1 files changed, 207 insertions, 15 deletions

diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index e72730f85af1..b22a09e9daee 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -20,6 +20,10 @@
 #include "xfs_trace.h"
 #include "xfs_error.h"
 #include "xfs_defer.h"
+#include "xfs_inode.h"
+#include "xfs_dquot_item.h"
+#include "xfs_dquot.h"
+#include "xfs_icache.h"
 
 kmem_zone_t	*xfs_trans_zone;
 
@@ -68,6 +72,7 @@ xfs_trans_free(
 	xfs_extent_busy_clear(tp->t_mountp, &tp->t_busy, false);
 
 	trace_xfs_trans_free(tp, _RET_IP_);
+	xfs_trans_clear_context(tp);
 	if (!(tp->t_flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_end_intwrite(tp->t_mountp->m_super);
 	xfs_trans_free_dqinfo(tp);
@@ -119,7 +124,8 @@ xfs_trans_dup(
 
 	ntp->t_rtx_res = tp->t_rtx_res - tp->t_rtx_res_used;
 	tp->t_rtx_res = tp->t_rtx_res_used;
-	ntp->t_pflags = tp->t_pflags;
+
+	xfs_trans_switch_context(tp, ntp);
 
 	/* move deferred ops over to the new tp */
 	xfs_defer_move(ntp, tp);
@@ -153,9 +159,6 @@ xfs_trans_reserve(
 	int			error = 0;
 	bool			rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
 
-	/* Mark this thread as being in a transaction */
-	current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
 	/*
 	 * Attempt to reserve the needed disk blocks by decrementing
 	 * the number needed from the number available.  This will
@@ -163,10 +166,8 @@ xfs_trans_reserve(
 	 */
 	if (blocks > 0) {
 		error = xfs_mod_fdblocks(mp, -((int64_t)blocks), rsvd);
-		if (error != 0) {
-			current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
+		if (error != 0)
 			return -ENOSPC;
-		}
 		tp->t_blk_res += blocks;
 	}
 
@@ -240,9 +241,6 @@ undo_blocks:
 		xfs_mod_fdblocks(mp, (int64_t)blocks, rsvd);
 		tp->t_blk_res = 0;
 	}
-
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
 	return error;
 }
 
@@ -256,6 +254,7 @@ xfs_trans_alloc(
 	struct xfs_trans	**tpp)
 {
 	struct xfs_trans	*tp;
+	bool			want_retry = true;
 	int			error;
 
 	/*
@@ -263,9 +262,11 @@ xfs_trans_alloc(
 	 * GFP_NOFS allocation context so that we avoid lockdep false positives
 	 * by doing GFP_KERNEL allocations inside sb_start_intwrite().
 	 */
+retry:
 	tp = kmem_cache_zalloc(xfs_trans_zone, GFP_KERNEL | __GFP_NOFAIL);
 	if (!(flags & XFS_TRANS_NO_WRITECOUNT))
 		sb_start_intwrite(mp->m_super);
+	xfs_trans_set_context(tp);
 
 	/*
 	 * Zero-reservation ("empty") transactions can't modify anything, so
@@ -285,6 +286,22 @@ xfs_trans_alloc(
 	tp->t_firstblock = NULLFSBLOCK;
 
 	error = xfs_trans_reserve(tp, resp, blocks, rtextents);
+	if (error == -ENOSPC && want_retry) {
+		xfs_trans_cancel(tp);
+
+		/*
+		 * We weren't able to reserve enough space for the transaction.
+		 * Flush the other speculative space allocations to free space.
+		 * Do not perform a synchronous scan because callers can hold
+		 * other locks.
+		 */
+		error = xfs_blockgc_free_space(mp, NULL);
+		if (error)
+			return error;
+
+		want_retry = false;
+		goto retry;
+	}
 	if (error) {
 		xfs_trans_cancel(tp);
 		return error;
@@ -878,7 +895,6 @@ __xfs_trans_commit(
 
 	xfs_log_commit_cil(mp, tp, &commit_lsn, regrant);
 
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	xfs_trans_free(tp);
 
 	/*
@@ -910,7 +926,6 @@ out_unreserve:
 			xfs_log_ticket_ungrant(mp->m_log, tp->t_ticket);
 		tp->t_ticket = NULL;
 	}
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	xfs_trans_free_items(tp, !!error);
 	xfs_trans_free(tp);
 
