1 files changed, 264 insertions, 308 deletions

diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 81f2f93caec0..2e10e1c66ad6 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -13,6 +13,8 @@
 #include "xfs_inode.h"
 #include "xfs_acl.h"
 #include "xfs_quota.h"
+#include "xfs_da_format.h"
+#include "xfs_da_btree.h"
 #include "xfs_attr.h"
 #include "xfs_trans.h"
 #include "xfs_trace.h"
@@ -21,18 +23,20 @@
 #include "xfs_dir2.h"
 #include "xfs_iomap.h"
 #include "xfs_error.h"
+#include "xfs_ioctl.h"
+#include "xfs_xattr.h"
 
-#include <linux/xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/security.h>
 #include <linux/iversion.h>
+#include <linux/fiemap.h>
 
 /*
- * Directories have different lock order w.r.t. mmap_sem compared to regular
+ * Directories have different lock order w.r.t. mmap_lock compared to regular
  * files. This is due to readdir potentially triggering page faults on a user
  * buffer inside filldir(), and this happens with the ilock on the directory
  * held. For regular files, the lock order is the other way around - the
- * mmap_sem is taken during the page fault, and then we lock the ilock to do
+ * mmap_lock is taken during the page fault, and then we lock the ilock to do
  * block mapping. Hence we need a different class for the directory ilock so
  * that lockdep can tell them apart.
  */
@@ -50,10 +54,15 @@ xfs_initxattrs(
 	int			error = 0;
 
 	for (xattr = xattr_array; xattr->name != NULL; xattr++) {
-		error = xfs_attr_set(ip, xattr->name,
-				     strlen(xattr->name),
-				     xattr->value, xattr->value_len,
-				     ATTR_SECURE);
+		struct xfs_da_args	args = {
+			.dp		= ip,
+			.attr_filter	= XFS_ATTR_SECURE,
+			.name		= xattr->name,
+			.namelen	= strlen(xattr->name),
+			.value		= xattr->value,
+			.valuelen	= xattr->value_len,
+		};
+		error = xfs_attr_change(&args);
 		if (error < 0)
 			break;
 	}
@@ -66,9 +75,8 @@ xfs_initxattrs(
  * these attrs can be journalled at inode creation time (along with the
  * inode, of course, such that log replay can't cause these to be lost).
  */
-
-STATIC int
-xfs_init_security(
+int
+xfs_inode_init_security(
 	struct inode	*inode,
 	struct inode	*dir,
 	const struct qstr *qstr)
@@ -113,7 +121,7 @@ xfs_cleanup_inode(
 
 	/* Oh, the horror.
 	 * If we can't add the ACL or we fail in
-	 * xfs_init_security we must back out.
+	 * xfs_inode_init_security we must back out.
 	 * ENOSPC can hit here, among other things.
 	 */
 	xfs_dentry_to_name(&teardown, dentry);
@@ -121,13 +129,45 @@ xfs_cleanup_inode(
 	xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
 }
 
+/*
+ * Check to see if we are likely to need an extended attribute to be added to
+ * the inode we are about to allocate. This allows the attribute fork to be
+ * created during the inode allocation, reducing the number of transactions we
+ * need to do in this fast path.
+ *
+ * The security checks are optimistic, but not guaranteed. The two LSMs that
+ * require xattrs to be added here (selinux and smack) are also the only two
+ * LSMs that add a sb->s_security structure to the superblock. Hence if security
+ * is enabled and sb->s_security is set, we have a pretty good idea that we are
+ * going to be asked to add a security xattr immediately after allocating the
+ * xfs inode and instantiating the VFS inode.
+ */
+static inline bool
+xfs_create_need_xattr(
+	struct inode	*dir,
+	struct posix_acl *default_acl,
+	struct posix_acl *acl)
+{
+	if (acl)
+		return true;
+	if (default_acl)
+		return true;
+#if IS_ENABLED(CONFIG_SECURITY)
+	if (dir->i_sb->s_security)
+		return true;
+#endif
+	return false;
+}
+
+
 STATIC int
 xfs_generic_create(
+	struct user_namespace	*mnt_userns,
 	struct inode	*dir,
 	struct dentry	*dentry,
 	umode_t		mode,
 	dev_t		rdev,
-	bool		tmpfile)	/* unnamed file */
+	struct file	*tmpfile)	/* unnamed file */
 {
 	struct inode	*inode;
 	struct xfs_inode *ip = NULL;
@@ -156,20 +196,21 @@ xfs_generic_create(
 		goto out_free_acl;
 
 	if (!tmpfile) {
-		error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
+		error = xfs_create(mnt_userns, XFS_I(dir), &name, mode, rdev,
+				xfs_create_need_xattr(dir, default_acl, acl),
+				&ip);
 	} else {
-		error = xfs_create_tmpfile(XFS_I(dir), mode, &ip);
+		error = xfs_create_tmpfile(mnt_userns, XFS_I(dir), mode, &ip);
 	}
 	if (unlikely(error))
 		goto out_free_acl;
 
 	inode = VFS_I(ip);
 
-	error = xfs_init_security(inode, dir, &dentry->d_name);
+	error = xfs_inode_init_security(inode, dir, &dentry->d_name);
 	if (unlikely(error))
 		goto out_cleanup_inode;
 
