diff options
Diffstat (limited to 'arch/arm64')
31 files changed, 119 insertions, 170 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 7f2a80091337..9f1d8566bbf9 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -11,6 +11,12 @@ config ARM64 select ACPI_PPTT if ACPI select ARCH_HAS_DEBUG_WX select ARCH_BINFMT_ELF_STATE + select ARCH_ENABLE_HUGEPAGE_MIGRATION if HUGETLB_PAGE && MIGRATION + select ARCH_ENABLE_MEMORY_HOTPLUG + select ARCH_ENABLE_MEMORY_HOTREMOVE + select ARCH_ENABLE_SPLIT_PMD_PTLOCK if PGTABLE_LEVELS > 2 + select ARCH_ENABLE_THP_MIGRATION if TRANSPARENT_HUGEPAGE + select ARCH_HAS_CACHE_LINE_SIZE select ARCH_HAS_DEBUG_VIRTUAL select ARCH_HAS_DEBUG_VM_PGTABLE select ARCH_HAS_DMA_PREP_COHERENT @@ -72,6 +78,7 @@ config ARM64 select ARCH_USE_QUEUED_SPINLOCKS select ARCH_USE_SYM_ANNOTATIONS select ARCH_SUPPORTS_DEBUG_PAGEALLOC + select ARCH_SUPPORTS_HUGETLBFS select ARCH_SUPPORTS_MEMORY_FAILURE select ARCH_SUPPORTS_SHADOW_CALL_STACK if CC_HAVE_SHADOW_CALL_STACK select ARCH_SUPPORTS_LTO_CLANG if CPU_LITTLE_ENDIAN @@ -163,7 +170,6 @@ config ARM64 select HAVE_CMPXCHG_DOUBLE select HAVE_CMPXCHG_LOCAL select HAVE_CONTEXT_TRACKING - select HAVE_DEBUG_BUGVERBOSE select HAVE_DEBUG_KMEMLEAK select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE @@ -213,6 +219,7 @@ config ARM64 select SWIOTLB select SYSCTL_EXCEPTION_TRACE select THREAD_INFO_IN_TASK + select HAVE_ARCH_USERFAULTFD_MINOR if USERFAULTFD help ARM 64-bit (AArch64) Linux support. @@ -308,10 +315,7 @@ config ZONE_DMA32 bool "Support DMA32 zone" if EXPERT default y -config ARCH_ENABLE_MEMORY_HOTPLUG - def_bool y - -config ARCH_ENABLE_MEMORY_HOTREMOVE +config ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE def_bool y config SMP @@ -1056,32 +1060,15 @@ source "kernel/Kconfig.hz" config ARCH_SPARSEMEM_ENABLE def_bool y select SPARSEMEM_VMEMMAP_ENABLE - -config ARCH_SPARSEMEM_DEFAULT - def_bool ARCH_SPARSEMEM_ENABLE - -config ARCH_SELECT_MEMORY_MODEL - def_bool ARCH_SPARSEMEM_ENABLE - -config ARCH_FLATMEM_ENABLE - def_bool !NUMA + select SPARSEMEM_VMEMMAP config HW_PERF_EVENTS def_bool y depends on ARM_PMU -config SYS_SUPPORTS_HUGETLBFS - def_bool y - -config ARCH_HAS_CACHE_LINE_SIZE - def_bool y - config ARCH_HAS_FILTER_PGPROT def_bool y -config ARCH_ENABLE_SPLIT_PMD_PTLOCK - def_bool y if PGTABLE_LEVELS > 2 - # Supported by clang >= 7.0 config CC_HAVE_SHADOW_CALL_STACK def_bool $(cc-option, -fsanitize=shadow-call-stack -ffixed-x18) @@ -1923,14 +1910,6 @@ config SYSVIPC_COMPAT def_bool y depends on COMPAT && SYSVIPC -config ARCH_ENABLE_HUGEPAGE_MIGRATION - def_bool y - depends on HUGETLB_PAGE && MIGRATION - -config ARCH_ENABLE_THP_MIGRATION - def_bool y - depends on TRANSPARENT_HUGEPAGE - menu "Power management options" source "kernel/power/Kconfig" diff --git a/arch/arm64/boot/dts/rockchip/rk3368.dtsi b/arch/arm64/boot/dts/rockchip/rk3368.dtsi index 242f821a90ba..dfc6376171d0 100644 --- a/arch/arm64/boot/dts/rockchip/rk3368.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3368.dtsi @@ -558,7 +558,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pwm0_pin>; clocks = <&cru PCLK_PWM1>; - clock-names = "pwm"; status = "disabled"; }; @@ -569,7 +568,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pwm1_pin>; clocks = <&cru PCLK_PWM1>; - clock-names = "pwm"; status = "disabled"; }; @@ -578,7 +576,6 @@ reg = <0x0 0xff680020 0x0 0x10>; #pwm-cells = <3>; clocks = <&cru PCLK_PWM1>; - clock-names = "pwm"; status = "disabled"; }; @@ -589,7 +586,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pwm3_pin>; clocks = <&cru PCLK_PWM1>; - clock-names = "pwm"; status = "disabled"; }; diff --git a/arch/arm64/boot/dts/rockchip/rk3399.dtsi