seccomp: hoist out filter resolving logic

With the new SECCOMP_FILTER_FLAG_LOG, we need to be able to extract these flags for checkpoint restore, since they describe the state of a filter.

So, let's add PTRACE_SECCOMP_GET_METADATA, similar to ..._GET_FILTER, which returns the metadata of the nth filter (right now, just the flags). Hopefully this will be future proof, and new per-filter metadata can be added to this struct.

v3: * use GET_METADATA instead of GET_FLAGS

Signed-off-by Tycho Andersen <[email protected]>

CC Kees Cook <[email protected]>

CC Andy Lutomirski <[email protected]>

CC Oleg Nesterov <[email protected]>

---
 include/linux/seccomp.h     |  8 ++++++++
 include/uapi/linux/ptrace.h |  6 ++++++
 kernel/ptrace.c             |  4 ++++
 kernel/seccomp.c            | 34 ++++++++++++++++++++++++++++++++++
 4 files changed, 52 insertions(+)

include/linux/seccomp.h +8 -0

index c8bef436b61d..a6dee99cd187 100644
@@ -94,11 +94,19 @@ static inline void get_seccomp_filter(struct task_struct *tsk)
 #if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE)
 extern long seccomp_get_filter(struct task_struct *task,
                               unsigned long filter_off, void __user *data);
+extern long seccomp_get_metadata(struct task_struct *task,
+                                unsigned long filter_off, void __user *data);
 #else
 static inline long seccomp_get_filter(struct task_struct *task,
                                      unsigned long n, void __user *data)
 {
        return -EINVAL;
 }
+static inline long seccomp_get_metadata(struct task_struct *task,
+                                       unsigned long filter_off,
+                                       void __user *data)
+{
+       return -EINVAL;
+}
 #endif /* CONFIG_SECCOMP_FILTER && CONFIG_CHECKPOINT_RESTORE */
 #endif /* _LINUX_SECCOMP_H */

include/uapi/linux/ptrace.h +6 -0

index fb8106509000..4e9774812dba 100644
@@ -65,6 +65,12 @@ struct ptrace_peeksiginfo_args {
 #define PTRACE_SETSIGMASK      0x420b
 
 #define PTRACE_SECCOMP_GET_FILTER      0x420c
+#define PTRACE_SECCOMP_GET_METADATA    0x420d
+
+struct seccomp_metadata {
+       unsigned long filter_off;       /* Input: which filter */
+       unsigned int flags;             /* Output: filter's flags */
+};
 
 /* Read signals from a shared (process wide) queue */
 #define PTRACE_PEEKSIGINFO_SHARED      (1 << 0)

kernel/ptrace.c +4 -0

index 84b1367935e4..58291e9f3276 100644
@@ -1092,6 +1092,10 @@ int ptrace_request(struct task_struct *child, long request,
                ret = seccomp_get_filter(child, addr, datavp);
                break;
 
+       case PTRACE_SECCOMP_GET_METADATA:
+               ret = seccomp_get_metadata(child, addr, datavp);
+               break;
+
        default:
                break;
        }

kernel/seccomp.c +34 -1

index 2e1568261ac4..ea762af4974d 100644
@@ -1060,6 +1060,40 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off,
        __put_seccomp_filter(filter);
        return ret;
 }
+
+long seccomp_get_metadata(struct task_struct *task,
+                         unsigned long size, void __user *data)
+{
+       long ret;
+       struct seccomp_filter *filter;
+       struct seccomp_metadata kmd = {};
+
+       if (!capable(CAP_SYS_ADMIN) ||
+           current->seccomp.mode != SECCOMP_MODE_DISABLED) {
+               return -EACCES;
+       }
+
+       size = min_t(unsigned long, size, sizeof(kmd));
+
+       if (copy_from_user(&kmd, data, size))
+               return -EFAULT;
+
+       filter = get_nth_filter(task, kmd.filter_off);
+       if (IS_ERR(filter))
+               return PTR_ERR(filter);
+
+       memset(&kmd, 0, sizeof(kmd));
+       if (filter->log)
+               kmd.flags |= SECCOMP_FILTER_FLAG_LOG;
+
+       ret = size;
+       if (copy_to_user(data, &kmd, size))
+               ret = -EFAULT;
+
+       __put_seccomp_filter(filter);
+       return ret;
+
+}
 #endif
 
