fix(format): validate chunk dimensions and chunk index offsets like libhdf5

A chunk dimension of 0 read a dataset as all fill values, 0x80000000 made
an 8 GiB chunk, and a chunk dimension the chunk index's offsets are not
multiples of read chunks at the wrong place (cve-2018-11205). libhdf5
refuses all of these; now so does clawhdf5:

- DataLayout::parse (H5O__layout_decode): no chunk dimension 0 ("bad chunk
  dimension value"), at most 33 dimensions, and before layout v4 at least
  2 ("bad dimensions for chunked storage"). New
  FormatError::InvalidChunkDimensions.
- Reading a chunked dataset (H5D__chunk_init / H5D__chunk_set_sizes): the
  chunk rank must match the dataspace's and a chunk must be under 4 GiB.
  One chunked_read::chunk_geometry replaces the four copies of the rank
  check.
- v1 B-tree chunk index (H5D__btree_decode_key): every key's offsets must
  be multiples of the chunk dimensions, including the keys that only bound
  a node, which is where cve-2018-11205's bad dimension shows. New
  chunked_read::collect_chunk_info_checked; the chunked read and selection
  paths use it.

New interop test header_validation_interop.rs: h5py writes chunked files
(layout v3 and v4), the script corrupts the chunk dimension, and
clawhdf5 must read exactly the copies h5py reads.

Conformance (cached corpus, tank): 570 ok, unchanged; cve-2018-11205 now
refuses the dataset h5py refuses; six more objects that already failed now
fail with libhdf5's reason.

Co-Authored-By: Claude Opus 5.5 (1M context) <[email protected]>

crates/clawhdf5-format/src/data_layout.rs

@@ -24,6 +24,34 @@ pub struct VdsMapping {
     pub virtual_selection: Vec<u8>,
 }
 
+/// Most dimensions a layout message can list (libhdf5 `H5O_LAYOUT_NDIMS`):
+/// 32 dataspace dimensions plus the element size.
+const MAX_LAYOUT_NDIMS: usize = 33;
+
+/// libhdf5's checks on a chunked layout message's dimensions
+/// (`H5O__layout_decode`): at most [`MAX_LAYOUT_NDIMS`], no dimension 0, and
+/// before version 4 at least one dataspace dimension plus the element size.
+/// A zero chunk dimension used to read the dataset as all fill values.
+fn check_chunk_dims(dims: Vec<u32>, layout_version: u8) -> Result<Vec<u32>, FormatError> {
+    if dims.len() > MAX_LAYOUT_NDIMS {
+        return Err(FormatError::InvalidChunkDimensions(
+            "dimensionality is too large".into(),
+        ));
+    }
+    if layout_version < 4 && dims.len() < 2 {
+        return Err(FormatError::InvalidChunkDimensions(
+            "bad dimensions for chunked storage".into(),
+        ));
+    }
+    if let Some(u) = dims.iter().position(|&d| d == 0) {
+        return Err(FormatError::InvalidChunkDimensions(format!(
+            "bad chunk dimension value when parsing layout message - chunk dimension must be \
+             positive: mesg->u.chunk.dim[{u}] = 0"
+        )));
+    }
+    Ok(dims)
+}
+
 /// Parsed HDF5 data layout message.
 #[derive(Debug, Clone, PartialEq)]
 pub enum DataLayout {
@@ -394,7 +422,7 @@ impl DataLayout {
                 Ok(DataLayout::Contiguous { address, size })
             }
             _ => Ok(DataLayout::Chunked {
-                chunk_dimensions: dims,
+                chunk_dimensions: check_chunk_dims(dims, 2)?,
                 btree_address: address,
                 version: 3,
                 chunk_index_type: None,
@@ -457,7 +485,7 @@ impl DataLayout {
                     p += 4;
                 }
                 Ok(DataLayout::Chunked {
-                    chunk_dimensions,
+                    chunk_dimensions: check_chunk_dims(chunk_dimensions, 3)?,
                     btree_address,
                     version: 3,
                     chunk_index_type: None,
@@ -506,6 +534,11 @@ impl DataLayout {
                 let dimensionality = data[pos + 1] as usize;
                 let dim_size_encoded_length = data[pos + 2] as usize;
                 let mut p = pos + 3;
+                if dimensionality > MAX_LAYOUT_NDIMS {
+                    return Err(FormatError::InvalidChunkDimensions(
+                        "dimensionality is too large".into(),
+                    ));
+                }
 
                 // dimension sizes
                 ensure_len(data, p, dimensionality * dim_size_encoded_length)?;
@@ -547,6 +580,7 @@ impl DataLayout {
                     chunk_dimensions.push(val);
                     p += dim_size_encoded_length;
                 }
+                let chunk_dimensions = check_chunk_dims(chunk_dimensions, 4)?;
 
                 // chunk index type
                 ensure_len(data, p, 1)?;
@@ -755,6 +789,55 @@ mod tests {
         );
     }
 
+    /// A v3 chunked layout message with these dims (element size last).
+    fn v3_chunked_msg(dims: &[u32]) -> Vec<u8> {
+        let mut buf = vec![3u8, 2, dims.len() as u8];
+        buf.extend_from_slice(&0x1000u64.to_le_bytes());
+        for d in dims {
+            buf.extend_from_slice(&d.to_le_bytes());
+        }
+        buf
+    }
+
+    #[test]
+    fn chunk_dimensions_are_checked_when_the_layout_is_parsed() {
+        assert!(DataLayout::parse(&v3_chunked_msg(&[4, 4, 8]), 8, 8).is_ok());
+        // A zero chunk dimension used to read as all fill values.
+        let err = DataLayout::parse(&v3_chunked_msg(&[4, 0, 8]), 8, 8).unwrap_err();
+        assert!(
+            matches!(&err, FormatError::InvalidChunkDimensions(m) if m.contains("dim[1] = 0")),
+            "{err:?}"
+        );
+        // Only the element-size dimension: libhdf5 "bad dimensions".
+        assert_eq!(
+            DataLayout::parse(&v3_chunked_msg(&[8]), 8, 8).unwrap_err(),
+            FormatError::InvalidChunkDimensions("bad dimensions for chunked storage".into())
+        );
+        assert_eq!(
+            DataLayout::parse(&v3_chunked_msg(&[1; 34]), 8, 8).unwrap_err(),
+            FormatError::InvalidChunkDimensions("dimensionality is too large".into())
+        );
+        // v1/v2 and v4 messages get the zero check too.
+        let mut v1 = v1v2_header(1, 2, 2);
+        v1.extend_from_slice(&0x1000u64.to_le_bytes());
+        v1.extend_from_slice(&0u32.to_le_bytes());
+        v1.extend_from_slice(&8u32.to_le_bytes());
+        assert!(matches!(
+            DataLayout::parse(&v1, 8, 8),
+            Err(FormatError::InvalidChunkDimensions(_))
+        ));
+        let mut v4 = vec![4u8, 2, 0, 2, 4];
+        v4.extend_from_slice(&0u32.to_le_bytes());
+        v4.extend_from_slice(&8u32.to_le_bytes());
+        v4.push(3); // fixed array index
+        v4.push(0); // page bits
+        v4.extend_from_slice(&0x1000u64.to_le_bytes());
+        assert!(matches!(
+            DataLayout::parse(&v4, 8, 8),
+            Err(FormatError::InvalidChunkDimensions(_))
+        ));
+    }
+
     #[test]
     fn v1v2_rejects_bad_class_dimensionality_and_truncation() {
         assert_eq!(