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

Pull arm64 updates from Will Deacon:
 "It's a bit all over the place this time with no "killer feature" to
  speak of.  Support for mismatched cache line sizes should help people
  seeing whacky JIT failures on some SoCs, and the big.LITTLE perf
  updates have been a long time coming, but a lot of the changes here
  are cleanups.

  We stray outside arch/arm64 in a few areas: the arch/arm/ arch_timer
  workaround is acked by Russell, the DT/OF bits are acked by Rob, the
  arch_timer clocksource changes acked by Marc, CPU hotplug by tglx and
  jump_label by Peter (all CC'd).

  Summary:

   - Support for execute-only page permissions
   - Support for hibernate and DEBUG_PAGEALLOC
   - Support for heterogeneous systems with mismatches cache line sizes
   - Errata workarounds (A53 843419 update and QorIQ A-008585 timer bug)
   - arm64 PMU perf updates, including cpumasks for heterogeneous systems
   - Set UTS_MACHINE for building rpm packages
   - Yet another head.S tidy-up
   - Some cleanups and refactoring, particularly in the NUMA code
   - Lots of random, non-critical fixes across the board"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (100 commits)
  arm64: tlbflush.h: add __tlbi() macro
  arm64: Kconfig: remove SMP dependence for NUMA
  arm64: Kconfig: select OF/ACPI_NUMA under NUMA config
  arm64: fix dump_backtrace/unwind_frame with NULL tsk
  arm/arm64: arch_timer: Use archdata to indicate vdso suitability
  arm64: arch_timer: Work around QorIQ Erratum A-008585
  arm64: arch_timer: Add device tree binding for A-008585 erratum
  arm64: Correctly bounds check virt_addr_valid
  arm64: migrate exception table users off module.h and onto extable.h
  arm64: pmu: Hoist pmu platform device name
  arm64: pmu: Probe default hw/cache counters
  arm64: pmu: add fallback probe table
  MAINTAINERS: Update ARM PMU PROFILING AND DEBUGGING entry
  arm64: Improve kprobes test for atomic sequence
  arm64/kvm: use alternative auto-nop
  arm64: use alternative auto-nop
  arm64: alternative: add auto-nop infrastructure
  arm64: lse: convert lse alternatives NOP padding to use __nops
  arm64: barriers: introduce nops and __nops macros for NOP sequences
  arm64: sysreg: replace open-coded mrs_s/msr_s with {read,write}_sysreg_s
  ...

Documentation/arm64/silicon-errata.txt

@@ -61,3 +61,5 @@ stable kernels.
 | Cavium         | ThunderX GICv3  | #23154          | CAVIUM_ERRATUM_23154    |
 | Cavium         | ThunderX Core   | #27456          | CAVIUM_ERRATUM_27456    |
 | Cavium         | ThunderX SMMUv2 | #27704          | N/A		       |
+|                |                 |                 |                         |
+| Freescale/NXP  | LS2080A/LS1043A | A-008585        | FSL_ERRATUM_A008585     |

Documentation/devicetree/bindings/arm/arch_timer.txt

@@ -25,6 +25,12 @@ to deliver its interrupts via SPIs.
 - always-on : a boolean property. If present, the timer is powered through an
   always-on power domain, therefore it never loses context.
 
+- fsl,erratum-a008585 : A boolean property. Indicates the presence of
+  QorIQ erratum A-008585, which says that reading the counter is
+  unreliable unless the same value is returned by back-to-back reads.
+  This also affects writes to the tval register, due to the implicit
+  counter read.
+
 ** Optional properties:
 
 - arm,cpu-registers-not-fw-configured : Firmware does not initialize

Documentation/kernel-parameters.txt

@@ -698,6 +698,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			loops can be debugged more effectively on production
 			systems.
 
+	clocksource.arm_arch_timer.fsl-a008585=
+			[ARM64]
+			Format: <bool>
+			Enable/disable the workaround of Freescale/NXP
+			erratum A-008585.  This can be useful for KVM
+			guests, if the guest device tree doesn't show the
+			erratum.  If unspecified, the workaround is
+			enabled based on the device tree.
+
 	clearcpuid=BITNUM [X86]
 			Disable CPUID feature X for the kernel. See
 			arch/x86/include/asm/cpufeatures.h for the valid bit

Documentation/static-keys.txt

@@ -15,6 +15,8 @@ The updated API replacements are:
 
 DEFINE_STATIC_KEY_TRUE(key);
 DEFINE_STATIC_KEY_FALSE(key);
+DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
+DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
 static_branch_likely()
 static_branch_unlikely()
 
@@ -140,6 +142,13 @@ static_branch_inc(), will change the branch back to true. Likewise, if the
 key is initialized false, a 'static_branch_inc()', will change the branch to
 true. And then a 'static_branch_dec()', will again make the branch false.
 
+Where an array of keys is required, it can be defined as:
+
+	DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count);
+
+or:
+
+	DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count);
 
 4) Architecture level code patching interface, 'jump labels'
 

MAINTAINERS

@@ -913,15 +913,17 @@ F:	arch/arm/include/asm/floppy.h
 
 ARM PMU PROFILING AND DEBUGGING
 M:	Will Deacon <will.deacon@arm.com>
-R:	Mark Rutland <mark.rutland@arm.com>
+M:	Mark Rutland <mark.rutland@arm.com>
 S:	Maintained
+L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 F:	arch/arm*/kernel/perf_*
 F:	arch/arm/oprofile/common.c
 F:	arch/arm*/kernel/hw_breakpoint.c
 F:	arch/arm*/include/asm/hw_breakpoint.h
 F:	arch/arm*/include/asm/perf_event.h
-F:	drivers/perf/arm_pmu.c
+F:	drivers/perf/*
 F:	include/linux/perf/arm_pmu.h
+F:	Documentation/devicetree/bindings/arm/pmu.txt
 
 ARM PORT
 M:	Russell King <linux@armlinux.org.uk>

arch/arm/Kconfig

@@ -1,6 +1,7 @@
 config ARM
 	bool
 	default y
+	select ARCH_CLOCKSOURCE_DATA
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ELF_RANDOMIZE

arch/arm/include/asm/clocksource.h

@@ -0,0 +1,8 @@
+#ifndef _ASM_CLOCKSOURCE_H
+#define _ASM_CLOCKSOURCE_H
+
+struct arch_clocksource_data {
+	bool vdso_direct;	/* Usable for direct VDSO access? */
+};
+
+#endif

arch/arm/kernel/perf_event_v7.c

@@ -596,12 +596,6 @@ static struct attribute_group armv7_pmuv1_events_attr_group = {
 	.attrs = armv7_pmuv1_event_attrs,
 };
 
-static const struct attribute_group *armv7_pmuv1_attr_groups[] = {
-	&armv7_pmuv1_events_attr_group,
-	&armv7_pmu_format_attr_group,
-	NULL,
-};
-
 ARMV7_EVENT_ATTR(mem_access, ARMV7_PERFCTR_MEM_ACCESS);
 ARMV7_EVENT_ATTR(l1i_cache, ARMV7_PERFCTR_L1_ICACHE_ACCESS);
 ARMV7_EVENT_ATTR(l1d_cache_wb, ARMV7_PERFCTR_L1_DCACHE_WB);
@@ -653,12 +647,6 @@ static struct attribute_group armv7_pmuv2_events_attr_group = {
 	.attrs = armv7_pmuv2_event_attrs,
 };
 
-static const struct attribute_group *armv7_pmuv2_attr_groups[] = {
-	&armv7_pmuv2_events_attr_group,
-	&armv7_pmu_format_attr_group,
-	NULL,
-};
-
 /*
  * Perf Events' indices
  */
@@ -1208,7 +1196,10 @@ static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a8";
 	cpu_pmu->map_event	= armv7_a8_map_event;
-	cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv7_pmuv1_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv7_pmu_format_attr_group;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1217,7 +1208,10 @@ static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu)
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a9";
 	cpu_pmu->map_event	= armv7_a9_map_event;
-	cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv7_pmuv1_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv7_pmu_format_attr_group;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1226,7 +1220,10 @@ static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu)
 	armv7pmu_init(cpu_pmu);
 	cpu_pmu->name		= "armv7_cortex_a5";
 	cpu_pmu->map_event	= armv7_a5_map_event;
-	cpu_pmu->pmu.attr_groups = armv7_pmuv1_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv7_pmuv1_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv7_pmu_format_attr_group;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1236,7 +1233,10 @@ static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->name		= "armv7_cortex_a15";
 	cpu_pmu->map_event	= armv7_a15_map_event;
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
-	cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv7_pmuv2_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv7_pmu_format_attr_group;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1246,7 +1246,10 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->name		= "armv7_cortex_a7";
 	cpu_pmu->map_event	= armv7_a7_map_event;
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
-	cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv7_pmuv2_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv7_pmu_format_attr_group;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1256,7 +1259,10 @@ static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->name		= "armv7_cortex_a12";
 	cpu_pmu->map_event	= armv7_a12_map_event;
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
-	cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv7_pmuv2_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv7_pmu_format_attr_group;
 	return armv7_probe_num_events(cpu_pmu);
 }
 
@@ -1264,7 +1270,10 @@ static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	int ret = armv7_a12_pmu_init(cpu_pmu);
 	cpu_pmu->name = "armv7_cortex_a17";
-	cpu_pmu->pmu.attr_groups = armv7_pmuv2_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv7_pmuv2_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv7_pmu_format_attr_group;
 	return ret;
 }
 

arch/arm/kernel/vdso.c

@@ -270,7 +270,7 @@ static bool tk_is_cntvct(const struct timekeeper *tk)
 	if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER))
 		return false;
 
-	if (strcmp(tk->tkr_mono.clock->name, "arch_sys_counter") != 0)
+	if (!tk->tkr_mono.clock->archdata.vdso_direct)
 		return false;
 
 	return true;

arch/arm64/Kconfig

@@ -4,6 +4,7 @@ config ARM64
 	select ACPI_GENERIC_GSI if ACPI
 	select ACPI_REDUCED_HARDWARE_ONLY if ACPI
 	select ACPI_MCFG if ACPI
+	select ARCH_CLOCKSOURCE_DATA
 	select ARCH_HAS_DEVMEM_IS_ALLOWED
 	select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
@@ -102,10 +103,8 @@ config ARM64
 	select NO_BOOTMEM
 	select OF
 	select OF_EARLY_FLATTREE
-	select OF_NUMA if NUMA && OF
 	select OF_RESERVED_MEM
 	select PCI_ECAM if ACPI
-	select PERF_USE_VMALLOC
 	select POWER_RESET
 	select POWER_SUPPLY
 	select SPARSE_IRQ
@@ -122,6 +121,9 @@ config ARCH_PHYS_ADDR_T_64BIT
 config MMU
 	def_bool y
 
+config DEBUG_RODATA
+	def_bool y
+
 config ARM64_PAGE_SHIFT
 	int
 	default 16 if ARM64_64K_PAGES
@@ -415,18 +417,13 @@ config ARM64_ERRATUM_845719
 
 config ARM64_ERRATUM_843419
 	bool "Cortex-A53: 843419: A load or store might access an incorrect address"
-	depends on MODULES
 	default y
-	select ARM64_MODULE_CMODEL_LARGE
+	select ARM64_MODULE_CMODEL_LARGE if MODULES
 	help
-	  This option builds kernel modules using the large memory model in
-	  order to avoid the use of the ADRP instruction, which can cause
-	  a subsequent memory access to use an incorrect address on Cortex-A53
-	  parts up to r0p4.
-
-	  Note that the kernel itself must be linked with a version of ld
-	  which fixes potentially affected ADRP instructions through the
-	  use of veneers.
+	  This option links the kernel with '--fix-cortex-a53-843419' and
+	  builds modules using the large memory model in order to avoid the use
+	  of the ADRP instruction, which can cause a subsequent memory access
+	  to use an incorrect address on Cortex-A53 parts up to r0p4.
 
 	  If unsure, say Y.
 
@@ -582,7 +579,8 @@ config HOTPLUG_CPU
 # Common NUMA Features
 config NUMA
 	bool "Numa Memory Allocation and Scheduler Support"
-	depends on SMP
+	select ACPI_NUMA if ACPI
+	select OF_NUMA
 	help
 	  Enable NUMA (Non Uniform Memory Access) support.
 
@@ -603,11 +601,18 @@ config USE_PERCPU_NUMA_NODE_ID
 	def_bool y
 	depends on NUMA
 
+config HAVE_SETUP_PER_CPU_AREA
+	def_bool y
+	depends on NUMA
+
+config NEED_PER_CPU_EMBED_FIRST_CHUNK
+	def_bool y
+	depends on NUMA
+
 source kernel/Kconfig.preempt
 source kernel/Kconfig.hz
 
 config ARCH_SUPPORTS_DEBUG_PAGEALLOC
-	depends on !HIBERNATION
 	def_bool y
 
 config ARCH_HAS_HOLES_MEMORYMODEL

arch/arm64/Kconfig.debug

@@ -49,16 +49,6 @@ config DEBUG_SET_MODULE_RONX
 
 	  If in doubt, say Y.
 
-config DEBUG_RODATA
-	bool "Make kernel text and rodata read-only"
-	default y
-	help
-	  If this is set, kernel text and rodata will be made read-only. This
-	  is to help catch accidental or malicious attempts to change the
-	  kernel's executable code.
-
-	  If in doubt, say Y.
-
 config DEBUG_ALIGN_RODATA
 	depends on DEBUG_RODATA
 	bool "Align linker sections up to SECTION_SIZE"

arch/arm64/Kconfig.platforms

@@ -159,7 +159,6 @@ config ARCH_TEGRA
 	select CLKSRC_MMIO
 	select CLKSRC_OF
 	select GENERIC_CLOCKEVENTS
-	select HAVE_CLK
 	select PINCTRL
 	select RESET_CONTROLLER
 	help

arch/arm64/Makefile

@@ -18,6 +18,14 @@ ifneq ($(CONFIG_RELOCATABLE),)
 LDFLAGS_vmlinux		+= -pie -Bsymbolic
 endif
 
+ifeq ($(CONFIG_ARM64_ERRATUM_843419),y)
+  ifeq ($(call ld-option, --fix-cortex-a53-843419),)
+$(warning ld does not support --fix-cortex-a53-843419; kernel may be susceptible to erratum)
+  else
+LDFLAGS_vmlinux	+= --fix-cortex-a53-843419
+  endif
+endif
+
 KBUILD_DEFCONFIG := defconfig
 
 # Check for binutils support for specific extensions
@@ -38,10 +46,12 @@ ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian
 AS		+= -EB
 LD		+= -EB
+UTS_MACHINE	:= aarch64_be
 else
 KBUILD_CPPFLAGS	+= -mlittle-endian
 AS		+= -EL
 LD		+= -EL
+UTS_MACHINE	:= aarch64
 endif
 
 CHECKFLAGS	+= -D__aarch64__

arch/arm64/include/asm/Kbuild

@@ -1,4 +1,3 @@
-generic-y += bug.h
 generic-y += bugs.h
 generic-y += clkdev.h
 generic-y += cputime.h
@@ -10,7 +9,6 @@ generic-y += dma-contiguous.h
 generic-y += early_ioremap.h
 generic-y += emergency-restart.h
 generic-y += errno.h
-generic-y += ftrace.h
 generic-y += hw_irq.h
 generic-y += ioctl.h
 generic-y += ioctls.h
@@ -27,12 +25,10 @@ generic-y += mman.h
 generic-y += msgbuf.h
 generic-y += msi.h
 generic-y += mutex.h
-generic-y += pci.h
 generic-y += poll.h
 generic-y += preempt.h
 generic-y += resource.h
 generic-y += rwsem.h
-generic-y += sections.h
 generic-y += segment.h
 generic-y += sembuf.h
 generic-y += serial.h
@@ -45,7 +41,6 @@ generic-y += swab.h
 generic-y += switch_to.h
 generic-y += termbits.h
 generic-y += termios.h
-generic-y += topology.h
 generic-y += trace_clock.h
 generic-y += types.h
 generic-y += unaligned.h

arch/arm64/include/asm/acpi.h

@@ -12,7 +12,7 @@
 #ifndef _ASM_ACPI_H
 #define _ASM_ACPI_H
 
-#include <linux/mm.h>
+#include <linux/memblock.h>
 #include <linux/psci.h>
 
 #include <asm/cputype.h>
@@ -32,7 +32,11 @@
 static inline void __iomem *acpi_os_ioremap(acpi_physical_address phys,
 					    acpi_size size)
 {
-	if (!page_is_ram(phys >> PAGE_SHIFT))
+	/*
+	 * EFI's reserve_regions() call adds memory with the WB attribute
+	 * to memblock via early_init_dt_add_memory_arch().
+	 */
+	if (!memblock_is_memory(phys))
 		return ioremap(phys, size);
 
 	return ioremap_cache(phys, size);

arch/arm64/include/asm/alternative.h

@@ -2,6 +2,7 @@
 #define __ASM_ALTERNATIVE_H
 
 #include <asm/cpufeature.h>
+#include <asm/insn.h>
 
 #ifndef __ASSEMBLY__
 
@@ -90,34 +91,55 @@ void apply_alternatives(void *start, size_t length);
 .endm
 
 /*
- * Begin an alternative code sequence.
+ * Alternative sequences
+ *
+ * The code for the case where the capability is not present will be
+ * assembled and linked as normal. There are no restrictions on this
+ * code.
+ *
+ * The code for the case where the capability is present will be
+ * assembled into a special section to be used for dynamic patching.
+ * Code for that case must:
+ *
+ * 1. Be exactly the same length (in bytes) as the default code
+ *    sequence.
  *
- * The code that follows this macro will be assembled and linked as
- * normal. There are no restrictions on this code.
+ * 2. Not contain a branch target that is used outside of the
+ *    alternative sequence it is defined in (branches into an
+ *    alternative sequence are not fixed up).
+ */
+
+/*
+ * Begin an alternative code sequence.
  */
 .macro alternative_if_not cap
+	.set .Lasm_alt_mode, 0
 	.pushsection .altinstructions, "a"
 	altinstruction_entry 661f, 663f, \cap, 662f-661f, 664f-663f
 	.popsection
 661:
 .endm
 
+.macro alternative_if cap
+	.set .Lasm_alt_mode, 1
+	.pushsection .altinstructions, "a"
+	altinstruction_entry 663f, 661f, \cap, 664f-663f, 662f-661f
+	.popsection
+	.pushsection .altinstr_replacement, "ax"
+	.align 2	/* So GAS knows label 661 is suitably aligned */
+661:
+.endm
+
 /*
- * Provide the alternative code sequence.
- *
- * The code that follows this macro is assembled into a special
- * section to be used for dynamic patching. Code that follows this
- * macro must:
- *
- * 1. Be exactly the same length (in bytes) as the default code
- *    sequence.
- *
- * 2. Not contain a branch target that is used outside of the
- *    alternative sequence it is defined in (branches into an
- *    alternative sequence are not fixed up).
+ * Provide the other half of the alternative code sequence.
  */
 .macro alternative_else
-662:	.pushsection .altinstr_replacement, "ax"
+662:
+	.if .Lasm_alt_mode==0
+	.pushsection .altinstr_replacement, "ax"
+	.else
+	.popsection
+	.endif
 663:
 .endm
 
@@ -125,11 +147,25 @@ void apply_alternatives(void *start, size_t length);
  * Complete an alternative code sequence.
  */
 .macro alternative_endif
-664:	.popsection
+664:
+	.if .Lasm_alt_mode==0
+	.popsection
+	.endif
 	.org	. - (664b-663b) + (662b-661b)
 	.org	. - (662b-661b) + (664b-663b)
 .endm
 
+/*
+ * Provides a trivial alternative or default sequence consisting solely
+ * of NOPs. The number of NOPs is chosen automatically to match the
+ * previous case.
+ */
+.macro alternative_else_nop_endif
+alternative_else
+	nops	(662b-661b) / AARCH64_INSN_SIZE
+alternative_endif
+.endm
+
 #define _ALTERNATIVE_CFG(insn1, insn2, cap, cfg, ...)	\
 	alternative_insn insn1, insn2, cap, IS_ENABLED(cfg)
 

arch/arm64/include/asm/arch_timer.h

@@ -20,13 +20,55 @@
 #define __ASM_ARCH_TIMER_H
 
 #include <asm/barrier.h>
+#include <asm/sysreg.h>
 
 #include <linux/bug.h>
 #include <linux/init.h>
+#include <linux/jump_label.h>
 #include <linux/types.h>
 
 #include <clocksource/arm_arch_timer.h>
 
+#if IS_ENABLED(CONFIG_FSL_ERRATUM_A008585)
+extern struct static_key_false arch_timer_read_ool_enabled;
+#define needs_fsl_a008585_workaround() \
+	static_branch_unlikely(&arch_timer_read_ool_enabled)
+#else
+#define needs_fsl_a008585_workaround()  false
+#endif
+
+u32 __fsl_a008585_read_cntp_tval_el0(void);
+u32 __fsl_a008585_read_cntv_tval_el0(void);
+u64 __fsl_a008585_read_cntvct_el0(void);
+
+/*
+ * The number of retries is an arbitrary value well beyond the highest number
+ * of iterations the loop has been observed to take.
+ */
+#define __fsl_a008585_read_reg(reg) ({			\
+	u64 _old, _new;					\
+	int _retries = 200;				\
+							\
+	do {						\
+		_old = read_sysreg(reg);		\
+		_new = read_sysreg(reg);		\
+		_retries--;				\
+	} while (unlikely(_old != _new) && _retries);	\
+							\
+	WARN_ON_ONCE(!_retries);			\
+	_new;						\
+})
+
+#define arch_timer_reg_read_stable(reg) 		\
+({							\
+	u64 _val;					\
+	if (needs_fsl_a008585_workaround())		\
+		_val = __fsl_a008585_read_##reg();	\
+	else						\
+		_val = read_sysreg(reg);		\
+	_val;						\
+})
+
 /*
  * These register accessors are marked inline so the compiler can
  * nicely work out which register we want, and chuck away the rest of
@@ -38,19 +80,19 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
 	if (access == ARCH_TIMER_PHYS_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			asm volatile("msr cntp_ctl_el0,  %0" : : "r" (val));
+			write_sysreg(val, cntp_ctl_el0);
 			break;
 		case ARCH_TIMER_REG_TVAL:
-			asm volatile("msr cntp_tval_el0, %0" : : "r" (val));
+			write_sysreg(val, cntp_tval_el0);
 			break;
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			asm volatile("msr cntv_ctl_el0,  %0" : : "r" (val));
+			write_sysreg(val, cntv_ctl_el0);
 			break;
 		case ARCH_TIMER_REG_TVAL:
-			asm volatile("msr cntv_tval_el0, %0" : : "r" (val));
+			write_sysreg(val, cntv_tval_el0);
 			break;
 		}
 	}
@@ -61,48 +103,38 @@ void arch_timer_reg_write_cp15(int access, enum arch_timer_reg reg, u32 val)
 static __always_inline
 u32 arch_timer_reg_read_cp15(int access, enum arch_timer_reg reg)
 {
-	u32 val;
-
 	if (access == ARCH_TIMER_PHYS_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			asm volatile("mrs %0,  cntp_ctl_el0" : "=r" (val));
-			break;
+			return read_sysreg(cntp_ctl_el0);
 		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mrs %0, cntp_tval_el0" : "=r" (val));
-			break;
+			return arch_timer_reg_read_stable(cntp_tval_el0);
 		}
 	} else if (access == ARCH_TIMER_VIRT_ACCESS) {
 		switch (reg) {
 		case ARCH_TIMER_REG_CTRL:
-			asm volatile("mrs %0,  cntv_ctl_el0" : "=r" (val));
-			break;
+			return read_sysreg(cntv_ctl_el0);
 		case ARCH_TIMER_REG_TVAL:
-			asm volatile("mrs %0, cntv_tval_el0" : "=r" (val));
-			break;
+			return arch_timer_reg_read_stable(cntv_tval_el0);
 		}
 	}
 
-	return val;
+	BUG();
 }
 
 static inline u32 arch_timer_get_cntfrq(void)
 {
-	u32 val;
-	asm volatile("mrs %0,   cntfrq_el0" : "=r" (val));
-	return val;
+	return read_sysreg(cntfrq_el0);
 }
 
 static inline u32 arch_timer_get_cntkctl(void)
 {
-	u32 cntkctl;
-	asm volatile("mrs	%0, cntkctl_el1" : "=r" (cntkctl));
-	return cntkctl;
+	return read_sysreg(cntkctl_el1);
 }
 
 static inline void arch_timer_set_cntkctl(u32 cntkctl)
 {
-	asm volatile("msr	cntkctl_el1, %0" : : "r" (cntkctl));
+	write_sysreg(cntkctl, cntkctl_el1);
 }
 
 static inline u64 arch_counter_get_cntpct(void)
@@ -116,12 +148,8 @@ static inline u64 arch_counter_get_cntpct(void)
 
 static inline u64 arch_counter_get_cntvct(void)
 {
-	u64 cval;
-
 	isb();
-	asm volatile("mrs %0, cntvct_el0" : "=r" (cval));
-
-	return cval;
+	return arch_timer_reg_read_stable(cntvct_el0);
 }
 
 static inline int arch_timer_arch_init(void)

arch/arm64/include/asm/assembler.h

@@ -86,6 +86,15 @@
 	dmb	\opt
 	.endm
 
+/*
+ * NOP sequence
+ */
+	.macro	nops, num
+	.rept	\num
+	nop
+	.endr
+	.endm
+
 /*
  * Emit an entry into the exception table
  */
@@ -216,11 +225,26 @@ lr	.req	x30		// link register
 	.macro	mmid, rd, rn
 	ldr	\rd, [\rn, #MM_CONTEXT_ID]
 	.endm
+/*
+ * read_ctr - read CTR_EL0. If the system has mismatched
+ * cache line sizes, provide the system wide safe value
+ * from arm64_ftr_reg_ctrel0.sys_val
+ */
+	.macro	read_ctr, reg
+alternative_if_not ARM64_MISMATCHED_CACHE_LINE_SIZE
+	mrs	\reg, ctr_el0			// read CTR
+	nop
+alternative_else
+	ldr_l	\reg, arm64_ftr_reg_ctrel0 + ARM64_FTR_SYSVAL
+alternative_endif
+	.endm
+
 
