1 files changed, 472 insertions, 1 deletions

diff --git a/fs/xfs/scrub/xfbtree.c b/fs/xfs/scrub/xfbtree.c
index 80f9ab4fec07..f1accdf3112e 100644
--- a/fs/xfs/scrub/xfbtree.c
+++ b/fs/xfs/scrub/xfbtree.c
@@ -9,14 +9,19 @@
 #include "xfs_format.h"
 #include "xfs_log_format.h"
 #include "xfs_trans_resv.h"
+#include "xfs_bit.h"
 #include "xfs_mount.h"
 #include "xfs_trans.h"
+#include "xfs_buf_item.h"
 #include "xfs_btree.h"
 #include "xfs_error.h"
 #include "xfs_btree_mem.h"
 #include "xfs_ag.h"
+#include "scrub/scrub.h"
 #include "scrub/xfile.h"
 #include "scrub/xfbtree.h"
+#include "scrub/bitmap.h"
+#include "scrub/trace.h"
 
 /* btree ops functions for in-memory btrees. */
 
@@ -142,9 +147,18 @@ xfbtree_check_ptr(
 	else
 		bt_xfoff = be32_to_cpu(ptr->s);
 
-	if (!xfbtree_verify_xfileoff(cur, bt_xfoff))
+	if (!xfbtree_verify_xfileoff(cur, bt_xfoff)) {
 		fa = __this_address;
+		goto done;
+	}
 
+	/* Can't point to the head or anything before it */
+	if (bt_xfoff < XFBTREE_INIT_LEAF_BLOCK) {
+		fa = __this_address;
+		goto done;
+	}
+
+done:
 	if (fa) {
 		xfs_err(cur->bc_mp,
 "In-memory: Corrupt btree %d flags 0x%x pointer at level %d index %d fa %pS.",
@@ -350,3 +364,460 @@ xfbtree_sblock_verify(
 
 	return NULL;
 }
+
+/* Close the btree xfile and release all resources. */
+void
+xfbtree_destroy(
+	struct xfbtree		*xfbt)
+{
+	xbitmap_destroy(xfbt->freespace);
+	kfree(xfbt->freespace);
+	xfs_buftarg_drain(xfbt->target);
+	kfree(xfbt);
+}
+
+/* Compute the number of bytes available for records. */
+static inline unsigned int
+xfbtree_rec_bytes(
+	struct xfs_mount		*mp,
+	const struct xfbtree_config	*cfg)
+{
+	unsigned int			blocklen = xfo_to_b(1);
+
+	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS) {
+		if (xfs_has_crc(mp))
+			return blocklen - XFS_BTREE_LBLOCK_CRC_LEN;
+
+		return blocklen - XFS_BTREE_LBLOCK_LEN;
+	}
+
+	if (xfs_has_crc(mp))
+		return blocklen - XFS_BTREE_SBLOCK_CRC_LEN;
+
+	return blocklen - XFS_BTREE_SBLOCK_LEN;
+}
+
+/* Initialize an empty leaf block as the btree root. */
+STATIC int
+xfbtree_init_leaf_block(
+	struct xfs_mount		*mp,
+	struct xfbtree			*xfbt,
+	const struct xfbtree_config	*cfg)
+{
+	struct xfs_buf			*bp;
+	xfs_daddr_t			daddr;
+	int				error;
+	unsigned int			bc_flags = 0;
+
+	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS)
+		bc_flags |= XFS_BTREE_LONG_PTRS;
+
+	daddr = xfo_to_daddr(XFBTREE_INIT_LEAF_BLOCK);
+	error = xfs_buf_get(xfbt->target, daddr, xfbtree_bbsize(), &bp);
+	if (error)
+		return error;
+
+	trace_xfbtree_create_root_buf(xfbt, bp);
+
+	bp->b_ops = cfg->btree_ops->buf_ops;
+	xfs_btree_init_block_int(mp, bp->b_addr, daddr, cfg->btnum, 0, 0,
+			cfg->owner, bc_flags);
+	error = xfs_bwrite(bp);
+	xfs_buf_relse(bp);
+	if (error)
+		return error;
+
+	xfbt->xf_used++;
+	return 0;
+}
+
+/* Initialize the in-memory btree header block. */
+STATIC int
+xfbtree_init_head(
+	struct xfbtree		*xfbt)
+{
+	struct xfs_buf		*bp;
+	xfs_daddr_t		daddr;
+	int			error;
+
+	daddr = xfo_to_daddr(XFBTREE_HEAD_BLOCK);
+	error = xfs_buf_get(xfbt->target, daddr, xfbtree_bbsize(), &bp);
+	if (error)
+		return error;
+
+	xfs_btree_mem_head_init(bp, xfbt->owner, XFBTREE_INIT_LEAF_BLOCK);
