From 3486740a4f32a6a466f5ac931654d154790ba648 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Wed, 23 Mar 2011 16:43:17 -0700 Subject: userns: security: make capabilities relative to the user namespace - Introduce ns_capable to test for a capability in a non-default user namespace. - Teach cap_capable to handle capabilities in a non-default user namespace. The motivation is to get to the unprivileged creation of new namespaces. It looks like this gets us 90% of the way there, with only potential uid confusion issues left. I still need to handle getting all caps after creation but otherwise I think I have a good starter patch that achieves all of your goals. Changelog: 11/05/2010: [serge] add apparmor 12/14/2010: [serge] fix capabilities to created user namespaces Without this, if user serge creates a user_ns, he won't have capabilities to the user_ns he created. THis is because we were first checking whether his effective caps had the caps he needed and returning -EPERM if not, and THEN checking whether he was the creator. Reverse those checks. 12/16/2010: [serge] security_real_capable needs ns argument in !security case 01/11/2011: [serge] add task_ns_capable helper 01/11/2011: [serge] add nsown_capable() helper per Bastian Blank suggestion 02/16/2011: [serge] fix a logic bug: the root user is always creator of init_user_ns, but should not always have capabilities to it! Fix the check in cap_capable(). 02/21/2011: Add the required user_ns parameter to security_capable, fixing a compile failure. 02/23/2011: Convert some macros to functions as per akpm comments. Some couldn't be converted because we can't easily forward-declare them (they are inline if !SECURITY, extern if SECURITY). Add a current_user_ns function so we can use it in capability.h without #including cred.h. Move all forward declarations together to the top of the #ifdef __KERNEL__ section, and use kernel-doc format. 02/23/2011: Per dhowells, clean up comment in cap_capable(). 02/23/2011: Per akpm, remove unreachable 'return -EPERM' in cap_capable. (Original written and signed off by Eric; latest, modified version acked by him) [akpm@linux-foundation.org: fix build] [akpm@linux-foundation.org: export current_user_ns() for ecryptfs] [serge.hallyn@canonical.com: remove unneeded extra argument in selinux's task_has_capability] Signed-off-by: Eric W. Biederman Signed-off-by: Serge E. Hallyn Acked-by: "Eric W. Biederman" Acked-by: Daniel Lezcano Acked-by: David Howells Cc: James Morris Signed-off-by: Serge E. Hallyn Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/security.h | 28 +++++++++++++++++----------- 1 file changed, 17 insertions(+), 11 deletions(-) (limited to 'include/linux/security.h') diff --git a/include/linux/security.h b/include/linux/security.h index 56cac520d01..ca02f171673 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -47,13 +47,14 @@ struct ctl_table; struct audit_krule; +struct user_namespace; /* * These functions are in security/capability.c and are used * as the default capabilities functions */ extern int cap_capable(struct task_struct *tsk, const struct cred *cred, - int cap, int audit); + struct user_namespace *ns, int cap, int audit); extern int cap_settime(const struct timespec *ts, const struct timezone *tz); extern int cap_ptrace_access_check(struct task_struct *child, unsigned int mode); extern int cap_ptrace_traceme(struct task_struct *parent); @@ -1262,6 +1263,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * credentials. * @tsk contains the task_struct for the process. * @cred contains the credentials to use. + * @ns contains the user namespace we want the capability in * @cap contains the capability . * @audit: Whether to write an audit message or not * Return 0 if the capability is granted for @tsk. @@ -1384,7 +1386,7 @@ struct security_operations { const kernel_cap_t *inheritable, const kernel_cap_t *permitted); int (*capable) (struct task_struct *tsk, const struct cred *cred, - int cap, int audit); + struct user_namespace *ns, int cap, int audit); int (*quotactl) (int cmds, int type, int id, struct super_block *sb); int (*quota_on) (struct dentry *dentry); int (*syslog) (int type); @@ -1665,9 +1667,12 @@ int security_capset(struct cred *new, const struct cred *old, const kernel_cap_t *effective, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); -int security_capable(const struct cred *cred, int cap); -int security_real_capable(struct task_struct *tsk, int cap); -int security_real_capable_noaudit(struct task_struct *tsk, int cap); +int security_capable(struct user_namespace *ns, const struct cred *cred, + int cap); +int security_real_capable(struct task_struct *tsk, struct user_namespace *ns, + int cap); +int security_real_capable_noaudit(struct task_struct *tsk, + struct user_namespace *ns, int cap); int security_quotactl(int cmds, int type, int id, struct super_block *sb); int security_quota_on(struct dentry *dentry); int security_syslog(int type); @@ -1860,28 +1865,29 @@ static inline int security_capset(struct cred *new, return cap_capset(new, old, effective, inheritable, permitted); } -static inline int security_capable(const struct cred *cred, int cap) +static inline int security_capable(struct user_namespace *ns, + const struct cred *cred, int cap) { - return