From 3cf29931453215536916d0c4da953fce1911ced3 Mon Sep 17 00:00:00 2001 From: Tetsuo Handa Date: Fri, 14 Jul 2017 19:38:36 +0900 Subject: LSM: Remove security_task_create() hook. Since commit a79be238600d1a03 ("selinux: Use task_alloc hook rather than task_create hook") changed to use task_alloc hook, task_create hook is no longer used. Signed-off-by: Tetsuo Handa Signed-off-by: James Morris --- include/linux/security.h | 6 ------ 1 file changed, 6 deletions(-) (limited to 'include/linux/security.h') diff --git a/include/linux/security.h b/include/linux/security.h index b6ea1dc9cc9d..458e24bea2d4 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -318,7 +318,6 @@ int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig); int security_file_receive(struct file *file); int security_file_open(struct file *file, const struct cred *cred); -int security_task_create(unsigned long clone_flags); int security_task_alloc(struct task_struct *task, unsigned long clone_flags); void security_task_free(struct task_struct *task); int security_cred_alloc_blank(struct cred *cred, gfp_t gfp); @@ -885,11 +884,6 @@ static inline int security_file_open(struct file *file, return 0; } -static inline int security_task_create(unsigned long clone_flags) -{ - return 0; -} - static inline int security_task_alloc(struct task_struct *task, unsigned long clone_flags) { -- cgit v1.2.3 From 46d98eb4e1d2bc225f661879e0e157a952107598 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Jul 2017 15:25:27 -0700 Subject: commoncap: Refactor to remove bprm_secureexec hook The commoncap implementation of the bprm_secureexec hook is the only LSM that depends on the final call to its bprm_set_creds hook (since it may be called for multiple files, it ignores bprm->called_set_creds). As a result, it cannot safely _clear_ bprm->secureexec since other LSMs may have set it. Instead, remove the bprm_secureexec hook by introducing a new flag to bprm specific to commoncap: cap_elevated. This is similar to cap_effective, but that is used for a specific subset of elevated privileges, and exists solely to track state from bprm_set_creds to bprm_secureexec. As such, it will be removed in the next patch. Here, set the new bprm->cap_elevated flag when setuid/setgid has happened from bprm_fill_uid() or fscapabilities have been prepared. This temporarily moves the bprm_secureexec hook to a static inline. The helper will be removed in the next patch; this makes the step easier to review and bisect, since this does not introduce any changes to inputs nor outputs to the "elevated privileges" calculation. The new flag is merged with the bprm->secureexec flag in setup_new_exec() since this marks the end of any further prepare_binprm() calls. Cc: Andy Lutomirski Signed-off-by: Kees Cook Reviewed-by: Andy Lutomirski Acked-by: James Morris Acked-by: Serge Hallyn --- fs/exec.c | 7 +++++++ include/linux/binfmts.h | 7 +++++++ include/linux/security.h | 3 +-- security/commoncap.c | 12 ++++++++---- 4 files changed, 23 insertions(+), 6 deletions(-) (limited to 'include/linux/security.h') diff --git a/fs/exec.c b/fs/exec.c index 0f361115c88f..1536bc4502cc 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1345,6 +1345,13 @@ void setup_new_exec(struct linux_binprm * bprm) { bprm->secureexec |= security_bprm_secureexec(bprm); + /* + * Once here, prepare_binrpm() will not be called any more, so + * the final state of setuid/setgid/fscaps can be merged into the + * secureexec flag. + */ + bprm->secureexec |= bprm->cap_elevated; + arch_pick_mmap_layout(current->mm); current->sas_ss_sp = current->sas_ss_size = 0; diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 16838ba7ee75..213c61fa3780 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -34,6 +34,13 @@ struct linux_binprm { cap_effective:1,/* true if has elevated effective capabilities, * false if not; except for init which inherits * its parent's caps anyway */ + /* + * True if most recent call to the commoncaps bprm_set_creds + * hook (due to multiple prepare_binprm() calls from the + * binfmt_script/misc handlers) resulted in elevated + * privileges. + */ + cap_elevated:1, /* * Set by bprm_set_creds hook to indicate a privilege-gaining * exec has happened. Used to sanitize execution environment diff --git a/include/linux/security.h b/include/linux/security.h index b6ea1dc9cc9d..f89832ccdf55 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -85,7 +85,6 @@ extern int cap_capset(struct cred *new, const struct cred *old, const kernel_cap_t *inheritable, const kernel_cap_t *permitted); extern int cap_bprm_set_creds(struct linux_binprm *bprm); -extern int cap_bprm_secureexec(struct linux_binprm *bprm); extern int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags); extern int cap_inode_removexattr(struct dentry *dentry, const char *name); @@ -543,7 +542,7 @@ static inline void security_bprm_committed_creds(struct linux_binprm *bprm) static inline int security_bprm_secureexec(struct linux_binprm *bprm) { - return cap_bprm_secureexec(bprm); + return 0; } static inline int security_sb_alloc(struct super_block *sb) diff --git a/security/commoncap.c b/security/commoncap.c index 7abebd782d5e..abb6050c8083 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -481,6 +481,8 @@ out: return rc; } +static int is_secureexec(struct linux_binprm *bprm); + /** * cap_bprm_set_creds - Set up the proposed credentials for execve(). * @bprm: The execution parameters, including the proposed creds @@ -614,11 +616,14 @@ skip: if (WARN_ON(!cap_ambient_invariant_ok(new))) return -EPERM; + /* Check for privilege-elevated exec. */ + bprm->cap_elevated = is_secureexec(bprm); + return 0; } /** - * cap_bprm_secureexec - Determine whether a secure execution is required + * is_secureexec - Determine whether a secure execution is required * @bprm: The execution parameters * * Determine whether a secure execution is required, return 1 if it is, and 0 @@ -627,9 +632,9 @@ skip: * The credentials have been committed by this point, and so are no longer * available through @bprm->cred. */ -int cap_bprm_secureexec(struct linux_binprm *bprm) +static int is_secureexec(struct linux_binprm *bprm) { - const struct cred *cred = current_cred(); + const struct cred *cred = bprm->cred; kuid_t root_uid = make_kuid(cred->user_ns, 0); if (!uid_eq(cred->uid, root_uid)) { @@ -1079,7 +1084,6 @@ struct security_hook_list capability_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(capget, cap_capget), LSM_HOOK_INIT(capset, cap_capset), LSM_HOOK_INIT(bprm_set_creds, cap_bprm_set_creds), - LSM_HOOK_INIT(bprm_secureexec, cap_bprm_secureexec), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), -- cgit v1.2.3 From 2af622802696e1dbe28d81c8ea6355dc30800396 Mon Sep 17 00:00:00 2001 From: Kees Cook Date: Tue, 18 Jul 2017 15:25:29 -0700 Subject: LSM: drop bprm_secureexec hook This removes the bprm_secureexec hook since the logic has been folded into the bprm_set_creds hook for all LSMs now. Cc: Eric W. Biederman Signed-off-by: Kees Cook Reviewed-by: John Johansen Acked-by: James Morris Acked-by: Serge Hallyn --- fs/exec.c | 2 -- include/linux/lsm_hooks.h | 14 +++++--------- include/linux/security.h | 6 ------ security/security.c | 5 ----- 4 files changed, 5 insertions(+), 22 deletions(-) (limited to 'include/linux/security.h') diff --git a/fs/exec.c b/fs/exec.c index 1536bc4502cc..eca0cb550a06 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -1343,8 +1343,6 @@ EXPORT_SYMBOL(would_dump); void setup_new_exec(struct linux_binprm * bprm) { - bprm->secureexec |= security_bprm_secureexec(bprm); - /* * Once here, prepare_binrpm() will not be called any more, so * the final state of setuid/setgid/fscaps can be merged into the diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h index 3a90febadbe2..d1c7bef25691 100644 --- a/include/linux/lsm_hooks.h +++ b/include/linux/lsm_hooks.h @@ -43,7 +43,11 @@ * interpreters. The hook can tell whether it has already been called by * checking to see if @bprm->security is non-NULL. If so, then the hook * may decide either to retain the security information saved earlier or - * to replace it. + * to replace it. The hook must set @bprm->secureexec to 1 if a "secure + * exec" has happened as a result of this hook call. The flag is used to + * indicate the need for a sanitized execution environment, and is also + * passed in the ELF auxiliary table on the initial stack to indicate + * whether libc should enable secure mode. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. * @bprm_check_security: @@ -71,12 +75,6 @@ * linux_binprm structure. This hook is a good place to perform state * changes on the process such as clearing out non-inheritable signal * state. This is called immediately after commit_creds(). - * @bprm_secureexec: - * Return a boolean value (0 or 1) indicating whether a "secure exec" - * is required. The flag is passed in the auxiliary table - * on the initial stack to the ELF interpreter to indicate whether libc - * should enable secure mode. - * @bprm contains the linux_binprm structure. * * Security hooks for filesystem operations. * @@ -1388,7 +1386,6 @@ union security_list_options { int (*bprm_set_creds)(struct linux_binprm *bprm); int (*bprm_check_security)(struct linux_binprm *bprm); - int (*bprm_secureexec)(struct linux_binprm *bprm); void (*bprm_committing_creds)(struct linux_binprm *bprm); void (*bprm_committed_creds)(struct linux_binprm *bprm); @@ -1710,7 +1707,6 @@ struct security_hook_heads { struct list_head vm_enough_memory; struct list_head bprm_set_creds; struct list_head bprm_check_security; - struct list_head bprm_secureexec; struct list_head bprm_committing_creds; struct list_head bprm_committed_creds; struct list_head sb_alloc_security; diff --git a/include/linux/security.h b/include/linux/security.h index f89832ccdf55..974bb9b0996c 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -231,7 +231,6 @@ int security_bprm_set_creds(struct linux_binprm *bprm); int security_bprm_check(struct linux_binprm *bprm); void security_bprm_committing_creds(struct linux_binprm *bprm); void security_bprm_committed_creds(struct linux_binprm *bprm); -int security_bprm_secureexec(struct linux_binprm *bprm); int security_sb_alloc(struct super_block *sb); void security_sb_free(struct super_block *sb); int security_sb_copy_data(char *orig, char *copy); @@ -540,11 +539,6 @@ static inline void security_bprm_committed_creds(struct linux_binprm *bprm) { } -static inline int security_bprm_secureexec(struct linux_binprm *bprm) -{ - return 0; -} - static inline int security_sb_alloc(struct super_block *sb) { return 0; diff --git a/security/security.c