From 79d719749d23234e9b725098aa49133f3ef7299d Mon Sep 17 00:00:00 2001 From: Aristeu Rozanski Date: Mon, 21 Apr 2014 12:13:03 -0400 Subject: device_cgroup: rework device access check and exception checking Whenever a device file is opened and checked against current device cgroup rules, it uses the same function (may_access()) as when a new exception rule is added by writing devices.{allow,deny}. And in both cases, the algorithm is the same, doesn't matter the behavior. First problem is having device access to be considered the same as rule checking. Consider the following structure: A (default behavior: allow, exceptions disallow access) \ B (default behavior: allow, exceptions disallow access) A new exception is added to B by writing devices.deny: c 12:34 rw When checking if that exception is allowed in may_access(): if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) { if (behavior == DEVCG_DEFAULT_ALLOW) { /* the exception will deny access to certain devices */ return true; Which is ok, since B is not getting more privileges than A, it doesn't matter and the rule is accepted Now, consider it's a device file open check and the process belongs to cgroup B. The access will be generated as: behavior: allow exception: c 12:34 rw The very same chunk of code will allow it, even if there's an explicit exception telling to do otherwise. A simple test case: # mkdir new_group # cd new_group # echo $$ >tasks # echo "c 1:3 w" >devices.deny # echo >/dev/null # echo $? 0 This is a serious bug and was introduced on c39a2a3018f8 devcg: prepare may_access() for hierarchy support To solve this problem, the device file open function was split from the new exception check. Second problem is how exceptions are processed by may_access(). The first part of the said function tries to match fully with an existing exception: list_for_each_entry_rcu(ex, &dev_cgroup->exceptions, list) { if ((refex->type & DEV_BLOCK) && !(ex->type & DEV_BLOCK)) continue; if ((refex->type & DEV_CHAR) && !(ex->type & DEV_CHAR)) continue; if (ex->major != ~0 && ex->major != refex->major) continue; if (ex->minor != ~0 && ex->minor != refex->minor) continue; if (refex->access & (~ex->access)) continue; match = true; break; } That means the new exception should be contained into an existing one to be considered a match: New exception Existing match? notes b 12:34 rwm b 12:34 rwm yes b 12:34 r b *:34 rw yes b 12:34 rw b 12:34 w no extra "r" b *:34 rw b 12:34 rw no too broad "*" b *:34 rw b *:34 rwm yes Which is fine in some cases. Consider: A (default behavior: deny, exceptions allow access) \ B (default behavior: deny, exceptions allow access) In this case the full match makes sense, the new exception cannot add more access than the parent allows But this doesn't always work, consider: A (default behavior: allow, exceptions disallow access) \ B (default behavior: deny, exceptions allow access) In this case, a new exception in B shouldn't match any of the exceptions in A, after all you can't allow something that was forbidden by A. But consider this scenario: New exception Existing in A match? outcome b 12:34 rw b 12:34 r no exception is accepted Because the new exception has "w" as extra, it doesn't match, so it'll be added to B's exception list. The same problem can happen during a file access check. Consider a cgroup with allow as default behavior: Access Exception match? b 12:34 rw b 12:34 r no In this case, the access didn't match any of the exceptions in the cgroup, which is required since exceptions will disallow access. To solve this problem, two new functions were created to match an exception either fully or partially. In the example above, a partial check will be performed and it'll produce a match since at least "b 12:34 r" from "b 12:34 rw" access matches. Cc: cgroups@vger.kernel.org Cc: Tejun Heo Cc: Serge Hallyn Cc: Li Zefan Cc: stable@vger.kernel.org Signed-off-by: Aristeu Rozanski Signed-off-by: Tejun Heo --- security/device_cgroup.c | 162 +++++++++++++++++++++++++++++++++++------------ 1 file changed, 122 insertions(+), 40 deletions(-) (limited to 'security') diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 