaction_locksafe(
- struct btrfs_fs_info *fs_info)
-{
- set_bit(BTRFS_FS_NEED_ASYNC_COMMIT, &fs_info->flags);
- wake_up_process(fs_info->transaction_kthread);
-}
+void btrfs_commit_transaction_async(struct btrfs_trans_handle *trans);
+int btrfs_commit_current_transaction(struct btrfs_root *root);
int btrfs_end_transaction_throttle(struct btrfs_trans_handle *trans);
-int btrfs_should_end_transaction(struct btrfs_trans_handle *trans);
+bool btrfs_should_end_transaction(struct btrfs_trans_handle *trans);
void btrfs_throttle(struct btrfs_fs_info *fs_info);
int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
int btrfs_write_marked_extents(struct btrfs_fs_info *fs_info,
struct extent_io_tree *dirty_pages, int mark);
-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 *root, int mark);
int btrfs_transaction_blocked(struct btrfs_fs_info *info);
-int btrfs_transaction_in_commit(struct btrfs_fs_info *info);
void btrfs_put_transaction(struct btrfs_transaction *transaction);
-void btrfs_apply_pending_changes(struct btrfs_fs_info *fs_info);
void btrfs_add_dropped_root(struct btrfs_trans_handle *trans,
struct btrfs_root *root);
+void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
+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);
#endif
generated by cgit (git 2.34.1) at 2025-12-25 01:51:35 +0000