1 files changed, 327 insertions, 204 deletions

diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index b79b3846e71b..ad94fbf55014 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -13,8 +13,12 @@
 #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_trans_space.h"
+#include "xfs_bmap_btree.h"
 #include "xfs_trace.h"
 #include "xfs_icache.h"
 #include "xfs_symlink.h"
@@ -22,6 +26,10 @@
 #include "xfs_iomap.h"
 #include "xfs_error.h"
 #include "xfs_ioctl.h"
+#include "xfs_xattr.h"
+#include "xfs_file.h"
+#include "xfs_bmap.h"
+#include "xfs_zone_alloc.h"
 
 #include <linux/posix_acl.h>
 #include <linux/security.h>
@@ -35,7 +43,9 @@
  * held. For regular files, the lock order is the other way around - the
  * 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.
+ * that lockdep can tell them apart.  Directories in the metadata directory
+ * tree get a separate class so that lockdep reports will warn us if someone
+ * ever tries to lock regular directories after locking metadata directories.
  */
 static struct lock_class_key xfs_nondir_ilock_class;
 static struct lock_class_key xfs_dir_ilock_class;
@@ -59,7 +69,7 @@ xfs_initxattrs(
 			.value		= xattr->value,
 			.valuelen	= xattr->value_len,
 		};
-		error = xfs_attr_set(&args);
+		error = xfs_attr_change(&args, XFS_ATTRUPDATE_UPSERT);
 		if (error < 0)
 			break;
 	}
@@ -72,9 +82,8 @@ 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)
@@ -119,7 +128,7 @@ 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);
@@ -160,56 +169,72 @@ xfs_create_need_xattr(
 
 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 mnt_idmap	*idmap,
+	struct inode		*dir,
+	struct dentry		*dentry,
+	umode_t			mode,
+	dev_t			rdev,
+	struct file		*tmpfile)	/* unnamed file */
 {
-	struct inode	*inode;
-	struct xfs_inode *ip = NULL;
-	struct posix_acl *default_acl, *acl;
-	struct xfs_name	name;
-	int		error;
+	struct xfs_icreate_args	args = {
+		.idmap		= idmap,
+		.pip		= XFS_I(dir),
+		.rdev		= rdev,
+		.mode		= mode,
+	};
+	struct inode		*inode;
+	struct xfs_inode	*ip = NULL;
+	struct posix_acl	*default_acl, *acl;
+	struct xfs_name		name;
+	int			error;
 
 	/*
 	 * Irix uses Missed'em'V split, but doesn't want to see
 	 * the upper 5 bits of (14bit) major.
 	 */
-	if (S_ISCHR(mode) || S_ISBLK(mode)) {
-		if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
+	if (S_ISCHR(args.mode) || S_ISBLK(args.mode)) {
+		if (unlikely(!sysv_valid_dev(args.rdev) ||
+			     MAJOR(args.rdev) & ~0x1ff))
 			return -EINVAL;
 	} else {
-		rdev = 0;
+		args.rdev = 0;
 	}
 
-	error = posix_acl_create(dir, &mode, &default_acl, &acl);
+	error = posix_acl_create(dir, &args.mode, &default_acl, &acl);
 	if (error)
 		return error;
 
 	/* Verify mode is valid also for tmpfile case */
-	error = xfs_dentry_mode_to_name(&name, dentry, mode);
+	error = xfs_dentry_mode_to_name(&name, dentry, args.mode);
 	if (unlikely(error))
 		goto out_free_acl;
 
 	if (!tmpfile) {
-		error = xfs_create(mnt_userns, XFS_I(dir), &name, mode, rdev,
-				xfs_create_need_xattr(dir, default_acl, acl),
-				&ip);
+		if (xfs_create_need_xattr(dir, default_acl, acl))
+			args.flags |= XFS_ICREATE_INIT_XATTRS;
+
+		error = xfs_create(&args, &name, &ip);
 	} else {
-		error = xfs_create_tmpfile(mnt_userns, XFS_I(dir), mode, &ip);
+		args.flags |= XFS_ICREATE_TMPFILE;
+
+		/*
+		 * If this temporary file will not be linkable, don't bother
+		 * creating an attr fork to receive a parent pointer.
+		 */
+		if (tmpfile->f_flags & O_EXCL)
+			args.flags |= XFS_ICREATE_UNLINKABLE;
+
+		error = xfs_create_tmpfile(&args, &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)
@@ -220,7 +245,6 @@ xfs_generic_create(
 		if (error)
 			goto out_cleanup_inode;
 	}
-#endif
 
 	xfs_setup_iops(ip);
 