8365909f5f8..b9048dc46b1 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -306,57 +306,139 @@ static int devcgroup_seq_show(struct seq_file *m, void *v) } /** - * may_access - verifies if a new exception is part of what is allowed - * by a dev cgroup based on the default policy + - * exceptions. This is used to make sure a child cgroup - * won't have more privileges than its parent or to - * verify if a certain access is allowed. - * @dev_cgroup: dev cgroup to be tested against - * @refex: new exception - * @behavior: behavior of the exception + * match_exception - iterates the exception list trying to match a rule + * based on type, major, minor and access type. It is + * considered a match if an exception is found that + * will contain the entire range of provided parameters. + * @exceptions: list of exceptions + * @type: device type (DEV_BLOCK or DEV_CHAR) + * @major: device file major number, ~0 to match all + * @minor: device file minor number, ~0 to match all + * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD) + * + * returns: true in case it matches an exception completely */ -static bool may_access(struct dev_cgroup *dev_cgroup, - struct dev_exception_item *refex, - enum devcg_behavior behavior) +static bool match_exception(struct list_head *exceptions, short type, + u32 major, u32 minor, short access) { struct dev_exception_item *ex; - bool match = false; - rcu_lockdep_assert(rcu_read_lock_held() || - lockdep_is_held(&devcgroup_mutex), - "device_cgroup::may_access() called without proper synchronization"); + list_for_each_entry_rcu(ex, exceptions, list) { + if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK)) + continue; + if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR)) + continue; + if (ex->major != ~0 && ex->major != major) + continue; + if (ex->minor != ~0 && ex->minor != minor) + continue; + /* provided access cannot have more than the exception rule */ + if (access & (~ex->access)) + continue; + return true; + } + return false; +} + +/** + * match_exception_partial - iterates the exception list trying to match a rule + * based on type, major, minor and access type. It is + * considered a match if an exception's range is + * found to contain *any* of the devices specified by + * provided parameters. This is used to make sure no + * extra access is being granted that is forbidden by + * any of the exception list. + * @exceptions: list of exceptions + * @type: device type (DEV_BLOCK or DEV_CHAR) + * @major: device file major number, ~0 to match all + * @minor: device file minor number, ~0 to match all + * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD) + * + * returns: true in case the provided range mat matches an exception completely + */ +static bool match_exception_partial(struct list_head *exceptions, short type, + u32 major, u32 minor, short access) +{ + struct dev_exception_item *ex; - list_for_each_entry_rcu(ex, &dev_cgroup->exceptions, list) { - if ((refex->type & DEV_BLOCK) && !(ex->type & DEV_BLOCK)) + list_for_each_entry_rcu(ex, exceptions, list) { + if ((type & DEV_BLOCK) && !(ex->type & DEV_BLOCK)) continue; - if ((refex->type & DEV_CHAR) && !(ex->type & DEV_CHAR)) + if ((type & DEV_CHAR) && !(ex->type & DEV_CHAR)) continue; - if (ex->major != ~0 && ex->major != refex->major) + /* + * We must be sure that both the exception and the provided + * range aren't masking all devices + */ + if (ex->major != ~0 && major != ~0 && ex->major != major) continue; - if (ex->minor != ~0 && ex->minor != refex->minor) + if (ex->minor != ~0 && minor != ~0 && ex->minor != minor) continue; - if (refex->access & (~ex->access)) + /* + * In order to make sure the provided range isn't matching + * an exception, all its access bits shouldn't match the + * exception's access bits + */ + if (!