Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:

 - Pseudo NMI support for arm64 using GICv3 interrupt priorities

 - uaccess macros clean-up (unsafe user accessors also merged but
   reverted, waiting for objtool support on arm64)

 - ptrace regsets for Pointer Authentication (ARMv8.3) key management

 - inX() ordering w.r.t. delay() on arm64 and riscv (acks in place by
   the riscv maintainers)

 - arm64/perf updates: PMU bindings converted to json-schema, unused
   variable and misleading comment removed

 - arm64/debug fixes to ensure checking of the triggering exception
   level and to avoid the propagation of the UNKNOWN FAR value into the
   si_code for debug signals

 - Workaround for Fujitsu A64FX erratum 010001

 - lib/raid6 ARM NEON optimisations

 - NR_CPUS now defaults to 256 on arm64

 - Minor clean-ups (documentation/comments, Kconfig warning, unused
   asm-offsets, clang warnings)

 - MAINTAINERS update for list information to the ARM64 ACPI entry

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (54 commits)
  arm64: mmu: drop paging_init comments
  arm64: debug: Ensure debug handlers check triggering exception level
  arm64: debug: Don't propagate UNKNOWN FAR into si_code for debug signals
  Revert "arm64: uaccess: Implement unsafe accessors"
  arm64: avoid clang warning about self-assignment
  arm64: Kconfig.platforms: fix warning unmet direct dependencies
  lib/raid6: arm: optimize away a mask operation in NEON recovery routine
  lib/raid6: use vdupq_n_u8 to avoid endianness warnings
  arm64: io: Hook up __io_par() for inX() ordering
  riscv: io: Update __io_[p]ar() macros to take an argument
  asm-generic/io: Pass result of I/O accessor to __io_[p]ar()
  arm64: Add workaround for Fujitsu A64FX erratum 010001
  arm64: Rename get_thread_info()
  arm64: Remove documentation about TIF_USEDFPU
  arm64: irqflags: Fix clang build warnings
  arm64: Enable the support of pseudo-NMIs
  arm64: Skip irqflags tracing for NMI in IRQs disabled context
  arm64: Skip preemption when exiting an NMI
  arm64: Handle serror in NMI context
  irqchip/gic-v3: Allow interrupts to be set as pseudo-NMI
  ...

64 files changed, 1214 insertions, 368 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 49f2acc5eece..aa4f4cfd0491 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1846,6 +1846,11 @@
 			to let secondary kernels in charge of setting up
 			LPIs.
 
+	irqchip.gicv3_pseudo_nmi= [ARM64]
+			Enables support for pseudo-NMIs in the kernel. This
+			requires the kernel to be built with
+			CONFIG_ARM64_PSEUDO_NMI.
+
 	irqfixup	[HW]
 			When an interrupt is not handled search all handlers
 			for it. Intended to get systems with badly broken
diff --git a/Documentation/arm64/booting.txt b/Documentation/arm64/booting.txt
index 8df9f4658d6f..fbab7e21d116 100644
--- a/Documentation/arm64/booting.txt
+++ b/Documentation/arm64/booting.txt
@@ -188,6 +188,11 @@ Before jumping into the kernel, the following conditions must be met:
   the kernel image will be entered must be initialised by software at a
   higher exception level to prevent execution in an UNKNOWN state.
 
+  - SCR_EL3.FIQ must have the same value across all CPUs the kernel is
+    executing on.
+  - The value of SCR_EL3.FIQ must be the same as the one present at boot
+    time whenever the kernel is executing.
+
   For systems with a GICv3 interrupt controller to be used in v3 mode:
   - If EL3 is present:
     ICC_SRE_EL3.Enable (bit 3) must be initialiased to 0b1.
diff --git a/Documentation/arm64/pointer-authentication.txt b/Documentation/arm64/pointer-authentication.txt
index a25cd21290e9..5baca42ba146 100644
--- a/Documentation/arm64/pointer-authentication.txt
+++ b/Documentation/arm64/pointer-authentication.txt
@@ -78,6 +78,11 @@ bits can vary between the two. Note that the masks apply to TTBR0
 addresses, and are not valid to apply to TTBR1 addresses (e.g. kernel
 pointers).
 
