xfs: delayed allocation @ ENOSPC fixes

index f9fc154..05cd853 100644
@@ -607,7 +607,8 @@ xfssyncd(
 	set_freezable();
 	timeleft = xfs_syncd_centisecs * msecs_to_jiffies(10);
 	for (;;) {
-		timeleft = schedule_timeout_interruptible(timeleft);
+		if (list_empty(&mp->m_sync_list))
+			timeleft = schedule_timeout_interruptible(timeleft);
 		/* swsusp */
 		try_to_freeze();
 		if (kthread_should_stop() && list_empty(&mp->m_sync_list))

@@ -627,8 +628,7 @@ xfssyncd(
 			list_add_tail(&mp->m_sync_work.w_list,
 					&mp->m_sync_list);
 		}
-		list_for_each_entry_safe(work, n, &mp->m_sync_list, w_list)
-			list_move(&work->w_list, &tmp);
+		list_splice_init(&mp->m_sync_list, &tmp);
 		spin_unlock(&mp->m_sync_lock);
 
 		list_for_each_entry_safe(work, n, &tmp, w_list) {

index b493c63..65360b5 100644
@@ -39,6 +39,7 @@
 #include "xfs_iomap.h"
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
+#include "xfs_bmap.h"
 #include <linux/mpage.h>
 #include <linux/pagevec.h>
 #include <linux/writeback.h>

@@ -893,6 +894,100 @@ xfs_cluster_write(
 	}
 }
 
+STATIC void
+xfs_vm_invalidatepage(
+	struct page		*page,
+	unsigned long		offset)
+{
+	trace_xfs_invalidatepage(page->mapping->host, page, offset);
+	block_invalidatepage(page, offset);
+}
+
+/*
+ * If the page has delalloc buffers on it, we need to punch them out before we
+ * invalidate the page. If we don't, we leave a stale delalloc mapping on the
+ * inode that we can trip over later.
+ *
+ * This is not a performance critical path, so for now just do the punching a
+ * buffer head at a time.
+ */
+static void
+xfs_aops_discard_page(
+	struct page		*page)
+{
+	struct inode		*inode = page->mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct buffer_head	*bh, *head;
+	loff_t			offset = page_offset(page);
+	ssize_t			len = 1 << inode->i_blkbits;
+
+	if (!xfs_is_delayed_page(page, IOMAP_DELAY))
+		goto out_invalidate;
+
+	xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+		"page discard on page %p, inode 0x%llx, offset %llu.",
+			page, ip->i_ino, offset);
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	bh = head = page_buffers(page);
+	do {
+		int		done;
+		xfs_fileoff_t	offset_fsb;
+		xfs_bmbt_irec_t	imap;
+		int		nimaps = 1;
+		int		error;
+
+		if (!buffer_delay(bh))
+			goto next_buffer;
+
+		offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
+
+		/*
+		 * Map the range first and check that it is a delalloc extent
+		 * before trying to unmap the range. Otherwise we will be
+		 * trying to remove a real extent (which requires a
+		 * transaction) or a hole, which is probably a bad idea...
+		 */
+		error = xfs_bmapi(NULL, ip, offset_fsb, 1,
+				XFS_BMAPI_ENTIRE,  NULL, 0, &imap,
+				&nimaps, NULL, NULL);
+
+		if (error) {
+			/* something screwed, just bail */
+			xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+			"page discard failed delalloc mapping lookup.");
+			break;
+		}
+		if (!nimaps) {
+			/* nothing there */
+			goto next_buffer;
+		}
+		if (imap.br_startblock != DELAYSTARTBLOCK) {
+			/* been converted, ignore */
+			goto next_buffer;
+		}
+		WARN_ON(imap.br_blockcount == 0);
+
+		error = xfs_bunmapi(NULL, ip, offset_fsb, 1, 0, 1, NULL,
+					NULL, NULL, &done);
+
+		if (error) {
+			/* something screwed, just bail */
+			xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+			"page discard unable to remove delalloc mapping.");
+			break;
+		}
+next_buffer:
+		offset += len;
+
+	} while ((bh = bh->b_this_page) != head);
+
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out_invalidate:
+	xfs_vm_invalidatepage(page, 0);
+	return;
+}
+
 /*
  * Calling this without startio set means we are being asked to make a dirty
  * page ready for freeing it's buffers.  When called with startio set then

@@ -1144,7 +1239,7 @@ error:
 	 */
 	if (err != -EAGAIN) {
 		if (!unmapped)
-			block_invalidatepage(page, 0);
+			xfs_aops_discard_page(page);
 		ClearPageUptodate(page);
 	}
 	return err;

@@ -1554,15 +1649,6 @@ xfs_vm_readpages(
 	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
 }
 
