aboutsummaryrefslogtreecommitdiff
path: root/fs/nilfs2
diff options
context:
space:
mode:
Diffstat (limited to 'fs/nilfs2')
-rw-r--r--fs/nilfs2/btree.c47
-rw-r--r--fs/nilfs2/inode.c39
-rw-r--r--fs/nilfs2/namei.c15
-rw-r--r--fs/nilfs2/nilfs.h2
-rw-r--r--fs/nilfs2/segment.c45
-rw-r--r--fs/nilfs2/segment.h5
6 files changed, 131 insertions, 22 deletions
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index b2e3ff347620..090d8ce25bd1 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -31,6 +31,8 @@
#include "alloc.h"
#include "dat.h"
+static void __nilfs_btree_init(struct nilfs_bmap *bmap);
+
static struct nilfs_btree_path *nilfs_btree_alloc_path(void)
{
struct nilfs_btree_path *path;
@@ -368,6 +370,34 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node,
return ret;
}
+/**
+ * nilfs_btree_root_broken - verify consistency of btree root node
+ * @node: btree root node to be examined
+ * @ino: inode number
+ *
+ * Return Value: If node is broken, 1 is returned. Otherwise, 0 is returned.
+ */
+static int nilfs_btree_root_broken(const struct nilfs_btree_node *node,
+ unsigned long ino)
+{
+ int level, flags, nchildren;
+ int ret = 0;
+
+ level = nilfs_btree_node_get_level(node);
+ flags = nilfs_btree_node_get_flags(node);
+ nchildren = nilfs_btree_node_get_nchildren(node);
+
+ if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN ||
+ level >= NILFS_BTREE_LEVEL_MAX ||
+ nchildren < 0 ||
+ nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) {
+ pr_crit("NILFS: bad btree root (inode number=%lu): level = %d, flags = 0x%x, nchildren = %d\n",
+ ino, level, flags, nchildren);
+ ret = 1;
+ }
+ return ret;
+}
+
int nilfs_btree_broken_node_block(struct buffer_head *bh)
{
int ret;
@@ -1713,7 +1743,7 @@ nilfs_btree_commit_convert_and_insert(struct nilfs_bmap *btree,
/* convert and insert */
dat = NILFS_BMAP_USE_VBN(btree) ? nilfs_bmap_get_dat(btree) : NULL;
- nilfs_btree_init(btree);
+ __nilfs_btree_init(btree);
if (nreq != NULL) {
nilfs_bmap_commit_alloc_ptr(btree, dreq, dat);
nilfs_bmap_commit_alloc_ptr(btree, nreq, dat);
@@ -2294,12 +2324,23 @@ static const struct nilfs_bmap_operations nilfs_btree_ops_gc = {
.bop_gather_data = NULL,
};
-int nilfs_btree_init(struct nilfs_bmap *bmap)
+static void __nilfs_btree_init(struct nilfs_bmap *bmap)
{
bmap->b_ops = &nilfs_btree_ops;
bmap->b_nchildren_per_block =
NILFS_BTREE_NODE_NCHILDREN_MAX(nilfs_btree_node_size(bmap));
- return 0;
+}
+
+int nilfs_btree_init(struct nilfs_bmap *bmap)
+{
+ int ret = 0;
+
+ __nilfs_btree_init(bmap);
+
+ if (nilfs_btree_root_broken(nilfs_btree_get_root(bmap),
+ bmap->b_inode->i_ino))
+ ret = -EIO;
+ return ret;
}
void nilfs_btree_init_gc(struct nilfs_bmap *bmap)
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 7e350c562e0e..09480c53fd74 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -24,6 +24,7 @@
#include <linux/buffer_head.h>
#include <linux/gfp.h>
#include <linux/mpage.h>
+#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/aio.h>
#include "nilfs.h"
@@ -48,6 +49,8 @@ struct nilfs_iget_args {
int for_gc;
};
+static int nilfs_iget_test(struct inode *inode, void *opaque);
+
void nilfs_inode_add_blocks(struct inode *inode, int n)
{
struct nilfs_root *root = NILFS_I(inode)->i_root;
