xfs: refactor dir2 leaf readahead shadow buffer cleverness

Currently, the dir2 leaf block getdents function uses a complex state
tracking mechanism to create a shadow copy of the block mappings and
then uses the shadow copy to schedule readahead.  Since the read and
readahead functions are perfectly capable of reading the mappings
themselves, we can tear all that out in favor of a simpler function that
simply keeps pushing the readahead window further out.
Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>

fs/xfs/xfs_dir2_readdir.c

@@ -243,214 +243,100 @@ xfs_dir2_block_getdents(
 	return 0;
 }
 
-struct xfs_dir2_leaf_map_info {
-	xfs_extlen_t	map_blocks;	/* number of fsbs in map */
-	xfs_dablk_t	map_off;	/* last mapped file offset */
-	int		map_size;	/* total entries in *map */
-	int		map_valid;	/* valid entries in *map */
-	int		nmap;		/* mappings to ask xfs_bmapi */
-	xfs_dir2_db_t	curdb;		/* db for current block */
-	int		ra_current;	/* number of read-ahead blks */
-	int		ra_index;	/* *map index for read-ahead */
-	int		ra_offset;	/* map entry offset for ra */
-	int		ra_want;	/* readahead count wanted */
-	struct xfs_bmbt_irec map[];	/* map vector for blocks */
-};
-
+/*
+ * Read a directory block and initiate readahead for blocks beyond that.
+ * We maintain a sliding readahead window of the remaining space in the
+ * buffer rounded up to the nearest block.
+ */
 STATIC int
 xfs_dir2_leaf_readbuf(
 	struct xfs_da_args	*args,
 	size_t			bufsize,
-	struct xfs_dir2_leaf_map_info *mip,
-	xfs_dir2_off_t		*curoff,
-	struct xfs_buf		**bpp,
-	bool			trim_map)
+	xfs_dir2_off_t		*cur_off,
+	xfs_dablk_t		*ra_blk,
+	struct xfs_buf		**bpp)
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_buf		*bp = NULL;
-	struct xfs_bmbt_irec	*map = mip->map;
+	struct xfs_da_geometry	*geo = args->geo;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK);
+	struct xfs_bmbt_irec	map;
 	struct blk_plug		plug;
+	xfs_dir2_off_t		new_off;
+	xfs_dablk_t		next_ra;
+	xfs_dablk_t		map_off;
+	xfs_dablk_t		last_da;
+	xfs_extnum_t		idx;
+	int			ra_want;
 	int			error = 0;
-	int			length;
-	int			i;
-	int			j;
-	struct xfs_da_geometry	*geo = args->geo;
-
-	/*
-	 * If the caller just finished processing a buffer, it will tell us
-	 * we need to trim that block out of the mapping now it is done.
-	 */
-	if (trim_map) {
-		mip->map_blocks -= geo->fsbcount;
-		/*
-		 * Loop to get rid of the extents for the
-		 * directory block.
-		 */
-		for (i = geo->fsbcount; i > 0; ) {
-			j = min_t(int, map->br_blockcount, i);
-			map->br_blockcount -= j;
-			map->br_startblock += j;
-			map->br_startoff += j;
-			/*
-			 * If mapping is done, pitch it from
-			 * the table.
-			 */
-			if (!map->br_blockcount && --mip->map_valid)
-				memmove(&map[0], &map[1],
-					sizeof(map[0]) * mip->map_valid);
-			i -= j;
-		}
-	}
-
-	/*
-	 * Recalculate the readahead blocks wanted.
-	 */
-	mip->ra_want = howmany(bufsize + geo->blksize, (1 << geo->fsblog)) - 1;
-	ASSERT(mip->ra_want >= 0);
-
-	/*
-	 * If we don't have as many as we want, and we haven't
-	 * run out of data blocks, get some more mappings.
-	 */
-	if (1 + mip->ra_want > mip->map_blocks &&
-	    mip->map_off < xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET)) {
-		/*
-		 * Get more bmaps, fill in after the ones
-		 * we already have in the table.
-		 */
-		mip->nmap = mip->map_size - mip->map_valid;
-		error = xfs_bmapi_read(dp, mip->map_off,
-				xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET) -
-								mip->map_off,
-				&map[mip->map_valid], &mip->nmap, 0);
 
