summaryrefslogtreecommitdiffstats
path: root/security/integrity/ima
Commit message (Collapse)AuthorAgeFilesLines
* Merge branch 'next' of ↵James Morris2014-12-161-1/+1
|\ | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity into for-linus
| * ima: Fix build failure on powerpc when TCG_IBMVTPM dependencies are not metMichael Ellerman2014-12-061-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | On powerpc we can end up with IMA=y and PPC_PSERIES=n which leads to: warning: (IMA) selects TCG_IBMVTPM which has unmet direct dependencies (TCG_TPM && PPC_PSERIES) tpm_ibmvtpm.c:(.text+0x14f3e8): undefined reference to `.plpar_hcall_norets' I'm not sure why IMA needs to select those user-visible symbols, but if it must then the simplest fix is to just express the proper dependencies on the select. Tested-by: Hon Ching (Vicky) Lo <lo1@us.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* | Merge branch 'next' of ↵Linus Torvalds2014-12-148-107/+164
|\| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security Pull security layer updates from James Morris: "In terms of changes, there's general maintenance to the Smack, SELinux, and integrity code. The IMA code adds a new kconfig option, IMA_APPRAISE_SIGNED_INIT, which allows IMA appraisal to require signatures. Support for reading keys from rootfs before init is call is also added" * 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/jmorris/linux-security: (23 commits) selinux: Remove security_ops extern security: smack: fix out-of-bounds access in smk_parse_smack() VFS: refactor vfs_read() ima: require signature based appraisal integrity: provide a hook to load keys when rootfs is ready ima: load x509 certificate from the kernel integrity: provide a function to load x509 certificate from the kernel integrity: define a new function integrity_read_file() Security: smack: replace kzalloc with kmem_cache for inode_smack Smack: Lock mode for the floor and hat labels ima: added support for new kernel cmdline parameter ima_template_fmt ima: allocate field pointers array on demand in template_desc_init_fields() ima: don't allocate a copy of template_fmt in template_desc_init_fields() ima: display template format in meas. list if template name length is zero ima: added error messages to template-related functions ima: use atomic bit operations to protect policy update interface ima: ignore empty and with whitespaces policy lines ima: no need to allocate entry for comment ima: report policy load status ima: use path names cache ...
| * ima: require signature based appraisalDmitry Kasatkin2014-11-172-0/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch provides CONFIG_IMA_APPRAISE_SIGNED_INIT kernel configuration option to force IMA appraisal using signatures. This is useful, when EVM key is not initialized yet and we want securely initialize integrity or any other functionality. It forces embedded policy to require signature. Signed initialization script can initialize EVM key, update the IMA policy and change further requirement of everything to be signed. Changes in v3: * kernel parameter fixed to configuration option in the patch description Changes in v2: * policy change of this patch separated from the key loading patch Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: load x509 certificate from the kernelDmitry Kasatkin2014-11-173-2/+36
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Define configuration option to load X509 certificate into the IMA trusted kernel keyring. It implements ima_load_x509() hook to load X509 certificate into the .ima trusted kernel keyring from the root filesystem. Changes in v3: * use ima_policy_flag in ima_get_action() ima_load_x509 temporarily clears ima_policy_flag to disable appraisal to load key. Use it to skip appraisal rules. * Key directory path changed to /etc/keys (Mimi) * Expand IMA_LOAD_X509 Kconfig help Changes in v2: * added '__init' * use ima_policy_flag to disable appraisal to load keys Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * integrity: define a new function integrity_read_file()Dmitry Kasatkin2014-11-171-32/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch defines a new function called integrity_read_file() to read file from the kernel into a buffer. Subsequent patches will read a file containing the public keys and load them onto the IMA keyring. This patch moves and renames ima_kernel_read(), the non-security checking version of kernel_read(), to integrity_kernel_read(). Changes in v3: * Patch descriptions improved (Mimi) * Add missing cast (kbuild test robot) Changes in v2: * configuration option removed * function declared as '__init' Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: added support for new kernel cmdline parameter ima_template_fmtRoberto Sassu2014-10-131-5/+34