 /*
- * dcache_line_size - get the minimum D-cache line size from the CTR register.
+ * raw_dcache_line_size - get the minimum D-cache line size on this CPU
+ * from the CTR register.
  */
-	.macro	dcache_line_size, reg, tmp
+	.macro	raw_dcache_line_size, reg, tmp
 	mrs	\tmp, ctr_el0			// read CTR
 	ubfm	\tmp, \tmp, #16, #19		// cache line size encoding
 	mov	\reg, #4			// bytes per word
@@ -228,15 +252,36 @@ lr	.req	x30		// link register
 	.endm
 
 /*
- * icache_line_size - get the minimum I-cache line size from the CTR register.
+ * dcache_line_size - get the safe D-cache line size across all CPUs
  */
-	.macro	icache_line_size, reg, tmp
+	.macro	dcache_line_size, reg, tmp
+	read_ctr	\tmp
+	ubfm		\tmp, \tmp, #16, #19	// cache line size encoding
+	mov		\reg, #4		// bytes per word
+	lsl		\reg, \reg, \tmp	// actual cache line size
+	.endm
+
+/*
+ * raw_icache_line_size - get the minimum I-cache line size on this CPU
+ * from the CTR register.
+ */
+	.macro	raw_icache_line_size, reg, tmp
 	mrs	\tmp, ctr_el0			// read CTR
 	and	\tmp, \tmp, #0xf		// cache line size encoding
 	mov	\reg, #4			// bytes per word
 	lsl	\reg, \reg, \tmp		// actual cache line size
 	.endm
 
+/*
+ * icache_line_size - get the safe I-cache line size across all CPUs
+ */
+	.macro	icache_line_size, reg, tmp
+	read_ctr	\tmp
+	and		\tmp, \tmp, #0xf	// cache line size encoding
+	mov		\reg, #4		// bytes per word
+	lsl		\reg, \reg, \tmp	// actual cache line size
+	.endm
+
 /*
  * tcr_set_idmap_t0sz - update TCR.T0SZ so that we can load the ID map
  */

arch/arm64/include/asm/atomic_lse.h

@@ -86,8 +86,8 @@ static inline int atomic_add_return##name(int i, atomic_t *v)		\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC(add_return##name),				\
+	__LL_SC_ATOMIC(add_return##name)				\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	ldadd" #mb "	%w[i], w30, %[v]\n"			\
 	"	add	%w[i], %w[i], w30")				\
@@ -112,8 +112,8 @@ static inline void atomic_and(int i, atomic_t *v)
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC(and),
+	__LL_SC_ATOMIC(and)
+	__nops(1),
 	/* LSE atomics */
 	"	mvn	%w[i], %w[i]\n"
 	"	stclr	%w[i], %[v]")
@@ -130,8 +130,8 @@ static inline int atomic_fetch_and##name(int i, atomic_t *v)		\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC(fetch_and##name),				\
+	__LL_SC_ATOMIC(fetch_and##name)					\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	mvn	%w[i], %w[i]\n"					\
 	"	ldclr" #mb "	%w[i], %w[i], %[v]")			\
@@ -156,8 +156,8 @@ static inline void atomic_sub(int i, atomic_t *v)
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC(sub),
+	__LL_SC_ATOMIC(sub)
+	__nops(1),
 	/* LSE atomics */
 	"	neg	%w[i], %w[i]\n"
 	"	stadd	%w[i], %[v]")
@@ -174,9 +174,8 @@ static inline int atomic_sub_return##name(int i, atomic_t *v)		\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
 	__LL_SC_ATOMIC(sub_return##name)				\
-	"	nop",							\
+	__nops(2),							\
 	/* LSE atomics */						\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], w30, %[v]\n"			\
@@ -203,8 +202,8 @@ static inline int atomic_fetch_sub##name(int i, atomic_t *v)		\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC(fetch_sub##name),				\
+	__LL_SC_ATOMIC(fetch_sub##name)					\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	neg	%w[i], %w[i]\n"					\
 	"	ldadd" #mb "	%w[i], %w[i], %[v]")			\
@@ -284,8 +283,8 @@ static inline long atomic64_add_return##name(long i, atomic64_t *v)	\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC64(add_return##name),				\
+	__LL_SC_ATOMIC64(add_return##name)				\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	ldadd" #mb "	%[i], x30, %[v]\n"			\
 	"	add	%[i], %[i], x30")				\
@@ -310,8 +309,8 @@ static inline void atomic64_and(long i, atomic64_t *v)
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC64(and),
+	__LL_SC_ATOMIC64(and)
+	__nops(1),
 	/* LSE atomics */
 	"	mvn	%[i], %[i]\n"
 	"	stclr	%[i], %[v]")
@@ -328,8 +327,8 @@ static inline long atomic64_fetch_and##name(long i, atomic64_t *v)	\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC64(fetch_and##name),				\
+	__LL_SC_ATOMIC64(fetch_and##name)				\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	mvn	%[i], %[i]\n"					\
 	"	ldclr" #mb "	%[i], %[i], %[v]")			\
@@ -354,8 +353,8 @@ static inline void atomic64_sub(long i, atomic64_t *v)
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
-	"	nop\n"
-	__LL_SC_ATOMIC64(sub),
+	__LL_SC_ATOMIC64(sub)
+	__nops(1),
 	/* LSE atomics */
 	"	neg	%[i], %[i]\n"
 	"	stadd	%[i], %[v]")
@@ -372,9 +371,8 @@ static inline long atomic64_sub_return##name(long i, atomic64_t *v)	\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
 	__LL_SC_ATOMIC64(sub_return##name)				\
-	"	nop",							\
+	__nops(2),							\
 	/* LSE atomics */						\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], x30, %[v]\n"			\
@@ -401,8 +399,8 @@ static inline long atomic64_fetch_sub##name(long i, atomic64_t *v)	\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	__LL_SC_ATOMIC64(fetch_sub##name),				\
+	__LL_SC_ATOMIC64(fetch_sub##name)				\
+	__nops(1),							\
 	/* LSE atomics */						\
 	"	neg	%[i], %[i]\n"					\
 	"	ldadd" #mb "	%[i], %[i], %[v]")			\
@@ -426,13 +424,8 @@ static inline long atomic64_dec_if_positive(atomic64_t *v)
 
 	asm volatile(ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
-	"	nop\n"
 	__LL_SC_ATOMIC64(dec_if_positive)
-	"	nop\n"
-	"	nop\n"
-	"	nop\n"
-	"	nop\n"
-	"	nop",
+	__nops(6),
 	/* LSE atomics */
 	"1:	ldr	x30, %[v]\n"
 	"	subs	%[ret], x30, #1\n"
@@ -464,9 +457,8 @@ static inline unsigned long __cmpxchg_case_##name(volatile void *ptr,	\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-		__LL_SC_CMPXCHG(name)					\
-	"	nop",							\
+	__LL_SC_CMPXCHG(name)						\
+	__nops(2),							\
 	/* LSE atomics */						\
 	"	mov	" #w "30, %" #w "[old]\n"			\
 	"	cas" #mb #sz "\t" #w "30, %" #w "[new], %[v]\n"		\
@@ -517,10 +509,8 @@ static inline long __cmpxchg_double##name(unsigned long old1,		\
 									\
 	asm volatile(ARM64_LSE_ATOMIC_INSN(				\
 	/* LL/SC */							\
-	"	nop\n"							\
-	"	nop\n"							\
-	"	nop\n"							\
-	__LL_SC_CMPXCHG_DBL(name),					\
+	__LL_SC_CMPXCHG_DBL(name)					\
+	__nops(3),							\
 	/* LSE atomics */						\
 	"	casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\
 	"	eor	%[old1], %[old1], %[oldval1]\n"			\

arch/arm64/include/asm/barrier.h

@@ -20,6 +20,9 @@
 
 #ifndef __ASSEMBLY__
 
+#define __nops(n)	".rept	" #n "\nnop\n.endr\n"
+#define nops(n)		asm volatile(__nops(n))
+
 #define sev()		asm volatile("sev" : : : "memory")
 #define wfe()		asm volatile("wfe" : : : "memory")
 #define wfi()		asm volatile("wfi" : : : "memory")

arch/arm64/include/asm/cacheflush.h

@@ -68,6 +68,7 @@
 extern void flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void flush_icache_range(unsigned long start, unsigned long end);
 extern void __flush_dcache_area(void *addr, size_t len);
+extern void __clean_dcache_area_poc(void *addr, size_t len);
 extern void __clean_dcache_area_pou(void *addr, size_t len);
 extern long __flush_cache_user_range(unsigned long start, unsigned long end);
 
@@ -85,7 +86,7 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
  */
 extern void __dma_map_area(const void *, size_t, int);
 extern void __dma_unmap_area(const void *, size_t, int);
-extern void __dma_flush_range(const void *, const void *);
+extern void __dma_flush_area(const void *, size_t);
 
 /*
  * Copy user data from/to a page which is mapped into a different

arch/arm64/include/asm/clocksource.h

@@ -0,0 +1,8 @@
+#ifndef _ASM_CLOCKSOURCE_H
+#define _ASM_CLOCKSOURCE_H
+
+struct arch_clocksource_data {
+	bool vdso_direct;	/* Usable for direct VDSO access? */
+};
+
+#endif

arch/arm64/include/asm/cmpxchg.h

@@ -43,10 +43,8 @@ static inline unsigned long __xchg_case_##name(unsigned long x,		\
 	"	cbnz	%w1, 1b\n"					\
 	"	" #mb,							\
 	/* LSE atomics */						\
-	"	nop\n"							\
-	"	nop\n"							\
 	"	swp" #acq_lse #rel #sz "\t%" #w "3, %" #w "0, %2\n"	\
-	"	nop\n"							\
+		__nops(3)						\
 	"	" #nop_lse)						\
 	: "=&r" (ret), "=&r" (tmp), "+Q" (*(u8 *)ptr)			\
 	: "r" (x)							\

arch/arm64/include/asm/cpufeature.h

@@ -9,6 +9,8 @@
 #ifndef __ASM_CPUFEATURE_H
 #define __ASM_CPUFEATURE_H
 
+#include <linux/jump_label.h>
+
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
 
@@ -37,8 +39,9 @@
 #define ARM64_WORKAROUND_CAVIUM_27456		12
 #define ARM64_HAS_32BIT_EL0			13
 #define ARM64_HYP_OFFSET_LOW			14
+#define ARM64_MISMATCHED_CACHE_LINE_SIZE	15
 
-#define ARM64_NCAPS				15
+#define ARM64_NCAPS				16
 
 #ifndef __ASSEMBLY__
 
@@ -63,7 +66,7 @@ struct arm64_ftr_bits {
 	enum ftr_type	type;
 	u8		shift;
 	u8		width;
-	s64		safe_val; /* safe value for discrete features */
+	s64		safe_val; /* safe value for FTR_EXACT features */
 };
 
 /*
@@ -72,13 +75,14 @@ struct arm64_ftr_bits {
  * @sys_val		Safe value across the CPUs (system view)
  */
 struct arm64_ftr_reg {
-	u32			sys_id;
-	const char		*name;
-	u64			strict_mask;
-	u64			sys_val;
-	struct arm64_ftr_bits	*ftr_bits;
+	const char			*name;
+	u64				strict_mask;
+	u64				sys_val;
+	const struct arm64_ftr_bits	*ftr_bits;
 };
 
+extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0;
+
 /* scope of capability check */
 enum {
 	SCOPE_SYSTEM,
@@ -109,6 +113,7 @@ struct arm64_cpu_capabilities {
 };
 
 extern DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+extern struct static_key_false cpu_hwcap_keys[ARM64_NCAPS];
 
 bool this_cpu_has_cap(unsigned int cap);
 
@@ -121,16 +126,21 @@ static inline bool cpus_have_cap(unsigned int num)
 {
 	if (num >= ARM64_NCAPS)
 		return false;
-	return test_bit(num, cpu_hwcaps);
+	if (__builtin_constant_p(num))
+		return static_branch_unlikely(&cpu_hwcap_keys[num]);
+	else
+		return test_bit(num, cpu_hwcaps);
 }
 
 static inline void cpus_set_cap(unsigned int num)
 {
-	if (num >= ARM64_NCAPS)
+	if (num >= ARM64_NCAPS) {
 		pr_warn("Attempt to set an illegal CPU capability (%d >= %d)\n",
 			num, ARM64_NCAPS);
-	else
+	} else {
 		__set_bit(num, cpu_hwcaps);
+		static_branch_enable(&cpu_hwcap_keys[num]);
+	}
 }
 
 static inline int __attribute_const__
@@ -157,7 +167,7 @@ cpuid_feature_extract_unsigned_field(u64 features, int field)
 	return cpuid_feature_extract_unsigned_field_width(features, field, 4);
 }
 
-static inline u64 arm64_ftr_mask(struct arm64_ftr_bits *ftrp)
+static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp)
 {
 	return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift);
 }
@@ -170,7 +180,7 @@ cpuid_feature_extract_field(u64 features, int field, bool sign)
 		cpuid_feature_extract_unsigned_field(features, field);
 }
 
-static inline s64 arm64_ftr_value(struct arm64_ftr_bits *ftrp, u64 val)
+static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val)
 {
 	return (s64)cpuid_feature_extract_field(val, ftrp->shift, ftrp->sign);
 }
@@ -193,11 +203,11 @@ void __init setup_cpu_features(void);
 void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps,
 			    const char *info);
 void enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps);
-void check_local_cpu_errata(void);
-void __init enable_errata_workarounds(void);
+void check_local_cpu_capabilities(void);
 
-void verify_local_cpu_errata(void);
-void verify_local_cpu_capabilities(void);
+void update_cpu_errata_workarounds(void);
+void __init enable_errata_workarounds(void);
+void verify_local_cpu_errata_workarounds(void);
 
 u64 read_system_reg(u32 id);
 

arch/arm64/include/asm/cputype.h

@@ -93,11 +93,7 @@
 
 #include <asm/sysreg.h>
 
-#define read_cpuid(reg) ({						\
-	u64 __val;							\
-	asm("mrs_s	%0, " __stringify(SYS_ ## reg) : "=r" (__val));	\
-	__val;								\
-})
+#define read_cpuid(reg)			read_sysreg_s(SYS_ ## reg)
 
 /*
  * The CPU ID never changes at run time, so we might as well tell the

arch/arm64/include/asm/dcc.h

@@ -21,21 +21,16 @@
 #define __ASM_DCC_H
 
 #include <asm/barrier.h>
+#include <asm/sysreg.h>
 
 static inline u32 __dcc_getstatus(void)
 {
-	u32 ret;
-
-	asm volatile("mrs %0, mdccsr_el0" : "=r" (ret));
-
-	return ret;
+	return read_sysreg(mdccsr_el0);
 }
 
 static inline char __dcc_getchar(void)
 {
-	char c;
-
-	asm volatile("mrs %0, dbgdtrrx_el0" : "=r" (c));
+	char c = read_sysreg(dbgdtrrx_el0);
 	isb();
 
 	return c;
@@ -47,8 +42,7 @@ static inline void __dcc_putchar(char c)
 	 * The typecast is to make absolutely certain that 'c' is
 	 * zero-extended.
 	 */
-	asm volatile("msr dbgdtrtx_el0, %0"
-			: : "r" ((unsigned long)(unsigned char)c));
+	write_sysreg((unsigned char)c, dbgdtrtx_el0);
 	isb();
 }
 

arch/arm64/include/asm/esr.h

@@ -78,6 +78,23 @@
 
 #define ESR_ELx_IL		(UL(1) << 25)
 #define ESR_ELx_ISS_MASK	(ESR_ELx_IL - 1)
+
+/* ISS field definitions shared by different classes */
+#define ESR_ELx_WNR		(UL(1) << 6)
+
+/* Shared ISS field definitions for Data/Instruction aborts */
+#define ESR_ELx_EA		(UL(1) << 9)
+#define ESR_ELx_S1PTW		(UL(1) << 7)
+
+/* Shared ISS fault status code(IFSC/DFSC) for Data/Instruction aborts */
+#define ESR_ELx_FSC		(0x3F)
+#define ESR_ELx_FSC_TYPE	(0x3C)
+#define ESR_ELx_FSC_EXTABT	(0x10)
+#define ESR_ELx_FSC_ACCESS	(0x08)
+#define ESR_ELx_FSC_FAULT	(0x04)
+#define ESR_ELx_FSC_PERM	(0x0C)
+
+/* ISS field definitions for Data Aborts */
 #define ESR_ELx_ISV		(UL(1) << 24)
 #define ESR_ELx_SAS_SHIFT	(22)
 #define ESR_ELx_SAS		(UL(3) << ESR_ELx_SAS_SHIFT)
@@ -86,16 +103,9 @@
 #define ESR_ELx_SRT_MASK	(UL(0x1F) << ESR_ELx_SRT_SHIFT)
 #define ESR_ELx_SF 		(UL(1) << 15)
 #define ESR_ELx_AR 		(UL(1) << 14)
-#define ESR_ELx_EA 		(UL(1) << 9)
 #define ESR_ELx_CM 		(UL(1) << 8)
-#define ESR_ELx_S1PTW 		(UL(1) << 7)
-#define ESR_ELx_WNR		(UL(1) << 6)
-#define ESR_ELx_FSC		(0x3F)
-#define ESR_ELx_FSC_TYPE	(0x3C)
-#define ESR_ELx_FSC_EXTABT	(0x10)
-#define ESR_ELx_FSC_ACCESS	(0x08)
-#define ESR_ELx_FSC_FAULT	(0x04)
-#define ESR_ELx_FSC_PERM	(0x0C)
+
+/* ISS field definitions for exceptions taken in to Hyp */
 #define ESR_ELx_CV		(UL(1) << 24)
 #define ESR_ELx_COND_SHIFT	(20)
 #define ESR_ELx_COND_MASK	(UL(0xF) << ESR_ELx_COND_SHIFT)
@@ -109,6 +119,62 @@
 	((ESR_ELx_EC_BRK64 << ESR_ELx_EC_SHIFT) | ESR_ELx_IL |	\
 	 ((imm) & 0xffff))
 
+/* ISS field definitions for System instruction traps */
+#define ESR_ELx_SYS64_ISS_RES0_SHIFT	22
+#define ESR_ELx_SYS64_ISS_RES0_MASK	(UL(0x7) << ESR_ELx_SYS64_ISS_RES0_SHIFT)
+#define ESR_ELx_SYS64_ISS_DIR_MASK	0x1
+#define ESR_ELx_SYS64_ISS_DIR_READ	0x1
+#define ESR_ELx_SYS64_ISS_DIR_WRITE	0x0
+
+#define ESR_ELx_SYS64_ISS_RT_SHIFT	5
+#define ESR_ELx_SYS64_ISS_RT_MASK	(UL(0x1f) << ESR_ELx_SYS64_ISS_RT_SHIFT)
+#define ESR_ELx_SYS64_ISS_CRM_SHIFT	1
+#define ESR_ELx_SYS64_ISS_CRM_MASK	(UL(0xf) << ESR_ELx_SYS64_ISS_CRM_SHIFT)
+#define ESR_ELx_SYS64_ISS_CRN_SHIFT	10
+#define ESR_ELx_SYS64_ISS_CRN_MASK	(UL(0xf) << ESR_ELx_SYS64_ISS_CRN_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP1_SHIFT	14
+#define ESR_ELx_SYS64_ISS_OP1_MASK	(UL(0x7) << ESR_ELx_SYS64_ISS_OP1_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP2_SHIFT	17
+#define ESR_ELx_SYS64_ISS_OP2_MASK	(UL(0x7) << ESR_ELx_SYS64_ISS_OP2_SHIFT)
+#define ESR_ELx_SYS64_ISS_OP0_SHIFT	20
+#define ESR_ELx_SYS64_ISS_OP0_MASK	(UL(0x3) << ESR_ELx_SYS64_ISS_OP0_SHIFT)
+#define ESR_ELx_SYS64_ISS_SYS_MASK	(ESR_ELx_SYS64_ISS_OP0_MASK | \
+					 ESR_ELx_SYS64_ISS_OP1_MASK | \
+					 ESR_ELx_SYS64_ISS_OP2_MASK | \
+					 ESR_ELx_SYS64_ISS_CRN_MASK | \
+					 ESR_ELx_SYS64_ISS_CRM_MASK)
+#define ESR_ELx_SYS64_ISS_SYS_VAL(op0, op1, op2, crn, crm) \
+					(((op0) << ESR_ELx_SYS64_ISS_OP0_SHIFT) | \
+					 ((op1) << ESR_ELx_SYS64_ISS_OP1_SHIFT) | \
+					 ((op2) << ESR_ELx_SYS64_ISS_OP2_SHIFT) | \
+					 ((crn) << ESR_ELx_SYS64_ISS_CRN_SHIFT) | \
+					 ((crm) << ESR_ELx_SYS64_ISS_CRM_SHIFT))
+
+#define ESR_ELx_SYS64_ISS_SYS_OP_MASK	(ESR_ELx_SYS64_ISS_SYS_MASK | \
+					 ESR_ELx_SYS64_ISS_DIR_MASK)
+/*
+ * User space cache operations have the following sysreg encoding
+ * in System instructions.
+ * op0=1, op1=3, op2=1, crn=7, crm={ 5, 10, 11, 14 }, WRITE (L=0)
+ */
+#define ESR_ELx_SYS64_ISS_CRM_DC_CIVAC	14
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAU	11
+#define ESR_ELx_SYS64_ISS_CRM_DC_CVAC	10
+#define ESR_ELx_SYS64_ISS_CRM_IC_IVAU	5
+
+#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK	(ESR_ELx_SYS64_ISS_OP0_MASK | \
+						 ESR_ELx_SYS64_ISS_OP1_MASK | \
+						 ESR_ELx_SYS64_ISS_OP2_MASK | \
+						 ESR_ELx_SYS64_ISS_CRN_MASK | \
+						 ESR_ELx_SYS64_ISS_DIR_MASK)
+#define ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL \
+				(ESR_ELx_SYS64_ISS_SYS_VAL(1, 3, 1, 7, 0) | \
+				 ESR_ELx_SYS64_ISS_DIR_WRITE)
+
+#define ESR_ELx_SYS64_ISS_SYS_CTR	ESR_ELx_SYS64_ISS_SYS_VAL(3, 3, 1, 0, 0)
+#define ESR_ELx_SYS64_ISS_SYS_CTR_READ	(ESR_ELx_SYS64_ISS_SYS_CTR | \
+					 ESR_ELx_SYS64_ISS_DIR_READ)
+
 #ifndef __ASSEMBLY__
 #include <asm/types.h>
 

arch/arm64/include/asm/hw_breakpoint.h

@@ -18,6 +18,7 @@
 
 #include <asm/cputype.h>
 #include <asm/cpufeature.h>
+#include <asm/sysreg.h>
 #include <asm/virt.h>
 
 #ifdef __KERNEL__
@@ -98,18 +99,18 @@ static inline void decode_ctrl_reg(u32 reg,
 #define AARCH64_DBG_REG_WCR	(AARCH64_DBG_REG_WVR + ARM_MAX_WRP)
 
 /* Debug register names. */
-#define AARCH64_DBG_REG_NAME_BVR	"bvr"
-#define AARCH64_DBG_REG_NAME_BCR	"bcr"
-#define AARCH64_DBG_REG_NAME_WVR	"wvr"
-#define AARCH64_DBG_REG_NAME_WCR	"wcr"
+#define AARCH64_DBG_REG_NAME_BVR	bvr
+#define AARCH64_DBG_REG_NAME_BCR	bcr
+#define AARCH64_DBG_REG_NAME_WVR	wvr
+#define AARCH64_DBG_REG_NAME_WCR	wcr
 
 /* Accessor macros for the debug registers. */
 #define AARCH64_DBG_READ(N, REG, VAL) do {\
-	asm volatile("mrs %0, dbg" REG #N "_el1" : "=r" (VAL));\
+	VAL = read_sysreg(dbg##REG##N##_el1);\
 } while (0)
 
 #define AARCH64_DBG_WRITE(N, REG, VAL) do {\
-	asm volatile("msr dbg" REG #N "_el1, %0" :: "r" (VAL));\
+	write_sysreg(VAL, dbg##REG##N##_el1);\
 } while (0)
 
 struct task_struct;
@@ -141,8 +142,6 @@ static inline void ptrace_hw_copy_thread(struct task_struct *task)
 }
 #endif
 
-extern struct pmu perf_ops_bp;
-
 /* Determine number of BRP registers available. */
 static inline int get_num_brps(void)
 {

arch/arm64/include/asm/insn.h

@@ -246,7 +246,8 @@ static __always_inline bool aarch64_insn_is_##abbr(u32 code) \
 static __always_inline u32 aarch64_insn_get_##abbr##_value(void) \
 { return (val); }
 
-__AARCH64_INSN_FUNCS(adr_adrp,	0x1F000000, 0x10000000)
+__AARCH64_INSN_FUNCS(adr,	0x9F000000, 0x10000000)
+__AARCH64_INSN_FUNCS(adrp,	0x9F000000, 0x90000000)
 __AARCH64_INSN_FUNCS(prfm_lit,	0xFF000000, 0xD8000000)
 __AARCH64_INSN_FUNCS(str_reg,	0x3FE0EC00, 0x38206800)
 __AARCH64_INSN_FUNCS(ldr_reg,	0x3FE0EC00, 0x38606800)
@@ -318,6 +319,11 @@ __AARCH64_INSN_FUNCS(msr_reg,	0xFFF00000, 0xD5100000)
 bool aarch64_insn_is_nop(u32 insn);
 bool aarch64_insn_is_branch_imm(u32 insn);
 
+static inline bool aarch64_insn_is_adr_adrp(u32 insn)
+{
+	return aarch64_insn_is_adr(insn) || aarch64_insn_is_adrp(insn);
+}
+
 int aarch64_insn_read(void *addr, u32 *insnp);
 int aarch64_insn_write(void *addr, u32 insn);
 enum aarch64_insn_encoding_class aarch64_get_insn_class(u32 insn);
@@ -398,6 +404,9 @@ int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
 int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
 int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
 
+s32 aarch64_insn_adrp_get_offset(u32 insn);
+u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset);
+
 bool aarch32_insn_is_wide(u32 insn);
 
