Merge tag 'xfs-5.19-for-linus' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull xfs updates from Dave Chinner:
 "This is a big update with lots of new code. The summary below them
  all, so I'll just touch on teh higlights. The two main new features
  are Large Extent Counts and Logged Attribute Replay - these are two
  new foundational features that we are building more complex future
  features on top of.

  For upcoming functionality, we need to be able to store hundreds of
  millions of xattrs per inode. The Large Extent Count feature removes
  the limits that prevent this scale of xattr storage, and while we were
  modifying the on disk extent count format we also increased the number
  of data extents we support per inode from 2^32 to 2^47.

  We also need to be able to modify xattrs as part of larger atomic
  transactions rather than as standalone transactions. The Logged
  Attribute Replay feature introduces the infrastructure that allows us
  to use intents to record the attribute modifications in the journal
  before we start them, hence allowing other atomic transactions to log
  attribute modification intents and then defer the actual modification
  to later. If we then crash, log recovery then guarantees that the
  attribute is replayed in the context of the atomic transaction that
  logged the intent.

  A significant chunk of the commits in this merge are for the base
  attribute replay functionality along with fixes, improvements and
  cleanups related to this new functioanlity. Allison deserves a big
  round of thanks for her ongoing work to get this functionality into
  XFS.

  There are also many other smaller changes and improvements, so overall
  this is one of the bigger XFS merge requests in some time.

  I will be following up next week with another smaller pull request -
  we already have another round of fixes and improvements to the logged
  attribute replay functionality just about ready to go. They'll soak
  and test over the next week, and I'll send a pull request for them
  near the end of the merge window.

  Summary:

   - support for printk message indexing.

   - large extent counts to provide support for up to 2^47 data extents
     and 2^32 attribute extents, allowing us to scale beyond 4 billion
     data extents to billions of xattrs per inode.

   - conversion of various flags fields to be consistently declared as
     unsigned bit fields.

   - improvements to realtime extent accounting and converts them to
     per-cpu counters to match all the other block and inode accounting.

   - reworks core log formatting code to reduce iterations, have a
     shorter, cleaner fast path and generally be easier to understand
     and maintain.

   - improvements to rmap btree searches that reduce overhead by up to
     30% resulting in xfs_scrub runtime reductions of 15%.

   - improvements to reflink that remove the size limitations in
     remapping operations and greatly reduce the size of transaction
     reservations.

   - reworks the minimum log size calculations to allow us to change
     transaction reservations without changing the minimum supported log
     size.

   - removal of quota warning support as it has never been used on
     Linux.

   - intent whiteouts to allow us to cancel intents that are completed
     entirely in memory rather than having use CPU and disk bandwidth
     formatting and writing them into the journal when it is not
     necessary. This makes rmap, reflink and extent freeing slightly
     more efficient, but provides massive improvements for....

   - Logged Attribute Replay feature support. This is a fundamental
     change to the way we modify attributes, laying the foundation for
     future integration of attribute modifications as part of other
     atomic transactional operations the filesystem performs.

   - Lots of cleanups and fixes for the logged attribute replay
     functionality"

* tag 'xfs-5.19-for-linus' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (124 commits)
  xfs: can't use kmem_zalloc() for attribute buffers
  xfs: detect empty attr leaf blocks in xfs_attr3_leaf_verify
  xfs: ATTR_REPLACE algorithm with LARP enabled needs rework
  xfs: use XFS_DA_OP flags in deferred attr ops
  xfs: remove xfs_attri_remove_iter
  xfs: switch attr remove to xfs_attri_set_iter
  xfs: introduce attr remove initial states into xfs_attr_set_iter
  xfs: xfs_attr_set_iter() does not need to return EAGAIN
  xfs: clean up final attr removal in xfs_attr_set_iter
  xfs: remote xattr removal in xfs_attr_set_iter() is conditional
  xfs: XFS_DAS_LEAF_REPLACE state only needed if !LARP
  xfs: split remote attr setting out from replace path
  xfs: consolidate leaf/node states in xfs_attr_set_iter
  xfs: kill XFS_DAC_LEAF_ADDNAME_INIT
  xfs: separate out initial attr_set states
  xfs: don't set quota warning values
  xfs: remove warning counters from struct xfs_dquot_res
  xfs: remove quota warning limit from struct xfs_quota_limits
  xfs: rework deferred attribute operation setup
  xfs: make xattri_leaf_bp more useful
  ...

fs/xfs/Makefile

@@ -102,6 +102,7 @@ xfs-y				+= xfs_log.o \
 				   xfs_buf_item_recover.o \
 				   xfs_dquot_item_recover.o \
 				   xfs_extfree_item.o \
+				   xfs_attr_item.o \
 				   xfs_icreate_item.o \
 				   xfs_inode_item.o \
 				   xfs_inode_item_recover.o \

fs/xfs/libxfs/xfs_alloc.c

@@ -2511,7 +2511,7 @@ __xfs_free_extent_later(
 
 	ASSERT(bno != NULLFSBLOCK);
 	ASSERT(len > 0);
-	ASSERT(len <= MAXEXTLEN);
+	ASSERT(len <= XFS_MAX_BMBT_EXTLEN);
 	ASSERT(!isnullstartblock(bno));
 	agno = XFS_FSB_TO_AGNO(mp, bno);
 	agbno = XFS_FSB_TO_AGBNO(mp, bno);
@@ -2777,7 +2777,7 @@ xfs_alloc_get_freelist(
 	xfs_agblock_t		bno;
 	__be32			*agfl_bno;
 	int			error;
-	int			logflags;
+	uint32_t		logflags;
 	struct xfs_mount	*mp = tp->t_mountp;
 	struct xfs_perag	*pag;
 
@@ -2830,9 +2830,9 @@ xfs_alloc_get_freelist(
  */
 void
 xfs_alloc_log_agf(
-	xfs_trans_t	*tp,	/* transaction pointer */
-	struct xfs_buf	*bp,	/* buffer for a.g. freelist header */
-	int		fields)	/* mask of fields to be logged (XFS_AGF_...) */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
+	uint32_t		fields)
 {
 	int	first;		/* first byte offset */
 	int	last;		/* last byte offset */
@@ -2902,7 +2902,7 @@ xfs_alloc_put_freelist(
 	struct xfs_perag	*pag;
 	__be32			*blockp;
 	int			error;
-	int			logflags;
+	uint32_t		logflags;
 	__be32			*agfl_bno;
 	int			startoff;
 

fs/xfs/libxfs/xfs_alloc.h

@@ -121,7 +121,7 @@ void
 xfs_alloc_log_agf(
 	struct xfs_trans *tp,	/* transaction pointer */
 	struct xfs_buf	*bp,	/* buffer for a.g. freelist header */
-	int		fields);/* mask of fields to be logged (XFS_AGF_...) */
+	uint32_t	fields);/* mask of fields to be logged (XFS_AGF_...) */
 
 /*
  * Interface for inode allocation to force the pag data to be initialized.

fs/xfs/libxfs/xfs_attr.h

@@ -28,6 +28,15 @@ struct xfs_attr_list_context;
  */
 #define	ATTR_MAX_VALUELEN	(64*1024)	/* max length of a value */
 
+static inline bool xfs_has_larp(struct xfs_mount *mp)
+{
+#ifdef DEBUG
+	return xfs_globals.larp;
+#else
+	return false;
+#endif
+}
+
 /*
  * Kernel-internal version of the attrlist cursor.
  */
@@ -425,7 +434,7 @@ struct xfs_attr_list_context {
  */
 
 /*
- * Enum values for xfs_delattr_context.da_state
+ * Enum values for xfs_attr_item.xattri_da_state
  *
  * These values are used by delayed attribute operations to keep track  of where
  * they were before they returned -EAGAIN.  A return code of -EAGAIN signals the
@@ -434,46 +443,105 @@ struct xfs_attr_list_context {
  * to where it was and resume executing where it left off.
  */
 enum xfs_delattr_state {
-	XFS_DAS_UNINIT		= 0,  /* No state has been set yet */
-	XFS_DAS_RMTBLK,		      /* Removing remote blks */
-	XFS_DAS_RM_NAME,	      /* Remove attr name */
-	XFS_DAS_RM_SHRINK,	      /* We are shrinking the tree */
-	XFS_DAS_FOUND_LBLK,	      /* We found leaf blk for attr */
-	XFS_DAS_FOUND_NBLK,	      /* We found node blk for attr */
-	XFS_DAS_FLIP_LFLAG,	      /* Flipped leaf INCOMPLETE attr flag */
-	XFS_DAS_RM_LBLK,	      /* A rename is removing leaf blocks */
-	XFS_DAS_RD_LEAF,	      /* Read in the new leaf */
-	XFS_DAS_ALLOC_NODE,	      /* We are allocating node blocks */
-	XFS_DAS_FLIP_NFLAG,	      /* Flipped node INCOMPLETE attr flag */
-	XFS_DAS_RM_NBLK,	      /* A rename is removing node blocks */
-	XFS_DAS_CLR_FLAG,	      /* Clear incomplete flag */
+	XFS_DAS_UNINIT		= 0,	/* No state has been set yet */
+
+	/*
+	 * Initial sequence states. The replace setup code relies on the
+	 * ADD and REMOVE states for a specific format to be sequential so
+	 * that we can transform the initial operation to be performed
+	 * according to the xfs_has_larp() state easily.
+	 */
+	XFS_DAS_SF_ADD,			/* Initial sf add state */
+	XFS_DAS_SF_REMOVE,		/* Initial sf replace/remove state */
+
+	XFS_DAS_LEAF_ADD,		/* Initial leaf add state */
+	XFS_DAS_LEAF_REMOVE,		/* Initial leaf replace/remove state */
+
+	XFS_DAS_NODE_ADD,		/* Initial node add state */
+	XFS_DAS_NODE_REMOVE,		/* Initial node replace/remove state */
+
+	/* Leaf state set/replace/remove sequence */
+	XFS_DAS_LEAF_SET_RMT,		/* set a remote xattr from a leaf */
+	XFS_DAS_LEAF_ALLOC_RMT,		/* We are allocating remote blocks */
+	XFS_DAS_LEAF_REPLACE,		/* Perform replace ops on a leaf */
+	XFS_DAS_LEAF_REMOVE_OLD,	/* Start removing old attr from leaf */
+	XFS_DAS_LEAF_REMOVE_RMT,	/* A rename is removing remote blocks */
+	XFS_DAS_LEAF_REMOVE_ATTR,	/* Remove the old attr from a leaf */
+
+	/* Node state sequence, must match leaf state above */
+	XFS_DAS_NODE_SET_RMT,		/* set a remote xattr from a node */
+	XFS_DAS_NODE_ALLOC_RMT,		/* We are allocating remote blocks */
+	XFS_DAS_NODE_REPLACE,		/* Perform replace ops on a node */
+	XFS_DAS_NODE_REMOVE_OLD,	/* Start removing old attr from node */
+	XFS_DAS_NODE_REMOVE_RMT,	/* A rename is removing remote blocks */
+	XFS_DAS_NODE_REMOVE_ATTR,	/* Remove the old attr from a node */
+
+	XFS_DAS_DONE,			/* finished operation */
 };
 
+#define XFS_DAS_STRINGS	\
+	{ XFS_DAS_UNINIT,		"XFS_DAS_UNINIT" }, \
+	{ XFS_DAS_SF_ADD,		"XFS_DAS_SF_ADD" }, \
+	{ XFS_DAS_SF_REMOVE,		"XFS_DAS_SF_REMOVE" }, \
+	{ XFS_DAS_LEAF_ADD,		"XFS_DAS_LEAF_ADD" }, \
+	{ XFS_DAS_LEAF_REMOVE,		"XFS_DAS_LEAF_REMOVE" }, \
+	{ XFS_DAS_NODE_ADD,		"XFS_DAS_NODE_ADD" }, \
+	{ XFS_DAS_NODE_REMOVE,		"XFS_DAS_NODE_REMOVE" }, \
+	{ XFS_DAS_LEAF_SET_RMT,		"XFS_DAS_LEAF_SET_RMT" }, \
+	{ XFS_DAS_LEAF_ALLOC_RMT,	"XFS_DAS_LEAF_ALLOC_RMT" }, \
+	{ XFS_DAS_LEAF_REPLACE,		"XFS_DAS_LEAF_REPLACE" }, \
+	{ XFS_DAS_LEAF_REMOVE_OLD,	"XFS_DAS_LEAF_REMOVE_OLD" }, \
+	{ XFS_DAS_LEAF_REMOVE_RMT,	"XFS_DAS_LEAF_REMOVE_RMT" }, \
+	{ XFS_DAS_LEAF_REMOVE_ATTR,	"XFS_DAS_LEAF_REMOVE_ATTR" }, \
+	{ XFS_DAS_NODE_SET_RMT,		"XFS_DAS_NODE_SET_RMT" }, \
+	{ XFS_DAS_NODE_ALLOC_RMT,	"XFS_DAS_NODE_ALLOC_RMT" },  \
+	{ XFS_DAS_NODE_REPLACE,		"XFS_DAS_NODE_REPLACE" },  \
+	{ XFS_DAS_NODE_REMOVE_OLD,	"XFS_DAS_NODE_REMOVE_OLD" }, \
+	{ XFS_DAS_NODE_REMOVE_RMT,	"XFS_DAS_NODE_REMOVE_RMT" }, \
+	{ XFS_DAS_NODE_REMOVE_ATTR,	"XFS_DAS_NODE_REMOVE_ATTR" }, \
+	{ XFS_DAS_DONE,			"XFS_DAS_DONE" }
+
 /*
- * Defines for xfs_delattr_context.flags
+ * Defines for xfs_attr_item.xattri_flags
  */
-#define XFS_DAC_DEFER_FINISH		0x01 /* finish the transaction */
-#define XFS_DAC_LEAF_ADDNAME_INIT	0x02 /* xfs_attr_leaf_addname init*/
+#define XFS_DAC_LEAF_ADDNAME_INIT	0x01 /* xfs_attr_leaf_addname init*/
 
 /*
  * Context used for keeping track of delayed attribute operations
  */
-struct xfs_delattr_context {
-	struct xfs_da_args      *da_args;
+struct xfs_attr_item {
+	struct xfs_da_args		*xattri_da_args;
+
+	/*
+	 * Used by xfs_attr_set to hold a leaf buffer across a transaction roll
+	 */
+	struct xfs_buf			*xattri_leaf_bp;
 
 	/* Used in xfs_attr_rmtval_set_blk to roll through allocating blocks */
-	struct xfs_bmbt_irec	map;
-	xfs_dablk_t		lblkno;
-	int			blkcnt;
+	struct xfs_bmbt_irec		xattri_map;
+	xfs_dablk_t			xattri_lblkno;
+	int				xattri_blkcnt;
 
 	/* Used in xfs_attr_node_removename to roll through removing blocks */
-	struct xfs_da_state     *da_state;
+	struct xfs_da_state		*xattri_da_state;
 
