Re: [PATCH v2 5/8] ima: Switch to dynamically allocated buffer for template digests

[Mimi Zohar <zohar@linux.ibm.com>]

On Thu, 2020-02-06 at 16:27 +0000, Roberto Sassu wrote:
> > -----Original Message-----
> > From: Mimi Zohar [mailto:zohar@linux.ibm.com]
> > Sent: Thursday, February 6, 2020 5:08 PM
> > To: Roberto Sassu <roberto.sassu@huawei.com>;
> > James.Bottomley@HansenPartnership.com;
> > jarkko.sakkinen@linux.intel.com
> > Cc: linux-integrity@vger.kernel.org; linux-security-module@vger.kernel.org;
> > linux-kernel@vger.kernel.org; Silviu Vlasceanu
> > <Silviu.Vlasceanu@huawei.com>
> > Subject: Re: [PATCH v2 5/8] ima: Switch to dynamically allocated buffer for
> > template digests
> > 
> > Hi Roberto,
> > 
> > On Wed, 2020-02-05 at 11:33 +0100, Roberto Sassu wrote:
> > > This patch dynamically allocates the array of tpm_digest structures in
> > > ima_alloc_init_template() and ima_restore_template_data(). The size of
> > the
> > > array, stored in ima_num_template_digests, is initially equal to 1 (SHA1)
> > > and will be determined in the upcoming patches depending on the
> > allocated
> > > PCR banks and the chosen default IMA algorithm.
> > >
> > > Calculating the SHA1 digest is mandatory, as SHA1 still remains the default
> > > hash algorithm for the measurement list. When IMA will support the
> > Crypto
> > > Agile format, remaining digests will be also provided.
> > >
> > > The position in the array of the SHA1 digest is stored in the ima_sha1_idx
> > > global variable and it is determined at IMA initialization time.
> > >
> > > Changelog
> > >
> > > v1:
> > > - move ima_sha1_idx to ima_crypto.c
> > > - introduce ima_num_template_digests (suggested by Mimi)
> > 
> > Instead of hardcoding "nr_allocated_banks + 1" or nr_allocated_banks +
> > 2", I suggested defining "nr_allocated_banks + extra", where "extra"
> > could be 0, 1, or 2.
> > 
> > The rest of the code would remain exactly the same as you had.
> 
> Ok. I did a small improvement. Since we determine the number of
> required elements of ima_algo_array before kmalloc() I thought it
> was ok to directly set that number of elements in a single variable.
> 
> If you think that having two variables is better, I will change it.

The connection to nr_allocated_banks is then not as visible.  Using
two variables is clearer.

Mimi