b/arch/arm64/boot/dts/rockchip/rk3399.dtsi index 0f2879cc1a66..634a91af8e83 100644 --- a/arch/arm64/boot/dts/rockchip/rk3399.dtsi +++ b/arch/arm64/boot/dts/rockchip/rk3399.dtsi @@ -1182,7 +1182,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pwm0_pin>; clocks = <&pmucru PCLK_RKPWM_PMU>; - clock-names = "pwm"; status = "disabled"; }; @@ -1193,7 +1192,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pwm1_pin>; clocks = <&pmucru PCLK_RKPWM_PMU>; - clock-names = "pwm"; status = "disabled"; }; @@ -1204,7 +1202,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pwm2_pin>; clocks = <&pmucru PCLK_RKPWM_PMU>; - clock-names = "pwm"; status = "disabled"; }; @@ -1215,7 +1212,6 @@ pinctrl-names = "default"; pinctrl-0 = <&pwm3a_pin>; clocks = <&pmucru PCLK_RKPWM_PMU>; - clock-names = "pwm"; status = "disabled"; }; diff --git a/arch/arm64/include/asm/daifflags.h b/arch/arm64/include/asm/daifflags.h index 5eb7af9c4557..55f57dfa8e2f 100644 --- a/arch/arm64/include/asm/daifflags.h +++ b/arch/arm64/include/asm/daifflags.h @@ -131,6 +131,9 @@ static inline void local_daif_inherit(struct pt_regs *regs) if (interrupts_enabled(regs)) trace_hardirqs_on(); + if (system_uses_irq_prio_masking()) + gic_write_pmr(regs->pmr_save); + /* * We can't use local_daif_restore(regs->pstate) here as * system_has_prio_mask_debugging() won't restore the I bit if it can diff --git a/arch/arm64/include/asm/kernel-pgtable.h b/arch/arm64/include/asm/kernel-pgtable.h index 587c504a4c8b..d44df9d62fc9 100644 --- a/arch/arm64/include/asm/kernel-pgtable.h +++ b/arch/arm64/include/asm/kernel-pgtable.h @@ -136,7 +136,7 @@ * has a direct correspondence, and needs to appear sufficiently aligned * in the virtual address space. */ -#if defined(CONFIG_SPARSEMEM_VMEMMAP) && ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS +#if ARM64_MEMSTART_SHIFT < SECTION_SIZE_BITS #define ARM64_MEMSTART_ALIGN (1UL << SECTION_SIZE_BITS) #else #define ARM64_MEMSTART_ALIGN (1UL << ARM64_MEMSTART_SHIFT) diff --git a/arch/arm64/include/asm/kvm_asm.h b/arch/arm64/include/asm/kvm_asm.h index cf8df032b9c3..5e9b33cbac51 100644 --- a/arch/arm64/include/asm/kvm_asm.h +++ b/arch/arm64/include/asm/kvm_asm.h @@ -63,6 +63,7 @@ #define __KVM_HOST_SMCCC_FUNC___pkvm_cpu_set_vector 18 #define __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize 19 #define __KVM_HOST_SMCCC_FUNC___pkvm_mark_hyp 20 +#define __KVM_HOST_SMCCC_FUNC___kvm_adjust_pc 21 #ifndef __ASSEMBLY__ @@ -201,6 +202,8 @@ extern void __kvm_timer_set_cntvoff(u64 cntvoff); extern int __kvm_vcpu_run(struct kvm_vcpu *vcpu); +extern void __kvm_adjust_pc(struct kvm_vcpu *vcpu); + extern u64 __vgic_v3_get_gic_config(void); extern u64 __vgic_v3_read_vmcr(void); extern void __vgic_v3_write_vmcr(u32 vmcr); diff --git a/arch/arm64/include/asm/memory.h b/arch/arm64/include/asm/memory.h index 6d9915d066fa..87b90dc27a43 100644 --- a/arch/arm64/include/asm/memory.h +++ b/arch/arm64/include/asm/memory.h @@ -345,7 +345,7 @@ static inline void *phys_to_virt(phys_addr_t x) */ #define ARCH_PFN_OFFSET ((unsigned long)PHYS_PFN_OFFSET) -#if !defined(CONFIG_SPARSEMEM_VMEMMAP) || defined(CONFIG_DEBUG_VIRTUAL) +#if defined(CONFIG_DEBUG_VIRTUAL) #define page_to_virt(x) ({ \ __typeof__(x) __page = x; \ void *__addr = __va(page_to_phys(__page)); \ @@ -365,7 +365,7 @@ static inline void *phys_to_virt(phys_addr_t x) u64 __addr = VMEMMAP_START + (__idx * sizeof(struct page)); \ (struct page *)__addr; \ }) -#endif /* !CONFIG_SPARSEMEM_VMEMMAP || CONFIG_DEBUG_VIRTUAL */ +#endif /* CONFIG_DEBUG_VIRTUAL */ #define virt_addr_valid(addr) ({ \ __typeof__(addr) __addr = __tag_reset(addr); \ diff --git a/arch/arm64/include/asm/sparsemem.h