 	/* Used to keep track of current state of delayed operation */
-	unsigned int            flags;
-	enum xfs_delattr_state  dela_state;
+	unsigned int			xattri_flags;
+	enum xfs_delattr_state		xattri_dela_state;
+
+	/*
+	 * Attr operation being performed - XFS_ATTR_OP_FLAGS_*
+	 */
+	unsigned int			xattri_op_flags;
+
+	/*
+	 * used to log this item to an intent containing a list of attrs to
+	 * commit later
+	 */
+	struct list_head		xattri_list;
 };
 
+
 /*========================================================================
  * Function prototypes for the kernel.
  *========================================================================*/
@@ -489,11 +557,81 @@ bool xfs_attr_is_leaf(struct xfs_inode *ip);
 int xfs_attr_get_ilocked(struct xfs_da_args *args);
 int xfs_attr_get(struct xfs_da_args *args);
 int xfs_attr_set(struct xfs_da_args *args);
-int xfs_attr_set_args(struct xfs_da_args *args);
-int xfs_attr_remove_args(struct xfs_da_args *args);
-int xfs_attr_remove_iter(struct xfs_delattr_context *dac);
+int xfs_attr_set_iter(struct xfs_attr_item *attr);
+int xfs_attr_remove_iter(struct xfs_attr_item *attr);
 bool xfs_attr_namecheck(const void *name, size_t length);
-void xfs_delattr_context_init(struct xfs_delattr_context *dac,
-			      struct xfs_da_args *args);
+int xfs_attr_calc_size(struct xfs_da_args *args, int *local);
+void xfs_init_attr_trans(struct xfs_da_args *args, struct xfs_trans_res *tres,
+			 unsigned int *total);
+
+extern struct kmem_cache	*xfs_attri_cache;
+extern struct kmem_cache	*xfs_attrd_cache;
+
+int __init xfs_attri_init_cache(void);
+void xfs_attri_destroy_cache(void);
+int __init xfs_attrd_init_cache(void);
+void xfs_attrd_destroy_cache(void);
+
+/*
+ * Check to see if the attr should be upgraded from non-existent or shortform to
+ * single-leaf-block attribute list.
+ */
+static inline bool
+xfs_attr_is_shortform(
+	struct xfs_inode    *ip)
+{
+	return ip->i_afp->if_format == XFS_DINODE_FMT_LOCAL ||
+	       (ip->i_afp->if_format == XFS_DINODE_FMT_EXTENTS &&
+		ip->i_afp->if_nextents == 0);
+}
+
+static inline enum xfs_delattr_state
+xfs_attr_init_add_state(struct xfs_da_args *args)
+{
+	/*
+	 * When called from the completion of a attr remove to determine the
+	 * next state, the attribute fork may be null. This can occur only occur
+	 * on a pure remove, but we grab the next state before we check if a
+	 * replace operation is being performed. If we are called from any other
+	 * context, i_afp is guaranteed to exist. Hence if the attr fork is
+	 * null, we were called from a pure remove operation and so we are done.
+	 */
+	if (!args->dp->i_afp)
+		return XFS_DAS_DONE;
+
+	args->op_flags |= XFS_DA_OP_ADDNAME;
+	if (xfs_attr_is_shortform(args->dp))
+		return XFS_DAS_SF_ADD;
+	if (xfs_attr_is_leaf(args->dp))
+		return XFS_DAS_LEAF_ADD;
+	return XFS_DAS_NODE_ADD;
+}
+
+static inline enum xfs_delattr_state
+xfs_attr_init_remove_state(struct xfs_da_args *args)
+{
+	args->op_flags |= XFS_DA_OP_REMOVE;
+	if (xfs_attr_is_shortform(args->dp))
+		return XFS_DAS_SF_REMOVE;
+	if (xfs_attr_is_leaf(args->dp))
+		return XFS_DAS_LEAF_REMOVE;
+	return XFS_DAS_NODE_REMOVE;
+}
+
+/*
+ * If we are logging the attributes, then we have to start with removal of the
+ * old attribute so that there is always consistent state that we can recover
+ * from if the system goes down part way through. We always log the new attr
+ * value, so even when we remove the attr first we still have the information in
+ * the log to finish the replace operation atomically.
+ */
+static inline enum xfs_delattr_state
+xfs_attr_init_replace_state(struct xfs_da_args *args)
+{
+	args->op_flags |= XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE;
+	if (xfs_has_larp(args->dp->i_mount))
+		return xfs_attr_init_remove_state(args);
+	return xfs_attr_init_add_state(args);
+}
 
 #endif	/* __XFS_ATTR_H__ */

fs/xfs/libxfs/xfs_attr_leaf.c

@@ -28,6 +28,7 @@
 #include "xfs_dir2.h"
 #include "xfs_log.h"
 #include "xfs_ag.h"
+#include "xfs_errortag.h"
 
 
 /*
@@ -309,6 +310,15 @@ xfs_attr3_leaf_verify(
 	if (fa)
 		return fa;
 
+	/*
+	 * Empty leaf blocks should never occur;  they imply the existence of a
+	 * software bug that needs fixing. xfs_repair also flags them as a
+	 * corruption that needs fixing, so we should never let these go to
+	 * disk.
+	 */
+	if (ichdr.count == 0)
+		return __this_address;
+
 	/*
 	 * firstused is the block offset of the first name info structure.
 	 * Make sure it doesn't go off the block or crash into the header.
@@ -445,6 +455,14 @@ xfs_attr3_leaf_read(
  * Namespace helper routines
  *========================================================================*/
 
+/*
+ * If we are in log recovery, then we want the lookup to ignore the INCOMPLETE
+ * flag on disk - if there's an incomplete attr then recovery needs to tear it
+ * down. If there's no incomplete attr, then recovery needs to tear that attr
+ * down to replace it with the attr that has been logged. In this case, the
+ * INCOMPLETE flag will not be set in attr->attr_filter, but rather
+ * XFS_DA_OP_RECOVERY will be set in args->op_flags.
+ */
 static bool
 xfs_attr_match(
 	struct xfs_da_args	*args,
@@ -452,14 +470,18 @@ xfs_attr_match(
 	unsigned char		*name,
 	int			flags)
 {
+
 	if (args->namelen != namelen)
 		return false;
 	if (memcmp(args->name, name, namelen) != 0)
 		return false;
-	/*
-	 * If we are looking for incomplete entries, show only those, else only
-	 * show complete entries.
-	 */
+
+	/* Recovery ignores the INCOMPLETE flag. */
+	if ((args->op_flags & XFS_DA_OP_RECOVERY) &&
+	    args->attr_filter == (flags & XFS_ATTR_NSP_ONDISK_MASK))
+		return true;
+
+	/* All remaining matches need to be filtered by INCOMPLETE state. */
 	if (args->attr_filter !=
 	    (flags & (XFS_ATTR_NSP_ONDISK_MASK | XFS_ATTR_INCOMPLETE)))
 		return false;
@@ -798,6 +820,14 @@ xfs_attr_sf_removename(
 	sf = (struct xfs_attr_shortform *)dp->i_afp->if_u1.if_data;
 
 	error = xfs_attr_sf_findname(args, &sfe, &base);
+
+	/*
+	 * If we are recovering an operation, finding nothing to
+	 * remove is not an error - it just means there was nothing
+	 * to clean up.
+	 */
+	if (error == -ENOATTR && (args->op_flags & XFS_DA_OP_RECOVERY))
+		return 0;
 	if (error != -EEXIST)
 		return error;
 	size = xfs_attr_sf_entsize(sfe);
@@ -818,7 +848,7 @@ xfs_attr_sf_removename(
 	totsize -= size;
 	if (totsize == sizeof(xfs_attr_sf_hdr_t) && xfs_has_attr2(mp) &&
 	    (dp->i_df.if_format != XFS_DINODE_FMT_BTREE) &&
-	    !(args->op_flags & XFS_DA_OP_ADDNAME)) {
+	    !(args->op_flags & (XFS_DA_OP_ADDNAME | XFS_DA_OP_REPLACE))) {
 		xfs_attr_fork_remove(dp, args->trans);
 	} else {
 		xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
@@ -1127,9 +1157,17 @@ xfs_attr3_leaf_to_shortform(
 		goto out;
 
 	if (forkoff == -1) {
-		ASSERT(xfs_has_attr2(dp->i_mount));
-		ASSERT(dp->i_df.if_format != XFS_DINODE_FMT_BTREE);
-		xfs_attr_fork_remove(dp, args->trans);
+		/*
+		 * Don't remove the attr fork if this operation is the first
+		 * part of a attr replace operations. We're going to add a new
+		 * attr immediately, so we need to keep the attr fork around in
+		 * this case.
+		 */
+		if (!(args->op_flags & XFS_DA_OP_REPLACE)) {
+			ASSERT(xfs_has_attr2(dp->i_mount));
+			ASSERT(dp->i_df.if_format != XFS_DINODE_FMT_BTREE);
+			xfs_attr_fork_remove(dp, args->trans);
+		}
 		goto out;
 	}
 
@@ -1189,6 +1227,11 @@ xfs_attr3_leaf_to_node(
 
 	trace_xfs_attr_leaf_to_node(args);
 
+	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_ATTR_LEAF_TO_NODE)) {
+		error = -EIO;
+		goto out;
+	}
+
 	error = xfs_da_grow_inode(args, &blkno);
 	if (error)
 		goto out;
@@ -1486,8 +1529,9 @@ xfs_attr3_leaf_add_work(
 	entry->flags = args->attr_filter;
 	if (tmp)
 		entry->flags |= XFS_ATTR_LOCAL;
-	if (args->op_flags & XFS_DA_OP_RENAME) {
-		entry->flags |= XFS_ATTR_INCOMPLETE;
+	if (args->op_flags & XFS_DA_OP_REPLACE) {
+		if (!xfs_has_larp(mp))
+			entry->flags |= XFS_ATTR_INCOMPLETE;
 		if ((args->blkno2 == args->blkno) &&
 		    (args->index2 <= args->index)) {
 			args->index2++;

fs/xfs/libxfs/xfs_attr_remote.c

@@ -568,14 +568,14 @@ xfs_attr_rmtval_stale(
  */
 int
 xfs_attr_rmtval_find_space(
-	struct xfs_delattr_context	*dac)
+	struct xfs_attr_item		*attr)
 {
-	struct xfs_da_args		*args = dac->da_args;
-	struct xfs_bmbt_irec		*map = &dac->map;
+	struct xfs_da_args		*args = attr->xattri_da_args;
+	struct xfs_bmbt_irec		*map = &attr->xattri_map;
 	int				error;
 
-	dac->lblkno = 0;
-	dac->blkcnt = 0;
+	attr->xattri_lblkno = 0;
+	attr->xattri_blkcnt = 0;
 	args->rmtblkcnt = 0;
 	args->rmtblkno = 0;
 	memset(map, 0, sizeof(struct xfs_bmbt_irec));
@@ -584,8 +584,8 @@ xfs_attr_rmtval_find_space(
 	if (error)
 		return error;
 
-	dac->blkcnt = args->rmtblkcnt;
-	dac->lblkno = args->rmtblkno;
+	attr->xattri_blkcnt = args->rmtblkcnt;
+	attr->xattri_lblkno = args->rmtblkno;
 
 	return 0;
 }
@@ -598,17 +598,18 @@ xfs_attr_rmtval_find_space(
  */
 int
 xfs_attr_rmtval_set_blk(
-	struct xfs_delattr_context	*dac)
+	struct xfs_attr_item		*attr)
 {
-	struct xfs_da_args		*args = dac->da_args;
+	struct xfs_da_args		*args = attr->xattri_da_args;
 	struct xfs_inode		*dp = args->dp;
-	struct xfs_bmbt_irec		*map = &dac->map;
+	struct xfs_bmbt_irec		*map = &attr->xattri_map;
 	int nmap;
 	int error;
 
 	nmap = 1;
-	error = xfs_bmapi_write(args->trans, dp, (xfs_fileoff_t)dac->lblkno,
-			dac->blkcnt, XFS_BMAPI_ATTRFORK, args->total,
+	error = xfs_bmapi_write(args->trans, dp,
+			(xfs_fileoff_t)attr->xattri_lblkno,
+			attr->xattri_blkcnt, XFS_BMAPI_ATTRFORK, args->total,
 			map, &nmap);
 	if (error)
 		return error;
@@ -618,8 +619,8 @@ xfs_attr_rmtval_set_blk(
 	       (map->br_startblock != HOLESTARTBLOCK));
 
 	/* roll attribute extent map forwards */
-	dac->lblkno += map->br_blockcount;
-	dac->blkcnt -= map->br_blockcount;
+	attr->xattri_lblkno += map->br_blockcount;
+	attr->xattri_blkcnt -= map->br_blockcount;
 
 	return 0;
 }
@@ -673,9 +674,9 @@ xfs_attr_rmtval_invalidate(
  */
 int
 xfs_attr_rmtval_remove(
-	struct xfs_delattr_context	*dac)
+	struct xfs_attr_item		*attr)
 {
-	struct xfs_da_args		*args = dac->da_args;
+	struct xfs_da_args		*args = attr->xattri_da_args;
 	int				error, done;
 
 	/*
@@ -695,8 +696,8 @@ xfs_attr_rmtval_remove(
 	 * the parent
 	 */
 	if (!done) {
-		dac->flags |= XFS_DAC_DEFER_FINISH;
-		trace_xfs_attr_rmtval_remove_return(dac->dela_state, args->dp);
+		trace_xfs_attr_rmtval_remove_return(attr->xattri_dela_state,
+						    args->dp);
 		return -EAGAIN;
 	}
 

fs/xfs/libxfs/xfs_attr_remote.h

@@ -12,9 +12,9 @@ int xfs_attr_rmtval_get(struct xfs_da_args *args);
 int xfs_attr_rmtval_stale(struct xfs_inode *ip, struct xfs_bmbt_irec *map,
 		xfs_buf_flags_t incore_flags);
 int xfs_attr_rmtval_invalidate(struct xfs_da_args *args);
-int xfs_attr_rmtval_remove(struct xfs_delattr_context *dac);
+int xfs_attr_rmtval_remove(struct xfs_attr_item *attr);
 int xfs_attr_rmt_find_hole(struct xfs_da_args *args);
 int xfs_attr_rmtval_set_value(struct xfs_da_args *args);
-int xfs_attr_rmtval_set_blk(struct xfs_delattr_context *dac);
-int xfs_attr_rmtval_find_space(struct xfs_delattr_context *dac);
+int xfs_attr_rmtval_set_blk(struct xfs_attr_item *attr);
+int xfs_attr_rmtval_find_space(struct xfs_attr_item *attr);
 #endif /* __XFS_ATTR_REMOTE_H__ */

fs/xfs/libxfs/xfs_bmap.h

@@ -39,7 +39,7 @@ struct xfs_bmalloca {
 	bool			aeof;	/* allocated space at eof */
 	bool			conv;	/* overwriting unwritten extents */
 	int			datatype;/* data type being allocated */
-	int			flags;
+	uint32_t		flags;
 };
 
