arm64: errata: Add workaround for TSB flush failures

Arm Neoverse-N2 (#2067961) and Cortex-A710 (#2054223) suffers
from errata, where a TSB (trace synchronization barrier)
fails to flush the trace data completely, when executed from
a trace prohibited region. In Linux we always execute it
after we have moved the PE to trace prohibited region. So,
we can apply the workaround every time a TSB is executed.

The work around is to issue two TSB consecutively.

NOTE: This errata is defined as LOCAL_CPU_ERRATUM, implying
that a late CPU could be blocked from booting if it is the
first CPU that requires the workaround. This is because we
do not allow setting a cpu_hwcaps after the SMP boot. The
other alternative is to use "this_cpu_has_cap()" instead
of the faster system wide check, which may be a bit of an
overhead, given we may have to do this in nvhe KVM host
before a guest entry.

Cc: Will Deacon <will@kernel.org>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Mike Leach <mike.leach@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Link: https://lore.kernel.org/r/20211019163153.3692640-4-suzuki.poulose@arm.comSigned-off-by: Will Deacon <will@kernel.org>

Documentation/arm64/silicon-errata.rst

@@ -94,6 +94,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Cortex-A710     | #2119858        | ARM64_ERRATUM_2119858       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Cortex-A710     | #2054223        | ARM64_ERRATUM_2054223       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1188873,1418040| ARM64_ERRATUM_1418040       |
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N1     | #1349291        | N/A                         |
@@ -102,6 +104,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | Neoverse-N2     | #2139208        | ARM64_ERRATUM_2139208       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | Neoverse-N2     | #2067961        | ARM64_ERRATUM_2067961       |
++----------------+-----------------+-----------------+-----------------------------+
 | ARM            | MMU-500         | #841119,826419  | N/A                         |
 +----------------+-----------------+-----------------+-----------------------------+
 +----------------+-----------------+-----------------+-----------------------------+

arch/arm64/Kconfig

@@ -707,6 +707,39 @@ config ARM64_ERRATUM_2139208
 
 	  If unsure, say Y.
 
+config ARM64_WORKAROUND_TSB_FLUSH_FAILURE
+	bool
+
+config ARM64_ERRATUM_2054223
+	bool "Cortex-A710: 2054223: workaround TSB instruction failing to flush trace"
+	default y
+	select ARM64_WORKAROUND_TSB_FLUSH_FAILURE
+	help
+	  Enable workaround for ARM Cortex-A710 erratum 2054223
+
+	  Affected cores may fail to flush the trace data on a TSB instruction, when
+	  the PE is in trace prohibited state. This will cause losing a few bytes
+	  of the trace cached.
+
+	  Workaround is to issue two TSB consecutively on affected cores.
+
+	  If unsure, say Y.
+
+config ARM64_ERRATUM_2067961
+	bool "Neoverse-N2: 2067961: workaround TSB instruction failing to flush trace"
+	default y
+	select ARM64_WORKAROUND_TSB_FLUSH_FAILURE
+	help
+	  Enable workaround for ARM Neoverse-N2 erratum 2067961
+
+	  Affected cores may fail to flush the trace data on a TSB instruction, when
+	  the PE is in trace prohibited state. This will cause losing a few bytes
+	  of the trace cached.
+
+	  Workaround is to issue two TSB consecutively on affected cores.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y

arch/arm64/include/asm/barrier.h

@@ -23,7 +23,7 @@
 #define dsb(opt)	asm volatile("dsb " #opt : : : "memory")
 
 #define psb_csync()	asm volatile("hint #17" : : : "memory")
-#define tsb_csync()	asm volatile("hint #18" : : : "memory")
+#define __tsb_csync()	asm volatile("hint #18" : : : "memory")
 #define csdb()		asm volatile("hint #20" : : : "memory")
 
 #ifdef CONFIG_ARM64_PSEUDO_NMI
@@ -46,6 +46,20 @@
 #define dma_rmb()	dmb(oshld)
 #define dma_wmb()	dmb(oshst)
 
+
+#define tsb_csync()								\
+	do {									\
+		/*								\
+		 * CPUs affected by Arm Erratum 2054223 or 2067961 needs	\
+		 * another TSB to ensure the trace is flushed. The barriers	\
+		 * don't have to be strictly back to back, as long as the	\
+		 * CPU is in trace prohibited state.				\
+		 */								\
+		if (cpus_have_final_cap(ARM64_WORKAROUND_TSB_FLUSH_FAILURE))	\
+			__tsb_csync();						\
+		__tsb_csync();							\
+	} while (0)
+
 /*
  * Generate a mask for array_index__nospec() that is ~0UL when 0 <= idx < sz
  * and 0 otherwise.

arch/arm64/kernel/cpu_errata.c

@@ -352,6 +352,18 @@ static const struct midr_range trbe_overwrite_fill_mode_cpus[] = {
 };
 #endif	/* CONFIG_ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE */
 
+#ifdef CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILURE
+static const struct midr_range tsb_flush_fail_cpus[] = {
+#ifdef CONFIG_ARM64_ERRATUM_2067961
+	MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
+#endif
+#ifdef CONFIG_ARM64_ERRATUM_2054223
+	MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
+#endif
+	{},
+};
+#endif	/* CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILURE */
+
 const struct arm64_cpu_capabilities arm64_errata[] = {
 #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
 	{
@@ -558,6 +570,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
 		CAP_MIDR_RANGE_LIST(trbe_overwrite_fill_mode_cpus),
 	},
+#endif
+#ifdef CONFIG_ARM64_WORKAROUND_TSB_FLUSH_FAILURE
+	{
+		.desc = "ARM erratum 2067961 or 2054223",
+		.capability = ARM64_WORKAROUND_TSB_FLUSH_FAILURE,
+		ERRATA_MIDR_RANGE_LIST(tsb_flush_fail_cpus),
+	},
 #endif
 	{
 	}

arch/arm64/tools/cpucaps

@@ -54,6 +54,7 @@ WORKAROUND_1463225
 WORKAROUND_1508412
 WORKAROUND_1542419
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE
+WORKAROUND_TSB_FLUSH_FAILURE
 WORKAROUND_CAVIUM_23154
 WORKAROUND_CAVIUM_27456
 WORKAROUND_CAVIUM_30115