b/arch/arm64/include/asm/sparsemem.h index eb4a75d720ed..4b73463423c3 100644 --- a/arch/arm64/include/asm/sparsemem.h +++ b/arch/arm64/include/asm/sparsemem.h @@ -5,7 +5,6 @@ #ifndef __ASM_SPARSEMEM_H #define __ASM_SPARSEMEM_H -#ifdef CONFIG_SPARSEMEM #define MAX_PHYSMEM_BITS CONFIG_ARM64_PA_BITS /* @@ -27,6 +26,4 @@ #define SECTION_SIZE_BITS 27 #endif /* CONFIG_ARM64_64K_PAGES */ -#endif /* CONFIG_SPARSEMEM*/ - #endif diff --git a/arch/arm64/kernel/alternative.c b/arch/arm64/kernel/alternative.c index abc84636af07..c906d20c7b52 100644 --- a/arch/arm64/kernel/alternative.c +++ b/arch/arm64/kernel/alternative.c @@ -133,11 +133,10 @@ static void clean_dcache_range_nopatch(u64 start, u64 end) } while (cur += d_size, cur < end); } -static void __nocfi __apply_alternatives(void *alt_region, bool is_module, - unsigned long *feature_mask) +static void __nocfi __apply_alternatives(struct alt_region *region, bool is_module, + unsigned long *feature_mask) { struct alt_instr *alt; - struct alt_region *region = alt_region; __le32 *origptr, *updptr; alternative_cb_t alt_cb; diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 30c82d38c189..efed2830d141 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -68,6 +68,7 @@ #include <linux/sort.h> #include <linux/stop_machine.h> #include <linux/types.h> +#include <linux/minmax.h> #include <linux/mm.h> #include <linux/cpu.h> #include <linux/kasan.h> @@ -694,14 +695,14 @@ static s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, ret = ftrp->safe_val; break; case FTR_LOWER_SAFE: - ret = new < cur ? new : cur; + ret = min(new, cur); break; case FTR_HIGHER_OR_ZERO_SAFE: if (!cur || !new) break; fallthrough; case FTR_HIGHER_SAFE: - ret = new > cur ? new : cur; + ret = max(new, cur); break; default: BUG(); diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c index b512b5503f6e..03991eeff643 100644 --- a/arch/arm64/kernel/cpuidle.c +++ b/arch/arm64/kernel/cpuidle.c @@ -29,7 +29,7 @@ int arm_cpuidle_init(unsigned int cpu) /** * arm_cpuidle_suspend() - function to enter a low-power idle state - * @arg: argument to pass to CPU suspend operations + * @index: argument to pass to CPU suspend operations * * Return: 0 on success, -EOPNOTSUPP if CPU suspend hook not initialized, CPU * operations back-end error code otherwise. diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index a1ec351c36bd..340d04e13617 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -230,14 +230,6 @@ static void noinstr el1_dbg(struct pt_regs *regs, unsigned long esr) { unsigned long far = read_sysreg(far_el1); - /* - * The CPU masked interrupts, and we are leaving them masked during - * do_debug_exception(). Update PMR as if we had called - * local_daif_mask(). - */ - if (system_uses_irq_prio_masking()) - gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - arm64_enter_el1_dbg(regs); if (!cortex_a76_erratum_1463225_debug_handler(regs)) do_debug_exception(far, esr, regs); @@ -404,9 +396,6 @@ static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr) /* Only watchpoints write FAR_EL1, otherwise its UNKNOWN */ unsigned long far = read_sysreg(far_el1); - if (system_uses_irq_prio_masking()) - gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - enter_from_user_mode(); do_debug_exception(far, esr, regs); local_daif_restore(DAIF_PROCCTX_NOIRQ); @@ -414,9 +403,6 @@ static void noinstr el0_dbg(struct pt_regs *regs, unsigned long esr) static void noinstr el0_svc(struct pt_regs *regs) { - if (system_uses_irq_prio_masking()) - gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - enter_from_user_mode(); cortex_a76_erratum_1463225_svc_handler(); do_el0_svc(regs); @@ -492,9 +478,6 @@ static void noinstr