[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-id: <537C7420.3010303@samsung.com>
Date: Wed, 21 May 2014 18:38:40 +0900
From: Dmitry Kasatkin <d.kasatkin@...sung.com>
To: Mimi Zohar <zohar@...ux.vnet.ibm.com>,
"J. R. Okajima" <hooanon05g@...il.com>
Cc: linux-security-module <linux-security-module@...r.kernel.org>,
Al Viro <viro@...iv.linux.org.uk>,
linux-kernel <linux-kernel@...r.kernel.org>
Subject: Re: [PATCH v1] ima: audit log files opened with O_DIRECT flag
On 20/05/14 06:06, Mimi Zohar wrote:
> Files are measured or appraised based on the IMA policy. When a
> file, in policy, is opened with the O_DIRECT flag, a deadlock
> occurs.
>
> The first attempt at resolving this lockdep temporarily removed the
> O_DIRECT flag and restored it, after calculating the hash. The
> second attempt introduced the O_DIRECT_HAVELOCK flag. Based on this
> flag, do_blockdev_direct_IO() would skip taking the i_mutex a second
> time. The third attempt, by Dmitry Kasatkin, resolves the i_mutex
> locking issue, by re-introducing the IMA mutex, but uncovered
> another problem. Reading a file with O_DIRECT flag set, writes
> directly to userspace pages. A second patch allocates a user-space
> like memory. This works for all IMA hooks, except ima_file_free(),
> which is called on __fput() to recalculate the file hash.
>
> Until this last issue is addressed, do not 'collect' the
> measurement for measuring, appraising, or auditing files opened
> with the O_DIRECT flag set. Based on policy, permit or deny file
> access. This patch defines a new IMA policy rule option named
> 'permit_directio'. Policy rules could be defined, based on LSM
> or other criteria, to permit specific applications to open files
> with the O_DIRECT flag set.
>
> Changelog v1:
> - permit or deny file access based IMA policy rules
>
> Signed-off-by: Mimi Zohar <zohar@...ux.vnet.ibm.com>
Acked-by: Dmitry Kasatkin <d.kasatkin@...sung.com>
> ---
> Documentation/ABI/testing/ima_policy | 2 +-
> security/integrity/ima/ima_api.c | 10 +++++++++-
> security/integrity/ima/ima_main.c | 5 ++++-
> security/integrity/ima/ima_policy.c | 6 +++++-
> security/integrity/integrity.h | 1 +
> 5 files changed, 20 insertions(+), 4 deletions(-)
>
> diff --git a/Documentation/ABI/testing/ima_policy b/Documentation/ABI/testing/ima_policy
> index f1c5cc9..4c3efe4 100644
> --- a/Documentation/ABI/testing/ima_policy
> +++ b/Documentation/ABI/testing/ima_policy
> @@ -23,7 +23,7 @@ Description:
> [fowner]]
> lsm: [[subj_user=] [subj_role=] [subj_type=]
> [obj_user=] [obj_role=] [obj_type=]]
> - option: [[appraise_type=]]
> + option: [[appraise_type=]] [permit_directio]
>
> base: func:= [BPRM_CHECK][MMAP_CHECK][FILE_CHECK][MODULE_CHECK]
> mask:= [MAY_READ] [MAY_WRITE] [MAY_APPEND] [MAY_EXEC]
> diff --git a/security/integrity/ima/ima_api.c b/security/integrity/ima/ima_api.c
> index ba9e4d7..d719978 100644
> --- a/security/integrity/ima/ima_api.c
> +++ b/security/integrity/ima/ima_api.c
> @@ -199,6 +199,7 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
> struct evm_ima_xattr_data **xattr_value,
> int *xattr_len)
> {
> + const char *audit_cause = "failed";
> struct inode *inode = file_inode(file);
> const char *filename = file->f_dentry->d_name.name;
> int result = 0;
> @@ -213,6 +214,12 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
> if (!(iint->flags & IMA_COLLECTED)) {
> u64 i_version = file_inode(file)->i_version;
>
> + if (file->f_flags & O_DIRECT) {
> + audit_cause = "failed(directio)";
> + result = -EACCES;
> + goto out;
> + }
> +
> /* use default hash algorithm */
> hash.hdr.algo = ima_hash_algo;
>
> @@ -233,9 +240,10 @@ int ima_collect_measurement(struct integrity_iint_cache *iint,
> result = -ENOMEM;
> }
> }
> +out:
> if (result)
> integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode,
> - filename, "collect_data", "failed",
> + filename, "collect_data", audit_cause,
> result, 0);
> return result;
> }
> diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
> index 52ac6cf..27ab5df 100644
> --- a/security/integrity/ima/ima_main.c
> +++ b/security/integrity/ima/ima_main.c
> @@ -214,8 +214,11 @@ static int process_measurement(struct file *file, const char *filename,
> xattr_ptr = &xattr_value;
>
> rc = ima_collect_measurement(iint, file, xattr_ptr, &xattr_len);
> - if (rc != 0)
> + if (rc != 0) {
> + if (file->f_flags & O_DIRECT)
> + rc = (iint->flags & IMA_PERMIT_DIRECTIO) ? 0 : -EACCES;
> goto out_digsig;
> + }
>
> pathname = filename ?: ima_d_path(&file->f_path, &pathbuf);
>
> diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c
> index 93873a4..40a7488 100644
> --- a/security/integrity/ima/ima_policy.c
> +++ b/security/integrity/ima/ima_policy.c
> @@ -353,7 +353,7 @@ enum {
> Opt_obj_user, Opt_obj_role, Opt_obj_type,
> Opt_subj_user, Opt_subj_role, Opt_subj_type,
> Opt_func, Opt_mask, Opt_fsmagic, Opt_uid, Opt_fowner,
> - Opt_appraise_type, Opt_fsuuid
> + Opt_appraise_type, Opt_fsuuid, Opt_permit_directio
> };
>
> static match_table_t policy_tokens = {
> @@ -375,6 +375,7 @@ static match_table_t policy_tokens = {
> {Opt_uid, "uid=%s"},
> {Opt_fowner, "fowner=%s"},
> {Opt_appraise_type, "appraise_type=%s"},
> + {Opt_permit_directio, "permit_directio"},
> {Opt_err, NULL}
> };
>
> @@ -622,6 +623,9 @@ static int ima_parse_rule(char *rule, struct ima_rule_entry *entry)
> else
> result = -EINVAL;
> break;
> + case Opt_permit_directio:
> + entry->flags |= IMA_PERMIT_DIRECTIO;
> + break;
> case Opt_err:
> ima_log_string(ab, "UNKNOWN", p);
> result = -EINVAL;
> diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h
> index 2fb5e53..33c0a70 100644
> --- a/security/integrity/integrity.h
> +++ b/security/integrity/integrity.h
> @@ -30,6 +30,7 @@
> #define IMA_ACTION_FLAGS 0xff000000
> #define IMA_DIGSIG 0x01000000
> #define IMA_DIGSIG_REQUIRED 0x02000000
> +#define IMA_PERMIT_DIRECTIO 0x04000000
>
> #define IMA_DO_MASK (IMA_MEASURE | IMA_APPRAISE | IMA_AUDIT | \
> IMA_APPRAISE_SUBMASK)
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists