Re: [PATCH v5] hfsplus: validate B-tree record offset table
From: Viacheslav Dubeyko
Date: Tue Jul 28 2026 - 20:55:58 EST
On Tue, 2026-07-28 at 18:12 +0800, Jiaming Zhang wrote:
> A crafted HFS+ image can contain a corrupted B-tree node. The node
> descriptor may contain a record count that does not fit in the node,
> and
> record offsets may be unordered, unaligned, outside the node, or
> point into
> the offset table itself.
>
> Several B-tree helpers consume these on-disk fields before validating
> them:
> hfs_bnode_dump() can walk past the offset table when num_recs is
> corrupted,
> hfs_brec_lenoff() can produce an underflowed length or a record range
> that
> overlaps the offset table. This can make the unlink/writeback path
> repeatedly call hfs_bnode_read_u16() with invalid offsets while
> holding the
> HFS+ B-tree lock, producing a flood of "requested invalid offset"
> messages.
> Other writeback workers then block on tree->tree_lock and the system
> reports tasks hung in hfsplus_write_inode().
>
> Validate num_recs against the node size before walking the record
> offset
> table. Reject record ranges that are unordered, unaligned, outside
> the
> node, or overlapping the offset table. Reject invalid record indexes
> before
> reading their offset entries, and avoid decrementing an already-zero
> leaf_count.
>
> Closes:
> https://lore.kernel.org/lkml/CANypQFb_2TqKGrztAXj5m0_v+QChxXDnQVeifzV8J25Vuju10Q@xxxxxxxxxxxxxx/
> Assisted-by: Codex:gpt-5.5-xhigh
> Signed-off-by: Jiaming Zhang <r772577952@xxxxxxxxx>
> ---
> Changes in v5:
> - Switch helpers to invalid checker and invert callers.
> - hfs_brec_offsets_invalid(): Drop the redundant offset-table
> argument
> since it is already covered by the offset-table overlap check and
> take
> just the two neighboring record offsets (off and next_off).
> - hfs_brec_len_invalid(): reject a length against node_size.
> - Use hfs_brec_len_invalid() for both length checks in
> hfs_bmap_get_map_page().
> - Validate the record offset in hfs_bmap_free().
> - Check the __hfs_brec_find() return code in [2] and [3]. [1] and [4]
> call
> it to find the insertion slot for a new index key after a split, -
> ENOENT is
> one of expected, even -EINVAL the following hfs_brec_insert() just
> inserts
> at slot 0 of a node already validated by hfs_bnode_find(), so it
> stays
> in-bounds and cannot trigger the invalid-offset flood. Hence no
> check was
> added.
>
> [1]
> https://elixir.bootlin.com/linux/v7.2-rc3/source/fs/hfsplus/brec.c#L160
> [2]
> https://elixir.bootlin.com/linux/v7.2-rc3/source/fs/hfsplus/brec.c#L208
> [3]
> https://elixir.bootlin.com/linux/v7.2-rc3/source/fs/hfsplus/brec.c#L382
> [4]
> https://elixir.bootlin.com/linux/v7.2-rc3/source/fs/hfsplus/brec.c#L449
>
> Changes in v4:
> - Rename hfs_find_reset() to hfs_find_result_init().
> - Reset find result fields in __hfs_brec_find().
> - Move num_recs validation next to descriptor field initialization.
> - Rename hfs_brec_range_valid() to hfs_brec_offpair_valid().
> - Use U16_MAX for invalid offset/len/keylen sentinels and update
> callers.
> - Add hfs_brec_len_valid() to check validity of len/keylen.
> - Handle invalid B-tree map record lengths in hfs_bmap_get_map_page()
> and hfs_bmap_free().
> - Return -EINVAL instead of -EIO for invalid remove cursor/leaf_count
> state.
>
> Changes in v3:
> - Drop the keylen == len check.
> - Drop the explicit zero-record check in __hfs_brec_find().