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch allows users to provide a custom template format through the new kernel command line parameter 'ima_template_fmt'. If the supplied format is not valid, IMA uses the default template descriptor. Changelog: - v3: - added check for 'fields' and 'num_fields' in template_desc_init_fields() (suggested by Mimi Zohar) - v2: - using template_desc_init_fields() to validate a format string (Roberto Sassu) - updated documentation by stating that only the chosen template descriptor is initialized (Roberto Sassu) - v1: - simplified code of ima_template_fmt_setup() (Roberto Sassu, suggested by Mimi Zohar) Signed-off-by: Roberto Sassu <roberto.sassu@polito.it> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: allocate field pointers array on demand in template_desc_init_fields()Roberto Sassu2014-10-131-21/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The allocation of a field pointers array is moved at the end of template_desc_init_fields() and done only if the value of the 'fields' and 'num_fields' parameters is not NULL. For just validating a template format string, retrieved template field pointers are placed in a temporary array. Changelog: - v3: - do not check in this patch if 'fields' and 'num_fields' are NULL (suggested by Mimi Zohar) Signed-off-by: Roberto Sassu <roberto.sassu@polito.it> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: don't allocate a copy of template_fmt in template_desc_init_fields()Roberto Sassu2014-10-131-13/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch removes the allocation of a copy of 'template_fmt', needed for iterating over all fields in the passed template format string. The removal was possible by replacing strcspn(), which modifies the passed string, with strchrnul(). The currently processed template field is copied in a temporary variable. The purpose of this change is use template_desc_init_fields() in two ways: for just validating a template format string (the function should work if called by a setup function, when memory cannot be allocated), and for actually initializing a template descriptor. The implementation of this feature will be complete with the next patch. Changelog: - v3: - added 'goto out' in template_desc_init_fields() to free allocated memory if a template field length is not valid (suggested by Mimi Zohar) Signed-off-by: Roberto Sassu <roberto.sassu@polito.it> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: display template format in meas. list if template name length is zeroRoberto Sassu2014-10-132-5/+15
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | With the introduction of the 'ima_template_fmt' kernel cmdline parameter, a user can define a new template descriptor with custom format. However, in this case, userspace tools will be unable to parse the measurements list because the new template is unknown. For this reason, this patch modifies the current IMA behavior to display in the list the template format instead of the name (only if the length of the latter is zero) so that a tool can extract needed information if it can handle listed fields. This patch also correctly displays the error log message in ima_init_template() if the selected template cannot be initialized. Changelog: - v3: - check the first byte of 'e->template_desc->name' instead of using strlen() in ima_fs.c (suggested by Mimi Zohar) - v2: - print the template format in ima_init_template(), if the selected template is custom (Roberto Sassu) - v1: - fixed patch description (Roberto Sassu, suggested by Mimi Zohar) - set 'template_name' variable in ima_fs.c only once (Roberto Sassu, suggested by Mimi Zohar) Signed-off-by: Roberto Sassu <roberto.sassu@polito.it> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: added error messages to template-related functionsRoberto Sassu2014-10-131-5/+17
| | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds some error messages to inform users about the following events: template descriptor not found, invalid template descriptor, template field not found and template initialization failed. Changelog: - v2: - display an error message if the format string contains too many fields (Roberto Sassu) Signed-off-by: Roberto Sassu <roberto.sassu@polito.it> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: use atomic bit operations to protect policy update interfaceDmitry Kasatkin2014-10-112-28/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The current implementation uses an atomic counter to provide exclusive access to the sysfs 'policy' entry to update the IMA policy. While it is highly unlikely, the usage of a counter might potentially allow another process to overflow the counter, open the interface and insert additional rules into the policy being loaded. This patch replaces using an atomic counter with atomic bit operations which is more reliable and a widely used method to provide exclusive access. As bit operation keep the interface locked after successful update, it makes it unnecessary to verify if the default policy was set or not during parsing and interface closing. This patch also removes that code. Changes in v3: * move audit log message to ima_relead_policy() to report successful and unsuccessful result * unnecessary comment removed Changes in v2: * keep interface locked after successful policy load as in original design * remove sysfs entry as in original design Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: ignore empty and with whitespaces policy linesDmitry Kasatkin2014-10-111-1/+2