 #define A32_RN_OFFSET	16

arch/arm64/include/asm/io.h

@@ -40,25 +40,25 @@
 #define __raw_writeb __raw_writeb
 static inline void __raw_writeb(u8 val, volatile void __iomem *addr)
 {
-	asm volatile("strb %w0, [%1]" : : "r" (val), "r" (addr));
+	asm volatile("strb %w0, [%1]" : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_writew __raw_writew
 static inline void __raw_writew(u16 val, volatile void __iomem *addr)
 {
-	asm volatile("strh %w0, [%1]" : : "r" (val), "r" (addr));
+	asm volatile("strh %w0, [%1]" : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_writel __raw_writel
 static inline void __raw_writel(u32 val, volatile void __iomem *addr)
 {
-	asm volatile("str %w0, [%1]" : : "r" (val), "r" (addr));
+	asm volatile("str %w0, [%1]" : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_writeq __raw_writeq
 static inline void __raw_writeq(u64 val, volatile void __iomem *addr)
 {
-	asm volatile("str %0, [%1]" : : "r" (val), "r" (addr));
+	asm volatile("str %x0, [%1]" : : "rZ" (val), "r" (addr));
 }
 
 #define __raw_readb __raw_readb
@@ -184,17 +184,6 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 #define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
 #define iowrite64be(v,p)	({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); })
 
-/*
- * Convert a physical pointer to a virtual kernel pointer for /dev/mem
- * access
- */
-#define xlate_dev_mem_ptr(p)	__va(p)
-
-/*
- * Convert a virtual cached pointer to an uncached pointer
- */
-#define xlate_dev_kmem_ptr(p)	p
-
 #include <asm-generic/io.h>
 
 /*

arch/arm64/include/asm/kvm_mmu.h

@@ -99,14 +99,10 @@
 .macro kern_hyp_va	reg
 alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	and     \reg, \reg, #HYP_PAGE_OFFSET_HIGH_MASK
-alternative_else
-	nop
-alternative_endif
-alternative_if_not ARM64_HYP_OFFSET_LOW
-	nop
-alternative_else
+alternative_else_nop_endif
+alternative_if ARM64_HYP_OFFSET_LOW
 	and     \reg, \reg, #HYP_PAGE_OFFSET_LOW_MASK
-alternative_endif
+alternative_else_nop_endif
 .endm
 
 #else

arch/arm64/include/asm/memory.h

@@ -214,7 +214,7 @@ static inline void *phys_to_virt(phys_addr_t x)
 
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
 #define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
-#define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
+#define _virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #else
 #define __virt_to_pgoff(kaddr)	(((u64)(kaddr) & ~PAGE_OFFSET) / PAGE_SIZE * sizeof(struct page))
 #define __page_to_voff(kaddr)	(((u64)(page) & ~VMEMMAP_START) * PAGE_SIZE / sizeof(struct page))
@@ -222,11 +222,15 @@ static inline void *phys_to_virt(phys_addr_t x)
 #define page_to_virt(page)	((void *)((__page_to_voff(page)) | PAGE_OFFSET))
 #define virt_to_page(vaddr)	((struct page *)((__virt_to_pgoff(vaddr)) | VMEMMAP_START))
 
-#define virt_addr_valid(kaddr)	pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \
+#define _virt_addr_valid(kaddr)	pfn_valid((((u64)(kaddr) & ~PAGE_OFFSET) \
 					   + PHYS_OFFSET) >> PAGE_SHIFT)
 #endif
 #endif
 
+#define _virt_addr_is_linear(kaddr)	(((u64)(kaddr)) >= PAGE_OFFSET)
+#define virt_addr_valid(kaddr)		(_virt_addr_is_linear(kaddr) && \
+					 _virt_addr_valid(kaddr))
+
 #include <asm-generic/memory_model.h>
 
 #endif

arch/arm64/include/asm/mmu_context.h

@@ -27,22 +27,17 @@
 #include <asm-generic/mm_hooks.h>
 #include <asm/cputype.h>
 #include <asm/pgtable.h>
+#include <asm/sysreg.h>
 #include <asm/tlbflush.h>
 
-#ifdef CONFIG_PID_IN_CONTEXTIDR
-static inline void contextidr_thread_switch(struct task_struct *next)
-{
-	asm(
-	"	msr	contextidr_el1, %0\n"
-	"	isb"
-	:
-	: "r" (task_pid_nr(next)));
-}
-#else
 static inline void contextidr_thread_switch(struct task_struct *next)
 {
+	if (!IS_ENABLED(CONFIG_PID_IN_CONTEXTIDR))
+		return;
+
+	write_sysreg(task_pid_nr(next), contextidr_el1);
+	isb();
 }
-#endif
 
 /*
  * Set TTBR0 to empty_zero_page. No translations will be possible via TTBR0.
@@ -51,11 +46,8 @@ static inline void cpu_set_reserved_ttbr0(void)
 {
 	unsigned long ttbr = virt_to_phys(empty_zero_page);
 
-	asm(
-	"	msr	ttbr0_el1, %0			// set TTBR0\n"
-	"	isb"
-	:
-	: "r" (ttbr));
+	write_sysreg(ttbr, ttbr0_el1);
+	isb();
 }
 
 /*
@@ -81,13 +73,11 @@ static inline void __cpu_set_tcr_t0sz(unsigned long t0sz)
 	if (!__cpu_uses_extended_idmap())
 		return;
 
-	asm volatile (
-	"	mrs	%0, tcr_el1	;"
-	"	bfi	%0, %1, %2, %3	;"
-	"	msr	tcr_el1, %0	;"
-	"	isb"
-	: "=&r" (tcr)
-	: "r"(t0sz), "I"(TCR_T0SZ_OFFSET), "I"(TCR_TxSZ_WIDTH));
+	tcr = read_sysreg(tcr_el1);
+	tcr &= ~TCR_T0SZ_MASK;
+	tcr |= t0sz << TCR_T0SZ_OFFSET;
+	write_sysreg(tcr, tcr_el1);
+	isb();
 }
 
 #define cpu_set_default_tcr_t0sz()	__cpu_set_tcr_t0sz(TCR_T0SZ(VA_BITS))

arch/arm64/include/asm/pgtable-hwdef.h

@@ -208,6 +208,7 @@
 #define TCR_T1SZ(x)		((UL(64) - (x)) << TCR_T1SZ_OFFSET)
 #define TCR_TxSZ(x)		(TCR_T0SZ(x) | TCR_T1SZ(x))
 #define TCR_TxSZ_WIDTH		6
+#define TCR_T0SZ_MASK		(((UL(1) << TCR_TxSZ_WIDTH) - 1) << TCR_T0SZ_OFFSET)
 
 #define TCR_IRGN0_SHIFT		8
 #define TCR_IRGN0_MASK		(UL(3) << TCR_IRGN0_SHIFT)

arch/arm64/include/asm/pgtable-prot.h

@@ -70,12 +70,13 @@
 #define PAGE_COPY_EXEC		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
 #define PAGE_READONLY		__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN | PTE_UXN)
 #define PAGE_READONLY_EXEC	__pgprot(_PAGE_DEFAULT | PTE_USER | PTE_NG | PTE_PXN)
+#define PAGE_EXECONLY		__pgprot(_PAGE_DEFAULT | PTE_NG | PTE_PXN)
 
 #define __P000  PAGE_NONE
 #define __P001  PAGE_READONLY
 #define __P010  PAGE_COPY
 #define __P011  PAGE_COPY
-#define __P100  PAGE_READONLY_EXEC
+#define __P100  PAGE_EXECONLY
 #define __P101  PAGE_READONLY_EXEC
 #define __P110  PAGE_COPY_EXEC
 #define __P111  PAGE_COPY_EXEC
@@ -84,7 +85,7 @@
 #define __S001  PAGE_READONLY
 #define __S010  PAGE_SHARED
 #define __S011  PAGE_SHARED
-#define __S100  PAGE_READONLY_EXEC
+#define __S100  PAGE_EXECONLY
 #define __S101  PAGE_READONLY_EXEC
 #define __S110  PAGE_SHARED_EXEC
 #define __S111  PAGE_SHARED_EXEC

arch/arm64/include/asm/pgtable.h

@@ -73,7 +73,7 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_write(pte)		(!!(pte_val(pte) & PTE_WRITE))
 #define pte_exec(pte)		(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
-#define pte_user(pte)		(!!(pte_val(pte) & PTE_USER))
+#define pte_ng(pte)		(!!(pte_val(pte) & PTE_NG))
 
 #ifdef CONFIG_ARM64_HW_AFDBM
 #define pte_hw_dirty(pte)	(pte_write(pte) && !(pte_val(pte) & PTE_RDONLY))
@@ -84,8 +84,8 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
 #define pte_dirty(pte)		(pte_sw_dirty(pte) || pte_hw_dirty(pte))
 
 #define pte_valid(pte)		(!!(pte_val(pte) & PTE_VALID))
-#define pte_valid_not_user(pte) \
-	((pte_val(pte) & (PTE_VALID | PTE_USER)) == PTE_VALID)
+#define pte_valid_global(pte) \
+	((pte_val(pte) & (PTE_VALID | PTE_NG)) == PTE_VALID)
 #define pte_valid_young(pte) \
 	((pte_val(pte) & (PTE_VALID | PTE_AF)) == (PTE_VALID | PTE_AF))
 
@@ -155,6 +155,16 @@ static inline pte_t pte_mknoncont(pte_t pte)
 	return clear_pte_bit(pte, __pgprot(PTE_CONT));
 }
 
+static inline pte_t pte_clear_rdonly(pte_t pte)
+{
+	return clear_pte_bit(pte, __pgprot(PTE_RDONLY));
+}
+
+static inline pte_t pte_mkpresent(pte_t pte)
+{
+	return set_pte_bit(pte, __pgprot(PTE_VALID));
+}
+
 static inline pmd_t pmd_mkcont(pmd_t pmd)
 {
 	return __pmd(pmd_val(pmd) | PMD_SECT_CONT);
@@ -168,7 +178,7 @@ static inline void set_pte(pte_t *ptep, pte_t pte)
 	 * Only if the new pte is valid and kernel, otherwise TLB maintenance
 	 * or update_mmu_cache() have the necessary barriers.
 	 */
-	if (pte_valid_not_user(pte)) {
+	if (pte_valid_global(pte)) {
 		dsb(ishst);
 		isb();
 	}
@@ -202,7 +212,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 			pte_val(pte) &= ~PTE_RDONLY;
 		else
 			pte_val(pte) |= PTE_RDONLY;
-		if (pte_user(pte) && pte_exec(pte) && !pte_special(pte))
+		if (pte_ng(pte) && pte_exec(pte) && !pte_special(pte))
 			__sync_icache_dcache(pte, addr);
 	}
 

arch/arm64/include/asm/processor.h

@@ -37,7 +37,6 @@
 #include <asm/ptrace.h>
 #include <asm/types.h>
 
-#ifdef __KERNEL__
 #define STACK_TOP_MAX		TASK_SIZE_64
 #ifdef CONFIG_COMPAT
 #define AARCH32_VECTORS_BASE	0xffff0000
@@ -49,7 +48,6 @@
 
 extern phys_addr_t arm64_dma_phys_limit;
 #define ARCH_LOW_ADDRESS_LIMIT	(arm64_dma_phys_limit - 1)
-#endif /* __KERNEL__ */
 
 struct debug_info {
 	/* Have we suspended stepping by a debugger? */

arch/arm64/include/asm/sections.h

@@ -0,0 +1,30 @@
+/*
+ * Copyright (C) 2016 ARM Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef __ASM_SECTIONS_H
+#define __ASM_SECTIONS_H
+
+#include <asm-generic/sections.h>
+
+extern char __alt_instructions[], __alt_instructions_end[];
+extern char __exception_text_start[], __exception_text_end[];
+extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
+extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
+extern char __hyp_text_start[], __hyp_text_end[];
+extern char __idmap_text_start[], __idmap_text_end[];
+extern char __irqentry_text_start[], __irqentry_text_end[];
+extern char __mmuoff_data_start[], __mmuoff_data_end[];
+
+#endif /* __ASM_SECTIONS_H */

arch/arm64/include/asm/spinlock.h

@@ -66,8 +66,7 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
 	ARM64_LSE_ATOMIC_INSN(
 	/* LL/SC */
 "	stxr	%w1, %w0, %2\n"
-"	nop\n"
-"	nop\n",
+	__nops(2),
 	/* LSE atomics */
 "	mov	%w1, %w0\n"
 "	cas	%w0, %w0, %2\n"
@@ -99,9 +98,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	/* LSE atomics */
 "	mov	%w2, %w5\n"
 "	ldadda	%w2, %w0, %3\n"
-"	nop\n"
-"	nop\n"
-"	nop\n"
+	__nops(3)
 	)
 
 	/* Did we get the lock? */
@@ -165,8 +162,8 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	"	stlrh	%w1, %0",
 	/* LSE atomics */
 	"	mov	%w1, #1\n"
-	"	nop\n"
-	"	staddlh	%w1, %0")
+	"	staddlh	%w1, %0\n"
+	__nops(1))
 	: "=Q" (lock->owner), "=&r" (tmp)
 	:
 	: "memory");
@@ -212,7 +209,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 	"	cbnz	%w0, 1b\n"
 	"	stxr	%w0, %w2, %1\n"
 	"	cbnz	%w0, 2b\n"
-	"	nop",
+	__nops(1),
 	/* LSE atomics */
 	"1:	mov	%w0, wzr\n"
 	"2:	casa	%w0, %w2, %1\n"
@@ -241,8 +238,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 	/* LSE atomics */
 	"	mov	%w0, wzr\n"
 	"	casa	%w0, %w2, %1\n"
-	"	nop\n"
-	"	nop")
+	__nops(2))
 	: "=&r" (tmp), "+Q" (rw->lock)
 	: "r" (0x80000000)
 	: "memory");
@@ -290,8 +286,8 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 	"	add	%w0, %w0, #1\n"
 	"	tbnz	%w0, #31, 1b\n"
 	"	stxr	%w1, %w0, %2\n"
-	"	nop\n"
-	"	cbnz	%w1, 2b",
+	"	cbnz	%w1, 2b\n"
+	__nops(1),
 	/* LSE atomics */
 	"1:	wfe\n"
 	"2:	ldxr	%w0, %2\n"
@@ -317,9 +313,8 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 	"	cbnz	%w1, 1b",
 	/* LSE atomics */
 	"	movn	%w0, #0\n"
-	"	nop\n"
-	"	nop\n"
-	"	staddl	%w0, %2")
+	"	staddl	%w0, %2\n"
+	__nops(2))
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:
 	: "memory");
@@ -344,7 +339,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 	"	tbnz	%w1, #31, 1f\n"
 	"	casa	%w0, %w1, %2\n"
 	"	sbc	%w1, %w1, %w0\n"
-	"	nop\n"
+	__nops(1)
 	"1:")
 	: "=&r" (tmp), "=&r" (tmp2), "+Q" (rw->lock)
 	:

arch/arm64/include/asm/suspend.h

@@ -47,4 +47,7 @@ int swsusp_arch_resume(void);
 int arch_hibernation_header_save(void *addr, unsigned int max_size);
 int arch_hibernation_header_restore(void *addr);
 
+/* Used to resume on the CPU we hibernated on */
+int hibernate_resume_nonboot_cpu_disable(void);
+
 #endif

arch/arm64/include/asm/sysreg.h

@@ -100,6 +100,7 @@
 /* SCTLR_EL1 specific flags. */
 #define SCTLR_EL1_UCI		(1 << 26)
 #define SCTLR_EL1_SPAN		(1 << 23)
+#define SCTLR_EL1_UCT		(1 << 15)
 #define SCTLR_EL1_SED		(1 << 8)
 #define SCTLR_EL1_CP15BEN	(1 << 5)
 
@@ -253,16 +254,6 @@ asm(
 "	.endm\n"
 );
 
-static inline void config_sctlr_el1(u32 clear, u32 set)
-{
-	u32 val;
-
-	asm volatile("mrs %0, sctlr_el1" : "=r" (val));
-	val &= ~clear;
-	val |= set;
-	asm volatile("msr sctlr_el1, %0" : : "r" (val));
-}
-
 /*
  * Unlike read_cpuid, calls to read_sysreg are never expected to be
  * optimized away or replaced with synthetic values.
@@ -273,12 +264,41 @@ static inline void config_sctlr_el1(u32 clear, u32 set)
 	__val;							\
 })
 
+/*
+ * The "Z" constraint normally means a zero immediate, but when combined with
+ * the "%x0" template means XZR.
+ */
 #define write_sysreg(v, r) do {					\
 	u64 __val = (u64)v;					\
-	asm volatile("msr " __stringify(r) ", %0"		\
-		     : : "r" (__val));				\
+	asm volatile("msr " __stringify(r) ", %x0"		\
+		     : : "rZ" (__val));				\
+} while (0)
+
+/*
+ * For registers without architectural names, or simply unsupported by
+ * GAS.
+ */
+#define read_sysreg_s(r) ({						\
+	u64 __val;							\
+	asm volatile("mrs_s %0, " __stringify(r) : "=r" (__val));	\
+	__val;								\
+})
+
+#define write_sysreg_s(v, r) do {					\
+	u64 __val = (u64)v;						\
+	asm volatile("msr_s " __stringify(r) ", %0" : : "rZ" (__val));	\
 } while (0)
 
+static inline void config_sctlr_el1(u32 clear, u32 set)
+{
+	u32 val;
+
+	val = read_sysreg(sctlr_el1);
+	val &= ~clear;
+	val |= set;
+	write_sysreg(val, sctlr_el1);
+}
+
 #endif
 
 #endif	/* __ASM_SYSREG_H */

arch/arm64/include/asm/system_misc.h

@@ -56,12 +56,6 @@ extern void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
 	__show_ratelimited;						\
 })
 
-#define UDBG_UNDEFINED	(1 << 0)
-#define UDBG_SYSCALL	(1 << 1)
-#define UDBG_BADABORT	(1 << 2)
-#define UDBG_SEGV	(1 << 3)
-#define UDBG_BUS	(1 << 4)
-
 #endif	/* __ASSEMBLY__ */
 
 #endif	/* __ASM_SYSTEM_MISC_H */

arch/arm64/include/asm/thread_info.h

@@ -75,6 +75,9 @@ static inline struct thread_info *current_thread_info(void) __attribute_const__;
 
 /*
  * struct thread_info can be accessed directly via sp_el0.
+ *
+ * We don't use read_sysreg() as we want the compiler to cache the value where
+ * possible.
  */
 static inline struct thread_info *current_thread_info(void)
 {

arch/arm64/include/asm/tlbflush.h

@@ -24,6 +24,24 @@
 #include <linux/sched.h>
 #include <asm/cputype.h>
 
+/*
+ * Raw TLBI operations.
+ *
+ * Where necessary, use the __tlbi() macro to avoid asm()
+ * boilerplate. Drivers and most kernel code should use the TLB
+ * management routines in preference to the macro below.
+ *
+ * The macro can be used as __tlbi(op) or __tlbi(op, arg), depending
+ * on whether a particular TLBI operation takes an argument or
+ * not. The macros handles invoking the asm with or without the
+ * register argument as appropriate.
+ */
+#define __TLBI_0(op, arg)		asm ("tlbi " #op)
+#define __TLBI_1(op, arg)		asm ("tlbi " #op ", %0" : : "r" (arg))
+#define __TLBI_N(op, arg, n, ...)	__TLBI_##n(op, arg)
+
+#define __tlbi(op, ...)		__TLBI_N(op, ##__VA_ARGS__, 1, 0)
+
 /*
  *	TLB Management
  *	==============
@@ -66,7 +84,7 @@
 static inline void local_flush_tlb_all(void)
 {
 	dsb(nshst);
-	asm("tlbi	vmalle1");
+	__tlbi(vmalle1);
 	dsb(nsh);
 	isb();
 }
@@ -74,7 +92,7 @@ static inline void local_flush_tlb_all(void)
 static inline void flush_tlb_all(void)
 {
 	dsb(ishst);
-	asm("tlbi	vmalle1is");
+	__tlbi(vmalle1is);
 	dsb(ish);
 	isb();
 }
@@ -84,7 +102,7 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
 	unsigned long asid = ASID(mm) << 48;
 
 	dsb(ishst);
-	asm("tlbi	aside1is, %0" : : "r" (asid));
+	__tlbi(aside1is, asid);
 	dsb(ish);
 }
 
@@ -94,7 +112,7 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
 	unsigned long addr = uaddr >> 12 | (ASID(vma->vm_mm) << 48);
 
 	dsb(ishst);
-	asm("tlbi	vale1is, %0" : : "r" (addr));
+	__tlbi(vale1is, addr);
 	dsb(ish);
 }
 
@@ -122,9 +140,9 @@ static inline void __flush_tlb_range(struct vm_area_struct *vma,
 	dsb(ishst);
 	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12)) {
 		if (last_level)
-			asm("tlbi vale1is, %0" : : "r"(addr));
+			__tlbi(vale1is, addr);
 		else
-			asm("tlbi vae1is, %0" : : "r"(addr));
+			__tlbi(vae1is, addr);
 	}
 	dsb(ish);
 }
@@ -149,7 +167,7 @@ static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end
 
 	dsb(ishst);
 	for (addr = start; addr < end; addr += 1 << (PAGE_SHIFT - 12))
-		asm("tlbi vaae1is, %0" : : "r"(addr));
+		__tlbi(vaae1is, addr);
 	dsb(ish);
 	isb();
 }
@@ -163,7 +181,7 @@ static inline void __flush_tlb_pgtable(struct mm_struct *mm,
 {
 	unsigned long addr = uaddr >> 12 | (ASID(mm) << 48);
 
-	asm("tlbi	vae1is, %0" : : "r" (addr));
+	__tlbi(vae1is, addr);
 	dsb(ish);
 }
 

arch/arm64/include/asm/traps.h

@@ -19,6 +19,7 @@
 #define __ASM_TRAP_H
 
 #include <linux/list.h>
+#include <asm/sections.h>
 
 struct pt_regs;
 
@@ -39,9 +40,6 @@ void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 static inline int __in_irqentry_text(unsigned long ptr)
 {
-	extern char __irqentry_text_start[];
-	extern char __irqentry_text_end[];
-
 	return ptr >= (unsigned long)&__irqentry_text_start &&
 	       ptr < (unsigned long)&__irqentry_text_end;
 }
@@ -54,8 +52,6 @@ static inline int __in_irqentry_text(unsigned long ptr)
 
 static inline int in_exception_text(unsigned long ptr)
 {
-	extern char __exception_text_start[];
-	extern char __exception_text_end[];
 	int in;
 
 	in = ptr >= (unsigned long)&__exception_text_start &&

arch/arm64/include/asm/virt.h

@@ -45,6 +45,8 @@
 #ifndef __ASSEMBLY__
 
 #include <asm/ptrace.h>
+#include <asm/sections.h>
+#include <asm/sysreg.h>
 
 /*
  * __boot_cpu_mode records what mode CPUs were booted in.
@@ -75,10 +77,7 @@ static inline bool is_hyp_mode_mismatched(void)
 
 static inline bool is_kernel_in_hyp_mode(void)
 {
-	u64 el;
-
-	asm("mrs %0, CurrentEL" : "=r" (el));
-	return el == CurrentEL_EL2;
+	return read_sysreg(CurrentEL) == CurrentEL_EL2;
 }
 
 #ifdef CONFIG_ARM64_VHE
@@ -87,14 +86,6 @@ extern void verify_cpu_run_el(void);
 static inline void verify_cpu_run_el(void) {}
 #endif
 
-/* The section containing the hypervisor idmap text */
-extern char __hyp_idmap_text_start[];
-extern char __hyp_idmap_text_end[];
-
-/* The section containing the hypervisor text */
-extern char __hyp_text_start[];
-extern char __hyp_text_end[];
-
 #endif /* __ASSEMBLY__ */
 
 #endif /* ! __ASM__VIRT_H */

arch/arm64/kernel/Makefile

@@ -10,6 +10,8 @@ CFLAGS_REMOVE_ftrace.o = -pg
 CFLAGS_REMOVE_insn.o = -pg
 CFLAGS_REMOVE_return_address.o = -pg
 
+CFLAGS_setup.o = -DUTS_MACHINE='"$(UTS_MACHINE)"'
+
 # Object file lists.
 arm64-obj-y		:= debug-monitors.o entry.o irq.o fpsimd.o		\
 			   entry-fpsimd.o process.o ptrace.o setup.o signal.o	\

arch/arm64/kernel/acpi_numa.c

@@ -105,8 +105,10 @@ int __init arm64_acpi_numa_init(void)
 	int ret;
 
 	ret = acpi_numa_init();
-	if (ret)
+	if (ret) {
+		pr_info("Failed to initialise from firmware\n");
 		return ret;
+	}
 
 	return srat_disabled() ? -EINVAL : 0;
 }

arch/arm64/kernel/alternative.c

@@ -25,14 +25,13 @@
 #include <asm/alternative.h>
 #include <asm/cpufeature.h>
 #include <asm/insn.h>
+#include <asm/sections.h>
 #include <linux/stop_machine.h>
 
 #define __ALT_PTR(a,f)		(u32 *)((void *)&(a)->f + (a)->f)
 #define ALT_ORIG_PTR(a)		__ALT_PTR(a, orig_offset)
 #define ALT_REPL_PTR(a)		__ALT_PTR(a, alt_offset)
 
-extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
-
 struct alt_region {
 	struct alt_instr *begin;
 	struct alt_instr *end;
@@ -59,6 +58,8 @@ static bool branch_insn_requires_update(struct alt_instr *alt, unsigned long pc)
 	BUG();
 }
 
+#define align_down(x, a)	((unsigned long)(x) & ~(((unsigned long)(a)) - 1))
+
 static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
 {
 	u32 insn;
@@ -80,6 +81,25 @@ static u32 get_alt_insn(struct alt_instr *alt, u32 *insnptr, u32 *altinsnptr)
 			offset = target - (unsigned long)insnptr;
 			insn = aarch64_set_branch_offset(insn, offset);
 		}
+	} else if (aarch64_insn_is_adrp(insn)) {
+		s32 orig_offset, new_offset;
+		unsigned long target;
+
+		/*
+		 * If we're replacing an adrp instruction, which uses PC-relative
+		 * immediate addressing, adjust the offset to reflect the new
+		 * PC. adrp operates on 4K aligned addresses.
+		 */
+		orig_offset  = aarch64_insn_adrp_get_offset(insn);
+		target = align_down(altinsnptr, SZ_4K) + orig_offset;
+		new_offset = target - align_down(insnptr, SZ_4K);
+		insn = aarch64_insn_adrp_set_offset(insn, new_offset);
+	} else if (aarch64_insn_uses_literal(insn)) {
+		/*
+		 * Disallow patching unhandled instructions using PC relative
+		 * literal addresses
+		 */
+		BUG();
 	}
 
 	return insn;
@@ -124,8 +144,8 @@ static int __apply_alternatives_multi_stop(void *unused)
 {
 	static int patched = 0;
 	struct alt_region region = {
-		.begin	= __alt_instructions,
-		.end	= __alt_instructions_end,
+		.begin	= (struct alt_instr *)__alt_instructions,
+		.end	= (struct alt_instr *)__alt_instructions_end,
 	};
 