@@ -234,7 +258,7 @@ 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);
 
@@ -255,35 +279,34 @@ xfs_generic_create(
 
 STATIC int
 xfs_vn_mknod(
-	struct user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
 	struct inode		*dir,
 	struct dentry		*dentry,
 	umode_t			mode,
 	dev_t			rdev)
 {
-	return xfs_generic_create(mnt_userns, dir, dentry, mode, rdev, false);
+	return xfs_generic_create(idmap, dir, dentry, mode, rdev, NULL);
 }
 
 STATIC int
 xfs_vn_create(
-	struct user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
 	struct inode		*dir,
 	struct dentry		*dentry,
 	umode_t			mode,
 	bool			flags)
 {
-	return xfs_generic_create(mnt_userns, dir, dentry, mode, 0, false);
+	return xfs_generic_create(idmap, dir, dentry, mode, 0, NULL);
 }
 
-STATIC int
+STATIC struct dentry *
 xfs_vn_mkdir(
-	struct user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
 	struct inode		*dir,
 	struct dentry		*dentry,
 	umode_t			mode)
 {
-	return xfs_generic_create(mnt_userns, dir, dentry, mode | S_IFDIR, 0,
-				  false);
+	return ERR_PTR(xfs_generic_create(idmap, dir, dentry, mode | S_IFDIR, 0, NULL));
 }
 
 STATIC struct dentry *
@@ -347,7 +370,7 @@ xfs_vn_ci_lookup(
 	dname.name = ci_name.name;
 	dname.len = ci_name.len;
 	dentry = d_add_ci(dentry, VFS_I(ip), &dname);
-	kmem_free(ci_name.name);
+	kfree(ci_name.name);
 	return dentry;
 }
 
@@ -365,6 +388,9 @@ xfs_vn_link(
 	if (unlikely(error))
 		return error;
 
+	if (IS_PRIVATE(inode))
+		return -EPERM;
+
 	error = xfs_link(XFS_I(dir), XFS_I(inode), &name);
 	if (unlikely(error))
 		return error;
@@ -400,30 +426,28 @@ xfs_vn_unlink(
 
 STATIC int
 xfs_vn_symlink(
-	struct user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
 	struct inode		*dir,
 	struct dentry		*dentry,
 	const char		*symname)
 {
-	struct inode	*inode;
-	struct xfs_inode *cip = NULL;
-	struct xfs_name	name;
-	int		error;
-	umode_t		mode;
+	struct inode		*inode;
+	struct xfs_inode	*cip = NULL;
+	struct xfs_name		name;
+	int			error;
+	umode_t			mode = S_IFLNK | S_IRWXUGO;
 
-	mode = S_IFLNK |
-		(irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO);
 	error = xfs_dentry_mode_to_name(&name, dentry, mode);
 	if (unlikely(error))
 		goto out;
 
-	error = xfs_symlink(mnt_userns, XFS_I(dir), &name, symname, mode, &cip);
+	error = xfs_symlink(idmap, 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;
 
@@ -443,7 +467,7 @@ xfs_vn_symlink(
 
 STATIC int
 xfs_vn_rename(
-	struct user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
 	struct inode		*odir,
 	struct dentry		*odentry,
 	struct inode		*ndir,
@@ -472,7 +496,7 @@ xfs_vn_rename(
 	if (unlikely(error))
 		return error;
 
-	return xfs_rename(mnt_userns, XFS_I(odir), &oname,
+	return xfs_rename(idmap, XFS_I(odir), &oname,
 			  XFS_I(d_inode(odentry)), XFS_I(ndir), &nname,
 			  new_inode ? XFS_I(new_inode) : NULL, flags);
 }
@@ -522,7 +546,7 @@ xfs_stat_blksize(
 	 * always return the realtime extent size.
 	 */
 	if (XFS_IS_REALTIME_INODE(ip))
-		return XFS_FSB_TO_B(mp, xfs_get_extsz_hint(ip));
+		return XFS_FSB_TO_B(mp, xfs_get_extsz_hint(ip) ? : 1);
 
