1 files changed, 130 insertions, 178 deletions

diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 9cd3adfd2a42..39cd11cbe21f 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -24,6 +24,7 @@
 #include "xfs_dquot_item.h"
 #include "xfs_dquot.h"
 #include "xfs_icache.h"
+#include "xfs_rtbitmap.h"
 
 struct kmem_cache	*xfs_trans_cache;
 
@@ -162,7 +163,7 @@ xfs_trans_reserve(
 	 * fail if the count would go below zero.
 	 */
 	if (blocks > 0) {
-		error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd);
+		error = xfs_dec_fdblocks(mp, blocks, rsvd);
 		if (error != 0)
 			return -ENOSPC;
 		tp->t_blk_res += blocks;
@@ -209,7 +210,7 @@ xfs_trans_reserve(
 	 * fail if the count would go below zero.
 	 */
 	if (rtextents > 0) {
-		error = xfs_mod_frextents(mp, -((int64_t)rtextents));
+		error = xfs_dec_frextents(mp, rtextents);
 		if (error) {
 			error = -ENOSPC;
 			goto undo_log;
@@ -233,7 +234,7 @@ undo_log:
 
 undo_blocks:
 	if (blocks > 0) {
-		xfs_mod_fdblocks(mp, (int64_t)blocks, rsvd);
+		xfs_add_fdblocks(mp, blocks);
 		tp->t_blk_res = 0;
 	}
 	return error;
@@ -592,38 +593,44 @@ xfs_trans_unreserve_and_mod_sb(
 	struct xfs_trans	*tp)
 {
 	struct xfs_mount	*mp = tp->t_mountp;
-	bool			rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
-	int64_t			blkdelta = 0;
-	int64_t			rtxdelta = 0;
+	int64_t			blkdelta = tp->t_blk_res;
+	int64_t			rtxdelta = tp->t_rtx_res;
 	int64_t			idelta = 0;
 	int64_t			ifreedelta = 0;
-	int			error;
 
-	/* calculate deltas */
-	if (tp->t_blk_res > 0)
-		blkdelta = tp->t_blk_res;
-	if ((tp->t_fdblocks_delta != 0) &&
-	    (xfs_has_lazysbcount(mp) ||
-	     (tp->t_flags & XFS_TRANS_SB_DIRTY)))
+	/*
+	 * Calculate the deltas.
+	 *
+	 * t_fdblocks_delta and t_frextents_delta can be positive or negative:
+	 *
+	 *  - positive values indicate blocks freed in the transaction.
+	 *  - negative values indicate blocks allocated in the transaction
+	 *
+	 * Negative values can only happen if the transaction has a block
+	 * reservation that covers the allocated block.  The end result is
+	 * that the calculated delta values must always be positive and we
+	 * can only put back previous allocated or reserved blocks here.
+	 */
+	ASSERT(tp->t_blk_res || tp->t_fdblocks_delta >= 0);
+	if (xfs_has_lazysbcount(mp) || (tp->t_flags & XFS_TRANS_SB_DIRTY)) {
 	        blkdelta += tp->t_fdblocks_delta;
+		ASSERT(blkdelta >= 0);
+	}
 
-	if (tp->t_rtx_res > 0)
-		rtxdelta = tp->t_rtx_res;
-	if ((tp->t_frextents_delta != 0) &&
-	    (tp->t_flags & XFS_TRANS_SB_DIRTY))
+	ASSERT(tp->t_rtx_res || tp->t_frextents_delta >= 0);
+	if (tp->t_flags & XFS_TRANS_SB_DIRTY) {
 		rtxdelta += tp->t_frextents_delta;
+		ASSERT(rtxdelta >= 0);
+	}
 
-	if (xfs_has_lazysbcount(mp) ||
-	     (tp->t_flags & XFS_TRANS_SB_DIRTY)) {
+	if (xfs_has_lazysbcount(mp) || (tp->t_flags & XFS_TRANS_SB_DIRTY)) {
 		idelta = tp->t_icount_delta;
 		ifreedelta = tp->t_ifree_delta;
 	}
 
 	/* apply the per-cpu counters */
-	if (blkdelta) {
-		error = xfs_mod_fdblocks(mp, blkdelta, rsvd);
-		ASSERT(!error);
-	}
+	if (blkdelta)
+		xfs_add_fdblocks(mp, blkdelta);
 
 	if (idelta)
 		percpu_counter_add_batch(&mp->m_icount, idelta,
@@ -632,10 +639,8 @@ xfs_trans_unreserve_and_mod_sb(
 	if (ifreedelta)
 		percpu_counter_add(&mp->m_ifree, ifreedelta);
 