> - Move find cursor reset into hfs_find_reset() and call it from
> hfs_find_init() and hfs_brec_find().
> - Rename helper-local variables as suggested.
>
> fs/hfsplus/bfind.c | 23 ++++++------
> fs/hfsplus/bnode.c | 16 ++++++---
> fs/hfsplus/brec.c | 53 ++++++++++++++++++---------
> fs/hfsplus/btree.c | 14 ++++++--
> fs/hfsplus/hfsplus_fs.h | 79
> +++++++++++++++++++++++++++++++++++++++++
> 5 files changed, 153 insertions(+), 32 deletions(-)
>
> diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c
> index 9a55fa6d5294..ca9813f58a6d 100644
> --- a/fs/hfsplus/bfind.c
> +++ b/fs/hfsplus/bfind.c
> @@ -18,6 +18,7 @@ int hfs_find_init(struct hfs_btree *tree, struct
> hfs_find_data *fd)
>
> fd->tree = tree;
> fd->bnode = NULL;
> + hfs_find_result_init(fd);
> ptr = kzalloc(tree->max_key_len * 2 + 4, GFP_KERNEL);
> if (!ptr)
> return -ENOMEM;
> @@ -106,17 +107,21 @@ int __hfs_brec_find(struct hfs_bnode *bnode,
> struct hfs_find_data *fd,
> u16 off, len, keylen;
> int rec;
> int b, e;
> - int res;
> + int res = -ENOENT;
>
> BUG_ON(!rec_found);
> + hfs_find_result_init(fd);
> + if (hfs_bnode_num_recs_invalid(bnode))
> + goto fail;
> +
> b = 0;
> e = bnode->num_recs - 1;
> - res = -ENOENT;
> do {
> rec = (e + b) / 2;
> len = hfs_brec_lenoff(bnode, rec, &off);
> keylen = hfs_brec_keylen(bnode, rec);
> - if (keylen == 0) {
> + if (hfs_brec_len_invalid(bnode, len) ||
> + hfs_brec_len_invalid(bnode, keylen)) {
> res = -EINVAL;
> goto fail;
> }
> @@ -130,7 +135,8 @@ int __hfs_brec_find(struct hfs_bnode *bnode,
> struct hfs_find_data *fd,
> if (rec != e && e >= 0) {
> len = hfs_brec_lenoff(bnode, e, &off);
> keylen = hfs_brec_keylen(bnode, e);
> - if (keylen == 0) {
> + if (hfs_brec_len_invalid(bnode, keylen) ||
> + hfs_brec_len_invalid(bnode, len)) {
> res = -EINVAL;
> goto fail;
> }
> @@ -158,11 +164,7 @@ int hfs_brec_find(struct hfs_find_data *fd,
> search_strategy_t do_key_compare)
> __be32 data;
> int height, res;
>
> - fd->record = -1;
> - fd->keyoffset = -1;
> - fd->keylength = -1;
> - fd->entryoffset = -1;
> - fd->entrylength = -1;
> + hfs_find_result_init(fd);
>
> tree = fd->tree;
> if (fd->bnode)
> @@ -274,7 +276,8 @@ int hfs_brec_goto(struct hfs_find_data *fd, int
> cnt)
>
> len = hfs_brec_lenoff(bnode, fd->record, &off);
> keylen = hfs_brec_keylen(bnode, fd->record);
> - if (keylen == 0) {
> + if (hfs_brec_len_invalid(bnode, len) ||
> + hfs_brec_len_invalid(bnode, keylen)) {
> res = -EINVAL;
> goto out;
> }
> diff --git a/fs/hfsplus/bnode.c b/fs/hfsplus/bnode.c
> index d088fb7eb0df..3a1a1fa6f2e2 100644
> --- a/fs/hfsplus/bnode.c
> +++ b/fs/hfsplus/bnode.c
> @@ -352,15 +352,22 @@ void hfs_bnode_dump(struct hfs_bnode *node)
> struct hfs_bnode_desc desc;
> __be32 cnid;
> int i, off, key_off;
> + u16 num_recs;
>
> hfs_dbg("node %d\n", node->this);
> hfs_bnode_read(node, &desc, 0, sizeof(desc));
> + num_recs = node->num_recs;