+	error = xfs_bwrite(bp);
+	xfs_buf_relse(bp);
+	if (error)
+		return error;
+
+	xfbt->xf_used++;
+	return 0;
+}
+
+/* Create an xfile btree backing thing that can be used for in-memory btrees. */
+int
+xfbtree_create(
+	struct xfs_mount		*mp,
+	const struct xfbtree_config	*cfg,
+	struct xfbtree			**xfbtreep)
+{
+	struct xfbtree			*xfbt;
+	unsigned int			blocklen = xfbtree_rec_bytes(mp, cfg);
+	unsigned int			keyptr_len = cfg->btree_ops->key_len;
+	int				error;
+
+	/* Requires an xfile-backed buftarg. */
+	if (!(cfg->target->bt_flags & XFS_BUFTARG_IN_MEMORY)) {
+		ASSERT(cfg->target->bt_flags & XFS_BUFTARG_IN_MEMORY);
+		return -EINVAL;
+	}
+
+	xfbt = kzalloc(sizeof(struct xfbtree), XCHK_GFP_FLAGS);
+	if (!xfbt)
+		return -ENOMEM;
+
+	/* Assign our memory file and the free space bitmap. */
+	xfbt->target = cfg->target;
+	xfbt->freespace = kmalloc(sizeof(struct xbitmap), XCHK_GFP_FLAGS);
+	if (!xfbt->freespace) {
+		error = -ENOMEM;
+		goto err_buftarg;
+	}
+	xbitmap_init(xfbt->freespace);
+
+	/* Set up min/maxrecs for this btree. */
+	if (cfg->flags & XFBTREE_CREATE_LONG_PTRS)
+		keyptr_len += sizeof(__be64);
+	else
+		keyptr_len += sizeof(__be32);
+	xfbt->maxrecs[0] = blocklen / cfg->btree_ops->rec_len;
+	xfbt->maxrecs[1] = blocklen / keyptr_len;
+	xfbt->minrecs[0] = xfbt->maxrecs[0] / 2;
+	xfbt->minrecs[1] = xfbt->maxrecs[1] / 2;
+	xfbt->owner = cfg->owner;
+
+	/* Initialize the empty btree. */
+	error = xfbtree_init_leaf_block(mp, xfbt, cfg);
+	if (error)
+		goto err_freesp;
+
+	error = xfbtree_init_head(xfbt);
+	if (error)
+		goto err_freesp;
+
+	trace_xfbtree_create(mp, cfg, xfbt);
+
+	*xfbtreep = xfbt;
+	return 0;
+
+err_freesp:
+	xbitmap_destroy(xfbt->freespace);
+	kfree(xfbt->freespace);
+err_buftarg:
+	xfs_buftarg_drain(xfbt->target);
+	kfree(xfbt);
+	return error;
+}
+
+/* Read the in-memory btree head. */
+int
+xfbtree_head_read_buf(
+	struct xfbtree		*xfbt,
+	struct xfs_trans	*tp,
+	struct xfs_buf		**bpp)
+{
+	struct xfs_buftarg	*btp = xfbt->target;
+	struct xfs_mount	*mp = btp->bt_mount;
+	struct xfs_btree_mem_head *mhead;
+	struct xfs_buf		*bp;
+	xfs_daddr_t		daddr;
+	int			error;
+
+	daddr = xfo_to_daddr(XFBTREE_HEAD_BLOCK);
+	error = xfs_trans_read_buf(mp, tp, btp, daddr, xfbtree_bbsize(), 0,
+			&bp, &xfs_btree_mem_head_buf_ops);
+	if (error)
+		return error;
+
+	mhead = bp->b_addr;
+	if (be64_to_cpu(mhead->mh_owner) != xfbt->owner) {
+		xfs_verifier_error(bp, -EFSCORRUPTED, __this_address);
+		xfs_trans_brelse(tp, bp);
+		return -EFSCORRUPTED;
+	}
+
+	*bpp = bp;
+	return 0;
+}
+
+static inline struct xfile *xfbtree_xfile(struct xfbtree *xfbt)
+{
+	return xfbt->target->bt_xfile;
+}
+
+/* Allocate a block to our in-memory btree. */
+int
+xfbtree_alloc_block(
+	struct xfs_btree_cur		*cur,
+	const union xfs_btree_ptr	*start,
+	union xfs_btree_ptr		*new,
+	int				*stat)
+{
+	struct xfbtree			*xfbt = cur->bc_mem.xfbtree;
+	xfileoff_t			bt_xfoff;
+	loff_t				pos;
+	int				error;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_MEMORY);
+
+	/*
+	 * Find the first free block in the free space bitmap and take it.  If
+	 * none are found, seek to end of the file.
