Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4

Pull ext4 updates from Ted Ts'o:
 "This merge window saw the the following new featuers added to ext4:

   - Direct I/O via iomap (required the iomap-for-next branch from
     Darrick as a prereq).

   - Support for using dioread-nolock where the block size < page size.

   - Support for encryption for file systems where the block size < page
     size.

   - Rework of journal credits handling so a revoke-heavy workload will
     not cause the journal to run out of space.

   - Replace bit-spinlocks with spinlocks in jbd2

  Also included were some bug fixes and cleanups, mostly to clean up
  corner cases from fuzzed file systems and error path handling"

* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (59 commits)
  ext4: work around deleting a file with i_nlink == 0 safely
  ext4: add more paranoia checking in ext4_expand_extra_isize handling
  jbd2: make jbd2_handle_buffer_credits() handle reserved handles
  ext4: fix a bug in ext4_wait_for_tail_page_commit
  ext4: bio_alloc with __GFP_DIRECT_RECLAIM never fails
  ext4: code cleanup for get_next_id
  ext4: fix leak of quota reservations
  ext4: remove unused variable warning in parse_options()
  ext4: Enable encryption for subpage-sized blocks
  fs/buffer.c: support fscrypt in block_read_full_page()
  ext4: Add error handling for io_end_vec struct allocation
  jbd2: Fine tune estimate of necessary descriptor blocks
  jbd2: Provide trace event for handle restarts
  ext4: Reserve revoke credits for freed blocks
  jbd2: Make credit checking more strict
  jbd2: Rename h_buffer_credits to h_total_credits
  jbd2: Reserve space for revoke descriptor blocks
  jbd2: Drop jbd2_space_needed()
  jbd2: Account descriptor blocks into t_outstanding_credits
  jbd2: Factor out common parts of stopping and restarting a handle
  ...

4 files changed, 94 insertions, 74 deletions

diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index 564793c24d12..29dce6ff6bae 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -313,7 +313,6 @@ 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 	BH_Revoked,		/* Has been revoked from the log */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 */
@@ -342,26 +341,6 @@ static inline struct journal_head *bh2jh(struct buffer_head *bh)
 	return bh->b_private;
 }
 
-static inline void jbd_lock_bh_state(struct buffer_head *bh)
-{
-	bit_spin_lock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_trylock_bh_state(struct buffer_head *bh)
-{
-	return bit_spin_trylock(BH_State, &bh->b_state);
-}
-
-static inline int jbd_is_locked_bh_state(struct buffer_head *bh)
-{
-	return bit_spin_is_locked(BH_State, &bh->b_state);
-}
-
-static inline void jbd_unlock_bh_state(struct buffer_head *bh)
-{
-	bit_spin_unlock(BH_State, &bh->b_state);
-}
-
 static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
 {
 	bit_spin_lock(BH_JournalHead, &bh->b_state);
@@ -477,7 +456,9 @@ struct jbd2_revoke_table_s;
  * @h_transaction: Which compound transaction is this update a part of?
  * @h_journal: Which journal handle belongs to - used iff h_reserved set.
  * @h_rsv_handle: Handle reserved for finishing the logical operation.
- * @h_buffer_credits: Number of remaining buffers we are allowed to dirty.
+ * @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.
@@ -487,7 +468,8 @@ struct jbd2_revoke_table_s;
  * @h_type: For handle statistics.
  * @h_line_no: For handle statistics.
  * @h_start_jiffies: Handle Start time.
- * @h_requested_credits: Holds @h_buffer_credits after handle is started.
+ * @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.
  **/
 
@@ -504,7 +486,9 @@ struct jbd2_journal_handle
 	};
 
 	handle_t		*h_rsv_handle;
-	int			h_buffer_credits;
+	int			h_total_credits;
+	int			h_revoke_credits;
+	int			h_revoke_credits_requested;
 	int			h_ref;
 	int			h_err;
 
@@ -556,9 +540,9 @@ 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
@@ -681,12 +665,25 @@ struct transaction_s
 	atomic_t		t_updates;
 