-		/*
-		 * Don't know if we should ignore this or try to return an
-		 * error.  The trouble with returning errors is that readdir
-		 * will just stop without actually passing the error through.
-		 */
+	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(args->trans, dp, XFS_DATA_FORK);
 		if (error)
-			goto out;	/* XXX */
-
-		/*
-		 * If we got all the mappings we asked for, set the final map
-		 * offset based on the last bmap value received.  Otherwise,
-		 * we've reached the end.
-		 */
-		if (mip->nmap == mip->map_size - mip->map_valid) {
-			i = mip->map_valid + mip->nmap - 1;
-			mip->map_off = map[i].br_startoff + map[i].br_blockcount;
-		} else
-			mip->map_off = xfs_dir2_byte_to_da(geo,
-							XFS_DIR2_LEAF_OFFSET);
-
-		/*
-		 * Look for holes in the mapping, and eliminate them.  Count up
-		 * the valid blocks.
-		 */
-		for (i = mip->map_valid; i < mip->map_valid + mip->nmap; ) {
-			if (map[i].br_startblock == HOLESTARTBLOCK) {
-				mip->nmap--;
-				length = mip->map_valid + mip->nmap - i;
-				if (length)
-					memmove(&map[i], &map[i + 1],
-						sizeof(map[i]) * length);
-			} else {
-				mip->map_blocks += map[i].br_blockcount;
-				i++;
-			}
-		}
-		mip->map_valid += mip->nmap;
+			goto out;
 	}
 
 	/*
-	 * No valid mappings, so no more data blocks.
+	 * Look for mapped directory blocks at or above the current offset.
+	 * Truncate down to the nearest directory block to start the scanning
+	 * operation.
 	 */
-	if (!mip->map_valid) {
-		*curoff = xfs_dir2_da_to_byte(geo, mip->map_off);
+	last_da = xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET);
+	map_off = xfs_dir2_db_to_da(geo, xfs_dir2_byte_to_db(geo, *cur_off));
+	if (!xfs_iext_lookup_extent(dp, ifp, map_off, &idx, &map))
 		goto out;
-	}
+	if (map.br_startoff >= last_da)
+		goto out;
+	xfs_trim_extent(&map, map_off, last_da - map_off);
 
-	/*
-	 * Read the directory block starting at the first mapping.
-	 */
-	mip->curdb = xfs_dir2_da_to_db(geo, map->br_startoff);
-	error = xfs_dir3_data_read(NULL, dp, map->br_startoff,
-			map->br_blockcount >= geo->fsbcount ?
-			    XFS_FSB_TO_DADDR(dp->i_mount, map->br_startblock) :
-			    -1, &bp);
-	/*
-	 * Should just skip over the data block instead of giving up.
-	 */
+	/* Read the directory block of that first mapping. */
+	new_off = xfs_dir2_da_to_byte(geo, map.br_startoff);
+	if (new_off > *cur_off)
+		*cur_off = new_off;
+	error = xfs_dir3_data_read(args->trans, dp, map.br_startoff, -1, &bp);
 	if (error)
-		goto out;	/* XXX */
-
-	/*
-	 * Adjust the current amount of read-ahead: we just read a block that
-	 * was previously ra.
-	 */
-	if (mip->ra_current)
-		mip->ra_current -= geo->fsbcount;
+		goto out;
 
