[PATCH v6 18/44] instrumented.h: add KMSAN support

[Alexander Potapenko]

To avoid false positives, KMSAN needs to unpoison the data copied from
the userspace. To detect infoleaks - check the memory buffer passed to
copy_to_user().

Signed-off-by: Alexander Potapenko <glider@xxxxxxxxxx>
Reviewed-by: Marco Elver <elver@xxxxxxxxxx>

---
v2:
 -- move implementation of kmsan_copy_to_user() here

v5:
 -- simplify kmsan_copy_to_user()
 -- provide instrument_get_user() and instrument_put_user()

v6:
 -- rebase after changing "x86: asm: instrument usercopy in get_user()
    and put_user()"

Link: https://linux-review.googlesource.com/id/I43e93b9c02709e6be8d222342f1b044ac8bdbaaf
---
 include/linux/instrumented.h | 18 ++++++++++++-----
 include/linux/kmsan-checks.h | 19 ++++++++++++++++++
 mm/kmsan/hooks.c             | 38 ++++++++++++++++++++++++++++++++++++
 3 files changed, 70 insertions(+), 5 deletions(-)

diff --git a/include/linux/instrumented.h b/include/linux/instrumented.h
index 9f1dba8f717b0..501fa84867494 100644
--- a/include/linux/instrumented.h
+++ b/include/linux/instrumented.h
@@ -2,7 +2,7 @@
 
 /*
  * This header provides generic wrappers for memory access instrumentation that
- * the compiler cannot emit for: KASAN, KCSAN.
+ * the compiler cannot emit for: KASAN, KCSAN, KMSAN.
  */
 #ifndef _LINUX_INSTRUMENTED_H
 #define _LINUX_INSTRUMENTED_H
@@ -10,6 +10,7 @@
 #include <linux/compiler.h>
 #include <linux/kasan-checks.h>
 #include <linux/kcsan-checks.h>
+#include <linux/kmsan-checks.h>
 #include <linux/types.h>
 
 /**
@@ -117,6 +118,7 @@ instrument_copy_to_user(void __user *to, const void *from, unsigned long n)
 {
 	kasan_check_read(from, n);
 	kcsan_check_read(from, n);
+	kmsan_copy_to_user(to, from, n, 0);
 }
 
 /**
@@ -151,6 +153,7 @@ static __always_inline void
 instrument_copy_from_user_after(const void *to, const void __user *from,
 				unsigned long n, unsigned long left)
 {
+	kmsan_unpoison_memory(to, n - left);
 }
 
 /**
@@ -162,10 +165,14 @@ instrument_copy_from_user_after(const void *to, const void __user *from,
  *
  * @to destination variable, may not be address-taken
  */
-#define instrument_get_user(to)                         \
-({                                                      \
+#define instrument_get_user(to)				\
+({							\
+	u64 __tmp = (u64)(to);				\
+	kmsan_unpoison_memory(&__tmp, sizeof(__tmp));	\
+	to = __tmp;					\
 })
 
+
 /**
  * instrument_put_user() - add instrumentation to put_user()-like macros
  *
@@ -177,8 +184,9 @@ instrument_copy_from_user_after(const void *to, const void __user *from,
  * @ptr userspace pointer to copy to
  * @size number of bytes to copy
  */
-#define instrument_put_user(from, ptr, size)                    \
-({                                                              \
+#define instrument_put_user(from, ptr, size)			\
+({								\
+	kmsan_copy_to_user(ptr, &from, sizeof(from), 0);	\
 })
 
 #endif /* _LINUX_INSTRUMENTED_H */
diff --git a/include/linux/kmsan-checks.h b/include/linux/kmsan-checks.h
index a6522a0c28df9..c4cae333deec5 100644
--- a/include/linux/kmsan-checks.h
+++ b/include/linux/kmsan-checks.h
@@ -46,6 +46,21 @@ void kmsan_unpoison_memory(const void *address, size_t size);
  */
 void kmsan_check_memory(const void *address, size_t size);
 
+/**
+ * kmsan_copy_to_user() - Notify KMSAN about a data transfer to userspace.
+ * @to:      destination address in the userspace.
+ * @from:    source address in the kernel.
+ * @to_copy: number of bytes to copy.
+ * @left:    number of bytes not copied.
+ *
+ * If this is a real userspace data transfer, KMSAN checks the bytes that were
+ * actually copied to ensure there was no information leak. If @to belongs to
+ * the kernel space (which is possible for compat syscalls), KMSAN just copies
+ * the metadata.
+ */
+void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy,
+			size_t left);
+
 #else
 
 static inline void kmsan_poison_memory(const void *address, size_t size,
@@ -58,6 +73,10 @@ static inline void kmsan_unpoison_memory(const void *address, size_t size)
 static inline void kmsan_check_memory(const void *address, size_t size)
 {
 }
+static inline void kmsan_copy_to_user(void __user *to, const void *from,
+				      size_t to_copy, size_t left)
+{
+}
 
 #endif
 
diff --git a/mm/kmsan/hooks.c b/mm/kmsan/hooks.c
index 6f3e64b0b61f8..5c0eb25d984d7 100644
--- a/mm/kmsan/hooks.c
+++ b/mm/kmsan/hooks.c
@@ -205,6 +205,44 @@ void kmsan_iounmap_page_range(unsigned long start, unsigned long end)
 	kmsan_leave_runtime();
 }
 
+void kmsan_copy_to_user(void __user *to, const void *from, size_t to_copy,
+			size_t left)
+{
+	unsigned long ua_flags;
+
+	if (!kmsan_enabled || kmsan_in_runtime())
+		return;
+	/*
+	 * At this point we've copied the memory already. It's hard to check it
+	 * before copying, as the size of actually copied buffer is unknown.
+	 */
+
+	/* copy_to_user() may copy zero bytes. No need to check. */
+	if (!to_copy)
+		return;
+	/* Or maybe copy_to_user() failed to copy anything. */
+	if (to_copy <= left)
+		return;
+
+	ua_flags = user_access_save();
+	if ((u64)to < TASK_SIZE) {
+		/* This is a user memory access, check it. */
+		kmsan_internal_check_memory((void *)from, to_copy - left, to,
+					    REASON_COPY_TO_USER);
+	} else {
+		/* Otherwise this is a kernel memory access. This happens when a
+		 * compat syscall passes an argument allocated on the kernel
+		 * stack to a real syscall.
+		 * Don't check anything, just copy the shadow of the copied
+		 * bytes.
+		 */
+		kmsan_internal_memmove_metadata((void *)to, (void *)from,
+						to_copy - left);
+	}
+	user_access_restore(ua_flags);
+}
+EXPORT_SYMBOL(kmsan_copy_to_user);
+
 /* Functions from kmsan-checks.h follow. */
 void kmsan_poison_memory(const void *address, size_t size, gfp_t flags)
 {
-- 
2.37.2.789.g6183377224-goog