+Additionally, when CONFIG_CHECKPOINT_RESTORE is also set, the kernel
+will expose the NT_ARM_PACA_KEYS and NT_ARM_PACG_KEYS regsets (struct
+user_pac_address_keys and struct user_pac_generic_keys). These can be
+used to get and set the keys for a thread.
+
 
 Virtualization
 --------------
diff --git a/Documentation/arm64/silicon-errata.txt b/Documentation/arm64/silicon-errata.txt
index ddb8ce5333ba..d1e2bb801e1b 100644
--- a/Documentation/arm64/silicon-errata.txt
+++ b/Documentation/arm64/silicon-errata.txt
@@ -82,3 +82,4 @@ stable kernels.
 | Qualcomm Tech. | Falkor v1       | E1009           | QCOM_FALKOR_ERRATUM_1009    |
 | Qualcomm Tech. | QDF2400 ITS     | E0065           | QCOM_QDF2400_ERRATUM_0065   |
 | Qualcomm Tech. | Falkor v{1,2}   | E1041           | QCOM_FALKOR_ERRATUM_1041    |
+| Fujitsu        | A64FX           | E#010001        | FUJITSU_ERRATUM_010001      |
diff --git a/Documentation/devicetree/bindings/arm/pmu.txt b/Documentation/devicetree/bindings/arm/pmu.txt
deleted file mode 100644
index 13611a8199bb..000000000000
--- a/Documentation/devicetree/bindings/arm/pmu.txt
+++ /dev/null
@@ -1,70 +0,0 @@
-* ARM Performance Monitor Units
-
-ARM cores often have a PMU for counting cpu and cache events like cache misses
-and hits. The interface to the PMU is part of the ARM ARM. The ARM PMU
-representation in the device tree should be done as under:-
-
-Required properties:
-
-- compatible : should be one of
-	"apm,potenza-pmu"
-	"arm,armv8-pmuv3"
-	"arm,cortex-a73-pmu"
-	"arm,cortex-a72-pmu"
-	"arm,cortex-a57-pmu"
-	"arm,cortex-a53-pmu"
-	"arm,cortex-a35-pmu"
-	"arm,cortex-a17-pmu"
-	"arm,cortex-a15-pmu"
-	"arm,cortex-a12-pmu"
-	"arm,cortex-a9-pmu"
-	"arm,cortex-a8-pmu"
-	"arm,cortex-a7-pmu"
-	"arm,cortex-a5-pmu"
-	"arm,arm11mpcore-pmu"
-	"arm,arm1176-pmu"
-	"arm,arm1136-pmu"
-	"brcm,vulcan-pmu"
-	"cavium,thunder-pmu"
-	"qcom,scorpion-pmu"
-	"qcom,scorpion-mp-pmu"
-	"qcom,krait-pmu"
-- interrupts : 1 combined interrupt or 1 per core. If the interrupt is a per-cpu
-               interrupt (PPI) then 1 interrupt should be specified.
-
-Optional properties:
-
-- interrupt-affinity : When using SPIs, specifies a list of phandles to CPU
-                       nodes corresponding directly to the affinity of
-		       the SPIs listed in the interrupts property.
-
-                       When using a PPI, specifies a list of phandles to CPU
-		       nodes corresponding to the set of CPUs which have
-		       a PMU of this type signalling the PPI listed in the
-		       interrupts property, unless this is already specified
-		       by the PPI interrupt specifier itself (in which case
-		       the interrupt-affinity property shouldn't be present).
-
-                       This property should be present when there is more than
-		       a single SPI.
-
-
-- qcom,no-pc-write : Indicates that this PMU doesn't support the 0xc and 0xd
-                     events.
-
-- secure-reg-access : Indicates that the ARMv7 Secure Debug Enable Register
-		      (SDER) is accessible. This will cause the driver to do
-		      any setup required that is only possible in ARMv7 secure
-		      state. If not present the ARMv7 SDER will not be touched,
-		      which means the PMU may fail to operate unless external
-		      code (bootloader or security monitor) has performed the
-		      appropriate initialisation. Note that this property is
-		      not valid for non-ARMv7 CPUs or ARMv7 CPUs booting Linux
-		      in Non-secure state.
-
-Example:
-
-pmu {
-        compatible = "arm,cortex-a9-pmu";
