summaryrefslogtreecommitdiff
path: root/fs/nilfs2
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nilfs2')
-rw-r--r--fs/nilfs2/alloc.c104
-rw-r--r--fs/nilfs2/alloc.h2
-rw-r--r--fs/nilfs2/bmap.c15
-rw-r--r--fs/nilfs2/bmap.h20
-rw-r--r--fs/nilfs2/btnode.c129
-rw-r--r--fs/nilfs2/btree.c27
-rw-r--r--fs/nilfs2/btree.h1
-rw-r--r--fs/nilfs2/cpfile.c389
-rw-r--r--fs/nilfs2/cpfile.h10
-rw-r--r--fs/nilfs2/dat.c57
-rw-r--r--fs/nilfs2/dir.c285
-rw-r--r--fs/nilfs2/direct.c3
-rw-r--r--fs/nilfs2/file.c28
-rw-r--r--fs/nilfs2/gcinode.c5
-rw-r--r--fs/nilfs2/ifile.c21
-rw-r--r--fs/nilfs2/ifile.h10
-rw-r--r--fs/nilfs2/inode.c181
-rw-r--r--fs/nilfs2/ioctl.c123
-rw-r--r--fs/nilfs2/mdt.c97
-rw-r--r--fs/nilfs2/namei.c62
-rw-r--r--fs/nilfs2/nilfs.h52
-rw-r--r--fs/nilfs2/page.c217
-rw-r--r--fs/nilfs2/page.h25
-rw-r--r--fs/nilfs2/recovery.c40
-rw-r--r--fs/nilfs2/segbuf.c4
-rw-r--r--fs/nilfs2/segment.c585
-rw-r--r--fs/nilfs2/segment.h10
-rw-r--r--fs/nilfs2/sufile.c149
-rw-r--r--fs/nilfs2/super.c438
-rw-r--r--fs/nilfs2/sysfs.c6
-rw-r--r--fs/nilfs2/the_nilfs.c35
-rw-r--r--fs/nilfs2/the_nilfs.h12
32 files changed, 1673 insertions, 1469 deletions
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 25881bdd212b..ba50388ee4bf 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -529,60 +529,62 @@ int nilfs_palloc_prepare_alloc_entry(struct inode *inode,
ret = nilfs_palloc_get_desc_block(inode, group, 1, &desc_bh);
if (ret < 0)
return ret;
- desc_kaddr = kmap(desc_bh->b_page);
+ desc_kaddr = kmap_local_page(desc_bh->b_page);
desc = nilfs_palloc_block_get_group_desc(
inode, group, desc_bh, desc_kaddr);
n = nilfs_palloc_rest_groups_in_desc_block(inode, group,
maxgroup);
- for (j = 0; j < n; j++, desc++, group++) {
+ for (j = 0; j < n; j++, desc++, group++, group_offset = 0) {
lock = nilfs_mdt_bgl_lock(inode, group);
- if (nilfs_palloc_group_desc_nfrees(desc, lock) > 0) {
- ret = nilfs_palloc_get_bitmap_block(
- inode, group, 1, &bitmap_bh);
- if (ret < 0)
- goto out_desc;
- bitmap_kaddr = kmap(bitmap_bh->b_page);
- bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
- pos = nilfs_palloc_find_available_slot(
- bitmap, group_offset,
- entries_per_group, lock, wrap);
- /*
- * Since the search for a free slot in the
- * second and subsequent bitmap blocks always
- * starts from the beginning, the wrap flag
- * only has an effect on the first search.
- */
- if (pos >= 0) {
- /* found a free entry */
- nilfs_palloc_group_desc_add_entries(
- desc, lock, -1);
- req->pr_entry_nr =
- entries_per_group * group + pos;
- kunmap(desc_bh->b_page);
- kunmap(bitmap_bh->b_page);
-
- req->pr_desc_bh = desc_bh;
- req->pr_bitmap_bh = bitmap_bh;
- return 0;
- }
- kunmap(bitmap_bh->b_page);
- brelse(bitmap_bh);
+ if (nilfs_palloc_group_desc_nfrees(desc, lock) == 0)
+ continue;
+
+ kunmap_local(desc_kaddr);
+ ret = nilfs_palloc_get_bitmap_block(inode, group, 1,
+ &bitmap_bh);
+ if (unlikely(ret < 0)) {
+ brelse(desc_bh);
+ return ret;
}
- group_offset = 0;
+ desc_kaddr = kmap_local_page(desc_bh->b_page);
+ desc = nilfs_palloc_block_get_group_desc(
+ inode, group, desc_bh, desc_kaddr);
+
+ bitmap_kaddr = kmap_local_page(bitmap_bh->b_page);
+ bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
+ pos = nilfs_palloc_find_available_slot(
+ bitmap, group_offset, entries_per_group, lock,
+ wrap);
+ /*
+ * Since the search for a free slot in the second and
+ * subsequent bitmap blocks always starts from the
+ * beginning, the wrap flag only has an effect on the
+ * first search.
+ */
+ kunmap_local(bitmap_kaddr);
+ if (pos >= 0)
+ goto found;
+
+ brelse(bitmap_bh);
}
- kunmap(desc_bh->b_page);
+ kunmap_local(desc_kaddr);
brelse(desc_bh);
}
/* no entries left */
return -ENOSPC;
- out_desc:
- kunmap(desc_bh->b_page);
- brelse(desc_bh);
- return ret;
+found:
+ /* found a free entry */
+ nilfs_palloc_group_desc_add_entries(desc, lock, -1);
+ req->pr_entry_nr = entries_per_group * group + pos;
+ kunmap_local(desc_kaddr);
+
+ req->pr_desc_bh = desc_bh;
+ req->pr_bitmap_bh = bitmap_bh;
+ return 0;
}
/**
@@ -616,10 +618,10 @@ void nilfs_palloc_commit_free_entry(struct inode *inode,
spinlock_t *lock;
group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset);
- desc_kaddr = kmap(req->pr_desc_bh->b_page);
+ desc_kaddr = kmap_local_page(req->pr_desc_bh->b_page);
desc = nilfs_palloc_block_get_group_desc(inode, group,
req->pr_desc_bh, desc_kaddr);
- bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page);
+ bitmap_kaddr = kmap_local_page(req->pr_bitmap_bh->b_page);
bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh);
lock = nilfs_mdt_bgl_lock(inode, group);
@@ -631,8 +633,8 @@ void nilfs_palloc_commit_free_entry(struct inode *inode,
else
nilfs_palloc_group_desc_add_entries(desc, lock, 1);
- kunmap(req->pr_bitmap_bh->b_page);
- kunmap(req->pr_desc_bh->b_page);
+ kunmap_local(bitmap_kaddr);
+ kunmap_local(desc_kaddr);
mark_buffer_dirty(req->pr_desc_bh);
mark_buffer_dirty(req->pr_bitmap_bh);
@@ -657,10 +659,10 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
spinlock_t *lock;
group = nilfs_palloc_group(inode, req->pr_entry_nr, &group_offset);
- desc_kaddr = kmap(req->pr_desc_bh->b_page);
+ desc_kaddr = kmap_local_page(req->pr_desc_bh->b_page);
desc = nilfs_palloc_block_get_group_desc(inode, group,
req->pr_desc_bh, desc_kaddr);
- bitmap_kaddr = kmap(req->pr_bitmap_bh->b_page);
+ bitmap_kaddr = kmap_local_page(req->pr_bitmap_bh->b_page);
bitmap = bitmap_kaddr + bh_offset(req->pr_bitmap_bh);
lock = nilfs_mdt_bgl_lock(inode, group);
@@ -672,8 +674,8 @@ void nilfs_palloc_abort_alloc_entry(struct inode *inode,
else
nilfs_palloc_group_desc_add_entries(desc, lock, 1);
- kunmap(req->pr_bitmap_bh->b_page);
- kunmap(req->pr_desc_bh->b_page);
+ kunmap_local(bitmap_kaddr);
+ kunmap_local(desc_kaddr);
brelse(req->pr_bitmap_bh);
brelse(req->pr_desc_bh);
@@ -765,7 +767,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
/* Get the first entry number of the group */
group_min_nr = (__u64)group * epg;
- bitmap_kaddr = kmap(bitmap_bh->b_page);
+ bitmap_kaddr = kmap_local_page(bitmap_bh->b_page);
bitmap = bitmap_kaddr + bh_offset(bitmap_bh);
lock = nilfs_mdt_bgl_lock(inode, group);
@@ -811,7 +813,7 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
entry_start = rounddown(group_offset, epb);
} while (true);
- kunmap(bitmap_bh->b_page);
+ kunmap_local(bitmap_kaddr);
mark_buffer_dirty(bitmap_bh);
brelse(bitmap_bh);
@@ -825,11 +827,11 @@ int nilfs_palloc_freev(struct inode *inode, __u64 *entry_nrs, size_t nitems)
inode->i_ino);
}
- desc_kaddr = kmap_atomic(desc_bh->b_page);
+ desc_kaddr = kmap_local_page(desc_bh->b_page);
desc = nilfs_palloc_block_get_group_desc(
inode, group, desc_bh, desc_kaddr);
nfree = nilfs_palloc_group_desc_add_entries(desc, lock, n);
- kunmap_atomic(desc_kaddr);
+ kunmap_local(desc_kaddr);
mark_buffer_dirty(desc_bh);
nilfs_mdt_mark_dirty(inode);
brelse(desc_bh);
diff --git a/fs/nilfs2/alloc.h b/fs/nilfs2/alloc.h
index d825a9faca6d..e19d7eb10084 100644
--- a/fs/nilfs2/alloc.h
+++ b/fs/nilfs2/alloc.h
@@ -37,7 +37,7 @@ void *nilfs_palloc_block_get_entry(const struct inode *, __u64,
int nilfs_palloc_count_max_entries(struct inode *, u64, u64 *);
/**
- * nilfs_palloc_req - persistent allocator request and reply
+ * struct nilfs_palloc_req - persistent allocator request and reply
* @pr_entry_nr: entry number (vblocknr or inode number)
* @pr_desc_bh: buffer head of the buffer containing block group descriptors
* @pr_bitmap_bh: buffer head of the buffer containing a block group bitmap
diff --git a/fs/nilfs2/bmap.c b/fs/nilfs2/bmap.c
index 7a8f166f2c8d..c9e8d9a7d820 100644
--- a/fs/nilfs2/bmap.c
+++ b/fs/nilfs2/bmap.c
@@ -349,7 +349,7 @@ int nilfs_bmap_propagate(struct nilfs_bmap *bmap, struct buffer_head *bh)
}
/**
- * nilfs_bmap_lookup_dirty_buffers -
+ * nilfs_bmap_lookup_dirty_buffers - collect dirty block buffers
* @bmap: bmap
* @listp: pointer to buffer head list
*/
@@ -450,15 +450,9 @@ int nilfs_bmap_test_and_clear_dirty(struct nilfs_bmap *bmap)
__u64 nilfs_bmap_data_get_key(const struct nilfs_bmap *bmap,
const struct buffer_head *bh)
{
- struct buffer_head *pbh;
- __u64 key;
+ loff_t pos = folio_pos(bh->b_folio) + bh_offset(bh);
- key = page_index(bh->b_page) << (PAGE_SHIFT -
- bmap->b_inode->i_blkbits);
- for (pbh = page_buffers(bh->b_page); pbh != bh; pbh = pbh->b_this_page)
- key++;
-
- return key;
+ return pos >> bmap->b_inode->i_blkbits;
}
__u64 nilfs_bmap_find_target_seq(const struct nilfs_bmap *bmap, __u64 key)
@@ -548,13 +542,10 @@ int nilfs_bmap_read(struct nilfs_bmap *bmap, struct nilfs_inode *raw_inode)
*/
void nilfs_bmap_write(struct nilfs_bmap *bmap, struct nilfs_inode *raw_inode)
{
- down_write(&bmap->b_sem);
memcpy(raw_inode->i_bmap, bmap->b_u.u_data,
NILFS_INODE_BMAP_SIZE * sizeof(__le64));
if (bmap->b_inode->i_ino == NILFS_DAT_INO)
bmap->b_last_allocated_ptr = NILFS_BMAP_NEW_PTR_INIT;
-
- up_write(&bmap->b_sem);
}
void nilfs_bmap_init_gc(struct nilfs_bmap *bmap)
diff --git a/fs/nilfs2/bmap.h b/fs/nilfs2/bmap.h
index 608168a5cb88..4656df392722 100644
--- a/fs/nilfs2/bmap.h
+++ b/fs/nilfs2/bmap.h
@@ -44,6 +44,19 @@ struct nilfs_bmap_stats {
/**
* struct nilfs_bmap_operations - bmap operation table
+ * @bop_lookup: single block search operation
+ * @bop_lookup_contig: consecutive block search operation
+ * @bop_insert: block insertion operation
+ * @bop_delete: block delete operation
+ * @bop_clear: block mapping resource release operation
+ * @bop_propagate: operation to propagate dirty state towards the
+ * mapping root
+ * @bop_lookup_dirty_buffers: operation to collect dirty block buffers
+ * @bop_assign: disk block address assignment operation
+ * @bop_mark: operation to mark in-use blocks as dirty for
+ * relocation by GC
+ * @bop_seek_key: find valid block key operation
+ * @bop_last_key: find last valid block key operation
*/
struct nilfs_bmap_operations {
int (*bop_lookup)(const struct nilfs_bmap *, __u64, int, __u64 *);
@@ -66,7 +79,7 @@ struct nilfs_bmap_operations {
int (*bop_seek_key)(const struct nilfs_bmap *, __u64, __u64 *);
int (*bop_last_key)(const struct nilfs_bmap *, __u64 *);
- /* The following functions are internal use only. */
+ /* private: internal use only */
int (*bop_check_insert)(const struct nilfs_bmap *, __u64);
int (*bop_check_delete)(struct nilfs_bmap *, __u64);
int (*bop_gather_data)(struct nilfs_bmap *, __u64 *, __u64 *, int);
@@ -74,9 +87,8 @@ struct nilfs_bmap_operations {
#define NILFS_BMAP_SIZE (NILFS_INODE_BMAP_SIZE * sizeof(__le64))
-#define NILFS_BMAP_KEY_BIT (sizeof(unsigned long) * 8 /* CHAR_BIT */)
-#define NILFS_BMAP_NEW_PTR_INIT \
- (1UL << (sizeof(unsigned long) * 8 /* CHAR_BIT */ - 1))
+#define NILFS_BMAP_KEY_BIT BITS_PER_LONG
+#define NILFS_BMAP_NEW_PTR_INIT (1UL << (BITS_PER_LONG - 1))
static inline int nilfs_bmap_is_new_ptr(unsigned long ptr)
{
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index 3dda7c39089b..54a3fa0cf67e 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -73,13 +73,13 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
set_buffer_mapped(bh);
set_buffer_uptodate(bh);
- unlock_page(bh->b_page);
- put_page(bh->b_page);
+ folio_unlock(bh->b_folio);
+ folio_put(bh->b_folio);
return bh;
failed:
- unlock_page(bh->b_page);
- put_page(bh->b_page);
+ folio_unlock(bh->b_folio);
+ folio_put(bh->b_folio);
brelse(bh);
return ERR_PTR(-EIO);
}
@@ -90,7 +90,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
{
struct buffer_head *bh;
struct inode *inode = btnc->host;
- struct page *page;
+ struct folio *folio;
int err;
bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node));
@@ -98,7 +98,7 @@ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
return -ENOMEM;
err = -EEXIST; /* internal code */
- page = bh->b_page;
+ folio = bh->b_folio;
if (buffer_uptodate(bh) || buffer_dirty(bh))
goto found;
@@ -144,8 +144,8 @@ found:
*pbh = bh;
out_locked:
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
return err;
}
@@ -159,30 +159,51 @@ out_locked:
void nilfs_btnode_delete(struct buffer_head *bh)
{
struct address_space *mapping;
- struct page *page = bh->b_page;
- pgoff_t index = page_index(page);
+ struct folio *folio = bh->b_folio;
+ pgoff_t index = folio->index;
int still_dirty;
- get_page(page);
- lock_page(page);
- wait_on_page_writeback(page);
+ folio_get(folio);
+ folio_lock(folio);
+ folio_wait_writeback(folio);
nilfs_forget_buffer(bh);
- still_dirty = PageDirty(page);
- mapping = page->mapping;
- unlock_page(page);
- put_page(page);
+ still_dirty = folio_test_dirty(folio);
+ mapping = folio->mapping;
+ folio_unlock(folio);
+ folio_put(folio);
if (!still_dirty && mapping)
invalidate_inode_pages2_range(mapping, index, index);
}
/**
- * nilfs_btnode_prepare_change_key
- * prepare to move contents of the block for old key to one of new key.
- * the old buffer will not be removed, but might be reused for new buffer.
- * it might return -ENOMEM because of memory allocation errors,
- * and might return -EIO because of disk read errors.
+ * nilfs_btnode_prepare_change_key - prepare to change the search key of a
+ * b-tree node block
+ * @btnc: page cache in which the b-tree node block is buffered
+ * @ctxt: structure for exchanging context information for key change
+ *
+ * nilfs_btnode_prepare_change_key() prepares to move the contents of the
+ * b-tree node block of the old key given in the "oldkey" member of @ctxt to
+ * the position of the new key given in the "newkey" member of @ctxt in the
+ * page cache @btnc. Here, the key of the block is an index in units of
+ * blocks, and if the page and block sizes match, it matches the page index
+ * in the page cache.
+ *
+ * If the page size and block size match, this function attempts to move the
+ * entire folio, and in preparation for this, inserts the original folio into
+ * the new index of the cache. If this insertion fails or if the page size
+ * and block size are different, it falls back to a copy preparation using
+ * nilfs_btnode_create_block(), inserts a new block at the position
+ * corresponding to "newkey", and stores the buffer head pointer in the
+ * "newbh" member of @ctxt.
+ *
+ * Note that the current implementation does not support folio sizes larger
+ * than the page size.
+ *
+ * Return: 0 on success, or the following negative error code on failure.
+ * * %-EIO - I/O error (metadata corruption).
+ * * %-ENOMEM - Insufficient memory available.
*/
int nilfs_btnode_prepare_change_key(struct address_space *btnc,
struct nilfs_btnode_chkey_ctxt *ctxt)
@@ -199,23 +220,23 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc,
ctxt->newbh = NULL;
if (inode->i_blkbits == PAGE_SHIFT) {
- struct page *opage = obh->b_page;
- lock_page(opage);
+ struct folio *ofolio = obh->b_folio;
+ folio_lock(ofolio);
retry:
/* BUG_ON(oldkey != obh->b_folio->index); */
- if (unlikely(oldkey != opage->index))
- NILFS_PAGE_BUG(opage,
+ if (unlikely(oldkey != ofolio->index))
+ NILFS_FOLIO_BUG(ofolio,
"invalid oldkey %lld (newkey=%lld)",
(unsigned long long)oldkey,
(unsigned long long)newkey);
xa_lock_irq(&btnc->i_pages);
- err = __xa_insert(&btnc->i_pages, newkey, opage, GFP_NOFS);
+ err = __xa_insert(&btnc->i_pages, newkey, ofolio, GFP_NOFS);
xa_unlock_irq(&btnc->i_pages);
/*
- * Note: page->index will not change to newkey until
+ * Note: folio->index will not change to newkey until
* nilfs_btnode_commit_change_key() will be called.
- * To protect the page in intermediate state, the page lock
+ * To protect the folio in intermediate state, the folio lock
* is held.
*/
if (!err)
@@ -227,7 +248,7 @@ retry:
if (!err)
goto retry;
/* fallback to copy mode */
- unlock_page(opage);
+ folio_unlock(ofolio);
}
nbh = nilfs_btnode_create_block(btnc, newkey);
@@ -239,28 +260,41 @@ retry:
return 0;
failed_unlock:
- unlock_page(obh->b_page);
+ folio_unlock(obh->b_folio);
return err;
}
/**
- * nilfs_btnode_commit_change_key
- * commit the change_key operation prepared by prepare_change_key().
+ * nilfs_btnode_commit_change_key - commit the change of the search key of
+ * a b-tree node block
+ * @btnc: page cache in which the b-tree node block is buffered
+ * @ctxt: structure for exchanging context information for key change
+ *
+ * nilfs_btnode_commit_change_key() executes the key change based on the
+ * context @ctxt prepared by nilfs_btnode_prepare_change_key(). If no valid
+ * block buffer is prepared in "newbh" of @ctxt (i.e., a full folio move),
+ * this function removes the folio from the old index and completes the move.
+ * Otherwise, it copies the block data and inherited flag states of "oldbh"
+ * to "newbh" and clears the "oldbh" from the cache. In either case, the
+ * relocated buffer is marked as dirty.
+ *
+ * As with nilfs_btnode_prepare_change_key(), the current implementation does
+ * not support folio sizes larger than the page size.
*/
void nilfs_btnode_commit_change_key(struct address_space *btnc,
struct nilfs_btnode_chkey_ctxt *ctxt)
{
struct buffer_head *obh = ctxt->bh, *nbh = ctxt->newbh;
__u64 oldkey = ctxt->oldkey, newkey = ctxt->newkey;
- struct page *opage;
+ struct folio *ofolio;
if (oldkey == newkey)
return;
if (nbh == NULL) { /* blocksize == pagesize */
- opage = obh->b_page;
- if (unlikely(oldkey != opage->index))
- NILFS_PAGE_BUG(opage,
+ ofolio = obh->b_folio;
+ if (unlikely(oldkey != ofolio->index))
+ NILFS_FOLIO_BUG(ofolio,
"invalid oldkey %lld (newkey=%lld)",
(unsigned long long)oldkey,
(unsigned long long)newkey);
@@ -271,8 +305,8 @@ void nilfs_btnode_commit_change_key(struct address_space *btnc,
__xa_set_mark(&btnc->i_pages, newkey, PAGECACHE_TAG_DIRTY);
xa_unlock_irq(&btnc->i_pages);
- opage->index = obh->b_blocknr = newkey;
- unlock_page(opage);
+ ofolio->index = obh->b_blocknr = newkey;
+ folio_unlock(ofolio);
} else {
nilfs_copy_buffer(nbh, obh);
mark_buffer_dirty(nbh);
@@ -284,8 +318,19 @@ void nilfs_btnode_commit_change_key(struct address_space *btnc,
}
/**
- * nilfs_btnode_abort_change_key
- * abort the change_key operation prepared by prepare_change_key().
+ * nilfs_btnode_abort_change_key - abort the change of the search key of a
+ * b-tree node block
+ * @btnc: page cache in which the b-tree node block is buffered
+ * @ctxt: structure for exchanging context information for key change
+ *
+ * nilfs_btnode_abort_change_key() cancels the key change associated with the
+ * context @ctxt prepared via nilfs_btnode_prepare_change_key() and performs
+ * any necessary cleanup. If no valid block buffer is prepared in "newbh" of
+ * @ctxt, this function removes the folio from the destination index and aborts
+ * the move. Otherwise, it clears "newbh" from the cache.
+ *
+ * As with nilfs_btnode_prepare_change_key(), the current implementation does
+ * not support folio sizes larger than the page size.
*/
void nilfs_btnode_abort_change_key(struct address_space *btnc,
struct nilfs_btnode_chkey_ctxt *ctxt)
@@ -298,7 +343,7 @@ void nilfs_btnode_abort_change_key(struct address_space *btnc,
if (nbh == NULL) { /* blocksize == pagesize */
xa_erase_irq(&btnc->i_pages, newkey);
- unlock_page(ctxt->bh->b_page);
+ folio_unlock(ctxt->bh->b_folio);
} else {
/*
* When canceling a buffer that a prepare operation has
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index dbd27a44632f..9c51a4ac2627 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -1861,13 +1861,22 @@ nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree,
}
/**
- * nilfs_btree_convert_and_insert -
- * @bmap:
- * @key:
- * @ptr:
- * @keys:
- * @ptrs:
- * @n:
+ * nilfs_btree_convert_and_insert - Convert and insert entries into a B-tree
+ * @btree: NILFS B-tree structure
+ * @key: Key of the new entry to be inserted
+ * @ptr: Pointer (block number) associated with the key to be inserted
+ * @keys: Array of keys to be inserted in addition to @key
+ * @ptrs: Array of pointers associated with @keys
+ * @n: Number of keys and pointers in @keys and @ptrs
+ *
+ * This function is used to insert a new entry specified by @key and @ptr,
+ * along with additional entries specified by @keys and @ptrs arrays, into a
+ * NILFS B-tree.
+ * It prepares the necessary changes by allocating the required blocks and any
+ * necessary intermediate nodes. It converts configurations from other forms of
+ * block mapping (the one that currently exists is direct mapping) to a B-tree.
+ *
+ * Return: 0 on success or a negative error code on failure.
*/
int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree,
__u64 key, __u64 ptr,
@@ -2094,11 +2103,13 @@ static int nilfs_btree_propagate(struct nilfs_bmap *btree,
ret = nilfs_btree_do_lookup(btree, path, key, NULL, level + 1, 0);
if (ret < 0) {
- if (unlikely(ret == -ENOENT))
+ if (unlikely(ret == -ENOENT)) {
nilfs_crit(btree->b_inode->i_sb,
"writing node/leaf block does not appear in b-tree (ino=%lu) at key=%llu, level=%d",
btree->b_inode->i_ino,
(unsigned long long)key, level);
+ ret = -EINVAL;
+ }
goto out;
}
diff --git a/fs/nilfs2/btree.h b/fs/nilfs2/btree.h
index 92868e1a48ca..2a220f716c91 100644
--- a/fs/nilfs2/btree.h
+++ b/fs/nilfs2/btree.h
@@ -24,6 +24,7 @@
* @bp_index: index of child node
* @bp_oldreq: ptr end request for old ptr
* @bp_newreq: ptr alloc request for new ptr
+ * @bp_ctxt: context information for changing the key of a b-tree node block
* @bp_op: rebalance operation
*/
struct nilfs_btree_path {
diff --git a/fs/nilfs2/cpfile.c b/fs/nilfs2/cpfile.c
index 9ebefb3acb0e..f0ce37552446 100644
--- a/fs/nilfs2/cpfile.c
+++ b/fs/nilfs2/cpfile.c
@@ -28,7 +28,7 @@ nilfs_cpfile_get_blkoff(const struct inode *cpfile, __u64 cno)
{
__u64 tcno = cno + NILFS_MDT(cpfile)->mi_first_entry_offset - 1;
- do_div(tcno, nilfs_cpfile_checkpoints_per_block(cpfile));
+ tcno = div64_ul(tcno, nilfs_cpfile_checkpoints_per_block(cpfile));
return (unsigned long)tcno;
}
@@ -125,10 +125,17 @@ static void nilfs_cpfile_block_init(struct inode *cpfile,
}
}
-static inline int nilfs_cpfile_get_header_block(struct inode *cpfile,
- struct buffer_head **bhp)
+static int nilfs_cpfile_get_header_block(struct inode *cpfile,
+ struct buffer_head **bhp)
{
- return nilfs_mdt_get_block(cpfile, 0, 0, NULL, bhp);
+ int err = nilfs_mdt_get_block(cpfile, 0, 0, NULL, bhp);
+
+ if (unlikely(err == -ENOENT)) {
+ nilfs_error(cpfile->i_sb,
+ "missing header block in checkpoint metadata");
+ err = -EIO;
+ }
+ return err;
}
static inline int nilfs_cpfile_get_checkpoint_block(struct inode *cpfile,
@@ -187,35 +194,90 @@ static inline int nilfs_cpfile_delete_checkpoint_block(struct inode *cpfile,
}
/**
- * nilfs_cpfile_get_checkpoint - get a checkpoint
- * @cpfile: inode of checkpoint file
- * @cno: checkpoint number
- * @create: create flag
- * @cpp: pointer to a checkpoint
- * @bhp: pointer to a buffer head
- *
- * Description: nilfs_cpfile_get_checkpoint() acquires the checkpoint
- * specified by @cno. A new checkpoint will be created if @cno is the current
- * checkpoint number and @create is nonzero.
+ * nilfs_cpfile_read_checkpoint - read a checkpoint entry in cpfile
+ * @cpfile: checkpoint file inode
+ * @cno: number of checkpoint entry to read
+ * @root: nilfs root object
+ * @ifile: ifile's inode to read and attach to @root
*
- * Return Value: On success, 0 is returned, and the checkpoint and the
- * buffer head of the buffer on which the checkpoint is located are stored in
- * the place pointed by @cpp and @bhp, respectively. On error, one of the
- * following negative error codes is returned.
+ * This function imports checkpoint information from the checkpoint file and
+ * stores it to the inode file given by @ifile and the nilfs root object
+ * given by @root.