-	if (rtxdelta) {
-		error = xfs_mod_frextents(mp, rtxdelta);
-		ASSERT(!error);
-	}
+	if (rtxdelta)
+		xfs_add_frextents(mp, rtxdelta);
 
 	if (!(tp->t_flags & XFS_TRANS_SB_DIRTY))
 		return;
@@ -655,6 +660,10 @@ xfs_trans_unreserve_and_mod_sb(
 	mp->m_sb.sb_agcount += tp->t_agcount_delta;
 	mp->m_sb.sb_imax_pct += tp->t_imaxpct_delta;
 	mp->m_sb.sb_rextsize += tp->t_rextsize_delta;
+	if (tp->t_rextsize_delta) {
+		mp->m_rtxblklog = log2_if_power2(mp->m_sb.sb_rextsize);
+		mp->m_rtxblkmask = mask64_if_power2(mp->m_sb.sb_rextsize);
+	}
 	mp->m_sb.sb_rbmblocks += tp->t_rbmblocks_delta;
 	mp->m_sb.sb_rblocks += tp->t_rblocks_delta;
 	mp->m_sb.sb_rextents += tp->t_rextents_delta;
@@ -667,7 +676,6 @@ xfs_trans_unreserve_and_mod_sb(
 	 */
 	ASSERT(mp->m_sb.sb_imax_pct >= 0);
 	ASSERT(mp->m_sb.sb_rextslog >= 0);
-	return;
 }
 
 /* Add the given log item to the transaction's list of log items. */
@@ -717,135 +725,6 @@ xfs_trans_free_items(
 	}
 }
 
-static inline void
-xfs_log_item_batch_insert(
-	struct xfs_ail		*ailp,
-	struct xfs_ail_cursor	*cur,
-	struct xfs_log_item	**log_items,
-	int			nr_items,
-	xfs_lsn_t		commit_lsn)
-{
-	int	i;
-
-	spin_lock(&ailp->ail_lock);
-	/* xfs_trans_ail_update_bulk drops ailp->ail_lock */
-	xfs_trans_ail_update_bulk(ailp, cur, log_items, nr_items, commit_lsn);
-
-	for (i = 0; i < nr_items; i++) {
-		struct xfs_log_item *lip = log_items[i];
-
-		if (lip->li_ops->iop_unpin)
-			lip->li_ops->iop_unpin(lip, 0);
-	}
-}
-
-/*
- * Bulk operation version of xfs_trans_committed that takes a log vector of
- * items to insert into the AIL. This uses bulk AIL insertion techniques to
- * minimise lock traffic.
- *
- * If we are called with the aborted flag set, it is because a log write during
- * a CIL checkpoint commit has failed. In this case, all the items in the
- * checkpoint have already gone through iop_committed and iop_committing, which
- * means that checkpoint commit abort handling is treated exactly the same
- * as an iclog write error even though we haven't started any IO yet. Hence in
- * this case all we need to do is iop_committed processing, followed by an
- * iop_unpin(aborted) call.
- *
- * The AIL cursor is used to optimise the insert process. If commit_lsn is not
- * at the end of the AIL, the insert cursor avoids the need to walk
- * the AIL to find the insertion point on every xfs_log_item_batch_insert()
- * call. This saves a lot of needless list walking and is a net win, even
- * though it slightly increases that amount of AIL lock traffic to set it up
- * and tear it down.
- */
-void
-xfs_trans_committed_bulk(
-	struct xfs_ail		*ailp,
-	struct list_head	*lv_chain,
-	xfs_lsn_t		commit_lsn,
-	bool			aborted)
-{
-#define LOG_ITEM_BATCH_SIZE	32
-	struct xfs_log_item	*log_items[LOG_ITEM_BATCH_SIZE];
-	struct xfs_log_vec	*lv;
-	struct xfs_ail_cursor	cur;
-	int			i = 0;
-
-	spin_lock(&ailp->ail_lock);
-	xfs_trans_ail_cursor_last(ailp, &cur, commit_lsn);
-	spin_unlock(&ailp->ail_lock);
-
-	/* unpin all the log items */
-	list_for_each_entry(lv, lv_chain, lv_list) {
-		struct xfs_log_item	*lip = lv->lv_item;
-		xfs_lsn_t		item_lsn;
-
-		if (aborted)
-			set_bit(XFS_LI_ABORTED, &lip->li_flags);
-
-		if (lip->li_ops->flags & XFS_ITEM_RELEASE_WHEN_COMMITTED) {
-			lip->li_ops->iop_release(lip);
-			continue;
-		}
-
-		if (lip->li_ops->iop_committed)
-			item_lsn = lip->li_ops->iop_committed(lip, commit_lsn);
-		else
-			item_lsn = commit_lsn;
-
-		/* item_lsn of -1 means the item needs no further processing */
-		if (XFS_LSN_CMP(item_lsn, (xfs_lsn_t)-1) == 0)
-			continue;
-
-		/*
-		 * if we are aborting the operation, no point in inserting the
-		 * object into the AIL as we are in a shutdown situation.
-		 */
-		if (aborted) {
-			ASSERT(xlog_is_shutdown(ailp->ail_log));
-			if (lip->li_ops->iop_unpin)
-				lip->li_ops->iop_unpin(lip, 1);
-			continue;
-		}
-
-		if (item_lsn != commit_lsn) {
-
-			/*
-			 * Not a bulk update option due to unusual item_lsn.
-			 * Push into AIL immediately, rechecking the lsn once
-			 * we have the ail lock. Then unpin the item. This does
-			 * not affect the AIL cursor the bulk insert path is
-			 * using.
-			 */
-			spin_lock(&ailp->ail_lock);
-			if (XFS_LSN_CMP(item_lsn, lip->li_lsn) > 0)
-				xfs_trans_ail_update(ailp, lip, item_lsn);
-			else
-				spin_unlock(&ailp->ail_lock);
-			if (lip->li_ops->iop_unpin)
-				lip->li_ops->iop_unpin(lip, 0);
-			continue;
-		}
-
-		/* Item is a candidate for bulk AIL insert.  */
-		log_items[i++] = lv->lv_item;
-		if (i >= LOG_ITEM_BATCH_SIZE) {
-			xfs_log_item_batch_insert(ailp, &cur, log_items,
-					LOG_ITEM_BATCH_SIZE, commit_lsn);
-			i = 0;
-		}
-	}
-
-	/* make sure we insert the remainder! */
-	if (i)
-		xfs_log_item_batch_insert(ailp, &cur, log_items, i, commit_lsn);
-
-	spin_lock(&ailp->ail_lock);
-	xfs_trans_ail_cursor_done(&cur);
-	spin_unlock(&ailp->ail_lock);
-}
-
 /*
  * Sort transaction items prior to running precommit operations. This will
  * attempt to order the items such that they will always be locked in the same
@@ -956,16 +835,12 @@ __xfs_trans_commit(
 	trace_xfs_trans_commit(tp, _RET_IP_);
 