 	/* We always have a CPU 0 at this point (__init) */

arch/arm64/kernel/asm-offsets.c

@@ -23,6 +23,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/kvm_host.h>
 #include <linux/suspend.h>
+#include <asm/cpufeature.h>
 #include <asm/thread_info.h>
 #include <asm/memory.h>
 #include <asm/smp_plat.h>
@@ -145,5 +146,6 @@ int main(void)
   DEFINE(HIBERN_PBE_ORIG,	offsetof(struct pbe, orig_address));
   DEFINE(HIBERN_PBE_ADDR,	offsetof(struct pbe, address));
   DEFINE(HIBERN_PBE_NEXT,	offsetof(struct pbe, next));
+  DEFINE(ARM64_FTR_SYSVAL,	offsetof(struct arm64_ftr_reg, sys_val));
   return 0;
 }

arch/arm64/kernel/cacheinfo.c

@@ -39,7 +39,7 @@ static inline enum cache_type get_cache_type(int level)
 
 	if (level > MAX_CACHE_LEVEL)
 		return CACHE_TYPE_NOCACHE;
-	asm volatile ("mrs     %x0, clidr_el1" : "=r" (clidr));
+	clidr = read_sysreg(clidr_el1);
 	return CLIDR_CTYPE(clidr, level);
 }
 
@@ -55,11 +55,9 @@ u64 __attribute_const__ cache_get_ccsidr(u64 csselr)
 
 	WARN_ON(preemptible());
 
-	/* Put value into CSSELR */
-	asm volatile("msr csselr_el1, %x0" : : "r" (csselr));
+	write_sysreg(csselr, csselr_el1);
 	isb();
-	/* Read result out of CCSIDR */
-	asm volatile("mrs %x0, ccsidr_el1" : "=r" (ccsidr));
+	ccsidr = read_sysreg(ccsidr_el1);
 
 	return ccsidr;
 }

arch/arm64/kernel/cpu_errata.c

@@ -30,6 +30,21 @@ is_affected_midr_range(const struct arm64_cpu_capabilities *entry, int scope)
 				       entry->midr_range_max);
 }
 
+static bool
+has_mismatched_cache_line_size(const struct arm64_cpu_capabilities *entry,
+				int scope)
+{
+	WARN_ON(scope != SCOPE_LOCAL_CPU || preemptible());
+	return (read_cpuid_cachetype() & arm64_ftr_reg_ctrel0.strict_mask) !=
+		(arm64_ftr_reg_ctrel0.sys_val & arm64_ftr_reg_ctrel0.strict_mask);
+}
+
+static void cpu_enable_trap_ctr_access(void *__unused)
+{
+	/* Clear SCTLR_EL1.UCT */
+	config_sctlr_el1(SCTLR_EL1_UCT, 0);
+}
+
 #define MIDR_RANGE(model, min, max) \
 	.def_scope = SCOPE_LOCAL_CPU, \
 	.matches = is_affected_midr_range, \
@@ -107,6 +122,13 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
 		MIDR_RANGE(MIDR_THUNDERX_81XX, 0x00, 0x00),
 	},
 #endif
+	{
+		.desc = "Mismatched cache line size",
+		.capability = ARM64_MISMATCHED_CACHE_LINE_SIZE,
+		.matches = has_mismatched_cache_line_size,
+		.def_scope = SCOPE_LOCAL_CPU,
+		.enable = cpu_enable_trap_ctr_access,
+	},
 	{
 	}
 };
@@ -116,7 +138,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
  * and the related information is freed soon after. If the new CPU requires
  * an errata not detected at boot, fail this CPU.
  */
-void verify_local_cpu_errata(void)
+void verify_local_cpu_errata_workarounds(void)
 {
 	const struct arm64_cpu_capabilities *caps = arm64_errata;
 
@@ -131,7 +153,7 @@ void verify_local_cpu_errata(void)
 		}
 }
 
-void check_local_cpu_errata(void)
+void update_cpu_errata_workarounds(void)
 {
 	update_cpu_capabilities(arm64_errata, "enabling workaround for");
 }

arch/arm64/kernel/cpu_ops.c

@@ -17,6 +17,7 @@
  */
 
 #include <linux/acpi.h>
+#include <linux/cache.h>
 #include <linux/errno.h>
 #include <linux/of.h>
 #include <linux/string.h>
@@ -28,7 +29,7 @@ extern const struct cpu_operations smp_spin_table_ops;
 extern const struct cpu_operations acpi_parking_protocol_ops;
 extern const struct cpu_operations cpu_psci_ops;
 
-const struct cpu_operations *cpu_ops[NR_CPUS];
+const struct cpu_operations *cpu_ops[NR_CPUS] __ro_after_init;
 
 static const struct cpu_operations *dt_supported_cpu_ops[] __initconst = {
 	&smp_spin_table_ops,

arch/arm64/kernel/cpufeature.c

@@ -46,6 +46,9 @@ unsigned int compat_elf_hwcap2 __read_mostly;
 
 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
 
+DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS);
+EXPORT_SYMBOL(cpu_hwcap_keys);
+
 #define __ARM64_FTR_BITS(SIGNED, STRICT, TYPE, SHIFT, WIDTH, SAFE_VAL) \
 	{						\
 		.sign = SIGNED,				\
@@ -74,7 +77,7 @@ static bool __maybe_unused
 cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused);
 
 
-static struct arm64_ftr_bits ftr_id_aa64isar0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64isar0[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64ISAR0_RDM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0),
@@ -87,7 +90,7 @@ static struct arm64_ftr_bits ftr_id_aa64isar0[] = {
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64PFR0_GIC_SHIFT, 4, 0),
@@ -101,7 +104,7 @@ static struct arm64_ftr_bits ftr_id_aa64pfr0[] = {
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
 	S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN4_SHIFT, 4, ID_AA64MMFR0_TGRAN4_NI),
 	S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR0_TGRAN64_SHIFT, 4, ID_AA64MMFR0_TGRAN64_NI),
@@ -119,7 +122,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr0[] = {
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
+static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR1_PAN_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR1_LOR_SHIFT, 4, 0),
@@ -130,7 +133,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr1[] = {
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
+static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LVA_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_IESB_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_AA64MMFR2_LSM_SHIFT, 4, 0),
@@ -139,7 +142,7 @@ static struct arm64_ftr_bits ftr_id_aa64mmfr2[] = {
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_ctr[] = {
+static const struct arm64_ftr_bits ftr_ctr[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 31, 1, 1),	/* RAO */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 3, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_HIGHER_SAFE, 24, 4, 0),	/* CWG */
@@ -147,15 +150,21 @@ static struct arm64_ftr_bits ftr_ctr[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 16, 4, 1),	/* DminLine */
 	/*
 	 * Linux can handle differing I-cache policies. Userspace JITs will
-	 * make use of *minLine
+	 * make use of *minLine.
+	 * If we have differing I-cache policies, report it as the weakest - AIVIVT.
 	 */
-	ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, 0),	/* L1Ip */
+	ARM64_FTR_BITS(FTR_NONSTRICT, FTR_EXACT, 14, 2, ICACHE_POLICY_AIVIVT),	/* L1Ip */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 10, 0),	/* RAZ */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* IminLine */
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_id_mmfr0[] = {
+struct arm64_ftr_reg arm64_ftr_reg_ctrel0 = {
+	.name		= "SYS_CTR_EL0",
+	.ftr_bits	= ftr_ctr
+};
+
+static const struct arm64_ftr_bits ftr_id_mmfr0[] = {
 	S_ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 28, 4, 0xf),	/* InnerShr */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 24, 4, 0),	/* FCSE */
 	ARM64_FTR_BITS(FTR_NONSTRICT, FTR_LOWER_SAFE, 20, 4, 0),	/* AuxReg */
@@ -167,7 +176,7 @@ static struct arm64_ftr_bits ftr_id_mmfr0[] = {
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
+static const struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 32, 32, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_CTX_CMPS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, ID_AA64DFR0_WRPS_SHIFT, 4, 0),
@@ -178,14 +187,14 @@ static struct arm64_ftr_bits ftr_id_aa64dfr0[] = {
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_mvfr2[] = {
+static const struct arm64_ftr_bits ftr_mvfr2[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0),	/* RAZ */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0),		/* FPMisc */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0),		/* SIMDMisc */
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_dczid[] = {
+static const struct arm64_ftr_bits ftr_dczid[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 5, 27, 0),	/* RAZ */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 1, 1),		/* DZP */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 0, 4, 0),	/* BS */
@@ -193,7 +202,7 @@ static struct arm64_ftr_bits ftr_dczid[] = {
 };
 
 
-static struct arm64_ftr_bits ftr_id_isar5[] = {
+static const struct arm64_ftr_bits ftr_id_isar5[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_RDM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 20, 4, 0),	/* RAZ */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, ID_ISAR5_CRC32_SHIFT, 4, 0),
@@ -204,14 +213,14 @@ static struct arm64_ftr_bits ftr_id_isar5[] = {
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_id_mmfr4[] = {
+static const struct arm64_ftr_bits ftr_id_mmfr4[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 24, 0),	/* RAZ */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 4, 4, 0),		/* ac2 */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 4, 0),		/* RAZ */
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_id_pfr0[] = {
+static const struct arm64_ftr_bits ftr_id_pfr0[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 16, 16, 0),	/* RAZ */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 12, 4, 0),	/* State3 */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 8, 4, 0),		/* State2 */
@@ -220,7 +229,7 @@ static struct arm64_ftr_bits ftr_id_pfr0[] = {
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_id_dfr0[] = {
+static const struct arm64_ftr_bits ftr_id_dfr0[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
 	S_ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0xf),	/* PerfMon */
 	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
@@ -238,7 +247,7 @@ static struct arm64_ftr_bits ftr_id_dfr0[] = {
  * 0. Covers the following 32bit registers:
  * id_isar[0-4], id_mmfr[1-3], id_pfr1, mvfr[0-1]
  */
-static struct arm64_ftr_bits ftr_generic_32bits[] = {
+static const struct arm64_ftr_bits ftr_generic_32bits[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 28, 4, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 24, 4, 0),
 	ARM64_FTR_BITS(FTR_STRICT, FTR_LOWER_SAFE, 20, 4, 0),
@@ -250,29 +259,32 @@ static struct arm64_ftr_bits ftr_generic_32bits[] = {
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_generic[] = {
+static const struct arm64_ftr_bits ftr_generic[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0),
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_generic32[] = {
+static const struct arm64_ftr_bits ftr_generic32[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 32, 0),
 	ARM64_FTR_END,
 };
 
-static struct arm64_ftr_bits ftr_aa64raz[] = {
+static const struct arm64_ftr_bits ftr_aa64raz[] = {
 	ARM64_FTR_BITS(FTR_STRICT, FTR_EXACT, 0, 64, 0),
 	ARM64_FTR_END,
 };
 
-#define ARM64_FTR_REG(id, table)		\
-	{					\
-		.sys_id = id,			\
+#define ARM64_FTR_REG(id, table) {		\
+	.sys_id = id,				\
+	.reg = 	&(struct arm64_ftr_reg){	\
 		.name = #id,			\
 		.ftr_bits = &((table)[0]),	\
-	}
+	}}
 
-static struct arm64_ftr_reg arm64_ftr_regs[] = {
+static const struct __ftr_reg_entry {
+	u32			sys_id;
+	struct arm64_ftr_reg 	*reg;
+} arm64_ftr_regs[] = {
 
 	/* Op1 = 0, CRn = 0, CRm = 1 */
 	ARM64_FTR_REG(SYS_ID_PFR0_EL1, ftr_id_pfr0),
@@ -315,7 +327,7 @@ static struct arm64_ftr_reg arm64_ftr_regs[] = {
 	ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2),
 
 	/* Op1 = 3, CRn = 0, CRm = 0 */
-	ARM64_FTR_REG(SYS_CTR_EL0, ftr_ctr),
+	{ SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 },
 	ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid),
 
 	/* Op1 = 3, CRn = 14, CRm = 0 */
@@ -324,7 +336,7 @@ static struct arm64_ftr_reg arm64_ftr_regs[] = {
 
 static int search_cmp_ftr_reg(const void *id, const void *regp)
 {
-	return (int)(unsigned long)id - (int)((const struct arm64_ftr_reg *)regp)->sys_id;
+	return (int)(unsigned long)id - (int)((const struct __ftr_reg_entry *)regp)->sys_id;
 }
 
 /*
@@ -339,14 +351,20 @@ static int search_cmp_ftr_reg(const void *id, const void *regp)
  */
 static struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id)
 {
-	return bsearch((const void *)(unsigned long)sys_id,
+	const struct __ftr_reg_entry *ret;
+
+	ret = bsearch((const void *)(unsigned long)sys_id,
 			arm64_ftr_regs,
 			ARRAY_SIZE(arm64_ftr_regs),
 			sizeof(arm64_ftr_regs[0]),
 			search_cmp_ftr_reg);
+	if (ret)
+		return ret->reg;
+	return NULL;
 }
 
-static u64 arm64_ftr_set_value(struct arm64_ftr_bits *ftrp, s64 reg, s64 ftr_val)
+static u64 arm64_ftr_set_value(const struct arm64_ftr_bits *ftrp, s64 reg,
+			       s64 ftr_val)
 {
 	u64 mask = arm64_ftr_mask(ftrp);
 
@@ -355,7 +373,8 @@ static u64 arm64_ftr_set_value(struct arm64_ftr_bits *ftrp, s64 reg, s64 ftr_val
 	return reg;
 }
 
-static s64 arm64_ftr_safe_value(struct arm64_ftr_bits *ftrp, s64 new, s64 cur)
+static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new,
+				s64 cur)
 {
 	s64 ret = 0;
 
@@ -376,27 +395,13 @@ static s64 arm64_ftr_safe_value(struct arm64_ftr_bits *ftrp, s64 new, s64 cur)
 	return ret;
 }
 
-static int __init sort_cmp_ftr_regs(const void *a, const void *b)
-{
-	return ((const struct arm64_ftr_reg *)a)->sys_id -
-		 ((const struct arm64_ftr_reg *)b)->sys_id;
-}
-
-static void __init swap_ftr_regs(void *a, void *b, int size)
-{
-	struct arm64_ftr_reg tmp = *(struct arm64_ftr_reg *)a;
-	*(struct arm64_ftr_reg *)a = *(struct arm64_ftr_reg *)b;
-	*(struct arm64_ftr_reg *)b = tmp;
-}
-
 static void __init sort_ftr_regs(void)
 {
-	/* Keep the array sorted so that we can do the binary search */
-	sort(arm64_ftr_regs,
-		ARRAY_SIZE(arm64_ftr_regs),
-		sizeof(arm64_ftr_regs[0]),
-		sort_cmp_ftr_regs,
-		swap_ftr_regs);
+	int i;
+
+	/* Check that the array is sorted so that we can do the binary search */
+	for (i = 1; i < ARRAY_SIZE(arm64_ftr_regs); i++)
+		BUG_ON(arm64_ftr_regs[i].sys_id < arm64_ftr_regs[i - 1].sys_id);
 }
 
 /*
@@ -407,7 +412,7 @@ static void __init init_cpu_ftr_reg(u32 sys_reg, u64 new)
 {
 	u64 val = 0;
 	u64 strict_mask = ~0x0ULL;
-	struct arm64_ftr_bits *ftrp;
+	const struct arm64_ftr_bits *ftrp;
 	struct arm64_ftr_reg *reg = get_arm64_ftr_reg(sys_reg);
 
 	BUG_ON(!reg);
@@ -464,7 +469,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 
 static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new)
 {
-	struct arm64_ftr_bits *ftrp;
+	const struct arm64_ftr_bits *ftrp;
 
 	for (ftrp = reg->ftr_bits; ftrp->width; ftrp++) {
 		s64 ftr_cur = arm64_ftr_value(ftrp, reg->sys_val);
@@ -1004,23 +1009,33 @@ verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
  * cannot do anything to fix it up and could cause unexpected failures. So
  * we park the CPU.
  */
-void verify_local_cpu_capabilities(void)
+static void verify_local_cpu_capabilities(void)
 {
+	verify_local_cpu_errata_workarounds();
+	verify_local_cpu_features(arm64_features);
+	verify_local_elf_hwcaps(arm64_elf_hwcaps);
+	if (system_supports_32bit_el0())
+		verify_local_elf_hwcaps(compat_elf_hwcaps);
+}
 
+void check_local_cpu_capabilities(void)
+{
+	/*
+	 * All secondary CPUs should conform to the early CPU features
+	 * in use by the kernel based on boot CPU.
+	 */
 	check_early_cpu_features();
 
 	/*
-	 * If we haven't computed the system capabilities, there is nothing
-	 * to verify.
+	 * If we haven't finalised the system capabilities, this CPU gets
+	 * a chance to update the errata work arounds.
+	 * Otherwise, this CPU should verify that it has all the system
+	 * advertised capabilities.
 	 */
 	if (!sys_caps_initialised)
-		return;
-
-	verify_local_cpu_errata();
-	verify_local_cpu_features(arm64_features);
-	verify_local_elf_hwcaps(arm64_elf_hwcaps);
-	if (system_supports_32bit_el0())
-		verify_local_elf_hwcaps(compat_elf_hwcaps);
+		update_cpu_errata_workarounds();
+	else
+		verify_local_cpu_capabilities();
 }
 
 static void __init setup_feature_capabilities(void)

arch/arm64/kernel/cpuinfo.c

@@ -363,8 +363,6 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info)
 	}
 
 	cpuinfo_detect_icache_policy(info);
-
-	check_local_cpu_errata();
 }
 
 void cpuinfo_store_cpu(void)

arch/arm64/kernel/debug-monitors.c

@@ -46,16 +46,14 @@ static void mdscr_write(u32 mdscr)
 {
 	unsigned long flags;
 	local_dbg_save(flags);
-	asm volatile("msr mdscr_el1, %0" :: "r" (mdscr));
+	write_sysreg(mdscr, mdscr_el1);
 	local_dbg_restore(flags);
 }
 NOKPROBE_SYMBOL(mdscr_write);
 
 static u32 mdscr_read(void)
 {
-	u32 mdscr;
-	asm volatile("mrs %0, mdscr_el1" : "=r" (mdscr));
-	return mdscr;
+	return read_sysreg(mdscr_el1);
 }
 NOKPROBE_SYMBOL(mdscr_read);
 
@@ -132,36 +130,18 @@ NOKPROBE_SYMBOL(disable_debug_monitors);
 /*
  * OS lock clearing.
  */
-static void clear_os_lock(void *unused)
+static int clear_os_lock(unsigned int cpu)
 {
-	asm volatile("msr oslar_el1, %0" : : "r" (0));
-}
-
-static int os_lock_notify(struct notifier_block *self,
-				    unsigned long action, void *data)
-{
-	if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE)
-		clear_os_lock(NULL);
-	return NOTIFY_OK;
+	write_sysreg(0, oslar_el1);
+	isb();
+	return 0;
 }
 
-static struct notifier_block os_lock_nb = {
-	.notifier_call = os_lock_notify,
-};
-
 static int debug_monitors_init(void)
 {
-	cpu_notifier_register_begin();
-
-	/* Clear the OS lock. */
-	on_each_cpu(clear_os_lock, NULL, 1);
-	isb();
-
-	/* Register hotplug handler. */
-	__register_cpu_notifier(&os_lock_nb);
-
-	cpu_notifier_register_done();
-	return 0;
+	return cpuhp_setup_state(CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
+				 "CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING",
+				 clear_os_lock, NULL);
 }
 postcore_initcall(debug_monitors_init);
 
@@ -254,7 +234,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 		return 0;
 
 	if (user_mode(regs)) {
-		send_user_sigtrap(TRAP_HWBKPT);
+		send_user_sigtrap(TRAP_TRACE);
 
 		/*
 		 * ptrace will disable single step unless explicitly
@@ -382,7 +362,7 @@ NOKPROBE_SYMBOL(aarch32_break_handler);
 static int __init debug_traps_init(void)
 {
 	hook_debug_fault_code(DBG_ESR_EVT_HWSS, single_step_handler, SIGTRAP,
-			      TRAP_HWBKPT, "single-step handler");
+			      TRAP_TRACE, "single-step handler");
 	hook_debug_fault_code(DBG_ESR_EVT_BRK, brk_handler, SIGTRAP,
 			      TRAP_BRKPT, "ptrace BRK handler");
 	return 0;
@@ -435,8 +415,10 @@ NOKPROBE_SYMBOL(kernel_active_single_step);
 /* ptrace API */
 void user_enable_single_step(struct task_struct *task)
 {
-	set_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP);
-	set_regs_spsr_ss(task_pt_regs(task));
+	struct thread_info *ti = task_thread_info(task);
+
+	if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP))
+		set_regs_spsr_ss(task_pt_regs(task));
 }
 NOKPROBE_SYMBOL(user_enable_single_step);
 

arch/arm64/kernel/entry.S

@@ -104,7 +104,7 @@
 	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
 	mov	x20, #TASK_SIZE_64
 	str	x20, [tsk, #TI_ADDR_LIMIT]
-	ALTERNATIVE(nop, SET_PSTATE_UAO(0), ARM64_HAS_UAO, CONFIG_ARM64_UAO)
+	/* No need to reset PSTATE.UAO, hardware's already set it to 0 for us */
 	.endif /* \el == 0 */
 	mrs	x22, elr_el1
 	mrs	x23, spsr_el1
@@ -150,13 +150,7 @@
 	ldr	x23, [sp, #S_SP]		// load return stack pointer
 	msr	sp_el0, x23
 #ifdef CONFIG_ARM64_ERRATUM_845719
-alternative_if_not ARM64_WORKAROUND_845719
-	nop
-	nop
-#ifdef CONFIG_PID_IN_CONTEXTIDR
-	nop
-#endif
-alternative_else
+alternative_if ARM64_WORKAROUND_845719
 	tbz	x22, #4, 1f
 #ifdef CONFIG_PID_IN_CONTEXTIDR
 	mrs	x29, contextidr_el1
@@ -165,7 +159,7 @@ alternative_else
 	msr contextidr_el1, xzr
 #endif
 1:
-alternative_endif
+alternative_else_nop_endif
 #endif
 	.endif
 	msr	elr_el1, x21			// set up the return data
@@ -707,18 +701,13 @@ ret_fast_syscall_trace:
  * Ok, we need to do extra processing, enter the slow path.
  */
 work_pending:
-	tbnz	x1, #TIF_NEED_RESCHED, work_resched
-	/* TIF_SIGPENDING, TIF_NOTIFY_RESUME or TIF_FOREIGN_FPSTATE case */
 	mov	x0, sp				// 'regs'
-	enable_irq				// enable interrupts for do_notify_resume()
 	bl	do_notify_resume
-	b	ret_to_user
-work_resched:
 #ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_off		// the IRQs are off here, inform the tracing code
+	bl	trace_hardirqs_on		// enabled while in userspace
 #endif
-	bl	schedule
-
+	ldr	x1, [tsk, #TI_FLAGS]		// re-check for single-step
+	b	finish_ret_to_user
 /*
  * "slow" syscall return path.
  */
@@ -727,6 +716,7 @@ ret_to_user:
 	ldr	x1, [tsk, #TI_FLAGS]
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
+finish_ret_to_user:
 	enable_step_tsk x1, x2
 	kernel_exit 0
 ENDPROC(ret_to_user)

arch/arm64/kernel/head.S

@@ -208,13 +208,23 @@ efi_header_end:
 
 	__INIT
 
+	/*
+	 * The following callee saved general purpose registers are used on the
+	 * primary lowlevel boot path:
+	 *
+	 *  Register   Scope                      Purpose
+	 *  x21        stext() .. start_kernel()  FDT pointer passed at boot in x0
+	 *  x23        stext() .. start_kernel()  physical misalignment/KASLR offset
+	 *  x28        __create_page_tables()     callee preserved temp register
+	 *  x19/x20    __primary_switch()         callee preserved temp registers
+	 */
 ENTRY(stext)
 	bl	preserve_boot_args
-	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
-	adrp	x24, __PHYS_OFFSET
-	and	x23, x24, MIN_KIMG_ALIGN - 1	// KASLR offset, defaults to 0
+	bl	el2_setup			// Drop to EL1, w0=cpu_boot_mode
+	adrp	x23, __PHYS_OFFSET
+	and	x23, x23, MIN_KIMG_ALIGN - 1	// KASLR offset, defaults to 0
 	bl	set_cpu_boot_mode_flag
-	bl	__create_page_tables		// x25=TTBR0, x26=TTBR1
+	bl	__create_page_tables
 	/*
 	 * The following calls CPU setup code, see arch/arm64/mm/proc.S for
 	 * details.
@@ -222,9 +232,7 @@ ENTRY(stext)
 	 * the TCR will have been set.
 	 */
 	bl	__cpu_setup			// initialise processor
-	adr_l	x27, __primary_switch		// address to jump to after
-						// MMU has been enabled
-	b	__enable_mmu
+	b	__primary_switch
 ENDPROC(stext)
 
 /*
@@ -311,23 +319,21 @@ ENDPROC(preserve_boot_args)
  *     been enabled
  */
 __create_page_tables:
-	adrp	x25, idmap_pg_dir
-	adrp	x26, swapper_pg_dir
 	mov	x28, lr
 
 	/*
 	 * Invalidate the idmap and swapper page tables to avoid potential
 	 * dirty cache lines being evicted.
 	 */
-	mov	x0, x25
-	add	x1, x26, #SWAPPER_DIR_SIZE
+	adrp	x0, idmap_pg_dir
+	adrp	x1, swapper_pg_dir + SWAPPER_DIR_SIZE
 	bl	__inval_cache_range
 
 	/*
 	 * Clear the idmap and swapper page tables.
 	 */
-	mov	x0, x25
-	add	x6, x26, #SWAPPER_DIR_SIZE
+	adrp	x0, idmap_pg_dir
+	adrp	x6, swapper_pg_dir + SWAPPER_DIR_SIZE
 1:	stp	xzr, xzr, [x0], #16
 	stp	xzr, xzr, [x0], #16
 	stp	xzr, xzr, [x0], #16
@@ -340,7 +346,7 @@ __create_page_tables:
 	/*
 	 * Create the identity mapping.
 	 */
-	mov	x0, x25				// idmap_pg_dir
+	adrp	x0, idmap_pg_dir
 	adrp	x3, __idmap_text_start		// __pa(__idmap_text_start)
 
