1 files changed, 177 insertions, 170 deletions

diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 2877258d9497..63d17c5201b5 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0+
 /*
  * ext4_jbd2.h
  *
@@ -5,10 +6,6 @@
  *
  * Copyright 1998--1999 Red Hat corp --- 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.
- *
  * Ext4-specific journaling extensions.
  */
 
@@ -34,8 +31,7 @@
  */
 
 #define EXT4_SINGLEDATA_TRANS_BLOCKS(sb)				\
-	(EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)   \
-	 ? 20U : 8U)
+	(ext4_has_feature_extents(sb) ? 20U : 8U)
 
 /* Extended attribute operations touch at most two data buffers,
  * two bitmap buffers, and two group summaries, in addition to the inode
@@ -78,23 +74,26 @@
 
 #define EXT4_RESERVE_TRANS_BLOCKS	12U
 
-#define EXT4_INDEX_EXTRA_TRANS_BLOCKS	8
+/*
+ * Number of credits needed if we need to insert an entry into a
+ * directory.  For each new index block, we need 4 blocks (old index
+ * block, new index block, bitmap block, bg summary).  For normal
+ * htree directories there are 2 levels; if the largedir feature
+ * enabled it's 3 levels.
+ */
+#define EXT4_INDEX_EXTRA_TRANS_BLOCKS	12U
 
 #ifdef CONFIG_QUOTA
 /* Amount of blocks needed for quota update - we know that the structure was
  * allocated so we need to update only data block */
-#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
-		EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\
-		1 : 0)
+#define EXT4_QUOTA_TRANS_BLOCKS(sb) ((ext4_quota_capable(sb)) ? 1 : 0)
 /* Amount of blocks needed for quota insert/delete - we do some block writes
  * but inode, sb and group updates are done only once */
-#define EXT4_QUOTA_INIT_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
-		EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\
+#define EXT4_QUOTA_INIT_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\
 		(DQUOT_INIT_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
 		 +3+DQUOT_INIT_REWRITE) : 0)
 
-#define EXT4_QUOTA_DEL_BLOCKS(sb) ((test_opt(sb, QUOTA) ||\
-		EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_QUOTA)) ?\
+#define EXT4_QUOTA_DEL_BLOCKS(sb) ((ext4_quota_capable(sb)) ?\
 		(DQUOT_DEL_ALLOC*(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)\
 		 +3+DQUOT_DEL_REWRITE) : 0)
 #else
@@ -102,23 +101,9 @@
 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0
 #define EXT4_QUOTA_DEL_BLOCKS(sb) 0
 #endif
-#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
-#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
-#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
-
-static inline int ext4_jbd2_credits_xattr(struct inode *inode)
-{
-	int credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb);
-
-	/*
-	 * In case of inline data, we may push out the data to a block,
-	 * so we need to reserve credits for this eventuality
-	 */
-	if (ext4_has_inline_data(inode))
-		credits += ext4_writepage_trans_blocks(inode) + 1;
-	return credits;
-}
-
+#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
 
 /*
  * Ext4 handle operation types -- for logging purposes
@@ -137,82 +122,6 @@ static inline int ext4_jbd2_credits_xattr(struct inode *inode)
 #define EXT4_HT_EXT_CONVERT     11
 #define EXT4_HT_MAX             12
 
