* [PATCH v2 1/2] hfsplus: prevent btree data loss on ENOSPC
@ 2018-09-09 22:46 Ernesto A. Fernández
2018-09-09 22:47 ` [PATCH v2 2/2] hfs: " Ernesto A. Fernández
0 siblings, 1 reply; 2+ messages in thread
From: Ernesto A. Fernández @ 2018-09-09 22:46 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Andrew Morton
Inserting or deleting a record in a btree may require splitting several
of its nodes. If we hit ENOSPC halfway through, the new nodes will be
left orphaned and their records will be lost. This could mean lost
inodes, extents or xattrs.
>From now on, check the available disk space before making any changes.
This still leaves the potential problem of corruption on ENOMEM.
The patch can be tested with xfstests generic/027.
Signed-off-by: Ernesto A. Fernández <ernesto.mnd.fernandez@gmail.com>
---
Changes in v2:
Increase the free node count after each loop in hfs_bmap_reserve(),
instead of resetting it.
fs/hfsplus/attributes.c | 10 ++++++++++
fs/hfsplus/btree.c | 44 ++++++++++++++++++++++++++++----------------
fs/hfsplus/catalog.c | 24 ++++++++++++++++++++++++
fs/hfsplus/extents.c | 4 ++++
fs/hfsplus/hfsplus_fs.h | 2 ++
5 files changed, 68 insertions(+), 16 deletions(-)
diff --git a/fs/hfsplus/attributes.c b/fs/hfsplus/attributes.c
index 2bab6b3cdba4..e6d554476db4 100644
--- a/fs/hfsplus/attributes.c
+++ b/fs/hfsplus/attributes.c
@@ -217,6 +217,11 @@ int hfsplus_create_attr(struct inode *inode,
if (err)
goto failed_init_create_attr;
+ /* Fail early and avoid ENOSPC during the btree operation */
+ err = hfs_bmap_reserve(fd.tree, fd.tree->depth + 1);
+ if (err)
+ goto failed_create_attr;
+
if (name) {
err = hfsplus_attr_build_key(sb, fd.search_key,
inode->i_ino, name);
@@ -313,6 +318,11 @@ int hfsplus_delete_attr(struct inode *inode, const char *name)
if (err)
return err;
+ /* Fail early and avoid ENOSPC during the btree operation */
+ err = hfs_bmap_reserve(fd.tree, fd.tree->depth);
+ if (err)
+ goto out;
+
if (name) {
err = hfsplus_attr_build_key(sb, fd.search_key,
inode->i_ino, name);
diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
index de14b2b6881b..236efe51eca6 100644
--- a/fs/hfsplus/btree.c
+++ b/fs/hfsplus/btree.c
@@ -342,26 +342,21 @@ static struct hfs_bnode *hfs_bmap_new_bmap(struct hfs_bnode *prev, u32 idx)
return node;
}
-struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
+/* Make sure @tree has enough space for the @rsvd_nodes */
+int hfs_bmap_reserve(struct hfs_btree *tree, int rsvd_nodes)
{
- struct hfs_bnode *node, *next_node;
- struct page **pagep;
- u32 nidx, idx;
- unsigned off;
- u16 off16;
- u16 len;
- u8 *data, byte, m;
- int i;
+ struct inode *inode = tree->inode;
+ struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
+ u32 count;
+ int res;
- while (!tree->free_nodes) {
- struct inode *inode = tree->inode;
- struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
- u32 count;
- int res;
+ if (rsvd_nodes <= 0)
+ return 0;
+ while (tree->free_nodes < rsvd_nodes) {
res = hfsplus_file_extend(inode, hfs_bnode_need_zeroout(tree));
if (res)
- return ERR_PTR(res);
+ return res;
hip->phys_size = inode->i_size =
(loff_t)hip->alloc_blocks <<
HFSPLUS_SB(tree->sb)->alloc_blksz_shift;
@@ -369,9 +364,26 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
hip->alloc_blocks << HFSPLUS_SB(tree->sb)->fs_shift;
inode_set_bytes(inode, inode->i_size);
count = inode->i_size >> tree->node_size_shift;
- tree->free_nodes = count - tree->node_count;
+ tree->free_nodes += count - tree->node_count;
tree->node_count = count;
}
+ return 0;
+}
+
+struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
+{
+ struct hfs_bnode *node, *next_node;
+ struct page **pagep;
+ u32 nidx, idx;
+ unsigned off;
+ u16 off16;
+ u16 len;
+ u8 *data, byte, m;
+ int i, res;
+
+ res = hfs_bmap_reserve(tree, 1);
+ if (res)
+ return ERR_PTR(res);
nidx = 0;
node = hfs_bnode_find(tree, nidx);
diff --git a/fs/hfsplus/catalog.c b/fs/hfsplus/catalog.c
index a196369ba779..35472cba750e 100644
--- a/fs/hfsplus/catalog.c
+++ b/fs/hfsplus/catalog.c
@@ -265,6 +265,14 @@ int hfsplus_create_cat(u32 cnid, struct inode *dir,
if (err)
return err;
+ /*
+ * Fail early and avoid ENOSPC during the btree operations. We may
+ * have to split the root node at most once.