-#ifdef CONFIG_XFS_POSIX_ACL
 	if (default_acl) {
 		error = __xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
 		if (error)
@@ -180,7 +221,6 @@ xfs_generic_create(
 		if (error)
 			goto out_cleanup_inode;
 	}
-#endif
 
 	xfs_setup_iops(ip);
 
@@ -194,17 +234,15 @@ xfs_generic_create(
 		 * d_tmpfile can immediately set it back to zero.
 		 */
 		set_nlink(inode, 1);
-		d_tmpfile(dentry, inode);
+		d_tmpfile(tmpfile, inode);
 	} else
 		d_instantiate(dentry, inode);
 
 	xfs_finish_inode_setup(ip);
 
  out_free_acl:
-	if (default_acl)
-		posix_acl_release(default_acl);
-	if (acl)
-		posix_acl_release(acl);
+	posix_acl_release(default_acl);
+	posix_acl_release(acl);
 	return error;
 
  out_cleanup_inode:
@@ -217,31 +255,35 @@ xfs_generic_create(
 
 STATIC int
 xfs_vn_mknod(
-	struct inode	*dir,
-	struct dentry	*dentry,
-	umode_t		mode,
-	dev_t		rdev)
+	struct user_namespace	*mnt_userns,
+	struct inode		*dir,
+	struct dentry		*dentry,
+	umode_t			mode,
+	dev_t			rdev)
 {
-	return xfs_generic_create(dir, dentry, mode, rdev, false);
+	return xfs_generic_create(mnt_userns, dir, dentry, mode, rdev, NULL);
 }
 
 STATIC int
 xfs_vn_create(
-	struct inode	*dir,
-	struct dentry	*dentry,
-	umode_t		mode,
-	bool		flags)
+	struct user_namespace	*mnt_userns,
+	struct inode		*dir,
+	struct dentry		*dentry,
+	umode_t			mode,
+	bool			flags)
 {
-	return xfs_vn_mknod(dir, dentry, mode, 0);
+	return xfs_generic_create(mnt_userns, dir, dentry, mode, 0, NULL);
 }
 
 STATIC int
 xfs_vn_mkdir(
-	struct inode	*dir,
-	struct dentry	*dentry,
-	umode_t		mode)
+	struct user_namespace	*mnt_userns,
+	struct inode		*dir,
+	struct dentry		*dentry,
+	umode_t			mode)
 {
-	return xfs_vn_mknod(dir, dentry, mode|S_IFDIR, 0);
+	return xfs_generic_create(mnt_userns, dir, dentry, mode | S_IFDIR, 0,
+				  NULL);
 }
 
 STATIC struct dentry *
@@ -351,16 +393,17 @@ xfs_vn_unlink(
 	 * but still hashed. This is incompatible with case-insensitive
 	 * mode, so invalidate (unhash) the dentry in CI-mode.
 	 */
-	if (xfs_sb_version_hasasciici(&XFS_M(dir->i_sb)->m_sb))
+	if (xfs_has_asciici(XFS_M(dir->i_sb)))
 		d_invalidate(dentry);
 	return 0;
 }
 
 STATIC int
 xfs_vn_symlink(
-	struct inode	*dir,
-	struct dentry	*dentry,
-	const char	*symname)
+	struct user_namespace	*mnt_userns,
+	struct inode		*dir,
+	struct dentry		*dentry,
+	const char		*symname)
 {
 	struct inode	*inode;
 	struct xfs_inode *cip = NULL;
@@ -374,13 +417,13 @@ xfs_vn_symlink(
 	if (unlikely(error))
 		goto out;
 
-	error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip);
+	error = xfs_symlink(mnt_userns, XFS_I(dir), &name, symname, mode, &cip);
 	if (unlikely(error))
 		goto out;
 
 	inode = VFS_I(cip);
 
-	error = xfs_init_security(inode, dir, &dentry->d_name);
+	error = xfs_inode_init_security(inode, dir, &dentry->d_name);
 	if (unlikely(error))
 		goto out_cleanup_inode;
 
@@ -400,11 +443,12 @@ xfs_vn_symlink(
 
 STATIC int
 xfs_vn_rename(
-	struct inode	*odir,
-	struct dentry	*odentry,
-	struct inode	*ndir,
-	struct dentry	*ndentry,
-	unsigned int	flags)
+	struct user_namespace	*mnt_userns,
+	struct inode		*odir,
+	struct dentry		*odentry,
+	struct inode		*ndir,
+	struct dentry		*ndentry,
+	unsigned int		flags)
 {
 	struct inode	*new_inode = d_inode(ndentry);
 	int		omode = 0;
@@ -428,8 +472,8 @@ xfs_vn_rename(
 	if (unlikely(error))
 		return error;
 
-	return xfs_rename(XFS_I(odir), &oname, XFS_I(d_inode(odentry)),
-			  XFS_I(ndir), &nname,
+	return xfs_rename(mnt_userns, XFS_I(odir), &oname,
+			  XFS_I(d_inode(odentry)), XFS_I(ndir), &nname,
 			  new_inode ? XFS_I(new_inode) : NULL, flags);
 }
 
