Re: [PATCH 12/12] ima: Support additional conditionals in the KEXEC_CMDLINE hook function

From: Mimi Zohar <zohar@linux.ibm.com>
To: Tyler Hicks <tyhicks@linux.microsoft.com>,
	Dmitry Kasatkin <dmitry.kasatkin@gmail.com>
Cc: James Morris <jmorris@namei.org>,
	"Serge E . Hallyn" <serge@hallyn.com>,
	Lakshmi Ramasubramanian <nramas@linux.microsoft.com>,
	Prakhar Srivastava <prsriva02@gmail.com>,
	linux-kernel@vger.kernel.org, linux-integrity@vger.kernel.org,
	linux-security-module@vger.kernel.org,
	Eric Biederman <ebiederm@xmission.com>,
	kexec@lists.infradead.org
Subject: Re: [PATCH 12/12] ima: Support additional conditionals in the KEXEC_CMDLINE hook function
Date: Thu, 25 Jun 2020 18:56:44 -0400	[thread overview]
Message-ID: <1593125804.27152.426.camel@linux.ibm.com> (raw)
In-Reply-To: <20200623003236.830149-13-tyhicks@linux.microsoft.com>

On Mon, 2020-06-22 at 19:32 -0500, Tyler Hicks wrote:
> Take the properties of the kexec kernel's inode and the current task
> ownership into consideration when matching a KEXEC_CMDLINE operation to
> the rules in the IMA policy. This allows for some uniformity when
> writing IMA policy rules for KEXEC_KERNEL_CHECK, KEXEC_INITRAMFS_CHECK,
> and KEXEC_CMDLINE operations.
> 
> Prior to this patch, it was not possible to write a set of rules like
> this:
> 
>  dont_measure func=KEXEC_KERNEL_CHECK obj_type=foo_t
>  dont_measure func=KEXEC_INITRAMFS_CHECK obj_type=foo_t
>  dont_measure func=KEXEC_CMDLINE obj_type=foo_t
>  measure func=KEXEC_KERNEL_CHECK
>  measure func=KEXEC_INITRAMFS_CHECK
>  measure func=KEXEC_CMDLINE
> 
> The inode information associated with the kernel being loaded by a
> kexec_kernel_load(2) syscall can now be included in the decision to
> measure or not
> 
> Additonally, the uid, euid, and subj_* conditionals can also now be
> used in KEXEC_CMDLINE rules. There was no technical reason as to why
> those conditionals weren't being considered previously other than
> ima_match_rules() didn't have a valid inode to use so it immediately
> bailed out for KEXEC_CMDLINE operations rather than going through the
> full list of conditional comparisons.

This makes a lot of sense.

<snip>

> diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
> index c1583d98c5e5..82acd66bf653 100644
> --- a/security/integrity/ima/ima_main.c
> +++ b/security/integrity/ima/ima_main.c
> @@ -731,13 +731,15 @@ int ima_load_data(enum kernel_load_data_id id)
>   * @eventname: event name to be used for the buffer entry.
>   * @func: IMA hook
>   * @pcr: pcr to extend the measurement
> + * @inode: inode associated with the object being measured (NULL for KEY_CHECK)
>   * @keyring: keyring name to determine the action to be performed
>   *
>   * Based on policy, the buffer is measured into the ima log.
>   */
>  void process_buffer_measurement(const void *buf, int size,
>  				const char *eventname, enum ima_hooks func,
> -				int pcr, const char *keyring)
> +				int pcr, struct inode *inode,
> +				const char *keyring)
>  {

The file descriptor is passed as the first arg to
process_measurement().  Sorry for the patch churn, but could we do the
same for process_buffer_measurements.  As much as possible lets keep
them in same.

thanks,

Mimi