diff --git a/Documentation/credentials.txt b/Documentation/credentials.txt new file mode 100644 index 00000000000..df03169782e --- /dev/null +++ b/Documentation/credentials.txt @@ -0,0 +1,582 @@ + ==================== + CREDENTIALS IN LINUX + ==================== + +By: David Howells + +Contents: + + (*) Overview. + + (*) Types of credentials. + + (*) File markings. + + (*) Task credentials. + + - Immutable credentials. + - Accessing task credentials. + - Accessing another task's credentials. + - Altering credentials. + - Managing credentials. + + (*) Open file credentials. + + (*) Overriding the VFS's use of credentials. + + +======== +OVERVIEW +======== + +There are several parts to the security check performed by Linux when one +object acts upon another: + + (1) Objects. + + Objects are things in the system that may be acted upon directly by + userspace programs. Linux has a variety of actionable objects, including: + + - Tasks + - Files/inodes + - Sockets + - Message queues + - Shared memory segments + - Semaphores + - Keys + + As a part of the description of all these objects there is a set of + credentials. What's in the set depends on the type of object. + + (2) Object ownership. + + Amongst the credentials of most objects, there will be a subset that + indicates the ownership of that object. This is used for resource + accounting and limitation (disk quotas and task rlimits for example). + + In a standard UNIX filesystem, for instance, this will be defined by the + UID marked on the inode. + + (3) The objective context. + + Also amongst the credentials of those objects, there will be a subset that + indicates the 'objective context' of that object. This may or may not be + the same set as in (2) - in standard UNIX files, for instance, this is the + defined by the UID and the GID marked on the inode. + + The objective context is used as part of the security calculation that is + carried out when an object is acted upon. + + (4) Subjects. + + A subject is an object that is acting upon another object. + + Most of the objects in the system are inactive: they don't act on other + objects within the system. Processes/tasks are the obvious exception: + they do stuff; they access and manipulate things. + + Objects other than tasks may under some circumstances also be subjects. + For instance an open file may send SIGIO to a task using the UID and EUID + given to it by a task that called fcntl(F_SETOWN) upon it. In this case, + the file struct will have a subjective context too. + + (5) The subjective context. + + A subject has an additional interpretation of its credentials. A subset + of its credentials forms the 'subjective context'. The subjective context + is used as part of the security calculation that is carried out when a + subject acts. + + A Linux task, for example, has the FSUID, FSGID and the supplementary + group list for when it is acting upon a file - which are quite separate + from the real UID and GID that normally form the objective context of the + task. + + (6) Actions. + + Linux has a number of actions available that a subject may perform upon an + object. The set of actions available depends on the nature of the subject + and the object. + + Actions include reading, writing, creating and deleting files; forking or + signalling and tracing tasks. + + (7) Rules, access control lists and security calculations. + + When a subject acts upon an object, a security calculation is made. This + involves taking the subjective context, the objective context and the + action, and searching one or more sets of rules to see whether the subject + is granted or denied permission to act in the desired manner on the + object, given those contexts. + + There are two main sources of rules: + + (a) Discretionary access control (DAC): + + Sometimes the object will include sets of rules as part of its + description. This is an 'Access Control List' or 'ACL'. A Linux + file may supply more than one ACL. + + A traditional UNIX file, for example, includes a permissions mask that + is an abbreviated ACL with three fixed classes of subject ('user', + 'group' and 'other'), each of which may be granted certain privileges + ('read', 'write' and 'execute' - whatever those map to for the object + in question). UNIX file permissions do not allow the arbitrary + specification of subjects, however, and so are of limited use. + + A Linux file might also sport a POSIX ACL. This is a list of rules + that grants various permissions to arbitrary subjects. + + (b) Mandatory access control (MAC): + + The system as a whole may have one or more sets of rules that get + applied to all subjects and objects, regardless of their source. + SELinux and Smack are examples of this. + + In the case of SELinux and Smack, each object is given a label as part + of its credentials. When an action is requested, they take the + subject label, the object label and the action and look for a rule + that says that this action is either granted or denied. + + +==================== +TYPES OF CREDENTIALS +==================== + +The Linux kernel supports the following types of credentials: + + (1) Traditional UNIX credentials. + + Real User ID + Real Group ID + + The UID and GID are carried by most, if not all, Linux objects, even if in + some cases it has to be invented (FAT or CIFS files for example, which are + derived from Windows). These (mostly) define the objective context of + that object, with tasks being slightly different in some cases. + + Effective, Saved and FS User ID + Effective, Saved and FS Group ID + Supplementary groups + + These are additional credentials used by tasks only. Usually, an + EUID/EGID/GROUPS will be used as the subjective context, and real UID/GID + will be used as the objective. For tasks, it should be noted that this is + not always true. + + (2) Capabilities. + + Set of permitted capabilities + Set of inheritable capabilities + Set of effective capabilities + Capability bounding set + + These are only carried by tasks. They indicate superior capabilities + granted piecemeal to a task that an ordinary task wouldn't otherwise have. + These are manipulated implicitly by changes to the traditional UNIX + credentials, but can also be manipulated directly by the capset() system + call. + + The permitted capabilities are those caps that the process might grant + itself to its effective or permitted sets through capset(). This + inheritable set might also be so constrained. + + The effective capabilities are the ones that a task is actually allowed to + make use of itself. + + The inheritable capabilities are the ones that may get passed across + execve(). + + The bounding set limits the capabilities that may be inherited across + execve(), especially when a binary is executed that will execute as UID 0. + + (3) Secure management flags (securebits). + + These are only carried by tasks. These govern the way the above + credentials are manipulated and inherited over certain operations such as + execve(). They aren't used directly as objective or subjective + credentials. + + (4) Keys and keyrings. + + These are only carried by tasks. They carry and cache security tokens + that don't fit into the other standard UNIX credentials. They are for + making such things as network filesystem keys available to the file + accesses performed by processes, without the necessity of ordinary + programs having to know about security details involved. + + Keyrings are a special type of key. They carry sets of other keys and can + be searched for the desired key. Each process may subscribe to a number + of keyrings: + + Per-thread keying + Per-process keyring + Per-session keyring + + When a process accesses a key, if not already present, it will normally be + cached on one of these keyrings for future accesses to find. + + For more information on using keys, see Documentation/keys.txt. + + (5) LSM + + The Linux Security Module allows extra controls to be placed over the + operations that a task may do. Currently Linux supports two main + alternate LSM options: SELinux and Smack. + + Both work by labelling the objects in a system and then applying sets of + rules (policies) that say what operations a task with one label may do to + an object with another label. + + (6) AF_KEY + + This is a socket-based approach to credential management for networking + stacks [RFC 2367]. It isn't discussed by this document as it doesn't + interact directly with task and file credentials; rather it keeps system + level credentials. + + +When a file is opened, part of the opening task's subjective context is +recorded in the file struct created. This allows operations using that file +struct to use those credentials instead of the subjective context of the task +that issued the operation. An example of this would be a file opened on a +network filesystem where the credentials of the opened file should be presented +to the server, regardless of who is actually doing a read or a write upon it. + + +============= +FILE MARKINGS +============= + +Files on disk or obtained over the network may have annotations that form the +objective security context of that file. Depending on the type of filesystem, +this may include one or more of the following: + + (*) UNIX UID, GID, mode; + + (*) Windows user ID; + + (*) Access control list; + + (*) LSM security label; + + (*) UNIX exec privilege escalation bits (SUID/SGID); + + (*) File capabilities exec privilege escalation bits. + +These are compared to the task's subjective security context, and certain +operations allowed or disallowed as a result. In the case of execve(), the +privilege escalation bits come into play, and may allow the resulting process +extra privileges, based on the annotations on the executable file. + + +================ +TASK CREDENTIALS +================ + +In Linux, all of a task's credentials are held in (uid, gid) or through +(groups, keys, LSM security) a refcounted structure of type 'struct cred'. +Each task points to its credentials by a pointer called 'cred' in its +task_struct. + +Once a set of credentials has been prepared and committed, it may not be +changed, barring the following exceptions: + + (1) its reference count may be changed; + + (2) the reference count on the group_info struct it points to may be changed; + + (3) the reference count on the security data it points to may be changed; + + (4) the reference count on any keyrings it points to may be changed; + + (5) any keyrings it points to may be revoked, expired or have their security + attributes changed; and + + (6) the contents of any keyrings to which it points may be changed (the whole + point of keyrings being a shared set of credentials, modifiable by anyone + with appropriate access). + +To alter anything in the cred struct, the copy-and-replace principle must be +adhered to. First take a copy, then alter the copy and then use RCU to change +the task pointer to make it point to the new copy. There are wrappers to aid +with this (see below). + +A task may only alter its _own_ credentials; it is no longer permitted for a +task to alter another's credentials. This means the capset() system call is no +longer permitted to take any PID other than the one of the current process. +Also keyctl_instantiate() and keyctl_negate() functions no longer permit +attachment to process-specific keyrings in the requesting process as the +instantiating process may need to create them. + + +IMMUTABLE CREDENTIALS +--------------------- + +Once a set of credentials has been made public (by calling commit_creds() for +example), it must be considered immutable, barring two exceptions: + + (1) The reference count may be altered. + + (2) Whilst the keyring subscriptions of a set of credentials may not be + changed, the keyrings subscribed to may have their contents altered. + +To catch accidental credential alteration at compile time, struct task_struct +has _const_ pointers to its credential sets, as does struct file. Furthermore, +certain functions such as get_cred() and put_cred() operate on const pointers, +thus rendering casts unnecessary, but require to temporarily ditch the const +qualification to be able to alter the reference count. + + +ACCESSING TASK CREDENTIALS +-------------------------- + +A task being able to alter only its own credentials permits the current process +to read or replace its own credentials without the need for any form of locking +- which simplifies things greatly. It can just call: + + const struct cred *current_cred() + +to get a pointer to its credentials structure, and it doesn't have to release +it afterwards. + +There are convenience wrappers for retrieving specific aspects of a task's +credentials (the value is simply returned in each case): + + uid_t current_uid(void) Current's real UID + gid_t current_gid(void) Current's real GID + uid_t current_euid(void) Current's effective UID + gid_t current_egid(void) Current's effective GID + uid_t current_fsuid(void) Current's file access UID + gid_t current_fsgid(void) Current's file access GID + kernel_cap_t current_cap(void) Current's effective capabilities + void *current_security(void) Current's LSM security pointer + struct user_struct *current_user(void) Current's user account + +There are also convenience wrappers for retrieving specific associated pairs of +a task's credentials: + + void current_uid_gid(uid_t *, gid_t *); + void current_euid_egid(uid_t *, gid_t *); + void current_fsuid_fsgid(uid_t *, gid_t *); + +which return these pairs of values through their arguments after retrieving +them from the current task's credentials. + + +In addition, there is a function for obtaining a reference on the current +process's current set of credentials: + + const struct cred *get_current_cred(void); + +and functions for getting references to one of the credentials that don't +actually live in struct cred: + + struct user_struct *get_current_user(void); + struct group_info *get_current_groups(void); + +which get references to the current process's user accounting structure and +supplementary groups list respectively. + +Once a reference has been obtained, it must be released with put_cred(), +free_uid() or put_group_info() as appropriate. + + +ACCESSING ANOTHER TASK'S CREDENTIALS +------------------------------------ + +Whilst a task may access its own credentials without the need for locking, the +same is not true of a task wanting to access another task's credentials. It +must use the RCU read lock and rcu_dereference(). + +The rcu_dereference() is wrapped by: + + const struct cred *__task_cred(struct task_struct *task); + +This should be used inside the RCU read lock, as in the following example: + + void foo(struct task_struct *t, struct foo_data *f) + { + const struct cred *tcred; + ... + rcu_read_lock(); + tcred = __task_cred(t); + f->uid = tcred->uid; + f->gid = tcred->gid; + f->groups = get_group_info(tcred->groups); + rcu_read_unlock(); + ... + } + +A function need not get RCU read lock to use __task_cred() if it is holding a +spinlock at the time as this implicitly holds the RCU read lock. + +Should it be necessary to hold another task's credentials for a long period of +time, and possibly to sleep whilst doing so, then the caller should get a +reference on them using: + + const struct cred *get_task_cred(struct task_struct *task); + +This does all the RCU magic inside of it. The caller must call put_cred() on +the credentials so obtained when they're finished with. + +There are a couple of convenience functions to access bits of another task's +credentials, hiding the RCU magic from the caller: + + uid_t task_uid(task) Task's real UID + uid_t task_euid(task) Task's effective UID + +If the caller is holding a spinlock or the RCU read lock at the time anyway, +then: + + __task_cred(task)->uid + __task_cred(task)->euid + +should be used instead. Similarly, if multiple aspects of a task's credentials +need to be accessed, RCU read lock or a spinlock should be used, __task_cred() +called, the result stored in a temporary pointer and then the credential +aspects called from that before dropping the lock. This prevents the +potentially expensive RCU magic from being invoked multiple times. + +Should some other single aspect of another task's credentials need to be +accessed, then this can be used: + + task_cred_xxx(task, member) + +where 'member' is a non-pointer member of the cred struct. For instance: + + uid_t task_cred_xxx(task, suid); + +will retrieve 'struct cred::suid' from the task, doing the appropriate RCU +magic. This may not be used for pointer members as what they point to may +disappear the moment the RCU read lock is dropped. + + +ALTERING CREDENTIALS +-------------------- + +As previously mentioned, a task may only alter its own credentials, and may not +alter those of another task. This means that it doesn't need to use any +locking to alter its own credentials. + +To alter the current process's credentials, a function should first prepare a +new set of credentials by calling: + + struct cred *prepare_creds(void); + +this locks current->cred_replace_mutex and then allocates and constructs a +duplicate of the current process's credentials, returning with the mutex still +held if successful. It returns NULL if not successful (out of memory). + +The mutex prevents ptrace() from altering the ptrace state of a process whilst +security checks on credentials construction and changing is taking place as +the ptrace state may alter the outcome, particularly in the case of execve(). + +The new credentials set should be altered appropriately, and any security +checks and hooks done. Both the current and the proposed sets of credentials +are available for this purpose as current_cred() will return the current set +still at this point. + + +When the credential set is ready, it should be committed to the current process +by calling: + + int commit_creds(struct cred *new); + +This will alter various aspects of the credentials and the process, giving the +LSM a chance to do likewise, then it will use rcu_assign_pointer() to actually +commit the new credentials to current->cred, it will release +current->cred_replace_mutex to allow ptrace() to take place, and it will notify +the scheduler and others of the changes. + +This function is guaranteed to return 0, so that it can be tail-called at the +end of such functions as sys_setresuid(). + +Note that this function consumes the caller's reference to the new credentials. +The caller should _not_ call put_cred() on the new credentials afterwards. + +Furthermore, once this function has been called on a new set of credentials, +those credentials may _not_ be changed further. + + +Should the security checks fail or some other error occur after prepare_creds() +has been called, then the following function should be invoked: + + void abort_creds(struct cred *new); + +This releases the lock on current->cred_replace_mutex that prepare_creds() got +and then releases the new credentials. + + +A typical credentials alteration function would look something like this: + + int alter_suid(uid_t suid) + { + struct cred *new; + int ret; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + new->suid = suid; + ret = security_alter_suid(new); + if (ret < 0) { + abort_creds(new); + return ret; + } + + return commit_creds(new); + } + + +MANAGING CREDENTIALS +-------------------- + +There are some functions to help manage credentials: + + (*) void put_cred(const struct cred *cred); + + This releases a reference to the given set of credentials. If the + reference count reaches zero, the credentials will be scheduled for + destruction by the RCU system. + + (*) const struct cred *get_cred(const struct cred *cred); + + This gets a reference on a live set of credentials, returning a pointer to + that set of credentials. + + (*) struct cred *get_new_cred(struct cred *cred); + + This gets a reference on a set of credentials that is under construction + and is thus still mutable, returning a pointer to that set of credentials. + + +===================== +OPEN FILE CREDENTIALS +===================== + +When a new file is opened, a reference is obtained on the opening task's +credentials and this is attached to the file struct as 'f_cred' in place of +'f_uid' and 'f_gid'. Code that used to access file->f_uid and file->f_gid +should now access file->f_cred->fsuid and file->f_cred->fsgid. + +It is safe to access f_cred without the use of RCU or locking because the +pointer will not change over the lifetime of the file struct, and nor will the +contents of the cred struct pointed to, barring the exceptions listed above +(see the Task Credentials section). + + +======================================= +OVERRIDING THE VFS'S USE OF CREDENTIALS +======================================= + +Under some circumstances it is desirable to override the credentials used by +the VFS, and that can be done by calling into such as vfs_mkdir() with a +different set of credentials. This is done in the following places: + + (*) sys_faccessat(). + + (*) do_coredump(). + + (*) nfs4recover.c. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index c9115c1b672..bffffa4e8ee 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1452,6 +1452,10 @@ and is between 256 and 4096 characters. It is defined in the file instruction doesn't work correctly and not to use it. + no_file_caps Tells the kernel not to honor file capabilities. The + only way then for a file to be executed with privilege + is to be setuid root or executed by root. + nohalt [IA-64] Tells the kernel not to use the power saving function PAL_HALT_LIGHT when idle. This increases power-consumption. On the positive side, it reduces diff --git a/Documentation/scheduler/sched-design-CFS.txt b/Documentation/scheduler/sched-design-CFS.txt index eb471c7a905..8398ca4ff4e 100644 --- a/Documentation/scheduler/sched-design-CFS.txt +++ b/Documentation/scheduler/sched-design-CFS.txt @@ -273,3 +273,24 @@ task groups and modify their CPU share using the "cgroups" pseudo filesystem. # #Launch gmplayer (or your favourite movie player) # echo > multimedia/tasks + +8. Implementation note: user namespaces + +User namespaces are intended to be hierarchical. But they are currently +only partially implemented. Each of those has ramifications for CFS. + +First, since user namespaces are hierarchical, the /sys/kernel/uids +presentation is inadequate. Eventually we will likely want to use sysfs +tagging to provide private views of /sys/kernel/uids within each user +namespace. + +Second, the hierarchical nature is intended to support completely +unprivileged use of user namespaces. So if using user groups, then +we want the users in a user namespace to be children of the user +who created it. + +That is currently unimplemented. So instead, every user in a new +user namespace will receive 1024 shares just like any user in the +initial user namespace. Note that at the moment creation of a new +user namespace requires each of CAP_SYS_ADMIN, CAP_SETUID, and +CAP_SETGID. diff --git a/arch/alpha/kernel/asm-offsets.c b/arch/alpha/kernel/asm-offsets.c index 4b18cd94d59..6ff8886e7e2 100644 --- a/arch/alpha/kernel/asm-offsets.c +++ b/arch/alpha/kernel/asm-offsets.c @@ -19,15 +19,18 @@ void foo(void) BLANK(); DEFINE(TASK_BLOCKED, offsetof(struct task_struct, blocked)); - DEFINE(TASK_UID, offsetof(struct task_struct, uid)); - DEFINE(TASK_EUID, offsetof(struct task_struct, euid)); - DEFINE(TASK_GID, offsetof(struct task_struct, gid)); - DEFINE(TASK_EGID, offsetof(struct task_struct, egid)); + DEFINE(TASK_CRED, offsetof(struct task_struct, cred)); DEFINE(TASK_REAL_PARENT, offsetof(struct task_struct, real_parent)); DEFINE(TASK_GROUP_LEADER, offsetof(struct task_struct, group_leader)); DEFINE(TASK_TGID, offsetof(struct task_struct, tgid)); BLANK(); + DEFINE(CRED_UID, offsetof(struct cred, uid)); + DEFINE(CRED_EUID, offsetof(struct cred, euid)); + DEFINE(CRED_GID, offsetof(struct cred, gid)); + DEFINE(CRED_EGID, offsetof(struct cred, egid)); + BLANK(); + DEFINE(SIZEOF_PT_REGS, sizeof(struct pt_regs)); DEFINE(PT_PTRACED, PT_PTRACED); DEFINE(CLONE_VM, CLONE_VM); diff --git a/arch/alpha/kernel/entry.S b/arch/alpha/kernel/entry.S index 5fc61e281ac..f77345bc66a 100644 --- a/arch/alpha/kernel/entry.S +++ b/arch/alpha/kernel/entry.S @@ -850,8 +850,9 @@ osf_getpriority: sys_getxuid: .prologue 0 ldq $2, TI_TASK($8) - ldl $0, TASK_UID($2) - ldl $1, TASK_EUID($2) + ldq $3, TASK_CRED($2) + ldl $0, CRED_UID($3) + ldl $1, CRED_EUID($3) stq $1, 80($sp) ret .end sys_getxuid @@ -862,8 +863,9 @@ sys_getxuid: sys_getxgid: .prologue 0 ldq $2, TI_TASK($8) - ldl $0, TASK_GID($2) - ldl $1, TASK_EGID($2) + ldq $3, TASK_CRED($2) + ldl $0, CRED_GID($3) + ldl $1, CRED_EGID($3) stq $1, 80($sp) ret .end sys_getxgid diff --git a/arch/ia64/ia32/sys_ia32.c b/arch/ia64/ia32/sys_ia32.c index 5e92ae00bdb..16ef61a91d9 100644 --- a/arch/ia64/ia32/sys_ia32.c +++ b/arch/ia64/ia32/sys_ia32.c @@ -1767,25 +1767,24 @@ groups16_from_user(struct group_info *group_info, short __user *grouplist) asmlinkage long sys32_getgroups16 (int gidsetsize, short __user *grouplist) { + const struct cred *cred = current_cred(); int i; if (gidsetsize < 0) return -EINVAL; - get_group_info(current->group_info); - i = current->group_info->ngroups; + i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } - if (groups16_to_user(grouplist, current->group_info)) { + if (groups16_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: - put_group_info(current->group_info); return i; } diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index fab1d21a4f2..f94aaa86933 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -158,7 +158,7 @@ mca_handler_bh(unsigned long paddr, void *iip, unsigned long ipsr) ia64_mlogbuf_dump(); printk(KERN_ERR "OS_MCA: process [cpu %d, pid: %d, uid: %d, " "iip: %p, psr: 0x%lx,paddr: 0x%lx](%s) encounters MCA.\n", - raw_smp_processor_id(), current->pid, current->uid, + raw_smp_processor_id(), current->pid, current_uid(), iip, ipsr, paddr, current->comm); spin_lock(&mca_bh_lock); diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 6543a5547c8..0e499757309 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -2220,8 +2220,8 @@ pfm_alloc_file(pfm_context_t *ctx) DPRINT(("new inode ino=%ld @%p\n", inode->i_ino, inode)); inode->i_mode = S_IFCHR|S_IRUGO; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); sprintf(name, "[%lu]", inode->i_ino); this.name = name; @@ -2399,22 +2399,33 @@ error_kmem: static int pfm_bad_permissions(struct task_struct *task) { + const struct cred *tcred; + uid_t uid = current_uid(); + gid_t gid = current_gid(); + int ret; + + rcu_read_lock(); + tcred = __task_cred(task); + /* inspired by ptrace_attach() */ DPRINT(("cur: uid=%d gid=%d task: euid=%d suid=%d uid=%d egid=%d sgid=%d\n", - current->uid, - current->gid, - task->euid, - task->suid, - task->uid, - task->egid, - task->sgid)); + uid, + gid, + tcred->euid, + tcred->suid, + tcred->uid, + tcred->egid, + tcred->sgid)); - return ((current->uid != task->euid) - || (current->uid != task->suid) - || (current->uid != task->uid) - || (current->gid != task->egid) - || (current->gid != task->sgid) - || (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE); + ret = ((uid != tcred->euid) + || (uid != tcred->suid) + || (uid != tcred->uid) + || (gid != tcred->egid) + || (gid != tcred->sgid) + || (gid != tcred->gid)) && !capable(CAP_SYS_PTRACE); + + rcu_read_unlock(); + return ret; } static int diff --git a/arch/ia64/kernel/signal.c b/arch/ia64/kernel/signal.c index e12500a9c44..e1821ca4c7d 100644 --- a/arch/ia64/kernel/signal.c +++ b/arch/ia64/kernel/signal.c @@ -229,7 +229,7 @@ ia64_rt_sigreturn (struct sigscratch *scr) si.si_errno = 0; si.si_code = SI_KERNEL; si.si_pid = task_pid_vnr(current); - si.si_uid = current->uid; + si.si_uid = current_uid(); si.si_addr = sc; force_sig_info(SIGSEGV, &si, current); return retval; @@ -326,7 +326,7 @@ force_sigsegv_info (int sig, void __user *addr) si.si_errno = 0; si.si_code = SI_KERNEL; si.si_pid = task_pid_vnr(current); - si.si_uid = current->uid; + si.si_uid = current_uid(); si.si_addr = addr; force_sig_info(SIGSEGV, &si, current); return 0; diff --git a/arch/mips/kernel/kspd.c b/arch/mips/kernel/kspd.c index b0591ae0ce5..fd6e5122403 100644 --- a/arch/mips/kernel/kspd.c +++ b/arch/mips/kernel/kspd.c @@ -174,8 +174,8 @@ static unsigned int translate_open_flags(int flags) static void sp_setfsuidgid( uid_t uid, gid_t gid) { - current->fsuid = uid; - current->fsgid = gid; + current->cred->fsuid = uid; + current->cred->fsgid = gid; key_fsuid_changed(current); key_fsgid_changed(current); diff --git a/arch/mips/kernel/mips-mt-fpaff.c b/arch/mips/kernel/mips-mt-fpaff.c index dc9eb72ed9d..5e77a3a21f9 100644 --- a/arch/mips/kernel/mips-mt-fpaff.c +++ b/arch/mips/kernel/mips-mt-fpaff.c @@ -51,6 +51,7 @@ asmlinkage long mipsmt_sys_sched_setaffinity(pid_t pid, unsigned int len, int retval; struct task_struct *p; struct thread_info *ti; + uid_t euid; if (len < sizeof(new_mask)) return -EINVAL; @@ -76,9 +77,9 @@ asmlinkage long mipsmt_sys_sched_setaffinity(pid_t pid, unsigned int len, */ get_task_struct(p); + euid = current_euid(); retval = -EPERM; - if ((current->euid != p->euid) && (current->euid != p->uid) && - !capable(CAP_SYS_NICE)) { + if (euid != p->euid && euid != p->uid && !capable(CAP_SYS_NICE)) { read_unlock(&tasklist_lock); goto out_unlock; } diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index a1b3da6bad5..010b27e01f7 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -1085,8 +1085,8 @@ static int vpe_open(struct inode *inode, struct file *filp) v->load_addr = NULL; v->len = 0; - v->uid = filp->f_uid; - v->gid = filp->f_gid; + v->uid = filp->f_cred->fsuid; + v->gid = filp->f_cred->fsgid; #ifdef CONFIG_MIPS_APSP_KSPD /* get kspd to tell us when a syscall_exit happens */ diff --git a/arch/parisc/kernel/signal.c b/arch/parisc/kernel/signal.c index 06213d1d6d9..f82544225e8 100644 --- a/arch/parisc/kernel/signal.c +++ b/arch/parisc/kernel/signal.c @@ -182,7 +182,7 @@ give_sigsegv: si.si_errno = 0; si.si_code = SI_KERNEL; si.si_pid = task_pid_vnr(current); - si.si_uid = current->uid; + si.si_uid = current_uid(); si.si_addr = &frame->uc; force_sig_info(SIGSEGV, &si, current); return; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index 565b7a237c8..866098686da 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -339,7 +339,7 @@ bad_area_nosemaphore: && printk_ratelimit()) printk(KERN_CRIT "kernel tried to execute NX-protected" " page (%lx) - exploit attempt? (uid: %d)\n", - address, current->uid); + address, current_uid()); return SIGSEGV; diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index cb85d237e49..6296bfd9cb0 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -95,8 +95,8 @@ spufs_new_inode(struct super_block *sb, int mode) goto out; inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; out: @@ -323,7 +323,7 @@ static int spufs_context_open(struct dentry *dentry, struct vfsmount *mnt) goto out; } - filp = dentry_open(dentry, mnt, O_RDONLY); + filp = dentry_open(dentry, mnt, O_RDONLY, current_cred()); if (IS_ERR(filp)) { put_unused_fd(ret); ret = PTR_ERR(filp); @@ -562,7 +562,7 @@ static int spufs_gang_open(struct dentry *dentry, struct vfsmount *mnt) goto out; } - filp = dentry_open(dentry, mnt, O_RDONLY); + filp = dentry_open(dentry, mnt, O_RDONLY, current_cred()); if (IS_ERR(filp)) { put_unused_fd(ret); ret = PTR_ERR(filp); diff --git a/arch/s390/hypfs/inode.c b/arch/s390/hypfs/inode.c index 36313801cd5..8aadcd7a7cf 100644 --- a/arch/s390/hypfs/inode.c +++ b/arch/s390/hypfs/inode.c @@ -280,8 +280,8 @@ static int hypfs_fill_super(struct super_block *sb, void *data, int silent) if (!sbi) return -ENOMEM; mutex_init(&sbi->lock); - sbi->uid = current->uid; - sbi->gid = current->gid; + sbi->uid = current_uid(); + sbi->gid = current_gid(); sb->s_fs_info = sbi; sb->s_blocksize = PAGE_CACHE_SIZE; sb->s_blocksize_bits = PAGE_CACHE_SHIFT; diff --git a/arch/s390/kernel/compat_linux.c b/arch/s390/kernel/compat_linux.c index 4646382af34..6cc87d8c868 100644 --- a/arch/s390/kernel/compat_linux.c +++ b/arch/s390/kernel/compat_linux.c @@ -148,9 +148,9 @@ asmlinkage long sys32_getresuid16(u16 __user *ruid, u16 __user *euid, u16 __user { int retval; - if (!(retval = put_user(high2lowuid(current->uid), ruid)) && - !(retval = put_user(high2lowuid(current->euid), euid))) - retval = put_user(high2lowuid(current->suid), suid); + if (!(retval = put_user(high2lowuid(current->cred->uid), ruid)) && + !(retval = put_user(high2lowuid(current->cred->euid), euid))) + retval = put_user(high2lowuid(current->cred->suid), suid); return retval; } @@ -165,9 +165,9 @@ asmlinkage long sys32_getresgid16(u16 __user *rgid, u16 __user *egid, u16 __user { int retval; - if (!(retval = put_user(high2lowgid(current->gid), rgid)) && - !(retval = put_user(high2lowgid(current->egid), egid))) - retval = put_user(high2lowgid(current->sgid), sgid); + if (!(retval = put_user(high2lowgid(current->cred->gid), rgid)) && + !(retval = put_user(high2lowgid(current->cred->egid), egid))) + retval = put_user(high2lowgid(current->cred->sgid), sgid); return retval; } @@ -217,20 +217,20 @@ asmlinkage long sys32_getgroups16(int gidsetsize, u16 __user *grouplist) if (gidsetsize < 0) return -EINVAL; - get_group_info(current->group_info); - i = current->group_info->ngroups; + get_group_info(current->cred->group_info); + i = current->cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } - if (groups16_to_user(grouplist, current->group_info)) { + if (groups16_to_user(grouplist, current->cred->group_info)) { i = -EFAULT; goto out; } } out: - put_group_info(current->group_info); + put_group_info(current->cred->group_info); return i; } @@ -261,22 +261,22 @@ asmlinkage long sys32_setgroups16(int gidsetsize, u16 __user *grouplist) asmlinkage long sys32_getuid16(void) { - return high2lowuid(current->uid); + return high2lowuid(current->cred->uid); } asmlinkage long sys32_geteuid16(void) { - return high2lowuid(current->euid); + return high2lowuid(current->cred->euid); } asmlinkage long sys32_getgid16(void) { - return high2lowgid(current->gid); + return high2lowgid(current->cred->gid); } asmlinkage long sys32_getegid16(void) { - return high2lowgid(current->egid); + return high2lowgid(current->cred->egid); } /* diff --git a/arch/um/drivers/mconsole_kern.c b/arch/um/drivers/mconsole_kern.c index 8f44ebb0dec..e14629c87de 100644 --- a/arch/um/drivers/mconsole_kern.c +++ b/arch/um/drivers/mconsole_kern.c @@ -161,7 +161,8 @@ void mconsole_proc(struct mc_request *req) goto out_kill; } - file = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY); + file = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY, + current_cred()); if (IS_ERR(file)) { mconsole_reply(req, "Failed to open file", 1, 0); goto out_kill; diff --git a/arch/x86/ia32/ia32_aout.c b/arch/x86/ia32/ia32_aout.c index 127ec3f0721..2a4d073d2cf 100644 --- a/arch/x86/ia32/ia32_aout.c +++ b/arch/x86/ia32/ia32_aout.c @@ -327,7 +327,7 @@ static int load_aout_binary(struct linux_binprm *bprm, struct pt_regs *regs) current->mm->cached_hole_size = 0; current->mm->mmap = NULL; - compute_creds(bprm); + install_exec_creds(bprm); current->flags &= ~PF_FORKNOEXEC; if (N_MAGIC(ex) == OMAGIC) { diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 31e8730fa24..3a1b6ef4f05 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -393,7 +393,7 @@ static void show_fault_oops(struct pt_regs *regs, unsigned long error_code, if (pte && pte_present(*pte) && !pte_exec(*pte)) printk(KERN_CRIT "kernel tried to execute " "NX-protected page - exploit attempt? " - "(uid: %d)\n", current->uid); + "(uid: %d)\n", current_uid()); } #endif diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 5c4ee70d5cf..fb06ed65921 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -936,8 +936,10 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) { int err; struct loop_func_table *xfer; + uid_t uid = current_uid(); - if (lo->lo_encrypt_key_size && lo->lo_key_owner != current->uid && + if (lo->lo_encrypt_key_size && + lo->lo_key_owner != uid && !capable(CAP_SYS_ADMIN)) return -EPERM; if (lo->lo_state != Lo_bound) @@ -992,7 +994,7 @@ loop_set_status(struct loop_device *lo, const struct loop_info64 *info) if (info->lo_encrypt_key_size) { memcpy(lo->lo_encrypt_key, info->lo_encrypt_key, info->lo_encrypt_key_size); - lo->lo_key_owner = current->uid; + lo->lo_key_owner = uid; } return 0; diff --git a/drivers/char/tty_audit.c b/drivers/char/tty_audit.c index 5787249934c..34ab6d798f8 100644 --- a/drivers/char/tty_audit.c +++ b/drivers/char/tty_audit.c @@ -67,6 +67,29 @@ static void tty_audit_buf_put(struct tty_audit_buf *buf) tty_audit_buf_free(buf); } +static void tty_audit_log(const char *description, struct task_struct *tsk, + uid_t loginuid, unsigned sessionid, int major, + int minor, unsigned char *data, size_t size) +{ + struct audit_buffer *ab; + + ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_TTY); + if (ab) { + char name[sizeof(tsk->comm)]; + uid_t uid = task_uid(tsk); + + audit_log_format(ab, "%s pid=%u uid=%u auid=%u ses=%u " + "major=%d minor=%d comm=", description, + tsk->pid, uid, loginuid, sessionid, + major, minor); + get_task_comm(name, tsk); + audit_log_untrustedstring(ab, name); + audit_log_format(ab, " data="); + audit_log_n_hex(ab, data, size); + audit_log_end(ab); + } +} + /** * tty_audit_buf_push - Push buffered data out * @@ -77,25 +100,12 @@ static void tty_audit_buf_push(struct task_struct *tsk, uid_t loginuid, unsigned int sessionid, struct tty_audit_buf *buf) { - struct audit_buffer *ab; - if (buf->valid == 0) return; if (audit_enabled == 0) return; - ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_TTY); - if (ab) { - char name[sizeof(tsk->comm)]; - - audit_log_format(ab, "tty pid=%u uid=%u auid=%u ses=%u " - "major=%d minor=%d comm=", tsk->pid, tsk->uid, - loginuid, sessionid, buf->major, buf->minor); - get_task_comm(name, tsk); - audit_log_untrustedstring(ab, name); - audit_log_format(ab, " data="); - audit_log_n_hex(ab, buf->data, buf->valid); - audit_log_end(ab); - } + tty_audit_log("tty", tsk, loginuid, sessionid, buf->major, buf->minor, + buf->data, buf->valid); buf->valid = 0; } @@ -149,6 +159,42 @@ void tty_audit_fork(struct signal_struct *sig) sig->tty_audit_buf = NULL; } +/** + * tty_audit_tiocsti - Log TIOCSTI + */ +void tty_audit_tiocsti(struct tty_struct *tty, char ch) +{ + struct tty_audit_buf *buf; + int major, minor, should_audit; + + spin_lock_irq(¤t->sighand->siglock); + should_audit = current->signal->audit_tty; + buf = current->signal->tty_audit_buf; + if (buf) + atomic_inc(&buf->count); + spin_unlock_irq(¤t->sighand->siglock); + + major = tty->driver->major; + minor = tty->driver->minor_start + tty->index; + if (buf) { + mutex_lock(&buf->mutex); + if (buf->major == major && buf->minor == minor) + tty_audit_buf_push_current(buf); + mutex_unlock(&buf->mutex); + tty_audit_buf_put(buf); + } + + if (should_audit && audit_enabled) { + uid_t auid; + unsigned int sessionid; + + auid = audit_get_loginuid(current); + sessionid = audit_get_sessionid(current); + tty_audit_log("ioctl=TIOCSTI", current, auid, sessionid, major, + minor, &ch, 1); + } +} + /** * tty_audit_push_task - Flush task's pending audit data */ diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c index 1412a8d1e58..db15f9ba7c0 100644 --- a/drivers/char/tty_io.c +++ b/drivers/char/tty_io.c @@ -2018,6 +2018,7 @@ static int tiocsti(struct tty_struct *tty, char __user *p) return -EPERM; if (get_user(ch, p)) return -EFAULT; + tty_audit_tiocsti(tty, ch); ld = tty_ldisc_ref_wait(tty); ld->ops->receive_buf(tty, &ch, &mbz, 1); tty_ldisc_deref(ld); diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index 5c9f67f98d1..c5afc98e267 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -106,6 +106,7 @@ void proc_id_connector(struct task_struct *task, int which_id) struct proc_event *ev; __u8 buffer[CN_PROC_MSG_SIZE]; struct timespec ts; + const struct cred *cred; if (atomic_read(&proc_event_num_listeners) < 1) return; @@ -115,14 +116,19 @@ void proc_id_connector(struct task_struct *task, int which_id) ev->what = which_id; ev->event_data.id.process_pid = task->pid; ev->event_data.id.process_tgid = task->tgid; + rcu_read_lock(); + cred = __task_cred(task); if (which_id == PROC_EVENT_UID) { - ev->event_data.id.r.ruid = task->uid; - ev->event_data.id.e.euid = task->euid; + ev->event_data.id.r.ruid = cred->uid; + ev->event_data.id.e.euid = cred->euid; } else if (which_id == PROC_EVENT_GID) { - ev->event_data.id.r.rgid = task->gid; - ev->event_data.id.e.egid = task->egid; - } else + ev->event_data.id.r.rgid = cred->gid; + ev->event_data.id.e.egid = cred->egid; + } else { + rcu_read_unlock(); return; + } + rcu_read_unlock(); get_seq(&msg->seq, &ev->cpu); ktime_get_ts(&ts); /* get high res monotonic timestamp */ put_unaligned(timespec_to_ns(&ts), (__u64 *)&ev->timestamp_ns); diff --git a/drivers/isdn/capi/capifs.c b/drivers/isdn/capi/capifs.c index 550e80f390a..0aa66ec4cbd 100644 --- a/drivers/isdn/capi/capifs.c +++ b/drivers/isdn/capi/capifs.c @@ -156,8 +156,8 @@ void capifs_new_ncci(unsigned int number, dev_t device) if (!inode) return; inode->i_ino = number+2; - inode->i_uid = config.setuid ? config.uid : current->fsuid; - inode->i_gid = config.setgid ? config.gid : current->fsgid; + inode->i_uid = config.setuid ? config.uid : current_fsuid(); + inode->i_gid = config.setgid ? config.gid : current_fsgid(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; init_special_inode(inode, S_IFCHR|config.mode, device); //inode->i_op = &capifs_file_inode_operations; diff --git a/drivers/isdn/hysdn/hysdn_procconf.c b/drivers/isdn/hysdn/hysdn_procconf.c index 484299b031f..8f9f4912de3 100644 --- a/drivers/isdn/hysdn/hysdn_procconf.c +++ b/drivers/isdn/hysdn/hysdn_procconf.c @@ -246,7 +246,8 @@ hysdn_conf_open(struct inode *ino, struct file *filep) } if (card->debug_flags & (LOG_PROC_OPEN | LOG_PROC_ALL)) hysdn_addlog(card, "config open for uid=%d gid=%d mode=0x%x", - filep->f_uid, filep->f_gid, filep->f_mode); + filep->f_cred->fsuid, filep->f_cred->fsgid, + filep->f_mode); if ((filep->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_WRITE) { /* write only access -> write boot file or conf line */ @@ -331,7 +332,8 @@ hysdn_conf_close(struct inode *ino, struct file *filep) } if (card->debug_flags & (LOG_PROC_OPEN | LOG_PROC_ALL)) hysdn_addlog(card, "config close for uid=%d gid=%d mode=0x%x", - filep->f_uid, filep->f_gid, filep->f_mode); + filep->f_cred->fsuid, filep->f_cred->fsgid, + filep->f_mode); if ((filep->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_WRITE) { /* write only access -> write boot file or conf line */ diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 33b6d1b122f..55dc70c6b4d 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -702,6 +702,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) struct tun_net *tn; struct tun_struct *tun; struct net_device *dev; + const struct cred *cred = current_cred(); int err; tn = net_generic(net, tun_net_id); @@ -712,11 +713,12 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr) /* Check permissions */ if (((tun->owner != -1 && - current->euid != tun->owner) || + cred->euid != tun->owner) || (tun->group != -1 && - current->egid != tun->group)) && - !capable(CAP_NET_ADMIN)) + cred->egid != tun->group)) && + !capable(CAP_NET_ADMIN)) { return -EPERM; + } } else if (__dev_get_by_name(net, ifr->ifr_name)) return -EINVAL; diff --git a/drivers/usb/core/devio.c b/drivers/usb/core/devio.c index 2bccefebff1..aa79280df15 100644 --- a/drivers/usb/core/devio.c +++ b/drivers/usb/core/devio.c @@ -574,6 +574,7 @@ static int usbdev_open(struct inode *inode, struct file *file) { struct usb_device *dev = NULL; struct dev_state *ps; + const struct cred *cred = current_cred(); int ret; lock_kernel(); @@ -617,8 +618,8 @@ static int usbdev_open(struct inode *inode, struct file *file) init_waitqueue_head(&ps->wait); ps->discsignr = 0; ps->disc_pid = get_pid(task_pid(current)); - ps->disc_uid = current->uid; - ps->disc_euid = current->euid; + ps->disc_uid = cred->uid; + ps->disc_euid = cred->euid; ps->disccontext = NULL; ps->ifclaimed = 0; security_task_getsecid(current, &ps->secid); @@ -967,6 +968,7 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb, struct usb_host_endpoint *ep; struct async *as; struct usb_ctrlrequest *dr = NULL; + const struct cred *cred = current_cred(); unsigned int u, totlen, isofrmlen; int ret, ifnum = -1; int is_in; @@ -1174,8 +1176,8 @@ static int proc_do_submiturb(struct dev_state *ps, struct usbdevfs_urb *uurb, as->signr = uurb->signr; as->ifnum = ifnum; as->pid = get_pid(task_pid(current)); - as->uid = current->uid; - as->euid = current->euid; + as->uid = cred->uid; + as->euid = cred->euid; security_task_getsecid(current, &as->secid); if (!is_in) { if (copy_from_user(as->urb->transfer_buffer, uurb->buffer, diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index 94632264dcc..185be760833 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -277,8 +277,8 @@ static struct inode *usbfs_get_inode (struct super_block *sb, int mode, dev_t de if (inode) { inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; switch (mode & S_IFMT) { diff --git a/fs/9p/fid.c b/fs/9p/fid.c index 2a983d49d19..14d94420457 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -120,7 +120,7 @@ struct p9_fid *v9fs_fid_lookup(struct dentry *dentry) switch (access) { case V9FS_ACCESS_SINGLE: case V9FS_ACCESS_USER: - uid = current->fsuid; + uid = current_fsuid(); any = 0; break; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 2dfcf5487ef..81f8bbf12f9 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -215,8 +215,8 @@ struct inode *v9fs_get_inode(struct super_block *sb, int mode) inode = new_inode(sb); if (inode) { inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_rdev = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index d6cb1a0ca72..93212e40221 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -113,8 +113,8 @@ static int v9fs_get_sb(struct file_system_type *fs_type, int flags, struct v9fs_session_info *v9ses = NULL; struct p9_wstat *st = NULL; int mode = S_IRWXUGO | S_ISVTX; - uid_t uid = current->fsuid; - gid_t gid = current->fsgid; + uid_t uid = current_fsuid(); + gid_t gid = current_fsgid(); struct p9_fid *fid; int retval = 0; diff --git a/fs/affs/inode.c b/fs/affs/inode.c index a13b334a391..415d9c67ac1 100644 --- a/fs/affs/inode.c +++ b/fs/affs/inode.c @@ -293,8 +293,8 @@ affs_new_inode(struct inode *dir) mark_buffer_dirty_inode(bh, inode); affs_brelse(bh); - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_ino = block; inode->i_nlink = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; diff --git a/fs/affs/super.c b/fs/affs/super.c index 8989c93193e..a19d64b582a 100644 --- a/fs/affs/super.c +++ b/fs/affs/super.c @@ -163,8 +163,8 @@ parse_options(char *options, uid_t *uid, gid_t *gid, int *mode, int *reserved, s /* Fill in defaults */ - *uid = current->uid; - *gid = current->gid; + *uid = current_uid(); + *gid = current_gid(); *reserved = 2; *root = -1; *blocksize = -1; diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 3662dd44896..c16d9be1b01 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -154,8 +154,8 @@ static struct inode *anon_inode_mkinode(void) */ inode->i_state = I_DIRTY; inode->i_mode = S_IRUSR | S_IWUSR; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; return inode; } diff --git a/fs/attr.c b/fs/attr.c index 7a83819f6ba..f4360192a93 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -29,13 +29,13 @@ int inode_change_ok(struct inode *inode, struct iattr *attr) /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && - (current->fsuid != inode->i_uid || + (current_fsuid() != inode->i_uid || attr->ia_uid != inode->i_uid) && !capable(CAP_CHOWN)) goto error; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && - (current->fsuid != inode->i_uid || + (current_fsuid() != inode->i_uid || (!in_group_p(attr->ia_gid) && attr->ia_gid != inode->i_gid)) && !capable(CAP_CHOWN)) goto error; diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c index b70eea1e8c5..c773680d5c6 100644 --- a/fs/autofs/inode.c +++ b/fs/autofs/inode.c @@ -76,8 +76,8 @@ static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid, substring_t args[MAX_OPT_ARGS]; int option; - *uid = current->uid; - *gid = current->gid; + *uid = current_uid(); + *gid = current_gid(); *pgrp = task_pgrp_nr(current); *minproto = *maxproto = AUTOFS_PROTO_VERSION; diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c index 33bf8cbfd05..63b7c7afe8d 100644 --- a/fs/autofs4/dev-ioctl.c +++ b/fs/autofs4/dev-ioctl.c @@ -308,7 +308,8 @@ static int autofs_dev_ioctl_open_mountpoint(const char *path, dev_t devid) goto out; } - filp = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY); + filp = dentry_open(nd.path.dentry, nd.path.mnt, O_RDONLY, + current_cred()); if (IS_ERR(filp)) { err = PTR_ERR(filp); goto out; diff --git a/fs/autofs4/inode.c b/fs/autofs4/inode.c index c7e65bb30ba..7b19802cfef 100644 --- a/fs/autofs4/inode.c +++ b/fs/autofs4/inode.c @@ -235,8 +235,8 @@ static int parse_options(char *options, int *pipefd, uid_t *uid, gid_t *gid, substring_t args[MAX_OPT_ARGS]; int option; - *uid = current->uid; - *gid = current->gid; + *uid = current_uid(); + *gid = current_gid(); *pgrp = task_pgrp_nr(current); *minproto = AUTOFS_MIN_PROTO_VERSION; diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c index 4b67c2a2d77..e02cc8ae5eb 100644 --- a/fs/autofs4/waitq.c +++ b/fs/autofs4/waitq.c @@ -391,8 +391,8 @@ int autofs4_wait(struct autofs_sb_info *sbi, struct dentry *dentry, memcpy(&wq->name, &qstr, sizeof(struct qstr)); wq->dev = autofs4_get_dev(sbi); wq->ino = autofs4_get_ino(sbi); - wq->uid = current->uid; - wq->gid = current->gid; + wq->uid = current_uid(); + wq->gid = current_gid(); wq->pid = current->pid; wq->tgid = current->tgid; wq->status = -EINTR; /* Status return if interrupted */ diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index daae463068e..4dd1b623f93 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -106,8 +106,8 @@ static int bfs_create(struct inode *dir, struct dentry *dentry, int mode, } set_bit(ino, info->si_imap); info->si_freei--; - inode->i_uid = current->fsuid; - inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current_fsgid(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; inode->i_blocks = 0; inode->i_op = &bfs_file_inops; diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c index 204cfd1d767..f1f3f4192a6 100644 --- a/fs/binfmt_aout.c +++ b/fs/binfmt_aout.c @@ -320,7 +320,7 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs) current->mm->free_area_cache = current->mm->mmap_base; current->mm->cached_hole_size = 0; - compute_creds(bprm); + install_exec_creds(bprm); current->flags &= ~PF_FORKNOEXEC; #ifdef __sparc__ if (N_MAGIC(ex) == NMAGIC) { diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 8fcfa398d35..f458c1217c5 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -157,7 +157,7 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, int items; elf_addr_t *elf_info; int ei_index = 0; - struct task_struct *tsk = current; + const struct cred *cred = current_cred(); struct vm_area_struct *vma; /* @@ -223,10 +223,10 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec, NEW_AUX_ENT(AT_BASE, interp_load_addr); NEW_AUX_ENT(AT_FLAGS, 0); NEW_AUX_ENT(AT_ENTRY, exec->e_entry); - NEW_AUX_ENT(AT_UID, tsk->uid); - NEW_AUX_ENT(AT_EUID, tsk->euid); - NEW_AUX_ENT(AT_GID, tsk->gid); - NEW_AUX_ENT(AT_EGID, tsk->egid); + NEW_AUX_ENT(AT_UID, cred->uid); + NEW_AUX_ENT(AT_EUID, cred->euid); + NEW_AUX_ENT(AT_GID, cred->gid); + NEW_AUX_ENT(AT_EGID, cred->egid); NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm)); NEW_AUX_ENT(AT_EXECFN, bprm->exec); if (k_platform) { @@ -956,7 +956,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) } #endif /* ARCH_HAS_SETUP_ADDITIONAL_PAGES */ - compute_creds(bprm); + install_exec_creds(bprm); current->flags &= ~PF_FORKNOEXEC; retval = create_elf_tables(bprm, &loc->elf_ex, load_addr, interp_load_addr); @@ -1361,6 +1361,7 @@ static void fill_prstatus(struct elf_prstatus *prstatus, static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, struct mm_struct *mm) { + const struct cred *cred; unsigned int i, len; /* first copy the parameters from user space */ @@ -1388,8 +1389,11 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, psinfo->pr_zomb = psinfo->pr_sname == 'Z'; psinfo->pr_nice = task_nice(p); psinfo->pr_flag = p->flags; - SET_UID(psinfo->pr_uid, p->uid); - SET_GID(psinfo->pr_gid, p->gid); + rcu_read_lock(); + cred = __task_cred(p); + SET_UID(psinfo->pr_uid, cred->uid); + SET_GID(psinfo->pr_gid, cred->gid); + rcu_read_unlock(); strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname)); return 0; diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 5b5424cb339..aa5b43205e3 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -404,7 +404,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, current->mm->start_stack = current->mm->start_brk + stack_size; #endif - compute_creds(bprm); + install_exec_creds(bprm); current->flags &= ~PF_FORKNOEXEC; if (create_elf_fdpic_tables(bprm, current->mm, &exec_params, &interp_params) < 0) @@ -475,6 +475,7 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, struct elf_fdpic_params *exec_params, struct elf_fdpic_params *interp_params) { + const struct cred *cred = current_cred(); unsigned long sp, csp, nitems; elf_caddr_t __user *argv, *envp; size_t platform_len = 0, len; @@ -623,10 +624,10 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm, NEW_AUX_ENT(AT_BASE, interp_params->elfhdr_addr); NEW_AUX_ENT(AT_FLAGS, 0); NEW_AUX_ENT(AT_ENTRY, exec_params->entry_addr); - NEW_AUX_ENT(AT_UID, (elf_addr_t) current->uid); - NEW_AUX_ENT(AT_EUID, (elf_addr_t) current->euid); - NEW_AUX_ENT(AT_GID, (elf_addr_t) current->gid); - NEW_AUX_ENT(AT_EGID, (elf_addr_t) current->egid); + NEW_AUX_ENT(AT_UID, (elf_addr_t) cred->uid); + NEW_AUX_ENT(AT_EUID, (elf_addr_t) cred->euid); + NEW_AUX_ENT(AT_GID, (elf_addr_t) cred->gid); + NEW_AUX_ENT(AT_EGID, (elf_addr_t) cred->egid); NEW_AUX_ENT(AT_SECURE, security_bprm_secureexec(bprm)); NEW_AUX_ENT(AT_EXECFN, bprm->exec); @@ -1413,6 +1414,7 @@ static void fill_prstatus(struct elf_prstatus *prstatus, static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, struct mm_struct *mm) { + const struct cred *cred; unsigned int i, len; /* first copy the parameters from user space */ @@ -1440,8 +1442,11 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p, psinfo->pr_zomb = psinfo->pr_sname == 'Z'; psinfo->pr_nice = task_nice(p); psinfo->pr_flag = p->flags; - SET_UID(psinfo->pr_uid, p->uid); - SET_GID(psinfo->pr_gid, p->gid); + rcu_read_lock(); + cred = __task_cred(p); + SET_UID(psinfo->pr_uid, cred->uid); + SET_GID(psinfo->pr_gid, cred->gid); + rcu_read_unlock(); strncpy(psinfo->pr_fname, p->comm, sizeof(psinfo->pr_fname)); return 0; diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index ccb781a6a80..7bbd5c6b372 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -880,7 +880,7 @@ static int load_flat_binary(struct linux_binprm * bprm, struct pt_regs * regs) (libinfo.lib_list[j].loaded)? libinfo.lib_list[j].start_data:UNLOADED_LIB; - compute_creds(bprm); + install_exec_creds(bprm); current->flags &= ~PF_FORKNOEXEC; set_binfmt(&flat_format); diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c index 74e587a5279..08644a61616 100644 --- a/fs/binfmt_som.c +++ b/fs/binfmt_som.c @@ -255,7 +255,7 @@ load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs) kfree(hpuxhdr); set_binfmt(&som_format); - compute_creds(bprm); + install_exec_creds(bprm); setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT); create_som_tables(bprm); diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h index 877c85409f1..1e7b87497f2 100644 --- a/fs/cifs/cifs_fs_sb.h +++ b/fs/cifs/cifs_fs_sb.h @@ -19,7 +19,7 @@ #define _CIFS_FS_SB_H #define CIFS_MOUNT_NO_PERM 1 /* do not do client vfs_perm check */ -#define CIFS_MOUNT_SET_UID 2 /* set current->euid in create etc. */ +#define CIFS_MOUNT_SET_UID 2 /* set current's euid in create etc. */ #define CIFS_MOUNT_SERVER_INUM 4 /* inode numbers from uniqueid from server */ #define CIFS_MOUNT_DIRECT_IO 8 /* do not write nor read through page cache */ #define CIFS_MOUNT_NO_XATTR 0x10 /* if set - disable xattr support */ diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h index 6f21ecb85ce..9d8b978137a 100644 --- a/fs/cifs/cifsproto.h +++ b/fs/cifs/cifsproto.h @@ -39,7 +39,7 @@ extern int smb_send(struct socket *, struct smb_hdr *, unsigned int /* length */ , struct sockaddr *, bool); extern unsigned int _GetXid(void); extern void _FreeXid(unsigned int); -#define GetXid() (int)_GetXid(); cFYI(1,("CIFS VFS: in %s as Xid: %d with uid: %d",__func__, xid,current->fsuid)); +#define GetXid() (int)_GetXid(); cFYI(1,("CIFS VFS: in %s as Xid: %d with uid: %d",__func__, xid,current_fsuid())); #define FreeXid(curr_xid) {_FreeXid(curr_xid); cFYI(1,("CIFS VFS: leaving %s (xid = %d) rc = %d",__func__,curr_xid,(int)rc));} extern char *build_path_from_dentry(struct dentry *); extern char *build_wildcard_path_from_dentry(struct dentry *direntry); diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index c7d34171458..683dee4d2f7 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -836,8 +836,8 @@ cifs_parse_mount_options(char *options, const char *devname, /* null target name indicates to use *SMBSERVR default called name if we end up sending RFC1001 session initialize */ vol->target_rfc1001_name[0] = 0; - vol->linux_uid = current->uid; /* current->euid instead? */ - vol->linux_gid = current->gid; + vol->linux_uid = current_uid(); /* use current_euid() instead? */ + vol->linux_gid = current_gid(); vol->dir_mode = S_IRWXUGO; /* 2767 perms indicate mandatory locking support */ vol->file_mode = (S_IRWXUGO | S_ISGID) & (~S_IXGRP); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index e962e75e6f7..2f02c52db66 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -235,11 +235,11 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, }; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { - args.uid = (__u64) current->fsuid; + args.uid = (__u64) current_fsuid(); if (inode->i_mode & S_ISGID) args.gid = (__u64) inode->i_gid; else - args.gid = (__u64) current->fsgid; + args.gid = (__u64) current_fsgid(); } else { args.uid = NO_CHANGE_64; args.gid = NO_CHANGE_64; @@ -271,13 +271,13 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode, if ((oplock & CIFS_CREATE_ACTION) && (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID)) { - newinode->i_uid = current->fsuid; + newinode->i_uid = current_fsuid(); if (inode->i_mode & S_ISGID) newinode->i_gid = inode->i_gid; else newinode->i_gid = - current->fsgid; + current_fsgid(); } } } @@ -375,8 +375,8 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode, .device = device_number, }; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { - args.uid = (__u64) current->fsuid; - args.gid = (__u64) current->fsgid; + args.uid = (__u64) current_fsuid(); + args.gid = (__u64) current_fsgid(); } else { args.uid = NO_CHANGE_64; args.gid = NO_CHANGE_64; diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c index ff8c68de4a9..8b7305e73d7 100644 --- a/fs/cifs/inode.c +++ b/fs/cifs/inode.c @@ -1143,11 +1143,11 @@ mkdir_get_info: .device = 0, }; if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { - args.uid = (__u64)current->fsuid; + args.uid = (__u64)current_fsuid(); if (inode->i_mode & S_ISGID) args.gid = (__u64)inode->i_gid; else - args.gid = (__u64)current->fsgid; + args.gid = (__u64)current_fsgid(); } else { args.uid = NO_CHANGE_64; args.gid = NO_CHANGE_64; @@ -1184,13 +1184,13 @@ mkdir_get_info: if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID) { direntry->d_inode->i_uid = - current->fsuid; + current_fsuid(); if (inode->i_mode & S_ISGID) direntry->d_inode->i_gid = inode->i_gid; else direntry->d_inode->i_gid = - current->fsgid; + current_fsgid(); } } } diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c index 0088a5b5256..f94650683a0 100644 --- a/fs/cifs/ioctl.c +++ b/fs/cifs/ioctl.c @@ -65,7 +65,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg) switch (command) { case CIFS_IOC_CHECKUMOUNT: cFYI(1, ("User unmount attempted")); - if (cifs_sb->mnt_uid == current->uid) + if (cifs_sb->mnt_uid == current_uid()) rc = 0; else { rc = -EACCES; diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 9ee3f689c2b..8a82d076450 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -338,13 +338,13 @@ header_assemble(struct smb_hdr *buffer, char smb_command /* command */ , /* BB Add support for establishing new tCon and SMB Session */ /* with userid/password pairs found on the smb session */ /* for other target tcp/ip addresses BB */ - if (current->fsuid != treeCon->ses->linux_uid) { + if (current_fsuid() != treeCon->ses->linux_uid) { cFYI(1, ("Multiuser mode and UID " "did not match tcon uid")); read_lock(&cifs_tcp_ses_lock); list_for_each(temp_item, &treeCon->ses->server->smb_ses_list) { ses = list_entry(temp_item, struct cifsSesInfo, smb_ses_list); - if (ses->linux_uid == current->fsuid) { + if (ses->linux_uid == current_fsuid()) { if (ses->server == treeCon->ses->server) { cFYI(1, ("found matching uid substitute right smb_uid")); buffer->Uid = ses->Suid; diff --git a/fs/coda/cache.c b/fs/coda/cache.c index 8a2370341c7..a5bf5771a22 100644 --- a/fs/coda/cache.c +++ b/fs/coda/cache.c @@ -32,8 +32,8 @@ void coda_cache_enter(struct inode *inode, int mask) struct coda_inode_info *cii = ITOC(inode); cii->c_cached_epoch = atomic_read(&permission_epoch); - if (cii->c_uid != current->fsuid) { - cii->c_uid = current->fsuid; + if (cii->c_uid != current_fsuid()) { + cii->c_uid = current_fsuid(); cii->c_cached_perm = mask; } else cii->c_cached_perm |= mask; @@ -60,7 +60,7 @@ int coda_cache_check(struct inode *inode, int mask) int hit; hit = (mask & cii->c_cached_perm) == mask && - cii->c_uid == current->fsuid && + cii->c_uid == current_fsuid() && cii->c_cached_epoch == atomic_read(&permission_epoch); return hit; diff --git a/fs/coda/file.c b/fs/coda/file.c index 29137ff3ca6..466303db2df 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -174,7 +175,7 @@ int coda_release(struct inode *coda_inode, struct file *coda_file) BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC); err = venus_close(coda_inode->i_sb, coda_i2f(coda_inode), - coda_flags, coda_file->f_uid); + coda_flags, coda_file->f_cred->fsuid); host_inode = cfi->cfi_container->f_path.dentry->d_inode; cii = ITOC(coda_inode); diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c index ce432bca95d..c274d949179 100644 --- a/fs/coda/upcall.c +++ b/fs/coda/upcall.c @@ -52,7 +52,7 @@ static void *alloc_upcall(int opcode, int size) inp->ih.opcode = opcode; inp->ih.pid = current->pid; inp->ih.pgid = task_pgrp_nr(current); - inp->ih.uid = current->fsuid; + inp->ih.uid = current_fsuid(); return (void*)inp; } diff --git a/fs/compat.c b/fs/compat.c index e5f49f53850..d1ece79b641 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -1393,10 +1393,20 @@ int compat_do_execve(char * filename, if (!bprm) goto out_ret; + retval = mutex_lock_interruptible(¤t->cred_exec_mutex); + if (retval < 0) + goto out_free; + + retval = -ENOMEM; + bprm->cred = prepare_exec_creds(); + if (!bprm->cred) + goto out_unlock; + check_unsafe_exec(bprm); + file = open_exec(filename); retval = PTR_ERR(file); if (IS_ERR(file)) - goto out_kfree; + goto out_unlock; sched_exec(); @@ -1410,14 +1420,10 @@ int compat_do_execve(char * filename, bprm->argc = compat_count(argv, MAX_ARG_STRINGS); if ((retval = bprm->argc) < 0) - goto out_mm; + goto out; bprm->envc = compat_count(envp, MAX_ARG_STRINGS); if ((retval = bprm->envc) < 0) - goto out_mm; - - retval = security_bprm_alloc(bprm); - if (retval) goto out; retval = prepare_binprm(bprm); @@ -1438,19 +1444,16 @@ int compat_do_execve(char * filename, goto out; retval = search_binary_handler(bprm, regs); - if (retval >= 0) { - /* execve success */ - security_bprm_free(bprm); - acct_update_integrals(current); - free_bprm(bprm); - return retval; - } + if (retval < 0) + goto out; + + /* execve succeeded */ + mutex_unlock(¤t->cred_exec_mutex); + acct_update_integrals(current); + free_bprm(bprm); + return retval; out: - if (bprm->security) - security_bprm_free(bprm); - -out_mm: if (bprm->mm) mmput(bprm->mm); @@ -1460,7 +1463,10 @@ out_file: fput(bprm->file); } -out_kfree: +out_unlock: + mutex_unlock(¤t->cred_exec_mutex); + +out_free: free_bprm(bprm); out_ret: diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 4a714f6c1be..5d61b7c06e1 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -222,8 +222,8 @@ int devpts_pty_new(struct inode *ptmx_inode, struct tty_struct *tty) return -ENOMEM; inode->i_ino = number+2; - inode->i_uid = config.setuid ? config.uid : current->fsuid; - inode->i_gid = config.setgid ? config.gid : current->fsgid; + inode->i_uid = config.setuid ? config.uid : current_fsuid(); + inode->i_gid = config.setgid ? config.gid : current_fsgid(); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME; init_special_inode(inode, S_IFCHR|config.mode, device); inode->i_private = tty; diff --git a/fs/dquot.c b/fs/dquot.c index 5e95261005b..c237ccc8581 100644 --- a/fs/dquot.c +++ b/fs/dquot.c @@ -874,7 +874,7 @@ static inline int need_print_warning(struct dquot *dquot) switch (dquot->dq_type) { case USRQUOTA: - return current->fsuid == dquot->dq_id; + return current_fsuid() == dquot->dq_id; case GRPQUOTA: return in_group_p(dquot->dq_id); } @@ -981,7 +981,7 @@ static void send_warning(const struct dquot *dquot, const char warntype) MINOR(dquot->dq_sb->s_dev)); if (ret) goto attr_err_out; - ret = nla_put_u64(skb, QUOTA_NL_A_CAUSED_ID, current->user->uid); + ret = nla_put_u64(skb, QUOTA_NL_A_CAUSED_ID, current_uid()); if (ret) goto attr_err_out; genlmsg_end(skb, msg_head); diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h index 3504cf9df35..a75026d35d1 100644 --- a/fs/ecryptfs/ecryptfs_kernel.h +++ b/fs/ecryptfs/ecryptfs_kernel.h @@ -691,7 +691,8 @@ int ecryptfs_init_kthread(void); void ecryptfs_destroy_kthread(void); int ecryptfs_privileged_open(struct file **lower_file, struct dentry *lower_dentry, - struct vfsmount *lower_mnt); + struct vfsmount *lower_mnt, + const struct cred *cred); int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry); #endif /* #ifndef ECRYPTFS_KERNEL_H */ diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c index c440c6b58b2..c6d7a4d748a 100644 --- a/fs/ecryptfs/kthread.c +++ b/fs/ecryptfs/kthread.c @@ -73,7 +73,7 @@ static int ecryptfs_threadfn(void *ignored) mntget(req->lower_mnt); (*req->lower_file) = dentry_open( req->lower_dentry, req->lower_mnt, - (O_RDWR | O_LARGEFILE)); + (O_RDWR | O_LARGEFILE), current_cred()); req->flags |= ECRYPTFS_REQ_PROCESSED; } wake_up(&req->wait); @@ -132,7 +132,8 @@ void ecryptfs_destroy_kthread(void) */ int ecryptfs_privileged_open(struct file **lower_file, struct dentry *lower_dentry, - struct vfsmount *lower_mnt) + struct vfsmount *lower_mnt, + const struct cred *cred) { struct ecryptfs_open_req *req; int rc = 0; @@ -143,7 +144,7 @@ int ecryptfs_privileged_open(struct file **lower_file, dget(lower_dentry); mntget(lower_mnt); (*lower_file) = dentry_open(lower_dentry, lower_mnt, - (O_RDWR | O_LARGEFILE)); + (O_RDWR | O_LARGEFILE), cred); if (!IS_ERR(*lower_file)) goto out; req = kmem_cache_alloc(ecryptfs_open_req_cache, GFP_KERNEL); @@ -184,7 +185,7 @@ int ecryptfs_privileged_open(struct file **lower_file, dget(lower_dentry); mntget(lower_mnt); (*lower_file) = dentry_open(lower_dentry, lower_mnt, - (O_RDONLY | O_LARGEFILE)); + (O_RDONLY | O_LARGEFILE), cred); if (IS_ERR(*lower_file)) { rc = PTR_ERR(*req->lower_file); (*lower_file) = NULL; diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c index 64d2ba980df..fd630713c5c 100644 --- a/fs/ecryptfs/main.c +++ b/fs/ecryptfs/main.c @@ -115,6 +115,7 @@ void __ecryptfs_printk(const char *fmt, ...) */ int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry) { + const struct cred *cred = current_cred(); struct ecryptfs_inode_info *inode_info = ecryptfs_inode_to_private(ecryptfs_dentry->d_inode); int rc = 0; @@ -127,7 +128,7 @@ int ecryptfs_init_persistent_file(struct dentry *ecryptfs_dentry) lower_dentry = ecryptfs_dentry_to_lower(ecryptfs_dentry); rc = ecryptfs_privileged_open(&inode_info->lower_file, - lower_dentry, lower_mnt); + lower_dentry, lower_mnt, cred); if (rc || IS_ERR(inode_info->lower_file)) { printk(KERN_ERR "Error opening lower persistent file " "for lower_dentry [0x%p] and lower_mnt [0x%p]; " diff --git a/fs/ecryptfs/messaging.c b/fs/ecryptfs/messaging.c index c6983978a31..6913f727624 100644 --- a/fs/ecryptfs/messaging.c +++ b/fs/ecryptfs/messaging.c @@ -360,7 +360,8 @@ int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t euid, struct ecryptfs_msg_ctx *msg_ctx; size_t msg_size; struct nsproxy *nsproxy; - struct user_namespace *current_user_ns; + struct user_namespace *tsk_user_ns; + uid_t ctx_euid; int rc; if (msg->index >= ecryptfs_message_buf_len) { @@ -384,9 +385,9 @@ int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t euid, mutex_unlock(&ecryptfs_daemon_hash_mux); goto wake_up; } - current_user_ns = nsproxy->user_ns; - rc = ecryptfs_find_daemon_by_euid(&daemon, msg_ctx->task->euid, - current_user_ns); + tsk_user_ns = __task_cred(msg_ctx->task)->user->user_ns; + ctx_euid = task_euid(msg_ctx->task); + rc = ecryptfs_find_daemon_by_euid(&daemon, ctx_euid, tsk_user_ns); rcu_read_unlock(); mutex_unlock(&ecryptfs_daemon_hash_mux); if (rc) { @@ -394,28 +395,28 @@ int ecryptfs_process_response(struct ecryptfs_message *msg, uid_t euid, printk(KERN_WARNING "%s: User [%d] received a " "message response from process [0x%p] but does " "not have a registered daemon\n", __func__, - msg_ctx->task->euid, pid); + ctx_euid, pid); goto wake_up; } - if (msg_ctx->task->euid != euid) { + if (ctx_euid != euid) { rc = -EBADMSG; printk(KERN_WARNING "%s: Received message from user " "[%d]; expected message from user [%d]\n", __func__, - euid, msg_ctx->task->euid); + euid, ctx_euid); goto unlock; } - if (current_user_ns != user_ns) { + if (tsk_user_ns != user_ns) { rc = -EBADMSG; printk(KERN_WARNING "%s: Received message from user_ns " "[0x%p]; expected message from user_ns [0x%p]\n", - __func__, user_ns, nsproxy->user_ns); + __func__, user_ns, tsk_user_ns); goto unlock; } if (daemon->pid != pid) { rc = -EBADMSG; printk(KERN_ERR "%s: User [%d] sent a message response " "from an unrecognized process [0x%p]\n", - __func__, msg_ctx->task->euid, pid); + __func__, ctx_euid, pid); goto unlock; } if (msg_ctx->state != ECRYPTFS_MSG_CTX_STATE_PENDING) { @@ -464,14 +465,14 @@ ecryptfs_send_message_locked(char *data, int data_len, u8 msg_type, struct ecryptfs_msg_ctx **msg_ctx) { struct ecryptfs_daemon *daemon; + uid_t euid = current_euid(); int rc; - rc = ecryptfs_find_daemon_by_euid(&daemon, current->euid, - current->nsproxy->user_ns); + rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); if (rc || !daemon) { rc = -ENOTCONN; printk(KERN_ERR "%s: User [%d] does not have a daemon " - "registered\n", __func__, current->euid); + "registered\n", __func__, euid); goto out; } mutex_lock(&ecryptfs_msg_ctx_lists_mux); diff --git a/fs/ecryptfs/miscdev.c b/fs/ecryptfs/miscdev.c index b484792a099..efd95a0ed1e 100644 --- a/fs/ecryptfs/miscdev.c +++ b/fs/ecryptfs/miscdev.c @@ -42,12 +42,12 @@ ecryptfs_miscdev_poll(struct file *file, poll_table *pt) { struct ecryptfs_daemon *daemon; unsigned int mask = 0; + uid_t euid = current_euid(); int rc; mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ - rc = ecryptfs_find_daemon_by_euid(&daemon, current->euid, - current->nsproxy->user_ns); + rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); BUG_ON(rc || !daemon); mutex_lock(&daemon->mux); mutex_unlock(&ecryptfs_daemon_hash_mux); @@ -83,6 +83,7 @@ static int ecryptfs_miscdev_open(struct inode *inode, struct file *file) { struct ecryptfs_daemon *daemon = NULL; + uid_t euid = current_euid(); int rc; mutex_lock(&ecryptfs_daemon_hash_mux); @@ -93,11 +94,9 @@ ecryptfs_miscdev_open(struct inode *inode, struct file *file) "count; rc = [%d]\n", __func__, rc); goto out_unlock_daemon_list; } - rc = ecryptfs_find_daemon_by_euid(&daemon, current->euid, - current->nsproxy->user_ns); + rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); if (rc || !daemon) { - rc = ecryptfs_spawn_daemon(&daemon, current->euid, - current->nsproxy->user_ns, + rc = ecryptfs_spawn_daemon(&daemon, euid, current_user_ns(), task_pid(current)); if (rc) { printk(KERN_ERR "%s: Error attempting to spawn daemon; " @@ -147,11 +146,11 @@ static int ecryptfs_miscdev_release(struct inode *inode, struct file *file) { struct ecryptfs_daemon *daemon = NULL; + uid_t euid = current_euid(); int rc; mutex_lock(&ecryptfs_daemon_hash_mux); - rc = ecryptfs_find_daemon_by_euid(&daemon, current->euid, - current->nsproxy->user_ns); + rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); BUG_ON(rc || !daemon); mutex_lock(&daemon->mux); BUG_ON(daemon->pid != task_pid(current)); @@ -246,12 +245,12 @@ ecryptfs_miscdev_read(struct file *file, char __user *buf, size_t count, char packet_length[3]; size_t i; size_t total_length; + uid_t euid = current_euid(); int rc; mutex_lock(&ecryptfs_daemon_hash_mux); /* TODO: Just use file->private_data? */ - rc = ecryptfs_find_daemon_by_euid(&daemon, current->euid, - current->nsproxy->user_ns); + rc = ecryptfs_find_daemon_by_euid(&daemon, euid, current_user_ns()); BUG_ON(rc || !daemon); mutex_lock(&daemon->mux); if (daemon->flags & ECRYPTFS_DAEMON_ZOMBIE) { @@ -290,8 +289,8 @@ check_list: * message from the queue; try again */ goto check_list; } - BUG_ON(current->euid != daemon->euid); - BUG_ON(current->nsproxy->user_ns != daemon->user_ns); + BUG_ON(euid != daemon->euid); + BUG_ON(current_user_ns() != daemon->user_ns); BUG_ON(task_pid(current) != daemon->pid); msg_ctx = list_first_entry(&daemon->msg_ctx_out_queue, struct ecryptfs_msg_ctx, daemon_out_list); @@ -414,6 +413,7 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf, size_t packet_size, packet_size_length, i; ssize_t sz = 0; char *data; + uid_t euid = current_euid(); int rc; if (count == 0) @@ -463,8 +463,7 @@ ecryptfs_miscdev_write(struct file *file, const char __user *buf, goto out_free; } rc = ecryptfs_miscdev_response(&data[i], packet_size, - current->euid, - current->nsproxy->user_ns, + euid, current_user_ns(), task_pid(current), seq); if (rc) printk(KERN_WARNING "%s: Failed to deliver miscdev " diff --git a/fs/exec.c b/fs/exec.c index ec5df9a3831..1f59ea079cb 100644 --- a/fs/exec.c +++ b/fs/exec.c @@ -55,6 +55,7 @@ #include #include #include +#include "internal.h" #ifdef __alpha__ /* for /sbin/loader handling in search_binary_handler() */ @@ -980,7 +981,7 @@ int flush_old_exec(struct linux_binprm * bprm) /* This is the point of no return */ current->sas_ss_sp = current->sas_ss_size = 0; - if (current->euid == current->uid && current->egid == current->gid) + if (current_euid() == current_uid() && current_egid() == current_gid()) set_dumpable(current->mm, 1); else set_dumpable(current->mm, suid_dumpable); @@ -1007,16 +1008,17 @@ int flush_old_exec(struct linux_binprm * bprm) */ current->mm->task_size = TASK_SIZE; - if (bprm->e_uid != current->euid || bprm->e_gid != current->egid) { - suid_keys(current); - set_dumpable(current->mm, suid_dumpable); + /* install the new credentials */ + if (bprm->cred->uid != current_euid() || + bprm->cred->gid != current_egid()) { current->pdeath_signal = 0; } else if (file_permission(bprm->file, MAY_READ) || - (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP)) { - suid_keys(current); + bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP) { set_dumpable(current->mm, suid_dumpable); } + current->personality &= ~bprm->per_clear; + /* An exec changes our domain. We are no longer part of the thread group */ @@ -1033,13 +1035,50 @@ out: EXPORT_SYMBOL(flush_old_exec); +/* + * install the new credentials for this executable + */ +void install_exec_creds(struct linux_binprm *bprm) +{ + security_bprm_committing_creds(bprm); + + commit_creds(bprm->cred); + bprm->cred = NULL; + + /* cred_exec_mutex must be held at least to this point to prevent + * ptrace_attach() from altering our determination of the task's + * credentials; any time after this it may be unlocked */ + + security_bprm_committed_creds(bprm); +} +EXPORT_SYMBOL(install_exec_creds); + +/* + * determine how safe it is to execute the proposed program + * - the caller must hold current->cred_exec_mutex to protect against + * PTRACE_ATTACH + */ +void check_unsafe_exec(struct linux_binprm *bprm) +{ + struct task_struct *p = current; + + bprm->unsafe = tracehook_unsafe_exec(p); + + if (atomic_read(&p->fs->count) > 1 || + atomic_read(&p->files->count) > 1 || + atomic_read(&p->sighand->count) > 1) + bprm->unsafe |= LSM_UNSAFE_SHARE; +} + /* * Fill the binprm structure from the inode. * Check permissions, then read the first 128 (BINPRM_BUF_SIZE) bytes + * + * This may be called multiple times for binary chains (scripts for example). */ int prepare_binprm(struct linux_binprm *bprm) { - int mode; + umode_t mode; struct inode * inode = bprm->file->f_path.dentry->d_inode; int retval; @@ -1047,14 +1086,15 @@ int prepare_binprm(struct linux_binprm *bprm) if (bprm->file->f_op == NULL) return -EACCES; - bprm->e_uid = current->euid; - bprm->e_gid = current->egid; + /* clear any previous set[ug]id data from a previous binary */ + bprm->cred->euid = current_euid(); + bprm->cred->egid = current_egid(); - if(!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) { + if (!(bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID)) { /* Set-uid? */ if (mode & S_ISUID) { - current->personality &= ~PER_CLEAR_ON_SETID; - bprm->e_uid = inode->i_uid; + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->euid = inode->i_uid; } /* Set-gid? */ @@ -1064,52 +1104,23 @@ int prepare_binprm(struct linux_binprm *bprm) * executable. */ if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { - current->personality &= ~PER_CLEAR_ON_SETID; - bprm->e_gid = inode->i_gid; + bprm->per_clear |= PER_CLEAR_ON_SETID; + bprm->cred->egid = inode->i_gid; } } /* fill in binprm security blob */ - retval = security_bprm_set(bprm); + retval = security_bprm_set_creds(bprm); if (retval) return retval; + bprm->cred_prepared = 1; - memset(bprm->buf,0,BINPRM_BUF_SIZE); - return kernel_read(bprm->file,0,bprm->buf,BINPRM_BUF_SIZE); + memset(bprm->buf, 0, BINPRM_BUF_SIZE); + return kernel_read(bprm->file, 0, bprm->buf, BINPRM_BUF_SIZE); } EXPORT_SYMBOL(prepare_binprm); -static int unsafe_exec(struct task_struct *p) -{ - int unsafe = tracehook_unsafe_exec(p); - - if (atomic_read(&p->fs->count) > 1 || - atomic_read(&p->files->count) > 1 || - atomic_read(&p->sighand->count) > 1) - unsafe |= LSM_UNSAFE_SHARE; - - return unsafe; -} - -void compute_creds(struct linux_binprm *bprm) -{ - int unsafe; - - if (bprm->e_uid != current->uid) { - suid_keys(current); - current->pdeath_signal = 0; - } - exec_keys(current); - - task_lock(current); - unsafe = unsafe_exec(current); - security_bprm_apply_creds(bprm, unsafe); - task_unlock(current); - security_bprm_post_apply_creds(bprm); -} -EXPORT_SYMBOL(compute_creds); - /* * Arguments are '\0' separated strings found at the location bprm->p * points to; chop off the first by relocating brpm->p to right after @@ -1270,6 +1281,8 @@ EXPORT_SYMBOL(search_binary_handler); void free_bprm(struct linux_binprm *bprm) { free_arg_pages(bprm); + if (bprm->cred) + abort_creds(bprm->cred); kfree(bprm); } @@ -1295,10 +1308,20 @@ int do_execve(char * filename, if (!bprm) goto out_files; + retval = mutex_lock_interruptible(¤t->cred_exec_mutex); + if (retval < 0) + goto out_free; + + retval = -ENOMEM; + bprm->cred = prepare_exec_creds(); + if (!bprm->cred) + goto out_unlock; + check_unsafe_exec(bprm); + file = open_exec(filename); retval = PTR_ERR(file); if (IS_ERR(file)) - goto out_kfree; + goto out_unlock; sched_exec(); @@ -1312,14 +1335,10 @@ int do_execve(char * filename, bprm->argc = count(argv, MAX_ARG_STRINGS); if ((retval = bprm->argc) < 0) - goto out_mm; + goto out; bprm->envc = count(envp, MAX_ARG_STRINGS); if ((retval = bprm->envc) < 0) - goto out_mm; - - retval = security_bprm_alloc(bprm); - if (retval) goto out; retval = prepare_binprm(bprm); @@ -1341,21 +1360,18 @@ int do_execve(char * filename, current->flags &= ~PF_KTHREAD; retval = search_binary_handler(bprm,regs); - if (retval >= 0) { - /* execve success */ - security_bprm_free(bprm); - acct_update_integrals(current); - free_bprm(bprm); - if (displaced) - put_files_struct(displaced); - return retval; - } + if (retval < 0) + goto out; + + /* execve succeeded */ + mutex_unlock(¤t->cred_exec_mutex); + acct_update_integrals(current); + free_bprm(bprm); + if (displaced) + put_files_struct(displaced); + return retval; out: - if (bprm->security) - security_bprm_free(bprm); - -out_mm: if (bprm->mm) mmput (bprm->mm); @@ -1364,7 +1380,11 @@ out_file: allow_write_access(bprm->file); fput(bprm->file); } -out_kfree: + +out_unlock: + mutex_unlock(¤t->cred_exec_mutex); + +out_free: free_bprm(bprm); out_files: @@ -1396,6 +1416,7 @@ EXPORT_SYMBOL(set_binfmt); */ static int format_corename(char *corename, long signr) { + const struct cred *cred = current_cred(); const char *pat_ptr = core_pattern; int ispipe = (*pat_ptr == '|'); char *out_ptr = corename; @@ -1432,7 +1453,7 @@ static int format_corename(char *corename, long signr) /* uid */ case 'u': rc = snprintf(out_ptr, out_end - out_ptr, - "%d", current->uid); + "%d", cred->uid); if (rc > out_end - out_ptr) goto out; out_ptr += rc; @@ -1440,7 +1461,7 @@ static int format_corename(char *corename, long signr) /* gid */ case 'g': rc = snprintf(out_ptr, out_end - out_ptr, - "%d", current->gid); + "%d", cred->gid); if (rc > out_end - out_ptr) goto out; out_ptr += rc; @@ -1716,8 +1737,9 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) struct linux_binfmt * binfmt; struct inode * inode; struct file * file; + const struct cred *old_cred; + struct cred *cred; int retval = 0; - int fsuid = current->fsuid; int flag = 0; int ispipe = 0; unsigned long core_limit = current->signal->rlim[RLIMIT_CORE].rlim_cur; @@ -1730,12 +1752,20 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) binfmt = current->binfmt; if (!binfmt || !binfmt->core_dump) goto fail; + + cred = prepare_creds(); + if (!cred) { + retval = -ENOMEM; + goto fail; + } + down_write(&mm->mmap_sem); /* * If another thread got here first, or we are not dumpable, bail out. */ if (mm->core_state || !get_dumpable(mm)) { up_write(&mm->mmap_sem); + put_cred(cred); goto fail; } @@ -1746,12 +1776,16 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) */ if (get_dumpable(mm) == 2) { /* Setuid core dump mode */ flag = O_EXCL; /* Stop rewrite attacks */ - current->fsuid = 0; /* Dump root private */ + cred->fsuid = 0; /* Dump root private */ } retval = coredump_wait(exit_code, &core_state); - if (retval < 0) + if (retval < 0) { + put_cred(cred); goto fail; + } + + old_cred = override_creds(cred); /* * Clear any false indication of pending signals that might @@ -1823,7 +1857,7 @@ int do_coredump(long signr, int exit_code, struct pt_regs * regs) * Dont allow local users get cute and trick others to coredump * into their pre-created files: */ - if (inode->i_uid != current->fsuid) + if (inode->i_uid != current_fsuid()) goto close_fail; if (!file->f_op) goto close_fail; @@ -1842,7 +1876,8 @@ fail_unlock: if (helper_argv) argv_free(helper_argv); - current->fsuid = fsuid; + revert_creds(old_cred); + put_cred(cred); coredump_finish(mm); fail: return retval; diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c index 890e0182881..197c7db583c 100644 --- a/fs/exportfs/expfs.c +++ b/fs/exportfs/expfs.c @@ -14,6 +14,7 @@ #include #include #include +#include #define dprintk(fmt, args...) do{}while(0) @@ -249,6 +250,7 @@ static int filldir_one(void * __buf, const char * name, int len, static int get_name(struct vfsmount *mnt, struct dentry *dentry, char *name, struct dentry *child) { + const struct cred *cred = current_cred(); struct inode *dir = dentry->d_inode; int error; struct file *file; @@ -263,7 +265,7 @@ static int get_name(struct vfsmount *mnt, struct dentry *dentry, /* * Open the directory ... */ - file = dentry_open(dget(dentry), mntget(mnt), O_RDONLY); + file = dentry_open(dget(dentry), mntget(mnt), O_RDONLY, cred); error = PTR_ERR(file); if (IS_ERR(file)) goto out; diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c index 6dac7ba2d22..4a29d637608 100644 --- a/fs/ext2/balloc.c +++ b/fs/ext2/balloc.c @@ -1193,7 +1193,7 @@ static int ext2_has_free_blocks(struct ext2_sb_info *sbi) free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count); if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) && - sbi->s_resuid != current->fsuid && + sbi->s_resuid != current_fsuid() && (sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) { return 0; } diff --git a/fs/ext2/ialloc.c b/fs/ext2/ialloc.c index f5974134676..8d0add62587 100644 --- a/fs/ext2/ialloc.c +++ b/fs/ext2/ialloc.c @@ -550,7 +550,7 @@ got: sb->s_dirt = 1; mark_buffer_dirty(bh2); - inode->i_uid = current->fsuid; + inode->i_uid = current_fsuid(); if (test_opt (sb, GRPID)) inode->i_gid = dir->i_gid; else if (dir->i_mode & S_ISGID) { @@ -558,7 +558,7 @@ got: if (S_ISDIR(mode)) mode |= S_ISGID; } else - inode->i_gid = current->fsgid; + inode->i_gid = current_fsgid(); inode->i_mode = mode; inode->i_ino = ino; diff --git a/fs/ext3/balloc.c b/fs/ext3/balloc.c index f5b57a2ca35..0dbf1c04847 100644 --- a/fs/ext3/balloc.c +++ b/fs/ext3/balloc.c @@ -1422,7 +1422,7 @@ static int ext3_has_free_blocks(struct ext3_sb_info *sbi) free_blocks = percpu_counter_read_positive(&sbi->s_freeblocks_counter); root_blocks = le32_to_cpu(sbi->s_es->s_r_blocks_count); if (free_blocks < root_blocks + 1 && !capable(CAP_SYS_RESOURCE) && - sbi->s_resuid != current->fsuid && + sbi->s_resuid != current_fsuid() && (sbi->s_resgid == 0 || !in_group_p (sbi->s_resgid))) { return 0; } diff --git a/fs/ext3/ialloc.c b/fs/ext3/ialloc.c index 47b678d73e7..490bd0ed789 100644 --- a/fs/ext3/ialloc.c +++ b/fs/ext3/ialloc.c @@ -539,7 +539,7 @@ got: percpu_counter_inc(&sbi->s_dirs_counter); sb->s_dirt = 1; - inode->i_uid = current->fsuid; + inode->i_uid = current_fsuid(); if (test_opt (sb, GRPID)) inode->i_gid = dir->i_gid; else if (dir->i_mode & S_ISGID) { @@ -547,7 +547,7 @@ got: if (S_ISDIR(mode)) mode |= S_ISGID; } else - inode->i_gid = current->fsgid; + inode->i_gid = current_fsgid(); inode->i_mode = mode; inode->i_ino = ino; diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c index db35cfdb3c8..38b3acf5683 100644 --- a/fs/ext4/balloc.c +++ b/fs/ext4/balloc.c @@ -624,7 +624,7 @@ int ext4_has_free_blocks(struct ext4_sb_info *sbi, s64 nblocks) return 1; /* Hm, nope. Are (enough) root reserved blocks available? */ - if (sbi->s_resuid == current->fsuid || + if (sbi->s_resuid == current_fsuid() || ((sbi->s_resgid != 0) && in_group_p(sbi->s_resgid)) || capable(CAP_SYS_RESOURCE)) { if (free_blocks >= (nblocks + dirty_blocks)) diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c index 2a117e286e5..08cac9fcace 100644 --- a/fs/ext4/ialloc.c +++ b/fs/ext4/ialloc.c @@ -787,7 +787,7 @@ got: spin_unlock(sb_bgl_lock(sbi, flex_group)); } - inode->i_uid = current->fsuid; + inode->i_uid = current_fsuid(); if (test_opt(sb, GRPID)) inode->i_gid = dir->i_gid; else if (dir->i_mode & S_ISGID) { @@ -795,7 +795,7 @@ got: if (S_ISDIR(mode)) mode |= S_ISGID; } else - inode->i_gid = current->fsgid; + inode->i_gid = current_fsgid(); inode->i_mode = mode; inode->i_ino = ino + group * EXT4_INODES_PER_GROUP(sb); diff --git a/fs/fat/file.c b/fs/fat/file.c index f06a4e525ec..0a7f4a9918b 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -304,7 +304,7 @@ static int fat_allow_set_time(struct msdos_sb_info *sbi, struct inode *inode) { mode_t allow_utime = sbi->options.allow_utime; - if (current->fsuid != inode->i_uid) { + if (current_fsuid() != inode->i_uid) { if (in_group_p(inode->i_gid)) allow_utime >>= 3; if (allow_utime & MAY_WRITE) diff --git a/fs/fat/inode.c b/fs/fat/inode.c index bdd8fb7be2c..d937aaf7737 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -926,8 +926,8 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug, opts->isvfat = is_vfat; - opts->fs_uid = current->uid; - opts->fs_gid = current->gid; + opts->fs_uid = current_uid(); + opts->fs_gid = current_gid(); opts->fs_fmask = opts->fs_dmask = current->fs->umask; opts->allow_utime = -1; opts->codepage = fat_default_codepage; diff --git a/fs/fcntl.c b/fs/fcntl.c index 549daf8005f..cdc14194672 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -212,13 +212,14 @@ static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, int __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { + const struct cred *cred = current_cred(); int err; err = security_file_set_fowner(filp); if (err) return err; - f_modown(filp, pid, type, current->uid, current->euid, force); + f_modown(filp, pid, type, cred->uid, cred->euid, force); return 0; } EXPORT_SYMBOL(__f_setown); @@ -407,10 +408,17 @@ static const long band_table[NSIGPOLL] = { static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { - return (((fown->euid == 0) || - (fown->euid == p->suid) || (fown->euid == p->uid) || - (fown->uid == p->suid) || (fown->uid == p->uid)) && - !security_file_send_sigiotask(p, fown, sig)); + const struct cred *cred; + int ret; + + rcu_read_lock(); + cred = __task_cred(p); + ret = ((fown->euid == 0 || + fown->euid == cred->suid || fown->euid == cred->uid || + fown->uid == cred->suid || fown->uid == cred->uid) && + !security_file_send_sigiotask(p, fown, sig)); + rcu_read_unlock(); + return ret; } static void send_sigio_to_task(struct task_struct *p, diff --git a/fs/file_table.c b/fs/file_table.c index 5ad0eca6eea..0fbcacc3ea7 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -36,7 +36,9 @@ static struct percpu_counter nr_files __cacheline_aligned_in_smp; static inline void file_free_rcu(struct rcu_head *head) { - struct file *f = container_of(head, struct file, f_u.fu_rcuhead); + struct file *f = container_of(head, struct file, f_u.fu_rcuhead); + + put_cred(f->f_cred); kmem_cache_free(filp_cachep, f); } @@ -94,7 +96,7 @@ int proc_nr_files(ctl_table *table, int write, struct file *filp, */ struct file *get_empty_filp(void) { - struct task_struct *tsk; + const struct cred *cred = current_cred(); static int old_max; struct file * f; @@ -118,12 +120,10 @@ struct file *get_empty_filp(void) if (security_file_alloc(f)) goto fail_sec; - tsk = current; INIT_LIST_HEAD(&f->f_u.fu_list); atomic_long_set(&f->f_count, 1); rwlock_init(&f->f_owner.lock); - f->f_uid = tsk->fsuid; - f->f_gid = tsk->fsgid; + f->f_cred = get_cred(cred); eventpoll_init_file(f); /* f->f_version: 0 */ return f; diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index b72361479be..fba571648a8 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -87,8 +87,8 @@ static void __fuse_put_request(struct fuse_req *req) static void fuse_req_init_context(struct fuse_req *req) { - req->in.h.uid = current->fsuid; - req->in.h.gid = current->fsgid; + req->in.h.uid = current_fsuid(); + req->in.h.gid = current_fsgid(); req->in.h.pid = current->pid; } diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index fd03330cade..95bc22bdd06 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -869,18 +869,25 @@ int fuse_update_attributes(struct inode *inode, struct kstat *stat, */ int fuse_allow_task(struct fuse_conn *fc, struct task_struct *task) { + const struct cred *cred; + int ret; + if (fc->flags & FUSE_ALLOW_OTHER) return 1; - if (task->euid == fc->user_id && - task->suid == fc->user_id && - task->uid == fc->user_id && - task->egid == fc->group_id && - task->sgid == fc->group_id && - task->gid == fc->group_id) - return 1; + rcu_read_lock(); + ret = 0; + cred = __task_cred(task); + if (cred->euid == fc->user_id && + cred->suid == fc->user_id && + cred->uid == fc->user_id && + cred->egid == fc->group_id && + cred->sgid == fc->group_id && + cred->gid == fc->group_id) + ret = 1; + rcu_read_unlock(); - return 0; + return ret; } static int fuse_access(struct inode *inode, int mask) diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c index 7cee695fa44..d57616840e8 100644 --- a/fs/gfs2/inode.c +++ b/fs/gfs2/inode.c @@ -705,18 +705,18 @@ static void munge_mode_uid_gid(struct gfs2_inode *dip, unsigned int *mode, (dip->i_inode.i_mode & S_ISUID) && dip->i_inode.i_uid) { if (S_ISDIR(*mode)) *mode |= S_ISUID; - else if (dip->i_inode.i_uid != current->fsuid) + else if (dip->i_inode.i_uid != current_fsuid()) *mode &= ~07111; *uid = dip->i_inode.i_uid; } else - *uid = current->fsuid; + *uid = current_fsuid(); if (dip->i_inode.i_mode & S_ISGID) { if (S_ISDIR(*mode)) *mode |= S_ISGID; *gid = dip->i_inode.i_gid; } else - *gid = current->fsgid; + *gid = current_fsgid(); } static int alloc_dinode(struct gfs2_inode *dip, u64 *no_addr, u64 *generation) @@ -1124,8 +1124,8 @@ int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name, return -EPERM; if ((dip->i_inode.i_mode & S_ISVTX) && - dip->i_inode.i_uid != current->fsuid && - ip->i_inode.i_uid != current->fsuid && !capable(CAP_FOWNER)) + dip->i_inode.i_uid != current_fsuid() && + ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER)) return -EPERM; if (IS_APPEND(&dip->i_inode)) diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c index c69b7ac75bf..9435dda8f1e 100644 --- a/fs/hfs/inode.c +++ b/fs/hfs/inode.c @@ -155,8 +155,8 @@ struct inode *hfs_new_inode(struct inode *dir, struct qstr *name, int mode) hfs_cat_build_key(sb, (btree_key *)&HFS_I(inode)->cat_key, dir->i_ino, name); inode->i_ino = HFS_SB(sb)->next_id++; inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_nlink = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; HFS_I(inode)->flags = 0; diff --git a/fs/hfs/super.c b/fs/hfs/super.c index 3c7c7637719..c8b5acf4b0b 100644 --- a/fs/hfs/super.c +++ b/fs/hfs/super.c @@ -210,8 +210,8 @@ static int parse_options(char *options, struct hfs_sb_info *hsb) int tmp, token; /* initialize the sb with defaults */ - hsb->s_uid = current->uid; - hsb->s_gid = current->gid; + hsb->s_uid = current_uid(); + hsb->s_gid = current_gid(); hsb->s_file_umask = 0133; hsb->s_dir_umask = 0022; hsb->s_type = hsb->s_creator = cpu_to_be32(0x3f3f3f3f); /* == '????' */ diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c index b207f0e6fc2..f105ee9e1cc 100644 --- a/fs/hfsplus/inode.c +++ b/fs/hfsplus/inode.c @@ -296,8 +296,8 @@ struct inode *hfsplus_new_inode(struct super_block *sb, int mode) inode->i_ino = HFSPLUS_SB(sb).next_cnid++; inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_nlink = 1; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; INIT_LIST_HEAD(&HFSPLUS_I(inode).open_dir_list); diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c index 9699c56d323..bab7f8d1bdf 100644 --- a/fs/hfsplus/options.c +++ b/fs/hfsplus/options.c @@ -49,8 +49,8 @@ void hfsplus_fill_defaults(struct hfsplus_sb_info *opts) opts->creator = HFSPLUS_DEF_CR_TYPE; opts->type = HFSPLUS_DEF_CR_TYPE; opts->umask = current->fs->umask; - opts->uid = current->uid; - opts->gid = current->gid; + opts->uid = current_uid(); + opts->gid = current_gid(); opts->part = -1; opts->session = -1; } diff --git a/fs/hpfs/namei.c b/fs/hpfs/namei.c index 10783f3d265..b649232dde9 100644 --- a/fs/hpfs/namei.c +++ b/fs/hpfs/namei.c @@ -92,11 +92,11 @@ static int hpfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) inc_nlink(dir); insert_inode_hash(result); - if (result->i_uid != current->fsuid || - result->i_gid != current->fsgid || + if (result->i_uid != current_fsuid() || + result->i_gid != current_fsgid() || result->i_mode != (mode | S_IFDIR)) { - result->i_uid = current->fsuid; - result->i_gid = current->fsgid; + result->i_uid = current_fsuid(); + result->i_gid = current_fsgid(); result->i_mode = mode | S_IFDIR; hpfs_write_inode_nolock(result); } @@ -184,11 +184,11 @@ static int hpfs_create(struct inode *dir, struct dentry *dentry, int mode, struc insert_inode_hash(result); - if (result->i_uid != current->fsuid || - result->i_gid != current->fsgid || + if (result->i_uid != current_fsuid() || + result->i_gid != current_fsgid() || result->i_mode != (mode | S_IFREG)) { - result->i_uid = current->fsuid; - result->i_gid = current->fsgid; + result->i_uid = current_fsuid(); + result->i_gid = current_fsgid(); result->i_mode = mode | S_IFREG; hpfs_write_inode_nolock(result); } @@ -247,8 +247,8 @@ static int hpfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t result->i_mtime.tv_nsec = 0; result->i_atime.tv_nsec = 0; hpfs_i(result)->i_ea_size = 0; - result->i_uid = current->fsuid; - result->i_gid = current->fsgid; + result->i_uid = current_fsuid(); + result->i_gid = current_fsgid(); result->i_nlink = 1; result->i_size = 0; result->i_blocks = 1; @@ -325,8 +325,8 @@ static int hpfs_symlink(struct inode *dir, struct dentry *dentry, const char *sy result->i_atime.tv_nsec = 0; hpfs_i(result)->i_ea_size = 0; result->i_mode = S_IFLNK | 0777; - result->i_uid = current->fsuid; - result->i_gid = current->fsgid; + result->i_uid = current_fsuid(); + result->i_gid = current_fsgid(); result->i_blocks = 1; result->i_nlink = 1; result->i_size = strlen(symlink); diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c index 29ad461d568..0d049b8919c 100644 --- a/fs/hpfs/super.c +++ b/fs/hpfs/super.c @@ -475,8 +475,8 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent) init_MUTEX(&sbi->hpfs_creation_de); - uid = current->uid; - gid = current->gid; + uid = current_uid(); + gid = current_gid(); umask = current->fs->umask; lowercase = 0; conv = CONV_BINARY; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index 2b3d1828db9..b278f7f5202 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -426,6 +426,7 @@ static int file_mode(int fmode) static int hppfs_open(struct inode *inode, struct file *file) { + const struct cred *cred = file->f_cred; struct hppfs_private *data; struct vfsmount *proc_mnt; struct dentry *proc_dentry; @@ -446,7 +447,7 @@ static int hppfs_open(struct inode *inode, struct file *file) /* XXX This isn't closed anywhere */ data->proc_file = dentry_open(dget(proc_dentry), mntget(proc_mnt), - file_mode(file->f_mode)); + file_mode(file->f_mode), cred); err = PTR_ERR(data->proc_file); if (IS_ERR(data->proc_file)) goto out_free1; @@ -489,6 +490,7 @@ static int hppfs_open(struct inode *inode, struct file *file) static int hppfs_dir_open(struct inode *inode, struct file *file) { + const struct cred *cred = file->f_cred; struct hppfs_private *data; struct vfsmount *proc_mnt; struct dentry *proc_dentry; @@ -502,7 +504,7 @@ static int hppfs_dir_open(struct inode *inode, struct file *file) proc_dentry = HPPFS_I(inode)->proc_dentry; proc_mnt = inode->i_sb->s_fs_info; data->proc_file = dentry_open(dget(proc_dentry), mntget(proc_mnt), - file_mode(file->f_mode)); + file_mode(file->f_mode), cred); err = PTR_ERR(data->proc_file); if (IS_ERR(data->proc_file)) goto out_free; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index 61edc701b0e..7d479ce3ace 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -551,9 +551,9 @@ static int hugetlbfs_mknod(struct inode *dir, if (S_ISDIR(mode)) mode |= S_ISGID; } else { - gid = current->fsgid; + gid = current_fsgid(); } - inode = hugetlbfs_get_inode(dir->i_sb, current->fsuid, gid, mode, dev); + inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(), gid, mode, dev); if (inode) { dir->i_ctime = dir->i_mtime = CURRENT_TIME; d_instantiate(dentry, inode); @@ -586,9 +586,9 @@ static int hugetlbfs_symlink(struct inode *dir, if (dir->i_mode & S_ISGID) gid = dir->i_gid; else - gid = current->fsgid; + gid = current_fsgid(); - inode = hugetlbfs_get_inode(dir->i_sb, current->fsuid, + inode = hugetlbfs_get_inode(dir->i_sb, current_fsuid(), gid, S_IFLNK|S_IRWXUGO, 0); if (inode) { int l = strlen(symname)+1; @@ -854,8 +854,8 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent) config.nr_blocks = -1; /* No limit on size by default */ config.nr_inodes = -1; /* No limit on number of inodes by default */ - config.uid = current->fsuid; - config.gid = current->fsgid; + config.uid = current_fsuid(); + config.gid = current_fsgid(); config.mode = 0755; config.hstate = &default_hstate; ret = hugetlbfs_parse_options(data, &config); @@ -951,6 +951,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size) struct inode *inode; struct dentry *dentry, *root; struct qstr quick_string; + struct user_struct *user = current_user(); if (!hugetlbfs_vfsmount) return ERR_PTR(-ENOENT); @@ -958,7 +959,7 @@ struct file *hugetlb_file_setup(const char *name, size_t size) if (!can_do_hugetlb_shm()) return ERR_PTR(-EPERM); - if (!user_shm_lock(size, current->user)) + if (!user_shm_lock(size, user)) return ERR_PTR(-ENOMEM); root = hugetlbfs_vfsmount->mnt_root; @@ -970,8 +971,8 @@ struct file *hugetlb_file_setup(const char *name, size_t size) goto out_shm_unlock; error = -ENOSPC; - inode = hugetlbfs_get_inode(root->d_sb, current->fsuid, - current->fsgid, S_IFREG | S_IRWXUGO, 0); + inode = hugetlbfs_get_inode(root->d_sb, current_fsuid(), + current_fsgid(), S_IFREG | S_IRWXUGO, 0); if (!inode) goto out_dentry; @@ -998,7 +999,7 @@ out_inode: out_dentry: dput(dentry); out_shm_unlock: - user_shm_unlock(size, current->user); + user_shm_unlock(size, user); return ERR_PTR(error); } diff --git a/fs/inotify_user.c b/fs/inotify_user.c index d367e9b9286..e2425bbd871 100644 --- a/fs/inotify_user.c +++ b/fs/inotify_user.c @@ -601,7 +601,7 @@ asmlinkage long sys_inotify_init1(int flags) goto out_put_fd; } - user = get_uid(current->user); + user = get_current_user(); if (unlikely(atomic_read(&user->inotify_devs) >= inotify_max_user_instances)) { ret = -EMFILE; diff --git a/fs/internal.h b/fs/internal.h index 80aa9a02337..53af885f173 100644 --- a/fs/internal.h +++ b/fs/internal.h @@ -10,6 +10,7 @@ */ struct super_block; +struct linux_binprm; /* * block_dev.c @@ -39,6 +40,11 @@ static inline int sb_is_blkdev_sb(struct super_block *sb) */ extern void __init chrdev_init(void); +/* + * exec.c + */ +extern void check_unsafe_exec(struct linux_binprm *); + /* * namespace.c */ diff --git a/fs/ioprio.c b/fs/ioprio.c index da3cc460d4d..3569e0ad86a 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -31,10 +31,16 @@ static int set_task_ioprio(struct task_struct *task, int ioprio) { int err; struct io_context *ioc; + const struct cred *cred = current_cred(), *tcred; - if (task->uid != current->euid && - task->uid != current->uid && !capable(CAP_SYS_NICE)) + rcu_read_lock(); + tcred = __task_cred(task); + if (tcred->uid != cred->euid && + tcred->uid != cred->uid && !capable(CAP_SYS_NICE)) { + rcu_read_unlock(); return -EPERM; + } + rcu_read_unlock(); err = security_task_setioprio(task, ioprio); if (err) @@ -123,7 +129,7 @@ asmlinkage long sys_ioprio_set(int which, int who, int ioprio) break; case IOPRIO_WHO_USER: if (!who) - user = current->user; + user = current_user(); else user = find_user(who); @@ -131,7 +137,7 @@ asmlinkage long sys_ioprio_set(int which, int who, int ioprio) break; do_each_thread(g, p) { - if (p->uid != who) + if (__task_cred(p)->uid != who) continue; ret = set_task_ioprio(p, ioprio); if (ret) @@ -216,7 +222,7 @@ asmlinkage long sys_ioprio_get(int which, int who) break; case IOPRIO_WHO_USER: if (!who) - user = current->user; + user = current_user(); else user = find_user(who); @@ -224,7 +230,7 @@ asmlinkage long sys_ioprio_get(int which, int who) break; do_each_thread(g, p) { - if (p->uid != user->uid) + if (__task_cred(p)->uid != user->uid) continue; tmpio = get_task_ioprio(p); if (tmpio < 0) diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c index ed6574bee51..70022fd1c53 100644 --- a/fs/jfs/jfs_inode.c +++ b/fs/jfs/jfs_inode.c @@ -93,13 +93,13 @@ struct inode *ialloc(struct inode *parent, umode_t mode) return ERR_PTR(rc); } - inode->i_uid = current->fsuid; + inode->i_uid = current_fsuid(); if (parent->i_mode & S_ISGID) { inode->i_gid = parent->i_gid; if (S_ISDIR(mode)) mode |= S_ISGID; } else - inode->i_gid = current->fsgid; + inode->i_gid = current_fsgid(); /* * New inodes need to save sane values on disk when diff --git a/fs/locks.c b/fs/locks.c index 09062e3ff10..46a2e12f7d4 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1349,7 +1349,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp) struct inode *inode = dentry->d_inode; int error, rdlease_count = 0, wrlease_count = 0; - if ((current->fsuid != inode->i_uid) && !capable(CAP_LEASE)) + if ((current_fsuid() != inode->i_uid) && !capable(CAP_LEASE)) return -EACCES; if (!S_ISREG(inode->i_mode)) return -EINVAL; diff --git a/fs/minix/bitmap.c b/fs/minix/bitmap.c index 703cc35e04b..3aebe322271 100644 --- a/fs/minix/bitmap.c +++ b/fs/minix/bitmap.c @@ -262,8 +262,8 @@ struct inode * minix_new_inode(const struct inode * dir, int * error) iput(inode); return NULL; } - inode->i_uid = current->fsuid; - inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = (dir->i_mode & S_ISGID) ? dir->i_gid : current_fsgid(); inode->i_ino = j; inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; inode->i_blocks = 0; diff --git a/fs/namei.c b/fs/namei.c index d34e0f9681c..af3783fff1d 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -186,7 +186,7 @@ int generic_permission(struct inode *inode, int mask, mask &= MAY_READ | MAY_WRITE | MAY_EXEC; - if (current->fsuid == inode->i_uid) + if (current_fsuid() == inode->i_uid) mode >>= 6; else { if (IS_POSIXACL(inode) && (mode & S_IRWXG) && check_acl) { @@ -441,7 +441,7 @@ static int exec_permission_lite(struct inode *inode) if (inode->i_op && inode->i_op->permission) return -EAGAIN; - if (current->fsuid == inode->i_uid) + if (current_fsuid() == inode->i_uid) mode >>= 6; else if (in_group_p(inode->i_gid)) mode >>= 3; @@ -1334,11 +1334,13 @@ static int user_path_parent(int dfd, const char __user *path, */ static inline int check_sticky(struct inode *dir, struct inode *inode) { + uid_t fsuid = current_fsuid(); + if (!(dir->i_mode & S_ISVTX)) return 0; - if (inode->i_uid == current->fsuid) + if (inode->i_uid == fsuid) return 0; - if (dir->i_uid == current->fsuid) + if (dir->i_uid == fsuid) return 0; return !capable(CAP_FOWNER); } diff --git a/fs/namespace.c b/fs/namespace.c index 65b3dc844c8..1c09cab8f7c 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -1176,7 +1176,7 @@ static int mount_is_safe(struct path *path) if (S_ISLNK(path->dentry->d_inode->i_mode)) return -EPERM; if (path->dentry->d_inode->i_mode & S_ISVTX) { - if (current->uid != path->dentry->d_inode->i_uid) + if (current_uid() != path->dentry->d_inode->i_uid) return -EPERM; } if (inode_permission(path->dentry->d_inode, MAY_WRITE)) diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c index 3a97c95e1ca..6d04e050c74 100644 --- a/fs/ncpfs/ioctl.c +++ b/fs/ncpfs/ioctl.c @@ -40,10 +40,10 @@ ncp_get_fs_info(struct ncp_server * server, struct file *file, struct inode *inode = file->f_path.dentry->d_inode; struct ncp_fs_info info; - if ((file_permission(file, MAY_WRITE) != 0) - && (current->uid != server->m.mounted_uid)) { + if (file_permission(file, MAY_WRITE) != 0 + && current_uid() != server->m.mounted_uid) return -EACCES; - } + if (copy_from_user(&info, arg, sizeof(info))) return -EFAULT; @@ -70,10 +70,10 @@ ncp_get_fs_info_v2(struct ncp_server * server, struct file *file, struct inode *inode = file->f_path.dentry->d_inode; struct ncp_fs_info_v2 info2; - if ((file_permission(file, MAY_WRITE) != 0) - && (current->uid != server->m.mounted_uid)) { + if (file_permission(file, MAY_WRITE) != 0 + && current_uid() != server->m.mounted_uid) return -EACCES; - } + if (copy_from_user(&info2, arg, sizeof(info2))) return -EFAULT; @@ -141,10 +141,10 @@ ncp_get_compat_fs_info_v2(struct ncp_server * server, struct file *file, struct inode *inode = file->f_path.dentry->d_inode; struct compat_ncp_fs_info_v2 info2; - if ((file_permission(file, MAY_WRITE) != 0) - && (current->uid != server->m.mounted_uid)) { + if (file_permission(file, MAY_WRITE) != 0 + && current_uid() != server->m.mounted_uid) return -EACCES; - } + if (copy_from_user(&info2, arg, sizeof(info2))) return -EFAULT; @@ -270,16 +270,17 @@ static int __ncp_ioctl(struct inode *inode, struct file *filp, struct ncp_ioctl_request request; char* bouncebuffer; void __user *argp = (void __user *)arg; + uid_t uid = current_uid(); switch (cmd) { #ifdef CONFIG_COMPAT case NCP_IOC_NCPREQUEST_32: #endif case NCP_IOC_NCPREQUEST: - if ((file_permission(filp, MAY_WRITE) != 0) - && (current->uid != server->m.mounted_uid)) { + if (file_permission(filp, MAY_WRITE) != 0 + && uid != server->m.mounted_uid) return -EACCES; - } + #ifdef CONFIG_COMPAT if (cmd == NCP_IOC_NCPREQUEST_32) { struct compat_ncp_ioctl_request request32; @@ -356,10 +357,10 @@ static int __ncp_ioctl(struct inode *inode, struct file *filp, case NCP_IOC_GETMOUNTUID16: case NCP_IOC_GETMOUNTUID32: case NCP_IOC_GETMOUNTUID64: - if ((file_permission(filp, MAY_READ) != 0) - && (current->uid != server->m.mounted_uid)) { + if (file_permission(filp, MAY_READ) != 0 + && uid != server->m.mounted_uid) return -EACCES; - } + if (cmd == NCP_IOC_GETMOUNTUID16) { u16 uid; SET_UID(uid, server->m.mounted_uid); @@ -380,11 +381,10 @@ static int __ncp_ioctl(struct inode *inode, struct file *filp, { struct ncp_setroot_ioctl sr; - if ((file_permission(filp, MAY_READ) != 0) - && (current->uid != server->m.mounted_uid)) - { + if (file_permission(filp, MAY_READ) != 0 + && uid != server->m.mounted_uid) return -EACCES; - } + if (server->m.mounted_vol[0]) { struct dentry* dentry = inode->i_sb->s_root; @@ -408,6 +408,7 @@ static int __ncp_ioctl(struct inode *inode, struct file *filp, return -EFAULT; return 0; } + case NCP_IOC_SETROOT: { struct ncp_setroot_ioctl sr; @@ -455,11 +456,10 @@ static int __ncp_ioctl(struct inode *inode, struct file *filp, #ifdef CONFIG_NCPFS_PACKET_SIGNING case NCP_IOC_SIGN_INIT: - if ((file_permission(filp, MAY_WRITE) != 0) - && (current->uid != server->m.mounted_uid)) - { + if (file_permission(filp, MAY_WRITE) != 0 + && uid != server->m.mounted_uid) return -EACCES; - } + if (argp) { if (server->sign_wanted) { @@ -478,24 +478,22 @@ static int __ncp_ioctl(struct inode *inode, struct file *filp, return 0; case NCP_IOC_SIGN_WANTED: - if ((file_permission(filp, MAY_READ) != 0) - && (current->uid != server->m.mounted_uid)) - { + if (file_permission(filp, MAY_READ) != 0 + && uid != server->m.mounted_uid) return -EACCES; - } if (put_user(server->sign_wanted, (int __user *)argp)) return -EFAULT; return 0; + case NCP_IOC_SET_SIGN_WANTED: { int newstate; - if ((file_permission(filp, MAY_WRITE) != 0) - && (current->uid != server->m.mounted_uid)) - { + if (file_permission(filp, MAY_WRITE) != 0 + && uid != server->m.mounted_uid) return -EACCES; - } + /* get only low 8 bits... */ if (get_user(newstate, (unsigned char __user *)argp)) return -EFAULT; @@ -512,11 +510,10 @@ static int __ncp_ioctl(struct inode *inode, struct file *filp, #ifdef CONFIG_NCPFS_IOCTL_LOCKING case NCP_IOC_LOCKUNLOCK: - if ((file_permission(filp, MAY_WRITE) != 0) - && (current->uid != server->m.mounted_uid)) - { + if (file_permission(filp, MAY_WRITE) != 0 + && uid != server->m.mounted_uid) return -EACCES; - } + { struct ncp_lock_ioctl rqdata; @@ -585,9 +582,8 @@ outrel: #ifdef CONFIG_COMPAT case NCP_IOC_GETOBJECTNAME_32: - if (current->uid != server->m.mounted_uid) { + if (uid != server->m.mounted_uid) return -EACCES; - } { struct compat_ncp_objectname_ioctl user; size_t outl; @@ -609,10 +605,10 @@ outrel: return 0; } #endif + case NCP_IOC_GETOBJECTNAME: - if (current->uid != server->m.mounted_uid) { + if (uid != server->m.mounted_uid) return -EACCES; - } { struct ncp_objectname_ioctl user; size_t outl; @@ -633,13 +629,13 @@ outrel: return -EFAULT; return 0; } + #ifdef CONFIG_COMPAT case NCP_IOC_SETOBJECTNAME_32: #endif case NCP_IOC_SETOBJECTNAME: - if (current->uid != server->m.mounted_uid) { + if (uid != server->m.mounted_uid) return -EACCES; - } { struct ncp_objectname_ioctl user; void* newname; @@ -691,13 +687,13 @@ outrel: kfree(oldname); return 0; } + #ifdef CONFIG_COMPAT case NCP_IOC_GETPRIVATEDATA_32: #endif case NCP_IOC_GETPRIVATEDATA: - if (current->uid != server->m.mounted_uid) { + if (uid != server->m.mounted_uid) return -EACCES; - } { struct ncp_privatedata_ioctl user; size_t outl; @@ -736,13 +732,13 @@ outrel: return 0; } + #ifdef CONFIG_COMPAT case NCP_IOC_SETPRIVATEDATA_32: #endif case NCP_IOC_SETPRIVATEDATA: - if (current->uid != server->m.mounted_uid) { + if (uid != server->m.mounted_uid) return -EACCES; - } { struct ncp_privatedata_ioctl user; void* new; @@ -794,9 +790,10 @@ outrel: #endif /* CONFIG_NCPFS_NLS */ case NCP_IOC_SETDENTRYTTL: - if ((file_permission(filp, MAY_WRITE) != 0) && - (current->uid != server->m.mounted_uid)) + if (file_permission(filp, MAY_WRITE) != 0 && + uid != server->m.mounted_uid) return -EACCES; + { u_int32_t user; diff --git a/fs/nfsctl.c b/fs/nfsctl.c index aed8145d908..b1acbd6ab6f 100644 --- a/fs/nfsctl.c +++ b/fs/nfsctl.c @@ -10,6 +10,8 @@ #include #include #include +#include +#include #include #include #include @@ -41,7 +43,8 @@ static struct file *do_open(char *name, int flags) error = may_open(&nd, MAY_WRITE, FMODE_WRITE); if (!error) - return dentry_open(nd.path.dentry, nd.path.mnt, flags); + return dentry_open(nd.path.dentry, nd.path.mnt, flags, + current_cred()); path_put(&nd.path); return ERR_PTR(error); diff --git a/fs/nfsd/auth.c b/fs/nfsd/auth.c index 294992e9bf6..0184fe9b514 100644 --- a/fs/nfsd/auth.c +++ b/fs/nfsd/auth.c @@ -27,53 +27,70 @@ int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp) int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp) { - struct svc_cred cred = rqstp->rq_cred; + struct group_info *rqgi; + struct group_info *gi; + struct cred *new; int i; int flags = nfsexp_flags(rqstp, exp); int ret; - if (flags & NFSEXP_ALLSQUASH) { - cred.cr_uid = exp->ex_anon_uid; - cred.cr_gid = exp->ex_anon_gid; - cred.cr_group_info = groups_alloc(0); - } else if (flags & NFSEXP_ROOTSQUASH) { - struct group_info *gi; - if (!cred.cr_uid) - cred.cr_uid = exp->ex_anon_uid; - if (!cred.cr_gid) - cred.cr_gid = exp->ex_anon_gid; - gi = groups_alloc(cred.cr_group_info->ngroups); - if (gi) - for (i = 0; i < cred.cr_group_info->ngroups; i++) { - if (!GROUP_AT(cred.cr_group_info, i)) - GROUP_AT(gi, i) = exp->ex_anon_gid; - else - GROUP_AT(gi, i) = GROUP_AT(cred.cr_group_info, i); - } - cred.cr_group_info = gi; - } else - get_group_info(cred.cr_group_info); - - if (cred.cr_uid != (uid_t) -1) - current->fsuid = cred.cr_uid; - else - current->fsuid = exp->ex_anon_uid; - if (cred.cr_gid != (gid_t) -1) - current->fsgid = cred.cr_gid; - else - current->fsgid = exp->ex_anon_gid; - - if (!cred.cr_group_info) + /* discard any old override before preparing the new set */ + revert_creds(get_cred(current->real_cred)); + new = prepare_creds(); + if (!new) return -ENOMEM; - ret = set_current_groups(cred.cr_group_info); - put_group_info(cred.cr_group_info); - if ((cred.cr_uid)) { - current->cap_effective = - cap_drop_nfsd_set(current->cap_effective); + + new->fsuid = rqstp->rq_cred.cr_uid; + new->fsgid = rqstp->rq_cred.cr_gid; + + rqgi = rqstp->rq_cred.cr_group_info; + + if (flags & NFSEXP_ALLSQUASH) { + new->fsuid = exp->ex_anon_uid; + new->fsgid = exp->ex_anon_gid; + gi = groups_alloc(0); + } else if (flags & NFSEXP_ROOTSQUASH) { + if (!new->fsuid) + new->fsuid = exp->ex_anon_uid; + if (!new->fsgid) + new->fsgid = exp->ex_anon_gid; + + gi = groups_alloc(rqgi->ngroups); + if (!gi) + goto oom; + + for (i = 0; i < rqgi->ngroups; i++) { + if (!GROUP_AT(rqgi, i)) + GROUP_AT(gi, i) = exp->ex_anon_gid; + else + GROUP_AT(gi, i) = GROUP_AT(rqgi, i); + } } else { - current->cap_effective = - cap_raise_nfsd_set(current->cap_effective, - current->cap_permitted); + gi = get_group_info(rqgi); } + + if (new->fsuid == (uid_t) -1) + new->fsuid = exp->ex_anon_uid; + if (new->fsgid == (gid_t) -1) + new->fsgid = exp->ex_anon_gid; + + ret = set_groups(new, gi); + put_group_info(gi); + if (!ret) + goto error; + + if (new->uid) + new->cap_effective = cap_drop_nfsd_set(new->cap_effective); + else + new->cap_effective = cap_raise_nfsd_set(new->cap_effective, + new->cap_permitted); + put_cred(override_creds(new)); + return 0; + +oom: + ret = -ENOMEM; +error: + abort_creds(new); return ret; } + diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index b79ec930d9f..0f9d6efaa62 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -54,20 +54,26 @@ static struct path rec_dir; static int rec_dir_init = 0; -static void -nfs4_save_user(uid_t *saveuid, gid_t *savegid) +static int +nfs4_save_creds(const struct cred **original_creds) { - *saveuid = current->fsuid; - *savegid = current->fsgid; - current->fsuid = 0; - current->fsgid = 0; + struct cred *new; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + new->fsuid = 0; + new->fsgid = 0; + *original_creds = override_creds(new); + put_cred(new); + return 0; } static void -nfs4_reset_user(uid_t saveuid, gid_t savegid) +nfs4_reset_creds(const struct cred *original) { - current->fsuid = saveuid; - current->fsgid = savegid; + revert_creds(original); } static void @@ -129,10 +135,9 @@ nfsd4_sync_rec_dir(void) int nfsd4_create_clid_dir(struct nfs4_client *clp) { + const struct cred *original_cred; char *dname = clp->cl_recdir; struct dentry *dentry; - uid_t uid; - gid_t gid; int status; dprintk("NFSD: nfsd4_create_clid_dir for \"%s\"\n", dname); @@ -140,7 +145,9 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) if (!rec_dir_init || clp->cl_firststate) return 0; - nfs4_save_user(&uid, &gid); + status = nfs4_save_creds(&original_cred); + if (status < 0) + return status; /* lock the parent */ mutex_lock(&rec_dir.dentry->d_inode->i_mutex); @@ -168,7 +175,7 @@ out_unlock: clp->cl_firststate = 1; nfsd4_sync_rec_dir(); } - nfs4_reset_user(uid, gid); + nfs4_reset_creds(original_cred); dprintk("NFSD: nfsd4_create_clid_dir returns %d\n", status); return status; } @@ -211,26 +218,29 @@ nfsd4_build_dentrylist(void *arg, const char *name, int namlen, static int nfsd4_list_rec_dir(struct dentry *dir, recdir_func *f) { + const struct cred *original_cred; struct file *filp; struct dentry_list_arg dla = { .parent = dir, }; struct list_head *dentries = &dla.dentries; struct dentry_list *child; - uid_t uid; - gid_t gid; int status; if (!rec_dir_init) return 0; - nfs4_save_user(&uid, &gid); + status = nfs4_save_creds(&original_cred); + if (status < 0) + return status; INIT_LIST_HEAD(dentries); - filp = dentry_open(dget(dir), mntget(rec_dir.mnt), O_RDONLY); + filp = dentry_open(dget(dir), mntget(rec_dir.mnt), O_RDONLY, + current_cred()); status = PTR_ERR(filp); if (IS_ERR(filp)) goto out; + INIT_LIST_HEAD(dentries); status = vfs_readdir(filp, nfsd4_build_dentrylist, &dla); fput(filp); while (!list_empty(dentries)) { @@ -249,7 +259,7 @@ out: dput(child->dentry); kfree(child); } - nfs4_reset_user(uid, gid); + nfs4_reset_creds(original_cred); return status; } @@ -311,8 +321,7 @@ out: void nfsd4_remove_clid_dir(struct nfs4_client *clp) { - uid_t uid; - gid_t gid; + const struct cred *original_cred; int status; if (!rec_dir_init || !clp->cl_firststate) @@ -322,9 +331,13 @@ nfsd4_remove_clid_dir(struct nfs4_client *clp) if (status) goto out; clp->cl_firststate = 0; - nfs4_save_user(&uid, &gid); + + status = nfs4_save_creds(&original_cred); + if (status < 0) + goto out; + status = nfsd4_unlink_clid_dir(clp->cl_recdir, HEXDIR_LEN-1); - nfs4_reset_user(uid, gid); + nfs4_reset_creds(original_cred); if (status == 0) nfsd4_sync_rec_dir(); mnt_drop_write(rec_dir.mnt); @@ -401,16 +414,21 @@ nfsd4_recdir_load(void) { void nfsd4_init_recdir(char *rec_dirname) { - uid_t uid = 0; - gid_t gid = 0; - int status; + const struct cred *original_cred; + int status; printk("NFSD: Using %s as the NFSv4 state recovery directory\n", rec_dirname); BUG_ON(rec_dir_init); - nfs4_save_user(&uid, &gid); + status = nfs4_save_creds(&original_cred); + if (status < 0) { + printk("NFSD: Unable to change credentials to find recovery" + " directory: error %d\n", + status); + return; + } status = kern_path(rec_dirname, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &rec_dir); @@ -420,7 +438,7 @@ nfsd4_init_recdir(char *rec_dirname) if (!status) rec_dir_init = 1; - nfs4_reset_user(uid, gid); + nfs4_reset_creds(original_cred); } void diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index cd25d91895a..f0da7d9c3a9 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -186,9 +186,14 @@ static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp) * access control settings being in effect, we cannot * fix that case easily. */ - current->cap_effective = - cap_raise_nfsd_set(current->cap_effective, - current->cap_permitted); + struct cred *new = prepare_creds(); + if (!new) + return nfserrno(-ENOMEM); + new->cap_effective = + cap_raise_nfsd_set(new->cap_effective, + new->cap_permitted); + put_cred(override_creds(new)); + put_cred(new); } else { error = nfsd_setuser_and_check_port(rqstp, exp); if (error) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 4433c8f0016..d1c5f787b36 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -671,6 +671,7 @@ __be32 nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access, struct file **filp) { + const struct cred *cred = current_cred(); struct dentry *dentry; struct inode *inode; int flags = O_RDONLY|O_LARGEFILE; @@ -725,7 +726,7 @@ nfsd_open(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, DQUOT_INIT(inode); } *filp = dentry_open(dget(dentry), mntget(fhp->fh_export->ex_path.mnt), - flags); + flags, cred); if (IS_ERR(*filp)) host_err = PTR_ERR(*filp); out_nfserr: @@ -1169,7 +1170,7 @@ nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp, * send along the gid on create when it tries to implement * setgid directories via NFS: */ - if (current->fsuid != 0) + if (current_fsuid() != 0) iap->ia_valid &= ~(ATTR_UID|ATTR_GID); if (iap->ia_valid) return nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0); @@ -2001,7 +2002,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, IS_APPEND(inode)? " append" : "", __mnt_is_readonly(exp->ex_path.mnt)? " ro" : ""); dprintk(" owner %d/%d user %d/%d\n", - inode->i_uid, inode->i_gid, current->fsuid, current->fsgid); + inode->i_uid, inode->i_gid, current_fsuid(), current_fsgid()); #endif /* Normally we reject any write/sattr etc access on a read-only file @@ -2044,7 +2045,7 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, * with NFSv3. */ if ((acc & NFSD_MAY_OWNER_OVERRIDE) && - inode->i_uid == current->fsuid) + inode->i_uid == current_fsuid()) return 0; /* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */ diff --git a/fs/ocfs2/dlm/dlmfs.c b/fs/ocfs2/dlm/dlmfs.c index ba962d71b34..6f7a77d5402 100644 --- a/fs/ocfs2/dlm/dlmfs.c +++ b/fs/ocfs2/dlm/dlmfs.c @@ -339,8 +339,8 @@ static struct inode *dlmfs_get_root_inode(struct super_block *sb) ip = DLMFS_I(inode); inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -365,8 +365,8 @@ static struct inode *dlmfs_get_inode(struct inode *parent, return NULL; inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &dlmfs_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c index f4967e634ff..2545e7402ef 100644 --- a/fs/ocfs2/namei.c +++ b/fs/ocfs2/namei.c @@ -421,13 +421,13 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb, fe->i_blkno = cpu_to_le64(fe_blkno); fe->i_suballoc_bit = cpu_to_le16(suballoc_bit); fe->i_suballoc_slot = cpu_to_le16(inode_ac->ac_alloc_slot); - fe->i_uid = cpu_to_le32(current->fsuid); + fe->i_uid = cpu_to_le32(current_fsuid()); if (dir->i_mode & S_ISGID) { fe->i_gid = cpu_to_le32(dir->i_gid); if (S_ISDIR(mode)) mode |= S_ISGID; } else - fe->i_gid = cpu_to_le32(current->fsgid); + fe->i_gid = cpu_to_le32(current_fsgid()); fe->i_mode = cpu_to_le16(mode); if (S_ISCHR(mode) || S_ISBLK(mode)) fe->id1.dev1.i_rdev = cpu_to_le64(huge_encode_dev(dev)); diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c index cbf047a847c..6afe57c84f8 100644 --- a/fs/omfs/inode.c +++ b/fs/omfs/inode.c @@ -37,8 +37,8 @@ struct inode *omfs_new_inode(struct inode *dir, int mode) inode->i_ino = new_block; inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_mapping->a_ops = &omfs_aops; @@ -420,8 +420,8 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent) sb->s_fs_info = sbi; - sbi->s_uid = current->uid; - sbi->s_gid = current->gid; + sbi->s_uid = current_uid(); + sbi->s_gid = current_gid(); sbi->s_dmask = sbi->s_fmask = current->fs->umask; if (!parse_options((char *) data, sbi)) diff --git a/fs/open.c b/fs/open.c index 83cdb9dee0c..c0a426d5766 100644 --- a/fs/open.c +++ b/fs/open.c @@ -425,39 +425,33 @@ out: */ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode) { + const struct cred *old_cred; + struct cred *override_cred; struct path path; struct inode *inode; - int old_fsuid, old_fsgid; - kernel_cap_t uninitialized_var(old_cap); /* !SECURE_NO_SETUID_FIXUP */ int res; if (mode & ~S_IRWXO) /* where's F_OK, X_OK, W_OK, R_OK? */ return -EINVAL; - old_fsuid = current->fsuid; - old_fsgid = current->fsgid; + override_cred = prepare_creds(); + if (!override_cred) + return -ENOMEM; - current->fsuid = current->uid; - current->fsgid = current->gid; + override_cred->fsuid = override_cred->uid; + override_cred->fsgid = override_cred->gid; if (!issecure(SECURE_NO_SETUID_FIXUP)) { - /* - * Clear the capabilities if we switch to a non-root user - */ -#ifndef CONFIG_SECURITY_FILE_CAPABILITIES - /* - * FIXME: There is a race here against sys_capset. The - * capabilities can change yet we will restore the old - * value below. We should hold task_capabilities_lock, - * but we cannot because user_path_at can sleep. - */ -#endif /* ndef CONFIG_SECURITY_FILE_CAPABILITIES */ - if (current->uid) - old_cap = cap_set_effective(__cap_empty_set); + /* Clear the capabilities if we switch to a non-root user */ + if (override_cred->uid) + cap_clear(override_cred->cap_effective); else - old_cap = cap_set_effective(current->cap_permitted); + override_cred->cap_effective = + override_cred->cap_permitted; } + old_cred = override_creds(override_cred); + res = user_path_at(dfd, filename, LOOKUP_FOLLOW, &path); if (res) goto out; @@ -494,12 +488,8 @@ asmlinkage long sys_faccessat(int dfd, const char __user *filename, int mode) out_path_release: path_put(&path); out: - current->fsuid = old_fsuid; - current->fsgid = old_fsgid; - - if (!issecure(SECURE_NO_SETUID_FIXUP)) - cap_set_effective(old_cap); - + revert_creds(old_cred); + put_cred(override_cred); return res; } @@ -792,7 +782,8 @@ static inline int __get_file_write_access(struct inode *inode, static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags, struct file *f, - int (*open)(struct inode *, struct file *)) + int (*open)(struct inode *, struct file *), + const struct cred *cred) { struct inode *inode; int error; @@ -816,7 +807,7 @@ static struct file *__dentry_open(struct dentry *dentry, struct vfsmount *mnt, f->f_op = fops_get(inode->i_fop); file_move(f, &inode->i_sb->s_files); - error = security_dentry_open(f); + error = security_dentry_open(f, cred); if (error) goto cleanup_all; @@ -891,6 +882,8 @@ cleanup_file: struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry, int (*open)(struct inode *, struct file *)) { + const struct cred *cred = current_cred(); + if (IS_ERR(nd->intent.open.file)) goto out; if (IS_ERR(dentry)) @@ -898,7 +891,7 @@ struct file *lookup_instantiate_filp(struct nameidata *nd, struct dentry *dentry nd->intent.open.file = __dentry_open(dget(dentry), mntget(nd->path.mnt), nd->intent.open.flags - 1, nd->intent.open.file, - open); + open, cred); out: return nd->intent.open.file; out_err: @@ -917,6 +910,7 @@ EXPORT_SYMBOL_GPL(lookup_instantiate_filp); */ struct file *nameidata_to_filp(struct nameidata *nd, int flags) { + const struct cred *cred = current_cred(); struct file *filp; /* Pick up the filp from the open intent */ @@ -924,7 +918,7 @@ struct file *nameidata_to_filp(struct nameidata *nd, int flags) /* Has the filesystem initialised the file for us? */ if (filp->f_path.dentry == NULL) filp = __dentry_open(nd->path.dentry, nd->path.mnt, flags, filp, - NULL); + NULL, cred); else path_put(&nd->path); return filp; @@ -934,7 +928,8 @@ struct file *nameidata_to_filp(struct nameidata *nd, int flags) * dentry_open() will have done dput(dentry) and mntput(mnt) if it returns an * error. */ -struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags) +struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags, + const struct cred *cred) { int error; struct file *f; @@ -959,7 +954,7 @@ struct file *dentry_open(struct dentry *dentry, struct vfsmount *mnt, int flags) return ERR_PTR(error); } - return __dentry_open(dentry, mnt, flags, f, NULL); + return __dentry_open(dentry, mnt, flags, f, NULL, cred); } EXPORT_SYMBOL(dentry_open); diff --git a/fs/pipe.c b/fs/pipe.c index 7aea8b89baa..aaf797bd57b 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -899,8 +899,8 @@ static struct inode * get_pipe_inode(void) */ inode->i_state = I_DIRTY; inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; return inode; diff --git a/fs/posix_acl.c b/fs/posix_acl.c index aec931e0997..39df95a0ec2 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -217,11 +217,11 @@ posix_acl_permission(struct inode *inode, const struct posix_acl *acl, int want) switch(pa->e_tag) { case ACL_USER_OBJ: /* (May have been checked already) */ - if (inode->i_uid == current->fsuid) + if (inode->i_uid == current_fsuid()) goto check_perm; break; case ACL_USER: - if (pa->e_id == current->fsuid) + if (pa->e_id == current_fsuid()) goto mask; break; case ACL_GROUP_OBJ: diff --git a/fs/proc/array.c b/fs/proc/array.c index 6af7fba7abb..7e4877d9dcb 100644 --- a/fs/proc/array.c +++ b/fs/proc/array.c @@ -159,6 +159,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, struct group_info *group_info; int g; struct fdtable *fdt = NULL; + const struct cred *cred; pid_t ppid, tpid; rcu_read_lock(); @@ -170,6 +171,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, if (tracer) tpid = task_pid_nr_ns(tracer, ns); } + cred = get_cred((struct cred *) __task_cred(p)); seq_printf(m, "State:\t%s\n" "Tgid:\t%d\n" @@ -182,8 +184,8 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, task_tgid_nr_ns(p, ns), pid_nr_ns(pid, ns), ppid, tpid, - p->uid, p->euid, p->suid, p->fsuid, - p->gid, p->egid, p->sgid, p->fsgid); + cred->uid, cred->euid, cred->suid, cred->fsuid, + cred->gid, cred->egid, cred->sgid, cred->fsgid); task_lock(p); if (p->files) @@ -194,13 +196,12 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns, fdt ? fdt->max_fds : 0); rcu_read_unlock(); - group_info = p->group_info; - get_group_info(group_info); + group_info = cred->group_info; task_unlock(p); for (g = 0; g < min(group_info->ngroups, NGROUPS_SMALL); g++) seq_printf(m, "%d ", GROUP_AT(group_info, g)); - put_group_info(group_info); + put_cred(cred); seq_printf(m, "\n"); } @@ -262,7 +263,7 @@ static inline void task_sig(struct seq_file *m, struct task_struct *p) blocked = p->blocked; collect_sigign_sigcatch(p, &ignored, &caught); num_threads = atomic_read(&p->signal->count); - qsize = atomic_read(&p->user->sigpending); + qsize = atomic_read(&__task_cred(p)->user->sigpending); qlim = p->signal->rlim[RLIMIT_SIGPENDING].rlim_cur; unlock_task_sighand(p, &flags); } @@ -293,10 +294,21 @@ static void render_cap_t(struct seq_file *m, const char *header, static inline void task_cap(struct seq_file *m, struct task_struct *p) { - render_cap_t(m, "CapInh:\t", &p->cap_inheritable); - render_cap_t(m, "CapPrm:\t", &p->cap_permitted); - render_cap_t(m, "CapEff:\t", &p->cap_effective); - render_cap_t(m, "CapBnd:\t", &p->cap_bset); + const struct cred *cred; + kernel_cap_t cap_inheritable, cap_permitted, cap_effective, cap_bset; + + rcu_read_lock(); + cred = __task_cred(p); + cap_inheritable = cred->cap_inheritable; + cap_permitted = cred->cap_permitted; + cap_effective = cred->cap_effective; + cap_bset = cred->cap_bset; + rcu_read_unlock(); + + render_cap_t(m, "CapInh:\t", &cap_inheritable); + render_cap_t(m, "CapPrm:\t", &cap_permitted); + render_cap_t(m, "CapEff:\t", &cap_effective); + render_cap_t(m, "CapBnd:\t", &cap_bset); } static inline void task_context_switch_counts(struct seq_file *m, diff --git a/fs/proc/base.c b/fs/proc/base.c index d4677603c88..0a8a5f88034 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1406,6 +1406,7 @@ static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_st { struct inode * inode; struct proc_inode *ei; + const struct cred *cred; /* We need a new inode */ @@ -1428,8 +1429,11 @@ static struct inode *proc_pid_make_inode(struct super_block * sb, struct task_st inode->i_uid = 0; inode->i_gid = 0; if (task_dumpable(task)) { - inode->i_uid = task->euid; - inode->i_gid = task->egid; + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; + rcu_read_unlock(); } security_task_to_inode(task, inode); @@ -1445,6 +1449,8 @@ static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat { struct inode *inode = dentry->d_inode; struct task_struct *task; + const struct cred *cred; + generic_fillattr(inode, stat); rcu_read_lock(); @@ -1454,8 +1460,9 @@ static int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat if (task) { if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || task_dumpable(task)) { - stat->uid = task->euid; - stat->gid = task->egid; + cred = __task_cred(task); + stat->uid = cred->euid; + stat->gid = cred->egid; } } rcu_read_unlock(); @@ -1483,11 +1490,16 @@ static int pid_revalidate(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; struct task_struct *task = get_proc_task(inode); + const struct cred *cred; + if (task) { if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) || task_dumpable(task)) { - inode->i_uid = task->euid; - inode->i_gid = task->egid; + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; + rcu_read_unlock(); } else { inode->i_uid = 0; inode->i_gid = 0; @@ -1649,6 +1661,7 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) struct task_struct *task = get_proc_task(inode); int fd = proc_fd(inode); struct files_struct *files; + const struct cred *cred; if (task) { files = get_files_struct(task); @@ -1658,8 +1671,11 @@ static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd) rcu_read_unlock(); put_files_struct(files); if (task_dumpable(task)) { - inode->i_uid = task->euid; - inode->i_gid = task->egid; + rcu_read_lock(); + cred = __task_cred(task); + inode->i_uid = cred->euid; + inode->i_gid = cred->egid; + rcu_read_unlock(); } else { inode->i_uid = 0; inode->i_gid = 0; diff --git a/fs/quota.c b/fs/quota.c index 7f4386ebc23..b7fe44e0161 100644 --- a/fs/quota.c +++ b/fs/quota.c @@ -79,7 +79,7 @@ static int generic_quotactl_valid(struct super_block *sb, int type, int cmd, qid /* Check privileges */ if (cmd == Q_GETQUOTA) { - if (((type == USRQUOTA && current->euid != id) || + if (((type == USRQUOTA && current_euid() != id) || (type == GRPQUOTA && !in_egroup_p(id))) && !capable(CAP_SYS_ADMIN)) return -EPERM; @@ -130,7 +130,7 @@ static int xqm_quotactl_valid(struct super_block *sb, int type, int cmd, qid_t i /* Check privileges */ if (cmd == Q_XGETQUOTA) { - if (((type == XQM_USRQUOTA && current->euid != id) || + if (((type == XQM_USRQUOTA && current_euid() != id) || (type == XQM_GRPQUOTA && !in_egroup_p(id))) && !capable(CAP_SYS_ADMIN)) return -EPERM; diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c index f031d1c925f..a83a3518ae3 100644 --- a/fs/ramfs/inode.c +++ b/fs/ramfs/inode.c @@ -55,8 +55,8 @@ struct inode *ramfs_get_inode(struct super_block *sb, int mode, dev_t dev) if (inode) { inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_mapping->a_ops = &ramfs_aops; inode->i_mapping->backing_dev_info = &ramfs_backing_dev_info; diff --git a/fs/reiserfs/namei.c b/fs/reiserfs/namei.c index f89ebb943f3..4f322e5ed84 100644 --- a/fs/reiserfs/namei.c +++ b/fs/reiserfs/namei.c @@ -573,7 +573,7 @@ static int new_inode_init(struct inode *inode, struct inode *dir, int mode) /* the quota init calls have to know who to charge the quota to, so ** we have to set uid and gid here */ - inode->i_uid = current->fsuid; + inode->i_uid = current_fsuid(); inode->i_mode = mode; /* Make inode invalid - just in case we are going to drop it before * the initialization happens */ @@ -584,7 +584,7 @@ static int new_inode_init(struct inode *inode, struct inode *dir, int mode) if (S_ISDIR(mode)) inode->i_mode |= S_ISGID; } else { - inode->i_gid = current->fsgid; + inode->i_gid = current_fsgid(); } DQUOT_INIT(inode); return 0; diff --git a/fs/smbfs/dir.c b/fs/smbfs/dir.c index 48da4fa6b7d..e7ddd0328dd 100644 --- a/fs/smbfs/dir.c +++ b/fs/smbfs/dir.c @@ -667,8 +667,7 @@ smb_make_node(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) attr.ia_valid = ATTR_MODE | ATTR_UID | ATTR_GID; attr.ia_mode = mode; - attr.ia_uid = current->euid; - attr.ia_gid = current->egid; + current_euid_egid(&attr.ia_uid, &attr.ia_gid); if (!new_valid_dev(dev)) return -EINVAL; diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c index 3528f40ffb0..fc27fbfc539 100644 --- a/fs/smbfs/inode.c +++ b/fs/smbfs/inode.c @@ -586,7 +586,7 @@ static int smb_fill_super(struct super_block *sb, void *raw_data, int silent) if (parse_options(mnt, raw_data)) goto out_bad_option; } - mnt->mounted_uid = current->uid; + mnt->mounted_uid = current_uid(); smb_setcodepage(server, &mnt->codepage); /* diff --git a/fs/smbfs/proc.c b/fs/smbfs/proc.c index ee536e8a649..9468168b9af 100644 --- a/fs/smbfs/proc.c +++ b/fs/smbfs/proc.c @@ -864,7 +864,7 @@ smb_newconn(struct smb_sb_info *server, struct smb_conn_opt *opt) goto out; error = -EACCES; - if (current->uid != server->mnt->mounted_uid && + if (current_uid() != server->mnt->mounted_uid && !capable(CAP_SYS_ADMIN)) goto out; diff --git a/fs/super.c b/fs/super.c index 400a7608f15..ddba069d7a9 100644 --- a/fs/super.c +++ b/fs/super.c @@ -914,7 +914,7 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void goto out_free_secdata; BUG_ON(!mnt->mnt_sb); - error = security_sb_kern_mount(mnt->mnt_sb, secdata); + error = security_sb_kern_mount(mnt->mnt_sb, flags, secdata); if (error) goto out_sb; diff --git a/fs/sysv/ialloc.c b/fs/sysv/ialloc.c index 115ab0d6f4b..241e9765cfa 100644 --- a/fs/sysv/ialloc.c +++ b/fs/sysv/ialloc.c @@ -165,9 +165,9 @@ struct inode * sysv_new_inode(const struct inode * dir, mode_t mode) if (S_ISDIR(mode)) mode |= S_ISGID; } else - inode->i_gid = current->fsgid; + inode->i_gid = current_fsgid(); - inode->i_uid = current->fsuid; + inode->i_uid = current_fsuid(); inode->i_ino = fs16_to_cpu(sbi, ino); inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME_SEC; inode->i_blocks = 0; diff --git a/fs/ubifs/budget.c b/fs/ubifs/budget.c index 1a4973e1066..4a18f084cc4 100644 --- a/fs/ubifs/budget.c +++ b/fs/ubifs/budget.c @@ -363,7 +363,7 @@ long long ubifs_calc_available(const struct ubifs_info *c, int min_idx_lebs) */ static int can_use_rp(struct ubifs_info *c) { - if (current->fsuid == c->rp_uid || capable(CAP_SYS_RESOURCE) || + if (current_fsuid() == c->rp_uid || capable(CAP_SYS_RESOURCE) || (c->rp_gid != 0 && in_group_p(c->rp_gid))) return 1; return 0; diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c index 0422c98e179..f448ab1f9c3 100644 --- a/fs/ubifs/dir.c +++ b/fs/ubifs/dir.c @@ -104,13 +104,13 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, const struct inode *dir, */ inode->i_flags |= (S_NOCMTIME); - inode->i_uid = current->fsuid; + inode->i_uid = current_fsuid(); if (dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; if (S_ISDIR(mode)) mode |= S_ISGID; } else - inode->i_gid = current->fsgid; + inode->i_gid = current_fsgid(); inode->i_mode = mode; inode->i_mtime = inode->i_atime = inode->i_ctime = ubifs_current_time(inode); diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c index a4f2b3ce45b..31fc84297dd 100644 --- a/fs/udf/ialloc.c +++ b/fs/udf/ialloc.c @@ -126,13 +126,13 @@ struct inode *udf_new_inode(struct inode *dir, int mode, int *err) } mutex_unlock(&sbi->s_alloc_mutex); inode->i_mode = mode; - inode->i_uid = current->fsuid; + inode->i_uid = current_fsuid(); if (dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; if (S_ISDIR(mode)) mode |= S_ISGID; } else { - inode->i_gid = current->fsgid; + inode->i_gid = current_fsgid(); } iinfo->i_location.logicalBlockNum = block; diff --git a/fs/udf/namei.c b/fs/udf/namei.c index 082409cd4b8..f84bfaa8d94 100644 --- a/fs/udf/namei.c +++ b/fs/udf/namei.c @@ -604,7 +604,7 @@ static int udf_mknod(struct inode *dir, struct dentry *dentry, int mode, goto out; iinfo = UDF_I(inode); - inode->i_uid = current->fsuid; + inode->i_uid = current_fsuid(); init_special_inode(inode, mode, rdev); fi = udf_add_entry(dir, dentry, &fibh, &cfi, &err); if (!fi) { diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c index ac181f6806a..6f5dcf00609 100644 --- a/fs/ufs/ialloc.c +++ b/fs/ufs/ialloc.c @@ -304,13 +304,13 @@ cg_found: inode->i_ino = cg * uspi->s_ipg + bit; inode->i_mode = mode; - inode->i_uid = current->fsuid; + inode->i_uid = current_fsuid(); if (dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; if (S_ISDIR(mode)) inode->i_mode |= S_ISGID; } else - inode->i_gid = current->fsgid; + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_generation = 0; diff --git a/fs/xfs/linux-2.6/xfs_cred.h b/fs/xfs/linux-2.6/xfs_cred.h index 652721ce0ea..8c022cd0ad6 100644 --- a/fs/xfs/linux-2.6/xfs_cred.h +++ b/fs/xfs/linux-2.6/xfs_cred.h @@ -23,11 +23,9 @@ /* * Credentials */ -typedef struct cred { - /* EMPTY */ -} cred_t; +typedef const struct cred cred_t; -extern struct cred *sys_cred; +extern cred_t *sys_cred; /* this is a hack.. (assumes sys_cred is the only cred_t in the system) */ static inline int capable_cred(cred_t *cr, int cid) diff --git a/fs/xfs/linux-2.6/xfs_globals.h b/fs/xfs/linux-2.6/xfs_globals.h index 2770b0085ee..6eda8a3eb6f 100644 --- a/fs/xfs/linux-2.6/xfs_globals.h +++ b/fs/xfs/linux-2.6/xfs_globals.h @@ -19,6 +19,6 @@ #define __XFS_GLOBALS_H__ extern uint64_t xfs_panic_mask; /* set to cause more panics */ -extern struct cred *sys_cred; +extern cred_t *sys_cred; #endif /* __XFS_GLOBALS_H__ */ diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c index d3438c72dca..281cbd5a25c 100644 --- a/fs/xfs/linux-2.6/xfs_ioctl.c +++ b/fs/xfs/linux-2.6/xfs_ioctl.c @@ -256,6 +256,7 @@ xfs_open_by_handle( struct file *parfilp, struct inode *parinode) { + const struct cred *cred = current_cred(); int error; int new_fd; int permflag; @@ -321,7 +322,7 @@ xfs_open_by_handle( mntget(parfilp->f_path.mnt); /* Create file pointer. */ - filp = dentry_open(dentry, parfilp->f_path.mnt, hreq.oflags); + filp = dentry_open(dentry, parfilp->f_path.mnt, hreq.oflags, cred); if (IS_ERR(filp)) { put_unused_fd(new_fd); return -XFS_ERROR(-PTR_ERR(filp)); @@ -1007,7 +1008,7 @@ xfs_ioctl_setattr( * to the file owner ID, except in cases where the * CAP_FSETID capability is applicable. */ - if (current->fsuid != ip->i_d.di_uid && !capable(CAP_FOWNER)) { + if (current_fsuid() != ip->i_d.di_uid && !capable(CAP_FOWNER)) { code = XFS_ERROR(EPERM); goto error_return; } diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c index b2f639a1416..91d69338d3b 100644 --- a/fs/xfs/xfs_acl.c +++ b/fs/xfs/xfs_acl.c @@ -366,7 +366,7 @@ xfs_acl_allow_set( return ENOTDIR; if (vp->i_sb->s_flags & MS_RDONLY) return EROFS; - if (XFS_I(vp)->i_d.di_uid != current->fsuid && !capable(CAP_FOWNER)) + if (XFS_I(vp)->i_d.di_uid != current_fsuid() && !capable(CAP_FOWNER)) return EPERM; return 0; } @@ -413,13 +413,13 @@ xfs_acl_access( switch (fap->acl_entry[i].ae_tag) { case ACL_USER_OBJ: seen_userobj = 1; - if (fuid != current->fsuid) + if (fuid != current_fsuid()) continue; matched.ae_tag = ACL_USER_OBJ; matched.ae_perm = allows; break; case ACL_USER: - if (fap->acl_entry[i].ae_id != current->fsuid) + if (fap->acl_entry[i].ae_id != current_fsuid()) continue; matched.ae_tag = ACL_USER; matched.ae_perm = allows; diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h index 1420c49674d..6be310d41da 100644 --- a/fs/xfs/xfs_inode.h +++ b/fs/xfs/xfs_inode.h @@ -497,7 +497,7 @@ int xfs_iread(struct xfs_mount *, struct xfs_trans *, xfs_ino_t, xfs_inode_t **, xfs_daddr_t, uint); int xfs_iread_extents(struct xfs_trans *, xfs_inode_t *, int); int xfs_ialloc(struct xfs_trans *, xfs_inode_t *, mode_t, - xfs_nlink_t, xfs_dev_t, struct cred *, xfs_prid_t, + xfs_nlink_t, xfs_dev_t, cred_t *, xfs_prid_t, int, struct xfs_buf **, boolean_t *, xfs_inode_t **); void xfs_dinode_from_disk(struct xfs_icdinode *, struct xfs_dinode_core *); diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h index e932a96bec5..7b0c2ab8833 100644 --- a/fs/xfs/xfs_vnodeops.h +++ b/fs/xfs/xfs_vnodeops.h @@ -16,7 +16,7 @@ struct xfs_iomap; int xfs_open(struct xfs_inode *ip); int xfs_setattr(struct xfs_inode *ip, struct iattr *vap, int flags, - struct cred *credp); + cred_t *credp); #define XFS_ATTR_DMI 0x01 /* invocation from a DMI function */ #define XFS_ATTR_NONBLOCK 0x02 /* return EAGAIN if operation would block */ #define XFS_ATTR_NOLOCK 0x04 /* Don't grab any conflicting locks */ @@ -28,24 +28,24 @@ int xfs_inactive(struct xfs_inode *ip); int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name, struct xfs_inode **ipp, struct xfs_name *ci_name); int xfs_create(struct xfs_inode *dp, struct xfs_name *name, mode_t mode, - xfs_dev_t rdev, struct xfs_inode **ipp, struct cred *credp); + xfs_dev_t rdev, struct xfs_inode **ipp, cred_t *credp); int xfs_remove(struct xfs_inode *dp, struct xfs_name *name, struct xfs_inode *ip); int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip, struct xfs_name *target_name); int xfs_mkdir(struct xfs_inode *dp, struct xfs_name *dir_name, - mode_t mode, struct xfs_inode **ipp, struct cred *credp); + mode_t mode, struct xfs_inode **ipp, cred_t *credp); int xfs_readdir(struct xfs_inode *dp, void *dirent, size_t bufsize, xfs_off_t *offset, filldir_t filldir); int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name, const char *target_path, mode_t mode, struct xfs_inode **ipp, - struct cred *credp); + cred_t *credp); int xfs_inode_flush(struct xfs_inode *ip, int flags); int xfs_set_dmattrs(struct xfs_inode *ip, u_int evmask, u_int16_t state); int xfs_reclaim(struct xfs_inode *ip); int xfs_change_file_space(struct xfs_inode *ip, int cmd, xfs_flock64_t *bf, xfs_off_t offset, - struct cred *credp, int attr_flags); + cred_t *credp, int attr_flags); int xfs_rename(struct xfs_inode *src_dp, struct xfs_name *src_name, struct xfs_inode *src_ip, struct xfs_inode *target_dp, struct xfs_name *target_name, struct xfs_inode *target_ip); diff --git a/include/keys/keyring-type.h b/include/keys/keyring-type.h new file mode 100644 index 00000000000..843f872a4b6 --- /dev/null +++ b/include/keys/keyring-type.h @@ -0,0 +1,31 @@ +/* Keyring key type + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _KEYS_KEYRING_TYPE_H +#define _KEYS_KEYRING_TYPE_H + +#include +#include + +/* + * the keyring payload contains a list of the keys to which the keyring is + * subscribed + */ +struct keyring_list { + struct rcu_head rcu; /* RCU deletion hook */ + unsigned short maxkeys; /* max keys this list can hold */ + unsigned short nkeys; /* number of keys currently held */ + unsigned short delkey; /* key to be unlinked by RCU */ + struct key *keys[0]; +}; + + +#endif /* _KEYS_KEYRING_TYPE_H */ diff --git a/include/linux/audit.h b/include/linux/audit.h index 8f0672d13eb..26c4f6f65a4 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -99,6 +99,8 @@ #define AUDIT_OBJ_PID 1318 /* ptrace target */ #define AUDIT_TTY 1319 /* Input on an administrative TTY */ #define AUDIT_EOE 1320 /* End of multi-record event */ +#define AUDIT_BPRM_FCAPS 1321 /* Information about fcaps increasing perms */ +#define AUDIT_CAPSET 1322 /* Record showing argument to sys_capset */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ @@ -453,6 +455,10 @@ extern int __audit_mq_timedsend(mqd_t mqdes, size_t msg_len, unsigned int msg_pr extern int __audit_mq_timedreceive(mqd_t mqdes, size_t msg_len, unsigned int __user *u_msg_prio, const struct timespec __user *u_abs_timeout); extern int __audit_mq_notify(mqd_t mqdes, const struct sigevent __user *u_notification); extern int __audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat); +extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm, + const struct cred *new, + const struct cred *old); +extern int __audit_log_capset(pid_t pid, const struct cred *new, const struct cred *old); static inline int audit_ipc_obj(struct kern_ipc_perm *ipcp) { @@ -502,6 +508,24 @@ static inline int audit_mq_getsetattr(mqd_t mqdes, struct mq_attr *mqstat) return __audit_mq_getsetattr(mqdes, mqstat); return 0; } + +static inline int audit_log_bprm_fcaps(struct linux_binprm *bprm, + const struct cred *new, + const struct cred *old) +{ + if (unlikely(!audit_dummy_context())) + return __audit_log_bprm_fcaps(bprm, new, old); + return 0; +} + +static inline int audit_log_capset(pid_t pid, const struct cred *new, + const struct cred *old) +{ + if (unlikely(!audit_dummy_context())) + return __audit_log_capset(pid, new, old); + return 0; +} + extern int audit_n_rules; extern int audit_signals; #else @@ -534,6 +558,8 @@ extern int audit_signals; #define audit_mq_timedreceive(d,l,p,t) ({ 0; }) #define audit_mq_notify(d,n) ({ 0; }) #define audit_mq_getsetattr(d,s) ({ 0; }) +#define audit_log_bprm_fcaps(b, ncr, ocr) ({ 0; }) +#define audit_log_capset(pid, ncr, ocr) ({ 0; }) #define audit_ptrace(t) ((void)0) #define audit_n_rules 0 #define audit_signals 0 diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h index 7394b5b349f..6cbfbe29718 100644 --- a/include/linux/binfmts.h +++ b/include/linux/binfmts.h @@ -35,16 +35,20 @@ struct linux_binprm{ struct mm_struct *mm; unsigned long p; /* current top of mem */ unsigned int sh_bang:1, - misc_bang:1; + misc_bang:1, + cred_prepared:1,/* true if creds already prepared (multiple + * preps happen for interpreters) */ + cap_effective:1;/* true if has elevated effective capabilities, + * false if not; except for init which inherits + * its parent's caps anyway */ #ifdef __alpha__ unsigned int taso:1; #endif unsigned int recursion_depth; struct file * file; - int e_uid, e_gid; - kernel_cap_t cap_post_exec_permitted; - bool cap_effective; - void *security; + struct cred *cred; /* new credentials */ + int unsafe; /* how unsafe this exec is (mask of LSM_UNSAFE_*) */ + unsigned int per_clear; /* bits to clear in current->personality */ int argc, envc; char * filename; /* Name of binary as seen by procps */ char * interp; /* Name of the binary really executed. Most @@ -101,7 +105,7 @@ extern int setup_arg_pages(struct linux_binprm * bprm, int executable_stack); extern int bprm_mm_init(struct linux_binprm *bprm); extern int copy_strings_kernel(int argc,char ** argv,struct linux_binprm *bprm); -extern void compute_creds(struct linux_binprm *binprm); +extern void install_exec_creds(struct linux_binprm *bprm); extern int do_coredump(long signr, int exit_code, struct pt_regs * regs); extern int set_binfmt(struct linux_binfmt *new); extern void free_bprm(struct linux_binprm *); diff --git a/include/linux/capability.h b/include/linux/capability.h index 9d1fe30b6f6..e22f48c2a46 100644 --- a/include/linux/capability.h +++ b/include/linux/capability.h @@ -53,6 +53,7 @@ typedef struct __user_cap_data_struct { #define XATTR_NAME_CAPS XATTR_SECURITY_PREFIX XATTR_CAPS_SUFFIX #define VFS_CAP_REVISION_MASK 0xFF000000 +#define VFS_CAP_REVISION_SHIFT 24 #define VFS_CAP_FLAGS_MASK ~VFS_CAP_REVISION_MASK #define VFS_CAP_FLAGS_EFFECTIVE 0x000001 @@ -68,6 +69,9 @@ typedef struct __user_cap_data_struct { #define VFS_CAP_U32 VFS_CAP_U32_2 #define VFS_CAP_REVISION VFS_CAP_REVISION_2 +#ifdef CONFIG_SECURITY_FILE_CAPABILITIES +extern int file_caps_enabled; +#endif struct vfs_cap_data { __le32 magic_etc; /* Little endian */ @@ -96,6 +100,13 @@ typedef struct kernel_cap_struct { __u32 cap[_KERNEL_CAPABILITY_U32S]; } kernel_cap_t; +/* exact same as vfs_cap_data but in cpu endian and always filled completely */ +struct cpu_vfs_cap_data { + __u32 magic_etc; + kernel_cap_t permitted; + kernel_cap_t inheritable; +}; + #define _USER_CAP_HEADER_SIZE (sizeof(struct __user_cap_header_struct)) #define _KERNEL_CAP_T_SIZE (sizeof(kernel_cap_t)) @@ -454,6 +465,13 @@ static inline int cap_isclear(const kernel_cap_t a) return 1; } +/* + * Check if "a" is a subset of "set". + * return 1 if ALL of the capabilities in "a" are also in "set" + * cap_issubset(0101, 1111) will return 1 + * return 0 if ANY of the capabilities in "a" are not in "set" + * cap_issubset(1111, 0101) will return 0 + */ static inline int cap_issubset(const kernel_cap_t a, const kernel_cap_t set) { kernel_cap_t dest; @@ -501,8 +519,6 @@ extern const kernel_cap_t __cap_empty_set; extern const kernel_cap_t __cap_full_set; extern const kernel_cap_t __cap_init_eff_set; -kernel_cap_t cap_set_effective(const kernel_cap_t pE_new); - /** * has_capability - Determine if a task has a superior capability available * @t: The task in question @@ -514,9 +530,14 @@ kernel_cap_t cap_set_effective(const kernel_cap_t pE_new); * Note that this does not set PF_SUPERPRIV on the task. */ #define has_capability(t, cap) (security_capable((t), (cap)) == 0) +#define has_capability_noaudit(t, cap) (security_capable_noaudit((t), (cap)) == 0) extern int capable(int cap); +/* audit system wants to get cap info from files as well */ +struct dentry; +extern int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps); + #endif /* __KERNEL__ */ #endif /* !_LINUX_CAPABILITY_H */ diff --git a/include/linux/cred.h b/include/linux/cred.h index b69222cc1fd..3282ee4318e 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -1,4 +1,4 @@ -/* Credentials management +/* Credentials management - see Documentation/credentials.txt * * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) @@ -12,39 +12,335 @@ #ifndef _LINUX_CRED_H #define _LINUX_CRED_H -#define get_current_user() (get_uid(current->user)) +#include +#include +#include -#define task_uid(task) ((task)->uid) -#define task_gid(task) ((task)->gid) -#define task_euid(task) ((task)->euid) -#define task_egid(task) ((task)->egid) +struct user_struct; +struct cred; +struct inode; -#define current_uid() (current->uid) -#define current_gid() (current->gid) -#define current_euid() (current->euid) -#define current_egid() (current->egid) -#define current_suid() (current->suid) -#define current_sgid() (current->sgid) -#define current_fsuid() (current->fsuid) -#define current_fsgid() (current->fsgid) -#define current_cap() (current->cap_effective) +/* + * COW Supplementary groups list + */ +#define NGROUPS_SMALL 32 +#define NGROUPS_PER_BLOCK ((unsigned int)(PAGE_SIZE / sizeof(gid_t))) + +struct group_info { + atomic_t usage; + int ngroups; + int nblocks; + gid_t small_block[NGROUPS_SMALL]; + gid_t *blocks[0]; +}; + +/** + * get_group_info - Get a reference to a group info structure + * @group_info: The group info to reference + * + * This gets a reference to a set of supplementary groups. + * + * If the caller is accessing a task's credentials, they must hold the RCU read + * lock when reading. + */ +static inline struct group_info *get_group_info(struct group_info *gi) +{ + atomic_inc(&gi->usage); + return gi; +} + +/** + * put_group_info - Release a reference to a group info structure + * @group_info: The group info to release + */ +#define put_group_info(group_info) \ +do { \ + if (atomic_dec_and_test(&(group_info)->usage)) \ + groups_free(group_info); \ +} while (0) + +extern struct group_info *groups_alloc(int); +extern struct group_info init_groups; +extern void groups_free(struct group_info *); +extern int set_current_groups(struct group_info *); +extern int set_groups(struct cred *, struct group_info *); +extern int groups_search(const struct group_info *, gid_t); + +/* access the groups "array" with this macro */ +#define GROUP_AT(gi, i) \ + ((gi)->blocks[(i) / NGROUPS_PER_BLOCK][(i) % NGROUPS_PER_BLOCK]) + +extern int in_group_p(gid_t); +extern int in_egroup_p(gid_t); + +/* + * The common credentials for a thread group + * - shared by CLONE_THREAD + */ +#ifdef CONFIG_KEYS +struct thread_group_cred { + atomic_t usage; + pid_t tgid; /* thread group process ID */ + spinlock_t lock; + struct key *session_keyring; /* keyring inherited over fork */ + struct key *process_keyring; /* keyring private to this process */ + struct rcu_head rcu; /* RCU deletion hook */ +}; +#endif + +/* + * The security context of a task + * + * The parts of the context break down into two categories: + * + * (1) The objective context of a task. These parts are used when some other + * task is attempting to affect this one. + * + * (2) The subjective context. These details are used when the task is acting + * upon another object, be that a file, a task, a key or whatever. + * + * Note that some members of this structure belong to both categories - the + * LSM security pointer for instance. + * + * A task has two security pointers. task->real_cred points to the objective + * context that defines that task's actual details. The objective part of this + * context is used whenever that task is acted upon. + * + * task->cred points to the subjective context that defines the details of how + * that task is going to act upon another object. This may be overridden + * temporarily to point to another security context, but normally points to the + * same context as task->real_cred. + */ +struct cred { + atomic_t usage; + uid_t uid; /* real UID of the task */ + gid_t gid; /* real GID of the task */ + uid_t suid; /* saved UID of the task */ + gid_t sgid; /* saved GID of the task */ + uid_t euid; /* effective UID of the task */ + gid_t egid; /* effective GID of the task */ + uid_t fsuid; /* UID for VFS ops */ + gid_t fsgid; /* GID for VFS ops */ + unsigned securebits; /* SUID-less security management */ + kernel_cap_t cap_inheritable; /* caps our children can inherit */ + kernel_cap_t cap_permitted; /* caps we're permitted */ + kernel_cap_t cap_effective; /* caps we can actually use */ + kernel_cap_t cap_bset; /* capability bounding set */ +#ifdef CONFIG_KEYS + unsigned char jit_keyring; /* default keyring to attach requested + * keys to */ + struct key *thread_keyring; /* keyring private to this thread */ + struct key *request_key_auth; /* assumed request_key authority */ + struct thread_group_cred *tgcred; /* thread-group shared credentials */ +#endif +#ifdef CONFIG_SECURITY + void *security; /* subjective LSM security */ +#endif + struct user_struct *user; /* real user ID subscription */ + struct group_info *group_info; /* supplementary groups for euid/fsgid */ + struct rcu_head rcu; /* RCU deletion hook */ +}; + +extern void __put_cred(struct cred *); +extern int copy_creds(struct task_struct *, unsigned long); +extern struct cred *prepare_creds(void); +extern struct cred *prepare_exec_creds(void); +extern struct cred *prepare_usermodehelper_creds(void); +extern int commit_creds(struct cred *); +extern void abort_creds(struct cred *); +extern const struct cred *override_creds(const struct cred *); +extern void revert_creds(const struct cred *); +extern struct cred *prepare_kernel_cred(struct task_struct *); +extern int change_create_files_as(struct cred *, struct inode *); +extern int set_security_override(struct cred *, u32); +extern int set_security_override_from_ctx(struct cred *, const char *); +extern int set_create_files_as(struct cred *, struct inode *); +extern void __init cred_init(void); + +/** + * get_new_cred - Get a reference on a new set of credentials + * @cred: The new credentials to reference + * + * Get a reference on the specified set of new credentials. The caller must + * release the reference. + */ +static inline struct cred *get_new_cred(struct cred *cred) +{ + atomic_inc(&cred->usage); + return cred; +} + +/** + * get_cred - Get a reference on a set of credentials + * @cred: The credentials to reference + * + * Get a reference on the specified set of credentials. The caller must + * release the reference. + * + * This is used to deal with a committed set of credentials. Although the + * pointer is const, this will temporarily discard the const and increment the + * usage count. The purpose of this is to attempt to catch at compile time the + * accidental alteration of a set of credentials that should be considered + * immutable. + */ +static inline const struct cred *get_cred(const struct cred *cred) +{ + return get_new_cred((struct cred *) cred); +} + +/** + * put_cred - Release a reference to a set of credentials + * @cred: The credentials to release + * + * Release a reference to a set of credentials, deleting them when the last ref + * is released. + * + * This takes a const pointer to a set of credentials because the credentials + * on task_struct are attached by const pointers to prevent accidental + * alteration of otherwise immutable credential sets. + */ +static inline void put_cred(const struct cred *_cred) +{ + struct cred *cred = (struct cred *) _cred; + + BUG_ON(atomic_read(&(cred)->usage) <= 0); + if (atomic_dec_and_test(&(cred)->usage)) + __put_cred(cred); +} + +/** + * current_cred - Access the current task's subjective credentials + * + * Access the subjective credentials of the current task. + */ +#define current_cred() \ + (current->cred) + +/** + * __task_cred - Access a task's objective credentials + * @task: The task to query + * + * Access the objective credentials of a task. The caller must hold the RCU + * readlock. + * + * The caller must make sure task doesn't go away, either by holding a ref on + * task or by holding tasklist_lock to prevent it from being unlinked. + */ +#define __task_cred(task) \ + ((const struct cred *)(rcu_dereference((task)->real_cred))) + +/** + * get_task_cred - Get another task's objective credentials + * @task: The task to query + * + * Get the objective credentials of a task, pinning them so that they can't go + * away. Accessing a task's credentials directly is not permitted. + * + * The caller must make sure task doesn't go away, either by holding a ref on + * task or by holding tasklist_lock to prevent it from being unlinked. + */ +#define get_task_cred(task) \ +({ \ + struct cred *__cred; \ + rcu_read_lock(); \ + __cred = (struct cred *) __task_cred((task)); \ + get_cred(__cred); \ + rcu_read_unlock(); \ + __cred; \ +}) + +/** + * get_current_cred - Get the current task's subjective credentials + * + * Get the subjective credentials of the current task, pinning them so that + * they can't go away. Accessing the current task's credentials directly is + * not permitted. + */ +#define get_current_cred() \ + (get_cred(current_cred())) + +/** + * get_current_user - Get the current task's user_struct + * + * Get the user record of the current task, pinning it so that it can't go + * away. + */ +#define get_current_user() \ +({ \ + struct user_struct *__u; \ + struct cred *__cred; \ + __cred = (struct cred *) current_cred(); \ + __u = get_uid(__cred->user); \ + __u; \ +}) + +/** + * get_current_groups - Get the current task's supplementary group list + * + * Get the supplementary group list of the current task, pinning it so that it + * can't go away. + */ +#define get_current_groups() \ +({ \ + struct group_info *__groups; \ + struct cred *__cred; \ + __cred = (struct cred *) current_cred(); \ + __groups = get_group_info(__cred->group_info); \ + __groups; \ +}) + +#define task_cred_xxx(task, xxx) \ +({ \ + __typeof__(((struct cred *)NULL)->xxx) ___val; \ + rcu_read_lock(); \ + ___val = __task_cred((task))->xxx; \ + rcu_read_unlock(); \ + ___val; \ +}) + +#define task_uid(task) (task_cred_xxx((task), uid)) +#define task_euid(task) (task_cred_xxx((task), euid)) + +#define current_cred_xxx(xxx) \ +({ \ + current->cred->xxx; \ +}) + +#define current_uid() (current_cred_xxx(uid)) +#define current_gid() (current_cred_xxx(gid)) +#define current_euid() (current_cred_xxx(euid)) +#define current_egid() (current_cred_xxx(egid)) +#define current_suid() (current_cred_xxx(suid)) +#define current_sgid() (current_cred_xxx(sgid)) +#define current_fsuid() (current_cred_xxx(fsuid)) +#define current_fsgid() (current_cred_xxx(fsgid)) +#define current_cap() (current_cred_xxx(cap_effective)) +#define current_user() (current_cred_xxx(user)) +#define current_user_ns() (current_cred_xxx(user)->user_ns) +#define current_security() (current_cred_xxx(security)) #define current_uid_gid(_uid, _gid) \ do { \ - *(_uid) = current->uid; \ - *(_gid) = current->gid; \ + const struct cred *__cred; \ + __cred = current_cred(); \ + *(_uid) = __cred->uid; \ + *(_gid) = __cred->gid; \ } while(0) -#define current_euid_egid(_uid, _gid) \ +#define current_euid_egid(_euid, _egid) \ do { \ - *(_uid) = current->euid; \ - *(_gid) = current->egid; \ + const struct cred *__cred; \ + __cred = current_cred(); \ + *(_euid) = __cred->euid; \ + *(_egid) = __cred->egid; \ } while(0) -#define current_fsuid_fsgid(_uid, _gid) \ +#define current_fsuid_fsgid(_fsuid, _fsgid) \ do { \ - *(_uid) = current->fsuid; \ - *(_gid) = current->fsgid; \ + const struct cred *__cred; \ + __cred = current_cred(); \ + *(_fsuid) = __cred->fsuid; \ + *(_fsgid) = __cred->fsgid; \ } while(0) #endif /* _LINUX_CRED_H */ diff --git a/include/linux/fs.h b/include/linux/fs.h index 4a853ef6fd3..195a8cb2a74 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -316,6 +316,7 @@ struct poll_table_struct; struct kstatfs; struct vm_area_struct; struct vfsmount; +struct cred; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -827,7 +828,7 @@ struct file { fmode_t f_mode; loff_t f_pos; struct fown_struct f_owner; - unsigned int f_uid, f_gid; + const struct cred *f_cred; struct file_ra_state f_ra; u64 f_version; @@ -1194,7 +1195,7 @@ enum { #define has_fs_excl() atomic_read(¤t->fs_excl) #define is_owner_or_cap(inode) \ - ((current->fsuid == (inode)->i_uid) || capable(CAP_FOWNER)) + ((current_fsuid() == (inode)->i_uid) || capable(CAP_FOWNER)) /* not quite ready to be deprecated, but... */ extern void lock_super(struct super_block *); @@ -1674,7 +1675,8 @@ extern int do_truncate(struct dentry *, loff_t start, unsigned int time_attrs, extern long do_sys_open(int dfd, const char __user *filename, int flags, int mode); extern struct file *filp_open(const char *, int, int); -extern struct file * dentry_open(struct dentry *, struct vfsmount *, int); +extern struct file * dentry_open(struct dentry *, struct vfsmount *, int, + const struct cred *); extern int filp_close(struct file *, fl_owner_t id); extern char * getname(const char __user *); diff --git a/include/linux/init_task.h b/include/linux/init_task.h index 23fd8909b9e..959f5522d10 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -57,7 +57,6 @@ extern struct nsproxy init_nsproxy; .mnt_ns = NULL, \ INIT_NET_NS(net_ns) \ INIT_IPC_NS(ipc_ns) \ - .user_ns = &init_user_ns, \ } #define INIT_SIGHAND(sighand) { \ @@ -113,6 +112,8 @@ extern struct group_info init_groups; # define CAP_INIT_BSET CAP_INIT_EFF_SET #endif +extern struct cred init_cred; + /* * INIT_TASK is used to set up the first task table, touch at * your own risk!. Base=0, limit=0x1fffff (=2MB) @@ -147,13 +148,10 @@ extern struct group_info init_groups; .children = LIST_HEAD_INIT(tsk.children), \ .sibling = LIST_HEAD_INIT(tsk.sibling), \ .group_leader = &tsk, \ - .group_info = &init_groups, \ - .cap_effective = CAP_INIT_EFF_SET, \ - .cap_inheritable = CAP_INIT_INH_SET, \ - .cap_permitted = CAP_FULL_SET, \ - .cap_bset = CAP_INIT_BSET, \ - .securebits = SECUREBITS_DEFAULT, \ - .user = INIT_USER, \ + .real_cred = &init_cred, \ + .cred = &init_cred, \ + .cred_exec_mutex = \ + __MUTEX_INITIALIZER(tsk.cred_exec_mutex), \ .comm = "swapper", \ .thread = INIT_THREAD, \ .fs = &init_fs, \ diff --git a/include/linux/key-ui.h b/include/linux/key-ui.h deleted file mode 100644 index e8b8a7a5c49..00000000000 --- a/include/linux/key-ui.h +++ /dev/null @@ -1,66 +0,0 @@ -/* key-ui.h: key userspace interface stuff - * - * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. - * Written by David Howells (dhowells@redhat.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#ifndef _LINUX_KEY_UI_H -#define _LINUX_KEY_UI_H - -#include - -/* the key tree */ -extern struct rb_root key_serial_tree; -extern spinlock_t key_serial_lock; - -/* required permissions */ -#define KEY_VIEW 0x01 /* require permission to view attributes */ -#define KEY_READ 0x02 /* require permission to read content */ -#define KEY_WRITE 0x04 /* require permission to update / modify */ -#define KEY_SEARCH 0x08 /* require permission to search (keyring) or find (key) */ -#define KEY_LINK 0x10 /* require permission to link */ -#define KEY_SETATTR 0x20 /* require permission to change attributes */ -#define KEY_ALL 0x3f /* all the above permissions */ - -/* - * the keyring payload contains a list of the keys to which the keyring is - * subscribed - */ -struct keyring_list { - struct rcu_head rcu; /* RCU deletion hook */ - unsigned short maxkeys; /* max keys this list can hold */ - unsigned short nkeys; /* number of keys currently held */ - unsigned short delkey; /* key to be unlinked by RCU */ - struct key *keys[0]; -}; - -/* - * check to see whether permission is granted to use a key in the desired way - */ -extern int key_task_permission(const key_ref_t key_ref, - struct task_struct *context, - key_perm_t perm); - -static inline int key_permission(const key_ref_t key_ref, key_perm_t perm) -{ - return key_task_permission(key_ref, current, perm); -} - -extern key_ref_t lookup_user_key(struct task_struct *context, - key_serial_t id, int create, int partial, - key_perm_t perm); - -extern long join_session_keyring(const char *name); - -extern struct key_type *key_type_lookup(const char *type); -extern void key_type_put(struct key_type *ktype); - -#define key_negative_timeout 60 /* default timeout on a negative key's existence */ - - -#endif /* _LINUX_KEY_UI_H */ diff --git a/include/linux/key.h b/include/linux/key.h index 1b70e35a71e..21d32a142c0 100644 --- a/include/linux/key.h +++ b/include/linux/key.h @@ -73,6 +73,7 @@ struct key; struct seq_file; struct user_struct; struct signal_struct; +struct cred; struct key_type; struct key_owner; @@ -181,7 +182,7 @@ struct key { extern struct key *key_alloc(struct key_type *type, const char *desc, uid_t uid, gid_t gid, - struct task_struct *ctx, + const struct cred *cred, key_perm_t perm, unsigned long flags); @@ -249,7 +250,7 @@ extern int key_unlink(struct key *keyring, struct key *key); extern struct key *keyring_alloc(const char *description, uid_t uid, gid_t gid, - struct task_struct *ctx, + const struct cred *cred, unsigned long flags, struct key *dest); @@ -276,24 +277,11 @@ extern ctl_table key_sysctls[]; /* * the userspace interface */ -extern void switch_uid_keyring(struct user_struct *new_user); -extern int copy_keys(unsigned long clone_flags, struct task_struct *tsk); -extern int copy_thread_group_keys(struct task_struct *tsk); -extern void exit_keys(struct task_struct *tsk); -extern void exit_thread_group_keys(struct signal_struct *tg); -extern int suid_keys(struct task_struct *tsk); -extern int exec_keys(struct task_struct *tsk); +extern int install_thread_keyring_to_cred(struct cred *cred); extern void key_fsuid_changed(struct task_struct *tsk); extern void key_fsgid_changed(struct task_struct *tsk); extern void key_init(void); -#define __install_session_keyring(tsk, keyring) \ -({ \ - struct key *old_session = tsk->signal->session_keyring; \ - tsk->signal->session_keyring = keyring; \ - old_session; \ -}) - #else /* CONFIG_KEYS */ #define key_validate(k) 0 @@ -302,17 +290,9 @@ extern void key_init(void); #define key_revoke(k) do { } while(0) #define key_put(k) do { } while(0) #define key_ref_put(k) do { } while(0) -#define make_key_ref(k, p) ({ NULL; }) -#define key_ref_to_ptr(k) ({ NULL; }) +#define make_key_ref(k, p) NULL +#define key_ref_to_ptr(k) NULL #define is_key_possessed(k) 0 -#define switch_uid_keyring(u) do { } while(0) -#define __install_session_keyring(t, k) ({ NULL; }) -#define copy_keys(f,t) 0 -#define copy_thread_group_keys(t) 0 -#define exit_keys(t) do { } while(0) -#define exit_thread_group_keys(tg) do { } while(0) -#define suid_keys(t) do { } while(0) -#define exec_keys(t) do { } while(0) #define key_fsuid_changed(t) do { } while(0) #define key_fsgid_changed(t) do { } while(0) #define key_init() do { } while(0) diff --git a/include/linux/keyctl.h b/include/linux/keyctl.h index 656ee6b77a4..c0688eb7209 100644 --- a/include/linux/keyctl.h +++ b/include/linux/keyctl.h @@ -1,6 +1,6 @@ /* keyctl.h: keyctl command IDs * - * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. + * Copyright (C) 2004, 2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) * * This program is free software; you can redistribute it and/or @@ -20,6 +20,7 @@ #define KEY_SPEC_USER_SESSION_KEYRING -5 /* - key ID for UID-session keyring */ #define KEY_SPEC_GROUP_KEYRING -6 /* - key ID for GID-specific keyring */ #define KEY_SPEC_REQKEY_AUTH_KEY -7 /* - key ID for assumed request_key auth key */ +#define KEY_SPEC_REQUESTOR_KEYRING -8 /* - key ID for request_key() dest keyring */ /* request-key default keyrings */ #define KEY_REQKEY_DEFL_NO_CHANGE -1 @@ -30,6 +31,7 @@ #define KEY_REQKEY_DEFL_USER_KEYRING 4 #define KEY_REQKEY_DEFL_USER_SESSION_KEYRING 5 #define KEY_REQKEY_DEFL_GROUP_KEYRING 6 +#define KEY_REQKEY_DEFL_REQUESTOR_KEYRING 7 /* keyctl commands */ #define KEYCTL_GET_KEYRING_ID 0 /* ask for a keyring's ID */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index c8a768e5964..afad7dec1b3 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -27,7 +27,6 @@ struct nsproxy { struct ipc_namespace *ipc_ns; struct mnt_namespace *mnt_ns; struct pid_namespace *pid_ns; - struct user_namespace *user_ns; struct net *net_ns; }; extern struct nsproxy init_nsproxy; diff --git a/include/linux/sched.h b/include/linux/sched.h index 55e30d11447..9624e2cfc2d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -572,12 +572,6 @@ struct signal_struct { */ struct rlimit rlim[RLIM_NLIMITS]; - /* keep the process-shared keyrings here so that they do the right - * thing in threads created with CLONE_THREAD */ -#ifdef CONFIG_KEYS - struct key *session_keyring; /* keyring inherited over fork */ - struct key *process_keyring; /* keyring private to this process */ -#endif #ifdef CONFIG_BSD_PROCESS_ACCT struct pacct_struct pacct; /* per-process accounting information */ #endif @@ -648,6 +642,7 @@ struct user_struct { /* Hash table maintenance information */ struct hlist_node uidhash_node; uid_t uid; + struct user_namespace *user_ns; #ifdef CONFIG_USER_SCHED struct task_group *tg; @@ -665,6 +660,7 @@ extern struct user_struct *find_user(uid_t); extern struct user_struct root_user; #define INIT_USER (&root_user) + struct backing_dev_info; struct reclaim_state; @@ -888,38 +884,7 @@ partition_sched_domains(int ndoms_new, cpumask_t *doms_new, #endif /* !CONFIG_SMP */ struct io_context; /* See blkdev.h */ -#define NGROUPS_SMALL 32 -#define NGROUPS_PER_BLOCK ((unsigned int)(PAGE_SIZE / sizeof(gid_t))) -struct group_info { - int ngroups; - atomic_t usage; - gid_t small_block[NGROUPS_SMALL]; - int nblocks; - gid_t *blocks[0]; -}; -/* - * get_group_info() must be called with the owning task locked (via task_lock()) - * when task != current. The reason being that the vast majority of callers are - * looking at current->group_info, which can not be changed except by the - * current task. Changing current->group_info requires the task lock, too. - */ -#define get_group_info(group_info) do { \ - atomic_inc(&(group_info)->usage); \ -} while (0) - -#define put_group_info(group_info) do { \ - if (atomic_dec_and_test(&(group_info)->usage)) \ - groups_free(group_info); \ -} while (0) - -extern struct group_info *groups_alloc(int gidsetsize); -extern void groups_free(struct group_info *group_info); -extern int set_current_groups(struct group_info *group_info); -extern int groups_search(struct group_info *group_info, gid_t grp); -/* access the groups "array" with this macro */ -#define GROUP_AT(gi, i) \ - ((gi)->blocks[(i)/NGROUPS_PER_BLOCK][(i)%NGROUPS_PER_BLOCK]) #ifdef ARCH_HAS_PREFETCH_SWITCH_STACK extern void prefetch_stack(struct task_struct *t); @@ -1186,17 +1151,12 @@ struct task_struct { struct list_head cpu_timers[3]; /* process credentials */ - uid_t uid,euid,suid,fsuid; - gid_t gid,egid,sgid,fsgid; - struct group_info *group_info; - kernel_cap_t cap_effective, cap_inheritable, cap_permitted, cap_bset; - struct user_struct *user; - unsigned securebits; -#ifdef CONFIG_KEYS - unsigned char jit_keyring; /* default keyring to attach requested keys to */ - struct key *request_key_auth; /* assumed request_key authority */ - struct key *thread_keyring; /* keyring private to this thread */ -#endif + const struct cred *real_cred; /* objective and real subjective task + * credentials (COW) */ + const struct cred *cred; /* effective (overridable) subjective task + * credentials (COW) */ + struct mutex cred_exec_mutex; /* execve vs ptrace cred calculation mutex */ + char comm[TASK_COMM_LEN]; /* executable name excluding path - access with [gs]et_task_comm (which lock it with task_lock()) @@ -1233,9 +1193,6 @@ struct task_struct { int (*notifier)(void *priv); void *notifier_data; sigset_t *notifier_mask; -#ifdef CONFIG_SECURITY - void *security; -#endif struct audit_context *audit_context; #ifdef CONFIG_AUDITSYSCALL uid_t loginuid; @@ -1775,7 +1732,6 @@ static inline struct user_struct *get_uid(struct user_struct *u) return u; } extern void free_uid(struct user_struct *); -extern void switch_uid(struct user_struct *); extern void release_uids(struct user_namespace *ns); #include @@ -1794,9 +1750,6 @@ extern void wake_up_new_task(struct task_struct *tsk, extern void sched_fork(struct task_struct *p, int clone_flags); extern void sched_dead(struct task_struct *p); -extern int in_group_p(gid_t); -extern int in_egroup_p(gid_t); - extern void proc_caches_init(void); extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); @@ -1928,6 +1881,8 @@ static inline unsigned long wait_task_inactive(struct task_struct *p, #define for_each_process(p) \ for (p = &init_task ; (p = next_task(p)) != &init_task ; ) +extern bool is_single_threaded(struct task_struct *); + /* * Careful: do_each_thread/while_each_thread is a double loop so * 'break' will not work as expected - use goto instead. diff --git a/include/linux/securebits.h b/include/linux/securebits.h index 92f09bdf117..d2c5ed845bc 100644 --- a/include/linux/securebits.h +++ b/include/linux/securebits.h @@ -32,7 +32,7 @@ setting is locked or not. A setting which is locked cannot be changed from user-level. */ #define issecure_mask(X) (1 << (X)) -#define issecure(X) (issecure_mask(X) & current->securebits) +#define issecure(X) (issecure_mask(X) & current_cred_xxx(securebits)) #define SECURE_ALL_BITS (issecure_mask(SECURE_NOROOT) | \ issecure_mask(SECURE_NO_SETUID_FIXUP) | \ diff --git a/include/linux/security.h b/include/linux/security.h index e3d4ecda267..3416cb85e77 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -37,6 +37,10 @@ /* Maximum number of letters for an LSM name string */ #define SECURITY_NAME_MAX 10 +/* If capable should audit the security request */ +#define SECURITY_CAP_NOAUDIT 0 +#define SECURITY_CAP_AUDIT 1 + struct ctl_table; struct audit_krule; @@ -44,25 +48,25 @@ struct audit_krule; * These functions are in security/capability.c and are used * as the default capabilities functions */ -extern int cap_capable(struct task_struct *tsk, int cap); +extern int cap_capable(struct task_struct *tsk, int cap, int audit); extern int cap_settime(struct timespec *ts, struct timezone *tz); extern int cap_ptrace_may_access(struct task_struct *child, unsigned int mode); extern int cap_ptrace_traceme(struct task_struct *parent); extern int cap_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted); -extern int cap_capset_check(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted); -extern void cap_capset_set(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted); -extern int cap_bprm_set_security(struct linux_binprm *bprm); -extern void cap_bprm_apply_creds(struct linux_binprm *bprm, int unsafe); +extern int cap_capset(struct cred *new, const struct cred *old, + const kernel_cap_t *effective, + 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); extern int cap_inode_need_killpriv(struct dentry *dentry); extern int cap_inode_killpriv(struct dentry *dentry); -extern int cap_task_post_setuid(uid_t old_ruid, uid_t old_euid, uid_t old_suid, int flags); -extern void cap_task_reparent_to_init(struct task_struct *p); +extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags); extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5, long *rc_p); + unsigned long arg4, unsigned long arg5); extern int cap_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp); extern int cap_task_setioprio(struct task_struct *p, int ioprio); extern int cap_task_setnice(struct task_struct *p, int nice); @@ -105,7 +109,7 @@ extern unsigned long mmap_min_addr; struct sched_param; struct request_sock; -/* bprm_apply_creds unsafe reasons */ +/* bprm->unsafe reasons */ #define LSM_UNSAFE_SHARE 1 #define LSM_UNSAFE_PTRACE 2 #define LSM_UNSAFE_PTRACE_CAP 4 @@ -149,36 +153,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * * Security hooks for program execution operations. * - * @bprm_alloc_security: - * Allocate and attach a security structure to the @bprm->security field. - * The security field is initialized to NULL when the bprm structure is - * allocated. - * @bprm contains the linux_binprm structure to be modified. - * Return 0 if operation was successful. - * @bprm_free_security: - * @bprm contains the linux_binprm structure to be modified. - * Deallocate and clear the @bprm->security field. - * @bprm_apply_creds: - * Compute and set the security attributes of a process being transformed - * by an execve operation based on the old attributes (current->security) - * and the information saved in @bprm->security by the set_security hook. - * Since this hook function (and its caller) are void, this hook can not - * return an error. However, it can leave the security attributes of the - * process unchanged if an access failure occurs at this point. - * bprm_apply_creds is called under task_lock. @unsafe indicates various - * reasons why it may be unsafe to change security state. - * @bprm contains the linux_binprm structure. - * @bprm_post_apply_creds: - * Runs after bprm_apply_creds with the task_lock dropped, so that - * functions which cannot be called safely under the task_lock can - * be used. This hook is a good place to perform state changes on - * the process such as closing open file descriptors to which access - * is no longer granted if the attributes were changed. - * Note that a security module might need to save state between - * bprm_apply_creds and bprm_post_apply_creds to store the decision - * on whether the process may proceed. - * @bprm contains the linux_binprm structure. - * @bprm_set_security: + * @bprm_set_creds: * Save security information in the bprm->security field, typically based * on information about the bprm->file, for later use by the apply_creds * hook. This hook may also optionally check permissions (e.g. for @@ -191,15 +166,30 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. * @bprm_check_security: - * This hook mediates the point when a search for a binary handler will - * begin. It allows a check the @bprm->security value which is set in - * the preceding set_security call. The primary difference from - * set_security is that the argv list and envp list are reliably - * available in @bprm. This hook may be called multiple times - * during a single execve; and in each pass set_security is called - * first. + * This hook mediates the point when a search for a binary handler will + * begin. It allows a check the @bprm->security value which is set in the + * preceding set_creds call. The primary difference from set_creds is + * that the argv list and envp list are reliably available in @bprm. This + * hook may be called multiple times during a single execve; and in each + * pass set_creds is called first. * @bprm contains the linux_binprm structure. * Return 0 if the hook is successful and permission is granted. + * @bprm_committing_creds: + * Prepare to install the new security attributes of a process being + * transformed by an execve operation, based on the old credentials + * pointed to by @current->cred and the information set in @bprm->cred by + * the bprm_set_creds hook. @bprm points to the linux_binprm structure. + * This hook is a good place to perform state changes on the process such + * as closing open file descriptors to which access will no longer be + * granted when the attributes are changed. This is called immediately + * before commit_creds(). + * @bprm_committed_creds: + * Tidy up after the installation of the new security attributes of a + * process being transformed by an execve operation. The new credentials + * have, by this point, been set to @current->cred. @bprm points to the + * 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 @@ -585,15 +575,31 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * manual page for definitions of the @clone_flags. * @clone_flags contains the flags indicating what should be shared. * Return 0 if permission is granted. - * @task_alloc_security: - * @p contains the task_struct for child process. - * Allocate and attach a security structure to the p->security field. The - * security field is initialized to NULL when the task structure is - * allocated. - * Return 0 if operation was successful. - * @task_free_security: - * @p contains the task_struct for process. - * Deallocate and clear the p->security field. + * @cred_free: + * @cred points to the credentials. + * Deallocate and clear the cred->security field in a set of credentials. + * @cred_prepare: + * @new points to the new credentials. + * @old points to the original credentials. + * @gfp indicates the atomicity of any memory allocations. + * Prepare a new set of credentials by copying the data from the old set. + * @cred_commit: + * @new points to the new credentials. + * @old points to the original credentials. + * Install a new set of credentials. + * @kernel_act_as: + * Set the credentials for a kernel service to act as (subjective context). + * @new points to the credentials to be modified. + * @secid specifies the security ID to be set + * The current task must be the one that nominated @secid. + * Return 0 if successful. + * @kernel_create_files_as: + * Set the file creation context in a set of credentials to be the same as + * the objective context of the specified inode. + * @new points to the credentials to be modified. + * @inode points to the inode to use as a reference. + * The current task must be the one that nominated @inode. + * Return 0 if successful. * @task_setuid: * Check permission before setting one or more of the user identity * attributes of the current process. The @flags parameter indicates @@ -606,15 +612,13 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @id2 contains a uid. * @flags contains one of the LSM_SETID_* values. * Return 0 if permission is granted. - * @task_post_setuid: + * @task_fix_setuid: * Update the module's state after setting one or more of the user * identity attributes of the current process. The @flags parameter * indicates which of the set*uid system calls invoked this hook. If - * @flags is LSM_SETID_FS, then @old_ruid is the old fs uid and the other - * parameters are not used. - * @old_ruid contains the old real uid (or fs uid if LSM_SETID_FS). - * @old_euid contains the old effective uid (or -1 if LSM_SETID_FS). - * @old_suid contains the old saved uid (or -1 if LSM_SETID_FS). + * @new is the set of credentials that will be installed. Modifications + * should be made to this rather than to @current->cred. + * @old is the set of credentials that are being replaces * @flags contains one of the LSM_SETID_* values. * Return 0 on success. * @task_setgid: @@ -717,13 +721,8 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @arg3 contains a argument. * @arg4 contains a argument. * @arg5 contains a argument. - * @rc_p contains a pointer to communicate back the forced return code - * Return 0 if permission is granted, and non-zero if the security module - * has taken responsibility (setting *rc_p) for the prctl call. - * @task_reparent_to_init: - * Set the security attributes in @p->security for a kernel thread that - * is being reparented to the init task. - * @p contains the task_struct for the kernel thread. + * Return -ENOSYS if no-one wanted to handle this op, any other value to + * cause prctl() to return immediately with that value. * @task_to_inode: * Set the security attributes for an inode based on an associated task's * security attributes, e.g. for /proc/pid inodes. @@ -1000,7 +999,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * See whether a specific operational right is granted to a process on a * key. * @key_ref refers to the key (key pointer + possession attribute bit). - * @context points to the process to provide the context against which to + * @cred points to the credentials to provide the context against which to * evaluate the security data on the key. * @perm describes the combination of permissions required of this key. * Return 1 if permission granted, 0 if permission denied and -ve it the @@ -1162,6 +1161,7 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @child process. * Security modules may also want to perform a process tracing check * during an execve in the set_security or apply_creds hooks of + * tracing check during an execve in the bprm_set_creds hook of * binprm_security_ops if the process is being traced and its security * attributes would be changed by the execve. * @child contains the task_struct structure for the target process. @@ -1185,29 +1185,15 @@ static inline void security_free_mnt_opts(struct security_mnt_opts *opts) * @inheritable contains the inheritable capability set. * @permitted contains the permitted capability set. * Return 0 if the capability sets were successfully obtained. - * @capset_check: - * Check permission before setting the @effective, @inheritable, and - * @permitted capability sets for the @target process. - * Caveat: @target is also set to current if a set of processes is - * specified (i.e. all processes other than current and init or a - * particular process group). Hence, the capset_set hook may need to - * revalidate permission to the actual target process. - * @target contains the task_struct structure for target process. - * @effective contains the effective capability set. - * @inheritable contains the inheritable capability set. - * @permitted contains the permitted capability set. - * Return 0 if permission is granted. - * @capset_set: + * @capset: * Set the @effective, @inheritable, and @permitted capability sets for - * the @target process. Since capset_check cannot always check permission - * to the real @target process, this hook may also perform permission - * checking to determine if the current process is allowed to set the - * capability sets of the @target process. However, this hook has no way - * of returning an error due to the structure of the sys_capset code. - * @target contains the task_struct structure for target process. + * the current process. + * @new contains the new credentials structure for target process. + * @old contains the current credentials structure for target process. * @effective contains the effective capability set. * @inheritable contains the inheritable capability set. * @permitted contains the permitted capability set. + * Return 0 and update @new if permission is granted. * @capable: * Check whether the @tsk process has the @cap capability. * @tsk contains the task_struct for the process. @@ -1299,15 +1285,12 @@ struct security_operations { int (*capget) (struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted); - int (*capset_check) (struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted); - void (*capset_set) (struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted); - int (*capable) (struct task_struct *tsk, int cap); + int (*capset) (struct cred *new, + const struct cred *old, + const kernel_cap_t *effective, + const kernel_cap_t *inheritable, + const kernel_cap_t *permitted); + int (*capable) (struct task_struct *tsk, int cap, int audit); int (*acct) (struct file *file); int (*sysctl) (struct ctl_table *table, int op); int (*quotactl) (int cmds, int type, int id, struct super_block *sb); @@ -1316,18 +1299,16 @@ struct security_operations { int (*settime) (struct timespec *ts, struct timezone *tz); int (*vm_enough_memory) (struct mm_struct *mm, long pages); - int (*bprm_alloc_security) (struct linux_binprm *bprm); - void (*bprm_free_security) (struct linux_binprm *bprm); - void (*bprm_apply_creds) (struct linux_binprm *bprm, int unsafe); - void (*bprm_post_apply_creds) (struct linux_binprm *bprm); - int (*bprm_set_security) (struct linux_binprm *bprm); + 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); int (*sb_alloc_security) (struct super_block *sb); void (*sb_free_security) (struct super_block *sb); int (*sb_copy_data) (char *orig, char *copy); - int (*sb_kern_mount) (struct super_block *sb, void *data); + int (*sb_kern_mount) (struct super_block *sb, int flags, void *data); int (*sb_show_options) (struct seq_file *m, struct super_block *sb); int (*sb_statfs) (struct dentry *dentry); int (*sb_mount) (char *dev_name, struct path *path, @@ -1406,14 +1387,18 @@ struct security_operations { int (*file_send_sigiotask) (struct task_struct *tsk, struct fown_struct *fown, int sig); int (*file_receive) (struct file *file); - int (*dentry_open) (struct file *file); + int (*dentry_open) (struct file *file, const struct cred *cred); int (*task_create) (unsigned long clone_flags); - int (*task_alloc_security) (struct task_struct *p); - void (*task_free_security) (struct task_struct *p); + void (*cred_free) (struct cred *cred); + int (*cred_prepare)(struct cred *new, const struct cred *old, + gfp_t gfp); + void (*cred_commit)(struct cred *new, const struct cred *old); + int (*kernel_act_as)(struct cred *new, u32 secid); + int (*kernel_create_files_as)(struct cred *new, struct inode *inode); int (*task_setuid) (uid_t id0, uid_t id1, uid_t id2, int flags); - int (*task_post_setuid) (uid_t old_ruid /* or fsuid */ , - uid_t old_euid, uid_t old_suid, int flags); + int (*task_fix_setuid) (struct cred *new, const struct cred *old, + int flags); int (*task_setgid) (gid_t id0, gid_t id1, gid_t id2, int flags); int (*task_setpgid) (struct task_struct *p, pid_t pgid); int (*task_getpgid) (struct task_struct *p); @@ -1433,8 +1418,7 @@ struct security_operations { int (*task_wait) (struct task_struct *p); int (*task_prctl) (int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, - unsigned long arg5, long *rc_p); - void (*task_reparent_to_init) (struct task_struct *p); + unsigned long arg5); void (*task_to_inode) (struct task_struct *p, struct inode *inode); int (*ipc_permission) (struct kern_ipc_perm *ipcp, short flag); @@ -1539,10 +1523,10 @@ struct security_operations { /* key management security hooks */ #ifdef CONFIG_KEYS - int (*key_alloc) (struct key *key, struct task_struct *tsk, unsigned long flags); + int (*key_alloc) (struct key *key, const struct cred *cred, unsigned long flags); void (*key_free) (struct key *key); int (*key_permission) (key_ref_t key_ref, - struct task_struct *context, + const struct cred *cred, key_perm_t perm); int (*key_getsecurity)(struct key *key, char **_buffer); #endif /* CONFIG_KEYS */ @@ -1568,15 +1552,12 @@ int security_capget(struct task_struct *target, kernel_cap_t *effective, kernel_cap_t *inheritable, kernel_cap_t *permitted); -int security_capset_check(struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted); -void security_capset_set(struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted); +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(struct task_struct *tsk, int cap); +int security_capable_noaudit(struct task_struct *tsk, int cap); int security_acct(struct file *file); int security_sysctl(struct ctl_table *table, int op); int security_quotactl(int cmds, int type, int id, struct super_block *sb); @@ -1586,17 +1567,15 @@ int security_settime(struct timespec *ts, struct timezone *tz); int security_vm_enough_memory(long pages); int security_vm_enough_memory_mm(struct mm_struct *mm, long pages); int security_vm_enough_memory_kern(long pages); -int security_bprm_alloc(struct linux_binprm *bprm); -void security_bprm_free(struct linux_binprm *bprm); -void security_bprm_apply_creds(struct linux_binprm *bprm, int unsafe); -void security_bprm_post_apply_creds(struct linux_binprm *bprm); -int security_bprm_set(struct linux_binprm *bprm); +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); -int security_sb_kern_mount(struct super_block *sb, void *data); +int security_sb_kern_mount(struct super_block *sb, int flags, void *data); int security_sb_show_options(struct seq_file *m, struct super_block *sb); int security_sb_statfs(struct dentry *dentry); int security_sb_mount(char *dev_name, struct path *path, @@ -1663,13 +1642,16 @@ int security_file_set_fowner(struct file *file); int security_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int sig); int security_file_receive(struct file *file); -int security_dentry_open(struct file *file); +int security_dentry_open(struct file *file, const struct cred *cred); int security_task_create(unsigned long clone_flags); -int security_task_alloc(struct task_struct *p); -void security_task_free(struct task_struct *p); +void security_cred_free(struct cred *cred); +int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp); +void security_commit_creds(struct cred *new, const struct cred *old); +int security_kernel_act_as(struct cred *new, u32 secid); +int security_kernel_create_files_as(struct cred *new, struct inode *inode); int security_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags); -int security_task_post_setuid(uid_t old_ruid, uid_t old_euid, - uid_t old_suid, int flags); +int security_task_fix_setuid(struct cred *new, const struct cred *old, + int flags); int security_task_setgid(gid_t id0, gid_t id1, gid_t id2, int flags); int security_task_setpgid(struct task_struct *p, pid_t pgid); int security_task_getpgid(struct task_struct *p); @@ -1688,8 +1670,7 @@ int security_task_kill(struct task_struct *p, struct siginfo *info, int sig, u32 secid); int security_task_wait(struct task_struct *p); int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5, long *rc_p); -void security_task_reparent_to_init(struct task_struct *p); + unsigned long arg4, unsigned long arg5); void security_task_to_inode(struct task_struct *p, struct inode *inode); int security_ipc_permission(struct kern_ipc_perm *ipcp, short flag); void security_ipc_getsecid(struct kern_ipc_perm *ipcp, u32 *secid); @@ -1764,25 +1745,23 @@ static inline int security_capget(struct task_struct *target, return cap_capget(target, effective, inheritable, permitted); } -static inline int security_capset_check(struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) +static inline 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) { - return cap_capset_check(target, effective, inheritable, permitted); -} - -static inline void security_capset_set(struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - cap_capset_set(target, effective, inheritable, permitted); + return cap_capset(new, old, effective, inheritable, permitted); } static inline int security_capable(struct task_struct *tsk, int cap) { - return cap_capable(tsk, cap); + return cap_capable(tsk, cap, SECURITY_CAP_AUDIT); +} + +static inline int security_capable_noaudit(struct task_struct *tsk, int cap) +{ + return cap_capable(tsk, cap, SECURITY_CAP_NOAUDIT); } static inline int security_acct(struct file *file) @@ -1835,27 +1814,9 @@ static inline int security_vm_enough_memory_kern(long pages) return cap_vm_enough_memory(current->mm, pages); } -static inline int security_bprm_alloc(struct