*
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * Return: 0 on success, or the following negative error code on failure.
+ * * %-EINVAL - Invalid checkpoint.
+ * * %-ENOMEM - Insufficient memory available.
+ * * %-EIO - I/O error (including metadata corruption).
+ */
+int nilfs_cpfile_read_checkpoint(struct inode *cpfile, __u64 cno,
+ struct nilfs_root *root, struct inode *ifile)
+{
+ struct buffer_head *cp_bh;
+ struct nilfs_checkpoint *cp;
+ void *kaddr;
+ int ret;
+
+ if (cno < 1 || cno > nilfs_mdt_cno(cpfile))
+ return -EINVAL;
+
+ down_read(&NILFS_MDT(cpfile)->mi_sem);
+ ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &cp_bh);
+ if (unlikely(ret < 0)) {
+ if (ret == -ENOENT)
+ ret = -EINVAL;
+ goto out_sem;
+ }
+
+ kaddr = kmap_local_page(cp_bh->b_page);
+ cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
+ if (nilfs_checkpoint_invalid(cp)) {
+ ret = -EINVAL;
+ goto put_cp;
+ }
+
+ ret = nilfs_read_inode_common(ifile, &cp->cp_ifile_inode);
+ if (unlikely(ret)) {
+ /*
+ * Since this inode is on a checkpoint entry, treat errors
+ * as metadata corruption.
+ */
+ nilfs_err(cpfile->i_sb,
+ "ifile inode (checkpoint number=%llu) corrupted",
+ (unsigned long long)cno);
+ ret = -EIO;
+ goto put_cp;
+ }
+
+ /* Configure the nilfs root object */
+ atomic64_set(&root->inodes_count, le64_to_cpu(cp->cp_inodes_count));
+ atomic64_set(&root->blocks_count, le64_to_cpu(cp->cp_blocks_count));
+ root->ifile = ifile;
+
+put_cp:
+ kunmap_local(kaddr);
+ brelse(cp_bh);
+out_sem:
+ up_read(&NILFS_MDT(cpfile)->mi_sem);
+ return ret;
+}
+
+/**
+ * nilfs_cpfile_create_checkpoint - create a checkpoint entry on cpfile
+ * @cpfile: checkpoint file inode
+ * @cno: number of checkpoint to set up
*
- * %-ENOENT - No such checkpoint.
+ * This function creates a checkpoint with the number specified by @cno on
+ * cpfile. If the specified checkpoint entry already exists due to a past
+ * failure, it will be reused without returning an error.
+ * In either case, the buffer of the block containing the checkpoint entry
+ * and the cpfile inode are made dirty for inclusion in the write log.
*
- * %-EINVAL - invalid checkpoint.
+ * Return: 0 on success, or the following negative error code on failure.
+ * * %-ENOMEM - Insufficient memory available.
+ * * %-EIO - I/O error (including metadata corruption).
+ * * %-EROFS - Read only filesystem
*/
-int nilfs_cpfile_get_checkpoint(struct inode *cpfile,
- __u64 cno,
- int create,
- struct nilfs_checkpoint **cpp,
- struct buffer_head **bhp)
+int nilfs_cpfile_create_checkpoint(struct inode *cpfile, __u64 cno)
{
struct buffer_head *header_bh, *cp_bh;
struct nilfs_cpfile_header *header;
@@ -223,70 +285,123 @@ int nilfs_cpfile_get_checkpoint(struct inode *cpfile,
void *kaddr;
int ret;
- if (unlikely(cno < 1 || cno > nilfs_mdt_cno(cpfile) ||
- (cno < nilfs_mdt_cno(cpfile) && create)))
- return -EINVAL;
+ if (WARN_ON_ONCE(cno < 1))
+ return -EIO;
down_write(&NILFS_MDT(cpfile)->mi_sem);
-
ret = nilfs_cpfile_get_header_block(cpfile, &header_bh);
- if (ret < 0)
+ if (unlikely(ret < 0))
goto out_sem;
- ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, create, &cp_bh);
- if (ret < 0)
+
+ ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 1, &cp_bh);
+ if (unlikely(ret < 0))
goto out_header;
- kaddr = kmap(cp_bh->b_page);
+
+ kaddr = kmap_local_page(cp_bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
if (nilfs_checkpoint_invalid(cp)) {
- if (!create) {
- kunmap(cp_bh->b_page);
- brelse(cp_bh);
- ret = -ENOENT;
- goto out_header;
- }
/* a newly-created checkpoint */
nilfs_checkpoint_clear_invalid(cp);
if (!nilfs_cpfile_is_in_first(cpfile, cno))
nilfs_cpfile_block_add_valid_checkpoints(cpfile, cp_bh,
kaddr, 1);
- mark_buffer_dirty(cp_bh);
+ kunmap_local(kaddr);
- kaddr = kmap_atomic(header_bh->b_page);
+ kaddr = kmap_local_page(header_bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, header_bh,
kaddr);
le64_add_cpu(&header->ch_ncheckpoints, 1);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
mark_buffer_dirty(header_bh);
- nilfs_mdt_mark_dirty(cpfile);
+ } else {
+ kunmap_local(kaddr);
}
- if (cpp != NULL)
- *cpp = cp;
- *bhp = cp_bh;
+ /* Force the buffer and the inode to become dirty */
+ mark_buffer_dirty(cp_bh);
+ brelse(cp_bh);
+ nilfs_mdt_mark_dirty(cpfile);
- out_header:
+out_header:
brelse(header_bh);
- out_sem:
+out_sem:
up_write(&NILFS_MDT(cpfile)->mi_sem);
return ret;
}
/**
- * nilfs_cpfile_put_checkpoint - put a checkpoint
- * @cpfile: inode of checkpoint file
- * @cno: checkpoint number
- * @bh: buffer head
+ * nilfs_cpfile_finalize_checkpoint - fill in a checkpoint entry in cpfile
+ * @cpfile: checkpoint file inode
+ * @cno: checkpoint number
+ * @root: nilfs root object
+ * @blkinc: number of blocks added by this checkpoint
+ * @ctime: checkpoint creation time
+ * @minor: minor checkpoint flag
*
- * Description: nilfs_cpfile_put_checkpoint() releases the checkpoint
- * specified by @cno. @bh must be the buffer head which has been returned by
- * a previous call to nilfs_cpfile_get_checkpoint() with @cno.
+ * This function completes the checkpoint entry numbered by @cno in the
+ * cpfile with the data given by the arguments @root, @blkinc, @ctime, and
+ * @minor.
+ *
+ * Return: 0 on success, or the following negative error code on failure.
+ * * %-ENOMEM - Insufficient memory available.
+ * * %-EIO - I/O error (including metadata corruption).
*/
-void nilfs_cpfile_put_checkpoint(struct inode *cpfile, __u64 cno,
- struct buffer_head *bh)
+int nilfs_cpfile_finalize_checkpoint(struct inode *cpfile, __u64 cno,
+ struct nilfs_root *root, __u64 blkinc,
+ time64_t ctime, bool minor)
{
- kunmap(bh->b_page);
- brelse(bh);
+ struct buffer_head *cp_bh;
+ struct nilfs_checkpoint *cp;
+ void *kaddr;
+ int ret;
+
+ if (WARN_ON_ONCE(cno < 1))
+ return -EIO;
+
+ down_write(&NILFS_MDT(cpfile)->mi_sem);
+ ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &cp_bh);
+ if (unlikely(ret < 0)) {
+ if (ret == -ENOENT)
+ goto error;
+ goto out_sem;
+ }
+
+ kaddr = kmap_local_page(cp_bh->b_page);
+ cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
+ if (unlikely(nilfs_checkpoint_invalid(cp))) {
+ kunmap_local(kaddr);
+ brelse(cp_bh);
+ goto error;
+ }
+
+ cp->cp_snapshot_list.ssl_next = 0;
+ cp->cp_snapshot_list.ssl_prev = 0;
+ cp->cp_inodes_count = cpu_to_le64(atomic64_read(&root->inodes_count));
+ cp->cp_blocks_count = cpu_to_le64(atomic64_read(&root->blocks_count));
+ cp->cp_nblk_inc = cpu_to_le64(blkinc);
+ cp->cp_create = cpu_to_le64(ctime);
+ cp->cp_cno = cpu_to_le64(cno);
+
+ if (minor)
+ nilfs_checkpoint_set_minor(cp);
+ else
+ nilfs_checkpoint_clear_minor(cp);
+
+ nilfs_write_inode_common(root->ifile, &cp->cp_ifile_inode);
+ nilfs_bmap_write(NILFS_I(root->ifile)->i_bmap, &cp->cp_ifile_inode);
+
+ kunmap_local(kaddr);
+ brelse(cp_bh);
+out_sem:
+ up_write(&NILFS_MDT(cpfile)->mi_sem);
+ return ret;
+
+error:
+ nilfs_error(cpfile->i_sb,
+ "checkpoint finalization failed due to metadata corruption.");
+ ret = -EIO;
+ goto out_sem;
}
/**
@@ -347,7 +462,7 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
continue;
}
- kaddr = kmap_atomic(cp_bh->b_page);
+ kaddr = kmap_local_page(cp_bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(
cpfile, cno, cp_bh, kaddr);
nicps = 0;
@@ -369,7 +484,7 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
cpfile, cp_bh, kaddr, nicps);
if (count == 0) {
/* make hole */
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(cp_bh);
ret =
nilfs_cpfile_delete_checkpoint_block(
@@ -384,18 +499,18 @@ int nilfs_cpfile_delete_checkpoints(struct inode *cpfile,
}
}
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(cp_bh);
}
if (tnicps > 0) {
- kaddr = kmap_atomic(header_bh->b_page);
+ kaddr = kmap_local_page(header_bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, header_bh,
kaddr);
le64_add_cpu(&header->ch_ncheckpoints, -(u64)tnicps);
mark_buffer_dirty(header_bh);
nilfs_mdt_mark_dirty(cpfile);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
}
brelse(header_bh);
@@ -447,7 +562,7 @@ static ssize_t nilfs_cpfile_do_get_cpinfo(struct inode *cpfile, __u64 *cnop,
}
ncps = nilfs_cpfile_checkpoints_in_block(cpfile, cno, cur_cno);
- kaddr = kmap_atomic(bh->b_page);
+ kaddr = kmap_local_page(bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, bh, kaddr);
for (i = 0; i < ncps && n < nci; i++, cp = (void *)cp + cpsz) {
if (!nilfs_checkpoint_invalid(cp)) {
@@ -457,7 +572,7 @@ static ssize_t nilfs_cpfile_do_get_cpinfo(struct inode *cpfile, __u64 *cnop,
n++;
}
}
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(bh);
}
@@ -491,10 +606,10 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
ret = nilfs_cpfile_get_header_block(cpfile, &bh);
if (ret < 0)
goto out;
- kaddr = kmap_atomic(bh->b_page);
+ kaddr = kmap_local_page(bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, bh, kaddr);
curr = le64_to_cpu(header->ch_snapshot_list.ssl_next);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(bh);
if (curr == 0) {
ret = 0;
@@ -512,7 +627,7 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
ret = 0; /* No snapshots (started from a hole block) */
goto out;
}
- kaddr = kmap_atomic(bh->b_page);
+ kaddr = kmap_local_page(bh->b_page);
while (n < nci) {
cp = nilfs_cpfile_block_get_checkpoint(cpfile, curr, bh, kaddr);
curr = ~(__u64)0; /* Terminator */
@@ -528,7 +643,7 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
next_blkoff = nilfs_cpfile_get_blkoff(cpfile, next);
if (curr_blkoff != next_blkoff) {
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(bh);
ret = nilfs_cpfile_get_checkpoint_block(cpfile, next,
0, &bh);
@@ -536,12 +651,12 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
WARN_ON(ret == -ENOENT);
goto out;
}
- kaddr = kmap_atomic(bh->b_page);
+ kaddr = kmap_local_page(bh->b_page);
}
curr = next;
curr_blkoff = next_blkoff;
}
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(bh);
*cnop = curr;
ret = n;
@@ -552,11 +667,29 @@ static ssize_t nilfs_cpfile_do_get_ssinfo(struct inode *cpfile, __u64 *cnop,
}
/**
- * nilfs_cpfile_get_cpinfo -
- * @cpfile:
- * @cno:
- * @ci:
- * @nci:
+ * nilfs_cpfile_get_cpinfo - get information on checkpoints
+ * @cpfile: checkpoint file inode
+ * @cnop: place to pass a starting checkpoint number and receive a
+ * checkpoint number to continue the search
+ * @mode: mode of checkpoints that the caller wants to retrieve
+ * @buf: buffer for storing checkpoints' information
+ * @cisz: byte size of one checkpoint info item in array
+ * @nci: number of checkpoint info items to retrieve
+ *
+ * nilfs_cpfile_get_cpinfo() searches for checkpoints in @mode state
+ * starting from the checkpoint number stored in @cnop, and stores
+ * information about found checkpoints in @buf.
+ * The buffer pointed to by @buf must be large enough to store information
+ * for @nci checkpoints. If at least one checkpoint information is
+ * successfully retrieved, @cnop is updated to point to the checkpoint
+ * number to continue searching.
+ *
+ * Return: Count of checkpoint info items stored in the output buffer on
+ * success, or the following negative error code on failure.
+ * * %-EINVAL - Invalid checkpoint mode.
+ * * %-ENOMEM - Insufficient memory available.
+ * * %-EIO - I/O error (including metadata corruption).
+ * * %-ENOENT - Invalid checkpoint number specified.
*/
ssize_t nilfs_cpfile_get_cpinfo(struct inode *cpfile, __u64 *cnop, int mode,
@@ -573,9 +706,15 @@ ssize_t nilfs_cpfile_get_cpinfo(struct inode *cpfile, __u64 *cnop, int mode,
}
/**
- * nilfs_cpfile_delete_checkpoint -
- * @cpfile:
- * @cno:
+ * nilfs_cpfile_delete_checkpoint - delete a checkpoint
+ * @cpfile: checkpoint file inode
+ * @cno: checkpoint number to delete
+ *
+ * Return: 0 on success, or the following negative error code on failure.
+ * * %-EBUSY - Checkpoint in use (snapshot specified).
+ * * %-EIO - I/O error (including metadata corruption).
+ * * %-ENOENT - No valid checkpoint found.
+ * * %-ENOMEM - Insufficient memory available.
*/
int nilfs_cpfile_delete_checkpoint(struct inode *cpfile, __u64 cno)
{
@@ -632,24 +771,24 @@ static int nilfs_cpfile_set_snapshot(struct inode *cpfile, __u64 cno)
ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &cp_bh);
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(cp_bh->b_page);
+ kaddr = kmap_local_page(cp_bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
if (nilfs_checkpoint_invalid(cp)) {
ret = -ENOENT;
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
goto out_cp;
}
if (nilfs_checkpoint_snapshot(cp)) {
ret = 0;
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
goto out_cp;
}
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
ret = nilfs_cpfile_get_header_block(cpfile, &header_bh);
if (ret < 0)
goto out_cp;
- kaddr = kmap_atomic(header_bh->b_page);
+ kaddr = kmap_local_page(header_bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, header_bh, kaddr);
list = &header->ch_snapshot_list;
curr_bh = header_bh;
@@ -661,13 +800,13 @@ static int nilfs_cpfile_set_snapshot(struct inode *cpfile, __u64 cno)
prev_blkoff = nilfs_cpfile_get_blkoff(cpfile, prev);
curr = prev;
if (curr_blkoff != prev_blkoff) {
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(curr_bh);
ret = nilfs_cpfile_get_checkpoint_block(cpfile, curr,
0, &curr_bh);
if (ret < 0)
goto out_header;
- kaddr = kmap_atomic(curr_bh->b_page);
+ kaddr = kmap_local_page(curr_bh->b_page);
}
curr_blkoff = prev_blkoff;
cp = nilfs_cpfile_block_get_checkpoint(
@@ -675,7 +814,7 @@ static int nilfs_cpfile_set_snapshot(struct inode *cpfile, __u64 cno)
list = &cp->cp_snapshot_list;
prev = le64_to_cpu(list->ssl_prev);
}
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
if (prev != 0) {
ret = nilfs_cpfile_get_checkpoint_block(cpfile, prev, 0,
@@ -687,29 +826,29 @@ static int nilfs_cpfile_set_snapshot(struct inode *cpfile, __u64 cno)
get_bh(prev_bh);
}
- kaddr = kmap_atomic(curr_bh->b_page);
+ kaddr = kmap_local_page(curr_bh->b_page);
list = nilfs_cpfile_block_get_snapshot_list(
cpfile, curr, curr_bh, kaddr);
list->ssl_prev = cpu_to_le64(cno);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
- kaddr = kmap_atomic(cp_bh->b_page);
+ kaddr = kmap_local_page(cp_bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
cp->cp_snapshot_list.ssl_next = cpu_to_le64(curr);
cp->cp_snapshot_list.ssl_prev = cpu_to_le64(prev);
nilfs_checkpoint_set_snapshot(cp);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
- kaddr = kmap_atomic(prev_bh->b_page);
+ kaddr = kmap_local_page(prev_bh->b_page);
list = nilfs_cpfile_block_get_snapshot_list(
cpfile, prev, prev_bh, kaddr);
list->ssl_next = cpu_to_le64(cno);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
- kaddr = kmap_atomic(header_bh->b_page);
+ kaddr = kmap_local_page(header_bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, header_bh, kaddr);
le64_add_cpu(&header->ch_nsnapshots, 1);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
mark_buffer_dirty(prev_bh);
mark_buffer_dirty(curr_bh);
@@ -750,23 +889,23 @@ static int nilfs_cpfile_clear_snapshot(struct inode *cpfile, __u64 cno)
ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &cp_bh);
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(cp_bh->b_page);
+ kaddr = kmap_local_page(cp_bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
if (nilfs_checkpoint_invalid(cp)) {
ret = -ENOENT;
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
goto out_cp;
}
if (!nilfs_checkpoint_snapshot(cp)) {
ret = 0;
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
goto out_cp;
}
list = &cp->cp_snapshot_list;
next = le64_to_cpu(list->ssl_next);
prev = le64_to_cpu(list->ssl_prev);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
ret = nilfs_cpfile_get_header_block(cpfile, &header_bh);
if (ret < 0)
@@ -790,29 +929,29 @@ static int nilfs_cpfile_clear_snapshot(struct inode *cpfile, __u64 cno)
get_bh(prev_bh);
}
- kaddr = kmap_atomic(next_bh->b_page);
+ kaddr = kmap_local_page(next_bh->b_page);
list = nilfs_cpfile_block_get_snapshot_list(
cpfile, next, next_bh, kaddr);
list->ssl_prev = cpu_to_le64(prev);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
- kaddr = kmap_atomic(prev_bh->b_page);
+ kaddr = kmap_local_page(prev_bh->b_page);
list = nilfs_cpfile_block_get_snapshot_list(
cpfile, prev, prev_bh, kaddr);
list->ssl_next = cpu_to_le64(next);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
- kaddr = kmap_atomic(cp_bh->b_page);
+ kaddr = kmap_local_page(cp_bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, cp_bh, kaddr);
cp->cp_snapshot_list.ssl_next = cpu_to_le64(0);
cp->cp_snapshot_list.ssl_prev = cpu_to_le64(0);
nilfs_checkpoint_clear_snapshot(cp);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
- kaddr = kmap_atomic(header_bh->b_page);
+ kaddr = kmap_local_page(header_bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, header_bh, kaddr);
le64_add_cpu(&header->ch_nsnapshots, -1);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
mark_buffer_dirty(next_bh);
mark_buffer_dirty(prev_bh);
@@ -837,21 +976,15 @@ static int nilfs_cpfile_clear_snapshot(struct inode *cpfile, __u64 cno)
}
/**
- * nilfs_cpfile_is_snapshot -
+ * nilfs_cpfile_is_snapshot - determine if checkpoint is a snapshot
* @cpfile: inode of checkpoint file
- * @cno: checkpoint number
- *
- * Description:
- *
- * Return Value: On success, 1 is returned if the checkpoint specified by
- * @cno is a snapshot, or 0 if not. On error, one of the following negative
- * error codes is returned.
+ * @cno: checkpoint number
*
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
- *
- * %-ENOENT - No such checkpoint.
+ * Return: 1 if the checkpoint specified by @cno is a snapshot, 0 if not, or
+ * the following negative error code on failure.
+ * * %-EIO - I/O error (including metadata corruption).
+ * * %-ENOENT - No such checkpoint.
+ * * %-ENOMEM - Insufficient memory available.
*/
int nilfs_cpfile_is_snapshot(struct inode *cpfile, __u64 cno)
{
@@ -871,13 +1004,13 @@ int nilfs_cpfile_is_snapshot(struct inode *cpfile, __u64 cno)
ret = nilfs_cpfile_get_checkpoint_block(cpfile, cno, 0, &bh);
if (ret < 0)
goto out;
- kaddr = kmap_atomic(bh->b_page);
+ kaddr = kmap_local_page(bh->b_page);
cp = nilfs_cpfile_block_get_checkpoint(cpfile, cno, bh, kaddr);
if (nilfs_checkpoint_invalid(cp))
ret = -ENOENT;
else
ret = nilfs_checkpoint_snapshot(cp);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(bh);
out:
@@ -954,12 +1087,12 @@ int nilfs_cpfile_get_stat(struct inode *cpfile, struct nilfs_cpstat *cpstat)
ret = nilfs_cpfile_get_header_block(cpfile, &bh);
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(bh->b_page);
+ kaddr = kmap_local_page(bh->b_page);
header = nilfs_cpfile_block_get_header(cpfile, bh, kaddr);
cpstat->cs_cno = nilfs_mdt_cno(cpfile);
cpstat->cs_ncps = le64_to_cpu(header->ch_ncheckpoints);
cpstat->cs_nsss = le64_to_cpu(header->ch_nsnapshots);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(bh);
out_sem:
diff --git a/fs/nilfs2/cpfile.h b/fs/nilfs2/cpfile.h
index edabb2dc5756..f5b1d59289eb 100644
--- a/fs/nilfs2/cpfile.h
+++ b/fs/nilfs2/cpfile.h
@@ -16,10 +16,12 @@
#include <linux/nilfs2_ondisk.h> /* nilfs_inode, nilfs_checkpoint */
-int nilfs_cpfile_get_checkpoint(struct inode *, __u64, int,
- struct nilfs_checkpoint **,
- struct buffer_head **);
-void nilfs_cpfile_put_checkpoint(struct inode *, __u64, struct buffer_head *);
+int nilfs_cpfile_read_checkpoint(struct inode *cpfile, __u64 cno,
+ struct nilfs_root *root, struct inode *ifile);
+int nilfs_cpfile_create_checkpoint(struct inode *cpfile, __u64 cno);
+int nilfs_cpfile_finalize_checkpoint(struct inode *cpfile, __u64 cno,
+ struct nilfs_root *root, __u64 blkinc,
+ time64_t ctime, bool minor);
int nilfs_cpfile_delete_checkpoints(struct inode *, __u64, __u64);
int nilfs_cpfile_delete_checkpoint(struct inode *, __u64);
int nilfs_cpfile_change_cpmode(struct inode *, __u64, int);
diff --git a/fs/nilfs2/dat.c b/fs/nilfs2/dat.c
index 351010828d88..0bef662176a4 100644
--- a/fs/nilfs2/dat.c
+++ b/fs/nilfs2/dat.c
@@ -91,13 +91,13 @@ void nilfs_dat_commit_alloc(struct inode *dat, struct nilfs_palloc_req *req)
struct nilfs_dat_entry *entry;
void *kaddr;
- kaddr = kmap_atomic(req->pr_entry_bh->b_page);
+ kaddr = kmap_local_page(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
entry->de_start = cpu_to_le64(NILFS_CNO_MIN);
entry->de_end = cpu_to_le64(NILFS_CNO_MAX);
entry->de_blocknr = cpu_to_le64(0);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
nilfs_palloc_commit_alloc_entry(dat, req);
nilfs_dat_commit_entry(dat, req);
@@ -115,13 +115,13 @@ static void nilfs_dat_commit_free(struct inode *dat,
struct nilfs_dat_entry *entry;
void *kaddr;
- kaddr = kmap_atomic(req->pr_entry_bh->b_page);
+ kaddr = kmap_local_page(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
entry->de_start = cpu_to_le64(NILFS_CNO_MIN);
entry->de_end = cpu_to_le64(NILFS_CNO_MIN);
entry->de_blocknr = cpu_to_le64(0);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
nilfs_dat_commit_entry(dat, req);
@@ -145,12 +145,12 @@ void nilfs_dat_commit_start(struct inode *dat, struct nilfs_palloc_req *req,
struct nilfs_dat_entry *entry;
void *kaddr;
- kaddr = kmap_atomic(req->pr_entry_bh->b_page);
+ kaddr = kmap_local_page(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
entry->de_start = cpu_to_le64(nilfs_mdt_cno(dat));
entry->de_blocknr = cpu_to_le64(blocknr);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
nilfs_dat_commit_entry(dat, req);
}
@@ -167,12 +167,12 @@ int nilfs_dat_prepare_end(struct inode *dat, struct nilfs_palloc_req *req)
if (ret < 0)
return ret;
- kaddr = kmap_atomic(req->pr_entry_bh->b_page);
+ kaddr = kmap_local_page(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
start = le64_to_cpu(entry->de_start);
blocknr = le64_to_cpu(entry->de_blocknr);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
if (blocknr == 0) {
ret = nilfs_palloc_prepare_free_entry(dat, req);
@@ -202,7 +202,7 @@ void nilfs_dat_commit_end(struct inode *dat, struct nilfs_palloc_req *req,
sector_t blocknr;
void *kaddr;
- kaddr = kmap_atomic(req->pr_entry_bh->b_page);
+ kaddr = kmap_local_page(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
end = start = le64_to_cpu(entry->de_start);
@@ -212,7 +212,7 @@ void nilfs_dat_commit_end(struct inode *dat, struct nilfs_palloc_req *req,
}
entry->de_end = cpu_to_le64(end);
blocknr = le64_to_cpu(entry->de_blocknr);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
if (blocknr == 0)
nilfs_dat_commit_free(dat, req);
@@ -227,12 +227,12 @@ void nilfs_dat_abort_end(struct inode *dat, struct nilfs_palloc_req *req)
sector_t blocknr;
void *kaddr;
- kaddr = kmap_atomic(req->pr_entry_bh->b_page);
+ kaddr = kmap_local_page(req->pr_entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, req->pr_entry_nr,
req->pr_entry_bh, kaddr);
start = le64_to_cpu(entry->de_start);
blocknr = le64_to_cpu(entry->de_blocknr);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
if (start == nilfs_mdt_cno(dat) && blocknr == 0)
nilfs_palloc_abort_free_entry(dat, req);
@@ -271,18 +271,15 @@ void nilfs_dat_abort_update(struct inode *dat,
}
/**
- * nilfs_dat_mark_dirty -
- * @dat: DAT file inode
+ * nilfs_dat_mark_dirty - mark the DAT block buffer containing the specified
+ * virtual block address entry as dirty
+ * @dat: DAT file inode
* @vblocknr: virtual block number
*
- * Description:
- *
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * Return: 0 on success, or the following negative error code on failure.
+ * * %-EINVAL - Invalid DAT entry (internal code).
+ * * %-EIO - I/O error (including metadata corruption).
+ * * %-ENOMEM - Insufficient memory available.
