arm64: errata: add detection for AMEVCNTR01 incrementing incorrectly

The AMU counter AMEVCNTR01 (constant counter) should increment at the same
rate as the system counter. On affected Cortex-A510 cores, AMEVCNTR01
increments incorrectly giving a significantly higher output value. This
results in inaccurate task scheduler utilization tracking and incorrect
feedback on CPU frequency.

Work around this problem by returning 0 when reading the affected counter
in key locations that results in disabling all users of this counter from
using it either for frequency invariance or as FFH reference counter. This
effect is the same to firmware disabling affected counters.

Details on how the two features are affected by this erratum:

 - AMU counters will not be used for frequency invariance for affected
   CPUs and CPUs in the same cpufreq policy. AMUs can still be used for
   frequency invariance for unaffected CPUs in the system. Although
   unlikely, if no alternative method can be found to support frequency
   invariance for affected CPUs (cpufreq based or solution based on
   platform counters) frequency invariance will be disabled. Please check
   the chapter on frequency invariance at
   Documentation/scheduler/sched-capacity.rst for details of its effect.

 - Given that FFH can be used to fetch either the core or constant counter
   values, restrictions are lifted regarding any of these counters
   returning a valid (!0) value. Therefore FFH is considered supported
   if there is a least one CPU that support AMUs, independent of any
   counters being disabled or affected by this erratum. Clarifying
   comments are now added to the cpc_ffh_supported(), cpu_read_constcnt()
   and cpu_read_corecnt() functions.

The above is achieved through adding a new erratum: ARM64_ERRATUM_2457168.

Signed-off-by: Ionela Voinescu <ionela.voinescu@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Will Deacon <will@kernel.org>
Cc: James Morse <james.morse@arm.com>
Link: https://lore.kernel.org/r/20220819103050.24211-1-ionela.voinescu@arm.com
Signed-off-by: Will Deacon <will@kernel.org>

5 files changed, 62 insertions, 3 deletions

diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 571cc234d0b3..9fb9fff08c94 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -917,6 +917,23 @@ config ARM64_ERRATUM_1902691
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_2457168
+	bool "Cortex-A510: 2457168: workaround for AMEVCNTR01 incrementing incorrectly"
+	depends on ARM64_AMU_EXTN
+	default y
+	help
+	  This option adds the workaround for ARM Cortex-A510 erratum 2457168.
+
+	  The AMU counter AMEVCNTR01 (constant counter) should increment at the same rate
+	  as the system counter. On affected Cortex-A510 cores AMEVCNTR01 increments
+	  incorrectly giving a significantly higher output value.
+
+	  Work around this problem by returning 0 when reading the affected counter in
+	  key locations that results in disabling all users of this counter. This effect
+	  is the same to firmware disabling affected counters.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 0f7e9087d900..53b973b6059f 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -656,6 +656,16 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_REV_RANGE(MIDR_CORTEX_A510, 0, 0, 2)
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_2457168
+	{
+		.desc = "ARM erratum 2457168",
+		.capability = ARM64_WORKAROUND_2457168,
+		.type = ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE,
+
+		/* Cortex-A510 r0p0-r1p1 */
+		CAP_MIDR_RANGE(MIDR_CORTEX_A510, 0, 0, 1, 1)
+	},
+#endif
 #ifdef CONFIG_ARM64_ERRATUM_2038923
 	{
 		.desc = "ARM erratum 2038923",
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 907401e4fffb..af4de817d712 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -1870,7 +1870,10 @@ static void cpu_amu_enable(struct arm64_cpu_capabilities const *cap)
 		pr_info("detected CPU%d: Activity Monitors Unit (AMU)\n",
 			smp_processor_id());
 		cpumask_set_cpu(smp_processor_id(), &amu_cpus);
-		update_freq_counters_refs();
+
+		/* 0 reference values signal broken/disabled counters */
+		if (!this_cpu_has_cap(ARM64_WORKAROUND_2457168))
+			update_freq_counters_refs();
 	}
 }
 
diff --git a/arch/arm64/kernel/topology.c b/arch/arm64/kernel/topology.c
index 869ffc4d4484..ad2bfc794257 100644
--- a/arch/arm64/kernel/topology.c
+++ b/arch/arm64/kernel/topology.c
@@ -296,12 +296,25 @@ core_initcall(init_amu_fie);
 
 static void cpu_read_corecnt(void *val)
 {
+	/*
+	 * A value of 0 can be returned if the current CPU does not support AMUs
+	 * or if the counter is disabled for this CPU. A return value of 0 at
+	 * counter read is properly handled as an error case by the users of the
+	 * counter.
+	 */
 	*(u64 *)val = read_corecnt();
 }
 
 static void cpu_read_constcnt(void *val)
 {
-	*(u64 *)val = read_constcnt();
+	/*
+	 * Return 0 if the current CPU is affected by erratum 2457168. A value
+	 * of 0 is also returned if the current CPU does not support AMUs or if
+	 * the counter is disabled. A return value of 0 at counter read is
+	 * properly handled as an error case by the users of the counter.
+	 */
+	*(u64 *)val = this_cpu_has_cap(ARM64_WORKAROUND_2457168) ?
+		      0UL : read_constcnt();
 }
 
 static inline
@@ -328,7 +341,22 @@ int counters_read_on_cpu(int cpu, smp_call_func_t func, u64 *val)
  */
 bool cpc_ffh_supported(void)
 {
-	return freq_counters_valid(get_cpu_with_amu_feat());
+	int cpu = get_cpu_with_amu_feat();
+
+	/*
+	 * FFH is considered supported if there is at least one present CPU that
+	 * supports AMUs. Using FFH to read core and reference counters for CPUs
+	 * that do not support AMUs, have counters disabled or that are affected
+	 * by errata, will result in a return value of 0.
+	 *
+	 * This is done to allow any enabled and valid counters to be read
+	 * through FFH, knowing that potentially returning 0 as counter value is
+	 * properly handled by the users of these counters.
+	 */
+	if ((cpu >= nr_cpu_ids) || !cpumask_test_cpu(cpu, cpu_present_mask))
+		return false;
+
+	return true;
 }
 
 int cpc_read_ffh(int cpu, struct cpc_reg *reg, u64 *val)
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 779653771507..63b2484ce6c3 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -67,6 +67,7 @@ WORKAROUND_1902691
 WORKAROUND_2038923
 WORKAROUND_2064142
 WORKAROUND_2077057
+WORKAROUND_2457168
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 WORKAROUND_TSB_FLUSH_FAILURE
 WORKAROUND_TRBE_WRITE_OUT_OF_RANGE