el0_cp15(struct pt_regs *regs, unsigned long esr) static void noinstr el0_svc_compat(struct pt_regs *regs) { - if (system_uses_irq_prio_masking()) - gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - enter_from_user_mode(); cortex_a76_erratum_1463225_svc_handler(); do_el0_svc_compat(regs); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 4ac5455c0ead..3513984a88bd 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -285,16 +285,16 @@ alternative_else_nop_endif stp lr, x21, [sp, #S_LR] /* - * For exceptions from EL0, terminate the callchain here. + * For exceptions from EL0, create a terminal frame record. * For exceptions from EL1, create a synthetic frame record so the * interrupted code shows up in the backtrace. */ .if \el == 0 - mov x29, xzr + stp xzr, xzr, [sp, #S_STACKFRAME] .else stp x29, x22, [sp, #S_STACKFRAME] - add x29, sp, #S_STACKFRAME .endif + add x29, sp, #S_STACKFRAME #ifdef CONFIG_ARM64_SW_TTBR0_PAN alternative_if_not ARM64_HAS_PAN @@ -314,6 +314,8 @@ alternative_else_nop_endif alternative_if ARM64_HAS_IRQ_PRIO_MASKING mrs_s x20, SYS_ICC_PMR_EL1 str x20, [sp, #S_PMR_SAVE] + mov x20, #GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET + msr_s SYS_ICC_PMR_EL1, x20 alternative_else_nop_endif /* Re-enable tag checking (TCO set on exception entry) */ @@ -550,17 +552,7 @@ tsk .req x28 // current thread_info #endif .endm - .macro gic_prio_irq_setup, pmr:req, tmp:req -#ifdef CONFIG_ARM64_PSEUDO_NMI - alternative_if ARM64_HAS_IRQ_PRIO_MASKING - orr \tmp, \pmr, #GIC_PRIO_PSR_I_SET - msr_s SYS_ICC_PMR_EL1, \tmp - alternative_else_nop_endif -#endif - .endm - .macro el1_interrupt_handler, handler:req - gic_prio_irq_setup pmr=x20, tmp=x1 enable_da mov x0, sp @@ -590,7 +582,6 @@ alternative_else_nop_endif .endm .macro el0_interrupt_handler, handler:req - gic_prio_irq_setup pmr=x20, tmp=x0 user_exit_irqoff enable_da @@ -788,7 +779,6 @@ SYM_CODE_END(el0_fiq) SYM_CODE_START_LOCAL(el1_error) kernel_entry 1 mrs x1, esr_el1 - gic_prio_kentry_setup tmp=x2 enable_dbg mov x0, sp bl do_serror @@ -799,7 +789,6 @@ SYM_CODE_START_LOCAL(el0_error) kernel_entry 0 el0_error_naked: mrs x25, esr_el1 - gic_prio_kentry_setup tmp=x2 user_exit_irqoff enable_dbg mov x0, sp diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index cbf52109583b..b4bb67f17a2c 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -294,13 +294,10 @@ void __show_regs(struct pt_regs *regs) i = top_reg; while (i >= 0) { - printk("x%-2d: %016llx ", i, regs->regs[i]); - i--; + printk("x%-2d: %016llx", i, regs->regs[i]); - if (i % 2 == 0) { - pr_cont("x%-2d: %016llx ", i, regs->regs[i]); - i--; - } + while (i-- % 3) + pr_cont(" x%-2d: %016llx", i, regs->regs[i]); pr_cont("\n"); } diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 84b676bcf867..de07147a7926 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -68,10 +68,6 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) unsigned long fp = frame->fp; struct stack_info info; - /* Terminal record; nothing to unwind */ - if (!fp) - return -ENOENT; - if (fp & 0xf) return -EINVAL; @@ -132,6 +128,12 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->pc = ptrauth_strip_insn_pac(frame->pc); + /* + * This is a terminal record, so we have finished unwinding. + */ + if (!frame->fp && !frame->pc) + return -ENOENT; + return 0; } NOKPROBE_SYMBOL(unwind_frame); diff --git a/arch/arm64/kernel/vdso/vdso.lds.S b/arch/arm64/kernel/vdso/vdso.lds.S index 61dbb4c838ef..a5e61e09ea92 100644 --- a/arch/arm64/kernel/vdso/vdso.lds.S +++ b/arch/arm64/kernel/vdso/vdso.lds.S @@ -31,6 +31,13 @@ SECTIONS .gnu.version_d : { *(.gnu.version_d) } .gnu.version_r : { *(.gnu.version_r) } + /* + * Discard .note.gnu.property sections which are unused and have + * different alignment requirement from vDSO note sections. + */ + /DISCARD/ : { + *(.note.GNU-stack .note.gnu.property) + } .note : { *(.note.