 #define	XFS_BMAP_MAX_NMAP	4
@@ -47,17 +47,17 @@ struct xfs_bmalloca {
 /*
  * Flags for xfs_bmapi_*
  */
-#define XFS_BMAPI_ENTIRE	0x001	/* return entire extent, not trimmed */
-#define XFS_BMAPI_METADATA	0x002	/* mapping metadata not user data */
-#define XFS_BMAPI_ATTRFORK	0x004	/* use attribute fork not data */
-#define XFS_BMAPI_PREALLOC	0x008	/* preallocation op: unwritten space */
-#define XFS_BMAPI_CONTIG	0x020	/* must allocate only one extent */
+#define XFS_BMAPI_ENTIRE	(1u << 0) /* return entire extent untrimmed */
+#define XFS_BMAPI_METADATA	(1u << 1) /* mapping metadata not user data */
+#define XFS_BMAPI_ATTRFORK	(1u << 2) /* use attribute fork not data */
+#define XFS_BMAPI_PREALLOC	(1u << 3) /* preallocating unwritten space */
+#define XFS_BMAPI_CONTIG	(1u << 4) /* must allocate only one extent */
 /*
  * unwritten extent conversion - this needs write cache flushing and no additional
  * allocation alignments. When specified with XFS_BMAPI_PREALLOC it converts
  * from written to unwritten, otherwise convert from unwritten to written.
  */
-#define XFS_BMAPI_CONVERT	0x040
+#define XFS_BMAPI_CONVERT	(1u << 5)
 
 /*
  * allocate zeroed extents - this requires all newly allocated user data extents
@@ -65,7 +65,7 @@ struct xfs_bmalloca {
  * Use in conjunction with XFS_BMAPI_CONVERT to convert unwritten extents found
  * during the allocation range to zeroed written extents.
  */
-#define XFS_BMAPI_ZERO		0x080
+#define XFS_BMAPI_ZERO		(1u << 6)
 
 /*
  * Map the inode offset to the block given in ap->firstblock.  Primarily
@@ -75,16 +75,16 @@ struct xfs_bmalloca {
  * For bunmapi, this flag unmaps the range without adjusting quota, reducing
  * refcount, or freeing the blocks.
  */
-#define XFS_BMAPI_REMAP		0x100
+#define XFS_BMAPI_REMAP		(1u << 7)
 
 /* Map something in the CoW fork. */
-#define XFS_BMAPI_COWFORK	0x200
+#define XFS_BMAPI_COWFORK	(1u << 8)
 
 /* Skip online discard of freed extents */
-#define XFS_BMAPI_NODISCARD	0x1000
+#define XFS_BMAPI_NODISCARD	(1u << 9)
 
 /* Do not update the rmap btree.  Used for reconstructing bmbt from rmapbt. */
-#define XFS_BMAPI_NORMAP	0x2000
+#define XFS_BMAPI_NORMAP	(1u << 10)
 
 #define XFS_BMAPI_FLAGS \
 	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
@@ -106,7 +106,7 @@ static inline int xfs_bmapi_aflag(int w)
 	       (w == XFS_COW_FORK ? XFS_BMAPI_COWFORK : 0));
 }
 
-static inline int xfs_bmapi_whichfork(int bmapi_flags)
+static inline int xfs_bmapi_whichfork(uint32_t bmapi_flags)
 {
 	if (bmapi_flags & XFS_BMAPI_COWFORK)
 		return XFS_COW_FORK;
@@ -124,16 +124,16 @@ static inline int xfs_bmapi_whichfork(int bmapi_flags)
 /*
  * Flags for xfs_bmap_add_extent*.
  */
-#define BMAP_LEFT_CONTIG	(1 << 0)
-#define BMAP_RIGHT_CONTIG	(1 << 1)
-#define BMAP_LEFT_FILLING	(1 << 2)
-#define BMAP_RIGHT_FILLING	(1 << 3)
-#define BMAP_LEFT_DELAY		(1 << 4)
-#define BMAP_RIGHT_DELAY	(1 << 5)
-#define BMAP_LEFT_VALID		(1 << 6)
-#define BMAP_RIGHT_VALID	(1 << 7)
-#define BMAP_ATTRFORK		(1 << 8)
-#define BMAP_COWFORK		(1 << 9)
+#define BMAP_LEFT_CONTIG	(1u << 0)
+#define BMAP_RIGHT_CONTIG	(1u << 1)
+#define BMAP_LEFT_FILLING	(1u << 2)
+#define BMAP_RIGHT_FILLING	(1u << 3)
+#define BMAP_LEFT_DELAY		(1u << 4)
+#define BMAP_RIGHT_DELAY	(1u << 5)
+#define BMAP_LEFT_VALID		(1u << 6)
+#define BMAP_RIGHT_VALID	(1u << 7)
+#define BMAP_ATTRFORK		(1u << 8)
+#define BMAP_COWFORK		(1u << 9)
 
 #define XFS_BMAP_EXT_FLAGS \
 	{ BMAP_LEFT_CONTIG,	"LC" }, \
@@ -183,15 +183,15 @@ int	xfs_bmap_last_offset(struct xfs_inode *ip, xfs_fileoff_t *unused,
 		int whichfork);
 int	xfs_bmapi_read(struct xfs_inode *ip, xfs_fileoff_t bno,
 		xfs_filblks_t len, struct xfs_bmbt_irec *mval,
-		int *nmap, int flags);
+		int *nmap, uint32_t flags);
 int	xfs_bmapi_write(struct xfs_trans *tp, struct xfs_inode *ip,
-		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
+		xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags,
 		xfs_extlen_t total, struct xfs_bmbt_irec *mval, int *nmap);
 int	__xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
-		xfs_fileoff_t bno, xfs_filblks_t *rlen, int flags,
+		xfs_fileoff_t bno, xfs_filblks_t *rlen, uint32_t flags,
 		xfs_extnum_t nexts);
 int	xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip,
-		xfs_fileoff_t bno, xfs_filblks_t len, int flags,
+		xfs_fileoff_t bno, xfs_filblks_t len, uint32_t flags,
 		xfs_extnum_t nexts, int *done);
 int	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
 		struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,
@@ -243,7 +243,7 @@ void	xfs_bmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 void	xfs_bmap_unmap_extent(struct xfs_trans *tp, struct xfs_inode *ip,
 		struct xfs_bmbt_irec *imap);
 
-static inline int xfs_bmap_fork_to_state(int whichfork)
+static inline uint32_t xfs_bmap_fork_to_state(int whichfork)
 {
 	switch (whichfork) {
 	case XFS_ATTR_FORK:
@@ -260,7 +260,7 @@ xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork,
 
 int	xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock,
-		int flags);
+		uint32_t flags);
 
 extern struct kmem_cache	*xfs_bmap_intent_cache;
 

fs/xfs/libxfs/xfs_bmap_btree.c

@@ -597,7 +597,11 @@ xfs_bmbt_maxrecs(
 	return xfs_bmbt_block_maxrecs(blocklen, leaf);
 }
 
-/* Compute the max possible height for block mapping btrees. */
+/*
+ * Calculate the maximum possible height of the btree that the on-disk format
+ * supports. This is used for sizing structures large enough to support every
+ * possible configuration of a filesystem that might get mounted.
+ */
 unsigned int
 xfs_bmbt_maxlevels_ondisk(void)
 {
@@ -611,7 +615,8 @@ xfs_bmbt_maxlevels_ondisk(void)
 	minrecs[1] = xfs_bmbt_block_maxrecs(blocklen, false) / 2;
 
 	/* One extra level for the inode root. */
-	return xfs_btree_compute_maxlevels(minrecs, MAXEXTNUM) + 1;
+	return xfs_btree_compute_maxlevels(minrecs,
+			XFS_MAX_EXTCNT_DATA_FORK_LARGE) + 1;
 }
 
 /*

fs/xfs/libxfs/xfs_btree.c

@@ -51,6 +51,52 @@ xfs_btree_magic(
 	return magic;
 }
 
+static xfs_failaddr_t
+xfs_btree_check_lblock_siblings(
+	struct xfs_mount	*mp,
+	struct xfs_btree_cur	*cur,
+	int			level,
+	xfs_fsblock_t		fsb,
+	xfs_fsblock_t		sibling)
+{
+	if (sibling == NULLFSBLOCK)
+		return NULL;
+	if (sibling == fsb)
+		return __this_address;
+	if (level >= 0) {
+		if (!xfs_btree_check_lptr(cur, sibling, level + 1))
+			return __this_address;
+	} else {
+		if (!xfs_verify_fsbno(mp, sibling))
+			return __this_address;
+	}
+
+	return NULL;
+}
+
+static xfs_failaddr_t
+xfs_btree_check_sblock_siblings(
+	struct xfs_mount	*mp,
+	struct xfs_btree_cur	*cur,
+	int			level,
+	xfs_agnumber_t		agno,
+	xfs_agblock_t		agbno,
+	xfs_agblock_t		sibling)
+{
+	if (sibling == NULLAGBLOCK)
+		return NULL;
+	if (sibling == agbno)
+		return __this_address;
+	if (level >= 0) {
+		if (!xfs_btree_check_sptr(cur, sibling, level + 1))
+			return __this_address;
+	} else {
+		if (!xfs_verify_agbno(mp, agno, sibling))
+			return __this_address;
+	}
+	return NULL;
+}
+
 /*
  * Check a long btree block header.  Return the address of the failing check,
  * or NULL if everything is ok.
@@ -65,6 +111,8 @@ __xfs_btree_check_lblock(
 	struct xfs_mount	*mp = cur->bc_mp;
 	xfs_btnum_t		btnum = cur->bc_btnum;
 	int			crc = xfs_has_crc(mp);
+	xfs_failaddr_t		fa;
+	xfs_fsblock_t		fsb = NULLFSBLOCK;
 
 	if (crc) {
 		if (!uuid_equal(&block->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid))
@@ -83,16 +131,16 @@ __xfs_btree_check_lblock(
 	if (be16_to_cpu(block->bb_numrecs) >
 	    cur->bc_ops->get_maxrecs(cur, level))
 		return __this_address;
-	if (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLFSBLOCK) &&
-	    !xfs_btree_check_lptr(cur, be64_to_cpu(block->bb_u.l.bb_leftsib),
-			level + 1))
-		return __this_address;
-	if (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK) &&
-	    !xfs_btree_check_lptr(cur, be64_to_cpu(block->bb_u.l.bb_rightsib),
-			level + 1))
-		return __this_address;
 
-	return NULL;
+	if (bp)
+		fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
+
+	fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb,
+			be64_to_cpu(block->bb_u.l.bb_leftsib));
+	if (!fa)
+		fa = xfs_btree_check_lblock_siblings(mp, cur, level, fsb,
+				be64_to_cpu(block->bb_u.l.bb_rightsib));
+	return fa;
 }
 
 /* Check a long btree block header. */
@@ -130,6 +178,9 @@ __xfs_btree_check_sblock(
 	struct xfs_mount	*mp = cur->bc_mp;
 	xfs_btnum_t		btnum = cur->bc_btnum;
 	int			crc = xfs_has_crc(mp);
+	xfs_failaddr_t		fa;
+	xfs_agblock_t		agbno = NULLAGBLOCK;
+	xfs_agnumber_t		agno = NULLAGNUMBER;
 
 	if (crc) {
 		if (!uuid_equal(&block->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid))
@@ -146,16 +197,18 @@ __xfs_btree_check_sblock(
 	if (be16_to_cpu(block->bb_numrecs) >
 	    cur->bc_ops->get_maxrecs(cur, level))
 		return __this_address;
-	if (block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK) &&
-	    !xfs_btree_check_sptr(cur, be32_to_cpu(block->bb_u.s.bb_leftsib),
-			level + 1))
-		return __this_address;
-	if (block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK) &&
-	    !xfs_btree_check_sptr(cur, be32_to_cpu(block->bb_u.s.bb_rightsib),
-			level + 1))
-		return __this_address;
 
-	return NULL;
+	if (bp) {
+		agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp));
+		agno = xfs_daddr_to_agno(mp, xfs_buf_daddr(bp));
+	}
+
+	fa = xfs_btree_check_sblock_siblings(mp, cur, level, agno, agbno,
+			be32_to_cpu(block->bb_u.s.bb_leftsib));
+	if (!fa)
+		fa = xfs_btree_check_sblock_siblings(mp, cur, level, agno,
+				 agbno, be32_to_cpu(block->bb_u.s.bb_rightsib));
+	return fa;
 }
 
 /* Check a short btree block header. */
@@ -751,20 +804,20 @@ xfs_btree_lastrec(
  */
 void
 xfs_btree_offsets(
-	int64_t		fields,		/* bitmask of fields */
+	uint32_t	fields,		/* bitmask of fields */
 	const short	*offsets,	/* table of field offsets */
 	int		nbits,		/* number of bits to inspect */
 	int		*first,		/* output: first byte offset */
 	int		*last)		/* output: last byte offset */
 {
 	int		i;		/* current bit number */
-	int64_t		imask;		/* mask for current bit number */
+	uint32_t	imask;		/* mask for current bit number */
 
 	ASSERT(fields != 0);
 	/*
 	 * Find the lowest bit, so the first byte offset.
 	 */
-	for (i = 0, imask = 1LL; ; i++, imask <<= 1) {
+	for (i = 0, imask = 1u; ; i++, imask <<= 1) {
 		if (imask & fields) {
 			*first = offsets[i];
 			break;
@@ -773,7 +826,7 @@ xfs_btree_offsets(
 	/*
 	 * Find the highest bit, so the last byte offset.
 	 */
-	for (i = nbits - 1, imask = 1LL << i; ; i--, imask >>= 1) {
+	for (i = nbits - 1, imask = 1u << i; ; i--, imask >>= 1) {
 		if (imask & fields) {
 			*last = offsets[i + 1] - 1;
 			break;
@@ -1456,7 +1509,7 @@ void
 xfs_btree_log_block(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	struct xfs_buf		*bp,	/* buffer containing btree block */
-	int			fields)	/* mask of fields: XFS_BB_... */
+	uint32_t		fields)	/* mask of fields: XFS_BB_... */
 {
 	int			first;	/* first byte offset logged */
 	int			last;	/* last byte offset logged */
@@ -4271,6 +4324,21 @@ xfs_btree_visit_block(
 	if (xfs_btree_ptr_is_null(cur, &rptr))
 		return -ENOENT;
 
+	/*
+	 * We only visit blocks once in this walk, so we have to avoid the
+	 * internal xfs_btree_lookup_get_block() optimisation where it will
+	 * return the same block without checking if the right sibling points
+	 * back to us and creates a cyclic reference in the btree.
+	 */
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+		if (be64_to_cpu(rptr.l) == XFS_DADDR_TO_FSB(cur->bc_mp,
+							xfs_buf_daddr(bp)))
+			return -EFSCORRUPTED;
+	} else {
+		if (be32_to_cpu(rptr.s) == xfs_daddr_to_agbno(cur->bc_mp,
+							xfs_buf_daddr(bp)))
+			return -EFSCORRUPTED;
+	}
 	return xfs_btree_lookup_get_block(cur, level, &rptr, &block);
 }
 
@@ -4445,20 +4513,21 @@ xfs_btree_lblock_verify(
 {
 	struct xfs_mount	*mp = bp->b_mount;
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	xfs_fsblock_t		fsb;
+	xfs_failaddr_t		fa;
 