b/security/security.c index 30132378d103..afc34f46c6c5 100644 --- a/security/security.c +++ b/security/security.c @@ -351,11 +351,6 @@ void security_bprm_committed_creds(struct linux_binprm *bprm) call_void_hook(bprm_committed_creds, bprm); } -int security_bprm_secureexec(struct linux_binprm *bprm) -{ - return call_int_hook(bprm_secureexec, 0, bprm); -} - int security_sb_alloc(struct super_block *sb) { return call_int_hook(sb_alloc_security, 0, sb); -- cgit v1.2.3 From 8db6c34f1dbc8e06aa016a9b829b06902c3e1340 Mon Sep 17 00:00:00 2001 From: "Serge E. Hallyn" Date: Mon, 8 May 2017 13:11:56 -0500 Subject: Introduce v3 namespaced file capabilities Root in a non-initial user ns cannot be trusted to write a traditional security.capability xattr. If it were allowed to do so, then any unprivileged user on the host could map his own uid to root in a private namespace, write the xattr, and execute the file with privilege on the host. However supporting file capabilities in a user namespace is very desirable. Not doing so means that any programs designed to run with limited privilege must continue to support other methods of gaining and dropping privilege. For instance a program installer must detect whether file capabilities can be assigned, and assign them if so but set setuid-root otherwise. The program in turn must know how to drop partial capabilities, and do so only if setuid-root. This patch introduces v3 of the security.capability xattr. It builds a vfs_ns_cap_data struct by appending a uid_t rootid to struct vfs_cap_data. This is the absolute uid_t (that is, the uid_t in user namespace which mounted the filesystem, usually init_user_ns) of the root id in whose namespaces the file capabilities may take effect. When a task asks to write a v2 security.capability xattr, if it is privileged with respect to the userns which mounted the filesystem, then nothing should change. Otherwise, the kernel will transparently rewrite the xattr as a v3 with the appropriate rootid. This is done during the execution of setxattr() to catch user-space-initiated capability writes. Subsequently, any task executing the file which has the noted kuid as its root uid, or which is in a descendent user_ns of such a user_ns, will run the file with capabilities. Similarly when asking to read file capabilities, a v3 capability will be presented as v2 if it applies to the caller's namespace. If a task writes a v3 security.capability, then it can provide a uid for the xattr so long as the uid is valid in its own user namespace, and it is privileged with CAP_SETFCAP over its namespace. The kernel will translate that rootid to an absolute uid, and write that to disk. After this, a task in the writer's namespace will not be able to use those capabilities (unless rootid was 0), but a task in a namespace where the given uid is root will. Only a single security.capability xattr may exist at a time for a given file. A task may overwrite an existing xattr so long as it is privileged over the inode. Note this is a departure from previous semantics, which required privilege to remove a security.capability xattr. This check can be re-added if deemed useful. This allows a simple setxattr to work, allows tar/untar to work, and allows us to tar in one namespace and untar in another while preserving the capability, without risking leaking privilege into a parent namespace. Example using tar: $ cp /bin/sleep sleepx $ mkdir b1 b2 $ lxc-usernsexec -m b:0:100000:1 -m b:1:$(id -u):1 -- chown 0:0 b1 $ lxc-usernsexec -m b:0:100001:1 -m