@@ -219,10 +222,10 @@ static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
static int nilfs_set_page_dirty(struct page *page)
{
+ struct inode *inode = page->mapping->host;
int ret = __set_page_dirty_nobuffers(page);
if (page_has_buffers(page)) {
- struct inode *inode = page->mapping->host;
unsigned nr_dirty = 0;
struct buffer_head *bh, *head;
@@ -245,6 +248,10 @@ static int nilfs_set_page_dirty(struct page *page)
if (nr_dirty)
nilfs_set_file_dirty(inode, nr_dirty);
+ } else if (ret) {
+ unsigned nr_dirty = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+
+ nilfs_set_file_dirty(inode, nr_dirty);
}
return ret;
}
@@ -342,6 +349,17 @@ const struct address_space_operations nilfs_aops = {
.is_partially_uptodate = block_is_partially_uptodate,
};
+static int nilfs_insert_inode_locked(struct inode *inode,
+ struct nilfs_root *root,
+ unsigned long ino)
+{
+ struct nilfs_iget_args args = {
+ .ino = ino, .root = root, .cno = 0, .for_gc = 0
+ };
+
+ return insert_inode_locked4(inode, ino, nilfs_iget_test, &args);
+}
+
struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
{
struct super_block *sb = dir->i_sb;
@@ -377,7 +395,7 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
err = nilfs_bmap_read(ii->i_bmap, NULL);
if (err < 0)
- goto failed_bmap;
+ goto failed_after_creation;
set_bit(NILFS_I_BMAP, &ii->i_state);
/* No lock is needed; iget() ensures it. */
@@ -393,21 +411,24 @@ struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
spin_lock(&nilfs->ns_next_gen_lock);
inode->i_generation = nilfs->ns_next_generation++;
spin_unlock(&nilfs->ns_next_gen_lock);
- insert_inode_hash(inode);
+ if (nilfs_insert_inode_locked(inode, root, ino) < 0) {
+ err = -EIO;
+ goto failed_after_creation;
+ }
err = nilfs_init_acl(inode, dir);
if (unlikely(err))
- goto failed_acl; /* never occur. When supporting
+ goto failed_after_creation; /* never occur. When supporting
nilfs_init_acl(), proper cancellation of
above jobs should be considered */
return inode;
- failed_acl:
- failed_bmap:
+ failed_after_creation:
clear_nlink(inode);
+ unlock_new_inode(inode);
iput(inode); /* raw_inode will be deleted through
- generic_delete_inode() */
+ nilfs_evict_inode() */
goto failed;
failed_ifile_create_inode:
@@ -455,8 +476,8 @@ int nilfs_read_inode_common(struct inode *inode,
inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
- if (inode->i_nlink == 0 && inode->i_mode == 0)
- return -EINVAL; /* this inode is deleted */
+ if (inode->i_nlink == 0)
+ return -ESTALE; /* this inode is deleted */
inode->i_blocks = le64_to_cpu(raw_inode->i_blocks);
ii->i_flags = le32_to_cpu(raw_inode->i_flags);
diff --git a/fs/nilfs2/namei.c b/fs/nilfs2/namei.c
index 9de78f08989e..0f84b257932c 100644
--- a/fs/nilfs2/namei.c
+++ b/fs/nilfs2/namei.c
@@ -51,9 +51,11 @@ static inline int nilfs_add_nondir(struct dentry *dentry, struct inode *inode)
int err = nilfs_add_link(dentry, inode);
if (!err) {
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
return 0;
}
inode_dec_link_count(inode);
+ unlock_new_inode(inode);
iput(inode);
return err;
}
@@ -182,6 +184,7 @@ out:
out_fail:
drop_nlink(inode);
nilfs_mark_inode_dirty(inode);
+ unlock_new_inode(inode);
iput(inode);
goto out;
}
@@ -201,11 +204,15 @@ static int nilfs_link(struct dentry *old_dentry, struct inode *dir,
inode_inc_link_count(inode);