-/**
- *   struct ext4_journal_cb_entry - Base structure for callback information.
- *
- *   This struct is a 'seed' structure for a using with your own callback
- *   structs. If you are using callbacks you must allocate one of these
- *   or another struct of your own definition which has this struct
- *   as it's first element and pass it to ext4_journal_callback_add().
- */
-struct ext4_journal_cb_entry {
-	/* list information for other callbacks attached to the same handle */
-	struct list_head jce_list;
-
-	/*  Function to call with this callback structure */
-	void (*jce_func)(struct super_block *sb,
-			 struct ext4_journal_cb_entry *jce, int error);
-
-	/* user data goes here */
-};
-
-/**
- * ext4_journal_callback_add: add a function to call after transaction commit
- * @handle: active journal transaction handle to register callback on
- * @func: callback function to call after the transaction has committed:
- *        @sb: superblock of current filesystem for transaction
- *        @jce: returned journal callback data
- *        @rc: journal state at commit (0 = transaction committed properly)
- * @jce: journal callback data (internal and function private data struct)
- *
- * The registered function will be called in the context of the journal thread
- * after the transaction for which the handle was created has completed.
- *
- * No locks are held when the callback function is called, so it is safe to
- * call blocking functions from within the callback, but the callback should
- * not block or run for too long, or the filesystem will be blocked waiting for
- * the next transaction to commit. No journaling functions can be used, or
- * there is a risk of deadlock.
- *
- * There is no guaranteed calling order of multiple registered callbacks on
- * the same transaction.
- */
-static inline void ext4_journal_callback_add(handle_t *handle,
-			void (*func)(struct super_block *sb,
-				     struct ext4_journal_cb_entry *jce,
-				     int rc),
-			struct ext4_journal_cb_entry *jce)
-{
-	struct ext4_sb_info *sbi =
-			EXT4_SB(handle->h_transaction->t_journal->j_private);
-
-	/* Add the jce to transaction's private list */
-	jce->jce_func = func;
-	spin_lock(&sbi->s_md_lock);
-	list_add_tail(&jce->jce_list, &handle->h_transaction->t_private_list);
-	spin_unlock(&sbi->s_md_lock);
-}
-
-/**
- * ext4_journal_callback_del: delete a registered callback
- * @handle: active journal transaction handle on which callback was registered
- * @jce: registered journal callback entry to unregister
- * Return true if object was sucessfully removed
- */
-static inline bool ext4_journal_callback_try_del(handle_t *handle,
-					     struct ext4_journal_cb_entry *jce)
-{
-	bool deleted;
-	struct ext4_sb_info *sbi =
-			EXT4_SB(handle->h_transaction->t_journal->j_private);
-
-	spin_lock(&sbi->s_md_lock);
-	deleted = !list_empty(&jce->jce_list);
-	list_del_init(&jce->jce_list);
-	spin_unlock(&sbi->s_md_lock);
-	return deleted;
-}
-
 int
 ext4_mark_iloc_dirty(handle_t *handle,
 		     struct inode *inode,
@@ -226,47 +135,51 @@ ext4_mark_iloc_dirty(handle_t *handle,
 int ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 			struct ext4_iloc *iloc);
 
-int ext4_mark_inode_dirty(handle_t *handle, struct inode *inode);
+#define ext4_mark_inode_dirty(__h, __i)					\
+		__ext4_mark_inode_dirty((__h), (__i), __func__, __LINE__)
+int __ext4_mark_inode_dirty(handle_t *handle, struct inode *inode,
+				const char *func, unsigned int line);
 
+int ext4_expand_extra_isize(struct inode *inode,
+			    unsigned int new_extra_isize,
+			    struct ext4_iloc *iloc);
 /*
  * Wrapper functions with which ext4 calls into JBD.
  */
-void ext4_journal_abort_handle(const char *caller, unsigned int line,
-			       const char *err_fn,
-		struct buffer_head *bh, handle_t *handle, int err);
-
 int __ext4_journal_get_write_access(const char *where, unsigned int line,
-				    handle_t *handle, struct buffer_head *bh);
+				    handle_t *handle, struct super_block *sb,
+				    struct buffer_head *bh,
+				    enum ext4_journal_trigger_type trigger_type);
 
 int __ext4_forget(const char *where, unsigned int line, handle_t *handle,
 		  int is_metadata, struct inode *inode,
 		  struct buffer_head *bh, ext4_fsblk_t blocknr);
 
 int __ext4_journal_get_create_access(const char *where, unsigned int line,
-				handle_t *handle, struct buffer_head *bh);
+				handle_t *handle, struct super_block *sb,
+				struct buffer_head *bh,
+				enum ext4_journal_trigger_type trigger_type);
 
 int __ext4_handle_dirty_metadata(const char *where, unsigned int line,
 				 handle_t *handle, struct inode *inode,
 				 struct buffer_head *bh);
 