 	/* numrecs verification */
 	if (be16_to_cpu(block->bb_numrecs) > max_recs)
 		return __this_address;
 
 	/* sibling pointer verification */
-	if (block->bb_u.l.bb_leftsib != cpu_to_be64(NULLFSBLOCK) &&
-	    !xfs_verify_fsbno(mp, be64_to_cpu(block->bb_u.l.bb_leftsib)))
-		return __this_address;
-	if (block->bb_u.l.bb_rightsib != cpu_to_be64(NULLFSBLOCK) &&
-	    !xfs_verify_fsbno(mp, be64_to_cpu(block->bb_u.l.bb_rightsib)))
-		return __this_address;
-
-	return NULL;
+	fsb = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp));
+	fa = xfs_btree_check_lblock_siblings(mp, NULL, -1, fsb,
+			be64_to_cpu(block->bb_u.l.bb_leftsib));
+	if (!fa)
+		fa = xfs_btree_check_lblock_siblings(mp, NULL, -1, fsb,
+				be64_to_cpu(block->bb_u.l.bb_rightsib));
+	return fa;
 }
 
 /**
@@ -4499,7 +4568,9 @@ xfs_btree_sblock_verify(
 {
 	struct xfs_mount	*mp = bp->b_mount;
 	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
-	xfs_agblock_t		agno;
+	xfs_agnumber_t		agno;
+	xfs_agblock_t		agbno;
+	xfs_failaddr_t		fa;
 
 	/* numrecs verification */
 	if (be16_to_cpu(block->bb_numrecs) > max_recs)
@@ -4507,14 +4578,13 @@ xfs_btree_sblock_verify(
 
 	/* sibling pointer verification */
 	agno = xfs_daddr_to_agno(mp, xfs_buf_daddr(bp));
-	if (block->bb_u.s.bb_leftsib != cpu_to_be32(NULLAGBLOCK) &&
-	    !xfs_verify_agbno(mp, agno, be32_to_cpu(block->bb_u.s.bb_leftsib)))
-		return __this_address;
-	if (block->bb_u.s.bb_rightsib != cpu_to_be32(NULLAGBLOCK) &&
-	    !xfs_verify_agbno(mp, agno, be32_to_cpu(block->bb_u.s.bb_rightsib)))
-		return __this_address;
-
-	return NULL;
+	agbno = xfs_daddr_to_agbno(mp, xfs_buf_daddr(bp));
+	fa = xfs_btree_check_sblock_siblings(mp, NULL, -1, agno, agbno,
+			be32_to_cpu(block->bb_u.s.bb_leftsib));
+	if (!fa)
+		fa = xfs_btree_check_sblock_siblings(mp, NULL, -1, agno, agbno,
+				be32_to_cpu(block->bb_u.s.bb_rightsib));
+	return fa;
 }
 
 /*

fs/xfs/libxfs/xfs_btree.h

@@ -68,19 +68,19 @@ uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
 /*
  * For logging record fields.
  */
-#define	XFS_BB_MAGIC		(1 << 0)
-#define	XFS_BB_LEVEL		(1 << 1)
-#define	XFS_BB_NUMRECS		(1 << 2)
-#define	XFS_BB_LEFTSIB		(1 << 3)
-#define	XFS_BB_RIGHTSIB		(1 << 4)
-#define	XFS_BB_BLKNO		(1 << 5)
-#define	XFS_BB_LSN		(1 << 6)
-#define	XFS_BB_UUID		(1 << 7)
-#define	XFS_BB_OWNER		(1 << 8)
+#define	XFS_BB_MAGIC		(1u << 0)
+#define	XFS_BB_LEVEL		(1u << 1)
+#define	XFS_BB_NUMRECS		(1u << 2)
+#define	XFS_BB_LEFTSIB		(1u << 3)
+#define	XFS_BB_RIGHTSIB		(1u << 4)
+#define	XFS_BB_BLKNO		(1u << 5)
+#define	XFS_BB_LSN		(1u << 6)
+#define	XFS_BB_UUID		(1u << 7)
+#define	XFS_BB_OWNER		(1u << 8)
 #define	XFS_BB_NUM_BITS		5
-#define	XFS_BB_ALL_BITS		((1 << XFS_BB_NUM_BITS) - 1)
+#define	XFS_BB_ALL_BITS		((1u << XFS_BB_NUM_BITS) - 1)
 #define	XFS_BB_NUM_BITS_CRC	9
-#define	XFS_BB_ALL_BITS_CRC	((1 << XFS_BB_NUM_BITS_CRC) - 1)
+#define	XFS_BB_ALL_BITS_CRC	((1u << XFS_BB_NUM_BITS_CRC) - 1)
 
 /*
  * Generic stats interface
@@ -345,7 +345,7 @@ xfs_btree_dup_cursor(
  */
 void
 xfs_btree_offsets(
-	int64_t			fields,	/* bitmask of fields */
+	uint32_t		fields,	/* bitmask of fields */
 	const short		*offsets,/* table of field offsets */
 	int			nbits,	/* number of bits to inspect */
 	int			*first,	/* output: first byte offset */
@@ -435,7 +435,7 @@ bool xfs_btree_sblock_verify_crc(struct xfs_buf *);
 /*
  * Internal btree helpers also used by xfs_bmap.c.
  */
-void xfs_btree_log_block(struct xfs_btree_cur *, struct xfs_buf *, int);
+void xfs_btree_log_block(struct xfs_btree_cur *, struct xfs_buf *, uint32_t);
 void xfs_btree_log_recs(struct xfs_btree_cur *, struct xfs_buf *, int, int);
 
 /*

fs/xfs/libxfs/xfs_da_btree.c

@@ -22,6 +22,7 @@
 #include "xfs_trace.h"
 #include "xfs_buf_item.h"
 #include "xfs_log.h"
+#include "xfs_errortag.h"
 
 /*
  * xfs_da_btree.c
@@ -482,6 +483,9 @@ xfs_da3_split(
 
 	trace_xfs_da_split(state->args);
 
+	if (XFS_TEST_ERROR(false, state->mp, XFS_ERRTAG_DA_LEAF_SPLIT))
+		return -EIO;
+
 	/*
 	 * Walk back up the tree splitting/inserting/adjusting as necessary.
 	 * If we need to insert and there isn't room, split the node, then

fs/xfs/libxfs/xfs_da_btree.h

@@ -30,6 +30,7 @@ struct xfs_da_geometry {
 	unsigned int	free_hdr_size;	/* dir2 free header size */
 	unsigned int	free_max_bests;	/* # of bests entries in dir2 free */
 	xfs_dablk_t	freeblk;	/* blockno of free data v2 */
+	xfs_extnum_t	max_extents;	/* Max. extents in corresponding fork */
 
 	xfs_dir2_data_aoff_t data_first_offset;
 	size_t		data_entry_offset;
@@ -76,27 +77,31 @@ typedef struct xfs_da_args {
 	xfs_dablk_t	rmtblkno2;	/* remote attr value starting blkno */
 	int		rmtblkcnt2;	/* remote attr value block count */
 	int		rmtvaluelen2;	/* remote attr value length in bytes */
-	int		op_flags;	/* operation flags */
+	uint32_t	op_flags;	/* operation flags */
 	enum xfs_dacmp	cmpresult;	/* name compare result for lookups */
 } xfs_da_args_t;
 
 /*
  * Operation flags:
  */
-#define XFS_DA_OP_JUSTCHECK	0x0001	/* check for ok with no space */
-#define XFS_DA_OP_RENAME	0x0002	/* this is an atomic rename op */
-#define XFS_DA_OP_ADDNAME	0x0004	/* this is an add operation */
-#define XFS_DA_OP_OKNOENT	0x0008	/* lookup/add op, ENOENT ok, else die */
-#define XFS_DA_OP_CILOOKUP	0x0010	/* lookup to return CI name if found */
-#define XFS_DA_OP_NOTIME	0x0020	/* don't update inode timestamps */
+#define XFS_DA_OP_JUSTCHECK	(1u << 0) /* check for ok with no space */
+#define XFS_DA_OP_REPLACE	(1u << 1) /* this is an atomic replace op */
+#define XFS_DA_OP_ADDNAME	(1u << 2) /* this is an add operation */
+#define XFS_DA_OP_OKNOENT	(1u << 3) /* lookup op, ENOENT ok, else die */
+#define XFS_DA_OP_CILOOKUP	(1u << 4) /* lookup returns CI name if found */
+#define XFS_DA_OP_NOTIME	(1u << 5) /* don't update inode timestamps */
+#define XFS_DA_OP_REMOVE	(1u << 6) /* this is a remove operation */
+#define XFS_DA_OP_RECOVERY	(1u << 7) /* Log recovery operation */
 
 #define XFS_DA_OP_FLAGS \
 	{ XFS_DA_OP_JUSTCHECK,	"JUSTCHECK" }, \
-	{ XFS_DA_OP_RENAME,	"RENAME" }, \
+	{ XFS_DA_OP_REPLACE,	"REPLACE" }, \
 	{ XFS_DA_OP_ADDNAME,	"ADDNAME" }, \
 	{ XFS_DA_OP_OKNOENT,	"OKNOENT" }, \
 	{ XFS_DA_OP_CILOOKUP,	"CILOOKUP" }, \
-	{ XFS_DA_OP_NOTIME,	"NOTIME" }
+	{ XFS_DA_OP_NOTIME,	"NOTIME" }, \
+	{ XFS_DA_OP_REMOVE,	"REMOVE" }, \
+	{ XFS_DA_OP_RECOVERY,	"RECOVERY" }
 
 /*
  * Storage for holding state during Btree searches and split/join ops.
@@ -197,7 +202,7 @@ int	xfs_da3_node_read_mapped(struct xfs_trans *tp, struct xfs_inode *dp,
  * Utility routines.
  */
 
-#define XFS_DABUF_MAP_HOLE_OK	(1 << 0)
+#define XFS_DABUF_MAP_HOLE_OK	(1u << 0)
 
 int	xfs_da_grow_inode(xfs_da_args_t *args, xfs_dablk_t *new_blkno);
 int	xfs_da_grow_inode_int(struct xfs_da_args *args, xfs_fileoff_t *bno,

fs/xfs/libxfs/xfs_da_format.h

@@ -277,6 +277,7 @@ xfs_dir2_sf_firstentry(struct xfs_dir2_sf_hdr *hdr)
  * Directory address space divided into sections,
  * spaces separated by 32GB.
  */
+#define	XFS_DIR2_MAX_SPACES	3
 #define	XFS_DIR2_SPACE_SIZE	(1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG))
 #define	XFS_DIR2_DATA_SPACE	0
 #define	XFS_DIR2_DATA_OFFSET	(XFS_DIR2_DATA_SPACE * XFS_DIR2_SPACE_SIZE)
@@ -688,10 +689,10 @@ struct xfs_attr3_leafblock {
 #define	XFS_ATTR_ROOT_BIT	1	/* limit access to trusted attrs */
 #define	XFS_ATTR_SECURE_BIT	2	/* limit access to secure attrs */
 #define	XFS_ATTR_INCOMPLETE_BIT	7	/* attr in middle of create/delete */
-#define XFS_ATTR_LOCAL		(1 << XFS_ATTR_LOCAL_BIT)
-#define XFS_ATTR_ROOT		(1 << XFS_ATTR_ROOT_BIT)
-#define XFS_ATTR_SECURE		(1 << XFS_ATTR_SECURE_BIT)
-#define XFS_ATTR_INCOMPLETE	(1 << XFS_ATTR_INCOMPLETE_BIT)
+#define XFS_ATTR_LOCAL		(1u << XFS_ATTR_LOCAL_BIT)
+#define XFS_ATTR_ROOT		(1u << XFS_ATTR_ROOT_BIT)
+#define XFS_ATTR_SECURE		(1u << XFS_ATTR_SECURE_BIT)
+#define XFS_ATTR_INCOMPLETE	(1u << XFS_ATTR_INCOMPLETE_BIT)
 #define XFS_ATTR_NSP_ONDISK_MASK	(XFS_ATTR_ROOT | XFS_ATTR_SECURE)
 
 /*

fs/xfs/libxfs/xfs_defer.c

@@ -22,6 +22,10 @@
 #include "xfs_refcount.h"
 #include "xfs_bmap.h"
 #include "xfs_alloc.h"
+#include "xfs_buf.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_attr.h"
 
 static struct kmem_cache	*xfs_defer_pending_cache;
 
@@ -184,9 +188,10 @@ static const struct xfs_defer_op_type *defer_op_types[] = {
 	[XFS_DEFER_OPS_TYPE_RMAP]	= &xfs_rmap_update_defer_type,
 	[XFS_DEFER_OPS_TYPE_FREE]	= &xfs_extent_free_defer_type,
 	[XFS_DEFER_OPS_TYPE_AGFL_FREE]	= &xfs_agfl_free_defer_type,
+	[XFS_DEFER_OPS_TYPE_ATTR]	= &xfs_attr_defer_type,
 };
 
-static void
+static bool
 xfs_defer_create_intent(
 	struct xfs_trans		*tp,
 	struct xfs_defer_pending	*dfp,
@@ -197,6 +202,7 @@ xfs_defer_create_intent(
 	if (!dfp->dfp_intent)
 		dfp->dfp_intent = ops->create_intent(tp, &dfp->dfp_work,
 						     dfp->dfp_count, sort);
+	return dfp->dfp_intent != NULL;
 }
 
 /*
@@ -204,16 +210,18 @@ xfs_defer_create_intent(
  * associated extents, then add the entire intake list to the end of
  * the pending list.
  */
-STATIC void
+static bool
 xfs_defer_create_intents(
 	struct xfs_trans		*tp)
 {
 	struct xfs_defer_pending	*dfp;
+	bool				ret = false;
 
 	list_for_each_entry(dfp, &tp->t_dfops, dfp_list) {
 		trace_xfs_defer_create_intent(tp->t_mountp, dfp);
-		xfs_defer_create_intent(tp, dfp, true);
+		ret |= xfs_defer_create_intent(tp, dfp, true);
 	}
+	return ret;
 }
 
 /* Abort all the intents that were committed. */
@@ -487,7 +495,7 @@ int
 xfs_defer_finish_noroll(
 	struct xfs_trans		**tp)
 {
-	struct xfs_defer_pending	*dfp;
+	struct xfs_defer_pending	*dfp = NULL;
 	int				error = 0;
 	LIST_HEAD(dop_pending);
 
@@ -506,17 +514,20 @@ xfs_defer_finish_noroll(
 		 * of time that any one intent item can stick around in memory,
 		 * pinning the log tail.
 		 */
-		xfs_defer_create_intents(*tp);
+		bool has_intents = xfs_defer_create_intents(*tp);
+
 		list_splice_init(&(*tp)->t_dfops, &dop_pending);
 
-		error = xfs_defer_trans_roll(tp);
-		if (error)
-			goto out_shutdown;
+		if (has_intents || dfp) {
+			error = xfs_defer_trans_roll(tp);
+			if (error)
+				goto out_shutdown;
 