*/
int nilfs_dat_mark_dirty(struct inode *dat, __u64 vblocknr)
{
@@ -362,7 +359,7 @@ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr)
}
}
- kaddr = kmap_atomic(entry_bh->b_page);
+ kaddr = kmap_local_page(entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, vblocknr, entry_bh, kaddr);
if (unlikely(entry->de_blocknr == cpu_to_le64(0))) {
nilfs_crit(dat->i_sb,
@@ -370,13 +367,13 @@ int nilfs_dat_move(struct inode *dat, __u64 vblocknr, sector_t blocknr)
__func__, (unsigned long long)vblocknr,
(unsigned long long)le64_to_cpu(entry->de_start),
(unsigned long long)le64_to_cpu(entry->de_end));
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(entry_bh);
return -EINVAL;
}
WARN_ON(blocknr == 0);
entry->de_blocknr = cpu_to_le64(blocknr);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
mark_buffer_dirty(entry_bh);
nilfs_mdt_mark_dirty(dat);
@@ -426,7 +423,7 @@ int nilfs_dat_translate(struct inode *dat, __u64 vblocknr, sector_t *blocknrp)
}
}
- kaddr = kmap_atomic(entry_bh->b_page);
+ kaddr = kmap_local_page(entry_bh->b_page);
entry = nilfs_palloc_block_get_entry(dat, vblocknr, entry_bh, kaddr);
blocknr = le64_to_cpu(entry->de_blocknr);
if (blocknr == 0) {
@@ -436,7 +433,7 @@ int nilfs_dat_translate(struct inode *dat, __u64 vblocknr, sector_t *blocknrp)
*blocknrp = blocknr;
out:
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(entry_bh);
return ret;
}
@@ -457,10 +454,10 @@ ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned int visz,
0, &entry_bh);
if (ret < 0)
return ret;
- kaddr = kmap_atomic(entry_bh->b_page);
+ kaddr = kmap_local_page(entry_bh->b_page);
/* last virtual block number in this block */
first = vinfo->vi_vblocknr;
- do_div(first, entries_per_block);
+ first = div64_ul(first, entries_per_block);
first *= entries_per_block;
last = first + entries_per_block - 1;
for (j = i, n = 0;
@@ -473,7 +470,7 @@ ssize_t nilfs_dat_get_vinfo(struct inode *dat, void *buf, unsigned int visz,
vinfo->vi_end = le64_to_cpu(entry->de_end);
vinfo->vi_blocknr = le64_to_cpu(entry->de_blocknr);
}
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(entry_bh);
}
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index 652279c8b168..0cc32e9c71cb 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -64,12 +64,6 @@ static inline unsigned int nilfs_chunk_size(struct inode *inode)
return inode->i_sb->s_blocksize;
}
-static inline void nilfs_put_page(struct page *page)
-{
- kunmap(page);
- put_page(page);
-}
-
/*
* Return the offset into page `page_nr' of the last valid
* byte in that page, plus one.
@@ -84,48 +78,46 @@ static unsigned int nilfs_last_byte(struct inode *inode, unsigned long page_nr)
return last_byte;
}
-static int nilfs_prepare_chunk(struct page *page, unsigned int from,
+static int nilfs_prepare_chunk(struct folio *folio, unsigned int from,
unsigned int to)
{
- loff_t pos = page_offset(page) + from;
+ loff_t pos = folio_pos(folio) + from;
- return __block_write_begin(page, pos, to - from, nilfs_get_block);
+ return __block_write_begin(folio, pos, to - from, nilfs_get_block);
}
-static void nilfs_commit_chunk(struct page *page,
- struct address_space *mapping,
- unsigned int from, unsigned int to)
+static void nilfs_commit_chunk(struct folio *folio,
+ struct address_space *mapping, size_t from, size_t to)
{
struct inode *dir = mapping->host;
- loff_t pos = page_offset(page) + from;
- unsigned int len = to - from;
- unsigned int nr_dirty, copied;
+ loff_t pos = folio_pos(folio) + from;
+ size_t copied, len = to - from;
+ unsigned int nr_dirty;
int err;
- nr_dirty = nilfs_page_count_clean_buffers(page, from, to);
- copied = block_write_end(NULL, mapping, pos, len, len, page, NULL);
+ nr_dirty = nilfs_page_count_clean_buffers(&folio->page, from, to);
+ copied = block_write_end(NULL, mapping, pos, len, len, folio, NULL);
if (pos + copied > dir->i_size)
i_size_write(dir, pos + copied);
if (IS_DIRSYNC(dir))
nilfs_set_transaction_flag(NILFS_TI_SYNC);
err = nilfs_set_file_dirty(dir, nr_dirty);
WARN_ON(err); /* do not happen */
- unlock_page(page);
+ folio_unlock(folio);
}
-static bool nilfs_check_page(struct page *page)
+static bool nilfs_check_folio(struct folio *folio, char *kaddr)
{
- struct inode *dir = page->mapping->host;
+ struct inode *dir = folio->mapping->host;
struct super_block *sb = dir->i_sb;
unsigned int chunk_size = nilfs_chunk_size(dir);
- char *kaddr = page_address(page);
- unsigned int offs, rec_len;
- unsigned int limit = PAGE_SIZE;
+ size_t offs, rec_len;
+ size_t limit = folio_size(folio);
struct nilfs_dir_entry *p;
char *error;
- if ((dir->i_size >> PAGE_SHIFT) == page->index) {
- limit = dir->i_size & ~PAGE_MASK;
+ if (dir->i_size < folio_pos(folio) + limit) {
+ limit = dir->i_size - folio_pos(folio);
if (limit & (chunk_size - 1))
goto Ebadsize;
if (!limit)
@@ -150,7 +142,7 @@ static bool nilfs_check_page(struct page *page)
if (offs != limit)
goto Eend;
out:
- SetPageChecked(page);
+ folio_set_checked(folio);
return true;
/* Too bad, we had an error */
@@ -176,8 +168,8 @@ Einumber:
error = "disallowed inode number";
bad_entry:
nilfs_error(sb,
- "bad entry in directory #%lu: %s - offset=%lu, inode=%lu, rec_len=%d, name_len=%d",
- dir->i_ino, error, (page->index << PAGE_SHIFT) + offs,
+ "bad entry in directory #%lu: %s - offset=%lu, inode=%lu, rec_len=%zd, name_len=%d",
+ dir->i_ino, error, (folio->index << PAGE_SHIFT) + offs,
(unsigned long)le64_to_cpu(p->inode),
rec_len, p->name_len);
goto fail;
@@ -185,34 +177,33 @@ Eend:
p = (struct nilfs_dir_entry *)(kaddr + offs);
nilfs_error(sb,
"entry in directory #%lu spans the page boundary offset=%lu, inode=%lu",
- dir->i_ino, (page->index << PAGE_SHIFT) + offs,
+ dir->i_ino, (folio->index << PAGE_SHIFT) + offs,
(unsigned long)le64_to_cpu(p->inode));
fail:
- SetPageError(page);
return false;
}
-static void *nilfs_get_page(struct inode *dir, unsigned long n,
- struct page **pagep)
+static void *nilfs_get_folio(struct inode *dir, unsigned long n,
+ struct folio **foliop)
{
struct address_space *mapping = dir->i_mapping;
- struct page *page = read_mapping_page(mapping, n, NULL);
+ struct folio *folio = read_mapping_folio(mapping, n, NULL);
void *kaddr;
- if (IS_ERR(page))
- return page;
+ if (IS_ERR(folio))
+ return folio;
- kaddr = kmap(page);
- if (unlikely(!PageChecked(page))) {
- if (!nilfs_check_page(page))
+ kaddr = kmap_local_folio(folio, 0);
+ if (unlikely(!folio_test_checked(folio))) {
+ if (!nilfs_check_folio(folio, kaddr))
goto fail;
}
- *pagep = page;
+ *foliop = folio;
return kaddr;
fail:
- nilfs_put_page(page);
+ folio_release_kmap(folio, kaddr);
return ERR_PTR(-EIO);
}
@@ -240,37 +231,6 @@ static struct nilfs_dir_entry *nilfs_next_entry(struct nilfs_dir_entry *p)
nilfs_rec_len_from_disk(p->rec_len));
}
-static unsigned char
-nilfs_filetype_table[NILFS_FT_MAX] = {
- [NILFS_FT_UNKNOWN] = DT_UNKNOWN,
- [NILFS_FT_REG_FILE] = DT_REG,
- [NILFS_FT_DIR] = DT_DIR,
- [NILFS_FT_CHRDEV] = DT_CHR,
- [NILFS_FT_BLKDEV] = DT_BLK,
- [NILFS_FT_FIFO] = DT_FIFO,
- [NILFS_FT_SOCK] = DT_SOCK,
- [NILFS_FT_SYMLINK] = DT_LNK,
-};
-
-#define S_SHIFT 12
-static unsigned char
-nilfs_type_by_mode[(S_IFMT >> S_SHIFT) + 1] = {
- [S_IFREG >> S_SHIFT] = NILFS_FT_REG_FILE,
- [S_IFDIR >> S_SHIFT] = NILFS_FT_DIR,
- [S_IFCHR >> S_SHIFT] = NILFS_FT_CHRDEV,
- [S_IFBLK >> S_SHIFT] = NILFS_FT_BLKDEV,
- [S_IFIFO >> S_SHIFT] = NILFS_FT_FIFO,
- [S_IFSOCK >> S_SHIFT] = NILFS_FT_SOCK,
- [S_IFLNK >> S_SHIFT] = NILFS_FT_SYMLINK,
-};
-
-static void nilfs_set_de_type(struct nilfs_dir_entry *de, struct inode *inode)
-{
- umode_t mode = inode->i_mode;
-
- de->file_type = nilfs_type_by_mode[(mode & S_IFMT)>>S_SHIFT];
-}
-
static int nilfs_readdir(struct file *file, struct dir_context *ctx)
{
loff_t pos = ctx->pos;
@@ -286,9 +246,9 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx)
for ( ; n < npages; n++, offset = 0) {
char *kaddr, *limit;
struct nilfs_dir_entry *de;
- struct page *page;
+ struct folio *folio;
- kaddr = nilfs_get_page(inode, n, &page);
+ kaddr = nilfs_get_folio(inode, n, &folio);
if (IS_ERR(kaddr)) {
nilfs_error(sb, "bad page in #%lu", inode->i_ino);
ctx->pos += PAGE_SIZE - offset;
@@ -300,65 +260,57 @@ static int nilfs_readdir(struct file *file, struct dir_context *ctx)
for ( ; (char *)de <= limit; de = nilfs_next_entry(de)) {
if (de->rec_len == 0) {
nilfs_error(sb, "zero-length directory entry");
- nilfs_put_page(page);
+ folio_release_kmap(folio, kaddr);
return -EIO;
}
if (de->inode) {
unsigned char t;
- if (de->file_type < NILFS_FT_MAX)
- t = nilfs_filetype_table[de->file_type];
- else
- t = DT_UNKNOWN;
+ t = fs_ftype_to_dtype(de->file_type);
if (!dir_emit(ctx, de->name, de->name_len,
le64_to_cpu(de->inode), t)) {
- nilfs_put_page(page);
+ folio_release_kmap(folio, kaddr);
return 0;
}
}
ctx->pos += nilfs_rec_len_from_disk(de->rec_len);
}
- nilfs_put_page(page);
+ folio_release_kmap(folio, kaddr);
}
return 0;
}
/*
- * nilfs_find_entry()
+ * nilfs_find_entry()
*
- * finds an entry in the specified directory with the wanted name. It
- * returns the page in which the entry was found, and the entry itself
- * (as a parameter - res_dir). Page is returned mapped and unlocked.
- * Entry is guaranteed to be valid.
+ * Finds an entry in the specified directory with the wanted name. It
+ * returns the folio in which the entry was found, and the entry itself.
+ * The folio is mapped and unlocked. When the caller is finished with
+ * the entry, it should call folio_release_kmap().
*
- * On failure, returns an error pointer and the caller should ignore res_page.
+ * On failure, returns an error pointer and the caller should ignore foliop.
*/
-struct nilfs_dir_entry *
-nilfs_find_entry(struct inode *dir, const struct qstr *qstr,
- struct page **res_page)
+struct nilfs_dir_entry *nilfs_find_entry(struct inode *dir,
+ const struct qstr *qstr, struct folio **foliop)
{
const unsigned char *name = qstr->name;
int namelen = qstr->len;
unsigned int reclen = NILFS_DIR_REC_LEN(namelen);
unsigned long start, n;
unsigned long npages = dir_pages(dir);
- struct page *page = NULL;
struct nilfs_inode_info *ei = NILFS_I(dir);
struct nilfs_dir_entry *de;
if (npages == 0)
goto out;
- /* OFFSET_CACHE */
- *res_page = NULL;
-
start = ei->i_dir_start_lookup;
if (start >= npages)
start = 0;
n = start;
do {
- char *kaddr = nilfs_get_page(dir, n, &page);
+ char *kaddr = nilfs_get_folio(dir, n, foliop);
if (IS_ERR(kaddr))
return ERR_CAST(kaddr);
@@ -369,18 +321,18 @@ nilfs_find_entry(struct inode *dir, const struct qstr *qstr,
if (de->rec_len == 0) {
nilfs_error(dir->i_sb,
"zero-length directory entry");
- nilfs_put_page(page);
+ folio_release_kmap(*foliop, kaddr);
goto out;
}
if (nilfs_match(namelen, name, de))
goto found;
de = nilfs_next_entry(de);
}
- nilfs_put_page(page);
+ folio_release_kmap(*foliop, kaddr);
if (++n >= npages)
n = 0;
- /* next page is past the blocks we've got */
+ /* next folio is past the blocks we've got */
if (unlikely(n > (dir->i_blocks >> (PAGE_SHIFT - 9)))) {
nilfs_error(dir->i_sb,
"dir %lu size %lld exceeds block count %llu",
@@ -393,19 +345,18 @@ out:
return ERR_PTR(-ENOENT);
found:
- *res_page = page;
ei->i_dir_start_lookup = n;
return de;
}
-struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct page **p)
+struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct folio **foliop)
{
- struct page *page;
+ struct folio *folio;
struct nilfs_dir_entry *de, *next_de;
size_t limit;
char *msg;
- de = nilfs_get_page(dir, 0, &page);
+ de = nilfs_get_folio(dir, 0, &folio);
if (IS_ERR(de))
return NULL;
@@ -426,47 +377,48 @@ struct nilfs_dir_entry *nilfs_dotdot(struct inode *dir, struct page **p)
msg = "missing '..'";
goto fail;
}
- *p = page;
+ *foliop = folio;
return next_de;
fail:
nilfs_error(dir->i_sb, "directory #%lu %s", dir->i_ino, msg);
- nilfs_put_page(page);
+ folio_release_kmap(folio, de);
return NULL;
}
int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino)
{
struct nilfs_dir_entry *de;
- struct page *page;
+ struct folio *folio;
- de = nilfs_find_entry(dir, qstr, &page);
+ de = nilfs_find_entry(dir, qstr, &folio);
if (IS_ERR(de))
return PTR_ERR(de);
*ino = le64_to_cpu(de->inode);
- kunmap(page);
- put_page(page);
+ folio_release_kmap(folio, de);
return 0;
}
-/* Releases the page */
-void nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de,
- struct page *page, struct inode *inode)
+int nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de,
+ struct folio *folio, struct inode *inode)
{
- unsigned int from = (char *)de - (char *)page_address(page);
- unsigned int to = from + nilfs_rec_len_from_disk(de->rec_len);
- struct address_space *mapping = page->mapping;
+ size_t from = offset_in_folio(folio, de);
+ size_t to = from + nilfs_rec_len_from_disk(de->rec_len);
+ struct address_space *mapping = folio->mapping;
int err;
- lock_page(page);
- err = nilfs_prepare_chunk(page, from, to);
- BUG_ON(err);
+ folio_lock(folio);
+ err = nilfs_prepare_chunk(folio, from, to);
+ if (unlikely(err)) {
+ folio_unlock(folio);
+ return err;
+ }
de->inode = cpu_to_le64(inode->i_ino);
- nilfs_set_de_type(de, inode);
- nilfs_commit_chunk(page, mapping, from, to);
- nilfs_put_page(page);
- dir->i_mtime = inode_set_ctime_current(dir);
+ de->file_type = fs_umode_to_ftype(inode->i_mode);
+ nilfs_commit_chunk(folio, mapping, from, to);
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
+ return 0;
}
/*
@@ -480,30 +432,28 @@ int nilfs_add_link(struct dentry *dentry, struct inode *inode)
unsigned int chunk_size = nilfs_chunk_size(dir);
unsigned int reclen = NILFS_DIR_REC_LEN(namelen);
unsigned short rec_len, name_len;
- struct page *page = NULL;
+ struct folio *folio = NULL;
struct nilfs_dir_entry *de;
unsigned long npages = dir_pages(dir);
unsigned long n;
- char *kaddr;
- unsigned int from, to;
+ size_t from, to;
int err;
/*
* We take care of directory expansion in the same loop.
- * This code plays outside i_size, so it locks the page
+ * This code plays outside i_size, so it locks the folio
* to protect that region.
*/
for (n = 0; n <= npages; n++) {
+ char *kaddr = nilfs_get_folio(dir, n, &folio);
char *dir_end;
- kaddr = nilfs_get_page(dir, n, &page);
- err = PTR_ERR(kaddr);
if (IS_ERR(kaddr))
- goto out;
- lock_page(page);
+ return PTR_ERR(kaddr);
+ folio_lock(folio);
dir_end = kaddr + nilfs_last_byte(dir, n);
de = (struct nilfs_dir_entry *)kaddr;
- kaddr += PAGE_SIZE - reclen;
+ kaddr += folio_size(folio) - reclen;
while ((char *)de <= kaddr) {
if ((char *)de == dir_end) {
/* We hit i_size */
@@ -530,16 +480,16 @@ int nilfs_add_link(struct dentry *dentry, struct inode *inode)
goto got_it;
de = (struct nilfs_dir_entry *)((char *)de + rec_len);
}
- unlock_page(page);
- nilfs_put_page(page);
+ folio_unlock(folio);
+ folio_release_kmap(folio, kaddr);
}
BUG();
return -EINVAL;
got_it:
- from = (char *)de - (char *)page_address(page);
+ from = offset_in_folio(folio, de);
to = from + rec_len;
- err = nilfs_prepare_chunk(page, from, to);
+ err = nilfs_prepare_chunk(folio, from, to);
if (err)
goto out_unlock;
if (de->inode) {
@@ -553,30 +503,29 @@ got_it:
de->name_len = namelen;
memcpy(de->name, name, namelen);
de->inode = cpu_to_le64(inode->i_ino);
- nilfs_set_de_type(de, inode);
- nilfs_commit_chunk(page, page->mapping, from, to);
- dir->i_mtime = inode_set_ctime_current(dir);
+ de->file_type = fs_umode_to_ftype(inode->i_mode);
+ nilfs_commit_chunk(folio, folio->mapping, from, to);
+ inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir));
nilfs_mark_inode_dirty(dir);
/* OFFSET_CACHE */
out_put:
- nilfs_put_page(page);
-out:
+ folio_release_kmap(folio, de);
return err;
out_unlock:
- unlock_page(page);
+ folio_unlock(folio);
goto out_put;
}
/*
* nilfs_delete_entry deletes a directory entry by merging it with the
- * previous entry. Page is up-to-date. Releases the page.
+ * previous entry. Folio is up-to-date.
*/
-int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct page *page)
+int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct folio *folio)
{
- struct address_space *mapping = page->mapping;
+ struct address_space *mapping = folio->mapping;
struct inode *inode = mapping->host;
- char *kaddr = page_address(page);
- unsigned int from, to;
+ char *kaddr = (char *)((unsigned long)dir & ~(folio_size(folio) - 1));
+ size_t from, to;
struct nilfs_dir_entry *de, *pde = NULL;
int err;
@@ -595,17 +544,19 @@ int nilfs_delete_entry(struct nilfs_dir_entry *dir, struct page *page)
de = nilfs_next_entry(de);
}
if (pde)
- from = (char *)pde - (char *)page_address(page);
- lock_page(page);
- err = nilfs_prepare_chunk(page, from, to);
- BUG_ON(err);
+ from = (char *)pde - kaddr;
+ folio_lock(folio);
+ err = nilfs_prepare_chunk(folio, from, to);
+ if (unlikely(err)) {
+ folio_unlock(folio);
+ goto out;
+ }
if (pde)
pde->rec_len = nilfs_rec_len_to_disk(to - from);
dir->inode = 0;
- nilfs_commit_chunk(page, mapping, from, to);
- inode->i_mtime = inode_set_ctime_current(inode);
+ nilfs_commit_chunk(folio, mapping, from, to);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
out:
- nilfs_put_page(page);
return err;
}
@@ -615,39 +566,39 @@ out:
int nilfs_make_empty(struct inode *inode, struct inode *parent)
{
struct address_space *mapping = inode->i_mapping;
- struct page *page = grab_cache_page(mapping, 0);
+ struct folio *folio = filemap_grab_folio(mapping, 0);
unsigned int chunk_size = nilfs_chunk_size(inode);
struct nilfs_dir_entry *de;
int err;
void *kaddr;
- if (!page)
- return -ENOMEM;
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
- err = nilfs_prepare_chunk(page, 0, chunk_size);
+ err = nilfs_prepare_chunk(folio, 0, chunk_size);
if (unlikely(err)) {
- unlock_page(page);
+ folio_unlock(folio);
goto fail;
}
- kaddr = kmap_atomic(page);
+ kaddr = kmap_local_folio(folio, 0);
memset(kaddr, 0, chunk_size);
de = (struct nilfs_dir_entry *)kaddr;
de->name_len = 1;
de->rec_len = nilfs_rec_len_to_disk(NILFS_DIR_REC_LEN(1));
memcpy(de->name, ".\0\0", 4);
de->inode = cpu_to_le64(inode->i_ino);
- nilfs_set_de_type(de, inode);
+ de->file_type = fs_umode_to_ftype(inode->i_mode);
de = (struct nilfs_dir_entry *)(kaddr + NILFS_DIR_REC_LEN(1));
de->name_len = 2;
de->rec_len = nilfs_rec_len_to_disk(chunk_size - NILFS_DIR_REC_LEN(1));
de->inode = cpu_to_le64(parent->i_ino);
memcpy(de->name, "..\0", 4);
- nilfs_set_de_type(de, inode);
- kunmap_atomic(kaddr);
- nilfs_commit_chunk(page, mapping, 0, chunk_size);
+ de->file_type = fs_umode_to_ftype(inode->i_mode);
+ kunmap_local(kaddr);
+ nilfs_commit_chunk(folio, mapping, 0, chunk_size);
fail:
- put_page(page);
+ folio_put(folio);
return err;
}
@@ -656,14 +607,14 @@ fail:
*/
int nilfs_empty_dir(struct inode *inode)
{
- struct page *page = NULL;
+ struct folio *folio = NULL;
+ char *kaddr;
unsigned long i, npages = dir_pages(inode);
for (i = 0; i < npages; i++) {
- char *kaddr;
struct nilfs_dir_entry *de;
- kaddr = nilfs_get_page(inode, i, &page);
+ kaddr = nilfs_get_folio(inode, i, &folio);
if (IS_ERR(kaddr))
return 0;
@@ -692,12 +643,12 @@ int nilfs_empty_dir(struct inode *inode)
}
de = nilfs_next_entry(de);
}
- nilfs_put_page(page);
+ folio_release_kmap(folio, kaddr);
}
return 1;
not_empty:
- nilfs_put_page(page);
+ folio_release_kmap(folio, kaddr);
return 0;
}
diff --git a/fs/nilfs2/direct.c b/fs/nilfs2/direct.c
index 893ab36824cc..2d8dc6b35b54 100644
--- a/fs/nilfs2/direct.c
+++ b/fs/nilfs2/direct.c
@@ -273,6 +273,9 @@ static int nilfs_direct_propagate(struct nilfs_bmap *bmap,
dat = nilfs_bmap_get_dat(bmap);
key = nilfs_bmap_data_get_key(bmap, bh);
ptr = nilfs_direct_get_ptr(bmap, key);
+ if (ptr == NILFS_BMAP_INVALID_PTR)
+ return -EINVAL;
+
if (!buffer_nilfs_volatile(bh)) {
oldreq.pr_entry_nr = ptr;
newreq.pr_entry_nr = ptr;
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 0505feef79f4..0e3fc5ba33c7 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -45,34 +45,36 @@ int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
- struct page *page = vmf->page;
+ struct folio *folio = page_folio(vmf->page);
struct inode *inode = file_inode(vma->vm_file);
struct nilfs_transaction_info ti;
+ struct buffer_head *bh, *head;
int ret = 0;
if (unlikely(nilfs_near_disk_full(inode->i_sb->s_fs_info)))
return VM_FAULT_SIGBUS; /* -ENOSPC */
sb_start_pagefault(inode->i_sb);
- lock_page(page);
- if (page->mapping != inode->i_mapping ||
- page_offset(page) >= i_size_read(inode) || !PageUptodate(page)) {
- unlock_page(page);
+ folio_lock(folio);
+ if (folio->mapping != inode->i_mapping ||
+ folio_pos(folio) >= i_size_read(inode) ||
+ !folio_test_uptodate(folio)) {
+ folio_unlock(folio);
ret = -EFAULT; /* make the VM retry the fault */
goto out;
}
/*
- * check to see if the page is mapped already (no holes)
+ * check to see if the folio is mapped already (no holes)
*/
- if (PageMappedToDisk(page))
+ if (folio_test_mappedtodisk(folio))
goto mapped;
- if (page_has_buffers(page)) {
- struct buffer_head *bh, *head;
+ head = folio_buffers(folio);
+ if (head) {
int fully_mapped = 1;
- bh = head = page_buffers(page);
+ bh = head;
do {
if (!buffer_mapped(bh)) {
fully_mapped = 0;
@@ -81,11 +83,11 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
} while (bh = bh->b_this_page, bh != head);
if (fully_mapped) {
- SetPageMappedToDisk(page);
+ folio_set_mappedtodisk(folio);
goto mapped;
}
}
- unlock_page(page);
+ folio_unlock(folio);
/*
* fill hole blocks
@@ -111,7 +113,7 @@ static vm_fault_t nilfs_page_mkwrite(struct vm_fault *vmf)
* necessary to wait for writeback to finish here, regardless of the
* stable write requirement of the backing device.
*/
- wait_on_page_writeback(page);
+ folio_wait_writeback(folio);
out:
sb_end_pagefault(inode->i_sb);
return vmf_fs_error(ret);
diff --git a/fs/nilfs2/gcinode.c b/fs/nilfs2/gcinode.c
index 3a50fe042477..2dbb15767df1 100644
--- a/fs/nilfs2/gcinode.c
+++ b/fs/nilfs2/gcinode.c
@@ -96,8 +96,8 @@ int nilfs_gccache_submit_read_data(struct inode *inode, sector_t blkoff,
*out_bh = bh;
failed:
- unlock_page(bh->b_page);
- put_page(bh->b_page);
+ folio_unlock(bh->b_folio);
+ folio_put(bh->b_folio);
if (unlikely(err))
brelse(bh);
return err;
@@ -173,6 +173,7 @@ int nilfs_init_gcinode(struct inode *inode)
/**
* nilfs_remove_all_gcinodes() - remove all unprocessed gc inodes
+ * @nilfs: NILFS filesystem instance
*/
void nilfs_remove_all_gcinodes(struct the_nilfs *nilfs)
{
diff --git a/fs/nilfs2/ifile.c b/fs/nilfs2/ifile.c
index ac10a62a41e9..1e86b9303b7c 100644
--- a/fs/nilfs2/ifile.c
+++ b/fs/nilfs2/ifile.c
@@ -15,6 +15,7 @@
#include "mdt.h"
#include "alloc.h"
#include "ifile.h"
+#include "cpfile.h"
/**
* struct nilfs_ifile_info - on-memory private data of ifile
@@ -112,11 +113,11 @@ int nilfs_ifile_delete_inode(struct inode *ifile, ino_t ino)
return ret;
}
- kaddr = kmap_atomic(req.pr_entry_bh->b_page);
+ kaddr = kmap_local_page(req.pr_entry_bh->b_page);
raw_inode = nilfs_palloc_block_get_entry(ifile, req.pr_entry_nr,
req.pr_entry_bh, kaddr);
raw_inode->i_flags = 0;
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
mark_buffer_dirty(req.pr_entry_bh);
brelse(req.pr_entry_bh);
@@ -170,14 +171,18 @@ int nilfs_ifile_count_free_inodes(struct inode *ifile,
* nilfs_ifile_read - read or get ifile inode
* @sb: super block instance
* @root: root object
+ * @cno: number of checkpoint entry to read
* @inode_size: size of an inode
- * @raw_inode: on-disk ifile inode
- * @inodep: buffer to store the inode
+ *
+ * Return: 0 on success, or the following negative error code on failure.
+ * * %-EINVAL - Invalid checkpoint.
+ * * %-ENOMEM - Insufficient memory available.
+ * * %-EIO - I/O error (including metadata corruption).