*) } :text :note . = ALIGN(16); @@ -48,7 +55,6 @@ SECTIONS PROVIDE(end = .); /DISCARD/ : { - *(.note.GNU-stack) *(.data .data.* .gnu.linkonce.d.* .sdata*) *(.bss .sbss .dynbss .dynsbss) *(.eh_frame .eh_frame_hdr) diff --git a/arch/arm64/kernel/vdso32/Makefile b/arch/arm64/kernel/vdso32/Makefile index 789ad420f16b..3dba0c4f8f42 100644 --- a/arch/arm64/kernel/vdso32/Makefile +++ b/arch/arm64/kernel/vdso32/Makefile @@ -10,15 +10,7 @@ include $(srctree)/lib/vdso/Makefile # Same as cc-*option, but using CC_COMPAT instead of CC ifeq ($(CONFIG_CC_IS_CLANG), y) -COMPAT_GCC_TOOLCHAIN_DIR := $(dir $(shell which $(CROSS_COMPILE_COMPAT)elfedit)) -COMPAT_GCC_TOOLCHAIN := $(realpath $(COMPAT_GCC_TOOLCHAIN_DIR)/..) - CC_COMPAT_CLANG_FLAGS := --target=$(notdir $(CROSS_COMPILE_COMPAT:%-=%)) -CC_COMPAT_CLANG_FLAGS += --prefix=$(COMPAT_GCC_TOOLCHAIN_DIR)$(notdir $(CROSS_COMPILE_COMPAT)) -CC_COMPAT_CLANG_FLAGS += -no-integrated-as -Qunused-arguments -ifneq ($(COMPAT_GCC_TOOLCHAIN),) -CC_COMPAT_CLANG_FLAGS += --gcc-toolchain=$(COMPAT_GCC_TOOLCHAIN) -endif CC_COMPAT ?= $(CC) CC_COMPAT += $(CC_COMPAT_CLANG_FLAGS) diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c index 1cb39c0803a4..1126eae27400 100644 --- a/arch/arm64/kvm/arm.c +++ b/arch/arm64/kvm/arm.c @@ -897,6 +897,17 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu) kvm_sigset_deactivate(vcpu); + /* + * In the unlikely event that we are returning to userspace + * with pending exceptions or PC adjustment, commit these + * adjustments in order to give userspace a consistent view of + * the vcpu state. Note that this relies on __kvm_adjust_pc() + * being preempt-safe on VHE. + */ + if (unlikely(vcpu->arch.flags & (KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_INCREMENT_PC))) + kvm_call_hyp(__kvm_adjust_pc, vcpu); + vcpu_put(vcpu); return ret; } diff --git a/arch/arm64/kvm/hyp/exception.c b/arch/arm64/kvm/hyp/exception.c index 73629094f903..11541b94b328 100644 --- a/arch/arm64/kvm/hyp/exception.c +++ b/arch/arm64/kvm/hyp/exception.c @@ -296,7 +296,7 @@ static void enter_exception32(struct kvm_vcpu *vcpu, u32 mode, u32 vect_offset) *vcpu_pc(vcpu) = vect_offset; } -void kvm_inject_exception(struct kvm_vcpu *vcpu) +static void kvm_inject_exception(struct kvm_vcpu *vcpu) { if (vcpu_el1_is_32bit(vcpu)) { switch (vcpu->arch.flags & KVM_ARM64_EXCEPT_MASK) { @@ -329,3 +329,19 @@ void kvm_inject_exception(struct kvm_vcpu *vcpu) } } } + +/* + * Adjust the guest PC (and potentially exception state) depending on + * flags provided by the emulation code. + */ +void __kvm_adjust_pc(struct kvm_vcpu *vcpu) +{ + if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) { + kvm_inject_exception(vcpu); + vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION | + KVM_ARM64_EXCEPT_MASK); + } else if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) { + kvm_skip_instr(vcpu); + vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC; + } +} diff --git a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h index 61716359035d..4fdfeabefeb4 100644 --- a/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h +++ b/arch/arm64/kvm/hyp/include/hyp/adjust_pc.h @@ -13,8 +13,6 @@ #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> -void kvm_inject_exception(struct kvm_vcpu *vcpu); - static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { @@ -44,22 +42,6 @@ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) } /* - * Adjust the guest PC on entry, depending on flags provided by EL1 - * for the purpose of emulation (MMIO, sysreg) or exception injection. - */ -static inline void __adjust_pc(struct kvm_vcpu *vcpu) -{ - if (vcpu->arch.flags & KVM_ARM64_PENDING_EXCEPTION) { - kvm_inject_exception(vcpu); - vcpu->arch.flags &= ~(KVM_ARM64_PENDING_EXCEPTION | - KVM_ARM64_EXCEPT_MASK); - } else if (vcpu->arch.flags & KVM_ARM64_INCREMENT_PC) { - kvm_skip_instr(vcpu); - vcpu->arch.flags &= ~KVM_ARM64_INCREMENT_PC; - } -} - -/* * Skip an instruction while host sysregs are live. * Assumes host is always 64-bit. */ diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c index f36420a80474..1632f001f4ed 100644 --- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c +++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c @@ -28,6 +28,13 @@ static void handle___kvm_vcpu_run(struct kvm_cpu_context *host_ctxt) cpu_reg(host_ctxt, 1) = __kvm_vcpu_run(kern_hyp_va(vcpu)); } +static void handle___kvm_adjust_pc(struct kvm_cpu_context *host_ctxt) +{ + DECLARE_REG(struct kvm_vcpu *, vcpu, host_ctxt, 1); + + __kvm_adjust_pc(kern_hyp_va(vcpu)); +} + static void handle___kvm_flush_vm_context(struct kvm_cpu_context *host_ctxt) { __kvm_flush_vm_context(); @@ -170,6 +177,7 @@ typedef void (*hcall_t)(struct kvm_cpu_context *); static const hcall_t host_hcall[] = { HANDLE_FUNC(__kvm_vcpu_run), + HANDLE_FUNC(__kvm_adjust_pc), HANDLE_FUNC(__kvm_flush_vm_context), HANDLE_FUNC(__kvm_tlb_flush_vmid_ipa), HANDLE_FUNC(__kvm_tlb_flush_vmid), diff --git a/arch/arm64/kvm/hyp/nvhe/mem_protect.c b/arch/arm64/kvm/hyp/nvhe/mem_protect.c index e342f7f4f4fb..4b60c0056c04 100644 --- a/arch/arm64/kvm/hyp/nvhe/mem_protect.c +++ b/arch/arm64/kvm/hyp/nvhe/mem_protect.c @@ -23,8 +23,8 @@ extern unsigned long hyp_nr_cpus; struct host_kvm host_kvm; -struct hyp_pool host_s2_mem; -struct hyp_pool host_s2_dev; +static struct hyp_pool host_s2_mem; +static struct hyp_pool host_s2_dev; /* * Copies of the host's CPU features registers holding sanitized values. diff --git a/arch/arm64/kvm/hyp/nvhe/setup.c b/arch/arm64/kvm/hyp/nvhe/setup.c index 7488f53b0aa2..a3d3a275344e 100644 --- a/arch/arm64/kvm/hyp/nvhe/setup.c +++ b/arch/arm64/kvm/hyp/nvhe/setup.c @@ -17,7 +17,6 @@ #include <nvhe/trap_handler.h> struct hyp_pool hpool; -struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; unsigned long hyp_nr_cpus; #define hyp_percpu_size ((unsigned long)__per_cpu_end - \ @@ -27,6 +26,7 @@ static void *vmemmap_base; static void *hyp_pgt_base; static void *host_s2_mem_pgt_base; static void *host_s2_dev_pgt_base; +static struct kvm_pgtable_mm_ops pkvm_pgtable_mm_ops; static int divide_memory_pool(void *virt, unsigned long size) { diff --git a/arch/arm64/kvm/hyp/nvhe/switch.c b/arch/arm64/kvm/hyp/nvhe/switch.c index e9f6ea704d07..f7af9688c1f7 100644 --- a/arch/arm64/kvm/hyp/nvhe/switch.c +++ b/arch/arm64/kvm/hyp/nvhe/switch.c @@ -4,7 +4,6 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ -#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <hyp/sysreg-sr.h> @@ -201,7 +200,7 @@ int __kvm_vcpu_run(struct kvm_vcpu *vcpu) */ __debug_save_host_buffers_nvhe(vcpu); - __adjust_pc(vcpu); + __kvm_adjust_pc(vcpu); /* * We must restore the 32-bit state before the sysregs, thanks diff --git a/arch/arm64/kvm/hyp/vhe/switch.c b/arch/arm64/kvm/hyp/vhe/switch.c index 7b8f7db5c1ed..b3229924d243 100644 --- a/arch/arm64/kvm/hyp/vhe/switch.c +++ b/arch/arm64/kvm/hyp/vhe/switch.c @@ -4,7 +4,6 @@ * Author: Marc Zyngier <marc.zyngier@arm.com> */ -#include <hyp/adjust_pc.h> #include <hyp/switch.h> #include <linux/arm-smccc.h> @@ -132,7 +131,7 @@ static int __kvm_vcpu_run_vhe(struct kvm_vcpu *vcpu) __load_guest_stage2(vcpu->arch.hw_mmu); __activate_traps(vcpu); - __adjust_pc(vcpu); + __kvm_adjust_pc(vcpu); sysreg_restore_guest_state_vhe(guest_ctxt); __debug_switch_to_guest(vcpu); diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c index c5d1f3c87dbd..c10207fed2f3 100644 --- a/arch/arm64/kvm/mmu.c +++ b/arch/arm64/kvm/mmu.c @@ -1156,13 +1156,13 @@ out_unlock: bool kvm_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) - return 0; + return false; __unmap_stage2_range(&kvm->arch.mmu, range->start << PAGE_SHIFT, (range->end - range->start) << PAGE_SHIFT, range->may_block); - return 0; + return false; } bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1170,7 +1170,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) kvm_pfn_t pfn = pte_pfn(range->pte); if (!kvm->arch.mmu.pgt) - return 0; + return false; WARN_ON(range->end - range->start != 1); @@ -1190,7 +1190,7 @@ bool kvm_set_spte_gfn(struct kvm *kvm, struct kvm_gfn_range *range) PAGE_SIZE, __pfn_to_phys(pfn), KVM_PGTABLE_PROT_R, NULL); - return 0; + return false; } bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) @@ -1200,7 +1200,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) pte_t pte; if (!kvm->arch.mmu.pgt) - return 0; + return false; WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PUD_SIZE); @@ -1213,7 +1213,7 @@ bool kvm_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) bool kvm_test_age_gfn(struct kvm *kvm, struct kvm_gfn_range *range) { if (!kvm->arch.mmu.pgt) - return 0; + return false; return kvm_pgtable_stage2_is_young(kvm->arch.mmu.pgt, range->start << PAGE_SHIFT); diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c index 76ea2800c33e..1a7968ad078c 100644 --- a/arch/arm64/kvm/sys_regs.c +++ b/arch/arm64/kvm/sys_regs.c @@ -399,14 +399,14 @@ static bool trap_bvr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -414,7 +414,7 @@ static bool trap_bvr(struct kvm_vcpu *vcpu, static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -424,7 +424,7 @@ static int set_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -434,21 +434,21 @@ static int get_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_bvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_bvr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_bvr[rd->CRm] = rd->val; } static bool trap_bcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -456,7 +456,7 @@ static bool trap_bcr(struct kvm_vcpu *vcpu, static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -467,7 +467,7 @@ static int set_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -477,22 +477,22 @@ static int get_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_bcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_bcr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_bcr[rd->CRm] = rd->val; } static bool trap_wvr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]); + trace_trap_reg(__func__, rd->CRm, p->is_write, + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]); return true; } @@ -500,7 +500,7 @@ static bool trap_wvr(struct kvm_vcpu *vcpu, static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -510,7 +510,7 @@ static int set_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -520,21 +520,21 @@ static int get_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_wvr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_wvr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_wvr[rd->CRm] = rd->val; } static bool trap_wcr(struct kvm_vcpu *vcpu, struct sys_reg_params *p, const struct sys_reg_desc *rd) { - u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + u64 *dbg_reg = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (p->is_write) reg_to_dbg(vcpu, p, rd, dbg_reg); else