 	/*
 	 * Allow large block sizes to be reported to userspace programs if the
@@ -544,12 +568,119 @@ xfs_stat_blksize(
 			return 1U << mp->m_allocsize_log;
 	}
 
-	return PAGE_SIZE;
+	return max_t(uint32_t, PAGE_SIZE, mp->m_sb.sb_blocksize);
+}
+
+static void
+xfs_report_dioalign(
+	struct xfs_inode	*ip,
+	struct kstat		*stat)
+{
+	struct xfs_buftarg	*target = xfs_inode_buftarg(ip);
+	struct block_device	*bdev = target->bt_bdev;
+
+	stat->result_mask |= STATX_DIOALIGN | STATX_DIO_READ_ALIGN;
+	stat->dio_mem_align = bdev_dma_alignment(bdev) + 1;
+
+	/*
+	 * For COW inodes, we can only perform out of place writes of entire
+	 * allocation units (blocks or RT extents).
+	 * For writes smaller than the allocation unit, we must fall back to
+	 * buffered I/O to perform read-modify-write cycles.  At best this is
+	 * highly inefficient; at worst it leads to page cache invalidation
+	 * races.  Tell applications to avoid this by reporting the larger write
+	 * alignment in dio_offset_align, and the smaller read alignment in
+	 * dio_read_offset_align.
+	 */
+	stat->dio_read_offset_align = bdev_logical_block_size(bdev);
+	if (xfs_is_cow_inode(ip))
+		stat->dio_offset_align = xfs_inode_alloc_unitsize(ip);
+	else
+		stat->dio_offset_align = stat->dio_read_offset_align;
+}
+
+unsigned int
+xfs_get_atomic_write_min(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	/*
+	 * If we can complete an atomic write via atomic out of place writes,
+	 * then advertise a minimum size of one fsblock.  Without this
+	 * mechanism, we can only guarantee atomic writes up to a single LBA.
+	 *
+	 * If out of place writes are not available, we can guarantee an atomic
+	 * write of exactly one single fsblock if the bdev will make that
+	 * guarantee for us.
+	 */
+	if (xfs_inode_can_hw_atomic_write(ip) ||
+	    xfs_inode_can_sw_atomic_write(ip))
+		return mp->m_sb.sb_blocksize;
+
+	return 0;
+}
+
+unsigned int
+xfs_get_atomic_write_max(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+
+	/*
+	 * If out of place writes are not available, we can guarantee an atomic
+	 * write of exactly one single fsblock if the bdev will make that
+	 * guarantee for us.
+	 */
+	if (!xfs_inode_can_sw_atomic_write(ip)) {
+		if (xfs_inode_can_hw_atomic_write(ip))
+			return mp->m_sb.sb_blocksize;
+		return 0;
+	}
+
+	/*
+	 * If we can complete an atomic write via atomic out of place writes,
+	 * then advertise a maximum size of whatever we can complete through
+	 * that means.  Hardware support is reported via max_opt, not here.
+	 */
+	if (XFS_IS_REALTIME_INODE(ip))
+		return XFS_FSB_TO_B(mp, mp->m_groups[XG_TYPE_RTG].awu_max);
+	return XFS_FSB_TO_B(mp, mp->m_groups[XG_TYPE_AG].awu_max);
+}
+
+unsigned int
+xfs_get_atomic_write_max_opt(
+	struct xfs_inode	*ip)
+{
+	unsigned int		awu_max = xfs_get_atomic_write_max(ip);
+
+	/* if the max is 1x block, then just keep behaviour that opt is 0 */
+	if (awu_max <= ip->i_mount->m_sb.sb_blocksize)
+		return 0;
+
+	/*
+	 * Advertise the maximum size of an atomic write that we can tell the
+	 * block device to perform for us.  In general the bdev limit will be
+	 * less than our out of place write limit, but we don't want to exceed
+	 * the awu_max.
+	 */
+	return min(awu_max, xfs_inode_buftarg(ip)->bt_awu_max);
+}
+
+static void
+xfs_report_atomic_write(
+	struct xfs_inode	*ip,
+	struct kstat		*stat)
+{
+	generic_fill_statx_atomic_writes(stat,
+			xfs_get_atomic_write_min(ip),
+			xfs_get_atomic_write_max(ip),
+			xfs_get_atomic_write_max_opt(ip));
 }
 