 	/*
-	 * Finish deferred items on final commit. Only permanent transactions
-	 * should ever have deferred ops.
+	 * Commit per-transaction changes that are not already tracked through
+	 * log items.  This can add dirty log items to the transaction.
 	 */
-	WARN_ON_ONCE(!list_empty(&tp->t_dfops) &&
-		     !(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
-	if (!regrant && (tp->t_flags & XFS_TRANS_PERM_LOG_RES)) {
-		error = xfs_defer_finish_noroll(&tp);
-		if (error)
-			goto out_unreserve;
-	}
+	if (tp->t_flags & XFS_TRANS_SB_DIRTY)
+		xfs_trans_apply_sb_deltas(tp);
+	xfs_trans_apply_dquot_deltas(tp);
 
 	error = xfs_trans_run_precommits(tp);
 	if (error)
@@ -994,13 +869,6 @@ __xfs_trans_commit(
 
 	ASSERT(tp->t_ticket != NULL);
 
-	/*
-	 * If we need to update the superblock, then do it now.
-	 */
-	if (tp->t_flags & XFS_TRANS_SB_DIRTY)
-		xfs_trans_apply_sb_deltas(tp);
-	xfs_trans_apply_dquot_deltas(tp);
-
 	xlog_cil_commit(log, tp, &commit_seq, regrant);
 
 	xfs_trans_free(tp);
@@ -1026,7 +894,7 @@ out_unreserve:
 	 * the dqinfo portion to be.  All that means is that we have some
 	 * (non-persistent) quota reservations that need to be unreserved.
 	 */
-	xfs_trans_unreserve_and_mod_dquots(tp);
+	xfs_trans_unreserve_and_mod_dquots(tp, true);
 	if (tp->t_ticket) {
 		if (regrant && !xlog_is_shutdown(log))
 			xfs_log_ticket_regrant(log, tp->t_ticket);
@@ -1045,6 +913,20 @@ int
 xfs_trans_commit(
 	struct xfs_trans	*tp)
 {
+	/*
+	 * Finish deferred items on final commit. Only permanent transactions
+	 * should ever have deferred ops.
+	 */
+	WARN_ON_ONCE(!list_empty(&tp->t_dfops) &&
+		     !(tp->t_flags & XFS_TRANS_PERM_LOG_RES));
+	if (tp->t_flags & XFS_TRANS_PERM_LOG_RES) {
+		int error = xfs_defer_finish_noroll(&tp);
+		if (error) {
+			xfs_trans_cancel(tp);
+			return error;
+		}
+	}
+
 	return __xfs_trans_commit(tp, false);
 }
 