-        interrupts = <100 101>;
-};
diff --git a/Documentation/devicetree/bindings/arm/pmu.yaml b/Documentation/devicetree/bindings/arm/pmu.yaml
new file mode 100644
index 000000000000..52ae094ce330
--- /dev/null
+++ b/Documentation/devicetree/bindings/arm/pmu.yaml
@@ -0,0 +1,87 @@
+# SPDX-License-Identifier: GPL-2.0
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/arm/pmu.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: ARM Performance Monitor Units
+
+maintainers:
+  - Mark Rutland <mark.rutland@arm.com>
+  - Will Deacon <will.deacon@arm.com>
+
+description: |+
+  ARM cores often have a PMU for counting cpu and cache events like cache misses
+  and hits. The interface to the PMU is part of the ARM ARM. The ARM PMU
+  representation in the device tree should be done as under:-
+
+properties:
+  compatible:
+    items:
+      - enum:
+          - apm,potenza-pmu
+          - arm,armv8-pmuv3
+          - arm,cortex-a73-pmu
+          - arm,cortex-a72-pmu
+          - arm,cortex-a57-pmu
+          - arm,cortex-a53-pmu
+          - arm,cortex-a35-pmu
+          - arm,cortex-a17-pmu
+          - arm,cortex-a15-pmu
+          - arm,cortex-a12-pmu
+          - arm,cortex-a9-pmu
+          - arm,cortex-a8-pmu
+          - arm,cortex-a7-pmu
+          - arm,cortex-a5-pmu
+          - arm,arm11mpcore-pmu
+          - arm,arm1176-pmu
+          - arm,arm1136-pmu
+          - brcm,vulcan-pmu
+          - cavium,thunder-pmu
+          - qcom,scorpion-pmu
+          - qcom,scorpion-mp-pmu
+          - qcom,krait-pmu
+
+  interrupts:
+    # Don't know how many CPUs, so no constraints to specify
+    description: 1 per-cpu interrupt (PPI) or 1 interrupt per core.
+
+  interrupt-affinity:
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    description:
+      When using SPIs, specifies a list of phandles to CPU
+      nodes corresponding directly to the affinity of
+      the SPIs listed in the interrupts property.
+
+      When using a PPI, specifies a list of phandles to CPU
+      nodes corresponding to the set of CPUs which have
+      a PMU of this type signalling the PPI listed in the
+      interrupts property, unless this is already specified
+      by the PPI interrupt specifier itself (in which case
+      the interrupt-affinity property shouldn't be present).
+
+      This property should be present when there is more than
+      a single SPI.
+
+  qcom,no-pc-write:
+    type: boolean
+    description:
+      Indicates that this PMU doesn't support the 0xc and 0xd events.
+
+  secure-reg-access:
+    type: boolean
+    description:
+      Indicates that the ARMv7 Secure Debug Enable Register
+      (SDER) is accessible. This will cause the driver to do
+      any setup required that is only possible in ARMv7 secure
+      state. If not present the ARMv7 SDER will not be touched,
+      which means the PMU may fail to operate unless external
+      code (bootloader or security monitor) has performed the
+      appropriate initialisation. Note that this property is
+      not valid for non-ARMv7 CPUs or ARMv7 CPUs booting Linux
+      in Non-secure state.
+
+required:
+  - compatible
+
+...
diff --git a/MAINTAINERS b/MAINTAINERS
index 15dbcdc7bb25..b5bffd2d7f8c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -366,6 +366,7 @@ M:	Lorenzo Pieralisi <lorenzo.pieralisi@arm.com>
 M:	Hanjun Guo <hanjun.guo@linaro.org>
 M:	Sudeep Holla <sudeep.holla@arm.com>
 L:	linux-acpi@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	drivers/acpi/arm64
 