(access & ex->access)) continue; - match = true; - break; + return true; } + return false; +} + +/** + * verify_new_ex - verifies if a new exception is part of what is allowed + * by a dev cgroup based on the default policy + + * exceptions. This is used to make sure a child cgroup + * won't have more privileges than its parent + * @dev_cgroup: dev cgroup to be tested against + * @refex: new exception + * @behavior: behavior of the exception's dev_cgroup + */ +static bool verify_new_ex(struct dev_cgroup *dev_cgroup, + struct dev_exception_item *refex, + enum devcg_behavior behavior) +{ + bool match = false; + + rcu_lockdep_assert(rcu_read_lock_held() || + lockdep_is_held(&devcgroup_mutex), + "device_cgroup:verify_new_ex called without proper synchronization"); if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) { if (behavior == DEVCG_DEFAULT_ALLOW) { - /* the exception will deny access to certain devices */ + /* + * new exception in the child doesn't matter, only + * adding extra restrictions + */ return true; } else { - /* the exception will allow access to certain devices */ + /* + * new exception in the child will add more devices + * that can be acessed, so it can't match any of + * parent's exceptions, even slightly + */ + match = match_exception_partial(&dev_cgroup->exceptions, + refex->type, + refex->major, + refex->minor, + refex->access); + if (match) - /* - * a new exception allowing access shouldn't - * match an parent's exception - */ return false; return true; } } else { - /* only behavior == DEVCG_DEFAULT_DENY allowed here */ + /* + * Only behavior == DEVCG_DEFAULT_DENY allowed here, therefore + * the new exception will add access to more devices and must + * be contained completely in an parent's exception to be + * allowed + */ + match = match_exception(&dev_cgroup->exceptions, refex->type, + refex->major, refex->minor, + refex->access); + if (match) /* parent has an exception that matches the proposed */ return true; @@ -378,7 +460,7 @@ static int parent_has_perm(struct dev_cgroup *childcg, if (!parent) return 1; - return may_access(parent, ex, childcg->behavior); + return verify_new_ex(parent, ex, childcg->behavior); } /** @@ -704,18 +786,18 @@ static int __devcgroup_check_permission(short type, u32 major, u32 minor, short access) { struct dev_cgroup *dev_cgroup; - struct dev_exception_item ex; - int rc; - - memset(&ex, 0, sizeof(ex)); - ex.type = type; - ex.major = major; - ex.minor = minor; - ex.access = access; + bool rc; rcu_read_lock(); dev_cgroup = task_devcgroup(current); - rc = may_access(dev_cgroup, &ex, dev_cgroup->behavior); + if (dev_cgroup->behavior == DEVCG_DEFAULT_ALLOW) + /* Can't match any of the exceptions, even partially */ + rc = !match_exception_partial(&dev_cgroup->exceptions, + type, major, minor, access); + else + /* Need to match completely one exception to be allowed */ + rc = match_exception(&dev_cgroup->exceptions, type, major, + minor, access); rcu_read_unlock(); if (!rc) -- cgit v1.2.3-70-g09d2 From f5f3cf6f7e49b9529fc00a2c4629fa92cf2755fe Mon Sep 17 00:00:00 2001 From: Aristeu Rozanski Date: Thu, 24 Apr 2014 15:33:21 -0400 Subject: device_cgroup: fix the comment format for recently added functions Moving more extensive explanations to the end of the comment. Cc: Li Zefan Signed-off-by: Aristeu Rozanski Acked-by: Serge Hallyn Signed-off-by: Tejun Heo --- security/device_cgroup.c | 33 ++++++++++++++++----------------- 1 file changed, 16 insertions(+), 17 deletions(-) (limited to 'security') diff --git a/security/device_cgroup.c b/security/device_cgroup.c index b9048dc46b1..6b1266dd92b 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -306,17 +306,17 @@ static int devcgroup_seq_show(struct seq_file *m, void *v) } /** - * match_exception - iterates the exception list trying to match a rule - * based on type, major, minor and access type. It is - * considered a match if an exception is found that - * will contain the entire range of provided parameters. + * match_exception - iterates the exception list trying to find a complete match * @exceptions: list of exceptions * @type: device type (DEV_BLOCK or DEV_CHAR) * @major: device file major number, ~0 to match all * @minor: device file minor number, ~0 to match all * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD) * - * returns: true in case it matches an exception completely + * It is considered a complete match if an exception is found that will + * contain the entire range of provided parameters. + * + * Return: true in case it matches an