| | | | | | | | | | | | | | | | | | | | | | Empty policy lines cause parsing failures which is, especially for new users, hard to spot. This patch prevents it. Changes in v2: * strip leading blanks and tabs in rules to prevent parsing failures Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: no need to allocate entry for commentDmitry Kasatkin2014-10-111-8/+6
| | | | | | | | | | | | | | | | If a rule is a comment, there is no need to allocate an entry. Move the checking for comments before allocating the entry. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: report policy load statusDmitry Kasatkin2014-10-111-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | Audit messages are rate limited, often causing the policy update info to not be visible. Report policy loading status also using pr_info. Changes in v2: * reporting moved to ima_release_policy to notice parsing errors * reporting both completed and failed status Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: use path names cacheDmitry Kasatkin2014-10-072-3/+4
| | | | | | | | | | | | | | | | __getname() uses slab allocation which is faster than kmalloc. Make use of it. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
| * ima: check ima_policy_flag in the ima_file_free() hookDmitry Kasatkin2014-10-071-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch completes the switching to the 'ima_policy_flag' variable in the checks at the beginning of IMA functions, starting with the commit a756024e. Checking 'iint_initialized' is completely unnecessary, because S_IMA flag is unset if iint was not allocated. At the same time the integrity cache is allocated with SLAB_PANIC and the kernel will panic if the allocation fails during kernel initialization. So on a running system iint_initialized is always true and can be removed. Changes in v3: * not limiting test to IMA_APPRAISE (spotted by Roberto Sassu) Changes in v2: * 'iint_initialized' removal patch merged to this patch (requested by Mimi) Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Acked-by: Roberto Sassu <roberto.sassu@polito.it>
* | Merge branch 'iov_iter' into for-nextAl Viro2014-12-081-0/+2
|\ \
| * \ Merge branch 'for-linus' of ↵James Morris2014-10-291-0/+2
| |\ \ | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/zohar/linux-integrity into for-linus
| | * | ima: check xattr value length and type in the ima_inode_setxattr()Dmitry Kasatkin2014-10-281-0/+2
| | |/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | ima_inode_setxattr() can be called with no value. Function does not check the length so that following command can be used to produce kernel oops: setfattr -n security.ima FOO. This patch fixes it. Changes in v3: * for stable reverted "allow setting hash only in fix or log mode" It will be a separate patch. Changes in v2: * testing validity of xattr type * allow setting hash only in fix or log mode (Mimi) [ 261.562522] BUG: unable to handle kernel NULL pointer dereference at (null) [ 261.564109] IP: [<ffffffff812af272>] ima_inode_setxattr+0x3e/0x5a [ 261.564109] PGD 3112f067 PUD 42965067 PMD 0 [ 261.564109] Oops: 0000 [#1] SMP [ 261.564109] Modules linked in: bridge stp llc evdev serio_raw i2c_piix4 button fuse [ 261.564109] CPU: 0 PID: 3299 Comm: setxattr Not tainted 3.16.0-kds+ #2924 [ 261.564109] Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 [ 261.564109] task: ffff8800428c2430 ti: ffff880042be0000 task.ti: ffff880042be0000 [ 261.564109] RIP: 0010:[<ffffffff812af272>] [<ffffffff812af272>] ima_inode_setxattr+0x3e/0x5a [ 261.564109] RSP: 0018:ffff880042be3d50 EFLAGS: 00010246 [ 261.564109] RAX: 0000000000000001 RBX: 0000000000000000 RCX: 0000000000000015 [ 261.564109] RDX: 0000001500000000 RSI: 0000000000000000 RDI: ffff8800375cc600 [ 261.564109] RBP: ffff880042be3d68 R08: 0000000000000000 R09: 00000000004d6256 [ 261.564109] R10: 0000000000000000 R11: 0000000000000000 R12: ffff88002149ba00 [ 261.564109] R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 [ 261.564109] FS: 00007f6c1e219740(0000) GS:ffff88005da00000(0000) knlGS:0000000000000000 [ 261.564109] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 261.564109] CR2: 0000000000000000 CR3: 000000003b35a000 CR4: 00000000000006f0 [ 261.564109] Stack: [ 261.564109] ffff88002149ba00 ffff880042be3df8 0000000000000000 ffff880042be3d98 [ 261.564109] ffffffff812a101b ffff88002149ba00 ffff880042be3df8 0000000000000000 [ 261.564109] 0000000000000000 ffff880042be3de0 ffffffff8116d08a ffff880042be3dc8 [ 261.564109] Call Trace: [ 261.564109] [<ffffffff812a101b>] security_inode_setxattr+0x48/0x6a [ 261.564109] [<ffffffff8116d08a>] vfs_setxattr+0x6b/0x9f [ 261.564109] [<ffffffff8116d1e0>] setxattr+0x122/0x16c [ 261.564109] [<ffffffff811687e8>] ? mnt_want_write+0x21/0x45 [ 261.564109] [<ffffffff8114d011>] ? __sb_start_write+0x10f/0x143 [ 261.564109] [<ffffffff811687e8>] ? mnt_want_write+0x21/0x45 [ 261.564109] [<ffffffff811687c0>] ? __mnt_want_write+0x48/0x4f [ 261.564109] [<ffffffff8116d3e6>] SyS_setxattr+0x6e/0xb0 [ 261.564109] [<ffffffff81529da9>] system_call_fastpath+0x16/0x1b [ 261.564109] Code: 48 89 f7 48 c7 c6 58 36 81 81 53 31 db e8 73 27 04 00 85 c0 75 28 bf 15 00 00 00 e8 8a a5 d9 ff 84 c0 75 05 83 cb ff eb 15 31 f6 <41> 80 7d 00 03 49 8b 7c 24 68 40 0f 94 c6 e8 e1 f9 ff ff 89 d8 [ 261.564109] RIP [<ffffffff812af272>] ima_inode_setxattr+0x3e/0x5a [ 261.564109] RSP <ffff880042be3d50> [ 261.564109] CR2: 0000000000000000 [ 261.599998] ---[ end trace 39a89a3fc267e652 ]--- Reported-by: Jan Kara <jack@suse.cz> Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Cc: stable@vger.kernel.org Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* | / kill f_dentry usesAl Viro2014-11-193-5/+5
