[Devel] [PATCH] seccomp, ptrace: add support for dumping seccomp filters

[Andrey Vagin]

From: Tycho Andersen <tycho.andersen at canonical.com>

ML: f8e529ed941ba2bbcbf310b575d968159ce7e895

https://jira.sw.ru/browse/PSBM-55322

This patch adds support for dumping a process' (classic BPF) seccomp
filters via ptrace.

PTRACE_SECCOMP_GET_FILTER allows the tracer to dump the user's classic BPF
seccomp filters. addr should be an integer which represents the ith seccomp
filter (0 is the most recently installed filter). data should be a struct
sock_filter * with enough room for the ith filter, or NULL, in which case
the filter is not saved. The return value for this command is the number of
BPF instructions the program represents, or negative in the case of errors.
Command specific errors are ENOENT: which indicates that there is no ith
filter in this seccomp tree, and EMEDIUMTYPE, which indicates that the ith
filter was not installed as a classic BPF filter.

A caveat with this approach is that there is no way to get explicitly at
the heirarchy of seccomp filters, and users need to memcmp() filters to
decide which are inherited. This means that a task which installs two of
the same filter can potentially confuse users of this interface.

v2: * make save_orig const
    * check that the orig_prog exists (not necessary right now, but when
       grows eBPF support it will be)
    * s/n/filter_off and make it an unsigned long to match ptrace
    * count "down" the tree instead of "up" when passing a filter offset

v3: * don't take the current task's lock for inspecting its seccomp mode
    * use a 0x42** constant for the ptrace command value

v4: * don't copy to userspace while holding spinlocks

v5: * add another condition to WARN_ON

v6: * rebase on net-next

Signed-off-by: Tycho Andersen <tycho.andersen at canonical.com>
Acked-by: Kees Cook <keescook at chromium.org>
CC: Will Drewry <wad at chromium.org>
Reviewed-by: Oleg Nesterov <oleg at redhat.com>
CC: Andy Lutomirski <luto at amacapital.net>
CC: Pavel Emelyanov <xemul at parallels.com>
CC: Serge E. Hallyn <serge.hallyn at ubuntu.com>
CC: Alexei Starovoitov <ast at kernel.org>
CC: Daniel Borkmann <daniel at iogearbox.net>
Acked-by: Alexei Starovoitov <ast at kernel.org>
Signed-off-by: David S. Miller <davem at davemloft.net>
---
 include/linux/seccomp.h     | 11 ++++++++
 include/uapi/linux/ptrace.h |  2 ++
 kernel/ptrace.c             |  5 ++++
 kernel/seccomp.c            | 62 +++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 80 insertions(+)

diff --git a/include/linux/seccomp.h b/include/linux/seccomp.h
index 6f19cfd..fd83f3e 100644
--- a/include/linux/seccomp.h
+++ b/include/linux/seccomp.h
@@ -87,4 +87,15 @@ static inline void get_seccomp_filter(struct task_struct *tsk)
 	return;
 }
 #endif /* CONFIG_SECCOMP_FILTER */
+
+#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);
+#else
+static inline long seccomp_get_filter(struct task_struct *task,
+				      unsigned long n, void __user *data)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_SECCOMP_FILTER && CONFIG_CHECKPOINT_RESTORE */
 #endif /* _LINUX_SECCOMP_H */
diff --git a/include/uapi/linux/ptrace.h b/include/uapi/linux/ptrace.h
index a7a6979..fb81065 100644
--- a/include/uapi/linux/ptrace.h
+++ b/include/uapi/linux/ptrace.h
@@ -64,6 +64,8 @@ struct ptrace_peeksiginfo_args {
 #define PTRACE_GETSIGMASK	0x420a
 #define PTRACE_SETSIGMASK	0x420b
 
+#define PTRACE_SECCOMP_GET_FILTER	0x420c
+
 /* Read signals from a shared (process wide) queue */
 #define PTRACE_PEEKSIGINFO_SHARED	(1 << 0)
 
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index f26c160..fb4f3bf 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -1039,6 +1039,11 @@ int ptrace_request(struct task_struct *child, long request,
 		break;
 	}
 #endif
+
+	case PTRACE_SECCOMP_GET_FILTER:
+		ret = seccomp_get_filter(child, addr, datavp);
+		break;
+
 	default:
 		break;
 	}
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index c1bac82..574b784 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -515,3 +515,65 @@ long prctl_set_seccomp(unsigned long seccomp_mode, char __user *filter)
 out:
 	return ret;
 }
+
+#if defined(CONFIG_SECCOMP_FILTER) && defined(CONFIG_CHECKPOINT_RESTORE)
+long seccomp_get_filter(struct task_struct *task, unsigned long filter_off,
+			void __user *data)
+{
+	struct seccomp_filter *filter;
+	long ret;
+	unsigned long count = 0;
+
+	if (!capable(CAP_SYS_ADMIN) ||
+	    current->seccomp.mode != SECCOMP_MODE_DISABLED) {
+		return -EACCES;
+	}
+
+	spin_lock_irq(&task->sighand->siglock);
+	if (task->seccomp.mode != SECCOMP_MODE_FILTER) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	filter = task->seccomp.filter;
+	while (filter) {
+		filter = filter->prev;
+		count++;
+	}
+
+	if (filter_off >= count) {
+		ret = -ENOENT;
+		goto out;
+	}
+	count -= filter_off;
+
+	filter = task->seccomp.filter;
+	while (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;
+		goto out;
+	}
+
+	ret = filter->len;
+	if (!data)
+		goto out;
+
+	get_seccomp_filter(task);
+	spin_unlock_irq(&task->sighand->siglock);
+
+	if (copy_to_user(data, filter->insns, filter->len))
+		ret = -EFAULT;
+
+	put_seccomp_filter(task);
+	return ret;
+
+out:
+	spin_unlock_irq(&task->sighand->siglock);
+	return ret;
+}
+#endif
-- 
2.7.4