From c7b6f29b6257532792fc722b68fcc0e00b5a856c Mon Sep 17 00:00:00 2001
From: Nadav Amit <namit@vmware.com>
Date: Thu, 25 Apr 2019 17:11:43 -0700
Subject: bpf: Fail bpf_probe_write_user() while mm is switched

When using a temporary mm, bpf_probe_write_user() should not be able to
write to user memory, since user memory addresses may be used to map
kernel memory.  Detect these cases and fail bpf_probe_write_user() in
such cases.

Suggested-by: Jann Horn <jannh@google.com>
Reported-by: Jann Horn <jannh@google.com>
Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <akpm@linux-foundation.org>
Cc: <ard.biesheuvel@linaro.org>
Cc: <deneen.t.dock@intel.com>
Cc: <kernel-hardening@lists.openwall.com>
Cc: <kristen@linux.intel.com>
Cc: <linux_dti@icloud.com>
Cc: <will.deacon@arm.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Rik van Riel <riel@surriel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20190426001143.4983-24-namit@vmware.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 kernel/trace/bpf_trace.c | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'kernel/trace/bpf_trace.c')

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index d64c00afceb5..94b0e37d90ef 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -14,6 +14,8 @@
 #include <linux/syscalls.h>
 #include <linux/error-injection.h>
 
+#include <asm/tlb.h>
+
 #include "trace_probe.h"
 #include "trace.h"
 
@@ -163,6 +165,10 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 	 * access_ok() should prevent writing to non-user memory, but in
 	 * some situations (nommu, temporary switch, etc) access_ok() does
 	 * not provide enough validation, hence the check on KERNEL_DS.
+	 *
+	 * nmi_uaccess_okay() ensures the probe is not run in an interim
+	 * state, when the task or mm are switched. This is specifically
+	 * required to prevent the use of temporary mm.
 	 */
 
 	if (unlikely(in_interrupt() ||
@@ -170,6 +176,8 @@ BPF_CALL_3(bpf_probe_write_user, void *, unsafe_ptr, const void *, src,
 		return -EPERM;
 	if (unlikely(uaccess_kernel()))
 		return -EPERM;
+	if (unlikely(!nmi_uaccess_okay()))
+		return -EPERM;
 	if (!access_ok(unsafe_ptr, size))
 		return -EPERM;
 
-- 
cgit v1.2.3