@@ -467,27 +511,6 @@ xfs_vn_get_link(
 	return ERR_PTR(error);
 }
 
-STATIC const char *
-xfs_vn_get_link_inline(
-	struct dentry		*dentry,
-	struct inode		*inode,
-	struct delayed_call	*done)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	char			*link;
-
-	ASSERT(ip->i_df.if_flags & XFS_IFINLINE);
-
-	/*
-	 * The VFS crashes on a NULL pointer, so return -EFSCORRUPTED if
-	 * if_data is junk.
-	 */
-	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)
@@ -499,7 +522,7 @@ xfs_stat_blksize(
 	 * always return the realtime extent size.
 	 */
 	if (XFS_IS_REALTIME_INODE(ip))
-		return xfs_get_extsz_hint(ip) << mp->m_sb.sb_blocklog;
+		return XFS_FSB_TO_B(mp, xfs_get_extsz_hint(ip));
 
 	/*
 	 * Allow large block sizes to be reported to userspace programs if the
@@ -514,10 +537,10 @@ xfs_stat_blksize(
 	 * default buffered I/O size, return that, otherwise return the compat
 	 * default.
 	 */
-	if (mp->m_flags & XFS_MOUNT_LARGEIO) {
+	if (xfs_has_large_iosize(mp)) {
 		if (mp->m_swidth)
-			return mp->m_swidth << mp->m_sb.sb_blocklog;
-		if (mp->m_flags & XFS_MOUNT_ALLOCSIZE)
+			return XFS_FSB_TO_B(mp, mp->m_swidth);
+		if (xfs_has_allocsize(mp))
 			return 1U << mp->m_allocsize_log;
 	}
 
@@ -526,6 +549,7 @@ xfs_stat_blksize(
 
 STATIC int
 xfs_vn_getattr(
+	struct user_namespace	*mnt_userns,
 	const struct path	*path,
 	struct kstat		*stat,
 	u32			request_mask,
@@ -534,29 +558,30 @@ xfs_vn_getattr(
 	struct inode		*inode = d_inode(path->dentry);
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
+	vfsuid_t		vfsuid = i_uid_into_vfsuid(mnt_userns, inode);
+	vfsgid_t		vfsgid = i_gid_into_vfsgid(mnt_userns, inode);
 
 	trace_xfs_getattr(ip);
 
-	if (XFS_FORCED_SHUTDOWN(mp))
+	if (xfs_is_shutdown(mp))
 		return -EIO;
 
 	stat->size = XFS_ISIZE(ip);
 	stat->dev = inode->i_sb->s_dev;
 	stat->mode = inode->i_mode;
 	stat->nlink = inode->i_nlink;
-	stat->uid = inode->i_uid;
-	stat->gid = inode->i_gid;
+	stat->uid = vfsuid_into_kuid(vfsuid);
+	stat->gid = vfsgid_into_kgid(vfsgid);
 	stat->ino = ip->i_ino;
 	stat->atime = inode->i_atime;
 	stat->mtime = inode->i_mtime;
 	stat->ctime = inode->i_ctime;
-	stat->blocks =
-		XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
+	stat->blocks = XFS_FSB_TO_BB(mp, ip->i_nblocks + ip->i_delayed_blks);
 
-	if (ip->i_d.di_version == 3) {
+	if (xfs_has_v3inodes(mp)) {
 		if (request_mask & STATX_BTIME) {
 			stat->result_mask |= STATX_BTIME;
-			stat->btime = ip->i_d.di_crtime;
+			stat->btime = ip->i_crtime;
 		}
 	}
 
@@ -564,11 +589,11 @@ xfs_vn_getattr(
 	 * Note: If you add another clause to set an attribute flag, please
 	 * update attributes_mask below.
 	 */
-	if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
+	if (ip->i_diflags & XFS_DIFLAG_IMMUTABLE)
 		stat->attributes |= STATX_ATTR_IMMUTABLE;
-	if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
+	if (ip->i_diflags & XFS_DIFLAG_APPEND)
 		stat->attributes |= STATX_ATTR_APPEND;
-	if (ip->i_d.di_flags & XFS_DIFLAG_NODUMP)
+	if (ip->i_diflags & XFS_DIFLAG_NODUMP)
 		stat->attributes |= STATX_ATTR_NODUMP;
 
 	stat->attributes_mask |= (STATX_ATTR_IMMUTABLE |
@@ -581,6 +606,16 @@ xfs_vn_getattr(
 		stat->blksize = BLKDEV_IOSIZE;
 		stat->rdev = inode->i_rdev;
 		break;
+	case S_IFREG:
+		if (request_mask & STATX_DIOALIGN) {
+			struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
+			struct block_device	*bdev = target->bt_bdev;
+
+			stat->result_mask |= STATX_DIOALIGN;
+			stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
+			stat->dio_offset_align = bdev_logical_block_size(bdev);
+		}
+		fallthrough;
 	default:
 		stat->blksize = xfs_stat_blksize(ip);
 		stat->rdev = 0;
@@ -590,51 +625,21 @@ xfs_vn_getattr(
 	return 0;
 }
 