b:1:$(id -u):1 -- chown 0:0 b2 $ lxc-usernsexec -m b:0:100000:1000 -- tar --xattrs-include=security.capability --xattrs -cf b1/sleepx.tar sleepx $ lxc-usernsexec -m b:0:100001:1000 -- tar --xattrs-include=security.capability --xattrs -C b2 -xf b1/sleepx.tar $ lxc-usernsexec -m b:0:100001:1000 -- getcap b2/sleepx b2/sleepx = cap_sys_admin+ep # /opt/ltp/testcases/bin/getv3xattr b2/sleepx v3 xattr, rootid is 100001 A patch to linux-test-project adding a new set of tests for this functionality is in the nsfscaps branch at github.com/hallyn/ltp Changelog: Nov 02 2016: fix invalid check at refuse_fcap_overwrite() Nov 07 2016: convert rootid from and to fs user_ns (From ebiederm: mar 28 2017) commoncap.c: fix typos - s/v4/v3 get_vfs_caps_from_disk: clarify the fs_ns root access check nsfscaps: change the code split for cap_inode_setxattr() Apr 09 2017: don't return v3 cap for caps owned by current root. return a v2 cap for a true v2 cap in non-init ns Apr 18 2017: . Change the flow of fscap writing to support s_user_ns writing. . Remove refuse_fcap_overwrite(). The value of the previous xattr doesn't matter. Apr 24 2017: . incorporate Eric's incremental diff . move cap_convert_nscap to setxattr and simplify its usage May 8, 2017: . fix leaking dentry refcount in cap_inode_getsecurity Signed-off-by: Serge Hallyn Signed-off-by: Eric W. Biederman --- fs/xattr.c | 6 + include/linux/capability.h | 2 + include/linux/security.h | 2 + include/uapi/linux/capability.h | 22 +++- security/commoncap.c | 270 +++++++++++++++++++++++++++++++++++++--- 5 files changed, 280 insertions(+), 22 deletions(-) (limited to 'include/linux/security.h') diff --git a/fs/xattr.c b/fs/xattr.c index 464c94bf65f9..7b03df6b8be2 100644 --- a/fs/xattr.c +++ b/fs/xattr.c @@ -441,6 +441,12 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value, if ((strcmp(kname, XATTR_NAME_POSIX_ACL_ACCESS) == 0) || (strcmp(kname, XATTR_NAME_POSIX_ACL_DEFAULT) == 0)) posix_acl_fix_xattr_from_user(kvalue, size); + else if (strcmp(kname, XATTR_NAME_CAPS) == 0) { + error = cap_convert_nscap(d, &kvalue, size); + if (error < 0) + goto out; + size = error; + } } error = vfs_setxattr(d, kname, kvalue, size, flags); diff --git a/include/linux/capability.h b/include/linux/capability.h index 6ffb67e10c06..b52e278e4744 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -248,4 +248,6 @@ extern bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns); /* audit system wants to get cap info from files as well */ extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); +extern int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size); + #endif /* !_LINUX_CAPABILITY_H */ diff --git a/include/linux/security.h b/include/linux/security.h index b6ea1dc9cc9d..6fff8c924718 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -91,6 +91,8 @@ extern int cap_inode_setxattr(struct dentry *dentry, const char *name, extern int cap_inode_removexattr(struct dentry *dentry, const char *name); extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); +extern int cap_inode_getsecurity(struct inode *inode, const char *name, + void **buffer, bool alloc); extern int cap_mmap_addr(unsigned long addr); extern int cap_mmap_file(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags); diff --git a/include/uapi/linux/capability.h b/include/uapi/linux/capability.h index 6fe14d001f68..230e05d35191 100644 --- a/include/uapi/linux/capability.h +++ b/include/uapi/linux/capability.h @@ -60,9 +60,13 @@ typedef struct __user_cap_data_struct { #define VFS_CAP_U32_2 2 #define