Merge tag 'metadir-quotas-6.13_2024-11-05' of https://git.kernel.org/pub/scm/linux/kernel/git/djwong/xfs-linux into staging-merge

xfs: persist quota options with metadir [v5.5 07/10]

Store the quota files in the metadata directory tree instead of the
superblock.  Since we're introducing a new incompat feature flag, let's
also make the mount process bring up quotas in whatever state they were
when the filesystem was last unmounted, instead of requiring sysadmins
to remember that themselves.

With a bit of luck, this should all go splendidly.

Signed-off-by: Darrick J. Wong <djwong@kernel.org>

Author: cmaiolino

fs/xfs/libxfs/xfs_dquot_buf.c

@@ -16,6 +16,9 @@
 #include "xfs_trans.h"
 #include "xfs_qm.h"
 #include "xfs_error.h"
+#include "xfs_health.h"
+#include "xfs_metadir.h"
+#include "xfs_metafile.h"
 
 int
 xfs_calc_dquots_per_chunk(
@@ -323,3 +326,190 @@ xfs_dquot_to_disk_ts(
 
 	return cpu_to_be32(t);
 }
+
+inline unsigned int
+xfs_dqinode_sick_mask(xfs_dqtype_t type)
+{
+	switch (type) {
+	case XFS_DQTYPE_USER:
+		return XFS_SICK_FS_UQUOTA;
+	case XFS_DQTYPE_GROUP:
+		return XFS_SICK_FS_GQUOTA;
+	case XFS_DQTYPE_PROJ:
+		return XFS_SICK_FS_PQUOTA;
+	}
+
+	ASSERT(0);
+	return 0;
+}
+
+/*
+ * Load the inode for a given type of quota, assuming that the sb fields have
+ * been sorted out.  This is not true when switching quota types on a V4
+ * filesystem, so do not use this function for that.  If metadir is enabled,
+ * @dp must be the /quota metadir.
+ *
+ * Returns -ENOENT if the quota inode field is NULLFSINO; 0 and an inode on
+ * success; or a negative errno.
+ */
+int
+xfs_dqinode_load(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*dp,
+	xfs_dqtype_t		type,
+	struct xfs_inode	**ipp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_inode	*ip;
+	enum xfs_metafile_type	metafile_type = xfs_dqinode_metafile_type(type);
+	int			error;
+
+	if (!xfs_has_metadir(mp)) {
+		xfs_ino_t	ino;
+
+		switch (type) {
+		case XFS_DQTYPE_USER:
+			ino = mp->m_sb.sb_uquotino;
+			break;
+		case XFS_DQTYPE_GROUP:
+			ino = mp->m_sb.sb_gquotino;
+			break;
+		case XFS_DQTYPE_PROJ:
+			ino = mp->m_sb.sb_pquotino;
+			break;
+		default:
+			ASSERT(0);
+			return -EFSCORRUPTED;
+		}
+
+		/* Should have set 0 to NULLFSINO when loading superblock */
+		if (ino == NULLFSINO)
+			return -ENOENT;
+
+		error = xfs_trans_metafile_iget(tp, ino, metafile_type, &ip);
+	} else {
+		error = xfs_metadir_load(tp, dp, xfs_dqinode_path(type),
+				metafile_type, &ip);
+		if (error == -ENOENT)
+			return error;
+	}
+	if (error) {
+		if (xfs_metadata_is_sick(error))
+			xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type));
+		return error;
+	}
+
+	if (XFS_IS_CORRUPT(mp, ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
+			       ip->i_df.if_format != XFS_DINODE_FMT_BTREE)) {
+		xfs_irele(ip);
+		xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type));
+		return -EFSCORRUPTED;
+	}
+
+	if (XFS_IS_CORRUPT(mp, ip->i_projid != 0)) {
+		xfs_irele(ip);
+		xfs_fs_mark_sick(mp, xfs_dqinode_sick_mask(type));
+		return -EFSCORRUPTED;
+	}
+
+	*ipp = ip;
+	return 0;
+}
+
+/* Create a metadata directory quota inode. */
+int
+xfs_dqinode_metadir_create(
+	struct xfs_inode		*dp,
+	xfs_dqtype_t			type,
+	struct xfs_inode		**ipp)
+{
+	struct xfs_metadir_update	upd = {
+		.dp			= dp,
+		.metafile_type		= xfs_dqinode_metafile_type(type),
+		.path			= xfs_dqinode_path(type),
+	};
+	int				error;
+
+	error = xfs_metadir_start_create(&upd);
+	if (error)
+		return error;
+
+	error = xfs_metadir_create(&upd, S_IFREG);
+	if (error)
+		return error;
+
+	xfs_trans_log_inode(upd.tp, upd.ip, XFS_ILOG_CORE);
+
+	error = xfs_metadir_commit(&upd);
+	if (error)
+		return error;
+
+	xfs_finish_inode_setup(upd.ip);
+	*ipp = upd.ip;
+	return 0;
+}
+
+#ifndef __KERNEL__
+/* Link a metadata directory quota inode. */
+int
+xfs_dqinode_metadir_link(
+	struct xfs_inode		*dp,
+	xfs_dqtype_t			type,
+	struct xfs_inode		*ip)
+{
+	struct xfs_metadir_update	upd = {
+		.dp			= dp,
+		.metafile_type		= xfs_dqinode_metafile_type(type),
+		.path			= xfs_dqinode_path(type),
+		.ip			= ip,
+	};
+	int				error;
+
+	error = xfs_metadir_start_link(&upd);
+	if (error)
+		return error;
+
+	error = xfs_metadir_link(&upd);
+	if (error)
+		return error;
+
+	xfs_trans_log_inode(upd.tp, upd.ip, XFS_ILOG_CORE);
+
+	return xfs_metadir_commit(&upd);
+}
+#endif /* __KERNEL__ */
+
+/* Create the parent directory for all quota inodes and load it. */
+int
+xfs_dqinode_mkdir_parent(
+	struct xfs_mount	*mp,
+	struct xfs_inode	**dpp)
+{
+	if (!mp->m_metadirip) {
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
+		return -EFSCORRUPTED;
+	}
+
+	return xfs_metadir_mkdir(mp->m_metadirip, "quota", dpp);
+}
+
+/*
+ * Load the parent directory of all quota inodes.  Pass the inode to the caller
+ * because quota functions (e.g. QUOTARM) can be called on the quota files even
+ * if quotas are not enabled.
+ */
+int
+xfs_dqinode_load_parent(
+	struct xfs_trans	*tp,
+	struct xfs_inode	**dpp)
+{
+	struct xfs_mount	*mp = tp->t_mountp;
+
+	if (!mp->m_metadirip) {
+		xfs_fs_mark_sick(mp, XFS_SICK_FS_METADIR);
+		return -EFSCORRUPTED;
+	}
+
+	return xfs_metadir_load(tp, mp->m_metadirip, "quota", XFS_METAFILE_DIR,
+			dpp);
+}