 #ifndef CONFIG_ARM64_VA_BITS_48
@@ -390,7 +396,7 @@ __create_page_tables:
 	/*
 	 * Map the kernel image (starting with PHYS_OFFSET).
 	 */
-	mov	x0, x26				// swapper_pg_dir
+	adrp	x0, swapper_pg_dir
 	mov_q	x5, KIMAGE_VADDR + TEXT_OFFSET	// compile time __va(_text)
 	add	x5, x5, x23			// add KASLR displacement
 	create_pgd_entry x0, x5, x3, x6
@@ -405,8 +411,8 @@ __create_page_tables:
 	 * accesses (MMU disabled), invalidate the idmap and swapper page
 	 * tables again to remove any speculatively loaded cache lines.
 	 */
-	mov	x0, x25
-	add	x1, x26, #SWAPPER_DIR_SIZE
+	adrp	x0, idmap_pg_dir
+	adrp	x1, swapper_pg_dir + SWAPPER_DIR_SIZE
 	dmb	sy
 	bl	__inval_cache_range
 
@@ -416,14 +422,27 @@ ENDPROC(__create_page_tables)
 
 /*
  * The following fragment of code is executed with the MMU enabled.
+ *
+ *   x0 = __PHYS_OFFSET
  */
-	.set	initial_sp, init_thread_union + THREAD_START_SP
 __primary_switched:
-	mov	x28, lr				// preserve LR
+	adrp	x4, init_thread_union
+	add	sp, x4, #THREAD_SIZE
+	msr	sp_el0, x4			// Save thread_info
+
 	adr_l	x8, vectors			// load VBAR_EL1 with virtual
 	msr	vbar_el1, x8			// vector table address
 	isb
 
+	stp	xzr, x30, [sp, #-16]!
+	mov	x29, sp
+
+	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
+
+	ldr_l	x4, kimage_vaddr		// Save the offset between
+	sub	x4, x4, x0			// the kernel virtual and
+	str_l	x4, kimage_voffset, x5		// physical mappings
+
 	// Clear BSS
 	adr_l	x0, __bss_start
 	mov	x1, xzr
@@ -432,17 +451,6 @@ __primary_switched:
 	bl	__pi_memset
 	dsb	ishst				// Make zero page visible to PTW
 
-	adr_l	sp, initial_sp, x4
-	mov	x4, sp
-	and	x4, x4, #~(THREAD_SIZE - 1)
-	msr	sp_el0, x4			// Save thread_info
-	str_l	x21, __fdt_pointer, x5		// Save FDT pointer
-
-	ldr_l	x4, kimage_vaddr		// Save the offset between
-	sub	x4, x4, x24			// the kernel virtual and
-	str_l	x4, kimage_voffset, x5		// physical mappings
-
-	mov	x29, #0
 #ifdef CONFIG_KASAN
 	bl	kasan_early_init
 #endif
@@ -454,8 +462,8 @@ __primary_switched:
 	bl	kaslr_early_init		// parse FDT for KASLR options
 	cbz	x0, 0f				// KASLR disabled? just proceed
 	orr	x23, x23, x0			// record KASLR offset
-	ret	x28				// we must enable KASLR, return
-						// to __enable_mmu()
+	ldp	x29, x30, [sp], #16		// we must enable KASLR, return
+	ret					// to __primary_switch()
 0:
 #endif
 	b	start_kernel
@@ -465,7 +473,7 @@ ENDPROC(__primary_switched)
  * end early head section, begin head code that is also used for
  * hotplug and needs to have the same protections as the text region
  */
-	.section ".text","ax"
+	.section ".idmap.text","ax"
 
 ENTRY(kimage_vaddr)
 	.quad		_text - TEXT_OFFSET
@@ -490,7 +498,7 @@ CPU_LE(	bic	x0, x0, #(1 << 25)	)	// Clear the EE bit for EL2
 CPU_BE(	orr	x0, x0, #(3 << 24)	)	// Set the EE and E0E bits for EL1
 CPU_LE(	bic	x0, x0, #(3 << 24)	)	// Clear the EE and E0E bits for EL1
 	msr	sctlr_el1, x0
-	mov	w20, #BOOT_CPU_MODE_EL1		// This cpu booted in EL1
+	mov	w0, #BOOT_CPU_MODE_EL1		// This cpu booted in EL1
 	isb
 	ret
 
@@ -586,7 +594,7 @@ CPU_LE(	movk	x0, #0x30d0, lsl #16	)	// Clear EE and E0E on LE systems
 
 	cbz	x2, install_el2_stub
 
-	mov	w20, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
+	mov	w0, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
 	isb
 	ret
 
@@ -601,7 +609,7 @@ install_el2_stub:
 		      PSR_MODE_EL1h)
 	msr	spsr_el2, x0
 	msr	elr_el2, lr
-	mov	w20, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
+	mov	w0, #BOOT_CPU_MODE_EL2		// This CPU booted in EL2
 	eret
 ENDPROC(el2_setup)
 
@@ -611,15 +619,22 @@ ENDPROC(el2_setup)
  */
 set_cpu_boot_mode_flag:
 	adr_l	x1, __boot_cpu_mode
-	cmp	w20, #BOOT_CPU_MODE_EL2
+	cmp	w0, #BOOT_CPU_MODE_EL2
 	b.ne	1f
 	add	x1, x1, #4
-1:	str	w20, [x1]			// This CPU has booted in EL1
+1:	str	w0, [x1]			// This CPU has booted in EL1
 	dmb	sy
 	dc	ivac, x1			// Invalidate potentially stale cache line
 	ret
 ENDPROC(set_cpu_boot_mode_flag)
 
+/*
+ * These values are written with the MMU off, but read with the MMU on.
+ * Writers will invalidate the corresponding address, discarding up to a
+ * 'Cache Writeback Granule' (CWG) worth of data. The linker script ensures
+ * sufficient alignment that the CWG doesn't overlap another section.
+ */
+	.pushsection ".mmuoff.data.write", "aw"
 /*
  * We need to find out the CPU boot mode long after boot, so we need to
  * store it in a writable variable.
@@ -627,11 +642,16 @@ ENDPROC(set_cpu_boot_mode_flag)
  * This is not in .bss, because we set it sufficiently early that the boot-time
  * zeroing of .bss would clobber it.
  */
-	.pushsection	.data..cacheline_aligned
-	.align	L1_CACHE_SHIFT
 ENTRY(__boot_cpu_mode)
 	.long	BOOT_CPU_MODE_EL2
 	.long	BOOT_CPU_MODE_EL1
+/*
+ * The booting CPU updates the failed status @__early_cpu_boot_status,
+ * with MMU turned off.
+ */
+ENTRY(__early_cpu_boot_status)
+	.long 	0
+
 	.popsection
 
 	/*
@@ -639,7 +659,7 @@ ENTRY(__boot_cpu_mode)
 	 * cores are held until we're ready for them to initialise.
 	 */
 ENTRY(secondary_holding_pen)
-	bl	el2_setup			// Drop to EL1, w20=cpu_boot_mode
+	bl	el2_setup			// Drop to EL1, w0=cpu_boot_mode
 	bl	set_cpu_boot_mode_flag
 	mrs	x0, mpidr_el1
 	mov_q	x1, MPIDR_HWID_BITMASK
@@ -666,12 +686,10 @@ secondary_startup:
 	/*
 	 * Common entry point for secondary CPUs.
 	 */
-	adrp	x25, idmap_pg_dir
-	adrp	x26, swapper_pg_dir
 	bl	__cpu_setup			// initialise processor
-
-	adr_l	x27, __secondary_switch		// address to jump to after enabling the MMU
-	b	__enable_mmu
+	bl	__enable_mmu
+	ldr	x8, =__secondary_switched
+	br	x8
 ENDPROC(secondary_startup)
 
 __secondary_switched:
@@ -706,33 +724,27 @@ ENDPROC(__secondary_switched)
 	dc	ivac, \tmp1			// Invalidate potentially stale cache line
 	.endm
 
-	.pushsection	.data..cacheline_aligned
-	.align	L1_CACHE_SHIFT
-ENTRY(__early_cpu_boot_status)
-	.long 	0
-	.popsection
-
 /*
  * Enable the MMU.
  *
  *  x0  = SCTLR_EL1 value for turning on the MMU.
- *  x27 = *virtual* address to jump to upon completion
  *
- * Other registers depend on the function called upon completion.
+ * Returns to the caller via x30/lr. This requires the caller to be covered
+ * by the .idmap.text section.
  *
  * Checks if the selected granule size is supported by the CPU.
  * If it isn't, park the CPU
  */
-	.section	".idmap.text", "ax"
 ENTRY(__enable_mmu)
-	mrs	x22, sctlr_el1			// preserve old SCTLR_EL1 value
 	mrs	x1, ID_AA64MMFR0_EL1
 	ubfx	x2, x1, #ID_AA64MMFR0_TGRAN_SHIFT, 4
 	cmp	x2, #ID_AA64MMFR0_TGRAN_SUPPORTED
 	b.ne	__no_granule_support
 	update_early_cpu_boot_status 0, x1, x2
-	msr	ttbr0_el1, x25			// load TTBR0
-	msr	ttbr1_el1, x26			// load TTBR1
+	adrp	x1, idmap_pg_dir
+	adrp	x2, swapper_pg_dir
+	msr	ttbr0_el1, x1			// load TTBR0
+	msr	ttbr1_el1, x2			// load TTBR1
 	isb
 	msr	sctlr_el1, x0
 	isb
@@ -744,29 +756,7 @@ ENTRY(__enable_mmu)
 	ic	iallu
 	dsb	nsh
 	isb
-#ifdef CONFIG_RANDOMIZE_BASE
-	mov	x19, x0				// preserve new SCTLR_EL1 value
-	blr	x27
-
-	/*
-	 * If we return here, we have a KASLR displacement in x23 which we need
-	 * to take into account by discarding the current kernel mapping and
-	 * creating a new one.
-	 */
-	msr	sctlr_el1, x22			// disable the MMU
-	isb
-	bl	__create_page_tables		// recreate kernel mapping
-
-	tlbi	vmalle1				// Remove any stale TLB entries
-	dsb	nsh
-
-	msr	sctlr_el1, x19			// re-enable the MMU
-	isb
-	ic	iallu				// flush instructions fetched
-	dsb	nsh				// via old mapping
-	isb
-#endif
-	br	x27
+	ret
 ENDPROC(__enable_mmu)
 
 __no_granule_support:
@@ -775,11 +765,11 @@ __no_granule_support:
 1:
 	wfe
 	wfi
-	b 1b
+	b	1b
 ENDPROC(__no_granule_support)
 
-__primary_switch:
 #ifdef CONFIG_RELOCATABLE
+__relocate_kernel:
 	/*
 	 * Iterate over each entry in the relocation table, and apply the
 	 * relocations in place.
@@ -801,14 +791,46 @@ __primary_switch:
 	add	x13, x13, x23			// relocate
 	str	x13, [x11, x23]
 	b	0b
+1:	ret
+ENDPROC(__relocate_kernel)
+#endif
 
-1:
+__primary_switch:
+#ifdef CONFIG_RANDOMIZE_BASE
+	mov	x19, x0				// preserve new SCTLR_EL1 value
+	mrs	x20, sctlr_el1			// preserve old SCTLR_EL1 value
 #endif
+
+	bl	__enable_mmu
+#ifdef CONFIG_RELOCATABLE
+	bl	__relocate_kernel
+#ifdef CONFIG_RANDOMIZE_BASE
 	ldr	x8, =__primary_switched
-	br	x8
-ENDPROC(__primary_switch)
+	adrp	x0, __PHYS_OFFSET
+	blr	x8
 
-__secondary_switch:
-	ldr	x8, =__secondary_switched
+	/*
+	 * If we return here, we have a KASLR displacement in x23 which we need
+	 * to take into account by discarding the current kernel mapping and
+	 * creating a new one.
+	 */
+	msr	sctlr_el1, x20			// disable the MMU
+	isb
+	bl	__create_page_tables		// recreate kernel mapping
+
+	tlbi	vmalle1				// Remove any stale TLB entries
+	dsb	nsh
+
+	msr	sctlr_el1, x19			// re-enable the MMU
+	isb
+	ic	iallu				// flush instructions fetched
+	dsb	nsh				// via old mapping
+	isb
+
+	bl	__relocate_kernel
+#endif
+#endif
+	ldr	x8, =__primary_switched
+	adrp	x0, __PHYS_OFFSET
 	br	x8
-ENDPROC(__secondary_switch)
+ENDPROC(__primary_switch)

arch/arm64/kernel/hibernate-asm.S

@@ -36,8 +36,8 @@
 .macro break_before_make_ttbr_switch zero_page, page_table
 	msr	ttbr1_el1, \zero_page
 	isb
-	tlbi	vmalle1is
-	dsb	ish
+	tlbi	vmalle1
+	dsb	nsh
 	msr	ttbr1_el1, \page_table
 	isb
 .endm
@@ -96,7 +96,7 @@ ENTRY(swsusp_arch_suspend_exit)
 
 	add	x1, x10, #PAGE_SIZE
 	/* Clean the copied page to PoU - based on flush_icache_range() */
-	dcache_line_size x2, x3
+	raw_dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x4, x10, x3
 2:	dc	cvau, x4	/* clean D line / unified line */

arch/arm64/kernel/hibernate.c

@@ -15,9 +15,9 @@
  * License terms: GNU General Public License (GPL) version 2
  */
 #define pr_fmt(x) "hibernate: " x
+#include <linux/cpu.h>
 #include <linux/kvm_host.h>
 #include <linux/mm.h>
-#include <linux/notifier.h>
 #include <linux/pm.h>
 #include <linux/sched.h>
 #include <linux/suspend.h>
@@ -26,6 +26,7 @@
 
 #include <asm/barrier.h>
 #include <asm/cacheflush.h>
+#include <asm/cputype.h>
 #include <asm/irqflags.h>
 #include <asm/memory.h>
 #include <asm/mmu_context.h>
@@ -34,6 +35,7 @@
 #include <asm/pgtable-hwdef.h>
 #include <asm/sections.h>
 #include <asm/smp.h>
+#include <asm/smp_plat.h>
 #include <asm/suspend.h>
 #include <asm/sysreg.h>
 #include <asm/virt.h>
@@ -54,18 +56,18 @@ extern int in_suspend;
 /* Do we need to reset el2? */
 #define el2_reset_needed() (is_hyp_mode_available() && !is_kernel_in_hyp_mode())
 
-/*
- * Start/end of the hibernate exit code, this must be copied to a 'safe'
- * location in memory, and executed from there.
- */
-extern char __hibernate_exit_text_start[], __hibernate_exit_text_end[];
-
 /* temporary el2 vectors in the __hibernate_exit_text section. */
 extern char hibernate_el2_vectors[];
 
 /* hyp-stub vectors, used to restore el2 during resume from hibernate. */
 extern char __hyp_stub_vectors[];
 
+/*
+ * The logical cpu number we should resume on, initialised to a non-cpu
+ * number.
+ */
+static int sleep_cpu = -EINVAL;
+
 /*
  * Values that may not change over hibernate/resume. We put the build number
  * and date in here so that we guarantee not to resume with a different
@@ -88,6 +90,8 @@ static struct arch_hibernate_hdr {
 	 * re-configure el2.
 	 */
 	phys_addr_t	__hyp_stub_vectors;
+
+	u64		sleep_cpu_mpidr;
 } resume_hdr;
 
 static inline void arch_hdr_invariants(struct arch_hibernate_hdr_invariants *i)
@@ -130,12 +134,22 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size)
 	else
 		hdr->__hyp_stub_vectors = 0;
 
+	/* Save the mpidr of the cpu we called cpu_suspend() on... */
+	if (sleep_cpu < 0) {
+		pr_err("Failing to hibernate on an unkown CPU.\n");
+		return -ENODEV;
+	}
+	hdr->sleep_cpu_mpidr = cpu_logical_map(sleep_cpu);
+	pr_info("Hibernating on CPU %d [mpidr:0x%llx]\n", sleep_cpu,
+		hdr->sleep_cpu_mpidr);
+
 	return 0;
 }
 EXPORT_SYMBOL(arch_hibernation_header_save);
 
 int arch_hibernation_header_restore(void *addr)
 {
+	int ret;
 	struct arch_hibernate_hdr_invariants invariants;
 	struct arch_hibernate_hdr *hdr = addr;
 
@@ -145,6 +159,24 @@ int arch_hibernation_header_restore(void *addr)
 		return -EINVAL;
 	}
 
+	sleep_cpu = get_logical_index(hdr->sleep_cpu_mpidr);
+	pr_info("Hibernated on CPU %d [mpidr:0x%llx]\n", sleep_cpu,
+		hdr->sleep_cpu_mpidr);
+	if (sleep_cpu < 0) {
+		pr_crit("Hibernated on a CPU not known to this kernel!\n");
+		sleep_cpu = -EINVAL;
+		return -EINVAL;
+	}
+	if (!cpu_online(sleep_cpu)) {
+		pr_info("Hibernated on a CPU that is offline! Bringing CPU up.\n");
+		ret = cpu_up(sleep_cpu);
+		if (ret) {
+			pr_err("Failed to bring hibernate-CPU up!\n");
+			sleep_cpu = -EINVAL;
+			return ret;
+		}
+	}
+
 	resume_hdr = *hdr;
 
 	return 0;
@@ -241,6 +273,7 @@ out:
 	return rc;
 }
 
+#define dcache_clean_range(start, end)	__flush_dcache_area(start, (end - start))
 
 int swsusp_arch_suspend(void)
 {
@@ -256,10 +289,16 @@ int swsusp_arch_suspend(void)
 	local_dbg_save(flags);
 
 	if (__cpu_suspend_enter(&state)) {
+		sleep_cpu = smp_processor_id();
 		ret = swsusp_save();
 	} else {
-		/* Clean kernel to PoC for secondary core startup */
-		__flush_dcache_area(LMADDR(KERNEL_START), KERNEL_END - KERNEL_START);
+		/* Clean kernel core startup/idle code to PoC*/
+		dcache_clean_range(__mmuoff_data_start, __mmuoff_data_end);
+		dcache_clean_range(__idmap_text_start, __idmap_text_end);
+
+		/* Clean kvm setup code to PoC? */
+		if (el2_reset_needed())
+			dcache_clean_range(__hyp_idmap_text_start, __hyp_idmap_text_end);
 
 		/*
 		 * Tell the hibernation core that we've just restored
@@ -267,6 +306,7 @@ int swsusp_arch_suspend(void)
 		 */
 		in_suspend = 0;
 
+		sleep_cpu = -EINVAL;
 		__cpu_suspend_exit();
 	}
 
@@ -275,6 +315,33 @@ int swsusp_arch_suspend(void)
 	return ret;
 }
 
+static void _copy_pte(pte_t *dst_pte, pte_t *src_pte, unsigned long addr)
+{
+	pte_t pte = *src_pte;
+
+	if (pte_valid(pte)) {
+		/*
+		 * Resume will overwrite areas that may be marked
+		 * read only (code, rodata). Clear the RDONLY bit from
+		 * the temporary mappings we use during restore.
+		 */
+		set_pte(dst_pte, pte_clear_rdonly(pte));
+	} else if (debug_pagealloc_enabled() && !pte_none(pte)) {
+		/*
+		 * debug_pagealloc will removed the PTE_VALID bit if
+		 * the page isn't in use by the resume kernel. It may have
+		 * been in use by the original kernel, in which case we need
+		 * to put it back in our copy to do the restore.
+		 *
+		 * Before marking this entry valid, check the pfn should
+		 * be mapped.
+		 */
+		BUG_ON(!pfn_valid(pte_pfn(pte)));
+
+		set_pte(dst_pte, pte_mkpresent(pte_clear_rdonly(pte)));
+	}
+}
+
 static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start,
 		    unsigned long end)
 {
@@ -290,13 +357,7 @@ static int copy_pte(pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long start,
 
 	src_pte = pte_offset_kernel(src_pmd, start);
 	do {
-		if (!pte_none(*src_pte))
-			/*
-			 * Resume will overwrite areas that may be marked
-			 * read only (code, rodata). Clear the RDONLY bit from
-			 * the temporary mappings we use during restore.
-			 */
-			set_pte(dst_pte, __pte(pte_val(*src_pte) & ~PTE_RDONLY));
+		_copy_pte(dst_pte, src_pte, addr);
 	} while (dst_pte++, src_pte++, addr += PAGE_SIZE, addr != end);
 
 	return 0;
@@ -483,27 +544,12 @@ out:
 	return rc;
 }
 
-static int check_boot_cpu_online_pm_callback(struct notifier_block *nb,
-					     unsigned long action, void *ptr)
+int hibernate_resume_nonboot_cpu_disable(void)
 {
-	if (action == PM_HIBERNATION_PREPARE &&
-	     cpumask_first(cpu_online_mask) != 0) {
-		pr_warn("CPU0 is offline.\n");
-		return notifier_from_errno(-ENODEV);
+	if (sleep_cpu < 0) {
+		pr_err("Failing to resume from hibernate on an unkown CPU.\n");
+		return -ENODEV;
 	}
 
-	return NOTIFY_OK;
-}
-
-static int __init check_boot_cpu_online_init(void)
-{
-	/*
-	 * Set this pm_notifier callback with a lower priority than
-	 * cpu_hotplug_pm_callback, so that cpu_hotplug_pm_callback will be
-	 * called earlier to disable cpu hotplug before the cpu online check.
-	 */
-	pm_notifier(check_boot_cpu_online_pm_callback, -INT_MAX);
-
-	return 0;
+	return freeze_secondary_cpus(sleep_cpu);
 }
-core_initcall(check_boot_cpu_online_init);

arch/arm64/kernel/hw_breakpoint.c

@@ -857,7 +857,7 @@ void hw_breakpoint_thread_switch(struct task_struct *next)
 /*
  * CPU initialisation.
  */
-static void hw_breakpoint_reset(void *unused)
+static int hw_breakpoint_reset(unsigned int cpu)
 {
 	int i;
 	struct perf_event **slots;
@@ -888,28 +888,14 @@ static void hw_breakpoint_reset(void *unused)
 			write_wb_reg(AARCH64_DBG_REG_WVR, i, 0UL);
 		}
 	}
-}
 
-static int hw_breakpoint_reset_notify(struct notifier_block *self,
-						unsigned long action,
-						void *hcpu)
-{
-	if ((action & ~CPU_TASKS_FROZEN) == CPU_ONLINE) {
-		local_irq_disable();
-		hw_breakpoint_reset(NULL);
-		local_irq_enable();
-	}
-	return NOTIFY_OK;
+	return 0;
 }
 
-static struct notifier_block hw_breakpoint_reset_nb = {
-	.notifier_call = hw_breakpoint_reset_notify,
-};
-
 #ifdef CONFIG_CPU_PM
-extern void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *));
+extern void cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int));
 #else
-static inline void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
+static inline void cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int))
 {
 }
 #endif
@@ -919,36 +905,34 @@ static inline void cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
  */
 static int __init arch_hw_breakpoint_init(void)
 {
+	int ret;
+
 	core_num_brps = get_num_brps();
 	core_num_wrps = get_num_wrps();
 
 	pr_info("found %d breakpoint and %d watchpoint registers.\n",
 		core_num_brps, core_num_wrps);
 
-	cpu_notifier_register_begin();
-
-	/*
-	 * Reset the breakpoint resources. We assume that a halting
-	 * debugger will leave the world in a nice state for us.
-	 */
-	smp_call_function(hw_breakpoint_reset, NULL, 1);
-	hw_breakpoint_reset(NULL);
-
 	/* Register debug fault handlers. */
 	hook_debug_fault_code(DBG_ESR_EVT_HWBP, breakpoint_handler, SIGTRAP,
 			      TRAP_HWBKPT, "hw-breakpoint handler");
 	hook_debug_fault_code(DBG_ESR_EVT_HWWP, watchpoint_handler, SIGTRAP,
 			      TRAP_HWBKPT, "hw-watchpoint handler");
 
-	/* Register hotplug notifier. */
-	__register_cpu_notifier(&hw_breakpoint_reset_nb);
-
-	cpu_notifier_register_done();
+	/*
+	 * Reset the breakpoint resources. We assume that a halting
+	 * debugger will leave the world in a nice state for us.
+	 */
+	ret = cpuhp_setup_state(CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING,
+			  "CPUHP_AP_PERF_ARM_HW_BREAKPOINT_STARTING",
+			  hw_breakpoint_reset, NULL);
+	if (ret)
+		pr_err("failed to register CPU hotplug notifier: %d\n", ret);
 
 	/* Register cpu_suspend hw breakpoint restore hook */
 	cpu_suspend_set_dbg_restorer(hw_breakpoint_reset);
 
-	return 0;
+	return ret;
 }
 arch_initcall(arch_hw_breakpoint_init);
 

arch/arm64/kernel/insn.c

@@ -96,7 +96,7 @@ static void __kprobes *patch_map(void *addr, int fixmap)
 
 	if (module && IS_ENABLED(CONFIG_DEBUG_SET_MODULE_RONX))
 		page = vmalloc_to_page(addr);
-	else if (!module && IS_ENABLED(CONFIG_DEBUG_RODATA))
+	else if (!module)
 		page = pfn_to_page(PHYS_PFN(__pa(addr)));
 	else
 		return addr;
@@ -1202,6 +1202,19 @@ u32 aarch64_set_branch_offset(u32 insn, s32 offset)
 	BUG();
 }
 
+s32 aarch64_insn_adrp_get_offset(u32 insn)
+{
+	BUG_ON(!aarch64_insn_is_adrp(insn));
+	return aarch64_insn_decode_immediate(AARCH64_INSN_IMM_ADR, insn) << 12;
+}
+
+u32 aarch64_insn_adrp_set_offset(u32 insn, s32 offset)
+{
+	BUG_ON(!aarch64_insn_is_adrp(insn));
+	return aarch64_insn_encode_immediate(AARCH64_INSN_IMM_ADR, insn,
+						offset >> 12);
+}
+
 /*
  * Extract the Op/CR data from a msr/mrs instruction.
  */

arch/arm64/kernel/kaslr.c

@@ -6,6 +6,7 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/cache.h>
 #include <linux/crc32.h>
 #include <linux/init.h>
 #include <linux/libfdt.h>
@@ -20,7 +21,7 @@
 #include <asm/pgtable.h>
 #include <asm/sections.h>
 
