1 files changed, 264 insertions, 37 deletions

diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index ca2941ab6cbc..2eb0c6011a2e 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -19,6 +19,7 @@
 #include "xfs_log.h"
 #include "xfs_log_priv.h"
 #include "xfs_error.h"
+#include "xfs_rtbitmap.h"
 
 #include <linux/iversion.h>
 
@@ -29,6 +30,189 @@ static inline struct xfs_inode_log_item *INODE_ITEM(struct xfs_log_item *lip)
 	return container_of(lip, struct xfs_inode_log_item, ili_item);
 }
 
+static uint64_t
+xfs_inode_item_sort(
+	struct xfs_log_item	*lip)
+{
+	return INODE_ITEM(lip)->ili_inode->i_ino;
+}
+
+#ifdef DEBUG_EXPENSIVE
+static void
+xfs_inode_item_precommit_check(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_dinode	*dip;
+	xfs_failaddr_t		fa;
+
+	dip = kzalloc(mp->m_sb.sb_inodesize, GFP_KERNEL | GFP_NOFS);
+	if (!dip) {
+		ASSERT(dip != NULL);
+		return;
+	}
+
+	xfs_inode_to_disk(ip, dip, 0);
+	xfs_dinode_calc_crc(mp, dip);
+	fa = xfs_dinode_verify(mp, ip->i_ino, dip);
+	if (fa) {
+		xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__, dip,
+				sizeof(*dip), fa);
+		xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+		ASSERT(fa == NULL);
+	}
+	kfree(dip);
+}
+#else
+# define xfs_inode_item_precommit_check(ip)	((void)0)
+#endif
+
+/*
+ * Prior to finally logging the inode, we have to ensure that all the
+ * per-modification inode state changes are applied. This includes VFS inode
+ * state updates, format conversions, verifier state synchronisation and
+ * ensuring the inode buffer remains in memory whilst the inode is dirty.
+ *
+ * We have to be careful when we grab the inode cluster buffer due to lock
+ * ordering constraints. The unlinked inode modifications (xfs_iunlink_item)
+ * require AGI -> inode cluster buffer lock order. The inode cluster buffer is
+ * not locked until ->precommit, so it happens after everything else has been
+ * modified.
+ *
+ * Further, we have AGI -> AGF lock ordering, and with O_TMPFILE handling we
+ * have AGI -> AGF -> iunlink item -> inode cluster buffer lock order. Hence we
+ * cannot safely lock the inode cluster buffer in xfs_trans_log_inode() because
+ * it can be called on a inode (e.g. via bumplink/droplink) before we take the
+ * AGF lock modifying directory blocks.
+ *
+ * Rather than force a complete rework of all the transactions to call
+ * xfs_trans_log_inode() once and once only at the end of every transaction, we
+ * move the pinning of the inode cluster buffer to a ->precommit operation. This
+ * matches how the xfs_iunlink_item locks the inode cluster buffer, and it
+ * ensures that the inode cluster buffer locking is always done last in a
+ * transaction. i.e. we ensure the lock order is always AGI -> AGF -> inode
+ * cluster buffer.
+ *
+ * If we return the inode number as the precommit sort key then we'll also
+ * guarantee that the order all inode cluster buffer locking is the same all the
+ * inodes and unlink items in the transaction.
+ */
+static int
+xfs_inode_item_precommit(
+	struct xfs_trans	*tp,
+	struct xfs_log_item	*lip)
+{
+	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
+	struct xfs_inode	*ip = iip->ili_inode;
+	struct inode		*inode = VFS_I(ip);
+	unsigned int		flags = iip->ili_dirty_flags;
+
+	/*
+	 * Don't bother with i_lock for the I_DIRTY_TIME check here, as races
+	 * don't matter - we either will need an extra transaction in 24 hours
+	 * to log the timestamps, or will clear already cleared fields in the
+	 * worst case.
+	 */
+	if (inode_state_read_once(inode) & I_DIRTY_TIME) {
+		spin_lock(&inode->i_lock);
+		inode_state_clear(inode, I_DIRTY_TIME);
+		spin_unlock(&inode->i_lock);
+	}
+
+	/*
+	 * If we're updating the inode core or the timestamps and it's possible
+	 * to upgrade this inode to bigtime format, do so now.
