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

Pull arm64 updates from Catalin Marinas:

 - struct thread_info moved off-stack (also touching
   include/linux/thread_info.h and include/linux/restart_block.h)

 - cpus_have_cap() reworked to avoid __builtin_constant_p() for static
   key use (also touching drivers/irqchip/irq-gic-v3.c)

 - uprobes support (currently only for native 64-bit tasks)

 - Emulation of kernel Privileged Access Never (PAN) using TTBR0_EL1
   switching to a reserved page table

 - CPU capacity information passing via DT or sysfs (used by the
   scheduler)

 - support for systems without FP/SIMD (IOW, kernel avoids touching
   these registers; there is no soft-float ABI, nor kernel emulation for
   AArch64 FP/SIMD)

 - handling of hardware watchpoint with unaligned addresses, varied
   lengths and offsets from base

 - use of the page table contiguous hint for kernel mappings

 - hugetlb fixes for sizes involving the contiguous hint

 - remove unnecessary I-cache invalidation in flush_cache_range()

 - CNTHCTL_EL2 access fix for CPUs with VHE support (ARMv8.1)

 - boot-time checks for writable+executable kernel mappings

 - simplify asm/opcodes.h and avoid including the 32-bit ARM counterpart
   and make the arm64 kernel headers self-consistent (Xen headers patch
   merged separately)

 - Workaround for broken .inst support in certain binutils versions

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (60 commits)
  arm64: Disable PAN on uaccess_enable()
  arm64: Work around broken .inst when defective gas is detected
  arm64: Add detection code for broken .inst support in binutils
  arm64: Remove reference to asm/opcodes.h
  arm64: Get rid of asm/opcodes.h
  arm64: smp: Prevent raw_smp_processor_id() recursion
  arm64: head.S: Fix CNTHCTL_EL2 access on VHE system
  arm64: Remove I-cache invalidation from flush_cache_range()
  arm64: Enable HIBERNATION in defconfig
  arm64: Enable CONFIG_ARM64_SW_TTBR0_PAN
  arm64: xen: Enable user access before a privcmd hvc call
  arm64: Handle faults caused by inadvertent user access with PAN enabled
  arm64: Disable TTBR0_EL1 during normal kernel execution
  arm64: Introduce uaccess_{disable,enable} functionality based on TTBR0_EL1
  arm64: Factor out TTBR0_EL1 post-update workaround into a specific asm macro
  arm64: Factor out PAN enabling/disabling into separate uaccess_* macros
  arm64: Update the synchronous external abort fault description
  selftests: arm64: add test for unaligned/inexact watchpoint handling
  arm64: Allow hw watchpoint of length 3,5,6 and 7
  arm64: hw_breakpoint: Handle inexact watchpoint addresses
  ...

Documentation/devicetree/bindings/arm/cpu-capacity.txt

@@ -0,0 +1,236 @@
+==========================================
+ARM CPUs capacity bindings
+==========================================
+
+==========================================
+1 - Introduction
+==========================================
+
+ARM systems may be configured to have cpus with different power/performance
+characteristics within the same chip. In this case, additional information has
+to be made available to the kernel for it to be aware of such differences and
+take decisions accordingly.
+
+==========================================
+2 - CPU capacity definition
+==========================================
+
+CPU capacity is a number that provides the scheduler information about CPUs
+heterogeneity. Such heterogeneity can come from micro-architectural differences
+(e.g., ARM big.LITTLE systems) or maximum frequency at which CPUs can run
+(e.g., SMP systems with multiple frequency domains). Heterogeneity in this
+context is about differing performance characteristics; this binding tries to
+capture a first-order approximation of the relative performance of CPUs.
+
+CPU capacities are obtained by running a suitable benchmark. This binding makes
+no guarantees on the validity or suitability of any particular benchmark, the
+final capacity should, however, be:
+
+* A "single-threaded" or CPU affine benchmark
+* Divided by the running frequency of the CPU executing the benchmark
+* Not subject to dynamic frequency scaling of the CPU
+
+For the time being we however advise usage of the Dhrystone benchmark. What
+above thus becomes:
+
+CPU capacities are obtained by running the Dhrystone benchmark on each CPU at
+max frequency (with caches enabled). The obtained DMIPS score is then divided
+by the frequency (in MHz) at which the benchmark has been run, so that
+DMIPS/MHz are obtained.  Such values are then normalized w.r.t. the highest
+score obtained in the system.
+
+==========================================
+3 - capacity-dmips-mhz
+==========================================
+
+capacity-dmips-mhz is an optional cpu node [1] property: u32 value
+representing CPU capacity expressed in normalized DMIPS/MHz. At boot time, the
+maximum frequency available to the cpu is then used to calculate the capacity
+value internally used by the kernel.
+
+capacity-dmips-mhz property is all-or-nothing: if it is specified for a cpu
+node, it has to be specified for every other cpu nodes, or the system will
+fall back to the default capacity value for every CPU. If cpufreq is not
+available, final capacities are calculated by directly using capacity-dmips-
+mhz values (normalized w.r.t. the highest value found while parsing the DT).
+
+===========================================
+4 - Examples
+===========================================
+
+Example 1 (ARM 64-bit, 6-cpu system, two clusters):
+capacities-dmips-mhz are scaled w.r.t. 1024 (cpu@0 and cpu@1)
+supposing cluster0@max-freq=1100 and custer1@max-freq=850,
+final capacities are 1024 for cluster0 and 446 for cluster1
+
+cpus {
+	#address-cells = <2>;
+	#size-cells = <0>;
+
+	cpu-map {
+		cluster0 {
+			core0 {
+				cpu = <&A57_0>;
+			};
+			core1 {
+				cpu = <&A57_1>;
+			};
+		};
+
+		cluster1 {
+			core0 {
+				cpu = <&A53_0>;
+			};
+			core1 {
+				cpu = <&A53_1>;
+			};
+			core2 {
+				cpu = <&A53_2>;
+			};
+			core3 {
+				cpu = <&A53_3>;
+			};
+		};
+	};
+
+	idle-states {
+		entry-method = "arm,psci";
+
+		CPU_SLEEP_0: cpu-sleep-0 {
+			compatible = "arm,idle-state";
+			arm,psci-suspend-param = <0x0010000>;
+			local-timer-stop;
+			entry-latency-us = <100>;
+			exit-latency-us = <250>;
+			min-residency-us = <150>;
+		};
+
+		CLUSTER_SLEEP_0: cluster-sleep-0 {
+			compatible = "arm,idle-state";
+			arm,psci-suspend-param = <0x1010000>;
+			local-timer-stop;
+			entry-latency-us = <800>;
+			exit-latency-us = <700>;
+			min-residency-us = <2500>;
+		};
+	};
+
+	A57_0: cpu@0 {
+		compatible = "arm,cortex-a57","arm,armv8";
+		reg = <0x0 0x0>;
+		device_type = "cpu";
+		enable-method = "psci";
+		next-level-cache = <&A57_L2>;
+		clocks = <&scpi_dvfs 0>;
+		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		capacity-dmips-mhz = <1024>;
+	};
+
+	A57_1: cpu@1 {
+		compatible = "arm,cortex-a57","arm,armv8";
+		reg = <0x0 0x1>;
+		device_type = "cpu";
+		enable-method = "psci";
+		next-level-cache = <&A57_L2>;
+		clocks = <&scpi_dvfs 0>;
+		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		capacity-dmips-mhz = <1024>;
+	};
+
+	A53_0: cpu@100 {
+		compatible = "arm,cortex-a53","arm,armv8";
+		reg = <0x0 0x100>;
+		device_type = "cpu";
+		enable-method = "psci";
+		next-level-cache = <&A53_L2>;
+		clocks = <&scpi_dvfs 1>;
+		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		capacity-dmips-mhz = <578>;
+	};
+
+	A53_1: cpu@101 {
+		compatible = "arm,cortex-a53","arm,armv8";
+		reg = <0x0 0x101>;
+		device_type = "cpu";
+		enable-method = "psci";
+		next-level-cache = <&A53_L2>;
+		clocks = <&scpi_dvfs 1>;
+		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		capacity-dmips-mhz = <578>;
+	};
+
+	A53_2: cpu@102 {
+		compatible = "arm,cortex-a53","arm,armv8";
+		reg = <0x0 0x102>;
+		device_type = "cpu";
+		enable-method = "psci";
+		next-level-cache = <&A53_L2>;
+		clocks = <&scpi_dvfs 1>;
+		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		capacity-dmips-mhz = <578>;
+	};
+
+	A53_3: cpu@103 {
+		compatible = "arm,cortex-a53","arm,armv8";
+		reg = <0x0 0x103>;
+		device_type = "cpu";
+		enable-method = "psci";
+		next-level-cache = <&A53_L2>;
+		clocks = <&scpi_dvfs 1>;
+		cpu-idle-states = <&CPU_SLEEP_0 &CLUSTER_SLEEP_0>;
+		capacity-dmips-mhz = <578>;
+	};
+
+	A57_L2: l2-cache0 {
+		compatible = "cache";
+	};
+
+	A53_L2: l2-cache1 {
+		compatible = "cache";
+	};
+};
+
+Example 2 (ARM 32-bit, 4-cpu system, two clusters,
+	   cpus 0,1@1GHz, cpus 2,3@500MHz):
+capacities-dmips-mhz are scaled w.r.t. 2 (cpu@0 and cpu@1), this means that first
+cpu@0 and cpu@1 are twice fast than cpu@2 and cpu@3 (at the same frequency)
+
+cpus {
+	#address-cells = <1>;
+	#size-cells = <0>;
+
+	cpu0: cpu@0 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a15";
+		reg = <0>;
+		capacity-dmips-mhz = <2>;
+	};
+
+	cpu1: cpu@1 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a15";
+		reg = <1>;
+		capacity-dmips-mhz = <2>;
+	};
+
+	cpu2: cpu@2 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a15";
+		reg = <0x100>;
+		capacity-dmips-mhz = <1>;
+	};
+
+	cpu3: cpu@3 {
+		device_type = "cpu";
+		compatible = "arm,cortex-a15";
+		reg = <0x101>;
+		capacity-dmips-mhz = <1>;
+	};
+};
+
+===========================================
+5 - References
+===========================================
+
+[1] ARM Linux Kernel documentation - CPUs bindings
+    Documentation/devicetree/bindings/arm/cpus.txt

Documentation/devicetree/bindings/arm/cpus.txt

@@ -241,6 +241,14 @@ nodes to be present and contain the properties described below.
 			# List of phandles to idle state nodes supported
 			  by this cpu [3].
 
+	- capacity-dmips-mhz
+		Usage: Optional
+		Value type: <u32>
+		Definition:
+			# u32 value representing CPU capacity [3] in
+			  DMIPS/MHz, relative to highest capacity-dmips-mhz
+			  in the system.
+
 	- rockchip,pmu
 		Usage: optional for systems that have an "enable-method"
 		       property value of "rockchip,rk3066-smp"
@@ -464,3 +472,5 @@ cpus {
 [2] arm/msm/qcom,kpss-acc.txt
 [3] ARM Linux kernel documentation - idle states bindings
     Documentation/devicetree/bindings/arm/idle-states.txt
+[3] ARM Linux kernel documentation - cpu capacity bindings
+    Documentation/devicetree/bindings/arm/cpu-capacity.txt

arch/arm64/Kconfig

@@ -110,6 +110,7 @@ config ARM64
 	select POWER_SUPPLY
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
+	select THREAD_INFO_IN_TASK
 	help
 	  ARM 64-bit (AArch64) Linux support.
 
@@ -239,6 +240,9 @@ config PGTABLE_LEVELS
 	default 3 if ARM64_16K_PAGES && ARM64_VA_BITS_47
 	default 4 if !ARM64_64K_PAGES && ARM64_VA_BITS_48
 
+config ARCH_SUPPORTS_UPROBES
+	def_bool y
+
 source "init/Kconfig"
 
 source "kernel/Kconfig.freezer"
@@ -791,6 +795,14 @@ config SETEND_EMULATION
 	  If unsure, say Y
 endif
 
+config ARM64_SW_TTBR0_PAN
+	bool "Emulate Privileged Access Never using TTBR0_EL1 switching"
+	help
+	  Enabling this option prevents the kernel from accessing
+	  user-space memory directly by pointing TTBR0_EL1 to a reserved
+	  zeroed area and reserved ASID. The user access routines
+	  restore the valid TTBR0_EL1 temporarily.
+
 menu "ARMv8.1 architectural features"
 
 config ARM64_HW_AFDBM

arch/arm64/Kconfig.debug

@@ -2,9 +2,13 @@ menu "Kernel hacking"
 
 source "lib/Kconfig.debug"
 
-config ARM64_PTDUMP
+config ARM64_PTDUMP_CORE
+	def_bool n
+
+config ARM64_PTDUMP_DEBUGFS
 	bool "Export kernel pagetable layout to userspace via debugfs"
 	depends on DEBUG_KERNEL
+	select ARM64_PTDUMP_CORE
 	select DEBUG_FS
         help
 	  Say Y here if you want to show the kernel pagetable layout in a
@@ -38,6 +42,35 @@ config ARM64_RANDOMIZE_TEXT_OFFSET
 	  of TEXT_OFFSET and platforms must not require a specific
 	  value.
 
+config DEBUG_WX
+	bool "Warn on W+X mappings at boot"
+	select ARM64_PTDUMP_CORE
+	---help---
+	  Generate a warning if any W+X mappings are found at boot.
+
+	  This is useful for discovering cases where the kernel is leaving
+	  W+X mappings after applying NX, as such mappings are a security risk.
+	  This check also includes UXN, which should be set on all kernel
+	  mappings.
+
+	  Look for a message in dmesg output like this:
+
+	    arm64/mm: Checked W+X mappings: passed, no W+X pages found.
+
+	  or like this, if the check failed:
+
+	    arm64/mm: Checked W+X mappings: FAILED, <N> W+X pages found.
+
+	  Note that even if the check fails, your kernel is possibly
+	  still fine, as W+X mappings are not a security hole in
+	  themselves, what they do is that they make the exploitation
+	  of other unfixed kernel bugs easier.
+
+	  There is no runtime or memory usage effect of this option
+	  once the kernel has booted up - it's a one time check.
+
+	  If in doubt, say "Y".
+
 config DEBUG_SET_MODULE_RONX
 	bool "Set loadable kernel module data as NX and text as RO"
 	depends on MODULES

arch/arm64/Makefile

@@ -37,10 +37,16 @@ $(warning LSE atomics not supported by binutils)
   endif
 endif
 
-KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr)
+brokengasinst := $(call as-instr,1:\n.inst 0\n.rept . - 1b\n\nnop\n.endr\n,,-DCONFIG_BROKEN_GAS_INST=1)
+
+ifneq ($(brokengasinst),)
+$(warning Detected assembler with broken .inst; disassembly will be unreliable)
+endif
+
+KBUILD_CFLAGS	+= -mgeneral-regs-only $(lseinstr) $(brokengasinst)
 KBUILD_CFLAGS	+= -fno-asynchronous-unwind-tables
 KBUILD_CFLAGS	+= $(call cc-option, -mpc-relative-literal-loads)
-KBUILD_AFLAGS	+= $(lseinstr)
+KBUILD_AFLAGS	+= $(lseinstr) $(brokengasinst)
 
 ifeq ($(CONFIG_CPU_BIG_ENDIAN), y)
 KBUILD_CPPFLAGS	+= -mbig-endian

arch/arm64/configs/defconfig

@@ -82,6 +82,7 @@ CONFIG_KEXEC=y
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y
 CONFIG_CPU_IDLE=y
+CONFIG_HIBERNATION=y
 CONFIG_ARM_CPUIDLE=y
 CONFIG_CPU_FREQ=y
 CONFIG_CPUFREQ_DT=y

arch/arm64/include/asm/Kbuild

@@ -1,7 +1,6 @@
 generic-y += bugs.h
 generic-y += clkdev.h
 generic-y += cputime.h
-generic-y += current.h
 generic-y += delay.h
 generic-y += div64.h
 generic-y += dma.h

arch/arm64/include/asm/assembler.h

@@ -41,6 +41,15 @@
 	msr	daifclr, #2
 	.endm
 
+	.macro	save_and_disable_irq, flags
+	mrs	\flags, daif
+	msr	daifset, #2
+	.endm
+
+	.macro	restore_irq, flags
+	msr	daif, \flags
+	.endm
+
 /*
  * Enable and disable debug exceptions.
  */
@@ -202,14 +211,25 @@ lr	.req	x30		// link register
 	.endm
 
 	/*
+	 * @dst: Result of per_cpu(sym, smp_processor_id())
 	 * @sym: The name of the per-cpu variable
-	 * @reg: Result of per_cpu(sym, smp_processor_id())
 	 * @tmp: scratch register
 	 */
-	.macro this_cpu_ptr, sym, reg, tmp
-	adr_l	\reg, \sym
+	.macro adr_this_cpu, dst, sym, tmp
+	adr_l	\dst, \sym
 	mrs	\tmp, tpidr_el1
-	add	\reg, \reg, \tmp
+	add	\dst, \dst, \tmp
+	.endm
+
+	/*
+	 * @dst: Result of READ_ONCE(per_cpu(sym, smp_processor_id()))
+	 * @sym: The name of the per-cpu variable
+	 * @tmp: scratch register
+	 */
+	.macro ldr_this_cpu dst, sym, tmp
+	adr_l	\dst, \sym
+	mrs	\tmp, tpidr_el1
+	ldr	\dst, [\dst, \tmp]
 	.endm
 
 /*
@@ -395,4 +415,24 @@ alternative_endif
 	movk	\reg, :abs_g0_nc:\val
 	.endm
 
+/*
+ * Return the current thread_info.
+ */
+	.macro	get_thread_info, rd
+	mrs	\rd, sp_el0
+	.endm
+
+/*
+ * Errata workaround post TTBR0_EL1 update.
+ */
+	.macro	post_ttbr0_update_workaround
+#ifdef CONFIG_CAVIUM_ERRATUM_27456
+alternative_if ARM64_WORKAROUND_CAVIUM_27456
+	ic	iallu
+	dsb	nsh
+	isb
+alternative_else_nop_endif
+#endif
+	.endm
+
 #endif	/* __ASM_ASSEMBLER_H */

arch/arm64/include/asm/cacheflush.h

@@ -65,12 +65,12 @@
  *		- kaddr  - page address
  *		- size   - region size
  */
-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);
+extern void sync_icache_aliases(void *kaddr, unsigned long len);
 
 static inline void flush_cache_mm(struct mm_struct *mm)
 {
@@ -81,6 +81,11 @@ static inline void flush_cache_page(struct vm_area_struct *vma,
 {
 }
 
+static inline void flush_cache_range(struct vm_area_struct *vma,
+				     unsigned long start, unsigned long end)
+{
+}
+
 /*
  * Cache maintenance functions used by the DMA API. No to be used directly.
  */

arch/arm64/include/asm/cpucaps.h

@@ -34,7 +34,8 @@
 #define ARM64_HAS_32BIT_EL0			13
 #define ARM64_HYP_OFFSET_LOW			14
 #define ARM64_MISMATCHED_CACHE_LINE_SIZE	15
+#define ARM64_HAS_NO_FPSIMD			16
 
-#define ARM64_NCAPS				16
+#define ARM64_NCAPS				17
 
 #endif /* __ASM_CPUCAPS_H */

arch/arm64/include/asm/cpufeature.h

@@ -9,8 +9,6 @@
 #ifndef __ASM_CPUFEATURE_H
 #define __ASM_CPUFEATURE_H
 
-#include <linux/jump_label.h>
-
 #include <asm/cpucaps.h>
 #include <asm/hwcap.h>
 #include <asm/sysreg.h>
@@ -27,6 +25,8 @@
 
 #ifndef __ASSEMBLY__
 
+#include <linux/bug.h>
+#include <linux/jump_label.h>
 #include <linux/kernel.h>
 
 /* CPU feature register tracking */
@@ -104,14 +104,19 @@ static inline bool cpu_have_feature(unsigned int num)
 	return elf_hwcap & (1UL << num);
 }
 
+/* System capability check for constant caps */
+static inline bool cpus_have_const_cap(int num)
+{
+	if (num >= ARM64_NCAPS)
+		return false;
+	return static_branch_unlikely(&cpu_hwcap_keys[num]);
+}
+
 static inline bool cpus_have_cap(unsigned int num)
 {
 	if (num >= ARM64_NCAPS)
 		return false;
-	if (__builtin_constant_p(num))
-		return static_branch_unlikely(&cpu_hwcap_keys[num]);
-	else
-		return test_bit(num, cpu_hwcaps);
+	return test_bit(num, cpu_hwcaps);
 }
 
 static inline void cpus_set_cap(unsigned int num)
@@ -200,7 +205,7 @@ static inline bool cpu_supports_mixed_endian_el0(void)
 
 static inline bool system_supports_32bit_el0(void)
 {
-	return cpus_have_cap(ARM64_HAS_32BIT_EL0);
+	return cpus_have_const_cap(ARM64_HAS_32BIT_EL0);
 }
 
 static inline bool system_supports_mixed_endian_el0(void)
@@ -208,6 +213,17 @@ static inline bool system_supports_mixed_endian_el0(void)
 	return id_aa64mmfr0_mixed_endian_el0(read_system_reg(SYS_ID_AA64MMFR0_EL1));
 }
 
+static inline bool system_supports_fpsimd(void)
+{
+	return !cpus_have_const_cap(ARM64_HAS_NO_FPSIMD);
+}
+
+static inline bool system_uses_ttbr0_pan(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) &&
+		!cpus_have_cap(ARM64_HAS_PAN);
+}
+
 #endif /* __ASSEMBLY__ */
 
 #endif

arch/arm64/include/asm/current.h

@@ -0,0 +1,22 @@
+#ifndef __ASM_CURRENT_H
+#define __ASM_CURRENT_H
+
+#include <linux/compiler.h>
+
+#include <asm/sysreg.h>
+
+#ifndef __ASSEMBLY__
+
+struct task_struct;
+
+static __always_inline struct task_struct *get_current(void)
+{
+	return (struct task_struct *)read_sysreg(sp_el0);
+}
+
+#define current get_current()
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __ASM_CURRENT_H */
+

arch/arm64/include/asm/debug-monitors.h

@@ -68,6 +68,9 @@
 #define BRK64_ESR_MASK		0xFFFF
 #define BRK64_ESR_KPROBES	0x0004
 #define BRK64_OPCODE_KPROBES	(AARCH64_BREAK_MON | (BRK64_ESR_KPROBES << 5))
+/* uprobes BRK opcodes with ESR encoding  */
+#define BRK64_ESR_UPROBES	0x0005
+#define BRK64_OPCODE_UPROBES	(AARCH64_BREAK_MON | (BRK64_ESR_UPROBES << 5))
 