> hfs_dbg("next %d, prev %d, type %d, height %d, num_recs
> %d\n",
> be32_to_cpu(desc.next), be32_to_cpu(desc.prev),
> desc.type, desc.height, be16_to_cpu(desc.num_recs));
>
> + if (hfs_bnode_num_recs_invalid(node)) {
> + hfs_dbg("invalid num_recs %u\n", num_recs);
> + return;
> + }
> +
> off = node->tree->node_size - 2;
> - for (i = be16_to_cpu(desc.num_recs); i >= 0; off -= 2, i--)
> {
> + for (i = num_recs; i >= 0; off -= 2, i--) {
> key_off = hfs_bnode_read_u16(node, off);
> hfs_dbg(" key_off %d", key_off);
> if (i && node->type == HFS_NODE_INDEX) {
> @@ -561,6 +568,9 @@ struct hfs_bnode *hfs_bnode_find(struct hfs_btree
> *tree, u32 num)
> node->height = desc->height;
> kunmap_local(desc);
>
> + if (hfs_bnode_num_recs_invalid(node))
> + goto node_error;
> +
> switch (node->type) {
> case HFS_NODE_HEADER:
> case HFS_NODE_MAP:
> @@ -586,9 +596,7 @@ struct hfs_bnode *hfs_bnode_find(struct hfs_btree
> *tree, u32 num)
> for (i = 1; i <= node->num_recs; off = next_off, i++) {
> rec_off -= 2;
> next_off = hfs_bnode_read_u16(node, rec_off);
> - if (next_off <= off ||
> - next_off > tree->node_size ||
> - next_off & 1)
> + if (hfs_brec_offsets_invalid(node, off, next_off))
> goto node_error;
> entry_size = next_off - off;
> if (node->type != HFS_NODE_INDEX &&
> diff --git a/fs/hfsplus/brec.c b/fs/hfsplus/brec.c
> index e3df89284079..f416e562d439 100644
> --- a/fs/hfsplus/brec.c
> +++ b/fs/hfsplus/brec.c
> @@ -9,6 +9,8 @@
> * Handle individual btree records
> */
>
> +#include <linux/limits.h>
> +
> #include "hfsplus_fs.h"
> #include "hfsplus_raw.h"
>
> @@ -20,41 +22,49 @@ static int hfs_btree_inc_height(struct hfs_btree
> *);
> u16 hfs_brec_lenoff(struct hfs_bnode *node, u16 rec, u16 *off)
> {
> __be16 retval[2];
> - u16 dataoff;
> + u16 data_off;
> + u16 next_off;
> +
> + if (hfs_brec_record_invalid(node, rec)) {
> + *off = U16_MAX;
> + return U16_MAX;
> + }
>
> - dataoff = node->tree->node_size - (rec + 2) * 2;
> - hfs_bnode_read(node, retval, dataoff, 4);
> + data_off = node->tree->node_size - (rec + 2) * 2;
> + hfs_bnode_read(node, retval, data_off, 4);
> *off = be16_to_cpu(retval[1]);
> - return be16_to_cpu(retval[0]) - *off;
> + next_off = be16_to_cpu(retval[0]);
> + if (hfs_brec_offsets_invalid(node, *off, next_off)) {
> + *off = U16_MAX;
> + return U16_MAX;
> + }
> + return next_off - *off;
> }
>
> /* Get the length of the key from a keyed record */
> u16 hfs_brec_keylen(struct hfs_bnode *node, u16 rec)
> {
> - u16 retval, recoff;
> + u16 retval, recoff, len;
>
> if (node->type != HFS_NODE_INDEX && node->type !=
> HFS_NODE_LEAF)
> return 0;
> + if (hfs_brec_record_invalid(node, rec))
> + return U16_MAX;
>
> if ((node->type == HFS_NODE_INDEX) &&
> !(node->tree->attributes & HFS_TREE_VARIDXKEYS) &&
> (node->tree->cnid != HFSPLUS_ATTR_CNID)) {
> retval = node->tree->max_key_len + 2;
> } else {