+	 */
+	if ((flags & (XFS_ILOG_CORE | XFS_ILOG_TIMESTAMP)) &&
+	    xfs_has_bigtime(ip->i_mount) &&
+	    !xfs_inode_has_bigtime(ip)) {
+		ip->i_diflags2 |= XFS_DIFLAG2_BIGTIME;
+		flags |= XFS_ILOG_CORE;
+	}
+
+	/*
+	 * Inode verifiers do not check that the extent size hints are an
+	 * integer multiple of the rt extent size on a directory with
+	 * rtinherit flags set.  If we're logging a directory that is
+	 * misconfigured in this way, clear the bad hints.
+	 */
+	if (ip->i_diflags & XFS_DIFLAG_RTINHERIT) {
+		if ((ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) &&
+		    xfs_extlen_to_rtxmod(ip->i_mount, ip->i_extsize) > 0) {
+			ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE |
+					   XFS_DIFLAG_EXTSZINHERIT);
+			ip->i_extsize = 0;
+			flags |= XFS_ILOG_CORE;
+		}
+		if ((ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) &&
+		    xfs_extlen_to_rtxmod(ip->i_mount, ip->i_cowextsize) > 0) {
+			ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE;
+			ip->i_cowextsize = 0;
+			flags |= XFS_ILOG_CORE;
+		}
+	}
+
+	spin_lock(&iip->ili_lock);
+	if (!iip->ili_item.li_buf) {
+		struct xfs_buf	*bp;
+		int		error;
+
+		/*
+		 * We hold the ILOCK here, so this inode is not going to be
+		 * flushed while we are here. Further, because there is no
+		 * buffer attached to the item, we know that there is no IO in
+		 * progress, so nothing will clear the ili_fields while we read
+		 * in the buffer. Hence we can safely drop the spin lock and
+		 * read the buffer knowing that the state will not change from
+		 * here.
+		 */
+		spin_unlock(&iip->ili_lock);
+		error = xfs_imap_to_bp(ip->i_mount, tp, &ip->i_imap, &bp);
+		if (error)
+			return error;
+
+		/*
+		 * We need an explicit buffer reference for the log item but
+		 * don't want the buffer to remain attached to the transaction.
+		 * Hold the buffer but release the transaction reference once
+		 * we've attached the inode log item to the buffer log item
+		 * list.
+		 */
+		xfs_buf_hold(bp);
+		spin_lock(&iip->ili_lock);
+		iip->ili_item.li_buf = bp;
+		bp->b_iodone = xfs_buf_inode_iodone;
+		list_add_tail(&iip->ili_item.li_bio_list, &bp->b_li_list);
+		xfs_trans_brelse(tp, bp);
+	}
+
+	/*
+	 * Store the dirty flags back into the inode item as this state is used
+	 * later on in xfs_inode_item_committing() to determine whether the
+	 * transaction is relevant to fsync state or not.
+	 */
+	iip->ili_dirty_flags = flags;
+
+	/*
+	 * Convert the flags on-disk fields that have been modified in the
+	 * transaction so that ili_fields tracks the changes correctly.
+	 */
+	if (flags & XFS_ILOG_IVERSION)
+		flags = ((flags & ~XFS_ILOG_IVERSION) | XFS_ILOG_CORE);
+
+	/*
+	 * Always OR in the bits from the ili_last_fields field.  This is to
+	 * coordinate with the xfs_iflush() and xfs_buf_inode_iodone() routines
+	 * in the eventual clearing of the ili_fields bits.  See the big comment
+	 * in xfs_iflush() for an explanation of this coordination mechanism.
+	 */
+	iip->ili_fields |= (flags | iip->ili_last_fields);
+	spin_unlock(&iip->ili_lock);
+
+	xfs_inode_item_precommit_check(ip);
+	return 0;
+}
+
 /*
  * The logged size of an inode fork is always the current size of the inode
  * fork. This means that when an inode fork is relogged, the size of the logged
@@ -62,6 +246,7 @@ xfs_inode_item_data_fork_size(
 		}
 		break;
 	case XFS_DINODE_FMT_BTREE:
+	case XFS_DINODE_FMT_META_BTREE:
 		if ((iip->ili_fields & XFS_ILOG_DBROOT) &&
 		    ip->i_df.if_broot_bytes > 0) {
 			*nbytes += ip->i_df.if_broot_bytes;
@@ -182,6 +367,7 @@ xfs_inode_item_format_data_fork(
 		}
 		break;
 	case XFS_DINODE_FMT_BTREE:
+	case XFS_DINODE_FMT_META_BTREE:
 		iip->ili_fields &=
 			~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | XFS_ILOG_DEV);
 