 /* AArch32 */
 #define DBG_ESR_EVT_BKPT	0x4

arch/arm64/include/asm/efi.h

@@ -1,6 +1,7 @@
 #ifndef _ASM_EFI_H
 #define _ASM_EFI_H
 
+#include <asm/cpufeature.h>
 #include <asm/io.h>
 #include <asm/mmu_context.h>
 #include <asm/neon.h>
@@ -78,7 +79,30 @@ static inline void efifb_setup_from_dmi(struct screen_info *si, const char *opt)
 
 static inline void efi_set_pgd(struct mm_struct *mm)
 {
-	switch_mm(NULL, mm, NULL);
+	__switch_mm(mm);
+
+	if (system_uses_ttbr0_pan()) {
+		if (mm != current->active_mm) {
+			/*
+			 * Update the current thread's saved ttbr0 since it is
+			 * restored as part of a return from exception. Set
+			 * the hardware TTBR0_EL1 using cpu_switch_mm()
+			 * directly to enable potential errata workarounds.
+			 */
+			update_saved_ttbr0(current, mm);
+			cpu_switch_mm(mm->pgd, mm);
+		} else {
+			/*
+			 * Defer the switch to the current thread's TTBR0_EL1
+			 * until uaccess_enable(). Restore the current
+			 * thread's saved ttbr0 corresponding to its active_mm
+			 * (if different from init_mm).
+			 */
+			cpu_set_reserved_ttbr0();
+			if (current->active_mm != &init_mm)
+				update_saved_ttbr0(current, current->active_mm);
+		}
+	}
 }
 
 void efi_virtmap_load(void);

arch/arm64/include/asm/elf.h

@@ -138,7 +138,11 @@ typedef struct user_fpsimd_state elf_fpregset_t;
  */
 #define ELF_PLAT_INIT(_r, load_addr)	(_r)->regs[0] = 0
 
-#define SET_PERSONALITY(ex)		clear_thread_flag(TIF_32BIT);
+#define SET_PERSONALITY(ex)						\
+({									\
+	clear_bit(TIF_32BIT, &current->mm->context.flags);		\
+	clear_thread_flag(TIF_32BIT);					\
+})
 
 /* update AT_VECTOR_SIZE_ARCH if the number of NEW_AUX_ENT entries changes */
 #define ARCH_DLINFO							\
@@ -183,7 +187,11 @@ typedef compat_elf_greg_t		compat_elf_gregset_t[COMPAT_ELF_NGREG];
 					 ((x)->e_flags & EF_ARM_EABI_MASK))
 
 #define compat_start_thread		compat_start_thread
-#define COMPAT_SET_PERSONALITY(ex)	set_thread_flag(TIF_32BIT);
+#define COMPAT_SET_PERSONALITY(ex)					\
+({									\
+	set_bit(TIF_32BIT, &current->mm->context.flags);		\
+	set_thread_flag(TIF_32BIT);					\
+ })
 #define COMPAT_ARCH_DLINFO
 extern int aarch32_setup_vectors_page(struct linux_binprm *bprm,
 				      int uses_interp);

arch/arm64/include/asm/futex.h

@@ -21,15 +21,12 @@
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 
-#include <asm/alternative.h>
-#include <asm/cpufeature.h>
 #include <asm/errno.h>
-#include <asm/sysreg.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, tmp, oparg)		\
+do {									\
+	uaccess_enable();						\
 	asm volatile(							\
-	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,		\
-		    CONFIG_ARM64_PAN)					\
 "	prfm	pstl1strm, %2\n"					\
 "1:	ldxr	%w1, %2\n"						\
 	insn "\n"							\
@@ -44,11 +41,11 @@
 "	.popsection\n"							\
 	_ASM_EXTABLE(1b, 4b)						\
 	_ASM_EXTABLE(2b, 4b)						\
-	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,		\
-		    CONFIG_ARM64_PAN)					\
 	: "=&r" (ret), "=&r" (oldval), "+Q" (*uaddr), "=&r" (tmp)	\
 	: "r" (oparg), "Ir" (-EFAULT)					\
-	: "memory")
+	: "memory");							\
+	uaccess_disable();						\
+} while (0)
 
 static inline int
 futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
@@ -118,8 +115,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	uaccess_enable();
 	asm volatile("// futex_atomic_cmpxchg_inatomic\n"
-ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 "	prfm	pstl1strm, %2\n"
 "1:	ldxr	%w1, %2\n"
 "	sub	%w3, %w1, %w4\n"
@@ -134,10 +131,10 @@ ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 "	.popsection\n"
 	_ASM_EXTABLE(1b, 4b)
 	_ASM_EXTABLE(2b, 4b)
-ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, CONFIG_ARM64_PAN)
 	: "+r" (ret), "=&r" (val), "+Q" (*uaddr), "=&r" (tmp)
 	: "r" (oldval), "r" (newval), "Ir" (-EFAULT)
 	: "memory");
+	uaccess_disable();
 
 	*uval = val;
 	return ret;

arch/arm64/include/asm/hw_breakpoint.h

@@ -77,7 +77,11 @@ static inline void decode_ctrl_reg(u32 reg,
 /* Lengths */
 #define ARM_BREAKPOINT_LEN_1	0x1
 #define ARM_BREAKPOINT_LEN_2	0x3
+#define ARM_BREAKPOINT_LEN_3	0x7
 #define ARM_BREAKPOINT_LEN_4	0xf
+#define ARM_BREAKPOINT_LEN_5	0x1f
+#define ARM_BREAKPOINT_LEN_6	0x3f
+#define ARM_BREAKPOINT_LEN_7	0x7f
 #define ARM_BREAKPOINT_LEN_8	0xff
 
 /* Kernel stepping */
@@ -119,7 +123,7 @@ struct perf_event;
 struct pmu;
 
 extern int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
-				  int *gen_len, int *gen_type);
+				  int *gen_len, int *gen_type, int *offset);
 extern int arch_check_bp_in_kernelspace(struct perf_event *bp);
 extern int arch_validate_hwbkpt_settings(struct perf_event *bp);
 extern int hw_breakpoint_exceptions_notify(struct notifier_block *unused,

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

@@ -19,6 +19,7 @@
 #ifndef __ASM_KERNEL_PGTABLE_H
 #define __ASM_KERNEL_PGTABLE_H
 
+#include <asm/pgtable.h>
 #include <asm/sparsemem.h>
 
 /*
@@ -54,6 +55,12 @@
 #define SWAPPER_DIR_SIZE	(SWAPPER_PGTABLE_LEVELS * PAGE_SIZE)
 #define IDMAP_DIR_SIZE		(IDMAP_PGTABLE_LEVELS * PAGE_SIZE)
 
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+#define RESERVED_TTBR0_SIZE	(PAGE_SIZE)
+#else
+#define RESERVED_TTBR0_SIZE	(0)
+#endif
+
 /* Initial memory map size */
 #if ARM64_SWAPPER_USES_SECTION_MAPS
 #define SWAPPER_BLOCK_SHIFT	SECTION_SHIFT

arch/arm64/include/asm/mmu.h

@@ -19,6 +19,7 @@
 typedef struct {
 	atomic64_t	id;
 	void		*vdso;
+	unsigned long	flags;
 } mm_context_t;
 
 /*
@@ -34,7 +35,7 @@ extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt);
 extern void init_mem_pgprot(void);
 extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
-			       pgprot_t prot, bool allow_block_mappings);
+			       pgprot_t prot, bool page_mappings_only);
 extern void *fixmap_remap_fdt(phys_addr_t dt_phys);
 
 #endif

arch/arm64/include/asm/mmu_context.h

@@ -23,6 +23,7 @@
 #include <linux/sched.h>
 
 #include <asm/cacheflush.h>
+#include <asm/cpufeature.h>
 #include <asm/proc-fns.h>
 #include <asm-generic/mm_hooks.h>
 #include <asm/cputype.h>
@@ -103,7 +104,7 @@ static inline void cpu_uninstall_idmap(void)
 	local_flush_tlb_all();
 	cpu_set_default_tcr_t0sz();
 
-	if (mm != &init_mm)
+	if (mm != &init_mm && !system_uses_ttbr0_pan())
 		cpu_switch_mm(mm->pgd, mm);
 }
 
@@ -163,20 +164,26 @@ enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 {
 }
 
-/*
- * This is the actual mm switch as far as the scheduler
- * is concerned.  No registers are touched.  We avoid
- * calling the CPU specific function when the mm hasn't
- * actually changed.
- */
-static inline void
-switch_mm(struct mm_struct *prev, struct mm_struct *next,
-	  struct task_struct *tsk)
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+static inline void update_saved_ttbr0(struct task_struct *tsk,
+				      struct mm_struct *mm)
 {
-	unsigned int cpu = smp_processor_id();
+	if (system_uses_ttbr0_pan()) {
+		BUG_ON(mm->pgd == swapper_pg_dir);
+		task_thread_info(tsk)->ttbr0 =
+			virt_to_phys(mm->pgd) | ASID(mm) << 48;
+	}
+}
+#else
+static inline void update_saved_ttbr0(struct task_struct *tsk,
+				      struct mm_struct *mm)
+{
+}
+#endif
 
-	if (prev == next)
-		return;
+static inline void __switch_mm(struct mm_struct *next)
+{
+	unsigned int cpu = smp_processor_id();
 
 	/*
 	 * init_mm.pgd does not contain any user mappings and it is always
@@ -190,8 +197,26 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 	check_and_switch_context(next, cpu);
 }
 
+static inline void
+switch_mm(struct mm_struct *prev, struct mm_struct *next,
+	  struct task_struct *tsk)
+{
+	if (prev != next)
+		__switch_mm(next);
+
+	/*
+	 * Update the saved TTBR0_EL1 of the scheduled-in task as the previous
+	 * value may have not been initialised yet (activate_mm caller) or the
+	 * ASID has changed since the last run (following the context switch
+	 * of another thread of the same process). Avoid setting the reserved
+	 * TTBR0_EL1 to swapper_pg_dir (init_mm; e.g. via idle_task_exit).
+	 */
+	if (next != &init_mm)
+		update_saved_ttbr0(tsk, next);
+}
+
 #define deactivate_mm(tsk,mm)	do { } while (0)
-#define activate_mm(prev,next)	switch_mm(prev, next, NULL)
+#define activate_mm(prev,next)	switch_mm(prev, next, current)
 
 void verify_cpu_asid_bits(void);
 

arch/arm64/include/asm/neon.h

@@ -9,8 +9,9 @@
  */
 
 #include <linux/types.h>
+#include <asm/fpsimd.h>
 
-#define cpu_has_neon()		(1)
+#define cpu_has_neon()		system_supports_fpsimd()
 
 #define kernel_neon_begin()	kernel_neon_begin_partial(32)
 

arch/arm64/include/asm/opcodes.h

@@ -1,5 +0,0 @@
-#ifdef CONFIG_CPU_BIG_ENDIAN
-#define CONFIG_CPU_ENDIAN_BE8 CONFIG_CPU_BIG_ENDIAN
-#endif
-
-#include <../../arm/include/asm/opcodes.h>

arch/arm64/include/asm/percpu.h

@@ -16,6 +16,8 @@
 #ifndef __ASM_PERCPU_H
 #define __ASM_PERCPU_H
 
+#include <asm/stack_pointer.h>
+
 static inline void set_my_cpu_offset(unsigned long off)
 {
 	asm volatile("msr tpidr_el1, %0" :: "r" (off) : "memory");
@@ -101,16 +103,16 @@ static inline unsigned long __percpu_read(void *ptr, int size)
 
 	switch (size) {
 	case 1:
-		ret = ACCESS_ONCE(*(u8 *)ptr);
+		ret = READ_ONCE(*(u8 *)ptr);
 		break;
 	case 2:
-		ret = ACCESS_ONCE(*(u16 *)ptr);
+		ret = READ_ONCE(*(u16 *)ptr);
 		break;
 	case 4:
-		ret = ACCESS_ONCE(*(u32 *)ptr);
+		ret = READ_ONCE(*(u32 *)ptr);
 		break;
 	case 8:
-		ret = ACCESS_ONCE(*(u64 *)ptr);
+		ret = READ_ONCE(*(u64 *)ptr);
 		break;
 	default:
 		BUILD_BUG();
@@ -123,16 +125,16 @@ static inline void __percpu_write(void *ptr, unsigned long val, int size)
 {
 	switch (size) {
 	case 1:
-		ACCESS_ONCE(*(u8 *)ptr) = (u8)val;
+		WRITE_ONCE(*(u8 *)ptr, (u8)val);
 		break;
 	case 2:
-		ACCESS_ONCE(*(u16 *)ptr) = (u16)val;
+		WRITE_ONCE(*(u16 *)ptr, (u16)val);
 		break;
 	case 4:
-		ACCESS_ONCE(*(u32 *)ptr) = (u32)val;
+		WRITE_ONCE(*(u32 *)ptr, (u32)val);
 		break;
 	case 8:
-		ACCESS_ONCE(*(u64 *)ptr) = (u64)val;
+		WRITE_ONCE(*(u64 *)ptr, (u64)val);
 		break;
 	default:
 		BUILD_BUG();

arch/arm64/include/asm/perf_event.h

@@ -17,6 +17,8 @@
 #ifndef __ASM_PERF_EVENT_H
 #define __ASM_PERF_EVENT_H
 
+#include <asm/stack_pointer.h>
+
 #define	ARMV8_PMU_MAX_COUNTERS	32
 #define	ARMV8_PMU_COUNTER_MASK	(ARMV8_PMU_MAX_COUNTERS - 1)
 

arch/arm64/include/asm/probes.h

@@ -15,21 +15,22 @@
 #ifndef _ARM_PROBES_H
 #define _ARM_PROBES_H
 
-#include <asm/opcodes.h>
-
-struct kprobe;
-struct arch_specific_insn;
-
-typedef u32 kprobe_opcode_t;
-typedef void (kprobes_handler_t) (u32 opcode, long addr, struct pt_regs *);
+typedef u32 probe_opcode_t;
+typedef void (probes_handler_t) (u32 opcode, long addr, struct pt_regs *);
 
 /* architecture specific copy of original instruction */
-struct arch_specific_insn {
-	kprobe_opcode_t *insn;
+struct arch_probe_insn {
+	probe_opcode_t *insn;
 	pstate_check_t *pstate_cc;
-	kprobes_handler_t *handler;
+	probes_handler_t *handler;
 	/* restore address after step xol */
 	unsigned long restore;
 };
+#ifdef CONFIG_KPROBES
+typedef u32 kprobe_opcode_t;
+struct arch_specific_insn {
+	struct arch_probe_insn api;
+};
+#endif
 
 #endif

arch/arm64/include/asm/ptdump.h

@@ -16,9 +16,10 @@
 #ifndef __ASM_PTDUMP_H
 #define __ASM_PTDUMP_H
 
-#ifdef CONFIG_ARM64_PTDUMP
+#ifdef CONFIG_ARM64_PTDUMP_CORE
 
 #include <linux/mm_types.h>
+#include <linux/seq_file.h>
 
 struct addr_marker {
 	unsigned long start_address;
@@ -29,16 +30,25 @@ struct ptdump_info {
 	struct mm_struct		*mm;
 	const struct addr_marker	*markers;
 	unsigned long			base_addr;
-	unsigned long			max_addr;
 };
 
-int ptdump_register(struct ptdump_info *info, const char *name);
-
+void ptdump_walk_pgd(struct seq_file *s, struct ptdump_info *info);
+#ifdef CONFIG_ARM64_PTDUMP_DEBUGFS
+int ptdump_debugfs_register(struct ptdump_info *info, const char *name);
 #else
-static inline int ptdump_register(struct ptdump_info *info, const char *name)
+static inline int ptdump_debugfs_register(struct ptdump_info *info,
+					const char *name)
 {
 	return 0;
 }
-#endif /* CONFIG_ARM64_PTDUMP */
+#endif
+void ptdump_check_wx(void);
+#endif /* CONFIG_ARM64_PTDUMP_CORE */
+
+#ifdef CONFIG_DEBUG_WX
+#define debug_checkwx()	ptdump_check_wx()
+#else
+#define debug_checkwx()	do { } while (0)
+#endif
 
 #endif /* __ASM_PTDUMP_H */

arch/arm64/include/asm/ptrace.h

@@ -217,6 +217,14 @@ int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task);
 
 #include <asm-generic/ptrace.h>
 
+#define procedure_link_pointer(regs)	((regs)->regs[30])
+
+static inline void procedure_link_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	procedure_link_pointer(regs) = val;
+}
+
 #undef profile_pc
 extern unsigned long profile_pc(struct pt_regs *regs);
 

arch/arm64/include/asm/smp.h

@@ -29,11 +29,22 @@
 
 #ifndef __ASSEMBLY__
 
+#include <asm/percpu.h>
+
 #include <linux/threads.h>
 #include <linux/cpumask.h>
 #include <linux/thread_info.h>
 
-#define raw_smp_processor_id() (current_thread_info()->cpu)
+DECLARE_PER_CPU_READ_MOSTLY(int, cpu_number);
+
+/*
+ * We don't use this_cpu_read(cpu_number) as that has implicit writes to
+ * preempt_count, and associated (compiler) barriers, that we'd like to avoid
+ * the expense of. If we're preemptible, the value can be stale at use anyway.
+ * And we can't use this_cpu_ptr() either, as that winds up recursing back
+ * here under CONFIG_DEBUG_PREEMPT=y.
+ */
+#define raw_smp_processor_id() (*raw_cpu_ptr(&cpu_number))
 
 struct seq_file;
 
@@ -73,6 +84,7 @@ asmlinkage void secondary_start_kernel(void);
  */
 struct secondary_data {
 	void *stack;
+	struct task_struct *task;
 	long status;
 };
 

arch/arm64/include/asm/stack_pointer.h

@@ -0,0 +1,9 @@
+#ifndef __ASM_STACK_POINTER_H
+#define __ASM_STACK_POINTER_H
+
+/*
+ * how to get the current stack pointer from C
+ */
+register unsigned long current_stack_pointer asm ("sp");
+
+#endif /* __ASM_STACK_POINTER_H */

arch/arm64/include/asm/suspend.h

@@ -1,7 +1,7 @@
 #ifndef __ASM_SUSPEND_H
 #define __ASM_SUSPEND_H
 
-#define NR_CTX_REGS 10
+#define NR_CTX_REGS 12
 #define NR_CALLEE_SAVED_REGS 12
 
 /*

arch/arm64/include/asm/sysreg.h

@@ -22,8 +22,6 @@
 
 #include <linux/stringify.h>
 
-#include <asm/opcodes.h>
-
 /*
  * ARMv8 ARM reserves the following encoding for system registers:
  * (Ref: ARMv8 ARM, Section: "System instruction class encoding overview",
@@ -37,6 +35,33 @@
 #define sys_reg(op0, op1, crn, crm, op2) \
 	((((op0)&3)<<19)|((op1)<<16)|((crn)<<12)|((crm)<<8)|((op2)<<5))
 
+#ifndef CONFIG_BROKEN_GAS_INST
+
+#ifdef __ASSEMBLY__
+#define __emit_inst(x)			.inst (x)
+#else
+#define __emit_inst(x)			".inst " __stringify((x)) "\n\t"
+#endif
+
+#else  /* CONFIG_BROKEN_GAS_INST */
+
+#ifndef CONFIG_CPU_BIG_ENDIAN
+#define __INSTR_BSWAP(x)		(x)
+#else  /* CONFIG_CPU_BIG_ENDIAN */
+#define __INSTR_BSWAP(x)		((((x) << 24) & 0xff000000)	| \
+					 (((x) <<  8) & 0x00ff0000)	| \
+					 (((x) >>  8) & 0x0000ff00)	| \
+					 (((x) >> 24) & 0x000000ff))
+#endif	/* CONFIG_CPU_BIG_ENDIAN */
+
+#ifdef __ASSEMBLY__
+#define __emit_inst(x)			.long __INSTR_BSWAP(x)
+#else  /* __ASSEMBLY__ */
+#define __emit_inst(x)			".long " __stringify(__INSTR_BSWAP(x)) "\n\t"
+#endif	/* __ASSEMBLY__ */
+
+#endif	/* CONFIG_BROKEN_GAS_INST */
+
 #define SYS_MIDR_EL1			sys_reg(3, 0, 0, 0, 0)
 #define SYS_MPIDR_EL1			sys_reg(3, 0, 0, 0, 5)
 #define SYS_REVIDR_EL1			sys_reg(3, 0, 0, 0, 6)
@@ -81,10 +106,10 @@
 #define REG_PSTATE_PAN_IMM		sys_reg(0, 0, 4, 0, 4)
 #define REG_PSTATE_UAO_IMM		sys_reg(0, 0, 4, 0, 3)
 
-#define SET_PSTATE_PAN(x) __inst_arm(0xd5000000 | REG_PSTATE_PAN_IMM |\
-				     (!!x)<<8 | 0x1f)
-#define SET_PSTATE_UAO(x) __inst_arm(0xd5000000 | REG_PSTATE_UAO_IMM |\
-				     (!!x)<<8 | 0x1f)
+#define SET_PSTATE_PAN(x) __emit_inst(0xd5000000 | REG_PSTATE_PAN_IMM |	\
+				      (!!x)<<8 | 0x1f)
+#define SET_PSTATE_UAO(x) __emit_inst(0xd5000000 | REG_PSTATE_UAO_IMM |	\
+				      (!!x)<<8 | 0x1f)
 
 /* Common SCTLR_ELx flags. */
 #define SCTLR_ELx_EE    (1 << 25)
@@ -228,11 +253,11 @@
 	.equ	.L__reg_num_xzr, 31
 
 	.macro	mrs_s, rt, sreg
-	.inst	0xd5200000|(\sreg)|(.L__reg_num_\rt)
+	 __emit_inst(0xd5200000|(\sreg)|(.L__reg_num_\rt))
 	.endm
 
 	.macro	msr_s, sreg, rt
-	.inst	0xd5000000|(\sreg)|(.L__reg_num_\rt)
+	__emit_inst(0xd5000000|(\sreg)|(.L__reg_num_\rt))
 	.endm
 