-static void
-xfs_setattr_mode(
-	struct xfs_inode	*ip,
-	struct iattr		*iattr)
-{
-	struct inode		*inode = VFS_I(ip);
-	umode_t			mode = iattr->ia_mode;
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
-	inode->i_mode &= S_IFMT;
-	inode->i_mode |= mode & ~S_IFMT;
-}
-
-void
-xfs_setattr_time(
-	struct xfs_inode	*ip,
-	struct iattr		*iattr)
-{
-	struct inode		*inode = VFS_I(ip);
-
-	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-
-	if (iattr->ia_valid & ATTR_ATIME)
-		inode->i_atime = iattr->ia_atime;
-	if (iattr->ia_valid & ATTR_CTIME)
-		inode->i_ctime = iattr->ia_ctime;
-	if (iattr->ia_valid & ATTR_MTIME)
-		inode->i_mtime = iattr->ia_mtime;
-}
-
 static int
 xfs_vn_change_ok(
-	struct dentry	*dentry,
-	struct iattr	*iattr)
+	struct user_namespace	*mnt_userns,
+	struct dentry		*dentry,
+	struct iattr		*iattr)
 {
 	struct xfs_mount	*mp = XFS_I(d_inode(dentry))->i_mount;
 
-	if (mp->m_flags & XFS_MOUNT_RDONLY)
+	if (xfs_is_readonly(mp))
 		return -EROFS;
 
-	if (XFS_FORCED_SHUTDOWN(mp))
+	if (xfs_is_shutdown(mp))
 		return -EIO;
 
-	return setattr_prepare(dentry, iattr);
+	return setattr_prepare(mnt_userns, dentry, iattr);
 }
 
 /*
@@ -643,21 +648,21 @@ xfs_vn_change_ok(
  * Caution: The caller of this function is responsible for calling
  * setattr_prepare() or otherwise verifying the change is fine.
  */
-int
+static int
 xfs_setattr_nonsize(
+	struct user_namespace	*mnt_userns,
 	struct xfs_inode	*ip,
-	struct iattr		*iattr,
-	int			flags)
+	struct iattr		*iattr)
 {
 	xfs_mount_t		*mp = ip->i_mount;
 	struct inode		*inode = VFS_I(ip);
 	int			mask = iattr->ia_valid;
 	xfs_trans_t		*tp;
 	int			error;
-	kuid_t			uid = GLOBAL_ROOT_UID, iuid = GLOBAL_ROOT_UID;
-	kgid_t			gid = GLOBAL_ROOT_GID, igid = GLOBAL_ROOT_GID;
+	kuid_t			uid = GLOBAL_ROOT_UID;
+	kgid_t			gid = GLOBAL_ROOT_GID;
 	struct xfs_dquot	*udqp = NULL, *gdqp = NULL;
-	struct xfs_dquot	*olddquot1 = NULL, *olddquot2 = NULL;
+	struct xfs_dquot	*old_udqp = NULL, *old_gdqp = NULL;
 
 	ASSERT((mask & ATTR_SIZE) == 0);
 
@@ -673,13 +678,15 @@ xfs_setattr_nonsize(
 		uint	qflags = 0;
 
 		if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
-			uid = iattr->ia_uid;
+			uid = from_vfsuid(mnt_userns, i_user_ns(inode),
+					  iattr->ia_vfsuid);
 			qflags |= XFS_QMOPT_UQUOTA;
 		} else {
 			uid = inode->i_uid;
 		}
 		if ((mask & ATTR_GID) && XFS_IS_GQUOTA_ON(mp)) {
-			gid = iattr->ia_gid;
+			gid = from_vfsgid(mnt_userns, i_user_ns(inode),
+					  iattr->ia_vfsgid);
 			qflags |= XFS_QMOPT_GQUOTA;
 		}  else {
 			gid = inode->i_gid;
@@ -692,114 +699,50 @@ xfs_setattr_nonsize(
 		 */
 		ASSERT(udqp == NULL);
 		ASSERT(gdqp == NULL);
-		error = xfs_qm_vop_dqalloc(ip, xfs_kuid_to_uid(uid),
-					   xfs_kgid_to_gid(gid),
-					   ip->i_d.di_projid,
+		error = xfs_qm_vop_dqalloc(ip, uid, gid, ip->i_projid,
 					   qflags, &udqp, &gdqp, NULL);
 		if (error)
 			return error;
 	}
 