+ */
+ err = hfs_bmap_reserve(fd.tree, 2 * fd.tree->depth);
+ if (err)
+ goto err2;
+
hfsplus_cat_build_key_with_cnid(sb, fd.search_key, cnid);
entry_size = hfsplus_fill_cat_thread(sb, &entry,
S_ISDIR(inode->i_mode) ?
@@ -333,6 +341,14 @@ int hfsplus_delete_cat(u32 cnid, struct inode *dir, const struct qstr *str)
if (err)
return err;
+ /*
+ * Fail early and avoid ENOSPC during the btree operations. We may
+ * have to split the root node at most once.
+ */
+ err = hfs_bmap_reserve(fd.tree, 2 * (int)fd.tree->depth - 2);
+ if (err)
+ goto out;
+
if (!str) {
int len;
@@ -433,6 +449,14 @@ int hfsplus_rename_cat(u32 cnid,
return err;
dst_fd = src_fd;
+ /*
+ * Fail early and avoid ENOSPC during the btree operations. We may
+ * have to split the root node at most twice.
+ */
+ err = hfs_bmap_reserve(src_fd.tree, 4 * (int)src_fd.tree->depth - 1);
+ if (err)
+ goto out;
+
/* find the old dir entry and read the data */
err = hfsplus_cat_build_key(sb, src_fd.search_key,
src_dir->i_ino, src_name);
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index 8e0f59767694..8a8893d522ef 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -100,6 +100,10 @@ static int __hfsplus_ext_write_extent(struct inode *inode,
if (hip->extent_state & HFSPLUS_EXT_NEW) {
if (res != -ENOENT)
return res;
+ /* Fail early and avoid ENOSPC during the btree operation */
+ res = hfs_bmap_reserve(fd->tree, fd->tree->depth + 1);
+ if (res)
+ return res;
hfs_brec_insert(fd, hip->cached_extents,
sizeof(hfsplus_extent_rec));
hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW);
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 8e039435958a..dd7ad9f13e3a 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -311,6 +311,7 @@ static inline unsigned short hfsplus_min_io_size(struct super_block *sb)
#define hfs_btree_open hfsplus_btree_open
#define hfs_btree_close hfsplus_btree_close
#define hfs_btree_write hfsplus_btree_write
+#define hfs_bmap_reserve hfsplus_bmap_reserve
#define hfs_bmap_alloc hfsplus_bmap_alloc
#define hfs_bmap_free hfsplus_bmap_free
#define hfs_bnode_read hfsplus_bnode_read
@@ -395,6 +396,7 @@ u32 hfsplus_calc_btree_clump_size(u32 block_size, u32 node_size, u64 sectors,
struct hfs_btree *hfs_btree_open(struct super_block *sb, u32 id);
void hfs_btree_close(struct hfs_btree *tree);
int hfs_btree_write(struct hfs_btree *tree);
+int hfs_bmap_reserve(struct hfs_btree *tree, int rsvd_nodes);
struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree);
void hfs_bmap_free(struct hfs_bnode *node);
--
2.11.0
^ permalink raw reply related [flat|nested] 2+ messages in thread* [PATCH v2 2/2] hfs: prevent btree data loss on ENOSPC
2018-09-09 22:46 [PATCH v2 1/2] hfsplus: prevent btree data loss on ENOSPC Ernesto A. Fernández
@ 2018-09-09 22:47 ` Ernesto A. Fernández
0 siblings, 0 replies; 2+ messages in thread
From: Ernesto A. Fernández @ 2018-09-09 22:47 UTC (permalink / raw)
To: linux-fsdevel; +Cc: Andrew Morton
Inserting a new record in a btree may require splitting several of its
nodes. If we hit ENOSPC halfway through, the new nodes will be left
orphaned and their records will be lost. This could mean lost inodes
or extents.
>From now on, check the available disk space before making any changes.
This still leaves the potential problem of corruption on ENOMEM.
There is no need to reserve space before deleting a catalog record, as
we do for hfsplus. This difference is because hfs index nodes have
fixed length keys.
Signed-off-by: Ernesto A. Fernández <ernesto.mnd.fernandez@gmail.com>
---
Changes in v2:
Increase the free node count after each loop in hfs_bmap_reserve(),
instead of resetting it.
