Re: [PATCH v17 18/23] platform/x86: Intel SGX driver

[Andy Lutomirski <luto@kernel.org>]

On Thu, Nov 15, 2018 at 5:08 PM Jarkko Sakkinen
<jarkko.sakkinen@linux.intel.com> wrote:
>
> Intel Software Guard eXtensions (SGX) is a set of CPU instructions that
> can be used by applications to set aside private regions of code and
> data. The code outside the enclave is disallowed to access the memory
> inside the enclave by the CPU access control.

This is a very partial review.

> +int sgx_encl_find(struct mm_struct *mm, unsigned long addr,
> +                 struct vm_area_struct **vma)
> +{
> +       struct vm_area_struct *result;
> +       struct sgx_encl *encl;
> +
> +       result = find_vma(mm, addr);
> +       if (!result || result->vm_ops != &sgx_vm_ops || addr < result->vm_start)
> +               return -EINVAL;
> +
> +       encl = result->vm_private_data;
> +       *vma = result;
> +
> +       return encl ? 0 : -ENOENT;
> +}

I realize that this function may go away entirely but, if you keep it:
what are the locking rules?  What, if anything, prevents another
thread from destroying the enclave after sgx_encl_find() returns?

> +static int sgx_validate_secs(const struct sgx_secs *secs,
> +                            unsigned long ssaframesize)
> +{

...

> +       if (secs->attributes & SGX_ATTR_MODE64BIT) {
> +               if (secs->size > sgx_encl_size_max_64)
> +                       return -EINVAL;
> +       } else {
> +               /* On 64-bit architecture allow 32-bit encls only in
> +                * the compatibility mode.
> +                */
> +               if (!test_thread_flag(TIF_ADDR32))
> +                       return -EINVAL;
> +               if (secs->size > sgx_encl_size_max_32)
> +                       return -EINVAL;
> +       }

Why do we need the 32-bit-on-64-bit check?  In general, anything that
checks per-task or per-mm flags like TIF_ADDR32 is IMO likely to be
problematic.  You're allowing 64-bit enclaves in 32-bit tasks, so I'm
guessing you could just delete the check.

> +
> +       if (!(secs->xfrm & XFEATURE_MASK_FP) ||
> +           !(secs->xfrm & XFEATURE_MASK_SSE) ||
> +           (((secs->xfrm >> XFEATURE_BNDREGS) & 1) !=
> +            ((secs->xfrm >> XFEATURE_BNDCSR) & 1)) ||
> +           (secs->xfrm & ~sgx_xfrm_mask))
> +               return -EINVAL;

Do we need to check that the enclave doesn't use xfeatures that the
kernel doesn't know about?  Or are they all safe by design in enclave
mode?

> +static int sgx_encl_pm_notifier(struct notifier_block *nb,
> +                               unsigned long action, void *data)
> +{
> +       struct sgx_encl *encl = container_of(nb, struct sgx_encl, pm_notifier);
> +
> +       if (action != PM_SUSPEND_PREPARE && action != PM_HIBERNATION_PREPARE)
> +               return NOTIFY_DONE;

Hmm.  There's an argument to made that omitting this would better
exercise the code that handles fully asynchronous loss of an enclave.
Also, I think you're unnecessarily killing enclaves when suspend is
attempted but fails.

> +
> +static int sgx_get_key_hash(const void *modulus, void *hash)
> +{
> +       struct crypto_shash *tfm;
> +       int ret;
> +
> +       tfm = crypto_alloc_shash("sha256", 0, CRYPTO_ALG_ASYNC);
> +       if (IS_ERR(tfm))
> +               return PTR_ERR(tfm);
> +
> +       ret = __sgx_get_key_hash(tfm, modulus, hash);
> +
> +       crypto_free_shash(tfm);
> +       return ret;
> +}
> +

I'm so sorry you had to deal with this API.  Once Zinc lands, you
could clean this up :)


> +static int sgx_encl_get(unsigned long addr, struct sgx_encl **encl)
> +{
> +       struct mm_struct *mm = current->mm;
> +       struct vm_area_struct *vma;
> +       int ret;
> +
> +       if (addr & (PAGE_SIZE - 1))
> +               return -EINVAL;
> +
> +       down_read(&mm->mmap_sem);
> +
> +       ret = sgx_encl_find(mm, addr, &vma);
> +       if (!ret) {
> +               *encl = vma->vm_private_data;
> +
> +               if ((*encl)->flags & SGX_ENCL_SUSPEND)
> +                       ret = SGX_POWER_LOST_ENCLAVE;
> +               else
> +                       kref_get(&(*encl)->refcount);
> +       }

Hmm.  This version has explicit refcounting.

> +static int sgx_mmap(struct file *file, struct vm_area_struct *vma)
> +{
> +       vma->vm_ops = &sgx_vm_ops;
> +       vma->vm_flags |= VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP | VM_IO |
> +                        VM_DONTCOPY;
> +
> +       return 0;
> +}
> +
> +static unsigned long sgx_get_unmapped_area(struct file *file,
> +                                          unsigned long addr,
> +                                          unsigned long len,
> +                                          unsigned long pgoff,
> +                                          unsigned long flags)
> +{
> +       if (len < 2 * PAGE_SIZE || (len & (len - 1)))
> +               return -EINVAL;
> +
> +       if (len > sgx_encl_size_max_64)
> +               return -EINVAL;
> +
> +       if (len > sgx_encl_size_max_32 && test_thread_flag(TIF_ADDR32))
> +               return -EINVAL;

Generally speaking, this type of check wants to be
in_compat_syscall().  But I'm not sure I understand why you need it at
all.

> +static void sgx_ipi_cb(void *info)
> +{
> +}
> +
> +void sgx_flush_cpus(struct sgx_encl *encl)
> +{
> +       on_each_cpu_mask(mm_cpumask(encl->mm), sgx_ipi_cb, NULL, 1);
> +}

Please add a comment explaining what this promises to do.