From: Darrick J. Wong <djwong@kernel.org>
Date: Tue, 15 Oct 2024 19:39:51 +0000 (-0700)
Subject: xfs: add realtime reverse map inode to metadata directory
X-Git-Url: https://www.infradead.org/git/?a=commitdiff_plain;h=1660db76b4e43aa863a5352c97f5e028d01b47d4;p=users%2Fhch%2Fxfs.git

xfs: add realtime reverse map inode to metadata directory

Add a metadir path to select the realtime rmap btree inode and load
it at mount time.  The rtrmapbt inode will have a unique extent format
code, which means that we also have to update the inode validation and
flush routines to look for it.

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

diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 469fc7afa591..e2597843de8e 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -857,6 +857,7 @@ enum xfs_metafile_type {
 	XFS_METAFILE_PRJQUOTA,		/* project quota */
 	XFS_METAFILE_RTBITMAP,		/* rt bitmap */
 	XFS_METAFILE_RTSUMMARY,		/* rt summary */
+	XFS_METAFILE_RTRMAP,		/* rt rmap */
 
 	XFS_METAFILE_MAX
 } __packed;
@@ -868,7 +869,8 @@ enum xfs_metafile_type {
 	{ XFS_METAFILE_GRPQUOTA,	"grpquota" }, \
 	{ XFS_METAFILE_PRJQUOTA,	"prjquota" }, \
 	{ XFS_METAFILE_RTBITMAP,	"rtbitmap" }, \
-	{ XFS_METAFILE_RTSUMMARY,	"rtsummary" }
+	{ XFS_METAFILE_RTSUMMARY,	"rtsummary" }, \
+	{ XFS_METAFILE_RTRMAP,		"rtrmap" }
 
 /*
  * On-disk inode structure.
@@ -997,7 +999,8 @@ enum xfs_dinode_fmt {
 	XFS_DINODE_FMT_LOCAL,		/* bulk data */
 	XFS_DINODE_FMT_EXTENTS,		/* struct xfs_bmbt_rec */
 	XFS_DINODE_FMT_BTREE,		/* struct xfs_bmdr_block */
-	XFS_DINODE_FMT_UUID		/* added long ago, but never used */
+	XFS_DINODE_FMT_UUID,		/* added long ago, but never used */
+	XFS_DINODE_FMT_RMAP,		/* reverse mapping btree */
 };
 
 #define XFS_INODE_FORMAT_STR \
@@ -1005,7 +1008,8 @@ enum xfs_dinode_fmt {
 	{ XFS_DINODE_FMT_LOCAL,		"local" }, \
 	{ XFS_DINODE_FMT_EXTENTS,	"extent" }, \
 	{ XFS_DINODE_FMT_BTREE,		"btree" }, \
-	{ XFS_DINODE_FMT_UUID,		"uuid" }
+	{ XFS_DINODE_FMT_UUID,		"uuid" }, \
+	{ XFS_DINODE_FMT_RMAP,		"rmap" }
 
 /*
  * Max values for extnum and aextnum.
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index 424861fbf1bd..a3993e4d8aed 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -441,6 +441,17 @@ xfs_dinode_verify_fork(
 		if (di_nextents > max_extents)
 			return __this_address;
 		break;
+	case XFS_DINODE_FMT_RMAP:
+		/*
+		 * growfs must create the rtrmap inodes before adding a
+		 * realtime volume to the filesystem, so we cannot use the
+		 * rtrmapbt predicate here.
+		 */
+		if (!xfs_has_rmapbt(mp))
+			return __this_address;
+		if (!(dip->di_flags2 & cpu_to_be64(XFS_DIFLAG2_METADATA)))
+			return __this_address;
+		break;
 	default:
 		return __this_address;
 	}
@@ -460,6 +471,10 @@ xfs_dinode_verify_forkoff(
 		if (dip->di_forkoff != (roundup(sizeof(xfs_dev_t), 8) >> 3))
 			return __this_address;
 		break;
+	case XFS_DINODE_FMT_RMAP:
+		if (!(xfs_has_metadir(mp) && xfs_has_parent(mp)))
+			return __this_address;
+		fallthrough;
 	case XFS_DINODE_FMT_LOCAL:	/* fall through ... */
 	case XFS_DINODE_FMT_EXTENTS:    /* fall through ... */
 	case XFS_DINODE_FMT_BTREE:
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index db1ce93d9899..40dce4bffd1d 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -268,6 +268,16 @@ xfs_iformat_data_fork(
 			return xfs_iformat_extents(ip, dip, XFS_DATA_FORK);
 		case XFS_DINODE_FMT_BTREE:
 			return xfs_iformat_btree(ip, dip, XFS_DATA_FORK);
+		case XFS_DINODE_FMT_RMAP:
+			/*
+			 * growfs must create the rtrmap inodes before adding a
+			 * realtime volume to the filesystem, so we cannot use
+			 * the rtrmapbt predicate here.
+			 */
+			if (!xfs_has_rmapbt(ip->i_mount))
+				return -EFSCORRUPTED;
+			ASSERT(0); /* to be implemented later */
+			return -EFSCORRUPTED;
 		default:
 			xfs_inode_verifier_error(ip, -EFSCORRUPTED, __func__,
 					dip, sizeof(*dip), __this_address);
@@ -587,6 +597,10 @@ xfs_iflush_fork(
 		}
 		break;
 
+	case XFS_DINODE_FMT_RMAP:
+		ASSERT(0); /* to be implemented later */
+		break;
+
 	default:
 		ASSERT(0);
 		break;
diff --git a/fs/xfs/libxfs/xfs_rtgroup.c b/fs/xfs/libxfs/xfs_rtgroup.c
index e74bb059f24f..065c92e50d7a 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.c
+++ b/fs/xfs/libxfs/xfs_rtgroup.c
@@ -284,7 +284,14 @@ xfs_rtginode_ilock_print_fn(
 	const struct xfs_inode *ip =
 		container_of(m, struct xfs_inode, i_lock.dep_map);
 
-	printk(KERN_CONT " rgno=%u", ip->i_projid);
+	switch (ip->i_df.if_format) {
+	case XFS_DINODE_FMT_RMAP:
+		printk(KERN_CONT " rgno=%u rmapbt", ip->i_projid);
+		break;
+	default:
+		printk(KERN_CONT " rgno=%u", ip->i_projid);
+		break;
+	}
 }
 
 /*
@@ -316,6 +323,8 @@ struct xfs_rtginode_ops {
 
 	unsigned int		sick;	/* rtgroup sickness flag */
 
+	unsigned int		fmt_mask; /* all valid data fork formats */
+
 	/* Does the fs have this feature? */
 	bool			(*enabled)(struct xfs_mount *mp);
 
@@ -331,14 +340,29 @@ static const struct xfs_rtginode_ops xfs_rtginode_ops[XFS_RTGI_MAX] = {
 		.name		= "bitmap",
 		.metafile_type	= XFS_METAFILE_RTBITMAP,
 		.sick		= XFS_SICK_RG_BITMAP,
+		.fmt_mask	= (1U << XFS_DINODE_FMT_EXTENTS) |
+				  (1U << XFS_DINODE_FMT_BTREE),
 		.create		= xfs_rtbitmap_create,
 	},
 	[XFS_RTGI_SUMMARY] = {
 		.name		= "summary",
 		.metafile_type	= XFS_METAFILE_RTSUMMARY,
 		.sick		= XFS_SICK_RG_SUMMARY,
+		.fmt_mask	= (1U << XFS_DINODE_FMT_EXTENTS) |
+				  (1U << XFS_DINODE_FMT_BTREE),
 		.create		= xfs_rtsummary_create,
 	},
+	[XFS_RTGI_RMAP] = {
+		.name		= "rmap",
+		.metafile_type	= XFS_METAFILE_RTRMAP,
+		.fmt_mask	= 1U << XFS_DINODE_FMT_RMAP,
+		/*
+		 * growfs must create the rtrmap inodes before adding a
+		 * realtime volume to the filesystem, so we cannot use the
+		 * rtrmapbt predicate here.
+		 */
+		.enabled	= xfs_has_rmapbt,
+	},
 };
 
 /* Return the shortname of this rtgroup inode. */
@@ -435,8 +459,7 @@ xfs_rtginode_load(
 		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)) {
+	if (XFS_IS_CORRUPT(mp, !((1U << ip->i_df.if_format) & ops->fmt_mask))) {
 		xfs_irele(ip);
 		xfs_rtginode_mark_sick(rtg, type);
 		return -EFSCORRUPTED;
diff --git a/fs/xfs/libxfs/xfs_rtgroup.h b/fs/xfs/libxfs/xfs_rtgroup.h
index 6d65bc1f0b6c..9589bb45aa42 100644
--- a/fs/xfs/libxfs/xfs_rtgroup.h
+++ b/fs/xfs/libxfs/xfs_rtgroup.h
@@ -14,6 +14,7 @@ struct xfs_trans;
 enum xfs_rtg_inodes {
 	XFS_RTGI_BITMAP,	/* allocation bitmap */
 	XFS_RTGI_SUMMARY,	/* allocation summary */
+	XFS_RTGI_RMAP,		/* rmap btree inode */
 
 	XFS_RTGI_MAX,
 };
@@ -274,6 +275,8 @@ int xfs_rtginode_create(struct xfs_rtgroup *rtg, enum xfs_rtg_inodes type,
 		bool init);
 void xfs_rtginode_irele(struct xfs_inode **ipp);
 
+void xfs_rtginode_irele(struct xfs_inode **ipp);
+
 static inline const char *xfs_rtginode_path(xfs_rgnumber_t rgno,
 		enum xfs_rtg_inodes type)
 {
diff --git a/fs/xfs/libxfs/xfs_rtrmap_btree.c b/fs/xfs/libxfs/xfs_rtrmap_btree.c
index 99d828bb5fe7..b40fac9e3860 100644
--- a/fs/xfs/libxfs/xfs_rtrmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rtrmap_btree.c
@@ -18,6 +18,7 @@
 #include "xfs_alloc.h"
 #include "xfs_btree.h"
 #include "xfs_btree_staging.h"
+#include "xfs_metafile.h"
 #include "xfs_rmap.h"
 #include "xfs_rtrmap_btree.h"
 #include "xfs_trace.h"
@@ -405,12 +406,10 @@ xfs_rtrmapbt_init_cursor(
 	struct xfs_trans	*tp,
 	struct xfs_rtgroup	*rtg)
 {
-	struct xfs_inode	*ip = NULL;
+	struct xfs_inode	*ip = rtg->rtg_inodes[XFS_RTGI_RMAP];
 	struct xfs_mount	*mp = rtg_mount(rtg);
 	struct xfs_btree_cur	*cur;
 
-	return NULL; /* XXX */
-
 	xfs_assert_ilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL);
 
 	cur = xfs_btree_alloc_cursor(mp, tp, &xfs_rtrmapbt_ops,
@@ -439,6 +438,7 @@ xfs_rtrmapbt_commit_staged_btree(
 	int			flags = XFS_ILOG_CORE | XFS_ILOG_DBROOT;
 
 	ASSERT(cur->bc_flags & XFS_BTREE_STAGING);
+	ASSERT(ifake->if_fork->if_format == XFS_DINODE_FMT_RMAP);
 
