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

* for-next/errata:
  arch: arm64: add early_param idle=<wfi|yield|nop>
  arm64: proton-pack: Restore the nospectre_bhb command-line option
  arm64: errata: work around NVIDIA Olympus device store/load ordering
  arm64: Clarify ARM64_WORKAROUND_REPEAT_TLBI semantics

Documentation/admin-guide/kernel-parameters.txt

@@ -2236,6 +2236,29 @@ Kernel parameters
 
 			idle=nomwait: Disable mwait for CPU C-states
 
+			[ARM64,EARLY]
+			Format: idle=wfi, idle=yield, idle=nop
+
+			idle=wfi: Use the WFI (Wait For Interrupt) hint
+			instruction in the idle loop. This is the default and
+			allows the CPU to enter a low-power state until an
+			interrupt arrives.
+
+			idle=yield: Use the YIELD hint instruction instead of
+			WFI. CPUs supporting simultaneous multi-threading (SMT),
+			can continue executing another thread when the current
+			thread reaches the idle loop. This will make the CPUs
+			eat more power, but may be useful to get slightly better
+			performance in some applications, since the CPUs will
+			not enter a low-power state.
+
+			idle=nop: Do not execute any idle instruction in the
+			idle loop. This is useful on platforms where WFI
+			misbehaves, leading to system instability or loss of CPU
+			state. This will make the CPUs eat more power, but may
+			give slightly better performance in some applications,
+			since the CPUs will not enter a low-power state.
+
 	idxd.sva=	[HW]
 			Format: <bool>
 			Allow force disabling of Shared Virtual Memory (SVA)

Documentation/arch/arm64/silicon-errata.rst

@@ -308,6 +308,8 @@ 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                         |

arch/arm64/Kconfig

@@ -701,12 +701,34 @@ config ARM64_ERRATUM_1530923
 
 	  If unsure, say Y.
 
-config ARM64_WORKAROUND_REPEAT_TLBI
+config ARM64_WORKAROUND_REPEAT_TLBI_SYNC
 	bool
+	# This workaround is (only) suitable for TLB invalidation errata where
+	# all of the following conditions are true:
+	#
+	# - The effects of the errata are only a loss of ordering/completion
+	#   for explicit memory accesses when the TLBI is completed with a DSB.
+	#   The removal of TLB entries is not affected.
+	#
+	#   Note that architecturally, S2-only invalidation does not remove
+	#   combined S1+S2 entries, and does not complete accesses translated
+	#   via those S1+S2 entries. Consequently, where this condition holds,
+	#   the errata do not affect S2-only invalidation.
+	#
+	# - The errata only affect broadcast TLB invalidation operations (e.g.
+	#   TLBI VMALLE1IS), and do not affect local TLB invalidation
+	#   operations (e.g. TLBI VMALLE1).
+	#
+	# - After any number of affected TLBI operations are completed with a
+	#   DSB, the errata can be mitigated by executing a single arbitrary
+	#   broadcast TLBI (which targets an arbitrary translation regime),
+	#   followed by a DSB.
+	#
+	# For more rationale, see commit a8f78680ee6bf795.
 
 config ARM64_ERRATUM_2441007
 	bool "Cortex-A55: Completion of affected memory accesses might not be guaranteed by completion of a TLBI (rare)"
-	select ARM64_WORKAROUND_REPEAT_TLBI
+	select ARM64_WORKAROUND_REPEAT_TLBI_SYNC
 	help
 	  This option adds a workaround for ARM Cortex-A55 erratum #2441007.
 
@@ -722,7 +744,7 @@ config ARM64_ERRATUM_2441007
 
 config ARM64_ERRATUM_1286807
 	bool "Cortex-A76: Modification of the translation table for a virtual address might lead to read-after-read ordering violation (rare)"
-	select ARM64_WORKAROUND_REPEAT_TLBI
+	select ARM64_WORKAROUND_REPEAT_TLBI_SYNC
 	help
 	  This option adds a workaround for ARM Cortex-A76 erratum 1286807.
 
@@ -944,7 +966,7 @@ config ARM64_ERRATUM_2224489
 
 config ARM64_ERRATUM_2441009
 	bool "Cortex-A510: Completion of affected memory accesses might not be guaranteed by completion of a TLBI (rare)"
-	select ARM64_WORKAROUND_REPEAT_TLBI
+	select ARM64_WORKAROUND_REPEAT_TLBI_SYNC
 	help
 	  This option adds a workaround for ARM Cortex-A510 erratum #2441009.
 
@@ -1156,7 +1178,7 @@ config ARM64_ERRATUM_4193714
 config ARM64_ERRATUM_4118414
 	bool "Various: Completion of affected memory accesses might not be guaranteed by completion of a TLBI"
 	default y
-	select ARM64_WORKAROUND_REPEAT_TLBI
+	select ARM64_WORKAROUND_REPEAT_TLBI_SYNC
 	help
 	  This option adds a workaround for the following errata:
 
@@ -1340,7 +1362,7 @@ config QCOM_FALKOR_ERRATUM_1003
 config QCOM_FALKOR_ERRATUM_1009
 	bool "Falkor E1009: Prematurely complete a DSB after a TLBI"
 	default y
-	select ARM64_WORKAROUND_REPEAT_TLBI
+	select ARM64_WORKAROUND_REPEAT_TLBI_SYNC
 	help
 	  On Falkor v1, the CPU may prematurely complete a DSB following a
 	  TLBI xxIS invalidate maintenance operation. Repeat the TLBI operation
@@ -1382,6 +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

arch/arm64/include/asm/cpucaps.h

@@ -60,8 +60,8 @@ cpucap_is_possible(const unsigned int cap)
 		return IS_ENABLED(CONFIG_CAVIUM_ERRATUM_23154);
 	case ARM64_WORKAROUND_DISABLE_CNP:
 		return IS_ENABLED(CONFIG_ARM64_WORKAROUND_DISABLE_CNP);
-	case ARM64_WORKAROUND_REPEAT_TLBI:
-		return IS_ENABLED(CONFIG_ARM64_WORKAROUND_REPEAT_TLBI);
+	case ARM64_WORKAROUND_REPEAT_TLBI_SYNC:
+		return IS_ENABLED(CONFIG_ARM64_WORKAROUND_REPEAT_TLBI_SYNC);
 	case ARM64_WORKAROUND_SPECULATIVE_SSBS:
 		return IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386);
 	case ARM64_WORKAROUND_4193714:

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));

arch/arm64/include/asm/tlbflush.h

@@ -236,7 +236,7 @@ static inline void __tlbi_level(tlbi_op op, u64 addr, u32 level)
 
 #define __repeat_tlbi_sync(op, arg...)						\
 do {										\
-	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))	\
+	if (!alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI_SYNC))	\
 		break;								\
 	__tlbi(op, ##arg);							\
 	dsb(ish);								\

arch/arm64/kernel/cpu_errata.c

@@ -309,7 +309,7 @@ static void cpu_enable_impdef_pmuv3_traps(const struct arm64_cpu_capabilities *_
 	sysreg_clear_set_s(SYS_HACR_EL2, 0, BIT(56));
 }
 
-#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
+#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI_SYNC
 static const struct arm64_cpu_capabilities arm64_repeat_tlbi_list[] = {
 #ifdef CONFIG_QCOM_FALKOR_ERRATUM_1009
 	{
@@ -733,10 +733,10 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		.match_list = qcom_erratum_1003_list,
 	},
 #endif
-#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
+#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI_SYNC
 	{
 		.desc = "Broken broadcast TLBI completion",
-		.capability = ARM64_WORKAROUND_REPEAT_TLBI,
+		.capability = ARM64_WORKAROUND_REPEAT_TLBI_SYNC,
 		.type = ARM64_CPUCAP_LOCAL_CPU_ERRATUM,
 		.matches = cpucap_multi_entry_cap_matches,
 		.match_list = arm64_repeat_tlbi_list,
@@ -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
 	{
 		/*

arch/arm64/kernel/idle.c

@@ -11,6 +11,29 @@
 #include <asm/cpufeature.h>
 #include <asm/sysreg.h>
 
+enum {
+    ARM64_IDLE_WFI,
+    ARM64_IDLE_YIELD,
+    ARM64_IDLE_NOP,
+} idle = ARM64_IDLE_WFI;
+
+static int __init setup_idle(char *arg)
+{
+	if (!arg)
+		return -1;
+	else if (!strcmp(arg, "wfi"))
+		idle = ARM64_IDLE_WFI;
+	else if (!strcmp(arg, "yield"))
+		idle = ARM64_IDLE_YIELD;
+	else if (!strcmp(arg, "nop"))
+		idle = ARM64_IDLE_NOP;
+	else
+		return -1;
+
+	return 0;
+}
+early_param("idle", setup_idle);
+
 /*
  *	cpu_do_idle()
  *
@@ -26,8 +49,13 @@ void __cpuidle cpu_do_idle(void)
 
 	arm_cpuidle_save_irq_context(&context);
 
-	dsb(sy);
-	wfi();
+	if (likely(idle == ARM64_IDLE_WFI)) {
+		dsb(sy);
+		wfi();
+	} else if (idle == ARM64_IDLE_YIELD) {
+		dsb(sy);
+		asm volatile("yield" ::: "memory");
+	}
 
 	arm_cpuidle_restore_irq_context(&context);
 }

arch/arm64/kernel/proton-pack.c

@@ -1023,6 +1023,11 @@ static int __init parse_spectre_bhb_param(char *str)
 }
 early_param("nospectre_bhb", parse_spectre_bhb_param);
 
+static bool spectre_bhb_mitigations_off(void)
+{
+	return __nospectre_bhb || cpu_mitigations_off();
+}
+
 void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 {
 	bp_hardening_cb_t cpu_cb;
@@ -1036,6 +1041,8 @@ void spectre_bhb_enable_mitigation(const struct arm64_cpu_capabilities *entry)
 		/* No point mitigating Spectre-BHB alone. */
 	} else if (!IS_ENABLED(CONFIG_MITIGATE_SPECTRE_BRANCH_HISTORY)) {
 		/* Do nothing */
+	} else if (spectre_bhb_mitigations_off()) {
+		/* Mitigation disabled on the command line */
 	} else if (supports_ecbhb(SCOPE_LOCAL_CPU)) {
 		state = SPECTRE_MITIGATED;
 		set_bit(BHB_HW, &system_bhb_mitigations);
@@ -1201,6 +1208,6 @@ void spectre_print_disabled_mitigations(void)
 	if (spectre_v4_mitigations_off())
 		pr_info("spectre-v4 %s", spectre_disabled_suffix);
 
-	if (__nospectre_bhb || cpu_mitigations_off())
+	if (spectre_bhb_mitigations_off())
 		pr_info("spectre-bhb %s", spectre_disabled_suffix);
 }

arch/arm64/tools/cpucaps

@@ -121,10 +121,11 @@ 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
-WORKAROUND_REPEAT_TLBI
+WORKAROUND_REPEAT_TLBI_SYNC
 WORKAROUND_SPECULATIVE_AT
 WORKAROUND_SPECULATIVE_SSBS
 WORKAROUND_SPECULATIVE_UNPRIV_LOAD