> - recoff = hfs_bnode_read_u16(node,
> - node->tree->node_size - (rec + 1) * 2);
> - if (!recoff)
> - return 0;
> - if (recoff > node->tree->node_size - 2) {
> - pr_err("recoff %d too large\n", recoff);
> - return 0;
> - }
> + len = hfs_brec_lenoff(node, rec, &recoff);
> + if (hfs_brec_len_invalid(node, len))
> + return len;
>
> retval = hfs_bnode_read_u16(node, recoff) + 2;
> if (retval > node->tree->max_key_len + 2) {
> pr_err("keylen %d too large\n",
> retval);
> - retval = 0;
> + retval = U16_MAX;
> }
> }
> return retval;
> @@ -181,14 +191,20 @@ int hfs_brec_remove(struct hfs_find_data *fd)
> struct hfs_btree *tree;
> struct hfs_bnode *node, *parent;
> int end_off, rec_off, data_off, size;
> + int res;
>
> tree = fd->tree;
> node = fd->bnode;
> again:
> + if (hfs_brec_record_invalid(node, fd->record))
> + return -EINVAL;
> +
> rec_off = tree->node_size - (fd->record + 2) * 2;
> end_off = tree->node_size - (node->num_recs + 1) * 2;
>
> if (node->type == HFS_NODE_LEAF) {
> + if (tree->leaf_count == 0)
> + return -EINVAL;
> tree->leaf_count--;
> mark_inode_dirty(tree->inode);
> }
> @@ -205,7 +221,9 @@ int hfs_brec_remove(struct hfs_find_data *fd)
> hfs_bnode_put(node);
> node = fd->bnode = parent;
>
> - __hfs_brec_find(node, fd, hfs_find_rec_by_key);
> + res = __hfs_brec_find(node, fd,
> hfs_find_rec_by_key);
> + if (res && res != -ENOENT)
> + return res;
> goto again;
> }
> hfs_bnode_write_u16(node,
> @@ -368,6 +386,7 @@ static int hfs_brec_update_parent(struct
> hfs_find_data *fd)
> int newkeylen, diff;
> int rec, rec_off, end_rec_off;
> int start_off, end_off;
> + int res;
>
> tree = fd->tree;
> node = fd->bnode;
> @@ -379,7 +398,9 @@ static int hfs_brec_update_parent(struct
> hfs_find_data *fd)
> parent = hfs_bnode_find(tree, node->parent);
> if (IS_ERR(parent))
> return PTR_ERR(parent);
> - __hfs_brec_find(parent, fd, hfs_find_rec_by_key);
> + res = __hfs_brec_find(parent, fd, hfs_find_rec_by_key);
> + if (res && res != -ENOENT)
> + return res;
> if (fd->record < 0)
> return -ENOENT;
> hfs_bnode_dump(parent);
> diff --git a/fs/hfsplus/btree.c b/fs/hfsplus/btree.c
> index 394542a47e60..b3d6ee78773e 100644
> --- a/fs/hfsplus/btree.c
> +++ b/fs/hfsplus/btree.c
> @@ -168,8 +168,8 @@ static struct page *hfs_bmap_get_map_page(struct
> hfs_bnode *node,
> }
>
> ctx->len = hfs_brec_lenoff(node, rec_idx, &off16);
> - if (!ctx->len)
> - return ERR_PTR(-ENOENT);
> + if (hfs_brec_len_invalid(node, ctx->len))
> + return ERR_PTR(-EINVAL);
>
> if (!is_bnode_offset_valid(node, off16))
> return ERR_PTR(-EIO);
> @@ -622,6 +622,11 @@ void hfs_bmap_free(struct hfs_bnode *node)
> if (IS_ERR(node))
> return;
> len = hfs_brec_lenoff(node, 2, &off);
> + if (hfs_brec_len_invalid(node, len) ||
> + !is_bnode_offset_valid(node, off)) {
If I am correct, the off value is never used. So, I think that this
check is not necessary here. Am I right?