 STATIC int
 xfs_vn_getattr(
-	struct user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
 	const struct path	*path,
 	struct kstat		*stat,
 	u32			request_mask,
@@ -558,6 +689,8 @@ 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(idmap, inode);
+	vfsgid_t		vfsgid = i_gid_into_vfsgid(idmap, inode);
 
 	trace_xfs_getattr(ip);
 
@@ -568,12 +701,13 @@ xfs_vn_getattr(
 	stat->dev = inode->i_sb->s_dev;
 	stat->mode = inode->i_mode;
 	stat->nlink = inode->i_nlink;
-	stat->uid = i_uid_into_mnt(mnt_userns, inode);
-	stat->gid = i_gid_into_mnt(mnt_userns, inode);
+	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->atime = inode_get_atime(inode);
+
+	fill_mg_cmtime(stat, request_mask, inode);
+
 	stat->blocks = XFS_FSB_TO_BB(mp, ip->i_nblocks + ip->i_delayed_blks);
 
 	if (xfs_has_v3inodes(mp)) {
@@ -604,6 +738,12 @@ xfs_vn_getattr(
 		stat->blksize = BLKDEV_IOSIZE;
 		stat->rdev = inode->i_rdev;
 		break;
+	case S_IFREG:
+		if (request_mask & (STATX_DIOALIGN | STATX_DIO_READ_ALIGN))
+			xfs_report_dioalign(ip, stat);
+		if (request_mask & STATX_WRITE_ATOMIC)
+			xfs_report_atomic_write(ip, stat);
+		fallthrough;
 	default:
 		stat->blksize = xfs_stat_blksize(ip);
 		stat->rdev = 0;
@@ -613,40 +753,9 @@ 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 user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
 	struct dentry		*dentry,
 	struct iattr		*iattr)
 {
@@ -658,7 +767,7 @@ xfs_vn_change_ok(
 	if (xfs_is_shutdown(mp))
 		return -EIO;
 
-	return setattr_prepare(mnt_userns, dentry, iattr);
+	return setattr_prepare(idmap, dentry, iattr);
 }
 
 /*
@@ -669,7 +778,8 @@ xfs_vn_change_ok(
  */
 static int
 xfs_setattr_nonsize(
-	struct user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
+	struct dentry		*dentry,
 	struct xfs_inode	*ip,
 	struct iattr		*iattr)
 {
@@ -678,10 +788,10 @@ xfs_setattr_nonsize(
 	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);
 
@@ -697,13 +807,15 @@ xfs_setattr_nonsize(
 		uint	qflags = 0;
 
 		if ((mask & ATTR_UID) && XFS_IS_UQUOTA_ON(mp)) {
-			uid = iattr->ia_uid;
+			uid = from_vfsuid(idmap, 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(idmap, i_user_ns(inode),
+					  iattr->ia_vfsgid);
 			qflags |= XFS_QMOPT_GQUOTA;
 		}  else {
 			gid = inode->i_gid;
@@ -723,66 +835,30 @@ xfs_setattr_nonsize(
 	}
 
 	error = xfs_trans_alloc_ichange(ip, udqp, gdqp, NULL,
-			capable(CAP_FOWNER), &tp);
+			has_capability_noaudit(current, CAP_FOWNER), &tp);
 	if (error)
 		goto out_dqrele;
 
 	/*
-	 * 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;
-
-		/*
-		 * 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_UQUOTA_ON(mp)) {
-				ASSERT(mask & ATTR_UID);
-				ASSERT(udqp);
-				olddquot1 = xfs_qm_vop_chown(tp, ip,
-							&ip->i_udquot, udqp);
-			}
-			inode->i_uid = uid;
-		}
-		if (!gid_eq(igid, gid)) {
-			if (XFS_IS_GQUOTA_ON(mp)) {
-				ASSERT(xfs_has_pquotino(mp) ||
-				       !XFS_IS_PQUOTA_ON(mp));
-				ASSERT(mask & ATTR_GID);
-				ASSERT(gdqp);
-				olddquot2 = xfs_qm_vop_chown(tp, ip,
-							&ip->i_gdquot, gdqp);
-			}
-			inode->i_gid = gid;
-		}
+	if (XFS_IS_UQUOTA_ON(mp) &&
+	    i_uid_needs_update(idmap, iattr, inode)) {
+		ASSERT(udqp);
+		old_udqp = xfs_qm_vop_chown(tp, ip, &ip->i_udquot, udqp);
+	}
+	if (XFS_IS_GQUOTA_ON(mp) &&
+	    i_gid_needs_update(idmap, 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(idmap, inode, iattr);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	XFS_STATS_INC(mp, xs_ig_attrchg);
@@ -794,8 +870,8 @@ xfs_setattr_nonsize(
 	/*
 	 * 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);
 
