ptrace: use fsuid, fsgid, effective creds for fs access checks

commit caaee6234d05a58c5b4d05e7bf766131b810a657 upstream.

By checking the effective credentials instead of the real UID / permitted
capabilities, ensure that the calling process actually intended to use its
credentials.

To ensure that all ptrace checks use the correct caller credentials (e.g.
in case out-of-tree code or newly added code omits the PTRACE_MODE_*CREDS
flag), use two new flags and require one of them to be set.

The problem was that when a privileged task had temporarily dropped its
privileges, e.g.  by calling setreuid(0, user_uid), with the intent to
perform following syscalls with the credentials of a user, it still passed
ptrace access checks that the user would not be able to pass.

While an attacker should not be able to convince the privileged task to
perform a ptrace() syscall, this is a problem because the ptrace access
check is reused for things in procfs.

In particular, the following somewhat interesting procfs entries only rely
on ptrace access checks:

 /proc/$pid/stat - uses the check for determining whether pointers
     should be visible, useful for bypassing ASLR
 /proc/$pid/maps - also useful for bypassing ASLR
 /proc/$pid/cwd - useful for gaining access to restricted
     directories that contain files with lax permissions, e.g. in
     this scenario:
     lrwxrwxrwx root root /proc/13020/cwd -> /root/foobar
     drwx------ root root /root
     drwxr-xr-x root root /root/foobar
     -rw-r--r-- root root /root/foobar/secret

Therefore, on a system where a root-owned mode 6755 binary changes its
effective credentials as described and then dumps a user-specified file,
this could be used by an attacker to reveal the memory layout of root's
processes or reveal the contents of files he is not allowed to access
(through /proc/$pid/cwd).

[akpm@linux-foundation.org: fix warning]
Signed-off-by: Jann Horn <jann@thejh.net>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: Casey Schaufler <casey@schaufler-ca.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: James Morris <james.l.morris@oracle.com>
Cc: "Serge E. Hallyn" <serge.hallyn@ubuntu.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Cc: Willy Tarreau <w@1wt.eu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/fs/proc/array.c b/fs/proc/array.c
index 09f0d9c374a32dd79d1fc10f5087510915db8a97..5c45eb5e4e0d389ddfabe1b92f9b379e9633ee8e 100644 (file)
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -398,7 +398,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 
        state = *get_task_state(task);
        vsize = eip = esp = 0;
-       permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT);
+       permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT);
        mm = get_task_mm(task);
        if (mm) {
                vsize = task_vsize(mm);

diff --git a/fs/proc/base.c b/fs/proc/base.c
index 8fc784aef0b8c1d12018f0c20e6f7ccb12d99b1f..7b5d453ebf5378a80f9d8eb6899e8377720a7e7e 100644 (file)
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -239,7 +239,7 @@ out:
 
 static int proc_pid_auxv(struct task_struct *task, char *buffer)
 {
-       struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ);
+       struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
        int res = PTR_ERR(mm);
        if (mm && !IS_ERR(mm)) {
                unsigned int nwords = 0;
@@ -269,7 +269,7 @@ static int proc_pid_wchan(struct task_struct *task, char *buffer)
        wchan = get_wchan(task);
 
        if (lookup_symbol_name(wchan, symname) < 0)
-               if (!ptrace_may_access(task, PTRACE_MODE_READ))
+               if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
                        return 0;
                else
                        return sprintf(buffer, "%lu", wchan);
@@ -283,7 +283,7 @@ static int lock_trace(struct task_struct *task)
        int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
        if (err)
                return err;
-       if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+       if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
                mutex_unlock(&task->signal->cred_guard_mutex);
                return -EPERM;
        }
@@ -557,7 +557,7 @@ static int proc_fd_access_allowed(struct inode *inode)
         */
        task = get_proc_task(inode);
        if (task) {
-               allowed = ptrace_may_access(task, PTRACE_MODE_READ);
+               allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
                put_task_struct(task);
        }
        return allowed;
@@ -592,7 +592,7 @@ static bool has_pid_permissions(struct pid_namespace *pid,
                return true;
        if (in_group_p(pid->pid_gid))
                return true;
-       return ptrace_may_access(task, PTRACE_MODE_READ);
+       return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
 }
 