> + hfs_bnode_put(node);
I think we cannot keep silence here. I believe that we should have the
error message for this case. Do you agree?
> + return;
> + }
> while (nidx >= len * 8) {
> u32 i;
>
> @@ -648,6 +653,11 @@ void hfs_bmap_free(struct hfs_bnode *node)
> return;
> }
> len = hfs_brec_lenoff(node, 0, &off);
> + if (hfs_brec_len_invalid(node, len) ||
> + !is_bnode_offset_valid(node, off)) {
Ditto.
> + hfs_bnode_put(node);
Ditto.
> + return;
> + }
> }
>
> res = hfs_bmap_clear_bit(node, nidx);
> diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
> index ec04b82ad927..90fcf1eac913 100644
> --- a/fs/hfsplus/hfsplus_fs.h
> +++ b/fs/hfsplus/hfsplus_fs.h
> @@ -587,6 +587,85 @@ bool is_bnode_offset_valid(struct hfs_bnode
> *node, u32 off)
> return is_valid;
> }
>
> +static inline
> +bool hfs_bnode_num_recs_invalid(struct hfs_bnode *node)
> +{
> + u32 node_size;
> + u32 table_size;
> + u32 area_size;
> + u32 rec_size = sizeof(__be16);
> + u32 desc_size = sizeof(struct hfs_bnode_desc);
> +
> + if (!node || !node->tree)
> + return true;
> +
> + node_size = node->tree->node_size;
> + if (node_size < desc_size)
> + return true;
> +
> + area_size = node_size - desc_size;
> + table_size = ((u32)node->num_recs + 1) * rec_size;
> +
> + return table_size > area_size;
> +}
> +
> +static inline
> +bool hfs_brec_record_invalid(struct hfs_bnode *node, int record)
> +{
> + if (hfs_bnode_num_recs_invalid(node))
> + return true;
> + if (record < 0)
> + return true;
> +
> + return record >= node->num_recs;
> +}
> +
> +static inline
> +bool hfs_brec_offsets_invalid(struct hfs_bnode *node, u16 off, u16
> next_off)
> +{
> + u32 table_size;
> + u32 table_start;
> + u32 rec_size = sizeof(__be16);
> + u32 desc_size = sizeof(struct hfs_bnode_desc);
> +
> + if (!node || !node->tree)
> + return true;
> +
> + if (off < desc_size || (off & 1))
> + return true;
> +
> + if (next_off <= off ||
> + next_off > node->tree->node_size ||
> + (next_off & 1))
> + return true;
> +
> + table_size = ((u32)node->num_recs + 1) * rec_size;
> + table_start = node->tree->node_size - table_size;
> + if (next_off > table_start)
> + return true;
> +
> + return false;
> +}
> +
> +static inline
> +bool hfs_brec_len_invalid(struct hfs_bnode *node, u16 len)
> +{
> + if (!node || !node->tree)
> + return true;
> +
> + return len == 0 || len > node->tree->node_size;
> +}
> +
> +static inline
> +void hfs_find_result_init(struct hfs_find_data *fd)
> +{
> + fd->record = -1;
> + fd->keyoffset = -1;
> + fd->keylength = -1;
> + fd->entryoffset = -1;
> + fd->entrylength = -1;
> +}
> +
> static inline
> u32 check_and_correct_requested_length(struct hfs_bnode *node, u32
> off, u32 len)
> {
Mostly, I don't see the critical issues in the patch. But some minor
corrections are necessary. Meanwhile, let me run xfstests for the
patch.
Thanks,
Slava.