-		/* Possibly relog intent items to keep the log moving. */
-		error = xfs_defer_relog(tp, &dop_pending);
-		if (error)
-			goto out_shutdown;
+			/* Relog intent items to keep the log moving. */
+			error = xfs_defer_relog(tp, &dop_pending);
+			if (error)
+				goto out_shutdown;
+		}
 
 		dfp = list_first_entry(&dop_pending, struct xfs_defer_pending,
 				       dfp_list);
@@ -774,17 +785,25 @@ xfs_defer_ops_continue(
 	struct xfs_trans		*tp,
 	struct xfs_defer_resources	*dres)
 {
+	unsigned int			i;
+
 	ASSERT(tp->t_flags & XFS_TRANS_PERM_LOG_RES);
 	ASSERT(!(tp->t_flags & XFS_TRANS_DIRTY));
 
-	/* Lock and join the captured inode to the new transaction. */
+	/* Lock the captured resources to the new transaction. */
 	if (dfc->dfc_held.dr_inos == 2)
 		xfs_lock_two_inodes(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL,
 				    dfc->dfc_held.dr_ip[1], XFS_ILOCK_EXCL);
 	else if (dfc->dfc_held.dr_inos == 1)
 		xfs_ilock(dfc->dfc_held.dr_ip[0], XFS_ILOCK_EXCL);
+
+	for (i = 0; i < dfc->dfc_held.dr_bufs; i++)
+		xfs_buf_lock(dfc->dfc_held.dr_bp[i]);
+
+	/* Join the captured resources to the new transaction. */
 	xfs_defer_restore_resources(tp, &dfc->dfc_held);
 	memcpy(dres, &dfc->dfc_held, sizeof(struct xfs_defer_resources));
+	dres->dr_bufs = 0;
 
 	/* Move captured dfops chain and state to the transaction. */
 	list_splice_init(&dfc->dfc_dfops, &tp->t_dfops);
@@ -854,7 +873,12 @@ xfs_defer_init_item_caches(void)
 	error = xfs_extfree_intent_init_cache();
 	if (error)
 		goto err;
-
+	error = xfs_attri_init_cache();
+	if (error)
+		goto err;
+	error = xfs_attrd_init_cache();
+	if (error)
+		goto err;
 	return 0;
 err:
 	xfs_defer_destroy_item_caches();
@@ -865,6 +889,8 @@ xfs_defer_init_item_caches(void)
 void
 xfs_defer_destroy_item_caches(void)
 {
+	xfs_attri_destroy_cache();
+	xfs_attrd_destroy_cache();
 	xfs_extfree_intent_destroy_cache();
 	xfs_bmap_intent_destroy_cache();
 	xfs_refcount_intent_destroy_cache();

fs/xfs/libxfs/xfs_defer.h

@@ -19,6 +19,7 @@ enum xfs_defer_ops_type {
 	XFS_DEFER_OPS_TYPE_RMAP,
 	XFS_DEFER_OPS_TYPE_FREE,
 	XFS_DEFER_OPS_TYPE_AGFL_FREE,
+	XFS_DEFER_OPS_TYPE_ATTR,
 	XFS_DEFER_OPS_TYPE_MAX,
 };
 
@@ -63,6 +64,8 @@ extern const struct xfs_defer_op_type xfs_refcount_update_defer_type;
 extern const struct xfs_defer_op_type xfs_rmap_update_defer_type;
 extern const struct xfs_defer_op_type xfs_extent_free_defer_type;
 extern const struct xfs_defer_op_type xfs_agfl_free_defer_type;
+extern const struct xfs_defer_op_type xfs_attr_defer_type;
+
 
 /*
  * Deferred operation item relogging limits.

fs/xfs/libxfs/xfs_dir2.c

@@ -150,6 +150,8 @@ xfs_da_mount(
 	dageo->freeblk = xfs_dir2_byte_to_da(dageo, XFS_DIR2_FREE_OFFSET);
 	dageo->node_ents = (dageo->blksize - dageo->node_hdr_size) /
 				(uint)sizeof(xfs_da_node_entry_t);
+	dageo->max_extents = (XFS_DIR2_MAX_SPACES * XFS_DIR2_SPACE_SIZE) >>
+					mp->m_sb.sb_blocklog;
 	dageo->magicpct = (dageo->blksize * 37) / 100;
 
 	/* set up attribute geometry - single fsb only */
@@ -161,6 +163,12 @@ xfs_da_mount(
 	dageo->node_hdr_size = mp->m_dir_geo->node_hdr_size;
 	dageo->node_ents = (dageo->blksize - dageo->node_hdr_size) /
 				(uint)sizeof(xfs_da_node_entry_t);
+
+	if (xfs_has_large_extent_counts(mp))
+		dageo->max_extents = XFS_MAX_EXTCNT_ATTR_FORK_LARGE;
+	else
+		dageo->max_extents = XFS_MAX_EXTCNT_ATTR_FORK_SMALL;
+
 	dageo->magicpct = (dageo->blksize * 37) / 100;
 	return 0;
 }

fs/xfs/libxfs/xfs_errortag.h

@@ -59,7 +59,10 @@
 #define XFS_ERRTAG_REDUCE_MAX_IEXTENTS			36
 #define XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT		37
 #define XFS_ERRTAG_AG_RESV_FAIL				38
-#define XFS_ERRTAG_MAX					39
+#define XFS_ERRTAG_LARP					39
+#define XFS_ERRTAG_DA_LEAF_SPLIT			40
+#define XFS_ERRTAG_ATTR_LEAF_TO_NODE			41
+#define XFS_ERRTAG_MAX					42
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -103,5 +106,8 @@
 #define XFS_RANDOM_REDUCE_MAX_IEXTENTS			1
 #define XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT		1
 #define XFS_RANDOM_AG_RESV_FAIL				1
+#define XFS_RANDOM_LARP					1
+#define XFS_RANDOM_DA_LEAF_SPLIT			1
+#define XFS_RANDOM_ATTR_LEAF_TO_NODE			1
 
 #endif /* __XFS_ERRORTAG_H_ */

fs/xfs/libxfs/xfs_fs.h

@@ -236,6 +236,7 @@ typedef struct xfs_fsop_resblks {
 #define XFS_FSOP_GEOM_FLAGS_REFLINK	(1 << 20) /* files can share blocks */
 #define XFS_FSOP_GEOM_FLAGS_BIGTIME	(1 << 21) /* 64-bit nsec timestamps */
 #define XFS_FSOP_GEOM_FLAGS_INOBTCNT	(1 << 22) /* inobt btree counter */
+#define XFS_FSOP_GEOM_FLAGS_NREXT64	(1 << 23) /* large extent counters */
 
 /*
  * Minimum and maximum sizes need for growth checks.
@@ -377,7 +378,7 @@ struct xfs_bulkstat {
 	uint32_t	bs_extsize_blks; /* extent size hint, blocks	*/
 
 	uint32_t	bs_nlink;	/* number of links		*/
-	uint32_t	bs_extents;	/* number of extents		*/
+	uint32_t	bs_extents;	/* 32-bit data fork extent counter */
 	uint32_t	bs_aextents;	/* attribute number of extents	*/
 	uint16_t	bs_version;	/* structure version		*/
 	uint16_t	bs_forkoff;	/* inode fork offset in bytes	*/
@@ -386,8 +387,9 @@ struct xfs_bulkstat {
 	uint16_t	bs_checked;	/* checked inode metadata	*/
 	uint16_t	bs_mode;	/* type and mode		*/
 	uint16_t	bs_pad2;	/* zeroed			*/
+	uint64_t	bs_extents64;	/* 64-bit data fork extent counter */
 
-	uint64_t	bs_pad[7];	/* zeroed			*/
+	uint64_t	bs_pad[6];	/* zeroed			*/
 };
 
 #define XFS_BULKSTAT_VERSION_V1	(1)
@@ -459,17 +461,28 @@ struct xfs_bulk_ireq {
  * Only return results from the specified @agno.  If @ino is zero, start
  * with the first inode of @agno.
  */
-#define XFS_BULK_IREQ_AGNO	(1 << 0)
+#define XFS_BULK_IREQ_AGNO	(1U << 0)
 
 /*
  * Return bulkstat information for a single inode, where @ino value is a
  * special value, not a literal inode number.  See the XFS_BULK_IREQ_SPECIAL_*
  * values below.  Not compatible with XFS_BULK_IREQ_AGNO.
  */
-#define XFS_BULK_IREQ_SPECIAL	(1 << 1)
+#define XFS_BULK_IREQ_SPECIAL	(1U << 1)
 
-#define XFS_BULK_IREQ_FLAGS_ALL	(XFS_BULK_IREQ_AGNO | \
-				 XFS_BULK_IREQ_SPECIAL)
+/*
+ * Return data fork extent count via xfs_bulkstat->bs_extents64 field and assign
+ * 0 to xfs_bulkstat->bs_extents when the flag is set.  Otherwise, use
+ * xfs_bulkstat->bs_extents for returning data fork extent count and set
+ * xfs_bulkstat->bs_extents64 to 0. In the second case, return -EOVERFLOW and
+ * assign 0 to xfs_bulkstat->bs_extents if data fork extent count is larger than
+ * XFS_MAX_EXTCNT_DATA_FORK_OLD.
+ */
+#define XFS_BULK_IREQ_NREXT64	(1U << 2)
+
+#define XFS_BULK_IREQ_FLAGS_ALL	(XFS_BULK_IREQ_AGNO |	 \
+				 XFS_BULK_IREQ_SPECIAL | \
+				 XFS_BULK_IREQ_NREXT64)
 
 /* Operate on the root directory inode. */
 #define XFS_BULK_IREQ_SPECIAL_ROOT	(1)
@@ -699,34 +712,34 @@ struct xfs_scrub_metadata {
 #define XFS_SCRUB_TYPE_NR	25
 
 /* i: Repair this metadata. */
-#define XFS_SCRUB_IFLAG_REPAIR		(1 << 0)
+#define XFS_SCRUB_IFLAG_REPAIR		(1u << 0)
 
 /* o: Metadata object needs repair. */
-#define XFS_SCRUB_OFLAG_CORRUPT		(1 << 1)
+#define XFS_SCRUB_OFLAG_CORRUPT		(1u << 1)
 
 /*
  * o: Metadata object could be optimized.  It's not corrupt, but
  *    we could improve on it somehow.
  */
-#define XFS_SCRUB_OFLAG_PREEN		(1 << 2)
+#define XFS_SCRUB_OFLAG_PREEN		(1u << 2)
 
 /* o: Cross-referencing failed. */
-#define XFS_SCRUB_OFLAG_XFAIL		(1 << 3)
+#define XFS_SCRUB_OFLAG_XFAIL		(1u << 3)
 
 /* o: Metadata object disagrees with cross-referenced metadata. */
-#define XFS_SCRUB_OFLAG_XCORRUPT	(1 << 4)
+#define XFS_SCRUB_OFLAG_XCORRUPT	(1u << 4)
 
 /* o: Scan was not complete. */
-#define XFS_SCRUB_OFLAG_INCOMPLETE	(1 << 5)
+#define XFS_SCRUB_OFLAG_INCOMPLETE	(1u << 5)
 
 /* o: Metadata object looked funny but isn't corrupt. */
-#define XFS_SCRUB_OFLAG_WARNING		(1 << 6)
+#define XFS_SCRUB_OFLAG_WARNING		(1u << 6)
 
 /*
  * o: IFLAG_REPAIR was set but metadata object did not need fixing or
  *    optimization and has therefore not been altered.
  */
-#define XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED (1 << 7)
+#define XFS_SCRUB_OFLAG_NO_REPAIR_NEEDED (1u << 7)
 
 #define XFS_SCRUB_FLAGS_IN	(XFS_SCRUB_IFLAG_REPAIR)
 #define XFS_SCRUB_FLAGS_OUT	(XFS_SCRUB_OFLAG_CORRUPT | \

fs/xfs/libxfs/xfs_ialloc.c

@@ -2414,9 +2414,9 @@ xfs_imap(
  */
 void
 xfs_ialloc_log_agi(
-	xfs_trans_t	*tp,		/* transaction pointer */
-	struct xfs_buf	*bp,		/* allocation group header buffer */
-	int		fields)		/* bitmask of fields to log */
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp,
+	uint32_t		fields)
 {
 	int			first;		/* first byte number */
 	int			last;		/* last byte number */
@@ -2772,6 +2772,8 @@ xfs_ialloc_setup_geometry(
 	igeo->new_diflags2 = 0;
 	if (xfs_has_bigtime(mp))
 		igeo->new_diflags2 |= XFS_DIFLAG2_BIGTIME;
+	if (xfs_has_large_extent_counts(mp))
+		igeo->new_diflags2 |= XFS_DIFLAG2_NREXT64;
 
 	/* Compute inode btree geometry. */
 	igeo->agino_log = sbp->sb_inopblog + sbp->sb_agblklog;

fs/xfs/libxfs/xfs_ialloc.h

@@ -60,7 +60,7 @@ void
 xfs_ialloc_log_agi(
 	struct xfs_trans *tp,		/* transaction pointer */
 	struct xfs_buf	*bp,		/* allocation group header buffer */
-	int		fields);	/* bitmask of fields to log */
+	uint32_t	fields);	/* bitmask of fields to log */
 
 /*
  * Read in the allocation group header (inode allocation section)

fs/xfs/libxfs/xfs_inode_buf.c

@@ -279,6 +279,25 @@ xfs_inode_to_disk_ts(
 	return ts;
 }
 
+static inline void
+xfs_inode_to_disk_iext_counters(
+	struct xfs_inode	*ip,
+	struct xfs_dinode	*to)
+{
+	if (xfs_inode_has_large_extent_counts(ip)) {
+		to->di_big_nextents = cpu_to_be64(xfs_ifork_nextents(&ip->i_df));
+		to->di_big_anextents = cpu_to_be32(xfs_ifork_nextents(ip->i_afp));
+		/*
+		 * We might be upgrading the inode to use larger extent counters
+		 * than was previously used. Hence zero the unused field.
+		 */
+		to->di_nrext64_pad = cpu_to_be16(0);
+	} else {
+		to->di_nextents = cpu_to_be32(xfs_ifork_nextents(&ip->i_df));
+		to->di_anextents = cpu_to_be16(xfs_ifork_nextents(ip->i_afp));
+	}
+}
+
 void
 xfs_inode_to_disk(
 	struct xfs_inode	*ip,
@@ -296,7 +315,6 @@ xfs_inode_to_disk(
 	to->di_projid_lo = cpu_to_be16(ip->i_projid & 0xffff);
 	to->di_projid_hi = cpu_to_be16(ip->i_projid >> 16);
 