linux_binprm *bprm) +static inline int security_bprm_set_creds(struct linux_binprm *bprm) { - return 0; -} - -static inline void security_bprm_free(struct linux_binprm *bprm) -{ } - -static inline void security_bprm_apply_creds(struct linux_binprm *bprm, int unsafe) -{ - cap_bprm_apply_creds(bprm, unsafe); -} - -static inline void security_bprm_post_apply_creds(struct linux_binprm *bprm) -{ - return; -} - -static inline int security_bprm_set(struct linux_binprm *bprm) -{ - return cap_bprm_set_security(bprm); + return cap_bprm_set_creds(bprm); } static inline int security_bprm_check(struct linux_binprm *bprm) @@ -1863,6 +1824,14 @@ static inline int security_bprm_check(struct linux_binprm *bprm) return 0; } +static inline void security_bprm_committing_creds(struct linux_binprm *bprm) +{ +} + +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); @@ -1881,7 +1850,7 @@ static inline int security_sb_copy_data(char *orig, char *copy) return 0; } -static inline int security_sb_kern_mount(struct super_block *sb, void *data) +static inline int security_sb_kern_mount(struct super_block *sb, int flags, void *data) { return 0; } @@ -2177,7 +2146,8 @@ static inline int security_file_receive(struct file *file) return 0; } -static inline int security_dentry_open(struct file *file) +static inline int security_dentry_open(struct file *file, + const struct cred *cred) { return 0; } @@ -2187,13 +2157,31 @@ static inline int security_task_create(unsigned long clone_flags) return 0; } -static inline int security_task_alloc(struct task_struct *p) +static inline void security_cred_free(struct cred *cred) +{ } + +static inline int security_prepare_creds(struct cred *new, + const struct cred *old, + gfp_t gfp) { return 0; } -static inline void security_task_free(struct task_struct *p) -{ } +static inline void security_commit_creds(struct cred *new, + const struct cred *old) +{ +} + +static inline int security_kernel_act_as(struct cred *cred, u32 secid) +{ + return 0; +} + +static inline int security_kernel_create_files_as(struct cred *cred, + struct inode *inode) +{ + return 0; +} static inline int security_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags) @@ -2201,10 +2189,11 @@ static inline int security_task_setuid(uid_t id0, uid_t id1, uid_t id2, return 0; } -static inline int security_task_post_setuid(uid_t old_ruid, uid_t old_euid, - uid_t old_suid, int flags) +static inline int security_task_fix_setuid(struct cred *new, + const struct cred *old, + int flags) { - return cap_task_post_setuid(old_ruid, old_euid, old_suid, flags); + return cap_task_fix_setuid(new, old, flags); } static inline int security_task_setgid(gid_t id0, gid_t id1, gid_t id2, @@ -2291,14 +2280,9 @@ static inline int security_task_wait(struct task_struct *p) static inline int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, - unsigned long arg5, long *rc_p) + unsigned long arg5) { - return cap_task_prctl(option, arg2, arg3, arg3, arg5, rc_p); -} - -static inline void security_task_reparent_to_init(struct task_struct *p) -{ - cap_task_reparent_to_init(p); + return cap_task_prctl(option, arg2, arg3, arg3, arg5); } static inline void security_task_to_inode(struct task_struct *p, struct inode *inode) @@ -2724,16 +2708,16 @@ static inline void security_skb_classify_flow(struct sk_buff *skb, struct flowi #ifdef CONFIG_KEYS #ifdef CONFIG_SECURITY -int security_key_alloc(struct key *key, struct task_struct *tsk, unsigned long flags); +int security_key_alloc(struct key *key, const struct cred *cred, unsigned long flags); void security_key_free(struct key *key); int security_key_permission(key_ref_t key_ref, - struct task_struct *context, key_perm_t perm); + const struct cred *cred, key_perm_t perm); int security_key_getsecurity(struct key *key, char **_buffer); #else static inline int security_key_alloc(struct key *key, - struct task_struct *tsk, + const struct cred *cred, unsigned long flags) { return 0; @@ -2744,7 +2728,7 @@ static inline void security_key_free(struct key *key) } static inline int security_key_permission(key_ref_t key_ref, - struct task_struct *context, + const struct cred *cred, key_perm_t perm) { return 0; diff --git a/include/linux/tty.h b/include/linux/tty.h index 3b8121d4e36..580700f20a1 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -442,6 +442,7 @@ extern void tty_audit_add_data(struct tty_struct *tty, unsigned char *data, size_t size); extern void tty_audit_exit(void); extern void tty_audit_fork(struct signal_struct *sig); +extern void tty_audit_tiocsti(struct tty_struct *tty, char ch); extern void tty_audit_push(struct tty_struct *tty); extern void tty_audit_push_task(struct task_struct *tsk, uid_t loginuid, u32 sessionid); @@ -450,6 +451,9 @@ static inline void tty_audit_add_data(struct tty_struct *tty, unsigned char *data, size_t size) { } +static inline void tty_audit_tiocsti(struct tty_struct *tty, char ch) +{ +} static inline void tty_audit_exit(void) { } diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index b5f41d4c2ee..315bcd37522 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -12,7 +12,7 @@ struct user_namespace { struct kref kref; struct hlist_head uidhash_table[UIDHASH_SZ]; - struct user_struct *root_user; + struct user_struct *creator; }; extern struct user_namespace init_user_ns; @@ -26,8 +26,7 @@ static inline struct user_namespace *get_user_ns(struct user_namespace *ns) return ns; } -extern struct user_namespace *copy_user_ns(int flags, - struct user_namespace *old_ns); +extern int create_user_ns(struct cred *new); extern void free_user_ns(struct kref *kref); static inline void put_user_ns(struct user_namespace *ns) @@ -43,13 +42,9 @@ static inline struct user_namespace *get_user_ns(struct user_namespace *ns) return &init_user_ns; } -static inline struct user_namespace *copy_user_ns(int flags, - struct user_namespace *old_ns) +static inline int create_user_ns(struct cred *new) { - if (flags & CLONE_NEWUSER) - return ERR_PTR(-EINVAL); - - return old_ns; + return -EINVAL; } static inline void put_user_ns(struct user_namespace *ns) diff --git a/include/net/scm.h b/include/net/scm.h index 33e9986beb8..f45bb6eca7d 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -55,8 +55,8 @@ static __inline__ int scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm) { struct task_struct *p = current; - scm->creds.uid = p->uid; - scm->creds.gid = p->gid; + scm->creds.uid = current_uid(); + scm->creds.gid = current_gid(); scm->creds.pid = task_tgid_vnr(p); scm->fp = NULL; scm->seq = 0; diff --git a/init/main.c b/init/main.c index 7e117a231af..db843bff573 100644 --- a/init/main.c +++ b/init/main.c @@ -669,6 +669,7 @@ asmlinkage void __init start_kernel(void) efi_enter_virtual_mode(); #endif thread_info_cache_init(); + cred_init(); fork_init(num_physpages); proc_caches_init(); buffer_init(); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 68eb857cfde..d9393f8e4c3 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -112,13 +112,14 @@ static inline struct mqueue_inode_info *MQUEUE_I(struct inode *inode) static struct inode *mqueue_get_inode(struct super_block *sb, int mode, struct mq_attr *attr) { + struct user_struct *u = current_user(); struct inode *inode; inode = new_inode(sb); if (inode) { inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_mtime = inode->i_ctime = inode->i_atime = CURRENT_TIME; @@ -126,7 +127,6 @@ static struct inode *mqueue_get_inode(struct super_block *sb, int mode, if (S_ISREG(mode)) { struct mqueue_inode_info *info; struct task_struct *p = current; - struct user_struct *u = p->user; unsigned long mq_bytes, mq_msg_tblsz; inode->i_fop = &mqueue_file_operations; @@ -507,7 +507,7 @@ static void __do_notify(struct mqueue_inode_info *info) sig_i.si_code = SI_MESGQ; sig_i.si_value = info->notify.sigev_value; sig_i.si_pid = task_tgid_vnr(current); - sig_i.si_uid = current->uid; + sig_i.si_uid = current_uid(); kill_pid_info(info->notify.sigev_signo, &sig_i, info->notify_owner); @@ -594,6 +594,7 @@ static int mq_attr_ok(struct mq_attr *attr) static struct file *do_create(struct dentry *dir, struct dentry *dentry, int oflag, mode_t mode, struct mq_attr __user *u_attr) { + const struct cred *cred = current_cred(); struct mq_attr attr; struct file *result; int ret; @@ -618,7 +619,7 @@ static struct file *do_create(struct dentry *dir, struct dentry *dentry, if (ret) goto out_drop_write; - result = dentry_open(dentry, mqueue_mnt, oflag); + result = dentry_open(dentry, mqueue_mnt, oflag, cred); /* * dentry_open() took a persistent mnt_want_write(), * so we can now drop this one. @@ -637,8 +638,10 @@ out: /* Opens existing queue */ static struct file *do_open(struct dentry *dentry, int oflag) { -static int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE, - MAY_READ | MAY_WRITE }; + const struct cred *cred = current_cred(); + + static const int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE, + MAY_READ | MAY_WRITE }; if ((oflag & O_ACCMODE) == (O_RDWR | O_WRONLY)) { dput(dentry); @@ -652,7 +655,7 @@ static int oflag2acc[O_ACCMODE] = { MAY_READ, MAY_WRITE, return ERR_PTR(-EACCES); } - return dentry_open(dentry, mqueue_mnt, oflag); + return dentry_open(dentry, mqueue_mnt, oflag, cred); } asmlinkage long sys_mq_open(const char __user *u_name, int oflag, mode_t mode, diff --git a/ipc/shm.c b/ipc/shm.c index 867e5d6a55c..38a055758a9 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -366,7 +366,7 @@ static int newseg(struct ipc_namespace *ns, struct ipc_params *params) if (shmflg & SHM_HUGETLB) { /* hugetlb_file_setup takes care of mlock user accounting */ file = hugetlb_file_setup(name, size); - shp->mlock_user = current->user; + shp->mlock_user = current_user(); } else { int acctflag = VM_ACCOUNT; /* @@ -752,9 +752,10 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) goto out_unlock; if (!capable(CAP_IPC_LOCK)) { + uid_t euid = current_euid(); err = -EPERM; - if (current->euid != shp->shm_perm.uid && - current->euid != shp->shm_perm.cuid) + if (euid != shp->shm_perm.uid && + euid != shp->shm_perm.cuid) goto out_unlock; if (cmd == SHM_LOCK && !current->signal->rlim[RLIMIT_MEMLOCK].rlim_cur) @@ -766,7 +767,7 @@ asmlinkage long sys_shmctl(int shmid, int cmd, struct shmid_ds __user *buf) goto out_unlock; if(cmd==SHM_LOCK) { - struct user_struct * user = current->user; + struct user_struct *user = current_user(); if (!is_file_hugepages(shp->shm_file)) { err = shmem_lock(shp->shm_file, 1, user); if (!err && !(shp->shm_perm.mode & SHM_LOCKED)){ diff --git a/ipc/util.c b/ipc/util.c index 361fd1c96fc..5a1808c774a 100644 --- a/ipc/util.c +++ b/ipc/util.c @@ -258,6 +258,8 @@ int ipc_get_maxid(struct ipc_ids *ids) int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) { + uid_t euid; + gid_t egid; int id, err; if (size > IPCMNI) @@ -280,8 +282,9 @@ int ipc_addid(struct ipc_ids* ids, struct kern_ipc_perm* new, int size) ids->in_use++; - new->cuid = new->uid = current->euid; - new->gid = new->cgid = current->egid; + current_euid_egid(&euid, &egid); + new->cuid = new->uid = euid; + new->gid = new->cgid = egid; new->seq = ids->seq++; if(ids->seq > ids->seq_max) @@ -620,13 +623,15 @@ void ipc_rcu_putref(void *ptr) int ipcperms (struct kern_ipc_perm *ipcp, short flag) { /* flag will most probably be 0 or S_...UGO from */ + uid_t euid = current_euid(); int requested_mode, granted_mode, err; if (unlikely((err = audit_ipc_obj(ipcp)))) return err; requested_mode = (flag >> 6) | (flag >> 3) | flag; granted_mode = ipcp->mode; - if (current->euid == ipcp->cuid || current->euid == ipcp->uid) + if (euid == ipcp->cuid || + euid == ipcp->uid) granted_mode >>= 6; else if (in_group_p(ipcp->cgid) || in_group_p(ipcp->gid)) granted_mode >>= 3; @@ -788,6 +793,7 @@ struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd, struct ipc64_perm *perm, int extra_perm) { struct kern_ipc_perm *ipcp; + uid_t euid; int err; down_write(&ids->rw_mutex); @@ -807,8 +813,10 @@ struct kern_ipc_perm *ipcctl_pre_down(struct ipc_ids *ids, int id, int cmd, if (err) goto out_unlock; } - if (current->euid == ipcp->cuid || - current->euid == ipcp->uid || capable(CAP_SYS_ADMIN)) + + euid = current_euid(); + if (euid == ipcp->cuid || + euid == ipcp->uid || capable(CAP_SYS_ADMIN)) return ipcp; err = -EPERM; diff --git a/kernel/Makefile b/kernel/Makefile index 19fad003b19..b1e6b6625ea 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -9,7 +9,7 @@ obj-y = sched.o fork.o exec_domain.o panic.o printk.o \ rcupdate.o extable.o params.o posix-timers.o \ kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \ hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \ - notifier.o ksysfs.o pm_qos_params.o sched_clock.o + notifier.o ksysfs.o pm_qos_params.o sched_clock.o cred.o ifdef CONFIG_FUNCTION_TRACER # Do not trace debug files and internal ftrace files diff --git a/kernel/acct.c b/kernel/acct.c index f6006a60df5..d57b7cbb98b 100644 --- a/kernel/acct.c +++ b/kernel/acct.c @@ -530,15 +530,14 @@ static void do_acct_process(struct bsd_acct_struct *acct, do_div(elapsed, AHZ); ac.ac_btime = get_seconds() - elapsed; /* we really need to bite the bullet and change layout */ - ac.ac_uid = current->uid; - ac.ac_gid = current->gid; + current_uid_gid(&ac.ac_uid, &ac.ac_gid); #if ACCT_VERSION==2 ac.ac_ahz = AHZ; #endif #if ACCT_VERSION==1 || ACCT_VERSION==2 /* backward-compatible 16 bit fields */ - ac.ac_uid16 = current->uid; - ac.ac_gid16 = current->gid; + ac.ac_uid16 = ac.ac_uid; + ac.ac_gid16 = ac.ac_gid; #endif #if ACCT_VERSION==3 ac.ac_pid = task_tgid_nr_ns(current, ns); diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 2a3f0afc4d2..4819f371197 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -65,6 +65,7 @@ #include #include #include +#include #include "audit.h" @@ -84,6 +85,15 @@ int audit_n_rules; /* determines whether we collect data for signals sent */ int audit_signals; +struct audit_cap_data { + kernel_cap_t permitted; + kernel_cap_t inheritable; + union { + unsigned int fE; /* effective bit of a file capability */ + kernel_cap_t effective; /* effective set of a process */ + }; +}; + /* When fs/namei.c:getname() is called, we store the pointer in name and * we don't let putname() free it (instead we free all of the saved * pointers at syscall exit time). @@ -100,6 +110,8 @@ struct audit_names { gid_t gid; dev_t rdev; u32 osid; + struct audit_cap_data fcap; + unsigned int fcap_ver; }; struct audit_aux_data { @@ -184,6 +196,20 @@ struct audit_aux_data_pids { int pid_count; }; +struct audit_aux_data_bprm_fcaps { + struct audit_aux_data d; + struct audit_cap_data fcap; + unsigned int fcap_ver; + struct audit_cap_data old_pcap; + struct audit_cap_data new_pcap; +}; + +struct audit_aux_data_capset { + struct audit_aux_data d; + pid_t pid; + struct audit_cap_data cap; +}; + struct audit_tree_refs { struct audit_tree_refs *next; struct audit_chunk *c[31]; @@ -421,6 +447,7 @@ static int audit_filter_rules(struct task_struct *tsk, struct audit_names *name, enum audit_state *state) { + const struct cred *cred = get_task_cred(tsk); int i, j, need_sid = 1; u32 sid; @@ -440,28 +467,28 @@ static int audit_filter_rules(struct task_struct *tsk, } break; case AUDIT_UID: - result = audit_comparator(tsk->uid, f->op, f->val); + result = audit_comparator(cred->uid, f->op, f->val); break; case AUDIT_EUID: - result = audit_comparator(tsk->euid, f->op, f->val); + result = audit_comparator(cred->euid, f->op, f->val); break; case AUDIT_SUID: - result = audit_comparator(tsk->suid, f->op, f->val); + result = audit_comparator(cred->suid, f->op, f->val); break; case AUDIT_FSUID: - result = audit_comparator(tsk->fsuid, f->op, f->val); + result = audit_comparator(cred->fsuid, f->op, f->val); break; case AUDIT_GID: - result = audit_comparator(tsk->gid, f->op, f->val); + result = audit_comparator(cred->gid, f->op, f->val); break; case AUDIT_EGID: - result = audit_comparator(tsk->egid, f->op, f->val); + result = audit_comparator(cred->egid, f->op, f->val); break; case AUDIT_SGID: - result = audit_comparator(tsk->sgid, f->op, f->val); + result = audit_comparator(cred->sgid, f->op, f->val); break; case AUDIT_FSGID: - result = audit_comparator(tsk->fsgid, f->op, f->val); + result = audit_comparator(cred->fsgid, f->op, f->val); break; case AUDIT_PERS: result = audit_comparator(tsk->personality, f->op, f->val); @@ -615,8 +642,10 @@ static int audit_filter_rules(struct task_struct *tsk, break; } - if (!result) + if (!result) { + put_cred(cred); return 0; + } } if (rule->filterkey && ctx) ctx->filterkey = kstrdup(rule->filterkey, GFP_ATOMIC); @@ -624,6 +653,7 @@ static int audit_filter_rules(struct task_struct *tsk, case AUDIT_NEVER: *state = AUDIT_DISABLED; break; case AUDIT_ALWAYS: *state = AUDIT_RECORD_CONTEXT; break; } + put_cred(cred); return 1; } @@ -1171,8 +1201,38 @@ static void audit_log_execve_info(struct audit_context *context, kfree(buf); } +static void audit_log_cap(struct audit_buffer *ab, char *prefix, kernel_cap_t *cap) +{ + int i; + + audit_log_format(ab, " %s=", prefix); + CAP_FOR_EACH_U32(i) { + audit_log_format(ab, "%08x", cap->cap[(_KERNEL_CAPABILITY_U32S-1) - i]); + } +} + +static void audit_log_fcaps(struct audit_buffer *ab, struct audit_names *name) +{ + kernel_cap_t *perm = &name->fcap.permitted; + kernel_cap_t *inh = &name->fcap.inheritable; + int log = 0; + + if (!cap_isclear(*perm)) { + audit_log_cap(ab, "cap_fp", perm); + log = 1; + } + if (!cap_isclear(*inh)) { + audit_log_cap(ab, "cap_fi", inh); + log = 1; + } + + if (log) + audit_log_format(ab, " cap_fe=%d cap_fver=%x", name->fcap.fE, name->fcap_ver); +} + static void audit_log_exit(struct audit_context *context, struct task_struct *tsk) { + const struct cred *cred; int i, call_panic = 0; struct audit_buffer *ab; struct audit_aux_data *aux; @@ -1182,14 +1242,15 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts context->pid = tsk->pid; if (!context->ppid) context->ppid = sys_getppid(); - context->uid = tsk->uid; - context->gid = tsk->gid; - context->euid = tsk->euid; - context->suid = tsk->suid; - context->fsuid = tsk->fsuid; - context->egid = tsk->egid; - context->sgid = tsk->sgid; - context->fsgid = tsk->fsgid; + cred = current_cred(); + context->uid = cred->uid; + context->gid = cred->gid; + context->euid = cred->euid; + context->suid = cred->suid; + context->fsuid = cred->fsuid; + context->egid = cred->egid; + context->sgid = cred->sgid; + context->fsgid = cred->fsgid; context->personality = tsk->personality; ab = audit_log_start(context, GFP_KERNEL, AUDIT_SYSCALL); @@ -1334,6 +1395,28 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts audit_log_format(ab, "fd0=%d fd1=%d", axs->fd[0], axs->fd[1]); break; } + case AUDIT_BPRM_FCAPS: { + struct audit_aux_data_bprm_fcaps *axs = (void *)aux; + audit_log_format(ab, "fver=%x", axs->fcap_ver); + audit_log_cap(ab, "fp", &axs->fcap.permitted); + audit_log_cap(ab, "fi", &axs->fcap.inheritable); + audit_log_format(ab, " fe=%d", axs->fcap.fE); + audit_log_cap(ab, "old_pp", &axs->old_pcap.permitted); + audit_log_cap(ab, "old_pi", &axs->old_pcap.inheritable); + audit_log_cap(ab, "old_pe", &axs->old_pcap.effective); + audit_log_cap(ab, "new_pp", &axs->new_pcap.permitted); + audit_log_cap(ab, "new_pi", &axs->new_pcap.inheritable); + audit_log_cap(ab, "new_pe", &axs->new_pcap.effective); + break; } + + case AUDIT_CAPSET: { + struct audit_aux_data_capset *axs = (void *)aux; + audit_log_format(ab, "pid=%d", axs->pid); + audit_log_cap(ab, "cap_pi", &axs->cap.inheritable); + audit_log_cap(ab, "cap_pp", &axs->cap.permitted); + audit_log_cap(ab, "cap_pe", &axs->cap.effective); + break; } + } audit_log_end(ab); } @@ -1421,6 +1504,8 @@ static void audit_log_exit(struct audit_context *context, struct task_struct *ts } } + audit_log_fcaps(ab, n); + audit_log_end(ab); } @@ -1802,8 +1887,36 @@ static int audit_inc_name_count(struct audit_context *context, return 0; } + +static inline int audit_copy_fcaps(struct audit_names *name, const struct dentry *dentry) +{ + struct cpu_vfs_cap_data caps; + int rc; + + memset(&name->fcap.permitted, 0, sizeof(kernel_cap_t)); + memset(&name->fcap.inheritable, 0, sizeof(kernel_cap_t)); + name->fcap.fE = 0; + name->fcap_ver = 0; + + if (!dentry) + return 0; + + rc = get_vfs_caps_from_disk(dentry, &caps); + if (rc) + return rc; + + name->fcap.permitted = caps.permitted; + name->fcap.inheritable = caps.inheritable; + name->fcap.fE = !!(caps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE); + name->fcap_ver = (caps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT; + + return 0; +} + + /* Copy inode data into an audit_names. */ -static void audit_copy_inode(struct audit_names *name, const struct inode *inode) +static void audit_copy_inode(struct audit_names *name, const struct dentry *dentry, + const struct inode *inode) { name->ino = inode->i_ino; name->dev = inode->i_sb->s_dev; @@ -1812,6 +1925,7 @@ static void audit_copy_inode(struct audit_names *name, const struct inode *inode name->gid = inode->i_gid; name->rdev = inode->i_rdev; security_inode_getsecid(inode, &name->osid); + audit_copy_fcaps(name, dentry); } /** @@ -1846,7 +1960,7 @@ void __audit_inode(const char *name, const struct dentry *dentry) context->names[idx].name = NULL; } handle_path(dentry); - audit_copy_inode(&context->names[idx], inode); + audit_copy_inode(&context->names[idx], dentry, inode); } /** @@ -1907,7 +2021,7 @@ void __audit_inode_child(const char *dname, const struct dentry *dentry, if (!strcmp(dname, n->name) || !audit_compare_dname_path(dname, n->name, &dirlen)) { if (inode) - audit_copy_inode(n, inode); + audit_copy_inode(n, NULL, inode); else n->ino = (unsigned long)-1; found_child = n->name; @@ -1921,7 +2035,7 @@ add_names: return; idx = context->name_count - 1; context->names[idx].name = NULL; - audit_copy_inode(&context->names[idx], parent); + audit_copy_inode(&context->names[idx], NULL, parent); } if (!found_child) { @@ -1942,7 +2056,7 @@ add_names: } if (inode) - audit_copy_inode(&context->names[idx], inode); + audit_copy_inode(&context->names[idx], NULL, inode); else context->names[idx].ino = (unsigned long)-1; } @@ -1996,7 +2110,7 @@ int audit_set_loginuid(struct task_struct *task, uid_t loginuid) audit_log_format(ab, "login pid=%d uid=%u " "old auid=%u new auid=%u" " old ses=%u new ses=%u", - task->pid, task->uid, + task->pid, task_uid(task), task->loginuid, loginuid, task->sessionid, sessionid); audit_log_end(ab); @@ -2379,7 +2493,7 @@ void __audit_ptrace(struct task_struct *t) context->target_pid = t->pid; context->target_auid = audit_get_loginuid(t); - context->target_uid = t->uid; + context->target_uid = task_uid(t); context->target_sessionid = audit_get_sessionid(t); security_task_getsecid(t, &context->target_sid); memcpy(context->target_comm, t->comm, TASK_COMM_LEN); @@ -2398,6 +2512,7 @@ int __audit_signal_info(int sig, struct task_struct *t) struct audit_aux_data_pids *axp; struct task_struct *tsk = current; struct audit_context *ctx = tsk->audit_context; + uid_t uid = current_uid(), t_uid = task_uid(t); if (audit_pid && t->tgid == audit_pid) { if (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2) { @@ -2405,7 +2520,7 @@ int __audit_signal_info(int sig, struct task_struct *t) if (tsk->loginuid != -1) audit_sig_uid = tsk->loginuid; else - audit_sig_uid = tsk->uid; + audit_sig_uid = uid; security_task_getsecid(tsk, &audit_sig_sid); } if (!audit_signals || audit_dummy_context()) @@ -2417,7 +2532,7 @@ int __audit_signal_info(int sig, struct task_struct *t) if (!ctx->target_pid) { ctx->target_pid = t->tgid; ctx->target_auid = audit_get_loginuid(t); - ctx->target_uid = t->uid; + ctx->target_uid = t_uid; ctx->target_sessionid = audit_get_sessionid(t); security_task_getsecid(t, &ctx->target_sid); memcpy(ctx->target_comm, t->comm, TASK_COMM_LEN); @@ -2438,7 +2553,7 @@ int __audit_signal_info(int sig, struct task_struct *t) axp->target_pid[axp->pid_count] = t->tgid; axp->target_auid[axp->pid_count] = audit_get_loginuid(t); - axp->target_uid[axp->pid_count] = t->uid; + axp->target_uid[axp->pid_count] = t_uid; axp->target_sessionid[axp->pid_count] = audit_get_sessionid(t); security_task_getsecid(t, &axp->target_sid[axp->pid_count]); memcpy(axp->target_comm[axp->pid_count], t->comm, TASK_COMM_LEN); @@ -2447,6 +2562,86 @@ int __audit_signal_info(int sig, struct task_struct *t) return 0; } +/** + * __audit_log_bprm_fcaps - store information about a loading bprm and relevant fcaps + * @bprm: pointer to the bprm being processed + * @new: the proposed new credentials + * @old: the old credentials + * + * Simply check if the proc already has the caps given by the file and if not + * store the priv escalation info for later auditing at the end of the syscall + * + * -Eric + */ +int __audit_log_bprm_fcaps(struct linux_binprm *bprm, + const struct cred *new, const struct cred *old) +{ + struct audit_aux_data_bprm_fcaps *ax; + struct audit_context *context = current->audit_context; + struct cpu_vfs_cap_data vcaps; + struct dentry *dentry; + + ax = kmalloc(sizeof(*ax), GFP_KERNEL); + if (!ax) + return -ENOMEM; + + ax->d.type = AUDIT_BPRM_FCAPS; + ax->d.next = context->aux; + context->aux = (void *)ax; + + dentry = dget(bprm->file->f_dentry); + get_vfs_caps_from_disk(dentry, &vcaps); + dput(dentry); + + ax->fcap.permitted = vcaps.permitted; + ax->fcap.inheritable = vcaps.inheritable; + ax->fcap.fE = !!(vcaps.magic_etc & VFS_CAP_FLAGS_EFFECTIVE); + ax->fcap_ver = (vcaps.magic_etc & VFS_CAP_REVISION_MASK) >> VFS_CAP_REVISION_SHIFT; + + ax->old_pcap.permitted = old->cap_permitted; + ax->old_pcap.inheritable = old->cap_inheritable; + ax->old_pcap.effective = old->cap_effective; + + ax->new_pcap.permitted = new->cap_permitted; + ax->new_pcap.inheritable = new->cap_inheritable; + ax->new_pcap.effective = new->cap_effective; + return 0; +} + +/** + * __audit_log_capset - store information about the arguments to the capset syscall + * @pid: target pid of the capset call + * @new: the new credentials + * @old: the old (current) credentials + * + * Record the aguments userspace sent to sys_capset for later printing by the + * audit system if applicable + */ +int __audit_log_capset(pid_t pid, + const struct cred *new, const struct cred *old) +{ + struct audit_aux_data_capset *ax; + struct audit_context *context = current->audit_context; + + if (likely(!audit_enabled || !context || context->dummy)) + return 0; + + ax = kmalloc(sizeof(*ax), GFP_KERNEL); + if (!ax) + return -ENOMEM; + + ax->d.type = AUDIT_CAPSET; + ax->d.next = context->aux; + context->aux = (void *)ax; + + ax->pid = pid; + ax->cap.effective = new->cap_effective; + ax->cap.inheritable = new->cap_effective; + ax->cap.permitted = new->cap_permitted; + + return 0; +} + /** * audit_core_dumps - record information about processes that end abnormally * @signr: signal value @@ -2458,7 +2653,8 @@ void audit_core_dumps(long signr) { struct audit_buffer *ab; u32 sid; - uid_t auid = audit_get_loginuid(current); + uid_t auid = audit_get_loginuid(current), uid; + gid_t gid; unsigned int sessionid = audit_get_sessionid(current); if (!audit_enabled) @@ -2468,8 +2664,9 @@ void audit_core_dumps(long signr) return; ab = audit_log_start(NULL, GFP_KERNEL, AUDIT_ANOM_ABEND); + current_uid_gid(&uid, &gid); audit_log_format(ab, "auid=%u uid=%u gid=%u ses=%u", - auid, current->uid, current->gid, sessionid); + auid, uid, gid, sessionid); security_task_getsecid(current, &sid); if (sid) { char *ctx = NULL; diff --git a/kernel/capability.c b/kernel/capability.c index 33e51e78c2d..36b4b4daebe 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -7,6 +7,7 @@ * 30 May 2002: Cleanup, Robert M. Love */ +#include #include #include #include @@ -14,12 +15,7 @@ #include #include #include - -/* - * This lock protects task->cap_* for all tasks including current. - * Locking rule: acquire this prior to tasklist_lock. - */ -static DEFINE_SPINLOCK(task_capability_lock); +#include "cred-internals.h" /* * Leveraged for setting/resetting capabilities @@ -33,6 +29,17 @@ EXPORT_SYMBOL(__cap_empty_set); EXPORT_SYMBOL(__cap_full_set); EXPORT_SYMBOL(__cap_init_eff_set); +#ifdef CONFIG_SECURITY_FILE_CAPABILITIES +int file_caps_enabled = 1; + +static int __init file_caps_disable(char *str) +{ + file_caps_enabled = 0; + return 1; +} +__setup("no_file_caps", file_caps_disable); +#endif + /* * More recent versions of libcap are available from: * @@ -115,167 +122,12 @@ static int cap_validate_magic(cap_user_header_t header, unsigned *tocopy) return 0; } -#ifndef CONFIG_SECURITY_FILE_CAPABILITIES - /* - * Without filesystem capability support, we nominally support one process - * setting the capabilities of another - */ -static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, - kernel_cap_t *pIp, kernel_cap_t *pPp) -{ - struct task_struct *target; - int ret; - - spin_lock(&task_capability_lock); - read_lock(&tasklist_lock); - - if (pid && pid != task_pid_vnr(current)) { - target = find_task_by_vpid(pid); - if (!target) { - ret = -ESRCH; - goto out; - } - } else - target = current; - - ret = security_capget(target, pEp, pIp, pPp); - -out: - read_unlock(&tasklist_lock); - spin_unlock(&task_capability_lock); - - return ret; -} - -/* - * cap_set_pg - set capabilities for all processes in a given process - * group. We call this holding task_capability_lock and tasklist_lock. - */ -static inline int cap_set_pg(int pgrp_nr, kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - struct task_struct *g, *target; - int ret = -EPERM; - int found = 0; - struct pid *pgrp; - - spin_lock(&task_capability_lock); - read_lock(&tasklist_lock); - - pgrp = find_vpid(pgrp_nr); - do_each_pid_task(pgrp, PIDTYPE_PGID, g) { - target = g; - while_each_thread(g, target) { - if (!security_capset_check(target, effective, - inheritable, permitted)) { - security_capset_set(target, effective, - inheritable, permitted); - ret = 0; - } - found = 1; - } - } while_each_pid_task(pgrp, PIDTYPE_PGID, g); - - read_unlock(&tasklist_lock); - spin_unlock(&task_capability_lock); - - if (!found) - ret = 0; - return ret; -} - -/* - * cap_set_all - set capabilities for all processes other than init - * and self. We call this holding task_capability_lock and tasklist_lock. - */ -static inline int cap_set_all(kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - struct task_struct *g, *target; - int ret = -EPERM; - int found = 0; - - spin_lock(&task_capability_lock); - read_lock(&tasklist_lock); - - do_each_thread(g, target) { - if (target == current - || is_container_init(target->group_leader)) - continue; - found = 1; - if (security_capset_check(target, effective, inheritable, - permitted)) - continue; - ret = 0; - security_capset_set(target, effective, inheritable, permitted); - } while_each_thread(g, target); - - read_unlock(&tasklist_lock); - spin_unlock(&task_capability_lock); - - if (!found) - ret = 0; - - return ret; -} - -/* - * Given the target pid does not refer to the current process we - * need more elaborate support... (This support is not present when - * filesystem capabilities are configured.) - */ -static inline int do_sys_capset_other_tasks(pid_t pid, kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - struct task_struct *target; - int ret; - - if (!capable(CAP_SETPCAP)) - return -EPERM; - - if (pid == -1) /* all procs other than current and init */ - return cap_set_all(effective, inheritable, permitted); - - else if (pid < 0) /* all procs in process group */ - return cap_set_pg(-pid, effective, inheritable, permitted); - - /* target != current */ - spin_lock(&task_capability_lock); - read_lock(&tasklist_lock); - - target = find_task_by_vpid(pid); - if (!target) - ret = -ESRCH; - else { - ret = security_capset_check(target, effective, inheritable, - permitted); - - /* having verified that the proposed changes are legal, - we now put them into effect. */ - if (!ret) - security_capset_set(target, effective, inheritable, - permitted); - } - - read_unlock(&tasklist_lock); - spin_unlock(&task_capability_lock); - - return ret; -} - -#else /* ie., def CONFIG_SECURITY_FILE_CAPABILITIES */ - -/* - * If we have configured with filesystem capability support, then the - * only thing that can change the capabilities of the current process - * is the current process. As such, we can't be in this code at the - * same time as we are in the process of setting capabilities in this - * process. The net result is that we can limit our use of locks to - * when we are reading the caps of another process. + * The only thing that can change the capabilities of the current + * process is the current process. As such, we can't be in this code + * at the same time as we are in the process of setting capabilities + * in this process. The net result is that we can limit our use of + * locks to when we are reading the caps of another process. */ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, kernel_cap_t *pIp, kernel_cap_t *pPp) @@ -285,7 +137,6 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, if (pid && (pid != task_pid_vnr(current))) { struct task_struct *target; - spin_lock(&task_capability_lock); read_lock(&tasklist_lock); target = find_task_by_vpid(pid); @@ -295,50 +146,12 @@ static inline int cap_get_target_pid(pid_t pid, kernel_cap_t *pEp, ret = security_capget(target, pEp, pIp, pPp); read_unlock(&tasklist_lock); - spin_unlock(&task_capability_lock); } else ret = security_capget(current, pEp, pIp, pPp); return ret; } -/* - * With filesystem capability support configured, the kernel does not - * permit the changing of capabilities in one process by another - * process. (CAP_SETPCAP has much less broad semantics when configured - * this way.) - */ -static inline int do_sys_capset_other_tasks(pid_t pid, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - return -EPERM; -} - -#endif /* ie., ndef CONFIG_SECURITY_FILE_CAPABILITIES */ - -/* - * Atomically modify the effective capabilities returning the original - * value. No permission check is performed here - it is assumed that the - * caller is permitted to set the desired effective capabilities. - */ -kernel_cap_t cap_set_effective(const kernel_cap_t pE_new) -{ - kernel_cap_t pE_old; - - spin_lock(&task_capability_lock); - - pE_old = current->cap_effective; - current->cap_effective = pE_new; - - spin_unlock(&task_capability_lock); - - return pE_old; -} - -EXPORT_SYMBOL(cap_set_effective); - /** * sys_capget - get the capabilities of a given process. * @header: pointer to struct that contains capability version and @@ -366,7 +179,6 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr) return -EINVAL; ret = cap_get_target_pid(pid, &pE, &pI, &pP); - if (!ret) { struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i; @@ -412,16 +224,14 @@ asmlinkage long sys_capget(cap_user_header_t header, cap_user_data_t dataptr) * @data: pointer to struct that contains the effective, permitted, * and inheritable capabilities * - * Set capabilities for a given process, all processes, or all - * processes in a given process group. + * Set capabilities for the current process only. The ability to any other + * process(es) has been deprecated and removed. * * The restrictions on setting capabilities are specified as: * - * [pid is for the 'target' task. 'current' is the calling task.] - * - * I: any raised capabilities must be a subset of the (old current) permitted - * P: any raised capabilities must be a subset of the (old current) permitted - * E: must be set to a subset of (new target) permitted + * I: any raised capabilities must be a subset of the old permitted + * P: any raised capabilities must be a subset of the old permitted + * E: must be set to a subset of new permitted * * Returns 0 on success and < 0 on error. */ @@ -430,6 +240,7 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) struct __user_cap_data_struct kdata[_KERNEL_CAPABILITY_U32S]; unsigned i, tocopy; kernel_cap_t inheritable, permitted, effective; + struct cred *new; int ret; pid_t pid; @@ -440,10 +251,13 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) if (get_user(pid, &header->pid)) return -EFAULT; - if (copy_from_user(&kdata, data, tocopy - * sizeof(struct __user_cap_data_struct))) { + /* may only affect current now */ + if (pid != 0 && pid != task_pid_vnr(current)) + return -EPERM; + + if (copy_from_user(&kdata, data, + tocopy * sizeof(struct __user_cap_data_struct))) return -EFAULT; - } for (i = 0; i < tocopy; i++) { effective.cap[i] = kdata[i].effective; @@ -457,32 +271,23 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) i++; } - if (pid && (pid != task_pid_vnr(current))) - ret = do_sys_capset_other_tasks(pid, &effective, &inheritable, - &permitted); - else { - /* - * This lock is required even when filesystem - * capability support is configured - it protects the - * sys_capget() call from returning incorrect data in - * the case that the targeted process is not the - * current one. - */ - spin_lock(&task_capability_lock); + new = prepare_creds(); + if (!new) + return -ENOMEM; - ret = security_capset_check(current, &effective, &inheritable, - &permitted); - /* - * Having verified that the proposed changes are - * legal, we now put them into effect. - */ - if (!ret) - security_capset_set(current, &effective, &inheritable, - &permitted); - spin_unlock(&task_capability_lock); - } + ret = security_capset(new, current_cred(), + &effective, &inheritable, &permitted); + if (ret < 0) + goto error; + ret = audit_log_capset(pid, new, current_cred()); + if (ret < 0) + return ret; + return commit_creds(new); + +error: + abort_creds(new); return ret; } @@ -498,6 +303,11 @@ asmlinkage long sys_capset(cap_user_header_t header, const cap_user_data_t data) */ int capable(int cap) { + if (unlikely(!cap_valid(cap))) { + printk(KERN_CRIT "capable() called with invalid cap=%u\n", cap); + BUG(); + } + if (has_capability(current, cap)) { current->flags |= PF_SUPERPRIV; return 1; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 2606d0fb4e5..48348dde6d8 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -571,8 +571,8 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb) if (inode) { inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_mapping->backing_dev_info = &cgroup_backing_dev_info; @@ -1280,6 +1280,7 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk) static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) { struct task_struct *tsk; + const struct cred *cred = current_cred(), *tcred; int ret; if (pid) { @@ -1289,14 +1290,16 @@ static int attach_task_by_pid(struct cgroup *cgrp, u64 pid) rcu_read_unlock(); return -ESRCH; } - get_task_struct(tsk); - rcu_read_unlock(); - if ((current->euid) && (current->euid != tsk->uid) - && (current->euid != tsk->suid)) { - put_task_struct(tsk); + tcred = __task_cred(tsk); + if (cred->euid && + cred->euid != tcred->uid && + cred->euid != tcred->suid) { + rcu_read_unlock(); return -EACCES; } + get_task_struct(tsk); + rcu_read_unlock(); } else { tsk = current; get_task_struct(tsk); diff --git a/kernel/cred-internals.h b/kernel/cred-internals.h new file mode 100644 index 00000000000..2dc4fc2d0bf --- /dev/null +++ b/kernel/cred-internals.h @@ -0,0 +1,21 @@ +/* Internal credentials stuff + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +/* + * user.c + */ +static inline void sched_switch_user(struct task_struct *p) +{ +#ifdef CONFIG_USER_SCHED + sched_move_task(p); +#endif /* CONFIG_USER_SCHED */ +} + diff --git a/kernel/cred.c b/kernel/cred.c new file mode 100644 index 00000000000..ff7bc071991 --- /dev/null +++ b/kernel/cred.c @@ -0,0 +1,588 @@ +/* Task credentials management - see Documentation/credentials.txt + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ +#include +#include +#include +#include +#include +#include +#include +#include +#include "cred-internals.h" + +static struct kmem_cache *cred_jar; + +/* + * The common credentials for the initial task's thread group + */ +#ifdef CONFIG_KEYS +static struct thread_group_cred init_tgcred = { + .usage = ATOMIC_INIT(2), + .tgid = 0, + .lock = SPIN_LOCK_UNLOCKED, +}; +#endif + +/* + * The initial credentials for the initial task + */ +struct cred init_cred = { + .usage = ATOMIC_INIT(4), + .securebits = SECUREBITS_DEFAULT, + .cap_inheritable = CAP_INIT_INH_SET, + .cap_permitted = CAP_FULL_SET, + .cap_effective = CAP_INIT_EFF_SET, + .cap_bset = CAP_INIT_BSET, + .user = INIT_USER, + .group_info = &init_groups, +#ifdef CONFIG_KEYS + .tgcred = &init_tgcred, +#endif +}; + +/* + * Dispose of the shared task group credentials + */ +#ifdef CONFIG_KEYS +static void release_tgcred_rcu(struct rcu_head *rcu) +{ + struct thread_group_cred *tgcred = + container_of(rcu, struct thread_group_cred, rcu); + + BUG_ON(atomic_read(&tgcred->usage) != 0); + + key_put(tgcred->session_keyring); + key_put(tgcred->process_keyring); + kfree(tgcred); +} +#endif + +/* + * Release a set of thread group credentials. + */ +static void release_tgcred(struct cred *cred) +{ +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred = cred->tgcred; + + if (atomic_dec_and_test(&tgcred->usage)) + call_rcu(&tgcred->rcu, release_tgcred_rcu); +#endif +} + +/* + * The RCU callback to actually dispose of a set of credentials + */ +static void put_cred_rcu(struct rcu_head *rcu) +{ + struct cred *cred = container_of(rcu, struct cred, rcu); + + if (atomic_read(&cred->usage) != 0) + panic("CRED: put_cred_rcu() sees %p with usage %d\n", + cred, atomic_read(&cred->usage)); + + security_cred_free(cred); + key_put(cred->thread_keyring); + key_put(cred->request_key_auth); + release_tgcred(cred); + put_group_info(cred->group_info); + free_uid(cred->user); + kmem_cache_free(cred_jar, cred); +} + +/** + * __put_cred - Destroy a set of credentials + * @cred: The record to release + * + * Destroy a set of credentials on which no references remain. + */ +void __put_cred(struct cred *cred) +{ + BUG_ON(atomic_read(&cred->usage) != 0); + + call_rcu(&cred->rcu, put_cred_rcu); +} +EXPORT_SYMBOL(__put_cred); + +/** + * prepare_creds - Prepare a new set of credentials for modification + * + * Prepare a new set of task credentials for modification. A task's creds + * shouldn't generally be modified directly, therefore this function is used to + * prepare a new copy, which the caller then modifies and then commits by + * calling commit_creds(). + * + * Preparation involves making a copy of the objective creds for modification. + * + * Returns a pointer to the new creds-to-be if successful, NULL otherwise. + * + * Call commit_creds() or abort_creds() to clean up. + */ +struct cred *prepare_creds(void) +{ + struct task_struct *task = current; + const struct cred *old; + struct cred *new; + + BUG_ON(atomic_read(&task->real_cred->usage) < 1); + + new = kmem_cache_alloc(cred_jar, GFP_KERNEL); + if (!new) + return NULL; + + old = task->cred; + memcpy(new, old, sizeof(struct cred)); + + atomic_set(&new->usage, 1); + get_group_info(new->group_info); + get_uid(new->user); + +#ifdef CONFIG_KEYS + key_get(new->thread_keyring); + key_get(new->request_key_auth); + atomic_inc(&new->tgcred->usage); +#endif + +#ifdef CONFIG_SECURITY + new->security = NULL; +#endif + + if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + goto error; + return new; + +error: + abort_creds(new); + return NULL; +} +EXPORT_SYMBOL(prepare_creds); + +/* + * Prepare credentials for current to perform an execve() + * - The caller must hold current->cred_exec_mutex + */ +struct cred *prepare_exec_creds(void) +{ + struct thread_group_cred *tgcred = NULL; + struct cred *new; + +#ifdef CONFIG_KEYS + tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); + if (!tgcred) + return NULL; +#endif + + new = prepare_creds(); + if (!new) { + kfree(tgcred); + return new; + } + +#ifdef CONFIG_KEYS + /* newly exec'd tasks don't get a thread keyring */ + key_put(new->thread_keyring); + new->thread_keyring = NULL; + + /* create a new per-thread-group creds for all this set of threads to + * share */ + memcpy(tgcred, new->tgcred, sizeof(struct thread_group_cred)); + + atomic_set(&tgcred->usage, 1); + spin_lock_init(&tgcred->lock); + + /* inherit the session keyring; new process keyring */ + key_get(tgcred->session_keyring); + tgcred->process_keyring = NULL; + + release_tgcred(new); + new->tgcred = tgcred; +#endif + + return new; +} + +/* + * prepare new credentials for the usermode helper dispatcher + */ +struct cred *prepare_usermodehelper_creds(void) +{ +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred = NULL; +#endif + struct cred *new; + +#ifdef CONFIG_KEYS + tgcred = kzalloc(sizeof(*new->tgcred), GFP_ATOMIC); + if (!tgcred) + return NULL; +#endif + + new = kmem_cache_alloc(cred_jar, GFP_ATOMIC); + if (!new) + return NULL; + + memcpy(new, &init_cred, sizeof(struct cred)); + + atomic_set(&new->usage, 1); + get_group_info(new->group_info); + get_uid(new->user); + +#ifdef CONFIG_KEYS + new->thread_keyring = NULL; + new->request_key_auth = NULL; + new->jit_keyring = KEY_REQKEY_DEFL_DEFAULT; + + atomic_set(&tgcred->usage, 1); + spin_lock_init(&tgcred->lock); + new->tgcred = tgcred; +#endif + +#ifdef CONFIG_SECURITY + new->security = NULL; +#endif + if (security_prepare_creds(new, &init_cred, GFP_ATOMIC) < 0) + goto error; + + BUG_ON(atomic_read(&new->usage) != 1); + return new; + +error: + put_cred(new); + return NULL; +} + +/* + * Copy credentials for the new process created by fork() + * + * We share if we can, but under some circumstances we have to generate a new + * set. + * + * The new process gets the current process's subjective credentials as its + * objective and subjective credentials + */ +int copy_creds(struct task_struct *p, unsigned long clone_flags) +{ +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred; +#endif + struct cred *new; + int ret; + + mutex_init(&p->cred_exec_mutex); + + if ( +#ifdef CONFIG_KEYS + !p->cred->thread_keyring && +#endif + clone_flags & CLONE_THREAD + ) { + p->real_cred = get_cred(p->cred); + get_cred(p->cred); + atomic_inc(&p->cred->user->processes); + return 0; + } + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + if (clone_flags & CLONE_NEWUSER) { + ret = create_user_ns(new); + if (ret < 0) + goto error_put; + } + +#ifdef CONFIG_KEYS + /* new threads get their own thread keyrings if their parent already + * had one */ + if (new->thread_keyring) { + key_put(new->thread_keyring); + new->thread_keyring = NULL; + if (clone_flags & CLONE_THREAD) + install_thread_keyring_to_cred(new); + } + + /* we share the process and session keyrings between all the threads in + * a process - this is slightly icky as we violate COW credentials a + * bit */ + if (!(clone_flags & CLONE_THREAD)) { + tgcred = kmalloc(sizeof(*tgcred), GFP_KERNEL); + if (!tgcred) { + ret = -ENOMEM; + goto error_put; + } + atomic_set(&tgcred->usage, 1); + spin_lock_init(&tgcred->lock); + tgcred->process_keyring = NULL; + tgcred->session_keyring = key_get(new->tgcred->session_keyring); + + release_tgcred(new); + new->tgcred = tgcred; + } +#endif + + atomic_inc(&new->user->processes); + p->cred = p->real_cred = get_cred(new); + return 0; + +error_put: + put_cred(new); + return ret; +} + +/** + * commit_creds - Install new credentials upon the current task + * @new: The credentials to be assigned + * + * Install a new set of credentials to the current task, using RCU to replace + * the old set. Both the objective and the subjective credentials pointers are + * updated. This function may not be called if the subjective credentials are + * in an overridden state. + * + * This function eats the caller's reference to the new credentials. + * + * Always returns 0 thus allowing this function to be tail-called at the end + * of, say, sys_setgid(). + */ +int commit_creds(struct cred *new) +{ + struct task_struct *task = current; + const struct cred *old; + + BUG_ON(task->cred != task->real_cred); + BUG_ON(atomic_read(&task->real_cred->usage) < 2); + BUG_ON(atomic_read(&new->usage) < 1); + + old = task->real_cred; + security_commit_creds(new, old); + + get_cred(new); /* we will require a ref for the subj creds too */ + + /* dumpability changes */ + if (old->euid != new->euid || + old->egid != new->egid || + old->fsuid != new->fsuid || + old->fsgid != new->fsgid || + !cap_issubset(new->cap_permitted, old->cap_permitted)) { + set_dumpable(task->mm, suid_dumpable); + task->pdeath_signal = 0; + smp_wmb(); + } + + /* alter the thread keyring */ + if (new->fsuid != old->fsuid) + key_fsuid_changed(task); + if (new->fsgid != old->fsgid) + key_fsgid_changed(task); + + /* do it + * - What if a process setreuid()'s and this brings the + * new uid over his NPROC rlimit? We can check this now + * cheaply with the new uid cache, so if it matters + * we should be checking for it. -DaveM + */ + if (new->user != old->user) + atomic_inc(&new->user->processes); + rcu_assign_pointer(task->real_cred, new); + rcu_assign_pointer(task->cred, new); + if (new->user != old->user) + atomic_dec(&old->user->processes); + + sched_switch_user(task); + + /* send notifications */ + if (new->uid != old->uid || + new->euid != old->euid || + new->suid != old->suid || + new->fsuid != old->fsuid) + proc_id_connector(task, PROC_EVENT_UID); + + if (new->gid != old->gid || + new->egid != old->egid || + new->sgid != old->sgid || + new->fsgid != old->fsgid) + proc_id_connector(task, PROC_EVENT_GID); + + /* release the old obj and subj refs both */ + put_cred(old); + put_cred(old); + return 0; +} +EXPORT_SYMBOL(commit_creds); + +/** + * abort_creds - Discard a set of credentials and unlock the current task + * @new: The credentials that were going to be applied + * + * Discard a set of credentials that were under construction and unlock the + * current task. + */ +void abort_creds(struct cred *new) +{ + BUG_ON(atomic_read(&new->usage) < 1); + put_cred(new); +} +EXPORT_SYMBOL(abort_creds); + +/** + * override_creds - Override the current process's subjective credentials + * @new: The credentials to be assigned + * + * Install a set of temporary override subjective credentials on the current + * process, returning the old set for later reversion. + */ +const struct cred *override_creds(const struct cred *new) +{ + const struct cred *old = current->cred; + + rcu_assign_pointer(current->cred, get_cred(new)); + return old; +} +EXPORT_SYMBOL(override_creds); + +/** + * revert_creds - Revert a temporary subjective credentials override + * @old: The credentials to be restored + * + * Revert a temporary set of override subjective credentials to an old set, + * discarding the override set. + */ +void revert_creds(const struct cred *old) +{ + const struct cred *override = current->cred; + + rcu_assign_pointer(current->cred, old); + put_cred(override); +} +EXPORT_SYMBOL(revert_creds); + +/* + * initialise the credentials stuff + */ +void __init cred_init(void) +{ + /* allocate a slab in which we can store credentials */ + cred_jar = kmem_cache_create("cred_jar", sizeof(struct cred), + 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); +} + +/** + * prepare_kernel_cred - Prepare a set of credentials for a kernel service + * @daemon: A userspace daemon to be used as a reference + * + * Prepare a set of credentials for a kernel service. This can then be used to + * override a task's own credentials so that work can be done on behalf of that + * task that requires a different subjective context. + * + * @daemon is used to provide a base for the security record, but can be NULL. + * If @daemon is supplied, then the security data will be derived from that; + * otherwise they'll be set to 0 and no groups, full capabilities and no keys. + * + * The caller may change these controls afterwards if desired. + * + * Returns the new credentials or NULL if out of memory. + * + * Does not take, and does not return holding current->cred_replace_mutex. + */ +struct cred *prepare_kernel_cred(struct task_struct *daemon) +{ + const struct cred *old; + struct cred *new; + + new = kmem_cache_alloc(cred_jar, GFP_KERNEL); + if (!new) + return NULL; + + if (daemon) + old = get_task_cred(daemon); + else + old = get_cred(&init_cred); + + get_uid(new->user); + get_group_info(new->group_info); + +#ifdef CONFIG_KEYS + atomic_inc(&init_tgcred.usage); + new->tgcred = &init_tgcred; + new->request_key_auth = NULL; + new->thread_keyring = NULL; + new->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; +#endif + +#ifdef CONFIG_SECURITY + new->security = NULL; +#endif + if (security_prepare_creds(new, old, GFP_KERNEL) < 0) + goto error; + + atomic_set(&new->usage, 1); + put_cred(old); + return new; + +error: + put_cred(new); + return NULL; +} +EXPORT_SYMBOL(prepare_kernel_cred); + +/** + * set_security_override - Set the security ID in a set of credentials + * @new: The credentials to alter + * @secid: The LSM security ID to set + * + * Set the LSM security ID in a set of credentials so that the subjective + * security is overridden when an alternative set of credentials is used. + */ +int set_security_override(struct cred *new, u32 secid) +{ + return security_kernel_act_as(new, secid); +} +EXPORT_SYMBOL(set_security_override); + +/** + * set_security_override_from_ctx - Set the security ID in a set of credentials + * @new: The credentials to alter + * @secctx: The LSM security context to generate the security ID from. + * + * Set the LSM security ID in a set of credentials so that the subjective + * security is overridden when an alternative set of credentials is used. The + * security ID is specified in string form as a security context to be + * interpreted by the LSM. + */ +int set_security_override_from_ctx(struct cred *new, const char *secctx) +{ + u32 secid; + int ret; + + ret = security_secctx_to_secid(secctx, strlen(secctx), &secid); + if (ret < 0) + return ret; + + return set_security_override(new, secid); +} +EXPORT_SYMBOL(set_security_override_from_ctx); + +/** + * set_create_files_as - Set the LSM file create context in a set of credentials + * @new: The credentials to alter + * @inode: The inode to take the context from + * + * Change the LSM file creation context in a set of credentials to be the same + * as the object context of the specified inode, so that the new inodes have + * the same MAC context as that inode. + */ +int set_create_files_as(struct cred *new, struct inode *inode) +{ + new->fsuid = inode->i_uid; + new->fsgid = inode->i_gid; + return security_kernel_create_files_as(new, inode); +} +EXPORT_SYMBOL(set_create_files_as); diff --git a/kernel/exit.c b/kernel/exit.c index 2d8be7ebb0f..ccb87162ff6 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -46,12 +46,14 @@ #include #include #include +#include #include #include #include #include #include +#include "cred-internals.h" static void exit_mm(struct task_struct * tsk); @@ -164,7 +166,10 @@ void release_task(struct task_struct * p) int zap_leader; repeat: tracehook_prepare_release_task(p); - atomic_dec(&p->user->processes); + /* don't need to get the RCU readlock here - the process is dead and + * can't be modifying its own credentials */ + atomic_dec(&__task_cred(p)->user->processes); + proc_flush_task(p); write_lock_irq(&tasklist_lock); tracehook_finish_release_task(p); @@ -339,12 +344,12 @@ static void reparent_to_kthreadd(void) /* cpus_allowed? */ /* rt_priority? */ /* signals? */ - security_task_reparent_to_init(current); memcpy(current->signal->rlim, init_task.signal->rlim, sizeof(current->signal->rlim)); - atomic_inc(&(INIT_USER->__count)); + + atomic_inc(&init_cred.usage); + commit_creds(&init_cred); write_unlock_irq(&tasklist_lock); - switch_uid(INIT_USER); } void __set_special_pids(struct pid *pid) @@ -1078,7 +1083,6 @@ NORET_TYPE void do_exit(long code) check_stack_usage(); exit_thread(); cgroup_exit(tsk, 1); - exit_keys(tsk); if (group_dead && tsk->signal->leader) disassociate_ctty(1); @@ -1263,12 +1267,12 @@ static int wait_task_zombie(struct task_struct *p, int options, unsigned long state; int retval, status, traced; pid_t pid = task_pid_vnr(p); + uid_t uid = __task_cred(p)->uid; if (!likely(options & WEXITED)) return 0; if (unlikely(options & WNOWAIT)) { - uid_t uid = p->uid; int exit_code = p->exit_code; int why, status; @@ -1389,7 +1393,7 @@ static int wait_task_zombie(struct task_struct *p, int options, if (!retval && infop) retval = put_user(pid, &infop->si_pid); if (!retval && infop) - retval = put_user(p->uid, &infop->si_uid); + retval = put_user(uid, &infop->si_uid); if (!retval) retval = pid; @@ -1454,7 +1458,8 @@ static int wait_task_stopped(int ptrace, struct task_struct *p, if (!unlikely(options & WNOWAIT)) p->exit_code = 0; - uid = p->uid; + /* don't need the RCU readlock here as we're holding a spinlock */ + uid = __task_cred(p)->uid; unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) @@ -1528,10 +1533,10 @@ static int wait_task_continued(struct task_struct *p, int options, } if (!unlikely(options & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; + uid = __task_cred(p)->uid; spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); - uid = p->uid; get_task_struct(p); read_unlock(&tasklist_lock); diff --git a/kernel/fork.c b/kernel/fork.c index 495da2e9a8b..4e8ca23c0ed 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -147,9 +147,8 @@ void __put_task_struct(struct task_struct *tsk) WARN_ON(atomic_read(&tsk->usage)); WARN_ON(tsk == current); - security_task_free(tsk); - free_uid(tsk->user); - put_group_info(tsk->group_info); + put_cred(tsk->real_cred); + put_cred(tsk->cred); delayacct_tsk_free(tsk); if (!profile_handoff_task(tsk)) @@ -818,12 +817,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) if (!sig) return -ENOMEM; - ret = copy_thread_group_keys(tsk); - if (ret < 0) { - kmem_cache_free(signal_cachep, sig); - return ret; - } - atomic_set(&sig->count, 1); atomic_set(&sig->live, 1); init_waitqueue_head(&sig->wait_chldexit); @@ -868,7 +861,6 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk) void __cleanup_signal(struct signal_struct *sig) { thread_group_cputime_free(sig); - exit_thread_group_keys(sig); tty_kref_put(sig->tty); kmem_cache_free(signal_cachep, sig); } @@ -984,16 +976,16 @@ static struct task_struct *copy_process(unsigned long clone_flags, DEBUG_LOCKS_WARN_ON(!p->softirqs_enabled); #endif retval = -EAGAIN; - if (atomic_read(&p->user->processes) >= + if (atomic_read(&p->real_cred->user->processes) >= p->signal->rlim[RLIMIT_NPROC].rlim_cur) { if (!capable(CAP_SYS_ADMIN) && !capable(CAP_SYS_RESOURCE) && - p->user != current->nsproxy->user_ns->root_user) + p->real_cred->user != INIT_USER) goto bad_fork_free; } - atomic_inc(&p->user->__count); - atomic_inc(&p->user->processes); - get_group_info(p->group_info); + retval = copy_creds(p, clone_flags); + if (retval < 0) + goto bad_fork_free; /* * If multiple threads are within copy_process(), then this check @@ -1048,10 +1040,6 @@ static struct task_struct *copy_process(unsigned long clone_flags, do_posix_clock_monotonic_gettime(&p->start_time); p->real_start_time = p->start_time; monotonic_to_bootbased(&p->real_start_time); -#ifdef CONFIG_SECURITY - p->security = NULL; -#endif - p->cap_bset = current->cap_bset; p->io_context = NULL; p->audit_context = NULL; cgroup_fork(p); @@ -1096,10 +1084,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, /* Perform scheduler related setup. Assign this task to a CPU. */ sched_fork(p, clone_flags); - if ((retval = security_task_alloc(p))) - goto bad_fork_cleanup_policy; if ((retval = audit_alloc(p))) - goto bad_fork_cleanup_security; + goto bad_fork_cleanup_policy; /* copy all the process information */ if ((retval = copy_semundo(clone_flags, p))) goto bad_fork_cleanup_audit; @@ -1113,10 +1099,8 @@ static struct task_struct *copy_process(unsigned long clone_flags, goto bad_fork_cleanup_sighand; if ((retval = copy_mm(clone_flags, p))) goto bad_fork_cleanup_signal; - if ((retval = copy_keys(clone_flags, p))) - goto bad_fork_cleanup_mm; if ((retval = copy_namespaces(clone_flags, p))) - goto bad_fork_cleanup_keys; + goto bad_fork_cleanup_mm; if ((retval = copy_io(clone_flags, p))) goto bad_fork_cleanup_namespaces; retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs); @@ -1281,8 +1265,6 @@ bad_fork_cleanup_io: put_io_context(p->io_context); bad_fork_cleanup_namespaces: exit_task_namespaces(p); -bad_fork_cleanup_keys: - exit_keys(p); bad_fork_cleanup_mm: if (p->mm) mmput(p->mm); @@ -1298,8 +1280,6 @@ bad_fork_cleanup_semundo: exit_sem(p); bad_fork_cleanup_audit: audit_free(p); -bad_fork_cleanup_security: - security_task_free(p); bad_fork_cleanup_policy: #ifdef CONFIG_NUMA mpol_put(p->mempolicy); @@ -1312,9 +1292,9 @@ bad_fork_cleanup_cgroup: bad_fork_cleanup_put_domain: module_put(task_thread_info(p)->exec_domain->module); bad_fork_cleanup_count: - put_group_info(p->group_info); - atomic_dec(&p->user->processes); - free_uid(p->user); + atomic_dec(&p->cred->user->processes); + put_cred(p->real_cred); + put_cred(p->cred); bad_fork_free: free_task(p); fork_out: @@ -1357,6 +1337,21 @@ long do_fork(unsigned long clone_flags, int trace = 0; long nr; + /* + * Do some preliminary argument and permissions checking before we + * actually start allocating stuff + */ + if (clone_flags & CLONE_NEWUSER) { + if (clone_flags & CLONE_THREAD) + return -EINVAL; + /* hopefully this check will go away when userns support is + * complete + */ + if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SETUID) || + !capable(CAP_SETGID)) + return -EPERM; + } + /* * We hope to recycle these flags after 2.6.26 */ @@ -1605,8 +1600,7 @@ asmlinkage long sys_unshare(unsigned long unshare_flags) err = -EINVAL; if (unshare_flags & ~(CLONE_THREAD|CLONE_FS|CLONE_NEWNS|CLONE_SIGHAND| CLONE_VM|CLONE_FILES|CLONE_SYSVSEM| - CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWUSER| - CLONE_NEWNET)) + CLONE_NEWUTS|CLONE_NEWIPC|CLONE_NEWNET)) goto bad_unshare_out; /* diff --git a/kernel/futex.c b/kernel/futex.c index 8af10027514..4fe790e89d0 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -439,13 +439,20 @@ static void free_pi_state(struct futex_pi_state *pi_state) static struct task_struct * futex_find_get_task(pid_t pid) { struct task_struct *p; + const struct cred *cred = current_cred(), *pcred; rcu_read_lock(); p = find_task_by_vpid(pid); - if (!p || ((current->euid != p->euid) && (current->euid != p->uid))) + if (!p) { p = ERR_PTR(-ESRCH); - else - get_task_struct(p); + } else { + pcred = __task_cred(p); + if (cred->euid != pcred->euid && + cred->euid != pcred->uid) + p = ERR_PTR(-ESRCH); + else + get_task_struct(p); + } rcu_read_unlock(); @@ -1829,6 +1836,7 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, { struct robust_list_head __user *head; unsigned long ret; + const struct cred *cred = current_cred(), *pcred; if (!futex_cmpxchg_enabled) return -ENOSYS; @@ -1844,8 +1852,10 @@ sys_get_robust_list(int pid, struct robust_list_head __user * __user *head_ptr, if (!p) goto err_unlock; ret = -EPERM; - if ((current->euid != p->euid) && (current->euid != p->uid) && - !capable(CAP_SYS_PTRACE)) + pcred = __task_cred(p); + if (cred->euid != pcred->euid && + cred->euid != pcred->uid && + !capable(CAP_SYS_PTRACE)) goto err_unlock; head = p->robust_list; rcu_read_unlock(); diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c index 04ac3a9e42c..d607a5b9ee2 100644 --- a/kernel/futex_compat.c +++ b/kernel/futex_compat.c @@ -135,6 +135,7 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, { struct compat_robust_list_head __user *head; unsigned long ret; + const struct cred *cred = current_cred(), *pcred; if (!futex_cmpxchg_enabled) return -ENOSYS; @@ -150,8 +151,10 @@ compat_sys_get_robust_list(int pid, compat_uptr_t __user *head_ptr, if (!p) goto err_unlock; ret = -EPERM; - if ((current->euid != p->euid) && (current->euid != p->uid) && - !capable(CAP_SYS_PTRACE)) + pcred = __task_cred(p); + if (cred->euid != pcred->euid && + cred->euid != pcred->uid && + !capable(CAP_SYS_PTRACE)) goto err_unlock; head = p->compat_robust_list; read_unlock(&tasklist_lock); diff --git a/kernel/kmod.c b/kernel/kmod.c index 3d3c3ea3a02..b46dbb90866 100644 --- a/kernel/kmod.c +++ b/kernel/kmod.c @@ -118,10 +118,10 @@ EXPORT_SYMBOL(request_module); struct subprocess_info { struct work_struct work; struct completion *complete; + struct cred *cred; char *path; char **argv; char **envp; - struct key *ring; enum umh_wait wait; int retval; struct file *stdin; @@ -134,19 +134,20 @@ struct subprocess_info { static int ____call_usermodehelper(void *data) { struct subprocess_info *sub_info = data; - struct key *new_session, *old_session; int retval; - /* Unblock all signals and set the session keyring. */ - new_session = key_get(sub_info->ring); + BUG_ON(atomic_read(&sub_info->cred->usage) != 1); + + /* Unblock all signals */ spin_lock_irq(¤t->sighand->siglock); - old_session = __install_session_keyring(current, new_session); flush_signal_handlers(current, 1); sigemptyset(¤t->blocked); recalc_sigpending(); spin_unlock_irq(¤t->sighand->siglock); - key_put(old_session); + /* Install the credentials */ + commit_creds(sub_info->cred); + sub_info->cred = NULL; /* Install input pipe when needed */ if (sub_info->stdin) { @@ -185,6 +186,8 @@ void call_usermodehelper_freeinfo(struct subprocess_info *info) { if (info->cleanup) (*info->cleanup)(info->argv, info->envp); + if (info->cred) + put_cred(info->cred); kfree(info); } EXPORT_SYMBOL(call_usermodehelper_freeinfo); @@ -240,6 +243,8 @@ static void __call_usermodehelper(struct work_struct *work) pid_t pid; enum umh_wait wait = sub_info->wait; + BUG_ON(atomic_read(&sub_info->cred->usage) != 1); + /* CLONE_VFORK: wait until the usermode helper has execve'd * successfully We need the data structures to stay around * until that is done. */ @@ -362,6 +367,9 @@ struct subprocess_info *call_usermodehelper_setup(char *path, char **argv, sub_info->path = path; sub_info->argv = argv; sub_info->envp = envp; + sub_info->cred = prepare_usermodehelper_creds(); + if (!sub_info->cred) + return NULL; out: return sub_info; @@ -376,7 +384,13 @@ EXPORT_SYMBOL(call_usermodehelper_setup); void call_usermodehelper_setkeys(struct subprocess_info *info, struct key *session_keyring) { - info->ring = session_keyring; +#ifdef CONFIG_KEYS + struct thread_group_cred *tgcred = info->cred->tgcred; + key_put(tgcred->session_keyring); + tgcred->session_keyring = key_get(session_keyring); +#else + BUG(); +#endif } EXPORT_SYMBOL(call_usermodehelper_setkeys); @@ -444,6 +458,8 @@ int call_usermodehelper_exec(struct subprocess_info *sub_info, DECLARE_COMPLETION_ONSTACK(done); int retval = 0; + BUG_ON(atomic_read(&sub_info->cred->usage) != 1); + helper_lock(); if (sub_info->path[0] == '\0') goto out; diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c index 1d3ef29a258..63598dca2d0 100644 --- a/kernel/nsproxy.c +++ b/kernel/nsproxy.c @@ -80,12 +80,6 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, goto out_pid; } - new_nsp->user_ns = copy_user_ns(flags, tsk->nsproxy->user_ns); - if (IS_ERR(new_nsp->user_ns)) { - err = PTR_ERR(new_nsp->user_ns); - goto out_user; - } - new_nsp->net_ns = copy_net_ns(flags, tsk->nsproxy->net_ns); if (IS_ERR(new_nsp->net_ns)) { err = PTR_ERR(new_nsp->net_ns); @@ -95,9 +89,6 @@ static struct nsproxy *create_new_namespaces(unsigned long flags, return new_nsp; out_net: - if (new_nsp->user_ns) - put_user_ns(new_nsp->user_ns); -out_user: if (new_nsp->pid_ns) put_pid_ns(new_nsp->pid_ns); out_pid: @@ -130,7 +121,7 @@ int copy_namespaces(unsigned long flags, struct task_struct *tsk) get_nsproxy(old_ns); if (!(flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | - CLONE_NEWUSER | CLONE_NEWPID | CLONE_NEWNET))) + CLONE_NEWPID | CLONE_NEWNET))) return 0; if (!capable(CAP_SYS_ADMIN)) { @@ -173,8 +164,6 @@ void free_nsproxy(struct nsproxy *ns) put_ipc_ns(ns->ipc_ns); if (ns->pid_ns) put_pid_ns(ns->pid_ns); - if (ns->user_ns) - put_user_ns(ns->user_ns); put_net(ns->net_ns); kmem_cache_free(nsproxy_cachep, ns); } @@ -189,7 +178,7 @@ int unshare_nsproxy_namespaces(unsigned long unshare_flags, int err = 0; if (!(unshare_flags & (CLONE_NEWNS | CLONE_NEWUTS | CLONE_NEWIPC | - CLONE_NEWUSER | CLONE_NEWNET))) + CLONE_NEWNET))) return 0; if (!capable(CAP_SYS_ADMIN)) diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 4c8bcd7dd8e..ca2df68faf7 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -115,6 +115,8 @@ int ptrace_check_attach(struct task_struct *child, int kill) int __ptrace_may_access(struct task_struct *task, unsigned int mode) { + const struct cred *cred = current_cred(), *tcred; + /* May we inspect the given task? * This check is used both for attaching with ptrace * and for allowing access to sensitive information in /proc. @@ -127,13 +129,19 @@ int __ptrace_may_access(struct task_struct *task, unsigned int mode) /* Don't let security modules deny introspection */ if (task == current) return 0; - if (((current->uid != task->euid) || - (current->uid != task->suid) || - (current->uid != task->uid) || - (current->gid != task->egid) || - (current->gid != task->sgid) || - (current->gid != task->gid)) && !capable(CAP_SYS_PTRACE)) + rcu_read_lock(); + tcred = __task_cred(task); + if ((cred->uid != tcred->euid || + cred->uid != tcred->suid || + cred->uid != tcred->uid || + cred->gid != tcred->egid || + cred->gid != tcred->sgid || + cred->gid != tcred->gid) && + !capable(CAP_SYS_PTRACE)) { + rcu_read_unlock(); return -EPERM; + } + rcu_read_unlock(); smp_rmb(); if (task->mm) dumpable = get_dumpable(task->mm); @@ -163,6 +171,14 @@ int ptrace_attach(struct task_struct *task) if (same_thread_group(task, current)) goto out; + /* Protect exec's credential calculations against our interference; + * SUID, SGID and LSM creds get determined differently under ptrace. + */ + retval = mutex_lock_interruptible(¤t->cred_exec_mutex); + if (retval < 0) + goto out; + + retval = -EPERM; repeat: /* * Nasty, nasty. @@ -202,6 +218,7 @@ repeat: bad: write_unlock_irqrestore(&tasklist_lock, flags); task_unlock(task); + mutex_unlock(¤t->cred_exec_mutex); out: return retval; } diff --git a/kernel/sched.c b/kernel/sched.c index e4bb1dd7b30..33cf4a1cbcd 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -345,7 +345,9 @@ static inline struct task_group *task_group(struct task_struct *p) struct task_group *tg; #ifdef CONFIG_USER_SCHED - tg = p->user->tg; + rcu_read_lock(); + tg = __task_cred(p)->user->tg; + rcu_read_unlock(); #elif defined(CONFIG_CGROUP_SCHED) tg = container_of(task_subsys_state(p, cpu_cgroup_subsys_id), struct task_group, css); @@ -5134,6 +5136,22 @@ __setscheduler(struct rq *rq, struct task_struct *p, int policy, int prio) set_load_weight(p); } +/* + * check the target process has a UID that matches the current process's + */ +static bool check_same_owner(struct task_struct *p) +{ + const struct cred *cred = current_cred(), *pcred; + bool match; + + rcu_read_lock(); + pcred = __task_cred(p); + match = (cred->euid == pcred->euid || + cred->euid == pcred->uid); + rcu_read_unlock(); + return match; +} + static int __sched_setscheduler(struct task_struct *p, int policy, struct sched_param *param, bool user) { @@ -5193,8 +5211,7 @@ recheck: return -EPERM; /* can't change other user's priorities */ - if ((current->euid != p->euid) && - (current->euid != p->uid)) + if (!check_same_owner(p)) return -EPERM; } @@ -5426,8 +5443,7 @@ long sched_setaffinity(pid_t pid, const cpumask_t *in_mask) read_unlock(&tasklist_lock); retval = -EPERM; - if ((current->euid != p->euid) && (current->euid != p->uid) && - !capable(CAP_SYS_NICE)) + if (!check_same_owner(p) && !capable(CAP_SYS_NICE)) goto out_unlock; retval = security_task_setscheduler(p, 0, NULL); diff --git a/kernel/signal.c b/kernel/signal.c index 4530fc65445..2a64304ed54 100644 --- a/kernel/signal.c +++ b/kernel/signal.c @@ -177,6 +177,11 @@ int next_signal(struct sigpending *pending, sigset_t *mask) return sig; } +/* + * allocate a new signal queue record + * - this may be called without locks if and only if t == current, otherwise an + * appopriate lock must be held to stop the target task from exiting + */ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags, int override_rlimit) { @@ -184,11 +189,12 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags, struct user_struct *user; /* - * In order to avoid problems with "switch_user()", we want to make - * sure that the compiler doesn't re-load "t->user" + * We won't get problems with the target's UID changing under us + * because changing it requires RCU be used, and if t != current, the + * caller must be holding the RCU readlock (by way of a spinlock) and + * we use RCU protection here */ - user = t->user; - barrier(); + user = get_uid(__task_cred(t)->user); atomic_inc(&user->sigpending); if (override_rlimit || atomic_read(&user->sigpending) <= @@ -196,12 +202,14 @@ static struct sigqueue *__sigqueue_alloc(struct task_struct *t, gfp_t flags, q = kmem_cache_alloc(sigqueue_cachep, flags); if (unlikely(q == NULL)) { atomic_dec(&user->sigpending); + free_uid(user); } else { INIT_LIST_HEAD(&q->list); q->flags = 0; - q->user = get_uid(user); + q->user = user; } - return(q); + + return q; } static void __sigqueue_free(struct sigqueue *q) @@ -562,10 +570,12 @@ static int rm_from_queue(unsigned long mask, struct sigpending *s) /* * Bad permissions for sending the signal + * - the caller must hold at least the RCU read lock */ static int check_kill_permission(int sig, struct siginfo *info, struct task_struct *t) { + const struct cred *cred = current_cred(), *tcred; struct pid *sid; int error; @@ -579,8 +589,11 @@ static int check_kill_permission(int sig, struct siginfo *info, if (error) return error; - if ((current->euid ^ t->suid) && (current->euid ^ t->uid) && - (current->uid ^ t->suid) && (current->uid ^ t->uid) && + tcred = __task_cred(t); + if ((cred->euid ^ tcred->suid) && + (cred->euid ^ tcred->uid) && + (cred->uid ^ tcred->suid) && + (cred->uid ^ tcred->uid) && !capable(CAP_KILL)) { switch (sig) { case SIGCONT: @@ -844,7 +857,7 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t, q->info.si_errno = 0; q->info.si_code = SI_USER; q->info.si_pid = task_pid_vnr(current); - q->info.si_uid = current->uid; + q->info.si_uid = current_uid(); break; case (unsigned long) SEND_SIG_PRIV: q->info.si_signo = sig; @@ -1008,6 +1021,10 @@ struct sighand_struct *lock_task_sighand(struct task_struct *tsk, unsigned long return sighand; } +/* + * send signal info to all the members of a group + * - the caller must hold the RCU read lock at least + */ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) { unsigned long flags; @@ -1029,8 +1046,8 @@ int group_send_sig_info(int sig, struct siginfo *info, struct task_struct *p) /* * __kill_pgrp_info() sends a signal to a process group: this is what the tty * control characters do (^C, ^Z etc) + * - the caller must hold at least a readlock on tasklist_lock */ - int __kill_pgrp_info(int sig, struct siginfo *info, struct pid *pgrp) { struct task_struct *p = NULL; @@ -1086,6 +1103,7 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid, { int ret = -EINVAL; struct task_struct *p; + const struct cred *pcred; if (!valid_signal(sig)) return ret; @@ -1096,9 +1114,11 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid, ret = -ESRCH; goto out_unlock; } - if ((info == SEND_SIG_NOINFO || (!is_si_special(info) && SI_FROMUSER(info))) - && (euid != p->suid) && (euid != p->uid) - && (uid != p->suid) && (uid != p->uid)) { + pcred = __task_cred(p); + if ((info == SEND_SIG_NOINFO || + (!is_si_special(info) && SI_FROMUSER(info))) && + euid != pcred->suid && euid != pcred->uid && + uid != pcred->suid && uid != pcred->uid) { ret = -EPERM; goto out_unlock; } @@ -1369,10 +1389,9 @@ int do_notify_parent(struct task_struct *tsk, int sig) */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns); + info.si_uid = __task_cred(tsk)->uid; rcu_read_unlock(); - info.si_uid = tsk->uid; - thread_group_cputime(tsk, &cputime); info.si_utime = cputime_to_jiffies(cputime.utime); info.si_stime = cputime_to_jiffies(cputime.stime); @@ -1440,10 +1459,9 @@ static void do_notify_parent_cldstop(struct task_struct *tsk, int why) */ rcu_read_lock(); info.si_pid = task_pid_nr_ns(tsk, tsk->parent->nsproxy->pid_ns); + info.si_uid = __task_cred(tsk)->uid; rcu_read_unlock(); - info.si_uid = tsk->uid; - info.si_utime = cputime_to_clock_t(tsk->utime); info.si_stime = cputime_to_clock_t(tsk->stime); @@ -1598,7 +1616,7 @@ void ptrace_notify(int exit_code) info.si_signo = SIGTRAP; info.si_code = exit_code; info.si_pid = task_pid_vnr(current); - info.si_uid = current->uid; + info.si_uid = current_uid(); /* Let the debugger run. */ spin_lock_irq(¤t->sighand->siglock); @@ -1710,7 +1728,7 @@ static int ptrace_signal(int signr, siginfo_t *info, info->si_errno = 0; info->si_code = SI_USER; info->si_pid = task_pid_vnr(current->parent); - info->si_uid = current->parent->uid; + info->si_uid = task_uid(current->parent); } /* If the (new) signal is now blocked, requeue it. */ @@ -2211,7 +2229,7 @@ sys_kill(pid_t pid, int sig) info.si_errno = 0; info.si_code = SI_USER; info.si_pid = task_tgid_vnr(current); - info.si_uid = current->uid; + info.si_uid = current_uid(); return kill_something_info(sig, &info, pid); } @@ -2228,7 +2246,7 @@ static int do_tkill(pid_t tgid, pid_t pid, int sig) info.si_errno = 0; info.si_code = SI_TKILL; info.si_pid = task_tgid_vnr(current); - info.si_uid = current->uid; + info.si_uid = current_uid(); rcu_read_lock(); p = find_task_by_vpid(pid); diff --git a/kernel/sys.c b/kernel/sys.c index 31deba8f7d1..ebe65c2c987 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -112,12 +112,17 @@ EXPORT_SYMBOL(cad_pid); void (*pm_power_off_prepare)(void); +/* + * set the priority of a task + * - the caller must hold the RCU read lock + */ static int set_one_prio(struct task_struct *p, int niceval, int error) { + const struct cred *cred = current_cred(), *pcred = __task_cred(p); int no_nice; - if (p->uid != current->euid && - p->euid != current->euid && !capable(CAP_SYS_NICE)) { + if (pcred->uid != cred->euid && + pcred->euid != cred->euid && !capable(CAP_SYS_NICE)) { error = -EPERM; goto out; } @@ -141,6 +146,7 @@ asmlinkage long sys_setpriority(int which, int who, int niceval) { struct task_struct *g, *p; struct user_struct *user; + const struct cred *cred = current_cred(); int error = -EINVAL; struct pid *pgrp; @@ -174,18 +180,18 @@ asmlinkage long sys_setpriority(int which, int who, int niceval) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: - user = current->user; + user = (struct user_struct *) cred->user; if (!who) - who = current->uid; - else - if ((who != current->uid) && !(user = find_user(who))) - goto out_unlock; /* No processes for this user */ + who = cred->uid; + else if ((who != cred->uid) && + !(user = find_user(who))) + goto out_unlock; /* No processes for this user */ do_each_thread(g, p) - if (p->uid == who) + if (__task_cred(p)->uid == who) error = set_one_prio(p, niceval, error); while_each_thread(g, p); - if (who != current->uid) + if (who != cred->uid) free_uid(user); /* For find_user() */ break; } @@ -205,6 +211,7 @@ asmlinkage long sys_getpriority(int which, int who) { struct task_struct *g, *p; struct user_struct *user; + const struct cred *cred = current_cred(); long niceval, retval = -ESRCH; struct pid *pgrp; @@ -236,21 +243,21 @@ asmlinkage long sys_getpriority(int which, int who) } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case PRIO_USER: - user = current->user; + user = (struct user_struct *) cred->user; if (!who) - who = current->uid; - else - if ((who != current->uid) && !(user = find_user(who))) - goto out_unlock; /* No processes for this user */ + who = cred->uid; + else if ((who != cred->uid) && + !(user = find_user(who))) + goto out_unlock; /* No processes for this user */ do_each_thread(g, p) - if (p->uid == who) { + if (__task_cred(p)->uid == who) { niceval = 20 - task_nice(p); if (niceval > retval) retval = niceval; } while_each_thread(g, p); - if (who != current->uid) + if (who != cred->uid) free_uid(user); /* for find_user() */ break; } @@ -472,46 +479,48 @@ void ctrl_alt_del(void) */ asmlinkage long sys_setregid(gid_t rgid, gid_t egid) { - int old_rgid = current->gid; - int old_egid = current->egid; - int new_rgid = old_rgid; - int new_egid = old_egid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setgid(rgid, egid, (gid_t)-1, LSM_SETID_RE); if (retval) - return retval; + goto error; + retval = -EPERM; if (rgid != (gid_t) -1) { - if ((old_rgid == rgid) || - (current->egid==rgid) || + if (old->gid == rgid || + old->egid == rgid || capable(CAP_SETGID)) - new_rgid = rgid; + new->gid = rgid; else - return -EPERM; + goto error; } if (egid != (gid_t) -1) { - if ((old_rgid == egid) || - (current->egid == egid) || - (current->sgid == egid) || + if (old->gid == egid || + old->egid == egid || + old->sgid == egid || capable(CAP_SETGID)) - new_egid = egid; + new->egid = egid; else - return -EPERM; - } - if (new_egid != old_egid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); + goto error; } + if (rgid != (gid_t) -1 || - (egid != (gid_t) -1 && egid != old_rgid)) - current->sgid = new_egid; - current->fsgid = new_egid; - current->egid = new_egid; - current->gid = new_rgid; - key_fsgid_changed(current); - proc_id_connector(current, PROC_EVENT_GID); - return 0; + (egid != (gid_t) -1 && egid != old->gid)) + new->sgid = new->egid; + new->fsgid = new->egid; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; } /* @@ -521,56 +530,54 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid) */ asmlinkage long sys_setgid(gid_t gid) { - int old_egid = current->egid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_ID); if (retval) - return retval; + goto error; - if (capable(CAP_SETGID)) { - if (old_egid != gid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->gid = current->egid = current->sgid = current->fsgid = gid; - } else if ((gid == current->gid) || (gid == current->sgid)) { - if (old_egid != gid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->egid = current->fsgid = gid; - } + retval = -EPERM; + if (capable(CAP_SETGID)) + new->gid = new->egid = new->sgid = new->fsgid = gid; + else if (gid == old->gid || gid == old->sgid) + new->egid = new->fsgid = gid; else - return -EPERM; + goto error; - key_fsgid_changed(current); - proc_id_connector(current, PROC_EVENT_GID); - return 0; + return commit_creds(new); + +error: + abort_creds(new); + return retval; } -static int set_user(uid_t new_ruid, int dumpclear) +/* + * change the user struct in a credentials set to match the new UID + */ +static int set_user(struct cred *new) { struct user_struct *new_user; - new_user = alloc_uid(current->nsproxy->user_ns, new_ruid); + new_user = alloc_uid(current_user_ns(), new->uid); if (!new_user) return -EAGAIN; if (atomic_read(&new_user->processes) >= current->signal->rlim[RLIMIT_NPROC].rlim_cur && - new_user != current->nsproxy->user_ns->root_user) { + new_user != INIT_USER) { free_uid(new_user); return -EAGAIN; } - switch_uid(new_user); - - if (dumpclear) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->uid = new_ruid; + free_uid(new->user); + new->user = new_user; return 0; } @@ -591,54 +598,56 @@ static int set_user(uid_t new_ruid, int dumpclear) */ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid) { - int old_ruid, old_euid, old_suid, new_ruid, new_euid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setuid(ruid, euid, (uid_t)-1, LSM_SETID_RE); if (retval) - return retval; - - new_ruid = old_ruid = current->uid; - new_euid = old_euid = current->euid; - old_suid = current->suid; + goto error; + retval = -EPERM; if (ruid != (uid_t) -1) { - new_ruid = ruid; - if ((old_ruid != ruid) && - (current->euid != ruid) && + new->uid = ruid; + if (old->uid != ruid && + old->euid != ruid && !capable(CAP_SETUID)) - return -EPERM; + goto error; } if (euid != (uid_t) -1) { - new_euid = euid; - if ((old_ruid != euid) && - (current->euid != euid) && - (current->suid != euid) && + new->euid = euid; + if (old->uid != euid && + old->euid != euid && + old->suid != euid && !capable(CAP_SETUID)) - return -EPERM; + goto error; } - if (new_ruid != old_ruid && set_user(new_ruid, new_euid != old_euid) < 0) - return -EAGAIN; + retval = -EAGAIN; + if (new->uid != old->uid && set_user(new) < 0) + goto error; - if (new_euid != old_euid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->fsuid = current->euid = new_euid; if (ruid != (uid_t) -1 || - (euid != (uid_t) -1 && euid != old_ruid)) - current->suid = current->euid; - current->fsuid = current->euid; + (euid != (uid_t) -1 && euid != old->uid)) + new->suid = new->euid; + new->fsuid = new->euid; - key_fsuid_changed(current); - proc_id_connector(current, PROC_EVENT_UID); + retval = security_task_fix_setuid(new, old, LSM_SETID_RE); + if (retval < 0) + goto error; - return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RE); + return commit_creds(new); + +error: + abort_creds(new); + return retval; } - - /* * setuid() is implemented like SysV with SAVED_IDS @@ -653,36 +662,41 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid) */ asmlinkage long sys_setuid(uid_t uid) { - int old_euid = current->euid; - int old_ruid, old_suid, new_suid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_ID); if (retval) - return retval; + goto error; - old_ruid = current->uid; - old_suid = current->suid; - new_suid = old_suid; - + retval = -EPERM; if (capable(CAP_SETUID)) { - if (uid != old_ruid && set_user(uid, old_euid != uid) < 0) - return -EAGAIN; - new_suid = uid; - } else if ((uid != current->uid) && (uid != new_suid)) - return -EPERM; - - if (old_euid != uid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); + new->suid = new->uid = uid; + if (uid != old->uid && set_user(new) < 0) { + retval = -EAGAIN; + goto error; + } + } else if (uid != old->uid && uid != new->suid) { + goto error; } - current->fsuid = current->euid = uid; - current->suid = new_suid; - key_fsuid_changed(current); - proc_id_connector(current, PROC_EVENT_UID); + new->fsuid = new->euid = uid; - return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_ID); + retval = security_task_fix_setuid(new, old, LSM_SETID_ID); + if (retval < 0) + goto error; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; } @@ -692,54 +706,63 @@ asmlinkage long sys_setuid(uid_t uid) */ asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid) { - int old_ruid = current->uid; - int old_euid = current->euid; - int old_suid = current->suid; + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + retval = security_task_setuid(ruid, euid, suid, LSM_SETID_RES); if (retval) - return retval; + goto error; + old = current_cred(); + retval = -EPERM; if (!capable(CAP_SETUID)) { - if ((ruid != (uid_t) -1) && (ruid != current->uid) && - (ruid != current->euid) && (ruid != current->suid)) - return -EPERM; - if ((euid != (uid_t) -1) && (euid != current->uid) && - (euid != current->euid) && (euid != current->suid)) - return -EPERM; - if ((suid != (uid_t) -1) && (suid != current->uid) && - (suid != current->euid) && (suid != current->suid)) - return -EPERM; + if (ruid != (uid_t) -1 && ruid != old->uid && + ruid != old->euid && ruid != old->suid) + goto error; + if (euid != (uid_t) -1 && euid != old->uid && + euid != old->euid && euid != old->suid) + goto error; + if (suid != (uid_t) -1 && suid != old->uid && + suid != old->euid && suid != old->suid) + goto error; } + + retval = -EAGAIN; if (ruid != (uid_t) -1) { - if (ruid != current->uid && set_user(ruid, euid != current->euid) < 0) - return -EAGAIN; + new->uid = ruid; + if (ruid != old->uid && set_user(new) < 0) + goto error; } - if (euid != (uid_t) -1) { - if (euid != current->euid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->euid = euid; - } - current->fsuid = current->euid; + if (euid != (uid_t) -1) + new->euid = euid; if (suid != (uid_t) -1) - current->suid = suid; + new->suid = suid; + new->fsuid = new->euid; - key_fsuid_changed(current); - proc_id_connector(current, PROC_EVENT_UID); + retval = security_task_fix_setuid(new, old, LSM_SETID_RES); + if (retval < 0) + goto error; - return security_task_post_setuid(old_ruid, old_euid, old_suid, LSM_SETID_RES); + return commit_creds(new); + +error: + abort_creds(new); + return retval; } asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __user *suid) { + const struct cred *cred = current_cred(); int retval; - if (!(retval = put_user(current->uid, ruid)) && - !(retval = put_user(current->euid, euid))) - retval = put_user(current->suid, suid); + if (!(retval = put_user(cred->uid, ruid)) && + !(retval = put_user(cred->euid, euid))) + retval = put_user(cred->suid, suid); return retval; } @@ -749,48 +772,55 @@ asmlinkage long sys_getresuid(uid_t __user *ruid, uid_t __user *euid, uid_t __us */ asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid) { + const struct cred *old; + struct cred *new; int retval; + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); + retval = security_task_setgid(rgid, egid, sgid, LSM_SETID_RES); if (retval) - return retval; + goto error; + retval = -EPERM; if (!capable(CAP_SETGID)) { - if ((rgid != (gid_t) -1) && (rgid != current->gid) && - (rgid != current->egid) && (rgid != current->sgid)) - return -EPERM; - if ((egid != (gid_t) -1) && (egid != current->gid) && - (egid != current->egid) && (egid != current->sgid)) - return -EPERM; - if ((sgid != (gid_t) -1) && (sgid != current->gid) && - (sgid != current->egid) && (sgid != current->sgid)) - return -EPERM; + if (rgid != (gid_t) -1 && rgid != old->gid && + rgid != old->egid && rgid != old->sgid) + goto error; + if (egid != (gid_t) -1 && egid != old->gid && + egid != old->egid && egid != old->sgid) + goto error; + if (sgid != (gid_t) -1 && sgid != old->gid && + sgid != old->egid && sgid != old->sgid) + goto error; } - if (egid != (gid_t) -1) { - if (egid != current->egid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); - } - current->egid = egid; - } - current->fsgid = current->egid; - if (rgid != (gid_t) -1) - current->gid = rgid; - if (sgid != (gid_t) -1) - current->sgid = sgid; - key_fsgid_changed(current); - proc_id_connector(current, PROC_EVENT_GID); - return 0; + if (rgid != (gid_t) -1) + new->gid = rgid; + if (egid != (gid_t) -1) + new->egid = egid; + if (sgid != (gid_t) -1) + new->sgid = sgid; + new->fsgid = new->egid; + + return commit_creds(new); + +error: + abort_creds(new); + return retval; } asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __user *sgid) { + const struct cred *cred = current_cred(); int retval; - if (!(retval = put_user(current->gid, rgid)) && - !(retval = put_user(current->egid, egid))) - retval = put_user(current->sgid, sgid); + if (!(retval = put_user(cred->gid, rgid)) && + !(retval = put_user(cred->egid, egid))) + retval = put_user(cred->sgid, sgid); return retval; } @@ -804,27 +834,35 @@ asmlinkage long sys_getresgid(gid_t __user *rgid, gid_t __user *egid, gid_t __us */ asmlinkage long sys_setfsuid(uid_t uid) { - int old_fsuid; + const struct cred *old; + struct cred *new; + uid_t old_fsuid; - old_fsuid = current->fsuid; - if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS)) - return old_fsuid; + new = prepare_creds(); + if (!new) + return current_fsuid(); + old = current_cred(); + old_fsuid = old->fsuid; - if (uid == current->uid || uid == current->euid || - uid == current->suid || uid == current->fsuid || + if (security_task_setuid(uid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS) < 0) + goto error; + + if (uid == old->uid || uid == old->euid || + uid == old->suid || uid == old->fsuid || capable(CAP_SETUID)) { if (uid != old_fsuid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); + new->fsuid = uid; + if (security_task_fix_setuid(new, old, LSM_SETID_FS) == 0) + goto change_okay; } - current->fsuid = uid; } - key_fsuid_changed(current); - proc_id_connector(current, PROC_EVENT_UID); - - security_task_post_setuid(old_fsuid, (uid_t)-1, (uid_t)-1, LSM_SETID_FS); +error: + abort_creds(new); + return old_fsuid; +change_okay: + commit_creds(new); return old_fsuid; } @@ -833,23 +871,34 @@ asmlinkage long sys_setfsuid(uid_t uid) */ asmlinkage long sys_setfsgid(gid_t gid) { - int old_fsgid; + const struct cred *old; + struct cred *new; + gid_t old_fsgid; + + new = prepare_creds(); + if (!new) + return current_fsgid(); + old = current_cred(); + old_fsgid = old->fsgid; - old_fsgid = current->fsgid; if (security_task_setgid(gid, (gid_t)-1, (gid_t)-1, LSM_SETID_FS)) - return old_fsgid; + goto error; - if (gid == current->gid || gid == current->egid || - gid == current->sgid || gid == current->fsgid || + if (gid == old->gid || gid == old->egid || + gid == old->sgid || gid == old->fsgid || capable(CAP_SETGID)) { if (gid != old_fsgid) { - set_dumpable(current->mm, suid_dumpable); - smp_wmb(); + new->fsgid = gid; + goto change_okay; } - current->fsgid = gid; - key_fsgid_changed(current); - proc_id_connector(current, PROC_EVENT_GID); } + +error: + abort_creds(new); + return old_fsgid; + +change_okay: + commit_creds(new); return old_fsgid; } @@ -1118,7 +1167,7 @@ EXPORT_SYMBOL(groups_free); /* export the group_info to a user-space array */ static int groups_to_user(gid_t __user *grouplist, - struct group_info *group_info) + const struct group_info *group_info) { int i; unsigned int count = group_info->ngroups; @@ -1186,7 +1235,7 @@ static void groups_sort(struct group_info *group_info) } /* a simple bsearch */ -int groups_search(struct group_info *group_info, gid_t grp) +int groups_search(const struct group_info *group_info, gid_t grp) { unsigned int left, right; @@ -1208,51 +1257,74 @@ int groups_search(struct group_info *group_info, gid_t grp) return 0; } -/* validate and set current->group_info */ -int set_current_groups(struct group_info *group_info) +/** + * set_groups - Change a group subscription in a set of credentials + * @new: The newly prepared set of credentials to alter + * @group_info: The group list to install + * + * Validate a group subscription and, if valid, insert it into a set + * of credentials. + */ +int set_groups(struct cred *new, struct group_info *group_info) { int retval; - struct group_info *old_info; retval = security_task_setgroups(group_info); if (retval) return retval; + put_group_info(new->group_info); groups_sort(group_info); get_group_info(group_info); - - task_lock(current); - old_info = current->group_info; - current->group_info = group_info; - task_unlock(current); - - put_group_info(old_info); - + new->group_info = group_info; return 0; } +EXPORT_SYMBOL(set_groups); + +/** + * set_current_groups - Change current's group subscription + * @group_info: The group list to impose + * + * Validate a group subscription and, if valid, impose it upon current's task + * security record. + */ +int set_current_groups(struct group_info *group_info) +{ + struct cred *new; + int ret; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + ret = set_groups(new, group_info); + if (ret < 0) { + abort_creds(new); + return ret; + } + + return commit_creds(new); +} + EXPORT_SYMBOL(set_current_groups); asmlinkage long sys_getgroups(int gidsetsize, gid_t __user *grouplist) { - int i = 0; - - /* - * SMP: Nobody else can change our grouplist. Thus we are - * safe. - */ + const struct cred *cred = current_cred(); + int i; if (gidsetsize < 0) return -EINVAL; /* no need to grab task_lock here; it cannot change */ - i = current->group_info->ngroups; + i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } - if (groups_to_user(grouplist, current->group_info)) { + if (groups_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } @@ -1296,9 +1368,11 @@ asmlinkage long sys_setgroups(int gidsetsize, gid_t __user *grouplist) */ int in_group_p(gid_t grp) { + const struct cred *cred = current_cred(); int retval = 1; - if (grp != current->fsgid) - retval = groups_search(current->group_info, grp); + + if (grp != cred->fsgid) + retval = groups_search(cred->group_info, grp); return retval; } @@ -1306,9 +1380,11 @@ EXPORT_SYMBOL(in_group_p); int in_egroup_p(gid_t grp) { + const struct cred *cred = current_cred(); int retval = 1; - if (grp != current->egid) - retval = groups_search(current->group_info, grp); + + if (grp != cred->egid) + retval = groups_search(cred->group_info, grp); return retval; } @@ -1624,50 +1700,56 @@ asmlinkage long sys_umask(int mask) asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, unsigned long arg5) { - long error = 0; + struct task_struct *me = current; + unsigned char comm[sizeof(me->comm)]; + long error; - if (security_task_prctl(option, arg2, arg3, arg4, arg5, &error)) + error = security_task_prctl(option, arg2, arg3, arg4, arg5); + if (error != -ENOSYS) return error; + error = 0; switch (option) { case PR_SET_PDEATHSIG: if (!valid_signal(arg2)) { error = -EINVAL; break; } - current->pdeath_signal = arg2; + me->pdeath_signal = arg2; + error = 0; break; case PR_GET_PDEATHSIG: - error = put_user(current->pdeath_signal, (int __user *)arg2); + error = put_user(me->pdeath_signal, (int __user *)arg2); break; case PR_GET_DUMPABLE: - error = get_dumpable(current->mm); + error = get_dumpable(me->mm); break; case PR_SET_DUMPABLE: if (arg2 < 0 || arg2 > 1) { error = -EINVAL; break; } - set_dumpable(current->mm, arg2); + set_dumpable(me->mm, arg2); + error = 0; break; case PR_SET_UNALIGN: - error = SET_UNALIGN_CTL(current, arg2); + error = SET_UNALIGN_CTL(me, arg2); break; case PR_GET_UNALIGN: - error = GET_UNALIGN_CTL(current, arg2); + error = GET_UNALIGN_CTL(me, arg2); break; case PR_SET_FPEMU: - error = SET_FPEMU_CTL(current, arg2); + error = SET_FPEMU_CTL(me, arg2); break; case PR_GET_FPEMU: - error = GET_FPEMU_CTL(current, arg2); + error = GET_FPEMU_CTL(me, arg2); break; case PR_SET_FPEXC: - error = SET_FPEXC_CTL(current, arg2); + error = SET_FPEXC_CTL(me, arg2); break; case PR_GET_FPEXC: - error = GET_FPEXC_CTL(current, arg2); + error = GET_FPEXC_CTL(me, arg2); break; case PR_GET_TIMING: error = PR_TIMING_STATISTICAL; @@ -1675,33 +1757,28 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, case PR_SET_TIMING: if (arg2 != PR_TIMING_STATISTICAL) error = -EINVAL; + else + error = 0; break; - case PR_SET_NAME: { - struct task_struct *me = current; - unsigned char ncomm[sizeof(me->comm)]; - - ncomm[sizeof(me->comm)-1] = 0; - if (strncpy_from_user(ncomm, (char __user *)arg2, - sizeof(me->comm)-1) < 0) + case PR_SET_NAME: + comm[sizeof(me->comm)-1] = 0; + if (strncpy_from_user(comm, (char __user *)arg2, + sizeof(me->comm) - 1) < 0) return -EFAULT; - set_task_comm(me, ncomm); + set_task_comm(me, comm); return 0; - } - case PR_GET_NAME: { - struct task_struct *me = current; - unsigned char tcomm[sizeof(me->comm)]; - - get_task_comm(tcomm, me); - if (copy_to_user((char __user *)arg2, tcomm, sizeof(tcomm))) + case PR_GET_NAME: + get_task_comm(comm, me); + if (copy_to_user((char __user *)arg2, comm, + sizeof(comm))) return -EFAULT; return 0; - } case PR_GET_ENDIAN: - error = GET_ENDIAN(current, arg2); + error = GET_ENDIAN(me, arg2); break; case PR_SET_ENDIAN: - error = SET_ENDIAN(current, arg2); + error = SET_ENDIAN(me, arg2); break; case PR_GET_SECCOMP: @@ -1725,6 +1802,7 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3, current->default_timer_slack_ns; else current->timer_slack_ns = arg2; + error = 0; break; default: error = -EINVAL; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 3d56fe7570d..9d52b57310a 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1651,7 +1651,7 @@ out: static int test_perm(int mode, int op) { - if (!current->euid) + if (!current_euid()) mode >>= 6; else if (in_egroup_p(0)) mode >>= 3; diff --git a/kernel/timer.c b/kernel/timer.c index dbd50fabe4c..566257d1dc1 100644 --- a/kernel/timer.c +++ b/kernel/timer.c @@ -1192,25 +1192,25 @@ asmlinkage long sys_getppid(void) asmlinkage long sys_getuid(void) { /* Only we change this so SMP safe */ - return current->uid; + return current_uid(); } asmlinkage long sys_geteuid(void) { /* Only we change this so SMP safe */ - return current->euid; + return current_euid(); } asmlinkage long sys_getgid(void) { /* Only we change this so SMP safe */ - return current->gid; + return current_gid(); } asmlinkage long sys_getegid(void) { /* Only we change this so SMP safe */ - return current->egid; + return current_egid(); } #endif diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index d86e3252f30..1ee9e4e454a 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -246,7 +246,7 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu) memcpy(data->comm, tsk->comm, TASK_COMM_LEN); data->pid = tsk->pid; - data->uid = tsk->uid; + data->uid = task_uid(tsk); data->nice = tsk->static_prio - 20 - MAX_RT_PRIO; data->policy = tsk->policy; data->rt_priority = tsk->rt_priority; diff --git a/kernel/tsacct.c b/kernel/tsacct.c index 8ebcd8532df..2dc06ab3571 100644 --- a/kernel/tsacct.c +++ b/kernel/tsacct.c @@ -27,6 +27,7 @@ */ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) { + const struct cred *tcred; struct timespec uptime, ts; u64 ac_etime; @@ -53,10 +54,11 @@ void bacct_add_tsk(struct taskstats *stats, struct task_struct *tsk) stats->ac_flag |= AXSIG; stats->ac_nice = task_nice(tsk); stats->ac_sched = tsk->policy; - stats->ac_uid = tsk->uid; - stats->ac_gid = tsk->gid; stats->ac_pid = tsk->pid; rcu_read_lock(); + tcred = __task_cred(tsk); + stats->ac_uid = tcred->uid; + stats->ac_gid = tcred->gid; stats->ac_ppid = pid_alive(tsk) ? rcu_dereference(tsk->real_parent)->tgid : 0; rcu_read_unlock(); diff --git a/kernel/uid16.c b/kernel/uid16.c index 3e41c1673e2..2460c3199b5 100644 --- a/kernel/uid16.c +++ b/kernel/uid16.c @@ -84,11 +84,12 @@ asmlinkage long sys_setresuid16(old_uid_t ruid, old_uid_t euid, old_uid_t suid) asmlinkage long sys_getresuid16(old_uid_t __user *ruid, old_uid_t __user *euid, old_uid_t __user *suid) { + const struct cred *cred = current_cred(); int retval; - if (!(retval = put_user(high2lowuid(current->uid), ruid)) && - !(retval = put_user(high2lowuid(current->euid), euid))) - retval = put_user(high2lowuid(current->suid), suid); + if (!(retval = put_user(high2lowuid(cred->uid), ruid)) && + !(retval = put_user(high2lowuid(cred->euid), euid))) + retval = put_user(high2lowuid(cred->suid), suid); return retval; } @@ -104,11 +105,12 @@ asmlinkage long sys_setresgid16(old_gid_t rgid, old_gid_t egid, old_gid_t sgid) asmlinkage long sys_getresgid16(old_gid_t __user *rgid, old_gid_t __user *egid, old_gid_t __user *sgid) { + const struct cred *cred = current_cred(); int retval; - if (!(retval = put_user(high2lowgid(current->gid), rgid)) && - !(retval = put_user(high2lowgid(current->egid), egid))) - retval = put_user(high2lowgid(current->sgid), sgid); + if (!(retval = put_user(high2lowgid(cred->gid), rgid)) && + !(retval = put_user(high2lowgid(cred->egid), egid))) + retval = put_user(high2lowgid(cred->sgid), sgid); return retval; } @@ -161,25 +163,24 @@ static int groups16_from_user(struct group_info *group_info, asmlinkage long sys_getgroups16(int gidsetsize, old_gid_t __user *grouplist) { - int i = 0; + const struct cred *cred = current_cred(); + int i; if (gidsetsize < 0) return -EINVAL; - get_group_info(current->group_info); - i = current->group_info->ngroups; + i = cred->group_info->ngroups; if (gidsetsize) { if (i > gidsetsize) { i = -EINVAL; goto out; } - if (groups16_to_user(grouplist, current->group_info)) { + if (groups16_to_user(grouplist, cred->group_info)) { i = -EFAULT; goto out; } } out: - put_group_info(current->group_info); return i; } @@ -210,20 +211,20 @@ asmlinkage long sys_setgroups16(int gidsetsize, old_gid_t __user *grouplist) asmlinkage long sys_getuid16(void) { - return high2lowuid(current->uid); + return high2lowuid(current_uid()); } asmlinkage long sys_geteuid16(void) { - return high2lowuid(current->euid); + return high2lowuid(current_euid()); } asmlinkage long sys_getgid16(void) { - return high2lowgid(current->gid); + return high2lowgid(current_gid()); } asmlinkage long sys_getegid16(void) { - return high2lowgid(current->egid); + return high2lowgid(current_egid()); } diff --git a/kernel/user.c b/kernel/user.c index 39d6159fae4..6608a3d8ca6 100644 --- a/kernel/user.c +++ b/kernel/user.c @@ -16,12 +16,13 @@ #include #include #include +#include "cred-internals.h" struct user_namespace init_user_ns = { .kref = { - .refcount = ATOMIC_INIT(2), + .refcount = ATOMIC_INIT(1), }, - .root_user = &root_user, + .creator = &root_user, }; EXPORT_SYMBOL_GPL(init_user_ns); @@ -47,12 +48,14 @@ static struct kmem_cache *uid_cachep; */ static DEFINE_SPINLOCK(uidhash_lock); +/* root_user.__count is 2, 1 for init task cred, 1 for init_user_ns->creator */ struct user_struct root_user = { - .__count = ATOMIC_INIT(1), + .__count = ATOMIC_INIT(2), .processes = ATOMIC_INIT(1), .files = ATOMIC_INIT(0), .sigpending = ATOMIC_INIT(0), .locked_shm = 0, + .user_ns = &init_user_ns, #ifdef CONFIG_USER_SCHED .tg = &init_task_group, #endif @@ -104,16 +107,10 @@ static int sched_create_user(struct user_struct *up) return rc; } -static void sched_switch_user(struct task_struct *p) -{ - sched_move_task(p); -} - #else /* CONFIG_USER_SCHED */ static void sched_destroy_user(struct user_struct *up) { } static int sched_create_user(struct user_struct *up) { return 0; } -static void sched_switch_user(struct task_struct *p) { } #endif /* CONFIG_USER_SCHED */ @@ -242,13 +239,21 @@ static struct kobj_type uids_ktype = { .release = uids_release, }; -/* create /sys/kernel/uids//cpu_share file for this user */ +/* + * Create /sys/kernel/uids//cpu_share file for this user + * We do not create this file for users in a user namespace (until + * sysfs tagging is implemented). + * + * See Documentation/scheduler/sched-design-CFS.txt for ramifications. + */ static int uids_user_create(struct user_struct *up) { struct kobject *kobj = &up->kobj; int error; memset(kobj, 0, sizeof(struct kobject)); + if (up->user_ns != &init_user_ns) + return 0; kobj->kset = uids_kset; error = kobject_init_and_add(kobj, &uids_ktype, NULL, "%d", up->uid); if (error) { @@ -284,6 +289,8 @@ static void remove_user_sysfs_dir(struct work_struct *w) unsigned long flags; int remove_user = 0; + if (up->user_ns != &init_user_ns) + return; /* Make uid_hash_remove() + sysfs_remove_file() + kobject_del() * atomic. */ @@ -319,12 +326,13 @@ done: * IRQ state (as stored in flags) is restored and uidhash_lock released * upon function exit. */ -static inline void free_user(struct user_struct *up, unsigned long flags) +static void free_user(struct user_struct *up, unsigned long flags) { /* restore back the count */ atomic_inc(&up->__count); spin_unlock_irqrestore(&uidhash_lock, flags); + put_user_ns(up->user_ns); INIT_WORK(&up->work, remove_user_sysfs_dir); schedule_work(&up->work); } @@ -340,13 +348,14 @@ static inline void uids_mutex_unlock(void) { } * IRQ state (as stored in flags) is restored and uidhash_lock released * upon function exit. */ -static inline void free_user(struct user_struct *up, unsigned long flags) +static void free_user(struct user_struct *up, unsigned long flags) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); sched_destroy_user(up); key_put(up->uid_keyring); key_put(up->session_keyring); + put_user_ns(up->user_ns); kmem_cache_free(uid_cachep, up); } @@ -362,7 +371,7 @@ struct user_struct *find_user(uid_t uid) { struct user_struct *ret; unsigned long flags; - struct user_namespace *ns = current->nsproxy->user_ns; + struct user_namespace *ns = current_user_ns(); spin_lock_irqsave(&uidhash_lock, flags); ret = uid_hash_find(uid, uidhashentry(ns, uid)); @@ -409,6 +418,8 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) if (sched_create_user(new) < 0) goto out_free_user; + new->user_ns = get_user_ns(ns); + if (uids_user_create(new)) goto out_destoy_sched; @@ -432,7 +443,6 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) up = new; } spin_unlock_irq(&uidhash_lock); - } uids_mutex_unlock(); @@ -441,6 +451,7 @@ struct user_struct *alloc_uid(struct user_namespace *ns, uid_t uid) out_destoy_sched: sched_destroy_user(new); + put_user_ns(new->user_ns); out_free_user: kmem_cache_free(uid_cachep, new); out_unlock: @@ -448,63 +459,6 @@ out_unlock: return NULL; } -void switch_uid(struct user_struct *new_user) -{ - struct user_struct *old_user; - - /* What if a process setreuid()'s and this brings the - * new uid over his NPROC rlimit? We can check this now - * cheaply with the new uid cache, so if it matters - * we should be checking for it. -DaveM - */ - old_user = current->user; - atomic_inc(&new_user->processes); - atomic_dec(&old_user->processes); - switch_uid_keyring(new_user); - current->user = new_user; - sched_switch_user(current); - - /* - * We need to synchronize with __sigqueue_alloc() - * doing a get_uid(p->user).. If that saw the old - * user value, we need to wait until it has exited - * its critical region before we can free the old - * structure. - */ - smp_mb(); - spin_unlock_wait(¤t->sighand->siglock); - - free_uid(old_user); - suid_keys(current); -} - -#ifdef CONFIG_USER_NS -void release_uids(struct user_namespace *ns) -{ - int i; - unsigned long flags; - struct hlist_head *head; - struct hlist_node *nd; - - spin_lock_irqsave(&uidhash_lock, flags); - /* - * collapse the chains so that the user_struct-s will - * be still alive, but not in hashes. subsequent free_uid() - * will free them. - */ - for (i = 0; i < UIDHASH_SZ; i++) { - head = ns->uidhash_table + i; - while (!hlist_empty(head)) { - nd = head->first; - hlist_del_init(nd); - } - } - spin_unlock_irqrestore(&uidhash_lock, flags); - - free_uid(ns->root_user); -} -#endif - static int __init uid_cache_init(void) { int n; diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c index 532858fa5b8..79084311ee5 100644 --- a/kernel/user_namespace.c +++ b/kernel/user_namespace.c @@ -9,60 +9,55 @@ #include #include #include +#include /* - * Clone a new ns copying an original user ns, setting refcount to 1 - * @old_ns: namespace to clone - * Return NULL on error (failure to kmalloc), new ns otherwise + * Create a new user namespace, deriving the creator from the user in the + * passed credentials, and replacing that user with the new root user for the + * new namespace. + * + * This is called by copy_creds(), which will finish setting the target task's + * credentials. */ -static struct user_namespace *clone_user_ns(struct user_namespace *old_ns) +int create_user_ns(struct cred *new) { struct user_namespace *ns; - struct user_struct *new_user; + struct user_struct *root_user; int n; ns = kmalloc(sizeof(struct user_namespace), GFP_KERNEL); if (!ns) - return ERR_PTR(-ENOMEM); + return -ENOMEM; kref_init(&ns->kref); for (n = 0; n < UIDHASH_SZ; ++n) INIT_HLIST_HEAD(ns->uidhash_table + n); - /* Insert new root user. */ - ns->root_user = alloc_uid(ns, 0); - if (!ns->root_user) { + /* Alloc new root user. */ + root_user = alloc_uid(ns, 0); + if (!root_user) { kfree(ns); - return ERR_PTR(-ENOMEM); + return -ENOMEM; } - /* Reset current->user with a new one */ - new_user = alloc_uid(ns, current->uid); - if (!new_user) { - free_uid(ns->root_user); - kfree(ns); - return ERR_PTR(-ENOMEM); - } + /* set the new root user in the credentials under preparation */ + ns->creator = new->user; + new->user = root_user; + new->uid = new->euid = new->suid = new->fsuid = 0; + new->gid = new->egid = new->sgid = new->fsgid = 0; + put_group_info(new->group_info); + new->group_info = get_group_info(&init_groups); +#ifdef CONFIG_KEYS + key_put(new->request_key_auth); + new->request_key_auth = NULL; +#endif + /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ - switch_uid(new_user); - return ns; -} + /* alloc_uid() incremented the userns refcount. Just set it to 1 */ + kref_set(&ns->kref, 1); -struct user_namespace * copy_user_ns(int flags, struct user_namespace *old_ns) -{ - struct user_namespace *new_ns; - - BUG_ON(!old_ns); - get_user_ns(old_ns); - - if (!(flags & CLONE_NEWUSER)) - return old_ns; - - new_ns = clone_user_ns(old_ns); - - put_user_ns(old_ns); - return new_ns; + return 0; } void free_user_ns(struct kref *kref) @@ -70,7 +65,7 @@ void free_user_ns(struct kref *kref) struct user_namespace *ns; ns = container_of(kref, struct user_namespace, kref); - release_uids(ns); + free_uid(ns->creator); kfree(ns); } EXPORT_SYMBOL(free_user_ns); diff --git a/kernel/workqueue.c b/kernel/workqueue.c index d4dc69ddebd..4952322cba4 100644 --- a/kernel/workqueue.c +++ b/kernel/workqueue.c @@ -84,21 +84,21 @@ static cpumask_t cpu_singlethread_map __read_mostly; static cpumask_t cpu_populated_map __read_mostly; /* If it's single threaded, it isn't in the list of workqueues. */ -static inline int is_single_threaded(struct workqueue_struct *wq) +static inline int is_wq_single_threaded(struct workqueue_struct *wq) { return wq->singlethread; } static const cpumask_t *wq_cpu_map(struct workqueue_struct *wq) { - return is_single_threaded(wq) + return is_wq_single_threaded(wq) ? &cpu_singlethread_map : &cpu_populated_map; } static struct cpu_workqueue_struct *wq_per_cpu(struct workqueue_struct *wq, int cpu) { - if (unlikely(is_single_threaded(wq))) + if (unlikely(is_wq_single_threaded(wq))) cpu = singlethread_cpu; return per_cpu_ptr(wq->cpu_wq, cpu); } @@ -769,7 +769,7 @@ static int create_workqueue_thread(struct cpu_workqueue_struct *cwq, int cpu) { struct sched_param param = { .sched_priority = MAX_RT_PRIO-1 }; struct workqueue_struct *wq = cwq->wq; - const char *fmt = is_single_threaded(wq) ? "%s" : "%s/%d"; + const char *fmt = is_wq_single_threaded(wq) ? "%s" : "%s/%d"; struct task_struct *p; p = kthread_create(worker_thread, cwq, fmt, wq->name, cpu); diff --git a/lib/Makefile b/lib/Makefile index 7cb65d85aeb..80fe8a3ec12 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -11,7 +11,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ rbtree.o radix-tree.o dump_stack.o \ idr.o int_sqrt.o extable.o prio_tree.o \ sha1.o irq_regs.o reciprocal_div.o argv_split.o \ - proportions.o prio_heap.o ratelimit.o show_mem.o + proportions.o prio_heap.o ratelimit.o show_mem.o is_single_threaded.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o diff --git a/lib/is_single_threaded.c b/lib/is_single_threaded.c new file mode 100644 index 00000000000..f1ed2fe76c6 --- /dev/null +++ b/lib/is_single_threaded.c @@ -0,0 +1,45 @@ +/* Function to determine if a thread group is single threaded or not + * + * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * - Derived from security/selinux/hooks.c + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include + +/** + * is_single_threaded - Determine if a thread group is single-threaded or not + * @p: A task in the thread group in question + * + * This returns true if the thread group to which a task belongs is single + * threaded, false if it is not. + */ +bool is_single_threaded(struct task_struct *p) +{ + struct task_struct *g, *t; + struct mm_struct *mm = p->mm; + + if (atomic_read(&p->signal->count) != 1) + goto no; + + if (atomic_read(&p->mm->mm_users) != 1) { + read_lock(&tasklist_lock); + do_each_thread(g, t) { + if (t->mm == mm && t != p) + goto no_unlock; + } while_each_thread(g, t); + read_unlock(&tasklist_lock); + } + + return true; + +no_unlock: + read_unlock(&tasklist_lock); +no: + return false; +} diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e9493b1c111..e412ffa8e52 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1114,6 +1114,7 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { + const struct cred *cred = current_cred(), *tcred; struct mm_struct *mm; struct task_struct *task; nodemask_t old; @@ -1148,12 +1149,16 @@ asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, * capabilities, superuser privileges or the same * userid as the target process. */ - if ((current->euid != task->suid) && (current->euid != task->uid) && - (current->uid != task->suid) && (current->uid != task->uid) && + rcu_read_lock(); + tcred = __task_cred(task); + if (cred->euid != tcred->suid && cred->euid != tcred->uid && + cred->uid != tcred->suid && cred->uid != tcred->uid && !capable(CAP_SYS_NICE)) { + rcu_read_unlock(); err = -EPERM; goto out; } + rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ diff --git a/mm/migrate.c b/mm/migrate.c index 037b0967c1e..21631ab8c08 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1075,6 +1075,7 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, const int __user *nodes, int __user *status, int flags) { + const struct cred *cred = current_cred(), *tcred; struct task_struct *task; struct mm_struct *mm; int err; @@ -1105,12 +1106,16 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, * capabilities, superuser privileges or the same * userid as the target process. */ - if ((current->euid != task->suid) && (current->euid != task->uid) && - (current->uid != task->suid) && (current->uid != task->uid) && + rcu_read_lock(); + tcred = __task_cred(task); + if (cred->euid != tcred->suid && cred->euid != tcred->uid && + cred->uid != tcred->suid && cred->uid != tcred->uid && !capable(CAP_SYS_NICE)) { + rcu_read_unlock(); err = -EPERM; goto out; } + rcu_read_unlock(); err = security_task_movememory(task); if (err) diff --git a/mm/oom_kill.c b/mm/oom_kill.c index a0a01902f55..558f9afe6e4 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -128,8 +128,8 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) * Superuser processes are usually more important, so we make it * less likely that we kill those. */ - if (has_capability(p, CAP_SYS_ADMIN) || - has_capability(p, CAP_SYS_RESOURCE)) + if (has_capability_noaudit(p, CAP_SYS_ADMIN) || + has_capability_noaudit(p, CAP_SYS_RESOURCE)) points /= 4; /* @@ -138,7 +138,7 @@ unsigned long badness(struct task_struct *p, unsigned long uptime) * tend to only have this flag set on applications they think * of as important. */ - if (has_capability(p, CAP_SYS_RAWIO)) + if (has_capability_noaudit(p, CAP_SYS_RAWIO)) points /= 4; /* @@ -299,9 +299,9 @@ static void dump_tasks(const struct mem_cgroup *mem) task_lock(p); printk(KERN_INFO "[%5d] %5d %5d %8lu %8lu %3d %3d %s\n", - p->pid, p->uid, p->tgid, p->mm->total_vm, - get_mm_rss(p->mm), (int)task_cpu(p), p->oomkilladj, - p->comm); + p->pid, __task_cred(p)->uid, p->tgid, + p->mm->total_vm, get_mm_rss(p->mm), (int)task_cpu(p), + p->oomkilladj, p->comm); task_unlock(p); } while_each_thread(g, p); } diff --git a/mm/shmem.c b/mm/shmem.c index 0ed075215e5..f1b0d4871f3 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1513,8 +1513,8 @@ shmem_get_inode(struct super_block *sb, int mode, dev_t dev) inode = new_inode(sb); if (inode) { inode->i_mode = mode; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); inode->i_blocks = 0; inode->i_mapping->backing_dev_info = &shmem_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; @@ -2278,8 +2278,8 @@ static int shmem_fill_super(struct super_block *sb, sbinfo->max_blocks = 0; sbinfo->max_inodes = 0; sbinfo->mode = S_IRWXUGO | S_ISVTX; - sbinfo->uid = current->fsuid; - sbinfo->gid = current->fsgid; + sbinfo->uid = current_fsuid(); + sbinfo->gid = current_fsgid(); sbinfo->mpol = NULL; sb->s_fs_info = sbinfo; diff --git a/net/9p/client.c b/net/9p/client.c index 4b529454616..821f1ec0b2c 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -627,7 +627,7 @@ static struct p9_fid *p9_fid_create(struct p9_client *clnt) memset(&fid->qid, 0, sizeof(struct p9_qid)); fid->mode = -1; fid->rdir_fpos = 0; - fid->uid = current->fsuid; + fid->uid = current_fsuid(); fid->clnt = clnt; fid->aux = NULL; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 28c71574a78..00d9e5e1315 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1045,7 +1045,7 @@ static int ax25_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr->fsa_ax25.sax25_family != AF_AX25) return -EINVAL; - user = ax25_findbyuid(current->euid); + user = ax25_findbyuid(current_euid()); if (user) { call = user->call; ax25_uid_put(user); diff --git a/net/ax25/ax25_route.c b/net/ax25/ax25_route.c index 8672cd84fdf..c833ba4c45a 100644 --- a/net/ax25/ax25_route.c +++ b/net/ax25/ax25_route.c @@ -421,7 +421,7 @@ int ax25_rt_autobind(ax25_cb *ax25, ax25_address *addr) goto put; } - user = ax25_findbyuid(current->euid); + user = ax25_findbyuid(current_euid()); if (user) { ax25->source_addr = user->call; ax25_uid_put(user); diff --git a/net/core/dev.c b/net/core/dev.c index 9174c77d311..89912ae6de6 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2961,6 +2961,8 @@ static void dev_change_rx_flags(struct net_device *dev, int flags) static int __dev_set_promiscuity(struct net_device *dev, int inc) { unsigned short old_flags = dev->flags; + uid_t uid; + gid_t gid; ASSERT_RTNL(); @@ -2985,15 +2987,17 @@ static int __dev_set_promiscuity(struct net_device *dev, int inc) printk(KERN_INFO "device %s %s promiscuous mode\n", dev->name, (dev->flags & IFF_PROMISC) ? "entered" : "left"); - if (audit_enabled) + if (audit_enabled) { + current_uid_gid(&uid, &gid); audit_log(current->audit_context, GFP_ATOMIC, AUDIT_ANOM_PROMISCUOUS, "dev=%s prom=%d old_prom=%d auid=%u uid=%u gid=%u ses=%u", dev->name, (dev->flags & IFF_PROMISC), (old_flags & IFF_PROMISC), audit_get_loginuid(current), - current->uid, current->gid, + uid, gid, audit_get_sessionid(current)); + } dev_change_rx_flags(dev, IFF_PROMISC); } diff --git a/net/core/scm.c b/net/core/scm.c index b12303dd39d..b7ba91b074b 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -44,11 +44,13 @@ static __inline__ int scm_check_creds(struct ucred *creds) { + const struct cred *cred = current_cred(); + if ((creds->pid == task_tgid_vnr(current) || capable(CAP_SYS_ADMIN)) && - ((creds->uid == current->uid || creds->uid == current->euid || - creds->uid == current->suid) || capable(CAP_SETUID)) && - ((creds->gid == current->gid || creds->gid == current->egid || - creds->gid == current->sgid) || capable(CAP_SETGID))) { + ((creds->uid == cred->uid || creds->uid == cred->euid || + creds->uid == cred->suid) || capable(CAP_SETUID)) && + ((creds->gid == cred->gid || creds->gid == cred->egid || + creds->gid == cred->sgid) || capable(CAP_SETGID))) { return 0; } return -EPERM; diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index fc6ce04a3e3..7b5dbe118c0 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -340,8 +340,8 @@ static void dump_packet(const struct nf_loginfo *info, read_lock_bh(&skb->sk->sk_callback_lock); if (skb->sk->sk_socket && skb->sk->sk_socket->file) printk("UID=%u GID=%u ", - skb->sk->sk_socket->file->f_uid, - skb->sk->sk_socket->file->f_gid); + skb->sk->sk_socket->file->f_cred->fsuid, + skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); } diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 37a4e777e34..bd3c7b96bba 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -388,7 +388,7 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, fl->owner = current->pid; break; case IPV6_FL_S_USER: - fl->owner = current->euid; + fl->owner = current_euid(); break; default: err = -EINVAL; diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index caa441d0956..871d157cec4 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -364,8 +364,8 @@ static void dump_packet(const struct nf_loginfo *info, read_lock_bh(&skb->sk->sk_callback_lock); if (skb->sk->sk_socket && skb->sk->sk_socket->file) printk("UID=%u GID=%u ", - skb->sk->sk_socket->file->f_uid, - skb->sk->sk_socket->file->f_gid); + skb->sk->sk_socket->file->f_cred->fsuid, + skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); } diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 41e0105d382..38f9efd90e8 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -474,8 +474,9 @@ __build_packet_message(struct nfulnl_instance *inst, if (skb->sk) { read_lock_bh(&skb->sk->sk_callback_lock); if (skb->sk->sk_socket && skb->sk->sk_socket->file) { - __be32 uid = htonl(skb->sk->sk_socket->file->f_uid); - __be32 gid = htonl(skb->sk->sk_socket->file->f_gid); + struct file *file = skb->sk->sk_socket->file; + __be32 uid = htonl(file->f_cred->fsuid); + __be32 gid = htonl(file->f_cred->fsgid); /* need to unlock here since NLA_PUT may goto */ read_unlock_bh(&skb->sk->sk_callback_lock); NLA_PUT_BE32(inst->skb, NFULA_UID, uid); diff --git a/net/netfilter/xt_owner.c b/net/netfilter/xt_owner.c index f19ebd9b78f..22b2a5e881e 100644 --- a/net/netfilter/xt_owner.c +++ b/net/netfilter/xt_owner.c @@ -34,12 +34,12 @@ owner_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) return false; if (info->match & IPT_OWNER_UID) - if ((filp->f_uid != info->uid) ^ + if ((filp->f_cred->fsuid != info->uid) ^ !!(info->invert & IPT_OWNER_UID)) return false; if (info->match & IPT_OWNER_GID) - if ((filp->f_gid != info->gid) ^ + if ((filp->f_cred->fsgid != info->gid) ^ !!(info->invert & IPT_OWNER_GID)) return false; @@ -60,12 +60,12 @@ owner_mt6_v0(const struct sk_buff *skb, const struct xt_match_param *par) return false; if (info->match & IP6T_OWNER_UID) - if ((filp->f_uid != info->uid) ^ + if ((filp->f_cred->fsuid != info->uid) ^ !!(info->invert & IP6T_OWNER_UID)) return false; if (info->match & IP6T_OWNER_GID) - if ((filp->f_gid != info->gid) ^ + if ((filp->f_cred->fsgid != info->gid) ^ !!(info->invert & IP6T_OWNER_GID)) return false; @@ -93,14 +93,14 @@ owner_mt(const struct sk_buff *skb, const struct xt_match_param *par) (XT_OWNER_UID | XT_OWNER_GID)) == 0; if (info->match & XT_OWNER_UID) - if ((filp->f_uid >= info->uid_min && - filp->f_uid <= info->uid_max) ^ + if ((filp->f_cred->fsuid >= info->uid_min && + filp->f_cred->fsuid <= info->uid_max) ^ !(info->invert & XT_OWNER_UID)) return false; if (info->match & XT_OWNER_GID) - if ((filp->f_gid >= info->gid_min && - filp->f_gid <= info->gid_max) ^ + if ((filp->f_cred->fsgid >= info->gid_min && + filp->f_cred->fsgid <= info->gid_max) ^ !(info->invert & XT_OWNER_GID)) return false; diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 9f1ea4a27b3..e9c05b8f4f4 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -609,7 +609,7 @@ static int nr_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } else { source = &addr->fsa_ax25.sax25_call; - user = ax25_findbyuid(current->euid); + user = ax25_findbyuid(current_euid()); if (user) { nr->user_addr = user->call; ax25_uid_put(user); @@ -683,7 +683,7 @@ static int nr_connect(struct socket *sock, struct sockaddr *uaddr, } source = (ax25_address *)dev->dev_addr; - user = ax25_findbyuid(current->euid); + user = ax25_findbyuid(current_euid()); if (user) { nr->user_addr = user->call; ax25_uid_put(user); diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index 0c1cc761280..01392649b46 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -690,7 +690,7 @@ static int rose_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) source = &addr->srose_call; - user = ax25_findbyuid(current->euid); + user = ax25_findbyuid(current_euid()); if (user) { rose->source_call = user->call; ax25_uid_put(user); @@ -791,7 +791,7 @@ static int rose_connect(struct socket *sock, struct sockaddr *uaddr, int addr_le goto out_release; } - user = ax25_findbyuid(current->euid); + user = ax25_findbyuid(current_euid()); if (!user) { err = -EINVAL; goto out_release; diff --git a/net/rxrpc/ar-key.c b/net/rxrpc/ar-key.c index 9a8ff684da7..ad8c7a782da 100644 --- a/net/rxrpc/ar-key.c +++ b/net/rxrpc/ar-key.c @@ -287,6 +287,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *conn, time_t expiry, u32 kvno) { + const struct cred *cred = current_cred(); struct key *key; int ret; @@ -297,7 +298,7 @@ int rxrpc_get_server_data_key(struct rxrpc_connection *conn, _enter(""); - key = key_alloc(&key_type_rxrpc, "x", 0, 0, current, 0, + key = key_alloc(&key_type_rxrpc, "x", 0, 0, cred, 0, KEY_ALLOC_NOT_IN_QUOTA); if (IS_ERR(key)) { _leave(" = -ENOMEM [alloc %ld]", PTR_ERR(key)); @@ -340,10 +341,11 @@ EXPORT_SYMBOL(rxrpc_get_server_data_key); */ struct key *rxrpc_get_null_key(const char *keyname) { + const struct cred *cred = current_cred(); struct key *key; int ret; - key = key_alloc(&key_type_rxrpc, keyname, 0, 0, current, + key = key_alloc(&key_type_rxrpc, keyname, 0, 0, cred, KEY_POS_SEARCH, KEY_ALLOC_NOT_IN_QUOTA); if (IS_ERR(key)) return key; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 0ebaff637e3..0ef4e3065bc 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -260,14 +260,14 @@ static u32 flow_get_rtclassid(const struct sk_buff *skb) static u32 flow_get_skuid(const struct sk_buff *skb) { if (skb->sk && skb->sk->sk_socket && skb->sk->sk_socket->file) - return skb->sk->sk_socket->file->f_uid; + return skb->sk->sk_socket->file->f_cred->fsuid; return 0; } static u32 flow_get_skgid(const struct sk_buff *skb) { if (skb->sk && skb->sk->sk_socket && skb->sk->sk_socket->file) - return skb->sk->sk_socket->file->f_gid; + return skb->sk->sk_socket->file->f_cred->fsgid; return 0; } diff --git a/net/socket.c b/net/socket.c index 76ba80aeac1..072e2e525ae 100644 --- a/net/socket.c +++ b/net/socket.c @@ -491,8 +491,8 @@ static struct socket *sock_alloc(void) sock = SOCKET_I(inode); inode->i_mode = S_IFSOCK | S_IRWXUGO; - inode->i_uid = current->fsuid; - inode->i_gid = current->fsgid; + inode->i_uid = current_fsuid(); + inode->i_gid = current_fsgid(); get_cpu_var(sockets_in_use)++; put_cpu_var(sockets_in_use); diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index cb216b2df66..0443f834945 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -350,16 +350,18 @@ EXPORT_SYMBOL_GPL(rpcauth_lookup_credcache); struct rpc_cred * rpcauth_lookupcred(struct rpc_auth *auth, int flags) { - struct auth_cred acred = { - .uid = current->fsuid, - .gid = current->fsgid, - .group_info = current->group_info, - }; + struct auth_cred acred; struct rpc_cred *ret; + const struct cred *cred = current_cred(); dprintk("RPC: looking up %s cred\n", auth->au_ops->au_name); - get_group_info(acred.group_info); + + memset(&acred, 0, sizeof(acred)); + acred.uid = cred->fsuid; + acred.gid = cred->fsgid; + acred.group_info = get_group_info(((struct cred *)cred)->group_info); + ret = auth->au_ops->lookup_cred(auth, &acred, flags); put_group_info(acred.group_info); return ret; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 66d5ac4773a..b152e2b9b98 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -467,8 +467,7 @@ static int unix_listen(struct socket *sock, int backlog) sk->sk_state = TCP_LISTEN; /* set credentials so connect can copy them */ sk->sk_peercred.pid = task_tgid_vnr(current); - sk->sk_peercred.uid = current->euid; - sk->sk_peercred.gid = current->egid; + current_euid_egid(&sk->sk_peercred.uid, &sk->sk_peercred.gid); err = 0; out_unlock: @@ -1126,8 +1125,7 @@ restart: newsk->sk_state = TCP_ESTABLISHED; newsk->sk_type = sk->sk_type; newsk->sk_peercred.pid = task_tgid_vnr(current); - newsk->sk_peercred.uid = current->euid; - newsk->sk_peercred.gid = current->egid; + current_euid_egid(&newsk->sk_peercred.uid, &newsk->sk_peercred.gid); newu = unix_sk(newsk); newsk->sk_sleep = &newu->peer_wait; otheru = unix_sk(other); @@ -1187,8 +1185,9 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb) unix_peer(ska)=skb; unix_peer(skb)=ska; ska->sk_peercred.pid = skb->sk_peercred.pid = task_tgid_vnr(current); - ska->sk_peercred.uid = skb->sk_peercred.uid = current->euid; - ska->sk_peercred.gid = skb->sk_peercred.gid = current->egid; + current_euid_egid(&skb->sk_peercred.uid, &skb->sk_peercred.gid); + ska->sk_peercred.uid = skb->sk_peercred.uid; + ska->sk_peercred.gid = skb->sk_peercred.gid; if (ska->sk_type != SOCK_DGRAM) { ska->sk_state = TCP_ESTABLISHED; diff --git a/security/capability.c b/security/capability.c index 24587481903..2dce66fcb99 100644 --- a/security/capability.c +++ b/security/capability.c @@ -32,24 +32,19 @@ static int cap_quota_on(struct dentry *dentry) return 0; } -static int cap_bprm_alloc_security(struct linux_binprm *bprm) +static int cap_bprm_check_security (struct linux_binprm *bprm) { return 0; } -static void cap_bprm_free_security(struct linux_binprm *bprm) +static void cap_bprm_committing_creds(struct linux_binprm *bprm) { } -static void cap_bprm_post_apply_creds(struct linux_binprm *bprm) +static void cap_bprm_committed_creds(struct linux_binprm *bprm) { } -static int cap_bprm_check_security(struct linux_binprm *bprm) -{ - return 0; -} - static int cap_sb_alloc_security(struct super_block *sb) { return 0; @@ -64,7 +59,7 @@ static int cap_sb_copy_data(char *orig, char *copy) return 0; } -static int cap_sb_kern_mount(struct super_block *sb, void *data) +static int cap_sb_kern_mount(struct super_block *sb, int flags, void *data) { return 0; } @@ -330,7 +325,7 @@ static int cap_file_receive(struct file *file) return 0; } -static int cap_dentry_open(struct file *file) +static int cap_dentry_open(struct file *file, const struct cred *cred) { return 0; } @@ -340,15 +335,29 @@ static int cap_task_create(unsigned long clone_flags) return 0; } -static int cap_task_alloc_security(struct task_struct *p) +static void cap_cred_free(struct cred *cred) +{ +} + +static int cap_cred_prepare(struct cred *new, const struct cred *old, gfp_t gfp) { return 0; } -static void cap_task_free_security(struct task_struct *p) +static void cap_cred_commit(struct cred *new, const struct cred *old) { } +static int cap_kernel_act_as(struct cred *new, u32 secid) +{ + return 0; +} + +static int cap_kernel_create_files_as(struct cred *new, struct inode *inode) +{ + return 0; +} + static int cap_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags) { return 0; @@ -750,7 +759,7 @@ static void cap_release_secctx(char *secdata, u32 seclen) } #ifdef CONFIG_KEYS -static int cap_key_alloc(struct key *key, struct task_struct *ctx, +static int cap_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { return 0; @@ -760,7 +769,7 @@ static void cap_key_free(struct key *key) { } -static int cap_key_permission(key_ref_t key_ref, struct task_struct *context, +static int cap_key_permission(key_ref_t key_ref, const struct cred *cred, key_perm_t perm) { return 0; @@ -814,8 +823,7 @@ void security_fixup_ops(struct security_operations *ops) set_to_cap_if_null(ops, ptrace_may_access); set_to_cap_if_null(ops, ptrace_traceme); set_to_cap_if_null(ops, capget); - set_to_cap_if_null(ops, capset_check); - set_to_cap_if_null(ops, capset_set); + set_to_cap_if_null(ops, capset); set_to_cap_if_null(ops, acct); set_to_cap_if_null(ops, capable); set_to_cap_if_null(ops, quotactl); @@ -824,11 +832,9 @@ void security_fixup_ops(struct security_operations *ops) set_to_cap_if_null(ops, syslog); set_to_cap_if_null(ops, settime); set_to_cap_if_null(ops, vm_enough_memory); - set_to_cap_if_null(ops, bprm_alloc_security); - set_to_cap_if_null(ops, bprm_free_security); - set_to_cap_if_null(ops, bprm_apply_creds); - set_to_cap_if_null(ops, bprm_post_apply_creds); - set_to_cap_if_null(ops, bprm_set_security); + set_to_cap_if_null(ops, bprm_set_creds); + set_to_cap_if_null(ops, bprm_committing_creds); + set_to_cap_if_null(ops, bprm_committed_creds); set_to_cap_if_null(ops, bprm_check_security); set_to_cap_if_null(ops, bprm_secureexec); set_to_cap_if_null(ops, sb_alloc_security); @@ -890,10 +896,13 @@ void security_fixup_ops(struct security_operations *ops) set_to_cap_if_null(ops, file_receive); set_to_cap_if_null(ops, dentry_open); set_to_cap_if_null(ops, task_create); - set_to_cap_if_null(ops, task_alloc_security); - set_to_cap_if_null(ops, task_free_security); + set_to_cap_if_null(ops, cred_free); + set_to_cap_if_null(ops, cred_prepare); + set_to_cap_if_null(ops, cred_commit); + set_to_cap_if_null(ops, kernel_act_as); + set_to_cap_if_null(ops, kernel_create_files_as); set_to_cap_if_null(ops, task_setuid); - set_to_cap_if_null(ops, task_post_setuid); + set_to_cap_if_null(ops, task_fix_setuid); set_to_cap_if_null(ops, task_setgid); set_to_cap_if_null(ops, task_setpgid); set_to_cap_if_null(ops, task_getpgid); @@ -910,7 +919,6 @@ void security_fixup_ops(struct security_operations *ops) set_to_cap_if_null(ops, task_wait); set_to_cap_if_null(ops, task_kill); set_to_cap_if_null(ops, task_prctl); - set_to_cap_if_null(ops, task_reparent_to_init); set_to_cap_if_null(ops, task_to_inode); set_to_cap_if_null(ops, ipc_permission); set_to_cap_if_null(ops, ipc_getsecid); diff --git a/security/commoncap.c b/security/commoncap.c index 3976613db82..79713545cd6 100644 --- a/security/commoncap.c +++ b/security/commoncap.c @@ -8,6 +8,7 @@ */ #include +#include #include #include #include @@ -29,7 +30,7 @@ int cap_netlink_send(struct sock *sk, struct sk_buff *skb) { - NETLINK_CB(skb).eff_cap = current->cap_effective; + NETLINK_CB(skb).eff_cap = current_cap(); return 0; } @@ -39,23 +40,41 @@ int cap_netlink_recv(struct sk_buff *skb, int cap) return -EPERM; return 0; } - EXPORT_SYMBOL(cap_netlink_recv); -/* +/** + * cap_capable - Determine whether a task has a particular effective capability + * @tsk: The task to query + * @cap: The capability to check for + * @audit: Whether to write an audit message or not + * + * Determine whether the nominated task has the specified capability amongst + * its effective set, returning 0 if it does, -ve if it does not. + * * NOTE WELL: cap_capable() cannot be used like the kernel's capable() - * function. That is, it has the reverse semantics: cap_capable() - * returns 0 when a task has a capability, but the kernel's capable() - * returns 1 for this case. + * function. That is, it has the reverse semantics: cap_capable() returns 0 + * when a task has a capability, but the kernel's capable() returns 1 for this + * case. */ -int cap_capable (struct task_struct *tsk, int cap) +int cap_capable(struct task_struct *tsk, int cap, int audit) { + __u32 cap_raised; + /* Derived from include/linux/sched.h:capable. */ - if (cap_raised(tsk->cap_effective, cap)) - return 0; - return -EPERM; + rcu_read_lock(); + cap_raised = cap_raised(__task_cred(tsk)->cap_effective, cap); + rcu_read_unlock(); + return cap_raised ? 0 : -EPERM; } +/** + * cap_settime - Determine whether the current process may set the system clock + * @ts: The time to set + * @tz: The timezone to set + * + * Determine whether the current process may set the system clock and timezone + * information, returning 0 if permission granted, -ve if denied. + */ int cap_settime(struct timespec *ts, struct timezone *tz) { if (!capable(CAP_SYS_TIME)) @@ -63,121 +82,157 @@ int cap_settime(struct timespec *ts, struct timezone *tz) return 0; } +/** + * cap_ptrace_may_access - Determine whether the current process may access + * another + * @child: The process to be accessed + * @mode: The mode of attachment. + * + * Determine whether a process may access another, returning 0 if permission + * granted, -ve if denied. + */ int cap_ptrace_may_access(struct task_struct *child, unsigned int mode) { - /* Derived from arch/i386/kernel/ptrace.c:sys_ptrace. */ - if (cap_issubset(child->cap_permitted, current->cap_permitted)) - return 0; - if (capable(CAP_SYS_PTRACE)) - return 0; - return -EPERM; + int ret = 0; + + rcu_read_lock(); + if (!cap_issubset(__task_cred(child)->cap_permitted, + current_cred()->cap_permitted) && + !capable(CAP_SYS_PTRACE)) + ret = -EPERM; + rcu_read_unlock(); + return ret; } +/** + * cap_ptrace_traceme - Determine whether another process may trace the current + * @parent: The task proposed to be the tracer + * + * Determine whether the nominated task is permitted to trace the current + * process, returning 0 if permission is granted, -ve if denied. + */ int cap_ptrace_traceme(struct task_struct *parent) { - /* Derived from arch/i386/kernel/ptrace.c:sys_ptrace. */ - if (cap_issubset(current->cap_permitted, parent->cap_permitted)) - return 0; - if (has_capability(parent, CAP_SYS_PTRACE)) - return 0; - return -EPERM; + int ret = 0; + + rcu_read_lock(); + if (!cap_issubset(current_cred()->cap_permitted, + __task_cred(parent)->cap_permitted) && + !has_capability(parent, CAP_SYS_PTRACE)) + ret = -EPERM; + rcu_read_unlock(); + return ret; } -int cap_capget (struct task_struct *target, kernel_cap_t *effective, - kernel_cap_t *inheritable, kernel_cap_t *permitted) +/** + * cap_capget - Retrieve a task's capability sets + * @target: The task from which to retrieve the capability sets + * @effective: The place to record the effective set + * @inheritable: The place to record the inheritable set + * @permitted: The place to record the permitted set + * + * This function retrieves the capabilities of the nominated task and returns + * them to the caller. + */ +int cap_capget(struct task_struct *target, kernel_cap_t *effective, + kernel_cap_t *inheritable, kernel_cap_t *permitted) { + const struct cred *cred; + /* Derived from kernel/capability.c:sys_capget. */ - *effective = target->cap_effective; - *inheritable = target->cap_inheritable; - *permitted = target->cap_permitted; + rcu_read_lock(); + cred = __task_cred(target); + *effective = cred->cap_effective; + *inheritable = cred->cap_inheritable; + *permitted = cred->cap_permitted; + rcu_read_unlock(); return 0; } -#ifdef CONFIG_SECURITY_FILE_CAPABILITIES - -static inline int cap_block_setpcap(struct task_struct *target) -{ - /* - * No support for remote process capability manipulation with - * filesystem capability support. - */ - return (target != current); -} - +/* + * Determine whether the inheritable capabilities are limited to the old + * permitted set. Returns 1 if they are limited, 0 if they are not. + */ static inline int cap_inh_is_capped(void) { - /* - * Return 1 if changes to the inheritable set are limited - * to the old permitted set. That is, if the current task - * does *not* possess the CAP_SETPCAP capability. +#ifdef CONFIG_SECURITY_FILE_CAPABILITIES + + /* they are so limited unless the current task has the CAP_SETPCAP + * capability */ - return (cap_capable(current, CAP_SETPCAP) != 0); + if (cap_capable(current, CAP_SETPCAP, SECURITY_CAP_AUDIT) == 0) + return 0; +#endif + return 1; } -static inline int cap_limit_ptraced_target(void) { return 1; } - -#else /* ie., ndef CONFIG_SECURITY_FILE_CAPABILITIES */ - -static inline int cap_block_setpcap(struct task_struct *t) { return 0; } -static inline int cap_inh_is_capped(void) { return 1; } -static inline int cap_limit_ptraced_target(void) +/** + * cap_capset - Validate and apply proposed changes to current's capabilities + * @new: The proposed new credentials; alterations should be made here + * @old: The current task's current credentials + * @effective: A pointer to the proposed new effective capabilities set + * @inheritable: A pointer to the proposed new inheritable capabilities set + * @permitted: A pointer to the proposed new permitted capabilities set + * + * This function validates and applies a proposed mass change to the current + * process's capability sets. The changes are made to the proposed new + * credentials, and assuming no error, will be committed by the caller of LSM. + */ +int cap_capset(struct cred *new, + const struct cred *old, + const kernel_cap_t *effective, + const kernel_cap_t *inheritable, + const kernel_cap_t *permitted) { - return !capable(CAP_SETPCAP); -} - -#endif /* def CONFIG_SECURITY_FILE_CAPABILITIES */ - -int cap_capset_check (struct task_struct *target, kernel_cap_t *effective, - kernel_cap_t *inheritable, kernel_cap_t *permitted) -{ - if (cap_block_setpcap(target)) { - return -EPERM; - } - if (cap_inh_is_capped() - && !cap_issubset(*inheritable, - cap_combine(target->cap_inheritable, - current->cap_permitted))) { + if (cap_inh_is_capped() && + !cap_issubset(*inheritable, + cap_combine(old->cap_inheritable, + old->cap_permitted))) /* incapable of using this inheritable set */ return -EPERM; - } + if (!cap_issubset(*inheritable, - cap_combine(target->cap_inheritable, - current->cap_bset))) { + cap_combine(old->cap_inheritable, + old->cap_bset))) /* no new pI capabilities outside bounding set */ return -EPERM; - } /* verify restrictions on target's new Permitted set */ - if (!cap_issubset (*permitted, - cap_combine (target->cap_permitted, - current->cap_permitted))) { + if (!cap_issubset(*permitted, old->cap_permitted)) return -EPERM; - } /* verify the _new_Effective_ is a subset of the _new_Permitted_ */ - if (!cap_issubset (*effective, *permitted)) { + if (!cap_issubset(*effective, *permitted)) return -EPERM; - } + new->cap_effective = *effective; + new->cap_inheritable = *inheritable; + new->cap_permitted = *permitted; return 0; } -void cap_capset_set (struct task_struct *target, kernel_cap_t *effective, - kernel_cap_t *inheritable, kernel_cap_t *permitted) -{ - target->cap_effective = *effective; - target->cap_inheritable = *inheritable; - target->cap_permitted = *permitted; -} - +/* + * Clear proposed capability sets for execve(). + */ static inline void bprm_clear_caps(struct linux_binprm *bprm) { - cap_clear(bprm->cap_post_exec_permitted); + cap_clear(bprm->cred->cap_permitted); bprm->cap_effective = false; } #ifdef CONFIG_SECURITY_FILE_CAPABILITIES +/** + * cap_inode_need_killpriv - Determine if inode change affects privileges + * @dentry: The inode/dentry in being changed with change marked ATTR_KILL_PRIV + * + * Determine if an inode having a change applied that's marked ATTR_KILL_PRIV + * affects the security markings on that inode, and if it is, should + * inode_killpriv() be invoked or the change rejected? + * + * Returns 0 if granted; +ve if granted, but inode_killpriv() is required; and + * -ve to deny the change. + */ int cap_inode_need_killpriv(struct dentry *dentry) { struct inode *inode = dentry->d_inode; @@ -192,6 +247,14 @@ int cap_inode_need_killpriv(struct dentry *dentry) return 1; } +/** + * cap_inode_killpriv - Erase the security markings on an inode + * @dentry: The inode/dentry to alter + * + * Erase the privilege-enhancing security markings on an inode. + * + * Returns 0 if successful, -ve on error. + */ int cap_inode_killpriv(struct dentry *dentry) { struct inode *inode = dentry->d_inode; @@ -202,19 +265,75 @@ int cap_inode_killpriv(struct dentry *dentry) return inode->i_op->removexattr(dentry, XATTR_NAME_CAPS); } -static inline int cap_from_disk(struct vfs_cap_data *caps, - struct linux_binprm *bprm, unsigned size) +/* + * Calculate the new process capability sets from the capability sets attached + * to a file. + */ +static inline int bprm_caps_from_vfs_caps(struct cpu_vfs_cap_data *caps, + struct linux_binprm *bprm, + bool *effective) { + struct cred *new = bprm->cred; + unsigned i; + int ret = 0; + + if (caps->magic_etc & VFS_CAP_FLAGS_EFFECTIVE) + *effective = true; + + CAP_FOR_EACH_U32(i) { + __u32 permitted = caps->permitted.cap[i]; + __u32 inheritable = caps->inheritable.cap[i]; + + /* + * pP' = (X & fP) | (pI & fI) + */ + new->cap_permitted.cap[i] = + (new->cap_bset.cap[i] & permitted) | + (new->cap_inheritable.cap[i] & inheritable); + + if (permitted & ~new->cap_permitted.cap[i]) + /* insufficient to execute correctly */ + ret = -EPERM; + } + + /* + * For legacy apps, with no internal support for recognizing they + * do not have enough capabilities, we return an error if they are + * missing some "forced" (aka file-permitted) capabilities. + */ + return *effective ? ret : 0; +} + +/* + * Extract the on-exec-apply capability sets for an executable file. + */ +int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) +{ + struct inode *inode = dentry->d_inode; __u32 magic_etc; unsigned tocopy, i; - int ret; + int size; + struct vfs_cap_data caps; + + memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); + + if (!inode || !inode->i_op || !inode->i_op->getxattr) + return -ENODATA; + + size = inode->i_op->getxattr((struct dentry *)dentry, XATTR_NAME_CAPS, &caps, + 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; - magic_etc = le32_to_cpu(caps->magic_etc); + cpu_caps->magic_etc = magic_etc = le32_to_cpu(caps.magic_etc); - switch ((magic_etc & VFS_CAP_REVISION_MASK)) { + switch (magic_etc & VFS_CAP_REVISION_MASK) { case VFS_CAP_REVISION_1: if (size != XATTR_CAPS_SZ_1) return -EINVAL; @@ -229,77 +348,48 @@ static inline int cap_from_disk(struct vfs_cap_data *caps, return -EINVAL; } - if (magic_etc & VFS_CAP_FLAGS_EFFECTIVE) { - bprm->cap_effective = true; - } else { - bprm->cap_effective = false; - } - - ret = 0; - CAP_FOR_EACH_U32(i) { - __u32 value_cpu; - - if (i >= tocopy) { - /* - * Legacy capability sets have no upper bits - */ - bprm->cap_post_exec_permitted.cap[i] = 0; - continue; - } - /* - * pP' = (X & fP) | (pI & fI) - */ - value_cpu = le32_to_cpu(caps->data[i].permitted); - bprm->cap_post_exec_permitted.cap[i] = - (current->cap_bset.cap[i] & value_cpu) | - (current->cap_inheritable.cap[i] & - le32_to_cpu(caps->data[i].inheritable)); - if (value_cpu & ~bprm->cap_post_exec_permitted.cap[i]) { - /* - * insufficient to execute correctly - */ - ret = -EPERM; - } + 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); } - /* - * For legacy apps, with no internal support for recognizing they - * do not have enough capabilities, we return an error if they are - * missing some "forced" (aka file-permitted) capabilities. - */ - return bprm->cap_effective ? ret : 0; + return 0; } -/* Locate any VFS capabilities: */ -static int get_file_caps(struct linux_binprm *bprm) +/* + * Attempt to get the on-exec apply capability sets for an executable file from + * its xattrs and, if present, apply them to the proposed credentials being + * constructed by execve(). + */ +static int get_file_caps(struct linux_binprm *bprm, bool *effective) { struct dentry *dentry; int rc = 0; - struct vfs_cap_data vcaps; - struct inode *inode; + struct cpu_vfs_cap_data vcaps; bprm_clear_caps(bprm); + if (!file_caps_enabled) + return 0; + if (bprm->file->f_vfsmnt->mnt_flags & MNT_NOSUID) return 0; dentry = dget(bprm->file->f_dentry); - inode = dentry->d_inode; - if (!inode->i_op || !inode->i_op->getxattr) - goto out; - rc = inode->i_op->getxattr(dentry, XATTR_NAME_CAPS, &vcaps, - XATTR_CAPS_SZ); - if (rc == -ENODATA || rc == -EOPNOTSUPP) { - /* no data, that's ok */ - rc = 0; + rc = get_vfs_caps_from_disk(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); + else if (rc == -ENODATA) + rc = 0; goto out; } - if (rc < 0) - goto out; - rc = cap_from_disk(&vcaps, bprm, rc); + rc = bprm_caps_from_vfs_caps(&vcaps, bprm, effective); if (rc == -EINVAL) printk(KERN_NOTICE "%s: cap_from_disk returned %d for %s\n", __func__, rc, bprm->filename); @@ -323,18 +413,57 @@ int cap_inode_killpriv(struct dentry *dentry) return 0; } -static inline int get_file_caps(struct linux_binprm *bprm) +int get_vfs_caps_from_disk(const struct dentry *dentry, struct cpu_vfs_cap_data *cpu_caps) +{ + memset(cpu_caps, 0, sizeof(struct cpu_vfs_cap_data)); + return -ENODATA; +} + +static inline int get_file_caps(struct linux_binprm *bprm, bool *effective) { bprm_clear_caps(bprm); return 0; } #endif -int cap_bprm_set_security (struct linux_binprm *bprm) +/* + * Determine whether a exec'ing process's new permitted capabilities should be + * limited to just what it already has. + * + * This prevents processes that are being ptraced from gaining access to + * CAP_SETPCAP, unless the process they're tracing already has it, and the + * binary they're executing has filecaps that elevate it. + * + * Returns 1 if they should be limited, 0 if they are not. + */ +static inline int cap_limit_ptraced_target(void) { +#ifndef CONFIG_SECURITY_FILE_CAPABILITIES + if (capable(CAP_SETPCAP)) + return 0; +#endif + return 1; +} + +/** + * cap_bprm_set_creds - Set up the proposed credentials for execve(). + * @bprm: The execution parameters, including the proposed creds + * + * Set up the proposed credentials for a new execution context being + * constructed by execve(). The proposed creds in @bprm->cred is altered, + * which won't take effect immediately. Returns 0 if successful, -ve on error. + */ +int cap_bprm_set_creds(struct linux_binprm *bprm) +{ + const struct cred *old = current_cred(); + struct cred *new = bprm->cred; + bool effective; int ret; - ret = get_file_caps(bprm); + effective = false; + ret = get_file_caps(bprm, &effective); + if (ret < 0) + return ret; if (!issecure(SECURE_NOROOT)) { /* @@ -342,75 +471,113 @@ int cap_bprm_set_security (struct linux_binprm *bprm) * executables under compatibility mode, we override the * capability sets for the file. * - * If only the real uid is 0, we do not set the effective - * bit. + * If only the real uid is 0, we do not set the effective bit. */ - if (bprm->e_uid == 0 || current->uid == 0) { + if (new->euid == 0 || new->uid == 0) { /* pP' = (cap_bset & ~0) | (pI & ~0) */ - bprm->cap_post_exec_permitted = cap_combine( - current->cap_bset, current->cap_inheritable - ); - bprm->cap_effective = (bprm->e_uid == 0); - ret = 0; + new->cap_permitted = cap_combine(old->cap_bset, + old->cap_inheritable); } + if (new->euid == 0) + effective = true; } - return ret; -} - -void cap_bprm_apply_creds (struct linux_binprm *bprm, int unsafe) -{ - if (bprm->e_uid != current->uid || bprm->e_gid != current->gid || - !cap_issubset(bprm->cap_post_exec_permitted, - current->cap_permitted)) { - set_dumpable(current->mm, suid_dumpable); - current->pdeath_signal = 0; - - if (unsafe & ~LSM_UNSAFE_PTRACE_CAP) { - if (!capable(CAP_SETUID)) { - bprm->e_uid = current->uid; - bprm->e_gid = current->gid; - } - if (cap_limit_ptraced_target()) { - bprm->cap_post_exec_permitted = cap_intersect( - bprm->cap_post_exec_permitted, - current->cap_permitted); - } + /* Don't let someone trace a set[ug]id/setpcap binary with the revised + * credentials unless they have the appropriate permit + */ + if ((new->euid != old->uid || + new->egid != old->gid || + !cap_issubset(new->cap_permitted, old->cap_permitted)) && + bprm->unsafe & ~LSM_UNSAFE_PTRACE_CAP) { + /* downgrade; they get no more than they had, and maybe less */ + if (!capable(CAP_SETUID)) { + new->euid = new->uid; + new->egid = new->gid; } + if (cap_limit_ptraced_target()) + new->cap_permitted = cap_intersect(new->cap_permitted, + old->cap_permitted); } - current->suid = current->euid = current->fsuid = bprm->e_uid; - current->sgid = current->egid = current->fsgid = bprm->e_gid; + new->suid = new->fsuid = new->euid; + new->sgid = new->fsgid = new->egid; - /* For init, we want to retain the capabilities set - * in the init_task struct. Thus we skip the usual - * capability rules */ + /* For init, we want to retain the capabilities set in the initial + * task. Thus we skip the usual capability rules + */ if (!is_global_init(current)) { - current->cap_permitted = bprm->cap_post_exec_permitted; - if (bprm->cap_effective) - current->cap_effective = bprm->cap_post_exec_permitted; + if (effective) + new->cap_effective = new->cap_permitted; else - cap_clear(current->cap_effective); + cap_clear(new->cap_effective); + } + bprm->cap_effective = effective; + + /* + * Audit candidate if current->cap_effective is set + * + * We do not bother to audit if 3 things are true: + * 1) cap_effective has all caps + * 2) we are root + * 3) root is supposed to have all caps (SECURE_NOROOT) + * Since this is just a normal root execing a process. + * + * Number 1 above might fail if you don't have a full bset, but I think + * that is interesting information to audit. + */ + if (!cap_isclear(new->cap_effective)) { + if (!cap_issubset(CAP_FULL_SET, new->cap_effective) || + new->euid != 0 || new->uid != 0 || + issecure(SECURE_NOROOT)) { + ret = audit_log_bprm_fcaps(bprm, new, old); + if (ret < 0) + return ret; + } } - /* AUD: Audit candidate if current->cap_effective is set */ - - current->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); + new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); + return 0; } -int cap_bprm_secureexec (struct linux_binprm *bprm) +/** + * cap_bprm_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 + * if it is not. + * + * 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) { - if (current->uid != 0) { + const struct cred *cred = current_cred(); + + if (cred->uid != 0) { if (bprm->cap_effective) return 1; - if (!cap_isclear(bprm->cap_post_exec_permitted)) + if (!cap_isclear(cred->cap_permitted)) return 1; } - return (current->euid != current->uid || - current->egid != current->gid); + return (cred->euid != cred->uid || + cred->egid != cred->gid); } +/** + * cap_inode_setxattr - Determine whether an xattr may be altered + * @dentry: The inode/dentry being altered + * @name: The name of the xattr to be changed + * @value: The value that the xattr will be changed to + * @size: The size of value + * @flags: The replacement flag + * + * Determine whether an xattr may be altered or set on an inode, returning 0 if + * permission is granted, -ve if denied. + * + * This is used to make sure security xattrs don't get updated or set by those + * who aren't privileged to do so. + */ int cap_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { @@ -418,28 +585,42 @@ int cap_inode_setxattr(struct dentry *dentry, const char *name, if (!capable(CAP_SETFCAP)) return -EPERM; return 0; - } else if (!strncmp(name, XATTR_SECURITY_PREFIX, + } + + if (!strncmp(name, XATTR_SECURITY_PREFIX, sizeof(XATTR_SECURITY_PREFIX) - 1) && !capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } +/** + * cap_inode_removexattr - Determine whether an xattr may be removed + * @dentry: The inode/dentry being altered + * @name: The name of the xattr to be changed + * + * Determine whether an xattr may be removed from an inode, returning 0 if + * permission is granted, -ve if denied. + * + * This is used to make sure security xattrs don't get removed by those who + * aren't privileged to remove them. + */ int cap_inode_removexattr(struct dentry *dentry, const char *name) { if (!strcmp(name, XATTR_NAME_CAPS)) { if (!capable(CAP_SETFCAP)) return -EPERM; return 0; - } else if (!strncmp(name, XATTR_SECURITY_PREFIX, + } + + if (!strncmp(name, XATTR_SECURITY_PREFIX, sizeof(XATTR_SECURITY_PREFIX) - 1) && !capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } -/* moved from kernel/sys.c. */ -/* +/* * cap_emulate_setxuid() fixes the effective / permitted capabilities of * a process after a call to setuid, setreuid, or setresuid. * @@ -453,10 +634,10 @@ int cap_inode_removexattr(struct dentry *dentry, const char *name) * 3) When set*uiding _from_ euid != 0 _to_ euid == 0, the effective * capabilities are set to the permitted capabilities. * - * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should + * fsuid is handled elsewhere. fsuid == 0 and {r,e,s}uid!= 0 should * never happen. * - * -astor + * -astor * * cevans - New behaviour, Oct '99 * A process may, via prctl(), elect to keep its capabilities when it @@ -468,61 +649,60 @@ int cap_inode_removexattr(struct dentry *dentry, const char *name) * files.. * Thanks to Olaf Kirch and Peter Benie for spotting this. */ -static inline void cap_emulate_setxuid (int old_ruid, int old_euid, - int old_suid) +static inline void cap_emulate_setxuid(struct cred *new, const struct cred *old) { - if ((old_ruid == 0 || old_euid == 0 || old_suid == 0) && - (current->uid != 0 && current->euid != 0 && current->suid != 0) && + if ((old->uid == 0 || old->euid == 0 || old->suid == 0) && + (new->uid != 0 && new->euid != 0 && new->suid != 0) && !issecure(SECURE_KEEP_CAPS)) { - cap_clear (current->cap_permitted); - cap_clear (current->cap_effective); - } - if (old_euid == 0 && current->euid != 0) { - cap_clear (current->cap_effective); - } - if (old_euid != 0 && current->euid == 0) { - current->cap_effective = current->cap_permitted; + cap_clear(new->cap_permitted); + cap_clear(new->cap_effective); } + if (old->euid == 0 && new->euid != 0) + cap_clear(new->cap_effective); + if (old->euid != 0 && new->euid == 0) + new->cap_effective = new->cap_permitted; } -int cap_task_post_setuid (uid_t old_ruid, uid_t old_euid, uid_t old_suid, - int flags) +/** + * cap_task_fix_setuid - Fix up the results of setuid() call + * @new: The proposed credentials + * @old: The current task's current credentials + * @flags: Indications of what has changed + * + * Fix up the results of setuid() call before the credential changes are + * actually applied, returning 0 to grant the changes, -ve to deny them. + */ +int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags) { switch (flags) { case LSM_SETID_RE: case LSM_SETID_ID: case LSM_SETID_RES: - /* Copied from kernel/sys.c:setreuid/setuid/setresuid. */ - if (!issecure (SECURE_NO_SETUID_FIXUP)) { - cap_emulate_setxuid (old_ruid, old_euid, old_suid); + /* juggle the capabilities to follow [RES]UID changes unless + * otherwise suppressed */ + if (!issecure(SECURE_NO_SETUID_FIXUP)) + cap_emulate_setxuid(new, old); + break; + + case LSM_SETID_FS: + /* juggle the capabilties to follow FSUID changes, unless + * otherwise suppressed + * + * FIXME - is fsuser used for all CAP_FS_MASK capabilities? + * if not, we might be a bit too harsh here. + */ + if (!issecure(SECURE_NO_SETUID_FIXUP)) { + if (old->fsuid == 0 && new->fsuid != 0) + new->cap_effective = + cap_drop_fs_set(new->cap_effective); + + if (old->fsuid != 0 && new->fsuid == 0) + new->cap_effective = + cap_raise_fs_set(new->cap_effective, + new->cap_permitted); } break; - case LSM_SETID_FS: - { - uid_t old_fsuid = old_ruid; - /* Copied from kernel/sys.c:setfsuid. */ - - /* - * FIXME - is fsuser used for all CAP_FS_MASK capabilities? - * if not, we might be a bit too harsh here. - */ - - if (!issecure (SECURE_NO_SETUID_FIXUP)) { - if (old_fsuid == 0 && current->fsuid != 0) { - current->cap_effective = - cap_drop_fs_set( - current->cap_effective); - } - if (old_fsuid != 0 && current->fsuid == 0) { - current->cap_effective = - cap_raise_fs_set( - current->cap_effective, - current->cap_permitted); - } - } - break; - } default: return -EINVAL; } @@ -543,42 +723,71 @@ int cap_task_post_setuid (uid_t old_ruid, uid_t old_euid, uid_t old_suid, */ static int cap_safe_nice(struct task_struct *p) { - if (!cap_issubset(p->cap_permitted, current->cap_permitted) && - !capable(CAP_SYS_NICE)) + int is_subset; + + rcu_read_lock(); + is_subset = cap_issubset(__task_cred(p)->cap_permitted, + current_cred()->cap_permitted); + rcu_read_unlock(); + + if (!is_subset && !capable(CAP_SYS_NICE)) return -EPERM; return 0; } -int cap_task_setscheduler (struct task_struct *p, int policy, +/** + * cap_task_setscheduler - Detemine if scheduler policy change is permitted + * @p: The task to affect + * @policy: The policy to effect + * @lp: The parameters to the scheduling policy + * + * Detemine if the requested scheduler policy change is permitted for the + * specified task, returning 0 if permission is granted, -ve if denied. + */ +int cap_task_setscheduler(struct task_struct *p, int policy, struct sched_param *lp) { return cap_safe_nice(p); } -int cap_task_setioprio (struct task_struct *p, int ioprio) +/** + * cap_task_ioprio - Detemine if I/O priority change is permitted + * @p: The task to affect + * @ioprio: The I/O priority to set + * + * Detemine if the requested I/O priority change is permitted for the specified + * task, returning 0 if permission is granted, -ve if denied. + */ +int cap_task_setioprio(struct task_struct *p, int ioprio) { return cap_safe_nice(p); } -int cap_task_setnice (struct task_struct *p, int nice) +/** + * cap_task_ioprio - Detemine if task priority change is permitted + * @p: The task to affect + * @nice: The nice value to set + * + * Detemine if the requested task priority change is permitted for the + * specified task, returning 0 if permission is granted, -ve if denied. + */ +int cap_task_setnice(struct task_struct *p, int nice) { return cap_safe_nice(p); } /* - * called from kernel/sys.c for prctl(PR_CABSET_DROP) - * done without task_capability_lock() because it introduces - * no new races - i.e. only another task doing capget() on - * this task could get inconsistent info. There can be no - * racing writer bc a task can only change its own caps. + * Implement PR_CAPBSET_DROP. Attempt to remove the specified capability from + * the current task's bounding set. Returns 0 on success, -ve on error. */ -static long cap_prctl_drop(unsigned long cap) +static long cap_prctl_drop(struct cred *new, unsigned long cap) { if (!capable(CAP_SETPCAP)) return -EPERM; if (!cap_valid(cap)) return -EINVAL; - cap_lower(current->cap_bset, cap); + + cap_lower(new->cap_bset, cap); return 0; } @@ -598,22 +807,42 @@ int cap_task_setnice (struct task_struct *p, int nice) } #endif +/** + * cap_task_prctl - Implement process control functions for this security module + * @option: The process control function requested + * @arg2, @arg3, @arg4, @arg5: The argument data for this function + * + * Allow process control functions (sys_prctl()) to alter capabilities; may + * also deny access to other functions not otherwise implemented here. + * + * Returns 0 or +ve on success, -ENOSYS if this function is not implemented + * here, other -ve on error. If -ENOSYS is returned, sys_prctl() and other LSM + * modules will consider performing the function. + */ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5, long *rc_p) + unsigned long arg4, unsigned long arg5) { + struct cred *new; long error = 0; + new = prepare_creds(); + if (!new) + return -ENOMEM; + switch (option) { case PR_CAPBSET_READ: + error = -EINVAL; if (!cap_valid(arg2)) - error = -EINVAL; - else - error = !!cap_raised(current->cap_bset, arg2); - break; + goto error; + error = !!cap_raised(new->cap_bset, arg2); + goto no_change; + #ifdef CONFIG_SECURITY_FILE_CAPABILITIES case PR_CAPBSET_DROP: - error = cap_prctl_drop(arg2); - break; + error = cap_prctl_drop(new, arg2); + if (error < 0) + goto error; + goto changed; /* * The next four prctl's remain to assist with transitioning a @@ -635,12 +864,12 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, * capability-based-privilege environment. */ case PR_SET_SECUREBITS: - if ((((current->securebits & SECURE_ALL_LOCKS) >> 1) - & (current->securebits ^ arg2)) /*[1]*/ - || ((current->securebits & SECURE_ALL_LOCKS - & ~arg2)) /*[2]*/ - || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ - || (cap_capable(current, CAP_SETPCAP) != 0)) { /*[4]*/ + error = -EPERM; + if ((((new->securebits & SECURE_ALL_LOCKS) >> 1) + & (new->securebits ^ arg2)) /*[1]*/ + || ((new->securebits & SECURE_ALL_LOCKS & ~arg2)) /*[2]*/ + || (arg2 & ~(SECURE_ALL_LOCKS | SECURE_ALL_BITS)) /*[3]*/ + || (cap_capable(current, CAP_SETPCAP, SECURITY_CAP_AUDIT) != 0) /*[4]*/ /* * [1] no changing of bits that are locked * [2] no unlocking of locks @@ -648,65 +877,80 @@ int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3, * [4] doing anything requires privilege (go read about * the "sendmail capabilities bug") */ - error = -EPERM; /* cannot change a locked bit */ - } else { - current->securebits = arg2; - } - break; + ) + /* cannot change a locked bit */ + goto error; + new->securebits = arg2; + goto changed; + case PR_GET_SECUREBITS: - error = current->securebits; - break; + error = new->securebits; + goto no_change; #endif /* def CONFIG_SECURITY_FILE_CAPABILITIES */ case PR_GET_KEEPCAPS: if (issecure(SECURE_KEEP_CAPS)) error = 1; - break; + goto no_change; + case PR_SET_KEEPCAPS: + error = -EINVAL; if (arg2 > 1) /* Note, we rely on arg2 being unsigned here */ - error = -EINVAL; - else if (issecure(SECURE_KEEP_CAPS_LOCKED)) - error = -EPERM; - else if (arg2) - current->securebits |= issecure_mask(SECURE_KEEP_CAPS); + goto error; + error = -EPERM; + if (issecure(SECURE_KEEP_CAPS_LOCKED)) + goto error; + if (arg2) + new->securebits |= issecure_mask(SECURE_KEEP_CAPS); else - current->securebits &= - ~issecure_mask(SECURE_KEEP_CAPS); - break; + new->securebits &= ~issecure_mask(SECURE_KEEP_CAPS); + goto changed; default: /* No functionality available - continue with default */ - return 0; + error = -ENOSYS; + goto error; } /* Functionality provided */ - *rc_p = error; - return 1; +changed: + return commit_creds(new); + +no_change: + error = 0; +error: + abort_creds(new); + return error; } -void cap_task_reparent_to_init (struct task_struct *p) -{ - cap_set_init_eff(p->cap_effective); - cap_clear(p->cap_inheritable); - cap_set_full(p->cap_permitted); - p->securebits = SECUREBITS_DEFAULT; - return; -} - -int cap_syslog (int type) +/** + * cap_syslog - Determine whether syslog function is permitted + * @type: Function requested + * + * Determine whether the current process is permitted to use a particular + * syslog function, returning 0 if permission is granted, -ve if not. + */ +int cap_syslog(int type) { if ((type != 3 && type != 10) && !capable(CAP_SYS_ADMIN)) return -EPERM; return 0; } +/** + * cap_vm_enough_memory - Determine whether a new virtual mapping is permitted + * @mm: The VM space in which the new mapping is to be made + * @pages: The size of the mapping + * + * Determine whether the allocation of a new virtual mapping by the current + * task is permitted, returning 0 if permission is granted, -ve if not. + */ int cap_vm_enough_memory(struct mm_struct *mm, long pages) { int cap_sys_admin = 0; - if (cap_capable(current, CAP_SYS_ADMIN) == 0) + if (cap_capable(current, CAP_SYS_ADMIN, SECURITY_CAP_NOAUDIT) == 0) cap_sys_admin = 1; return __vm_enough_memory(mm, pages, cap_sys_admin); } - diff --git a/security/keys/internal.h b/security/keys/internal.h index 239098f0fd7..81932abefe7 100644 --- a/security/keys/internal.h +++ b/security/keys/internal.h @@ -12,8 +12,8 @@ #ifndef _INTERNAL_H #define _INTERNAL_H +#include #include -#include static inline __attribute__((format(printf, 1, 2))) void no_printk(const char *fmt, ...) @@ -26,7 +26,7 @@ void no_printk(const char *fmt, ...) #define kleave(FMT, ...) \ printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__) #define kdebug(FMT, ...) \ - printk(KERN_DEBUG "xxx" FMT"yyy\n", ##__VA_ARGS__) + printk(KERN_DEBUG " "FMT"\n", ##__VA_ARGS__) #else #define kenter(FMT, ...) \ no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__) @@ -82,6 +82,9 @@ extern struct mutex key_construction_mutex; extern wait_queue_head_t request_key_conswq; +extern struct key_type *key_type_lookup(const char *type); +extern void key_type_put(struct key_type *ktype); + extern int __key_link(struct key *keyring, struct key *key); extern key_ref_t __keyring_search_one(key_ref_t keyring_ref, @@ -95,7 +98,7 @@ extern struct key *keyring_search_instkey(struct key *keyring, typedef int (*key_match_func_t)(const struct key *, const void *); extern key_ref_t keyring_search_aux(key_ref_t keyring_ref, - struct task_struct *tsk, + const struct cred *cred, struct key_type *type, const void *description, key_match_func_t match); @@ -103,13 +106,13 @@ extern key_ref_t keyring_search_aux(key_ref_t keyring_ref, extern key_ref_t search_process_keyrings(struct key_type *type, const void *description, key_match_func_t match, - struct task_struct *tsk); + const struct cred *cred); extern struct key *find_keyring_by_name(const char *name, bool skip_perm_check); -extern int install_user_keyrings(struct task_struct *tsk); -extern int install_thread_keyring(struct task_struct *tsk); -extern int install_process_keyring(struct task_struct *tsk); +extern int install_user_keyrings(void); +extern int install_thread_keyring_to_cred(struct cred *); +extern int install_process_keyring_to_cred(struct cred *); extern struct key *request_key_and_link(struct key_type *type, const char *description, @@ -119,12 +122,39 @@ extern struct key *request_key_and_link(struct key_type *type, struct key *dest_keyring, unsigned long flags); +extern key_ref_t lookup_user_key(key_serial_t id, int create, int partial, + key_perm_t perm); + +extern long join_session_keyring(const char *name); + +/* + * check to see whether permission is granted to use a key in the desired way + */ +extern int key_task_permission(const key_ref_t key_ref, + const struct cred *cred, + key_perm_t perm); + +static inline int key_permission(const key_ref_t key_ref, key_perm_t perm) +{ + return key_task_permission(key_ref, current_cred(), perm); +} + +/* required permissions */ +#define KEY_VIEW 0x01 /* require permission to view attributes */ +#define KEY_READ 0x02 /* require permission to read content */ +#define KEY_WRITE 0x04 /* require permission to update / modify */ +#define KEY_SEARCH 0x08 /* require permission to search (keyring) or find (key) */ +#define KEY_LINK 0x10 /* require permission to link */ +#define KEY_SETATTR 0x20 /* require permission to change attributes */ +#define KEY_ALL 0x3f /* all the above permissions */ + /* * request_key authorisation */ struct request_key_auth { struct key *target_key; - struct task_struct *context; + struct key *dest_keyring; + const struct cred *cred; void *callout_info; size_t callout_len; pid_t pid; @@ -133,7 +163,8 @@ struct request_key_auth { extern struct key_type key_type_request_key_auth; extern struct key *request_key_auth_new(struct key *target, const void *callout_info, - size_t callout_len); + size_t callout_len, + struct key *dest_keyring); extern struct key *key_get_instantiation_authkey(key_serial_t target_id); diff --git a/security/keys/key.c b/security/keys/key.c index 14948cf83ef..f76c8a546fd 100644 --- a/security/keys/key.c +++ b/security/keys/key.c @@ -218,7 +218,7 @@ serial_exists: * instantiate the key or discard it before returning */ struct key *key_alloc(struct key_type *type, const char *desc, - uid_t uid, gid_t gid, struct task_struct *ctx, + uid_t uid, gid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags) { struct key_user *user = NULL; @@ -294,7 +294,7 @@ struct key *key_alloc(struct key_type *type, const char *desc, #endif /* let the security module know about the key */ - ret = security_key_alloc(key, ctx, flags); + ret = security_key_alloc(key, cred, flags); if (ret < 0) goto security_error; @@ -391,7 +391,7 @@ static int __key_instantiate_and_link(struct key *key, const void *data, size_t datalen, struct key *keyring, - struct key *instkey) + struct key *authkey) { int ret, awaken; @@ -421,8 +421,8 @@ static int __key_instantiate_and_link(struct key *key, ret = __key_link(keyring, key); /* disable the authorisation key */ - if (instkey) - key_revoke(instkey); + if (authkey) + key_revoke(authkey); } } @@ -444,14 +444,14 @@ int key_instantiate_and_link(struct key *key, const void *data, size_t datalen, struct key *keyring, - struct key *instkey) + struct key *authkey) { int ret; if (keyring) down_write(&keyring->sem); - ret = __key_instantiate_and_link(key, data, datalen, keyring, instkey); + ret = __key_instantiate_and_link(key, data, datalen, keyring, authkey); if (keyring) up_write(&keyring->sem); @@ -469,7 +469,7 @@ EXPORT_SYMBOL(key_instantiate_and_link); int key_negate_and_link(struct key *key, unsigned timeout, struct key *keyring, - struct key *instkey) + struct key *authkey) { struct timespec now; int ret, awaken; @@ -504,8 +504,8 @@ int key_negate_and_link(struct key *key, ret = __key_link(keyring, key); /* disable the authorisation key */ - if (instkey) - key_revoke(instkey); + if (authkey) + key_revoke(authkey); } mutex_unlock(&key_construction_mutex); @@ -743,6 +743,7 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref, key_perm_t perm, unsigned long flags) { + const struct cred *cred = current_cred(); struct key_type *ktype; struct key *keyring, *key = NULL; key_ref_t key_ref; @@ -802,8 +803,8 @@ key_ref_t key_create_or_update(key_ref_t keyring_ref, } /* allocate a new key */ - key = key_alloc(ktype, description, current->fsuid, current->fsgid, - current, perm, flags); + key = key_alloc(ktype, description, cred->fsuid, cred->fsgid, cred, + perm, flags); if (IS_ERR(key)) { key_ref = ERR_CAST(key); goto error_3; diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c index acc9c89e40a..7c72baa02f2 100644 --- a/security/keys/keyctl.c +++ b/security/keys/keyctl.c @@ -103,7 +103,7 @@ asmlinkage long sys_add_key(const char __user *_type, } /* find the target keyring (which must be writable) */ - keyring_ref = lookup_user_key(NULL, ringid, 1, 0, KEY_WRITE); + keyring_ref = lookup_user_key(ringid, 1, 0, KEY_WRITE); if (IS_ERR(keyring_ref)) { ret = PTR_ERR(keyring_ref); goto error3; @@ -185,7 +185,7 @@ asmlinkage long sys_request_key(const char __user *_type, /* get the destination keyring if specified */ dest_ref = NULL; if (destringid) { - dest_ref = lookup_user_key(NULL, destringid, 1, 0, KEY_WRITE); + dest_ref = lookup_user_key(destringid, 1, 0, KEY_WRITE); if (IS_ERR(dest_ref)) { ret = PTR_ERR(dest_ref); goto error3; @@ -235,7 +235,7 @@ long keyctl_get_keyring_ID(key_serial_t id, int create) key_ref_t key_ref; long ret; - key_ref = lookup_user_key(NULL, id, create, 0, KEY_SEARCH); + key_ref = lookup_user_key(id, create, 0, KEY_SEARCH); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error; @@ -308,7 +308,7 @@ long keyctl_update_key(key_serial_t id, } /* find the target key (which must be writable) */ - key_ref = lookup_user_key(NULL, id, 0, 0, KEY_WRITE); + key_ref = lookup_user_key(id, 0, 0, KEY_WRITE); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error2; @@ -336,7 +336,7 @@ long keyctl_revoke_key(key_serial_t id) key_ref_t key_ref; long ret; - key_ref = lookup_user_key(NULL, id, 0, 0, KEY_WRITE); + key_ref = lookup_user_key(id, 0, 0, KEY_WRITE); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error; @@ -362,7 +362,7 @@ long keyctl_keyring_clear(key_serial_t ringid) key_ref_t keyring_ref; long ret; - keyring_ref = lookup_user_key(NULL, ringid, 1, 0, KEY_WRITE); + keyring_ref = lookup_user_key(ringid, 1, 0, KEY_WRITE); if (IS_ERR(keyring_ref)) { ret = PTR_ERR(keyring_ref); goto error; @@ -388,13 +388,13 @@ long keyctl_keyring_link(key_serial_t id, key_serial_t ringid) key_ref_t keyring_ref, key_ref; long ret; - keyring_ref = lookup_user_key(NULL, ringid, 1, 0, KEY_WRITE); + keyring_ref = lookup_user_key(ringid, 1, 0, KEY_WRITE); if (IS_ERR(keyring_ref)) { ret = PTR_ERR(keyring_ref); goto error; } - key_ref = lookup_user_key(NULL, id, 1, 0, KEY_LINK); + key_ref = lookup_user_key(id, 1, 0, KEY_LINK); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error2; @@ -422,13 +422,13 @@ long keyctl_keyring_unlink(key_serial_t id, key_serial_t ringid) key_ref_t keyring_ref, key_ref; long ret; - keyring_ref = lookup_user_key(NULL, ringid, 0, 0, KEY_WRITE); + keyring_ref = lookup_user_key(ringid, 0, 0, KEY_WRITE); if (IS_ERR(keyring_ref)) { ret = PTR_ERR(keyring_ref); goto error; } - key_ref = lookup_user_key(NULL, id, 0, 0, 0); + key_ref = lookup_user_key(id, 0, 0, 0); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error2; @@ -464,7 +464,7 @@ long keyctl_describe_key(key_serial_t keyid, char *tmpbuf; long ret; - key_ref = lookup_user_key(NULL, keyid, 0, 1, KEY_VIEW); + key_ref = lookup_user_key(keyid, 0, 1, KEY_VIEW); if (IS_ERR(key_ref)) { /* viewing a key under construction is permitted if we have the * authorisation token handy */ @@ -472,7 +472,7 @@ long keyctl_describe_key(key_serial_t keyid, instkey = key_get_instantiation_authkey(keyid); if (!IS_ERR(instkey)) { key_put(instkey); - key_ref = lookup_user_key(NULL, keyid, + key_ref = lookup_user_key(keyid, 0, 1, 0); if (!IS_ERR(key_ref)) goto okay; @@ -557,7 +557,7 @@ long keyctl_keyring_search(key_serial_t ringid, } /* get the keyring at which to begin the search */ - keyring_ref = lookup_user_key(NULL, ringid, 0, 0, KEY_SEARCH); + keyring_ref = lookup_user_key(ringid, 0, 0, KEY_SEARCH); if (IS_ERR(keyring_ref)) { ret = PTR_ERR(keyring_ref); goto error2; @@ -566,7 +566,7 @@ long keyctl_keyring_search(key_serial_t ringid, /* get the destination keyring if specified */ dest_ref = NULL; if (destringid) { - dest_ref = lookup_user_key(NULL, destringid, 1, 0, KEY_WRITE); + dest_ref = lookup_user_key(destringid, 1, 0, KEY_WRITE); if (IS_ERR(dest_ref)) { ret = PTR_ERR(dest_ref); goto error3; @@ -636,7 +636,7 @@ long keyctl_read_key(key_serial_t keyid, char __user *buffer, size_t buflen) long ret; /* find the key first */ - key_ref = lookup_user_key(NULL, keyid, 0, 0, 0); + key_ref = lookup_user_key(keyid, 0, 0, 0); if (IS_ERR(key_ref)) { ret = -ENOKEY; goto error; @@ -699,7 +699,7 @@ long keyctl_chown_key(key_serial_t id, uid_t uid, gid_t gid) if (uid == (uid_t) -1 && gid == (gid_t) -1) goto error; - key_ref = lookup_user_key(NULL, id, 1, 1, KEY_SETATTR); + key_ref = lookup_user_key(id, 1, 1, KEY_SETATTR); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error; @@ -804,7 +804,7 @@ long keyctl_setperm_key(key_serial_t id, key_perm_t perm) if (perm & ~(KEY_POS_ALL | KEY_USR_ALL | KEY_GRP_ALL | KEY_OTH_ALL)) goto error; - key_ref = lookup_user_key(NULL, id, 1, 1, KEY_SETATTR); + key_ref = lookup_user_key(id, 1, 1, KEY_SETATTR); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error; @@ -817,7 +817,7 @@ long keyctl_setperm_key(key_serial_t id, key_perm_t perm) down_write(&key->sem); /* if we're not the sysadmin, we can only change a key that we own */ - if (capable(CAP_SYS_ADMIN) || key->uid == current->fsuid) { + if (capable(CAP_SYS_ADMIN) || key->uid == current_fsuid()) { key->perm = perm; ret = 0; } @@ -829,6 +829,60 @@ error: } /* end keyctl_setperm_key() */ +/* + * get the destination keyring for instantiation + */ +static long get_instantiation_keyring(key_serial_t ringid, + struct request_key_auth *rka, + struct key **_dest_keyring) +{ + key_ref_t dkref; + + /* just return a NULL pointer if we weren't asked to make a link */ + if (ringid == 0) { + *_dest_keyring = NULL; + return 0; + } + + /* if a specific keyring is nominated by ID, then use that */ + if (ringid > 0) { + dkref = lookup_user_key(ringid, 1, 0, KEY_WRITE); + if (IS_ERR(dkref)) + return PTR_ERR(dkref); + *_dest_keyring = key_ref_to_ptr(dkref); + return 0; + } + + if (ringid == KEY_SPEC_REQKEY_AUTH_KEY) + return -EINVAL; + + /* otherwise specify the destination keyring recorded in the + * authorisation key (any KEY_SPEC_*_KEYRING) */ + if (ringid >= KEY_SPEC_REQUESTOR_KEYRING) { + *_dest_keyring = rka->dest_keyring; + return 0; + } + + return -ENOKEY; +} + +/* + * change the request_key authorisation key on the current process + */ +static int keyctl_change_reqkey_auth(struct key *key) +{ + struct cred *new; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + + key_put(new->request_key_auth); + new->request_key_auth = key_get(key); + + return commit_creds(new); +} + /*****************************************************************************/ /* * instantiate the key with the specified payload, and, if one is given, link @@ -839,13 +893,15 @@ long keyctl_instantiate_key(key_serial_t id, size_t plen, key_serial_t ringid) { + const struct cred *cred = current_cred(); struct request_key_auth *rka; - struct key *instkey; - key_ref_t keyring_ref; + struct key *instkey, *dest_keyring; void *payload; long ret; bool vm = false; + kenter("%d,,%zu,%d", id, plen, ringid); + ret = -EINVAL; if (plen > 1024 * 1024 - 1) goto error; @@ -853,7 +909,7 @@ long keyctl_instantiate_key(key_serial_t id, /* the appropriate instantiation authorisation key must have been * assumed before calling this */ ret = -EPERM; - instkey = current->request_key_auth; + instkey = cred->request_key_auth; if (!instkey) goto error; @@ -883,28 +939,20 @@ long keyctl_instantiate_key(key_serial_t id, /* find the destination keyring amongst those belonging to the * requesting task */ - keyring_ref = NULL; - if (ringid) { - keyring_ref = lookup_user_key(rka->context, ringid, 1, 0, - KEY_WRITE); - if (IS_ERR(keyring_ref)) { - ret = PTR_ERR(keyring_ref); - goto error2; - } - } + ret = get_instantiation_keyring(ringid, rka, &dest_keyring); + if (ret < 0) + goto error2; /* instantiate the key and link it into a keyring */ ret = key_instantiate_and_link(rka->target_key, payload, plen, - key_ref_to_ptr(keyring_ref), instkey); + dest_keyring, instkey); - key_ref_put(keyring_ref); + key_put(dest_keyring); /* discard the assumed authority if it's just been disabled by * instantiation of the key */ - if (ret == 0) { - key_put(current->request_key_auth); - current->request_key_auth = NULL; - } + if (ret == 0) + keyctl_change_reqkey_auth(NULL); error2: if (!vm) @@ -923,15 +971,17 @@ error: */ long keyctl_negate_key(key_serial_t id, unsigned timeout, key_serial_t ringid) { + const struct cred *cred = current_cred(); struct request_key_auth *rka; - struct key *instkey; - key_ref_t keyring_ref; + struct key *instkey, *dest_keyring; long ret; + kenter("%d,%u,%d", id, timeout, ringid); + /* the appropriate instantiation authorisation key must have been * assumed before calling this */ ret = -EPERM; - instkey = current->request_key_auth; + instkey = cred->request_key_auth; if (!instkey) goto error; @@ -941,27 +991,20 @@ long keyctl_negate_key(key_serial_t id, unsigned timeout, key_serial_t ringid) /* find the destination keyring if present (which must also be * writable) */ - keyring_ref = NULL; - if (ringid) { - keyring_ref = lookup_user_key(NULL, ringid, 1, 0, KEY_WRITE); - if (IS_ERR(keyring_ref)) { - ret = PTR_ERR(keyring_ref); - goto error; - } - } + ret = get_instantiation_keyring(ringid, rka, &dest_keyring); + if (ret < 0) + goto error; /* instantiate the key and link it into a keyring */ ret = key_negate_and_link(rka->target_key, timeout, - key_ref_to_ptr(keyring_ref), instkey); + dest_keyring, instkey); - key_ref_put(keyring_ref); + key_put(dest_keyring); /* discard the assumed authority if it's just been disabled by * instantiation of the key */ - if (ret == 0) { - key_put(current->request_key_auth); - current->request_key_auth = NULL; - } + if (ret == 0) + keyctl_change_reqkey_auth(NULL); error: return ret; @@ -975,35 +1018,56 @@ error: */ long keyctl_set_reqkey_keyring(int reqkey_defl) { - int ret; + struct cred *new; + int ret, old_setting; + + old_setting = current_cred_xxx(jit_keyring); + + if (reqkey_defl == KEY_REQKEY_DEFL_NO_CHANGE) + return old_setting; + + new = prepare_creds(); + if (!new) + return -ENOMEM; switch (reqkey_defl) { case KEY_REQKEY_DEFL_THREAD_KEYRING: - ret = install_thread_keyring(current); + ret = install_thread_keyring_to_cred(new); if (ret < 0) - return ret; + goto error; goto set; case KEY_REQKEY_DEFL_PROCESS_KEYRING: - ret = install_process_keyring(current); - if (ret < 0) - return ret; + ret = install_process_keyring_to_cred(new); + if (ret < 0) { + if (ret != -EEXIST) + goto error; + ret = 0; + } + goto set; case KEY_REQKEY_DEFL_DEFAULT: case KEY_REQKEY_DEFL_SESSION_KEYRING: case KEY_REQKEY_DEFL_USER_KEYRING: case KEY_REQKEY_DEFL_USER_SESSION_KEYRING: - set: - current->jit_keyring = reqkey_defl; + case KEY_REQKEY_DEFL_REQUESTOR_KEYRING: + goto set; case KEY_REQKEY_DEFL_NO_CHANGE: - return current->jit_keyring; - case KEY_REQKEY_DEFL_GROUP_KEYRING: default: - return -EINVAL; + ret = -EINVAL; + goto error; } +set: + new->jit_keyring = reqkey_defl; + commit_creds(new); + return old_setting; +error: + abort_creds(new); + return -EINVAL; + } /* end keyctl_set_reqkey_keyring() */ /*****************************************************************************/ @@ -1018,7 +1082,7 @@ long keyctl_set_timeout(key_serial_t id, unsigned timeout) time_t expiry; long ret; - key_ref = lookup_user_key(NULL, id, 1, 1, KEY_SETATTR); + key_ref = lookup_user_key(id, 1, 1, KEY_SETATTR); if (IS_ERR(key_ref)) { ret = PTR_ERR(key_ref); goto error; @@ -1062,9 +1126,7 @@ long keyctl_assume_authority(key_serial_t id) /* we divest ourselves of authority if given an ID of 0 */ if (id == 0) { - key_put(current->request_key_auth); - current->request_key_auth = NULL; - ret = 0; + ret = keyctl_change_reqkey_auth(NULL); goto error; } @@ -1079,10 +1141,12 @@ long keyctl_assume_authority(key_serial_t id) goto error; } - key_put(current->request_key_auth); - current->request_key_auth = authkey; - ret = authkey->serial; + ret = keyctl_change_reqkey_auth(authkey); + if (ret < 0) + goto error; + key_put(authkey); + ret = authkey->serial; error: return ret; @@ -1105,7 +1169,7 @@ long keyctl_get_security(key_serial_t keyid, char *context; long ret; - key_ref = lookup_user_key(NULL, keyid, 0, 1, KEY_VIEW); + key_ref = lookup_user_key(keyid, 0, 1, KEY_VIEW); if (IS_ERR(key_ref)) { if (PTR_ERR(key_ref) != -EACCES) return PTR_ERR(key_ref); @@ -1117,7 +1181,7 @@ long keyctl_get_security(key_serial_t keyid, return PTR_ERR(key_ref); key_put(instkey); - key_ref = lookup_user_key(NULL, keyid, 0, 1, 0); + key_ref = lookup_user_key(keyid, 0, 1, 0); if (IS_ERR(key_ref)) return PTR_ERR(key_ref); } diff --git a/security/keys/keyring.c b/security/keys/keyring.c index a9ab8affc09..ed851574d07 100644 --- a/security/keys/keyring.c +++ b/security/keys/keyring.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include "internal.h" @@ -244,14 +245,14 @@ static long keyring_read(const struct key *keyring, * allocate a keyring and link into the destination keyring */ struct key *keyring_alloc(const char *description, uid_t uid, gid_t gid, - struct task_struct *ctx, unsigned long flags, + const struct cred *cred, unsigned long flags, struct key *dest) { struct key *keyring; int ret; keyring = key_alloc(&key_type_keyring, description, - uid, gid, ctx, + uid, gid, cred, (KEY_POS_ALL & ~KEY_POS_SETATTR) | KEY_USR_ALL, flags); @@ -280,7 +281,7 @@ struct key *keyring_alloc(const char *description, uid_t uid, gid_t gid, * - we propagate the possession attribute from the keyring ref to the key ref */ key_ref_t keyring_search_aux(key_ref_t keyring_ref, - struct task_struct *context, + const struct cred *cred, struct key_type *type, const void *description, key_match_func_t match) @@ -303,7 +304,7 @@ key_ref_t keyring_search_aux(key_ref_t keyring_ref, key_check(keyring); /* top keyring must have search permission to begin the search */ - err = key_task_permission(keyring_ref, context, KEY_SEARCH); + err = key_task_permission(keyring_ref, cred, KEY_SEARCH); if (err < 0) { key_ref = ERR_PTR(err); goto error; @@ -376,7 +377,7 @@ descend: /* key must have search permissions */ if (key_task_permission(make_key_ref(key, possessed), - context, KEY_SEARCH) < 0) + cred, KEY_SEARCH) < 0) continue; /* we set a different error code if we pass a negative key */ @@ -403,7 +404,7 @@ ascend: continue; if (key_task_permission(make_key_ref(key, possessed), - context, KEY_SEARCH) < 0) + cred, KEY_SEARCH) < 0) continue; /* stack the current position */ @@ -458,7 +459,7 @@ key_ref_t keyring_search(key_ref_t keyring, if (!type->match) return ERR_PTR(-ENOKEY); - return keyring_search_aux(keyring, current, + return keyring_search_aux(keyring, current->cred, type, description, type->match); } /* end keyring_search() */ diff --git a/security/keys/permission.c b/security/keys/permission.c index 3b41f9b5253..5d9fc7b93f2 100644 --- a/security/keys/permission.c +++ b/security/keys/permission.c @@ -14,12 +14,19 @@ #include "internal.h" /*****************************************************************************/ -/* - * check to see whether permission is granted to use a key in the desired way, - * but permit the security modules to override +/** + * key_task_permission - Check a key can be used + * @key_ref: The key to check + * @cred: The credentials to use + * @perm: The permissions to check for + * + * Check to see whether permission is granted to use a key in the desired way, + * but permit the security modules to override. + * + * The caller must hold either a ref on cred or must hold the RCU readlock or a + * spinlock. */ -int key_task_permission(const key_ref_t key_ref, - struct task_struct *context, +int key_task_permission(const key_ref_t key_ref, const struct cred *cred, key_perm_t perm) { struct key *key; @@ -29,7 +36,7 @@ int key_task_permission(const key_ref_t key_ref, key = key_ref_to_ptr(key_ref); /* use the second 8-bits of permissions for keys the caller owns */ - if (key->uid == context->fsuid) { + if (key->uid == cred->fsuid) { kperm = key->perm >> 16; goto use_these_perms; } @@ -37,15 +44,12 @@ int key_task_permission(const key_ref_t key_ref, /* use the third 8-bits of permissions for keys the caller has a group * membership in common with */ if (key->gid != -1 && key->perm & KEY_GRP_ALL) { - if (key->gid == context->fsgid) { + if (key->gid == cred->fsgid) { kperm = key->perm >> 8; goto use_these_perms; } - task_lock(context); - ret = groups_search(context->group_info, key->gid); - task_unlock(context); - + ret = groups_search(cred->group_info, key->gid); if (ret) { kperm = key->perm >> 8; goto use_these_perms; @@ -56,6 +60,7 @@ int key_task_permission(const key_ref_t key_ref, kperm = key->perm; use_these_perms: + /* use the top 8-bits of permissions for keys the caller possesses * - possessor permissions are additive with other permissions */ @@ -68,7 +73,7 @@ use_these_perms: return -EACCES; /* let LSM be the final arbiter */ - return security_key_permission(key_ref, context, perm); + return security_key_permission(key_ref, cred, perm); } /* end key_task_permission() */ diff --git a/security/keys/proc.c b/security/keys/proc.c index f619170da76..7f508def50e 100644 --- a/security/keys/proc.c +++ b/security/keys/proc.c @@ -136,8 +136,12 @@ static int proc_keys_show(struct seq_file *m, void *v) int rc; /* check whether the current task is allowed to view the key (assuming - * non-possession) */ - rc = key_task_permission(make_key_ref(key, 0), current, KEY_VIEW); + * non-possession) + * - the caller holds a spinlock, and thus the RCU read lock, making our + * access to __current_cred() safe + */ + rc = key_task_permission(make_key_ref(key, 0), current_cred(), + KEY_VIEW); if (rc < 0) return 0; diff --git a/security/keys/process_keys.c b/security/keys/process_keys.c index 45b240af6db..2f5d89e92b8 100644 --- a/security/keys/process_keys.c +++ b/security/keys/process_keys.c @@ -40,13 +40,17 @@ struct key_user root_key_user = { /* * install user and user session keyrings for a particular UID */ -int install_user_keyrings(struct task_struct *tsk) +int install_user_keyrings(void) { - struct user_struct *user = tsk->user; + struct user_struct *user; + const struct cred *cred; struct key *uid_keyring, *session_keyring; char buf[20]; int ret; + cred = current_cred(); + user = cred->user; + kenter("%p{%u}", user, user->uid); if (user->uid_keyring) { @@ -67,7 +71,7 @@ int install_user_keyrings(struct task_struct *tsk) uid_keyring = find_keyring_by_name(buf, true); if (IS_ERR(uid_keyring)) { uid_keyring = keyring_alloc(buf, user->uid, (gid_t) -1, - tsk, KEY_ALLOC_IN_QUOTA, + cred, KEY_ALLOC_IN_QUOTA, NULL); if (IS_ERR(uid_keyring)) { ret = PTR_ERR(uid_keyring); @@ -83,7 +87,7 @@ int install_user_keyrings(struct task_struct *tsk) if (IS_ERR(session_keyring)) { session_keyring = keyring_alloc(buf, user->uid, (gid_t) -1, - tsk, KEY_ALLOC_IN_QUOTA, NULL); + cred, KEY_ALLOC_IN_QUOTA, NULL); if (IS_ERR(session_keyring)) { ret = PTR_ERR(session_keyring); goto error_release; @@ -115,140 +119,128 @@ error: return ret; } -/*****************************************************************************/ /* - * deal with the UID changing + * install a fresh thread keyring directly to new credentials */ -void switch_uid_keyring(struct user_struct *new_user) +int install_thread_keyring_to_cred(struct cred *new) { -#if 0 /* do nothing for now */ - struct key *old; + struct key *keyring; - /* switch to the new user's session keyring if we were running under - * root's default session keyring */ - if (new_user->uid != 0 && - current->session_keyring == &root_session_keyring - ) { - atomic_inc(&new_user->session_keyring->usage); + keyring = keyring_alloc("_tid", new->uid, new->gid, new, + KEY_ALLOC_QUOTA_OVERRUN, NULL); + if (IS_ERR(keyring)) + return PTR_ERR(keyring); - task_lock(current); - old = current->session_keyring; - current->session_keyring = new_user->session_keyring; - task_unlock(current); + new->thread_keyring = keyring; + return 0; +} - key_put(old); - } -#endif - -} /* end switch_uid_keyring() */ - -/*****************************************************************************/ /* * install a fresh thread keyring, discarding the old one */ -int install_thread_keyring(struct task_struct *tsk) +static int install_thread_keyring(void) { - struct key *keyring, *old; - char buf[20]; + struct cred *new; int ret; - sprintf(buf, "_tid.%u", tsk->pid); + new = prepare_creds(); + if (!new) + return -ENOMEM; - keyring = keyring_alloc(buf, tsk->uid, tsk->gid, tsk, - KEY_ALLOC_QUOTA_OVERRUN, NULL); - if (IS_ERR(keyring)) { - ret = PTR_ERR(keyring); - goto error; + BUG_ON(new->thread_keyring); + + ret = install_thread_keyring_to_cred(new); + if (ret < 0) { + abort_creds(new); + return ret; } - task_lock(tsk); - old = tsk->thread_keyring; - tsk->thread_keyring = keyring; - task_unlock(tsk); + return commit_creds(new); +} - ret = 0; - - key_put(old); -error: - return ret; - -} /* end install_thread_keyring() */ - -/*****************************************************************************/ /* - * make sure a process keyring is installed + * install a process keyring directly to a credentials struct + * - returns -EEXIST if there was already a process keyring, 0 if one installed, + * and other -ve on any other error */ -int install_process_keyring(struct task_struct *tsk) +int install_process_keyring_to_cred(struct cred *new) { struct key *keyring; - char buf[20]; int ret; - might_sleep(); + if (new->tgcred->process_keyring) + return -EEXIST; - if (!tsk->signal->process_keyring) { - sprintf(buf, "_pid.%u", tsk->tgid); + keyring = keyring_alloc("_pid", new->uid, new->gid, + new, KEY_ALLOC_QUOTA_OVERRUN, NULL); + if (IS_ERR(keyring)) + return PTR_ERR(keyring); - keyring = keyring_alloc(buf, tsk->uid, tsk->gid, tsk, - KEY_ALLOC_QUOTA_OVERRUN, NULL); - if (IS_ERR(keyring)) { - ret = PTR_ERR(keyring); - goto error; - } + spin_lock_irq(&new->tgcred->lock); + if (!new->tgcred->process_keyring) { + new->tgcred->process_keyring = keyring; + keyring = NULL; + ret = 0; + } else { + ret = -EEXIST; + } + spin_unlock_irq(&new->tgcred->lock); + key_put(keyring); + return ret; +} - /* attach keyring */ - spin_lock_irq(&tsk->sighand->siglock); - if (!tsk->signal->process_keyring) { - tsk->signal->process_keyring = keyring; - keyring = NULL; - } - spin_unlock_irq(&tsk->sighand->siglock); +/* + * make sure a process keyring is installed + * - we + */ +static int install_process_keyring(void) +{ + struct cred *new; + int ret; - key_put(keyring); + new = prepare_creds(); + if (!new) + return -ENOMEM; + + ret = install_process_keyring_to_cred(new); + if (ret < 0) { + abort_creds(new); + return ret != -EEXIST ?: 0; } - ret = 0; -error: - return ret; + return commit_creds(new); +} -} /* end install_process_keyring() */ - -/*****************************************************************************/ /* - * install a session keyring, discarding the old one - * - if a keyring is not supplied, an empty one is invented + * install a session keyring directly to a credentials struct */ -static int install_session_keyring(struct task_struct *tsk, - struct key *keyring) +static int install_session_keyring_to_cred(struct cred *cred, + struct key *keyring) { unsigned long flags; struct key *old; - char buf[20]; might_sleep(); /* create an empty session keyring */ if (!keyring) { - sprintf(buf, "_ses.