Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S964900AbaFXPzh (ORCPT ); Tue, 24 Jun 2014 11:55:37 -0400 Received: from mail.linuxfoundation.org ([140.211.169.12]:33211 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S964879AbaFXPzd (ORCPT ); Tue, 24 Jun 2014 11:55:33 -0400 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, Mimi Zohar , Dmitry Kasatkin Subject: [PATCH 3.15 04/61] ima: audit log files opened with O_DIRECT flag Date: Tue, 24 Jun 2014 11:50:47 -0400 Message-Id: <20140624154952.974196654@linuxfoundation.org> X-Mailer: git-send-email 2.0.0 In-Reply-To: <20140624154952.751713761@linuxfoundation.org> References: <20140624154952.751713761@linuxfoundation.org> User-Agent: quilt/0.63-1 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 3.15-stable review patch. If anyone has any objections, please let me know. ------------------ From: Mimi Zohar commit f9b2a735bdddf836214b5dca74f6ca7712e5a08c upstream. 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 Acked-by: Dmitry Kasatkin Signed-off-by: Greg Kroah-Hartman --- 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(-) --- 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] --- a/security/integrity/ima/ima_api.c +++ b/security/integrity/ima/ima_api.c @@ -199,6 +199,7 @@ int ima_collect_measurement(struct integ 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 integ 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 integ 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; } --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -214,8 +214,11 @@ static int process_measurement(struct fi 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); --- 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, st 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; --- 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@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/