-STATIC void
-xfs_vm_invalidatepage(
-	struct page		*page,
-	unsigned long		offset)
-{
-	trace_xfs_invalidatepage(page->mapping->host, page, offset);
-	block_invalidatepage(page, offset);
-}
-
 const struct address_space_operations xfs_address_space_operations = {
 	.readpage		= xfs_vm_readpage,
 	.readpages		= xfs_vm_readpages,

index 95a4813..7afd475 100644
@@ -5218,7 +5218,8 @@ xfs_bunmapi(
 	if (ifp->if_flags & XFS_IFBROOT) {
 		ASSERT(XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_BTREE);
 		cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
-		cur->bc_private.b.firstblock = *firstblock;
+		cur->bc_private.b.firstblock = firstblock ?
+						*firstblock : NULLFSBLOCK;
 		cur->bc_private.b.flist = flist;
 		cur->bc_private.b.flags = 0;
 	} else

@@ -5503,7 +5504,8 @@ error0:
 		xfs_trans_log_inode(tp, ip, logflags);
 	if (cur) {
 		if (!error) {
-			*firstblock = cur->bc_private.b.firstblock;
+			if (firstblock)
+				*firstblock = cur->bc_private.b.firstblock;
 			cur->bc_private.b.allocated = 0;
 		}
 		xfs_btree_del_cursor(cur,

index b493c63..e0eb7f1 100644
@@ -39,6 +39,7 @@
 #include "xfs_iomap.h"
 #include "xfs_vnodeops.h"
 #include "xfs_trace.h"
+#include "xfs_bmap.h"
 #include <linux/mpage.h>
 #include <linux/pagevec.h>
 #include <linux/writeback.h>

@@ -893,6 +894,118 @@ xfs_cluster_write(
 	}
 }
 
+STATIC void
+xfs_vm_invalidatepage(
+	struct page		*page,
+	unsigned long		offset)
+{
+	trace_xfs_invalidatepage(page->mapping->host, page, offset);
+	block_invalidatepage(page, offset);
+}
+
+/*
+ * If the page has delalloc buffers on it, we need to punch them out before we
+ * invalidate the page. If we don't, we leave a stale delalloc mapping on the
+ * inode that can trip a BUG() in xfs_get_blocks() later on if a direct IO read
+ * is done on that same region - the delalloc extent is returned when none is
+ * supposed to be there.
+ *
+ * We prevent this by truncating away the delalloc regions on the page before
+ * invalidating it. Because they are delalloc, we can do this without needing a
+ * transaction. Indeed - if we get ENOSPC errors, we have to be able to do this
+ * truncation without a transaction as there is no space left for block
+ * reservation (typically why we see a ENOSPC in writeback).
+ *
+ * This is not a performance critical path, so for now just do the punching a
+ * buffer head at a time.
+ */
+STATIC void
+xfs_aops_discard_page(
+	struct page		*page)
+{
+	struct inode		*inode = page->mapping->host;
+	struct xfs_inode	*ip = XFS_I(inode);
+	struct buffer_head	*bh, *head;
+	loff_t			offset = page_offset(page);
+	ssize_t			len = 1 << inode->i_blkbits;
+
+	if (!xfs_is_delayed_page(page, IOMAP_DELAY))
+		goto out_invalidate;
+
+	xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+		"page discard on page %p, inode 0x%llx, offset %llu.",
+			page, ip->i_ino, offset);
+
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	bh = head = page_buffers(page);
+	do {
+		int		done;
+		xfs_fileoff_t	offset_fsb;
+		xfs_bmbt_irec_t	imap;
+		int		nimaps = 1;
+		int		error;
+		xfs_fsblock_t	firstblock;
+		xfs_bmap_free_t flist;
+
+		if (!buffer_delay(bh))
+			goto next_buffer;
+
+		offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
+
+		/*
+		 * Map the range first and check that it is a delalloc extent
+		 * before trying to unmap the range. Otherwise we will be
+		 * trying to remove a real extent (which requires a
+		 * transaction) or a hole, which is probably a bad idea...
+		 */
+		error = xfs_bmapi(NULL, ip, offset_fsb, 1,
+				XFS_BMAPI_ENTIRE,  NULL, 0, &imap,
+				&nimaps, NULL, NULL);
+
+		if (error) {
+			/* something screwed, just bail */
+			xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+			"page discard failed delalloc mapping lookup.");
+			break;
+		}
+		if (!nimaps) {
+			/* nothing there */
+			goto next_buffer;
+		}
+		if (imap.br_startblock != DELAYSTARTBLOCK) {
+			/* been converted, ignore */
+			goto next_buffer;
+		}
+		WARN_ON(imap.br_blockcount == 0);
+
+		/*
+		 * Note: while we initialise the firstblock/flist pair, they
+		 * should never be used because blocks shoul dnever be
+		 * allocated or freed for a delalloc extent and hence we need
+		 * don't cancel or finish them after the xfs_bunmapi() call.
+		 */
+		xfs_bmap_init(&flist, &firstblock);
+		error = xfs_bunmapi(NULL, ip, offset_fsb, 1, 0, 1, &firstblock,
+					&flist, NULL, &done);
+
+		ASSERT(!flist.xbf_count && !flist.xbf_first);
+		if (error) {
+			/* something screwed, just bail */
+			xfs_fs_cmn_err(CE_ALERT, ip->i_mount,
+			"page discard unable to remove delalloc mapping.");
+			break;
+		}
+next_buffer:
+		offset += len;
+
+	} while ((bh = bh->b_this_page) != head);
+
+	xfs_iunlock(ip, XFS_ILOCK_EXCL);
+out_invalidate:
+	xfs_vm_invalidatepage(page, 0);
+	return;
+}
+
 /*
  * Calling this without startio set means we are being asked to make a dirty
  * page ready for freeing it's buffers.  When called with startio set then