|/ / | | | | | | Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
* / security, crypto: LLVMLinux: Remove VLAIS from ima_crypto.cBehan Webster2014-10-141-28/+19
|/ | | | | | | | | | | | | | | Replaced the use of a Variable Length Array In Struct (VLAIS) with a C99 compliant equivalent. This patch allocates the appropriate amount of memory using a char array using the SHASH_DESC_ON_STACK macro. The new code can be compiled with both gcc and clang. Signed-off-by: Behan Webster <behanw@converseincode.com> Reviewed-by: Mark Charlebois <charlebm@gmail.com> Reviewed-by: Jan-Simon Möller <dl9pf@gmx.de> Acked-by: Herbert Xu <herbert@gondor.apana.org.au> Acked-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Cc: tglx@linutronix.de
* ima: detect violations for mmaped filesRoberto Sassu2014-09-182-9/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes the detection of the 'open_writers' violation for mmaped files. before) an 'open_writers' violation is detected if the policy contains a rule with the criteria: func=FILE_CHECK mask=MAY_READ after) an 'open_writers' violation is detected if the current event matches one of the policy rules. With the old behaviour, the 'open_writers' violation is not detected in the following case: policy: measure func=FILE_MMAP mask=MAY_EXEC steps: 1) open a shared library for writing 2) execute a binary that links that shared library 3) during the binary execution, modify the shared library and save the change result: the 'open_writers' violation measurement is not present in the IMA list. Only binaries executed are protected from writes. For libraries mapped in memory there is the flag MAP_DENYWRITE for this purpose, but according to the output of 'man mmap', the mmap flag is ignored. Since ima_rdwr_violation_check() is now called by process_measurement() the information about if the inode must be measured is already provided by ima_get_action(). Thus the unnecessary function ima_must_measure() has been removed. Changes in v3 (Dmitry Kasatkin): - Violation for MMAP_CHECK function are verified since this patch - Changed patch description a bit Signed-off-by: Roberto Sassu <roberto.sassu@polito.it> Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: fix race condition on ima_rdwr_violation_check and process_measurementRoberto Sassu2014-09-181-21/+33
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes a race condition between two functions that try to access the same inode. Since the i_mutex lock is held and released separately in the two functions, there may be the possibility that a violation is not correctly detected. Suppose there are two processes, A (reader) and B (writer), if the following sequence happens: A: ima_rdwr_violation_check() B: ima_rdwr_violation_check() B: process_measurement() B: starts writing the inode A: process_measurement() the ToMToU violation (a reader may be accessing a content different from that measured, due to a concurrent modification by a writer) will not be detected. To avoid this issue, the violation check and the measurement must be done atomically. This patch fixes the problem by moving the violation check inside process_measurement() when the i_mutex lock is held. Differently from the old code, the violation check is executed also for the MMAP_CHECK hook (other than for FILE_CHECK). This allows to detect ToMToU violations that are possible because shared libraries can be opened for writing while they are in use (according to the output of 'man mmap', the mmap() flag MAP_DENYWRITE is ignored). Changes in v5 (Roberto Sassu): * get iint if action is not zero * exit process_measurement() after the violation check if action is zero * reverse order process_measurement() exit cleanup (Mimi) Changes in v4 (Dmitry Kasatkin): * iint allocation is done before calling ima_rdrw_violation_check() (Suggested-by Mimi) * do not check for violations if the policy does not contain 'measure' rules (done by Roberto Sassu) Changes in v3 (Dmitry Kasatkin): * no violation checking for MMAP_CHECK function in this patch * remove use of filename from violation * removes checking if ima is enabled from ima_rdrw_violation_check * slight style change Suggested-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Roberto Sassu <roberto.sassu@polito.it> Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: added ima_policy_flag variableRoberto Sassu2014-09-174-5/+34