 	/*
-	 * Number of buffers reserved for use by all handles in this transaction
-	 * handle but not yet modified. [none]
+	 * 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]
 	 */
@@ -704,11 +701,6 @@ struct transaction_s
 	ktime_t			t_start_time;
 
 	/*
-	 * How many handles used this transaction? [none]
-	 */
-	atomic_t		t_handle_count;
-
-	/*
 	 * This transaction is being forced and some process is
 	 * waiting for it to finish.
 	 */
@@ -1025,6 +1017,13 @@ struct journal_s
 	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_commit_interval:
 	 *
 	 * What is the maximum transaction lifetime before we begin a commit?
@@ -1257,7 +1256,7 @@ JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
 
 /* 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);
@@ -1358,14 +1357,16 @@ 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 *);
@@ -1561,37 +1562,18 @@ static inline int jbd2_journal_has_csum_v2or3(journal_t *journal)
 }
 
 /*
- * We reserve t_outstanding_credits >> JBD2_CONTROL_BLOCKS_SHIFT for
- * transaction control blocks.
- */
-#define JBD2_CONTROL_BLOCKS_SHIFT 5
-
-/*
- * 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)
-{
-	int nblocks = journal->j_max_transaction_buffers;
-	return nblocks + (nblocks >> JBD2_CONTROL_BLOCKS_SHIFT);
-}
-
-/*
  * Return number of free blocks in the log. Must be called under j_state_lock.
  */
 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);
 }
 
 /*
@@ -1645,6 +1627,20 @@ 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)
diff --git a/include/linux/journal-head.h b/include/linux/journal-head.h
index 9fb870524314..75bc56109031 100644
--- a/include/linux/journal-head.h
+++ b/include/linux/journal-head.h
@@ -11,6 +11,8 @@
 #ifndef JOURNAL_HEAD_H_INCLUDED
 #define JOURNAL_HEAD_H_INCLUDED
 
+#include <linux/spinlock.h>
+
 typedef unsigned int		tid_t;		/* Unique transaction ID */
 typedef struct transaction_s	transaction_t;	/* Compound transaction type */
 
@@ -24,13 +26,18 @@ struct journal_head {
 	struct buffer_head *b_bh;
 
 	/*
+	 * Protect the buffer head state
+	 */
+	spinlock_t b_state_lock;
+
+	/*
 	 * Reference count - see description in journal.c
 	 * [jbd_lock_bh_journal_head()]
 	 */
 	int b_jcount;
 
 	/*
-	 * Journalling list for this buffer [jbd_lock_bh_state()]
+	 * Journalling list for this buffer [b_state_lock]
 	 * NOTE: We *cannot* combine this with b_modified into a bitfield
 	 * as gcc would then (which the C standard allows but which is
 	 * very unuseful) make 64-bit accesses to the bitfield and clobber
@@ -41,20 +48,20 @@ struct journal_head {
 	/*
 	 * This flag signals the buffer has been modified by
 	 * the currently running transaction
-	 * [jbd_lock_bh_state()]
+	 * [b_state_lock]
 	 */
 	unsigned b_modified;
 
 	/*
 	 * Copy of the buffer data frozen for writing to the log.
-	 * [jbd_lock_bh_state()]
+	 * [b_state_lock]
 	 */
 	char *b_frozen_data;
 
 	/*
 	 * Pointer to a saved copy of the buffer containing no uncommitted
 	 * deallocation references, so that allocations can avoid overwriting
-	 * uncommitted deletes. [jbd_lock_bh_state()]
+	 * uncommitted deletes. [b_state_lock]
 	 */
 	char *b_committed_data;
 
@@ -63,7 +70,7 @@ struct journal_head {
 	 * metadata: either the running transaction or the committing
 	 * transaction (if there is one).  Only applies to buffers on a
 	 * transaction's data or metadata journaling list.
-	 * [j_list_lock] [jbd_lock_bh_state()]
+	 * [j_list_lock] [b_state_lock]
 	 * Either of these locks is enough for reading, both are needed for
 	 * changes.
 	 */
@@ -73,13 +80,13 @@ struct journal_head {
 	 * Pointer to the running compound transaction which is currently
 	 * modifying the buffer's metadata, if there was already a transaction
 	 * committing it when the new transaction touched it.
-	 * [t_list_lock] [jbd_lock_bh_state()]
+	 * [t_list_lock] [b_state_lock]
 	 */
 	transaction_t *b_next_transaction;
 