@@ -970,9 +985,6 @@ xfs_trans_cancel(
 		tp->t_ticket = NULL;
 	}
 
-	/* mark this thread as no longer being in a transaction */
-	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
-
 	xfs_trans_free_items(tp, dirty);
 	xfs_trans_free(tp);
 }
@@ -1024,3 +1036,183 @@ xfs_trans_roll(
 	tres.tr_logflags = XFS_TRANS_PERM_LOG_RES;
 	return xfs_trans_reserve(*tpp, &tres, 0, 0);
 }
+
+/*
+ * Allocate an transaction, lock and join the inode to it, and reserve quota.
+ *
+ * The caller must ensure that the on-disk dquots attached to this inode have
+ * already been allocated and initialized.  The caller is responsible for
+ * releasing ILOCK_EXCL if a new transaction is returned.
+ */
+int
+xfs_trans_alloc_inode(
+	struct xfs_inode	*ip,
+	struct xfs_trans_res	*resv,
+	unsigned int		dblocks,
+	unsigned int		rblocks,
+	bool			force,
+	struct xfs_trans	**tpp)
+{
+	struct xfs_trans	*tp;
+	struct xfs_mount	*mp = ip->i_mount;
+	bool			retried = false;
+	int			error;
+
+retry:
+	error = xfs_trans_alloc(mp, resv, dblocks,
+			rblocks / mp->m_sb.sb_rextsize,
+			force ? XFS_TRANS_RESERVE : 0, &tp);
+	if (error)
+		return error;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, 0);
+
+	error = xfs_qm_dqattach_locked(ip, false);
+	if (error) {
+		/* Caller should have allocated the dquots! */
+		ASSERT(error != -ENOENT);
+		goto out_cancel;
+	}
+
+	error = xfs_trans_reserve_quota_nblks(tp, ip, dblocks, rblocks, force);
+	if ((error == -EDQUOT || error == -ENOSPC) && !retried) {
+		xfs_trans_cancel(tp);
+		xfs_iunlock(ip, XFS_ILOCK_EXCL);
+		xfs_blockgc_free_quota(ip, 0);
+		retried = true;
+		goto retry;
+	}
+	if (error)
+		goto out_cancel;
+
+	*tpp = tp;
+	return 0;
+
+out_cancel:
+	xfs_trans_cancel(tp);
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+	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.
+ */
+int
+xfs_trans_alloc_icreate(
+	struct xfs_mount	*mp,
+	struct xfs_trans_res	*resv,
+	struct xfs_dquot	*udqp,
+	struct xfs_dquot	*gdqp,
+	struct xfs_dquot	*pdqp,
+	unsigned int		dblocks,
+	struct xfs_trans	**tpp)
+{
+	struct xfs_trans	*tp;
+	bool			retried = false;
+	int			error;
+
+retry:
+	error = xfs_trans_alloc(mp, resv, dblocks, 0, 0, &tp);
+	if (error)
+		return error;
+
+	error = xfs_trans_reserve_quota_icreate(tp, udqp, gdqp, pdqp, dblocks);
+	if ((error == -EDQUOT || error == -ENOSPC) && !retried) {
+		xfs_trans_cancel(tp);
+		xfs_blockgc_free_dquots(mp, udqp, gdqp, pdqp, 0);
+		retried = true;
+		goto retry;
+	}
+	if (error) {
+		xfs_trans_cancel(tp);
+		return error;
+	}
+
+	*tpp = tp;
+	return 0;
+}
+
+/*
+ * Allocate an transaction, lock and join the inode to it, and reserve quota
+ * in preparation for inode attribute changes that include uid, gid, or prid
+ * changes.
+ *
+ * The caller must ensure that the on-disk dquots attached to this inode have
+ * already been allocated and initialized.  The ILOCK will be dropped when the
+ * transaction is committed or cancelled.
+ */
+int
+xfs_trans_alloc_ichange(
+	struct xfs_inode	*ip,
+	struct xfs_dquot	*new_udqp,
+	struct xfs_dquot	*new_gdqp,
+	struct xfs_dquot	*new_pdqp,
+	bool			force,
+	struct xfs_trans	**tpp)
+{
+	struct xfs_trans	*tp;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_dquot	*udqp;
+	struct xfs_dquot	*gdqp;
+	struct xfs_dquot	*pdqp;
+	bool			retried = false;
+	int			error;
+
+retry:
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
+	if (error)
+		return error;
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
+
+	error = xfs_qm_dqattach_locked(ip, false);
+	if (error) {
+		/* Caller should have allocated the dquots! */
+		ASSERT(error != -ENOENT);
+		goto out_cancel;
+	}
+
+	/*
+	 * For each quota type, skip quota reservations if the inode's dquots
+	 * now match the ones that came from the caller, or the caller didn't
+	 * pass one in.  The inode's dquots can change if we drop the ILOCK to
+	 * perform a blockgc scan, so we must preserve the caller's arguments.
+	 */
+	udqp = (new_udqp != ip->i_udquot) ? new_udqp : NULL;
+	gdqp = (new_gdqp != ip->i_gdquot) ? new_gdqp : NULL;
+	pdqp = (new_pdqp != ip->i_pdquot) ? new_pdqp : NULL;
+	if (udqp || gdqp || pdqp) {
+		unsigned int	qflags = XFS_QMOPT_RES_REGBLKS;
+
+		if (force)
+			qflags |= XFS_QMOPT_FORCE_RES;
+
+		/*
+		 * Reserve enough quota to handle blocks on disk and reserved
+		 * for a delayed allocation.  We'll actually transfer the
+		 * delalloc reservation between dquots at chown time, even
+		 * though that part is only semi-transactional.
+		 */
+		error = xfs_trans_reserve_quota_bydquots(tp, mp, udqp, gdqp,
+				pdqp, ip->i_d.di_nblocks + ip->i_delayed_blks,
+				1, qflags);
+		if ((error == -EDQUOT || error == -ENOSPC) && !retried) {
+			xfs_trans_cancel(tp);
+			xfs_blockgc_free_dquots(mp, udqp, gdqp, pdqp, 0);
+			retried = true;
+			goto retry;
+		}
+		if (error)
+			goto out_cancel;
+	}
+
+	*tpp = tp;
+	return 0;
+
+out_cancel:
+	xfs_trans_cancel(tp);
+	return error;
+}