@@ -1195,7 +1196,7 @@ F:	arch/arm*/include/asm/hw_breakpoint.h
 F:	arch/arm*/include/asm/perf_event.h
 F:	drivers/perf/*
 F:	include/linux/perf/arm_pmu.h
-F:	Documentation/devicetree/bindings/arm/pmu.txt
+F:	Documentation/devicetree/bindings/arm/pmu.yaml
 F:	Documentation/devicetree/bindings/perf/
 
 ARM PORT
diff --git a/arch/arm/include/asm/arch_gicv3.h b/arch/arm/include/asm/arch_gicv3.h
index 0bd530702118..f6f485f4744e 100644
--- a/arch/arm/include/asm/arch_gicv3.h
+++ b/arch/arm/include/asm/arch_gicv3.h
@@ -34,6 +34,7 @@
 #define ICC_SRE				__ACCESS_CP15(c12, 0, c12, 5)
 #define ICC_IGRPEN1			__ACCESS_CP15(c12, 0, c12, 7)
 #define ICC_BPR1			__ACCESS_CP15(c12, 0, c12, 3)
+#define ICC_RPR				__ACCESS_CP15(c12, 0, c11, 3)
 
 #define __ICC_AP0Rx(x)			__ACCESS_CP15(c12, 0, c8, 4 | x)
 #define ICC_AP0R0			__ICC_AP0Rx(0)
@@ -245,6 +246,21 @@ static inline void gic_write_bpr1(u32 val)
 	write_sysreg(val, ICC_BPR1);
 }
 
+static inline u32 gic_read_pmr(void)
+{
+	return read_sysreg(ICC_PMR);
+}
+
+static inline void gic_write_pmr(u32 val)
+{
+	write_sysreg(val, ICC_PMR);
+}
+
+static inline u32 gic_read_rpr(void)
+{
+	return read_sysreg(ICC_RPR);
+}
+
 /*
  * Even in 32bit systems that use LPAE, there is no guarantee that the I/O
  * interface provides true 64bit atomic accesses, so using strd/ldrd doesn't
@@ -347,5 +363,22 @@ static inline void gits_write_vpendbaser(u64 val, void * __iomem addr)
 
 #define gits_read_vpendbaser(c)		__gic_readq_nonatomic(c)
 
+static inline bool gic_prio_masking_enabled(void)
+{
+	return false;
+}
+
+static inline void gic_pmr_mask_irqs(void)
+{
+	/* Should not get called. */
+	WARN_ON_ONCE(true);
+}
+
+static inline void gic_arch_enable_irqs(void)
+{
+	/* Should not get called. */
+	WARN_ON_ONCE(true);
+}
+
 #endif /* !__ASSEMBLY__ */
 #endif /* !__ASM_ARCH_GICV3_H */
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index cfbf307d6dc4..4fab69620719 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -643,6 +643,25 @@ config QCOM_FALKOR_ERRATUM_E1041
 
 	  If unsure, say Y.
 
+config FUJITSU_ERRATUM_010001
+	bool "Fujitsu-A64FX erratum E#010001: Undefined fault may occur wrongly"
+	default y
+	help
+	  This option adds workaround for Fujitsu-A64FX erratum E#010001.
+	  On some variants of the Fujitsu-A64FX cores ver(1.0, 1.1), memory
+	  accesses may cause undefined fault (Data abort, DFSC=0b111111).
+	  This fault occurs under a specific hardware condition when a
+	  load/store instruction performs an address translation using:
+	  case-1  TTBR0_EL1 with TCR_EL1.NFD0 == 1.
+	  case-2  TTBR0_EL2 with TCR_EL2.NFD0 == 1.
+	  case-3  TTBR1_EL1 with TCR_EL1.NFD1 == 1.
+	  case-4  TTBR1_EL2 with TCR_EL2.NFD1 == 1.
+
+	  The workaround is to ensure these bits are clear in TCR_ELx.
+	  The workaround only affect the Fujitsu-A64FX.
+
+	  If unsure, say Y.
+
 endmenu
 
 
@@ -792,8 +811,7 @@ config SCHED_SMT
 config NR_CPUS
 	int "Maximum number of CPUs (2-4096)"
 	range 2 4096
-	# These have to remain sorted largest to smallest
-	default "64"
+	default "256"
 
 config HOTPLUG_CPU
 	bool "Support for hot-pluggable CPUs"
@@ -1328,6 +1346,20 @@ config ARM64_MODULE_PLTS
 	bool
 	select HAVE_MOD_ARCH_SPECIFIC
 
+config ARM64_PSEUDO_NMI
+	bool "Support for NMI-like interrupts"
+	select CONFIG_ARM_GIC_V3
+	help
+	  Adds support for mimicking Non-Maskable Interrupts through the use of
+	  GIC interrupt priority. This support requires version 3 or later of
+	  Arm GIC.
+
+	  This high priority configuration for interrupts needs to be
+	  explicitly enabled by setting the kernel parameter
+	  "irqchip.gicv3_pseudo_nmi" to 1.
+
+	  If unsure, say N
+
 config RELOCATABLE
 	bool
 	help
diff --git a/arch/arm64/Kconfig.platforms b/arch/arm64/Kconfig.platforms
index c5f6a57f16b8..70498a033cf5 100644
--- a/arch/arm64/Kconfig.platforms
+++ b/arch/arm64/Kconfig.platforms
@@ -151,7 +151,7 @@ config ARCH_MVEBU
 config ARCH_MXC
 	bool "ARMv8 based NXP i.MX SoC family"
 	select ARM64_ERRATUM_843419
-	select ARM64_ERRATUM_845719
+	select ARM64_ERRATUM_845719 if COMPAT
 	select IMX_GPCV2
 	select IMX_GPCV2_PM_DOMAINS
 	select PM
diff --git a/arch/arm64/include/asm/alternative.h b/arch/arm64/include/asm/alternative.h
index 4b650ec1d7dd..b9f8d787eea9 100644
--- a/arch/arm64/include/asm/alternative.h
+++ b/arch/arm64/include/asm/alternative.h
@@ -14,8 +14,6 @@
 #include <linux/stddef.h>
 #include <linux/stringify.h>
 
