arm64: Work around Falkor erratum 1009

During a TLB invalidate sequence targeting the inner shareable domain,
Falkor may prematurely complete the DSB before all loads and stores using
the old translation are observed. Instruction fetches are not subject to
the conditions of this erratum. If the original code sequence includes
multiple TLB invalidate instructions followed by a single DSB, onle one of
the TLB instructions needs to be repeated to work around this erratum.
While the erratum only applies to cases in which the TLBI specifies the
inner-shareable domain (*IS form of TLBI) and the DSB is ISH form or
stronger (OSH, SYS), this changes applies the workaround overabundantly--
to local TLBI, DSB NSH sequences as well--for simplicity.

Based on work by Shanker Donthineni <shankerd@codeaurora.org>

Signed-off-by: Christopher Covington <cov@codeaurora.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>

arch/arm64/include/asm/tlbflush.h

@@ -36,9 +36,21 @@
  * not. The macros handles invoking the asm with or without the
  * register argument as appropriate.
  */
-#define __TLBI_0(op, arg)		asm ("tlbi " #op)
-#define __TLBI_1(op, arg)		asm ("tlbi " #op ", %0" : : "r" (arg))
-#define __TLBI_N(op, arg, n, ...)	__TLBI_##n(op, arg)
+#define __TLBI_0(op, arg) asm ("tlbi " #op "\n"				       \
+		   ALTERNATIVE("nop\n			nop",		       \
+			       "dsb ish\n		tlbi " #op,	       \
+			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
+			       CONFIG_QCOM_FALKOR_ERRATUM_1009)		       \
+			    : : )
+
+#define __TLBI_1(op, arg) asm ("tlbi " #op ", %0\n"			       \
+		   ALTERNATIVE("nop\n			nop",		       \
+			       "dsb ish\n		tlbi " #op ", %0",     \
+			       ARM64_WORKAROUND_REPEAT_TLBI,		       \
+			       CONFIG_QCOM_FALKOR_ERRATUM_1009)		       \
+			    : : "r" (arg))
+
+#define __TLBI_N(op, arg, n, ...) __TLBI_##n(op, arg)
 
 #define __tlbi(op, ...)		__TLBI_N(op, ##__VA_ARGS__, 1, 0)