-int __ext4_handle_dirty_super(const char *where, unsigned int line,
-			      handle_t *handle, struct super_block *sb);
-
-#define ext4_journal_get_write_access(handle, bh) \
-	__ext4_journal_get_write_access(__func__, __LINE__, (handle), (bh))
+#define ext4_journal_get_write_access(handle, sb, bh, trigger_type) \
+	__ext4_journal_get_write_access(__func__, __LINE__, (handle), (sb), \
+					(bh), (trigger_type))
 #define ext4_forget(handle, is_metadata, inode, bh, block_nr) \
 	__ext4_forget(__func__, __LINE__, (handle), (is_metadata), (inode), \
 		      (bh), (block_nr))
-#define ext4_journal_get_create_access(handle, bh) \
-	__ext4_journal_get_create_access(__func__, __LINE__, (handle), (bh))
+#define ext4_journal_get_create_access(handle, sb, bh, trigger_type) \
+	__ext4_journal_get_create_access(__func__, __LINE__, (handle), (sb), \
+					 (bh), (trigger_type))
 #define ext4_handle_dirty_metadata(handle, inode, bh) \
 	__ext4_handle_dirty_metadata(__func__, __LINE__, (handle), (inode), \
 				     (bh))
-#define ext4_handle_dirty_super(handle, sb) \
-	__ext4_handle_dirty_super(__func__, __LINE__, (handle), (sb))
 
-handle_t *__ext4_journal_start_sb(struct super_block *sb, unsigned int line,
-				  int type, int blocks, int rsv_blocks);
+handle_t *__ext4_journal_start_sb(struct inode *inode, struct super_block *sb,
+				  unsigned int line, int type, int blocks,
+				  int rsv_blocks, int revoke_creds);
 int __ext4_journal_stop(const char *where, unsigned int line, handle_t *handle);
 
 #define EXT4_NOJOURNAL_MAX_REF_COUNT ((unsigned long) 4096)
@@ -293,28 +206,41 @@ static inline int ext4_handle_is_aborted(handle_t *handle)
 	return 0;
 }
 
-static inline int ext4_handle_has_enough_credits(handle_t *handle, int needed)
+static inline int ext4_free_metadata_revoke_credits(struct super_block *sb,
+						    int blocks)
 {
-	if (ext4_handle_valid(handle) && handle->h_buffer_credits < needed)
-		return 0;
-	return 1;
+	/* Freeing each metadata block can result in freeing one cluster */
+	return blocks * EXT4_SB(sb)->s_cluster_ratio;
+}
+
+static inline int ext4_trans_default_revoke_credits(struct super_block *sb)
+{
+	return ext4_free_metadata_revoke_credits(sb, 8);
 }
 
 #define ext4_journal_start_sb(sb, type, nblocks)			\
-	__ext4_journal_start_sb((sb), __LINE__, (type), (nblocks), 0)
+	__ext4_journal_start_sb(NULL, (sb), __LINE__, (type), (nblocks), 0,\
+				ext4_trans_default_revoke_credits(sb))
 
 #define ext4_journal_start(inode, type, nblocks)			\
-	__ext4_journal_start((inode), __LINE__, (type), (nblocks), 0)
+	__ext4_journal_start((inode), __LINE__, (type), (nblocks), 0,	\
+			     ext4_trans_default_revoke_credits((inode)->i_sb))
 
-#define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks) \
-	__ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks))
+#define ext4_journal_start_with_reserve(inode, type, blocks, rsv_blocks)\
+	__ext4_journal_start((inode), __LINE__, (type), (blocks), (rsv_blocks),\
+			     ext4_trans_default_revoke_credits((inode)->i_sb))
+
+#define ext4_journal_start_with_revoke(inode, type, blocks, revoke_creds) \
+	__ext4_journal_start((inode), __LINE__, (type), (blocks), 0,	\
+			     (revoke_creds))
 
 static inline handle_t *__ext4_journal_start(struct inode *inode,
 					     unsigned int line, int type,
-					     int blocks, int rsv_blocks)
+					     int blocks, int rsv_blocks,
+					     int revoke_creds)
 {
-	return __ext4_journal_start_sb(inode->i_sb, line, type, blocks,
-				       rsv_blocks);
+	return __ext4_journal_start_sb(inode, inode->i_sb, line, type, blocks,
+				       rsv_blocks, revoke_creds);
 }
 
