[LogFS] Fix bdev erases

Erases for block devices were always just emulated by writing 0xff.
Some time back the write was removed and only the page cache was
changed to 0xff.  Superficialy a good idea with two problems:
1. Touching the page cache isn't necessary either.
2. However, writing out 0xff _is_ necessary for the journal.  As the
   journal is scanned linearly, an old non-overwritten commit entry
   can be used on next mount and cause havoc.

This should fix both aspects.

fs/logfs/dev_bdev.c

@@ -167,27 +167,91 @@ static void bdev_writeseg(struct super_block *sb, u64 ofs, size_t len)
 	generic_unplug_device(bdev_get_queue(logfs_super(sb)->s_bdev));
 }
 
-static int bdev_erase(struct super_block *sb, loff_t to, size_t len)
+
+static void erase_end_io(struct bio *bio, int err) 
+{ 
+	const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); 
+	struct super_block *sb = bio->bi_private; 
+	struct logfs_super *super = logfs_super(sb); 
+
+	BUG_ON(!uptodate); /* FIXME: Retry io or write elsewhere */ 
+	BUG_ON(err); 
+	BUG_ON(bio->bi_vcnt == 0); 
+	bio_put(bio); 
+	if (atomic_dec_and_test(&super->s_pending_writes))
+		wake_up(&wq); 
+} 
+
+static int do_erase(struct super_block *sb, u64 ofs, pgoff_t index,
+		size_t nr_pages)
+{
+	struct logfs_super *super = logfs_super(sb);
+	struct bio *bio;
+	struct request_queue *q = bdev_get_queue(sb->s_bdev);
+	unsigned int max_pages = queue_max_hw_sectors(q) >> (PAGE_SHIFT - 9);
+	int i;
+
+	bio = bio_alloc(GFP_NOFS, max_pages);
+	BUG_ON(!bio); /* FIXME: handle this */
+
+	for (i = 0; i < nr_pages; i++) {
+		if (i >= max_pages) {
+			/* Block layer cannot split bios :( */
+			bio->bi_vcnt = i;
+			bio->bi_idx = 0;
+			bio->bi_size = i * PAGE_SIZE;
+			bio->bi_bdev = super->s_bdev;
+			bio->bi_sector = ofs >> 9;
+			bio->bi_private = sb;
+			bio->bi_end_io = erase_end_io;
+			atomic_inc(&super->s_pending_writes);
+			submit_bio(WRITE, bio);
+
+			ofs += i * PAGE_SIZE;
+			index += i;
+			nr_pages -= i;
+			i = 0;
+
+			bio = bio_alloc(GFP_NOFS, max_pages);
+			BUG_ON(!bio);
+		}
+		bio->bi_io_vec[i].bv_page = super->s_erase_page;
+		bio->bi_io_vec[i].bv_len = PAGE_SIZE;
+		bio->bi_io_vec[i].bv_offset = 0;
+	}
+	bio->bi_vcnt = nr_pages;
+	bio->bi_idx = 0;
+	bio->bi_size = nr_pages * PAGE_SIZE;
+	bio->bi_bdev = super->s_bdev;
+	bio->bi_sector = ofs >> 9;
+	bio->bi_private = sb;
+	bio->bi_end_io = erase_end_io;
+	atomic_inc(&super->s_pending_writes);
+	submit_bio(WRITE, bio);
+	return 0;
+}
+
+static int bdev_erase(struct super_block *sb, loff_t to, size_t len,
+		int ensure_write)
 {
 	struct logfs_super *super = logfs_super(sb);
-	struct address_space *mapping = super->s_mapping_inode->i_mapping;
-	struct page *page;
-	pgoff_t index = to >> PAGE_SHIFT;
-	int i, nr_pages = len >> PAGE_SHIFT;
 
 	BUG_ON(to & (PAGE_SIZE - 1));
 	BUG_ON(len & (PAGE_SIZE - 1));
 
-	if (logfs_super(sb)->s_flags & LOGFS_SB_FLAG_RO)
+	if (super->s_flags & LOGFS_SB_FLAG_RO)
 		return -EROFS;
 
-	for (i = 0; i < nr_pages; i++) {
-		page = find_get_page(mapping, index + i);
-		if (page) {
-			memset(page_address(page), 0xFF, PAGE_SIZE);
-			page_cache_release(page);
-		}
+	if (ensure_write) {
+		/*
+		 * Object store doesn't care whether erases happen or not.
+		 * But for the journal they are required.  Otherwise a scan
+		 * can find an old commit entry and assume it is the current
+		 * one, travelling back in time.
+		 */
+		do_erase(sb, to, to >> PAGE_SHIFT, len >> PAGE_SHIFT);
 	}
+
 	return 0;
 }
 

fs/logfs/dev_mtd.c

@@ -83,7 +83,8 @@ static int mtd_erase_mapping(struct super_block *sb, loff_t ofs, size_t len)
 	return 0;
 }
 