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
+	error = xfs_trans_alloc_ichange(ip, udqp, gdqp, NULL,
+			has_capability_noaudit(current, CAP_FOWNER), &tp);
 	if (error)
 		goto out_dqrele;
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	xfs_trans_ijoin(tp, ip, 0);
-
 	/*
-	 * Change file ownership.  Must be the owner or privileged.
+	 * Register quota modifications in the transaction.  Must be the owner
+	 * or privileged.  These IDs could have changed since we last looked at
+	 * them.  But, we're assured that if the ownership did change while we
+	 * didn't have the inode locked, inode's dquot(s) would have changed
+	 * also.
 	 */
-	if (mask & (ATTR_UID|ATTR_GID)) {
-		/*
-		 * These IDs could have changed since we last looked at them.
-		 * But, we're assured that if the ownership did change
-		 * while we didn't have the inode locked, inode's dquot(s)
-		 * would have changed also.
-		 */
-		iuid = inode->i_uid;
-		igid = inode->i_gid;
-		gid = (mask & ATTR_GID) ? iattr->ia_gid : igid;
-		uid = (mask & ATTR_UID) ? iattr->ia_uid : iuid;
-
-		/*
-		 * Do a quota reservation only if uid/gid is actually
-		 * going to change.
-		 */
-		if (XFS_IS_QUOTA_RUNNING(mp) &&
-		    ((XFS_IS_UQUOTA_ON(mp) && !uid_eq(iuid, uid)) ||
-		     (XFS_IS_GQUOTA_ON(mp) && !gid_eq(igid, gid)))) {
-			ASSERT(tp);
-			error = xfs_qm_vop_chown_reserve(tp, ip, udqp, gdqp,
-						NULL, capable(CAP_FOWNER) ?
-						XFS_QMOPT_FORCE_RES : 0);
-			if (error)	/* out of quota */
-				goto out_cancel;
-		}
+	if (XFS_IS_UQUOTA_ON(mp) &&
+	    i_uid_needs_update(mnt_userns, iattr, inode)) {
+		ASSERT(udqp);
+		old_udqp = xfs_qm_vop_chown(tp, ip, &ip->i_udquot, udqp);
 	}
-
-	/*
-	 * Change file ownership.  Must be the owner or privileged.
-	 */
-	if (mask & (ATTR_UID|ATTR_GID)) {
-		/*
-		 * CAP_FSETID overrides the following restrictions:
-		 *
-		 * The set-user-ID and set-group-ID bits of a file will be
-		 * cleared upon successful return from chown()
-		 */
-		if ((inode->i_mode & (S_ISUID|S_ISGID)) &&
-		    !capable(CAP_FSETID))
-			inode->i_mode &= ~(S_ISUID|S_ISGID);
-
-		/*
-		 * Change the ownerships and register quota modifications
-		 * in the transaction.
-		 */
-		if (!uid_eq(iuid, uid)) {
-			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_UQUOTA_ON(mp)) {
-				ASSERT(mask & ATTR_UID);
-				ASSERT(udqp);
-				olddquot1 = xfs_qm_vop_chown(tp, ip,
-							&ip->i_udquot, udqp);
-			}
-			ip->i_d.di_uid = xfs_kuid_to_uid(uid);
-			inode->i_uid = uid;
-		}
-		if (!gid_eq(igid, gid)) {
-			if (XFS_IS_QUOTA_RUNNING(mp) && XFS_IS_GQUOTA_ON(mp)) {
-				ASSERT(xfs_sb_version_has_pquotino(&mp->m_sb) ||
-				       !XFS_IS_PQUOTA_ON(mp));
-				ASSERT(mask & ATTR_GID);
-				ASSERT(gdqp);
-				olddquot2 = xfs_qm_vop_chown(tp, ip,
-							&ip->i_gdquot, gdqp);
-			}
-			ip->i_d.di_gid = xfs_kgid_to_gid(gid);
-			inode->i_gid = gid;
-		}
+	if (XFS_IS_GQUOTA_ON(mp) &&
+	    i_gid_needs_update(mnt_userns, iattr, inode)) {
+		ASSERT(xfs_has_pquotino(mp) || !XFS_IS_PQUOTA_ON(mp));
+		ASSERT(gdqp);
+		old_gdqp = xfs_qm_vop_chown(tp, ip, &ip->i_gdquot, gdqp);
 	}
 
-	if (mask & ATTR_MODE)
-		xfs_setattr_mode(ip, iattr);
-	if (mask & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
-		xfs_setattr_time(ip, iattr);
-
+	setattr_copy(mnt_userns, inode, iattr);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	XFS_STATS_INC(mp, xs_ig_attrchg);
 
-	if (mp->m_flags & XFS_MOUNT_WSYNC)
+	if (xfs_has_wsync(mp))
 		xfs_trans_set_sync(tp);
 	error = xfs_trans_commit(tp);
 
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
-
 	/*
 	 * Release any dquot(s) the inode had kept before chown.
 	 */
-	xfs_qm_dqrele(olddquot1);
-	xfs_qm_dqrele(olddquot2);
+	xfs_qm_dqrele(old_udqp);
+	xfs_qm_dqrele(old_gdqp);
 	xfs_qm_dqrele(udqp);
 	xfs_qm_dqrele(gdqp);
 
@@ -813,39 +756,20 @@ xfs_setattr_nonsize(
 	 *	     to attr_set.  No previous user of the generic
 	 * 	     Posix ACL code seems to care about this issue either.
 	 */
-	if ((mask & ATTR_MODE) && !(flags & XFS_ATTR_NOACL)) {
-		error = posix_acl_chmod(inode, inode->i_mode);
+	if (mask & ATTR_MODE) {
+		error = posix_acl_chmod(mnt_userns, inode, inode->i_mode);
 		if (error)
 			return error;
 	}
 
 	return 0;
 
-out_cancel:
-	xfs_trans_cancel(tp);
-	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 out_dqrele:
 	xfs_qm_dqrele(udqp);
 	xfs_qm_dqrele(gdqp);
 	return error;
 }
 