-u64 __read_mostly module_alloc_base;
+u64 __ro_after_init module_alloc_base;
 u16 __initdata memstart_offset_seed;
 
 static __init u64 get_kaslr_seed(void *fdt)

arch/arm64/kernel/perf_event.c

@@ -24,6 +24,7 @@
 #include <asm/sysreg.h>
 #include <asm/virt.h>
 
+#include <linux/acpi.h>
 #include <linux/of.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
@@ -190,13 +191,23 @@
 #define ARMV8_THUNDER_PERFCTR_L1I_CACHE_PREF_MISS		0xED
 
 /* PMUv3 HW events mapping. */
+
+/*
+ * ARMv8 Architectural defined events, not all of these may
+ * be supported on any given implementation. Undefined events will
+ * be disabled at run-time.
+ */
 static const unsigned armv8_pmuv3_perf_map[PERF_COUNT_HW_MAX] = {
 	PERF_MAP_ALL_UNSUPPORTED,
 	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV8_PMUV3_PERFCTR_CPU_CYCLES,
 	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV8_PMUV3_PERFCTR_INST_RETIRED,
 	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE,
 	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV8_PMUV3_PERFCTR_PC_WRITE_RETIRED,
 	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV8_PMUV3_PERFCTR_BUS_CYCLES,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= ARMV8_PMUV3_PERFCTR_STALL_FRONTEND,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= ARMV8_PMUV3_PERFCTR_STALL_BACKEND,
 };
 
 /* ARM Cortex-A53 HW events mapping. */
@@ -258,6 +269,15 @@ static const unsigned armv8_pmuv3_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 	[C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE,
 	[C(L1D)][C(OP_WRITE)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1D_CACHE_REFILL,
 
+	[C(L1I)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1I_CACHE,
+	[C(L1I)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1I_CACHE_REFILL,
+
+	[C(DTLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1D_TLB_REFILL,
+	[C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1D_TLB,
+
+	[C(ITLB)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_L1I_TLB_REFILL,
+	[C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_L1I_TLB,
+
 	[C(BPU)][C(OP_READ)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_BR_PRED,
 	[C(BPU)][C(OP_READ)][C(RESULT_MISS)]	= ARMV8_PMUV3_PERFCTR_BR_MIS_PRED,
 	[C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)]	= ARMV8_PMUV3_PERFCTR_BR_PRED,
@@ -523,12 +543,6 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
 	.attrs = armv8_pmuv3_format_attrs,
 };
 
-static const struct attribute_group *armv8_pmuv3_attr_groups[] = {
-	&armv8_pmuv3_events_attr_group,
-	&armv8_pmuv3_format_attr_group,
-	NULL,
-};
-
 /*
  * Perf Events' indices
  */
@@ -905,9 +919,22 @@ static void armv8pmu_reset(void *info)
 
 static int armv8_pmuv3_map_event(struct perf_event *event)
 {
-	return armpmu_map_event(event, &armv8_pmuv3_perf_map,
-				&armv8_pmuv3_perf_cache_map,
-				ARMV8_PMU_EVTYPE_EVENT);
+	int hw_event_id;
+	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
+
+	hw_event_id = armpmu_map_event(event, &armv8_pmuv3_perf_map,
+				       &armv8_pmuv3_perf_cache_map,
+				       ARMV8_PMU_EVTYPE_EVENT);
+	if (hw_event_id < 0)
+		return hw_event_id;
+
+	/* disable micro/arch events not supported by this PMU */
+	if ((hw_event_id < ARMV8_PMUV3_MAX_COMMON_EVENTS) &&
+		!test_bit(hw_event_id, armpmu->pmceid_bitmap)) {
+			return -EOPNOTSUPP;
+	}
+
+	return hw_event_id;
 }
 
 static int armv8_a53_map_event(struct perf_event *event)
@@ -985,7 +1012,10 @@ static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
 	armv8_pmu_init(cpu_pmu);
 	cpu_pmu->name			= "armv8_pmuv3";
 	cpu_pmu->map_event		= armv8_pmuv3_map_event;
-	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv8_pmuv3_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv8_pmuv3_format_attr_group;
 	return armv8pmu_probe_pmu(cpu_pmu);
 }
 
@@ -994,7 +1024,10 @@ static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
 	armv8_pmu_init(cpu_pmu);
 	cpu_pmu->name			= "armv8_cortex_a53";
 	cpu_pmu->map_event		= armv8_a53_map_event;
-	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv8_pmuv3_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv8_pmuv3_format_attr_group;
 	return armv8pmu_probe_pmu(cpu_pmu);
 }
 
@@ -1003,7 +1036,10 @@ static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
 	armv8_pmu_init(cpu_pmu);
 	cpu_pmu->name			= "armv8_cortex_a57";
 	cpu_pmu->map_event		= armv8_a57_map_event;
-	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv8_pmuv3_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv8_pmuv3_format_attr_group;
 	return armv8pmu_probe_pmu(cpu_pmu);
 }
 
@@ -1012,7 +1048,10 @@ static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
 	armv8_pmu_init(cpu_pmu);
 	cpu_pmu->name			= "armv8_cortex_a72";
 	cpu_pmu->map_event		= armv8_a57_map_event;
-	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv8_pmuv3_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv8_pmuv3_format_attr_group;
 	return armv8pmu_probe_pmu(cpu_pmu);
 }
 
@@ -1021,7 +1060,10 @@ static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
 	armv8_pmu_init(cpu_pmu);
 	cpu_pmu->name			= "armv8_cavium_thunder";
 	cpu_pmu->map_event		= armv8_thunder_map_event;
-	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv8_pmuv3_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv8_pmuv3_format_attr_group;
 	return armv8pmu_probe_pmu(cpu_pmu);
 }
 
@@ -1030,7 +1072,10 @@ static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
 	armv8_pmu_init(cpu_pmu);
 	cpu_pmu->name			= "armv8_brcm_vulcan";
 	cpu_pmu->map_event		= armv8_vulcan_map_event;
-	cpu_pmu->pmu.attr_groups	= armv8_pmuv3_attr_groups;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] =
+		&armv8_pmuv3_events_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] =
+		&armv8_pmuv3_format_attr_group;
 	return armv8pmu_probe_pmu(cpu_pmu);
 }
 
@@ -1044,21 +1089,32 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{},
 };
 
+/*
+ * Non DT systems have their micro/arch events probed at run-time.
+ * A fairly complete list of generic events are provided and ones that
+ * aren't supported by the current PMU are disabled.
+ */
+static const struct pmu_probe_info armv8_pmu_probe_table[] = {
+	PMU_PROBE(0, 0, armv8_pmuv3_init), /* enable all defined counters */
+	{ /* sentinel value */ }
+};
+
 static int armv8_pmu_device_probe(struct platform_device *pdev)
 {
-	return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids, NULL);
+	if (acpi_disabled)
+		return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
+					    NULL);
+
+	return arm_pmu_device_probe(pdev, armv8_pmu_of_device_ids,
+				    armv8_pmu_probe_table);
 }
 
 static struct platform_driver armv8_pmu_driver = {
 	.driver		= {
-		.name	= "armv8-pmu",
+		.name	= ARMV8_PMU_PDEV_NAME,
 		.of_match_table = armv8_pmu_of_device_ids,
 	},
 	.probe		= armv8_pmu_device_probe,
 };
 
-static int __init register_armv8_pmu_driver(void)
-{
-	return platform_driver_register(&armv8_pmu_driver);
-}
-device_initcall(register_armv8_pmu_driver);
+builtin_platform_driver(armv8_pmu_driver);

arch/arm64/kernel/probes/decode-insn.c

@@ -16,6 +16,7 @@
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/module.h>
+#include <linux/kallsyms.h>
 #include <asm/kprobes.h>
 #include <asm/insn.h>
 #include <asm/sections.h>
@@ -122,7 +123,7 @@ arm_probe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 static bool __kprobes
 is_probed_address_atomic(kprobe_opcode_t *scan_start, kprobe_opcode_t *scan_end)
 {
-	while (scan_start > scan_end) {
+	while (scan_start >= scan_end) {
 		/*
 		 * atomic region starts from exclusive load and ends with
 		 * exclusive store.
@@ -142,33 +143,30 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
 {
 	enum kprobe_insn decoded;
 	kprobe_opcode_t insn = le32_to_cpu(*addr);
-	kprobe_opcode_t *scan_start = addr - 1;
-	kprobe_opcode_t *scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
-#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
-	struct module *mod;
-#endif
-
-	if (addr >= (kprobe_opcode_t *)_text &&
-	    scan_end < (kprobe_opcode_t *)_text)
-		scan_end = (kprobe_opcode_t *)_text;
-#if defined(CONFIG_MODULES) && defined(MODULES_VADDR)
-	else {
-		preempt_disable();
-		mod = __module_address((unsigned long)addr);
-		if (mod && within_module_init((unsigned long)addr, mod) &&
-			!within_module_init((unsigned long)scan_end, mod))
-			scan_end = (kprobe_opcode_t *)mod->init_layout.base;
-		else if (mod && within_module_core((unsigned long)addr, mod) &&
-			!within_module_core((unsigned long)scan_end, mod))
-			scan_end = (kprobe_opcode_t *)mod->core_layout.base;
-		preempt_enable();
+	kprobe_opcode_t *scan_end = NULL;
+	unsigned long size = 0, offset = 0;
+
+	/*
+	 * If there's a symbol defined in front of and near enough to
+	 * the probe address assume it is the entry point to this
+	 * code and use it to further limit how far back we search
+	 * when determining if we're in an atomic sequence. If we could
+	 * not find any symbol skip the atomic test altogether as we
+	 * could otherwise end up searching irrelevant text/literals.
+	 * KPROBES depends on KALLSYMS so this last case should never
+	 * happen.
+	 */
+	if (kallsyms_lookup_size_offset((unsigned long) addr, &size, &offset)) {
+		if (offset < (MAX_ATOMIC_CONTEXT_SIZE*sizeof(kprobe_opcode_t)))
+			scan_end = addr - (offset / sizeof(kprobe_opcode_t));
+		else
+			scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
 	}
-#endif
 	decoded = arm_probe_decode_insn(insn, asi);
 
-	if (decoded == INSN_REJECTED ||
-			is_probed_address_atomic(scan_start, scan_end))
-		return INSN_REJECTED;
+	if (decoded != INSN_REJECTED && scan_end)
+		if (is_probed_address_atomic(addr - 1, scan_end))
+			return INSN_REJECTED;
 
 	return decoded;
 }

arch/arm64/kernel/probes/kprobes.c

@@ -19,7 +19,7 @@
 #include <linux/kasan.h>
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/slab.h>
 #include <linux/stop_machine.h>
 #include <linux/stringify.h>
@@ -31,7 +31,7 @@
 #include <asm/insn.h>
 #include <asm/uaccess.h>
 #include <asm/irq.h>
-#include <asm-generic/sections.h>
+#include <asm/sections.h>
 
 #include "decode-insn.h"
 
@@ -166,13 +166,18 @@ static void __kprobes set_current_kprobe(struct kprobe *p)
 }
 
 /*
- * The D-flag (Debug mask) is set (masked) upon debug exception entry.
- * Kprobes needs to clear (unmask) D-flag -ONLY- in case of recursive
- * probe i.e. when probe hit from kprobe handler context upon
- * executing the pre/post handlers. In this case we return with
- * D-flag clear so that single-stepping can be carried-out.
- *
- * Leave D-flag set in all other cases.
+ * When PSTATE.D is set (masked), then software step exceptions can not be
+ * generated.
+ * SPSR's D bit shows the value of PSTATE.D immediately before the
+ * exception was taken. PSTATE.D is set while entering into any exception
+ * mode, however software clears it for any normal (none-debug-exception)
+ * mode in the exception entry. Therefore, when we are entering into kprobe
+ * breakpoint handler from any normal mode then SPSR.D bit is already
+ * cleared, however it is set when we are entering from any debug exception
+ * mode.
+ * Since we always need to generate single step exception after a kprobe
+ * breakpoint exception therefore we need to clear it unconditionally, when
+ * we become sure that the current breakpoint exception is for kprobe.
  */
 static void __kprobes
 spsr_set_debug_flag(struct pt_regs *regs, int mask)
@@ -245,10 +250,7 @@ static void __kprobes setup_singlestep(struct kprobe *p,
 
 		set_ss_context(kcb, slot);	/* mark pending ss */
 
-		if (kcb->kprobe_status == KPROBE_REENTER)
-			spsr_set_debug_flag(regs, 0);
-		else
-			WARN_ON(regs->pstate & PSR_D_BIT);
+		spsr_set_debug_flag(regs, 0);
 
 		/* IRQs and single stepping do not mix well. */
 		kprobes_save_local_irqflag(kcb, regs);
@@ -333,8 +335,6 @@ int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr)
 			BUG();
 
 		kernel_disable_single_step();
-		if (kcb->kprobe_status == KPROBE_REENTER)
-			spsr_set_debug_flag(regs, 1);
 
 		if (kcb->kprobe_status == KPROBE_REENTER)
 			restore_previous_kprobe(kcb);
@@ -457,9 +457,6 @@ kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr)
 		kprobes_restore_local_irqflag(kcb, regs);
 		kernel_disable_single_step();
 
-		if (kcb->kprobe_status == KPROBE_REENTER)
-			spsr_set_debug_flag(regs, 1);
-
 		post_kprobe_handler(kcb, regs);
 	}
 
@@ -543,9 +540,6 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
-	extern char __idmap_text_start[], __idmap_text_end[];
-	extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[];
-
 	if ((addr >= (unsigned long)__kprobes_text_start &&
 	    addr < (unsigned long)__kprobes_text_end) ||
 	    (addr >= (unsigned long)__entry_text_start &&

arch/arm64/kernel/process.c

@@ -202,7 +202,7 @@ void show_regs(struct pt_regs * regs)
 
 static void tls_thread_flush(void)
 {
-	asm ("msr tpidr_el0, xzr");
+	write_sysreg(0, tpidr_el0);
 
 	if (is_compat_task()) {
 		current->thread.tp_value = 0;
@@ -213,7 +213,7 @@ static void tls_thread_flush(void)
 		 * with a stale shadow state during context switch.
 		 */
 		barrier();
-		asm ("msr tpidrro_el0, xzr");
+		write_sysreg(0, tpidrro_el0);
 	}
 }
 
@@ -253,7 +253,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		 * Read the current TLS pointer from tpidr_el0 as it may be
 		 * out-of-sync with the saved value.
 		 */
-		asm("mrs %0, tpidr_el0" : "=r" (*task_user_tls(p)));
+		*task_user_tls(p) = read_sysreg(tpidr_el0);
 
 		if (stack_start) {
 			if (is_compat_thread(task_thread_info(p)))
@@ -289,17 +289,15 @@ static void tls_thread_switch(struct task_struct *next)
 {
 	unsigned long tpidr, tpidrro;
 
-	asm("mrs %0, tpidr_el0" : "=r" (tpidr));
+	tpidr = read_sysreg(tpidr_el0);
 	*task_user_tls(current) = tpidr;
 
 	tpidr = *task_user_tls(next);
 	tpidrro = is_compat_thread(task_thread_info(next)) ?
 		  next->thread.tp_value : 0;
 
-	asm(
-	"	msr	tpidr_el0, %0\n"
-	"	msr	tpidrro_el0, %1"
-	: : "r" (tpidr), "r" (tpidrro));
+	write_sysreg(tpidr, tpidr_el0);
+	write_sysreg(tpidrro, tpidrro_el0);
 }
 
 /* Restore the UAO state depending on next's addr_limit */

arch/arm64/kernel/relocate_kernel.S

@@ -34,7 +34,7 @@ ENTRY(arm64_relocate_new_kernel)
 	/* Setup the list loop variables. */
 	mov	x17, x1				/* x17 = kimage_start */
 	mov	x16, x0				/* x16 = kimage_head */
-	dcache_line_size x15, x0		/* x15 = dcache line size */
+	raw_dcache_line_size x15, x0		/* x15 = dcache line size */
 	mov	x14, xzr			/* x14 = entry ptr */
 	mov	x13, xzr			/* x13 = copy dest */
 

arch/arm64/kernel/setup.c

@@ -206,10 +206,15 @@ static void __init request_standard_resources(void)
 
 	for_each_memblock(memory, region) {
 		res = alloc_bootmem_low(sizeof(*res));
-		res->name  = "System RAM";
+		if (memblock_is_nomap(region)) {
+			res->name  = "reserved";
+			res->flags = IORESOURCE_MEM | IORESOURCE_BUSY;
+		} else {
+			res->name  = "System RAM";
+			res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
+		}
 		res->start = __pfn_to_phys(memblock_region_memory_base_pfn(region));
 		res->end = __pfn_to_phys(memblock_region_memory_end_pfn(region)) - 1;
-		res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY;
 
 		request_resource(&iomem_resource, res);
 
@@ -228,7 +233,7 @@ void __init setup_arch(char **cmdline_p)
 {
 	pr_info("Boot CPU: AArch64 Processor [%08x]\n", read_cpuid_id());
 
-	sprintf(init_utsname()->machine, ELF_PLATFORM);
+	sprintf(init_utsname()->machine, UTS_MACHINE);
 	init_mm.start_code = (unsigned long) _text;
 	init_mm.end_code   = (unsigned long) _etext;
 	init_mm.end_data   = (unsigned long) _edata;

arch/arm64/kernel/signal.c

@@ -402,15 +402,31 @@ static void do_signal(struct pt_regs *regs)
 asmlinkage void do_notify_resume(struct pt_regs *regs,
 				 unsigned int thread_flags)
 {
-	if (thread_flags & _TIF_SIGPENDING)
-		do_signal(regs);
-
-	if (thread_flags & _TIF_NOTIFY_RESUME) {
-		clear_thread_flag(TIF_NOTIFY_RESUME);
-		tracehook_notify_resume(regs);
-	}
-
-	if (thread_flags & _TIF_FOREIGN_FPSTATE)
-		fpsimd_restore_current_state();
+	/*
+	 * The assembly code enters us with IRQs off, but it hasn't
+	 * informed the tracing code of that for efficiency reasons.
+	 * Update the trace code with the current status.
+	 */
+	trace_hardirqs_off();
+	do {
+		if (thread_flags & _TIF_NEED_RESCHED) {
+			schedule();
+		} else {
+			local_irq_enable();
+
+			if (thread_flags & _TIF_SIGPENDING)
+				do_signal(regs);
+
+			if (thread_flags & _TIF_NOTIFY_RESUME) {
+				clear_thread_flag(TIF_NOTIFY_RESUME);
+				tracehook_notify_resume(regs);
+			}
+
+			if (thread_flags & _TIF_FOREIGN_FPSTATE)
+				fpsimd_restore_current_state();
+		}
 
+		local_irq_disable();
+		thread_flags = READ_ONCE(current_thread_info()->flags);
+	} while (thread_flags & _TIF_WORK_MASK);
 }

arch/arm64/kernel/sleep.S

@@ -73,10 +73,9 @@ ENTRY(__cpu_suspend_enter)
 	str	x2, [x0, #SLEEP_STACK_DATA_SYSTEM_REGS + CPU_CTX_SP]
 
 	/* find the mpidr_hash */
-	ldr	x1, =sleep_save_stash
-	ldr	x1, [x1]
+	ldr_l	x1, sleep_save_stash
 	mrs	x7, mpidr_el1
-	ldr	x9, =mpidr_hash
+	adr_l	x9, mpidr_hash
 	ldr	x10, [x9, #MPIDR_HASH_MASK]
 	/*
 	 * Following code relies on the struct mpidr_hash
@@ -95,36 +94,30 @@ ENTRY(__cpu_suspend_enter)
 	mov	x0, #1
 	ret
 ENDPROC(__cpu_suspend_enter)
-	.ltorg
 
+	.pushsection ".idmap.text", "ax"
 ENTRY(cpu_resume)
 	bl	el2_setup		// if in EL2 drop to EL1 cleanly
+	bl	__cpu_setup
 	/* enable the MMU early - so we can access sleep_save_stash by va */
-	adr_l	lr, __enable_mmu	/* __cpu_setup will return here */
-	adr_l	x27, _resume_switched	/* __enable_mmu will branch here */
-	adrp	x25, idmap_pg_dir
-	adrp	x26, swapper_pg_dir
-	b	__cpu_setup
-ENDPROC(cpu_resume)
-
-	.pushsection	".idmap.text", "ax"
-_resume_switched:
+	bl	__enable_mmu
 	ldr	x8, =_cpu_resume
 	br	x8
-ENDPROC(_resume_switched)
+ENDPROC(cpu_resume)
 	.ltorg
 	.popsection
 
 ENTRY(_cpu_resume)
 	mrs	x1, mpidr_el1
-	adrp	x8, mpidr_hash
-	add x8, x8, #:lo12:mpidr_hash // x8 = struct mpidr_hash phys address
-        /* retrieve mpidr_hash members to compute the hash */
+	adr_l	x8, mpidr_hash		// x8 = struct mpidr_hash virt address
+
+	/* retrieve mpidr_hash members to compute the hash */
 	ldr	x2, [x8, #MPIDR_HASH_MASK]
 	ldp	w3, w4, [x8, #MPIDR_HASH_SHIFTS]
 	ldp	w5, w6, [x8, #(MPIDR_HASH_SHIFTS + 8)]
 	compute_mpidr_hash x7, x3, x4, x5, x6, x1, x2
-        /* x7 contains hash index, let's use it to grab context pointer */
+
+	/* x7 contains hash index, let's use it to grab context pointer */
 	ldr_l	x0, sleep_save_stash
 	ldr	x0, [x0, x7, lsl #3]
 	add	x29, x0, #SLEEP_STACK_DATA_CALLEE_REGS

arch/arm64/kernel/smp.c

@@ -233,7 +233,7 @@ asmlinkage void secondary_start_kernel(void)
 	 * this CPU ticks all of those. If it doesn't, the CPU will
 	 * fail to come online.
 	 */
-	verify_local_cpu_capabilities();
+	check_local_cpu_capabilities();
 
 	if (cpu_ops[cpu]->cpu_postboot)
 		cpu_ops[cpu]->cpu_postboot();
@@ -431,8 +431,19 @@ void __init smp_cpus_done(unsigned int max_cpus)
 void __init smp_prepare_boot_cpu(void)
 {
 	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+	/*
+	 * Initialise the static keys early as they may be enabled by the
+	 * cpufeature code.
+	 */
+	jump_label_init();
 	cpuinfo_store_boot_cpu();
 	save_boot_cpu_run_el();
+	/*
+	 * Run the errata work around checks on the boot CPU, once we have
+	 * initialised the cpu feature infrastructure from
+	 * cpuinfo_store_boot_cpu() above.
+	 */
+	update_cpu_errata_workarounds();
 }
 
 static u64 __init of_get_cpu_mpidr(struct device_node *dn)
@@ -613,6 +624,7 @@ static void __init of_parse_and_init_cpus(void)
 			}
 
 			bootcpu_valid = true;
+			early_map_cpu_to_node(0, of_node_to_nid(dn));
 
 			/*
 			 * cpu_logical_map has already been

arch/arm64/kernel/smp_spin_table.c

@@ -29,7 +29,8 @@
 #include <asm/smp_plat.h>
 
 extern void secondary_holding_pen(void);
-volatile unsigned long secondary_holding_pen_release = INVALID_HWID;
+volatile unsigned long __section(".mmuoff.data.read")
+secondary_holding_pen_release = INVALID_HWID;
 
 static phys_addr_t cpu_release_addr[NR_CPUS];
 

arch/arm64/kernel/stacktrace.c

@@ -43,6 +43,9 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	unsigned long fp = frame->fp;
 	unsigned long irq_stack_ptr;
 
+	if (!tsk)
+		tsk = current;
+
 	/*
 	 * Switching between stacks is valid when tracing current and in
 	 * non-preemptible context.
@@ -67,7 +70,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
-	if (tsk && tsk->ret_stack &&
+	if (tsk->ret_stack &&
 			(frame->pc == (unsigned long)return_to_handler)) {
 		/*
 		 * This is a case where function graph tracer has
@@ -152,6 +155,27 @@ static int save_trace(struct stackframe *frame, void *d)
 	return trace->nr_entries >= trace->max_entries;
 }
 
+void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
+{
+	struct stack_trace_data data;
+	struct stackframe frame;
+
+	data.trace = trace;
+	data.skip = trace->skip;
+	data.no_sched_functions = 0;
+
+	frame.fp = regs->regs[29];
+	frame.sp = regs->sp;
+	frame.pc = regs->pc;
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	frame.graph = current->curr_ret_stack;
+#endif
+
+	walk_stackframe(current, &frame, save_trace, &data);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+
 void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 {
 	struct stack_trace_data data;

arch/arm64/kernel/suspend.c

@@ -23,8 +23,8 @@ unsigned long *sleep_save_stash;
  * time the notifier runs debug exceptions might have been enabled already,
  * with HW breakpoints registers content still in an unknown state.
  */
-static void (*hw_breakpoint_restore)(void *);
-void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
+static int (*hw_breakpoint_restore)(unsigned int);
+void __init cpu_suspend_set_dbg_restorer(int (*hw_bp_restore)(unsigned int))
 {
 	/* Prevent multiple restore hook initializations */
 	if (WARN_ON(hw_breakpoint_restore))
@@ -34,6 +34,8 @@ void __init cpu_suspend_set_dbg_restorer(void (*hw_bp_restore)(void *))
 
 void notrace __cpu_suspend_exit(void)
 {
+	unsigned int cpu = smp_processor_id();
+
 	/*
 	 * We are resuming from reset with the idmap active in TTBR0_EL1.
 	 * We must uninstall the idmap and restore the expected MMU
@@ -45,7 +47,7 @@ void notrace __cpu_suspend_exit(void)
 	 * Restore per-cpu offset before any kernel
 	 * subsystem relying on it has a chance to run.
 	 */
-	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
+	set_my_cpu_offset(per_cpu_offset(cpu));
 
 	/*
 	 * Restore HW breakpoint registers to sane values
@@ -53,7 +55,7 @@ void notrace __cpu_suspend_exit(void)
 	 * through local_dbg_restore.
 	 */
 	if (hw_breakpoint_restore)
-		hw_breakpoint_restore(NULL);
+		hw_breakpoint_restore(cpu);
 }
 
 /*

arch/arm64/kernel/sys_compat.c

@@ -94,7 +94,7 @@ long compat_arm_syscall(struct pt_regs *regs)
 		 * See comment in tls_thread_flush.
 		 */
 		barrier();
-		asm ("msr tpidrro_el0, %0" : : "r" (regs->regs[0]));
+		write_sysreg(regs->regs[0], tpidrro_el0);
 		return 0;
 
 	default:

arch/arm64/kernel/traps.c

@@ -142,6 +142,11 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 	unsigned long irq_stack_ptr;
 	int skip;
 
