arm64: uaccess: Fix omissions from usercopy whitelist

When the hardend usercopy support was added for arm64, it was
concluded that all cases of usercopy into and out of thread_struct
were statically sized and so didn't require explicit whitelisting
of the appropriate fields in thread_struct.

Testing with usercopy hardening enabled has revealed that this is
not the case for certain ptrace regset manipulation calls on arm64.
This occurs because the sizes of usercopies associated with the
regset API are dynamic by construction, and because arm64 does not
always stage such copies via the stack: indeed the regset API is
designed to avoid the need for that by adding some bounds checking.

This is currently believed to affect only the fpsimd and TLS
registers.

Because the whitelisted fields in thread_struct must be contiguous,
this patch groups them together in a nested struct.  It is also
necessary to be able to determine the location and size of that
struct, so rather than making the struct anonymous (which would
save on edits elsewhere) or adding an anonymous union containing
named and unnamed instances of the same struct (gross), this patch
gives the struct a name and makes the necessary edits to code that
references it (noisy but simple).

Care is needed to ensure that the new struct does not contain
padding (which the usercopy hardening would fail to protect).

For this reason, the presence of tp2_value is made unconditional,
since a padding field would be needed there in any case.  This pads
up to the 16-byte alignment required by struct user_fpsimd_state.

Acked-by: Kees Cook <keescook@chromium.org>
Reported-by: Mark Rutland <mark.rutland@arm.com>
Fixes: 9e8084d3f761 ("arm64: Implement thread_struct whitelist for hardened usercopy")
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

1 files changed, 25 insertions, 13 deletions

diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
index 63d3850db224..767598932549 100644
--- a/arch/arm64/include/asm/processor.h
+++ b/arch/arm64/include/asm/processor.h
@@ -34,6 +34,8 @@
 
 #ifdef __KERNEL__
 
+#include <linux/build_bug.h>
+#include <linux/stddef.h>
 #include <linux/string.h>
 
 #include <asm/alternative.h>
@@ -103,11 +105,18 @@ struct cpu_context {
 
 struct thread_struct {
 	struct cpu_context	cpu_context;	/* cpu context */
-	unsigned long		tp_value;	/* TLS register */
-#ifdef CONFIG_COMPAT
-	unsigned long		tp2_value;
-#endif
-	struct user_fpsimd_state fpsimd_state;
+
+	/*
+	 * Whitelisted fields for hardened usercopy:
+	 * Maintainers must ensure manually that this contains no
+	 * implicit padding.
+	 */
+	struct {
+		unsigned long	tp_value;	/* TLS register */
+		unsigned long	tp2_value;
+		struct user_fpsimd_state fpsimd_state;
+	} uw;
+
 	unsigned int		fpsimd_cpu;
 	void			*sve_state;	/* SVE registers, if any */
 	unsigned int		sve_vl;		/* SVE vector length */
@@ -117,14 +126,17 @@ struct thread_struct {
 	struct debug_info	debug;		/* debugging */
 };
 
-/*
- * Everything usercopied to/from thread_struct is statically-sized, so
- * no hardened usercopy whitelist is needed.
- */
 static inline void arch_thread_struct_whitelist(unsigned long *offset,
 						unsigned long *size)
 {
-	*offset = *size = 0;
+	/* Verify that there is no padding among the whitelisted fields: */
+	BUILD_BUG_ON(sizeof_field(struct thread_struct, uw) !=
+		     sizeof_field(struct thread_struct, uw.tp_value) +
+		     sizeof_field(struct thread_struct, uw.tp2_value) +
+		     sizeof_field(struct thread_struct, uw.fpsimd_state));
+
+	*offset = offsetof(struct thread_struct, uw);
+	*size = sizeof_field(struct thread_struct, uw);
 }
 
 #ifdef CONFIG_COMPAT
@@ -132,13 +144,13 @@ static inline void arch_thread_struct_whitelist(unsigned long *offset,
 ({									\
 	unsigned long *__tls;						\
 	if (is_compat_thread(task_thread_info(t)))			\
-		__tls = &(t)->thread.tp2_value;				\
+		__tls = &(t)->thread.uw.tp2_value;			\
 	else								\
-		__tls = &(t)->thread.tp_value;				\
+		__tls = &(t)->thread.uw.tp_value;			\
 	__tls;								\
  })
 #else
-#define task_user_tls(t)	(&(t)->thread.tp_value)
+#define task_user_tls(t)	(&(t)->thread.uw.tp_value)
 #endif
 
 /* Sync TPIDR_EL0 back to thread_struct for current */