-int
-xfs_vn_setattr_nonsize(
-	struct dentry		*dentry,
-	struct iattr		*iattr)
-{
-	struct xfs_inode	*ip = XFS_I(d_inode(dentry));
-	int error;
-
-	trace_xfs_setattr(ip);
-
-	error = xfs_vn_change_ok(dentry, iattr);
-	if (error)
-		return error;
-	return xfs_setattr_nonsize(ip, iattr, 0);
-}
-
 /*
  * Truncate file.  Must have write permission and not be a directory.
  *
@@ -854,6 +778,7 @@ xfs_vn_setattr_nonsize(
  */
 STATIC int
 xfs_setattr_size(
+	struct user_namespace	*mnt_userns,
 	struct xfs_inode	*ip,
 	struct iattr		*iattr)
 {
@@ -869,7 +794,7 @@ xfs_setattr_size(
 	ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
 	ASSERT(S_ISREG(inode->i_mode));
 	ASSERT((iattr->ia_valid & (ATTR_UID|ATTR_GID|ATTR_ATIME|ATTR_ATIME_SET|
-		ATTR_MTIME_SET|ATTR_KILL_PRIV|ATTR_TIMES_SET)) == 0);
+		ATTR_MTIME_SET|ATTR_TIMES_SET)) == 0);
 
 	oldsize = inode->i_size;
 	newsize = iattr->ia_size;
@@ -877,7 +802,7 @@ xfs_setattr_size(
 	/*
 	 * Short circuit the truncate case for zero length files.
 	 */
-	if (newsize == 0 && oldsize == 0 && ip->i_d.di_nextents == 0) {
+	if (newsize == 0 && oldsize == 0 && ip->i_df.if_nextents == 0) {
 		if (!(iattr->ia_valid & (ATTR_CTIME|ATTR_MTIME)))
 			return 0;
 
@@ -885,7 +810,7 @@ xfs_setattr_size(
 		 * Use the regular setattr path to update the timestamps.
 		 */
 		iattr->ia_valid &= ~ATTR_SIZE;
-		return xfs_setattr_nonsize(ip, iattr, 0);
+		return xfs_setattr_nonsize(mnt_userns, ip, iattr);
 	}
 
 	/*
@@ -912,11 +837,20 @@ 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_buffered_write_iomap_ops);
+		error = xfs_zero_range(ip, oldsize, newsize - oldsize,
+				&did_zeroing);
 	} else {
-		error = iomap_truncate_page(inode, newsize, &did_zeroing,
-				&xfs_buffered_write_iomap_ops);
+		/*
+		 * iomap won't detect a dirty page over an unwritten block (or a
+		 * cow block over a hole) and subsequently skips zeroing the
+		 * newly post-EOF portion of the page. Flush the new EOF to
+		 * convert the block before the pagecache truncate.
+		 */
+		error = filemap_write_and_wait_range(inode->i_mapping, newsize,
+						     newsize);
+		if (error)
+			return error;
+		error = xfs_truncate_page(ip, newsize, &did_zeroing);
 	}
 
 	if (error)
@@ -940,8 +874,8 @@ xfs_setattr_size(
 	 * operation.
 	 *
 	 * And we update in-core i_size and truncate page cache beyond newsize
-	 * before writeback the [di_size, newsize] range, so we're guaranteed
-	 * not to write stale data past the new EOF on truncate down.
+	 * before writeback the [i_disk_size, newsize] range, so we're
+	 * guaranteed not to write stale data past the new EOF on truncate down.
 	 */
 	truncate_setsize(inode, newsize);
 
@@ -954,9 +888,9 @@ xfs_setattr_size(
 	 * otherwise those blocks may not be zeroed after a crash.
 	 */
 	if (did_zeroing ||
-	    (newsize > ip->i_d.di_size && oldsize != ip->i_d.di_size)) {
+	    (newsize > ip->i_disk_size && oldsize != ip->i_disk_size)) {
 		error = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
-						ip->i_d.di_size, newsize - 1);
+						ip->i_disk_size, newsize - 1);
 		if (error)
 			return error;
 	}
@@ -998,7 +932,7 @@ xfs_setattr_size(
 	 * permanent before actually freeing any blocks it doesn't matter if
 	 * they get written to.
 	 */
-	ip->i_d.di_size = newsize;
+	ip->i_disk_size = newsize;
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	if (newsize <= oldsize) {
@@ -1019,16 +953,13 @@ xfs_setattr_size(
 		xfs_inode_clear_eofblocks_tag(ip);
 	}
 
-	if (iattr->ia_valid & ATTR_MODE)
-		xfs_setattr_mode(ip, iattr);
-	if (iattr->ia_valid & (ATTR_ATIME|ATTR_CTIME|ATTR_MTIME))
-		xfs_setattr_time(ip, iattr);
-
+	ASSERT(!(iattr->ia_valid & (ATTR_UID | ATTR_GID)));
+	setattr_copy(mnt_userns, inode, iattr);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	XFS_STATS_INC(mp, xs_ig_attrchg);
 
-	if (mp->m_flags & XFS_MOUNT_WSYNC)
+	if (xfs_has_wsync(mp))
 		xfs_trans_set_sync(tp);
 
 	error = xfs_trans_commit(tp);
@@ -1044,6 +975,7 @@ out_trans_cancel:
 
 int
 xfs_vn_setattr_size(
+	struct user_namespace	*mnt_userns,
 	struct dentry		*dentry,
 	struct iattr		*iattr)
 {
@@ -1052,22 +984,23 @@ xfs_vn_setattr_size(
 
 	trace_xfs_setattr(ip);
 