@@ -204,11 +390,10 @@ xfs_inode_item_format_data_fork(
 			~(XFS_ILOG_DEXT | XFS_ILOG_DBROOT | XFS_ILOG_DEV);
 		if ((iip->ili_fields & XFS_ILOG_DDATA) &&
 		    ip->i_df.if_bytes > 0) {
-			ASSERT(ip->i_df.if_u1.if_data != NULL);
+			ASSERT(ip->i_df.if_data != NULL);
 			ASSERT(ip->i_disk_size > 0);
 			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_ILOCAL,
-					ip->i_df.if_u1.if_data,
-					ip->i_df.if_bytes);
+					ip->i_df.if_data, ip->i_df.if_bytes);
 			ilf->ilf_dsize = (unsigned)ip->i_df.if_bytes;
 			ilf->ilf_size++;
 		} else {
@@ -283,10 +468,9 @@ xfs_inode_item_format_attr_fork(
 
 		if ((iip->ili_fields & XFS_ILOG_ADATA) &&
 		    ip->i_af.if_bytes > 0) {
-			ASSERT(ip->i_af.if_u1.if_data != NULL);
+			ASSERT(ip->i_af.if_data != NULL);
 			xlog_copy_iovec(lv, vecp, XLOG_REG_TYPE_IATTR_LOCAL,
-					ip->i_af.if_u1.if_data,
-					ip->i_af.if_bytes);
+					ip->i_af.if_data, ip->i_af.if_bytes);
 			ilf->ilf_asize = (unsigned)ip->i_af.if_bytes;
 			ilf->ilf_size++;
 		} else {
@@ -378,10 +562,9 @@ xfs_inode_to_log_dinode(
 	to->di_projid_lo = ip->i_projid & 0xffff;
 	to->di_projid_hi = ip->i_projid >> 16;
 
-	memset(to->di_pad3, 0, sizeof(to->di_pad3));
-	to->di_atime = xfs_inode_to_log_dinode_ts(ip, inode->i_atime);
-	to->di_mtime = xfs_inode_to_log_dinode_ts(ip, inode->i_mtime);
-	to->di_ctime = xfs_inode_to_log_dinode_ts(ip, inode->i_ctime);
+	to->di_atime = xfs_inode_to_log_dinode_ts(ip, inode_get_atime(inode));
+	to->di_mtime = xfs_inode_to_log_dinode_ts(ip, inode_get_mtime(inode));
+	to->di_ctime = xfs_inode_to_log_dinode_ts(ip, inode_get_ctime(inode));
 	to->di_nlink = inode->i_nlink;
 	to->di_gen = inode->i_generation;
 	to->di_mode = inode->i_mode;
@@ -403,16 +586,26 @@ xfs_inode_to_log_dinode(
 		to->di_changecount = inode_peek_iversion(inode);
 		to->di_crtime = xfs_inode_to_log_dinode_ts(ip, ip->i_crtime);
 		to->di_flags2 = ip->i_diflags2;
+		/* also covers the di_used_blocks union arm: */
 		to->di_cowextsize = ip->i_cowextsize;
 		to->di_ino = ip->i_ino;
 		to->di_lsn = 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_v3_pad = 0;
+
+		/* dummy value for initialisation */
+		to->di_crc = 0;
+
+		if (xfs_is_metadir_inode(ip))
+			to->di_metatype = ip->i_metatype;
+		else
+			to->di_metatype = 0;
 	} else {
 		to->di_version = 2;
 		to->di_flushiter = ip->i_flushiter;
 		memset(to->di_v2_pad, 0, sizeof(to->di_v2_pad));
+		to->di_metatype = 0;
 	}
 
 	xfs_inode_to_log_dinode_iext_counters(ip, to);
@@ -501,7 +694,7 @@ xfs_inode_item_pin(
 {
 	struct xfs_inode	*ip = INODE_ITEM(lip)->ili_inode;
 