 
@@ -707,7 +707,7 @@ static int __mem_open(struct inode *inode, struct file *file, unsigned int mode)
        if (!task)
                return -ESRCH;
 
-       mm = mm_access(task, mode);
+       mm = mm_access(task, mode | PTRACE_MODE_FSCREDS);
        put_task_struct(task);
 
        if (IS_ERR(mm))
@@ -1761,7 +1761,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
        if (!task)
                goto out_notask;
 
-       mm = mm_access(task, PTRACE_MODE_READ);
+       mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
        if (IS_ERR_OR_NULL(mm))
                goto out;
 
@@ -1896,7 +1896,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
                goto out;
 
        result = ERR_PTR(-EACCES);
-       if (!ptrace_may_access(task, PTRACE_MODE_READ))
+       if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
                goto out_put_task;
 
        result = ERR_PTR(-ENOENT);
@@ -1952,7 +1952,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir)
                goto out;
 
        ret = -EACCES;
-       if (!ptrace_may_access(task, PTRACE_MODE_READ))
+       if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
                goto out_put_task;
 
        ret = 0;
@@ -2488,7 +2488,7 @@ static int do_io_accounting(struct task_struct *task, char *buffer, int whole)
        if (result)
                return result;
 
-       if (!ptrace_may_access(task, PTRACE_MODE_READ)) {
+       if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
                result = -EACCES;
                goto out_unlock;
        }

diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 54bdc6701e9fd785ddc14c277a48ff455683d773..ac49a8d4aaf8b4a5d1a4b63e73dd242a079f5b78 100644 (file)
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -125,7 +125,7 @@ static void *proc_ns_follow_link(struct dentry *dentry, struct nameidata *nd)
        if (!task)
                goto out;
 
-       if (!ptrace_may_access(task, PTRACE_MODE_READ))
+       if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
                goto out_put_task;
 
        ns_path.dentry = proc_ns_get_dentry(sb, task, ei->ns.ns_ops);
@@ -158,7 +158,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
        if (!task)
                goto out;
 
-       if (!ptrace_may_access(task, PTRACE_MODE_READ))
+       if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
                goto out_put_task;
 
        len = -ENOENT;

diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index bb980ae6d9d3601524b1270c9f27880766e6d722..6af8988f5dddcbce247f8691befbf89a7fdac9a6 100644 (file)
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -56,7 +56,29 @@ extern void exit_ptrace(struct task_struct *tracer);
 #define PTRACE_MODE_READ       0x01
 #define PTRACE_MODE_ATTACH     0x02
 #define PTRACE_MODE_NOAUDIT    0x04
-/* Returns true on success, false on denial. */
+#define PTRACE_MODE_FSCREDS 0x08
+#define PTRACE_MODE_REALCREDS 0x10
+
+/* shorthands for READ/ATTACH and FSCREDS/REALCREDS combinations */
+#define PTRACE_MODE_READ_FSCREDS (PTRACE_MODE_READ | PTRACE_MODE_FSCREDS)
+#define PTRACE_MODE_READ_REALCREDS (PTRACE_MODE_READ | PTRACE_MODE_REALCREDS)
+#define PTRACE_MODE_ATTACH_FSCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_FSCREDS)
+#define PTRACE_MODE_ATTACH_REALCREDS (PTRACE_MODE_ATTACH | PTRACE_MODE_REALCREDS)
+
+/**
+ * ptrace_may_access - check whether the caller is permitted to access
+ * a target task.
+ * @task: target task
+ * @mode: selects type of access and caller credentials
+ *
+ * Returns true on success, false on denial.
+ *
+ * One of the flags PTRACE_MODE_FSCREDS and PTRACE_MODE_REALCREDS must
+ * be set in @mode to specify whether the access was requested through
+ * a filesystem syscall (should use effective capabilities and fsuid
+ * of the caller) or through an explicit syscall such as
+ * process_vm_writev or ptrace (and should use the real credentials).
+ */
 extern bool ptrace_may_access(struct task_struct *task, unsigned int mode);
 