cap_capable(current, cred, cap, SECURITY_CAP_AUDIT); + return cap_capable(current, cred, ns, cap, SECURITY_CAP_AUDIT); } -static inline int security_real_capable(struct task_struct *tsk, int cap) +static inline int security_real_capable(struct task_struct *tsk, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); - ret = cap_capable(tsk, __task_cred(tsk), cap, SECURITY_CAP_AUDIT); + ret = cap_capable(tsk, __task_cred(tsk), ns, cap, SECURITY_CAP_AUDIT); rcu_read_unlock(); return ret; } static inline -int security_real_capable_noaudit(struct task_struct *tsk, int cap) +int security_real_capable_noaudit(struct task_struct *tsk, struct user_namespace *ns, int cap) { int ret; rcu_read_lock(); - ret = cap_capable(tsk, __task_cred(tsk), cap, + ret = cap_capable(tsk, __task_cred(tsk), ns, cap, SECURITY_CAP_NOAUDIT); rcu_read_unlock(); return ret; -- cgit v1.2.3-70-g09d2 From 8c9e80ed276fc4b9c9fadf29d8bf6b3576112f1a Mon Sep 17 00:00:00 2001 From: Andi Kleen Date: Thu, 21 Apr 2011 17:23:19 -0700 Subject: SECURITY: Move exec_permission RCU checks into security modules Right now all RCU walks fall back to reference walk when CONFIG_SECURITY is enabled, even though just the standard capability module is active. This is because security_inode_exec_permission unconditionally fails RCU walks. Move this decision to the low level security module. This requires passing the RCU flags down the security hook. This way at least the capability module and a few easy cases in selinux/smack work with RCU walks with CONFIG_SECURITY=y Signed-off-by: Andi Kleen Acked-by: Eric Paris Signed-off-by: Linus Torvalds --- include/linux/security.h | 2 +- security/capability.c | 2 +- security/security.c | 6 ++---- security/selinux/hooks.c | 6 +++++- security/smack/smack_lsm.c | 6 +++++- 5 files changed, 14 insertions(+), 8 deletions(-) (limited to 'include/linux/security.h') diff --git a/include/linux/security.h b/include/linux/security.h index ca02f171673..8ce59ef3e5a 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1456,7 +1456,7 @@ struct security_operations { struct inode *new_dir, struct dentry *new_dentry); int (*inode_readlink) (struct dentry *dentry); int (*inode_follow_link) (struct dentry *dentry, struct nameidata *nd); - int (*inode_permission) (struct inode *inode, int mask); + int (*inode_permission) (struct inode *inode, int mask, unsigned flags); int (*inode_setattr) (struct dentry *dentry, struct iattr *attr); int (*inode_getattr) (struct vfsmount *mnt, struct dentry *dentry); int (*inode_setxattr) (struct dentry *dentry, const char *name, diff --git a/security/capability.c b/security/capability.c index 2984ea4f776..bbb51156261 100644 --- a/security/capability.c +++ b/security/capability.c @@ -181,7 +181,7 @@ static int cap_inode_follow_link(struct dentry *dentry, return 0; } -static int cap_inode_permission(struct inode *inode, int mask) +static int cap_inode_permission(struct inode *inode, int mask, unsigned flags) { return 0; } diff --git a/security/security.c b/security/security.c index 101142369db..4ba6d4cc061 100644 --- a/security/security.c +++ b/security/security.c @@ -518,16 +518,14 @@ int security_inode_permission(struct inode *inode, int mask) { if (unlikely(IS_PRIVATE(inode))) return 0; - return security_ops->inode_permission(inode, mask); + return security_ops->inode_permission(inode, mask, 0); } int security_inode_exec_permission(struct inode *inode, unsigned int flags) { if (unlikely(IS_PRIVATE(inode))) return 0; - if (flags) - return -ECHILD; - return security_ops->inode_permission(inode, MAY_EXEC); + return security_ops->inode_permission(inode, MAY_EXEC, flags); } int security_inode_setattr(struct dentry *dentry, struct iattr *attr) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index f9c3764e485..a73f4e46377 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -2635,7 +2635,7 @@ static int selinux_inode_follow_link(struct dentry *dentry, struct nameidata *na return dentry_has_perm(cred, NULL, dentry, FILE__READ); } -static int selinux_inode_permission(struct inode *inode, int mask) +static int selinux_inode_permission(struct inode *inode, int mask, unsigned flags) { const struct cred *cred = current_cred(); struct common_audit_data ad; @@ -2649,6 +2649,10 @@ static int selinux_inode_permission(struct inode *inode, int mask) if (!mask) return 0; + /* May be droppable after audit */ + if (flags & IPERM_FLAG_RCU) + return -ECHILD; + COMMON_AUDIT_DATA_INIT(&ad, FS); ad.u.fs.inode = inode; diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index c6f8fcadae0..400a5d5cde6 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -686,7 +686,7 @@ static int smack_inode_rename(struct inode *old_inode, * * Returns 0 if access is permitted, -EACCES otherwise */ -static int smack_inode_permission(struct inode *inode, int mask) +static int smack_inode_permission(struct inode *inode, int mask, unsigned flags) { struct smk_audit_info ad; @@ -696,6 +696,10 @@ static int smack_inode_permission(struct inode *inode, int mask) */ if (mask == 0) return 0; + + /* May be droppable after audit */ + if (flags & IPERM_FLAG_RCU) + return -ECHILD; smk_ad_init(&ad, __func__, LSM_AUDIT_DATA_FS); smk_ad_setfield_u_fs_inode(&ad, inode); return smk_curacc(smk_of_inode(inode), mask, &ad); -- cgit v1.2.3-70-g09d2