@@ -1144,7 +1257,7 @@ error:
 	 */
 	if (err != -EAGAIN) {
 		if (!unmapped)
-			block_invalidatepage(page, 0);
+			xfs_aops_discard_page(page);
 		ClearPageUptodate(page);
 	}
 	return err;

@@ -1554,15 +1667,6 @@ xfs_vm_readpages(
 	return mpage_readpages(mapping, pages, nr_pages, xfs_get_blocks);
 }
 
-STATIC void
-xfs_vm_invalidatepage(
-	struct page		*page,
-	unsigned long		offset)
-{
-	trace_xfs_invalidatepage(page->mapping->host, page, offset);
-	block_invalidatepage(page, offset);
-}
-
 const struct address_space_operations xfs_address_space_operations = {
 	.readpage		= xfs_vm_readpage,
 	.readpages		= xfs_vm_readpages,

index c207fef..e79b56b 100644
@@ -1097,13 +1097,15 @@ xfs_default_resblks(xfs_mount_t *mp)
 	__uint64_t resblks;
 
 	/*
-	 * We default to 5% or 1024 fsbs of space reserved, whichever is smaller.
-	 * This may drive us straight to ENOSPC on mount, but that implies
-	 * we were already there on the last unmount. Warn if this occurs.
+	 * We default to 5% or 8192 fsbs of space reserved, whichever is
+	 * smaller.  This is intended to cover concurrent allocation
+	 * transactions when we initially hit enospc. These each require a 4
+	 * block reservation. Hence by default we cover roughly 2000 concurrent
+	 * allocation reservations.
 	 */
 	resblks = mp->m_sb.sb_dblocks;
 	do_div(resblks, 20);
-	resblks = min_t(__uint64_t, resblks, 1024);
+	resblks = min_t(__uint64_t, resblks, 8192);
 	return resblks;
 }
 

@@ -1417,6 +1419,9 @@ xfs_mountfs(
 	 * when at ENOSPC. This is needed for operations like create with
 	 * attr, unwritten extent conversion at ENOSPC, etc. Data allocations
 	 * are not allowed to use this reserved space.
+	 *
+	 * This may drive us straight to ENOSPC on mount, but that implies
+	 * we were already there on the last unmount. Warn if this occurs.
 	 */
 	if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
 		resblks = xfs_default_resblks(mp);

@@ -1725,26 +1730,30 @@ xfs_mod_incore_sb_unlocked(
 				lcounter += rem;
 			}
 		} else {				/* Taking blocks away */
-
 			lcounter += delta;
+			if (lcounter >= 0) {
+				mp->m_sb.sb_fdblocks = lcounter +
+							XFS_ALLOC_SET_ASIDE(mp);
+				return 0;
+			}
 
-		/*
-		 * If were out of blocks, use any available reserved blocks if
-		 * were allowed to.
-		 */
+			/*
+			 * We are out of blocks, use any available reserved
+			 * blocks if were allowed to.
+			 */
+			if (!rsvd)
+				return XFS_ERROR(ENOSPC);
 
-			if (lcounter < 0) {
-				if (rsvd) {
-					lcounter = (long long)mp->m_resblks_avail + delta;
-					if (lcounter < 0) {
-						return XFS_ERROR(ENOSPC);
-					}
-					mp->m_resblks_avail = lcounter;
-					return 0;
-				} else {	/* not reserved */
-					return XFS_ERROR(ENOSPC);
-				}
+			lcounter = (long long)mp->m_resblks_avail + delta;
+			if (lcounter >= 0) {
+				mp->m_resblks_avail = lcounter;
+				return 0;
 			}
+			printk_once(KERN_WARNING
+				"Filesystem \"%s\": reserve blocks depleted! "
+				"Consider increasing reserve pool size.",
+				mp->m_fsname);
+			return XFS_ERROR(ENOSPC);
 		}
 
 		mp->m_sb.sb_fdblocks = lcounter + XFS_ALLOC_SET_ASIDE(mp);