 #else
@@ -246,11 +271,11 @@ asm(
 "	.equ	.L__reg_num_xzr, 31\n"
 "\n"
 "	.macro	mrs_s, rt, sreg\n"
-"	.inst	0xd5200000|(\\sreg)|(.L__reg_num_\\rt)\n"
+	__emit_inst(0xd5200000|(\\sreg)|(.L__reg_num_\\rt))
 "	.endm\n"
 "\n"
 "	.macro	msr_s, sreg, rt\n"
-"	.inst	0xd5000000|(\\sreg)|(.L__reg_num_\\rt)\n"
+	__emit_inst(0xd5000000|(\\sreg)|(.L__reg_num_\\rt))
 "	.endm\n"
 );
 

arch/arm64/include/asm/thread_info.h

@@ -36,58 +36,31 @@
 
 struct task_struct;
 
+#include <asm/stack_pointer.h>
 #include <asm/types.h>
 
 typedef unsigned long mm_segment_t;
 
 /*
  * low level task data that entry.S needs immediate access to.
- * __switch_to() assumes cpu_context follows immediately after cpu_domain.
  */
 struct thread_info {
 	unsigned long		flags;		/* low level flags */
 	mm_segment_t		addr_limit;	/* address limit */
-	struct task_struct	*task;		/* main task structure */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	u64			ttbr0;		/* saved TTBR0_EL1 */
+#endif
 	int			preempt_count;	/* 0 => preemptable, <0 => bug */
-	int			cpu;		/* cpu */
 };
 
 #define INIT_THREAD_INFO(tsk)						\
 {									\
-	.task		= &tsk,						\
-	.flags		= 0,						\
 	.preempt_count	= INIT_PREEMPT_COUNT,				\
 	.addr_limit	= KERNEL_DS,					\
 }
 
-#define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
 
-/*
- * how to get the current stack pointer from C
- */
-register unsigned long current_stack_pointer asm ("sp");
-
-/*
- * how to get the thread information struct from C
- */
-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)
-{
-	unsigned long sp_el0;
-
-	asm ("mrs %0, sp_el0" : "=r" (sp_el0));
-
-	return (struct thread_info *)sp_el0;
-}
-
 #define thread_saved_pc(tsk)	\
 	((unsigned long)(tsk->thread.cpu_context.pc))
 #define thread_saved_sp(tsk)	\
@@ -112,6 +85,7 @@ static inline struct thread_info *current_thread_info(void)
 #define TIF_NEED_RESCHED	1
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
 #define TIF_FOREIGN_FPSTATE	3	/* CPU's FP state is not current's */
+#define TIF_UPROBE		4	/* uprobe breakpoint or singlestep */
 #define TIF_NOHZ		7
 #define TIF_SYSCALL_TRACE	8
 #define TIF_SYSCALL_AUDIT	9
@@ -132,10 +106,12 @@ static inline struct thread_info *current_thread_info(void)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
 #define _TIF_SECCOMP		(1 << TIF_SECCOMP)
+#define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_32BIT		(1 << TIF_32BIT)
 
 #define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
-				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE)
+				 _TIF_NOTIFY_RESUME | _TIF_FOREIGN_FPSTATE | \
+				 _TIF_UPROBE)
 
 #define _TIF_SYSCALL_WORK	(_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
 				 _TIF_SYSCALL_TRACEPOINT | _TIF_SECCOMP | \

arch/arm64/include/asm/uaccess.h

@@ -18,6 +18,12 @@
 #ifndef __ASM_UACCESS_H
 #define __ASM_UACCESS_H
 
+#include <asm/alternative.h>
+#include <asm/kernel-pgtable.h>
+#include <asm/sysreg.h>
+
+#ifndef __ASSEMBLY__
+
 /*
  * User space memory access functions
  */
@@ -26,10 +32,8 @@
 #include <linux/string.h>
 #include <linux/thread_info.h>
 
-#include <asm/alternative.h>
 #include <asm/cpufeature.h>
 #include <asm/ptrace.h>
-#include <asm/sysreg.h>
 #include <asm/errno.h>
 #include <asm/memory.h>
 #include <asm/compiler.h>
@@ -119,6 +123,99 @@ static inline void set_fs(mm_segment_t fs)
 	"	.long		(" #from " - .), (" #to " - .)\n"	\
 	"	.popsection\n"
 
+/*
+ * User access enabling/disabling.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+static inline void __uaccess_ttbr0_disable(void)
+{
+	unsigned long ttbr;
+
+	/* reserved_ttbr0 placed at the end of swapper_pg_dir */
+	ttbr = read_sysreg(ttbr1_el1) + SWAPPER_DIR_SIZE;
+	write_sysreg(ttbr, ttbr0_el1);
+	isb();
+}
+
+static inline void __uaccess_ttbr0_enable(void)
+{
+	unsigned long flags;
+
+	/*
+	 * Disable interrupts to avoid preemption between reading the 'ttbr0'
+	 * variable and the MSR. A context switch could trigger an ASID
+	 * roll-over and an update of 'ttbr0'.
+	 */
+	local_irq_save(flags);
+	write_sysreg(current_thread_info()->ttbr0, ttbr0_el1);
+	isb();
+	local_irq_restore(flags);
+}
+
+static inline bool uaccess_ttbr0_disable(void)
+{
+	if (!system_uses_ttbr0_pan())
+		return false;
+	__uaccess_ttbr0_disable();
+	return true;
+}
+
+static inline bool uaccess_ttbr0_enable(void)
+{
+	if (!system_uses_ttbr0_pan())
+		return false;
+	__uaccess_ttbr0_enable();
+	return true;
+}
+#else
+static inline bool uaccess_ttbr0_disable(void)
+{
+	return false;
+}
+
+static inline bool uaccess_ttbr0_enable(void)
+{
+	return false;
+}
+#endif
+
+#define __uaccess_disable(alt)						\
+do {									\
+	if (!uaccess_ttbr0_disable())					\
+		asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), alt,		\
+				CONFIG_ARM64_PAN));			\
+} while (0)
+
+#define __uaccess_enable(alt)						\
+do {									\
+	if (!uaccess_ttbr0_enable())					\
+		asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), alt,		\
+				CONFIG_ARM64_PAN));			\
+} while (0)
+
+static inline void uaccess_disable(void)
+{
+	__uaccess_disable(ARM64_HAS_PAN);
+}
+
+static inline void uaccess_enable(void)
+{
+	__uaccess_enable(ARM64_HAS_PAN);
+}
+
+/*
+ * These functions are no-ops when UAO is present.
+ */
+static inline void uaccess_disable_not_uao(void)
+{
+	__uaccess_disable(ARM64_ALT_PAN_NOT_UAO);
+}
+
+static inline void uaccess_enable_not_uao(void)
+{
+	__uaccess_enable(ARM64_ALT_PAN_NOT_UAO);
+}
+
 /*
  * The "__xxx" versions of the user access functions do not verify the address
  * space - it must have been done previously with a separate "access_ok()"
@@ -146,8 +243,7 @@ static inline void set_fs(mm_segment_t fs)
 do {									\
 	unsigned long __gu_val;						\
 	__chk_user_ptr(ptr);						\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
+	uaccess_enable_not_uao();					\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__get_user_asm("ldrb", "ldtrb", "%w", __gu_val, (ptr),  \
@@ -168,9 +264,8 @@ do {									\
 	default:							\
 		BUILD_BUG();						\
 	}								\
+	uaccess_disable_not_uao();					\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
 } while (0)
 
 #define __get_user(x, ptr)						\
@@ -215,8 +310,7 @@ do {									\
 do {									\
 	__typeof__(*(ptr)) __pu_val = (x);				\
 	__chk_user_ptr(ptr);						\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
+	uaccess_enable_not_uao();					\
 	switch (sizeof(*(ptr))) {					\
 	case 1:								\
 		__put_user_asm("strb", "sttrb", "%w", __pu_val, (ptr),	\
@@ -237,8 +331,7 @@ do {									\
 	default:							\
 		BUILD_BUG();						\
 	}								\
-	asm(ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_ALT_PAN_NOT_UAO,\
-			CONFIG_ARM64_PAN));				\
+	uaccess_disable_not_uao();					\
 } while (0)
 
 #define __put_user(x, ptr)						\
@@ -331,4 +424,66 @@ extern long strncpy_from_user(char *dest, const char __user *src, long count);
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
+#else	/* __ASSEMBLY__ */
+
+#include <asm/assembler.h>
+
+/*
+ * User access enabling/disabling macros.
+ */
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	.macro	__uaccess_ttbr0_disable, tmp1
+	mrs	\tmp1, ttbr1_el1		// swapper_pg_dir
+	add	\tmp1, \tmp1, #SWAPPER_DIR_SIZE	// reserved_ttbr0 at the end of swapper_pg_dir
+	msr	ttbr0_el1, \tmp1		// set reserved TTBR0_EL1
+	isb
+	.endm
+
+	.macro	__uaccess_ttbr0_enable, tmp1
+	get_thread_info \tmp1
+	ldr	\tmp1, [\tmp1, #TSK_TI_TTBR0]	// load saved TTBR0_EL1
+	msr	ttbr0_el1, \tmp1		// set the non-PAN TTBR0_EL1
+	isb
+	.endm
+
+	.macro	uaccess_ttbr0_disable, tmp1
+alternative_if_not ARM64_HAS_PAN
+	__uaccess_ttbr0_disable \tmp1
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+alternative_if_not ARM64_HAS_PAN
+	save_and_disable_irq \tmp2		// avoid preemption
+	__uaccess_ttbr0_enable \tmp1
+	restore_irq \tmp2
+alternative_else_nop_endif
+	.endm
+#else
+	.macro	uaccess_ttbr0_disable, tmp1
+	.endm
+
+	.macro	uaccess_ttbr0_enable, tmp1, tmp2
+	.endm
+#endif
+
+/*
+ * These macros are no-ops when UAO is present.
+ */
+	.macro	uaccess_disable_not_uao, tmp1
+	uaccess_ttbr0_disable \tmp1
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(1)
+alternative_else_nop_endif
+	.endm
+
+	.macro	uaccess_enable_not_uao, tmp1, tmp2
+	uaccess_ttbr0_enable \tmp1, \tmp2
+alternative_if ARM64_ALT_PAN_NOT_UAO
+	SET_PSTATE_PAN(0)
+alternative_else_nop_endif
+	.endm
+
+#endif	/* __ASSEMBLY__ */
+
 #endif /* __ASM_UACCESS_H */

arch/arm64/include/asm/uprobes.h

@@ -0,0 +1,36 @@
+/*
+ * Copyright (C) 2014-2016 Pratyush Anand <panand@redhat.com>
+ *
+ * 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.
+ */
+
+#ifndef _ASM_UPROBES_H
+#define _ASM_UPROBES_H
+
+#include <asm/debug-monitors.h>
+#include <asm/insn.h>
+#include <asm/probes.h>
+
+#define MAX_UINSN_BYTES		AARCH64_INSN_SIZE
+
+#define UPROBE_SWBP_INSN	BRK64_OPCODE_UPROBES
+#define UPROBE_SWBP_INSN_SIZE	AARCH64_INSN_SIZE
+#define UPROBE_XOL_SLOT_BYTES	MAX_UINSN_BYTES
+
+typedef u32 uprobe_opcode_t;
+
+struct arch_uprobe_task {
+};
+
+struct arch_uprobe {
+	union {
+		u8 insn[MAX_UINSN_BYTES];
+		u8 ixol[MAX_UINSN_BYTES];
+	};
+	struct arch_probe_insn api;
+	bool simulate;
+};
+
+#endif

arch/arm64/kernel/armv8_deprecated.c

@@ -14,10 +14,8 @@
 #include <linux/slab.h>
 #include <linux/sysctl.h>
 
-#include <asm/alternative.h>
 #include <asm/cpufeature.h>
 #include <asm/insn.h>
-#include <asm/opcodes.h>
 #include <asm/sysreg.h>
 #include <asm/system_misc.h>
 #include <asm/traps.h>
@@ -285,10 +283,10 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 #define __SWP_LL_SC_LOOPS	4
 
 #define __user_swpX_asm(data, addr, res, temp, temp2, B)	\
+do {								\
+	uaccess_enable();					\
 	__asm__ __volatile__(					\
 	"	mov		%w3, %w7\n"			\
-	ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN,	\
-		    CONFIG_ARM64_PAN)				\
 	"0:	ldxr"B"		%w2, [%4]\n"			\
 	"1:	stxr"B"		%w0, %w1, [%4]\n"		\
 	"	cbz		%w0, 2f\n"			\
@@ -306,12 +304,12 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table)
 	"	.popsection"					\
 	_ASM_EXTABLE(0b, 4b)					\
 	_ASM_EXTABLE(1b, 4b)					\
-	ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN,	\
-		CONFIG_ARM64_PAN)				\
 	: "=&r" (res), "+r" (data), "=&r" (temp), "=&r" (temp2)	\
 	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT),		\
 	  "i" (__SWP_LL_SC_LOOPS)				\
-	: "memory")
+	: "memory");						\
+	uaccess_disable();					\
+} while (0)
 
 #define __user_swp_asm(data, addr, res, temp, temp2) \
 	__user_swpX_asm(data, addr, res, temp, temp2, "")
@@ -352,6 +350,10 @@ static int emulate_swpX(unsigned int address, unsigned int *data,
 	return res;
 }
 
+#define ARM_OPCODE_CONDTEST_FAIL   0
+#define ARM_OPCODE_CONDTEST_PASS   1
+#define ARM_OPCODE_CONDTEST_UNCOND 2
+
 #define	ARM_OPCODE_CONDITION_UNCOND	0xf
 
 static unsigned int __kprobes aarch32_check_condition(u32 opcode, u32 psr)

arch/arm64/kernel/asm-offsets.c

@@ -36,11 +36,13 @@ int main(void)
 {
   DEFINE(TSK_ACTIVE_MM,		offsetof(struct task_struct, active_mm));
   BLANK();
-  DEFINE(TI_FLAGS,		offsetof(struct thread_info, flags));
-  DEFINE(TI_PREEMPT,		offsetof(struct thread_info, preempt_count));
-  DEFINE(TI_ADDR_LIMIT,		offsetof(struct thread_info, addr_limit));
-  DEFINE(TI_TASK,		offsetof(struct thread_info, task));
-  DEFINE(TI_CPU,		offsetof(struct thread_info, cpu));
+  DEFINE(TSK_TI_FLAGS,		offsetof(struct task_struct, thread_info.flags));
+  DEFINE(TSK_TI_PREEMPT,	offsetof(struct task_struct, thread_info.preempt_count));
+  DEFINE(TSK_TI_ADDR_LIMIT,	offsetof(struct task_struct, thread_info.addr_limit));
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+  DEFINE(TSK_TI_TTBR0,		offsetof(struct task_struct, thread_info.ttbr0));
+#endif
+  DEFINE(TSK_STACK,		offsetof(struct task_struct, stack));
   BLANK();
   DEFINE(THREAD_CPU_CONTEXT,	offsetof(struct task_struct, thread.cpu_context));
   BLANK();
@@ -123,6 +125,7 @@ int main(void)
   DEFINE(TZ_DSTTIME,		offsetof(struct timezone, tz_dsttime));
   BLANK();
   DEFINE(CPU_BOOT_STACK,	offsetof(struct secondary_data, stack));
+  DEFINE(CPU_BOOT_TASK,		offsetof(struct secondary_data, task));
   BLANK();
 #ifdef CONFIG_KVM_ARM_HOST
   DEFINE(VCPU_CONTEXT,		offsetof(struct kvm_vcpu, arch.ctxt));

arch/arm64/kernel/cpufeature.c

@@ -47,6 +47,7 @@ unsigned int compat_elf_hwcap2 __read_mostly;
 #endif
 
 DECLARE_BITMAP(cpu_hwcaps, ARM64_NCAPS);
+EXPORT_SYMBOL(cpu_hwcaps);
 
 DEFINE_STATIC_KEY_ARRAY_FALSE(cpu_hwcap_keys, ARM64_NCAPS);
 EXPORT_SYMBOL(cpu_hwcap_keys);
@@ -746,6 +747,14 @@ static bool hyp_offset_low(const struct arm64_cpu_capabilities *entry,
 	return idmap_addr > GENMASK(VA_BITS - 2, 0) && !is_kernel_in_hyp_mode();
 }
 
+static bool has_no_fpsimd(const struct arm64_cpu_capabilities *entry, int __unused)
+{
+	u64 pfr0 = read_system_reg(SYS_ID_AA64PFR0_EL1);
+
+	return cpuid_feature_extract_signed_field(pfr0,
+					ID_AA64PFR0_FP_SHIFT) < 0;
+}
+
 static const struct arm64_cpu_capabilities arm64_features[] = {
 	{
 		.desc = "GIC system register CPU interface",
@@ -829,6 +838,13 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.def_scope = SCOPE_SYSTEM,
 		.matches = hyp_offset_low,
 	},
+	{
+		/* FP/SIMD is not implemented */
+		.capability = ARM64_HAS_NO_FPSIMD,
+		.def_scope = SCOPE_SYSTEM,
+		.min_field_value = 0,
+		.matches = has_no_fpsimd,
+	},
 	{},
 };
 
@@ -1102,5 +1118,5 @@ void __init setup_cpu_features(void)
 static bool __maybe_unused
 cpufeature_pan_not_uao(const struct arm64_cpu_capabilities *entry, int __unused)
 {
-	return (cpus_have_cap(ARM64_HAS_PAN) && !cpus_have_cap(ARM64_HAS_UAO));
+	return (cpus_have_const_cap(ARM64_HAS_PAN) && !cpus_have_const_cap(ARM64_HAS_UAO));
 }

arch/arm64/kernel/debug-monitors.c

@@ -226,6 +226,8 @@ static void send_user_sigtrap(int si_code)
 static int single_step_handler(unsigned long addr, unsigned int esr,
 			       struct pt_regs *regs)
 {
+	bool handler_found = false;
+
 	/*
 	 * If we are stepping a pending breakpoint, call the hw_breakpoint
 	 * handler first.
@@ -233,7 +235,14 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 	if (!reinstall_suspended_bps(regs))
 		return 0;
 
-	if (user_mode(regs)) {
+#ifdef	CONFIG_KPROBES
+	if (kprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED)
+		handler_found = true;
+#endif
+	if (!handler_found && call_step_hook(regs, esr) == DBG_HOOK_HANDLED)
+		handler_found = true;
+
+	if (!handler_found && user_mode(regs)) {
 		send_user_sigtrap(TRAP_TRACE);
 
 		/*
@@ -243,15 +252,8 @@ static int single_step_handler(unsigned long addr, unsigned int esr,
 		 * to the active-not-pending state).
 		 */
 		user_rewind_single_step(current);
-	} else {
-#ifdef	CONFIG_KPROBES
-		if (kprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED)
-			return 0;
-#endif
-		if (call_step_hook(regs, esr) == DBG_HOOK_HANDLED)
-			return 0;
-
-		pr_warning("Unexpected kernel single-step exception at EL1\n");
+	} else if (!handler_found) {
+		pr_warn("Unexpected kernel single-step exception at EL1\n");
 		/*
 		 * Re-enable stepping since we know that we will be
 		 * returning to regs.
@@ -304,16 +306,20 @@ NOKPROBE_SYMBOL(call_break_hook);
 static int brk_handler(unsigned long addr, unsigned int esr,
 		       struct pt_regs *regs)
 {
-	if (user_mode(regs)) {
-		send_user_sigtrap(TRAP_BRKPT);
-	}
+	bool handler_found = false;
+
 #ifdef	CONFIG_KPROBES
-	else if ((esr & BRK64_ESR_MASK) == BRK64_ESR_KPROBES) {
-		if (kprobe_breakpoint_handler(regs, esr) != DBG_HOOK_HANDLED)
-			return -EFAULT;
+	if ((esr & BRK64_ESR_MASK) == BRK64_ESR_KPROBES) {
+		if (kprobe_breakpoint_handler(regs, esr) == DBG_HOOK_HANDLED)
+			handler_found = true;
 	}
 #endif
-	else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) {
+	if (!handler_found && call_break_hook(regs, esr) == DBG_HOOK_HANDLED)
+		handler_found = true;
+
+	if (!handler_found && user_mode(regs)) {
+		send_user_sigtrap(TRAP_BRKPT);
+	} else if (!handler_found) {
 		pr_warn("Unexpected kernel BRK exception at EL1\n");
 		return -EFAULT;
 	}

arch/arm64/kernel/efi.c

@@ -62,8 +62,8 @@ struct screen_info screen_info __section(.data);
 int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 {
 	pteval_t prot_val = create_mapping_protection(md);
-	bool allow_block_mappings = (md->type != EFI_RUNTIME_SERVICES_CODE &&
-				     md->type != EFI_RUNTIME_SERVICES_DATA);
+	bool page_mappings_only = (md->type == EFI_RUNTIME_SERVICES_CODE ||
+				   md->type == EFI_RUNTIME_SERVICES_DATA);
 
 	if (!PAGE_ALIGNED(md->phys_addr) ||
 	    !PAGE_ALIGNED(md->num_pages << EFI_PAGE_SHIFT)) {
@@ -76,12 +76,12 @@ int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md)
 		 * from the MMU routines. So avoid block mappings altogether in
 		 * that case.
 		 */
-		allow_block_mappings = false;
+		page_mappings_only = true;
 	}
 
 	create_pgd_mapping(mm, md->phys_addr, md->virt_addr,
 			   md->num_pages << EFI_PAGE_SHIFT,
-			   __pgprot(prot_val | PTE_NG), allow_block_mappings);
+			   __pgprot(prot_val | PTE_NG), page_mappings_only);
 	return 0;
 }
 

arch/arm64/kernel/entry.S

@@ -29,7 +29,9 @@
 #include <asm/esr.h>
 #include <asm/irq.h>
 #include <asm/memory.h>
+#include <asm/ptrace.h>
 #include <asm/thread_info.h>
+#include <asm/uaccess.h>
 #include <asm/unistd.h>
 
 /*
@@ -90,9 +92,8 @@
 
 	.if	\el == 0
 	mrs	x21, sp_el0
-	mov	tsk, sp
-	and	tsk, tsk, #~(THREAD_SIZE - 1)	// Ensure MDSCR_EL1.SS is clear,
-	ldr	x19, [tsk, #TI_FLAGS]		// since we can unmask debug
+	ldr_this_cpu	tsk, __entry_task, x20	// Ensure MDSCR_EL1.SS is clear,
+	ldr	x19, [tsk, #TSK_TI_FLAGS]	// since we can unmask debug
 	disable_step_tsk x19, x20		// exceptions when scheduling.
 