fs/hfs/btree.c | 41 +++++++++++++++++++++++++----------------
fs/hfs/btree.h | 1 +
fs/hfs/catalog.c | 16 ++++++++++++++++
fs/hfs/extent.c | 4 ++++
4 files changed, 46 insertions(+), 16 deletions(-)
diff --git a/fs/hfs/btree.c b/fs/hfs/btree.c
index 374b5688e29e..98b96ffb95ed 100644
--- a/fs/hfs/btree.c
+++ b/fs/hfs/btree.c
@@ -220,25 +220,17 @@ static struct hfs_bnode *hfs_bmap_new_bmap(struct hfs_bnode *prev, u32 idx)
return node;
}
-struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
+/* Make sure @tree has enough space for the @rsvd_nodes */
+int hfs_bmap_reserve(struct hfs_btree *tree, int rsvd_nodes)
{
- struct hfs_bnode *node, *next_node;
- struct page **pagep;
- u32 nidx, idx;
- unsigned off;
- u16 off16;
- u16 len;
- u8 *data, byte, m;
- int i;
-
- while (!tree->free_nodes) {
- struct inode *inode = tree->inode;
- u32 count;
- int res;
+ struct inode *inode = tree->inode;
+ u32 count;
+ int res;
+ while (tree->free_nodes < rsvd_nodes) {
res = hfs_extend_file(inode);
if (res)
- return ERR_PTR(res);
+ return res;
HFS_I(inode)->phys_size = inode->i_size =
(loff_t)HFS_I(inode)->alloc_blocks *
HFS_SB(tree->sb)->alloc_blksz;
@@ -246,9 +238,26 @@ struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
tree->sb->s_blocksize_bits;
inode_set_bytes(inode, inode->i_size);
count = inode->i_size >> tree->node_size_shift;
- tree->free_nodes = count - tree->node_count;
+ tree->free_nodes += count - tree->node_count;
tree->node_count = count;
}
+ return 0;
+}
+
+struct hfs_bnode *hfs_bmap_alloc(struct hfs_btree *tree)
+{
+ struct hfs_bnode *node, *next_node;
+ struct page **pagep;
+ u32 nidx, idx;
+ unsigned off;
+ u16 off16;
+ u16 len;
+ u8 *data, byte, m;
+ int i, res;
+
+ res = hfs_bmap_reserve(tree, 1);
+ if (res)
+ return ERR_PTR(res);
nidx = 0;
node = hfs_bnode_find(tree, nidx);
diff --git a/fs/hfs/btree.h b/fs/hfs/btree.h
index c8b252dbb26c..dcc2aab1b2c4 100644
--- a/fs/hfs/btree.h
+++ b/fs/hfs/btree.h
@@ -82,6 +82,7 @@ struct hfs_find_data {
extern struct hfs_btree *hfs_btree_open(struct super_block *, u32, btree_keycmp);
extern void hfs_btree_close(struct hfs_btree *);
extern void hfs_btree_write(struct hfs_btree *);
+extern int hfs_bmap_reserve(struct hfs_btree *, int);
extern struct hfs_bnode * hfs_bmap_alloc(struct hfs_btree *);
extern void hfs_bmap_free(struct hfs_bnode *node);
diff --git a/fs/hfs/catalog.c b/fs/hfs/catalog.c
index 8a66405b0f8b..d365bf0b8c77 100644
--- a/fs/hfs/catalog.c
+++ b/fs/hfs/catalog.c
@@ -97,6 +97,14 @@ int hfs_cat_create(u32 cnid, struct inode *dir, const struct qstr *str, struct i
if (err)
return err;
+ /*
+ * Fail early and avoid ENOSPC during the btree operations. We may
+ * have to split the root node at most once.
+ */
+ err = hfs_bmap_reserve(fd.tree, 2 * fd.tree->depth);
+ if (err)
+ goto err2;
+
hfs_cat_build_key(sb, fd.search_key, cnid, NULL);
entry_size = hfs_cat_build_thread(sb, &entry, S_ISDIR(inode->i_mode) ?
HFS_CDR_THD : HFS_CDR_FTH,
@@ -295,6 +303,14 @@ int hfs_cat_move(u32 cnid, struct inode *src_dir, const struct qstr *src_name,
return err;
dst_fd = src_fd;
+ /*
+ * Fail early and avoid ENOSPC during the btree operations. We may
+ * have to split the root node at most once.
+ */
+ err = hfs_bmap_reserve(src_fd.tree, 2 * src_fd.tree->depth);
+ if (err)
+ goto out;
+
/* find the old dir entry and read the data */
hfs_cat_build_key(sb, src_fd.search_key, src_dir->i_ino, src_name);
err = hfs_brec_find(&src_fd);
diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c
index 5d0182654580..0c638c612152 100644
--- a/fs/hfs/extent.c
+++ b/fs/hfs/extent.c
@@ -117,6 +117,10 @@ static int __hfs_ext_write_extent(struct inode *inode, struct hfs_find_data *fd)
if (HFS_I(inode)->flags & HFS_FLG_EXT_NEW) {
if (res != -ENOENT)
return res;
+ /* Fail early and avoid ENOSPC during the btree operation */
+ res = hfs_bmap_reserve(fd->tree, fd->tree->depth + 1);
+ if (res)
+ return res;
hfs_brec_insert(fd, HFS_I(inode)->cached_extents, sizeof(hfs_extent_rec));
HFS_I(inode)->flags &= ~(HFS_FLG_EXT_DIRTY|HFS_FLG_EXT_NEW);
} else {
--
2.11.0
^ permalink raw reply related [flat|nested] 2+ messages in thread
end of thread, other threads:[~2018-09-10 8:03 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2018-09-09 22:46 [PATCH v2 1/2] hfsplus: prevent btree data loss on ENOSPC Ernesto A. Fernández
2018-09-09 22:47 ` [PATCH v2 2/2] hfs: " Ernesto A. Fernández
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).