-	error = xfs_vn_change_ok(dentry, iattr);
+	error = xfs_vn_change_ok(mnt_userns, dentry, iattr);
 	if (error)
 		return error;
-	return xfs_setattr_size(ip, iattr);
+	return xfs_setattr_size(mnt_userns, ip, iattr);
 }
 
 STATIC int
 xfs_vn_setattr(
+	struct user_namespace	*mnt_userns,
 	struct dentry		*dentry,
 	struct iattr		*iattr)
 {
+	struct inode		*inode = d_inode(dentry);
+	struct xfs_inode	*ip = XFS_I(inode);
 	int			error;
 
 	if (iattr->ia_valid & ATTR_SIZE) {
-		struct inode		*inode = d_inode(dentry);
-		struct xfs_inode	*ip = XFS_I(inode);
 		uint			iolock;
 
 		xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
@@ -1079,10 +1012,14 @@ xfs_vn_setattr(
 			return error;
 		}
 
-		error = xfs_vn_setattr_size(dentry, iattr);
+		error = xfs_vn_setattr_size(mnt_userns, dentry, iattr);
 		xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	} else {
-		error = xfs_vn_setattr_nonsize(dentry, iattr);
+		trace_xfs_setattr(ip);
+
+		error = xfs_vn_change_ok(mnt_userns, dentry, iattr);
+		if (!error)
+			error = xfs_setattr_nonsize(mnt_userns, ip, iattr);
 	}
 
 	return error;
@@ -1153,11 +1090,14 @@ xfs_vn_fiemap(
 
 STATIC int
 xfs_vn_tmpfile(
-	struct inode	*dir,
-	struct dentry	*dentry,
-	umode_t		mode)
+	struct user_namespace	*mnt_userns,
+	struct inode		*dir,
+	struct file		*file,
+	umode_t			mode)
 {
-	return xfs_generic_create(dir, dentry, mode, 0, true);
+	int err = xfs_generic_create(mnt_userns, dir, file->f_path.dentry, mode, 0, file);
+
+	return finish_open_simple(file, err);
 }
 
 static const struct inode_operations xfs_inode_operations = {
@@ -1168,6 +1108,8 @@ static const struct inode_operations xfs_inode_operations = {
 	.listxattr		= xfs_vn_listxattr,
 	.fiemap			= xfs_vn_fiemap,
 	.update_time		= xfs_vn_update_time,
+	.fileattr_get		= xfs_fileattr_get,
+	.fileattr_set		= xfs_fileattr_set,
 };
 
 static const struct inode_operations xfs_dir_inode_operations = {
@@ -1193,6 +1135,8 @@ static const struct inode_operations xfs_dir_inode_operations = {
 	.listxattr		= xfs_vn_listxattr,
 	.update_time		= xfs_vn_update_time,
 	.tmpfile		= xfs_vn_tmpfile,
+	.fileattr_get		= xfs_fileattr_get,
+	.fileattr_set		= xfs_fileattr_set,
 };
 
 static const struct inode_operations xfs_dir_ci_inode_operations = {
@@ -1218,6 +1162,8 @@ static const struct inode_operations xfs_dir_ci_inode_operations = {
 	.listxattr		= xfs_vn_listxattr,
 	.update_time		= xfs_vn_update_time,
 	.tmpfile		= xfs_vn_tmpfile,
+	.fileattr_get		= xfs_fileattr_get,
+	.fileattr_set		= xfs_fileattr_set,
 };
 
 static const struct inode_operations xfs_symlink_inode_operations = {
@@ -1228,14 +1174,6 @@ static const struct inode_operations xfs_symlink_inode_operations = {
 	.update_time		= xfs_vn_update_time,
 };
 
-static const struct inode_operations xfs_inline_symlink_inode_operations = {
-	.get_link		= xfs_vn_get_link_inline,
-	.getattr		= xfs_vn_getattr,
-	.setattr		= xfs_vn_setattr,
-	.listxattr		= xfs_vn_listxattr,
-	.update_time		= xfs_vn_update_time,
-};
-
 /* Figure out if this file actually supports DAX. */
 static bool
 xfs_inode_supports_dax(
@@ -1243,13 +1181,12 @@ xfs_inode_supports_dax(
 {
 	struct xfs_mount	*mp = ip->i_mount;
 
-	/* Only supported on non-reflinked files. */
-	if (!S_ISREG(VFS_I(ip)->i_mode) || xfs_is_reflink_inode(ip))
+	/* Only supported on regular files. */
+	if (!S_ISREG(VFS_I(ip)->i_mode))
 		return false;
 
-	/* DAX mount option or DAX iflag must be set. */
-	if (!(mp->m_flags & XFS_MOUNT_DAX) &&
-	    !(ip->i_d.di_flags2 & XFS_DIFLAG2_DAX))
+	/* Only supported on non-reflinked files. */
+	if (xfs_is_reflink_inode(ip))
 		return false;
 
 	/* Block size must match page size */
@@ -1260,35 +1197,60 @@ xfs_inode_supports_dax(
 	return xfs_inode_buftarg(ip)->bt_daxdev != NULL;
 }
 