@@ -810,7 +886,7 @@ xfs_setattr_nonsize(
 	 * 	     Posix ACL code seems to care about this issue either.
 	 */
 	if (mask & ATTR_MODE) {
-		error = posix_acl_chmod(mnt_userns, inode, inode->i_mode);
+		error = posix_acl_chmod(idmap, dentry, inode->i_mode);
 		if (error)
 			return error;
 	}
@@ -831,7 +907,8 @@ out_dqrele:
  */
 STATIC int
 xfs_setattr_size(
-	struct user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
+	struct dentry		*dentry,
 	struct xfs_inode	*ip,
 	struct iattr		*iattr)
 {
@@ -841,10 +918,11 @@ xfs_setattr_size(
 	struct xfs_trans	*tp;
 	int			error;
 	uint			lock_flags = 0;
+	uint			resblks = 0;
 	bool			did_zeroing = false;
+	struct xfs_zone_alloc_ctx ac = { };
 
-	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
-	ASSERT(xfs_isilocked(ip, XFS_MMAPLOCK_EXCL));
+	xfs_assert_ilocked(ip, XFS_IOLOCK_EXCL | 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_TIMES_SET)) == 0);
@@ -863,7 +941,7 @@ xfs_setattr_size(
 		 * Use the regular setattr path to update the timestamps.
 		 */
 		iattr->ia_valid &= ~ATTR_SIZE;
-		return xfs_setattr_nonsize(mnt_userns, ip, iattr);
+		return xfs_setattr_nonsize(idmap, dentry, ip, iattr);
 	}
 
 	/*
@@ -879,6 +957,28 @@ xfs_setattr_size(
 	inode_dio_wait(inode);
 
 	/*
+	 * Normally xfs_zoned_space_reserve is supposed to be called outside the
+	 * IOLOCK.  For truncate we can't do that since ->setattr is called with
+	 * it already held by the VFS.  So for now chicken out and try to
+	 * allocate space under it.
+	 *
+	 * To avoid deadlocks this means we can't block waiting for space, which
+	 * can lead to spurious -ENOSPC if there are no directly available
+	 * blocks.  We mitigate this a bit by allowing zeroing to dip into the
+	 * reserved pool, but eventually the VFS calling convention needs to
+	 * change.
+	 */
+	if (xfs_is_zoned_inode(ip)) {
+		error = xfs_zoned_space_reserve(mp, 1,
+				XFS_ZR_NOWAIT | XFS_ZR_RESERVED, &ac);
+		if (error) {
+			if (error == -EAGAIN)
+				return -ENOSPC;
+			return error;
+		}
+	}
+
+	/*
 	 * File data changes must be complete before we start the transaction to
 	 * modify the inode.  This needs to be done before joining the inode to
 	 * the transaction because the inode cannot be unlocked once it is a
@@ -891,21 +991,14 @@ xfs_setattr_size(
 	if (newsize > oldsize) {
 		trace_xfs_zero_eof(ip, oldsize, newsize - oldsize);
 		error = xfs_zero_range(ip, oldsize, newsize - oldsize,
-				&did_zeroing);
+				&ac, &did_zeroing);
 	} else {
-		/*
-		 * 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);
+		error = xfs_truncate_page(ip, newsize, &ac, &did_zeroing);
 	}
 
+	if (xfs_is_zoned_inode(ip))
+		xfs_zoned_space_unreserve(mp, &ac);
+
 	if (error)
 		return error;
 
