Merge tag 'xfs-5.5-merge-16' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux

Pull XFS updates from Darrick Wong:
 "For this release, we changed quite a few things.

  Highlights:

   - Fixed some long tail latency problems in the block allocator

   - Removed some long deprecated (and for the past several years no-op)
     mount options and ioctls

   - Strengthened the extended attribute and directory verifiers

   - Audited and fixed all the places where we could return EFSCORRUPTED
     without logging anything

   - Refactored the old SGI space allocation ioctls to make the
     equivalent fallocate calls

   - Fixed a race between fallocate and directio

   - Fixed an integer overflow when files have more than a few
     billion(!) extents

   - Fixed a longstanding bug where quota accounting could be incorrect
     when performing unwritten extent conversion on a freshly mounted fs

   - Fixed various complaints in scrub about soft lockups and
     unresponsiveness to signals

   - De-vtable'd the directory handling code, which should make it
     faster

   - Converted to the new mount api, for better or for worse

   - Cleaned up some memory leaks

  and quite a lot of other smaller fixes and cleanups.

  A more detailed summary:

   - Fill out the build string

   - Prevent inode fork extent count overflows

   - Refactor the allocator to reduce long tail latency

   - Rework incore log locking a little to reduce spinning

   - Break up the xfs_iomap_begin functions into smaller more cohesive
     parts

   - Fix allocation alignment being dropped too early when the
     allocation request is for more blocks than an AG is large

   - Other small cleanups

   - Clean up file buftarg retrieval helpers

   - Hoist the resvsp and unresvsp ioctls to the vfs

   - Remove the undocumented biosize mount option, since it has never
     been mentioned as existing or supported on linux

   - Clean up some of the mount option printing and parsing

   - Enhance attr leaf verifier to check block structure

   - Check dirent and attr names for invalid characters before passing
     them to the vfs

   - Refactor open-coded bmbt walking

   - Fix a few places where we return EIO instead of EFSCORRUPTED after
     failing metadata sanity checks

   - Fix a synchronization problem between fallocate and aio dio
     corrupting the file length

   - Clean up various loose ends in the iomap and bmap code

   - Convert to the new mount api

   - Make sure we always log something when returning EFSCORRUPTED

   - Fix some problems where long running scrub loops could trigger soft
     lockup warnings and/or fail to exit due to fatal signals pending

   - Fix various Coverity complaints

   - Remove most of the function pointers from the directory code to
     reduce indirection penalties

   - Ensure that dquots are attached to the inode when performing
     unwritten extent conversion after io

   - Deuglify incore projid and crtime types

   - Fix another AGI/AGF locking order deadlock when renaming

   - Clean up some quota typedefs

   - Remove the FSSETDM ioctls which haven't done anything in 20 years

   - Fix some memory leaks when mounting the log fails

   - Fix an underflow when updating an xattr leaf freemap

   - Remove some trivial wrappers

   - Report metadata corruption as an error, not a (potentially) fatal
     assertion

   - Clean up the dir/attr buffer mapping code

   - Allow fatal signals to kill scrub during parent pointer checks"

* tag 'xfs-5.5-merge-16' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (198 commits)
  xfs: allow parent directory scans to be interrupted with fatal signals
  xfs: remove the mappedbno argument to xfs_da_get_buf
  xfs: remove the mappedbno argument to xfs_da_read_buf
  xfs: split xfs_da3_node_read
  xfs: remove the mappedbno argument to xfs_dir3_leafn_read
  xfs: remove the mappedbno argument to xfs_dir3_leaf_read
  xfs: remove the mappedbno argument to xfs_attr3_leaf_read
  xfs: remove the mappedbno argument to xfs_da_reada_buf
  xfs: improve the xfs_dabuf_map calling conventions
  xfs: refactor xfs_dabuf_map
  xfs: simplify mappedbno handling in xfs_da_{get,read}_buf
  xfs: report corruption only as a regular error
  xfs: Remove kmem_zone_free() wrapper
  xfs: Remove kmem_zone_destroy() wrapper
  xfs: Remove slab init wrappers
  xfs: fix attr leaf header freemap.size underflow
  xfs: fix some memory leaks in log recovery
  xfs: fix another missing include
  xfs: remove XFS_IOC_FSSETDM and XFS_IOC_FSSETDM_BY_HANDLE
  xfs: remove duplicated include from xfs_dir2_data.c
  ...