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
 	ASSERT(lip->li_buf);
 
 	trace_xfs_inode_pin(ip, _RET_IP_);
@@ -526,13 +719,24 @@ xfs_inode_item_unpin(
 	struct xfs_log_item	*lip,
 	int			remove)
 {
-	struct xfs_inode	*ip = INODE_ITEM(lip)->ili_inode;
+	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
+	struct xfs_inode	*ip = iip->ili_inode;
 
 	trace_xfs_inode_unpin(ip, _RET_IP_);
 	ASSERT(lip->li_buf || xfs_iflags_test(ip, XFS_ISTALE));
 	ASSERT(atomic_read(&ip->i_pincount) > 0);
-	if (atomic_dec_and_test(&ip->i_pincount))
+
+	/*
+	 * If this is the last unpin, then the inode no longer needs a journal
+	 * flush to persist it. Hence we can clear the commit sequence numbers
+	 * as a fsync/fdatasync operation on the inode at this point is a no-op.
+	 */
+	if (atomic_dec_and_lock(&ip->i_pincount, &iip->ili_lock)) {
+		iip->ili_commit_seq = 0;
+		iip->ili_datasync_seq = 0;
+		spin_unlock(&iip->ili_lock);
 		wake_up_bit(&ip->i_flags, __XFS_IPINNED_BIT);
+	}
 }
 
 STATIC uint
@@ -555,11 +759,14 @@ xfs_inode_item_push(
 		 * completed and items removed from the AIL before the next push
 		 * attempt.
 		 */
+		trace_xfs_inode_push_stale(ip, _RET_IP_);
 		return XFS_ITEM_PINNED;
 	}
 
-	if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp))
+	if (xfs_ipincount(ip) > 0 || xfs_buf_ispinned(bp)) {
+		trace_xfs_inode_push_pinned(ip, _RET_IP_);
 		return XFS_ITEM_PINNED;
+	}
 
 	if (xfs_iflags_test(ip, XFS_IFLUSHING))
 		return XFS_ITEM_FLUSHING;
@@ -607,7 +814,7 @@ xfs_inode_item_release(
 	unsigned short		lock_flags;
 
 	ASSERT(ip->i_itemp != NULL);
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
 
 	lock_flags = iip->ili_lock_flags;
 	iip->ili_lock_flags = 0;
@@ -652,16 +859,51 @@ xfs_inode_item_committed(
 	return lsn;
 }
 
+/*
+ * The modification is now complete, so before we unlock the inode we need to
+ * update the commit sequence numbers for data integrity journal flushes. We
+ * always record the commit sequence number (ili_commit_seq) so that anything
+ * that needs a full journal sync will capture all of this modification.
+ *
+ * We then
+ * check if the changes will impact a datasync (O_DSYNC) journal flush. If the
+ * changes will require a datasync flush, then we also record the sequence in
+ * ili_datasync_seq.
+ *
+ * These commit sequence numbers will get cleared atomically with the inode being
+ * unpinned (i.e. pin count goes to zero), and so it will only be set when the
+ * inode is dirty in the journal. This removes the need for checking if the
+ * inode is pinned to determine if a journal flush is necessary, and hence
+ * removes the need for holding the ILOCK_SHARED in xfs_file_fsync() to
+ * serialise pin counts against commit sequence number updates.
+ *
+ */
 STATIC void
 xfs_inode_item_committing(
 	struct xfs_log_item	*lip,
 	xfs_csn_t		seq)
 {
-	INODE_ITEM(lip)->ili_commit_seq = seq;
+	struct xfs_inode_log_item *iip = INODE_ITEM(lip);
+
+	spin_lock(&iip->ili_lock);
+	iip->ili_commit_seq = seq;
+	if (iip->ili_dirty_flags & ~(XFS_ILOG_IVERSION | XFS_ILOG_TIMESTAMP))
+		iip->ili_datasync_seq = seq;
+	spin_unlock(&iip->ili_lock);
+
+	/*
+	 * Clear the per-transaction dirty flags now that we have finished
+	 * recording the transaction's inode modifications in the CIL and are
+	 * about to release and (maybe) unlock the inode.
+	 */
+	iip->ili_dirty_flags = 0;
+
 	return xfs_inode_item_release(lip);
 }
 