 	mov	x29, xzr			// fp pointed to user-space
@@ -100,15 +101,41 @@
 	add	x21, sp, #S_FRAME_SIZE
 	get_thread_info tsk
 	/* Save the task's original addr_limit and set USER_DS (TASK_SIZE_64) */
-	ldr	x20, [tsk, #TI_ADDR_LIMIT]
+	ldr	x20, [tsk, #TSK_TI_ADDR_LIMIT]
 	str	x20, [sp, #S_ORIG_ADDR_LIMIT]
 	mov	x20, #TASK_SIZE_64
-	str	x20, [tsk, #TI_ADDR_LIMIT]
+	str	x20, [tsk, #TSK_TI_ADDR_LIMIT]
 	/* 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
 	stp	lr, x21, [sp, #S_LR]
+
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	/*
+	 * Set the TTBR0 PAN bit in SPSR. When the exception is taken from
+	 * EL0, there is no need to check the state of TTBR0_EL1 since
+	 * accesses are always enabled.
+	 * Note that the meaning of this bit differs from the ARMv8.1 PAN
+	 * feature as all TTBR0_EL1 accesses are disabled, not just those to
+	 * user mappings.
+	 */
+alternative_if ARM64_HAS_PAN
+	b	1f				// skip TTBR0 PAN
+alternative_else_nop_endif
+
+	.if	\el != 0
+	mrs	x21, ttbr0_el1
+	tst	x21, #0xffff << 48		// Check for the reserved ASID
+	orr	x23, x23, #PSR_PAN_BIT		// Set the emulated PAN in the saved SPSR
+	b.eq	1f				// TTBR0 access already disabled
+	and	x23, x23, #~PSR_PAN_BIT		// Clear the emulated PAN in the saved SPSR
+	.endif
+
+	__uaccess_ttbr0_disable x21
+1:
+#endif
+
 	stp	x22, x23, [sp, #S_PC]
 
 	/*
@@ -139,7 +166,7 @@
 	.if	\el != 0
 	/* Restore the task's original addr_limit. */
 	ldr	x20, [sp, #S_ORIG_ADDR_LIMIT]
-	str	x20, [tsk, #TI_ADDR_LIMIT]
+	str	x20, [tsk, #TSK_TI_ADDR_LIMIT]
 
 	/* No need to restore UAO, it will be restored from SPSR_EL1 */
 	.endif
@@ -147,6 +174,40 @@
 	ldp	x21, x22, [sp, #S_PC]		// load ELR, SPSR
 	.if	\el == 0
 	ct_user_enter
+	.endif
+
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	/*
+	 * Restore access to TTBR0_EL1. If returning to EL0, no need for SPSR
+	 * PAN bit checking.
+	 */
+alternative_if ARM64_HAS_PAN
+	b	2f				// skip TTBR0 PAN
+alternative_else_nop_endif
+
+	.if	\el != 0
+	tbnz	x22, #22, 1f			// Skip re-enabling TTBR0 access if the PSR_PAN_BIT is set
+	.endif
+
+	__uaccess_ttbr0_enable x0
+
+	.if	\el == 0
+	/*
+	 * Enable errata workarounds only if returning to user. The only
+	 * workaround currently required for TTBR0_EL1 changes are for the
+	 * Cavium erratum 27456 (broadcast TLBI instructions may cause I-cache
+	 * corruption).
+	 */
+	post_ttbr0_update_workaround
+	.endif
+1:
+	.if	\el != 0
+	and	x22, x22, #~PSR_PAN_BIT		// ARMv8.0 CPUs do not understand this bit
+	.endif
+2:
+#endif
+
+	.if	\el == 0
 	ldr	x23, [sp, #S_SP]		// load return stack pointer
 	msr	sp_el0, x23
 #ifdef CONFIG_ARM64_ERRATUM_845719
@@ -162,6 +223,7 @@ alternative_if ARM64_WORKAROUND_845719
 alternative_else_nop_endif
 #endif
 	.endif
+
 	msr	elr_el1, x21			// set up the return data
 	msr	spsr_el1, x22
 	ldp	x0, x1, [sp, #16 * 0]
@@ -184,23 +246,20 @@ alternative_else_nop_endif
 	eret					// return to kernel
 	.endm
 
-	.macro	get_thread_info, rd
-	mrs	\rd, sp_el0
-	.endm
-
 	.macro	irq_stack_entry
 	mov	x19, sp			// preserve the original sp
 
 	/*
-	 * Compare sp with the current thread_info, if the top
-	 * ~(THREAD_SIZE - 1) bits match, we are on a task stack, and
-	 * should switch to the irq stack.
+	 * Compare sp with the base of the task stack.
+	 * If the top ~(THREAD_SIZE - 1) bits match, we are on a task stack,
+	 * and should switch to the irq stack.
 	 */
-	and	x25, x19, #~(THREAD_SIZE - 1)
-	cmp	x25, tsk
-	b.ne	9998f
+	ldr	x25, [tsk, TSK_STACK]
+	eor	x25, x25, x19
+	and	x25, x25, #~(THREAD_SIZE - 1)
+	cbnz	x25, 9998f
 
-	this_cpu_ptr irq_stack, x25, x26
+	adr_this_cpu x25, irq_stack, x26
 	mov	x26, #IRQ_STACK_START_SP
 	add	x26, x25, x26
 
@@ -427,9 +486,9 @@ el1_irq:
 	irq_handler
 
 #ifdef CONFIG_PREEMPT
-	ldr	w24, [tsk, #TI_PREEMPT]		// get preempt count
+	ldr	w24, [tsk, #TSK_TI_PREEMPT]	// get preempt count
 	cbnz	w24, 1f				// preempt count != 0
-	ldr	x0, [tsk, #TI_FLAGS]		// get flags
+	ldr	x0, [tsk, #TSK_TI_FLAGS]	// get flags
 	tbz	x0, #TIF_NEED_RESCHED, 1f	// needs rescheduling?
 	bl	el1_preempt
 1:
@@ -444,7 +503,7 @@ ENDPROC(el1_irq)
 el1_preempt:
 	mov	x24, lr
 1:	bl	preempt_schedule_irq		// irq en/disable is done inside
-	ldr	x0, [tsk, #TI_FLAGS]		// get new tasks TI_FLAGS
+	ldr	x0, [tsk, #TSK_TI_FLAGS]	// get new tasks TI_FLAGS
 	tbnz	x0, #TIF_NEED_RESCHED, 1b	// needs rescheduling?
 	ret	x24
 #endif
@@ -674,8 +733,7 @@ ENTRY(cpu_switch_to)
 	ldp	x29, x9, [x8], #16
 	ldr	lr, [x8]
 	mov	sp, x9
-	and	x9, x9, #~(THREAD_SIZE - 1)
-	msr	sp_el0, x9
+	msr	sp_el0, x1
 	ret
 ENDPROC(cpu_switch_to)
 
@@ -686,7 +744,7 @@ ENDPROC(cpu_switch_to)
 ret_fast_syscall:
 	disable_irq				// disable interrupts
 	str	x0, [sp, #S_X0]			// returned x0
-	ldr	x1, [tsk, #TI_FLAGS]		// re-check for syscall tracing
+	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for syscall tracing
 	and	x2, x1, #_TIF_SYSCALL_WORK
 	cbnz	x2, ret_fast_syscall_trace
 	and	x2, x1, #_TIF_WORK_MASK
@@ -706,14 +764,14 @@ work_pending:
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_on		// enabled while in userspace
 #endif
-	ldr	x1, [tsk, #TI_FLAGS]		// re-check for single-step
+	ldr	x1, [tsk, #TSK_TI_FLAGS]	// re-check for single-step
 	b	finish_ret_to_user
 /*
  * "slow" syscall return path.
  */
 ret_to_user:
 	disable_irq				// disable interrupts
-	ldr	x1, [tsk, #TI_FLAGS]
+	ldr	x1, [tsk, #TSK_TI_FLAGS]
 	and	x2, x1, #_TIF_WORK_MASK
 	cbnz	x2, work_pending
 finish_ret_to_user:
@@ -746,7 +804,7 @@ el0_svc_naked:					// compat entry point
 	enable_dbg_and_irq
 	ct_user_exit 1
 
-	ldr	x16, [tsk, #TI_FLAGS]		// check for syscall hooks
+	ldr	x16, [tsk, #TSK_TI_FLAGS]	// check for syscall hooks
 	tst	x16, #_TIF_SYSCALL_WORK
 	b.ne	__sys_trace
 	cmp     scno, sc_nr                     // check upper syscall limit

arch/arm64/kernel/fpsimd.c

@@ -127,6 +127,8 @@ void do_fpsimd_exc(unsigned int esr, struct pt_regs *regs)
 
 void fpsimd_thread_switch(struct task_struct *next)
 {
+	if (!system_supports_fpsimd())
+		return;
 	/*
 	 * Save the current FPSIMD state to memory, but only if whatever is in
 	 * the registers is in fact the most recent userland FPSIMD state of
@@ -157,6 +159,8 @@ void fpsimd_thread_switch(struct task_struct *next)
 
 void fpsimd_flush_thread(void)
 {
+	if (!system_supports_fpsimd())
+		return;
 	memset(&current->thread.fpsimd_state, 0, sizeof(struct fpsimd_state));
 	fpsimd_flush_task_state(current);
 	set_thread_flag(TIF_FOREIGN_FPSTATE);
@@ -168,6 +172,8 @@ void fpsimd_flush_thread(void)
  */
 void fpsimd_preserve_current_state(void)
 {
+	if (!system_supports_fpsimd())
+		return;
 	preempt_disable();
 	if (!test_thread_flag(TIF_FOREIGN_FPSTATE))
 		fpsimd_save_state(&current->thread.fpsimd_state);
@@ -181,6 +187,8 @@ void fpsimd_preserve_current_state(void)
  */
 void fpsimd_restore_current_state(void)
 {
+	if (!system_supports_fpsimd())
+		return;
 	preempt_disable();
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
 		struct fpsimd_state *st = &current->thread.fpsimd_state;
@@ -199,6 +207,8 @@ void fpsimd_restore_current_state(void)
  */
 void fpsimd_update_current_state(struct fpsimd_state *state)
 {
+	if (!system_supports_fpsimd())
+		return;
 	preempt_disable();
 	fpsimd_load_state(state);
 	if (test_and_clear_thread_flag(TIF_FOREIGN_FPSTATE)) {
@@ -228,6 +238,8 @@ static DEFINE_PER_CPU(struct fpsimd_partial_state, softirq_fpsimdstate);
  */
 void kernel_neon_begin_partial(u32 num_regs)
 {
+	if (WARN_ON(!system_supports_fpsimd()))
+		return;
 	if (in_interrupt()) {
 		struct fpsimd_partial_state *s = this_cpu_ptr(
 			in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);
@@ -252,6 +264,8 @@ EXPORT_SYMBOL(kernel_neon_begin_partial);
 
 void kernel_neon_end(void)
 {
+	if (!system_supports_fpsimd())
+		return;
 	if (in_interrupt()) {
 		struct fpsimd_partial_state *s = this_cpu_ptr(
 			in_irq() ? &hardirq_fpsimdstate : &softirq_fpsimdstate);

arch/arm64/kernel/head.S

@@ -326,14 +326,14 @@ __create_page_tables:
 	 * dirty cache lines being evicted.
 	 */
 	adrp	x0, idmap_pg_dir
-	adrp	x1, swapper_pg_dir + SWAPPER_DIR_SIZE
+	adrp	x1, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
 	bl	__inval_cache_range
 
 	/*
 	 * Clear the idmap and swapper page tables.
 	 */
 	adrp	x0, idmap_pg_dir
-	adrp	x6, swapper_pg_dir + SWAPPER_DIR_SIZE
+	adrp	x6, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
 1:	stp	xzr, xzr, [x0], #16
 	stp	xzr, xzr, [x0], #16
 	stp	xzr, xzr, [x0], #16
@@ -412,7 +412,7 @@ __create_page_tables:
 	 * tables again to remove any speculatively loaded cache lines.
 	 */
 	adrp	x0, idmap_pg_dir
-	adrp	x1, swapper_pg_dir + SWAPPER_DIR_SIZE
+	adrp	x1, swapper_pg_dir + SWAPPER_DIR_SIZE + RESERVED_TTBR0_SIZE
 	dmb	sy
 	bl	__inval_cache_range
 
@@ -428,7 +428,8 @@ ENDPROC(__create_page_tables)
 __primary_switched:
 	adrp	x4, init_thread_union
 	add	sp, x4, #THREAD_SIZE
-	msr	sp_el0, x4			// Save thread_info
+	adr_l	x5, init_task
+	msr	sp_el0, x5			// Save thread_info
 
 	adr_l	x8, vectors			// load VBAR_EL1 with virtual
 	msr	vbar_el1, x8			// vector table address
@@ -524,10 +525,21 @@ set_hcr:
 	msr	hcr_el2, x0
 	isb
 
-	/* Generic timers. */
+	/*
+	 * Allow Non-secure EL1 and EL0 to access physical timer and counter.
+	 * This is not necessary for VHE, since the host kernel runs in EL2,
+	 * and EL0 accesses are configured in the later stage of boot process.
+	 * Note that when HCR_EL2.E2H == 1, CNTHCTL_EL2 has the same bit layout
+	 * as CNTKCTL_EL1, and CNTKCTL_EL1 accessing instructions are redefined
+	 * to access CNTHCTL_EL2. This allows the kernel designed to run at EL1
+	 * to transparently mess with the EL0 bits via CNTKCTL_EL1 access in
+	 * EL2.
+	 */
+	cbnz	x2, 1f
 	mrs	x0, cnthctl_el2
 	orr	x0, x0, #3			// Enable EL1 physical timers
 	msr	cnthctl_el2, x0
+1:
 	msr	cntvoff_el2, xzr		// Clear virtual offset
 
 #ifdef CONFIG_ARM_GIC_V3
@@ -699,10 +711,10 @@ __secondary_switched:
 	isb
 
 	adr_l	x0, secondary_data
-	ldr	x0, [x0, #CPU_BOOT_STACK]	// get secondary_data.stack
-	mov	sp, x0
-	and	x0, x0, #~(THREAD_SIZE - 1)
-	msr	sp_el0, x0			// save thread_info
+	ldr	x1, [x0, #CPU_BOOT_STACK]	// get secondary_data.stack
+	mov	sp, x1
+	ldr	x2, [x0, #CPU_BOOT_TASK]
+	msr	sp_el0, x2
 	mov	x29, #0
 	b	secondary_start_kernel
 ENDPROC(__secondary_switched)

arch/arm64/kernel/hw_breakpoint.c

@@ -317,9 +317,21 @@ static int get_hbp_len(u8 hbp_len)
 	case ARM_BREAKPOINT_LEN_2:
 		len_in_bytes = 2;
 		break;
+	case ARM_BREAKPOINT_LEN_3:
+		len_in_bytes = 3;
+		break;
 	case ARM_BREAKPOINT_LEN_4:
 		len_in_bytes = 4;
 		break;
+	case ARM_BREAKPOINT_LEN_5:
+		len_in_bytes = 5;
+		break;
+	case ARM_BREAKPOINT_LEN_6:
+		len_in_bytes = 6;
+		break;
+	case ARM_BREAKPOINT_LEN_7:
+		len_in_bytes = 7;
+		break;
 	case ARM_BREAKPOINT_LEN_8:
 		len_in_bytes = 8;
 		break;
@@ -349,7 +361,7 @@ int arch_check_bp_in_kernelspace(struct perf_event *bp)
  * to generic breakpoint descriptions.
  */
 int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
-			   int *gen_len, int *gen_type)
+			   int *gen_len, int *gen_type, int *offset)
 {
 	/* Type */
 	switch (ctrl.type) {
@@ -369,17 +381,33 @@ int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl,
 		return -EINVAL;
 	}
 
+	if (!ctrl.len)
+		return -EINVAL;
+	*offset = __ffs(ctrl.len);
+
 	/* Len */
-	switch (ctrl.len) {
+	switch (ctrl.len >> *offset) {
 	case ARM_BREAKPOINT_LEN_1:
 		*gen_len = HW_BREAKPOINT_LEN_1;
 		break;
 	case ARM_BREAKPOINT_LEN_2:
 		*gen_len = HW_BREAKPOINT_LEN_2;
 		break;
+	case ARM_BREAKPOINT_LEN_3:
+		*gen_len = HW_BREAKPOINT_LEN_3;
+		break;
 	case ARM_BREAKPOINT_LEN_4:
 		*gen_len = HW_BREAKPOINT_LEN_4;
 		break;
+	case ARM_BREAKPOINT_LEN_5:
+		*gen_len = HW_BREAKPOINT_LEN_5;
+		break;
+	case ARM_BREAKPOINT_LEN_6:
+		*gen_len = HW_BREAKPOINT_LEN_6;
+		break;
+	case ARM_BREAKPOINT_LEN_7:
+		*gen_len = HW_BREAKPOINT_LEN_7;
+		break;
 	case ARM_BREAKPOINT_LEN_8:
 		*gen_len = HW_BREAKPOINT_LEN_8;
 		break;
@@ -423,9 +451,21 @@ static int arch_build_bp_info(struct perf_event *bp)
 	case HW_BREAKPOINT_LEN_2:
 		info->ctrl.len = ARM_BREAKPOINT_LEN_2;
 		break;
+	case HW_BREAKPOINT_LEN_3:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_3;
+		break;
 	case HW_BREAKPOINT_LEN_4:
 		info->ctrl.len = ARM_BREAKPOINT_LEN_4;
 		break;
+	case HW_BREAKPOINT_LEN_5:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_5;
+		break;
+	case HW_BREAKPOINT_LEN_6:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_6;
+		break;
+	case HW_BREAKPOINT_LEN_7:
+		info->ctrl.len = ARM_BREAKPOINT_LEN_7;
+		break;
 	case HW_BREAKPOINT_LEN_8:
 		info->ctrl.len = ARM_BREAKPOINT_LEN_8;
 		break;
@@ -517,18 +557,17 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		default:
 			return -EINVAL;
 		}
-
-		info->address &= ~alignment_mask;
-		info->ctrl.len <<= offset;
 	} else {
 		if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE)
 			alignment_mask = 0x3;
 		else
 			alignment_mask = 0x7;
-		if (info->address & alignment_mask)
-			return -EINVAL;
+		offset = info->address & alignment_mask;
 	}
 
+	info->address &= ~alignment_mask;
+	info->ctrl.len <<= offset;
+
 	/*
 	 * Disallow per-task kernel breakpoints since these would
 	 * complicate the stepping code.
@@ -661,12 +700,47 @@ unlock:
 }
 NOKPROBE_SYMBOL(breakpoint_handler);
 
+/*
+ * Arm64 hardware does not always report a watchpoint hit address that matches
+ * one of the watchpoints set. It can also report an address "near" the
+ * watchpoint if a single instruction access both watched and unwatched
+ * addresses. There is no straight-forward way, short of disassembling the
+ * offending instruction, to map that address back to the watchpoint. This
+ * function computes the distance of the memory access from the watchpoint as a
+ * heuristic for the likelyhood that a given access triggered the watchpoint.
+ *
+ * See Section D2.10.5 "Determining the memory location that caused a Watchpoint
+ * exception" of ARMv8 Architecture Reference Manual for details.
+ *
+ * The function returns the distance of the address from the bytes watched by
+ * the watchpoint. In case of an exact match, it returns 0.
+ */
+static u64 get_distance_from_watchpoint(unsigned long addr, u64 val,
+					struct arch_hw_breakpoint_ctrl *ctrl)
+{
+	u64 wp_low, wp_high;
+	u32 lens, lene;
+
+	lens = __ffs(ctrl->len);
+	lene = __fls(ctrl->len);
+
+	wp_low = val + lens;
+	wp_high = val + lene;
+	if (addr < wp_low)
+		return wp_low - addr;
+	else if (addr > wp_high)
+		return addr - wp_high;
+	else
+		return 0;
+}
+
 static int watchpoint_handler(unsigned long addr, unsigned int esr,
 			      struct pt_regs *regs)
 {
-	int i, step = 0, *kernel_step, access;
+	int i, step = 0, *kernel_step, access, closest_match = 0;
+	u64 min_dist = -1, dist;
 	u32 ctrl_reg;
-	u64 val, alignment_mask;
+	u64 val;
 	struct perf_event *wp, **slots;
 	struct debug_info *debug_info;
 	struct arch_hw_breakpoint *info;
@@ -675,35 +749,15 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 	slots = this_cpu_ptr(wp_on_reg);
 	debug_info = &current->thread.debug;
 
+	/*
+	 * Find all watchpoints that match the reported address. If no exact
+	 * match is found. Attribute the hit to the closest watchpoint.
+	 */
+	rcu_read_lock();
 	for (i = 0; i < core_num_wrps; ++i) {
-		rcu_read_lock();
-
 		wp = slots[i];
-
 		if (wp == NULL)
-			goto unlock;
-
-		info = counter_arch_bp(wp);
-		/* AArch32 watchpoints are either 4 or 8 bytes aligned. */
-		if (is_compat_task()) {
-			if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
-				alignment_mask = 0x7;
-			else
-				alignment_mask = 0x3;
-		} else {
-			alignment_mask = 0x7;
-		}
-
-		/* Check if the watchpoint value matches. */
-		val = read_wb_reg(AARCH64_DBG_REG_WVR, i);
-		if (val != (addr & ~alignment_mask))
-			goto unlock;
-
-		/* Possible match, check the byte address select to confirm. */
-		ctrl_reg = read_wb_reg(AARCH64_DBG_REG_WCR, i);
-		decode_ctrl_reg(ctrl_reg, &ctrl);
-		if (!((1 << (addr & alignment_mask)) & ctrl.len))
-			goto unlock;
+			continue;
 
 		/*
 		 * Check that the access type matches.
@@ -712,18 +766,41 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 		access = (esr & AARCH64_ESR_ACCESS_MASK) ? HW_BREAKPOINT_W :
 			 HW_BREAKPOINT_R;
 		if (!(access & hw_breakpoint_type(wp)))
-			goto unlock;
+			continue;
 