*/
int nilfs_ifile_read(struct super_block *sb, struct nilfs_root *root,
- size_t inode_size, struct nilfs_inode *raw_inode,
- struct inode **inodep)
+ __u64 cno, size_t inode_size)
{
+ struct the_nilfs *nilfs;
struct inode *ifile;
int err;
@@ -198,13 +203,13 @@ int nilfs_ifile_read(struct super_block *sb, struct nilfs_root *root,
nilfs_palloc_setup_cache(ifile, &NILFS_IFILE_I(ifile)->palloc_cache);
- err = nilfs_read_inode_common(ifile, raw_inode);
+ nilfs = sb->s_fs_info;
+ err = nilfs_cpfile_read_checkpoint(nilfs->ns_cpfile, cno, root, ifile);
if (err)
goto failed;
unlock_new_inode(ifile);
out:
- *inodep = ifile;
return 0;
failed:
iget_failed(ifile);
diff --git a/fs/nilfs2/ifile.h b/fs/nilfs2/ifile.h
index 35c5273f4821..625545cc2a98 100644
--- a/fs/nilfs2/ifile.h
+++ b/fs/nilfs2/ifile.h
@@ -21,15 +21,14 @@
static inline struct nilfs_inode *
nilfs_ifile_map_inode(struct inode *ifile, ino_t ino, struct buffer_head *ibh)
{
- void *kaddr = kmap(ibh->b_page);
+ void *kaddr = kmap_local_page(ibh->b_page);
return nilfs_palloc_block_get_entry(ifile, ino, ibh, kaddr);
}
-static inline void nilfs_ifile_unmap_inode(struct inode *ifile, ino_t ino,
- struct buffer_head *ibh)
+static inline void nilfs_ifile_unmap_inode(struct nilfs_inode *raw_inode)
{
- kunmap(ibh->b_page);
+ kunmap_local(raw_inode);
}
int nilfs_ifile_create_inode(struct inode *, ino_t *, struct buffer_head **);
@@ -39,7 +38,6 @@ int nilfs_ifile_get_inode_block(struct inode *, ino_t, struct buffer_head **);
int nilfs_ifile_count_free_inodes(struct inode *, u64 *, u64 *);
int nilfs_ifile_read(struct super_block *sb, struct nilfs_root *root,
- size_t inode_size, struct nilfs_inode *raw_inode,
- struct inode **inodep);
+ __u64 cno, size_t inode_size);
#endif /* _NILFS_IFILE_H */
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 489592644b68..afb3b9637740 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -15,6 +15,7 @@
#include <linux/writeback.h>
#include <linux/uio.h>
#include <linux/fiemap.h>
+#include <linux/random.h>
#include "nilfs.h"
#include "btnode.h"
#include "segment.h"
@@ -28,17 +29,13 @@
* @ino: inode number
* @cno: checkpoint number
* @root: pointer on NILFS root object (mounted checkpoint)
- * @for_gc: inode for GC flag
- * @for_btnc: inode for B-tree node cache flag
- * @for_shadow: inode for shadowed page cache flag
+ * @type: inode type
*/
struct nilfs_iget_args {
u64 ino;
__u64 cno;
struct nilfs_root *root;
- bool for_gc;
- bool for_btnc;
- bool for_shadow;
+ unsigned int type;
};
static int nilfs_iget_test(struct inode *inode, void *opaque);
@@ -162,7 +159,7 @@ static int nilfs_writepages(struct address_space *mapping,
int err = 0;
if (sb_rdonly(inode->i_sb)) {
- nilfs_clear_dirty_pages(mapping, false);
+ nilfs_clear_dirty_pages(mapping);
return -EROFS;
}
@@ -175,7 +172,8 @@ static int nilfs_writepages(struct address_space *mapping,
static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
{
- struct inode *inode = page->mapping->host;
+ struct folio *folio = page_folio(page);
+ struct inode *inode = folio->mapping->host;
int err;
if (sb_rdonly(inode->i_sb)) {
@@ -185,13 +183,13 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
* have dirty pages that try to be flushed in background.
* So, here we simply discard this dirty page.
*/
- nilfs_clear_dirty_page(page, false);
- unlock_page(page);
+ nilfs_clear_folio_dirty(folio);
+ folio_unlock(folio);
return -EROFS;
}
- redirty_page_for_writepage(wbc, page);
- unlock_page(page);
+ folio_redirty_for_writepage(wbc, folio);
+ folio_unlock(folio);
if (wbc->sync_mode == WB_SYNC_ALL) {
err = nilfs_construct_segment(inode->i_sb);
@@ -214,7 +212,7 @@ static bool nilfs_dirty_folio(struct address_space *mapping,
/*
* The page may not be locked, eg if called from try_to_unmap_one()
*/
- spin_lock(&mapping->private_lock);
+ spin_lock(&mapping->i_private_lock);
head = folio_buffers(folio);
if (head) {
struct buffer_head *bh = head;
@@ -230,7 +228,7 @@ static bool nilfs_dirty_folio(struct address_space *mapping,
} else if (ret) {
nr_dirty = 1 << (folio_shift(folio) - inode->i_blkbits);
}
- spin_unlock(&mapping->private_lock);
+ spin_unlock(&mapping->i_private_lock);
if (nr_dirty)
nilfs_set_file_dirty(inode, nr_dirty);
@@ -249,7 +247,7 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to)
static int nilfs_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len,
- struct page **pagep, void **fsdata)
+ struct folio **foliop, void **fsdata)
{
struct inode *inode = mapping->host;
@@ -258,7 +256,7 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping,
if (unlikely(err))
return err;
- err = block_write_begin(mapping, pos, len, pagep, nilfs_get_block);
+ err = block_write_begin(mapping, pos, len, foliop, nilfs_get_block);
if (unlikely(err)) {
nilfs_write_failed(mapping, pos + len);
nilfs_transaction_abort(inode->i_sb);
@@ -268,16 +266,16 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping,
static int nilfs_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
- struct page *page, void *fsdata)
+ struct folio *folio, void *fsdata)
{
struct inode *inode = mapping->host;
unsigned int start = pos & (PAGE_SIZE - 1);
unsigned int nr_dirty;
int err;
- nr_dirty = nilfs_page_count_clean_buffers(page, start,
+ nr_dirty = nilfs_page_count_clean_buffers(&folio->page, start,
start + copied);
- copied = generic_write_end(file, mapping, pos, len, copied, page,
+ copied = generic_write_end(file, mapping, pos, len, copied, folio,
fsdata);
nilfs_set_file_dirty(inode, nr_dirty);
err = nilfs_transaction_commit(inode->i_sb);
@@ -318,8 +316,7 @@ static int nilfs_insert_inode_locked(struct inode *inode,
unsigned long ino)
{
struct nilfs_iget_args args = {
- .ino = ino, .root = root, .cno = 0, .for_gc = false,
- .for_btnc = false, .for_shadow = false
+ .ino = ino, .root = root, .cno = 0, .type = NILFS_I_TYPE_NORMAL
};
return insert_inode_locked4(inode, ino, nilfs_iget_test, &args);
@@ -328,7 +325,6 @@ static int nilfs_insert_inode_locked(struct inode *inode,
struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
{
struct super_block *sb = dir->i_sb;
- struct the_nilfs *nilfs = sb->s_fs_info;
struct inode *inode;
struct nilfs_inode_info *ii;
struct nilfs_root *root;
@@ -346,31 +342,19 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
root = NILFS_I(dir)->i_root;
ii = NILFS_I(inode);
ii->i_state = BIT(NILFS_I_NEW);
+ ii->i_type = NILFS_I_TYPE_NORMAL;
ii->i_root = root;
err = nilfs_ifile_create_inode(root->ifile, &ino, &bh);
if (unlikely(err))
goto failed_ifile_create_inode;
/* reference count of i_bh inherits from nilfs_mdt_read_block() */
-
- if (unlikely(ino < NILFS_USER_INO)) {
- nilfs_warn(sb,
- "inode bitmap is inconsistent for reserved inodes");
- do {
- brelse(bh);
- err = nilfs_ifile_create_inode(root->ifile, &ino, &bh);
- if (unlikely(err))
- goto failed_ifile_create_inode;
- } while (ino < NILFS_USER_INO);
-
- nilfs_info(sb, "repaired inode bitmap for reserved inodes");
- }
ii->i_bh = bh;
atomic64_inc(&root->inodes_count);
inode_init_owner(&nop_mnt_idmap, inode, dir, mode);
inode->i_ino = ino;
- inode->i_mtime = inode->i_atime = inode_set_ctime_current(inode);
+ simple_inode_init_ts(inode);
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
err = nilfs_bmap_read(ii->i_bmap, NULL);
@@ -388,9 +372,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
/* ii->i_dir_acl = 0; */
ii->i_dir_start_lookup = 0;
nilfs_set_inode_flags(inode);
- spin_lock(&nilfs->ns_next_gen_lock);
- inode->i_generation = nilfs->ns_next_generation++;
- spin_unlock(&nilfs->ns_next_gen_lock);
+ inode->i_generation = get_random_u32();
if (nilfs_insert_inode_locked(inode, root, ino) < 0) {
err = -EIO;
goto failed_after_creation;
@@ -453,12 +435,12 @@ int nilfs_read_inode_common(struct inode *inode,
i_gid_write(inode, le32_to_cpu(raw_inode->i_gid));
set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
inode->i_size = le64_to_cpu(raw_inode->i_size);
- inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
+ inode_set_atime(inode, le64_to_cpu(raw_inode->i_mtime),
+ le32_to_cpu(raw_inode->i_mtime_nsec));
inode_set_ctime(inode, le64_to_cpu(raw_inode->i_ctime),
le32_to_cpu(raw_inode->i_ctime_nsec));
- inode->i_mtime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
- inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
- inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
+ inode_set_mtime(inode, le64_to_cpu(raw_inode->i_mtime),
+ le32_to_cpu(raw_inode->i_mtime_nsec));
if (nilfs_is_metadata_file_inode(inode) && !S_ISREG(inode->i_mode))
return -EIO; /* this inode is for metadata and corrupted */
if (inode->i_nlink == 0)
@@ -517,13 +499,20 @@ static int __nilfs_read_inode(struct super_block *sb,
inode->i_op = &nilfs_symlink_inode_operations;
inode_nohighmem(inode);
inode->i_mapping->a_ops = &nilfs_aops;
- } else {
+ } else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode) ||
+ S_ISFIFO(inode->i_mode) || S_ISSOCK(inode->i_mode)) {
inode->i_op = &nilfs_special_inode_operations;
init_special_inode(
inode, inode->i_mode,
huge_decode_dev(le64_to_cpu(raw_inode->i_device_code)));
+ } else {
+ nilfs_error(sb,
+ "invalid file type bits in mode 0%o for inode %lu",
+ inode->i_mode, ino);
+ err = -EIO;
+ goto failed_unmap;
}
- nilfs_ifile_unmap_inode(root->ifile, ino, bh);
+ nilfs_ifile_unmap_inode(raw_inode);
brelse(bh);
up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
nilfs_set_inode_flags(inode);
@@ -532,7 +521,7 @@ static int __nilfs_read_inode(struct super_block *sb,
return 0;
failed_unmap:
- nilfs_ifile_unmap_inode(root->ifile, ino, bh);
+ nilfs_ifile_unmap_inode(raw_inode);
brelse(bh);
bad_inode:
@@ -549,23 +538,10 @@ static int nilfs_iget_test(struct inode *inode, void *opaque)
return 0;
ii = NILFS_I(inode);
- if (test_bit(NILFS_I_BTNC, &ii->i_state)) {
- if (!args->for_btnc)
- return 0;
- } else if (args->for_btnc) {
- return 0;
- }
- if (test_bit(NILFS_I_SHADOW, &ii->i_state)) {
- if (!args->for_shadow)
- return 0;
- } else if (args->for_shadow) {
+ if (ii->i_type != args->type)
return 0;
- }
-
- if (!test_bit(NILFS_I_GCINODE, &ii->i_state))
- return !args->for_gc;
- return args->for_gc && args->cno == ii->i_cno;
+ return !(args->type & NILFS_I_TYPE_GC) || args->cno == ii->i_cno;
}
static int nilfs_iget_set(struct inode *inode, void *opaque)
@@ -575,15 +551,9 @@ static int nilfs_iget_set(struct inode *inode, void *opaque)
inode->i_ino = args->ino;
NILFS_I(inode)->i_cno = args->cno;
NILFS_I(inode)->i_root = args->root;
+ NILFS_I(inode)->i_type = args->type;
if (args->root && args->ino == NILFS_ROOT_INO)
nilfs_get_root(args->root);
-
- if (args->for_gc)
- NILFS_I(inode)->i_state = BIT(NILFS_I_GCINODE);
- if (args->for_btnc)
- NILFS_I(inode)->i_state |= BIT(NILFS_I_BTNC);
- if (args->for_shadow)
- NILFS_I(inode)->i_state |= BIT(NILFS_I_SHADOW);
return 0;
}
@@ -591,8 +561,7 @@ struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root,
unsigned long ino)
{
struct nilfs_iget_args args = {
- .ino = ino, .root = root, .cno = 0, .for_gc = false,
- .for_btnc = false, .for_shadow = false
+ .ino = ino, .root = root, .cno = 0, .type = NILFS_I_TYPE_NORMAL
};
return ilookup5(sb, ino, nilfs_iget_test, &args);
@@ -602,8 +571,7 @@ struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root,
unsigned long ino)
{
struct nilfs_iget_args args = {
- .ino = ino, .root = root, .cno = 0, .for_gc = false,
- .for_btnc = false, .for_shadow = false
+ .ino = ino, .root = root, .cno = 0, .type = NILFS_I_TYPE_NORMAL
};
return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
@@ -640,8 +608,7 @@ struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino,
__u64 cno)
{
struct nilfs_iget_args args = {
- .ino = ino, .root = NULL, .cno = cno, .for_gc = true,
- .for_btnc = false, .for_shadow = false
+ .ino = ino, .root = NULL, .cno = cno, .type = NILFS_I_TYPE_GC
};
struct inode *inode;
int err;
@@ -686,9 +653,7 @@ int nilfs_attach_btree_node_cache(struct inode *inode)
args.ino = inode->i_ino;
args.root = ii->i_root;
args.cno = ii->i_cno;
- args.for_gc = test_bit(NILFS_I_GCINODE, &ii->i_state) != 0;
- args.for_btnc = true;
- args.for_shadow = test_bit(NILFS_I_SHADOW, &ii->i_state) != 0;
+ args.type = ii->i_type | NILFS_I_TYPE_BTNC;
btnc_inode = iget5_locked(inode->i_sb, inode->i_ino, nilfs_iget_test,
nilfs_iget_set, &args);
@@ -742,8 +707,8 @@ void nilfs_detach_btree_node_cache(struct inode *inode)
struct inode *nilfs_iget_for_shadow(struct inode *inode)
{
struct nilfs_iget_args args = {
- .ino = inode->i_ino, .root = NULL, .cno = 0, .for_gc = false,
- .for_btnc = false, .for_shadow = true
+ .ino = inode->i_ino, .root = NULL, .cno = 0,
+ .type = NILFS_I_TYPE_SHADOW
};
struct inode *s_inode;
int err;
@@ -769,8 +734,18 @@ struct inode *nilfs_iget_for_shadow(struct inode *inode)
return s_inode;
}
+/**
+ * nilfs_write_inode_common - export common inode information to on-disk inode
+ * @inode: inode object
+ * @raw_inode: on-disk inode
+ *
+ * This function writes standard information from the on-memory inode @inode
+ * to @raw_inode on ifile, cpfile or a super root block. Since inode bmap
+ * data is not exported, nilfs_bmap_write() must be called separately during
+ * log writing.
+ */
void nilfs_write_inode_common(struct inode *inode,
- struct nilfs_inode *raw_inode, int has_bmap)
+ struct nilfs_inode *raw_inode)
{
struct nilfs_inode_info *ii = NILFS_I(inode);
@@ -779,30 +754,15 @@ void nilfs_write_inode_common(struct inode *inode,
raw_inode->i_gid = cpu_to_le32(i_gid_read(inode));
raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
raw_inode->i_size = cpu_to_le64(inode->i_size);
- raw_inode->i_ctime = cpu_to_le64(inode_get_ctime(inode).tv_sec);
- raw_inode->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
- raw_inode->i_ctime_nsec = cpu_to_le32(inode_get_ctime(inode).tv_nsec);
- raw_inode->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
+ raw_inode->i_ctime = cpu_to_le64(inode_get_ctime_sec(inode));
+ raw_inode->i_mtime = cpu_to_le64(inode_get_mtime_sec(inode));
+ raw_inode->i_ctime_nsec = cpu_to_le32(inode_get_ctime_nsec(inode));
+ raw_inode->i_mtime_nsec = cpu_to_le32(inode_get_mtime_nsec(inode));
raw_inode->i_blocks = cpu_to_le64(inode->i_blocks);
raw_inode->i_flags = cpu_to_le32(ii->i_flags);
raw_inode->i_generation = cpu_to_le32(inode->i_generation);
- if (NILFS_ROOT_METADATA_FILE(inode->i_ino)) {
- struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
-
- /* zero-fill unused portion in the case of super root block */
- raw_inode->i_xattr = 0;
- raw_inode->i_pad = 0;
- memset((void *)raw_inode + sizeof(*raw_inode), 0,
- nilfs->ns_inode_size - sizeof(*raw_inode));
- }
-
- if (has_bmap)
- nilfs_bmap_write(ii->i_bmap, raw_inode);
- else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
- raw_inode->i_device_code =
- cpu_to_le64(huge_encode_dev(inode->i_rdev));
/*
* When extending inode, nilfs->ns_inode_size should be checked
* for substitutions of appended fields.
@@ -823,14 +783,13 @@ void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh, int flags)
if (flags & I_DIRTY_DATASYNC)
set_bit(NILFS_I_INODE_SYNC, &ii->i_state);
- nilfs_write_inode_common(inode, raw_inode, 0);
- /*
- * XXX: call with has_bmap = 0 is a workaround to avoid
- * deadlock of bmap. This delays update of i_bmap to just
- * before writing.
- */
+ nilfs_write_inode_common(inode, raw_inode);
+
+ if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
+ raw_inode->i_device_code =
+ cpu_to_le64(huge_encode_dev(inode->i_rdev));
- nilfs_ifile_unmap_inode(ifile, ino, ibh);
+ nilfs_ifile_unmap_inode(raw_inode);
}
#define NILFS_MAX_TRUNCATE_BLOCKS 16384 /* 64MB for 4KB block */
@@ -886,7 +845,7 @@ void nilfs_truncate(struct inode *inode)
nilfs_truncate_bmap(ii, blkoff);
- inode->i_mtime = inode_set_ctime_current(inode);
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
if (IS_SYNC(inode))
nilfs_set_transaction_flag(NILFS_TI_SYNC);
@@ -916,7 +875,7 @@ static void nilfs_clear_inode(struct inode *inode)
if (test_bit(NILFS_I_BMAP, &ii->i_state))
nilfs_bmap_clear(ii->i_bmap);
- if (!test_bit(NILFS_I_BTNC, &ii->i_state))
+ if (!(ii->i_type & NILFS_I_TYPE_BTNC))
nilfs_detach_btree_node_cache(inode);
if (ii->i_root && inode->i_ino == NILFS_ROOT_INO)
@@ -1267,7 +1226,7 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
if (size) {
if (phys && blkphy << blkbits == phys + size) {
/* The current extent goes on */
- size += n << blkbits;
+ size += (u64)n << blkbits;
} else {
/* Terminate the current extent */
ret = fiemap_fill_next_extent(
@@ -1280,14 +1239,14 @@ int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
flags = FIEMAP_EXTENT_MERGED;
logical = blkoff << blkbits;
phys = blkphy << blkbits;
- size = n << blkbits;
+ size = (u64)n << blkbits;
}
} else {
/* Start a new extent */
flags = FIEMAP_EXTENT_MERGED;
logical = blkoff << blkbits;
phys = blkphy << blkbits;
- size = n << blkbits;
+ size = (u64)n << blkbits;
}
blkoff += n;
}
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index 53022bfe0b72..fa77f78df681 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -17,6 +17,7 @@
#include <linux/mount.h> /* mnt_want_write_file(), mnt_drop_write_file() */
#include <linux/buffer_head.h>
#include <linux/fileattr.h>
+#include <linux/string.h>
#include "nilfs.h"
#include "segment.h"
#include "bmap.h"
@@ -114,7 +115,11 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs,
}
/**
- * nilfs_fileattr_get - ioctl to support lsattr
+ * nilfs_fileattr_get - retrieve miscellaneous file attributes
+ * @dentry: the object to retrieve from
+ * @fa: fileattr pointer
+ *
+ * Return: always 0 as success.
*/
int nilfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
{
@@ -126,7 +131,12 @@ int nilfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
}
/**
- * nilfs_fileattr_set - ioctl to support chattr
+ * nilfs_fileattr_set - change miscellaneous file attributes
+ * @idmap: idmap of the mount
+ * @dentry: the object to change
+ * @fa: fileattr pointer
+ *
+ * Return: 0 on success, or a negative error code on failure.
*/
int nilfs_fileattr_set(struct mnt_idmap *idmap,
struct dentry *dentry, struct fileattr *fa)
@@ -159,6 +169,10 @@ int nilfs_fileattr_set(struct mnt_idmap *idmap,
/**
* nilfs_ioctl_getversion - get info about a file's version (generation number)
+ * @inode: inode object
+ * @argp: userspace memory where the generation number of @inode is stored
+ *
+ * Return: 0 on success, or %-EFAULT on error.
*/
static int nilfs_ioctl_getversion(struct inode *inode, void __user *argp)
{
@@ -872,16 +886,14 @@ static int nilfs_ioctl_clean_segments(struct inode *inode, struct file *filp,
nsegs = argv[4].v_nmembs;
if (argv[4].v_size != argsz[4])
goto out;
- if (nsegs > UINT_MAX / sizeof(__u64))
- goto out;
/*
* argv[4] points to segment numbers this ioctl cleans. We
- * use kmalloc() for its buffer because memory used for the
- * segment numbers is enough small.
+ * use kmalloc() for its buffer because the memory used for the
+ * segment numbers is small enough.
*/
- kbufs[4] = memdup_user((void __user *)(unsigned long)argv[4].v_base,
- nsegs * sizeof(__u64));
+ kbufs[4] = memdup_array_user((void __user *)(unsigned long)argv[4].v_base,
+ nsegs, sizeof(__u64));
if (IS_ERR(kbufs[4])) {
ret = PTR_ERR(kbufs[4]);
goto out;
@@ -1113,7 +1125,7 @@ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp)
segbytes = nilfs->ns_blocks_per_segment * nilfs->ns_blocksize;
minseg = range[0] + segbytes - 1;
- do_div(minseg, segbytes);
+ minseg = div64_ul(minseg, segbytes);
if (range[1] < 4096)
goto out;
@@ -1122,7 +1134,7 @@ static int nilfs_ioctl_set_alloc_range(struct inode *inode, void __user *argp)
if (maxseg < segbytes)
goto out;
- do_div(maxseg, segbytes);
+ maxseg = div64_ul(maxseg, segbytes);
maxseg--;
ret = nilfs_sufile_set_alloc_range(nilfs->ns_sufile, minseg, maxseg);
@@ -1268,6 +1280,91 @@ out:
return ret;
}
+/**
+ * nilfs_ioctl_get_fslabel - get the volume name of the file system
+ * @sb: super block instance
+ * @argp: pointer to userspace memory where the volume name should be stored
+ *
+ * Return: 0 on success, %-EFAULT if copying to userspace memory fails.
+ */
+static int nilfs_ioctl_get_fslabel(struct super_block *sb, void __user *argp)
+{
+ struct the_nilfs *nilfs = sb->s_fs_info;
+ char label[NILFS_MAX_VOLUME_NAME + 1];
+
+ BUILD_BUG_ON(NILFS_MAX_VOLUME_NAME >= FSLABEL_MAX);
+
+ down_read(&nilfs->ns_sem);
+ memtostr_pad(label, nilfs->ns_sbp[0]->s_volume_name);
+ up_read(&nilfs->ns_sem);
+
+ if (copy_to_user(argp, label, sizeof(label)))
+ return -EFAULT;
+ return 0;
+}
+
+/**
+ * nilfs_ioctl_set_fslabel - set the volume name of the file system
+ * @sb: super block instance
+ * @filp: file object
+ * @argp: pointer to userspace memory that contains the volume name
+ *
+ * Return: 0 on success, or the following negative error code on failure.
+ * * %-EFAULT - Error copying input data.
+ * * %-EINVAL - Label length exceeds record size in superblock.
+ * * %-EIO - I/O error.
+ * * %-EPERM - Operation not permitted (insufficient permissions).
+ * * %-EROFS - Read only file system.
+ */
+static int nilfs_ioctl_set_fslabel(struct super_block *sb, struct file *filp,
+ void __user *argp)
+{
+ char label[NILFS_MAX_VOLUME_NAME + 1];
+ struct the_nilfs *nilfs = sb->s_fs_info;
+ struct nilfs_super_block **sbp;
+ size_t len;
+ int ret;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ ret = mnt_want_write_file(filp);
+ if (ret)
+ return ret;
+
+ if (copy_from_user(label, argp, NILFS_MAX_VOLUME_NAME + 1)) {
+ ret = -EFAULT;
+ goto out_drop_write;
+ }
+
+ len = strnlen(label, NILFS_MAX_VOLUME_NAME + 1);
+ if (len > NILFS_MAX_VOLUME_NAME) {
+ nilfs_err(sb, "unable to set label with more than %zu bytes",
+ NILFS_MAX_VOLUME_NAME);
+ ret = -EINVAL;
+ goto out_drop_write;
+ }
+
+ down_write(&nilfs->ns_sem);
+ sbp = nilfs_prepare_super(sb, false);
+ if (unlikely(!sbp)) {
+ ret = -EIO;
+ goto out_unlock;
+ }
+
+ strtomem_pad(sbp[0]->s_volume_name, label, 0);
+ if (sbp[1])
+ strtomem_pad(sbp[1]->s_volume_name, label, 0);
+
+ ret = nilfs_commit_super(sb, NILFS_SB_COMMIT_ALL);
+
+out_unlock:
+ up_write(&nilfs->ns_sem);
+out_drop_write:
+ mnt_drop_write_file(filp);
+ return ret;
+}
+
long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
@@ -1310,6 +1407,10 @@ long nilfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
return nilfs_ioctl_set_alloc_range(inode, argp);
case FITRIM:
return nilfs_ioctl_trim_fs(inode, argp);
+ case FS_IOC_GETFSLABEL:
+ return nilfs_ioctl_get_fslabel(inode->i_sb, argp);
+ case FS_IOC_SETFSLABEL:
+ return nilfs_ioctl_set_fslabel(inode->i_sb, filp, argp);
default:
return -ENOTTY;
}
@@ -1336,6 +1437,8 @@ long nilfs_compat_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
case NILFS_IOCTL_RESIZE:
case NILFS_IOCTL_SET_ALLOC_RANGE:
case FITRIM:
+ case FS_IOC_GETFSLABEL:
+ case FS_IOC_SETFSLABEL:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index 75a2ed5ee6e0..2db6350b5ac2 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -47,12 +47,12 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block,
set_buffer_mapped(bh);
- kaddr = kmap_atomic(bh->b_page);
+ kaddr = kmap_local_page(bh->b_page);
memset(kaddr + bh_offset(bh), 0, i_blocksize(inode));
if (init_block)
init_block(inode, bh, kaddr);
flush_dcache_page(bh->b_page);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
@@ -96,8 +96,8 @@ static int nilfs_mdt_create_block(struct inode *inode, unsigned long block,
}
failed_bh:
- unlock_page(bh->b_page);
- put_page(bh->b_page);
+ folio_unlock(bh->b_folio);
+ folio_put(bh->b_folio);
brelse(bh);
failed_unlock:
@@ -157,8 +157,8 @@ nilfs_mdt_submit_block(struct inode *inode, unsigned long blkoff, blk_opf_t opf,
*out_bh = bh;
failed_bh:
- unlock_page(bh->b_page);
- put_page(bh->b_page);
+ folio_unlock(bh->b_folio);
+ folio_put(bh->b_folio);
brelse(bh);
failed:
return ret;
@@ -355,30 +355,28 @@ int nilfs_mdt_delete_block(struct inode *inode, unsigned long block)
*/
int nilfs_mdt_forget_block(struct inode *inode, unsigned long block)
{
- pgoff_t index = (pgoff_t)block >>
- (PAGE_SHIFT - inode->i_blkbits);
- struct page *page;
- unsigned long first_block;
+ pgoff_t index = block >> (PAGE_SHIFT - inode->i_blkbits);
+ struct folio *folio;
+ struct buffer_head *bh;
int ret = 0;
int still_dirty;
- page = find_lock_page(inode->i_mapping, index);
- if (!page)
+ folio = filemap_lock_folio(inode->i_mapping, index);
+ if (IS_ERR(folio))
return -ENOENT;
- wait_on_page_writeback(page);
-
- first_block = (unsigned long)index <<
- (PAGE_SHIFT - inode->i_blkbits);
- if (page_has_buffers(page)) {
- struct buffer_head *bh;
+ folio_wait_writeback(folio);
- bh = nilfs_page_get_nth_block(page, block - first_block);
+ bh = folio_buffers(folio);
+ if (bh) {
+ unsigned long first_block = index <<
+ (PAGE_SHIFT - inode->i_blkbits);
+ bh = get_nth_bh(bh, block - first_block);
nilfs_forget_buffer(bh);
}
- still_dirty = PageDirty(page);
- unlock_page(page);
- put_page(page);
+ still_dirty = folio_test_dirty(folio);
+ folio_unlock(folio);
+ folio_put(folio);
if (still_dirty ||
invalidate_inode_pages2_range(inode->i_mapping, index, index) != 0)
@@ -400,7 +398,8 @@ int nilfs_mdt_fetch_dirty(struct inode *inode)
static int
nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)
{
- struct inode *inode = page->mapping->host;
+ struct folio *folio = page_folio(page);
+ struct inode *inode = folio->mapping->host;
struct super_block *sb;
int err = 0;
@@ -408,16 +407,16 @@ nilfs_mdt_write_page(struct page *page, struct writeback_control *wbc)
/*
* It means that filesystem was remounted in read-only
* mode because of error or metadata corruption. But we
- * have dirty pages that try to be flushed in background.