1 files changed, 48 insertions, 22 deletions

diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index fe285d123d69..8afe69ca188b 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -20,6 +20,7 @@
 #include "xfs_symlink.h"
 #include "xfs_dir2.h"
 #include "xfs_iomap.h"
+#include "xfs_error.h"
 
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
@@ -470,20 +471,57 @@ xfs_vn_get_link_inline(
 	struct inode		*inode,
 	struct delayed_call	*done)
 {
+	struct xfs_inode	*ip = XFS_I(inode);
 	char			*link;
 
-	ASSERT(XFS_I(inode)->i_df.if_flags & XFS_IFINLINE);
+	ASSERT(ip->i_df.if_flags & XFS_IFINLINE);
 
 	/*
 	 * The VFS crashes on a NULL pointer, so return -EFSCORRUPTED if
 	 * if_data is junk.
 	 */
-	link = XFS_I(inode)->i_df.if_u1.if_data;
-	if (!link)
+	link = ip->i_df.if_u1.if_data;
+	if (XFS_IS_CORRUPT(ip->i_mount, !link))
 		return ERR_PTR(-EFSCORRUPTED);
 	return link;
 }
 
+static uint32_t
+xfs_stat_blksize(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	/*
+	 * If the file blocks are being allocated from a realtime volume, then
+	 * always return the realtime extent size.
+	 */
+	if (XFS_IS_REALTIME_INODE(ip))
+		return xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog;
+
+	/*
+	 * Allow large block sizes to be reported to userspace programs if the
+	 * "largeio" mount option is used.
+	 *
+	 * If compatibility mode is specified, simply return the basic unit of
+	 * caching so that we don't get inefficient read/modify/write I/O from
+	 * user apps. Otherwise....
+	 *
+	 * If the underlying volume is a stripe, then return the stripe width in
+	 * bytes as the recommended I/O size. It is not a stripe and we've set a
+	 * default buffered I/O size, return that, otherwise return the compat
+	 * default.
+	 */
+	if (mp->m_flags & XFS_MOUNT_LARGEIO) {
+		if (mp->m_swidth)
+			return mp->m_swidth << mp->m_sb.sb_blocklog;
+		if (mp->m_flags & XFS_MOUNT_ALLOCSIZE)
+			return 1U << mp->m_allocsize_log;
+	}
+
+	return PAGE_SIZE;
+}
+
 STATIC int
 xfs_vn_getattr(
 	const struct path	*path,
@@ -516,8 +554,7 @@ xfs_vn_getattr(
 	if (ip->i_d.di_version == 3) {
 		if (request_mask & STATX_BTIME) {
 			stat->result_mask |= STATX_BTIME;
-			stat->btime.tv_sec = ip->i_d.di_crtime.t_sec;
-			stat->btime.tv_nsec = ip->i_d.di_crtime.t_nsec;
+			stat->btime = ip->i_d.di_crtime;
 		}
 	}
 
@@ -543,16 +580,7 @@ xfs_vn_getattr(
 		stat->rdev = inode->i_rdev;
 		break;
 	default:
-		if (XFS_IS_REALTIME_INODE(ip)) {
-			/*
-			 * If the file blocks are being allocated from a
-			 * realtime volume, then return the inode's realtime
-			 * extent size or the realtime volume's extent size.
-			 */
-			stat->blksize =
-				xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog;
-		} else
-			stat->blksize = xfs_preferred_iosize(mp);
+		stat->blksize = xfs_stat_blksize(ip);
 		stat->rdev = 0;
 		break;
 	}
@@ -664,7 +692,7 @@ xfs_setattr_nonsize(
 		ASSERT(gdqp == NULL);
 		error = xfs_qm_vop_dqalloc(ip, xfs_kuid_to_uid(uid),
 					   xfs_kgid_to_gid(gid),
-					   xfs_get_projid(ip),
+					   ip->i_d.di_projid,
 					   qflags, &udqp, &gdqp, NULL);
 		if (error)
 			return error;
@@ -883,10 +911,10 @@ xfs_setattr_size(
 	if (newsize > oldsize) {
 		trace_xfs_zero_eof(ip, oldsize, newsize - oldsize);
 		error = iomap_zero_range(inode, oldsize, newsize - oldsize,
-				&did_zeroing, &xfs_iomap_ops);
+				&did_zeroing, &xfs_buffered_write_iomap_ops);
 	} else {
 		error = iomap_truncate_page(inode, newsize, &did_zeroing,
-				&xfs_iomap_ops);
+				&xfs_buffered_write_iomap_ops);
 	}
 
 	if (error)
@@ -1114,7 +1142,7 @@ xfs_vn_fiemap(
 				&xfs_xattr_iomap_ops);
 	} else {
 		error = iomap_fiemap(inode, fieinfo, start, length,
-				&xfs_iomap_ops);
+				&xfs_read_iomap_ops);
 	}
 	xfs_iunlock(XFS_I(inode), XFS_IOLOCK_SHARED);
 
@@ -1227,7 +1255,7 @@ xfs_inode_supports_dax(
 		return false;
 
 	/* Device has to support DAX too. */
-	return xfs_find_daxdev_for_inode(VFS_I(ip)) != NULL;
+	return xfs_inode_buftarg(ip)->bt_daxdev != NULL;
 }
 
 STATIC void
@@ -1290,9 +1318,7 @@ xfs_setup_inode(
 		lockdep_set_class(&inode->i_rwsem,
 				  &inode->i_sb->s_type->i_mutex_dir_key);
 		lockdep_set_class(&ip->i_lock.mr_lock, &xfs_dir_ilock_class);
-		ip->d_ops = ip->i_mount->m_dir_inode_ops;
 	} else {
-		ip->d_ops = ip->i_mount->m_nondir_inode_ops;
 		lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
 	}