-	memset(to->di_pad, 0, sizeof(to->di_pad));
 	to->di_atime = xfs_inode_to_disk_ts(ip, inode->i_atime);
 	to->di_mtime = xfs_inode_to_disk_ts(ip, inode->i_mtime);
 	to->di_ctime = xfs_inode_to_disk_ts(ip, inode->i_ctime);
@@ -307,8 +325,6 @@ xfs_inode_to_disk(
 	to->di_size = cpu_to_be64(ip->i_disk_size);
 	to->di_nblocks = cpu_to_be64(ip->i_nblocks);
 	to->di_extsize = cpu_to_be32(ip->i_extsize);
-	to->di_nextents = cpu_to_be32(xfs_ifork_nextents(&ip->i_df));
-	to->di_anextents = cpu_to_be16(xfs_ifork_nextents(ip->i_afp));
 	to->di_forkoff = ip->i_forkoff;
 	to->di_aformat = xfs_ifork_format(ip->i_afp);
 	to->di_flags = cpu_to_be16(ip->i_diflags);
@@ -323,11 +339,14 @@ xfs_inode_to_disk(
 		to->di_lsn = cpu_to_be64(lsn);
 		memset(to->di_pad2, 0, sizeof(to->di_pad2));
 		uuid_copy(&to->di_uuid, &ip->i_mount->m_sb.sb_meta_uuid);
-		to->di_flushiter = 0;
+		to->di_v3_pad = 0;
 	} else {
 		to->di_version = 2;
 		to->di_flushiter = cpu_to_be16(ip->i_flushiter);
+		memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad));
 	}
+
+	xfs_inode_to_disk_iext_counters(ip, to);
 }
 
 static xfs_failaddr_t
@@ -336,20 +355,40 @@ xfs_dinode_verify_fork(
 	struct xfs_mount	*mp,
 	int			whichfork)
 {
-	uint32_t		di_nextents = XFS_DFORK_NEXTENTS(dip, whichfork);
+	xfs_extnum_t		di_nextents;
+	xfs_extnum_t		max_extents;
+	mode_t			mode = be16_to_cpu(dip->di_mode);
+	uint32_t		fork_size = XFS_DFORK_SIZE(dip, mp, whichfork);
+	uint32_t		fork_format = XFS_DFORK_FORMAT(dip, whichfork);
+
+	di_nextents = xfs_dfork_nextents(dip, whichfork);
+
+	/*
+	 * For fork types that can contain local data, check that the fork
+	 * format matches the size of local data contained within the fork.
+	 *
+	 * For all types, check that when the size says the should be in extent
+	 * or btree format, the inode isn't claiming it is in local format.
+	 */
+	if (whichfork == XFS_DATA_FORK) {
+		if (S_ISDIR(mode) || S_ISLNK(mode)) {
+			if (be64_to_cpu(dip->di_size) <= fork_size &&
+			    fork_format != XFS_DINODE_FMT_LOCAL)
+				return __this_address;
+		}
 
-	switch (XFS_DFORK_FORMAT(dip, whichfork)) {
+		if (be64_to_cpu(dip->di_size) > fork_size &&
+		    fork_format == XFS_DINODE_FMT_LOCAL)
+			return __this_address;
+	}
+
+	switch (fork_format) {
 	case XFS_DINODE_FMT_LOCAL:
 		/*
-		 * no local regular files yet
+		 * No local regular files yet.
 		 */
-		if (whichfork == XFS_DATA_FORK) {
-			if (S_ISREG(be16_to_cpu(dip->di_mode)))
-				return __this_address;
-			if (be64_to_cpu(dip->di_size) >
-					XFS_DFORK_SIZE(dip, mp, whichfork))
-				return __this_address;
-		}
+		if (S_ISREG(mode) && whichfork == XFS_DATA_FORK)
+			return __this_address;
 		if (di_nextents)
 			return __this_address;
 		break;
@@ -358,12 +397,11 @@ xfs_dinode_verify_fork(
 			return __this_address;
 		break;
 	case XFS_DINODE_FMT_BTREE:
-		if (whichfork == XFS_ATTR_FORK) {
-			if (di_nextents > MAXAEXTNUM)
-				return __this_address;
-		} else if (di_nextents > MAXEXTNUM) {
+		max_extents = xfs_iext_max_nextents(
+					xfs_dinode_has_large_extent_counts(dip),
+					whichfork);
+		if (di_nextents > max_extents)
 			return __this_address;
-		}
 		break;
 	default:
 		return __this_address;
@@ -396,6 +434,24 @@ xfs_dinode_verify_forkoff(
 	return NULL;
 }
 
+static xfs_failaddr_t
+xfs_dinode_verify_nrext64(
+	struct xfs_mount	*mp,
+	struct xfs_dinode	*dip)
+{
+	if (xfs_dinode_has_large_extent_counts(dip)) {
+		if (!xfs_has_large_extent_counts(mp))
+			return __this_address;
+		if (dip->di_nrext64_pad != 0)
+			return __this_address;
+	} else if (dip->di_version >= 3) {
+		if (dip->di_v3_pad != 0)
+			return __this_address;
+	}
+
+	return NULL;
+}
+
 xfs_failaddr_t
 xfs_dinode_verify(
 	struct xfs_mount	*mp,
@@ -407,6 +463,9 @@ xfs_dinode_verify(
 	uint16_t		flags;
 	uint64_t		flags2;
 	uint64_t		di_size;
+	xfs_extnum_t		nextents;
+	xfs_extnum_t		naextents;
+	xfs_filblks_t		nblocks;
 
 	if (dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC))
 		return __this_address;
@@ -437,10 +496,19 @@ xfs_dinode_verify(
 	if ((S_ISLNK(mode) || S_ISDIR(mode)) && di_size == 0)
 		return __this_address;
 
+	fa = xfs_dinode_verify_nrext64(mp, dip);
+	if (fa)
+		return fa;
+
+	nextents = xfs_dfork_data_extents(dip);
+	naextents = xfs_dfork_attr_extents(dip);
+	nblocks = be64_to_cpu(dip->di_nblocks);
+
 	/* Fork checks carried over from xfs_iformat_fork */
-	if (mode &&
-	    be32_to_cpu(dip->di_nextents) + be16_to_cpu(dip->di_anextents) >
-			be64_to_cpu(dip->di_nblocks))
+	if (mode && nextents + naextents > nblocks)
+		return __this_address;
+
+	if (S_ISDIR(mode) && nextents > mp->m_dir_geo->max_extents)
 		return __this_address;
 
 	if (mode && XFS_DFORK_BOFF(dip) > mp->m_sb.sb_inodesize)
@@ -497,7 +565,7 @@ xfs_dinode_verify(
 		default:
 			return __this_address;
 		}
-		if (dip->di_anextents)
+		if (naextents)
 			return __this_address;
 	}
 
@@ -639,7 +707,7 @@ xfs_inode_validate_extsize(
 	if (extsize_bytes % blocksize_bytes)
 		return __this_address;
 
-	if (extsize > MAXEXTLEN)
+	if (extsize > XFS_MAX_BMBT_EXTLEN)
 		return __this_address;
 
 	if (!rt_flag && extsize > mp->m_sb.sb_agblocks / 2)
@@ -696,7 +764,7 @@ xfs_inode_validate_cowextsize(
 	if (cowextsize_bytes % mp->m_sb.sb_blocksize)
 		return __this_address;
 
-	if (cowextsize > MAXEXTLEN)
+	if (cowextsize > XFS_MAX_BMBT_EXTLEN)
 		return __this_address;
 
 	if (cowextsize > mp->m_sb.sb_agblocks / 2)

fs/xfs/libxfs/xfs_inode_fork.c

@@ -36,7 +36,7 @@ xfs_init_local_fork(
 	int64_t			size)
 {
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
-	int			mem_size = size, real_size = 0;
+	int			mem_size = size;
 	bool			zero_terminate;
 
 	/*
@@ -50,8 +50,7 @@ xfs_init_local_fork(
 		mem_size++;
 
 	if (size) {
-		real_size = roundup(mem_size, 4);
-		ifp->if_u1.if_data = kmem_alloc(real_size, KM_NOFS);
+		ifp->if_u1.if_data = kmem_alloc(mem_size, KM_NOFS);
 		memcpy(ifp->if_u1.if_data, data, size);
 		if (zero_terminate)
 			ifp->if_u1.if_data[size] = '\0';
@@ -105,7 +104,7 @@ xfs_iformat_extents(
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
 	int			state = xfs_bmap_fork_to_state(whichfork);
-	int			nex = XFS_DFORK_NEXTENTS(dip, whichfork);
+	xfs_extnum_t		nex = xfs_dfork_nextents(dip, whichfork);
 	int			size = nex * sizeof(xfs_bmbt_rec_t);
 	struct xfs_iext_cursor	icur;
 	struct xfs_bmbt_rec	*dp;
@@ -117,8 +116,8 @@ xfs_iformat_extents(
 	 * we just bail out rather than crash in kmem_alloc() or memcpy() below.
 	 */
 	if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, mp, whichfork))) {
-		xfs_warn(ip->i_mount, "corrupt inode %Lu ((a)extents = %d).",
-			(unsigned long long) ip->i_ino, nex);
+		xfs_warn(ip->i_mount, "corrupt inode %llu ((a)extents = %llu).",
+			ip->i_ino, nex);
 		xfs_inode_verifier_error(ip, -EFSCORRUPTED,
 				"xfs_iformat_extents(1)", dip, sizeof(*dip),
 				__this_address);
@@ -230,7 +229,7 @@ xfs_iformat_data_fork(
 	 * depend on it.
 	 */
 	ip->i_df.if_format = dip->di_format;
-	ip->i_df.if_nextents = be32_to_cpu(dip->di_nextents);
+	ip->i_df.if_nextents = xfs_dfork_data_extents(dip);
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFIFO:
@@ -295,14 +294,14 @@ xfs_iformat_attr_fork(
 	struct xfs_inode	*ip,
 	struct xfs_dinode	*dip)
 {
+	xfs_extnum_t		naextents = xfs_dfork_attr_extents(dip);
 	int			error = 0;
 
 	/*
 	 * Initialize the extent count early, as the per-format routines may
 	 * depend on it.
 	 */
-	ip->i_afp = xfs_ifork_alloc(dip->di_aformat,
-				be16_to_cpu(dip->di_anextents));
+	ip->i_afp = xfs_ifork_alloc(dip->di_aformat, naextents);
 
 	switch (ip->i_afp->if_format) {
 	case XFS_DINODE_FMT_LOCAL:
@@ -497,12 +496,7 @@ xfs_idata_realloc(
 		return;
 	}
 
-	/*
-	 * For inline data, the underlying buffer must be a multiple of 4 bytes
-	 * in size so that it can be logged and stay on word boundaries.
-	 * We enforce that here.
-	 */
-	ifp->if_u1.if_data = krealloc(ifp->if_u1.if_data, roundup(new_size, 4),
+	ifp->if_u1.if_data = krealloc(ifp->if_u1.if_data, new_size,
 				      GFP_NOFS | __GFP_NOFAIL);
 	ifp->if_bytes = new_size;
 }
@@ -744,7 +738,8 @@ xfs_iext_count_may_overflow(
 	if (whichfork == XFS_COW_FORK)
 		return 0;
 
-	max_exts = (whichfork == XFS_ATTR_FORK) ? MAXAEXTNUM : MAXEXTNUM;
+	max_exts = xfs_iext_max_nextents(xfs_inode_has_large_extent_counts(ip),
+				whichfork);
 
 	if (XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
 		max_exts = 10;
@@ -755,3 +750,27 @@ xfs_iext_count_may_overflow(
 
 	return 0;
 }
+
+/*
+ * Upgrade this inode's extent counter fields to be able to handle a potential
+ * increase in the extent count by nr_to_add.  Normally this is the same
+ * quantity that caused xfs_iext_count_may_overflow() to return -EFBIG.
+ */
+int
+xfs_iext_count_upgrade(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	uint			nr_to_add)
+{
+	ASSERT(nr_to_add <= XFS_MAX_EXTCNT_UPGRADE_NR);
+
+	if (!xfs_has_large_extent_counts(ip->i_mount) ||
+	    xfs_inode_has_large_extent_counts(ip) ||
+	    XFS_TEST_ERROR(false, ip->i_mount, XFS_ERRTAG_REDUCE_MAX_IEXTENTS))
+		return -EFBIG;
+
+	ip->i_diflags2 |= XFS_DIFLAG2_NREXT64;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	return 0;
+}

fs/xfs/libxfs/xfs_inode_fork.h

@@ -21,9 +21,9 @@ struct xfs_ifork {
 		void		*if_root;	/* extent tree root */
 		char		*if_data;	/* inline file data */
 	} if_u1;
+	xfs_extnum_t		if_nextents;	/* # of extents in this fork */
 	short			if_broot_bytes;	/* bytes allocated for root */
 	int8_t			if_format;	/* format of this fork */
-	xfs_extnum_t		if_nextents;	/* # of extents in this fork */
 };
 
 /*
@@ -39,19 +39,6 @@ struct xfs_ifork {
  */
 #define XFS_IEXT_PUNCH_HOLE_CNT		(1)
 
-/*
- * Directory entry addition can cause the following,
- * 1. Data block can be added/removed.
- *    A new extent can cause extent count to increase by 1.
- * 2. Free disk block can be added/removed.
- *    Same behaviour as described above for Data block.
- * 3. Dabtree blocks.
- *    XFS_DA_NODE_MAXDEPTH blocks can be added. Each of these can be new
- *    extents. Hence extent count can increase by XFS_DA_NODE_MAXDEPTH.
- */
-#define XFS_IEXT_DIR_MANIP_CNT(mp) \
-	((XFS_DA_NODE_MAXDEPTH + 1 + 1) * (mp)->m_dir_geo->fsbcount)
-
 /*
  * Adding/removing an xattr can cause XFS_DA_NODE_MAXDEPTH extents to
  * be added. One extra extent for dabtree in case a local attr is
@@ -133,6 +120,65 @@ static inline int8_t xfs_ifork_format(struct xfs_ifork *ifp)
 	return ifp->if_format;
 }
 
+static inline xfs_extnum_t xfs_iext_max_nextents(bool has_large_extent_counts,
+				int whichfork)
+{
+	switch (whichfork) {
+	case XFS_DATA_FORK:
+	case XFS_COW_FORK:
+		if (has_large_extent_counts)
+			return XFS_MAX_EXTCNT_DATA_FORK_LARGE;
+		return XFS_MAX_EXTCNT_DATA_FORK_SMALL;
+
+	case XFS_ATTR_FORK:
+		if (has_large_extent_counts)
+			return XFS_MAX_EXTCNT_ATTR_FORK_LARGE;
+		return XFS_MAX_EXTCNT_ATTR_FORK_SMALL;
+
+	default:
+		ASSERT(0);
+		return 0;
+	}
+}
+
+static inline xfs_extnum_t
+xfs_dfork_data_extents(
+	struct xfs_dinode	*dip)
+{
+	if (xfs_dinode_has_large_extent_counts(dip))
+		return be64_to_cpu(dip->di_big_nextents);
+
+	return be32_to_cpu(dip->di_nextents);
+}
+
+static inline xfs_extnum_t
+xfs_dfork_attr_extents(
+	struct xfs_dinode	*dip)
+{
+	if (xfs_dinode_has_large_extent_counts(dip))
+		return be32_to_cpu(dip->di_big_anextents);
+
+	return be16_to_cpu(dip->di_anextents);
+}
+
+static inline xfs_extnum_t
+xfs_dfork_nextents(
+	struct xfs_dinode	*dip,
+	int			whichfork)
+{
+	switch (whichfork) {
+	case XFS_DATA_FORK:
+		return xfs_dfork_data_extents(dip);
+	case XFS_ATTR_FORK:
+		return xfs_dfork_attr_extents(dip);
+	default:
+		ASSERT(0);
+		break;
+	}
+
+	return 0;
+}
+
 struct xfs_ifork *xfs_ifork_alloc(enum xfs_dinode_fmt format,
 				xfs_extnum_t nextents);
 struct xfs_ifork *xfs_iext_state_to_fork(struct xfs_inode *ip, int state);
@@ -229,6 +275,8 @@ int xfs_ifork_verify_local_data(struct xfs_inode *ip);
 int xfs_ifork_verify_local_attr(struct xfs_inode *ip);
 int xfs_iext_count_may_overflow(struct xfs_inode *ip, int whichfork,
 		int nr_to_add);
+int xfs_iext_count_upgrade(struct xfs_trans *tp, struct xfs_inode *ip,
+		uint nr_to_add);
 