 	/*
-	 * Do we need more readahead?
-	 * Each loop tries to process 1 full dir blk; last may be partial.
+	 * Start readahead for the next bufsize's worth of dir data blocks.
+	 * We may have already issued readahead for some of that range;
+	 * ra_blk tracks the last block we tried to read(ahead).
 	 */
+	ra_want = howmany(bufsize + geo->blksize, (1 << geo->fsblog));
+	if (*ra_blk >= last_da)
+		goto out;
+	else if (*ra_blk == 0)
+		*ra_blk = map.br_startoff;
+	next_ra = map.br_startoff + geo->fsbcount;
+	if (next_ra >= last_da)
+		goto out_no_ra;
+	if (map.br_blockcount < geo->fsbcount &&
+	    !xfs_iext_get_extent(ifp, ++idx, &map))
+		goto out_no_ra;
+	if (map.br_startoff >= last_da)
+		goto out_no_ra;
+	xfs_trim_extent(&map, next_ra, last_da - next_ra);
+
+	/* Start ra for each dir (not fs) block that has a mapping. */
 	blk_start_plug(&plug);
-	for (mip->ra_index = mip->ra_offset = i = 0;
-	     mip->ra_want > mip->ra_current && i < mip->map_blocks;
-	     i += geo->fsbcount) {
-		ASSERT(mip->ra_index < mip->map_valid);
-		/*
-		 * Read-ahead a contiguous directory block.
-		 */
-		if (i > mip->ra_current &&
-		    (map[mip->ra_index].br_blockcount - mip->ra_offset) >=
-		    geo->fsbcount) {
-			xfs_dir3_data_readahead(dp,
-				map[mip->ra_index].br_startoff + mip->ra_offset,
-				XFS_FSB_TO_DADDR(dp->i_mount,
-					map[mip->ra_index].br_startblock +
-							mip->ra_offset));
-			mip->ra_current = i;
+	while (ra_want > 0) {
+		next_ra = roundup((xfs_dablk_t)map.br_startoff, geo->fsbcount);
+		while (ra_want > 0 &&
+		       next_ra < map.br_startoff + map.br_blockcount) {
+			if (next_ra >= last_da) {
+				*ra_blk = last_da;
+				break;
 			}
-
-		/*
-		 * Read-ahead a non-contiguous directory block.  This doesn't
-		 * use our mapping, but this is a very rare case.
-		 */
-		else if (i > mip->ra_current) {
-			xfs_dir3_data_readahead(dp,
-					map[mip->ra_index].br_startoff +
-							mip->ra_offset, -1);
-			mip->ra_current = i;
+			if (next_ra > *ra_blk) {
+				xfs_dir3_data_readahead(dp, next_ra, -2);
+				*ra_blk = next_ra;
 			}
-
-		/*
-		 * Advance offset through the mapping table, processing a full
-		 * dir block even if it is fragmented into several extents.
-		 * But stop if we have consumed all valid mappings, even if
-		 * it's not yet a full directory block.
-		 */
-		for (j = 0;
-		     j < geo->fsbcount && mip->ra_index < mip->map_valid;
-		     j += length ) {
-			/*
-			 * The rest of this extent but not more than a dir
-			 * block.
-			 */
-			length = min_t(int, geo->fsbcount - j,
-					map[mip->ra_index].br_blockcount -
-							mip->ra_offset);
-			mip->ra_offset += length;
-
-			/*
-			 * Advance to the next mapping if this one is used up.
-			 */
-			if (mip->ra_offset == map[mip->ra_index].br_blockcount) {
-				mip->ra_offset = 0;
-				mip->ra_index++;
+			ra_want -= geo->fsbcount;
+			next_ra += geo->fsbcount;
 		}
+		if (!xfs_iext_get_extent(ifp, ++idx, &map)) {
+			*ra_blk = last_da;
+			break;
 		}
 	}
 	blk_finish_plug(&plug);
@@ -458,6 +344,9 @@ xfs_dir2_leaf_readbuf(
 out:
 	*bpp = bp;
 	return error;
+out_no_ra:
+	*ra_blk = last_da;
+	goto out;
 }
 