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch introduces the new variable 'ima_policy_flag', whose bits are set depending on the action of the current policy rules. Only the flags IMA_MEASURE, IMA_APPRAISE and IMA_AUDIT are set. The new variable will be used to improve performance by skipping the unnecessary execution of IMA code if the policy does not contain rules with the above actions. Changes in v6 (Roberto Sassu) * do not check 'ima_initialized' before calling ima_update_policy_flag() in ima_update_policy() (suggested by Dmitry) * calling ima_update_policy_flag() moved to init_ima to co-locate with ima_initialized (Dmitry) * add/revise comments (Mimi) Changes in v5 (Roberto Sassu) * reset IMA_APPRAISE flag in 'ima_policy_flag' if 'ima_appraise' is set to zero (reported by Dmitry) * update 'ima_policy_flag' only if IMA initialization is successful (suggested by Mimi and Dmitry) * check 'ima_policy_flag' instead of 'ima_initialized' (suggested by Mimi and Dmitry) Signed-off-by: Roberto Sassu <roberto.sassu@polito.it> Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: return an error code from ima_add_boot_aggregate()Roberto Sassu2014-09-171-6/+15
| | | | | | | | | This patch modifies ima_add_boot_aggregate() to return an error code. This way we can determine if all the initialization procedures have been executed successfully. Signed-off-by: Roberto Sassu <roberto.sassu@polito.it> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: provide 'ima_appraise=log' kernel optionDmitry Kasatkin2014-09-172-2/+5
| | | | | | | | | | | | | | The kernel boot parameter "ima_appraise" currently defines 'off', 'enforce' and 'fix' modes. When designing a policy and labeling the system, access to files are either blocked in the default 'enforce' mode or automatically fixed in the 'fix' mode. It is beneficial to be able to run the system in a logging only mode, without fixing it, in order to properly analyze the system. This patch adds a 'log' mode to run the system in a permissive mode and log the appraisal results. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: move keyring initialization to ima_init()Dmitry Kasatkin2014-09-172-8/+6
| | | | | | | | | | | | | | | ima_init() is used as a single place for all initializations. Experimental keyring patches used the 'late_initcall' which was co-located with the late_initcall(init_ima). When the late_initcall for the keyring initialization was abandoned, initialization moved to init_ima, though it would be more logical to move it to ima_init, where the rest of the initialization is done. This patch moves the keyring initialization to ima_init() as a preparatory step for loading the keys which will be added to ima_init() in following patches. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* integrity: base integrity subsystem kconfig options on integrityDmitry Kasatkin2014-09-091-2/+0
| | | | | | | | | | | | | | | | | | | | | | | The integrity subsystem has lots of options and takes more than half of the security menu. This patch consolidates the options under "integrity", which are hidden if not enabled. This change does not affect existing configurations. Re-configuration is not needed. Changes v4: - no need to change "integrity subsystem" to menuconfig as options are hidden, when not enabled. (Mimi) - add INTEGRITY Kconfig help description Changes v3: - dependency to INTEGRITY removed when behind 'if INTEGRITY' Changes v2: - previous patch moved integrity out of the 'security' menu. This version keeps integrity as a security option (Mimi). Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: initialize only required templateDmitry Kasatkin2014-09-091-24/+4
| | | | | | | | | IMA uses only one template. This patch initializes only required template to avoid unnecessary memory allocations. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Reviewed-by: Roberto Sassu <roberto.sassu@polito.it> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: remove usage of filename parameterDmitry Kasatkin2014-09-092-14/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In all cases except ima_bprm_check() the filename was not defined and ima_d_path() was used to find the full path. Unfortunately, the bprm filename is a relative pathname (eg. ./<dir>/filename). ima_bprm_check() selects between bprm->interp and bprm->filename. The following dump demonstrates the differences between using filename and interp. bprm->filename filename: ./foo.sh, pathname: /root/bin/foo.sh filename: ./foo.sh, pathname: /bin/dash bprm->interp filename: ./foo.sh, pathname: /root/bin/foo.sh filename: /bin/sh, pathname: /bin/dash In both cases the pathnames are currently the same. This patch removes usage of filename and interp in favor of d_absolute_path. Changes v3: - 11 extra bytes for "deleted" not needed (Mimi) - purpose "replace relative bprm filename with full pathname" (Mimi) Changes v2: - use d_absolute_path() instead of d_path to work in chroot environments. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: remove unnecessary appraisal testDmitry Kasatkin2014-09-091-2/+0
| | | | | | | | | | | | | ima_get_action() sets the "action" flags based on policy. Before collecting, measuring, appraising, or auditing the file, the "action" flag is updated based on the cached iint->flags. This patch removes the subsequent unnecessary appraisal test in ima_appraise_measurement(). Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: add missing '__init' keywordsDmitry Kasatkin2014-09-093-5/+3