 /* returns true if the fork has extents but they are not read in yet. */
 static inline bool xfs_need_iread_extents(struct xfs_ifork *ifp)

fs/xfs/libxfs/xfs_log_format.h

@@ -69,7 +69,6 @@ static inline uint xlog_get_cycle(char *ptr)
 
 /* Log Clients */
 #define XFS_TRANSACTION		0x69
-#define XFS_VOLUME		0x2
 #define XFS_LOG			0xaa
 
 #define XLOG_UNMOUNT_TYPE	0x556e	/* Un for Unmount */
@@ -114,7 +113,12 @@ struct xfs_unmount_log_format {
 #define XLOG_REG_TYPE_CUD_FORMAT	24
 #define XLOG_REG_TYPE_BUI_FORMAT	25
 #define XLOG_REG_TYPE_BUD_FORMAT	26
-#define XLOG_REG_TYPE_MAX		26
+#define XLOG_REG_TYPE_ATTRI_FORMAT	27
+#define XLOG_REG_TYPE_ATTRD_FORMAT	28
+#define XLOG_REG_TYPE_ATTR_NAME	29
+#define XLOG_REG_TYPE_ATTR_VALUE	30
+#define XLOG_REG_TYPE_MAX		30
+
 
 /*
  * Flags to log operation header
@@ -237,6 +241,8 @@ typedef struct xfs_trans_header {
 #define	XFS_LI_CUD		0x1243
 #define	XFS_LI_BUI		0x1244	/* bmbt update intent */
 #define	XFS_LI_BUD		0x1245
+#define	XFS_LI_ATTRI		0x1246  /* attr set/remove intent*/
+#define	XFS_LI_ATTRD		0x1247  /* attr set/remove done */
 
 #define XFS_LI_TYPE_DESC \
 	{ XFS_LI_EFI,		"XFS_LI_EFI" }, \
@@ -252,7 +258,9 @@ typedef struct xfs_trans_header {
 	{ XFS_LI_CUI,		"XFS_LI_CUI" }, \
 	{ XFS_LI_CUD,		"XFS_LI_CUD" }, \
 	{ XFS_LI_BUI,		"XFS_LI_BUI" }, \
-	{ XFS_LI_BUD,		"XFS_LI_BUD" }
+	{ XFS_LI_BUD,		"XFS_LI_BUD" }, \
+	{ XFS_LI_ATTRI,		"XFS_LI_ATTRI" }, \
+	{ XFS_LI_ATTRD,		"XFS_LI_ATTRD" }
 
 /*
  * Inode Log Item Format definitions.
@@ -388,16 +396,41 @@ struct xfs_log_dinode {
 	uint32_t	di_nlink;	/* number of links to file */
 	uint16_t	di_projid_lo;	/* lower part of owner's project id */
 	uint16_t	di_projid_hi;	/* higher part of owner's project id */
-	uint8_t		di_pad[6];	/* unused, zeroed space */
-	uint16_t	di_flushiter;	/* incremented on flush */
+	union {
+		/* Number of data fork extents if NREXT64 is set */
+		uint64_t	di_big_nextents;
+
+		/* Padding for V3 inodes without NREXT64 set. */
+		uint64_t	di_v3_pad;
+
+		/* Padding and inode flush counter for V2 inodes. */
+		struct {
+			uint8_t	di_v2_pad[6];	/* V2 inode zeroed space */
+			uint16_t di_flushiter;	/* V2 inode incremented on flush */
+		};
+	};
 	xfs_log_timestamp_t di_atime;	/* time last accessed */
 	xfs_log_timestamp_t di_mtime;	/* time last modified */
 	xfs_log_timestamp_t di_ctime;	/* time created/inode modified */
 	xfs_fsize_t	di_size;	/* number of bytes in file */
 	xfs_rfsblock_t	di_nblocks;	/* # of direct & btree blocks used */
 	xfs_extlen_t	di_extsize;	/* basic/minimum extent size for file */
-	xfs_extnum_t	di_nextents;	/* number of extents in data fork */
-	xfs_aextnum_t	di_anextents;	/* number of extents in attribute fork*/
+	union {
+		/*
+		 * For V2 inodes and V3 inodes without NREXT64 set, this
+		 * is the number of data and attr fork extents.
+		 */
+		struct {
+			uint32_t  di_nextents;
+			uint16_t  di_anextents;
+		} __packed;
+
+		/* Number of attr fork extents if NREXT64 is set. */
+		struct {
+			uint32_t  di_big_anextents;
+			uint16_t  di_nrext64_pad;
+		} __packed;
+	} __packed;
 	uint8_t		di_forkoff;	/* attr fork offs, <<3 for 64b align */
 	int8_t		di_aformat;	/* format of attr fork's data */
 	uint32_t	di_dmevmask;	/* DMIG event mask */
@@ -869,4 +902,36 @@ struct xfs_icreate_log {
 	__be32		icl_gen;	/* inode generation number to use */
 };
 
+/*
+ * Flags for deferred attribute operations.
+ * Upper bits are flags, lower byte is type code
+ */
+#define XFS_ATTR_OP_FLAGS_SET		1	/* Set the attribute */
+#define XFS_ATTR_OP_FLAGS_REMOVE	2	/* Remove the attribute */
+#define XFS_ATTR_OP_FLAGS_REPLACE	3	/* Replace the attribute */
+#define XFS_ATTR_OP_FLAGS_TYPE_MASK	0xFF	/* Flags type mask */
+
+/*
+ * This is the structure used to lay out an attr log item in the
+ * log.
+ */
+struct xfs_attri_log_format {
+	uint16_t	alfi_type;	/* attri log item type */
+	uint16_t	alfi_size;	/* size of this item */
+	uint32_t	__pad;		/* pad to 64 bit aligned */
+	uint64_t	alfi_id;	/* attri identifier */
+	uint64_t	alfi_ino;	/* the inode for this attr operation */
+	uint32_t	alfi_op_flags;	/* marks the op as a set or remove */
+	uint32_t	alfi_name_len;	/* attr name length */
+	uint32_t	alfi_value_len;	/* attr value length */
+	uint32_t	alfi_attr_flags;/* attr flags */
+};
+
+struct xfs_attrd_log_format {
+	uint16_t	alfd_type;	/* attrd log item type */
+	uint16_t	alfd_size;	/* size of this item */
+	uint32_t	__pad;		/* pad to 64 bit aligned */
+	uint64_t	alfd_alf_id;	/* id of corresponding attri */
+};
+
 #endif /* __XFS_LOG_FORMAT_H__ */

fs/xfs/libxfs/xfs_log_recover.h

@@ -72,6 +72,8 @@ extern const struct xlog_recover_item_ops xlog_rui_item_ops;
 extern const struct xlog_recover_item_ops xlog_rud_item_ops;
 extern const struct xlog_recover_item_ops xlog_cui_item_ops;
 extern const struct xlog_recover_item_ops xlog_cud_item_ops;
+extern const struct xlog_recover_item_ops xlog_attri_item_ops;
+extern const struct xlog_recover_item_ops xlog_attrd_item_ops;
 
 /*
  * Macros, structures, prototypes for internal log manager use.

fs/xfs/libxfs/xfs_log_rlimit.c

@@ -14,6 +14,7 @@
 #include "xfs_trans_space.h"
 #include "xfs_da_btree.h"
 #include "xfs_bmap_btree.h"
+#include "xfs_trace.h"
 
 /*
  * Calculate the maximum length in bytes that would be required for a local
@@ -36,6 +37,65 @@ xfs_log_calc_max_attrsetm_res(
 		M_RES(mp)->tr_attrsetrt.tr_logres * nblks;
 }
 
+/*
+ * Compute an alternate set of log reservation sizes for use exclusively with
+ * minimum log size calculations.
+ */
+static void
+xfs_log_calc_trans_resv_for_minlogblocks(
+	struct xfs_mount	*mp,
+	struct xfs_trans_resv	*resv)
+{
+	unsigned int		rmap_maxlevels = mp->m_rmap_maxlevels;
+
+	/*
+	 * In the early days of rmap+reflink, we always set the rmap maxlevels
+	 * to 9 even if the AG was small enough that it would never grow to
+	 * that height.  Transaction reservation sizes influence the minimum
+	 * log size calculation, which influences the size of the log that mkfs
+	 * creates.  Use the old value here to ensure that newly formatted
+	 * small filesystems will mount on older kernels.
+	 */
+	if (xfs_has_rmapbt(mp) && xfs_has_reflink(mp))
+		mp->m_rmap_maxlevels = XFS_OLD_REFLINK_RMAP_MAXLEVELS;
+
+	xfs_trans_resv_calc(mp, resv);
+
+	if (xfs_has_reflink(mp)) {
+		/*
+		 * In the early days of reflink, typical log operation counts
+		 * were greatly overestimated.
+		 */
+		resv->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT_REFLINK;
+		resv->tr_itruncate.tr_logcount =
+				XFS_ITRUNCATE_LOG_COUNT_REFLINK;
+		resv->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT_REFLINK;
+	} else if (xfs_has_rmapbt(mp)) {
+		/*
+		 * In the early days of non-reflink rmap, the impact of rmapbt
+		 * updates on log counts were not taken into account at all.
+		 */
+		resv->tr_write.tr_logcount = XFS_WRITE_LOG_COUNT;
+		resv->tr_itruncate.tr_logcount = XFS_ITRUNCATE_LOG_COUNT;
+		resv->tr_qm_dqalloc.tr_logcount = XFS_WRITE_LOG_COUNT;
+	}
+
+	/*
+	 * In the early days of reflink, we did not use deferred refcount
+	 * update log items, so log reservations must be recomputed using the
+	 * old calculations.
+	 */
+	resv->tr_write.tr_logres =
+			xfs_calc_write_reservation_minlogsize(mp);
+	resv->tr_itruncate.tr_logres =
+			xfs_calc_itruncate_reservation_minlogsize(mp);
+	resv->tr_qm_dqalloc.tr_logres =
+			xfs_calc_qm_dqalloc_reservation_minlogsize(mp);
+
+	/* Put everything back the way it was.  This goes at the end. */
+	mp->m_rmap_maxlevels = rmap_maxlevels;
+}
+
 /*
  * Iterate over the log space reservation table to figure out and return
  * the maximum one in terms of the pre-calculated values which were done
@@ -46,19 +106,25 @@ xfs_log_get_max_trans_res(
 	struct xfs_mount	*mp,
 	struct xfs_trans_res	*max_resp)
 {
+	struct xfs_trans_resv	resv = {};
 	struct xfs_trans_res	*resp;
 	struct xfs_trans_res	*end_resp;
+	unsigned int		i;
 	int			log_space = 0;
 	int			attr_space;
 
 	attr_space = xfs_log_calc_max_attrsetm_res(mp);
 
-	resp = (struct xfs_trans_res *)M_RES(mp);
-	end_resp = (struct xfs_trans_res *)(M_RES(mp) + 1);
-	for (; resp < end_resp; resp++) {
+	xfs_log_calc_trans_resv_for_minlogblocks(mp, &resv);
+
+	resp = (struct xfs_trans_res *)&resv;
+	end_resp = (struct xfs_trans_res *)(&resv + 1);
+	for (i = 0; resp < end_resp; i++, resp++) {
 		int		tmp = resp->tr_logcount > 1 ?
 				      resp->tr_logres * resp->tr_logcount :
 				      resp->tr_logres;
+
+		trace_xfs_trans_resv_calc_minlogsize(mp, i, resp);
 		if (log_space < tmp) {
 			log_space = tmp;
 			*max_resp = *resp;		/* struct copy */
@@ -66,9 +132,10 @@ xfs_log_get_max_trans_res(
 	}
 
 	if (attr_space > log_space) {
-		*max_resp = M_RES(mp)->tr_attrsetm;	/* struct copy */
+		*max_resp = resv.tr_attrsetm;	/* struct copy */
 		max_resp->tr_logres = attr_space;
 	}
+	trace_xfs_log_get_max_trans_res(mp, max_resp);
 }
 
 /*

fs/xfs/libxfs/xfs_quota_defs.h

@@ -16,7 +16,6 @@
  * and quota-limits. This is a waste in the common case, but hey ...
  */
 typedef uint64_t	xfs_qcnt_t;
-typedef uint16_t	xfs_qwarncnt_t;
 
 typedef uint8_t		xfs_dqtype_t;
 
@@ -29,8 +28,8 @@ typedef uint8_t		xfs_dqtype_t;
 /*
  * flags for q_flags field in the dquot.
  */
-#define XFS_DQFLAG_DIRTY	(1 << 0)	/* dquot is dirty */
-#define XFS_DQFLAG_FREEING	(1 << 1)	/* dquot is being torn down */
+#define XFS_DQFLAG_DIRTY	(1u << 0)	/* dquot is dirty */
+#define XFS_DQFLAG_FREEING	(1u << 1)	/* dquot is being torn down */
 
 #define XFS_DQFLAG_STRINGS \
 	{ XFS_DQFLAG_DIRTY,	"DIRTY" }, \
@@ -73,29 +72,45 @@ typedef uint8_t		xfs_dqtype_t;
  * to a single function. None of these XFS_QMOPT_* flags are meant to have
  * persistent values (ie. their values can and will change between versions)
  */
-#define XFS_QMOPT_UQUOTA	0x0000004 /* user dquot requested */
-#define XFS_QMOPT_PQUOTA	0x0000008 /* project dquot requested */
-#define XFS_QMOPT_FORCE_RES	0x0000010 /* ignore quota limits */
-#define XFS_QMOPT_SBVERSION	0x0000040 /* change superblock version num */
-#define XFS_QMOPT_GQUOTA	0x0002000 /* group dquot requested */
+#define XFS_QMOPT_UQUOTA	(1u << 0) /* user dquot requested */
+#define XFS_QMOPT_GQUOTA	(1u << 1) /* group dquot requested */
+#define XFS_QMOPT_PQUOTA	(1u << 2) /* project dquot requested */
+#define XFS_QMOPT_FORCE_RES	(1u << 3) /* ignore quota limits */
+#define XFS_QMOPT_SBVERSION	(1u << 4) /* change superblock version num */
 