 	/*
 	 * Free any resources hanging off the real fork, then shallow-copy the
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index c8ad2606f928..85db8db11b48 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -2382,7 +2382,15 @@ xfs_iflush(
 			__func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
 		goto flush_out;
 	}
-	if (S_ISREG(VFS_I(ip)->i_mode)) {
+	if (ip->i_df.if_format == XFS_DINODE_FMT_RMAP) {
+		if (!S_ISREG(VFS_I(ip)->i_mode) ||
+		    !(ip->i_diflags2 & XFS_DIFLAG2_METADATA)) {
+			xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
+				"%s: Bad rt rmapbt inode %Lu, ptr "PTR_FMT,
+				__func__, ip->i_ino, ip);
+			goto flush_out;
+		}
+	} else if (S_ISREG(VFS_I(ip)->i_mode)) {
 		if (XFS_TEST_ERROR(
 		    ip->i_df.if_format != XFS_DINODE_FMT_EXTENTS &&
 		    ip->i_df.if_format != XFS_DINODE_FMT_BTREE,
@@ -2422,6 +2430,15 @@ xfs_iflush(
 		goto flush_out;
 	}
 
+	if (xfs_inode_has_attr_fork(ip)) {
+		if (ip->i_af.if_format == XFS_DINODE_FMT_RMAP) {
+			xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
+				"%s: rt rmapbt in inode %Lu attr fork, ptr "PTR_FMT,
+				__func__, ip->i_ino, ip);
+			goto flush_out;
+		}
+	}
+
 	/*
 	 * Inode item log recovery for v2 inodes are dependent on the flushiter
 	 * count for correct sequencing.  We bump the flush iteration count so
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 912f0b1bc3cb..df7c834bc15f 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -242,6 +242,7 @@ xfs_inode_item_data_fork_size(
 		}
 		break;
 	case XFS_DINODE_FMT_BTREE:
+	case XFS_DINODE_FMT_RMAP:
 		if ((iip->ili_fields & XFS_ILOG_DBROOT) &&
 		    ip->i_df.if_broot_bytes > 0) {
 			*nbytes += ip->i_df.if_broot_bytes;
@@ -362,6 +363,7 @@ xfs_inode_item_format_data_fork(
 		}
 		break;
 	case XFS_DINODE_FMT_BTREE:
+	case XFS_DINODE_FMT_RMAP:
 		iip->ili_fields &=
 			~(XFS_ILOG_DDATA | XFS_ILOG_DEXT | XFS_ILOG_DEV);
 
diff --git a/fs/xfs/xfs_inode_item_recover.c b/fs/xfs/xfs_inode_item_recover.c
index e70d2611456b..07db6b6dd0b9 100644
--- a/fs/xfs/xfs_inode_item_recover.c
+++ b/fs/xfs/xfs_inode_item_recover.c
@@ -394,6 +394,7 @@ xlog_recover_inode_commit_pass2(
 
 	if (unlikely(S_ISREG(ldip->di_mode))) {
 		if ((ldip->di_format != XFS_DINODE_FMT_EXTENTS) &&
+		    (ldip->di_format != XFS_DINODE_FMT_RMAP) &&
 		    (ldip->di_format != XFS_DINODE_FMT_BTREE)) {
 			XFS_CORRUPTION_ERROR(
 				"Bad log dinode data fork format for regular file",
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 2c88e24cb76c..d35587fd71c8 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -2295,6 +2295,7 @@ TRACE_DEFINE_ENUM(XFS_DINODE_FMT_LOCAL);
 TRACE_DEFINE_ENUM(XFS_DINODE_FMT_EXTENTS);
 TRACE_DEFINE_ENUM(XFS_DINODE_FMT_BTREE);
 TRACE_DEFINE_ENUM(XFS_DINODE_FMT_UUID);
+TRACE_DEFINE_ENUM(XFS_DINODE_FMT_RMAP);
 
 DECLARE_EVENT_CLASS(xfs_swap_extent_class,
 	TP_PROTO(struct xfs_inode *ip, int which),