+	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
+
+	if (!tsk)
+		tsk = current;
+
 	/*
 	 * Switching between stacks is valid when tracing current and in
 	 * non-preemptible context.
@@ -151,11 +156,6 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 	else
 		irq_stack_ptr = 0;
 
-	pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk);
-
-	if (!tsk)
-		tsk = current;
-
 	if (tsk == current) {
 		frame.fp = (unsigned long)__builtin_frame_address(0);
 		frame.sp = current_stack_pointer;
@@ -447,36 +447,29 @@ void cpu_enable_cache_maint_trap(void *__unused)
 		: "=r" (res)					\
 		: "r" (address), "i" (-EFAULT) )
 
-asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
+static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 {
 	unsigned long address;
-	int ret;
-
-	/* if this is a write with: Op0=1, Op2=1, Op1=3, CRn=7 */
-	if ((esr & 0x01fffc01) == 0x0012dc00) {
-		int rt = (esr >> 5) & 0x1f;
-		int crm = (esr >> 1) & 0x0f;
+	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+	int crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT;
+	int ret = 0;
 
-		address = (rt == 31) ? 0 : regs->regs[rt];
+	address = (rt == 31) ? 0 : regs->regs[rt];
 
-		switch (crm) {
-		case 11:		/* DC CVAU, gets promoted */
-			__user_cache_maint("dc civac", address, ret);
-			break;
-		case 10:		/* DC CVAC, gets promoted */
-			__user_cache_maint("dc civac", address, ret);
-			break;
-		case 14:		/* DC CIVAC */
-			__user_cache_maint("dc civac", address, ret);
-			break;
-		case 5:			/* IC IVAU */
-			__user_cache_maint("ic ivau", address, ret);
-			break;
-		default:
-			force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
-			return;
-		}
-	} else {
+	switch (crm) {
+	case ESR_ELx_SYS64_ISS_CRM_DC_CVAU:	/* DC CVAU, gets promoted */
+		__user_cache_maint("dc civac", address, ret);
+		break;
+	case ESR_ELx_SYS64_ISS_CRM_DC_CVAC:	/* DC CVAC, gets promoted */
+		__user_cache_maint("dc civac", address, ret);
+		break;
+	case ESR_ELx_SYS64_ISS_CRM_DC_CIVAC:	/* DC CIVAC */
+		__user_cache_maint("dc civac", address, ret);
+		break;
+	case ESR_ELx_SYS64_ISS_CRM_IC_IVAU:	/* IC IVAU */
+		__user_cache_maint("ic ivau", address, ret);
+		break;
+	default:
 		force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
 		return;
 	}
@@ -487,6 +480,48 @@ asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
 		regs->pc += 4;
 }
 
+static void ctr_read_handler(unsigned int esr, struct pt_regs *regs)
+{
+	int rt = (esr & ESR_ELx_SYS64_ISS_RT_MASK) >> ESR_ELx_SYS64_ISS_RT_SHIFT;
+
+	regs->regs[rt] = arm64_ftr_reg_ctrel0.sys_val;
+	regs->pc += 4;
+}
+
+struct sys64_hook {
+	unsigned int esr_mask;
+	unsigned int esr_val;
+	void (*handler)(unsigned int esr, struct pt_regs *regs);
+};
+
+static struct sys64_hook sys64_hooks[] = {
+	{
+		.esr_mask = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_MASK,
+		.esr_val = ESR_ELx_SYS64_ISS_EL0_CACHE_OP_VAL,
+		.handler = user_cache_maint_handler,
+	},
+	{
+		/* Trap read access to CTR_EL0 */
+		.esr_mask = ESR_ELx_SYS64_ISS_SYS_OP_MASK,
+		.esr_val = ESR_ELx_SYS64_ISS_SYS_CTR_READ,
+		.handler = ctr_read_handler,
+	},
+	{},
+};
+
+asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs)
+{
+	struct sys64_hook *hook;
+
+	for (hook = sys64_hooks; hook->handler; hook++)
+		if ((hook->esr_mask & esr) == hook->esr_val) {
+			hook->handler(esr, regs);
+			return;
+		}
+
+	force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0);
+}
+
 long compat_arm_syscall(struct pt_regs *regs);
 
 asmlinkage long do_ni_syscall(struct pt_regs *regs)

arch/arm64/kernel/vdso.c

@@ -18,12 +18,13 @@
  * Author: Will Deacon <will.deacon@arm.com>
  */
 
-#include <linux/kernel.h>
+#include <linux/cache.h>
 #include <linux/clocksource.h>
 #include <linux/elf.h>
 #include <linux/err.h>
 #include <linux/errno.h>
 #include <linux/gfp.h>
+#include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/signal.h>
@@ -37,8 +38,7 @@
 #include <asm/vdso_datapage.h>
 
 extern char vdso_start, vdso_end;
-static unsigned long vdso_pages;
-static struct page **vdso_pagelist;
+static unsigned long vdso_pages __ro_after_init;
 
 /*
  * The vDSO data page.
@@ -53,9 +53,9 @@ struct vdso_data *vdso_data = &vdso_data_store.data;
 /*
  * Create and map the vectors page for AArch32 tasks.
  */
-static struct page *vectors_page[1];
+static struct page *vectors_page[1] __ro_after_init;
 
-static int alloc_vectors_page(void)
+static int __init alloc_vectors_page(void)
 {
 	extern char __kuser_helper_start[], __kuser_helper_end[];
 	extern char __aarch32_sigret_code_start[], __aarch32_sigret_code_end[];
@@ -88,7 +88,7 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long addr = AARCH32_VECTORS_BASE;
-	static struct vm_special_mapping spec = {
+	static const struct vm_special_mapping spec = {
 		.name	= "[vectors]",
 		.pages	= vectors_page,
 
@@ -110,11 +110,19 @@ int aarch32_setup_vectors_page(struct linux_binprm *bprm, int uses_interp)
 }
 #endif /* CONFIG_COMPAT */
 
-static struct vm_special_mapping vdso_spec[2];
+static struct vm_special_mapping vdso_spec[2] __ro_after_init = {
+	{
+		.name	= "[vvar]",
+	},
+	{
+		.name	= "[vdso]",
+	},
+};
 
 static int __init vdso_init(void)
 {
 	int i;
+	struct page **vdso_pagelist;
 
 	if (memcmp(&vdso_start, "\177ELF", 4)) {
 		pr_err("vDSO is not a valid ELF object!\n");
@@ -138,16 +146,8 @@ static int __init vdso_init(void)
 	for (i = 0; i < vdso_pages; i++)
 		vdso_pagelist[i + 1] = pfn_to_page(PHYS_PFN(__pa(&vdso_start)) + i);
 
-	/* Populate the special mapping structures */
-	vdso_spec[0] = (struct vm_special_mapping) {
-		.name	= "[vvar]",
-		.pages	= vdso_pagelist,
-	};
-
-	vdso_spec[1] = (struct vm_special_mapping) {
-		.name	= "[vdso]",
-		.pages	= &vdso_pagelist[1],
-	};
+	vdso_spec[0].pages = &vdso_pagelist[0];
+	vdso_spec[1].pages = &vdso_pagelist[1];
 
 	return 0;
 }
@@ -201,7 +201,7 @@ up_fail:
  */
 void update_vsyscall(struct timekeeper *tk)
 {
-	u32 use_syscall = strcmp(tk->tkr_mono.clock->name, "arch_sys_counter");
+	u32 use_syscall = !tk->tkr_mono.clock->archdata.vdso_direct;
 
 	++vdso_data->tb_seq_count;
 	smp_wmb();

arch/arm64/kernel/vmlinux.lds.S

@@ -185,6 +185,25 @@ SECTIONS
 	_data = .;
 	_sdata = .;
 	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+
+	/*
+	 * Data written with the MMU off but read with the MMU on requires
+	 * cache lines to be invalidated, discarding up to a Cache Writeback
+	 * Granule (CWG) of data from the cache. Keep the section that
+	 * requires this type of maintenance to be in its own Cache Writeback
+	 * Granule (CWG) area so the cache maintenance operations don't
+	 * interfere with adjacent data.
+	 */
+	.mmuoff.data.write : ALIGN(SZ_2K) {
+		__mmuoff_data_start = .;
+		*(.mmuoff.data.write)
+	}
+	. = ALIGN(SZ_2K);
+	.mmuoff.data.read : {
+		*(.mmuoff.data.read)
+		__mmuoff_data_end = .;
+	}
+
 	PECOFF_EDATA_PADDING
 	_edata = .;
 

arch/arm64/kvm/hyp.S

@@ -46,10 +46,6 @@ alternative_if_not ARM64_HAS_VIRT_HOST_EXTN
 	hvc	#0
 	ldr     lr, [sp], #16
 	ret
-alternative_else
+alternative_else_nop_endif
 	b	__vhe_hyp_call
-	nop
-	nop
-	nop
-alternative_endif
 ENDPROC(__kvm_call_hyp)

arch/arm64/kvm/sys_regs.c

@@ -36,6 +36,7 @@
 #include <asm/kvm_host.h>
 #include <asm/kvm_mmu.h>
 #include <asm/perf_event.h>
+#include <asm/sysreg.h>
 
 #include <trace/events/kvm.h>
 
@@ -67,11 +68,9 @@ static u32 get_ccsidr(u32 csselr)
 
 	/* Make sure noone else changes CSSELR during this! */
 	local_irq_disable();
-	/* Put value into CSSELR */
-	asm volatile("msr csselr_el1, %x0" : : "r" (csselr));
+	write_sysreg(csselr, csselr_el1);
 	isb();
-	/* Read result out of CCSIDR */
-	asm volatile("mrs %0, ccsidr_el1" : "=r" (ccsidr));
+	ccsidr = read_sysreg(ccsidr_el1);
 	local_irq_enable();
 
 	return ccsidr;
@@ -174,9 +173,7 @@ static bool trap_dbgauthstatus_el1(struct kvm_vcpu *vcpu,
 	if (p->is_write) {
 		return ignore_write(vcpu, p);
 	} else {
-		u32 val;
-		asm volatile("mrs %0, dbgauthstatus_el1" : "=r" (val));
-		p->regval = val;
+		p->regval = read_sysreg(dbgauthstatus_el1);
 		return true;
 	}
 }
@@ -429,10 +426,7 @@ static void reset_wcr(struct kvm_vcpu *vcpu,
 
 static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	u64 amair;
-
-	asm volatile("mrs %0, amair_el1\n" : "=r" (amair));
-	vcpu_sys_reg(vcpu, AMAIR_EL1) = amair;
+	vcpu_sys_reg(vcpu, AMAIR_EL1) = read_sysreg(amair_el1);
 }
 
 static void reset_mpidr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
@@ -456,8 +450,9 @@ static void reset_pmcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
 	u64 pmcr, val;
 
-	asm volatile("mrs %0, pmcr_el0\n" : "=r" (pmcr));
-	/* Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) is reset to UNKNOWN
+	pmcr = read_sysreg(pmcr_el0);
+	/*
+	 * Writable bits of PMCR_EL0 (ARMV8_PMU_PMCR_MASK) are reset to UNKNOWN
 	 * except PMCR.E resetting to zero.
 	 */
 	val = ((pmcr & ~ARMV8_PMU_PMCR_MASK)
@@ -557,9 +552,9 @@ static bool access_pmceid(struct kvm_vcpu *vcpu, struct sys_reg_params *p,
 		return false;
 
 	if (!(p->Op2 & 1))
-		asm volatile("mrs %0, pmceid0_el0\n" : "=r" (pmceid));
+		pmceid = read_sysreg(pmceid0_el0);
 	else
-		asm volatile("mrs %0, pmceid1_el0\n" : "=r" (pmceid));
+		pmceid = read_sysreg(pmceid1_el0);
 
 	p->regval = pmceid;
 
@@ -1833,11 +1828,7 @@ static const struct sys_reg_desc *index_to_sys_reg_desc(struct kvm_vcpu *vcpu,
 	static void get_##reg(struct kvm_vcpu *v,			\
 			      const struct sys_reg_desc *r)		\
 	{								\
-		u64 val;						\
-									\
-		asm volatile("mrs %0, " __stringify(reg) "\n"		\
-			     : "=r" (val));				\
-		((struct sys_reg_desc *)r)->val = val;			\
+		((struct sys_reg_desc *)r)->val = read_sysreg(reg);	\
 	}
 
 FUNCTION_INVARIANT(midr_el1)

arch/arm64/kvm/sys_regs_generic_v8.c

@@ -26,6 +26,7 @@
 #include <asm/kvm_host.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_coproc.h>
+#include <asm/sysreg.h>
 #include <linux/init.h>
 
 #include "sys_regs.h"
@@ -43,10 +44,7 @@ static bool access_actlr(struct kvm_vcpu *vcpu,
 
 static void reset_actlr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r)
 {
-	u64 actlr;
-
-	asm volatile("mrs %0, actlr_el1\n" : "=r" (actlr));
-	vcpu_sys_reg(vcpu, ACTLR_EL1) = actlr;
+	vcpu_sys_reg(vcpu, ACTLR_EL1) = read_sysreg(actlr_el1);
 }
 
 /*

arch/arm64/lib/copy_page.S

@@ -29,14 +29,11 @@
  *	x1 - src
  */
 ENTRY(copy_page)
-alternative_if_not ARM64_HAS_NO_HW_PREFETCH
-	nop
-	nop
-alternative_else
+alternative_if ARM64_HAS_NO_HW_PREFETCH
 	# Prefetch two cache lines ahead.
 	prfm    pldl1strm, [x1, #128]
 	prfm    pldl1strm, [x1, #256]
-alternative_endif
+alternative_else_nop_endif
 
 	ldp	x2, x3, [x1]
 	ldp	x4, x5, [x1, #16]
@@ -52,11 +49,9 @@ alternative_endif
 1:
 	subs	x18, x18, #128
 
-alternative_if_not ARM64_HAS_NO_HW_PREFETCH
-	nop
-alternative_else
+alternative_if ARM64_HAS_NO_HW_PREFETCH
 	prfm    pldl1strm, [x1, #384]
-alternative_endif
+alternative_else_nop_endif
 
 	stnp	x2, x3, [x0]
 	ldp	x2, x3, [x1]

arch/arm64/mm/cache.S

@@ -105,19 +105,20 @@ ENTRY(__clean_dcache_area_pou)
 ENDPROC(__clean_dcache_area_pou)
 
 /*
- *	__inval_cache_range(start, end)
- *	- start   - start address of region
- *	- end     - end address of region
+ *	__dma_inv_area(start, size)
+ *	- start   - virtual start address of region
+ *	- size    - size in question
  */
-ENTRY(__inval_cache_range)
+__dma_inv_area:
+	add	x1, x1, x0
 	/* FALLTHROUGH */
 
 /*
- *	__dma_inv_range(start, end)
- *	- start   - virtual start address of region
- *	- end     - virtual end address of region
+ *	__inval_cache_range(start, end)
+ *	- start   - start address of region
+ *	- end     - end address of region
  */
-__dma_inv_range:
+ENTRY(__inval_cache_range)
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	tst	x1, x3				// end cache line aligned?
@@ -136,46 +137,43 @@ __dma_inv_range:
 	dsb	sy
 	ret
 ENDPIPROC(__inval_cache_range)
-ENDPROC(__dma_inv_range)
+ENDPROC(__dma_inv_area)
+
+/*
+ *	__clean_dcache_area_poc(kaddr, size)
+ *
+ * 	Ensure that any D-cache lines for the interval [kaddr, kaddr+size)
+ * 	are cleaned to the PoC.
+ *
+ *	- kaddr   - kernel address
+ *	- size    - size in question
+ */
+ENTRY(__clean_dcache_area_poc)
+	/* FALLTHROUGH */
 
 /*
- *	__dma_clean_range(start, end)
+ *	__dma_clean_area(start, size)
  *	- start   - virtual start address of region
- *	- end     - virtual end address of region
+ *	- size    - size in question
  */
-__dma_clean_range:
-	dcache_line_size x2, x3
-	sub	x3, x2, #1
-	bic	x0, x0, x3
-1:
-alternative_if_not ARM64_WORKAROUND_CLEAN_CACHE
-	dc	cvac, x0
-alternative_else
-	dc	civac, x0
-alternative_endif
-	add	x0, x0, x2
-	cmp	x0, x1
-	b.lo	1b
-	dsb	sy
+__dma_clean_area:
+	dcache_by_line_op cvac, sy, x0, x1, x2, x3
 	ret
-ENDPROC(__dma_clean_range)
+ENDPIPROC(__clean_dcache_area_poc)
+ENDPROC(__dma_clean_area)
 
 /*
- *	__dma_flush_range(start, end)
+ *	__dma_flush_area(start, size)
+ *
+ *	clean & invalidate D / U line
+ *
  *	- start   - virtual start address of region
- *	- end     - virtual end address of region
+ *	- size    - size in question
  */
-ENTRY(__dma_flush_range)
-	dcache_line_size x2, x3
-	sub	x3, x2, #1
-	bic	x0, x0, x3
-1:	dc	civac, x0			// clean & invalidate D / U line
-	add	x0, x0, x2
-	cmp	x0, x1
-	b.lo	1b
-	dsb	sy
+ENTRY(__dma_flush_area)
+	dcache_by_line_op civac, sy, x0, x1, x2, x3
 	ret
-ENDPIPROC(__dma_flush_range)
+ENDPIPROC(__dma_flush_area)
 
 /*
  *	__dma_map_area(start, size, dir)
@@ -184,10 +182,9 @@ ENDPIPROC(__dma_flush_range)
  *	- dir	- DMA direction
  */
 ENTRY(__dma_map_area)
-	add	x1, x1, x0
 	cmp	w2, #DMA_FROM_DEVICE
-	b.eq	__dma_inv_range
-	b	__dma_clean_range
+	b.eq	__dma_inv_area
+	b	__dma_clean_area
 ENDPIPROC(__dma_map_area)
 
 /*
@@ -197,8 +194,7 @@ ENDPIPROC(__dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(__dma_unmap_area)
-	add	x1, x1, x0
 	cmp	w2, #DMA_TO_DEVICE
-	b.ne	__dma_inv_range
+	b.ne	__dma_inv_area
 	ret
 ENDPIPROC(__dma_unmap_area)

arch/arm64/mm/dma-mapping.c

@@ -20,6 +20,7 @@
 #include <linux/gfp.h>
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
+#include <linux/cache.h>
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/genalloc.h>
@@ -30,7 +31,7 @@
 
 #include <asm/cacheflush.h>
 
-static int swiotlb __read_mostly;
+static int swiotlb __ro_after_init;
 
 static pgprot_t __get_dma_pgprot(unsigned long attrs, pgprot_t prot,
 				 bool coherent)
@@ -168,7 +169,7 @@ static void *__dma_alloc(struct device *dev, size_t size,
 		return ptr;
 
 	/* remove any dirty cache lines on the kernel alias */
-	__dma_flush_range(ptr, ptr + size);
+	__dma_flush_area(ptr, size);
 
 	/* create a coherent mapping */
 	page = virt_to_page(ptr);
@@ -387,7 +388,7 @@ static int __init atomic_pool_init(void)
 		void *page_addr = page_address(page);
 
 		memset(page_addr, 0, atomic_pool_size);
-		__dma_flush_range(page_addr, page_addr + atomic_pool_size);
+		__dma_flush_area(page_addr, atomic_pool_size);
 
 		atomic_pool = gen_pool_create(PAGE_SHIFT, -1);
 		if (!atomic_pool)
@@ -548,7 +549,7 @@ fs_initcall(dma_debug_do_init);
 /* Thankfully, all cache ops are by VA so we can ignore phys here */
 static void flush_page(struct device *dev, const void *virt, phys_addr_t phys)
 {
-	__dma_flush_range(virt, virt + PAGE_SIZE);
+	__dma_flush_area(virt, PAGE_SIZE);
 }
 
 static void *__iommu_alloc_attrs(struct device *dev, size_t size,

arch/arm64/mm/extable.c

@@ -2,7 +2,7 @@
  * Based on arch/arm/mm/extable.c
  */
 
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/uaccess.h>
 
 int fixup_exception(struct pt_regs *regs)

arch/arm64/mm/fault.c

@@ -18,7 +18,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <linux/module.h>
+#include <linux/extable.h>
 #include <linux/signal.h>
 #include <linux/mm.h>
 #include <linux/hardirq.h>
@@ -251,8 +251,7 @@ static int __do_page_fault(struct mm_struct *mm, unsigned long addr,
 good_area:
 	/*
 	 * Check that the permissions on the VMA allow for the fault which
-	 * occurred. If we encountered a write or exec fault, we must have
-	 * appropriate permissions, otherwise we allow any permission.
+	 * occurred.
 	 */
 	if (!(vma->vm_flags & vm_flags)) {
 		fault = VM_FAULT_BADACCESS;
@@ -288,7 +287,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 	struct task_struct *tsk;
 	struct mm_struct *mm;
 	int fault, sig, code;
-	unsigned long vm_flags = VM_READ | VM_WRITE | VM_EXEC;
+	unsigned long vm_flags = VM_READ | VM_WRITE;
 	unsigned int mm_flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
 
 	if (notify_page_fault(regs, esr))

arch/arm64/mm/flush.c

@@ -25,8 +25,6 @@
 #include <asm/cachetype.h>
 #include <asm/tlbflush.h>
 
-#include "mm.h"
-
 void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
 		       unsigned long end)
 {

arch/arm64/mm/init.c

@@ -23,6 +23,7 @@
 #include <linux/swap.h>
 #include <linux/init.h>
 #include <linux/bootmem.h>
+#include <linux/cache.h>
 #include <linux/mman.h>
 #include <linux/nodemask.h>
 #include <linux/initrd.h>
@@ -34,6 +35,7 @@
 #include <linux/dma-contiguous.h>
 #include <linux/efi.h>
 #include <linux/swiotlb.h>
+#include <linux/vmalloc.h>
 
 #include <asm/boot.h>
 #include <asm/fixmap.h>
@@ -47,16 +49,14 @@
 #include <asm/tlb.h>
 #include <asm/alternative.h>
 
-#include "mm.h"
-
 /*
  * We need to be able to catch inadvertent references to memstart_addr
  * that occur (potentially in generic code) before arm64_memblock_init()
  * executes, which assigns it its actual value. So use a default value
  * that cannot be mistaken for a real physical address.
  */
-s64 memstart_addr __read_mostly = -1;
-phys_addr_t arm64_dma_phys_limit __read_mostly;
+s64 memstart_addr __ro_after_init = -1;
+phys_addr_t arm64_dma_phys_limit __ro_after_init;
 
 #ifdef CONFIG_BLK_DEV_INITRD
 static int __init early_initrd(char *p)
@@ -485,7 +485,12 @@ void free_initmem(void)
 {
 	free_reserved_area(__va(__pa(__init_begin)), __va(__pa(__init_end)),
 			   0, "unused kernel");
-	fixup_init();
+	/*
+	 * Unmap the __init region but leave the VM area in place. This
+	 * prevents the region from being reused for kernel modules, which
+	 * is not supported by kallsyms.
+	 */
+	unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
 }
 
 #ifdef CONFIG_BLK_DEV_INITRD

arch/arm64/mm/mm.h

@@ -1,2 +0,0 @@
-
-void fixup_init(void);

arch/arm64/mm/mmu.c

@@ -17,6 +17,7 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#include <linux/cache.h>
 #include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
@@ -42,11 +43,9 @@
 #include <asm/memblock.h>
 #include <asm/mmu_context.h>
 
-#include "mm.h"
-
 u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
 
-u64 kimage_voffset __read_mostly;
+u64 kimage_voffset __ro_after_init;
 EXPORT_SYMBOL(kimage_voffset);
 
 /*
@@ -399,16 +398,6 @@ void mark_rodata_ro(void)
 			    section_size, PAGE_KERNEL_RO);
 }
 
-void fixup_init(void)
-{
-	/*
-	 * Unmap the __init region but leave the VM area in place. This
-	 * prevents the region from being reused for kernel modules, which
-	 * is not supported by kallsyms.
-	 */
-	unmap_kernel_range((u64)__init_begin, (u64)(__init_end - __init_begin));
-}
-
 static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 				      pgprot_t prot, struct vm_struct *vma)
 {

arch/arm64/mm/numa.c

@@ -17,6 +17,8 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#define pr_fmt(fmt) "NUMA: " fmt
+
 #include <linux/acpi.h>
 #include <linux/bootmem.h>
 #include <linux/memblock.h>
@@ -24,6 +26,7 @@
 #include <linux/of.h>
 
 #include <asm/acpi.h>
+#include <asm/sections.h>
 
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
@@ -38,10 +41,9 @@ static __init int numa_parse_early_param(char *opt)
 {
 	if (!opt)
 		return -EINVAL;
-	if (!strncmp(opt, "off", 3)) {
-		pr_info("%s\n", "NUMA turned off");
+	if (!strncmp(opt, "off", 3))
 		numa_off = true;
-	}
+
 	return 0;
 }
 early_param("numa", numa_parse_early_param);
@@ -93,7 +95,6 @@ void numa_clear_node(unsigned int cpu)
  */
 static void __init setup_node_to_cpumask_map(void)
 {
-	unsigned int cpu;
 	int node;
 
 	/* setup nr_node_ids if not done yet */
@@ -106,11 +107,8 @@ static void __init setup_node_to_cpumask_map(void)
 		cpumask_clear(node_to_cpumask_map[node]);
 	}
 
-	for_each_possible_cpu(cpu)
-		set_cpu_numa_node(cpu, NUMA_NO_NODE);
-
 	/* cpumask_of_node() will now work */
-	pr_debug("NUMA: Node to cpumask map for %d nodes\n", nr_node_ids);
+	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
 }
 
 /*
@@ -118,18 +116,77 @@ static void __init setup_node_to_cpumask_map(void)
  */
 void numa_store_cpu_info(unsigned int cpu)
 {
-	map_cpu_to_node(cpu, numa_off ? 0 : cpu_to_node_map[cpu]);
+	map_cpu_to_node(cpu, cpu_to_node_map[cpu]);
 }
 
 void __init early_map_cpu_to_node(unsigned int cpu, int nid)
 {
 	/* fallback to node 0 */
-	if (nid < 0 || nid >= MAX_NUMNODES)
+	if (nid < 0 || nid >= MAX_NUMNODES || numa_off)
 		nid = 0;
 
 	cpu_to_node_map[cpu] = nid;
+
+	/*
+	 * We should set the numa node of cpu0 as soon as possible, because it
+	 * has already been set up online before. cpu_to_node(0) will soon be
+	 * called.
+	 */
+	if (!cpu)
+		set_cpu_numa_node(cpu, nid);
+}
+
+#ifdef CONFIG_HAVE_SETUP_PER_CPU_AREA
+unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
+EXPORT_SYMBOL(__per_cpu_offset);
+
+static int __init early_cpu_to_node(int cpu)
+{
+	return cpu_to_node_map[cpu];
+}
+
+static int __init pcpu_cpu_distance(unsigned int from, unsigned int to)
+{
+	return node_distance(from, to);
 }
 