 /*
  * flags to xfs_trans_mod_dquot to indicate which field needs to be
  * modified.
  */
-#define XFS_QMOPT_RES_REGBLKS	0x0010000
-#define XFS_QMOPT_RES_RTBLKS	0x0020000
-#define XFS_QMOPT_BCOUNT	0x0040000
-#define XFS_QMOPT_ICOUNT	0x0080000
-#define XFS_QMOPT_RTBCOUNT	0x0100000
-#define XFS_QMOPT_DELBCOUNT	0x0200000
-#define XFS_QMOPT_DELRTBCOUNT	0x0400000
-#define XFS_QMOPT_RES_INOS	0x0800000
+#define XFS_QMOPT_RES_REGBLKS	(1u << 7)
+#define XFS_QMOPT_RES_RTBLKS	(1u << 8)
+#define XFS_QMOPT_BCOUNT	(1u << 9)
+#define XFS_QMOPT_ICOUNT	(1u << 10)
+#define XFS_QMOPT_RTBCOUNT	(1u << 11)
+#define XFS_QMOPT_DELBCOUNT	(1u << 12)
+#define XFS_QMOPT_DELRTBCOUNT	(1u << 13)
+#define XFS_QMOPT_RES_INOS	(1u << 14)
 
 /*
  * flags for dqalloc.
  */
-#define XFS_QMOPT_INHERIT	0x1000000
+#define XFS_QMOPT_INHERIT	(1u << 31)
+
+#define XFS_QMOPT_FLAGS \
+	{ XFS_QMOPT_UQUOTA,		"UQUOTA" }, \
+	{ XFS_QMOPT_PQUOTA,		"PQUOTA" }, \
+	{ XFS_QMOPT_FORCE_RES,		"FORCE_RES" }, \
+	{ XFS_QMOPT_SBVERSION,		"SBVERSION" }, \
+	{ XFS_QMOPT_GQUOTA,		"GQUOTA" }, \
+	{ XFS_QMOPT_INHERIT,		"INHERIT" }, \
+	{ XFS_QMOPT_RES_REGBLKS,	"RES_REGBLKS" }, \
+	{ XFS_QMOPT_RES_RTBLKS,		"RES_RTBLKS" }, \
+	{ XFS_QMOPT_BCOUNT,		"BCOUNT" }, \
+	{ XFS_QMOPT_ICOUNT,		"ICOUNT" }, \
+	{ XFS_QMOPT_RTBCOUNT,		"RTBCOUNT" }, \
+	{ XFS_QMOPT_DELBCOUNT,		"DELBCOUNT" }, \
+	{ XFS_QMOPT_DELRTBCOUNT,	"DELRTBCOUNT" }, \
+	{ XFS_QMOPT_RES_INOS,		"RES_INOS" }
 
 /*
  * flags to xfs_trans_mod_dquot.
@@ -114,6 +129,7 @@ typedef uint8_t		xfs_dqtype_t;
 		(XFS_QMOPT_UQUOTA | XFS_QMOPT_PQUOTA | XFS_QMOPT_GQUOTA)
 #define XFS_QMOPT_RESBLK_MASK	(XFS_QMOPT_RES_REGBLKS | XFS_QMOPT_RES_RTBLKS)
 
+
 extern xfs_failaddr_t xfs_dquot_verify(struct xfs_mount *mp,
 		struct xfs_disk_dquot *ddq, xfs_dqid_t id);
 extern xfs_failaddr_t xfs_dqblk_verify(struct xfs_mount *mp,

fs/xfs/libxfs/xfs_refcount.c

@@ -886,8 +886,13 @@ xfs_refcount_still_have_space(
 {
 	unsigned long			overhead;
 
-	overhead = cur->bc_ag.refc.shape_changes *
-			xfs_allocfree_log_count(cur->bc_mp, 1);
+	/*
+	 * Worst case estimate: full splits of the free space and rmap btrees
+	 * to handle each of the shape changes to the refcount btree.
+	 */
+	overhead = xfs_allocfree_block_count(cur->bc_mp,
+				cur->bc_ag.refc.shape_changes);
+	overhead += cur->bc_mp->m_refc_maxlevels;
 	overhead *= cur->bc_mp->m_sb.sb_blocksize;
 
 	/*
@@ -960,6 +965,7 @@ xfs_refcount_adjust_extents(
 			 * Either cover the hole (increment) or
 			 * delete the range (decrement).
 			 */
+			cur->bc_ag.refc.nr_ops++;
 			if (tmp.rc_refcount) {
 				error = xfs_refcount_insert(cur, &tmp,
 						&found_tmp);
@@ -970,7 +976,6 @@ xfs_refcount_adjust_extents(
 					error = -EFSCORRUPTED;
 					goto out_error;
 				}
-				cur->bc_ag.refc.nr_ops++;
 			} else {
 				fsbno = XFS_AGB_TO_FSB(cur->bc_mp,
 						cur->bc_ag.pag->pag_agno,
@@ -1001,11 +1006,11 @@ xfs_refcount_adjust_extents(
 		ext.rc_refcount += adj;
 		trace_xfs_refcount_modify_extent(cur->bc_mp,
 				cur->bc_ag.pag->pag_agno, &ext);
+		cur->bc_ag.refc.nr_ops++;
 		if (ext.rc_refcount > 1) {
 			error = xfs_refcount_update(cur, &ext);
 			if (error)
 				goto out_error;
-			cur->bc_ag.refc.nr_ops++;
 		} else if (ext.rc_refcount == 1) {
 			error = xfs_refcount_delete(cur, &found_rec);
 			if (error)
@@ -1014,7 +1019,6 @@ xfs_refcount_adjust_extents(
 				error = -EFSCORRUPTED;
 				goto out_error;
 			}
-			cur->bc_ag.refc.nr_ops++;
 			goto advloop;
 		} else {
 			fsbno = XFS_AGB_TO_FSB(cur->bc_mp,

fs/xfs/libxfs/xfs_refcount.h

@@ -67,14 +67,17 @@ extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
  * log (plus any key updates) so we'll conservatively assume 32 bytes
  * per record.  We must also leave space for btree splits on both ends
  * of the range and space for the CUD and a new CUI.
+ *
+ * Each EFI that we attach to the transaction is assumed to consume ~32 bytes.
+ * This is a low estimate for an EFI tracking a single extent (16 bytes for the
+ * EFI header, 16 for the extent, and 12 for the xlog op header), but the
+ * estimate is acceptable if there's more than one extent being freed.
+ * In the worst case of freeing every other block during a refcount decrease
+ * operation, we amortize the space used for one EFI log item across 16
+ * extents.
  */
 #define XFS_REFCOUNT_ITEM_OVERHEAD	32
 
-static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res)
-{
-	return (log_res * 3 / 4) / XFS_REFCOUNT_ITEM_OVERHEAD;
-}
-
 extern int xfs_refcount_has_record(struct xfs_btree_cur *cur,
 		xfs_agblock_t bno, xfs_extlen_t len, bool *exists);
 union xfs_btree_rec;

fs/xfs/libxfs/xfs_rmap.h

@@ -122,8 +122,8 @@ int xfs_rmap_free(struct xfs_trans *tp, struct xfs_buf *agbp,
 		  const struct xfs_owner_info *oinfo);
 
 int xfs_rmap_lookup_le(struct xfs_btree_cur *cur, xfs_agblock_t bno,
-		xfs_extlen_t len, uint64_t owner, uint64_t offset,
-		unsigned int flags, int *stat);
+		uint64_t owner, uint64_t offset, unsigned int flags,
+		struct xfs_rmap_irec *irec, int *stat);
 int xfs_rmap_lookup_eq(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		xfs_extlen_t len, uint64_t owner, uint64_t offset,
 		unsigned int flags, int *stat);
@@ -184,9 +184,6 @@ int xfs_rmap_finish_one(struct xfs_trans *tp, enum xfs_rmap_intent_type type,
 		xfs_fsblock_t startblock, xfs_filblks_t blockcount,
 		xfs_exntst_t state, struct xfs_btree_cur **pcur);
 
-int xfs_rmap_find_left_neighbor(struct xfs_btree_cur *cur, xfs_agblock_t bno,
-		uint64_t owner, uint64_t offset, unsigned int flags,
-		struct xfs_rmap_irec *irec, int	*stat);
 int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		uint64_t owner, uint64_t offset, unsigned int flags,
 		struct xfs_rmap_irec *irec, int	*stat);

fs/xfs/libxfs/xfs_rtbitmap.c

@@ -1008,6 +1008,7 @@ xfs_rtfree_extent(
 /* Find all the free records within a given range. */
 int
 xfs_rtalloc_query_range(
+	struct xfs_mount		*mp,
 	struct xfs_trans		*tp,
 	const struct xfs_rtalloc_rec	*low_rec,
 	const struct xfs_rtalloc_rec	*high_rec,
@@ -1015,7 +1016,6 @@ xfs_rtalloc_query_range(
 	void				*priv)
 {
 	struct xfs_rtalloc_rec		rec;
-	struct xfs_mount		*mp = tp->t_mountp;
 	xfs_rtblock_t			rtstart;
 	xfs_rtblock_t			rtend;
 	xfs_rtblock_t			high_key;
@@ -1048,7 +1048,7 @@ xfs_rtalloc_query_range(
 			rec.ar_startext = rtstart;
 			rec.ar_extcount = rtend - rtstart + 1;
 
-			error = fn(tp, &rec, priv);
+			error = fn(mp, tp, &rec, priv);
 			if (error)
 				break;
 		}
@@ -1062,6 +1062,7 @@ xfs_rtalloc_query_range(
 /* Find all the free records. */
 int
 xfs_rtalloc_query_all(
+	struct xfs_mount		*mp,
 	struct xfs_trans		*tp,
 	xfs_rtalloc_query_range_fn	fn,
 	void				*priv)
@@ -1069,10 +1070,10 @@ xfs_rtalloc_query_all(
 	struct xfs_rtalloc_rec		keys[2];
 
 	keys[0].ar_startext = 0;
-	keys[1].ar_startext = tp->t_mountp->m_sb.sb_rextents - 1;
+	keys[1].ar_startext = mp->m_sb.sb_rextents - 1;
 	keys[0].ar_extcount = keys[1].ar_extcount = 0;
 
-	return xfs_rtalloc_query_range(tp, &keys[0], &keys[1], fn, priv);
+	return xfs_rtalloc_query_range(mp, tp, &keys[0], &keys[1], fn, priv);
 }
 
 /* Is the given extent all free? */

fs/xfs/libxfs/xfs_shared.h

@@ -54,13 +54,23 @@ void	xfs_log_get_max_trans_res(struct xfs_mount *mp,
 /*
  * Values for t_flags.
  */
-#define	XFS_TRANS_DIRTY		0x01	/* something needs to be logged */
-#define	XFS_TRANS_SB_DIRTY	0x02	/* superblock is modified */
-#define	XFS_TRANS_PERM_LOG_RES	0x04	/* xact took a permanent log res */
-#define	XFS_TRANS_SYNC		0x08	/* make commit synchronous */
-#define XFS_TRANS_RESERVE	0x20    /* OK to use reserved data blocks */
-#define XFS_TRANS_NO_WRITECOUNT 0x40	/* do not elevate SB writecount */
-#define XFS_TRANS_RES_FDBLKS	0x80	/* reserve newly freed blocks */
+/* Transaction needs to be logged */
+#define XFS_TRANS_DIRTY			(1u << 0)
+/* Superblock is dirty and needs to be logged */
+#define XFS_TRANS_SB_DIRTY		(1u << 1)
+/* Transaction took a permanent log reservation */
+#define XFS_TRANS_PERM_LOG_RES		(1u << 2)
+/* Synchronous transaction commit needed */
+#define XFS_TRANS_SYNC			(1u << 3)
+/* Transaction can use reserve block pool */
+#define XFS_TRANS_RESERVE		(1u << 4)
+/* Transaction should avoid VFS level superblock write accounting */
+#define XFS_TRANS_NO_WRITECOUNT		(1u << 5)
+/* Transaction has freed blocks returned to it's reservation */
+#define XFS_TRANS_RES_FDBLKS		(1u << 6)
+/* Transaction contains an intent done log item */
+#define XFS_TRANS_HAS_INTENT_DONE	(1u << 7)
+
 /*
  * LOWMODE is used by the allocator to activate the lowspace algorithm - when
  * free space is running low the extent allocator may choose to allocate an

fs/xfs/libxfs/xfs_trans_resv.h

@@ -73,7 +73,6 @@ struct xfs_trans_resv {
 #define	XFS_DEFAULT_LOG_COUNT		1
 #define	XFS_DEFAULT_PERM_LOG_COUNT	2
 #define	XFS_ITRUNCATE_LOG_COUNT		2
-#define	XFS_ITRUNCATE_LOG_COUNT_REFLINK	8
 #define XFS_INACTIVE_LOG_COUNT		2
 #define	XFS_CREATE_LOG_COUNT		2
 #define	XFS_CREATE_TMPFILE_LOG_COUNT	2
@@ -83,13 +82,24 @@ struct xfs_trans_resv {
 #define	XFS_LINK_LOG_COUNT		2
 #define	XFS_RENAME_LOG_COUNT		2
 #define	XFS_WRITE_LOG_COUNT		2
-#define	XFS_WRITE_LOG_COUNT_REFLINK	8
 #define	XFS_ADDAFORK_LOG_COUNT		2
 #define	XFS_ATTRINVAL_LOG_COUNT		1
 #define	XFS_ATTRSET_LOG_COUNT		3
 #define	XFS_ATTRRM_LOG_COUNT		3
 
+/*
+ * Original log operation counts were overestimated in the early days of
+ * reflink.  These are retained here purely for minimum log size calculations
+ * and must not be used for runtime reservations.
+ */
+#define	XFS_ITRUNCATE_LOG_COUNT_REFLINK	8
+#define	XFS_WRITE_LOG_COUNT_REFLINK	8
+
 void xfs_trans_resv_calc(struct xfs_mount *mp, struct xfs_trans_resv *resp);
-uint xfs_allocfree_log_count(struct xfs_mount *mp, uint num_ops);
+uint xfs_allocfree_block_count(struct xfs_mount *mp, uint num_ops);
+
+unsigned int xfs_calc_itruncate_reservation_minlogsize(struct xfs_mount *mp);
+unsigned int xfs_calc_write_reservation_minlogsize(struct xfs_mount *mp);
+unsigned int xfs_calc_qm_dqalloc_reservation_minlogsize(struct xfs_mount *mp);
 
 #endif	/* __XFS_TRANS_RESV_H__ */

fs/xfs/scrub/common.c

@@ -23,6 +23,8 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_log.h"
 #include "xfs_trans_priv.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
 #include "xfs_attr.h"
 #include "xfs_reflink.h"
 #include "xfs_ag.h"

fs/xfs/xfs_attr_list.c

@@ -15,6 +15,7 @@
 #include "xfs_inode.h"
 #include "xfs_trans.h"
 #include "xfs_bmap.h"
+#include "xfs_da_btree.h"
 #include "xfs_attr.h"
 #include "xfs_attr_sf.h"
 #include "xfs_attr_leaf.h"