fs/xfs/libxfs/xfs_fs.h

@@ -825,9 +825,13 @@ struct xfs_scrub_vec_head {
 #define XFS_SCRUB_METAPATH_RTDIR	(1)  /* rtrgroups metadir */
 #define XFS_SCRUB_METAPATH_RTBITMAP	(2)  /* per-rtg bitmap */
 #define XFS_SCRUB_METAPATH_RTSUMMARY	(3)  /* per-rtg summary */
+#define XFS_SCRUB_METAPATH_QUOTADIR	(4)  /* quota metadir */
+#define XFS_SCRUB_METAPATH_USRQUOTA	(5)  /* user quota */
+#define XFS_SCRUB_METAPATH_GRPQUOTA	(6)  /* group quota */
+#define XFS_SCRUB_METAPATH_PRJQUOTA	(7)  /* project quota */
 
 /* Number of metapath sm_ino values */
-#define XFS_SCRUB_METAPATH_NR		(4)
+#define XFS_SCRUB_METAPATH_NR		(8)
 
 /*
  * ioctl limits

fs/xfs/libxfs/xfs_quota_defs.h

@@ -143,4 +143,47 @@ time64_t xfs_dquot_from_disk_ts(struct xfs_disk_dquot *ddq,
 		__be32 dtimer);
 __be32 xfs_dquot_to_disk_ts(struct xfs_dquot *ddq, time64_t timer);
 
+static inline const char *
+xfs_dqinode_path(xfs_dqtype_t type)
+{
+	switch (type) {
+	case XFS_DQTYPE_USER:
+		return "user";
+	case XFS_DQTYPE_GROUP:
+		return "group";
+	case XFS_DQTYPE_PROJ:
+		return "project";
+	}
+
+	ASSERT(0);
+	return NULL;
+}
+
+static inline enum xfs_metafile_type
+xfs_dqinode_metafile_type(xfs_dqtype_t type)
+{
+	switch (type) {
+	case XFS_DQTYPE_USER:
+		return XFS_METAFILE_USRQUOTA;
+	case XFS_DQTYPE_GROUP:
+		return XFS_METAFILE_GRPQUOTA;
+	case XFS_DQTYPE_PROJ:
+		return XFS_METAFILE_PRJQUOTA;
+	}
+
+	ASSERT(0);
+	return XFS_METAFILE_UNKNOWN;
+}
+
+unsigned int xfs_dqinode_sick_mask(xfs_dqtype_t type);
+
+int xfs_dqinode_load(struct xfs_trans *tp, struct xfs_inode *dp,
+		xfs_dqtype_t type, struct xfs_inode **ipp);
+int xfs_dqinode_metadir_create(struct xfs_inode *dp, xfs_dqtype_t type,
+		struct xfs_inode **ipp);
+int xfs_dqinode_metadir_link(struct xfs_inode *dp, xfs_dqtype_t type,
+		struct xfs_inode *ip);
+int xfs_dqinode_mkdir_parent(struct xfs_mount *mp, struct xfs_inode **dpp);
+int xfs_dqinode_load_parent(struct xfs_trans *tp, struct xfs_inode **dpp);
+
 #endif	/* __XFS_QUOTA_H__ */

fs/xfs/libxfs/xfs_sb.c

@@ -858,6 +858,7 @@ xfs_sb_quota_to_disk(
 
 	if (xfs_sb_is_v5(from) &&
 	    (from->sb_features_incompat & XFS_SB_FEAT_INCOMPAT_METADIR)) {
+		to->sb_qflags = cpu_to_be16(from->sb_qflags);
 		to->sb_uquotino = cpu_to_be64(0);
 		to->sb_gquotino = cpu_to_be64(0);
 		to->sb_pquotino = cpu_to_be64(0);

fs/xfs/scrub/metapath.c

@@ -165,6 +165,74 @@ xchk_setup_metapath_rtginode(
 # define xchk_setup_metapath_rtginode(...)	(-ENOENT)
 #endif /* CONFIG_XFS_RT */
 