@@ -948,7 +1041,17 @@ xfs_setattr_size(
 			return error;
 	}
 
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
+	/*
+	 * For realtime inode with more than one block rtextsize, we need the
+	 * block reservation for bmap btree block allocations/splits that can
+	 * happen since it could split the tail written extent and convert the
+	 * right beyond EOF one to unwritten.
+	 */
+	if (xfs_inode_has_bigrtalloc(ip))
+		resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
+
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, resblks,
+				0, 0, &tp);
 	if (error)
 		return error;
 
@@ -1006,11 +1109,8 @@ 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(idmap, inode, iattr);
 	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
 
 	XFS_STATS_INC(mp, xs_ig_attrchg);
@@ -1031,7 +1131,7 @@ out_trans_cancel:
 
 int
 xfs_vn_setattr_size(
-	struct user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
 	struct dentry		*dentry,
 	struct iattr		*iattr)
 {
@@ -1040,15 +1140,15 @@ xfs_vn_setattr_size(
 
 	trace_xfs_setattr(ip);
 
-	error = xfs_vn_change_ok(mnt_userns, dentry, iattr);
+	error = xfs_vn_change_ok(idmap, dentry, iattr);
 	if (error)
 		return error;
-	return xfs_setattr_size(mnt_userns, ip, iattr);
+	return xfs_setattr_size(idmap, dentry, ip, iattr);
 }
 
 STATIC int
 xfs_vn_setattr(
-	struct user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
 	struct dentry		*dentry,
 	struct iattr		*iattr)
 {
@@ -1068,14 +1168,14 @@ xfs_vn_setattr(
 			return error;
 		}
 
-		error = xfs_vn_setattr_size(mnt_userns, dentry, iattr);
+		error = xfs_vn_setattr_size(idmap, dentry, iattr);
 		xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
 	} else {
 		trace_xfs_setattr(ip);
 
-		error = xfs_vn_change_ok(mnt_userns, dentry, iattr);
+		error = xfs_vn_change_ok(idmap, dentry, iattr);
 		if (!error)
-			error = xfs_setattr_nonsize(mnt_userns, ip, iattr);
+			error = xfs_setattr_nonsize(idmap, dentry, ip, iattr);
 	}
 
 	return error;
@@ -1084,7 +1184,6 @@ xfs_vn_setattr(
 STATIC int
 xfs_vn_update_time(
 	struct inode		*inode,
-	struct timespec64	*now,
 	int			flags)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
@@ -1092,13 +1191,16 @@ xfs_vn_update_time(
 	int			log_flags = XFS_ILOG_TIMESTAMP;
 	struct xfs_trans	*tp;
 	int			error;
+	struct timespec64	now;
 
 	trace_xfs_update_time(ip);
 
 	if (inode->i_sb->s_flags & SB_LAZYTIME) {
 		if (!((flags & S_VERSION) &&
-		      inode_maybe_inc_iversion(inode, false)))
-			return generic_update_time(inode, now, flags);
+		      inode_maybe_inc_iversion(inode, false))) {
+			generic_update_time(inode, flags);
+			return 0;
+		}
 
 		/* Capture the iversion update that just occurred */
 		log_flags |= XFS_ILOG_CORE;
@@ -1109,12 +1211,15 @@ xfs_vn_update_time(
 		return error;
 
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
-	if (flags & S_CTIME)
-		inode->i_ctime = *now;
+	if (flags & (S_CTIME|S_MTIME))
+		now = inode_set_ctime_current(inode);
+	else
+		now = current_time(inode);
+
 	if (flags & S_MTIME)
-		inode->i_mtime = *now;
+		inode_set_mtime_to_ts(inode, now);
 	if (flags & S_ATIME)
-		inode->i_atime = *now;
+		inode_set_atime_to_ts(inode, now);
 
 	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
 	xfs_trans_log_inode(tp, ip, log_flags);
@@ -1146,16 +1251,18 @@ xfs_vn_fiemap(
 