+		/* Check if the watchpoint value and byte select match. */
+		val = read_wb_reg(AARCH64_DBG_REG_WVR, i);
+		ctrl_reg = read_wb_reg(AARCH64_DBG_REG_WCR, i);
+		decode_ctrl_reg(ctrl_reg, &ctrl);
+		dist = get_distance_from_watchpoint(addr, val, &ctrl);
+		if (dist < min_dist) {
+			min_dist = dist;
+			closest_match = i;
+		}
+		/* Is this an exact match? */
+		if (dist != 0)
+			continue;
+
+		info = counter_arch_bp(wp);
 		info->trigger = addr;
 		perf_bp_event(wp, regs);
 
 		/* Do we need to handle the stepping? */
 		if (is_default_overflow_handler(wp))
 			step = 1;
+	}
+	if (min_dist > 0 && min_dist != -1) {
+		/* No exact match found. */
+		wp = slots[closest_match];
+		info = counter_arch_bp(wp);
+		info->trigger = addr;
+		perf_bp_event(wp, regs);
 
-unlock:
-		rcu_read_unlock();
+		/* Do we need to handle the stepping? */
+		if (is_default_overflow_handler(wp))
+			step = 1;
 	}
+	rcu_read_unlock();
 
 	if (!step)
 		return 0;

arch/arm64/kernel/insn.c

@@ -30,7 +30,6 @@
 #include <asm/cacheflush.h>
 #include <asm/debug-monitors.h>
 #include <asm/fixmap.h>
-#include <asm/opcodes.h>
 #include <asm/insn.h>
 
 #define AARCH64_INSN_SF_BIT	BIT(31)

arch/arm64/kernel/kgdb.c

@@ -247,6 +247,9 @@ NOKPROBE_SYMBOL(kgdb_compiled_brk_fn);
 
 static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr)
 {
+	if (!kgdb_single_step)
+		return DBG_HOOK_ERROR;
+
 	kgdb_handle_exception(1, SIGTRAP, 0, regs);
 	return 0;
 }

arch/arm64/kernel/probes/Makefile

@@ -1,3 +1,5 @@
 obj-$(CONFIG_KPROBES)		+= kprobes.o decode-insn.o	\
 				   kprobes_trampoline.o		\
 				   simulate-insn.o
+obj-$(CONFIG_UPROBES)		+= uprobes.o decode-insn.o	\
+				   simulate-insn.o

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

@@ -17,7 +17,6 @@
 #include <linux/kprobes.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
-#include <asm/kprobes.h>
 #include <asm/insn.h>
 #include <asm/sections.h>
 
@@ -78,8 +77,8 @@ static bool __kprobes aarch64_insn_is_steppable(u32 insn)
  *   INSN_GOOD         If instruction is supported and uses instruction slot,
  *   INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot.
  */
-static enum kprobe_insn __kprobes
-arm_probe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+enum probe_insn __kprobes
+arm_probe_decode_insn(probe_opcode_t insn, struct arch_probe_insn *api)
 {
 	/*
 	 * Instructions reading or modifying the PC won't work from the XOL
@@ -89,26 +88,26 @@ arm_probe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 		return INSN_GOOD;
 
 	if (aarch64_insn_is_bcond(insn)) {
-		asi->handler = simulate_b_cond;
+		api->handler = simulate_b_cond;
 	} else if (aarch64_insn_is_cbz(insn) ||
 	    aarch64_insn_is_cbnz(insn)) {
-		asi->handler = simulate_cbz_cbnz;
+		api->handler = simulate_cbz_cbnz;
 	} else if (aarch64_insn_is_tbz(insn) ||
 	    aarch64_insn_is_tbnz(insn)) {
-		asi->handler = simulate_tbz_tbnz;
+		api->handler = simulate_tbz_tbnz;
 	} else if (aarch64_insn_is_adr_adrp(insn)) {
-		asi->handler = simulate_adr_adrp;
+		api->handler = simulate_adr_adrp;
 	} else if (aarch64_insn_is_b(insn) ||
 	    aarch64_insn_is_bl(insn)) {
-		asi->handler = simulate_b_bl;
+		api->handler = simulate_b_bl;
 	} else if (aarch64_insn_is_br(insn) ||
 	    aarch64_insn_is_blr(insn) ||
 	    aarch64_insn_is_ret(insn)) {
-		asi->handler = simulate_br_blr_ret;
+		api->handler = simulate_br_blr_ret;
 	} else if (aarch64_insn_is_ldr_lit(insn)) {
-		asi->handler = simulate_ldr_literal;
+		api->handler = simulate_ldr_literal;
 	} else if (aarch64_insn_is_ldrsw_lit(insn)) {
-		asi->handler = simulate_ldrsw_literal;
+		api->handler = simulate_ldrsw_literal;
 	} else {
 		/*
 		 * Instruction cannot be stepped out-of-line and we don't
@@ -120,6 +119,7 @@ arm_probe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	return INSN_GOOD_NO_SLOT;
 }
 
+#ifdef CONFIG_KPROBES
 static bool __kprobes
 is_probed_address_atomic(kprobe_opcode_t *scan_start, kprobe_opcode_t *scan_end)
 {
@@ -138,12 +138,12 @@ is_probed_address_atomic(kprobe_opcode_t *scan_start, kprobe_opcode_t *scan_end)
 	return false;
 }
 
-enum kprobe_insn __kprobes
+enum probe_insn __kprobes
 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_end = NULL;
+	enum probe_insn decoded;
+	probe_opcode_t insn = le32_to_cpu(*addr);
+	probe_opcode_t *scan_end = NULL;
 	unsigned long size = 0, offset = 0;
 
 	/*
@@ -162,7 +162,7 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
 		else
 			scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE;
 	}
-	decoded = arm_probe_decode_insn(insn, asi);
+	decoded = arm_probe_decode_insn(insn, &asi->api);
 
 	if (decoded != INSN_REJECTED && scan_end)
 		if (is_probed_address_atomic(addr - 1, scan_end))
@@ -170,3 +170,4 @@ arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi)
 
 	return decoded;
 }
+#endif

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

@@ -23,13 +23,17 @@
  */
 #define MAX_ATOMIC_CONTEXT_SIZE	(128 / sizeof(kprobe_opcode_t))
 
-enum kprobe_insn {
+enum probe_insn {
 	INSN_REJECTED,
 	INSN_GOOD_NO_SLOT,
 	INSN_GOOD,
 };
 
-enum kprobe_insn __kprobes
+#ifdef CONFIG_KPROBES
+enum probe_insn __kprobes
 arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi);
+#endif
+enum probe_insn __kprobes
+arm_probe_decode_insn(probe_opcode_t insn, struct arch_probe_insn *asi);
 
 #endif /* _ARM_KERNEL_KPROBES_ARM64_H */

arch/arm64/kernel/probes/kprobes.c

@@ -44,31 +44,31 @@ post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *);
 static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
 {
 	/* prepare insn slot */
-	p->ainsn.insn[0] = cpu_to_le32(p->opcode);
+	p->ainsn.api.insn[0] = cpu_to_le32(p->opcode);
 
-	flush_icache_range((uintptr_t) (p->ainsn.insn),
-			   (uintptr_t) (p->ainsn.insn) +
+	flush_icache_range((uintptr_t) (p->ainsn.api.insn),
+			   (uintptr_t) (p->ainsn.api.insn) +
 			   MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
 
 	/*
 	 * Needs restoring of return address after stepping xol.
 	 */
-	p->ainsn.restore = (unsigned long) p->addr +
+	p->ainsn.api.restore = (unsigned long) p->addr +
 	  sizeof(kprobe_opcode_t);
 }
 
 static void __kprobes arch_prepare_simulate(struct kprobe *p)
 {
 	/* This instructions is not executed xol. No need to adjust the PC */
-	p->ainsn.restore = 0;
+	p->ainsn.api.restore = 0;
 }
 
 static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe_ctlblk *kcb = get_kprobe_ctlblk();
 
-	if (p->ainsn.handler)
-		p->ainsn.handler((u32)p->opcode, (long)p->addr, regs);
+	if (p->ainsn.api.handler)
+		p->ainsn.api.handler((u32)p->opcode, (long)p->addr, regs);
 
 	/* single step simulated, now go for post processing */
 	post_kprobe_handler(kcb, regs);
@@ -98,18 +98,18 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 		return -EINVAL;
 
 	case INSN_GOOD_NO_SLOT:	/* insn need simulation */
-		p->ainsn.insn = NULL;
+		p->ainsn.api.insn = NULL;
 		break;
 
 	case INSN_GOOD:	/* instruction uses slot */
-		p->ainsn.insn = get_insn_slot();
-		if (!p->ainsn.insn)
+		p->ainsn.api.insn = get_insn_slot();
+		if (!p->ainsn.api.insn)
 			return -ENOMEM;
 		break;
 	};
 
 	/* prepare the instruction */
-	if (p->ainsn.insn)
+	if (p->ainsn.api.insn)
 		arch_prepare_ss_slot(p);
 	else
 		arch_prepare_simulate(p);
@@ -142,9 +142,9 @@ void __kprobes arch_disarm_kprobe(struct kprobe *p)
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
 {
-	if (p->ainsn.insn) {
-		free_insn_slot(p->ainsn.insn, 0);
-		p->ainsn.insn = NULL;
+	if (p->ainsn.api.insn) {
+		free_insn_slot(p->ainsn.api.insn, 0);
+		p->ainsn.api.insn = NULL;
 	}
 }
 
@@ -244,9 +244,9 @@ static void __kprobes setup_singlestep(struct kprobe *p,
 	}
 
 
-	if (p->ainsn.insn) {
+	if (p->ainsn.api.insn) {
 		/* prepare for single stepping */
-		slot = (unsigned long)p->ainsn.insn;
+		slot = (unsigned long)p->ainsn.api.insn;
 
 		set_ss_context(kcb, slot);	/* mark pending ss */
 
@@ -295,8 +295,8 @@ post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs)
 		return;
 
 	/* return addr restore if non-branching insn */
-	if (cur->ainsn.restore != 0)
-		instruction_pointer_set(regs, cur->ainsn.restore);
+	if (cur->ainsn.api.restore != 0)
+		instruction_pointer_set(regs, cur->ainsn.api.restore);
 
 	/* restore back original saved kprobe variables and continue */
 	if (kcb->kprobe_status == KPROBE_REENTER) {

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

@@ -13,28 +13,26 @@
  * General Public License for more details.
  */
 
+#include <linux/bitops.h>
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 
 #include "simulate-insn.h"
 
-#define sign_extend(x, signbit)		\
-	((x) | (0 - ((x) & (1 << (signbit)))))
-
 #define bbl_displacement(insn)		\
-	sign_extend(((insn) & 0x3ffffff) << 2, 27)
+	sign_extend32(((insn) & 0x3ffffff) << 2, 27)
 
 #define bcond_displacement(insn)	\
-	sign_extend(((insn >> 5) & 0x7ffff) << 2, 20)
+	sign_extend32(((insn >> 5) & 0x7ffff) << 2, 20)
 
 #define cbz_displacement(insn)	\
-	sign_extend(((insn >> 5) & 0x7ffff) << 2, 20)
+	sign_extend32(((insn >> 5) & 0x7ffff) << 2, 20)
 
 #define tbz_displacement(insn)	\
-	sign_extend(((insn >> 5) & 0x3fff) << 2, 15)
+	sign_extend32(((insn >> 5) & 0x3fff) << 2, 15)
 
 #define ldr_displacement(insn)	\
-	sign_extend(((insn >> 5) & 0x7ffff) << 2, 20)
+	sign_extend32(((insn >> 5) & 0x7ffff) << 2, 20)
 
 static inline void set_x_reg(struct pt_regs *regs, int reg, u64 val)
 {
@@ -106,7 +104,7 @@ simulate_adr_adrp(u32 opcode, long addr, struct pt_regs *regs)
 
 	xn = opcode & 0x1f;
 	imm = ((opcode >> 3) & 0x1ffffc) | ((opcode >> 29) & 0x3);
-	imm = sign_extend(imm, 20);
+	imm = sign_extend64(imm, 20);
 	if (opcode & 0x80000000)
 		val = (imm<<12) + (addr & 0xfffffffffffff000);
 	else

arch/arm64/kernel/probes/uprobes.c

@@ -0,0 +1,216 @@
+/*
+ * Copyright (C) 2014-2016 Pratyush Anand <panand@redhat.com>
+ *
+ * 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.
+ */
+#include <linux/highmem.h>
+#include <linux/ptrace.h>
+#include <linux/uprobes.h>
+#include <asm/cacheflush.h>
+
+#include "decode-insn.h"
+
+#define UPROBE_INV_FAULT_CODE	UINT_MAX
+
+void arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr,
+		void *src, unsigned long len)
+{
+	void *xol_page_kaddr = kmap_atomic(page);
+	void *dst = xol_page_kaddr + (vaddr & ~PAGE_MASK);
+
+	/* Initialize the slot */
+	memcpy(dst, src, len);
+
+	/* flush caches (dcache/icache) */
+	sync_icache_aliases(dst, len);
+
+	kunmap_atomic(xol_page_kaddr);
+}
+
+unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
+{
+	return instruction_pointer(regs);
+}
+
+int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
+		unsigned long addr)
+{
+	probe_opcode_t insn;
+
+	/* TODO: Currently we do not support AARCH32 instruction probing */
+	if (test_bit(TIF_32BIT, &mm->context.flags))
+		return -ENOTSUPP;
+	else if (!IS_ALIGNED(addr, AARCH64_INSN_SIZE))
+		return -EINVAL;
+
+	insn = *(probe_opcode_t *)(&auprobe->insn[0]);
+
+	switch (arm_probe_decode_insn(insn, &auprobe->api)) {
+	case INSN_REJECTED:
+		return -EINVAL;
+
+	case INSN_GOOD_NO_SLOT:
+		auprobe->simulate = true;
+		break;
+
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	/* Initialize with an invalid fault code to detect if ol insn trapped */
+	current->thread.fault_code = UPROBE_INV_FAULT_CODE;
+
+	/* Instruction points to execute ol */
+	instruction_pointer_set(regs, utask->xol_vaddr);
+
+	user_enable_single_step(current);
+
+	return 0;
+}
+
+int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	WARN_ON_ONCE(current->thread.fault_code != UPROBE_INV_FAULT_CODE);
+
+	/* Instruction points to execute next to breakpoint address */
+	instruction_pointer_set(regs, utask->vaddr + 4);
+
+	user_disable_single_step(current);
+
+	return 0;
+}
+bool arch_uprobe_xol_was_trapped(struct task_struct *t)
+{
+	/*
+	 * Between arch_uprobe_pre_xol and arch_uprobe_post_xol, if an xol
+	 * insn itself is trapped, then detect the case with the help of
+	 * invalid fault code which is being set in arch_uprobe_pre_xol
+	 */
+	if (t->thread.fault_code != UPROBE_INV_FAULT_CODE)
+		return true;
+
+	return false;
+}
+
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	probe_opcode_t insn;
+	unsigned long addr;
+
+	if (!auprobe->simulate)
+		return false;
+
+	insn = *(probe_opcode_t *)(&auprobe->insn[0]);
+	addr = instruction_pointer(regs);
+
+	if (auprobe->api.handler)
+		auprobe->api.handler(insn, addr, regs);
+
+	return true;
+}
+
+void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	/*
+	 * Task has received a fatal signal, so reset back to probbed
+	 * address.
+	 */
+	instruction_pointer_set(regs, utask->vaddr);
+
+	user_disable_single_step(current);
+}
+
+bool arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx,
+		struct pt_regs *regs)
+{
+	/*
+	 * If a simple branch instruction (B) was called for retprobed
+	 * assembly label then return true even when regs->sp and ret->stack
+	 * are same. It will ensure that cleanup and reporting of return
+	 * instances corresponding to callee label is done when
+	 * handle_trampoline for called function is executed.
+	 */
+	if (ctx == RP_CHECK_CHAIN_CALL)
+		return regs->sp <= ret->stack;
+	else
+		return regs->sp < ret->stack;
+}
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr,
+				  struct pt_regs *regs)
+{
+	unsigned long orig_ret_vaddr;
+
+	orig_ret_vaddr = procedure_link_pointer(regs);
+	/* Replace the return addr with trampoline addr */
+	procedure_link_pointer_set(regs, trampoline_vaddr);
+
+	return orig_ret_vaddr;
+}
+
+int arch_uprobe_exception_notify(struct notifier_block *self,
+				 unsigned long val, void *data)
+{
+	return NOTIFY_DONE;
+}
+
+static int uprobe_breakpoint_handler(struct pt_regs *regs,
+		unsigned int esr)
+{
+	if (user_mode(regs) && uprobe_pre_sstep_notifier(regs))
+		return DBG_HOOK_HANDLED;
+
+	return DBG_HOOK_ERROR;
+}
+
+static int uprobe_single_step_handler(struct pt_regs *regs,
+		unsigned int esr)
+{
+	struct uprobe_task *utask = current->utask;
+
+	if (user_mode(regs)) {
+		WARN_ON(utask &&
+			(instruction_pointer(regs) != utask->xol_vaddr + 4));
+
+		if (uprobe_post_sstep_notifier(regs))
+			return DBG_HOOK_HANDLED;
+	}
+
+	return DBG_HOOK_ERROR;
+}
+
+/* uprobe breakpoint handler hook */
+static struct break_hook uprobes_break_hook = {
+	.esr_mask = BRK64_ESR_MASK,
+	.esr_val = BRK64_ESR_UPROBES,
+	.fn = uprobe_breakpoint_handler,
+};
+
+/* uprobe single step handler hook */
+static struct step_hook uprobes_step_hook = {
+	.fn = uprobe_single_step_handler,
+};
+
+static int __init arch_init_uprobes(void)
+{
+	register_break_hook(&uprobes_break_hook);
+	register_step_hook(&uprobes_step_hook);
+
+	return 0;
+}
+
+device_initcall(arch_init_uprobes);

arch/arm64/kernel/process.c

@@ -45,6 +45,7 @@
 #include <linux/personality.h>
 #include <linux/notifier.h>
 #include <trace/events/power.h>
+#include <linux/percpu.h>
 
 #include <asm/alternative.h>
 #include <asm/compat.h>
@@ -282,7 +283,7 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start,
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->pstate = PSR_MODE_EL1h;
 		if (IS_ENABLED(CONFIG_ARM64_UAO) &&
-		    cpus_have_cap(ARM64_HAS_UAO))
+		    cpus_have_const_cap(ARM64_HAS_UAO))
 			childregs->pstate |= PSR_UAO_BIT;
 		p->thread.cpu_context.x19 = stack_start;
 		p->thread.cpu_context.x20 = stk_sz;
@@ -321,6 +322,20 @@ void uao_thread_switch(struct task_struct *next)
 	}
 }
 
+/*
+ * We store our current task in sp_el0, which is clobbered by userspace. Keep a
+ * shadow copy so that we can restore this upon entry from userspace.
+ *
+ * This is *only* for exception entry from EL0, and is not valid until we
+ * __switch_to() a user task.
+ */
+DEFINE_PER_CPU(struct task_struct *, __entry_task);
+
+static void entry_task_switch(struct task_struct *next)
+{
+	__this_cpu_write(__entry_task, next);
+}
+
 /*
  * Thread switching.
  */
@@ -333,6 +348,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	tls_thread_switch(next);
 	hw_breakpoint_thread_switch(next);
 	contextidr_thread_switch(next);
+	entry_task_switch(next);
 	uao_thread_switch(next);
 
 	/*
@@ -350,27 +366,35 @@ struct task_struct *__switch_to(struct task_struct *prev,
 unsigned long get_wchan(struct task_struct *p)
 {
 	struct stackframe frame;
-	unsigned long stack_page;
+	unsigned long stack_page, ret = 0;
 	int count = 0;
 	if (!p || p == current || p->state == TASK_RUNNING)
 		return 0;
 
+	stack_page = (unsigned long)try_get_task_stack(p);
+	if (!stack_page)
+		return 0;
+
 	frame.fp = thread_saved_fp(p);
 	frame.sp = thread_saved_sp(p);
 	frame.pc = thread_saved_pc(p);
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	frame.graph = p->curr_ret_stack;
 #endif
-	stack_page = (unsigned long)task_stack_page(p);
 	do {
 		if (frame.sp < stack_page ||
 		    frame.sp >= stack_page + THREAD_SIZE ||
 		    unwind_frame(p, &frame))
-			return 0;
-		if (!in_sched_functions(frame.pc))
-			return frame.pc;
+			goto out;
+		if (!in_sched_functions(frame.pc)) {
+			ret = frame.pc;
+			goto out;
+		}
 	} while (count ++ < 16);
-	return 0;
+
+out:
+	put_task_stack(p);
+	return ret;
 }
 
 unsigned long arch_align_stack(unsigned long sp)

arch/arm64/kernel/ptrace.c

@@ -327,13 +327,13 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 				     struct arch_hw_breakpoint_ctrl ctrl,
 				     struct perf_event_attr *attr)
 {
-	int err, len, type, disabled = !ctrl.enabled;
+	int err, len, type, offset, disabled = !ctrl.enabled;
 
 	attr->disabled = disabled;
 	if (disabled)
 		return 0;
 
-	err = arch_bp_generic_fields(ctrl, &len, &type);
+	err = arch_bp_generic_fields(ctrl, &len, &type, &offset);
 	if (err)
 		return err;
 
@@ -352,6 +352,7 @@ static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type,
 
 	attr->bp_len	= len;
 	attr->bp_type	= type;
+	attr->bp_addr	+= offset;
 
 	return 0;
 }
@@ -404,7 +405,7 @@ static int ptrace_hbp_get_addr(unsigned int note_type,
 	if (IS_ERR(bp))
 		return PTR_ERR(bp);
 
-	*addr = bp ? bp->attr.bp_addr : 0;
+	*addr = bp ? counter_arch_bp(bp)->address : 0;
 	return 0;
 }
 

arch/arm64/kernel/return_address.c

@@ -12,6 +12,7 @@
 #include <linux/export.h>
 #include <linux/ftrace.h>
 
+#include <asm/stack_pointer.h>
 #include <asm/stacktrace.h>
 
 struct return_address_data {

arch/arm64/kernel/setup.c

@@ -291,6 +291,15 @@ void __init setup_arch(char **cmdline_p)
 	smp_init_cpus();
 	smp_build_mpidr_hash();
 