-extern int alternatives_applied;
-
 struct alt_instr {
 	s32 orig_offset;	/* offset to original instruction */
 	s32 alt_offset;		/* offset to replacement instruction */
@@ -27,7 +25,9 @@ struct alt_instr {
 typedef void (*alternative_cb_t)(struct alt_instr *alt,
 				 __le32 *origptr, __le32 *updptr, int nr_inst);
 
+void __init apply_boot_alternatives(void);
 void __init apply_alternatives_all(void);
+bool alternative_is_applied(u16 cpufeature);
 
 #ifdef CONFIG_MODULES
 void apply_alternatives_module(void *start, size_t length);
diff --git a/arch/arm64/include/asm/arch_gicv3.h b/arch/arm64/include/asm/arch_gicv3.h
index e278f94df0c9..14b41ddc68ba 100644
--- a/arch/arm64/include/asm/arch_gicv3.h
+++ b/arch/arm64/include/asm/arch_gicv3.h
@@ -22,6 +22,7 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/irqchip/arm-gic-common.h>
 #include <linux/stringify.h>
 #include <asm/barrier.h>
 #include <asm/cacheflush.h>
@@ -114,6 +115,21 @@ static inline void gic_write_bpr1(u32 val)
 	write_sysreg_s(val, SYS_ICC_BPR1_EL1);
 }
 
+static inline u32 gic_read_pmr(void)
+{
+	return read_sysreg_s(SYS_ICC_PMR_EL1);
+}
+
+static inline void gic_write_pmr(u32 val)
+{
+	write_sysreg_s(val, SYS_ICC_PMR_EL1);
+}
+
+static inline u32 gic_read_rpr(void)
+{
+	return read_sysreg_s(SYS_ICC_RPR_EL1);
+}
+
 #define gic_read_typer(c)		readq_relaxed(c)
 #define gic_write_irouter(v, c)		writeq_relaxed(v, c)
 #define gic_read_lpir(c)		readq_relaxed(c)
@@ -140,5 +156,21 @@ static inline void gic_write_bpr1(u32 val)
 #define gits_write_vpendbaser(v, c)	writeq_relaxed(v, c)
 #define gits_read_vpendbaser(c)		readq_relaxed(c)
 
+static inline bool gic_prio_masking_enabled(void)
+{
+	return system_uses_irq_prio_masking();
+}
+
+static inline void gic_pmr_mask_irqs(void)
+{
+	BUILD_BUG_ON(GICD_INT_DEF_PRI <= GIC_PRIO_IRQOFF);
+	gic_write_pmr(GIC_PRIO_IRQOFF);
+}
+
+static inline void gic_arch_enable_irqs(void)
+{
+	asm volatile ("msr daifclr, #2" : : : "memory");
+}
+
 #endif /* __ASSEMBLY__ */
 #endif /* __ASM_ARCH_GICV3_H */
diff --git a/arch/arm64/include/asm/asm-uaccess.h b/arch/arm64/include/asm/asm-uaccess.h
index 4128bec033f6..f74909ba29bd 100644
--- a/arch/arm64/include/asm/asm-uaccess.h
+++ b/arch/arm64/include/asm/asm-uaccess.h
@@ -24,7 +24,7 @@
 	.endm
 
 	.macro	__uaccess_ttbr0_enable, tmp1, tmp2
-	get_thread_info \tmp1
+	get_current_task \tmp1
 	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
 	mrs	\tmp2, ttbr1_el1
 	extr    \tmp2, \tmp2, \tmp1, #48
diff --git a/arch/arm64/include/asm/assembler.h b/arch/arm64/include/asm/assembler.h
index 4feb6119c3c9..c5308d01e228 100644
--- a/arch/arm64/include/asm/assembler.h
+++ b/arch/arm64/include/asm/assembler.h
@@ -27,6 +27,7 @@
 
 #include <asm/asm-offsets.h>
 #include <asm/cpufeature.h>
+#include <asm/cputype.h>
 #include <asm/