+static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size,
+				       size_t align)
+{
+	int nid = early_cpu_to_node(cpu);
+
+	return  memblock_virt_alloc_try_nid(size, align,
+			__pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid);
+}
+
+static void __init pcpu_fc_free(void *ptr, size_t size)
+{
+	memblock_free_early(__pa(ptr), size);
+}
+
+void __init setup_per_cpu_areas(void)
+{
+	unsigned long delta;
+	unsigned int cpu;
+	int rc;
+
+	/*
+	 * Always reserve area for module percpu variables.  That's
+	 * what the legacy allocator did.
+	 */
+	rc = pcpu_embed_first_chunk(PERCPU_MODULE_RESERVE,
+				    PERCPU_DYNAMIC_RESERVE, PAGE_SIZE,
+				    pcpu_cpu_distance,
+				    pcpu_fc_alloc, pcpu_fc_free);
+	if (rc < 0)
+		panic("Failed to initialize percpu areas.");
+
+	delta = (unsigned long)pcpu_base_addr - (unsigned long)__per_cpu_start;
+	for_each_possible_cpu(cpu)
+		__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
+}
+#endif
+
 /**
  * numa_add_memblk - Set node id to memblk
  * @nid: NUMA node ID of the new memblk
@@ -145,13 +202,13 @@ int __init numa_add_memblk(int nid, u64 start, u64 end)
 
 	ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
 	if (ret < 0) {
-		pr_err("NUMA: memblock [0x%llx - 0x%llx] failed to add on node %d\n",
+		pr_err("memblock [0x%llx - 0x%llx] failed to add on node %d\n",
 			start, (end - 1), nid);
 		return ret;
 	}
 
 	node_set(nid, numa_nodes_parsed);
-	pr_info("NUMA: Adding memblock [0x%llx - 0x%llx] on node %d\n",
+	pr_info("Adding memblock [0x%llx - 0x%llx] on node %d\n",
 			start, (end - 1), nid);
 	return ret;
 }
@@ -166,19 +223,18 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
 	void *nd;
 	int tnid;
 
-	pr_info("NUMA: Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
-			nid, start_pfn << PAGE_SHIFT,
-			(end_pfn << PAGE_SHIFT) - 1);
+	pr_info("Initmem setup node %d [mem %#010Lx-%#010Lx]\n",
+		nid, start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1);
 
 	nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid);
 	nd = __va(nd_pa);
 
 	/* report and initialize */
-	pr_info("NUMA: NODE_DATA [mem %#010Lx-%#010Lx]\n",
+	pr_info("NODE_DATA [mem %#010Lx-%#010Lx]\n",
 		nd_pa, nd_pa + nd_size - 1);
 	tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT);
 	if (tnid != nid)
-		pr_info("NUMA: NODE_DATA(%d) on node %d\n", nid, tnid);
+		pr_info("NODE_DATA(%d) on node %d\n", nid, tnid);
 
 	node_data[nid] = nd;
 	memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
@@ -235,8 +291,7 @@ static int __init numa_alloc_distance(void)
 			numa_distance[i * numa_distance_cnt + j] = i == j ?
 				LOCAL_DISTANCE : REMOTE_DISTANCE;
 
-	pr_debug("NUMA: Initialized distance table, cnt=%d\n",
-			numa_distance_cnt);
+	pr_debug("Initialized distance table, cnt=%d\n", numa_distance_cnt);
 
 	return 0;
 }
@@ -257,20 +312,20 @@ static int __init numa_alloc_distance(void)
 void __init numa_set_distance(int from, int to, int distance)
 {
 	if (!numa_distance) {
-		pr_warn_once("NUMA: Warning: distance table not allocated yet\n");
+		pr_warn_once("Warning: distance table not allocated yet\n");
 		return;
 	}
 
 	if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
 			from < 0 || to < 0) {
-		pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
+		pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
 			    from, to, distance);
 		return;
 	}
 
 	if ((u8)distance != distance ||
 	    (from == to && distance != LOCAL_DISTANCE)) {
-		pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
+		pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
 			     from, to, distance);
 		return;
 	}
@@ -297,7 +352,7 @@ static int __init numa_register_nodes(void)
 	/* Check that valid nid is set to memblks */
 	for_each_memblock(memory, mblk)
 		if (mblk->nid == NUMA_NO_NODE || mblk->nid >= MAX_NUMNODES) {
-			pr_warn("NUMA: Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
+			pr_warn("Warning: invalid memblk node %d [mem %#010Lx-%#010Lx]\n",
 				mblk->nid, mblk->base,
 				mblk->base + mblk->size - 1);
 			return -EINVAL;
@@ -335,8 +390,10 @@ static int __init numa_init(int (*init_func)(void))
 	if (ret < 0)
 		return ret;
 
-	if (nodes_empty(numa_nodes_parsed))
+	if (nodes_empty(numa_nodes_parsed)) {
+		pr_info("No NUMA configuration found\n");
 		return -EINVAL;
+	}
 
 	ret = numa_register_nodes();
 	if (ret < 0)
@@ -344,10 +401,6 @@ static int __init numa_init(int (*init_func)(void))
 
 	setup_node_to_cpumask_map();
 
-	/* init boot processor */
-	cpu_to_node_map[0] = 0;
-	map_cpu_to_node(0, 0);
-
 	return 0;
 }
 
@@ -367,10 +420,8 @@ static int __init dummy_numa_init(void)
 
 	if (numa_off)
 		pr_info("NUMA disabled\n"); /* Forced off on command line. */
-	else
-		pr_info("No NUMA configuration found\n");
-	pr_info("NUMA: Faking a node at [mem %#018Lx-%#018Lx]\n",
-	       0LLU, PFN_PHYS(max_pfn) - 1);
+	pr_info("Faking a node at [mem %#018Lx-%#018Lx]\n",
+		0LLU, PFN_PHYS(max_pfn) - 1);
 
 	for_each_memblock(memory, mblk) {
 		ret = numa_add_memblk(0, mblk->base, mblk->base + mblk->size);

arch/arm64/mm/pageattr.c

@@ -139,4 +139,43 @@ void __kernel_map_pages(struct page *page, int numpages, int enable)
 					__pgprot(0),
 					__pgprot(PTE_VALID));
 }
-#endif
+#ifdef CONFIG_HIBERNATION
+/*
+ * When built with CONFIG_DEBUG_PAGEALLOC and CONFIG_HIBERNATION, this function
+ * is used to determine if a linear map page has been marked as not-valid by
+ * CONFIG_DEBUG_PAGEALLOC. Walk the page table and check the PTE_VALID bit.
+ * This is based on kern_addr_valid(), which almost does what we need.
+ *
+ * Because this is only called on the kernel linear map,  p?d_sect() implies
+ * p?d_present(). When debug_pagealloc is enabled, sections mappings are
+ * disabled.
+ */
+bool kernel_page_present(struct page *page)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+	unsigned long addr = (unsigned long)page_address(page);
+
+	pgd = pgd_offset_k(addr);
+	if (pgd_none(*pgd))
+		return false;
+
+	pud = pud_offset(pgd, addr);
+	if (pud_none(*pud))
+		return false;
+	if (pud_sect(*pud))
+		return true;
+
+	pmd = pmd_offset(pud, addr);
+	if (pmd_none(*pmd))
+		return false;
+	if (pmd_sect(*pmd))
+		return true;
+
+	pte = pte_offset_kernel(pmd, addr);
+	return pte_valid(*pte);
+}
+#endif /* CONFIG_HIBERNATION */
+#endif /* CONFIG_DEBUG_PAGEALLOC */

arch/arm64/mm/pgd.c

@@ -26,8 +26,6 @@
 #include <asm/page.h>
 #include <asm/tlbflush.h>
 
-#include "mm.h"
-
 static struct kmem_cache *pgd_cache;
 
 pgd_t *pgd_alloc(struct mm_struct *mm)

arch/arm64/mm/proc.S

@@ -83,6 +83,7 @@ ENDPROC(cpu_do_suspend)
  *
  * x0: Address of context pointer
  */
+	.pushsection ".idmap.text", "ax"
 ENTRY(cpu_do_resume)
 	ldp	x2, x3, [x0]
 	ldp	x4, x5, [x0, #16]
@@ -120,6 +121,7 @@ ENTRY(cpu_do_resume)
 	isb
 	ret
 ENDPROC(cpu_do_resume)
+	.popsection
 #endif
 
 /*
@@ -134,17 +136,12 @@ ENTRY(cpu_do_switch_mm)
 	bfi	x0, x1, #48, #16		// set the ASID
 	msr	ttbr0_el1, x0			// set TTBR0
 	isb
-alternative_if_not ARM64_WORKAROUND_CAVIUM_27456
-	ret
-	nop
-	nop
-	nop
-alternative_else
+alternative_if ARM64_WORKAROUND_CAVIUM_27456
 	ic	iallu
 	dsb	nsh
 	isb
+alternative_else_nop_endif
 	ret
-alternative_endif
 ENDPROC(cpu_do_switch_mm)
 
 	.pushsection ".idmap.text", "ax"
@@ -181,6 +178,7 @@ ENDPROC(idmap_cpu_replace_ttbr1)
  *	Initialise the processor for turning the MMU on.  Return in x0 the
  *	value of the SCTLR_EL1 register.
  */
+	.pushsection ".idmap.text", "ax"
 ENTRY(__cpu_setup)
 	tlbi	vmalle1				// Invalidate local TLB
 	dsb	nsh
@@ -266,3 +264,4 @@ ENDPROC(__cpu_setup)
 crval:
 	.word	0xfcffffff			// clear
 	.word	0x34d5d91d			// set
+	.popsection

drivers/clocksource/Kconfig

@@ -305,6 +305,16 @@ config ARM_ARCH_TIMER_EVTSTREAM
 	  This must be disabled for hardware validation purposes to detect any
 	  hardware anomalies of missing events.
 
+config FSL_ERRATUM_A008585
+	bool "Workaround for Freescale/NXP Erratum A-008585"
+	default y
+	depends on ARM_ARCH_TIMER && ARM64
+	help
+	  This option enables a workaround for Freescale/NXP Erratum
+	  A-008585 ("ARM generic timer may contain an erroneous
+	  value").  The workaround will only be active if the
+	  fsl,erratum-a008585 property is found in the timer node.
+
 config ARM_GLOBAL_TIMER
 	bool "Support for the ARM global timer" if COMPILE_TEST
 	select CLKSRC_OF if OF

drivers/clocksource/arm_arch_timer.c

@@ -94,6 +94,43 @@ early_param("clocksource.arm_arch_timer.evtstrm", early_evtstrm_cfg);
  * Architected system timer support.
  */
 
+#ifdef CONFIG_FSL_ERRATUM_A008585
+DEFINE_STATIC_KEY_FALSE(arch_timer_read_ool_enabled);
+EXPORT_SYMBOL_GPL(arch_timer_read_ool_enabled);
+
+static int fsl_a008585_enable = -1;
+
+static int __init early_fsl_a008585_cfg(char *buf)
+{
+	int ret;
+	bool val;
+
+	ret = strtobool(buf, &val);
+	if (ret)
+		return ret;
+
+	fsl_a008585_enable = val;
+	return 0;
+}
+early_param("clocksource.arm_arch_timer.fsl-a008585", early_fsl_a008585_cfg);
+
+u32 __fsl_a008585_read_cntp_tval_el0(void)
+{
+	return __fsl_a008585_read_reg(cntp_tval_el0);
+}
+
+u32 __fsl_a008585_read_cntv_tval_el0(void)
+{
+	return __fsl_a008585_read_reg(cntv_tval_el0);
+}
+
+u64 __fsl_a008585_read_cntvct_el0(void)
+{
+	return __fsl_a008585_read_reg(cntvct_el0);
+}
+EXPORT_SYMBOL(__fsl_a008585_read_cntvct_el0);
+#endif /* CONFIG_FSL_ERRATUM_A008585 */
+
 static __always_inline
 void arch_timer_reg_write(int access, enum arch_timer_reg reg, u32 val,
 			  struct clock_event_device *clk)
@@ -243,6 +280,40 @@ static __always_inline void set_next_event(const int access, unsigned long evt,
 	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
 }
 
+#ifdef CONFIG_FSL_ERRATUM_A008585
+static __always_inline void fsl_a008585_set_next_event(const int access,
+		unsigned long evt, struct clock_event_device *clk)
+{
+	unsigned long ctrl;
+	u64 cval = evt + arch_counter_get_cntvct();
+
+	ctrl = arch_timer_reg_read(access, ARCH_TIMER_REG_CTRL, clk);
+	ctrl |= ARCH_TIMER_CTRL_ENABLE;
+	ctrl &= ~ARCH_TIMER_CTRL_IT_MASK;
+
+	if (access == ARCH_TIMER_PHYS_ACCESS)
+		write_sysreg(cval, cntp_cval_el0);
+	else if (access == ARCH_TIMER_VIRT_ACCESS)
+		write_sysreg(cval, cntv_cval_el0);
+
+	arch_timer_reg_write(access, ARCH_TIMER_REG_CTRL, ctrl, clk);
+}
+
+static int fsl_a008585_set_next_event_virt(unsigned long evt,
+					   struct clock_event_device *clk)
+{
+	fsl_a008585_set_next_event(ARCH_TIMER_VIRT_ACCESS, evt, clk);
+	return 0;
+}
+
+static int fsl_a008585_set_next_event_phys(unsigned long evt,
+					   struct clock_event_device *clk)
+{
+	fsl_a008585_set_next_event(ARCH_TIMER_PHYS_ACCESS, evt, clk);
+	return 0;
+}
+#endif /* CONFIG_FSL_ERRATUM_A008585 */
+
 static int arch_timer_set_next_event_virt(unsigned long evt,
 					  struct clock_event_device *clk)
 {
@@ -271,6 +342,19 @@ static int arch_timer_set_next_event_phys_mem(unsigned long evt,
 	return 0;
 }
 
+static void fsl_a008585_set_sne(struct clock_event_device *clk)
+{
+#ifdef CONFIG_FSL_ERRATUM_A008585
+	if (!static_branch_unlikely(&arch_timer_read_ool_enabled))
+		return;
+
+	if (arch_timer_uses_ppi == VIRT_PPI)
+		clk->set_next_event = fsl_a008585_set_next_event_virt;
+	else
+		clk->set_next_event = fsl_a008585_set_next_event_phys;
+#endif
+}
+
 static void __arch_timer_setup(unsigned type,
 			       struct clock_event_device *clk)
 {
@@ -299,6 +383,8 @@ static void __arch_timer_setup(unsigned type,
 		default:
 			BUG();
 		}
+
+		fsl_a008585_set_sne(clk);
 	} else {
 		clk->features |= CLOCK_EVT_FEAT_DYNIRQ;
 		clk->name = "arch_mem_timer";
@@ -515,15 +601,19 @@ static void __init arch_counter_register(unsigned type)
 			arch_timer_read_counter = arch_counter_get_cntvct;
 		else
 			arch_timer_read_counter = arch_counter_get_cntpct;
-	} else {
-		arch_timer_read_counter = arch_counter_get_cntvct_mem;
 
-		/* If the clocksource name is "arch_sys_counter" the
-		 * VDSO will attempt to read the CP15-based counter.
-		 * Ensure this does not happen when CP15-based
-		 * counter is not available.
+		clocksource_counter.archdata.vdso_direct = true;
+
+#ifdef CONFIG_FSL_ERRATUM_A008585
+		/*
+		 * Don't use the vdso fastpath if errata require using
+		 * the out-of-line counter accessor.
 		 */
-		clocksource_counter.name = "arch_mem_counter";
+		if (static_branch_unlikely(&arch_timer_read_ool_enabled))
+			clocksource_counter.archdata.vdso_direct = false;
+#endif
+	} else {
+		arch_timer_read_counter = arch_counter_get_cntvct_mem;
 	}
 
 	start_count = arch_timer_read_counter();
@@ -800,6 +890,15 @@ static int __init arch_timer_of_init(struct device_node *np)
 
 	arch_timer_c3stop = !of_property_read_bool(np, "always-on");
 
+#ifdef CONFIG_FSL_ERRATUM_A008585
+	if (fsl_a008585_enable < 0)
+		fsl_a008585_enable = of_property_read_bool(np, "fsl,erratum-a008585");
+	if (fsl_a008585_enable) {
+		static_branch_enable(&arch_timer_read_ool_enabled);
+		pr_info("Enabling workaround for FSL erratum A-008585\n");
+	}
+#endif
+
 	/*
 	 * If we cannot rely on firmware initializing the timer registers then
 	 * we should use the physical timers instead.

drivers/of/of_numa.c

@@ -16,6 +16,8 @@
  * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 
+#define pr_fmt(fmt) "OF: NUMA: " fmt
+
 #include <linux/of.h>
 #include <linux/of_address.h>
 #include <linux/nodemask.h>
@@ -49,10 +51,9 @@ static void __init of_numa_parse_cpu_nodes(void)
 		if (r)
 			continue;
 
-		pr_debug("NUMA: CPU on %u\n", nid);
+		pr_debug("CPU on %u\n", nid);
 		if (nid >= MAX_NUMNODES)
-			pr_warn("NUMA: Node id %u exceeds maximum value\n",
-				nid);
+			pr_warn("Node id %u exceeds maximum value\n", nid);
 		else
 			node_set(nid, numa_nodes_parsed);
 	}
@@ -63,13 +64,9 @@ static int __init of_numa_parse_memory_nodes(void)
 	struct device_node *np = NULL;
 	struct resource rsrc;
 	u32 nid;
-	int r = 0;
-
-	for (;;) {
-		np = of_find_node_by_type(np, "memory");
-		if (!np)
-			break;
+	int i, r;
 
+	for_each_node_by_type(np, "memory") {
 		r = of_property_read_u32(np, "numa-node-id", &nid);
 		if (r == -EINVAL)
 			/*
@@ -78,27 +75,23 @@ static int __init of_numa_parse_memory_nodes(void)
 			 * "numa-node-id" property
 			 */
 			continue;
-		else if (r)
-			/* some other error */
-			break;
 
-		r = of_address_to_resource(np, 0, &rsrc);
-		if (r) {
-			pr_err("NUMA: bad reg property in memory node\n");
-			break;
+		if (nid >= MAX_NUMNODES) {
+			pr_warn("Node id %u exceeds maximum value\n", nid);
+			r = -EINVAL;
 		}
 
-		pr_debug("NUMA:  base = %llx len = %llx, node = %u\n",
-			 rsrc.start, rsrc.end - rsrc.start + 1, nid);
-
+		for (i = 0; !r && !of_address_to_resource(np, i, &rsrc); i++)
+			r = numa_add_memblk(nid, rsrc.start, rsrc.end + 1);
 
-		r = numa_add_memblk(nid, rsrc.start, rsrc.end + 1);
-		if (r)
-			break;
+		if (!i || r) {
+			of_node_put(np);
+			pr_err("bad property in memory node\n");
+			return r ? : -EINVAL;
+		}
 	}
-	of_node_put(np);
 
-	return r;
+	return 0;
 }
 
 static int __init of_numa_parse_distance_map_v1(struct device_node *map)
@@ -107,17 +100,17 @@ static int __init of_numa_parse_distance_map_v1(struct device_node *map)
 	int entry_count;
 	int i;
 
-	pr_info("NUMA: parsing numa-distance-map-v1\n");
+	pr_info("parsing numa-distance-map-v1\n");
 
 	matrix = of_get_property(map, "distance-matrix", NULL);
 	if (!matrix) {
-		pr_err("NUMA: No distance-matrix property in distance-map\n");
+		pr_err("No distance-matrix property in distance-map\n");
 		return -EINVAL;
 	}
 
 	entry_count = of_property_count_u32_elems(map, "distance-matrix");
 	if (entry_count <= 0) {
-		pr_err("NUMA: Invalid distance-matrix\n");
+		pr_err("Invalid distance-matrix\n");
 		return -EINVAL;
 	}
 
@@ -132,7 +125,7 @@ static int __init of_numa_parse_distance_map_v1(struct device_node *map)
 		matrix++;
 
 		numa_set_distance(nodea, nodeb, distance);
-		pr_debug("NUMA:  distance[node%d -> node%d] = %d\n",
+		pr_debug("distance[node%d -> node%d] = %d\n",
 			 nodea, nodeb, distance);
 
 		/* Set default distance of node B->A same as A->B */
@@ -166,8 +159,6 @@ int of_node_to_nid(struct device_node *device)
 	np = of_node_get(device);
 
 	while (np) {
-		struct device_node *parent;
-
 		r = of_property_read_u32(np, "numa-node-id", &nid);
 		/*
 		 * -EINVAL indicates the property was not found, and
@@ -178,22 +169,15 @@ int of_node_to_nid(struct device_node *device)
 		if (r != -EINVAL)
 			break;
 
-		parent = of_get_parent(np);
-		of_node_put(np);
-		np = parent;
+		np = of_get_next_parent(np);
 	}
 	if (np && r)
-		pr_warn("NUMA: Invalid \"numa-node-id\" property in node %s\n",
+		pr_warn("Invalid \"numa-node-id\" property in node %s\n",
 			np->name);
 	of_node_put(np);
 
-	if (!r) {
-		if (nid >= MAX_NUMNODES)
-			pr_warn("NUMA: Node id %u exceeds maximum value\n",
-				nid);
-		else
-			return nid;
-	}
+	if (!r)
+		return nid;
 
 	return NUMA_NO_NODE;
 }

drivers/perf/arm_pmu.c

@@ -534,6 +534,24 @@ static int armpmu_filter_match(struct perf_event *event)
 	return cpumask_test_cpu(cpu, &armpmu->supported_cpus);
 }
 
+static ssize_t armpmu_cpumask_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct arm_pmu *armpmu = to_arm_pmu(dev_get_drvdata(dev));
+	return cpumap_print_to_pagebuf(true, buf, &armpmu->supported_cpus);
+}
+
+static DEVICE_ATTR(cpus, S_IRUGO, armpmu_cpumask_show, NULL);
+
+static struct attribute *armpmu_common_attrs[] = {
+	&dev_attr_cpus.attr,
+	NULL,
+};
+
+static struct attribute_group armpmu_common_attr_group = {
+	.attrs = armpmu_common_attrs,
+};
+
 static void armpmu_init(struct arm_pmu *armpmu)
 {
 	atomic_set(&armpmu->active_events, 0);
@@ -549,7 +567,10 @@ static void armpmu_init(struct arm_pmu *armpmu)
 		.stop		= armpmu_stop,
 		.read		= armpmu_read,
 		.filter_match	= armpmu_filter_match,
+		.attr_groups	= armpmu->attr_groups,
 	};
+	armpmu->attr_groups[ARMPMU_ATTR_GROUP_COMMON] =
+		&armpmu_common_attr_group;
 }
 
 /* Set at runtime when we know what CPU type we are. */
@@ -602,7 +623,7 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 
 	irq = platform_get_irq(pmu_device, 0);
-	if (irq >= 0 && irq_is_percpu(irq)) {
+	if (irq > 0 && irq_is_percpu(irq)) {
 		on_each_cpu_mask(&cpu_pmu->supported_cpus,
 				 cpu_pmu_disable_percpu_irq, &irq, 1);
 		free_percpu_irq(irq, &hw_events->percpu_pmu);
@@ -616,7 +637,7 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 			if (!cpumask_test_and_clear_cpu(cpu, &cpu_pmu->active_irqs))
 				continue;
 			irq = platform_get_irq(pmu_device, i);
-			if (irq >= 0)
+			if (irq > 0)
 				free_irq(irq, per_cpu_ptr(&hw_events->percpu_pmu, cpu));
 		}
 	}
@@ -638,7 +659,7 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 	}
 
 	irq = platform_get_irq(pmu_device, 0);
-	if (irq >= 0 && irq_is_percpu(irq)) {
+	if (irq > 0 && irq_is_percpu(irq)) {
 		err = request_percpu_irq(irq, handler, "arm-pmu",
 					 &hw_events->percpu_pmu);
 		if (err) {
@@ -919,7 +940,7 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu)
 
 		/* Check the IRQ type and prohibit a mix of PPIs and SPIs */
 		irq = platform_get_irq(pdev, i);
-		if (irq >= 0) {
+		if (irq > 0) {
 			bool spi = !irq_is_percpu(irq);
 
 			if (i > 0 && spi != using_spi) {
@@ -970,7 +991,7 @@ static int of_pmu_irq_cfg(struct arm_pmu *pmu)
 	if (cpumask_weight(&pmu->supported_cpus) == 0) {
 		int irq = platform_get_irq(pdev, 0);
 
-		if (irq >= 0 && irq_is_percpu(irq)) {
+		if (irq > 0 && irq_is_percpu(irq)) {
 			/* If using PPIs, check the affinity of the partition */
 			int ret;
 
@@ -1029,7 +1050,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 		ret = of_pmu_irq_cfg(pmu);
 		if (!ret)
 			ret = init_fn(pmu);
-	} else {
+	} else if (probe_table) {
 		cpumask_setall(&pmu->supported_cpus);
 		ret = probe_current_pmu(pmu, probe_table);
 	}
@@ -1039,6 +1060,7 @@ int arm_pmu_device_probe(struct platform_device *pdev,
 		goto out_free;
 	}
 
+
 	ret = cpu_pmu_init(pmu);
 	if (ret)
 		goto out_free;

include/linux/cpu.h

@@ -228,7 +228,11 @@ static inline void cpu_hotplug_done(void) {}
 #endif		/* CONFIG_HOTPLUG_CPU */
 
 #ifdef CONFIG_PM_SLEEP_SMP
-extern int disable_nonboot_cpus(void);
+extern int freeze_secondary_cpus(int primary);
+static inline int disable_nonboot_cpus(void)
+{
+	return freeze_secondary_cpus(0);
+}
 extern void enable_nonboot_cpus(void);
 #else /* !CONFIG_PM_SLEEP_SMP */
 static inline int disable_nonboot_cpus(void) { return 0; }