%u", tsk->tgid); - flags = KEY_ALLOC_QUOTA_OVERRUN; - if (tsk->signal->session_keyring) + if (cred->tgcred->session_keyring) flags = KEY_ALLOC_IN_QUOTA; - keyring = keyring_alloc(buf, tsk->uid, tsk->gid, tsk, - flags, NULL); + keyring = keyring_alloc("_ses", cred->uid, cred->gid, + cred, flags, NULL); if (IS_ERR(keyring)) return PTR_ERR(keyring); - } - else { + } else { atomic_inc(&keyring->usage); } /* install the keyring */ - spin_lock_irq(&tsk->sighand->siglock); - old = tsk->signal->session_keyring; - rcu_assign_pointer(tsk->signal->session_keyring, keyring); - spin_unlock_irq(&tsk->sighand->siglock); + spin_lock_irq(&cred->tgcred->lock); + old = cred->tgcred->session_keyring; + rcu_assign_pointer(cred->tgcred->session_keyring, keyring); + spin_unlock_irq(&cred->tgcred->lock); /* we're using RCU on the pointer, but there's no point synchronising * on it if it didn't previously point to anything */ @@ -258,110 +250,29 @@ static int install_session_keyring(struct task_struct *tsk, } return 0; +} -} /* end install_session_keyring() */ - -/*****************************************************************************/ /* - * copy the keys in a thread group for fork without CLONE_THREAD + * install a session keyring, discarding the old one + * - if a keyring is not supplied, an empty one is invented */ -int copy_thread_group_keys(struct task_struct *tsk) +static int install_session_keyring(struct key *keyring) { - key_check(current->thread_group->session_keyring); - key_check(current->thread_group->process_keyring); + struct cred *new; + int ret; - /* no process keyring yet */ - tsk->signal->process_keyring = NULL; + new = prepare_creds(); + if (!new) + return -ENOMEM; - /* same session keyring */ - rcu_read_lock(); - tsk->signal->session_keyring = - key_get(rcu_dereference(current->signal->session_keyring)); - rcu_read_unlock(); + ret = install_session_keyring_to_cred(new, NULL); + if (ret < 0) { + abort_creds(new); + return ret; + } - return 0; - -} /* end copy_thread_group_keys() */ - -/*****************************************************************************/ -/* - * copy the keys for fork - */ -int copy_keys(unsigned long clone_flags, struct task_struct *tsk) -{ - key_check(tsk->thread_keyring); - key_check(tsk->request_key_auth); - - /* no thread keyring yet */ - tsk->thread_keyring = NULL; - - /* copy the request_key() authorisation for this thread */ - key_get(tsk->request_key_auth); - - return 0; - -} /* end copy_keys() */ - -/*****************************************************************************/ -/* - * dispose of thread group keys upon thread group destruction - */ -void exit_thread_group_keys(struct signal_struct *tg) -{ - key_put(tg->session_keyring); - key_put(tg->process_keyring); - -} /* end exit_thread_group_keys() */ - -/*****************************************************************************/ -/* - * dispose of per-thread keys upon thread exit - */ -void exit_keys(struct task_struct *tsk) -{ - key_put(tsk->thread_keyring); - key_put(tsk->request_key_auth); - -} /* end exit_keys() */ - -/*****************************************************************************/ -/* - * deal with execve() - */ -int exec_keys(struct task_struct *tsk) -{ - struct key *old; - - /* newly exec'd tasks don't get a thread keyring */ - task_lock(tsk); - old = tsk->thread_keyring; - tsk->thread_keyring = NULL; - task_unlock(tsk); - - key_put(old); - - /* discard the process keyring from a newly exec'd task */ - spin_lock_irq(&tsk->sighand->siglock); - old = tsk->signal->process_keyring; - tsk->signal->process_keyring = NULL; - spin_unlock_irq(&tsk->sighand->siglock); - - key_put(old); - - return 0; - -} /* end exec_keys() */ - -/*****************************************************************************/ -/* - * deal with SUID programs - * - we might want to make this invent a new session keyring - */ -int suid_keys(struct task_struct *tsk) -{ - return 0; - -} /* end suid_keys() */ + return commit_creds(new); +} /*****************************************************************************/ /* @@ -370,10 +281,11 @@ int suid_keys(struct task_struct *tsk) void key_fsuid_changed(struct task_struct *tsk) { /* update the ownership of the thread keyring */ - if (tsk->thread_keyring) { - down_write(&tsk->thread_keyring->sem); - tsk->thread_keyring->uid = tsk->fsuid; - up_write(&tsk->thread_keyring->sem); + BUG_ON(!tsk->cred); + if (tsk->cred->thread_keyring) { + down_write(&tsk->cred->thread_keyring->sem); + tsk->cred->thread_keyring->uid = tsk->cred->fsuid; + up_write(&tsk->cred->thread_keyring->sem); } } /* end key_fsuid_changed() */ @@ -385,10 +297,11 @@ void key_fsuid_changed(struct task_struct *tsk) void key_fsgid_changed(struct task_struct *tsk) { /* update the ownership of the thread keyring */ - if (tsk->thread_keyring) { - down_write(&tsk->thread_keyring->sem); - tsk->thread_keyring->gid = tsk->fsgid; - up_write(&tsk->thread_keyring->sem); + BUG_ON(!tsk->cred); + if (tsk->cred->thread_keyring) { + down_write(&tsk->cred->thread_keyring->sem); + tsk->cred->thread_keyring->gid = tsk->cred->fsgid; + up_write(&tsk->cred->thread_keyring->sem); } } /* end key_fsgid_changed() */ @@ -404,7 +317,7 @@ void key_fsgid_changed(struct task_struct *tsk) key_ref_t search_process_keyrings(struct key_type *type, const void *description, key_match_func_t match, - struct task_struct *context) + const struct cred *cred) { struct request_key_auth *rka; key_ref_t key_ref, ret, err; @@ -423,10 +336,10 @@ key_ref_t search_process_keyrings(struct key_type *type, err = ERR_PTR(-EAGAIN); /* search the thread keyring first */ - if (context->thread_keyring) { + if (cred->thread_keyring) { key_ref = keyring_search_aux( - make_key_ref(context->thread_keyring, 1), - context, type, description, match); + make_key_ref(cred->thread_keyring, 1), + cred, type, description, match); if (!IS_ERR(key_ref)) goto found; @@ -444,10 +357,10 @@ key_ref_t search_process_keyrings(struct key_type *type, } /* search the process keyring second */ - if (context->signal->process_keyring) { + if (cred->tgcred->process_keyring) { key_ref = keyring_search_aux( - make_key_ref(context->signal->process_keyring, 1), - context, type, description, match); + make_key_ref(cred->tgcred->process_keyring, 1), + cred, type, description, match); if (!IS_ERR(key_ref)) goto found; @@ -465,13 +378,13 @@ key_ref_t search_process_keyrings(struct key_type *type, } /* search the session keyring */ - if (context->signal->session_keyring) { + if (cred->tgcred->session_keyring) { rcu_read_lock(); key_ref = keyring_search_aux( make_key_ref(rcu_dereference( - context->signal->session_keyring), + cred->tgcred->session_keyring), 1), - context, type, description, match); + cred, type, description, match); rcu_read_unlock(); if (!IS_ERR(key_ref)) @@ -490,10 +403,10 @@ key_ref_t search_process_keyrings(struct key_type *type, } } /* or search the user-session keyring */ - else if (context->user->session_keyring) { + else if (cred->user->session_keyring) { key_ref = keyring_search_aux( - make_key_ref(context->user->session_keyring, 1), - context, type, description, match); + make_key_ref(cred->user->session_keyring, 1), + cred, type, description, match); if (!IS_ERR(key_ref)) goto found; @@ -514,20 +427,20 @@ key_ref_t search_process_keyrings(struct key_type *type, * search the keyrings of the process mentioned there * - we don't permit access to request_key auth keys via this method */ - if (context->request_key_auth && - context == current && + if (cred->request_key_auth && + cred == current_cred() && type != &key_type_request_key_auth ) { /* defend against the auth key being revoked */ - down_read(&context->request_key_auth->sem); + down_read(&cred->request_key_auth->sem); - if (key_validate(context->request_key_auth) == 0) { - rka = context->request_key_auth->payload.data; + if (key_validate(cred->request_key_auth) == 0) { + rka = cred->request_key_auth->payload.data; key_ref = search_process_keyrings(type, description, - match, rka->context); + match, rka->cred); - up_read(&context->request_key_auth->sem); + up_read(&cred->request_key_auth->sem); if (!IS_ERR(key_ref)) goto found; @@ -544,7 +457,7 @@ key_ref_t search_process_keyrings(struct key_type *type, break; } } else { - up_read(&context->request_key_auth->sem); + up_read(&cred->request_key_auth->sem); } } @@ -572,93 +485,98 @@ static int lookup_user_key_possessed(const struct key *key, const void *target) * - don't create special keyrings unless so requested * - partially constructed keys aren't found unless requested */ -key_ref_t lookup_user_key(struct task_struct *context, key_serial_t id, - int create, int partial, key_perm_t perm) +key_ref_t lookup_user_key(key_serial_t id, int create, int partial, + key_perm_t perm) { - key_ref_t key_ref, skey_ref; + struct request_key_auth *rka; + const struct cred *cred; struct key *key; + key_ref_t key_ref, skey_ref; int ret; - if (!context) - context = current; - +try_again: + cred = get_current_cred(); key_ref = ERR_PTR(-ENOKEY); switch (id) { case KEY_SPEC_THREAD_KEYRING: - if (!context->thread_keyring) { + if (!cred->thread_keyring) { if (!create) goto error; - ret = install_thread_keyring(context); + ret = install_thread_keyring(); if (ret < 0) { key = ERR_PTR(ret); goto error; } + goto reget_creds; } - key = context->thread_keyring; + key = cred->thread_keyring; atomic_inc(&key->usage); key_ref = make_key_ref(key, 1); break; case KEY_SPEC_PROCESS_KEYRING: - if (!context->signal->process_keyring) { + if (!cred->tgcred->process_keyring) { if (!create) goto error; - ret = install_process_keyring(context); + ret = install_process_keyring(); if (ret < 0) { key = ERR_PTR(ret); goto error; } + goto reget_creds; } - key = context->signal->process_keyring; + key = cred->tgcred->process_keyring; atomic_inc(&key->usage); key_ref = make_key_ref(key, 1); break; case KEY_SPEC_SESSION_KEYRING: - if (!context->signal->session_keyring) { + if (!cred->tgcred->session_keyring) { /* always install a session keyring upon access if one * doesn't exist yet */ - ret = install_user_keyrings(context); + ret = install_user_keyrings(); if (ret < 0) goto error; ret = install_session_keyring( - context, context->user->session_keyring); + cred->user->session_keyring); + if (ret < 0) goto error; + goto reget_creds; } rcu_read_lock(); - key = rcu_dereference(context->signal->session_keyring); + key = rcu_dereference(cred->tgcred->session_keyring); atomic_inc(&key->usage); rcu_read_unlock(); key_ref = make_key_ref(key, 1); break; case KEY_SPEC_USER_KEYRING: - if (!context->user->uid_keyring) { - ret = install_user_keyrings(context); + if (!cred->user->uid_keyring) { + ret = install_user_keyrings(); if (ret < 0) goto error; } - key = context->user->uid_keyring; + key = cred->user->uid_keyring; atomic_inc(&key->usage); key_ref = make_key_ref(key, 1); break; case KEY_SPEC_USER_SESSION_KEYRING: - if (!context->user->session_keyring) { - ret = install_user_keyrings(context); + if (!cred->user->session_keyring) { + ret = install_user_keyrings(); if (ret < 0) goto error; } - key = context->user->session_keyring; + key = cred->user->session_keyring; atomic_inc(&key->usage); key_ref = make_key_ref(key, 1); break; @@ -669,7 +587,7 @@ key_ref_t lookup_user_key(struct task_struct *context, key_serial_t id, goto error; case KEY_SPEC_REQKEY_AUTH_KEY: - key = context->request_key_auth; + key = cred->request_key_auth; if (!key) goto error; @@ -677,6 +595,25 @@ key_ref_t lookup_user_key(struct task_struct *context, key_serial_t id, key_ref = make_key_ref(key, 1); break; + case KEY_SPEC_REQUESTOR_KEYRING: + if (!cred->request_key_auth) + goto error; + + down_read(&cred->request_key_auth->sem); + if (cred->request_key_auth->flags & KEY_FLAG_REVOKED) { + key_ref = ERR_PTR(-EKEYREVOKED); + key = NULL; + } else { + rka = cred->request_key_auth->payload.data; + key = rka->dest_keyring; + atomic_inc(&key->usage); + } + up_read(&cred->request_key_auth->sem); + if (!key) + goto error; + key_ref = make_key_ref(key, 1); + break; + default: key_ref = ERR_PTR(-EINVAL); if (id < 1) @@ -693,7 +630,7 @@ key_ref_t lookup_user_key(struct task_struct *context, key_serial_t id, /* check to see if we possess the key */ skey_ref = search_process_keyrings(key->type, key, lookup_user_key_possessed, - current); + cred); if (!IS_ERR(skey_ref)) { key_put(key); @@ -725,11 +662,12 @@ key_ref_t lookup_user_key(struct task_struct *context, key_serial_t id, goto invalid_key; /* check the permissions */ - ret = key_task_permission(key_ref, context, perm); + ret = key_task_permission(key_ref, cred, perm); if (ret < 0) goto invalid_key; error: + put_cred(cred); return key_ref; invalid_key: @@ -737,6 +675,12 @@ invalid_key: key_ref = ERR_PTR(ret); goto error; + /* if we attempted to install a keyring, then it may have caused new + * creds to be installed */ +reget_creds: + put_cred(cred); + goto try_again; + } /* end lookup_user_key() */ /*****************************************************************************/ @@ -748,20 +692,33 @@ invalid_key: */ long join_session_keyring(const char *name) { - struct task_struct *tsk = current; + const struct cred *old; + struct cred *new; struct key *keyring; - long ret; + long ret, serial; + + /* only permit this if there's a single thread in the thread group - + * this avoids us having to adjust the creds on all threads and risking + * ENOMEM */ + if (!is_single_threaded(current)) + return -EMLINK; + + new = prepare_creds(); + if (!new) + return -ENOMEM; + old = current_cred(); /* if no name is provided, install an anonymous keyring */ if (!name) { - ret = install_session_keyring(tsk, NULL); + ret = install_session_keyring_to_cred(new, NULL); if (ret < 0) goto error; - rcu_read_lock(); - ret = rcu_dereference(tsk->signal->session_keyring)->serial; - rcu_read_unlock(); - goto error; + serial = new->tgcred->session_keyring->serial; + ret = commit_creds(new); + if (ret == 0) + ret = serial; + goto okay; } /* allow the user to join or create a named keyring */ @@ -771,29 +728,33 @@ long join_session_keyring(const char *name) keyring = find_keyring_by_name(name, false); if (PTR_ERR(keyring) == -ENOKEY) { /* not found - try and create a new one */ - keyring = keyring_alloc(name, tsk->uid, tsk->gid, tsk, + keyring = keyring_alloc(name, old->uid, old->gid, old, KEY_ALLOC_IN_QUOTA, NULL); if (IS_ERR(keyring)) { ret = PTR_ERR(keyring); goto error2; } - } - else if (IS_ERR(keyring)) { + } else if (IS_ERR(keyring)) { ret = PTR_ERR(keyring); goto error2; } /* we've got a keyring - now to install it */ - ret = install_session_keyring(tsk, keyring); + ret = install_session_keyring_to_cred(new, keyring); if (ret < 0) goto error2; + commit_creds(new); + mutex_unlock(&key_session_mutex); + ret = keyring->serial; key_put(keyring); +okay: + return ret; error2: mutex_unlock(&key_session_mutex); error: + abort_creds(new); return ret; - -} /* end join_session_keyring() */ +} diff --git a/security/keys/request_key.c b/security/keys/request_key.c index abea08f87fe..0e04f72ef2d 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -19,6 +19,8 @@ #include #include "internal.h" +#define key_negative_timeout 60 /* default timeout on a negative key's existence */ + /* * wait_on_bit() sleep function for uninterruptible waiting */ @@ -64,7 +66,7 @@ static int call_sbin_request_key(struct key_construction *cons, const char *op, void *aux) { - struct task_struct *tsk = current; + const struct cred *cred = current_cred(); key_serial_t prkey, sskey; struct key *key = cons->key, *authkey = cons->authkey, *keyring; char *argv[9], *envp[3], uid_str[12], gid_str[12]; @@ -74,15 +76,17 @@ static int call_sbin_request_key(struct key_construction *cons, kenter("{%d},{%d},%s", key->serial, authkey->serial, op); - ret = install_user_keyrings(tsk); + ret = install_user_keyrings(); if (ret < 0) goto error_alloc; /* allocate a new session keyring */ sprintf(desc, "_req.%u", key->serial); - keyring = keyring_alloc(desc, current->fsuid, current->fsgid, current, + cred = get_current_cred(); + keyring = keyring_alloc(desc, cred->fsuid, cred->fsgid, cred, KEY_ALLOC_QUOTA_OVERRUN, NULL); + put_cred(cred); if (IS_ERR(keyring)) { ret = PTR_ERR(keyring); goto error_alloc; @@ -94,29 +98,24 @@ static int call_sbin_request_key(struct key_construction *cons, goto error_link; /* record the UID and GID */ - sprintf(uid_str, "%d", current->fsuid); - sprintf(gid_str, "%d", current->fsgid); + sprintf(uid_str, "%d", cred->fsuid); + sprintf(gid_str, "%d", cred->fsgid); /* we say which key is under construction */ sprintf(key_str, "%d", key->serial); /* we specify the process's default keyrings */ sprintf(keyring_str[0], "%d", - tsk->thread_keyring ? tsk->thread_keyring->serial : 0); + cred->thread_keyring ? cred->thread_keyring->serial : 0); prkey = 0; - if (tsk->signal->process_keyring) - prkey = tsk->signal->process_keyring->serial; + if (cred->tgcred->process_keyring) + prkey = cred->tgcred->process_keyring->serial; - sprintf(keyring_str[1], "%d", prkey); - - if (tsk->signal->session_keyring) { - rcu_read_lock(); - sskey = rcu_dereference(tsk->signal->session_keyring)->serial; - rcu_read_unlock(); - } else { - sskey = tsk->user->session_keyring->serial; - } + if (cred->tgcred->session_keyring) + sskey = rcu_dereference(cred->tgcred->session_keyring)->serial; + else + sskey = cred->user->session_keyring->serial; sprintf(keyring_str[2], "%d", sskey); @@ -157,8 +156,8 @@ error_link: key_put(keyring); error_alloc: - kleave(" = %d", ret); complete_request_key(cons, ret); + kleave(" = %d", ret); return ret; } @@ -167,7 +166,8 @@ error_alloc: * - we ignore program failure and go on key status instead */ static int construct_key(struct key *key, const void *callout_info, - size_t callout_len, void *aux) + size_t callout_len, void *aux, + struct key *dest_keyring) { struct key_construction *cons; request_key_actor_t actor; @@ -181,7 +181,8 @@ static int construct_key(struct key *key, const void *callout_info, return -ENOMEM; /* allocate an authorisation key */ - authkey = request_key_auth_new(key, callout_info, callout_len); + authkey = request_key_auth_new(key, callout_info, callout_len, + dest_keyring); if (IS_ERR(authkey)) { kfree(cons); ret = PTR_ERR(authkey); @@ -209,46 +210,67 @@ static int construct_key(struct key *key, const void *callout_info, } /* - * link a key to the appropriate destination keyring - * - the caller must hold a write lock on the destination keyring + * get the appropriate destination keyring for the request + * - we return whatever keyring we select with an extra reference upon it which + * the caller must release */ -static void construct_key_make_link(struct key *key, struct key *dest_keyring) +static void construct_get_dest_keyring(struct key **_dest_keyring) { - struct task_struct *tsk = current; - struct key *drop = NULL; + struct request_key_auth *rka; + const struct cred *cred = current_cred(); + struct key *dest_keyring = *_dest_keyring, *authkey; - kenter("{%d},%p", key->serial, dest_keyring); + kenter("%p", dest_keyring); /* find the appropriate keyring */ - if (!dest_keyring) { - switch (tsk->jit_keyring) { + if (dest_keyring) { + /* the caller supplied one */ + key_get(dest_keyring); + } else { + /* use a default keyring; falling through the cases until we + * find one that we actually have */ + switch (cred->jit_keyring) { case KEY_REQKEY_DEFL_DEFAULT: + case KEY_REQKEY_DEFL_REQUESTOR_KEYRING: + if (cred->request_key_auth) { + authkey = cred->request_key_auth; + down_read(&authkey->sem); + rka = authkey->payload.data; + if (!test_bit(KEY_FLAG_REVOKED, + &authkey->flags)) + dest_keyring = + key_get(rka->dest_keyring); + up_read(&authkey->sem); + if (dest_keyring) + break; + } + case KEY_REQKEY_DEFL_THREAD_KEYRING: - dest_keyring = tsk->thread_keyring; + dest_keyring = key_get(cred->thread_keyring); if (dest_keyring) break; case KEY_REQKEY_DEFL_PROCESS_KEYRING: - dest_keyring = tsk->signal->process_keyring; + dest_keyring = key_get(cred->tgcred->process_keyring); if (dest_keyring) break; case KEY_REQKEY_DEFL_SESSION_KEYRING: rcu_read_lock(); dest_keyring = key_get( - rcu_dereference(tsk->signal->session_keyring)); + rcu_dereference(cred->tgcred->session_keyring)); rcu_read_unlock(); - drop = dest_keyring; if (dest_keyring) break; case KEY_REQKEY_DEFL_USER_SESSION_KEYRING: - dest_keyring = tsk->user->session_keyring; + dest_keyring = + key_get(cred->user->session_keyring); break; case KEY_REQKEY_DEFL_USER_KEYRING: - dest_keyring = tsk->user->uid_keyring; + dest_keyring = key_get(cred->user->uid_keyring); break; case KEY_REQKEY_DEFL_GROUP_KEYRING: @@ -257,10 +279,9 @@ static void construct_key_make_link(struct key *key, struct key *dest_keyring) } } - /* and attach the key to it */ - __key_link(dest_keyring, key); - key_put(drop); - kleave(""); + *_dest_keyring = dest_keyring; + kleave(" [dk %d]", key_serial(dest_keyring)); + return; } /* @@ -275,6 +296,7 @@ static int construct_alloc_key(struct key_type *type, struct key_user *user, struct key **_key) { + const struct cred *cred = current_cred(); struct key *key; key_ref_t key_ref; @@ -282,33 +304,28 @@ static int construct_alloc_key(struct key_type *type, mutex_lock(&user->cons_lock); - key = key_alloc(type, description, - current->fsuid, current->fsgid, current, KEY_POS_ALL, - flags); + key = key_alloc(type, description, cred->fsuid, cred->fsgid, cred, + KEY_POS_ALL, flags); if (IS_ERR(key)) goto alloc_failed; set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags); - if (dest_keyring) - down_write(&dest_keyring->sem); + down_write(&dest_keyring->sem); /* attach the key to the destination keyring under lock, but we do need * to do another check just in case someone beat us to it whilst we * waited for locks */ mutex_lock(&key_construction_mutex); - key_ref = search_process_keyrings(type, description, type->match, - current); + key_ref = search_process_keyrings(type, description, type->match, cred); if (!IS_ERR(key_ref)) goto key_already_present; - if (dest_keyring) - construct_key_make_link(key, dest_keyring); + __key_link(dest_keyring, key); mutex_unlock(&key_construction_mutex); - if (dest_keyring) - up_write(&dest_keyring->sem); + up_write(&dest_keyring->sem); mutex_unlock(&user->cons_lock); *_key = key; kleave(" = 0 [%d]", key_serial(key)); @@ -346,25 +363,36 @@ static struct key *construct_key_and_link(struct key_type *type, struct key *key; int ret; - user = key_user_lookup(current->fsuid); + kenter(""); + + user = key_user_lookup(current_fsuid()); if (!user) return ERR_PTR(-ENOMEM); + construct_get_dest_keyring(&dest_keyring); + ret = construct_alloc_key(type, description, dest_keyring, flags, user, &key); key_user_put(user); if (ret == 0) { - ret = construct_key(key, callout_info, callout_len, aux); - if (ret < 0) + ret = construct_key(key, callout_info, callout_len, aux, + dest_keyring); + if (ret < 0) { + kdebug("cons failed"); goto construction_failed; + } } + key_put(dest_keyring); + kleave(" = key %d", key_serial(key)); return key; construction_failed: key_negate_and_link(key, key_negative_timeout, NULL, NULL); key_put(key); + key_put(dest_keyring); + kleave(" = %d", ret); return ERR_PTR(ret); } @@ -383,6 +411,7 @@ struct key *request_key_and_link(struct key_type *type, struct key *dest_keyring, unsigned long flags) { + const struct cred *cred = current_cred(); struct key *key; key_ref_t key_ref; @@ -392,7 +421,7 @@ struct key *request_key_and_link(struct key_type *type, /* search all the process keyrings for a key */ key_ref = search_process_keyrings(type, description, type->match, - current); + cred); if (!IS_ERR(key_ref)) { key = key_ref_to_ptr(key_ref); diff --git a/security/keys/request_key_auth.c b/security/keys/request_key_auth.c index bd237b0a633..86747151ee5 100644 --- a/security/keys/request_key_auth.c +++ b/security/keys/request_key_auth.c @@ -105,9 +105,9 @@ static void request_key_auth_revoke(struct key *key) kenter("{%d}", key->serial); - if (rka->context) { - put_task_struct(rka->context); - rka->context = NULL; + if (rka->cred) { + put_cred(rka->cred); + rka->cred = NULL; } } /* end request_key_auth_revoke() */ @@ -122,12 +122,13 @@ static void request_key_auth_destroy(struct key *key) kenter("{%d}", key->serial); - if (rka->context) { - put_task_struct(rka->context); - rka->context = NULL; + if (rka->cred) { + put_cred(rka->cred); + rka->cred = NULL; } key_put(rka->target_key); + key_put(rka->dest_keyring); kfree(rka->callout_info); kfree(rka); @@ -139,9 +140,10 @@ static void request_key_auth_destroy(struct key *key) * access to the caller's security data */ struct key *request_key_auth_new(struct key *target, const void *callout_info, - size_t callout_len) + size_t callout_len, struct key *dest_keyring) { struct request_key_auth *rka, *irka; + const struct cred *cred = current->cred; struct key *authkey = NULL; char desc[20]; int ret; @@ -163,31 +165,29 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, /* see if the calling process is already servicing the key request of * another process */ - if (current->request_key_auth) { + if (cred->request_key_auth) { /* it is - use that instantiation context here too */ - down_read(¤t->request_key_auth->sem); + down_read(&cred->request_key_auth->sem); /* if the auth key has been revoked, then the key we're * servicing is already instantiated */ - if (test_bit(KEY_FLAG_REVOKED, - ¤t->request_key_auth->flags)) + if (test_bit(KEY_FLAG_REVOKED, &cred->request_key_auth->flags)) goto auth_key_revoked; - irka = current->request_key_auth->payload.data; - rka->context = irka->context; + irka = cred->request_key_auth->payload.data; + rka->cred = get_cred(irka->cred); rka->pid = irka->pid; - get_task_struct(rka->context); - up_read(¤t->request_key_auth->sem); + up_read(&cred->request_key_auth->sem); } else { /* it isn't - use this process as the context */ - rka->context = current; + rka->cred = get_cred(cred); rka->pid = current->pid; - get_task_struct(rka->context); } rka->target_key = key_get(target); + rka->dest_keyring = key_get(dest_keyring); memcpy(rka->callout_info, callout_info, callout_len); rka->callout_len = callout_len; @@ -195,7 +195,7 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, sprintf(desc, "%x", target->serial); authkey = key_alloc(&key_type_request_key_auth, desc, - current->fsuid, current->fsgid, current, + cred->fsuid, cred->fsgid, cred, KEY_POS_VIEW | KEY_POS_READ | KEY_POS_SEARCH | KEY_USR_VIEW, KEY_ALLOC_NOT_IN_QUOTA); if (IS_ERR(authkey)) { @@ -203,16 +203,16 @@ struct key *request_key_auth_new(struct key *target, const void *callout_info, goto error_alloc; } - /* construct and attach to the keyring */ + /* construct the auth key */ ret = key_instantiate_and_link(authkey, rka, 0, NULL, NULL); if (ret < 0) goto error_inst; - kleave(" = {%d}", authkey->serial); + kleave(" = {%d,%d}", authkey->serial, atomic_read(&authkey->usage)); return authkey; auth_key_revoked: - up_read(¤t->request_key_auth->sem); + up_read(&cred->request_key_auth->sem); kfree(rka->callout_info); kfree(rka); kleave("= -EKEYREVOKED"); @@ -223,6 +223,7 @@ error_inst: key_put(authkey); error_alloc: key_put(rka->target_key); + key_put(rka->dest_keyring); kfree(rka->callout_info); kfree(rka); kleave("= %d", ret); @@ -254,6 +255,7 @@ static int key_get_instantiation_authkey_match(const struct key *key, */ struct key *key_get_instantiation_authkey(key_serial_t target_id) { + const struct cred *cred = current_cred(); struct key *authkey; key_ref_t authkey_ref; @@ -261,7 +263,7 @@ struct key *key_get_instantiation_authkey(key_serial_t target_id) &key_type_request_key_auth, (void *) (unsigned long) target_id, key_get_instantiation_authkey_match, - current); + cred); if (IS_ERR(authkey_ref)) { authkey = ERR_CAST(authkey_ref); diff --git a/security/root_plug.c b/security/root_plug.c index c3f68b5b372..40fb4f15e27 100644 --- a/security/root_plug.c +++ b/security/root_plug.c @@ -55,9 +55,9 @@ static int rootplug_bprm_check_security (struct linux_binprm *bprm) struct usb_device *dev; root_dbg("file %s, e_uid = %d, e_gid = %d\n", - bprm->filename, bprm->e_uid, bprm->e_gid); + bprm->filename, bprm->cred->euid, bprm->cred->egid); - if (bprm->e_gid == 0) { + if (bprm->cred->egid == 0) { dev = usb_find_device(vendor_id, product_id); if (!dev) { root_dbg("e_gid = 0, and device not found, " @@ -75,15 +75,12 @@ static struct security_operations rootplug_security_ops = { .ptrace_may_access = cap_ptrace_may_access, .ptrace_traceme = cap_ptrace_traceme, .capget = cap_capget, - .capset_check = cap_capset_check, - .capset_set = cap_capset_set, + .capset = cap_capset, .capable = cap_capable, - .bprm_apply_creds = cap_bprm_apply_creds, - .bprm_set_security = cap_bprm_set_security, + .bprm_set_creds = cap_bprm_set_creds, - .task_post_setuid = cap_task_post_setuid, - .task_reparent_to_init = cap_task_reparent_to_init, + .task_fix_setuid = cap_task_fix_setuid, .task_prctl = cap_task_prctl, .bprm_check_security = rootplug_bprm_check_security, diff --git a/security/security.c b/security/security.c index c0acfa7177e..d85dbb37c97 100644 --- a/security/security.c +++ b/security/security.c @@ -145,25 +145,23 @@ int security_capget(struct task_struct *target, return security_ops->capget(target, effective, inheritable, permitted); } -int security_capset_check(struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) +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) { - return security_ops->capset_check(target, effective, inheritable, permitted); -} - -void security_capset_set(struct task_struct *target, - kernel_cap_t *effective, - kernel_cap_t *inheritable, - kernel_cap_t *permitted) -{ - security_ops->capset_set(target, effective, inheritable, permitted); + return security_ops->capset(new, old, + effective, inheritable, permitted); } int security_capable(struct task_struct *tsk, int cap) { - return security_ops->capable(tsk, cap); + return security_ops->capable(tsk, cap, SECURITY_CAP_AUDIT); +} + +int security_capable_noaudit(struct task_struct *tsk, int cap) +{ + return security_ops->capable(tsk, cap, SECURITY_CAP_NOAUDIT); } int security_acct(struct file *file) @@ -215,29 +213,9 @@ int security_vm_enough_memory_kern(long pages) return security_ops->vm_enough_memory(current->mm, pages); } -int security_bprm_alloc(struct linux_binprm *bprm) +int security_bprm_set_creds(struct linux_binprm *bprm) { - return security_ops->bprm_alloc_security(bprm); -} - -void security_bprm_free(struct linux_binprm *bprm) -{ - security_ops->bprm_free_security(bprm); -} - -void security_bprm_apply_creds(struct linux_binprm *bprm, int unsafe) -{ - security_ops->bprm_apply_creds(bprm, unsafe); -} - -void security_bprm_post_apply_creds(struct linux_binprm *bprm) -{ - security_ops->bprm_post_apply_creds(bprm); -} - -int security_bprm_set(struct linux_binprm *bprm) -{ - return security_ops->bprm_set_security(bprm); + return security_ops->bprm_set_creds(bprm); } int security_bprm_check(struct linux_binprm *bprm) @@ -245,6 +223,16 @@ int security_bprm_check(struct linux_binprm *bprm) return security_ops->bprm_check_security(bprm); } +void security_bprm_committing_creds(struct linux_binprm *bprm) +{ + security_ops->bprm_committing_creds(bprm); +} + +void security_bprm_committed_creds(struct linux_binprm *bprm) +{ + security_ops->bprm_committed_creds(bprm); +} + int security_bprm_secureexec(struct linux_binprm *bprm) { return security_ops->bprm_secureexec(bprm); @@ -266,9 +254,9 @@ int security_sb_copy_data(char *orig, char *copy) } EXPORT_SYMBOL(security_sb_copy_data); -int security_sb_kern_mount(struct super_block *sb, void *data) +int security_sb_kern_mount(struct super_block *sb, int flags, void *data) { - return security_ops->sb_kern_mount(sb, data); + return security_ops->sb_kern_mount(sb, flags, data); } int security_sb_show_options(struct seq_file *m, struct super_block *sb) @@ -603,9 +591,9 @@ int security_file_receive(struct file *file) return security_ops->file_receive(file); } -int security_dentry_open(struct file *file) +int security_dentry_open(struct file *file, const struct cred *cred) { - return security_ops->dentry_open(file); + return security_ops->dentry_open(file, cred); } int security_task_create(unsigned long clone_flags) @@ -613,14 +601,29 @@ int security_task_create(unsigned long clone_flags) return security_ops->task_create(clone_flags); } -int security_task_alloc(struct task_struct *p) +void security_cred_free(struct cred *cred) { - return security_ops->task_alloc_security(p); + security_ops->cred_free(cred); } -void security_task_free(struct task_struct *p) +int security_prepare_creds(struct cred *new, const struct cred *old, gfp_t gfp) { - security_ops->task_free_security(p); + return security_ops->cred_prepare(new, old, gfp); +} + +void security_commit_creds(struct cred *new, const struct cred *old) +{ + security_ops->cred_commit(new, old); +} + +int security_kernel_act_as(struct cred *new, u32 secid) +{ + return security_ops->kernel_act_as(new, secid); +} + +int security_kernel_create_files_as(struct cred *new, struct inode *inode) +{ + return security_ops->kernel_create_files_as(new, inode); } int security_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags) @@ -628,10 +631,10 @@ int security_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags) return security_ops->task_setuid(id0, id1, id2, flags); } -int security_task_post_setuid(uid_t old_ruid, uid_t old_euid, - uid_t old_suid, int flags) +int security_task_fix_setuid(struct cred *new, const struct cred *old, + int flags) { - return security_ops->task_post_setuid(old_ruid, old_euid, old_suid, flags); + return security_ops->task_fix_setuid(new, old, flags); } int security_task_setgid(gid_t id0, gid_t id1, gid_t id2, int flags) @@ -713,14 +716,9 @@ int security_task_wait(struct task_struct *p) } int security_task_prctl(int option, unsigned long arg2, unsigned long arg3, - unsigned long arg4, unsigned long arg5, long *rc_p) + unsigned long arg4, unsigned long arg5) { - return security_ops->task_prctl(option, arg2, arg3, arg4, arg5, rc_p); -} - -void security_task_reparent_to_init(struct task_struct *p) -{ - security_ops->task_reparent_to_init(p); + return security_ops->task_prctl(option, arg2, arg3, arg4, arg5); } void security_task_to_inode(struct task_struct *p, struct inode *inode) @@ -1120,9 +1118,10 @@ EXPORT_SYMBOL(security_skb_classify_flow); #ifdef CONFIG_KEYS -int security_key_alloc(struct key *key, struct task_struct *tsk, unsigned long flags) +int security_key_alloc(struct key *key, const struct cred *cred, + unsigned long flags) { - return security_ops->key_alloc(key, tsk, flags); + return security_ops->key_alloc(key, cred, flags); } void security_key_free(struct key *key) @@ -1131,9 +1130,9 @@ void security_key_free(struct key *key) } int security_key_permission(key_ref_t key_ref, - struct task_struct *context, key_perm_t perm) + const struct cred *cred, key_perm_t perm) { - return security_ops->key_permission(key_ref, context, perm); + return security_ops->key_permission(key_ref, cred, perm); } int security_key_getsecurity(struct key *key, char **_buffer) diff --git a/security/selinux/exports.c b/security/selinux/exports.c index 64af2d3409e..c73aeaa008e 100644 --- a/security/selinux/exports.c +++ b/security/selinux/exports.c @@ -39,9 +39,13 @@ EXPORT_SYMBOL_GPL(selinux_string_to_sid); int selinux_secmark_relabel_packet_permission(u32 sid) { if (selinux_enabled) { - struct task_security_struct *tsec = current->security; + const struct task_security_struct *__tsec; + u32 tsid; - return avc_has_perm(tsec->sid, sid, SECCLASS_PACKET, + __tsec = current_security(); + tsid = __tsec->sid; + + return avc_has_perm(tsid, sid, SECCLASS_PACKET, PACKET__RELABELTO, NULL); } return 0; diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index f85597a4d73..853b58c8b2c 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -156,33 +156,62 @@ static int selinux_secmark_enabled(void) return (atomic_read(&selinux_secmark_refcount) > 0); } -/* Allocate and free functions for each kind of security blob. */ - -static int task_alloc_security(struct task_struct *task) +/* + * initialise the security for the init task + */ +static void cred_init_security(void) { + struct cred *cred = (struct cred *) current->real_cred; struct task_security_struct *tsec; tsec = kzalloc(sizeof(struct task_security_struct), GFP_KERNEL); if (!tsec) - return -ENOMEM; + panic("SELinux: Failed to initialize initial task.\n"); - tsec->osid = tsec->sid = SECINITSID_UNLABELED; - task->security = tsec; - - return 0; + tsec->osid = tsec->sid = SECINITSID_KERNEL; + cred->security = tsec; } -static void task_free_security(struct task_struct *task) +/* + * get the security ID of a set of credentials + */ +static inline u32 cred_sid(const struct cred *cred) { - struct task_security_struct *tsec = task->security; - task->security = NULL; - kfree(tsec); + const struct task_security_struct *tsec; + + tsec = cred->security; + return tsec->sid; } +/* + * get the objective security ID of a task + */ +static inline u32 task_sid(const struct task_struct *task) +{ + u32 sid; + + rcu_read_lock(); + sid = cred_sid(__task_cred(task)); + rcu_read_unlock(); + return sid; +} + +/* + * get the subjective security ID of the current task + */ +static inline u32 current_sid(void) +{ + const struct task_security_struct *tsec = current_cred()->security; + + return tsec->sid; +} + +/* Allocate and free functions for each kind of security blob. */ + static int inode_alloc_security(struct inode *inode) { - struct task_security_struct *tsec = current->security; struct inode_security_struct *isec; + u32 sid = current_sid(); isec = kmem_cache_zalloc(sel_inode_cache, GFP_NOFS); if (!isec) @@ -193,7 +222,7 @@ static int inode_alloc_security(struct inode *inode) isec->inode = inode; isec->sid = SECINITSID_UNLABELED; isec->sclass = SECCLASS_FILE; - isec->task_sid = tsec->sid; + isec->task_sid = sid; inode->i_security = isec; return 0; @@ -215,15 +244,15 @@ static void inode_free_security(struct inode *inode) static int file_alloc_security(struct file *file) { - struct task_security_struct *tsec = current->security; struct file_security_struct *fsec; + u32 sid = current_sid(); fsec = kzalloc(sizeof(struct file_security_struct), GFP_KERNEL); if (!fsec) return -ENOMEM; - fsec->sid = tsec->sid; - fsec->fown_sid = tsec->sid; + fsec->sid = sid; + fsec->fown_sid = sid; file->f_security = fsec; return 0; @@ -338,8 +367,9 @@ static const match_table_t tokens = { static int may_context_mount_sb_relabel(u32 sid, struct superblock_security_struct *sbsec, - struct task_security_struct *tsec) + const struct cred *cred) { + const struct task_security_struct *tsec = cred->security; int rc; rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, @@ -354,8 +384,9 @@ static int may_context_mount_sb_relabel(u32 sid, static int may_context_mount_inode_relabel(u32 sid, struct superblock_security_struct *sbsec, - struct task_security_struct *tsec) + const struct cred *cred) { + const struct task_security_struct *tsec = cred->security; int rc; rc = avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, FILESYSTEM__RELABELFROM, NULL); @@ -553,8 +584,8 @@ static int bad_option(struct superblock_security_struct *sbsec, char flag, static int selinux_set_mnt_opts(struct super_block *sb, struct security_mnt_opts *opts) { + const struct cred *cred = current_cred(); int rc = 0, i; - struct task_security_struct *tsec = current->security; struct superblock_security_struct *sbsec = sb->s_security; const char *name = sb->s_type->name; struct inode *inode = sbsec->sb->s_root->d_inode; @@ -671,7 +702,7 @@ static int selinux_set_mnt_opts(struct super_block *sb, sbsec->proc = 1; /* Determine the labeling behavior to use for this filesystem type. */ - rc = security_fs_use(sb->s_type->name, &sbsec->behavior, &sbsec->sid); + rc = security_fs_use(sbsec->proc ? "proc" : sb->s_type->name, &sbsec->behavior, &sbsec->sid); if (rc) { printk(KERN_WARNING "%s: security_fs_use(%s) returned %d\n", __func__, sb->s_type->name, rc); @@ -680,8 +711,7 @@ static int selinux_set_mnt_opts(struct super_block *sb, /* sets the context of the superblock for the fs being mounted. */ if (fscontext_sid) { - - rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, tsec); + rc = may_context_mount_sb_relabel(fscontext_sid, sbsec, cred); if (rc) goto out; @@ -695,12 +725,14 @@ static int selinux_set_mnt_opts(struct super_block *sb, */ if (context_sid) { if (!fscontext_sid) { - rc = may_context_mount_sb_relabel(context_sid, sbsec, tsec); + rc = may_context_mount_sb_relabel(context_sid, sbsec, + cred); if (rc) goto out; sbsec->sid = context_sid; } else { - rc = may_context_mount_inode_relabel(context_sid, sbsec, tsec); + rc = may_context_mount_inode_relabel(context_sid, sbsec, + cred); if (rc) goto out; } @@ -712,7 +744,8 @@ static int selinux_set_mnt_opts(struct super_block *sb, } if (rootcontext_sid) { - rc = may_context_mount_inode_relabel(rootcontext_sid, sbsec, tsec); + rc = may_context_mount_inode_relabel(rootcontext_sid, sbsec, + cred); if (rc) goto out; @@ -730,7 +763,7 @@ static int selinux_set_mnt_opts(struct super_block *sb, if (defcontext_sid != sbsec->def_sid) { rc = may_context_mount_inode_relabel(defcontext_sid, - sbsec, tsec); + sbsec, cred); if (rc) goto out; } @@ -1345,18 +1378,53 @@ static inline u32 signal_to_av(int sig) return perm; } -/* Check permission betweeen a pair of tasks, e.g. signal checks, - fork check, ptrace check, etc. */ -static int task_has_perm(struct task_struct *tsk1, - struct task_struct *tsk2, +/* + * Check permission between a pair of credentials + * fork check, ptrace check, etc. + */ +static int cred_has_perm(const struct cred *actor, + const struct cred *target, u32 perms) { - struct task_security_struct *tsec1, *tsec2; + u32 asid = cred_sid(actor), tsid = cred_sid(target); - tsec1 = tsk1->security; - tsec2 = tsk2->security; - return avc_has_perm(tsec1->sid, tsec2->sid, - SECCLASS_PROCESS, perms, NULL); + return avc_has_perm(asid, tsid, SECCLASS_PROCESS, perms, NULL); +} + +/* + * Check permission between a pair of tasks, e.g. signal checks, + * fork check, ptrace check, etc. + * tsk1 is the actor and tsk2 is the target + * - this uses the default subjective creds of tsk1 + */ +static int task_has_perm(const struct task_struct *tsk1, + const struct task_struct *tsk2, + u32 perms) +{ + const struct task_security_struct *__tsec1, *__tsec2; + u32 sid1, sid2; + + rcu_read_lock(); + __tsec1 = __task_cred(tsk1)->security; sid1 = __tsec1->sid; + __tsec2 = __task_cred(tsk2)->security; sid2 = __tsec2->sid; + rcu_read_unlock(); + return avc_has_perm(sid1, sid2, SECCLASS_PROCESS, perms, NULL); +} + +/* + * Check permission between current and another task, e.g. signal checks, + * fork check, ptrace check, etc. + * current is the actor and tsk2 is the target + * - this uses current's subjective creds + */ +static int current_has_perm(const struct task_struct *tsk, + u32 perms) +{ + u32 sid, tsid; + + sid = current_sid(); + tsid = task_sid(tsk); + return avc_has_perm(sid, tsid, SECCLASS_PROCESS, perms, NULL); } #if CAP_LAST_CAP > 63 @@ -1365,14 +1433,14 @@ static int task_has_perm(struct task_struct *tsk1, /* Check whether a task is allowed to use a capability. */ static int task_has_capability(struct task_struct *tsk, - int cap) + int cap, int audit) { - struct task_security_struct *tsec; struct avc_audit_data ad; + struct av_decision avd; u16 sclass; + u32 sid = task_sid(tsk); u32 av = CAP_TO_MASK(cap); - - tsec = tsk->security; + int rc; AVC_AUDIT_DATA_INIT(&ad, CAP); ad.tsk = tsk; @@ -1390,37 +1458,39 @@ static int task_has_capability(struct task_struct *tsk, "SELinux: out of range capability %d\n", cap); BUG(); } - return avc_has_perm(tsec->sid, tsec->sid, sclass, av, &ad); + + rc = avc_has_perm_noaudit(sid, sid, sclass, av, 0, &avd); + if (audit == SECURITY_CAP_AUDIT) + avc_audit(sid, sid, sclass, av, &avd, rc, &ad); + return rc; } /* Check whether a task is allowed to use a system operation. */ static int task_has_system(struct task_struct *tsk, u32 perms) { - struct task_security_struct *tsec; + u32 sid = task_sid(tsk); - tsec = tsk->security; - - return avc_has_perm(tsec->sid, SECINITSID_KERNEL, + return avc_has_perm(sid, SECINITSID_KERNEL, SECCLASS_SYSTEM, perms, NULL); } /* Check whether a task has a particular permission to an inode. The 'adp' parameter is optional and allows other audit data to be passed (e.g. the dentry). */ -static int inode_has_perm(struct task_struct *tsk, +static int inode_has_perm(const struct cred *cred, struct inode *inode, u32 perms, struct avc_audit_data *adp) { - struct task_security_struct *tsec; struct inode_security_struct *isec; struct avc_audit_data ad; + u32 sid; if (unlikely(IS_PRIVATE(inode))) return 0; - tsec = tsk->security; + sid = cred_sid(cred); isec = inode->i_security; if (!adp) { @@ -1429,23 +1499,24 @@ static int inode_has_perm(struct task_struct *tsk, ad.u.fs.inode = inode; } - return avc_has_perm(tsec->sid, isec->sid, isec->sclass, perms, adp); + return avc_has_perm(sid, isec->sid, isec->sclass, perms, adp); } /* Same as inode_has_perm, but pass explicit audit data containing the dentry to help the auditing code to more easily generate the pathname if needed. */ -static inline int dentry_has_perm(struct task_struct *tsk, +static inline int dentry_has_perm(const struct cred *cred, struct vfsmount *mnt, struct dentry *dentry, u32 av) { struct inode *inode = dentry->d_inode; struct avc_audit_data ad; + AVC_AUDIT_DATA_INIT(&ad, FS); ad.u.fs.path.mnt = mnt; ad.u.fs.path.dentry = dentry; - return inode_has_perm(tsk, inode, av, &ad); + return inode_has_perm(cred, inode, av, &ad); } /* Check whether a task can use an open file descriptor to @@ -1456,33 +1527,35 @@ static inline int dentry_has_perm(struct task_struct *tsk, has the same SID as the process. If av is zero, then access to the file is not checked, e.g. for cases where only the descriptor is affected like seek. */ -static int file_has_perm(struct task_struct *tsk, - struct file *file, - u32 av) +static int file_has_perm(const struct cred *cred, + struct file *file, + u32 av) { - struct task_security_struct *tsec = tsk->security; struct file_security_struct *fsec = file->f_security; struct inode *inode = file->f_path.dentry->d_inode; struct avc_audit_data ad; + u32 sid = cred_sid(cred); int rc; AVC_AUDIT_DATA_INIT(&ad, FS); ad.u.fs.path = file->f_path; - if (tsec->sid != fsec->sid) { - rc = avc_has_perm(tsec->sid, fsec->sid, + if (sid != fsec->sid) { + rc = avc_has_perm(sid, fsec->sid, SECCLASS_FD, FD__USE, &ad); if (rc) - return rc; + goto out; } /* av is zero if only checking access to the descriptor. */ + rc = 0; if (av) - return inode_has_perm(tsk, inode, av, &ad); + rc = inode_has_perm(cred, inode, av, &ad); - return 0; +out: + return rc; } /* Check whether a task can create a file. */ @@ -1490,36 +1563,36 @@ static int may_create(struct inode *dir, struct dentry *dentry, u16 tclass) { - struct task_security_struct *tsec; + const struct cred *cred = current_cred(); + const struct task_security_struct *tsec = cred->security; struct inode_security_struct *dsec; struct superblock_security_struct *sbsec; - u32 newsid; + u32 sid, newsid; struct avc_audit_data ad; int rc; - tsec = current->security; dsec = dir->i_security; sbsec = dir->i_sb->s_security; + sid = tsec->sid; + newsid = tsec->create_sid; + AVC_AUDIT_DATA_INIT(&ad, FS); ad.u.fs.path.dentry = dentry; - rc = avc_has_perm(tsec->sid, dsec->sid, SECCLASS_DIR, + rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, DIR__ADD_NAME | DIR__SEARCH, &ad); if (rc) return rc; - if (tsec->create_sid && sbsec->behavior != SECURITY_FS_USE_MNTPOINT) { - newsid = tsec->create_sid; - } else { - rc = security_transition_sid(tsec->sid, dsec->sid, tclass, - &newsid); + if (!newsid || sbsec->behavior == SECURITY_FS_USE_MNTPOINT) { + rc = security_transition_sid(sid, dsec->sid, tclass, &newsid); if (rc) return rc; } - rc = avc_has_perm(tsec->sid, newsid, tclass, FILE__CREATE, &ad); + rc = avc_has_perm(sid, newsid, tclass, FILE__CREATE, &ad); if (rc) return rc; @@ -1532,11 +1605,9 @@ static int may_create(struct inode *dir, static int may_create_key(u32 ksid, struct task_struct *ctx) { - struct task_security_struct *tsec; + u32 sid = task_sid(ctx); - tsec = ctx->security; - - return avc_has_perm(tsec->sid, ksid, SECCLASS_KEY, KEY__CREATE, NULL); + return avc_has_perm(sid, ksid, SECCLASS_KEY, KEY__CREATE, NULL); } #define MAY_LINK 0 @@ -1549,13 +1620,12 @@ static int may_link(struct inode *dir, int kind) { - struct task_security_struct *tsec; struct inode_security_struct *dsec, *isec; struct avc_audit_data ad; + u32 sid = current_sid(); u32 av; int rc; - tsec = current->security; dsec = dir->i_security; isec = dentry->d_inode->i_security; @@ -1564,7 +1634,7 @@ static int may_link(struct inode *dir, av = DIR__SEARCH; av |= (kind ? DIR__REMOVE_NAME : DIR__ADD_NAME); - rc = avc_has_perm(tsec->sid, dsec->sid, SECCLASS_DIR, av, &ad); + rc = avc_has_perm(sid, dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; @@ -1584,7 +1654,7 @@ static int may_link(struct inode *dir, return 0; } - rc = avc_has_perm(tsec->sid, isec->sid, isec->sclass, av, &ad); + rc = avc_has_perm(sid, isec->sid, isec->sclass, av, &ad); return rc; } @@ -1593,14 +1663,13 @@ static inline int may_rename(struct inode *old_dir, struct inode *new_dir, struct dentry *new_dentry) { - struct task_security_struct *tsec; struct inode_security_struct *old_dsec, *new_dsec, *old_isec, *new_isec; struct avc_audit_data ad; + u32 sid = current_sid(); u32 av; int old_is_dir, new_is_dir; int rc; - tsec = current->security; old_dsec = old_dir->i_security; old_isec = old_dentry->d_inode->i_security; old_is_dir = S_ISDIR(old_dentry->d_inode->i_mode); @@ -1609,16 +1678,16 @@ static inline int may_rename(struct inode *old_dir, AVC_AUDIT_DATA_INIT(&ad, FS); ad.u.fs.path.dentry = old_dentry; - rc = avc_has_perm(tsec->sid, old_dsec->sid, SECCLASS_DIR, + rc = avc_has_perm(sid, old_dsec->sid, SECCLASS_DIR, DIR__REMOVE_NAME | DIR__SEARCH, &ad); if (rc) return rc; - rc = avc_has_perm(tsec->sid, old_isec->sid, + rc = avc_has_perm(sid, old_isec->sid, old_isec->sclass, FILE__RENAME, &ad); if (rc) return rc; if (old_is_dir && new_dir != old_dir) { - rc = avc_has_perm(tsec->sid, old_isec->sid, + rc = avc_has_perm(sid, old_isec->sid, old_isec->sclass, DIR__REPARENT, &ad); if (rc) return rc; @@ -1628,13 +1697,13 @@ static inline int may_rename(struct inode *old_dir, av = DIR__ADD_NAME | DIR__SEARCH; if (new_dentry->d_inode) av |= DIR__REMOVE_NAME; - rc = avc_has_perm(tsec->sid, new_dsec->sid, SECCLASS_DIR, av, &ad); + rc = avc_has_perm(sid, new_dsec->sid, SECCLASS_DIR, av, &ad); if (rc) return rc; if (new_dentry->d_inode) { new_isec = new_dentry->d_inode->i_security; new_is_dir = S_ISDIR(new_dentry->d_inode->i_mode); - rc = avc_has_perm(tsec->sid, new_isec->sid, + rc = avc_has_perm(sid, new_isec->sid, new_isec->sclass, (new_is_dir ? DIR__RMDIR : FILE__UNLINK), &ad); if (rc) @@ -1645,18 +1714,16 @@ static inline int may_rename(struct inode *old_dir, } /* Check whether a task can perform a filesystem operation. */ -static int superblock_has_perm(struct task_struct *tsk, +static int superblock_has_perm(const struct cred *cred, struct super_block *sb, u32 perms, struct avc_audit_data *ad) { - struct task_security_struct *tsec; struct superblock_security_struct *sbsec; + u32 sid = cred_sid(cred); - tsec = tsk->security; sbsec = sb->s_security; - return avc_has_perm(tsec->sid, sbsec->sid, SECCLASS_FILESYSTEM, - perms, ad); + return avc_has_perm(sid, sbsec->sid, SECCLASS_FILESYSTEM, perms, ad); } /* Convert a Linux mode and permission mask to an access vector. */ @@ -1687,35 +1754,6 @@ static inline u32 file_mask_to_av(int mode, int mask) return av; } -/* - * Convert a file mask to an access vector and include the correct open - * open permission. - */ -static inline u32 open_file_mask_to_av(int mode, int mask) -{ - u32 av = file_mask_to_av(mode, mask); - - if (selinux_policycap_openperm) { - /* - * lnk files and socks do not really have an 'open' - */ - if (S_ISREG(mode)) - av |= FILE__OPEN; - else if (S_ISCHR(mode)) - av |= CHR_FILE__OPEN; - else if (S_ISBLK(mode)) - av |= BLK_FILE__OPEN; - else if (S_ISFIFO(mode)) - av |= FIFO_FILE__OPEN; - else if (S_ISDIR(mode)) - av |= DIR__OPEN; - else - printk(KERN_ERR "SELinux: WARNING: inside %s with " - "unknown mode:%x\n", __func__, mode); - } - return av; -} - /* Convert a Linux file to an access vector. */ static inline u32 file_to_av(struct file *file) { @@ -1739,6 +1777,36 @@ static inline u32 file_to_av(struct file *file) return av; } +/* + * Convert a file to an access vector and include the correct open + * open permission. + */ +static inline u32 open_file_to_av(struct file *file) +{ + u32 av = file_to_av(file); + + if (selinux_policycap_openperm) { + mode_t mode = file->f_path.dentry->d_inode->i_mode; + /* + * lnk files and socks do not really have an 'open' + */ + if (S_ISREG(mode)) + av |= FILE__OPEN; + else if (S_ISCHR(mode)) + av |= CHR_FILE__OPEN; + else if (S_ISBLK(mode)) + av |= BLK_FILE__OPEN; + else if (S_ISFIFO(mode)) + av |= FIFO_FILE__OPEN; + else if (S_ISDIR(mode)) + av |= DIR__OPEN; + else + printk(KERN_ERR "SELinux: WARNING: inside %s with " + "unknown mode:%o\n", __func__, mode); + } + return av; +} + /* Hook functions begin here. */ static int selinux_ptrace_may_access(struct task_struct *child, @@ -1751,13 +1819,12 @@ static int selinux_ptrace_may_access(struct task_struct *child, return rc; if (mode == PTRACE_MODE_READ) { - struct task_security_struct *tsec = current->security; - struct task_security_struct *csec = child->security; - return avc_has_perm(tsec->sid, csec->sid, - SECCLASS_FILE, FILE__READ, NULL); + u32 sid = current_sid(); + u32 csid = task_sid(child); + return avc_has_perm(sid, csid, SECCLASS_FILE, FILE__READ, NULL); } - return task_has_perm(current, child, PROCESS__PTRACE); + return current_has_perm(child, PROCESS__PTRACE); } static int selinux_ptrace_traceme(struct task_struct *parent) @@ -1776,40 +1843,37 @@ static int selinux_capget(struct task_struct *target, kernel_cap_t *effective, { int error; - error = task_has_perm(current, target, PROCESS__GETCAP); + error = current_has_perm(target, PROCESS__GETCAP); if (error) return error; return secondary_ops->capget(target, effective, inheritable, permitted); } -static int selinux_capset_check(struct task_struct *target, kernel_cap_t *effective, - kernel_cap_t *inheritable, kernel_cap_t *permitted) +static int selinux_capset(struct cred *new, const struct cred *old, + const kernel_cap_t *effective, + const kernel_cap_t *inheritable, + const kernel_cap_t *permitted) { int error; - error = secondary_ops->capset_check(target, effective, inheritable, permitted); + error = secondary_ops->capset(new, old, + effective, inheritable, permitted); if (error) return error; - return task_has_perm(current, target, PROCESS__SETCAP); + return cred_has_perm(old, new, PROCESS__SETCAP); } -static void selinux_capset_set(struct task_struct *target, kernel_cap_t *effective, - kernel_cap_t *inheritable, kernel_cap_t *permitted) -{ - secondary_ops->capset_set(target, effective, inheritable, permitted); -} - -static int selinux_capable(struct task_struct *tsk, int cap) +static int selinux_capable(struct task_struct *tsk, int cap, int audit) { int rc; - rc = secondary_ops->capable(tsk, cap); + rc = secondary_ops->capable(tsk, cap, audit); if (rc) return rc; - return task_has_capability(tsk, cap); + return task_has_capability(tsk, cap, audit); } static int selinux_sysctl_get_sid(ctl_table *table, u16 tclass, u32 *sid) @@ -1857,15 +1921,14 @@ static int selinux_sysctl(ctl_table *table, int op) { int error = 0; u32 av; - struct task_security_struct *tsec; - u32 tsid; + u32 tsid, sid; int rc; rc = secondary_ops->sysctl(table, op); if (rc) return rc; - tsec = current->security; + sid = current_sid(); rc = selinux_sysctl_get_sid(table, (op == 0001) ? SECCLASS_DIR : SECCLASS_FILE, &tsid); @@ -1877,7 +1940,7 @@ static int selinux_sysctl(ctl_table *table, int op) /* The op values are "defined" in sysctl.c, thereby creating * a bad coupling between this module and sysctl.c */ if (op == 001) { - error = avc_has_perm(tsec->sid, tsid, + error = avc_has_perm(sid, tsid, SECCLASS_DIR, DIR__SEARCH, NULL); } else { av = 0; @@ -1886,7 +1949,7 @@ static int selinux_sysctl(ctl_table *table, int op) if (op & 002) av |= FILE__WRITE; if (av) - error = avc_has_perm(tsec->sid, tsid, + error = avc_has_perm(sid, tsid, SECCLASS_FILE, av, NULL); } @@ -1895,6 +1958,7 @@ static int selinux_sysctl(ctl_table *table, int op) static int selinux_quotactl(int cmds, int type, int id, struct super_block *sb) { + const struct cred *cred = current_cred(); int rc = 0; if (!sb) @@ -1906,14 +1970,12 @@ static int selinux_quotactl(int cmds, int type, int id, struct super_block *sb) case Q_QUOTAOFF: case Q_SETINFO: case Q_SETQUOTA: - rc = superblock_has_perm(current, sb, FILESYSTEM__QUOTAMOD, - NULL); + rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAMOD, NULL); break; case Q_GETFMT: case Q_GETINFO: case Q_GETQUOTA: - rc = superblock_has_perm(current, sb, FILESYSTEM__QUOTAGET, - NULL); + rc = superblock_has_perm(cred, sb, FILESYSTEM__QUOTAGET, NULL); break; default: rc = 0; /* let the kernel handle invalid cmds */ @@ -1924,7 +1986,9 @@ static int selinux_quotactl(int cmds, int type, int id, struct super_block *sb) static int selinux_quota_on(struct dentry *dentry) { - return dentry_has_perm(current, NULL, dentry, FILE__QUOTAON); + const struct cred *cred = current_cred(); + + return dentry_has_perm(cred, NULL, dentry, FILE__QUOTAON); } static int selinux_syslog(int type) @@ -1972,16 +2036,8 @@ static int selinux_syslog(int type) static int selinux_vm_enough_memory(struct mm_struct *mm, long pages) { int rc, cap_sys_admin = 0; - struct task_security_struct *tsec = current->security; - - rc = secondary_ops->capable(current, CAP_SYS_ADMIN); - if (rc == 0) - rc = avc_has_perm_noaudit(tsec->sid, tsec->sid, - SECCLASS_CAPABILITY, - CAP_TO_MASK(CAP_SYS_ADMIN), - 0, - NULL); + rc = selinux_capable(current, CAP_SYS_ADMIN, SECURITY_CAP_NOAUDIT); if (rc == 0) cap_sys_admin = 1; @@ -1990,59 +2046,45 @@ static int selinux_vm_enough_memory(struct mm_struct *mm, long pages) /* binprm security operations */ -static int selinux_bprm_alloc_security(struct linux_binprm *bprm) +static int selinux_bprm_set_creds(struct linux_binprm *bprm) { - struct bprm_security_struct *bsec; - - bsec = kzalloc(sizeof(struct bprm_security_struct), GFP_KERNEL); - if (!bsec) - return -ENOMEM; - - bsec->sid = SECINITSID_UNLABELED; - bsec->set = 0; - - bprm->security = bsec; - return 0; -} - -static int selinux_bprm_set_security(struct linux_binprm *bprm) -{ - struct task_security_struct *tsec; - struct inode *inode = bprm->file->f_path.dentry->d_inode; + const struct task_security_struct *old_tsec; + struct task_security_struct *new_tsec; struct inode_security_struct *isec; - struct bprm_security_struct *bsec; - u32 newsid; struct avc_audit_data ad; + struct inode *inode = bprm->file->f_path.dentry->d_inode; int rc; - rc = secondary_ops->bprm_set_security(bprm); + rc = secondary_ops->bprm_set_creds(bprm); if (rc) return rc; - bsec = bprm->security; - - if (bsec->set) + /* SELinux context only depends on initial program or script and not + * the script interpreter */ + if (bprm->cred_prepared) return 0; - tsec = current->security; + old_tsec = current_security(); + new_tsec = bprm->cred->security; isec = inode->i_security; /* Default to the current task SID. */ - bsec->sid = tsec->sid; + new_tsec->sid = old_tsec->sid; + new_tsec->osid = old_tsec->sid; /* Reset fs, key, and sock SIDs on execve. */ - tsec->create_sid = 0; - tsec->keycreate_sid = 0; - tsec->sockcreate_sid = 0; + new_tsec->create_sid = 0; + new_tsec->keycreate_sid = 0; + new_tsec->sockcreate_sid = 0; - if (tsec->exec_sid) { - newsid = tsec->exec_sid; + if (old_tsec->exec_sid) { + new_tsec->sid = old_tsec->exec_sid; /* Reset exec SID on execve. */ - tsec->exec_sid = 0; + new_tsec->exec_sid = 0; } else { /* Check for a default transition on this program. */ - rc = security_transition_sid(tsec->sid, isec->sid, - SECCLASS_PROCESS, &newsid); + rc = security_transition_sid(old_tsec->sid, isec->sid, + SECCLASS_PROCESS, &new_tsec->sid); if (rc) return rc; } @@ -2051,33 +2093,63 @@ static int selinux_bprm_set_security(struct linux_binprm *bprm) ad.u.fs.path = bprm->file->f_path; if (bprm->file->f_path.mnt->mnt_flags & MNT_NOSUID) - newsid = tsec->sid; + new_tsec->sid = old_tsec->sid; - if (tsec->sid == newsid) { - rc = avc_has_perm(tsec->sid, isec->sid, + if (new_tsec->sid == old_tsec->sid) { + rc = avc_has_perm(old_tsec->sid, isec->sid, SECCLASS_FILE, FILE__EXECUTE_NO_TRANS, &ad); if (rc) return rc; } else { /* Check permissions for the transition. */ - rc = avc_has_perm(tsec->sid, newsid, + rc = avc_has_perm(old_tsec->sid, new_tsec->sid, SECCLASS_PROCESS, PROCESS__TRANSITION, &ad); if (rc) return rc; - rc = avc_has_perm(newsid, isec->sid, + rc = avc_has_perm(new_tsec->sid, isec->sid, SECCLASS_FILE, FILE__ENTRYPOINT, &ad); if (rc) return rc; - /* Clear any possibly unsafe personality bits on exec: */ - current->personality &= ~PER_CLEAR_ON_SETID; + /* Check for shared state */ + if (bprm->unsafe & LSM_UNSAFE_SHARE) { + rc = avc_has_perm(old_tsec->sid, new_tsec->sid, + SECCLASS_PROCESS, PROCESS__SHARE, + NULL); + if (rc) + return -EPERM; + } - /* Set the security field to the new SID. */ - bsec->sid = newsid; + /* Make sure that anyone attempting to ptrace over a task that + * changes its SID has the appropriate permit */ + if (bprm->unsafe & + (LSM_UNSAFE_PTRACE | LSM_UNSAFE_PTRACE_CAP)) { + struct task_struct *tracer; + struct task_security_struct *sec; + u32 ptsid = 0; + + rcu_read_lock(); + tracer = tracehook_tracer_task(current); + if (likely(tracer != NULL)) { + sec = __task_cred(tracer)->security; + ptsid = sec->sid; + } + rcu_read_unlock(); + + if (ptsid != 0) { + rc = avc_has_perm(ptsid, new_tsec->sid, + SECCLASS_PROCESS, + PROCESS__PTRACE, NULL); + if (rc) + return -EPERM; + } + } + + /* Clear any possibly unsafe personality bits on exec: */ + bprm->per_clear |= PER_CLEAR_ON_SETID; } - bsec->set = 1; return 0; } @@ -2086,35 +2158,34 @@ static int selinux_bprm_check_security(struct linux_binprm *bprm) return secondary_ops->bprm_check_security(bprm); } - static int selinux_bprm_secureexec(struct linux_binprm *bprm) { - struct task_security_struct *tsec = current->security; + const struct cred *cred = current_cred(); + const struct task_security_struct *tsec = cred->security; + u32 sid, osid; int atsecure = 0; - if (tsec->osid != tsec->sid) { + sid = tsec->sid; + osid = tsec->osid; + + if (osid != sid) { /* Enable secure mode for SIDs transitions unless the noatsecure permission is granted between the two SIDs, i.e. ahp returns 0. */ - atsecure = avc_has_perm(tsec->osid, tsec->sid, - SECCLASS_PROCESS, - PROCESS__NOATSECURE, NULL); + atsecure = avc_has_perm(osid, sid, + SECCLASS_PROCESS, + PROCESS__NOATSECURE, NULL); } return (atsecure || secondary_ops->bprm_secureexec(bprm)); } -static void selinux_bprm_free_security(struct linux_binprm *bprm) -{ - kfree(bprm->security); - bprm->security = NULL; -} - extern struct vfsmount *selinuxfs_mount; extern struct dentry *selinux_null; /* Derived from fs/exec.c:flush_old_files. */ -static inline void flush_unauthorized_files(struct files_struct *files) +static inline void flush_unauthorized_files(const struct cred *cred, + struct files_struct *files) { struct avc_audit_data ad; struct file *file, *devnull = NULL; @@ -2136,7 +2207,7 @@ static inline void flush_unauthorized_files(struct files_struct *files) interested in the inode-based check here. */ file = list_first_entry(&tty->tty_files, struct file, f_u.fu_list); inode = file->f_path.dentry->d_inode; - if (inode_has_perm(current, inode, + if (inode_has_perm(cred, inode, FILE__READ | FILE__WRITE, NULL)) { drop_tty = 1; } @@ -2171,7 +2242,7 @@ static inline void flush_unauthorized_files(struct files_struct *files) file = fget(i); if (!file) continue; - if (file_has_perm(current, + if (file_has_perm(cred, file, file_to_av(file))) { sys_close(i); @@ -2185,7 +2256,10 @@ static inline void flush_unauthorized_files(struct files_struct *files) if (devnull) { get_file(devnull); } else { - devnull = dentry_open(dget(selinux_null), mntget(selinuxfs_mount), O_RDWR); + devnull = dentry_open( + dget(selinux_null), + mntget(selinuxfs_mount), + O_RDWR, cred); if (IS_ERR(devnull)) { devnull = NULL; put_unused_fd(fd); @@ -2204,94 +2278,78 @@ static inline void flush_unauthorized_files(struct files_struct *files) spin_unlock(&files->file_lock); } -static void selinux_bprm_apply_creds(struct linux_binprm *bprm, int unsafe) +/* + * Prepare a process for imminent new credential changes due to exec + */ +static void selinux_bprm_committing_creds(struct linux_binprm *bprm) { - struct task_security_struct *tsec; - struct bprm_security_struct *bsec; - u32 sid; - int rc; + struct task_security_struct *new_tsec; + struct rlimit *rlim, *initrlim; + int rc, i; - secondary_ops->bprm_apply_creds(bprm, unsafe); + secondary_ops->bprm_committing_creds(bprm); - tsec = current->security; + new_tsec = bprm->cred->security; + if (new_tsec->sid == new_tsec->osid) + return; - bsec = bprm->security; - sid = bsec->sid; + /* Close files for which the new task SID is not authorized. */ + flush_unauthorized_files(bprm->cred, current->files); - tsec->osid = tsec->sid; - bsec->unsafe = 0; - if (tsec->sid != sid) { - /* Check for shared state. If not ok, leave SID - unchanged and kill. */ - if (unsafe & LSM_UNSAFE_SHARE) { - rc = avc_has_perm(tsec->sid, sid, SECCLASS_PROCESS, - PROCESS__SHARE, NULL); - if (rc) { - bsec->unsafe = 1; - return; - } + /* Always clear parent death signal on SID transitions. */ + current->pdeath_signal = 0; + + /* Check whether the new SID can inherit resource limits from the old + * SID. If not, reset all soft limits to the lower of the current + * task's hard limit and the init task's soft limit. + * + * Note that the setting of hard limits (even to lower them) can be + * controlled by the setrlimit check. The inclusion of the init task's + * soft limit into the computation is to avoid resetting soft limits + * higher than the default soft limit for cases where the default is + * lower than the hard limit, e.g. RLIMIT_CORE or RLIMIT_STACK. + */ + rc = avc_has_perm(new_tsec->osid, new_tsec->sid, SECCLASS_PROCESS, + PROCESS__RLIMITINH, NULL); + if (rc) { + for (i = 0; i < RLIM_NLIMITS; i++) { + rlim = current->signal->rlim + i; + initrlim = init_task.signal->rlim + i; + rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); } - - /* Check for ptracing, and update the task SID if ok. - Otherwise, leave SID unchanged and kill. */ - if (unsafe & (LSM_UNSAFE_PTRACE | LSM_UNSAFE_PTRACE_CAP)) { - struct task_struct *tracer; - struct task_security_struct *sec; - u32 ptsid = 0; - - rcu_read_lock(); - tracer = tracehook_tracer_task(current); - if (likely(tracer != NULL)) { - sec = tracer->security; - ptsid = sec->sid; - } - rcu_read_unlock(); - - if (ptsid != 0) { - rc = avc_has_perm(ptsid, sid, SECCLASS_PROCESS, - PROCESS__PTRACE, NULL); - if (rc) { - bsec->unsafe = 1; - return; - } - } - } - tsec->sid = sid; + update_rlimit_cpu(rlim->rlim_cur); } } /* - * called after apply_creds without the task lock held + * Clean up the process immediately after the installation of new credentials + * due to exec */ -static void selinux_bprm_post_apply_creds(struct linux_binprm *bprm) +static void selinux_bprm_committed_creds(struct linux_binprm *bprm) { - struct task_security_struct *tsec; - struct rlimit *rlim, *initrlim; + const struct task_security_struct *tsec = current_security(); struct itimerval itimer; - struct bprm_security_struct *bsec; + struct sighand_struct *psig; + u32 osid, sid; int rc, i; + unsigned long flags; - tsec = current->security; - bsec = bprm->security; + secondary_ops->bprm_committed_creds(bprm); - if (bsec->unsafe) { - force_sig_specific(SIGKILL, current); - return; - } - if (tsec->osid == tsec->sid) + osid = tsec->osid; + sid = tsec->sid; + + if (sid == osid) return; - /* Close files for which the new task SID is not authorized. */ - flush_unauthorized_files(current->files); - - /* Check whether the new SID can inherit signal state - from the old SID. If not, clear itimers to avoid - subsequent signal generation and flush and unblock - signals. This must occur _after_ the task SID has - been updated so that any kill done after the flush - will be checked against the new SID. */ - rc = avc_has_perm(tsec->osid, tsec->sid, SECCLASS_PROCESS, - PROCESS__SIGINH, NULL); + /* Check whether the new SID can inherit signal state from the old SID. + * If not, clear itimers to avoid subsequent signal generation and + * flush and unblock signals. + * + * This must occur _after_ the task SID has been updated so that any + * kill done after the flush will be checked against the new SID. + */ + rc = avc_has_perm(osid, sid, SECCLASS_PROCESS, PROCESS__SIGINH, NULL); if (rc) { memset(&itimer, 0, sizeof itimer); for (i = 0; i < 3; i++) @@ -2304,33 +2362,14 @@ static void selinux_bprm_post_apply_creds(struct linux_binprm *bprm) spin_unlock_irq(¤t->sighand->siglock); } - /* Always clear parent death signal on SID transitions. */ - current->pdeath_signal = 0; - - /* Check whether the new SID can inherit resource limits - from the old SID. If not, reset all soft limits to - the lower of the current task's hard limit and the init - task's soft limit. Note that the setting of hard limits - (even to lower them) can be controlled by the setrlimit - check. The inclusion of the init task's soft limit into - the computation is to avoid resetting soft limits higher - than the default soft limit for cases where the default - is lower than the hard limit, e.g. RLIMIT_CORE or - RLIMIT_STACK.