 static const struct xfs_item_ops xfs_inode_item_ops = {
+	.iop_sort	= xfs_inode_item_sort,
+	.iop_precommit	= xfs_inode_item_precommit,
 	.iop_size	= xfs_inode_item_size,
 	.iop_format	= xfs_inode_item_format,
 	.iop_pin	= xfs_inode_item_pin,
@@ -705,7 +947,7 @@ xfs_inode_item_destroy(
 	ASSERT(iip->ili_item.li_buf == NULL);
 
 	ip->i_itemp = NULL;
-	kmem_free(iip->ili_item.li_lv_shadow);
+	kvfree(iip->ili_item.li_lv_shadow);
 	kmem_cache_free(xfs_ili_cache, iip);
 }
 
@@ -782,6 +1024,7 @@ xfs_iflush_finish(
 		}
 		iip->ili_last_fields = 0;
 		iip->ili_flush_lsn = 0;
+		clear_bit(XFS_LI_FLUSHING, &lip->li_flags);
 		spin_unlock(&iip->ili_lock);
 		xfs_iflags_clear(iip->ili_inode, XFS_IFLUSHING);
 		if (drop_buffer)
@@ -834,16 +1077,6 @@ xfs_buf_inode_iodone(
 		list_splice_tail(&flushed_inodes, &bp->b_li_list);
 }
 
-void
-xfs_buf_inode_io_fail(
-	struct xfs_buf		*bp)
-{
-	struct xfs_log_item	*lip;
-
-	list_for_each_entry(lip, &bp->b_li_list, li_bio_list)
-		set_bit(XFS_LI_FAILED, &lip->li_flags);
-}
-
 /*
  * Clear the inode logging fields so no more flushes are attempted.  If we are
  * on a buffer list, it is now safe to remove it because the buffer is
@@ -856,10 +1089,10 @@ xfs_iflush_abort_clean(
 {
 	iip->ili_last_fields = 0;
 	iip->ili_fields = 0;
-	iip->ili_fsync_fields = 0;
 	iip->ili_flush_lsn = 0;
 	iip->ili_item.li_buf = NULL;
 	list_del_init(&iip->ili_item.li_bio_list);
+	clear_bit(XFS_LI_FLUSHING, &iip->ili_item.li_flags);
 }
 
 /*
@@ -892,13 +1125,7 @@ xfs_iflush_abort(
 	 * state. Whilst the inode is in the AIL, it should have a valid buffer
 	 * pointer for push operations to access - it is only safe to remove the
 	 * inode from the buffer once it has been removed from the AIL.
-	 *
-	 * We also clear the failed bit before removing the item from the AIL
-	 * as xfs_trans_ail_delete()->xfs_clear_li_failed() will release buffer
-	 * references the inode item owns and needs to hold until we've fully
-	 * aborted the inode log item and detached it from the buffer.
 	 */
-	clear_bit(XFS_LI_FAILED, &iip->ili_item.li_flags);
 	xfs_trans_ail_delete(&iip->ili_item, 0);
 
 	/*
@@ -988,12 +1215,12 @@ xfs_iflush_shutdown_abort(
  */
 int
 xfs_inode_item_format_convert(
-	struct xfs_log_iovec		*buf,
+	struct kvec			*buf,
 	struct xfs_inode_log_format	*in_f)
 {
-	struct xfs_inode_log_format_32	*in_f32 = buf->i_addr;
+	struct xfs_inode_log_format_32	*in_f32 = buf->iov_base;
 
-	if (buf->i_len != sizeof(*in_f32)) {
+	if (buf->iov_len != sizeof(*in_f32)) {
 		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, NULL);
 		return -EFSCORRUPTED;
 	}