 #define ext4_journal_stop(handle) \
@@ -326,35 +252,77 @@ static inline handle_t *__ext4_journal_start(struct inode *inode,
 handle_t *__ext4_journal_start_reserved(handle_t *handle, unsigned int line,
 					int type);
 
-static inline void ext4_journal_free_reserved(handle_t *handle)
-{
-	if (ext4_handle_valid(handle))
-		jbd2_journal_free_reserved(handle);
-}
-
 static inline handle_t *ext4_journal_current_handle(void)
 {
 	return journal_current_handle();
 }
 
-static inline int ext4_journal_extend(handle_t *handle, int nblocks)
+static inline int ext4_journal_extend(handle_t *handle, int nblocks, int revoke)
 {
 	if (ext4_handle_valid(handle))
-		return jbd2_journal_extend(handle, nblocks);
+		return jbd2_journal_extend(handle, nblocks, revoke);
 	return 0;
 }
 
-static inline int ext4_journal_restart(handle_t *handle, int nblocks)
+static inline int ext4_journal_restart(handle_t *handle, int nblocks,
+				       int revoke)
 {
 	if (ext4_handle_valid(handle))
-		return jbd2_journal_restart(handle, nblocks);
+		return jbd2__journal_restart(handle, nblocks, revoke, GFP_NOFS);
 	return 0;
 }
 
-static inline int ext4_journal_blocks_per_page(struct inode *inode)
+int __ext4_journal_ensure_credits(handle_t *handle, int check_cred,
+				  int extend_cred, int revoke_cred);
+
+
+/*
+ * Ensure @handle has at least @check_creds credits available. If not,
+ * transaction will be extended or restarted to contain at least @extend_cred
+ * credits. Before restarting transaction @fn is executed to allow for cleanup
+ * before the transaction is restarted.
+ *
+ * The return value is < 0 in case of error, 0 in case the handle has enough
+ * credits or transaction extension succeeded, 1 in case transaction had to be
+ * restarted.
+ */
+#define ext4_journal_ensure_credits_fn(handle, check_cred, extend_cred,	\
+				       revoke_cred, fn) \
+({									\
+	__label__ __ensure_end;						\
+	int err = __ext4_journal_ensure_credits((handle), (check_cred),	\
+					(extend_cred), (revoke_cred));	\
+									\
+	if (err <= 0)							\
+		goto __ensure_end;					\
+	err = (fn);							\
+	if (err < 0)							\
+		goto __ensure_end;					\
+	err = ext4_journal_restart((handle), (extend_cred), (revoke_cred)); \
+	if (err == 0)							\
+		err = 1;						\
+__ensure_end:								\
+	err;								\
+})
+
+/*
+ * Ensure given handle has at least requested amount of credits available,
+ * possibly restarting transaction if needed. We also make sure the transaction
+ * has space for at least ext4_trans_default_revoke_credits(sb) revoke records
+ * as freeing one or two blocks is very common pattern and requesting this is
+ * very cheap.
+ */
+static inline int ext4_journal_ensure_credits(handle_t *handle, int credits,
+					      int revoke_creds)
+{
+	return ext4_journal_ensure_credits_fn(handle, credits, credits,
+				revoke_creds, 0);
+}
+
+static inline int ext4_journal_blocks_per_folio(struct inode *inode)
 {
 	if (EXT4_JOURNAL(inode) != NULL)
-		return jbd2_journal_blocks_per_page(inode);
+		return jbd2_journal_blocks_per_folio(inode);
 	return 0;
 }
 
@@ -365,10 +333,21 @@ static inline int ext4_journal_force_commit(journal_t *journal)
 	return 0;
 }
 
-static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
+static inline int ext4_jbd2_inode_add_write(handle_t *handle,
+		struct inode *inode, loff_t start_byte, loff_t length)
 {
 	if (ext4_handle_valid(handle))
-		return jbd2_journal_file_inode(handle, EXT4_I(inode)->jinode);
+		return jbd2_journal_inode_ranged_write(handle,
+				EXT4_I(inode)->jinode, start_byte, length);
+	return 0;
+}
+
+static inline int ext4_jbd2_inode_add_wait(handle_t *handle,
+		struct inode *inode, loff_t start_byte, loff_t length)
+{
+	if (ext4_handle_valid(handle))
+		return jbd2_journal_inode_ranged_wait(handle,
+				EXT4_I(inode)->jinode, start_byte, length);
 	return 0;
 }
 
