Merge branch 'for-next/errata' into for-next/core

* for-next/errata:
  arm64: errata: Workaround for SI L1 downstream coherency issue

5 files changed, 62 insertions, 0 deletions

diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index a7ec57060f64..4c300caad901 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -212,6 +212,7 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | ARM            | GIC-700         | #2941627        | ARM64_ERRATUM_2941627       |
 +----------------+-----------------+-----------------+-----------------------------+
+| ARM            | SI L1           | #4311569        | ARM64_ERRATUM_4311569       |
 +----------------+-----------------+-----------------+-----------------------------+
 | Broadcom       | Brahma-B53      | N/A             | ARM64_ERRATUM_845719        |
 +----------------+-----------------+-----------------+-----------------------------+
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index fcfb62ec4bae..1d5e86068bd6 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1155,6 +1155,25 @@ config ARM64_ERRATUM_3194386
 
 	  If unsure, say Y.
 
+config ARM64_ERRATUM_4311569
+	bool "SI L1: 4311569: workaround for premature CMO completion erratum"
+	default y
+	help
+	  This option adds the workaround for ARM SI L1 erratum 4311569.
+
+	  The erratum of SI L1 can cause an early response to a combined write
+	  and cache maintenance operation (WR+CMO) before the operation is fully
+	  completed to the Point of Serialization (POS).
+	  This can result in a non-I/O coherent agent observing stale data,
+	  potentially leading to system instability or incorrect behavior.
+
+	  Enabling this option implements a software workaround by inserting a
+	  second loop of Cache Maintenance Operation (CMO) immediately following the
+	  end of function to do CMOs. This ensures that the data is correctly serialized
+	  before the buffer is handed off to a non-coherent agent.
+
+	  If unsure, say Y.
+
 config CAVIUM_ERRATUM_22375
 	bool "Cavium erratum 22375, 24313"
 	default y
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index f0ca7196f6fa..d3d46e5f7188 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -381,6 +381,9 @@ alternative_endif
 	.macro dcache_by_myline_op op, domain, start, end, linesz, tmp, fixup
 	sub	\tmp, \linesz, #1
 	bic	\start, \start, \tmp
+alternative_if ARM64_WORKAROUND_4311569
+	mov	\tmp, \start
+alternative_else_nop_endif
 .Ldcache_op\@:
 	.ifc	\op, cvau
 	__dcache_op_workaround_clean_cache \op, \start
@@ -402,6 +405,13 @@ alternative_endif
 	add	\start, \start, \linesz
 	cmp	\start, \end
 	b.lo	.Ldcache_op\@
+alternative_if ARM64_WORKAROUND_4311569
+	.ifnc	\op, cvau
+	mov	\start, \tmp
+	mov	\tmp, xzr
+	cbnz	\start, .Ldcache_op\@
+	.endif
+alternative_else_nop_endif
 	dsb	\domain
 
 	_cond_uaccess_extable .Ldcache_op\@, \fixup
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 8cb3b575a031..5c0ab6bfd44a 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -141,6 +141,30 @@ has_mismatched_cache_type(const struct arm64_cpu_capabilities *entry,
 	return (ctr_real != sys) && (ctr_raw != sys);
 }
 
+#ifdef CONFIG_ARM64_ERRATUM_4311569
+static DEFINE_STATIC_KEY_FALSE(arm_si_l1_workaround_4311569);
+static int __init early_arm_si_l1_workaround_4311569_cfg(char *arg)
+{
+	static_branch_enable(&arm_si_l1_workaround_4311569);
+	pr_info("Enabling cache maintenance workaround for ARM SI-L1 erratum 4311569\n");
+
+	return 0;
+}
+early_param("arm_si_l1_workaround_4311569", early_arm_si_l1_workaround_4311569_cfg);
+
+/*
+ * We have some earlier use cases to call cache maintenance operation functions, for example,
+ * dcache_inval_poc() and dcache_clean_poc() in head.S, before making decision to turn on this
+ * workaround. Since the scope of this workaround is limited to non-coherent DMA agents, its
+ * safe to have the workaround off by default.
+ */
+static bool
+need_arm_si_l1_workaround_4311569(const struct arm64_cpu_capabilities *entry, int scope)
+{
+	return static_branch_unlikely(&arm_si_l1_workaround_4311569);
+}
+#endif
+
 static void
 cpu_enable_trap_ctr_access(const struct arm64_cpu_capabilities *cap)
 {
@@ -870,6 +894,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(erratum_spec_ssbs_list),
 	},
 #endif
+#ifdef CONFIG_ARM64_ERRATUM_4311569
+	{
+		.capability = ARM64_WORKAROUND_4311569,
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.matches = need_arm_si_l1_workaround_4311569,
+	},
+#endif
 #ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_UNPRIV_LOAD
 	{
 		.desc = "ARM errata 2966298, 3117295",
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index 50a0c695f340..7261553b644b 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -105,6 +105,7 @@ WORKAROUND_2077057
 WORKAROUND_2457168
 WORKAROUND_2645198
 WORKAROUND_2658417
+WORKAROUND_4311569
 WORKAROUND_AMPERE_AC03_CPU_38
 WORKAROUND_AMPERE_AC04_CPU_23
 WORKAROUND_TRBE_OVERWRITE_FILL_MODE