*/ - rc = avc_has_perm(tsec->osid, tsec->sid, SECCLASS_PROCESS, - PROCESS__RLIMITINH, NULL); - if (rc) { - for (i = 0; i < RLIM_NLIMITS; i++) { - rlim = current->signal->rlim + i; - initrlim = init_task.signal->rlim+i; - rlim->rlim_cur = min(rlim->rlim_max, initrlim->rlim_cur); - } - update_rlimit_cpu(rlim->rlim_cur); - } - - /* Wake up the parent if it is waiting so that it can - recheck wait permission to the new task SID. */ + /* Wake up the parent if it is waiting so that it can recheck + * wait permission to the new task SID. */ + read_lock_irq(&tasklist_lock); + psig = current->parent->sighand; + spin_lock_irqsave(&psig->siglock, flags); wake_up_interruptible(¤t->parent->signal->wait_chldexit); + spin_unlock_irqrestore(&psig->siglock, flags); + read_unlock_irq(&tasklist_lock); } /* superblock security operations */ @@ -2435,8 +2474,9 @@ out: return rc; } -static int selinux_sb_kern_mount(struct super_block *sb, void *data) +static int selinux_sb_kern_mount(struct super_block *sb, int flags, void *data) { + const struct cred *cred = current_cred(); struct avc_audit_data ad; int rc; @@ -2444,18 +2484,23 @@ static int selinux_sb_kern_mount(struct super_block *sb, void *data) if (rc) return rc; + /* Allow all mounts performed by the kernel */ + if (flags & MS_KERNMOUNT) + return 0; + AVC_AUDIT_DATA_INIT(&ad, FS); ad.u.fs.path.dentry = sb->s_root; - return superblock_has_perm(current, sb, FILESYSTEM__MOUNT, &ad); + return superblock_has_perm(cred, sb, FILESYSTEM__MOUNT, &ad); } static int selinux_sb_statfs(struct dentry *dentry) { + const struct cred *cred = current_cred(); struct avc_audit_data ad; AVC_AUDIT_DATA_INIT(&ad, FS); ad.u.fs.path.dentry = dentry->d_sb->s_root; - return superblock_has_perm(current, dentry->d_sb, FILESYSTEM__GETATTR, &ad); + return superblock_has_perm(cred, dentry->d_sb, FILESYSTEM__GETATTR, &ad); } static int selinux_mount(char *dev_name, @@ -2464,6 +2509,7 @@ static int selinux_mount(char *dev_name, unsigned long flags, void *data) { + const struct cred *cred = current_cred(); int rc; rc = secondary_ops->sb_mount(dev_name, path, type, flags, data); @@ -2471,22 +2517,23 @@ static int selinux_mount(char *dev_name, return rc; if (flags & MS_REMOUNT) - return superblock_has_perm(current, path->mnt->mnt_sb, + return superblock_has_perm(cred, path->mnt->mnt_sb, FILESYSTEM__REMOUNT, NULL); else - return dentry_has_perm(current, path->mnt, path->dentry, + return dentry_has_perm(cred, path->mnt, path->dentry, FILE__MOUNTON); } static int selinux_umount(struct vfsmount *mnt, int flags) { + const struct cred *cred = current_cred(); int rc; rc = secondary_ops->sb_umount(mnt, flags); if (rc) return rc; - return superblock_has_perm(current, mnt->mnt_sb, + return superblock_has_perm(cred, mnt->mnt_sb, FILESYSTEM__UNMOUNT, NULL); } @@ -2506,21 +2553,22 @@ static int selinux_inode_init_security(struct inode *inode, struct inode *dir, char **name, void **value, size_t *len) { - struct task_security_struct *tsec; + const struct cred *cred = current_cred(); + const struct task_security_struct *tsec = cred->security; struct inode_security_struct *dsec; struct superblock_security_struct *sbsec; - u32 newsid, clen; + u32 sid, newsid, clen; int rc; char *namep = NULL, *context; - tsec = current->security; dsec = dir->i_security; sbsec = dir->i_sb->s_security; - if (tsec->create_sid && sbsec->behavior != SECURITY_FS_USE_MNTPOINT) { - newsid = tsec->create_sid; - } else { - rc = security_transition_sid(tsec->sid, dsec->sid, + sid = tsec->sid; + newsid = tsec->create_sid; + + if (!newsid || sbsec->behavior == SECURITY_FS_USE_MNTPOINT) { + rc = security_transition_sid(sid, dsec->sid, inode_mode_to_security_class(inode->i_mode), &newsid); if (rc) { @@ -2623,21 +2671,25 @@ static int selinux_inode_rename(struct inode *old_inode, struct dentry *old_dent static int selinux_inode_readlink(struct dentry *dentry) { - return dentry_has_perm(current, NULL, dentry, FILE__READ); + const struct cred *cred = current_cred(); + + return dentry_has_perm(cred, NULL, dentry, FILE__READ); } static int selinux_inode_follow_link(struct dentry *dentry, struct nameidata *nameidata) { + const struct cred *cred = current_cred(); int rc; rc = secondary_ops->inode_follow_link(dentry, nameidata); if (rc) return rc; - return dentry_has_perm(current, NULL, dentry, FILE__READ); + return dentry_has_perm(cred, NULL, dentry, FILE__READ); } static int selinux_inode_permission(struct inode *inode, int mask) { + const struct cred *cred = current_cred(); int rc; rc = secondary_ops->inode_permission(inode, mask); @@ -2649,12 +2701,13 @@ static int selinux_inode_permission(struct inode *inode, int mask) return 0; } - return inode_has_perm(current, inode, - open_file_mask_to_av(inode->i_mode, mask), NULL); + return inode_has_perm(cred, inode, + file_mask_to_av(inode->i_mode, mask), NULL); } static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr) { + const struct cred *cred = current_cred(); int rc; rc = secondary_ops->inode_setattr(dentry, iattr); @@ -2666,18 +2719,22 @@ static int selinux_inode_setattr(struct dentry *dentry, struct iattr *iattr) if (iattr->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_ATIME_SET | ATTR_MTIME_SET)) - return dentry_has_perm(current, NULL, dentry, FILE__SETATTR); + return dentry_has_perm(cred, NULL, dentry, FILE__SETATTR); - return dentry_has_perm(current, NULL, dentry, FILE__WRITE); + return dentry_has_perm(cred, NULL, dentry, FILE__WRITE); } static int selinux_inode_getattr(struct vfsmount *mnt, struct dentry *dentry) { - return dentry_has_perm(current, mnt, dentry, FILE__GETATTR); + const struct cred *cred = current_cred(); + + return dentry_has_perm(cred, mnt, dentry, FILE__GETATTR); } static int selinux_inode_setotherxattr(struct dentry *dentry, const char *name) { + const struct cred *cred = current_cred(); + if (!strncmp(name, XATTR_SECURITY_PREFIX, sizeof XATTR_SECURITY_PREFIX - 1)) { if (!strcmp(name, XATTR_NAME_CAPS)) { @@ -2692,18 +2749,17 @@ static int selinux_inode_setotherxattr(struct dentry *dentry, const char *name) /* Not an attribute we recognize, so just check the ordinary setattr permission. */ - return dentry_has_perm(current, NULL, dentry, FILE__SETATTR); + return dentry_has_perm(cred, NULL, dentry, FILE__SETATTR); } static int selinux_inode_setxattr(struct dentry *dentry, const char *name, const void *value, size_t size, int flags) { - struct task_security_struct *tsec = current->security; struct inode *inode = dentry->d_inode; struct inode_security_struct *isec = inode->i_security; struct superblock_security_struct *sbsec; struct avc_audit_data ad; - u32 newsid; + u32 newsid, sid = current_sid(); int rc = 0; if (strcmp(name, XATTR_NAME_SELINUX)) @@ -2719,7 +2775,7 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name, AVC_AUDIT_DATA_INIT(&ad, FS); ad.u.fs.path.dentry = dentry; - rc = avc_has_perm(tsec->sid, isec->sid, isec->sclass, + rc = avc_has_perm(sid, isec->sid, isec->sclass, FILE__RELABELFROM, &ad); if (rc) return rc; @@ -2733,12 +2789,12 @@ static int selinux_inode_setxattr(struct dentry *dentry, const char *name, if (rc) return rc; - rc = avc_has_perm(tsec->sid, newsid, isec->sclass, + rc = avc_has_perm(sid, newsid, isec->sclass, FILE__RELABELTO, &ad); if (rc) return rc; - rc = security_validate_transition(isec->sid, newsid, tsec->sid, + rc = security_validate_transition(isec->sid, newsid, sid, isec->sclass); if (rc) return rc; @@ -2778,12 +2834,16 @@ static void selinux_inode_post_setxattr(struct dentry *dentry, const char *name, static int selinux_inode_getxattr(struct dentry *dentry, const char *name) { - return dentry_has_perm(current, NULL, dentry, FILE__GETATTR); + const struct cred *cred = current_cred(); + + return dentry_has_perm(cred, NULL, dentry, FILE__GETATTR); } static int selinux_inode_listxattr(struct dentry *dentry) { - return dentry_has_perm(current, NULL, dentry, FILE__GETATTR); + const struct cred *cred = current_cred(); + + return dentry_has_perm(cred, NULL, dentry, FILE__GETATTR); } static int selinux_inode_removexattr(struct dentry *dentry, const char *name) @@ -2806,7 +2866,6 @@ static int selinux_inode_getsecurity(const struct inode *inode, const char *name u32 size; int error; char *context = NULL; - struct task_security_struct *tsec = current->security; struct inode_security_struct *isec = inode->i_security; if (strcmp(name, XATTR_SELINUX_SUFFIX)) @@ -2821,13 +2880,7 @@ static int selinux_inode_getsecurity(const struct inode *inode, const char *name * and lack of permission just means that we fall back to the * in-core context value, not a denial. */ - error = secondary_ops->capable(current, CAP_MAC_ADMIN); - if (!error) - error = avc_has_perm_noaudit(tsec->sid, tsec->sid, - SECCLASS_CAPABILITY2, - CAPABILITY2__MAC_ADMIN, - 0, - NULL); + error = selinux_capable(current, CAP_MAC_ADMIN, SECURITY_CAP_NOAUDIT); if (!error) error = security_sid_to_context_force(isec->sid, &context, &size); @@ -2894,6 +2947,7 @@ static void selinux_inode_getsecid(const struct inode *inode, u32 *secid) static int selinux_revalidate_file_permission(struct file *file, int mask) { + const struct cred *cred = current_cred(); int rc; struct inode *inode = file->f_path.dentry->d_inode; @@ -2906,7 +2960,7 @@ static int selinux_revalidate_file_permission(struct file *file, int mask) if ((file->f_flags & O_APPEND) && (mask & MAY_WRITE)) mask |= MAY_APPEND; - rc = file_has_perm(current, file, + rc = file_has_perm(cred, file, file_mask_to_av(inode->i_mode, mask)); if (rc) return rc; @@ -2917,16 +2971,16 @@ static int selinux_revalidate_file_permission(struct file *file, int mask) static int selinux_file_permission(struct file *file, int mask) { struct inode *inode = file->f_path.dentry->d_inode; - struct task_security_struct *tsec = current->security; struct file_security_struct *fsec = file->f_security; struct inode_security_struct *isec = inode->i_security; + u32 sid = current_sid(); if (!mask) { /* No permission to check. Existence test. */ return 0; } - if (tsec->sid == fsec->sid && fsec->isid == isec->sid + if (sid == fsec->sid && fsec->isid == isec->sid && fsec->pseqno == avc_policy_seqno()) return selinux_netlbl_inode_permission(inode, mask); @@ -2946,6 +3000,7 @@ static void selinux_file_free_security(struct file *file) static int selinux_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { + const struct cred *cred = current_cred(); u32 av = 0; if (_IOC_DIR(cmd) & _IOC_WRITE) @@ -2955,11 +3010,14 @@ static int selinux_file_ioctl(struct file *file, unsigned int cmd, if (!av) av = FILE__IOCTL; - return file_has_perm(current, file, av); + return file_has_perm(cred, file, av); } static int file_map_prot_check(struct file *file, unsigned long prot, int shared) { + const struct cred *cred = current_cred(); + int rc = 0; + #ifndef CONFIG_PPC32 if ((prot & PROT_EXEC) && (!file || (!shared && (prot & PROT_WRITE)))) { /* @@ -2967,9 +3025,9 @@ static int file_map_prot_check(struct file *file, unsigned long prot, int shared * private file mapping that will also be writable. * This has an additional check. */ - int rc = task_has_perm(current, current, PROCESS__EXECMEM); + rc = cred_has_perm(cred, cred, PROCESS__EXECMEM); if (rc) - return rc; + goto error; } #endif @@ -2984,9 +3042,11 @@ static int file_map_prot_check(struct file *file, unsigned long prot, int shared if (prot & PROT_EXEC) av |= FILE__EXECUTE; - return file_has_perm(current, file, av); + return file_has_perm(cred, file, av); } - return 0; + +error: + return rc; } static int selinux_file_mmap(struct file *file, unsigned long reqprot, @@ -2994,7 +3054,7 @@ static int selinux_file_mmap(struct file *file, unsigned long reqprot, unsigned long addr, unsigned long addr_only) { int rc = 0; - u32 sid = ((struct task_security_struct *)(current->security))->sid; + u32 sid = current_sid(); if (addr < mmap_min_addr) rc = avc_has_perm(sid, sid, SECCLASS_MEMPROTECT, @@ -3013,6 +3073,7 @@ static int selinux_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { + const struct cred *cred = current_cred(); int rc; rc = secondary_ops->file_mprotect(vma, reqprot, prot); @@ -3027,12 +3088,11 @@ static int selinux_file_mprotect(struct vm_area_struct *vma, rc = 0; if (vma->vm_start >= vma->vm_mm->start_brk && vma->vm_end <= vma->vm_mm->brk) { - rc = task_has_perm(current, current, - PROCESS__EXECHEAP); + rc = cred_has_perm(cred, cred, PROCESS__EXECHEAP); } else if (!vma->vm_file && vma->vm_start <= vma->vm_mm->start_stack && vma->vm_end >= vma->vm_mm->start_stack) { - rc = task_has_perm(current, current, PROCESS__EXECSTACK); + rc = current_has_perm(current, PROCESS__EXECSTACK); } else if (vma->vm_file && vma->anon_vma) { /* * We are making executable a file mapping that has @@ -3041,8 +3101,7 @@ static int selinux_file_mprotect(struct vm_area_struct *vma, * modified content. This typically should only * occur for text relocations. */ - rc = file_has_perm(current, vma->vm_file, - FILE__EXECMOD); + rc = file_has_perm(cred, vma->vm_file, FILE__EXECMOD); } if (rc) return rc; @@ -3054,12 +3113,15 @@ static int selinux_file_mprotect(struct vm_area_struct *vma, static int selinux_file_lock(struct file *file, unsigned int cmd) { - return file_has_perm(current, file, FILE__LOCK); + const struct cred *cred = current_cred(); + + return file_has_perm(cred, file, FILE__LOCK); } static int selinux_file_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { + const struct cred *cred = current_cred(); int err = 0; switch (cmd) { @@ -3070,7 +3132,7 @@ static int selinux_file_fcntl(struct file *file, unsigned int cmd, } if ((file->f_flags & O_APPEND) && !(arg & O_APPEND)) { - err = file_has_perm(current, file, FILE__WRITE); + err = file_has_perm(cred, file, FILE__WRITE); break; } /* fall through */ @@ -3080,7 +3142,7 @@ static int selinux_file_fcntl(struct file *file, unsigned int cmd, case F_GETOWN: case F_GETSIG: /* Just check FD__USE permission */ - err = file_has_perm(current, file, 0); + err = file_has_perm(cred, file, 0); break; case F_GETLK: case F_SETLK: @@ -3094,7 +3156,7 @@ static int selinux_file_fcntl(struct file *file, unsigned int cmd, err = -EINVAL; break; } - err = file_has_perm(current, file, FILE__LOCK); + err = file_has_perm(cred, file, FILE__LOCK); break; } @@ -3103,12 +3165,10 @@ static int selinux_file_fcntl(struct file *file, unsigned int cmd, static int selinux_file_set_fowner(struct file *file) { - struct task_security_struct *tsec; struct file_security_struct *fsec; - tsec = current->security; fsec = file->f_security; - fsec->fown_sid = tsec->sid; + fsec->fown_sid = current_sid(); return 0; } @@ -3117,14 +3177,13 @@ static int selinux_file_send_sigiotask(struct task_struct *tsk, struct fown_struct *fown, int signum) { struct file *file; + u32 sid = current_sid(); u32 perm; - struct task_security_struct *tsec; struct file_security_struct *fsec; /* struct fown_struct is never outside the context of a struct file */ file = container_of(fown, struct file, f_owner); - tsec = tsk->security; fsec = file->f_security; if (!signum) @@ -3132,20 +3191,23 @@ static int selinux_file_send_sigiotask(struct task_struct *tsk, else perm = signal_to_av(signum); - return avc_has_perm(fsec->fown_sid, tsec->sid, + return avc_has_perm(fsec->fown_sid, sid, SECCLASS_PROCESS, perm, NULL); } static int selinux_file_receive(struct file *file) { - return file_has_perm(current, file, file_to_av(file)); + const struct cred *cred = current_cred(); + + return file_has_perm(cred, file, file_to_av(file)); } -static int selinux_dentry_open(struct file *file) +static int selinux_dentry_open(struct file *file, const struct cred *cred) { struct file_security_struct *fsec; struct inode *inode; struct inode_security_struct *isec; + inode = file->f_path.dentry->d_inode; fsec = file->f_security; isec = inode->i_security; @@ -3166,7 +3228,7 @@ static int selinux_dentry_open(struct file *file) * new inode label or new policy. * This check is not redundant - do not remove. */ - return inode_has_perm(current, inode, file_to_av(file), NULL); + return inode_has_perm(cred, inode, open_file_to_av(file), NULL); } /* task security operations */ @@ -3179,36 +3241,88 @@ static int selinux_task_create(unsigned long clone_flags) if (rc) return rc; - return task_has_perm(current, current, PROCESS__FORK); + return current_has_perm(current, PROCESS__FORK); } -static int selinux_task_alloc_security(struct task_struct *tsk) +/* + * detach and free the LSM part of a set of credentials + */ +static void selinux_cred_free(struct cred *cred) { - struct task_security_struct *tsec1, *tsec2; - int rc; + struct task_security_struct *tsec = cred->security; + cred->security = NULL; + kfree(tsec); +} - tsec1 = current->security; +/* + * prepare a new set of credentials for modification + */ +static int selinux_cred_prepare(struct cred *new, const struct cred *old, + gfp_t gfp) +{ + const struct task_security_struct *old_tsec; + struct task_security_struct *tsec; - rc = task_alloc_security(tsk); - if (rc) - return rc; - tsec2 = tsk->security; + old_tsec = old->security; - tsec2->osid = tsec1->osid; - tsec2->sid = tsec1->sid; - - /* Retain the exec, fs, key, and sock SIDs across fork */ - tsec2->exec_sid = tsec1->exec_sid; - tsec2->create_sid = tsec1->create_sid; - tsec2->keycreate_sid = tsec1->keycreate_sid; - tsec2->sockcreate_sid = tsec1->sockcreate_sid; + tsec = kmemdup(old_tsec, sizeof(struct task_security_struct), gfp); + if (!tsec) + return -ENOMEM; + new->security = tsec; return 0; } -static void selinux_task_free_security(struct task_struct *tsk) +/* + * commit new credentials + */ +static void selinux_cred_commit(struct cred *new, const struct cred *old) { - task_free_security(tsk); + secondary_ops->cred_commit(new, old); +} + +/* + * set the security data for a kernel service + * - all the creation contexts are set to unlabelled + */ +static int selinux_kernel_act_as(struct cred *new, u32 secid) +{ + struct task_security_struct *tsec = new->security; + u32 sid = current_sid(); + int ret; + + ret = avc_has_perm(sid, secid, + SECCLASS_KERNEL_SERVICE, + KERNEL_SERVICE__USE_AS_OVERRIDE, + NULL); + if (ret == 0) { + tsec->sid = secid; + tsec->create_sid = 0; + tsec->keycreate_sid = 0; + tsec->sockcreate_sid = 0; + } + return ret; +} + +/* + * set the file creation context in a security record to the same as the + * objective context of the specified inode + */ +static int selinux_kernel_create_files_as(struct cred *new, struct inode *inode) +{ + struct inode_security_struct *isec = inode->i_security; + struct task_security_struct *tsec = new->security; + u32 sid = current_sid(); + int ret; + + ret = avc_has_perm(sid, isec->sid, + SECCLASS_KERNEL_SERVICE, + KERNEL_SERVICE__CREATE_FILES_AS, + NULL); + + if (ret == 0) + tsec->create_sid = isec->sid; + return 0; } static int selinux_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags) @@ -3222,9 +3336,10 @@ static int selinux_task_setuid(uid_t id0, uid_t id1, uid_t id2, int flags) return 0; } -static int selinux_task_post_setuid(uid_t id0, uid_t id1, uid_t id2, int flags) +static int selinux_task_fix_setuid(struct cred *new, const struct cred *old, + int flags) { - return secondary_ops->task_post_setuid(id0, id1, id2, flags); + return secondary_ops->task_fix_setuid(new, old, flags); } static int selinux_task_setgid(gid_t id0, gid_t id1, gid_t id2, int flags) @@ -3235,23 +3350,22 @@ static int selinux_task_setgid(gid_t id0, gid_t id1, gid_t id2, int flags) static int selinux_task_setpgid(struct task_struct *p, pid_t pgid) { - return task_has_perm(current, p, PROCESS__SETPGID); + return current_has_perm(p, PROCESS__SETPGID); } static int selinux_task_getpgid(struct task_struct *p) { - return task_has_perm(current, p, PROCESS__GETPGID); + return current_has_perm(p, PROCESS__GETPGID); } static int selinux_task_getsid(struct task_struct *p) { - return task_has_perm(current, p, PROCESS__GETSESSION); + return current_has_perm(p, PROCESS__GETSESSION); } static void selinux_task_getsecid(struct task_struct *p, u32 *secid) { - struct task_security_struct *tsec = p->security; - *secid = tsec->sid; + *secid = task_sid(p); } static int selinux_task_setgroups(struct group_info *group_info) @@ -3268,7 +3382,7 @@ static int selinux_task_setnice(struct task_struct *p, int nice) if (rc) return rc; - return task_has_perm(current, p, PROCESS__SETSCHED); + return current_has_perm(p, PROCESS__SETSCHED); } static int selinux_task_setioprio(struct task_struct *p, int ioprio) @@ -3279,12 +3393,12 @@ static int selinux_task_setioprio(struct task_struct *p, int ioprio) if (rc) return rc; - return task_has_perm(current, p, PROCESS__SETSCHED); + return current_has_perm(p, PROCESS__SETSCHED); } static int selinux_task_getioprio(struct task_struct *p) { - return task_has_perm(current, p, PROCESS__GETSCHED); + return current_has_perm(p, PROCESS__GETSCHED); } static int selinux_task_setrlimit(unsigned int resource, struct rlimit *new_rlim) @@ -3299,9 +3413,9 @@ static int selinux_task_setrlimit(unsigned int resource, struct rlimit *new_rlim /* Control the ability to change the hard limit (whether lowering or raising it), so that the hard limit can later be used as a safe reset point for the soft limit - upon context transitions. See selinux_bprm_apply_creds. */ + upon context transitions. See selinux_bprm_committing_creds. */ if (old_rlim->rlim_max != new_rlim->rlim_max) - return task_has_perm(current, current, PROCESS__SETRLIMIT); + return current_has_perm(current, PROCESS__SETRLIMIT); return 0; } @@ -3314,17 +3428,17 @@ static int selinux_task_setscheduler(struct task_struct *p, int policy, struct s if (rc) return rc; - return task_has_perm(current, p, PROCESS__SETSCHED); + return current_has_perm(p, PROCESS__SETSCHED); } static int selinux_task_getscheduler(struct task_struct *p) { - return task_has_perm(current, p, PROCESS__GETSCHED); + return current_has_perm(p, PROCESS__GETSCHED); } static int selinux_task_movememory(struct task_struct *p) { - return task_has_perm(current, p, PROCESS__SETSCHED); + return current_has_perm(p, PROCESS__SETSCHED); } static int selinux_task_kill(struct task_struct *p, struct siginfo *info, @@ -3332,7 +3446,6 @@ static int selinux_task_kill(struct task_struct *p, struct siginfo *info, { u32 perm; int rc; - struct task_security_struct *tsec; rc = secondary_ops->task_kill(p, info, sig, secid); if (rc) @@ -3342,11 +3455,11 @@ static int selinux_task_kill(struct task_struct *p, struct siginfo *info, perm = PROCESS__SIGNULL; /* null signal; existence test */ else perm = signal_to_av(sig); - tsec = p->security; if (secid) - rc = avc_has_perm(secid, tsec->sid, SECCLASS_PROCESS, perm, NULL); + rc = avc_has_perm(secid, task_sid(p), + SECCLASS_PROCESS, perm, NULL); else - rc = task_has_perm(current, p, perm); + rc = current_has_perm(p, perm); return rc; } @@ -3354,13 +3467,12 @@ static int selinux_task_prctl(int option, unsigned long arg2, unsigned long arg3, unsigned long arg4, - unsigned long arg5, - long *rc_p) + unsigned long arg5) { /* The current prctl operations do not appear to require any SELinux controls since they merely observe or modify the state of the current process. */ - return secondary_ops->task_prctl(option, arg2, arg3, arg4, arg5, rc_p); + return secondary_ops->task_prctl(option, arg2, arg3, arg4, arg5); } static int selinux_task_wait(struct task_struct *p) @@ -3368,27 +3480,14 @@ static int selinux_task_wait(struct task_struct *p) return task_has_perm(p, current, PROCESS__SIGCHLD); } -static void selinux_task_reparent_to_init(struct task_struct *p) -{ - struct task_security_struct *tsec; - - secondary_ops->task_reparent_to_init(p); - - tsec = p->security; - tsec->osid = tsec->sid; - tsec->sid = SECINITSID_KERNEL; - return; -} - static void selinux_task_to_inode(struct task_struct *p, struct inode *inode) { - struct task_security_struct *tsec = p->security; struct inode_security_struct *isec = inode->i_security; + u32 sid = task_sid(p); - isec->sid = tsec->sid; + isec->sid = sid; isec->initialized = 1; - return; } /* Returns error only if unable to parse addresses */ @@ -3627,19 +3726,19 @@ static int socket_has_perm(struct task_struct *task, struct socket *sock, u32 perms) { struct inode_security_struct *isec; - struct task_security_struct *tsec; struct avc_audit_data ad; + u32 sid; int err = 0; - tsec = task->security; isec = SOCK_INODE(sock)->i_security; if (isec->sid == SECINITSID_KERNEL) goto out; + sid = task_sid(task); AVC_AUDIT_DATA_INIT(&ad, NET); ad.u.net.sk = sock->sk; - err = avc_has_perm(tsec->sid, isec->sid, isec->sclass, perms, &ad); + err = avc_has_perm(sid, isec->sid, isec->sclass, perms, &ad); out: return err; @@ -3648,18 +3747,20 @@ out: static int selinux_socket_create(int family, int type, int protocol, int kern) { + const struct cred *cred = current_cred(); + const struct task_security_struct *tsec = cred->security; + u32 sid, newsid; + u16 secclass; int err = 0; - struct task_security_struct *tsec; - u32 newsid; if (kern) goto out; - tsec = current->security; - newsid = tsec->sockcreate_sid ? : tsec->sid; - err = avc_has_perm(tsec->sid, newsid, - socket_type_to_security_class(family, type, - protocol), SOCKET__CREATE, NULL); + sid = tsec->sid; + newsid = tsec->sockcreate_sid ?: sid; + + secclass = socket_type_to_security_class(family, type, protocol); + err = avc_has_perm(sid, newsid, secclass, SOCKET__CREATE, NULL); out: return err; @@ -3668,18 +3769,26 @@ out: static int selinux_socket_post_create(struct socket *sock, int family, int type, int protocol, int kern) { - int err = 0; + const struct cred *cred = current_cred(); + const struct task_security_struct *tsec = cred->security; struct inode_security_struct *isec; - struct task_security_struct *tsec; struct sk_security_struct *sksec; - u32 newsid; + u32 sid, newsid; + int err = 0; + + sid = tsec->sid; + newsid = tsec->sockcreate_sid; isec = SOCK_INODE(sock)->i_security; - tsec = current->security; - newsid = tsec->sockcreate_sid ? : tsec->sid; + if (kern) + isec->sid = SECINITSID_KERNEL; + else if (newsid) + isec->sid = newsid; + else + isec->sid = sid; + isec->sclass = socket_type_to_security_class(family, type, protocol); - isec->sid = kern ? SECINITSID_KERNEL : newsid; isec->initialized = 1; if (sock->sk) { @@ -3714,7 +3823,6 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in if (family == PF_INET || family == PF_INET6) { char *addrp; struct inode_security_struct *isec; - struct task_security_struct *tsec; struct avc_audit_data ad; struct sockaddr_in *addr4 = NULL; struct sockaddr_in6 *addr6 = NULL; @@ -3722,7 +3830,6 @@ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, in struct sock *sk = sock->sk; u32 sid, node_perm; - tsec = current->security; isec = SOCK_INODE(sock)->i_security; if (family == PF_INET) { @@ -4387,7 +4494,7 @@ static int selinux_nlmsg_perm(struct sock *sk, struct sk_buff *skb) "SELinux: unrecognized netlink message" " type=%hu for sclass=%hu\n", nlh->nlmsg_type, isec->sclass); - if (!selinux_enforcing) + if (!selinux_enforcing || security_get_allow_unknown()) err = 0; } @@ -4763,15 +4870,16 @@ static int ipc_alloc_security(struct task_struct *task, struct kern_ipc_perm *perm, u16 sclass) { - struct task_security_struct *tsec = task->security; struct ipc_security_struct *isec; + u32 sid; isec = kzalloc(sizeof(struct ipc_security_struct), GFP_KERNEL); if (!isec) return -ENOMEM; + sid = task_sid(task); isec->sclass = sclass; - isec->sid = tsec->sid; + isec->sid = sid; perm->security = isec; return 0; @@ -4809,17 +4917,16 @@ static void msg_msg_free_security(struct msg_msg *msg) static int ipc_has_perm(struct kern_ipc_perm *ipc_perms, u32 perms) { - struct task_security_struct *tsec; struct ipc_security_struct *isec; struct avc_audit_data ad; + u32 sid = current_sid(); - tsec = current->security; isec = ipc_perms->security; AVC_AUDIT_DATA_INIT(&ad, IPC); ad.u.ipc_id = ipc_perms->key; - return avc_has_perm(tsec->sid, isec->sid, isec->sclass, perms, &ad); + return avc_has_perm(sid, isec->sid, isec->sclass, perms, &ad); } static int selinux_msg_msg_alloc_security(struct msg_msg *msg) @@ -4835,22 +4942,21 @@ static void selinux_msg_msg_free_security(struct msg_msg *msg) /* message queue security operations */ static int selinux_msg_queue_alloc_security(struct msg_queue *msq) { - struct task_security_struct *tsec; struct ipc_security_struct *isec; struct avc_audit_data ad; + u32 sid = current_sid(); int rc; rc = ipc_alloc_security(current, &msq->q_perm, SECCLASS_MSGQ); if (rc) return rc; - tsec = current->security; isec = msq->q_perm.security; AVC_AUDIT_DATA_INIT(&ad, IPC); ad.u.ipc_id = msq->q_perm.key; - rc = avc_has_perm(tsec->sid, isec->sid, SECCLASS_MSGQ, + rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__CREATE, &ad); if (rc) { ipc_free_security(&msq->q_perm); @@ -4866,17 +4972,16 @@ static void selinux_msg_queue_free_security(struct msg_queue *msq) static int selinux_msg_queue_associate(struct msg_queue *msq, int msqflg) { - struct task_security_struct *tsec; struct ipc_security_struct *isec; struct avc_audit_data ad; + u32 sid = current_sid(); - tsec = current->security; isec = msq->q_perm.security; AVC_AUDIT_DATA_INIT(&ad, IPC); ad.u.ipc_id = msq->q_perm.key; - return avc_has_perm(tsec->sid, isec->sid, SECCLASS_MSGQ, + return avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__ASSOCIATE, &ad); } @@ -4910,13 +5015,12 @@ static int selinux_msg_queue_msgctl(struct msg_queue *msq, int cmd) static int selinux_msg_queue_msgsnd(struct msg_queue *msq, struct msg_msg *msg, int msqflg) { - struct task_security_struct *tsec; struct ipc_security_struct *isec; struct msg_security_struct *msec; struct avc_audit_data ad; + u32 sid = current_sid(); int rc; - tsec = current->security; isec = msq->q_perm.security; msec = msg->security; @@ -4928,9 +5032,7 @@ static int selinux_msg_queue_msgsnd(struct msg_queue *msq, struct msg_msg *msg, * Compute new sid based on current process and * message queue this message will be stored in */ - rc = security_transition_sid(tsec->sid, - isec->sid, - SECCLASS_MSG, + rc = security_transition_sid(sid, isec->sid, SECCLASS_MSG, &msec->sid); if (rc) return rc; @@ -4940,16 +5042,16 @@ static int selinux_msg_queue_msgsnd(struct msg_queue *msq, struct msg_msg *msg, ad.u.ipc_id = msq->q_perm.key; /* Can this process write to the queue? */ - rc = avc_has_perm(tsec->sid, isec->sid, SECCLASS_MSGQ, + rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__WRITE, &ad); if (!rc) /* Can this process send the message */ - rc = avc_has_perm(tsec->sid, msec->sid, - SECCLASS_MSG, MSG__SEND, &ad); + rc = avc_has_perm(sid, msec->sid, SECCLASS_MSG, + MSG__SEND, &ad); if (!rc) /* Can the message be put in the queue? */ - rc = avc_has_perm(msec->sid, isec->sid, - SECCLASS_MSGQ, MSGQ__ENQUEUE, &ad); + rc = avc_has_perm(msec->sid, isec->sid, SECCLASS_MSGQ, + MSGQ__ENQUEUE, &ad); return rc; } @@ -4958,23 +5060,22 @@ static int selinux_msg_queue_msgrcv(struct msg_queue *msq, struct msg_msg *msg, struct task_struct *target, long type, int mode) { - struct task_security_struct *tsec; struct ipc_security_struct *isec; struct msg_security_struct *msec; struct avc_audit_data ad; + u32 sid = task_sid(target); int rc; - tsec = target->security; isec = msq->q_perm.security; msec = msg->security; AVC_AUDIT_DATA_INIT(&ad, IPC); ad.u.ipc_id = msq->q_perm.key; - rc = avc_has_perm(tsec->sid, isec->sid, + rc = avc_has_perm(sid, isec->sid, SECCLASS_MSGQ, MSGQ__READ, &ad); if (!rc) - rc = avc_has_perm(tsec->sid, msec->sid, + rc = avc_has_perm(sid, msec->sid, SECCLASS_MSG, MSG__RECEIVE, &ad); return rc; } @@ -4982,22 +5083,21 @@ static int selinux_msg_queue_msgrcv(struct msg_queue *msq, struct msg_msg *msg, /* Shared Memory security operations */ static int selinux_shm_alloc_security(struct shmid_kernel *shp) { - struct task_security_struct *tsec; struct ipc_security_struct *isec; struct avc_audit_data ad; + u32 sid = current_sid(); int rc; rc = ipc_alloc_security(current, &shp->shm_perm, SECCLASS_SHM); if (rc) return rc; - tsec = current->security; isec = shp->shm_perm.security; AVC_AUDIT_DATA_INIT(&ad, IPC); ad.u.ipc_id = shp->shm_perm.key; - rc = avc_has_perm(tsec->sid, isec->sid, SECCLASS_SHM, + rc = avc_has_perm(sid, isec->sid, SECCLASS_SHM, SHM__CREATE, &ad); if (rc) { ipc_free_security(&shp->shm_perm); @@ -5013,17 +5113,16 @@ static void selinux_shm_free_security(struct shmid_kernel *shp) static int selinux_shm_associate(struct shmid_kernel *shp, int shmflg) { - struct task_security_struct *tsec; struct ipc_security_struct *isec; struct avc_audit_data ad; + u32 sid = current_sid(); - tsec = current->security; isec = shp->shm_perm.security; AVC_AUDIT_DATA_INIT(&ad, IPC); ad.u.ipc_id = shp->shm_perm.key; - return avc_has_perm(tsec->sid, isec->sid, SECCLASS_SHM, + return avc_has_perm(sid, isec->sid, SECCLASS_SHM, SHM__ASSOCIATE, &ad); } @@ -5081,22 +5180,21 @@ static int selinux_shm_shmat(struct shmid_kernel *shp, /* Semaphore security operations */ static int selinux_sem_alloc_security(struct sem_array *sma) { - struct task_security_struct *tsec; struct ipc_security_struct *isec; struct avc_audit_data ad; + u32 sid = current_sid(); int rc; rc = ipc_alloc_security(current, &sma->sem_perm, SECCLASS_SEM); if (rc) return rc; - tsec = current->security; isec = sma->sem_perm.security; AVC_AUDIT_DATA_INIT(&ad, IPC); ad.u.ipc_id = sma->sem_perm.key; - rc = avc_has_perm(tsec->sid, isec->sid, SECCLASS_SEM, + rc = avc_has_perm(sid, isec->sid, SECCLASS_SEM, SEM__CREATE, &ad); if (rc) { ipc_free_security(&sma->sem_perm); @@ -5112,17 +5210,16 @@ static void selinux_sem_free_security(struct sem_array *sma) static int selinux_sem_associate(struct sem_array *sma, int semflg) { - struct task_security_struct *tsec; struct ipc_security_struct *isec; struct avc_audit_data ad; + u32 sid = current_sid(); - tsec = current->security; isec = sma->sem_perm.security; AVC_AUDIT_DATA_INIT(&ad, IPC); ad.u.ipc_id = sma->sem_perm.key; - return avc_has_perm(tsec->sid, isec->sid, SECCLASS_SEM, + return avc_has_perm(sid, isec->sid, SECCLASS_SEM, SEM__ASSOCIATE, &ad); } @@ -5212,33 +5309,35 @@ static void selinux_d_instantiate(struct dentry *dentry, struct inode *inode) static int selinux_getprocattr(struct task_struct *p, char *name, char **value) { - struct task_security_struct *tsec; + const struct task_security_struct *__tsec; u32 sid; int error; unsigned len; if (current != p) { - error = task_has_perm(current, p, PROCESS__GETATTR); + error = current_has_perm(p, PROCESS__GETATTR); if (error) return error; } - tsec = p->security; + rcu_read_lock(); + __tsec = __task_cred(p)->security; if (!strcmp(name, "current")) - sid = tsec->sid; + sid = __tsec->sid; else if (!strcmp(name, "prev")) - sid = tsec->osid; + sid = __tsec->osid; else if (!strcmp(name, "exec")) - sid = tsec->exec_sid; + sid = __tsec->exec_sid; else if (!strcmp(name, "fscreate")) - sid = tsec->create_sid; + sid = __tsec->create_sid; else if (!strcmp(name, "keycreate")) - sid = tsec->keycreate_sid; + sid = __tsec->keycreate_sid; else if (!strcmp(name, "sockcreate")) - sid = tsec->sockcreate_sid; + sid = __tsec->sockcreate_sid; else - return -EINVAL; + goto invalid; + rcu_read_unlock(); if (!sid) return 0; @@ -5247,6 +5346,10 @@ static int selinux_getprocattr(struct task_struct *p, if (error) return error; return len; + +invalid: + rcu_read_unlock(); + return -EINVAL; } static int selinux_setprocattr(struct task_struct *p, @@ -5254,7 +5357,8 @@ static int selinux_setprocattr(struct task_struct *p, { struct task_security_struct *tsec; struct task_struct *tracer; - u32 sid = 0; + struct cred *new; + u32 sid = 0, ptsid; int error; char *str = value; @@ -5270,15 +5374,15 @@ static int selinux_setprocattr(struct task_struct *p, * above restriction is ever removed. */ if (!strcmp(name, "exec")) - error = task_has_perm(current, p, PROCESS__SETEXEC); + error = current_has_perm(p, PROCESS__SETEXEC); else if (!strcmp(name, "fscreate")) - error = task_has_perm(current, p, PROCESS__SETFSCREATE); + error = current_has_perm(p, PROCESS__SETFSCREATE); else if (!strcmp(name, "keycreate")) - error = task_has_perm(current, p, PROCESS__SETKEYCREATE); + error = current_has_perm(p, PROCESS__SETKEYCREATE); else if (!strcmp(name, "sockcreate")) - error = task_has_perm(current, p, PROCESS__SETSOCKCREATE); + error = current_has_perm(p, PROCESS__SETSOCKCREATE); else if (!strcmp(name, "current")) - error = task_has_perm(current, p, PROCESS__SETCURRENT); + error = current_has_perm(p, PROCESS__SETCURRENT); else error = -EINVAL; if (error) @@ -5301,87 +5405,75 @@ static int selinux_setprocattr(struct task_struct *p, return error; } + new = prepare_creds(); + if (!new) + return -ENOMEM; + /* Permission checking based on the specified context is performed during the actual operation (execve, open/mkdir/...), when we know the full context of the - operation. See selinux_bprm_set_security for the execve + operation. See selinux_bprm_set_creds for the execve checks and may_create for the file creation checks. The operation will then fail if the context is not permitted. */ - tsec = p->security; - if (!strcmp(name, "exec")) + tsec = new->security; + if (!strcmp(name, "exec")) { tsec->exec_sid = sid; - else if (!strcmp(name, "fscreate")) + } else if (!strcmp(name, "fscreate")) { tsec->create_sid = sid; - else if (!strcmp(name, "keycreate")) { + } else if (!strcmp(name, "keycreate")) { error = may_create_key(sid, p); if (error) - return error; + goto abort_change; tsec->keycreate_sid = sid; - } else if (!strcmp(name, "sockcreate")) + } else if (!strcmp(name, "sockcreate")) { tsec->sockcreate_sid = sid; - else if (!strcmp(name, "current")) { - struct av_decision avd; - + } else if (!strcmp(name, "current")) { + error = -EINVAL; if (sid == 0) - return -EINVAL; - /* - * SELinux allows to change context in the following case only. - * - Single threaded processes. - * - Multi threaded processes intend to change its context into - * more restricted domain (defined by TYPEBOUNDS statement). - */ - if (atomic_read(&p->mm->mm_users) != 1) { - struct task_struct *g, *t; - struct mm_struct *mm = p->mm; - read_lock(&tasklist_lock); - do_each_thread(g, t) { - if (t->mm == mm && t != p) { - read_unlock(&tasklist_lock); - error = security_bounded_transition(tsec->sid, sid); - if (!error) - goto boundary_ok; + goto abort_change; - return error; - } - } while_each_thread(g, t); - read_unlock(&tasklist_lock); + /* Only allow single threaded processes to change context */ + error = -EPERM; + if (!is_single_threaded(p)) { + error = security_bounded_transition(tsec->sid, sid); + if (error) + goto abort_change; } -boundary_ok: /* Check permissions for the transition. */ error = avc_has_perm(tsec->sid, sid, SECCLASS_PROCESS, PROCESS__DYNTRANSITION, NULL); if (error) - return error; + goto abort_change; /* Check for ptracing, and update the task SID if ok. Otherwise, leave SID unchanged and fail. */ + ptsid = 0; task_lock(p); - rcu_read_lock(); tracer = tracehook_tracer_task(p); - if (tracer != NULL) { - struct task_security_struct *ptsec = tracer->security; - u32 ptsid = ptsec->sid; - rcu_read_unlock(); - error = avc_has_perm_noaudit(ptsid, sid, - SECCLASS_PROCESS, - PROCESS__PTRACE, 0, &avd); - if (!error) - tsec->sid = sid; - task_unlock(p); - avc_audit(ptsid, sid, SECCLASS_PROCESS, - PROCESS__PTRACE, &avd, error, NULL); - if (error) - return error; - } else { - rcu_read_unlock(); - tsec->sid = sid; - task_unlock(p); - } - } else - return -EINVAL; + if (tracer) + ptsid = task_sid(tracer); + task_unlock(p); + if (tracer) { + error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS, + PROCESS__PTRACE, NULL); + if (error) + goto abort_change; + } + + tsec->sid = sid; + } else { + error = -EINVAL; + goto abort_change; + } + + commit_creds(new); return size; + +abort_change: + abort_creds(new); + return error; } static int selinux_secid_to_secctx(u32 secid, char **secdata, u32 *seclen) @@ -5401,22 +5493,23 @@ static void selinux_release_secctx(char *secdata, u32 seclen) #ifdef CONFIG_KEYS -static int selinux_key_alloc(struct key *k, struct task_struct *tsk, +static int selinux_key_alloc(struct key *k, const struct cred *cred, unsigned long flags) { - struct task_security_struct *tsec = tsk->security; + const struct task_security_struct *tsec; struct key_security_struct *ksec; ksec = kzalloc(sizeof(struct key_security_struct), GFP_KERNEL); if (!ksec) return -ENOMEM; + tsec = cred->security; if (tsec->keycreate_sid) ksec->sid = tsec->keycreate_sid; else ksec->sid = tsec->sid; - k->security = ksec; + k->security = ksec; return 0; } @@ -5429,17 +5522,12 @@ static void selinux_key_free(struct key *k) } static int selinux_key_permission(key_ref_t key_ref, - struct task_struct *ctx, - key_perm_t perm) + const struct cred *cred, + key_perm_t perm) { struct key *key; - struct task_security_struct *tsec; struct key_security_struct *ksec; - - key = key_ref_to_ptr(key_ref); - - tsec = ctx->security; - ksec = key->security; + u32 sid; /* if no specific permissions are requested, we skip the permission check. No serious, additional covert channels @@ -5447,8 +5535,12 @@ static int selinux_key_permission(key_ref_t key_ref, if (perm == 0) return 0; - return avc_has_perm(tsec->sid, ksec->sid, - SECCLASS_KEY, perm, NULL); + sid = cred_sid(cred); + + key = key_ref_to_ptr(key_ref); + ksec = key->security; + + return avc_has_perm(sid, ksec->sid, SECCLASS_KEY, perm, NULL); } static int selinux_key_getsecurity(struct key *key, char **_buffer) @@ -5473,8 +5565,7 @@ static struct security_operations selinux_ops = { .ptrace_may_access = selinux_ptrace_may_access, .ptrace_traceme = selinux_ptrace_traceme, .capget = selinux_capget, - .capset_check = selinux_capset_check, - .capset_set = selinux_capset_set, + .capset = selinux_capset, .sysctl = selinux_sysctl, .capable = selinux_capable, .quotactl = selinux_quotactl, @@ -5485,12 +5576,10 @@ static struct security_operations selinux_ops = { .netlink_send = selinux_netlink_send, .netlink_recv = selinux_netlink_recv, - .bprm_alloc_security = selinux_bprm_alloc_security, - .bprm_free_security = selinux_bprm_free_security, - .bprm_apply_creds = selinux_bprm_apply_creds, - .bprm_post_apply_creds = selinux_bprm_post_apply_creds, - .bprm_set_security = selinux_bprm_set_security, + .bprm_set_creds = selinux_bprm_set_creds, .bprm_check_security = selinux_bprm_check_security, + .bprm_committing_creds = selinux_bprm_committing_creds, + .bprm_committed_creds = selinux_bprm_committed_creds, .bprm_secureexec = selinux_bprm_secureexec, .sb_alloc_security = selinux_sb_alloc_security, @@ -5549,10 +5638,13 @@ static struct security_operations selinux_ops = { .dentry_open = selinux_dentry_open, .task_create = selinux_task_create, - .task_alloc_security = selinux_task_alloc_security, - .task_free_security = selinux_task_free_security, + .cred_free = selinux_cred_free, + .cred_prepare = selinux_cred_prepare, + .cred_commit = selinux_cred_commit, + .kernel_act_as = selinux_kernel_act_as, + .kernel_create_files_as = selinux_kernel_create_files_as, .task_setuid = selinux_task_setuid, - .task_post_setuid = selinux_task_post_setuid, + .task_fix_setuid = selinux_task_fix_setuid, .task_setgid = selinux_task_setgid, .task_setpgid = selinux_task_setpgid, .task_getpgid = selinux_task_getpgid, @@ -5569,7 +5661,6 @@ static struct security_operations selinux_ops = { .task_kill = selinux_task_kill, .task_wait = selinux_task_wait, .task_prctl = selinux_task_prctl, - .task_reparent_to_init = selinux_task_reparent_to_init, .task_to_inode = selinux_task_to_inode, .ipc_permission = selinux_ipc_permission, @@ -5665,8 +5756,6 @@ static struct security_operations selinux_ops = { static __init int selinux_init(void) { - struct task_security_struct *tsec; - if (!security_module_enable(&selinux_ops)) { selinux_enabled = 0; return 0; @@ -5680,10 +5769,7 @@ static __init int selinux_init(void) printk(KERN_INFO "SELinux: Initializing.\n"); /* Set the security state for the initial task. */ - if (task_alloc_security(current)) - panic("SELinux: Failed to initialize initial task.\n"); - tsec = current->security; - tsec->osid = tsec->sid = SECINITSID_KERNEL; + cred_init_security(); sel_inode_cache = kmem_cache_create("selinux_inode_security", sizeof(struct inode_security_struct), diff --git a/security/selinux/include/av_perm_to_string.h b/security/selinux/include/av_perm_to_string.h index 1223b4ff9be..c0c885427b9 100644 --- a/security/selinux/include/av_perm_to_string.h +++ b/security/selinux/include/av_perm_to_string.h @@ -176,3 +176,5 @@ S_(SECCLASS_DCCP_SOCKET, DCCP_SOCKET__NAME_CONNECT, "name_connect") S_(SECCLASS_MEMPROTECT, MEMPROTECT__MMAP_ZERO, "mmap_zero") S_(SECCLASS_PEER, PEER__RECV, "recv") + S_(SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__USE_AS_OVERRIDE, "use_as_override") + S_(SECCLASS_KERNEL_SERVICE, KERNEL_SERVICE__CREATE_FILES_AS, "create_files_as") diff --git a/security/selinux/include/av_permissions.h b/security/selinux/include/av_permissions.h index c4c51165c50..0ba79fe00e1 100644 --- a/security/selinux/include/av_permissions.h +++ b/security/selinux/include/av_permissions.h @@ -841,3 +841,5 @@ #define DCCP_SOCKET__NAME_CONNECT 0x00800000UL #define MEMPROTECT__MMAP_ZERO 0x00000001UL #define PEER__RECV 0x00000001UL +#define KERNEL_SERVICE__USE_AS_OVERRIDE 0x00000001UL +#define KERNEL_SERVICE__CREATE_FILES_AS 0x00000002UL diff --git a/security/selinux/include/class_to_string.h b/security/selinux/include/class_to_string.h index bd813c366e3..21ec786611d 100644 --- a/security/selinux/include/class_to_string.h +++ b/security/selinux/include/class_to_string.h @@ -72,3 +72,8 @@ S_(NULL) S_("peer") S_("capability2") + S_(NULL) + S_(NULL) + S_(NULL) + S_(NULL) + S_("kernel_service") diff --git a/security/selinux/include/flask.h b/security/selinux/include/flask.h index febf8868e85..882f27d66fa 100644 --- a/security/selinux/include/flask.h +++ b/security/selinux/include/flask.h @@ -52,6 +52,7 @@ #define SECCLASS_MEMPROTECT 61 #define SECCLASS_PEER 68 #define SECCLASS_CAPABILITY2 69 +#define SECCLASS_KERNEL_SERVICE 74 /* * Security identifier indices for initial entities diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h index f8be8d7fa26..3cc45168f67 100644 --- a/security/selinux/include/objsec.h +++ b/security/selinux/include/objsec.h @@ -77,17 +77,6 @@ struct ipc_security_struct { u32 sid; /* SID of IPC resource */ }; -struct bprm_security_struct { - u32 sid; /* SID for transformed process */ - unsigned char set; - - /* - * unsafe is used to share failure information from bprm_apply_creds() - * to bprm_post_apply_creds(). - */ - char unsafe; -}; - struct netif_security_struct { int ifindex; /* device index */ u32 sid; /* SID for this interface */ diff --git a/security/selinux/nlmsgtab.c b/security/selinux/nlmsgtab.c index ff59c0c4804..4ed7bab89c5 100644 --- a/security/selinux/nlmsgtab.c +++ b/security/selinux/nlmsgtab.c @@ -63,6 +63,9 @@ static struct nlmsg_perm nlmsg_route_perms[] = { RTM_GETANYCAST, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_GETNEIGHTBL, NETLINK_ROUTE_SOCKET__NLMSG_READ }, { RTM_SETNEIGHTBL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, + { RTM_NEWADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, + { RTM_DELADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, + { RTM_GETADDRLABEL, NETLINK_ROUTE_SOCKET__NLMSG_READ }, }; static struct nlmsg_perm nlmsg_firewall_perms[] = diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c index 69c9dccc8cf..c8630363823 100644 --- a/security/selinux/selinuxfs.c +++ b/security/selinux/selinuxfs.c @@ -95,13 +95,18 @@ extern void selnl_notify_setenforce(int val); static int task_has_security(struct task_struct *tsk, u32 perms) { - struct task_security_struct *tsec; + const struct task_security_struct *tsec; + u32 sid = 0; - tsec = tsk->security; + rcu_read_lock(); + tsec = __task_cred(tsk)->security; + if (tsec) + sid = tsec->sid; + rcu_read_unlock(); if (!tsec) return -EACCES; - return avc_has_perm(tsec->sid, SECINITSID_SECURITY, + return avc_has_perm(sid, SECINITSID_SECURITY, SECCLASS_SECURITY, perms, NULL); } diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c index 8f17f542a11..c0eb72013d6 100644 --- a/security/selinux/xfrm.c +++ b/security/selinux/xfrm.c @@ -197,7 +197,7 @@ static int selinux_xfrm_sec_ctx_alloc(struct xfrm_sec_ctx **ctxp, struct xfrm_user_sec_ctx *uctx, u32 sid) { int rc = 0; - struct task_security_struct *tsec = current->security; + const struct task_security_struct *tsec = current_security(); struct xfrm_sec_ctx *ctx = NULL; char *ctx_str = NULL; u32 str_len; @@ -333,7 +333,7 @@ void selinux_xfrm_policy_free(struct xfrm_sec_ctx *ctx) */ int selinux_xfrm_policy_delete(struct xfrm_sec_ctx *ctx) { - struct task_security_struct *tsec = current->security; + const struct task_security_struct *tsec = current_security(); int rc = 0; if (ctx) { @@ -378,7 +378,7 @@ void selinux_xfrm_state_free(struct xfrm_state *x) */ int selinux_xfrm_state_delete(struct xfrm_state *x) { - struct task_security_struct *tsec = current->security; + const struct task_security_struct *tsec = current_security(); struct xfrm_sec_ctx *ctx = x->security; int rc = 0; diff --git a/security/smack/smack_access.c b/security/smack/smack_access.c index 79ff21ed4c3..247cec3b5a4 100644 --- a/security/smack/smack_access.c +++ b/security/smack/smack_access.c @@ -164,7 +164,7 @@ int smk_curacc(char *obj_label, u32 mode) { int rc; - rc = smk_access(current->security, obj_label, mode); + rc = smk_access(current_security(), obj_label, mode); if (rc == 0) return 0; @@ -173,7 +173,7 @@ int smk_curacc(char *obj_label, u32 mode) * only one that gets privilege and current does not * have that label. */ - if (smack_onlycap != NULL && smack_onlycap != current->security) + if (smack_onlycap != NULL && smack_onlycap != current->cred->security) return rc; if (capable(CAP_MAC_OVERRIDE)) diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c index 6e2dc0bab70..1b5551dfc1f 100644 --- a/security/smack/smack_lsm.c +++ b/security/smack/smack_lsm.c @@ -30,6 +30,8 @@ #include "smack.h" +#define task_security(task) (task_cred_xxx((task), security)) + /* * I hope these are the hokeyist lines of code in the module. Casey. */ @@ -102,7 +104,7 @@ static int smack_ptrace_may_access(struct task_struct *ctp, unsigned int mode) if (rc != 0) return rc; - rc = smk_access(current->security, ctp->security, MAY_READWRITE); + rc = smk_access(current_security(), task_security(ctp), MAY_READWRITE); if (rc != 0 && capable(CAP_MAC_OVERRIDE)) return 0; return rc; @@ -124,7 +126,7 @@ static int smack_ptrace_traceme(struct task_struct *ptp) if (rc != 0) return rc; - rc = smk_access(ptp->security, current->security, MAY_READWRITE); + rc = smk_access(task_security(ptp), current_security(), MAY_READWRITE); if (rc != 0 && has_capability(ptp, CAP_MAC_OVERRIDE)) return 0; return rc; @@ -141,7 +143,7 @@ static int smack_ptrace_traceme(struct task_struct *ptp) static int smack_syslog(int type) { int rc; - char *sp = current->security; + char *sp = current_security(); rc = cap_syslog(type); if (rc != 0) @@ -248,11 +250,12 @@ static int smack_sb_copy_data(char *orig, char *smackopts) /** * smack_sb_kern_mount - Smack specific mount processing * @sb: the file system superblock + * @flags: the mount flags * @data: the smack mount options * * Returns 0 on success, an error code on failure */ -static int smack_sb_kern_mount(struct super_block *sb, void *data) +static int smack_sb_kern_mount(struct super_block *sb, int flags, void *data) { struct dentry *root = sb->s_root; struct inode *inode = root->d_inode; @@ -373,7 +376,7 @@ static int smack_sb_umount(struct vfsmount *mnt, int flags) */ static int smack_inode_alloc_security(struct inode *inode) { - inode->i_security = new_inode_smack(current->security); + inode->i_security = new_inode_smack(current_security()); if (inode->i_security == NULL) return -ENOMEM; return 0; @@ -818,7 +821,7 @@ static int smack_file_permission(struct file *file, int mask) */ static int smack_file_alloc_security(struct file *file) { - file->f_security = current->security; + file->f_security = current_security(); return 0; } @@ -916,7 +919,7 @@ static int smack_file_fcntl(struct file *file, unsigned int cmd, */ static int smack_file_set_fowner(struct file *file) { - file->f_security = current->security; + file->f_security = current_security(); return 0; } @@ -941,7 +944,7 @@ static int smack_file_send_sigiotask(struct task_struct *tsk, * struct fown_struct is never outside the context of a struct file */ file = container_of(fown, struct file, f_owner); - rc = smk_access(file->f_security, tsk->security, MAY_WRITE); + rc = smk_access(file->f_security, tsk->cred->security, MAY_WRITE); if (rc != 0 && has_capability(tsk, CAP_MAC_OVERRIDE)) return 0; return rc; @@ -973,33 +976,75 @@ static int smack_file_receive(struct file *file) */ /** - * smack_task_alloc_security - "allocate" a task blob - * @tsk: the task in need of a blob - * - * Smack isn't using copies of blobs. Everyone - * points to an immutable list. No alloc required. - * No data copy required. - * - * Always returns 0 - */ -static int smack_task_alloc_security(struct task_struct *tsk) -{ - tsk->security = current->security; - - return 0; -} - -/** - * smack_task_free_security - "free" a task blob - * @task: the task with the blob + * smack_cred_free - "free" task-level security credentials + * @cred: the credentials in question * * Smack isn't using copies of blobs. Everyone * points to an immutable list. The blobs never go away. * There is no leak here. */ -static void smack_task_free_security(struct task_struct *task) +static void smack_cred_free(struct cred *cred) { - task->security = NULL; + cred->security = NULL; +} + +/** + * smack_cred_prepare - prepare new set of credentials for modification + * @new: the new credentials + * @old: the original credentials + * @gfp: the atomicity of any memory allocations + * + * Prepare a new set of credentials for modification. + */ +static int smack_cred_prepare(struct cred *new, const struct cred *old, + gfp_t gfp) +{ + new->security = old->security; + return 0; +} + +/* + * commit new credentials + * @new: the new credentials + * @old: the original credentials + */ +static void smack_cred_commit(struct cred *new, const struct cred *old) +{ +} + +/** + * smack_kernel_act_as - Set the subjective context in a set of credentials + * @new points to the set of credentials to be modified. + * @secid specifies the security ID to be set + * + * Set the security data for a kernel service. + */ +static int smack_kernel_act_as(struct cred *new, u32 secid) +{ + char *smack = smack_from_secid(secid); + + if (smack == NULL) + return -EINVAL; + + new->security = smack; + return 0; +} + +/** + * smack_kernel_create_files_as - Set the file creation label in a set of creds + * @new points to the set of credentials to be modified + * @inode points to the inode to use as a reference + * + * Set the file creation context in a set of credentials to the same + * as the objective context of the specified inode + */ +static int smack_kernel_create_files_as(struct cred *new, + struct inode *inode) +{ + struct inode_smack *isp = inode->i_security; + + new->security = isp->smk_inode; + return 0; } /** @@ -1011,7 +1056,7 @@ static void smack_task_free_security(struct task_struct *task) */ static int smack_task_setpgid(struct task_struct *p, pid_t pgid) { - return smk_curacc(p->security, MAY_WRITE); + return smk_curacc(task_security(p), MAY_WRITE); } /** @@ -1022,7 +1067,7 @@ static int smack_task_setpgid(struct task_struct *p, pid_t pgid) */ static int smack_task_getpgid(struct task_struct *p) { - return smk_curacc(p->security, MAY_READ); + return smk_curacc(task_security(p), MAY_READ); } /** @@ -1033,7 +1078,7 @@ static int smack_task_getpgid(struct task_struct *p) */ static int smack_task_getsid(struct task_struct *p) { - return smk_curacc(p->security, MAY_READ); + return smk_curacc(task_security(p), MAY_READ); } /** @@ -1045,7 +1090,7 @@ static int smack_task_getsid(struct task_struct *p) */ static void smack_task_getsecid(struct task_struct *p, u32 *secid) { - *secid = smack_to_secid(p->security); + *secid = smack_to_secid(task_security(p)); } /** @@ -1061,7 +1106,7 @@ static int smack_task_setnice(struct task_struct *p, int nice) rc = cap_task_setnice(p, nice); if (rc == 0) - rc = smk_curacc(p->security, MAY_WRITE); + rc = smk_curacc(task_security(p), MAY_WRITE); return rc; } @@ -1078,7 +1123,7 @@ static int smack_task_setioprio(struct task_struct *p, int ioprio) rc = cap_task_setioprio(p, ioprio); if (rc == 0) - rc = smk_curacc(p->security, MAY_WRITE); + rc = smk_curacc(task_security(p), MAY_WRITE); return rc; } @@ -1090,7 +1135,7 @@ static int smack_task_setioprio(struct task_struct *p, int ioprio) */ static int smack_task_getioprio(struct task_struct *p) { - return smk_curacc(p->security, MAY_READ); + return smk_curacc(task_security(p), MAY_READ); } /** @@ -1108,7 +1153,7 @@ static int smack_task_setscheduler(struct task_struct *p, int policy, rc = cap_task_setscheduler(p, policy, lp); if (rc == 0) - rc = smk_curacc(p->security, MAY_WRITE); + rc = smk_curacc(task_security(p), MAY_WRITE); return rc; } @@ -1120,7 +1165,7 @@ static int smack_task_setscheduler(struct task_struct *p, int policy, */ static int smack_task_getscheduler(struct task_struct *p) { - return smk_curacc(p->security, MAY_READ); + return smk_curacc(task_security(p), MAY_READ); } /** @@ -1131,7 +1176,7 @@ static int smack_task_getscheduler(struct task_struct *p) */ static int smack_task_movememory(struct task_struct *p) { - return smk_curacc(p->security, MAY_WRITE); + return smk_curacc(task_security(p), MAY_WRITE); } /** @@ -1154,13 +1199,13 @@ static int smack_task_kill(struct task_struct *p, struct siginfo *info, * can write the receiver. */ if (secid == 0) - return smk_curacc(p->security, MAY_WRITE); + return smk_curacc(task_security(p), MAY_WRITE); /* * If the secid isn't 0 we're dealing with some USB IO * specific behavior. This is not clean. For one thing * we can't take privilege into account. */ - return smk_access(smack_from_secid(secid), p->security, MAY_WRITE); + return smk_access(smack_from_secid(secid), task_security(p), MAY_WRITE); } /** @@ -1173,7 +1218,7 @@ static int smack_task_wait(struct task_struct *p) { int rc; - rc = smk_access(current->security, p->security, MAY_WRITE); + rc = smk_access(current_security(), task_security(p), MAY_WRITE); if (rc == 0) return 0; @@ -1204,7 +1249,7 @@ static int smack_task_wait(struct task_struct *p) static void smack_task_to_inode(struct task_struct *p, struct inode *inode) { struct inode_smack *isp = inode->i_security; - isp->smk_inode = p->security; + isp->smk_inode = task_security(p); } /* @@ -1223,7 +1268,7 @@ static void smack_task_to_inode(struct task_struct *p, struct inode *inode) */ static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags) { - char *csp = current->security; + char *csp = current_security(); struct socket_smack *ssp; ssp = kzalloc(sizeof(struct socket_smack), gfp_flags); @@ -1448,7 +1493,7 @@ static int smack_flags_to_may(int flags) */ static int smack_msg_msg_alloc_security(struct msg_msg *msg) { - msg->security = current->security; + msg->security = current_security(); return 0; } @@ -1484,7 +1529,7 @@ static int smack_shm_alloc_security(struct shmid_kernel *shp) { struct kern_ipc_perm *isp = &shp->shm_perm; - isp->security = current->security; + isp->security = current_security(); return 0; } @@ -1593,7 +1638,7 @@ static int smack_sem_alloc_security(struct sem_array *sma) { struct kern_ipc_perm *isp = &sma->sem_perm; - isp->security = current->security; + isp->security = current_security(); return 0; } @@ -1697,7 +1742,7 @@ static int smack_msg_queue_alloc_security(struct msg_queue *msq) { struct kern_ipc_perm *kisp = &msq->q_perm; - kisp->security = current->security; + kisp->security = current_security(); return 0; } @@ -1852,7 +1897,7 @@ static void smack_d_instantiate(struct dentry *opt_dentry, struct inode *inode) struct super_block *sbp; struct superblock_smack *sbsp; struct inode_smack *isp; - char *csp = current->security; + char *csp = current_security(); char *fetched; char *final; struct dentry *dp; @@ -2009,7 +2054,7 @@ static int smack_getprocattr(struct task_struct *p, char *name, char **value) if (strcmp(name, "current") != 0) return -EINVAL; - cp = kstrdup(p->security, GFP_KERNEL); + cp = kstrdup(task_security(p), GFP_KERNEL); if (cp == NULL) return -ENOMEM; @@ -2033,6 +2078,7 @@ static int smack_getprocattr(struct task_struct *p, char *name, char **value) static int smack_setprocattr(struct task_struct *p, char *name, void *value, size_t size) { + struct cred *new; char *newsmack; /* @@ -2055,7 +2101,11 @@ static int smack_setprocattr(struct task_struct *p, char *name, if (newsmack == NULL) return -EINVAL; - p->security = newsmack; + new = prepare_creds(); + if (!new) + return -ENOMEM; + new->security = newsmack; + commit_creds(new); return size; } @@ -2288,8 +2338,7 @@ static void smack_sock_graft(struct sock *sk, struct socket *parent) return; ssp = sk->sk_security; - ssp->smk_in = current->security; - ssp->smk_out = current->security; + ssp->smk_in = ssp->smk_out = current_security(); ssp->smk_packet[0] = '\0'; rc = smack_netlabel(sk); @@ -2352,17 +2401,17 @@ static int smack_inet_conn_request(struct sock *sk, struct sk_buff *skb, /** * smack_key_alloc - Set the key security blob * @key: object - * @tsk: the task associated with the key + * @cred: the credentials to use * @flags: unused * * No allocation required * * Returns 0 */ -static int smack_key_alloc(struct key *key, struct task_struct *tsk, +static int smack_key_alloc(struct key *key, const struct cred *cred, unsigned long flags) { - key->security = tsk->security; + key->security = cred->security; return 0; } @@ -2380,14 +2429,14 @@ static void smack_key_free(struct key *key) /* * smack_key_permission - Smack access on a key * @key_ref: gets to the object - * @context: task involved + * @cred: the credentials to use * @perm: unused * * Return 0 if the task has read and write to the object, * an error code otherwise */ static int smack_key_permission(key_ref_t key_ref, - struct task_struct *context, key_perm_t perm) + const struct cred *cred, key_perm_t perm) { struct key *keyp; @@ -2403,10 +2452,10 @@ static int smack_key_permission(key_ref_t key_ref, /* * This should not occur */ - if (context->security == NULL) + if (cred->security == NULL) return -EACCES; - return smk_access(context->security, keyp->security, MAY_READWRITE); + return smk_access(cred->security, keyp->security, MAY_READWRITE); } #endif /* CONFIG_KEYS */ @@ -2577,15 +2626,13 @@ struct security_operations smack_ops = { .ptrace_may_access = smack_ptrace_may_access, .ptrace_traceme = smack_ptrace_traceme, .capget = cap_capget, - .capset_check = cap_capset_check, - .capset_set = cap_capset_set, + .capset = cap_capset, .capable = cap_capable, .syslog = smack_syslog, .settime = cap_settime, .vm_enough_memory = cap_vm_enough_memory, - .bprm_apply_creds = cap_bprm_apply_creds, - .bprm_set_security = cap_bprm_set_security, + .bprm_set_creds = cap_bprm_set_creds, .bprm_secureexec = cap_bprm_secureexec, .sb_alloc_security = smack_sb_alloc_security, @@ -2627,9 +2674,12 @@ struct security_operations smack_ops = { .file_send_sigiotask = smack_file_send_sigiotask, .file_receive = smack_file_receive, - .task_alloc_security = smack_task_alloc_security, - .task_free_security = smack_task_free_security, - .task_post_setuid = cap_task_post_setuid, + .cred_free = smack_cred_free, + .cred_prepare = smack_cred_prepare, + .cred_commit = smack_cred_commit, + .kernel_act_as = smack_kernel_act_as, + .kernel_create_files_as = smack_kernel_create_files_as, + .task_fix_setuid = cap_task_fix_setuid, .task_setpgid = smack_task_setpgid, .task_getpgid = smack_task_getpgid, .task_getsid = smack_task_getsid, @@ -2642,7 +2692,6 @@ struct security_operations smack_ops = { .task_movememory = smack_task_movememory, .task_kill = smack_task_kill, .task_wait = smack_task_wait, - .task_reparent_to_init = cap_task_reparent_to_init, .task_to_inode = smack_task_to_inode, .task_prctl = cap_task_prctl, @@ -2718,6 +2767,8 @@ struct security_operations smack_ops = { */ static __init int smack_init(void) { + struct cred *cred; + if (!security_module_enable(&smack_ops)) return 0; @@ -2726,7 +2777,8 @@ static __init int smack_init(void) /* * Set the security state for the initial task. */ - current->security = &smack_known_floor.smk_known; + cred = (struct cred *) current->cred; + cred->security = &smack_known_floor.smk_known; /* * Initialize locks diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c index c21d8c8bf0c..ca257dfdc75 100644 --- a/security/smack/smackfs.c +++ b/security/smack/smackfs.c @@ -336,7 +336,7 @@ static void smk_cipso_doi(void) audit_info.loginuid = audit_get_loginuid(current); audit_info.sessionid = audit_get_sessionid(current); - audit_info.secid = smack_to_secid(current->security); + audit_info.secid = smack_to_secid(current_security()); rc = netlbl_cfg_map_del(NULL, &audit_info); if (rc != 0) @@ -371,7 +371,7 @@ static void smk_unlbl_ambient(char *oldambient) audit_info.loginuid = audit_get_loginuid(current); audit_info.sessionid = audit_get_sessionid(current); - audit_info.secid = smack_to_secid(current->security); + audit_info.secid = smack_to_secid(current_security()); if (oldambient != NULL) { rc = netlbl_cfg_map_del(oldambient, &audit_info); @@ -843,7 +843,7 @@ static ssize_t smk_write_onlycap(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { char in[SMK_LABELLEN]; - char *sp = current->security; + char *sp = current->cred->security; if (!capable(CAP_MAC_ADMIN)) return -EPERM;