- * So, here we simply discard this dirty page.
+ * have dirty folios that try to be flushed in background.
+ * So, here we simply discard this dirty folio.
*/
- nilfs_clear_dirty_page(page, false);
- unlock_page(page);
+ nilfs_clear_folio_dirty(folio);
+ folio_unlock(folio);
return -EROFS;
}
- redirty_page_for_writepage(wbc, page);
- unlock_page(page);
+ folio_redirty_for_writepage(wbc, folio);
+ folio_unlock(folio);
if (!inode)
return 0;
@@ -559,17 +558,19 @@ int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh)
{
struct nilfs_shadow_map *shadow = NILFS_MDT(inode)->mi_shadow;
struct buffer_head *bh_frozen;
- struct page *page;
+ struct folio *folio;
int blkbits = inode->i_blkbits;
- page = grab_cache_page(shadow->inode->i_mapping, bh->b_folio->index);
- if (!page)
- return -ENOMEM;
+ folio = filemap_grab_folio(shadow->inode->i_mapping,
+ bh->b_folio->index);
+ if (IS_ERR(folio))
+ return PTR_ERR(folio);
- if (!page_has_buffers(page))
- create_empty_buffers(page, 1 << blkbits, 0);
+ bh_frozen = folio_buffers(folio);
+ if (!bh_frozen)
+ bh_frozen = create_empty_buffers(folio, 1 << blkbits, 0);
- bh_frozen = nilfs_page_get_nth_block(page, bh_offset(bh) >> blkbits);
+ bh_frozen = get_nth_bh(bh_frozen, bh_offset(bh) >> blkbits);
if (!buffer_uptodate(bh_frozen))
nilfs_copy_buffer(bh_frozen, bh);
@@ -581,8 +582,8 @@ int nilfs_mdt_freeze_buffer(struct inode *inode, struct buffer_head *bh)
brelse(bh_frozen); /* already frozen */
}
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
return 0;
}
@@ -591,17 +592,19 @@ nilfs_mdt_get_frozen_buffer(struct inode *inode, struct buffer_head *bh)
{
struct nilfs_shadow_map *shadow = NILFS_MDT(inode)->mi_shadow;
struct buffer_head *bh_frozen = NULL;
- struct page *page;
+ struct folio *folio;
int n;
- page = find_lock_page(shadow->inode->i_mapping, bh->b_folio->index);
- if (page) {
- if (page_has_buffers(page)) {
+ folio = filemap_lock_folio(shadow->inode->i_mapping,
+ bh->b_folio->index);
+ if (!IS_ERR(folio)) {
+ bh_frozen = folio_buffers(folio);
+ if (bh_frozen) {
n = bh_offset(bh) >> inode->i_blkbits;
- bh_frozen = nilfs_page_get_nth_block(page, n);
+ bh_frozen = get_nth_bh(bh_frozen, n);
}
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
}
return bh_frozen;
}
@@ -634,10 +637,10 @@ void nilfs_mdt_restore_from_shadow_map(struct inode *inode)
if (mi->mi_palloc_cache)
nilfs_palloc_clear_cache(inode);
- nilfs_clear_dirty_pages(inode->i_mapping, true);
+ nilfs_clear_dirty_pages(inode->i_mapping);
nilfs_copy_back_pages(inode->i_mapping, shadow->inode->i_mapping);
- nilfs_clear_dirty_pages(ii->i_assoc_inode->i_mapping, true);
+ nilfs_clear_dirty_pages(ii->i_assoc_inode->i_mapping);
nilfs_copy_back_pages(ii->i_assoc_inode->i_mapping,
NILFS_I(shadow->inode)->i_assoc_inode->i_mapping);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index ac0adeb58e41..e02fae6757f1 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -276,10 +276,10 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry)
{
struct inode *inode;
struct nilfs_dir_entry *de;
- struct page *page;
+ struct folio *folio;
int err;
- de = nilfs_find_entry(dir, &dentry->d_name, &page);
+ de = nilfs_find_entry(dir, &dentry->d_name, &folio);
if (IS_ERR(de)) {
err = PTR_ERR(de);
goto out;
@@ -296,7 +296,8 @@ static int nilfs_do_unlink(struct inode *dir, struct dentry *dentry)
inode->i_ino, inode->i_nlink);
set_nlink(inode, 1);
}
- err = nilfs_delete_entry(de, page);
+ err = nilfs_delete_entry(de, folio);
+ folio_release_kmap(folio, de);
if (err)
goto out;
@@ -364,9 +365,9 @@ static int nilfs_rename(struct mnt_idmap *idmap,
{
struct inode *old_inode = d_inode(old_dentry);
struct inode *new_inode = d_inode(new_dentry);
- struct page *dir_page = NULL;
+ struct folio *dir_folio = NULL;
struct nilfs_dir_entry *dir_de = NULL;
- struct page *old_page;
+ struct folio *old_folio;
struct nilfs_dir_entry *old_de;
struct nilfs_transaction_info ti;
int err;
@@ -378,7 +379,7 @@ static int nilfs_rename(struct mnt_idmap *idmap,
if (unlikely(err))
return err;
- old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_page);
+ old_de = nilfs_find_entry(old_dir, &old_dentry->d_name, &old_folio);
if (IS_ERR(old_de)) {
err = PTR_ERR(old_de);
goto out;
@@ -386,13 +387,13 @@ static int nilfs_rename(struct mnt_idmap *idmap,
if (S_ISDIR(old_inode->i_mode)) {
err = -EIO;
- dir_de = nilfs_dotdot(old_inode, &dir_page);
+ dir_de = nilfs_dotdot(old_inode, &dir_folio);
if (!dir_de)
goto out_old;
}
if (new_inode) {
- struct page *new_page;
+ struct folio *new_folio;
struct nilfs_dir_entry *new_de;
err = -ENOTEMPTY;
@@ -400,12 +401,15 @@ static int nilfs_rename(struct mnt_idmap *idmap,
goto out_dir;
new_de = nilfs_find_entry(new_dir, &new_dentry->d_name,
- &new_page);
+ &new_folio);
if (IS_ERR(new_de)) {
err = PTR_ERR(new_de);
goto out_dir;
}
- nilfs_set_link(new_dir, new_de, new_page, old_inode);
+ err = nilfs_set_link(new_dir, new_de, new_folio, old_inode);
+ folio_release_kmap(new_folio, new_de);
+ if (unlikely(err))
+ goto out_dir;
nilfs_mark_inode_dirty(new_dir);
inode_set_ctime_current(new_inode);
if (dir_de)
@@ -428,28 +432,27 @@ static int nilfs_rename(struct mnt_idmap *idmap,
*/
inode_set_ctime_current(old_inode);
- nilfs_delete_entry(old_de, old_page);
-
- if (dir_de) {
- nilfs_set_link(old_inode, dir_de, dir_page, new_dir);
- drop_nlink(old_dir);
+ err = nilfs_delete_entry(old_de, old_folio);
+ if (likely(!err)) {
+ if (dir_de) {
+ err = nilfs_set_link(old_inode, dir_de, dir_folio,
+ new_dir);
+ drop_nlink(old_dir);
+ }
+ nilfs_mark_inode_dirty(old_dir);
}
- nilfs_mark_inode_dirty(old_dir);
nilfs_mark_inode_dirty(old_inode);
- err = nilfs_transaction_commit(old_dir->i_sb);
- return err;
-
out_dir:
- if (dir_de) {
- kunmap(dir_page);
- put_page(dir_page);
- }
+ if (dir_de)
+ folio_release_kmap(dir_folio, dir_de);
out_old:
- kunmap(old_page);
- put_page(old_page);
+ folio_release_kmap(old_folio, old_de);
out:
- nilfs_transaction_abort(old_dir->i_sb);
+ if (likely(!err))
+ err = nilfs_transaction_commit(old_dir->i_sb);
+ else
+ nilfs_transaction_abort(old_dir->i_sb);
return err;
}
@@ -460,7 +463,6 @@ static struct dentry *nilfs_get_parent(struct dentry *child)
{
ino_t ino;
int res;
- struct inode *inode;
struct nilfs_root *root;
res = nilfs_inode_by_name(d_inode(child), &dotdot_name, &ino);
@@ -469,11 +471,7 @@ static struct dentry *nilfs_get_parent(struct dentry *child)
root = NILFS_I(d_inode(child))->i_root;
- inode = nilfs_iget(child->d_sb, root, ino);
- if (IS_ERR(inode))
- return ERR_CAST(inode);
-
- return d_obtain_alias(inode);
+ return d_obtain_alias(nilfs_iget(child->d_sb, root, ino));
}
static struct dentry *nilfs_get_dentry(struct super_block *sb, u64 cno,
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index e2c5376b56cd..cb6ed54accd7 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -22,6 +22,7 @@
/**
* struct nilfs_inode_info - nilfs inode data in memory
* @i_flags: inode flags
+ * @i_type: inode type (combination of flags that inidicate usage)
* @i_state: dynamic state flags
* @i_bmap: pointer on i_bmap_data
* @i_bmap_data: raw block mapping
@@ -37,6 +38,7 @@
*/
struct nilfs_inode_info {
__u32 i_flags;
+ unsigned int i_type;
unsigned long i_state; /* Dynamic state flags */
struct nilfs_bmap *i_bmap;
struct nilfs_bmap i_bmap_data;
@@ -90,9 +92,16 @@ enum {
NILFS_I_UPDATED, /* The file has been written back */
NILFS_I_INODE_SYNC, /* dsync is not allowed for inode */
NILFS_I_BMAP, /* has bmap and btnode_cache */
- NILFS_I_GCINODE, /* inode for GC, on memory only */
- NILFS_I_BTNC, /* inode for btree node cache */
- NILFS_I_SHADOW, /* inode for shadowed page cache */
+};
+
+/*
+ * Flags to identify the usage of on-memory inodes (i_type)
+ */
+enum {
+ NILFS_I_TYPE_NORMAL = 0,
+ NILFS_I_TYPE_GC = 0x0001, /* For data caching during GC */
+ NILFS_I_TYPE_BTNC = 0x0002, /* For btree node cache */
+ NILFS_I_TYPE_SHADOW = 0x0004, /* For shadowed page cache */
};
/*
@@ -103,6 +112,18 @@ enum {
NILFS_SB_COMMIT_ALL /* Commit both super blocks */
};
+/**
+ * define NILFS_MAX_VOLUME_NAME - maximum number of characters (bytes) in a
+ * file system volume name
+ *
+ * Defined by the size of the volume name field in the on-disk superblocks.
+ * This volume name does not include the terminating NULL byte if the string
+ * length matches the field size, so use (NILFS_MAX_VOLUME_NAME + 1) for the
+ * size of the buffer that requires a NULL byte termination.
+ */
+#define NILFS_MAX_VOLUME_NAME \
+ sizeof_field(struct nilfs_super_block, s_volume_name)
+
/*
* Macros to check inode numbers
*/
@@ -232,16 +253,16 @@ static inline __u32 nilfs_mask_flags(umode_t mode, __u32 flags)
}
/* dir.c */
-extern int nilfs_add_link(struct dentry *, struct inode *);
+int nilfs_add_link(struct dentry *, struct inode *);
int nilfs_inode_by_name(struct inode *dir, const struct qstr *qstr, ino_t *ino);
-extern int nilfs_make_empty(struct inode *, struct inode *);
-extern struct nilfs_dir_entry *
-nilfs_find_entry(struct inode *, const struct qstr *, struct page **);
-extern int nilfs_delete_entry(struct nilfs_dir_entry *, struct page *);
-extern int nilfs_empty_dir(struct inode *);
-extern struct nilfs_dir_entry *nilfs_dotdot(struct inode *, struct page **);
-extern void nilfs_set_link(struct inode *, struct nilfs_dir_entry *,
- struct page *, struct inode *);
+int nilfs_make_empty(struct inode *, struct inode *);
+struct nilfs_dir_entry *nilfs_find_entry(struct inode *, const struct qstr *,
+ struct folio **);
+int nilfs_delete_entry(struct nilfs_dir_entry *, struct folio *);
+int nilfs_empty_dir(struct inode *);
+struct nilfs_dir_entry *nilfs_dotdot(struct inode *, struct folio **);
+int nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de,
+ struct folio *folio, struct inode *inode);
/* file.c */
extern int nilfs_sync_file(struct file *, loff_t, loff_t, int);
@@ -262,7 +283,8 @@ extern struct inode *nilfs_new_inode(struct inode *, umode_t);
extern int nilfs_get_block(struct inode *, sector_t, struct buffer_head *, int);
extern void nilfs_set_inode_flags(struct inode *);
extern int nilfs_read_inode_common(struct inode *, struct nilfs_inode *);
-extern void nilfs_write_inode_common(struct inode *, struct nilfs_inode *, int);
+void nilfs_write_inode_common(struct inode *inode,
+ struct nilfs_inode *raw_inode);
struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root,
unsigned long ino);
struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root,
@@ -340,8 +362,8 @@ void __nilfs_error(struct super_block *sb, const char *function,
extern struct nilfs_super_block *
nilfs_read_super_block(struct super_block *, u64, int, struct buffer_head **);
-extern int nilfs_store_magic_and_option(struct super_block *,
- struct nilfs_super_block *, char *);
+extern int nilfs_store_magic(struct super_block *sb,
+ struct nilfs_super_block *sbp);
extern int nilfs_check_feature_compatibility(struct super_block *,
struct nilfs_super_block *);
extern void nilfs_set_log_cursor(struct nilfs_super_block *,
diff --git a/fs/nilfs2/page.c b/fs/nilfs2/page.c
index 144e200c4909..06f18fe86407 100644
--- a/fs/nilfs2/page.c
+++ b/fs/nilfs2/page.c
@@ -25,19 +25,19 @@
(BIT(BH_Uptodate) | BIT(BH_Mapped) | BIT(BH_NILFS_Node) | \
BIT(BH_NILFS_Volatile) | BIT(BH_NILFS_Checked))
-static struct buffer_head *
-__nilfs_get_page_block(struct page *page, unsigned long block, pgoff_t index,
- int blkbits, unsigned long b_state)
+static struct buffer_head *__nilfs_get_folio_block(struct folio *folio,
+ unsigned long block, pgoff_t index, int blkbits,
+ unsigned long b_state)
{
unsigned long first_block;
- struct buffer_head *bh;
+ struct buffer_head *bh = folio_buffers(folio);
- if (!page_has_buffers(page))
- create_empty_buffers(page, 1 << blkbits, b_state);
+ if (!bh)
+ bh = create_empty_buffers(folio, 1 << blkbits, b_state);
first_block = (unsigned long)index << (PAGE_SHIFT - blkbits);
- bh = nilfs_page_get_nth_block(page, block - first_block);
+ bh = get_nth_bh(bh, block - first_block);
wait_on_buffer(bh);
return bh;
@@ -50,17 +50,17 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode,
{
int blkbits = inode->i_blkbits;
pgoff_t index = blkoff >> (PAGE_SHIFT - blkbits);
- struct page *page;
+ struct folio *folio;
struct buffer_head *bh;
- page = grab_cache_page(mapping, index);
- if (unlikely(!page))
+ folio = filemap_grab_folio(mapping, index);
+ if (IS_ERR(folio))
return NULL;
- bh = __nilfs_get_page_block(page, blkoff, index, blkbits, b_state);
+ bh = __nilfs_get_folio_block(folio, blkoff, index, blkbits, b_state);
if (unlikely(!bh)) {
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
return NULL;
}
bh->b_bdev = inode->i_sb->s_bdev;
@@ -73,7 +73,7 @@ struct buffer_head *nilfs_grab_buffer(struct inode *inode,
*/
void nilfs_forget_buffer(struct buffer_head *bh)
{
- struct page *page = bh->b_page;
+ struct folio *folio = bh->b_folio;
const unsigned long clear_bits =
(BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) |
BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) |
@@ -82,12 +82,12 @@ void nilfs_forget_buffer(struct buffer_head *bh)
lock_buffer(bh);
set_mask_bits(&bh->b_state, clear_bits, 0);
- if (nilfs_page_buffers_clean(page))
- __nilfs_clear_page_dirty(page);
+ if (nilfs_folio_buffers_clean(folio))
+ __nilfs_clear_folio_dirty(folio);
bh->b_blocknr = -1;
- ClearPageUptodate(page);
- ClearPageMappedToDisk(page);
+ folio_clear_uptodate(folio);
+ folio_clear_mappedtodisk(folio);
unlock_buffer(bh);
brelse(bh);
}
@@ -104,11 +104,11 @@ void nilfs_copy_buffer(struct buffer_head *dbh, struct buffer_head *sbh)
struct page *spage = sbh->b_page, *dpage = dbh->b_page;
struct buffer_head *bh;
- kaddr0 = kmap_atomic(spage);
- kaddr1 = kmap_atomic(dpage);
+ kaddr0 = kmap_local_page(spage);
+ kaddr1 = kmap_local_page(dpage);
memcpy(kaddr1 + bh_offset(dbh), kaddr0 + bh_offset(sbh), sbh->b_size);
- kunmap_atomic(kaddr1);
- kunmap_atomic(kaddr0);
+ kunmap_local(kaddr1);
+ kunmap_local(kaddr0);
dbh->b_state = sbh->b_state & NILFS_BUFFER_INHERENT_BITS;
dbh->b_blocknr = sbh->b_blocknr;
@@ -132,48 +132,49 @@ void nilfs_copy_buffer(struct buffer_head *dbh, struct buffer_head *sbh)
}
/**
- * nilfs_page_buffers_clean - check if a page has dirty buffers or not.
- * @page: page to be checked
+ * nilfs_folio_buffers_clean - Check if a folio has dirty buffers or not.
+ * @folio: Folio to be checked.
*
- * nilfs_page_buffers_clean() returns zero if the page has dirty buffers.
- * Otherwise, it returns non-zero value.
+ * nilfs_folio_buffers_clean() returns false if the folio has dirty buffers.
+ * Otherwise, it returns true.
*/
-int nilfs_page_buffers_clean(struct page *page)
+bool nilfs_folio_buffers_clean(struct folio *folio)
{
struct buffer_head *bh, *head;
- bh = head = page_buffers(page);
+ bh = head = folio_buffers(folio);
do {
if (buffer_dirty(bh))
- return 0;
+ return false;
bh = bh->b_this_page;
} while (bh != head);
- return 1;
+ return true;
}
-void nilfs_page_bug(struct page *page)
+void nilfs_folio_bug(struct folio *folio)
{
+ struct buffer_head *bh, *head;
struct address_space *m;
unsigned long ino;
- if (unlikely(!page)) {
- printk(KERN_CRIT "NILFS_PAGE_BUG(NULL)\n");
+ if (unlikely(!folio)) {
+ printk(KERN_CRIT "NILFS_FOLIO_BUG(NULL)\n");
return;
}
- m = page->mapping;
+ m = folio->mapping;
ino = m ? m->host->i_ino : 0;
- printk(KERN_CRIT "NILFS_PAGE_BUG(%p): cnt=%d index#=%llu flags=0x%lx "
+ printk(KERN_CRIT "NILFS_FOLIO_BUG(%p): cnt=%d index#=%llu flags=0x%lx "
"mapping=%p ino=%lu\n",
- page, page_ref_count(page),
- (unsigned long long)page->index, page->flags, m, ino);
+ folio, folio_ref_count(folio),
+ (unsigned long long)folio->index, folio->flags, m, ino);
- if (page_has_buffers(page)) {
- struct buffer_head *bh, *head;
+ head = folio_buffers(folio);
+ if (head) {
int i = 0;
- bh = head = page_buffers(page);
+ bh = head;
do {
printk(KERN_CRIT
" BH[%d] %p: cnt=%d block#=%llu state=0x%lx\n",
@@ -185,30 +186,32 @@ void nilfs_page_bug(struct page *page)
}
/**
- * nilfs_copy_page -- copy the page with buffers
- * @dst: destination page
- * @src: source page
- * @copy_dirty: flag whether to copy dirty states on the page's buffer heads.
+ * nilfs_copy_folio -- copy the folio with buffers
+ * @dst: destination folio
+ * @src: source folio
+ * @copy_dirty: flag whether to copy dirty states on the folio's buffer heads.
*
- * This function is for both data pages and btnode pages. The dirty flag
- * should be treated by caller. The page must not be under i/o.
- * Both src and dst page must be locked
+ * This function is for both data folios and btnode folios. The dirty flag
+ * should be treated by caller. The folio must not be under i/o.
+ * Both src and dst folio must be locked
*/
-static void nilfs_copy_page(struct page *dst, struct page *src, int copy_dirty)
+static void nilfs_copy_folio(struct folio *dst, struct folio *src,
+ bool copy_dirty)
{
struct buffer_head *dbh, *dbufs, *sbh;
unsigned long mask = NILFS_BUFFER_INHERENT_BITS;
- BUG_ON(PageWriteback(dst));
+ BUG_ON(folio_test_writeback(dst));
- sbh = page_buffers(src);
- if (!page_has_buffers(dst))
- create_empty_buffers(dst, sbh->b_size, 0);
+ sbh = folio_buffers(src);
+ dbh = folio_buffers(dst);
+ if (!dbh)
+ dbh = create_empty_buffers(dst, sbh->b_size, 0);
if (copy_dirty)
mask |= BIT(BH_Dirty);
- dbh = dbufs = page_buffers(dst);
+ dbufs = dbh;
do {
lock_buffer(sbh);
lock_buffer(dbh);
@@ -219,16 +222,16 @@ static void nilfs_copy_page(struct page *dst, struct page *src, int copy_dirty)
dbh = dbh->b_this_page;
} while (dbh != dbufs);
- copy_highpage(dst, src);
+ folio_copy(dst, src);
- if (PageUptodate(src) && !PageUptodate(dst))
- SetPageUptodate(dst);
- else if (!PageUptodate(src) && PageUptodate(dst))
- ClearPageUptodate(dst);
- if (PageMappedToDisk(src) && !PageMappedToDisk(dst))
- SetPageMappedToDisk(dst);
- else if (!PageMappedToDisk(src) && PageMappedToDisk(dst))
- ClearPageMappedToDisk(dst);
+ if (folio_test_uptodate(src) && !folio_test_uptodate(dst))
+ folio_mark_uptodate(dst);
+ else if (!folio_test_uptodate(src) && folio_test_uptodate(dst))
+ folio_clear_uptodate(dst);
+ if (folio_test_mappedtodisk(src) && !folio_test_mappedtodisk(dst))
+ folio_set_mappedtodisk(dst);
+ else if (!folio_test_mappedtodisk(src) && folio_test_mappedtodisk(dst))
+ folio_clear_mappedtodisk(dst);
do {
unlock_buffer(sbh);
@@ -257,20 +260,20 @@ repeat:
folio_lock(folio);
if (unlikely(!folio_test_dirty(folio)))
- NILFS_PAGE_BUG(&folio->page, "inconsistent dirty state");
+ NILFS_FOLIO_BUG(folio, "inconsistent dirty state");
dfolio = filemap_grab_folio(dmap, folio->index);
- if (unlikely(IS_ERR(dfolio))) {
+ if (IS_ERR(dfolio)) {
/* No empty page is added to the page cache */
folio_unlock(folio);
err = PTR_ERR(dfolio);
break;
}
if (unlikely(!folio_buffers(folio)))
- NILFS_PAGE_BUG(&folio->page,
+ NILFS_FOLIO_BUG(folio,
"found empty page in dat page cache");
- nilfs_copy_page(&dfolio->page, &folio->page, 1);
+ nilfs_copy_folio(dfolio, folio, true);
filemap_dirty_folio(folio_mapping(dfolio), dfolio);
folio_unlock(dfolio);
@@ -315,7 +318,7 @@ repeat:
if (!IS_ERR(dfolio)) {
/* overwrite existing folio in the destination cache */
WARN_ON(folio_test_dirty(dfolio));
- nilfs_copy_page(&dfolio->page, &folio->page, 0);
+ nilfs_copy_folio(dfolio, folio, false);
folio_unlock(dfolio);
folio_put(dfolio);
/* Do we not need to remove folio from smap here? */
@@ -355,9 +358,8 @@ repeat:
/**
* nilfs_clear_dirty_pages - discard dirty pages in address space
* @mapping: address space with dirty pages for discarding
- * @silent: suppress [true] or print [false] warning messages
*/
-void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
+void nilfs_clear_dirty_pages(struct address_space *mapping)
{
struct folio_batch fbatch;
unsigned int i;
@@ -378,7 +380,7 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
* was acquired. Skip processing in that case.
*/
if (likely(folio->mapping == mapping))
- nilfs_clear_dirty_page(&folio->page, silent);
+ nilfs_clear_folio_dirty(folio);
folio_unlock(folio);
}
@@ -388,47 +390,59 @@ void nilfs_clear_dirty_pages(struct address_space *mapping, bool silent)
}
/**
- * nilfs_clear_dirty_page - discard dirty page
- * @page: dirty page that will be discarded
- * @silent: suppress [true] or print [false] warning messages
+ * nilfs_clear_folio_dirty - discard dirty folio
+ * @folio: dirty folio that will be discarded
+ *
+ * nilfs_clear_folio_dirty() clears working states including dirty state for
+ * the folio and its buffers. If the folio has buffers, clear only if it is
+ * confirmed that none of the buffer heads are busy (none have valid
+ * references and none are locked).
*/
-void nilfs_clear_dirty_page(struct page *page, bool silent)
+void nilfs_clear_folio_dirty(struct folio *folio)
{
- struct inode *inode = page->mapping->host;
- struct super_block *sb = inode->i_sb;
-
- BUG_ON(!PageLocked(page));
-
- if (!silent)
- nilfs_warn(sb, "discard dirty page: offset=%lld, ino=%lu",
- page_offset(page), inode->i_ino);
+ struct buffer_head *bh, *head;
- ClearPageUptodate(page);
- ClearPageMappedToDisk(page);
- ClearPageChecked(page);
+ BUG_ON(!folio_test_locked(folio));
- if (page_has_buffers(page)) {
- struct buffer_head *bh, *head;
+ head = folio_buffers(folio);
+ if (head) {
const unsigned long clear_bits =
(BIT(BH_Uptodate) | BIT(BH_Dirty) | BIT(BH_Mapped) |
BIT(BH_Async_Write) | BIT(BH_NILFS_Volatile) |
BIT(BH_NILFS_Checked) | BIT(BH_NILFS_Redirected) |
BIT(BH_Delay));
+ bool busy, invalidated = false;
- bh = head = page_buffers(page);
+recheck_buffers:
+ busy = false;
+ bh = head;
do {
- lock_buffer(bh);
- if (!silent)
- nilfs_warn(sb,
- "discard dirty block: blocknr=%llu, size=%zu",
- (u64)bh->b_blocknr, bh->b_size);
+ if (atomic_read(&bh->b_count) | buffer_locked(bh)) {
+ busy = true;
+ break;
+ }
+ } while (bh = bh->b_this_page, bh != head);
+
+ if (busy) {
+ if (invalidated)
+ return;
+ invalidate_bh_lrus();
+ invalidated = true;
+ goto recheck_buffers;
+ }
+ bh = head;
+ do {
+ lock_buffer(bh);
set_mask_bits(&bh->b_state, clear_bits, 0);
unlock_buffer(bh);
} while (bh = bh->b_this_page, bh != head);
}
- __nilfs_clear_page_dirty(page);
+ folio_clear_uptodate(folio);
+ folio_clear_mappedtodisk(folio);
+ folio_clear_checked(folio);
+ __nilfs_clear_folio_dirty(folio);
}
unsigned int nilfs_page_count_clean_buffers(struct page *page,
@@ -458,22 +472,23 @@ unsigned int nilfs_page_count_clean_buffers(struct page *page,
* 2) Some B-tree operations like insertion or deletion may dispose buffers
* in dirty state, and this needs to cancel the dirty state of their pages.
