On Qualcomm Adreno/KGSL builds where CONFIG_QCOM_KGSL_USE_SHMEM is not set (or on older KGSL versions without CONFIG_QCOM_KGSL_USE_SHMEM), KGSL allocates GPU-shared memory from its own page pool. Pages from this pool are inserted into VMAs that don't have any weird flags like VM_PFNMAP set, which means userspace can grab extra references to these pages through get_user_pages() (for example, using vmsplice()). But when GPU-shared memory is freed, KGSL puts the freed pages into its own page pool without checking the page refcount. This means that pages that are still accessible from userspace can be reallocated as GPU memory by another process.

CVE-2023-21666