From bfedb589252c01fa505ac9f6f2a3d5d68d707ef4 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 13 Oct 2016 21:23:16 -0500 Subject: mm: Add a user_ns owner to mm_struct and fix ptrace permission checks During exec dumpable is cleared if the file that is being executed is not readable by the user executing the file. A bug in ptrace_may_access allows reading the file if the executable happens to enter into a subordinate user namespace (aka clone(CLONE_NEWUSER), unshare(CLONE_NEWUSER), or setns(fd, CLONE_NEWUSER). This problem is fixed with only necessary userspace breakage by adding a user namespace owner to mm_struct, captured at the time of exec, so it is clear in which user namespace CAP_SYS_PTRACE must be present in to be able to safely give read permission to the executable. The function ptrace_may_access is modified to verify that the ptracer has CAP_SYS_ADMIN in task->mm->user_ns instead of task->cred->user_ns. This ensures that if the task changes it's cred into a subordinate user namespace it does not become ptraceable. The function ptrace_attach is modified to only set PT_PTRACE_CAP when CAP_SYS_PTRACE is held over task->mm->user_ns. The intent of PT_PTRACE_CAP is to be a flag to note that whatever permission changes the task might go through the tracer has sufficient permissions for it not to be an issue. task->cred->user_ns is always the same as or descendent of mm->user_ns. Which guarantees that having CAP_SYS_PTRACE over mm->user_ns is the worst case for the tasks credentials. To prevent regressions mm->dumpable and mm->user_ns are not considered when a task has no mm. As simply failing ptrace_may_attach causes regressions in privileged applications attempting to read things such as /proc//stat Cc: stable@vger.kernel.org Acked-by: Kees Cook Tested-by: Cyrill Gorcunov Fixes: 8409cca70561 ("userns: allow ptrace from non-init user namespaces") Signed-off-by: "Eric W. Biederman" --- kernel/fork.c | 9 ++++++--- kernel/ptrace.c | 26 +++++++++++--------------- 2 files changed, 17 insertions(+), 18 deletions(-) (limited to 'kernel') diff --git a/kernel/fork.c b/kernel/fork.c index 997ac1d584f7..ba8a01564985 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -745,7 +745,8 @@ static void mm_init_owner(struct mm_struct *mm, struct task_struct *p) #endif } -static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) +static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, + struct user_namespace *user_ns) { mm->mmap = NULL; mm->mm_rb = RB_ROOT; @@ -785,6 +786,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p) if (init_new_context(p, mm)) goto fail_nocontext; + mm->user_ns = get_user_ns(user_ns); return mm; fail_nocontext: @@ -830,7 +832,7 @@ struct mm_struct *mm_alloc(void) return NULL; memset(mm, 0, sizeof(*mm)); - return mm_init(mm, current); + return mm_init(mm, current, current_user_ns()); } /* @@ -845,6 +847,7 @@ void __mmdrop(struct mm_struct *mm) destroy_context(mm); mmu_notifier_mm_destroy(mm); check_mm(mm); + put_user_ns(mm->user_ns); free_mm(mm); } EXPORT_SYMBOL_GPL(__mmdrop); @@ -1126,7 +1129,7 @@ static struct mm_struct *dup_mm(struct task_struct *tsk) memcpy(mm, oldmm, sizeof(*mm)); - if (!mm_init(mm, tsk)) + if (!mm_init(mm, tsk, mm->user_ns)) goto fail_nomem; err = dup_mmap(mm, oldmm); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index e6474f7272ec..282821557183 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -220,7 +220,7 @@ static int ptrace_has_cap(struct user_namespace *ns, unsigned int mode) static int __ptrace_may_access(struct task_struct *task, unsigned int mode) { const struct cred *cred = current_cred(), *tcred; - int dumpable = 0; + struct mm_struct *mm; kuid_t caller_uid; kgid_t caller_gid; @@ -271,16 +271,11 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode) return -EPERM; ok: rcu_read_unlock(); - smp_rmb(); - if (task->mm) - dumpable = get_dumpable(task->mm); - rcu_read_lock(); - if (dumpable != SUID_DUMP_USER && - !ptrace_has_cap(__task_cred(task)->user_ns, mode)) { - rcu_read_unlock(); - return -EPERM; - } - rcu_read_unlock(); + mm = task->mm; + if (mm && + ((get_dumpable(mm) != SUID_DUMP_USER) && + !ptrace_has_cap(mm->user_ns, mode))) + return -EPERM; return security_ptrace_access_check(task, mode); } @@ -331,6 +326,11 @@ static int ptrace_attach(struct task_struct *task, long request, task_lock(task); retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); + if (!retval) { + struct mm_struct *mm = task->mm; + if (mm && ns_capable(mm->user_ns, CAP_SYS_PTRACE)) + flags |= PT_PTRACE_CAP; + } task_unlock(task); if (retval) goto unlock_creds; @@ -344,10 +344,6 @@ static int ptrace_attach(struct task_struct *task, long request, if (seize) flags |= PT_SEIZED; - rcu_read_lock(); - if (ns_capable(__task_cred(task)->user_ns, CAP_SYS_PTRACE)) - flags |= PT_PTRACE_CAP; - rcu_read_unlock(); task->ptrace = flags; __ptrace_link(task, current); -- cgit v1.2.3 From 64b875f7ac8a5d60a4e191479299e931ee949b67 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 14 Nov 2016 18:48:07 -0600 Subject: ptrace: Capture the ptracer's creds not PT_PTRACE_CAP When the flag PT_PTRACE_CAP was added the PTRACE_TRACEME path was overlooked. This can result in incorrect behavior when an application like strace traces an exec of a setuid executable. Further PT_PTRACE_CAP does not have enough information for making good security decisions as it does not report which user namespace the capability is in. This has already allowed one mistake through insufficient granulariy. I found this issue when I was testing another corner case of exec and discovered that I could not get strace to set PT_PTRACE_CAP even when running strace as root with a full set of caps. This change fixes the above issue with strace allowing stracing as root a setuid executable without disabling setuid. More fundamentaly this change allows what is allowable at all times, by using the correct information in it's decision. Cc: stable@vger.kernel.org Fixes: 4214e42f96d4 ("v2.4.9.11 -> v2.4.9.12") Signed-off-by: "Eric W. Biederman" --- kernel/capability.c | 20 ++++++++++++++++++++ kernel/ptrace.c | 12 +++++++----- 2 files changed, 27 insertions(+), 5 deletions(-) (limited to 'kernel') diff --git a/kernel/capability.c b/kernel/capability.c index 00411c82dac5..dfa0e4528b0b 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -473,3 +473,23 @@ bool capable_wrt_inode_uidgid(const struct inode *inode, int cap) kgid_has_mapping(ns, inode->i_gid); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); + +/** + * ptracer_capable - Determine if the ptracer holds CAP_SYS_PTRACE in the namespace + * @tsk: The task that may be ptraced + * @ns: The user namespace to search for CAP_SYS_PTRACE in + * + * Return true if the task that is ptracing the current task had CAP_SYS_PTRACE + * in the specified user namespace. + */ +bool ptracer_capable(struct task_struct *tsk, struct user_namespace *ns) +{ + int ret = 0; /* An absent tracer adds no restrictions */ + const struct cred *cred; + rcu_read_lock(); + cred = rcu_dereference(tsk->ptracer_cred); + if (cred) + ret = security_capable_noaudit(cred, ns, CAP_SYS_PTRACE); + rcu_read_unlock(); + return (ret == 0); +} diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 282821557183..e82c15cadd6d 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -39,6 +39,9 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent) BUG_ON(!list_empty(&child->ptrace_entry)); list_add(&child->ptrace_entry, &new_parent->ptraced); child->parent = new_parent; + rcu_read_lock(); + child->ptracer_cred = get_cred(__task_cred(new_parent)); + rcu_read_unlock(); } /** @@ -71,12 +74,16 @@ void __ptrace_link(struct task_struct *child, struct task_struct *new_parent) */ void __ptrace_unlink(struct task_struct *child) { + const struct cred *old_cred; BUG_ON(!child->ptrace); clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE); child->parent = child->real_parent; list_del_init(&child->ptrace_entry); + old_cred = child->ptracer_cred; + child->ptracer_cred = NULL; + put_cred(old_cred); spin_lock(&child->sighand->siglock); child->ptrace = 0; @@ -326,11 +333,6 @@ static int ptrace_attach(struct task_struct *task, long request, task_lock(task); retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS); - if (!retval) { - struct mm_struct *mm = task->mm; - if (mm && ns_capable(mm->user_ns, CAP_SYS_PTRACE)) - flags |= PT_PTRACE_CAP; - } task_unlock(task); if (retval) goto unlock_creds; -- cgit v1.2.3 From 84d77d3f06e7e8dea057d10e8ec77ad71f721be3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Tue, 22 Nov 2016 12:06:50 -0600 Subject: ptrace: Don't allow accessing an undumpable mm It is the reasonable expectation that if an executable file is not readable there will be no way for a user without special privileges to read the file. This is enforced in ptrace_attach but if ptrace is already attached before exec there is no enforcement for read-only executables. As the only way to read such an mm is through access_process_vm spin a variant called ptrace_access_vm that will fail if the target process is not being ptraced by the current process, or the current process did not have sufficient privileges when ptracing began to read the target processes mm. In the ptrace implementations replace access_process_vm by ptrace_access_vm. There remain several ptrace sites that still use access_process_vm as they are reading the target executables instructions (for kernel consumption) or register stacks. As such it does not appear necessary to add a permission check to those calls. This bug has always existed in Linux. Fixes: v1.0 Cc: stable@vger.kernel.org Reported-by: Andy Lutomirski Signed-off-by: "Eric W. Biederman" --- kernel/ptrace.c | 42 ++++++++++++++++++++++++++++++++++++------ 1 file changed, 36 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/ptrace.c b/kernel/ptrace.c index e82c15cadd6d..49ba7c1ade9d 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -27,6 +27,35 @@ #include #include +/* + * Access another process' address space via ptrace. + * Source/target buffer must be kernel space, + * Do not walk the page table directly, use get_user_pages + */ +int ptrace_access_vm(struct task_struct *tsk, unsigned long addr, + void *buf, int len, unsigned int gup_flags) +{ + struct mm_struct *mm; + int ret; + + mm = get_task_mm(tsk); + if (!mm) + return 0; + + if (!tsk->ptrace || + (current != tsk->parent) || + ((get_dumpable(mm) != SUID_DUMP_USER) && + !ptracer_capable(tsk, mm->user_ns))) { + mmput(mm); + return 0; + } + + ret = __access_remote_vm(tsk, mm, addr, buf, len, gup_flags); + mmput(mm); + + return ret; +} + /* * ptrace a task: make the debugger its new parent and @@ -535,7 +564,8 @@ int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst int this_len, retval; this_len = (len > sizeof(buf)) ? sizeof(buf) : len; - retval = access_process_vm(tsk, src, buf, this_len, FOLL_FORCE); + retval = ptrace_access_vm(tsk, src, buf, this_len, FOLL_FORCE); + if (!retval) { if (copied) break; @@ -562,7 +592,7 @@ int ptrace_writedata(struct task_struct *tsk, char __user *src, unsigned long ds this_len = (len > sizeof(buf)) ? sizeof(buf) : len; if (copy_from_user(buf, src, this_len)) return -EFAULT; - retval = access_process_vm(tsk, dst, buf, this_len, + retval = ptrace_access_vm(tsk, dst, buf, this_len, FOLL_FORCE | FOLL_WRITE); if (!retval) { if (copied) @@ -1126,7 +1156,7 @@ int generic_ptrace_peekdata(struct task_struct *tsk, unsigned long addr, unsigned long tmp; int copied; - copied = access_process_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE); + copied = ptrace_access_vm(tsk, addr, &tmp, sizeof(tmp), FOLL_FORCE); if (copied != sizeof(tmp)) return -EIO; return put_user(tmp, (unsigned long __user *)data); @@ -1137,7 +1167,7 @@ int generic_ptrace_pokedata(struct task_struct *tsk, unsigned long addr, { int copied; - copied = access_process_vm(tsk, addr, &data, sizeof(data), + copied = ptrace_access_vm(tsk, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); return (copied == sizeof(data)) ? 0 : -EIO; } @@ -1155,7 +1185,7 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request, switch (request) { case PTRACE_PEEKTEXT: case PTRACE_PEEKDATA: - ret = access_process_vm(child, addr, &word, sizeof(word), + ret = ptrace_access_vm(child, addr, &word, sizeof(word), FOLL_FORCE); if (ret != sizeof(word)) ret = -EIO; @@ -1165,7 +1195,7 @@ int compat_ptrace_request(struct task_struct *child, compat_long_t request, case PTRACE_POKETEXT: case PTRACE_POKEDATA: - ret = access_process_vm(child, addr, &data, sizeof(data), + ret = ptrace_access_vm(child, addr, &data, sizeof(data), FOLL_FORCE | FOLL_WRITE); ret = (ret != sizeof(data) ? -EIO : 0); break; -- cgit v1.2.3 From f84df2a6f268de584a201e8911384a2d244876e3 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Wed, 16 Nov 2016 22:06:51 -0600 Subject: exec: Ensure mm->user_ns contains the execed files When the user namespace support was merged the need to prevent ptrace from revealing the contents of an unreadable executable was overlooked. Correct this oversight by ensuring that the executed file or files are in mm->user_ns, by adjusting mm->user_ns. Use the new function privileged_wrt_inode_uidgid to see if the executable is a member of the user namespace, and as such if having CAP_SYS_PTRACE in the user namespace should allow tracing the executable. If not update mm->user_ns to the parent user namespace until an appropriate parent is found. Cc: stable@vger.kernel.org Reported-by: Jann Horn Fixes: 9e4a36ece652 ("userns: Fail exec for suid and sgid binaries with ids outside our user namespace.") Signed-off-by: "Eric W. Biederman" --- kernel/capability.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/capability.c b/kernel/capability.c index dfa0e4528b0b..4984e1f552eb 100644 --- a/kernel/capability.c +++ b/kernel/capability.c @@ -456,6 +456,19 @@ bool file_ns_capable(const struct file *file, struct user_namespace *ns, } EXPORT_SYMBOL(file_ns_capable); +/** + * privileged_wrt_inode_uidgid - Do capabilities in the namespace work over the inode? + * @ns: The user namespace in question + * @inode: The inode in question + * + * Return true if the inode uid and gid are within the namespace. + */ +bool privileged_wrt_inode_uidgid(struct user_namespace *ns, const struct inode *inode) +{ + return kuid_has_mapping(ns, inode->i_uid) && + kgid_has_mapping(ns, inode->i_gid); +} + /** * capable_wrt_inode_uidgid - Check nsown_capable and uid and gid mapped * @inode: The inode in question @@ -469,8 +482,7 @@ bool capable_wrt_inode_uidgid(const struct inode *inode, int cap) { struct user_namespace *ns = current_user_ns(); - return ns_capable(ns, cap) && kuid_has_mapping(ns, inode->i_uid) && - kgid_has_mapping(ns, inode->i_gid); + return ns_capable(ns, cap) && privileged_wrt_inode_uidgid(ns, inode); } EXPORT_SYMBOL(capable_wrt_inode_uidgid); -- cgit v1.2.3