*/
-int __nilfs_clear_page_dirty(struct page *page)
+void __nilfs_clear_folio_dirty(struct folio *folio)
{
- struct address_space *mapping = page->mapping;
+ struct address_space *mapping = folio->mapping;
if (mapping) {
xa_lock_irq(&mapping->i_pages);
- if (test_bit(PG_dirty, &page->flags)) {
- __xa_clear_mark(&mapping->i_pages, page_index(page),
+ if (folio_test_dirty(folio)) {
+ __xa_clear_mark(&mapping->i_pages, folio->index,
PAGECACHE_TAG_DIRTY);
xa_unlock_irq(&mapping->i_pages);
- return clear_page_dirty_for_io(page);
+ folio_clear_dirty_for_io(folio);
+ return;
}
xa_unlock_irq(&mapping->i_pages);
- return 0;
+ return;
}
- return TestClearPageDirty(page);
+ folio_clear_dirty(folio);
}
/**
diff --git a/fs/nilfs2/page.h b/fs/nilfs2/page.h
index 21ddcdd4d63e..64521a03a19e 100644
--- a/fs/nilfs2/page.h
+++ b/fs/nilfs2/page.h
@@ -30,37 +30,26 @@ BUFFER_FNS(NILFS_Checked, nilfs_checked) /* buffer is verified */
BUFFER_FNS(NILFS_Redirected, nilfs_redirected) /* redirected to a copy */
-int __nilfs_clear_page_dirty(struct page *);
+void __nilfs_clear_folio_dirty(struct folio *);
struct buffer_head *nilfs_grab_buffer(struct inode *, struct address_space *,
unsigned long, unsigned long);
void nilfs_forget_buffer(struct buffer_head *);
void nilfs_copy_buffer(struct buffer_head *, struct buffer_head *);
-int nilfs_page_buffers_clean(struct page *);
-void nilfs_page_bug(struct page *);
+bool nilfs_folio_buffers_clean(struct folio *);
+void nilfs_folio_bug(struct folio *);
int nilfs_copy_dirty_pages(struct address_space *, struct address_space *);
void nilfs_copy_back_pages(struct address_space *, struct address_space *);
-void nilfs_clear_dirty_page(struct page *, bool);
-void nilfs_clear_dirty_pages(struct address_space *, bool);
+void nilfs_clear_folio_dirty(struct folio *folio);
+void nilfs_clear_dirty_pages(struct address_space *mapping);
unsigned int nilfs_page_count_clean_buffers(struct page *, unsigned int,
unsigned int);
unsigned long nilfs_find_uncommitted_extent(struct inode *inode,
sector_t start_blk,
sector_t *blkoff);
-#define NILFS_PAGE_BUG(page, m, a...) \
- do { nilfs_page_bug(page); BUG(); } while (0)
-
-static inline struct buffer_head *
-nilfs_page_get_nth_block(struct page *page, unsigned int count)
-{
- struct buffer_head *bh = page_buffers(page);
-
- while (count-- > 0)
- bh = bh->b_this_page;
- get_bh(bh);
- return bh;
-}
+#define NILFS_FOLIO_BUG(folio, m, a...) \
+ do { nilfs_folio_bug(folio); BUG(); } while (0)
#endif /* _NILFS_PAGE_H */
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index ce30b51ac593..21d81097a89f 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -433,8 +433,17 @@ static int nilfs_prepare_segment_for_recovery(struct the_nilfs *nilfs,
* The next segment is invalidated by this recovery.
*/
err = nilfs_sufile_free(sufile, segnum[1]);
- if (unlikely(err))
+ if (unlikely(err)) {
+ if (err == -ENOENT) {
+ nilfs_err(sb,
+ "checkpoint log inconsistency at block %llu (segment %llu): next segment %llu is unallocated",
+ (unsigned long long)nilfs->ns_last_pseg,
+ (unsigned long long)nilfs->ns_segnum,
+ (unsigned long long)segnum[1]);
+ err = -EINVAL;
+ }
goto failed;
+ }
for (i = 1; i < 4; i++) {
err = nilfs_segment_list_add(head, segnum[i]);
@@ -482,9 +491,9 @@ static int nilfs_recovery_copy_block(struct the_nilfs *nilfs,
if (unlikely(!bh_org))
return -EIO;
- kaddr = kmap_atomic(page);
+ kaddr = kmap_local_page(page);
memcpy(kaddr + from, bh_org->b_data, bh_org->b_size);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(bh_org);
return 0;
}
@@ -498,7 +507,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
struct inode *inode;
struct nilfs_recovery_block *rb, *n;
unsigned int blocksize = nilfs->ns_blocksize;
- struct page *page;
+ struct folio *folio;
loff_t pos;
int err = 0, err2 = 0;
@@ -512,7 +521,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
pos = rb->blkoff << inode->i_blkbits;
err = block_write_begin(inode->i_mapping, pos, blocksize,
- &page, nilfs_get_block);
+ &folio, nilfs_get_block);
if (unlikely(err)) {
loff_t isize = inode->i_size;
@@ -522,7 +531,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
goto failed_inode;
}
- err = nilfs_recovery_copy_block(nilfs, rb, pos, page);
+ err = nilfs_recovery_copy_block(nilfs, rb, pos, &folio->page);
if (unlikely(err))
goto failed_page;
@@ -531,17 +540,17 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
goto failed_page;
block_write_end(NULL, inode->i_mapping, pos, blocksize,
- blocksize, page, NULL);
+ blocksize, folio, NULL);
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
(*nr_salvaged_blocks)++;
goto next;
failed_page:
- unlock_page(page);
- put_page(page);
+ folio_unlock(folio);
+ folio_put(folio);
failed_inode:
nilfs_warn(sb,
@@ -563,6 +572,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
* checkpoint
* @nilfs: nilfs object
* @sb: super block instance
+ * @root: NILFS root instance
* @ri: pointer to a nilfs_recovery_info
*/
static int nilfs_do_roll_forward(struct the_nilfs *nilfs,
@@ -698,9 +708,15 @@ static void nilfs_finish_roll_forward(struct the_nilfs *nilfs,
return;
bh = __getblk(nilfs->ns_bdev, ri->ri_lsegs_start, nilfs->ns_blocksize);
- BUG_ON(!bh);
+ if (WARN_ON(!bh))
+ return; /* should never happen */
+
+ lock_buffer(bh);
memset(bh->b_data, 0, bh->b_size);
+ set_buffer_uptodate(bh);
set_buffer_dirty(bh);
+ unlock_buffer(bh);
+
err = sync_dirty_buffer(bh);
if (unlikely(err))
nilfs_warn(nilfs->ns_sb,
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 6e59dc19a732..dc431b4c34c9 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -220,9 +220,9 @@ static void nilfs_segbuf_fill_in_data_crc(struct nilfs_segment_buffer *segbuf,
crc = crc32_le(crc, bh->b_data, bh->b_size);
}
list_for_each_entry(bh, &segbuf->sb_payload_buffers, b_assoc_buffers) {
- kaddr = kmap_atomic(bh->b_page);
+ kaddr = kmap_local_page(bh->b_page);
crc = crc32_le(crc, kaddr + bh_offset(bh), bh->b_size);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
}
raw_sum->ss_datasum = cpu_to_le32(crc);
}
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index 0610cb12c11c..58a598b548fa 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -519,7 +519,7 @@ static void nilfs_segctor_end_finfo(struct nilfs_sc_info *sci,
ii = NILFS_I(inode);
- if (test_bit(NILFS_I_GCINODE, &ii->i_state))
+ if (ii->i_type & NILFS_I_TYPE_GC)
cno = ii->i_cno;
else if (NILFS_ROOT_METADATA_FILE(inode->i_ino))
cno = 0;
@@ -731,11 +731,9 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
continue;
}
head = folio_buffers(folio);
- if (!head) {
- create_empty_buffers(&folio->page, i_blocksize(inode), 0);
- head = folio_buffers(folio);
- }
- folio_unlock(folio);
+ if (!head)
+ head = create_empty_buffers(folio,
+ i_blocksize(inode), 0);
bh = head;
do {
@@ -745,11 +743,14 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
list_add_tail(&bh->b_assoc_buffers, listp);
ndirties++;
if (unlikely(ndirties >= nlimit)) {
+ folio_unlock(folio);
folio_batch_release(&fbatch);
cond_resched();
return ndirties;
}
} while (bh = bh->b_this_page, bh != head);
+
+ folio_unlock(folio);
}
folio_batch_release(&fbatch);
cond_resched();
@@ -881,76 +882,6 @@ static void nilfs_segctor_clear_metadata_dirty(struct nilfs_sc_info *sci)
nilfs_mdt_clear_dirty(nilfs->ns_dat);
}
-static int nilfs_segctor_create_checkpoint(struct nilfs_sc_info *sci)
-{
- struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
- struct buffer_head *bh_cp;
- struct nilfs_checkpoint *raw_cp;
- int err;
-
- /* XXX: this interface will be changed */
- err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, 1,
- &raw_cp, &bh_cp);
- if (likely(!err)) {
- /*
- * The following code is duplicated with cpfile. But, it is
- * needed to collect the checkpoint even if it was not newly
- * created.
- */
- mark_buffer_dirty(bh_cp);
- nilfs_mdt_mark_dirty(nilfs->ns_cpfile);
- nilfs_cpfile_put_checkpoint(
- nilfs->ns_cpfile, nilfs->ns_cno, bh_cp);
- } else if (err == -EINVAL || err == -ENOENT) {
- nilfs_error(sci->sc_super,
- "checkpoint creation failed due to metadata corruption.");
- err = -EIO;
- }
- return err;
-}
-
-static int nilfs_segctor_fill_in_checkpoint(struct nilfs_sc_info *sci)
-{
- struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
- struct buffer_head *bh_cp;
- struct nilfs_checkpoint *raw_cp;
- int err;
-
- err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, 0,
- &raw_cp, &bh_cp);
- if (unlikely(err)) {
- if (err == -EINVAL || err == -ENOENT) {
- nilfs_error(sci->sc_super,
- "checkpoint finalization failed due to metadata corruption.");
- err = -EIO;
- }
- goto failed_ibh;
- }
- raw_cp->cp_snapshot_list.ssl_next = 0;
- raw_cp->cp_snapshot_list.ssl_prev = 0;
- raw_cp->cp_inodes_count =
- cpu_to_le64(atomic64_read(&sci->sc_root->inodes_count));
- raw_cp->cp_blocks_count =
- cpu_to_le64(atomic64_read(&sci->sc_root->blocks_count));
- raw_cp->cp_nblk_inc =
- cpu_to_le64(sci->sc_nblk_inc + sci->sc_nblk_this_inc);
- raw_cp->cp_create = cpu_to_le64(sci->sc_seg_ctime);
- raw_cp->cp_cno = cpu_to_le64(nilfs->ns_cno);
-
- if (test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags))
- nilfs_checkpoint_clear_minor(raw_cp);
- else
- nilfs_checkpoint_set_minor(raw_cp);
-
- nilfs_write_inode_common(sci->sc_root->ifile,
- &raw_cp->cp_ifile_inode, 1);
- nilfs_cpfile_put_checkpoint(nilfs->ns_cpfile, nilfs->ns_cno, bh_cp);
- return 0;
-
- failed_ibh:
- return err;
-}
-
static void nilfs_fill_in_file_bmap(struct inode *ifile,
struct nilfs_inode_info *ii)
@@ -964,7 +895,7 @@ static void nilfs_fill_in_file_bmap(struct inode *ifile,
raw_inode = nilfs_ifile_map_inode(ifile, ii->vfs_inode.i_ino,
ibh);
nilfs_bmap_write(ii->i_bmap, raw_inode);
- nilfs_ifile_unmap_inode(ifile, ii->vfs_inode.i_ino, ibh);
+ nilfs_ifile_unmap_inode(raw_inode);
}
}
@@ -978,6 +909,33 @@ static void nilfs_segctor_fill_in_file_bmap(struct nilfs_sc_info *sci)
}
}
+/**
+ * nilfs_write_root_mdt_inode - export root metadata inode information to
+ * the on-disk inode
+ * @inode: inode object of the root metadata file
+ * @raw_inode: on-disk inode
+ *
+ * nilfs_write_root_mdt_inode() writes inode information and bmap data of
+ * @inode to the inode area of the metadata file allocated on the super root
+ * block created to finalize the log. Since super root blocks are configured
+ * each time, this function zero-fills the unused area of @raw_inode.
+ */
+static void nilfs_write_root_mdt_inode(struct inode *inode,
+ struct nilfs_inode *raw_inode)
+{
+ struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
+
+ nilfs_write_inode_common(inode, raw_inode);
+
+ /* zero-fill unused portion of raw_inode */
+ raw_inode->i_xattr = 0;
+ raw_inode->i_pad = 0;
+ memset((void *)raw_inode + sizeof(*raw_inode), 0,
+ nilfs->ns_inode_size - sizeof(*raw_inode));
+
+ nilfs_bmap_write(NILFS_I(inode)->i_bmap, raw_inode);
+}
+
static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci,
struct the_nilfs *nilfs)
{
@@ -999,12 +957,13 @@ static void nilfs_segctor_fill_in_super_root(struct nilfs_sc_info *sci,
nilfs->ns_nongc_ctime : sci->sc_seg_ctime);
raw_sr->sr_flags = 0;
- nilfs_write_inode_common(nilfs->ns_dat, (void *)raw_sr +
- NILFS_SR_DAT_OFFSET(isz), 1);
- nilfs_write_inode_common(nilfs->ns_cpfile, (void *)raw_sr +
- NILFS_SR_CPFILE_OFFSET(isz), 1);
- nilfs_write_inode_common(nilfs->ns_sufile, (void *)raw_sr +
- NILFS_SR_SUFILE_OFFSET(isz), 1);
+ nilfs_write_root_mdt_inode(nilfs->ns_dat, (void *)raw_sr +
+ NILFS_SR_DAT_OFFSET(isz));
+ nilfs_write_root_mdt_inode(nilfs->ns_cpfile, (void *)raw_sr +
+ NILFS_SR_CPFILE_OFFSET(isz));
+ nilfs_write_root_mdt_inode(nilfs->ns_sufile, (void *)raw_sr +
+ NILFS_SR_SUFILE_OFFSET(isz));
+
memset((void *)raw_sr + srsz, 0, nilfs->ns_blocksize - srsz);
set_buffer_uptodate(bh_sr);
unlock_buffer(bh_sr);
@@ -1145,12 +1104,64 @@ static int nilfs_segctor_scan_file_dsync(struct nilfs_sc_info *sci,
return err;
}
+/**
+ * nilfs_free_segments - free the segments given by an array of segment numbers
+ * @nilfs: nilfs object
+ * @segnumv: array of segment numbers to be freed
+ * @nsegs: number of segments to be freed in @segnumv
+ *
+ * nilfs_free_segments() wraps nilfs_sufile_freev() and
+ * nilfs_sufile_cancel_freev(), and edits the segment usage metadata file
+ * (sufile) to free all segments given by @segnumv and @nsegs at once. If
+ * it fails midway, it cancels the changes so that none of the segments are
+ * freed. If @nsegs is 0, this function does nothing.
+ *
+ * The freeing of segments is not finalized until the writing of a log with
+ * a super root block containing this sufile change is complete, and it can
+ * be canceled with nilfs_sufile_cancel_freev() until then.
+ *
+ * Return: 0 on success, or the following negative error code on failure.
+ * * %-EINVAL - Invalid segment number.
+ * * %-EIO - I/O error (including metadata corruption).
+ * * %-ENOMEM - Insufficient memory available.
+ */
+static int nilfs_free_segments(struct the_nilfs *nilfs, __u64 *segnumv,
+ size_t nsegs)
+{
+ size_t ndone;
+ int ret;
+
+ if (!nsegs)
+ return 0;
+
+ ret = nilfs_sufile_freev(nilfs->ns_sufile, segnumv, nsegs, &ndone);
+ if (unlikely(ret)) {
+ nilfs_sufile_cancel_freev(nilfs->ns_sufile, segnumv, ndone,
+ NULL);
+ /*
+ * If a segment usage of the segments to be freed is in a
+ * hole block, nilfs_sufile_freev() will return -ENOENT.
+ * In this case, -EINVAL should be returned to the caller
+ * since there is something wrong with the given segment
+ * number array. This error can only occur during GC, so
+ * there is no need to worry about it propagating to other
+ * callers (such as fsync).
+ */
+ if (ret == -ENOENT) {
+ nilfs_err(nilfs->ns_sb,
+ "The segment usage entry %llu to be freed is invalid (in a hole)",
+ (unsigned long long)segnumv[ndone]);
+ ret = -EINVAL;
+ }
+ }
+ return ret;
+}
+
static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
{
struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
struct list_head *head;
struct nilfs_inode_info *ii;
- size_t ndone;
int err = 0;
switch (nilfs_sc_cstage_get(sci)) {
@@ -1231,7 +1242,8 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
break;
nilfs_sc_cstage_inc(sci);
/* Creating a checkpoint */
- err = nilfs_segctor_create_checkpoint(sci);
+ err = nilfs_cpfile_create_checkpoint(nilfs->ns_cpfile,
+ nilfs->ns_cno);
if (unlikely(err))
break;
fallthrough;
@@ -1243,14 +1255,10 @@ static int nilfs_segctor_collect_blocks(struct nilfs_sc_info *sci, int mode)
nilfs_sc_cstage_inc(sci);
fallthrough;
case NILFS_ST_SUFILE:
- err = nilfs_sufile_freev(nilfs->ns_sufile, sci->sc_freesegs,
- sci->sc_nfreesegs, &ndone);
- if (unlikely(err)) {
- nilfs_sufile_cancel_freev(nilfs->ns_sufile,
- sci->sc_freesegs, ndone,
- NULL);
+ err = nilfs_free_segments(nilfs, sci->sc_freesegs,
+ sci->sc_nfreesegs);
+ if (unlikely(err))
break;
- }
sci->sc_stage.flags |= NILFS_CF_SUFREED;
err = nilfs_segctor_scan_file(sci, nilfs->ns_sufile,
@@ -1666,71 +1674,95 @@ static int nilfs_segctor_assign(struct nilfs_sc_info *sci, int mode)
return 0;
}
-static void nilfs_begin_page_io(struct page *page)
+static void nilfs_begin_folio_io(struct folio *folio)
{
- if (!page || PageWriteback(page))
+ if (!folio || folio_test_writeback(folio))
/*
* For split b-tree node pages, this function may be called
* twice. We ignore the 2nd or later calls by this check.
*/
return;
- lock_page(page);
- clear_page_dirty_for_io(page);
- set_page_writeback(page);
- unlock_page(page);
+ folio_lock(folio);
+ folio_clear_dirty_for_io(folio);
+ folio_start_writeback(folio);
+ folio_unlock(folio);
}
-static void nilfs_segctor_prepare_write(struct nilfs_sc_info *sci)
+/**
+ * nilfs_prepare_write_logs - prepare to write logs
+ * @logs: logs to prepare for writing
+ * @seed: checksum seed value
+ *
+ * nilfs_prepare_write_logs() adds checksums and prepares the block
+ * buffers/folios for writing logs. In order to stabilize folios of
+ * memory-mapped file blocks by putting them in writeback state before
+ * calculating the checksums, first prepare to write payload blocks other
+ * than segment summary and super root blocks in which the checksums will
+ * be embedded.
+ */
+static void nilfs_prepare_write_logs(struct list_head *logs, u32 seed)
{
struct nilfs_segment_buffer *segbuf;
- struct page *bd_page = NULL, *fs_page = NULL;
-
- list_for_each_entry(segbuf, &sci->sc_segbufs, sb_list) {
- struct buffer_head *bh;
+ struct folio *bd_folio = NULL, *fs_folio = NULL;
+ struct buffer_head *bh;
- list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
+ /* Prepare to write payload blocks */
+ list_for_each_entry(segbuf, logs, sb_list) {
+ list_for_each_entry(bh, &segbuf->sb_payload_buffers,
b_assoc_buffers) {
- if (bh->b_page != bd_page) {
- if (bd_page) {
- lock_page(bd_page);
- wait_on_page_writeback(bd_page);
- clear_page_dirty_for_io(bd_page);
- set_page_writeback(bd_page);
- unlock_page(bd_page);
- }
- bd_page = bh->b_page;
+ if (bh == segbuf->sb_super_root)
+ break;
+ set_buffer_async_write(bh);
+ if (bh->b_folio != fs_folio) {
+ nilfs_begin_folio_io(fs_folio);
+ fs_folio = bh->b_folio;
}
}
+ }
+ nilfs_begin_folio_io(fs_folio);
- list_for_each_entry(bh, &segbuf->sb_payload_buffers,
+ nilfs_add_checksums_on_logs(logs, seed);
+
+ /* Prepare to write segment summary blocks */
+ list_for_each_entry(segbuf, logs, sb_list) {
+ list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
b_assoc_buffers) {
- if (bh == segbuf->sb_super_root) {
- if (bh->b_page != bd_page) {
- lock_page(bd_page);
- wait_on_page_writeback(bd_page);
- clear_page_dirty_for_io(bd_page);
- set_page_writeback(bd_page);
- unlock_page(bd_page);
- bd_page = bh->b_page;
- }
- break;
- }
- set_buffer_async_write(bh);
- if (bh->b_page != fs_page) {
- nilfs_begin_page_io(fs_page);
- fs_page = bh->b_page;
+ mark_buffer_dirty(bh);
+ if (bh->b_folio == bd_folio)
+ continue;
+ if (bd_folio) {
+ folio_lock(bd_folio);
+ folio_wait_writeback(bd_folio);
+ folio_clear_dirty_for_io(bd_folio);
+ folio_start_writeback(bd_folio);
+ folio_unlock(bd_folio);
}
+ bd_folio = bh->b_folio;
}
}
- if (bd_page) {
- lock_page(bd_page);
- wait_on_page_writeback(bd_page);
- clear_page_dirty_for_io(bd_page);
- set_page_writeback(bd_page);
- unlock_page(bd_page);
+
+ /* Prepare to write super root block */
+ bh = NILFS_LAST_SEGBUF(logs)->sb_super_root;
+ if (bh) {
+ mark_buffer_dirty(bh);
+ if (bh->b_folio != bd_folio) {
+ folio_lock(bd_folio);
+ folio_wait_writeback(bd_folio);
+ folio_clear_dirty_for_io(bd_folio);
+ folio_start_writeback(bd_folio);
+ folio_unlock(bd_folio);
+ bd_folio = bh->b_folio;
+ }
+ }
+
+ if (bd_folio) {
+ folio_lock(bd_folio);
+ folio_wait_writeback(bd_folio);
+ folio_clear_dirty_for_io(bd_folio);
+ folio_start_writeback(bd_folio);
+ folio_unlock(bd_folio);
}
- nilfs_begin_page_io(fs_page);
}
static int nilfs_segctor_write(struct nilfs_sc_info *sci,
@@ -1743,17 +1775,18 @@ static int nilfs_segctor_write(struct nilfs_sc_info *sci,
return ret;
}
-static void nilfs_end_page_io(struct page *page, int err)
+static void nilfs_end_folio_io(struct folio *folio, int err)
{
- if (!page)
+ if (!folio)
return;
- if (buffer_nilfs_node(page_buffers(page)) && !PageWriteback(page)) {
+ if (buffer_nilfs_node(folio_buffers(folio)) &&
+ !folio_test_writeback(folio)) {
/*
* For b-tree node pages, this function may be called twice
* or more because they might be split in a segment.
*/
- if (PageDirty(page)) {
+ if (folio_test_dirty(folio)) {
/*
* For pages holding split b-tree node buffers, dirty
* flag on the buffers may be cleared discretely.
@@ -1761,30 +1794,24 @@ static void nilfs_end_page_io(struct page *page, int err)
* remaining buffers, and it must be cancelled if
* all the buffers get cleaned later.
*/
- lock_page(page);
- if (nilfs_page_buffers_clean(page))
- __nilfs_clear_page_dirty(page);
- unlock_page(page);
+ folio_lock(folio);
+ if (nilfs_folio_buffers_clean(folio))
+ __nilfs_clear_folio_dirty(folio);
+ folio_unlock(folio);
}
return;
}
- if (!err) {
- if (!nilfs_page_buffers_clean(page))
- __set_page_dirty_nobuffers(page);
- ClearPageError(page);
- } else {
- __set_page_dirty_nobuffers(page);
- SetPageError(page);
- }
+ if (err || !nilfs_folio_buffers_clean(folio))
+ filemap_dirty_folio(folio->mapping, folio);
- end_page_writeback(page);
+ folio_end_writeback(folio);
}
static void nilfs_abort_logs(struct list_head *logs, int err)
{
struct nilfs_segment_buffer *segbuf;
- struct page *bd_page = NULL, *fs_page = NULL;
+ struct folio *bd_folio = NULL, *fs_folio = NULL;
struct buffer_head *bh;
if (list_empty(logs))
@@ -1794,10 +1821,10 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
list_for_each_entry(bh, &segbuf->sb_segsum_buffers,
b_assoc_buffers) {
clear_buffer_uptodate(bh);
- if (bh->b_page != bd_page) {
- if (bd_page)
- end_page_writeback(bd_page);
- bd_page = bh->b_page;
+ if (bh->b_folio != bd_folio) {
+ if (bd_folio)
+ folio_end_writeback(bd_folio);
+ bd_folio = bh->b_folio;
}
}
@@ -1805,23 +1832,23 @@ static void nilfs_abort_logs(struct list_head *logs, int err)
b_assoc_buffers) {
if (bh == segbuf->sb_super_root) {
clear_buffer_uptodate(bh);
- if (bh->b_page != bd_page) {
- end_page_writeback(bd_page);
- bd_page = bh->b_page;
+ if (bh->b_folio != bd_folio) {
+ folio_end_writeback(bd_folio);
+ bd_folio = bh->b_folio;
}
break;
}
clear_buffer_async_write(bh);
- if (bh->b_page != fs_page) {
- nilfs_end_page_io(fs_page, err);
- fs_page = bh->b_page;
+ if (bh->b_folio != fs_folio) {
+ nilfs_end_folio_io(fs_folio, err);
+ fs_folio = bh->b_folio;
}
}
}
- if (bd_page)
- end_page_writeback(bd_page);
+ if (bd_folio)
+ folio_end_writeback(bd_folio);
- nilfs_end_page_io(fs_page, err);
+ nilfs_end_folio_io(fs_folio, err);
}
static void nilfs_segctor_abort_construction(struct nilfs_sc_info *sci,
@@ -1866,7 +1893,7 @@ static void nilfs_set_next_segment(struct the_nilfs *nilfs,
static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
{
struct nilfs_segment_buffer *segbuf;
- struct page *bd_page = NULL, *fs_page = NULL;
+ struct folio *bd_folio = NULL, *fs_folio = NULL;
struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
int update_sr = false;
@@ -1877,21 +1904,21 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
b_assoc_buffers) {
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
- if (bh->b_page != bd_page) {
- if (bd_page)
- end_page_writeback(bd_page);
- bd_page = bh->b_page;
+ if (bh->b_folio != bd_folio) {
+ if (bd_folio)
+ folio_end_writeback(bd_folio);
+ bd_folio = bh->b_folio;
}
}
/*
- * We assume that the buffers which belong to the same page
+ * We assume that the buffers which belong to the same folio
* continue over the buffer list.
- * Under this assumption, the last BHs of pages is
- * identifiable by the discontinuity of bh->b_page
- * (page != fs_page).
+ * Under this assumption, the last BHs of folios is
+ * identifiable by the discontinuity of bh->b_folio
+ * (folio != fs_folio).
*
* For B-tree node blocks, however, this assumption is not
- * guaranteed. The cleanup code of B-tree node pages needs
+ * guaranteed. The cleanup code of B-tree node folios needs
* special care.
*/
list_for_each_entry(bh, &segbuf->sb_payload_buffers,
@@ -1905,17 +1932,17 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
if (bh == segbuf->sb_super_root) {
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
- if (bh->b_page != bd_page) {
- end_page_writeback(bd_page);
- bd_page = bh->b_page;
+ if (bh->b_folio != bd_folio) {
+ folio_end_writeback(bd_folio);
+ bd_folio = bh->b_folio;
}
update_sr = true;
break;
}
set_mask_bits(&bh->b_state, clear_bits, set_bits);
- if (bh->b_page != fs_page) {
- nilfs_end_page_io(fs_page, 0);
- fs_page = bh->b_page;
+ if (bh->b_folio != fs_folio) {
+ nilfs_end_folio_io(fs_folio, 0);
+ fs_folio = bh->b_folio;
}
}
@@ -1929,13 +1956,13 @@ static void nilfs_segctor_complete_write(struct nilfs_sc_info *sci)
}
}
/*
- * Since pages may continue over multiple segment buffers,
- * end of the last page must be checked outside of the loop.
