From 895ebf705ea5b830685424cbfe0ebef7cfd90d28 Mon Sep 17 00:00:00 2001
From: jhendersonHDF <jhenderson@hdfgroup.org>
Date: Fri, 14 Apr 2023 20:30:21 -0500
Subject: Fix a heap buffer overflow during H5D__compact_readvv (GitHub #2606)
 (#2664) (#2726)

---
 release_docs/RELEASE.txt | 19 +++++++++++++++++++
 src/H5Dint.c             | 27 +++++++++++++++++++++++++++
 2 files changed, 46 insertions(+)

diff --git a/release_docs/RELEASE.txt b/release_docs/RELEASE.txt
index 61a2d40..acc5411 100644
--- a/release_docs/RELEASE.txt
+++ b/release_docs/RELEASE.txt
@@ -223,6 +223,25 @@ Bug Fixes since HDF5-1.12.1 release
 ===================================
     Library
     -------
+    - Fixed a heap buffer overflow that occurs when reading from
+      a dataset with a compact layout within a malformed HDF5 file
+
+      During opening of a dataset that has a compact layout, the
+      library allocates a buffer that stores the dataset's raw data.
+      The dataset's object header that gets written to the file
+      contains information about how large of a buffer the library
+      should allocate. If this object header is malformed such that
+      it causes the library to allocate a buffer that is too small
+      to hold the dataset's raw data, future I/O to the dataset can
+      result in heap buffer overflows. To fix this issue, an extra
+      check is now performed for compact datasets to ensure that
+      the size of the allocated buffer matches the expected size
+      of the dataset's raw data (as calculated from the dataset's
+      dataspace and datatype information). If the two sizes do not
+      match, opening of the dataset will fail.
+
+      (JTH - 2023/04/04, GH-2606)
+
     - Fix for CVE-2019-8396
 
       Malformed HDF5 files may have truncated content which does not match
diff --git a/src/H5Dint.c b/src/H5Dint.c
index 24985f3..95be827 100644
--- a/src/H5Dint.c
+++ b/src/H5Dint.c
@@ -1764,6 +1764,33 @@ H5D__open_oid(H5D_t *dataset, hid_t dapl_id)
     /* Indicate that the layout information was initialized */
     layout_init = TRUE;
 
+    /*
+     * Now that we've read the dataset's datatype, dataspace and
+     * layout information, perform a quick check for compact datasets
+     * to ensure that the size of the internal buffer that was
+     * allocated for the dataset's raw data matches the size of
+     * the data. A corrupted file can cause a mismatch between the
+     * two, which might result in buffer overflows during future
+     * I/O to the dataset.
+     */
+    if (H5D_COMPACT == dataset->shared->layout.type) {
+        hssize_t dset_nelemts   = 0;
+        size_t   dset_type_size = H5T_GET_SIZE(dataset->shared->type);
+        size_t   dset_data_size = 0;
+
+        HDassert(H5D_COMPACT == dataset->shared->layout.storage.type);
+
+        if ((dset_nelemts = H5S_GET_EXTENT_NPOINTS(dataset->shared->space)) < 0)
+            HGOTO_ERROR(H5E_DATASET, H5E_CANTGET, FAIL, "can't get number of elements in dataset's dataspace")
+
+        dset_data_size = (size_t)dset_nelemts * dset_type_size;
+
+        if (dataset->shared->layout.storage.u.compact.size != dset_data_size)
+            HGOTO_ERROR(H5E_DATASET, H5E_BADVALUE, FAIL,
+                        "bad value from dataset header - size of compact dataset's data buffer doesn't match "
+                        "size of dataset data");
+    }
+
     /* Set up flush append property */
     if (H5D__append_flush_setup(dataset, dapl_id))
         HGOTO_ERROR(H5E_DATASET, H5E_CANTSET, FAIL, "unable to set up flush append property")
-- 
cgit v0.12