-STATIC void
+static bool
+xfs_inode_should_enable_dax(
+	struct xfs_inode *ip)
+{
+	if (!IS_ENABLED(CONFIG_FS_DAX))
+		return false;
+	if (xfs_has_dax_never(ip->i_mount))
+		return false;
+	if (!xfs_inode_supports_dax(ip))
+		return false;
+	if (xfs_has_dax_always(ip->i_mount))
+		return true;
+	if (ip->i_diflags2 & XFS_DIFLAG2_DAX)
+		return true;
+	return false;
+}
+
+void
 xfs_diflags_to_iflags(
-	struct inode		*inode,
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	bool init)
 {
-	uint16_t		flags = ip->i_d.di_flags;
-
-	inode->i_flags &= ~(S_IMMUTABLE | S_APPEND | S_SYNC |
-			    S_NOATIME | S_DAX);
-
-	if (flags & XFS_DIFLAG_IMMUTABLE)
-		inode->i_flags |= S_IMMUTABLE;
-	if (flags & XFS_DIFLAG_APPEND)
-		inode->i_flags |= S_APPEND;
-	if (flags & XFS_DIFLAG_SYNC)
-		inode->i_flags |= S_SYNC;
-	if (flags & XFS_DIFLAG_NOATIME)
-		inode->i_flags |= S_NOATIME;
-	if (xfs_inode_supports_dax(ip))
-		inode->i_flags |= S_DAX;
+	struct inode            *inode = VFS_I(ip);
+	unsigned int            xflags = xfs_ip2xflags(ip);
+	unsigned int            flags = 0;
+
+	ASSERT(!(IS_DAX(inode) && init));
+
+	if (xflags & FS_XFLAG_IMMUTABLE)
+		flags |= S_IMMUTABLE;
+	if (xflags & FS_XFLAG_APPEND)
+		flags |= S_APPEND;
+	if (xflags & FS_XFLAG_SYNC)
+		flags |= S_SYNC;
+	if (xflags & FS_XFLAG_NOATIME)
+		flags |= S_NOATIME;
+	if (init && xfs_inode_should_enable_dax(ip))
+		flags |= S_DAX;
+
+	/*
+	 * S_DAX can only be set during inode initialization and is never set by
+	 * the VFS, so we cannot mask off S_DAX in i_flags.
+	 */
+	inode->i_flags &= ~(S_IMMUTABLE | S_APPEND | S_SYNC | S_NOATIME);
+	inode->i_flags |= flags;
 }
 
 /*
  * Initialize the Linux inode.
  *
  * When reading existing inodes from disk this is called directly from xfs_iget,
- * when creating a new inode it is called from xfs_ialloc after setting up the
- * inode. These callers have different criteria for clearing XFS_INEW, so leave
- * it up to the caller to deal with unlocking the inode appropriately.
+ * when creating a new inode it is called from xfs_init_new_inode after setting
+ * up the inode. These callers have different criteria for clearing XFS_INEW, so
+ * leave it up to the caller to deal with unlocking the inode appropriately.
  */
 void
 xfs_setup_inode(
@@ -1298,17 +1260,14 @@ xfs_setup_inode(
 	gfp_t			gfp_mask;
 
 	inode->i_ino = ip->i_ino;
-	inode->i_state = I_NEW;
+	inode->i_state |= I_NEW;
 
 	inode_sb_list_add(inode);
 	/* make the inode look hashed for the writeback code */
 	inode_fake_hash(inode);
 
-	inode->i_uid    = xfs_uid_to_kuid(ip->i_d.di_uid);
-	inode->i_gid    = xfs_gid_to_kgid(ip->i_d.di_gid);
-
-	i_size_write(inode, ip->i_d.di_size);
-	xfs_diflags_to_iflags(inode, ip);
+	i_size_write(inode, ip->i_disk_size);
+	xfs_diflags_to_iflags(ip, true);
 
 	if (S_ISDIR(inode->i_mode)) {
 		/*
@@ -1336,7 +1295,7 @@ xfs_setup_inode(
 	 * If there is no attribute fork no ACL can exist on this inode,
 	 * and it can't have any file capabilities attached to it either.
 	 */
-	if (!XFS_IFORK_Q(ip)) {
+	if (!xfs_inode_has_attr_fork(ip)) {
 		inode_has_no_xattr(inode);
 		cache_no_acl(inode);
 	}
@@ -1358,17 +1317,14 @@ xfs_setup_iops(
 			inode->i_mapping->a_ops = &xfs_address_space_operations;
 		break;
 	case S_IFDIR:
-		if (xfs_sb_version_hasasciici(&XFS_M(inode->i_sb)->m_sb))
+		if (xfs_has_asciici(XFS_M(inode->i_sb)))
 			inode->i_op = &xfs_dir_ci_inode_operations;
 		else
 			inode->i_op = &xfs_dir_inode_operations;
 		inode->i_fop = &xfs_dir_file_operations;
 		break;
 	case S_IFLNK:
-		if (ip->i_df.if_flags & XFS_IFINLINE)
-			inode->i_op = &xfs_inline_symlink_inode_operations;
-		else
-			inode->i_op = &xfs_symlink_inode_operations;
+		inode->i_op = &xfs_symlink_inode_operations;
 		break;
 	default:
 		inode->i_op = &xfs_inode_operations;