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	/*
+	 * Make sure init_thread_info.ttbr0 always generates translation
+	 * faults in case uaccess_enable() is inadvertently called by the init
+	 * thread.
+	 */
+	init_task.thread_info.ttbr0 = virt_to_phys(empty_zero_page);
+#endif
+
 #ifdef CONFIG_VT
 #if defined(CONFIG_VGA_CONSOLE)
 	conswitchp = &vga_con;

arch/arm64/kernel/signal.c

@@ -414,6 +414,9 @@ asmlinkage void do_notify_resume(struct pt_regs *regs,
 		} else {
 			local_irq_enable();
 
+			if (thread_flags & _TIF_UPROBE)
+				uprobe_notify_resume(regs);
+
 			if (thread_flags & _TIF_SIGPENDING)
 				do_signal(regs);
 

arch/arm64/kernel/sleep.S

@@ -125,9 +125,6 @@ ENTRY(_cpu_resume)
 	/* load sp from context */
 	ldr	x2, [x0, #CPU_CTX_SP]
 	mov	sp, x2
-	/* save thread_info */
-	and	x2, x2, #~(THREAD_SIZE - 1)
-	msr	sp_el0, x2
 	/*
 	 * cpu_do_resume expects x0 to contain context address pointer
 	 */

arch/arm64/kernel/smp.c

@@ -58,6 +58,9 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/ipi.h>
 
+DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number);
+EXPORT_PER_CPU_SYMBOL(cpu_number);
+
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
  * so we need some other way of telling a new secondary core
@@ -146,6 +149,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	 * We need to tell the secondary core where to find its stack and the
 	 * page tables.
 	 */
+	secondary_data.task = idle;
 	secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
 	update_cpu_boot_status(CPU_MMU_OFF);
 	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
@@ -170,6 +174,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 		pr_err("CPU%u: failed to boot: %d\n", cpu, ret);
 	}
 
+	secondary_data.task = NULL;
 	secondary_data.stack = NULL;
 	status = READ_ONCE(secondary_data.status);
 	if (ret && status) {
@@ -208,7 +213,10 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 asmlinkage void secondary_start_kernel(void)
 {
 	struct mm_struct *mm = &init_mm;
-	unsigned int cpu = smp_processor_id();
+	unsigned int cpu;
+
+	cpu = task_cpu(current);
+	set_my_cpu_offset(per_cpu_offset(cpu));
 
 	/*
 	 * All kernel threads share the same mm context; grab a
@@ -217,8 +225,6 @@ asmlinkage void secondary_start_kernel(void)
 	atomic_inc(&mm->mm_count);
 	current->active_mm = mm;
 
-	set_my_cpu_offset(per_cpu_offset(smp_processor_id()));
-
 	/*
 	 * TTBR0 is only used for the identity mapping at this stage. Make it
 	 * point to zero page to avoid speculatively fetching new entries.
@@ -718,6 +724,8 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	 */
 	for_each_possible_cpu(cpu) {
 
+		per_cpu(cpu_number, cpu) = cpu;
+
 		if (cpu == smp_processor_id())
 			continue;
 

arch/arm64/kernel/stacktrace.c

@@ -22,6 +22,7 @@
 #include <linux/stacktrace.h>
 
 #include <asm/irq.h>
+#include <asm/stack_pointer.h>
 #include <asm/stacktrace.h>
 
 /*
@@ -128,7 +129,6 @@ void notrace walk_stackframe(struct task_struct *tsk, struct stackframe *frame,
 			break;
 	}
 }
-EXPORT_SYMBOL(walk_stackframe);
 
 #ifdef CONFIG_STACKTRACE
 struct stack_trace_data {
@@ -181,6 +181,9 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	struct stack_trace_data data;
 	struct stackframe frame;
 
+	if (!try_get_task_stack(tsk))
+		return;
+
 	data.trace = trace;
 	data.skip = trace->skip;
 
@@ -202,6 +205,8 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	walk_stackframe(tsk, &frame, save_trace, &data);
 	if (trace->nr_entries < trace->max_entries)
 		trace->entries[trace->nr_entries++] = ULONG_MAX;
+
+	put_task_stack(tsk);
 }
 
 void save_stack_trace(struct stack_trace *trace)

arch/arm64/kernel/suspend.c

@@ -46,12 +46,6 @@ void notrace __cpu_suspend_exit(void)
 	 */
 	cpu_uninstall_idmap();
 
-	/*
-	 * Restore per-cpu offset before any kernel
-	 * subsystem relying on it has a chance to run.
-	 */
-	set_my_cpu_offset(per_cpu_offset(cpu));
-
 	/*
 	 * PSTATE was not saved over suspend/resume, re-enable any detected
 	 * features that might not have been set correctly.

arch/arm64/kernel/topology.c

@@ -19,10 +19,226 @@
 #include <linux/nodemask.h>
 #include <linux/of.h>
 #include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/cpufreq.h>
 
+#include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/topology.h>
 
+static DEFINE_PER_CPU(unsigned long, cpu_scale) = SCHED_CAPACITY_SCALE;
+static DEFINE_MUTEX(cpu_scale_mutex);
+
+unsigned long arch_scale_cpu_capacity(struct sched_domain *sd, int cpu)
+{
+	return per_cpu(cpu_scale, cpu);
+}
+
+static void set_capacity_scale(unsigned int cpu, unsigned long capacity)
+{
+	per_cpu(cpu_scale, cpu) = capacity;
+}
+
+#ifdef CONFIG_PROC_SYSCTL
+static ssize_t cpu_capacity_show(struct device *dev,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, dev);
+
+	return sprintf(buf, "%lu\n",
+			arch_scale_cpu_capacity(NULL, cpu->dev.id));
+}
+
+static ssize_t cpu_capacity_store(struct device *dev,
+				  struct device_attribute *attr,
+				  const char *buf,
+				  size_t count)
+{
+	struct cpu *cpu = container_of(dev, struct cpu, dev);
+	int this_cpu = cpu->dev.id, i;
+	unsigned long new_capacity;
+	ssize_t ret;
+
+	if (count) {
+		ret = kstrtoul(buf, 0, &new_capacity);
+		if (ret)
+			return ret;
+		if (new_capacity > SCHED_CAPACITY_SCALE)
+			return -EINVAL;
+
+		mutex_lock(&cpu_scale_mutex);
+		for_each_cpu(i, &cpu_topology[this_cpu].core_sibling)
+			set_capacity_scale(i, new_capacity);
+		mutex_unlock(&cpu_scale_mutex);
+	}
+
+	return count;
+}
+
+static DEVICE_ATTR_RW(cpu_capacity);
+
+static int register_cpu_capacity_sysctl(void)
+{
+	int i;
+	struct device *cpu;
+
+	for_each_possible_cpu(i) {
+		cpu = get_cpu_device(i);
+		if (!cpu) {
+			pr_err("%s: too early to get CPU%d device!\n",
+			       __func__, i);
+			continue;
+		}
+		device_create_file(cpu, &dev_attr_cpu_capacity);
+	}
+
+	return 0;
+}
+subsys_initcall(register_cpu_capacity_sysctl);
+#endif
+
+static u32 capacity_scale;
+static u32 *raw_capacity;
+static bool cap_parsing_failed;
+
+static void __init parse_cpu_capacity(struct device_node *cpu_node, int cpu)
+{
+	int ret;
+	u32 cpu_capacity;
+
+	if (cap_parsing_failed)
+		return;
+
+	ret = of_property_read_u32(cpu_node,
+				   "capacity-dmips-mhz",
+				   &cpu_capacity);
+	if (!ret) {
+		if (!raw_capacity) {
+			raw_capacity = kcalloc(num_possible_cpus(),
+					       sizeof(*raw_capacity),
+					       GFP_KERNEL);
+			if (!raw_capacity) {
+				pr_err("cpu_capacity: failed to allocate memory for raw capacities\n");
+				cap_parsing_failed = true;
+				return;
+			}
+		}
+		capacity_scale = max(cpu_capacity, capacity_scale);
+		raw_capacity[cpu] = cpu_capacity;
+		pr_debug("cpu_capacity: %s cpu_capacity=%u (raw)\n",
+			cpu_node->full_name, raw_capacity[cpu]);
+	} else {
+		if (raw_capacity) {
+			pr_err("cpu_capacity: missing %s raw capacity\n",
+				cpu_node->full_name);
+			pr_err("cpu_capacity: partial information: fallback to 1024 for all CPUs\n");
+		}
+		cap_parsing_failed = true;
+		kfree(raw_capacity);
+	}
+}
+
+static void normalize_cpu_capacity(void)
+{
+	u64 capacity;
+	int cpu;
+
+	if (!raw_capacity || cap_parsing_failed)
+		return;
+
+	pr_debug("cpu_capacity: capacity_scale=%u\n", capacity_scale);
+	mutex_lock(&cpu_scale_mutex);
+	for_each_possible_cpu(cpu) {
+		pr_debug("cpu_capacity: cpu=%d raw_capacity=%u\n",
+			 cpu, raw_capacity[cpu]);
+		capacity = (raw_capacity[cpu] << SCHED_CAPACITY_SHIFT)
+			/ capacity_scale;
+		set_capacity_scale(cpu, capacity);
+		pr_debug("cpu_capacity: CPU%d cpu_capacity=%lu\n",
+			cpu, arch_scale_cpu_capacity(NULL, cpu));
+	}
+	mutex_unlock(&cpu_scale_mutex);
+}
+
+#ifdef CONFIG_CPU_FREQ
+static cpumask_var_t cpus_to_visit;
+static bool cap_parsing_done;
+static void parsing_done_workfn(struct work_struct *work);
+static DECLARE_WORK(parsing_done_work, parsing_done_workfn);
+
+static int
+init_cpu_capacity_callback(struct notifier_block *nb,
+			   unsigned long val,
+			   void *data)
+{
+	struct cpufreq_policy *policy = data;
+	int cpu;
+
+	if (cap_parsing_failed || cap_parsing_done)
+		return 0;
+
+	switch (val) {
+	case CPUFREQ_NOTIFY:
+		pr_debug("cpu_capacity: init cpu capacity for CPUs [%*pbl] (to_visit=%*pbl)\n",
+				cpumask_pr_args(policy->related_cpus),
+				cpumask_pr_args(cpus_to_visit));
+		cpumask_andnot(cpus_to_visit,
+			       cpus_to_visit,
+			       policy->related_cpus);
+		for_each_cpu(cpu, policy->related_cpus) {
+			raw_capacity[cpu] = arch_scale_cpu_capacity(NULL, cpu) *
+					    policy->cpuinfo.max_freq / 1000UL;
+			capacity_scale = max(raw_capacity[cpu], capacity_scale);
+		}
+		if (cpumask_empty(cpus_to_visit)) {
+			normalize_cpu_capacity();
+			kfree(raw_capacity);
+			pr_debug("cpu_capacity: parsing done\n");
+			cap_parsing_done = true;
+			schedule_work(&parsing_done_work);
+		}
+	}
+	return 0;
+}
+
+static struct notifier_block init_cpu_capacity_notifier = {
+	.notifier_call = init_cpu_capacity_callback,
+};
+
+static int __init register_cpufreq_notifier(void)
+{
+	if (cap_parsing_failed)
+		return -EINVAL;
+
+	if (!alloc_cpumask_var(&cpus_to_visit, GFP_KERNEL)) {
+		pr_err("cpu_capacity: failed to allocate memory for cpus_to_visit\n");
+		return -ENOMEM;
+	}
+	cpumask_copy(cpus_to_visit, cpu_possible_mask);
+
+	return cpufreq_register_notifier(&init_cpu_capacity_notifier,
+					 CPUFREQ_POLICY_NOTIFIER);
+}
+core_initcall(register_cpufreq_notifier);
+
+static void parsing_done_workfn(struct work_struct *work)
+{
+	cpufreq_unregister_notifier(&init_cpu_capacity_notifier,
+					 CPUFREQ_POLICY_NOTIFIER);
+}
+
+#else
+static int __init free_raw_capacity(void)
+{
+	kfree(raw_capacity);
+
+	return 0;
+}
+core_initcall(free_raw_capacity);
+#endif
+
 static int __init get_cpu_for_node(struct device_node *node)
 {
 	struct device_node *cpu_node;
@@ -34,6 +250,7 @@ static int __init get_cpu_for_node(struct device_node *node)
 
 	for_each_possible_cpu(cpu) {
 		if (of_get_cpu_node(cpu, NULL) == cpu_node) {
+			parse_cpu_capacity(cpu_node, cpu);
 			of_node_put(cpu_node);
 			return cpu;
 		}
@@ -178,13 +395,17 @@ static int __init parse_dt_topology(void)
 	 * cluster with restricted subnodes.
 	 */
 	map = of_get_child_by_name(cn, "cpu-map");
-	if (!map)
+	if (!map) {
+		cap_parsing_failed = true;
 		goto out;
+	}
 
 	ret = parse_cluster(map, 0);
 	if (ret != 0)
 		goto out_map;
 
+	normalize_cpu_capacity();
+
 	/*
 	 * Check that all cores are in the topology; the SMP code will
 	 * only mark cores described in the DT as possible.

arch/arm64/kernel/traps.c

@@ -38,6 +38,7 @@
 #include <asm/esr.h>
 #include <asm/insn.h>
 #include <asm/traps.h>
+#include <asm/stack_pointer.h>
 #include <asm/stacktrace.h>
 #include <asm/exception.h>
 #include <asm/system_misc.h>
@@ -147,6 +148,9 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 	if (!tsk)
 		tsk = current;
 
+	if (!try_get_task_stack(tsk))
+		return;
+
 	/*
 	 * Switching between stacks is valid when tracing current and in
 	 * non-preemptible context.
@@ -212,6 +216,8 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 				 stack + sizeof(struct pt_regs));
 		}
 	}
+
+	put_task_stack(tsk);
 }
 
 void show_stack(struct task_struct *tsk, unsigned long *sp)
@@ -227,10 +233,9 @@ void show_stack(struct task_struct *tsk, unsigned long *sp)
 #endif
 #define S_SMP " SMP"
 
-static int __die(const char *str, int err, struct thread_info *thread,
-		 struct pt_regs *regs)
+static int __die(const char *str, int err, struct pt_regs *regs)
 {
-	struct task_struct *tsk = thread->task;
+	struct task_struct *tsk = current;
 	static int die_counter;
 	int ret;
 
@@ -245,7 +250,8 @@ static int __die(const char *str, int err, struct thread_info *thread,
 	print_modules();
 	__show_regs(regs);
 	pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n",
-		 TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), thread + 1);
+		 TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk),
+		 end_of_stack(tsk));
 
 	if (!user_mode(regs)) {
 		dump_mem(KERN_EMERG, "Stack: ", regs->sp,
@@ -264,7 +270,6 @@ static DEFINE_RAW_SPINLOCK(die_lock);
  */
 void die(const char *str, struct pt_regs *regs, int err)
 {
-	struct thread_info *thread = current_thread_info();
 	int ret;
 
 	oops_enter();
@@ -272,9 +277,9 @@ void die(const char *str, struct pt_regs *regs, int err)
 	raw_spin_lock_irq(&die_lock);
 	console_verbose();
 	bust_spinlocks(1);
-	ret = __die(str, err, thread, regs);
+	ret = __die(str, err, regs);
 
-	if (regs && kexec_should_crash(thread->task))
+	if (regs && kexec_should_crash(current))
 		crash_kexec(regs);
 
 	bust_spinlocks(0);
@@ -435,9 +440,10 @@ int cpu_enable_cache_maint_trap(void *__unused)
 }
 
 #define __user_cache_maint(insn, address, res)			\
-	if (untagged_addr(address) >= user_addr_max())		\
+	if (untagged_addr(address) >= user_addr_max()) {	\
 		res = -EFAULT;					\
-	else							\
+	} else {						\
+		uaccess_ttbr0_enable();				\
 		asm volatile (					\
 			"1:	" insn ", %1\n"			\
 			"	mov	%w0, #0\n"		\
@@ -449,7 +455,9 @@ int cpu_enable_cache_maint_trap(void *__unused)
 			"	.popsection\n"			\
 			_ASM_EXTABLE(1b, 3b)			\
 			: "=r" (res)				\
-			: "r" (address), "i" (-EFAULT) )
+			: "r" (address), "i" (-EFAULT));	\
+		uaccess_ttbr0_disable();			\
+	}
 
 static void user_cache_maint_handler(unsigned int esr, struct pt_regs *regs)
 {

arch/arm64/kernel/vmlinux.lds.S

@@ -216,6 +216,11 @@ SECTIONS
 	swapper_pg_dir = .;
 	. += SWAPPER_DIR_SIZE;
 
+#ifdef CONFIG_ARM64_SW_TTBR0_PAN
+	reserved_ttbr0 = .;
+	. += RESERVED_TTBR0_SIZE;
+#endif
+
 	_end = .;
 
 	STABS_DEBUG

arch/arm64/kvm/handle_exit.c

@@ -57,6 +57,16 @@ static int handle_smc(struct kvm_vcpu *vcpu, struct kvm_run *run)
 	return 1;
 }
 
+/*
+ * Guest access to FP/ASIMD registers are routed to this handler only
+ * when the system doesn't support FP/ASIMD.
+ */
+static int handle_no_fpsimd(struct kvm_vcpu *vcpu, struct kvm_run *run)
+{
+	kvm_inject_undefined(vcpu);
+	return 1;
+}
+
 /**
  * kvm_handle_wfx - handle a wait-for-interrupts or wait-for-event
  *		    instruction executed by a guest
@@ -144,6 +154,7 @@ static exit_handle_fn arm_exit_handlers[] = {
 	[ESR_ELx_EC_BREAKPT_LOW]= kvm_handle_guest_debug,
 	[ESR_ELx_EC_BKPT32]	= kvm_handle_guest_debug,
 	[ESR_ELx_EC_BRK64]	= kvm_handle_guest_debug,
+	[ESR_ELx_EC_FP_ASIMD]	= handle_no_fpsimd,
 };
 
 static exit_handle_fn kvm_get_exit_handler(struct kvm_vcpu *vcpu)

arch/arm64/kvm/hyp/hyp-entry.S

@@ -106,9 +106,16 @@ el1_trap:
 	 * x0: ESR_EC
 	 */
 
-	/* Guest accessed VFP/SIMD registers, save host, restore Guest */
+	/*
+	 * We trap the first access to the FP/SIMD to save the host context
+	 * and restore the guest context lazily.
+	 * If FP/SIMD is not implemented, handle the trap and inject an
+	 * undefined instruction exception to the guest.
+	 */
+alternative_if_not ARM64_HAS_NO_FPSIMD
 	cmp	x0, #ESR_ELx_EC_FP_ASIMD
 	b.eq	__fpsimd_guest_restore
+alternative_else_nop_endif
 
 	mrs	x1, tpidr_el2
 	mov	x0, #ARM_EXCEPTION_TRAP

arch/arm64/kvm/hyp/switch.c

@@ -21,6 +21,7 @@
 #include <asm/kvm_asm.h>
 #include <asm/kvm_emulate.h>
 #include <asm/kvm_hyp.h>
+#include <asm/fpsimd.h>
 
 static bool __hyp_text __fpsimd_enabled_nvhe(void)
 {
@@ -76,9 +77,11 @@ static void __hyp_text __activate_traps(struct kvm_vcpu *vcpu)
 	 * traps are only taken to EL2 if the operation would not otherwise
 	 * trap to EL1.  Therefore, always make sure that for 32-bit guests,
 	 * we set FPEXC.EN to prevent traps to EL1, when setting the TFP bit.
+	 * If FP/ASIMD is not implemented, FPEXC is UNDEFINED and any access to
+	 * it will cause an exception.
 	 */
 	val = vcpu->arch.hcr_el2;
-	if (!(val & HCR_RW)) {
+	if (!(val & HCR_RW) && system_supports_fpsimd()) {
 		write_sysreg(1 << 30, fpexc32_el2);
 		isb();
 	}

arch/arm64/lib/clear_user.S

@@ -17,10 +17,7 @@
  */
 #include <linux/linkage.h>
 
-#include <asm/alternative.h>
-#include <asm/assembler.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
 
 	.text
 
@@ -33,8 +30,7 @@
  * Alignment fixed up by hardware.
  */
 ENTRY(__clear_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_enable_not_uao x2, x3
 	mov	x2, x1			// save the size for fixup return
 	subs	x1, x1, #8
 	b.mi	2f
@@ -54,8 +50,7 @@ uao_user_alternative 9f, strh, sttrh, wzr, x0, 2
 	b.mi	5f
 uao_user_alternative 9f, strb, sttrb, wzr, x0, 0
 5:	mov	x0, #0
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_disable_not_uao x2
 	ret
 ENDPROC(__clear_user)
 

arch/arm64/lib/copy_from_user.S

@@ -16,11 +16,8 @@
 
 #include <linux/linkage.h>
 
-#include <asm/alternative.h>
-#include <asm/assembler.h>
 #include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
 
 /*
  * Copy from user space to a kernel buffer (alignment handled by the hardware)
@@ -67,12 +64,10 @@
 
 end	.req	x5
 ENTRY(__arch_copy_from_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_enable_not_uao x3, x4
 	add	end, x0, x2
 #include "copy_template.S"
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_disable_not_uao x3
 	mov	x0, #0				// Nothing to copy
 	ret
 ENDPROC(__arch_copy_from_user)

arch/arm64/lib/copy_in_user.S

@@ -18,11 +18,8 @@
 
 #include <linux/linkage.h>
 
-#include <asm/alternative.h>
-#include <asm/assembler.h>
 #include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
 
 /*
  * Copy from user space to user space (alignment handled by the hardware)
@@ -68,12 +65,10 @@
 
 end	.req	x5
 ENTRY(__copy_in_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_enable_not_uao x3, x4
 	add	end, x0, x2
 #include "copy_template.S"
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_disable_not_uao x3
 	mov	x0, #0
 	ret
 ENDPROC(__copy_in_user)

arch/arm64/lib/copy_to_user.S

@@ -16,11 +16,8 @@
 
 #include <linux/linkage.h>
 
-#include <asm/alternative.h>
-#include <asm/assembler.h>
 #include <asm/cache.h>
-#include <asm/cpufeature.h>
-#include <asm/sysreg.h>
+#include <asm/uaccess.h>
 