 STATIC int
 xfs_vn_tmpfile(
-	struct user_namespace	*mnt_userns,
+	struct mnt_idmap	*idmap,
 	struct inode		*dir,
-	struct dentry		*dentry,
+	struct file		*file,
 	umode_t			mode)
 {
-	return xfs_generic_create(mnt_userns, dir, dentry, mode, 0, true);
+	int err = xfs_generic_create(idmap, dir, file->f_path.dentry, mode, 0, file);
+
+	return finish_open_simple(file, err);
 }
 
 static const struct inode_operations xfs_inode_operations = {
-	.get_acl		= xfs_get_acl,
+	.get_inode_acl		= xfs_get_acl,
 	.set_acl		= xfs_set_acl,
 	.getattr		= xfs_vn_getattr,
 	.setattr		= xfs_vn_setattr,
@@ -1182,7 +1289,7 @@ static const struct inode_operations xfs_dir_inode_operations = {
 	.rmdir			= xfs_vn_unlink,
 	.mknod			= xfs_vn_mknod,
 	.rename			= xfs_vn_rename,
-	.get_acl		= xfs_get_acl,
+	.get_inode_acl		= xfs_get_acl,
 	.set_acl		= xfs_set_acl,
 	.getattr		= xfs_vn_getattr,
 	.setattr		= xfs_vn_setattr,
@@ -1209,7 +1316,7 @@ static const struct inode_operations xfs_dir_ci_inode_operations = {
 	.rmdir			= xfs_vn_unlink,
 	.mknod			= xfs_vn_mknod,
 	.rename			= xfs_vn_rename,
-	.get_acl		= xfs_get_acl,
+	.get_inode_acl		= xfs_get_acl,
 	.set_acl		= xfs_set_acl,
 	.getattr		= xfs_vn_getattr,
 	.setattr		= xfs_vn_setattr,
@@ -1226,6 +1333,8 @@ static const struct inode_operations xfs_symlink_inode_operations = {
 	.setattr		= xfs_vn_setattr,
 	.listxattr		= xfs_vn_listxattr,
 	.update_time		= xfs_vn_update_time,
+	.fileattr_get		= xfs_fileattr_get,
+	.fileattr_set		= xfs_fileattr_set,
 };
 
 /* Figure out if this file actually supports DAX. */
@@ -1239,10 +1348,6 @@ xfs_inode_supports_dax(
 	if (!S_ISREG(VFS_I(ip)->i_mode))
 		return false;
 
-	/* Only supported on non-reflinked files. */
-	if (xfs_is_reflink_inode(ip))
-		return false;
-
 	/* Block size must match page size */
 	if (mp->m_sb.sb_blocksize != PAGE_SIZE)
 		return false;
@@ -1312,9 +1417,10 @@ xfs_setup_inode(
 {
 	struct inode		*inode = &ip->i_vnode;
 	gfp_t			gfp_mask;
+	bool			is_meta = xfs_is_internal_inode(ip);
 
 	inode->i_ino = ip->i_ino;
-	inode->i_state |= I_NEW;
+	inode_state_set_raw(inode, I_NEW);
 
 	inode_sb_list_add(inode);
 	/* make the inode look hashed for the writeback code */
@@ -1323,6 +1429,16 @@ xfs_setup_inode(
 	i_size_write(inode, ip->i_disk_size);
 	xfs_diflags_to_iflags(ip, true);
 
+	/*
+	 * Mark our metadata files as private so that LSMs and the ACL code
+	 * don't try to add their own metadata or reason about these files,
+	 * and users cannot ever obtain file handles to them.
+	 */
+	if (is_meta) {
+		inode->i_flags |= S_PRIVATE;
+		inode->i_opflags &= ~IOP_XATTR;
+	}
+
 	if (S_ISDIR(inode->i_mode)) {
 		/*
 		 * We set the i_rwsem class here to avoid potential races with
@@ -1332,9 +1448,9 @@ 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);
+		lockdep_set_class(&ip->i_lock, &xfs_dir_ilock_class);
 	} else {
-		lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
+		lockdep_set_class(&ip->i_lock, &xfs_nondir_ilock_class);
 	}
 
 	/*
@@ -1346,10 +1462,17 @@ xfs_setup_inode(
 	mapping_set_gfp_mask(inode->i_mapping, (gfp_mask & ~(__GFP_FS)));
 
 	/*
+	 * For real-time inodes update the stable write flags to that of the RT
+	 * device instead of the data device.
+	 */
+	if (S_ISREG(inode->i_mode) && XFS_IS_REALTIME_INODE(ip))
+		xfs_update_stable_writes(ip);
+
+	/*
 	 * 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);
 	}