 #ifdef CONFIG_SYSCTL
--

2.11.0

Hoist out the nth filter resolving logic that ptrace uses into a new function. We'll use this in the next patch to implement the new PTRACE_SECCOMP_GET_FILTER_FLAGS command.

v3: * significantly revamp get_nth_filter logic (Oleg)
* rebase on 4.14-rc4, using the new __{get,put}_seccomp_filter primitives

Signed-off-by Tycho Andersen <[email protected]>

CC Kees Cook <[email protected]>

CC Andy Lutomirski <[email protected]>

CC Oleg Nesterov <[email protected]>

---
 kernel/seccomp.c | 77 +++++++++++++++++++++++++++++++++-----------------------
 1 file changed, 45 insertions(+), 32 deletions(-)

kernel/seccomp.c +45 -33

index bb3a38005b9c..2e1568261ac4 100644
@@ -977,49 +977,68 @@ long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
 }
 
 #if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE)
-long seccomp_get_filter(struct task_struct *task, unsigned long filter_off,
-                       void __user *data)
+static struct seccomp_filter *get_nth_filter(struct task_struct *task,
+                                            unsigned long filter_off)
 {
-       struct seccomp_filter *filter;
-       struct sock_fprog_kern *fprog;
-       long ret;
-       unsigned long count = 0;
-
-       if (!capable(CAP_SYS_ADMIN) ||
-           current->seccomp.mode != SECCOMP_MODE_DISABLED) {
-               return -EACCES;
-       }
+       struct seccomp_filter *orig, *filter;
+       unsigned long count;
 
+       /*
+        * Note: this is only correct because the caller should be the (ptrace)
+        * tracer of the task, otherwise lock_task_sighand is needed.
+        */
        spin_lock_irq(&task->sighand->siglock);
+
        if (task->seccomp.mode != SECCOMP_MODE_FILTER) {
-               ret = -EINVAL;
-               goto out;
+               spin_unlock_irq(&task->sighand->siglock);
+               return ERR_PTR(-EINVAL);
        }
 
-       filter = task->seccomp.filter;
-       while (filter) {
-               filter = filter->prev;
+       orig = task->seccomp.filter;
+       __get_seccomp_filter(orig);
+       spin_unlock_irq(&task->sighand->siglock);
+
+       count = 0;
+       for (filter = orig; filter; filter = filter->prev)
                count++;
-       }
 
        if (filter_off >= count) {
-               ret = -ENOENT;
+               filter = ERR_PTR(-ENOENT);
                goto out;
        }
-       count -= filter_off;
 
-       filter = task->seccomp.filter;
-       while (filter && count > 1) {
-               filter = filter->prev;
+       count -= filter_off;
+       for (filter = orig; filter && count > 1; filter = filter->prev)
                count--;
-       }
 
        if (WARN_ON(count != 1 || !filter)) {
-               /* The filter tree shouldn't shrink while we're using it. */
-               ret = -ENOENT;
+               filter = ERR_PTR(-ENOENT);
                goto out;
        }
 
+       __get_seccomp_filter(filter);
+
+out:
+       __put_seccomp_filter(orig);
+       return filter;
+}
+
+long seccomp_get_filter(struct task_struct *task, unsigned long filter_off,
+                       void __user *data)
+{
+       struct seccomp_filter *filter;
+       struct sock_fprog_kern *fprog;
+       long ret;
+
+       if (!capable(CAP_SYS_ADMIN) ||
+           current->seccomp.mode != SECCOMP_MODE_DISABLED) {
+               return -EACCES;
+       }
+
+       filter = get_nth_filter(task, filter_off);
+       if (IS_ERR(filter))
+               return PTR_ERR(filter);
+
        fprog = filter->prog->orig_prog;
        if (!fprog) {
                /* This must be a new non-cBPF filter, since we save

@@ -1034,17 +1053,11 @@ long seccomp_get_filter(struct task_struct *task, unsigned long filter_off,
        if (!data)
                goto out;
 
-       __get_seccomp_filter(filter);
-       spin_unlock_irq(&task->sighand->siglock);
-
        if (copy_to_user(data, fprog->filter, bpf_classic_proglen(fprog)))
                ret = -EFAULT;
 
-       __put_seccomp_filter(filter);
-       return ret;
-
 out:
-       spin_unlock_irq(&task->sighand->siglock);
+       __put_seccomp_filter(filter);
        return ret;
 }
 #endif
--

2.11.0