+ * Since folios may continue over multiple segment buffers,
+ * end of the last folio must be checked outside of the loop.
*/
- if (bd_page)
- end_page_writeback(bd_page);
+ if (bd_folio)
+ folio_end_writeback(bd_folio);
- nilfs_end_page_io(fs_page, 0);
+ nilfs_end_folio_io(fs_folio, 0);
nilfs_drop_collected_inodes(&sci->sc_dirty_files);
@@ -2107,7 +2134,11 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
if (mode == SC_LSEG_SR &&
nilfs_sc_cstage_get(sci) >= NILFS_ST_CPFILE) {
- err = nilfs_segctor_fill_in_checkpoint(sci);
+ err = nilfs_cpfile_finalize_checkpoint(
+ nilfs->ns_cpfile, nilfs->ns_cno, sci->sc_root,
+ sci->sc_nblk_inc + sci->sc_nblk_this_inc,
+ sci->sc_seg_ctime,
+ !test_bit(NILFS_SC_HAVE_DELTA, &sci->sc_flags));
if (unlikely(err))
goto failed_to_write;
@@ -2116,10 +2147,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
nilfs_segctor_update_segusage(sci, nilfs->ns_sufile);
/* Write partial segments */
- nilfs_segctor_prepare_write(sci);
-
- nilfs_add_checksums_on_logs(&sci->sc_segbufs,
- nilfs->ns_crc_seed);
+ nilfs_prepare_write_logs(&sci->sc_segbufs, nilfs->ns_crc_seed);
err = nilfs_segctor_write(sci, nilfs);
if (unlikely(err))
@@ -2478,7 +2506,7 @@ static void nilfs_construction_timeout(struct timer_list *t)
{
struct nilfs_sc_info *sci = from_timer(sci, t, sc_timer);
- wake_up_process(sci->sc_timer_task);
+ wake_up_process(sci->sc_task);
}
static void
@@ -2604,122 +2632,85 @@ static int nilfs_segctor_flush_mode(struct nilfs_sc_info *sci)
}
/**
- * nilfs_segctor_thread - main loop of the segment constructor thread.
+ * nilfs_log_write_required - determine whether log writing is required
+ * @sci: nilfs_sc_info struct
+ * @modep: location for storing log writing mode
+ *
+ * Return: true if log writing is required, false otherwise. If log writing
+ * is required, the mode is stored in the location pointed to by @modep.
+ */
+static bool nilfs_log_write_required(struct nilfs_sc_info *sci, int *modep)
+{
+ bool timedout, ret = true;
+
+ spin_lock(&sci->sc_state_lock);
+ timedout = ((sci->sc_state & NILFS_SEGCTOR_COMMIT) &&
+ time_after_eq(jiffies, sci->sc_timer.expires));
+ if (timedout || sci->sc_seq_request != sci->sc_seq_done)
+ *modep = SC_LSEG_SR;
+ else if (sci->sc_flush_request)
+ *modep = nilfs_segctor_flush_mode(sci);
+ else
+ ret = false;
+
+ spin_unlock(&sci->sc_state_lock);
+ return ret;
+}
+
+/**
+ * nilfs_segctor_thread - main loop of the log writer thread
* @arg: pointer to a struct nilfs_sc_info.
*
- * nilfs_segctor_thread() initializes a timer and serves as a daemon
- * to execute segment constructions.
+ * nilfs_segctor_thread() is the main loop function of the log writer kernel
+ * thread, which determines whether log writing is necessary, and if so,
+ * performs the log write in the background, or waits if not. It is also
+ * used to decide the background writeback of the superblock.
+ *
+ * Return: Always 0.
*/
static int nilfs_segctor_thread(void *arg)
{
struct nilfs_sc_info *sci = (struct nilfs_sc_info *)arg;
struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
- int timeout = 0;
-
- sci->sc_timer_task = current;
- timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0);
- /* start sync. */
- sci->sc_task = current;
- wake_up(&sci->sc_wait_task); /* for nilfs_segctor_start_thread() */
nilfs_info(sci->sc_super,
"segctord starting. Construction interval = %lu seconds, CP frequency < %lu seconds",
sci->sc_interval / HZ, sci->sc_mjcp_freq / HZ);
- spin_lock(&sci->sc_state_lock);
- loop:
- for (;;) {
- int mode;
+ set_freezable();
- if (sci->sc_state & NILFS_SEGCTOR_QUIT)
- goto end_thread;
-
- if (timeout || sci->sc_seq_request != sci->sc_seq_done)
- mode = SC_LSEG_SR;
- else if (sci->sc_flush_request)
- mode = nilfs_segctor_flush_mode(sci);
- else
- break;
-
- spin_unlock(&sci->sc_state_lock);
- nilfs_segctor_thread_construct(sci, mode);
- spin_lock(&sci->sc_state_lock);
- timeout = 0;
- }
-
-
- if (freezing(current)) {
- spin_unlock(&sci->sc_state_lock);
- try_to_freeze();
- spin_lock(&sci->sc_state_lock);
- } else {
+ while (!kthread_should_stop()) {
DEFINE_WAIT(wait);
- int should_sleep = 1;
+ bool should_write;
+ int mode;
+
+ if (freezing(current)) {
+ try_to_freeze();
+ continue;
+ }
prepare_to_wait(&sci->sc_wait_daemon, &wait,
TASK_INTERRUPTIBLE);
-
- if (sci->sc_seq_request != sci->sc_seq_done)
- should_sleep = 0;
- else if (sci->sc_flush_request)
- should_sleep = 0;
- else if (sci->sc_state & NILFS_SEGCTOR_COMMIT)
- should_sleep = time_before(jiffies,
- sci->sc_timer.expires);
-
- if (should_sleep) {
- spin_unlock(&sci->sc_state_lock);
+ should_write = nilfs_log_write_required(sci, &mode);
+ if (!should_write)
schedule();
- spin_lock(&sci->sc_state_lock);
- }
finish_wait(&sci->sc_wait_daemon, &wait);
- timeout = ((sci->sc_state & NILFS_SEGCTOR_COMMIT) &&
- time_after_eq(jiffies, sci->sc_timer.expires));
if (nilfs_sb_dirty(nilfs) && nilfs_sb_need_update(nilfs))
set_nilfs_discontinued(nilfs);
+
+ if (should_write)
+ nilfs_segctor_thread_construct(sci, mode);
}
- goto loop;
- end_thread:
/* end sync. */
+ spin_lock(&sci->sc_state_lock);
sci->sc_task = NULL;
timer_shutdown_sync(&sci->sc_timer);
- wake_up(&sci->sc_wait_task); /* for nilfs_segctor_kill_thread() */
spin_unlock(&sci->sc_state_lock);
return 0;
}
-static int nilfs_segctor_start_thread(struct nilfs_sc_info *sci)
-{
- struct task_struct *t;
-
- t = kthread_run(nilfs_segctor_thread, sci, "segctord");
- if (IS_ERR(t)) {
- int err = PTR_ERR(t);
-
- nilfs_err(sci->sc_super, "error %d creating segctord thread",
- err);
- return err;
- }
- wait_event(sci->sc_wait_task, sci->sc_task != NULL);
- return 0;
-}
-
-static void nilfs_segctor_kill_thread(struct nilfs_sc_info *sci)
- __acquires(&sci->sc_state_lock)
- __releases(&sci->sc_state_lock)
-{
- sci->sc_state |= NILFS_SEGCTOR_QUIT;
-
- while (sci->sc_task) {
- wake_up(&sci->sc_wait_daemon);
- spin_unlock(&sci->sc_state_lock);
- wait_event(sci->sc_wait_task, sci->sc_task == NULL);
- spin_lock(&sci->sc_state_lock);
- }
-}
-
/*
* Setup & clean-up functions
*/
@@ -2740,7 +2731,6 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb,
init_waitqueue_head(&sci->sc_wait_request);
init_waitqueue_head(&sci->sc_wait_daemon);
- init_waitqueue_head(&sci->sc_wait_task);
spin_lock_init(&sci->sc_state_lock);
INIT_LIST_HEAD(&sci->sc_dirty_files);
INIT_LIST_HEAD(&sci->sc_segbufs);
@@ -2795,8 +2785,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
up_write(&nilfs->ns_segctor_sem);
+ if (sci->sc_task) {
+ wake_up(&sci->sc_wait_daemon);
+ kthread_stop(sci->sc_task);
+ }
+
spin_lock(&sci->sc_state_lock);
- nilfs_segctor_kill_thread(sci);
flag = ((sci->sc_state & NILFS_SEGCTOR_COMMIT) || sci->sc_flush_request
|| sci->sc_seq_request != sci->sc_seq_done);
spin_unlock(&sci->sc_state_lock);
@@ -2844,14 +2838,15 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
* This allocates a log writer object, initializes it, and starts the
* log writer.
*
- * Return Value: On success, 0 is returned. On error, one of the following
- * negative error code is returned.
- *
- * %-ENOMEM - Insufficient memory available.
+ * Return: 0 on success, or the following negative error code on failure.
+ * * %-EINTR - Log writer thread creation failed due to interruption.
+ * * %-ENOMEM - Insufficient memory available.
*/
int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root)
{
struct the_nilfs *nilfs = sb->s_fs_info;
+ struct nilfs_sc_info *sci;
+ struct task_struct *t;
int err;
if (nilfs->ns_writer) {
@@ -2864,17 +2859,23 @@ int nilfs_attach_log_writer(struct super_block *sb, struct nilfs_root *root)
return 0;
}
- nilfs->ns_writer = nilfs_segctor_new(sb, root);
- if (!nilfs->ns_writer)
+ sci = nilfs_segctor_new(sb, root);
+ if (unlikely(!sci))
return -ENOMEM;
- inode_attach_wb(nilfs->ns_bdev->bd_inode, NULL);
-
- err = nilfs_segctor_start_thread(nilfs->ns_writer);
- if (unlikely(err))
+ nilfs->ns_writer = sci;
+ t = kthread_create(nilfs_segctor_thread, sci, "segctord");
+ if (IS_ERR(t)) {
+ err = PTR_ERR(t);
+ nilfs_err(sb, "error %d creating segctord thread", err);
nilfs_detach_log_writer(sb);
+ return err;
+ }
+ sci->sc_task = t;
+ timer_setup(&sci->sc_timer, nilfs_construction_timeout, 0);
- return err;
+ wake_up_process(sci->sc_task);
+ return 0;
}
/**
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index 1060f72ebf5a..f723f47ddc4e 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -22,10 +22,10 @@ struct nilfs_root;
* struct nilfs_recovery_info - Recovery information
* @ri_need_recovery: Recovery status
* @ri_super_root: Block number of the last super root
- * @ri_ri_cno: Number of the last checkpoint
+ * @ri_cno: Number of the last checkpoint
* @ri_lsegs_start: Region for roll-forwarding (start block number)
* @ri_lsegs_end: Region for roll-forwarding (end block number)
- * @ri_lseg_start_seq: Sequence value of the segment at ri_lsegs_start
+ * @ri_lsegs_start_seq: Sequence value of the segment at ri_lsegs_start
* @ri_used_segments: List of segments to be mark active
* @ri_pseg_start: Block number of the last partial segment
* @ri_seq: Sequence number on the last partial segment
@@ -105,9 +105,8 @@ struct nilfs_segsum_pointer {
* @sc_flush_request: inode bitmap of metadata files to be flushed
* @sc_wait_request: Client request queue
* @sc_wait_daemon: Daemon wait queue
- * @sc_wait_task: Start/end wait queue to control segctord task
* @sc_seq_request: Request counter
- * @sc_seq_accept: Accepted request count
+ * @sc_seq_accepted: Accepted request count
* @sc_seq_done: Completion counter
* @sc_sync: Request of explicit sync operation
* @sc_interval: Timeout value of background construction
@@ -158,7 +157,6 @@ struct nilfs_sc_info {
wait_queue_head_t sc_wait_request;
wait_queue_head_t sc_wait_daemon;
- wait_queue_head_t sc_wait_task;
__u32 sc_seq_request;
__u32 sc_seq_accepted;
@@ -171,7 +169,6 @@ struct nilfs_sc_info {
unsigned long sc_watermark;
struct timer_list sc_timer;
- struct task_struct *sc_timer_task;
struct task_struct *sc_task;
};
@@ -192,7 +189,6 @@ enum {
};
/* sc_state */
-#define NILFS_SEGCTOR_QUIT 0x0001 /* segctord is being destroyed */
#define NILFS_SEGCTOR_COMMIT 0x0004 /* committed transaction exists */
/*
diff --git a/fs/nilfs2/sufile.c b/fs/nilfs2/sufile.c
index 58ca7c936393..eea5a6a12f7b 100644
--- a/fs/nilfs2/sufile.c
+++ b/fs/nilfs2/sufile.c
@@ -48,7 +48,7 @@ nilfs_sufile_get_blkoff(const struct inode *sufile, __u64 segnum)
{
__u64 t = segnum + NILFS_MDT(sufile)->mi_first_entry_offset;
- do_div(t, nilfs_sufile_segment_usages_per_block(sufile));
+ t = div64_ul(t, nilfs_sufile_segment_usages_per_block(sufile));
return (unsigned long)t;
}
@@ -79,10 +79,17 @@ nilfs_sufile_block_get_segment_usage(const struct inode *sufile, __u64 segnum,
NILFS_MDT(sufile)->mi_entry_size;
}
-static inline int nilfs_sufile_get_header_block(struct inode *sufile,
- struct buffer_head **bhp)
+static int nilfs_sufile_get_header_block(struct inode *sufile,
+ struct buffer_head **bhp)
{
- return nilfs_mdt_get_block(sufile, 0, 0, NULL, bhp);
+ int err = nilfs_mdt_get_block(sufile, 0, 0, NULL, bhp);
+
+ if (unlikely(err == -ENOENT)) {
+ nilfs_error(sufile->i_sb,
+ "missing header block in segment usage metadata");
+ err = -EIO;
+ }
+ return err;
}
static inline int
@@ -107,11 +114,11 @@ static void nilfs_sufile_mod_counter(struct buffer_head *header_bh,
struct nilfs_sufile_header *header;
void *kaddr;
- kaddr = kmap_atomic(header_bh->b_page);
+ kaddr = kmap_local_page(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
le64_add_cpu(&header->sh_ncleansegs, ncleanadd);
le64_add_cpu(&header->sh_ndirtysegs, ndirtyadd);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
mark_buffer_dirty(header_bh);
}
@@ -315,10 +322,10 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
ret = nilfs_sufile_get_header_block(sufile, &header_bh);
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(header_bh->b_page);
+ kaddr = kmap_local_page(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
last_alloc = le64_to_cpu(header->sh_last_alloc);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
nsegments = nilfs_sufile_get_nsegments(sufile);
maxsegnum = sui->allocmax;
@@ -352,7 +359,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
&su_bh);
if (ret < 0)
goto out_header;
- kaddr = kmap_atomic(su_bh->b_page);
+ kaddr = kmap_local_page(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(
sufile, segnum, su_bh, kaddr);
@@ -363,14 +370,14 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
continue;
/* found a clean segment */
nilfs_segment_usage_set_dirty(su);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
- kaddr = kmap_atomic(header_bh->b_page);
+ kaddr = kmap_local_page(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
le64_add_cpu(&header->sh_ncleansegs, -1);
le64_add_cpu(&header->sh_ndirtysegs, 1);
header->sh_last_alloc = cpu_to_le64(segnum);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
sui->ncleansegs--;
mark_buffer_dirty(header_bh);
@@ -384,7 +391,7 @@ int nilfs_sufile_alloc(struct inode *sufile, __u64 *segnump)
goto out_header;
}
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(su_bh);
}
@@ -406,16 +413,16 @@ void nilfs_sufile_do_cancel_free(struct inode *sufile, __u64 segnum,
struct nilfs_segment_usage *su;
void *kaddr;
- kaddr = kmap_atomic(su_bh->b_page);
+ kaddr = kmap_local_page(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
if (unlikely(!nilfs_segment_usage_clean(su))) {
nilfs_warn(sufile->i_sb, "%s: segment %llu must be clean",
__func__, (unsigned long long)segnum);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
return;
}
nilfs_segment_usage_set_dirty(su);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
nilfs_sufile_mod_counter(header_bh, -1, 1);
NILFS_SUI(sufile)->ncleansegs--;
@@ -432,11 +439,11 @@ void nilfs_sufile_do_scrap(struct inode *sufile, __u64 segnum,
void *kaddr;
int clean, dirty;
- kaddr = kmap_atomic(su_bh->b_page);
+ kaddr = kmap_local_page(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
if (su->su_flags == cpu_to_le32(BIT(NILFS_SEGMENT_USAGE_DIRTY)) &&
su->su_nblocks == cpu_to_le32(0)) {
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
return;
}
clean = nilfs_segment_usage_clean(su);
@@ -446,7 +453,7 @@ void nilfs_sufile_do_scrap(struct inode *sufile, __u64 segnum,
su->su_lastmod = cpu_to_le64(0);
su->su_nblocks = cpu_to_le32(0);
su->su_flags = cpu_to_le32(BIT(NILFS_SEGMENT_USAGE_DIRTY));
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
nilfs_sufile_mod_counter(header_bh, clean ? (u64)-1 : 0, dirty ? 0 : 1);
NILFS_SUI(sufile)->ncleansegs -= clean;
@@ -463,20 +470,25 @@ void nilfs_sufile_do_free(struct inode *sufile, __u64 segnum,
void *kaddr;
int sudirty;
- kaddr = kmap_atomic(su_bh->b_page);
+ kaddr = kmap_local_page(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
if (nilfs_segment_usage_clean(su)) {
nilfs_warn(sufile->i_sb, "%s: segment %llu is already clean",
__func__, (unsigned long long)segnum);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
return;
}
- WARN_ON(nilfs_segment_usage_error(su));
- WARN_ON(!nilfs_segment_usage_dirty(su));
+ if (unlikely(nilfs_segment_usage_error(su)))
+ nilfs_warn(sufile->i_sb, "free segment %llu marked in error",
+ (unsigned long long)segnum);
sudirty = nilfs_segment_usage_dirty(su);
+ if (unlikely(!sudirty))
+ nilfs_warn(sufile->i_sb, "free unallocated segment %llu",
+ (unsigned long long)segnum);
+
nilfs_segment_usage_set_clean(su);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
mark_buffer_dirty(su_bh);
nilfs_sufile_mod_counter(header_bh, 1, sudirty ? (u64)-1 : 0);
@@ -501,15 +513,22 @@ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum)
down_write(&NILFS_MDT(sufile)->mi_sem);
ret = nilfs_sufile_get_segment_usage_block(sufile, segnum, 0, &bh);
- if (ret)
+ if (unlikely(ret)) {
+ if (ret == -ENOENT) {
+ nilfs_error(sufile->i_sb,
+ "segment usage for segment %llu is unreadable due to a hole block",
+ (unsigned long long)segnum);
+ ret = -EIO;
+ }
goto out_sem;
+ }
- kaddr = kmap_atomic(bh->b_page);
+ kaddr = kmap_local_page(bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
if (unlikely(nilfs_segment_usage_error(su))) {
struct the_nilfs *nilfs = sufile->i_sb->s_fs_info;
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(bh);
if (nilfs_segment_is_active(nilfs, segnum)) {
nilfs_error(sufile->i_sb,
@@ -527,7 +546,7 @@ int nilfs_sufile_mark_dirty(struct inode *sufile, __u64 segnum)
ret = -EIO;
} else {
nilfs_segment_usage_set_dirty(su);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
mark_buffer_dirty(bh);
nilfs_mdt_mark_dirty(sufile);
brelse(bh);
@@ -557,7 +576,7 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(bh->b_page);
+ kaddr = kmap_local_page(bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum, bh, kaddr);
if (modtime) {
/*
@@ -568,7 +587,7 @@ int nilfs_sufile_set_segment_usage(struct inode *sufile, __u64 segnum,
su->su_lastmod = cpu_to_le64(modtime);
}
su->su_nblocks = cpu_to_le32(nblocks);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
mark_buffer_dirty(bh);
nilfs_mdt_mark_dirty(sufile);
@@ -609,7 +628,7 @@ int nilfs_sufile_get_stat(struct inode *sufile, struct nilfs_sustat *sustat)
if (ret < 0)
goto out_sem;
- kaddr = kmap_atomic(header_bh->b_page);
+ kaddr = kmap_local_page(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
sustat->ss_nsegs = nilfs_sufile_get_nsegments(sufile);
sustat->ss_ncleansegs = le64_to_cpu(header->sh_ncleansegs);
@@ -619,7 +638,7 @@ int nilfs_sufile_get_stat(struct inode *sufile, struct nilfs_sustat *sustat)
spin_lock(&nilfs->ns_last_segment_lock);
sustat->ss_prot_seq = nilfs->ns_prot_seq;
spin_unlock(&nilfs->ns_last_segment_lock);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(header_bh);
out_sem:
@@ -635,15 +654,15 @@ void nilfs_sufile_do_set_error(struct inode *sufile, __u64 segnum,
void *kaddr;
int suclean;
- kaddr = kmap_atomic(su_bh->b_page);
+ kaddr = kmap_local_page(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum, su_bh, kaddr);
if (nilfs_segment_usage_error(su)) {
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
return;
}
suclean = nilfs_segment_usage_clean(su);
nilfs_segment_usage_set_error(su);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
if (suclean) {
nilfs_sufile_mod_counter(header_bh, -1, 0);
@@ -712,7 +731,7 @@ static int nilfs_sufile_truncate_range(struct inode *sufile,
/* hole */
continue;
}
- kaddr = kmap_atomic(su_bh->b_page);
+ kaddr = kmap_local_page(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(
sufile, segnum, su_bh, kaddr);
su2 = su;
@@ -721,7 +740,7 @@ static int nilfs_sufile_truncate_range(struct inode *sufile,
~BIT(NILFS_SEGMENT_USAGE_ERROR)) ||
nilfs_segment_is_active(nilfs, segnum + j)) {
ret = -EBUSY;
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(su_bh);
goto out_header;
}
@@ -733,7 +752,7 @@ static int nilfs_sufile_truncate_range(struct inode *sufile,
nc++;
}
}
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
if (nc > 0) {
mark_buffer_dirty(su_bh);
ncleaned += nc;
@@ -818,10 +837,10 @@ int nilfs_sufile_resize(struct inode *sufile, __u64 newnsegs)
sui->allocmin = 0;
}
- kaddr = kmap_atomic(header_bh->b_page);
+ kaddr = kmap_local_page(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
header->sh_ncleansegs = cpu_to_le64(sui->ncleansegs);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
mark_buffer_dirty(header_bh);
nilfs_mdt_mark_dirty(sufile);
@@ -835,21 +854,17 @@ out:
}
/**
- * nilfs_sufile_get_suinfo -
+ * nilfs_sufile_get_suinfo - get segment usage information
* @sufile: inode of segment usage file
* @segnum: segment number to start looking
- * @buf: array of suinfo
- * @sisz: byte size of suinfo
- * @nsi: size of suinfo array
- *
- * Description:
+ * @buf: array of suinfo
+ * @sisz: byte size of suinfo
+ * @nsi: size of suinfo array
*
- * Return Value: On success, 0 is returned and .... On error, one of the
- * following negative error codes is returned.
- *
- * %-EIO - I/O error.
- *
- * %-ENOMEM - Insufficient amount of memory available.
+ * Return: Count of segment usage info items stored in the output buffer on
+ * success, or the following negative error code on failure.
+ * * %-EIO - I/O error (including metadata corruption).
+ * * %-ENOMEM - Insufficient memory available.
*/
ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
unsigned int sisz, size_t nsi)
@@ -886,7 +901,7 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
continue;
}
- kaddr = kmap_atomic(su_bh->b_page);
+ kaddr = kmap_local_page(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(
sufile, segnum, su_bh, kaddr);
for (j = 0; j < n;
@@ -899,7 +914,7 @@ ssize_t nilfs_sufile_get_suinfo(struct inode *sufile, __u64 segnum, void *buf,
si->sui_flags |=
BIT(NILFS_SEGMENT_USAGE_ACTIVE);
}
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(su_bh);
}
ret = nsegs;
@@ -968,7 +983,7 @@ ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
goto out_header;
for (;;) {
- kaddr = kmap_atomic(bh->b_page);
+ kaddr = kmap_local_page(bh->b_page);
su = nilfs_sufile_block_get_segment_usage(
sufile, sup->sup_segnum, bh, kaddr);
@@ -1005,7 +1020,7 @@ ssize_t nilfs_sufile_set_suinfo(struct inode *sufile, void *buf,
su->su_flags = cpu_to_le32(sup->sup_sui.sui_flags);
}
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
sup = (void *)sup + supsz;
if (sup >= supend)
@@ -1110,7 +1125,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
continue;
}
- kaddr = kmap_atomic(su_bh->b_page);
+ kaddr = kmap_local_page(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(sufile, segnum,
su_bh, kaddr);
for (i = 0; i < n; ++i, ++segnum, su = (void *)su + susz) {
@@ -1140,7 +1155,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
}
if (nblocks >= minlen) {
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
ret = blkdev_issue_discard(nilfs->ns_bdev,
start * sects_per_block,
@@ -1152,7 +1167,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
}
ndiscarded += nblocks;
- kaddr = kmap_atomic(su_bh->b_page);
+ kaddr = kmap_local_page(su_bh->b_page);
su = nilfs_sufile_block_get_segment_usage(
sufile, segnum, su_bh, kaddr);
}
@@ -1161,7 +1176,7 @@ int nilfs_sufile_trim_fs(struct inode *sufile, struct fstrim_range *range)
start = seg_start;
nblocks = seg_end - seg_start + 1;
}
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
put_bh(su_bh);
}
@@ -1236,15 +1251,21 @@ int nilfs_sufile_read(struct super_block *sb, size_t susize,
if (err)
goto failed;
- err = nilfs_sufile_get_header_block(sufile, &header_bh);
- if (err)
+ err = nilfs_mdt_get_block(sufile, 0, 0, NULL, &header_bh);
+ if (unlikely(err)) {
+ if (err == -ENOENT) {
+ nilfs_err(sb,
+ "missing header block in segment usage metadata");
+ err = -EINVAL;
+ }
goto failed;
+ }
sui = NILFS_SUI(sufile);
- kaddr = kmap_atomic(header_bh->b_page);
+ kaddr = kmap_local_page(header_bh->b_page);
header = kaddr + bh_offset(header_bh);
sui->ncleansegs = le64_to_cpu(header->sh_ncleansegs);
- kunmap_atomic(kaddr);
+ kunmap_local(kaddr);
brelse(header_bh);
sui->allocmax = nilfs_sufile_get_nsegments(sufile) - 1;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index a5d1fa4e7552..eca79cca3803 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -29,13 +29,13 @@
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
-#include <linux/parser.h>
#include <linux/crc32.h>
#include <linux/vfs.h>
#include <linux/writeback.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/fs_context.h>
+#include <linux/fs_parser.h>
#include "nilfs.h"
#include "export.h"
#include "mdt.h"
@@ -61,7 +61,6 @@ struct kmem_cache *nilfs_segbuf_cachep;
struct kmem_cache *nilfs_btree_path_cache;
static int nilfs_setup_super(struct super_block *sb, int is_mount);
-static int nilfs_remount(struct super_block *sb, int *flags, char *data);
void __nilfs_msg(struct super_block *sb, const char *fmt, ...)
