diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
index 014aa1c215a1..02617007a57c 100644
--- a/Documentation/arch/arm64/silicon-errata.rst
+++ b/Documentation/arch/arm64/silicon-errata.rst
@@ -304,6 +304,8 @@ stable kernels.
 +----------------+-----------------+-----------------+-----------------------------+
 | NVIDIA         | Carmel Core     | N/A             | NVIDIA_CARMEL_CNP_ERRATUM   |
 +----------------+-----------------+-----------------+-----------------------------+
+| NVIDIA         | Olympus core    | T410-OLY-1027   | NVIDIA_OLYMPUS_1027_ERRATUM |
++----------------+-----------------+-----------------+-----------------------------+
 | NVIDIA         | Olympus core    | T410-OLY-1029   | ARM64_ERRATUM_4118414       |
 +----------------+-----------------+-----------------+-----------------------------+
 | NVIDIA         | T241 GICv3/4.x  | T241-FABRIC-4   | N/A                         |
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 757110421543..3510b04468de 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -1404,6 +1404,28 @@ config NVIDIA_CARMEL_CNP_ERRATUM
 
 	  If unsure, say Y.
 
+config NVIDIA_OLYMPUS_1027_ERRATUM
+	bool "NVIDIA Olympus: device store/load ordering erratum"
+	default y
+	help
+	  This option adds an alternative code sequence to work around an
+	  NVIDIA Olympus core erratum where a Device-nGnR* store can be
+	  observed by a peripheral after a younger Device-nGnR* load to the
+	  same peripheral. This breaks the program order that drivers rely
+	  on for MMIO and can leave a device in an incorrect state.
+
+	  The workaround inserts a DMB OSH immediately before raw MMIO loads.
+	  The erratum cannot occur when a DMB that orders loads appears
+	  between the store and load, preventing the younger load from being
+	  observed before the older store.
+
+	  The alternatives framework patches in DMB OSH only when an affected
+	  CPU is detected. Other CPUs execute a NOP in its place. Disabling
+	  this option leaves the original MMIO read instruction stream
+	  unchanged.
+
+	  If unsure, say Y.
+
 config ROCKCHIP_ERRATUM_3568002
 	bool "Rockchip 3568002: GIC600 can not access physical addresses higher than 4GB"
 	default y
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 21c8e400107c..49a7002661a9 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -54,7 +54,9 @@ static __always_inline void __raw_writeq(u64 val, volatile void __iomem *addr)
 static __always_inline u8 __raw_readb(const volatile void __iomem *addr)
 {
 	u8 val;
-	asm volatile(ALTERNATIVE("ldrb %w0, [%1]",
+	asm volatile(ALTERNATIVE("nop", "dmb osh",
+				 ARM64_WORKAROUND_NVIDIA_OLYMPUS_1027)
+		     ALTERNATIVE("ldrb %w0, [%1]",
 				 "ldarb %w0, [%1]",
 				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
 		     : "=r" (val) : "r" (addr));
@@ -66,7 +68,9 @@ static __always_inline u16 __raw_readw(const volatile void __iomem *addr)
 {
 	u16 val;
 
-	asm volatile(ALTERNATIVE("ldrh %w0, [%1]",
+	asm volatile(ALTERNATIVE("nop", "dmb osh",
+				 ARM64_WORKAROUND_NVIDIA_OLYMPUS_1027)
+		     ALTERNATIVE("ldrh %w0, [%1]",
 				 "ldarh %w0, [%1]",
 				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
 		     : "=r" (val) : "r" (addr));
@@ -77,7 +81,9 @@ static __always_inline u16 __raw_readw(const volatile void __iomem *addr)
 static __always_inline u32 __raw_readl(const volatile void __iomem *addr)
 {
 	u32 val;
-	asm volatile(ALTERNATIVE("ldr %w0, [%1]",
+	asm volatile(ALTERNATIVE("nop", "dmb osh",
+				 ARM64_WORKAROUND_NVIDIA_OLYMPUS_1027)
+		     ALTERNATIVE("ldr %w0, [%1]",
 				 "ldar %w0, [%1]",
 				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
 		     : "=r" (val) : "r" (addr));
@@ -88,7 +94,9 @@ static __always_inline u32 __raw_readl(const volatile void __iomem *addr)
 static __always_inline u64 __raw_readq(const volatile void __iomem *addr)
 {
 	u64 val;
-	asm volatile(ALTERNATIVE("ldr %0, [%1]",
+	asm volatile(ALTERNATIVE("nop", "dmb osh",
+				 ARM64_WORKAROUND_NVIDIA_OLYMPUS_1027)
+		     ALTERNATIVE("ldr %0, [%1]",
 				 "ldar %0, [%1]",
 				 ARM64_WORKAROUND_DEVICE_LOAD_ACQUIRE)
 		     : "=r" (val) : "r" (addr));
diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
index 685077d44ad1..b5ba9c455aef 100644
--- a/arch/arm64/kernel/cpu_errata.c
+++ b/arch/arm64/kernel/cpu_errata.c
@@ -850,6 +850,14 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		ERRATA_MIDR_RANGE_LIST(cnp_erratum_cpus),
 	},
 #endif
+#ifdef CONFIG_NVIDIA_OLYMPUS_1027_ERRATUM
+	{
+		/* NVIDIA Olympus core */
+		.desc = "NVIDIA Olympus device store/load ordering erratum",
+		.capability = ARM64_WORKAROUND_NVIDIA_OLYMPUS_1027,
+		ERRATA_MIDR_ALL_VERSIONS(MIDR_NVIDIA_OLYMPUS),
+	},
+#endif
 #ifdef CONFIG_ARM64_WORKAROUND_TRBE_OVERWRITE_FILL_MODE
 	{
 		/*
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index f8368e5d81a8..e43c9095424b 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -121,6 +121,7 @@ WORKAROUND_CAVIUM_TX2_219_TVM
 WORKAROUND_CLEAN_CACHE
 WORKAROUND_DEVICE_LOAD_ACQUIRE
 WORKAROUND_DISABLE_CNP
+WORKAROUND_NVIDIA_OLYMPUS_1027
 WORKAROUND_PMUV3_IMPDEF_TRAPS
 WORKAROUND_QCOM_FALKOR_E1003
 WORKAROUND_QCOM_ORYON_CNTVOFF