 static inline int ptrace_reparented(struct task_struct *child)

diff --git a/kernel/events/core.c b/kernel/events/core.c
index f4021a97f687a08cd419b2b7336a07df4a776d73..0f52078396738a4098bd720535e15e2686ae4f57 100644 (file)
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2938,7 +2938,7 @@ find_lively_task_by_vpid(pid_t vpid)
 
        /* Reuse ptrace permission checks for now. */
        err = -EACCES;
-       if (!ptrace_may_access(task, PTRACE_MODE_READ))
+       if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS))
                goto errout;
 
        return task;

diff --git a/kernel/futex.c b/kernel/futex.c
index 625a4e659e7a8bf58d4cdbb6108e22218456f821..4d919452c90848dc3828cffd88f51407797e69cb 100644 (file)
--- a/kernel/futex.c
+++ b/kernel/futex.c
@@ -2620,7 +2620,7 @@ SYSCALL_DEFINE3(get_robust_list, int, pid,
        }
 
        ret = -EPERM;
-       if (!ptrace_may_access(p, PTRACE_MODE_READ))
+       if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
                goto err_unlock;
 
        head = p->robust_list;

diff --git a/kernel/futex_compat.c b/kernel/futex_compat.c
index f9f44fd4d34d443b1d7f28c3d5f3428b06aec614..3888617a1f9ef986a93db05975d33d88370196c1 100644 (file)
--- a/kernel/futex_compat.c
+++ b/kernel/futex_compat.c
@@ -155,7 +155,7 @@ COMPAT_SYSCALL_DEFINE3(get_robust_list, int, pid,
        }
 
        ret = -EPERM;
-       if (!ptrace_may_access(p, PTRACE_MODE_READ))
+       if (!ptrace_may_access(p, PTRACE_MODE_READ_REALCREDS))
                goto err_unlock;
 
        head = p->compat_robust_list;

diff --git a/kernel/kcmp.c b/kernel/kcmp.c
index 0aa69ea1d8fdcfa68046aa75b03c4373783a02fa..3a47fa998fe07277c592f62de36f59dad0d09f8b 100644 (file)
--- a/kernel/kcmp.c
+++ b/kernel/kcmp.c
@@ -122,8 +122,8 @@ SYSCALL_DEFINE5(kcmp, pid_t, pid1, pid_t, pid2, int, type,
                        &task2->signal->cred_guard_mutex);
        if (ret)
                goto err;
-       if (!ptrace_may_access(task1, PTRACE_MODE_READ) ||
-           !ptrace_may_access(task2, PTRACE_MODE_READ)) {
+       if (!ptrace_may_access(task1, PTRACE_MODE_READ_REALCREDS) ||
+           !ptrace_may_access(task2, PTRACE_MODE_READ_REALCREDS)) {
                ret = -EPERM;
                goto err_unlock;
        }

diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 30ab20623bcafc6861163f11323df8053b3d38be..72b0b3e0e06571d9948e60f1750f4f4155261809 100644 (file)
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -225,6 +225,14 @@ 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;
+       kuid_t caller_uid;
+       kgid_t caller_gid;
+
+       if (!(mode & PTRACE_MODE_FSCREDS) == !(mode & PTRACE_MODE_REALCREDS)) {
+               WARN(1, "denying ptrace access check without PTRACE_MODE_*CREDS\n");
+               return -EPERM;
+       }
 