| | | | | | | | | Add missing keywords to the function definition to cleanup to discard initialization code. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Reviewed-by: Roberto Sassu <roberto.sassu@polito.it> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: remove unnecessary extra variableDmitry Kasatkin2014-09-091-4/+5
| | | | | | | | 'function' variable value can be changed instead of allocating extra '_func' variable. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: simplify conditional statement to improve performanceDmitry Kasatkin2014-09-091-4/+2
| | | | | | | | | | | Precede bit testing before string comparison makes code faster. Also refactor statement as a single line pointer assignment. Logic is following: we set 'xattr_ptr' to read xattr value when we will do appraisal or in any case when measurement template is other than 'ima'. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* integrity: remove declaration of non-existing functionsDmitry Kasatkin2014-09-091-9/+0
| | | | | | | | | | | | | Commit f381c27 "integrity: move ima inode integrity data management" (re)moved few functions but left their declarations in header files. This patch removes them and also removes duplicated declaration of integrity_iint_find(). Commit c7de7ad "ima: remove unused cleanup functions". This patch removes these definitions as well. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: pass 'opened' flag to identify newly created filesDmitry Kasatkin2014-09-093-12/+12
| | | | | | | | | | Empty files and missing xattrs do not guarantee that a file was just created. This patch passes FILE_CREATED flag to IMA to reliably identify new files. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> 3.14+
* ima: provide flag to identify new empty filesDmitry Kasatkin2014-09-082-7/+12
| | | | | | | | | | | | | | | | | | | On ima_file_free(), newly created empty files are not labeled with an initial security.ima value, because the iversion did not change. Commit dff6efc "fs: fix iversion handling" introduced a change in iversion behavior. To verify this change use the shell command: $ (exec >foo) $ getfattr -h -e hex -d -m security foo This patch defines the IMA_NEW_FILE flag. The flag is initially set, when IMA detects that a new file is created, and subsequently checked on the ima_file_free() hook to set the initial security.ima value. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> 3.14+
* ima: fix fallback to use new_sync_read()Dmitry Kasatkin2014-09-021-4/+4
| | | | | | | | | | | | | | | 3.16 commit aad4f8bb42af06371aa0e85bf0cd9d52c0494985 'switch simple generic_file_aio_read() users to ->read_iter()' replaced ->aio_read with ->read_iter in most of the file systems and introduced new_sync_read() as a replacement for do_sync_read(). Most of file systems set '->read' and ima_kernel_read is not affected. When ->read is not set, this patch adopts fallback call changes from the vfs_read. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org> 3.16+
* ima: prevent buffer overflow in ima_alloc_tfm()Dmitry Kasatkin2014-09-021-1/+4
| | | | | | | | | This patch fixes the case where the file's signature/hash xattr contains an invalid hash algorithm. Although we can not verify the xattr, we still need to measure the file. Use the default IMA hash algorithm. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: fix ima_alloc_atfm()Mimi Zohar2014-09-021-1/+4
| | | | | | | | | | | | | | | | | | | | | | | | The patch 3bcced39ea7d: "ima: use ahash API for file hash calculation" from Feb 26, 2014, leads to the following static checker warning: security/integrity/ima/ima_crypto.c:204 ima_alloc_atfm()          error: buffer overflow 'hash_algo_name' 17 <= 17 Unlike shash tfm memory, which is allocated on initialization, the ahash tfm memory allocation is deferred until needed. This patch fixes the case where ima_ahash_tfm has not yet been allocated and the file's signature/hash xattr contains an invalid hash algorithm. Although we can not verify the xattr, we still need to measure the file. Use the default IMA hash algorithm. Changelog: - set valid algo before testing tfm - based on Dmitry's comment Reported-by: Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com> Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com>
* ima: add support for measuring and appraising firmwareMimi Zohar2014-07-254-1/+28
| | | | | | | | | | | | | The "security: introduce kernel_fw_from_file hook" patch defined a new security hook to evaluate any loaded firmware that wasn't built into the kernel. This patch defines ima_fw_from_file(), which is called from the new security hook, to measure and/or appraise the loaded firmware's integrity. Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com> Signed-off-by: Kees Cook <keescook@chromium.org>
* ima: define '.ima' as a builtin 'trusted' keyringMimi Zohar2014-07-173-2/+30
