aarch32: Apply workaround for errata 813419 of Cortex-A57

TLBI instructions for monitor mode won't have the desired effect under
specific circumstances in Cortex-A57 r0p0. The workaround is to
execute DSB and TLBI twice each time.

Even though this errata is only needed in r0p0, the current errata
framework is not prepared to apply run-time workarounds. The current one
is always applied if compiled in, regardless of the CPU or its revision.

The `DSB` instruction used when initializing the translation tables has
been changed to `DSB ISH` as an optimization and to be consistent with
the barriers used for the workaround.

NOTE: This workaround is present in AArch64 TF and already enabled by
default on Juno.

Change-Id: I10b0baa304ed64b13b7b26ea766e61461e759dfa
Signed-off-by: Dimitris Papastamos <dimitris.papastamos@arm.com>
diff --git a/include/lib/aarch32/arch_helpers.h b/include/lib/aarch32/arch_helpers.h
index e652a59..bd1ac25 100644
--- a/include/lib/aarch32/arch_helpers.h
+++ b/include/lib/aarch32/arch_helpers.h
@@ -100,15 +100,30 @@
  * Macros to create inline functions for tlbi operations
  *********************************************************************/
 
+#if ERRATA_A57_813419
+/*
+ * Define function for TLBI instruction with type specifier that
+ * implements the workaround for errata 813419 of Cortex-A57
+ */
 #define _DEFINE_TLBIOP_FUNC(_op, coproc, opc1, CRn, CRm, opc2)		\
 static inline void tlbi##_op(void)					\
 {									\
 	u_register_t v = 0;						\
 	__asm__ volatile ("mcr "#coproc","#opc1",%0,"#CRn","#CRm","#opc2 : : "r" (v));\
+	__asm__ volatile ("dsb ish");\
+	__asm__ volatile ("mcr "#coproc","#opc1",%0,"#CRn","#CRm","#opc2 : : "r" (v));\
 }
 
-#define _DEFINE_BPIOP_FUNC(_op, coproc, opc1, CRn, CRm, opc2)		\
-static inline void bpi##_op(void)					\
+#define _DEFINE_TLBIOP_PARAM_FUNC(_op, coproc, opc1, CRn, CRm, opc2)	\
+static inline void tlbi##_op(u_register_t v)				\
+{									\
+	__asm__ volatile ("mcr "#coproc","#opc1",%0,"#CRn","#CRm","#opc2 : : "r" (v));\
+	__asm__ volatile ("dsb ish");\
+	__asm__ volatile ("mcr "#coproc","#opc1",%0,"#CRn","#CRm","#opc2 : : "r" (v));\
+}
+#else
+#define _DEFINE_TLBIOP_FUNC(_op, coproc, opc1, CRn, CRm, opc2)		\
+static inline void tlbi##_op(void)					\
 {									\
 	u_register_t v = 0;						\
 	__asm__ volatile ("mcr "#coproc","#opc1",%0,"#CRn","#CRm","#opc2 : : "r" (v));\
@@ -119,6 +134,14 @@
 {									\
 	__asm__ volatile ("mcr "#coproc","#opc1",%0,"#CRn","#CRm","#opc2 : : "r" (v));\
 }
+#endif /* ERRATA_A57_813419 */
+
+#define _DEFINE_BPIOP_FUNC(_op, coproc, opc1, CRn, CRm, opc2)		\
+static inline void bpi##_op(void)					\
+{									\
+	u_register_t v = 0;						\
+	__asm__ volatile ("mcr "#coproc","#opc1",%0,"#CRn","#CRm","#opc2 : : "r" (v));\
+}
 
 /* Define function for simple TLBI operation */
 #define DEFINE_TLBIOP_FUNC(_op, ...)					\
diff --git a/lib/xlat_tables/aarch32/xlat_tables.c b/lib/xlat_tables/aarch32/xlat_tables.c
index 3c9051c..9c15624 100644
--- a/lib/xlat_tables/aarch32/xlat_tables.c
+++ b/lib/xlat_tables/aarch32/xlat_tables.c
@@ -149,7 +149,7 @@
 	 * and translation register writes are committed
 	 * before enabling the MMU
 	 */
-	dsb();
+	dsbish();
 	isb();
 
 	sctlr = read_sctlr();
diff --git a/lib/xlat_tables_v2/aarch32/xlat_tables_arch.c b/lib/xlat_tables_v2/aarch32/xlat_tables_arch.c
index afc65e7..40fd2d0 100644
--- a/lib/xlat_tables_v2/aarch32/xlat_tables_arch.c
+++ b/lib/xlat_tables_v2/aarch32/xlat_tables_arch.c
@@ -141,7 +141,7 @@
 	 * and translation register writes are committed
 	 * before enabling the MMU
 	 */
-	dsb();
+	dsbish();
 	isb();
 
 	sctlr = read_sctlr();