exception completely */ static bool match_exception(struct list_head *exceptions, short type, u32 major, u32 minor, short access) @@ -341,20 +341,19 @@ static bool match_exception(struct list_head *exceptions, short type, } /** - * match_exception_partial - iterates the exception list trying to match a rule - * based on type, major, minor and access type. It is - * considered a match if an exception's range is - * found to contain *any* of the devices specified by - * provided parameters. This is used to make sure no - * extra access is being granted that is forbidden by - * any of the exception list. + * match_exception_partial - iterates the exception list trying to find a partial match * @exceptions: list of exceptions * @type: device type (DEV_BLOCK or DEV_CHAR) * @major: device file major number, ~0 to match all * @minor: device file minor number, ~0 to match all * @access: permission mask (ACC_READ, ACC_WRITE, ACC_MKNOD) * - * returns: true in case the provided range mat matches an exception completely + * It is considered a partial match if an exception's range is found to + * contain *any* of the devices specified by provided parameters. This is + * used to make sure no extra access is being granted that is forbidden by + * any of the exception list. + * + * Return: true in case the provided range mat matches an exception completely */ static bool match_exception_partial(struct list_head *exceptions, short type, u32 major, u32 minor, short access) @@ -387,13 +386,13 @@ static bool match_exception_partial(struct list_head *exceptions, short type, } /** - * verify_new_ex - verifies if a new exception is part of what is allowed - * by a dev cgroup based on the default policy + - * exceptions. This is used to make sure a child cgroup - * won't have more privileges than its parent + * verify_new_ex - verifies if a new exception is allowed by parent cgroup's permissions * @dev_cgroup: dev cgroup to be tested against * @refex: new exception * @behavior: behavior of the exception's dev_cgroup + * + * This is used to make sure a child cgroup won't have more privileges + * than its parent */ static bool verify_new_ex(struct dev_cgroup *dev_cgroup, struct dev_exception_item *refex, -- cgit v1.2.3-70-g09d2 From d2c2b11cfa134f4fbdcc34088824da26a084d8de Mon Sep 17 00:00:00 2001 From: Aristeu Rozanski Date: Mon, 5 May 2014 11:18:59 -0400 Subject: device_cgroup: check if exception removal is allowed [PATCH v3 1/2] device_cgroup: check if exception removal is allowed When the device cgroup hierarchy was introduced in bd2953ebbb53 - devcg: propagate local changes down the hierarchy a specific case was overlooked. Consider the hierarchy bellow: A default policy: ALLOW, exceptions will deny access \ B default policy: ALLOW, exceptions will deny access There's no need to verify when an new exception is added to B because in this case exceptions will deny access to further devices, which is always fine. Hierarchy in device cgroup only makes sure B won't have more access than A. But when an exception is removed (by writing devices.allow), it isn't checked if the user is in fact removing an inherited exception from A, thus giving more access to B. Example: # echo 'a' >A/devices.allow # echo 'c 1:3 rw' >A/devices.deny # echo $$ >A/B/tasks # echo >/dev/null -bash: /dev/null: Operation not permitted # echo 'c 1:3 w' >A/B/devices.allow # echo >/dev/null # This shouldn't be allowed and this patch fixes it by making sure to never allow exceptions in this case to be removed if the exception is partially or fully present on the parent. v3: missing '*' in function description v2: improved log message and formatting fixes Cc: cgroups@vger.kernel.org Cc: Li Zefan Cc: stable@vger.kernel.org Signed-off-by: Aristeu Rozanski Acked-by: Serge Hallyn Signed-off-by: Tejun Heo --- security/device_cgroup.c | 41 ++++++++++++++++++++++++++++++++++++++--- 1 file changed, 38 insertions(+), 3 deletions(-) (limited to 'security') diff --git a/security/device_cgroup.c b/security/device_cgroup.c index 6b1266dd92b..9134dbf70d3 100644 --- a/security/device_cgroup.c +++ b/security/device_cgroup.c @@ -462,6 +462,37 @@ static int