 /*
  * Copy to user space from a kernel buffer (alignment handled by the hardware)
@@ -66,12 +63,10 @@
 
 end	.req	x5
 ENTRY(__arch_copy_to_user)
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(0)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_enable_not_uao x3, x4
 	add	end, x0, x2
 #include "copy_template.S"
-ALTERNATIVE("nop", __stringify(SET_PSTATE_PAN(1)), ARM64_ALT_PAN_NOT_UAO, \
-	    CONFIG_ARM64_PAN)
+	uaccess_disable_not_uao x3
 	mov	x0, #0
 	ret
 ENDPROC(__arch_copy_to_user)

arch/arm64/mm/Makefile

@@ -3,7 +3,8 @@ obj-y				:= dma-mapping.o extable.o fault.o init.o \
 				   ioremap.o mmap.o pgd.o mmu.o \
 				   context.o proc.o pageattr.o
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
-obj-$(CONFIG_ARM64_PTDUMP)	+= dump.o
+obj-$(CONFIG_ARM64_PTDUMP_CORE)	+= dump.o
+obj-$(CONFIG_ARM64_PTDUMP_DEBUGFS)	+= ptdump_debugfs.o
 obj-$(CONFIG_NUMA)		+= numa.o
 
 obj-$(CONFIG_KASAN)		+= kasan_init.o

arch/arm64/mm/cache.S

@@ -23,6 +23,7 @@
 #include <asm/assembler.h>
 #include <asm/cpufeature.h>
 #include <asm/alternative.h>
+#include <asm/uaccess.h>
 
 /*
  *	flush_icache_range(start,end)
@@ -48,6 +49,7 @@ ENTRY(flush_icache_range)
  *	- end     - virtual end address of region
  */
 ENTRY(__flush_cache_user_range)
+	uaccess_ttbr0_enable x2, x3
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	bic	x4, x0, x3
@@ -69,10 +71,12 @@ USER(9f, ic	ivau, x4	)		// invalidate I line PoU
 	dsb	ish
 	isb
 	mov	x0, #0
+1:
+	uaccess_ttbr0_disable x1
 	ret
 9:
 	mov	x0, #-EFAULT
-	ret
+	b	1b
 ENDPROC(flush_icache_range)
 ENDPROC(__flush_cache_user_range)
 

arch/arm64/mm/context.c

@@ -221,7 +221,12 @@ void check_and_switch_context(struct mm_struct *mm, unsigned int cpu)
 	raw_spin_unlock_irqrestore(&cpu_asid_lock, flags);
 
 switch_mm_fastpath:
-	cpu_switch_mm(mm->pgd, mm);
+	/*
+	 * Defer TTBR0_EL1 setting for user threads to uaccess_enable() when
+	 * emulating PAN.
+	 */
+	if (!system_uses_ttbr0_pan())
+		cpu_switch_mm(mm->pgd, mm);
 }
 
 static int asids_init(void)

arch/arm64/mm/dma-mapping.c

@@ -938,11 +938,6 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 
 void arch_teardown_dma_ops(struct device *dev)
 {
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-
-	if (WARN_ON(domain))
-		iommu_detach_device(domain, dev);
-
 	dev->archdata.dma_ops = NULL;
 }
 

arch/arm64/mm/dump.c

@@ -50,6 +50,18 @@ static const struct addr_marker address_markers[] = {
 	{ -1,				NULL },
 };
 
+#define pt_dump_seq_printf(m, fmt, args...)	\
+({						\
+	if (m)					\
+		seq_printf(m, fmt, ##args);	\
+})
+
+#define pt_dump_seq_puts(m, fmt)	\
+({					\
+	if (m)				\
+		seq_printf(m, fmt);	\
+})
+
 /*
  * The page dumper groups page table entries of the same type into a single
  * description. It uses pg_state to track the range information while
@@ -62,6 +74,9 @@ struct pg_state {
 	unsigned long start_address;
 	unsigned level;
 	u64 current_prot;
+	bool check_wx;
+	unsigned long wx_pages;
+	unsigned long uxn_pages;
 };
 
 struct prot_bits {
@@ -186,10 +201,39 @@ static void dump_prot(struct pg_state *st, const struct prot_bits *bits,
 			s = bits->clear;
 
 		if (s)
-			seq_printf(st->seq, " %s", s);
+			pt_dump_seq_printf(st->seq, " %s", s);
 	}
 }
 
+static void note_prot_uxn(struct pg_state *st, unsigned long addr)
+{
+	if (!st->check_wx)
+		return;
+
+	if ((st->current_prot & PTE_UXN) == PTE_UXN)
+		return;
+
+	WARN_ONCE(1, "arm64/mm: Found non-UXN mapping at address %p/%pS\n",
+		  (void *)st->start_address, (void *)st->start_address);
+
+	st->uxn_pages += (addr - st->start_address) / PAGE_SIZE;
+}
+
+static void note_prot_wx(struct pg_state *st, unsigned long addr)
+{
+	if (!st->check_wx)
+		return;
+	if ((st->current_prot & PTE_RDONLY) == PTE_RDONLY)
+		return;
+	if ((st->current_prot & PTE_PXN) == PTE_PXN)
+		return;
+
+	WARN_ONCE(1, "arm64/mm: Found insecure W+X mapping at address %p/%pS\n",
+		  (void *)st->start_address, (void *)st->start_address);
+
+	st->wx_pages += (addr - st->start_address) / PAGE_SIZE;
+}
+
 static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 				u64 val)
 {
@@ -200,14 +244,16 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 		st->level = level;
 		st->current_prot = prot;
 		st->start_address = addr;
-		seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+		pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
 	} else if (prot != st->current_prot || level != st->level ||
 		   addr >= st->marker[1].start_address) {
 		const char *unit = units;
 		unsigned long delta;
 
 		if (st->current_prot) {
-			seq_printf(st->seq, "0x%016lx-0x%016lx   ",
+			note_prot_uxn(st, addr);
+			note_prot_wx(st, addr);
+			pt_dump_seq_printf(st->seq, "0x%016lx-0x%016lx   ",
 				   st->start_address, addr);
 
 			delta = (addr - st->start_address) >> 10;
@@ -215,17 +261,17 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 				delta >>= 10;
 				unit++;
 			}
-			seq_printf(st->seq, "%9lu%c %s", delta, *unit,
+			pt_dump_seq_printf(st->seq, "%9lu%c %s", delta, *unit,
 				   pg_level[st->level].name);
 			if (pg_level[st->level].bits)
 				dump_prot(st, pg_level[st->level].bits,
 					  pg_level[st->level].num);
-			seq_puts(st->seq, "\n");
+			pt_dump_seq_puts(st->seq, "\n");
 		}
 
 		if (addr >= st->marker[1].start_address) {
 			st->marker++;
-			seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+			pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
 		}
 
 		st->start_address = addr;
@@ -235,7 +281,7 @@ static void note_page(struct pg_state *st, unsigned long addr, unsigned level,
 
 	if (addr >= st->marker[1].start_address) {
 		st->marker++;
-		seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
+		pt_dump_seq_printf(st->seq, "---[ %s ]---\n", st->marker->name);
 	}
 
 }
@@ -304,9 +350,8 @@ static void walk_pgd(struct pg_state *st, struct mm_struct *mm,
 	}
 }
 
-static int ptdump_show(struct seq_file *m, void *v)
+void ptdump_walk_pgd(struct seq_file *m, struct ptdump_info *info)
 {
-	struct ptdump_info *info = m->private;
 	struct pg_state st = {
 		.seq = m,
 		.marker = info->markers,
@@ -315,33 +360,16 @@ static int ptdump_show(struct seq_file *m, void *v)
 	walk_pgd(&st, info->mm, info->base_addr);
 
 	note_page(&st, 0, 0, 0);
-	return 0;
 }
 
-static int ptdump_open(struct inode *inode, struct file *file)
+static void ptdump_initialize(void)
 {
-	return single_open(file, ptdump_show, inode->i_private);
-}
-
-static const struct file_operations ptdump_fops = {
-	.open		= ptdump_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= single_release,
-};
-
-int ptdump_register(struct ptdump_info *info, const char *name)
-{
-	struct dentry *pe;
 	unsigned i, j;
 
 	for (i = 0; i < ARRAY_SIZE(pg_level); i++)
 		if (pg_level[i].bits)
 			for (j = 0; j < pg_level[i].num; j++)
 				pg_level[i].mask |= pg_level[i].bits[j].mask;
-
-	pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
-	return pe ? 0 : -ENOMEM;
 }
 
 static struct ptdump_info kernel_ptdump_info = {
@@ -350,8 +378,30 @@ static struct ptdump_info kernel_ptdump_info = {
 	.base_addr	= VA_START,
 };
 
+void ptdump_check_wx(void)
+{
+	struct pg_state st = {
+		.seq = NULL,
+		.marker = (struct addr_marker[]) {
+			{ 0, NULL},
+			{ -1, NULL},
+		},
+		.check_wx = true,
+	};
+
+	walk_pgd(&st, &init_mm, 0);
+	note_page(&st, 0, 0, 0);
+	if (st.wx_pages || st.uxn_pages)
+		pr_warn("Checked W+X mappings: FAILED, %lu W+X pages found, %lu non-UXN pages found\n",
+			st.wx_pages, st.uxn_pages);
+	else
+		pr_info("Checked W+X mappings: passed, no W+X pages found\n");
+}
+
 static int ptdump_init(void)
 {
-	return ptdump_register(&kernel_ptdump_info, "kernel_page_tables");
+	ptdump_initialize();
+	return ptdump_debugfs_register(&kernel_ptdump_info,
+					"kernel_page_tables");
 }
 device_initcall(ptdump_init);

arch/arm64/mm/fault.c

@@ -269,13 +269,19 @@ out:
 	return fault;
 }
 
-static inline bool is_permission_fault(unsigned int esr)
+static inline bool is_permission_fault(unsigned int esr, struct pt_regs *regs)
 {
 	unsigned int ec       = ESR_ELx_EC(esr);
 	unsigned int fsc_type = esr & ESR_ELx_FSC_TYPE;
 
-	return (ec == ESR_ELx_EC_DABT_CUR && fsc_type == ESR_ELx_FSC_PERM) ||
-	       (ec == ESR_ELx_EC_IABT_CUR && fsc_type == ESR_ELx_FSC_PERM);
+	if (ec != ESR_ELx_EC_DABT_CUR && ec != ESR_ELx_EC_IABT_CUR)
+		return false;
+
+	if (system_uses_ttbr0_pan())
+		return fsc_type == ESR_ELx_FSC_FAULT &&
+			(regs->pstate & PSR_PAN_BIT);
+	else
+		return fsc_type == ESR_ELx_FSC_PERM;
 }
 
 static bool is_el0_instruction_abort(unsigned int esr)
@@ -315,7 +321,7 @@ static int __kprobes do_page_fault(unsigned long addr, unsigned int esr,
 		mm_flags |= FAULT_FLAG_WRITE;
 	}
 
-	if (is_permission_fault(esr) && (addr < USER_DS)) {
+	if (addr < USER_DS && is_permission_fault(esr, regs)) {
 		/* regs->orig_addr_limit may be 0 if we entered from EL0 */
 		if (regs->orig_addr_limit == KERNEL_DS)
 			die("Accessing user space memory with fs=KERNEL_DS", regs, esr);
@@ -507,10 +513,10 @@ static const struct fault_info {
 	{ do_bad,		SIGBUS,  0,		"unknown 17"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 18"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 19"			},
-	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
-	{ do_bad,		SIGBUS,  0,		"synchronous abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
+	{ do_bad,		SIGBUS,  0,		"synchronous external abort (translation table walk)" },
 	{ do_bad,		SIGBUS,  0,		"synchronous parity error"	},
 	{ do_bad,		SIGBUS,  0,		"unknown 25"			},
 	{ do_bad,		SIGBUS,  0,		"unknown 26"			},

arch/arm64/mm/flush.c

@@ -25,14 +25,7 @@
 #include <asm/cachetype.h>
 #include <asm/tlbflush.h>
 
-void flush_cache_range(struct vm_area_struct *vma, unsigned long start,
-		       unsigned long end)
-{
-	if (vma->vm_flags & VM_EXEC)
-		__flush_icache_all();
-}
-
-static void sync_icache_aliases(void *kaddr, unsigned long len)
+void sync_icache_aliases(void *kaddr, unsigned long len)
 {
 	unsigned long addr = (unsigned long)kaddr;
 

arch/arm64/mm/hugetlbpage.c

@@ -51,20 +51,8 @@ static int find_num_contig(struct mm_struct *mm, unsigned long addr,
 	*pgsize = PAGE_SIZE;
 	if (!pte_cont(pte))
 		return 1;
-	if (!pgd_present(*pgd)) {
-		VM_BUG_ON(!pgd_present(*pgd));
-		return 1;
-	}
 	pud = pud_offset(pgd, addr);
-	if (!pud_present(*pud)) {
-		VM_BUG_ON(!pud_present(*pud));
-		return 1;
-	}
 	pmd = pmd_offset(pud, addr);
-	if (!pmd_present(*pmd)) {
-		VM_BUG_ON(!pmd_present(*pmd));
-		return 1;
-	}
 	if ((pte_t *)pmd == ptep) {
 		*pgsize = PMD_SIZE;
 		return CONT_PMDS;
@@ -212,7 +200,7 @@ pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 		ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize);
 		/* save the 1st pte to return */
 		pte = ptep_get_and_clear(mm, addr, cpte);
-		for (i = 1; i < ncontig; ++i) {
+		for (i = 1, addr += pgsize; i < ncontig; ++i, addr += pgsize) {
 			/*
 			 * If HW_AFDBM is enabled, then the HW could
 			 * turn on the dirty bit for any of the page
@@ -250,7 +238,7 @@ int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 		pfn = pte_pfn(*cpte);
 		ncontig = find_num_contig(vma->vm_mm, addr, cpte,
 					  *cpte, &pgsize);
-		for (i = 0; i < ncontig; ++i, ++cpte) {
+		for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize) {
 			changed = ptep_set_access_flags(vma, addr, cpte,
 							pfn_pte(pfn,
 								hugeprot),
@@ -273,7 +261,7 @@ void huge_ptep_set_wrprotect(struct mm_struct *mm,
 
 		cpte = huge_pte_offset(mm, addr);
 		ncontig = find_num_contig(mm, addr, cpte, *cpte, &pgsize);
-		for (i = 0; i < ncontig; ++i, ++cpte)
+		for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize)
 			ptep_set_wrprotect(mm, addr, cpte);
 	} else {
 		ptep_set_wrprotect(mm, addr, ptep);
@@ -291,7 +279,7 @@ void huge_ptep_clear_flush(struct vm_area_struct *vma,
 		cpte = huge_pte_offset(vma->vm_mm, addr);
 		ncontig = find_num_contig(vma->vm_mm, addr, cpte,
 					  *cpte, &pgsize);
-		for (i = 0; i < ncontig; ++i, ++cpte)
+		for (i = 0; i < ncontig; ++i, ++cpte, addr += pgsize)
 			ptep_clear_flush(vma, addr, cpte);
 	} else {
 		ptep_clear_flush(vma, addr, ptep);
@@ -323,7 +311,7 @@ __setup("hugepagesz=", setup_hugepagesz);
 static __init int add_default_hugepagesz(void)
 {
 	if (size_to_hstate(CONT_PTES * PAGE_SIZE) == NULL)
-		hugetlb_add_hstate(CONT_PMD_SHIFT);
+		hugetlb_add_hstate(CONT_PTE_SHIFT);
 	return 0;
 }
 arch_initcall(add_default_hugepagesz);

arch/arm64/mm/mmu.c

@@ -28,8 +28,6 @@
 #include <linux/memblock.h>
 #include <linux/fs.h>
 #include <linux/io.h>
-#include <linux/slab.h>
-#include <linux/stop_machine.h>
 
 #include <asm/barrier.h>
 #include <asm/cputype.h>
@@ -42,6 +40,7 @@
 #include <asm/tlb.h>
 #include <asm/memblock.h>
 #include <asm/mmu_context.h>
+#include <asm/ptdump.h>
 
 u64 idmap_t0sz = TCR_T0SZ(VA_BITS);
 
@@ -95,11 +94,24 @@ static phys_addr_t __init early_pgtable_alloc(void)
 	return phys;
 }
 
+static bool pgattr_change_is_safe(u64 old, u64 new)
+{
+	/*
+	 * The following mapping attributes may be updated in live
+	 * kernel mappings without the need for break-before-make.
+	 */
+	static const pteval_t mask = PTE_PXN | PTE_RDONLY | PTE_WRITE;
+
+	return old  == 0 || new  == 0 || ((old ^ new) & ~mask) == 0;
+}
+
 static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
 				  unsigned long end, unsigned long pfn,
 				  pgprot_t prot,
-				  phys_addr_t (*pgtable_alloc)(void))
+				  phys_addr_t (*pgtable_alloc)(void),
+				  bool page_mappings_only)
 {
+	pgprot_t __prot = prot;
 	pte_t *pte;
 
 	BUG_ON(pmd_sect(*pmd));
@@ -115,8 +127,28 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
 
 	pte = pte_set_fixmap_offset(pmd, addr);
 	do {
-		set_pte(pte, pfn_pte(pfn, prot));
+		pte_t old_pte = *pte;
+
+		/*
+		 * Set the contiguous bit for the subsequent group of PTEs if
+		 * its size and alignment are appropriate.
+		 */
+		if (((addr | PFN_PHYS(pfn)) & ~CONT_PTE_MASK) == 0) {
+			if (end - addr >= CONT_PTE_SIZE && !page_mappings_only)
+				__prot = __pgprot(pgprot_val(prot) | PTE_CONT);
+			else
+				__prot = prot;
+		}
+
+		set_pte(pte, pfn_pte(pfn, __prot));
 		pfn++;
+
+		/*
+		 * After the PTE entry has been populated once, we
+		 * only allow updates to the permission attributes.
+		 */
+		BUG_ON(!pgattr_change_is_safe(pte_val(old_pte), pte_val(*pte)));
+
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 
 	pte_clear_fixmap();
@@ -125,8 +157,9 @@ static void alloc_init_pte(pmd_t *pmd, unsigned long addr,
 static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 				  phys_addr_t phys, pgprot_t prot,
 				  phys_addr_t (*pgtable_alloc)(void),
-				  bool allow_block_mappings)
+				  bool page_mappings_only)
 {
+	pgprot_t __prot = prot;
 	pmd_t *pmd;
 	unsigned long next;
 
@@ -146,27 +179,39 @@ static void alloc_init_pmd(pud_t *pud, unsigned long addr, unsigned long end,
 
 	pmd = pmd_set_fixmap_offset(pud, addr);
 	do {
+		pmd_t old_pmd = *pmd;
+
 		next = pmd_addr_end(addr, end);
+
 		/* try section mapping first */
 		if (((addr | next | phys) & ~SECTION_MASK) == 0 &&
-		      allow_block_mappings) {
-			pmd_t old_pmd =*pmd;
-			pmd_set_huge(pmd, phys, prot);
+		      !page_mappings_only) {
 			/*
-			 * Check for previous table entries created during
-			 * boot (__create_page_tables) and flush them.
+			 * Set the contiguous bit for the subsequent group of
+			 * PMDs if its size and alignment are appropriate.
 			 */
-			if (!pmd_none(old_pmd)) {
-				flush_tlb_all();
-				if (pmd_table(old_pmd)) {
-					phys_addr_t table = pmd_page_paddr(old_pmd);
-					if (!WARN_ON_ONCE(slab_is_available()))
-						memblock_free(table, PAGE_SIZE);
-				}
+			if (((addr | phys) & ~CONT_PMD_MASK) == 0) {
+				if (end - addr >= CONT_PMD_SIZE)
+					__prot = __pgprot(pgprot_val(prot) |
+							  PTE_CONT);
+				else
+					__prot = prot;
 			}
+			pmd_set_huge(pmd, phys, __prot);
+
+			/*
+			 * After the PMD entry has been populated once, we
+			 * only allow updates to the permission attributes.
+			 */
+			BUG_ON(!pgattr_change_is_safe(pmd_val(old_pmd),
+						      pmd_val(*pmd)));
 		} else {
 			alloc_init_pte(pmd, addr, next, __phys_to_pfn(phys),
-				       prot, pgtable_alloc);
+				       prot, pgtable_alloc,
+				       page_mappings_only);
+
+			BUG_ON(pmd_val(old_pmd) != 0 &&
+			       pmd_val(old_pmd) != pmd_val(*pmd));
 		}
 		phys += next - addr;
 	} while (pmd++, addr = next, addr != end);
@@ -189,7 +234,7 @@ static inline bool use_1G_block(unsigned long addr, unsigned long next,
 static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 				  phys_addr_t phys, pgprot_t prot,
 				  phys_addr_t (*pgtable_alloc)(void),
-				  bool allow_block_mappings)
+				  bool page_mappings_only)
 {
 	pud_t *pud;
 	unsigned long next;
@@ -204,33 +249,28 @@ static void alloc_init_pud(pgd_t *pgd, unsigned long addr, unsigned long end,
 
 	pud = pud_set_fixmap_offset(pgd, addr);
 	do {
+		pud_t old_pud = *pud;
+
 		next = pud_addr_end(addr, end);
 
 		/*
 		 * For 4K granule only, attempt to put down a 1GB block
 		 */
-		if (use_1G_block(addr, next, phys) && allow_block_mappings) {
-			pud_t old_pud = *pud;
+		if (use_1G_block(addr, next, phys) && !page_mappings_only) {
 			pud_set_huge(pud, phys, prot);
 