dbg_to_reg(vcpu, p, rd, dbg_reg); - trace_trap_reg(__func__, rd->reg, p->is_write, *dbg_reg); + trace_trap_reg(__func__, rd->CRm, p->is_write, *dbg_reg); return true; } @@ -542,7 +542,7 @@ static bool trap_wcr(struct kvm_vcpu *vcpu, static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (copy_from_user(r, uaddr, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -552,7 +552,7 @@ static int set_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, const struct kvm_one_reg *reg, void __user *uaddr) { - __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg]; + __u64 *r = &vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm]; if (copy_to_user(uaddr, r, KVM_REG_SIZE(reg->id)) != 0) return -EFAULT; @@ -562,7 +562,7 @@ static int get_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, static void reset_wcr(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd) { - vcpu->arch.vcpu_debug_state.dbg_wcr[rd->reg] = rd->val; + vcpu->arch.vcpu_debug_state.dbg_wcr[rd->CRm] = rd->val; } static void reset_amair_el1(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c index 55ecf6de9ff7..58987a98e179 100644 --- a/arch/arm64/mm/hugetlbpage.c +++ b/arch/arm64/mm/hugetlbpage.c @@ -252,7 +252,7 @@ void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr, set_pte(ptep, pte); } -pte_t *huge_pte_alloc(struct mm_struct *mm, +pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgdp; @@ -284,9 +284,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, */ ptep = pte_alloc_map(mm, pmdp, addr); } else if (sz == PMD_SIZE) { - if (IS_ENABLED(CONFIG_ARCH_WANT_HUGE_PMD_SHARE) && - pud_none(READ_ONCE(*pudp))) - ptep = huge_pmd_share(mm, addr, pudp); + if (want_pmd_share(vma, addr) && pud_none(READ_ONCE(*pudp))) + ptep = huge_pmd_share(mm, vma, addr, pudp); else ptep = (pte_t *)pmd_alloc(mm, pudp, addr); } else if (sz == (CONT_PMD_SIZE)) { diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 0696a459ea95..16a2b2b1c54d 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -221,6 +221,7 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max) int pfn_valid(unsigned long pfn) { phys_addr_t addr = PFN_PHYS(pfn); + struct mem_section *ms; /* * Ensure the upper PAGE_SHIFT bits are clear in the @@ -231,10 +232,6 @@ int pfn_valid(unsigned long pfn) if (PHYS_PFN(addr) != pfn) return 0; -#ifdef CONFIG_SPARSEMEM -{ - struct mem_section *ms; - if (pfn_to_section_nr(pfn) >= NR_MEM_SECTIONS) return 0; @@ -253,8 +250,7 @@ int pfn_valid(unsigned long pfn) */ if (!early_section(ms)) return pfn_section_valid(ms, pfn); -} -#endif + return memblock_is_map_memory(addr); } EXPORT_SYMBOL(pfn_valid); diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 70fa3cdbe841..6dd9369e3ea0 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -1113,7 +1113,6 @@ static void free_empty_tables(unsigned long addr, unsigned long end, } #endif -#ifdef CONFIG_SPARSEMEM_VMEMMAP #if !ARM64_SWAPPER_USES_SECTION_MAPS int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node, struct vmem_altmap *altmap) @@ -1177,7 +1176,6 @@ void vmemmap_free(unsigned long start, unsigned long end, free_empty_tables(start, end, VMEMMAP_START, VMEMMAP_END); #endif } -#endif /* CONFIG_SPARSEMEM_VMEMMAP */ static inline pud_t *fixmap_pud(unsigned long addr) { diff --git a/arch/arm64/mm/ptdump.c b/arch/arm64/mm/ptdump.c index a50e92ea1878..a1937dfff31c 100644 --- a/arch/arm64/mm/ptdump.c +++ b/arch/arm64/mm/ptdump.c @@ -51,10 +51,8 @@ static struct addr_marker address_markers[] = { { FIXADDR_TOP, "Fixmap end" }, { PCI_IO_START, "PCI I/O start" }, { PCI_IO_END, "PCI I/O end" }, -#ifdef CONFIG_SPARSEMEM_VMEMMAP { VMEMMAP_START, "vmemmap start" }, { VMEMMAP_START + VMEMMAP_SIZE, "vmemmap end" }, -#endif { -1, NULL }, }; |