parent_has_perm(struct dev_cgroup *childcg, return verify_new_ex(parent, ex, childcg->behavior); } +/** + * parent_allows_removal - verify if it's ok to remove an exception + * @childcg: child cgroup from where the exception will be removed + * @ex: exception being removed + * + * When removing an exception in cgroups with default ALLOW policy, it must + * be checked if removing it will give the child cgroup more access than the + * parent. + * + * Return: true if it's ok to remove exception, false otherwise + */ +static bool parent_allows_removal(struct dev_cgroup *childcg, + struct dev_exception_item *ex) +{ + struct dev_cgroup *parent = css_to_devcgroup(css_parent(&childcg->css)); + + if (!parent) + return true; + + /* It's always allowed to remove access to devices */ + if (childcg->behavior == DEVCG_DEFAULT_DENY) + return true; + + /* + * Make sure you're not removing part or a whole exception existing in + * the parent cgroup + */ + return !match_exception_partial(&parent->exceptions, ex->type, + ex->major, ex->minor, ex->access); +} + /** * may_allow_all - checks if it's possible to change the behavior to * allow based on parent's rules. @@ -697,17 +728,21 @@ static int devcgroup_update_access(struct dev_cgroup *devcgroup, switch (filetype) { case DEVCG_ALLOW: - if (!parent_has_perm(devcgroup, &ex)) - return -EPERM; /* * If the default policy is to allow by default, try to remove * an matching exception instead. And be silent about it: we * don't want to break compatibility */ if (devcgroup->behavior == DEVCG_DEFAULT_ALLOW) { + /* Check if the parent allows removing it first */ + if (!parent_allows_removal(devcgroup, &ex)) + return -EPERM; dev_exception_rm(devcgroup, &ex); - return 0; + break; } + + if (!parent_has_perm(devcgroup, &ex)) + return -EPERM; rc = dev_exception_add(devcgroup, &ex); break; case DEVCG_DENY: -- cgit v1.2.3-70-g09d2 From 39f1f78d53b9bcbca91967380c5f0f2305a5c55f Mon Sep 17 00:00:00 2001 From: Al Viro Date: Tue, 6 May 2014 14:02:53 -0400 Subject: nick kvfree() from apparmor too many places open-code it Signed-off-by: Al Viro --- include/linux/mm.h | 2 ++ mm/util.c | 10 ++++++++++ security/apparmor/include/apparmor.h | 1 - security/apparmor/lib.c | 14 -------------- 4 files changed, 12 insertions(+), 15 deletions(-) (limited to 'security') diff --git a/include/linux/mm.h b/include/linux/mm.h index bf9811e1321..d6777060449 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -370,6 +370,8 @@ static inline int is_vmalloc_or_module_addr(const void *x) } #endif +extern void kvfree(const void *addr); + static inline void compound_lock(struct page *page) { #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/mm/util.c b/mm/util.c index f380af7ea77..d5ea733c508 100644 --- a/mm/util.c +++ b/mm/util.c @@ -10,6 +10,7 @@ #include #include #include +#include #include @@ -387,6 +388,15 @@ unsigned long vm_mmap(struct file *file, unsigned long addr, } EXPORT_SYMBOL(vm_mmap); +void kvfree(const void *addr) +{ + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); +} +EXPORT_SYMBOL(kvfree); + struct address_space *page_mapping(struct page *page) { struct address_space *mapping = page->mapping; diff --git a/security/apparmor/include/apparmor.h b/security/apparmor/include/apparmor.h index 8fb1488a3cd..97130f88838 100644 --- a/security/apparmor/include/apparmor.h +++ b/security/apparmor/include/apparmor.h @@ -66,7 +66,6 @@ extern int apparmor_initialized __initdata; char *aa_split_fqname(char *args, char **ns_name); void aa_info_message(const char *str); void *__aa_kvmalloc(size_t size, gfp_t flags); -void kvfree(void *buffer); static inline void *kvmalloc(size_t size) { diff --git a/security/apparmor/lib.c b/security/apparmor/lib.c index 69689922c49..c1827e06845 100644 --- a/security/apparmor/lib.c +++ b/security/apparmor/lib.c @@ -104,17 +104,3 @@ void *__aa_kvmalloc(size_t size, gfp_t flags) } return buffer; } - -/** - * kvfree - free an allocation do by kvmalloc - * @buffer: buffer to free (MAYBE_NULL) - * - * Free a buffer allocated by kvmalloc - */ -void kvfree(void *buffer) -{ - if (is_vmalloc_addr(buffer)) - vfree(buffer); - else - kfree(buffer); -} -- cgit v1.2.3-70-g09d2