-static int mtd_erase(struct super_block *sb, loff_t ofs, size_t len)
+static int mtd_erase(struct super_block *sb, loff_t ofs, size_t len,
+		int ensure_write)
 {
 	struct mtd_info *mtd = logfs_super(sb)->s_mtd;
 	struct erase_info ei;

fs/logfs/journal.c

@@ -392,7 +392,7 @@ static int journal_erase_segment(struct logfs_area *area)
 	u64 ofs;
 	int err;
 
-	err = logfs_erase_segment(sb, area->a_segno);
+	err = logfs_erase_segment(sb, area->a_segno, 1);
 	if (err)
 		return err;
 

fs/logfs/logfs.h

@@ -151,7 +151,8 @@ struct logfs_device_ops {
 	int (*write_sb)(struct super_block *sb, struct page *page);
 	int (*readpage)(void *_sb, struct page *page);
 	void (*writeseg)(struct super_block *sb, u64 ofs, size_t len);
-	int (*erase)(struct super_block *sb, loff_t ofs, size_t len);
+	int (*erase)(struct super_block *sb, loff_t ofs, size_t len,
+			int ensure_write);
 	void (*sync)(struct super_block *sb);
 	void (*put_device)(struct super_block *sb);
 };
@@ -327,6 +328,7 @@ struct logfs_super {
 	u64	 s_feature_compat;
 	u64	 s_feature_flags;
 	u64	 s_sb_ofs[2];
+	struct page *s_erase_page;		/* for dev_bdev.c */
 	/* alias.c fields */
 	struct btree_head32 s_segment_alias;	/* remapped segments */
 	int	 s_no_object_aliases;
@@ -572,7 +574,7 @@ int get_page_reserve(struct inode *inode, struct page *page);
 extern struct logfs_block_ops indirect_block_ops;
 
 /* segment.c */
-int logfs_erase_segment(struct super_block *sb, u32 ofs);
+int logfs_erase_segment(struct super_block *sb, u32 ofs, int ensure_erase);
 int wbuf_read(struct super_block *sb, u64 ofs, size_t len, void *buf);
 int logfs_segment_read(struct inode *inode, struct page *page, u64 ofs, u64 bix,
 		level_t level);

fs/logfs/segment.c

@@ -25,14 +25,14 @@ static int logfs_mark_segment_bad(struct super_block *sb, u32 segno)
 	return 0;
 }
 
-int logfs_erase_segment(struct super_block *sb, u32 segno)
+int logfs_erase_segment(struct super_block *sb, u32 segno, int ensure_erase)
 {
 	struct logfs_super *super = logfs_super(sb);
 
 	super->s_gec++;
 
 	return super->s_devops->erase(sb, (u64)segno << super->s_segshift,
-			super->s_segsize);
+			super->s_segsize, ensure_erase);
 }
 
 static s64 logfs_get_free_bytes(struct logfs_area *area, size_t bytes)
@@ -798,7 +798,7 @@ static int ostore_erase_segment(struct logfs_area *area)
 	u64 ofs;
 	int err;
 
-	err = logfs_erase_segment(sb, area->a_segno);
+	err = logfs_erase_segment(sb, area->a_segno, 0);
 	if (err)
 		return err;
 

fs/logfs/super.c

@@ -317,6 +317,7 @@ static int logfs_make_writeable(struct super_block *sb)
 
 static int logfs_get_sb_final(struct super_block *sb, struct vfsmount *mnt)
 {
+	struct logfs_super *super = logfs_super(sb);
 	struct inode *rootdir;
 	int err;
 
@@ -329,15 +330,22 @@ static int logfs_get_sb_final(struct super_block *sb, struct vfsmount *mnt)
 	if (!sb->s_root)
 		goto fail;
 
+	super->s_erase_page = alloc_pages(GFP_KERNEL, 0);
+	if (!super->s_erase_page)
+		goto fail2;
+	memset(page_address(super->s_erase_page), 0xFF, PAGE_SIZE);
+
 	/* FIXME: check for read-only mounts */
 	err = logfs_make_writeable(sb);
 	if (err)
-		goto fail2;
+		goto fail3;
 
 	log_super("LogFS: Finished mounting\n");
 	simple_set_mnt(mnt, sb);
 	return 0;
 
+fail3:
+	__free_page(super->s_erase_page);
 fail2:
 	iput(rootdir);
 fail:
@@ -498,6 +506,8 @@ static void logfs_kill_sb(struct super_block *sb)
 	logfs_cleanup_journal(sb);
 	logfs_cleanup_areas(sb);
 	logfs_cleanup_rw(sb);
+	if (super->s_erase_page)
+		__free_page(super->s_erase_page);
 	super->s_devops->put_device(sb);
 	mempool_destroy(super->s_btree_pool);
 	mempool_destroy(super->s_alias_pool);