ihold(inode);
- err = nilfs_add_nondir(dentry, inode);
- if (!err)
+ err = nilfs_add_link(dentry, inode);
+ if (!err) {
+ d_instantiate(dentry, inode);
err = nilfs_transaction_commit(dir->i_sb);
- else
+ } else {
+ inode_dec_link_count(inode);
+ iput(inode);
nilfs_transaction_abort(dir->i_sb);
+ }
return err;
}
@@ -243,6 +250,7 @@ static int nilfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
nilfs_mark_inode_dirty(inode);
d_instantiate(dentry, inode);
+ unlock_new_inode(inode);
out:
if (!err)
err = nilfs_transaction_commit(dir->i_sb);
@@ -255,6 +263,7 @@ out_fail:
drop_nlink(inode);
drop_nlink(inode);
nilfs_mark_inode_dirty(inode);
+ unlock_new_inode(inode);
iput(inode);
out_dir:
drop_nlink(dir);
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index 9bc72dec3fa6..b02c202223a6 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -141,7 +141,6 @@ enum {
* @ti_save: Backup of journal_info field of task_struct
* @ti_flags: Flags
* @ti_count: Nest level
- * @ti_garbage: List of inode to be put when releasing semaphore
*/
struct nilfs_transaction_info {
u32 ti_magic;
@@ -150,7 +149,6 @@ struct nilfs_transaction_info {
one of other filesystems has a bug. */
unsigned short ti_flags;
unsigned short ti_count;
- struct list_head ti_garbage;
};
/* ti_magic */
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index a1a191634abc..14538a865102 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -305,7 +305,6 @@ static void nilfs_transaction_lock(struct super_block *sb,
ti->ti_count = 0;
ti->ti_save = cur_ti;
ti->ti_magic = NILFS_TI_MAGIC;
- INIT_LIST_HEAD(&ti->ti_garbage);
current->journal_info = ti;
for (;;) {
@@ -332,8 +331,6 @@ static void nilfs_transaction_unlock(struct super_block *sb)
up_write(&nilfs->ns_segctor_sem);
current->journal_info = ti->ti_save;
- if (!list_empty(&ti->ti_garbage))
- nilfs_dispose_list(nilfs, &ti->ti_garbage, 0);
}
static void *nilfs_segctor_map_segsum_entry(struct nilfs_sc_info *sci,
@@ -746,6 +743,15 @@ static void nilfs_dispose_list(struct the_nilfs *nilfs,
}
}
+static void nilfs_iput_work_func(struct work_struct *work)
+{
+ struct nilfs_sc_info *sci = container_of(work, struct nilfs_sc_info,
+ sc_iput_work);
+ struct the_nilfs *nilfs = sci->sc_super->s_fs_info;
+
+ nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 0);
+}
+
static int nilfs_test_metadata_dirty(struct the_nilfs *nilfs,
struct nilfs_root *root)
{
@@ -1899,8 +1905,9 @@ static int nilfs_segctor_collect_dirty_files(struct nilfs_sc_info *sci,
static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
struct the_nilfs *nilfs)
{
- struct nilfs_transaction_info *ti = current->journal_info;
struct nilfs_inode_info *ii, *n;
+ int during_mount = !(sci->sc_super->s_flags & MS_ACTIVE);
+ int defer_iput = false;
spin_lock(&nilfs->ns_inode_lock);
list_for_each_entry_safe(ii, n, &sci->sc_dirty_files, i_dirty) {
@@ -1911,9 +1918,24 @@ static void nilfs_segctor_drop_written_files(struct nilfs_sc_info *sci,
clear_bit(NILFS_I_BUSY, &ii->i_state);
brelse(ii->i_bh);
ii->i_bh = NULL;
- list_move_tail(&ii->i_dirty, &ti->ti_garbage);
+ list_del_init(&ii->i_dirty);
+ if (!ii->vfs_inode.i_nlink || during_mount) {
+ /*
+ * Defer calling iput() to avoid deadlocks if
+ * i_nlink == 0 or mount is not yet finished.