 /*
@@ -475,14 +364,14 @@ xfs_dir2_leaf_getdents(
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_data_entry_t	*dep;		/* data entry */
 	xfs_dir2_data_unused_t	*dup;		/* unused entry */
-	int			error = 0;	/* error return value */
-	int			length;		/* temporary length value */
-	int			byteoff;	/* offset in current block */
-	xfs_dir2_off_t		curoff;		/* current overall offset */
-	xfs_dir2_off_t		newoff;		/* new curoff after new blk */
 	char			*ptr = NULL;	/* pointer to current data */
-	struct xfs_dir2_leaf_map_info *map_info;
 	struct xfs_da_geometry	*geo = args->geo;
+	xfs_dablk_t		rablk = 0;	/* current readahead block */
+	xfs_dir2_off_t		curoff;		/* current overall offset */
+	int			length;		/* temporary length value */
+	int			byteoff;	/* offset in current block */
+	int			lock_mode;
+	int			error = 0;	/* error return value */
 
 	/*
 	 * If the offset is at or past the largest allowed value,
@@ -491,30 +380,12 @@ xfs_dir2_leaf_getdents(
 	if (ctx->pos >= XFS_DIR2_MAX_DATAPTR)
 		return 0;
 
-	/*
-	 * Set up to bmap a number of blocks based on the caller's
-	 * buffer size, the directory block size, and the filesystem
-	 * block size.
-	 */
-	length = howmany(bufsize + geo->blksize, (1 << geo->fsblog));
-	map_info = kmem_zalloc(offsetof(struct xfs_dir2_leaf_map_info, map) +
-				(length * sizeof(struct xfs_bmbt_irec)),
-			       KM_SLEEP | KM_NOFS);
-	map_info->map_size = length;
-
 	/*
 	 * Inside the loop we keep the main offset value as a byte offset
 	 * in the directory file.
 	 */
 	curoff = xfs_dir2_dataptr_to_byte(ctx->pos);
 
-	/*
-	 * Force this conversion through db so we truncate the offset
-	 * down to get the start of the data block.
-	 */
-	map_info->map_off = xfs_dir2_db_to_da(geo,
-					      xfs_dir2_byte_to_db(geo, curoff));
-
 	/*
 	 * Loop over directory entries until we reach the end offset.
 	 * Get more blocks and readahead as necessary.
@@ -527,38 +398,18 @@ xfs_dir2_leaf_getdents(
 		 * current buffer, need to get another one.
 		 */
 		if (!bp || ptr >= (char *)bp->b_addr + geo->blksize) {
-			int	lock_mode;
-			bool	trim_map = false;
-
 			if (bp) {
-				xfs_trans_brelse(NULL, bp);
+				xfs_trans_brelse(args->trans, bp);
 				bp = NULL;
-				trim_map = true;
 			}
 
 			lock_mode = xfs_ilock_data_map_shared(dp);
-			error = xfs_dir2_leaf_readbuf(args, bufsize, map_info,
-						      &curoff, &bp, trim_map);
+			error = xfs_dir2_leaf_readbuf(args, bufsize, &curoff,
+					&rablk, &bp);
 			xfs_iunlock(dp, lock_mode);
-			if (error || !map_info->map_valid)
+			if (error || !bp)
 				break;
 
-			/*
-			 * Having done a read, we need to set a new offset.
-			 */
-			newoff = xfs_dir2_db_off_to_byte(geo,
-							 map_info->curdb, 0);
-			/*
-			 * Start of the current block.
-			 */
-			if (curoff < newoff)
-				curoff = newoff;
-			/*
-			 * Make sure we're in the right block.
-			 */
-			else if (curoff > newoff)
-				ASSERT(xfs_dir2_byte_to_db(geo, curoff) ==
-				       map_info->curdb);
 			hdr = bp->b_addr;
 			xfs_dir3_data_check(dp, bp);
 			/*
@@ -643,7 +494,6 @@ xfs_dir2_leaf_getdents(
 		ctx->pos = XFS_DIR2_MAX_DATAPTR & 0x7fffffff;
 	else
 		ctx->pos = xfs_dir2_byte_to_dataptr(curoff) & 0x7fffffff;
-	kmem_free(map_info);
 	if (bp)
 		xfs_trans_brelse(NULL, bp);
 	return error;