@@ -1106,7 +988,7 @@ xfs_trans_cancel(
 	}
 #endif
 	xfs_trans_unreserve_and_mod_sb(tp);
-	xfs_trans_unreserve_and_mod_dquots(tp);
+	xfs_trans_unreserve_and_mod_dquots(tp, false);
 
 	if (tp->t_ticket) {
 		xfs_log_ticket_ungrant(log, tp->t_ticket);
@@ -1188,7 +1070,7 @@ xfs_trans_alloc_inode(
 
 retry:
 	error = xfs_trans_alloc(mp, resv, dblocks,
-			rblocks / mp->m_sb.sb_rextsize,
+			xfs_extlen_to_rtxlen(mp, rblocks),
 			force ? XFS_TRANS_RESERVE : 0, &tp);
 	if (error)
 		return error;
@@ -1224,6 +1106,68 @@ out_cancel:
 }
 
 /*
+ * Try to reserve more blocks for a transaction.
+ *
+ * This is for callers that need to attach resources to a transaction, scan
+ * those resources to determine the space reservation requirements, and then
+ * modify the attached resources.  In other words, online repair.  This can
+ * fail due to ENOSPC, so the caller must be able to cancel the transaction
+ * without shutting down the fs.
+ */
+int
+xfs_trans_reserve_more(
+	struct xfs_trans	*tp,
+	unsigned int		blocks,
+	unsigned int		rtextents)
+{
+	struct xfs_trans_res	resv = { };
+
+	return xfs_trans_reserve(tp, &resv, blocks, rtextents);
+}
+
+/*
+ * Try to reserve more blocks and file quota for a transaction.  Same
+ * conditions of usage as xfs_trans_reserve_more.
+ */
+int
+xfs_trans_reserve_more_inode(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	unsigned int		dblocks,
+	unsigned int		rblocks,
+	bool			force_quota)
+{
+	struct xfs_trans_res	resv = { };
+	struct xfs_mount	*mp = ip->i_mount;
+	unsigned int		rtx = xfs_extlen_to_rtxlen(mp, rblocks);
+	int			error;
+
+	xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
+
+	error = xfs_trans_reserve(tp, &resv, dblocks, rtx);
+	if (error)
+		return error;
+
+	if (!XFS_IS_QUOTA_ON(mp) || xfs_is_quota_inode(&mp->m_sb, ip->i_ino))
+		return 0;
+
+	if (tp->t_flags & XFS_TRANS_RESERVE)
+		force_quota = true;
+
+	error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks,
+			force_quota);
+	if (!error)
+		return 0;
+
+	/* Quota failed, give back the new reservation. */
+	xfs_add_fdblocks(mp, dblocks);
+	tp->t_blk_res -= dblocks;
+	xfs_add_frextents(mp, rtx);
+	tp->t_rtx_res -= rtx;
+	return error;
+}
+
+/*
  * Allocate an transaction in preparation for inode creation by reserving quota
  * against the given dquots.  Callers are not required to hold any inode locks.
  */
@@ -1355,6 +1299,8 @@ out_cancel:
  * The caller must ensure that the on-disk dquots attached to this inode have
  * already been allocated and initialized.  The ILOCKs will be dropped when the
  * transaction is committed or cancelled.
+ *
+ * Caller is responsible for unlocking the inodes manually upon return
  */
 int
 xfs_trans_alloc_dir(
@@ -1385,8 +1331,8 @@ retry:
 
 	xfs_lock_two_inodes(dp, XFS_ILOCK_EXCL, ip, XFS_ILOCK_EXCL);
 
-	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, dp, 0);
+	xfs_trans_ijoin(tp, ip, 0);
 
 	error = xfs_qm_dqattach_locked(dp, false);
 	if (error) {
@@ -1409,6 +1355,9 @@ retry:
 	if (error == -EDQUOT || error == -ENOSPC) {
 		if (!retried) {
 			xfs_trans_cancel(tp);
+			xfs_iunlock(dp, XFS_ILOCK_EXCL);
+			if (dp != ip)
+				xfs_iunlock(ip, XFS_ILOCK_EXCL);
 			xfs_blockgc_free_quota(dp, 0);
 			retried = true;
 			goto retry;
@@ -1428,5 +1377,8 @@ done:
 
 out_cancel:
 	xfs_trans_cancel(tp);
+	xfs_iunlock(dp, XFS_ILOCK_EXCL);
+	if (dp != ip)
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
 }