XATTR_CAPS_SZ_2 (sizeof(__le32)*(1 + 2*VFS_CAP_U32_2)) -#define XATTR_CAPS_SZ XATTR_CAPS_SZ_2 -#define VFS_CAP_U32 VFS_CAP_U32_2 -#define VFS_CAP_REVISION VFS_CAP_REVISION_2 +#define VFS_CAP_REVISION_3 0x03000000 +#define VFS_CAP_U32_3 2 +#define XATTR_CAPS_SZ_3 (sizeof(__le32)*(2 + 2*VFS_CAP_U32_3)) + +#define XATTR_CAPS_SZ XATTR_CAPS_SZ_3 +#define VFS_CAP_U32 VFS_CAP_U32_3 +#define VFS_CAP_REVISION VFS_CAP_REVISION_3 struct vfs_cap_data { __le32 magic_etc; /* Little endian */ @@ -72,6 +76,18 @@ struct vfs_cap_data { } data[VFS_CAP_U32]; }; +/* + * same as vfs_cap_data but with a rootid at the end + */ +struct vfs_ns_cap_data { + __le32 magic_etc; + struct { + __le32 permitted; /* Little endian */ + __le32 inheritable; /* Little endian */ + } data[VFS_CAP_U32]; + __le32 rootid; +}; + #ifndef __KERNEL__ /* diff --git a/security/commoncap.c b/security/commoncap.c index d59320282294..c37d27dd1e2c 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -335,6 +335,209 @@ int cap_inode_killpriv(struct dentry *dentry) return error; } +static bool rootid_owns_currentns(kuid_t kroot) +{ + struct user_namespace *ns; + + if (!uid_valid(kroot)) + return false; + + for (ns = current_user_ns(); ; ns = ns->parent) { + if (from_kuid(ns, kroot) == 0) + return true; + if (ns == &init_user_ns) + break; + } + + return false; +} + +static __u32 sansflags(__u32 m) +{ + return m & ~VFS_CAP_FLAGS_EFFECTIVE; +} + +static bool is_v2header(size_t size, __le32 magic) +{ + __u32 m = le32_to_cpu(magic); + if (size != XATTR_CAPS_SZ_2) + return false; + return sansflags(m) == VFS_CAP_REVISION_2; +} + +static bool is_v3header(size_t size, __le32 magic) +{ + __u32 m = le32_to_cpu(magic); + + if (size != XATTR_CAPS_SZ_3) + return false; + return sansflags(m) == VFS_CAP_REVISION_3; +} + +/* + * getsecurity: We are called for security.* before any attempt to read the + * xattr from the inode itself. + * + * This gives us a chance to read the on-disk value and convert it. If we + * return -EOPNOTSUPP, then vfs_getxattr() will call the i_op handler. + * + * Note we are not called by vfs_getxattr_alloc(), but that is only called + * by the integrity subsystem, which really wants the unconverted values - + * so that's good. + */ +int cap_inode_getsecurity(struct inode *inode, const char *name, void **buffer, + bool alloc) +{ + int size, ret; + kuid_t kroot; + uid_t root, mappedroot; + char *tmpbuf = NULL; + struct vfs_cap_data *cap; + struct vfs_ns_cap_data *nscap; + struct dentry *dentry; + struct user_namespace *fs_ns; + + if (strcmp(name, "capability") != 0) + return -EOPNOTSUPP; + + dentry = d_find_alias(inode); + if (!dentry) + return -EINVAL; + + size = sizeof(struct vfs_ns_cap_data); + ret = (int) vfs_getxattr_alloc(dentry, XATTR_NAME_CAPS, + &tmpbuf, size, GFP_NOFS); + dput(dentry); + + if (ret < 0) + return ret; + + fs_ns = inode->i_sb->s_user_ns; + cap = (struct vfs_cap_data *) tmpbuf; + if (is_v2header((size_t) ret, cap->magic_etc)) { + /* If this is sizeof(vfs_cap_data) then we're ok with the + * on-disk value, so return that. */ + if (alloc) + *buffer = tmpbuf; + else + kfree(tmpbuf); + return ret; + } else if (!is_v3header((size_t) ret, cap->magic_etc)) { + kfree(tmpbuf); + return -EINVAL; + } + + nscap = (struct vfs_ns_cap_data *) tmpbuf; + root = le32_to_cpu(nscap->rootid); + kroot = make_kuid(fs_ns, root); + + /* If the root kuid maps to a valid uid in current ns, then return + * this as a nscap. */ + mappedroot = from_kuid(current_user_ns(), kroot); + if (mappedroot != (uid_t)-1 && mappedroot != (uid_t)0) { + if (alloc) { + *buffer = tmpbuf; + nscap->rootid = cpu_to_le32(mappedroot); + } else + kfree(tmpbuf); + return size; + } + + if (!rootid_owns_currentns(kroot)) { + kfree(tmpbuf); + return -EOPNOTSUPP; + } + + /* This comes from a parent namespace. Return as a v2 capability */ + size = sizeof(struct vfs_cap_data); + if (alloc) { + *buffer = kmalloc(size, GFP_ATOMIC); + if (*buffer) { + struct vfs_cap_data *cap = *buffer; + __le32 nsmagic, magic; + magic = VFS_CAP_REVISION_2; + nsmagic = le32_to_cpu(nscap->magic_etc); + if (nsmagic & VFS_CAP_FLAGS_EFFECTIVE) + magic |= VFS_CAP_FLAGS_EFFECTIVE; + memcpy(&cap->data, &nscap->data, sizeof(__le32) * 2 * VFS_CAP_U32); + cap->magic_etc = cpu_to_le32(magic); + } + } + kfree(tmpbuf); + return size; +} + +static kuid_t rootid_from_xattr(const void *value, size_t size, + struct user_namespace *task_ns) +{ + const struct vfs_ns_cap_data *nscap = value; + uid_t rootid = 0; + + if (size == XATTR_CAPS_SZ_3) + rootid = le32_to_cpu(nscap->rootid); + + return make_kuid(task_ns, rootid); +} + +static bool validheader(size_t size, __le32 magic) +{ + return is_v2header(size, magic) || is_v3header(size, magic); +} + +/* + * User requested a write of security.capability. If needed, update the + * xattr to change from v2 to v3, or to fixup the v3 rootid. + * + * If all is ok, we return the new size, on error return < 0. + */ +int cap_convert_nscap(struct dentry *dentry, void **ivalue, size_t size) +{ + struct vfs_ns_cap_data *nscap; + uid_t nsrootid; + const struct vfs_cap_data *cap = *ivalue; + __u32 magic, nsmagic; + struct inode *inode = d_backing_inode(dentry); + struct user_namespace *task_ns = current_user_ns(), + *fs_ns = inode->i_sb->s_user_ns; + kuid_t rootid; + size_t newsize; + + if (!*ivalue) + return -EINVAL; + if (!validheader(size, cap->magic_etc)) + return -EINVAL; + if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) + return -EPERM; + if (size == XATTR_CAPS_SZ_2) + if (ns_capable(inode->i_sb->s_user_ns, CAP_SETFCAP)) + /* user is privileged, just write the v2 */ + return size; + + rootid = rootid_from_xattr(*ivalue, size, task_ns); + if (!uid_valid(rootid)) + return -EINVAL; + + nsrootid = from_kuid(fs_ns, rootid); + if (nsrootid == -1) + return -EINVAL; + + newsize = sizeof(struct vfs_ns_cap_data); + nscap = kmalloc(newsize, GFP_ATOMIC); + if (!nscap) + return -ENOMEM; + nscap->rootid = cpu_to_le32(nsrootid); + nsmagic = VFS_CAP_REVISION_3; + magic = le32_to_cpu(cap->magic_etc); + if (magic & VFS_CAP_FLAGS_EFFECTIVE) + nsmagic |= VFS_CAP_FLAGS_EFFECTIVE; + nscap->magic_etc = cpu_to_le32(nsmagic); + memcpy(&nscap->data, &cap->data, sizeof(__le32) * 2 * VFS_CAP_U32); + + kvfree(*ivalue); + *ivalue = nscap; + return newsize; +} + /* * Calculate the new process capability sets from the capability sets attached * to a file. @@ -388,7 +591,10 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data __u32 magic_etc; unsigned tocopy, i; int size; - struct vfs_cap_data caps; + struct vfs_ns_cap_data data, *nscaps = &data; + struct vfs_cap_data *caps = (struct vfs_cap_data *) &data; + kuid_t rootkuid; + struct user_namespace *fs_ns = inode->i_sb->s_user_ns; memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); @@ -396,18 +602,20 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data return -ENODATA; size = __vfs_getxattr((struct dentry *)dentry, inode, - XATTR_NAME_CAPS, &caps, XATTR_CAPS_SZ); + XATTR_NAME_CAPS, &data, XATTR_CAPS_SZ); if (size == -ENODATA || size == -EOPNOTSUPP) /* no data, that's ok */ return -ENODATA; + if (size < 0) return size; if (size < sizeof(magic_etc)) return -EINVAL; - cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps.magic_etc); + cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps->magic_etc); + rootkuid = make_kuid(fs_ns, 0); switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) @@ -419,15 +627,27 @@ int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data return -EINVAL; tocopy = VFS_CAP_U32_2; break; + case VFS_CAP_REVISION_3: + if (size != XATTR_CAPS_SZ_3) + return -EINVAL; + tocopy = VFS_CAP_U32_3; + rootkuid = make_kuid(fs_ns, le32_to_cpu(nscaps->rootid)); + break; + default: return -EINVAL; } + /* Limit the caps to the mounter of the filesystem + * or the more limited uid specified in the xattr. + */ + if (!rootid_owns_currentns(rootkuid)) + return -ENODATA; CAP_FOR_EACH_U32(i) { if (i >= tocopy) break; - cpu_caps->permitted.cap[i] = le32_to_cpu(caps.data[i].permitted); - cpu_caps->inheritable.cap[i] = le32_to_cpu(caps.data[i].inheritable); + cpu_caps->permitted.cap[i] = le32_to_cpu(caps->data[i].permitted); + cpu_caps->inheritable.cap[i] = le32_to_cpu(caps->data[i].inheritable); } cpu_caps->permitted.cap[CAP_LAST_U32] &= CAP_LAST_U32_VALID_MASK; @@ -465,8 +685,8 @@ static int get_file_caps(struct linux_binprm *bprm, bool *effective, bool *has_c rc = get_vfs_caps_from_disk(bprm->file->f_path.dentry, &vcaps); if (rc < 0) { if (rc == -EINVAL) - printk(KERN_NOTICE "%s: get_vfs_caps_from_disk returned %d for %s\n", - __func__, rc, bprm->filename); + printk(KERN_NOTICE "Invalid argument reading file caps for %s\n", + bprm->filename); else if (rc == -ENODATA) rc = 0; goto out; @@ -663,15 +883,19 @@ int cap_bprm_secureexec(struct linux_binprm *bprm) int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - if (!strcmp(name, XATTR_NAME_CAPS)) { - if (!capable(CAP_SETFCAP)) - return -EPERM; + /* Ignore non-security xattrs */ + if (strncmp(name, XATTR_SECURITY_PREFIX, + sizeof(XATTR_SECURITY_PREFIX) - 1) != 0) + return 0; + + /* + * For XATTR_NAME_CAPS the check will be done in + * cap_convert_nscap(), called by setxattr() + */ + if (strcmp(name, XATTR_NAME_CAPS) == 0) return 0; - } - if (!strncmp(name, XATTR_SECURITY_PREFIX, - sizeof(XATTR_SECURITY_PREFIX) - 1) && - !capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } @@ -689,15 +913,22 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name, */ int cap_inode_removexattr(struct dentry *dentry, const char *name) { - if (!strcmp(name, XATTR_NAME_CAPS)) { - if (!capable(CAP_SETFCAP)) + /* Ignore non-security xattrs */ + if (strncmp(name, XATTR_SECURITY_PREFIX, + sizeof(XATTR_SECURITY_PREFIX) - 1) != 0) + return 0; + + if (strcmp(name, XATTR_NAME_CAPS) == 0) { + /* security.capability gets namespaced */ + struct inode *inode = d_backing_inode(dentry); + if (!inode) + return -EINVAL; + if (!capable_wrt_inode_uidgid(inode, CAP_SETFCAP)) return -EPERM; return 0; } - if (!strncmp(name, XATTR_SECURITY_PREFIX, - sizeof(XATTR_SECURITY_PREFIX) - 1) && - !capable(CAP_SYS_ADMIN)) + if (!capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } @@ -1085,6 +1316,7 @@ struct security_hook_list capability_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(bprm_secureexec, cap_bprm_secureexec), LSM_HOOK_INIT(inode_need_killpriv, cap_inode_need_killpriv), LSM_HOOK_INIT(inode_killpriv, cap_inode_killpriv), + LSM_HOOK_INIT(inode_getsecurity, cap_inode_getsecurity), LSM_HOOK_INIT(mmap_addr, cap_mmap_addr), LSM_HOOK_INIT(mmap_file, cap_mmap_file), LSM_HOOK_INIT(task_fix_setuid, cap_task_fix_setuid), -- cgit v1.2.3