+	 */
+	error = xbitmap_take_first_set(xfbt->freespace, 0, -1ULL, &bt_xfoff);
+	if (error == -ENODATA) {
+		bt_xfoff = xfbt->xf_used;
+		xfbt->xf_used++;
+	} else if (error) {
+		return error;
+	}
+
+	trace_xfbtree_alloc_block(xfbt, cur, bt_xfoff);
+
+	/* Fail if the block address exceeds the maximum for short pointers. */
+	if (!(cur->bc_flags & XFS_BTREE_LONG_PTRS) && bt_xfoff >= INT_MAX) {
+		*stat = 0;
+		return 0;
+	}
+
+	/* Make sure we actually can write to the block before we return it. */
+	pos = xfo_to_b(bt_xfoff);
+	error = xfile_prealloc(xfbtree_xfile(xfbt), pos, xfo_to_b(1));
+	if (error)
+		return error;
+
+	if (cur->bc_flags & XFS_BTREE_LONG_PTRS)
+		new->l = cpu_to_be64(bt_xfoff);
+	else
+		new->s = cpu_to_be32(bt_xfoff);
+
+	*stat = 1;
+	return 0;
+}
+
+/* Free a block from our in-memory btree. */
+int
+xfbtree_free_block(
+	struct xfs_btree_cur	*cur,
+	struct xfs_buf		*bp)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+	xfileoff_t		bt_xfoff, bt_xflen;
+	int			error;
+
+	ASSERT(cur->bc_flags & XFS_BTREE_IN_MEMORY);
+
+	bt_xfoff = xfs_daddr_to_xfot(xfs_buf_daddr(bp));
+	bt_xflen = xfs_daddr_to_xfot(bp->b_length);
+
+	trace_xfbtree_free_block(xfbt, cur, bt_xfoff);
+
+	error = xbitmap_set(xfbt->freespace, bt_xfoff, bt_xflen);
+	if (error)
+		return error;
+
+	xfile_discard(xfbtree_xfile(xfbt), xfo_to_b(bt_xfoff),
+			xfo_to_b(bt_xflen));
+	return 0;
+}
+
+/* Return the minimum number of records for a btree block. */
+int
+xfbtree_get_minrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+
+	return xfbt->minrecs[level != 0];
+}
+
+/* Return the maximum number of records for a btree block. */
+int
+xfbtree_get_maxrecs(
+	struct xfs_btree_cur	*cur,
+	int			level)
+{
+	struct xfbtree		*xfbt = cur->bc_mem.xfbtree;
+
+	return xfbt->maxrecs[level != 0];
+}
+
+/* If this log item is a buffer item that came from the xfbtree, return it. */
+static inline struct xfs_buf *
+xfbtree_buf_match(
+	struct xfbtree			*xfbt,
+	const struct xfs_log_item	*lip)
+{
+	const struct xfs_buf_log_item	*bli;
+	struct xfs_buf			*bp;
+
+	if (lip->li_type != XFS_LI_BUF)
+		return NULL;
+
+	bli = container_of(lip, struct xfs_buf_log_item, bli_item);
+	bp = bli->bli_buf;
+	if (bp->b_target != xfbt->target)
+		return NULL;
+
+	return bp;
+}
+
+/*
+ * Detach this (probably dirty) xfbtree buffer from the transaction by any
+ * means necessary.  Returns true if the buffer needs to be written.
+ */
+STATIC bool
+xfbtree_trans_bdetach(
+	struct xfs_trans	*tp,
+	struct xfs_buf		*bp)
+{
+	struct xfs_buf_log_item	*bli = bp->b_log_item;
+	bool			dirty;
+
+	ASSERT(bli != NULL);
+
+	dirty = bli->bli_flags & (XFS_BLI_DIRTY | XFS_BLI_ORDERED);
+
+	bli->bli_flags &= ~(XFS_BLI_DIRTY | XFS_BLI_ORDERED |
+			    XFS_BLI_LOGGED | XFS_BLI_STALE);
+	clear_bit(XFS_LI_DIRTY, &bli->bli_item.li_flags);
+
+	while (bp->b_log_item != NULL)
+		xfs_trans_bdetach(tp, bp);
+
+	return dirty;
+}
+
+/*
+ * Commit changes to the incore btree immediately by writing all dirty xfbtree
+ * buffers to the backing xfile.  This detaches all xfbtree buffers from the
+ * transaction, even on failure.  The buffer locks are dropped between the
+ * delwri queue and submit, so the caller must synchronize btree access.