@@ -378,7 +357,7 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle,
 {
 	struct ext4_inode_info *ei = EXT4_I(inode);
 
-	if (ext4_handle_valid(handle)) {
+	if (ext4_handle_valid(handle) && !is_handle_aborted(handle)) {
 		ei->i_sync_tid = handle->h_transaction->t_tid;
 		if (datasync)
 			ei->i_datasync_tid = handle->h_transaction->t_tid;
@@ -395,24 +374,7 @@ int ext4_force_commit(struct super_block *sb);
 #define EXT4_INODE_ORDERED_DATA_MODE	0x02 /* ordered data mode */
 #define EXT4_INODE_WRITEBACK_DATA_MODE	0x04 /* writeback data mode */
 
-static inline int ext4_inode_journal_mode(struct inode *inode)
-{
-	if (EXT4_JOURNAL(inode) == NULL)
-		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
-	/* We do not support data journalling with delayed allocation */
-	if (!S_ISREG(inode->i_mode) ||
-	    test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
-		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
-	if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
-	    !test_opt(inode->i_sb, DELALLOC))
-		return EXT4_INODE_JOURNAL_DATA_MODE;	/* journal data */
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
-		return EXT4_INODE_ORDERED_DATA_MODE;	/* ordered */
-	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
-		return EXT4_INODE_WRITEBACK_DATA_MODE;	/* writeback */
-	else
-		BUG();
-}
+int ext4_inode_journal_mode(struct inode *inode);
 
 static inline int ext4_should_journal_data(struct inode *inode)
 {
@@ -429,10 +391,23 @@ static inline int ext4_should_writeback_data(struct inode *inode)
 	return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
 }
 
+static inline int ext4_free_data_revoke_credits(struct inode *inode, int blocks)
+{
+	if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+		return 0;
+	if (!ext4_should_journal_data(inode))
+		return 0;
+	/*
+	 * Data blocks in one extent are contiguous, just account for partial
+	 * clusters at extent boundaries
+	 */
+	return blocks + 2*(EXT4_SB(inode->i_sb)->s_cluster_ratio - 1);
+}
+
 /*
  * This function controls whether or not we should try to go down the
  * dioread_nolock code paths, which makes it safe to avoid taking
- * i_mutex for direct I/O reads.  This only works for extent-based
+ * i_rwsem for direct I/O reads.  This only works for extent-based
  * files, and it doesn't work if data journaling is enabled, since the
  * dioread_nolock code uses b_private to pass information back to the
  * I/O completion handler, and this conflicts with the jbd's use of
@@ -448,7 +423,39 @@ static inline int ext4_should_dioread_nolock(struct inode *inode)
 		return 0;
 	if (ext4_should_journal_data(inode))
 		return 0;
+	/* temporary fix to prevent generic/422 test failures */
+	if (!test_opt(inode->i_sb, DELALLOC))
+		return 0;
 	return 1;
 }
 
+/*
+ * Pass journal explicitly as it may not be cached in the sbi->s_journal in some
+ * cases
+ */
+static inline int ext4_journal_destroy(struct ext4_sb_info *sbi, journal_t *journal)
+{
+	int err = 0;
+
+	/*
+	 * At this point only two things can be operating on the journal.
+	 * JBD2 thread performing transaction commit and s_sb_upd_work
+	 * issuing sb update through the journal. Once we set
+	 * EXT4_JOURNAL_DESTROY, new ext4_handle_error() calls will not
+	 * queue s_sb_upd_work and ext4_force_commit() makes sure any
+	 * ext4_handle_error() calls from the running transaction commit are
+	 * finished. Hence no new s_sb_upd_work can be queued after we
+	 * flush it here.
+	 */
+	ext4_set_mount_flag(sbi->s_sb, EXT4_MF_JOURNAL_DESTROY);
+
+	ext4_force_commit(sbi->s_sb);
+	flush_work(&sbi->s_sb_upd_work);
+
+	err = jbd2_journal_destroy(journal);
+	sbi->s_journal = NULL;
+
+	return err;
+}
+
 #endif	/* _EXT4_JBD2_H */