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Require all keys added to the IMA keyring be signed by an existing trusted key on the system trusted keyring. Changelog v6: - remove ifdef CONFIG_IMA_TRUSTED_KEYRING in C code - Dmitry - update Kconfig dependency and help - select KEYS_DEBUG_PROC_KEYS - Dmitry Changelog v5: - Move integrity_init_keyring() to init_ima() - Dmitry - reset keyring[id] on failure - Dmitry Changelog v1: - don't link IMA trusted keyring to user keyring Changelog: - define stub integrity_init_keyring() function (reported-by Fengguang Wu) - differentiate between regular and trusted keyring names. - replace printk with pr_info (D. Kasatkin) - only make the IMA keyring a trusted keyring (reported-by D. Kastatkin) - define stub integrity_init_keyring() definition based on CONFIG_INTEGRITY_SIGNATURE, not CONFIG_INTEGRITY_ASYMMETRIC_KEYS. (reported-by Jim Davis) Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com> Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Acked-by: David Howells <dhowells@redhat.com>
* ima: provide double buffering for hash calculationDmitry Kasatkin2014-07-171-16/+49
| | | | | | | | | | | | | | | The asynchronous hash API allows initiating a hash calculation and then performing other tasks, while waiting for the hash calculation to complete. This patch introduces usage of double buffering for simultaneous hashing and reading of the next chunk of data from storage. Changes in v3: - better comments Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: introduce multi-page collect buffersDmitry Kasatkin2014-07-171-2/+96
| | | | | | | | | | | | | | | | | | | | | | Use of multiple-page collect buffers reduces: 1) the number of block IO requests 2) the number of asynchronous hash update requests Second is important for HW accelerated hashing, because significant amount of time is spent for preparation of hash update operation, which includes configuring acceleration HW, DMA engine, etc... Thus, HW accelerators are more efficient when working on large chunks of data. This patch introduces usage of multi-page collect buffers. Buffer size can be specified using 'ahash_bufsize' module parameter. Default buffer size is 4096 bytes. Changes in v3: - kernel parameter replaced with module parameter Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: use ahash API for file hash calculationDmitry Kasatkin2014-07-171-4/+183
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Async hash API allows the use of HW acceleration for hash calculation. It may give significant performance gain and/or reduce power consumption, which might be very beneficial for battery powered devices. This patch introduces hash calculation using ahash API. ahash performance depends on the data size and the particular HW. Depending on the specific system, shash performance may be better. This patch defines 'ahash_minsize' module parameter, which is used to define the minimal file size to use with ahash. If this minimum file size is not set or the file is smaller than defined by the parameter, shash will be used. Changes in v3: - kernel parameter replaced with module parameter - pr_crit replaced with pr_crit_ratelimited - more comment changes - Mimi Changes in v2: - ima_ahash_size became as ima_ahash - ahash pre-allocation moved out from __init code to be able to use ahash crypto modules. Ahash allocated once on the first use. - hash calculation falls back to shash if ahash allocation/calculation fails - complex initialization separated from variable declaration - improved comments Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* audit: fix dangling keywords in integrity ima message outputRichard Guy Briggs2014-07-172-4/+4
| | | | | | | | | Replace spaces in op keyword labels in log output since userspace audit tools can't parse orphaned keywords. Reported-by: Steve Grubb <sgrubb@redhat.com> Signed-off-by: Richard Guy Briggs <rgb@redhat.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: delay template descriptor lookup until useDmitry Kasatkin2014-07-171-1/+2
| | | | | | | | | | | process_measurement() always calls ima_template_desc_current(), including when an IMA policy has not been defined. This patch delays template descriptor lookup until action is determined. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: remove unnecessary i_mutex locking from ima_rdwr_violation_check()Dmitry Kasatkin2014-07-171-4/+0
| | | | | | | | | | | | | | | Before 2.6.39 inode->i_readcount was maintained by IMA. It was not atomic and protected using spinlock. For 2.6.39, i_readcount was converted to atomic and maintaining was moved VFS layer. Spinlock for some unclear reason was replaced by i_mutex. After analyzing the code, we came to conclusion that i_mutex locking is unnecessary, especially when an IMA policy has not been defined. This patch removes i_mutex locking from ima_rdwr_violation_check(). Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
* ima: introduce ima_kernel_read()Dmitry Kasatkin2014-06-121-1/+31