+#ifdef CONFIG_XFS_QUOTA
+/* Scan the /quota directory itself. */
+static int
+xchk_setup_metapath_quotadir(
+	struct xfs_scrub	*sc)
+{
+	struct xfs_trans	*tp;
+	struct xfs_inode	*dp = NULL;
+	int			error;
+
+	error = xfs_trans_alloc_empty(sc->mp, &tp);
+	if (error)
+		return error;
+
+	error = xfs_dqinode_load_parent(tp, &dp);
+	xfs_trans_cancel(tp);
+	if (error)
+		return error;
+
+	error = xchk_setup_metapath_scan(sc, sc->mp->m_metadirip,
+			kasprintf(GFP_KERNEL, "quota"), dp);
+	xfs_irele(dp);
+	return error;
+}
+
+/* Scan a quota inode under the /quota directory. */
+static int
+xchk_setup_metapath_dqinode(
+	struct xfs_scrub	*sc,
+	xfs_dqtype_t		type)
+{
+	struct xfs_trans	*tp = NULL;
+	struct xfs_inode	*dp = NULL;
+	struct xfs_inode	*ip = NULL;
+	const char		*path;
+	int			error;
+
+	error = xfs_trans_alloc_empty(sc->mp, &tp);
+	if (error)
+		return error;
+
+	error = xfs_dqinode_load_parent(tp, &dp);
+	if (error)
+		goto out_cancel;
+
+	error = xfs_dqinode_load(tp, dp, type, &ip);
+	if (error)
+		goto out_dp;
+
+	xfs_trans_cancel(tp);
+	tp = NULL;
+
+	path = kasprintf(GFP_KERNEL, "%s", xfs_dqinode_path(type));
+	error = xchk_setup_metapath_scan(sc, dp, path, ip);
+
+	xfs_irele(ip);
+out_dp:
+	xfs_irele(dp);
+out_cancel:
+	if (tp)
+		xfs_trans_cancel(tp);
+	return error;
+}
+#else
+# define xchk_setup_metapath_quotadir(...)	(-ENOENT)
+# define xchk_setup_metapath_dqinode(...)	(-ENOENT)
+#endif /* CONFIG_XFS_QUOTA */
+
 int
 xchk_setup_metapath(
 	struct xfs_scrub	*sc)
@@ -186,6 +254,14 @@ xchk_setup_metapath(
 		return xchk_setup_metapath_rtginode(sc, XFS_RTGI_BITMAP);
 	case XFS_SCRUB_METAPATH_RTSUMMARY:
 		return xchk_setup_metapath_rtginode(sc, XFS_RTGI_SUMMARY);
+	case XFS_SCRUB_METAPATH_QUOTADIR:
+		return xchk_setup_metapath_quotadir(sc);
+	case XFS_SCRUB_METAPATH_USRQUOTA:
+		return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_USER);
+	case XFS_SCRUB_METAPATH_GRPQUOTA:
+		return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_GROUP);
+	case XFS_SCRUB_METAPATH_PRJQUOTA:
+		return xchk_setup_metapath_dqinode(sc, XFS_DQTYPE_PROJ);
 	default:
 		return -ENOENT;
 	}

fs/xfs/xfs_mount.c

@@ -852,6 +852,13 @@ xfs_mountfs(
 	if (error)
 		goto out_fail_wait;
 
+	/*
+	 * If we're resuming quota status, pick up the preliminary qflags from
+	 * the ondisk superblock so that we know if we should recover dquots.
+	 */
+	if (xfs_is_resuming_quotaon(mp))
+		xfs_qm_resume_quotaon(mp);
+
 	/*
 	 * Log's mount-time initialization. The first part of recovery can place
 	 * some items on the AIL, to be handled when recovery is finished or
@@ -865,6 +872,14 @@ xfs_mountfs(
 		goto out_inodegc_shrinker;
 	}
 
+	/*
+	 * If we're resuming quota status and recovered the log, re-sample the
+	 * qflags from the ondisk superblock now that we've recovered it, just
+	 * in case someone shut down enforcement just before a crash.
+	 */
+	if (xfs_clear_resuming_quotaon(mp) && xlog_recovery_needed(mp->m_log))
+		xfs_qm_resume_quotaon(mp);
+
 	/*
 	 * If logged xattrs are still enabled after log recovery finishes, then
 	 * they'll be available until unmount.  Otherwise, turn them off.