{
@@ -106,6 +105,10 @@ static void nilfs_set_error(struct super_block *sb)
/**
* __nilfs_error() - report failure condition on a filesystem
+ * @sb: super block instance
+ * @function: name of calling function
+ * @fmt: format string for message to be output
+ * @...: optional arguments to @fmt
*
* __nilfs_error() sets an ERROR_FS flag on the superblock as well as
* reporting an error message. This function should be called when
@@ -157,6 +160,7 @@ struct inode *nilfs_alloc_inode(struct super_block *sb)
return NULL;
ii->i_bh = NULL;
ii->i_state = 0;
+ ii->i_type = 0;
ii->i_cno = 0;
ii->i_assoc_inode = NULL;
ii->i_bmap = &ii->i_bmap_data;
@@ -448,7 +452,7 @@ int nilfs_resize_fs(struct super_block *sb, __u64 newsize)
sb2off = NILFS_SB2_OFFSET_BYTES(newsize);
newnsegs = sb2off >> nilfs->ns_blocksize_bits;
- do_div(newnsegs, nilfs->ns_blocks_per_segment);
+ newnsegs = div64_ul(newnsegs, nilfs->ns_blocks_per_segment);
ret = nilfs_sufile_resize(nilfs->ns_sufile, newnsegs);
up_write(&nilfs->ns_segctor_sem);
@@ -544,8 +548,6 @@ int nilfs_attach_checkpoint(struct super_block *sb, __u64 cno, int curr_mnt,
{
struct the_nilfs *nilfs = sb->s_fs_info;
struct nilfs_root *root;
- struct nilfs_checkpoint *raw_cp;
- struct buffer_head *bh_cp;
int err = -ENOMEM;
root = nilfs_find_or_create_root(
@@ -557,38 +559,19 @@ int nilfs_attach_checkpoint(struct super_block *sb, __u64 cno, int curr_mnt,
goto reuse; /* already attached checkpoint */
down_read(&nilfs->ns_segctor_sem);
- err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, cno, 0, &raw_cp,
- &bh_cp);
+ err = nilfs_ifile_read(sb, root, cno, nilfs->ns_inode_size);
up_read(&nilfs->ns_segctor_sem);
- if (unlikely(err)) {
- if (err == -ENOENT || err == -EINVAL) {
- nilfs_err(sb,
- "Invalid checkpoint (checkpoint number=%llu)",
- (unsigned long long)cno);
- err = -EINVAL;
- }
+ if (unlikely(err))
goto failed;
- }
-
- err = nilfs_ifile_read(sb, root, nilfs->ns_inode_size,
- &raw_cp->cp_ifile_inode, &root->ifile);
- if (err)
- goto failed_bh;
-
- atomic64_set(&root->inodes_count,
- le64_to_cpu(raw_cp->cp_inodes_count));
- atomic64_set(&root->blocks_count,
- le64_to_cpu(raw_cp->cp_blocks_count));
-
- nilfs_cpfile_put_checkpoint(nilfs->ns_cpfile, cno, bh_cp);
reuse:
*rootp = root;
return 0;
- failed_bh:
- nilfs_cpfile_put_checkpoint(nilfs->ns_cpfile, cno, bh_cp);
failed:
+ if (err == -EINVAL)
+ nilfs_err(sb, "Invalid checkpoint (checkpoint number=%llu)",
+ (unsigned long long)cno);
nilfs_put_root(root);
return err;
@@ -723,105 +706,98 @@ static const struct super_operations nilfs_sops = {
.freeze_fs = nilfs_freeze,
.unfreeze_fs = nilfs_unfreeze,
.statfs = nilfs_statfs,
- .remount_fs = nilfs_remount,
.show_options = nilfs_show_options
};
enum {
- Opt_err_cont, Opt_err_panic, Opt_err_ro,
- Opt_barrier, Opt_nobarrier, Opt_snapshot, Opt_order, Opt_norecovery,
- Opt_discard, Opt_nodiscard, Opt_err,
+ Opt_err, Opt_barrier, Opt_snapshot, Opt_order, Opt_norecovery,
+ Opt_discard,
};
-static match_table_t tokens = {
- {Opt_err_cont, "errors=continue"},
- {Opt_err_panic, "errors=panic"},
- {Opt_err_ro, "errors=remount-ro"},
- {Opt_barrier, "barrier"},
- {Opt_nobarrier, "nobarrier"},
- {Opt_snapshot, "cp=%u"},
- {Opt_order, "order=%s"},
- {Opt_norecovery, "norecovery"},
- {Opt_discard, "discard"},
- {Opt_nodiscard, "nodiscard"},
- {Opt_err, NULL}
+static const struct constant_table nilfs_param_err[] = {
+ {"continue", NILFS_MOUNT_ERRORS_CONT},
+ {"panic", NILFS_MOUNT_ERRORS_PANIC},
+ {"remount-ro", NILFS_MOUNT_ERRORS_RO},
+ {}
};
-static int parse_options(char *options, struct super_block *sb, int is_remount)
-{
- struct the_nilfs *nilfs = sb->s_fs_info;
- char *p;
- substring_t args[MAX_OPT_ARGS];
-
- if (!options)
- return 1;
-
- while ((p = strsep(&options, ",")) != NULL) {
- int token;
+static const struct fs_parameter_spec nilfs_param_spec[] = {
+ fsparam_enum ("errors", Opt_err, nilfs_param_err),
+ fsparam_flag_no ("barrier", Opt_barrier),
+ fsparam_u64 ("cp", Opt_snapshot),
+ fsparam_string ("order", Opt_order),
+ fsparam_flag ("norecovery", Opt_norecovery),
+ fsparam_flag_no ("discard", Opt_discard),
+ {}
+};
- if (!*p)
- continue;
+struct nilfs_fs_context {
+ unsigned long ns_mount_opt;
+ __u64 cno;
+};
- token = match_token(p, tokens, args);
- switch (token) {
- case Opt_barrier:
- nilfs_set_opt(nilfs, BARRIER);
- break;
- case Opt_nobarrier:
+static int nilfs_parse_param(struct fs_context *fc, struct fs_parameter *param)
+{
+ struct nilfs_fs_context *nilfs = fc->fs_private;
+ int is_remount = fc->purpose == FS_CONTEXT_FOR_RECONFIGURE;
+ struct fs_parse_result result;
+ int opt;
+
+ opt = fs_parse(fc, nilfs_param_spec, param, &result);
+ if (opt < 0)
+ return opt;
+
+ switch (opt) {
+ case Opt_barrier:
+ if (result.negated)
nilfs_clear_opt(nilfs, BARRIER);
- break;
- case Opt_order:
- if (strcmp(args[0].from, "relaxed") == 0)
- /* Ordered data semantics */
- nilfs_clear_opt(nilfs, STRICT_ORDER);
- else if (strcmp(args[0].from, "strict") == 0)
- /* Strict in-order semantics */
- nilfs_set_opt(nilfs, STRICT_ORDER);
- else
- return 0;
- break;
- case Opt_err_panic:
- nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_PANIC);
- break;
- case Opt_err_ro:
- nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_RO);
- break;
- case Opt_err_cont:
- nilfs_write_opt(nilfs, ERROR_MODE, ERRORS_CONT);
- break;
- case Opt_snapshot:
- if (is_remount) {
- nilfs_err(sb,
- "\"%s\" option is invalid for remount",
- p);
- return 0;
- }
- break;
- case Opt_norecovery:
- nilfs_set_opt(nilfs, NORECOVERY);
- break;
- case Opt_discard:
- nilfs_set_opt(nilfs, DISCARD);
- break;
- case Opt_nodiscard:
- nilfs_clear_opt(nilfs, DISCARD);
- break;
- default:
- nilfs_err(sb, "unrecognized mount option \"%s\"", p);
- return 0;
+ else
+ nilfs_set_opt(nilfs, BARRIER);
+ break;
+ case Opt_order:
+ if (strcmp(param->string, "relaxed") == 0)
+ /* Ordered data semantics */
+ nilfs_clear_opt(nilfs, STRICT_ORDER);
+ else if (strcmp(param->string, "strict") == 0)
+ /* Strict in-order semantics */
+ nilfs_set_opt(nilfs, STRICT_ORDER);
+ else
+ return -EINVAL;
+ break;
+ case Opt_err:
+ nilfs->ns_mount_opt &= ~NILFS_MOUNT_ERROR_MODE;
+ nilfs->ns_mount_opt |= result.uint_32;
+ break;
+ case Opt_snapshot:
+ if (is_remount) {
+ struct super_block *sb = fc->root->d_sb;
+
+ nilfs_err(sb,
+ "\"%s\" option is invalid for remount",
+ param->key);
+ return -EINVAL;
+ }
+ if (result.uint_64 == 0) {
+ nilfs_err(NULL,
+ "invalid option \"cp=0\": invalid checkpoint number 0");
+ return -EINVAL;
}
+ nilfs->cno = result.uint_64;
+ break;
+ case Opt_norecovery:
+ nilfs_set_opt(nilfs, NORECOVERY);
+ break;
+ case Opt_discard:
+ if (result.negated)
+ nilfs_clear_opt(nilfs, DISCARD);
+ else
+ nilfs_set_opt(nilfs, DISCARD);
+ break;
+ default:
+ return -EINVAL;
}
- return 1;
-}
-static inline void
-nilfs_set_default_options(struct super_block *sb,
- struct nilfs_super_block *sbp)
-{
- struct the_nilfs *nilfs = sb->s_fs_info;
-
- nilfs->ns_mount_opt =
- NILFS_MOUNT_ERRORS_RO | NILFS_MOUNT_BARRIER;
+ return 0;
}
static int nilfs_setup_super(struct super_block *sb, int is_mount)
@@ -878,9 +854,8 @@ struct nilfs_super_block *nilfs_read_super_block(struct super_block *sb,
return (struct nilfs_super_block *)((char *)(*pbh)->b_data + offset);
}
-int nilfs_store_magic_and_option(struct super_block *sb,
- struct nilfs_super_block *sbp,
- char *data)
+int nilfs_store_magic(struct super_block *sb,
+ struct nilfs_super_block *sbp)
{
struct the_nilfs *nilfs = sb->s_fs_info;
@@ -891,14 +866,12 @@ int nilfs_store_magic_and_option(struct super_block *sb,
sb->s_flags |= SB_NOATIME;
#endif
- nilfs_set_default_options(sb, sbp);
-
nilfs->ns_resuid = le16_to_cpu(sbp->s_def_resuid);
nilfs->ns_resgid = le16_to_cpu(sbp->s_def_resgid);
nilfs->ns_interval = le32_to_cpu(sbp->s_c_interval);
nilfs->ns_watermark = le32_to_cpu(sbp->s_c_block_max);
- return !parse_options(data, sb, 0) ? -EINVAL : 0;
+ return 0;
}
int nilfs_check_feature_compatibility(struct super_block *sb,
@@ -1056,17 +1029,17 @@ int nilfs_checkpoint_is_mounted(struct super_block *sb, __u64 cno)
/**
* nilfs_fill_super() - initialize a super block instance
* @sb: super_block
- * @data: mount options
- * @silent: silent mode flag
+ * @fc: filesystem context
*
* This function is called exclusively by nilfs->ns_mount_mutex.
* So, the recovery process is protected from other simultaneous mounts.
*/
static int
-nilfs_fill_super(struct super_block *sb, void *data, int silent)
+nilfs_fill_super(struct super_block *sb, struct fs_context *fc)
{
struct the_nilfs *nilfs;
struct nilfs_root *fsroot;
+ struct nilfs_fs_context *ctx = fc->fs_private;
__u64 cno;
int err;
@@ -1076,10 +1049,13 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
sb->s_fs_info = nilfs;
- err = init_nilfs(nilfs, sb, (char *)data);
+ err = init_nilfs(nilfs, sb);
if (err)
goto failed_nilfs;
+ /* Copy in parsed mount options */
+ nilfs->ns_mount_opt = ctx->ns_mount_opt;
+
sb->s_op = &nilfs_sops;
sb->s_export_op = &nilfs_export_ops;
sb->s_root = NULL;
@@ -1092,6 +1068,10 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
if (err)
goto failed_nilfs;
+ super_set_uuid(sb, nilfs->ns_sbp[0]->s_uuid,
+ sizeof(nilfs->ns_sbp[0]->s_uuid));
+ super_set_sysfs_name_bdev(sb);
+
cno = nilfs_last_cno(nilfs);
err = nilfs_attach_checkpoint(sb, cno, true, &fsroot);
if (err) {
@@ -1138,34 +1118,25 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
return err;
}
-static int nilfs_remount(struct super_block *sb, int *flags, char *data)
+static int nilfs_reconfigure(struct fs_context *fc)
{
+ struct nilfs_fs_context *ctx = fc->fs_private;
+ struct super_block *sb = fc->root->d_sb;
struct the_nilfs *nilfs = sb->s_fs_info;
- unsigned long old_sb_flags;
- unsigned long old_mount_opt;
int err;
sync_filesystem(sb);
- old_sb_flags = sb->s_flags;
- old_mount_opt = nilfs->ns_mount_opt;
-
- if (!parse_options(data, sb, 1)) {
- err = -EINVAL;
- goto restore_opts;
- }
- sb->s_flags = (sb->s_flags & ~SB_POSIXACL);
err = -EINVAL;
if (!nilfs_valid_fs(nilfs)) {
nilfs_warn(sb,
"couldn't remount because the filesystem is in an incomplete recovery state");
- goto restore_opts;
+ goto ignore_opts;
}
-
- if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
+ if ((bool)(fc->sb_flags & SB_RDONLY) == sb_rdonly(sb))
goto out;
- if (*flags & SB_RDONLY) {
+ if (fc->sb_flags & SB_RDONLY) {
sb->s_flags |= SB_RDONLY;
/*
@@ -1193,146 +1164,67 @@ static int nilfs_remount(struct super_block *sb, int *flags, char *data)
"couldn't remount RDWR because of unsupported optional features (%llx)",
(unsigned long long)features);
err = -EROFS;
- goto restore_opts;
+ goto ignore_opts;
}
sb->s_flags &= ~SB_RDONLY;
root = NILFS_I(d_inode(sb->s_root))->i_root;
err = nilfs_attach_log_writer(sb, root);
- if (err)
- goto restore_opts;
+ if (err) {
+ sb->s_flags |= SB_RDONLY;
+ goto ignore_opts;
+ }
down_write(&nilfs->ns_sem);
nilfs_setup_super(sb, true);
up_write(&nilfs->ns_sem);
}
out:
- return 0;
-
- restore_opts:
- sb->s_flags = old_sb_flags;
- nilfs->ns_mount_opt = old_mount_opt;
- return err;
-}
-
-struct nilfs_super_data {
- __u64 cno;
- int flags;
-};
-
-static int nilfs_parse_snapshot_option(const char *option,
- const substring_t *arg,
- struct nilfs_super_data *sd)
-{
- unsigned long long val;
- const char *msg = NULL;
- int err;
-
- if (!(sd->flags & SB_RDONLY)) {
- msg = "read-only option is not specified";
- goto parse_error;
- }
-
- err = kstrtoull(arg->from, 0, &val);
- if (err) {
- if (err == -ERANGE)
- msg = "too large checkpoint number";
- else
- msg = "malformed argument";
- goto parse_error;
- } else if (val == 0) {
- msg = "invalid checkpoint number 0";
- goto parse_error;
- }
- sd->cno = val;
- return 0;
-
-parse_error:
- nilfs_err(NULL, "invalid option \"%s\": %s", option, msg);
- return 1;
-}
-
-/**
- * nilfs_identify - pre-read mount options needed to identify mount instance
- * @data: mount options
- * @sd: nilfs_super_data
- */
-static int nilfs_identify(char *data, struct nilfs_super_data *sd)
-{
- char *p, *options = data;
- substring_t args[MAX_OPT_ARGS];
- int token;
- int ret = 0;
-
- do {
- p = strsep(&options, ",");
- if (p != NULL && *p) {
- token = match_token(p, tokens, args);
- if (token == Opt_snapshot)
- ret = nilfs_parse_snapshot_option(p, &args[0],
- sd);
- }
- if (!options)
- break;
- BUG_ON(options == data);
- *(options - 1) = ',';
- } while (!ret);
- return ret;
-}
+ sb->s_flags = (sb->s_flags & ~SB_POSIXACL);
+ /* Copy over parsed remount options */
+ nilfs->ns_mount_opt = ctx->ns_mount_opt;
-static int nilfs_set_bdev_super(struct super_block *s, void *data)
-{
- s->s_dev = *(dev_t *)data;
return 0;
-}
-static int nilfs_test_bdev_super(struct super_block *s, void *data)
-{
- return !(s->s_iflags & SB_I_RETIRED) && s->s_dev == *(dev_t *)data;
+ ignore_opts:
+ return err;
}
-static struct dentry *
-nilfs_mount(struct file_system_type *fs_type, int flags,
- const char *dev_name, void *data)
+static int
+nilfs_get_tree(struct fs_context *fc)
{
- struct nilfs_super_data sd = { .flags = flags };
+ struct nilfs_fs_context *ctx = fc->fs_private;
struct super_block *s;
dev_t dev;
int err;
- if (nilfs_identify(data, &sd))
- return ERR_PTR(-EINVAL);
+ if (ctx->cno && !(fc->sb_flags & SB_RDONLY)) {
+ nilfs_err(NULL,
+ "invalid option \"cp=%llu\": read-only option is not specified",
+ ctx->cno);
+ return -EINVAL;
+ }
- err = lookup_bdev(dev_name, &dev);
+ err = lookup_bdev(fc->source, &dev);
if (err)
- return ERR_PTR(err);
+ return err;
- s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, flags,
- &dev);
+ s = sget_dev(fc, dev);
if (IS_ERR(s))
- return ERR_CAST(s);
+ return PTR_ERR(s);
if (!s->s_root) {
- /*
- * We drop s_umount here because we need to open the bdev and
- * bdev->open_mutex ranks above s_umount (blkdev_put() ->
- * __invalidate_device()). It is safe because we have active sb
- * reference and SB_BORN is not set yet.
- */
- up_write(&s->s_umount);
- err = setup_bdev_super(s, flags, NULL);
- down_write(&s->s_umount);
+ err = setup_bdev_super(s, fc->sb_flags, fc);
if (!err)
- err = nilfs_fill_super(s, data,
- flags & SB_SILENT ? 1 : 0);
+ err = nilfs_fill_super(s, fc);
if (err)
goto failed_super;
s->s_flags |= SB_ACTIVE;
- } else if (!sd.cno) {
+ } else if (!ctx->cno) {
if (nilfs_tree_is_busy(s->s_root)) {
- if ((flags ^ s->s_flags) & SB_RDONLY) {
+ if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) {
nilfs_err(s,
"the device already has a %s mount.",
sb_rdonly(s) ? "read-only" : "read/write");
@@ -1341,37 +1233,75 @@ nilfs_mount(struct file_system_type *fs_type, int flags,
}
} else {
/*
- * Try remount to setup mount states if the current
+ * Try reconfigure to setup mount states if the current
* tree is not mounted and only snapshots use this sb.
+ *
+ * Since nilfs_reconfigure() requires fc->root to be
+ * set, set it first and release it on failure.
*/
- err = nilfs_remount(s, &flags, data);
- if (err)
+ fc->root = dget(s->s_root);
+ err = nilfs_reconfigure(fc);
+ if (err) {
+ dput(fc->root);
+ fc->root = NULL; /* prevent double release */
goto failed_super;
+ }
+ return 0;
}
}
- if (sd.cno) {
+ if (ctx->cno) {
struct dentry *root_dentry;
- err = nilfs_attach_snapshot(s, sd.cno, &root_dentry);
+ err = nilfs_attach_snapshot(s, ctx->cno, &root_dentry);
if (err)
goto failed_super;
- return root_dentry;
+ fc->root = root_dentry;
+ return 0;
}
- return dget(s->s_root);
+ fc->root = dget(s->s_root);
+ return 0;
failed_super:
deactivate_locked_super(s);
- return ERR_PTR(err);
+ return err;
+}
+
+static void nilfs_free_fc(struct fs_context *fc)
+{
+ kfree(fc->fs_private);
+}
+
+static const struct fs_context_operations nilfs_context_ops = {
+ .parse_param = nilfs_parse_param,
+ .get_tree = nilfs_get_tree,
+ .reconfigure = nilfs_reconfigure,
+ .free = nilfs_free_fc,
+};
+
+static int nilfs_init_fs_context(struct fs_context *fc)
+{
+ struct nilfs_fs_context *ctx;
+
+ ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+ if (!ctx)
+ return -ENOMEM;
+
+ ctx->ns_mount_opt = NILFS_MOUNT_ERRORS_RO | NILFS_MOUNT_BARRIER;
+ fc->fs_private = ctx;
+ fc->ops = &nilfs_context_ops;
+
+ return 0;
}
struct file_system_type nilfs_fs_type = {
.owner = THIS_MODULE,
.name = "nilfs2",
- .mount = nilfs_mount,
.kill_sb = kill_block_super,
.fs_flags = FS_REQUIRES_DEV,
+ .init_fs_context = nilfs_init_fs_context,
+ .parameters = nilfs_param_spec,
};
MODULE_ALIAS_FS("nilfs2");
diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c
index 905c7eadf967..14868a3dd592 100644
--- a/fs/nilfs2/sysfs.c
+++ b/fs/nilfs2/sysfs.c
@@ -56,7 +56,7 @@ static void nilfs_##name##_attr_release(struct kobject *kobj) \
sg_##name##_kobj); \
complete(&subgroups->sg_##name##_kobj_unregister); \
} \
-static struct kobj_type nilfs_##name##_ktype = { \
+static const struct kobj_type nilfs_##name##_ktype = { \
.default_groups = nilfs_##name##_groups, \
.sysfs_ops = &nilfs_##name##_attr_ops, \
.release = nilfs_##name##_attr_release, \
@@ -166,7 +166,7 @@ static const struct sysfs_ops nilfs_snapshot_attr_ops = {
.store = nilfs_snapshot_attr_store,
};
-static struct kobj_type nilfs_snapshot_ktype = {
+static const struct kobj_type nilfs_snapshot_ktype = {
.default_groups = nilfs_snapshot_groups,
.sysfs_ops = &nilfs_snapshot_attr_ops,
.release = nilfs_snapshot_attr_release,
@@ -990,7 +990,7 @@ static const struct sysfs_ops nilfs_dev_attr_ops = {
.store = nilfs_dev_attr_store,
};
-static struct kobj_type nilfs_dev_ktype = {
+static const struct kobj_type nilfs_dev_ktype = {
.default_groups = nilfs_dev_groups,
.sysfs_ops = &nilfs_dev_attr_ops,
.release = nilfs_dev_attr_release,
diff --git a/fs/nilfs2/the_nilfs.c b/fs/nilfs2/the_nilfs.c
index be41e26b7824..ecd71c190885 100644
--- a/fs/nilfs2/the_nilfs.c
+++ b/fs/nilfs2/the_nilfs.c
@@ -12,7 +12,6 @@
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
-#include <linux/random.h>
#include <linux/log2.h>
#include <linux/crc32.h>
#include "nilfs.h"
@@ -69,7 +68,6 @@ struct the_nilfs *alloc_nilfs(struct super_block *sb)
INIT_LIST_HEAD(&nilfs->ns_dirty_files);
INIT_LIST_HEAD(&nilfs->ns_gc_inodes);
spin_lock_init(&nilfs->ns_inode_lock);
- spin_lock_init(&nilfs->ns_next_gen_lock);
spin_lock_init(&nilfs->ns_last_segment_lock);
nilfs->ns_cptree = RB_ROOT;
spin_lock_init(&nilfs->ns_cptree_lock);
@@ -413,7 +411,7 @@ static u64 nilfs_max_segment_count(struct the_nilfs *nilfs)
{
u64 max_count = U64_MAX;
- do_div(max_count, nilfs->ns_blocks_per_segment);
+ max_count = div64_ul(max_count, nilfs->ns_blocks_per_segment);
return min_t(u64, max_count, ULONG_MAX);
}
@@ -598,7 +596,7 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
struct nilfs_super_block **sbp = nilfs->ns_sbp;
struct buffer_head **sbh = nilfs->ns_sbh;
u64 sb2off, devsize = bdev_nr_bytes(nilfs->ns_bdev);
- int valid[2], swp = 0;
+ int valid[2], swp = 0, older;
if (devsize < NILFS_SEG_MIN_BLOCKS * NILFS_MIN_BLOCK_SIZE + 4096) {
nilfs_err(sb, "device size too small");
@@ -654,9 +652,25 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
if (swp)
nilfs_swap_super_block(nilfs);
+ /*
+ * Calculate the array index of the older superblock data.
+ * If one has been dropped, set index 0 pointing to the remaining one,
+ * otherwise set index 1 pointing to the old one (including if both
+ * are the same).
+ *
+ * Divided case valid[0] valid[1] swp -> older
+ * -------------------------------------------------------------
+ * Both SBs are invalid 0 0 N/A (Error)
+ * SB1 is invalid 0 1 1 0
+ * SB2 is invalid 1 0 0 0
+ * SB2 is newer 1 1 1 0
+ * SB2 is older or the same 1 1 0 1
+ */
+ older = valid[1] ^ swp;
+
nilfs->ns_sbwcount = 0;
nilfs->ns_sbwtime = le64_to_cpu(sbp[0]->s_wtime);
- nilfs->ns_prot_seq = le64_to_cpu(sbp[valid[1] & !swp]->s_last_seq);
+ nilfs->ns_prot_seq = le64_to_cpu(sbp[older]->s_last_seq);
*sbpp = sbp[0];
return 0;
}
@@ -665,7 +679,6 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
* init_nilfs - initialize a NILFS instance.
* @nilfs: the_nilfs structure
* @sb: super block
- * @data: mount options
*
* init_nilfs() performs common initialization per block device (e.g.
* reading the super block, getting disk layout information, initializing
@@ -674,14 +687,12 @@ static int nilfs_load_super_block(struct the_nilfs *nilfs,
* Return Value: On success, 0 is returned. On error, a negative error
* code is returned.
*/
-int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
+int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb)
{
struct nilfs_super_block *sbp;
int blocksize;
int err;
- down_write(&nilfs->ns_sem);
-
blocksize = sb_min_blocksize(sb, NILFS_MIN_BLOCK_SIZE);
if (!blocksize) {
nilfs_err(sb, "unable to set blocksize");
@@ -692,7 +703,7 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
if (err)
goto out;
- err = nilfs_store_magic_and_option(sb, sbp, data);
+ err = nilfs_store_magic(sb, sbp);
if (err)
goto failed_sbh;
@@ -739,9 +750,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
nilfs->ns_blocksize_bits = sb->s_blocksize_bits;
nilfs->ns_blocksize = blocksize;
- get_random_bytes(&nilfs->ns_next_generation,
- sizeof(nilfs->ns_next_generation));
-
err = nilfs_store_disk_layout(nilfs, sbp);
if (err)
goto failed_sbh;
@@ -757,7 +765,6 @@ int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data)
set_nilfs_init(nilfs);
err = 0;
out:
- up_write(&nilfs->ns_sem);
return err;
failed_sbh:
diff --git a/fs/nilfs2/the_nilfs.h b/fs/nilfs2/the_nilfs.h
index 17fee562ee50..4776a70f01ae 100644
--- a/fs/nilfs2/the_nilfs.h
+++ b/fs/nilfs2/the_nilfs.h
@@ -71,8 +71,6 @@ enum {
* @ns_dirty_files: list of dirty files
* @ns_inode_lock: lock protecting @ns_dirty_files
* @ns_gc_inodes: dummy inodes to keep live blocks
- * @ns_next_generation: next generation number for inodes
- * @ns_next_gen_lock: lock protecting @ns_next_generation
* @ns_mount_opt: mount options
* @ns_resuid: uid for reserved blocks
* @ns_resgid: gid for reserved blocks
@@ -161,10 +159,6 @@ struct the_nilfs {
/* GC inode list */
struct list_head ns_gc_inodes;
- /* Inode allocator */
- u32 ns_next_generation;
- spinlock_t ns_next_gen_lock;
-
/* Mount options */
unsigned long ns_mount_opt;
@@ -219,10 +213,6 @@ THE_NILFS_FNS(PURGING, purging)
#define nilfs_set_opt(nilfs, opt) \
((nilfs)->ns_mount_opt |= NILFS_MOUNT_##opt)
#define nilfs_test_opt(nilfs, opt) ((nilfs)->ns_mount_opt & NILFS_MOUNT_##opt)
-#define nilfs_write_opt(nilfs, mask, opt) \
- ((nilfs)->ns_mount_opt = \
- (((nilfs)->ns_mount_opt & ~NILFS_MOUNT_##mask) | \
- NILFS_MOUNT_##opt)) \
/**
* struct nilfs_root - nilfs root object
@@ -276,7 +266,7 @@ static inline int nilfs_sb_will_flip(struct the_nilfs *nilfs)
void nilfs_set_last_segment(struct the_nilfs *, sector_t, u64, __u64);
struct the_nilfs *alloc_nilfs(struct super_block *sb);
void destroy_nilfs(struct the_nilfs *nilfs);
-int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb, char *data);
+int init_nilfs(struct the_nilfs *nilfs, struct super_block *sb);
int load_nilfs(struct the_nilfs *nilfs, struct super_block *sb);
unsigned long nilfs_nrsvsegs(struct the_nilfs *nilfs, unsigned long nsegs);
void nilfs_set_nsegments(struct the_nilfs *nilfs, unsigned long nsegs);
generated by cgit v1.2.3 (git 2.39.0) at 2025-08-30 09:37:03 +0300