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit 8aac62706 "move exit_task_namespaces() outside of exit_notify" introduced the kernel opps since the kernel v3.10, which happens when Apparmor and IMA-appraisal are enabled at the same time. ---------------------------------------------------------------------- [ 106.750167] BUG: unable to handle kernel NULL pointer dereference at 0000000000000018 [ 106.750221] IP: [<ffffffff811ec7da>] our_mnt+0x1a/0x30 [ 106.750241] PGD 0 [ 106.750254] Oops: 0000 [#1] SMP [ 106.750272] Modules linked in: cuse parport_pc ppdev bnep rfcomm bluetooth rpcsec_gss_krb5 nfsd auth_rpcgss nfs_acl nfs lockd sunrpc fscache dm_crypt intel_rapl x86_pkg_temp_thermal intel_powerclamp kvm_intel snd_hda_codec_hdmi kvm crct10dif_pclmul crc32_pclmul ghash_clmulni_intel aesni_intel aes_x86_64 glue_helper lrw gf128mul ablk_helper cryptd snd_hda_codec_realtek dcdbas snd_hda_intel snd_hda_codec snd_hwdep snd_pcm snd_page_alloc snd_seq_midi snd_seq_midi_event snd_rawmidi psmouse snd_seq microcode serio_raw snd_timer snd_seq_device snd soundcore video lpc_ich coretemp mac_hid lp parport mei_me mei nbd hid_generic e1000e usbhid ahci ptp hid libahci pps_core [ 106.750658] CPU: 6 PID: 1394 Comm: mysqld Not tainted 3.13.0-rc7-kds+ #15 [ 106.750673] Hardware name: Dell Inc. OptiPlex 9010/0M9KCM, BIOS A08 09/19/2012 [ 106.750689] task: ffff8800de804920 ti: ffff880400fca000 task.ti: ffff880400fca000 [ 106.750704] RIP: 0010:[<ffffffff811ec7da>] [<ffffffff811ec7da>] our_mnt+0x1a/0x30 [ 106.750725] RSP: 0018:ffff880400fcba60 EFLAGS: 00010286 [ 106.750738] RAX: 0000000000000000 RBX: 0000000000000100 RCX: ffff8800d51523e7 [ 106.750764] RDX: ffffffffffffffea RSI: ffff880400fcba34 RDI: ffff880402d20020 [ 106.750791] RBP: ffff880400fcbae0 R08: 0000000000000000 R09: 0000000000000001 [ 106.750817] R10: 0000000000000000 R11: 0000000000000001 R12: ffff8800d5152300 [ 106.750844] R13: ffff8803eb8df510 R14: ffff880400fcbb28 R15: ffff8800d51523e7 [ 106.750871] FS: 0000000000000000(0000) GS:ffff88040d200000(0000) knlGS:0000000000000000 [ 106.750910] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 106.750935] CR2: 0000000000000018 CR3: 0000000001c0e000 CR4: 00000000001407e0 [ 106.750962] Stack: [ 106.750981] ffffffff813434eb ffff880400fcbb20 ffff880400fcbb18 0000000000000000 [ 106.751037] ffff8800de804920 ffffffff8101b9b9 0001800000000000 0000000000000100 [ 106.751093] 0000010000000000 0000000000000002 000000000000000e ffff8803eb8df500 [ 106.751149] Call Trace: [ 106.751172] [<ffffffff813434eb>] ? aa_path_name+0x2ab/0x430 [ 106.751199] [<ffffffff8101b9b9>] ? sched_clock+0x9/0x10 [ 106.751225] [<ffffffff8134a68d>] aa_path_perm+0x7d/0x170 [ 106.751250] [<ffffffff8101b945>] ? native_sched_clock+0x15/0x80 [ 106.751276] [<ffffffff8134aa73>] aa_file_perm+0x33/0x40 [ 106.751301] [<ffffffff81348c5e>] common_file_perm+0x8e/0xb0 [ 106.751327] [<ffffffff81348d78>] apparmor_file_permission+0x18/0x20 [ 106.751355] [<ffffffff8130c853>] security_file_permission+0x23/0xa0 [ 106.751382] [<ffffffff811c77a2>] rw_verify_area+0x52/0xe0 [ 106.751407] [<ffffffff811c789d>] vfs_read+0x6d/0x170 [ 106.751432] [<ffffffff811cda31>] kernel_read+0x41/0x60 [ 106.751457] [<ffffffff8134fd45>] ima_calc_file_hash+0x225/0x280 [ 106.751483] [<ffffffff8134fb52>] ? ima_calc_file_hash+0x32/0x280 [ 106.751509] [<ffffffff8135022d>] ima_collect_measurement+0x9d/0x160 [ 106.751536] [<ffffffff810b552d>] ? trace_hardirqs_on+0xd/0x10 [ 106.751562] [<ffffffff8134f07c>] ? ima_file_free+0x6c/0xd0 [ 106.751587] [<ffffffff81352824>] ima_update_xattr+0x34/0x60 [ 106.751612] [<ffffffff8134f0d0>] ima_file_free+0xc0/0xd0 [ 106.751637] [<ffffffff811c9635>] __fput+0xd5/0x300 [ 106.751662] [<ffffffff811c98ae>] ____fput+0xe/0x10 [ 106.751687] [<ffffffff81086774>] task_work_run+0xc4/0xe0 [ 106.751712] [<ffffffff81066fad>] do_exit+0x2bd/0xa90 [ 106.751738] [<ffffffff8173c958>] ? retint_swapgs+0x13/0x1b [ 106.751763] [<ffffffff8106780c>] do_group_exit+0x4c/0xc0 [ 106.751788] [<ffffffff81067894>] SyS_exit_group+0x14/0x20 [ 106.751814] [<ffffffff8174522d>] system_call_fastpath+0x1a/0x1f [ 106.751839] Code: c3 0f 1f 44 00 00 55 48 89 e5 e8 22 fe ff ff 5d c3 0f 1f 44 00 00 55 65 48 8b 04 25 c0 c9 00 00 48 8b 80 28 06 00 00 48 89 e5 5d <48> 8b 40 18 48 39 87 c0 00 00 00 0f 94 c0 c3 0f 1f 80 00 00 00 [ 106.752185] RIP [<ffffffff811ec7da>] our_mnt+0x1a/0x30 [ 106.752214] RSP <ffff880400fcba60> [ 106.752236] CR2: 0000000000000018 [ 106.752258] ---[ end trace 3c520748b4732721 ]--- ---------------------------------------------------------------------- The reason for the oops is that IMA-appraisal uses "kernel_read()" when file is closed. kernel_read() honors LSM security hook which calls Apparmor handler, which uses current->nsproxy->mnt_ns. The 'guilty' commit changed the order of cleanup code so that nsproxy->mnt_ns was not already available for Apparmor. Discussion about the issue with Al Viro and Eric W. Biederman suggested that kernel_read() is too high-level for IMA. Another issue, except security checking, that was identified is mandatory locking. kernel_read honors it as well and it might prevent IMA from calculating necessary hash. It was suggested to use simplified version of the function without security and locking checks. This patch introduces special version ima_kernel_read(), which skips security and mandatory locking checking. It prevents the kernel oops to happen. Signed-off-by: Dmitry Kasatkin <d.kasatkin@samsung.com> Suggested-by: Eric W. Biederman <ebiederm@xmission.com> Signed-off-by: Mimi Zohar <zohar@linux.vnet.ibm.com> Cc: <stable@vger.kernel.org>
generated by cgit v1.2.3 (git 2.25.1) at 2024-11-10 17:46:15 +0000