+ *
+ * Normally we'd let the buffers commit with the transaction and get written to
+ * the xfile via the log, but online repair stages ephemeral btrees in memory
+ * and uses the btree_staging functions to write new btrees to disk atomically.
+ * The in-memory btree (and its backing store) are discarded at the end of the
+ * repair phase, which means that xfbtree buffers cannot commit with the rest
+ * of a transaction.
+ *
+ * In other words, online repair only needs the transaction to collect buffer
+ * pointers and to avoid buffer deadlocks, not to guarantee consistency of
+ * updates.
+ */
+int
+xfbtree_trans_commit(
+	struct xfbtree		*xfbt,
+	struct xfs_trans	*tp)
+{
+	LIST_HEAD(buffer_list);
+	struct xfs_log_item	*lip, *n;
+	bool			corrupt = false;
+	bool			tp_dirty = false;
+
+	/*
+	 * For each xfbtree buffer attached to the transaction, write the dirty
+	 * buffers to the xfile and release them.
+	 */
+	list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) {
+		struct xfs_buf	*bp = xfbtree_buf_match(xfbt, lip);
+		bool		dirty;
+
+		if (!bp) {
+			if (test_bit(XFS_LI_DIRTY, &lip->li_flags))
+				tp_dirty |= true;
+			continue;
+		}
+
+		trace_xfbtree_trans_commit_buf(xfbt, bp);
+
+		dirty = xfbtree_trans_bdetach(tp, bp);
+		if (dirty && !corrupt) {
+			xfs_failaddr_t	fa = bp->b_ops->verify_struct(bp);
+
+			/*
+			 * Because this btree is ephemeral, validate the buffer
+			 * structure before delwri_submit so that we can return
+			 * corruption errors to the caller without shutting
+			 * down the filesystem.
+			 *
+			 * If the buffer fails verification, log the failure
+			 * but continue walking the transaction items so that
+			 * we remove all ephemeral btree buffers.
+			 */
+			if (fa) {
+				corrupt = true;
+				xfs_verifier_error(bp, -EFSCORRUPTED, fa);
+			} else {
+				xfs_buf_delwri_queue_here(bp, &buffer_list);
+			}
+		}
+
+		xfs_buf_relse(bp);
+	}
+
+	/*
+	 * Reset the transaction's dirty flag to reflect the dirty state of the
+	 * log items that are still attached.
+	 */
+	tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) |
+			(tp_dirty ? XFS_TRANS_DIRTY : 0);
+
+	if (corrupt) {
+		xfs_buf_delwri_cancel(&buffer_list);
+		return -EFSCORRUPTED;
+	}
+
+	if (list_empty(&buffer_list))
+		return 0;
+
+	return xfs_buf_delwri_submit(&buffer_list);
+}
+
+/*
+ * Cancel changes to the incore btree by detaching all the xfbtree buffers.
+ * Changes are not written to the backing store.  This is needed for online
+ * repair btrees, which are by nature ephemeral.
+ */
+void
+xfbtree_trans_cancel(
+	struct xfbtree		*xfbt,
+	struct xfs_trans	*tp)
+{
+	struct xfs_log_item	*lip, *n;
+	bool			tp_dirty = false;
+
+	list_for_each_entry_safe(lip, n, &tp->t_items, li_trans) {
+		struct xfs_buf	*bp = xfbtree_buf_match(xfbt, lip);
+
+		if (!bp) {
+			if (test_bit(XFS_LI_DIRTY, &lip->li_flags))
+				tp_dirty |= true;
+			continue;
+		}
+
+		trace_xfbtree_trans_cancel_buf(xfbt, bp);
+
+		xfbtree_trans_bdetach(tp, bp);
+		xfs_buf_relse(bp);
+	}
+
+	/*
+	 * Reset the transaction's dirty flag to reflect the dirty state of the
+	 * log items that are still attached.
+	 */
+	tp->t_flags = (tp->t_flags & ~XFS_TRANS_DIRTY) |
+			(tp_dirty ? XFS_TRANS_DIRTY : 0);
+}