+ */
+ list_add_tail(&ii->i_dirty, &sci->sc_iput_queue);
+ defer_iput = true;
+ } else {
+ spin_unlock(&nilfs->ns_inode_lock);
+ iput(&ii->vfs_inode);
+ spin_lock(&nilfs->ns_inode_lock);
+ }
}
spin_unlock(&nilfs->ns_inode_lock);
+
+ if (defer_iput)
+ schedule_work(&sci->sc_iput_work);
}
/*
@@ -2580,6 +2602,8 @@ static struct nilfs_sc_info *nilfs_segctor_new(struct super_block *sb,
INIT_LIST_HEAD(&sci->sc_segbufs);
INIT_LIST_HEAD(&sci->sc_write_logs);
INIT_LIST_HEAD(&sci->sc_gc_inodes);
+ INIT_LIST_HEAD(&sci->sc_iput_queue);
+ INIT_WORK(&sci->sc_iput_work, nilfs_iput_work_func);
init_timer(&sci->sc_timer);
sci->sc_interval = HZ * NILFS_SC_DEFAULT_TIMEOUT;
@@ -2606,6 +2630,8 @@ static void nilfs_segctor_write_out(struct nilfs_sc_info *sci)
ret = nilfs_segctor_construct(sci, SC_LSEG_SR);
nilfs_transaction_unlock(sci->sc_super);
+ flush_work(&sci->sc_iput_work);
+
} while (ret && retrycount-- > 0);
}
@@ -2630,6 +2656,9 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
|| sci->sc_seq_request != sci->sc_seq_done);
spin_unlock(&sci->sc_state_lock);
+ if (flush_work(&sci->sc_iput_work))
+ flag = true;
+
if (flag || !nilfs_segctor_confirm(sci))
nilfs_segctor_write_out(sci);
@@ -2639,6 +2668,12 @@ static void nilfs_segctor_destroy(struct nilfs_sc_info *sci)
nilfs_dispose_list(nilfs, &sci->sc_dirty_files, 1);
}
+ if (!list_empty(&sci->sc_iput_queue)) {
+ nilfs_warning(sci->sc_super, __func__,
+ "iput queue is not empty\n");
+ nilfs_dispose_list(nilfs, &sci->sc_iput_queue, 1);
+ }
+
WARN_ON(!list_empty(&sci->sc_segbufs));
WARN_ON(!list_empty(&sci->sc_write_logs));
diff --git a/fs/nilfs2/segment.h b/fs/nilfs2/segment.h
index 38a1d0013314..a48d6de1e02c 100644
--- a/fs/nilfs2/segment.h
+++ b/fs/nilfs2/segment.h
@@ -26,6 +26,7 @@
#include <linux/types.h>
#include <linux/fs.h>
#include <linux/buffer_head.h>
+#include <linux/workqueue.h>
#include <linux/nilfs2_fs.h>
#include "nilfs.h"
@@ -92,6 +93,8 @@ struct nilfs_segsum_pointer {
* @sc_nblk_inc: Block count of current generation
* @sc_dirty_files: List of files to be written
* @sc_gc_inodes: List of GC inodes having blocks to be written
+ * @sc_iput_queue: list of inodes for which iput should be done
+ * @sc_iput_work: work struct to defer iput call
* @sc_freesegs: array of segment numbers to be freed
* @sc_nfreesegs: number of segments on @sc_freesegs
* @sc_dsync_inode: inode whose data pages are written for a sync operation
@@ -135,6 +138,8 @@ struct nilfs_sc_info {
struct list_head sc_dirty_files;
struct list_head sc_gc_inodes;
+ struct list_head sc_iput_queue;
+ struct work_struct sc_iput_work;
__u64 *sc_freesegs;
size_t sc_nfreesegs;
generated by cgit v1.2.3 (git 2.25.1) at 2024-06-19 20:17:43 +0000