 			/*
-			 * If we have an old value for a pud, it will
-			 * be pointing to a pmd table that we no longer
-			 * need (from swapper_pg_dir).
-			 *
-			 * Look up the old pmd table and free it.
+			 * After the PUD entry has been populated once, we
+			 * only allow updates to the permission attributes.
 			 */
-			if (!pud_none(old_pud)) {
-				flush_tlb_all();
-				if (pud_table(old_pud)) {
-					phys_addr_t table = pud_page_paddr(old_pud);
-					if (!WARN_ON_ONCE(slab_is_available()))
-						memblock_free(table, PAGE_SIZE);
-				}
-			}
+			BUG_ON(!pgattr_change_is_safe(pud_val(old_pud),
+						      pud_val(*pud)));
 		} else {
 			alloc_init_pmd(pud, addr, next, phys, prot,
-				       pgtable_alloc, allow_block_mappings);
+				       pgtable_alloc, page_mappings_only);
+
+			BUG_ON(pud_val(old_pud) != 0 &&
+			       pud_val(old_pud) != pud_val(*pud));
 		}
 		phys += next - addr;
 	} while (pud++, addr = next, addr != end);
@@ -242,7 +282,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 				 unsigned long virt, phys_addr_t size,
 				 pgprot_t prot,
 				 phys_addr_t (*pgtable_alloc)(void),
-				 bool allow_block_mappings)
+				 bool page_mappings_only)
 {
 	unsigned long addr, length, end, next;
 	pgd_t *pgd = pgd_offset_raw(pgdir, virt);
@@ -262,7 +302,7 @@ static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
 	do {
 		next = pgd_addr_end(addr, end);
 		alloc_init_pud(pgd, addr, next, phys, prot, pgtable_alloc,
-			       allow_block_mappings);
+			       page_mappings_only);
 		phys += next - addr;
 	} while (pgd++, addr = next, addr != end);
 }
@@ -291,17 +331,17 @@ static void __init create_mapping_noalloc(phys_addr_t phys, unsigned long virt,
 			&phys, virt);
 		return;
 	}
-	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, true);
+	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot, NULL, false);
 }
 
 void __init create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys,
 			       unsigned long virt, phys_addr_t size,
-			       pgprot_t prot, bool allow_block_mappings)
+			       pgprot_t prot, bool page_mappings_only)
 {
 	BUG_ON(mm == &init_mm);
 
 	__create_pgd_mapping(mm->pgd, phys, virt, size, prot,
-			     pgd_pgtable_alloc, allow_block_mappings);
+			     pgd_pgtable_alloc, page_mappings_only);
 }
 
 static void create_mapping_late(phys_addr_t phys, unsigned long virt,
@@ -314,7 +354,7 @@ static void create_mapping_late(phys_addr_t phys, unsigned long virt,
 	}
 
 	__create_pgd_mapping(init_mm.pgd, phys, virt, size, prot,
-			     NULL, !debug_pagealloc_enabled());
+			     NULL, debug_pagealloc_enabled());
 }
 
 static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end)
@@ -332,7 +372,7 @@ static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end
 		__create_pgd_mapping(pgd, start, __phys_to_virt(start),
 				     end - start, PAGE_KERNEL,
 				     early_pgtable_alloc,
-				     !debug_pagealloc_enabled());
+				     debug_pagealloc_enabled());
 		return;
 	}
 
@@ -345,13 +385,13 @@ static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end
 				     __phys_to_virt(start),
 				     kernel_start - start, PAGE_KERNEL,
 				     early_pgtable_alloc,
-				     !debug_pagealloc_enabled());
+				     debug_pagealloc_enabled());
 	if (kernel_end < end)
 		__create_pgd_mapping(pgd, kernel_end,
 				     __phys_to_virt(kernel_end),
 				     end - kernel_end, PAGE_KERNEL,
 				     early_pgtable_alloc,
-				     !debug_pagealloc_enabled());
+				     debug_pagealloc_enabled());
 
 	/*
 	 * Map the linear alias of the [_text, __init_begin) interval as
@@ -361,7 +401,7 @@ static void __init __map_memblock(pgd_t *pgd, phys_addr_t start, phys_addr_t end
 	 */
 	__create_pgd_mapping(pgd, kernel_start, __phys_to_virt(kernel_start),
 			     kernel_end - kernel_start, PAGE_KERNEL_RO,
-			     early_pgtable_alloc, !debug_pagealloc_enabled());
+			     early_pgtable_alloc, debug_pagealloc_enabled());
 }
 
 static void __init map_mem(pgd_t *pgd)
@@ -396,6 +436,11 @@ void mark_rodata_ro(void)
 	section_size = (unsigned long)__init_begin - (unsigned long)__start_rodata;
 	create_mapping_late(__pa(__start_rodata), (unsigned long)__start_rodata,
 			    section_size, PAGE_KERNEL_RO);
+
+	/* flush the TLBs after updating live kernel mappings */
+	flush_tlb_all();
+
+	debug_checkwx();
 }
 
 static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
@@ -408,7 +453,7 @@ static void __init map_kernel_segment(pgd_t *pgd, void *va_start, void *va_end,
 	BUG_ON(!PAGE_ALIGNED(size));
 
 	__create_pgd_mapping(pgd, pa_start, (unsigned long)va_start, size, prot,
-			     early_pgtable_alloc, !debug_pagealloc_enabled());
+			     early_pgtable_alloc, debug_pagealloc_enabled());
 
 	vma->addr	= va_start;
 	vma->phys_addr	= pa_start;

arch/arm64/mm/proc.S

@@ -70,11 +70,14 @@ ENTRY(cpu_do_suspend)
 	mrs	x8, mdscr_el1
 	mrs	x9, oslsr_el1
 	mrs	x10, sctlr_el1
+	mrs	x11, tpidr_el1
+	mrs	x12, sp_el0
 	stp	x2, x3, [x0]
 	stp	x4, xzr, [x0, #16]
 	stp	x5, x6, [x0, #32]
 	stp	x7, x8, [x0, #48]
 	stp	x9, x10, [x0, #64]
+	stp	x11, x12, [x0, #80]
 	ret
 ENDPROC(cpu_do_suspend)
 
@@ -90,6 +93,7 @@ ENTRY(cpu_do_resume)
 	ldp	x6, x8, [x0, #32]
 	ldp	x9, x10, [x0, #48]
 	ldp	x11, x12, [x0, #64]
+	ldp	x13, x14, [x0, #80]
 	msr	tpidr_el0, x2
 	msr	tpidrro_el0, x3
 	msr	contextidr_el1, x4
@@ -112,6 +116,8 @@ ENTRY(cpu_do_resume)
 	msr	mdscr_el1, x10
 
 	msr	sctlr_el1, x12
+	msr	tpidr_el1, x13
+	msr	sp_el0, x14
 	/*
 	 * Restore oslsr_el1 by writing oslar_el1
 	 */
@@ -136,11 +142,7 @@ ENTRY(cpu_do_switch_mm)
 	bfi	x0, x1, #48, #16		// set the ASID
 	msr	ttbr0_el1, x0			// set TTBR0
 	isb
-alternative_if ARM64_WORKAROUND_CAVIUM_27456
-	ic	iallu
-	dsb	nsh
-	isb
-alternative_else_nop_endif
+	post_ttbr0_update_workaround
 	ret
 ENDPROC(cpu_do_switch_mm)
 

arch/arm64/mm/ptdump_debugfs.c

@@ -0,0 +1,31 @@
+#include <linux/debugfs.h>
+#include <linux/seq_file.h>
+
+#include <asm/ptdump.h>
+
+static int ptdump_show(struct seq_file *m, void *v)
+{
+	struct ptdump_info *info = m->private;
+	ptdump_walk_pgd(m, info);
+	return 0;
+}
+
+static int ptdump_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, ptdump_show, inode->i_private);
+}
+
+static const struct file_operations ptdump_fops = {
+	.open		= ptdump_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+int ptdump_debugfs_register(struct ptdump_info *info, const char *name)
+{
+	struct dentry *pe;
+	pe = debugfs_create_file(name, 0400, NULL, info, &ptdump_fops);
+	return pe ? 0 : -ENOMEM;
+
+}

arch/arm64/xen/hypercall.S

@@ -49,6 +49,7 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/uaccess.h>
 #include <xen/interface/xen.h>
 
 
@@ -91,6 +92,20 @@ ENTRY(privcmd_call)
 	mov x2, x3
 	mov x3, x4
 	mov x4, x5
+	/*
+	 * Privcmd calls are issued by the userspace. The kernel needs to
+	 * enable access to TTBR0_EL1 as the hypervisor would issue stage 1
+	 * translations to user memory via AT instructions. Since AT
+	 * instructions are not affected by the PAN bit (ARMv8.1), we only
+	 * need the explicit uaccess_enable/disable if the TTBR0 PAN emulation
+	 * is enabled (it implies that hardware UAO and PAN disabled).
+	 */
+	uaccess_ttbr0_enable x6, x7
 	hvc XEN_IMM
+
+	/*
+	 * Disable userspace access from kernel once the hyp call completed.
+	 */
+	uaccess_ttbr0_disable x6
 	ret
 ENDPROC(privcmd_call);

drivers/firmware/efi/arm-runtime.c

@@ -39,7 +39,7 @@ static struct mm_struct efi_mm = {
 	.mmlist			= LIST_HEAD_INIT(efi_mm.mmlist),
 };
 
-#ifdef CONFIG_ARM64_PTDUMP
+#ifdef CONFIG_ARM64_PTDUMP_DEBUGFS
 #include <asm/ptdump.h>
 
 static struct ptdump_info efi_ptdump_info = {
@@ -53,7 +53,7 @@ static struct ptdump_info efi_ptdump_info = {
 
 static int __init ptdump_init(void)
 {
-	return ptdump_register(&efi_ptdump_info, "efi_page_tables");
+	return ptdump_debugfs_register(&efi_ptdump_info, "efi_page_tables");
 }
 device_initcall(ptdump_init);
 

drivers/irqchip/irq-gic-v3.c

@@ -120,11 +120,10 @@ static void gic_redist_wait_for_rwp(void)
 }
 
 #ifdef CONFIG_ARM64
-static DEFINE_STATIC_KEY_FALSE(is_cavium_thunderx);
 
 static u64 __maybe_unused gic_read_iar(void)
 {
-	if (static_branch_unlikely(&is_cavium_thunderx))
+	if (cpus_have_const_cap(ARM64_WORKAROUND_CAVIUM_23154))
 		return gic_read_iar_cavium_thunderx();
 	else
 		return gic_read_iar_common();
@@ -905,14 +904,6 @@ static const struct irq_domain_ops partition_domain_ops = {
 	.select = gic_irq_domain_select,
 };
 
-static void gicv3_enable_quirks(void)
-{
-#ifdef CONFIG_ARM64
-	if (cpus_have_cap(ARM64_WORKAROUND_CAVIUM_23154))
-		static_branch_enable(&is_cavium_thunderx);
-#endif
-}
-
 static int __init gic_init_bases(void __iomem *dist_base,
 				 struct redist_region *rdist_regs,
 				 u32 nr_redist_regions,
@@ -935,8 +926,6 @@ static int __init gic_init_bases(void __iomem *dist_base,
 	gic_data.nr_redist_regions = nr_redist_regions;
 	gic_data.redist_stride = redist_stride;
 
-	gicv3_enable_quirks();
-
 	/*
 	 * Find out how many interrupts are supported.
 	 * The GIC only supports up to 1020 interrupt sources (SGI+PPI+SPI)

include/linux/restart_block.h

@@ -0,0 +1,51 @@
+/*
+ * Common syscall restarting data
+ */
+#ifndef __LINUX_RESTART_BLOCK_H
+#define __LINUX_RESTART_BLOCK_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+struct timespec;
+struct compat_timespec;
+struct pollfd;
+
+/*
+ * System call restart block.
+ */
+struct restart_block {
+	long (*fn)(struct restart_block *);
+	union {
+		/* For futex_wait and futex_wait_requeue_pi */
+		struct {
+			u32 __user *uaddr;
+			u32 val;
+			u32 flags;
+			u32 bitset;
+			u64 time;
+			u32 __user *uaddr2;
+		} futex;
+		/* For nanosleep */
+		struct {
+			clockid_t clockid;
+			struct timespec __user *rmtp;
+#ifdef CONFIG_COMPAT
+			struct compat_timespec __user *compat_rmtp;
+#endif
+			u64 expires;
+		} nanosleep;
+		/* For poll */
+		struct {
+			struct pollfd __user *ufds;
+			int nfds;
+			int has_timeout;
+			unsigned long tv_sec;
+			unsigned long tv_nsec;
+		} poll;
+	};
+};
+
+extern long do_no_restart_syscall(struct restart_block *parm);
+
+#endif /* __LINUX_RESTART_BLOCK_H */

include/linux/thread_info.h

@@ -9,50 +9,17 @@
 
 #include <linux/types.h>
 #include <linux/bug.h>
-
-struct timespec;
-struct compat_timespec;
+#include <linux/restart_block.h>
 
 #ifdef CONFIG_THREAD_INFO_IN_TASK
-#define current_thread_info() ((struct thread_info *)current)
-#endif
-
 /*
- * System call restart block.
+ * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the
+ * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels,
+ * including <asm/current.h> can cause a circular dependency on some platforms.
  */
-struct restart_block {
-	long (*fn)(struct restart_block *);
-	union {
-		/* For futex_wait and futex_wait_requeue_pi */
-		struct {
-			u32 __user *uaddr;
-			u32 val;
-			u32 flags;
-			u32 bitset;
-			u64 time;
-			u32 __user *uaddr2;
-		} futex;
-		/* For nanosleep */
-		struct {
-			clockid_t clockid;
-			struct timespec __user *rmtp;
-#ifdef CONFIG_COMPAT
-			struct compat_timespec __user *compat_rmtp;
+#include <asm/current.h>
+#define current_thread_info() ((struct thread_info *)current)
 #endif
-			u64 expires;
-		} nanosleep;
-		/* For poll */
-		struct {
-			struct pollfd __user *ufds;
-			int nfds;
-			int has_timeout;
-			unsigned long tv_sec;
-			unsigned long tv_nsec;
-		} poll;
-	};
-};
-
-extern long do_no_restart_syscall(struct restart_block *parm);
 
 #include <linux/bitops.h>
 #include <asm/thread_info.h>

include/uapi/linux/hw_breakpoint.h

@@ -4,7 +4,11 @@
 enum {
 	HW_BREAKPOINT_LEN_1 = 1,
 	HW_BREAKPOINT_LEN_2 = 2,
+	HW_BREAKPOINT_LEN_3 = 3,
 	HW_BREAKPOINT_LEN_4 = 4,
+	HW_BREAKPOINT_LEN_5 = 5,
+	HW_BREAKPOINT_LEN_6 = 6,
+	HW_BREAKPOINT_LEN_7 = 7,
 	HW_BREAKPOINT_LEN_8 = 8,
 };
 

tools/include/uapi/linux/hw_breakpoint.h

@@ -4,7 +4,11 @@
 enum {
 	HW_BREAKPOINT_LEN_1 = 1,
 	HW_BREAKPOINT_LEN_2 = 2,
+	HW_BREAKPOINT_LEN_3 = 3,
 	HW_BREAKPOINT_LEN_4 = 4,
+	HW_BREAKPOINT_LEN_5 = 5,
+	HW_BREAKPOINT_LEN_6 = 6,
+	HW_BREAKPOINT_LEN_7 = 7,
 	HW_BREAKPOINT_LEN_8 = 8,
 };
 

tools/testing/selftests/breakpoints/Makefile

@@ -5,6 +5,9 @@ ARCH ?= $(shell echo $(uname_M) | sed -e s/i.86/x86/ -e s/x86_64/x86/)
 ifeq ($(ARCH),x86)
 TEST_PROGS := breakpoint_test
 endif
+ifeq ($(ARCH),aarch64)
+TEST_PROGS := breakpoint_test_arm64
+endif
 
 TEST_PROGS += step_after_suspend_test
 
@@ -13,4 +16,4 @@ all: $(TEST_PROGS)
 include ../lib.mk
 
 clean:
-	rm -fr breakpoint_test step_after_suspend_test
+	rm -fr breakpoint_test breakpoint_test_arm64 step_after_suspend_test

tools/testing/selftests/breakpoints/breakpoint_test_arm64.c

@@ -0,0 +1,236 @@
+/*
+ * Copyright (C) 2016 Google, Inc.
+ *
+ * This software is licensed under the terms of the GNU General Public
+ * License version 2, as published by the Free Software Foundation, and
+ * may be copied, distributed, and modified under those terms.
+ *
+ * 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.
+ *
+ * Original Code by Pavel Labath <labath@google.com>
+ *
+ * Code modified by Pratyush Anand <panand@redhat.com>
+ * for testing different byte select for each access size.
+ *
+ */
+
+#define _GNU_SOURCE
+
+#include <sys/types.h>
+#include <sys/wait.h>
+#include <sys/ptrace.h>
+#include <sys/param.h>
+#include <sys/uio.h>
+#include <stdint.h>
+#include <stdbool.h>
+#include <stddef.h>
+#include <string.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <elf.h>
+#include <errno.h>
+#include <signal.h>
+
+#include "../kselftest.h"
+
+static volatile uint8_t var[96] __attribute__((__aligned__(32)));
+
+static void child(int size, int wr)
+{
+	volatile uint8_t *addr = &var[32 + wr];
+
+	if (ptrace(PTRACE_TRACEME, 0, NULL, NULL) != 0) {
+		perror("ptrace(PTRACE_TRACEME) failed");
+		_exit(1);
+	}
+
+	if (raise(SIGSTOP) != 0) {
+		perror("raise(SIGSTOP) failed");
+		_exit(1);
+	}
+
+	if ((uintptr_t) addr % size) {
+		perror("Wrong address write for the given size\n");
+		_exit(1);
+	}
+	switch (size) {
+	case 1:
+		*addr = 47;
+		break;
+	case 2:
+		*(uint16_t *)addr = 47;
+		break;
+	case 4:
+		*(uint32_t *)addr = 47;
+		break;
+	case 8:
+		*(uint64_t *)addr = 47;
+		break;
+	case 16:
+		__asm__ volatile ("stp x29, x30, %0" : "=m" (addr[0]));
+		break;
+	case 32:
+		__asm__ volatile ("stp q29, q30, %0" : "=m" (addr[0]));
+		break;
+	}
+
+	_exit(0);
+}
+
+static bool set_watchpoint(pid_t pid, int size, int wp)
+{
+	const volatile uint8_t *addr = &var[32 + wp];
+	const int offset = (uintptr_t)addr % 8;
+	const unsigned int byte_mask = ((1 << size) - 1) << offset;
+	const unsigned int type = 2; /* Write */
+	const unsigned int enable = 1;
+	const unsigned int control = byte_mask << 5 | type << 3 | enable;
+	struct user_hwdebug_state dreg_state;
+	struct iovec iov;
+
+	memset(&dreg_state, 0, sizeof(dreg_state));
+	dreg_state.dbg_regs[0].addr = (uintptr_t)(addr - offset);
+	dreg_state.dbg_regs[0].ctrl = control;
+	iov.iov_base = &dreg_state;
+	iov.iov_len = offsetof(struct user_hwdebug_state, dbg_regs) +
+				sizeof(dreg_state.dbg_regs[0]);
+	if (ptrace(PTRACE_SETREGSET, pid, NT_ARM_HW_WATCH, &iov) == 0)
+		return true;
+
+	if (errno == EIO) {
+		printf("ptrace(PTRACE_SETREGSET, NT_ARM_HW_WATCH) "
+			"not supported on this hardware\n");
+		ksft_exit_skip();
+	}
+	perror("ptrace(PTRACE_SETREGSET, NT_ARM_HW_WATCH) failed");
+	return false;
+}
+
+static bool run_test(int wr_size, int wp_size, int wr, int wp)
+{
+	int status;
+	siginfo_t siginfo;
+	pid_t pid = fork();
+	pid_t wpid;
+
+	if (pid < 0) {
+		perror("fork() failed");
+		return false;
+	}
+	if (pid == 0)
+		child(wr_size, wr);
+
+	wpid = waitpid(pid, &status, __WALL);
+	if (wpid != pid) {
+		perror("waitpid() failed");
+		return false;
+	}
+	if (!WIFSTOPPED(status)) {
+		printf("child did not stop\n");
+		return false;
+	}
+	if (WSTOPSIG(status) != SIGSTOP) {
+		printf("child did not stop with SIGSTOP\n");
+		return false;
+	}
+
+	if (!set_watchpoint(pid, wp_size, wp))
+		return false;
+
+	if (ptrace(PTRACE_CONT, pid, NULL, NULL) < 0) {
+		perror("ptrace(PTRACE_SINGLESTEP) failed");
+		return false;
+	}
+
+	alarm(3);
+	wpid = waitpid(pid, &status, __WALL);
+	if (wpid != pid) {
+		perror("waitpid() failed");
+		return false;
+	}
+	alarm(0);
+	if (WIFEXITED(status)) {
+		printf("child did not single-step\t");
+		return false;
+	}
+	if (!WIFSTOPPED(status)) {
+		printf("child did not stop\n");
+		return false;
+	}
+	if (WSTOPSIG(status) != SIGTRAP) {
+		printf("child did not stop with SIGTRAP\n");
+		return false;
+	}
+	if (ptrace(PTRACE_GETSIGINFO, pid, NULL, &siginfo) != 0) {
+		perror("ptrace(PTRACE_GETSIGINFO)");
+		return false;
+	}
+	if (siginfo.si_code != TRAP_HWBKPT) {
+		printf("Unexpected si_code %d\n", siginfo.si_code);
+		return false;
+	}
+
+	kill(pid, SIGKILL);
+	wpid = waitpid(pid, &status, 0);
+	if (wpid != pid) {
+		perror("waitpid() failed");
+		return false;
+	}
+	return true;
+}
+
+static void sigalrm(int sig)
+{
+}
+
+int main(int argc, char **argv)
+{
+	int opt;
+	bool succeeded = true;
+	struct sigaction act;
+	int wr, wp, size;
+	bool result;
+
+	act.sa_handler = sigalrm;
+	sigemptyset(&act.sa_mask);
+	act.sa_flags = 0;
+	sigaction(SIGALRM, &act, NULL);
+	for (size = 1; size <= 32; size = size*2) {
+		for (wr = 0; wr <= 32; wr = wr + size) {
+			for (wp = wr - size; wp <= wr + size; wp = wp + size) {
+				printf("Test size = %d write offset = %d watchpoint offset = %d\t", size, wr, wp);
+				result = run_test(size, MIN(size, 8), wr, wp);
+				if ((result && wr == wp) || (!result && wr != wp)) {
+					printf("[OK]\n");
+					ksft_inc_pass_cnt();
+				} else {
+					printf("[FAILED]\n");
+					ksft_inc_fail_cnt();
+					succeeded = false;
+				}
+			}
+		}
+	}
+
+	for (size = 1; size <= 32; size = size*2) {
+		printf("Test size = %d write offset = %d watchpoint offset = -8\t", size, -size);
+
+		if (run_test(size, 8, -size, -8)) {
+			printf("[OK]\n");
+			ksft_inc_pass_cnt();
+		} else {
+			printf("[FAILED]\n");
+			ksft_inc_fail_cnt();
+			succeeded = false;
+		}
+	}
+
+	ksft_print_cnts();
+	if (succeeded)
+		ksft_exit_pass();
+	else
+		ksft_exit_fail();
+}