        /* May we inspect the given task?
         * This check is used both for attaching with ptrace
@@ -234,18 +242,33 @@ static int __ptrace_may_access(struct task_struct *task, unsigned int mode)
         * because setting up the necessary parent/child relationship
         * or halting the specified task is impossible.
         */
-       int dumpable = 0;
+
        /* Don't let security modules deny introspection */
        if (same_thread_group(task, current))
                return 0;
        rcu_read_lock();
+       if (mode & PTRACE_MODE_FSCREDS) {
+               caller_uid = cred->fsuid;
+               caller_gid = cred->fsgid;
+       } else {
+               /*
+                * Using the euid would make more sense here, but something
+                * in userland might rely on the old behavior, and this
+                * shouldn't be a security problem since
+                * PTRACE_MODE_REALCREDS implies that the caller explicitly
+                * used a syscall that requests access to another process
+                * (and not a filesystem syscall to procfs).
+                */
+               caller_uid = cred->uid;
+               caller_gid = cred->gid;
+       }
        tcred = __task_cred(task);
-       if (uid_eq(cred->uid, tcred->euid) &&
-           uid_eq(cred->uid, tcred->suid) &&
-           uid_eq(cred->uid, tcred->uid)  &&
-           gid_eq(cred->gid, tcred->egid) &&
-           gid_eq(cred->gid, tcred->sgid) &&
-           gid_eq(cred->gid, tcred->gid))
+       if (uid_eq(caller_uid, tcred->euid) &&
+           uid_eq(caller_uid, tcred->suid) &&
+           uid_eq(caller_uid, tcred->uid)  &&
+           gid_eq(caller_gid, tcred->egid) &&
+           gid_eq(caller_gid, tcred->sgid) &&
+           gid_eq(caller_gid, tcred->gid))
                goto ok;
        if (ptrace_has_cap(tcred->user_ns, mode))
                goto ok;
@@ -312,7 +335,7 @@ static int ptrace_attach(struct task_struct *task, long request,
                goto out;
 
        task_lock(task);
-       retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH);
+       retval = __ptrace_may_access(task, PTRACE_MODE_ATTACH_REALCREDS);
        task_unlock(task);
        if (retval)
                goto unlock_creds;

diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index fd26d0433509e2b5885c74249a9eb04828285180..e739825be8b35b1f4e3fe40ab62101991160f466 100644 (file)
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -298,7 +298,7 @@ static ssize_t process_vm_rw_core(pid_t pid, const struct iovec *lvec,
                goto free_proc_pages;
        }
 
-       mm = mm_access(task, PTRACE_MODE_ATTACH);
+       mm = mm_access(task, PTRACE_MODE_ATTACH_REALCREDS);
        if (!mm || IS_ERR(mm)) {
                rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH;
                /*

diff --git a/security/commoncap.c b/security/commoncap.c
index c9219a66b7c6d99e557b4d8f36755842e2332e37..4fd7bf2b19e1d769bea8e5c7518eba22418ac016 100644 (file)
--- a/security/commoncap.c
+++ b/security/commoncap.c
@@ -142,12 +142,17 @@ int cap_ptrace_access_check(struct task_struct *child, unsigned int mode)
 {
        int ret = 0;
        const struct cred *cred, *child_cred;
+       const kernel_cap_t *caller_caps;
 
        rcu_read_lock();
        cred = current_cred();
        child_cred = __task_cred(child);
+       if (mode & PTRACE_MODE_FSCREDS)
+               caller_caps = &cred->cap_effective;
+       else
+               caller_caps = &cred->cap_permitted;
        if (cred->user_ns == child_cred->user_ns &&
-           cap_issubset(child_cred->cap_permitted, cred->cap_permitted))
+           cap_issubset(child_cred->cap_permitted, *caller_caps))
                goto out;
        if (ns_capable(child_cred->user_ns, CAP_SYS_PTRACE))
                goto out;