 	/*
 	 * Doubly-linked list of buffers on a transaction's data, metadata or
-	 * forget queue. [t_list_lock] [jbd_lock_bh_state()]
+	 * forget queue. [t_list_lock] [b_state_lock]
 	 */
 	struct journal_head *b_tnext, *b_tprev;
 
diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h
index d68e9e536814..182c9fe9c0e9 100644
--- a/include/trace/events/ext4.h
+++ b/include/trace/events/ext4.h
@@ -1746,15 +1746,16 @@ TRACE_EVENT(ext4_load_inode,
 
 TRACE_EVENT(ext4_journal_start,
 	TP_PROTO(struct super_block *sb, int blocks, int rsv_blocks,
-		 unsigned long IP),
+		 int revoke_creds, unsigned long IP),
 
-	TP_ARGS(sb, blocks, rsv_blocks, IP),
+	TP_ARGS(sb, blocks, rsv_blocks, revoke_creds, IP),
 
 	TP_STRUCT__entry(
 		__field(	dev_t,	dev			)
 		__field(unsigned long,	ip			)
 		__field(	  int,	blocks			)
 		__field(	  int,	rsv_blocks		)
+		__field(	  int,	revoke_creds		)
 	),
 
 	TP_fast_assign(
@@ -1762,11 +1763,13 @@ TRACE_EVENT(ext4_journal_start,
 		__entry->ip		 = IP;
 		__entry->blocks		 = blocks;
 		__entry->rsv_blocks	 = rsv_blocks;
+		__entry->revoke_creds	 = revoke_creds;
 	),
 
-	TP_printk("dev %d,%d blocks, %d rsv_blocks, %d caller %pS",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->blocks, __entry->rsv_blocks, (void *)__entry->ip)
+	TP_printk("dev %d,%d blocks %d, rsv_blocks %d, revoke_creds %d, "
+		  "caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev),
+		  __entry->blocks, __entry->rsv_blocks, __entry->revoke_creds,
+		  (void *)__entry->ip)
 );
 
 TRACE_EVENT(ext4_journal_start_reserved,
diff --git a/include/trace/events/jbd2.h b/include/trace/events/jbd2.h
index 2310b259329f..d16a32867f3a 100644
--- a/include/trace/events/jbd2.h
+++ b/include/trace/events/jbd2.h
@@ -133,7 +133,7 @@ TRACE_EVENT(jbd2_submit_inode_data,
 		  (unsigned long) __entry->ino)
 );
 
-TRACE_EVENT(jbd2_handle_start,
+DECLARE_EVENT_CLASS(jbd2_handle_start_class,
 	TP_PROTO(dev_t dev, unsigned long tid, unsigned int type,
 		 unsigned int line_no, int requested_blocks),
 
@@ -161,6 +161,20 @@ TRACE_EVENT(jbd2_handle_start,
 		  __entry->type, __entry->line_no, __entry->requested_blocks)
 );
 
+DEFINE_EVENT(jbd2_handle_start_class, jbd2_handle_start,
+	TP_PROTO(dev_t dev, unsigned long tid, unsigned int type,
+		 unsigned int line_no, int requested_blocks),
+
+	TP_ARGS(dev, tid, type, line_no, requested_blocks)
+);
+
+DEFINE_EVENT(jbd2_handle_start_class, jbd2_handle_restart,
+	TP_PROTO(dev_t dev, unsigned long tid, unsigned int type,
+		 unsigned int line_no, int requested_blocks),
+
+	TP_ARGS(dev, tid, type, line_no, requested_blocks)
+);
+
 TRACE_EVENT(jbd2_handle_extend,
 	TP_PROTO(dev_t dev, unsigned long tid, unsigned int type,
 		 unsigned int line_no, int buffer_credits,